diff --git "a/trainer_state.json" "b/trainer_state.json" new file mode 100644--- /dev/null +++ "b/trainer_state.json" @@ -0,0 +1,388585 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 19.99901565304665, + "global_step": 64760, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 5.899705014749263e-08, + "loss": 1.0263, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 1.1799410029498526e-07, + "loss": 1.078, + "step": 2 + }, + { + "epoch": 0.0, + "learning_rate": 1.7699115044247788e-07, + "loss": 1.0339, + "step": 3 + }, + { + "epoch": 0.0, + "learning_rate": 2.359882005899705e-07, + "loss": 1.0974, + "step": 4 + }, + { + "epoch": 0.0, + "learning_rate": 2.9498525073746315e-07, + "loss": 1.0659, + "step": 5 + }, + { + "epoch": 0.01, + "learning_rate": 3.5398230088495575e-07, + "loss": 1.0759, + "step": 6 + }, + { + "epoch": 0.01, + "learning_rate": 4.129793510324484e-07, + "loss": 1.1204, + "step": 7 + }, + { + "epoch": 0.01, + "learning_rate": 4.71976401179941e-07, + "loss": 1.0621, + "step": 8 + }, + { + "epoch": 0.01, + "learning_rate": 5.309734513274336e-07, + "loss": 1.077, + "step": 9 + }, + { + "epoch": 0.01, + "learning_rate": 5.899705014749263e-07, + "loss": 1.1068, + "step": 10 + }, + { + "epoch": 0.01, + "learning_rate": 6.48967551622419e-07, + "loss": 1.1423, + "step": 11 + }, + { + "epoch": 0.01, + "learning_rate": 7.079646017699115e-07, + "loss": 1.0427, + "step": 12 + }, + { + "epoch": 0.01, + "learning_rate": 7.669616519174042e-07, + "loss": 0.9915, + "step": 13 + }, + { + "epoch": 0.01, + "learning_rate": 8.259587020648968e-07, + "loss": 1.0646, + "step": 14 + }, + { + "epoch": 0.01, + "learning_rate": 8.849557522123895e-07, + "loss": 1.0652, + "step": 15 + }, + { + "epoch": 0.01, + "learning_rate": 9.43952802359882e-07, + "loss": 1.025, + "step": 16 + }, + { + "epoch": 0.02, + "learning_rate": 1.0029498525073746e-06, + "loss": 1.01, + "step": 17 + }, + { + "epoch": 0.02, + "learning_rate": 1.0619469026548673e-06, + "loss": 1.0116, + "step": 18 + }, + { + "epoch": 0.02, + "learning_rate": 1.12094395280236e-06, + "loss": 0.9366, + "step": 19 + }, + { + "epoch": 0.02, + "learning_rate": 1.1799410029498526e-06, + "loss": 0.9468, + "step": 20 + }, + { + "epoch": 0.02, + "learning_rate": 1.2389380530973452e-06, + "loss": 0.9654, + "step": 21 + }, + { + "epoch": 0.02, + "learning_rate": 1.297935103244838e-06, + "loss": 0.896, + "step": 22 + }, + { + "epoch": 0.02, + "learning_rate": 1.3569321533923306e-06, + "loss": 0.9244, + "step": 23 + }, + { + "epoch": 0.02, + "learning_rate": 1.415929203539823e-06, + "loss": 0.9261, + "step": 24 + }, + { + "epoch": 0.02, + "learning_rate": 1.4749262536873157e-06, + "loss": 0.8575, + "step": 25 + }, + { + "epoch": 0.02, + "learning_rate": 1.5339233038348083e-06, + "loss": 0.8038, + "step": 26 + }, + { + "epoch": 0.02, + "learning_rate": 1.592920353982301e-06, + "loss": 0.8699, + "step": 27 + }, + { + "epoch": 0.02, + "learning_rate": 1.6519174041297937e-06, + "loss": 0.8717, + "step": 28 + }, + { + "epoch": 0.03, + "learning_rate": 1.7109144542772863e-06, + "loss": 0.8862, + "step": 29 + }, + { + "epoch": 0.03, + "learning_rate": 1.769911504424779e-06, + "loss": 0.8268, + "step": 30 + }, + { + "epoch": 0.03, + "learning_rate": 1.8289085545722714e-06, + "loss": 0.8223, + "step": 31 + }, + { + "epoch": 0.03, + "learning_rate": 1.887905604719764e-06, + "loss": 0.789, + "step": 32 + }, + { + "epoch": 0.03, + "learning_rate": 1.9469026548672567e-06, + "loss": 0.8296, + "step": 33 + }, + { + "epoch": 0.03, + "learning_rate": 2.005899705014749e-06, + "loss": 0.8111, + "step": 34 + }, + { + "epoch": 0.03, + "learning_rate": 2.064896755162242e-06, + "loss": 0.8197, + "step": 35 + }, + { + "epoch": 0.03, + "learning_rate": 2.1238938053097345e-06, + "loss": 0.8051, + "step": 36 + }, + { + "epoch": 0.03, + "learning_rate": 2.1828908554572274e-06, + "loss": 0.7771, + "step": 37 + }, + { + "epoch": 0.03, + "learning_rate": 2.24188790560472e-06, + "loss": 0.7935, + "step": 38 + }, + { + "epoch": 0.03, + "learning_rate": 2.3008849557522127e-06, + "loss": 0.7944, + "step": 39 + }, + { + "epoch": 0.04, + "learning_rate": 2.359882005899705e-06, + "loss": 0.7549, + "step": 40 + }, + { + "epoch": 0.04, + "learning_rate": 2.4188790560471976e-06, + "loss": 0.7661, + "step": 41 + }, + { + "epoch": 0.04, + "learning_rate": 2.4778761061946905e-06, + "loss": 0.7352, + "step": 42 + }, + { + "epoch": 0.04, + "learning_rate": 2.5368731563421834e-06, + "loss": 0.7503, + "step": 43 + }, + { + "epoch": 0.04, + "learning_rate": 2.595870206489676e-06, + "loss": 0.7432, + "step": 44 + }, + { + "epoch": 0.04, + "learning_rate": 2.6548672566371687e-06, + "loss": 0.7574, + "step": 45 + }, + { + "epoch": 0.04, + "learning_rate": 2.713864306784661e-06, + "loss": 0.757, + "step": 46 + }, + { + "epoch": 0.04, + "learning_rate": 2.772861356932154e-06, + "loss": 0.7458, + "step": 47 + }, + { + "epoch": 0.04, + "learning_rate": 2.831858407079646e-06, + "loss": 0.7574, + "step": 48 + }, + { + "epoch": 0.04, + "learning_rate": 2.8908554572271393e-06, + "loss": 0.7198, + "step": 49 + }, + { + "epoch": 0.04, + "learning_rate": 2.9498525073746313e-06, + "loss": 0.7239, + "step": 50 + }, + { + "epoch": 0.05, + "learning_rate": 3.0088495575221242e-06, + "loss": 0.7408, + "step": 51 + }, + { + "epoch": 0.05, + "learning_rate": 3.0678466076696167e-06, + "loss": 0.7235, + "step": 52 + }, + { + "epoch": 0.05, + "learning_rate": 3.1268436578171095e-06, + "loss": 0.7613, + "step": 53 + }, + { + "epoch": 0.05, + "learning_rate": 3.185840707964602e-06, + "loss": 0.6907, + "step": 54 + }, + { + "epoch": 0.05, + "learning_rate": 3.244837758112095e-06, + "loss": 0.7044, + "step": 55 + }, + { + "epoch": 0.05, + "learning_rate": 3.3038348082595873e-06, + "loss": 0.7608, + "step": 56 + }, + { + "epoch": 0.05, + "learning_rate": 3.36283185840708e-06, + "loss": 0.7272, + "step": 57 + }, + { + "epoch": 0.05, + "learning_rate": 3.4218289085545726e-06, + "loss": 0.7162, + "step": 58 + }, + { + "epoch": 0.05, + "learning_rate": 3.4808259587020655e-06, + "loss": 0.723, + "step": 59 + }, + { + "epoch": 0.05, + "learning_rate": 3.539823008849558e-06, + "loss": 0.7068, + "step": 60 + }, + { + "epoch": 0.05, + "learning_rate": 3.598820058997051e-06, + "loss": 0.717, + "step": 61 + }, + { + "epoch": 0.05, + "learning_rate": 3.657817109144543e-06, + "loss": 0.7018, + "step": 62 + }, + { + "epoch": 0.06, + "learning_rate": 3.7168141592920357e-06, + "loss": 0.6991, + "step": 63 + }, + { + "epoch": 0.06, + "learning_rate": 3.775811209439528e-06, + "loss": 0.7278, + "step": 64 + }, + { + "epoch": 0.06, + "learning_rate": 3.8348082595870215e-06, + "loss": 0.7189, + "step": 65 + }, + { + "epoch": 0.06, + "learning_rate": 3.8938053097345135e-06, + "loss": 0.7081, + "step": 66 + }, + { + "epoch": 0.06, + "learning_rate": 3.952802359882006e-06, + "loss": 0.7036, + "step": 67 + }, + { + "epoch": 0.06, + "learning_rate": 4.011799410029498e-06, + "loss": 0.7036, + "step": 68 + }, + { + "epoch": 0.06, + "learning_rate": 4.070796460176992e-06, + "loss": 0.6879, + "step": 69 + }, + { + "epoch": 0.06, + "learning_rate": 4.129793510324484e-06, + "loss": 0.687, + "step": 70 + }, + { + "epoch": 0.06, + "learning_rate": 4.188790560471977e-06, + "loss": 0.7076, + "step": 71 + }, + { + "epoch": 0.06, + "learning_rate": 4.247787610619469e-06, + "loss": 0.7093, + "step": 72 + }, + { + "epoch": 0.06, + "learning_rate": 4.306784660766962e-06, + "loss": 0.6933, + "step": 73 + }, + { + "epoch": 0.07, + "learning_rate": 4.365781710914455e-06, + "loss": 0.6658, + "step": 74 + }, + { + "epoch": 0.07, + "learning_rate": 4.424778761061948e-06, + "loss": 0.7036, + "step": 75 + }, + { + "epoch": 0.07, + "learning_rate": 4.48377581120944e-06, + "loss": 0.6663, + "step": 76 + }, + { + "epoch": 0.07, + "learning_rate": 4.5427728613569326e-06, + "loss": 0.6814, + "step": 77 + }, + { + "epoch": 0.07, + "learning_rate": 4.6017699115044254e-06, + "loss": 0.7188, + "step": 78 + }, + { + "epoch": 0.07, + "learning_rate": 4.660766961651918e-06, + "loss": 0.7005, + "step": 79 + }, + { + "epoch": 0.07, + "learning_rate": 4.71976401179941e-06, + "loss": 0.6715, + "step": 80 + }, + { + "epoch": 0.07, + "learning_rate": 4.778761061946903e-06, + "loss": 0.6873, + "step": 81 + }, + { + "epoch": 0.07, + "learning_rate": 4.837758112094395e-06, + "loss": 0.6995, + "step": 82 + }, + { + "epoch": 0.07, + "learning_rate": 4.896755162241888e-06, + "loss": 0.6867, + "step": 83 + }, + { + "epoch": 0.07, + "learning_rate": 4.955752212389381e-06, + "loss": 0.675, + "step": 84 + }, + { + "epoch": 0.08, + "learning_rate": 5.014749262536873e-06, + "loss": 0.681, + "step": 85 + }, + { + "epoch": 0.08, + "learning_rate": 5.073746312684367e-06, + "loss": 0.6974, + "step": 86 + }, + { + "epoch": 0.08, + "learning_rate": 5.132743362831859e-06, + "loss": 0.6571, + "step": 87 + }, + { + "epoch": 0.08, + "learning_rate": 5.191740412979352e-06, + "loss": 0.6999, + "step": 88 + }, + { + "epoch": 0.08, + "learning_rate": 5.250737463126844e-06, + "loss": 0.6657, + "step": 89 + }, + { + "epoch": 0.08, + "learning_rate": 5.309734513274337e-06, + "loss": 0.679, + "step": 90 + }, + { + "epoch": 0.08, + "learning_rate": 5.368731563421829e-06, + "loss": 0.7036, + "step": 91 + }, + { + "epoch": 0.08, + "learning_rate": 5.427728613569322e-06, + "loss": 0.7085, + "step": 92 + }, + { + "epoch": 0.08, + "learning_rate": 5.486725663716814e-06, + "loss": 0.6972, + "step": 93 + }, + { + "epoch": 0.08, + "learning_rate": 5.545722713864308e-06, + "loss": 0.6544, + "step": 94 + }, + { + "epoch": 0.08, + "learning_rate": 5.6047197640118e-06, + "loss": 0.6758, + "step": 95 + }, + { + "epoch": 0.08, + "learning_rate": 5.663716814159292e-06, + "loss": 0.6637, + "step": 96 + }, + { + "epoch": 0.09, + "learning_rate": 5.722713864306785e-06, + "loss": 0.6935, + "step": 97 + }, + { + "epoch": 0.09, + "learning_rate": 5.781710914454279e-06, + "loss": 0.6657, + "step": 98 + }, + { + "epoch": 0.09, + "learning_rate": 5.840707964601771e-06, + "loss": 0.6742, + "step": 99 + }, + { + "epoch": 0.09, + "learning_rate": 5.899705014749263e-06, + "loss": 0.6721, + "step": 100 + }, + { + "epoch": 0.09, + "learning_rate": 5.9587020648967556e-06, + "loss": 0.6567, + "step": 101 + }, + { + "epoch": 0.09, + "learning_rate": 6.0176991150442484e-06, + "loss": 0.6492, + "step": 102 + }, + { + "epoch": 0.09, + "learning_rate": 6.076696165191741e-06, + "loss": 0.6628, + "step": 103 + }, + { + "epoch": 0.09, + "learning_rate": 6.135693215339233e-06, + "loss": 0.6895, + "step": 104 + }, + { + "epoch": 0.09, + "learning_rate": 6.194690265486726e-06, + "loss": 0.6557, + "step": 105 + }, + { + "epoch": 0.09, + "learning_rate": 6.253687315634219e-06, + "loss": 0.6988, + "step": 106 + }, + { + "epoch": 0.09, + "learning_rate": 6.312684365781712e-06, + "loss": 0.7034, + "step": 107 + }, + { + "epoch": 0.1, + "learning_rate": 6.371681415929204e-06, + "loss": 0.6892, + "step": 108 + }, + { + "epoch": 0.1, + "learning_rate": 6.430678466076696e-06, + "loss": 0.6749, + "step": 109 + }, + { + "epoch": 0.1, + "learning_rate": 6.48967551622419e-06, + "loss": 0.6563, + "step": 110 + }, + { + "epoch": 0.1, + "learning_rate": 6.548672566371682e-06, + "loss": 0.6822, + "step": 111 + }, + { + "epoch": 0.1, + "learning_rate": 6.607669616519175e-06, + "loss": 0.6636, + "step": 112 + }, + { + "epoch": 0.1, + "learning_rate": 6.666666666666667e-06, + "loss": 0.6546, + "step": 113 + }, + { + "epoch": 0.1, + "learning_rate": 6.72566371681416e-06, + "loss": 0.6485, + "step": 114 + }, + { + "epoch": 0.1, + "learning_rate": 6.784660766961652e-06, + "loss": 0.6654, + "step": 115 + }, + { + "epoch": 0.1, + "learning_rate": 6.843657817109145e-06, + "loss": 0.6385, + "step": 116 + }, + { + "epoch": 0.1, + "learning_rate": 6.902654867256637e-06, + "loss": 0.6803, + "step": 117 + }, + { + "epoch": 0.1, + "learning_rate": 6.961651917404131e-06, + "loss": 0.6848, + "step": 118 + }, + { + "epoch": 0.11, + "learning_rate": 7.020648967551623e-06, + "loss": 0.6559, + "step": 119 + }, + { + "epoch": 0.11, + "learning_rate": 7.079646017699116e-06, + "loss": 0.6527, + "step": 120 + }, + { + "epoch": 0.11, + "learning_rate": 7.138643067846608e-06, + "loss": 0.6659, + "step": 121 + }, + { + "epoch": 0.11, + "learning_rate": 7.197640117994102e-06, + "loss": 0.6471, + "step": 122 + }, + { + "epoch": 0.11, + "learning_rate": 7.256637168141594e-06, + "loss": 0.6467, + "step": 123 + }, + { + "epoch": 0.11, + "learning_rate": 7.315634218289086e-06, + "loss": 0.6569, + "step": 124 + }, + { + "epoch": 0.11, + "learning_rate": 7.374631268436579e-06, + "loss": 0.6474, + "step": 125 + }, + { + "epoch": 0.11, + "learning_rate": 7.4336283185840714e-06, + "loss": 0.6666, + "step": 126 + }, + { + "epoch": 0.11, + "learning_rate": 7.492625368731564e-06, + "loss": 0.6263, + "step": 127 + }, + { + "epoch": 0.11, + "learning_rate": 7.551622418879056e-06, + "loss": 0.6836, + "step": 128 + }, + { + "epoch": 0.11, + "learning_rate": 7.610619469026549e-06, + "loss": 0.651, + "step": 129 + }, + { + "epoch": 0.11, + "learning_rate": 7.669616519174043e-06, + "loss": 0.6831, + "step": 130 + }, + { + "epoch": 0.12, + "learning_rate": 7.728613569321535e-06, + "loss": 0.6573, + "step": 131 + }, + { + "epoch": 0.12, + "learning_rate": 7.787610619469027e-06, + "loss": 0.6681, + "step": 132 + }, + { + "epoch": 0.12, + "learning_rate": 7.846607669616519e-06, + "loss": 0.6827, + "step": 133 + }, + { + "epoch": 0.12, + "learning_rate": 7.905604719764013e-06, + "loss": 0.6837, + "step": 134 + }, + { + "epoch": 0.12, + "learning_rate": 7.964601769911505e-06, + "loss": 0.6739, + "step": 135 + }, + { + "epoch": 0.12, + "learning_rate": 8.023598820058997e-06, + "loss": 0.6793, + "step": 136 + }, + { + "epoch": 0.12, + "learning_rate": 8.08259587020649e-06, + "loss": 0.6722, + "step": 137 + }, + { + "epoch": 0.12, + "learning_rate": 8.141592920353984e-06, + "loss": 0.6418, + "step": 138 + }, + { + "epoch": 0.12, + "learning_rate": 8.200589970501476e-06, + "loss": 0.6439, + "step": 139 + }, + { + "epoch": 0.12, + "learning_rate": 8.259587020648968e-06, + "loss": 0.6368, + "step": 140 + }, + { + "epoch": 0.12, + "learning_rate": 8.31858407079646e-06, + "loss": 0.6285, + "step": 141 + }, + { + "epoch": 0.13, + "learning_rate": 8.377581120943954e-06, + "loss": 0.6506, + "step": 142 + }, + { + "epoch": 0.13, + "learning_rate": 8.436578171091446e-06, + "loss": 0.6471, + "step": 143 + }, + { + "epoch": 0.13, + "learning_rate": 8.495575221238938e-06, + "loss": 0.6428, + "step": 144 + }, + { + "epoch": 0.13, + "learning_rate": 8.554572271386432e-06, + "loss": 0.6344, + "step": 145 + }, + { + "epoch": 0.13, + "learning_rate": 8.613569321533924e-06, + "loss": 0.6501, + "step": 146 + }, + { + "epoch": 0.13, + "learning_rate": 8.672566371681418e-06, + "loss": 0.6435, + "step": 147 + }, + { + "epoch": 0.13, + "learning_rate": 8.73156342182891e-06, + "loss": 0.6683, + "step": 148 + }, + { + "epoch": 0.13, + "learning_rate": 8.790560471976402e-06, + "loss": 0.6464, + "step": 149 + }, + { + "epoch": 0.13, + "learning_rate": 8.849557522123895e-06, + "loss": 0.6539, + "step": 150 + }, + { + "epoch": 0.13, + "learning_rate": 8.908554572271387e-06, + "loss": 0.657, + "step": 151 + }, + { + "epoch": 0.13, + "learning_rate": 8.96755162241888e-06, + "loss": 0.6396, + "step": 152 + }, + { + "epoch": 0.14, + "learning_rate": 9.026548672566371e-06, + "loss": 0.6435, + "step": 153 + }, + { + "epoch": 0.14, + "learning_rate": 9.085545722713865e-06, + "loss": 0.6383, + "step": 154 + }, + { + "epoch": 0.14, + "learning_rate": 9.144542772861357e-06, + "loss": 0.6629, + "step": 155 + }, + { + "epoch": 0.14, + "learning_rate": 9.203539823008851e-06, + "loss": 0.6541, + "step": 156 + }, + { + "epoch": 0.14, + "learning_rate": 9.262536873156343e-06, + "loss": 0.6314, + "step": 157 + }, + { + "epoch": 0.14, + "learning_rate": 9.321533923303837e-06, + "loss": 0.6627, + "step": 158 + }, + { + "epoch": 0.14, + "learning_rate": 9.380530973451329e-06, + "loss": 0.6332, + "step": 159 + }, + { + "epoch": 0.14, + "learning_rate": 9.43952802359882e-06, + "loss": 0.6275, + "step": 160 + }, + { + "epoch": 0.14, + "learning_rate": 9.498525073746313e-06, + "loss": 0.6418, + "step": 161 + }, + { + "epoch": 0.14, + "learning_rate": 9.557522123893806e-06, + "loss": 0.6177, + "step": 162 + }, + { + "epoch": 0.14, + "learning_rate": 9.616519174041298e-06, + "loss": 0.6457, + "step": 163 + }, + { + "epoch": 0.15, + "learning_rate": 9.67551622418879e-06, + "loss": 0.6093, + "step": 164 + }, + { + "epoch": 0.15, + "learning_rate": 9.734513274336284e-06, + "loss": 0.6309, + "step": 165 + }, + { + "epoch": 0.15, + "learning_rate": 9.793510324483776e-06, + "loss": 0.6608, + "step": 166 + }, + { + "epoch": 0.15, + "learning_rate": 9.85250737463127e-06, + "loss": 0.6306, + "step": 167 + }, + { + "epoch": 0.15, + "learning_rate": 9.911504424778762e-06, + "loss": 0.6553, + "step": 168 + }, + { + "epoch": 0.15, + "learning_rate": 9.970501474926254e-06, + "loss": 0.6266, + "step": 169 + }, + { + "epoch": 0.15, + "learning_rate": 1.0029498525073746e-05, + "loss": 0.6388, + "step": 170 + }, + { + "epoch": 0.15, + "learning_rate": 1.008849557522124e-05, + "loss": 0.6539, + "step": 171 + }, + { + "epoch": 0.15, + "learning_rate": 1.0147492625368733e-05, + "loss": 0.621, + "step": 172 + }, + { + "epoch": 0.15, + "learning_rate": 1.0206489675516225e-05, + "loss": 0.6438, + "step": 173 + }, + { + "epoch": 0.15, + "learning_rate": 1.0265486725663717e-05, + "loss": 0.5964, + "step": 174 + }, + { + "epoch": 0.15, + "learning_rate": 1.032448377581121e-05, + "loss": 0.6286, + "step": 175 + }, + { + "epoch": 0.16, + "learning_rate": 1.0383480825958703e-05, + "loss": 0.6261, + "step": 176 + }, + { + "epoch": 0.16, + "learning_rate": 1.0442477876106197e-05, + "loss": 0.6599, + "step": 177 + }, + { + "epoch": 0.16, + "learning_rate": 1.0501474926253687e-05, + "loss": 0.6409, + "step": 178 + }, + { + "epoch": 0.16, + "learning_rate": 1.0560471976401181e-05, + "loss": 0.6325, + "step": 179 + }, + { + "epoch": 0.16, + "learning_rate": 1.0619469026548675e-05, + "loss": 0.6612, + "step": 180 + }, + { + "epoch": 0.16, + "learning_rate": 1.0678466076696165e-05, + "loss": 0.6402, + "step": 181 + }, + { + "epoch": 0.16, + "learning_rate": 1.0737463126843659e-05, + "loss": 0.6472, + "step": 182 + }, + { + "epoch": 0.16, + "learning_rate": 1.079646017699115e-05, + "loss": 0.6254, + "step": 183 + }, + { + "epoch": 0.16, + "learning_rate": 1.0855457227138645e-05, + "loss": 0.6236, + "step": 184 + }, + { + "epoch": 0.16, + "learning_rate": 1.0914454277286137e-05, + "loss": 0.6472, + "step": 185 + }, + { + "epoch": 0.16, + "learning_rate": 1.0973451327433629e-05, + "loss": 0.664, + "step": 186 + }, + { + "epoch": 0.17, + "learning_rate": 1.1032448377581122e-05, + "loss": 0.6303, + "step": 187 + }, + { + "epoch": 0.17, + "learning_rate": 1.1091445427728616e-05, + "loss": 0.6331, + "step": 188 + }, + { + "epoch": 0.17, + "learning_rate": 1.1150442477876106e-05, + "loss": 0.6047, + "step": 189 + }, + { + "epoch": 0.17, + "learning_rate": 1.12094395280236e-05, + "loss": 0.6462, + "step": 190 + }, + { + "epoch": 0.17, + "learning_rate": 1.1268436578171092e-05, + "loss": 0.6399, + "step": 191 + }, + { + "epoch": 0.17, + "learning_rate": 1.1327433628318584e-05, + "loss": 0.5993, + "step": 192 + }, + { + "epoch": 0.17, + "learning_rate": 1.1386430678466078e-05, + "loss": 0.619, + "step": 193 + }, + { + "epoch": 0.17, + "learning_rate": 1.144542772861357e-05, + "loss": 0.6339, + "step": 194 + }, + { + "epoch": 0.17, + "learning_rate": 1.1504424778761064e-05, + "loss": 0.6303, + "step": 195 + }, + { + "epoch": 0.17, + "learning_rate": 1.1563421828908557e-05, + "loss": 0.6205, + "step": 196 + }, + { + "epoch": 0.17, + "learning_rate": 1.1622418879056048e-05, + "loss": 0.6102, + "step": 197 + }, + { + "epoch": 0.18, + "learning_rate": 1.1681415929203541e-05, + "loss": 0.6387, + "step": 198 + }, + { + "epoch": 0.18, + "learning_rate": 1.1740412979351032e-05, + "loss": 0.6419, + "step": 199 + }, + { + "epoch": 0.18, + "learning_rate": 1.1799410029498525e-05, + "loss": 0.6414, + "step": 200 + }, + { + "epoch": 0.18, + "learning_rate": 1.1858407079646019e-05, + "loss": 0.6158, + "step": 201 + }, + { + "epoch": 0.18, + "learning_rate": 1.1917404129793511e-05, + "loss": 0.6345, + "step": 202 + }, + { + "epoch": 0.18, + "learning_rate": 1.1976401179941005e-05, + "loss": 0.6055, + "step": 203 + }, + { + "epoch": 0.18, + "learning_rate": 1.2035398230088497e-05, + "loss": 0.6462, + "step": 204 + }, + { + "epoch": 0.18, + "learning_rate": 1.2094395280235989e-05, + "loss": 0.6076, + "step": 205 + }, + { + "epoch": 0.18, + "learning_rate": 1.2153392330383483e-05, + "loss": 0.6308, + "step": 206 + }, + { + "epoch": 0.18, + "learning_rate": 1.2212389380530973e-05, + "loss": 0.6167, + "step": 207 + }, + { + "epoch": 0.18, + "learning_rate": 1.2271386430678467e-05, + "loss": 0.5947, + "step": 208 + }, + { + "epoch": 0.18, + "learning_rate": 1.233038348082596e-05, + "loss": 0.6192, + "step": 209 + }, + { + "epoch": 0.19, + "learning_rate": 1.2389380530973452e-05, + "loss": 0.6368, + "step": 210 + }, + { + "epoch": 0.19, + "learning_rate": 1.2448377581120944e-05, + "loss": 0.6378, + "step": 211 + }, + { + "epoch": 0.19, + "learning_rate": 1.2507374631268438e-05, + "loss": 0.643, + "step": 212 + }, + { + "epoch": 0.19, + "learning_rate": 1.256637168141593e-05, + "loss": 0.645, + "step": 213 + }, + { + "epoch": 0.19, + "learning_rate": 1.2625368731563424e-05, + "loss": 0.6202, + "step": 214 + }, + { + "epoch": 0.19, + "learning_rate": 1.2684365781710914e-05, + "loss": 0.6253, + "step": 215 + }, + { + "epoch": 0.19, + "learning_rate": 1.2743362831858408e-05, + "loss": 0.6127, + "step": 216 + }, + { + "epoch": 0.19, + "learning_rate": 1.2802359882005902e-05, + "loss": 0.6071, + "step": 217 + }, + { + "epoch": 0.19, + "learning_rate": 1.2861356932153392e-05, + "loss": 0.6326, + "step": 218 + }, + { + "epoch": 0.19, + "learning_rate": 1.2920353982300886e-05, + "loss": 0.6143, + "step": 219 + }, + { + "epoch": 0.19, + "learning_rate": 1.297935103244838e-05, + "loss": 0.6226, + "step": 220 + }, + { + "epoch": 0.2, + "learning_rate": 1.3038348082595871e-05, + "loss": 0.6388, + "step": 221 + }, + { + "epoch": 0.2, + "learning_rate": 1.3097345132743363e-05, + "loss": 0.6366, + "step": 222 + }, + { + "epoch": 0.2, + "learning_rate": 1.3156342182890856e-05, + "loss": 0.6456, + "step": 223 + }, + { + "epoch": 0.2, + "learning_rate": 1.321533923303835e-05, + "loss": 0.6474, + "step": 224 + }, + { + "epoch": 0.2, + "learning_rate": 1.3274336283185843e-05, + "loss": 0.6142, + "step": 225 + }, + { + "epoch": 0.2, + "learning_rate": 1.3333333333333333e-05, + "loss": 0.6333, + "step": 226 + }, + { + "epoch": 0.2, + "learning_rate": 1.3392330383480827e-05, + "loss": 0.623, + "step": 227 + }, + { + "epoch": 0.2, + "learning_rate": 1.345132743362832e-05, + "loss": 0.6407, + "step": 228 + }, + { + "epoch": 0.2, + "learning_rate": 1.3510324483775811e-05, + "loss": 0.6323, + "step": 229 + }, + { + "epoch": 0.2, + "learning_rate": 1.3569321533923305e-05, + "loss": 0.6274, + "step": 230 + }, + { + "epoch": 0.2, + "learning_rate": 1.3628318584070797e-05, + "loss": 0.6397, + "step": 231 + }, + { + "epoch": 0.21, + "learning_rate": 1.368731563421829e-05, + "loss": 0.6273, + "step": 232 + }, + { + "epoch": 0.21, + "learning_rate": 1.3746312684365784e-05, + "loss": 0.6453, + "step": 233 + }, + { + "epoch": 0.21, + "learning_rate": 1.3805309734513275e-05, + "loss": 0.6068, + "step": 234 + }, + { + "epoch": 0.21, + "learning_rate": 1.3864306784660768e-05, + "loss": 0.6381, + "step": 235 + }, + { + "epoch": 0.21, + "learning_rate": 1.3923303834808262e-05, + "loss": 0.6328, + "step": 236 + }, + { + "epoch": 0.21, + "learning_rate": 1.3982300884955752e-05, + "loss": 0.6393, + "step": 237 + }, + { + "epoch": 0.21, + "learning_rate": 1.4041297935103246e-05, + "loss": 0.6262, + "step": 238 + }, + { + "epoch": 0.21, + "learning_rate": 1.4100294985250738e-05, + "loss": 0.6473, + "step": 239 + }, + { + "epoch": 0.21, + "learning_rate": 1.4159292035398232e-05, + "loss": 0.6186, + "step": 240 + }, + { + "epoch": 0.21, + "learning_rate": 1.4218289085545724e-05, + "loss": 0.6314, + "step": 241 + }, + { + "epoch": 0.21, + "learning_rate": 1.4277286135693216e-05, + "loss": 0.6356, + "step": 242 + }, + { + "epoch": 0.21, + "learning_rate": 1.433628318584071e-05, + "loss": 0.6372, + "step": 243 + }, + { + "epoch": 0.22, + "learning_rate": 1.4395280235988203e-05, + "loss": 0.6155, + "step": 244 + }, + { + "epoch": 0.22, + "learning_rate": 1.4454277286135694e-05, + "loss": 0.6189, + "step": 245 + }, + { + "epoch": 0.22, + "learning_rate": 1.4513274336283187e-05, + "loss": 0.607, + "step": 246 + }, + { + "epoch": 0.22, + "learning_rate": 1.457227138643068e-05, + "loss": 0.6249, + "step": 247 + }, + { + "epoch": 0.22, + "learning_rate": 1.4631268436578171e-05, + "loss": 0.6108, + "step": 248 + }, + { + "epoch": 0.22, + "learning_rate": 1.4690265486725665e-05, + "loss": 0.625, + "step": 249 + }, + { + "epoch": 0.22, + "learning_rate": 1.4749262536873157e-05, + "loss": 0.6546, + "step": 250 + }, + { + "epoch": 0.22, + "learning_rate": 1.4808259587020651e-05, + "loss": 0.6237, + "step": 251 + }, + { + "epoch": 0.22, + "learning_rate": 1.4867256637168143e-05, + "loss": 0.6156, + "step": 252 + }, + { + "epoch": 0.22, + "learning_rate": 1.4926253687315635e-05, + "loss": 0.6318, + "step": 253 + }, + { + "epoch": 0.22, + "learning_rate": 1.4985250737463129e-05, + "loss": 0.6093, + "step": 254 + }, + { + "epoch": 0.23, + "learning_rate": 1.5044247787610619e-05, + "loss": 0.6535, + "step": 255 + }, + { + "epoch": 0.23, + "learning_rate": 1.5103244837758113e-05, + "loss": 0.651, + "step": 256 + }, + { + "epoch": 0.23, + "learning_rate": 1.5162241887905606e-05, + "loss": 0.6109, + "step": 257 + }, + { + "epoch": 0.23, + "learning_rate": 1.5221238938053098e-05, + "loss": 0.6114, + "step": 258 + }, + { + "epoch": 0.23, + "learning_rate": 1.5280235988200592e-05, + "loss": 0.6165, + "step": 259 + }, + { + "epoch": 0.23, + "learning_rate": 1.5339233038348086e-05, + "loss": 0.6077, + "step": 260 + }, + { + "epoch": 0.23, + "learning_rate": 1.5398230088495576e-05, + "loss": 0.6541, + "step": 261 + }, + { + "epoch": 0.23, + "learning_rate": 1.545722713864307e-05, + "loss": 0.614, + "step": 262 + }, + { + "epoch": 0.23, + "learning_rate": 1.551622418879056e-05, + "loss": 0.6251, + "step": 263 + }, + { + "epoch": 0.23, + "learning_rate": 1.5575221238938054e-05, + "loss": 0.6157, + "step": 264 + }, + { + "epoch": 0.23, + "learning_rate": 1.5634218289085548e-05, + "loss": 0.6038, + "step": 265 + }, + { + "epoch": 0.24, + "learning_rate": 1.5693215339233038e-05, + "loss": 0.6519, + "step": 266 + }, + { + "epoch": 0.24, + "learning_rate": 1.5752212389380532e-05, + "loss": 0.6545, + "step": 267 + }, + { + "epoch": 0.24, + "learning_rate": 1.5811209439528025e-05, + "loss": 0.6356, + "step": 268 + }, + { + "epoch": 0.24, + "learning_rate": 1.5870206489675516e-05, + "loss": 0.5948, + "step": 269 + }, + { + "epoch": 0.24, + "learning_rate": 1.592920353982301e-05, + "loss": 0.615, + "step": 270 + }, + { + "epoch": 0.24, + "learning_rate": 1.5988200589970503e-05, + "loss": 0.6186, + "step": 271 + }, + { + "epoch": 0.24, + "learning_rate": 1.6047197640117994e-05, + "loss": 0.6442, + "step": 272 + }, + { + "epoch": 0.24, + "learning_rate": 1.6106194690265487e-05, + "loss": 0.634, + "step": 273 + }, + { + "epoch": 0.24, + "learning_rate": 1.616519174041298e-05, + "loss": 0.6221, + "step": 274 + }, + { + "epoch": 0.24, + "learning_rate": 1.6224188790560475e-05, + "loss": 0.6094, + "step": 275 + }, + { + "epoch": 0.24, + "learning_rate": 1.628318584070797e-05, + "loss": 0.6264, + "step": 276 + }, + { + "epoch": 0.25, + "learning_rate": 1.634218289085546e-05, + "loss": 0.6104, + "step": 277 + }, + { + "epoch": 0.25, + "learning_rate": 1.6401179941002953e-05, + "loss": 0.6231, + "step": 278 + }, + { + "epoch": 0.25, + "learning_rate": 1.6460176991150443e-05, + "loss": 0.6395, + "step": 279 + }, + { + "epoch": 0.25, + "learning_rate": 1.6519174041297937e-05, + "loss": 0.6223, + "step": 280 + }, + { + "epoch": 0.25, + "learning_rate": 1.657817109144543e-05, + "loss": 0.6142, + "step": 281 + }, + { + "epoch": 0.25, + "learning_rate": 1.663716814159292e-05, + "loss": 0.6383, + "step": 282 + }, + { + "epoch": 0.25, + "learning_rate": 1.6696165191740414e-05, + "loss": 0.6125, + "step": 283 + }, + { + "epoch": 0.25, + "learning_rate": 1.6755162241887908e-05, + "loss": 0.6038, + "step": 284 + }, + { + "epoch": 0.25, + "learning_rate": 1.68141592920354e-05, + "loss": 0.6067, + "step": 285 + }, + { + "epoch": 0.25, + "learning_rate": 1.6873156342182892e-05, + "loss": 0.6259, + "step": 286 + }, + { + "epoch": 0.25, + "learning_rate": 1.6932153392330382e-05, + "loss": 0.6254, + "step": 287 + }, + { + "epoch": 0.25, + "learning_rate": 1.6991150442477876e-05, + "loss": 0.6093, + "step": 288 + }, + { + "epoch": 0.26, + "learning_rate": 1.705014749262537e-05, + "loss": 0.601, + "step": 289 + }, + { + "epoch": 0.26, + "learning_rate": 1.7109144542772864e-05, + "loss": 0.5954, + "step": 290 + }, + { + "epoch": 0.26, + "learning_rate": 1.7168141592920354e-05, + "loss": 0.6501, + "step": 291 + }, + { + "epoch": 0.26, + "learning_rate": 1.7227138643067848e-05, + "loss": 0.5941, + "step": 292 + }, + { + "epoch": 0.26, + "learning_rate": 1.728613569321534e-05, + "loss": 0.6135, + "step": 293 + }, + { + "epoch": 0.26, + "learning_rate": 1.7345132743362835e-05, + "loss": 0.6215, + "step": 294 + }, + { + "epoch": 0.26, + "learning_rate": 1.7404129793510325e-05, + "loss": 0.6164, + "step": 295 + }, + { + "epoch": 0.26, + "learning_rate": 1.746312684365782e-05, + "loss": 0.6346, + "step": 296 + }, + { + "epoch": 0.26, + "learning_rate": 1.7522123893805313e-05, + "loss": 0.6386, + "step": 297 + }, + { + "epoch": 0.26, + "learning_rate": 1.7581120943952803e-05, + "loss": 0.6246, + "step": 298 + }, + { + "epoch": 0.26, + "learning_rate": 1.7640117994100297e-05, + "loss": 0.6122, + "step": 299 + }, + { + "epoch": 0.27, + "learning_rate": 1.769911504424779e-05, + "loss": 0.5873, + "step": 300 + }, + { + "epoch": 0.27, + "learning_rate": 1.775811209439528e-05, + "loss": 0.6102, + "step": 301 + }, + { + "epoch": 0.27, + "learning_rate": 1.7817109144542775e-05, + "loss": 0.6144, + "step": 302 + }, + { + "epoch": 0.27, + "learning_rate": 1.7876106194690265e-05, + "loss": 0.6328, + "step": 303 + }, + { + "epoch": 0.27, + "learning_rate": 1.793510324483776e-05, + "loss": 0.5994, + "step": 304 + }, + { + "epoch": 0.27, + "learning_rate": 1.7994100294985252e-05, + "loss": 0.6364, + "step": 305 + }, + { + "epoch": 0.27, + "learning_rate": 1.8053097345132743e-05, + "loss": 0.59, + "step": 306 + }, + { + "epoch": 0.27, + "learning_rate": 1.8112094395280236e-05, + "loss": 0.6054, + "step": 307 + }, + { + "epoch": 0.27, + "learning_rate": 1.817109144542773e-05, + "loss": 0.6258, + "step": 308 + }, + { + "epoch": 0.27, + "learning_rate": 1.823008849557522e-05, + "loss": 0.5913, + "step": 309 + }, + { + "epoch": 0.27, + "learning_rate": 1.8289085545722714e-05, + "loss": 0.6189, + "step": 310 + }, + { + "epoch": 0.28, + "learning_rate": 1.8348082595870208e-05, + "loss": 0.5768, + "step": 311 + }, + { + "epoch": 0.28, + "learning_rate": 1.8407079646017702e-05, + "loss": 0.6298, + "step": 312 + }, + { + "epoch": 0.28, + "learning_rate": 1.8466076696165195e-05, + "loss": 0.6336, + "step": 313 + }, + { + "epoch": 0.28, + "learning_rate": 1.8525073746312686e-05, + "loss": 0.6172, + "step": 314 + }, + { + "epoch": 0.28, + "learning_rate": 1.858407079646018e-05, + "loss": 0.6081, + "step": 315 + }, + { + "epoch": 0.28, + "learning_rate": 1.8643067846607673e-05, + "loss": 0.6278, + "step": 316 + }, + { + "epoch": 0.28, + "learning_rate": 1.8702064896755164e-05, + "loss": 0.6009, + "step": 317 + }, + { + "epoch": 0.28, + "learning_rate": 1.8761061946902657e-05, + "loss": 0.6163, + "step": 318 + }, + { + "epoch": 0.28, + "learning_rate": 1.8820058997050148e-05, + "loss": 0.6329, + "step": 319 + }, + { + "epoch": 0.28, + "learning_rate": 1.887905604719764e-05, + "loss": 0.599, + "step": 320 + }, + { + "epoch": 0.28, + "learning_rate": 1.8938053097345135e-05, + "loss": 0.6284, + "step": 321 + }, + { + "epoch": 0.28, + "learning_rate": 1.8997050147492625e-05, + "loss": 0.6156, + "step": 322 + }, + { + "epoch": 0.29, + "learning_rate": 1.905604719764012e-05, + "loss": 0.6198, + "step": 323 + }, + { + "epoch": 0.29, + "learning_rate": 1.9115044247787613e-05, + "loss": 0.603, + "step": 324 + }, + { + "epoch": 0.29, + "learning_rate": 1.9174041297935103e-05, + "loss": 0.6135, + "step": 325 + }, + { + "epoch": 0.29, + "learning_rate": 1.9233038348082597e-05, + "loss": 0.5993, + "step": 326 + }, + { + "epoch": 0.29, + "learning_rate": 1.929203539823009e-05, + "loss": 0.617, + "step": 327 + }, + { + "epoch": 0.29, + "learning_rate": 1.935103244837758e-05, + "loss": 0.6083, + "step": 328 + }, + { + "epoch": 0.29, + "learning_rate": 1.9410029498525075e-05, + "loss": 0.6114, + "step": 329 + }, + { + "epoch": 0.29, + "learning_rate": 1.946902654867257e-05, + "loss": 0.6234, + "step": 330 + }, + { + "epoch": 0.29, + "learning_rate": 1.9528023598820062e-05, + "loss": 0.5841, + "step": 331 + }, + { + "epoch": 0.29, + "learning_rate": 1.9587020648967552e-05, + "loss": 0.6174, + "step": 332 + }, + { + "epoch": 0.29, + "learning_rate": 1.9646017699115046e-05, + "loss": 0.6219, + "step": 333 + }, + { + "epoch": 0.3, + "learning_rate": 1.970501474926254e-05, + "loss": 0.6037, + "step": 334 + }, + { + "epoch": 0.3, + "learning_rate": 1.976401179941003e-05, + "loss": 0.5876, + "step": 335 + }, + { + "epoch": 0.3, + "learning_rate": 1.9823008849557524e-05, + "loss": 0.6115, + "step": 336 + }, + { + "epoch": 0.3, + "learning_rate": 1.9882005899705018e-05, + "loss": 0.6086, + "step": 337 + }, + { + "epoch": 0.3, + "learning_rate": 1.9941002949852508e-05, + "loss": 0.6017, + "step": 338 + }, + { + "epoch": 0.3, + "learning_rate": 2e-05, + "loss": 0.6014, + "step": 339 + }, + { + "epoch": 0.3, + "learning_rate": 1.999999958925774e-05, + "loss": 0.5928, + "step": 340 + }, + { + "epoch": 0.3, + "learning_rate": 1.9999998357030983e-05, + "loss": 0.6216, + "step": 341 + }, + { + "epoch": 0.3, + "learning_rate": 1.999999630331984e-05, + "loss": 0.6169, + "step": 342 + }, + { + "epoch": 0.3, + "learning_rate": 1.9999993428124474e-05, + "loss": 0.6257, + "step": 343 + }, + { + "epoch": 0.3, + "learning_rate": 1.999998973144512e-05, + "loss": 0.5999, + "step": 344 + }, + { + "epoch": 0.31, + "learning_rate": 1.9999985213282084e-05, + "loss": 0.6159, + "step": 345 + }, + { + "epoch": 0.31, + "learning_rate": 1.9999979873635742e-05, + "loss": 0.6281, + "step": 346 + }, + { + "epoch": 0.31, + "learning_rate": 1.9999973712506525e-05, + "loss": 0.5937, + "step": 347 + }, + { + "epoch": 0.31, + "learning_rate": 1.999996672989494e-05, + "loss": 0.5355, + "step": 348 + }, + { + "epoch": 0.31, + "learning_rate": 1.9999958925801567e-05, + "loss": 0.5979, + "step": 349 + }, + { + "epoch": 0.31, + "learning_rate": 1.999995030022704e-05, + "loss": 0.6145, + "step": 350 + }, + { + "epoch": 0.31, + "learning_rate": 1.999994085317207e-05, + "loss": 0.6002, + "step": 351 + }, + { + "epoch": 0.31, + "learning_rate": 1.999993058463743e-05, + "loss": 0.6053, + "step": 352 + }, + { + "epoch": 0.31, + "learning_rate": 1.9999919494623975e-05, + "loss": 0.5882, + "step": 353 + }, + { + "epoch": 0.31, + "learning_rate": 1.9999907583132603e-05, + "loss": 0.6077, + "step": 354 + }, + { + "epoch": 0.31, + "learning_rate": 1.9999894850164298e-05, + "loss": 0.5852, + "step": 355 + }, + { + "epoch": 0.31, + "learning_rate": 1.9999881295720106e-05, + "loss": 0.6232, + "step": 356 + }, + { + "epoch": 0.32, + "learning_rate": 1.999986691980114e-05, + "loss": 0.6204, + "step": 357 + }, + { + "epoch": 0.32, + "learning_rate": 1.999985172240858e-05, + "loss": 0.6096, + "step": 358 + }, + { + "epoch": 0.32, + "learning_rate": 1.999983570354368e-05, + "loss": 0.5992, + "step": 359 + }, + { + "epoch": 0.32, + "learning_rate": 1.9999818863207743e-05, + "loss": 0.5982, + "step": 360 + }, + { + "epoch": 0.32, + "learning_rate": 1.9999801201402165e-05, + "loss": 0.6054, + "step": 361 + }, + { + "epoch": 0.32, + "learning_rate": 1.9999782718128392e-05, + "loss": 0.627, + "step": 362 + }, + { + "epoch": 0.32, + "learning_rate": 1.9999763413387945e-05, + "loss": 0.6194, + "step": 363 + }, + { + "epoch": 0.32, + "learning_rate": 1.9999743287182406e-05, + "loss": 0.5725, + "step": 364 + }, + { + "epoch": 0.32, + "learning_rate": 1.999972233951343e-05, + "loss": 0.6076, + "step": 365 + }, + { + "epoch": 0.32, + "learning_rate": 1.9999700570382735e-05, + "loss": 0.609, + "step": 366 + }, + { + "epoch": 0.32, + "learning_rate": 1.9999677979792116e-05, + "loss": 0.6232, + "step": 367 + }, + { + "epoch": 0.33, + "learning_rate": 1.9999654567743425e-05, + "loss": 0.605, + "step": 368 + }, + { + "epoch": 0.33, + "learning_rate": 1.9999630334238584e-05, + "loss": 0.5994, + "step": 369 + }, + { + "epoch": 0.33, + "learning_rate": 1.9999605279279585e-05, + "loss": 0.5952, + "step": 370 + }, + { + "epoch": 0.33, + "learning_rate": 1.9999579402868487e-05, + "loss": 0.6249, + "step": 371 + }, + { + "epoch": 0.33, + "learning_rate": 1.9999552705007416e-05, + "loss": 0.5971, + "step": 372 + }, + { + "epoch": 0.33, + "learning_rate": 1.9999525185698562e-05, + "loss": 0.6, + "step": 373 + }, + { + "epoch": 0.33, + "learning_rate": 1.999949684494419e-05, + "loss": 0.6109, + "step": 374 + }, + { + "epoch": 0.33, + "learning_rate": 1.999946768274662e-05, + "loss": 0.6236, + "step": 375 + }, + { + "epoch": 0.33, + "learning_rate": 1.999943769910826e-05, + "loss": 0.5981, + "step": 376 + }, + { + "epoch": 0.33, + "learning_rate": 1.9999406894031567e-05, + "loss": 0.6346, + "step": 377 + }, + { + "epoch": 0.33, + "learning_rate": 1.9999375267519068e-05, + "loss": 0.6088, + "step": 378 + }, + { + "epoch": 0.34, + "learning_rate": 1.9999342819573367e-05, + "loss": 0.6317, + "step": 379 + }, + { + "epoch": 0.34, + "learning_rate": 1.9999309550197123e-05, + "loss": 0.6196, + "step": 380 + }, + { + "epoch": 0.34, + "learning_rate": 1.9999275459393078e-05, + "loss": 0.6346, + "step": 381 + }, + { + "epoch": 0.34, + "learning_rate": 1.999924054716402e-05, + "loss": 0.6229, + "step": 382 + }, + { + "epoch": 0.34, + "learning_rate": 1.9999204813512832e-05, + "loss": 0.6017, + "step": 383 + }, + { + "epoch": 0.34, + "learning_rate": 1.999916825844244e-05, + "loss": 0.5828, + "step": 384 + }, + { + "epoch": 0.34, + "learning_rate": 1.999913088195585e-05, + "loss": 0.589, + "step": 385 + }, + { + "epoch": 0.34, + "learning_rate": 1.999909268405613e-05, + "loss": 0.6079, + "step": 386 + }, + { + "epoch": 0.34, + "learning_rate": 1.9999053664746417e-05, + "loss": 0.5958, + "step": 387 + }, + { + "epoch": 0.34, + "learning_rate": 1.999901382402992e-05, + "loss": 0.6114, + "step": 388 + }, + { + "epoch": 0.34, + "learning_rate": 1.9998973161909906e-05, + "loss": 0.5977, + "step": 389 + }, + { + "epoch": 0.34, + "learning_rate": 1.9998931678389725e-05, + "loss": 0.6129, + "step": 390 + }, + { + "epoch": 0.35, + "learning_rate": 1.999888937347278e-05, + "loss": 0.5911, + "step": 391 + }, + { + "epoch": 0.35, + "learning_rate": 1.9998846247162542e-05, + "loss": 0.5914, + "step": 392 + }, + { + "epoch": 0.35, + "learning_rate": 1.999880229946256e-05, + "loss": 0.6113, + "step": 393 + }, + { + "epoch": 0.35, + "learning_rate": 1.9998757530376444e-05, + "loss": 0.6178, + "step": 394 + }, + { + "epoch": 0.35, + "learning_rate": 1.9998711939907866e-05, + "loss": 0.5837, + "step": 395 + }, + { + "epoch": 0.35, + "learning_rate": 1.9998665528060573e-05, + "loss": 0.5929, + "step": 396 + }, + { + "epoch": 0.35, + "learning_rate": 1.9998618294838384e-05, + "loss": 0.575, + "step": 397 + }, + { + "epoch": 0.35, + "learning_rate": 1.999857024024517e-05, + "loss": 0.5949, + "step": 398 + }, + { + "epoch": 0.35, + "learning_rate": 1.999852136428489e-05, + "loss": 0.6033, + "step": 399 + }, + { + "epoch": 0.35, + "learning_rate": 1.9998471666961548e-05, + "loss": 0.5986, + "step": 400 + }, + { + "epoch": 0.35, + "learning_rate": 1.999842114827923e-05, + "loss": 0.5688, + "step": 401 + }, + { + "epoch": 0.36, + "learning_rate": 1.9998369808242088e-05, + "loss": 0.6043, + "step": 402 + }, + { + "epoch": 0.36, + "learning_rate": 1.9998317646854336e-05, + "loss": 0.6086, + "step": 403 + }, + { + "epoch": 0.36, + "learning_rate": 1.999826466412026e-05, + "loss": 0.6083, + "step": 404 + }, + { + "epoch": 0.36, + "learning_rate": 1.999821086004422e-05, + "loss": 0.602, + "step": 405 + }, + { + "epoch": 0.36, + "learning_rate": 1.9998156234630624e-05, + "loss": 0.6194, + "step": 406 + }, + { + "epoch": 0.36, + "learning_rate": 1.999810078788397e-05, + "loss": 0.6057, + "step": 407 + }, + { + "epoch": 0.36, + "learning_rate": 1.9998044519808803e-05, + "loss": 0.5945, + "step": 408 + }, + { + "epoch": 0.36, + "learning_rate": 1.9997987430409755e-05, + "loss": 0.6092, + "step": 409 + }, + { + "epoch": 0.36, + "learning_rate": 1.9997929519691505e-05, + "loss": 0.5869, + "step": 410 + }, + { + "epoch": 0.36, + "learning_rate": 1.999787078765882e-05, + "loss": 0.5683, + "step": 411 + }, + { + "epoch": 0.36, + "learning_rate": 1.9997811234316524e-05, + "loss": 0.582, + "step": 412 + }, + { + "epoch": 0.37, + "learning_rate": 1.9997750859669503e-05, + "loss": 0.5817, + "step": 413 + }, + { + "epoch": 0.37, + "learning_rate": 1.999768966372272e-05, + "loss": 0.6015, + "step": 414 + }, + { + "epoch": 0.37, + "learning_rate": 1.99976276464812e-05, + "loss": 0.5906, + "step": 415 + }, + { + "epoch": 0.37, + "learning_rate": 1.9997564807950042e-05, + "loss": 0.5887, + "step": 416 + }, + { + "epoch": 0.37, + "learning_rate": 1.9997501148134403e-05, + "loss": 0.6034, + "step": 417 + }, + { + "epoch": 0.37, + "learning_rate": 1.9997436667039518e-05, + "loss": 0.6179, + "step": 418 + }, + { + "epoch": 0.37, + "learning_rate": 1.9997371364670682e-05, + "loss": 0.5763, + "step": 419 + }, + { + "epoch": 0.37, + "learning_rate": 1.9997305241033257e-05, + "loss": 0.6104, + "step": 420 + }, + { + "epoch": 0.37, + "learning_rate": 1.999723829613268e-05, + "loss": 0.598, + "step": 421 + }, + { + "epoch": 0.37, + "learning_rate": 1.9997170529974444e-05, + "loss": 0.6292, + "step": 422 + }, + { + "epoch": 0.37, + "learning_rate": 1.999710194256412e-05, + "loss": 0.5909, + "step": 423 + }, + { + "epoch": 0.38, + "learning_rate": 1.9997032533907343e-05, + "loss": 0.5596, + "step": 424 + }, + { + "epoch": 0.38, + "learning_rate": 1.9996962304009813e-05, + "loss": 0.6097, + "step": 425 + }, + { + "epoch": 0.38, + "learning_rate": 1.9996891252877296e-05, + "loss": 0.5863, + "step": 426 + }, + { + "epoch": 0.38, + "learning_rate": 1.9996819380515637e-05, + "loss": 0.5771, + "step": 427 + }, + { + "epoch": 0.38, + "learning_rate": 1.9996746686930734e-05, + "loss": 0.6115, + "step": 428 + }, + { + "epoch": 0.38, + "learning_rate": 1.9996673172128558e-05, + "loss": 0.5654, + "step": 429 + }, + { + "epoch": 0.38, + "learning_rate": 1.9996598836115152e-05, + "loss": 0.5871, + "step": 430 + }, + { + "epoch": 0.38, + "learning_rate": 1.9996523678896623e-05, + "loss": 0.5631, + "step": 431 + }, + { + "epoch": 0.38, + "learning_rate": 1.999644770047914e-05, + "loss": 0.5902, + "step": 432 + }, + { + "epoch": 0.38, + "learning_rate": 1.999637090086895e-05, + "loss": 0.6115, + "step": 433 + }, + { + "epoch": 0.38, + "learning_rate": 1.9996293280072353e-05, + "loss": 0.5888, + "step": 434 + }, + { + "epoch": 0.38, + "learning_rate": 1.999621483809574e-05, + "loss": 0.6032, + "step": 435 + }, + { + "epoch": 0.39, + "learning_rate": 1.9996135574945543e-05, + "loss": 0.5791, + "step": 436 + }, + { + "epoch": 0.39, + "learning_rate": 1.9996055490628276e-05, + "loss": 0.5753, + "step": 437 + }, + { + "epoch": 0.39, + "learning_rate": 1.9995974585150518e-05, + "loss": 0.5876, + "step": 438 + }, + { + "epoch": 0.39, + "learning_rate": 1.9995892858518918e-05, + "loss": 0.5585, + "step": 439 + }, + { + "epoch": 0.39, + "learning_rate": 1.9995810310740193e-05, + "loss": 0.6204, + "step": 440 + }, + { + "epoch": 0.39, + "learning_rate": 1.999572694182111e-05, + "loss": 0.6138, + "step": 441 + }, + { + "epoch": 0.39, + "learning_rate": 1.9995642751768534e-05, + "loss": 0.597, + "step": 442 + }, + { + "epoch": 0.39, + "learning_rate": 1.999555774058937e-05, + "loss": 0.6108, + "step": 443 + }, + { + "epoch": 0.39, + "learning_rate": 1.9995471908290603e-05, + "loss": 0.5562, + "step": 444 + }, + { + "epoch": 0.39, + "learning_rate": 1.9995385254879292e-05, + "loss": 0.5669, + "step": 445 + }, + { + "epoch": 0.39, + "learning_rate": 1.9995297780362547e-05, + "loss": 0.5681, + "step": 446 + }, + { + "epoch": 0.4, + "learning_rate": 1.9995209484747556e-05, + "loss": 0.6023, + "step": 447 + }, + { + "epoch": 0.4, + "learning_rate": 1.9995120368041574e-05, + "loss": 0.5978, + "step": 448 + }, + { + "epoch": 0.4, + "learning_rate": 1.999503043025192e-05, + "loss": 0.5907, + "step": 449 + }, + { + "epoch": 0.4, + "learning_rate": 1.9994939671385986e-05, + "loss": 0.6151, + "step": 450 + }, + { + "epoch": 0.4, + "learning_rate": 1.9994848091451218e-05, + "loss": 0.5677, + "step": 451 + }, + { + "epoch": 0.4, + "learning_rate": 1.9994755690455154e-05, + "loss": 0.584, + "step": 452 + }, + { + "epoch": 0.4, + "learning_rate": 1.999466246840537e-05, + "loss": 0.5953, + "step": 453 + }, + { + "epoch": 0.4, + "learning_rate": 1.999456842530953e-05, + "loss": 0.5836, + "step": 454 + }, + { + "epoch": 0.4, + "learning_rate": 1.9994473561175366e-05, + "loss": 0.5766, + "step": 455 + }, + { + "epoch": 0.4, + "learning_rate": 1.999437787601066e-05, + "loss": 0.5837, + "step": 456 + }, + { + "epoch": 0.4, + "learning_rate": 1.999428136982328e-05, + "loss": 0.6042, + "step": 457 + }, + { + "epoch": 0.41, + "learning_rate": 1.9994184042621148e-05, + "loss": 0.5818, + "step": 458 + }, + { + "epoch": 0.41, + "learning_rate": 1.9994085894412265e-05, + "loss": 0.6114, + "step": 459 + }, + { + "epoch": 0.41, + "learning_rate": 1.999398692520469e-05, + "loss": 0.5833, + "step": 460 + }, + { + "epoch": 0.41, + "learning_rate": 1.9993887135006558e-05, + "loss": 0.6127, + "step": 461 + }, + { + "epoch": 0.41, + "learning_rate": 1.999378652382606e-05, + "loss": 0.5819, + "step": 462 + }, + { + "epoch": 0.41, + "learning_rate": 1.9993685091671466e-05, + "loss": 0.5769, + "step": 463 + }, + { + "epoch": 0.41, + "learning_rate": 1.9993582838551103e-05, + "loss": 0.5778, + "step": 464 + }, + { + "epoch": 0.41, + "learning_rate": 1.9993479764473374e-05, + "loss": 0.617, + "step": 465 + }, + { + "epoch": 0.41, + "learning_rate": 1.999337586944675e-05, + "loss": 0.5939, + "step": 466 + }, + { + "epoch": 0.41, + "learning_rate": 1.9993271153479762e-05, + "loss": 0.5949, + "step": 467 + }, + { + "epoch": 0.41, + "learning_rate": 1.9993165616581013e-05, + "loss": 0.5878, + "step": 468 + }, + { + "epoch": 0.41, + "learning_rate": 1.999305925875917e-05, + "loss": 0.5755, + "step": 469 + }, + { + "epoch": 0.42, + "learning_rate": 1.9992952080022972e-05, + "loss": 0.5898, + "step": 470 + }, + { + "epoch": 0.42, + "learning_rate": 1.9992844080381228e-05, + "loss": 0.5883, + "step": 471 + }, + { + "epoch": 0.42, + "learning_rate": 1.9992735259842808e-05, + "loss": 0.6224, + "step": 472 + }, + { + "epoch": 0.42, + "learning_rate": 1.9992625618416645e-05, + "loss": 0.5867, + "step": 473 + }, + { + "epoch": 0.42, + "learning_rate": 1.9992515156111753e-05, + "loss": 0.6103, + "step": 474 + }, + { + "epoch": 0.42, + "learning_rate": 1.9992403872937204e-05, + "loss": 0.5842, + "step": 475 + }, + { + "epoch": 0.42, + "learning_rate": 1.9992291768902137e-05, + "loss": 0.6048, + "step": 476 + }, + { + "epoch": 0.42, + "learning_rate": 1.999217884401577e-05, + "loss": 0.5892, + "step": 477 + }, + { + "epoch": 0.42, + "learning_rate": 1.9992065098287368e-05, + "loss": 0.5834, + "step": 478 + }, + { + "epoch": 0.42, + "learning_rate": 1.9991950531726282e-05, + "loss": 0.5894, + "step": 479 + }, + { + "epoch": 0.42, + "learning_rate": 1.999183514434192e-05, + "loss": 0.5656, + "step": 480 + }, + { + "epoch": 0.43, + "learning_rate": 1.9991718936143764e-05, + "loss": 0.6113, + "step": 481 + }, + { + "epoch": 0.43, + "learning_rate": 1.999160190714136e-05, + "loss": 0.5893, + "step": 482 + }, + { + "epoch": 0.43, + "learning_rate": 1.999148405734432e-05, + "loss": 0.6175, + "step": 483 + }, + { + "epoch": 0.43, + "learning_rate": 1.9991365386762326e-05, + "loss": 0.6108, + "step": 484 + }, + { + "epoch": 0.43, + "learning_rate": 1.9991245895405128e-05, + "loss": 0.612, + "step": 485 + }, + { + "epoch": 0.43, + "learning_rate": 1.9991125583282538e-05, + "loss": 0.6169, + "step": 486 + }, + { + "epoch": 0.43, + "learning_rate": 1.9991004450404447e-05, + "loss": 0.6033, + "step": 487 + }, + { + "epoch": 0.43, + "learning_rate": 1.9990882496780794e-05, + "loss": 0.5694, + "step": 488 + }, + { + "epoch": 0.43, + "learning_rate": 1.999075972242161e-05, + "loss": 0.5979, + "step": 489 + }, + { + "epoch": 0.43, + "learning_rate": 1.9990636127336973e-05, + "loss": 0.6105, + "step": 490 + }, + { + "epoch": 0.43, + "learning_rate": 1.999051171153704e-05, + "loss": 0.5634, + "step": 491 + }, + { + "epoch": 0.44, + "learning_rate": 1.9990386475032024e-05, + "loss": 0.5808, + "step": 492 + }, + { + "epoch": 0.44, + "learning_rate": 1.9990260417832227e-05, + "loss": 0.5964, + "step": 493 + }, + { + "epoch": 0.44, + "learning_rate": 1.999013353994799e-05, + "loss": 0.578, + "step": 494 + }, + { + "epoch": 0.44, + "learning_rate": 1.9990005841389743e-05, + "loss": 0.5803, + "step": 495 + }, + { + "epoch": 0.44, + "learning_rate": 1.9989877322167975e-05, + "loss": 0.622, + "step": 496 + }, + { + "epoch": 0.44, + "learning_rate": 1.9989747982293245e-05, + "loss": 0.566, + "step": 497 + }, + { + "epoch": 0.44, + "learning_rate": 1.998961782177618e-05, + "loss": 0.5726, + "step": 498 + }, + { + "epoch": 0.44, + "learning_rate": 1.9989486840627465e-05, + "loss": 0.6148, + "step": 499 + }, + { + "epoch": 0.44, + "learning_rate": 1.9989355038857866e-05, + "loss": 0.5982, + "step": 500 + }, + { + "epoch": 0.44, + "learning_rate": 1.9989222416478208e-05, + "loss": 0.5837, + "step": 501 + }, + { + "epoch": 0.44, + "learning_rate": 1.9989088973499386e-05, + "loss": 0.6072, + "step": 502 + }, + { + "epoch": 0.44, + "learning_rate": 1.9988954709932366e-05, + "loss": 0.5844, + "step": 503 + }, + { + "epoch": 0.45, + "learning_rate": 1.9988819625788168e-05, + "loss": 0.5832, + "step": 504 + }, + { + "epoch": 0.45, + "learning_rate": 1.99886837210779e-05, + "loss": 0.5918, + "step": 505 + }, + { + "epoch": 0.45, + "learning_rate": 1.998854699581272e-05, + "loss": 0.5795, + "step": 506 + }, + { + "epoch": 0.45, + "learning_rate": 1.998840945000386e-05, + "loss": 0.6132, + "step": 507 + }, + { + "epoch": 0.45, + "learning_rate": 1.9988271083662624e-05, + "loss": 0.6027, + "step": 508 + }, + { + "epoch": 0.45, + "learning_rate": 1.998813189680037e-05, + "loss": 0.5766, + "step": 509 + }, + { + "epoch": 0.45, + "learning_rate": 1.998799188942854e-05, + "loss": 0.6023, + "step": 510 + }, + { + "epoch": 0.45, + "learning_rate": 1.9987851061558626e-05, + "loss": 0.5899, + "step": 511 + }, + { + "epoch": 0.45, + "learning_rate": 1.998770941320221e-05, + "loss": 0.5631, + "step": 512 + }, + { + "epoch": 0.45, + "learning_rate": 1.9987566944370923e-05, + "loss": 0.5824, + "step": 513 + }, + { + "epoch": 0.45, + "learning_rate": 1.998742365507646e-05, + "loss": 0.5858, + "step": 514 + }, + { + "epoch": 0.46, + "learning_rate": 1.9987279545330603e-05, + "loss": 0.565, + "step": 515 + }, + { + "epoch": 0.46, + "learning_rate": 1.9987134615145183e-05, + "loss": 0.5893, + "step": 516 + }, + { + "epoch": 0.46, + "learning_rate": 1.998698886453211e-05, + "loss": 0.6223, + "step": 517 + }, + { + "epoch": 0.46, + "learning_rate": 1.9986842293503362e-05, + "loss": 0.5794, + "step": 518 + }, + { + "epoch": 0.46, + "learning_rate": 1.9986694902070966e-05, + "loss": 0.5953, + "step": 519 + }, + { + "epoch": 0.46, + "learning_rate": 1.9986546690247042e-05, + "loss": 0.5827, + "step": 520 + }, + { + "epoch": 0.46, + "learning_rate": 1.998639765804376e-05, + "loss": 0.6111, + "step": 521 + }, + { + "epoch": 0.46, + "learning_rate": 1.998624780547336e-05, + "loss": 0.5855, + "step": 522 + }, + { + "epoch": 0.46, + "learning_rate": 1.9986097132548164e-05, + "loss": 0.572, + "step": 523 + }, + { + "epoch": 0.46, + "learning_rate": 1.9985945639280534e-05, + "loss": 0.5948, + "step": 524 + }, + { + "epoch": 0.46, + "learning_rate": 1.998579332568293e-05, + "loss": 0.5831, + "step": 525 + }, + { + "epoch": 0.47, + "learning_rate": 1.9985640191767853e-05, + "loss": 0.592, + "step": 526 + }, + { + "epoch": 0.47, + "learning_rate": 1.9985486237547885e-05, + "loss": 0.5599, + "step": 527 + }, + { + "epoch": 0.47, + "learning_rate": 1.9985331463035678e-05, + "loss": 0.5596, + "step": 528 + }, + { + "epoch": 0.47, + "learning_rate": 1.9985175868243938e-05, + "loss": 0.581, + "step": 529 + }, + { + "epoch": 0.47, + "learning_rate": 1.9985019453185457e-05, + "loss": 0.5974, + "step": 530 + }, + { + "epoch": 0.47, + "learning_rate": 1.9984862217873074e-05, + "loss": 0.6011, + "step": 531 + }, + { + "epoch": 0.47, + "learning_rate": 1.998470416231972e-05, + "loss": 0.5893, + "step": 532 + }, + { + "epoch": 0.47, + "learning_rate": 1.9984545286538362e-05, + "loss": 0.5903, + "step": 533 + }, + { + "epoch": 0.47, + "learning_rate": 1.998438559054206e-05, + "loss": 0.5933, + "step": 534 + }, + { + "epoch": 0.47, + "learning_rate": 1.9984225074343935e-05, + "loss": 0.5916, + "step": 535 + }, + { + "epoch": 0.47, + "learning_rate": 1.998406373795717e-05, + "loss": 0.5945, + "step": 536 + }, + { + "epoch": 0.48, + "learning_rate": 1.998390158139502e-05, + "loss": 0.5802, + "step": 537 + }, + { + "epoch": 0.48, + "learning_rate": 1.99837386046708e-05, + "loss": 0.5511, + "step": 538 + }, + { + "epoch": 0.48, + "learning_rate": 1.998357480779791e-05, + "loss": 0.5846, + "step": 539 + }, + { + "epoch": 0.48, + "learning_rate": 1.998341019078979e-05, + "loss": 0.5816, + "step": 540 + }, + { + "epoch": 0.48, + "learning_rate": 1.9983244753659975e-05, + "loss": 0.574, + "step": 541 + }, + { + "epoch": 0.48, + "learning_rate": 1.9983078496422055e-05, + "loss": 0.5912, + "step": 542 + }, + { + "epoch": 0.48, + "learning_rate": 1.9982911419089684e-05, + "loss": 0.5587, + "step": 543 + }, + { + "epoch": 0.48, + "learning_rate": 1.9982743521676586e-05, + "loss": 0.5696, + "step": 544 + }, + { + "epoch": 0.48, + "learning_rate": 1.9982574804196556e-05, + "loss": 0.5946, + "step": 545 + }, + { + "epoch": 0.48, + "learning_rate": 1.9982405266663455e-05, + "loss": 0.5609, + "step": 546 + }, + { + "epoch": 0.48, + "learning_rate": 1.998223490909121e-05, + "loss": 0.58, + "step": 547 + }, + { + "epoch": 0.48, + "learning_rate": 1.998206373149381e-05, + "loss": 0.5701, + "step": 548 + }, + { + "epoch": 0.49, + "learning_rate": 1.9981891733885322e-05, + "loss": 0.6096, + "step": 549 + }, + { + "epoch": 0.49, + "learning_rate": 1.9981718916279878e-05, + "loss": 0.5889, + "step": 550 + }, + { + "epoch": 0.49, + "learning_rate": 1.9981545278691666e-05, + "loss": 0.5773, + "step": 551 + }, + { + "epoch": 0.49, + "learning_rate": 1.998137082113496e-05, + "loss": 0.6023, + "step": 552 + }, + { + "epoch": 0.49, + "learning_rate": 1.9981195543624086e-05, + "loss": 0.5953, + "step": 553 + }, + { + "epoch": 0.49, + "learning_rate": 1.9981019446173442e-05, + "loss": 0.5884, + "step": 554 + }, + { + "epoch": 0.49, + "learning_rate": 1.9980842528797497e-05, + "loss": 0.5733, + "step": 555 + }, + { + "epoch": 0.49, + "learning_rate": 1.9980664791510783e-05, + "loss": 0.5768, + "step": 556 + }, + { + "epoch": 0.49, + "learning_rate": 1.99804862343279e-05, + "loss": 0.5806, + "step": 557 + }, + { + "epoch": 0.49, + "learning_rate": 1.9980306857263515e-05, + "loss": 0.5923, + "step": 558 + }, + { + "epoch": 0.49, + "learning_rate": 1.9980126660332367e-05, + "loss": 0.6173, + "step": 559 + }, + { + "epoch": 0.5, + "learning_rate": 1.9979945643549265e-05, + "loss": 0.5806, + "step": 560 + }, + { + "epoch": 0.5, + "learning_rate": 1.997976380692906e-05, + "loss": 0.5955, + "step": 561 + }, + { + "epoch": 0.5, + "learning_rate": 1.997958115048671e-05, + "loss": 0.5739, + "step": 562 + }, + { + "epoch": 0.5, + "learning_rate": 1.997939767423721e-05, + "loss": 0.5667, + "step": 563 + }, + { + "epoch": 0.5, + "learning_rate": 1.9979213378195633e-05, + "loss": 0.5849, + "step": 564 + }, + { + "epoch": 0.5, + "learning_rate": 1.997902826237712e-05, + "loss": 0.5848, + "step": 565 + }, + { + "epoch": 0.5, + "learning_rate": 1.9978842326796876e-05, + "loss": 0.5577, + "step": 566 + }, + { + "epoch": 0.5, + "learning_rate": 1.9978655571470174e-05, + "loss": 0.5675, + "step": 567 + }, + { + "epoch": 0.5, + "learning_rate": 1.9978467996412363e-05, + "loss": 0.5685, + "step": 568 + }, + { + "epoch": 0.5, + "learning_rate": 1.9978279601638846e-05, + "loss": 0.5876, + "step": 569 + }, + { + "epoch": 0.5, + "learning_rate": 1.99780903871651e-05, + "loss": 0.5654, + "step": 570 + }, + { + "epoch": 0.51, + "learning_rate": 1.997790035300667e-05, + "loss": 0.5606, + "step": 571 + }, + { + "epoch": 0.51, + "learning_rate": 1.9977709499179167e-05, + "loss": 0.553, + "step": 572 + }, + { + "epoch": 0.51, + "learning_rate": 1.9977517825698264e-05, + "loss": 0.5648, + "step": 573 + }, + { + "epoch": 0.51, + "learning_rate": 1.997732533257972e-05, + "loss": 0.5988, + "step": 574 + }, + { + "epoch": 0.51, + "learning_rate": 1.997713201983933e-05, + "loss": 0.5865, + "step": 575 + }, + { + "epoch": 0.51, + "learning_rate": 1.997693788749299e-05, + "loss": 0.5982, + "step": 576 + }, + { + "epoch": 0.51, + "learning_rate": 1.9976742935556638e-05, + "loss": 0.6088, + "step": 577 + }, + { + "epoch": 0.51, + "learning_rate": 1.9976547164046297e-05, + "loss": 0.581, + "step": 578 + }, + { + "epoch": 0.51, + "learning_rate": 1.997635057297804e-05, + "loss": 0.599, + "step": 579 + }, + { + "epoch": 0.51, + "learning_rate": 1.9976153162368025e-05, + "loss": 0.596, + "step": 580 + }, + { + "epoch": 0.51, + "learning_rate": 1.997595493223246e-05, + "loss": 0.596, + "step": 581 + }, + { + "epoch": 0.51, + "learning_rate": 1.997575588258764e-05, + "loss": 0.5636, + "step": 582 + }, + { + "epoch": 0.52, + "learning_rate": 1.997555601344991e-05, + "loss": 0.5788, + "step": 583 + }, + { + "epoch": 0.52, + "learning_rate": 1.997535532483569e-05, + "loss": 0.5978, + "step": 584 + }, + { + "epoch": 0.52, + "learning_rate": 1.9975153816761463e-05, + "loss": 0.5771, + "step": 585 + }, + { + "epoch": 0.52, + "learning_rate": 1.997495148924379e-05, + "loss": 0.5714, + "step": 586 + }, + { + "epoch": 0.52, + "learning_rate": 1.9974748342299287e-05, + "loss": 0.6075, + "step": 587 + }, + { + "epoch": 0.52, + "learning_rate": 1.9974544375944644e-05, + "loss": 0.5813, + "step": 588 + }, + { + "epoch": 0.52, + "learning_rate": 1.9974339590196616e-05, + "loss": 0.5857, + "step": 589 + }, + { + "epoch": 0.52, + "learning_rate": 1.9974133985072026e-05, + "loss": 0.587, + "step": 590 + }, + { + "epoch": 0.52, + "learning_rate": 1.997392756058776e-05, + "loss": 0.5873, + "step": 591 + }, + { + "epoch": 0.52, + "learning_rate": 1.997372031676078e-05, + "loss": 0.5623, + "step": 592 + }, + { + "epoch": 0.52, + "learning_rate": 1.9973512253608113e-05, + "loss": 0.5715, + "step": 593 + }, + { + "epoch": 0.53, + "learning_rate": 1.9973303371146844e-05, + "loss": 0.5717, + "step": 594 + }, + { + "epoch": 0.53, + "learning_rate": 1.9973093669394137e-05, + "loss": 0.5584, + "step": 595 + }, + { + "epoch": 0.53, + "learning_rate": 1.997288314836722e-05, + "loss": 0.5616, + "step": 596 + }, + { + "epoch": 0.53, + "learning_rate": 1.9972671808083387e-05, + "loss": 0.5968, + "step": 597 + }, + { + "epoch": 0.53, + "learning_rate": 1.9972459648559992e-05, + "loss": 0.583, + "step": 598 + }, + { + "epoch": 0.53, + "learning_rate": 1.9972246669814472e-05, + "loss": 0.5736, + "step": 599 + }, + { + "epoch": 0.53, + "learning_rate": 1.9972032871864317e-05, + "loss": 0.559, + "step": 600 + }, + { + "epoch": 0.53, + "learning_rate": 1.9971818254727097e-05, + "loss": 0.5804, + "step": 601 + }, + { + "epoch": 0.53, + "learning_rate": 1.997160281842043e-05, + "loss": 0.5956, + "step": 602 + }, + { + "epoch": 0.53, + "learning_rate": 1.9971386562962032e-05, + "loss": 0.6282, + "step": 603 + }, + { + "epoch": 0.53, + "learning_rate": 1.9971169488369654e-05, + "loss": 0.5749, + "step": 604 + }, + { + "epoch": 0.54, + "learning_rate": 1.9970951594661132e-05, + "loss": 0.5714, + "step": 605 + }, + { + "epoch": 0.54, + "learning_rate": 1.997073288185437e-05, + "loss": 0.5607, + "step": 606 + }, + { + "epoch": 0.54, + "learning_rate": 1.9970513349967326e-05, + "loss": 0.5819, + "step": 607 + }, + { + "epoch": 0.54, + "learning_rate": 1.997029299901804e-05, + "loss": 0.5834, + "step": 608 + }, + { + "epoch": 0.54, + "learning_rate": 1.9970071829024615e-05, + "loss": 0.5745, + "step": 609 + }, + { + "epoch": 0.54, + "learning_rate": 1.9969849840005217e-05, + "loss": 0.5636, + "step": 610 + }, + { + "epoch": 0.54, + "learning_rate": 1.9969627031978082e-05, + "loss": 0.5587, + "step": 611 + }, + { + "epoch": 0.54, + "learning_rate": 1.996940340496151e-05, + "loss": 0.5891, + "step": 612 + }, + { + "epoch": 0.54, + "learning_rate": 1.996917895897388e-05, + "loss": 0.5737, + "step": 613 + }, + { + "epoch": 0.54, + "learning_rate": 1.9968953694033623e-05, + "loss": 0.5838, + "step": 614 + }, + { + "epoch": 0.54, + "learning_rate": 1.996872761015925e-05, + "loss": 0.5847, + "step": 615 + }, + { + "epoch": 0.54, + "learning_rate": 1.9968500707369327e-05, + "loss": 0.5836, + "step": 616 + }, + { + "epoch": 0.55, + "learning_rate": 1.9968272985682496e-05, + "loss": 0.5962, + "step": 617 + }, + { + "epoch": 0.55, + "learning_rate": 1.9968044445117467e-05, + "loss": 0.5991, + "step": 618 + }, + { + "epoch": 0.55, + "learning_rate": 1.996781508569301e-05, + "loss": 0.5857, + "step": 619 + }, + { + "epoch": 0.55, + "learning_rate": 1.996758490742797e-05, + "loss": 0.5774, + "step": 620 + }, + { + "epoch": 0.55, + "learning_rate": 1.9967353910341253e-05, + "loss": 0.5779, + "step": 621 + }, + { + "epoch": 0.55, + "learning_rate": 1.996712209445184e-05, + "loss": 0.577, + "step": 622 + }, + { + "epoch": 0.55, + "learning_rate": 1.9966889459778767e-05, + "loss": 0.5712, + "step": 623 + }, + { + "epoch": 0.55, + "learning_rate": 1.996665600634115e-05, + "loss": 0.5831, + "step": 624 + }, + { + "epoch": 0.55, + "learning_rate": 1.996642173415816e-05, + "loss": 0.5709, + "step": 625 + }, + { + "epoch": 0.55, + "learning_rate": 1.9966186643249052e-05, + "loss": 0.5855, + "step": 626 + }, + { + "epoch": 0.55, + "learning_rate": 1.9965950733633133e-05, + "loss": 0.5787, + "step": 627 + }, + { + "epoch": 0.56, + "learning_rate": 1.9965714005329785e-05, + "loss": 0.5733, + "step": 628 + }, + { + "epoch": 0.56, + "learning_rate": 1.996547645835845e-05, + "loss": 0.5781, + "step": 629 + }, + { + "epoch": 0.56, + "learning_rate": 1.9965238092738643e-05, + "loss": 0.5927, + "step": 630 + }, + { + "epoch": 0.56, + "learning_rate": 1.9964998908489952e-05, + "loss": 0.589, + "step": 631 + }, + { + "epoch": 0.56, + "learning_rate": 1.996475890563202e-05, + "loss": 0.5721, + "step": 632 + }, + { + "epoch": 0.56, + "learning_rate": 1.9964518084184563e-05, + "loss": 0.5706, + "step": 633 + }, + { + "epoch": 0.56, + "learning_rate": 1.9964276444167363e-05, + "loss": 0.568, + "step": 634 + }, + { + "epoch": 0.56, + "learning_rate": 1.9964033985600274e-05, + "loss": 0.5516, + "step": 635 + }, + { + "epoch": 0.56, + "learning_rate": 1.9963790708503215e-05, + "loss": 0.5717, + "step": 636 + }, + { + "epoch": 0.56, + "learning_rate": 1.9963546612896163e-05, + "loss": 0.573, + "step": 637 + }, + { + "epoch": 0.56, + "learning_rate": 1.9963301698799178e-05, + "loss": 0.5819, + "step": 638 + }, + { + "epoch": 0.57, + "learning_rate": 1.9963055966232376e-05, + "loss": 0.551, + "step": 639 + }, + { + "epoch": 0.57, + "learning_rate": 1.9962809415215943e-05, + "loss": 0.5365, + "step": 640 + }, + { + "epoch": 0.57, + "learning_rate": 1.9962562045770134e-05, + "loss": 0.5772, + "step": 641 + }, + { + "epoch": 0.57, + "learning_rate": 1.9962313857915267e-05, + "loss": 0.6042, + "step": 642 + }, + { + "epoch": 0.57, + "learning_rate": 1.9962064851671735e-05, + "loss": 0.585, + "step": 643 + }, + { + "epoch": 0.57, + "learning_rate": 1.9961815027059992e-05, + "loss": 0.5981, + "step": 644 + }, + { + "epoch": 0.57, + "learning_rate": 1.996156438410056e-05, + "loss": 0.5708, + "step": 645 + }, + { + "epoch": 0.57, + "learning_rate": 1.9961312922814028e-05, + "loss": 0.5708, + "step": 646 + }, + { + "epoch": 0.57, + "learning_rate": 1.9961060643221053e-05, + "loss": 0.565, + "step": 647 + }, + { + "epoch": 0.57, + "learning_rate": 1.9960807545342362e-05, + "loss": 0.5877, + "step": 648 + }, + { + "epoch": 0.57, + "learning_rate": 1.9960553629198745e-05, + "loss": 0.5619, + "step": 649 + }, + { + "epoch": 0.57, + "learning_rate": 1.9960298894811057e-05, + "loss": 0.5632, + "step": 650 + }, + { + "epoch": 0.58, + "learning_rate": 1.9960043342200236e-05, + "loss": 0.5734, + "step": 651 + }, + { + "epoch": 0.58, + "learning_rate": 1.995978697138726e-05, + "loss": 0.5656, + "step": 652 + }, + { + "epoch": 0.58, + "learning_rate": 1.99595297823932e-05, + "loss": 0.5703, + "step": 653 + }, + { + "epoch": 0.58, + "learning_rate": 1.995927177523918e-05, + "loss": 0.5624, + "step": 654 + }, + { + "epoch": 0.58, + "learning_rate": 1.9959012949946396e-05, + "loss": 0.5949, + "step": 655 + }, + { + "epoch": 0.58, + "learning_rate": 1.995875330653611e-05, + "loss": 0.6083, + "step": 656 + }, + { + "epoch": 0.58, + "learning_rate": 1.9958492845029643e-05, + "loss": 0.5749, + "step": 657 + }, + { + "epoch": 0.58, + "learning_rate": 1.9958231565448407e-05, + "loss": 0.6104, + "step": 658 + }, + { + "epoch": 0.58, + "learning_rate": 1.9957969467813853e-05, + "loss": 0.5669, + "step": 659 + }, + { + "epoch": 0.58, + "learning_rate": 1.995770655214752e-05, + "loss": 0.5815, + "step": 660 + }, + { + "epoch": 0.58, + "learning_rate": 1.9957442818471e-05, + "loss": 0.5865, + "step": 661 + }, + { + "epoch": 0.59, + "learning_rate": 1.9957178266805965e-05, + "loss": 0.5497, + "step": 662 + }, + { + "epoch": 0.59, + "learning_rate": 1.9956912897174145e-05, + "loss": 0.5637, + "step": 663 + }, + { + "epoch": 0.59, + "learning_rate": 1.9956646709597332e-05, + "loss": 0.5782, + "step": 664 + }, + { + "epoch": 0.59, + "learning_rate": 1.9956379704097405e-05, + "loss": 0.578, + "step": 665 + }, + { + "epoch": 0.59, + "learning_rate": 1.9956111880696287e-05, + "loss": 0.5823, + "step": 666 + }, + { + "epoch": 0.59, + "learning_rate": 1.9955843239415987e-05, + "loss": 0.5564, + "step": 667 + }, + { + "epoch": 0.59, + "learning_rate": 1.9955573780278574e-05, + "loss": 0.5608, + "step": 668 + }, + { + "epoch": 0.59, + "learning_rate": 1.9955303503306178e-05, + "loss": 0.5593, + "step": 669 + }, + { + "epoch": 0.59, + "learning_rate": 1.9955032408521004e-05, + "loss": 0.5777, + "step": 670 + }, + { + "epoch": 0.59, + "learning_rate": 1.9954760495945324e-05, + "loss": 0.5929, + "step": 671 + }, + { + "epoch": 0.59, + "learning_rate": 1.9954487765601474e-05, + "loss": 0.5735, + "step": 672 + }, + { + "epoch": 0.6, + "learning_rate": 1.9954214217511855e-05, + "loss": 0.575, + "step": 673 + }, + { + "epoch": 0.6, + "learning_rate": 1.9953939851698946e-05, + "loss": 0.5627, + "step": 674 + }, + { + "epoch": 0.6, + "learning_rate": 1.995366466818528e-05, + "loss": 0.5644, + "step": 675 + }, + { + "epoch": 0.6, + "learning_rate": 1.9953388666993463e-05, + "loss": 0.5721, + "step": 676 + }, + { + "epoch": 0.6, + "learning_rate": 1.9953111848146173e-05, + "loss": 0.5628, + "step": 677 + }, + { + "epoch": 0.6, + "learning_rate": 1.995283421166614e-05, + "loss": 0.5889, + "step": 678 + }, + { + "epoch": 0.6, + "learning_rate": 1.9952555757576185e-05, + "loss": 0.5957, + "step": 679 + }, + { + "epoch": 0.6, + "learning_rate": 1.9952276485899173e-05, + "loss": 0.5901, + "step": 680 + }, + { + "epoch": 0.6, + "learning_rate": 1.9951996396658045e-05, + "loss": 0.5795, + "step": 681 + }, + { + "epoch": 0.6, + "learning_rate": 1.9951715489875818e-05, + "loss": 0.5616, + "step": 682 + }, + { + "epoch": 0.6, + "learning_rate": 1.995143376557556e-05, + "loss": 0.5911, + "step": 683 + }, + { + "epoch": 0.61, + "learning_rate": 1.9951151223780422e-05, + "loss": 0.5933, + "step": 684 + }, + { + "epoch": 0.61, + "learning_rate": 1.9950867864513605e-05, + "loss": 0.5593, + "step": 685 + }, + { + "epoch": 0.61, + "learning_rate": 1.9950583687798395e-05, + "loss": 0.5788, + "step": 686 + }, + { + "epoch": 0.61, + "learning_rate": 1.995029869365813e-05, + "loss": 0.5518, + "step": 687 + }, + { + "epoch": 0.61, + "learning_rate": 1.995001288211623e-05, + "loss": 0.6199, + "step": 688 + }, + { + "epoch": 0.61, + "learning_rate": 1.9949726253196164e-05, + "loss": 0.5683, + "step": 689 + }, + { + "epoch": 0.61, + "learning_rate": 1.9949438806921485e-05, + "loss": 0.5889, + "step": 690 + }, + { + "epoch": 0.61, + "learning_rate": 1.99491505433158e-05, + "loss": 0.5702, + "step": 691 + }, + { + "epoch": 0.61, + "learning_rate": 1.9948861462402802e-05, + "loss": 0.5728, + "step": 692 + }, + { + "epoch": 0.61, + "learning_rate": 1.9948571564206225e-05, + "loss": 0.5701, + "step": 693 + }, + { + "epoch": 0.61, + "learning_rate": 1.9948280848749892e-05, + "loss": 0.5818, + "step": 694 + }, + { + "epoch": 0.61, + "learning_rate": 1.9947989316057675e-05, + "loss": 0.5578, + "step": 695 + }, + { + "epoch": 0.62, + "learning_rate": 1.9947696966153536e-05, + "loss": 0.5568, + "step": 696 + }, + { + "epoch": 0.62, + "learning_rate": 1.9947403799061483e-05, + "loss": 0.5497, + "step": 697 + }, + { + "epoch": 0.62, + "learning_rate": 1.9947109814805602e-05, + "loss": 0.5607, + "step": 698 + }, + { + "epoch": 0.62, + "learning_rate": 1.9946815013410044e-05, + "loss": 0.591, + "step": 699 + }, + { + "epoch": 0.62, + "learning_rate": 1.9946519394899023e-05, + "loss": 0.5501, + "step": 700 + }, + { + "epoch": 0.62, + "learning_rate": 1.9946222959296823e-05, + "loss": 0.5693, + "step": 701 + }, + { + "epoch": 0.62, + "learning_rate": 1.9945925706627804e-05, + "loss": 0.5543, + "step": 702 + }, + { + "epoch": 0.62, + "learning_rate": 1.9945627636916374e-05, + "loss": 0.5731, + "step": 703 + }, + { + "epoch": 0.62, + "learning_rate": 1.9945328750187025e-05, + "loss": 0.5767, + "step": 704 + }, + { + "epoch": 0.62, + "learning_rate": 1.994502904646431e-05, + "loss": 0.5719, + "step": 705 + }, + { + "epoch": 0.62, + "learning_rate": 1.9944728525772845e-05, + "loss": 0.5646, + "step": 706 + }, + { + "epoch": 0.63, + "learning_rate": 1.9944427188137326e-05, + "loss": 0.5746, + "step": 707 + }, + { + "epoch": 0.63, + "learning_rate": 1.99441250335825e-05, + "loss": 0.5769, + "step": 708 + }, + { + "epoch": 0.63, + "learning_rate": 1.9943822062133188e-05, + "loss": 0.5606, + "step": 709 + }, + { + "epoch": 0.63, + "learning_rate": 1.9943518273814285e-05, + "loss": 0.5756, + "step": 710 + }, + { + "epoch": 0.63, + "learning_rate": 1.994321366865074e-05, + "loss": 0.572, + "step": 711 + }, + { + "epoch": 0.63, + "learning_rate": 1.9942908246667582e-05, + "loss": 0.5877, + "step": 712 + }, + { + "epoch": 0.63, + "learning_rate": 1.994260200788989e-05, + "loss": 0.5734, + "step": 713 + }, + { + "epoch": 0.63, + "learning_rate": 1.9942294952342837e-05, + "loss": 0.5787, + "step": 714 + }, + { + "epoch": 0.63, + "learning_rate": 1.9941987080051638e-05, + "loss": 0.5653, + "step": 715 + }, + { + "epoch": 0.63, + "learning_rate": 1.9941678391041582e-05, + "loss": 0.5826, + "step": 716 + }, + { + "epoch": 0.63, + "learning_rate": 1.994136888533803e-05, + "loss": 0.574, + "step": 717 + }, + { + "epoch": 0.64, + "learning_rate": 1.9941058562966414e-05, + "loss": 0.5586, + "step": 718 + }, + { + "epoch": 0.64, + "learning_rate": 1.9940747423952217e-05, + "loss": 0.5745, + "step": 719 + }, + { + "epoch": 0.64, + "learning_rate": 1.9940435468321002e-05, + "loss": 0.5711, + "step": 720 + }, + { + "epoch": 0.64, + "learning_rate": 1.9940122696098394e-05, + "loss": 0.585, + "step": 721 + }, + { + "epoch": 0.64, + "learning_rate": 1.9939809107310092e-05, + "loss": 0.5562, + "step": 722 + }, + { + "epoch": 0.64, + "learning_rate": 1.9939494701981846e-05, + "loss": 0.5559, + "step": 723 + }, + { + "epoch": 0.64, + "learning_rate": 1.9939179480139498e-05, + "loss": 0.5542, + "step": 724 + }, + { + "epoch": 0.64, + "learning_rate": 1.9938863441808935e-05, + "loss": 0.5644, + "step": 725 + }, + { + "epoch": 0.64, + "learning_rate": 1.9938546587016118e-05, + "loss": 0.5758, + "step": 726 + }, + { + "epoch": 0.64, + "learning_rate": 1.993822891578708e-05, + "loss": 0.5892, + "step": 727 + }, + { + "epoch": 0.64, + "learning_rate": 1.9937910428147916e-05, + "loss": 0.575, + "step": 728 + }, + { + "epoch": 0.64, + "learning_rate": 1.9937591124124786e-05, + "loss": 0.5843, + "step": 729 + }, + { + "epoch": 0.65, + "learning_rate": 1.9937271003743927e-05, + "loss": 0.5577, + "step": 730 + }, + { + "epoch": 0.65, + "learning_rate": 1.993695006703163e-05, + "loss": 0.5752, + "step": 731 + }, + { + "epoch": 0.65, + "learning_rate": 1.993662831401426e-05, + "loss": 0.6125, + "step": 732 + }, + { + "epoch": 0.65, + "learning_rate": 1.9936305744718253e-05, + "loss": 0.5815, + "step": 733 + }, + { + "epoch": 0.65, + "learning_rate": 1.9935982359170106e-05, + "loss": 0.5774, + "step": 734 + }, + { + "epoch": 0.65, + "learning_rate": 1.9935658157396382e-05, + "loss": 0.5784, + "step": 735 + }, + { + "epoch": 0.65, + "learning_rate": 1.9935333139423716e-05, + "loss": 0.5716, + "step": 736 + }, + { + "epoch": 0.65, + "learning_rate": 1.9935007305278806e-05, + "loss": 0.5467, + "step": 737 + }, + { + "epoch": 0.65, + "learning_rate": 1.9934680654988422e-05, + "loss": 0.5776, + "step": 738 + }, + { + "epoch": 0.65, + "learning_rate": 1.9934353188579395e-05, + "loss": 0.5806, + "step": 739 + }, + { + "epoch": 0.65, + "learning_rate": 1.9934024906078626e-05, + "loss": 0.5685, + "step": 740 + }, + { + "epoch": 0.66, + "learning_rate": 1.9933695807513085e-05, + "loss": 0.5692, + "step": 741 + }, + { + "epoch": 0.66, + "learning_rate": 1.9933365892909802e-05, + "loss": 0.5866, + "step": 742 + }, + { + "epoch": 0.66, + "learning_rate": 1.9933035162295886e-05, + "loss": 0.5708, + "step": 743 + }, + { + "epoch": 0.66, + "learning_rate": 1.99327036156985e-05, + "loss": 0.5791, + "step": 744 + }, + { + "epoch": 0.66, + "learning_rate": 1.9932371253144883e-05, + "loss": 0.5777, + "step": 745 + }, + { + "epoch": 0.66, + "learning_rate": 1.9932038074662338e-05, + "loss": 0.5495, + "step": 746 + }, + { + "epoch": 0.66, + "learning_rate": 1.9931704080278234e-05, + "loss": 0.5446, + "step": 747 + }, + { + "epoch": 0.66, + "learning_rate": 1.9931369270020008e-05, + "loss": 0.5833, + "step": 748 + }, + { + "epoch": 0.66, + "learning_rate": 1.9931033643915164e-05, + "loss": 0.5462, + "step": 749 + }, + { + "epoch": 0.66, + "learning_rate": 1.9930697201991277e-05, + "loss": 0.6001, + "step": 750 + }, + { + "epoch": 0.66, + "learning_rate": 1.9930359944275978e-05, + "loss": 0.5825, + "step": 751 + }, + { + "epoch": 0.67, + "learning_rate": 1.993002187079698e-05, + "loss": 0.5683, + "step": 752 + }, + { + "epoch": 0.67, + "learning_rate": 1.992968298158205e-05, + "loss": 0.5545, + "step": 753 + }, + { + "epoch": 0.67, + "learning_rate": 1.992934327665903e-05, + "loss": 0.5594, + "step": 754 + }, + { + "epoch": 0.67, + "learning_rate": 1.9929002756055822e-05, + "loss": 0.548, + "step": 755 + }, + { + "epoch": 0.67, + "learning_rate": 1.9928661419800406e-05, + "loss": 0.5519, + "step": 756 + }, + { + "epoch": 0.67, + "learning_rate": 1.9928319267920816e-05, + "loss": 0.5755, + "step": 757 + }, + { + "epoch": 0.67, + "learning_rate": 1.9927976300445162e-05, + "loss": 0.5423, + "step": 758 + }, + { + "epoch": 0.67, + "learning_rate": 1.9927632517401622e-05, + "loss": 0.5598, + "step": 759 + }, + { + "epoch": 0.67, + "learning_rate": 1.992728791881843e-05, + "loss": 0.5693, + "step": 760 + }, + { + "epoch": 0.67, + "learning_rate": 1.9926942504723896e-05, + "loss": 0.5773, + "step": 761 + }, + { + "epoch": 0.67, + "learning_rate": 1.9926596275146397e-05, + "loss": 0.5625, + "step": 762 + }, + { + "epoch": 0.67, + "learning_rate": 1.992624923011438e-05, + "loss": 0.5667, + "step": 763 + }, + { + "epoch": 0.68, + "learning_rate": 1.9925901369656343e-05, + "loss": 0.5967, + "step": 764 + }, + { + "epoch": 0.68, + "learning_rate": 1.9925552693800872e-05, + "loss": 0.5623, + "step": 765 + }, + { + "epoch": 0.68, + "learning_rate": 1.9925203202576605e-05, + "loss": 0.545, + "step": 766 + }, + { + "epoch": 0.68, + "learning_rate": 1.9924852896012253e-05, + "loss": 0.5727, + "step": 767 + }, + { + "epoch": 0.68, + "learning_rate": 1.9924501774136592e-05, + "loss": 0.5713, + "step": 768 + }, + { + "epoch": 0.68, + "learning_rate": 1.9924149836978475e-05, + "loss": 0.5393, + "step": 769 + }, + { + "epoch": 0.68, + "learning_rate": 1.99237970845668e-05, + "loss": 0.5589, + "step": 770 + }, + { + "epoch": 0.68, + "learning_rate": 1.9923443516930554e-05, + "loss": 0.5434, + "step": 771 + }, + { + "epoch": 0.68, + "learning_rate": 1.9923089134098776e-05, + "loss": 0.5335, + "step": 772 + }, + { + "epoch": 0.68, + "learning_rate": 1.9922733936100584e-05, + "loss": 0.5835, + "step": 773 + }, + { + "epoch": 0.68, + "learning_rate": 1.9922377922965156e-05, + "loss": 0.553, + "step": 774 + }, + { + "epoch": 0.69, + "learning_rate": 1.992202109472173e-05, + "loss": 0.5537, + "step": 775 + }, + { + "epoch": 0.69, + "learning_rate": 1.992166345139963e-05, + "loss": 0.5606, + "step": 776 + }, + { + "epoch": 0.69, + "learning_rate": 1.992130499302823e-05, + "loss": 0.5756, + "step": 777 + }, + { + "epoch": 0.69, + "learning_rate": 1.9920945719636977e-05, + "loss": 0.5911, + "step": 778 + }, + { + "epoch": 0.69, + "learning_rate": 1.9920585631255386e-05, + "loss": 0.5433, + "step": 779 + }, + { + "epoch": 0.69, + "learning_rate": 1.9920224727913035e-05, + "loss": 0.5513, + "step": 780 + }, + { + "epoch": 0.69, + "learning_rate": 1.991986300963957e-05, + "loss": 0.5411, + "step": 781 + }, + { + "epoch": 0.69, + "learning_rate": 1.9919500476464718e-05, + "loss": 0.5379, + "step": 782 + }, + { + "epoch": 0.69, + "learning_rate": 1.991913712841825e-05, + "loss": 0.5686, + "step": 783 + }, + { + "epoch": 0.69, + "learning_rate": 1.9918772965530014e-05, + "loss": 0.5668, + "step": 784 + }, + { + "epoch": 0.69, + "learning_rate": 1.9918407987829926e-05, + "loss": 0.5593, + "step": 785 + }, + { + "epoch": 0.7, + "learning_rate": 1.9918042195347973e-05, + "loss": 0.5544, + "step": 786 + }, + { + "epoch": 0.7, + "learning_rate": 1.9917675588114202e-05, + "loss": 0.5766, + "step": 787 + }, + { + "epoch": 0.7, + "learning_rate": 1.9917308166158728e-05, + "loss": 0.5788, + "step": 788 + }, + { + "epoch": 0.7, + "learning_rate": 1.9916939929511733e-05, + "loss": 0.579, + "step": 789 + }, + { + "epoch": 0.7, + "learning_rate": 1.9916570878203468e-05, + "loss": 0.5544, + "step": 790 + }, + { + "epoch": 0.7, + "learning_rate": 1.9916201012264255e-05, + "loss": 0.5648, + "step": 791 + }, + { + "epoch": 0.7, + "learning_rate": 1.991583033172447e-05, + "loss": 0.5394, + "step": 792 + }, + { + "epoch": 0.7, + "learning_rate": 1.991545883661457e-05, + "loss": 0.5511, + "step": 793 + }, + { + "epoch": 0.7, + "learning_rate": 1.991508652696507e-05, + "loss": 0.5682, + "step": 794 + }, + { + "epoch": 0.7, + "learning_rate": 1.9914713402806552e-05, + "loss": 0.5852, + "step": 795 + }, + { + "epoch": 0.7, + "learning_rate": 1.991433946416967e-05, + "loss": 0.59, + "step": 796 + }, + { + "epoch": 0.71, + "learning_rate": 1.9913964711085146e-05, + "loss": 0.5535, + "step": 797 + }, + { + "epoch": 0.71, + "learning_rate": 1.9913589143583762e-05, + "loss": 0.5537, + "step": 798 + }, + { + "epoch": 0.71, + "learning_rate": 1.991321276169637e-05, + "loss": 0.522, + "step": 799 + }, + { + "epoch": 0.71, + "learning_rate": 1.9912835565453892e-05, + "loss": 0.5554, + "step": 800 + }, + { + "epoch": 0.71, + "learning_rate": 1.991245755488731e-05, + "loss": 0.5948, + "step": 801 + }, + { + "epoch": 0.71, + "learning_rate": 1.991207873002768e-05, + "loss": 0.5619, + "step": 802 + }, + { + "epoch": 0.71, + "learning_rate": 1.991169909090612e-05, + "loss": 0.5695, + "step": 803 + }, + { + "epoch": 0.71, + "learning_rate": 1.9911318637553818e-05, + "loss": 0.5473, + "step": 804 + }, + { + "epoch": 0.71, + "learning_rate": 1.9910937370002027e-05, + "loss": 0.5617, + "step": 805 + }, + { + "epoch": 0.71, + "learning_rate": 1.991055528828207e-05, + "loss": 0.5625, + "step": 806 + }, + { + "epoch": 0.71, + "learning_rate": 1.9910172392425328e-05, + "loss": 0.5588, + "step": 807 + }, + { + "epoch": 0.71, + "learning_rate": 1.990978868246326e-05, + "loss": 0.5642, + "step": 808 + }, + { + "epoch": 0.72, + "learning_rate": 1.990940415842739e-05, + "loss": 0.5497, + "step": 809 + }, + { + "epoch": 0.72, + "learning_rate": 1.99090188203493e-05, + "loss": 0.5524, + "step": 810 + }, + { + "epoch": 0.72, + "learning_rate": 1.990863266826065e-05, + "loss": 0.5632, + "step": 811 + }, + { + "epoch": 0.72, + "learning_rate": 1.9908245702193156e-05, + "loss": 0.5605, + "step": 812 + }, + { + "epoch": 0.72, + "learning_rate": 1.9907857922178612e-05, + "loss": 0.5919, + "step": 813 + }, + { + "epoch": 0.72, + "learning_rate": 1.9907469328248873e-05, + "loss": 0.5324, + "step": 814 + }, + { + "epoch": 0.72, + "learning_rate": 1.9907079920435857e-05, + "loss": 0.5578, + "step": 815 + }, + { + "epoch": 0.72, + "learning_rate": 1.990668969877156e-05, + "loss": 0.5575, + "step": 816 + }, + { + "epoch": 0.72, + "learning_rate": 1.9906298663288032e-05, + "loss": 0.5412, + "step": 817 + }, + { + "epoch": 0.72, + "learning_rate": 1.9905906814017397e-05, + "loss": 0.558, + "step": 818 + }, + { + "epoch": 0.72, + "learning_rate": 1.990551415099185e-05, + "loss": 0.5498, + "step": 819 + }, + { + "epoch": 0.73, + "learning_rate": 1.9905120674243642e-05, + "loss": 0.5579, + "step": 820 + }, + { + "epoch": 0.73, + "learning_rate": 1.9904726383805096e-05, + "loss": 0.5638, + "step": 821 + }, + { + "epoch": 0.73, + "learning_rate": 1.990433127970861e-05, + "loss": 0.5739, + "step": 822 + }, + { + "epoch": 0.73, + "learning_rate": 1.990393536198663e-05, + "loss": 0.5515, + "step": 823 + }, + { + "epoch": 0.73, + "learning_rate": 1.9903538630671687e-05, + "loss": 0.5689, + "step": 824 + }, + { + "epoch": 0.73, + "learning_rate": 1.9903141085796375e-05, + "loss": 0.5172, + "step": 825 + }, + { + "epoch": 0.73, + "learning_rate": 1.9902742727393345e-05, + "loss": 0.5557, + "step": 826 + }, + { + "epoch": 0.73, + "learning_rate": 1.9902343555495322e-05, + "loss": 0.5713, + "step": 827 + }, + { + "epoch": 0.73, + "learning_rate": 1.9901943570135103e-05, + "loss": 0.5574, + "step": 828 + }, + { + "epoch": 0.73, + "learning_rate": 1.990154277134554e-05, + "loss": 0.5789, + "step": 829 + }, + { + "epoch": 0.73, + "learning_rate": 1.990114115915956e-05, + "loss": 0.556, + "step": 830 + }, + { + "epoch": 0.74, + "learning_rate": 1.9900738733610158e-05, + "loss": 0.575, + "step": 831 + }, + { + "epoch": 0.74, + "learning_rate": 1.9900335494730388e-05, + "loss": 0.5672, + "step": 832 + }, + { + "epoch": 0.74, + "learning_rate": 1.989993144255338e-05, + "loss": 0.548, + "step": 833 + }, + { + "epoch": 0.74, + "learning_rate": 1.989952657711232e-05, + "loss": 0.5904, + "step": 834 + }, + { + "epoch": 0.74, + "learning_rate": 1.9899120898440473e-05, + "loss": 0.5643, + "step": 835 + }, + { + "epoch": 0.74, + "learning_rate": 1.989871440657116e-05, + "loss": 0.5281, + "step": 836 + }, + { + "epoch": 0.74, + "learning_rate": 1.989830710153778e-05, + "loss": 0.5705, + "step": 837 + }, + { + "epoch": 0.74, + "learning_rate": 1.989789898337379e-05, + "loss": 0.5692, + "step": 838 + }, + { + "epoch": 0.74, + "learning_rate": 1.989749005211271e-05, + "loss": 0.5478, + "step": 839 + }, + { + "epoch": 0.74, + "learning_rate": 1.9897080307788142e-05, + "loss": 0.5302, + "step": 840 + }, + { + "epoch": 0.74, + "learning_rate": 1.989666975043374e-05, + "loss": 0.572, + "step": 841 + }, + { + "epoch": 0.74, + "learning_rate": 1.9896258380083233e-05, + "loss": 0.5492, + "step": 842 + }, + { + "epoch": 0.75, + "learning_rate": 1.989584619677041e-05, + "loss": 0.5458, + "step": 843 + }, + { + "epoch": 0.75, + "learning_rate": 1.989543320052914e-05, + "loss": 0.5594, + "step": 844 + }, + { + "epoch": 0.75, + "learning_rate": 1.9895019391393346e-05, + "loss": 0.5517, + "step": 845 + }, + { + "epoch": 0.75, + "learning_rate": 1.9894604769397023e-05, + "loss": 0.5692, + "step": 846 + }, + { + "epoch": 0.75, + "learning_rate": 1.9894189334574223e-05, + "loss": 0.5503, + "step": 847 + }, + { + "epoch": 0.75, + "learning_rate": 1.9893773086959084e-05, + "loss": 0.5973, + "step": 848 + }, + { + "epoch": 0.75, + "learning_rate": 1.9893356026585797e-05, + "loss": 0.565, + "step": 849 + }, + { + "epoch": 0.75, + "learning_rate": 1.989293815348862e-05, + "loss": 0.5319, + "step": 850 + }, + { + "epoch": 0.75, + "learning_rate": 1.989251946770188e-05, + "loss": 0.5588, + "step": 851 + }, + { + "epoch": 0.75, + "learning_rate": 1.989209996925998e-05, + "loss": 0.5539, + "step": 852 + }, + { + "epoch": 0.75, + "learning_rate": 1.989167965819737e-05, + "loss": 0.5547, + "step": 853 + }, + { + "epoch": 0.76, + "learning_rate": 1.9891258534548587e-05, + "loss": 0.5463, + "step": 854 + }, + { + "epoch": 0.76, + "learning_rate": 1.989083659834822e-05, + "loss": 0.559, + "step": 855 + }, + { + "epoch": 0.76, + "learning_rate": 1.989041384963093e-05, + "loss": 0.5706, + "step": 856 + }, + { + "epoch": 0.76, + "learning_rate": 1.988999028843145e-05, + "loss": 0.5505, + "step": 857 + }, + { + "epoch": 0.76, + "learning_rate": 1.988956591478457e-05, + "loss": 0.5508, + "step": 858 + }, + { + "epoch": 0.76, + "learning_rate": 1.9889140728725157e-05, + "loss": 0.5486, + "step": 859 + }, + { + "epoch": 0.76, + "learning_rate": 1.988871473028813e-05, + "loss": 0.5633, + "step": 860 + }, + { + "epoch": 0.76, + "learning_rate": 1.9888287919508496e-05, + "loss": 0.5719, + "step": 861 + }, + { + "epoch": 0.76, + "learning_rate": 1.988786029642131e-05, + "loss": 0.5337, + "step": 862 + }, + { + "epoch": 0.76, + "learning_rate": 1.98874318610617e-05, + "loss": 0.5486, + "step": 863 + }, + { + "epoch": 0.76, + "learning_rate": 1.9887002613464866e-05, + "loss": 0.5361, + "step": 864 + }, + { + "epoch": 0.77, + "learning_rate": 1.9886572553666065e-05, + "loss": 0.5356, + "step": 865 + }, + { + "epoch": 0.77, + "learning_rate": 1.9886141681700625e-05, + "loss": 0.5412, + "step": 866 + }, + { + "epoch": 0.77, + "learning_rate": 1.988570999760395e-05, + "loss": 0.5659, + "step": 867 + }, + { + "epoch": 0.77, + "learning_rate": 1.988527750141149e-05, + "loss": 0.5409, + "step": 868 + }, + { + "epoch": 0.77, + "learning_rate": 1.9884844193158786e-05, + "loss": 0.588, + "step": 869 + }, + { + "epoch": 0.77, + "learning_rate": 1.9884410072881425e-05, + "loss": 0.5827, + "step": 870 + }, + { + "epoch": 0.77, + "learning_rate": 1.9883975140615072e-05, + "loss": 0.5898, + "step": 871 + }, + { + "epoch": 0.77, + "learning_rate": 1.9883539396395458e-05, + "loss": 0.546, + "step": 872 + }, + { + "epoch": 0.77, + "learning_rate": 1.9883102840258376e-05, + "loss": 0.5558, + "step": 873 + }, + { + "epoch": 0.77, + "learning_rate": 1.988266547223969e-05, + "loss": 0.5465, + "step": 874 + }, + { + "epoch": 0.77, + "learning_rate": 1.9882227292375327e-05, + "loss": 0.5377, + "step": 875 + }, + { + "epoch": 0.77, + "learning_rate": 1.9881788300701284e-05, + "loss": 0.5489, + "step": 876 + }, + { + "epoch": 0.78, + "learning_rate": 1.9881348497253623e-05, + "loss": 0.559, + "step": 877 + }, + { + "epoch": 0.78, + "learning_rate": 1.9880907882068477e-05, + "loss": 0.5618, + "step": 878 + }, + { + "epoch": 0.78, + "learning_rate": 1.9880466455182035e-05, + "loss": 0.5511, + "step": 879 + }, + { + "epoch": 0.78, + "learning_rate": 1.9880024216630565e-05, + "loss": 0.5203, + "step": 880 + }, + { + "epoch": 0.78, + "learning_rate": 1.9879581166450394e-05, + "loss": 0.5515, + "step": 881 + }, + { + "epoch": 0.78, + "learning_rate": 1.987913730467792e-05, + "loss": 0.5342, + "step": 882 + }, + { + "epoch": 0.78, + "learning_rate": 1.9878692631349605e-05, + "loss": 0.5371, + "step": 883 + }, + { + "epoch": 0.78, + "learning_rate": 1.9878247146501976e-05, + "loss": 0.5394, + "step": 884 + }, + { + "epoch": 0.78, + "learning_rate": 1.9877800850171626e-05, + "loss": 0.5789, + "step": 885 + }, + { + "epoch": 0.78, + "learning_rate": 1.9877353742395225e-05, + "loss": 0.5527, + "step": 886 + }, + { + "epoch": 0.78, + "learning_rate": 1.98769058232095e-05, + "loss": 0.5469, + "step": 887 + }, + { + "epoch": 0.79, + "learning_rate": 1.9876457092651243e-05, + "loss": 0.5419, + "step": 888 + }, + { + "epoch": 0.79, + "learning_rate": 1.9876007550757322e-05, + "loss": 0.5677, + "step": 889 + }, + { + "epoch": 0.79, + "learning_rate": 1.987555719756466e-05, + "loss": 0.5617, + "step": 890 + }, + { + "epoch": 0.79, + "learning_rate": 1.9875106033110262e-05, + "loss": 0.5399, + "step": 891 + }, + { + "epoch": 0.79, + "learning_rate": 1.987465405743118e-05, + "loss": 0.574, + "step": 892 + }, + { + "epoch": 0.79, + "learning_rate": 1.987420127056455e-05, + "loss": 0.5556, + "step": 893 + }, + { + "epoch": 0.79, + "learning_rate": 1.9873747672547563e-05, + "loss": 0.5751, + "step": 894 + }, + { + "epoch": 0.79, + "learning_rate": 1.9873293263417485e-05, + "loss": 0.5481, + "step": 895 + }, + { + "epoch": 0.79, + "learning_rate": 1.987283804321164e-05, + "loss": 0.5889, + "step": 896 + }, + { + "epoch": 0.79, + "learning_rate": 1.9872382011967434e-05, + "loss": 0.5296, + "step": 897 + }, + { + "epoch": 0.79, + "learning_rate": 1.9871925169722323e-05, + "loss": 0.5943, + "step": 898 + }, + { + "epoch": 0.8, + "learning_rate": 1.987146751651383e-05, + "loss": 0.5498, + "step": 899 + }, + { + "epoch": 0.8, + "learning_rate": 1.987100905237956e-05, + "loss": 0.5758, + "step": 900 + }, + { + "epoch": 0.8, + "learning_rate": 1.9870549777357172e-05, + "loss": 0.5604, + "step": 901 + }, + { + "epoch": 0.8, + "learning_rate": 1.9870089691484387e-05, + "loss": 0.5176, + "step": 902 + }, + { + "epoch": 0.8, + "learning_rate": 1.9869628794799018e-05, + "loss": 0.57, + "step": 903 + }, + { + "epoch": 0.8, + "learning_rate": 1.9869167087338908e-05, + "loss": 0.5458, + "step": 904 + }, + { + "epoch": 0.8, + "learning_rate": 1.9868704569141996e-05, + "loss": 0.5548, + "step": 905 + }, + { + "epoch": 0.8, + "learning_rate": 1.986824124024628e-05, + "loss": 0.5353, + "step": 906 + }, + { + "epoch": 0.8, + "learning_rate": 1.9867777100689812e-05, + "loss": 0.5502, + "step": 907 + }, + { + "epoch": 0.8, + "learning_rate": 1.9867312150510726e-05, + "loss": 0.5748, + "step": 908 + }, + { + "epoch": 0.8, + "learning_rate": 1.986684638974721e-05, + "loss": 0.5027, + "step": 909 + }, + { + "epoch": 0.8, + "learning_rate": 1.986637981843754e-05, + "loss": 0.5456, + "step": 910 + }, + { + "epoch": 0.81, + "learning_rate": 1.9865912436620035e-05, + "loss": 0.56, + "step": 911 + }, + { + "epoch": 0.81, + "learning_rate": 1.9865444244333086e-05, + "loss": 0.5658, + "step": 912 + }, + { + "epoch": 0.81, + "learning_rate": 1.986497524161516e-05, + "loss": 0.5268, + "step": 913 + }, + { + "epoch": 0.81, + "learning_rate": 1.9864505428504786e-05, + "loss": 0.5752, + "step": 914 + }, + { + "epoch": 0.81, + "learning_rate": 1.9864034805040555e-05, + "loss": 0.5658, + "step": 915 + }, + { + "epoch": 0.81, + "learning_rate": 1.9863563371261127e-05, + "loss": 0.5376, + "step": 916 + }, + { + "epoch": 0.81, + "learning_rate": 1.9863091127205235e-05, + "loss": 0.5567, + "step": 917 + }, + { + "epoch": 0.81, + "learning_rate": 1.986261807291167e-05, + "loss": 0.5354, + "step": 918 + }, + { + "epoch": 0.81, + "learning_rate": 1.986214420841929e-05, + "loss": 0.5715, + "step": 919 + }, + { + "epoch": 0.81, + "learning_rate": 1.986166953376702e-05, + "loss": 0.547, + "step": 920 + }, + { + "epoch": 0.81, + "learning_rate": 1.9861194048993865e-05, + "loss": 0.5602, + "step": 921 + }, + { + "epoch": 0.82, + "learning_rate": 1.9860717754138875e-05, + "loss": 0.5425, + "step": 922 + }, + { + "epoch": 0.82, + "learning_rate": 1.9860240649241182e-05, + "loss": 0.5729, + "step": 923 + }, + { + "epoch": 0.82, + "learning_rate": 1.985976273433998e-05, + "loss": 0.5463, + "step": 924 + }, + { + "epoch": 0.82, + "learning_rate": 1.9859284009474522e-05, + "loss": 0.5432, + "step": 925 + }, + { + "epoch": 0.82, + "learning_rate": 1.9858804474684143e-05, + "loss": 0.5729, + "step": 926 + }, + { + "epoch": 0.82, + "learning_rate": 1.985832413000823e-05, + "loss": 0.5763, + "step": 927 + }, + { + "epoch": 0.82, + "learning_rate": 1.9857842975486246e-05, + "loss": 0.5327, + "step": 928 + }, + { + "epoch": 0.82, + "learning_rate": 1.9857361011157715e-05, + "loss": 0.5563, + "step": 929 + }, + { + "epoch": 0.82, + "learning_rate": 1.9856878237062234e-05, + "loss": 0.5424, + "step": 930 + }, + { + "epoch": 0.82, + "learning_rate": 1.9856394653239458e-05, + "loss": 0.5497, + "step": 931 + }, + { + "epoch": 0.82, + "learning_rate": 1.985591025972911e-05, + "loss": 0.5631, + "step": 932 + }, + { + "epoch": 0.83, + "learning_rate": 1.985542505657099e-05, + "loss": 0.5655, + "step": 933 + }, + { + "epoch": 0.83, + "learning_rate": 1.985493904380495e-05, + "loss": 0.5129, + "step": 934 + }, + { + "epoch": 0.83, + "learning_rate": 1.985445222147092e-05, + "loss": 0.5531, + "step": 935 + }, + { + "epoch": 0.83, + "learning_rate": 1.985396458960889e-05, + "loss": 0.5653, + "step": 936 + }, + { + "epoch": 0.83, + "learning_rate": 1.985347614825891e-05, + "loss": 0.5363, + "step": 937 + }, + { + "epoch": 0.83, + "learning_rate": 1.985298689746112e-05, + "loss": 0.5676, + "step": 938 + }, + { + "epoch": 0.83, + "learning_rate": 1.9852496837255703e-05, + "loss": 0.546, + "step": 939 + }, + { + "epoch": 0.83, + "learning_rate": 1.9852005967682914e-05, + "loss": 0.5527, + "step": 940 + }, + { + "epoch": 0.83, + "learning_rate": 1.985151428878308e-05, + "loss": 0.5416, + "step": 941 + }, + { + "epoch": 0.83, + "learning_rate": 1.9851021800596593e-05, + "loss": 0.5763, + "step": 942 + }, + { + "epoch": 0.83, + "learning_rate": 1.985052850316391e-05, + "loss": 0.5349, + "step": 943 + }, + { + "epoch": 0.84, + "learning_rate": 1.9850034396525553e-05, + "loss": 0.5218, + "step": 944 + }, + { + "epoch": 0.84, + "learning_rate": 1.9849539480722115e-05, + "loss": 0.557, + "step": 945 + }, + { + "epoch": 0.84, + "learning_rate": 1.9849043755794245e-05, + "loss": 0.5213, + "step": 946 + }, + { + "epoch": 0.84, + "learning_rate": 1.9848547221782675e-05, + "loss": 0.5454, + "step": 947 + }, + { + "epoch": 0.84, + "learning_rate": 1.9848049878728193e-05, + "loss": 0.5378, + "step": 948 + }, + { + "epoch": 0.84, + "learning_rate": 1.984755172667165e-05, + "loss": 0.5437, + "step": 949 + }, + { + "epoch": 0.84, + "learning_rate": 1.9847052765653973e-05, + "loss": 0.5365, + "step": 950 + }, + { + "epoch": 0.84, + "learning_rate": 1.9846552995716147e-05, + "loss": 0.5607, + "step": 951 + }, + { + "epoch": 0.84, + "learning_rate": 1.984605241689923e-05, + "loss": 0.5871, + "step": 952 + }, + { + "epoch": 0.84, + "learning_rate": 1.9845551029244342e-05, + "loss": 0.5394, + "step": 953 + }, + { + "epoch": 0.84, + "learning_rate": 1.9845048832792675e-05, + "loss": 0.5348, + "step": 954 + }, + { + "epoch": 0.84, + "learning_rate": 1.9844545827585483e-05, + "loss": 0.5709, + "step": 955 + }, + { + "epoch": 0.85, + "learning_rate": 1.984404201366408e-05, + "loss": 0.5268, + "step": 956 + }, + { + "epoch": 0.85, + "learning_rate": 1.984353739106986e-05, + "loss": 0.5631, + "step": 957 + }, + { + "epoch": 0.85, + "learning_rate": 1.984303195984428e-05, + "loss": 0.5509, + "step": 958 + }, + { + "epoch": 0.85, + "learning_rate": 1.9842525720028854e-05, + "loss": 0.5913, + "step": 959 + }, + { + "epoch": 0.85, + "learning_rate": 1.9842018671665167e-05, + "loss": 0.5569, + "step": 960 + }, + { + "epoch": 0.85, + "learning_rate": 1.984151081479488e-05, + "loss": 0.5637, + "step": 961 + }, + { + "epoch": 0.85, + "learning_rate": 1.984100214945971e-05, + "loss": 0.5646, + "step": 962 + }, + { + "epoch": 0.85, + "learning_rate": 1.984049267570144e-05, + "loss": 0.5504, + "step": 963 + }, + { + "epoch": 0.85, + "learning_rate": 1.9839982393561926e-05, + "loss": 0.5564, + "step": 964 + }, + { + "epoch": 0.85, + "learning_rate": 1.9839471303083082e-05, + "loss": 0.5324, + "step": 965 + }, + { + "epoch": 0.85, + "learning_rate": 1.98389594043069e-05, + "loss": 0.569, + "step": 966 + }, + { + "epoch": 0.86, + "learning_rate": 1.9838446697275424e-05, + "loss": 0.5371, + "step": 967 + }, + { + "epoch": 0.86, + "learning_rate": 1.983793318203078e-05, + "loss": 0.5211, + "step": 968 + }, + { + "epoch": 0.86, + "learning_rate": 1.9837418858615147e-05, + "loss": 0.5261, + "step": 969 + }, + { + "epoch": 0.86, + "learning_rate": 1.983690372707078e-05, + "loss": 0.544, + "step": 970 + }, + { + "epoch": 0.86, + "learning_rate": 1.983638778743999e-05, + "loss": 0.556, + "step": 971 + }, + { + "epoch": 0.86, + "learning_rate": 1.983587103976517e-05, + "loss": 0.5263, + "step": 972 + }, + { + "epoch": 0.86, + "learning_rate": 1.9835353484088763e-05, + "loss": 0.5543, + "step": 973 + }, + { + "epoch": 0.86, + "learning_rate": 1.9834835120453287e-05, + "loss": 0.5334, + "step": 974 + }, + { + "epoch": 0.86, + "learning_rate": 1.9834315948901322e-05, + "loss": 0.5636, + "step": 975 + }, + { + "epoch": 0.86, + "learning_rate": 1.9833795969475523e-05, + "loss": 0.56, + "step": 976 + }, + { + "epoch": 0.86, + "learning_rate": 1.98332751822186e-05, + "loss": 0.5511, + "step": 977 + }, + { + "epoch": 0.87, + "learning_rate": 1.9832753587173338e-05, + "loss": 0.5524, + "step": 978 + }, + { + "epoch": 0.87, + "learning_rate": 1.9832231184382587e-05, + "loss": 0.5553, + "step": 979 + }, + { + "epoch": 0.87, + "learning_rate": 1.9831707973889254e-05, + "loss": 0.5714, + "step": 980 + }, + { + "epoch": 0.87, + "learning_rate": 1.983118395573633e-05, + "loss": 0.5461, + "step": 981 + }, + { + "epoch": 0.87, + "learning_rate": 1.9830659129966853e-05, + "loss": 0.5332, + "step": 982 + }, + { + "epoch": 0.87, + "learning_rate": 1.9830133496623944e-05, + "loss": 0.5353, + "step": 983 + }, + { + "epoch": 0.87, + "learning_rate": 1.982960705575078e-05, + "loss": 0.5695, + "step": 984 + }, + { + "epoch": 0.87, + "learning_rate": 1.9829079807390608e-05, + "loss": 0.5409, + "step": 985 + }, + { + "epoch": 0.87, + "learning_rate": 1.9828551751586738e-05, + "loss": 0.571, + "step": 986 + }, + { + "epoch": 0.87, + "learning_rate": 1.9828022888382552e-05, + "loss": 0.567, + "step": 987 + }, + { + "epoch": 0.87, + "learning_rate": 1.9827493217821496e-05, + "loss": 0.5165, + "step": 988 + }, + { + "epoch": 0.87, + "learning_rate": 1.9826962739947076e-05, + "loss": 0.573, + "step": 989 + }, + { + "epoch": 0.88, + "learning_rate": 1.9826431454802874e-05, + "loss": 0.5505, + "step": 990 + }, + { + "epoch": 0.88, + "learning_rate": 1.9825899362432537e-05, + "loss": 0.5637, + "step": 991 + }, + { + "epoch": 0.88, + "learning_rate": 1.982536646287977e-05, + "loss": 0.5546, + "step": 992 + }, + { + "epoch": 0.88, + "learning_rate": 1.9824832756188353e-05, + "loss": 0.578, + "step": 993 + }, + { + "epoch": 0.88, + "learning_rate": 1.9824298242402127e-05, + "loss": 0.563, + "step": 994 + }, + { + "epoch": 0.88, + "learning_rate": 1.9823762921565003e-05, + "loss": 0.5483, + "step": 995 + }, + { + "epoch": 0.88, + "learning_rate": 1.982322679372096e-05, + "loss": 0.5376, + "step": 996 + }, + { + "epoch": 0.88, + "learning_rate": 1.9822689858914037e-05, + "loss": 0.539, + "step": 997 + }, + { + "epoch": 0.88, + "learning_rate": 1.9822152117188336e-05, + "loss": 0.5617, + "step": 998 + }, + { + "epoch": 0.88, + "learning_rate": 1.9821613568588046e-05, + "loss": 0.5504, + "step": 999 + }, + { + "epoch": 0.88, + "learning_rate": 1.9821074213157398e-05, + "loss": 0.5418, + "step": 1000 + }, + { + "epoch": 0.89, + "learning_rate": 1.9820534050940698e-05, + "loss": 0.5499, + "step": 1001 + }, + { + "epoch": 0.89, + "learning_rate": 1.9819993081982324e-05, + "loss": 0.5376, + "step": 1002 + }, + { + "epoch": 0.89, + "learning_rate": 1.9819451306326712e-05, + "loss": 0.5902, + "step": 1003 + }, + { + "epoch": 0.89, + "learning_rate": 1.9818908724018376e-05, + "loss": 0.5576, + "step": 1004 + }, + { + "epoch": 0.89, + "learning_rate": 1.9818365335101878e-05, + "loss": 0.5575, + "step": 1005 + }, + { + "epoch": 0.89, + "learning_rate": 1.981782113962186e-05, + "loss": 0.56, + "step": 1006 + }, + { + "epoch": 0.89, + "learning_rate": 1.9817276137623032e-05, + "loss": 0.5933, + "step": 1007 + }, + { + "epoch": 0.89, + "learning_rate": 1.981673032915016e-05, + "loss": 0.5449, + "step": 1008 + }, + { + "epoch": 0.89, + "learning_rate": 1.981618371424808e-05, + "loss": 0.5403, + "step": 1009 + }, + { + "epoch": 0.89, + "learning_rate": 1.98156362929617e-05, + "loss": 0.5463, + "step": 1010 + }, + { + "epoch": 0.89, + "learning_rate": 1.9815088065335988e-05, + "loss": 0.5776, + "step": 1011 + }, + { + "epoch": 0.9, + "learning_rate": 1.981453903141598e-05, + "loss": 0.5431, + "step": 1012 + }, + { + "epoch": 0.9, + "learning_rate": 1.981398919124678e-05, + "loss": 0.5399, + "step": 1013 + }, + { + "epoch": 0.9, + "learning_rate": 1.981343854487355e-05, + "loss": 0.5625, + "step": 1014 + }, + { + "epoch": 0.9, + "learning_rate": 1.9812887092341532e-05, + "loss": 0.5468, + "step": 1015 + }, + { + "epoch": 0.9, + "learning_rate": 1.9812334833696024e-05, + "loss": 0.5671, + "step": 1016 + }, + { + "epoch": 0.9, + "learning_rate": 1.9811781768982392e-05, + "loss": 0.5445, + "step": 1017 + }, + { + "epoch": 0.9, + "learning_rate": 1.9811227898246072e-05, + "loss": 0.5079, + "step": 1018 + }, + { + "epoch": 0.9, + "learning_rate": 1.9810673221532563e-05, + "loss": 0.5626, + "step": 1019 + }, + { + "epoch": 0.9, + "learning_rate": 1.981011773888743e-05, + "loss": 0.5606, + "step": 1020 + }, + { + "epoch": 0.9, + "learning_rate": 1.9809561450356306e-05, + "loss": 0.5463, + "step": 1021 + }, + { + "epoch": 0.9, + "learning_rate": 1.9809004355984892e-05, + "loss": 0.5227, + "step": 1022 + }, + { + "epoch": 0.9, + "learning_rate": 1.9808446455818943e-05, + "loss": 0.5142, + "step": 1023 + }, + { + "epoch": 0.91, + "learning_rate": 1.9807887749904298e-05, + "loss": 0.5623, + "step": 1024 + }, + { + "epoch": 0.91, + "learning_rate": 1.980732823828685e-05, + "loss": 0.5372, + "step": 1025 + }, + { + "epoch": 0.91, + "learning_rate": 1.980676792101257e-05, + "loss": 0.5566, + "step": 1026 + }, + { + "epoch": 0.91, + "learning_rate": 1.9806206798127477e-05, + "loss": 0.5388, + "step": 1027 + }, + { + "epoch": 0.91, + "learning_rate": 1.9805644869677668e-05, + "loss": 0.5518, + "step": 1028 + }, + { + "epoch": 0.91, + "learning_rate": 1.9805082135709307e-05, + "loss": 0.5417, + "step": 1029 + }, + { + "epoch": 0.91, + "learning_rate": 1.9804518596268625e-05, + "loss": 0.5567, + "step": 1030 + }, + { + "epoch": 0.91, + "learning_rate": 1.980395425140191e-05, + "loss": 0.5494, + "step": 1031 + }, + { + "epoch": 0.91, + "learning_rate": 1.9803389101155525e-05, + "loss": 0.5383, + "step": 1032 + }, + { + "epoch": 0.91, + "learning_rate": 1.9802823145575893e-05, + "loss": 0.5576, + "step": 1033 + }, + { + "epoch": 0.91, + "learning_rate": 1.980225638470951e-05, + "loss": 0.566, + "step": 1034 + }, + { + "epoch": 0.92, + "learning_rate": 1.9801688818602938e-05, + "loss": 0.5445, + "step": 1035 + }, + { + "epoch": 0.92, + "learning_rate": 1.9801120447302792e-05, + "loss": 0.5304, + "step": 1036 + }, + { + "epoch": 0.92, + "learning_rate": 1.9800551270855774e-05, + "loss": 0.5425, + "step": 1037 + }, + { + "epoch": 0.92, + "learning_rate": 1.979998128930863e-05, + "loss": 0.5415, + "step": 1038 + }, + { + "epoch": 0.92, + "learning_rate": 1.979941050270819e-05, + "loss": 0.5537, + "step": 1039 + }, + { + "epoch": 0.92, + "learning_rate": 1.979883891110134e-05, + "loss": 0.5403, + "step": 1040 + }, + { + "epoch": 0.92, + "learning_rate": 1.979826651453504e-05, + "loss": 0.5386, + "step": 1041 + }, + { + "epoch": 0.92, + "learning_rate": 1.9797693313056302e-05, + "loss": 0.5229, + "step": 1042 + }, + { + "epoch": 0.92, + "learning_rate": 1.9797119306712225e-05, + "loss": 0.5563, + "step": 1043 + }, + { + "epoch": 0.92, + "learning_rate": 1.9796544495549958e-05, + "loss": 0.5395, + "step": 1044 + }, + { + "epoch": 0.92, + "learning_rate": 1.9795968879616713e-05, + "loss": 0.554, + "step": 1045 + }, + { + "epoch": 0.93, + "learning_rate": 1.9795392458959793e-05, + "loss": 0.5328, + "step": 1046 + }, + { + "epoch": 0.93, + "learning_rate": 1.9794815233626534e-05, + "loss": 0.5291, + "step": 1047 + }, + { + "epoch": 0.93, + "learning_rate": 1.979423720366436e-05, + "loss": 0.5645, + "step": 1048 + }, + { + "epoch": 0.93, + "learning_rate": 1.979365836912076e-05, + "loss": 0.5461, + "step": 1049 + }, + { + "epoch": 0.93, + "learning_rate": 1.979307873004328e-05, + "loss": 0.5393, + "step": 1050 + }, + { + "epoch": 0.93, + "learning_rate": 1.9792498286479535e-05, + "loss": 0.5388, + "step": 1051 + }, + { + "epoch": 0.93, + "learning_rate": 1.979191703847721e-05, + "loss": 0.528, + "step": 1052 + }, + { + "epoch": 0.93, + "learning_rate": 1.9791334986084056e-05, + "loss": 0.537, + "step": 1053 + }, + { + "epoch": 0.93, + "learning_rate": 1.9790752129347876e-05, + "loss": 0.5487, + "step": 1054 + }, + { + "epoch": 0.93, + "learning_rate": 1.9790168468316566e-05, + "loss": 0.5145, + "step": 1055 + }, + { + "epoch": 0.93, + "learning_rate": 1.9789584003038064e-05, + "loss": 0.5247, + "step": 1056 + }, + { + "epoch": 0.94, + "learning_rate": 1.9788998733560386e-05, + "loss": 0.5385, + "step": 1057 + }, + { + "epoch": 0.94, + "learning_rate": 1.978841265993161e-05, + "loss": 0.5182, + "step": 1058 + }, + { + "epoch": 0.94, + "learning_rate": 1.9787825782199882e-05, + "loss": 0.5478, + "step": 1059 + }, + { + "epoch": 0.94, + "learning_rate": 1.9787238100413408e-05, + "loss": 0.5435, + "step": 1060 + }, + { + "epoch": 0.94, + "learning_rate": 1.978664961462047e-05, + "loss": 0.5465, + "step": 1061 + }, + { + "epoch": 0.94, + "learning_rate": 1.9786060324869418e-05, + "loss": 0.5472, + "step": 1062 + }, + { + "epoch": 0.94, + "learning_rate": 1.9785470231208648e-05, + "loss": 0.5771, + "step": 1063 + }, + { + "epoch": 0.94, + "learning_rate": 1.978487933368664e-05, + "loss": 0.5051, + "step": 1064 + }, + { + "epoch": 0.94, + "learning_rate": 1.978428763235194e-05, + "loss": 0.5393, + "step": 1065 + }, + { + "epoch": 0.94, + "learning_rate": 1.978369512725315e-05, + "loss": 0.555, + "step": 1066 + }, + { + "epoch": 0.94, + "learning_rate": 1.9783101818438944e-05, + "loss": 0.5613, + "step": 1067 + }, + { + "epoch": 0.94, + "learning_rate": 1.9782507705958066e-05, + "loss": 0.5322, + "step": 1068 + }, + { + "epoch": 0.95, + "learning_rate": 1.978191278985931e-05, + "loss": 0.531, + "step": 1069 + }, + { + "epoch": 0.95, + "learning_rate": 1.9781317070191563e-05, + "loss": 0.574, + "step": 1070 + }, + { + "epoch": 0.95, + "learning_rate": 1.9780720547003753e-05, + "loss": 0.5187, + "step": 1071 + }, + { + "epoch": 0.95, + "learning_rate": 1.9780123220344888e-05, + "loss": 0.5849, + "step": 1072 + }, + { + "epoch": 0.95, + "learning_rate": 1.977952509026403e-05, + "loss": 0.5601, + "step": 1073 + }, + { + "epoch": 0.95, + "learning_rate": 1.977892615681032e-05, + "loss": 0.5563, + "step": 1074 + }, + { + "epoch": 0.95, + "learning_rate": 1.9778326420032957e-05, + "loss": 0.5421, + "step": 1075 + }, + { + "epoch": 0.95, + "learning_rate": 1.9777725879981215e-05, + "loss": 0.5189, + "step": 1076 + }, + { + "epoch": 0.95, + "learning_rate": 1.9777124536704422e-05, + "loss": 0.5928, + "step": 1077 + }, + { + "epoch": 0.95, + "learning_rate": 1.9776522390251975e-05, + "loss": 0.544, + "step": 1078 + }, + { + "epoch": 0.95, + "learning_rate": 1.9775919440673343e-05, + "loss": 0.5631, + "step": 1079 + }, + { + "epoch": 0.96, + "learning_rate": 1.9775315688018057e-05, + "loss": 0.5772, + "step": 1080 + }, + { + "epoch": 0.96, + "learning_rate": 1.9774711132335717e-05, + "loss": 0.5429, + "step": 1081 + }, + { + "epoch": 0.96, + "learning_rate": 1.977410577367598e-05, + "loss": 0.5401, + "step": 1082 + }, + { + "epoch": 0.96, + "learning_rate": 1.977349961208858e-05, + "loss": 0.5468, + "step": 1083 + }, + { + "epoch": 0.96, + "learning_rate": 1.977289264762331e-05, + "loss": 0.515, + "step": 1084 + }, + { + "epoch": 0.96, + "learning_rate": 1.9772284880330033e-05, + "loss": 0.5333, + "step": 1085 + }, + { + "epoch": 0.96, + "learning_rate": 1.9771676310258675e-05, + "loss": 0.5562, + "step": 1086 + }, + { + "epoch": 0.96, + "learning_rate": 1.977106693745923e-05, + "loss": 0.5211, + "step": 1087 + }, + { + "epoch": 0.96, + "learning_rate": 1.9770456761981752e-05, + "loss": 0.5424, + "step": 1088 + }, + { + "epoch": 0.96, + "learning_rate": 1.9769845783876373e-05, + "loss": 0.5466, + "step": 1089 + }, + { + "epoch": 0.96, + "learning_rate": 1.9769234003193284e-05, + "loss": 0.5507, + "step": 1090 + }, + { + "epoch": 0.97, + "learning_rate": 1.9768621419982737e-05, + "loss": 0.5673, + "step": 1091 + }, + { + "epoch": 0.97, + "learning_rate": 1.9768008034295056e-05, + "loss": 0.5494, + "step": 1092 + }, + { + "epoch": 0.97, + "learning_rate": 1.9767393846180633e-05, + "loss": 0.5491, + "step": 1093 + }, + { + "epoch": 0.97, + "learning_rate": 1.9766778855689917e-05, + "loss": 0.5613, + "step": 1094 + }, + { + "epoch": 0.97, + "learning_rate": 1.9766163062873432e-05, + "loss": 0.5429, + "step": 1095 + }, + { + "epoch": 0.97, + "learning_rate": 1.9765546467781767e-05, + "loss": 0.5298, + "step": 1096 + }, + { + "epoch": 0.97, + "learning_rate": 1.976492907046557e-05, + "loss": 0.5666, + "step": 1097 + }, + { + "epoch": 0.97, + "learning_rate": 1.9764310870975557e-05, + "loss": 0.5526, + "step": 1098 + }, + { + "epoch": 0.97, + "learning_rate": 1.9763691869362522e-05, + "loss": 0.5317, + "step": 1099 + }, + { + "epoch": 0.97, + "learning_rate": 1.9763072065677306e-05, + "loss": 0.5537, + "step": 1100 + }, + { + "epoch": 0.97, + "learning_rate": 1.9762451459970825e-05, + "loss": 0.5315, + "step": 1101 + }, + { + "epoch": 0.97, + "learning_rate": 1.976183005229407e-05, + "loss": 0.5194, + "step": 1102 + }, + { + "epoch": 0.98, + "learning_rate": 1.976120784269808e-05, + "loss": 0.5249, + "step": 1103 + }, + { + "epoch": 0.98, + "learning_rate": 1.9760584831233968e-05, + "loss": 0.522, + "step": 1104 + }, + { + "epoch": 0.98, + "learning_rate": 1.9759961017952915e-05, + "loss": 0.5452, + "step": 1105 + }, + { + "epoch": 0.98, + "learning_rate": 1.975933640290617e-05, + "loss": 0.5465, + "step": 1106 + }, + { + "epoch": 0.98, + "learning_rate": 1.975871098614504e-05, + "loss": 0.5199, + "step": 1107 + }, + { + "epoch": 0.98, + "learning_rate": 1.9758084767720905e-05, + "loss": 0.5312, + "step": 1108 + }, + { + "epoch": 0.98, + "learning_rate": 1.975745774768521e-05, + "loss": 0.5412, + "step": 1109 + }, + { + "epoch": 0.98, + "learning_rate": 1.9756829926089452e-05, + "loss": 0.5432, + "step": 1110 + }, + { + "epoch": 0.98, + "learning_rate": 1.9756201302985222e-05, + "loss": 0.538, + "step": 1111 + }, + { + "epoch": 0.98, + "learning_rate": 1.975557187842415e-05, + "loss": 0.5347, + "step": 1112 + }, + { + "epoch": 0.98, + "learning_rate": 1.975494165245794e-05, + "loss": 0.5218, + "step": 1113 + }, + { + "epoch": 0.99, + "learning_rate": 1.9754310625138374e-05, + "loss": 0.5673, + "step": 1114 + }, + { + "epoch": 0.99, + "learning_rate": 1.975367879651728e-05, + "loss": 0.5484, + "step": 1115 + }, + { + "epoch": 0.99, + "learning_rate": 1.975304616664657e-05, + "loss": 0.5535, + "step": 1116 + }, + { + "epoch": 0.99, + "learning_rate": 1.975241273557821e-05, + "loss": 0.5382, + "step": 1117 + }, + { + "epoch": 0.99, + "learning_rate": 1.9751778503364233e-05, + "loss": 0.5609, + "step": 1118 + }, + { + "epoch": 0.99, + "learning_rate": 1.9751143470056742e-05, + "loss": 0.5498, + "step": 1119 + }, + { + "epoch": 0.99, + "learning_rate": 1.9750507635707906e-05, + "loss": 0.5389, + "step": 1120 + }, + { + "epoch": 0.99, + "learning_rate": 1.9749871000369956e-05, + "loss": 0.5706, + "step": 1121 + }, + { + "epoch": 0.99, + "learning_rate": 1.974923356409519e-05, + "loss": 0.5578, + "step": 1122 + }, + { + "epoch": 0.99, + "learning_rate": 1.9748595326935973e-05, + "loss": 0.5594, + "step": 1123 + }, + { + "epoch": 0.99, + "learning_rate": 1.974795628894474e-05, + "loss": 0.523, + "step": 1124 + }, + { + "epoch": 1.0, + "learning_rate": 1.9747316450173976e-05, + "loss": 0.5553, + "step": 1125 + }, + { + "epoch": 1.0, + "learning_rate": 1.974667581067625e-05, + "loss": 0.5509, + "step": 1126 + }, + { + "epoch": 1.0, + "learning_rate": 1.974603437050419e-05, + "loss": 0.5141, + "step": 1127 + }, + { + "epoch": 1.0, + "learning_rate": 1.974539212971049e-05, + "loss": 0.5202, + "step": 1128 + }, + { + "epoch": 1.0, + "learning_rate": 1.9744749088347906e-05, + "loss": 0.5278, + "step": 1129 + }, + { + "epoch": 1.0, + "learning_rate": 1.9744105246469264e-05, + "loss": 0.551, + "step": 1130 + }, + { + "epoch": 1.0, + "learning_rate": 1.9743460604127454e-05, + "loss": 0.4941, + "step": 1131 + }, + { + "epoch": 1.0, + "learning_rate": 1.974281516137543e-05, + "loss": 0.4561, + "step": 1132 + }, + { + "epoch": 1.0, + "learning_rate": 1.974216891826622e-05, + "loss": 0.4695, + "step": 1133 + }, + { + "epoch": 1.0, + "learning_rate": 1.974152187485291e-05, + "loss": 0.4662, + "step": 1134 + }, + { + "epoch": 1.0, + "learning_rate": 1.974087403118865e-05, + "loss": 0.4659, + "step": 1135 + }, + { + "epoch": 1.0, + "learning_rate": 1.9740225387326665e-05, + "loss": 0.4715, + "step": 1136 + }, + { + "epoch": 1.01, + "learning_rate": 1.9739575943320232e-05, + "loss": 0.4439, + "step": 1137 + }, + { + "epoch": 1.01, + "learning_rate": 1.973892569922271e-05, + "loss": 0.4789, + "step": 1138 + }, + { + "epoch": 1.01, + "learning_rate": 1.9738274655087515e-05, + "loss": 0.4855, + "step": 1139 + }, + { + "epoch": 1.01, + "learning_rate": 1.9737622810968123e-05, + "loss": 0.4797, + "step": 1140 + }, + { + "epoch": 1.01, + "learning_rate": 1.9736970166918087e-05, + "loss": 0.4625, + "step": 1141 + }, + { + "epoch": 1.01, + "learning_rate": 1.973631672299102e-05, + "loss": 0.4966, + "step": 1142 + }, + { + "epoch": 1.01, + "learning_rate": 1.9735662479240597e-05, + "loss": 0.4698, + "step": 1143 + }, + { + "epoch": 1.01, + "learning_rate": 1.973500743572057e-05, + "loss": 0.483, + "step": 1144 + }, + { + "epoch": 1.01, + "learning_rate": 1.973435159248475e-05, + "loss": 0.4723, + "step": 1145 + }, + { + "epoch": 1.01, + "learning_rate": 1.9733694949587005e-05, + "loss": 0.4627, + "step": 1146 + }, + { + "epoch": 1.01, + "learning_rate": 1.9733037507081282e-05, + "loss": 0.4513, + "step": 1147 + }, + { + "epoch": 1.02, + "learning_rate": 1.973237926502159e-05, + "loss": 0.4816, + "step": 1148 + }, + { + "epoch": 1.02, + "learning_rate": 1.9731720223462004e-05, + "loss": 0.4944, + "step": 1149 + }, + { + "epoch": 1.02, + "learning_rate": 1.973106038245666e-05, + "loss": 0.4947, + "step": 1150 + }, + { + "epoch": 1.02, + "learning_rate": 1.9730399742059762e-05, + "loss": 0.4935, + "step": 1151 + }, + { + "epoch": 1.02, + "learning_rate": 1.9729738302325584e-05, + "loss": 0.4857, + "step": 1152 + }, + { + "epoch": 1.02, + "learning_rate": 1.972907606330846e-05, + "loss": 0.4567, + "step": 1153 + }, + { + "epoch": 1.02, + "learning_rate": 1.9728413025062795e-05, + "loss": 0.4858, + "step": 1154 + }, + { + "epoch": 1.02, + "learning_rate": 1.972774918764305e-05, + "loss": 0.4947, + "step": 1155 + }, + { + "epoch": 1.02, + "learning_rate": 1.9727084551103768e-05, + "loss": 0.4736, + "step": 1156 + }, + { + "epoch": 1.02, + "learning_rate": 1.972641911549954e-05, + "loss": 0.4834, + "step": 1157 + }, + { + "epoch": 1.02, + "learning_rate": 1.972575288088503e-05, + "loss": 0.4766, + "step": 1158 + }, + { + "epoch": 1.03, + "learning_rate": 1.9725085847314976e-05, + "loss": 0.4658, + "step": 1159 + }, + { + "epoch": 1.03, + "learning_rate": 1.9724418014844167e-05, + "loss": 0.4815, + "step": 1160 + }, + { + "epoch": 1.03, + "learning_rate": 1.9723749383527465e-05, + "loss": 0.4892, + "step": 1161 + }, + { + "epoch": 1.03, + "learning_rate": 1.9723079953419798e-05, + "loss": 0.5029, + "step": 1162 + }, + { + "epoch": 1.03, + "learning_rate": 1.9722409724576158e-05, + "loss": 0.4705, + "step": 1163 + }, + { + "epoch": 1.03, + "learning_rate": 1.9721738697051607e-05, + "loss": 0.4701, + "step": 1164 + }, + { + "epoch": 1.03, + "learning_rate": 1.9721066870901265e-05, + "loss": 0.4597, + "step": 1165 + }, + { + "epoch": 1.03, + "learning_rate": 1.972039424618032e-05, + "loss": 0.4856, + "step": 1166 + }, + { + "epoch": 1.03, + "learning_rate": 1.9719720822944033e-05, + "loss": 0.4906, + "step": 1167 + }, + { + "epoch": 1.03, + "learning_rate": 1.971904660124772e-05, + "loss": 0.4904, + "step": 1168 + }, + { + "epoch": 1.03, + "learning_rate": 1.971837158114677e-05, + "loss": 0.4731, + "step": 1169 + }, + { + "epoch": 1.03, + "learning_rate": 1.971769576269663e-05, + "loss": 0.4698, + "step": 1170 + }, + { + "epoch": 1.04, + "learning_rate": 1.9717019145952823e-05, + "loss": 0.4872, + "step": 1171 + }, + { + "epoch": 1.04, + "learning_rate": 1.971634173097093e-05, + "loss": 0.4753, + "step": 1172 + }, + { + "epoch": 1.04, + "learning_rate": 1.97156635178066e-05, + "loss": 0.475, + "step": 1173 + }, + { + "epoch": 1.04, + "learning_rate": 1.9714984506515545e-05, + "loss": 0.4537, + "step": 1174 + }, + { + "epoch": 1.04, + "learning_rate": 1.9714304697153547e-05, + "loss": 0.473, + "step": 1175 + }, + { + "epoch": 1.04, + "learning_rate": 1.971362408977645e-05, + "loss": 0.479, + "step": 1176 + }, + { + "epoch": 1.04, + "learning_rate": 1.9712942684440162e-05, + "loss": 0.4722, + "step": 1177 + }, + { + "epoch": 1.04, + "learning_rate": 1.9712260481200666e-05, + "loss": 0.4867, + "step": 1178 + }, + { + "epoch": 1.04, + "learning_rate": 1.9711577480114002e-05, + "loss": 0.4749, + "step": 1179 + }, + { + "epoch": 1.04, + "learning_rate": 1.9710893681236275e-05, + "loss": 0.4664, + "step": 1180 + }, + { + "epoch": 1.04, + "learning_rate": 1.971020908462366e-05, + "loss": 0.4904, + "step": 1181 + }, + { + "epoch": 1.05, + "learning_rate": 1.9709523690332395e-05, + "loss": 0.5073, + "step": 1182 + }, + { + "epoch": 1.05, + "learning_rate": 1.9708837498418782e-05, + "loss": 0.498, + "step": 1183 + }, + { + "epoch": 1.05, + "learning_rate": 1.9708150508939196e-05, + "loss": 0.4589, + "step": 1184 + }, + { + "epoch": 1.05, + "learning_rate": 1.9707462721950064e-05, + "loss": 0.4723, + "step": 1185 + }, + { + "epoch": 1.05, + "learning_rate": 1.9706774137507896e-05, + "loss": 0.4784, + "step": 1186 + }, + { + "epoch": 1.05, + "learning_rate": 1.970608475566925e-05, + "loss": 0.4814, + "step": 1187 + }, + { + "epoch": 1.05, + "learning_rate": 1.9705394576490762e-05, + "loss": 0.484, + "step": 1188 + }, + { + "epoch": 1.05, + "learning_rate": 1.9704703600029127e-05, + "loss": 0.4741, + "step": 1189 + }, + { + "epoch": 1.05, + "learning_rate": 1.9704011826341108e-05, + "loss": 0.5046, + "step": 1190 + }, + { + "epoch": 1.05, + "learning_rate": 1.9703319255483538e-05, + "loss": 0.4824, + "step": 1191 + }, + { + "epoch": 1.05, + "learning_rate": 1.9702625887513304e-05, + "loss": 0.4797, + "step": 1192 + }, + { + "epoch": 1.06, + "learning_rate": 1.9701931722487367e-05, + "loss": 0.4726, + "step": 1193 + }, + { + "epoch": 1.06, + "learning_rate": 1.9701236760462757e-05, + "loss": 0.4813, + "step": 1194 + }, + { + "epoch": 1.06, + "learning_rate": 1.9700541001496556e-05, + "loss": 0.4762, + "step": 1195 + }, + { + "epoch": 1.06, + "learning_rate": 1.9699844445645922e-05, + "loss": 0.4683, + "step": 1196 + }, + { + "epoch": 1.06, + "learning_rate": 1.9699147092968077e-05, + "loss": 0.4661, + "step": 1197 + }, + { + "epoch": 1.06, + "learning_rate": 1.969844894352031e-05, + "loss": 0.4863, + "step": 1198 + }, + { + "epoch": 1.06, + "learning_rate": 1.9697749997359967e-05, + "loss": 0.4735, + "step": 1199 + }, + { + "epoch": 1.06, + "learning_rate": 1.969705025454447e-05, + "loss": 0.4565, + "step": 1200 + }, + { + "epoch": 1.06, + "learning_rate": 1.96963497151313e-05, + "loss": 0.4853, + "step": 1201 + }, + { + "epoch": 1.06, + "learning_rate": 1.969564837917801e-05, + "loss": 0.5105, + "step": 1202 + }, + { + "epoch": 1.06, + "learning_rate": 1.96949462467422e-05, + "loss": 0.5153, + "step": 1203 + }, + { + "epoch": 1.07, + "learning_rate": 1.9694243317881565e-05, + "loss": 0.4704, + "step": 1204 + }, + { + "epoch": 1.07, + "learning_rate": 1.969353959265384e-05, + "loss": 0.492, + "step": 1205 + }, + { + "epoch": 1.07, + "learning_rate": 1.9692835071116837e-05, + "loss": 0.4666, + "step": 1206 + }, + { + "epoch": 1.07, + "learning_rate": 1.9692129753328437e-05, + "loss": 0.4576, + "step": 1207 + }, + { + "epoch": 1.07, + "learning_rate": 1.9691423639346573e-05, + "loss": 0.4836, + "step": 1208 + }, + { + "epoch": 1.07, + "learning_rate": 1.969071672922925e-05, + "loss": 0.4964, + "step": 1209 + }, + { + "epoch": 1.07, + "learning_rate": 1.969000902303455e-05, + "loss": 0.5032, + "step": 1210 + }, + { + "epoch": 1.07, + "learning_rate": 1.96893005208206e-05, + "loss": 0.4409, + "step": 1211 + }, + { + "epoch": 1.07, + "learning_rate": 1.9688591222645607e-05, + "loss": 0.4654, + "step": 1212 + }, + { + "epoch": 1.07, + "learning_rate": 1.968788112856784e-05, + "loss": 0.4641, + "step": 1213 + }, + { + "epoch": 1.07, + "learning_rate": 1.968717023864563e-05, + "loss": 0.47, + "step": 1214 + }, + { + "epoch": 1.07, + "learning_rate": 1.968645855293737e-05, + "loss": 0.4984, + "step": 1215 + }, + { + "epoch": 1.08, + "learning_rate": 1.9685746071501533e-05, + "loss": 0.4846, + "step": 1216 + }, + { + "epoch": 1.08, + "learning_rate": 1.9685032794396642e-05, + "loss": 0.487, + "step": 1217 + }, + { + "epoch": 1.08, + "learning_rate": 1.9684318721681297e-05, + "loss": 0.4851, + "step": 1218 + }, + { + "epoch": 1.08, + "learning_rate": 1.9683603853414155e-05, + "loss": 0.4661, + "step": 1219 + }, + { + "epoch": 1.08, + "learning_rate": 1.9682888189653938e-05, + "loss": 0.5004, + "step": 1220 + }, + { + "epoch": 1.08, + "learning_rate": 1.968217173045944e-05, + "loss": 0.4884, + "step": 1221 + }, + { + "epoch": 1.08, + "learning_rate": 1.9681454475889522e-05, + "loss": 0.4958, + "step": 1222 + }, + { + "epoch": 1.08, + "learning_rate": 1.96807364260031e-05, + "loss": 0.4678, + "step": 1223 + }, + { + "epoch": 1.08, + "learning_rate": 1.9680017580859157e-05, + "loss": 0.4828, + "step": 1224 + }, + { + "epoch": 1.08, + "learning_rate": 1.967929794051675e-05, + "loss": 0.4984, + "step": 1225 + }, + { + "epoch": 1.08, + "learning_rate": 1.9678577505034998e-05, + "loss": 0.5036, + "step": 1226 + }, + { + "epoch": 1.09, + "learning_rate": 1.967785627447308e-05, + "loss": 0.487, + "step": 1227 + }, + { + "epoch": 1.09, + "learning_rate": 1.9677134248890245e-05, + "loss": 0.4986, + "step": 1228 + }, + { + "epoch": 1.09, + "learning_rate": 1.9676411428345805e-05, + "loss": 0.4824, + "step": 1229 + }, + { + "epoch": 1.09, + "learning_rate": 1.9675687812899142e-05, + "loss": 0.482, + "step": 1230 + }, + { + "epoch": 1.09, + "learning_rate": 1.9674963402609694e-05, + "loss": 0.48, + "step": 1231 + }, + { + "epoch": 1.09, + "learning_rate": 1.967423819753698e-05, + "loss": 0.508, + "step": 1232 + }, + { + "epoch": 1.09, + "learning_rate": 1.9673512197740563e-05, + "loss": 0.4839, + "step": 1233 + }, + { + "epoch": 1.09, + "learning_rate": 1.967278540328009e-05, + "loss": 0.477, + "step": 1234 + }, + { + "epoch": 1.09, + "learning_rate": 1.9672057814215266e-05, + "loss": 0.4752, + "step": 1235 + }, + { + "epoch": 1.09, + "learning_rate": 1.967132943060586e-05, + "loss": 0.4912, + "step": 1236 + }, + { + "epoch": 1.09, + "learning_rate": 1.9670600252511707e-05, + "loss": 0.4888, + "step": 1237 + }, + { + "epoch": 1.1, + "learning_rate": 1.9669870279992708e-05, + "loss": 0.4687, + "step": 1238 + }, + { + "epoch": 1.1, + "learning_rate": 1.9669139513108827e-05, + "loss": 0.4665, + "step": 1239 + }, + { + "epoch": 1.1, + "learning_rate": 1.9668407951920097e-05, + "loss": 0.5099, + "step": 1240 + }, + { + "epoch": 1.1, + "learning_rate": 1.966767559648662e-05, + "loss": 0.5194, + "step": 1241 + }, + { + "epoch": 1.1, + "learning_rate": 1.9666942446868546e-05, + "loss": 0.5065, + "step": 1242 + }, + { + "epoch": 1.1, + "learning_rate": 1.9666208503126115e-05, + "loss": 0.4713, + "step": 1243 + }, + { + "epoch": 1.1, + "learning_rate": 1.966547376531961e-05, + "loss": 0.4645, + "step": 1244 + }, + { + "epoch": 1.1, + "learning_rate": 1.966473823350939e-05, + "loss": 0.4853, + "step": 1245 + }, + { + "epoch": 1.1, + "learning_rate": 1.966400190775589e-05, + "loss": 0.4659, + "step": 1246 + }, + { + "epoch": 1.1, + "learning_rate": 1.9663264788119577e-05, + "loss": 0.4688, + "step": 1247 + }, + { + "epoch": 1.1, + "learning_rate": 1.9662526874661022e-05, + "loss": 0.4659, + "step": 1248 + }, + { + "epoch": 1.1, + "learning_rate": 1.9661788167440835e-05, + "loss": 0.4763, + "step": 1249 + }, + { + "epoch": 1.11, + "learning_rate": 1.96610486665197e-05, + "loss": 0.4665, + "step": 1250 + }, + { + "epoch": 1.11, + "learning_rate": 1.9660308371958365e-05, + "loss": 0.4472, + "step": 1251 + }, + { + "epoch": 1.11, + "learning_rate": 1.9659567283817647e-05, + "loss": 0.4633, + "step": 1252 + }, + { + "epoch": 1.11, + "learning_rate": 1.9658825402158427e-05, + "loss": 0.4894, + "step": 1253 + }, + { + "epoch": 1.11, + "learning_rate": 1.9658082727041648e-05, + "loss": 0.4903, + "step": 1254 + }, + { + "epoch": 1.11, + "learning_rate": 1.9657339258528315e-05, + "loss": 0.5036, + "step": 1255 + }, + { + "epoch": 1.11, + "learning_rate": 1.965659499667951e-05, + "loss": 0.4614, + "step": 1256 + }, + { + "epoch": 1.11, + "learning_rate": 1.9655849941556366e-05, + "loss": 0.4702, + "step": 1257 + }, + { + "epoch": 1.11, + "learning_rate": 1.965510409322009e-05, + "loss": 0.4676, + "step": 1258 + }, + { + "epoch": 1.11, + "learning_rate": 1.9654357451731953e-05, + "loss": 0.4746, + "step": 1259 + }, + { + "epoch": 1.11, + "learning_rate": 1.9653610017153296e-05, + "loss": 0.4797, + "step": 1260 + }, + { + "epoch": 1.12, + "learning_rate": 1.965286178954551e-05, + "loss": 0.517, + "step": 1261 + }, + { + "epoch": 1.12, + "learning_rate": 1.965211276897007e-05, + "loss": 0.4733, + "step": 1262 + }, + { + "epoch": 1.12, + "learning_rate": 1.9651362955488498e-05, + "loss": 0.4758, + "step": 1263 + }, + { + "epoch": 1.12, + "learning_rate": 1.9650612349162394e-05, + "loss": 0.4758, + "step": 1264 + }, + { + "epoch": 1.12, + "learning_rate": 1.964986095005342e-05, + "loss": 0.4823, + "step": 1265 + }, + { + "epoch": 1.12, + "learning_rate": 1.9649108758223304e-05, + "loss": 0.518, + "step": 1266 + }, + { + "epoch": 1.12, + "learning_rate": 1.9648355773733833e-05, + "loss": 0.4762, + "step": 1267 + }, + { + "epoch": 1.12, + "learning_rate": 1.9647601996646868e-05, + "loss": 0.4969, + "step": 1268 + }, + { + "epoch": 1.12, + "learning_rate": 1.9646847427024327e-05, + "loss": 0.472, + "step": 1269 + }, + { + "epoch": 1.12, + "learning_rate": 1.96460920649282e-05, + "loss": 0.4594, + "step": 1270 + }, + { + "epoch": 1.12, + "learning_rate": 1.964533591042053e-05, + "loss": 0.479, + "step": 1271 + }, + { + "epoch": 1.13, + "learning_rate": 1.964457896356345e-05, + "loss": 0.4996, + "step": 1272 + }, + { + "epoch": 1.13, + "learning_rate": 1.9643821224419124e-05, + "loss": 0.4638, + "step": 1273 + }, + { + "epoch": 1.13, + "learning_rate": 1.9643062693049812e-05, + "loss": 0.489, + "step": 1274 + }, + { + "epoch": 1.13, + "learning_rate": 1.964230336951782e-05, + "loss": 0.4699, + "step": 1275 + }, + { + "epoch": 1.13, + "learning_rate": 1.9641543253885528e-05, + "loss": 0.4837, + "step": 1276 + }, + { + "epoch": 1.13, + "learning_rate": 1.964078234621538e-05, + "loss": 0.4713, + "step": 1277 + }, + { + "epoch": 1.13, + "learning_rate": 1.9640020646569878e-05, + "loss": 0.4926, + "step": 1278 + }, + { + "epoch": 1.13, + "learning_rate": 1.96392581550116e-05, + "loss": 0.4756, + "step": 1279 + }, + { + "epoch": 1.13, + "learning_rate": 1.9638494871603176e-05, + "loss": 0.5, + "step": 1280 + }, + { + "epoch": 1.13, + "learning_rate": 1.9637730796407318e-05, + "loss": 0.4885, + "step": 1281 + }, + { + "epoch": 1.13, + "learning_rate": 1.963696592948679e-05, + "loss": 0.478, + "step": 1282 + }, + { + "epoch": 1.13, + "learning_rate": 1.9636200270904423e-05, + "loss": 0.4812, + "step": 1283 + }, + { + "epoch": 1.14, + "learning_rate": 1.963543382072311e-05, + "loss": 0.4687, + "step": 1284 + }, + { + "epoch": 1.14, + "learning_rate": 1.9634666579005824e-05, + "loss": 0.4764, + "step": 1285 + }, + { + "epoch": 1.14, + "learning_rate": 1.963389854581559e-05, + "loss": 0.5024, + "step": 1286 + }, + { + "epoch": 1.14, + "learning_rate": 1.9633129721215493e-05, + "loss": 0.4772, + "step": 1287 + }, + { + "epoch": 1.14, + "learning_rate": 1.9632360105268698e-05, + "loss": 0.4665, + "step": 1288 + }, + { + "epoch": 1.14, + "learning_rate": 1.9631589698038426e-05, + "loss": 0.4893, + "step": 1289 + }, + { + "epoch": 1.14, + "learning_rate": 1.9630818499587965e-05, + "loss": 0.4991, + "step": 1290 + }, + { + "epoch": 1.14, + "learning_rate": 1.9630046509980668e-05, + "loss": 0.4318, + "step": 1291 + }, + { + "epoch": 1.14, + "learning_rate": 1.962927372927995e-05, + "loss": 0.4994, + "step": 1292 + }, + { + "epoch": 1.14, + "learning_rate": 1.96285001575493e-05, + "loss": 0.4609, + "step": 1293 + }, + { + "epoch": 1.14, + "learning_rate": 1.962772579485226e-05, + "loss": 0.4809, + "step": 1294 + }, + { + "epoch": 1.15, + "learning_rate": 1.9626950641252442e-05, + "loss": 0.5046, + "step": 1295 + }, + { + "epoch": 1.15, + "learning_rate": 1.962617469681353e-05, + "loss": 0.4668, + "step": 1296 + }, + { + "epoch": 1.15, + "learning_rate": 1.9625397961599258e-05, + "loss": 0.5034, + "step": 1297 + }, + { + "epoch": 1.15, + "learning_rate": 1.9624620435673443e-05, + "loss": 0.479, + "step": 1298 + }, + { + "epoch": 1.15, + "learning_rate": 1.9623842119099952e-05, + "loss": 0.5059, + "step": 1299 + }, + { + "epoch": 1.15, + "learning_rate": 1.962306301194272e-05, + "loss": 0.5277, + "step": 1300 + }, + { + "epoch": 1.15, + "learning_rate": 1.9622283114265755e-05, + "loss": 0.4575, + "step": 1301 + }, + { + "epoch": 1.15, + "learning_rate": 1.962150242613312e-05, + "loss": 0.4901, + "step": 1302 + }, + { + "epoch": 1.15, + "learning_rate": 1.9620720947608953e-05, + "loss": 0.4856, + "step": 1303 + }, + { + "epoch": 1.15, + "learning_rate": 1.9619938678757447e-05, + "loss": 0.4941, + "step": 1304 + }, + { + "epoch": 1.15, + "learning_rate": 1.9619155619642867e-05, + "loss": 0.4734, + "step": 1305 + }, + { + "epoch": 1.16, + "learning_rate": 1.9618371770329536e-05, + "loss": 0.4739, + "step": 1306 + }, + { + "epoch": 1.16, + "learning_rate": 1.9617587130881848e-05, + "loss": 0.5024, + "step": 1307 + }, + { + "epoch": 1.16, + "learning_rate": 1.9616801701364257e-05, + "loss": 0.4642, + "step": 1308 + }, + { + "epoch": 1.16, + "learning_rate": 1.9616015481841293e-05, + "loss": 0.4425, + "step": 1309 + }, + { + "epoch": 1.16, + "learning_rate": 1.9615228472377533e-05, + "loss": 0.4858, + "step": 1310 + }, + { + "epoch": 1.16, + "learning_rate": 1.9614440673037637e-05, + "loss": 0.4722, + "step": 1311 + }, + { + "epoch": 1.16, + "learning_rate": 1.9613652083886315e-05, + "loss": 0.4803, + "step": 1312 + }, + { + "epoch": 1.16, + "learning_rate": 1.961286270498835e-05, + "loss": 0.4538, + "step": 1313 + }, + { + "epoch": 1.16, + "learning_rate": 1.9612072536408593e-05, + "loss": 0.4682, + "step": 1314 + }, + { + "epoch": 1.16, + "learning_rate": 1.961128157821195e-05, + "loss": 0.4657, + "step": 1315 + }, + { + "epoch": 1.16, + "learning_rate": 1.96104898304634e-05, + "loss": 0.4824, + "step": 1316 + }, + { + "epoch": 1.17, + "learning_rate": 1.9609697293227978e-05, + "loss": 0.4702, + "step": 1317 + }, + { + "epoch": 1.17, + "learning_rate": 1.9608903966570793e-05, + "loss": 0.4809, + "step": 1318 + }, + { + "epoch": 1.17, + "learning_rate": 1.960810985055702e-05, + "loss": 0.4842, + "step": 1319 + }, + { + "epoch": 1.17, + "learning_rate": 1.9607314945251892e-05, + "loss": 0.4844, + "step": 1320 + }, + { + "epoch": 1.17, + "learning_rate": 1.9606519250720707e-05, + "loss": 0.482, + "step": 1321 + }, + { + "epoch": 1.17, + "learning_rate": 1.960572276702883e-05, + "loss": 0.4597, + "step": 1322 + }, + { + "epoch": 1.17, + "learning_rate": 1.9604925494241693e-05, + "loss": 0.4792, + "step": 1323 + }, + { + "epoch": 1.17, + "learning_rate": 1.960412743242479e-05, + "loss": 0.4737, + "step": 1324 + }, + { + "epoch": 1.17, + "learning_rate": 1.960332858164368e-05, + "loss": 0.4869, + "step": 1325 + }, + { + "epoch": 1.17, + "learning_rate": 1.9602528941963986e-05, + "loss": 0.4731, + "step": 1326 + }, + { + "epoch": 1.17, + "learning_rate": 1.9601728513451402e-05, + "loss": 0.4769, + "step": 1327 + }, + { + "epoch": 1.17, + "learning_rate": 1.9600927296171678e-05, + "loss": 0.4814, + "step": 1328 + }, + { + "epoch": 1.18, + "learning_rate": 1.9600125290190632e-05, + "loss": 0.4457, + "step": 1329 + }, + { + "epoch": 1.18, + "learning_rate": 1.959932249557415e-05, + "loss": 0.4689, + "step": 1330 + }, + { + "epoch": 1.18, + "learning_rate": 1.959851891238818e-05, + "loss": 0.4755, + "step": 1331 + }, + { + "epoch": 1.18, + "learning_rate": 1.9597714540698734e-05, + "loss": 0.4826, + "step": 1332 + }, + { + "epoch": 1.18, + "learning_rate": 1.959690938057189e-05, + "loss": 0.5054, + "step": 1333 + }, + { + "epoch": 1.18, + "learning_rate": 1.9596103432073792e-05, + "loss": 0.4855, + "step": 1334 + }, + { + "epoch": 1.18, + "learning_rate": 1.9595296695270648e-05, + "loss": 0.484, + "step": 1335 + }, + { + "epoch": 1.18, + "learning_rate": 1.9594489170228726e-05, + "loss": 0.4821, + "step": 1336 + }, + { + "epoch": 1.18, + "learning_rate": 1.9593680857014367e-05, + "loss": 0.5021, + "step": 1337 + }, + { + "epoch": 1.18, + "learning_rate": 1.9592871755693973e-05, + "loss": 0.4959, + "step": 1338 + }, + { + "epoch": 1.18, + "learning_rate": 1.9592061866334007e-05, + "loss": 0.4401, + "step": 1339 + }, + { + "epoch": 1.19, + "learning_rate": 1.9591251189001002e-05, + "loss": 0.4861, + "step": 1340 + }, + { + "epoch": 1.19, + "learning_rate": 1.9590439723761554e-05, + "loss": 0.4706, + "step": 1341 + }, + { + "epoch": 1.19, + "learning_rate": 1.9589627470682324e-05, + "loss": 0.4741, + "step": 1342 + }, + { + "epoch": 1.19, + "learning_rate": 1.9588814429830036e-05, + "loss": 0.4847, + "step": 1343 + }, + { + "epoch": 1.19, + "learning_rate": 1.958800060127148e-05, + "loss": 0.4642, + "step": 1344 + }, + { + "epoch": 1.19, + "learning_rate": 1.9587185985073514e-05, + "loss": 0.4835, + "step": 1345 + }, + { + "epoch": 1.19, + "learning_rate": 1.9586370581303052e-05, + "loss": 0.4747, + "step": 1346 + }, + { + "epoch": 1.19, + "learning_rate": 1.9585554390027083e-05, + "loss": 0.4816, + "step": 1347 + }, + { + "epoch": 1.19, + "learning_rate": 1.9584737411312657e-05, + "loss": 0.479, + "step": 1348 + }, + { + "epoch": 1.19, + "learning_rate": 1.958391964522688e-05, + "loss": 0.4661, + "step": 1349 + }, + { + "epoch": 1.19, + "learning_rate": 1.9583101091836937e-05, + "loss": 0.5095, + "step": 1350 + }, + { + "epoch": 1.2, + "learning_rate": 1.9582281751210067e-05, + "loss": 0.4691, + "step": 1351 + }, + { + "epoch": 1.2, + "learning_rate": 1.958146162341358e-05, + "loss": 0.4735, + "step": 1352 + }, + { + "epoch": 1.2, + "learning_rate": 1.958064070851485e-05, + "loss": 0.4902, + "step": 1353 + }, + { + "epoch": 1.2, + "learning_rate": 1.9579819006581308e-05, + "loss": 0.4842, + "step": 1354 + }, + { + "epoch": 1.2, + "learning_rate": 1.957899651768046e-05, + "loss": 0.5115, + "step": 1355 + }, + { + "epoch": 1.2, + "learning_rate": 1.957817324187987e-05, + "loss": 0.4665, + "step": 1356 + }, + { + "epoch": 1.2, + "learning_rate": 1.9577349179247175e-05, + "loss": 0.5285, + "step": 1357 + }, + { + "epoch": 1.2, + "learning_rate": 1.9576524329850063e-05, + "loss": 0.4829, + "step": 1358 + }, + { + "epoch": 1.2, + "learning_rate": 1.9575698693756292e-05, + "loss": 0.4843, + "step": 1359 + }, + { + "epoch": 1.2, + "learning_rate": 1.9574872271033695e-05, + "loss": 0.4626, + "step": 1360 + }, + { + "epoch": 1.2, + "learning_rate": 1.9574045061750158e-05, + "loss": 0.4766, + "step": 1361 + }, + { + "epoch": 1.2, + "learning_rate": 1.9573217065973632e-05, + "loss": 0.4795, + "step": 1362 + }, + { + "epoch": 1.21, + "learning_rate": 1.9572388283772144e-05, + "loss": 0.4665, + "step": 1363 + }, + { + "epoch": 1.21, + "learning_rate": 1.9571558715213766e-05, + "loss": 0.4619, + "step": 1364 + }, + { + "epoch": 1.21, + "learning_rate": 1.957072836036665e-05, + "loss": 0.4945, + "step": 1365 + }, + { + "epoch": 1.21, + "learning_rate": 1.9569897219299014e-05, + "loss": 0.4418, + "step": 1366 + }, + { + "epoch": 1.21, + "learning_rate": 1.956906529207913e-05, + "loss": 0.4634, + "step": 1367 + }, + { + "epoch": 1.21, + "learning_rate": 1.9568232578775337e-05, + "loss": 0.4631, + "step": 1368 + }, + { + "epoch": 1.21, + "learning_rate": 1.9567399079456043e-05, + "loss": 0.4906, + "step": 1369 + }, + { + "epoch": 1.21, + "learning_rate": 1.9566564794189724e-05, + "loss": 0.4554, + "step": 1370 + }, + { + "epoch": 1.21, + "learning_rate": 1.956572972304491e-05, + "loss": 0.4766, + "step": 1371 + }, + { + "epoch": 1.21, + "learning_rate": 1.95648938660902e-05, + "loss": 0.4837, + "step": 1372 + }, + { + "epoch": 1.21, + "learning_rate": 1.956405722339426e-05, + "loss": 0.4596, + "step": 1373 + }, + { + "epoch": 1.22, + "learning_rate": 1.9563219795025824e-05, + "loss": 0.4839, + "step": 1374 + }, + { + "epoch": 1.22, + "learning_rate": 1.9562381581053674e-05, + "loss": 0.4812, + "step": 1375 + }, + { + "epoch": 1.22, + "learning_rate": 1.9561542581546676e-05, + "loss": 0.4919, + "step": 1376 + }, + { + "epoch": 1.22, + "learning_rate": 1.956070279657375e-05, + "loss": 0.4799, + "step": 1377 + }, + { + "epoch": 1.22, + "learning_rate": 1.9559862226203887e-05, + "loss": 0.4777, + "step": 1378 + }, + { + "epoch": 1.22, + "learning_rate": 1.9559020870506136e-05, + "loss": 0.4568, + "step": 1379 + }, + { + "epoch": 1.22, + "learning_rate": 1.955817872954961e-05, + "loss": 0.4681, + "step": 1380 + }, + { + "epoch": 1.22, + "learning_rate": 1.9557335803403495e-05, + "loss": 0.49, + "step": 1381 + }, + { + "epoch": 1.22, + "learning_rate": 1.9556492092137032e-05, + "loss": 0.4934, + "step": 1382 + }, + { + "epoch": 1.22, + "learning_rate": 1.955564759581953e-05, + "loss": 0.4615, + "step": 1383 + }, + { + "epoch": 1.22, + "learning_rate": 1.955480231452037e-05, + "loss": 0.477, + "step": 1384 + }, + { + "epoch": 1.23, + "learning_rate": 1.955395624830898e-05, + "loss": 0.4666, + "step": 1385 + }, + { + "epoch": 1.23, + "learning_rate": 1.955310939725487e-05, + "loss": 0.4803, + "step": 1386 + }, + { + "epoch": 1.23, + "learning_rate": 1.9552261761427606e-05, + "loss": 0.4597, + "step": 1387 + }, + { + "epoch": 1.23, + "learning_rate": 1.9551413340896822e-05, + "loss": 0.5086, + "step": 1388 + }, + { + "epoch": 1.23, + "learning_rate": 1.9550564135732212e-05, + "loss": 0.4886, + "step": 1389 + }, + { + "epoch": 1.23, + "learning_rate": 1.9549714146003532e-05, + "loss": 0.4977, + "step": 1390 + }, + { + "epoch": 1.23, + "learning_rate": 1.9548863371780617e-05, + "loss": 0.4772, + "step": 1391 + }, + { + "epoch": 1.23, + "learning_rate": 1.9548011813133354e-05, + "loss": 0.4776, + "step": 1392 + }, + { + "epoch": 1.23, + "learning_rate": 1.9547159470131695e-05, + "loss": 0.4692, + "step": 1393 + }, + { + "epoch": 1.23, + "learning_rate": 1.9546306342845658e-05, + "loss": 0.5082, + "step": 1394 + }, + { + "epoch": 1.23, + "learning_rate": 1.9545452431345328e-05, + "loss": 0.4737, + "step": 1395 + }, + { + "epoch": 1.23, + "learning_rate": 1.954459773570085e-05, + "loss": 0.4526, + "step": 1396 + }, + { + "epoch": 1.24, + "learning_rate": 1.9543742255982442e-05, + "loss": 0.483, + "step": 1397 + }, + { + "epoch": 1.24, + "learning_rate": 1.9542885992260373e-05, + "loss": 0.4948, + "step": 1398 + }, + { + "epoch": 1.24, + "learning_rate": 1.9542028944604987e-05, + "loss": 0.4645, + "step": 1399 + }, + { + "epoch": 1.24, + "learning_rate": 1.954117111308669e-05, + "loss": 0.4955, + "step": 1400 + }, + { + "epoch": 1.24, + "learning_rate": 1.954031249777595e-05, + "loss": 0.4821, + "step": 1401 + }, + { + "epoch": 1.24, + "learning_rate": 1.9539453098743303e-05, + "loss": 0.4804, + "step": 1402 + }, + { + "epoch": 1.24, + "learning_rate": 1.9538592916059344e-05, + "loss": 0.4731, + "step": 1403 + }, + { + "epoch": 1.24, + "learning_rate": 1.9537731949794736e-05, + "loss": 0.4908, + "step": 1404 + }, + { + "epoch": 1.24, + "learning_rate": 1.953687020002021e-05, + "loss": 0.4547, + "step": 1405 + }, + { + "epoch": 1.24, + "learning_rate": 1.9536007666806555e-05, + "loss": 0.4972, + "step": 1406 + }, + { + "epoch": 1.24, + "learning_rate": 1.9535144350224626e-05, + "loss": 0.4769, + "step": 1407 + }, + { + "epoch": 1.25, + "learning_rate": 1.9534280250345343e-05, + "loss": 0.473, + "step": 1408 + }, + { + "epoch": 1.25, + "learning_rate": 1.9533415367239695e-05, + "loss": 0.4862, + "step": 1409 + }, + { + "epoch": 1.25, + "learning_rate": 1.953254970097872e-05, + "loss": 0.5087, + "step": 1410 + }, + { + "epoch": 1.25, + "learning_rate": 1.9531683251633544e-05, + "loss": 0.4593, + "step": 1411 + }, + { + "epoch": 1.25, + "learning_rate": 1.953081601927534e-05, + "loss": 0.469, + "step": 1412 + }, + { + "epoch": 1.25, + "learning_rate": 1.9529948003975345e-05, + "loss": 0.4677, + "step": 1413 + }, + { + "epoch": 1.25, + "learning_rate": 1.9529079205804867e-05, + "loss": 0.4807, + "step": 1414 + }, + { + "epoch": 1.25, + "learning_rate": 1.9528209624835285e-05, + "loss": 0.4802, + "step": 1415 + }, + { + "epoch": 1.25, + "learning_rate": 1.952733926113802e-05, + "loss": 0.5081, + "step": 1416 + }, + { + "epoch": 1.25, + "learning_rate": 1.952646811478458e-05, + "loss": 0.4737, + "step": 1417 + }, + { + "epoch": 1.25, + "learning_rate": 1.9525596185846527e-05, + "loss": 0.4602, + "step": 1418 + }, + { + "epoch": 1.26, + "learning_rate": 1.9524723474395485e-05, + "loss": 0.5108, + "step": 1419 + }, + { + "epoch": 1.26, + "learning_rate": 1.9523849980503153e-05, + "loss": 0.5006, + "step": 1420 + }, + { + "epoch": 1.26, + "learning_rate": 1.952297570424128e-05, + "loss": 0.4849, + "step": 1421 + }, + { + "epoch": 1.26, + "learning_rate": 1.9522100645681693e-05, + "loss": 0.4793, + "step": 1422 + }, + { + "epoch": 1.26, + "learning_rate": 1.9521224804896264e-05, + "loss": 0.4628, + "step": 1423 + }, + { + "epoch": 1.26, + "learning_rate": 1.952034818195696e-05, + "loss": 0.4716, + "step": 1424 + }, + { + "epoch": 1.26, + "learning_rate": 1.9519470776935783e-05, + "loss": 0.467, + "step": 1425 + }, + { + "epoch": 1.26, + "learning_rate": 1.951859258990481e-05, + "loss": 0.4697, + "step": 1426 + }, + { + "epoch": 1.26, + "learning_rate": 1.9517713620936188e-05, + "loss": 0.4682, + "step": 1427 + }, + { + "epoch": 1.26, + "learning_rate": 1.951683387010212e-05, + "loss": 0.4712, + "step": 1428 + }, + { + "epoch": 1.26, + "learning_rate": 1.9515953337474873e-05, + "loss": 0.4694, + "step": 1429 + }, + { + "epoch": 1.26, + "learning_rate": 1.951507202312679e-05, + "loss": 0.4686, + "step": 1430 + }, + { + "epoch": 1.27, + "learning_rate": 1.951418992713026e-05, + "loss": 0.4733, + "step": 1431 + }, + { + "epoch": 1.27, + "learning_rate": 1.9513307049557754e-05, + "loss": 0.4949, + "step": 1432 + }, + { + "epoch": 1.27, + "learning_rate": 1.951242339048179e-05, + "loss": 0.4813, + "step": 1433 + }, + { + "epoch": 1.27, + "learning_rate": 1.951153894997497e-05, + "loss": 0.4917, + "step": 1434 + }, + { + "epoch": 1.27, + "learning_rate": 1.951065372810994e-05, + "loss": 0.4825, + "step": 1435 + }, + { + "epoch": 1.27, + "learning_rate": 1.9509767724959427e-05, + "loss": 0.4737, + "step": 1436 + }, + { + "epoch": 1.27, + "learning_rate": 1.950888094059621e-05, + "loss": 0.4642, + "step": 1437 + }, + { + "epoch": 1.27, + "learning_rate": 1.950799337509314e-05, + "loss": 0.4676, + "step": 1438 + }, + { + "epoch": 1.27, + "learning_rate": 1.9507105028523125e-05, + "loss": 0.4803, + "step": 1439 + }, + { + "epoch": 1.27, + "learning_rate": 1.9506215900959145e-05, + "loss": 0.4769, + "step": 1440 + }, + { + "epoch": 1.27, + "learning_rate": 1.9505325992474236e-05, + "loss": 0.4899, + "step": 1441 + }, + { + "epoch": 1.28, + "learning_rate": 1.950443530314151e-05, + "loss": 0.4682, + "step": 1442 + }, + { + "epoch": 1.28, + "learning_rate": 1.950354383303413e-05, + "loss": 0.4699, + "step": 1443 + }, + { + "epoch": 1.28, + "learning_rate": 1.950265158222533e-05, + "loss": 0.5146, + "step": 1444 + }, + { + "epoch": 1.28, + "learning_rate": 1.9501758550788404e-05, + "loss": 0.4846, + "step": 1445 + }, + { + "epoch": 1.28, + "learning_rate": 1.9500864738796722e-05, + "loss": 0.4552, + "step": 1446 + }, + { + "epoch": 1.28, + "learning_rate": 1.9499970146323703e-05, + "loss": 0.4434, + "step": 1447 + }, + { + "epoch": 1.28, + "learning_rate": 1.9499074773442833e-05, + "loss": 0.4774, + "step": 1448 + }, + { + "epoch": 1.28, + "learning_rate": 1.9498178620227674e-05, + "loss": 0.458, + "step": 1449 + }, + { + "epoch": 1.28, + "learning_rate": 1.9497281686751842e-05, + "loss": 0.4498, + "step": 1450 + }, + { + "epoch": 1.28, + "learning_rate": 1.949638397308901e-05, + "loss": 0.4702, + "step": 1451 + }, + { + "epoch": 1.28, + "learning_rate": 1.949548547931293e-05, + "loss": 0.4892, + "step": 1452 + }, + { + "epoch": 1.29, + "learning_rate": 1.9494586205497413e-05, + "loss": 0.4932, + "step": 1453 + }, + { + "epoch": 1.29, + "learning_rate": 1.9493686151716335e-05, + "loss": 0.5131, + "step": 1454 + }, + { + "epoch": 1.29, + "learning_rate": 1.949278531804363e-05, + "loss": 0.4828, + "step": 1455 + }, + { + "epoch": 1.29, + "learning_rate": 1.9491883704553297e-05, + "loss": 0.4534, + "step": 1456 + }, + { + "epoch": 1.29, + "learning_rate": 1.949098131131941e-05, + "loss": 0.4748, + "step": 1457 + }, + { + "epoch": 1.29, + "learning_rate": 1.949007813841609e-05, + "loss": 0.4697, + "step": 1458 + }, + { + "epoch": 1.29, + "learning_rate": 1.948917418591754e-05, + "loss": 0.4534, + "step": 1459 + }, + { + "epoch": 1.29, + "learning_rate": 1.9488269453898017e-05, + "loss": 0.4872, + "step": 1460 + }, + { + "epoch": 1.29, + "learning_rate": 1.9487363942431837e-05, + "loss": 0.4799, + "step": 1461 + }, + { + "epoch": 1.29, + "learning_rate": 1.9486457651593393e-05, + "loss": 0.4697, + "step": 1462 + }, + { + "epoch": 1.29, + "learning_rate": 1.948555058145713e-05, + "loss": 0.4858, + "step": 1463 + }, + { + "epoch": 1.3, + "learning_rate": 1.9484642732097567e-05, + "loss": 0.4614, + "step": 1464 + }, + { + "epoch": 1.3, + "learning_rate": 1.948373410358928e-05, + "loss": 0.5072, + "step": 1465 + }, + { + "epoch": 1.3, + "learning_rate": 1.9482824696006913e-05, + "loss": 0.4787, + "step": 1466 + }, + { + "epoch": 1.3, + "learning_rate": 1.948191450942517e-05, + "loss": 0.4765, + "step": 1467 + }, + { + "epoch": 1.3, + "learning_rate": 1.9481003543918823e-05, + "loss": 0.4752, + "step": 1468 + }, + { + "epoch": 1.3, + "learning_rate": 1.9480091799562706e-05, + "loss": 0.5034, + "step": 1469 + }, + { + "epoch": 1.3, + "learning_rate": 1.947917927643172e-05, + "loss": 0.4874, + "step": 1470 + }, + { + "epoch": 1.3, + "learning_rate": 1.9478265974600822e-05, + "loss": 0.4778, + "step": 1471 + }, + { + "epoch": 1.3, + "learning_rate": 1.9477351894145045e-05, + "loss": 0.456, + "step": 1472 + }, + { + "epoch": 1.3, + "learning_rate": 1.947643703513947e-05, + "loss": 0.4832, + "step": 1473 + }, + { + "epoch": 1.3, + "learning_rate": 1.9475521397659262e-05, + "loss": 0.4647, + "step": 1474 + }, + { + "epoch": 1.3, + "learning_rate": 1.9474604981779635e-05, + "loss": 0.4929, + "step": 1475 + }, + { + "epoch": 1.31, + "learning_rate": 1.9473687787575867e-05, + "loss": 0.4785, + "step": 1476 + }, + { + "epoch": 1.31, + "learning_rate": 1.9472769815123308e-05, + "loss": 0.4629, + "step": 1477 + }, + { + "epoch": 1.31, + "learning_rate": 1.9471851064497366e-05, + "loss": 0.4588, + "step": 1478 + }, + { + "epoch": 1.31, + "learning_rate": 1.9470931535773518e-05, + "loss": 0.5089, + "step": 1479 + }, + { + "epoch": 1.31, + "learning_rate": 1.9470011229027302e-05, + "loss": 0.4914, + "step": 1480 + }, + { + "epoch": 1.31, + "learning_rate": 1.9469090144334315e-05, + "loss": 0.4808, + "step": 1481 + }, + { + "epoch": 1.31, + "learning_rate": 1.9468168281770226e-05, + "loss": 0.4397, + "step": 1482 + }, + { + "epoch": 1.31, + "learning_rate": 1.9467245641410765e-05, + "loss": 0.4675, + "step": 1483 + }, + { + "epoch": 1.31, + "learning_rate": 1.9466322223331726e-05, + "loss": 0.4738, + "step": 1484 + }, + { + "epoch": 1.31, + "learning_rate": 1.946539802760896e-05, + "loss": 0.4532, + "step": 1485 + }, + { + "epoch": 1.31, + "learning_rate": 1.94644730543184e-05, + "loss": 0.4788, + "step": 1486 + }, + { + "epoch": 1.32, + "learning_rate": 1.946354730353602e-05, + "loss": 0.4638, + "step": 1487 + }, + { + "epoch": 1.32, + "learning_rate": 1.9462620775337873e-05, + "loss": 0.4409, + "step": 1488 + }, + { + "epoch": 1.32, + "learning_rate": 1.946169346980008e-05, + "loss": 0.4786, + "step": 1489 + }, + { + "epoch": 1.32, + "learning_rate": 1.9460765386998802e-05, + "loss": 0.4706, + "step": 1490 + }, + { + "epoch": 1.32, + "learning_rate": 1.945983652701029e-05, + "loss": 0.47, + "step": 1491 + }, + { + "epoch": 1.32, + "learning_rate": 1.9458906889910843e-05, + "loss": 0.4729, + "step": 1492 + }, + { + "epoch": 1.32, + "learning_rate": 1.9457976475776834e-05, + "loss": 0.4623, + "step": 1493 + }, + { + "epoch": 1.32, + "learning_rate": 1.9457045284684697e-05, + "loss": 0.4845, + "step": 1494 + }, + { + "epoch": 1.32, + "learning_rate": 1.9456113316710922e-05, + "loss": 0.4551, + "step": 1495 + }, + { + "epoch": 1.32, + "learning_rate": 1.9455180571932067e-05, + "loss": 0.4544, + "step": 1496 + }, + { + "epoch": 1.32, + "learning_rate": 1.9454247050424765e-05, + "loss": 0.4644, + "step": 1497 + }, + { + "epoch": 1.33, + "learning_rate": 1.9453312752265693e-05, + "loss": 0.5028, + "step": 1498 + }, + { + "epoch": 1.33, + "learning_rate": 1.945237767753161e-05, + "loss": 0.4877, + "step": 1499 + }, + { + "epoch": 1.33, + "learning_rate": 1.945144182629933e-05, + "loss": 0.4578, + "step": 1500 + }, + { + "epoch": 1.33, + "learning_rate": 1.9450505198645726e-05, + "loss": 0.4699, + "step": 1501 + }, + { + "epoch": 1.33, + "learning_rate": 1.9449567794647745e-05, + "loss": 0.4474, + "step": 1502 + }, + { + "epoch": 1.33, + "learning_rate": 1.9448629614382394e-05, + "loss": 0.4831, + "step": 1503 + }, + { + "epoch": 1.33, + "learning_rate": 1.944769065792674e-05, + "loss": 0.4789, + "step": 1504 + }, + { + "epoch": 1.33, + "learning_rate": 1.944675092535792e-05, + "loss": 0.4727, + "step": 1505 + }, + { + "epoch": 1.33, + "learning_rate": 1.9445810416753126e-05, + "loss": 0.4763, + "step": 1506 + }, + { + "epoch": 1.33, + "learning_rate": 1.9444869132189625e-05, + "loss": 0.4501, + "step": 1507 + }, + { + "epoch": 1.33, + "learning_rate": 1.944392707174474e-05, + "loss": 0.4802, + "step": 1508 + }, + { + "epoch": 1.33, + "learning_rate": 1.944298423549586e-05, + "loss": 0.4892, + "step": 1509 + }, + { + "epoch": 1.34, + "learning_rate": 1.944204062352044e-05, + "loss": 0.5013, + "step": 1510 + }, + { + "epoch": 1.34, + "learning_rate": 1.9441096235895994e-05, + "loss": 0.4709, + "step": 1511 + }, + { + "epoch": 1.34, + "learning_rate": 1.94401510727001e-05, + "loss": 0.4705, + "step": 1512 + }, + { + "epoch": 1.34, + "learning_rate": 1.9439205134010403e-05, + "loss": 0.4732, + "step": 1513 + }, + { + "epoch": 1.34, + "learning_rate": 1.9438258419904615e-05, + "loss": 0.4552, + "step": 1514 + }, + { + "epoch": 1.34, + "learning_rate": 1.9437310930460497e-05, + "loss": 0.4636, + "step": 1515 + }, + { + "epoch": 1.34, + "learning_rate": 1.9436362665755894e-05, + "loss": 0.4906, + "step": 1516 + }, + { + "epoch": 1.34, + "learning_rate": 1.94354136258687e-05, + "loss": 0.4776, + "step": 1517 + }, + { + "epoch": 1.34, + "learning_rate": 1.9434463810876875e-05, + "loss": 0.4318, + "step": 1518 + }, + { + "epoch": 1.34, + "learning_rate": 1.9433513220858452e-05, + "loss": 0.4653, + "step": 1519 + }, + { + "epoch": 1.34, + "learning_rate": 1.9432561855891514e-05, + "loss": 0.4951, + "step": 1520 + }, + { + "epoch": 1.35, + "learning_rate": 1.9431609716054213e-05, + "loss": 0.4578, + "step": 1521 + }, + { + "epoch": 1.35, + "learning_rate": 1.943065680142477e-05, + "loss": 0.4585, + "step": 1522 + }, + { + "epoch": 1.35, + "learning_rate": 1.9429703112081462e-05, + "loss": 0.489, + "step": 1523 + }, + { + "epoch": 1.35, + "learning_rate": 1.9428748648102642e-05, + "loss": 0.4645, + "step": 1524 + }, + { + "epoch": 1.35, + "learning_rate": 1.942779340956671e-05, + "loss": 0.4876, + "step": 1525 + }, + { + "epoch": 1.35, + "learning_rate": 1.9426837396552135e-05, + "loss": 0.4885, + "step": 1526 + }, + { + "epoch": 1.35, + "learning_rate": 1.9425880609137454e-05, + "loss": 0.4632, + "step": 1527 + }, + { + "epoch": 1.35, + "learning_rate": 1.9424923047401272e-05, + "loss": 0.4537, + "step": 1528 + }, + { + "epoch": 1.35, + "learning_rate": 1.9423964711422245e-05, + "loss": 0.4748, + "step": 1529 + }, + { + "epoch": 1.35, + "learning_rate": 1.9423005601279098e-05, + "loss": 0.4669, + "step": 1530 + }, + { + "epoch": 1.35, + "learning_rate": 1.9422045717050623e-05, + "loss": 0.4754, + "step": 1531 + }, + { + "epoch": 1.36, + "learning_rate": 1.9421085058815672e-05, + "loss": 0.4747, + "step": 1532 + }, + { + "epoch": 1.36, + "learning_rate": 1.9420123626653162e-05, + "loss": 0.5003, + "step": 1533 + }, + { + "epoch": 1.36, + "learning_rate": 1.9419161420642076e-05, + "loss": 0.4538, + "step": 1534 + }, + { + "epoch": 1.36, + "learning_rate": 1.9418198440861453e-05, + "loss": 0.4818, + "step": 1535 + }, + { + "epoch": 1.36, + "learning_rate": 1.9417234687390402e-05, + "loss": 0.4861, + "step": 1536 + }, + { + "epoch": 1.36, + "learning_rate": 1.9416270160308097e-05, + "loss": 0.4526, + "step": 1537 + }, + { + "epoch": 1.36, + "learning_rate": 1.9415304859693767e-05, + "loss": 0.4511, + "step": 1538 + }, + { + "epoch": 1.36, + "learning_rate": 1.9414338785626713e-05, + "loss": 0.4531, + "step": 1539 + }, + { + "epoch": 1.36, + "learning_rate": 1.9413371938186296e-05, + "loss": 0.4747, + "step": 1540 + }, + { + "epoch": 1.36, + "learning_rate": 1.941240431745194e-05, + "loss": 0.4985, + "step": 1541 + }, + { + "epoch": 1.36, + "learning_rate": 1.9411435923503137e-05, + "loss": 0.4785, + "step": 1542 + }, + { + "epoch": 1.36, + "learning_rate": 1.9410466756419436e-05, + "loss": 0.4472, + "step": 1543 + }, + { + "epoch": 1.37, + "learning_rate": 1.940949681628045e-05, + "loss": 0.4929, + "step": 1544 + }, + { + "epoch": 1.37, + "learning_rate": 1.940852610316587e-05, + "loss": 0.4719, + "step": 1545 + }, + { + "epoch": 1.37, + "learning_rate": 1.940755461715542e-05, + "loss": 0.4814, + "step": 1546 + }, + { + "epoch": 1.37, + "learning_rate": 1.9406582358328922e-05, + "loss": 0.4649, + "step": 1547 + }, + { + "epoch": 1.37, + "learning_rate": 1.9405609326766237e-05, + "loss": 0.4851, + "step": 1548 + }, + { + "epoch": 1.37, + "learning_rate": 1.94046355225473e-05, + "loss": 0.4646, + "step": 1549 + }, + { + "epoch": 1.37, + "learning_rate": 1.940366094575211e-05, + "loss": 0.4754, + "step": 1550 + }, + { + "epoch": 1.37, + "learning_rate": 1.9402685596460722e-05, + "loss": 0.4873, + "step": 1551 + }, + { + "epoch": 1.37, + "learning_rate": 1.9401709474753265e-05, + "loss": 0.4654, + "step": 1552 + }, + { + "epoch": 1.37, + "learning_rate": 1.940073258070992e-05, + "loss": 0.4734, + "step": 1553 + }, + { + "epoch": 1.37, + "learning_rate": 1.9399754914410946e-05, + "loss": 0.4752, + "step": 1554 + }, + { + "epoch": 1.38, + "learning_rate": 1.9398776475936648e-05, + "loss": 0.4831, + "step": 1555 + }, + { + "epoch": 1.38, + "learning_rate": 1.9397797265367407e-05, + "loss": 0.4707, + "step": 1556 + }, + { + "epoch": 1.38, + "learning_rate": 1.9396817282783667e-05, + "loss": 0.4847, + "step": 1557 + }, + { + "epoch": 1.38, + "learning_rate": 1.9395836528265925e-05, + "loss": 0.4593, + "step": 1558 + }, + { + "epoch": 1.38, + "learning_rate": 1.939485500189475e-05, + "loss": 0.495, + "step": 1559 + }, + { + "epoch": 1.38, + "learning_rate": 1.939387270375078e-05, + "loss": 0.4808, + "step": 1560 + }, + { + "epoch": 1.38, + "learning_rate": 1.93928896339147e-05, + "loss": 0.487, + "step": 1561 + }, + { + "epoch": 1.38, + "learning_rate": 1.939190579246727e-05, + "loss": 0.4743, + "step": 1562 + }, + { + "epoch": 1.38, + "learning_rate": 1.9390921179489316e-05, + "loss": 0.4644, + "step": 1563 + }, + { + "epoch": 1.38, + "learning_rate": 1.938993579506172e-05, + "loss": 0.462, + "step": 1564 + }, + { + "epoch": 1.38, + "learning_rate": 1.9388949639265426e-05, + "loss": 0.4687, + "step": 1565 + }, + { + "epoch": 1.39, + "learning_rate": 1.938796271218145e-05, + "loss": 0.4935, + "step": 1566 + }, + { + "epoch": 1.39, + "learning_rate": 1.9386975013890863e-05, + "loss": 0.4721, + "step": 1567 + }, + { + "epoch": 1.39, + "learning_rate": 1.9385986544474807e-05, + "loss": 0.4815, + "step": 1568 + }, + { + "epoch": 1.39, + "learning_rate": 1.938499730401448e-05, + "loss": 0.4295, + "step": 1569 + }, + { + "epoch": 1.39, + "learning_rate": 1.938400729259115e-05, + "loss": 0.4578, + "step": 1570 + }, + { + "epoch": 1.39, + "learning_rate": 1.9383016510286133e-05, + "loss": 0.4662, + "step": 1571 + }, + { + "epoch": 1.39, + "learning_rate": 1.9382024957180835e-05, + "loss": 0.4709, + "step": 1572 + }, + { + "epoch": 1.39, + "learning_rate": 1.9381032633356706e-05, + "loss": 0.4669, + "step": 1573 + }, + { + "epoch": 1.39, + "learning_rate": 1.9380039538895264e-05, + "loss": 0.4564, + "step": 1574 + }, + { + "epoch": 1.39, + "learning_rate": 1.9379045673878086e-05, + "loss": 0.5005, + "step": 1575 + }, + { + "epoch": 1.39, + "learning_rate": 1.937805103838682e-05, + "loss": 0.4734, + "step": 1576 + }, + { + "epoch": 1.4, + "learning_rate": 1.9377055632503176e-05, + "loss": 0.4618, + "step": 1577 + }, + { + "epoch": 1.4, + "learning_rate": 1.937605945630892e-05, + "loss": 0.4722, + "step": 1578 + }, + { + "epoch": 1.4, + "learning_rate": 1.9375062509885892e-05, + "loss": 0.4727, + "step": 1579 + }, + { + "epoch": 1.4, + "learning_rate": 1.937406479331598e-05, + "loss": 0.5054, + "step": 1580 + }, + { + "epoch": 1.4, + "learning_rate": 1.9373066306681156e-05, + "loss": 0.477, + "step": 1581 + }, + { + "epoch": 1.4, + "learning_rate": 1.937206705006344e-05, + "loss": 0.4827, + "step": 1582 + }, + { + "epoch": 1.4, + "learning_rate": 1.9371067023544915e-05, + "loss": 0.4382, + "step": 1583 + }, + { + "epoch": 1.4, + "learning_rate": 1.9370066227207735e-05, + "loss": 0.4883, + "step": 1584 + }, + { + "epoch": 1.4, + "learning_rate": 1.9369064661134117e-05, + "loss": 0.4649, + "step": 1585 + }, + { + "epoch": 1.4, + "learning_rate": 1.9368062325406332e-05, + "loss": 0.4837, + "step": 1586 + }, + { + "epoch": 1.4, + "learning_rate": 1.936705922010673e-05, + "loss": 0.4877, + "step": 1587 + }, + { + "epoch": 1.4, + "learning_rate": 1.9366055345317702e-05, + "loss": 0.4605, + "step": 1588 + }, + { + "epoch": 1.41, + "learning_rate": 1.9365050701121726e-05, + "loss": 0.5015, + "step": 1589 + }, + { + "epoch": 1.41, + "learning_rate": 1.9364045287601322e-05, + "loss": 0.4607, + "step": 1590 + }, + { + "epoch": 1.41, + "learning_rate": 1.9363039104839088e-05, + "loss": 0.4655, + "step": 1591 + }, + { + "epoch": 1.41, + "learning_rate": 1.9362032152917683e-05, + "loss": 0.488, + "step": 1592 + }, + { + "epoch": 1.41, + "learning_rate": 1.9361024431919825e-05, + "loss": 0.4829, + "step": 1593 + }, + { + "epoch": 1.41, + "learning_rate": 1.9360015941928293e-05, + "loss": 0.4791, + "step": 1594 + }, + { + "epoch": 1.41, + "learning_rate": 1.935900668302594e-05, + "loss": 0.4728, + "step": 1595 + }, + { + "epoch": 1.41, + "learning_rate": 1.9357996655295665e-05, + "loss": 0.4765, + "step": 1596 + }, + { + "epoch": 1.41, + "learning_rate": 1.935698585882045e-05, + "loss": 0.4586, + "step": 1597 + }, + { + "epoch": 1.41, + "learning_rate": 1.9355974293683322e-05, + "loss": 0.4771, + "step": 1598 + }, + { + "epoch": 1.41, + "learning_rate": 1.9354961959967386e-05, + "loss": 0.4907, + "step": 1599 + }, + { + "epoch": 1.42, + "learning_rate": 1.93539488577558e-05, + "loss": 0.4729, + "step": 1600 + }, + { + "epoch": 1.42, + "learning_rate": 1.9352934987131796e-05, + "loss": 0.4824, + "step": 1601 + }, + { + "epoch": 1.42, + "learning_rate": 1.935192034817865e-05, + "loss": 0.4772, + "step": 1602 + }, + { + "epoch": 1.42, + "learning_rate": 1.9350904940979722e-05, + "loss": 0.4588, + "step": 1603 + }, + { + "epoch": 1.42, + "learning_rate": 1.934988876561842e-05, + "loss": 0.4868, + "step": 1604 + }, + { + "epoch": 1.42, + "learning_rate": 1.9348871822178227e-05, + "loss": 0.494, + "step": 1605 + }, + { + "epoch": 1.42, + "learning_rate": 1.9347854110742682e-05, + "loss": 0.4971, + "step": 1606 + }, + { + "epoch": 1.42, + "learning_rate": 1.9346835631395386e-05, + "loss": 0.468, + "step": 1607 + }, + { + "epoch": 1.42, + "learning_rate": 1.9345816384220004e-05, + "loss": 0.4647, + "step": 1608 + }, + { + "epoch": 1.42, + "learning_rate": 1.934479636930027e-05, + "loss": 0.4638, + "step": 1609 + }, + { + "epoch": 1.42, + "learning_rate": 1.9343775586719978e-05, + "loss": 0.4833, + "step": 1610 + }, + { + "epoch": 1.43, + "learning_rate": 1.9342754036562975e-05, + "loss": 0.5008, + "step": 1611 + }, + { + "epoch": 1.43, + "learning_rate": 1.934173171891319e-05, + "loss": 0.4719, + "step": 1612 + }, + { + "epoch": 1.43, + "learning_rate": 1.9340708633854597e-05, + "loss": 0.4754, + "step": 1613 + }, + { + "epoch": 1.43, + "learning_rate": 1.9339684781471245e-05, + "loss": 0.462, + "step": 1614 + }, + { + "epoch": 1.43, + "learning_rate": 1.933866016184724e-05, + "loss": 0.5023, + "step": 1615 + }, + { + "epoch": 1.43, + "learning_rate": 1.9337634775066757e-05, + "loss": 0.4572, + "step": 1616 + }, + { + "epoch": 1.43, + "learning_rate": 1.9336608621214027e-05, + "loss": 0.4867, + "step": 1617 + }, + { + "epoch": 1.43, + "learning_rate": 1.9335581700373343e-05, + "loss": 0.4601, + "step": 1618 + }, + { + "epoch": 1.43, + "learning_rate": 1.933455401262907e-05, + "loss": 0.4857, + "step": 1619 + }, + { + "epoch": 1.43, + "learning_rate": 1.933352555806563e-05, + "loss": 0.4645, + "step": 1620 + }, + { + "epoch": 1.43, + "learning_rate": 1.9332496336767507e-05, + "loss": 0.4643, + "step": 1621 + }, + { + "epoch": 1.43, + "learning_rate": 1.9331466348819257e-05, + "loss": 0.4652, + "step": 1622 + }, + { + "epoch": 1.44, + "learning_rate": 1.933043559430548e-05, + "loss": 0.4671, + "step": 1623 + }, + { + "epoch": 1.44, + "learning_rate": 1.9329404073310863e-05, + "loss": 0.4715, + "step": 1624 + }, + { + "epoch": 1.44, + "learning_rate": 1.9328371785920134e-05, + "loss": 0.4799, + "step": 1625 + }, + { + "epoch": 1.44, + "learning_rate": 1.93273387322181e-05, + "loss": 0.4749, + "step": 1626 + }, + { + "epoch": 1.44, + "learning_rate": 1.9326304912289622e-05, + "loss": 0.4754, + "step": 1627 + }, + { + "epoch": 1.44, + "learning_rate": 1.9325270326219626e-05, + "loss": 0.4644, + "step": 1628 + }, + { + "epoch": 1.44, + "learning_rate": 1.9324234974093107e-05, + "loss": 0.4651, + "step": 1629 + }, + { + "epoch": 1.44, + "learning_rate": 1.9323198855995108e-05, + "loss": 0.4422, + "step": 1630 + }, + { + "epoch": 1.44, + "learning_rate": 1.9322161972010757e-05, + "loss": 0.4668, + "step": 1631 + }, + { + "epoch": 1.44, + "learning_rate": 1.932112432222522e-05, + "loss": 0.4805, + "step": 1632 + }, + { + "epoch": 1.44, + "learning_rate": 1.9320085906723746e-05, + "loss": 0.4884, + "step": 1633 + }, + { + "epoch": 1.45, + "learning_rate": 1.931904672559164e-05, + "loss": 0.4796, + "step": 1634 + }, + { + "epoch": 1.45, + "learning_rate": 1.9318006778914263e-05, + "loss": 0.4913, + "step": 1635 + }, + { + "epoch": 1.45, + "learning_rate": 1.9316966066777047e-05, + "loss": 0.4598, + "step": 1636 + }, + { + "epoch": 1.45, + "learning_rate": 1.9315924589265488e-05, + "loss": 0.4661, + "step": 1637 + }, + { + "epoch": 1.45, + "learning_rate": 1.9314882346465144e-05, + "loss": 0.4804, + "step": 1638 + }, + { + "epoch": 1.45, + "learning_rate": 1.931383933846162e-05, + "loss": 0.4991, + "step": 1639 + }, + { + "epoch": 1.45, + "learning_rate": 1.9312795565340616e-05, + "loss": 0.4611, + "step": 1640 + }, + { + "epoch": 1.45, + "learning_rate": 1.9311751027187863e-05, + "loss": 0.466, + "step": 1641 + }, + { + "epoch": 1.45, + "learning_rate": 1.9310705724089173e-05, + "loss": 0.4803, + "step": 1642 + }, + { + "epoch": 1.45, + "learning_rate": 1.9309659656130417e-05, + "loss": 0.4801, + "step": 1643 + }, + { + "epoch": 1.45, + "learning_rate": 1.930861282339753e-05, + "loss": 0.5144, + "step": 1644 + }, + { + "epoch": 1.46, + "learning_rate": 1.93075652259765e-05, + "loss": 0.4746, + "step": 1645 + }, + { + "epoch": 1.46, + "learning_rate": 1.9306516863953385e-05, + "loss": 0.4599, + "step": 1646 + }, + { + "epoch": 1.46, + "learning_rate": 1.9305467737414317e-05, + "loss": 0.4728, + "step": 1647 + }, + { + "epoch": 1.46, + "learning_rate": 1.9304417846445473e-05, + "loss": 0.4786, + "step": 1648 + }, + { + "epoch": 1.46, + "learning_rate": 1.9303367191133102e-05, + "loss": 0.4635, + "step": 1649 + }, + { + "epoch": 1.46, + "learning_rate": 1.9302315771563512e-05, + "loss": 0.4828, + "step": 1650 + }, + { + "epoch": 1.46, + "learning_rate": 1.9301263587823077e-05, + "loss": 0.4707, + "step": 1651 + }, + { + "epoch": 1.46, + "learning_rate": 1.930021063999823e-05, + "loss": 0.4721, + "step": 1652 + }, + { + "epoch": 1.46, + "learning_rate": 1.9299156928175474e-05, + "loss": 0.4839, + "step": 1653 + }, + { + "epoch": 1.46, + "learning_rate": 1.929810245244136e-05, + "loss": 0.479, + "step": 1654 + }, + { + "epoch": 1.46, + "learning_rate": 1.9297047212882524e-05, + "loss": 0.4484, + "step": 1655 + }, + { + "epoch": 1.46, + "learning_rate": 1.9295991209585643e-05, + "loss": 0.4802, + "step": 1656 + }, + { + "epoch": 1.47, + "learning_rate": 1.9294934442637474e-05, + "loss": 0.4832, + "step": 1657 + }, + { + "epoch": 1.47, + "learning_rate": 1.929387691212482e-05, + "loss": 0.4292, + "step": 1658 + }, + { + "epoch": 1.47, + "learning_rate": 1.9292818618134557e-05, + "loss": 0.4742, + "step": 1659 + }, + { + "epoch": 1.47, + "learning_rate": 1.9291759560753628e-05, + "loss": 0.4663, + "step": 1660 + }, + { + "epoch": 1.47, + "learning_rate": 1.929069974006903e-05, + "loss": 0.4663, + "step": 1661 + }, + { + "epoch": 1.47, + "learning_rate": 1.9289639156167823e-05, + "loss": 0.4836, + "step": 1662 + }, + { + "epoch": 1.47, + "learning_rate": 1.9288577809137138e-05, + "loss": 0.4649, + "step": 1663 + }, + { + "epoch": 1.47, + "learning_rate": 1.9287515699064158e-05, + "loss": 0.5066, + "step": 1664 + }, + { + "epoch": 1.47, + "learning_rate": 1.9286452826036133e-05, + "loss": 0.4782, + "step": 1665 + }, + { + "epoch": 1.47, + "learning_rate": 1.928538919014038e-05, + "loss": 0.4653, + "step": 1666 + }, + { + "epoch": 1.47, + "learning_rate": 1.9284324791464276e-05, + "loss": 0.4611, + "step": 1667 + }, + { + "epoch": 1.48, + "learning_rate": 1.9283259630095253e-05, + "loss": 0.469, + "step": 1668 + }, + { + "epoch": 1.48, + "learning_rate": 1.928219370612082e-05, + "loss": 0.4957, + "step": 1669 + }, + { + "epoch": 1.48, + "learning_rate": 1.928112701962854e-05, + "loss": 0.4757, + "step": 1670 + }, + { + "epoch": 1.48, + "learning_rate": 1.9280059570706032e-05, + "loss": 0.4794, + "step": 1671 + }, + { + "epoch": 1.48, + "learning_rate": 1.9278991359440994e-05, + "loss": 0.4565, + "step": 1672 + }, + { + "epoch": 1.48, + "learning_rate": 1.9277922385921174e-05, + "loss": 0.5014, + "step": 1673 + }, + { + "epoch": 1.48, + "learning_rate": 1.9276852650234387e-05, + "loss": 0.4711, + "step": 1674 + }, + { + "epoch": 1.48, + "learning_rate": 1.9275782152468512e-05, + "loss": 0.4834, + "step": 1675 + }, + { + "epoch": 1.48, + "learning_rate": 1.9274710892711487e-05, + "loss": 0.4618, + "step": 1676 + }, + { + "epoch": 1.48, + "learning_rate": 1.9273638871051314e-05, + "loss": 0.4917, + "step": 1677 + }, + { + "epoch": 1.48, + "learning_rate": 1.9272566087576057e-05, + "loss": 0.4593, + "step": 1678 + }, + { + "epoch": 1.49, + "learning_rate": 1.9271492542373846e-05, + "loss": 0.4545, + "step": 1679 + }, + { + "epoch": 1.49, + "learning_rate": 1.9270418235532866e-05, + "loss": 0.4472, + "step": 1680 + }, + { + "epoch": 1.49, + "learning_rate": 1.926934316714138e-05, + "loss": 0.4381, + "step": 1681 + }, + { + "epoch": 1.49, + "learning_rate": 1.9268267337287692e-05, + "loss": 0.4601, + "step": 1682 + }, + { + "epoch": 1.49, + "learning_rate": 1.9267190746060186e-05, + "loss": 0.4608, + "step": 1683 + }, + { + "epoch": 1.49, + "learning_rate": 1.92661133935473e-05, + "loss": 0.4622, + "step": 1684 + }, + { + "epoch": 1.49, + "learning_rate": 1.926503527983754e-05, + "loss": 0.479, + "step": 1685 + }, + { + "epoch": 1.49, + "learning_rate": 1.9263956405019466e-05, + "loss": 0.4771, + "step": 1686 + }, + { + "epoch": 1.49, + "learning_rate": 1.9262876769181708e-05, + "loss": 0.4701, + "step": 1687 + }, + { + "epoch": 1.49, + "learning_rate": 1.926179637241296e-05, + "loss": 0.4597, + "step": 1688 + }, + { + "epoch": 1.49, + "learning_rate": 1.9260715214801973e-05, + "loss": 0.4943, + "step": 1689 + }, + { + "epoch": 1.49, + "learning_rate": 1.925963329643756e-05, + "loss": 0.4504, + "step": 1690 + }, + { + "epoch": 1.5, + "learning_rate": 1.92585506174086e-05, + "loss": 0.4584, + "step": 1691 + }, + { + "epoch": 1.5, + "learning_rate": 1.9257467177804033e-05, + "loss": 0.4707, + "step": 1692 + }, + { + "epoch": 1.5, + "learning_rate": 1.9256382977712867e-05, + "loss": 0.4652, + "step": 1693 + }, + { + "epoch": 1.5, + "learning_rate": 1.925529801722416e-05, + "loss": 0.4896, + "step": 1694 + }, + { + "epoch": 1.5, + "learning_rate": 1.9254212296427043e-05, + "loss": 0.4731, + "step": 1695 + }, + { + "epoch": 1.5, + "learning_rate": 1.9253125815410706e-05, + "loss": 0.4839, + "step": 1696 + }, + { + "epoch": 1.5, + "learning_rate": 1.9252038574264403e-05, + "loss": 0.4662, + "step": 1697 + }, + { + "epoch": 1.5, + "learning_rate": 1.9250950573077453e-05, + "loss": 0.4778, + "step": 1698 + }, + { + "epoch": 1.5, + "learning_rate": 1.924986181193922e-05, + "loss": 0.4719, + "step": 1699 + }, + { + "epoch": 1.5, + "learning_rate": 1.924877229093916e-05, + "loss": 0.4698, + "step": 1700 + }, + { + "epoch": 1.5, + "learning_rate": 1.9247682010166763e-05, + "loss": 0.4733, + "step": 1701 + }, + { + "epoch": 1.51, + "learning_rate": 1.92465909697116e-05, + "loss": 0.4742, + "step": 1702 + }, + { + "epoch": 1.51, + "learning_rate": 1.9245499169663303e-05, + "loss": 0.5048, + "step": 1703 + }, + { + "epoch": 1.51, + "learning_rate": 1.924440661011155e-05, + "loss": 0.4713, + "step": 1704 + }, + { + "epoch": 1.51, + "learning_rate": 1.9243313291146103e-05, + "loss": 0.499, + "step": 1705 + }, + { + "epoch": 1.51, + "learning_rate": 1.924221921285677e-05, + "loss": 0.4558, + "step": 1706 + }, + { + "epoch": 1.51, + "learning_rate": 1.924112437533343e-05, + "loss": 0.46, + "step": 1707 + }, + { + "epoch": 1.51, + "learning_rate": 1.924002877866603e-05, + "loss": 0.4721, + "step": 1708 + }, + { + "epoch": 1.51, + "learning_rate": 1.9238932422944558e-05, + "loss": 0.4645, + "step": 1709 + }, + { + "epoch": 1.51, + "learning_rate": 1.9237835308259084e-05, + "loss": 0.4738, + "step": 1710 + }, + { + "epoch": 1.51, + "learning_rate": 1.9236737434699737e-05, + "loss": 0.4798, + "step": 1711 + }, + { + "epoch": 1.51, + "learning_rate": 1.9235638802356703e-05, + "loss": 0.4675, + "step": 1712 + }, + { + "epoch": 1.52, + "learning_rate": 1.923453941132023e-05, + "loss": 0.4807, + "step": 1713 + }, + { + "epoch": 1.52, + "learning_rate": 1.923343926168064e-05, + "loss": 0.4776, + "step": 1714 + }, + { + "epoch": 1.52, + "learning_rate": 1.9232338353528295e-05, + "loss": 0.4492, + "step": 1715 + }, + { + "epoch": 1.52, + "learning_rate": 1.9231236686953646e-05, + "loss": 0.4556, + "step": 1716 + }, + { + "epoch": 1.52, + "learning_rate": 1.923013426204719e-05, + "loss": 0.4775, + "step": 1717 + }, + { + "epoch": 1.52, + "learning_rate": 1.9229031078899486e-05, + "loss": 0.4398, + "step": 1718 + }, + { + "epoch": 1.52, + "learning_rate": 1.922792713760116e-05, + "loss": 0.454, + "step": 1719 + }, + { + "epoch": 1.52, + "learning_rate": 1.9226822438242897e-05, + "loss": 0.4946, + "step": 1720 + }, + { + "epoch": 1.52, + "learning_rate": 1.922571698091545e-05, + "loss": 0.4879, + "step": 1721 + }, + { + "epoch": 1.52, + "learning_rate": 1.9224610765709632e-05, + "loss": 0.473, + "step": 1722 + }, + { + "epoch": 1.52, + "learning_rate": 1.922350379271631e-05, + "loss": 0.4421, + "step": 1723 + }, + { + "epoch": 1.53, + "learning_rate": 1.9222396062026427e-05, + "loss": 0.4758, + "step": 1724 + }, + { + "epoch": 1.53, + "learning_rate": 1.922128757373098e-05, + "loss": 0.4911, + "step": 1725 + }, + { + "epoch": 1.53, + "learning_rate": 1.9220178327921026e-05, + "loss": 0.4719, + "step": 1726 + }, + { + "epoch": 1.53, + "learning_rate": 1.921906832468769e-05, + "loss": 0.4726, + "step": 1727 + }, + { + "epoch": 1.53, + "learning_rate": 1.921795756412216e-05, + "loss": 0.4661, + "step": 1728 + }, + { + "epoch": 1.53, + "learning_rate": 1.921684604631568e-05, + "loss": 0.4829, + "step": 1729 + }, + { + "epoch": 1.53, + "learning_rate": 1.921573377135956e-05, + "loss": 0.4881, + "step": 1730 + }, + { + "epoch": 1.53, + "learning_rate": 1.9214620739345168e-05, + "loss": 0.4538, + "step": 1731 + }, + { + "epoch": 1.53, + "learning_rate": 1.921350695036394e-05, + "loss": 0.4727, + "step": 1732 + }, + { + "epoch": 1.53, + "learning_rate": 1.921239240450738e-05, + "loss": 0.4824, + "step": 1733 + }, + { + "epoch": 1.53, + "learning_rate": 1.9211277101867036e-05, + "loss": 0.4866, + "step": 1734 + }, + { + "epoch": 1.53, + "learning_rate": 1.9210161042534533e-05, + "loss": 0.4566, + "step": 1735 + }, + { + "epoch": 1.54, + "learning_rate": 1.9209044226601556e-05, + "loss": 0.4815, + "step": 1736 + }, + { + "epoch": 1.54, + "learning_rate": 1.9207926654159843e-05, + "loss": 0.4682, + "step": 1737 + }, + { + "epoch": 1.54, + "learning_rate": 1.9206808325301203e-05, + "loss": 0.4361, + "step": 1738 + }, + { + "epoch": 1.54, + "learning_rate": 1.9205689240117508e-05, + "loss": 0.4732, + "step": 1739 + }, + { + "epoch": 1.54, + "learning_rate": 1.9204569398700686e-05, + "loss": 0.4483, + "step": 1740 + }, + { + "epoch": 1.54, + "learning_rate": 1.9203448801142733e-05, + "loss": 0.4744, + "step": 1741 + }, + { + "epoch": 1.54, + "learning_rate": 1.9202327447535704e-05, + "loss": 0.4762, + "step": 1742 + }, + { + "epoch": 1.54, + "learning_rate": 1.9201205337971715e-05, + "loss": 0.4637, + "step": 1743 + }, + { + "epoch": 1.54, + "learning_rate": 1.9200082472542944e-05, + "loss": 0.4619, + "step": 1744 + }, + { + "epoch": 1.54, + "learning_rate": 1.9198958851341633e-05, + "loss": 0.4776, + "step": 1745 + }, + { + "epoch": 1.54, + "learning_rate": 1.9197834474460092e-05, + "loss": 0.4732, + "step": 1746 + }, + { + "epoch": 1.55, + "learning_rate": 1.9196709341990677e-05, + "loss": 0.4499, + "step": 1747 + }, + { + "epoch": 1.55, + "learning_rate": 1.9195583454025824e-05, + "loss": 0.4748, + "step": 1748 + }, + { + "epoch": 1.55, + "learning_rate": 1.919445681065802e-05, + "loss": 0.4723, + "step": 1749 + }, + { + "epoch": 1.55, + "learning_rate": 1.9193329411979818e-05, + "loss": 0.5005, + "step": 1750 + }, + { + "epoch": 1.55, + "learning_rate": 1.9192201258083826e-05, + "loss": 0.4458, + "step": 1751 + }, + { + "epoch": 1.55, + "learning_rate": 1.919107234906273e-05, + "loss": 0.4838, + "step": 1752 + }, + { + "epoch": 1.55, + "learning_rate": 1.9189942685009265e-05, + "loss": 0.4562, + "step": 1753 + }, + { + "epoch": 1.55, + "learning_rate": 1.9188812266016224e-05, + "loss": 0.4495, + "step": 1754 + }, + { + "epoch": 1.55, + "learning_rate": 1.918768109217648e-05, + "loss": 0.4882, + "step": 1755 + }, + { + "epoch": 1.55, + "learning_rate": 1.9186549163582947e-05, + "loss": 0.5227, + "step": 1756 + }, + { + "epoch": 1.55, + "learning_rate": 1.918541648032862e-05, + "loss": 0.4855, + "step": 1757 + }, + { + "epoch": 1.56, + "learning_rate": 1.918428304250654e-05, + "loss": 0.5076, + "step": 1758 + }, + { + "epoch": 1.56, + "learning_rate": 1.918314885020982e-05, + "loss": 0.4644, + "step": 1759 + }, + { + "epoch": 1.56, + "learning_rate": 1.9182013903531636e-05, + "loss": 0.5166, + "step": 1760 + }, + { + "epoch": 1.56, + "learning_rate": 1.9180878202565217e-05, + "loss": 0.4718, + "step": 1761 + }, + { + "epoch": 1.56, + "learning_rate": 1.917974174740386e-05, + "loss": 0.4733, + "step": 1762 + }, + { + "epoch": 1.56, + "learning_rate": 1.9178604538140923e-05, + "loss": 0.4692, + "step": 1763 + }, + { + "epoch": 1.56, + "learning_rate": 1.917746657486983e-05, + "loss": 0.4578, + "step": 1764 + }, + { + "epoch": 1.56, + "learning_rate": 1.9176327857684053e-05, + "loss": 0.4962, + "step": 1765 + }, + { + "epoch": 1.56, + "learning_rate": 1.9175188386677147e-05, + "loss": 0.4656, + "step": 1766 + }, + { + "epoch": 1.56, + "learning_rate": 1.9174048161942712e-05, + "loss": 0.4466, + "step": 1767 + }, + { + "epoch": 1.56, + "learning_rate": 1.917290718357442e-05, + "loss": 0.4968, + "step": 1768 + }, + { + "epoch": 1.56, + "learning_rate": 1.9171765451665997e-05, + "loss": 0.4816, + "step": 1769 + }, + { + "epoch": 1.57, + "learning_rate": 1.917062296631123e-05, + "loss": 0.4522, + "step": 1770 + }, + { + "epoch": 1.57, + "learning_rate": 1.9169479727603984e-05, + "loss": 0.4743, + "step": 1771 + }, + { + "epoch": 1.57, + "learning_rate": 1.916833573563816e-05, + "loss": 0.4749, + "step": 1772 + }, + { + "epoch": 1.57, + "learning_rate": 1.916719099050775e-05, + "loss": 0.5033, + "step": 1773 + }, + { + "epoch": 1.57, + "learning_rate": 1.9166045492306783e-05, + "loss": 0.4379, + "step": 1774 + }, + { + "epoch": 1.57, + "learning_rate": 1.9164899241129366e-05, + "loss": 0.4791, + "step": 1775 + }, + { + "epoch": 1.57, + "learning_rate": 1.9163752237069655e-05, + "loss": 0.4926, + "step": 1776 + }, + { + "epoch": 1.57, + "learning_rate": 1.9162604480221876e-05, + "loss": 0.4925, + "step": 1777 + }, + { + "epoch": 1.57, + "learning_rate": 1.9161455970680323e-05, + "loss": 0.4465, + "step": 1778 + }, + { + "epoch": 1.57, + "learning_rate": 1.9160306708539337e-05, + "loss": 0.4467, + "step": 1779 + }, + { + "epoch": 1.57, + "learning_rate": 1.9159156693893328e-05, + "loss": 0.4748, + "step": 1780 + }, + { + "epoch": 1.58, + "learning_rate": 1.9158005926836772e-05, + "loss": 0.4585, + "step": 1781 + }, + { + "epoch": 1.58, + "learning_rate": 1.91568544074642e-05, + "loss": 0.4696, + "step": 1782 + }, + { + "epoch": 1.58, + "learning_rate": 1.915570213587021e-05, + "loss": 0.4516, + "step": 1783 + }, + { + "epoch": 1.58, + "learning_rate": 1.9154549112149454e-05, + "loss": 0.4516, + "step": 1784 + }, + { + "epoch": 1.58, + "learning_rate": 1.915339533639666e-05, + "loss": 0.4774, + "step": 1785 + }, + { + "epoch": 1.58, + "learning_rate": 1.91522408087066e-05, + "loss": 0.4573, + "step": 1786 + }, + { + "epoch": 1.58, + "learning_rate": 1.915108552917412e-05, + "loss": 0.4614, + "step": 1787 + }, + { + "epoch": 1.58, + "learning_rate": 1.9149929497894125e-05, + "loss": 0.4861, + "step": 1788 + }, + { + "epoch": 1.58, + "learning_rate": 1.914877271496158e-05, + "loss": 0.4738, + "step": 1789 + }, + { + "epoch": 1.58, + "learning_rate": 1.9147615180471513e-05, + "loss": 0.4786, + "step": 1790 + }, + { + "epoch": 1.58, + "learning_rate": 1.914645689451902e-05, + "loss": 0.5009, + "step": 1791 + }, + { + "epoch": 1.59, + "learning_rate": 1.9145297857199243e-05, + "loss": 0.4637, + "step": 1792 + }, + { + "epoch": 1.59, + "learning_rate": 1.9144138068607398e-05, + "loss": 0.4791, + "step": 1793 + }, + { + "epoch": 1.59, + "learning_rate": 1.9142977528838763e-05, + "loss": 0.4747, + "step": 1794 + }, + { + "epoch": 1.59, + "learning_rate": 1.914181623798867e-05, + "loss": 0.4641, + "step": 1795 + }, + { + "epoch": 1.59, + "learning_rate": 1.914065419615252e-05, + "loss": 0.5084, + "step": 1796 + }, + { + "epoch": 1.59, + "learning_rate": 1.9139491403425774e-05, + "loss": 0.4662, + "step": 1797 + }, + { + "epoch": 1.59, + "learning_rate": 1.9138327859903955e-05, + "loss": 0.4944, + "step": 1798 + }, + { + "epoch": 1.59, + "learning_rate": 1.913716356568264e-05, + "loss": 0.4704, + "step": 1799 + }, + { + "epoch": 1.59, + "learning_rate": 1.9135998520857475e-05, + "loss": 0.4678, + "step": 1800 + }, + { + "epoch": 1.59, + "learning_rate": 1.913483272552417e-05, + "loss": 0.4858, + "step": 1801 + }, + { + "epoch": 1.59, + "learning_rate": 1.9133666179778498e-05, + "loss": 0.4782, + "step": 1802 + }, + { + "epoch": 1.59, + "learning_rate": 1.913249888371628e-05, + "loss": 0.4674, + "step": 1803 + }, + { + "epoch": 1.6, + "learning_rate": 1.9131330837433407e-05, + "loss": 0.4934, + "step": 1804 + }, + { + "epoch": 1.6, + "learning_rate": 1.913016204102584e-05, + "loss": 0.4716, + "step": 1805 + }, + { + "epoch": 1.6, + "learning_rate": 1.912899249458959e-05, + "loss": 0.4805, + "step": 1806 + }, + { + "epoch": 1.6, + "learning_rate": 1.912782219822073e-05, + "loss": 0.5072, + "step": 1807 + }, + { + "epoch": 1.6, + "learning_rate": 1.9126651152015404e-05, + "loss": 0.4899, + "step": 1808 + }, + { + "epoch": 1.6, + "learning_rate": 1.9125479356069806e-05, + "loss": 0.4936, + "step": 1809 + }, + { + "epoch": 1.6, + "learning_rate": 1.9124306810480205e-05, + "loss": 0.4651, + "step": 1810 + }, + { + "epoch": 1.6, + "learning_rate": 1.9123133515342916e-05, + "loss": 0.4952, + "step": 1811 + }, + { + "epoch": 1.6, + "learning_rate": 1.9121959470754324e-05, + "loss": 0.4757, + "step": 1812 + }, + { + "epoch": 1.6, + "learning_rate": 1.9120784676810883e-05, + "loss": 0.4545, + "step": 1813 + }, + { + "epoch": 1.6, + "learning_rate": 1.911960913360909e-05, + "loss": 0.5004, + "step": 1814 + }, + { + "epoch": 1.61, + "learning_rate": 1.911843284124552e-05, + "loss": 0.5009, + "step": 1815 + }, + { + "epoch": 1.61, + "learning_rate": 1.9117255799816804e-05, + "loss": 0.4758, + "step": 1816 + }, + { + "epoch": 1.61, + "learning_rate": 1.911607800941963e-05, + "loss": 0.4745, + "step": 1817 + }, + { + "epoch": 1.61, + "learning_rate": 1.911489947015076e-05, + "loss": 0.4818, + "step": 1818 + }, + { + "epoch": 1.61, + "learning_rate": 1.9113720182107e-05, + "loss": 0.4882, + "step": 1819 + }, + { + "epoch": 1.61, + "learning_rate": 1.9112540145385226e-05, + "loss": 0.4743, + "step": 1820 + }, + { + "epoch": 1.61, + "learning_rate": 1.9111359360082385e-05, + "loss": 0.4501, + "step": 1821 + }, + { + "epoch": 1.61, + "learning_rate": 1.9110177826295472e-05, + "loss": 0.4654, + "step": 1822 + }, + { + "epoch": 1.61, + "learning_rate": 1.9108995544121547e-05, + "loss": 0.4641, + "step": 1823 + }, + { + "epoch": 1.61, + "learning_rate": 1.9107812513657733e-05, + "loss": 0.4474, + "step": 1824 + }, + { + "epoch": 1.61, + "learning_rate": 1.9106628735001216e-05, + "loss": 0.4687, + "step": 1825 + }, + { + "epoch": 1.62, + "learning_rate": 1.9105444208249242e-05, + "loss": 0.488, + "step": 1826 + }, + { + "epoch": 1.62, + "learning_rate": 1.9104258933499115e-05, + "loss": 0.4906, + "step": 1827 + }, + { + "epoch": 1.62, + "learning_rate": 1.9103072910848203e-05, + "loss": 0.4971, + "step": 1828 + }, + { + "epoch": 1.62, + "learning_rate": 1.9101886140393938e-05, + "loss": 0.4702, + "step": 1829 + }, + { + "epoch": 1.62, + "learning_rate": 1.9100698622233814e-05, + "loss": 0.4781, + "step": 1830 + }, + { + "epoch": 1.62, + "learning_rate": 1.9099510356465382e-05, + "loss": 0.4741, + "step": 1831 + }, + { + "epoch": 1.62, + "learning_rate": 1.909832134318625e-05, + "loss": 0.4853, + "step": 1832 + }, + { + "epoch": 1.62, + "learning_rate": 1.9097131582494107e-05, + "loss": 0.4402, + "step": 1833 + }, + { + "epoch": 1.62, + "learning_rate": 1.9095941074486678e-05, + "loss": 0.4693, + "step": 1834 + }, + { + "epoch": 1.62, + "learning_rate": 1.9094749819261762e-05, + "loss": 0.462, + "step": 1835 + }, + { + "epoch": 1.62, + "learning_rate": 1.9093557816917225e-05, + "loss": 0.488, + "step": 1836 + }, + { + "epoch": 1.63, + "learning_rate": 1.9092365067550984e-05, + "loss": 0.4573, + "step": 1837 + }, + { + "epoch": 1.63, + "learning_rate": 1.9091171571261024e-05, + "loss": 0.4666, + "step": 1838 + }, + { + "epoch": 1.63, + "learning_rate": 1.9089977328145387e-05, + "loss": 0.4583, + "step": 1839 + }, + { + "epoch": 1.63, + "learning_rate": 1.908878233830218e-05, + "loss": 0.4569, + "step": 1840 + }, + { + "epoch": 1.63, + "learning_rate": 1.9087586601829565e-05, + "loss": 0.4813, + "step": 1841 + }, + { + "epoch": 1.63, + "learning_rate": 1.9086390118825777e-05, + "loss": 0.4388, + "step": 1842 + }, + { + "epoch": 1.63, + "learning_rate": 1.90851928893891e-05, + "loss": 0.4635, + "step": 1843 + }, + { + "epoch": 1.63, + "learning_rate": 1.9083994913617888e-05, + "loss": 0.4947, + "step": 1844 + }, + { + "epoch": 1.63, + "learning_rate": 1.9082796191610547e-05, + "loss": 0.442, + "step": 1845 + }, + { + "epoch": 1.63, + "learning_rate": 1.9081596723465558e-05, + "loss": 0.4746, + "step": 1846 + }, + { + "epoch": 1.63, + "learning_rate": 1.908039650928145e-05, + "loss": 0.4855, + "step": 1847 + }, + { + "epoch": 1.63, + "learning_rate": 1.9079195549156818e-05, + "loss": 0.4954, + "step": 1848 + }, + { + "epoch": 1.64, + "learning_rate": 1.9077993843190325e-05, + "loss": 0.4931, + "step": 1849 + }, + { + "epoch": 1.64, + "learning_rate": 1.9076791391480683e-05, + "loss": 0.493, + "step": 1850 + }, + { + "epoch": 1.64, + "learning_rate": 1.9075588194126675e-05, + "loss": 0.4526, + "step": 1851 + }, + { + "epoch": 1.64, + "learning_rate": 1.907438425122714e-05, + "loss": 0.4935, + "step": 1852 + }, + { + "epoch": 1.64, + "learning_rate": 1.907317956288098e-05, + "loss": 0.463, + "step": 1853 + }, + { + "epoch": 1.64, + "learning_rate": 1.9071974129187163e-05, + "loss": 0.4577, + "step": 1854 + }, + { + "epoch": 1.64, + "learning_rate": 1.9070767950244708e-05, + "loss": 0.4613, + "step": 1855 + }, + { + "epoch": 1.64, + "learning_rate": 1.9069561026152702e-05, + "loss": 0.4306, + "step": 1856 + }, + { + "epoch": 1.64, + "learning_rate": 1.9068353357010293e-05, + "loss": 0.4721, + "step": 1857 + }, + { + "epoch": 1.64, + "learning_rate": 1.906714494291669e-05, + "loss": 0.4692, + "step": 1858 + }, + { + "epoch": 1.64, + "learning_rate": 1.906593578397116e-05, + "loss": 0.4725, + "step": 1859 + }, + { + "epoch": 1.65, + "learning_rate": 1.9064725880273033e-05, + "loss": 0.4581, + "step": 1860 + }, + { + "epoch": 1.65, + "learning_rate": 1.90635152319217e-05, + "loss": 0.4794, + "step": 1861 + }, + { + "epoch": 1.65, + "learning_rate": 1.906230383901662e-05, + "loss": 0.479, + "step": 1862 + }, + { + "epoch": 1.65, + "learning_rate": 1.9061091701657304e-05, + "loss": 0.4595, + "step": 1863 + }, + { + "epoch": 1.65, + "learning_rate": 1.9059878819943326e-05, + "loss": 0.4691, + "step": 1864 + }, + { + "epoch": 1.65, + "learning_rate": 1.9058665193974318e-05, + "loss": 0.4848, + "step": 1865 + }, + { + "epoch": 1.65, + "learning_rate": 1.9057450823849986e-05, + "loss": 0.4802, + "step": 1866 + }, + { + "epoch": 1.65, + "learning_rate": 1.9056235709670083e-05, + "loss": 0.4762, + "step": 1867 + }, + { + "epoch": 1.65, + "learning_rate": 1.9055019851534434e-05, + "loss": 0.4763, + "step": 1868 + }, + { + "epoch": 1.65, + "learning_rate": 1.905380324954291e-05, + "loss": 0.4542, + "step": 1869 + }, + { + "epoch": 1.65, + "learning_rate": 1.9052585903795468e-05, + "loss": 0.4848, + "step": 1870 + }, + { + "epoch": 1.66, + "learning_rate": 1.9051367814392097e-05, + "loss": 0.4889, + "step": 1871 + }, + { + "epoch": 1.66, + "learning_rate": 1.9050148981432868e-05, + "loss": 0.474, + "step": 1872 + }, + { + "epoch": 1.66, + "learning_rate": 1.9048929405017903e-05, + "loss": 0.4763, + "step": 1873 + }, + { + "epoch": 1.66, + "learning_rate": 1.9047709085247393e-05, + "loss": 0.4639, + "step": 1874 + }, + { + "epoch": 1.66, + "learning_rate": 1.904648802222158e-05, + "loss": 0.4725, + "step": 1875 + }, + { + "epoch": 1.66, + "learning_rate": 1.904526621604078e-05, + "loss": 0.4833, + "step": 1876 + }, + { + "epoch": 1.66, + "learning_rate": 1.904404366680535e-05, + "loss": 0.4746, + "step": 1877 + }, + { + "epoch": 1.66, + "learning_rate": 1.9042820374615735e-05, + "loss": 0.4764, + "step": 1878 + }, + { + "epoch": 1.66, + "learning_rate": 1.9041596339572415e-05, + "loss": 0.482, + "step": 1879 + }, + { + "epoch": 1.66, + "learning_rate": 1.9040371561775946e-05, + "loss": 0.4594, + "step": 1880 + }, + { + "epoch": 1.66, + "learning_rate": 1.9039146041326945e-05, + "loss": 0.45, + "step": 1881 + }, + { + "epoch": 1.66, + "learning_rate": 1.9037919778326085e-05, + "loss": 0.4811, + "step": 1882 + }, + { + "epoch": 1.67, + "learning_rate": 1.9036692772874103e-05, + "loss": 0.4863, + "step": 1883 + }, + { + "epoch": 1.67, + "learning_rate": 1.903546502507179e-05, + "loss": 0.4771, + "step": 1884 + }, + { + "epoch": 1.67, + "learning_rate": 1.9034236535020006e-05, + "loss": 0.4822, + "step": 1885 + }, + { + "epoch": 1.67, + "learning_rate": 1.9033007302819677e-05, + "loss": 0.4729, + "step": 1886 + }, + { + "epoch": 1.67, + "learning_rate": 1.903177732857177e-05, + "loss": 0.495, + "step": 1887 + }, + { + "epoch": 1.67, + "learning_rate": 1.9030546612377336e-05, + "loss": 0.4595, + "step": 1888 + }, + { + "epoch": 1.67, + "learning_rate": 1.902931515433747e-05, + "loss": 0.4681, + "step": 1889 + }, + { + "epoch": 1.67, + "learning_rate": 1.9028082954553337e-05, + "loss": 0.4881, + "step": 1890 + }, + { + "epoch": 1.67, + "learning_rate": 1.902685001312616e-05, + "loss": 0.4897, + "step": 1891 + }, + { + "epoch": 1.67, + "learning_rate": 1.902561633015722e-05, + "loss": 0.5003, + "step": 1892 + }, + { + "epoch": 1.67, + "learning_rate": 1.9024381905747867e-05, + "loss": 0.459, + "step": 1893 + }, + { + "epoch": 1.68, + "learning_rate": 1.9023146739999506e-05, + "loss": 0.4658, + "step": 1894 + }, + { + "epoch": 1.68, + "learning_rate": 1.9021910833013602e-05, + "loss": 0.5103, + "step": 1895 + }, + { + "epoch": 1.68, + "learning_rate": 1.902067418489169e-05, + "loss": 0.4754, + "step": 1896 + }, + { + "epoch": 1.68, + "learning_rate": 1.9019436795735346e-05, + "loss": 0.4617, + "step": 1897 + }, + { + "epoch": 1.68, + "learning_rate": 1.901819866564623e-05, + "loss": 0.4614, + "step": 1898 + }, + { + "epoch": 1.68, + "learning_rate": 1.9016959794726046e-05, + "loss": 0.4564, + "step": 1899 + }, + { + "epoch": 1.68, + "learning_rate": 1.9015720183076573e-05, + "loss": 0.4534, + "step": 1900 + }, + { + "epoch": 1.68, + "learning_rate": 1.9014479830799634e-05, + "loss": 0.4574, + "step": 1901 + }, + { + "epoch": 1.68, + "learning_rate": 1.9013238737997127e-05, + "loss": 0.4858, + "step": 1902 + }, + { + "epoch": 1.68, + "learning_rate": 1.9011996904771005e-05, + "loss": 0.4727, + "step": 1903 + }, + { + "epoch": 1.68, + "learning_rate": 1.901075433122328e-05, + "loss": 0.4709, + "step": 1904 + }, + { + "epoch": 1.69, + "learning_rate": 1.9009511017456036e-05, + "loss": 0.4589, + "step": 1905 + }, + { + "epoch": 1.69, + "learning_rate": 1.9008266963571402e-05, + "loss": 0.4712, + "step": 1906 + }, + { + "epoch": 1.69, + "learning_rate": 1.9007022169671575e-05, + "loss": 0.4824, + "step": 1907 + }, + { + "epoch": 1.69, + "learning_rate": 1.9005776635858815e-05, + "loss": 0.4615, + "step": 1908 + }, + { + "epoch": 1.69, + "learning_rate": 1.9004530362235445e-05, + "loss": 0.4531, + "step": 1909 + }, + { + "epoch": 1.69, + "learning_rate": 1.9003283348903837e-05, + "loss": 0.4804, + "step": 1910 + }, + { + "epoch": 1.69, + "learning_rate": 1.9002035595966433e-05, + "loss": 0.4553, + "step": 1911 + }, + { + "epoch": 1.69, + "learning_rate": 1.9000787103525736e-05, + "loss": 0.4651, + "step": 1912 + }, + { + "epoch": 1.69, + "learning_rate": 1.8999537871684308e-05, + "loss": 0.4804, + "step": 1913 + }, + { + "epoch": 1.69, + "learning_rate": 1.8998287900544764e-05, + "loss": 0.4691, + "step": 1914 + }, + { + "epoch": 1.69, + "learning_rate": 1.89970371902098e-05, + "loss": 0.4757, + "step": 1915 + }, + { + "epoch": 1.69, + "learning_rate": 1.8995785740782152e-05, + "loss": 0.4943, + "step": 1916 + }, + { + "epoch": 1.7, + "learning_rate": 1.8994533552364625e-05, + "loss": 0.4627, + "step": 1917 + }, + { + "epoch": 1.7, + "learning_rate": 1.8993280625060088e-05, + "loss": 0.4756, + "step": 1918 + }, + { + "epoch": 1.7, + "learning_rate": 1.899202695897146e-05, + "loss": 0.4697, + "step": 1919 + }, + { + "epoch": 1.7, + "learning_rate": 1.8990772554201732e-05, + "loss": 0.4791, + "step": 1920 + }, + { + "epoch": 1.7, + "learning_rate": 1.8989517410853956e-05, + "loss": 0.4611, + "step": 1921 + }, + { + "epoch": 1.7, + "learning_rate": 1.8988261529031235e-05, + "loss": 0.4641, + "step": 1922 + }, + { + "epoch": 1.7, + "learning_rate": 1.8987004908836734e-05, + "loss": 0.4518, + "step": 1923 + }, + { + "epoch": 1.7, + "learning_rate": 1.8985747550373686e-05, + "loss": 0.4506, + "step": 1924 + }, + { + "epoch": 1.7, + "learning_rate": 1.8984489453745386e-05, + "loss": 0.4857, + "step": 1925 + }, + { + "epoch": 1.7, + "learning_rate": 1.898323061905518e-05, + "loss": 0.4678, + "step": 1926 + }, + { + "epoch": 1.7, + "learning_rate": 1.898197104640648e-05, + "loss": 0.4605, + "step": 1927 + }, + { + "epoch": 1.71, + "learning_rate": 1.8980710735902757e-05, + "loss": 0.4612, + "step": 1928 + }, + { + "epoch": 1.71, + "learning_rate": 1.897944968764754e-05, + "loss": 0.4999, + "step": 1929 + }, + { + "epoch": 1.71, + "learning_rate": 1.8978187901744433e-05, + "loss": 0.4885, + "step": 1930 + }, + { + "epoch": 1.71, + "learning_rate": 1.897692537829708e-05, + "loss": 0.4722, + "step": 1931 + }, + { + "epoch": 1.71, + "learning_rate": 1.89756621174092e-05, + "loss": 0.445, + "step": 1932 + }, + { + "epoch": 1.71, + "learning_rate": 1.8974398119184566e-05, + "loss": 0.4877, + "step": 1933 + }, + { + "epoch": 1.71, + "learning_rate": 1.8973133383727016e-05, + "loss": 0.4757, + "step": 1934 + }, + { + "epoch": 1.71, + "learning_rate": 1.897186791114044e-05, + "loss": 0.4882, + "step": 1935 + }, + { + "epoch": 1.71, + "learning_rate": 1.89706017015288e-05, + "loss": 0.4901, + "step": 1936 + }, + { + "epoch": 1.71, + "learning_rate": 1.8969334754996114e-05, + "loss": 0.4595, + "step": 1937 + }, + { + "epoch": 1.71, + "learning_rate": 1.8968067071646453e-05, + "loss": 0.4747, + "step": 1938 + }, + { + "epoch": 1.72, + "learning_rate": 1.8966798651583965e-05, + "loss": 0.4675, + "step": 1939 + }, + { + "epoch": 1.72, + "learning_rate": 1.8965529494912843e-05, + "loss": 0.4615, + "step": 1940 + }, + { + "epoch": 1.72, + "learning_rate": 1.8964259601737344e-05, + "loss": 0.477, + "step": 1941 + }, + { + "epoch": 1.72, + "learning_rate": 1.8962988972161792e-05, + "loss": 0.4695, + "step": 1942 + }, + { + "epoch": 1.72, + "learning_rate": 1.8961717606290563e-05, + "loss": 0.4511, + "step": 1943 + }, + { + "epoch": 1.72, + "learning_rate": 1.89604455042281e-05, + "loss": 0.4855, + "step": 1944 + }, + { + "epoch": 1.72, + "learning_rate": 1.895917266607891e-05, + "loss": 0.4979, + "step": 1945 + }, + { + "epoch": 1.72, + "learning_rate": 1.8957899091947545e-05, + "loss": 0.4706, + "step": 1946 + }, + { + "epoch": 1.72, + "learning_rate": 1.8956624781938634e-05, + "loss": 0.4753, + "step": 1947 + }, + { + "epoch": 1.72, + "learning_rate": 1.8955349736156855e-05, + "loss": 0.4591, + "step": 1948 + }, + { + "epoch": 1.72, + "learning_rate": 1.8954073954706954e-05, + "loss": 0.4832, + "step": 1949 + }, + { + "epoch": 1.72, + "learning_rate": 1.8952797437693736e-05, + "loss": 0.4925, + "step": 1950 + }, + { + "epoch": 1.73, + "learning_rate": 1.895152018522206e-05, + "loss": 0.4753, + "step": 1951 + }, + { + "epoch": 1.73, + "learning_rate": 1.8950242197396856e-05, + "loss": 0.4663, + "step": 1952 + }, + { + "epoch": 1.73, + "learning_rate": 1.8948963474323102e-05, + "loss": 0.4742, + "step": 1953 + }, + { + "epoch": 1.73, + "learning_rate": 1.8947684016105845e-05, + "loss": 0.4855, + "step": 1954 + }, + { + "epoch": 1.73, + "learning_rate": 1.8946403822850198e-05, + "loss": 0.4711, + "step": 1955 + }, + { + "epoch": 1.73, + "learning_rate": 1.8945122894661318e-05, + "loss": 0.4838, + "step": 1956 + }, + { + "epoch": 1.73, + "learning_rate": 1.8943841231644434e-05, + "loss": 0.4524, + "step": 1957 + }, + { + "epoch": 1.73, + "learning_rate": 1.8942558833904833e-05, + "loss": 0.4697, + "step": 1958 + }, + { + "epoch": 1.73, + "learning_rate": 1.8941275701547862e-05, + "loss": 0.4721, + "step": 1959 + }, + { + "epoch": 1.73, + "learning_rate": 1.893999183467893e-05, + "loss": 0.4716, + "step": 1960 + }, + { + "epoch": 1.73, + "learning_rate": 1.89387072334035e-05, + "loss": 0.4685, + "step": 1961 + }, + { + "epoch": 1.74, + "learning_rate": 1.8937421897827108e-05, + "loss": 0.477, + "step": 1962 + }, + { + "epoch": 1.74, + "learning_rate": 1.8936135828055332e-05, + "loss": 0.4742, + "step": 1963 + }, + { + "epoch": 1.74, + "learning_rate": 1.893484902419383e-05, + "loss": 0.4696, + "step": 1964 + }, + { + "epoch": 1.74, + "learning_rate": 1.89335614863483e-05, + "loss": 0.4564, + "step": 1965 + }, + { + "epoch": 1.74, + "learning_rate": 1.8932273214624526e-05, + "loss": 0.4696, + "step": 1966 + }, + { + "epoch": 1.74, + "learning_rate": 1.8930984209128327e-05, + "loss": 0.4619, + "step": 1967 + }, + { + "epoch": 1.74, + "learning_rate": 1.8929694469965595e-05, + "loss": 0.458, + "step": 1968 + }, + { + "epoch": 1.74, + "learning_rate": 1.8928403997242282e-05, + "loss": 0.4712, + "step": 1969 + }, + { + "epoch": 1.74, + "learning_rate": 1.8927112791064398e-05, + "loss": 0.4739, + "step": 1970 + }, + { + "epoch": 1.74, + "learning_rate": 1.892582085153801e-05, + "loss": 0.5127, + "step": 1971 + }, + { + "epoch": 1.74, + "learning_rate": 1.892452817876925e-05, + "loss": 0.4698, + "step": 1972 + }, + { + "epoch": 1.75, + "learning_rate": 1.892323477286431e-05, + "loss": 0.4725, + "step": 1973 + }, + { + "epoch": 1.75, + "learning_rate": 1.8921940633929448e-05, + "loss": 0.4859, + "step": 1974 + }, + { + "epoch": 1.75, + "learning_rate": 1.8920645762070965e-05, + "loss": 0.501, + "step": 1975 + }, + { + "epoch": 1.75, + "learning_rate": 1.8919350157395236e-05, + "loss": 0.474, + "step": 1976 + }, + { + "epoch": 1.75, + "learning_rate": 1.8918053820008696e-05, + "loss": 0.4633, + "step": 1977 + }, + { + "epoch": 1.75, + "learning_rate": 1.8916756750017833e-05, + "loss": 0.4866, + "step": 1978 + }, + { + "epoch": 1.75, + "learning_rate": 1.8915458947529202e-05, + "loss": 0.4403, + "step": 1979 + }, + { + "epoch": 1.75, + "learning_rate": 1.8914160412649413e-05, + "loss": 0.4859, + "step": 1980 + }, + { + "epoch": 1.75, + "learning_rate": 1.8912861145485146e-05, + "loss": 0.451, + "step": 1981 + }, + { + "epoch": 1.75, + "learning_rate": 1.891156114614312e-05, + "loss": 0.4554, + "step": 1982 + }, + { + "epoch": 1.75, + "learning_rate": 1.891026041473014e-05, + "loss": 0.4852, + "step": 1983 + }, + { + "epoch": 1.76, + "learning_rate": 1.890895895135306e-05, + "loss": 0.4291, + "step": 1984 + }, + { + "epoch": 1.76, + "learning_rate": 1.890765675611878e-05, + "loss": 0.4637, + "step": 1985 + }, + { + "epoch": 1.76, + "learning_rate": 1.8906353829134288e-05, + "loss": 0.4529, + "step": 1986 + }, + { + "epoch": 1.76, + "learning_rate": 1.890505017050661e-05, + "loss": 0.4848, + "step": 1987 + }, + { + "epoch": 1.76, + "learning_rate": 1.8903745780342838e-05, + "loss": 0.47, + "step": 1988 + }, + { + "epoch": 1.76, + "learning_rate": 1.890244065875013e-05, + "loss": 0.4622, + "step": 1989 + }, + { + "epoch": 1.76, + "learning_rate": 1.8901134805835698e-05, + "loss": 0.4825, + "step": 1990 + }, + { + "epoch": 1.76, + "learning_rate": 1.8899828221706816e-05, + "loss": 0.4934, + "step": 1991 + }, + { + "epoch": 1.76, + "learning_rate": 1.8898520906470818e-05, + "loss": 0.4718, + "step": 1992 + }, + { + "epoch": 1.76, + "learning_rate": 1.8897212860235096e-05, + "loss": 0.4661, + "step": 1993 + }, + { + "epoch": 1.76, + "learning_rate": 1.8895904083107106e-05, + "loss": 0.4503, + "step": 1994 + }, + { + "epoch": 1.76, + "learning_rate": 1.8894594575194363e-05, + "loss": 0.4567, + "step": 1995 + }, + { + "epoch": 1.77, + "learning_rate": 1.889328433660444e-05, + "loss": 0.4645, + "step": 1996 + }, + { + "epoch": 1.77, + "learning_rate": 1.8891973367444967e-05, + "loss": 0.4417, + "step": 1997 + }, + { + "epoch": 1.77, + "learning_rate": 1.8890661667823644e-05, + "loss": 0.467, + "step": 1998 + }, + { + "epoch": 1.77, + "learning_rate": 1.8889349237848223e-05, + "loss": 0.4836, + "step": 1999 + }, + { + "epoch": 1.77, + "learning_rate": 1.888803607762652e-05, + "loss": 0.4404, + "step": 2000 + }, + { + "epoch": 1.77, + "learning_rate": 1.88867221872664e-05, + "loss": 0.5009, + "step": 2001 + }, + { + "epoch": 1.77, + "learning_rate": 1.8885407566875814e-05, + "loss": 0.4647, + "step": 2002 + }, + { + "epoch": 1.77, + "learning_rate": 1.888409221656274e-05, + "loss": 0.4583, + "step": 2003 + }, + { + "epoch": 1.77, + "learning_rate": 1.8882776136435238e-05, + "loss": 0.4803, + "step": 2004 + }, + { + "epoch": 1.77, + "learning_rate": 1.8881459326601423e-05, + "loss": 0.4898, + "step": 2005 + }, + { + "epoch": 1.77, + "learning_rate": 1.888014178716947e-05, + "loss": 0.4934, + "step": 2006 + }, + { + "epoch": 1.78, + "learning_rate": 1.8878823518247608e-05, + "loss": 0.4564, + "step": 2007 + }, + { + "epoch": 1.78, + "learning_rate": 1.8877504519944135e-05, + "loss": 0.4457, + "step": 2008 + }, + { + "epoch": 1.78, + "learning_rate": 1.8876184792367406e-05, + "loss": 0.4697, + "step": 2009 + }, + { + "epoch": 1.78, + "learning_rate": 1.8874864335625827e-05, + "loss": 0.4544, + "step": 2010 + }, + { + "epoch": 1.78, + "learning_rate": 1.8873543149827876e-05, + "loss": 0.4742, + "step": 2011 + }, + { + "epoch": 1.78, + "learning_rate": 1.887222123508209e-05, + "loss": 0.4585, + "step": 2012 + }, + { + "epoch": 1.78, + "learning_rate": 1.8870898591497056e-05, + "loss": 0.4616, + "step": 2013 + }, + { + "epoch": 1.78, + "learning_rate": 1.886957521918143e-05, + "loss": 0.471, + "step": 2014 + }, + { + "epoch": 1.78, + "learning_rate": 1.886825111824393e-05, + "loss": 0.4509, + "step": 2015 + }, + { + "epoch": 1.78, + "learning_rate": 1.886692628879332e-05, + "loss": 0.4652, + "step": 2016 + }, + { + "epoch": 1.78, + "learning_rate": 1.886560073093844e-05, + "loss": 0.4529, + "step": 2017 + }, + { + "epoch": 1.79, + "learning_rate": 1.8864274444788172e-05, + "loss": 0.4856, + "step": 2018 + }, + { + "epoch": 1.79, + "learning_rate": 1.8862947430451482e-05, + "loss": 0.4644, + "step": 2019 + }, + { + "epoch": 1.79, + "learning_rate": 1.8861619688037373e-05, + "loss": 0.4542, + "step": 2020 + }, + { + "epoch": 1.79, + "learning_rate": 1.886029121765492e-05, + "loss": 0.4595, + "step": 2021 + }, + { + "epoch": 1.79, + "learning_rate": 1.8858962019413253e-05, + "loss": 0.4428, + "step": 2022 + }, + { + "epoch": 1.79, + "learning_rate": 1.8857632093421566e-05, + "loss": 0.464, + "step": 2023 + }, + { + "epoch": 1.79, + "learning_rate": 1.8856301439789112e-05, + "loss": 0.4608, + "step": 2024 + }, + { + "epoch": 1.79, + "learning_rate": 1.8854970058625196e-05, + "loss": 0.4553, + "step": 2025 + }, + { + "epoch": 1.79, + "learning_rate": 1.885363795003919e-05, + "loss": 0.4594, + "step": 2026 + }, + { + "epoch": 1.79, + "learning_rate": 1.885230511414053e-05, + "loss": 0.4579, + "step": 2027 + }, + { + "epoch": 1.79, + "learning_rate": 1.8850971551038707e-05, + "loss": 0.4838, + "step": 2028 + }, + { + "epoch": 1.79, + "learning_rate": 1.8849637260843262e-05, + "loss": 0.4721, + "step": 2029 + }, + { + "epoch": 1.8, + "learning_rate": 1.8848302243663816e-05, + "loss": 0.4586, + "step": 2030 + }, + { + "epoch": 1.8, + "learning_rate": 1.884696649961003e-05, + "loss": 0.4293, + "step": 2031 + }, + { + "epoch": 1.8, + "learning_rate": 1.8845630028791632e-05, + "loss": 0.4697, + "step": 2032 + }, + { + "epoch": 1.8, + "learning_rate": 1.884429283131842e-05, + "loss": 0.4656, + "step": 2033 + }, + { + "epoch": 1.8, + "learning_rate": 1.8842954907300236e-05, + "loss": 0.4681, + "step": 2034 + }, + { + "epoch": 1.8, + "learning_rate": 1.8841616256846996e-05, + "loss": 0.45, + "step": 2035 + }, + { + "epoch": 1.8, + "learning_rate": 1.8840276880068656e-05, + "loss": 0.4887, + "step": 2036 + }, + { + "epoch": 1.8, + "learning_rate": 1.883893677707525e-05, + "loss": 0.4398, + "step": 2037 + }, + { + "epoch": 1.8, + "learning_rate": 1.883759594797687e-05, + "loss": 0.4656, + "step": 2038 + }, + { + "epoch": 1.8, + "learning_rate": 1.8836254392883658e-05, + "loss": 0.4526, + "step": 2039 + }, + { + "epoch": 1.8, + "learning_rate": 1.883491211190582e-05, + "loss": 0.4747, + "step": 2040 + }, + { + "epoch": 1.81, + "learning_rate": 1.8833569105153625e-05, + "loss": 0.443, + "step": 2041 + }, + { + "epoch": 1.81, + "learning_rate": 1.8832225372737395e-05, + "loss": 0.4625, + "step": 2042 + }, + { + "epoch": 1.81, + "learning_rate": 1.883088091476752e-05, + "loss": 0.4398, + "step": 2043 + }, + { + "epoch": 1.81, + "learning_rate": 1.882953573135444e-05, + "loss": 0.4689, + "step": 2044 + }, + { + "epoch": 1.81, + "learning_rate": 1.8828189822608664e-05, + "loss": 0.4821, + "step": 2045 + }, + { + "epoch": 1.81, + "learning_rate": 1.882684318864076e-05, + "loss": 0.484, + "step": 2046 + }, + { + "epoch": 1.81, + "learning_rate": 1.8825495829561342e-05, + "loss": 0.4829, + "step": 2047 + }, + { + "epoch": 1.81, + "learning_rate": 1.88241477454811e-05, + "loss": 0.482, + "step": 2048 + }, + { + "epoch": 1.81, + "learning_rate": 1.8822798936510777e-05, + "loss": 0.4762, + "step": 2049 + }, + { + "epoch": 1.81, + "learning_rate": 1.8821449402761174e-05, + "loss": 0.4739, + "step": 2050 + }, + { + "epoch": 1.81, + "learning_rate": 1.8820099144343152e-05, + "loss": 0.4694, + "step": 2051 + }, + { + "epoch": 1.82, + "learning_rate": 1.8818748161367635e-05, + "loss": 0.4447, + "step": 2052 + }, + { + "epoch": 1.82, + "learning_rate": 1.8817396453945603e-05, + "loss": 0.4706, + "step": 2053 + }, + { + "epoch": 1.82, + "learning_rate": 1.8816044022188097e-05, + "loss": 0.4799, + "step": 2054 + }, + { + "epoch": 1.82, + "learning_rate": 1.881469086620622e-05, + "loss": 0.4477, + "step": 2055 + }, + { + "epoch": 1.82, + "learning_rate": 1.8813336986111122e-05, + "loss": 0.4869, + "step": 2056 + }, + { + "epoch": 1.82, + "learning_rate": 1.8811982382014037e-05, + "loss": 0.459, + "step": 2057 + }, + { + "epoch": 1.82, + "learning_rate": 1.8810627054026228e-05, + "loss": 0.4524, + "step": 2058 + }, + { + "epoch": 1.82, + "learning_rate": 1.8809271002259044e-05, + "loss": 0.4544, + "step": 2059 + }, + { + "epoch": 1.82, + "learning_rate": 1.8807914226823878e-05, + "loss": 0.4654, + "step": 2060 + }, + { + "epoch": 1.82, + "learning_rate": 1.880655672783219e-05, + "loss": 0.4485, + "step": 2061 + }, + { + "epoch": 1.82, + "learning_rate": 1.880519850539549e-05, + "loss": 0.4661, + "step": 2062 + }, + { + "epoch": 1.82, + "learning_rate": 1.8803839559625366e-05, + "loss": 0.4978, + "step": 2063 + }, + { + "epoch": 1.83, + "learning_rate": 1.880247989063344e-05, + "loss": 0.4897, + "step": 2064 + }, + { + "epoch": 1.83, + "learning_rate": 1.8801119498531413e-05, + "loss": 0.4615, + "step": 2065 + }, + { + "epoch": 1.83, + "learning_rate": 1.879975838343104e-05, + "loss": 0.5215, + "step": 2066 + }, + { + "epoch": 1.83, + "learning_rate": 1.879839654544413e-05, + "loss": 0.4639, + "step": 2067 + }, + { + "epoch": 1.83, + "learning_rate": 1.8797033984682564e-05, + "loss": 0.4613, + "step": 2068 + }, + { + "epoch": 1.83, + "learning_rate": 1.8795670701258267e-05, + "loss": 0.4464, + "step": 2069 + }, + { + "epoch": 1.83, + "learning_rate": 1.879430669528323e-05, + "loss": 0.4679, + "step": 2070 + }, + { + "epoch": 1.83, + "learning_rate": 1.879294196686951e-05, + "loss": 0.4299, + "step": 2071 + }, + { + "epoch": 1.83, + "learning_rate": 1.8791576516129212e-05, + "loss": 0.4956, + "step": 2072 + }, + { + "epoch": 1.83, + "learning_rate": 1.879021034317451e-05, + "loss": 0.4985, + "step": 2073 + }, + { + "epoch": 1.83, + "learning_rate": 1.878884344811763e-05, + "loss": 0.4908, + "step": 2074 + }, + { + "epoch": 1.84, + "learning_rate": 1.878747583107086e-05, + "loss": 0.4749, + "step": 2075 + }, + { + "epoch": 1.84, + "learning_rate": 1.878610749214655e-05, + "loss": 0.4545, + "step": 2076 + }, + { + "epoch": 1.84, + "learning_rate": 1.8784738431457103e-05, + "loss": 0.4774, + "step": 2077 + }, + { + "epoch": 1.84, + "learning_rate": 1.878336864911499e-05, + "loss": 0.4523, + "step": 2078 + }, + { + "epoch": 1.84, + "learning_rate": 1.8781998145232735e-05, + "loss": 0.4478, + "step": 2079 + }, + { + "epoch": 1.84, + "learning_rate": 1.8780626919922923e-05, + "loss": 0.4657, + "step": 2080 + }, + { + "epoch": 1.84, + "learning_rate": 1.8779254973298196e-05, + "loss": 0.4469, + "step": 2081 + }, + { + "epoch": 1.84, + "learning_rate": 1.8777882305471254e-05, + "loss": 0.4581, + "step": 2082 + }, + { + "epoch": 1.84, + "learning_rate": 1.877650891655487e-05, + "loss": 0.4444, + "step": 2083 + }, + { + "epoch": 1.84, + "learning_rate": 1.8775134806661858e-05, + "loss": 0.4864, + "step": 2084 + }, + { + "epoch": 1.84, + "learning_rate": 1.8773759975905098e-05, + "loss": 0.4604, + "step": 2085 + }, + { + "epoch": 1.85, + "learning_rate": 1.8772384424397537e-05, + "loss": 0.4337, + "step": 2086 + }, + { + "epoch": 1.85, + "learning_rate": 1.877100815225217e-05, + "loss": 0.4878, + "step": 2087 + }, + { + "epoch": 1.85, + "learning_rate": 1.8769631159582053e-05, + "loss": 0.4646, + "step": 2088 + }, + { + "epoch": 1.85, + "learning_rate": 1.876825344650031e-05, + "loss": 0.4589, + "step": 2089 + }, + { + "epoch": 1.85, + "learning_rate": 1.8766875013120113e-05, + "loss": 0.4453, + "step": 2090 + }, + { + "epoch": 1.85, + "learning_rate": 1.8765495859554698e-05, + "loss": 0.4486, + "step": 2091 + }, + { + "epoch": 1.85, + "learning_rate": 1.876411598591737e-05, + "loss": 0.4559, + "step": 2092 + }, + { + "epoch": 1.85, + "learning_rate": 1.8762735392321468e-05, + "loss": 0.4711, + "step": 2093 + }, + { + "epoch": 1.85, + "learning_rate": 1.8761354078880415e-05, + "loss": 0.4777, + "step": 2094 + }, + { + "epoch": 1.85, + "learning_rate": 1.8759972045707683e-05, + "loss": 0.4618, + "step": 2095 + }, + { + "epoch": 1.85, + "learning_rate": 1.8758589292916804e-05, + "loss": 0.4506, + "step": 2096 + }, + { + "epoch": 1.86, + "learning_rate": 1.8757205820621367e-05, + "loss": 0.4764, + "step": 2097 + }, + { + "epoch": 1.86, + "learning_rate": 1.8755821628935026e-05, + "loss": 0.4788, + "step": 2098 + }, + { + "epoch": 1.86, + "learning_rate": 1.8754436717971485e-05, + "loss": 0.4908, + "step": 2099 + }, + { + "epoch": 1.86, + "learning_rate": 1.8753051087844514e-05, + "loss": 0.4476, + "step": 2100 + }, + { + "epoch": 1.86, + "learning_rate": 1.875166473866794e-05, + "loss": 0.4757, + "step": 2101 + }, + { + "epoch": 1.86, + "learning_rate": 1.875027767055565e-05, + "loss": 0.4427, + "step": 2102 + }, + { + "epoch": 1.86, + "learning_rate": 1.87488898836216e-05, + "loss": 0.4782, + "step": 2103 + }, + { + "epoch": 1.86, + "learning_rate": 1.8747501377979775e-05, + "loss": 0.4746, + "step": 2104 + }, + { + "epoch": 1.86, + "learning_rate": 1.874611215374425e-05, + "loss": 0.4515, + "step": 2105 + }, + { + "epoch": 1.86, + "learning_rate": 1.8744722211029142e-05, + "loss": 0.4497, + "step": 2106 + }, + { + "epoch": 1.86, + "learning_rate": 1.8743331549948642e-05, + "loss": 0.4325, + "step": 2107 + }, + { + "epoch": 1.86, + "learning_rate": 1.8741940170616986e-05, + "loss": 0.4393, + "step": 2108 + }, + { + "epoch": 1.87, + "learning_rate": 1.8740548073148467e-05, + "loss": 0.4497, + "step": 2109 + }, + { + "epoch": 1.87, + "learning_rate": 1.8739155257657457e-05, + "loss": 0.4773, + "step": 2110 + }, + { + "epoch": 1.87, + "learning_rate": 1.873776172425836e-05, + "loss": 0.4646, + "step": 2111 + }, + { + "epoch": 1.87, + "learning_rate": 1.873636747306566e-05, + "loss": 0.4834, + "step": 2112 + }, + { + "epoch": 1.87, + "learning_rate": 1.8734972504193888e-05, + "loss": 0.4675, + "step": 2113 + }, + { + "epoch": 1.87, + "learning_rate": 1.873357681775765e-05, + "loss": 0.4588, + "step": 2114 + }, + { + "epoch": 1.87, + "learning_rate": 1.8732180413871582e-05, + "loss": 0.459, + "step": 2115 + }, + { + "epoch": 1.87, + "learning_rate": 1.8730783292650412e-05, + "loss": 0.4625, + "step": 2116 + }, + { + "epoch": 1.87, + "learning_rate": 1.8729385454208905e-05, + "loss": 0.4733, + "step": 2117 + }, + { + "epoch": 1.87, + "learning_rate": 1.8727986898661888e-05, + "loss": 0.4672, + "step": 2118 + }, + { + "epoch": 1.87, + "learning_rate": 1.8726587626124257e-05, + "loss": 0.4972, + "step": 2119 + }, + { + "epoch": 1.88, + "learning_rate": 1.8725187636710952e-05, + "loss": 0.4779, + "step": 2120 + }, + { + "epoch": 1.88, + "learning_rate": 1.8723786930536986e-05, + "loss": 0.4435, + "step": 2121 + }, + { + "epoch": 1.88, + "learning_rate": 1.8722385507717425e-05, + "loss": 0.4381, + "step": 2122 + }, + { + "epoch": 1.88, + "learning_rate": 1.872098336836739e-05, + "loss": 0.4492, + "step": 2123 + }, + { + "epoch": 1.88, + "learning_rate": 1.8719580512602068e-05, + "loss": 0.4649, + "step": 2124 + }, + { + "epoch": 1.88, + "learning_rate": 1.87181769405367e-05, + "loss": 0.4696, + "step": 2125 + }, + { + "epoch": 1.88, + "learning_rate": 1.8716772652286588e-05, + "loss": 0.464, + "step": 2126 + }, + { + "epoch": 1.88, + "learning_rate": 1.871536764796709e-05, + "loss": 0.4625, + "step": 2127 + }, + { + "epoch": 1.88, + "learning_rate": 1.8713961927693625e-05, + "loss": 0.4654, + "step": 2128 + }, + { + "epoch": 1.88, + "learning_rate": 1.8712555491581678e-05, + "loss": 0.4451, + "step": 2129 + }, + { + "epoch": 1.88, + "learning_rate": 1.8711148339746774e-05, + "loss": 0.4868, + "step": 2130 + }, + { + "epoch": 1.89, + "learning_rate": 1.8709740472304515e-05, + "loss": 0.4637, + "step": 2131 + }, + { + "epoch": 1.89, + "learning_rate": 1.8708331889370557e-05, + "loss": 0.4774, + "step": 2132 + }, + { + "epoch": 1.89, + "learning_rate": 1.870692259106061e-05, + "loss": 0.4421, + "step": 2133 + }, + { + "epoch": 1.89, + "learning_rate": 1.870551257749044e-05, + "loss": 0.4521, + "step": 2134 + }, + { + "epoch": 1.89, + "learning_rate": 1.8704101848775886e-05, + "loss": 0.4734, + "step": 2135 + }, + { + "epoch": 1.89, + "learning_rate": 1.8702690405032835e-05, + "loss": 0.477, + "step": 2136 + }, + { + "epoch": 1.89, + "learning_rate": 1.8701278246377236e-05, + "loss": 0.4756, + "step": 2137 + }, + { + "epoch": 1.89, + "learning_rate": 1.869986537292509e-05, + "loss": 0.4776, + "step": 2138 + }, + { + "epoch": 1.89, + "learning_rate": 1.8698451784792468e-05, + "loss": 0.4795, + "step": 2139 + }, + { + "epoch": 1.89, + "learning_rate": 1.8697037482095495e-05, + "loss": 0.4297, + "step": 2140 + }, + { + "epoch": 1.89, + "learning_rate": 1.869562246495035e-05, + "loss": 0.4798, + "step": 2141 + }, + { + "epoch": 1.89, + "learning_rate": 1.8694206733473274e-05, + "loss": 0.4657, + "step": 2142 + }, + { + "epoch": 1.9, + "learning_rate": 1.8692790287780566e-05, + "loss": 0.468, + "step": 2143 + }, + { + "epoch": 1.9, + "learning_rate": 1.869137312798859e-05, + "loss": 0.4803, + "step": 2144 + }, + { + "epoch": 1.9, + "learning_rate": 1.8689955254213763e-05, + "loss": 0.4905, + "step": 2145 + }, + { + "epoch": 1.9, + "learning_rate": 1.868853666657256e-05, + "loss": 0.4832, + "step": 2146 + }, + { + "epoch": 1.9, + "learning_rate": 1.8687117365181514e-05, + "loss": 0.4707, + "step": 2147 + }, + { + "epoch": 1.9, + "learning_rate": 1.8685697350157218e-05, + "loss": 0.4435, + "step": 2148 + }, + { + "epoch": 1.9, + "learning_rate": 1.8684276621616326e-05, + "loss": 0.4394, + "step": 2149 + }, + { + "epoch": 1.9, + "learning_rate": 1.8682855179675546e-05, + "loss": 0.4543, + "step": 2150 + }, + { + "epoch": 1.9, + "learning_rate": 1.868143302445165e-05, + "loss": 0.4744, + "step": 2151 + }, + { + "epoch": 1.9, + "learning_rate": 1.8680010156061468e-05, + "loss": 0.4683, + "step": 2152 + }, + { + "epoch": 1.9, + "learning_rate": 1.867858657462188e-05, + "loss": 0.4769, + "step": 2153 + }, + { + "epoch": 1.91, + "learning_rate": 1.8677162280249837e-05, + "loss": 0.4617, + "step": 2154 + }, + { + "epoch": 1.91, + "learning_rate": 1.867573727306234e-05, + "loss": 0.4763, + "step": 2155 + }, + { + "epoch": 1.91, + "learning_rate": 1.867431155317645e-05, + "loss": 0.4523, + "step": 2156 + }, + { + "epoch": 1.91, + "learning_rate": 1.867288512070929e-05, + "loss": 0.4566, + "step": 2157 + }, + { + "epoch": 1.91, + "learning_rate": 1.8671457975778037e-05, + "loss": 0.4506, + "step": 2158 + }, + { + "epoch": 1.91, + "learning_rate": 1.8670030118499934e-05, + "loss": 0.4765, + "step": 2159 + }, + { + "epoch": 1.91, + "learning_rate": 1.8668601548992267e-05, + "loss": 0.4785, + "step": 2160 + }, + { + "epoch": 1.91, + "learning_rate": 1.86671722673724e-05, + "loss": 0.4276, + "step": 2161 + }, + { + "epoch": 1.91, + "learning_rate": 1.8665742273757747e-05, + "loss": 0.4902, + "step": 2162 + }, + { + "epoch": 1.91, + "learning_rate": 1.866431156826577e-05, + "loss": 0.4665, + "step": 2163 + }, + { + "epoch": 1.91, + "learning_rate": 1.866288015101401e-05, + "loss": 0.4756, + "step": 2164 + }, + { + "epoch": 1.92, + "learning_rate": 1.8661448022120047e-05, + "loss": 0.4643, + "step": 2165 + }, + { + "epoch": 1.92, + "learning_rate": 1.8660015181701536e-05, + "loss": 0.4728, + "step": 2166 + }, + { + "epoch": 1.92, + "learning_rate": 1.865858162987618e-05, + "loss": 0.4648, + "step": 2167 + }, + { + "epoch": 1.92, + "learning_rate": 1.8657147366761736e-05, + "loss": 0.4658, + "step": 2168 + }, + { + "epoch": 1.92, + "learning_rate": 1.8655712392476034e-05, + "loss": 0.4981, + "step": 2169 + }, + { + "epoch": 1.92, + "learning_rate": 1.8654276707136958e-05, + "loss": 0.4482, + "step": 2170 + }, + { + "epoch": 1.92, + "learning_rate": 1.8652840310862438e-05, + "loss": 0.4735, + "step": 2171 + }, + { + "epoch": 1.92, + "learning_rate": 1.8651403203770476e-05, + "loss": 0.4587, + "step": 2172 + }, + { + "epoch": 1.92, + "learning_rate": 1.864996538597913e-05, + "loss": 0.4809, + "step": 2173 + }, + { + "epoch": 1.92, + "learning_rate": 1.8648526857606514e-05, + "loss": 0.4706, + "step": 2174 + }, + { + "epoch": 1.92, + "learning_rate": 1.86470876187708e-05, + "loss": 0.4702, + "step": 2175 + }, + { + "epoch": 1.92, + "learning_rate": 1.8645647669590216e-05, + "loss": 0.4672, + "step": 2176 + }, + { + "epoch": 1.93, + "learning_rate": 1.8644207010183056e-05, + "loss": 0.4803, + "step": 2177 + }, + { + "epoch": 1.93, + "learning_rate": 1.864276564066767e-05, + "loss": 0.4874, + "step": 2178 + }, + { + "epoch": 1.93, + "learning_rate": 1.8641323561162455e-05, + "loss": 0.4581, + "step": 2179 + }, + { + "epoch": 1.93, + "learning_rate": 1.8639880771785884e-05, + "loss": 0.4628, + "step": 2180 + }, + { + "epoch": 1.93, + "learning_rate": 1.863843727265648e-05, + "loss": 0.4739, + "step": 2181 + }, + { + "epoch": 1.93, + "learning_rate": 1.8636993063892822e-05, + "loss": 0.4678, + "step": 2182 + }, + { + "epoch": 1.93, + "learning_rate": 1.8635548145613545e-05, + "loss": 0.4765, + "step": 2183 + }, + { + "epoch": 1.93, + "learning_rate": 1.8634102517937354e-05, + "loss": 0.4749, + "step": 2184 + }, + { + "epoch": 1.93, + "learning_rate": 1.8632656180983e-05, + "loss": 0.4842, + "step": 2185 + }, + { + "epoch": 1.93, + "learning_rate": 1.86312091348693e-05, + "loss": 0.4837, + "step": 2186 + }, + { + "epoch": 1.93, + "learning_rate": 1.862976137971512e-05, + "loss": 0.4635, + "step": 2187 + }, + { + "epoch": 1.94, + "learning_rate": 1.862831291563941e-05, + "loss": 0.4866, + "step": 2188 + }, + { + "epoch": 1.94, + "learning_rate": 1.8626863742761136e-05, + "loss": 0.4666, + "step": 2189 + }, + { + "epoch": 1.94, + "learning_rate": 1.8625413861199358e-05, + "loss": 0.4815, + "step": 2190 + }, + { + "epoch": 1.94, + "learning_rate": 1.862396327107318e-05, + "loss": 0.459, + "step": 2191 + }, + { + "epoch": 1.94, + "learning_rate": 1.8622511972501766e-05, + "loss": 0.4783, + "step": 2192 + }, + { + "epoch": 1.94, + "learning_rate": 1.862105996560433e-05, + "loss": 0.4822, + "step": 2193 + }, + { + "epoch": 1.94, + "learning_rate": 1.861960725050016e-05, + "loss": 0.4607, + "step": 2194 + }, + { + "epoch": 1.94, + "learning_rate": 1.8618153827308595e-05, + "loss": 0.443, + "step": 2195 + }, + { + "epoch": 1.94, + "learning_rate": 1.8616699696149032e-05, + "loss": 0.4666, + "step": 2196 + }, + { + "epoch": 1.94, + "learning_rate": 1.8615244857140918e-05, + "loss": 0.4493, + "step": 2197 + }, + { + "epoch": 1.94, + "learning_rate": 1.8613789310403776e-05, + "loss": 0.4784, + "step": 2198 + }, + { + "epoch": 1.95, + "learning_rate": 1.8612333056057167e-05, + "loss": 0.4553, + "step": 2199 + }, + { + "epoch": 1.95, + "learning_rate": 1.8610876094220726e-05, + "loss": 0.4617, + "step": 2200 + }, + { + "epoch": 1.95, + "learning_rate": 1.860941842501414e-05, + "loss": 0.4738, + "step": 2201 + }, + { + "epoch": 1.95, + "learning_rate": 1.8607960048557152e-05, + "loss": 0.4574, + "step": 2202 + }, + { + "epoch": 1.95, + "learning_rate": 1.8606500964969565e-05, + "loss": 0.4451, + "step": 2203 + }, + { + "epoch": 1.95, + "learning_rate": 1.8605041174371244e-05, + "loss": 0.4577, + "step": 2204 + }, + { + "epoch": 1.95, + "learning_rate": 1.8603580676882105e-05, + "loss": 0.4762, + "step": 2205 + }, + { + "epoch": 1.95, + "learning_rate": 1.860211947262213e-05, + "loss": 0.4679, + "step": 2206 + }, + { + "epoch": 1.95, + "learning_rate": 1.8600657561711348e-05, + "loss": 0.4839, + "step": 2207 + }, + { + "epoch": 1.95, + "learning_rate": 1.859919494426986e-05, + "loss": 0.443, + "step": 2208 + }, + { + "epoch": 1.95, + "learning_rate": 1.859773162041781e-05, + "loss": 0.4669, + "step": 2209 + }, + { + "epoch": 1.95, + "learning_rate": 1.8596267590275414e-05, + "loss": 0.4732, + "step": 2210 + }, + { + "epoch": 1.96, + "learning_rate": 1.859480285396294e-05, + "loss": 0.4631, + "step": 2211 + }, + { + "epoch": 1.96, + "learning_rate": 1.8593337411600707e-05, + "loss": 0.4684, + "step": 2212 + }, + { + "epoch": 1.96, + "learning_rate": 1.8591871263309107e-05, + "loss": 0.4799, + "step": 2213 + }, + { + "epoch": 1.96, + "learning_rate": 1.8590404409208578e-05, + "loss": 0.4749, + "step": 2214 + }, + { + "epoch": 1.96, + "learning_rate": 1.8588936849419618e-05, + "loss": 0.4523, + "step": 2215 + }, + { + "epoch": 1.96, + "learning_rate": 1.858746858406279e-05, + "loss": 0.4429, + "step": 2216 + }, + { + "epoch": 1.96, + "learning_rate": 1.8585999613258707e-05, + "loss": 0.4603, + "step": 2217 + }, + { + "epoch": 1.96, + "learning_rate": 1.8584529937128034e-05, + "loss": 0.4725, + "step": 2218 + }, + { + "epoch": 1.96, + "learning_rate": 1.858305955579152e-05, + "loss": 0.4598, + "step": 2219 + }, + { + "epoch": 1.96, + "learning_rate": 1.858158846936994e-05, + "loss": 0.4554, + "step": 2220 + }, + { + "epoch": 1.96, + "learning_rate": 1.8580116677984147e-05, + "loss": 0.4595, + "step": 2221 + }, + { + "epoch": 1.97, + "learning_rate": 1.857864418175505e-05, + "loss": 0.4666, + "step": 2222 + }, + { + "epoch": 1.97, + "learning_rate": 1.857717098080361e-05, + "loss": 0.4473, + "step": 2223 + }, + { + "epoch": 1.97, + "learning_rate": 1.857569707525084e-05, + "loss": 0.4778, + "step": 2224 + }, + { + "epoch": 1.97, + "learning_rate": 1.857422246521783e-05, + "loss": 0.4631, + "step": 2225 + }, + { + "epoch": 1.97, + "learning_rate": 1.8572747150825713e-05, + "loss": 0.4438, + "step": 2226 + }, + { + "epoch": 1.97, + "learning_rate": 1.8571271132195684e-05, + "loss": 0.4857, + "step": 2227 + }, + { + "epoch": 1.97, + "learning_rate": 1.8569794409448988e-05, + "loss": 0.4556, + "step": 2228 + }, + { + "epoch": 1.97, + "learning_rate": 1.856831698270695e-05, + "loss": 0.4792, + "step": 2229 + }, + { + "epoch": 1.97, + "learning_rate": 1.856683885209093e-05, + "loss": 0.4608, + "step": 2230 + }, + { + "epoch": 1.97, + "learning_rate": 1.8565360017722356e-05, + "loss": 0.4577, + "step": 2231 + }, + { + "epoch": 1.97, + "learning_rate": 1.8563880479722706e-05, + "loss": 0.4781, + "step": 2232 + }, + { + "epoch": 1.98, + "learning_rate": 1.8562400238213533e-05, + "loss": 0.4763, + "step": 2233 + }, + { + "epoch": 1.98, + "learning_rate": 1.8560919293316426e-05, + "loss": 0.4679, + "step": 2234 + }, + { + "epoch": 1.98, + "learning_rate": 1.8559437645153048e-05, + "loss": 0.4565, + "step": 2235 + }, + { + "epoch": 1.98, + "learning_rate": 1.8557955293845112e-05, + "loss": 0.4655, + "step": 2236 + }, + { + "epoch": 1.98, + "learning_rate": 1.8556472239514393e-05, + "loss": 0.4639, + "step": 2237 + }, + { + "epoch": 1.98, + "learning_rate": 1.855498848228272e-05, + "loss": 0.4481, + "step": 2238 + }, + { + "epoch": 1.98, + "learning_rate": 1.855350402227198e-05, + "loss": 0.4533, + "step": 2239 + }, + { + "epoch": 1.98, + "learning_rate": 1.8552018859604123e-05, + "loss": 0.4765, + "step": 2240 + }, + { + "epoch": 1.98, + "learning_rate": 1.8550532994401148e-05, + "loss": 0.491, + "step": 2241 + }, + { + "epoch": 1.98, + "learning_rate": 1.8549046426785124e-05, + "loss": 0.4456, + "step": 2242 + }, + { + "epoch": 1.98, + "learning_rate": 1.8547559156878162e-05, + "loss": 0.4802, + "step": 2243 + }, + { + "epoch": 1.99, + "learning_rate": 1.8546071184802442e-05, + "loss": 0.4427, + "step": 2244 + }, + { + "epoch": 1.99, + "learning_rate": 1.85445825106802e-05, + "loss": 0.4651, + "step": 2245 + }, + { + "epoch": 1.99, + "learning_rate": 1.8543093134633725e-05, + "loss": 0.4622, + "step": 2246 + }, + { + "epoch": 1.99, + "learning_rate": 1.854160305678537e-05, + "loss": 0.4622, + "step": 2247 + }, + { + "epoch": 1.99, + "learning_rate": 1.854011227725754e-05, + "loss": 0.4738, + "step": 2248 + }, + { + "epoch": 1.99, + "learning_rate": 1.8538620796172705e-05, + "loss": 0.4619, + "step": 2249 + }, + { + "epoch": 1.99, + "learning_rate": 1.8537128613653384e-05, + "loss": 0.4951, + "step": 2250 + }, + { + "epoch": 1.99, + "learning_rate": 1.853563572982216e-05, + "loss": 0.4772, + "step": 2251 + }, + { + "epoch": 1.99, + "learning_rate": 1.8534142144801666e-05, + "loss": 0.4659, + "step": 2252 + }, + { + "epoch": 1.99, + "learning_rate": 1.85326478587146e-05, + "loss": 0.4568, + "step": 2253 + }, + { + "epoch": 1.99, + "learning_rate": 1.853115287168372e-05, + "loss": 0.4551, + "step": 2254 + }, + { + "epoch": 1.99, + "learning_rate": 1.852965718383183e-05, + "loss": 0.4374, + "step": 2255 + }, + { + "epoch": 2.0, + "learning_rate": 1.8528160795281803e-05, + "loss": 0.4444, + "step": 2256 + }, + { + "epoch": 2.0, + "learning_rate": 1.852666370615656e-05, + "loss": 0.4649, + "step": 2257 + }, + { + "epoch": 2.0, + "learning_rate": 1.8525165916579097e-05, + "loss": 0.4638, + "step": 2258 + }, + { + "epoch": 2.0, + "learning_rate": 1.8523667426672437e-05, + "loss": 0.447, + "step": 2259 + }, + { + "epoch": 2.0, + "learning_rate": 1.8522168236559693e-05, + "loss": 0.4785, + "step": 2260 + }, + { + "epoch": 2.0, + "learning_rate": 1.8520668346364016e-05, + "loss": 0.4587, + "step": 2261 + }, + { + "epoch": 2.0, + "learning_rate": 1.8519167756208617e-05, + "loss": 0.3777, + "step": 2262 + }, + { + "epoch": 2.0, + "learning_rate": 1.8517666466216774e-05, + "loss": 0.3735, + "step": 2263 + }, + { + "epoch": 2.0, + "learning_rate": 1.8516164476511807e-05, + "loss": 0.3865, + "step": 2264 + }, + { + "epoch": 2.0, + "learning_rate": 1.851466178721711e-05, + "loss": 0.3874, + "step": 2265 + }, + { + "epoch": 2.0, + "learning_rate": 1.8513158398456122e-05, + "loss": 0.4013, + "step": 2266 + }, + { + "epoch": 2.01, + "learning_rate": 1.8511654310352345e-05, + "loss": 0.3868, + "step": 2267 + }, + { + "epoch": 2.01, + "learning_rate": 1.8510149523029338e-05, + "loss": 0.3709, + "step": 2268 + }, + { + "epoch": 2.01, + "learning_rate": 1.8508644036610717e-05, + "loss": 0.3708, + "step": 2269 + }, + { + "epoch": 2.01, + "learning_rate": 1.8507137851220155e-05, + "loss": 0.3868, + "step": 2270 + }, + { + "epoch": 2.01, + "learning_rate": 1.850563096698138e-05, + "loss": 0.3681, + "step": 2271 + }, + { + "epoch": 2.01, + "learning_rate": 1.850412338401819e-05, + "loss": 0.3939, + "step": 2272 + }, + { + "epoch": 2.01, + "learning_rate": 1.8502615102454418e-05, + "loss": 0.3559, + "step": 2273 + }, + { + "epoch": 2.01, + "learning_rate": 1.8501106122413975e-05, + "loss": 0.3556, + "step": 2274 + }, + { + "epoch": 2.01, + "learning_rate": 1.8499596444020818e-05, + "loss": 0.3712, + "step": 2275 + }, + { + "epoch": 2.01, + "learning_rate": 1.8498086067398967e-05, + "loss": 0.3716, + "step": 2276 + }, + { + "epoch": 2.01, + "learning_rate": 1.8496574992672494e-05, + "loss": 0.4077, + "step": 2277 + }, + { + "epoch": 2.02, + "learning_rate": 1.8495063219965536e-05, + "loss": 0.3681, + "step": 2278 + }, + { + "epoch": 2.02, + "learning_rate": 1.8493550749402278e-05, + "loss": 0.3724, + "step": 2279 + }, + { + "epoch": 2.02, + "learning_rate": 1.8492037581106973e-05, + "loss": 0.3702, + "step": 2280 + }, + { + "epoch": 2.02, + "learning_rate": 1.8490523715203916e-05, + "loss": 0.3907, + "step": 2281 + }, + { + "epoch": 2.02, + "learning_rate": 1.848900915181748e-05, + "loss": 0.3708, + "step": 2282 + }, + { + "epoch": 2.02, + "learning_rate": 1.8487493891072074e-05, + "loss": 0.3751, + "step": 2283 + }, + { + "epoch": 2.02, + "learning_rate": 1.8485977933092182e-05, + "loss": 0.3856, + "step": 2284 + }, + { + "epoch": 2.02, + "learning_rate": 1.848446127800233e-05, + "loss": 0.3729, + "step": 2285 + }, + { + "epoch": 2.02, + "learning_rate": 1.848294392592712e-05, + "loss": 0.3817, + "step": 2286 + }, + { + "epoch": 2.02, + "learning_rate": 1.848142587699119e-05, + "loss": 0.3778, + "step": 2287 + }, + { + "epoch": 2.02, + "learning_rate": 1.8479907131319246e-05, + "loss": 0.3652, + "step": 2288 + }, + { + "epoch": 2.02, + "learning_rate": 1.8478387689036058e-05, + "loss": 0.3892, + "step": 2289 + }, + { + "epoch": 2.03, + "learning_rate": 1.847686755026644e-05, + "loss": 0.3741, + "step": 2290 + }, + { + "epoch": 2.03, + "learning_rate": 1.8475346715135272e-05, + "loss": 0.3787, + "step": 2291 + }, + { + "epoch": 2.03, + "learning_rate": 1.8473825183767485e-05, + "loss": 0.3863, + "step": 2292 + }, + { + "epoch": 2.03, + "learning_rate": 1.847230295628807e-05, + "loss": 0.3738, + "step": 2293 + }, + { + "epoch": 2.03, + "learning_rate": 1.8470780032822077e-05, + "loss": 0.3564, + "step": 2294 + }, + { + "epoch": 2.03, + "learning_rate": 1.8469256413494616e-05, + "loss": 0.3636, + "step": 2295 + }, + { + "epoch": 2.03, + "learning_rate": 1.8467732098430846e-05, + "loss": 0.3821, + "step": 2296 + }, + { + "epoch": 2.03, + "learning_rate": 1.8466207087755987e-05, + "loss": 0.3763, + "step": 2297 + }, + { + "epoch": 2.03, + "learning_rate": 1.8464681381595316e-05, + "loss": 0.3734, + "step": 2298 + }, + { + "epoch": 2.03, + "learning_rate": 1.846315498007417e-05, + "loss": 0.3632, + "step": 2299 + }, + { + "epoch": 2.03, + "learning_rate": 1.8461627883317935e-05, + "loss": 0.3916, + "step": 2300 + }, + { + "epoch": 2.04, + "learning_rate": 1.8460100091452067e-05, + "loss": 0.3657, + "step": 2301 + }, + { + "epoch": 2.04, + "learning_rate": 1.8458571604602066e-05, + "loss": 0.3728, + "step": 2302 + }, + { + "epoch": 2.04, + "learning_rate": 1.8457042422893496e-05, + "loss": 0.3627, + "step": 2303 + }, + { + "epoch": 2.04, + "learning_rate": 1.8455512546451982e-05, + "loss": 0.3572, + "step": 2304 + }, + { + "epoch": 2.04, + "learning_rate": 1.8453981975403194e-05, + "loss": 0.3918, + "step": 2305 + }, + { + "epoch": 2.04, + "learning_rate": 1.8452450709872868e-05, + "loss": 0.348, + "step": 2306 + }, + { + "epoch": 2.04, + "learning_rate": 1.84509187499868e-05, + "loss": 0.387, + "step": 2307 + }, + { + "epoch": 2.04, + "learning_rate": 1.8449386095870833e-05, + "loss": 0.3618, + "step": 2308 + }, + { + "epoch": 2.04, + "learning_rate": 1.844785274765087e-05, + "loss": 0.3656, + "step": 2309 + }, + { + "epoch": 2.04, + "learning_rate": 1.8446318705452877e-05, + "loss": 0.3714, + "step": 2310 + }, + { + "epoch": 2.04, + "learning_rate": 1.8444783969402872e-05, + "loss": 0.3746, + "step": 2311 + }, + { + "epoch": 2.05, + "learning_rate": 1.8443248539626935e-05, + "loss": 0.3634, + "step": 2312 + }, + { + "epoch": 2.05, + "learning_rate": 1.8441712416251194e-05, + "loss": 0.3862, + "step": 2313 + }, + { + "epoch": 2.05, + "learning_rate": 1.844017559940184e-05, + "loss": 0.3954, + "step": 2314 + }, + { + "epoch": 2.05, + "learning_rate": 1.8438638089205126e-05, + "loss": 0.3951, + "step": 2315 + }, + { + "epoch": 2.05, + "learning_rate": 1.8437099885787348e-05, + "loss": 0.372, + "step": 2316 + }, + { + "epoch": 2.05, + "learning_rate": 1.8435560989274872e-05, + "loss": 0.3828, + "step": 2317 + }, + { + "epoch": 2.05, + "learning_rate": 1.843402139979411e-05, + "loss": 0.3785, + "step": 2318 + }, + { + "epoch": 2.05, + "learning_rate": 1.843248111747155e-05, + "loss": 0.3505, + "step": 2319 + }, + { + "epoch": 2.05, + "learning_rate": 1.8430940142433706e-05, + "loss": 0.3762, + "step": 2320 + }, + { + "epoch": 2.05, + "learning_rate": 1.842939847480718e-05, + "loss": 0.369, + "step": 2321 + }, + { + "epoch": 2.05, + "learning_rate": 1.8427856114718615e-05, + "loss": 0.3812, + "step": 2322 + }, + { + "epoch": 2.05, + "learning_rate": 1.842631306229471e-05, + "loss": 0.3738, + "step": 2323 + }, + { + "epoch": 2.06, + "learning_rate": 1.8424769317662223e-05, + "loss": 0.3982, + "step": 2324 + }, + { + "epoch": 2.06, + "learning_rate": 1.8423224880947976e-05, + "loss": 0.3794, + "step": 2325 + }, + { + "epoch": 2.06, + "learning_rate": 1.842167975227884e-05, + "loss": 0.3775, + "step": 2326 + }, + { + "epoch": 2.06, + "learning_rate": 1.8420133931781745e-05, + "loss": 0.3824, + "step": 2327 + }, + { + "epoch": 2.06, + "learning_rate": 1.8418587419583677e-05, + "loss": 0.3581, + "step": 2328 + }, + { + "epoch": 2.06, + "learning_rate": 1.8417040215811682e-05, + "loss": 0.3564, + "step": 2329 + }, + { + "epoch": 2.06, + "learning_rate": 1.8415492320592855e-05, + "loss": 0.3582, + "step": 2330 + }, + { + "epoch": 2.06, + "learning_rate": 1.8413943734054355e-05, + "loss": 0.3821, + "step": 2331 + }, + { + "epoch": 2.06, + "learning_rate": 1.84123944563234e-05, + "loss": 0.3854, + "step": 2332 + }, + { + "epoch": 2.06, + "learning_rate": 1.841084448752726e-05, + "loss": 0.3561, + "step": 2333 + }, + { + "epoch": 2.06, + "learning_rate": 1.840929382779326e-05, + "loss": 0.3658, + "step": 2334 + }, + { + "epoch": 2.07, + "learning_rate": 1.8407742477248783e-05, + "loss": 0.3784, + "step": 2335 + }, + { + "epoch": 2.07, + "learning_rate": 1.840619043602127e-05, + "loss": 0.3648, + "step": 2336 + }, + { + "epoch": 2.07, + "learning_rate": 1.8404637704238223e-05, + "loss": 0.367, + "step": 2337 + }, + { + "epoch": 2.07, + "learning_rate": 1.84030842820272e-05, + "loss": 0.3566, + "step": 2338 + }, + { + "epoch": 2.07, + "learning_rate": 1.8401530169515798e-05, + "loss": 0.3609, + "step": 2339 + }, + { + "epoch": 2.07, + "learning_rate": 1.83999753668317e-05, + "loss": 0.3774, + "step": 2340 + }, + { + "epoch": 2.07, + "learning_rate": 1.839841987410262e-05, + "loss": 0.3696, + "step": 2341 + }, + { + "epoch": 2.07, + "learning_rate": 1.8396863691456345e-05, + "loss": 0.3869, + "step": 2342 + }, + { + "epoch": 2.07, + "learning_rate": 1.8395306819020713e-05, + "loss": 0.3858, + "step": 2343 + }, + { + "epoch": 2.07, + "learning_rate": 1.8393749256923613e-05, + "loss": 0.3646, + "step": 2344 + }, + { + "epoch": 2.07, + "learning_rate": 1.8392191005293006e-05, + "loss": 0.3753, + "step": 2345 + }, + { + "epoch": 2.08, + "learning_rate": 1.839063206425689e-05, + "loss": 0.3595, + "step": 2346 + }, + { + "epoch": 2.08, + "learning_rate": 1.8389072433943337e-05, + "loss": 0.3734, + "step": 2347 + }, + { + "epoch": 2.08, + "learning_rate": 1.8387512114480466e-05, + "loss": 0.3617, + "step": 2348 + }, + { + "epoch": 2.08, + "learning_rate": 1.838595110599645e-05, + "loss": 0.369, + "step": 2349 + }, + { + "epoch": 2.08, + "learning_rate": 1.838438940861953e-05, + "loss": 0.3608, + "step": 2350 + }, + { + "epoch": 2.08, + "learning_rate": 1.8382827022477995e-05, + "loss": 0.3934, + "step": 2351 + }, + { + "epoch": 2.08, + "learning_rate": 1.838126394770019e-05, + "loss": 0.3681, + "step": 2352 + }, + { + "epoch": 2.08, + "learning_rate": 1.8379700184414525e-05, + "loss": 0.3777, + "step": 2353 + }, + { + "epoch": 2.08, + "learning_rate": 1.837813573274945e-05, + "loss": 0.3672, + "step": 2354 + }, + { + "epoch": 2.08, + "learning_rate": 1.8376570592833495e-05, + "loss": 0.3777, + "step": 2355 + }, + { + "epoch": 2.08, + "learning_rate": 1.837500476479523e-05, + "loss": 0.3979, + "step": 2356 + }, + { + "epoch": 2.09, + "learning_rate": 1.837343824876328e-05, + "loss": 0.3896, + "step": 2357 + }, + { + "epoch": 2.09, + "learning_rate": 1.8371871044866332e-05, + "loss": 0.3655, + "step": 2358 + }, + { + "epoch": 2.09, + "learning_rate": 1.837030315323314e-05, + "loss": 0.3838, + "step": 2359 + }, + { + "epoch": 2.09, + "learning_rate": 1.8368734573992496e-05, + "loss": 0.3602, + "step": 2360 + }, + { + "epoch": 2.09, + "learning_rate": 1.8367165307273253e-05, + "loss": 0.396, + "step": 2361 + }, + { + "epoch": 2.09, + "learning_rate": 1.836559535320433e-05, + "loss": 0.3683, + "step": 2362 + }, + { + "epoch": 2.09, + "learning_rate": 1.8364024711914693e-05, + "loss": 0.3876, + "step": 2363 + }, + { + "epoch": 2.09, + "learning_rate": 1.8362453383533368e-05, + "loss": 0.375, + "step": 2364 + }, + { + "epoch": 2.09, + "learning_rate": 1.836088136818944e-05, + "loss": 0.3971, + "step": 2365 + }, + { + "epoch": 2.09, + "learning_rate": 1.8359308666012046e-05, + "loss": 0.3771, + "step": 2366 + }, + { + "epoch": 2.09, + "learning_rate": 1.835773527713038e-05, + "loss": 0.377, + "step": 2367 + }, + { + "epoch": 2.09, + "learning_rate": 1.8356161201673692e-05, + "loss": 0.3724, + "step": 2368 + }, + { + "epoch": 2.1, + "learning_rate": 1.8354586439771297e-05, + "loss": 0.3744, + "step": 2369 + }, + { + "epoch": 2.1, + "learning_rate": 1.835301099155255e-05, + "loss": 0.3775, + "step": 2370 + }, + { + "epoch": 2.1, + "learning_rate": 1.8351434857146878e-05, + "loss": 0.3841, + "step": 2371 + }, + { + "epoch": 2.1, + "learning_rate": 1.834985803668375e-05, + "loss": 0.373, + "step": 2372 + }, + { + "epoch": 2.1, + "learning_rate": 1.8348280530292712e-05, + "loss": 0.3644, + "step": 2373 + }, + { + "epoch": 2.1, + "learning_rate": 1.834670233810335e-05, + "loss": 0.402, + "step": 2374 + }, + { + "epoch": 2.1, + "learning_rate": 1.83451234602453e-05, + "loss": 0.3567, + "step": 2375 + }, + { + "epoch": 2.1, + "learning_rate": 1.8343543896848275e-05, + "loss": 0.3735, + "step": 2376 + }, + { + "epoch": 2.1, + "learning_rate": 1.8341963648042028e-05, + "loss": 0.3796, + "step": 2377 + }, + { + "epoch": 2.1, + "learning_rate": 1.8340382713956376e-05, + "loss": 0.3679, + "step": 2378 + }, + { + "epoch": 2.1, + "learning_rate": 1.833880109472119e-05, + "loss": 0.3833, + "step": 2379 + }, + { + "epoch": 2.11, + "learning_rate": 1.8337218790466404e-05, + "loss": 0.369, + "step": 2380 + }, + { + "epoch": 2.11, + "learning_rate": 1.8335635801321988e-05, + "loss": 0.3554, + "step": 2381 + }, + { + "epoch": 2.11, + "learning_rate": 1.8334052127417994e-05, + "loss": 0.3903, + "step": 2382 + }, + { + "epoch": 2.11, + "learning_rate": 1.8332467768884513e-05, + "loss": 0.3862, + "step": 2383 + }, + { + "epoch": 2.11, + "learning_rate": 1.8330882725851703e-05, + "loss": 0.3537, + "step": 2384 + }, + { + "epoch": 2.11, + "learning_rate": 1.8329296998449763e-05, + "loss": 0.3745, + "step": 2385 + }, + { + "epoch": 2.11, + "learning_rate": 1.8327710586808967e-05, + "loss": 0.3867, + "step": 2386 + }, + { + "epoch": 2.11, + "learning_rate": 1.832612349105963e-05, + "loss": 0.3899, + "step": 2387 + }, + { + "epoch": 2.11, + "learning_rate": 1.8324535711332136e-05, + "loss": 0.3638, + "step": 2388 + }, + { + "epoch": 2.11, + "learning_rate": 1.8322947247756916e-05, + "loss": 0.389, + "step": 2389 + }, + { + "epoch": 2.11, + "learning_rate": 1.8321358100464456e-05, + "loss": 0.3929, + "step": 2390 + }, + { + "epoch": 2.12, + "learning_rate": 1.8319768269585304e-05, + "loss": 0.3782, + "step": 2391 + }, + { + "epoch": 2.12, + "learning_rate": 1.8318177755250067e-05, + "loss": 0.3864, + "step": 2392 + }, + { + "epoch": 2.12, + "learning_rate": 1.8316586557589397e-05, + "loss": 0.3751, + "step": 2393 + }, + { + "epoch": 2.12, + "learning_rate": 1.831499467673401e-05, + "loss": 0.3854, + "step": 2394 + }, + { + "epoch": 2.12, + "learning_rate": 1.831340211281468e-05, + "loss": 0.3683, + "step": 2395 + }, + { + "epoch": 2.12, + "learning_rate": 1.831180886596223e-05, + "loss": 0.3528, + "step": 2396 + }, + { + "epoch": 2.12, + "learning_rate": 1.8310214936307545e-05, + "loss": 0.3768, + "step": 2397 + }, + { + "epoch": 2.12, + "learning_rate": 1.830862032398156e-05, + "loss": 0.3699, + "step": 2398 + }, + { + "epoch": 2.12, + "learning_rate": 1.830702502911527e-05, + "loss": 0.3536, + "step": 2399 + }, + { + "epoch": 2.12, + "learning_rate": 1.8305429051839736e-05, + "loss": 0.4102, + "step": 2400 + }, + { + "epoch": 2.12, + "learning_rate": 1.830383239228605e-05, + "loss": 0.3775, + "step": 2401 + }, + { + "epoch": 2.12, + "learning_rate": 1.830223505058539e-05, + "loss": 0.3548, + "step": 2402 + }, + { + "epoch": 2.13, + "learning_rate": 1.8300637026868963e-05, + "loss": 0.3895, + "step": 2403 + }, + { + "epoch": 2.13, + "learning_rate": 1.8299038321268053e-05, + "loss": 0.3824, + "step": 2404 + }, + { + "epoch": 2.13, + "learning_rate": 1.8297438933913983e-05, + "loss": 0.3609, + "step": 2405 + }, + { + "epoch": 2.13, + "learning_rate": 1.8295838864938145e-05, + "loss": 0.3703, + "step": 2406 + }, + { + "epoch": 2.13, + "learning_rate": 1.8294238114471985e-05, + "loss": 0.3472, + "step": 2407 + }, + { + "epoch": 2.13, + "learning_rate": 1.8292636682646997e-05, + "loss": 0.3894, + "step": 2408 + }, + { + "epoch": 2.13, + "learning_rate": 1.829103456959474e-05, + "loss": 0.3799, + "step": 2409 + }, + { + "epoch": 2.13, + "learning_rate": 1.828943177544682e-05, + "loss": 0.3745, + "step": 2410 + }, + { + "epoch": 2.13, + "learning_rate": 1.828782830033491e-05, + "loss": 0.3696, + "step": 2411 + }, + { + "epoch": 2.13, + "learning_rate": 1.828622414439073e-05, + "loss": 0.373, + "step": 2412 + }, + { + "epoch": 2.13, + "learning_rate": 1.8284619307746053e-05, + "loss": 0.3781, + "step": 2413 + }, + { + "epoch": 2.14, + "learning_rate": 1.8283013790532726e-05, + "loss": 0.4019, + "step": 2414 + }, + { + "epoch": 2.14, + "learning_rate": 1.828140759288263e-05, + "loss": 0.3944, + "step": 2415 + }, + { + "epoch": 2.14, + "learning_rate": 1.827980071492772e-05, + "loss": 0.357, + "step": 2416 + }, + { + "epoch": 2.14, + "learning_rate": 1.827819315679999e-05, + "loss": 0.3848, + "step": 2417 + }, + { + "epoch": 2.14, + "learning_rate": 1.8276584918631504e-05, + "loss": 0.3448, + "step": 2418 + }, + { + "epoch": 2.14, + "learning_rate": 1.8274976000554374e-05, + "loss": 0.3735, + "step": 2419 + }, + { + "epoch": 2.14, + "learning_rate": 1.8273366402700768e-05, + "loss": 0.368, + "step": 2420 + }, + { + "epoch": 2.14, + "learning_rate": 1.827175612520292e-05, + "loss": 0.3793, + "step": 2421 + }, + { + "epoch": 2.14, + "learning_rate": 1.8270145168193106e-05, + "loss": 0.3668, + "step": 2422 + }, + { + "epoch": 2.14, + "learning_rate": 1.8268533531803663e-05, + "loss": 0.3737, + "step": 2423 + }, + { + "epoch": 2.14, + "learning_rate": 1.8266921216166983e-05, + "loss": 0.3988, + "step": 2424 + }, + { + "epoch": 2.15, + "learning_rate": 1.8265308221415518e-05, + "loss": 0.3606, + "step": 2425 + }, + { + "epoch": 2.15, + "learning_rate": 1.8263694547681776e-05, + "loss": 0.3742, + "step": 2426 + }, + { + "epoch": 2.15, + "learning_rate": 1.8262080195098313e-05, + "loss": 0.3728, + "step": 2427 + }, + { + "epoch": 2.15, + "learning_rate": 1.8260465163797747e-05, + "loss": 0.3761, + "step": 2428 + }, + { + "epoch": 2.15, + "learning_rate": 1.8258849453912752e-05, + "loss": 0.3612, + "step": 2429 + }, + { + "epoch": 2.15, + "learning_rate": 1.8257233065576053e-05, + "loss": 0.3803, + "step": 2430 + }, + { + "epoch": 2.15, + "learning_rate": 1.8255615998920435e-05, + "loss": 0.3805, + "step": 2431 + }, + { + "epoch": 2.15, + "learning_rate": 1.8253998254078737e-05, + "loss": 0.365, + "step": 2432 + }, + { + "epoch": 2.15, + "learning_rate": 1.8252379831183857e-05, + "loss": 0.3649, + "step": 2433 + }, + { + "epoch": 2.15, + "learning_rate": 1.8250760730368743e-05, + "loss": 0.3823, + "step": 2434 + }, + { + "epoch": 2.15, + "learning_rate": 1.8249140951766403e-05, + "loss": 0.3911, + "step": 2435 + }, + { + "epoch": 2.15, + "learning_rate": 1.82475204955099e-05, + "loss": 0.3686, + "step": 2436 + }, + { + "epoch": 2.16, + "learning_rate": 1.824589936173235e-05, + "loss": 0.3918, + "step": 2437 + }, + { + "epoch": 2.16, + "learning_rate": 1.8244277550566928e-05, + "loss": 0.3615, + "step": 2438 + }, + { + "epoch": 2.16, + "learning_rate": 1.8242655062146862e-05, + "loss": 0.3976, + "step": 2439 + }, + { + "epoch": 2.16, + "learning_rate": 1.824103189660544e-05, + "loss": 0.3577, + "step": 2440 + }, + { + "epoch": 2.16, + "learning_rate": 1.8239408054076e-05, + "loss": 0.3716, + "step": 2441 + }, + { + "epoch": 2.16, + "learning_rate": 1.8237783534691937e-05, + "loss": 0.3864, + "step": 2442 + }, + { + "epoch": 2.16, + "learning_rate": 1.82361583385867e-05, + "loss": 0.3775, + "step": 2443 + }, + { + "epoch": 2.16, + "learning_rate": 1.8234532465893807e-05, + "loss": 0.3759, + "step": 2444 + }, + { + "epoch": 2.16, + "learning_rate": 1.8232905916746815e-05, + "loss": 0.3943, + "step": 2445 + }, + { + "epoch": 2.16, + "learning_rate": 1.8231278691279336e-05, + "loss": 0.379, + "step": 2446 + }, + { + "epoch": 2.16, + "learning_rate": 1.8229650789625055e-05, + "loss": 0.378, + "step": 2447 + }, + { + "epoch": 2.17, + "learning_rate": 1.8228022211917695e-05, + "loss": 0.3936, + "step": 2448 + }, + { + "epoch": 2.17, + "learning_rate": 1.8226392958291044e-05, + "loss": 0.365, + "step": 2449 + }, + { + "epoch": 2.17, + "learning_rate": 1.822476302887894e-05, + "loss": 0.351, + "step": 2450 + }, + { + "epoch": 2.17, + "learning_rate": 1.8223132423815282e-05, + "loss": 0.3635, + "step": 2451 + }, + { + "epoch": 2.17, + "learning_rate": 1.8221501143234018e-05, + "loss": 0.3713, + "step": 2452 + }, + { + "epoch": 2.17, + "learning_rate": 1.821986918726916e-05, + "loss": 0.3835, + "step": 2453 + }, + { + "epoch": 2.17, + "learning_rate": 1.8218236556054764e-05, + "loss": 0.3721, + "step": 2454 + }, + { + "epoch": 2.17, + "learning_rate": 1.8216603249724956e-05, + "loss": 0.3815, + "step": 2455 + }, + { + "epoch": 2.17, + "learning_rate": 1.8214969268413905e-05, + "loss": 0.4027, + "step": 2456 + }, + { + "epoch": 2.17, + "learning_rate": 1.821333461225584e-05, + "loss": 0.3898, + "step": 2457 + }, + { + "epoch": 2.17, + "learning_rate": 1.8211699281385048e-05, + "loss": 0.3904, + "step": 2458 + }, + { + "epoch": 2.18, + "learning_rate": 1.821006327593587e-05, + "loss": 0.3689, + "step": 2459 + }, + { + "epoch": 2.18, + "learning_rate": 1.8208426596042693e-05, + "loss": 0.362, + "step": 2460 + }, + { + "epoch": 2.18, + "learning_rate": 1.8206789241839975e-05, + "loss": 0.4035, + "step": 2461 + }, + { + "epoch": 2.18, + "learning_rate": 1.820515121346222e-05, + "loss": 0.3955, + "step": 2462 + }, + { + "epoch": 2.18, + "learning_rate": 1.8203512511043992e-05, + "loss": 0.3658, + "step": 2463 + }, + { + "epoch": 2.18, + "learning_rate": 1.8201873134719905e-05, + "loss": 0.362, + "step": 2464 + }, + { + "epoch": 2.18, + "learning_rate": 1.8200233084624632e-05, + "loss": 0.367, + "step": 2465 + }, + { + "epoch": 2.18, + "learning_rate": 1.81985923608929e-05, + "loss": 0.3834, + "step": 2466 + }, + { + "epoch": 2.18, + "learning_rate": 1.8196950963659493e-05, + "loss": 0.3849, + "step": 2467 + }, + { + "epoch": 2.18, + "learning_rate": 1.8195308893059247e-05, + "loss": 0.361, + "step": 2468 + }, + { + "epoch": 2.18, + "learning_rate": 1.8193666149227058e-05, + "loss": 0.3898, + "step": 2469 + }, + { + "epoch": 2.18, + "learning_rate": 1.8192022732297877e-05, + "loss": 0.401, + "step": 2470 + }, + { + "epoch": 2.19, + "learning_rate": 1.8190378642406702e-05, + "loss": 0.3838, + "step": 2471 + }, + { + "epoch": 2.19, + "learning_rate": 1.81887338796886e-05, + "loss": 0.3937, + "step": 2472 + }, + { + "epoch": 2.19, + "learning_rate": 1.8187088444278675e-05, + "loss": 0.386, + "step": 2473 + }, + { + "epoch": 2.19, + "learning_rate": 1.8185442336312106e-05, + "loss": 0.3543, + "step": 2474 + }, + { + "epoch": 2.19, + "learning_rate": 1.818379555592412e-05, + "loss": 0.3879, + "step": 2475 + }, + { + "epoch": 2.19, + "learning_rate": 1.8182148103249987e-05, + "loss": 0.3874, + "step": 2476 + }, + { + "epoch": 2.19, + "learning_rate": 1.818049997842505e-05, + "loss": 0.3835, + "step": 2477 + }, + { + "epoch": 2.19, + "learning_rate": 1.8178851181584703e-05, + "loss": 0.3585, + "step": 2478 + }, + { + "epoch": 2.19, + "learning_rate": 1.8177201712864384e-05, + "loss": 0.3822, + "step": 2479 + }, + { + "epoch": 2.19, + "learning_rate": 1.81755515723996e-05, + "loss": 0.3799, + "step": 2480 + }, + { + "epoch": 2.19, + "learning_rate": 1.8173900760325904e-05, + "loss": 0.3836, + "step": 2481 + }, + { + "epoch": 2.2, + "learning_rate": 1.817224927677891e-05, + "loss": 0.3462, + "step": 2482 + }, + { + "epoch": 2.2, + "learning_rate": 1.8170597121894286e-05, + "loss": 0.3817, + "step": 2483 + }, + { + "epoch": 2.2, + "learning_rate": 1.816894429580775e-05, + "loss": 0.3694, + "step": 2484 + }, + { + "epoch": 2.2, + "learning_rate": 1.816729079865508e-05, + "loss": 0.3863, + "step": 2485 + }, + { + "epoch": 2.2, + "learning_rate": 1.816563663057211e-05, + "loss": 0.3624, + "step": 2486 + }, + { + "epoch": 2.2, + "learning_rate": 1.816398179169473e-05, + "loss": 0.395, + "step": 2487 + }, + { + "epoch": 2.2, + "learning_rate": 1.8162326282158874e-05, + "loss": 0.3611, + "step": 2488 + }, + { + "epoch": 2.2, + "learning_rate": 1.8160670102100547e-05, + "loss": 0.3616, + "step": 2489 + }, + { + "epoch": 2.2, + "learning_rate": 1.8159013251655802e-05, + "loss": 0.3814, + "step": 2490 + }, + { + "epoch": 2.2, + "learning_rate": 1.8157355730960743e-05, + "loss": 0.3887, + "step": 2491 + }, + { + "epoch": 2.2, + "learning_rate": 1.815569754015153e-05, + "loss": 0.3589, + "step": 2492 + }, + { + "epoch": 2.21, + "learning_rate": 1.8154038679364388e-05, + "loss": 0.3789, + "step": 2493 + }, + { + "epoch": 2.21, + "learning_rate": 1.8152379148735586e-05, + "loss": 0.3893, + "step": 2494 + }, + { + "epoch": 2.21, + "learning_rate": 1.8150718948401454e-05, + "loss": 0.3718, + "step": 2495 + }, + { + "epoch": 2.21, + "learning_rate": 1.814905807849837e-05, + "loss": 0.3656, + "step": 2496 + }, + { + "epoch": 2.21, + "learning_rate": 1.8147396539162777e-05, + "loss": 0.3919, + "step": 2497 + }, + { + "epoch": 2.21, + "learning_rate": 1.8145734330531166e-05, + "loss": 0.3739, + "step": 2498 + }, + { + "epoch": 2.21, + "learning_rate": 1.8144071452740085e-05, + "loss": 0.3898, + "step": 2499 + }, + { + "epoch": 2.21, + "learning_rate": 1.8142407905926135e-05, + "loss": 0.3696, + "step": 2500 + }, + { + "epoch": 2.21, + "learning_rate": 1.8140743690225978e-05, + "loss": 0.3883, + "step": 2501 + }, + { + "epoch": 2.21, + "learning_rate": 1.813907880577632e-05, + "loss": 0.3724, + "step": 2502 + }, + { + "epoch": 2.21, + "learning_rate": 1.813741325271394e-05, + "loss": 0.3856, + "step": 2503 + }, + { + "epoch": 2.22, + "learning_rate": 1.813574703117565e-05, + "loss": 0.3873, + "step": 2504 + }, + { + "epoch": 2.22, + "learning_rate": 1.8134080141298328e-05, + "loss": 0.3871, + "step": 2505 + }, + { + "epoch": 2.22, + "learning_rate": 1.8132412583218914e-05, + "loss": 0.3719, + "step": 2506 + }, + { + "epoch": 2.22, + "learning_rate": 1.813074435707439e-05, + "loss": 0.3694, + "step": 2507 + }, + { + "epoch": 2.22, + "learning_rate": 1.8129075463001796e-05, + "loss": 0.4085, + "step": 2508 + }, + { + "epoch": 2.22, + "learning_rate": 1.8127405901138236e-05, + "loss": 0.3877, + "step": 2509 + }, + { + "epoch": 2.22, + "learning_rate": 1.8125735671620854e-05, + "loss": 0.3773, + "step": 2510 + }, + { + "epoch": 2.22, + "learning_rate": 1.8124064774586866e-05, + "loss": 0.3755, + "step": 2511 + }, + { + "epoch": 2.22, + "learning_rate": 1.8122393210173525e-05, + "loss": 0.3644, + "step": 2512 + }, + { + "epoch": 2.22, + "learning_rate": 1.812072097851815e-05, + "loss": 0.3637, + "step": 2513 + }, + { + "epoch": 2.22, + "learning_rate": 1.8119048079758115e-05, + "loss": 0.3796, + "step": 2514 + }, + { + "epoch": 2.22, + "learning_rate": 1.8117374514030844e-05, + "loss": 0.38, + "step": 2515 + }, + { + "epoch": 2.23, + "learning_rate": 1.8115700281473816e-05, + "loss": 0.3792, + "step": 2516 + }, + { + "epoch": 2.23, + "learning_rate": 1.811402538222457e-05, + "loss": 0.3455, + "step": 2517 + }, + { + "epoch": 2.23, + "learning_rate": 1.8112349816420696e-05, + "loss": 0.3889, + "step": 2518 + }, + { + "epoch": 2.23, + "learning_rate": 1.8110673584199835e-05, + "loss": 0.3714, + "step": 2519 + }, + { + "epoch": 2.23, + "learning_rate": 1.8108996685699694e-05, + "loss": 0.3669, + "step": 2520 + }, + { + "epoch": 2.23, + "learning_rate": 1.810731912105802e-05, + "loss": 0.3558, + "step": 2521 + }, + { + "epoch": 2.23, + "learning_rate": 1.810564089041263e-05, + "loss": 0.3809, + "step": 2522 + }, + { + "epoch": 2.23, + "learning_rate": 1.8103961993901377e-05, + "loss": 0.3837, + "step": 2523 + }, + { + "epoch": 2.23, + "learning_rate": 1.810228243166219e-05, + "loss": 0.3543, + "step": 2524 + }, + { + "epoch": 2.23, + "learning_rate": 1.810060220383304e-05, + "loss": 0.3833, + "step": 2525 + }, + { + "epoch": 2.23, + "learning_rate": 1.8098921310551956e-05, + "loss": 0.3598, + "step": 2526 + }, + { + "epoch": 2.24, + "learning_rate": 1.809723975195702e-05, + "loss": 0.3726, + "step": 2527 + }, + { + "epoch": 2.24, + "learning_rate": 1.8095557528186363e-05, + "loss": 0.3776, + "step": 2528 + }, + { + "epoch": 2.24, + "learning_rate": 1.8093874639378187e-05, + "loss": 0.3805, + "step": 2529 + }, + { + "epoch": 2.24, + "learning_rate": 1.8092191085670733e-05, + "loss": 0.3832, + "step": 2530 + }, + { + "epoch": 2.24, + "learning_rate": 1.8090506867202305e-05, + "loss": 0.4024, + "step": 2531 + }, + { + "epoch": 2.24, + "learning_rate": 1.8088821984111257e-05, + "loss": 0.3811, + "step": 2532 + }, + { + "epoch": 2.24, + "learning_rate": 1.8087136436535997e-05, + "loss": 0.3867, + "step": 2533 + }, + { + "epoch": 2.24, + "learning_rate": 1.8085450224614996e-05, + "loss": 0.3656, + "step": 2534 + }, + { + "epoch": 2.24, + "learning_rate": 1.808376334848677e-05, + "loss": 0.3685, + "step": 2535 + }, + { + "epoch": 2.24, + "learning_rate": 1.8082075808289893e-05, + "loss": 0.4107, + "step": 2536 + }, + { + "epoch": 2.24, + "learning_rate": 1.8080387604162995e-05, + "loss": 0.3403, + "step": 2537 + }, + { + "epoch": 2.25, + "learning_rate": 1.8078698736244763e-05, + "loss": 0.3623, + "step": 2538 + }, + { + "epoch": 2.25, + "learning_rate": 1.807700920467393e-05, + "loss": 0.3849, + "step": 2539 + }, + { + "epoch": 2.25, + "learning_rate": 1.807531900958929e-05, + "loss": 0.3794, + "step": 2540 + }, + { + "epoch": 2.25, + "learning_rate": 1.8073628151129688e-05, + "loss": 0.3734, + "step": 2541 + }, + { + "epoch": 2.25, + "learning_rate": 1.8071936629434026e-05, + "loss": 0.365, + "step": 2542 + }, + { + "epoch": 2.25, + "learning_rate": 1.8070244444641264e-05, + "loss": 0.3592, + "step": 2543 + }, + { + "epoch": 2.25, + "learning_rate": 1.8068551596890404e-05, + "loss": 0.3785, + "step": 2544 + }, + { + "epoch": 2.25, + "learning_rate": 1.806685808632052e-05, + "loss": 0.3819, + "step": 2545 + }, + { + "epoch": 2.25, + "learning_rate": 1.8065163913070726e-05, + "loss": 0.3785, + "step": 2546 + }, + { + "epoch": 2.25, + "learning_rate": 1.80634690772802e-05, + "loss": 0.3965, + "step": 2547 + }, + { + "epoch": 2.25, + "learning_rate": 1.8061773579088166e-05, + "loss": 0.3771, + "step": 2548 + }, + { + "epoch": 2.25, + "learning_rate": 1.8060077418633902e-05, + "loss": 0.3618, + "step": 2549 + }, + { + "epoch": 2.26, + "learning_rate": 1.8058380596056758e-05, + "loss": 0.3726, + "step": 2550 + }, + { + "epoch": 2.26, + "learning_rate": 1.8056683111496115e-05, + "loss": 0.3985, + "step": 2551 + }, + { + "epoch": 2.26, + "learning_rate": 1.805498496509142e-05, + "loss": 0.4016, + "step": 2552 + }, + { + "epoch": 2.26, + "learning_rate": 1.805328615698218e-05, + "loss": 0.3811, + "step": 2553 + }, + { + "epoch": 2.26, + "learning_rate": 1.8051586687307934e-05, + "loss": 0.3985, + "step": 2554 + }, + { + "epoch": 2.26, + "learning_rate": 1.804988655620831e-05, + "loss": 0.3682, + "step": 2555 + }, + { + "epoch": 2.26, + "learning_rate": 1.804818576382296e-05, + "loss": 0.3771, + "step": 2556 + }, + { + "epoch": 2.26, + "learning_rate": 1.8046484310291605e-05, + "loss": 0.3838, + "step": 2557 + }, + { + "epoch": 2.26, + "learning_rate": 1.8044782195754015e-05, + "loss": 0.3795, + "step": 2558 + }, + { + "epoch": 2.26, + "learning_rate": 1.8043079420350016e-05, + "loss": 0.3812, + "step": 2559 + }, + { + "epoch": 2.26, + "learning_rate": 1.804137598421949e-05, + "loss": 0.3813, + "step": 2560 + }, + { + "epoch": 2.27, + "learning_rate": 1.803967188750237e-05, + "loss": 0.3677, + "step": 2561 + }, + { + "epoch": 2.27, + "learning_rate": 1.8037967130338644e-05, + "loss": 0.3709, + "step": 2562 + }, + { + "epoch": 2.27, + "learning_rate": 1.8036261712868358e-05, + "loss": 0.3586, + "step": 2563 + }, + { + "epoch": 2.27, + "learning_rate": 1.803455563523161e-05, + "loss": 0.3779, + "step": 2564 + }, + { + "epoch": 2.27, + "learning_rate": 1.803284889756854e-05, + "loss": 0.3746, + "step": 2565 + }, + { + "epoch": 2.27, + "learning_rate": 1.8031141500019374e-05, + "loss": 0.3681, + "step": 2566 + }, + { + "epoch": 2.27, + "learning_rate": 1.802943344272436e-05, + "loss": 0.3686, + "step": 2567 + }, + { + "epoch": 2.27, + "learning_rate": 1.802772472582381e-05, + "loss": 0.3787, + "step": 2568 + }, + { + "epoch": 2.27, + "learning_rate": 1.80260153494581e-05, + "loss": 0.3864, + "step": 2569 + }, + { + "epoch": 2.27, + "learning_rate": 1.8024305313767648e-05, + "loss": 0.4012, + "step": 2570 + }, + { + "epoch": 2.27, + "learning_rate": 1.802259461889293e-05, + "loss": 0.3695, + "step": 2571 + }, + { + "epoch": 2.28, + "learning_rate": 1.802088326497448e-05, + "loss": 0.3819, + "step": 2572 + }, + { + "epoch": 2.28, + "learning_rate": 1.801917125215288e-05, + "loss": 0.3965, + "step": 2573 + }, + { + "epoch": 2.28, + "learning_rate": 1.8017458580568772e-05, + "loss": 0.3915, + "step": 2574 + }, + { + "epoch": 2.28, + "learning_rate": 1.8015745250362852e-05, + "loss": 0.3474, + "step": 2575 + }, + { + "epoch": 2.28, + "learning_rate": 1.801403126167586e-05, + "loss": 0.3749, + "step": 2576 + }, + { + "epoch": 2.28, + "learning_rate": 1.8012316614648602e-05, + "loss": 0.3499, + "step": 2577 + }, + { + "epoch": 2.28, + "learning_rate": 1.8010601309421935e-05, + "loss": 0.3863, + "step": 2578 + }, + { + "epoch": 2.28, + "learning_rate": 1.8008885346136763e-05, + "loss": 0.3691, + "step": 2579 + }, + { + "epoch": 2.28, + "learning_rate": 1.800716872493405e-05, + "loss": 0.3881, + "step": 2580 + }, + { + "epoch": 2.28, + "learning_rate": 1.8005451445954825e-05, + "loss": 0.3662, + "step": 2581 + }, + { + "epoch": 2.28, + "learning_rate": 1.8003733509340148e-05, + "loss": 0.376, + "step": 2582 + }, + { + "epoch": 2.28, + "learning_rate": 1.8002014915231147e-05, + "loss": 0.3724, + "step": 2583 + }, + { + "epoch": 2.29, + "learning_rate": 1.8000295663769005e-05, + "loss": 0.3956, + "step": 2584 + }, + { + "epoch": 2.29, + "learning_rate": 1.7998575755094957e-05, + "loss": 0.3998, + "step": 2585 + }, + { + "epoch": 2.29, + "learning_rate": 1.7996855189350282e-05, + "loss": 0.3784, + "step": 2586 + }, + { + "epoch": 2.29, + "learning_rate": 1.799513396667633e-05, + "loss": 0.3605, + "step": 2587 + }, + { + "epoch": 2.29, + "learning_rate": 1.79934120872145e-05, + "loss": 0.3733, + "step": 2588 + }, + { + "epoch": 2.29, + "learning_rate": 1.799168955110623e-05, + "loss": 0.411, + "step": 2589 + }, + { + "epoch": 2.29, + "learning_rate": 1.7989966358493033e-05, + "loss": 0.374, + "step": 2590 + }, + { + "epoch": 2.29, + "learning_rate": 1.7988242509516464e-05, + "loss": 0.3615, + "step": 2591 + }, + { + "epoch": 2.29, + "learning_rate": 1.7986518004318134e-05, + "loss": 0.4122, + "step": 2592 + }, + { + "epoch": 2.29, + "learning_rate": 1.7984792843039708e-05, + "loss": 0.365, + "step": 2593 + }, + { + "epoch": 2.29, + "learning_rate": 1.7983067025822908e-05, + "loss": 0.3731, + "step": 2594 + }, + { + "epoch": 2.3, + "learning_rate": 1.7981340552809503e-05, + "loss": 0.3914, + "step": 2595 + }, + { + "epoch": 2.3, + "learning_rate": 1.7979613424141325e-05, + "loss": 0.3743, + "step": 2596 + }, + { + "epoch": 2.3, + "learning_rate": 1.7977885639960248e-05, + "loss": 0.3992, + "step": 2597 + }, + { + "epoch": 2.3, + "learning_rate": 1.7976157200408214e-05, + "loss": 0.3749, + "step": 2598 + }, + { + "epoch": 2.3, + "learning_rate": 1.797442810562721e-05, + "loss": 0.3902, + "step": 2599 + }, + { + "epoch": 2.3, + "learning_rate": 1.7972698355759275e-05, + "loss": 0.3962, + "step": 2600 + }, + { + "epoch": 2.3, + "learning_rate": 1.7970967950946506e-05, + "loss": 0.3847, + "step": 2601 + }, + { + "epoch": 2.3, + "learning_rate": 1.796923689133106e-05, + "loss": 0.3846, + "step": 2602 + }, + { + "epoch": 2.3, + "learning_rate": 1.796750517705513e-05, + "loss": 0.3772, + "step": 2603 + }, + { + "epoch": 2.3, + "learning_rate": 1.7965772808260983e-05, + "loss": 0.3814, + "step": 2604 + }, + { + "epoch": 2.3, + "learning_rate": 1.7964039785090925e-05, + "loss": 0.3811, + "step": 2605 + }, + { + "epoch": 2.31, + "learning_rate": 1.7962306107687323e-05, + "loss": 0.3664, + "step": 2606 + }, + { + "epoch": 2.31, + "learning_rate": 1.7960571776192593e-05, + "loss": 0.3861, + "step": 2607 + }, + { + "epoch": 2.31, + "learning_rate": 1.7958836790749214e-05, + "loss": 0.3907, + "step": 2608 + }, + { + "epoch": 2.31, + "learning_rate": 1.7957101151499704e-05, + "loss": 0.3881, + "step": 2609 + }, + { + "epoch": 2.31, + "learning_rate": 1.7955364858586652e-05, + "loss": 0.3705, + "step": 2610 + }, + { + "epoch": 2.31, + "learning_rate": 1.7953627912152685e-05, + "loss": 0.3809, + "step": 2611 + }, + { + "epoch": 2.31, + "learning_rate": 1.795189031234049e-05, + "loss": 0.3773, + "step": 2612 + }, + { + "epoch": 2.31, + "learning_rate": 1.7950152059292816e-05, + "loss": 0.3721, + "step": 2613 + }, + { + "epoch": 2.31, + "learning_rate": 1.7948413153152452e-05, + "loss": 0.3878, + "step": 2614 + }, + { + "epoch": 2.31, + "learning_rate": 1.7946673594062246e-05, + "loss": 0.4227, + "step": 2615 + }, + { + "epoch": 2.31, + "learning_rate": 1.7944933382165103e-05, + "loss": 0.4092, + "step": 2616 + }, + { + "epoch": 2.32, + "learning_rate": 1.7943192517603975e-05, + "loss": 0.3789, + "step": 2617 + }, + { + "epoch": 2.32, + "learning_rate": 1.7941451000521874e-05, + "loss": 0.392, + "step": 2618 + }, + { + "epoch": 2.32, + "learning_rate": 1.7939708831061865e-05, + "loss": 0.378, + "step": 2619 + }, + { + "epoch": 2.32, + "learning_rate": 1.793796600936706e-05, + "loss": 0.3879, + "step": 2620 + }, + { + "epoch": 2.32, + "learning_rate": 1.7936222535580626e-05, + "loss": 0.3716, + "step": 2621 + }, + { + "epoch": 2.32, + "learning_rate": 1.7934478409845798e-05, + "loss": 0.3695, + "step": 2622 + }, + { + "epoch": 2.32, + "learning_rate": 1.7932733632305845e-05, + "loss": 0.3791, + "step": 2623 + }, + { + "epoch": 2.32, + "learning_rate": 1.79309882031041e-05, + "loss": 0.3967, + "step": 2624 + }, + { + "epoch": 2.32, + "learning_rate": 1.7929242122383948e-05, + "loss": 0.3721, + "step": 2625 + }, + { + "epoch": 2.32, + "learning_rate": 1.792749539028882e-05, + "loss": 0.3841, + "step": 2626 + }, + { + "epoch": 2.32, + "learning_rate": 1.792574800696222e-05, + "loss": 0.3715, + "step": 2627 + }, + { + "epoch": 2.32, + "learning_rate": 1.7923999972547686e-05, + "loss": 0.3755, + "step": 2628 + }, + { + "epoch": 2.33, + "learning_rate": 1.7922251287188813e-05, + "loss": 0.3902, + "step": 2629 + }, + { + "epoch": 2.33, + "learning_rate": 1.7920501951029255e-05, + "loss": 0.386, + "step": 2630 + }, + { + "epoch": 2.33, + "learning_rate": 1.7918751964212723e-05, + "loss": 0.37, + "step": 2631 + }, + { + "epoch": 2.33, + "learning_rate": 1.7917001326882968e-05, + "loss": 0.3787, + "step": 2632 + }, + { + "epoch": 2.33, + "learning_rate": 1.7915250039183806e-05, + "loss": 0.3893, + "step": 2633 + }, + { + "epoch": 2.33, + "learning_rate": 1.7913498101259098e-05, + "loss": 0.3681, + "step": 2634 + }, + { + "epoch": 2.33, + "learning_rate": 1.7911745513252773e-05, + "loss": 0.3839, + "step": 2635 + }, + { + "epoch": 2.33, + "learning_rate": 1.7909992275308796e-05, + "loss": 0.3974, + "step": 2636 + }, + { + "epoch": 2.33, + "learning_rate": 1.790823838757119e-05, + "loss": 0.37, + "step": 2637 + }, + { + "epoch": 2.33, + "learning_rate": 1.790648385018404e-05, + "loss": 0.3761, + "step": 2638 + }, + { + "epoch": 2.33, + "learning_rate": 1.790472866329148e-05, + "loss": 0.3836, + "step": 2639 + }, + { + "epoch": 2.34, + "learning_rate": 1.790297282703769e-05, + "loss": 0.3816, + "step": 2640 + }, + { + "epoch": 2.34, + "learning_rate": 1.7901216341566908e-05, + "loss": 0.3937, + "step": 2641 + }, + { + "epoch": 2.34, + "learning_rate": 1.7899459207023433e-05, + "loss": 0.3659, + "step": 2642 + }, + { + "epoch": 2.34, + "learning_rate": 1.789770142355161e-05, + "loss": 0.3874, + "step": 2643 + }, + { + "epoch": 2.34, + "learning_rate": 1.7895942991295835e-05, + "loss": 0.3955, + "step": 2644 + }, + { + "epoch": 2.34, + "learning_rate": 1.789418391040056e-05, + "loss": 0.3828, + "step": 2645 + }, + { + "epoch": 2.34, + "learning_rate": 1.7892424181010298e-05, + "loss": 0.3867, + "step": 2646 + }, + { + "epoch": 2.34, + "learning_rate": 1.7890663803269598e-05, + "loss": 0.3746, + "step": 2647 + }, + { + "epoch": 2.34, + "learning_rate": 1.7888902777323077e-05, + "loss": 0.3651, + "step": 2648 + }, + { + "epoch": 2.34, + "learning_rate": 1.7887141103315403e-05, + "loss": 0.3761, + "step": 2649 + }, + { + "epoch": 2.34, + "learning_rate": 1.7885378781391292e-05, + "loss": 0.3624, + "step": 2650 + }, + { + "epoch": 2.35, + "learning_rate": 1.7883615811695512e-05, + "loss": 0.386, + "step": 2651 + }, + { + "epoch": 2.35, + "learning_rate": 1.7881852194372897e-05, + "loss": 0.4025, + "step": 2652 + }, + { + "epoch": 2.35, + "learning_rate": 1.7880087929568322e-05, + "loss": 0.3726, + "step": 2653 + }, + { + "epoch": 2.35, + "learning_rate": 1.7878323017426718e-05, + "loss": 0.3749, + "step": 2654 + }, + { + "epoch": 2.35, + "learning_rate": 1.7876557458093063e-05, + "loss": 0.4027, + "step": 2655 + }, + { + "epoch": 2.35, + "learning_rate": 1.7874791251712407e-05, + "loss": 0.3787, + "step": 2656 + }, + { + "epoch": 2.35, + "learning_rate": 1.7873024398429833e-05, + "loss": 0.3952, + "step": 2657 + }, + { + "epoch": 2.35, + "learning_rate": 1.7871256898390492e-05, + "loss": 0.4026, + "step": 2658 + }, + { + "epoch": 2.35, + "learning_rate": 1.7869488751739575e-05, + "loss": 0.3775, + "step": 2659 + }, + { + "epoch": 2.35, + "learning_rate": 1.7867719958622332e-05, + "loss": 0.3667, + "step": 2660 + }, + { + "epoch": 2.35, + "learning_rate": 1.7865950519184072e-05, + "loss": 0.3767, + "step": 2661 + }, + { + "epoch": 2.35, + "learning_rate": 1.7864180433570148e-05, + "loss": 0.4206, + "step": 2662 + }, + { + "epoch": 2.36, + "learning_rate": 1.7862409701925973e-05, + "loss": 0.3466, + "step": 2663 + }, + { + "epoch": 2.36, + "learning_rate": 1.7860638324397004e-05, + "loss": 0.3874, + "step": 2664 + }, + { + "epoch": 2.36, + "learning_rate": 1.7858866301128764e-05, + "loss": 0.3988, + "step": 2665 + }, + { + "epoch": 2.36, + "learning_rate": 1.7857093632266818e-05, + "loss": 0.3746, + "step": 2666 + }, + { + "epoch": 2.36, + "learning_rate": 1.7855320317956785e-05, + "loss": 0.3774, + "step": 2667 + }, + { + "epoch": 2.36, + "learning_rate": 1.785354635834435e-05, + "loss": 0.3929, + "step": 2668 + }, + { + "epoch": 2.36, + "learning_rate": 1.785177175357523e-05, + "loss": 0.356, + "step": 2669 + }, + { + "epoch": 2.36, + "learning_rate": 1.784999650379521e-05, + "loss": 0.3735, + "step": 2670 + }, + { + "epoch": 2.36, + "learning_rate": 1.7848220609150128e-05, + "loss": 0.3928, + "step": 2671 + }, + { + "epoch": 2.36, + "learning_rate": 1.7846444069785865e-05, + "loss": 0.3854, + "step": 2672 + }, + { + "epoch": 2.36, + "learning_rate": 1.7844666885848367e-05, + "loss": 0.371, + "step": 2673 + }, + { + "epoch": 2.37, + "learning_rate": 1.784288905748362e-05, + "loss": 0.3566, + "step": 2674 + }, + { + "epoch": 2.37, + "learning_rate": 1.7841110584837675e-05, + "loss": 0.3924, + "step": 2675 + }, + { + "epoch": 2.37, + "learning_rate": 1.7839331468056632e-05, + "loss": 0.3772, + "step": 2676 + }, + { + "epoch": 2.37, + "learning_rate": 1.7837551707286635e-05, + "loss": 0.3879, + "step": 2677 + }, + { + "epoch": 2.37, + "learning_rate": 1.7835771302673895e-05, + "loss": 0.367, + "step": 2678 + }, + { + "epoch": 2.37, + "learning_rate": 1.783399025436467e-05, + "loss": 0.4144, + "step": 2679 + }, + { + "epoch": 2.37, + "learning_rate": 1.7832208562505267e-05, + "loss": 0.3906, + "step": 2680 + }, + { + "epoch": 2.37, + "learning_rate": 1.783042622724205e-05, + "loss": 0.3725, + "step": 2681 + }, + { + "epoch": 2.37, + "learning_rate": 1.7828643248721435e-05, + "loss": 0.4007, + "step": 2682 + }, + { + "epoch": 2.37, + "learning_rate": 1.7826859627089894e-05, + "loss": 0.3654, + "step": 2683 + }, + { + "epoch": 2.37, + "learning_rate": 1.7825075362493948e-05, + "loss": 0.3809, + "step": 2684 + }, + { + "epoch": 2.38, + "learning_rate": 1.7823290455080166e-05, + "loss": 0.3696, + "step": 2685 + }, + { + "epoch": 2.38, + "learning_rate": 1.7821504904995178e-05, + "loss": 0.3794, + "step": 2686 + }, + { + "epoch": 2.38, + "learning_rate": 1.781971871238567e-05, + "loss": 0.3854, + "step": 2687 + }, + { + "epoch": 2.38, + "learning_rate": 1.7817931877398366e-05, + "loss": 0.386, + "step": 2688 + }, + { + "epoch": 2.38, + "learning_rate": 1.781614440018006e-05, + "loss": 0.3784, + "step": 2689 + }, + { + "epoch": 2.38, + "learning_rate": 1.7814356280877585e-05, + "loss": 0.3867, + "step": 2690 + }, + { + "epoch": 2.38, + "learning_rate": 1.7812567519637833e-05, + "loss": 0.3727, + "step": 2691 + }, + { + "epoch": 2.38, + "learning_rate": 1.7810778116607748e-05, + "loss": 0.3857, + "step": 2692 + }, + { + "epoch": 2.38, + "learning_rate": 1.7808988071934333e-05, + "loss": 0.3814, + "step": 2693 + }, + { + "epoch": 2.38, + "learning_rate": 1.7807197385764628e-05, + "loss": 0.3765, + "step": 2694 + }, + { + "epoch": 2.38, + "learning_rate": 1.780540605824574e-05, + "loss": 0.3707, + "step": 2695 + }, + { + "epoch": 2.38, + "learning_rate": 1.780361408952482e-05, + "loss": 0.3822, + "step": 2696 + }, + { + "epoch": 2.39, + "learning_rate": 1.780182147974908e-05, + "loss": 0.3643, + "step": 2697 + }, + { + "epoch": 2.39, + "learning_rate": 1.780002822906578e-05, + "loss": 0.3852, + "step": 2698 + }, + { + "epoch": 2.39, + "learning_rate": 1.7798234337622232e-05, + "loss": 0.4121, + "step": 2699 + }, + { + "epoch": 2.39, + "learning_rate": 1.7796439805565797e-05, + "loss": 0.3753, + "step": 2700 + }, + { + "epoch": 2.39, + "learning_rate": 1.7794644633043898e-05, + "loss": 0.3836, + "step": 2701 + }, + { + "epoch": 2.39, + "learning_rate": 1.7792848820204003e-05, + "loss": 0.3993, + "step": 2702 + }, + { + "epoch": 2.39, + "learning_rate": 1.779105236719364e-05, + "loss": 0.3772, + "step": 2703 + }, + { + "epoch": 2.39, + "learning_rate": 1.7789255274160377e-05, + "loss": 0.3868, + "step": 2704 + }, + { + "epoch": 2.39, + "learning_rate": 1.7787457541251852e-05, + "loss": 0.3735, + "step": 2705 + }, + { + "epoch": 2.39, + "learning_rate": 1.7785659168615738e-05, + "loss": 0.3918, + "step": 2706 + }, + { + "epoch": 2.39, + "learning_rate": 1.778386015639977e-05, + "loss": 0.3846, + "step": 2707 + }, + { + "epoch": 2.4, + "learning_rate": 1.778206050475174e-05, + "loss": 0.3752, + "step": 2708 + }, + { + "epoch": 2.4, + "learning_rate": 1.7780260213819475e-05, + "loss": 0.3825, + "step": 2709 + }, + { + "epoch": 2.4, + "learning_rate": 1.7778459283750878e-05, + "loss": 0.3744, + "step": 2710 + }, + { + "epoch": 2.4, + "learning_rate": 1.7776657714693883e-05, + "loss": 0.3824, + "step": 2711 + }, + { + "epoch": 2.4, + "learning_rate": 1.7774855506796497e-05, + "loss": 0.3734, + "step": 2712 + }, + { + "epoch": 2.4, + "learning_rate": 1.777305266020676e-05, + "loss": 0.3939, + "step": 2713 + }, + { + "epoch": 2.4, + "learning_rate": 1.777124917507277e-05, + "loss": 0.3891, + "step": 2714 + }, + { + "epoch": 2.4, + "learning_rate": 1.776944505154269e-05, + "loss": 0.4003, + "step": 2715 + }, + { + "epoch": 2.4, + "learning_rate": 1.7767640289764725e-05, + "loss": 0.3777, + "step": 2716 + }, + { + "epoch": 2.4, + "learning_rate": 1.7765834889887127e-05, + "loss": 0.3945, + "step": 2717 + }, + { + "epoch": 2.4, + "learning_rate": 1.7764028852058212e-05, + "loss": 0.3932, + "step": 2718 + }, + { + "epoch": 2.41, + "learning_rate": 1.776222217642634e-05, + "loss": 0.3885, + "step": 2719 + }, + { + "epoch": 2.41, + "learning_rate": 1.7760414863139924e-05, + "loss": 0.3798, + "step": 2720 + }, + { + "epoch": 2.41, + "learning_rate": 1.7758606912347444e-05, + "loss": 0.384, + "step": 2721 + }, + { + "epoch": 2.41, + "learning_rate": 1.7756798324197406e-05, + "loss": 0.3689, + "step": 2722 + }, + { + "epoch": 2.41, + "learning_rate": 1.7754989098838393e-05, + "loss": 0.373, + "step": 2723 + }, + { + "epoch": 2.41, + "learning_rate": 1.775317923641902e-05, + "loss": 0.3788, + "step": 2724 + }, + { + "epoch": 2.41, + "learning_rate": 1.7751368737087976e-05, + "loss": 0.375, + "step": 2725 + }, + { + "epoch": 2.41, + "learning_rate": 1.7749557600993982e-05, + "loss": 0.373, + "step": 2726 + }, + { + "epoch": 2.41, + "learning_rate": 1.7747745828285827e-05, + "loss": 0.3936, + "step": 2727 + }, + { + "epoch": 2.41, + "learning_rate": 1.774593341911234e-05, + "loss": 0.3781, + "step": 2728 + }, + { + "epoch": 2.41, + "learning_rate": 1.7744120373622408e-05, + "loss": 0.388, + "step": 2729 + }, + { + "epoch": 2.41, + "learning_rate": 1.7742306691964966e-05, + "loss": 0.3995, + "step": 2730 + }, + { + "epoch": 2.42, + "learning_rate": 1.7740492374289018e-05, + "loss": 0.3954, + "step": 2731 + }, + { + "epoch": 2.42, + "learning_rate": 1.7738677420743597e-05, + "loss": 0.3767, + "step": 2732 + }, + { + "epoch": 2.42, + "learning_rate": 1.7736861831477803e-05, + "loss": 0.3746, + "step": 2733 + }, + { + "epoch": 2.42, + "learning_rate": 1.773504560664078e-05, + "loss": 0.4103, + "step": 2734 + }, + { + "epoch": 2.42, + "learning_rate": 1.773322874638173e-05, + "loss": 0.3822, + "step": 2735 + }, + { + "epoch": 2.42, + "learning_rate": 1.7731411250849903e-05, + "loss": 0.398, + "step": 2736 + }, + { + "epoch": 2.42, + "learning_rate": 1.7729593120194607e-05, + "loss": 0.3823, + "step": 2737 + }, + { + "epoch": 2.42, + "learning_rate": 1.77277743545652e-05, + "loss": 0.3887, + "step": 2738 + }, + { + "epoch": 2.42, + "learning_rate": 1.7725954954111085e-05, + "loss": 0.3534, + "step": 2739 + }, + { + "epoch": 2.42, + "learning_rate": 1.772413491898173e-05, + "loss": 0.3771, + "step": 2740 + }, + { + "epoch": 2.42, + "learning_rate": 1.772231424932664e-05, + "loss": 0.3952, + "step": 2741 + }, + { + "epoch": 2.43, + "learning_rate": 1.7720492945295385e-05, + "loss": 0.3883, + "step": 2742 + }, + { + "epoch": 2.43, + "learning_rate": 1.7718671007037588e-05, + "loss": 0.3779, + "step": 2743 + }, + { + "epoch": 2.43, + "learning_rate": 1.7716848434702903e-05, + "loss": 0.3597, + "step": 2744 + }, + { + "epoch": 2.43, + "learning_rate": 1.7715025228441066e-05, + "loss": 0.3867, + "step": 2745 + }, + { + "epoch": 2.43, + "learning_rate": 1.7713201388401843e-05, + "loss": 0.3794, + "step": 2746 + }, + { + "epoch": 2.43, + "learning_rate": 1.771137691473506e-05, + "loss": 0.3699, + "step": 2747 + }, + { + "epoch": 2.43, + "learning_rate": 1.77095518075906e-05, + "loss": 0.3825, + "step": 2748 + }, + { + "epoch": 2.43, + "learning_rate": 1.770772606711839e-05, + "loss": 0.37, + "step": 2749 + }, + { + "epoch": 2.43, + "learning_rate": 1.7705899693468408e-05, + "loss": 0.3751, + "step": 2750 + }, + { + "epoch": 2.43, + "learning_rate": 1.770407268679069e-05, + "loss": 0.3748, + "step": 2751 + }, + { + "epoch": 2.43, + "learning_rate": 1.7702245047235325e-05, + "loss": 0.4001, + "step": 2752 + }, + { + "epoch": 2.44, + "learning_rate": 1.770041677495245e-05, + "loss": 0.3577, + "step": 2753 + }, + { + "epoch": 2.44, + "learning_rate": 1.769858787009225e-05, + "loss": 0.3754, + "step": 2754 + }, + { + "epoch": 2.44, + "learning_rate": 1.769675833280497e-05, + "loss": 0.3759, + "step": 2755 + }, + { + "epoch": 2.44, + "learning_rate": 1.7694928163240903e-05, + "loss": 0.3518, + "step": 2756 + }, + { + "epoch": 2.44, + "learning_rate": 1.7693097361550396e-05, + "loss": 0.3934, + "step": 2757 + }, + { + "epoch": 2.44, + "learning_rate": 1.7691265927883843e-05, + "loss": 0.3664, + "step": 2758 + }, + { + "epoch": 2.44, + "learning_rate": 1.76894338623917e-05, + "loss": 0.3599, + "step": 2759 + }, + { + "epoch": 2.44, + "learning_rate": 1.768760116522446e-05, + "loss": 0.3764, + "step": 2760 + }, + { + "epoch": 2.44, + "learning_rate": 1.7685767836532682e-05, + "loss": 0.3769, + "step": 2761 + }, + { + "epoch": 2.44, + "learning_rate": 1.768393387646697e-05, + "loss": 0.3871, + "step": 2762 + }, + { + "epoch": 2.44, + "learning_rate": 1.768209928517798e-05, + "loss": 0.3685, + "step": 2763 + }, + { + "epoch": 2.45, + "learning_rate": 1.768026406281642e-05, + "loss": 0.3535, + "step": 2764 + }, + { + "epoch": 2.45, + "learning_rate": 1.7678428209533057e-05, + "loss": 0.3786, + "step": 2765 + }, + { + "epoch": 2.45, + "learning_rate": 1.7676591725478696e-05, + "loss": 0.3828, + "step": 2766 + }, + { + "epoch": 2.45, + "learning_rate": 1.7674754610804203e-05, + "loss": 0.3663, + "step": 2767 + }, + { + "epoch": 2.45, + "learning_rate": 1.7672916865660498e-05, + "loss": 0.3596, + "step": 2768 + }, + { + "epoch": 2.45, + "learning_rate": 1.7671078490198543e-05, + "loss": 0.3627, + "step": 2769 + }, + { + "epoch": 2.45, + "learning_rate": 1.7669239484569362e-05, + "loss": 0.3836, + "step": 2770 + }, + { + "epoch": 2.45, + "learning_rate": 1.7667399848924023e-05, + "loss": 0.3792, + "step": 2771 + }, + { + "epoch": 2.45, + "learning_rate": 1.766555958341365e-05, + "loss": 0.3708, + "step": 2772 + }, + { + "epoch": 2.45, + "learning_rate": 1.7663718688189425e-05, + "loss": 0.3865, + "step": 2773 + }, + { + "epoch": 2.45, + "learning_rate": 1.7661877163402564e-05, + "loss": 0.3654, + "step": 2774 + }, + { + "epoch": 2.45, + "learning_rate": 1.7660035009204354e-05, + "loss": 0.3643, + "step": 2775 + }, + { + "epoch": 2.46, + "learning_rate": 1.7658192225746123e-05, + "loss": 0.3818, + "step": 2776 + }, + { + "epoch": 2.46, + "learning_rate": 1.7656348813179246e-05, + "loss": 0.3772, + "step": 2777 + }, + { + "epoch": 2.46, + "learning_rate": 1.7654504771655166e-05, + "loss": 0.3905, + "step": 2778 + }, + { + "epoch": 2.46, + "learning_rate": 1.765266010132536e-05, + "loss": 0.3817, + "step": 2779 + }, + { + "epoch": 2.46, + "learning_rate": 1.7650814802341374e-05, + "loss": 0.3899, + "step": 2780 + }, + { + "epoch": 2.46, + "learning_rate": 1.7648968874854787e-05, + "loss": 0.3659, + "step": 2781 + }, + { + "epoch": 2.46, + "learning_rate": 1.7647122319017246e-05, + "loss": 0.3793, + "step": 2782 + }, + { + "epoch": 2.46, + "learning_rate": 1.764527513498044e-05, + "loss": 0.3629, + "step": 2783 + }, + { + "epoch": 2.46, + "learning_rate": 1.764342732289611e-05, + "loss": 0.356, + "step": 2784 + }, + { + "epoch": 2.46, + "learning_rate": 1.7641578882916052e-05, + "loss": 0.3691, + "step": 2785 + }, + { + "epoch": 2.46, + "learning_rate": 1.7639729815192117e-05, + "loss": 0.3779, + "step": 2786 + }, + { + "epoch": 2.47, + "learning_rate": 1.76378801198762e-05, + "loss": 0.379, + "step": 2787 + }, + { + "epoch": 2.47, + "learning_rate": 1.763602979712025e-05, + "loss": 0.3904, + "step": 2788 + }, + { + "epoch": 2.47, + "learning_rate": 1.763417884707627e-05, + "loss": 0.3557, + "step": 2789 + }, + { + "epoch": 2.47, + "learning_rate": 1.763232726989631e-05, + "loss": 0.3644, + "step": 2790 + }, + { + "epoch": 2.47, + "learning_rate": 1.7630475065732472e-05, + "loss": 0.3507, + "step": 2791 + }, + { + "epoch": 2.47, + "learning_rate": 1.762862223473692e-05, + "loss": 0.3776, + "step": 2792 + }, + { + "epoch": 2.47, + "learning_rate": 1.7626768777061854e-05, + "loss": 0.3625, + "step": 2793 + }, + { + "epoch": 2.47, + "learning_rate": 1.7624914692859533e-05, + "loss": 0.4117, + "step": 2794 + }, + { + "epoch": 2.47, + "learning_rate": 1.7623059982282274e-05, + "loss": 0.3759, + "step": 2795 + }, + { + "epoch": 2.47, + "learning_rate": 1.762120464548243e-05, + "loss": 0.384, + "step": 2796 + }, + { + "epoch": 2.47, + "learning_rate": 1.761934868261242e-05, + "loss": 0.4271, + "step": 2797 + }, + { + "epoch": 2.48, + "learning_rate": 1.7617492093824705e-05, + "loss": 0.3994, + "step": 2798 + }, + { + "epoch": 2.48, + "learning_rate": 1.7615634879271805e-05, + "loss": 0.3954, + "step": 2799 + }, + { + "epoch": 2.48, + "learning_rate": 1.7613777039106282e-05, + "loss": 0.3815, + "step": 2800 + }, + { + "epoch": 2.48, + "learning_rate": 1.7611918573480756e-05, + "loss": 0.3861, + "step": 2801 + }, + { + "epoch": 2.48, + "learning_rate": 1.7610059482547898e-05, + "loss": 0.3818, + "step": 2802 + }, + { + "epoch": 2.48, + "learning_rate": 1.7608199766460435e-05, + "loss": 0.3816, + "step": 2803 + }, + { + "epoch": 2.48, + "learning_rate": 1.7606339425371128e-05, + "loss": 0.3902, + "step": 2804 + }, + { + "epoch": 2.48, + "learning_rate": 1.7604478459432812e-05, + "loss": 0.3773, + "step": 2805 + }, + { + "epoch": 2.48, + "learning_rate": 1.7602616868798357e-05, + "loss": 0.38, + "step": 2806 + }, + { + "epoch": 2.48, + "learning_rate": 1.7600754653620692e-05, + "loss": 0.3766, + "step": 2807 + }, + { + "epoch": 2.48, + "learning_rate": 1.759889181405279e-05, + "loss": 0.3608, + "step": 2808 + }, + { + "epoch": 2.48, + "learning_rate": 1.7597028350247688e-05, + "loss": 0.4058, + "step": 2809 + }, + { + "epoch": 2.49, + "learning_rate": 1.7595164262358463e-05, + "loss": 0.4005, + "step": 2810 + }, + { + "epoch": 2.49, + "learning_rate": 1.7593299550538246e-05, + "loss": 0.3743, + "step": 2811 + }, + { + "epoch": 2.49, + "learning_rate": 1.7591434214940223e-05, + "loss": 0.3855, + "step": 2812 + }, + { + "epoch": 2.49, + "learning_rate": 1.7589568255717625e-05, + "loss": 0.4078, + "step": 2813 + }, + { + "epoch": 2.49, + "learning_rate": 1.758770167302374e-05, + "loss": 0.3671, + "step": 2814 + }, + { + "epoch": 2.49, + "learning_rate": 1.7585834467011903e-05, + "loss": 0.3811, + "step": 2815 + }, + { + "epoch": 2.49, + "learning_rate": 1.7583966637835505e-05, + "loss": 0.3669, + "step": 2816 + }, + { + "epoch": 2.49, + "learning_rate": 1.7582098185647982e-05, + "loss": 0.3753, + "step": 2817 + }, + { + "epoch": 2.49, + "learning_rate": 1.7580229110602825e-05, + "loss": 0.3852, + "step": 2818 + }, + { + "epoch": 2.49, + "learning_rate": 1.7578359412853578e-05, + "loss": 0.3686, + "step": 2819 + }, + { + "epoch": 2.49, + "learning_rate": 1.7576489092553833e-05, + "loss": 0.3939, + "step": 2820 + }, + { + "epoch": 2.5, + "learning_rate": 1.7574618149857234e-05, + "loss": 0.3982, + "step": 2821 + }, + { + "epoch": 2.5, + "learning_rate": 1.757274658491747e-05, + "loss": 0.4086, + "step": 2822 + }, + { + "epoch": 2.5, + "learning_rate": 1.7570874397888303e-05, + "loss": 0.369, + "step": 2823 + }, + { + "epoch": 2.5, + "learning_rate": 1.7569001588923512e-05, + "loss": 0.3746, + "step": 2824 + }, + { + "epoch": 2.5, + "learning_rate": 1.7567128158176955e-05, + "loss": 0.3734, + "step": 2825 + }, + { + "epoch": 2.5, + "learning_rate": 1.756525410580253e-05, + "loss": 0.3765, + "step": 2826 + }, + { + "epoch": 2.5, + "learning_rate": 1.7563379431954187e-05, + "loss": 0.381, + "step": 2827 + }, + { + "epoch": 2.5, + "learning_rate": 1.7561504136785923e-05, + "loss": 0.378, + "step": 2828 + }, + { + "epoch": 2.5, + "learning_rate": 1.75596282204518e-05, + "loss": 0.3969, + "step": 2829 + }, + { + "epoch": 2.5, + "learning_rate": 1.7557751683105918e-05, + "loss": 0.3926, + "step": 2830 + }, + { + "epoch": 2.5, + "learning_rate": 1.755587452490243e-05, + "loss": 0.3695, + "step": 2831 + }, + { + "epoch": 2.51, + "learning_rate": 1.7553996745995538e-05, + "loss": 0.3911, + "step": 2832 + }, + { + "epoch": 2.51, + "learning_rate": 1.7552118346539505e-05, + "loss": 0.3886, + "step": 2833 + }, + { + "epoch": 2.51, + "learning_rate": 1.7550239326688638e-05, + "loss": 0.3755, + "step": 2834 + }, + { + "epoch": 2.51, + "learning_rate": 1.7548359686597295e-05, + "loss": 0.3586, + "step": 2835 + }, + { + "epoch": 2.51, + "learning_rate": 1.754647942641988e-05, + "loss": 0.3586, + "step": 2836 + }, + { + "epoch": 2.51, + "learning_rate": 1.7544598546310863e-05, + "loss": 0.4054, + "step": 2837 + }, + { + "epoch": 2.51, + "learning_rate": 1.7542717046424748e-05, + "loss": 0.3778, + "step": 2838 + }, + { + "epoch": 2.51, + "learning_rate": 1.7540834926916095e-05, + "loss": 0.395, + "step": 2839 + }, + { + "epoch": 2.51, + "learning_rate": 1.753895218793953e-05, + "loss": 0.3474, + "step": 2840 + }, + { + "epoch": 2.51, + "learning_rate": 1.7537068829649704e-05, + "loss": 0.3547, + "step": 2841 + }, + { + "epoch": 2.51, + "learning_rate": 1.7535184852201336e-05, + "loss": 0.3765, + "step": 2842 + }, + { + "epoch": 2.51, + "learning_rate": 1.7533300255749198e-05, + "loss": 0.3602, + "step": 2843 + }, + { + "epoch": 2.52, + "learning_rate": 1.7531415040448097e-05, + "loss": 0.3661, + "step": 2844 + }, + { + "epoch": 2.52, + "learning_rate": 1.7529529206452905e-05, + "loss": 0.3713, + "step": 2845 + }, + { + "epoch": 2.52, + "learning_rate": 1.7527642753918544e-05, + "loss": 0.3547, + "step": 2846 + }, + { + "epoch": 2.52, + "learning_rate": 1.7525755682999977e-05, + "loss": 0.376, + "step": 2847 + }, + { + "epoch": 2.52, + "learning_rate": 1.7523867993852227e-05, + "loss": 0.3825, + "step": 2848 + }, + { + "epoch": 2.52, + "learning_rate": 1.752197968663036e-05, + "loss": 0.3745, + "step": 2849 + }, + { + "epoch": 2.52, + "learning_rate": 1.7520090761489505e-05, + "loss": 0.3744, + "step": 2850 + }, + { + "epoch": 2.52, + "learning_rate": 1.7518201218584835e-05, + "loss": 0.3777, + "step": 2851 + }, + { + "epoch": 2.52, + "learning_rate": 1.7516311058071563e-05, + "loss": 0.3749, + "step": 2852 + }, + { + "epoch": 2.52, + "learning_rate": 1.751442028010497e-05, + "loss": 0.4035, + "step": 2853 + }, + { + "epoch": 2.52, + "learning_rate": 1.751252888484038e-05, + "loss": 0.3711, + "step": 2854 + }, + { + "epoch": 2.53, + "learning_rate": 1.7510636872433168e-05, + "loss": 0.3665, + "step": 2855 + }, + { + "epoch": 2.53, + "learning_rate": 1.7508744243038758e-05, + "loss": 0.3696, + "step": 2856 + }, + { + "epoch": 2.53, + "learning_rate": 1.750685099681263e-05, + "loss": 0.3875, + "step": 2857 + }, + { + "epoch": 2.53, + "learning_rate": 1.7504957133910307e-05, + "loss": 0.3636, + "step": 2858 + }, + { + "epoch": 2.53, + "learning_rate": 1.750306265448737e-05, + "loss": 0.3769, + "step": 2859 + }, + { + "epoch": 2.53, + "learning_rate": 1.7501167558699446e-05, + "loss": 0.3816, + "step": 2860 + }, + { + "epoch": 2.53, + "learning_rate": 1.7499271846702216e-05, + "loss": 0.3681, + "step": 2861 + }, + { + "epoch": 2.53, + "learning_rate": 1.7497375518651407e-05, + "loss": 0.3868, + "step": 2862 + }, + { + "epoch": 2.53, + "learning_rate": 1.7495478574702804e-05, + "loss": 0.3835, + "step": 2863 + }, + { + "epoch": 2.53, + "learning_rate": 1.7493581015012232e-05, + "loss": 0.3879, + "step": 2864 + }, + { + "epoch": 2.53, + "learning_rate": 1.7491682839735573e-05, + "loss": 0.3886, + "step": 2865 + }, + { + "epoch": 2.54, + "learning_rate": 1.7489784049028767e-05, + "loss": 0.3825, + "step": 2866 + }, + { + "epoch": 2.54, + "learning_rate": 1.748788464304779e-05, + "loss": 0.3829, + "step": 2867 + }, + { + "epoch": 2.54, + "learning_rate": 1.7485984621948678e-05, + "loss": 0.3515, + "step": 2868 + }, + { + "epoch": 2.54, + "learning_rate": 1.748408398588751e-05, + "loss": 0.3557, + "step": 2869 + }, + { + "epoch": 2.54, + "learning_rate": 1.7482182735020427e-05, + "loss": 0.3698, + "step": 2870 + }, + { + "epoch": 2.54, + "learning_rate": 1.7480280869503608e-05, + "loss": 0.3745, + "step": 2871 + }, + { + "epoch": 2.54, + "learning_rate": 1.747837838949329e-05, + "loss": 0.3627, + "step": 2872 + }, + { + "epoch": 2.54, + "learning_rate": 1.7476475295145764e-05, + "loss": 0.3916, + "step": 2873 + }, + { + "epoch": 2.54, + "learning_rate": 1.7474571586617358e-05, + "loss": 0.3839, + "step": 2874 + }, + { + "epoch": 2.54, + "learning_rate": 1.7472667264064465e-05, + "loss": 0.3709, + "step": 2875 + }, + { + "epoch": 2.54, + "learning_rate": 1.7470762327643523e-05, + "loss": 0.3886, + "step": 2876 + }, + { + "epoch": 2.55, + "learning_rate": 1.7468856777511008e-05, + "loss": 0.411, + "step": 2877 + }, + { + "epoch": 2.55, + "learning_rate": 1.7466950613823476e-05, + "loss": 0.3747, + "step": 2878 + }, + { + "epoch": 2.55, + "learning_rate": 1.74650438367375e-05, + "loss": 0.3922, + "step": 2879 + }, + { + "epoch": 2.55, + "learning_rate": 1.7463136446409725e-05, + "loss": 0.3775, + "step": 2880 + }, + { + "epoch": 2.55, + "learning_rate": 1.7461228442996844e-05, + "loss": 0.4111, + "step": 2881 + }, + { + "epoch": 2.55, + "learning_rate": 1.7459319826655584e-05, + "loss": 0.3913, + "step": 2882 + }, + { + "epoch": 2.55, + "learning_rate": 1.745741059754275e-05, + "loss": 0.3713, + "step": 2883 + }, + { + "epoch": 2.55, + "learning_rate": 1.7455500755815172e-05, + "loss": 0.3714, + "step": 2884 + }, + { + "epoch": 2.55, + "learning_rate": 1.7453590301629748e-05, + "loss": 0.3757, + "step": 2885 + }, + { + "epoch": 2.55, + "learning_rate": 1.7451679235143414e-05, + "loss": 0.3924, + "step": 2886 + }, + { + "epoch": 2.55, + "learning_rate": 1.744976755651316e-05, + "loss": 0.3646, + "step": 2887 + }, + { + "epoch": 2.55, + "learning_rate": 1.744785526589603e-05, + "loss": 0.3873, + "step": 2888 + }, + { + "epoch": 2.56, + "learning_rate": 1.7445942363449112e-05, + "loss": 0.4006, + "step": 2889 + }, + { + "epoch": 2.56, + "learning_rate": 1.7444028849329556e-05, + "loss": 0.3655, + "step": 2890 + }, + { + "epoch": 2.56, + "learning_rate": 1.7442114723694547e-05, + "loss": 0.3817, + "step": 2891 + }, + { + "epoch": 2.56, + "learning_rate": 1.7440199986701328e-05, + "loss": 0.3903, + "step": 2892 + }, + { + "epoch": 2.56, + "learning_rate": 1.7438284638507196e-05, + "loss": 0.399, + "step": 2893 + }, + { + "epoch": 2.56, + "learning_rate": 1.743636867926949e-05, + "loss": 0.349, + "step": 2894 + }, + { + "epoch": 2.56, + "learning_rate": 1.743445210914561e-05, + "loss": 0.3796, + "step": 2895 + }, + { + "epoch": 2.56, + "learning_rate": 1.7432534928292984e-05, + "loss": 0.3712, + "step": 2896 + }, + { + "epoch": 2.56, + "learning_rate": 1.7430617136869122e-05, + "loss": 0.3683, + "step": 2897 + }, + { + "epoch": 2.56, + "learning_rate": 1.742869873503156e-05, + "loss": 0.3706, + "step": 2898 + }, + { + "epoch": 2.56, + "learning_rate": 1.742677972293789e-05, + "loss": 0.3787, + "step": 2899 + }, + { + "epoch": 2.57, + "learning_rate": 1.742486010074576e-05, + "loss": 0.4039, + "step": 2900 + }, + { + "epoch": 2.57, + "learning_rate": 1.7422939868612862e-05, + "loss": 0.411, + "step": 2901 + }, + { + "epoch": 2.57, + "learning_rate": 1.742101902669694e-05, + "loss": 0.3735, + "step": 2902 + }, + { + "epoch": 2.57, + "learning_rate": 1.741909757515579e-05, + "loss": 0.377, + "step": 2903 + }, + { + "epoch": 2.57, + "learning_rate": 1.7417175514147256e-05, + "loss": 0.3712, + "step": 2904 + }, + { + "epoch": 2.57, + "learning_rate": 1.741525284382923e-05, + "loss": 0.3677, + "step": 2905 + }, + { + "epoch": 2.57, + "learning_rate": 1.7413329564359656e-05, + "loss": 0.3649, + "step": 2906 + }, + { + "epoch": 2.57, + "learning_rate": 1.741140567589653e-05, + "loss": 0.3813, + "step": 2907 + }, + { + "epoch": 2.57, + "learning_rate": 1.74094811785979e-05, + "loss": 0.3458, + "step": 2908 + }, + { + "epoch": 2.57, + "learning_rate": 1.7407556072621853e-05, + "loss": 0.3861, + "step": 2909 + }, + { + "epoch": 2.57, + "learning_rate": 1.740563035812654e-05, + "loss": 0.3873, + "step": 2910 + }, + { + "epoch": 2.58, + "learning_rate": 1.740370403527015e-05, + "loss": 0.3735, + "step": 2911 + }, + { + "epoch": 2.58, + "learning_rate": 1.740177710421093e-05, + "loss": 0.3735, + "step": 2912 + }, + { + "epoch": 2.58, + "learning_rate": 1.7399849565107182e-05, + "loss": 0.3774, + "step": 2913 + }, + { + "epoch": 2.58, + "learning_rate": 1.7397921418117237e-05, + "loss": 0.3754, + "step": 2914 + }, + { + "epoch": 2.58, + "learning_rate": 1.73959926633995e-05, + "loss": 0.3846, + "step": 2915 + }, + { + "epoch": 2.58, + "learning_rate": 1.7394063301112405e-05, + "loss": 0.3809, + "step": 2916 + }, + { + "epoch": 2.58, + "learning_rate": 1.7392133331414457e-05, + "loss": 0.407, + "step": 2917 + }, + { + "epoch": 2.58, + "learning_rate": 1.7390202754464193e-05, + "loss": 0.3774, + "step": 2918 + }, + { + "epoch": 2.58, + "learning_rate": 1.7388271570420205e-05, + "loss": 0.3767, + "step": 2919 + }, + { + "epoch": 2.58, + "learning_rate": 1.7386339779441144e-05, + "loss": 0.3793, + "step": 2920 + }, + { + "epoch": 2.58, + "learning_rate": 1.73844073816857e-05, + "loss": 0.3798, + "step": 2921 + }, + { + "epoch": 2.58, + "learning_rate": 1.7382474377312616e-05, + "loss": 0.3815, + "step": 2922 + }, + { + "epoch": 2.59, + "learning_rate": 1.7380540766480687e-05, + "loss": 0.3857, + "step": 2923 + }, + { + "epoch": 2.59, + "learning_rate": 1.7378606549348754e-05, + "loss": 0.3779, + "step": 2924 + }, + { + "epoch": 2.59, + "learning_rate": 1.737667172607571e-05, + "loss": 0.3485, + "step": 2925 + }, + { + "epoch": 2.59, + "learning_rate": 1.7374736296820504e-05, + "loss": 0.3673, + "step": 2926 + }, + { + "epoch": 2.59, + "learning_rate": 1.7372800261742116e-05, + "loss": 0.388, + "step": 2927 + }, + { + "epoch": 2.59, + "learning_rate": 1.7370863620999602e-05, + "loss": 0.3836, + "step": 2928 + }, + { + "epoch": 2.59, + "learning_rate": 1.736892637475204e-05, + "loss": 0.3388, + "step": 2929 + }, + { + "epoch": 2.59, + "learning_rate": 1.7366988523158586e-05, + "loss": 0.375, + "step": 2930 + }, + { + "epoch": 2.59, + "learning_rate": 1.7365050066378422e-05, + "loss": 0.3888, + "step": 2931 + }, + { + "epoch": 2.59, + "learning_rate": 1.7363111004570793e-05, + "loss": 0.3635, + "step": 2932 + }, + { + "epoch": 2.59, + "learning_rate": 1.7361171337894988e-05, + "loss": 0.3969, + "step": 2933 + }, + { + "epoch": 2.6, + "learning_rate": 1.735923106651035e-05, + "loss": 0.3859, + "step": 2934 + }, + { + "epoch": 2.6, + "learning_rate": 1.7357290190576267e-05, + "loss": 0.3597, + "step": 2935 + }, + { + "epoch": 2.6, + "learning_rate": 1.735534871025218e-05, + "loss": 0.3727, + "step": 2936 + }, + { + "epoch": 2.6, + "learning_rate": 1.7353406625697582e-05, + "loss": 0.3887, + "step": 2937 + }, + { + "epoch": 2.6, + "learning_rate": 1.7351463937072008e-05, + "loss": 0.3615, + "step": 2938 + }, + { + "epoch": 2.6, + "learning_rate": 1.7349520644535042e-05, + "loss": 0.3916, + "step": 2939 + }, + { + "epoch": 2.6, + "learning_rate": 1.7347576748246335e-05, + "loss": 0.3902, + "step": 2940 + }, + { + "epoch": 2.6, + "learning_rate": 1.7345632248365564e-05, + "loss": 0.3817, + "step": 2941 + }, + { + "epoch": 2.6, + "learning_rate": 1.734368714505247e-05, + "loss": 0.3686, + "step": 2942 + }, + { + "epoch": 2.6, + "learning_rate": 1.7341741438466845e-05, + "loss": 0.3756, + "step": 2943 + }, + { + "epoch": 2.6, + "learning_rate": 1.7339795128768516e-05, + "loss": 0.373, + "step": 2944 + }, + { + "epoch": 2.61, + "learning_rate": 1.733784821611738e-05, + "loss": 0.3772, + "step": 2945 + }, + { + "epoch": 2.61, + "learning_rate": 1.7335900700673363e-05, + "loss": 0.3573, + "step": 2946 + }, + { + "epoch": 2.61, + "learning_rate": 1.7333952582596463e-05, + "loss": 0.3954, + "step": 2947 + }, + { + "epoch": 2.61, + "learning_rate": 1.7332003862046702e-05, + "loss": 0.3714, + "step": 2948 + }, + { + "epoch": 2.61, + "learning_rate": 1.7330054539184172e-05, + "loss": 0.3651, + "step": 2949 + }, + { + "epoch": 2.61, + "learning_rate": 1.7328104614169003e-05, + "loss": 0.3897, + "step": 2950 + }, + { + "epoch": 2.61, + "learning_rate": 1.732615408716138e-05, + "loss": 0.3984, + "step": 2951 + }, + { + "epoch": 2.61, + "learning_rate": 1.7324202958321538e-05, + "loss": 0.394, + "step": 2952 + }, + { + "epoch": 2.61, + "learning_rate": 1.7322251227809753e-05, + "loss": 0.359, + "step": 2953 + }, + { + "epoch": 2.61, + "learning_rate": 1.7320298895786363e-05, + "loss": 0.3622, + "step": 2954 + }, + { + "epoch": 2.61, + "learning_rate": 1.7318345962411743e-05, + "loss": 0.3915, + "step": 2955 + }, + { + "epoch": 2.61, + "learning_rate": 1.7316392427846334e-05, + "loss": 0.3846, + "step": 2956 + }, + { + "epoch": 2.62, + "learning_rate": 1.7314438292250604e-05, + "loss": 0.3821, + "step": 2957 + }, + { + "epoch": 2.62, + "learning_rate": 1.7312483555785087e-05, + "loss": 0.3889, + "step": 2958 + }, + { + "epoch": 2.62, + "learning_rate": 1.7310528218610364e-05, + "loss": 0.4013, + "step": 2959 + }, + { + "epoch": 2.62, + "learning_rate": 1.7308572280887058e-05, + "loss": 0.3615, + "step": 2960 + }, + { + "epoch": 2.62, + "learning_rate": 1.730661574277585e-05, + "loss": 0.3855, + "step": 2961 + }, + { + "epoch": 2.62, + "learning_rate": 1.7304658604437465e-05, + "loss": 0.3746, + "step": 2962 + }, + { + "epoch": 2.62, + "learning_rate": 1.730270086603268e-05, + "loss": 0.3674, + "step": 2963 + }, + { + "epoch": 2.62, + "learning_rate": 1.730074252772232e-05, + "loss": 0.4004, + "step": 2964 + }, + { + "epoch": 2.62, + "learning_rate": 1.7298783589667256e-05, + "loss": 0.3821, + "step": 2965 + }, + { + "epoch": 2.62, + "learning_rate": 1.7296824052028415e-05, + "loss": 0.3479, + "step": 2966 + }, + { + "epoch": 2.62, + "learning_rate": 1.7294863914966773e-05, + "loss": 0.3882, + "step": 2967 + }, + { + "epoch": 2.63, + "learning_rate": 1.7292903178643348e-05, + "loss": 0.3661, + "step": 2968 + }, + { + "epoch": 2.63, + "learning_rate": 1.7290941843219208e-05, + "loss": 0.376, + "step": 2969 + }, + { + "epoch": 2.63, + "learning_rate": 1.7288979908855482e-05, + "loss": 0.3755, + "step": 2970 + }, + { + "epoch": 2.63, + "learning_rate": 1.7287017375713335e-05, + "loss": 0.3724, + "step": 2971 + }, + { + "epoch": 2.63, + "learning_rate": 1.728505424395399e-05, + "loss": 0.3587, + "step": 2972 + }, + { + "epoch": 2.63, + "learning_rate": 1.7283090513738706e-05, + "loss": 0.4097, + "step": 2973 + }, + { + "epoch": 2.63, + "learning_rate": 1.728112618522881e-05, + "loss": 0.3889, + "step": 2974 + }, + { + "epoch": 2.63, + "learning_rate": 1.7279161258585666e-05, + "loss": 0.3782, + "step": 2975 + }, + { + "epoch": 2.63, + "learning_rate": 1.7277195733970685e-05, + "loss": 0.3845, + "step": 2976 + }, + { + "epoch": 2.63, + "learning_rate": 1.727522961154534e-05, + "loss": 0.3744, + "step": 2977 + }, + { + "epoch": 2.63, + "learning_rate": 1.727326289147114e-05, + "loss": 0.4003, + "step": 2978 + }, + { + "epoch": 2.64, + "learning_rate": 1.7271295573909645e-05, + "loss": 0.3546, + "step": 2979 + }, + { + "epoch": 2.64, + "learning_rate": 1.7269327659022473e-05, + "loss": 0.3949, + "step": 2980 + }, + { + "epoch": 2.64, + "learning_rate": 1.7267359146971287e-05, + "loss": 0.3629, + "step": 2981 + }, + { + "epoch": 2.64, + "learning_rate": 1.7265390037917787e-05, + "loss": 0.3673, + "step": 2982 + }, + { + "epoch": 2.64, + "learning_rate": 1.726342033202374e-05, + "loss": 0.3935, + "step": 2983 + }, + { + "epoch": 2.64, + "learning_rate": 1.726145002945095e-05, + "loss": 0.3835, + "step": 2984 + }, + { + "epoch": 2.64, + "learning_rate": 1.725947913036128e-05, + "loss": 0.3776, + "step": 2985 + }, + { + "epoch": 2.64, + "learning_rate": 1.725750763491663e-05, + "loss": 0.3766, + "step": 2986 + }, + { + "epoch": 2.64, + "learning_rate": 1.7255535543278964e-05, + "loss": 0.3672, + "step": 2987 + }, + { + "epoch": 2.64, + "learning_rate": 1.7253562855610274e-05, + "loss": 0.3716, + "step": 2988 + }, + { + "epoch": 2.64, + "learning_rate": 1.7251589572072625e-05, + "loss": 0.3831, + "step": 2989 + }, + { + "epoch": 2.64, + "learning_rate": 1.724961569282811e-05, + "loss": 0.3854, + "step": 2990 + }, + { + "epoch": 2.65, + "learning_rate": 1.7247641218038887e-05, + "loss": 0.414, + "step": 2991 + }, + { + "epoch": 2.65, + "learning_rate": 1.724566614786716e-05, + "loss": 0.368, + "step": 2992 + }, + { + "epoch": 2.65, + "learning_rate": 1.7243690482475162e-05, + "loss": 0.3674, + "step": 2993 + }, + { + "epoch": 2.65, + "learning_rate": 1.72417142220252e-05, + "loss": 0.3667, + "step": 2994 + }, + { + "epoch": 2.65, + "learning_rate": 1.7239737366679626e-05, + "loss": 0.4093, + "step": 2995 + }, + { + "epoch": 2.65, + "learning_rate": 1.7237759916600828e-05, + "loss": 0.3991, + "step": 2996 + }, + { + "epoch": 2.65, + "learning_rate": 1.723578187195125e-05, + "loss": 0.3722, + "step": 2997 + }, + { + "epoch": 2.65, + "learning_rate": 1.7233803232893392e-05, + "loss": 0.3921, + "step": 2998 + }, + { + "epoch": 2.65, + "learning_rate": 1.7231823999589794e-05, + "loss": 0.3658, + "step": 2999 + }, + { + "epoch": 2.65, + "learning_rate": 1.722984417220304e-05, + "loss": 0.3758, + "step": 3000 + }, + { + "epoch": 2.65, + "learning_rate": 1.722786375089578e-05, + "loss": 0.3858, + "step": 3001 + }, + { + "epoch": 2.66, + "learning_rate": 1.7225882735830696e-05, + "loss": 0.3761, + "step": 3002 + }, + { + "epoch": 2.66, + "learning_rate": 1.7223901127170527e-05, + "loss": 0.3707, + "step": 3003 + }, + { + "epoch": 2.66, + "learning_rate": 1.722191892507806e-05, + "loss": 0.3774, + "step": 3004 + }, + { + "epoch": 2.66, + "learning_rate": 1.7219936129716126e-05, + "loss": 0.3892, + "step": 3005 + }, + { + "epoch": 2.66, + "learning_rate": 1.7217952741247615e-05, + "loss": 0.3608, + "step": 3006 + }, + { + "epoch": 2.66, + "learning_rate": 1.7215968759835454e-05, + "loss": 0.388, + "step": 3007 + }, + { + "epoch": 2.66, + "learning_rate": 1.7213984185642623e-05, + "loss": 0.3978, + "step": 3008 + }, + { + "epoch": 2.66, + "learning_rate": 1.7211999018832156e-05, + "loss": 0.3661, + "step": 3009 + }, + { + "epoch": 2.66, + "learning_rate": 1.7210013259567133e-05, + "loss": 0.3705, + "step": 3010 + }, + { + "epoch": 2.66, + "learning_rate": 1.7208026908010676e-05, + "loss": 0.376, + "step": 3011 + }, + { + "epoch": 2.66, + "learning_rate": 1.720603996432596e-05, + "loss": 0.3932, + "step": 3012 + }, + { + "epoch": 2.67, + "learning_rate": 1.7204052428676218e-05, + "loss": 0.3828, + "step": 3013 + }, + { + "epoch": 2.67, + "learning_rate": 1.7202064301224714e-05, + "loss": 0.3608, + "step": 3014 + }, + { + "epoch": 2.67, + "learning_rate": 1.720007558213477e-05, + "loss": 0.3718, + "step": 3015 + }, + { + "epoch": 2.67, + "learning_rate": 1.7198086271569763e-05, + "loss": 0.3799, + "step": 3016 + }, + { + "epoch": 2.67, + "learning_rate": 1.7196096369693102e-05, + "loss": 0.3592, + "step": 3017 + }, + { + "epoch": 2.67, + "learning_rate": 1.7194105876668264e-05, + "loss": 0.3582, + "step": 3018 + }, + { + "epoch": 2.67, + "learning_rate": 1.719211479265876e-05, + "loss": 0.3896, + "step": 3019 + }, + { + "epoch": 2.67, + "learning_rate": 1.7190123117828154e-05, + "loss": 0.3688, + "step": 3020 + }, + { + "epoch": 2.67, + "learning_rate": 1.718813085234006e-05, + "loss": 0.3938, + "step": 3021 + }, + { + "epoch": 2.67, + "learning_rate": 1.718613799635814e-05, + "loss": 0.3705, + "step": 3022 + }, + { + "epoch": 2.67, + "learning_rate": 1.7184144550046107e-05, + "loss": 0.3655, + "step": 3023 + }, + { + "epoch": 2.68, + "learning_rate": 1.7182150513567714e-05, + "loss": 0.3824, + "step": 3024 + }, + { + "epoch": 2.68, + "learning_rate": 1.7180155887086773e-05, + "loss": 0.3424, + "step": 3025 + }, + { + "epoch": 2.68, + "learning_rate": 1.717816067076713e-05, + "loss": 0.3811, + "step": 3026 + }, + { + "epoch": 2.68, + "learning_rate": 1.7176164864772702e-05, + "loss": 0.3638, + "step": 3027 + }, + { + "epoch": 2.68, + "learning_rate": 1.7174168469267435e-05, + "loss": 0.3915, + "step": 3028 + }, + { + "epoch": 2.68, + "learning_rate": 1.717217148441533e-05, + "loss": 0.3855, + "step": 3029 + }, + { + "epoch": 2.68, + "learning_rate": 1.7170173910380434e-05, + "loss": 0.3542, + "step": 3030 + }, + { + "epoch": 2.68, + "learning_rate": 1.7168175747326847e-05, + "loss": 0.3619, + "step": 3031 + }, + { + "epoch": 2.68, + "learning_rate": 1.7166176995418713e-05, + "loss": 0.3775, + "step": 3032 + }, + { + "epoch": 2.68, + "learning_rate": 1.716417765482023e-05, + "loss": 0.3913, + "step": 3033 + }, + { + "epoch": 2.68, + "learning_rate": 1.716217772569564e-05, + "loss": 0.3694, + "step": 3034 + }, + { + "epoch": 2.68, + "learning_rate": 1.716017720820923e-05, + "loss": 0.3762, + "step": 3035 + }, + { + "epoch": 2.69, + "learning_rate": 1.7158176102525344e-05, + "loss": 0.3773, + "step": 3036 + }, + { + "epoch": 2.69, + "learning_rate": 1.715617440880837e-05, + "loss": 0.4029, + "step": 3037 + }, + { + "epoch": 2.69, + "learning_rate": 1.7154172127222742e-05, + "loss": 0.3691, + "step": 3038 + }, + { + "epoch": 2.69, + "learning_rate": 1.7152169257932944e-05, + "loss": 0.3634, + "step": 3039 + }, + { + "epoch": 2.69, + "learning_rate": 1.7150165801103505e-05, + "loss": 0.3887, + "step": 3040 + }, + { + "epoch": 2.69, + "learning_rate": 1.7148161756899012e-05, + "loss": 0.3768, + "step": 3041 + }, + { + "epoch": 2.69, + "learning_rate": 1.7146157125484097e-05, + "loss": 0.38, + "step": 3042 + }, + { + "epoch": 2.69, + "learning_rate": 1.7144151907023426e-05, + "loss": 0.3879, + "step": 3043 + }, + { + "epoch": 2.69, + "learning_rate": 1.7142146101681737e-05, + "loss": 0.3986, + "step": 3044 + }, + { + "epoch": 2.69, + "learning_rate": 1.7140139709623795e-05, + "loss": 0.374, + "step": 3045 + }, + { + "epoch": 2.69, + "learning_rate": 1.7138132731014426e-05, + "loss": 0.3685, + "step": 3046 + }, + { + "epoch": 2.7, + "learning_rate": 1.7136125166018497e-05, + "loss": 0.3737, + "step": 3047 + }, + { + "epoch": 2.7, + "learning_rate": 1.7134117014800927e-05, + "loss": 0.3624, + "step": 3048 + }, + { + "epoch": 2.7, + "learning_rate": 1.713210827752669e-05, + "loss": 0.3718, + "step": 3049 + }, + { + "epoch": 2.7, + "learning_rate": 1.713009895436079e-05, + "loss": 0.3938, + "step": 3050 + }, + { + "epoch": 2.7, + "learning_rate": 1.7128089045468294e-05, + "loss": 0.3783, + "step": 3051 + }, + { + "epoch": 2.7, + "learning_rate": 1.7126078551014314e-05, + "loss": 0.3689, + "step": 3052 + }, + { + "epoch": 2.7, + "learning_rate": 1.712406747116401e-05, + "loss": 0.3678, + "step": 3053 + }, + { + "epoch": 2.7, + "learning_rate": 1.7122055806082584e-05, + "loss": 0.3862, + "step": 3054 + }, + { + "epoch": 2.7, + "learning_rate": 1.71200435559353e-05, + "loss": 0.3923, + "step": 3055 + }, + { + "epoch": 2.7, + "learning_rate": 1.711803072088745e-05, + "loss": 0.3746, + "step": 3056 + }, + { + "epoch": 2.7, + "learning_rate": 1.7116017301104397e-05, + "loss": 0.4182, + "step": 3057 + }, + { + "epoch": 2.71, + "learning_rate": 1.711400329675153e-05, + "loss": 0.3924, + "step": 3058 + }, + { + "epoch": 2.71, + "learning_rate": 1.7111988707994304e-05, + "loss": 0.3725, + "step": 3059 + }, + { + "epoch": 2.71, + "learning_rate": 1.7109973534998207e-05, + "loss": 0.3743, + "step": 3060 + }, + { + "epoch": 2.71, + "learning_rate": 1.7107957777928786e-05, + "loss": 0.403, + "step": 3061 + }, + { + "epoch": 2.71, + "learning_rate": 1.710594143695164e-05, + "loss": 0.3908, + "step": 3062 + }, + { + "epoch": 2.71, + "learning_rate": 1.7103924512232393e-05, + "loss": 0.3756, + "step": 3063 + }, + { + "epoch": 2.71, + "learning_rate": 1.7101907003936747e-05, + "loss": 0.3628, + "step": 3064 + }, + { + "epoch": 2.71, + "learning_rate": 1.7099888912230428e-05, + "loss": 0.4081, + "step": 3065 + }, + { + "epoch": 2.71, + "learning_rate": 1.709787023727922e-05, + "loss": 0.3685, + "step": 3066 + }, + { + "epoch": 2.71, + "learning_rate": 1.7095850979248956e-05, + "loss": 0.3768, + "step": 3067 + }, + { + "epoch": 2.71, + "learning_rate": 1.7093831138305515e-05, + "loss": 0.3867, + "step": 3068 + }, + { + "epoch": 2.71, + "learning_rate": 1.709181071461482e-05, + "loss": 0.3957, + "step": 3069 + }, + { + "epoch": 2.72, + "learning_rate": 1.7089789708342856e-05, + "loss": 0.3789, + "step": 3070 + }, + { + "epoch": 2.72, + "learning_rate": 1.7087768119655637e-05, + "loss": 0.3849, + "step": 3071 + }, + { + "epoch": 2.72, + "learning_rate": 1.708574594871923e-05, + "loss": 0.3887, + "step": 3072 + }, + { + "epoch": 2.72, + "learning_rate": 1.7083723195699763e-05, + "loss": 0.3609, + "step": 3073 + }, + { + "epoch": 2.72, + "learning_rate": 1.7081699860763395e-05, + "loss": 0.3711, + "step": 3074 + }, + { + "epoch": 2.72, + "learning_rate": 1.7079675944076343e-05, + "loss": 0.3777, + "step": 3075 + }, + { + "epoch": 2.72, + "learning_rate": 1.7077651445804865e-05, + "loss": 0.3951, + "step": 3076 + }, + { + "epoch": 2.72, + "learning_rate": 1.7075626366115278e-05, + "loss": 0.4018, + "step": 3077 + }, + { + "epoch": 2.72, + "learning_rate": 1.707360070517393e-05, + "loss": 0.3879, + "step": 3078 + }, + { + "epoch": 2.72, + "learning_rate": 1.707157446314723e-05, + "loss": 0.3665, + "step": 3079 + }, + { + "epoch": 2.72, + "learning_rate": 1.7069547640201635e-05, + "loss": 0.3799, + "step": 3080 + }, + { + "epoch": 2.73, + "learning_rate": 1.7067520236503637e-05, + "loss": 0.394, + "step": 3081 + }, + { + "epoch": 2.73, + "learning_rate": 1.7065492252219794e-05, + "loss": 0.3753, + "step": 3082 + }, + { + "epoch": 2.73, + "learning_rate": 1.706346368751669e-05, + "loss": 0.3727, + "step": 3083 + }, + { + "epoch": 2.73, + "learning_rate": 1.7061434542560976e-05, + "loss": 0.3654, + "step": 3084 + }, + { + "epoch": 2.73, + "learning_rate": 1.705940481751934e-05, + "loss": 0.398, + "step": 3085 + }, + { + "epoch": 2.73, + "learning_rate": 1.7057374512558524e-05, + "loss": 0.3742, + "step": 3086 + }, + { + "epoch": 2.73, + "learning_rate": 1.7055343627845317e-05, + "loss": 0.366, + "step": 3087 + }, + { + "epoch": 2.73, + "learning_rate": 1.7053312163546542e-05, + "loss": 0.3803, + "step": 3088 + }, + { + "epoch": 2.73, + "learning_rate": 1.7051280119829093e-05, + "loss": 0.3843, + "step": 3089 + }, + { + "epoch": 2.73, + "learning_rate": 1.704924749685989e-05, + "loss": 0.3669, + "step": 3090 + }, + { + "epoch": 2.73, + "learning_rate": 1.7047214294805914e-05, + "loss": 0.3854, + "step": 3091 + }, + { + "epoch": 2.74, + "learning_rate": 1.7045180513834187e-05, + "loss": 0.3578, + "step": 3092 + }, + { + "epoch": 2.74, + "learning_rate": 1.704314615411179e-05, + "loss": 0.3748, + "step": 3093 + }, + { + "epoch": 2.74, + "learning_rate": 1.7041111215805826e-05, + "loss": 0.3677, + "step": 3094 + }, + { + "epoch": 2.74, + "learning_rate": 1.7039075699083477e-05, + "loss": 0.3826, + "step": 3095 + }, + { + "epoch": 2.74, + "learning_rate": 1.703703960411195e-05, + "loss": 0.3848, + "step": 3096 + }, + { + "epoch": 2.74, + "learning_rate": 1.703500293105851e-05, + "loss": 0.3577, + "step": 3097 + }, + { + "epoch": 2.74, + "learning_rate": 1.7032965680090467e-05, + "loss": 0.3594, + "step": 3098 + }, + { + "epoch": 2.74, + "learning_rate": 1.7030927851375177e-05, + "loss": 0.3861, + "step": 3099 + }, + { + "epoch": 2.74, + "learning_rate": 1.702888944508004e-05, + "loss": 0.3689, + "step": 3100 + }, + { + "epoch": 2.74, + "learning_rate": 1.702685046137252e-05, + "loss": 0.364, + "step": 3101 + }, + { + "epoch": 2.74, + "learning_rate": 1.70248109004201e-05, + "loss": 0.3689, + "step": 3102 + }, + { + "epoch": 2.74, + "learning_rate": 1.7022770762390334e-05, + "loss": 0.384, + "step": 3103 + }, + { + "epoch": 2.75, + "learning_rate": 1.7020730047450823e-05, + "loss": 0.3741, + "step": 3104 + }, + { + "epoch": 2.75, + "learning_rate": 1.70186887557692e-05, + "loss": 0.4112, + "step": 3105 + }, + { + "epoch": 2.75, + "learning_rate": 1.7016646887513158e-05, + "loss": 0.3678, + "step": 3106 + }, + { + "epoch": 2.75, + "learning_rate": 1.701460444285043e-05, + "loss": 0.3645, + "step": 3107 + }, + { + "epoch": 2.75, + "learning_rate": 1.7012561421948806e-05, + "loss": 0.3666, + "step": 3108 + }, + { + "epoch": 2.75, + "learning_rate": 1.701051782497611e-05, + "loss": 0.3453, + "step": 3109 + }, + { + "epoch": 2.75, + "learning_rate": 1.7008473652100225e-05, + "loss": 0.3827, + "step": 3110 + }, + { + "epoch": 2.75, + "learning_rate": 1.7006428903489072e-05, + "loss": 0.3916, + "step": 3111 + }, + { + "epoch": 2.75, + "learning_rate": 1.700438357931063e-05, + "loss": 0.3897, + "step": 3112 + }, + { + "epoch": 2.75, + "learning_rate": 1.700233767973291e-05, + "loss": 0.375, + "step": 3113 + }, + { + "epoch": 2.75, + "learning_rate": 1.700029120492399e-05, + "loss": 0.387, + "step": 3114 + }, + { + "epoch": 2.76, + "learning_rate": 1.6998244155051983e-05, + "loss": 0.3695, + "step": 3115 + }, + { + "epoch": 2.76, + "learning_rate": 1.6996196530285042e-05, + "loss": 0.3858, + "step": 3116 + }, + { + "epoch": 2.76, + "learning_rate": 1.6994148330791386e-05, + "loss": 0.3849, + "step": 3117 + }, + { + "epoch": 2.76, + "learning_rate": 1.6992099556739266e-05, + "loss": 0.3653, + "step": 3118 + }, + { + "epoch": 2.76, + "learning_rate": 1.6990050208296988e-05, + "loss": 0.4015, + "step": 3119 + }, + { + "epoch": 2.76, + "learning_rate": 1.69880002856329e-05, + "loss": 0.3805, + "step": 3120 + }, + { + "epoch": 2.76, + "learning_rate": 1.6985949788915408e-05, + "loss": 0.3848, + "step": 3121 + }, + { + "epoch": 2.76, + "learning_rate": 1.6983898718312945e-05, + "loss": 0.3823, + "step": 3122 + }, + { + "epoch": 2.76, + "learning_rate": 1.6981847073994012e-05, + "loss": 0.3868, + "step": 3123 + }, + { + "epoch": 2.76, + "learning_rate": 1.6979794856127147e-05, + "loss": 0.356, + "step": 3124 + }, + { + "epoch": 2.76, + "learning_rate": 1.6977742064880935e-05, + "loss": 0.374, + "step": 3125 + }, + { + "epoch": 2.77, + "learning_rate": 1.697568870042401e-05, + "loss": 0.3688, + "step": 3126 + }, + { + "epoch": 2.77, + "learning_rate": 1.697363476292505e-05, + "loss": 0.3567, + "step": 3127 + }, + { + "epoch": 2.77, + "learning_rate": 1.6971580252552794e-05, + "loss": 0.3704, + "step": 3128 + }, + { + "epoch": 2.77, + "learning_rate": 1.6969525169476e-05, + "loss": 0.3706, + "step": 3129 + }, + { + "epoch": 2.77, + "learning_rate": 1.69674695138635e-05, + "loss": 0.4047, + "step": 3130 + }, + { + "epoch": 2.77, + "learning_rate": 1.696541328588416e-05, + "loss": 0.37, + "step": 3131 + }, + { + "epoch": 2.77, + "learning_rate": 1.69633564857069e-05, + "loss": 0.3838, + "step": 3132 + }, + { + "epoch": 2.77, + "learning_rate": 1.696129911350068e-05, + "loss": 0.3649, + "step": 3133 + }, + { + "epoch": 2.77, + "learning_rate": 1.6959241169434512e-05, + "loss": 0.4002, + "step": 3134 + }, + { + "epoch": 2.77, + "learning_rate": 1.6957182653677445e-05, + "loss": 0.3828, + "step": 3135 + }, + { + "epoch": 2.77, + "learning_rate": 1.6955123566398595e-05, + "loss": 0.3914, + "step": 3136 + }, + { + "epoch": 2.78, + "learning_rate": 1.6953063907767108e-05, + "loss": 0.378, + "step": 3137 + }, + { + "epoch": 2.78, + "learning_rate": 1.6951003677952173e-05, + "loss": 0.3697, + "step": 3138 + }, + { + "epoch": 2.78, + "learning_rate": 1.694894287712305e-05, + "loss": 0.3749, + "step": 3139 + }, + { + "epoch": 2.78, + "learning_rate": 1.694688150544902e-05, + "loss": 0.4131, + "step": 3140 + }, + { + "epoch": 2.78, + "learning_rate": 1.6944819563099422e-05, + "loss": 0.3623, + "step": 3141 + }, + { + "epoch": 2.78, + "learning_rate": 1.6942757050243642e-05, + "loss": 0.3806, + "step": 3142 + }, + { + "epoch": 2.78, + "learning_rate": 1.694069396705112e-05, + "loss": 0.3611, + "step": 3143 + }, + { + "epoch": 2.78, + "learning_rate": 1.6938630313691323e-05, + "loss": 0.3644, + "step": 3144 + }, + { + "epoch": 2.78, + "learning_rate": 1.6936566090333787e-05, + "loss": 0.364, + "step": 3145 + }, + { + "epoch": 2.78, + "learning_rate": 1.6934501297148077e-05, + "loss": 0.3907, + "step": 3146 + }, + { + "epoch": 2.78, + "learning_rate": 1.6932435934303822e-05, + "loss": 0.3626, + "step": 3147 + }, + { + "epoch": 2.78, + "learning_rate": 1.693037000197068e-05, + "loss": 0.3987, + "step": 3148 + }, + { + "epoch": 2.79, + "learning_rate": 1.6928303500318367e-05, + "loss": 0.3632, + "step": 3149 + }, + { + "epoch": 2.79, + "learning_rate": 1.6926236429516644e-05, + "loss": 0.3867, + "step": 3150 + }, + { + "epoch": 2.79, + "learning_rate": 1.692416878973531e-05, + "loss": 0.3714, + "step": 3151 + }, + { + "epoch": 2.79, + "learning_rate": 1.6922100581144228e-05, + "loss": 0.38, + "step": 3152 + }, + { + "epoch": 2.79, + "learning_rate": 1.6920031803913297e-05, + "loss": 0.3687, + "step": 3153 + }, + { + "epoch": 2.79, + "learning_rate": 1.6917962458212463e-05, + "loss": 0.38, + "step": 3154 + }, + { + "epoch": 2.79, + "learning_rate": 1.6915892544211713e-05, + "loss": 0.3763, + "step": 3155 + }, + { + "epoch": 2.79, + "learning_rate": 1.69138220620811e-05, + "loss": 0.3845, + "step": 3156 + }, + { + "epoch": 2.79, + "learning_rate": 1.6911751011990696e-05, + "loss": 0.4209, + "step": 3157 + }, + { + "epoch": 2.79, + "learning_rate": 1.6909679394110645e-05, + "loss": 0.3983, + "step": 3158 + }, + { + "epoch": 2.79, + "learning_rate": 1.6907607208611123e-05, + "loss": 0.391, + "step": 3159 + }, + { + "epoch": 2.8, + "learning_rate": 1.690553445566236e-05, + "loss": 0.3769, + "step": 3160 + }, + { + "epoch": 2.8, + "learning_rate": 1.6903461135434627e-05, + "loss": 0.3563, + "step": 3161 + }, + { + "epoch": 2.8, + "learning_rate": 1.6901387248098246e-05, + "loss": 0.3929, + "step": 3162 + }, + { + "epoch": 2.8, + "learning_rate": 1.689931279382358e-05, + "loss": 0.3992, + "step": 3163 + }, + { + "epoch": 2.8, + "learning_rate": 1.6897237772781046e-05, + "loss": 0.3782, + "step": 3164 + }, + { + "epoch": 2.8, + "learning_rate": 1.6895162185141097e-05, + "loss": 0.3984, + "step": 3165 + }, + { + "epoch": 2.8, + "learning_rate": 1.689308603107425e-05, + "loss": 0.4003, + "step": 3166 + }, + { + "epoch": 2.8, + "learning_rate": 1.689100931075105e-05, + "loss": 0.3506, + "step": 3167 + }, + { + "epoch": 2.8, + "learning_rate": 1.6888932024342098e-05, + "loss": 0.3964, + "step": 3168 + }, + { + "epoch": 2.8, + "learning_rate": 1.6886854172018043e-05, + "loss": 0.3611, + "step": 3169 + }, + { + "epoch": 2.8, + "learning_rate": 1.6884775753949572e-05, + "loss": 0.3752, + "step": 3170 + }, + { + "epoch": 2.81, + "learning_rate": 1.6882696770307428e-05, + "loss": 0.3688, + "step": 3171 + }, + { + "epoch": 2.81, + "learning_rate": 1.6880617221262396e-05, + "loss": 0.3784, + "step": 3172 + }, + { + "epoch": 2.81, + "learning_rate": 1.6878537106985305e-05, + "loss": 0.3718, + "step": 3173 + }, + { + "epoch": 2.81, + "learning_rate": 1.6876456427647036e-05, + "loss": 0.3768, + "step": 3174 + }, + { + "epoch": 2.81, + "learning_rate": 1.6874375183418514e-05, + "loss": 0.3651, + "step": 3175 + }, + { + "epoch": 2.81, + "learning_rate": 1.6872293374470706e-05, + "loss": 0.3597, + "step": 3176 + }, + { + "epoch": 2.81, + "learning_rate": 1.6870211000974633e-05, + "loss": 0.3865, + "step": 3177 + }, + { + "epoch": 2.81, + "learning_rate": 1.6868128063101358e-05, + "loss": 0.366, + "step": 3178 + }, + { + "epoch": 2.81, + "learning_rate": 1.6866044561021987e-05, + "loss": 0.4104, + "step": 3179 + }, + { + "epoch": 2.81, + "learning_rate": 1.6863960494907687e-05, + "loss": 0.397, + "step": 3180 + }, + { + "epoch": 2.81, + "learning_rate": 1.686187586492965e-05, + "loss": 0.3741, + "step": 3181 + }, + { + "epoch": 2.81, + "learning_rate": 1.685979067125913e-05, + "loss": 0.3849, + "step": 3182 + }, + { + "epoch": 2.82, + "learning_rate": 1.685770491406742e-05, + "loss": 0.3762, + "step": 3183 + }, + { + "epoch": 2.82, + "learning_rate": 1.6855618593525863e-05, + "loss": 0.3641, + "step": 3184 + }, + { + "epoch": 2.82, + "learning_rate": 1.685353170980585e-05, + "loss": 0.395, + "step": 3185 + }, + { + "epoch": 2.82, + "learning_rate": 1.6851444263078807e-05, + "loss": 0.3874, + "step": 3186 + }, + { + "epoch": 2.82, + "learning_rate": 1.6849356253516224e-05, + "loss": 0.3862, + "step": 3187 + }, + { + "epoch": 2.82, + "learning_rate": 1.6847267681289626e-05, + "loss": 0.3818, + "step": 3188 + }, + { + "epoch": 2.82, + "learning_rate": 1.6845178546570583e-05, + "loss": 0.3594, + "step": 3189 + }, + { + "epoch": 2.82, + "learning_rate": 1.6843088849530714e-05, + "loss": 0.3869, + "step": 3190 + }, + { + "epoch": 2.82, + "learning_rate": 1.6840998590341684e-05, + "loss": 0.3753, + "step": 3191 + }, + { + "epoch": 2.82, + "learning_rate": 1.6838907769175205e-05, + "loss": 0.3769, + "step": 3192 + }, + { + "epoch": 2.82, + "learning_rate": 1.6836816386203037e-05, + "loss": 0.3725, + "step": 3193 + }, + { + "epoch": 2.83, + "learning_rate": 1.6834724441596987e-05, + "loss": 0.3699, + "step": 3194 + }, + { + "epoch": 2.83, + "learning_rate": 1.6832631935528897e-05, + "loss": 0.3849, + "step": 3195 + }, + { + "epoch": 2.83, + "learning_rate": 1.6830538868170666e-05, + "loss": 0.3693, + "step": 3196 + }, + { + "epoch": 2.83, + "learning_rate": 1.6828445239694237e-05, + "loss": 0.3942, + "step": 3197 + }, + { + "epoch": 2.83, + "learning_rate": 1.68263510502716e-05, + "loss": 0.3838, + "step": 3198 + }, + { + "epoch": 2.83, + "learning_rate": 1.6824256300074785e-05, + "loss": 0.3805, + "step": 3199 + }, + { + "epoch": 2.83, + "learning_rate": 1.6822160989275875e-05, + "loss": 0.3734, + "step": 3200 + }, + { + "epoch": 2.83, + "learning_rate": 1.6820065118047e-05, + "loss": 0.3882, + "step": 3201 + }, + { + "epoch": 2.83, + "learning_rate": 1.681796868656033e-05, + "loss": 0.3588, + "step": 3202 + }, + { + "epoch": 2.83, + "learning_rate": 1.681587169498808e-05, + "loss": 0.3899, + "step": 3203 + }, + { + "epoch": 2.83, + "learning_rate": 1.6813774143502516e-05, + "loss": 0.371, + "step": 3204 + }, + { + "epoch": 2.84, + "learning_rate": 1.681167603227595e-05, + "loss": 0.3866, + "step": 3205 + }, + { + "epoch": 2.84, + "learning_rate": 1.6809577361480746e-05, + "loss": 0.3879, + "step": 3206 + }, + { + "epoch": 2.84, + "learning_rate": 1.680747813128929e-05, + "loss": 0.3813, + "step": 3207 + }, + { + "epoch": 2.84, + "learning_rate": 1.6805378341874044e-05, + "loss": 0.3776, + "step": 3208 + }, + { + "epoch": 2.84, + "learning_rate": 1.6803277993407497e-05, + "loss": 0.376, + "step": 3209 + }, + { + "epoch": 2.84, + "learning_rate": 1.680117708606219e-05, + "loss": 0.3962, + "step": 3210 + }, + { + "epoch": 2.84, + "learning_rate": 1.6799075620010714e-05, + "loss": 0.3863, + "step": 3211 + }, + { + "epoch": 2.84, + "learning_rate": 1.6796973595425698e-05, + "loss": 0.3879, + "step": 3212 + }, + { + "epoch": 2.84, + "learning_rate": 1.6794871012479812e-05, + "loss": 0.3831, + "step": 3213 + }, + { + "epoch": 2.84, + "learning_rate": 1.679276787134579e-05, + "loss": 0.354, + "step": 3214 + }, + { + "epoch": 2.84, + "learning_rate": 1.67906641721964e-05, + "loss": 0.3945, + "step": 3215 + }, + { + "epoch": 2.84, + "learning_rate": 1.6788559915204458e-05, + "loss": 0.3845, + "step": 3216 + }, + { + "epoch": 2.85, + "learning_rate": 1.678645510054282e-05, + "loss": 0.3877, + "step": 3217 + }, + { + "epoch": 2.85, + "learning_rate": 1.6784349728384403e-05, + "loss": 0.3649, + "step": 3218 + }, + { + "epoch": 2.85, + "learning_rate": 1.6782243798902148e-05, + "loss": 0.3681, + "step": 3219 + }, + { + "epoch": 2.85, + "learning_rate": 1.6780137312269064e-05, + "loss": 0.3674, + "step": 3220 + }, + { + "epoch": 2.85, + "learning_rate": 1.677803026865819e-05, + "loss": 0.3807, + "step": 3221 + }, + { + "epoch": 2.85, + "learning_rate": 1.677592266824262e-05, + "loss": 0.3566, + "step": 3222 + }, + { + "epoch": 2.85, + "learning_rate": 1.6773814511195487e-05, + "loss": 0.4022, + "step": 3223 + }, + { + "epoch": 2.85, + "learning_rate": 1.6771705797689972e-05, + "loss": 0.3528, + "step": 3224 + }, + { + "epoch": 2.85, + "learning_rate": 1.6769596527899307e-05, + "loss": 0.404, + "step": 3225 + }, + { + "epoch": 2.85, + "learning_rate": 1.6767486701996763e-05, + "loss": 0.3964, + "step": 3226 + }, + { + "epoch": 2.85, + "learning_rate": 1.6765376320155657e-05, + "loss": 0.3906, + "step": 3227 + }, + { + "epoch": 2.86, + "learning_rate": 1.676326538254936e-05, + "loss": 0.3601, + "step": 3228 + }, + { + "epoch": 2.86, + "learning_rate": 1.6761153889351272e-05, + "loss": 0.3907, + "step": 3229 + }, + { + "epoch": 2.86, + "learning_rate": 1.6759041840734856e-05, + "loss": 0.3714, + "step": 3230 + }, + { + "epoch": 2.86, + "learning_rate": 1.6756929236873616e-05, + "loss": 0.3931, + "step": 3231 + }, + { + "epoch": 2.86, + "learning_rate": 1.675481607794109e-05, + "loss": 0.3965, + "step": 3232 + }, + { + "epoch": 2.86, + "learning_rate": 1.6752702364110877e-05, + "loss": 0.3589, + "step": 3233 + }, + { + "epoch": 2.86, + "learning_rate": 1.6750588095556618e-05, + "loss": 0.3711, + "step": 3234 + }, + { + "epoch": 2.86, + "learning_rate": 1.674847327245199e-05, + "loss": 0.3542, + "step": 3235 + }, + { + "epoch": 2.86, + "learning_rate": 1.6746357894970725e-05, + "loss": 0.3771, + "step": 3236 + }, + { + "epoch": 2.86, + "learning_rate": 1.6744241963286603e-05, + "loss": 0.3936, + "step": 3237 + }, + { + "epoch": 2.86, + "learning_rate": 1.6742125477573434e-05, + "loss": 0.4008, + "step": 3238 + }, + { + "epoch": 2.87, + "learning_rate": 1.6740008438005095e-05, + "loss": 0.3566, + "step": 3239 + }, + { + "epoch": 2.87, + "learning_rate": 1.673789084475549e-05, + "loss": 0.4037, + "step": 3240 + }, + { + "epoch": 2.87, + "learning_rate": 1.673577269799858e-05, + "loss": 0.3739, + "step": 3241 + }, + { + "epoch": 2.87, + "learning_rate": 1.6733653997908367e-05, + "loss": 0.3656, + "step": 3242 + }, + { + "epoch": 2.87, + "learning_rate": 1.6731534744658896e-05, + "loss": 0.3783, + "step": 3243 + }, + { + "epoch": 2.87, + "learning_rate": 1.6729414938424263e-05, + "loss": 0.3797, + "step": 3244 + }, + { + "epoch": 2.87, + "learning_rate": 1.6727294579378605e-05, + "loss": 0.3692, + "step": 3245 + }, + { + "epoch": 2.87, + "learning_rate": 1.672517366769611e-05, + "loss": 0.3866, + "step": 3246 + }, + { + "epoch": 2.87, + "learning_rate": 1.6723052203551004e-05, + "loss": 0.3606, + "step": 3247 + }, + { + "epoch": 2.87, + "learning_rate": 1.6720930187117564e-05, + "loss": 0.3586, + "step": 3248 + }, + { + "epoch": 2.87, + "learning_rate": 1.671880761857011e-05, + "loss": 0.3905, + "step": 3249 + }, + { + "epoch": 2.87, + "learning_rate": 1.6716684498083005e-05, + "loss": 0.376, + "step": 3250 + }, + { + "epoch": 2.88, + "learning_rate": 1.6714560825830664e-05, + "loss": 0.393, + "step": 3251 + }, + { + "epoch": 2.88, + "learning_rate": 1.671243660198754e-05, + "loss": 0.3747, + "step": 3252 + }, + { + "epoch": 2.88, + "learning_rate": 1.6710311826728136e-05, + "loss": 0.3831, + "step": 3253 + }, + { + "epoch": 2.88, + "learning_rate": 1.6708186500226998e-05, + "loss": 0.3753, + "step": 3254 + }, + { + "epoch": 2.88, + "learning_rate": 1.6706060622658724e-05, + "loss": 0.3571, + "step": 3255 + }, + { + "epoch": 2.88, + "learning_rate": 1.6703934194197947e-05, + "loss": 0.4007, + "step": 3256 + }, + { + "epoch": 2.88, + "learning_rate": 1.6701807215019347e-05, + "loss": 0.3838, + "step": 3257 + }, + { + "epoch": 2.88, + "learning_rate": 1.6699679685297655e-05, + "loss": 0.3706, + "step": 3258 + }, + { + "epoch": 2.88, + "learning_rate": 1.6697551605207646e-05, + "loss": 0.3685, + "step": 3259 + }, + { + "epoch": 2.88, + "learning_rate": 1.6695422974924137e-05, + "loss": 0.3665, + "step": 3260 + }, + { + "epoch": 2.88, + "learning_rate": 1.669329379462199e-05, + "loss": 0.3729, + "step": 3261 + }, + { + "epoch": 2.89, + "learning_rate": 1.6691164064476116e-05, + "loss": 0.3811, + "step": 3262 + }, + { + "epoch": 2.89, + "learning_rate": 1.668903378466147e-05, + "loss": 0.3489, + "step": 3263 + }, + { + "epoch": 2.89, + "learning_rate": 1.6686902955353045e-05, + "loss": 0.3804, + "step": 3264 + }, + { + "epoch": 2.89, + "learning_rate": 1.6684771576725896e-05, + "loss": 0.3776, + "step": 3265 + }, + { + "epoch": 2.89, + "learning_rate": 1.6682639648955104e-05, + "loss": 0.3838, + "step": 3266 + }, + { + "epoch": 2.89, + "learning_rate": 1.6680507172215804e-05, + "loss": 0.3846, + "step": 3267 + }, + { + "epoch": 2.89, + "learning_rate": 1.667837414668318e-05, + "loss": 0.3893, + "step": 3268 + }, + { + "epoch": 2.89, + "learning_rate": 1.6676240572532453e-05, + "loss": 0.3791, + "step": 3269 + }, + { + "epoch": 2.89, + "learning_rate": 1.6674106449938894e-05, + "loss": 0.3862, + "step": 3270 + }, + { + "epoch": 2.89, + "learning_rate": 1.6671971779077818e-05, + "loss": 0.3864, + "step": 3271 + }, + { + "epoch": 2.89, + "learning_rate": 1.6669836560124585e-05, + "loss": 0.3668, + "step": 3272 + }, + { + "epoch": 2.9, + "learning_rate": 1.6667700793254598e-05, + "loss": 0.3572, + "step": 3273 + }, + { + "epoch": 2.9, + "learning_rate": 1.6665564478643316e-05, + "loss": 0.3702, + "step": 3274 + }, + { + "epoch": 2.9, + "learning_rate": 1.6663427616466216e-05, + "loss": 0.3895, + "step": 3275 + }, + { + "epoch": 2.9, + "learning_rate": 1.6661290206898858e-05, + "loss": 0.3874, + "step": 3276 + }, + { + "epoch": 2.9, + "learning_rate": 1.665915225011681e-05, + "loss": 0.3771, + "step": 3277 + }, + { + "epoch": 2.9, + "learning_rate": 1.6657013746295717e-05, + "loss": 0.371, + "step": 3278 + }, + { + "epoch": 2.9, + "learning_rate": 1.665487469561124e-05, + "loss": 0.3544, + "step": 3279 + }, + { + "epoch": 2.9, + "learning_rate": 1.6652735098239108e-05, + "loss": 0.3553, + "step": 3280 + }, + { + "epoch": 2.9, + "learning_rate": 1.665059495435508e-05, + "loss": 0.4129, + "step": 3281 + }, + { + "epoch": 2.9, + "learning_rate": 1.6648454264134972e-05, + "loss": 0.3874, + "step": 3282 + }, + { + "epoch": 2.9, + "learning_rate": 1.664631302775463e-05, + "loss": 0.3672, + "step": 3283 + }, + { + "epoch": 2.91, + "learning_rate": 1.664417124538996e-05, + "loss": 0.3851, + "step": 3284 + }, + { + "epoch": 2.91, + "learning_rate": 1.6642028917216902e-05, + "loss": 0.3839, + "step": 3285 + }, + { + "epoch": 2.91, + "learning_rate": 1.663988604341145e-05, + "loss": 0.3735, + "step": 3286 + }, + { + "epoch": 2.91, + "learning_rate": 1.6637742624149634e-05, + "loss": 0.373, + "step": 3287 + }, + { + "epoch": 2.91, + "learning_rate": 1.663559865960753e-05, + "loss": 0.3825, + "step": 3288 + }, + { + "epoch": 2.91, + "learning_rate": 1.6633454149961264e-05, + "loss": 0.3681, + "step": 3289 + }, + { + "epoch": 2.91, + "learning_rate": 1.6631309095387012e-05, + "loss": 0.3827, + "step": 3290 + }, + { + "epoch": 2.91, + "learning_rate": 1.662916349606097e-05, + "loss": 0.3753, + "step": 3291 + }, + { + "epoch": 2.91, + "learning_rate": 1.662701735215941e-05, + "loss": 0.3581, + "step": 3292 + }, + { + "epoch": 2.91, + "learning_rate": 1.6624870663858632e-05, + "loss": 0.3704, + "step": 3293 + }, + { + "epoch": 2.91, + "learning_rate": 1.6622723431334976e-05, + "loss": 0.3726, + "step": 3294 + }, + { + "epoch": 2.91, + "learning_rate": 1.662057565476484e-05, + "loss": 0.3812, + "step": 3295 + }, + { + "epoch": 2.92, + "learning_rate": 1.6618427334324657e-05, + "loss": 0.3853, + "step": 3296 + }, + { + "epoch": 2.92, + "learning_rate": 1.6616278470190915e-05, + "loss": 0.385, + "step": 3297 + }, + { + "epoch": 2.92, + "learning_rate": 1.661412906254013e-05, + "loss": 0.3793, + "step": 3298 + }, + { + "epoch": 2.92, + "learning_rate": 1.661197911154888e-05, + "loss": 0.3746, + "step": 3299 + }, + { + "epoch": 2.92, + "learning_rate": 1.660982861739378e-05, + "loss": 0.3918, + "step": 3300 + }, + { + "epoch": 2.92, + "learning_rate": 1.660767758025148e-05, + "loss": 0.3675, + "step": 3301 + }, + { + "epoch": 2.92, + "learning_rate": 1.66055260002987e-05, + "loss": 0.3884, + "step": 3302 + }, + { + "epoch": 2.92, + "learning_rate": 1.6603373877712176e-05, + "loss": 0.381, + "step": 3303 + }, + { + "epoch": 2.92, + "learning_rate": 1.6601221212668706e-05, + "loss": 0.367, + "step": 3304 + }, + { + "epoch": 2.92, + "learning_rate": 1.6599068005345134e-05, + "loss": 0.3558, + "step": 3305 + }, + { + "epoch": 2.92, + "learning_rate": 1.6596914255918332e-05, + "loss": 0.3579, + "step": 3306 + }, + { + "epoch": 2.93, + "learning_rate": 1.6594759964565237e-05, + "loss": 0.3969, + "step": 3307 + }, + { + "epoch": 2.93, + "learning_rate": 1.6592605131462808e-05, + "loss": 0.379, + "step": 3308 + }, + { + "epoch": 2.93, + "learning_rate": 1.6590449756788075e-05, + "loss": 0.3807, + "step": 3309 + }, + { + "epoch": 2.93, + "learning_rate": 1.6588293840718096e-05, + "loss": 0.3635, + "step": 3310 + }, + { + "epoch": 2.93, + "learning_rate": 1.6586137383429967e-05, + "loss": 0.3768, + "step": 3311 + }, + { + "epoch": 2.93, + "learning_rate": 1.6583980385100847e-05, + "loss": 0.3837, + "step": 3312 + }, + { + "epoch": 2.93, + "learning_rate": 1.6581822845907926e-05, + "loss": 0.3787, + "step": 3313 + }, + { + "epoch": 2.93, + "learning_rate": 1.657966476602844e-05, + "loss": 0.4033, + "step": 3314 + }, + { + "epoch": 2.93, + "learning_rate": 1.657750614563968e-05, + "loss": 0.35, + "step": 3315 + }, + { + "epoch": 2.93, + "learning_rate": 1.6575346984918964e-05, + "loss": 0.3623, + "step": 3316 + }, + { + "epoch": 2.93, + "learning_rate": 1.6573187284043673e-05, + "loss": 0.387, + "step": 3317 + }, + { + "epoch": 2.94, + "learning_rate": 1.6571027043191214e-05, + "loss": 0.3872, + "step": 3318 + }, + { + "epoch": 2.94, + "learning_rate": 1.6568866262539055e-05, + "loss": 0.3889, + "step": 3319 + }, + { + "epoch": 2.94, + "learning_rate": 1.6566704942264698e-05, + "loss": 0.3608, + "step": 3320 + }, + { + "epoch": 2.94, + "learning_rate": 1.6564543082545686e-05, + "loss": 0.383, + "step": 3321 + }, + { + "epoch": 2.94, + "learning_rate": 1.6562380683559625e-05, + "loss": 0.3848, + "step": 3322 + }, + { + "epoch": 2.94, + "learning_rate": 1.6560217745484143e-05, + "loss": 0.3667, + "step": 3323 + }, + { + "epoch": 2.94, + "learning_rate": 1.6558054268496923e-05, + "loss": 0.3828, + "step": 3324 + }, + { + "epoch": 2.94, + "learning_rate": 1.6555890252775693e-05, + "loss": 0.372, + "step": 3325 + }, + { + "epoch": 2.94, + "learning_rate": 1.6553725698498228e-05, + "loss": 0.381, + "step": 3326 + }, + { + "epoch": 2.94, + "learning_rate": 1.6551560605842335e-05, + "loss": 0.3706, + "step": 3327 + }, + { + "epoch": 2.94, + "learning_rate": 1.654939497498588e-05, + "loss": 0.365, + "step": 3328 + }, + { + "epoch": 2.94, + "learning_rate": 1.654722880610676e-05, + "loss": 0.3671, + "step": 3329 + }, + { + "epoch": 2.95, + "learning_rate": 1.6545062099382926e-05, + "loss": 0.3906, + "step": 3330 + }, + { + "epoch": 2.95, + "learning_rate": 1.6542894854992368e-05, + "loss": 0.3905, + "step": 3331 + }, + { + "epoch": 2.95, + "learning_rate": 1.6540727073113122e-05, + "loss": 0.3919, + "step": 3332 + }, + { + "epoch": 2.95, + "learning_rate": 1.6538558753923267e-05, + "loss": 0.3493, + "step": 3333 + }, + { + "epoch": 2.95, + "learning_rate": 1.653638989760093e-05, + "loss": 0.4009, + "step": 3334 + }, + { + "epoch": 2.95, + "learning_rate": 1.653422050432428e-05, + "loss": 0.3505, + "step": 3335 + }, + { + "epoch": 2.95, + "learning_rate": 1.6532050574271527e-05, + "loss": 0.3718, + "step": 3336 + }, + { + "epoch": 2.95, + "learning_rate": 1.6529880107620924e-05, + "loss": 0.38, + "step": 3337 + }, + { + "epoch": 2.95, + "learning_rate": 1.6527709104550777e-05, + "loss": 0.3782, + "step": 3338 + }, + { + "epoch": 2.95, + "learning_rate": 1.6525537565239425e-05, + "loss": 0.3759, + "step": 3339 + }, + { + "epoch": 2.95, + "learning_rate": 1.6523365489865265e-05, + "loss": 0.4082, + "step": 3340 + }, + { + "epoch": 2.96, + "learning_rate": 1.6521192878606722e-05, + "loss": 0.3664, + "step": 3341 + }, + { + "epoch": 2.96, + "learning_rate": 1.6519019731642277e-05, + "loss": 0.4043, + "step": 3342 + }, + { + "epoch": 2.96, + "learning_rate": 1.651684604915045e-05, + "loss": 0.3984, + "step": 3343 + }, + { + "epoch": 2.96, + "learning_rate": 1.65146718313098e-05, + "loss": 0.3919, + "step": 3344 + }, + { + "epoch": 2.96, + "learning_rate": 1.6512497078298943e-05, + "loss": 0.3707, + "step": 3345 + }, + { + "epoch": 2.96, + "learning_rate": 1.6510321790296527e-05, + "loss": 0.3526, + "step": 3346 + }, + { + "epoch": 2.96, + "learning_rate": 1.650814596748125e-05, + "loss": 0.3575, + "step": 3347 + }, + { + "epoch": 2.96, + "learning_rate": 1.6505969610031854e-05, + "loss": 0.3824, + "step": 3348 + }, + { + "epoch": 2.96, + "learning_rate": 1.6503792718127124e-05, + "loss": 0.3729, + "step": 3349 + }, + { + "epoch": 2.96, + "learning_rate": 1.6501615291945886e-05, + "loss": 0.3956, + "step": 3350 + }, + { + "epoch": 2.96, + "learning_rate": 1.649943733166701e-05, + "loss": 0.4034, + "step": 3351 + }, + { + "epoch": 2.97, + "learning_rate": 1.6497258837469417e-05, + "loss": 0.3969, + "step": 3352 + }, + { + "epoch": 2.97, + "learning_rate": 1.6495079809532068e-05, + "loss": 0.3686, + "step": 3353 + }, + { + "epoch": 2.97, + "learning_rate": 1.6492900248033957e-05, + "loss": 0.4032, + "step": 3354 + }, + { + "epoch": 2.97, + "learning_rate": 1.6490720153154144e-05, + "loss": 0.372, + "step": 3355 + }, + { + "epoch": 2.97, + "learning_rate": 1.648853952507171e-05, + "loss": 0.3786, + "step": 3356 + }, + { + "epoch": 2.97, + "learning_rate": 1.6486358363965792e-05, + "loss": 0.3872, + "step": 3357 + }, + { + "epoch": 2.97, + "learning_rate": 1.648417667001558e-05, + "loss": 0.372, + "step": 3358 + }, + { + "epoch": 2.97, + "learning_rate": 1.6481994443400283e-05, + "loss": 0.374, + "step": 3359 + }, + { + "epoch": 2.97, + "learning_rate": 1.6479811684299173e-05, + "loss": 0.4078, + "step": 3360 + }, + { + "epoch": 2.97, + "learning_rate": 1.6477628392891563e-05, + "loss": 0.3826, + "step": 3361 + }, + { + "epoch": 2.97, + "learning_rate": 1.6475444569356806e-05, + "loss": 0.3785, + "step": 3362 + }, + { + "epoch": 2.97, + "learning_rate": 1.6473260213874292e-05, + "loss": 0.3745, + "step": 3363 + }, + { + "epoch": 2.98, + "learning_rate": 1.6471075326623474e-05, + "loss": 0.3454, + "step": 3364 + }, + { + "epoch": 2.98, + "learning_rate": 1.6468889907783828e-05, + "loss": 0.3579, + "step": 3365 + }, + { + "epoch": 2.98, + "learning_rate": 1.6466703957534888e-05, + "loss": 0.3799, + "step": 3366 + }, + { + "epoch": 2.98, + "learning_rate": 1.6464517476056224e-05, + "loss": 0.3604, + "step": 3367 + }, + { + "epoch": 2.98, + "learning_rate": 1.6462330463527452e-05, + "loss": 0.3751, + "step": 3368 + }, + { + "epoch": 2.98, + "learning_rate": 1.6460142920128238e-05, + "loss": 0.3765, + "step": 3369 + }, + { + "epoch": 2.98, + "learning_rate": 1.6457954846038275e-05, + "loss": 0.3672, + "step": 3370 + }, + { + "epoch": 2.98, + "learning_rate": 1.6455766241437315e-05, + "loss": 0.3625, + "step": 3371 + }, + { + "epoch": 2.98, + "learning_rate": 1.645357710650515e-05, + "loss": 0.3955, + "step": 3372 + }, + { + "epoch": 2.98, + "learning_rate": 1.6451387441421613e-05, + "loss": 0.3652, + "step": 3373 + }, + { + "epoch": 2.98, + "learning_rate": 1.6449197246366577e-05, + "loss": 0.3769, + "step": 3374 + }, + { + "epoch": 2.99, + "learning_rate": 1.6447006521519968e-05, + "loss": 0.3942, + "step": 3375 + }, + { + "epoch": 2.99, + "learning_rate": 1.644481526706175e-05, + "loss": 0.3778, + "step": 3376 + }, + { + "epoch": 2.99, + "learning_rate": 1.6442623483171934e-05, + "loss": 0.354, + "step": 3377 + }, + { + "epoch": 2.99, + "learning_rate": 1.6440431170030566e-05, + "loss": 0.3867, + "step": 3378 + }, + { + "epoch": 2.99, + "learning_rate": 1.6438238327817744e-05, + "loss": 0.3843, + "step": 3379 + }, + { + "epoch": 2.99, + "learning_rate": 1.6436044956713607e-05, + "loss": 0.4044, + "step": 3380 + }, + { + "epoch": 2.99, + "learning_rate": 1.6433851056898335e-05, + "loss": 0.3921, + "step": 3381 + }, + { + "epoch": 2.99, + "learning_rate": 1.6431656628552156e-05, + "loss": 0.3761, + "step": 3382 + }, + { + "epoch": 2.99, + "learning_rate": 1.642946167185534e-05, + "loss": 0.3854, + "step": 3383 + }, + { + "epoch": 2.99, + "learning_rate": 1.642726618698819e-05, + "loss": 0.368, + "step": 3384 + }, + { + "epoch": 2.99, + "learning_rate": 1.6425070174131073e-05, + "loss": 0.391, + "step": 3385 + }, + { + "epoch": 3.0, + "learning_rate": 1.6422873633464385e-05, + "loss": 0.3656, + "step": 3386 + }, + { + "epoch": 3.0, + "learning_rate": 1.6420676565168566e-05, + "loss": 0.393, + "step": 3387 + }, + { + "epoch": 3.0, + "learning_rate": 1.64184789694241e-05, + "loss": 0.3739, + "step": 3388 + }, + { + "epoch": 3.0, + "learning_rate": 1.6416280846411523e-05, + "loss": 0.3758, + "step": 3389 + }, + { + "epoch": 3.0, + "learning_rate": 1.6414082196311402e-05, + "loss": 0.3842, + "step": 3390 + }, + { + "epoch": 3.0, + "learning_rate": 1.6411883019304353e-05, + "loss": 0.3926, + "step": 3391 + }, + { + "epoch": 3.0, + "learning_rate": 1.6409683315571035e-05, + "loss": 0.3123, + "step": 3392 + }, + { + "epoch": 3.0, + "learning_rate": 1.6407483085292154e-05, + "loss": 0.2773, + "step": 3393 + }, + { + "epoch": 3.0, + "learning_rate": 1.640528232864845e-05, + "loss": 0.3006, + "step": 3394 + }, + { + "epoch": 3.0, + "learning_rate": 1.640308104582072e-05, + "loss": 0.2683, + "step": 3395 + }, + { + "epoch": 3.0, + "learning_rate": 1.6400879236989786e-05, + "loss": 0.2682, + "step": 3396 + }, + { + "epoch": 3.01, + "learning_rate": 1.639867690233653e-05, + "loss": 0.2656, + "step": 3397 + }, + { + "epoch": 3.01, + "learning_rate": 1.6396474042041867e-05, + "loss": 0.2958, + "step": 3398 + }, + { + "epoch": 3.01, + "learning_rate": 1.639427065628676e-05, + "loss": 0.2677, + "step": 3399 + }, + { + "epoch": 3.01, + "learning_rate": 1.6392066745252213e-05, + "loss": 0.2762, + "step": 3400 + }, + { + "epoch": 3.01, + "learning_rate": 1.6389862309119273e-05, + "loss": 0.2715, + "step": 3401 + }, + { + "epoch": 3.01, + "learning_rate": 1.6387657348069035e-05, + "loss": 0.2634, + "step": 3402 + }, + { + "epoch": 3.01, + "learning_rate": 1.6385451862282627e-05, + "loss": 0.2883, + "step": 3403 + }, + { + "epoch": 3.01, + "learning_rate": 1.6383245851941235e-05, + "loss": 0.2722, + "step": 3404 + }, + { + "epoch": 3.01, + "learning_rate": 1.6381039317226068e-05, + "loss": 0.2788, + "step": 3405 + }, + { + "epoch": 3.01, + "learning_rate": 1.63788322583184e-05, + "loss": 0.2927, + "step": 3406 + }, + { + "epoch": 3.01, + "learning_rate": 1.637662467539953e-05, + "loss": 0.2711, + "step": 3407 + }, + { + "epoch": 3.01, + "learning_rate": 1.6374416568650813e-05, + "loss": 0.2637, + "step": 3408 + }, + { + "epoch": 3.02, + "learning_rate": 1.6372207938253637e-05, + "loss": 0.2886, + "step": 3409 + }, + { + "epoch": 3.02, + "learning_rate": 1.6369998784389442e-05, + "loss": 0.289, + "step": 3410 + }, + { + "epoch": 3.02, + "learning_rate": 1.6367789107239703e-05, + "loss": 0.2875, + "step": 3411 + }, + { + "epoch": 3.02, + "learning_rate": 1.636557890698594e-05, + "loss": 0.2795, + "step": 3412 + }, + { + "epoch": 3.02, + "learning_rate": 1.6363368183809723e-05, + "loss": 0.2858, + "step": 3413 + }, + { + "epoch": 3.02, + "learning_rate": 1.636115693789266e-05, + "loss": 0.2623, + "step": 3414 + }, + { + "epoch": 3.02, + "learning_rate": 1.635894516941639e-05, + "loss": 0.2894, + "step": 3415 + }, + { + "epoch": 3.02, + "learning_rate": 1.635673287856262e-05, + "loss": 0.2632, + "step": 3416 + }, + { + "epoch": 3.02, + "learning_rate": 1.635452006551308e-05, + "loss": 0.2677, + "step": 3417 + }, + { + "epoch": 3.02, + "learning_rate": 1.635230673044955e-05, + "loss": 0.2745, + "step": 3418 + }, + { + "epoch": 3.02, + "learning_rate": 1.635009287355385e-05, + "loss": 0.2608, + "step": 3419 + }, + { + "epoch": 3.03, + "learning_rate": 1.634787849500785e-05, + "loss": 0.2672, + "step": 3420 + }, + { + "epoch": 3.03, + "learning_rate": 1.6345663594993453e-05, + "loss": 0.2874, + "step": 3421 + }, + { + "epoch": 3.03, + "learning_rate": 1.634344817369261e-05, + "loss": 0.296, + "step": 3422 + }, + { + "epoch": 3.03, + "learning_rate": 1.634123223128732e-05, + "loss": 0.2867, + "step": 3423 + }, + { + "epoch": 3.03, + "learning_rate": 1.633901576795961e-05, + "loss": 0.2749, + "step": 3424 + }, + { + "epoch": 3.03, + "learning_rate": 1.6336798783891564e-05, + "loss": 0.2654, + "step": 3425 + }, + { + "epoch": 3.03, + "learning_rate": 1.633458127926531e-05, + "loss": 0.2836, + "step": 3426 + }, + { + "epoch": 3.03, + "learning_rate": 1.6332363254263e-05, + "loss": 0.2787, + "step": 3427 + }, + { + "epoch": 3.03, + "learning_rate": 1.633014470906685e-05, + "loss": 0.2802, + "step": 3428 + }, + { + "epoch": 3.03, + "learning_rate": 1.632792564385911e-05, + "loss": 0.2812, + "step": 3429 + }, + { + "epoch": 3.03, + "learning_rate": 1.6325706058822066e-05, + "loss": 0.2756, + "step": 3430 + }, + { + "epoch": 3.04, + "learning_rate": 1.6323485954138064e-05, + "loss": 0.2733, + "step": 3431 + }, + { + "epoch": 3.04, + "learning_rate": 1.6321265329989467e-05, + "loss": 0.2896, + "step": 3432 + }, + { + "epoch": 3.04, + "learning_rate": 1.6319044186558713e-05, + "loss": 0.2664, + "step": 3433 + }, + { + "epoch": 3.04, + "learning_rate": 1.6316822524028255e-05, + "loss": 0.2773, + "step": 3434 + }, + { + "epoch": 3.04, + "learning_rate": 1.6314600342580603e-05, + "loss": 0.2832, + "step": 3435 + }, + { + "epoch": 3.04, + "learning_rate": 1.6312377642398302e-05, + "loss": 0.2773, + "step": 3436 + }, + { + "epoch": 3.04, + "learning_rate": 1.6310154423663948e-05, + "loss": 0.2591, + "step": 3437 + }, + { + "epoch": 3.04, + "learning_rate": 1.6307930686560172e-05, + "loss": 0.2813, + "step": 3438 + }, + { + "epoch": 3.04, + "learning_rate": 1.630570643126965e-05, + "loss": 0.2726, + "step": 3439 + }, + { + "epoch": 3.04, + "learning_rate": 1.6303481657975104e-05, + "loss": 0.259, + "step": 3440 + }, + { + "epoch": 3.04, + "learning_rate": 1.6301256366859296e-05, + "loss": 0.2853, + "step": 3441 + }, + { + "epoch": 3.04, + "learning_rate": 1.629903055810502e-05, + "loss": 0.2789, + "step": 3442 + }, + { + "epoch": 3.05, + "learning_rate": 1.629680423189514e-05, + "loss": 0.2843, + "step": 3443 + }, + { + "epoch": 3.05, + "learning_rate": 1.6294577388412537e-05, + "loss": 0.2873, + "step": 3444 + }, + { + "epoch": 3.05, + "learning_rate": 1.6292350027840137e-05, + "loss": 0.2838, + "step": 3445 + }, + { + "epoch": 3.05, + "learning_rate": 1.629012215036092e-05, + "loss": 0.2622, + "step": 3446 + }, + { + "epoch": 3.05, + "learning_rate": 1.6287893756157904e-05, + "loss": 0.258, + "step": 3447 + }, + { + "epoch": 3.05, + "learning_rate": 1.6285664845414146e-05, + "loss": 0.2736, + "step": 3448 + }, + { + "epoch": 3.05, + "learning_rate": 1.6283435418312743e-05, + "loss": 0.2807, + "step": 3449 + }, + { + "epoch": 3.05, + "learning_rate": 1.628120547503685e-05, + "loss": 0.271, + "step": 3450 + }, + { + "epoch": 3.05, + "learning_rate": 1.6278975015769645e-05, + "loss": 0.2551, + "step": 3451 + }, + { + "epoch": 3.05, + "learning_rate": 1.6276744040694356e-05, + "loss": 0.2808, + "step": 3452 + }, + { + "epoch": 3.05, + "learning_rate": 1.6274512549994262e-05, + "loss": 0.2687, + "step": 3453 + }, + { + "epoch": 3.06, + "learning_rate": 1.627228054385267e-05, + "loss": 0.2519, + "step": 3454 + }, + { + "epoch": 3.06, + "learning_rate": 1.6270048022452932e-05, + "loss": 0.2712, + "step": 3455 + }, + { + "epoch": 3.06, + "learning_rate": 1.6267814985978462e-05, + "loss": 0.2736, + "step": 3456 + }, + { + "epoch": 3.06, + "learning_rate": 1.626558143461268e-05, + "loss": 0.266, + "step": 3457 + }, + { + "epoch": 3.06, + "learning_rate": 1.6263347368539084e-05, + "loss": 0.2594, + "step": 3458 + }, + { + "epoch": 3.06, + "learning_rate": 1.6261112787941193e-05, + "loss": 0.2885, + "step": 3459 + }, + { + "epoch": 3.06, + "learning_rate": 1.6258877693002576e-05, + "loss": 0.2938, + "step": 3460 + }, + { + "epoch": 3.06, + "learning_rate": 1.625664208390684e-05, + "loss": 0.2794, + "step": 3461 + }, + { + "epoch": 3.06, + "learning_rate": 1.625440596083764e-05, + "loss": 0.2976, + "step": 3462 + }, + { + "epoch": 3.06, + "learning_rate": 1.625216932397867e-05, + "loss": 0.2837, + "step": 3463 + }, + { + "epoch": 3.06, + "learning_rate": 1.6249932173513662e-05, + "loss": 0.2631, + "step": 3464 + }, + { + "epoch": 3.07, + "learning_rate": 1.62476945096264e-05, + "loss": 0.2736, + "step": 3465 + }, + { + "epoch": 3.07, + "learning_rate": 1.62454563325007e-05, + "loss": 0.2871, + "step": 3466 + }, + { + "epoch": 3.07, + "learning_rate": 1.624321764232043e-05, + "loss": 0.2687, + "step": 3467 + }, + { + "epoch": 3.07, + "learning_rate": 1.6240978439269486e-05, + "loss": 0.2885, + "step": 3468 + }, + { + "epoch": 3.07, + "learning_rate": 1.6238738723531825e-05, + "loss": 0.2864, + "step": 3469 + }, + { + "epoch": 3.07, + "learning_rate": 1.6236498495291434e-05, + "loss": 0.2966, + "step": 3470 + }, + { + "epoch": 3.07, + "learning_rate": 1.623425775473234e-05, + "loss": 0.2776, + "step": 3471 + }, + { + "epoch": 3.07, + "learning_rate": 1.6232016502038617e-05, + "loss": 0.2856, + "step": 3472 + }, + { + "epoch": 3.07, + "learning_rate": 1.6229774737394382e-05, + "loss": 0.2842, + "step": 3473 + }, + { + "epoch": 3.07, + "learning_rate": 1.6227532460983795e-05, + "loss": 0.2748, + "step": 3474 + }, + { + "epoch": 3.07, + "learning_rate": 1.6225289672991053e-05, + "loss": 0.2972, + "step": 3475 + }, + { + "epoch": 3.07, + "learning_rate": 1.6223046373600398e-05, + "loss": 0.2665, + "step": 3476 + }, + { + "epoch": 3.08, + "learning_rate": 1.622080256299611e-05, + "loss": 0.297, + "step": 3477 + }, + { + "epoch": 3.08, + "learning_rate": 1.6218558241362522e-05, + "loss": 0.2695, + "step": 3478 + }, + { + "epoch": 3.08, + "learning_rate": 1.6216313408883995e-05, + "loss": 0.2751, + "step": 3479 + }, + { + "epoch": 3.08, + "learning_rate": 1.6214068065744943e-05, + "loss": 0.278, + "step": 3480 + }, + { + "epoch": 3.08, + "learning_rate": 1.621182221212981e-05, + "loss": 0.275, + "step": 3481 + }, + { + "epoch": 3.08, + "learning_rate": 1.62095758482231e-05, + "loss": 0.3093, + "step": 3482 + }, + { + "epoch": 3.08, + "learning_rate": 1.6207328974209343e-05, + "loss": 0.2761, + "step": 3483 + }, + { + "epoch": 3.08, + "learning_rate": 1.6205081590273113e-05, + "loss": 0.2749, + "step": 3484 + }, + { + "epoch": 3.08, + "learning_rate": 1.6202833696599036e-05, + "loss": 0.2882, + "step": 3485 + }, + { + "epoch": 3.08, + "learning_rate": 1.620058529337177e-05, + "loss": 0.2832, + "step": 3486 + }, + { + "epoch": 3.08, + "learning_rate": 1.6198336380776013e-05, + "loss": 0.2639, + "step": 3487 + }, + { + "epoch": 3.09, + "learning_rate": 1.6196086958996517e-05, + "loss": 0.2776, + "step": 3488 + }, + { + "epoch": 3.09, + "learning_rate": 1.6193837028218064e-05, + "loss": 0.2723, + "step": 3489 + }, + { + "epoch": 3.09, + "learning_rate": 1.6191586588625487e-05, + "loss": 0.2656, + "step": 3490 + }, + { + "epoch": 3.09, + "learning_rate": 1.618933564040365e-05, + "loss": 0.2702, + "step": 3491 + }, + { + "epoch": 3.09, + "learning_rate": 1.6187084183737468e-05, + "loss": 0.2788, + "step": 3492 + }, + { + "epoch": 3.09, + "learning_rate": 1.6184832218811896e-05, + "loss": 0.2637, + "step": 3493 + }, + { + "epoch": 3.09, + "learning_rate": 1.6182579745811923e-05, + "loss": 0.2534, + "step": 3494 + }, + { + "epoch": 3.09, + "learning_rate": 1.6180326764922596e-05, + "loss": 0.2637, + "step": 3495 + }, + { + "epoch": 3.09, + "learning_rate": 1.6178073276328988e-05, + "loss": 0.285, + "step": 3496 + }, + { + "epoch": 3.09, + "learning_rate": 1.617581928021622e-05, + "loss": 0.2827, + "step": 3497 + }, + { + "epoch": 3.09, + "learning_rate": 1.6173564776769455e-05, + "loss": 0.2869, + "step": 3498 + }, + { + "epoch": 3.1, + "learning_rate": 1.6171309766173898e-05, + "loss": 0.2822, + "step": 3499 + }, + { + "epoch": 3.1, + "learning_rate": 1.6169054248614793e-05, + "loss": 0.2885, + "step": 3500 + }, + { + "epoch": 3.1, + "learning_rate": 1.6166798224277428e-05, + "loss": 0.2939, + "step": 3501 + }, + { + "epoch": 3.1, + "learning_rate": 1.616454169334713e-05, + "loss": 0.2738, + "step": 3502 + }, + { + "epoch": 3.1, + "learning_rate": 1.6162284656009276e-05, + "loss": 0.2686, + "step": 3503 + }, + { + "epoch": 3.1, + "learning_rate": 1.6160027112449267e-05, + "loss": 0.2898, + "step": 3504 + }, + { + "epoch": 3.1, + "learning_rate": 1.6157769062852567e-05, + "loss": 0.2799, + "step": 3505 + }, + { + "epoch": 3.1, + "learning_rate": 1.6155510507404667e-05, + "loss": 0.2673, + "step": 3506 + }, + { + "epoch": 3.1, + "learning_rate": 1.6153251446291105e-05, + "loss": 0.2755, + "step": 3507 + }, + { + "epoch": 3.1, + "learning_rate": 1.6150991879697455e-05, + "loss": 0.2756, + "step": 3508 + }, + { + "epoch": 3.1, + "learning_rate": 1.6148731807809347e-05, + "loss": 0.2806, + "step": 3509 + }, + { + "epoch": 3.1, + "learning_rate": 1.614647123081243e-05, + "loss": 0.2826, + "step": 3510 + }, + { + "epoch": 3.11, + "learning_rate": 1.614421014889241e-05, + "loss": 0.2768, + "step": 3511 + }, + { + "epoch": 3.11, + "learning_rate": 1.6141948562235042e-05, + "loss": 0.2738, + "step": 3512 + }, + { + "epoch": 3.11, + "learning_rate": 1.61396864710261e-05, + "loss": 0.2833, + "step": 3513 + }, + { + "epoch": 3.11, + "learning_rate": 1.6137423875451416e-05, + "loss": 0.2727, + "step": 3514 + }, + { + "epoch": 3.11, + "learning_rate": 1.6135160775696857e-05, + "loss": 0.2633, + "step": 3515 + }, + { + "epoch": 3.11, + "learning_rate": 1.6132897171948337e-05, + "loss": 0.2393, + "step": 3516 + }, + { + "epoch": 3.11, + "learning_rate": 1.6130633064391802e-05, + "loss": 0.2977, + "step": 3517 + }, + { + "epoch": 3.11, + "learning_rate": 1.6128368453213248e-05, + "loss": 0.2804, + "step": 3518 + }, + { + "epoch": 3.11, + "learning_rate": 1.612610333859871e-05, + "loss": 0.2787, + "step": 3519 + }, + { + "epoch": 3.11, + "learning_rate": 1.612383772073426e-05, + "loss": 0.2794, + "step": 3520 + }, + { + "epoch": 3.11, + "learning_rate": 1.612157159980602e-05, + "loss": 0.2773, + "step": 3521 + }, + { + "epoch": 3.12, + "learning_rate": 1.611930497600015e-05, + "loss": 0.289, + "step": 3522 + }, + { + "epoch": 3.12, + "learning_rate": 1.6117037849502834e-05, + "loss": 0.3022, + "step": 3523 + }, + { + "epoch": 3.12, + "learning_rate": 1.6114770220500333e-05, + "loss": 0.2816, + "step": 3524 + }, + { + "epoch": 3.12, + "learning_rate": 1.611250208917892e-05, + "loss": 0.2853, + "step": 3525 + }, + { + "epoch": 3.12, + "learning_rate": 1.611023345572492e-05, + "loss": 0.2841, + "step": 3526 + }, + { + "epoch": 3.12, + "learning_rate": 1.6107964320324693e-05, + "loss": 0.2812, + "step": 3527 + }, + { + "epoch": 3.12, + "learning_rate": 1.6105694683164653e-05, + "loss": 0.2597, + "step": 3528 + }, + { + "epoch": 3.12, + "learning_rate": 1.610342454443124e-05, + "loss": 0.2778, + "step": 3529 + }, + { + "epoch": 3.12, + "learning_rate": 1.6101153904310947e-05, + "loss": 0.2904, + "step": 3530 + }, + { + "epoch": 3.12, + "learning_rate": 1.60988827629903e-05, + "loss": 0.2756, + "step": 3531 + }, + { + "epoch": 3.12, + "learning_rate": 1.6096611120655877e-05, + "loss": 0.266, + "step": 3532 + }, + { + "epoch": 3.13, + "learning_rate": 1.609433897749428e-05, + "loss": 0.2624, + "step": 3533 + }, + { + "epoch": 3.13, + "learning_rate": 1.609206633369217e-05, + "loss": 0.2926, + "step": 3534 + }, + { + "epoch": 3.13, + "learning_rate": 1.6089793189436232e-05, + "loss": 0.2769, + "step": 3535 + }, + { + "epoch": 3.13, + "learning_rate": 1.6087519544913212e-05, + "loss": 0.2861, + "step": 3536 + }, + { + "epoch": 3.13, + "learning_rate": 1.608524540030988e-05, + "loss": 0.2644, + "step": 3537 + }, + { + "epoch": 3.13, + "learning_rate": 1.6082970755813055e-05, + "loss": 0.2604, + "step": 3538 + }, + { + "epoch": 3.13, + "learning_rate": 1.6080695611609596e-05, + "loss": 0.2822, + "step": 3539 + }, + { + "epoch": 3.13, + "learning_rate": 1.6078419967886402e-05, + "loss": 0.2755, + "step": 3540 + }, + { + "epoch": 3.13, + "learning_rate": 1.6076143824830416e-05, + "loss": 0.2785, + "step": 3541 + }, + { + "epoch": 3.13, + "learning_rate": 1.6073867182628613e-05, + "loss": 0.2826, + "step": 3542 + }, + { + "epoch": 3.13, + "learning_rate": 1.6071590041468022e-05, + "loss": 0.2693, + "step": 3543 + }, + { + "epoch": 3.14, + "learning_rate": 1.6069312401535703e-05, + "loss": 0.2736, + "step": 3544 + }, + { + "epoch": 3.14, + "learning_rate": 1.6067034263018767e-05, + "loss": 0.2887, + "step": 3545 + }, + { + "epoch": 3.14, + "learning_rate": 1.6064755626104348e-05, + "loss": 0.2679, + "step": 3546 + }, + { + "epoch": 3.14, + "learning_rate": 1.6062476490979644e-05, + "loss": 0.2914, + "step": 3547 + }, + { + "epoch": 3.14, + "learning_rate": 1.606019685783188e-05, + "loss": 0.2639, + "step": 3548 + }, + { + "epoch": 3.14, + "learning_rate": 1.6057916726848314e-05, + "loss": 0.2535, + "step": 3549 + }, + { + "epoch": 3.14, + "learning_rate": 1.6055636098216273e-05, + "loss": 0.2767, + "step": 3550 + }, + { + "epoch": 3.14, + "learning_rate": 1.605335497212309e-05, + "loss": 0.2821, + "step": 3551 + }, + { + "epoch": 3.14, + "learning_rate": 1.6051073348756166e-05, + "loss": 0.2839, + "step": 3552 + }, + { + "epoch": 3.14, + "learning_rate": 1.6048791228302928e-05, + "loss": 0.2662, + "step": 3553 + }, + { + "epoch": 3.14, + "learning_rate": 1.6046508610950856e-05, + "loss": 0.2801, + "step": 3554 + }, + { + "epoch": 3.14, + "learning_rate": 1.6044225496887453e-05, + "loss": 0.2661, + "step": 3555 + }, + { + "epoch": 3.15, + "learning_rate": 1.604194188630028e-05, + "loss": 0.2625, + "step": 3556 + }, + { + "epoch": 3.15, + "learning_rate": 1.603965777937693e-05, + "loss": 0.3091, + "step": 3557 + }, + { + "epoch": 3.15, + "learning_rate": 1.6037373176305042e-05, + "loss": 0.2838, + "step": 3558 + }, + { + "epoch": 3.15, + "learning_rate": 1.603508807727229e-05, + "loss": 0.286, + "step": 3559 + }, + { + "epoch": 3.15, + "learning_rate": 1.6032802482466388e-05, + "loss": 0.2836, + "step": 3560 + }, + { + "epoch": 3.15, + "learning_rate": 1.60305163920751e-05, + "loss": 0.2788, + "step": 3561 + }, + { + "epoch": 3.15, + "learning_rate": 1.6028229806286223e-05, + "loss": 0.2813, + "step": 3562 + }, + { + "epoch": 3.15, + "learning_rate": 1.6025942725287594e-05, + "loss": 0.2699, + "step": 3563 + }, + { + "epoch": 3.15, + "learning_rate": 1.6023655149267098e-05, + "loss": 0.287, + "step": 3564 + }, + { + "epoch": 3.15, + "learning_rate": 1.602136707841265e-05, + "loss": 0.2812, + "step": 3565 + }, + { + "epoch": 3.15, + "learning_rate": 1.6019078512912213e-05, + "loss": 0.2631, + "step": 3566 + }, + { + "epoch": 3.16, + "learning_rate": 1.6016789452953795e-05, + "loss": 0.298, + "step": 3567 + }, + { + "epoch": 3.16, + "learning_rate": 1.601449989872543e-05, + "loss": 0.2961, + "step": 3568 + }, + { + "epoch": 3.16, + "learning_rate": 1.6012209850415204e-05, + "loss": 0.2888, + "step": 3569 + }, + { + "epoch": 3.16, + "learning_rate": 1.6009919308211247e-05, + "loss": 0.2531, + "step": 3570 + }, + { + "epoch": 3.16, + "learning_rate": 1.600762827230172e-05, + "loss": 0.2944, + "step": 3571 + }, + { + "epoch": 3.16, + "learning_rate": 1.6005336742874823e-05, + "loss": 0.2634, + "step": 3572 + }, + { + "epoch": 3.16, + "learning_rate": 1.600304472011881e-05, + "loss": 0.3044, + "step": 3573 + }, + { + "epoch": 3.16, + "learning_rate": 1.6000752204221957e-05, + "loss": 0.2874, + "step": 3574 + }, + { + "epoch": 3.16, + "learning_rate": 1.59984591953726e-05, + "loss": 0.2917, + "step": 3575 + }, + { + "epoch": 3.16, + "learning_rate": 1.5996165693759102e-05, + "loss": 0.2667, + "step": 3576 + }, + { + "epoch": 3.16, + "learning_rate": 1.5993871699569868e-05, + "loss": 0.2963, + "step": 3577 + }, + { + "epoch": 3.17, + "learning_rate": 1.599157721299335e-05, + "loss": 0.2655, + "step": 3578 + }, + { + "epoch": 3.17, + "learning_rate": 1.5989282234218037e-05, + "loss": 0.2884, + "step": 3579 + }, + { + "epoch": 3.17, + "learning_rate": 1.598698676343246e-05, + "loss": 0.2998, + "step": 3580 + }, + { + "epoch": 3.17, + "learning_rate": 1.598469080082518e-05, + "loss": 0.2769, + "step": 3581 + }, + { + "epoch": 3.17, + "learning_rate": 1.5982394346584813e-05, + "loss": 0.2879, + "step": 3582 + }, + { + "epoch": 3.17, + "learning_rate": 1.598009740090001e-05, + "loss": 0.2814, + "step": 3583 + }, + { + "epoch": 3.17, + "learning_rate": 1.5977799963959458e-05, + "loss": 0.2834, + "step": 3584 + }, + { + "epoch": 3.17, + "learning_rate": 1.597550203595189e-05, + "loss": 0.2851, + "step": 3585 + }, + { + "epoch": 3.17, + "learning_rate": 1.5973203617066073e-05, + "loss": 0.2757, + "step": 3586 + }, + { + "epoch": 3.17, + "learning_rate": 1.5970904707490826e-05, + "loss": 0.282, + "step": 3587 + }, + { + "epoch": 3.17, + "learning_rate": 1.5968605307414994e-05, + "loss": 0.2782, + "step": 3588 + }, + { + "epoch": 3.17, + "learning_rate": 1.5966305417027473e-05, + "loss": 0.2535, + "step": 3589 + }, + { + "epoch": 3.18, + "learning_rate": 1.59640050365172e-05, + "loss": 0.2772, + "step": 3590 + }, + { + "epoch": 3.18, + "learning_rate": 1.5961704166073136e-05, + "loss": 0.2813, + "step": 3591 + }, + { + "epoch": 3.18, + "learning_rate": 1.59594028058843e-05, + "loss": 0.2964, + "step": 3592 + }, + { + "epoch": 3.18, + "learning_rate": 1.595710095613975e-05, + "loss": 0.2713, + "step": 3593 + }, + { + "epoch": 3.18, + "learning_rate": 1.5954798617028573e-05, + "loss": 0.2799, + "step": 3594 + }, + { + "epoch": 3.18, + "learning_rate": 1.5952495788739902e-05, + "loss": 0.2646, + "step": 3595 + }, + { + "epoch": 3.18, + "learning_rate": 1.5950192471462916e-05, + "loss": 0.2855, + "step": 3596 + }, + { + "epoch": 3.18, + "learning_rate": 1.5947888665386827e-05, + "loss": 0.3073, + "step": 3597 + }, + { + "epoch": 3.18, + "learning_rate": 1.5945584370700884e-05, + "loss": 0.2999, + "step": 3598 + }, + { + "epoch": 3.18, + "learning_rate": 1.594327958759439e-05, + "loss": 0.2784, + "step": 3599 + }, + { + "epoch": 3.18, + "learning_rate": 1.594097431625667e-05, + "loss": 0.2713, + "step": 3600 + }, + { + "epoch": 3.19, + "learning_rate": 1.5938668556877105e-05, + "loss": 0.3052, + "step": 3601 + }, + { + "epoch": 3.19, + "learning_rate": 1.593636230964511e-05, + "loss": 0.2816, + "step": 3602 + }, + { + "epoch": 3.19, + "learning_rate": 1.5934055574750135e-05, + "loss": 0.281, + "step": 3603 + }, + { + "epoch": 3.19, + "learning_rate": 1.593174835238168e-05, + "loss": 0.2756, + "step": 3604 + }, + { + "epoch": 3.19, + "learning_rate": 1.592944064272927e-05, + "loss": 0.3024, + "step": 3605 + }, + { + "epoch": 3.19, + "learning_rate": 1.5927132445982497e-05, + "loss": 0.2575, + "step": 3606 + }, + { + "epoch": 3.19, + "learning_rate": 1.592482376233096e-05, + "loss": 0.2791, + "step": 3607 + }, + { + "epoch": 3.19, + "learning_rate": 1.5922514591964317e-05, + "loss": 0.2775, + "step": 3608 + }, + { + "epoch": 3.19, + "learning_rate": 1.592020493507227e-05, + "loss": 0.2786, + "step": 3609 + }, + { + "epoch": 3.19, + "learning_rate": 1.591789479184455e-05, + "loss": 0.2769, + "step": 3610 + }, + { + "epoch": 3.19, + "learning_rate": 1.5915584162470925e-05, + "loss": 0.2866, + "step": 3611 + }, + { + "epoch": 3.2, + "learning_rate": 1.5913273047141217e-05, + "loss": 0.2756, + "step": 3612 + }, + { + "epoch": 3.2, + "learning_rate": 1.5910961446045277e-05, + "loss": 0.2699, + "step": 3613 + }, + { + "epoch": 3.2, + "learning_rate": 1.5908649359373006e-05, + "loss": 0.2885, + "step": 3614 + }, + { + "epoch": 3.2, + "learning_rate": 1.5906336787314328e-05, + "loss": 0.2538, + "step": 3615 + }, + { + "epoch": 3.2, + "learning_rate": 1.5904023730059227e-05, + "loss": 0.2969, + "step": 3616 + }, + { + "epoch": 3.2, + "learning_rate": 1.5901710187797716e-05, + "loss": 0.2723, + "step": 3617 + }, + { + "epoch": 3.2, + "learning_rate": 1.5899396160719834e-05, + "loss": 0.2719, + "step": 3618 + }, + { + "epoch": 3.2, + "learning_rate": 1.5897081649015698e-05, + "loss": 0.287, + "step": 3619 + }, + { + "epoch": 3.2, + "learning_rate": 1.5894766652875424e-05, + "loss": 0.2798, + "step": 3620 + }, + { + "epoch": 3.2, + "learning_rate": 1.5892451172489193e-05, + "loss": 0.2887, + "step": 3621 + }, + { + "epoch": 3.2, + "learning_rate": 1.5890135208047217e-05, + "loss": 0.2752, + "step": 3622 + }, + { + "epoch": 3.2, + "learning_rate": 1.5887818759739747e-05, + "loss": 0.2851, + "step": 3623 + }, + { + "epoch": 3.21, + "learning_rate": 1.5885501827757078e-05, + "loss": 0.2716, + "step": 3624 + }, + { + "epoch": 3.21, + "learning_rate": 1.588318441228954e-05, + "loss": 0.2749, + "step": 3625 + }, + { + "epoch": 3.21, + "learning_rate": 1.588086651352751e-05, + "loss": 0.281, + "step": 3626 + }, + { + "epoch": 3.21, + "learning_rate": 1.587854813166139e-05, + "loss": 0.2711, + "step": 3627 + }, + { + "epoch": 3.21, + "learning_rate": 1.587622926688164e-05, + "loss": 0.2837, + "step": 3628 + }, + { + "epoch": 3.21, + "learning_rate": 1.5873909919378755e-05, + "loss": 0.2819, + "step": 3629 + }, + { + "epoch": 3.21, + "learning_rate": 1.5871590089343255e-05, + "loss": 0.2919, + "step": 3630 + }, + { + "epoch": 3.21, + "learning_rate": 1.5869269776965714e-05, + "loss": 0.2853, + "step": 3631 + }, + { + "epoch": 3.21, + "learning_rate": 1.5866948982436748e-05, + "loss": 0.2719, + "step": 3632 + }, + { + "epoch": 3.21, + "learning_rate": 1.5864627705946997e-05, + "loss": 0.2911, + "step": 3633 + }, + { + "epoch": 3.21, + "learning_rate": 1.5862305947687156e-05, + "loss": 0.2726, + "step": 3634 + }, + { + "epoch": 3.22, + "learning_rate": 1.5859983707847955e-05, + "loss": 0.2637, + "step": 3635 + }, + { + "epoch": 3.22, + "learning_rate": 1.585766098662016e-05, + "loss": 0.2873, + "step": 3636 + }, + { + "epoch": 3.22, + "learning_rate": 1.5855337784194576e-05, + "loss": 0.2827, + "step": 3637 + }, + { + "epoch": 3.22, + "learning_rate": 1.5853014100762057e-05, + "loss": 0.2799, + "step": 3638 + }, + { + "epoch": 3.22, + "learning_rate": 1.5850689936513488e-05, + "loss": 0.297, + "step": 3639 + }, + { + "epoch": 3.22, + "learning_rate": 1.5848365291639793e-05, + "loss": 0.2811, + "step": 3640 + }, + { + "epoch": 3.22, + "learning_rate": 1.5846040166331938e-05, + "loss": 0.2736, + "step": 3641 + }, + { + "epoch": 3.22, + "learning_rate": 1.584371456078093e-05, + "loss": 0.2849, + "step": 3642 + }, + { + "epoch": 3.22, + "learning_rate": 1.5841388475177817e-05, + "loss": 0.2858, + "step": 3643 + }, + { + "epoch": 3.22, + "learning_rate": 1.583906190971368e-05, + "loss": 0.2824, + "step": 3644 + }, + { + "epoch": 3.22, + "learning_rate": 1.5836734864579638e-05, + "loss": 0.2892, + "step": 3645 + }, + { + "epoch": 3.23, + "learning_rate": 1.5834407339966863e-05, + "loss": 0.2727, + "step": 3646 + }, + { + "epoch": 3.23, + "learning_rate": 1.583207933606655e-05, + "loss": 0.2877, + "step": 3647 + }, + { + "epoch": 3.23, + "learning_rate": 1.5829750853069946e-05, + "loss": 0.2887, + "step": 3648 + }, + { + "epoch": 3.23, + "learning_rate": 1.5827421891168335e-05, + "loss": 0.2949, + "step": 3649 + }, + { + "epoch": 3.23, + "learning_rate": 1.5825092450553027e-05, + "loss": 0.2793, + "step": 3650 + }, + { + "epoch": 3.23, + "learning_rate": 1.5822762531415393e-05, + "loss": 0.2804, + "step": 3651 + }, + { + "epoch": 3.23, + "learning_rate": 1.5820432133946825e-05, + "loss": 0.2615, + "step": 3652 + }, + { + "epoch": 3.23, + "learning_rate": 1.5818101258338764e-05, + "loss": 0.2741, + "step": 3653 + }, + { + "epoch": 3.23, + "learning_rate": 1.581576990478269e-05, + "loss": 0.2674, + "step": 3654 + }, + { + "epoch": 3.23, + "learning_rate": 1.5813438073470114e-05, + "loss": 0.2841, + "step": 3655 + }, + { + "epoch": 3.23, + "learning_rate": 1.5811105764592598e-05, + "loss": 0.2501, + "step": 3656 + }, + { + "epoch": 3.24, + "learning_rate": 1.5808772978341736e-05, + "loss": 0.2964, + "step": 3657 + }, + { + "epoch": 3.24, + "learning_rate": 1.5806439714909165e-05, + "loss": 0.274, + "step": 3658 + }, + { + "epoch": 3.24, + "learning_rate": 1.5804105974486554e-05, + "loss": 0.2838, + "step": 3659 + }, + { + "epoch": 3.24, + "learning_rate": 1.5801771757265618e-05, + "loss": 0.2773, + "step": 3660 + }, + { + "epoch": 3.24, + "learning_rate": 1.5799437063438114e-05, + "loss": 0.287, + "step": 3661 + }, + { + "epoch": 3.24, + "learning_rate": 1.5797101893195827e-05, + "loss": 0.2692, + "step": 3662 + }, + { + "epoch": 3.24, + "learning_rate": 1.5794766246730588e-05, + "loss": 0.2731, + "step": 3663 + }, + { + "epoch": 3.24, + "learning_rate": 1.5792430124234272e-05, + "loss": 0.2576, + "step": 3664 + }, + { + "epoch": 3.24, + "learning_rate": 1.5790093525898783e-05, + "loss": 0.2585, + "step": 3665 + }, + { + "epoch": 3.24, + "learning_rate": 1.5787756451916077e-05, + "loss": 0.2616, + "step": 3666 + }, + { + "epoch": 3.24, + "learning_rate": 1.5785418902478127e-05, + "loss": 0.2567, + "step": 3667 + }, + { + "epoch": 3.24, + "learning_rate": 1.578308087777697e-05, + "loss": 0.278, + "step": 3668 + }, + { + "epoch": 3.25, + "learning_rate": 1.5780742378004666e-05, + "loss": 0.2768, + "step": 3669 + }, + { + "epoch": 3.25, + "learning_rate": 1.577840340335332e-05, + "loss": 0.2736, + "step": 3670 + }, + { + "epoch": 3.25, + "learning_rate": 1.5776063954015084e-05, + "loss": 0.2721, + "step": 3671 + }, + { + "epoch": 3.25, + "learning_rate": 1.577372403018213e-05, + "loss": 0.2795, + "step": 3672 + }, + { + "epoch": 3.25, + "learning_rate": 1.5771383632046674e-05, + "loss": 0.2755, + "step": 3673 + }, + { + "epoch": 3.25, + "learning_rate": 1.5769042759800987e-05, + "loss": 0.2732, + "step": 3674 + }, + { + "epoch": 3.25, + "learning_rate": 1.5766701413637368e-05, + "loss": 0.2683, + "step": 3675 + }, + { + "epoch": 3.25, + "learning_rate": 1.576435959374815e-05, + "loss": 0.2866, + "step": 3676 + }, + { + "epoch": 3.25, + "learning_rate": 1.576201730032571e-05, + "loss": 0.293, + "step": 3677 + }, + { + "epoch": 3.25, + "learning_rate": 1.5759674533562465e-05, + "loss": 0.2702, + "step": 3678 + }, + { + "epoch": 3.25, + "learning_rate": 1.5757331293650873e-05, + "loss": 0.2753, + "step": 3679 + }, + { + "epoch": 3.26, + "learning_rate": 1.575498758078342e-05, + "loss": 0.3112, + "step": 3680 + }, + { + "epoch": 3.26, + "learning_rate": 1.5752643395152647e-05, + "loss": 0.2785, + "step": 3681 + }, + { + "epoch": 3.26, + "learning_rate": 1.575029873695112e-05, + "loss": 0.2722, + "step": 3682 + }, + { + "epoch": 3.26, + "learning_rate": 1.5747953606371446e-05, + "loss": 0.2843, + "step": 3683 + }, + { + "epoch": 3.26, + "learning_rate": 1.5745608003606286e-05, + "loss": 0.2825, + "step": 3684 + }, + { + "epoch": 3.26, + "learning_rate": 1.5743261928848316e-05, + "loss": 0.2659, + "step": 3685 + }, + { + "epoch": 3.26, + "learning_rate": 1.574091538229026e-05, + "loss": 0.2747, + "step": 3686 + }, + { + "epoch": 3.26, + "learning_rate": 1.5738568364124896e-05, + "loss": 0.289, + "step": 3687 + }, + { + "epoch": 3.26, + "learning_rate": 1.573622087454502e-05, + "loss": 0.2663, + "step": 3688 + }, + { + "epoch": 3.26, + "learning_rate": 1.5733872913743472e-05, + "loss": 0.283, + "step": 3689 + }, + { + "epoch": 3.26, + "learning_rate": 1.573152448191314e-05, + "loss": 0.3062, + "step": 3690 + }, + { + "epoch": 3.27, + "learning_rate": 1.572917557924694e-05, + "loss": 0.2925, + "step": 3691 + }, + { + "epoch": 3.27, + "learning_rate": 1.5726826205937834e-05, + "loss": 0.2911, + "step": 3692 + }, + { + "epoch": 3.27, + "learning_rate": 1.5724476362178816e-05, + "loss": 0.2684, + "step": 3693 + }, + { + "epoch": 3.27, + "learning_rate": 1.572212604816292e-05, + "loss": 0.2997, + "step": 3694 + }, + { + "epoch": 3.27, + "learning_rate": 1.5719775264083233e-05, + "loss": 0.2935, + "step": 3695 + }, + { + "epoch": 3.27, + "learning_rate": 1.571742401013285e-05, + "loss": 0.2923, + "step": 3696 + }, + { + "epoch": 3.27, + "learning_rate": 1.5715072286504935e-05, + "loss": 0.2749, + "step": 3697 + }, + { + "epoch": 3.27, + "learning_rate": 1.5712720093392678e-05, + "loss": 0.2648, + "step": 3698 + }, + { + "epoch": 3.27, + "learning_rate": 1.57103674309893e-05, + "loss": 0.2746, + "step": 3699 + }, + { + "epoch": 3.27, + "learning_rate": 1.570801429948808e-05, + "loss": 0.2968, + "step": 3700 + }, + { + "epoch": 3.27, + "learning_rate": 1.5705660699082314e-05, + "loss": 0.2677, + "step": 3701 + }, + { + "epoch": 3.27, + "learning_rate": 1.570330662996535e-05, + "loss": 0.2654, + "step": 3702 + }, + { + "epoch": 3.28, + "learning_rate": 1.5700952092330575e-05, + "loss": 0.2886, + "step": 3703 + }, + { + "epoch": 3.28, + "learning_rate": 1.569859708637141e-05, + "loss": 0.2806, + "step": 3704 + }, + { + "epoch": 3.28, + "learning_rate": 1.5696241612281306e-05, + "loss": 0.2956, + "step": 3705 + }, + { + "epoch": 3.28, + "learning_rate": 1.5693885670253774e-05, + "loss": 0.2734, + "step": 3706 + }, + { + "epoch": 3.28, + "learning_rate": 1.569152926048234e-05, + "loss": 0.2675, + "step": 3707 + }, + { + "epoch": 3.28, + "learning_rate": 1.568917238316059e-05, + "loss": 0.2609, + "step": 3708 + }, + { + "epoch": 3.28, + "learning_rate": 1.5686815038482128e-05, + "loss": 0.2774, + "step": 3709 + }, + { + "epoch": 3.28, + "learning_rate": 1.5684457226640614e-05, + "loss": 0.2735, + "step": 3710 + }, + { + "epoch": 3.28, + "learning_rate": 1.5682098947829737e-05, + "loss": 0.2979, + "step": 3711 + }, + { + "epoch": 3.28, + "learning_rate": 1.567974020224322e-05, + "loss": 0.2846, + "step": 3712 + }, + { + "epoch": 3.28, + "learning_rate": 1.5677380990074835e-05, + "loss": 0.3122, + "step": 3713 + }, + { + "epoch": 3.29, + "learning_rate": 1.5675021311518385e-05, + "loss": 0.2898, + "step": 3714 + }, + { + "epoch": 3.29, + "learning_rate": 1.5672661166767723e-05, + "loss": 0.2726, + "step": 3715 + }, + { + "epoch": 3.29, + "learning_rate": 1.5670300556016717e-05, + "loss": 0.2792, + "step": 3716 + }, + { + "epoch": 3.29, + "learning_rate": 1.56679394794593e-05, + "loss": 0.2779, + "step": 3717 + }, + { + "epoch": 3.29, + "learning_rate": 1.5665577937289422e-05, + "loss": 0.2815, + "step": 3718 + }, + { + "epoch": 3.29, + "learning_rate": 1.5663215929701087e-05, + "loss": 0.272, + "step": 3719 + }, + { + "epoch": 3.29, + "learning_rate": 1.5660853456888324e-05, + "loss": 0.2953, + "step": 3720 + }, + { + "epoch": 3.29, + "learning_rate": 1.5658490519045214e-05, + "loss": 0.2669, + "step": 3721 + }, + { + "epoch": 3.29, + "learning_rate": 1.565612711636586e-05, + "loss": 0.2961, + "step": 3722 + }, + { + "epoch": 3.29, + "learning_rate": 1.5653763249044415e-05, + "loss": 0.2619, + "step": 3723 + }, + { + "epoch": 3.29, + "learning_rate": 1.565139891727507e-05, + "loss": 0.2944, + "step": 3724 + }, + { + "epoch": 3.3, + "learning_rate": 1.564903412125205e-05, + "loss": 0.2733, + "step": 3725 + }, + { + "epoch": 3.3, + "learning_rate": 1.5646668861169615e-05, + "loss": 0.2722, + "step": 3726 + }, + { + "epoch": 3.3, + "learning_rate": 1.5644303137222075e-05, + "loss": 0.2677, + "step": 3727 + }, + { + "epoch": 3.3, + "learning_rate": 1.564193694960377e-05, + "loss": 0.2858, + "step": 3728 + }, + { + "epoch": 3.3, + "learning_rate": 1.5639570298509067e-05, + "loss": 0.2687, + "step": 3729 + }, + { + "epoch": 3.3, + "learning_rate": 1.5637203184132394e-05, + "loss": 0.2658, + "step": 3730 + }, + { + "epoch": 3.3, + "learning_rate": 1.5634835606668203e-05, + "loss": 0.2821, + "step": 3731 + }, + { + "epoch": 3.3, + "learning_rate": 1.5632467566310988e-05, + "loss": 0.2965, + "step": 3732 + }, + { + "epoch": 3.3, + "learning_rate": 1.5630099063255277e-05, + "loss": 0.2719, + "step": 3733 + }, + { + "epoch": 3.3, + "learning_rate": 1.562773009769564e-05, + "loss": 0.2743, + "step": 3734 + }, + { + "epoch": 3.3, + "learning_rate": 1.5625360669826684e-05, + "loss": 0.2471, + "step": 3735 + }, + { + "epoch": 3.3, + "learning_rate": 1.5622990779843053e-05, + "loss": 0.2707, + "step": 3736 + }, + { + "epoch": 3.31, + "learning_rate": 1.5620620427939435e-05, + "loss": 0.2846, + "step": 3737 + }, + { + "epoch": 3.31, + "learning_rate": 1.5618249614310543e-05, + "loss": 0.2715, + "step": 3738 + }, + { + "epoch": 3.31, + "learning_rate": 1.561587833915114e-05, + "loss": 0.3124, + "step": 3739 + }, + { + "epoch": 3.31, + "learning_rate": 1.5613506602656022e-05, + "loss": 0.298, + "step": 3740 + }, + { + "epoch": 3.31, + "learning_rate": 1.5611134405020022e-05, + "loss": 0.2969, + "step": 3741 + }, + { + "epoch": 3.31, + "learning_rate": 1.5608761746438015e-05, + "loss": 0.29, + "step": 3742 + }, + { + "epoch": 3.31, + "learning_rate": 1.5606388627104912e-05, + "loss": 0.2917, + "step": 3743 + }, + { + "epoch": 3.31, + "learning_rate": 1.5604015047215656e-05, + "loss": 0.272, + "step": 3744 + }, + { + "epoch": 3.31, + "learning_rate": 1.5601641006965235e-05, + "loss": 0.281, + "step": 3745 + }, + { + "epoch": 3.31, + "learning_rate": 1.5599266506548673e-05, + "loss": 0.2813, + "step": 3746 + }, + { + "epoch": 3.31, + "learning_rate": 1.5596891546161036e-05, + "loss": 0.2983, + "step": 3747 + }, + { + "epoch": 3.32, + "learning_rate": 1.5594516125997416e-05, + "loss": 0.2841, + "step": 3748 + }, + { + "epoch": 3.32, + "learning_rate": 1.5592140246252954e-05, + "loss": 0.2617, + "step": 3749 + }, + { + "epoch": 3.32, + "learning_rate": 1.5589763907122826e-05, + "loss": 0.2624, + "step": 3750 + }, + { + "epoch": 3.32, + "learning_rate": 1.558738710880224e-05, + "loss": 0.2817, + "step": 3751 + }, + { + "epoch": 3.32, + "learning_rate": 1.5585009851486455e-05, + "loss": 0.2717, + "step": 3752 + }, + { + "epoch": 3.32, + "learning_rate": 1.558263213537075e-05, + "loss": 0.286, + "step": 3753 + }, + { + "epoch": 3.32, + "learning_rate": 1.5580253960650452e-05, + "loss": 0.282, + "step": 3754 + }, + { + "epoch": 3.32, + "learning_rate": 1.5577875327520926e-05, + "loss": 0.2562, + "step": 3755 + }, + { + "epoch": 3.32, + "learning_rate": 1.557549623617758e-05, + "loss": 0.2751, + "step": 3756 + }, + { + "epoch": 3.32, + "learning_rate": 1.5573116686815837e-05, + "loss": 0.2831, + "step": 3757 + }, + { + "epoch": 3.32, + "learning_rate": 1.5570736679631185e-05, + "loss": 0.2667, + "step": 3758 + }, + { + "epoch": 3.33, + "learning_rate": 1.556835621481914e-05, + "loss": 0.2856, + "step": 3759 + }, + { + "epoch": 3.33, + "learning_rate": 1.5565975292575247e-05, + "loss": 0.2924, + "step": 3760 + }, + { + "epoch": 3.33, + "learning_rate": 1.5563593913095095e-05, + "loss": 0.2687, + "step": 3761 + }, + { + "epoch": 3.33, + "learning_rate": 1.556121207657431e-05, + "loss": 0.2689, + "step": 3762 + }, + { + "epoch": 3.33, + "learning_rate": 1.555882978320856e-05, + "loss": 0.2613, + "step": 3763 + }, + { + "epoch": 3.33, + "learning_rate": 1.555644703319355e-05, + "loss": 0.2652, + "step": 3764 + }, + { + "epoch": 3.33, + "learning_rate": 1.555406382672501e-05, + "loss": 0.2928, + "step": 3765 + }, + { + "epoch": 3.33, + "learning_rate": 1.5551680163998722e-05, + "loss": 0.2766, + "step": 3766 + }, + { + "epoch": 3.33, + "learning_rate": 1.55492960452105e-05, + "loss": 0.2694, + "step": 3767 + }, + { + "epoch": 3.33, + "learning_rate": 1.5546911470556196e-05, + "loss": 0.2943, + "step": 3768 + }, + { + "epoch": 3.33, + "learning_rate": 1.5544526440231698e-05, + "loss": 0.2792, + "step": 3769 + }, + { + "epoch": 3.33, + "learning_rate": 1.5542140954432935e-05, + "loss": 0.2727, + "step": 3770 + }, + { + "epoch": 3.34, + "learning_rate": 1.5539755013355863e-05, + "loss": 0.2947, + "step": 3771 + }, + { + "epoch": 3.34, + "learning_rate": 1.5537368617196494e-05, + "loss": 0.3013, + "step": 3772 + }, + { + "epoch": 3.34, + "learning_rate": 1.553498176615086e-05, + "loss": 0.2913, + "step": 3773 + }, + { + "epoch": 3.34, + "learning_rate": 1.553259446041504e-05, + "loss": 0.2984, + "step": 3774 + }, + { + "epoch": 3.34, + "learning_rate": 1.5530206700185145e-05, + "loss": 0.2796, + "step": 3775 + }, + { + "epoch": 3.34, + "learning_rate": 1.5527818485657328e-05, + "loss": 0.2682, + "step": 3776 + }, + { + "epoch": 3.34, + "learning_rate": 1.5525429817027776e-05, + "loss": 0.2859, + "step": 3777 + }, + { + "epoch": 3.34, + "learning_rate": 1.5523040694492715e-05, + "loss": 0.2786, + "step": 3778 + }, + { + "epoch": 3.34, + "learning_rate": 1.552065111824841e-05, + "loss": 0.2775, + "step": 3779 + }, + { + "epoch": 3.34, + "learning_rate": 1.5518261088491155e-05, + "loss": 0.2754, + "step": 3780 + }, + { + "epoch": 3.34, + "learning_rate": 1.551587060541729e-05, + "loss": 0.2849, + "step": 3781 + }, + { + "epoch": 3.35, + "learning_rate": 1.5513479669223194e-05, + "loss": 0.27, + "step": 3782 + }, + { + "epoch": 3.35, + "learning_rate": 1.5511088280105276e-05, + "loss": 0.2966, + "step": 3783 + }, + { + "epoch": 3.35, + "learning_rate": 1.5508696438259982e-05, + "loss": 0.2758, + "step": 3784 + }, + { + "epoch": 3.35, + "learning_rate": 1.5506304143883798e-05, + "loss": 0.2788, + "step": 3785 + }, + { + "epoch": 3.35, + "learning_rate": 1.5503911397173253e-05, + "loss": 0.27, + "step": 3786 + }, + { + "epoch": 3.35, + "learning_rate": 1.55015181983249e-05, + "loss": 0.28, + "step": 3787 + }, + { + "epoch": 3.35, + "learning_rate": 1.5499124547535346e-05, + "loss": 0.2734, + "step": 3788 + }, + { + "epoch": 3.35, + "learning_rate": 1.5496730445001213e-05, + "loss": 0.2761, + "step": 3789 + }, + { + "epoch": 3.35, + "learning_rate": 1.5494335890919182e-05, + "loss": 0.2884, + "step": 3790 + }, + { + "epoch": 3.35, + "learning_rate": 1.5491940885485962e-05, + "loss": 0.2884, + "step": 3791 + }, + { + "epoch": 3.35, + "learning_rate": 1.54895454288983e-05, + "loss": 0.2918, + "step": 3792 + }, + { + "epoch": 3.36, + "learning_rate": 1.548714952135297e-05, + "loss": 0.2841, + "step": 3793 + }, + { + "epoch": 3.36, + "learning_rate": 1.5484753163046798e-05, + "loss": 0.2764, + "step": 3794 + }, + { + "epoch": 3.36, + "learning_rate": 1.5482356354176645e-05, + "loss": 0.2794, + "step": 3795 + }, + { + "epoch": 3.36, + "learning_rate": 1.5479959094939395e-05, + "loss": 0.2932, + "step": 3796 + }, + { + "epoch": 3.36, + "learning_rate": 1.5477561385531988e-05, + "loss": 0.2894, + "step": 3797 + }, + { + "epoch": 3.36, + "learning_rate": 1.5475163226151393e-05, + "loss": 0.2806, + "step": 3798 + }, + { + "epoch": 3.36, + "learning_rate": 1.547276461699461e-05, + "loss": 0.2903, + "step": 3799 + }, + { + "epoch": 3.36, + "learning_rate": 1.547036555825868e-05, + "loss": 0.279, + "step": 3800 + }, + { + "epoch": 3.36, + "learning_rate": 1.5467966050140687e-05, + "loss": 0.2766, + "step": 3801 + }, + { + "epoch": 3.36, + "learning_rate": 1.5465566092837745e-05, + "loss": 0.2702, + "step": 3802 + }, + { + "epoch": 3.36, + "learning_rate": 1.5463165686547006e-05, + "loss": 0.2928, + "step": 3803 + }, + { + "epoch": 3.37, + "learning_rate": 1.546076483146566e-05, + "loss": 0.2807, + "step": 3804 + }, + { + "epoch": 3.37, + "learning_rate": 1.545836352779093e-05, + "loss": 0.2865, + "step": 3805 + }, + { + "epoch": 3.37, + "learning_rate": 1.5455961775720084e-05, + "loss": 0.2641, + "step": 3806 + }, + { + "epoch": 3.37, + "learning_rate": 1.5453559575450422e-05, + "loss": 0.274, + "step": 3807 + }, + { + "epoch": 3.37, + "learning_rate": 1.545115692717928e-05, + "loss": 0.2606, + "step": 3808 + }, + { + "epoch": 3.37, + "learning_rate": 1.5448753831104034e-05, + "loss": 0.2745, + "step": 3809 + }, + { + "epoch": 3.37, + "learning_rate": 1.5446350287422086e-05, + "loss": 0.2666, + "step": 3810 + }, + { + "epoch": 3.37, + "learning_rate": 1.5443946296330898e-05, + "loss": 0.3066, + "step": 3811 + }, + { + "epoch": 3.37, + "learning_rate": 1.544154185802794e-05, + "loss": 0.2808, + "step": 3812 + }, + { + "epoch": 3.37, + "learning_rate": 1.543913697271074e-05, + "loss": 0.2856, + "step": 3813 + }, + { + "epoch": 3.37, + "learning_rate": 1.5436731640576858e-05, + "loss": 0.2765, + "step": 3814 + }, + { + "epoch": 3.37, + "learning_rate": 1.543432586182388e-05, + "loss": 0.298, + "step": 3815 + }, + { + "epoch": 3.38, + "learning_rate": 1.5431919636649447e-05, + "loss": 0.3027, + "step": 3816 + }, + { + "epoch": 3.38, + "learning_rate": 1.5429512965251216e-05, + "loss": 0.287, + "step": 3817 + }, + { + "epoch": 3.38, + "learning_rate": 1.54271058478269e-05, + "loss": 0.2622, + "step": 3818 + }, + { + "epoch": 3.38, + "learning_rate": 1.5424698284574237e-05, + "loss": 0.2758, + "step": 3819 + }, + { + "epoch": 3.38, + "learning_rate": 1.5422290275691002e-05, + "loss": 0.3061, + "step": 3820 + }, + { + "epoch": 3.38, + "learning_rate": 1.5419881821375014e-05, + "loss": 0.2751, + "step": 3821 + }, + { + "epoch": 3.38, + "learning_rate": 1.5417472921824123e-05, + "loss": 0.2785, + "step": 3822 + }, + { + "epoch": 3.38, + "learning_rate": 1.5415063577236212e-05, + "loss": 0.2854, + "step": 3823 + }, + { + "epoch": 3.38, + "learning_rate": 1.5412653787809207e-05, + "loss": 0.2796, + "step": 3824 + }, + { + "epoch": 3.38, + "learning_rate": 1.5410243553741072e-05, + "loss": 0.2721, + "step": 3825 + }, + { + "epoch": 3.38, + "learning_rate": 1.5407832875229796e-05, + "loss": 0.2889, + "step": 3826 + }, + { + "epoch": 3.39, + "learning_rate": 1.5405421752473422e-05, + "loss": 0.2925, + "step": 3827 + }, + { + "epoch": 3.39, + "learning_rate": 1.5403010185670017e-05, + "loss": 0.2883, + "step": 3828 + }, + { + "epoch": 3.39, + "learning_rate": 1.5400598175017682e-05, + "loss": 0.2619, + "step": 3829 + }, + { + "epoch": 3.39, + "learning_rate": 1.5398185720714568e-05, + "loss": 0.275, + "step": 3830 + }, + { + "epoch": 3.39, + "learning_rate": 1.5395772822958844e-05, + "loss": 0.2876, + "step": 3831 + }, + { + "epoch": 3.39, + "learning_rate": 1.5393359481948742e-05, + "loss": 0.2918, + "step": 3832 + }, + { + "epoch": 3.39, + "learning_rate": 1.53909456978825e-05, + "loss": 0.282, + "step": 3833 + }, + { + "epoch": 3.39, + "learning_rate": 1.5388531470958408e-05, + "loss": 0.2683, + "step": 3834 + }, + { + "epoch": 3.39, + "learning_rate": 1.5386116801374797e-05, + "loss": 0.2936, + "step": 3835 + }, + { + "epoch": 3.39, + "learning_rate": 1.5383701689330025e-05, + "loss": 0.2786, + "step": 3836 + }, + { + "epoch": 3.39, + "learning_rate": 1.538128613502249e-05, + "loss": 0.2804, + "step": 3837 + }, + { + "epoch": 3.4, + "learning_rate": 1.5378870138650624e-05, + "loss": 0.2731, + "step": 3838 + }, + { + "epoch": 3.4, + "learning_rate": 1.5376453700412905e-05, + "loss": 0.2819, + "step": 3839 + }, + { + "epoch": 3.4, + "learning_rate": 1.5374036820507833e-05, + "loss": 0.2753, + "step": 3840 + }, + { + "epoch": 3.4, + "learning_rate": 1.537161949913395e-05, + "loss": 0.2715, + "step": 3841 + }, + { + "epoch": 3.4, + "learning_rate": 1.536920173648984e-05, + "loss": 0.2801, + "step": 3842 + }, + { + "epoch": 3.4, + "learning_rate": 1.5366783532774112e-05, + "loss": 0.2877, + "step": 3843 + }, + { + "epoch": 3.4, + "learning_rate": 1.536436488818543e-05, + "loss": 0.2717, + "step": 3844 + }, + { + "epoch": 3.4, + "learning_rate": 1.5361945802922466e-05, + "loss": 0.285, + "step": 3845 + }, + { + "epoch": 3.4, + "learning_rate": 1.535952627718395e-05, + "loss": 0.2876, + "step": 3846 + }, + { + "epoch": 3.4, + "learning_rate": 1.535710631116865e-05, + "loss": 0.2932, + "step": 3847 + }, + { + "epoch": 3.4, + "learning_rate": 1.5354685905075354e-05, + "loss": 0.3002, + "step": 3848 + }, + { + "epoch": 3.4, + "learning_rate": 1.5352265059102896e-05, + "loss": 0.2807, + "step": 3849 + }, + { + "epoch": 3.41, + "learning_rate": 1.5349843773450146e-05, + "loss": 0.2894, + "step": 3850 + }, + { + "epoch": 3.41, + "learning_rate": 1.534742204831601e-05, + "loss": 0.2808, + "step": 3851 + }, + { + "epoch": 3.41, + "learning_rate": 1.5344999883899426e-05, + "loss": 0.2834, + "step": 3852 + }, + { + "epoch": 3.41, + "learning_rate": 1.5342577280399373e-05, + "loss": 0.2668, + "step": 3853 + }, + { + "epoch": 3.41, + "learning_rate": 1.5340154238014866e-05, + "loss": 0.2919, + "step": 3854 + }, + { + "epoch": 3.41, + "learning_rate": 1.5337730756944948e-05, + "loss": 0.2828, + "step": 3855 + }, + { + "epoch": 3.41, + "learning_rate": 1.5335306837388713e-05, + "loss": 0.2721, + "step": 3856 + }, + { + "epoch": 3.41, + "learning_rate": 1.533288247954527e-05, + "loss": 0.2876, + "step": 3857 + }, + { + "epoch": 3.41, + "learning_rate": 1.5330457683613794e-05, + "loss": 0.2482, + "step": 3858 + }, + { + "epoch": 3.41, + "learning_rate": 1.5328032449793462e-05, + "loss": 0.3105, + "step": 3859 + }, + { + "epoch": 3.41, + "learning_rate": 1.532560677828351e-05, + "loss": 0.2883, + "step": 3860 + }, + { + "epoch": 3.42, + "learning_rate": 1.5323180669283203e-05, + "loss": 0.2682, + "step": 3861 + }, + { + "epoch": 3.42, + "learning_rate": 1.5320754122991835e-05, + "loss": 0.2887, + "step": 3862 + }, + { + "epoch": 3.42, + "learning_rate": 1.531832713960876e-05, + "loss": 0.2842, + "step": 3863 + }, + { + "epoch": 3.42, + "learning_rate": 1.5315899719333333e-05, + "loss": 0.2654, + "step": 3864 + }, + { + "epoch": 3.42, + "learning_rate": 1.531347186236497e-05, + "loss": 0.2758, + "step": 3865 + }, + { + "epoch": 3.42, + "learning_rate": 1.531104356890312e-05, + "loss": 0.2815, + "step": 3866 + }, + { + "epoch": 3.42, + "learning_rate": 1.5308614839147256e-05, + "loss": 0.2817, + "step": 3867 + }, + { + "epoch": 3.42, + "learning_rate": 1.5306185673296903e-05, + "loss": 0.2636, + "step": 3868 + }, + { + "epoch": 3.42, + "learning_rate": 1.5303756071551604e-05, + "loss": 0.2719, + "step": 3869 + }, + { + "epoch": 3.42, + "learning_rate": 1.5301326034110952e-05, + "loss": 0.2871, + "step": 3870 + }, + { + "epoch": 3.42, + "learning_rate": 1.529889556117457e-05, + "loss": 0.2762, + "step": 3871 + }, + { + "epoch": 3.43, + "learning_rate": 1.5296464652942113e-05, + "loss": 0.2842, + "step": 3872 + }, + { + "epoch": 3.43, + "learning_rate": 1.5294033309613287e-05, + "loss": 0.3061, + "step": 3873 + }, + { + "epoch": 3.43, + "learning_rate": 1.5291601531387814e-05, + "loss": 0.265, + "step": 3874 + }, + { + "epoch": 3.43, + "learning_rate": 1.5289169318465463e-05, + "loss": 0.2534, + "step": 3875 + }, + { + "epoch": 3.43, + "learning_rate": 1.528673667104604e-05, + "loss": 0.2731, + "step": 3876 + }, + { + "epoch": 3.43, + "learning_rate": 1.528430358932938e-05, + "loss": 0.2801, + "step": 3877 + }, + { + "epoch": 3.43, + "learning_rate": 1.5281870073515353e-05, + "loss": 0.2814, + "step": 3878 + }, + { + "epoch": 3.43, + "learning_rate": 1.5279436123803877e-05, + "loss": 0.2899, + "step": 3879 + }, + { + "epoch": 3.43, + "learning_rate": 1.5277001740394893e-05, + "loss": 0.2925, + "step": 3880 + }, + { + "epoch": 3.43, + "learning_rate": 1.5274566923488382e-05, + "loss": 0.2784, + "step": 3881 + }, + { + "epoch": 3.43, + "learning_rate": 1.527213167328436e-05, + "loss": 0.3022, + "step": 3882 + }, + { + "epoch": 3.43, + "learning_rate": 1.526969598998288e-05, + "loss": 0.2804, + "step": 3883 + }, + { + "epoch": 3.44, + "learning_rate": 1.5267259873784026e-05, + "loss": 0.2798, + "step": 3884 + }, + { + "epoch": 3.44, + "learning_rate": 1.5264823324887926e-05, + "loss": 0.2914, + "step": 3885 + }, + { + "epoch": 3.44, + "learning_rate": 1.5262386343494737e-05, + "loss": 0.2874, + "step": 3886 + }, + { + "epoch": 3.44, + "learning_rate": 1.5259948929804652e-05, + "loss": 0.2733, + "step": 3887 + }, + { + "epoch": 3.44, + "learning_rate": 1.5257511084017904e-05, + "loss": 0.2794, + "step": 3888 + }, + { + "epoch": 3.44, + "learning_rate": 1.5255072806334758e-05, + "loss": 0.2834, + "step": 3889 + }, + { + "epoch": 3.44, + "learning_rate": 1.525263409695551e-05, + "loss": 0.288, + "step": 3890 + }, + { + "epoch": 3.44, + "learning_rate": 1.5250194956080501e-05, + "loss": 0.2793, + "step": 3891 + }, + { + "epoch": 3.44, + "learning_rate": 1.5247755383910097e-05, + "loss": 0.2923, + "step": 3892 + }, + { + "epoch": 3.44, + "learning_rate": 1.5245315380644711e-05, + "loss": 0.2701, + "step": 3893 + }, + { + "epoch": 3.44, + "learning_rate": 1.5242874946484785e-05, + "loss": 0.2651, + "step": 3894 + }, + { + "epoch": 3.45, + "learning_rate": 1.5240434081630793e-05, + "loss": 0.2728, + "step": 3895 + }, + { + "epoch": 3.45, + "learning_rate": 1.5237992786283253e-05, + "loss": 0.272, + "step": 3896 + }, + { + "epoch": 3.45, + "learning_rate": 1.5235551060642708e-05, + "loss": 0.2986, + "step": 3897 + }, + { + "epoch": 3.45, + "learning_rate": 1.5233108904909748e-05, + "loss": 0.2951, + "step": 3898 + }, + { + "epoch": 3.45, + "learning_rate": 1.5230666319284985e-05, + "loss": 0.2905, + "step": 3899 + }, + { + "epoch": 3.45, + "learning_rate": 1.5228223303969083e-05, + "loss": 0.2765, + "step": 3900 + }, + { + "epoch": 3.45, + "learning_rate": 1.5225779859162727e-05, + "loss": 0.2645, + "step": 3901 + }, + { + "epoch": 3.45, + "learning_rate": 1.522333598506664e-05, + "loss": 0.2848, + "step": 3902 + }, + { + "epoch": 3.45, + "learning_rate": 1.5220891681881586e-05, + "loss": 0.3026, + "step": 3903 + }, + { + "epoch": 3.45, + "learning_rate": 1.5218446949808358e-05, + "loss": 0.2913, + "step": 3904 + }, + { + "epoch": 3.45, + "learning_rate": 1.521600178904779e-05, + "loss": 0.2841, + "step": 3905 + }, + { + "epoch": 3.46, + "learning_rate": 1.5213556199800743e-05, + "loss": 0.2871, + "step": 3906 + }, + { + "epoch": 3.46, + "learning_rate": 1.5211110182268127e-05, + "loss": 0.2902, + "step": 3907 + }, + { + "epoch": 3.46, + "learning_rate": 1.520866373665087e-05, + "loss": 0.2809, + "step": 3908 + }, + { + "epoch": 3.46, + "learning_rate": 1.520621686314995e-05, + "loss": 0.2957, + "step": 3909 + }, + { + "epoch": 3.46, + "learning_rate": 1.5203769561966369e-05, + "loss": 0.306, + "step": 3910 + }, + { + "epoch": 3.46, + "learning_rate": 1.5201321833301168e-05, + "loss": 0.3049, + "step": 3911 + }, + { + "epoch": 3.46, + "learning_rate": 1.5198873677355433e-05, + "loss": 0.2803, + "step": 3912 + }, + { + "epoch": 3.46, + "learning_rate": 1.5196425094330267e-05, + "loss": 0.2818, + "step": 3913 + }, + { + "epoch": 3.46, + "learning_rate": 1.5193976084426823e-05, + "loss": 0.2601, + "step": 3914 + }, + { + "epoch": 3.46, + "learning_rate": 1.519152664784628e-05, + "loss": 0.2865, + "step": 3915 + }, + { + "epoch": 3.46, + "learning_rate": 1.5189076784789855e-05, + "loss": 0.2806, + "step": 3916 + }, + { + "epoch": 3.47, + "learning_rate": 1.5186626495458808e-05, + "loss": 0.269, + "step": 3917 + }, + { + "epoch": 3.47, + "learning_rate": 1.5184175780054411e-05, + "loss": 0.2869, + "step": 3918 + }, + { + "epoch": 3.47, + "learning_rate": 1.5181724638778001e-05, + "loss": 0.2678, + "step": 3919 + }, + { + "epoch": 3.47, + "learning_rate": 1.5179273071830932e-05, + "loss": 0.2876, + "step": 3920 + }, + { + "epoch": 3.47, + "learning_rate": 1.5176821079414591e-05, + "loss": 0.2758, + "step": 3921 + }, + { + "epoch": 3.47, + "learning_rate": 1.5174368661730415e-05, + "loss": 0.2873, + "step": 3922 + }, + { + "epoch": 3.47, + "learning_rate": 1.5171915818979854e-05, + "loss": 0.2915, + "step": 3923 + }, + { + "epoch": 3.47, + "learning_rate": 1.5169462551364413e-05, + "loss": 0.2811, + "step": 3924 + }, + { + "epoch": 3.47, + "learning_rate": 1.5167008859085626e-05, + "loss": 0.2925, + "step": 3925 + }, + { + "epoch": 3.47, + "learning_rate": 1.5164554742345057e-05, + "loss": 0.2815, + "step": 3926 + }, + { + "epoch": 3.47, + "learning_rate": 1.5162100201344306e-05, + "loss": 0.2937, + "step": 3927 + }, + { + "epoch": 3.47, + "learning_rate": 1.515964523628501e-05, + "loss": 0.2802, + "step": 3928 + }, + { + "epoch": 3.48, + "learning_rate": 1.5157189847368848e-05, + "loss": 0.2742, + "step": 3929 + }, + { + "epoch": 3.48, + "learning_rate": 1.5154734034797517e-05, + "loss": 0.283, + "step": 3930 + }, + { + "epoch": 3.48, + "learning_rate": 1.5152277798772758e-05, + "loss": 0.2849, + "step": 3931 + }, + { + "epoch": 3.48, + "learning_rate": 1.5149821139496354e-05, + "loss": 0.2987, + "step": 3932 + }, + { + "epoch": 3.48, + "learning_rate": 1.5147364057170113e-05, + "loss": 0.305, + "step": 3933 + }, + { + "epoch": 3.48, + "learning_rate": 1.5144906551995879e-05, + "loss": 0.2668, + "step": 3934 + }, + { + "epoch": 3.48, + "learning_rate": 1.5142448624175533e-05, + "loss": 0.2851, + "step": 3935 + }, + { + "epoch": 3.48, + "learning_rate": 1.5139990273910992e-05, + "loss": 0.2796, + "step": 3936 + }, + { + "epoch": 3.48, + "learning_rate": 1.5137531501404201e-05, + "loss": 0.2721, + "step": 3937 + }, + { + "epoch": 3.48, + "learning_rate": 1.5135072306857152e-05, + "loss": 0.2903, + "step": 3938 + }, + { + "epoch": 3.48, + "learning_rate": 1.5132612690471856e-05, + "loss": 0.3006, + "step": 3939 + }, + { + "epoch": 3.49, + "learning_rate": 1.513015265245037e-05, + "loss": 0.2879, + "step": 3940 + }, + { + "epoch": 3.49, + "learning_rate": 1.5127692192994782e-05, + "loss": 0.2823, + "step": 3941 + }, + { + "epoch": 3.49, + "learning_rate": 1.5125231312307218e-05, + "loss": 0.2622, + "step": 3942 + }, + { + "epoch": 3.49, + "learning_rate": 1.512277001058983e-05, + "loss": 0.2834, + "step": 3943 + }, + { + "epoch": 3.49, + "learning_rate": 1.5120308288044814e-05, + "loss": 0.2877, + "step": 3944 + }, + { + "epoch": 3.49, + "learning_rate": 1.5117846144874395e-05, + "loss": 0.2768, + "step": 3945 + }, + { + "epoch": 3.49, + "learning_rate": 1.5115383581280835e-05, + "loss": 0.2695, + "step": 3946 + }, + { + "epoch": 3.49, + "learning_rate": 1.511292059746643e-05, + "loss": 0.2976, + "step": 3947 + }, + { + "epoch": 3.49, + "learning_rate": 1.5110457193633508e-05, + "loss": 0.2601, + "step": 3948 + }, + { + "epoch": 3.49, + "learning_rate": 1.510799336998444e-05, + "loss": 0.2878, + "step": 3949 + }, + { + "epoch": 3.49, + "learning_rate": 1.5105529126721617e-05, + "loss": 0.279, + "step": 3950 + }, + { + "epoch": 3.5, + "learning_rate": 1.5103064464047479e-05, + "loss": 0.2699, + "step": 3951 + }, + { + "epoch": 3.5, + "learning_rate": 1.510059938216449e-05, + "loss": 0.277, + "step": 3952 + }, + { + "epoch": 3.5, + "learning_rate": 1.5098133881275156e-05, + "loss": 0.2675, + "step": 3953 + }, + { + "epoch": 3.5, + "learning_rate": 1.5095667961582012e-05, + "loss": 0.284, + "step": 3954 + }, + { + "epoch": 3.5, + "learning_rate": 1.5093201623287631e-05, + "loss": 0.2788, + "step": 3955 + }, + { + "epoch": 3.5, + "learning_rate": 1.509073486659462e-05, + "loss": 0.2876, + "step": 3956 + }, + { + "epoch": 3.5, + "learning_rate": 1.5088267691705616e-05, + "loss": 0.3078, + "step": 3957 + }, + { + "epoch": 3.5, + "learning_rate": 1.508580009882329e-05, + "loss": 0.2818, + "step": 3958 + }, + { + "epoch": 3.5, + "learning_rate": 1.5083332088150364e-05, + "loss": 0.2798, + "step": 3959 + }, + { + "epoch": 3.5, + "learning_rate": 1.5080863659889566e-05, + "loss": 0.299, + "step": 3960 + }, + { + "epoch": 3.5, + "learning_rate": 1.5078394814243687e-05, + "loss": 0.2792, + "step": 3961 + }, + { + "epoch": 3.5, + "learning_rate": 1.5075925551415529e-05, + "loss": 0.2718, + "step": 3962 + }, + { + "epoch": 3.51, + "learning_rate": 1.5073455871607942e-05, + "loss": 0.2807, + "step": 3963 + }, + { + "epoch": 3.51, + "learning_rate": 1.5070985775023808e-05, + "loss": 0.2806, + "step": 3964 + }, + { + "epoch": 3.51, + "learning_rate": 1.5068515261866039e-05, + "loss": 0.2792, + "step": 3965 + }, + { + "epoch": 3.51, + "learning_rate": 1.5066044332337586e-05, + "loss": 0.2626, + "step": 3966 + }, + { + "epoch": 3.51, + "learning_rate": 1.5063572986641423e-05, + "loss": 0.2892, + "step": 3967 + }, + { + "epoch": 3.51, + "learning_rate": 1.5061101224980585e-05, + "loss": 0.289, + "step": 3968 + }, + { + "epoch": 3.51, + "learning_rate": 1.5058629047558106e-05, + "loss": 0.2971, + "step": 3969 + }, + { + "epoch": 3.51, + "learning_rate": 1.5056156454577082e-05, + "loss": 0.2963, + "step": 3970 + }, + { + "epoch": 3.51, + "learning_rate": 1.5053683446240631e-05, + "loss": 0.264, + "step": 3971 + }, + { + "epoch": 3.51, + "learning_rate": 1.5051210022751901e-05, + "loss": 0.3025, + "step": 3972 + }, + { + "epoch": 3.51, + "learning_rate": 1.5048736184314085e-05, + "loss": 0.2782, + "step": 3973 + }, + { + "epoch": 3.52, + "learning_rate": 1.5046261931130405e-05, + "loss": 0.2804, + "step": 3974 + }, + { + "epoch": 3.52, + "learning_rate": 1.5043787263404118e-05, + "loss": 0.2796, + "step": 3975 + }, + { + "epoch": 3.52, + "learning_rate": 1.5041312181338513e-05, + "loss": 0.2868, + "step": 3976 + }, + { + "epoch": 3.52, + "learning_rate": 1.5038836685136908e-05, + "loss": 0.303, + "step": 3977 + }, + { + "epoch": 3.52, + "learning_rate": 1.5036360775002673e-05, + "loss": 0.2783, + "step": 3978 + }, + { + "epoch": 3.52, + "learning_rate": 1.5033884451139188e-05, + "loss": 0.29, + "step": 3979 + }, + { + "epoch": 3.52, + "learning_rate": 1.5031407713749888e-05, + "loss": 0.2729, + "step": 3980 + }, + { + "epoch": 3.52, + "learning_rate": 1.502893056303823e-05, + "loss": 0.3046, + "step": 3981 + }, + { + "epoch": 3.52, + "learning_rate": 1.502645299920771e-05, + "loss": 0.267, + "step": 3982 + }, + { + "epoch": 3.52, + "learning_rate": 1.5023975022461852e-05, + "loss": 0.3014, + "step": 3983 + }, + { + "epoch": 3.52, + "learning_rate": 1.502149663300422e-05, + "loss": 0.2746, + "step": 3984 + }, + { + "epoch": 3.53, + "learning_rate": 1.5019017831038412e-05, + "loss": 0.2998, + "step": 3985 + }, + { + "epoch": 3.53, + "learning_rate": 1.5016538616768054e-05, + "loss": 0.2891, + "step": 3986 + }, + { + "epoch": 3.53, + "learning_rate": 1.5014058990396813e-05, + "loss": 0.2977, + "step": 3987 + }, + { + "epoch": 3.53, + "learning_rate": 1.5011578952128384e-05, + "loss": 0.281, + "step": 3988 + }, + { + "epoch": 3.53, + "learning_rate": 1.50090985021665e-05, + "loss": 0.2915, + "step": 3989 + }, + { + "epoch": 3.53, + "learning_rate": 1.5006617640714926e-05, + "loss": 0.3033, + "step": 3990 + }, + { + "epoch": 3.53, + "learning_rate": 1.5004136367977458e-05, + "loss": 0.2855, + "step": 3991 + }, + { + "epoch": 3.53, + "learning_rate": 1.5001654684157934e-05, + "loss": 0.278, + "step": 3992 + }, + { + "epoch": 3.53, + "learning_rate": 1.4999172589460217e-05, + "loss": 0.2802, + "step": 3993 + }, + { + "epoch": 3.53, + "learning_rate": 1.4996690084088206e-05, + "loss": 0.2874, + "step": 3994 + }, + { + "epoch": 3.53, + "learning_rate": 1.4994207168245836e-05, + "loss": 0.2863, + "step": 3995 + }, + { + "epoch": 3.53, + "learning_rate": 1.4991723842137079e-05, + "loss": 0.2732, + "step": 3996 + }, + { + "epoch": 3.54, + "learning_rate": 1.4989240105965927e-05, + "loss": 0.2836, + "step": 3997 + }, + { + "epoch": 3.54, + "learning_rate": 1.4986755959936427e-05, + "loss": 0.2882, + "step": 3998 + }, + { + "epoch": 3.54, + "learning_rate": 1.498427140425264e-05, + "loss": 0.2886, + "step": 3999 + }, + { + "epoch": 3.54, + "learning_rate": 1.498178643911867e-05, + "loss": 0.2772, + "step": 4000 + }, + { + "epoch": 3.54, + "learning_rate": 1.4979301064738652e-05, + "loss": 0.2808, + "step": 4001 + }, + { + "epoch": 3.54, + "learning_rate": 1.4976815281316755e-05, + "loss": 0.2885, + "step": 4002 + }, + { + "epoch": 3.54, + "learning_rate": 1.4974329089057189e-05, + "loss": 0.2689, + "step": 4003 + }, + { + "epoch": 3.54, + "learning_rate": 1.497184248816418e-05, + "loss": 0.2846, + "step": 4004 + }, + { + "epoch": 3.54, + "learning_rate": 1.496935547884201e-05, + "loss": 0.2883, + "step": 4005 + }, + { + "epoch": 3.54, + "learning_rate": 1.4966868061294975e-05, + "loss": 0.3004, + "step": 4006 + }, + { + "epoch": 3.54, + "learning_rate": 1.4964380235727413e-05, + "loss": 0.2704, + "step": 4007 + }, + { + "epoch": 3.55, + "learning_rate": 1.49618920023437e-05, + "loss": 0.3021, + "step": 4008 + }, + { + "epoch": 3.55, + "learning_rate": 1.4959403361348234e-05, + "loss": 0.2826, + "step": 4009 + }, + { + "epoch": 3.55, + "learning_rate": 1.4956914312945461e-05, + "loss": 0.2888, + "step": 4010 + }, + { + "epoch": 3.55, + "learning_rate": 1.4954424857339845e-05, + "loss": 0.2626, + "step": 4011 + }, + { + "epoch": 3.55, + "learning_rate": 1.495193499473589e-05, + "loss": 0.2891, + "step": 4012 + }, + { + "epoch": 3.55, + "learning_rate": 1.4949444725338145e-05, + "loss": 0.2926, + "step": 4013 + }, + { + "epoch": 3.55, + "learning_rate": 1.494695404935117e-05, + "loss": 0.2725, + "step": 4014 + }, + { + "epoch": 3.55, + "learning_rate": 1.4944462966979575e-05, + "loss": 0.278, + "step": 4015 + }, + { + "epoch": 3.55, + "learning_rate": 1.4941971478428001e-05, + "loss": 0.2789, + "step": 4016 + }, + { + "epoch": 3.55, + "learning_rate": 1.4939479583901118e-05, + "loss": 0.2836, + "step": 4017 + }, + { + "epoch": 3.55, + "learning_rate": 1.493698728360363e-05, + "loss": 0.2865, + "step": 4018 + }, + { + "epoch": 3.56, + "learning_rate": 1.4934494577740273e-05, + "loss": 0.2901, + "step": 4019 + }, + { + "epoch": 3.56, + "learning_rate": 1.4932001466515828e-05, + "loss": 0.2925, + "step": 4020 + }, + { + "epoch": 3.56, + "learning_rate": 1.4929507950135091e-05, + "loss": 0.2696, + "step": 4021 + }, + { + "epoch": 3.56, + "learning_rate": 1.4927014028802904e-05, + "loss": 0.276, + "step": 4022 + }, + { + "epoch": 3.56, + "learning_rate": 1.492451970272414e-05, + "loss": 0.2765, + "step": 4023 + }, + { + "epoch": 3.56, + "learning_rate": 1.4922024972103704e-05, + "loss": 0.2868, + "step": 4024 + }, + { + "epoch": 3.56, + "learning_rate": 1.4919529837146529e-05, + "loss": 0.2683, + "step": 4025 + }, + { + "epoch": 3.56, + "learning_rate": 1.4917034298057593e-05, + "loss": 0.265, + "step": 4026 + }, + { + "epoch": 3.56, + "learning_rate": 1.4914538355041901e-05, + "loss": 0.2922, + "step": 4027 + }, + { + "epoch": 3.56, + "learning_rate": 1.4912042008304484e-05, + "loss": 0.2629, + "step": 4028 + }, + { + "epoch": 3.56, + "learning_rate": 1.490954525805042e-05, + "loss": 0.2775, + "step": 4029 + }, + { + "epoch": 3.56, + "learning_rate": 1.4907048104484808e-05, + "loss": 0.2939, + "step": 4030 + }, + { + "epoch": 3.57, + "learning_rate": 1.490455054781279e-05, + "loss": 0.2842, + "step": 4031 + }, + { + "epoch": 3.57, + "learning_rate": 1.4902052588239535e-05, + "loss": 0.2732, + "step": 4032 + }, + { + "epoch": 3.57, + "learning_rate": 1.4899554225970243e-05, + "loss": 0.2641, + "step": 4033 + }, + { + "epoch": 3.57, + "learning_rate": 1.4897055461210155e-05, + "loss": 0.2567, + "step": 4034 + }, + { + "epoch": 3.57, + "learning_rate": 1.4894556294164535e-05, + "loss": 0.2846, + "step": 4035 + }, + { + "epoch": 3.57, + "learning_rate": 1.4892056725038692e-05, + "loss": 0.292, + "step": 4036 + }, + { + "epoch": 3.57, + "learning_rate": 1.4889556754037959e-05, + "loss": 0.2883, + "step": 4037 + }, + { + "epoch": 3.57, + "learning_rate": 1.4887056381367706e-05, + "loss": 0.2972, + "step": 4038 + }, + { + "epoch": 3.57, + "learning_rate": 1.4884555607233336e-05, + "loss": 0.2801, + "step": 4039 + }, + { + "epoch": 3.57, + "learning_rate": 1.4882054431840277e-05, + "loss": 0.2776, + "step": 4040 + }, + { + "epoch": 3.57, + "learning_rate": 1.4879552855394004e-05, + "loss": 0.2939, + "step": 4041 + }, + { + "epoch": 3.58, + "learning_rate": 1.4877050878100012e-05, + "loss": 0.2907, + "step": 4042 + }, + { + "epoch": 3.58, + "learning_rate": 1.487454850016384e-05, + "loss": 0.2994, + "step": 4043 + }, + { + "epoch": 3.58, + "learning_rate": 1.4872045721791051e-05, + "loss": 0.2864, + "step": 4044 + }, + { + "epoch": 3.58, + "learning_rate": 1.4869542543187244e-05, + "loss": 0.2851, + "step": 4045 + }, + { + "epoch": 3.58, + "learning_rate": 1.4867038964558056e-05, + "loss": 0.2889, + "step": 4046 + }, + { + "epoch": 3.58, + "learning_rate": 1.4864534986109145e-05, + "loss": 0.307, + "step": 4047 + }, + { + "epoch": 3.58, + "learning_rate": 1.4862030608046211e-05, + "loss": 0.2685, + "step": 4048 + }, + { + "epoch": 3.58, + "learning_rate": 1.485952583057499e-05, + "loss": 0.2744, + "step": 4049 + }, + { + "epoch": 3.58, + "learning_rate": 1.4857020653901244e-05, + "loss": 0.269, + "step": 4050 + }, + { + "epoch": 3.58, + "learning_rate": 1.485451507823076e-05, + "loss": 0.2791, + "step": 4051 + }, + { + "epoch": 3.58, + "learning_rate": 1.485200910376938e-05, + "loss": 0.2789, + "step": 4052 + }, + { + "epoch": 3.59, + "learning_rate": 1.4849502730722962e-05, + "loss": 0.281, + "step": 4053 + }, + { + "epoch": 3.59, + "learning_rate": 1.4846995959297395e-05, + "loss": 0.2791, + "step": 4054 + }, + { + "epoch": 3.59, + "learning_rate": 1.4844488789698612e-05, + "loss": 0.2765, + "step": 4055 + }, + { + "epoch": 3.59, + "learning_rate": 1.484198122213257e-05, + "loss": 0.2877, + "step": 4056 + }, + { + "epoch": 3.59, + "learning_rate": 1.4839473256805265e-05, + "loss": 0.3078, + "step": 4057 + }, + { + "epoch": 3.59, + "learning_rate": 1.4836964893922718e-05, + "loss": 0.2749, + "step": 4058 + }, + { + "epoch": 3.59, + "learning_rate": 1.4834456133690996e-05, + "loss": 0.2741, + "step": 4059 + }, + { + "epoch": 3.59, + "learning_rate": 1.4831946976316177e-05, + "loss": 0.2792, + "step": 4060 + }, + { + "epoch": 3.59, + "learning_rate": 1.4829437422004396e-05, + "loss": 0.2607, + "step": 4061 + }, + { + "epoch": 3.59, + "learning_rate": 1.4826927470961804e-05, + "loss": 0.2939, + "step": 4062 + }, + { + "epoch": 3.59, + "learning_rate": 1.4824417123394585e-05, + "loss": 0.2598, + "step": 4063 + }, + { + "epoch": 3.6, + "learning_rate": 1.4821906379508968e-05, + "loss": 0.2805, + "step": 4064 + }, + { + "epoch": 3.6, + "learning_rate": 1.4819395239511202e-05, + "loss": 0.272, + "step": 4065 + }, + { + "epoch": 3.6, + "learning_rate": 1.4816883703607578e-05, + "loss": 0.2824, + "step": 4066 + }, + { + "epoch": 3.6, + "learning_rate": 1.481437177200441e-05, + "loss": 0.2953, + "step": 4067 + }, + { + "epoch": 3.6, + "learning_rate": 1.4811859444908053e-05, + "loss": 0.2678, + "step": 4068 + }, + { + "epoch": 3.6, + "learning_rate": 1.4809346722524887e-05, + "loss": 0.2911, + "step": 4069 + }, + { + "epoch": 3.6, + "learning_rate": 1.4806833605061329e-05, + "loss": 0.2761, + "step": 4070 + }, + { + "epoch": 3.6, + "learning_rate": 1.4804320092723829e-05, + "loss": 0.2807, + "step": 4071 + }, + { + "epoch": 3.6, + "learning_rate": 1.4801806185718868e-05, + "loss": 0.2719, + "step": 4072 + }, + { + "epoch": 3.6, + "learning_rate": 1.479929188425296e-05, + "loss": 0.2783, + "step": 4073 + }, + { + "epoch": 3.6, + "learning_rate": 1.479677718853265e-05, + "loss": 0.3039, + "step": 4074 + }, + { + "epoch": 3.6, + "learning_rate": 1.4794262098764515e-05, + "loss": 0.2675, + "step": 4075 + }, + { + "epoch": 3.61, + "learning_rate": 1.4791746615155171e-05, + "loss": 0.2727, + "step": 4076 + }, + { + "epoch": 3.61, + "learning_rate": 1.4789230737911254e-05, + "loss": 0.2689, + "step": 4077 + }, + { + "epoch": 3.61, + "learning_rate": 1.4786714467239447e-05, + "loss": 0.2618, + "step": 4078 + }, + { + "epoch": 3.61, + "learning_rate": 1.4784197803346452e-05, + "loss": 0.2757, + "step": 4079 + }, + { + "epoch": 3.61, + "learning_rate": 1.4781680746439011e-05, + "loss": 0.2719, + "step": 4080 + }, + { + "epoch": 3.61, + "learning_rate": 1.4779163296723894e-05, + "loss": 0.2624, + "step": 4081 + }, + { + "epoch": 3.61, + "learning_rate": 1.4776645454407907e-05, + "loss": 0.2848, + "step": 4082 + }, + { + "epoch": 3.61, + "learning_rate": 1.4774127219697894e-05, + "loss": 0.2885, + "step": 4083 + }, + { + "epoch": 3.61, + "learning_rate": 1.477160859280071e-05, + "loss": 0.2894, + "step": 4084 + }, + { + "epoch": 3.61, + "learning_rate": 1.4769089573923268e-05, + "loss": 0.2898, + "step": 4085 + }, + { + "epoch": 3.61, + "learning_rate": 1.4766570163272499e-05, + "loss": 0.3141, + "step": 4086 + }, + { + "epoch": 3.62, + "learning_rate": 1.4764050361055363e-05, + "loss": 0.2823, + "step": 4087 + }, + { + "epoch": 3.62, + "learning_rate": 1.4761530167478864e-05, + "loss": 0.2733, + "step": 4088 + }, + { + "epoch": 3.62, + "learning_rate": 1.475900958275003e-05, + "loss": 0.2741, + "step": 4089 + }, + { + "epoch": 3.62, + "learning_rate": 1.4756488607075922e-05, + "loss": 0.2714, + "step": 4090 + }, + { + "epoch": 3.62, + "learning_rate": 1.4753967240663635e-05, + "loss": 0.2843, + "step": 4091 + }, + { + "epoch": 3.62, + "learning_rate": 1.47514454837203e-05, + "loss": 0.2854, + "step": 4092 + }, + { + "epoch": 3.62, + "learning_rate": 1.4748923336453067e-05, + "loss": 0.2843, + "step": 4093 + }, + { + "epoch": 3.62, + "learning_rate": 1.4746400799069132e-05, + "loss": 0.2628, + "step": 4094 + }, + { + "epoch": 3.62, + "learning_rate": 1.4743877871775718e-05, + "loss": 0.2873, + "step": 4095 + }, + { + "epoch": 3.62, + "learning_rate": 1.4741354554780077e-05, + "loss": 0.2886, + "step": 4096 + }, + { + "epoch": 3.62, + "learning_rate": 1.4738830848289494e-05, + "loss": 0.292, + "step": 4097 + }, + { + "epoch": 3.63, + "learning_rate": 1.4736306752511288e-05, + "loss": 0.2602, + "step": 4098 + }, + { + "epoch": 3.63, + "learning_rate": 1.4733782267652818e-05, + "loss": 0.2991, + "step": 4099 + }, + { + "epoch": 3.63, + "learning_rate": 1.4731257393921457e-05, + "loss": 0.2875, + "step": 4100 + }, + { + "epoch": 3.63, + "learning_rate": 1.472873213152462e-05, + "loss": 0.2896, + "step": 4101 + }, + { + "epoch": 3.63, + "learning_rate": 1.472620648066976e-05, + "loss": 0.2845, + "step": 4102 + }, + { + "epoch": 3.63, + "learning_rate": 1.4723680441564348e-05, + "loss": 0.2847, + "step": 4103 + }, + { + "epoch": 3.63, + "learning_rate": 1.4721154014415899e-05, + "loss": 0.2825, + "step": 4104 + }, + { + "epoch": 3.63, + "learning_rate": 1.4718627199431955e-05, + "loss": 0.3059, + "step": 4105 + }, + { + "epoch": 3.63, + "learning_rate": 1.4716099996820085e-05, + "loss": 0.2922, + "step": 4106 + }, + { + "epoch": 3.63, + "learning_rate": 1.47135724067879e-05, + "loss": 0.3008, + "step": 4107 + }, + { + "epoch": 3.63, + "learning_rate": 1.4711044429543036e-05, + "loss": 0.2699, + "step": 4108 + }, + { + "epoch": 3.63, + "learning_rate": 1.4708516065293164e-05, + "loss": 0.2863, + "step": 4109 + }, + { + "epoch": 3.64, + "learning_rate": 1.4705987314245978e-05, + "loss": 0.2773, + "step": 4110 + }, + { + "epoch": 3.64, + "learning_rate": 1.4703458176609221e-05, + "loss": 0.283, + "step": 4111 + }, + { + "epoch": 3.64, + "learning_rate": 1.470092865259065e-05, + "loss": 0.2869, + "step": 4112 + }, + { + "epoch": 3.64, + "learning_rate": 1.4698398742398069e-05, + "loss": 0.2818, + "step": 4113 + }, + { + "epoch": 3.64, + "learning_rate": 1.4695868446239298e-05, + "loss": 0.2883, + "step": 4114 + }, + { + "epoch": 3.64, + "learning_rate": 1.4693337764322204e-05, + "loss": 0.2875, + "step": 4115 + }, + { + "epoch": 3.64, + "learning_rate": 1.4690806696854676e-05, + "loss": 0.2692, + "step": 4116 + }, + { + "epoch": 3.64, + "learning_rate": 1.4688275244044632e-05, + "loss": 0.2916, + "step": 4117 + }, + { + "epoch": 3.64, + "learning_rate": 1.4685743406100035e-05, + "loss": 0.2958, + "step": 4118 + }, + { + "epoch": 3.64, + "learning_rate": 1.4683211183228866e-05, + "loss": 0.268, + "step": 4119 + }, + { + "epoch": 3.64, + "learning_rate": 1.4680678575639147e-05, + "loss": 0.2743, + "step": 4120 + }, + { + "epoch": 3.65, + "learning_rate": 1.4678145583538923e-05, + "loss": 0.2743, + "step": 4121 + }, + { + "epoch": 3.65, + "learning_rate": 1.4675612207136283e-05, + "loss": 0.2688, + "step": 4122 + }, + { + "epoch": 3.65, + "learning_rate": 1.4673078446639333e-05, + "loss": 0.2736, + "step": 4123 + }, + { + "epoch": 3.65, + "learning_rate": 1.467054430225622e-05, + "loss": 0.2905, + "step": 4124 + }, + { + "epoch": 3.65, + "learning_rate": 1.4668009774195123e-05, + "loss": 0.2783, + "step": 4125 + }, + { + "epoch": 3.65, + "learning_rate": 1.4665474862664242e-05, + "loss": 0.2843, + "step": 4126 + }, + { + "epoch": 3.65, + "learning_rate": 1.4662939567871823e-05, + "loss": 0.293, + "step": 4127 + }, + { + "epoch": 3.65, + "learning_rate": 1.4660403890026133e-05, + "loss": 0.3059, + "step": 4128 + }, + { + "epoch": 3.65, + "learning_rate": 1.465786782933548e-05, + "loss": 0.2682, + "step": 4129 + }, + { + "epoch": 3.65, + "learning_rate": 1.4655331386008188e-05, + "loss": 0.2756, + "step": 4130 + }, + { + "epoch": 3.65, + "learning_rate": 1.4652794560252626e-05, + "loss": 0.2814, + "step": 4131 + }, + { + "epoch": 3.66, + "learning_rate": 1.4650257352277195e-05, + "loss": 0.2776, + "step": 4132 + }, + { + "epoch": 3.66, + "learning_rate": 1.4647719762290314e-05, + "loss": 0.2825, + "step": 4133 + }, + { + "epoch": 3.66, + "learning_rate": 1.4645181790500448e-05, + "loss": 0.2796, + "step": 4134 + }, + { + "epoch": 3.66, + "learning_rate": 1.4642643437116086e-05, + "loss": 0.3093, + "step": 4135 + }, + { + "epoch": 3.66, + "learning_rate": 1.464010470234575e-05, + "loss": 0.3041, + "step": 4136 + }, + { + "epoch": 3.66, + "learning_rate": 1.4637565586397995e-05, + "loss": 0.2744, + "step": 4137 + }, + { + "epoch": 3.66, + "learning_rate": 1.4635026089481402e-05, + "loss": 0.2945, + "step": 4138 + }, + { + "epoch": 3.66, + "learning_rate": 1.4632486211804589e-05, + "loss": 0.2646, + "step": 4139 + }, + { + "epoch": 3.66, + "learning_rate": 1.46299459535762e-05, + "loss": 0.2907, + "step": 4140 + }, + { + "epoch": 3.66, + "learning_rate": 1.462740531500492e-05, + "loss": 0.2884, + "step": 4141 + }, + { + "epoch": 3.66, + "learning_rate": 1.462486429629945e-05, + "loss": 0.29, + "step": 4142 + }, + { + "epoch": 3.66, + "learning_rate": 1.4622322897668535e-05, + "loss": 0.2807, + "step": 4143 + }, + { + "epoch": 3.67, + "learning_rate": 1.461978111932095e-05, + "loss": 0.2992, + "step": 4144 + }, + { + "epoch": 3.67, + "learning_rate": 1.4617238961465493e-05, + "loss": 0.2757, + "step": 4145 + }, + { + "epoch": 3.67, + "learning_rate": 1.4614696424310999e-05, + "loss": 0.2697, + "step": 4146 + }, + { + "epoch": 3.67, + "learning_rate": 1.4612153508066335e-05, + "loss": 0.2966, + "step": 4147 + }, + { + "epoch": 3.67, + "learning_rate": 1.4609610212940399e-05, + "loss": 0.2863, + "step": 4148 + }, + { + "epoch": 3.67, + "learning_rate": 1.4607066539142117e-05, + "loss": 0.2779, + "step": 4149 + }, + { + "epoch": 3.67, + "learning_rate": 1.4604522486880446e-05, + "loss": 0.2915, + "step": 4150 + }, + { + "epoch": 3.67, + "learning_rate": 1.4601978056364381e-05, + "loss": 0.3046, + "step": 4151 + }, + { + "epoch": 3.67, + "learning_rate": 1.4599433247802936e-05, + "loss": 0.2845, + "step": 4152 + }, + { + "epoch": 3.67, + "learning_rate": 1.4596888061405172e-05, + "loss": 0.3029, + "step": 4153 + }, + { + "epoch": 3.67, + "learning_rate": 1.4594342497380166e-05, + "loss": 0.2778, + "step": 4154 + }, + { + "epoch": 3.68, + "learning_rate": 1.4591796555937033e-05, + "loss": 0.2728, + "step": 4155 + }, + { + "epoch": 3.68, + "learning_rate": 1.4589250237284916e-05, + "loss": 0.2859, + "step": 4156 + }, + { + "epoch": 3.68, + "learning_rate": 1.4586703541632994e-05, + "loss": 0.2701, + "step": 4157 + }, + { + "epoch": 3.68, + "learning_rate": 1.4584156469190479e-05, + "loss": 0.2874, + "step": 4158 + }, + { + "epoch": 3.68, + "learning_rate": 1.4581609020166597e-05, + "loss": 0.2872, + "step": 4159 + }, + { + "epoch": 3.68, + "learning_rate": 1.4579061194770628e-05, + "loss": 0.2708, + "step": 4160 + }, + { + "epoch": 3.68, + "learning_rate": 1.4576512993211865e-05, + "loss": 0.2954, + "step": 4161 + }, + { + "epoch": 3.68, + "learning_rate": 1.4573964415699643e-05, + "loss": 0.2761, + "step": 4162 + }, + { + "epoch": 3.68, + "learning_rate": 1.4571415462443323e-05, + "loss": 0.2753, + "step": 4163 + }, + { + "epoch": 3.68, + "learning_rate": 1.4568866133652298e-05, + "loss": 0.3052, + "step": 4164 + }, + { + "epoch": 3.68, + "learning_rate": 1.4566316429535986e-05, + "loss": 0.2814, + "step": 4165 + }, + { + "epoch": 3.69, + "learning_rate": 1.4563766350303848e-05, + "loss": 0.2862, + "step": 4166 + }, + { + "epoch": 3.69, + "learning_rate": 1.4561215896165368e-05, + "loss": 0.2891, + "step": 4167 + }, + { + "epoch": 3.69, + "learning_rate": 1.4558665067330057e-05, + "loss": 0.2744, + "step": 4168 + }, + { + "epoch": 3.69, + "learning_rate": 1.4556113864007469e-05, + "loss": 0.2868, + "step": 4169 + }, + { + "epoch": 3.69, + "learning_rate": 1.4553562286407174e-05, + "loss": 0.2723, + "step": 4170 + }, + { + "epoch": 3.69, + "learning_rate": 1.4551010334738784e-05, + "loss": 0.2558, + "step": 4171 + }, + { + "epoch": 3.69, + "learning_rate": 1.4548458009211939e-05, + "loss": 0.2809, + "step": 4172 + }, + { + "epoch": 3.69, + "learning_rate": 1.4545905310036306e-05, + "loss": 0.2869, + "step": 4173 + }, + { + "epoch": 3.69, + "learning_rate": 1.454335223742159e-05, + "loss": 0.2756, + "step": 4174 + }, + { + "epoch": 3.69, + "learning_rate": 1.4540798791577511e-05, + "loss": 0.2759, + "step": 4175 + }, + { + "epoch": 3.69, + "learning_rate": 1.4538244972713844e-05, + "loss": 0.3059, + "step": 4176 + }, + { + "epoch": 3.7, + "learning_rate": 1.4535690781040375e-05, + "loss": 0.2839, + "step": 4177 + }, + { + "epoch": 3.7, + "learning_rate": 1.4533136216766924e-05, + "loss": 0.2647, + "step": 4178 + }, + { + "epoch": 3.7, + "learning_rate": 1.453058128010335e-05, + "loss": 0.274, + "step": 4179 + }, + { + "epoch": 3.7, + "learning_rate": 1.4528025971259532e-05, + "loss": 0.2833, + "step": 4180 + }, + { + "epoch": 3.7, + "learning_rate": 1.4525470290445392e-05, + "loss": 0.2978, + "step": 4181 + }, + { + "epoch": 3.7, + "learning_rate": 1.4522914237870864e-05, + "loss": 0.2885, + "step": 4182 + }, + { + "epoch": 3.7, + "learning_rate": 1.4520357813745936e-05, + "loss": 0.2822, + "step": 4183 + }, + { + "epoch": 3.7, + "learning_rate": 1.4517801018280607e-05, + "loss": 0.2559, + "step": 4184 + }, + { + "epoch": 3.7, + "learning_rate": 1.4515243851684915e-05, + "loss": 0.2906, + "step": 4185 + }, + { + "epoch": 3.7, + "learning_rate": 1.4512686314168929e-05, + "loss": 0.2843, + "step": 4186 + }, + { + "epoch": 3.7, + "learning_rate": 1.4510128405942742e-05, + "loss": 0.2905, + "step": 4187 + }, + { + "epoch": 3.7, + "learning_rate": 1.4507570127216488e-05, + "loss": 0.2964, + "step": 4188 + }, + { + "epoch": 3.71, + "learning_rate": 1.4505011478200324e-05, + "loss": 0.2943, + "step": 4189 + }, + { + "epoch": 3.71, + "learning_rate": 1.4502452459104438e-05, + "loss": 0.2723, + "step": 4190 + }, + { + "epoch": 3.71, + "learning_rate": 1.449989307013905e-05, + "loss": 0.2784, + "step": 4191 + }, + { + "epoch": 3.71, + "learning_rate": 1.4497333311514408e-05, + "loss": 0.2726, + "step": 4192 + }, + { + "epoch": 3.71, + "learning_rate": 1.4494773183440797e-05, + "loss": 0.3009, + "step": 4193 + }, + { + "epoch": 3.71, + "learning_rate": 1.4492212686128522e-05, + "loss": 0.2883, + "step": 4194 + }, + { + "epoch": 3.71, + "learning_rate": 1.4489651819787926e-05, + "loss": 0.3049, + "step": 4195 + }, + { + "epoch": 3.71, + "learning_rate": 1.4487090584629382e-05, + "loss": 0.293, + "step": 4196 + }, + { + "epoch": 3.71, + "learning_rate": 1.448452898086329e-05, + "loss": 0.2673, + "step": 4197 + }, + { + "epoch": 3.71, + "learning_rate": 1.4481967008700081e-05, + "loss": 0.2849, + "step": 4198 + }, + { + "epoch": 3.71, + "learning_rate": 1.4479404668350219e-05, + "loss": 0.2777, + "step": 4199 + }, + { + "epoch": 3.72, + "learning_rate": 1.4476841960024195e-05, + "loss": 0.2842, + "step": 4200 + }, + { + "epoch": 3.72, + "learning_rate": 1.447427888393253e-05, + "loss": 0.2704, + "step": 4201 + }, + { + "epoch": 3.72, + "learning_rate": 1.4471715440285778e-05, + "loss": 0.2832, + "step": 4202 + }, + { + "epoch": 3.72, + "learning_rate": 1.4469151629294524e-05, + "loss": 0.2594, + "step": 4203 + }, + { + "epoch": 3.72, + "learning_rate": 1.4466587451169381e-05, + "loss": 0.2845, + "step": 4204 + }, + { + "epoch": 3.72, + "learning_rate": 1.4464022906120989e-05, + "loss": 0.2875, + "step": 4205 + }, + { + "epoch": 3.72, + "learning_rate": 1.4461457994360021e-05, + "loss": 0.291, + "step": 4206 + }, + { + "epoch": 3.72, + "learning_rate": 1.4458892716097188e-05, + "loss": 0.3109, + "step": 4207 + }, + { + "epoch": 3.72, + "learning_rate": 1.4456327071543213e-05, + "loss": 0.2804, + "step": 4208 + }, + { + "epoch": 3.72, + "learning_rate": 1.4453761060908869e-05, + "loss": 0.2944, + "step": 4209 + }, + { + "epoch": 3.72, + "learning_rate": 1.445119468440494e-05, + "loss": 0.286, + "step": 4210 + }, + { + "epoch": 3.73, + "learning_rate": 1.444862794224226e-05, + "loss": 0.287, + "step": 4211 + }, + { + "epoch": 3.73, + "learning_rate": 1.4446060834631681e-05, + "loss": 0.2855, + "step": 4212 + }, + { + "epoch": 3.73, + "learning_rate": 1.4443493361784083e-05, + "loss": 0.3006, + "step": 4213 + }, + { + "epoch": 3.73, + "learning_rate": 1.4440925523910379e-05, + "loss": 0.2698, + "step": 4214 + }, + { + "epoch": 3.73, + "learning_rate": 1.4438357321221514e-05, + "loss": 0.2878, + "step": 4215 + }, + { + "epoch": 3.73, + "learning_rate": 1.4435788753928468e-05, + "loss": 0.284, + "step": 4216 + }, + { + "epoch": 3.73, + "learning_rate": 1.4433219822242237e-05, + "loss": 0.2875, + "step": 4217 + }, + { + "epoch": 3.73, + "learning_rate": 1.443065052637386e-05, + "loss": 0.2863, + "step": 4218 + }, + { + "epoch": 3.73, + "learning_rate": 1.4428080866534397e-05, + "loss": 0.2711, + "step": 4219 + }, + { + "epoch": 3.73, + "learning_rate": 1.4425510842934943e-05, + "loss": 0.272, + "step": 4220 + }, + { + "epoch": 3.73, + "learning_rate": 1.4422940455786621e-05, + "loss": 0.2841, + "step": 4221 + }, + { + "epoch": 3.73, + "learning_rate": 1.4420369705300585e-05, + "loss": 0.2697, + "step": 4222 + }, + { + "epoch": 3.74, + "learning_rate": 1.4417798591688019e-05, + "loss": 0.2832, + "step": 4223 + }, + { + "epoch": 3.74, + "learning_rate": 1.4415227115160136e-05, + "loss": 0.2803, + "step": 4224 + }, + { + "epoch": 3.74, + "learning_rate": 1.4412655275928176e-05, + "loss": 0.2831, + "step": 4225 + }, + { + "epoch": 3.74, + "learning_rate": 1.4410083074203413e-05, + "loss": 0.2886, + "step": 4226 + }, + { + "epoch": 3.74, + "learning_rate": 1.440751051019715e-05, + "loss": 0.2836, + "step": 4227 + }, + { + "epoch": 3.74, + "learning_rate": 1.4404937584120722e-05, + "loss": 0.2808, + "step": 4228 + }, + { + "epoch": 3.74, + "learning_rate": 1.4402364296185485e-05, + "loss": 0.277, + "step": 4229 + }, + { + "epoch": 3.74, + "learning_rate": 1.4399790646602836e-05, + "loss": 0.2865, + "step": 4230 + }, + { + "epoch": 3.74, + "learning_rate": 1.439721663558419e-05, + "loss": 0.2945, + "step": 4231 + }, + { + "epoch": 3.74, + "learning_rate": 1.4394642263341006e-05, + "loss": 0.2998, + "step": 4232 + }, + { + "epoch": 3.74, + "learning_rate": 1.4392067530084759e-05, + "loss": 0.2849, + "step": 4233 + }, + { + "epoch": 3.75, + "learning_rate": 1.4389492436026957e-05, + "loss": 0.2924, + "step": 4234 + }, + { + "epoch": 3.75, + "learning_rate": 1.4386916981379149e-05, + "loss": 0.2905, + "step": 4235 + }, + { + "epoch": 3.75, + "learning_rate": 1.4384341166352898e-05, + "loss": 0.285, + "step": 4236 + }, + { + "epoch": 3.75, + "learning_rate": 1.4381764991159803e-05, + "loss": 0.284, + "step": 4237 + }, + { + "epoch": 3.75, + "learning_rate": 1.4379188456011497e-05, + "loss": 0.2814, + "step": 4238 + }, + { + "epoch": 3.75, + "learning_rate": 1.4376611561119636e-05, + "loss": 0.2893, + "step": 4239 + }, + { + "epoch": 3.75, + "learning_rate": 1.4374034306695905e-05, + "loss": 0.2775, + "step": 4240 + }, + { + "epoch": 3.75, + "learning_rate": 1.4371456692952029e-05, + "loss": 0.2909, + "step": 4241 + }, + { + "epoch": 3.75, + "learning_rate": 1.4368878720099748e-05, + "loss": 0.293, + "step": 4242 + }, + { + "epoch": 3.75, + "learning_rate": 1.436630038835084e-05, + "loss": 0.2815, + "step": 4243 + }, + { + "epoch": 3.75, + "learning_rate": 1.436372169791711e-05, + "loss": 0.2935, + "step": 4244 + }, + { + "epoch": 3.76, + "learning_rate": 1.4361142649010397e-05, + "loss": 0.2734, + "step": 4245 + }, + { + "epoch": 3.76, + "learning_rate": 1.4358563241842567e-05, + "loss": 0.2948, + "step": 4246 + }, + { + "epoch": 3.76, + "learning_rate": 1.4355983476625508e-05, + "loss": 0.2784, + "step": 4247 + }, + { + "epoch": 3.76, + "learning_rate": 1.4353403353571148e-05, + "loss": 0.2913, + "step": 4248 + }, + { + "epoch": 3.76, + "learning_rate": 1.4350822872891442e-05, + "loss": 0.2827, + "step": 4249 + }, + { + "epoch": 3.76, + "learning_rate": 1.4348242034798362e-05, + "loss": 0.2735, + "step": 4250 + }, + { + "epoch": 3.76, + "learning_rate": 1.4345660839503935e-05, + "loss": 0.2973, + "step": 4251 + }, + { + "epoch": 3.76, + "learning_rate": 1.434307928722019e-05, + "loss": 0.307, + "step": 4252 + }, + { + "epoch": 3.76, + "learning_rate": 1.4340497378159204e-05, + "loss": 0.2835, + "step": 4253 + }, + { + "epoch": 3.76, + "learning_rate": 1.4337915112533077e-05, + "loss": 0.2832, + "step": 4254 + }, + { + "epoch": 3.76, + "learning_rate": 1.4335332490553935e-05, + "loss": 0.2824, + "step": 4255 + }, + { + "epoch": 3.76, + "learning_rate": 1.4332749512433938e-05, + "loss": 0.2736, + "step": 4256 + }, + { + "epoch": 3.77, + "learning_rate": 1.433016617838527e-05, + "loss": 0.2848, + "step": 4257 + }, + { + "epoch": 3.77, + "learning_rate": 1.4327582488620155e-05, + "loss": 0.2765, + "step": 4258 + }, + { + "epoch": 3.77, + "learning_rate": 1.4324998443350835e-05, + "loss": 0.2839, + "step": 4259 + }, + { + "epoch": 3.77, + "learning_rate": 1.4322414042789582e-05, + "loss": 0.2865, + "step": 4260 + }, + { + "epoch": 3.77, + "learning_rate": 1.431982928714871e-05, + "loss": 0.2838, + "step": 4261 + }, + { + "epoch": 3.77, + "learning_rate": 1.4317244176640543e-05, + "loss": 0.2684, + "step": 4262 + }, + { + "epoch": 3.77, + "learning_rate": 1.4314658711477447e-05, + "loss": 0.2859, + "step": 4263 + }, + { + "epoch": 3.77, + "learning_rate": 1.4312072891871815e-05, + "loss": 0.2751, + "step": 4264 + }, + { + "epoch": 3.77, + "learning_rate": 1.430948671803607e-05, + "loss": 0.2886, + "step": 4265 + }, + { + "epoch": 3.77, + "learning_rate": 1.430690019018266e-05, + "loss": 0.2997, + "step": 4266 + }, + { + "epoch": 3.77, + "learning_rate": 1.430431330852406e-05, + "loss": 0.2828, + "step": 4267 + }, + { + "epoch": 3.78, + "learning_rate": 1.4301726073272785e-05, + "loss": 0.2864, + "step": 4268 + }, + { + "epoch": 3.78, + "learning_rate": 1.429913848464137e-05, + "loss": 0.2931, + "step": 4269 + }, + { + "epoch": 3.78, + "learning_rate": 1.429655054284238e-05, + "loss": 0.3047, + "step": 4270 + }, + { + "epoch": 3.78, + "learning_rate": 1.4293962248088413e-05, + "loss": 0.289, + "step": 4271 + }, + { + "epoch": 3.78, + "learning_rate": 1.4291373600592094e-05, + "loss": 0.2824, + "step": 4272 + }, + { + "epoch": 3.78, + "learning_rate": 1.428878460056607e-05, + "loss": 0.2986, + "step": 4273 + }, + { + "epoch": 3.78, + "learning_rate": 1.4286195248223029e-05, + "loss": 0.2626, + "step": 4274 + }, + { + "epoch": 3.78, + "learning_rate": 1.4283605543775684e-05, + "loss": 0.2873, + "step": 4275 + }, + { + "epoch": 3.78, + "learning_rate": 1.4281015487436767e-05, + "loss": 0.2794, + "step": 4276 + }, + { + "epoch": 3.78, + "learning_rate": 1.4278425079419058e-05, + "loss": 0.2779, + "step": 4277 + }, + { + "epoch": 3.78, + "learning_rate": 1.4275834319935347e-05, + "loss": 0.2814, + "step": 4278 + }, + { + "epoch": 3.79, + "learning_rate": 1.4273243209198464e-05, + "loss": 0.2685, + "step": 4279 + }, + { + "epoch": 3.79, + "learning_rate": 1.4270651747421263e-05, + "loss": 0.2693, + "step": 4280 + }, + { + "epoch": 3.79, + "learning_rate": 1.4268059934816627e-05, + "loss": 0.269, + "step": 4281 + }, + { + "epoch": 3.79, + "learning_rate": 1.426546777159748e-05, + "loss": 0.2663, + "step": 4282 + }, + { + "epoch": 3.79, + "learning_rate": 1.4262875257976747e-05, + "loss": 0.2974, + "step": 4283 + }, + { + "epoch": 3.79, + "learning_rate": 1.4260282394167413e-05, + "loss": 0.2691, + "step": 4284 + }, + { + "epoch": 3.79, + "learning_rate": 1.425768918038247e-05, + "loss": 0.2603, + "step": 4285 + }, + { + "epoch": 3.79, + "learning_rate": 1.425509561683495e-05, + "loss": 0.2776, + "step": 4286 + }, + { + "epoch": 3.79, + "learning_rate": 1.4252501703737913e-05, + "loss": 0.2913, + "step": 4287 + }, + { + "epoch": 3.79, + "learning_rate": 1.424990744130444e-05, + "loss": 0.2794, + "step": 4288 + }, + { + "epoch": 3.79, + "learning_rate": 1.4247312829747645e-05, + "loss": 0.2925, + "step": 4289 + }, + { + "epoch": 3.79, + "learning_rate": 1.4244717869280677e-05, + "loss": 0.2952, + "step": 4290 + }, + { + "epoch": 3.8, + "learning_rate": 1.4242122560116705e-05, + "loss": 0.2853, + "step": 4291 + }, + { + "epoch": 3.8, + "learning_rate": 1.4239526902468925e-05, + "loss": 0.311, + "step": 4292 + }, + { + "epoch": 3.8, + "learning_rate": 1.4236930896550571e-05, + "loss": 0.2902, + "step": 4293 + }, + { + "epoch": 3.8, + "learning_rate": 1.4234334542574906e-05, + "loss": 0.3126, + "step": 4294 + }, + { + "epoch": 3.8, + "learning_rate": 1.4231737840755204e-05, + "loss": 0.271, + "step": 4295 + }, + { + "epoch": 3.8, + "learning_rate": 1.422914079130479e-05, + "loss": 0.2778, + "step": 4296 + }, + { + "epoch": 3.8, + "learning_rate": 1.4226543394437002e-05, + "loss": 0.2802, + "step": 4297 + }, + { + "epoch": 3.8, + "learning_rate": 1.4223945650365218e-05, + "loss": 0.2721, + "step": 4298 + }, + { + "epoch": 3.8, + "learning_rate": 1.4221347559302832e-05, + "loss": 0.2909, + "step": 4299 + }, + { + "epoch": 3.8, + "learning_rate": 1.4218749121463278e-05, + "loss": 0.3006, + "step": 4300 + }, + { + "epoch": 3.8, + "learning_rate": 1.4216150337060013e-05, + "loss": 0.289, + "step": 4301 + }, + { + "epoch": 3.81, + "learning_rate": 1.421355120630652e-05, + "loss": 0.2789, + "step": 4302 + }, + { + "epoch": 3.81, + "learning_rate": 1.4210951729416318e-05, + "loss": 0.2812, + "step": 4303 + }, + { + "epoch": 3.81, + "learning_rate": 1.4208351906602947e-05, + "loss": 0.2789, + "step": 4304 + }, + { + "epoch": 3.81, + "learning_rate": 1.4205751738079978e-05, + "loss": 0.2856, + "step": 4305 + }, + { + "epoch": 3.81, + "learning_rate": 1.420315122406101e-05, + "loss": 0.2787, + "step": 4306 + }, + { + "epoch": 3.81, + "learning_rate": 1.4200550364759678e-05, + "loss": 0.2808, + "step": 4307 + }, + { + "epoch": 3.81, + "learning_rate": 1.419794916038963e-05, + "loss": 0.2629, + "step": 4308 + }, + { + "epoch": 3.81, + "learning_rate": 1.4195347611164556e-05, + "loss": 0.286, + "step": 4309 + }, + { + "epoch": 3.81, + "learning_rate": 1.419274571729817e-05, + "loss": 0.2839, + "step": 4310 + }, + { + "epoch": 3.81, + "learning_rate": 1.4190143479004209e-05, + "loss": 0.2664, + "step": 4311 + }, + { + "epoch": 3.81, + "learning_rate": 1.4187540896496443e-05, + "loss": 0.2846, + "step": 4312 + }, + { + "epoch": 3.82, + "learning_rate": 1.4184937969988675e-05, + "loss": 0.2716, + "step": 4313 + }, + { + "epoch": 3.82, + "learning_rate": 1.4182334699694728e-05, + "loss": 0.304, + "step": 4314 + }, + { + "epoch": 3.82, + "learning_rate": 1.4179731085828458e-05, + "loss": 0.2914, + "step": 4315 + }, + { + "epoch": 3.82, + "learning_rate": 1.4177127128603748e-05, + "loss": 0.2904, + "step": 4316 + }, + { + "epoch": 3.82, + "learning_rate": 1.4174522828234508e-05, + "loss": 0.2668, + "step": 4317 + }, + { + "epoch": 3.82, + "learning_rate": 1.4171918184934677e-05, + "loss": 0.2846, + "step": 4318 + }, + { + "epoch": 3.82, + "learning_rate": 1.4169313198918223e-05, + "loss": 0.273, + "step": 4319 + }, + { + "epoch": 3.82, + "learning_rate": 1.4166707870399139e-05, + "loss": 0.2807, + "step": 4320 + }, + { + "epoch": 3.82, + "learning_rate": 1.4164102199591457e-05, + "loss": 0.276, + "step": 4321 + }, + { + "epoch": 3.82, + "learning_rate": 1.4161496186709218e-05, + "loss": 0.2783, + "step": 4322 + }, + { + "epoch": 3.82, + "learning_rate": 1.4158889831966507e-05, + "loss": 0.2839, + "step": 4323 + }, + { + "epoch": 3.83, + "learning_rate": 1.4156283135577437e-05, + "loss": 0.2606, + "step": 4324 + }, + { + "epoch": 3.83, + "learning_rate": 1.4153676097756132e-05, + "loss": 0.2717, + "step": 4325 + }, + { + "epoch": 3.83, + "learning_rate": 1.415106871871677e-05, + "loss": 0.2785, + "step": 4326 + }, + { + "epoch": 3.83, + "learning_rate": 1.4148460998673533e-05, + "loss": 0.2716, + "step": 4327 + }, + { + "epoch": 3.83, + "learning_rate": 1.4145852937840642e-05, + "loss": 0.2746, + "step": 4328 + }, + { + "epoch": 3.83, + "learning_rate": 1.4143244536432353e-05, + "loss": 0.2758, + "step": 4329 + }, + { + "epoch": 3.83, + "learning_rate": 1.4140635794662934e-05, + "loss": 0.2911, + "step": 4330 + }, + { + "epoch": 3.83, + "learning_rate": 1.4138026712746694e-05, + "loss": 0.2729, + "step": 4331 + }, + { + "epoch": 3.83, + "learning_rate": 1.413541729089796e-05, + "loss": 0.2696, + "step": 4332 + }, + { + "epoch": 3.83, + "learning_rate": 1.4132807529331096e-05, + "loss": 0.2989, + "step": 4333 + }, + { + "epoch": 3.83, + "learning_rate": 1.4130197428260487e-05, + "loss": 0.2798, + "step": 4334 + }, + { + "epoch": 3.83, + "learning_rate": 1.4127586987900554e-05, + "loss": 0.2826, + "step": 4335 + }, + { + "epoch": 3.84, + "learning_rate": 1.4124976208465737e-05, + "loss": 0.2901, + "step": 4336 + }, + { + "epoch": 3.84, + "learning_rate": 1.4122365090170504e-05, + "loss": 0.2809, + "step": 4337 + }, + { + "epoch": 3.84, + "learning_rate": 1.4119753633229361e-05, + "loss": 0.2753, + "step": 4338 + }, + { + "epoch": 3.84, + "learning_rate": 1.4117141837856832e-05, + "loss": 0.2883, + "step": 4339 + }, + { + "epoch": 3.84, + "learning_rate": 1.4114529704267473e-05, + "loss": 0.2933, + "step": 4340 + }, + { + "epoch": 3.84, + "learning_rate": 1.4111917232675864e-05, + "loss": 0.2878, + "step": 4341 + }, + { + "epoch": 3.84, + "learning_rate": 1.4109304423296618e-05, + "loss": 0.2823, + "step": 4342 + }, + { + "epoch": 3.84, + "learning_rate": 1.4106691276344372e-05, + "loss": 0.2719, + "step": 4343 + }, + { + "epoch": 3.84, + "learning_rate": 1.4104077792033792e-05, + "loss": 0.2719, + "step": 4344 + }, + { + "epoch": 3.84, + "learning_rate": 1.4101463970579575e-05, + "loss": 0.288, + "step": 4345 + }, + { + "epoch": 3.84, + "learning_rate": 1.4098849812196436e-05, + "loss": 0.29, + "step": 4346 + }, + { + "epoch": 3.85, + "learning_rate": 1.4096235317099132e-05, + "loss": 0.2786, + "step": 4347 + }, + { + "epoch": 3.85, + "learning_rate": 1.4093620485502433e-05, + "loss": 0.2926, + "step": 4348 + }, + { + "epoch": 3.85, + "learning_rate": 1.4091005317621144e-05, + "loss": 0.2813, + "step": 4349 + }, + { + "epoch": 3.85, + "learning_rate": 1.4088389813670102e-05, + "loss": 0.299, + "step": 4350 + }, + { + "epoch": 3.85, + "learning_rate": 1.408577397386416e-05, + "loss": 0.2801, + "step": 4351 + }, + { + "epoch": 3.85, + "learning_rate": 1.4083157798418213e-05, + "loss": 0.277, + "step": 4352 + }, + { + "epoch": 3.85, + "learning_rate": 1.4080541287547168e-05, + "loss": 0.2957, + "step": 4353 + }, + { + "epoch": 3.85, + "learning_rate": 1.4077924441465973e-05, + "loss": 0.2938, + "step": 4354 + }, + { + "epoch": 3.85, + "learning_rate": 1.4075307260389593e-05, + "loss": 0.2968, + "step": 4355 + }, + { + "epoch": 3.85, + "learning_rate": 1.4072689744533028e-05, + "loss": 0.2697, + "step": 4356 + }, + { + "epoch": 3.85, + "learning_rate": 1.4070071894111306e-05, + "loss": 0.285, + "step": 4357 + }, + { + "epoch": 3.86, + "learning_rate": 1.4067453709339471e-05, + "loss": 0.2708, + "step": 4358 + }, + { + "epoch": 3.86, + "learning_rate": 1.4064835190432612e-05, + "loss": 0.3036, + "step": 4359 + }, + { + "epoch": 3.86, + "learning_rate": 1.4062216337605831e-05, + "loss": 0.2963, + "step": 4360 + }, + { + "epoch": 3.86, + "learning_rate": 1.4059597151074264e-05, + "loss": 0.2668, + "step": 4361 + }, + { + "epoch": 3.86, + "learning_rate": 1.4056977631053074e-05, + "loss": 0.2701, + "step": 4362 + }, + { + "epoch": 3.86, + "learning_rate": 1.4054357777757451e-05, + "loss": 0.2717, + "step": 4363 + }, + { + "epoch": 3.86, + "learning_rate": 1.4051737591402608e-05, + "loss": 0.2934, + "step": 4364 + }, + { + "epoch": 3.86, + "learning_rate": 1.4049117072203791e-05, + "loss": 0.2851, + "step": 4365 + }, + { + "epoch": 3.86, + "learning_rate": 1.4046496220376273e-05, + "loss": 0.2905, + "step": 4366 + }, + { + "epoch": 3.86, + "learning_rate": 1.4043875036135353e-05, + "loss": 0.2809, + "step": 4367 + }, + { + "epoch": 3.86, + "learning_rate": 1.4041253519696357e-05, + "loss": 0.2912, + "step": 4368 + }, + { + "epoch": 3.86, + "learning_rate": 1.4038631671274637e-05, + "loss": 0.2812, + "step": 4369 + }, + { + "epoch": 3.87, + "learning_rate": 1.4036009491085576e-05, + "loss": 0.2649, + "step": 4370 + }, + { + "epoch": 3.87, + "learning_rate": 1.403338697934458e-05, + "loss": 0.2806, + "step": 4371 + }, + { + "epoch": 3.87, + "learning_rate": 1.4030764136267084e-05, + "loss": 0.2656, + "step": 4372 + }, + { + "epoch": 3.87, + "learning_rate": 1.4028140962068554e-05, + "loss": 0.2899, + "step": 4373 + }, + { + "epoch": 3.87, + "learning_rate": 1.4025517456964473e-05, + "loss": 0.2701, + "step": 4374 + }, + { + "epoch": 3.87, + "learning_rate": 1.4022893621170368e-05, + "loss": 0.2867, + "step": 4375 + }, + { + "epoch": 3.87, + "learning_rate": 1.4020269454901774e-05, + "loss": 0.2809, + "step": 4376 + }, + { + "epoch": 3.87, + "learning_rate": 1.4017644958374264e-05, + "loss": 0.2876, + "step": 4377 + }, + { + "epoch": 3.87, + "learning_rate": 1.4015020131803443e-05, + "loss": 0.277, + "step": 4378 + }, + { + "epoch": 3.87, + "learning_rate": 1.4012394975404926e-05, + "loss": 0.2807, + "step": 4379 + }, + { + "epoch": 3.87, + "learning_rate": 1.4009769489394374e-05, + "loss": 0.2774, + "step": 4380 + }, + { + "epoch": 3.88, + "learning_rate": 1.400714367398746e-05, + "loss": 0.2556, + "step": 4381 + }, + { + "epoch": 3.88, + "learning_rate": 1.40045175293999e-05, + "loss": 0.2987, + "step": 4382 + }, + { + "epoch": 3.88, + "learning_rate": 1.4001891055847416e-05, + "loss": 0.2809, + "step": 4383 + }, + { + "epoch": 3.88, + "learning_rate": 1.3999264253545777e-05, + "loss": 0.2513, + "step": 4384 + }, + { + "epoch": 3.88, + "learning_rate": 1.3996637122710768e-05, + "loss": 0.2908, + "step": 4385 + }, + { + "epoch": 3.88, + "learning_rate": 1.3994009663558204e-05, + "loss": 0.2846, + "step": 4386 + }, + { + "epoch": 3.88, + "learning_rate": 1.3991381876303925e-05, + "loss": 0.2819, + "step": 4387 + }, + { + "epoch": 3.88, + "learning_rate": 1.3988753761163802e-05, + "loss": 0.2903, + "step": 4388 + }, + { + "epoch": 3.88, + "learning_rate": 1.3986125318353732e-05, + "loss": 0.2957, + "step": 4389 + }, + { + "epoch": 3.88, + "learning_rate": 1.3983496548089635e-05, + "loss": 0.3108, + "step": 4390 + }, + { + "epoch": 3.88, + "learning_rate": 1.3980867450587459e-05, + "loss": 0.2671, + "step": 4391 + }, + { + "epoch": 3.89, + "learning_rate": 1.3978238026063185e-05, + "loss": 0.2984, + "step": 4392 + }, + { + "epoch": 3.89, + "learning_rate": 1.397560827473281e-05, + "loss": 0.3043, + "step": 4393 + }, + { + "epoch": 3.89, + "learning_rate": 1.3972978196812367e-05, + "loss": 0.2656, + "step": 4394 + }, + { + "epoch": 3.89, + "learning_rate": 1.3970347792517916e-05, + "loss": 0.2823, + "step": 4395 + }, + { + "epoch": 3.89, + "learning_rate": 1.3967717062065538e-05, + "loss": 0.2819, + "step": 4396 + }, + { + "epoch": 3.89, + "learning_rate": 1.3965086005671343e-05, + "loss": 0.2891, + "step": 4397 + }, + { + "epoch": 3.89, + "learning_rate": 1.3962454623551464e-05, + "loss": 0.2973, + "step": 4398 + }, + { + "epoch": 3.89, + "learning_rate": 1.3959822915922074e-05, + "loss": 0.2965, + "step": 4399 + }, + { + "epoch": 3.89, + "learning_rate": 1.3957190882999357e-05, + "loss": 0.2726, + "step": 4400 + }, + { + "epoch": 3.89, + "learning_rate": 1.3954558524999535e-05, + "loss": 0.2786, + "step": 4401 + }, + { + "epoch": 3.89, + "learning_rate": 1.3951925842138846e-05, + "loss": 0.2831, + "step": 4402 + }, + { + "epoch": 3.89, + "learning_rate": 1.3949292834633568e-05, + "loss": 0.2696, + "step": 4403 + }, + { + "epoch": 3.9, + "learning_rate": 1.3946659502699993e-05, + "loss": 0.2921, + "step": 4404 + }, + { + "epoch": 3.9, + "learning_rate": 1.3944025846554447e-05, + "loss": 0.2868, + "step": 4405 + }, + { + "epoch": 3.9, + "learning_rate": 1.3941391866413283e-05, + "loss": 0.2864, + "step": 4406 + }, + { + "epoch": 3.9, + "learning_rate": 1.3938757562492873e-05, + "loss": 0.2875, + "step": 4407 + }, + { + "epoch": 3.9, + "learning_rate": 1.3936122935009628e-05, + "loss": 0.277, + "step": 4408 + }, + { + "epoch": 3.9, + "learning_rate": 1.3933487984179973e-05, + "loss": 0.2754, + "step": 4409 + }, + { + "epoch": 3.9, + "learning_rate": 1.3930852710220366e-05, + "loss": 0.3128, + "step": 4410 + }, + { + "epoch": 3.9, + "learning_rate": 1.3928217113347292e-05, + "loss": 0.2699, + "step": 4411 + }, + { + "epoch": 3.9, + "learning_rate": 1.3925581193777263e-05, + "loss": 0.2805, + "step": 4412 + }, + { + "epoch": 3.9, + "learning_rate": 1.3922944951726811e-05, + "loss": 0.2834, + "step": 4413 + }, + { + "epoch": 3.9, + "learning_rate": 1.3920308387412502e-05, + "loss": 0.2719, + "step": 4414 + }, + { + "epoch": 3.91, + "learning_rate": 1.3917671501050927e-05, + "loss": 0.2951, + "step": 4415 + }, + { + "epoch": 3.91, + "learning_rate": 1.3915034292858698e-05, + "loss": 0.281, + "step": 4416 + }, + { + "epoch": 3.91, + "learning_rate": 1.3912396763052463e-05, + "loss": 0.287, + "step": 4417 + }, + { + "epoch": 3.91, + "learning_rate": 1.390975891184889e-05, + "loss": 0.2882, + "step": 4418 + }, + { + "epoch": 3.91, + "learning_rate": 1.390712073946467e-05, + "loss": 0.3021, + "step": 4419 + }, + { + "epoch": 3.91, + "learning_rate": 1.3904482246116527e-05, + "loss": 0.2737, + "step": 4420 + }, + { + "epoch": 3.91, + "learning_rate": 1.3901843432021207e-05, + "loss": 0.2704, + "step": 4421 + }, + { + "epoch": 3.91, + "learning_rate": 1.3899204297395492e-05, + "loss": 0.2901, + "step": 4422 + }, + { + "epoch": 3.91, + "learning_rate": 1.3896564842456172e-05, + "loss": 0.2908, + "step": 4423 + }, + { + "epoch": 3.91, + "learning_rate": 1.3893925067420086e-05, + "loss": 0.2774, + "step": 4424 + }, + { + "epoch": 3.91, + "learning_rate": 1.3891284972504078e-05, + "loss": 0.278, + "step": 4425 + }, + { + "epoch": 3.92, + "learning_rate": 1.388864455792503e-05, + "loss": 0.272, + "step": 4426 + }, + { + "epoch": 3.92, + "learning_rate": 1.3886003823899854e-05, + "loss": 0.2814, + "step": 4427 + }, + { + "epoch": 3.92, + "learning_rate": 1.3883362770645474e-05, + "loss": 0.2759, + "step": 4428 + }, + { + "epoch": 3.92, + "learning_rate": 1.3880721398378851e-05, + "loss": 0.2838, + "step": 4429 + }, + { + "epoch": 3.92, + "learning_rate": 1.3878079707316971e-05, + "loss": 0.2979, + "step": 4430 + }, + { + "epoch": 3.92, + "learning_rate": 1.3875437697676846e-05, + "loss": 0.2783, + "step": 4431 + }, + { + "epoch": 3.92, + "learning_rate": 1.3872795369675509e-05, + "loss": 0.2849, + "step": 4432 + }, + { + "epoch": 3.92, + "learning_rate": 1.3870152723530026e-05, + "loss": 0.2883, + "step": 4433 + }, + { + "epoch": 3.92, + "learning_rate": 1.3867509759457488e-05, + "loss": 0.3036, + "step": 4434 + }, + { + "epoch": 3.92, + "learning_rate": 1.3864866477675003e-05, + "loss": 0.2773, + "step": 4435 + }, + { + "epoch": 3.92, + "learning_rate": 1.386222287839972e-05, + "loss": 0.2839, + "step": 4436 + }, + { + "epoch": 3.93, + "learning_rate": 1.3859578961848805e-05, + "loss": 0.2785, + "step": 4437 + }, + { + "epoch": 3.93, + "learning_rate": 1.3856934728239452e-05, + "loss": 0.3045, + "step": 4438 + }, + { + "epoch": 3.93, + "learning_rate": 1.3854290177788876e-05, + "loss": 0.2834, + "step": 4439 + }, + { + "epoch": 3.93, + "learning_rate": 1.3851645310714327e-05, + "loss": 0.2722, + "step": 4440 + }, + { + "epoch": 3.93, + "learning_rate": 1.384900012723308e-05, + "loss": 0.2686, + "step": 4441 + }, + { + "epoch": 3.93, + "learning_rate": 1.3846354627562426e-05, + "loss": 0.2832, + "step": 4442 + }, + { + "epoch": 3.93, + "learning_rate": 1.3843708811919689e-05, + "loss": 0.2679, + "step": 4443 + }, + { + "epoch": 3.93, + "learning_rate": 1.3841062680522224e-05, + "loss": 0.3039, + "step": 4444 + }, + { + "epoch": 3.93, + "learning_rate": 1.3838416233587404e-05, + "loss": 0.257, + "step": 4445 + }, + { + "epoch": 3.93, + "learning_rate": 1.3835769471332628e-05, + "loss": 0.289, + "step": 4446 + }, + { + "epoch": 3.93, + "learning_rate": 1.3833122393975327e-05, + "loss": 0.2786, + "step": 4447 + }, + { + "epoch": 3.93, + "learning_rate": 1.3830475001732952e-05, + "loss": 0.2982, + "step": 4448 + }, + { + "epoch": 3.94, + "learning_rate": 1.3827827294822984e-05, + "loss": 0.2924, + "step": 4449 + }, + { + "epoch": 3.94, + "learning_rate": 1.3825179273462927e-05, + "loss": 0.284, + "step": 4450 + }, + { + "epoch": 3.94, + "learning_rate": 1.3822530937870311e-05, + "loss": 0.2565, + "step": 4451 + }, + { + "epoch": 3.94, + "learning_rate": 1.3819882288262693e-05, + "loss": 0.277, + "step": 4452 + }, + { + "epoch": 3.94, + "learning_rate": 1.381723332485766e-05, + "loss": 0.2861, + "step": 4453 + }, + { + "epoch": 3.94, + "learning_rate": 1.3814584047872814e-05, + "loss": 0.2813, + "step": 4454 + }, + { + "epoch": 3.94, + "learning_rate": 1.3811934457525794e-05, + "loss": 0.2654, + "step": 4455 + }, + { + "epoch": 3.94, + "learning_rate": 1.380928455403425e-05, + "loss": 0.2764, + "step": 4456 + }, + { + "epoch": 3.94, + "learning_rate": 1.3806634337615881e-05, + "loss": 0.2878, + "step": 4457 + }, + { + "epoch": 3.94, + "learning_rate": 1.3803983808488388e-05, + "loss": 0.2959, + "step": 4458 + }, + { + "epoch": 3.94, + "learning_rate": 1.3801332966869514e-05, + "loss": 0.2813, + "step": 4459 + }, + { + "epoch": 3.95, + "learning_rate": 1.3798681812977019e-05, + "loss": 0.2651, + "step": 4460 + }, + { + "epoch": 3.95, + "learning_rate": 1.379603034702869e-05, + "loss": 0.2707, + "step": 4461 + }, + { + "epoch": 3.95, + "learning_rate": 1.3793378569242343e-05, + "loss": 0.2874, + "step": 4462 + }, + { + "epoch": 3.95, + "learning_rate": 1.3790726479835816e-05, + "loss": 0.2709, + "step": 4463 + }, + { + "epoch": 3.95, + "learning_rate": 1.3788074079026976e-05, + "loss": 0.2747, + "step": 4464 + }, + { + "epoch": 3.95, + "learning_rate": 1.3785421367033714e-05, + "loss": 0.2967, + "step": 4465 + }, + { + "epoch": 3.95, + "learning_rate": 1.378276834407394e-05, + "loss": 0.2939, + "step": 4466 + }, + { + "epoch": 3.95, + "learning_rate": 1.3780115010365603e-05, + "loss": 0.2775, + "step": 4467 + }, + { + "epoch": 3.95, + "learning_rate": 1.3777461366126667e-05, + "loss": 0.2619, + "step": 4468 + }, + { + "epoch": 3.95, + "learning_rate": 1.3774807411575123e-05, + "loss": 0.2921, + "step": 4469 + }, + { + "epoch": 3.95, + "learning_rate": 1.3772153146928995e-05, + "loss": 0.3019, + "step": 4470 + }, + { + "epoch": 3.96, + "learning_rate": 1.3769498572406321e-05, + "loss": 0.2723, + "step": 4471 + }, + { + "epoch": 3.96, + "learning_rate": 1.3766843688225174e-05, + "loss": 0.279, + "step": 4472 + }, + { + "epoch": 3.96, + "learning_rate": 1.3764188494603646e-05, + "loss": 0.276, + "step": 4473 + }, + { + "epoch": 3.96, + "learning_rate": 1.3761532991759859e-05, + "loss": 0.2689, + "step": 4474 + }, + { + "epoch": 3.96, + "learning_rate": 1.3758877179911953e-05, + "loss": 0.299, + "step": 4475 + }, + { + "epoch": 3.96, + "learning_rate": 1.375622105927811e-05, + "loss": 0.2665, + "step": 4476 + }, + { + "epoch": 3.96, + "learning_rate": 1.3753564630076515e-05, + "loss": 0.2895, + "step": 4477 + }, + { + "epoch": 3.96, + "learning_rate": 1.3750907892525396e-05, + "loss": 0.3042, + "step": 4478 + }, + { + "epoch": 3.96, + "learning_rate": 1.3748250846842997e-05, + "loss": 0.2887, + "step": 4479 + }, + { + "epoch": 3.96, + "learning_rate": 1.3745593493247594e-05, + "loss": 0.2868, + "step": 4480 + }, + { + "epoch": 3.96, + "learning_rate": 1.374293583195748e-05, + "loss": 0.2884, + "step": 4481 + }, + { + "epoch": 3.96, + "learning_rate": 1.3740277863190977e-05, + "loss": 0.2963, + "step": 4482 + }, + { + "epoch": 3.97, + "learning_rate": 1.3737619587166438e-05, + "loss": 0.2902, + "step": 4483 + }, + { + "epoch": 3.97, + "learning_rate": 1.3734961004102231e-05, + "loss": 0.2669, + "step": 4484 + }, + { + "epoch": 3.97, + "learning_rate": 1.373230211421676e-05, + "loss": 0.2807, + "step": 4485 + }, + { + "epoch": 3.97, + "learning_rate": 1.3729642917728444e-05, + "loss": 0.2894, + "step": 4486 + }, + { + "epoch": 3.97, + "learning_rate": 1.3726983414855737e-05, + "loss": 0.2661, + "step": 4487 + }, + { + "epoch": 3.97, + "learning_rate": 1.3724323605817106e-05, + "loss": 0.2956, + "step": 4488 + }, + { + "epoch": 3.97, + "learning_rate": 1.3721663490831056e-05, + "loss": 0.2687, + "step": 4489 + }, + { + "epoch": 3.97, + "learning_rate": 1.371900307011611e-05, + "loss": 0.2864, + "step": 4490 + }, + { + "epoch": 3.97, + "learning_rate": 1.3716342343890814e-05, + "loss": 0.301, + "step": 4491 + }, + { + "epoch": 3.97, + "learning_rate": 1.3713681312373747e-05, + "loss": 0.2737, + "step": 4492 + }, + { + "epoch": 3.97, + "learning_rate": 1.3711019975783509e-05, + "loss": 0.2814, + "step": 4493 + }, + { + "epoch": 3.98, + "learning_rate": 1.3708358334338723e-05, + "loss": 0.2888, + "step": 4494 + }, + { + "epoch": 3.98, + "learning_rate": 1.3705696388258033e-05, + "loss": 0.2675, + "step": 4495 + }, + { + "epoch": 3.98, + "learning_rate": 1.3703034137760123e-05, + "loss": 0.287, + "step": 4496 + }, + { + "epoch": 3.98, + "learning_rate": 1.370037158306369e-05, + "loss": 0.2637, + "step": 4497 + }, + { + "epoch": 3.98, + "learning_rate": 1.3697708724387453e-05, + "loss": 0.2697, + "step": 4498 + }, + { + "epoch": 3.98, + "learning_rate": 1.3695045561950172e-05, + "loss": 0.2909, + "step": 4499 + }, + { + "epoch": 3.98, + "learning_rate": 1.369238209597061e-05, + "loss": 0.2924, + "step": 4500 + }, + { + "epoch": 3.98, + "learning_rate": 1.3689718326667576e-05, + "loss": 0.2825, + "step": 4501 + }, + { + "epoch": 3.98, + "learning_rate": 1.3687054254259891e-05, + "loss": 0.2733, + "step": 4502 + }, + { + "epoch": 3.98, + "learning_rate": 1.3684389878966405e-05, + "loss": 0.2685, + "step": 4503 + }, + { + "epoch": 3.98, + "learning_rate": 1.368172520100599e-05, + "loss": 0.2817, + "step": 4504 + }, + { + "epoch": 3.99, + "learning_rate": 1.3679060220597549e-05, + "loss": 0.2777, + "step": 4505 + }, + { + "epoch": 3.99, + "learning_rate": 1.3676394937960003e-05, + "loss": 0.2534, + "step": 4506 + }, + { + "epoch": 3.99, + "learning_rate": 1.3673729353312301e-05, + "loss": 0.2886, + "step": 4507 + }, + { + "epoch": 3.99, + "learning_rate": 1.367106346687342e-05, + "loss": 0.2779, + "step": 4508 + }, + { + "epoch": 3.99, + "learning_rate": 1.3668397278862355e-05, + "loss": 0.2818, + "step": 4509 + }, + { + "epoch": 3.99, + "learning_rate": 1.366573078949813e-05, + "loss": 0.2875, + "step": 4510 + }, + { + "epoch": 3.99, + "learning_rate": 1.3663063998999793e-05, + "loss": 0.2911, + "step": 4511 + }, + { + "epoch": 3.99, + "learning_rate": 1.3660396907586417e-05, + "loss": 0.2882, + "step": 4512 + }, + { + "epoch": 3.99, + "learning_rate": 1.36577295154771e-05, + "loss": 0.2616, + "step": 4513 + }, + { + "epoch": 3.99, + "learning_rate": 1.3655061822890962e-05, + "loss": 0.2883, + "step": 4514 + }, + { + "epoch": 3.99, + "learning_rate": 1.3652393830047152e-05, + "loss": 0.2732, + "step": 4515 + }, + { + "epoch": 3.99, + "learning_rate": 1.3649725537164842e-05, + "loss": 0.2767, + "step": 4516 + }, + { + "epoch": 4.0, + "learning_rate": 1.3647056944463227e-05, + "loss": 0.2948, + "step": 4517 + }, + { + "epoch": 4.0, + "learning_rate": 1.3644388052161524e-05, + "loss": 0.2892, + "step": 4518 + }, + { + "epoch": 4.0, + "learning_rate": 1.3641718860478985e-05, + "loss": 0.2646, + "step": 4519 + }, + { + "epoch": 4.0, + "learning_rate": 1.3639049369634878e-05, + "loss": 0.2709, + "step": 4520 + }, + { + "epoch": 4.0, + "learning_rate": 1.3636379579848493e-05, + "loss": 0.2968, + "step": 4521 + }, + { + "epoch": 4.0, + "learning_rate": 1.3633709491339155e-05, + "loss": 0.2496, + "step": 4522 + }, + { + "epoch": 4.0, + "learning_rate": 1.3631039104326208e-05, + "loss": 0.1909, + "step": 4523 + }, + { + "epoch": 4.0, + "learning_rate": 1.362836841902901e-05, + "loss": 0.1917, + "step": 4524 + }, + { + "epoch": 4.0, + "learning_rate": 1.3625697435666967e-05, + "loss": 0.1903, + "step": 4525 + }, + { + "epoch": 4.0, + "learning_rate": 1.362302615445949e-05, + "loss": 0.2013, + "step": 4526 + }, + { + "epoch": 4.0, + "learning_rate": 1.3620354575626018e-05, + "loss": 0.1886, + "step": 4527 + }, + { + "epoch": 4.01, + "learning_rate": 1.3617682699386024e-05, + "loss": 0.1874, + "step": 4528 + }, + { + "epoch": 4.01, + "learning_rate": 1.3615010525958991e-05, + "loss": 0.1942, + "step": 4529 + }, + { + "epoch": 4.01, + "learning_rate": 1.361233805556444e-05, + "loss": 0.1952, + "step": 4530 + }, + { + "epoch": 4.01, + "learning_rate": 1.3609665288421903e-05, + "loss": 0.2085, + "step": 4531 + }, + { + "epoch": 4.01, + "learning_rate": 1.3606992224750952e-05, + "loss": 0.1702, + "step": 4532 + }, + { + "epoch": 4.01, + "learning_rate": 1.3604318864771171e-05, + "loss": 0.1958, + "step": 4533 + }, + { + "epoch": 4.01, + "learning_rate": 1.3601645208702173e-05, + "loss": 0.1903, + "step": 4534 + }, + { + "epoch": 4.01, + "learning_rate": 1.3598971256763596e-05, + "loss": 0.1915, + "step": 4535 + }, + { + "epoch": 4.01, + "learning_rate": 1.3596297009175097e-05, + "loss": 0.1803, + "step": 4536 + }, + { + "epoch": 4.01, + "learning_rate": 1.3593622466156365e-05, + "loss": 0.1906, + "step": 4537 + }, + { + "epoch": 4.01, + "learning_rate": 1.3590947627927105e-05, + "loss": 0.1872, + "step": 4538 + }, + { + "epoch": 4.02, + "learning_rate": 1.3588272494707057e-05, + "loss": 0.19, + "step": 4539 + }, + { + "epoch": 4.02, + "learning_rate": 1.3585597066715973e-05, + "loss": 0.1707, + "step": 4540 + }, + { + "epoch": 4.02, + "learning_rate": 1.3582921344173645e-05, + "loss": 0.1862, + "step": 4541 + }, + { + "epoch": 4.02, + "learning_rate": 1.3580245327299872e-05, + "loss": 0.1584, + "step": 4542 + }, + { + "epoch": 4.02, + "learning_rate": 1.3577569016314482e-05, + "loss": 0.1753, + "step": 4543 + }, + { + "epoch": 4.02, + "learning_rate": 1.3574892411437334e-05, + "loss": 0.1816, + "step": 4544 + }, + { + "epoch": 4.02, + "learning_rate": 1.3572215512888307e-05, + "loss": 0.1813, + "step": 4545 + }, + { + "epoch": 4.02, + "learning_rate": 1.3569538320887305e-05, + "loss": 0.1833, + "step": 4546 + }, + { + "epoch": 4.02, + "learning_rate": 1.3566860835654252e-05, + "loss": 0.176, + "step": 4547 + }, + { + "epoch": 4.02, + "learning_rate": 1.3564183057409101e-05, + "loss": 0.1854, + "step": 4548 + }, + { + "epoch": 4.02, + "learning_rate": 1.3561504986371827e-05, + "loss": 0.1775, + "step": 4549 + }, + { + "epoch": 4.02, + "learning_rate": 1.355882662276243e-05, + "loss": 0.1742, + "step": 4550 + }, + { + "epoch": 4.03, + "learning_rate": 1.3556147966800935e-05, + "loss": 0.1887, + "step": 4551 + }, + { + "epoch": 4.03, + "learning_rate": 1.3553469018707385e-05, + "loss": 0.1781, + "step": 4552 + }, + { + "epoch": 4.03, + "learning_rate": 1.3550789778701853e-05, + "loss": 0.1695, + "step": 4553 + }, + { + "epoch": 4.03, + "learning_rate": 1.3548110247004437e-05, + "loss": 0.1752, + "step": 4554 + }, + { + "epoch": 4.03, + "learning_rate": 1.3545430423835257e-05, + "loss": 0.1701, + "step": 4555 + }, + { + "epoch": 4.03, + "learning_rate": 1.354275030941445e-05, + "loss": 0.1904, + "step": 4556 + }, + { + "epoch": 4.03, + "learning_rate": 1.354006990396219e-05, + "loss": 0.1874, + "step": 4557 + }, + { + "epoch": 4.03, + "learning_rate": 1.3537389207698665e-05, + "loss": 0.1844, + "step": 4558 + }, + { + "epoch": 4.03, + "learning_rate": 1.3534708220844088e-05, + "loss": 0.1765, + "step": 4559 + }, + { + "epoch": 4.03, + "learning_rate": 1.3532026943618703e-05, + "loss": 0.1943, + "step": 4560 + }, + { + "epoch": 4.03, + "learning_rate": 1.3529345376242771e-05, + "loss": 0.1774, + "step": 4561 + }, + { + "epoch": 4.04, + "learning_rate": 1.3526663518936576e-05, + "loss": 0.1864, + "step": 4562 + }, + { + "epoch": 4.04, + "learning_rate": 1.3523981371920432e-05, + "loss": 0.1869, + "step": 4563 + }, + { + "epoch": 4.04, + "learning_rate": 1.3521298935414669e-05, + "loss": 0.1906, + "step": 4564 + }, + { + "epoch": 4.04, + "learning_rate": 1.351861620963965e-05, + "loss": 0.1955, + "step": 4565 + }, + { + "epoch": 4.04, + "learning_rate": 1.351593319481575e-05, + "loss": 0.1908, + "step": 4566 + }, + { + "epoch": 4.04, + "learning_rate": 1.3513249891163384e-05, + "loss": 0.1767, + "step": 4567 + }, + { + "epoch": 4.04, + "learning_rate": 1.3510566298902975e-05, + "loss": 0.1983, + "step": 4568 + }, + { + "epoch": 4.04, + "learning_rate": 1.3507882418254977e-05, + "loss": 0.1983, + "step": 4569 + }, + { + "epoch": 4.04, + "learning_rate": 1.3505198249439863e-05, + "loss": 0.1725, + "step": 4570 + }, + { + "epoch": 4.04, + "learning_rate": 1.350251379267814e-05, + "loss": 0.1894, + "step": 4571 + }, + { + "epoch": 4.04, + "learning_rate": 1.3499829048190332e-05, + "loss": 0.1631, + "step": 4572 + }, + { + "epoch": 4.05, + "learning_rate": 1.3497144016196976e-05, + "loss": 0.1649, + "step": 4573 + }, + { + "epoch": 4.05, + "learning_rate": 1.3494458696918656e-05, + "loss": 0.1981, + "step": 4574 + }, + { + "epoch": 4.05, + "learning_rate": 1.3491773090575962e-05, + "loss": 0.1808, + "step": 4575 + }, + { + "epoch": 4.05, + "learning_rate": 1.3489087197389507e-05, + "loss": 0.1728, + "step": 4576 + }, + { + "epoch": 4.05, + "learning_rate": 1.3486401017579945e-05, + "loss": 0.1684, + "step": 4577 + }, + { + "epoch": 4.05, + "learning_rate": 1.3483714551367931e-05, + "loss": 0.1867, + "step": 4578 + }, + { + "epoch": 4.05, + "learning_rate": 1.3481027798974155e-05, + "loss": 0.1816, + "step": 4579 + }, + { + "epoch": 4.05, + "learning_rate": 1.3478340760619333e-05, + "loss": 0.1822, + "step": 4580 + }, + { + "epoch": 4.05, + "learning_rate": 1.3475653436524203e-05, + "loss": 0.18, + "step": 4581 + }, + { + "epoch": 4.05, + "learning_rate": 1.3472965826909518e-05, + "loss": 0.1903, + "step": 4582 + }, + { + "epoch": 4.05, + "learning_rate": 1.3470277931996067e-05, + "loss": 0.1668, + "step": 4583 + }, + { + "epoch": 4.06, + "learning_rate": 1.3467589752004656e-05, + "loss": 0.1963, + "step": 4584 + }, + { + "epoch": 4.06, + "learning_rate": 1.3464901287156109e-05, + "loss": 0.1935, + "step": 4585 + }, + { + "epoch": 4.06, + "learning_rate": 1.3462212537671284e-05, + "loss": 0.1714, + "step": 4586 + }, + { + "epoch": 4.06, + "learning_rate": 1.3459523503771056e-05, + "loss": 0.1869, + "step": 4587 + }, + { + "epoch": 4.06, + "learning_rate": 1.3456834185676328e-05, + "loss": 0.1861, + "step": 4588 + }, + { + "epoch": 4.06, + "learning_rate": 1.3454144583608019e-05, + "loss": 0.179, + "step": 4589 + }, + { + "epoch": 4.06, + "learning_rate": 1.345145469778708e-05, + "loss": 0.2022, + "step": 4590 + }, + { + "epoch": 4.06, + "learning_rate": 1.3448764528434474e-05, + "loss": 0.1851, + "step": 4591 + }, + { + "epoch": 4.06, + "learning_rate": 1.3446074075771202e-05, + "loss": 0.1874, + "step": 4592 + }, + { + "epoch": 4.06, + "learning_rate": 1.3443383340018277e-05, + "loss": 0.1869, + "step": 4593 + }, + { + "epoch": 4.06, + "learning_rate": 1.3440692321396738e-05, + "loss": 0.1754, + "step": 4594 + }, + { + "epoch": 4.06, + "learning_rate": 1.3438001020127651e-05, + "loss": 0.1757, + "step": 4595 + }, + { + "epoch": 4.07, + "learning_rate": 1.3435309436432101e-05, + "loss": 0.1839, + "step": 4596 + }, + { + "epoch": 4.07, + "learning_rate": 1.3432617570531194e-05, + "loss": 0.1947, + "step": 4597 + }, + { + "epoch": 4.07, + "learning_rate": 1.3429925422646068e-05, + "loss": 0.1611, + "step": 4598 + }, + { + "epoch": 4.07, + "learning_rate": 1.3427232992997871e-05, + "loss": 0.1944, + "step": 4599 + }, + { + "epoch": 4.07, + "learning_rate": 1.3424540281807791e-05, + "loss": 0.1698, + "step": 4600 + }, + { + "epoch": 4.07, + "learning_rate": 1.3421847289297028e-05, + "loss": 0.1709, + "step": 4601 + }, + { + "epoch": 4.07, + "learning_rate": 1.3419154015686802e-05, + "loss": 0.1814, + "step": 4602 + }, + { + "epoch": 4.07, + "learning_rate": 1.3416460461198364e-05, + "loss": 0.1817, + "step": 4603 + }, + { + "epoch": 4.07, + "learning_rate": 1.341376662605299e-05, + "loss": 0.1782, + "step": 4604 + }, + { + "epoch": 4.07, + "learning_rate": 1.3411072510471969e-05, + "loss": 0.184, + "step": 4605 + }, + { + "epoch": 4.07, + "learning_rate": 1.3408378114676616e-05, + "loss": 0.2117, + "step": 4606 + }, + { + "epoch": 4.08, + "learning_rate": 1.3405683438888281e-05, + "loss": 0.2021, + "step": 4607 + }, + { + "epoch": 4.08, + "learning_rate": 1.3402988483328319e-05, + "loss": 0.1841, + "step": 4608 + }, + { + "epoch": 4.08, + "learning_rate": 1.3400293248218116e-05, + "loss": 0.1877, + "step": 4609 + }, + { + "epoch": 4.08, + "learning_rate": 1.3397597733779088e-05, + "loss": 0.1892, + "step": 4610 + }, + { + "epoch": 4.08, + "learning_rate": 1.3394901940232666e-05, + "loss": 0.1713, + "step": 4611 + }, + { + "epoch": 4.08, + "learning_rate": 1.3392205867800298e-05, + "loss": 0.1745, + "step": 4612 + }, + { + "epoch": 4.08, + "learning_rate": 1.338950951670347e-05, + "loss": 0.1865, + "step": 4613 + }, + { + "epoch": 4.08, + "learning_rate": 1.338681288716368e-05, + "loss": 0.1991, + "step": 4614 + }, + { + "epoch": 4.08, + "learning_rate": 1.338411597940245e-05, + "loss": 0.2004, + "step": 4615 + }, + { + "epoch": 4.08, + "learning_rate": 1.3381418793641331e-05, + "loss": 0.1867, + "step": 4616 + }, + { + "epoch": 4.08, + "learning_rate": 1.3378721330101891e-05, + "loss": 0.1845, + "step": 4617 + }, + { + "epoch": 4.09, + "learning_rate": 1.3376023589005724e-05, + "loss": 0.1832, + "step": 4618 + }, + { + "epoch": 4.09, + "learning_rate": 1.337332557057444e-05, + "loss": 0.1824, + "step": 4619 + }, + { + "epoch": 4.09, + "learning_rate": 1.3370627275029681e-05, + "loss": 0.1653, + "step": 4620 + }, + { + "epoch": 4.09, + "learning_rate": 1.3367928702593109e-05, + "loss": 0.1978, + "step": 4621 + }, + { + "epoch": 4.09, + "learning_rate": 1.3365229853486403e-05, + "loss": 0.1843, + "step": 4622 + }, + { + "epoch": 4.09, + "learning_rate": 1.3362530727931275e-05, + "loss": 0.1763, + "step": 4623 + }, + { + "epoch": 4.09, + "learning_rate": 1.335983132614945e-05, + "loss": 0.1867, + "step": 4624 + }, + { + "epoch": 4.09, + "learning_rate": 1.335713164836268e-05, + "loss": 0.193, + "step": 4625 + }, + { + "epoch": 4.09, + "learning_rate": 1.3354431694792743e-05, + "loss": 0.1989, + "step": 4626 + }, + { + "epoch": 4.09, + "learning_rate": 1.335173146566143e-05, + "loss": 0.1895, + "step": 4627 + }, + { + "epoch": 4.09, + "learning_rate": 1.3349030961190563e-05, + "loss": 0.1747, + "step": 4628 + }, + { + "epoch": 4.09, + "learning_rate": 1.3346330181601985e-05, + "loss": 0.1845, + "step": 4629 + }, + { + "epoch": 4.1, + "learning_rate": 1.3343629127117565e-05, + "loss": 0.1849, + "step": 4630 + }, + { + "epoch": 4.1, + "learning_rate": 1.3340927797959182e-05, + "loss": 0.184, + "step": 4631 + }, + { + "epoch": 4.1, + "learning_rate": 1.3338226194348754e-05, + "loss": 0.193, + "step": 4632 + }, + { + "epoch": 4.1, + "learning_rate": 1.3335524316508208e-05, + "loss": 0.189, + "step": 4633 + }, + { + "epoch": 4.1, + "learning_rate": 1.33328221646595e-05, + "loss": 0.2022, + "step": 4634 + }, + { + "epoch": 4.1, + "learning_rate": 1.333011973902461e-05, + "loss": 0.184, + "step": 4635 + }, + { + "epoch": 4.1, + "learning_rate": 1.3327417039825536e-05, + "loss": 0.1856, + "step": 4636 + }, + { + "epoch": 4.1, + "learning_rate": 1.33247140672843e-05, + "loss": 0.1711, + "step": 4637 + }, + { + "epoch": 4.1, + "learning_rate": 1.3322010821622951e-05, + "loss": 0.1837, + "step": 4638 + }, + { + "epoch": 4.1, + "learning_rate": 1.331930730306355e-05, + "loss": 0.1919, + "step": 4639 + }, + { + "epoch": 4.1, + "learning_rate": 1.3316603511828197e-05, + "loss": 0.1989, + "step": 4640 + }, + { + "epoch": 4.11, + "learning_rate": 1.331389944813899e-05, + "loss": 0.1685, + "step": 4641 + }, + { + "epoch": 4.11, + "learning_rate": 1.3311195112218076e-05, + "loss": 0.1717, + "step": 4642 + }, + { + "epoch": 4.11, + "learning_rate": 1.3308490504287605e-05, + "loss": 0.1918, + "step": 4643 + }, + { + "epoch": 4.11, + "learning_rate": 1.3305785624569762e-05, + "loss": 0.1826, + "step": 4644 + }, + { + "epoch": 4.11, + "learning_rate": 1.3303080473286744e-05, + "loss": 0.1739, + "step": 4645 + }, + { + "epoch": 4.11, + "learning_rate": 1.3300375050660777e-05, + "loss": 0.1838, + "step": 4646 + }, + { + "epoch": 4.11, + "learning_rate": 1.3297669356914107e-05, + "loss": 0.1947, + "step": 4647 + }, + { + "epoch": 4.11, + "learning_rate": 1.3294963392268997e-05, + "loss": 0.1837, + "step": 4648 + }, + { + "epoch": 4.11, + "learning_rate": 1.329225715694775e-05, + "loss": 0.1989, + "step": 4649 + }, + { + "epoch": 4.11, + "learning_rate": 1.3289550651172669e-05, + "loss": 0.1733, + "step": 4650 + }, + { + "epoch": 4.11, + "learning_rate": 1.3286843875166093e-05, + "loss": 0.1778, + "step": 4651 + }, + { + "epoch": 4.12, + "learning_rate": 1.328413682915038e-05, + "loss": 0.1835, + "step": 4652 + }, + { + "epoch": 4.12, + "learning_rate": 1.3281429513347908e-05, + "loss": 0.1767, + "step": 4653 + }, + { + "epoch": 4.12, + "learning_rate": 1.3278721927981077e-05, + "loss": 0.1807, + "step": 4654 + }, + { + "epoch": 4.12, + "learning_rate": 1.3276014073272317e-05, + "loss": 0.1684, + "step": 4655 + }, + { + "epoch": 4.12, + "learning_rate": 1.3273305949444068e-05, + "loss": 0.2012, + "step": 4656 + }, + { + "epoch": 4.12, + "learning_rate": 1.3270597556718801e-05, + "loss": 0.195, + "step": 4657 + }, + { + "epoch": 4.12, + "learning_rate": 1.3267888895319005e-05, + "loss": 0.179, + "step": 4658 + }, + { + "epoch": 4.12, + "learning_rate": 1.3265179965467197e-05, + "loss": 0.1985, + "step": 4659 + }, + { + "epoch": 4.12, + "learning_rate": 1.3262470767385902e-05, + "loss": 0.1944, + "step": 4660 + }, + { + "epoch": 4.12, + "learning_rate": 1.3259761301297684e-05, + "loss": 0.18, + "step": 4661 + }, + { + "epoch": 4.12, + "learning_rate": 1.3257051567425121e-05, + "loss": 0.1928, + "step": 4662 + }, + { + "epoch": 4.12, + "learning_rate": 1.3254341565990812e-05, + "loss": 0.188, + "step": 4663 + }, + { + "epoch": 4.13, + "learning_rate": 1.3251631297217375e-05, + "loss": 0.1754, + "step": 4664 + }, + { + "epoch": 4.13, + "learning_rate": 1.3248920761327464e-05, + "loss": 0.2, + "step": 4665 + }, + { + "epoch": 4.13, + "learning_rate": 1.3246209958543737e-05, + "loss": 0.1741, + "step": 4666 + }, + { + "epoch": 4.13, + "learning_rate": 1.3243498889088886e-05, + "loss": 0.1857, + "step": 4667 + }, + { + "epoch": 4.13, + "learning_rate": 1.3240787553185622e-05, + "loss": 0.1663, + "step": 4668 + }, + { + "epoch": 4.13, + "learning_rate": 1.3238075951056675e-05, + "loss": 0.197, + "step": 4669 + }, + { + "epoch": 4.13, + "learning_rate": 1.3235364082924797e-05, + "loss": 0.1852, + "step": 4670 + }, + { + "epoch": 4.13, + "learning_rate": 1.3232651949012767e-05, + "loss": 0.1718, + "step": 4671 + }, + { + "epoch": 4.13, + "learning_rate": 1.3229939549543382e-05, + "loss": 0.1938, + "step": 4672 + }, + { + "epoch": 4.13, + "learning_rate": 1.3227226884739461e-05, + "loss": 0.193, + "step": 4673 + }, + { + "epoch": 4.13, + "learning_rate": 1.3224513954823847e-05, + "loss": 0.1882, + "step": 4674 + }, + { + "epoch": 4.14, + "learning_rate": 1.3221800760019402e-05, + "loss": 0.1888, + "step": 4675 + }, + { + "epoch": 4.14, + "learning_rate": 1.3219087300549007e-05, + "loss": 0.1774, + "step": 4676 + }, + { + "epoch": 4.14, + "learning_rate": 1.3216373576635572e-05, + "loss": 0.191, + "step": 4677 + }, + { + "epoch": 4.14, + "learning_rate": 1.3213659588502025e-05, + "loss": 0.1856, + "step": 4678 + }, + { + "epoch": 4.14, + "learning_rate": 1.3210945336371319e-05, + "loss": 0.1817, + "step": 4679 + }, + { + "epoch": 4.14, + "learning_rate": 1.3208230820466422e-05, + "loss": 0.1955, + "step": 4680 + }, + { + "epoch": 4.14, + "learning_rate": 1.3205516041010325e-05, + "loss": 0.1915, + "step": 4681 + }, + { + "epoch": 4.14, + "learning_rate": 1.3202800998226048e-05, + "loss": 0.1729, + "step": 4682 + }, + { + "epoch": 4.14, + "learning_rate": 1.3200085692336621e-05, + "loss": 0.18, + "step": 4683 + }, + { + "epoch": 4.14, + "learning_rate": 1.319737012356511e-05, + "loss": 0.1931, + "step": 4684 + }, + { + "epoch": 4.14, + "learning_rate": 1.3194654292134589e-05, + "loss": 0.1807, + "step": 4685 + }, + { + "epoch": 4.15, + "learning_rate": 1.3191938198268165e-05, + "loss": 0.1789, + "step": 4686 + }, + { + "epoch": 4.15, + "learning_rate": 1.3189221842188955e-05, + "loss": 0.1798, + "step": 4687 + }, + { + "epoch": 4.15, + "learning_rate": 1.3186505224120105e-05, + "loss": 0.1841, + "step": 4688 + }, + { + "epoch": 4.15, + "learning_rate": 1.3183788344284784e-05, + "loss": 0.1631, + "step": 4689 + }, + { + "epoch": 4.15, + "learning_rate": 1.3181071202906176e-05, + "loss": 0.1695, + "step": 4690 + }, + { + "epoch": 4.15, + "learning_rate": 1.3178353800207491e-05, + "loss": 0.1899, + "step": 4691 + }, + { + "epoch": 4.15, + "learning_rate": 1.317563613641196e-05, + "loss": 0.1841, + "step": 4692 + }, + { + "epoch": 4.15, + "learning_rate": 1.3172918211742836e-05, + "loss": 0.1675, + "step": 4693 + }, + { + "epoch": 4.15, + "learning_rate": 1.3170200026423387e-05, + "loss": 0.1909, + "step": 4694 + }, + { + "epoch": 4.15, + "learning_rate": 1.3167481580676915e-05, + "loss": 0.1911, + "step": 4695 + }, + { + "epoch": 4.15, + "learning_rate": 1.3164762874726733e-05, + "loss": 0.1869, + "step": 4696 + }, + { + "epoch": 4.16, + "learning_rate": 1.3162043908796174e-05, + "loss": 0.1888, + "step": 4697 + }, + { + "epoch": 4.16, + "learning_rate": 1.3159324683108606e-05, + "loss": 0.176, + "step": 4698 + }, + { + "epoch": 4.16, + "learning_rate": 1.31566051978874e-05, + "loss": 0.1749, + "step": 4699 + }, + { + "epoch": 4.16, + "learning_rate": 1.3153885453355964e-05, + "loss": 0.1835, + "step": 4700 + }, + { + "epoch": 4.16, + "learning_rate": 1.315116544973772e-05, + "loss": 0.1792, + "step": 4701 + }, + { + "epoch": 4.16, + "learning_rate": 1.3148445187256107e-05, + "loss": 0.1811, + "step": 4702 + }, + { + "epoch": 4.16, + "learning_rate": 1.3145724666134597e-05, + "loss": 0.1726, + "step": 4703 + }, + { + "epoch": 4.16, + "learning_rate": 1.314300388659667e-05, + "loss": 0.2137, + "step": 4704 + }, + { + "epoch": 4.16, + "learning_rate": 1.3140282848865841e-05, + "loss": 0.1874, + "step": 4705 + }, + { + "epoch": 4.16, + "learning_rate": 1.3137561553165635e-05, + "loss": 0.1829, + "step": 4706 + }, + { + "epoch": 4.16, + "learning_rate": 1.31348399997196e-05, + "loss": 0.1918, + "step": 4707 + }, + { + "epoch": 4.16, + "learning_rate": 1.3132118188751313e-05, + "loss": 0.1989, + "step": 4708 + }, + { + "epoch": 4.17, + "learning_rate": 1.3129396120484361e-05, + "loss": 0.1819, + "step": 4709 + }, + { + "epoch": 4.17, + "learning_rate": 1.3126673795142362e-05, + "loss": 0.1879, + "step": 4710 + }, + { + "epoch": 4.17, + "learning_rate": 1.312395121294895e-05, + "loss": 0.1735, + "step": 4711 + }, + { + "epoch": 4.17, + "learning_rate": 1.3121228374127779e-05, + "loss": 0.1732, + "step": 4712 + }, + { + "epoch": 4.17, + "learning_rate": 1.3118505278902527e-05, + "loss": 0.1838, + "step": 4713 + }, + { + "epoch": 4.17, + "learning_rate": 1.3115781927496892e-05, + "loss": 0.1795, + "step": 4714 + }, + { + "epoch": 4.17, + "learning_rate": 1.3113058320134593e-05, + "loss": 0.1938, + "step": 4715 + }, + { + "epoch": 4.17, + "learning_rate": 1.3110334457039366e-05, + "loss": 0.1779, + "step": 4716 + }, + { + "epoch": 4.17, + "learning_rate": 1.3107610338434984e-05, + "loss": 0.1746, + "step": 4717 + }, + { + "epoch": 4.17, + "learning_rate": 1.3104885964545217e-05, + "loss": 0.184, + "step": 4718 + }, + { + "epoch": 4.17, + "learning_rate": 1.3102161335593877e-05, + "loss": 0.1949, + "step": 4719 + }, + { + "epoch": 4.18, + "learning_rate": 1.3099436451804781e-05, + "loss": 0.1812, + "step": 4720 + }, + { + "epoch": 4.18, + "learning_rate": 1.3096711313401775e-05, + "loss": 0.1771, + "step": 4721 + }, + { + "epoch": 4.18, + "learning_rate": 1.3093985920608729e-05, + "loss": 0.1748, + "step": 4722 + }, + { + "epoch": 4.18, + "learning_rate": 1.3091260273649525e-05, + "loss": 0.1781, + "step": 4723 + }, + { + "epoch": 4.18, + "learning_rate": 1.3088534372748077e-05, + "loss": 0.1711, + "step": 4724 + }, + { + "epoch": 4.18, + "learning_rate": 1.3085808218128307e-05, + "loss": 0.1726, + "step": 4725 + }, + { + "epoch": 4.18, + "learning_rate": 1.3083081810014165e-05, + "loss": 0.183, + "step": 4726 + }, + { + "epoch": 4.18, + "learning_rate": 1.3080355148629625e-05, + "loss": 0.1837, + "step": 4727 + }, + { + "epoch": 4.18, + "learning_rate": 1.3077628234198679e-05, + "loss": 0.1964, + "step": 4728 + }, + { + "epoch": 4.18, + "learning_rate": 1.3074901066945334e-05, + "loss": 0.1878, + "step": 4729 + }, + { + "epoch": 4.18, + "learning_rate": 1.3072173647093625e-05, + "loss": 0.1876, + "step": 4730 + }, + { + "epoch": 4.19, + "learning_rate": 1.3069445974867606e-05, + "loss": 0.179, + "step": 4731 + }, + { + "epoch": 4.19, + "learning_rate": 1.3066718050491347e-05, + "loss": 0.178, + "step": 4732 + }, + { + "epoch": 4.19, + "learning_rate": 1.3063989874188944e-05, + "loss": 0.1816, + "step": 4733 + }, + { + "epoch": 4.19, + "learning_rate": 1.3061261446184518e-05, + "loss": 0.1813, + "step": 4734 + }, + { + "epoch": 4.19, + "learning_rate": 1.3058532766702204e-05, + "loss": 0.1806, + "step": 4735 + }, + { + "epoch": 4.19, + "learning_rate": 1.3055803835966153e-05, + "loss": 0.1857, + "step": 4736 + }, + { + "epoch": 4.19, + "learning_rate": 1.3053074654200545e-05, + "loss": 0.1818, + "step": 4737 + }, + { + "epoch": 4.19, + "learning_rate": 1.3050345221629578e-05, + "loss": 0.2018, + "step": 4738 + }, + { + "epoch": 4.19, + "learning_rate": 1.3047615538477472e-05, + "loss": 0.2036, + "step": 4739 + }, + { + "epoch": 4.19, + "learning_rate": 1.3044885604968466e-05, + "loss": 0.1819, + "step": 4740 + }, + { + "epoch": 4.19, + "learning_rate": 1.3042155421326821e-05, + "loss": 0.1808, + "step": 4741 + }, + { + "epoch": 4.19, + "learning_rate": 1.3039424987776812e-05, + "loss": 0.1767, + "step": 4742 + }, + { + "epoch": 4.2, + "learning_rate": 1.3036694304542748e-05, + "loss": 0.1833, + "step": 4743 + }, + { + "epoch": 4.2, + "learning_rate": 1.3033963371848944e-05, + "loss": 0.1748, + "step": 4744 + }, + { + "epoch": 4.2, + "learning_rate": 1.3031232189919744e-05, + "loss": 0.1726, + "step": 4745 + }, + { + "epoch": 4.2, + "learning_rate": 1.3028500758979507e-05, + "loss": 0.1852, + "step": 4746 + }, + { + "epoch": 4.2, + "learning_rate": 1.3025769079252624e-05, + "loss": 0.1813, + "step": 4747 + }, + { + "epoch": 4.2, + "learning_rate": 1.302303715096349e-05, + "loss": 0.1901, + "step": 4748 + }, + { + "epoch": 4.2, + "learning_rate": 1.3020304974336535e-05, + "loss": 0.1815, + "step": 4749 + }, + { + "epoch": 4.2, + "learning_rate": 1.30175725495962e-05, + "loss": 0.1857, + "step": 4750 + }, + { + "epoch": 4.2, + "learning_rate": 1.3014839876966947e-05, + "loss": 0.1817, + "step": 4751 + }, + { + "epoch": 4.2, + "learning_rate": 1.3012106956673265e-05, + "loss": 0.1951, + "step": 4752 + }, + { + "epoch": 4.2, + "learning_rate": 1.3009373788939656e-05, + "loss": 0.2011, + "step": 4753 + }, + { + "epoch": 4.21, + "learning_rate": 1.3006640373990652e-05, + "loss": 0.1984, + "step": 4754 + }, + { + "epoch": 4.21, + "learning_rate": 1.3003906712050789e-05, + "loss": 0.1849, + "step": 4755 + }, + { + "epoch": 4.21, + "learning_rate": 1.300117280334464e-05, + "loss": 0.1781, + "step": 4756 + }, + { + "epoch": 4.21, + "learning_rate": 1.299843864809679e-05, + "loss": 0.1951, + "step": 4757 + }, + { + "epoch": 4.21, + "learning_rate": 1.2995704246531842e-05, + "loss": 0.1973, + "step": 4758 + }, + { + "epoch": 4.21, + "learning_rate": 1.2992969598874428e-05, + "loss": 0.2001, + "step": 4759 + }, + { + "epoch": 4.21, + "learning_rate": 1.2990234705349192e-05, + "loss": 0.1889, + "step": 4760 + }, + { + "epoch": 4.21, + "learning_rate": 1.2987499566180803e-05, + "loss": 0.1722, + "step": 4761 + }, + { + "epoch": 4.21, + "learning_rate": 1.2984764181593948e-05, + "loss": 0.1735, + "step": 4762 + }, + { + "epoch": 4.21, + "learning_rate": 1.2982028551813332e-05, + "loss": 0.1883, + "step": 4763 + }, + { + "epoch": 4.21, + "learning_rate": 1.297929267706369e-05, + "loss": 0.1745, + "step": 4764 + }, + { + "epoch": 4.22, + "learning_rate": 1.2976556557569758e-05, + "loss": 0.1795, + "step": 4765 + }, + { + "epoch": 4.22, + "learning_rate": 1.2973820193556316e-05, + "loss": 0.188, + "step": 4766 + }, + { + "epoch": 4.22, + "learning_rate": 1.2971083585248145e-05, + "loss": 0.1746, + "step": 4767 + }, + { + "epoch": 4.22, + "learning_rate": 1.2968346732870058e-05, + "loss": 0.1883, + "step": 4768 + }, + { + "epoch": 4.22, + "learning_rate": 1.2965609636646876e-05, + "loss": 0.1999, + "step": 4769 + }, + { + "epoch": 4.22, + "learning_rate": 1.2962872296803454e-05, + "loss": 0.1791, + "step": 4770 + }, + { + "epoch": 4.22, + "learning_rate": 1.2960134713564657e-05, + "loss": 0.1845, + "step": 4771 + }, + { + "epoch": 4.22, + "learning_rate": 1.2957396887155373e-05, + "loss": 0.1837, + "step": 4772 + }, + { + "epoch": 4.22, + "learning_rate": 1.2954658817800514e-05, + "loss": 0.1834, + "step": 4773 + }, + { + "epoch": 4.22, + "learning_rate": 1.2951920505725002e-05, + "loss": 0.1807, + "step": 4774 + }, + { + "epoch": 4.22, + "learning_rate": 1.294918195115379e-05, + "loss": 0.1807, + "step": 4775 + }, + { + "epoch": 4.22, + "learning_rate": 1.2946443154311847e-05, + "loss": 0.1897, + "step": 4776 + }, + { + "epoch": 4.23, + "learning_rate": 1.2943704115424153e-05, + "loss": 0.1828, + "step": 4777 + }, + { + "epoch": 4.23, + "learning_rate": 1.2940964834715723e-05, + "loss": 0.172, + "step": 4778 + }, + { + "epoch": 4.23, + "learning_rate": 1.2938225312411585e-05, + "loss": 0.1726, + "step": 4779 + }, + { + "epoch": 4.23, + "learning_rate": 1.2935485548736785e-05, + "loss": 0.2017, + "step": 4780 + }, + { + "epoch": 4.23, + "learning_rate": 1.2932745543916387e-05, + "loss": 0.1794, + "step": 4781 + }, + { + "epoch": 4.23, + "learning_rate": 1.2930005298175481e-05, + "loss": 0.2022, + "step": 4782 + }, + { + "epoch": 4.23, + "learning_rate": 1.2927264811739175e-05, + "loss": 0.1935, + "step": 4783 + }, + { + "epoch": 4.23, + "learning_rate": 1.2924524084832595e-05, + "loss": 0.1795, + "step": 4784 + }, + { + "epoch": 4.23, + "learning_rate": 1.2921783117680887e-05, + "loss": 0.1818, + "step": 4785 + }, + { + "epoch": 4.23, + "learning_rate": 1.2919041910509213e-05, + "loss": 0.1829, + "step": 4786 + }, + { + "epoch": 4.23, + "learning_rate": 1.2916300463542769e-05, + "loss": 0.1872, + "step": 4787 + }, + { + "epoch": 4.24, + "learning_rate": 1.291355877700675e-05, + "loss": 0.1793, + "step": 4788 + }, + { + "epoch": 4.24, + "learning_rate": 1.2910816851126389e-05, + "loss": 0.1998, + "step": 4789 + }, + { + "epoch": 4.24, + "learning_rate": 1.2908074686126926e-05, + "loss": 0.1855, + "step": 4790 + }, + { + "epoch": 4.24, + "learning_rate": 1.2905332282233629e-05, + "loss": 0.1916, + "step": 4791 + }, + { + "epoch": 4.24, + "learning_rate": 1.2902589639671783e-05, + "loss": 0.1913, + "step": 4792 + }, + { + "epoch": 4.24, + "learning_rate": 1.2899846758666685e-05, + "loss": 0.1785, + "step": 4793 + }, + { + "epoch": 4.24, + "learning_rate": 1.2897103639443666e-05, + "loss": 0.1899, + "step": 4794 + }, + { + "epoch": 4.24, + "learning_rate": 1.2894360282228065e-05, + "loss": 0.1814, + "step": 4795 + }, + { + "epoch": 4.24, + "learning_rate": 1.2891616687245248e-05, + "loss": 0.1911, + "step": 4796 + }, + { + "epoch": 4.24, + "learning_rate": 1.2888872854720592e-05, + "loss": 0.1859, + "step": 4797 + }, + { + "epoch": 4.24, + "learning_rate": 1.2886128784879504e-05, + "loss": 0.1875, + "step": 4798 + }, + { + "epoch": 4.25, + "learning_rate": 1.2883384477947401e-05, + "loss": 0.2061, + "step": 4799 + }, + { + "epoch": 4.25, + "learning_rate": 1.2880639934149725e-05, + "loss": 0.1872, + "step": 4800 + }, + { + "epoch": 4.25, + "learning_rate": 1.8304630807339465e-05, + "loss": 0.1725, + "step": 4801 + }, + { + "epoch": 4.25, + "learning_rate": 1.830383239228605e-05, + "loss": 0.1877, + "step": 4802 + }, + { + "epoch": 4.25, + "learning_rate": 1.8303033806695894e-05, + "loss": 0.2024, + "step": 4803 + }, + { + "epoch": 4.25, + "learning_rate": 1.830223505058539e-05, + "loss": 0.214, + "step": 4804 + }, + { + "epoch": 4.25, + "learning_rate": 1.8301436123970945e-05, + "loss": 0.2014, + "step": 4805 + }, + { + "epoch": 4.25, + "learning_rate": 1.8300637026868963e-05, + "loss": 0.2103, + "step": 4806 + }, + { + "epoch": 4.25, + "learning_rate": 1.8299837759295863e-05, + "loss": 0.2124, + "step": 4807 + }, + { + "epoch": 4.25, + "learning_rate": 1.8299038321268053e-05, + "loss": 0.2119, + "step": 4808 + }, + { + "epoch": 4.26, + "learning_rate": 1.829823871280195e-05, + "loss": 0.2176, + "step": 4809 + }, + { + "epoch": 4.26, + "learning_rate": 1.8297438933913983e-05, + "loss": 0.2281, + "step": 4810 + }, + { + "epoch": 4.26, + "learning_rate": 1.8296638984620576e-05, + "loss": 0.2299, + "step": 4811 + }, + { + "epoch": 4.26, + "learning_rate": 1.8295838864938145e-05, + "loss": 0.2352, + "step": 4812 + }, + { + "epoch": 4.26, + "learning_rate": 1.829503857488314e-05, + "loss": 0.2386, + "step": 4813 + }, + { + "epoch": 4.26, + "learning_rate": 1.8294238114471985e-05, + "loss": 0.2507, + "step": 4814 + }, + { + "epoch": 4.26, + "learning_rate": 1.8293437483721124e-05, + "loss": 0.2488, + "step": 4815 + }, + { + "epoch": 4.26, + "learning_rate": 1.8292636682646997e-05, + "loss": 0.2493, + "step": 4816 + }, + { + "epoch": 4.26, + "learning_rate": 1.8291835711266053e-05, + "loss": 0.264, + "step": 4817 + }, + { + "epoch": 4.26, + "learning_rate": 1.829103456959474e-05, + "loss": 0.2575, + "step": 4818 + }, + { + "epoch": 4.26, + "learning_rate": 1.829023325764951e-05, + "loss": 0.2806, + "step": 4819 + }, + { + "epoch": 4.27, + "learning_rate": 1.828943177544682e-05, + "loss": 0.2897, + "step": 4820 + }, + { + "epoch": 4.27, + "learning_rate": 1.828863012300313e-05, + "loss": 0.2546, + "step": 4821 + }, + { + "epoch": 4.27, + "learning_rate": 1.828782830033491e-05, + "loss": 0.28, + "step": 4822 + }, + { + "epoch": 4.27, + "learning_rate": 1.828702630745862e-05, + "loss": 0.2676, + "step": 4823 + }, + { + "epoch": 4.27, + "learning_rate": 1.828622414439073e-05, + "loss": 0.2727, + "step": 4824 + }, + { + "epoch": 4.27, + "learning_rate": 1.8285421811147712e-05, + "loss": 0.2866, + "step": 4825 + }, + { + "epoch": 4.27, + "learning_rate": 1.8284619307746053e-05, + "loss": 0.256, + "step": 4826 + }, + { + "epoch": 4.27, + "learning_rate": 1.828381663420223e-05, + "loss": 0.2828, + "step": 4827 + }, + { + "epoch": 4.27, + "learning_rate": 1.8283013790532726e-05, + "loss": 0.2646, + "step": 4828 + }, + { + "epoch": 4.27, + "learning_rate": 1.8282210776754027e-05, + "loss": 0.2899, + "step": 4829 + }, + { + "epoch": 4.27, + "learning_rate": 1.828140759288263e-05, + "loss": 0.2562, + "step": 4830 + }, + { + "epoch": 4.28, + "learning_rate": 1.8280604238935028e-05, + "loss": 0.2916, + "step": 4831 + }, + { + "epoch": 4.28, + "learning_rate": 1.827980071492772e-05, + "loss": 0.2925, + "step": 4832 + }, + { + "epoch": 4.28, + "learning_rate": 1.8278997020877205e-05, + "loss": 0.2763, + "step": 4833 + }, + { + "epoch": 4.28, + "learning_rate": 1.827819315679999e-05, + "loss": 0.2851, + "step": 4834 + }, + { + "epoch": 4.28, + "learning_rate": 1.8277389122712586e-05, + "loss": 0.3064, + "step": 4835 + }, + { + "epoch": 4.28, + "learning_rate": 1.8276584918631504e-05, + "loss": 0.2941, + "step": 4836 + }, + { + "epoch": 4.28, + "learning_rate": 1.8275780544573258e-05, + "loss": 0.2801, + "step": 4837 + }, + { + "epoch": 4.28, + "learning_rate": 1.8274976000554374e-05, + "loss": 0.2758, + "step": 4838 + }, + { + "epoch": 4.28, + "learning_rate": 1.8274171286591368e-05, + "loss": 0.2977, + "step": 4839 + }, + { + "epoch": 4.28, + "learning_rate": 1.8273366402700768e-05, + "loss": 0.289, + "step": 4840 + }, + { + "epoch": 4.28, + "learning_rate": 1.827256134889911e-05, + "loss": 0.2862, + "step": 4841 + }, + { + "epoch": 4.28, + "learning_rate": 1.827175612520292e-05, + "loss": 0.278, + "step": 4842 + }, + { + "epoch": 4.29, + "learning_rate": 1.8270950731628742e-05, + "loss": 0.2911, + "step": 4843 + }, + { + "epoch": 4.29, + "learning_rate": 1.8270145168193106e-05, + "loss": 0.2874, + "step": 4844 + }, + { + "epoch": 4.29, + "learning_rate": 1.826933943491256e-05, + "loss": 0.2837, + "step": 4845 + }, + { + "epoch": 4.29, + "learning_rate": 1.8268533531803663e-05, + "loss": 0.3035, + "step": 4846 + }, + { + "epoch": 4.29, + "learning_rate": 1.826772745888295e-05, + "loss": 0.2789, + "step": 4847 + }, + { + "epoch": 4.29, + "learning_rate": 1.8266921216166983e-05, + "loss": 0.2906, + "step": 4848 + }, + { + "epoch": 4.29, + "learning_rate": 1.826611480367232e-05, + "loss": 0.2905, + "step": 4849 + }, + { + "epoch": 4.29, + "learning_rate": 1.8265308221415518e-05, + "loss": 0.2926, + "step": 4850 + }, + { + "epoch": 4.29, + "learning_rate": 1.826450146941315e-05, + "loss": 0.2877, + "step": 4851 + }, + { + "epoch": 4.29, + "learning_rate": 1.8263694547681776e-05, + "loss": 0.29, + "step": 4852 + }, + { + "epoch": 4.29, + "learning_rate": 1.826288745623797e-05, + "loss": 0.292, + "step": 4853 + }, + { + "epoch": 4.3, + "learning_rate": 1.8262080195098313e-05, + "loss": 0.3009, + "step": 4854 + }, + { + "epoch": 4.3, + "learning_rate": 1.8261272764279378e-05, + "loss": 0.3067, + "step": 4855 + }, + { + "epoch": 4.3, + "learning_rate": 1.8260465163797747e-05, + "loss": 0.2988, + "step": 4856 + }, + { + "epoch": 4.3, + "learning_rate": 1.8259657393670007e-05, + "loss": 0.3056, + "step": 4857 + }, + { + "epoch": 4.3, + "learning_rate": 1.8258849453912752e-05, + "loss": 0.3023, + "step": 4858 + }, + { + "epoch": 4.3, + "learning_rate": 1.8258041344542567e-05, + "loss": 0.2955, + "step": 4859 + }, + { + "epoch": 4.3, + "learning_rate": 1.8257233065576053e-05, + "loss": 0.3052, + "step": 4860 + }, + { + "epoch": 4.3, + "learning_rate": 1.8256424617029806e-05, + "loss": 0.2915, + "step": 4861 + }, + { + "epoch": 4.3, + "learning_rate": 1.8255615998920435e-05, + "loss": 0.2821, + "step": 4862 + }, + { + "epoch": 4.3, + "learning_rate": 1.825480721126454e-05, + "loss": 0.2957, + "step": 4863 + }, + { + "epoch": 4.3, + "learning_rate": 1.8253998254078737e-05, + "loss": 0.2783, + "step": 4864 + }, + { + "epoch": 4.31, + "learning_rate": 1.8253189127379637e-05, + "loss": 0.3054, + "step": 4865 + }, + { + "epoch": 4.31, + "learning_rate": 1.8252379831183857e-05, + "loss": 0.2883, + "step": 4866 + }, + { + "epoch": 4.31, + "learning_rate": 1.825157036550802e-05, + "loss": 0.3014, + "step": 4867 + }, + { + "epoch": 4.31, + "learning_rate": 1.8250760730368743e-05, + "loss": 0.2882, + "step": 4868 + }, + { + "epoch": 4.31, + "learning_rate": 1.8249950925782664e-05, + "loss": 0.2954, + "step": 4869 + }, + { + "epoch": 4.31, + "learning_rate": 1.8249140951766403e-05, + "loss": 0.2829, + "step": 4870 + }, + { + "epoch": 4.31, + "learning_rate": 1.8248330808336604e-05, + "loss": 0.2807, + "step": 4871 + }, + { + "epoch": 4.31, + "learning_rate": 1.82475204955099e-05, + "loss": 0.2984, + "step": 4872 + }, + { + "epoch": 4.31, + "learning_rate": 1.8246710013302934e-05, + "loss": 0.3036, + "step": 4873 + }, + { + "epoch": 4.31, + "learning_rate": 1.824589936173235e-05, + "loss": 0.29, + "step": 4874 + }, + { + "epoch": 4.31, + "learning_rate": 1.82450885408148e-05, + "loss": 0.293, + "step": 4875 + }, + { + "epoch": 4.31, + "learning_rate": 1.8244277550566928e-05, + "loss": 0.2736, + "step": 4876 + }, + { + "epoch": 4.32, + "learning_rate": 1.8243466391005397e-05, + "loss": 0.3088, + "step": 4877 + }, + { + "epoch": 4.32, + "learning_rate": 1.8242655062146862e-05, + "loss": 0.2815, + "step": 4878 + }, + { + "epoch": 4.32, + "learning_rate": 1.8241843564007987e-05, + "loss": 0.2931, + "step": 4879 + }, + { + "epoch": 4.32, + "learning_rate": 1.824103189660544e-05, + "loss": 0.2903, + "step": 4880 + }, + { + "epoch": 4.32, + "learning_rate": 1.8240220059955885e-05, + "loss": 0.3026, + "step": 4881 + }, + { + "epoch": 4.32, + "learning_rate": 1.8239408054076e-05, + "loss": 0.2969, + "step": 4882 + }, + { + "epoch": 4.32, + "learning_rate": 1.8238595878982456e-05, + "loss": 0.2842, + "step": 4883 + }, + { + "epoch": 4.32, + "learning_rate": 1.8237783534691937e-05, + "loss": 0.2814, + "step": 4884 + }, + { + "epoch": 4.32, + "learning_rate": 1.8236971021221122e-05, + "loss": 0.2781, + "step": 4885 + }, + { + "epoch": 4.32, + "learning_rate": 1.82361583385867e-05, + "loss": 0.287, + "step": 4886 + }, + { + "epoch": 4.32, + "learning_rate": 1.8235345486805367e-05, + "loss": 0.277, + "step": 4887 + }, + { + "epoch": 4.33, + "learning_rate": 1.8234532465893807e-05, + "loss": 0.2908, + "step": 4888 + }, + { + "epoch": 4.33, + "learning_rate": 1.823371927586872e-05, + "loss": 0.2905, + "step": 4889 + }, + { + "epoch": 4.33, + "learning_rate": 1.8232905916746815e-05, + "loss": 0.3026, + "step": 4890 + }, + { + "epoch": 4.33, + "learning_rate": 1.8232092388544783e-05, + "loss": 0.3044, + "step": 4891 + }, + { + "epoch": 4.33, + "learning_rate": 1.8231278691279336e-05, + "loss": 0.2935, + "step": 4892 + }, + { + "epoch": 4.33, + "learning_rate": 1.823046482496719e-05, + "loss": 0.2806, + "step": 4893 + }, + { + "epoch": 4.33, + "learning_rate": 1.8229650789625055e-05, + "loss": 0.2897, + "step": 4894 + }, + { + "epoch": 4.33, + "learning_rate": 1.8228836585269652e-05, + "loss": 0.292, + "step": 4895 + }, + { + "epoch": 4.33, + "learning_rate": 1.8228022211917695e-05, + "loss": 0.2681, + "step": 4896 + }, + { + "epoch": 4.33, + "learning_rate": 1.8227207669585918e-05, + "loss": 0.2855, + "step": 4897 + }, + { + "epoch": 4.33, + "learning_rate": 1.8226392958291044e-05, + "loss": 0.2823, + "step": 4898 + }, + { + "epoch": 4.34, + "learning_rate": 1.8225578078049807e-05, + "loss": 0.2912, + "step": 4899 + }, + { + "epoch": 4.34, + "learning_rate": 1.822476302887894e-05, + "loss": 0.2885, + "step": 4900 + }, + { + "epoch": 4.34, + "learning_rate": 1.8223947810795182e-05, + "loss": 0.2976, + "step": 4901 + }, + { + "epoch": 4.34, + "learning_rate": 1.8223132423815282e-05, + "loss": 0.2911, + "step": 4902 + }, + { + "epoch": 4.34, + "learning_rate": 1.8222316867955976e-05, + "loss": 0.2836, + "step": 4903 + }, + { + "epoch": 4.34, + "learning_rate": 1.8221501143234018e-05, + "loss": 0.2965, + "step": 4904 + }, + { + "epoch": 4.34, + "learning_rate": 1.822068524966616e-05, + "loss": 0.2845, + "step": 4905 + }, + { + "epoch": 4.34, + "learning_rate": 1.821986918726916e-05, + "loss": 0.2793, + "step": 4906 + }, + { + "epoch": 4.34, + "learning_rate": 1.8219052956059774e-05, + "loss": 0.2937, + "step": 4907 + }, + { + "epoch": 4.34, + "learning_rate": 1.8218236556054764e-05, + "loss": 0.2892, + "step": 4908 + }, + { + "epoch": 4.34, + "learning_rate": 1.8217419987270905e-05, + "loss": 0.275, + "step": 4909 + }, + { + "epoch": 4.34, + "learning_rate": 1.8216603249724956e-05, + "loss": 0.2812, + "step": 4910 + }, + { + "epoch": 4.35, + "learning_rate": 1.82157863434337e-05, + "loss": 0.3082, + "step": 4911 + }, + { + "epoch": 4.35, + "learning_rate": 1.8214969268413905e-05, + "loss": 0.2925, + "step": 4912 + }, + { + "epoch": 4.35, + "learning_rate": 1.821415202468236e-05, + "loss": 0.2875, + "step": 4913 + }, + { + "epoch": 4.35, + "learning_rate": 1.821333461225584e-05, + "loss": 0.2993, + "step": 4914 + }, + { + "epoch": 4.35, + "learning_rate": 1.821251703115114e-05, + "loss": 0.2812, + "step": 4915 + }, + { + "epoch": 4.35, + "learning_rate": 1.8211699281385048e-05, + "loss": 0.2805, + "step": 4916 + }, + { + "epoch": 4.35, + "learning_rate": 1.8210881362974357e-05, + "loss": 0.2792, + "step": 4917 + }, + { + "epoch": 4.35, + "learning_rate": 1.821006327593587e-05, + "loss": 0.2777, + "step": 4918 + }, + { + "epoch": 4.35, + "learning_rate": 1.8209245020286376e-05, + "loss": 0.2823, + "step": 4919 + }, + { + "epoch": 4.35, + "learning_rate": 1.8208426596042693e-05, + "loss": 0.3006, + "step": 4920 + }, + { + "epoch": 4.35, + "learning_rate": 1.8207608003221622e-05, + "loss": 0.2803, + "step": 4921 + }, + { + "epoch": 4.36, + "learning_rate": 1.8206789241839975e-05, + "loss": 0.279, + "step": 4922 + }, + { + "epoch": 4.36, + "learning_rate": 1.820597031191457e-05, + "loss": 0.2872, + "step": 4923 + }, + { + "epoch": 4.36, + "learning_rate": 1.820515121346222e-05, + "loss": 0.2683, + "step": 4924 + }, + { + "epoch": 4.36, + "learning_rate": 1.8204331946499754e-05, + "loss": 0.2963, + "step": 4925 + }, + { + "epoch": 4.36, + "learning_rate": 1.8203512511043992e-05, + "loss": 0.2917, + "step": 4926 + }, + { + "epoch": 4.36, + "learning_rate": 1.8202692907111767e-05, + "loss": 0.3022, + "step": 4927 + }, + { + "epoch": 4.36, + "learning_rate": 1.8201873134719905e-05, + "loss": 0.3061, + "step": 4928 + }, + { + "epoch": 4.36, + "learning_rate": 1.8201053193885244e-05, + "loss": 0.2858, + "step": 4929 + }, + { + "epoch": 4.36, + "learning_rate": 1.8200233084624632e-05, + "loss": 0.2946, + "step": 4930 + }, + { + "epoch": 4.36, + "learning_rate": 1.8199412806954902e-05, + "loss": 0.2934, + "step": 4931 + }, + { + "epoch": 4.36, + "learning_rate": 1.81985923608929e-05, + "loss": 0.2997, + "step": 4932 + }, + { + "epoch": 4.37, + "learning_rate": 1.819777174645548e-05, + "loss": 0.2933, + "step": 4933 + }, + { + "epoch": 4.37, + "learning_rate": 1.8196950963659493e-05, + "loss": 0.2736, + "step": 4934 + }, + { + "epoch": 4.37, + "learning_rate": 1.8196130012521792e-05, + "loss": 0.2777, + "step": 4935 + }, + { + "epoch": 4.37, + "learning_rate": 1.8195308893059247e-05, + "loss": 0.2886, + "step": 4936 + }, + { + "epoch": 4.37, + "learning_rate": 1.8194487605288712e-05, + "loss": 0.2903, + "step": 4937 + }, + { + "epoch": 4.37, + "learning_rate": 1.8193666149227058e-05, + "loss": 0.2862, + "step": 4938 + }, + { + "epoch": 4.37, + "learning_rate": 1.8192844524891156e-05, + "loss": 0.2872, + "step": 4939 + }, + { + "epoch": 4.37, + "learning_rate": 1.8192022732297877e-05, + "loss": 0.2632, + "step": 4940 + }, + { + "epoch": 4.37, + "learning_rate": 1.8191200771464096e-05, + "loss": 0.2794, + "step": 4941 + }, + { + "epoch": 4.37, + "learning_rate": 1.8190378642406702e-05, + "loss": 0.2661, + "step": 4942 + }, + { + "epoch": 4.37, + "learning_rate": 1.818955634514257e-05, + "loss": 0.2815, + "step": 4943 + }, + { + "epoch": 4.38, + "learning_rate": 1.81887338796886e-05, + "loss": 0.2967, + "step": 4944 + }, + { + "epoch": 4.38, + "learning_rate": 1.8187911246061664e-05, + "loss": 0.2906, + "step": 4945 + }, + { + "epoch": 4.38, + "learning_rate": 1.8187088444278675e-05, + "loss": 0.2786, + "step": 4946 + }, + { + "epoch": 4.38, + "learning_rate": 1.8186265474356523e-05, + "loss": 0.2753, + "step": 4947 + }, + { + "epoch": 4.38, + "learning_rate": 1.8185442336312106e-05, + "loss": 0.2673, + "step": 4948 + }, + { + "epoch": 4.38, + "learning_rate": 1.8184619030162336e-05, + "loss": 0.2797, + "step": 4949 + }, + { + "epoch": 4.38, + "learning_rate": 1.818379555592412e-05, + "loss": 0.2618, + "step": 4950 + }, + { + "epoch": 4.38, + "learning_rate": 1.8182971913614364e-05, + "loss": 0.2755, + "step": 4951 + }, + { + "epoch": 4.38, + "learning_rate": 1.8182148103249987e-05, + "loss": 0.2865, + "step": 4952 + }, + { + "epoch": 4.38, + "learning_rate": 1.818132412484791e-05, + "loss": 0.2911, + "step": 4953 + }, + { + "epoch": 4.38, + "learning_rate": 1.818049997842505e-05, + "loss": 0.2744, + "step": 4954 + }, + { + "epoch": 4.38, + "learning_rate": 1.817967566399834e-05, + "loss": 0.2786, + "step": 4955 + }, + { + "epoch": 4.39, + "learning_rate": 1.8178851181584703e-05, + "loss": 0.2771, + "step": 4956 + }, + { + "epoch": 4.39, + "learning_rate": 1.8178026531201072e-05, + "loss": 0.2738, + "step": 4957 + }, + { + "epoch": 4.39, + "learning_rate": 1.8177201712864384e-05, + "loss": 0.2698, + "step": 4958 + }, + { + "epoch": 4.39, + "learning_rate": 1.817637672659158e-05, + "loss": 0.2824, + "step": 4959 + }, + { + "epoch": 4.39, + "learning_rate": 1.81755515723996e-05, + "loss": 0.2817, + "step": 4960 + }, + { + "epoch": 4.39, + "learning_rate": 1.817472625030539e-05, + "loss": 0.2818, + "step": 4961 + }, + { + "epoch": 4.39, + "learning_rate": 1.8173900760325904e-05, + "loss": 0.2851, + "step": 4962 + }, + { + "epoch": 4.39, + "learning_rate": 1.817307510247809e-05, + "loss": 0.2821, + "step": 4963 + }, + { + "epoch": 4.39, + "learning_rate": 1.817224927677891e-05, + "loss": 0.2761, + "step": 4964 + }, + { + "epoch": 4.39, + "learning_rate": 1.817142328324532e-05, + "loss": 0.2863, + "step": 4965 + }, + { + "epoch": 4.39, + "learning_rate": 1.8170597121894286e-05, + "loss": 0.2913, + "step": 4966 + }, + { + "epoch": 4.4, + "learning_rate": 1.816977079274277e-05, + "loss": 0.2817, + "step": 4967 + }, + { + "epoch": 4.4, + "learning_rate": 1.816894429580775e-05, + "loss": 0.2551, + "step": 4968 + }, + { + "epoch": 4.4, + "learning_rate": 1.8168117631106193e-05, + "loss": 0.279, + "step": 4969 + }, + { + "epoch": 4.4, + "learning_rate": 1.816729079865508e-05, + "loss": 0.2615, + "step": 4970 + }, + { + "epoch": 4.4, + "learning_rate": 1.816646379847139e-05, + "loss": 0.2932, + "step": 4971 + }, + { + "epoch": 4.4, + "learning_rate": 1.816563663057211e-05, + "loss": 0.2895, + "step": 4972 + }, + { + "epoch": 4.4, + "learning_rate": 1.8164809294974227e-05, + "loss": 0.2876, + "step": 4973 + }, + { + "epoch": 4.4, + "learning_rate": 1.816398179169473e-05, + "loss": 0.2674, + "step": 4974 + }, + { + "epoch": 4.4, + "learning_rate": 1.816315412075061e-05, + "loss": 0.2755, + "step": 4975 + }, + { + "epoch": 4.4, + "learning_rate": 1.8162326282158874e-05, + "loss": 0.2976, + "step": 4976 + }, + { + "epoch": 4.4, + "learning_rate": 1.8161498275936517e-05, + "loss": 0.2934, + "step": 4977 + }, + { + "epoch": 4.41, + "learning_rate": 1.8160670102100547e-05, + "loss": 0.2984, + "step": 4978 + }, + { + "epoch": 4.41, + "learning_rate": 1.815984176066797e-05, + "loss": 0.2862, + "step": 4979 + }, + { + "epoch": 4.41, + "learning_rate": 1.8159013251655802e-05, + "loss": 0.2605, + "step": 4980 + }, + { + "epoch": 4.41, + "learning_rate": 1.815818457508105e-05, + "loss": 0.3003, + "step": 4981 + }, + { + "epoch": 4.41, + "learning_rate": 1.8157355730960743e-05, + "loss": 0.2817, + "step": 4982 + }, + { + "epoch": 4.41, + "learning_rate": 1.8156526719311894e-05, + "loss": 0.2827, + "step": 4983 + }, + { + "epoch": 4.41, + "learning_rate": 1.815569754015153e-05, + "loss": 0.252, + "step": 4984 + }, + { + "epoch": 4.41, + "learning_rate": 1.8154868193496688e-05, + "loss": 0.2824, + "step": 4985 + }, + { + "epoch": 4.41, + "learning_rate": 1.8154038679364388e-05, + "loss": 0.2513, + "step": 4986 + }, + { + "epoch": 4.41, + "learning_rate": 1.8153208997771675e-05, + "loss": 0.2905, + "step": 4987 + }, + { + "epoch": 4.41, + "learning_rate": 1.8152379148735586e-05, + "loss": 0.2761, + "step": 4988 + }, + { + "epoch": 4.41, + "learning_rate": 1.8151549132273164e-05, + "loss": 0.2692, + "step": 4989 + }, + { + "epoch": 4.42, + "learning_rate": 1.8150718948401454e-05, + "loss": 0.296, + "step": 4990 + }, + { + "epoch": 4.42, + "learning_rate": 1.8149888597137507e-05, + "loss": 0.2741, + "step": 4991 + }, + { + "epoch": 4.42, + "learning_rate": 1.814905807849837e-05, + "loss": 0.2785, + "step": 4992 + }, + { + "epoch": 4.42, + "learning_rate": 1.814822739250111e-05, + "loss": 0.2748, + "step": 4993 + }, + { + "epoch": 4.42, + "learning_rate": 1.8147396539162777e-05, + "loss": 0.2774, + "step": 4994 + }, + { + "epoch": 4.42, + "learning_rate": 1.8146565518500442e-05, + "loss": 0.2694, + "step": 4995 + }, + { + "epoch": 4.42, + "learning_rate": 1.8145734330531166e-05, + "loss": 0.2874, + "step": 4996 + }, + { + "epoch": 4.42, + "learning_rate": 1.8144902975272023e-05, + "loss": 0.2844, + "step": 4997 + }, + { + "epoch": 4.42, + "learning_rate": 1.8144071452740085e-05, + "loss": 0.2727, + "step": 4998 + }, + { + "epoch": 4.42, + "learning_rate": 1.8143239762952428e-05, + "loss": 0.2841, + "step": 4999 + }, + { + "epoch": 4.42, + "learning_rate": 1.8142407905926135e-05, + "loss": 0.2649, + "step": 5000 + }, + { + "epoch": 4.43, + "learning_rate": 1.814157588167829e-05, + "loss": 0.2655, + "step": 5001 + }, + { + "epoch": 4.43, + "learning_rate": 1.8140743690225978e-05, + "loss": 0.2829, + "step": 5002 + }, + { + "epoch": 4.43, + "learning_rate": 1.813991133158629e-05, + "loss": 0.2844, + "step": 5003 + }, + { + "epoch": 4.43, + "learning_rate": 1.813907880577632e-05, + "loss": 0.2927, + "step": 5004 + }, + { + "epoch": 4.43, + "learning_rate": 1.8138246112813172e-05, + "loss": 0.2892, + "step": 5005 + }, + { + "epoch": 4.43, + "learning_rate": 1.813741325271394e-05, + "loss": 0.2755, + "step": 5006 + }, + { + "epoch": 4.43, + "learning_rate": 1.813658022549573e-05, + "loss": 0.286, + "step": 5007 + }, + { + "epoch": 4.43, + "learning_rate": 1.813574703117565e-05, + "loss": 0.2791, + "step": 5008 + }, + { + "epoch": 4.43, + "learning_rate": 1.8134913669770812e-05, + "loss": 0.266, + "step": 5009 + }, + { + "epoch": 4.43, + "learning_rate": 1.8134080141298328e-05, + "loss": 0.2818, + "step": 5010 + }, + { + "epoch": 4.43, + "learning_rate": 1.8133246445775324e-05, + "loss": 0.2826, + "step": 5011 + }, + { + "epoch": 4.44, + "learning_rate": 1.8132412583218914e-05, + "loss": 0.2768, + "step": 5012 + }, + { + "epoch": 4.44, + "learning_rate": 1.8131578553646227e-05, + "loss": 0.2771, + "step": 5013 + }, + { + "epoch": 4.44, + "learning_rate": 1.813074435707439e-05, + "loss": 0.2652, + "step": 5014 + }, + { + "epoch": 4.44, + "learning_rate": 1.8129909993520535e-05, + "loss": 0.2649, + "step": 5015 + }, + { + "epoch": 4.44, + "learning_rate": 1.8129075463001796e-05, + "loss": 0.2845, + "step": 5016 + }, + { + "epoch": 4.44, + "learning_rate": 1.8128240765535316e-05, + "loss": 0.2681, + "step": 5017 + }, + { + "epoch": 4.44, + "learning_rate": 1.8127405901138236e-05, + "loss": 0.2793, + "step": 5018 + }, + { + "epoch": 4.44, + "learning_rate": 1.8126570869827696e-05, + "loss": 0.28, + "step": 5019 + }, + { + "epoch": 4.44, + "learning_rate": 1.8125735671620854e-05, + "loss": 0.2819, + "step": 5020 + }, + { + "epoch": 4.44, + "learning_rate": 1.812490030653486e-05, + "loss": 0.2784, + "step": 5021 + }, + { + "epoch": 4.44, + "learning_rate": 1.8124064774586866e-05, + "loss": 0.29, + "step": 5022 + }, + { + "epoch": 4.44, + "learning_rate": 1.812322907579403e-05, + "loss": 0.2721, + "step": 5023 + }, + { + "epoch": 4.45, + "learning_rate": 1.8122393210173525e-05, + "loss": 0.2741, + "step": 5024 + }, + { + "epoch": 4.45, + "learning_rate": 1.8121557177742507e-05, + "loss": 0.285, + "step": 5025 + }, + { + "epoch": 4.45, + "learning_rate": 1.812072097851815e-05, + "loss": 0.2758, + "step": 5026 + }, + { + "epoch": 4.45, + "learning_rate": 1.8119884612517627e-05, + "loss": 0.2578, + "step": 5027 + }, + { + "epoch": 4.45, + "learning_rate": 1.8119048079758115e-05, + "loss": 0.2836, + "step": 5028 + }, + { + "epoch": 4.45, + "learning_rate": 1.8118211380256792e-05, + "loss": 0.2714, + "step": 5029 + }, + { + "epoch": 4.45, + "learning_rate": 1.8117374514030844e-05, + "loss": 0.2638, + "step": 5030 + }, + { + "epoch": 4.45, + "learning_rate": 1.8116537481097455e-05, + "loss": 0.2747, + "step": 5031 + }, + { + "epoch": 4.45, + "learning_rate": 1.8115700281473816e-05, + "loss": 0.2792, + "step": 5032 + }, + { + "epoch": 4.45, + "learning_rate": 1.811486291517712e-05, + "loss": 0.2721, + "step": 5033 + }, + { + "epoch": 4.45, + "learning_rate": 1.811402538222457e-05, + "loss": 0.2586, + "step": 5034 + }, + { + "epoch": 4.46, + "learning_rate": 1.8113187682633362e-05, + "loss": 0.2578, + "step": 5035 + }, + { + "epoch": 4.46, + "learning_rate": 1.8112349816420696e-05, + "loss": 0.252, + "step": 5036 + }, + { + "epoch": 4.46, + "learning_rate": 1.8111511783603784e-05, + "loss": 0.2678, + "step": 5037 + }, + { + "epoch": 4.46, + "learning_rate": 1.8110673584199835e-05, + "loss": 0.2728, + "step": 5038 + }, + { + "epoch": 4.46, + "learning_rate": 1.810983521822607e-05, + "loss": 0.291, + "step": 5039 + }, + { + "epoch": 4.46, + "learning_rate": 1.8108996685699694e-05, + "loss": 0.2783, + "step": 5040 + }, + { + "epoch": 4.46, + "learning_rate": 1.810815798663794e-05, + "loss": 0.2981, + "step": 5041 + }, + { + "epoch": 4.46, + "learning_rate": 1.810731912105802e-05, + "loss": 0.2832, + "step": 5042 + }, + { + "epoch": 4.46, + "learning_rate": 1.8106480088977174e-05, + "loss": 0.2891, + "step": 5043 + }, + { + "epoch": 4.46, + "learning_rate": 1.810564089041263e-05, + "loss": 0.2928, + "step": 5044 + }, + { + "epoch": 4.46, + "learning_rate": 1.8104801525381617e-05, + "loss": 0.2822, + "step": 5045 + }, + { + "epoch": 4.47, + "learning_rate": 1.8103961993901377e-05, + "loss": 0.2553, + "step": 5046 + }, + { + "epoch": 4.47, + "learning_rate": 1.8103122295989158e-05, + "loss": 0.2739, + "step": 5047 + }, + { + "epoch": 4.47, + "learning_rate": 1.810228243166219e-05, + "loss": 0.2787, + "step": 5048 + }, + { + "epoch": 4.47, + "learning_rate": 1.8101442400937737e-05, + "loss": 0.2773, + "step": 5049 + }, + { + "epoch": 4.47, + "learning_rate": 1.810060220383304e-05, + "loss": 0.2812, + "step": 5050 + }, + { + "epoch": 4.47, + "learning_rate": 1.8099761840365364e-05, + "loss": 0.2754, + "step": 5051 + }, + { + "epoch": 4.47, + "learning_rate": 1.8098921310551956e-05, + "loss": 0.2798, + "step": 5052 + }, + { + "epoch": 4.47, + "learning_rate": 1.8098080614410087e-05, + "loss": 0.2847, + "step": 5053 + }, + { + "epoch": 4.47, + "learning_rate": 1.809723975195702e-05, + "loss": 0.2608, + "step": 5054 + }, + { + "epoch": 4.47, + "learning_rate": 1.809639872321002e-05, + "loss": 0.2915, + "step": 5055 + }, + { + "epoch": 4.47, + "learning_rate": 1.8095557528186363e-05, + "loss": 0.2733, + "step": 5056 + }, + { + "epoch": 4.48, + "learning_rate": 1.8094716166903328e-05, + "loss": 0.2702, + "step": 5057 + }, + { + "epoch": 4.48, + "learning_rate": 1.8093874639378187e-05, + "loss": 0.257, + "step": 5058 + }, + { + "epoch": 4.48, + "learning_rate": 1.8093032945628228e-05, + "loss": 0.2771, + "step": 5059 + }, + { + "epoch": 4.48, + "learning_rate": 1.8092191085670733e-05, + "loss": 0.2626, + "step": 5060 + }, + { + "epoch": 4.48, + "learning_rate": 1.8091349059522996e-05, + "loss": 0.2656, + "step": 5061 + }, + { + "epoch": 4.48, + "learning_rate": 1.8090506867202305e-05, + "loss": 0.2596, + "step": 5062 + }, + { + "epoch": 4.48, + "learning_rate": 1.8089664508725957e-05, + "loss": 0.266, + "step": 5063 + }, + { + "epoch": 4.48, + "learning_rate": 1.8088821984111257e-05, + "loss": 0.2782, + "step": 5064 + }, + { + "epoch": 4.48, + "learning_rate": 1.80879792933755e-05, + "loss": 0.2687, + "step": 5065 + }, + { + "epoch": 4.48, + "learning_rate": 1.8087136436535997e-05, + "loss": 0.2721, + "step": 5066 + }, + { + "epoch": 4.48, + "learning_rate": 1.8086293413610058e-05, + "loss": 0.2599, + "step": 5067 + }, + { + "epoch": 4.48, + "learning_rate": 1.8085450224614996e-05, + "loss": 0.2817, + "step": 5068 + }, + { + "epoch": 4.49, + "learning_rate": 1.8084606869568126e-05, + "loss": 0.2663, + "step": 5069 + }, + { + "epoch": 4.49, + "learning_rate": 1.808376334848677e-05, + "loss": 0.2726, + "step": 5070 + }, + { + "epoch": 4.49, + "learning_rate": 1.8082919661388253e-05, + "loss": 0.2667, + "step": 5071 + }, + { + "epoch": 4.49, + "learning_rate": 1.8082075808289893e-05, + "loss": 0.2721, + "step": 5072 + }, + { + "epoch": 4.49, + "learning_rate": 1.8081231789209034e-05, + "loss": 0.2907, + "step": 5073 + }, + { + "epoch": 4.49, + "learning_rate": 1.8080387604162995e-05, + "loss": 0.2567, + "step": 5074 + }, + { + "epoch": 4.49, + "learning_rate": 1.8079543253169128e-05, + "loss": 0.2702, + "step": 5075 + }, + { + "epoch": 4.49, + "learning_rate": 1.8078698736244763e-05, + "loss": 0.2768, + "step": 5076 + }, + { + "epoch": 4.49, + "learning_rate": 1.807785405340725e-05, + "loss": 0.2696, + "step": 5077 + }, + { + "epoch": 4.49, + "learning_rate": 1.807700920467393e-05, + "loss": 0.2869, + "step": 5078 + }, + { + "epoch": 4.49, + "learning_rate": 1.807616419006216e-05, + "loss": 0.2888, + "step": 5079 + }, + { + "epoch": 4.5, + "learning_rate": 1.807531900958929e-05, + "loss": 0.2764, + "step": 5080 + }, + { + "epoch": 4.5, + "learning_rate": 1.8074473663272677e-05, + "loss": 0.2689, + "step": 5081 + }, + { + "epoch": 4.5, + "learning_rate": 1.8073628151129688e-05, + "loss": 0.2627, + "step": 5082 + }, + { + "epoch": 4.5, + "learning_rate": 1.8072782473177678e-05, + "loss": 0.2804, + "step": 5083 + }, + { + "epoch": 4.5, + "learning_rate": 1.8071936629434026e-05, + "loss": 0.2783, + "step": 5084 + }, + { + "epoch": 4.5, + "learning_rate": 1.8071090619916095e-05, + "loss": 0.2584, + "step": 5085 + }, + { + "epoch": 4.5, + "learning_rate": 1.8070244444641264e-05, + "loss": 0.277, + "step": 5086 + }, + { + "epoch": 4.5, + "learning_rate": 1.8069398103626903e-05, + "loss": 0.2409, + "step": 5087 + }, + { + "epoch": 4.5, + "learning_rate": 1.8068551596890404e-05, + "loss": 0.2688, + "step": 5088 + }, + { + "epoch": 4.5, + "learning_rate": 1.8067704924449147e-05, + "loss": 0.2822, + "step": 5089 + }, + { + "epoch": 4.5, + "learning_rate": 1.806685808632052e-05, + "loss": 0.2717, + "step": 5090 + }, + { + "epoch": 4.51, + "learning_rate": 1.8066011082521913e-05, + "loss": 0.2752, + "step": 5091 + }, + { + "epoch": 4.51, + "learning_rate": 1.8065163913070726e-05, + "loss": 0.2554, + "step": 5092 + }, + { + "epoch": 4.51, + "learning_rate": 1.8064316577984353e-05, + "loss": 0.2866, + "step": 5093 + }, + { + "epoch": 4.51, + "learning_rate": 1.80634690772802e-05, + "loss": 0.2878, + "step": 5094 + }, + { + "epoch": 4.51, + "learning_rate": 1.8062621410975666e-05, + "loss": 0.2592, + "step": 5095 + }, + { + "epoch": 4.51, + "learning_rate": 1.8061773579088166e-05, + "loss": 0.276, + "step": 5096 + }, + { + "epoch": 4.51, + "learning_rate": 1.8060925581635102e-05, + "loss": 0.2716, + "step": 5097 + }, + { + "epoch": 4.51, + "learning_rate": 1.8060077418633902e-05, + "loss": 0.2672, + "step": 5098 + }, + { + "epoch": 4.51, + "learning_rate": 1.805922909010198e-05, + "loss": 0.2725, + "step": 5099 + }, + { + "epoch": 4.51, + "learning_rate": 1.8058380596056758e-05, + "loss": 0.2935, + "step": 5100 + }, + { + "epoch": 4.51, + "learning_rate": 1.805753193651566e-05, + "loss": 0.2723, + "step": 5101 + }, + { + "epoch": 4.51, + "learning_rate": 1.8056683111496115e-05, + "loss": 0.2717, + "step": 5102 + }, + { + "epoch": 4.52, + "learning_rate": 1.8055834121015557e-05, + "loss": 0.2619, + "step": 5103 + }, + { + "epoch": 4.52, + "learning_rate": 1.805498496509142e-05, + "loss": 0.2662, + "step": 5104 + }, + { + "epoch": 4.52, + "learning_rate": 1.8054135643741147e-05, + "loss": 0.2692, + "step": 5105 + }, + { + "epoch": 4.52, + "learning_rate": 1.805328615698218e-05, + "loss": 0.2844, + "step": 5106 + }, + { + "epoch": 4.52, + "learning_rate": 1.8052436504831957e-05, + "loss": 0.2657, + "step": 5107 + }, + { + "epoch": 4.52, + "learning_rate": 1.8051586687307934e-05, + "loss": 0.253, + "step": 5108 + }, + { + "epoch": 4.52, + "learning_rate": 1.805073670442757e-05, + "loss": 0.2538, + "step": 5109 + }, + { + "epoch": 4.52, + "learning_rate": 1.804988655620831e-05, + "loss": 0.2624, + "step": 5110 + }, + { + "epoch": 4.52, + "learning_rate": 1.804903624266762e-05, + "loss": 0.2534, + "step": 5111 + }, + { + "epoch": 4.52, + "learning_rate": 1.804818576382296e-05, + "loss": 0.287, + "step": 5112 + }, + { + "epoch": 4.52, + "learning_rate": 1.80473351196918e-05, + "loss": 0.259, + "step": 5113 + }, + { + "epoch": 4.53, + "learning_rate": 1.8046484310291605e-05, + "loss": 0.2753, + "step": 5114 + }, + { + "epoch": 4.53, + "learning_rate": 1.804563333563985e-05, + "loss": 0.255, + "step": 5115 + }, + { + "epoch": 4.53, + "learning_rate": 1.8044782195754015e-05, + "loss": 0.2988, + "step": 5116 + }, + { + "epoch": 4.53, + "learning_rate": 1.8043930890651577e-05, + "loss": 0.2643, + "step": 5117 + }, + { + "epoch": 4.53, + "learning_rate": 1.8043079420350016e-05, + "loss": 0.2573, + "step": 5118 + }, + { + "epoch": 4.53, + "learning_rate": 1.8042227784866823e-05, + "loss": 0.2599, + "step": 5119 + }, + { + "epoch": 4.53, + "learning_rate": 1.804137598421949e-05, + "loss": 0.2534, + "step": 5120 + }, + { + "epoch": 4.53, + "learning_rate": 1.8040524018425504e-05, + "loss": 0.2706, + "step": 5121 + }, + { + "epoch": 4.53, + "learning_rate": 1.803967188750237e-05, + "loss": 0.2878, + "step": 5122 + }, + { + "epoch": 4.53, + "learning_rate": 1.803881959146758e-05, + "loss": 0.259, + "step": 5123 + }, + { + "epoch": 4.53, + "learning_rate": 1.8037967130338644e-05, + "loss": 0.2655, + "step": 5124 + }, + { + "epoch": 4.54, + "learning_rate": 1.8037114504133067e-05, + "loss": 0.278, + "step": 5125 + }, + { + "epoch": 4.54, + "learning_rate": 1.8036261712868358e-05, + "loss": 0.2712, + "step": 5126 + }, + { + "epoch": 4.54, + "learning_rate": 1.803540875656203e-05, + "loss": 0.2449, + "step": 5127 + }, + { + "epoch": 4.54, + "learning_rate": 1.803455563523161e-05, + "loss": 0.2665, + "step": 5128 + }, + { + "epoch": 4.54, + "learning_rate": 1.80337023488946e-05, + "loss": 0.2443, + "step": 5129 + }, + { + "epoch": 4.54, + "learning_rate": 1.803284889756854e-05, + "loss": 0.2615, + "step": 5130 + }, + { + "epoch": 4.54, + "learning_rate": 1.8031995281270957e-05, + "loss": 0.2727, + "step": 5131 + }, + { + "epoch": 4.54, + "learning_rate": 1.8031141500019374e-05, + "loss": 0.2577, + "step": 5132 + }, + { + "epoch": 4.54, + "learning_rate": 1.803028755383133e-05, + "loss": 0.2498, + "step": 5133 + }, + { + "epoch": 4.54, + "learning_rate": 1.802943344272436e-05, + "loss": 0.2533, + "step": 5134 + }, + { + "epoch": 4.54, + "learning_rate": 1.8028579166716004e-05, + "loss": 0.2699, + "step": 5135 + }, + { + "epoch": 4.54, + "learning_rate": 1.802772472582381e-05, + "loss": 0.2622, + "step": 5136 + }, + { + "epoch": 4.55, + "learning_rate": 1.8026870120065324e-05, + "loss": 0.2621, + "step": 5137 + }, + { + "epoch": 4.55, + "learning_rate": 1.80260153494581e-05, + "loss": 0.2668, + "step": 5138 + }, + { + "epoch": 4.55, + "learning_rate": 1.8025160414019688e-05, + "loss": 0.2569, + "step": 5139 + }, + { + "epoch": 4.55, + "learning_rate": 1.8024305313767648e-05, + "loss": 0.2655, + "step": 5140 + }, + { + "epoch": 4.55, + "learning_rate": 1.802345004871954e-05, + "loss": 0.2741, + "step": 5141 + }, + { + "epoch": 4.55, + "learning_rate": 1.802259461889293e-05, + "loss": 0.2574, + "step": 5142 + }, + { + "epoch": 4.55, + "learning_rate": 1.8021739024305387e-05, + "loss": 0.281, + "step": 5143 + }, + { + "epoch": 4.55, + "learning_rate": 1.802088326497448e-05, + "loss": 0.2815, + "step": 5144 + }, + { + "epoch": 4.55, + "learning_rate": 1.8020027340917786e-05, + "loss": 0.2623, + "step": 5145 + }, + { + "epoch": 4.55, + "learning_rate": 1.801917125215288e-05, + "loss": 0.2672, + "step": 5146 + }, + { + "epoch": 4.55, + "learning_rate": 1.801831499869735e-05, + "loss": 0.2691, + "step": 5147 + }, + { + "epoch": 4.56, + "learning_rate": 1.8017458580568772e-05, + "loss": 0.2747, + "step": 5148 + }, + { + "epoch": 4.56, + "learning_rate": 1.8016601997784743e-05, + "loss": 0.2586, + "step": 5149 + }, + { + "epoch": 4.56, + "learning_rate": 1.8015745250362852e-05, + "loss": 0.2692, + "step": 5150 + }, + { + "epoch": 4.56, + "learning_rate": 1.801488833832069e-05, + "loss": 0.2529, + "step": 5151 + }, + { + "epoch": 4.56, + "learning_rate": 1.801403126167586e-05, + "loss": 0.271, + "step": 5152 + }, + { + "epoch": 4.56, + "learning_rate": 1.801317402044596e-05, + "loss": 0.2797, + "step": 5153 + }, + { + "epoch": 4.56, + "learning_rate": 1.8012316614648602e-05, + "loss": 0.2616, + "step": 5154 + }, + { + "epoch": 4.56, + "learning_rate": 1.8011459044301388e-05, + "loss": 0.2665, + "step": 5155 + }, + { + "epoch": 4.56, + "learning_rate": 1.8010601309421935e-05, + "loss": 0.2827, + "step": 5156 + }, + { + "epoch": 4.56, + "learning_rate": 1.800974341002785e-05, + "loss": 0.269, + "step": 5157 + }, + { + "epoch": 4.56, + "learning_rate": 1.8008885346136763e-05, + "loss": 0.2712, + "step": 5158 + }, + { + "epoch": 4.57, + "learning_rate": 1.8008027117766286e-05, + "loss": 0.2545, + "step": 5159 + }, + { + "epoch": 4.57, + "learning_rate": 1.800716872493405e-05, + "loss": 0.2785, + "step": 5160 + }, + { + "epoch": 4.57, + "learning_rate": 1.8006310167657688e-05, + "loss": 0.2753, + "step": 5161 + }, + { + "epoch": 4.57, + "learning_rate": 1.8005451445954825e-05, + "loss": 0.2567, + "step": 5162 + }, + { + "epoch": 4.57, + "learning_rate": 1.8004592559843098e-05, + "loss": 0.2774, + "step": 5163 + }, + { + "epoch": 4.57, + "learning_rate": 1.8003733509340148e-05, + "loss": 0.2744, + "step": 5164 + }, + { + "epoch": 4.57, + "learning_rate": 1.8002874294463613e-05, + "loss": 0.2899, + "step": 5165 + }, + { + "epoch": 4.57, + "learning_rate": 1.8002014915231147e-05, + "loss": 0.2475, + "step": 5166 + }, + { + "epoch": 4.57, + "learning_rate": 1.800115537166039e-05, + "loss": 0.2739, + "step": 5167 + }, + { + "epoch": 4.57, + "learning_rate": 1.8000295663769005e-05, + "loss": 0.2648, + "step": 5168 + }, + { + "epoch": 4.57, + "learning_rate": 1.799943579157464e-05, + "loss": 0.2701, + "step": 5169 + }, + { + "epoch": 4.57, + "learning_rate": 1.7998575755094957e-05, + "loss": 0.2519, + "step": 5170 + }, + { + "epoch": 4.58, + "learning_rate": 1.7997715554347614e-05, + "loss": 0.2543, + "step": 5171 + }, + { + "epoch": 4.58, + "learning_rate": 1.7996855189350282e-05, + "loss": 0.2436, + "step": 5172 + }, + { + "epoch": 4.58, + "learning_rate": 1.7995994660120632e-05, + "loss": 0.2506, + "step": 5173 + }, + { + "epoch": 4.58, + "learning_rate": 1.799513396667633e-05, + "loss": 0.2835, + "step": 5174 + }, + { + "epoch": 4.58, + "learning_rate": 1.7994273109035063e-05, + "loss": 0.2749, + "step": 5175 + }, + { + "epoch": 4.58, + "learning_rate": 1.79934120872145e-05, + "loss": 0.2719, + "step": 5176 + }, + { + "epoch": 4.58, + "learning_rate": 1.7992550901232327e-05, + "loss": 0.2581, + "step": 5177 + }, + { + "epoch": 4.58, + "learning_rate": 1.799168955110623e-05, + "loss": 0.2543, + "step": 5178 + }, + { + "epoch": 4.58, + "learning_rate": 1.7990828036853903e-05, + "loss": 0.2497, + "step": 5179 + }, + { + "epoch": 4.58, + "learning_rate": 1.7989966358493033e-05, + "loss": 0.2594, + "step": 5180 + }, + { + "epoch": 4.58, + "learning_rate": 1.7989104516041323e-05, + "loss": 0.2693, + "step": 5181 + }, + { + "epoch": 4.59, + "learning_rate": 1.7988242509516464e-05, + "loss": 0.2658, + "step": 5182 + }, + { + "epoch": 4.59, + "learning_rate": 1.7987380338936167e-05, + "loss": 0.2617, + "step": 5183 + }, + { + "epoch": 4.59, + "learning_rate": 1.7986518004318134e-05, + "loss": 0.263, + "step": 5184 + }, + { + "epoch": 4.59, + "learning_rate": 1.798565550568008e-05, + "loss": 0.2691, + "step": 5185 + }, + { + "epoch": 4.59, + "learning_rate": 1.7984792843039708e-05, + "loss": 0.2567, + "step": 5186 + }, + { + "epoch": 4.59, + "learning_rate": 1.7983930016414744e-05, + "loss": 0.2681, + "step": 5187 + }, + { + "epoch": 4.59, + "learning_rate": 1.7983067025822908e-05, + "loss": 0.2588, + "step": 5188 + }, + { + "epoch": 4.59, + "learning_rate": 1.798220387128192e-05, + "loss": 0.27, + "step": 5189 + }, + { + "epoch": 4.59, + "learning_rate": 1.7981340552809503e-05, + "loss": 0.2567, + "step": 5190 + }, + { + "epoch": 4.59, + "learning_rate": 1.7980477070423395e-05, + "loss": 0.2588, + "step": 5191 + }, + { + "epoch": 4.59, + "learning_rate": 1.7979613424141325e-05, + "loss": 0.2684, + "step": 5192 + }, + { + "epoch": 4.6, + "learning_rate": 1.797874961398103e-05, + "loss": 0.2719, + "step": 5193 + }, + { + "epoch": 4.6, + "learning_rate": 1.7977885639960248e-05, + "loss": 0.2604, + "step": 5194 + }, + { + "epoch": 4.6, + "learning_rate": 1.797702150209673e-05, + "loss": 0.2625, + "step": 5195 + }, + { + "epoch": 4.6, + "learning_rate": 1.7976157200408214e-05, + "loss": 0.2763, + "step": 5196 + }, + { + "epoch": 4.6, + "learning_rate": 1.797529273491246e-05, + "loss": 0.2689, + "step": 5197 + }, + { + "epoch": 4.6, + "learning_rate": 1.797442810562721e-05, + "loss": 0.2541, + "step": 5198 + }, + { + "epoch": 4.6, + "learning_rate": 1.797356331257023e-05, + "loss": 0.267, + "step": 5199 + }, + { + "epoch": 4.6, + "learning_rate": 1.7972698355759275e-05, + "loss": 0.2534, + "step": 5200 + }, + { + "epoch": 4.6, + "learning_rate": 1.797183323521211e-05, + "loss": 0.2745, + "step": 5201 + }, + { + "epoch": 4.6, + "learning_rate": 1.7970967950946506e-05, + "loss": 0.2718, + "step": 5202 + }, + { + "epoch": 4.6, + "learning_rate": 1.797010250298023e-05, + "loss": 0.2551, + "step": 5203 + }, + { + "epoch": 4.61, + "learning_rate": 1.796923689133106e-05, + "loss": 0.2732, + "step": 5204 + }, + { + "epoch": 4.61, + "learning_rate": 1.7968371116016764e-05, + "loss": 0.2593, + "step": 5205 + }, + { + "epoch": 4.61, + "learning_rate": 1.796750517705513e-05, + "loss": 0.2545, + "step": 5206 + }, + { + "epoch": 4.61, + "learning_rate": 1.7966639074463942e-05, + "loss": 0.272, + "step": 5207 + }, + { + "epoch": 4.61, + "learning_rate": 1.7965772808260983e-05, + "loss": 0.2391, + "step": 5208 + }, + { + "epoch": 4.61, + "learning_rate": 1.7964906378464046e-05, + "loss": 0.267, + "step": 5209 + }, + { + "epoch": 4.61, + "learning_rate": 1.7964039785090925e-05, + "loss": 0.2745, + "step": 5210 + }, + { + "epoch": 4.61, + "learning_rate": 1.7963173028159414e-05, + "loss": 0.2707, + "step": 5211 + }, + { + "epoch": 4.61, + "learning_rate": 1.7962306107687323e-05, + "loss": 0.266, + "step": 5212 + }, + { + "epoch": 4.61, + "learning_rate": 1.7961439023692444e-05, + "loss": 0.2623, + "step": 5213 + }, + { + "epoch": 4.61, + "learning_rate": 1.7960571776192593e-05, + "loss": 0.2441, + "step": 5214 + }, + { + "epoch": 4.61, + "learning_rate": 1.7959704365205578e-05, + "loss": 0.2725, + "step": 5215 + }, + { + "epoch": 4.62, + "learning_rate": 1.7958836790749214e-05, + "loss": 0.2681, + "step": 5216 + }, + { + "epoch": 4.62, + "learning_rate": 1.7957969052841312e-05, + "loss": 0.2582, + "step": 5217 + }, + { + "epoch": 4.62, + "learning_rate": 1.7957101151499704e-05, + "loss": 0.265, + "step": 5218 + }, + { + "epoch": 4.62, + "learning_rate": 1.7956233086742204e-05, + "loss": 0.2556, + "step": 5219 + }, + { + "epoch": 4.62, + "learning_rate": 1.7955364858586652e-05, + "loss": 0.2626, + "step": 5220 + }, + { + "epoch": 4.62, + "learning_rate": 1.7954496467050865e-05, + "loss": 0.2493, + "step": 5221 + }, + { + "epoch": 4.62, + "learning_rate": 1.7953627912152685e-05, + "loss": 0.2774, + "step": 5222 + }, + { + "epoch": 4.62, + "learning_rate": 1.7952759193909945e-05, + "loss": 0.2702, + "step": 5223 + }, + { + "epoch": 4.62, + "learning_rate": 1.795189031234049e-05, + "loss": 0.2762, + "step": 5224 + }, + { + "epoch": 4.62, + "learning_rate": 1.7951021267462168e-05, + "loss": 0.2562, + "step": 5225 + }, + { + "epoch": 4.62, + "learning_rate": 1.7950152059292816e-05, + "loss": 0.2552, + "step": 5226 + }, + { + "epoch": 4.63, + "learning_rate": 1.7949282687850295e-05, + "loss": 0.2678, + "step": 5227 + }, + { + "epoch": 4.63, + "learning_rate": 1.7948413153152452e-05, + "loss": 0.2617, + "step": 5228 + }, + { + "epoch": 4.63, + "learning_rate": 1.7947543455217147e-05, + "loss": 0.2594, + "step": 5229 + }, + { + "epoch": 4.63, + "learning_rate": 1.7946673594062246e-05, + "loss": 0.2589, + "step": 5230 + }, + { + "epoch": 4.63, + "learning_rate": 1.7945803569705607e-05, + "loss": 0.2432, + "step": 5231 + }, + { + "epoch": 4.63, + "learning_rate": 1.7944933382165103e-05, + "loss": 0.2595, + "step": 5232 + }, + { + "epoch": 4.63, + "learning_rate": 1.79440630314586e-05, + "loss": 0.2801, + "step": 5233 + }, + { + "epoch": 4.63, + "learning_rate": 1.7943192517603975e-05, + "loss": 0.2643, + "step": 5234 + }, + { + "epoch": 4.63, + "learning_rate": 1.7942321840619105e-05, + "loss": 0.248, + "step": 5235 + }, + { + "epoch": 4.63, + "learning_rate": 1.7941451000521874e-05, + "loss": 0.2612, + "step": 5236 + }, + { + "epoch": 4.63, + "learning_rate": 1.7940579997330167e-05, + "loss": 0.2665, + "step": 5237 + }, + { + "epoch": 4.64, + "learning_rate": 1.7939708831061865e-05, + "loss": 0.2717, + "step": 5238 + }, + { + "epoch": 4.64, + "learning_rate": 1.7938837501734863e-05, + "loss": 0.2561, + "step": 5239 + }, + { + "epoch": 4.64, + "learning_rate": 1.793796600936706e-05, + "loss": 0.2498, + "step": 5240 + }, + { + "epoch": 4.64, + "learning_rate": 1.7937094353976348e-05, + "loss": 0.258, + "step": 5241 + }, + { + "epoch": 4.64, + "learning_rate": 1.7936222535580626e-05, + "loss": 0.2636, + "step": 5242 + }, + { + "epoch": 4.64, + "learning_rate": 1.793535055419781e-05, + "loss": 0.2589, + "step": 5243 + }, + { + "epoch": 4.64, + "learning_rate": 1.7934478409845798e-05, + "loss": 0.2719, + "step": 5244 + }, + { + "epoch": 4.64, + "learning_rate": 1.7933606102542507e-05, + "loss": 0.2588, + "step": 5245 + }, + { + "epoch": 4.64, + "learning_rate": 1.7932733632305845e-05, + "loss": 0.2783, + "step": 5246 + }, + { + "epoch": 4.64, + "learning_rate": 1.793186099915374e-05, + "loss": 0.2375, + "step": 5247 + }, + { + "epoch": 4.64, + "learning_rate": 1.79309882031041e-05, + "loss": 0.2925, + "step": 5248 + }, + { + "epoch": 4.64, + "learning_rate": 1.7930115244174863e-05, + "loss": 0.2511, + "step": 5249 + }, + { + "epoch": 4.65, + "learning_rate": 1.7929242122383948e-05, + "loss": 0.2615, + "step": 5250 + }, + { + "epoch": 4.65, + "learning_rate": 1.792836883774929e-05, + "loss": 0.2478, + "step": 5251 + }, + { + "epoch": 4.65, + "learning_rate": 1.792749539028882e-05, + "loss": 0.2587, + "step": 5252 + }, + { + "epoch": 4.65, + "learning_rate": 1.7926621780020487e-05, + "loss": 0.2687, + "step": 5253 + }, + { + "epoch": 4.65, + "learning_rate": 1.792574800696222e-05, + "loss": 0.2623, + "step": 5254 + }, + { + "epoch": 4.65, + "learning_rate": 1.792487407113197e-05, + "loss": 0.2447, + "step": 5255 + }, + { + "epoch": 4.65, + "learning_rate": 1.7923999972547686e-05, + "loss": 0.236, + "step": 5256 + }, + { + "epoch": 4.65, + "learning_rate": 1.7923125711227314e-05, + "loss": 0.2576, + "step": 5257 + }, + { + "epoch": 4.65, + "learning_rate": 1.7922251287188813e-05, + "loss": 0.2491, + "step": 5258 + }, + { + "epoch": 4.65, + "learning_rate": 1.792137670045014e-05, + "loss": 0.2449, + "step": 5259 + }, + { + "epoch": 4.65, + "learning_rate": 1.7920501951029255e-05, + "loss": 0.2551, + "step": 5260 + }, + { + "epoch": 4.66, + "learning_rate": 1.791962703894413e-05, + "loss": 0.2566, + "step": 5261 + }, + { + "epoch": 4.66, + "learning_rate": 1.7918751964212723e-05, + "loss": 0.2641, + "step": 5262 + }, + { + "epoch": 4.66, + "learning_rate": 1.7917876726853013e-05, + "loss": 0.2694, + "step": 5263 + }, + { + "epoch": 4.66, + "learning_rate": 1.7917001326882968e-05, + "loss": 0.2541, + "step": 5264 + }, + { + "epoch": 4.66, + "learning_rate": 1.791612576432057e-05, + "loss": 0.2518, + "step": 5265 + }, + { + "epoch": 4.66, + "learning_rate": 1.7915250039183806e-05, + "loss": 0.2812, + "step": 5266 + }, + { + "epoch": 4.66, + "learning_rate": 1.791437415149065e-05, + "loss": 0.2619, + "step": 5267 + }, + { + "epoch": 4.66, + "learning_rate": 1.7913498101259098e-05, + "loss": 0.2614, + "step": 5268 + }, + { + "epoch": 4.66, + "learning_rate": 1.7912621888507146e-05, + "loss": 0.2486, + "step": 5269 + }, + { + "epoch": 4.66, + "learning_rate": 1.7911745513252773e-05, + "loss": 0.2557, + "step": 5270 + }, + { + "epoch": 4.66, + "learning_rate": 1.7910868975513992e-05, + "loss": 0.2584, + "step": 5271 + }, + { + "epoch": 4.67, + "learning_rate": 1.7909992275308796e-05, + "loss": 0.2654, + "step": 5272 + }, + { + "epoch": 4.67, + "learning_rate": 1.7909115412655192e-05, + "loss": 0.2629, + "step": 5273 + }, + { + "epoch": 4.67, + "learning_rate": 1.790823838757119e-05, + "loss": 0.265, + "step": 5274 + }, + { + "epoch": 4.67, + "learning_rate": 1.7907361200074804e-05, + "loss": 0.2441, + "step": 5275 + }, + { + "epoch": 4.67, + "learning_rate": 1.790648385018404e-05, + "loss": 0.273, + "step": 5276 + }, + { + "epoch": 4.67, + "learning_rate": 1.7905606337916926e-05, + "loss": 0.2745, + "step": 5277 + }, + { + "epoch": 4.67, + "learning_rate": 1.790472866329148e-05, + "loss": 0.2509, + "step": 5278 + }, + { + "epoch": 4.67, + "learning_rate": 1.7903850826325722e-05, + "loss": 0.2799, + "step": 5279 + }, + { + "epoch": 4.67, + "learning_rate": 1.790297282703769e-05, + "loss": 0.2722, + "step": 5280 + }, + { + "epoch": 4.67, + "learning_rate": 1.7902094665445403e-05, + "loss": 0.2881, + "step": 5281 + }, + { + "epoch": 4.67, + "learning_rate": 1.7901216341566908e-05, + "loss": 0.2529, + "step": 5282 + }, + { + "epoch": 4.67, + "learning_rate": 1.7900337855420237e-05, + "loss": 0.2474, + "step": 5283 + }, + { + "epoch": 4.68, + "learning_rate": 1.7899459207023433e-05, + "loss": 0.2679, + "step": 5284 + }, + { + "epoch": 4.68, + "learning_rate": 1.7898580396394543e-05, + "loss": 0.2845, + "step": 5285 + }, + { + "epoch": 4.68, + "learning_rate": 1.789770142355161e-05, + "loss": 0.259, + "step": 5286 + }, + { + "epoch": 4.68, + "learning_rate": 1.7896822288512688e-05, + "loss": 0.2656, + "step": 5287 + }, + { + "epoch": 4.68, + "learning_rate": 1.7895942991295835e-05, + "loss": 0.2691, + "step": 5288 + }, + { + "epoch": 4.68, + "learning_rate": 1.7895063531919103e-05, + "loss": 0.2701, + "step": 5289 + }, + { + "epoch": 4.68, + "learning_rate": 1.789418391040056e-05, + "loss": 0.2385, + "step": 5290 + }, + { + "epoch": 4.68, + "learning_rate": 1.789330412675827e-05, + "loss": 0.2497, + "step": 5291 + }, + { + "epoch": 4.68, + "learning_rate": 1.7892424181010298e-05, + "loss": 0.2572, + "step": 5292 + }, + { + "epoch": 4.68, + "learning_rate": 1.7891544073174712e-05, + "loss": 0.2636, + "step": 5293 + }, + { + "epoch": 4.68, + "learning_rate": 1.7890663803269598e-05, + "loss": 0.2637, + "step": 5294 + }, + { + "epoch": 4.69, + "learning_rate": 1.7889783371313026e-05, + "loss": 0.2663, + "step": 5295 + }, + { + "epoch": 4.69, + "learning_rate": 1.7888902777323077e-05, + "loss": 0.274, + "step": 5296 + }, + { + "epoch": 4.69, + "learning_rate": 1.788802202131784e-05, + "loss": 0.2514, + "step": 5297 + }, + { + "epoch": 4.69, + "learning_rate": 1.7887141103315403e-05, + "loss": 0.2658, + "step": 5298 + }, + { + "epoch": 4.69, + "learning_rate": 1.7886260023333856e-05, + "loss": 0.2705, + "step": 5299 + }, + { + "epoch": 4.69, + "learning_rate": 1.7885378781391292e-05, + "loss": 0.2448, + "step": 5300 + }, + { + "epoch": 4.69, + "learning_rate": 1.7884497377505813e-05, + "loss": 0.2517, + "step": 5301 + }, + { + "epoch": 4.69, + "learning_rate": 1.7883615811695512e-05, + "loss": 0.2581, + "step": 5302 + }, + { + "epoch": 4.69, + "learning_rate": 1.788273408397851e-05, + "loss": 0.2506, + "step": 5303 + }, + { + "epoch": 4.69, + "learning_rate": 1.7881852194372897e-05, + "loss": 0.2589, + "step": 5304 + }, + { + "epoch": 4.69, + "learning_rate": 1.7880970142896798e-05, + "loss": 0.2596, + "step": 5305 + }, + { + "epoch": 4.7, + "learning_rate": 1.7880087929568322e-05, + "loss": 0.2547, + "step": 5306 + }, + { + "epoch": 4.7, + "learning_rate": 1.787920555440559e-05, + "loss": 0.2532, + "step": 5307 + }, + { + "epoch": 4.7, + "learning_rate": 1.7878323017426718e-05, + "loss": 0.2489, + "step": 5308 + }, + { + "epoch": 4.7, + "learning_rate": 1.7877440318649833e-05, + "loss": 0.2496, + "step": 5309 + }, + { + "epoch": 4.7, + "learning_rate": 1.7876557458093063e-05, + "loss": 0.2646, + "step": 5310 + }, + { + "epoch": 4.7, + "learning_rate": 1.7875674435774546e-05, + "loss": 0.2632, + "step": 5311 + }, + { + "epoch": 4.7, + "learning_rate": 1.7874791251712407e-05, + "loss": 0.272, + "step": 5312 + }, + { + "epoch": 4.7, + "learning_rate": 1.787390790592479e-05, + "loss": 0.2552, + "step": 5313 + }, + { + "epoch": 4.7, + "learning_rate": 1.7873024398429833e-05, + "loss": 0.2535, + "step": 5314 + }, + { + "epoch": 4.7, + "learning_rate": 1.7872140729245685e-05, + "loss": 0.2515, + "step": 5315 + }, + { + "epoch": 4.7, + "learning_rate": 1.7871256898390492e-05, + "loss": 0.2669, + "step": 5316 + }, + { + "epoch": 4.71, + "learning_rate": 1.7870372905882402e-05, + "loss": 0.2714, + "step": 5317 + }, + { + "epoch": 4.71, + "learning_rate": 1.7869488751739575e-05, + "loss": 0.2461, + "step": 5318 + }, + { + "epoch": 4.71, + "learning_rate": 1.7868604435980165e-05, + "loss": 0.2751, + "step": 5319 + }, + { + "epoch": 4.71, + "learning_rate": 1.7867719958622332e-05, + "loss": 0.2746, + "step": 5320 + }, + { + "epoch": 4.71, + "learning_rate": 1.7866835319684246e-05, + "loss": 0.2489, + "step": 5321 + }, + { + "epoch": 4.71, + "learning_rate": 1.7865950519184072e-05, + "loss": 0.2563, + "step": 5322 + }, + { + "epoch": 4.71, + "learning_rate": 1.7865065557139984e-05, + "loss": 0.2587, + "step": 5323 + }, + { + "epoch": 4.71, + "learning_rate": 1.7864180433570148e-05, + "loss": 0.25, + "step": 5324 + }, + { + "epoch": 4.71, + "learning_rate": 1.786329514849275e-05, + "loss": 0.2546, + "step": 5325 + }, + { + "epoch": 4.71, + "learning_rate": 1.7862409701925973e-05, + "loss": 0.2692, + "step": 5326 + }, + { + "epoch": 4.71, + "learning_rate": 1.7861524093887996e-05, + "loss": 0.2556, + "step": 5327 + }, + { + "epoch": 4.71, + "learning_rate": 1.7860638324397004e-05, + "loss": 0.2597, + "step": 5328 + }, + { + "epoch": 4.72, + "learning_rate": 1.78597523934712e-05, + "loss": 0.2759, + "step": 5329 + }, + { + "epoch": 4.72, + "learning_rate": 1.7858866301128764e-05, + "loss": 0.2565, + "step": 5330 + }, + { + "epoch": 4.72, + "learning_rate": 1.7857980047387905e-05, + "loss": 0.2615, + "step": 5331 + }, + { + "epoch": 4.72, + "learning_rate": 1.7857093632266818e-05, + "loss": 0.2468, + "step": 5332 + }, + { + "epoch": 4.72, + "learning_rate": 1.785620705578371e-05, + "loss": 0.2604, + "step": 5333 + }, + { + "epoch": 4.72, + "learning_rate": 1.7855320317956785e-05, + "loss": 0.2537, + "step": 5334 + }, + { + "epoch": 4.72, + "learning_rate": 1.7854433418804263e-05, + "loss": 0.2749, + "step": 5335 + }, + { + "epoch": 4.72, + "learning_rate": 1.785354635834435e-05, + "loss": 0.2448, + "step": 5336 + }, + { + "epoch": 4.72, + "learning_rate": 1.7852659136595264e-05, + "loss": 0.2553, + "step": 5337 + }, + { + "epoch": 4.72, + "learning_rate": 1.785177175357523e-05, + "loss": 0.2502, + "step": 5338 + }, + { + "epoch": 4.72, + "learning_rate": 1.785088420930247e-05, + "loss": 0.2665, + "step": 5339 + }, + { + "epoch": 4.73, + "learning_rate": 1.784999650379521e-05, + "loss": 0.2653, + "step": 5340 + }, + { + "epoch": 4.73, + "learning_rate": 1.7849108637071688e-05, + "loss": 0.2431, + "step": 5341 + }, + { + "epoch": 4.73, + "learning_rate": 1.7848220609150128e-05, + "loss": 0.2452, + "step": 5342 + }, + { + "epoch": 4.73, + "learning_rate": 1.7847332420048774e-05, + "loss": 0.2348, + "step": 5343 + }, + { + "epoch": 4.73, + "learning_rate": 1.7846444069785865e-05, + "loss": 0.2713, + "step": 5344 + }, + { + "epoch": 4.73, + "learning_rate": 1.7845555558379648e-05, + "loss": 0.2676, + "step": 5345 + }, + { + "epoch": 4.73, + "learning_rate": 1.7844666885848367e-05, + "loss": 0.2655, + "step": 5346 + }, + { + "epoch": 4.73, + "learning_rate": 1.7843778052210274e-05, + "loss": 0.2562, + "step": 5347 + }, + { + "epoch": 4.73, + "learning_rate": 1.784288905748362e-05, + "loss": 0.2609, + "step": 5348 + }, + { + "epoch": 4.73, + "learning_rate": 1.7841999901686668e-05, + "loss": 0.2712, + "step": 5349 + }, + { + "epoch": 4.73, + "learning_rate": 1.7841110584837675e-05, + "loss": 0.244, + "step": 5350 + }, + { + "epoch": 4.74, + "learning_rate": 1.7840221106954908e-05, + "loss": 0.2484, + "step": 5351 + }, + { + "epoch": 4.74, + "learning_rate": 1.7839331468056632e-05, + "loss": 0.2551, + "step": 5352 + }, + { + "epoch": 4.74, + "learning_rate": 1.7838441668161114e-05, + "loss": 0.2618, + "step": 5353 + }, + { + "epoch": 4.74, + "learning_rate": 1.7837551707286635e-05, + "loss": 0.2554, + "step": 5354 + }, + { + "epoch": 4.74, + "learning_rate": 1.7836661585451468e-05, + "loss": 0.2564, + "step": 5355 + }, + { + "epoch": 4.74, + "learning_rate": 1.7835771302673895e-05, + "loss": 0.2563, + "step": 5356 + }, + { + "epoch": 4.74, + "learning_rate": 1.78348808589722e-05, + "loss": 0.2758, + "step": 5357 + }, + { + "epoch": 4.74, + "learning_rate": 1.783399025436467e-05, + "loss": 0.2719, + "step": 5358 + }, + { + "epoch": 4.74, + "learning_rate": 1.7833099488869593e-05, + "loss": 0.2628, + "step": 5359 + }, + { + "epoch": 4.74, + "learning_rate": 1.7832208562505267e-05, + "loss": 0.2562, + "step": 5360 + }, + { + "epoch": 4.74, + "learning_rate": 1.7831317475289983e-05, + "loss": 0.2565, + "step": 5361 + }, + { + "epoch": 4.74, + "learning_rate": 1.783042622724205e-05, + "loss": 0.2594, + "step": 5362 + }, + { + "epoch": 4.75, + "learning_rate": 1.7829534818379766e-05, + "loss": 0.2518, + "step": 5363 + }, + { + "epoch": 4.75, + "learning_rate": 1.7828643248721435e-05, + "loss": 0.2742, + "step": 5364 + }, + { + "epoch": 4.75, + "learning_rate": 1.7827751518285374e-05, + "loss": 0.2534, + "step": 5365 + }, + { + "epoch": 4.75, + "learning_rate": 1.7826859627089894e-05, + "loss": 0.2646, + "step": 5366 + }, + { + "epoch": 4.75, + "learning_rate": 1.7825967575153313e-05, + "loss": 0.2544, + "step": 5367 + }, + { + "epoch": 4.75, + "learning_rate": 1.7825075362493948e-05, + "loss": 0.2611, + "step": 5368 + }, + { + "epoch": 4.75, + "learning_rate": 1.7824182989130122e-05, + "loss": 0.2562, + "step": 5369 + }, + { + "epoch": 4.75, + "learning_rate": 1.7823290455080166e-05, + "loss": 0.2562, + "step": 5370 + }, + { + "epoch": 4.75, + "learning_rate": 1.7822397760362407e-05, + "loss": 0.2678, + "step": 5371 + }, + { + "epoch": 4.75, + "learning_rate": 1.7821504904995178e-05, + "loss": 0.275, + "step": 5372 + }, + { + "epoch": 4.75, + "learning_rate": 1.782061188899682e-05, + "loss": 0.2571, + "step": 5373 + }, + { + "epoch": 4.76, + "learning_rate": 1.781971871238567e-05, + "loss": 0.2547, + "step": 5374 + }, + { + "epoch": 4.76, + "learning_rate": 1.781882537518007e-05, + "loss": 0.2473, + "step": 5375 + }, + { + "epoch": 4.76, + "learning_rate": 1.7817931877398366e-05, + "loss": 0.2393, + "step": 5376 + }, + { + "epoch": 4.76, + "learning_rate": 1.781703821905891e-05, + "loss": 0.2805, + "step": 5377 + }, + { + "epoch": 4.76, + "learning_rate": 1.781614440018006e-05, + "loss": 0.2553, + "step": 5378 + }, + { + "epoch": 4.76, + "learning_rate": 1.7815250420780163e-05, + "loss": 0.2528, + "step": 5379 + }, + { + "epoch": 4.76, + "learning_rate": 1.7814356280877585e-05, + "loss": 0.2659, + "step": 5380 + }, + { + "epoch": 4.76, + "learning_rate": 1.7813461980490684e-05, + "loss": 0.2507, + "step": 5381 + }, + { + "epoch": 4.76, + "learning_rate": 1.7812567519637833e-05, + "loss": 0.2455, + "step": 5382 + }, + { + "epoch": 4.76, + "learning_rate": 1.78116728983374e-05, + "loss": 0.2519, + "step": 5383 + }, + { + "epoch": 4.76, + "learning_rate": 1.7810778116607748e-05, + "loss": 0.2617, + "step": 5384 + }, + { + "epoch": 4.77, + "learning_rate": 1.780988317446727e-05, + "loss": 0.255, + "step": 5385 + }, + { + "epoch": 4.77, + "learning_rate": 1.7808988071934333e-05, + "loss": 0.2319, + "step": 5386 + }, + { + "epoch": 4.77, + "learning_rate": 1.7808092809027326e-05, + "loss": 0.2559, + "step": 5387 + }, + { + "epoch": 4.77, + "learning_rate": 1.7807197385764628e-05, + "loss": 0.2347, + "step": 5388 + }, + { + "epoch": 4.77, + "learning_rate": 1.7806301802164635e-05, + "loss": 0.2548, + "step": 5389 + }, + { + "epoch": 4.77, + "learning_rate": 1.780540605824574e-05, + "loss": 0.2623, + "step": 5390 + }, + { + "epoch": 4.77, + "learning_rate": 1.7804510154026334e-05, + "loss": 0.2592, + "step": 5391 + }, + { + "epoch": 4.77, + "learning_rate": 1.780361408952482e-05, + "loss": 0.2805, + "step": 5392 + }, + { + "epoch": 4.77, + "learning_rate": 1.7802717864759603e-05, + "loss": 0.233, + "step": 5393 + }, + { + "epoch": 4.77, + "learning_rate": 1.780182147974908e-05, + "loss": 0.2623, + "step": 5394 + }, + { + "epoch": 4.77, + "learning_rate": 1.780092493451167e-05, + "loss": 0.2601, + "step": 5395 + }, + { + "epoch": 4.77, + "learning_rate": 1.780002822906578e-05, + "loss": 0.2599, + "step": 5396 + }, + { + "epoch": 4.78, + "learning_rate": 1.779913136342983e-05, + "loss": 0.2542, + "step": 5397 + }, + { + "epoch": 4.78, + "learning_rate": 1.7798234337622232e-05, + "loss": 0.2827, + "step": 5398 + }, + { + "epoch": 4.78, + "learning_rate": 1.7797337151661413e-05, + "loss": 0.2628, + "step": 5399 + }, + { + "epoch": 4.78, + "learning_rate": 1.7796439805565797e-05, + "loss": 0.2537, + "step": 5400 + }, + { + "epoch": 4.78, + "learning_rate": 1.7795542299353818e-05, + "loss": 0.2602, + "step": 5401 + }, + { + "epoch": 4.78, + "learning_rate": 1.7794644633043898e-05, + "loss": 0.2579, + "step": 5402 + }, + { + "epoch": 4.78, + "learning_rate": 1.779374680665448e-05, + "loss": 0.2555, + "step": 5403 + }, + { + "epoch": 4.78, + "learning_rate": 1.7792848820204003e-05, + "loss": 0.2532, + "step": 5404 + }, + { + "epoch": 4.78, + "learning_rate": 1.779195067371091e-05, + "loss": 0.2578, + "step": 5405 + }, + { + "epoch": 4.78, + "learning_rate": 1.779105236719364e-05, + "loss": 0.2549, + "step": 5406 + }, + { + "epoch": 4.78, + "learning_rate": 1.7790153900670647e-05, + "loss": 0.2655, + "step": 5407 + }, + { + "epoch": 4.79, + "learning_rate": 1.7789255274160377e-05, + "loss": 0.2532, + "step": 5408 + }, + { + "epoch": 4.79, + "learning_rate": 1.7788356487681297e-05, + "loss": 0.2636, + "step": 5409 + }, + { + "epoch": 4.79, + "learning_rate": 1.7787457541251852e-05, + "loss": 0.2565, + "step": 5410 + }, + { + "epoch": 4.79, + "learning_rate": 1.778655843489051e-05, + "loss": 0.2695, + "step": 5411 + }, + { + "epoch": 4.79, + "learning_rate": 1.7785659168615738e-05, + "loss": 0.238, + "step": 5412 + }, + { + "epoch": 4.79, + "learning_rate": 1.7784759742446002e-05, + "loss": 0.2624, + "step": 5413 + }, + { + "epoch": 4.79, + "learning_rate": 1.778386015639977e-05, + "loss": 0.2662, + "step": 5414 + }, + { + "epoch": 4.79, + "learning_rate": 1.7782960410495524e-05, + "loss": 0.2565, + "step": 5415 + }, + { + "epoch": 4.79, + "learning_rate": 1.778206050475174e-05, + "loss": 0.2738, + "step": 5416 + }, + { + "epoch": 4.79, + "learning_rate": 1.778116043918689e-05, + "loss": 0.2551, + "step": 5417 + }, + { + "epoch": 4.79, + "learning_rate": 1.7780260213819475e-05, + "loss": 0.2749, + "step": 5418 + }, + { + "epoch": 4.8, + "learning_rate": 1.777935982866797e-05, + "loss": 0.2457, + "step": 5419 + }, + { + "epoch": 4.8, + "learning_rate": 1.7778459283750878e-05, + "loss": 0.2597, + "step": 5420 + }, + { + "epoch": 4.8, + "learning_rate": 1.777755857908668e-05, + "loss": 0.2469, + "step": 5421 + }, + { + "epoch": 4.8, + "learning_rate": 1.7776657714693883e-05, + "loss": 0.2597, + "step": 5422 + }, + { + "epoch": 4.8, + "learning_rate": 1.7775756690590986e-05, + "loss": 0.2473, + "step": 5423 + }, + { + "epoch": 4.8, + "learning_rate": 1.7774855506796497e-05, + "loss": 0.2628, + "step": 5424 + }, + { + "epoch": 4.8, + "learning_rate": 1.7773954163328915e-05, + "loss": 0.2636, + "step": 5425 + }, + { + "epoch": 4.8, + "learning_rate": 1.777305266020676e-05, + "loss": 0.2404, + "step": 5426 + }, + { + "epoch": 4.8, + "learning_rate": 1.7772150997448535e-05, + "loss": 0.2562, + "step": 5427 + }, + { + "epoch": 4.8, + "learning_rate": 1.777124917507277e-05, + "loss": 0.2617, + "step": 5428 + }, + { + "epoch": 4.8, + "learning_rate": 1.7770347193097983e-05, + "loss": 0.2585, + "step": 5429 + }, + { + "epoch": 4.8, + "learning_rate": 1.776944505154269e-05, + "loss": 0.255, + "step": 5430 + }, + { + "epoch": 4.81, + "learning_rate": 1.7768542750425427e-05, + "loss": 0.2465, + "step": 5431 + }, + { + "epoch": 4.81, + "learning_rate": 1.7767640289764725e-05, + "loss": 0.2721, + "step": 5432 + }, + { + "epoch": 4.81, + "learning_rate": 1.776673766957911e-05, + "loss": 0.2446, + "step": 5433 + }, + { + "epoch": 4.81, + "learning_rate": 1.7765834889887127e-05, + "loss": 0.2471, + "step": 5434 + }, + { + "epoch": 4.81, + "learning_rate": 1.776493195070731e-05, + "loss": 0.2677, + "step": 5435 + }, + { + "epoch": 4.81, + "learning_rate": 1.7764028852058212e-05, + "loss": 0.2577, + "step": 5436 + }, + { + "epoch": 4.81, + "learning_rate": 1.776312559395837e-05, + "loss": 0.2525, + "step": 5437 + }, + { + "epoch": 4.81, + "learning_rate": 1.776222217642634e-05, + "loss": 0.2636, + "step": 5438 + }, + { + "epoch": 4.81, + "learning_rate": 1.776131859948067e-05, + "loss": 0.2429, + "step": 5439 + }, + { + "epoch": 4.81, + "learning_rate": 1.7760414863139924e-05, + "loss": 0.2506, + "step": 5440 + }, + { + "epoch": 4.81, + "learning_rate": 1.775951096742266e-05, + "loss": 0.2349, + "step": 5441 + }, + { + "epoch": 4.82, + "learning_rate": 1.7758606912347444e-05, + "loss": 0.2588, + "step": 5442 + }, + { + "epoch": 4.82, + "learning_rate": 1.7757702697932834e-05, + "loss": 0.2595, + "step": 5443 + }, + { + "epoch": 4.82, + "learning_rate": 1.7756798324197406e-05, + "loss": 0.2753, + "step": 5444 + }, + { + "epoch": 4.82, + "learning_rate": 1.775589379115973e-05, + "loss": 0.2556, + "step": 5445 + }, + { + "epoch": 4.82, + "learning_rate": 1.7754989098838393e-05, + "loss": 0.2554, + "step": 5446 + }, + { + "epoch": 4.82, + "learning_rate": 1.775408424725196e-05, + "loss": 0.2627, + "step": 5447 + }, + { + "epoch": 4.82, + "learning_rate": 1.775317923641902e-05, + "loss": 0.247, + "step": 5448 + }, + { + "epoch": 4.82, + "learning_rate": 1.7752274066358165e-05, + "loss": 0.2362, + "step": 5449 + }, + { + "epoch": 4.82, + "learning_rate": 1.7751368737087976e-05, + "loss": 0.2859, + "step": 5450 + }, + { + "epoch": 4.82, + "learning_rate": 1.775046324862705e-05, + "loss": 0.2472, + "step": 5451 + }, + { + "epoch": 4.82, + "learning_rate": 1.7749557600993982e-05, + "loss": 0.2478, + "step": 5452 + }, + { + "epoch": 4.83, + "learning_rate": 1.7748651794207376e-05, + "loss": 0.2483, + "step": 5453 + }, + { + "epoch": 4.83, + "learning_rate": 1.7747745828285827e-05, + "loss": 0.2374, + "step": 5454 + }, + { + "epoch": 4.83, + "learning_rate": 1.7746839703247943e-05, + "loss": 0.2588, + "step": 5455 + }, + { + "epoch": 4.83, + "learning_rate": 1.774593341911234e-05, + "loss": 0.2396, + "step": 5456 + }, + { + "epoch": 4.83, + "learning_rate": 1.774502697589762e-05, + "loss": 0.2441, + "step": 5457 + }, + { + "epoch": 4.83, + "learning_rate": 1.7744120373622408e-05, + "loss": 0.2673, + "step": 5458 + }, + { + "epoch": 4.83, + "learning_rate": 1.7743213612305313e-05, + "loss": 0.2492, + "step": 5459 + }, + { + "epoch": 4.83, + "learning_rate": 1.7742306691964966e-05, + "loss": 0.2645, + "step": 5460 + }, + { + "epoch": 4.83, + "learning_rate": 1.7741399612619994e-05, + "loss": 0.2764, + "step": 5461 + }, + { + "epoch": 4.83, + "learning_rate": 1.7740492374289018e-05, + "loss": 0.2666, + "step": 5462 + }, + { + "epoch": 4.83, + "learning_rate": 1.7739584976990673e-05, + "loss": 0.2752, + "step": 5463 + }, + { + "epoch": 4.84, + "learning_rate": 1.7738677420743597e-05, + "loss": 0.2587, + "step": 5464 + }, + { + "epoch": 4.84, + "learning_rate": 1.7737769705566424e-05, + "loss": 0.2562, + "step": 5465 + }, + { + "epoch": 4.84, + "learning_rate": 1.7736861831477803e-05, + "loss": 0.2331, + "step": 5466 + }, + { + "epoch": 4.84, + "learning_rate": 1.773595379849637e-05, + "loss": 0.2555, + "step": 5467 + }, + { + "epoch": 4.84, + "learning_rate": 1.773504560664078e-05, + "loss": 0.255, + "step": 5468 + }, + { + "epoch": 4.84, + "learning_rate": 1.7734137255929678e-05, + "loss": 0.2656, + "step": 5469 + }, + { + "epoch": 4.84, + "learning_rate": 1.773322874638173e-05, + "loss": 0.2591, + "step": 5470 + }, + { + "epoch": 4.84, + "learning_rate": 1.7732320078015584e-05, + "loss": 0.2601, + "step": 5471 + }, + { + "epoch": 4.84, + "learning_rate": 1.7731411250849903e-05, + "loss": 0.2497, + "step": 5472 + }, + { + "epoch": 4.84, + "learning_rate": 1.7730502264903355e-05, + "loss": 0.2585, + "step": 5473 + }, + { + "epoch": 4.84, + "learning_rate": 1.7729593120194607e-05, + "loss": 0.2777, + "step": 5474 + }, + { + "epoch": 4.84, + "learning_rate": 1.7728683816742333e-05, + "loss": 0.2681, + "step": 5475 + }, + { + "epoch": 4.85, + "learning_rate": 1.77277743545652e-05, + "loss": 0.2495, + "step": 5476 + }, + { + "epoch": 4.85, + "learning_rate": 1.7726864733681893e-05, + "loss": 0.2472, + "step": 5477 + }, + { + "epoch": 4.85, + "learning_rate": 1.7725954954111085e-05, + "loss": 0.2719, + "step": 5478 + }, + { + "epoch": 4.85, + "learning_rate": 1.772504501587147e-05, + "loss": 0.2654, + "step": 5479 + }, + { + "epoch": 4.85, + "learning_rate": 1.772413491898173e-05, + "loss": 0.2352, + "step": 5480 + }, + { + "epoch": 4.85, + "learning_rate": 1.7723224663460557e-05, + "loss": 0.2594, + "step": 5481 + }, + { + "epoch": 4.85, + "learning_rate": 1.772231424932664e-05, + "loss": 0.2401, + "step": 5482 + }, + { + "epoch": 4.85, + "learning_rate": 1.7721403676598684e-05, + "loss": 0.2594, + "step": 5483 + }, + { + "epoch": 4.85, + "learning_rate": 1.7720492945295385e-05, + "loss": 0.2617, + "step": 5484 + }, + { + "epoch": 4.85, + "learning_rate": 1.771958205543545e-05, + "loss": 0.2752, + "step": 5485 + }, + { + "epoch": 4.85, + "learning_rate": 1.7718671007037588e-05, + "loss": 0.2407, + "step": 5486 + }, + { + "epoch": 4.86, + "learning_rate": 1.7717759800120498e-05, + "loss": 0.2556, + "step": 5487 + }, + { + "epoch": 4.86, + "learning_rate": 1.7716848434702903e-05, + "loss": 0.2717, + "step": 5488 + }, + { + "epoch": 4.86, + "learning_rate": 1.771593691080352e-05, + "loss": 0.2504, + "step": 5489 + }, + { + "epoch": 4.86, + "learning_rate": 1.7715025228441066e-05, + "loss": 0.2453, + "step": 5490 + }, + { + "epoch": 4.86, + "learning_rate": 1.7714113387634263e-05, + "loss": 0.2285, + "step": 5491 + }, + { + "epoch": 4.86, + "learning_rate": 1.7713201388401843e-05, + "loss": 0.2511, + "step": 5492 + }, + { + "epoch": 4.86, + "learning_rate": 1.7712289230762532e-05, + "loss": 0.2445, + "step": 5493 + }, + { + "epoch": 4.86, + "learning_rate": 1.771137691473506e-05, + "loss": 0.2308, + "step": 5494 + }, + { + "epoch": 4.86, + "learning_rate": 1.7710464440338173e-05, + "loss": 0.2477, + "step": 5495 + }, + { + "epoch": 4.86, + "learning_rate": 1.77095518075906e-05, + "loss": 0.2289, + "step": 5496 + }, + { + "epoch": 4.86, + "learning_rate": 1.770863901651109e-05, + "loss": 0.2576, + "step": 5497 + }, + { + "epoch": 4.87, + "learning_rate": 1.770772606711839e-05, + "loss": 0.2356, + "step": 5498 + }, + { + "epoch": 4.87, + "learning_rate": 1.7706812959431242e-05, + "loss": 0.2578, + "step": 5499 + }, + { + "epoch": 4.87, + "learning_rate": 1.7705899693468408e-05, + "loss": 0.2499, + "step": 5500 + }, + { + "epoch": 4.87, + "learning_rate": 1.7704986269248635e-05, + "loss": 0.2641, + "step": 5501 + }, + { + "epoch": 4.87, + "learning_rate": 1.770407268679069e-05, + "loss": 0.2603, + "step": 5502 + }, + { + "epoch": 4.87, + "learning_rate": 1.7703158946113334e-05, + "loss": 0.2611, + "step": 5503 + }, + { + "epoch": 4.87, + "learning_rate": 1.7702245047235325e-05, + "loss": 0.2609, + "step": 5504 + }, + { + "epoch": 4.87, + "learning_rate": 1.7701330990175442e-05, + "loss": 0.2582, + "step": 5505 + }, + { + "epoch": 4.87, + "learning_rate": 1.770041677495245e-05, + "loss": 0.2506, + "step": 5506 + }, + { + "epoch": 4.87, + "learning_rate": 1.7699502401585125e-05, + "loss": 0.2656, + "step": 5507 + }, + { + "epoch": 4.87, + "learning_rate": 1.769858787009225e-05, + "loss": 0.246, + "step": 5508 + }, + { + "epoch": 4.87, + "learning_rate": 1.7697673180492602e-05, + "loss": 0.2489, + "step": 5509 + }, + { + "epoch": 4.88, + "learning_rate": 1.769675833280497e-05, + "loss": 0.2604, + "step": 5510 + }, + { + "epoch": 4.88, + "learning_rate": 1.769584332704814e-05, + "loss": 0.27, + "step": 5511 + }, + { + "epoch": 4.88, + "learning_rate": 1.7694928163240903e-05, + "loss": 0.2719, + "step": 5512 + }, + { + "epoch": 4.88, + "learning_rate": 1.7694012841402055e-05, + "loss": 0.2598, + "step": 5513 + }, + { + "epoch": 4.88, + "learning_rate": 1.7693097361550396e-05, + "loss": 0.2306, + "step": 5514 + }, + { + "epoch": 4.88, + "learning_rate": 1.769218172370472e-05, + "loss": 0.2638, + "step": 5515 + }, + { + "epoch": 4.88, + "learning_rate": 1.7691265927883843e-05, + "loss": 0.2347, + "step": 5516 + }, + { + "epoch": 4.88, + "learning_rate": 1.7690349974106564e-05, + "loss": 0.2671, + "step": 5517 + }, + { + "epoch": 4.88, + "learning_rate": 1.76894338623917e-05, + "loss": 0.2443, + "step": 5518 + }, + { + "epoch": 4.88, + "learning_rate": 1.7688517592758056e-05, + "loss": 0.2583, + "step": 5519 + }, + { + "epoch": 4.88, + "learning_rate": 1.768760116522446e-05, + "loss": 0.262, + "step": 5520 + }, + { + "epoch": 4.89, + "learning_rate": 1.7686684579809727e-05, + "loss": 0.2604, + "step": 5521 + }, + { + "epoch": 4.89, + "learning_rate": 1.7685767836532682e-05, + "loss": 0.2407, + "step": 5522 + }, + { + "epoch": 4.89, + "learning_rate": 1.7684850935412156e-05, + "loss": 0.2378, + "step": 5523 + }, + { + "epoch": 4.89, + "learning_rate": 1.768393387646697e-05, + "loss": 0.2602, + "step": 5524 + }, + { + "epoch": 4.89, + "learning_rate": 1.768301665971597e-05, + "loss": 0.2448, + "step": 5525 + }, + { + "epoch": 4.89, + "learning_rate": 1.768209928517798e-05, + "loss": 0.2397, + "step": 5526 + }, + { + "epoch": 4.89, + "learning_rate": 1.7681181752871853e-05, + "loss": 0.2381, + "step": 5527 + }, + { + "epoch": 4.89, + "learning_rate": 1.768026406281642e-05, + "loss": 0.2447, + "step": 5528 + }, + { + "epoch": 4.89, + "learning_rate": 1.7679346215030543e-05, + "loss": 0.2421, + "step": 5529 + }, + { + "epoch": 4.89, + "learning_rate": 1.7678428209533057e-05, + "loss": 0.2404, + "step": 5530 + }, + { + "epoch": 4.89, + "learning_rate": 1.767751004634282e-05, + "loss": 0.2464, + "step": 5531 + }, + { + "epoch": 4.9, + "learning_rate": 1.7676591725478696e-05, + "loss": 0.2412, + "step": 5532 + }, + { + "epoch": 4.9, + "learning_rate": 1.7675673246959534e-05, + "loss": 0.2612, + "step": 5533 + }, + { + "epoch": 4.9, + "learning_rate": 1.7674754610804203e-05, + "loss": 0.2697, + "step": 5534 + }, + { + "epoch": 4.9, + "learning_rate": 1.7673835817031565e-05, + "loss": 0.2626, + "step": 5535 + }, + { + "epoch": 4.9, + "learning_rate": 1.7672916865660498e-05, + "loss": 0.2606, + "step": 5536 + }, + { + "epoch": 4.9, + "learning_rate": 1.767199775670986e-05, + "loss": 0.2395, + "step": 5537 + }, + { + "epoch": 4.9, + "learning_rate": 1.7671078490198543e-05, + "loss": 0.2654, + "step": 5538 + }, + { + "epoch": 4.9, + "learning_rate": 1.7670159066145413e-05, + "loss": 0.2561, + "step": 5539 + }, + { + "epoch": 4.9, + "learning_rate": 1.7669239484569362e-05, + "loss": 0.2572, + "step": 5540 + }, + { + "epoch": 4.9, + "learning_rate": 1.766831974548927e-05, + "loss": 0.2639, + "step": 5541 + }, + { + "epoch": 4.9, + "learning_rate": 1.7667399848924023e-05, + "loss": 0.2565, + "step": 5542 + }, + { + "epoch": 4.9, + "learning_rate": 1.766647979489252e-05, + "loss": 0.2525, + "step": 5543 + }, + { + "epoch": 4.91, + "learning_rate": 1.766555958341365e-05, + "loss": 0.2359, + "step": 5544 + }, + { + "epoch": 4.91, + "learning_rate": 1.766463921450632e-05, + "loss": 0.2526, + "step": 5545 + }, + { + "epoch": 4.91, + "learning_rate": 1.7663718688189425e-05, + "loss": 0.2488, + "step": 5546 + }, + { + "epoch": 4.91, + "learning_rate": 1.7662798004481872e-05, + "loss": 0.2594, + "step": 5547 + }, + { + "epoch": 4.91, + "learning_rate": 1.7661877163402564e-05, + "loss": 0.2515, + "step": 5548 + }, + { + "epoch": 4.91, + "learning_rate": 1.7660956164970423e-05, + "loss": 0.2547, + "step": 5549 + }, + { + "epoch": 4.91, + "learning_rate": 1.7660035009204354e-05, + "loss": 0.2573, + "step": 5550 + }, + { + "epoch": 4.91, + "learning_rate": 1.765911369612328e-05, + "loss": 0.2555, + "step": 5551 + }, + { + "epoch": 4.91, + "learning_rate": 1.7658192225746123e-05, + "loss": 0.2543, + "step": 5552 + }, + { + "epoch": 4.91, + "learning_rate": 1.76572705980918e-05, + "loss": 0.2583, + "step": 5553 + }, + { + "epoch": 4.91, + "learning_rate": 1.7656348813179246e-05, + "loss": 0.2481, + "step": 5554 + }, + { + "epoch": 4.92, + "learning_rate": 1.765542687102739e-05, + "loss": 0.2463, + "step": 5555 + }, + { + "epoch": 4.92, + "learning_rate": 1.7654504771655166e-05, + "loss": 0.2372, + "step": 5556 + }, + { + "epoch": 4.92, + "learning_rate": 1.765358251508151e-05, + "loss": 0.2493, + "step": 5557 + }, + { + "epoch": 4.92, + "learning_rate": 1.765266010132536e-05, + "loss": 0.2492, + "step": 5558 + }, + { + "epoch": 4.92, + "learning_rate": 1.765173753040567e-05, + "loss": 0.2462, + "step": 5559 + }, + { + "epoch": 4.92, + "learning_rate": 1.7650814802341374e-05, + "loss": 0.2419, + "step": 5560 + }, + { + "epoch": 4.92, + "learning_rate": 1.764989191715143e-05, + "loss": 0.2466, + "step": 5561 + }, + { + "epoch": 4.92, + "learning_rate": 1.7648968874854787e-05, + "loss": 0.2555, + "step": 5562 + }, + { + "epoch": 4.92, + "learning_rate": 1.7648045675470406e-05, + "loss": 0.2474, + "step": 5563 + }, + { + "epoch": 4.92, + "learning_rate": 1.7647122319017246e-05, + "loss": 0.2465, + "step": 5564 + }, + { + "epoch": 4.92, + "learning_rate": 1.7646198805514267e-05, + "loss": 0.2485, + "step": 5565 + }, + { + "epoch": 4.93, + "learning_rate": 1.764527513498044e-05, + "loss": 0.2556, + "step": 5566 + }, + { + "epoch": 4.93, + "learning_rate": 1.7644351307434727e-05, + "loss": 0.2378, + "step": 5567 + }, + { + "epoch": 4.93, + "learning_rate": 1.764342732289611e-05, + "loss": 0.2642, + "step": 5568 + }, + { + "epoch": 4.93, + "learning_rate": 1.7642503181383558e-05, + "loss": 0.2562, + "step": 5569 + }, + { + "epoch": 4.93, + "learning_rate": 1.7641578882916052e-05, + "loss": 0.2473, + "step": 5570 + }, + { + "epoch": 4.93, + "learning_rate": 1.764065442751258e-05, + "loss": 0.2394, + "step": 5571 + }, + { + "epoch": 4.93, + "learning_rate": 1.7639729815192117e-05, + "loss": 0.2553, + "step": 5572 + }, + { + "epoch": 4.93, + "learning_rate": 1.763880504597366e-05, + "loss": 0.2724, + "step": 5573 + }, + { + "epoch": 4.93, + "learning_rate": 1.76378801198762e-05, + "loss": 0.2511, + "step": 5574 + }, + { + "epoch": 4.93, + "learning_rate": 1.763695503691873e-05, + "loss": 0.2529, + "step": 5575 + }, + { + "epoch": 4.93, + "learning_rate": 1.763602979712025e-05, + "loss": 0.252, + "step": 5576 + }, + { + "epoch": 4.94, + "learning_rate": 1.763510440049976e-05, + "loss": 0.2462, + "step": 5577 + }, + { + "epoch": 4.94, + "learning_rate": 1.763417884707627e-05, + "loss": 0.2629, + "step": 5578 + }, + { + "epoch": 4.94, + "learning_rate": 1.763325313686878e-05, + "loss": 0.2503, + "step": 5579 + }, + { + "epoch": 4.94, + "learning_rate": 1.763232726989631e-05, + "loss": 0.2437, + "step": 5580 + }, + { + "epoch": 4.94, + "learning_rate": 1.7631401246177866e-05, + "loss": 0.2481, + "step": 5581 + }, + { + "epoch": 4.94, + "learning_rate": 1.7630475065732472e-05, + "loss": 0.2387, + "step": 5582 + }, + { + "epoch": 4.94, + "learning_rate": 1.762954872857915e-05, + "loss": 0.2578, + "step": 5583 + }, + { + "epoch": 4.94, + "learning_rate": 1.762862223473692e-05, + "loss": 0.2702, + "step": 5584 + }, + { + "epoch": 4.94, + "learning_rate": 1.7627695584224808e-05, + "loss": 0.2368, + "step": 5585 + }, + { + "epoch": 4.94, + "learning_rate": 1.7626768777061854e-05, + "loss": 0.2397, + "step": 5586 + }, + { + "epoch": 4.94, + "learning_rate": 1.7625841813267085e-05, + "loss": 0.2459, + "step": 5587 + }, + { + "epoch": 4.94, + "learning_rate": 1.7624914692859533e-05, + "loss": 0.2514, + "step": 5588 + }, + { + "epoch": 4.95, + "learning_rate": 1.762398741585825e-05, + "loss": 0.2458, + "step": 5589 + }, + { + "epoch": 4.95, + "learning_rate": 1.7623059982282274e-05, + "loss": 0.253, + "step": 5590 + }, + { + "epoch": 4.95, + "learning_rate": 1.762213239215065e-05, + "loss": 0.2364, + "step": 5591 + }, + { + "epoch": 4.95, + "learning_rate": 1.762120464548243e-05, + "loss": 0.2756, + "step": 5592 + }, + { + "epoch": 4.95, + "learning_rate": 1.762027674229667e-05, + "loss": 0.2228, + "step": 5593 + }, + { + "epoch": 4.95, + "learning_rate": 1.761934868261242e-05, + "loss": 0.2393, + "step": 5594 + }, + { + "epoch": 4.95, + "learning_rate": 1.7618420466448744e-05, + "loss": 0.2433, + "step": 5595 + }, + { + "epoch": 4.95, + "learning_rate": 1.7617492093824705e-05, + "loss": 0.2469, + "step": 5596 + }, + { + "epoch": 4.95, + "learning_rate": 1.761656356475937e-05, + "loss": 0.2657, + "step": 5597 + }, + { + "epoch": 4.95, + "learning_rate": 1.7615634879271805e-05, + "loss": 0.2571, + "step": 5598 + }, + { + "epoch": 4.95, + "learning_rate": 1.761470603738108e-05, + "loss": 0.2395, + "step": 5599 + }, + { + "epoch": 4.96, + "learning_rate": 1.7613777039106282e-05, + "loss": 0.2471, + "step": 5600 + }, + { + "epoch": 4.96, + "learning_rate": 1.761284788446648e-05, + "loss": 0.2523, + "step": 5601 + }, + { + "epoch": 4.96, + "learning_rate": 1.7611918573480756e-05, + "loss": 0.2399, + "step": 5602 + }, + { + "epoch": 4.96, + "learning_rate": 1.76109891061682e-05, + "loss": 0.2588, + "step": 5603 + }, + { + "epoch": 4.96, + "learning_rate": 1.7610059482547898e-05, + "loss": 0.257, + "step": 5604 + }, + { + "epoch": 4.96, + "learning_rate": 1.7609129702638946e-05, + "loss": 0.2625, + "step": 5605 + }, + { + "epoch": 4.96, + "learning_rate": 1.7608199766460435e-05, + "loss": 0.2675, + "step": 5606 + }, + { + "epoch": 4.96, + "learning_rate": 1.760726967403146e-05, + "loss": 0.262, + "step": 5607 + }, + { + "epoch": 4.96, + "learning_rate": 1.7606339425371128e-05, + "loss": 0.2476, + "step": 5608 + }, + { + "epoch": 4.96, + "learning_rate": 1.7605409020498543e-05, + "loss": 0.243, + "step": 5609 + }, + { + "epoch": 4.96, + "learning_rate": 1.7604478459432812e-05, + "loss": 0.2599, + "step": 5610 + }, + { + "epoch": 4.97, + "learning_rate": 1.7603547742193047e-05, + "loss": 0.2361, + "step": 5611 + }, + { + "epoch": 4.97, + "learning_rate": 1.7602616868798357e-05, + "loss": 0.2672, + "step": 5612 + }, + { + "epoch": 4.97, + "learning_rate": 1.7601685839267864e-05, + "loss": 0.242, + "step": 5613 + }, + { + "epoch": 4.97, + "learning_rate": 1.7600754653620692e-05, + "loss": 0.252, + "step": 5614 + }, + { + "epoch": 4.97, + "learning_rate": 1.7599823311875956e-05, + "loss": 0.2437, + "step": 5615 + }, + { + "epoch": 4.97, + "learning_rate": 1.759889181405279e-05, + "loss": 0.2426, + "step": 5616 + }, + { + "epoch": 4.97, + "learning_rate": 1.7597960160170326e-05, + "loss": 0.2344, + "step": 5617 + }, + { + "epoch": 4.97, + "learning_rate": 1.7597028350247688e-05, + "loss": 0.2546, + "step": 5618 + }, + { + "epoch": 4.97, + "learning_rate": 1.7596096384304023e-05, + "loss": 0.2607, + "step": 5619 + }, + { + "epoch": 4.97, + "learning_rate": 1.7595164262358463e-05, + "loss": 0.2609, + "step": 5620 + }, + { + "epoch": 4.97, + "learning_rate": 1.7594231984430158e-05, + "loss": 0.2454, + "step": 5621 + }, + { + "epoch": 4.97, + "learning_rate": 1.7593299550538246e-05, + "loss": 0.2487, + "step": 5622 + }, + { + "epoch": 4.98, + "learning_rate": 1.7592366960701884e-05, + "loss": 0.256, + "step": 5623 + }, + { + "epoch": 4.98, + "learning_rate": 1.7591434214940223e-05, + "loss": 0.2663, + "step": 5624 + }, + { + "epoch": 4.98, + "learning_rate": 1.7590501313272415e-05, + "loss": 0.241, + "step": 5625 + }, + { + "epoch": 4.98, + "learning_rate": 1.7589568255717625e-05, + "loss": 0.2724, + "step": 5626 + }, + { + "epoch": 4.98, + "learning_rate": 1.7588635042295013e-05, + "loss": 0.2608, + "step": 5627 + }, + { + "epoch": 4.98, + "learning_rate": 1.758770167302374e-05, + "loss": 0.2591, + "step": 5628 + }, + { + "epoch": 4.98, + "learning_rate": 1.758676814792298e-05, + "loss": 0.2515, + "step": 5629 + }, + { + "epoch": 4.98, + "learning_rate": 1.7585834467011903e-05, + "loss": 0.2484, + "step": 5630 + }, + { + "epoch": 4.98, + "learning_rate": 1.7584900630309686e-05, + "loss": 0.2496, + "step": 5631 + }, + { + "epoch": 4.98, + "learning_rate": 1.7583966637835505e-05, + "loss": 0.2444, + "step": 5632 + }, + { + "epoch": 4.98, + "learning_rate": 1.758303248960854e-05, + "loss": 0.263, + "step": 5633 + }, + { + "epoch": 4.99, + "learning_rate": 1.7582098185647982e-05, + "loss": 0.2496, + "step": 5634 + }, + { + "epoch": 4.99, + "learning_rate": 1.7581163725973015e-05, + "loss": 0.2571, + "step": 5635 + }, + { + "epoch": 4.99, + "learning_rate": 1.7580229110602825e-05, + "loss": 0.2641, + "step": 5636 + }, + { + "epoch": 4.99, + "learning_rate": 1.7579294339556616e-05, + "loss": 0.2463, + "step": 5637 + }, + { + "epoch": 4.99, + "learning_rate": 1.7578359412853578e-05, + "loss": 0.2545, + "step": 5638 + }, + { + "epoch": 4.99, + "learning_rate": 1.7577424330512918e-05, + "loss": 0.2312, + "step": 5639 + }, + { + "epoch": 4.99, + "learning_rate": 1.7576489092553833e-05, + "loss": 0.2505, + "step": 5640 + }, + { + "epoch": 4.99, + "learning_rate": 1.757555369899554e-05, + "loss": 0.2533, + "step": 5641 + }, + { + "epoch": 4.99, + "learning_rate": 1.7574618149857234e-05, + "loss": 0.2456, + "step": 5642 + }, + { + "epoch": 4.99, + "learning_rate": 1.757368244515814e-05, + "loss": 0.2486, + "step": 5643 + }, + { + "epoch": 4.99, + "learning_rate": 1.757274658491747e-05, + "loss": 0.2617, + "step": 5644 + }, + { + "epoch": 5.0, + "learning_rate": 1.7571810569154452e-05, + "loss": 0.2564, + "step": 5645 + }, + { + "epoch": 5.0, + "learning_rate": 1.7570874397888303e-05, + "loss": 0.2621, + "step": 5646 + }, + { + "epoch": 5.0, + "learning_rate": 1.7569938071138245e-05, + "loss": 0.2447, + "step": 5647 + }, + { + "epoch": 5.0, + "learning_rate": 1.7569001588923512e-05, + "loss": 0.2648, + "step": 5648 + }, + { + "epoch": 5.0, + "learning_rate": 1.7568064951263337e-05, + "loss": 0.2508, + "step": 5649 + }, + { + "epoch": 5.0, + "learning_rate": 1.7567128158176955e-05, + "loss": 0.2453, + "step": 5650 + }, + { + "epoch": 5.0, + "learning_rate": 1.7566191209683606e-05, + "loss": 0.2078, + "step": 5651 + }, + { + "epoch": 5.0, + "learning_rate": 1.756525410580253e-05, + "loss": 0.1707, + "step": 5652 + }, + { + "epoch": 5.0, + "learning_rate": 1.7564316846552972e-05, + "loss": 0.1613, + "step": 5653 + }, + { + "epoch": 5.0, + "learning_rate": 1.7563379431954187e-05, + "loss": 0.1672, + "step": 5654 + }, + { + "epoch": 5.0, + "learning_rate": 1.7562441862025415e-05, + "loss": 0.1618, + "step": 5655 + }, + { + "epoch": 5.0, + "learning_rate": 1.7561504136785923e-05, + "loss": 0.1536, + "step": 5656 + }, + { + "epoch": 5.01, + "learning_rate": 1.7560566256254964e-05, + "loss": 0.1647, + "step": 5657 + }, + { + "epoch": 5.01, + "learning_rate": 1.75596282204518e-05, + "loss": 0.156, + "step": 5658 + }, + { + "epoch": 5.01, + "learning_rate": 1.7558690029395697e-05, + "loss": 0.1563, + "step": 5659 + }, + { + "epoch": 5.01, + "learning_rate": 1.7557751683105918e-05, + "loss": 0.1648, + "step": 5660 + }, + { + "epoch": 5.01, + "learning_rate": 1.7556813181601736e-05, + "loss": 0.1721, + "step": 5661 + }, + { + "epoch": 5.01, + "learning_rate": 1.755587452490243e-05, + "loss": 0.1582, + "step": 5662 + }, + { + "epoch": 5.01, + "learning_rate": 1.755493571302727e-05, + "loss": 0.1538, + "step": 5663 + }, + { + "epoch": 5.01, + "learning_rate": 1.7553996745995538e-05, + "loss": 0.1626, + "step": 5664 + }, + { + "epoch": 5.01, + "learning_rate": 1.755305762382652e-05, + "loss": 0.1617, + "step": 5665 + }, + { + "epoch": 5.01, + "learning_rate": 1.7552118346539505e-05, + "loss": 0.1535, + "step": 5666 + }, + { + "epoch": 5.01, + "learning_rate": 1.755117891415378e-05, + "loss": 0.1772, + "step": 5667 + }, + { + "epoch": 5.02, + "learning_rate": 1.7550239326688638e-05, + "loss": 0.1578, + "step": 5668 + }, + { + "epoch": 5.02, + "learning_rate": 1.7549299584163376e-05, + "loss": 0.1533, + "step": 5669 + }, + { + "epoch": 5.02, + "learning_rate": 1.7548359686597295e-05, + "loss": 0.1512, + "step": 5670 + }, + { + "epoch": 5.02, + "learning_rate": 1.7547419634009693e-05, + "loss": 0.1532, + "step": 5671 + }, + { + "epoch": 5.02, + "learning_rate": 1.754647942641988e-05, + "loss": 0.1577, + "step": 5672 + }, + { + "epoch": 5.02, + "learning_rate": 1.7545539063847165e-05, + "loss": 0.1637, + "step": 5673 + }, + { + "epoch": 5.02, + "learning_rate": 1.7544598546310863e-05, + "loss": 0.1579, + "step": 5674 + }, + { + "epoch": 5.02, + "learning_rate": 1.7543657873830283e-05, + "loss": 0.1594, + "step": 5675 + }, + { + "epoch": 5.02, + "learning_rate": 1.7542717046424748e-05, + "loss": 0.1574, + "step": 5676 + }, + { + "epoch": 5.02, + "learning_rate": 1.7541776064113577e-05, + "loss": 0.163, + "step": 5677 + }, + { + "epoch": 5.02, + "learning_rate": 1.7540834926916095e-05, + "loss": 0.1614, + "step": 5678 + }, + { + "epoch": 5.03, + "learning_rate": 1.7539893634851637e-05, + "loss": 0.1543, + "step": 5679 + }, + { + "epoch": 5.03, + "learning_rate": 1.753895218793953e-05, + "loss": 0.1561, + "step": 5680 + }, + { + "epoch": 5.03, + "learning_rate": 1.7538010586199107e-05, + "loss": 0.1442, + "step": 5681 + }, + { + "epoch": 5.03, + "learning_rate": 1.7537068829649704e-05, + "loss": 0.152, + "step": 5682 + }, + { + "epoch": 5.03, + "learning_rate": 1.753612691831067e-05, + "loss": 0.1588, + "step": 5683 + }, + { + "epoch": 5.03, + "learning_rate": 1.7535184852201336e-05, + "loss": 0.1652, + "step": 5684 + }, + { + "epoch": 5.03, + "learning_rate": 1.7534242631341066e-05, + "loss": 0.1524, + "step": 5685 + }, + { + "epoch": 5.03, + "learning_rate": 1.7533300255749198e-05, + "loss": 0.1572, + "step": 5686 + }, + { + "epoch": 5.03, + "learning_rate": 1.753235772544509e-05, + "loss": 0.1567, + "step": 5687 + }, + { + "epoch": 5.03, + "learning_rate": 1.7531415040448097e-05, + "loss": 0.1625, + "step": 5688 + }, + { + "epoch": 5.03, + "learning_rate": 1.753047220077758e-05, + "loss": 0.134, + "step": 5689 + }, + { + "epoch": 5.03, + "learning_rate": 1.7529529206452905e-05, + "loss": 0.146, + "step": 5690 + }, + { + "epoch": 5.04, + "learning_rate": 1.7528586057493434e-05, + "loss": 0.1762, + "step": 5691 + }, + { + "epoch": 5.04, + "learning_rate": 1.7527642753918544e-05, + "loss": 0.1618, + "step": 5692 + }, + { + "epoch": 5.04, + "learning_rate": 1.7526699295747595e-05, + "loss": 0.1589, + "step": 5693 + }, + { + "epoch": 5.04, + "learning_rate": 1.7525755682999977e-05, + "loss": 0.1479, + "step": 5694 + }, + { + "epoch": 5.04, + "learning_rate": 1.7524811915695056e-05, + "loss": 0.1475, + "step": 5695 + }, + { + "epoch": 5.04, + "learning_rate": 1.7523867993852227e-05, + "loss": 0.1518, + "step": 5696 + }, + { + "epoch": 5.04, + "learning_rate": 1.7522923917490863e-05, + "loss": 0.1459, + "step": 5697 + }, + { + "epoch": 5.04, + "learning_rate": 1.752197968663036e-05, + "loss": 0.1537, + "step": 5698 + }, + { + "epoch": 5.04, + "learning_rate": 1.752103530129011e-05, + "loss": 0.1568, + "step": 5699 + }, + { + "epoch": 5.04, + "learning_rate": 1.7520090761489505e-05, + "loss": 0.1616, + "step": 5700 + }, + { + "epoch": 5.04, + "learning_rate": 1.7519146067247947e-05, + "loss": 0.1643, + "step": 5701 + }, + { + "epoch": 5.05, + "learning_rate": 1.7518201218584835e-05, + "loss": 0.157, + "step": 5702 + }, + { + "epoch": 5.05, + "learning_rate": 1.751725621551957e-05, + "loss": 0.1562, + "step": 5703 + }, + { + "epoch": 5.05, + "learning_rate": 1.7516311058071563e-05, + "loss": 0.1626, + "step": 5704 + }, + { + "epoch": 5.05, + "learning_rate": 1.7515365746260227e-05, + "loss": 0.147, + "step": 5705 + }, + { + "epoch": 5.05, + "learning_rate": 1.751442028010497e-05, + "loss": 0.1583, + "step": 5706 + }, + { + "epoch": 5.05, + "learning_rate": 1.7513474659625217e-05, + "loss": 0.1499, + "step": 5707 + }, + { + "epoch": 5.05, + "learning_rate": 1.751252888484038e-05, + "loss": 0.1444, + "step": 5708 + }, + { + "epoch": 5.05, + "learning_rate": 1.751158295576989e-05, + "loss": 0.1671, + "step": 5709 + }, + { + "epoch": 5.05, + "learning_rate": 1.7510636872433168e-05, + "loss": 0.1566, + "step": 5710 + }, + { + "epoch": 5.05, + "learning_rate": 1.7509690634849644e-05, + "loss": 0.1516, + "step": 5711 + }, + { + "epoch": 5.05, + "learning_rate": 1.7508744243038758e-05, + "loss": 0.1671, + "step": 5712 + }, + { + "epoch": 5.06, + "learning_rate": 1.750779769701994e-05, + "loss": 0.1625, + "step": 5713 + }, + { + "epoch": 5.06, + "learning_rate": 1.750685099681263e-05, + "loss": 0.1572, + "step": 5714 + }, + { + "epoch": 5.06, + "learning_rate": 1.750590414243627e-05, + "loss": 0.142, + "step": 5715 + }, + { + "epoch": 5.06, + "learning_rate": 1.7504957133910307e-05, + "loss": 0.1628, + "step": 5716 + }, + { + "epoch": 5.06, + "learning_rate": 1.750400997125419e-05, + "loss": 0.157, + "step": 5717 + }, + { + "epoch": 5.06, + "learning_rate": 1.750306265448737e-05, + "loss": 0.1634, + "step": 5718 + }, + { + "epoch": 5.06, + "learning_rate": 1.7502115183629303e-05, + "loss": 0.1517, + "step": 5719 + }, + { + "epoch": 5.06, + "learning_rate": 1.7501167558699446e-05, + "loss": 0.1577, + "step": 5720 + }, + { + "epoch": 5.06, + "learning_rate": 1.750021977971726e-05, + "loss": 0.1495, + "step": 5721 + }, + { + "epoch": 5.06, + "learning_rate": 1.7499271846702216e-05, + "loss": 0.1725, + "step": 5722 + }, + { + "epoch": 5.06, + "learning_rate": 1.7498323759673775e-05, + "loss": 0.1573, + "step": 5723 + }, + { + "epoch": 5.07, + "learning_rate": 1.7497375518651407e-05, + "loss": 0.1515, + "step": 5724 + }, + { + "epoch": 5.07, + "learning_rate": 1.749642712365459e-05, + "loss": 0.1458, + "step": 5725 + }, + { + "epoch": 5.07, + "learning_rate": 1.7495478574702804e-05, + "loss": 0.1475, + "step": 5726 + }, + { + "epoch": 5.07, + "learning_rate": 1.749452987181552e-05, + "loss": 0.1472, + "step": 5727 + }, + { + "epoch": 5.07, + "learning_rate": 1.7493581015012232e-05, + "loss": 0.1492, + "step": 5728 + }, + { + "epoch": 5.07, + "learning_rate": 1.749263200431242e-05, + "loss": 0.1556, + "step": 5729 + }, + { + "epoch": 5.07, + "learning_rate": 1.7491682839735573e-05, + "loss": 0.145, + "step": 5730 + }, + { + "epoch": 5.07, + "learning_rate": 1.749073352130119e-05, + "loss": 0.1621, + "step": 5731 + }, + { + "epoch": 5.07, + "learning_rate": 1.7489784049028767e-05, + "loss": 0.1506, + "step": 5732 + }, + { + "epoch": 5.07, + "learning_rate": 1.74888344229378e-05, + "loss": 0.1563, + "step": 5733 + }, + { + "epoch": 5.07, + "learning_rate": 1.748788464304779e-05, + "loss": 0.1532, + "step": 5734 + }, + { + "epoch": 5.07, + "learning_rate": 1.7486934709378245e-05, + "loss": 0.1675, + "step": 5735 + }, + { + "epoch": 5.08, + "learning_rate": 1.7485984621948678e-05, + "loss": 0.1543, + "step": 5736 + }, + { + "epoch": 5.08, + "learning_rate": 1.7485034380778592e-05, + "loss": 0.1589, + "step": 5737 + }, + { + "epoch": 5.08, + "learning_rate": 1.748408398588751e-05, + "loss": 0.1482, + "step": 5738 + }, + { + "epoch": 5.08, + "learning_rate": 1.7483133437294947e-05, + "loss": 0.1554, + "step": 5739 + }, + { + "epoch": 5.08, + "learning_rate": 1.7482182735020427e-05, + "loss": 0.1502, + "step": 5740 + }, + { + "epoch": 5.08, + "learning_rate": 1.748123187908347e-05, + "loss": 0.1576, + "step": 5741 + }, + { + "epoch": 5.08, + "learning_rate": 1.7480280869503608e-05, + "loss": 0.1465, + "step": 5742 + }, + { + "epoch": 5.08, + "learning_rate": 1.747932970630037e-05, + "loss": 0.1497, + "step": 5743 + }, + { + "epoch": 5.08, + "learning_rate": 1.747837838949329e-05, + "loss": 0.1571, + "step": 5744 + }, + { + "epoch": 5.08, + "learning_rate": 1.7477426919101906e-05, + "loss": 0.1544, + "step": 5745 + }, + { + "epoch": 5.08, + "learning_rate": 1.7476475295145764e-05, + "loss": 0.1528, + "step": 5746 + }, + { + "epoch": 5.09, + "learning_rate": 1.7475523517644398e-05, + "loss": 0.1403, + "step": 5747 + }, + { + "epoch": 5.09, + "learning_rate": 1.7474571586617358e-05, + "loss": 0.1651, + "step": 5748 + }, + { + "epoch": 5.09, + "learning_rate": 1.7473619502084197e-05, + "loss": 0.1545, + "step": 5749 + }, + { + "epoch": 5.09, + "learning_rate": 1.7472667264064465e-05, + "loss": 0.1597, + "step": 5750 + }, + { + "epoch": 5.09, + "learning_rate": 1.7471714872577722e-05, + "loss": 0.1555, + "step": 5751 + }, + { + "epoch": 5.09, + "learning_rate": 1.7470762327643523e-05, + "loss": 0.1561, + "step": 5752 + }, + { + "epoch": 5.09, + "learning_rate": 1.746980962928143e-05, + "loss": 0.1602, + "step": 5753 + }, + { + "epoch": 5.09, + "learning_rate": 1.7468856777511008e-05, + "loss": 0.1564, + "step": 5754 + }, + { + "epoch": 5.09, + "learning_rate": 1.7467903772351835e-05, + "loss": 0.1594, + "step": 5755 + }, + { + "epoch": 5.09, + "learning_rate": 1.7466950613823476e-05, + "loss": 0.1664, + "step": 5756 + }, + { + "epoch": 5.09, + "learning_rate": 1.74659973019455e-05, + "loss": 0.1499, + "step": 5757 + }, + { + "epoch": 5.1, + "learning_rate": 1.74650438367375e-05, + "loss": 0.1623, + "step": 5758 + }, + { + "epoch": 5.1, + "learning_rate": 1.7464090218219045e-05, + "loss": 0.1473, + "step": 5759 + }, + { + "epoch": 5.1, + "learning_rate": 1.7463136446409725e-05, + "loss": 0.171, + "step": 5760 + }, + { + "epoch": 5.1, + "learning_rate": 1.746218252132913e-05, + "loss": 0.163, + "step": 5761 + }, + { + "epoch": 5.1, + "learning_rate": 1.7461228442996844e-05, + "loss": 0.1568, + "step": 5762 + }, + { + "epoch": 5.1, + "learning_rate": 1.7460274211432463e-05, + "loss": 0.1708, + "step": 5763 + }, + { + "epoch": 5.1, + "learning_rate": 1.7459319826655584e-05, + "loss": 0.1658, + "step": 5764 + }, + { + "epoch": 5.1, + "learning_rate": 1.7458365288685816e-05, + "loss": 0.1671, + "step": 5765 + }, + { + "epoch": 5.1, + "learning_rate": 1.745741059754275e-05, + "loss": 0.1549, + "step": 5766 + }, + { + "epoch": 5.1, + "learning_rate": 1.7456455753246e-05, + "loss": 0.1683, + "step": 5767 + }, + { + "epoch": 5.1, + "learning_rate": 1.7455500755815172e-05, + "loss": 0.1495, + "step": 5768 + }, + { + "epoch": 5.1, + "learning_rate": 1.7454545605269883e-05, + "loss": 0.1625, + "step": 5769 + }, + { + "epoch": 5.11, + "learning_rate": 1.7453590301629748e-05, + "loss": 0.165, + "step": 5770 + }, + { + "epoch": 5.11, + "learning_rate": 1.745263484491438e-05, + "loss": 0.1458, + "step": 5771 + }, + { + "epoch": 5.11, + "learning_rate": 1.7451679235143414e-05, + "loss": 0.1607, + "step": 5772 + }, + { + "epoch": 5.11, + "learning_rate": 1.745072347233646e-05, + "loss": 0.1627, + "step": 5773 + }, + { + "epoch": 5.11, + "learning_rate": 1.744976755651316e-05, + "loss": 0.1452, + "step": 5774 + }, + { + "epoch": 5.11, + "learning_rate": 1.7448811487693136e-05, + "loss": 0.1504, + "step": 5775 + }, + { + "epoch": 5.11, + "learning_rate": 1.744785526589603e-05, + "loss": 0.1672, + "step": 5776 + }, + { + "epoch": 5.11, + "learning_rate": 1.7446898891141475e-05, + "loss": 0.1541, + "step": 5777 + }, + { + "epoch": 5.11, + "learning_rate": 1.7445942363449112e-05, + "loss": 0.1655, + "step": 5778 + }, + { + "epoch": 5.11, + "learning_rate": 1.744498568283859e-05, + "loss": 0.157, + "step": 5779 + }, + { + "epoch": 5.11, + "learning_rate": 1.7444028849329556e-05, + "loss": 0.1652, + "step": 5780 + }, + { + "epoch": 5.12, + "learning_rate": 1.7443071862941656e-05, + "loss": 0.159, + "step": 5781 + }, + { + "epoch": 5.12, + "learning_rate": 1.7442114723694547e-05, + "loss": 0.1614, + "step": 5782 + }, + { + "epoch": 5.12, + "learning_rate": 1.7441157431607885e-05, + "loss": 0.1598, + "step": 5783 + }, + { + "epoch": 5.12, + "learning_rate": 1.7440199986701328e-05, + "loss": 0.1586, + "step": 5784 + }, + { + "epoch": 5.12, + "learning_rate": 1.7439242388994544e-05, + "loss": 0.1603, + "step": 5785 + }, + { + "epoch": 5.12, + "learning_rate": 1.7438284638507196e-05, + "loss": 0.1577, + "step": 5786 + }, + { + "epoch": 5.12, + "learning_rate": 1.7437326735258955e-05, + "loss": 0.1551, + "step": 5787 + }, + { + "epoch": 5.12, + "learning_rate": 1.743636867926949e-05, + "loss": 0.15, + "step": 5788 + }, + { + "epoch": 5.12, + "learning_rate": 1.743541047055848e-05, + "loss": 0.1574, + "step": 5789 + }, + { + "epoch": 5.12, + "learning_rate": 1.743445210914561e-05, + "loss": 0.1587, + "step": 5790 + }, + { + "epoch": 5.12, + "learning_rate": 1.7433493595050545e-05, + "loss": 0.1621, + "step": 5791 + }, + { + "epoch": 5.13, + "learning_rate": 1.7432534928292984e-05, + "loss": 0.1565, + "step": 5792 + }, + { + "epoch": 5.13, + "learning_rate": 1.7431576108892616e-05, + "loss": 0.1547, + "step": 5793 + }, + { + "epoch": 5.13, + "learning_rate": 1.7430617136869122e-05, + "loss": 0.1618, + "step": 5794 + }, + { + "epoch": 5.13, + "learning_rate": 1.7429658012242206e-05, + "loss": 0.1507, + "step": 5795 + }, + { + "epoch": 5.13, + "learning_rate": 1.742869873503156e-05, + "loss": 0.162, + "step": 5796 + }, + { + "epoch": 5.13, + "learning_rate": 1.7427739305256887e-05, + "loss": 0.1529, + "step": 5797 + }, + { + "epoch": 5.13, + "learning_rate": 1.742677972293789e-05, + "loss": 0.1557, + "step": 5798 + }, + { + "epoch": 5.13, + "learning_rate": 1.7425819988094277e-05, + "loss": 0.1528, + "step": 5799 + }, + { + "epoch": 5.13, + "learning_rate": 1.742486010074576e-05, + "loss": 0.1669, + "step": 5800 + }, + { + "epoch": 5.13, + "learning_rate": 1.7423900060912048e-05, + "loss": 0.1677, + "step": 5801 + }, + { + "epoch": 5.13, + "learning_rate": 1.7422939868612862e-05, + "loss": 0.1503, + "step": 5802 + }, + { + "epoch": 5.13, + "learning_rate": 1.742197952386792e-05, + "loss": 0.1709, + "step": 5803 + }, + { + "epoch": 5.14, + "learning_rate": 1.742101902669694e-05, + "loss": 0.1673, + "step": 5804 + }, + { + "epoch": 5.14, + "learning_rate": 1.7420058377119656e-05, + "loss": 0.1561, + "step": 5805 + }, + { + "epoch": 5.14, + "learning_rate": 1.741909757515579e-05, + "loss": 0.1489, + "step": 5806 + }, + { + "epoch": 5.14, + "learning_rate": 1.7418136620825077e-05, + "loss": 0.1525, + "step": 5807 + }, + { + "epoch": 5.14, + "learning_rate": 1.7417175514147256e-05, + "loss": 0.1383, + "step": 5808 + }, + { + "epoch": 5.14, + "learning_rate": 1.7416214255142058e-05, + "loss": 0.1388, + "step": 5809 + }, + { + "epoch": 5.14, + "learning_rate": 1.741525284382923e-05, + "loss": 0.1617, + "step": 5810 + }, + { + "epoch": 5.14, + "learning_rate": 1.7414291280228513e-05, + "loss": 0.1737, + "step": 5811 + }, + { + "epoch": 5.14, + "learning_rate": 1.7413329564359656e-05, + "loss": 0.1587, + "step": 5812 + }, + { + "epoch": 5.14, + "learning_rate": 1.741236769624241e-05, + "loss": 0.144, + "step": 5813 + }, + { + "epoch": 5.14, + "learning_rate": 1.741140567589653e-05, + "loss": 0.1586, + "step": 5814 + }, + { + "epoch": 5.15, + "learning_rate": 1.7410443503341773e-05, + "loss": 0.1696, + "step": 5815 + }, + { + "epoch": 5.15, + "learning_rate": 1.74094811785979e-05, + "loss": 0.1552, + "step": 5816 + }, + { + "epoch": 5.15, + "learning_rate": 1.740851870168467e-05, + "loss": 0.1593, + "step": 5817 + }, + { + "epoch": 5.15, + "learning_rate": 1.7407556072621853e-05, + "loss": 0.1639, + "step": 5818 + }, + { + "epoch": 5.15, + "learning_rate": 1.740659329142922e-05, + "loss": 0.1561, + "step": 5819 + }, + { + "epoch": 5.15, + "learning_rate": 1.740563035812654e-05, + "loss": 0.1542, + "step": 5820 + }, + { + "epoch": 5.15, + "learning_rate": 1.740466727273359e-05, + "loss": 0.1674, + "step": 5821 + }, + { + "epoch": 5.15, + "learning_rate": 1.740370403527015e-05, + "loss": 0.1588, + "step": 5822 + }, + { + "epoch": 5.15, + "learning_rate": 1.7402740645756006e-05, + "loss": 0.1441, + "step": 5823 + }, + { + "epoch": 5.15, + "learning_rate": 1.740177710421093e-05, + "loss": 0.1679, + "step": 5824 + }, + { + "epoch": 5.15, + "learning_rate": 1.740081341065473e-05, + "loss": 0.1609, + "step": 5825 + }, + { + "epoch": 5.16, + "learning_rate": 1.7399849565107182e-05, + "loss": 0.1607, + "step": 5826 + }, + { + "epoch": 5.16, + "learning_rate": 1.7398885567588087e-05, + "loss": 0.147, + "step": 5827 + }, + { + "epoch": 5.16, + "learning_rate": 1.7397921418117237e-05, + "loss": 0.1639, + "step": 5828 + }, + { + "epoch": 5.16, + "learning_rate": 1.739695711671444e-05, + "loss": 0.165, + "step": 5829 + }, + { + "epoch": 5.16, + "learning_rate": 1.73959926633995e-05, + "loss": 0.1476, + "step": 5830 + }, + { + "epoch": 5.16, + "learning_rate": 1.7395028058192216e-05, + "loss": 0.1594, + "step": 5831 + }, + { + "epoch": 5.16, + "learning_rate": 1.7394063301112405e-05, + "loss": 0.1728, + "step": 5832 + }, + { + "epoch": 5.16, + "learning_rate": 1.7393098392179882e-05, + "loss": 0.1509, + "step": 5833 + }, + { + "epoch": 5.16, + "learning_rate": 1.7392133331414457e-05, + "loss": 0.1579, + "step": 5834 + }, + { + "epoch": 5.16, + "learning_rate": 1.7391168118835954e-05, + "loss": 0.1619, + "step": 5835 + }, + { + "epoch": 5.16, + "learning_rate": 1.7390202754464193e-05, + "loss": 0.1512, + "step": 5836 + }, + { + "epoch": 5.17, + "learning_rate": 1.7389237238319002e-05, + "loss": 0.1538, + "step": 5837 + }, + { + "epoch": 5.17, + "learning_rate": 1.7388271570420205e-05, + "loss": 0.1525, + "step": 5838 + }, + { + "epoch": 5.17, + "learning_rate": 1.7387305750787642e-05, + "loss": 0.1508, + "step": 5839 + }, + { + "epoch": 5.17, + "learning_rate": 1.7386339779441144e-05, + "loss": 0.1728, + "step": 5840 + }, + { + "epoch": 5.17, + "learning_rate": 1.738537365640055e-05, + "loss": 0.1518, + "step": 5841 + }, + { + "epoch": 5.17, + "learning_rate": 1.73844073816857e-05, + "loss": 0.159, + "step": 5842 + }, + { + "epoch": 5.17, + "learning_rate": 1.738344095531644e-05, + "loss": 0.1688, + "step": 5843 + }, + { + "epoch": 5.17, + "learning_rate": 1.7382474377312616e-05, + "loss": 0.162, + "step": 5844 + }, + { + "epoch": 5.17, + "learning_rate": 1.738150764769408e-05, + "loss": 0.1729, + "step": 5845 + }, + { + "epoch": 5.17, + "learning_rate": 1.7380540766480687e-05, + "loss": 0.1596, + "step": 5846 + }, + { + "epoch": 5.17, + "learning_rate": 1.7379573733692293e-05, + "loss": 0.1578, + "step": 5847 + }, + { + "epoch": 5.17, + "learning_rate": 1.7378606549348754e-05, + "loss": 0.1469, + "step": 5848 + }, + { + "epoch": 5.18, + "learning_rate": 1.737763921346994e-05, + "loss": 0.1495, + "step": 5849 + }, + { + "epoch": 5.18, + "learning_rate": 1.737667172607571e-05, + "loss": 0.1651, + "step": 5850 + }, + { + "epoch": 5.18, + "learning_rate": 1.737570408718594e-05, + "loss": 0.1611, + "step": 5851 + }, + { + "epoch": 5.18, + "learning_rate": 1.7374736296820504e-05, + "loss": 0.1638, + "step": 5852 + }, + { + "epoch": 5.18, + "learning_rate": 1.7373768354999266e-05, + "loss": 0.1611, + "step": 5853 + }, + { + "epoch": 5.18, + "learning_rate": 1.7372800261742116e-05, + "loss": 0.1754, + "step": 5854 + }, + { + "epoch": 5.18, + "learning_rate": 1.7371832017068933e-05, + "loss": 0.1485, + "step": 5855 + }, + { + "epoch": 5.18, + "learning_rate": 1.7370863620999602e-05, + "loss": 0.159, + "step": 5856 + }, + { + "epoch": 5.18, + "learning_rate": 1.7369895073554004e-05, + "loss": 0.1606, + "step": 5857 + }, + { + "epoch": 5.18, + "learning_rate": 1.736892637475204e-05, + "loss": 0.1505, + "step": 5858 + }, + { + "epoch": 5.18, + "learning_rate": 1.7367957524613603e-05, + "loss": 0.1536, + "step": 5859 + }, + { + "epoch": 5.19, + "learning_rate": 1.7366988523158586e-05, + "loss": 0.1605, + "step": 5860 + }, + { + "epoch": 5.19, + "learning_rate": 1.736601937040689e-05, + "loss": 0.1544, + "step": 5861 + }, + { + "epoch": 5.19, + "learning_rate": 1.7365050066378422e-05, + "loss": 0.15, + "step": 5862 + }, + { + "epoch": 5.19, + "learning_rate": 1.736408061109309e-05, + "loss": 0.1609, + "step": 5863 + }, + { + "epoch": 5.19, + "learning_rate": 1.7363111004570793e-05, + "loss": 0.1541, + "step": 5864 + }, + { + "epoch": 5.19, + "learning_rate": 1.7362141246831455e-05, + "loss": 0.1619, + "step": 5865 + }, + { + "epoch": 5.19, + "learning_rate": 1.7361171337894988e-05, + "loss": 0.1527, + "step": 5866 + }, + { + "epoch": 5.19, + "learning_rate": 1.7360201277781314e-05, + "loss": 0.1478, + "step": 5867 + }, + { + "epoch": 5.19, + "learning_rate": 1.735923106651035e-05, + "loss": 0.1694, + "step": 5868 + }, + { + "epoch": 5.19, + "learning_rate": 1.7358260704102026e-05, + "loss": 0.1405, + "step": 5869 + }, + { + "epoch": 5.19, + "learning_rate": 1.7357290190576267e-05, + "loss": 0.15, + "step": 5870 + }, + { + "epoch": 5.2, + "learning_rate": 1.735631952595301e-05, + "loss": 0.1511, + "step": 5871 + }, + { + "epoch": 5.2, + "learning_rate": 1.735534871025218e-05, + "loss": 0.1618, + "step": 5872 + }, + { + "epoch": 5.2, + "learning_rate": 1.7354377743493725e-05, + "loss": 0.1548, + "step": 5873 + }, + { + "epoch": 5.2, + "learning_rate": 1.7353406625697582e-05, + "loss": 0.1466, + "step": 5874 + }, + { + "epoch": 5.2, + "learning_rate": 1.735243535688369e-05, + "loss": 0.1698, + "step": 5875 + }, + { + "epoch": 5.2, + "learning_rate": 1.7351463937072008e-05, + "loss": 0.1691, + "step": 5876 + }, + { + "epoch": 5.2, + "learning_rate": 1.735049236628247e-05, + "loss": 0.1415, + "step": 5877 + }, + { + "epoch": 5.2, + "learning_rate": 1.7349520644535042e-05, + "loss": 0.1466, + "step": 5878 + }, + { + "epoch": 5.2, + "learning_rate": 1.734854877184968e-05, + "loss": 0.1329, + "step": 5879 + }, + { + "epoch": 5.2, + "learning_rate": 1.7347576748246335e-05, + "loss": 0.1792, + "step": 5880 + }, + { + "epoch": 5.2, + "learning_rate": 1.7346604573744972e-05, + "loss": 0.1469, + "step": 5881 + }, + { + "epoch": 5.2, + "learning_rate": 1.7345632248365564e-05, + "loss": 0.1609, + "step": 5882 + }, + { + "epoch": 5.21, + "learning_rate": 1.734465977212807e-05, + "loss": 0.1367, + "step": 5883 + }, + { + "epoch": 5.21, + "learning_rate": 1.734368714505247e-05, + "loss": 0.1456, + "step": 5884 + }, + { + "epoch": 5.21, + "learning_rate": 1.7342714367158734e-05, + "loss": 0.1571, + "step": 5885 + }, + { + "epoch": 5.21, + "learning_rate": 1.7341741438466845e-05, + "loss": 0.1589, + "step": 5886 + }, + { + "epoch": 5.21, + "learning_rate": 1.7340768358996776e-05, + "loss": 0.1613, + "step": 5887 + }, + { + "epoch": 5.21, + "learning_rate": 1.7339795128768516e-05, + "loss": 0.1427, + "step": 5888 + }, + { + "epoch": 5.21, + "learning_rate": 1.7338821747802056e-05, + "loss": 0.1697, + "step": 5889 + }, + { + "epoch": 5.21, + "learning_rate": 1.733784821611738e-05, + "loss": 0.158, + "step": 5890 + }, + { + "epoch": 5.21, + "learning_rate": 1.7336874533734483e-05, + "loss": 0.1551, + "step": 5891 + }, + { + "epoch": 5.21, + "learning_rate": 1.7335900700673363e-05, + "loss": 0.164, + "step": 5892 + }, + { + "epoch": 5.21, + "learning_rate": 1.7334926716954027e-05, + "loss": 0.1523, + "step": 5893 + }, + { + "epoch": 5.22, + "learning_rate": 1.7333952582596463e-05, + "loss": 0.1562, + "step": 5894 + }, + { + "epoch": 5.22, + "learning_rate": 1.7332978297620684e-05, + "loss": 0.1531, + "step": 5895 + }, + { + "epoch": 5.22, + "learning_rate": 1.7332003862046702e-05, + "loss": 0.1538, + "step": 5896 + }, + { + "epoch": 5.22, + "learning_rate": 1.7331029275894528e-05, + "loss": 0.1524, + "step": 5897 + }, + { + "epoch": 5.22, + "learning_rate": 1.7330054539184172e-05, + "loss": 0.147, + "step": 5898 + }, + { + "epoch": 5.22, + "learning_rate": 1.7329079651935658e-05, + "loss": 0.153, + "step": 5899 + }, + { + "epoch": 5.22, + "learning_rate": 1.7328104614169003e-05, + "loss": 0.1471, + "step": 5900 + }, + { + "epoch": 5.22, + "learning_rate": 1.7327129425904234e-05, + "loss": 0.137, + "step": 5901 + }, + { + "epoch": 5.22, + "learning_rate": 1.732615408716138e-05, + "loss": 0.1538, + "step": 5902 + }, + { + "epoch": 5.22, + "learning_rate": 1.732517859796047e-05, + "loss": 0.1634, + "step": 5903 + }, + { + "epoch": 5.22, + "learning_rate": 1.7324202958321538e-05, + "loss": 0.1533, + "step": 5904 + }, + { + "epoch": 5.23, + "learning_rate": 1.7323227168264617e-05, + "loss": 0.1542, + "step": 5905 + }, + { + "epoch": 5.23, + "learning_rate": 1.7322251227809753e-05, + "loss": 0.1545, + "step": 5906 + }, + { + "epoch": 5.23, + "learning_rate": 1.7321275136976986e-05, + "loss": 0.1571, + "step": 5907 + }, + { + "epoch": 5.23, + "learning_rate": 1.7320298895786363e-05, + "loss": 0.1445, + "step": 5908 + }, + { + "epoch": 5.23, + "learning_rate": 1.7319322504257933e-05, + "loss": 0.1537, + "step": 5909 + }, + { + "epoch": 5.23, + "learning_rate": 1.7318345962411743e-05, + "loss": 0.1444, + "step": 5910 + }, + { + "epoch": 5.23, + "learning_rate": 1.7317369270267857e-05, + "loss": 0.1586, + "step": 5911 + }, + { + "epoch": 5.23, + "learning_rate": 1.7316392427846334e-05, + "loss": 0.1697, + "step": 5912 + }, + { + "epoch": 5.23, + "learning_rate": 1.7315415435167223e-05, + "loss": 0.1628, + "step": 5913 + }, + { + "epoch": 5.23, + "learning_rate": 1.7314438292250604e-05, + "loss": 0.1356, + "step": 5914 + }, + { + "epoch": 5.23, + "learning_rate": 1.7313460999116537e-05, + "loss": 0.1577, + "step": 5915 + }, + { + "epoch": 5.23, + "learning_rate": 1.7312483555785087e-05, + "loss": 0.1512, + "step": 5916 + }, + { + "epoch": 5.24, + "learning_rate": 1.731150596227634e-05, + "loss": 0.148, + "step": 5917 + }, + { + "epoch": 5.24, + "learning_rate": 1.7310528218610364e-05, + "loss": 0.1626, + "step": 5918 + }, + { + "epoch": 5.24, + "learning_rate": 1.7309550324807243e-05, + "loss": 0.1523, + "step": 5919 + }, + { + "epoch": 5.24, + "learning_rate": 1.7308572280887058e-05, + "loss": 0.1549, + "step": 5920 + }, + { + "epoch": 5.24, + "learning_rate": 1.7307594086869897e-05, + "loss": 0.1582, + "step": 5921 + }, + { + "epoch": 5.24, + "learning_rate": 1.730661574277585e-05, + "loss": 0.1544, + "step": 5922 + }, + { + "epoch": 5.24, + "learning_rate": 1.7305637248625007e-05, + "loss": 0.1547, + "step": 5923 + }, + { + "epoch": 5.24, + "learning_rate": 1.7304658604437465e-05, + "loss": 0.1602, + "step": 5924 + }, + { + "epoch": 5.24, + "learning_rate": 1.7303679810233324e-05, + "loss": 0.1574, + "step": 5925 + }, + { + "epoch": 5.24, + "learning_rate": 1.730270086603268e-05, + "loss": 0.1574, + "step": 5926 + }, + { + "epoch": 5.24, + "learning_rate": 1.730172177185564e-05, + "loss": 0.1566, + "step": 5927 + }, + { + "epoch": 5.25, + "learning_rate": 1.730074252772232e-05, + "loss": 0.1419, + "step": 5928 + }, + { + "epoch": 5.25, + "learning_rate": 1.729976313365282e-05, + "loss": 0.155, + "step": 5929 + }, + { + "epoch": 5.25, + "learning_rate": 1.7298783589667256e-05, + "loss": 0.1329, + "step": 5930 + }, + { + "epoch": 5.25, + "learning_rate": 1.729780389578575e-05, + "loss": 0.1591, + "step": 5931 + }, + { + "epoch": 5.25, + "learning_rate": 1.7296824052028415e-05, + "loss": 0.1549, + "step": 5932 + }, + { + "epoch": 5.25, + "learning_rate": 1.729584405841538e-05, + "loss": 0.1649, + "step": 5933 + }, + { + "epoch": 5.25, + "learning_rate": 1.7294863914966773e-05, + "loss": 0.1567, + "step": 5934 + }, + { + "epoch": 5.25, + "learning_rate": 1.729388362170272e-05, + "loss": 0.145, + "step": 5935 + }, + { + "epoch": 5.25, + "learning_rate": 1.7292903178643348e-05, + "loss": 0.1506, + "step": 5936 + }, + { + "epoch": 5.25, + "learning_rate": 1.72919225858088e-05, + "loss": 0.162, + "step": 5937 + }, + { + "epoch": 5.25, + "learning_rate": 1.7290941843219208e-05, + "loss": 0.154, + "step": 5938 + }, + { + "epoch": 5.26, + "learning_rate": 1.7289960950894724e-05, + "loss": 0.1562, + "step": 5939 + }, + { + "epoch": 5.26, + "learning_rate": 1.7288979908855482e-05, + "loss": 0.1745, + "step": 5940 + }, + { + "epoch": 5.26, + "learning_rate": 1.7287998717121636e-05, + "loss": 0.1662, + "step": 5941 + }, + { + "epoch": 5.26, + "learning_rate": 1.7287017375713335e-05, + "loss": 0.1667, + "step": 5942 + }, + { + "epoch": 5.26, + "learning_rate": 1.7286035884650733e-05, + "loss": 0.1446, + "step": 5943 + }, + { + "epoch": 5.26, + "learning_rate": 1.728505424395399e-05, + "loss": 0.1651, + "step": 5944 + }, + { + "epoch": 5.26, + "learning_rate": 1.7284072453643256e-05, + "loss": 0.1412, + "step": 5945 + }, + { + "epoch": 5.26, + "learning_rate": 1.7283090513738706e-05, + "loss": 0.163, + "step": 5946 + }, + { + "epoch": 5.26, + "learning_rate": 1.72821084242605e-05, + "loss": 0.1577, + "step": 5947 + }, + { + "epoch": 5.26, + "learning_rate": 1.728112618522881e-05, + "loss": 0.1578, + "step": 5948 + }, + { + "epoch": 5.26, + "learning_rate": 1.7280143796663806e-05, + "loss": 0.1409, + "step": 5949 + }, + { + "epoch": 5.26, + "learning_rate": 1.7279161258585666e-05, + "loss": 0.1595, + "step": 5950 + }, + { + "epoch": 5.27, + "learning_rate": 1.7278178571014566e-05, + "loss": 0.1566, + "step": 5951 + }, + { + "epoch": 5.27, + "learning_rate": 1.7277195733970685e-05, + "loss": 0.1598, + "step": 5952 + }, + { + "epoch": 5.27, + "learning_rate": 1.7276212747474218e-05, + "loss": 0.1638, + "step": 5953 + }, + { + "epoch": 5.27, + "learning_rate": 1.727522961154534e-05, + "loss": 0.154, + "step": 5954 + }, + { + "epoch": 5.27, + "learning_rate": 1.727424632620425e-05, + "loss": 0.1517, + "step": 5955 + }, + { + "epoch": 5.27, + "learning_rate": 1.727326289147114e-05, + "loss": 0.1626, + "step": 5956 + }, + { + "epoch": 5.27, + "learning_rate": 1.7272279307366203e-05, + "loss": 0.1592, + "step": 5957 + }, + { + "epoch": 5.27, + "learning_rate": 1.7271295573909645e-05, + "loss": 0.1619, + "step": 5958 + }, + { + "epoch": 5.27, + "learning_rate": 1.727031169112167e-05, + "loss": 0.1522, + "step": 5959 + }, + { + "epoch": 5.27, + "learning_rate": 1.7269327659022473e-05, + "loss": 0.1541, + "step": 5960 + }, + { + "epoch": 5.27, + "learning_rate": 1.7268343477632273e-05, + "loss": 0.1542, + "step": 5961 + }, + { + "epoch": 5.28, + "learning_rate": 1.7267359146971287e-05, + "loss": 0.1431, + "step": 5962 + }, + { + "epoch": 5.28, + "learning_rate": 1.7266374667059717e-05, + "loss": 0.1697, + "step": 5963 + }, + { + "epoch": 5.28, + "learning_rate": 1.7265390037917787e-05, + "loss": 0.1639, + "step": 5964 + }, + { + "epoch": 5.28, + "learning_rate": 1.726440525956572e-05, + "loss": 0.1824, + "step": 5965 + }, + { + "epoch": 5.28, + "learning_rate": 1.726342033202374e-05, + "loss": 0.1545, + "step": 5966 + }, + { + "epoch": 5.28, + "learning_rate": 1.7262435255312073e-05, + "loss": 0.1626, + "step": 5967 + }, + { + "epoch": 5.28, + "learning_rate": 1.726145002945095e-05, + "loss": 0.1505, + "step": 5968 + }, + { + "epoch": 5.28, + "learning_rate": 1.7260464654460606e-05, + "loss": 0.1676, + "step": 5969 + }, + { + "epoch": 5.28, + "learning_rate": 1.725947913036128e-05, + "loss": 0.1518, + "step": 5970 + }, + { + "epoch": 5.28, + "learning_rate": 1.7258493457173208e-05, + "loss": 0.1543, + "step": 5971 + }, + { + "epoch": 5.28, + "learning_rate": 1.725750763491663e-05, + "loss": 0.1624, + "step": 5972 + }, + { + "epoch": 5.29, + "learning_rate": 1.7256521663611802e-05, + "loss": 0.16, + "step": 5973 + }, + { + "epoch": 5.29, + "learning_rate": 1.7255535543278964e-05, + "loss": 0.1584, + "step": 5974 + }, + { + "epoch": 5.29, + "learning_rate": 1.725454927393837e-05, + "loss": 0.1532, + "step": 5975 + }, + { + "epoch": 5.29, + "learning_rate": 1.7253562855610274e-05, + "loss": 0.1742, + "step": 5976 + }, + { + "epoch": 5.29, + "learning_rate": 1.725257628831494e-05, + "loss": 0.153, + "step": 5977 + }, + { + "epoch": 5.29, + "learning_rate": 1.7251589572072625e-05, + "loss": 0.1538, + "step": 5978 + }, + { + "epoch": 5.29, + "learning_rate": 1.7250602706903593e-05, + "loss": 0.1453, + "step": 5979 + }, + { + "epoch": 5.29, + "learning_rate": 1.724961569282811e-05, + "loss": 0.1679, + "step": 5980 + }, + { + "epoch": 5.29, + "learning_rate": 1.7248628529866454e-05, + "loss": 0.1585, + "step": 5981 + }, + { + "epoch": 5.29, + "learning_rate": 1.7247641218038887e-05, + "loss": 0.1653, + "step": 5982 + }, + { + "epoch": 5.29, + "learning_rate": 1.7246653757365697e-05, + "loss": 0.1668, + "step": 5983 + }, + { + "epoch": 5.3, + "learning_rate": 1.724566614786716e-05, + "loss": 0.1596, + "step": 5984 + }, + { + "epoch": 5.3, + "learning_rate": 1.724467838956355e-05, + "loss": 0.1595, + "step": 5985 + }, + { + "epoch": 5.3, + "learning_rate": 1.7243690482475162e-05, + "loss": 0.1503, + "step": 5986 + }, + { + "epoch": 5.3, + "learning_rate": 1.724270242662228e-05, + "loss": 0.155, + "step": 5987 + }, + { + "epoch": 5.3, + "learning_rate": 1.72417142220252e-05, + "loss": 0.1739, + "step": 5988 + }, + { + "epoch": 5.3, + "learning_rate": 1.7240725868704218e-05, + "loss": 0.1703, + "step": 5989 + }, + { + "epoch": 5.3, + "learning_rate": 1.7239737366679626e-05, + "loss": 0.1527, + "step": 5990 + }, + { + "epoch": 5.3, + "learning_rate": 1.723874871597173e-05, + "loss": 0.1627, + "step": 5991 + }, + { + "epoch": 5.3, + "learning_rate": 1.7237759916600828e-05, + "loss": 0.1627, + "step": 5992 + }, + { + "epoch": 5.3, + "learning_rate": 1.7236770968587232e-05, + "loss": 0.1571, + "step": 5993 + }, + { + "epoch": 5.3, + "learning_rate": 1.723578187195125e-05, + "loss": 0.1538, + "step": 5994 + }, + { + "epoch": 5.3, + "learning_rate": 1.72347926267132e-05, + "loss": 0.156, + "step": 5995 + }, + { + "epoch": 5.31, + "learning_rate": 1.7233803232893392e-05, + "loss": 0.159, + "step": 5996 + }, + { + "epoch": 5.31, + "learning_rate": 1.7232813690512152e-05, + "loss": 0.1622, + "step": 5997 + }, + { + "epoch": 5.31, + "learning_rate": 1.7231823999589794e-05, + "loss": 0.1482, + "step": 5998 + }, + { + "epoch": 5.31, + "learning_rate": 1.7230834160146646e-05, + "loss": 0.1514, + "step": 5999 + }, + { + "epoch": 5.31, + "learning_rate": 1.722984417220304e-05, + "loss": 0.1588, + "step": 6000 + }, + { + "epoch": 5.31, + "learning_rate": 1.7228854035779306e-05, + "loss": 0.143, + "step": 6001 + }, + { + "epoch": 5.31, + "learning_rate": 1.722786375089578e-05, + "loss": 0.169, + "step": 6002 + }, + { + "epoch": 5.31, + "learning_rate": 1.7226873317572797e-05, + "loss": 0.1594, + "step": 6003 + }, + { + "epoch": 5.31, + "learning_rate": 1.7225882735830696e-05, + "loss": 0.1583, + "step": 6004 + }, + { + "epoch": 5.31, + "learning_rate": 1.7224892005689825e-05, + "loss": 0.1648, + "step": 6005 + }, + { + "epoch": 5.31, + "learning_rate": 1.7223901127170527e-05, + "loss": 0.1684, + "step": 6006 + }, + { + "epoch": 5.32, + "learning_rate": 1.7222910100293154e-05, + "loss": 0.1548, + "step": 6007 + }, + { + "epoch": 5.32, + "learning_rate": 1.722191892507806e-05, + "loss": 0.1477, + "step": 6008 + }, + { + "epoch": 5.32, + "learning_rate": 1.7220927601545598e-05, + "loss": 0.1573, + "step": 6009 + }, + { + "epoch": 5.32, + "learning_rate": 1.7219936129716126e-05, + "loss": 0.1724, + "step": 6010 + }, + { + "epoch": 5.32, + "learning_rate": 1.721894450961001e-05, + "loss": 0.1572, + "step": 6011 + }, + { + "epoch": 5.32, + "learning_rate": 1.7217952741247615e-05, + "loss": 0.1648, + "step": 6012 + }, + { + "epoch": 5.32, + "learning_rate": 1.7216960824649304e-05, + "loss": 0.1456, + "step": 6013 + }, + { + "epoch": 5.32, + "learning_rate": 1.7215968759835454e-05, + "loss": 0.161, + "step": 6014 + }, + { + "epoch": 5.32, + "learning_rate": 1.721497654682643e-05, + "loss": 0.1459, + "step": 6015 + }, + { + "epoch": 5.32, + "learning_rate": 1.7213984185642623e-05, + "loss": 0.1717, + "step": 6016 + }, + { + "epoch": 5.32, + "learning_rate": 1.7212991676304405e-05, + "loss": 0.156, + "step": 6017 + }, + { + "epoch": 5.33, + "learning_rate": 1.7211999018832156e-05, + "loss": 0.149, + "step": 6018 + }, + { + "epoch": 5.33, + "learning_rate": 1.7211006213246272e-05, + "loss": 0.182, + "step": 6019 + }, + { + "epoch": 5.33, + "learning_rate": 1.7210013259567133e-05, + "loss": 0.1587, + "step": 6020 + }, + { + "epoch": 5.33, + "learning_rate": 1.720902015781514e-05, + "loss": 0.1651, + "step": 6021 + }, + { + "epoch": 5.33, + "learning_rate": 1.7208026908010676e-05, + "loss": 0.1522, + "step": 6022 + }, + { + "epoch": 5.33, + "learning_rate": 1.720703351017415e-05, + "loss": 0.1566, + "step": 6023 + }, + { + "epoch": 5.33, + "learning_rate": 1.720603996432596e-05, + "loss": 0.1503, + "step": 6024 + }, + { + "epoch": 5.33, + "learning_rate": 1.7205046270486515e-05, + "loss": 0.1547, + "step": 6025 + }, + { + "epoch": 5.33, + "learning_rate": 1.7204052428676218e-05, + "loss": 0.1455, + "step": 6026 + }, + { + "epoch": 5.33, + "learning_rate": 1.7203058438915475e-05, + "loss": 0.164, + "step": 6027 + }, + { + "epoch": 5.33, + "learning_rate": 1.7202064301224714e-05, + "loss": 0.1666, + "step": 6028 + }, + { + "epoch": 5.33, + "learning_rate": 1.7201070015624338e-05, + "loss": 0.1488, + "step": 6029 + }, + { + "epoch": 5.34, + "learning_rate": 1.720007558213477e-05, + "loss": 0.1535, + "step": 6030 + }, + { + "epoch": 5.34, + "learning_rate": 1.7199081000776435e-05, + "loss": 0.158, + "step": 6031 + }, + { + "epoch": 5.34, + "learning_rate": 1.7198086271569763e-05, + "loss": 0.1542, + "step": 6032 + }, + { + "epoch": 5.34, + "learning_rate": 1.7197091394535174e-05, + "loss": 0.1683, + "step": 6033 + }, + { + "epoch": 5.34, + "learning_rate": 1.7196096369693102e-05, + "loss": 0.161, + "step": 6034 + }, + { + "epoch": 5.34, + "learning_rate": 1.7195101197063987e-05, + "loss": 0.156, + "step": 6035 + }, + { + "epoch": 5.34, + "learning_rate": 1.7194105876668264e-05, + "loss": 0.1512, + "step": 6036 + }, + { + "epoch": 5.34, + "learning_rate": 1.7193110408526373e-05, + "loss": 0.1594, + "step": 6037 + }, + { + "epoch": 5.34, + "learning_rate": 1.719211479265876e-05, + "loss": 0.1527, + "step": 6038 + }, + { + "epoch": 5.34, + "learning_rate": 1.719111902908587e-05, + "loss": 0.1509, + "step": 6039 + }, + { + "epoch": 5.34, + "learning_rate": 1.7190123117828154e-05, + "loss": 0.1619, + "step": 6040 + }, + { + "epoch": 5.35, + "learning_rate": 1.7189127058906064e-05, + "loss": 0.1723, + "step": 6041 + }, + { + "epoch": 5.35, + "learning_rate": 1.718813085234006e-05, + "loss": 0.1608, + "step": 6042 + }, + { + "epoch": 5.35, + "learning_rate": 1.71871344981506e-05, + "loss": 0.1471, + "step": 6043 + }, + { + "epoch": 5.35, + "learning_rate": 1.718613799635814e-05, + "loss": 0.1736, + "step": 6044 + }, + { + "epoch": 5.35, + "learning_rate": 1.7185141346983155e-05, + "loss": 0.1401, + "step": 6045 + }, + { + "epoch": 5.35, + "learning_rate": 1.7184144550046107e-05, + "loss": 0.166, + "step": 6046 + }, + { + "epoch": 5.35, + "learning_rate": 1.718314760556747e-05, + "loss": 0.1618, + "step": 6047 + }, + { + "epoch": 5.35, + "learning_rate": 1.7182150513567714e-05, + "loss": 0.1628, + "step": 6048 + }, + { + "epoch": 5.35, + "learning_rate": 1.718115327406732e-05, + "loss": 0.1555, + "step": 6049 + }, + { + "epoch": 5.35, + "learning_rate": 1.7180155887086773e-05, + "loss": 0.1608, + "step": 6050 + }, + { + "epoch": 5.35, + "learning_rate": 1.7179158352646546e-05, + "loss": 0.1736, + "step": 6051 + }, + { + "epoch": 5.36, + "learning_rate": 1.717816067076713e-05, + "loss": 0.1603, + "step": 6052 + }, + { + "epoch": 5.36, + "learning_rate": 1.717716284146902e-05, + "loss": 0.169, + "step": 6053 + }, + { + "epoch": 5.36, + "learning_rate": 1.7176164864772702e-05, + "loss": 0.1562, + "step": 6054 + }, + { + "epoch": 5.36, + "learning_rate": 1.7175166740698676e-05, + "loss": 0.1478, + "step": 6055 + }, + { + "epoch": 5.36, + "learning_rate": 1.7174168469267435e-05, + "loss": 0.1579, + "step": 6056 + }, + { + "epoch": 5.36, + "learning_rate": 1.7173170050499482e-05, + "loss": 0.1399, + "step": 6057 + }, + { + "epoch": 5.36, + "learning_rate": 1.717217148441533e-05, + "loss": 0.1577, + "step": 6058 + }, + { + "epoch": 5.36, + "learning_rate": 1.7171172771035473e-05, + "loss": 0.1604, + "step": 6059 + }, + { + "epoch": 5.36, + "learning_rate": 1.7170173910380434e-05, + "loss": 0.1473, + "step": 6060 + }, + { + "epoch": 5.36, + "learning_rate": 1.7169174902470715e-05, + "loss": 0.1755, + "step": 6061 + }, + { + "epoch": 5.36, + "learning_rate": 1.7168175747326847e-05, + "loss": 0.1467, + "step": 6062 + }, + { + "epoch": 5.36, + "learning_rate": 1.7167176444969336e-05, + "loss": 0.1741, + "step": 6063 + }, + { + "epoch": 5.37, + "learning_rate": 1.7166176995418713e-05, + "loss": 0.1503, + "step": 6064 + }, + { + "epoch": 5.37, + "learning_rate": 1.71651773986955e-05, + "loss": 0.164, + "step": 6065 + }, + { + "epoch": 5.37, + "learning_rate": 1.716417765482023e-05, + "loss": 0.1476, + "step": 6066 + }, + { + "epoch": 5.37, + "learning_rate": 1.716317776381343e-05, + "loss": 0.1533, + "step": 6067 + }, + { + "epoch": 5.37, + "learning_rate": 1.716217772569564e-05, + "loss": 0.1552, + "step": 6068 + }, + { + "epoch": 5.37, + "learning_rate": 1.716117754048739e-05, + "loss": 0.1694, + "step": 6069 + }, + { + "epoch": 5.37, + "learning_rate": 1.716017720820923e-05, + "loss": 0.1632, + "step": 6070 + }, + { + "epoch": 5.37, + "learning_rate": 1.7159176728881698e-05, + "loss": 0.1475, + "step": 6071 + }, + { + "epoch": 5.37, + "learning_rate": 1.7158176102525344e-05, + "loss": 0.1608, + "step": 6072 + }, + { + "epoch": 5.37, + "learning_rate": 1.7157175329160717e-05, + "loss": 0.1672, + "step": 6073 + }, + { + "epoch": 5.37, + "learning_rate": 1.715617440880837e-05, + "loss": 0.167, + "step": 6074 + }, + { + "epoch": 5.38, + "learning_rate": 1.715517334148886e-05, + "loss": 0.166, + "step": 6075 + }, + { + "epoch": 5.38, + "learning_rate": 1.7154172127222742e-05, + "loss": 0.1562, + "step": 6076 + }, + { + "epoch": 5.38, + "learning_rate": 1.715317076603058e-05, + "loss": 0.1432, + "step": 6077 + }, + { + "epoch": 5.38, + "learning_rate": 1.7152169257932944e-05, + "loss": 0.1691, + "step": 6078 + }, + { + "epoch": 5.38, + "learning_rate": 1.7151167602950394e-05, + "loss": 0.1556, + "step": 6079 + }, + { + "epoch": 5.38, + "learning_rate": 1.7150165801103505e-05, + "loss": 0.1574, + "step": 6080 + }, + { + "epoch": 5.38, + "learning_rate": 1.7149163852412857e-05, + "loss": 0.1528, + "step": 6081 + }, + { + "epoch": 5.38, + "learning_rate": 1.7148161756899012e-05, + "loss": 0.1586, + "step": 6082 + }, + { + "epoch": 5.38, + "learning_rate": 1.7147159514582567e-05, + "loss": 0.1572, + "step": 6083 + }, + { + "epoch": 5.38, + "learning_rate": 1.7146157125484097e-05, + "loss": 0.1677, + "step": 6084 + }, + { + "epoch": 5.38, + "learning_rate": 1.714515458962419e-05, + "loss": 0.1672, + "step": 6085 + }, + { + "epoch": 5.39, + "learning_rate": 1.7144151907023426e-05, + "loss": 0.1644, + "step": 6086 + }, + { + "epoch": 5.39, + "learning_rate": 1.714314907770241e-05, + "loss": 0.1524, + "step": 6087 + }, + { + "epoch": 5.39, + "learning_rate": 1.7142146101681737e-05, + "loss": 0.1629, + "step": 6088 + }, + { + "epoch": 5.39, + "learning_rate": 1.7141142978981994e-05, + "loss": 0.1636, + "step": 6089 + }, + { + "epoch": 5.39, + "learning_rate": 1.7140139709623795e-05, + "loss": 0.1458, + "step": 6090 + }, + { + "epoch": 5.39, + "learning_rate": 1.7139136293627734e-05, + "loss": 0.1614, + "step": 6091 + }, + { + "epoch": 5.39, + "learning_rate": 1.7138132731014426e-05, + "loss": 0.1542, + "step": 6092 + }, + { + "epoch": 5.39, + "learning_rate": 1.7137129021804476e-05, + "loss": 0.1589, + "step": 6093 + }, + { + "epoch": 5.39, + "learning_rate": 1.7136125166018497e-05, + "loss": 0.1657, + "step": 6094 + }, + { + "epoch": 5.39, + "learning_rate": 1.7135121163677108e-05, + "loss": 0.1578, + "step": 6095 + }, + { + "epoch": 5.39, + "learning_rate": 1.7134117014800927e-05, + "loss": 0.1563, + "step": 6096 + }, + { + "epoch": 5.4, + "learning_rate": 1.713311271941058e-05, + "loss": 0.1522, + "step": 6097 + }, + { + "epoch": 5.4, + "learning_rate": 1.713210827752669e-05, + "loss": 0.1525, + "step": 6098 + }, + { + "epoch": 5.4, + "learning_rate": 1.713110368916988e-05, + "loss": 0.1508, + "step": 6099 + }, + { + "epoch": 5.4, + "learning_rate": 1.713009895436079e-05, + "loss": 0.1414, + "step": 6100 + }, + { + "epoch": 5.4, + "learning_rate": 1.712909407312005e-05, + "loss": 0.1546, + "step": 6101 + }, + { + "epoch": 5.4, + "learning_rate": 1.7128089045468294e-05, + "loss": 0.1551, + "step": 6102 + }, + { + "epoch": 5.4, + "learning_rate": 1.712708387142617e-05, + "loss": 0.1583, + "step": 6103 + }, + { + "epoch": 5.4, + "learning_rate": 1.7126078551014314e-05, + "loss": 0.1598, + "step": 6104 + }, + { + "epoch": 5.4, + "learning_rate": 1.7125073084253377e-05, + "loss": 0.1537, + "step": 6105 + }, + { + "epoch": 5.4, + "learning_rate": 1.712406747116401e-05, + "loss": 0.1504, + "step": 6106 + }, + { + "epoch": 5.4, + "learning_rate": 1.7123061711766863e-05, + "loss": 0.1661, + "step": 6107 + }, + { + "epoch": 5.4, + "learning_rate": 1.7122055806082584e-05, + "loss": 0.1684, + "step": 6108 + }, + { + "epoch": 5.41, + "learning_rate": 1.7121049754131846e-05, + "loss": 0.161, + "step": 6109 + }, + { + "epoch": 5.41, + "learning_rate": 1.71200435559353e-05, + "loss": 0.1471, + "step": 6110 + }, + { + "epoch": 5.41, + "learning_rate": 1.7119037211513615e-05, + "loss": 0.1507, + "step": 6111 + }, + { + "epoch": 5.41, + "learning_rate": 1.711803072088745e-05, + "loss": 0.1628, + "step": 6112 + }, + { + "epoch": 5.41, + "learning_rate": 1.7117024084077488e-05, + "loss": 0.1567, + "step": 6113 + }, + { + "epoch": 5.41, + "learning_rate": 1.7116017301104397e-05, + "loss": 0.149, + "step": 6114 + }, + { + "epoch": 5.41, + "learning_rate": 1.711501037198885e-05, + "loss": 0.1714, + "step": 6115 + }, + { + "epoch": 5.41, + "learning_rate": 1.711400329675153e-05, + "loss": 0.1585, + "step": 6116 + }, + { + "epoch": 5.41, + "learning_rate": 1.7112996075413118e-05, + "loss": 0.1611, + "step": 6117 + }, + { + "epoch": 5.41, + "learning_rate": 1.7111988707994304e-05, + "loss": 0.1575, + "step": 6118 + }, + { + "epoch": 5.41, + "learning_rate": 1.7110981194515767e-05, + "loss": 0.1602, + "step": 6119 + }, + { + "epoch": 5.42, + "learning_rate": 1.7109973534998207e-05, + "loss": 0.1516, + "step": 6120 + }, + { + "epoch": 5.42, + "learning_rate": 1.7108965729462314e-05, + "loss": 0.1575, + "step": 6121 + }, + { + "epoch": 5.42, + "learning_rate": 1.7107957777928786e-05, + "loss": 0.1495, + "step": 6122 + }, + { + "epoch": 5.42, + "learning_rate": 1.710694968041833e-05, + "loss": 0.1483, + "step": 6123 + }, + { + "epoch": 5.42, + "learning_rate": 1.710594143695164e-05, + "loss": 0.1582, + "step": 6124 + }, + { + "epoch": 5.42, + "learning_rate": 1.7104933047549424e-05, + "loss": 0.1535, + "step": 6125 + }, + { + "epoch": 5.42, + "learning_rate": 1.7103924512232393e-05, + "loss": 0.1596, + "step": 6126 + }, + { + "epoch": 5.42, + "learning_rate": 1.7102915831021266e-05, + "loss": 0.1486, + "step": 6127 + }, + { + "epoch": 5.42, + "learning_rate": 1.7101907003936747e-05, + "loss": 0.1589, + "step": 6128 + }, + { + "epoch": 5.42, + "learning_rate": 1.710089803099956e-05, + "loss": 0.1563, + "step": 6129 + }, + { + "epoch": 5.42, + "learning_rate": 1.7099888912230428e-05, + "loss": 0.1697, + "step": 6130 + }, + { + "epoch": 5.43, + "learning_rate": 1.7098879647650068e-05, + "loss": 0.1599, + "step": 6131 + }, + { + "epoch": 5.43, + "learning_rate": 1.709787023727922e-05, + "loss": 0.1413, + "step": 6132 + }, + { + "epoch": 5.43, + "learning_rate": 1.7096860681138603e-05, + "loss": 0.1581, + "step": 6133 + }, + { + "epoch": 5.43, + "learning_rate": 1.7095850979248956e-05, + "loss": 0.1512, + "step": 6134 + }, + { + "epoch": 5.43, + "learning_rate": 1.7094841131631014e-05, + "loss": 0.1414, + "step": 6135 + }, + { + "epoch": 5.43, + "learning_rate": 1.7093831138305515e-05, + "loss": 0.1564, + "step": 6136 + }, + { + "epoch": 5.43, + "learning_rate": 1.7092820999293206e-05, + "loss": 0.1591, + "step": 6137 + }, + { + "epoch": 5.43, + "learning_rate": 1.709181071461482e-05, + "loss": 0.1633, + "step": 6138 + }, + { + "epoch": 5.43, + "learning_rate": 1.7090800284291124e-05, + "loss": 0.1511, + "step": 6139 + }, + { + "epoch": 5.43, + "learning_rate": 1.7089789708342856e-05, + "loss": 0.1472, + "step": 6140 + }, + { + "epoch": 5.43, + "learning_rate": 1.7088778986790773e-05, + "loss": 0.1706, + "step": 6141 + }, + { + "epoch": 5.43, + "learning_rate": 1.7087768119655637e-05, + "loss": 0.1531, + "step": 6142 + }, + { + "epoch": 5.44, + "learning_rate": 1.70867571069582e-05, + "loss": 0.1657, + "step": 6143 + }, + { + "epoch": 5.44, + "learning_rate": 1.708574594871923e-05, + "loss": 0.1684, + "step": 6144 + }, + { + "epoch": 5.44, + "learning_rate": 1.7084734644959494e-05, + "loss": 0.155, + "step": 6145 + }, + { + "epoch": 5.44, + "learning_rate": 1.7083723195699763e-05, + "loss": 0.145, + "step": 6146 + }, + { + "epoch": 5.44, + "learning_rate": 1.7082711600960804e-05, + "loss": 0.1517, + "step": 6147 + }, + { + "epoch": 5.44, + "learning_rate": 1.7081699860763395e-05, + "loss": 0.1588, + "step": 6148 + }, + { + "epoch": 5.44, + "learning_rate": 1.7080687975128315e-05, + "loss": 0.1627, + "step": 6149 + }, + { + "epoch": 5.44, + "learning_rate": 1.7079675944076343e-05, + "loss": 0.1647, + "step": 6150 + }, + { + "epoch": 5.44, + "learning_rate": 1.7078663767628266e-05, + "loss": 0.156, + "step": 6151 + }, + { + "epoch": 5.44, + "learning_rate": 1.7077651445804865e-05, + "loss": 0.1631, + "step": 6152 + }, + { + "epoch": 5.44, + "learning_rate": 1.707663897862694e-05, + "loss": 0.173, + "step": 6153 + }, + { + "epoch": 5.45, + "learning_rate": 1.7075626366115278e-05, + "loss": 0.1461, + "step": 6154 + }, + { + "epoch": 5.45, + "learning_rate": 1.7074613608290676e-05, + "loss": 0.1508, + "step": 6155 + }, + { + "epoch": 5.45, + "learning_rate": 1.707360070517393e-05, + "loss": 0.1687, + "step": 6156 + }, + { + "epoch": 5.45, + "learning_rate": 1.7072587656785848e-05, + "loss": 0.169, + "step": 6157 + }, + { + "epoch": 5.45, + "learning_rate": 1.707157446314723e-05, + "loss": 0.1606, + "step": 6158 + }, + { + "epoch": 5.45, + "learning_rate": 1.7070561124278892e-05, + "loss": 0.1555, + "step": 6159 + }, + { + "epoch": 5.45, + "learning_rate": 1.7069547640201635e-05, + "loss": 0.1609, + "step": 6160 + }, + { + "epoch": 5.45, + "learning_rate": 1.706853401093628e-05, + "loss": 0.1556, + "step": 6161 + }, + { + "epoch": 5.45, + "learning_rate": 1.7067520236503637e-05, + "loss": 0.1665, + "step": 6162 + }, + { + "epoch": 5.45, + "learning_rate": 1.7066506316924533e-05, + "loss": 0.1533, + "step": 6163 + }, + { + "epoch": 5.45, + "learning_rate": 1.7065492252219794e-05, + "loss": 0.1534, + "step": 6164 + }, + { + "epoch": 5.46, + "learning_rate": 1.7064478042410234e-05, + "loss": 0.1582, + "step": 6165 + }, + { + "epoch": 5.46, + "learning_rate": 1.706346368751669e-05, + "loss": 0.1681, + "step": 6166 + }, + { + "epoch": 5.46, + "learning_rate": 1.706244918755999e-05, + "loss": 0.1649, + "step": 6167 + }, + { + "epoch": 5.46, + "learning_rate": 1.7061434542560976e-05, + "loss": 0.1472, + "step": 6168 + }, + { + "epoch": 5.46, + "learning_rate": 1.7060419752540478e-05, + "loss": 0.157, + "step": 6169 + }, + { + "epoch": 5.46, + "learning_rate": 1.705940481751934e-05, + "loss": 0.1547, + "step": 6170 + }, + { + "epoch": 5.46, + "learning_rate": 1.705838973751841e-05, + "loss": 0.155, + "step": 6171 + }, + { + "epoch": 5.46, + "learning_rate": 1.7057374512558524e-05, + "loss": 0.1511, + "step": 6172 + }, + { + "epoch": 5.46, + "learning_rate": 1.7056359142660544e-05, + "loss": 0.1594, + "step": 6173 + }, + { + "epoch": 5.46, + "learning_rate": 1.7055343627845317e-05, + "loss": 0.1475, + "step": 6174 + }, + { + "epoch": 5.46, + "learning_rate": 1.7054327968133696e-05, + "loss": 0.167, + "step": 6175 + }, + { + "epoch": 5.46, + "learning_rate": 1.7053312163546542e-05, + "loss": 0.155, + "step": 6176 + }, + { + "epoch": 5.47, + "learning_rate": 1.705229621410472e-05, + "loss": 0.1533, + "step": 6177 + }, + { + "epoch": 5.47, + "learning_rate": 1.7051280119829093e-05, + "loss": 0.1721, + "step": 6178 + }, + { + "epoch": 5.47, + "learning_rate": 1.7050263880740522e-05, + "loss": 0.1563, + "step": 6179 + }, + { + "epoch": 5.47, + "learning_rate": 1.704924749685989e-05, + "loss": 0.1666, + "step": 6180 + }, + { + "epoch": 5.47, + "learning_rate": 1.704823096820806e-05, + "loss": 0.1655, + "step": 6181 + }, + { + "epoch": 5.47, + "learning_rate": 1.7047214294805914e-05, + "loss": 0.1655, + "step": 6182 + }, + { + "epoch": 5.47, + "learning_rate": 1.704619747667433e-05, + "loss": 0.1608, + "step": 6183 + }, + { + "epoch": 5.47, + "learning_rate": 1.7045180513834187e-05, + "loss": 0.1627, + "step": 6184 + }, + { + "epoch": 5.47, + "learning_rate": 1.7044163406306378e-05, + "loss": 0.1579, + "step": 6185 + }, + { + "epoch": 5.47, + "learning_rate": 1.704314615411179e-05, + "loss": 0.1505, + "step": 6186 + }, + { + "epoch": 5.47, + "learning_rate": 1.7042128757271305e-05, + "loss": 0.1601, + "step": 6187 + }, + { + "epoch": 5.48, + "learning_rate": 1.7041111215805826e-05, + "loss": 0.148, + "step": 6188 + }, + { + "epoch": 5.48, + "learning_rate": 1.7040093529736252e-05, + "loss": 0.173, + "step": 6189 + }, + { + "epoch": 5.48, + "learning_rate": 1.7039075699083477e-05, + "loss": 0.1459, + "step": 6190 + }, + { + "epoch": 5.48, + "learning_rate": 1.7038057723868408e-05, + "loss": 0.1534, + "step": 6191 + }, + { + "epoch": 5.48, + "learning_rate": 1.703703960411195e-05, + "loss": 0.165, + "step": 6192 + }, + { + "epoch": 5.48, + "learning_rate": 1.7036021339835014e-05, + "loss": 0.1637, + "step": 6193 + }, + { + "epoch": 5.48, + "learning_rate": 1.703500293105851e-05, + "loss": 0.1436, + "step": 6194 + }, + { + "epoch": 5.48, + "learning_rate": 1.7033984377803355e-05, + "loss": 0.1639, + "step": 6195 + }, + { + "epoch": 5.48, + "learning_rate": 1.7032965680090467e-05, + "loss": 0.1728, + "step": 6196 + }, + { + "epoch": 5.48, + "learning_rate": 1.7031946837940768e-05, + "loss": 0.1589, + "step": 6197 + }, + { + "epoch": 5.48, + "learning_rate": 1.7030927851375177e-05, + "loss": 0.1625, + "step": 6198 + }, + { + "epoch": 5.49, + "learning_rate": 1.7029908720414627e-05, + "loss": 0.145, + "step": 6199 + }, + { + "epoch": 5.49, + "learning_rate": 1.702888944508004e-05, + "loss": 0.1606, + "step": 6200 + }, + { + "epoch": 5.49, + "learning_rate": 1.702787002539236e-05, + "loss": 0.1526, + "step": 6201 + }, + { + "epoch": 5.49, + "learning_rate": 1.702685046137252e-05, + "loss": 0.1676, + "step": 6202 + }, + { + "epoch": 5.49, + "learning_rate": 1.702583075304145e-05, + "loss": 0.1525, + "step": 6203 + }, + { + "epoch": 5.49, + "learning_rate": 1.70248109004201e-05, + "loss": 0.1508, + "step": 6204 + }, + { + "epoch": 5.49, + "learning_rate": 1.7023790903529412e-05, + "loss": 0.1577, + "step": 6205 + }, + { + "epoch": 5.49, + "learning_rate": 1.7022770762390334e-05, + "loss": 0.1577, + "step": 6206 + }, + { + "epoch": 5.49, + "learning_rate": 1.7021750477023823e-05, + "loss": 0.1489, + "step": 6207 + }, + { + "epoch": 5.49, + "learning_rate": 1.7020730047450823e-05, + "loss": 0.1697, + "step": 6208 + }, + { + "epoch": 5.49, + "learning_rate": 1.7019709473692297e-05, + "loss": 0.1461, + "step": 6209 + }, + { + "epoch": 5.49, + "learning_rate": 1.70186887557692e-05, + "loss": 0.1642, + "step": 6210 + }, + { + "epoch": 5.5, + "learning_rate": 1.70176678937025e-05, + "loss": 0.1596, + "step": 6211 + }, + { + "epoch": 5.5, + "learning_rate": 1.7016646887513158e-05, + "loss": 0.159, + "step": 6212 + }, + { + "epoch": 5.5, + "learning_rate": 1.7015625737222144e-05, + "loss": 0.1626, + "step": 6213 + }, + { + "epoch": 5.5, + "learning_rate": 1.701460444285043e-05, + "loss": 0.1691, + "step": 6214 + }, + { + "epoch": 5.5, + "learning_rate": 1.7013583004418994e-05, + "loss": 0.1483, + "step": 6215 + }, + { + "epoch": 5.5, + "learning_rate": 1.7012561421948806e-05, + "loss": 0.1673, + "step": 6216 + }, + { + "epoch": 5.5, + "learning_rate": 1.701153969546085e-05, + "loss": 0.1737, + "step": 6217 + }, + { + "epoch": 5.5, + "learning_rate": 1.701051782497611e-05, + "loss": 0.1466, + "step": 6218 + }, + { + "epoch": 5.5, + "learning_rate": 1.700949581051557e-05, + "loss": 0.1641, + "step": 6219 + }, + { + "epoch": 5.5, + "learning_rate": 1.7008473652100225e-05, + "loss": 0.1584, + "step": 6220 + }, + { + "epoch": 5.5, + "learning_rate": 1.700745134975106e-05, + "loss": 0.1664, + "step": 6221 + }, + { + "epoch": 5.51, + "learning_rate": 1.7006428903489072e-05, + "loss": 0.1609, + "step": 6222 + }, + { + "epoch": 5.51, + "learning_rate": 1.7005406313335263e-05, + "loss": 0.1527, + "step": 6223 + }, + { + "epoch": 5.51, + "learning_rate": 1.700438357931063e-05, + "loss": 0.1689, + "step": 6224 + }, + { + "epoch": 5.51, + "learning_rate": 1.7003360701436174e-05, + "loss": 0.1612, + "step": 6225 + }, + { + "epoch": 5.51, + "learning_rate": 1.700233767973291e-05, + "loss": 0.163, + "step": 6226 + }, + { + "epoch": 5.51, + "learning_rate": 1.7001314514221845e-05, + "loss": 0.1561, + "step": 6227 + }, + { + "epoch": 5.51, + "learning_rate": 1.700029120492399e-05, + "loss": 0.1586, + "step": 6228 + }, + { + "epoch": 5.51, + "learning_rate": 1.6999267751860364e-05, + "loss": 0.1608, + "step": 6229 + }, + { + "epoch": 5.51, + "learning_rate": 1.6998244155051983e-05, + "loss": 0.1694, + "step": 6230 + }, + { + "epoch": 5.51, + "learning_rate": 1.6997220414519864e-05, + "loss": 0.1752, + "step": 6231 + }, + { + "epoch": 5.51, + "learning_rate": 1.6996196530285042e-05, + "loss": 0.1528, + "step": 6232 + }, + { + "epoch": 5.52, + "learning_rate": 1.699517250236854e-05, + "loss": 0.1452, + "step": 6233 + }, + { + "epoch": 5.52, + "learning_rate": 1.6994148330791386e-05, + "loss": 0.1499, + "step": 6234 + }, + { + "epoch": 5.52, + "learning_rate": 1.6993124015574616e-05, + "loss": 0.1555, + "step": 6235 + }, + { + "epoch": 5.52, + "learning_rate": 1.6992099556739266e-05, + "loss": 0.1556, + "step": 6236 + }, + { + "epoch": 5.52, + "learning_rate": 1.6991074954306376e-05, + "loss": 0.1674, + "step": 6237 + }, + { + "epoch": 5.52, + "learning_rate": 1.6990050208296988e-05, + "loss": 0.1595, + "step": 6238 + }, + { + "epoch": 5.52, + "learning_rate": 1.6989025318732147e-05, + "loss": 0.1433, + "step": 6239 + }, + { + "epoch": 5.52, + "learning_rate": 1.69880002856329e-05, + "loss": 0.1509, + "step": 6240 + }, + { + "epoch": 5.52, + "learning_rate": 1.6986975109020303e-05, + "loss": 0.1575, + "step": 6241 + }, + { + "epoch": 5.52, + "learning_rate": 1.6985949788915408e-05, + "loss": 0.1566, + "step": 6242 + }, + { + "epoch": 5.52, + "learning_rate": 1.6984924325339266e-05, + "loss": 0.1672, + "step": 6243 + }, + { + "epoch": 5.53, + "learning_rate": 1.6983898718312945e-05, + "loss": 0.1556, + "step": 6244 + }, + { + "epoch": 5.53, + "learning_rate": 1.6982872967857504e-05, + "loss": 0.1505, + "step": 6245 + }, + { + "epoch": 5.53, + "learning_rate": 1.6981847073994012e-05, + "loss": 0.1603, + "step": 6246 + }, + { + "epoch": 5.53, + "learning_rate": 1.6980821036743536e-05, + "loss": 0.1732, + "step": 6247 + }, + { + "epoch": 5.53, + "learning_rate": 1.6979794856127147e-05, + "loss": 0.1538, + "step": 6248 + }, + { + "epoch": 5.53, + "learning_rate": 1.697876853216592e-05, + "loss": 0.1602, + "step": 6249 + }, + { + "epoch": 5.53, + "learning_rate": 1.6977742064880935e-05, + "loss": 0.1476, + "step": 6250 + }, + { + "epoch": 5.53, + "learning_rate": 1.6976715454293267e-05, + "loss": 0.1625, + "step": 6251 + }, + { + "epoch": 5.53, + "learning_rate": 1.697568870042401e-05, + "loss": 0.1572, + "step": 6252 + }, + { + "epoch": 5.53, + "learning_rate": 1.697466180329424e-05, + "loss": 0.1665, + "step": 6253 + }, + { + "epoch": 5.53, + "learning_rate": 1.697363476292505e-05, + "loss": 0.161, + "step": 6254 + }, + { + "epoch": 5.53, + "learning_rate": 1.6972607579337535e-05, + "loss": 0.1549, + "step": 6255 + }, + { + "epoch": 5.54, + "learning_rate": 1.6971580252552794e-05, + "loss": 0.1547, + "step": 6256 + }, + { + "epoch": 5.54, + "learning_rate": 1.6970552782591912e-05, + "loss": 0.1668, + "step": 6257 + }, + { + "epoch": 5.54, + "learning_rate": 1.6969525169476e-05, + "loss": 0.1668, + "step": 6258 + }, + { + "epoch": 5.54, + "learning_rate": 1.6968497413226162e-05, + "loss": 0.1757, + "step": 6259 + }, + { + "epoch": 5.54, + "learning_rate": 1.69674695138635e-05, + "loss": 0.1446, + "step": 6260 + }, + { + "epoch": 5.54, + "learning_rate": 1.696644147140913e-05, + "loss": 0.1574, + "step": 6261 + }, + { + "epoch": 5.54, + "learning_rate": 1.696541328588416e-05, + "loss": 0.1606, + "step": 6262 + }, + { + "epoch": 5.54, + "learning_rate": 1.696438495730971e-05, + "loss": 0.1616, + "step": 6263 + }, + { + "epoch": 5.54, + "learning_rate": 1.69633564857069e-05, + "loss": 0.1575, + "step": 6264 + }, + { + "epoch": 5.54, + "learning_rate": 1.6962327871096847e-05, + "loss": 0.1565, + "step": 6265 + }, + { + "epoch": 5.54, + "learning_rate": 1.696129911350068e-05, + "loss": 0.1453, + "step": 6266 + }, + { + "epoch": 5.55, + "learning_rate": 1.6960270212939525e-05, + "loss": 0.1591, + "step": 6267 + }, + { + "epoch": 5.55, + "learning_rate": 1.6959241169434512e-05, + "loss": 0.158, + "step": 6268 + }, + { + "epoch": 5.55, + "learning_rate": 1.6958211983006773e-05, + "loss": 0.1592, + "step": 6269 + }, + { + "epoch": 5.55, + "learning_rate": 1.6957182653677445e-05, + "loss": 0.155, + "step": 6270 + }, + { + "epoch": 5.55, + "learning_rate": 1.6956153181467675e-05, + "loss": 0.152, + "step": 6271 + }, + { + "epoch": 5.55, + "learning_rate": 1.6955123566398595e-05, + "loss": 0.1774, + "step": 6272 + }, + { + "epoch": 5.55, + "learning_rate": 1.6954093808491357e-05, + "loss": 0.1774, + "step": 6273 + }, + { + "epoch": 5.55, + "learning_rate": 1.6953063907767108e-05, + "loss": 0.1681, + "step": 6274 + }, + { + "epoch": 5.55, + "learning_rate": 1.6952033864246994e-05, + "loss": 0.1577, + "step": 6275 + }, + { + "epoch": 5.55, + "learning_rate": 1.6951003677952173e-05, + "loss": 0.1757, + "step": 6276 + }, + { + "epoch": 5.55, + "learning_rate": 1.6949973348903806e-05, + "loss": 0.1611, + "step": 6277 + }, + { + "epoch": 5.56, + "learning_rate": 1.694894287712305e-05, + "loss": 0.1773, + "step": 6278 + }, + { + "epoch": 5.56, + "learning_rate": 1.6947912262631063e-05, + "loss": 0.176, + "step": 6279 + }, + { + "epoch": 5.56, + "learning_rate": 1.694688150544902e-05, + "loss": 0.1624, + "step": 6280 + }, + { + "epoch": 5.56, + "learning_rate": 1.694585060559808e-05, + "loss": 0.1592, + "step": 6281 + }, + { + "epoch": 5.56, + "learning_rate": 1.6944819563099422e-05, + "loss": 0.1666, + "step": 6282 + }, + { + "epoch": 5.56, + "learning_rate": 1.6943788377974215e-05, + "loss": 0.1583, + "step": 6283 + }, + { + "epoch": 5.56, + "learning_rate": 1.6942757050243642e-05, + "loss": 0.1618, + "step": 6284 + }, + { + "epoch": 5.56, + "learning_rate": 1.6941725579928882e-05, + "loss": 0.1389, + "step": 6285 + }, + { + "epoch": 5.56, + "learning_rate": 1.694069396705112e-05, + "loss": 0.1631, + "step": 6286 + }, + { + "epoch": 5.56, + "learning_rate": 1.6939662211631537e-05, + "loss": 0.1423, + "step": 6287 + }, + { + "epoch": 5.56, + "learning_rate": 1.6938630313691323e-05, + "loss": 0.159, + "step": 6288 + }, + { + "epoch": 5.56, + "learning_rate": 1.6937598273251677e-05, + "loss": 0.1537, + "step": 6289 + }, + { + "epoch": 5.57, + "learning_rate": 1.6936566090333787e-05, + "loss": 0.1564, + "step": 6290 + }, + { + "epoch": 5.57, + "learning_rate": 1.6935533764958854e-05, + "loss": 0.163, + "step": 6291 + }, + { + "epoch": 5.57, + "learning_rate": 1.6934501297148077e-05, + "loss": 0.1669, + "step": 6292 + }, + { + "epoch": 5.57, + "learning_rate": 1.693346868692267e-05, + "loss": 0.1477, + "step": 6293 + }, + { + "epoch": 5.57, + "learning_rate": 1.6932435934303822e-05, + "loss": 0.1441, + "step": 6294 + }, + { + "epoch": 5.57, + "learning_rate": 1.6931403039312754e-05, + "loss": 0.1483, + "step": 6295 + }, + { + "epoch": 5.57, + "learning_rate": 1.693037000197068e-05, + "loss": 0.1485, + "step": 6296 + }, + { + "epoch": 5.57, + "learning_rate": 1.692933682229881e-05, + "loss": 0.1563, + "step": 6297 + }, + { + "epoch": 5.57, + "learning_rate": 1.6928303500318367e-05, + "loss": 0.1581, + "step": 6298 + }, + { + "epoch": 5.57, + "learning_rate": 1.692727003605057e-05, + "loss": 0.1607, + "step": 6299 + }, + { + "epoch": 5.57, + "learning_rate": 1.6926236429516644e-05, + "loss": 0.1641, + "step": 6300 + }, + { + "epoch": 5.58, + "learning_rate": 1.6925202680737812e-05, + "loss": 0.1475, + "step": 6301 + }, + { + "epoch": 5.58, + "learning_rate": 1.692416878973531e-05, + "loss": 0.1569, + "step": 6302 + }, + { + "epoch": 5.58, + "learning_rate": 1.692313475653037e-05, + "loss": 0.1591, + "step": 6303 + }, + { + "epoch": 5.58, + "learning_rate": 1.6922100581144228e-05, + "loss": 0.1544, + "step": 6304 + }, + { + "epoch": 5.58, + "learning_rate": 1.6921066263598124e-05, + "loss": 0.1505, + "step": 6305 + }, + { + "epoch": 5.58, + "learning_rate": 1.6920031803913297e-05, + "loss": 0.1527, + "step": 6306 + }, + { + "epoch": 5.58, + "learning_rate": 1.6918997202110996e-05, + "loss": 0.1648, + "step": 6307 + }, + { + "epoch": 5.58, + "learning_rate": 1.6917962458212463e-05, + "loss": 0.1509, + "step": 6308 + }, + { + "epoch": 5.58, + "learning_rate": 1.691692757223895e-05, + "loss": 0.1767, + "step": 6309 + }, + { + "epoch": 5.58, + "learning_rate": 1.6915892544211713e-05, + "loss": 0.1544, + "step": 6310 + }, + { + "epoch": 5.58, + "learning_rate": 1.6914857374152012e-05, + "loss": 0.153, + "step": 6311 + }, + { + "epoch": 5.59, + "learning_rate": 1.69138220620811e-05, + "loss": 0.1531, + "step": 6312 + }, + { + "epoch": 5.59, + "learning_rate": 1.6912786608020236e-05, + "loss": 0.164, + "step": 6313 + }, + { + "epoch": 5.59, + "learning_rate": 1.6911751011990696e-05, + "loss": 0.1608, + "step": 6314 + }, + { + "epoch": 5.59, + "learning_rate": 1.6910715274013744e-05, + "loss": 0.1508, + "step": 6315 + }, + { + "epoch": 5.59, + "learning_rate": 1.6909679394110645e-05, + "loss": 0.1549, + "step": 6316 + }, + { + "epoch": 5.59, + "learning_rate": 1.6908643372302683e-05, + "loss": 0.1488, + "step": 6317 + }, + { + "epoch": 5.59, + "learning_rate": 1.6907607208611123e-05, + "loss": 0.1628, + "step": 6318 + }, + { + "epoch": 5.59, + "learning_rate": 1.6906570903057258e-05, + "loss": 0.1454, + "step": 6319 + }, + { + "epoch": 5.59, + "learning_rate": 1.690553445566236e-05, + "loss": 0.1715, + "step": 6320 + }, + { + "epoch": 5.59, + "learning_rate": 1.690449786644772e-05, + "loss": 0.1551, + "step": 6321 + }, + { + "epoch": 5.59, + "learning_rate": 1.6903461135434627e-05, + "loss": 0.1548, + "step": 6322 + }, + { + "epoch": 5.59, + "learning_rate": 1.690242426264437e-05, + "loss": 0.1441, + "step": 6323 + }, + { + "epoch": 5.6, + "learning_rate": 1.6901387248098246e-05, + "loss": 0.1721, + "step": 6324 + }, + { + "epoch": 5.6, + "learning_rate": 1.6900350091817546e-05, + "loss": 0.1705, + "step": 6325 + }, + { + "epoch": 5.6, + "learning_rate": 1.689931279382358e-05, + "loss": 0.1728, + "step": 6326 + }, + { + "epoch": 5.6, + "learning_rate": 1.6898275354137644e-05, + "loss": 0.1571, + "step": 6327 + }, + { + "epoch": 5.6, + "learning_rate": 1.6897237772781046e-05, + "loss": 0.1664, + "step": 6328 + }, + { + "epoch": 5.6, + "learning_rate": 1.689620004977509e-05, + "loss": 0.1655, + "step": 6329 + }, + { + "epoch": 5.6, + "learning_rate": 1.6895162185141097e-05, + "loss": 0.1757, + "step": 6330 + }, + { + "epoch": 5.6, + "learning_rate": 1.6894124178900376e-05, + "loss": 0.155, + "step": 6331 + }, + { + "epoch": 5.6, + "learning_rate": 1.689308603107425e-05, + "loss": 0.1552, + "step": 6332 + }, + { + "epoch": 5.6, + "learning_rate": 1.6892047741684033e-05, + "loss": 0.1416, + "step": 6333 + }, + { + "epoch": 5.6, + "learning_rate": 1.689100931075105e-05, + "loss": 0.173, + "step": 6334 + }, + { + "epoch": 5.61, + "learning_rate": 1.6889970738296628e-05, + "loss": 0.1588, + "step": 6335 + }, + { + "epoch": 5.61, + "learning_rate": 1.6888932024342098e-05, + "loss": 0.1541, + "step": 6336 + }, + { + "epoch": 5.61, + "learning_rate": 1.6887893168908794e-05, + "loss": 0.1674, + "step": 6337 + }, + { + "epoch": 5.61, + "learning_rate": 1.6886854172018043e-05, + "loss": 0.1702, + "step": 6338 + }, + { + "epoch": 5.61, + "learning_rate": 1.688581503369119e-05, + "loss": 0.1668, + "step": 6339 + }, + { + "epoch": 5.61, + "learning_rate": 1.6884775753949572e-05, + "loss": 0.1521, + "step": 6340 + }, + { + "epoch": 5.61, + "learning_rate": 1.688373633281454e-05, + "loss": 0.1656, + "step": 6341 + }, + { + "epoch": 5.61, + "learning_rate": 1.6882696770307428e-05, + "loss": 0.1573, + "step": 6342 + }, + { + "epoch": 5.61, + "learning_rate": 1.6881657066449596e-05, + "loss": 0.144, + "step": 6343 + }, + { + "epoch": 5.61, + "learning_rate": 1.6880617221262396e-05, + "loss": 0.1496, + "step": 6344 + }, + { + "epoch": 5.61, + "learning_rate": 1.6879577234767183e-05, + "loss": 0.1718, + "step": 6345 + }, + { + "epoch": 5.62, + "learning_rate": 1.6878537106985305e-05, + "loss": 0.1686, + "step": 6346 + }, + { + "epoch": 5.62, + "learning_rate": 1.687749683793814e-05, + "loss": 0.1563, + "step": 6347 + }, + { + "epoch": 5.62, + "learning_rate": 1.6876456427647036e-05, + "loss": 0.1456, + "step": 6348 + }, + { + "epoch": 5.62, + "learning_rate": 1.6875415876133373e-05, + "loss": 0.1538, + "step": 6349 + }, + { + "epoch": 5.62, + "learning_rate": 1.6874375183418514e-05, + "loss": 0.1662, + "step": 6350 + }, + { + "epoch": 5.62, + "learning_rate": 1.6873334349523832e-05, + "loss": 0.1759, + "step": 6351 + }, + { + "epoch": 5.62, + "learning_rate": 1.6872293374470706e-05, + "loss": 0.1658, + "step": 6352 + }, + { + "epoch": 5.62, + "learning_rate": 1.6871252258280513e-05, + "loss": 0.1626, + "step": 6353 + }, + { + "epoch": 5.62, + "learning_rate": 1.6870211000974633e-05, + "loss": 0.1632, + "step": 6354 + }, + { + "epoch": 5.62, + "learning_rate": 1.6869169602574454e-05, + "loss": 0.1515, + "step": 6355 + }, + { + "epoch": 5.62, + "learning_rate": 1.6868128063101358e-05, + "loss": 0.162, + "step": 6356 + }, + { + "epoch": 5.63, + "learning_rate": 1.6867086382576737e-05, + "loss": 0.1533, + "step": 6357 + }, + { + "epoch": 5.63, + "learning_rate": 1.6866044561021987e-05, + "loss": 0.1565, + "step": 6358 + }, + { + "epoch": 5.63, + "learning_rate": 1.6865002598458505e-05, + "loss": 0.1657, + "step": 6359 + }, + { + "epoch": 5.63, + "learning_rate": 1.6863960494907687e-05, + "loss": 0.1399, + "step": 6360 + }, + { + "epoch": 5.63, + "learning_rate": 1.686291825039093e-05, + "loss": 0.15, + "step": 6361 + }, + { + "epoch": 5.63, + "learning_rate": 1.686187586492965e-05, + "loss": 0.1635, + "step": 6362 + }, + { + "epoch": 5.63, + "learning_rate": 1.6860833338545245e-05, + "loss": 0.1668, + "step": 6363 + }, + { + "epoch": 5.63, + "learning_rate": 1.685979067125913e-05, + "loss": 0.1573, + "step": 6364 + }, + { + "epoch": 5.63, + "learning_rate": 1.6858747863092713e-05, + "loss": 0.1638, + "step": 6365 + }, + { + "epoch": 5.63, + "learning_rate": 1.685770491406742e-05, + "loss": 0.1617, + "step": 6366 + }, + { + "epoch": 5.63, + "learning_rate": 1.685666182420466e-05, + "loss": 0.152, + "step": 6367 + }, + { + "epoch": 5.63, + "learning_rate": 1.6855618593525863e-05, + "loss": 0.169, + "step": 6368 + }, + { + "epoch": 5.64, + "learning_rate": 1.685457522205245e-05, + "loss": 0.152, + "step": 6369 + }, + { + "epoch": 5.64, + "learning_rate": 1.685353170980585e-05, + "loss": 0.1512, + "step": 6370 + }, + { + "epoch": 5.64, + "learning_rate": 1.685248805680749e-05, + "loss": 0.1901, + "step": 6371 + }, + { + "epoch": 5.64, + "learning_rate": 1.6851444263078807e-05, + "loss": 0.1655, + "step": 6372 + }, + { + "epoch": 5.64, + "learning_rate": 1.6850400328641242e-05, + "loss": 0.1461, + "step": 6373 + }, + { + "epoch": 5.64, + "learning_rate": 1.6849356253516224e-05, + "loss": 0.1485, + "step": 6374 + }, + { + "epoch": 5.64, + "learning_rate": 1.6848312037725206e-05, + "loss": 0.1681, + "step": 6375 + }, + { + "epoch": 5.64, + "learning_rate": 1.6847267681289626e-05, + "loss": 0.1711, + "step": 6376 + }, + { + "epoch": 5.64, + "learning_rate": 1.6846223184230934e-05, + "loss": 0.1486, + "step": 6377 + }, + { + "epoch": 5.64, + "learning_rate": 1.6845178546570583e-05, + "loss": 0.1509, + "step": 6378 + }, + { + "epoch": 5.64, + "learning_rate": 1.6844133768330024e-05, + "loss": 0.1662, + "step": 6379 + }, + { + "epoch": 5.65, + "learning_rate": 1.6843088849530714e-05, + "loss": 0.1568, + "step": 6380 + }, + { + "epoch": 5.65, + "learning_rate": 1.6842043790194113e-05, + "loss": 0.1611, + "step": 6381 + }, + { + "epoch": 5.65, + "learning_rate": 1.6840998590341684e-05, + "loss": 0.152, + "step": 6382 + }, + { + "epoch": 5.65, + "learning_rate": 1.6839953249994893e-05, + "loss": 0.1769, + "step": 6383 + }, + { + "epoch": 5.65, + "learning_rate": 1.6838907769175205e-05, + "loss": 0.1712, + "step": 6384 + }, + { + "epoch": 5.65, + "learning_rate": 1.68378621479041e-05, + "loss": 0.145, + "step": 6385 + }, + { + "epoch": 5.65, + "learning_rate": 1.6836816386203037e-05, + "loss": 0.1562, + "step": 6386 + }, + { + "epoch": 5.65, + "learning_rate": 1.683577048409351e-05, + "loss": 0.1533, + "step": 6387 + }, + { + "epoch": 5.65, + "learning_rate": 1.6834724441596987e-05, + "loss": 0.1529, + "step": 6388 + }, + { + "epoch": 5.65, + "learning_rate": 1.6833678258734953e-05, + "loss": 0.156, + "step": 6389 + }, + { + "epoch": 5.65, + "learning_rate": 1.6832631935528897e-05, + "loss": 0.1689, + "step": 6390 + }, + { + "epoch": 5.66, + "learning_rate": 1.6831585472000303e-05, + "loss": 0.1498, + "step": 6391 + }, + { + "epoch": 5.66, + "learning_rate": 1.6830538868170666e-05, + "loss": 0.1602, + "step": 6392 + }, + { + "epoch": 5.66, + "learning_rate": 1.6829492124061477e-05, + "loss": 0.1664, + "step": 6393 + }, + { + "epoch": 5.66, + "learning_rate": 1.6828445239694237e-05, + "loss": 0.1526, + "step": 6394 + }, + { + "epoch": 5.66, + "learning_rate": 1.6827398215090443e-05, + "loss": 0.1583, + "step": 6395 + }, + { + "epoch": 5.66, + "learning_rate": 1.68263510502716e-05, + "loss": 0.1532, + "step": 6396 + }, + { + "epoch": 5.66, + "learning_rate": 1.682530374525921e-05, + "loss": 0.1724, + "step": 6397 + }, + { + "epoch": 5.66, + "learning_rate": 1.6824256300074785e-05, + "loss": 0.1577, + "step": 6398 + }, + { + "epoch": 5.66, + "learning_rate": 1.6823208714739835e-05, + "loss": 0.159, + "step": 6399 + }, + { + "epoch": 5.66, + "learning_rate": 1.6822160989275875e-05, + "loss": 0.1669, + "step": 6400 + }, + { + "epoch": 5.66, + "learning_rate": 1.6821113123704425e-05, + "loss": 0.1587, + "step": 6401 + }, + { + "epoch": 5.66, + "learning_rate": 1.6820065118047e-05, + "loss": 0.1626, + "step": 6402 + }, + { + "epoch": 5.67, + "learning_rate": 1.6819016972325126e-05, + "loss": 0.1454, + "step": 6403 + }, + { + "epoch": 5.67, + "learning_rate": 1.681796868656033e-05, + "loss": 0.1621, + "step": 6404 + }, + { + "epoch": 5.67, + "learning_rate": 1.6816920260774136e-05, + "loss": 0.1627, + "step": 6405 + }, + { + "epoch": 5.67, + "learning_rate": 1.681587169498808e-05, + "loss": 0.145, + "step": 6406 + }, + { + "epoch": 5.67, + "learning_rate": 1.681482298922369e-05, + "loss": 0.1703, + "step": 6407 + }, + { + "epoch": 5.67, + "learning_rate": 1.6813774143502516e-05, + "loss": 0.1352, + "step": 6408 + }, + { + "epoch": 5.67, + "learning_rate": 1.6812725157846088e-05, + "loss": 0.1506, + "step": 6409 + }, + { + "epoch": 5.67, + "learning_rate": 1.681167603227595e-05, + "loss": 0.1533, + "step": 6410 + }, + { + "epoch": 5.67, + "learning_rate": 1.6810626766813654e-05, + "loss": 0.169, + "step": 6411 + }, + { + "epoch": 5.67, + "learning_rate": 1.6809577361480746e-05, + "loss": 0.1454, + "step": 6412 + }, + { + "epoch": 5.67, + "learning_rate": 1.680852781629877e-05, + "loss": 0.1665, + "step": 6413 + }, + { + "epoch": 5.68, + "learning_rate": 1.680747813128929e-05, + "loss": 0.1637, + "step": 6414 + }, + { + "epoch": 5.68, + "learning_rate": 1.6806428306473863e-05, + "loss": 0.1597, + "step": 6415 + }, + { + "epoch": 5.68, + "learning_rate": 1.6805378341874044e-05, + "loss": 0.1686, + "step": 6416 + }, + { + "epoch": 5.68, + "learning_rate": 1.68043282375114e-05, + "loss": 0.1536, + "step": 6417 + }, + { + "epoch": 5.68, + "learning_rate": 1.6803277993407497e-05, + "loss": 0.1801, + "step": 6418 + }, + { + "epoch": 5.68, + "learning_rate": 1.6802227609583907e-05, + "loss": 0.1572, + "step": 6419 + }, + { + "epoch": 5.68, + "learning_rate": 1.680117708606219e-05, + "loss": 0.148, + "step": 6420 + }, + { + "epoch": 5.68, + "learning_rate": 1.6800126422863936e-05, + "loss": 0.1584, + "step": 6421 + }, + { + "epoch": 5.68, + "learning_rate": 1.6799075620010714e-05, + "loss": 0.1521, + "step": 6422 + }, + { + "epoch": 5.68, + "learning_rate": 1.6798024677524107e-05, + "loss": 0.1674, + "step": 6423 + }, + { + "epoch": 5.68, + "learning_rate": 1.6796973595425698e-05, + "loss": 0.1739, + "step": 6424 + }, + { + "epoch": 5.69, + "learning_rate": 1.679592237373707e-05, + "loss": 0.1398, + "step": 6425 + }, + { + "epoch": 5.69, + "learning_rate": 1.6794871012479812e-05, + "loss": 0.1601, + "step": 6426 + }, + { + "epoch": 5.69, + "learning_rate": 1.679381951167552e-05, + "loss": 0.1602, + "step": 6427 + }, + { + "epoch": 5.69, + "learning_rate": 1.679276787134579e-05, + "loss": 0.1587, + "step": 6428 + }, + { + "epoch": 5.69, + "learning_rate": 1.6791716091512217e-05, + "loss": 0.1537, + "step": 6429 + }, + { + "epoch": 5.69, + "learning_rate": 1.67906641721964e-05, + "loss": 0.1544, + "step": 6430 + }, + { + "epoch": 5.69, + "learning_rate": 1.6789612113419947e-05, + "loss": 0.1515, + "step": 6431 + }, + { + "epoch": 5.69, + "learning_rate": 1.6788559915204458e-05, + "loss": 0.1611, + "step": 6432 + }, + { + "epoch": 5.69, + "learning_rate": 1.6787507577571544e-05, + "loss": 0.1463, + "step": 6433 + }, + { + "epoch": 5.69, + "learning_rate": 1.678645510054282e-05, + "loss": 0.1571, + "step": 6434 + }, + { + "epoch": 5.69, + "learning_rate": 1.67854024841399e-05, + "loss": 0.1585, + "step": 6435 + }, + { + "epoch": 5.69, + "learning_rate": 1.6784349728384403e-05, + "loss": 0.1617, + "step": 6436 + }, + { + "epoch": 5.7, + "learning_rate": 1.6783296833297944e-05, + "loss": 0.1626, + "step": 6437 + }, + { + "epoch": 5.7, + "learning_rate": 1.6782243798902148e-05, + "loss": 0.1462, + "step": 6438 + }, + { + "epoch": 5.7, + "learning_rate": 1.6781190625218644e-05, + "loss": 0.1632, + "step": 6439 + }, + { + "epoch": 5.7, + "learning_rate": 1.6780137312269064e-05, + "loss": 0.1601, + "step": 6440 + }, + { + "epoch": 5.7, + "learning_rate": 1.6779083860075032e-05, + "loss": 0.1722, + "step": 6441 + }, + { + "epoch": 5.7, + "learning_rate": 1.677803026865819e-05, + "loss": 0.1707, + "step": 6442 + }, + { + "epoch": 5.7, + "learning_rate": 1.677697653804017e-05, + "loss": 0.167, + "step": 6443 + }, + { + "epoch": 5.7, + "learning_rate": 1.677592266824262e-05, + "loss": 0.1612, + "step": 6444 + }, + { + "epoch": 5.7, + "learning_rate": 1.6774868659287176e-05, + "loss": 0.1738, + "step": 6445 + }, + { + "epoch": 5.7, + "learning_rate": 1.6773814511195487e-05, + "loss": 0.1657, + "step": 6446 + }, + { + "epoch": 5.7, + "learning_rate": 1.6772760223989203e-05, + "loss": 0.1687, + "step": 6447 + }, + { + "epoch": 5.71, + "learning_rate": 1.6771705797689972e-05, + "loss": 0.1562, + "step": 6448 + }, + { + "epoch": 5.71, + "learning_rate": 1.6770651232319455e-05, + "loss": 0.149, + "step": 6449 + }, + { + "epoch": 5.71, + "learning_rate": 1.6769596527899307e-05, + "loss": 0.1702, + "step": 6450 + }, + { + "epoch": 5.71, + "learning_rate": 1.676854168445119e-05, + "loss": 0.1694, + "step": 6451 + }, + { + "epoch": 5.71, + "learning_rate": 1.6767486701996763e-05, + "loss": 0.1518, + "step": 6452 + }, + { + "epoch": 5.71, + "learning_rate": 1.6766431580557697e-05, + "loss": 0.1669, + "step": 6453 + }, + { + "epoch": 5.71, + "learning_rate": 1.6765376320155657e-05, + "loss": 0.1474, + "step": 6454 + }, + { + "epoch": 5.71, + "learning_rate": 1.6764320920812322e-05, + "loss": 0.1587, + "step": 6455 + }, + { + "epoch": 5.71, + "learning_rate": 1.676326538254936e-05, + "loss": 0.1626, + "step": 6456 + }, + { + "epoch": 5.71, + "learning_rate": 1.6762209705388447e-05, + "loss": 0.1702, + "step": 6457 + }, + { + "epoch": 5.71, + "learning_rate": 1.6761153889351272e-05, + "loss": 0.1685, + "step": 6458 + }, + { + "epoch": 5.72, + "learning_rate": 1.6760097934459515e-05, + "loss": 0.1661, + "step": 6459 + }, + { + "epoch": 5.72, + "learning_rate": 1.6759041840734856e-05, + "loss": 0.1509, + "step": 6460 + }, + { + "epoch": 5.72, + "learning_rate": 1.6757985608198994e-05, + "loss": 0.1566, + "step": 6461 + }, + { + "epoch": 5.72, + "learning_rate": 1.6756929236873616e-05, + "loss": 0.1643, + "step": 6462 + }, + { + "epoch": 5.72, + "learning_rate": 1.6755872726780415e-05, + "loss": 0.1597, + "step": 6463 + }, + { + "epoch": 5.72, + "learning_rate": 1.675481607794109e-05, + "loss": 0.1534, + "step": 6464 + }, + { + "epoch": 5.72, + "learning_rate": 1.675375929037734e-05, + "loss": 0.1612, + "step": 6465 + }, + { + "epoch": 5.72, + "learning_rate": 1.6752702364110877e-05, + "loss": 0.1716, + "step": 6466 + }, + { + "epoch": 5.72, + "learning_rate": 1.6751645299163398e-05, + "loss": 0.1583, + "step": 6467 + }, + { + "epoch": 5.72, + "learning_rate": 1.6750588095556618e-05, + "loss": 0.1621, + "step": 6468 + }, + { + "epoch": 5.72, + "learning_rate": 1.6749530753312243e-05, + "loss": 0.1542, + "step": 6469 + }, + { + "epoch": 5.72, + "learning_rate": 1.674847327245199e-05, + "loss": 0.1611, + "step": 6470 + }, + { + "epoch": 5.73, + "learning_rate": 1.674741565299758e-05, + "loss": 0.1632, + "step": 6471 + }, + { + "epoch": 5.73, + "learning_rate": 1.6746357894970725e-05, + "loss": 0.1485, + "step": 6472 + }, + { + "epoch": 5.73, + "learning_rate": 1.674529999839316e-05, + "loss": 0.1607, + "step": 6473 + }, + { + "epoch": 5.73, + "learning_rate": 1.6744241963286603e-05, + "loss": 0.1668, + "step": 6474 + }, + { + "epoch": 5.73, + "learning_rate": 1.674318378967278e-05, + "loss": 0.1546, + "step": 6475 + }, + { + "epoch": 5.73, + "learning_rate": 1.6742125477573434e-05, + "loss": 0.1579, + "step": 6476 + }, + { + "epoch": 5.73, + "learning_rate": 1.6741067027010293e-05, + "loss": 0.1393, + "step": 6477 + }, + { + "epoch": 5.73, + "learning_rate": 1.6740008438005095e-05, + "loss": 0.1538, + "step": 6478 + }, + { + "epoch": 5.73, + "learning_rate": 1.673894971057958e-05, + "loss": 0.149, + "step": 6479 + }, + { + "epoch": 5.73, + "learning_rate": 1.673789084475549e-05, + "loss": 0.1603, + "step": 6480 + }, + { + "epoch": 5.73, + "learning_rate": 1.6736831840554575e-05, + "loss": 0.1568, + "step": 6481 + }, + { + "epoch": 5.74, + "learning_rate": 1.673577269799858e-05, + "loss": 0.1449, + "step": 6482 + }, + { + "epoch": 5.74, + "learning_rate": 1.6734713417109262e-05, + "loss": 0.1539, + "step": 6483 + }, + { + "epoch": 5.74, + "learning_rate": 1.6733653997908367e-05, + "loss": 0.1677, + "step": 6484 + }, + { + "epoch": 5.74, + "learning_rate": 1.6732594440417654e-05, + "loss": 0.1674, + "step": 6485 + }, + { + "epoch": 5.74, + "learning_rate": 1.6731534744658896e-05, + "loss": 0.1563, + "step": 6486 + }, + { + "epoch": 5.74, + "learning_rate": 1.673047491065384e-05, + "loss": 0.1604, + "step": 6487 + }, + { + "epoch": 5.74, + "learning_rate": 1.6729414938424263e-05, + "loss": 0.1474, + "step": 6488 + }, + { + "epoch": 5.74, + "learning_rate": 1.672835482799193e-05, + "loss": 0.1566, + "step": 6489 + }, + { + "epoch": 5.74, + "learning_rate": 1.6727294579378605e-05, + "loss": 0.1623, + "step": 6490 + }, + { + "epoch": 5.74, + "learning_rate": 1.6726234192606075e-05, + "loss": 0.1578, + "step": 6491 + }, + { + "epoch": 5.74, + "learning_rate": 1.672517366769611e-05, + "loss": 0.1476, + "step": 6492 + }, + { + "epoch": 5.75, + "learning_rate": 1.6724113004670492e-05, + "loss": 0.1537, + "step": 6493 + }, + { + "epoch": 5.75, + "learning_rate": 1.6723052203551004e-05, + "loss": 0.1553, + "step": 6494 + }, + { + "epoch": 5.75, + "learning_rate": 1.6721991264359432e-05, + "loss": 0.1643, + "step": 6495 + }, + { + "epoch": 5.75, + "learning_rate": 1.6720930187117564e-05, + "loss": 0.1567, + "step": 6496 + }, + { + "epoch": 5.75, + "learning_rate": 1.671986897184719e-05, + "loss": 0.1656, + "step": 6497 + }, + { + "epoch": 5.75, + "learning_rate": 1.671880761857011e-05, + "loss": 0.1677, + "step": 6498 + }, + { + "epoch": 5.75, + "learning_rate": 1.6717746127308114e-05, + "loss": 0.1615, + "step": 6499 + }, + { + "epoch": 5.75, + "learning_rate": 1.6716684498083005e-05, + "loss": 0.1674, + "step": 6500 + }, + { + "epoch": 5.75, + "learning_rate": 1.6715622730916585e-05, + "loss": 0.1723, + "step": 6501 + }, + { + "epoch": 5.75, + "learning_rate": 1.6714560825830664e-05, + "loss": 0.1636, + "step": 6502 + }, + { + "epoch": 5.75, + "learning_rate": 1.6713498782847043e-05, + "loss": 0.1575, + "step": 6503 + }, + { + "epoch": 5.76, + "learning_rate": 1.671243660198754e-05, + "loss": 0.1619, + "step": 6504 + }, + { + "epoch": 5.76, + "learning_rate": 1.6711374283273963e-05, + "loss": 0.1553, + "step": 6505 + }, + { + "epoch": 5.76, + "learning_rate": 1.6710311826728136e-05, + "loss": 0.1504, + "step": 6506 + }, + { + "epoch": 5.76, + "learning_rate": 1.6709249232371874e-05, + "loss": 0.1561, + "step": 6507 + }, + { + "epoch": 5.76, + "learning_rate": 1.6708186500226998e-05, + "loss": 0.1582, + "step": 6508 + }, + { + "epoch": 5.76, + "learning_rate": 1.6707123630315344e-05, + "loss": 0.1648, + "step": 6509 + }, + { + "epoch": 5.76, + "learning_rate": 1.6706060622658724e-05, + "loss": 0.1619, + "step": 6510 + }, + { + "epoch": 5.76, + "learning_rate": 1.670499747727898e-05, + "loss": 0.1477, + "step": 6511 + }, + { + "epoch": 5.76, + "learning_rate": 1.6703934194197947e-05, + "loss": 0.1649, + "step": 6512 + }, + { + "epoch": 5.76, + "learning_rate": 1.6702870773437453e-05, + "loss": 0.1473, + "step": 6513 + }, + { + "epoch": 5.76, + "learning_rate": 1.6701807215019347e-05, + "loss": 0.1619, + "step": 6514 + }, + { + "epoch": 5.76, + "learning_rate": 1.6700743518965467e-05, + "loss": 0.1668, + "step": 6515 + }, + { + "epoch": 5.77, + "learning_rate": 1.6699679685297655e-05, + "loss": 0.1635, + "step": 6516 + }, + { + "epoch": 5.77, + "learning_rate": 1.6698615714037767e-05, + "loss": 0.1538, + "step": 6517 + }, + { + "epoch": 5.77, + "learning_rate": 1.6697551605207646e-05, + "loss": 0.1552, + "step": 6518 + }, + { + "epoch": 5.77, + "learning_rate": 1.6696487358829153e-05, + "loss": 0.1464, + "step": 6519 + }, + { + "epoch": 5.77, + "learning_rate": 1.6695422974924137e-05, + "loss": 0.1518, + "step": 6520 + }, + { + "epoch": 5.77, + "learning_rate": 1.6694358453514463e-05, + "loss": 0.1561, + "step": 6521 + }, + { + "epoch": 5.77, + "learning_rate": 1.669329379462199e-05, + "loss": 0.1557, + "step": 6522 + }, + { + "epoch": 5.77, + "learning_rate": 1.669222899826859e-05, + "loss": 0.1606, + "step": 6523 + }, + { + "epoch": 5.77, + "learning_rate": 1.6691164064476116e-05, + "loss": 0.1601, + "step": 6524 + }, + { + "epoch": 5.77, + "learning_rate": 1.6690098993266453e-05, + "loss": 0.1641, + "step": 6525 + }, + { + "epoch": 5.77, + "learning_rate": 1.668903378466147e-05, + "loss": 0.1477, + "step": 6526 + }, + { + "epoch": 5.78, + "learning_rate": 1.668796843868304e-05, + "loss": 0.1584, + "step": 6527 + }, + { + "epoch": 5.78, + "learning_rate": 1.6686902955353045e-05, + "loss": 0.171, + "step": 6528 + }, + { + "epoch": 5.78, + "learning_rate": 1.668583733469337e-05, + "loss": 0.1507, + "step": 6529 + }, + { + "epoch": 5.78, + "learning_rate": 1.6684771576725896e-05, + "loss": 0.1625, + "step": 6530 + }, + { + "epoch": 5.78, + "learning_rate": 1.668370568147251e-05, + "loss": 0.1632, + "step": 6531 + }, + { + "epoch": 5.78, + "learning_rate": 1.6682639648955104e-05, + "loss": 0.1641, + "step": 6532 + }, + { + "epoch": 5.78, + "learning_rate": 1.6681573479195567e-05, + "loss": 0.1628, + "step": 6533 + }, + { + "epoch": 5.78, + "learning_rate": 1.6680507172215804e-05, + "loss": 0.1536, + "step": 6534 + }, + { + "epoch": 5.78, + "learning_rate": 1.6679440728037704e-05, + "loss": 0.1553, + "step": 6535 + }, + { + "epoch": 5.78, + "learning_rate": 1.667837414668318e-05, + "loss": 0.1649, + "step": 6536 + }, + { + "epoch": 5.78, + "learning_rate": 1.6677307428174124e-05, + "loss": 0.1558, + "step": 6537 + }, + { + "epoch": 5.79, + "learning_rate": 1.6676240572532453e-05, + "loss": 0.1759, + "step": 6538 + }, + { + "epoch": 5.79, + "learning_rate": 1.667517357978007e-05, + "loss": 0.1654, + "step": 6539 + }, + { + "epoch": 5.79, + "learning_rate": 1.6674106449938894e-05, + "loss": 0.1626, + "step": 6540 + }, + { + "epoch": 5.79, + "learning_rate": 1.6673039183030838e-05, + "loss": 0.1494, + "step": 6541 + }, + { + "epoch": 5.79, + "learning_rate": 1.6671971779077818e-05, + "loss": 0.1463, + "step": 6542 + }, + { + "epoch": 5.79, + "learning_rate": 1.667090423810176e-05, + "loss": 0.1609, + "step": 6543 + }, + { + "epoch": 5.79, + "learning_rate": 1.6669836560124585e-05, + "loss": 0.166, + "step": 6544 + }, + { + "epoch": 5.79, + "learning_rate": 1.666876874516822e-05, + "loss": 0.1722, + "step": 6545 + }, + { + "epoch": 5.79, + "learning_rate": 1.6667700793254598e-05, + "loss": 0.1644, + "step": 6546 + }, + { + "epoch": 5.79, + "learning_rate": 1.666663270440565e-05, + "loss": 0.1636, + "step": 6547 + }, + { + "epoch": 5.79, + "learning_rate": 1.6665564478643316e-05, + "loss": 0.152, + "step": 6548 + }, + { + "epoch": 5.79, + "learning_rate": 1.6664496115989522e-05, + "loss": 0.1796, + "step": 6549 + }, + { + "epoch": 5.8, + "learning_rate": 1.6663427616466216e-05, + "loss": 0.1634, + "step": 6550 + }, + { + "epoch": 5.8, + "learning_rate": 1.666235898009535e-05, + "loss": 0.1479, + "step": 6551 + }, + { + "epoch": 5.8, + "learning_rate": 1.6661290206898858e-05, + "loss": 0.159, + "step": 6552 + }, + { + "epoch": 5.8, + "learning_rate": 1.6660221296898696e-05, + "loss": 0.156, + "step": 6553 + }, + { + "epoch": 5.8, + "learning_rate": 1.665915225011681e-05, + "loss": 0.1634, + "step": 6554 + }, + { + "epoch": 5.8, + "learning_rate": 1.665808306657517e-05, + "loss": 0.1632, + "step": 6555 + }, + { + "epoch": 5.8, + "learning_rate": 1.6657013746295717e-05, + "loss": 0.1635, + "step": 6556 + }, + { + "epoch": 5.8, + "learning_rate": 1.6655944289300418e-05, + "loss": 0.152, + "step": 6557 + }, + { + "epoch": 5.8, + "learning_rate": 1.665487469561124e-05, + "loss": 0.1492, + "step": 6558 + }, + { + "epoch": 5.8, + "learning_rate": 1.6653804965250148e-05, + "loss": 0.1636, + "step": 6559 + }, + { + "epoch": 5.8, + "learning_rate": 1.6652735098239108e-05, + "loss": 0.1621, + "step": 6560 + }, + { + "epoch": 5.81, + "learning_rate": 1.6651665094600095e-05, + "loss": 0.1634, + "step": 6561 + }, + { + "epoch": 5.81, + "learning_rate": 1.665059495435508e-05, + "loss": 0.1569, + "step": 6562 + }, + { + "epoch": 5.81, + "learning_rate": 1.6649524677526048e-05, + "loss": 0.1494, + "step": 6563 + }, + { + "epoch": 5.81, + "learning_rate": 1.6648454264134972e-05, + "loss": 0.1567, + "step": 6564 + }, + { + "epoch": 5.81, + "learning_rate": 1.664738371420384e-05, + "loss": 0.1685, + "step": 6565 + }, + { + "epoch": 5.81, + "learning_rate": 1.664631302775463e-05, + "loss": 0.1796, + "step": 6566 + }, + { + "epoch": 5.81, + "learning_rate": 1.664524220480934e-05, + "loss": 0.1617, + "step": 6567 + }, + { + "epoch": 5.81, + "learning_rate": 1.664417124538996e-05, + "loss": 0.1515, + "step": 6568 + }, + { + "epoch": 5.81, + "learning_rate": 1.6643100149518483e-05, + "loss": 0.165, + "step": 6569 + }, + { + "epoch": 5.81, + "learning_rate": 1.6642028917216902e-05, + "loss": 0.1706, + "step": 6570 + }, + { + "epoch": 5.81, + "learning_rate": 1.6640957548507225e-05, + "loss": 0.1596, + "step": 6571 + }, + { + "epoch": 5.82, + "learning_rate": 1.663988604341145e-05, + "loss": 0.1536, + "step": 6572 + }, + { + "epoch": 5.82, + "learning_rate": 1.6638814401951583e-05, + "loss": 0.1359, + "step": 6573 + }, + { + "epoch": 5.82, + "learning_rate": 1.6637742624149634e-05, + "loss": 0.1526, + "step": 6574 + }, + { + "epoch": 5.82, + "learning_rate": 1.6636670710027612e-05, + "loss": 0.1465, + "step": 6575 + }, + { + "epoch": 5.82, + "learning_rate": 1.663559865960753e-05, + "loss": 0.1572, + "step": 6576 + }, + { + "epoch": 5.82, + "learning_rate": 1.663452647291141e-05, + "loss": 0.1456, + "step": 6577 + }, + { + "epoch": 5.82, + "learning_rate": 1.6633454149961264e-05, + "loss": 0.1665, + "step": 6578 + }, + { + "epoch": 5.82, + "learning_rate": 1.6632381690779124e-05, + "loss": 0.1564, + "step": 6579 + }, + { + "epoch": 5.82, + "learning_rate": 1.6631309095387012e-05, + "loss": 0.1551, + "step": 6580 + }, + { + "epoch": 5.82, + "learning_rate": 1.663023636380695e-05, + "loss": 0.1636, + "step": 6581 + }, + { + "epoch": 5.82, + "learning_rate": 1.662916349606097e-05, + "loss": 0.1594, + "step": 6582 + }, + { + "epoch": 5.82, + "learning_rate": 1.6628090492171113e-05, + "loss": 0.1706, + "step": 6583 + }, + { + "epoch": 5.83, + "learning_rate": 1.662701735215941e-05, + "loss": 0.158, + "step": 6584 + }, + { + "epoch": 5.83, + "learning_rate": 1.6625944076047905e-05, + "loss": 0.168, + "step": 6585 + }, + { + "epoch": 5.83, + "learning_rate": 1.6624870663858632e-05, + "loss": 0.155, + "step": 6586 + }, + { + "epoch": 5.83, + "learning_rate": 1.6623797115613638e-05, + "loss": 0.1525, + "step": 6587 + }, + { + "epoch": 5.83, + "learning_rate": 1.6622723431334976e-05, + "loss": 0.1667, + "step": 6588 + }, + { + "epoch": 5.83, + "learning_rate": 1.6621649611044694e-05, + "loss": 0.1536, + "step": 6589 + }, + { + "epoch": 5.83, + "learning_rate": 1.662057565476484e-05, + "loss": 0.1382, + "step": 6590 + }, + { + "epoch": 5.83, + "learning_rate": 1.6619501562517476e-05, + "loss": 0.1757, + "step": 6591 + }, + { + "epoch": 5.83, + "learning_rate": 1.6618427334324657e-05, + "loss": 0.1629, + "step": 6592 + }, + { + "epoch": 5.83, + "learning_rate": 1.661735297020845e-05, + "loss": 0.1603, + "step": 6593 + }, + { + "epoch": 5.83, + "learning_rate": 1.6616278470190915e-05, + "loss": 0.1611, + "step": 6594 + }, + { + "epoch": 5.84, + "learning_rate": 1.661520383429412e-05, + "loss": 0.1452, + "step": 6595 + }, + { + "epoch": 5.84, + "learning_rate": 1.661412906254013e-05, + "loss": 0.1563, + "step": 6596 + }, + { + "epoch": 5.84, + "learning_rate": 1.6613054154951026e-05, + "loss": 0.1663, + "step": 6597 + }, + { + "epoch": 5.84, + "learning_rate": 1.661197911154888e-05, + "loss": 0.1552, + "step": 6598 + }, + { + "epoch": 5.84, + "learning_rate": 1.6610903932355767e-05, + "loss": 0.1528, + "step": 6599 + }, + { + "epoch": 5.84, + "learning_rate": 1.660982861739378e-05, + "loss": 0.1649, + "step": 6600 + }, + { + "epoch": 5.84, + "learning_rate": 1.6608753166684985e-05, + "loss": 0.1458, + "step": 6601 + }, + { + "epoch": 5.84, + "learning_rate": 1.660767758025148e-05, + "loss": 0.1365, + "step": 6602 + }, + { + "epoch": 5.84, + "learning_rate": 1.6606601858115358e-05, + "loss": 0.1598, + "step": 6603 + }, + { + "epoch": 5.84, + "learning_rate": 1.66055260002987e-05, + "loss": 0.1677, + "step": 6604 + }, + { + "epoch": 5.84, + "learning_rate": 1.6604450006823606e-05, + "loss": 0.1747, + "step": 6605 + }, + { + "epoch": 5.85, + "learning_rate": 1.6603373877712176e-05, + "loss": 0.1526, + "step": 6606 + }, + { + "epoch": 5.85, + "learning_rate": 1.6602297612986513e-05, + "loss": 0.1601, + "step": 6607 + }, + { + "epoch": 5.85, + "learning_rate": 1.6601221212668706e-05, + "loss": 0.1599, + "step": 6608 + }, + { + "epoch": 5.85, + "learning_rate": 1.6600144676780878e-05, + "loss": 0.1613, + "step": 6609 + }, + { + "epoch": 5.85, + "learning_rate": 1.6599068005345134e-05, + "loss": 0.1619, + "step": 6610 + }, + { + "epoch": 5.85, + "learning_rate": 1.6597991198383578e-05, + "loss": 0.1578, + "step": 6611 + }, + { + "epoch": 5.85, + "learning_rate": 1.6596914255918332e-05, + "loss": 0.1522, + "step": 6612 + }, + { + "epoch": 5.85, + "learning_rate": 1.659583717797151e-05, + "loss": 0.1539, + "step": 6613 + }, + { + "epoch": 5.85, + "learning_rate": 1.6594759964565237e-05, + "loss": 0.1717, + "step": 6614 + }, + { + "epoch": 5.85, + "learning_rate": 1.6593682615721623e-05, + "loss": 0.1463, + "step": 6615 + }, + { + "epoch": 5.85, + "learning_rate": 1.6592605131462808e-05, + "loss": 0.156, + "step": 6616 + }, + { + "epoch": 5.86, + "learning_rate": 1.659152751181092e-05, + "loss": 0.1543, + "step": 6617 + }, + { + "epoch": 5.86, + "learning_rate": 1.6590449756788075e-05, + "loss": 0.1509, + "step": 6618 + }, + { + "epoch": 5.86, + "learning_rate": 1.6589371866416424e-05, + "loss": 0.1652, + "step": 6619 + }, + { + "epoch": 5.86, + "learning_rate": 1.6588293840718096e-05, + "loss": 0.1432, + "step": 6620 + }, + { + "epoch": 5.86, + "learning_rate": 1.6587215679715226e-05, + "loss": 0.1565, + "step": 6621 + }, + { + "epoch": 5.86, + "learning_rate": 1.6586137383429967e-05, + "loss": 0.1824, + "step": 6622 + }, + { + "epoch": 5.86, + "learning_rate": 1.6585058951884455e-05, + "loss": 0.1537, + "step": 6623 + }, + { + "epoch": 5.86, + "learning_rate": 1.6583980385100847e-05, + "loss": 0.1472, + "step": 6624 + }, + { + "epoch": 5.86, + "learning_rate": 1.6582901683101283e-05, + "loss": 0.1623, + "step": 6625 + }, + { + "epoch": 5.86, + "learning_rate": 1.6581822845907926e-05, + "loss": 0.1621, + "step": 6626 + }, + { + "epoch": 5.86, + "learning_rate": 1.6580743873542923e-05, + "loss": 0.1591, + "step": 6627 + }, + { + "epoch": 5.86, + "learning_rate": 1.657966476602844e-05, + "loss": 0.1614, + "step": 6628 + }, + { + "epoch": 5.87, + "learning_rate": 1.657858552338664e-05, + "loss": 0.1509, + "step": 6629 + }, + { + "epoch": 5.87, + "learning_rate": 1.657750614563968e-05, + "loss": 0.1679, + "step": 6630 + }, + { + "epoch": 5.87, + "learning_rate": 1.657642663280973e-05, + "loss": 0.1695, + "step": 6631 + }, + { + "epoch": 5.87, + "learning_rate": 1.6575346984918964e-05, + "loss": 0.1685, + "step": 6632 + }, + { + "epoch": 5.87, + "learning_rate": 1.6574267201989553e-05, + "loss": 0.1523, + "step": 6633 + }, + { + "epoch": 5.87, + "learning_rate": 1.6573187284043673e-05, + "loss": 0.1477, + "step": 6634 + }, + { + "epoch": 5.87, + "learning_rate": 1.65721072311035e-05, + "loss": 0.1629, + "step": 6635 + }, + { + "epoch": 5.87, + "learning_rate": 1.6571027043191214e-05, + "loss": 0.179, + "step": 6636 + }, + { + "epoch": 5.87, + "learning_rate": 1.6569946720329003e-05, + "loss": 0.1666, + "step": 6637 + }, + { + "epoch": 5.87, + "learning_rate": 1.6568866262539055e-05, + "loss": 0.158, + "step": 6638 + }, + { + "epoch": 5.87, + "learning_rate": 1.6567785669843555e-05, + "loss": 0.1594, + "step": 6639 + }, + { + "epoch": 5.88, + "learning_rate": 1.6566704942264698e-05, + "loss": 0.1535, + "step": 6640 + }, + { + "epoch": 5.88, + "learning_rate": 1.6565624079824675e-05, + "loss": 0.1495, + "step": 6641 + }, + { + "epoch": 5.88, + "learning_rate": 1.6564543082545686e-05, + "loss": 0.1632, + "step": 6642 + }, + { + "epoch": 5.88, + "learning_rate": 1.6563461950449936e-05, + "loss": 0.1718, + "step": 6643 + }, + { + "epoch": 5.88, + "learning_rate": 1.6562380683559625e-05, + "loss": 0.1716, + "step": 6644 + }, + { + "epoch": 5.88, + "learning_rate": 1.6561299281896957e-05, + "loss": 0.1675, + "step": 6645 + }, + { + "epoch": 5.88, + "learning_rate": 1.6560217745484143e-05, + "loss": 0.1605, + "step": 6646 + }, + { + "epoch": 5.88, + "learning_rate": 1.6559136074343395e-05, + "loss": 0.1599, + "step": 6647 + }, + { + "epoch": 5.88, + "learning_rate": 1.6558054268496923e-05, + "loss": 0.1583, + "step": 6648 + }, + { + "epoch": 5.88, + "learning_rate": 1.655697232796695e-05, + "loss": 0.1462, + "step": 6649 + }, + { + "epoch": 5.88, + "learning_rate": 1.6555890252775693e-05, + "loss": 0.1704, + "step": 6650 + }, + { + "epoch": 5.89, + "learning_rate": 1.655480804294538e-05, + "loss": 0.153, + "step": 6651 + }, + { + "epoch": 5.89, + "learning_rate": 1.6553725698498228e-05, + "loss": 0.1627, + "step": 6652 + }, + { + "epoch": 5.89, + "learning_rate": 1.655264321945647e-05, + "loss": 0.1457, + "step": 6653 + }, + { + "epoch": 5.89, + "learning_rate": 1.6551560605842335e-05, + "loss": 0.1597, + "step": 6654 + }, + { + "epoch": 5.89, + "learning_rate": 1.655047785767806e-05, + "loss": 0.1633, + "step": 6655 + }, + { + "epoch": 5.89, + "learning_rate": 1.654939497498588e-05, + "loss": 0.1604, + "step": 6656 + }, + { + "epoch": 5.89, + "learning_rate": 1.6548311957788033e-05, + "loss": 0.1549, + "step": 6657 + }, + { + "epoch": 5.89, + "learning_rate": 1.654722880610676e-05, + "loss": 0.1515, + "step": 6658 + }, + { + "epoch": 5.89, + "learning_rate": 1.654614551996431e-05, + "loss": 0.1743, + "step": 6659 + }, + { + "epoch": 5.89, + "learning_rate": 1.6545062099382926e-05, + "loss": 0.1537, + "step": 6660 + }, + { + "epoch": 5.89, + "learning_rate": 1.654397854438486e-05, + "loss": 0.1657, + "step": 6661 + }, + { + "epoch": 5.89, + "learning_rate": 1.6542894854992368e-05, + "loss": 0.1528, + "step": 6662 + }, + { + "epoch": 5.9, + "learning_rate": 1.65418110312277e-05, + "loss": 0.165, + "step": 6663 + }, + { + "epoch": 5.9, + "learning_rate": 1.6540727073113122e-05, + "loss": 0.1508, + "step": 6664 + }, + { + "epoch": 5.9, + "learning_rate": 1.653964298067089e-05, + "loss": 0.1506, + "step": 6665 + }, + { + "epoch": 5.9, + "learning_rate": 1.6538558753923267e-05, + "loss": 0.1449, + "step": 6666 + }, + { + "epoch": 5.9, + "learning_rate": 1.6537474392892527e-05, + "loss": 0.1615, + "step": 6667 + }, + { + "epoch": 5.9, + "learning_rate": 1.653638989760093e-05, + "loss": 0.1591, + "step": 6668 + }, + { + "epoch": 5.9, + "learning_rate": 1.6535305268070757e-05, + "loss": 0.1654, + "step": 6669 + }, + { + "epoch": 5.9, + "learning_rate": 1.653422050432428e-05, + "loss": 0.1756, + "step": 6670 + }, + { + "epoch": 5.9, + "learning_rate": 1.6533135606383774e-05, + "loss": 0.144, + "step": 6671 + }, + { + "epoch": 5.9, + "learning_rate": 1.6532050574271527e-05, + "loss": 0.1629, + "step": 6672 + }, + { + "epoch": 5.9, + "learning_rate": 1.653096540800981e-05, + "loss": 0.1714, + "step": 6673 + }, + { + "epoch": 5.91, + "learning_rate": 1.6529880107620924e-05, + "loss": 0.184, + "step": 6674 + }, + { + "epoch": 5.91, + "learning_rate": 1.652879467312715e-05, + "loss": 0.1464, + "step": 6675 + }, + { + "epoch": 5.91, + "learning_rate": 1.6527709104550777e-05, + "loss": 0.1552, + "step": 6676 + }, + { + "epoch": 5.91, + "learning_rate": 1.6526623401914103e-05, + "loss": 0.1643, + "step": 6677 + }, + { + "epoch": 5.91, + "learning_rate": 1.6525537565239425e-05, + "loss": 0.1551, + "step": 6678 + }, + { + "epoch": 5.91, + "learning_rate": 1.6524451594549048e-05, + "loss": 0.1676, + "step": 6679 + }, + { + "epoch": 5.91, + "learning_rate": 1.6523365489865265e-05, + "loss": 0.1615, + "step": 6680 + }, + { + "epoch": 5.91, + "learning_rate": 1.6522279251210387e-05, + "loss": 0.167, + "step": 6681 + }, + { + "epoch": 5.91, + "learning_rate": 1.6521192878606722e-05, + "loss": 0.1639, + "step": 6682 + }, + { + "epoch": 5.91, + "learning_rate": 1.652010637207658e-05, + "loss": 0.1641, + "step": 6683 + }, + { + "epoch": 5.91, + "learning_rate": 1.6519019731642277e-05, + "loss": 0.162, + "step": 6684 + }, + { + "epoch": 5.92, + "learning_rate": 1.6517932957326124e-05, + "loss": 0.1562, + "step": 6685 + }, + { + "epoch": 5.92, + "learning_rate": 1.651684604915045e-05, + "loss": 0.1666, + "step": 6686 + }, + { + "epoch": 5.92, + "learning_rate": 1.6515759007137564e-05, + "loss": 0.1559, + "step": 6687 + }, + { + "epoch": 5.92, + "learning_rate": 1.65146718313098e-05, + "loss": 0.1583, + "step": 6688 + }, + { + "epoch": 5.92, + "learning_rate": 1.6513584521689483e-05, + "loss": 0.1697, + "step": 6689 + }, + { + "epoch": 5.92, + "learning_rate": 1.6512497078298943e-05, + "loss": 0.1844, + "step": 6690 + }, + { + "epoch": 5.92, + "learning_rate": 1.651140950116051e-05, + "loss": 0.1542, + "step": 6691 + }, + { + "epoch": 5.92, + "learning_rate": 1.6510321790296527e-05, + "loss": 0.1596, + "step": 6692 + }, + { + "epoch": 5.92, + "learning_rate": 1.650923394572933e-05, + "loss": 0.1602, + "step": 6693 + }, + { + "epoch": 5.92, + "learning_rate": 1.650814596748125e-05, + "loss": 0.1551, + "step": 6694 + }, + { + "epoch": 5.92, + "learning_rate": 1.6507057855574643e-05, + "loss": 0.1648, + "step": 6695 + }, + { + "epoch": 5.92, + "learning_rate": 1.6505969610031854e-05, + "loss": 0.1422, + "step": 6696 + }, + { + "epoch": 5.93, + "learning_rate": 1.650488123087523e-05, + "loss": 0.1537, + "step": 6697 + }, + { + "epoch": 5.93, + "learning_rate": 1.6503792718127124e-05, + "loss": 0.1689, + "step": 6698 + }, + { + "epoch": 5.93, + "learning_rate": 1.650270407180989e-05, + "loss": 0.161, + "step": 6699 + }, + { + "epoch": 5.93, + "learning_rate": 1.6501615291945886e-05, + "loss": 0.1569, + "step": 6700 + }, + { + "epoch": 5.93, + "learning_rate": 1.6500526378557473e-05, + "loss": 0.1604, + "step": 6701 + }, + { + "epoch": 5.93, + "learning_rate": 1.649943733166701e-05, + "loss": 0.1524, + "step": 6702 + }, + { + "epoch": 5.93, + "learning_rate": 1.649834815129687e-05, + "loss": 0.1376, + "step": 6703 + }, + { + "epoch": 5.93, + "learning_rate": 1.6497258837469417e-05, + "loss": 0.1802, + "step": 6704 + }, + { + "epoch": 5.93, + "learning_rate": 1.6496169390207027e-05, + "loss": 0.1616, + "step": 6705 + }, + { + "epoch": 5.93, + "learning_rate": 1.6495079809532068e-05, + "loss": 0.1932, + "step": 6706 + }, + { + "epoch": 5.93, + "learning_rate": 1.6493990095466913e-05, + "loss": 0.1672, + "step": 6707 + }, + { + "epoch": 5.94, + "learning_rate": 1.6492900248033957e-05, + "loss": 0.1726, + "step": 6708 + }, + { + "epoch": 5.94, + "learning_rate": 1.649181026725557e-05, + "loss": 0.1635, + "step": 6709 + }, + { + "epoch": 5.94, + "learning_rate": 1.6490720153154144e-05, + "loss": 0.1667, + "step": 6710 + }, + { + "epoch": 5.94, + "learning_rate": 1.6489629905752054e-05, + "loss": 0.1736, + "step": 6711 + }, + { + "epoch": 5.94, + "learning_rate": 1.648853952507171e-05, + "loss": 0.1619, + "step": 6712 + }, + { + "epoch": 5.94, + "learning_rate": 1.648744901113549e-05, + "loss": 0.1671, + "step": 6713 + }, + { + "epoch": 5.94, + "learning_rate": 1.6486358363965792e-05, + "loss": 0.145, + "step": 6714 + }, + { + "epoch": 5.94, + "learning_rate": 1.6485267583585022e-05, + "loss": 0.1631, + "step": 6715 + }, + { + "epoch": 5.94, + "learning_rate": 1.648417667001558e-05, + "loss": 0.1486, + "step": 6716 + }, + { + "epoch": 5.94, + "learning_rate": 1.648308562327986e-05, + "loss": 0.1608, + "step": 6717 + }, + { + "epoch": 5.94, + "learning_rate": 1.6481994443400283e-05, + "loss": 0.1601, + "step": 6718 + }, + { + "epoch": 5.95, + "learning_rate": 1.648090313039925e-05, + "loss": 0.1631, + "step": 6719 + }, + { + "epoch": 5.95, + "learning_rate": 1.6479811684299173e-05, + "loss": 0.1511, + "step": 6720 + }, + { + "epoch": 5.95, + "learning_rate": 1.647872010512247e-05, + "loss": 0.1756, + "step": 6721 + }, + { + "epoch": 5.95, + "learning_rate": 1.6477628392891563e-05, + "loss": 0.1718, + "step": 6722 + }, + { + "epoch": 5.95, + "learning_rate": 1.6476536547628866e-05, + "loss": 0.1434, + "step": 6723 + }, + { + "epoch": 5.95, + "learning_rate": 1.6475444569356806e-05, + "loss": 0.1669, + "step": 6724 + }, + { + "epoch": 5.95, + "learning_rate": 1.6474352458097805e-05, + "loss": 0.1599, + "step": 6725 + }, + { + "epoch": 5.95, + "learning_rate": 1.6473260213874292e-05, + "loss": 0.1636, + "step": 6726 + }, + { + "epoch": 5.95, + "learning_rate": 1.6472167836708704e-05, + "loss": 0.1609, + "step": 6727 + }, + { + "epoch": 5.95, + "learning_rate": 1.6471075326623474e-05, + "loss": 0.165, + "step": 6728 + }, + { + "epoch": 5.95, + "learning_rate": 1.6469982683641034e-05, + "loss": 0.1529, + "step": 6729 + }, + { + "epoch": 5.95, + "learning_rate": 1.6468889907783828e-05, + "loss": 0.179, + "step": 6730 + }, + { + "epoch": 5.96, + "learning_rate": 1.6467796999074298e-05, + "loss": 0.1597, + "step": 6731 + }, + { + "epoch": 5.96, + "learning_rate": 1.6466703957534888e-05, + "loss": 0.1538, + "step": 6732 + }, + { + "epoch": 5.96, + "learning_rate": 1.6465610783188047e-05, + "loss": 0.1598, + "step": 6733 + }, + { + "epoch": 5.96, + "learning_rate": 1.6464517476056224e-05, + "loss": 0.1695, + "step": 6734 + }, + { + "epoch": 5.96, + "learning_rate": 1.6463424036161874e-05, + "loss": 0.182, + "step": 6735 + }, + { + "epoch": 5.96, + "learning_rate": 1.6462330463527452e-05, + "loss": 0.1747, + "step": 6736 + }, + { + "epoch": 5.96, + "learning_rate": 1.646123675817542e-05, + "loss": 0.1492, + "step": 6737 + }, + { + "epoch": 5.96, + "learning_rate": 1.6460142920128238e-05, + "loss": 0.149, + "step": 6738 + }, + { + "epoch": 5.96, + "learning_rate": 1.6459048949408365e-05, + "loss": 0.1624, + "step": 6739 + }, + { + "epoch": 5.96, + "learning_rate": 1.6457954846038275e-05, + "loss": 0.1679, + "step": 6740 + }, + { + "epoch": 5.96, + "learning_rate": 1.6456860610040432e-05, + "loss": 0.1651, + "step": 6741 + }, + { + "epoch": 5.97, + "learning_rate": 1.6455766241437315e-05, + "loss": 0.1625, + "step": 6742 + }, + { + "epoch": 5.97, + "learning_rate": 1.6454671740251394e-05, + "loss": 0.1575, + "step": 6743 + }, + { + "epoch": 5.97, + "learning_rate": 1.645357710650515e-05, + "loss": 0.1708, + "step": 6744 + }, + { + "epoch": 5.97, + "learning_rate": 1.6452482340221062e-05, + "loss": 0.1885, + "step": 6745 + }, + { + "epoch": 5.97, + "learning_rate": 1.6451387441421613e-05, + "loss": 0.1631, + "step": 6746 + }, + { + "epoch": 5.97, + "learning_rate": 1.6450292410129286e-05, + "loss": 0.1573, + "step": 6747 + }, + { + "epoch": 5.97, + "learning_rate": 1.6449197246366577e-05, + "loss": 0.1611, + "step": 6748 + }, + { + "epoch": 5.97, + "learning_rate": 1.644810195015597e-05, + "loss": 0.1754, + "step": 6749 + }, + { + "epoch": 5.97, + "learning_rate": 1.6447006521519968e-05, + "loss": 0.1475, + "step": 6750 + }, + { + "epoch": 5.97, + "learning_rate": 1.6445910960481063e-05, + "loss": 0.1619, + "step": 6751 + }, + { + "epoch": 5.97, + "learning_rate": 1.644481526706175e-05, + "loss": 0.1492, + "step": 6752 + }, + { + "epoch": 5.98, + "learning_rate": 1.6443719441284543e-05, + "loss": 0.1534, + "step": 6753 + }, + { + "epoch": 5.98, + "learning_rate": 1.6442623483171934e-05, + "loss": 0.1497, + "step": 6754 + }, + { + "epoch": 5.98, + "learning_rate": 1.644152739274644e-05, + "loss": 0.1518, + "step": 6755 + }, + { + "epoch": 5.98, + "learning_rate": 1.6440431170030566e-05, + "loss": 0.148, + "step": 6756 + }, + { + "epoch": 5.98, + "learning_rate": 1.643933481504683e-05, + "loss": 0.1555, + "step": 6757 + }, + { + "epoch": 5.98, + "learning_rate": 1.6438238327817744e-05, + "loss": 0.1601, + "step": 6758 + }, + { + "epoch": 5.98, + "learning_rate": 1.6437141708365828e-05, + "loss": 0.1549, + "step": 6759 + }, + { + "epoch": 5.98, + "learning_rate": 1.6436044956713607e-05, + "loss": 0.1562, + "step": 6760 + }, + { + "epoch": 5.98, + "learning_rate": 1.64349480728836e-05, + "loss": 0.1574, + "step": 6761 + }, + { + "epoch": 5.98, + "learning_rate": 1.6433851056898335e-05, + "loss": 0.1598, + "step": 6762 + }, + { + "epoch": 5.98, + "learning_rate": 1.6432753908780342e-05, + "loss": 0.155, + "step": 6763 + }, + { + "epoch": 5.99, + "learning_rate": 1.6431656628552156e-05, + "loss": 0.1661, + "step": 6764 + }, + { + "epoch": 5.99, + "learning_rate": 1.643055921623631e-05, + "loss": 0.1673, + "step": 6765 + }, + { + "epoch": 5.99, + "learning_rate": 1.642946167185534e-05, + "loss": 0.1503, + "step": 6766 + }, + { + "epoch": 5.99, + "learning_rate": 1.6428363995431784e-05, + "loss": 0.1547, + "step": 6767 + }, + { + "epoch": 5.99, + "learning_rate": 1.642726618698819e-05, + "loss": 0.1523, + "step": 6768 + }, + { + "epoch": 5.99, + "learning_rate": 1.6426168246547104e-05, + "loss": 0.1512, + "step": 6769 + }, + { + "epoch": 5.99, + "learning_rate": 1.6425070174131073e-05, + "loss": 0.1618, + "step": 6770 + }, + { + "epoch": 5.99, + "learning_rate": 1.6423971969762652e-05, + "loss": 0.1537, + "step": 6771 + }, + { + "epoch": 5.99, + "learning_rate": 1.6422873633464385e-05, + "loss": 0.1598, + "step": 6772 + }, + { + "epoch": 5.99, + "learning_rate": 1.6421775165258836e-05, + "loss": 0.1616, + "step": 6773 + }, + { + "epoch": 5.99, + "learning_rate": 1.6420676565168566e-05, + "loss": 0.163, + "step": 6774 + }, + { + "epoch": 5.99, + "learning_rate": 1.641957783321613e-05, + "loss": 0.1693, + "step": 6775 + }, + { + "epoch": 6.0, + "learning_rate": 1.64184789694241e-05, + "loss": 0.1624, + "step": 6776 + }, + { + "epoch": 6.0, + "learning_rate": 1.6417379973815042e-05, + "loss": 0.166, + "step": 6777 + }, + { + "epoch": 6.0, + "learning_rate": 1.6416280846411523e-05, + "loss": 0.1698, + "step": 6778 + }, + { + "epoch": 6.0, + "learning_rate": 1.6415181587236117e-05, + "loss": 0.1648, + "step": 6779 + }, + { + "epoch": 6.0, + "learning_rate": 1.6414082196311402e-05, + "loss": 0.1404, + "step": 6780 + }, + { + "epoch": 6.0, + "learning_rate": 1.641298267365995e-05, + "loss": 0.1384, + "step": 6781 + }, + { + "epoch": 6.0, + "learning_rate": 1.6411883019304353e-05, + "loss": 0.0881, + "step": 6782 + }, + { + "epoch": 6.0, + "learning_rate": 1.6410783233267184e-05, + "loss": 0.0887, + "step": 6783 + }, + { + "epoch": 6.0, + "learning_rate": 1.6409683315571035e-05, + "loss": 0.0814, + "step": 6784 + }, + { + "epoch": 6.0, + "learning_rate": 1.6408583266238496e-05, + "loss": 0.0848, + "step": 6785 + }, + { + "epoch": 6.0, + "learning_rate": 1.6407483085292154e-05, + "loss": 0.0824, + "step": 6786 + }, + { + "epoch": 6.01, + "learning_rate": 1.640638277275461e-05, + "loss": 0.0869, + "step": 6787 + }, + { + "epoch": 6.01, + "learning_rate": 1.640528232864845e-05, + "loss": 0.0893, + "step": 6788 + }, + { + "epoch": 6.01, + "learning_rate": 1.6404181752996287e-05, + "loss": 0.0861, + "step": 6789 + }, + { + "epoch": 6.01, + "learning_rate": 1.640308104582072e-05, + "loss": 0.0953, + "step": 6790 + }, + { + "epoch": 6.01, + "learning_rate": 1.640198020714435e-05, + "loss": 0.0882, + "step": 6791 + }, + { + "epoch": 6.01, + "learning_rate": 1.6400879236989786e-05, + "loss": 0.0948, + "step": 6792 + }, + { + "epoch": 6.01, + "learning_rate": 1.639977813537964e-05, + "loss": 0.074, + "step": 6793 + }, + { + "epoch": 6.01, + "learning_rate": 1.639867690233653e-05, + "loss": 0.0777, + "step": 6794 + }, + { + "epoch": 6.01, + "learning_rate": 1.6397575537883064e-05, + "loss": 0.0857, + "step": 6795 + }, + { + "epoch": 6.01, + "learning_rate": 1.6396474042041867e-05, + "loss": 0.078, + "step": 6796 + }, + { + "epoch": 6.01, + "learning_rate": 1.6395372414835557e-05, + "loss": 0.089, + "step": 6797 + }, + { + "epoch": 6.02, + "learning_rate": 1.639427065628676e-05, + "loss": 0.0782, + "step": 6798 + }, + { + "epoch": 6.02, + "learning_rate": 1.63931687664181e-05, + "loss": 0.0898, + "step": 6799 + }, + { + "epoch": 6.02, + "learning_rate": 1.6392066745252213e-05, + "loss": 0.0789, + "step": 6800 + }, + { + "epoch": 6.02, + "learning_rate": 1.6390964592811723e-05, + "loss": 0.0842, + "step": 6801 + }, + { + "epoch": 6.02, + "learning_rate": 1.6389862309119273e-05, + "loss": 0.0851, + "step": 6802 + }, + { + "epoch": 6.02, + "learning_rate": 1.6388759894197496e-05, + "loss": 0.0792, + "step": 6803 + }, + { + "epoch": 6.02, + "learning_rate": 1.6387657348069035e-05, + "loss": 0.0734, + "step": 6804 + }, + { + "epoch": 6.02, + "learning_rate": 1.638655467075653e-05, + "loss": 0.08, + "step": 6805 + }, + { + "epoch": 6.02, + "learning_rate": 1.6385451862282627e-05, + "loss": 0.0861, + "step": 6806 + }, + { + "epoch": 6.02, + "learning_rate": 1.638434892266998e-05, + "loss": 0.0861, + "step": 6807 + }, + { + "epoch": 6.02, + "learning_rate": 1.6383245851941235e-05, + "loss": 0.0731, + "step": 6808 + }, + { + "epoch": 6.02, + "learning_rate": 1.6382142650119043e-05, + "loss": 0.0895, + "step": 6809 + }, + { + "epoch": 6.03, + "learning_rate": 1.6381039317226068e-05, + "loss": 0.0772, + "step": 6810 + }, + { + "epoch": 6.03, + "learning_rate": 1.6379935853284966e-05, + "loss": 0.0768, + "step": 6811 + }, + { + "epoch": 6.03, + "learning_rate": 1.63788322583184e-05, + "loss": 0.0812, + "step": 6812 + }, + { + "epoch": 6.03, + "learning_rate": 1.6377728532349034e-05, + "loss": 0.0893, + "step": 6813 + }, + { + "epoch": 6.03, + "learning_rate": 1.637662467539953e-05, + "loss": 0.0795, + "step": 6814 + }, + { + "epoch": 6.03, + "learning_rate": 1.6375520687492568e-05, + "loss": 0.0811, + "step": 6815 + }, + { + "epoch": 6.03, + "learning_rate": 1.6374416568650813e-05, + "loss": 0.0991, + "step": 6816 + }, + { + "epoch": 6.03, + "learning_rate": 1.6373312318896945e-05, + "loss": 0.0988, + "step": 6817 + }, + { + "epoch": 6.03, + "learning_rate": 1.6372207938253637e-05, + "loss": 0.0795, + "step": 6818 + }, + { + "epoch": 6.03, + "learning_rate": 1.6371103426743576e-05, + "loss": 0.0837, + "step": 6819 + }, + { + "epoch": 6.03, + "learning_rate": 1.6369998784389442e-05, + "loss": 0.0892, + "step": 6820 + }, + { + "epoch": 6.04, + "learning_rate": 1.6368894011213922e-05, + "loss": 0.0777, + "step": 6821 + }, + { + "epoch": 6.04, + "learning_rate": 1.6367789107239703e-05, + "loss": 0.0761, + "step": 6822 + }, + { + "epoch": 6.04, + "learning_rate": 1.636668407248948e-05, + "loss": 0.0771, + "step": 6823 + }, + { + "epoch": 6.04, + "learning_rate": 1.636557890698594e-05, + "loss": 0.0828, + "step": 6824 + }, + { + "epoch": 6.04, + "learning_rate": 1.636447361075179e-05, + "loss": 0.0804, + "step": 6825 + }, + { + "epoch": 6.04, + "learning_rate": 1.6363368183809723e-05, + "loss": 0.0802, + "step": 6826 + }, + { + "epoch": 6.04, + "learning_rate": 1.6362262626182442e-05, + "loss": 0.0831, + "step": 6827 + }, + { + "epoch": 6.04, + "learning_rate": 1.636115693789266e-05, + "loss": 0.0848, + "step": 6828 + }, + { + "epoch": 6.04, + "learning_rate": 1.636005111896307e-05, + "loss": 0.0892, + "step": 6829 + }, + { + "epoch": 6.04, + "learning_rate": 1.635894516941639e-05, + "loss": 0.0805, + "step": 6830 + }, + { + "epoch": 6.04, + "learning_rate": 1.6357839089275336e-05, + "loss": 0.09, + "step": 6831 + }, + { + "epoch": 6.05, + "learning_rate": 1.635673287856262e-05, + "loss": 0.0817, + "step": 6832 + }, + { + "epoch": 6.05, + "learning_rate": 1.635562653730096e-05, + "loss": 0.0915, + "step": 6833 + }, + { + "epoch": 6.05, + "learning_rate": 1.635452006551308e-05, + "loss": 0.0874, + "step": 6834 + }, + { + "epoch": 6.05, + "learning_rate": 1.6353413463221703e-05, + "loss": 0.0838, + "step": 6835 + }, + { + "epoch": 6.05, + "learning_rate": 1.635230673044955e-05, + "loss": 0.0792, + "step": 6836 + }, + { + "epoch": 6.05, + "learning_rate": 1.6351199867219353e-05, + "loss": 0.0826, + "step": 6837 + }, + { + "epoch": 6.05, + "learning_rate": 1.635009287355385e-05, + "loss": 0.0813, + "step": 6838 + }, + { + "epoch": 6.05, + "learning_rate": 1.634898574947577e-05, + "loss": 0.0925, + "step": 6839 + }, + { + "epoch": 6.05, + "learning_rate": 1.634787849500785e-05, + "loss": 0.0847, + "step": 6840 + }, + { + "epoch": 6.05, + "learning_rate": 1.634677111017283e-05, + "loss": 0.0856, + "step": 6841 + }, + { + "epoch": 6.05, + "learning_rate": 1.6345663594993453e-05, + "loss": 0.08, + "step": 6842 + }, + { + "epoch": 6.05, + "learning_rate": 1.6344555949492464e-05, + "loss": 0.0849, + "step": 6843 + }, + { + "epoch": 6.06, + "learning_rate": 1.634344817369261e-05, + "loss": 0.0833, + "step": 6844 + }, + { + "epoch": 6.06, + "learning_rate": 1.634234026761664e-05, + "loss": 0.0796, + "step": 6845 + }, + { + "epoch": 6.06, + "learning_rate": 1.634123223128732e-05, + "loss": 0.0923, + "step": 6846 + }, + { + "epoch": 6.06, + "learning_rate": 1.6340124064727387e-05, + "loss": 0.0993, + "step": 6847 + }, + { + "epoch": 6.06, + "learning_rate": 1.633901576795961e-05, + "loss": 0.0805, + "step": 6848 + }, + { + "epoch": 6.06, + "learning_rate": 1.6337907341006748e-05, + "loss": 0.0948, + "step": 6849 + }, + { + "epoch": 6.06, + "learning_rate": 1.6336798783891564e-05, + "loss": 0.0913, + "step": 6850 + }, + { + "epoch": 6.06, + "learning_rate": 1.633569009663683e-05, + "loss": 0.085, + "step": 6851 + }, + { + "epoch": 6.06, + "learning_rate": 1.633458127926531e-05, + "loss": 0.089, + "step": 6852 + }, + { + "epoch": 6.06, + "learning_rate": 1.6333472331799772e-05, + "loss": 0.09, + "step": 6853 + }, + { + "epoch": 6.06, + "learning_rate": 1.6332363254263e-05, + "loss": 0.0901, + "step": 6854 + }, + { + "epoch": 6.07, + "learning_rate": 1.6331254046677768e-05, + "loss": 0.0798, + "step": 6855 + }, + { + "epoch": 6.07, + "learning_rate": 1.633014470906685e-05, + "loss": 0.0765, + "step": 6856 + }, + { + "epoch": 6.07, + "learning_rate": 1.6329035241453035e-05, + "loss": 0.088, + "step": 6857 + }, + { + "epoch": 6.07, + "learning_rate": 1.632792564385911e-05, + "loss": 0.0901, + "step": 6858 + }, + { + "epoch": 6.07, + "learning_rate": 1.6326815916307857e-05, + "loss": 0.0752, + "step": 6859 + }, + { + "epoch": 6.07, + "learning_rate": 1.6325706058822066e-05, + "loss": 0.0826, + "step": 6860 + }, + { + "epoch": 6.07, + "learning_rate": 1.6324596071424537e-05, + "loss": 0.081, + "step": 6861 + }, + { + "epoch": 6.07, + "learning_rate": 1.6323485954138064e-05, + "loss": 0.0903, + "step": 6862 + }, + { + "epoch": 6.07, + "learning_rate": 1.6322375706985438e-05, + "loss": 0.0696, + "step": 6863 + }, + { + "epoch": 6.07, + "learning_rate": 1.6321265329989467e-05, + "loss": 0.0809, + "step": 6864 + }, + { + "epoch": 6.07, + "learning_rate": 1.6320154823172962e-05, + "loss": 0.0787, + "step": 6865 + }, + { + "epoch": 6.08, + "learning_rate": 1.6319044186558713e-05, + "loss": 0.0774, + "step": 6866 + }, + { + "epoch": 6.08, + "learning_rate": 1.6317933420169544e-05, + "loss": 0.0749, + "step": 6867 + }, + { + "epoch": 6.08, + "learning_rate": 1.6316822524028255e-05, + "loss": 0.0891, + "step": 6868 + }, + { + "epoch": 6.08, + "learning_rate": 1.631571149815767e-05, + "loss": 0.0832, + "step": 6869 + }, + { + "epoch": 6.08, + "learning_rate": 1.6314600342580603e-05, + "loss": 0.0938, + "step": 6870 + }, + { + "epoch": 6.08, + "learning_rate": 1.6313489057319874e-05, + "loss": 0.0863, + "step": 6871 + }, + { + "epoch": 6.08, + "learning_rate": 1.6312377642398302e-05, + "loss": 0.093, + "step": 6872 + }, + { + "epoch": 6.08, + "learning_rate": 1.6311266097838717e-05, + "loss": 0.0862, + "step": 6873 + }, + { + "epoch": 6.08, + "learning_rate": 1.6310154423663948e-05, + "loss": 0.076, + "step": 6874 + }, + { + "epoch": 6.08, + "learning_rate": 1.630904261989682e-05, + "loss": 0.0873, + "step": 6875 + }, + { + "epoch": 6.08, + "learning_rate": 1.6307930686560172e-05, + "loss": 0.0808, + "step": 6876 + }, + { + "epoch": 6.09, + "learning_rate": 1.6306818623676838e-05, + "loss": 0.0834, + "step": 6877 + }, + { + "epoch": 6.09, + "learning_rate": 1.630570643126965e-05, + "loss": 0.071, + "step": 6878 + }, + { + "epoch": 6.09, + "learning_rate": 1.6304594109361457e-05, + "loss": 0.0766, + "step": 6879 + }, + { + "epoch": 6.09, + "learning_rate": 1.6303481657975104e-05, + "loss": 0.0839, + "step": 6880 + }, + { + "epoch": 6.09, + "learning_rate": 1.6302369077133433e-05, + "loss": 0.0828, + "step": 6881 + }, + { + "epoch": 6.09, + "learning_rate": 1.6301256366859296e-05, + "loss": 0.0849, + "step": 6882 + }, + { + "epoch": 6.09, + "learning_rate": 1.630014352717554e-05, + "loss": 0.0889, + "step": 6883 + }, + { + "epoch": 6.09, + "learning_rate": 1.629903055810502e-05, + "loss": 0.0889, + "step": 6884 + }, + { + "epoch": 6.09, + "learning_rate": 1.6297917459670606e-05, + "loss": 0.0899, + "step": 6885 + }, + { + "epoch": 6.09, + "learning_rate": 1.629680423189514e-05, + "loss": 0.0875, + "step": 6886 + }, + { + "epoch": 6.09, + "learning_rate": 1.6295690874801496e-05, + "loss": 0.0818, + "step": 6887 + }, + { + "epoch": 6.09, + "learning_rate": 1.6294577388412537e-05, + "loss": 0.0813, + "step": 6888 + }, + { + "epoch": 6.1, + "learning_rate": 1.6293463772751124e-05, + "loss": 0.073, + "step": 6889 + }, + { + "epoch": 6.1, + "learning_rate": 1.6292350027840137e-05, + "loss": 0.0724, + "step": 6890 + }, + { + "epoch": 6.1, + "learning_rate": 1.6291236153702442e-05, + "loss": 0.0944, + "step": 6891 + }, + { + "epoch": 6.1, + "learning_rate": 1.629012215036092e-05, + "loss": 0.0914, + "step": 6892 + }, + { + "epoch": 6.1, + "learning_rate": 1.6289008017838447e-05, + "loss": 0.0725, + "step": 6893 + }, + { + "epoch": 6.1, + "learning_rate": 1.6287893756157904e-05, + "loss": 0.0836, + "step": 6894 + }, + { + "epoch": 6.1, + "learning_rate": 1.6286779365342177e-05, + "loss": 0.0791, + "step": 6895 + }, + { + "epoch": 6.1, + "learning_rate": 1.6285664845414146e-05, + "loss": 0.0813, + "step": 6896 + }, + { + "epoch": 6.1, + "learning_rate": 1.62845501963967e-05, + "loss": 0.0812, + "step": 6897 + }, + { + "epoch": 6.1, + "learning_rate": 1.6283435418312743e-05, + "loss": 0.0816, + "step": 6898 + }, + { + "epoch": 6.1, + "learning_rate": 1.6282320511185163e-05, + "loss": 0.0794, + "step": 6899 + }, + { + "epoch": 6.11, + "learning_rate": 1.628120547503685e-05, + "loss": 0.082, + "step": 6900 + }, + { + "epoch": 6.11, + "learning_rate": 1.628009030989071e-05, + "loss": 0.091, + "step": 6901 + }, + { + "epoch": 6.11, + "learning_rate": 1.6278975015769645e-05, + "loss": 0.0819, + "step": 6902 + }, + { + "epoch": 6.11, + "learning_rate": 1.6277859592696556e-05, + "loss": 0.0787, + "step": 6903 + }, + { + "epoch": 6.11, + "learning_rate": 1.6276744040694356e-05, + "loss": 0.0897, + "step": 6904 + }, + { + "epoch": 6.11, + "learning_rate": 1.6275628359785956e-05, + "loss": 0.0951, + "step": 6905 + }, + { + "epoch": 6.11, + "learning_rate": 1.6274512549994262e-05, + "loss": 0.0814, + "step": 6906 + }, + { + "epoch": 6.11, + "learning_rate": 1.6273396611342192e-05, + "loss": 0.0841, + "step": 6907 + }, + { + "epoch": 6.11, + "learning_rate": 1.627228054385267e-05, + "loss": 0.0915, + "step": 6908 + }, + { + "epoch": 6.11, + "learning_rate": 1.627116434754861e-05, + "loss": 0.0732, + "step": 6909 + }, + { + "epoch": 6.11, + "learning_rate": 1.6270048022452932e-05, + "loss": 0.0877, + "step": 6910 + }, + { + "epoch": 6.12, + "learning_rate": 1.6268931568588576e-05, + "loss": 0.0851, + "step": 6911 + }, + { + "epoch": 6.12, + "learning_rate": 1.6267814985978462e-05, + "loss": 0.0848, + "step": 6912 + }, + { + "epoch": 6.12, + "learning_rate": 1.626669827464552e-05, + "loss": 0.0911, + "step": 6913 + }, + { + "epoch": 6.12, + "learning_rate": 1.626558143461268e-05, + "loss": 0.0812, + "step": 6914 + }, + { + "epoch": 6.12, + "learning_rate": 1.6264464465902888e-05, + "loss": 0.075, + "step": 6915 + }, + { + "epoch": 6.12, + "learning_rate": 1.6263347368539084e-05, + "loss": 0.09, + "step": 6916 + }, + { + "epoch": 6.12, + "learning_rate": 1.6262230142544204e-05, + "loss": 0.0799, + "step": 6917 + }, + { + "epoch": 6.12, + "learning_rate": 1.6261112787941193e-05, + "loss": 0.0786, + "step": 6918 + }, + { + "epoch": 6.12, + "learning_rate": 1.6259995304753e-05, + "loss": 0.0798, + "step": 6919 + }, + { + "epoch": 6.12, + "learning_rate": 1.6258877693002576e-05, + "loss": 0.085, + "step": 6920 + }, + { + "epoch": 6.12, + "learning_rate": 1.6257759952712874e-05, + "loss": 0.0925, + "step": 6921 + }, + { + "epoch": 6.12, + "learning_rate": 1.625664208390684e-05, + "loss": 0.0894, + "step": 6922 + }, + { + "epoch": 6.13, + "learning_rate": 1.6255524086607445e-05, + "loss": 0.085, + "step": 6923 + }, + { + "epoch": 6.13, + "learning_rate": 1.625440596083764e-05, + "loss": 0.08, + "step": 6924 + }, + { + "epoch": 6.13, + "learning_rate": 1.6253287706620394e-05, + "loss": 0.0824, + "step": 6925 + }, + { + "epoch": 6.13, + "learning_rate": 1.625216932397867e-05, + "loss": 0.0872, + "step": 6926 + }, + { + "epoch": 6.13, + "learning_rate": 1.6251050812935437e-05, + "loss": 0.0913, + "step": 6927 + }, + { + "epoch": 6.13, + "learning_rate": 1.6249932173513662e-05, + "loss": 0.0824, + "step": 6928 + }, + { + "epoch": 6.13, + "learning_rate": 1.6248813405736322e-05, + "loss": 0.088, + "step": 6929 + }, + { + "epoch": 6.13, + "learning_rate": 1.62476945096264e-05, + "loss": 0.0838, + "step": 6930 + }, + { + "epoch": 6.13, + "learning_rate": 1.6246575485206862e-05, + "loss": 0.0883, + "step": 6931 + }, + { + "epoch": 6.13, + "learning_rate": 1.62454563325007e-05, + "loss": 0.0805, + "step": 6932 + }, + { + "epoch": 6.13, + "learning_rate": 1.6244337051530893e-05, + "loss": 0.0857, + "step": 6933 + }, + { + "epoch": 6.14, + "learning_rate": 1.624321764232043e-05, + "loss": 0.0878, + "step": 6934 + }, + { + "epoch": 6.14, + "learning_rate": 1.6242098104892297e-05, + "loss": 0.0824, + "step": 6935 + }, + { + "epoch": 6.14, + "learning_rate": 1.6240978439269486e-05, + "loss": 0.0797, + "step": 6936 + }, + { + "epoch": 6.14, + "learning_rate": 1.6239858645474998e-05, + "loss": 0.0705, + "step": 6937 + }, + { + "epoch": 6.14, + "learning_rate": 1.6238738723531825e-05, + "loss": 0.0751, + "step": 6938 + }, + { + "epoch": 6.14, + "learning_rate": 1.6237618673462972e-05, + "loss": 0.0795, + "step": 6939 + }, + { + "epoch": 6.14, + "learning_rate": 1.6236498495291434e-05, + "loss": 0.093, + "step": 6940 + }, + { + "epoch": 6.14, + "learning_rate": 1.6235378189040217e-05, + "loss": 0.0832, + "step": 6941 + }, + { + "epoch": 6.14, + "learning_rate": 1.623425775473234e-05, + "loss": 0.0834, + "step": 6942 + }, + { + "epoch": 6.14, + "learning_rate": 1.62331371923908e-05, + "loss": 0.0903, + "step": 6943 + }, + { + "epoch": 6.14, + "learning_rate": 1.6232016502038617e-05, + "loss": 0.0788, + "step": 6944 + }, + { + "epoch": 6.15, + "learning_rate": 1.6230895683698805e-05, + "loss": 0.0935, + "step": 6945 + }, + { + "epoch": 6.15, + "learning_rate": 1.6229774737394382e-05, + "loss": 0.0939, + "step": 6946 + }, + { + "epoch": 6.15, + "learning_rate": 1.6228653663148373e-05, + "loss": 0.0855, + "step": 6947 + }, + { + "epoch": 6.15, + "learning_rate": 1.6227532460983795e-05, + "loss": 0.0889, + "step": 6948 + }, + { + "epoch": 6.15, + "learning_rate": 1.6226411130923678e-05, + "loss": 0.0856, + "step": 6949 + }, + { + "epoch": 6.15, + "learning_rate": 1.6225289672991053e-05, + "loss": 0.0856, + "step": 6950 + }, + { + "epoch": 6.15, + "learning_rate": 1.6224168087208946e-05, + "loss": 0.0765, + "step": 6951 + }, + { + "epoch": 6.15, + "learning_rate": 1.6223046373600398e-05, + "loss": 0.0885, + "step": 6952 + }, + { + "epoch": 6.15, + "learning_rate": 1.622192453218844e-05, + "loss": 0.0768, + "step": 6953 + }, + { + "epoch": 6.15, + "learning_rate": 1.622080256299611e-05, + "loss": 0.0961, + "step": 6954 + }, + { + "epoch": 6.15, + "learning_rate": 1.6219680466046457e-05, + "loss": 0.0892, + "step": 6955 + }, + { + "epoch": 6.15, + "learning_rate": 1.6218558241362522e-05, + "loss": 0.0805, + "step": 6956 + }, + { + "epoch": 6.16, + "learning_rate": 1.621743588896735e-05, + "loss": 0.089, + "step": 6957 + }, + { + "epoch": 6.16, + "learning_rate": 1.6216313408883995e-05, + "loss": 0.0713, + "step": 6958 + }, + { + "epoch": 6.16, + "learning_rate": 1.6215190801135508e-05, + "loss": 0.077, + "step": 6959 + }, + { + "epoch": 6.16, + "learning_rate": 1.6214068065744943e-05, + "loss": 0.087, + "step": 6960 + }, + { + "epoch": 6.16, + "learning_rate": 1.621294520273536e-05, + "loss": 0.0855, + "step": 6961 + }, + { + "epoch": 6.16, + "learning_rate": 1.621182221212981e-05, + "loss": 0.0904, + "step": 6962 + }, + { + "epoch": 6.16, + "learning_rate": 1.621069909395137e-05, + "loss": 0.0952, + "step": 6963 + }, + { + "epoch": 6.16, + "learning_rate": 1.62095758482231e-05, + "loss": 0.0901, + "step": 6964 + }, + { + "epoch": 6.16, + "learning_rate": 1.6208452474968068e-05, + "loss": 0.0874, + "step": 6965 + }, + { + "epoch": 6.16, + "learning_rate": 1.6207328974209343e-05, + "loss": 0.0809, + "step": 6966 + }, + { + "epoch": 6.16, + "learning_rate": 1.6206205345970002e-05, + "loss": 0.0975, + "step": 6967 + }, + { + "epoch": 6.17, + "learning_rate": 1.6205081590273113e-05, + "loss": 0.08, + "step": 6968 + }, + { + "epoch": 6.17, + "learning_rate": 1.6203957707141765e-05, + "loss": 0.0942, + "step": 6969 + }, + { + "epoch": 6.17, + "learning_rate": 1.6202833696599036e-05, + "loss": 0.0846, + "step": 6970 + }, + { + "epoch": 6.17, + "learning_rate": 1.620170955866801e-05, + "loss": 0.0806, + "step": 6971 + }, + { + "epoch": 6.17, + "learning_rate": 1.620058529337177e-05, + "loss": 0.0897, + "step": 6972 + }, + { + "epoch": 6.17, + "learning_rate": 1.6199460900733407e-05, + "loss": 0.0876, + "step": 6973 + }, + { + "epoch": 6.17, + "learning_rate": 1.6198336380776013e-05, + "loss": 0.0775, + "step": 6974 + }, + { + "epoch": 6.17, + "learning_rate": 1.6197211733522683e-05, + "loss": 0.0834, + "step": 6975 + }, + { + "epoch": 6.17, + "learning_rate": 1.6196086958996517e-05, + "loss": 0.0794, + "step": 6976 + }, + { + "epoch": 6.17, + "learning_rate": 1.619496205722061e-05, + "loss": 0.0809, + "step": 6977 + }, + { + "epoch": 6.17, + "learning_rate": 1.6193837028218064e-05, + "loss": 0.0876, + "step": 6978 + }, + { + "epoch": 6.18, + "learning_rate": 1.6192711872011988e-05, + "loss": 0.0835, + "step": 6979 + }, + { + "epoch": 6.18, + "learning_rate": 1.6191586588625487e-05, + "loss": 0.0909, + "step": 6980 + }, + { + "epoch": 6.18, + "learning_rate": 1.6190461178081667e-05, + "loss": 0.0922, + "step": 6981 + }, + { + "epoch": 6.18, + "learning_rate": 1.618933564040365e-05, + "loss": 0.0882, + "step": 6982 + }, + { + "epoch": 6.18, + "learning_rate": 1.618820997561454e-05, + "loss": 0.0877, + "step": 6983 + }, + { + "epoch": 6.18, + "learning_rate": 1.6187084183737468e-05, + "loss": 0.0908, + "step": 6984 + }, + { + "epoch": 6.18, + "learning_rate": 1.6185958264795543e-05, + "loss": 0.0912, + "step": 6985 + }, + { + "epoch": 6.18, + "learning_rate": 1.6184832218811896e-05, + "loss": 0.0875, + "step": 6986 + }, + { + "epoch": 6.18, + "learning_rate": 1.6183706045809644e-05, + "loss": 0.0765, + "step": 6987 + }, + { + "epoch": 6.18, + "learning_rate": 1.6182579745811923e-05, + "loss": 0.0913, + "step": 6988 + }, + { + "epoch": 6.18, + "learning_rate": 1.6181453318841862e-05, + "loss": 0.088, + "step": 6989 + }, + { + "epoch": 6.18, + "learning_rate": 1.6180326764922596e-05, + "loss": 0.0826, + "step": 6990 + }, + { + "epoch": 6.19, + "learning_rate": 1.617920008407726e-05, + "loss": 0.0734, + "step": 6991 + }, + { + "epoch": 6.19, + "learning_rate": 1.6178073276328988e-05, + "loss": 0.0806, + "step": 6992 + }, + { + "epoch": 6.19, + "learning_rate": 1.6176946341700928e-05, + "loss": 0.0856, + "step": 6993 + }, + { + "epoch": 6.19, + "learning_rate": 1.617581928021622e-05, + "loss": 0.0898, + "step": 6994 + }, + { + "epoch": 6.19, + "learning_rate": 1.6174692091898014e-05, + "loss": 0.0897, + "step": 6995 + }, + { + "epoch": 6.19, + "learning_rate": 1.6173564776769455e-05, + "loss": 0.0813, + "step": 6996 + }, + { + "epoch": 6.19, + "learning_rate": 1.61724373348537e-05, + "loss": 0.086, + "step": 6997 + }, + { + "epoch": 6.19, + "learning_rate": 1.6171309766173898e-05, + "loss": 0.0854, + "step": 6998 + }, + { + "epoch": 6.19, + "learning_rate": 1.6170182070753208e-05, + "loss": 0.0847, + "step": 6999 + }, + { + "epoch": 6.19, + "learning_rate": 1.6169054248614793e-05, + "loss": 0.072, + "step": 7000 + }, + { + "epoch": 6.19, + "learning_rate": 1.6167926299781812e-05, + "loss": 0.0905, + "step": 7001 + }, + { + "epoch": 6.2, + "learning_rate": 1.6166798224277428e-05, + "loss": 0.0874, + "step": 7002 + }, + { + "epoch": 6.2, + "learning_rate": 1.6165670022124814e-05, + "loss": 0.0902, + "step": 7003 + }, + { + "epoch": 6.2, + "learning_rate": 1.616454169334713e-05, + "loss": 0.0789, + "step": 7004 + }, + { + "epoch": 6.2, + "learning_rate": 1.616341323796756e-05, + "loss": 0.0843, + "step": 7005 + }, + { + "epoch": 6.2, + "learning_rate": 1.6162284656009276e-05, + "loss": 0.094, + "step": 7006 + }, + { + "epoch": 6.2, + "learning_rate": 1.616115594749545e-05, + "loss": 0.0858, + "step": 7007 + }, + { + "epoch": 6.2, + "learning_rate": 1.6160027112449267e-05, + "loss": 0.0792, + "step": 7008 + }, + { + "epoch": 6.2, + "learning_rate": 1.6158898150893915e-05, + "loss": 0.0824, + "step": 7009 + }, + { + "epoch": 6.2, + "learning_rate": 1.6157769062852567e-05, + "loss": 0.0786, + "step": 7010 + }, + { + "epoch": 6.2, + "learning_rate": 1.6156639848348424e-05, + "loss": 0.0875, + "step": 7011 + }, + { + "epoch": 6.2, + "learning_rate": 1.6155510507404667e-05, + "loss": 0.0814, + "step": 7012 + }, + { + "epoch": 6.21, + "learning_rate": 1.6154381040044493e-05, + "loss": 0.084, + "step": 7013 + }, + { + "epoch": 6.21, + "learning_rate": 1.6153251446291105e-05, + "loss": 0.0748, + "step": 7014 + }, + { + "epoch": 6.21, + "learning_rate": 1.615212172616769e-05, + "loss": 0.0905, + "step": 7015 + }, + { + "epoch": 6.21, + "learning_rate": 1.6150991879697455e-05, + "loss": 0.0821, + "step": 7016 + }, + { + "epoch": 6.21, + "learning_rate": 1.6149861906903607e-05, + "loss": 0.0724, + "step": 7017 + }, + { + "epoch": 6.21, + "learning_rate": 1.6148731807809347e-05, + "loss": 0.0859, + "step": 7018 + }, + { + "epoch": 6.21, + "learning_rate": 1.6147601582437883e-05, + "loss": 0.0859, + "step": 7019 + }, + { + "epoch": 6.21, + "learning_rate": 1.614647123081243e-05, + "loss": 0.0846, + "step": 7020 + }, + { + "epoch": 6.21, + "learning_rate": 1.61453407529562e-05, + "loss": 0.087, + "step": 7021 + }, + { + "epoch": 6.21, + "learning_rate": 1.614421014889241e-05, + "loss": 0.082, + "step": 7022 + }, + { + "epoch": 6.21, + "learning_rate": 1.6143079418644286e-05, + "loss": 0.0788, + "step": 7023 + }, + { + "epoch": 6.22, + "learning_rate": 1.6141948562235042e-05, + "loss": 0.0863, + "step": 7024 + }, + { + "epoch": 6.22, + "learning_rate": 1.6140817579687905e-05, + "loss": 0.0882, + "step": 7025 + }, + { + "epoch": 6.22, + "learning_rate": 1.61396864710261e-05, + "loss": 0.087, + "step": 7026 + }, + { + "epoch": 6.22, + "learning_rate": 1.613855523627286e-05, + "loss": 0.0842, + "step": 7027 + }, + { + "epoch": 6.22, + "learning_rate": 1.6137423875451416e-05, + "loss": 0.0777, + "step": 7028 + }, + { + "epoch": 6.22, + "learning_rate": 1.6136292388585002e-05, + "loss": 0.0777, + "step": 7029 + }, + { + "epoch": 6.22, + "learning_rate": 1.6135160775696857e-05, + "loss": 0.0729, + "step": 7030 + }, + { + "epoch": 6.22, + "learning_rate": 1.613402903681022e-05, + "loss": 0.0921, + "step": 7031 + }, + { + "epoch": 6.22, + "learning_rate": 1.6132897171948337e-05, + "loss": 0.0909, + "step": 7032 + }, + { + "epoch": 6.22, + "learning_rate": 1.6131765181134443e-05, + "loss": 0.0827, + "step": 7033 + }, + { + "epoch": 6.22, + "learning_rate": 1.6130633064391802e-05, + "loss": 0.0856, + "step": 7034 + }, + { + "epoch": 6.22, + "learning_rate": 1.612950082174365e-05, + "loss": 0.0904, + "step": 7035 + }, + { + "epoch": 6.23, + "learning_rate": 1.6128368453213248e-05, + "loss": 0.0847, + "step": 7036 + }, + { + "epoch": 6.23, + "learning_rate": 1.6127235958823847e-05, + "loss": 0.0904, + "step": 7037 + }, + { + "epoch": 6.23, + "learning_rate": 1.612610333859871e-05, + "loss": 0.0865, + "step": 7038 + }, + { + "epoch": 6.23, + "learning_rate": 1.6124970592561092e-05, + "loss": 0.0821, + "step": 7039 + }, + { + "epoch": 6.23, + "learning_rate": 1.612383772073426e-05, + "loss": 0.088, + "step": 7040 + }, + { + "epoch": 6.23, + "learning_rate": 1.6122704723141482e-05, + "loss": 0.0798, + "step": 7041 + }, + { + "epoch": 6.23, + "learning_rate": 1.612157159980602e-05, + "loss": 0.0802, + "step": 7042 + }, + { + "epoch": 6.23, + "learning_rate": 1.6120438350751152e-05, + "loss": 0.0872, + "step": 7043 + }, + { + "epoch": 6.23, + "learning_rate": 1.611930497600015e-05, + "loss": 0.0764, + "step": 7044 + }, + { + "epoch": 6.23, + "learning_rate": 1.6118171475576282e-05, + "loss": 0.081, + "step": 7045 + }, + { + "epoch": 6.23, + "learning_rate": 1.6117037849502834e-05, + "loss": 0.0873, + "step": 7046 + }, + { + "epoch": 6.24, + "learning_rate": 1.6115904097803093e-05, + "loss": 0.0782, + "step": 7047 + }, + { + "epoch": 6.24, + "learning_rate": 1.6114770220500333e-05, + "loss": 0.0924, + "step": 7048 + }, + { + "epoch": 6.24, + "learning_rate": 1.6113636217617848e-05, + "loss": 0.08, + "step": 7049 + }, + { + "epoch": 6.24, + "learning_rate": 1.611250208917892e-05, + "loss": 0.0808, + "step": 7050 + }, + { + "epoch": 6.24, + "learning_rate": 1.6111367835206845e-05, + "loss": 0.0917, + "step": 7051 + }, + { + "epoch": 6.24, + "learning_rate": 1.611023345572492e-05, + "loss": 0.092, + "step": 7052 + }, + { + "epoch": 6.24, + "learning_rate": 1.6109098950756434e-05, + "loss": 0.0861, + "step": 7053 + }, + { + "epoch": 6.24, + "learning_rate": 1.6107964320324693e-05, + "loss": 0.0836, + "step": 7054 + }, + { + "epoch": 6.24, + "learning_rate": 1.6106829564452997e-05, + "loss": 0.0777, + "step": 7055 + }, + { + "epoch": 6.24, + "learning_rate": 1.6105694683164653e-05, + "loss": 0.0918, + "step": 7056 + }, + { + "epoch": 6.24, + "learning_rate": 1.610455967648296e-05, + "loss": 0.0825, + "step": 7057 + }, + { + "epoch": 6.25, + "learning_rate": 1.610342454443124e-05, + "loss": 0.1027, + "step": 7058 + }, + { + "epoch": 6.25, + "learning_rate": 1.6102289287032794e-05, + "loss": 0.0957, + "step": 7059 + }, + { + "epoch": 6.25, + "learning_rate": 1.6101153904310947e-05, + "loss": 0.0907, + "step": 7060 + }, + { + "epoch": 6.25, + "learning_rate": 1.6100018396289007e-05, + "loss": 0.0826, + "step": 7061 + }, + { + "epoch": 6.25, + "learning_rate": 1.60988827629903e-05, + "loss": 0.0789, + "step": 7062 + }, + { + "epoch": 6.25, + "learning_rate": 1.609774700443815e-05, + "loss": 0.0778, + "step": 7063 + }, + { + "epoch": 6.25, + "learning_rate": 1.6096611120655877e-05, + "loss": 0.0876, + "step": 7064 + }, + { + "epoch": 6.25, + "learning_rate": 1.6095475111666807e-05, + "loss": 0.0851, + "step": 7065 + }, + { + "epoch": 6.25, + "learning_rate": 1.609433897749428e-05, + "loss": 0.0935, + "step": 7066 + }, + { + "epoch": 6.25, + "learning_rate": 1.609320271816162e-05, + "loss": 0.0973, + "step": 7067 + }, + { + "epoch": 6.25, + "learning_rate": 1.609206633369217e-05, + "loss": 0.0834, + "step": 7068 + }, + { + "epoch": 6.25, + "learning_rate": 1.6090929824109256e-05, + "loss": 0.0802, + "step": 7069 + }, + { + "epoch": 6.26, + "learning_rate": 1.6089793189436232e-05, + "loss": 0.0841, + "step": 7070 + }, + { + "epoch": 6.26, + "learning_rate": 1.6088656429696436e-05, + "loss": 0.0906, + "step": 7071 + }, + { + "epoch": 6.26, + "learning_rate": 1.6087519544913212e-05, + "loss": 0.0981, + "step": 7072 + }, + { + "epoch": 6.26, + "learning_rate": 1.608638253510991e-05, + "loss": 0.0847, + "step": 7073 + }, + { + "epoch": 6.26, + "learning_rate": 1.608524540030988e-05, + "loss": 0.0823, + "step": 7074 + }, + { + "epoch": 6.26, + "learning_rate": 1.6084108140536477e-05, + "loss": 0.0824, + "step": 7075 + }, + { + "epoch": 6.26, + "learning_rate": 1.6082970755813055e-05, + "loss": 0.0841, + "step": 7076 + }, + { + "epoch": 6.26, + "learning_rate": 1.6081833246162973e-05, + "loss": 0.0773, + "step": 7077 + }, + { + "epoch": 6.26, + "learning_rate": 1.6080695611609596e-05, + "loss": 0.0894, + "step": 7078 + }, + { + "epoch": 6.26, + "learning_rate": 1.6079557852176284e-05, + "loss": 0.083, + "step": 7079 + }, + { + "epoch": 6.26, + "learning_rate": 1.6078419967886402e-05, + "loss": 0.0809, + "step": 7080 + }, + { + "epoch": 6.27, + "learning_rate": 1.6077281958763323e-05, + "loss": 0.0888, + "step": 7081 + }, + { + "epoch": 6.27, + "learning_rate": 1.6076143824830416e-05, + "loss": 0.0851, + "step": 7082 + }, + { + "epoch": 6.27, + "learning_rate": 1.6075005566111053e-05, + "loss": 0.0864, + "step": 7083 + }, + { + "epoch": 6.27, + "learning_rate": 1.6073867182628613e-05, + "loss": 0.0826, + "step": 7084 + }, + { + "epoch": 6.27, + "learning_rate": 1.6072728674406473e-05, + "loss": 0.086, + "step": 7085 + }, + { + "epoch": 6.27, + "learning_rate": 1.6071590041468022e-05, + "loss": 0.1047, + "step": 7086 + }, + { + "epoch": 6.27, + "learning_rate": 1.6070451283836638e-05, + "loss": 0.0907, + "step": 7087 + }, + { + "epoch": 6.27, + "learning_rate": 1.6069312401535703e-05, + "loss": 0.0777, + "step": 7088 + }, + { + "epoch": 6.27, + "learning_rate": 1.606817339458862e-05, + "loss": 0.0817, + "step": 7089 + }, + { + "epoch": 6.27, + "learning_rate": 1.6067034263018767e-05, + "loss": 0.0852, + "step": 7090 + }, + { + "epoch": 6.27, + "learning_rate": 1.6065895006849547e-05, + "loss": 0.0942, + "step": 7091 + }, + { + "epoch": 6.28, + "learning_rate": 1.6064755626104348e-05, + "loss": 0.0898, + "step": 7092 + }, + { + "epoch": 6.28, + "learning_rate": 1.6063616120806584e-05, + "loss": 0.0885, + "step": 7093 + }, + { + "epoch": 6.28, + "learning_rate": 1.6062476490979644e-05, + "loss": 0.0886, + "step": 7094 + }, + { + "epoch": 6.28, + "learning_rate": 1.6061336736646943e-05, + "loss": 0.0846, + "step": 7095 + }, + { + "epoch": 6.28, + "learning_rate": 1.606019685783188e-05, + "loss": 0.0884, + "step": 7096 + }, + { + "epoch": 6.28, + "learning_rate": 1.6059056854557866e-05, + "loss": 0.0942, + "step": 7097 + }, + { + "epoch": 6.28, + "learning_rate": 1.6057916726848314e-05, + "loss": 0.0868, + "step": 7098 + }, + { + "epoch": 6.28, + "learning_rate": 1.6056776474726645e-05, + "loss": 0.0734, + "step": 7099 + }, + { + "epoch": 6.28, + "learning_rate": 1.6055636098216273e-05, + "loss": 0.0931, + "step": 7100 + }, + { + "epoch": 6.28, + "learning_rate": 1.605449559734061e-05, + "loss": 0.0813, + "step": 7101 + }, + { + "epoch": 6.28, + "learning_rate": 1.605335497212309e-05, + "loss": 0.0756, + "step": 7102 + }, + { + "epoch": 6.28, + "learning_rate": 1.6052214222587133e-05, + "loss": 0.085, + "step": 7103 + }, + { + "epoch": 6.29, + "learning_rate": 1.6051073348756166e-05, + "loss": 0.0842, + "step": 7104 + }, + { + "epoch": 6.29, + "learning_rate": 1.604993235065362e-05, + "loss": 0.0825, + "step": 7105 + }, + { + "epoch": 6.29, + "learning_rate": 1.6048791228302928e-05, + "loss": 0.0865, + "step": 7106 + }, + { + "epoch": 6.29, + "learning_rate": 1.604764998172753e-05, + "loss": 0.0932, + "step": 7107 + }, + { + "epoch": 6.29, + "learning_rate": 1.6046508610950856e-05, + "loss": 0.0872, + "step": 7108 + }, + { + "epoch": 6.29, + "learning_rate": 1.6045367115996348e-05, + "loss": 0.0821, + "step": 7109 + }, + { + "epoch": 6.29, + "learning_rate": 1.6044225496887453e-05, + "loss": 0.0858, + "step": 7110 + }, + { + "epoch": 6.29, + "learning_rate": 1.604308375364761e-05, + "loss": 0.0868, + "step": 7111 + }, + { + "epoch": 6.29, + "learning_rate": 1.604194188630028e-05, + "loss": 0.0777, + "step": 7112 + }, + { + "epoch": 6.29, + "learning_rate": 1.60407998948689e-05, + "loss": 0.0767, + "step": 7113 + }, + { + "epoch": 6.29, + "learning_rate": 1.603965777937693e-05, + "loss": 0.0845, + "step": 7114 + }, + { + "epoch": 6.3, + "learning_rate": 1.6038515539847826e-05, + "loss": 0.074, + "step": 7115 + }, + { + "epoch": 6.3, + "learning_rate": 1.6037373176305042e-05, + "loss": 0.0731, + "step": 7116 + }, + { + "epoch": 6.3, + "learning_rate": 1.6036230688772044e-05, + "loss": 0.0899, + "step": 7117 + }, + { + "epoch": 6.3, + "learning_rate": 1.603508807727229e-05, + "loss": 0.0892, + "step": 7118 + }, + { + "epoch": 6.3, + "learning_rate": 1.603394534182925e-05, + "loss": 0.0904, + "step": 7119 + }, + { + "epoch": 6.3, + "learning_rate": 1.6032802482466388e-05, + "loss": 0.0715, + "step": 7120 + }, + { + "epoch": 6.3, + "learning_rate": 1.603165949920718e-05, + "loss": 0.0856, + "step": 7121 + }, + { + "epoch": 6.3, + "learning_rate": 1.60305163920751e-05, + "loss": 0.0963, + "step": 7122 + }, + { + "epoch": 6.3, + "learning_rate": 1.602937316109362e-05, + "loss": 0.081, + "step": 7123 + }, + { + "epoch": 6.3, + "learning_rate": 1.6028229806286223e-05, + "loss": 0.0797, + "step": 7124 + }, + { + "epoch": 6.3, + "learning_rate": 1.6027086327676386e-05, + "loss": 0.0782, + "step": 7125 + }, + { + "epoch": 6.31, + "learning_rate": 1.6025942725287594e-05, + "loss": 0.0862, + "step": 7126 + }, + { + "epoch": 6.31, + "learning_rate": 1.6024798999143335e-05, + "loss": 0.0854, + "step": 7127 + }, + { + "epoch": 6.31, + "learning_rate": 1.6023655149267098e-05, + "loss": 0.09, + "step": 7128 + }, + { + "epoch": 6.31, + "learning_rate": 1.602251117568237e-05, + "loss": 0.0878, + "step": 7129 + }, + { + "epoch": 6.31, + "learning_rate": 1.602136707841265e-05, + "loss": 0.0895, + "step": 7130 + }, + { + "epoch": 6.31, + "learning_rate": 1.602022285748143e-05, + "loss": 0.0917, + "step": 7131 + }, + { + "epoch": 6.31, + "learning_rate": 1.6019078512912213e-05, + "loss": 0.0853, + "step": 7132 + }, + { + "epoch": 6.31, + "learning_rate": 1.60179340447285e-05, + "loss": 0.0845, + "step": 7133 + }, + { + "epoch": 6.31, + "learning_rate": 1.6016789452953795e-05, + "loss": 0.0928, + "step": 7134 + }, + { + "epoch": 6.31, + "learning_rate": 1.60156447376116e-05, + "loss": 0.0936, + "step": 7135 + }, + { + "epoch": 6.31, + "learning_rate": 1.601449989872543e-05, + "loss": 0.0958, + "step": 7136 + }, + { + "epoch": 6.32, + "learning_rate": 1.601335493631879e-05, + "loss": 0.08, + "step": 7137 + }, + { + "epoch": 6.32, + "learning_rate": 1.6012209850415204e-05, + "loss": 0.0834, + "step": 7138 + }, + { + "epoch": 6.32, + "learning_rate": 1.601106464103818e-05, + "loss": 0.0844, + "step": 7139 + }, + { + "epoch": 6.32, + "learning_rate": 1.6009919308211247e-05, + "loss": 0.0965, + "step": 7140 + }, + { + "epoch": 6.32, + "learning_rate": 1.600877385195792e-05, + "loss": 0.0874, + "step": 7141 + }, + { + "epoch": 6.32, + "learning_rate": 1.600762827230172e-05, + "loss": 0.0805, + "step": 7142 + }, + { + "epoch": 6.32, + "learning_rate": 1.600648256926618e-05, + "loss": 0.0934, + "step": 7143 + }, + { + "epoch": 6.32, + "learning_rate": 1.6005336742874823e-05, + "loss": 0.0957, + "step": 7144 + }, + { + "epoch": 6.32, + "learning_rate": 1.6004190793151187e-05, + "loss": 0.0789, + "step": 7145 + }, + { + "epoch": 6.32, + "learning_rate": 1.600304472011881e-05, + "loss": 0.0884, + "step": 7146 + }, + { + "epoch": 6.32, + "learning_rate": 1.6001898523801215e-05, + "loss": 0.0901, + "step": 7147 + }, + { + "epoch": 6.32, + "learning_rate": 1.6000752204221957e-05, + "loss": 0.0833, + "step": 7148 + }, + { + "epoch": 6.33, + "learning_rate": 1.599960576140457e-05, + "loss": 0.0881, + "step": 7149 + }, + { + "epoch": 6.33, + "learning_rate": 1.59984591953726e-05, + "loss": 0.0995, + "step": 7150 + }, + { + "epoch": 6.33, + "learning_rate": 1.5997312506149592e-05, + "loss": 0.0854, + "step": 7151 + }, + { + "epoch": 6.33, + "learning_rate": 1.5996165693759102e-05, + "loss": 0.0888, + "step": 7152 + }, + { + "epoch": 6.33, + "learning_rate": 1.599501875822467e-05, + "loss": 0.0794, + "step": 7153 + }, + { + "epoch": 6.33, + "learning_rate": 1.5993871699569868e-05, + "loss": 0.0725, + "step": 7154 + }, + { + "epoch": 6.33, + "learning_rate": 1.599272451781824e-05, + "loss": 0.0789, + "step": 7155 + }, + { + "epoch": 6.33, + "learning_rate": 1.599157721299335e-05, + "loss": 0.0867, + "step": 7156 + }, + { + "epoch": 6.33, + "learning_rate": 1.5990429785118764e-05, + "loss": 0.0819, + "step": 7157 + }, + { + "epoch": 6.33, + "learning_rate": 1.5989282234218037e-05, + "loss": 0.0913, + "step": 7158 + }, + { + "epoch": 6.33, + "learning_rate": 1.5988134560314748e-05, + "loss": 0.0825, + "step": 7159 + }, + { + "epoch": 6.34, + "learning_rate": 1.598698676343246e-05, + "loss": 0.093, + "step": 7160 + }, + { + "epoch": 6.34, + "learning_rate": 1.5985838843594745e-05, + "loss": 0.0822, + "step": 7161 + }, + { + "epoch": 6.34, + "learning_rate": 1.598469080082518e-05, + "loss": 0.0885, + "step": 7162 + }, + { + "epoch": 6.34, + "learning_rate": 1.5983542635147342e-05, + "loss": 0.076, + "step": 7163 + }, + { + "epoch": 6.34, + "learning_rate": 1.5982394346584813e-05, + "loss": 0.089, + "step": 7164 + }, + { + "epoch": 6.34, + "learning_rate": 1.5981245935161174e-05, + "loss": 0.0834, + "step": 7165 + }, + { + "epoch": 6.34, + "learning_rate": 1.598009740090001e-05, + "loss": 0.0811, + "step": 7166 + }, + { + "epoch": 6.34, + "learning_rate": 1.597894874382491e-05, + "loss": 0.0924, + "step": 7167 + }, + { + "epoch": 6.34, + "learning_rate": 1.5977799963959458e-05, + "loss": 0.088, + "step": 7168 + }, + { + "epoch": 6.34, + "learning_rate": 1.5976651061327254e-05, + "loss": 0.0934, + "step": 7169 + }, + { + "epoch": 6.34, + "learning_rate": 1.597550203595189e-05, + "loss": 0.0836, + "step": 7170 + }, + { + "epoch": 6.35, + "learning_rate": 1.5974352887856963e-05, + "loss": 0.0954, + "step": 7171 + }, + { + "epoch": 6.35, + "learning_rate": 1.5973203617066073e-05, + "loss": 0.0815, + "step": 7172 + }, + { + "epoch": 6.35, + "learning_rate": 1.5972054223602827e-05, + "loss": 0.0873, + "step": 7173 + }, + { + "epoch": 6.35, + "learning_rate": 1.5970904707490826e-05, + "loss": 0.0953, + "step": 7174 + }, + { + "epoch": 6.35, + "learning_rate": 1.5969755068753682e-05, + "loss": 0.0818, + "step": 7175 + }, + { + "epoch": 6.35, + "learning_rate": 1.5968605307414994e-05, + "loss": 0.0856, + "step": 7176 + }, + { + "epoch": 6.35, + "learning_rate": 1.5967455423498387e-05, + "loss": 0.0804, + "step": 7177 + }, + { + "epoch": 6.35, + "learning_rate": 1.5966305417027473e-05, + "loss": 0.0847, + "step": 7178 + }, + { + "epoch": 6.35, + "learning_rate": 1.5965155288025874e-05, + "loss": 0.0897, + "step": 7179 + }, + { + "epoch": 6.35, + "learning_rate": 1.59640050365172e-05, + "loss": 0.0854, + "step": 7180 + }, + { + "epoch": 6.35, + "learning_rate": 1.596285466252508e-05, + "loss": 0.0901, + "step": 7181 + }, + { + "epoch": 6.35, + "learning_rate": 1.5961704166073136e-05, + "loss": 0.0912, + "step": 7182 + }, + { + "epoch": 6.36, + "learning_rate": 1.5960553547185e-05, + "loss": 0.0908, + "step": 7183 + }, + { + "epoch": 6.36, + "learning_rate": 1.59594028058843e-05, + "loss": 0.093, + "step": 7184 + }, + { + "epoch": 6.36, + "learning_rate": 1.5958251942194675e-05, + "loss": 0.0869, + "step": 7185 + }, + { + "epoch": 6.36, + "learning_rate": 1.595710095613975e-05, + "loss": 0.0834, + "step": 7186 + }, + { + "epoch": 6.36, + "learning_rate": 1.595594984774317e-05, + "loss": 0.0951, + "step": 7187 + }, + { + "epoch": 6.36, + "learning_rate": 1.5954798617028573e-05, + "loss": 0.0999, + "step": 7188 + }, + { + "epoch": 6.36, + "learning_rate": 1.59536472640196e-05, + "loss": 0.0899, + "step": 7189 + }, + { + "epoch": 6.36, + "learning_rate": 1.5952495788739902e-05, + "loss": 0.0974, + "step": 7190 + }, + { + "epoch": 6.36, + "learning_rate": 1.5951344191213122e-05, + "loss": 0.0867, + "step": 7191 + }, + { + "epoch": 6.36, + "learning_rate": 1.5950192471462916e-05, + "loss": 0.098, + "step": 7192 + }, + { + "epoch": 6.36, + "learning_rate": 1.594904062951293e-05, + "loss": 0.0825, + "step": 7193 + }, + { + "epoch": 6.37, + "learning_rate": 1.5947888665386827e-05, + "loss": 0.0954, + "step": 7194 + }, + { + "epoch": 6.37, + "learning_rate": 1.5946736579108257e-05, + "loss": 0.1046, + "step": 7195 + }, + { + "epoch": 6.37, + "learning_rate": 1.5945584370700884e-05, + "loss": 0.0823, + "step": 7196 + }, + { + "epoch": 6.37, + "learning_rate": 1.5944432040188373e-05, + "loss": 0.0803, + "step": 7197 + }, + { + "epoch": 6.37, + "learning_rate": 1.594327958759439e-05, + "loss": 0.0888, + "step": 7198 + }, + { + "epoch": 6.37, + "learning_rate": 1.5942127012942597e-05, + "loss": 0.0814, + "step": 7199 + }, + { + "epoch": 6.37, + "learning_rate": 1.594097431625667e-05, + "loss": 0.0908, + "step": 7200 + }, + { + "epoch": 6.37, + "learning_rate": 1.5939821497560282e-05, + "loss": 0.0798, + "step": 7201 + }, + { + "epoch": 6.37, + "learning_rate": 1.5938668556877105e-05, + "loss": 0.0886, + "step": 7202 + }, + { + "epoch": 6.37, + "learning_rate": 1.5937515494230818e-05, + "loss": 0.0881, + "step": 7203 + }, + { + "epoch": 6.37, + "learning_rate": 1.593636230964511e-05, + "loss": 0.0884, + "step": 7204 + }, + { + "epoch": 6.38, + "learning_rate": 1.5935209003143652e-05, + "loss": 0.095, + "step": 7205 + }, + { + "epoch": 6.38, + "learning_rate": 1.5934055574750135e-05, + "loss": 0.0994, + "step": 7206 + }, + { + "epoch": 6.38, + "learning_rate": 1.5932902024488244e-05, + "loss": 0.0959, + "step": 7207 + }, + { + "epoch": 6.38, + "learning_rate": 1.593174835238168e-05, + "loss": 0.0893, + "step": 7208 + }, + { + "epoch": 6.38, + "learning_rate": 1.593059455845412e-05, + "loss": 0.0909, + "step": 7209 + }, + { + "epoch": 6.38, + "learning_rate": 1.592944064272927e-05, + "loss": 0.0889, + "step": 7210 + }, + { + "epoch": 6.38, + "learning_rate": 1.592828660523083e-05, + "loss": 0.0811, + "step": 7211 + }, + { + "epoch": 6.38, + "learning_rate": 1.5927132445982497e-05, + "loss": 0.0996, + "step": 7212 + }, + { + "epoch": 6.38, + "learning_rate": 1.592597816500797e-05, + "loss": 0.0848, + "step": 7213 + }, + { + "epoch": 6.38, + "learning_rate": 1.592482376233096e-05, + "loss": 0.0922, + "step": 7214 + }, + { + "epoch": 6.38, + "learning_rate": 1.592366923797517e-05, + "loss": 0.0988, + "step": 7215 + }, + { + "epoch": 6.38, + "learning_rate": 1.5922514591964317e-05, + "loss": 0.0862, + "step": 7216 + }, + { + "epoch": 6.39, + "learning_rate": 1.5921359824322114e-05, + "loss": 0.0772, + "step": 7217 + }, + { + "epoch": 6.39, + "learning_rate": 1.592020493507227e-05, + "loss": 0.0853, + "step": 7218 + }, + { + "epoch": 6.39, + "learning_rate": 1.5919049924238508e-05, + "loss": 0.0991, + "step": 7219 + }, + { + "epoch": 6.39, + "learning_rate": 1.591789479184455e-05, + "loss": 0.09, + "step": 7220 + }, + { + "epoch": 6.39, + "learning_rate": 1.591673953791411e-05, + "loss": 0.082, + "step": 7221 + }, + { + "epoch": 6.39, + "learning_rate": 1.5915584162470925e-05, + "loss": 0.0889, + "step": 7222 + }, + { + "epoch": 6.39, + "learning_rate": 1.5914428665538718e-05, + "loss": 0.083, + "step": 7223 + }, + { + "epoch": 6.39, + "learning_rate": 1.5913273047141217e-05, + "loss": 0.0845, + "step": 7224 + }, + { + "epoch": 6.39, + "learning_rate": 1.591211730730216e-05, + "loss": 0.0738, + "step": 7225 + }, + { + "epoch": 6.39, + "learning_rate": 1.5910961446045277e-05, + "loss": 0.0864, + "step": 7226 + }, + { + "epoch": 6.39, + "learning_rate": 1.5909805463394316e-05, + "loss": 0.0923, + "step": 7227 + }, + { + "epoch": 6.4, + "learning_rate": 1.5908649359373006e-05, + "loss": 0.0877, + "step": 7228 + }, + { + "epoch": 6.4, + "learning_rate": 1.5907493134005095e-05, + "loss": 0.0805, + "step": 7229 + }, + { + "epoch": 6.4, + "learning_rate": 1.5906336787314328e-05, + "loss": 0.0891, + "step": 7230 + }, + { + "epoch": 6.4, + "learning_rate": 1.590518031932446e-05, + "loss": 0.0933, + "step": 7231 + }, + { + "epoch": 6.4, + "learning_rate": 1.5904023730059227e-05, + "loss": 0.0775, + "step": 7232 + }, + { + "epoch": 6.4, + "learning_rate": 1.5902867019542395e-05, + "loss": 0.0754, + "step": 7233 + }, + { + "epoch": 6.4, + "learning_rate": 1.5901710187797716e-05, + "loss": 0.0843, + "step": 7234 + }, + { + "epoch": 6.4, + "learning_rate": 1.590055323484894e-05, + "loss": 0.0868, + "step": 7235 + }, + { + "epoch": 6.4, + "learning_rate": 1.5899396160719834e-05, + "loss": 0.0995, + "step": 7236 + }, + { + "epoch": 6.4, + "learning_rate": 1.589823896543417e-05, + "loss": 0.0859, + "step": 7237 + }, + { + "epoch": 6.4, + "learning_rate": 1.5897081649015698e-05, + "loss": 0.0818, + "step": 7238 + }, + { + "epoch": 6.41, + "learning_rate": 1.5895924211488193e-05, + "loss": 0.0803, + "step": 7239 + }, + { + "epoch": 6.41, + "learning_rate": 1.5894766652875424e-05, + "loss": 0.0924, + "step": 7240 + }, + { + "epoch": 6.41, + "learning_rate": 1.5893608973201166e-05, + "loss": 0.0837, + "step": 7241 + }, + { + "epoch": 6.41, + "learning_rate": 1.5892451172489193e-05, + "loss": 0.0898, + "step": 7242 + }, + { + "epoch": 6.41, + "learning_rate": 1.5891293250763283e-05, + "loss": 0.0706, + "step": 7243 + }, + { + "epoch": 6.41, + "learning_rate": 1.5890135208047217e-05, + "loss": 0.0796, + "step": 7244 + }, + { + "epoch": 6.41, + "learning_rate": 1.5888977044364774e-05, + "loss": 0.0894, + "step": 7245 + }, + { + "epoch": 6.41, + "learning_rate": 1.5887818759739747e-05, + "loss": 0.0835, + "step": 7246 + }, + { + "epoch": 6.41, + "learning_rate": 1.5886660354195916e-05, + "loss": 0.0784, + "step": 7247 + }, + { + "epoch": 6.41, + "learning_rate": 1.5885501827757078e-05, + "loss": 0.0784, + "step": 7248 + }, + { + "epoch": 6.41, + "learning_rate": 1.588434318044702e-05, + "loss": 0.0751, + "step": 7249 + }, + { + "epoch": 6.41, + "learning_rate": 1.588318441228954e-05, + "loss": 0.0912, + "step": 7250 + }, + { + "epoch": 6.42, + "learning_rate": 1.5882025523308437e-05, + "loss": 0.0883, + "step": 7251 + }, + { + "epoch": 6.42, + "learning_rate": 1.588086651352751e-05, + "loss": 0.0774, + "step": 7252 + }, + { + "epoch": 6.42, + "learning_rate": 1.587970738297056e-05, + "loss": 0.0898, + "step": 7253 + }, + { + "epoch": 6.42, + "learning_rate": 1.587854813166139e-05, + "loss": 0.086, + "step": 7254 + }, + { + "epoch": 6.42, + "learning_rate": 1.5877388759623818e-05, + "loss": 0.0866, + "step": 7255 + }, + { + "epoch": 6.42, + "learning_rate": 1.587622926688164e-05, + "loss": 0.0849, + "step": 7256 + }, + { + "epoch": 6.42, + "learning_rate": 1.5875069653458687e-05, + "loss": 0.0836, + "step": 7257 + }, + { + "epoch": 6.42, + "learning_rate": 1.5873909919378755e-05, + "loss": 0.0821, + "step": 7258 + }, + { + "epoch": 6.42, + "learning_rate": 1.587275006466567e-05, + "loss": 0.0854, + "step": 7259 + }, + { + "epoch": 6.42, + "learning_rate": 1.5871590089343255e-05, + "loss": 0.0815, + "step": 7260 + }, + { + "epoch": 6.42, + "learning_rate": 1.5870429993435327e-05, + "loss": 0.0812, + "step": 7261 + }, + { + "epoch": 6.43, + "learning_rate": 1.5869269776965714e-05, + "loss": 0.0962, + "step": 7262 + }, + { + "epoch": 6.43, + "learning_rate": 1.5868109439958246e-05, + "loss": 0.081, + "step": 7263 + }, + { + "epoch": 6.43, + "learning_rate": 1.5866948982436748e-05, + "loss": 0.0777, + "step": 7264 + }, + { + "epoch": 6.43, + "learning_rate": 1.5865788404425053e-05, + "loss": 0.0923, + "step": 7265 + }, + { + "epoch": 6.43, + "learning_rate": 1.5864627705946997e-05, + "loss": 0.0815, + "step": 7266 + }, + { + "epoch": 6.43, + "learning_rate": 1.586346688702642e-05, + "loss": 0.0822, + "step": 7267 + }, + { + "epoch": 6.43, + "learning_rate": 1.5862305947687156e-05, + "loss": 0.0851, + "step": 7268 + }, + { + "epoch": 6.43, + "learning_rate": 1.5861144887953055e-05, + "loss": 0.081, + "step": 7269 + }, + { + "epoch": 6.43, + "learning_rate": 1.5859983707847955e-05, + "loss": 0.075, + "step": 7270 + }, + { + "epoch": 6.43, + "learning_rate": 1.5858822407395707e-05, + "loss": 0.0867, + "step": 7271 + }, + { + "epoch": 6.43, + "learning_rate": 1.585766098662016e-05, + "loss": 0.0868, + "step": 7272 + }, + { + "epoch": 6.44, + "learning_rate": 1.5856499445545165e-05, + "loss": 0.0842, + "step": 7273 + }, + { + "epoch": 6.44, + "learning_rate": 1.5855337784194576e-05, + "loss": 0.1025, + "step": 7274 + }, + { + "epoch": 6.44, + "learning_rate": 1.5854176002592255e-05, + "loss": 0.1018, + "step": 7275 + }, + { + "epoch": 6.44, + "learning_rate": 1.5853014100762057e-05, + "loss": 0.0873, + "step": 7276 + }, + { + "epoch": 6.44, + "learning_rate": 1.585185207872785e-05, + "loss": 0.0833, + "step": 7277 + }, + { + "epoch": 6.44, + "learning_rate": 1.5850689936513488e-05, + "loss": 0.0831, + "step": 7278 + }, + { + "epoch": 6.44, + "learning_rate": 1.5849527674142845e-05, + "loss": 0.0914, + "step": 7279 + }, + { + "epoch": 6.44, + "learning_rate": 1.5848365291639793e-05, + "loss": 0.0862, + "step": 7280 + }, + { + "epoch": 6.44, + "learning_rate": 1.58472027890282e-05, + "loss": 0.0903, + "step": 7281 + }, + { + "epoch": 6.44, + "learning_rate": 1.5846040166331938e-05, + "loss": 0.0834, + "step": 7282 + }, + { + "epoch": 6.44, + "learning_rate": 1.584487742357489e-05, + "loss": 0.0998, + "step": 7283 + }, + { + "epoch": 6.45, + "learning_rate": 1.584371456078093e-05, + "loss": 0.0924, + "step": 7284 + }, + { + "epoch": 6.45, + "learning_rate": 1.5842551577973947e-05, + "loss": 0.0853, + "step": 7285 + }, + { + "epoch": 6.45, + "learning_rate": 1.5841388475177817e-05, + "loss": 0.085, + "step": 7286 + }, + { + "epoch": 6.45, + "learning_rate": 1.584022525241643e-05, + "loss": 0.0829, + "step": 7287 + }, + { + "epoch": 6.45, + "learning_rate": 1.583906190971368e-05, + "loss": 0.0948, + "step": 7288 + }, + { + "epoch": 6.45, + "learning_rate": 1.583789844709345e-05, + "loss": 0.0954, + "step": 7289 + }, + { + "epoch": 6.45, + "learning_rate": 1.5836734864579638e-05, + "loss": 0.091, + "step": 7290 + }, + { + "epoch": 6.45, + "learning_rate": 1.5835571162196146e-05, + "loss": 0.0905, + "step": 7291 + }, + { + "epoch": 6.45, + "learning_rate": 1.5834407339966863e-05, + "loss": 0.0821, + "step": 7292 + }, + { + "epoch": 6.45, + "learning_rate": 1.58332433979157e-05, + "loss": 0.0893, + "step": 7293 + }, + { + "epoch": 6.45, + "learning_rate": 1.583207933606655e-05, + "loss": 0.0904, + "step": 7294 + }, + { + "epoch": 6.45, + "learning_rate": 1.583091515444333e-05, + "loss": 0.0836, + "step": 7295 + }, + { + "epoch": 6.46, + "learning_rate": 1.5829750853069946e-05, + "loss": 0.0942, + "step": 7296 + }, + { + "epoch": 6.46, + "learning_rate": 1.582858643197031e-05, + "loss": 0.0894, + "step": 7297 + }, + { + "epoch": 6.46, + "learning_rate": 1.5827421891168335e-05, + "loss": 0.0948, + "step": 7298 + }, + { + "epoch": 6.46, + "learning_rate": 1.5826257230687933e-05, + "loss": 0.0913, + "step": 7299 + }, + { + "epoch": 6.46, + "learning_rate": 1.5825092450553027e-05, + "loss": 0.0911, + "step": 7300 + }, + { + "epoch": 6.46, + "learning_rate": 1.5823927550787538e-05, + "loss": 0.0769, + "step": 7301 + }, + { + "epoch": 6.46, + "learning_rate": 1.5822762531415393e-05, + "loss": 0.0922, + "step": 7302 + }, + { + "epoch": 6.46, + "learning_rate": 1.582159739246051e-05, + "loss": 0.0845, + "step": 7303 + }, + { + "epoch": 6.46, + "learning_rate": 1.5820432133946825e-05, + "loss": 0.0838, + "step": 7304 + }, + { + "epoch": 6.46, + "learning_rate": 1.5819266755898267e-05, + "loss": 0.091, + "step": 7305 + }, + { + "epoch": 6.46, + "learning_rate": 1.5818101258338764e-05, + "loss": 0.0846, + "step": 7306 + }, + { + "epoch": 6.47, + "learning_rate": 1.581693564129226e-05, + "loss": 0.0905, + "step": 7307 + }, + { + "epoch": 6.47, + "learning_rate": 1.581576990478269e-05, + "loss": 0.0984, + "step": 7308 + }, + { + "epoch": 6.47, + "learning_rate": 1.581460404883399e-05, + "loss": 0.0832, + "step": 7309 + }, + { + "epoch": 6.47, + "learning_rate": 1.5813438073470114e-05, + "loss": 0.0802, + "step": 7310 + }, + { + "epoch": 6.47, + "learning_rate": 1.5812271978715e-05, + "loss": 0.0795, + "step": 7311 + }, + { + "epoch": 6.47, + "learning_rate": 1.5811105764592598e-05, + "loss": 0.0914, + "step": 7312 + }, + { + "epoch": 6.47, + "learning_rate": 1.580993943112686e-05, + "loss": 0.0814, + "step": 7313 + }, + { + "epoch": 6.47, + "learning_rate": 1.5808772978341736e-05, + "loss": 0.0851, + "step": 7314 + }, + { + "epoch": 6.47, + "learning_rate": 1.5807606406261187e-05, + "loss": 0.096, + "step": 7315 + }, + { + "epoch": 6.47, + "learning_rate": 1.5806439714909165e-05, + "loss": 0.0868, + "step": 7316 + }, + { + "epoch": 6.47, + "learning_rate": 1.5805272904309633e-05, + "loss": 0.0849, + "step": 7317 + }, + { + "epoch": 6.48, + "learning_rate": 1.5804105974486554e-05, + "loss": 0.0747, + "step": 7318 + }, + { + "epoch": 6.48, + "learning_rate": 1.5802938925463897e-05, + "loss": 0.0832, + "step": 7319 + }, + { + "epoch": 6.48, + "learning_rate": 1.5801771757265618e-05, + "loss": 0.0802, + "step": 7320 + }, + { + "epoch": 6.48, + "learning_rate": 1.5800604469915702e-05, + "loss": 0.0868, + "step": 7321 + }, + { + "epoch": 6.48, + "learning_rate": 1.5799437063438114e-05, + "loss": 0.0922, + "step": 7322 + }, + { + "epoch": 6.48, + "learning_rate": 1.579826953785683e-05, + "loss": 0.0835, + "step": 7323 + }, + { + "epoch": 6.48, + "learning_rate": 1.5797101893195827e-05, + "loss": 0.0849, + "step": 7324 + }, + { + "epoch": 6.48, + "learning_rate": 1.5795934129479088e-05, + "loss": 0.0814, + "step": 7325 + }, + { + "epoch": 6.48, + "learning_rate": 1.5794766246730588e-05, + "loss": 0.0909, + "step": 7326 + }, + { + "epoch": 6.48, + "learning_rate": 1.579359824497432e-05, + "loss": 0.0773, + "step": 7327 + }, + { + "epoch": 6.48, + "learning_rate": 1.5792430124234272e-05, + "loss": 0.0958, + "step": 7328 + }, + { + "epoch": 6.48, + "learning_rate": 1.579126188453443e-05, + "loss": 0.0872, + "step": 7329 + }, + { + "epoch": 6.49, + "learning_rate": 1.5790093525898783e-05, + "loss": 0.0903, + "step": 7330 + }, + { + "epoch": 6.49, + "learning_rate": 1.5788925048351337e-05, + "loss": 0.0875, + "step": 7331 + }, + { + "epoch": 6.49, + "learning_rate": 1.5787756451916077e-05, + "loss": 0.0866, + "step": 7332 + }, + { + "epoch": 6.49, + "learning_rate": 1.5786587736617005e-05, + "loss": 0.0905, + "step": 7333 + }, + { + "epoch": 6.49, + "learning_rate": 1.5785418902478127e-05, + "loss": 0.0851, + "step": 7334 + }, + { + "epoch": 6.49, + "learning_rate": 1.5784249949523447e-05, + "loss": 0.0956, + "step": 7335 + }, + { + "epoch": 6.49, + "learning_rate": 1.578308087777697e-05, + "loss": 0.0902, + "step": 7336 + }, + { + "epoch": 6.49, + "learning_rate": 1.578191168726271e-05, + "loss": 0.0786, + "step": 7337 + }, + { + "epoch": 6.49, + "learning_rate": 1.5780742378004666e-05, + "loss": 0.0873, + "step": 7338 + }, + { + "epoch": 6.49, + "learning_rate": 1.5779572950026865e-05, + "loss": 0.0899, + "step": 7339 + }, + { + "epoch": 6.49, + "learning_rate": 1.577840340335332e-05, + "loss": 0.0869, + "step": 7340 + }, + { + "epoch": 6.5, + "learning_rate": 1.5777233738008052e-05, + "loss": 0.0892, + "step": 7341 + }, + { + "epoch": 6.5, + "learning_rate": 1.5776063954015084e-05, + "loss": 0.0864, + "step": 7342 + }, + { + "epoch": 6.5, + "learning_rate": 1.577489405139843e-05, + "loss": 0.0885, + "step": 7343 + }, + { + "epoch": 6.5, + "learning_rate": 1.577372403018213e-05, + "loss": 0.0878, + "step": 7344 + }, + { + "epoch": 6.5, + "learning_rate": 1.5772553890390196e-05, + "loss": 0.0882, + "step": 7345 + }, + { + "epoch": 6.5, + "learning_rate": 1.5771383632046674e-05, + "loss": 0.0955, + "step": 7346 + }, + { + "epoch": 6.5, + "learning_rate": 1.5770213255175593e-05, + "loss": 0.0851, + "step": 7347 + }, + { + "epoch": 6.5, + "learning_rate": 1.5769042759800987e-05, + "loss": 0.0891, + "step": 7348 + }, + { + "epoch": 6.5, + "learning_rate": 1.57678721459469e-05, + "loss": 0.0834, + "step": 7349 + }, + { + "epoch": 6.5, + "learning_rate": 1.5766701413637368e-05, + "loss": 0.0877, + "step": 7350 + }, + { + "epoch": 6.5, + "learning_rate": 1.5765530562896435e-05, + "loss": 0.0861, + "step": 7351 + }, + { + "epoch": 6.51, + "learning_rate": 1.576435959374815e-05, + "loss": 0.0867, + "step": 7352 + }, + { + "epoch": 6.51, + "learning_rate": 1.5763188506216555e-05, + "loss": 0.0885, + "step": 7353 + }, + { + "epoch": 6.51, + "learning_rate": 1.576201730032571e-05, + "loss": 0.0991, + "step": 7354 + }, + { + "epoch": 6.51, + "learning_rate": 1.576084597609966e-05, + "loss": 0.0916, + "step": 7355 + }, + { + "epoch": 6.51, + "learning_rate": 1.5759674533562465e-05, + "loss": 0.0856, + "step": 7356 + }, + { + "epoch": 6.51, + "learning_rate": 1.575850297273818e-05, + "loss": 0.0973, + "step": 7357 + }, + { + "epoch": 6.51, + "learning_rate": 1.5757331293650873e-05, + "loss": 0.0988, + "step": 7358 + }, + { + "epoch": 6.51, + "learning_rate": 1.5756159496324595e-05, + "loss": 0.088, + "step": 7359 + }, + { + "epoch": 6.51, + "learning_rate": 1.575498758078342e-05, + "loss": 0.0837, + "step": 7360 + }, + { + "epoch": 6.51, + "learning_rate": 1.5753815547051414e-05, + "loss": 0.0935, + "step": 7361 + }, + { + "epoch": 6.51, + "learning_rate": 1.5752643395152647e-05, + "loss": 0.0791, + "step": 7362 + }, + { + "epoch": 6.51, + "learning_rate": 1.5751471125111192e-05, + "loss": 0.0809, + "step": 7363 + }, + { + "epoch": 6.52, + "learning_rate": 1.575029873695112e-05, + "loss": 0.084, + "step": 7364 + }, + { + "epoch": 6.52, + "learning_rate": 1.574912623069651e-05, + "loss": 0.0912, + "step": 7365 + }, + { + "epoch": 6.52, + "learning_rate": 1.5747953606371446e-05, + "loss": 0.0886, + "step": 7366 + }, + { + "epoch": 6.52, + "learning_rate": 1.574678086400001e-05, + "loss": 0.0903, + "step": 7367 + }, + { + "epoch": 6.52, + "learning_rate": 1.5745608003606286e-05, + "loss": 0.0971, + "step": 7368 + }, + { + "epoch": 6.52, + "learning_rate": 1.5744435025214352e-05, + "loss": 0.0903, + "step": 7369 + }, + { + "epoch": 6.52, + "learning_rate": 1.5743261928848316e-05, + "loss": 0.0814, + "step": 7370 + }, + { + "epoch": 6.52, + "learning_rate": 1.5742088714532247e-05, + "loss": 0.0769, + "step": 7371 + }, + { + "epoch": 6.52, + "learning_rate": 1.574091538229026e-05, + "loss": 0.0899, + "step": 7372 + }, + { + "epoch": 6.52, + "learning_rate": 1.5739741932146443e-05, + "loss": 0.0987, + "step": 7373 + }, + { + "epoch": 6.52, + "learning_rate": 1.5738568364124896e-05, + "loss": 0.0835, + "step": 7374 + }, + { + "epoch": 6.53, + "learning_rate": 1.573739467824972e-05, + "loss": 0.0789, + "step": 7375 + }, + { + "epoch": 6.53, + "learning_rate": 1.573622087454502e-05, + "loss": 0.0974, + "step": 7376 + }, + { + "epoch": 6.53, + "learning_rate": 1.57350469530349e-05, + "loss": 0.0926, + "step": 7377 + }, + { + "epoch": 6.53, + "learning_rate": 1.5733872913743472e-05, + "loss": 0.0953, + "step": 7378 + }, + { + "epoch": 6.53, + "learning_rate": 1.5732698756694848e-05, + "loss": 0.0831, + "step": 7379 + }, + { + "epoch": 6.53, + "learning_rate": 1.573152448191314e-05, + "loss": 0.0908, + "step": 7380 + }, + { + "epoch": 6.53, + "learning_rate": 1.5730350089422465e-05, + "loss": 0.0898, + "step": 7381 + }, + { + "epoch": 6.53, + "learning_rate": 1.572917557924694e-05, + "loss": 0.0936, + "step": 7382 + }, + { + "epoch": 6.53, + "learning_rate": 1.572800095141069e-05, + "loss": 0.0976, + "step": 7383 + }, + { + "epoch": 6.53, + "learning_rate": 1.5726826205937834e-05, + "loss": 0.0898, + "step": 7384 + }, + { + "epoch": 6.53, + "learning_rate": 1.57256513428525e-05, + "loss": 0.0821, + "step": 7385 + }, + { + "epoch": 6.54, + "learning_rate": 1.5724476362178816e-05, + "loss": 0.0896, + "step": 7386 + }, + { + "epoch": 6.54, + "learning_rate": 1.5723301263940913e-05, + "loss": 0.0972, + "step": 7387 + }, + { + "epoch": 6.54, + "learning_rate": 1.572212604816292e-05, + "loss": 0.0984, + "step": 7388 + }, + { + "epoch": 6.54, + "learning_rate": 1.5720950714868984e-05, + "loss": 0.0969, + "step": 7389 + }, + { + "epoch": 6.54, + "learning_rate": 1.5719775264083233e-05, + "loss": 0.091, + "step": 7390 + }, + { + "epoch": 6.54, + "learning_rate": 1.5718599695829807e-05, + "loss": 0.0919, + "step": 7391 + }, + { + "epoch": 6.54, + "learning_rate": 1.571742401013285e-05, + "loss": 0.0928, + "step": 7392 + }, + { + "epoch": 6.54, + "learning_rate": 1.571624820701651e-05, + "loss": 0.0909, + "step": 7393 + }, + { + "epoch": 6.54, + "learning_rate": 1.5715072286504935e-05, + "loss": 0.0922, + "step": 7394 + }, + { + "epoch": 6.54, + "learning_rate": 1.5713896248622274e-05, + "loss": 0.0804, + "step": 7395 + }, + { + "epoch": 6.54, + "learning_rate": 1.5712720093392678e-05, + "loss": 0.0841, + "step": 7396 + }, + { + "epoch": 6.55, + "learning_rate": 1.57115438208403e-05, + "loss": 0.0832, + "step": 7397 + }, + { + "epoch": 6.55, + "learning_rate": 1.57103674309893e-05, + "loss": 0.0916, + "step": 7398 + }, + { + "epoch": 6.55, + "learning_rate": 1.570919092386384e-05, + "loss": 0.0852, + "step": 7399 + }, + { + "epoch": 6.55, + "learning_rate": 1.570801429948808e-05, + "loss": 0.0889, + "step": 7400 + }, + { + "epoch": 6.55, + "learning_rate": 1.570683755788618e-05, + "loss": 0.0895, + "step": 7401 + }, + { + "epoch": 6.55, + "learning_rate": 1.5705660699082314e-05, + "loss": 0.0803, + "step": 7402 + }, + { + "epoch": 6.55, + "learning_rate": 1.570448372310065e-05, + "loss": 0.0894, + "step": 7403 + }, + { + "epoch": 6.55, + "learning_rate": 1.570330662996535e-05, + "loss": 0.0893, + "step": 7404 + }, + { + "epoch": 6.55, + "learning_rate": 1.5702129419700603e-05, + "loss": 0.0871, + "step": 7405 + }, + { + "epoch": 6.55, + "learning_rate": 1.5700952092330575e-05, + "loss": 0.082, + "step": 7406 + }, + { + "epoch": 6.55, + "learning_rate": 1.5699774647879452e-05, + "loss": 0.1021, + "step": 7407 + }, + { + "epoch": 6.55, + "learning_rate": 1.569859708637141e-05, + "loss": 0.0744, + "step": 7408 + }, + { + "epoch": 6.56, + "learning_rate": 1.569741940783063e-05, + "loss": 0.076, + "step": 7409 + }, + { + "epoch": 6.56, + "learning_rate": 1.5696241612281306e-05, + "loss": 0.0946, + "step": 7410 + }, + { + "epoch": 6.56, + "learning_rate": 1.5695063699747623e-05, + "loss": 0.0966, + "step": 7411 + }, + { + "epoch": 6.56, + "learning_rate": 1.5693885670253774e-05, + "loss": 0.0883, + "step": 7412 + }, + { + "epoch": 6.56, + "learning_rate": 1.5692707523823947e-05, + "loss": 0.0859, + "step": 7413 + }, + { + "epoch": 6.56, + "learning_rate": 1.569152926048234e-05, + "loss": 0.09, + "step": 7414 + }, + { + "epoch": 6.56, + "learning_rate": 1.5690350880253157e-05, + "loss": 0.082, + "step": 7415 + }, + { + "epoch": 6.56, + "learning_rate": 1.568917238316059e-05, + "loss": 0.0886, + "step": 7416 + }, + { + "epoch": 6.56, + "learning_rate": 1.5687993769228845e-05, + "loss": 0.0819, + "step": 7417 + }, + { + "epoch": 6.56, + "learning_rate": 1.5686815038482128e-05, + "loss": 0.0892, + "step": 7418 + }, + { + "epoch": 6.56, + "learning_rate": 1.5685636190944648e-05, + "loss": 0.0865, + "step": 7419 + }, + { + "epoch": 6.57, + "learning_rate": 1.5684457226640614e-05, + "loss": 0.0947, + "step": 7420 + }, + { + "epoch": 6.57, + "learning_rate": 1.568327814559424e-05, + "loss": 0.0909, + "step": 7421 + }, + { + "epoch": 6.57, + "learning_rate": 1.5682098947829737e-05, + "loss": 0.0887, + "step": 7422 + }, + { + "epoch": 6.57, + "learning_rate": 1.5680919633371322e-05, + "loss": 0.0888, + "step": 7423 + }, + { + "epoch": 6.57, + "learning_rate": 1.567974020224322e-05, + "loss": 0.0938, + "step": 7424 + }, + { + "epoch": 6.57, + "learning_rate": 1.567856065446965e-05, + "loss": 0.0921, + "step": 7425 + }, + { + "epoch": 6.57, + "learning_rate": 1.5677380990074835e-05, + "loss": 0.0751, + "step": 7426 + }, + { + "epoch": 6.57, + "learning_rate": 1.5676201209083005e-05, + "loss": 0.0912, + "step": 7427 + }, + { + "epoch": 6.57, + "learning_rate": 1.5675021311518385e-05, + "loss": 0.087, + "step": 7428 + }, + { + "epoch": 6.57, + "learning_rate": 1.5673841297405215e-05, + "loss": 0.0953, + "step": 7429 + }, + { + "epoch": 6.57, + "learning_rate": 1.5672661166767723e-05, + "loss": 0.0826, + "step": 7430 + }, + { + "epoch": 6.58, + "learning_rate": 1.567148091963014e-05, + "loss": 0.0971, + "step": 7431 + }, + { + "epoch": 6.58, + "learning_rate": 1.5670300556016717e-05, + "loss": 0.0884, + "step": 7432 + }, + { + "epoch": 6.58, + "learning_rate": 1.566912007595169e-05, + "loss": 0.0998, + "step": 7433 + }, + { + "epoch": 6.58, + "learning_rate": 1.56679394794593e-05, + "loss": 0.088, + "step": 7434 + }, + { + "epoch": 6.58, + "learning_rate": 1.5666758766563793e-05, + "loss": 0.0828, + "step": 7435 + }, + { + "epoch": 6.58, + "learning_rate": 1.5665577937289422e-05, + "loss": 0.079, + "step": 7436 + }, + { + "epoch": 6.58, + "learning_rate": 1.5664396991660436e-05, + "loss": 0.0938, + "step": 7437 + }, + { + "epoch": 6.58, + "learning_rate": 1.5663215929701087e-05, + "loss": 0.0935, + "step": 7438 + }, + { + "epoch": 6.58, + "learning_rate": 1.566203475143563e-05, + "loss": 0.093, + "step": 7439 + }, + { + "epoch": 6.58, + "learning_rate": 1.5660853456888324e-05, + "loss": 0.0887, + "step": 7440 + }, + { + "epoch": 6.58, + "learning_rate": 1.565967204608343e-05, + "loss": 0.079, + "step": 7441 + }, + { + "epoch": 6.58, + "learning_rate": 1.5658490519045214e-05, + "loss": 0.0923, + "step": 7442 + }, + { + "epoch": 6.59, + "learning_rate": 1.565730887579793e-05, + "loss": 0.0945, + "step": 7443 + }, + { + "epoch": 6.59, + "learning_rate": 1.565612711636586e-05, + "loss": 0.0817, + "step": 7444 + }, + { + "epoch": 6.59, + "learning_rate": 1.5654945240773264e-05, + "loss": 0.0961, + "step": 7445 + }, + { + "epoch": 6.59, + "learning_rate": 1.5653763249044415e-05, + "loss": 0.0961, + "step": 7446 + }, + { + "epoch": 6.59, + "learning_rate": 1.5652581141203592e-05, + "loss": 0.1062, + "step": 7447 + }, + { + "epoch": 6.59, + "learning_rate": 1.565139891727507e-05, + "loss": 0.0789, + "step": 7448 + }, + { + "epoch": 6.59, + "learning_rate": 1.565021657728313e-05, + "loss": 0.0942, + "step": 7449 + }, + { + "epoch": 6.59, + "learning_rate": 1.564903412125205e-05, + "loss": 0.0898, + "step": 7450 + }, + { + "epoch": 6.59, + "learning_rate": 1.5647851549206116e-05, + "loss": 0.0809, + "step": 7451 + }, + { + "epoch": 6.59, + "learning_rate": 1.5646668861169615e-05, + "loss": 0.0943, + "step": 7452 + }, + { + "epoch": 6.59, + "learning_rate": 1.564548605716684e-05, + "loss": 0.0772, + "step": 7453 + }, + { + "epoch": 6.6, + "learning_rate": 1.5644303137222075e-05, + "loss": 0.0986, + "step": 7454 + }, + { + "epoch": 6.6, + "learning_rate": 1.564312010135962e-05, + "loss": 0.0845, + "step": 7455 + }, + { + "epoch": 6.6, + "learning_rate": 1.564193694960377e-05, + "loss": 0.1015, + "step": 7456 + }, + { + "epoch": 6.6, + "learning_rate": 1.5640753681978815e-05, + "loss": 0.085, + "step": 7457 + }, + { + "epoch": 6.6, + "learning_rate": 1.5639570298509067e-05, + "loss": 0.0905, + "step": 7458 + }, + { + "epoch": 6.6, + "learning_rate": 1.5638386799218826e-05, + "loss": 0.0943, + "step": 7459 + }, + { + "epoch": 6.6, + "learning_rate": 1.5637203184132394e-05, + "loss": 0.106, + "step": 7460 + }, + { + "epoch": 6.6, + "learning_rate": 1.5636019453274082e-05, + "loss": 0.0863, + "step": 7461 + }, + { + "epoch": 6.6, + "learning_rate": 1.5634835606668203e-05, + "loss": 0.0978, + "step": 7462 + }, + { + "epoch": 6.6, + "learning_rate": 1.5633651644339066e-05, + "loss": 0.0882, + "step": 7463 + }, + { + "epoch": 6.6, + "learning_rate": 1.5632467566310988e-05, + "loss": 0.0947, + "step": 7464 + }, + { + "epoch": 6.61, + "learning_rate": 1.5631283372608283e-05, + "loss": 0.09, + "step": 7465 + }, + { + "epoch": 6.61, + "learning_rate": 1.5630099063255277e-05, + "loss": 0.0943, + "step": 7466 + }, + { + "epoch": 6.61, + "learning_rate": 1.5628914638276287e-05, + "loss": 0.1006, + "step": 7467 + }, + { + "epoch": 6.61, + "learning_rate": 1.562773009769564e-05, + "loss": 0.0883, + "step": 7468 + }, + { + "epoch": 6.61, + "learning_rate": 1.5626545441537665e-05, + "loss": 0.0915, + "step": 7469 + }, + { + "epoch": 6.61, + "learning_rate": 1.5625360669826684e-05, + "loss": 0.0918, + "step": 7470 + }, + { + "epoch": 6.61, + "learning_rate": 1.5624175782587035e-05, + "loss": 0.0899, + "step": 7471 + }, + { + "epoch": 6.61, + "learning_rate": 1.5622990779843053e-05, + "loss": 0.0931, + "step": 7472 + }, + { + "epoch": 6.61, + "learning_rate": 1.5621805661619075e-05, + "loss": 0.0972, + "step": 7473 + }, + { + "epoch": 6.61, + "learning_rate": 1.5620620427939435e-05, + "loss": 0.0953, + "step": 7474 + }, + { + "epoch": 6.61, + "learning_rate": 1.5619435078828478e-05, + "loss": 0.0939, + "step": 7475 + }, + { + "epoch": 6.61, + "learning_rate": 1.5618249614310543e-05, + "loss": 0.0869, + "step": 7476 + }, + { + "epoch": 6.62, + "learning_rate": 1.561706403440998e-05, + "loss": 0.0875, + "step": 7477 + }, + { + "epoch": 6.62, + "learning_rate": 1.561587833915114e-05, + "loss": 0.0913, + "step": 7478 + }, + { + "epoch": 6.62, + "learning_rate": 1.561469252855837e-05, + "loss": 0.0849, + "step": 7479 + }, + { + "epoch": 6.62, + "learning_rate": 1.5613506602656022e-05, + "loss": 0.0983, + "step": 7480 + }, + { + "epoch": 6.62, + "learning_rate": 1.5612320561468455e-05, + "loss": 0.0812, + "step": 7481 + }, + { + "epoch": 6.62, + "learning_rate": 1.5611134405020022e-05, + "loss": 0.0925, + "step": 7482 + }, + { + "epoch": 6.62, + "learning_rate": 1.5609948133335087e-05, + "loss": 0.0952, + "step": 7483 + }, + { + "epoch": 6.62, + "learning_rate": 1.5608761746438015e-05, + "loss": 0.074, + "step": 7484 + }, + { + "epoch": 6.62, + "learning_rate": 1.5607575244353167e-05, + "loss": 0.0853, + "step": 7485 + }, + { + "epoch": 6.62, + "learning_rate": 1.5606388627104912e-05, + "loss": 0.1056, + "step": 7486 + }, + { + "epoch": 6.62, + "learning_rate": 1.5605201894717616e-05, + "loss": 0.0883, + "step": 7487 + }, + { + "epoch": 6.63, + "learning_rate": 1.5604015047215656e-05, + "loss": 0.0949, + "step": 7488 + }, + { + "epoch": 6.63, + "learning_rate": 1.56028280846234e-05, + "loss": 0.0852, + "step": 7489 + }, + { + "epoch": 6.63, + "learning_rate": 1.5601641006965235e-05, + "loss": 0.0987, + "step": 7490 + }, + { + "epoch": 6.63, + "learning_rate": 1.5600453814265534e-05, + "loss": 0.1048, + "step": 7491 + }, + { + "epoch": 6.63, + "learning_rate": 1.5599266506548673e-05, + "loss": 0.0864, + "step": 7492 + }, + { + "epoch": 6.63, + "learning_rate": 1.5598079083839048e-05, + "loss": 0.0938, + "step": 7493 + }, + { + "epoch": 6.63, + "learning_rate": 1.5596891546161036e-05, + "loss": 0.0992, + "step": 7494 + }, + { + "epoch": 6.63, + "learning_rate": 1.559570389353903e-05, + "loss": 0.0984, + "step": 7495 + }, + { + "epoch": 6.63, + "learning_rate": 1.5594516125997416e-05, + "loss": 0.0931, + "step": 7496 + }, + { + "epoch": 6.63, + "learning_rate": 1.5593328243560592e-05, + "loss": 0.0815, + "step": 7497 + }, + { + "epoch": 6.63, + "learning_rate": 1.5592140246252954e-05, + "loss": 0.0784, + "step": 7498 + }, + { + "epoch": 6.64, + "learning_rate": 1.55909521340989e-05, + "loss": 0.0896, + "step": 7499 + }, + { + "epoch": 6.64, + "learning_rate": 1.5589763907122826e-05, + "loss": 0.0917, + "step": 7500 + }, + { + "epoch": 6.64, + "learning_rate": 1.558857556534914e-05, + "loss": 0.0943, + "step": 7501 + }, + { + "epoch": 6.64, + "learning_rate": 1.558738710880224e-05, + "loss": 0.0943, + "step": 7502 + }, + { + "epoch": 6.64, + "learning_rate": 1.5586198537506544e-05, + "loss": 0.1038, + "step": 7503 + }, + { + "epoch": 6.64, + "learning_rate": 1.5585009851486455e-05, + "loss": 0.0952, + "step": 7504 + }, + { + "epoch": 6.64, + "learning_rate": 1.5583821050766383e-05, + "loss": 0.0907, + "step": 7505 + }, + { + "epoch": 6.64, + "learning_rate": 1.558263213537075e-05, + "loss": 0.0878, + "step": 7506 + }, + { + "epoch": 6.64, + "learning_rate": 1.5581443105323967e-05, + "loss": 0.0928, + "step": 7507 + }, + { + "epoch": 6.64, + "learning_rate": 1.5580253960650452e-05, + "loss": 0.0888, + "step": 7508 + }, + { + "epoch": 6.64, + "learning_rate": 1.557906470137463e-05, + "loss": 0.0965, + "step": 7509 + }, + { + "epoch": 6.64, + "learning_rate": 1.5577875327520926e-05, + "loss": 0.0825, + "step": 7510 + }, + { + "epoch": 6.65, + "learning_rate": 1.5576685839113767e-05, + "loss": 0.0908, + "step": 7511 + }, + { + "epoch": 6.65, + "learning_rate": 1.557549623617758e-05, + "loss": 0.0852, + "step": 7512 + }, + { + "epoch": 6.65, + "learning_rate": 1.5574306518736788e-05, + "loss": 0.0956, + "step": 7513 + }, + { + "epoch": 6.65, + "learning_rate": 1.5573116686815837e-05, + "loss": 0.0901, + "step": 7514 + }, + { + "epoch": 6.65, + "learning_rate": 1.5571926740439157e-05, + "loss": 0.0879, + "step": 7515 + }, + { + "epoch": 6.65, + "learning_rate": 1.5570736679631185e-05, + "loss": 0.0782, + "step": 7516 + }, + { + "epoch": 6.65, + "learning_rate": 1.556954650441637e-05, + "loss": 0.096, + "step": 7517 + }, + { + "epoch": 6.65, + "learning_rate": 1.556835621481914e-05, + "loss": 0.0945, + "step": 7518 + }, + { + "epoch": 6.65, + "learning_rate": 1.556716581086395e-05, + "loss": 0.0881, + "step": 7519 + }, + { + "epoch": 6.65, + "learning_rate": 1.5565975292575247e-05, + "loss": 0.092, + "step": 7520 + }, + { + "epoch": 6.65, + "learning_rate": 1.5564784659977474e-05, + "loss": 0.0807, + "step": 7521 + }, + { + "epoch": 6.66, + "learning_rate": 1.5563593913095095e-05, + "loss": 0.0924, + "step": 7522 + }, + { + "epoch": 6.66, + "learning_rate": 1.5562403051952553e-05, + "loss": 0.0904, + "step": 7523 + }, + { + "epoch": 6.66, + "learning_rate": 1.556121207657431e-05, + "loss": 0.0956, + "step": 7524 + }, + { + "epoch": 6.66, + "learning_rate": 1.5560020986984828e-05, + "loss": 0.0922, + "step": 7525 + }, + { + "epoch": 6.66, + "learning_rate": 1.555882978320856e-05, + "loss": 0.1052, + "step": 7526 + }, + { + "epoch": 6.66, + "learning_rate": 1.5557638465269982e-05, + "loss": 0.0831, + "step": 7527 + }, + { + "epoch": 6.66, + "learning_rate": 1.555644703319355e-05, + "loss": 0.096, + "step": 7528 + }, + { + "epoch": 6.66, + "learning_rate": 1.5555255487003735e-05, + "loss": 0.0943, + "step": 7529 + }, + { + "epoch": 6.66, + "learning_rate": 1.555406382672501e-05, + "loss": 0.0928, + "step": 7530 + }, + { + "epoch": 6.66, + "learning_rate": 1.5552872052381847e-05, + "loss": 0.0903, + "step": 7531 + }, + { + "epoch": 6.66, + "learning_rate": 1.5551680163998722e-05, + "loss": 0.0849, + "step": 7532 + }, + { + "epoch": 6.67, + "learning_rate": 1.5550488161600114e-05, + "loss": 0.091, + "step": 7533 + }, + { + "epoch": 6.67, + "learning_rate": 1.55492960452105e-05, + "loss": 0.0759, + "step": 7534 + }, + { + "epoch": 6.67, + "learning_rate": 1.5548103814854365e-05, + "loss": 0.0969, + "step": 7535 + }, + { + "epoch": 6.67, + "learning_rate": 1.5546911470556196e-05, + "loss": 0.0873, + "step": 7536 + }, + { + "epoch": 6.67, + "learning_rate": 1.5545719012340475e-05, + "loss": 0.0949, + "step": 7537 + }, + { + "epoch": 6.67, + "learning_rate": 1.5544526440231698e-05, + "loss": 0.0835, + "step": 7538 + }, + { + "epoch": 6.67, + "learning_rate": 1.554333375425435e-05, + "loss": 0.0996, + "step": 7539 + }, + { + "epoch": 6.67, + "learning_rate": 1.5542140954432935e-05, + "loss": 0.0928, + "step": 7540 + }, + { + "epoch": 6.67, + "learning_rate": 1.5540948040791938e-05, + "loss": 0.0866, + "step": 7541 + }, + { + "epoch": 6.67, + "learning_rate": 1.5539755013355863e-05, + "loss": 0.0892, + "step": 7542 + }, + { + "epoch": 6.67, + "learning_rate": 1.5538561872149213e-05, + "loss": 0.0824, + "step": 7543 + }, + { + "epoch": 6.68, + "learning_rate": 1.5537368617196494e-05, + "loss": 0.0888, + "step": 7544 + }, + { + "epoch": 6.68, + "learning_rate": 1.5536175248522205e-05, + "loss": 0.0918, + "step": 7545 + }, + { + "epoch": 6.68, + "learning_rate": 1.553498176615086e-05, + "loss": 0.0905, + "step": 7546 + }, + { + "epoch": 6.68, + "learning_rate": 1.5533788170106964e-05, + "loss": 0.099, + "step": 7547 + }, + { + "epoch": 6.68, + "learning_rate": 1.553259446041504e-05, + "loss": 0.078, + "step": 7548 + }, + { + "epoch": 6.68, + "learning_rate": 1.553140063709959e-05, + "loss": 0.0987, + "step": 7549 + }, + { + "epoch": 6.68, + "learning_rate": 1.5530206700185145e-05, + "loss": 0.0873, + "step": 7550 + }, + { + "epoch": 6.68, + "learning_rate": 1.5529012649696215e-05, + "loss": 0.0877, + "step": 7551 + }, + { + "epoch": 6.68, + "learning_rate": 1.5527818485657328e-05, + "loss": 0.0945, + "step": 7552 + }, + { + "epoch": 6.68, + "learning_rate": 1.5526624208093007e-05, + "loss": 0.0883, + "step": 7553 + }, + { + "epoch": 6.68, + "learning_rate": 1.5525429817027776e-05, + "loss": 0.101, + "step": 7554 + }, + { + "epoch": 6.68, + "learning_rate": 1.552423531248617e-05, + "loss": 0.0949, + "step": 7555 + }, + { + "epoch": 6.69, + "learning_rate": 1.5523040694492715e-05, + "loss": 0.0841, + "step": 7556 + }, + { + "epoch": 6.69, + "learning_rate": 1.552184596307195e-05, + "loss": 0.0883, + "step": 7557 + }, + { + "epoch": 6.69, + "learning_rate": 1.552065111824841e-05, + "loss": 0.0971, + "step": 7558 + }, + { + "epoch": 6.69, + "learning_rate": 1.5519456160046627e-05, + "loss": 0.0782, + "step": 7559 + }, + { + "epoch": 6.69, + "learning_rate": 1.5518261088491155e-05, + "loss": 0.0865, + "step": 7560 + }, + { + "epoch": 6.69, + "learning_rate": 1.5517065903606527e-05, + "loss": 0.0849, + "step": 7561 + }, + { + "epoch": 6.69, + "learning_rate": 1.551587060541729e-05, + "loss": 0.1005, + "step": 7562 + }, + { + "epoch": 6.69, + "learning_rate": 1.5514675193947998e-05, + "loss": 0.0953, + "step": 7563 + }, + { + "epoch": 6.69, + "learning_rate": 1.5513479669223194e-05, + "loss": 0.0965, + "step": 7564 + }, + { + "epoch": 6.69, + "learning_rate": 1.551228403126744e-05, + "loss": 0.1024, + "step": 7565 + }, + { + "epoch": 6.69, + "learning_rate": 1.5511088280105276e-05, + "loss": 0.0841, + "step": 7566 + }, + { + "epoch": 6.7, + "learning_rate": 1.550989241576127e-05, + "loss": 0.0845, + "step": 7567 + }, + { + "epoch": 6.7, + "learning_rate": 1.5508696438259982e-05, + "loss": 0.0905, + "step": 7568 + }, + { + "epoch": 6.7, + "learning_rate": 1.5507500347625967e-05, + "loss": 0.0981, + "step": 7569 + }, + { + "epoch": 6.7, + "learning_rate": 1.5506304143883798e-05, + "loss": 0.0867, + "step": 7570 + }, + { + "epoch": 6.7, + "learning_rate": 1.5505107827058038e-05, + "loss": 0.0931, + "step": 7571 + }, + { + "epoch": 6.7, + "learning_rate": 1.5503911397173253e-05, + "loss": 0.0867, + "step": 7572 + }, + { + "epoch": 6.7, + "learning_rate": 1.5502714854254016e-05, + "loss": 0.0892, + "step": 7573 + }, + { + "epoch": 6.7, + "learning_rate": 1.55015181983249e-05, + "loss": 0.0956, + "step": 7574 + }, + { + "epoch": 6.7, + "learning_rate": 1.5500321429410483e-05, + "loss": 0.0913, + "step": 7575 + }, + { + "epoch": 6.7, + "learning_rate": 1.5499124547535346e-05, + "loss": 0.0897, + "step": 7576 + }, + { + "epoch": 6.7, + "learning_rate": 1.549792755272406e-05, + "loss": 0.0893, + "step": 7577 + }, + { + "epoch": 6.71, + "learning_rate": 1.5496730445001213e-05, + "loss": 0.0857, + "step": 7578 + }, + { + "epoch": 6.71, + "learning_rate": 1.5495533224391392e-05, + "loss": 0.0898, + "step": 7579 + }, + { + "epoch": 6.71, + "learning_rate": 1.5494335890919182e-05, + "loss": 0.0896, + "step": 7580 + }, + { + "epoch": 6.71, + "learning_rate": 1.5493138444609176e-05, + "loss": 0.095, + "step": 7581 + }, + { + "epoch": 6.71, + "learning_rate": 1.5491940885485962e-05, + "loss": 0.0974, + "step": 7582 + }, + { + "epoch": 6.71, + "learning_rate": 1.5490743213574138e-05, + "loss": 0.0929, + "step": 7583 + }, + { + "epoch": 6.71, + "learning_rate": 1.54895454288983e-05, + "loss": 0.0872, + "step": 7584 + }, + { + "epoch": 6.71, + "learning_rate": 1.548834753148304e-05, + "loss": 0.09, + "step": 7585 + }, + { + "epoch": 6.71, + "learning_rate": 1.548714952135297e-05, + "loss": 0.0982, + "step": 7586 + }, + { + "epoch": 6.71, + "learning_rate": 1.5485951398532684e-05, + "loss": 0.09, + "step": 7587 + }, + { + "epoch": 6.71, + "learning_rate": 1.5484753163046798e-05, + "loss": 0.0922, + "step": 7588 + }, + { + "epoch": 6.71, + "learning_rate": 1.5483554814919912e-05, + "loss": 0.0878, + "step": 7589 + }, + { + "epoch": 6.72, + "learning_rate": 1.5482356354176645e-05, + "loss": 0.0859, + "step": 7590 + }, + { + "epoch": 6.72, + "learning_rate": 1.54811577808416e-05, + "loss": 0.0963, + "step": 7591 + }, + { + "epoch": 6.72, + "learning_rate": 1.5479959094939395e-05, + "loss": 0.0852, + "step": 7592 + }, + { + "epoch": 6.72, + "learning_rate": 1.5478760296494656e-05, + "loss": 0.0918, + "step": 7593 + }, + { + "epoch": 6.72, + "learning_rate": 1.5477561385531988e-05, + "loss": 0.0946, + "step": 7594 + }, + { + "epoch": 6.72, + "learning_rate": 1.547636236207603e-05, + "loss": 0.0964, + "step": 7595 + }, + { + "epoch": 6.72, + "learning_rate": 1.5475163226151393e-05, + "loss": 0.0968, + "step": 7596 + }, + { + "epoch": 6.72, + "learning_rate": 1.547396397778271e-05, + "loss": 0.0922, + "step": 7597 + }, + { + "epoch": 6.72, + "learning_rate": 1.547276461699461e-05, + "loss": 0.0883, + "step": 7598 + }, + { + "epoch": 6.72, + "learning_rate": 1.547156514381172e-05, + "loss": 0.089, + "step": 7599 + }, + { + "epoch": 6.72, + "learning_rate": 1.547036555825868e-05, + "loss": 0.0921, + "step": 7600 + }, + { + "epoch": 6.73, + "learning_rate": 1.546916586036012e-05, + "loss": 0.0876, + "step": 7601 + }, + { + "epoch": 6.73, + "learning_rate": 1.5467966050140687e-05, + "loss": 0.0934, + "step": 7602 + }, + { + "epoch": 6.73, + "learning_rate": 1.5466766127625015e-05, + "loss": 0.0905, + "step": 7603 + }, + { + "epoch": 6.73, + "learning_rate": 1.5465566092837745e-05, + "loss": 0.0824, + "step": 7604 + }, + { + "epoch": 6.73, + "learning_rate": 1.5464365945803526e-05, + "loss": 0.0908, + "step": 7605 + }, + { + "epoch": 6.73, + "learning_rate": 1.5463165686547006e-05, + "loss": 0.0914, + "step": 7606 + }, + { + "epoch": 6.73, + "learning_rate": 1.546196531509283e-05, + "loss": 0.0949, + "step": 7607 + }, + { + "epoch": 6.73, + "learning_rate": 1.546076483146566e-05, + "loss": 0.0841, + "step": 7608 + }, + { + "epoch": 6.73, + "learning_rate": 1.5459564235690138e-05, + "loss": 0.0992, + "step": 7609 + }, + { + "epoch": 6.73, + "learning_rate": 1.545836352779093e-05, + "loss": 0.088, + "step": 7610 + }, + { + "epoch": 6.73, + "learning_rate": 1.5457162707792692e-05, + "loss": 0.0867, + "step": 7611 + }, + { + "epoch": 6.74, + "learning_rate": 1.5455961775720084e-05, + "loss": 0.089, + "step": 7612 + }, + { + "epoch": 6.74, + "learning_rate": 1.5454760731597773e-05, + "loss": 0.0856, + "step": 7613 + }, + { + "epoch": 6.74, + "learning_rate": 1.5453559575450422e-05, + "loss": 0.0907, + "step": 7614 + }, + { + "epoch": 6.74, + "learning_rate": 1.54523583073027e-05, + "loss": 0.0897, + "step": 7615 + }, + { + "epoch": 6.74, + "learning_rate": 1.545115692717928e-05, + "loss": 0.0924, + "step": 7616 + }, + { + "epoch": 6.74, + "learning_rate": 1.544995543510483e-05, + "loss": 0.0802, + "step": 7617 + }, + { + "epoch": 6.74, + "learning_rate": 1.5448753831104034e-05, + "loss": 0.0913, + "step": 7618 + }, + { + "epoch": 6.74, + "learning_rate": 1.544755211520156e-05, + "loss": 0.0873, + "step": 7619 + }, + { + "epoch": 6.74, + "learning_rate": 1.5446350287422086e-05, + "loss": 0.0996, + "step": 7620 + }, + { + "epoch": 6.74, + "learning_rate": 1.5445148347790305e-05, + "loss": 0.0931, + "step": 7621 + }, + { + "epoch": 6.74, + "learning_rate": 1.5443946296330898e-05, + "loss": 0.0898, + "step": 7622 + }, + { + "epoch": 6.74, + "learning_rate": 1.5442744133068545e-05, + "loss": 0.0829, + "step": 7623 + }, + { + "epoch": 6.75, + "learning_rate": 1.544154185802794e-05, + "loss": 0.0987, + "step": 7624 + }, + { + "epoch": 6.75, + "learning_rate": 1.5440339471233775e-05, + "loss": 0.0906, + "step": 7625 + }, + { + "epoch": 6.75, + "learning_rate": 1.543913697271074e-05, + "loss": 0.0971, + "step": 7626 + }, + { + "epoch": 6.75, + "learning_rate": 1.5437934362483535e-05, + "loss": 0.0702, + "step": 7627 + }, + { + "epoch": 6.75, + "learning_rate": 1.5436731640576858e-05, + "loss": 0.0906, + "step": 7628 + }, + { + "epoch": 6.75, + "learning_rate": 1.5435528807015402e-05, + "loss": 0.0984, + "step": 7629 + }, + { + "epoch": 6.75, + "learning_rate": 1.543432586182388e-05, + "loss": 0.0944, + "step": 7630 + }, + { + "epoch": 6.75, + "learning_rate": 1.543312280502699e-05, + "loss": 0.0912, + "step": 7631 + }, + { + "epoch": 6.75, + "learning_rate": 1.5431919636649447e-05, + "loss": 0.0897, + "step": 7632 + }, + { + "epoch": 6.75, + "learning_rate": 1.543071635671595e-05, + "loss": 0.0923, + "step": 7633 + }, + { + "epoch": 6.75, + "learning_rate": 1.5429512965251216e-05, + "loss": 0.0914, + "step": 7634 + }, + { + "epoch": 6.76, + "learning_rate": 1.542830946227996e-05, + "loss": 0.0815, + "step": 7635 + }, + { + "epoch": 6.76, + "learning_rate": 1.54271058478269e-05, + "loss": 0.0888, + "step": 7636 + }, + { + "epoch": 6.76, + "learning_rate": 1.5425902121916752e-05, + "loss": 0.0942, + "step": 7637 + }, + { + "epoch": 6.76, + "learning_rate": 1.5424698284574237e-05, + "loss": 0.0891, + "step": 7638 + }, + { + "epoch": 6.76, + "learning_rate": 1.542349433582408e-05, + "loss": 0.0933, + "step": 7639 + }, + { + "epoch": 6.76, + "learning_rate": 1.5422290275691002e-05, + "loss": 0.0885, + "step": 7640 + }, + { + "epoch": 6.76, + "learning_rate": 1.542108610419974e-05, + "loss": 0.086, + "step": 7641 + }, + { + "epoch": 6.76, + "learning_rate": 1.5419881821375014e-05, + "loss": 0.0833, + "step": 7642 + }, + { + "epoch": 6.76, + "learning_rate": 1.5418677427241564e-05, + "loss": 0.0835, + "step": 7643 + }, + { + "epoch": 6.76, + "learning_rate": 1.5417472921824123e-05, + "loss": 0.0897, + "step": 7644 + }, + { + "epoch": 6.76, + "learning_rate": 1.5416268305147423e-05, + "loss": 0.0861, + "step": 7645 + }, + { + "epoch": 6.77, + "learning_rate": 1.5415063577236212e-05, + "loss": 0.0992, + "step": 7646 + }, + { + "epoch": 6.77, + "learning_rate": 1.5413858738115224e-05, + "loss": 0.0825, + "step": 7647 + }, + { + "epoch": 6.77, + "learning_rate": 1.5412653787809207e-05, + "loss": 0.0945, + "step": 7648 + }, + { + "epoch": 6.77, + "learning_rate": 1.5411448726342906e-05, + "loss": 0.0982, + "step": 7649 + }, + { + "epoch": 6.77, + "learning_rate": 1.5410243553741072e-05, + "loss": 0.0821, + "step": 7650 + }, + { + "epoch": 6.77, + "learning_rate": 1.540903827002845e-05, + "loss": 0.0988, + "step": 7651 + }, + { + "epoch": 6.77, + "learning_rate": 1.5407832875229796e-05, + "loss": 0.0991, + "step": 7652 + }, + { + "epoch": 6.77, + "learning_rate": 1.540662736936987e-05, + "loss": 0.0926, + "step": 7653 + }, + { + "epoch": 6.77, + "learning_rate": 1.5405421752473422e-05, + "loss": 0.0817, + "step": 7654 + }, + { + "epoch": 6.77, + "learning_rate": 1.5404216024565217e-05, + "loss": 0.0855, + "step": 7655 + }, + { + "epoch": 6.77, + "learning_rate": 1.5403010185670017e-05, + "loss": 0.1003, + "step": 7656 + }, + { + "epoch": 6.78, + "learning_rate": 1.540180423581258e-05, + "loss": 0.1009, + "step": 7657 + }, + { + "epoch": 6.78, + "learning_rate": 1.5400598175017682e-05, + "loss": 0.0869, + "step": 7658 + }, + { + "epoch": 6.78, + "learning_rate": 1.5399392003310088e-05, + "loss": 0.097, + "step": 7659 + }, + { + "epoch": 6.78, + "learning_rate": 1.5398185720714568e-05, + "loss": 0.0883, + "step": 7660 + }, + { + "epoch": 6.78, + "learning_rate": 1.5396979327255893e-05, + "loss": 0.0914, + "step": 7661 + }, + { + "epoch": 6.78, + "learning_rate": 1.5395772822958844e-05, + "loss": 0.0834, + "step": 7662 + }, + { + "epoch": 6.78, + "learning_rate": 1.5394566207848204e-05, + "loss": 0.0981, + "step": 7663 + }, + { + "epoch": 6.78, + "learning_rate": 1.5393359481948742e-05, + "loss": 0.0894, + "step": 7664 + }, + { + "epoch": 6.78, + "learning_rate": 1.539215264528524e-05, + "loss": 0.0889, + "step": 7665 + }, + { + "epoch": 6.78, + "learning_rate": 1.53909456978825e-05, + "loss": 0.0981, + "step": 7666 + }, + { + "epoch": 6.78, + "learning_rate": 1.538973863976529e-05, + "loss": 0.0958, + "step": 7667 + }, + { + "epoch": 6.78, + "learning_rate": 1.5388531470958408e-05, + "loss": 0.0918, + "step": 7668 + }, + { + "epoch": 6.79, + "learning_rate": 1.5387324191486644e-05, + "loss": 0.1016, + "step": 7669 + }, + { + "epoch": 6.79, + "learning_rate": 1.5386116801374797e-05, + "loss": 0.0955, + "step": 7670 + }, + { + "epoch": 6.79, + "learning_rate": 1.5384909300647657e-05, + "loss": 0.0886, + "step": 7671 + }, + { + "epoch": 6.79, + "learning_rate": 1.5383701689330025e-05, + "loss": 0.1057, + "step": 7672 + }, + { + "epoch": 6.79, + "learning_rate": 1.5382493967446702e-05, + "loss": 0.0858, + "step": 7673 + }, + { + "epoch": 6.79, + "learning_rate": 1.538128613502249e-05, + "loss": 0.0971, + "step": 7674 + }, + { + "epoch": 6.79, + "learning_rate": 1.5380078192082195e-05, + "loss": 0.0928, + "step": 7675 + }, + { + "epoch": 6.79, + "learning_rate": 1.5378870138650624e-05, + "loss": 0.0861, + "step": 7676 + }, + { + "epoch": 6.79, + "learning_rate": 1.5377661974752594e-05, + "loss": 0.0886, + "step": 7677 + }, + { + "epoch": 6.79, + "learning_rate": 1.5376453700412905e-05, + "loss": 0.0849, + "step": 7678 + }, + { + "epoch": 6.79, + "learning_rate": 1.5375245315656377e-05, + "loss": 0.1004, + "step": 7679 + }, + { + "epoch": 6.8, + "learning_rate": 1.5374036820507833e-05, + "loss": 0.0896, + "step": 7680 + }, + { + "epoch": 6.8, + "learning_rate": 1.5372828214992083e-05, + "loss": 0.09, + "step": 7681 + }, + { + "epoch": 6.8, + "learning_rate": 1.537161949913395e-05, + "loss": 0.0903, + "step": 7682 + }, + { + "epoch": 6.8, + "learning_rate": 1.5370410672958263e-05, + "loss": 0.0932, + "step": 7683 + }, + { + "epoch": 6.8, + "learning_rate": 1.536920173648984e-05, + "loss": 0.104, + "step": 7684 + }, + { + "epoch": 6.8, + "learning_rate": 1.5367992689753512e-05, + "loss": 0.0966, + "step": 7685 + }, + { + "epoch": 6.8, + "learning_rate": 1.5366783532774112e-05, + "loss": 0.0899, + "step": 7686 + }, + { + "epoch": 6.8, + "learning_rate": 1.5365574265576474e-05, + "loss": 0.0935, + "step": 7687 + }, + { + "epoch": 6.8, + "learning_rate": 1.536436488818543e-05, + "loss": 0.0979, + "step": 7688 + }, + { + "epoch": 6.8, + "learning_rate": 1.536315540062581e-05, + "loss": 0.0862, + "step": 7689 + }, + { + "epoch": 6.8, + "learning_rate": 1.5361945802922466e-05, + "loss": 0.0988, + "step": 7690 + }, + { + "epoch": 6.81, + "learning_rate": 1.536073609510023e-05, + "loss": 0.0924, + "step": 7691 + }, + { + "epoch": 6.81, + "learning_rate": 1.535952627718395e-05, + "loss": 0.0898, + "step": 7692 + }, + { + "epoch": 6.81, + "learning_rate": 1.5358316349198476e-05, + "loss": 0.0958, + "step": 7693 + }, + { + "epoch": 6.81, + "learning_rate": 1.535710631116865e-05, + "loss": 0.0854, + "step": 7694 + }, + { + "epoch": 6.81, + "learning_rate": 1.5355896163119324e-05, + "loss": 0.106, + "step": 7695 + }, + { + "epoch": 6.81, + "learning_rate": 1.5354685905075354e-05, + "loss": 0.0821, + "step": 7696 + }, + { + "epoch": 6.81, + "learning_rate": 1.5353475537061592e-05, + "loss": 0.1036, + "step": 7697 + }, + { + "epoch": 6.81, + "learning_rate": 1.5352265059102896e-05, + "loss": 0.0929, + "step": 7698 + }, + { + "epoch": 6.81, + "learning_rate": 1.5351054471224127e-05, + "loss": 0.0943, + "step": 7699 + }, + { + "epoch": 6.81, + "learning_rate": 1.5349843773450146e-05, + "loss": 0.0927, + "step": 7700 + }, + { + "epoch": 6.81, + "learning_rate": 1.534863296580582e-05, + "loss": 0.0898, + "step": 7701 + }, + { + "epoch": 6.81, + "learning_rate": 1.534742204831601e-05, + "loss": 0.0959, + "step": 7702 + }, + { + "epoch": 6.82, + "learning_rate": 1.534621102100559e-05, + "loss": 0.0907, + "step": 7703 + }, + { + "epoch": 6.82, + "learning_rate": 1.5344999883899426e-05, + "loss": 0.0979, + "step": 7704 + }, + { + "epoch": 6.82, + "learning_rate": 1.5343788637022394e-05, + "loss": 0.0939, + "step": 7705 + }, + { + "epoch": 6.82, + "learning_rate": 1.5342577280399373e-05, + "loss": 0.0808, + "step": 7706 + }, + { + "epoch": 6.82, + "learning_rate": 1.5341365814055237e-05, + "loss": 0.1, + "step": 7707 + }, + { + "epoch": 6.82, + "learning_rate": 1.5340154238014866e-05, + "loss": 0.0875, + "step": 7708 + }, + { + "epoch": 6.82, + "learning_rate": 1.533894255230314e-05, + "loss": 0.0894, + "step": 7709 + }, + { + "epoch": 6.82, + "learning_rate": 1.5337730756944948e-05, + "loss": 0.1092, + "step": 7710 + }, + { + "epoch": 6.82, + "learning_rate": 1.5336518851965177e-05, + "loss": 0.088, + "step": 7711 + }, + { + "epoch": 6.82, + "learning_rate": 1.5335306837388713e-05, + "loss": 0.084, + "step": 7712 + }, + { + "epoch": 6.82, + "learning_rate": 1.5334094713240447e-05, + "loss": 0.1009, + "step": 7713 + }, + { + "epoch": 6.83, + "learning_rate": 1.533288247954527e-05, + "loss": 0.0888, + "step": 7714 + }, + { + "epoch": 6.83, + "learning_rate": 1.5331670136328088e-05, + "loss": 0.0955, + "step": 7715 + }, + { + "epoch": 6.83, + "learning_rate": 1.5330457683613794e-05, + "loss": 0.1031, + "step": 7716 + }, + { + "epoch": 6.83, + "learning_rate": 1.5329245121427278e-05, + "loss": 0.0884, + "step": 7717 + }, + { + "epoch": 6.83, + "learning_rate": 1.5328032449793462e-05, + "loss": 0.0866, + "step": 7718 + }, + { + "epoch": 6.83, + "learning_rate": 1.5326819668737234e-05, + "loss": 0.0964, + "step": 7719 + }, + { + "epoch": 6.83, + "learning_rate": 1.532560677828351e-05, + "loss": 0.1, + "step": 7720 + }, + { + "epoch": 6.83, + "learning_rate": 1.5324393778457193e-05, + "loss": 0.0897, + "step": 7721 + }, + { + "epoch": 6.83, + "learning_rate": 1.5323180669283203e-05, + "loss": 0.0873, + "step": 7722 + }, + { + "epoch": 6.83, + "learning_rate": 1.5321967450786445e-05, + "loss": 0.0956, + "step": 7723 + }, + { + "epoch": 6.83, + "learning_rate": 1.5320754122991835e-05, + "loss": 0.0894, + "step": 7724 + }, + { + "epoch": 6.84, + "learning_rate": 1.5319540685924303e-05, + "loss": 0.0878, + "step": 7725 + }, + { + "epoch": 6.84, + "learning_rate": 1.531832713960876e-05, + "loss": 0.0915, + "step": 7726 + }, + { + "epoch": 6.84, + "learning_rate": 1.531711348407013e-05, + "loss": 0.0946, + "step": 7727 + }, + { + "epoch": 6.84, + "learning_rate": 1.5315899719333333e-05, + "loss": 0.0869, + "step": 7728 + }, + { + "epoch": 6.84, + "learning_rate": 1.5314685845423303e-05, + "loss": 0.0928, + "step": 7729 + }, + { + "epoch": 6.84, + "learning_rate": 1.531347186236497e-05, + "loss": 0.0975, + "step": 7730 + }, + { + "epoch": 6.84, + "learning_rate": 1.5312257770183266e-05, + "loss": 0.0984, + "step": 7731 + }, + { + "epoch": 6.84, + "learning_rate": 1.531104356890312e-05, + "loss": 0.0861, + "step": 7732 + }, + { + "epoch": 6.84, + "learning_rate": 1.5309829258549475e-05, + "loss": 0.0852, + "step": 7733 + }, + { + "epoch": 6.84, + "learning_rate": 1.5308614839147256e-05, + "loss": 0.0876, + "step": 7734 + }, + { + "epoch": 6.84, + "learning_rate": 1.530740031072142e-05, + "loss": 0.0992, + "step": 7735 + }, + { + "epoch": 6.84, + "learning_rate": 1.5306185673296903e-05, + "loss": 0.0803, + "step": 7736 + }, + { + "epoch": 6.85, + "learning_rate": 1.5304970926898645e-05, + "loss": 0.0907, + "step": 7737 + }, + { + "epoch": 6.85, + "learning_rate": 1.5303756071551604e-05, + "loss": 0.0995, + "step": 7738 + }, + { + "epoch": 6.85, + "learning_rate": 1.530254110728072e-05, + "loss": 0.0852, + "step": 7739 + }, + { + "epoch": 6.85, + "learning_rate": 1.5301326034110952e-05, + "loss": 0.0983, + "step": 7740 + }, + { + "epoch": 6.85, + "learning_rate": 1.530011085206725e-05, + "loss": 0.0951, + "step": 7741 + }, + { + "epoch": 6.85, + "learning_rate": 1.529889556117457e-05, + "loss": 0.092, + "step": 7742 + }, + { + "epoch": 6.85, + "learning_rate": 1.529768016145787e-05, + "loss": 0.0945, + "step": 7743 + }, + { + "epoch": 6.85, + "learning_rate": 1.5296464652942113e-05, + "loss": 0.0929, + "step": 7744 + }, + { + "epoch": 6.85, + "learning_rate": 1.5295249035652263e-05, + "loss": 0.0884, + "step": 7745 + }, + { + "epoch": 6.85, + "learning_rate": 1.5294033309613287e-05, + "loss": 0.0925, + "step": 7746 + }, + { + "epoch": 6.85, + "learning_rate": 1.5292817474850147e-05, + "loss": 0.0886, + "step": 7747 + }, + { + "epoch": 6.86, + "learning_rate": 1.5291601531387814e-05, + "loss": 0.092, + "step": 7748 + }, + { + "epoch": 6.86, + "learning_rate": 1.5290385479251263e-05, + "loss": 0.099, + "step": 7749 + }, + { + "epoch": 6.86, + "learning_rate": 1.5289169318465463e-05, + "loss": 0.0921, + "step": 7750 + }, + { + "epoch": 6.86, + "learning_rate": 1.5287953049055396e-05, + "loss": 0.0893, + "step": 7751 + }, + { + "epoch": 6.86, + "learning_rate": 1.528673667104604e-05, + "loss": 0.0975, + "step": 7752 + }, + { + "epoch": 6.86, + "learning_rate": 1.528552018446237e-05, + "loss": 0.0868, + "step": 7753 + }, + { + "epoch": 6.86, + "learning_rate": 1.528430358932938e-05, + "loss": 0.0862, + "step": 7754 + }, + { + "epoch": 6.86, + "learning_rate": 1.5283086885672044e-05, + "loss": 0.0896, + "step": 7755 + }, + { + "epoch": 6.86, + "learning_rate": 1.5281870073515353e-05, + "loss": 0.0957, + "step": 7756 + }, + { + "epoch": 6.86, + "learning_rate": 1.5280653152884303e-05, + "loss": 0.0853, + "step": 7757 + }, + { + "epoch": 6.86, + "learning_rate": 1.5279436123803877e-05, + "loss": 0.0934, + "step": 7758 + }, + { + "epoch": 6.87, + "learning_rate": 1.5278218986299074e-05, + "loss": 0.1013, + "step": 7759 + }, + { + "epoch": 6.87, + "learning_rate": 1.5277001740394893e-05, + "loss": 0.1031, + "step": 7760 + }, + { + "epoch": 6.87, + "learning_rate": 1.527578438611633e-05, + "loss": 0.0881, + "step": 7761 + }, + { + "epoch": 6.87, + "learning_rate": 1.5274566923488382e-05, + "loss": 0.0901, + "step": 7762 + }, + { + "epoch": 6.87, + "learning_rate": 1.5273349352536057e-05, + "loss": 0.1004, + "step": 7763 + }, + { + "epoch": 6.87, + "learning_rate": 1.527213167328436e-05, + "loss": 0.093, + "step": 7764 + }, + { + "epoch": 6.87, + "learning_rate": 1.5270913885758296e-05, + "loss": 0.0884, + "step": 7765 + }, + { + "epoch": 6.87, + "learning_rate": 1.526969598998288e-05, + "loss": 0.0791, + "step": 7766 + }, + { + "epoch": 6.87, + "learning_rate": 1.5268477985983117e-05, + "loss": 0.0949, + "step": 7767 + }, + { + "epoch": 6.87, + "learning_rate": 1.5267259873784026e-05, + "loss": 0.0861, + "step": 7768 + }, + { + "epoch": 6.87, + "learning_rate": 1.5266041653410622e-05, + "loss": 0.0815, + "step": 7769 + }, + { + "epoch": 6.87, + "learning_rate": 1.5264823324887926e-05, + "loss": 0.0921, + "step": 7770 + }, + { + "epoch": 6.88, + "learning_rate": 1.5263604888240956e-05, + "loss": 0.0853, + "step": 7771 + }, + { + "epoch": 6.88, + "learning_rate": 1.5262386343494737e-05, + "loss": 0.0928, + "step": 7772 + }, + { + "epoch": 6.88, + "learning_rate": 1.5261167690674296e-05, + "loss": 0.1022, + "step": 7773 + }, + { + "epoch": 6.88, + "learning_rate": 1.5259948929804652e-05, + "loss": 0.0909, + "step": 7774 + }, + { + "epoch": 6.88, + "learning_rate": 1.525873006091085e-05, + "loss": 0.0894, + "step": 7775 + }, + { + "epoch": 6.88, + "learning_rate": 1.5257511084017904e-05, + "loss": 0.0937, + "step": 7776 + }, + { + "epoch": 6.88, + "learning_rate": 1.5256291999150863e-05, + "loss": 0.0876, + "step": 7777 + }, + { + "epoch": 6.88, + "learning_rate": 1.5255072806334758e-05, + "loss": 0.0889, + "step": 7778 + }, + { + "epoch": 6.88, + "learning_rate": 1.5253853505594625e-05, + "loss": 0.0929, + "step": 7779 + }, + { + "epoch": 6.88, + "learning_rate": 1.525263409695551e-05, + "loss": 0.0877, + "step": 7780 + }, + { + "epoch": 6.88, + "learning_rate": 1.5251414580442452e-05, + "loss": 0.096, + "step": 7781 + }, + { + "epoch": 6.89, + "learning_rate": 1.5250194956080501e-05, + "loss": 0.0952, + "step": 7782 + }, + { + "epoch": 6.89, + "learning_rate": 1.5248975223894697e-05, + "loss": 0.1048, + "step": 7783 + }, + { + "epoch": 6.89, + "learning_rate": 1.5247755383910097e-05, + "loss": 0.0933, + "step": 7784 + }, + { + "epoch": 6.89, + "learning_rate": 1.524653543615175e-05, + "loss": 0.0936, + "step": 7785 + }, + { + "epoch": 6.89, + "learning_rate": 1.5245315380644711e-05, + "loss": 0.1101, + "step": 7786 + }, + { + "epoch": 6.89, + "learning_rate": 1.5244095217414037e-05, + "loss": 0.0963, + "step": 7787 + }, + { + "epoch": 6.89, + "learning_rate": 1.5242874946484785e-05, + "loss": 0.0995, + "step": 7788 + }, + { + "epoch": 6.89, + "learning_rate": 1.5241654567882016e-05, + "loss": 0.0847, + "step": 7789 + }, + { + "epoch": 6.89, + "learning_rate": 1.5240434081630793e-05, + "loss": 0.0969, + "step": 7790 + }, + { + "epoch": 6.89, + "learning_rate": 1.5239213487756184e-05, + "loss": 0.0941, + "step": 7791 + }, + { + "epoch": 6.89, + "learning_rate": 1.5237992786283253e-05, + "loss": 0.1082, + "step": 7792 + }, + { + "epoch": 6.9, + "learning_rate": 1.523677197723707e-05, + "loss": 0.1017, + "step": 7793 + }, + { + "epoch": 6.9, + "learning_rate": 1.5235551060642708e-05, + "loss": 0.0946, + "step": 7794 + }, + { + "epoch": 6.9, + "learning_rate": 1.5234330036525243e-05, + "loss": 0.0986, + "step": 7795 + }, + { + "epoch": 6.9, + "learning_rate": 1.5233108904909748e-05, + "loss": 0.0973, + "step": 7796 + }, + { + "epoch": 6.9, + "learning_rate": 1.52318876658213e-05, + "loss": 0.1016, + "step": 7797 + }, + { + "epoch": 6.9, + "learning_rate": 1.5230666319284985e-05, + "loss": 0.0973, + "step": 7798 + }, + { + "epoch": 6.9, + "learning_rate": 1.5229444865325888e-05, + "loss": 0.0899, + "step": 7799 + }, + { + "epoch": 6.9, + "learning_rate": 1.5228223303969083e-05, + "loss": 0.0982, + "step": 7800 + }, + { + "epoch": 6.9, + "learning_rate": 1.5227001635239668e-05, + "loss": 0.0985, + "step": 7801 + }, + { + "epoch": 6.9, + "learning_rate": 1.5225779859162727e-05, + "loss": 0.0948, + "step": 7802 + }, + { + "epoch": 6.9, + "learning_rate": 1.5224557975763352e-05, + "loss": 0.0875, + "step": 7803 + }, + { + "epoch": 6.91, + "learning_rate": 1.522333598506664e-05, + "loss": 0.0958, + "step": 7804 + }, + { + "epoch": 6.91, + "learning_rate": 1.5222113887097685e-05, + "loss": 0.0787, + "step": 7805 + }, + { + "epoch": 6.91, + "learning_rate": 1.5220891681881586e-05, + "loss": 0.096, + "step": 7806 + }, + { + "epoch": 6.91, + "learning_rate": 1.5219669369443443e-05, + "loss": 0.0893, + "step": 7807 + }, + { + "epoch": 6.91, + "learning_rate": 1.5218446949808358e-05, + "loss": 0.0981, + "step": 7808 + }, + { + "epoch": 6.91, + "learning_rate": 1.5217224423001438e-05, + "loss": 0.0868, + "step": 7809 + }, + { + "epoch": 6.91, + "learning_rate": 1.521600178904779e-05, + "loss": 0.1023, + "step": 7810 + }, + { + "epoch": 6.91, + "learning_rate": 1.521477904797252e-05, + "loss": 0.0906, + "step": 7811 + }, + { + "epoch": 6.91, + "learning_rate": 1.5213556199800743e-05, + "loss": 0.0881, + "step": 7812 + }, + { + "epoch": 6.91, + "learning_rate": 1.5212333244557575e-05, + "loss": 0.0934, + "step": 7813 + }, + { + "epoch": 6.91, + "learning_rate": 1.5211110182268127e-05, + "loss": 0.0908, + "step": 7814 + }, + { + "epoch": 6.91, + "learning_rate": 1.5209887012957518e-05, + "loss": 0.1058, + "step": 7815 + }, + { + "epoch": 6.92, + "learning_rate": 1.520866373665087e-05, + "loss": 0.0969, + "step": 7816 + }, + { + "epoch": 6.92, + "learning_rate": 1.5207440353373307e-05, + "loss": 0.0892, + "step": 7817 + }, + { + "epoch": 6.92, + "learning_rate": 1.520621686314995e-05, + "loss": 0.0826, + "step": 7818 + }, + { + "epoch": 6.92, + "learning_rate": 1.5204993266005925e-05, + "loss": 0.0957, + "step": 7819 + }, + { + "epoch": 6.92, + "learning_rate": 1.5203769561966369e-05, + "loss": 0.086, + "step": 7820 + }, + { + "epoch": 6.92, + "learning_rate": 1.5202545751056405e-05, + "loss": 0.0879, + "step": 7821 + }, + { + "epoch": 6.92, + "learning_rate": 1.5201321833301168e-05, + "loss": 0.088, + "step": 7822 + }, + { + "epoch": 6.92, + "learning_rate": 1.52000978087258e-05, + "loss": 0.0857, + "step": 7823 + }, + { + "epoch": 6.92, + "learning_rate": 1.5198873677355433e-05, + "loss": 0.0917, + "step": 7824 + }, + { + "epoch": 6.92, + "learning_rate": 1.519764943921521e-05, + "loss": 0.095, + "step": 7825 + }, + { + "epoch": 6.92, + "learning_rate": 1.5196425094330267e-05, + "loss": 0.0979, + "step": 7826 + }, + { + "epoch": 6.93, + "learning_rate": 1.5195200642725758e-05, + "loss": 0.0882, + "step": 7827 + }, + { + "epoch": 6.93, + "learning_rate": 1.5193976084426823e-05, + "loss": 0.0884, + "step": 7828 + }, + { + "epoch": 6.93, + "learning_rate": 1.5192751419458614e-05, + "loss": 0.0973, + "step": 7829 + }, + { + "epoch": 6.93, + "learning_rate": 1.519152664784628e-05, + "loss": 0.0928, + "step": 7830 + }, + { + "epoch": 6.93, + "learning_rate": 1.5190301769614975e-05, + "loss": 0.0971, + "step": 7831 + }, + { + "epoch": 6.93, + "learning_rate": 1.5189076784789855e-05, + "loss": 0.0913, + "step": 7832 + }, + { + "epoch": 6.93, + "learning_rate": 1.5187851693396078e-05, + "loss": 0.0945, + "step": 7833 + }, + { + "epoch": 6.93, + "learning_rate": 1.5186626495458808e-05, + "loss": 0.0829, + "step": 7834 + }, + { + "epoch": 6.93, + "learning_rate": 1.5185401191003193e-05, + "loss": 0.0876, + "step": 7835 + }, + { + "epoch": 6.93, + "learning_rate": 1.5184175780054411e-05, + "loss": 0.0999, + "step": 7836 + }, + { + "epoch": 6.93, + "learning_rate": 1.5182950262637626e-05, + "loss": 0.0826, + "step": 7837 + }, + { + "epoch": 6.94, + "learning_rate": 1.5181724638778001e-05, + "loss": 0.0972, + "step": 7838 + }, + { + "epoch": 6.94, + "learning_rate": 1.5180498908500713e-05, + "loss": 0.0866, + "step": 7839 + }, + { + "epoch": 6.94, + "learning_rate": 1.5179273071830932e-05, + "loss": 0.1062, + "step": 7840 + }, + { + "epoch": 6.94, + "learning_rate": 1.5178047128793831e-05, + "loss": 0.0885, + "step": 7841 + }, + { + "epoch": 6.94, + "learning_rate": 1.5176821079414591e-05, + "loss": 0.0938, + "step": 7842 + }, + { + "epoch": 6.94, + "learning_rate": 1.517559492371839e-05, + "loss": 0.094, + "step": 7843 + }, + { + "epoch": 6.94, + "learning_rate": 1.5174368661730415e-05, + "loss": 0.1023, + "step": 7844 + }, + { + "epoch": 6.94, + "learning_rate": 1.517314229347584e-05, + "loss": 0.0969, + "step": 7845 + }, + { + "epoch": 6.94, + "learning_rate": 1.5171915818979854e-05, + "loss": 0.1053, + "step": 7846 + }, + { + "epoch": 6.94, + "learning_rate": 1.5170689238267651e-05, + "loss": 0.0857, + "step": 7847 + }, + { + "epoch": 6.94, + "learning_rate": 1.5169462551364413e-05, + "loss": 0.097, + "step": 7848 + }, + { + "epoch": 6.94, + "learning_rate": 1.5168235758295342e-05, + "loss": 0.0936, + "step": 7849 + }, + { + "epoch": 6.95, + "learning_rate": 1.5167008859085626e-05, + "loss": 0.0874, + "step": 7850 + }, + { + "epoch": 6.95, + "learning_rate": 1.5165781853760467e-05, + "loss": 0.0822, + "step": 7851 + }, + { + "epoch": 6.95, + "learning_rate": 1.5164554742345057e-05, + "loss": 0.0917, + "step": 7852 + }, + { + "epoch": 6.95, + "learning_rate": 1.5163327524864601e-05, + "loss": 0.0804, + "step": 7853 + }, + { + "epoch": 6.95, + "learning_rate": 1.5162100201344306e-05, + "loss": 0.1012, + "step": 7854 + }, + { + "epoch": 6.95, + "learning_rate": 1.5160872771809372e-05, + "loss": 0.1012, + "step": 7855 + }, + { + "epoch": 6.95, + "learning_rate": 1.515964523628501e-05, + "loss": 0.0925, + "step": 7856 + }, + { + "epoch": 6.95, + "learning_rate": 1.5158417594796431e-05, + "loss": 0.0943, + "step": 7857 + }, + { + "epoch": 6.95, + "learning_rate": 1.5157189847368848e-05, + "loss": 0.1041, + "step": 7858 + }, + { + "epoch": 6.95, + "learning_rate": 1.5155961994027469e-05, + "loss": 0.0996, + "step": 7859 + }, + { + "epoch": 6.95, + "learning_rate": 1.5154734034797517e-05, + "loss": 0.087, + "step": 7860 + }, + { + "epoch": 6.96, + "learning_rate": 1.5153505969704201e-05, + "loss": 0.0932, + "step": 7861 + }, + { + "epoch": 6.96, + "learning_rate": 1.5152277798772758e-05, + "loss": 0.0869, + "step": 7862 + }, + { + "epoch": 6.96, + "learning_rate": 1.5151049522028398e-05, + "loss": 0.0944, + "step": 7863 + }, + { + "epoch": 6.96, + "learning_rate": 1.5149821139496354e-05, + "loss": 0.1131, + "step": 7864 + }, + { + "epoch": 6.96, + "learning_rate": 1.514859265120185e-05, + "loss": 0.0896, + "step": 7865 + }, + { + "epoch": 6.96, + "learning_rate": 1.5147364057170113e-05, + "loss": 0.0886, + "step": 7866 + }, + { + "epoch": 6.96, + "learning_rate": 1.5146135357426377e-05, + "loss": 0.0841, + "step": 7867 + }, + { + "epoch": 6.96, + "learning_rate": 1.5144906551995879e-05, + "loss": 0.0901, + "step": 7868 + }, + { + "epoch": 6.96, + "learning_rate": 1.5143677640903853e-05, + "loss": 0.089, + "step": 7869 + }, + { + "epoch": 6.96, + "learning_rate": 1.5142448624175533e-05, + "loss": 0.0866, + "step": 7870 + }, + { + "epoch": 6.96, + "learning_rate": 1.5141219501836166e-05, + "loss": 0.1058, + "step": 7871 + }, + { + "epoch": 6.97, + "learning_rate": 1.5139990273910992e-05, + "loss": 0.0866, + "step": 7872 + }, + { + "epoch": 6.97, + "learning_rate": 1.5138760940425257e-05, + "loss": 0.0813, + "step": 7873 + }, + { + "epoch": 6.97, + "learning_rate": 1.5137531501404201e-05, + "loss": 0.0934, + "step": 7874 + }, + { + "epoch": 6.97, + "learning_rate": 1.5136301956873084e-05, + "loss": 0.0876, + "step": 7875 + }, + { + "epoch": 6.97, + "learning_rate": 1.5135072306857152e-05, + "loss": 0.1049, + "step": 7876 + }, + { + "epoch": 6.97, + "learning_rate": 1.5133842551381658e-05, + "loss": 0.0878, + "step": 7877 + }, + { + "epoch": 6.97, + "learning_rate": 1.5132612690471856e-05, + "loss": 0.1037, + "step": 7878 + }, + { + "epoch": 6.97, + "learning_rate": 1.5131382724153008e-05, + "loss": 0.084, + "step": 7879 + }, + { + "epoch": 6.97, + "learning_rate": 1.513015265245037e-05, + "loss": 0.091, + "step": 7880 + }, + { + "epoch": 6.97, + "learning_rate": 1.5128922475389207e-05, + "loss": 0.0959, + "step": 7881 + }, + { + "epoch": 6.97, + "learning_rate": 1.5127692192994782e-05, + "loss": 0.0909, + "step": 7882 + }, + { + "epoch": 6.97, + "learning_rate": 1.5126461805292363e-05, + "loss": 0.0928, + "step": 7883 + }, + { + "epoch": 6.98, + "learning_rate": 1.5125231312307218e-05, + "loss": 0.0871, + "step": 7884 + }, + { + "epoch": 6.98, + "learning_rate": 1.5124000714064615e-05, + "loss": 0.0891, + "step": 7885 + }, + { + "epoch": 6.98, + "learning_rate": 1.512277001058983e-05, + "loss": 0.1018, + "step": 7886 + }, + { + "epoch": 6.98, + "learning_rate": 1.5121539201908136e-05, + "loss": 0.1039, + "step": 7887 + }, + { + "epoch": 6.98, + "learning_rate": 1.5120308288044814e-05, + "loss": 0.0896, + "step": 7888 + }, + { + "epoch": 6.98, + "learning_rate": 1.5119077269025138e-05, + "loss": 0.0865, + "step": 7889 + }, + { + "epoch": 6.98, + "learning_rate": 1.5117846144874395e-05, + "loss": 0.0845, + "step": 7890 + }, + { + "epoch": 6.98, + "learning_rate": 1.5116614915617866e-05, + "loss": 0.0838, + "step": 7891 + }, + { + "epoch": 6.98, + "learning_rate": 1.5115383581280835e-05, + "loss": 0.0838, + "step": 7892 + }, + { + "epoch": 6.98, + "learning_rate": 1.5114152141888592e-05, + "loss": 0.0885, + "step": 7893 + }, + { + "epoch": 6.98, + "learning_rate": 1.511292059746643e-05, + "loss": 0.0902, + "step": 7894 + }, + { + "epoch": 6.99, + "learning_rate": 1.5111688948039636e-05, + "loss": 0.0993, + "step": 7895 + }, + { + "epoch": 6.99, + "learning_rate": 1.5110457193633508e-05, + "loss": 0.0982, + "step": 7896 + }, + { + "epoch": 6.99, + "learning_rate": 1.5109225334273343e-05, + "loss": 0.1029, + "step": 7897 + }, + { + "epoch": 6.99, + "learning_rate": 1.510799336998444e-05, + "loss": 0.1029, + "step": 7898 + }, + { + "epoch": 6.99, + "learning_rate": 1.5106761300792095e-05, + "loss": 0.0948, + "step": 7899 + }, + { + "epoch": 6.99, + "learning_rate": 1.5105529126721617e-05, + "loss": 0.1028, + "step": 7900 + }, + { + "epoch": 6.99, + "learning_rate": 1.5104296847798307e-05, + "loss": 0.093, + "step": 7901 + }, + { + "epoch": 6.99, + "learning_rate": 1.5103064464047479e-05, + "loss": 0.0982, + "step": 7902 + }, + { + "epoch": 6.99, + "learning_rate": 1.5101831975494431e-05, + "loss": 0.0906, + "step": 7903 + }, + { + "epoch": 6.99, + "learning_rate": 1.510059938216449e-05, + "loss": 0.094, + "step": 7904 + }, + { + "epoch": 6.99, + "learning_rate": 1.509936668408296e-05, + "loss": 0.0922, + "step": 7905 + }, + { + "epoch": 7.0, + "learning_rate": 1.5098133881275156e-05, + "loss": 0.1001, + "step": 7906 + }, + { + "epoch": 7.0, + "learning_rate": 1.5096900973766402e-05, + "loss": 0.0933, + "step": 7907 + }, + { + "epoch": 7.0, + "learning_rate": 1.5095667961582012e-05, + "loss": 0.1156, + "step": 7908 + }, + { + "epoch": 7.0, + "learning_rate": 1.5094434844747314e-05, + "loss": 0.0952, + "step": 7909 + }, + { + "epoch": 7.0, + "learning_rate": 1.5093201623287631e-05, + "loss": 0.0861, + "step": 7910 + }, + { + "epoch": 7.0, + "learning_rate": 1.5091968297228289e-05, + "loss": 0.0956, + "step": 7911 + }, + { + "epoch": 7.0, + "learning_rate": 1.509073486659462e-05, + "loss": 0.067, + "step": 7912 + }, + { + "epoch": 7.0, + "learning_rate": 1.5089501331411947e-05, + "loss": 0.0491, + "step": 7913 + }, + { + "epoch": 7.0, + "learning_rate": 1.5088267691705616e-05, + "loss": 0.05, + "step": 7914 + }, + { + "epoch": 7.0, + "learning_rate": 1.5087033947500952e-05, + "loss": 0.0407, + "step": 7915 + }, + { + "epoch": 7.0, + "learning_rate": 1.508580009882329e-05, + "loss": 0.0512, + "step": 7916 + }, + { + "epoch": 7.01, + "learning_rate": 1.5084566145697983e-05, + "loss": 0.0506, + "step": 7917 + }, + { + "epoch": 7.01, + "learning_rate": 1.5083332088150364e-05, + "loss": 0.0488, + "step": 7918 + }, + { + "epoch": 7.01, + "learning_rate": 1.5082097926205777e-05, + "loss": 0.0519, + "step": 7919 + }, + { + "epoch": 7.01, + "learning_rate": 1.5080863659889566e-05, + "loss": 0.0479, + "step": 7920 + }, + { + "epoch": 7.01, + "learning_rate": 1.5079629289227089e-05, + "loss": 0.0509, + "step": 7921 + }, + { + "epoch": 7.01, + "learning_rate": 1.5078394814243687e-05, + "loss": 0.0503, + "step": 7922 + }, + { + "epoch": 7.01, + "learning_rate": 1.5077160234964716e-05, + "loss": 0.0528, + "step": 7923 + }, + { + "epoch": 7.01, + "learning_rate": 1.5075925551415529e-05, + "loss": 0.047, + "step": 7924 + }, + { + "epoch": 7.01, + "learning_rate": 1.5074690763621487e-05, + "loss": 0.0512, + "step": 7925 + }, + { + "epoch": 7.01, + "learning_rate": 1.5073455871607942e-05, + "loss": 0.0483, + "step": 7926 + }, + { + "epoch": 7.01, + "learning_rate": 1.5072220875400261e-05, + "loss": 0.0456, + "step": 7927 + }, + { + "epoch": 7.01, + "learning_rate": 1.5070985775023808e-05, + "loss": 0.045, + "step": 7928 + }, + { + "epoch": 7.02, + "learning_rate": 1.5069750570503945e-05, + "loss": 0.057, + "step": 7929 + }, + { + "epoch": 7.02, + "learning_rate": 1.5068515261866039e-05, + "loss": 0.0483, + "step": 7930 + }, + { + "epoch": 7.02, + "learning_rate": 1.506727984913546e-05, + "loss": 0.0487, + "step": 7931 + }, + { + "epoch": 7.02, + "learning_rate": 1.5066044332337586e-05, + "loss": 0.0569, + "step": 7932 + }, + { + "epoch": 7.02, + "learning_rate": 1.5064808711497781e-05, + "loss": 0.0544, + "step": 7933 + }, + { + "epoch": 7.02, + "learning_rate": 1.5063572986641423e-05, + "loss": 0.0465, + "step": 7934 + }, + { + "epoch": 7.02, + "learning_rate": 1.5062337157793901e-05, + "loss": 0.0472, + "step": 7935 + }, + { + "epoch": 7.02, + "learning_rate": 1.5061101224980585e-05, + "loss": 0.0548, + "step": 7936 + }, + { + "epoch": 7.02, + "learning_rate": 1.5059865188226859e-05, + "loss": 0.0453, + "step": 7937 + }, + { + "epoch": 7.02, + "learning_rate": 1.5058629047558106e-05, + "loss": 0.0416, + "step": 7938 + }, + { + "epoch": 7.02, + "learning_rate": 1.505739280299972e-05, + "loss": 0.0484, + "step": 7939 + }, + { + "epoch": 7.03, + "learning_rate": 1.5056156454577082e-05, + "loss": 0.0405, + "step": 7940 + }, + { + "epoch": 7.03, + "learning_rate": 1.5054920002315587e-05, + "loss": 0.0536, + "step": 7941 + }, + { + "epoch": 7.03, + "learning_rate": 1.5053683446240631e-05, + "loss": 0.051, + "step": 7942 + }, + { + "epoch": 7.03, + "learning_rate": 1.5052446786377602e-05, + "loss": 0.0475, + "step": 7943 + }, + { + "epoch": 7.03, + "learning_rate": 1.5051210022751901e-05, + "loss": 0.039, + "step": 7944 + }, + { + "epoch": 7.03, + "learning_rate": 1.5049973155388929e-05, + "loss": 0.0412, + "step": 7945 + }, + { + "epoch": 7.03, + "learning_rate": 1.5048736184314085e-05, + "loss": 0.041, + "step": 7946 + }, + { + "epoch": 7.03, + "learning_rate": 1.5047499109552775e-05, + "loss": 0.043, + "step": 7947 + }, + { + "epoch": 7.03, + "learning_rate": 1.5046261931130405e-05, + "loss": 0.0481, + "step": 7948 + }, + { + "epoch": 7.03, + "learning_rate": 1.5045024649072384e-05, + "loss": 0.0561, + "step": 7949 + }, + { + "epoch": 7.03, + "learning_rate": 1.5043787263404118e-05, + "loss": 0.0437, + "step": 7950 + }, + { + "epoch": 7.04, + "learning_rate": 1.5042549774151023e-05, + "loss": 0.0451, + "step": 7951 + }, + { + "epoch": 7.04, + "learning_rate": 1.5041312181338513e-05, + "loss": 0.0479, + "step": 7952 + }, + { + "epoch": 7.04, + "learning_rate": 1.5040074484992e-05, + "loss": 0.0487, + "step": 7953 + }, + { + "epoch": 7.04, + "learning_rate": 1.5038836685136908e-05, + "loss": 0.0493, + "step": 7954 + }, + { + "epoch": 7.04, + "learning_rate": 1.5037598781798658e-05, + "loss": 0.0446, + "step": 7955 + }, + { + "epoch": 7.04, + "learning_rate": 1.5036360775002673e-05, + "loss": 0.0455, + "step": 7956 + }, + { + "epoch": 7.04, + "learning_rate": 1.5035122664774374e-05, + "loss": 0.0362, + "step": 7957 + }, + { + "epoch": 7.04, + "learning_rate": 1.5033884451139188e-05, + "loss": 0.0561, + "step": 7958 + }, + { + "epoch": 7.04, + "learning_rate": 1.5032646134122551e-05, + "loss": 0.045, + "step": 7959 + }, + { + "epoch": 7.04, + "learning_rate": 1.5031407713749888e-05, + "loss": 0.0482, + "step": 7960 + }, + { + "epoch": 7.04, + "learning_rate": 1.5030169190046637e-05, + "loss": 0.0414, + "step": 7961 + }, + { + "epoch": 7.04, + "learning_rate": 1.502893056303823e-05, + "loss": 0.05, + "step": 7962 + }, + { + "epoch": 7.05, + "learning_rate": 1.5027691832750109e-05, + "loss": 0.0475, + "step": 7963 + }, + { + "epoch": 7.05, + "learning_rate": 1.502645299920771e-05, + "loss": 0.0415, + "step": 7964 + }, + { + "epoch": 7.05, + "learning_rate": 1.5025214062436475e-05, + "loss": 0.0455, + "step": 7965 + }, + { + "epoch": 7.05, + "learning_rate": 1.5023975022461852e-05, + "loss": 0.0448, + "step": 7966 + }, + { + "epoch": 7.05, + "learning_rate": 1.5022735879309282e-05, + "loss": 0.0459, + "step": 7967 + }, + { + "epoch": 7.05, + "learning_rate": 1.502149663300422e-05, + "loss": 0.0474, + "step": 7968 + }, + { + "epoch": 7.05, + "learning_rate": 1.5020257283572112e-05, + "loss": 0.0505, + "step": 7969 + }, + { + "epoch": 7.05, + "learning_rate": 1.5019017831038412e-05, + "loss": 0.0452, + "step": 7970 + }, + { + "epoch": 7.05, + "learning_rate": 1.5017778275428575e-05, + "loss": 0.0428, + "step": 7971 + }, + { + "epoch": 7.05, + "learning_rate": 1.5016538616768054e-05, + "loss": 0.0425, + "step": 7972 + }, + { + "epoch": 7.05, + "learning_rate": 1.5015298855082314e-05, + "loss": 0.0485, + "step": 7973 + }, + { + "epoch": 7.06, + "learning_rate": 1.5014058990396813e-05, + "loss": 0.0398, + "step": 7974 + }, + { + "epoch": 7.06, + "learning_rate": 1.5012819022737015e-05, + "loss": 0.0418, + "step": 7975 + }, + { + "epoch": 7.06, + "learning_rate": 1.5011578952128384e-05, + "loss": 0.0494, + "step": 7976 + }, + { + "epoch": 7.06, + "learning_rate": 1.5010338778596392e-05, + "loss": 0.0524, + "step": 7977 + }, + { + "epoch": 7.06, + "learning_rate": 1.50090985021665e-05, + "loss": 0.0435, + "step": 7978 + }, + { + "epoch": 7.06, + "learning_rate": 1.5007858122864186e-05, + "loss": 0.0543, + "step": 7979 + }, + { + "epoch": 7.06, + "learning_rate": 1.5006617640714926e-05, + "loss": 0.0502, + "step": 7980 + }, + { + "epoch": 7.06, + "learning_rate": 1.500537705574419e-05, + "loss": 0.0434, + "step": 7981 + }, + { + "epoch": 7.06, + "learning_rate": 1.5004136367977458e-05, + "loss": 0.0428, + "step": 7982 + }, + { + "epoch": 7.06, + "learning_rate": 1.5002895577440214e-05, + "loss": 0.0427, + "step": 7983 + }, + { + "epoch": 7.06, + "learning_rate": 1.5001654684157934e-05, + "loss": 0.0425, + "step": 7984 + }, + { + "epoch": 7.07, + "learning_rate": 1.5000413688156106e-05, + "loss": 0.0379, + "step": 7985 + }, + { + "epoch": 7.07, + "learning_rate": 1.4999172589460217e-05, + "loss": 0.0446, + "step": 7986 + }, + { + "epoch": 7.07, + "learning_rate": 1.499793138809575e-05, + "loss": 0.044, + "step": 7987 + }, + { + "epoch": 7.07, + "learning_rate": 1.4996690084088206e-05, + "loss": 0.0377, + "step": 7988 + }, + { + "epoch": 7.07, + "learning_rate": 1.4995448677463069e-05, + "loss": 0.0442, + "step": 7989 + }, + { + "epoch": 7.07, + "learning_rate": 1.4994207168245836e-05, + "loss": 0.0485, + "step": 7990 + }, + { + "epoch": 7.07, + "learning_rate": 1.4992965556462008e-05, + "loss": 0.0507, + "step": 7991 + }, + { + "epoch": 7.07, + "learning_rate": 1.4991723842137079e-05, + "loss": 0.0436, + "step": 7992 + }, + { + "epoch": 7.07, + "learning_rate": 1.4990482025296552e-05, + "loss": 0.053, + "step": 7993 + }, + { + "epoch": 7.07, + "learning_rate": 1.4989240105965927e-05, + "loss": 0.0477, + "step": 7994 + }, + { + "epoch": 7.07, + "learning_rate": 1.498799808417072e-05, + "loss": 0.0482, + "step": 7995 + }, + { + "epoch": 7.07, + "learning_rate": 1.4986755959936427e-05, + "loss": 0.0506, + "step": 7996 + }, + { + "epoch": 7.08, + "learning_rate": 1.4985513733288563e-05, + "loss": 0.0503, + "step": 7997 + }, + { + "epoch": 7.08, + "learning_rate": 1.498427140425264e-05, + "loss": 0.0476, + "step": 7998 + }, + { + "epoch": 7.08, + "learning_rate": 1.498302897285417e-05, + "loss": 0.047, + "step": 7999 + }, + { + "epoch": 7.08, + "learning_rate": 1.498178643911867e-05, + "loss": 0.0361, + "step": 8000 + }, + { + "epoch": 7.08, + "learning_rate": 1.4980543803071657e-05, + "loss": 0.0462, + "step": 8001 + }, + { + "epoch": 7.08, + "learning_rate": 1.4979301064738652e-05, + "loss": 0.041, + "step": 8002 + }, + { + "epoch": 7.08, + "learning_rate": 1.4978058224145177e-05, + "loss": 0.0482, + "step": 8003 + }, + { + "epoch": 7.08, + "learning_rate": 1.4976815281316755e-05, + "loss": 0.0489, + "step": 8004 + }, + { + "epoch": 7.08, + "learning_rate": 1.4975572236278919e-05, + "loss": 0.0423, + "step": 8005 + }, + { + "epoch": 7.08, + "learning_rate": 1.4974329089057189e-05, + "loss": 0.0531, + "step": 8006 + }, + { + "epoch": 7.08, + "learning_rate": 1.49730858396771e-05, + "loss": 0.0426, + "step": 8007 + }, + { + "epoch": 7.09, + "learning_rate": 1.497184248816418e-05, + "loss": 0.0427, + "step": 8008 + }, + { + "epoch": 7.09, + "learning_rate": 1.4970599034543976e-05, + "loss": 0.0471, + "step": 8009 + }, + { + "epoch": 7.09, + "learning_rate": 1.496935547884201e-05, + "loss": 0.051, + "step": 8010 + }, + { + "epoch": 7.09, + "learning_rate": 1.4968111821083829e-05, + "loss": 0.0494, + "step": 8011 + }, + { + "epoch": 7.09, + "learning_rate": 1.4966868061294975e-05, + "loss": 0.044, + "step": 8012 + }, + { + "epoch": 7.09, + "learning_rate": 1.4965624199500988e-05, + "loss": 0.052, + "step": 8013 + }, + { + "epoch": 7.09, + "learning_rate": 1.4964380235727413e-05, + "loss": 0.0486, + "step": 8014 + }, + { + "epoch": 7.09, + "learning_rate": 1.4963136169999801e-05, + "loss": 0.0486, + "step": 8015 + }, + { + "epoch": 7.09, + "learning_rate": 1.49618920023437e-05, + "loss": 0.0454, + "step": 8016 + }, + { + "epoch": 7.09, + "learning_rate": 1.496064773278466e-05, + "loss": 0.0439, + "step": 8017 + }, + { + "epoch": 7.09, + "learning_rate": 1.4959403361348234e-05, + "loss": 0.0463, + "step": 8018 + }, + { + "epoch": 7.1, + "learning_rate": 1.4958158888059984e-05, + "loss": 0.0489, + "step": 8019 + }, + { + "epoch": 7.1, + "learning_rate": 1.4956914312945461e-05, + "loss": 0.0438, + "step": 8020 + }, + { + "epoch": 7.1, + "learning_rate": 1.4955669636030225e-05, + "loss": 0.048, + "step": 8021 + }, + { + "epoch": 7.1, + "learning_rate": 1.4954424857339845e-05, + "loss": 0.046, + "step": 8022 + }, + { + "epoch": 7.1, + "learning_rate": 1.4953179976899878e-05, + "loss": 0.0431, + "step": 8023 + }, + { + "epoch": 7.1, + "learning_rate": 1.495193499473589e-05, + "loss": 0.04, + "step": 8024 + }, + { + "epoch": 7.1, + "learning_rate": 1.4950689910873457e-05, + "loss": 0.0473, + "step": 8025 + }, + { + "epoch": 7.1, + "learning_rate": 1.4949444725338145e-05, + "loss": 0.0425, + "step": 8026 + }, + { + "epoch": 7.1, + "learning_rate": 1.4948199438155525e-05, + "loss": 0.0448, + "step": 8027 + }, + { + "epoch": 7.1, + "learning_rate": 1.494695404935117e-05, + "loss": 0.0492, + "step": 8028 + }, + { + "epoch": 7.1, + "learning_rate": 1.4945708558950662e-05, + "loss": 0.0458, + "step": 8029 + }, + { + "epoch": 7.1, + "learning_rate": 1.4944462966979575e-05, + "loss": 0.0456, + "step": 8030 + }, + { + "epoch": 7.11, + "learning_rate": 1.4943217273463495e-05, + "loss": 0.0557, + "step": 8031 + }, + { + "epoch": 7.11, + "learning_rate": 1.4941971478428001e-05, + "loss": 0.0443, + "step": 8032 + }, + { + "epoch": 7.11, + "learning_rate": 1.4940725581898681e-05, + "loss": 0.0459, + "step": 8033 + }, + { + "epoch": 7.11, + "learning_rate": 1.4939479583901118e-05, + "loss": 0.0433, + "step": 8034 + }, + { + "epoch": 7.11, + "learning_rate": 1.4938233484460901e-05, + "loss": 0.0519, + "step": 8035 + }, + { + "epoch": 7.11, + "learning_rate": 1.493698728360363e-05, + "loss": 0.0451, + "step": 8036 + }, + { + "epoch": 7.11, + "learning_rate": 1.4935740981354888e-05, + "loss": 0.0598, + "step": 8037 + }, + { + "epoch": 7.11, + "learning_rate": 1.4934494577740273e-05, + "loss": 0.0396, + "step": 8038 + }, + { + "epoch": 7.11, + "learning_rate": 1.4933248072785386e-05, + "loss": 0.0457, + "step": 8039 + }, + { + "epoch": 7.11, + "learning_rate": 1.4932001466515828e-05, + "loss": 0.0532, + "step": 8040 + }, + { + "epoch": 7.11, + "learning_rate": 1.4930754758957193e-05, + "loss": 0.0402, + "step": 8041 + }, + { + "epoch": 7.12, + "learning_rate": 1.4929507950135091e-05, + "loss": 0.0486, + "step": 8042 + }, + { + "epoch": 7.12, + "learning_rate": 1.4928261040075125e-05, + "loss": 0.0484, + "step": 8043 + }, + { + "epoch": 7.12, + "learning_rate": 1.4927014028802904e-05, + "loss": 0.0477, + "step": 8044 + }, + { + "epoch": 7.12, + "learning_rate": 1.4925766916344038e-05, + "loss": 0.0517, + "step": 8045 + }, + { + "epoch": 7.12, + "learning_rate": 1.492451970272414e-05, + "loss": 0.044, + "step": 8046 + }, + { + "epoch": 7.12, + "learning_rate": 1.4923272387968823e-05, + "loss": 0.0471, + "step": 8047 + }, + { + "epoch": 7.12, + "learning_rate": 1.4922024972103704e-05, + "loss": 0.04, + "step": 8048 + }, + { + "epoch": 7.12, + "learning_rate": 1.4920777455154398e-05, + "loss": 0.0433, + "step": 8049 + }, + { + "epoch": 7.12, + "learning_rate": 1.4919529837146529e-05, + "loss": 0.0464, + "step": 8050 + }, + { + "epoch": 7.12, + "learning_rate": 1.491828211810572e-05, + "loss": 0.0501, + "step": 8051 + }, + { + "epoch": 7.12, + "learning_rate": 1.4917034298057593e-05, + "loss": 0.0458, + "step": 8052 + }, + { + "epoch": 7.13, + "learning_rate": 1.4915786377027779e-05, + "loss": 0.0462, + "step": 8053 + }, + { + "epoch": 7.13, + "learning_rate": 1.4914538355041901e-05, + "loss": 0.0543, + "step": 8054 + }, + { + "epoch": 7.13, + "learning_rate": 1.4913290232125592e-05, + "loss": 0.0491, + "step": 8055 + }, + { + "epoch": 7.13, + "learning_rate": 1.4912042008304484e-05, + "loss": 0.0538, + "step": 8056 + }, + { + "epoch": 7.13, + "learning_rate": 1.4910793683604217e-05, + "loss": 0.0502, + "step": 8057 + }, + { + "epoch": 7.13, + "learning_rate": 1.490954525805042e-05, + "loss": 0.0502, + "step": 8058 + }, + { + "epoch": 7.13, + "learning_rate": 1.4908296731668737e-05, + "loss": 0.046, + "step": 8059 + }, + { + "epoch": 7.13, + "learning_rate": 1.4907048104484808e-05, + "loss": 0.0446, + "step": 8060 + }, + { + "epoch": 7.13, + "learning_rate": 1.490579937652428e-05, + "loss": 0.0416, + "step": 8061 + }, + { + "epoch": 7.13, + "learning_rate": 1.490455054781279e-05, + "loss": 0.042, + "step": 8062 + }, + { + "epoch": 7.13, + "learning_rate": 1.4903301618375991e-05, + "loss": 0.0506, + "step": 8063 + }, + { + "epoch": 7.14, + "learning_rate": 1.4902052588239535e-05, + "loss": 0.05, + "step": 8064 + }, + { + "epoch": 7.14, + "learning_rate": 1.4900803457429065e-05, + "loss": 0.0444, + "step": 8065 + }, + { + "epoch": 7.14, + "learning_rate": 1.4899554225970243e-05, + "loss": 0.0518, + "step": 8066 + }, + { + "epoch": 7.14, + "learning_rate": 1.4898304893888718e-05, + "loss": 0.0423, + "step": 8067 + }, + { + "epoch": 7.14, + "learning_rate": 1.4897055461210155e-05, + "loss": 0.0433, + "step": 8068 + }, + { + "epoch": 7.14, + "learning_rate": 1.4895805927960206e-05, + "loss": 0.055, + "step": 8069 + }, + { + "epoch": 7.14, + "learning_rate": 1.4894556294164535e-05, + "loss": 0.0445, + "step": 8070 + }, + { + "epoch": 7.14, + "learning_rate": 1.489330655984881e-05, + "loss": 0.0534, + "step": 8071 + }, + { + "epoch": 7.14, + "learning_rate": 1.4892056725038692e-05, + "loss": 0.0393, + "step": 8072 + }, + { + "epoch": 7.14, + "learning_rate": 1.4890806789759854e-05, + "loss": 0.0488, + "step": 8073 + }, + { + "epoch": 7.14, + "learning_rate": 1.4889556754037959e-05, + "loss": 0.0418, + "step": 8074 + }, + { + "epoch": 7.14, + "learning_rate": 1.488830661789869e-05, + "loss": 0.0549, + "step": 8075 + }, + { + "epoch": 7.15, + "learning_rate": 1.4887056381367706e-05, + "loss": 0.0503, + "step": 8076 + }, + { + "epoch": 7.15, + "learning_rate": 1.4885806044470697e-05, + "loss": 0.0525, + "step": 8077 + }, + { + "epoch": 7.15, + "learning_rate": 1.4884555607233336e-05, + "loss": 0.0472, + "step": 8078 + }, + { + "epoch": 7.15, + "learning_rate": 1.48833050696813e-05, + "loss": 0.0473, + "step": 8079 + }, + { + "epoch": 7.15, + "learning_rate": 1.4882054431840277e-05, + "loss": 0.047, + "step": 8080 + }, + { + "epoch": 7.15, + "learning_rate": 1.4880803693735948e-05, + "loss": 0.0418, + "step": 8081 + }, + { + "epoch": 7.15, + "learning_rate": 1.4879552855394004e-05, + "loss": 0.0571, + "step": 8082 + }, + { + "epoch": 7.15, + "learning_rate": 1.4878301916840125e-05, + "loss": 0.0563, + "step": 8083 + }, + { + "epoch": 7.15, + "learning_rate": 1.4877050878100012e-05, + "loss": 0.0463, + "step": 8084 + }, + { + "epoch": 7.15, + "learning_rate": 1.4875799739199353e-05, + "loss": 0.0509, + "step": 8085 + }, + { + "epoch": 7.15, + "learning_rate": 1.487454850016384e-05, + "loss": 0.0501, + "step": 8086 + }, + { + "epoch": 7.16, + "learning_rate": 1.4873297161019173e-05, + "loss": 0.0506, + "step": 8087 + }, + { + "epoch": 7.16, + "learning_rate": 1.4872045721791051e-05, + "loss": 0.0464, + "step": 8088 + }, + { + "epoch": 7.16, + "learning_rate": 1.4870794182505173e-05, + "loss": 0.049, + "step": 8089 + }, + { + "epoch": 7.16, + "learning_rate": 1.4869542543187244e-05, + "loss": 0.0461, + "step": 8090 + }, + { + "epoch": 7.16, + "learning_rate": 1.4868290803862968e-05, + "loss": 0.0519, + "step": 8091 + }, + { + "epoch": 7.16, + "learning_rate": 1.4867038964558056e-05, + "loss": 0.0474, + "step": 8092 + }, + { + "epoch": 7.16, + "learning_rate": 1.4865787025298208e-05, + "loss": 0.0528, + "step": 8093 + }, + { + "epoch": 7.16, + "learning_rate": 1.4864534986109145e-05, + "loss": 0.0467, + "step": 8094 + }, + { + "epoch": 7.16, + "learning_rate": 1.4863282847016574e-05, + "loss": 0.0469, + "step": 8095 + }, + { + "epoch": 7.16, + "learning_rate": 1.4862030608046211e-05, + "loss": 0.0424, + "step": 8096 + }, + { + "epoch": 7.16, + "learning_rate": 1.486077826922378e-05, + "loss": 0.0451, + "step": 8097 + }, + { + "epoch": 7.17, + "learning_rate": 1.485952583057499e-05, + "loss": 0.0498, + "step": 8098 + }, + { + "epoch": 7.17, + "learning_rate": 1.4858273292125574e-05, + "loss": 0.0498, + "step": 8099 + }, + { + "epoch": 7.17, + "learning_rate": 1.4857020653901244e-05, + "loss": 0.054, + "step": 8100 + }, + { + "epoch": 7.17, + "learning_rate": 1.485576791592773e-05, + "loss": 0.0498, + "step": 8101 + }, + { + "epoch": 7.17, + "learning_rate": 1.485451507823076e-05, + "loss": 0.0508, + "step": 8102 + }, + { + "epoch": 7.17, + "learning_rate": 1.4853262140836068e-05, + "loss": 0.0485, + "step": 8103 + }, + { + "epoch": 7.17, + "learning_rate": 1.485200910376938e-05, + "loss": 0.0458, + "step": 8104 + }, + { + "epoch": 7.17, + "learning_rate": 1.4850755967056434e-05, + "loss": 0.0497, + "step": 8105 + }, + { + "epoch": 7.17, + "learning_rate": 1.4849502730722962e-05, + "loss": 0.0425, + "step": 8106 + }, + { + "epoch": 7.17, + "learning_rate": 1.4848249394794703e-05, + "loss": 0.0462, + "step": 8107 + }, + { + "epoch": 7.17, + "learning_rate": 1.4846995959297395e-05, + "loss": 0.0512, + "step": 8108 + }, + { + "epoch": 7.17, + "learning_rate": 1.4845742424256781e-05, + "loss": 0.0414, + "step": 8109 + }, + { + "epoch": 7.18, + "learning_rate": 1.4844488789698612e-05, + "loss": 0.0427, + "step": 8110 + }, + { + "epoch": 7.18, + "learning_rate": 1.4843235055648624e-05, + "loss": 0.0453, + "step": 8111 + }, + { + "epoch": 7.18, + "learning_rate": 1.484198122213257e-05, + "loss": 0.0379, + "step": 8112 + }, + { + "epoch": 7.18, + "learning_rate": 1.48407272891762e-05, + "loss": 0.0464, + "step": 8113 + }, + { + "epoch": 7.18, + "learning_rate": 1.4839473256805265e-05, + "loss": 0.0471, + "step": 8114 + }, + { + "epoch": 7.18, + "learning_rate": 1.4838219125045519e-05, + "loss": 0.0427, + "step": 8115 + }, + { + "epoch": 7.18, + "learning_rate": 1.4836964893922718e-05, + "loss": 0.0469, + "step": 8116 + }, + { + "epoch": 7.18, + "learning_rate": 1.4835710563462627e-05, + "loss": 0.0484, + "step": 8117 + }, + { + "epoch": 7.18, + "learning_rate": 1.4834456133690996e-05, + "loss": 0.0424, + "step": 8118 + }, + { + "epoch": 7.18, + "learning_rate": 1.4833201604633592e-05, + "loss": 0.0407, + "step": 8119 + }, + { + "epoch": 7.18, + "learning_rate": 1.4831946976316177e-05, + "loss": 0.0406, + "step": 8120 + }, + { + "epoch": 7.19, + "learning_rate": 1.4830692248764527e-05, + "loss": 0.0451, + "step": 8121 + }, + { + "epoch": 7.19, + "learning_rate": 1.4829437422004396e-05, + "loss": 0.0433, + "step": 8122 + }, + { + "epoch": 7.19, + "learning_rate": 1.4828182496061563e-05, + "loss": 0.0447, + "step": 8123 + }, + { + "epoch": 7.19, + "learning_rate": 1.4826927470961804e-05, + "loss": 0.0466, + "step": 8124 + }, + { + "epoch": 7.19, + "learning_rate": 1.4825672346730883e-05, + "loss": 0.04, + "step": 8125 + }, + { + "epoch": 7.19, + "learning_rate": 1.4824417123394585e-05, + "loss": 0.045, + "step": 8126 + }, + { + "epoch": 7.19, + "learning_rate": 1.4823161800978687e-05, + "loss": 0.0549, + "step": 8127 + }, + { + "epoch": 7.19, + "learning_rate": 1.4821906379508968e-05, + "loss": 0.0478, + "step": 8128 + }, + { + "epoch": 7.19, + "learning_rate": 1.4820650859011211e-05, + "loss": 0.0494, + "step": 8129 + }, + { + "epoch": 7.19, + "learning_rate": 1.4819395239511202e-05, + "loss": 0.0499, + "step": 8130 + }, + { + "epoch": 7.19, + "learning_rate": 1.4818139521034731e-05, + "loss": 0.0499, + "step": 8131 + }, + { + "epoch": 7.2, + "learning_rate": 1.4816883703607578e-05, + "loss": 0.046, + "step": 8132 + }, + { + "epoch": 7.2, + "learning_rate": 1.4815627787255542e-05, + "loss": 0.0505, + "step": 8133 + }, + { + "epoch": 7.2, + "learning_rate": 1.481437177200441e-05, + "loss": 0.0488, + "step": 8134 + }, + { + "epoch": 7.2, + "learning_rate": 1.4813115657879982e-05, + "loss": 0.0461, + "step": 8135 + }, + { + "epoch": 7.2, + "learning_rate": 1.4811859444908053e-05, + "loss": 0.0496, + "step": 8136 + }, + { + "epoch": 7.2, + "learning_rate": 1.481060313311442e-05, + "loss": 0.0455, + "step": 8137 + }, + { + "epoch": 7.2, + "learning_rate": 1.4809346722524887e-05, + "loss": 0.0474, + "step": 8138 + }, + { + "epoch": 7.2, + "learning_rate": 1.4808090213165254e-05, + "loss": 0.0513, + "step": 8139 + }, + { + "epoch": 7.2, + "learning_rate": 1.4806833605061329e-05, + "loss": 0.0475, + "step": 8140 + }, + { + "epoch": 7.2, + "learning_rate": 1.4805576898238917e-05, + "loss": 0.044, + "step": 8141 + }, + { + "epoch": 7.2, + "learning_rate": 1.4804320092723829e-05, + "loss": 0.0501, + "step": 8142 + }, + { + "epoch": 7.2, + "learning_rate": 1.4803063188541873e-05, + "loss": 0.0554, + "step": 8143 + }, + { + "epoch": 7.21, + "learning_rate": 1.4801806185718868e-05, + "loss": 0.0579, + "step": 8144 + }, + { + "epoch": 7.21, + "learning_rate": 1.4800549084280624e-05, + "loss": 0.0472, + "step": 8145 + }, + { + "epoch": 7.21, + "learning_rate": 1.479929188425296e-05, + "loss": 0.05, + "step": 8146 + }, + { + "epoch": 7.21, + "learning_rate": 1.4798034585661696e-05, + "loss": 0.0479, + "step": 8147 + }, + { + "epoch": 7.21, + "learning_rate": 1.479677718853265e-05, + "loss": 0.0516, + "step": 8148 + }, + { + "epoch": 7.21, + "learning_rate": 1.479551969289165e-05, + "loss": 0.0492, + "step": 8149 + }, + { + "epoch": 7.21, + "learning_rate": 1.4794262098764515e-05, + "loss": 0.0552, + "step": 8150 + }, + { + "epoch": 7.21, + "learning_rate": 1.479300440617708e-05, + "loss": 0.0556, + "step": 8151 + }, + { + "epoch": 7.21, + "learning_rate": 1.4791746615155171e-05, + "loss": 0.0422, + "step": 8152 + }, + { + "epoch": 7.21, + "learning_rate": 1.479048872572462e-05, + "loss": 0.0438, + "step": 8153 + }, + { + "epoch": 7.21, + "learning_rate": 1.4789230737911254e-05, + "loss": 0.0526, + "step": 8154 + }, + { + "epoch": 7.22, + "learning_rate": 1.4787972651740919e-05, + "loss": 0.0531, + "step": 8155 + }, + { + "epoch": 7.22, + "learning_rate": 1.4786714467239447e-05, + "loss": 0.0524, + "step": 8156 + }, + { + "epoch": 7.22, + "learning_rate": 1.4785456184432677e-05, + "loss": 0.0486, + "step": 8157 + }, + { + "epoch": 7.22, + "learning_rate": 1.4784197803346452e-05, + "loss": 0.0412, + "step": 8158 + }, + { + "epoch": 7.22, + "learning_rate": 1.4782939324006615e-05, + "loss": 0.0574, + "step": 8159 + }, + { + "epoch": 7.22, + "learning_rate": 1.4781680746439011e-05, + "loss": 0.0532, + "step": 8160 + }, + { + "epoch": 7.22, + "learning_rate": 1.4780422070669485e-05, + "loss": 0.0474, + "step": 8161 + }, + { + "epoch": 7.22, + "learning_rate": 1.4779163296723894e-05, + "loss": 0.05, + "step": 8162 + }, + { + "epoch": 7.22, + "learning_rate": 1.4777904424628085e-05, + "loss": 0.0502, + "step": 8163 + }, + { + "epoch": 7.22, + "learning_rate": 1.4776645454407907e-05, + "loss": 0.0513, + "step": 8164 + }, + { + "epoch": 7.22, + "learning_rate": 1.4775386386089226e-05, + "loss": 0.0472, + "step": 8165 + }, + { + "epoch": 7.23, + "learning_rate": 1.4774127219697894e-05, + "loss": 0.0537, + "step": 8166 + }, + { + "epoch": 7.23, + "learning_rate": 1.4772867955259767e-05, + "loss": 0.0424, + "step": 8167 + }, + { + "epoch": 7.23, + "learning_rate": 1.477160859280071e-05, + "loss": 0.0533, + "step": 8168 + }, + { + "epoch": 7.23, + "learning_rate": 1.4770349132346591e-05, + "loss": 0.0509, + "step": 8169 + }, + { + "epoch": 7.23, + "learning_rate": 1.4769089573923268e-05, + "loss": 0.0531, + "step": 8170 + }, + { + "epoch": 7.23, + "learning_rate": 1.4767829917556613e-05, + "loss": 0.0448, + "step": 8171 + }, + { + "epoch": 7.23, + "learning_rate": 1.4766570163272499e-05, + "loss": 0.0513, + "step": 8172 + }, + { + "epoch": 7.23, + "learning_rate": 1.476531031109679e-05, + "loss": 0.0494, + "step": 8173 + }, + { + "epoch": 7.23, + "learning_rate": 1.4764050361055363e-05, + "loss": 0.0434, + "step": 8174 + }, + { + "epoch": 7.23, + "learning_rate": 1.4762790313174096e-05, + "loss": 0.0438, + "step": 8175 + }, + { + "epoch": 7.23, + "learning_rate": 1.4761530167478864e-05, + "loss": 0.0466, + "step": 8176 + }, + { + "epoch": 7.24, + "learning_rate": 1.4760269923995549e-05, + "loss": 0.0445, + "step": 8177 + }, + { + "epoch": 7.24, + "learning_rate": 1.475900958275003e-05, + "loss": 0.0516, + "step": 8178 + }, + { + "epoch": 7.24, + "learning_rate": 1.4757749143768191e-05, + "loss": 0.0475, + "step": 8179 + }, + { + "epoch": 7.24, + "learning_rate": 1.4756488607075922e-05, + "loss": 0.046, + "step": 8180 + }, + { + "epoch": 7.24, + "learning_rate": 1.4755227972699107e-05, + "loss": 0.0464, + "step": 8181 + }, + { + "epoch": 7.24, + "learning_rate": 1.4753967240663635e-05, + "loss": 0.0489, + "step": 8182 + }, + { + "epoch": 7.24, + "learning_rate": 1.4752706410995404e-05, + "loss": 0.0513, + "step": 8183 + }, + { + "epoch": 7.24, + "learning_rate": 1.47514454837203e-05, + "loss": 0.0492, + "step": 8184 + }, + { + "epoch": 7.24, + "learning_rate": 1.4750184458864223e-05, + "loss": 0.0468, + "step": 8185 + }, + { + "epoch": 7.24, + "learning_rate": 1.4748923336453067e-05, + "loss": 0.0476, + "step": 8186 + }, + { + "epoch": 7.24, + "learning_rate": 1.4747662116512738e-05, + "loss": 0.0462, + "step": 8187 + }, + { + "epoch": 7.24, + "learning_rate": 1.4746400799069132e-05, + "loss": 0.0569, + "step": 8188 + }, + { + "epoch": 7.25, + "learning_rate": 1.4745139384148156e-05, + "loss": 0.0543, + "step": 8189 + }, + { + "epoch": 7.25, + "learning_rate": 1.4743877871775718e-05, + "loss": 0.0404, + "step": 8190 + }, + { + "epoch": 7.25, + "learning_rate": 1.474261626197772e-05, + "loss": 0.0516, + "step": 8191 + }, + { + "epoch": 7.25, + "learning_rate": 1.4741354554780077e-05, + "loss": 0.041, + "step": 8192 + }, + { + "epoch": 7.25, + "learning_rate": 1.4740092750208694e-05, + "loss": 0.0497, + "step": 8193 + }, + { + "epoch": 7.25, + "learning_rate": 1.4738830848289494e-05, + "loss": 0.0444, + "step": 8194 + }, + { + "epoch": 7.25, + "learning_rate": 1.4737568849048384e-05, + "loss": 0.0468, + "step": 8195 + }, + { + "epoch": 7.25, + "learning_rate": 1.4736306752511288e-05, + "loss": 0.0437, + "step": 8196 + }, + { + "epoch": 7.25, + "learning_rate": 1.4735044558704129e-05, + "loss": 0.0505, + "step": 8197 + }, + { + "epoch": 7.25, + "learning_rate": 1.4733782267652818e-05, + "loss": 0.0439, + "step": 8198 + }, + { + "epoch": 7.25, + "learning_rate": 1.4732519879383284e-05, + "loss": 0.0479, + "step": 8199 + }, + { + "epoch": 7.26, + "learning_rate": 1.4731257393921457e-05, + "loss": 0.048, + "step": 8200 + }, + { + "epoch": 7.26, + "learning_rate": 1.4729994811293258e-05, + "loss": 0.0442, + "step": 8201 + }, + { + "epoch": 7.26, + "learning_rate": 1.472873213152462e-05, + "loss": 0.0496, + "step": 8202 + }, + { + "epoch": 7.26, + "learning_rate": 1.4727469354641476e-05, + "loss": 0.0519, + "step": 8203 + }, + { + "epoch": 7.26, + "learning_rate": 1.472620648066976e-05, + "loss": 0.0493, + "step": 8204 + }, + { + "epoch": 7.26, + "learning_rate": 1.4724943509635406e-05, + "loss": 0.0409, + "step": 8205 + }, + { + "epoch": 7.26, + "learning_rate": 1.4723680441564348e-05, + "loss": 0.0477, + "step": 8206 + }, + { + "epoch": 7.26, + "learning_rate": 1.4722417276482533e-05, + "loss": 0.0443, + "step": 8207 + }, + { + "epoch": 7.26, + "learning_rate": 1.4721154014415899e-05, + "loss": 0.0525, + "step": 8208 + }, + { + "epoch": 7.26, + "learning_rate": 1.471989065539039e-05, + "loss": 0.0425, + "step": 8209 + }, + { + "epoch": 7.26, + "learning_rate": 1.4718627199431955e-05, + "loss": 0.0495, + "step": 8210 + }, + { + "epoch": 7.27, + "learning_rate": 1.4717363646566537e-05, + "loss": 0.0475, + "step": 8211 + }, + { + "epoch": 7.27, + "learning_rate": 1.4716099996820085e-05, + "loss": 0.0459, + "step": 8212 + }, + { + "epoch": 7.27, + "learning_rate": 1.4714836250218554e-05, + "loss": 0.0489, + "step": 8213 + }, + { + "epoch": 7.27, + "learning_rate": 1.47135724067879e-05, + "loss": 0.0472, + "step": 8214 + }, + { + "epoch": 7.27, + "learning_rate": 1.4712308466554075e-05, + "loss": 0.0484, + "step": 8215 + }, + { + "epoch": 7.27, + "learning_rate": 1.4711044429543036e-05, + "loss": 0.0451, + "step": 8216 + }, + { + "epoch": 7.27, + "learning_rate": 1.4709780295780744e-05, + "loss": 0.0468, + "step": 8217 + }, + { + "epoch": 7.27, + "learning_rate": 1.4708516065293164e-05, + "loss": 0.0487, + "step": 8218 + }, + { + "epoch": 7.27, + "learning_rate": 1.470725173810625e-05, + "loss": 0.047, + "step": 8219 + }, + { + "epoch": 7.27, + "learning_rate": 1.4705987314245978e-05, + "loss": 0.0416, + "step": 8220 + }, + { + "epoch": 7.27, + "learning_rate": 1.4704722793738314e-05, + "loss": 0.0482, + "step": 8221 + }, + { + "epoch": 7.27, + "learning_rate": 1.4703458176609221e-05, + "loss": 0.0497, + "step": 8222 + }, + { + "epoch": 7.28, + "learning_rate": 1.4702193462884675e-05, + "loss": 0.0486, + "step": 8223 + }, + { + "epoch": 7.28, + "learning_rate": 1.470092865259065e-05, + "loss": 0.0411, + "step": 8224 + }, + { + "epoch": 7.28, + "learning_rate": 1.4699663745753126e-05, + "loss": 0.0552, + "step": 8225 + }, + { + "epoch": 7.28, + "learning_rate": 1.4698398742398069e-05, + "loss": 0.0507, + "step": 8226 + }, + { + "epoch": 7.28, + "learning_rate": 1.4697133642551466e-05, + "loss": 0.0446, + "step": 8227 + }, + { + "epoch": 7.28, + "learning_rate": 1.4695868446239298e-05, + "loss": 0.0493, + "step": 8228 + }, + { + "epoch": 7.28, + "learning_rate": 1.469460315348755e-05, + "loss": 0.0593, + "step": 8229 + }, + { + "epoch": 7.28, + "learning_rate": 1.4693337764322204e-05, + "loss": 0.0462, + "step": 8230 + }, + { + "epoch": 7.28, + "learning_rate": 1.4692072278769249e-05, + "loss": 0.0502, + "step": 8231 + }, + { + "epoch": 7.28, + "learning_rate": 1.4690806696854676e-05, + "loss": 0.0478, + "step": 8232 + }, + { + "epoch": 7.28, + "learning_rate": 1.468954101860447e-05, + "loss": 0.0467, + "step": 8233 + }, + { + "epoch": 7.29, + "learning_rate": 1.4688275244044632e-05, + "loss": 0.0444, + "step": 8234 + }, + { + "epoch": 7.29, + "learning_rate": 1.4687009373201153e-05, + "loss": 0.0454, + "step": 8235 + }, + { + "epoch": 7.29, + "learning_rate": 1.4685743406100035e-05, + "loss": 0.0408, + "step": 8236 + }, + { + "epoch": 7.29, + "learning_rate": 1.4684477342767271e-05, + "loss": 0.0478, + "step": 8237 + }, + { + "epoch": 7.29, + "learning_rate": 1.4683211183228866e-05, + "loss": 0.0478, + "step": 8238 + }, + { + "epoch": 7.29, + "learning_rate": 1.4681944927510823e-05, + "loss": 0.048, + "step": 8239 + }, + { + "epoch": 7.29, + "learning_rate": 1.4680678575639147e-05, + "loss": 0.0518, + "step": 8240 + }, + { + "epoch": 7.29, + "learning_rate": 1.4679412127639842e-05, + "loss": 0.0475, + "step": 8241 + }, + { + "epoch": 7.29, + "learning_rate": 1.4678145583538923e-05, + "loss": 0.0474, + "step": 8242 + }, + { + "epoch": 7.29, + "learning_rate": 1.4676878943362401e-05, + "loss": 0.049, + "step": 8243 + }, + { + "epoch": 7.29, + "learning_rate": 1.4675612207136283e-05, + "loss": 0.0516, + "step": 8244 + }, + { + "epoch": 7.3, + "learning_rate": 1.467434537488659e-05, + "loss": 0.0428, + "step": 8245 + }, + { + "epoch": 7.3, + "learning_rate": 1.4673078446639333e-05, + "loss": 0.0411, + "step": 8246 + }, + { + "epoch": 7.3, + "learning_rate": 1.4671811422420536e-05, + "loss": 0.0418, + "step": 8247 + }, + { + "epoch": 7.3, + "learning_rate": 1.467054430225622e-05, + "loss": 0.0584, + "step": 8248 + }, + { + "epoch": 7.3, + "learning_rate": 1.4669277086172406e-05, + "loss": 0.0507, + "step": 8249 + }, + { + "epoch": 7.3, + "learning_rate": 1.4668009774195123e-05, + "loss": 0.0483, + "step": 8250 + }, + { + "epoch": 7.3, + "learning_rate": 1.466674236635039e-05, + "loss": 0.0399, + "step": 8251 + }, + { + "epoch": 7.3, + "learning_rate": 1.4665474862664242e-05, + "loss": 0.0511, + "step": 8252 + }, + { + "epoch": 7.3, + "learning_rate": 1.4664207263162712e-05, + "loss": 0.0534, + "step": 8253 + }, + { + "epoch": 7.3, + "learning_rate": 1.4662939567871823e-05, + "loss": 0.0572, + "step": 8254 + }, + { + "epoch": 7.3, + "learning_rate": 1.4661671776817619e-05, + "loss": 0.0489, + "step": 8255 + }, + { + "epoch": 7.3, + "learning_rate": 1.4660403890026133e-05, + "loss": 0.053, + "step": 8256 + }, + { + "epoch": 7.31, + "learning_rate": 1.465913590752341e-05, + "loss": 0.0418, + "step": 8257 + }, + { + "epoch": 7.31, + "learning_rate": 1.465786782933548e-05, + "loss": 0.0501, + "step": 8258 + }, + { + "epoch": 7.31, + "learning_rate": 1.4656599655488388e-05, + "loss": 0.0449, + "step": 8259 + }, + { + "epoch": 7.31, + "learning_rate": 1.4655331386008188e-05, + "loss": 0.0497, + "step": 8260 + }, + { + "epoch": 7.31, + "learning_rate": 1.4654063020920917e-05, + "loss": 0.0491, + "step": 8261 + }, + { + "epoch": 7.31, + "learning_rate": 1.4652794560252626e-05, + "loss": 0.0466, + "step": 8262 + }, + { + "epoch": 7.31, + "learning_rate": 1.4651526004029366e-05, + "loss": 0.0551, + "step": 8263 + }, + { + "epoch": 7.31, + "learning_rate": 1.4650257352277195e-05, + "loss": 0.0486, + "step": 8264 + }, + { + "epoch": 7.31, + "learning_rate": 1.4648988605022157e-05, + "loss": 0.045, + "step": 8265 + }, + { + "epoch": 7.31, + "learning_rate": 1.4647719762290314e-05, + "loss": 0.0499, + "step": 8266 + }, + { + "epoch": 7.31, + "learning_rate": 1.4646450824107725e-05, + "loss": 0.0524, + "step": 8267 + }, + { + "epoch": 7.32, + "learning_rate": 1.4645181790500448e-05, + "loss": 0.0558, + "step": 8268 + }, + { + "epoch": 7.32, + "learning_rate": 1.4643912661494548e-05, + "loss": 0.0485, + "step": 8269 + }, + { + "epoch": 7.32, + "learning_rate": 1.4642643437116086e-05, + "loss": 0.0528, + "step": 8270 + }, + { + "epoch": 7.32, + "learning_rate": 1.4641374117391134e-05, + "loss": 0.0441, + "step": 8271 + }, + { + "epoch": 7.32, + "learning_rate": 1.464010470234575e-05, + "loss": 0.0457, + "step": 8272 + }, + { + "epoch": 7.32, + "learning_rate": 1.4638835192006013e-05, + "loss": 0.0473, + "step": 8273 + }, + { + "epoch": 7.32, + "learning_rate": 1.4637565586397995e-05, + "loss": 0.0513, + "step": 8274 + }, + { + "epoch": 7.32, + "learning_rate": 1.4636295885547766e-05, + "loss": 0.0566, + "step": 8275 + }, + { + "epoch": 7.32, + "learning_rate": 1.4635026089481402e-05, + "loss": 0.05, + "step": 8276 + }, + { + "epoch": 7.32, + "learning_rate": 1.4633756198224985e-05, + "loss": 0.058, + "step": 8277 + }, + { + "epoch": 7.32, + "learning_rate": 1.4632486211804589e-05, + "loss": 0.0446, + "step": 8278 + }, + { + "epoch": 7.33, + "learning_rate": 1.46312161302463e-05, + "loss": 0.047, + "step": 8279 + }, + { + "epoch": 7.33, + "learning_rate": 1.46299459535762e-05, + "loss": 0.0573, + "step": 8280 + }, + { + "epoch": 7.33, + "learning_rate": 1.462867568182038e-05, + "loss": 0.0488, + "step": 8281 + }, + { + "epoch": 7.33, + "learning_rate": 1.462740531500492e-05, + "loss": 0.0421, + "step": 8282 + }, + { + "epoch": 7.33, + "learning_rate": 1.4626134853155911e-05, + "loss": 0.0482, + "step": 8283 + }, + { + "epoch": 7.33, + "learning_rate": 1.462486429629945e-05, + "loss": 0.0502, + "step": 8284 + }, + { + "epoch": 7.33, + "learning_rate": 1.4623593644461624e-05, + "loss": 0.0481, + "step": 8285 + }, + { + "epoch": 7.33, + "learning_rate": 1.4622322897668535e-05, + "loss": 0.0533, + "step": 8286 + }, + { + "epoch": 7.33, + "learning_rate": 1.4621052055946277e-05, + "loss": 0.0511, + "step": 8287 + }, + { + "epoch": 7.33, + "learning_rate": 1.461978111932095e-05, + "loss": 0.0507, + "step": 8288 + }, + { + "epoch": 7.33, + "learning_rate": 1.4618510087818653e-05, + "loss": 0.0425, + "step": 8289 + }, + { + "epoch": 7.33, + "learning_rate": 1.4617238961465493e-05, + "loss": 0.0522, + "step": 8290 + }, + { + "epoch": 7.34, + "learning_rate": 1.4615967740287572e-05, + "loss": 0.0421, + "step": 8291 + }, + { + "epoch": 7.34, + "learning_rate": 1.4614696424310999e-05, + "loss": 0.0532, + "step": 8292 + }, + { + "epoch": 7.34, + "learning_rate": 1.4613425013561883e-05, + "loss": 0.048, + "step": 8293 + }, + { + "epoch": 7.34, + "learning_rate": 1.4612153508066335e-05, + "loss": 0.0479, + "step": 8294 + }, + { + "epoch": 7.34, + "learning_rate": 1.4610881907850471e-05, + "loss": 0.0468, + "step": 8295 + }, + { + "epoch": 7.34, + "learning_rate": 1.4609610212940399e-05, + "loss": 0.0534, + "step": 8296 + }, + { + "epoch": 7.34, + "learning_rate": 1.4608338423362243e-05, + "loss": 0.055, + "step": 8297 + }, + { + "epoch": 7.34, + "learning_rate": 1.4607066539142117e-05, + "loss": 0.0489, + "step": 8298 + }, + { + "epoch": 7.34, + "learning_rate": 1.4605794560306144e-05, + "loss": 0.0535, + "step": 8299 + }, + { + "epoch": 7.34, + "learning_rate": 1.4604522486880446e-05, + "loss": 0.0517, + "step": 8300 + }, + { + "epoch": 7.34, + "learning_rate": 1.460325031889115e-05, + "loss": 0.0468, + "step": 8301 + }, + { + "epoch": 7.35, + "learning_rate": 1.4601978056364381e-05, + "loss": 0.0413, + "step": 8302 + }, + { + "epoch": 7.35, + "learning_rate": 1.4600705699326267e-05, + "loss": 0.0443, + "step": 8303 + }, + { + "epoch": 7.35, + "learning_rate": 1.4599433247802936e-05, + "loss": 0.0526, + "step": 8304 + }, + { + "epoch": 7.35, + "learning_rate": 1.4598160701820527e-05, + "loss": 0.0466, + "step": 8305 + }, + { + "epoch": 7.35, + "learning_rate": 1.4596888061405172e-05, + "loss": 0.0436, + "step": 8306 + }, + { + "epoch": 7.35, + "learning_rate": 1.4595615326583003e-05, + "loss": 0.0577, + "step": 8307 + }, + { + "epoch": 7.35, + "learning_rate": 1.4594342497380166e-05, + "loss": 0.0546, + "step": 8308 + }, + { + "epoch": 7.35, + "learning_rate": 1.4593069573822793e-05, + "loss": 0.0456, + "step": 8309 + }, + { + "epoch": 7.35, + "learning_rate": 1.4591796555937033e-05, + "loss": 0.0491, + "step": 8310 + }, + { + "epoch": 7.35, + "learning_rate": 1.4590523443749023e-05, + "loss": 0.0476, + "step": 8311 + }, + { + "epoch": 7.35, + "learning_rate": 1.4589250237284916e-05, + "loss": 0.0489, + "step": 8312 + }, + { + "epoch": 7.36, + "learning_rate": 1.4587976936570856e-05, + "loss": 0.0471, + "step": 8313 + }, + { + "epoch": 7.36, + "learning_rate": 1.4586703541632994e-05, + "loss": 0.0523, + "step": 8314 + }, + { + "epoch": 7.36, + "learning_rate": 1.4585430052497482e-05, + "loss": 0.0492, + "step": 8315 + }, + { + "epoch": 7.36, + "learning_rate": 1.4584156469190479e-05, + "loss": 0.0497, + "step": 8316 + }, + { + "epoch": 7.36, + "learning_rate": 1.4582882791738126e-05, + "loss": 0.0508, + "step": 8317 + }, + { + "epoch": 7.36, + "learning_rate": 1.4581609020166597e-05, + "loss": 0.0471, + "step": 8318 + }, + { + "epoch": 7.36, + "learning_rate": 1.4580335154502043e-05, + "loss": 0.0544, + "step": 8319 + }, + { + "epoch": 7.36, + "learning_rate": 1.4579061194770628e-05, + "loss": 0.0567, + "step": 8320 + }, + { + "epoch": 7.36, + "learning_rate": 1.4577787140998511e-05, + "loss": 0.0485, + "step": 8321 + }, + { + "epoch": 7.36, + "learning_rate": 1.4576512993211865e-05, + "loss": 0.0465, + "step": 8322 + }, + { + "epoch": 7.36, + "learning_rate": 1.4575238751436852e-05, + "loss": 0.0417, + "step": 8323 + }, + { + "epoch": 7.37, + "learning_rate": 1.4573964415699643e-05, + "loss": 0.0534, + "step": 8324 + }, + { + "epoch": 7.37, + "learning_rate": 1.4572689986026407e-05, + "loss": 0.0428, + "step": 8325 + }, + { + "epoch": 7.37, + "learning_rate": 1.4571415462443323e-05, + "loss": 0.0448, + "step": 8326 + }, + { + "epoch": 7.37, + "learning_rate": 1.4570140844976559e-05, + "loss": 0.0443, + "step": 8327 + }, + { + "epoch": 7.37, + "learning_rate": 1.4568866133652298e-05, + "loss": 0.0441, + "step": 8328 + }, + { + "epoch": 7.37, + "learning_rate": 1.456759132849671e-05, + "loss": 0.044, + "step": 8329 + }, + { + "epoch": 7.37, + "learning_rate": 1.4566316429535986e-05, + "loss": 0.0442, + "step": 8330 + }, + { + "epoch": 7.37, + "learning_rate": 1.4565041436796303e-05, + "loss": 0.0582, + "step": 8331 + }, + { + "epoch": 7.37, + "learning_rate": 1.4563766350303848e-05, + "loss": 0.0507, + "step": 8332 + }, + { + "epoch": 7.37, + "learning_rate": 1.4562491170084807e-05, + "loss": 0.0478, + "step": 8333 + }, + { + "epoch": 7.37, + "learning_rate": 1.4561215896165368e-05, + "loss": 0.0504, + "step": 8334 + }, + { + "epoch": 7.37, + "learning_rate": 1.455994052857172e-05, + "loss": 0.0535, + "step": 8335 + }, + { + "epoch": 7.38, + "learning_rate": 1.4558665067330057e-05, + "loss": 0.0467, + "step": 8336 + }, + { + "epoch": 7.38, + "learning_rate": 1.4557389512466575e-05, + "loss": 0.0508, + "step": 8337 + }, + { + "epoch": 7.38, + "learning_rate": 1.4556113864007469e-05, + "loss": 0.0613, + "step": 8338 + }, + { + "epoch": 7.38, + "learning_rate": 1.4554838121978933e-05, + "loss": 0.0397, + "step": 8339 + }, + { + "epoch": 7.38, + "learning_rate": 1.4553562286407174e-05, + "loss": 0.0475, + "step": 8340 + }, + { + "epoch": 7.38, + "learning_rate": 1.455228635731839e-05, + "loss": 0.0448, + "step": 8341 + }, + { + "epoch": 7.38, + "learning_rate": 1.4551010334738784e-05, + "loss": 0.0482, + "step": 8342 + }, + { + "epoch": 7.38, + "learning_rate": 1.4549734218694565e-05, + "loss": 0.0437, + "step": 8343 + }, + { + "epoch": 7.38, + "learning_rate": 1.4548458009211939e-05, + "loss": 0.0524, + "step": 8344 + }, + { + "epoch": 7.38, + "learning_rate": 1.4547181706317115e-05, + "loss": 0.0454, + "step": 8345 + }, + { + "epoch": 7.38, + "learning_rate": 1.4545905310036306e-05, + "loss": 0.0501, + "step": 8346 + }, + { + "epoch": 7.39, + "learning_rate": 1.4544628820395727e-05, + "loss": 0.0503, + "step": 8347 + }, + { + "epoch": 7.39, + "learning_rate": 1.454335223742159e-05, + "loss": 0.0499, + "step": 8348 + }, + { + "epoch": 7.39, + "learning_rate": 1.4542075561140113e-05, + "loss": 0.0476, + "step": 8349 + }, + { + "epoch": 7.39, + "learning_rate": 1.4540798791577511e-05, + "loss": 0.0461, + "step": 8350 + }, + { + "epoch": 7.39, + "learning_rate": 1.4539521928760017e-05, + "loss": 0.0404, + "step": 8351 + }, + { + "epoch": 7.39, + "learning_rate": 1.4538244972713844e-05, + "loss": 0.0515, + "step": 8352 + }, + { + "epoch": 7.39, + "learning_rate": 1.4536967923465222e-05, + "loss": 0.0502, + "step": 8353 + }, + { + "epoch": 7.39, + "learning_rate": 1.4535690781040375e-05, + "loss": 0.0474, + "step": 8354 + }, + { + "epoch": 7.39, + "learning_rate": 1.4534413545465531e-05, + "loss": 0.0563, + "step": 8355 + }, + { + "epoch": 7.39, + "learning_rate": 1.4533136216766924e-05, + "loss": 0.0476, + "step": 8356 + }, + { + "epoch": 7.39, + "learning_rate": 1.4531858794970783e-05, + "loss": 0.0504, + "step": 8357 + }, + { + "epoch": 7.4, + "learning_rate": 1.453058128010335e-05, + "loss": 0.0428, + "step": 8358 + }, + { + "epoch": 7.4, + "learning_rate": 1.4529303672190852e-05, + "loss": 0.0501, + "step": 8359 + }, + { + "epoch": 7.4, + "learning_rate": 1.4528025971259532e-05, + "loss": 0.0502, + "step": 8360 + }, + { + "epoch": 7.4, + "learning_rate": 1.452674817733563e-05, + "loss": 0.0475, + "step": 8361 + }, + { + "epoch": 7.4, + "learning_rate": 1.4525470290445392e-05, + "loss": 0.0451, + "step": 8362 + }, + { + "epoch": 7.4, + "learning_rate": 1.4524192310615051e-05, + "loss": 0.0391, + "step": 8363 + }, + { + "epoch": 7.4, + "learning_rate": 1.4522914237870864e-05, + "loss": 0.0453, + "step": 8364 + }, + { + "epoch": 7.4, + "learning_rate": 1.4521636072239078e-05, + "loss": 0.0461, + "step": 8365 + }, + { + "epoch": 7.4, + "learning_rate": 1.4520357813745936e-05, + "loss": 0.045, + "step": 8366 + }, + { + "epoch": 7.4, + "learning_rate": 1.4519079462417694e-05, + "loss": 0.0428, + "step": 8367 + }, + { + "epoch": 7.4, + "learning_rate": 1.4517801018280607e-05, + "loss": 0.0484, + "step": 8368 + }, + { + "epoch": 7.4, + "learning_rate": 1.4516522481360927e-05, + "loss": 0.0561, + "step": 8369 + }, + { + "epoch": 7.41, + "learning_rate": 1.4515243851684915e-05, + "loss": 0.0494, + "step": 8370 + }, + { + "epoch": 7.41, + "learning_rate": 1.4513965129278827e-05, + "loss": 0.0523, + "step": 8371 + }, + { + "epoch": 7.41, + "learning_rate": 1.4512686314168929e-05, + "loss": 0.0501, + "step": 8372 + }, + { + "epoch": 7.41, + "learning_rate": 1.4511407406381479e-05, + "loss": 0.0485, + "step": 8373 + }, + { + "epoch": 7.41, + "learning_rate": 1.4510128405942742e-05, + "loss": 0.044, + "step": 8374 + }, + { + "epoch": 7.41, + "learning_rate": 1.450884931287899e-05, + "loss": 0.0548, + "step": 8375 + }, + { + "epoch": 7.41, + "learning_rate": 1.4507570127216488e-05, + "loss": 0.0514, + "step": 8376 + }, + { + "epoch": 7.41, + "learning_rate": 1.450629084898151e-05, + "loss": 0.0543, + "step": 8377 + }, + { + "epoch": 7.41, + "learning_rate": 1.4505011478200324e-05, + "loss": 0.0445, + "step": 8378 + }, + { + "epoch": 7.41, + "learning_rate": 1.450373201489921e-05, + "loss": 0.051, + "step": 8379 + }, + { + "epoch": 7.41, + "learning_rate": 1.4502452459104438e-05, + "loss": 0.0502, + "step": 8380 + }, + { + "epoch": 7.42, + "learning_rate": 1.4501172810842292e-05, + "loss": 0.0478, + "step": 8381 + }, + { + "epoch": 7.42, + "learning_rate": 1.449989307013905e-05, + "loss": 0.0483, + "step": 8382 + }, + { + "epoch": 7.42, + "learning_rate": 1.4498613237020994e-05, + "loss": 0.0491, + "step": 8383 + }, + { + "epoch": 7.42, + "learning_rate": 1.4497333311514408e-05, + "loss": 0.0442, + "step": 8384 + }, + { + "epoch": 7.42, + "learning_rate": 1.449605329364558e-05, + "loss": 0.0463, + "step": 8385 + }, + { + "epoch": 7.42, + "learning_rate": 1.4494773183440797e-05, + "loss": 0.0488, + "step": 8386 + }, + { + "epoch": 7.42, + "learning_rate": 1.4493492980926346e-05, + "loss": 0.0455, + "step": 8387 + }, + { + "epoch": 7.42, + "learning_rate": 1.4492212686128522e-05, + "loss": 0.0518, + "step": 8388 + }, + { + "epoch": 7.42, + "learning_rate": 1.4490932299073616e-05, + "loss": 0.0458, + "step": 8389 + }, + { + "epoch": 7.42, + "learning_rate": 1.4489651819787926e-05, + "loss": 0.0499, + "step": 8390 + }, + { + "epoch": 7.42, + "learning_rate": 1.4488371248297748e-05, + "loss": 0.0504, + "step": 8391 + }, + { + "epoch": 7.43, + "learning_rate": 1.4487090584629382e-05, + "loss": 0.0457, + "step": 8392 + }, + { + "epoch": 7.43, + "learning_rate": 1.4485809828809129e-05, + "loss": 0.0463, + "step": 8393 + }, + { + "epoch": 7.43, + "learning_rate": 1.448452898086329e-05, + "loss": 0.0429, + "step": 8394 + }, + { + "epoch": 7.43, + "learning_rate": 1.4483248040818172e-05, + "loss": 0.0501, + "step": 8395 + }, + { + "epoch": 7.43, + "learning_rate": 1.4481967008700081e-05, + "loss": 0.0577, + "step": 8396 + }, + { + "epoch": 7.43, + "learning_rate": 1.4480685884535327e-05, + "loss": 0.056, + "step": 8397 + }, + { + "epoch": 7.43, + "learning_rate": 1.4479404668350219e-05, + "loss": 0.049, + "step": 8398 + }, + { + "epoch": 7.43, + "learning_rate": 1.4478123360171068e-05, + "loss": 0.0534, + "step": 8399 + }, + { + "epoch": 7.43, + "learning_rate": 1.4476841960024195e-05, + "loss": 0.051, + "step": 8400 + }, + { + "epoch": 7.43, + "learning_rate": 1.447556046793591e-05, + "loss": 0.0487, + "step": 8401 + }, + { + "epoch": 7.43, + "learning_rate": 1.447427888393253e-05, + "loss": 0.0514, + "step": 8402 + }, + { + "epoch": 7.43, + "learning_rate": 1.447299720804038e-05, + "loss": 0.044, + "step": 8403 + }, + { + "epoch": 7.44, + "learning_rate": 1.4471715440285778e-05, + "loss": 0.0509, + "step": 8404 + }, + { + "epoch": 7.44, + "learning_rate": 1.4470433580695051e-05, + "loss": 0.0488, + "step": 8405 + }, + { + "epoch": 7.44, + "learning_rate": 1.4469151629294524e-05, + "loss": 0.042, + "step": 8406 + }, + { + "epoch": 7.44, + "learning_rate": 1.4467869586110526e-05, + "loss": 0.0559, + "step": 8407 + }, + { + "epoch": 7.44, + "learning_rate": 1.4466587451169381e-05, + "loss": 0.0547, + "step": 8408 + }, + { + "epoch": 7.44, + "learning_rate": 1.4465305224497423e-05, + "loss": 0.0416, + "step": 8409 + }, + { + "epoch": 7.44, + "learning_rate": 1.4464022906120989e-05, + "loss": 0.0531, + "step": 8410 + }, + { + "epoch": 7.44, + "learning_rate": 1.446274049606641e-05, + "loss": 0.0498, + "step": 8411 + }, + { + "epoch": 7.44, + "learning_rate": 1.4461457994360021e-05, + "loss": 0.049, + "step": 8412 + }, + { + "epoch": 7.44, + "learning_rate": 1.4460175401028166e-05, + "loss": 0.0535, + "step": 8413 + }, + { + "epoch": 7.44, + "learning_rate": 1.4458892716097188e-05, + "loss": 0.0581, + "step": 8414 + }, + { + "epoch": 7.45, + "learning_rate": 1.445760993959342e-05, + "loss": 0.0479, + "step": 8415 + }, + { + "epoch": 7.45, + "learning_rate": 1.4456327071543213e-05, + "loss": 0.0431, + "step": 8416 + }, + { + "epoch": 7.45, + "learning_rate": 1.4455044111972914e-05, + "loss": 0.0554, + "step": 8417 + }, + { + "epoch": 7.45, + "learning_rate": 1.4453761060908869e-05, + "loss": 0.0426, + "step": 8418 + }, + { + "epoch": 7.45, + "learning_rate": 1.4452477918377428e-05, + "loss": 0.0482, + "step": 8419 + }, + { + "epoch": 7.45, + "learning_rate": 1.445119468440494e-05, + "loss": 0.0435, + "step": 8420 + }, + { + "epoch": 7.45, + "learning_rate": 1.444991135901777e-05, + "loss": 0.0593, + "step": 8421 + }, + { + "epoch": 7.45, + "learning_rate": 1.444862794224226e-05, + "loss": 0.0468, + "step": 8422 + }, + { + "epoch": 7.45, + "learning_rate": 1.4447344434104777e-05, + "loss": 0.0434, + "step": 8423 + }, + { + "epoch": 7.45, + "learning_rate": 1.4446060834631681e-05, + "loss": 0.0516, + "step": 8424 + }, + { + "epoch": 7.45, + "learning_rate": 1.4444777143849327e-05, + "loss": 0.0545, + "step": 8425 + }, + { + "epoch": 7.46, + "learning_rate": 1.4443493361784083e-05, + "loss": 0.0525, + "step": 8426 + }, + { + "epoch": 7.46, + "learning_rate": 1.4442209488462308e-05, + "loss": 0.0429, + "step": 8427 + }, + { + "epoch": 7.46, + "learning_rate": 1.4440925523910379e-05, + "loss": 0.0531, + "step": 8428 + }, + { + "epoch": 7.46, + "learning_rate": 1.4439641468154656e-05, + "loss": 0.0505, + "step": 8429 + }, + { + "epoch": 7.46, + "learning_rate": 1.4438357321221514e-05, + "loss": 0.0429, + "step": 8430 + }, + { + "epoch": 7.46, + "learning_rate": 1.443707308313733e-05, + "loss": 0.048, + "step": 8431 + }, + { + "epoch": 7.46, + "learning_rate": 1.4435788753928468e-05, + "loss": 0.0597, + "step": 8432 + }, + { + "epoch": 7.46, + "learning_rate": 1.443450433362131e-05, + "loss": 0.0455, + "step": 8433 + }, + { + "epoch": 7.46, + "learning_rate": 1.4433219822242237e-05, + "loss": 0.0417, + "step": 8434 + }, + { + "epoch": 7.46, + "learning_rate": 1.4431935219817625e-05, + "loss": 0.05, + "step": 8435 + }, + { + "epoch": 7.46, + "learning_rate": 1.443065052637386e-05, + "loss": 0.0503, + "step": 8436 + }, + { + "epoch": 7.47, + "learning_rate": 1.442936574193732e-05, + "loss": 0.054, + "step": 8437 + }, + { + "epoch": 7.47, + "learning_rate": 1.4428080866534397e-05, + "loss": 0.0441, + "step": 8438 + }, + { + "epoch": 7.47, + "learning_rate": 1.4426795900191475e-05, + "loss": 0.0522, + "step": 8439 + }, + { + "epoch": 7.47, + "learning_rate": 1.4425510842934943e-05, + "loss": 0.0513, + "step": 8440 + }, + { + "epoch": 7.47, + "learning_rate": 1.4424225694791194e-05, + "loss": 0.0552, + "step": 8441 + }, + { + "epoch": 7.47, + "learning_rate": 1.4422940455786621e-05, + "loss": 0.05, + "step": 8442 + }, + { + "epoch": 7.47, + "learning_rate": 1.442165512594762e-05, + "loss": 0.0503, + "step": 8443 + }, + { + "epoch": 7.47, + "learning_rate": 1.4420369705300585e-05, + "loss": 0.0444, + "step": 8444 + }, + { + "epoch": 7.47, + "learning_rate": 1.441908419387192e-05, + "loss": 0.055, + "step": 8445 + }, + { + "epoch": 7.47, + "learning_rate": 1.4417798591688019e-05, + "loss": 0.0538, + "step": 8446 + }, + { + "epoch": 7.47, + "learning_rate": 1.441651289877529e-05, + "loss": 0.0591, + "step": 8447 + }, + { + "epoch": 7.47, + "learning_rate": 1.4415227115160136e-05, + "loss": 0.0463, + "step": 8448 + }, + { + "epoch": 7.48, + "learning_rate": 1.441394124086896e-05, + "loss": 0.0494, + "step": 8449 + }, + { + "epoch": 7.48, + "learning_rate": 1.4412655275928176e-05, + "loss": 0.0511, + "step": 8450 + }, + { + "epoch": 7.48, + "learning_rate": 1.4411369220364189e-05, + "loss": 0.0459, + "step": 8451 + }, + { + "epoch": 7.48, + "learning_rate": 1.4410083074203413e-05, + "loss": 0.0622, + "step": 8452 + }, + { + "epoch": 7.48, + "learning_rate": 1.4408796837472264e-05, + "loss": 0.0535, + "step": 8453 + }, + { + "epoch": 7.48, + "learning_rate": 1.440751051019715e-05, + "loss": 0.048, + "step": 8454 + }, + { + "epoch": 7.48, + "learning_rate": 1.44062240924045e-05, + "loss": 0.057, + "step": 8455 + }, + { + "epoch": 7.48, + "learning_rate": 1.4404937584120722e-05, + "loss": 0.0497, + "step": 8456 + }, + { + "epoch": 7.48, + "learning_rate": 1.4403650985372242e-05, + "loss": 0.0553, + "step": 8457 + }, + { + "epoch": 7.48, + "learning_rate": 1.4402364296185485e-05, + "loss": 0.0555, + "step": 8458 + }, + { + "epoch": 7.48, + "learning_rate": 1.4401077516586874e-05, + "loss": 0.056, + "step": 8459 + }, + { + "epoch": 7.49, + "learning_rate": 1.4399790646602836e-05, + "loss": 0.0438, + "step": 8460 + }, + { + "epoch": 7.49, + "learning_rate": 1.4398503686259795e-05, + "loss": 0.0455, + "step": 8461 + }, + { + "epoch": 7.49, + "learning_rate": 1.439721663558419e-05, + "loss": 0.0553, + "step": 8462 + }, + { + "epoch": 7.49, + "learning_rate": 1.439592949460245e-05, + "loss": 0.0554, + "step": 8463 + }, + { + "epoch": 7.49, + "learning_rate": 1.4394642263341006e-05, + "loss": 0.0429, + "step": 8464 + }, + { + "epoch": 7.49, + "learning_rate": 1.4393354941826294e-05, + "loss": 0.0553, + "step": 8465 + }, + { + "epoch": 7.49, + "learning_rate": 1.4392067530084759e-05, + "loss": 0.0457, + "step": 8466 + }, + { + "epoch": 7.49, + "learning_rate": 1.439078002814283e-05, + "loss": 0.0565, + "step": 8467 + }, + { + "epoch": 7.49, + "learning_rate": 1.4389492436026957e-05, + "loss": 0.0445, + "step": 8468 + }, + { + "epoch": 7.49, + "learning_rate": 1.4388204753763584e-05, + "loss": 0.0497, + "step": 8469 + }, + { + "epoch": 7.49, + "learning_rate": 1.4386916981379149e-05, + "loss": 0.0503, + "step": 8470 + }, + { + "epoch": 7.5, + "learning_rate": 1.4385629118900105e-05, + "loss": 0.0553, + "step": 8471 + }, + { + "epoch": 7.5, + "learning_rate": 1.4384341166352898e-05, + "loss": 0.0566, + "step": 8472 + }, + { + "epoch": 7.5, + "learning_rate": 1.4383053123763981e-05, + "loss": 0.0463, + "step": 8473 + }, + { + "epoch": 7.5, + "learning_rate": 1.4381764991159803e-05, + "loss": 0.0488, + "step": 8474 + }, + { + "epoch": 7.5, + "learning_rate": 1.4380476768566825e-05, + "loss": 0.0518, + "step": 8475 + }, + { + "epoch": 7.5, + "learning_rate": 1.4379188456011497e-05, + "loss": 0.0542, + "step": 8476 + }, + { + "epoch": 7.5, + "learning_rate": 1.4377900053520282e-05, + "loss": 0.052, + "step": 8477 + }, + { + "epoch": 7.5, + "learning_rate": 1.4376611561119636e-05, + "loss": 0.0492, + "step": 8478 + }, + { + "epoch": 7.5, + "learning_rate": 1.4375322978836024e-05, + "loss": 0.0442, + "step": 8479 + }, + { + "epoch": 7.5, + "learning_rate": 1.4374034306695905e-05, + "loss": 0.0542, + "step": 8480 + }, + { + "epoch": 7.5, + "learning_rate": 1.4372745544725752e-05, + "loss": 0.0535, + "step": 8481 + }, + { + "epoch": 7.5, + "learning_rate": 1.4371456692952029e-05, + "loss": 0.0504, + "step": 8482 + }, + { + "epoch": 7.51, + "learning_rate": 1.4370167751401201e-05, + "loss": 0.0432, + "step": 8483 + }, + { + "epoch": 7.51, + "learning_rate": 1.4368878720099748e-05, + "loss": 0.049, + "step": 8484 + }, + { + "epoch": 7.51, + "learning_rate": 1.4367589599074134e-05, + "loss": 0.052, + "step": 8485 + }, + { + "epoch": 7.51, + "learning_rate": 1.436630038835084e-05, + "loss": 0.0502, + "step": 8486 + }, + { + "epoch": 7.51, + "learning_rate": 1.4365011087956337e-05, + "loss": 0.0562, + "step": 8487 + }, + { + "epoch": 7.51, + "learning_rate": 1.436372169791711e-05, + "loss": 0.0428, + "step": 8488 + }, + { + "epoch": 7.51, + "learning_rate": 1.4362432218259637e-05, + "loss": 0.0463, + "step": 8489 + }, + { + "epoch": 7.51, + "learning_rate": 1.4361142649010397e-05, + "loss": 0.0457, + "step": 8490 + }, + { + "epoch": 7.51, + "learning_rate": 1.4359852990195881e-05, + "loss": 0.0508, + "step": 8491 + }, + { + "epoch": 7.51, + "learning_rate": 1.4358563241842567e-05, + "loss": 0.0485, + "step": 8492 + }, + { + "epoch": 7.51, + "learning_rate": 1.4357273403976945e-05, + "loss": 0.0478, + "step": 8493 + }, + { + "epoch": 7.52, + "learning_rate": 1.4355983476625508e-05, + "loss": 0.0458, + "step": 8494 + }, + { + "epoch": 7.52, + "learning_rate": 1.4354693459814743e-05, + "loss": 0.0589, + "step": 8495 + }, + { + "epoch": 7.52, + "learning_rate": 1.4353403353571148e-05, + "loss": 0.0498, + "step": 8496 + }, + { + "epoch": 7.52, + "learning_rate": 1.4352113157921212e-05, + "loss": 0.0511, + "step": 8497 + }, + { + "epoch": 7.52, + "learning_rate": 1.4350822872891442e-05, + "loss": 0.0552, + "step": 8498 + }, + { + "epoch": 7.52, + "learning_rate": 1.4349532498508323e-05, + "loss": 0.0524, + "step": 8499 + }, + { + "epoch": 7.52, + "learning_rate": 1.4348242034798362e-05, + "loss": 0.0487, + "step": 8500 + }, + { + "epoch": 7.52, + "learning_rate": 1.4346951481788067e-05, + "loss": 0.0493, + "step": 8501 + }, + { + "epoch": 7.52, + "learning_rate": 1.4345660839503935e-05, + "loss": 0.0485, + "step": 8502 + }, + { + "epoch": 7.52, + "learning_rate": 1.4344370107972471e-05, + "loss": 0.0549, + "step": 8503 + }, + { + "epoch": 7.52, + "learning_rate": 1.434307928722019e-05, + "loss": 0.0526, + "step": 8504 + }, + { + "epoch": 7.53, + "learning_rate": 1.43417883772736e-05, + "loss": 0.0544, + "step": 8505 + }, + { + "epoch": 7.53, + "learning_rate": 1.4340497378159204e-05, + "loss": 0.046, + "step": 8506 + }, + { + "epoch": 7.53, + "learning_rate": 1.4339206289903524e-05, + "loss": 0.0485, + "step": 8507 + }, + { + "epoch": 7.53, + "learning_rate": 1.4337915112533077e-05, + "loss": 0.0477, + "step": 8508 + }, + { + "epoch": 7.53, + "learning_rate": 1.4336623846074374e-05, + "loss": 0.0478, + "step": 8509 + }, + { + "epoch": 7.53, + "learning_rate": 1.4335332490553935e-05, + "loss": 0.0503, + "step": 8510 + }, + { + "epoch": 7.53, + "learning_rate": 1.4334041045998281e-05, + "loss": 0.0519, + "step": 8511 + }, + { + "epoch": 7.53, + "learning_rate": 1.4332749512433938e-05, + "loss": 0.0547, + "step": 8512 + }, + { + "epoch": 7.53, + "learning_rate": 1.4331457889887423e-05, + "loss": 0.0569, + "step": 8513 + }, + { + "epoch": 7.53, + "learning_rate": 1.433016617838527e-05, + "loss": 0.0438, + "step": 8514 + }, + { + "epoch": 7.53, + "learning_rate": 1.4328874377954005e-05, + "loss": 0.0553, + "step": 8515 + }, + { + "epoch": 7.53, + "learning_rate": 1.4327582488620155e-05, + "loss": 0.0484, + "step": 8516 + }, + { + "epoch": 7.54, + "learning_rate": 1.4326290510410255e-05, + "loss": 0.0512, + "step": 8517 + }, + { + "epoch": 7.54, + "learning_rate": 1.4324998443350835e-05, + "loss": 0.0435, + "step": 8518 + }, + { + "epoch": 7.54, + "learning_rate": 1.4323706287468433e-05, + "loss": 0.0553, + "step": 8519 + }, + { + "epoch": 7.54, + "learning_rate": 1.4322414042789582e-05, + "loss": 0.044, + "step": 8520 + }, + { + "epoch": 7.54, + "learning_rate": 1.4321121709340828e-05, + "loss": 0.0542, + "step": 8521 + }, + { + "epoch": 7.54, + "learning_rate": 1.431982928714871e-05, + "loss": 0.0572, + "step": 8522 + }, + { + "epoch": 7.54, + "learning_rate": 1.4318536776239767e-05, + "loss": 0.0518, + "step": 8523 + }, + { + "epoch": 7.54, + "learning_rate": 1.4317244176640543e-05, + "loss": 0.0452, + "step": 8524 + }, + { + "epoch": 7.54, + "learning_rate": 1.4315951488377589e-05, + "loss": 0.0508, + "step": 8525 + }, + { + "epoch": 7.54, + "learning_rate": 1.4314658711477447e-05, + "loss": 0.0493, + "step": 8526 + }, + { + "epoch": 7.54, + "learning_rate": 1.4313365845966674e-05, + "loss": 0.047, + "step": 8527 + }, + { + "epoch": 7.55, + "learning_rate": 1.4312072891871815e-05, + "loss": 0.0541, + "step": 8528 + }, + { + "epoch": 7.55, + "learning_rate": 1.4310779849219432e-05, + "loss": 0.0534, + "step": 8529 + }, + { + "epoch": 7.55, + "learning_rate": 1.430948671803607e-05, + "loss": 0.0566, + "step": 8530 + }, + { + "epoch": 7.55, + "learning_rate": 1.4308193498348293e-05, + "loss": 0.0551, + "step": 8531 + }, + { + "epoch": 7.55, + "learning_rate": 1.430690019018266e-05, + "loss": 0.0513, + "step": 8532 + }, + { + "epoch": 7.55, + "learning_rate": 1.4305606793565728e-05, + "loss": 0.0513, + "step": 8533 + }, + { + "epoch": 7.55, + "learning_rate": 1.430431330852406e-05, + "loss": 0.054, + "step": 8534 + }, + { + "epoch": 7.55, + "learning_rate": 1.4303019735084225e-05, + "loss": 0.0525, + "step": 8535 + }, + { + "epoch": 7.55, + "learning_rate": 1.4301726073272785e-05, + "loss": 0.0496, + "step": 8536 + }, + { + "epoch": 7.55, + "learning_rate": 1.4300432323116312e-05, + "loss": 0.0472, + "step": 8537 + }, + { + "epoch": 7.55, + "learning_rate": 1.429913848464137e-05, + "loss": 0.0556, + "step": 8538 + }, + { + "epoch": 7.56, + "learning_rate": 1.4297844557874536e-05, + "loss": 0.05, + "step": 8539 + }, + { + "epoch": 7.56, + "learning_rate": 1.429655054284238e-05, + "loss": 0.0505, + "step": 8540 + }, + { + "epoch": 7.56, + "learning_rate": 1.4295256439571481e-05, + "loss": 0.046, + "step": 8541 + }, + { + "epoch": 7.56, + "learning_rate": 1.4293962248088413e-05, + "loss": 0.0473, + "step": 8542 + }, + { + "epoch": 7.56, + "learning_rate": 1.4292667968419758e-05, + "loss": 0.0462, + "step": 8543 + }, + { + "epoch": 7.56, + "learning_rate": 1.4291373600592094e-05, + "loss": 0.048, + "step": 8544 + }, + { + "epoch": 7.56, + "learning_rate": 1.4290079144632004e-05, + "loss": 0.0487, + "step": 8545 + }, + { + "epoch": 7.56, + "learning_rate": 1.428878460056607e-05, + "loss": 0.0461, + "step": 8546 + }, + { + "epoch": 7.56, + "learning_rate": 1.4287489968420885e-05, + "loss": 0.0533, + "step": 8547 + }, + { + "epoch": 7.56, + "learning_rate": 1.4286195248223029e-05, + "loss": 0.0496, + "step": 8548 + }, + { + "epoch": 7.56, + "learning_rate": 1.4284900439999099e-05, + "loss": 0.0529, + "step": 8549 + }, + { + "epoch": 7.56, + "learning_rate": 1.4283605543775684e-05, + "loss": 0.051, + "step": 8550 + }, + { + "epoch": 7.57, + "learning_rate": 1.4282310559579375e-05, + "loss": 0.0525, + "step": 8551 + }, + { + "epoch": 7.57, + "learning_rate": 1.4281015487436767e-05, + "loss": 0.0464, + "step": 8552 + }, + { + "epoch": 7.57, + "learning_rate": 1.4279720327374464e-05, + "loss": 0.0479, + "step": 8553 + }, + { + "epoch": 7.57, + "learning_rate": 1.4278425079419058e-05, + "loss": 0.0456, + "step": 8554 + }, + { + "epoch": 7.57, + "learning_rate": 1.4277129743597152e-05, + "loss": 0.048, + "step": 8555 + }, + { + "epoch": 7.57, + "learning_rate": 1.4275834319935347e-05, + "loss": 0.0519, + "step": 8556 + }, + { + "epoch": 7.57, + "learning_rate": 1.427453880846025e-05, + "loss": 0.0526, + "step": 8557 + }, + { + "epoch": 7.57, + "learning_rate": 1.4273243209198464e-05, + "loss": 0.0483, + "step": 8558 + }, + { + "epoch": 7.57, + "learning_rate": 1.4271947522176594e-05, + "loss": 0.0508, + "step": 8559 + }, + { + "epoch": 7.57, + "learning_rate": 1.4270651747421263e-05, + "loss": 0.0584, + "step": 8560 + }, + { + "epoch": 7.57, + "learning_rate": 1.4269355884959069e-05, + "loss": 0.0491, + "step": 8561 + }, + { + "epoch": 7.58, + "learning_rate": 1.4268059934816627e-05, + "loss": 0.0608, + "step": 8562 + }, + { + "epoch": 7.58, + "learning_rate": 1.4266763897020558e-05, + "loss": 0.0421, + "step": 8563 + }, + { + "epoch": 7.58, + "learning_rate": 1.426546777159748e-05, + "loss": 0.0553, + "step": 8564 + }, + { + "epoch": 7.58, + "learning_rate": 1.4264171558573999e-05, + "loss": 0.0489, + "step": 8565 + }, + { + "epoch": 7.58, + "learning_rate": 1.4262875257976747e-05, + "loss": 0.0524, + "step": 8566 + }, + { + "epoch": 7.58, + "learning_rate": 1.4261578869832344e-05, + "loss": 0.0486, + "step": 8567 + }, + { + "epoch": 7.58, + "learning_rate": 1.4260282394167413e-05, + "loss": 0.0555, + "step": 8568 + }, + { + "epoch": 7.58, + "learning_rate": 1.4258985831008579e-05, + "loss": 0.0483, + "step": 8569 + }, + { + "epoch": 7.58, + "learning_rate": 1.425768918038247e-05, + "loss": 0.0511, + "step": 8570 + }, + { + "epoch": 7.58, + "learning_rate": 1.425639244231572e-05, + "loss": 0.0447, + "step": 8571 + }, + { + "epoch": 7.58, + "learning_rate": 1.425509561683495e-05, + "loss": 0.0513, + "step": 8572 + }, + { + "epoch": 7.59, + "learning_rate": 1.4253798703966806e-05, + "loss": 0.052, + "step": 8573 + }, + { + "epoch": 7.59, + "learning_rate": 1.4252501703737913e-05, + "loss": 0.0458, + "step": 8574 + }, + { + "epoch": 7.59, + "learning_rate": 1.4251204616174911e-05, + "loss": 0.0525, + "step": 8575 + }, + { + "epoch": 7.59, + "learning_rate": 1.424990744130444e-05, + "loss": 0.0507, + "step": 8576 + }, + { + "epoch": 7.59, + "learning_rate": 1.4248610179153137e-05, + "loss": 0.0596, + "step": 8577 + }, + { + "epoch": 7.59, + "learning_rate": 1.4247312829747645e-05, + "loss": 0.0525, + "step": 8578 + }, + { + "epoch": 7.59, + "learning_rate": 1.424601539311461e-05, + "loss": 0.0527, + "step": 8579 + }, + { + "epoch": 7.59, + "learning_rate": 1.4244717869280677e-05, + "loss": 0.0444, + "step": 8580 + }, + { + "epoch": 7.59, + "learning_rate": 1.4243420258272492e-05, + "loss": 0.0462, + "step": 8581 + }, + { + "epoch": 7.59, + "learning_rate": 1.4242122560116705e-05, + "loss": 0.0528, + "step": 8582 + }, + { + "epoch": 7.59, + "learning_rate": 1.4240824774839963e-05, + "loss": 0.054, + "step": 8583 + }, + { + "epoch": 7.6, + "learning_rate": 1.4239526902468925e-05, + "loss": 0.0503, + "step": 8584 + }, + { + "epoch": 7.6, + "learning_rate": 1.4238228943030244e-05, + "loss": 0.0489, + "step": 8585 + }, + { + "epoch": 7.6, + "learning_rate": 1.4236930896550571e-05, + "loss": 0.0538, + "step": 8586 + }, + { + "epoch": 7.6, + "learning_rate": 1.4235632763056573e-05, + "loss": 0.0499, + "step": 8587 + }, + { + "epoch": 7.6, + "learning_rate": 1.4234334542574906e-05, + "loss": 0.0518, + "step": 8588 + }, + { + "epoch": 7.6, + "learning_rate": 1.4233036235132227e-05, + "loss": 0.0492, + "step": 8589 + }, + { + "epoch": 7.6, + "learning_rate": 1.4231737840755204e-05, + "loss": 0.04, + "step": 8590 + }, + { + "epoch": 7.6, + "learning_rate": 1.42304393594705e-05, + "loss": 0.0564, + "step": 8591 + }, + { + "epoch": 7.6, + "learning_rate": 1.422914079130479e-05, + "loss": 0.0467, + "step": 8592 + }, + { + "epoch": 7.6, + "learning_rate": 1.4227842136284733e-05, + "loss": 0.0502, + "step": 8593 + }, + { + "epoch": 7.6, + "learning_rate": 1.4226543394437002e-05, + "loss": 0.0482, + "step": 8594 + }, + { + "epoch": 7.6, + "learning_rate": 1.4225244565788274e-05, + "loss": 0.0499, + "step": 8595 + }, + { + "epoch": 7.61, + "learning_rate": 1.4223945650365218e-05, + "loss": 0.0467, + "step": 8596 + }, + { + "epoch": 7.61, + "learning_rate": 1.4222646648194513e-05, + "loss": 0.0551, + "step": 8597 + }, + { + "epoch": 7.61, + "learning_rate": 1.4221347559302832e-05, + "loss": 0.0531, + "step": 8598 + }, + { + "epoch": 7.61, + "learning_rate": 1.4220048383716863e-05, + "loss": 0.0547, + "step": 8599 + }, + { + "epoch": 7.61, + "learning_rate": 1.4218749121463278e-05, + "loss": 0.0544, + "step": 8600 + }, + { + "epoch": 7.61, + "learning_rate": 1.4217449772568768e-05, + "loss": 0.052, + "step": 8601 + }, + { + "epoch": 7.61, + "learning_rate": 1.4216150337060013e-05, + "loss": 0.0499, + "step": 8602 + }, + { + "epoch": 7.61, + "learning_rate": 1.4214850814963704e-05, + "loss": 0.0526, + "step": 8603 + }, + { + "epoch": 7.61, + "learning_rate": 1.421355120630652e-05, + "loss": 0.0445, + "step": 8604 + }, + { + "epoch": 7.61, + "learning_rate": 1.4212251511115161e-05, + "loss": 0.057, + "step": 8605 + }, + { + "epoch": 7.61, + "learning_rate": 1.4210951729416318e-05, + "loss": 0.0504, + "step": 8606 + }, + { + "epoch": 7.62, + "learning_rate": 1.420965186123668e-05, + "loss": 0.0487, + "step": 8607 + }, + { + "epoch": 7.62, + "learning_rate": 1.4208351906602947e-05, + "loss": 0.0552, + "step": 8608 + }, + { + "epoch": 7.62, + "learning_rate": 1.4207051865541812e-05, + "loss": 0.0534, + "step": 8609 + }, + { + "epoch": 7.62, + "learning_rate": 1.4205751738079978e-05, + "loss": 0.0496, + "step": 8610 + }, + { + "epoch": 7.62, + "learning_rate": 1.4204451524244143e-05, + "loss": 0.0482, + "step": 8611 + }, + { + "epoch": 7.62, + "learning_rate": 1.420315122406101e-05, + "loss": 0.0544, + "step": 8612 + }, + { + "epoch": 7.62, + "learning_rate": 1.4201850837557286e-05, + "loss": 0.0503, + "step": 8613 + }, + { + "epoch": 7.62, + "learning_rate": 1.4200550364759678e-05, + "loss": 0.0556, + "step": 8614 + }, + { + "epoch": 7.62, + "learning_rate": 1.4199249805694889e-05, + "loss": 0.0514, + "step": 8615 + }, + { + "epoch": 7.62, + "learning_rate": 1.419794916038963e-05, + "loss": 0.0596, + "step": 8616 + }, + { + "epoch": 7.62, + "learning_rate": 1.4196648428870615e-05, + "loss": 0.0384, + "step": 8617 + }, + { + "epoch": 7.63, + "learning_rate": 1.4195347611164556e-05, + "loss": 0.0506, + "step": 8618 + }, + { + "epoch": 7.63, + "learning_rate": 1.4194046707298168e-05, + "loss": 0.0457, + "step": 8619 + }, + { + "epoch": 7.63, + "learning_rate": 1.419274571729817e-05, + "loss": 0.0511, + "step": 8620 + }, + { + "epoch": 7.63, + "learning_rate": 1.4191444641191274e-05, + "loss": 0.0479, + "step": 8621 + }, + { + "epoch": 7.63, + "learning_rate": 1.4190143479004209e-05, + "loss": 0.0551, + "step": 8622 + }, + { + "epoch": 7.63, + "learning_rate": 1.4188842230763688e-05, + "loss": 0.0489, + "step": 8623 + }, + { + "epoch": 7.63, + "learning_rate": 1.4187540896496443e-05, + "loss": 0.0461, + "step": 8624 + }, + { + "epoch": 7.63, + "learning_rate": 1.4186239476229196e-05, + "loss": 0.0467, + "step": 8625 + }, + { + "epoch": 7.63, + "learning_rate": 1.4184937969988675e-05, + "loss": 0.0523, + "step": 8626 + }, + { + "epoch": 7.63, + "learning_rate": 1.418363637780161e-05, + "loss": 0.0462, + "step": 8627 + }, + { + "epoch": 7.63, + "learning_rate": 1.4182334699694728e-05, + "loss": 0.0505, + "step": 8628 + }, + { + "epoch": 7.63, + "learning_rate": 1.4181032935694767e-05, + "loss": 0.053, + "step": 8629 + }, + { + "epoch": 7.64, + "learning_rate": 1.4179731085828458e-05, + "loss": 0.0585, + "step": 8630 + }, + { + "epoch": 7.64, + "learning_rate": 1.4178429150122538e-05, + "loss": 0.0486, + "step": 8631 + }, + { + "epoch": 7.64, + "learning_rate": 1.4177127128603748e-05, + "loss": 0.0416, + "step": 8632 + }, + { + "epoch": 7.64, + "learning_rate": 1.4175825021298822e-05, + "loss": 0.048, + "step": 8633 + }, + { + "epoch": 7.64, + "learning_rate": 1.4174522828234508e-05, + "loss": 0.0472, + "step": 8634 + }, + { + "epoch": 7.64, + "learning_rate": 1.4173220549437543e-05, + "loss": 0.0583, + "step": 8635 + }, + { + "epoch": 7.64, + "learning_rate": 1.4171918184934677e-05, + "loss": 0.0522, + "step": 8636 + }, + { + "epoch": 7.64, + "learning_rate": 1.4170615734752652e-05, + "loss": 0.054, + "step": 8637 + }, + { + "epoch": 7.64, + "learning_rate": 1.4169313198918223e-05, + "loss": 0.0515, + "step": 8638 + }, + { + "epoch": 7.64, + "learning_rate": 1.4168010577458133e-05, + "loss": 0.0572, + "step": 8639 + }, + { + "epoch": 7.64, + "learning_rate": 1.4166707870399139e-05, + "loss": 0.058, + "step": 8640 + }, + { + "epoch": 7.65, + "learning_rate": 1.4165405077767998e-05, + "loss": 0.0535, + "step": 8641 + }, + { + "epoch": 7.65, + "learning_rate": 1.4164102199591457e-05, + "loss": 0.0461, + "step": 8642 + }, + { + "epoch": 7.65, + "learning_rate": 1.4162799235896274e-05, + "loss": 0.0516, + "step": 8643 + }, + { + "epoch": 7.65, + "learning_rate": 1.4161496186709218e-05, + "loss": 0.0572, + "step": 8644 + }, + { + "epoch": 7.65, + "learning_rate": 1.416019305205704e-05, + "loss": 0.0538, + "step": 8645 + }, + { + "epoch": 7.65, + "learning_rate": 1.4158889831966507e-05, + "loss": 0.0541, + "step": 8646 + }, + { + "epoch": 7.65, + "learning_rate": 1.4157586526464384e-05, + "loss": 0.0506, + "step": 8647 + }, + { + "epoch": 7.65, + "learning_rate": 1.4156283135577437e-05, + "loss": 0.0569, + "step": 8648 + }, + { + "epoch": 7.65, + "learning_rate": 1.415497965933243e-05, + "loss": 0.0553, + "step": 8649 + }, + { + "epoch": 7.65, + "learning_rate": 1.4153676097756132e-05, + "loss": 0.0407, + "step": 8650 + }, + { + "epoch": 7.65, + "learning_rate": 1.4152372450875325e-05, + "loss": 0.0479, + "step": 8651 + }, + { + "epoch": 7.66, + "learning_rate": 1.415106871871677e-05, + "loss": 0.0578, + "step": 8652 + }, + { + "epoch": 7.66, + "learning_rate": 1.4149764901307245e-05, + "loss": 0.0546, + "step": 8653 + }, + { + "epoch": 7.66, + "learning_rate": 1.4148460998673533e-05, + "loss": 0.0483, + "step": 8654 + }, + { + "epoch": 7.66, + "learning_rate": 1.4147157010842408e-05, + "loss": 0.0585, + "step": 8655 + }, + { + "epoch": 7.66, + "learning_rate": 1.4145852937840642e-05, + "loss": 0.0426, + "step": 8656 + }, + { + "epoch": 7.66, + "learning_rate": 1.414454877969503e-05, + "loss": 0.0512, + "step": 8657 + }, + { + "epoch": 7.66, + "learning_rate": 1.4143244536432353e-05, + "loss": 0.0506, + "step": 8658 + }, + { + "epoch": 7.66, + "learning_rate": 1.4141940208079392e-05, + "loss": 0.0473, + "step": 8659 + }, + { + "epoch": 7.66, + "learning_rate": 1.4140635794662934e-05, + "loss": 0.0523, + "step": 8660 + }, + { + "epoch": 7.66, + "learning_rate": 1.4139331296209771e-05, + "loss": 0.0476, + "step": 8661 + }, + { + "epoch": 7.66, + "learning_rate": 1.4138026712746694e-05, + "loss": 0.0513, + "step": 8662 + }, + { + "epoch": 7.66, + "learning_rate": 1.413672204430049e-05, + "loss": 0.058, + "step": 8663 + }, + { + "epoch": 7.67, + "learning_rate": 1.413541729089796e-05, + "loss": 0.0549, + "step": 8664 + }, + { + "epoch": 7.67, + "learning_rate": 1.4134112452565896e-05, + "loss": 0.0494, + "step": 8665 + }, + { + "epoch": 7.67, + "learning_rate": 1.4132807529331096e-05, + "loss": 0.0561, + "step": 8666 + }, + { + "epoch": 7.67, + "learning_rate": 1.413150252122036e-05, + "loss": 0.0499, + "step": 8667 + }, + { + "epoch": 7.67, + "learning_rate": 1.4130197428260487e-05, + "loss": 0.0539, + "step": 8668 + }, + { + "epoch": 7.67, + "learning_rate": 1.4128892250478286e-05, + "loss": 0.0509, + "step": 8669 + }, + { + "epoch": 7.67, + "learning_rate": 1.4127586987900554e-05, + "loss": 0.0454, + "step": 8670 + }, + { + "epoch": 7.67, + "learning_rate": 1.4126281640554101e-05, + "loss": 0.0462, + "step": 8671 + }, + { + "epoch": 7.67, + "learning_rate": 1.4124976208465737e-05, + "loss": 0.0486, + "step": 8672 + }, + { + "epoch": 7.67, + "learning_rate": 1.4123670691662268e-05, + "loss": 0.0528, + "step": 8673 + }, + { + "epoch": 7.67, + "learning_rate": 1.4122365090170504e-05, + "loss": 0.0479, + "step": 8674 + }, + { + "epoch": 7.68, + "learning_rate": 1.4121059404017266e-05, + "loss": 0.0481, + "step": 8675 + }, + { + "epoch": 7.68, + "learning_rate": 1.4119753633229361e-05, + "loss": 0.0504, + "step": 8676 + }, + { + "epoch": 7.68, + "learning_rate": 1.411844777783361e-05, + "loss": 0.0528, + "step": 8677 + }, + { + "epoch": 7.68, + "learning_rate": 1.4117141837856832e-05, + "loss": 0.0515, + "step": 8678 + }, + { + "epoch": 7.68, + "learning_rate": 1.4115835813325847e-05, + "loss": 0.045, + "step": 8679 + }, + { + "epoch": 7.68, + "learning_rate": 1.4114529704267473e-05, + "loss": 0.0469, + "step": 8680 + }, + { + "epoch": 7.68, + "learning_rate": 1.4113223510708536e-05, + "loss": 0.0623, + "step": 8681 + }, + { + "epoch": 7.68, + "learning_rate": 1.4111917232675864e-05, + "loss": 0.0488, + "step": 8682 + }, + { + "epoch": 7.68, + "learning_rate": 1.4110610870196282e-05, + "loss": 0.0446, + "step": 8683 + }, + { + "epoch": 7.68, + "learning_rate": 1.4109304423296618e-05, + "loss": 0.0487, + "step": 8684 + }, + { + "epoch": 7.68, + "learning_rate": 1.4107997892003701e-05, + "loss": 0.0524, + "step": 8685 + }, + { + "epoch": 7.69, + "learning_rate": 1.4106691276344372e-05, + "loss": 0.0497, + "step": 8686 + }, + { + "epoch": 7.69, + "learning_rate": 1.4105384576345458e-05, + "loss": 0.0484, + "step": 8687 + }, + { + "epoch": 7.69, + "learning_rate": 1.4104077792033792e-05, + "loss": 0.0489, + "step": 8688 + }, + { + "epoch": 7.69, + "learning_rate": 1.410277092343622e-05, + "loss": 0.0519, + "step": 8689 + }, + { + "epoch": 7.69, + "learning_rate": 1.4101463970579575e-05, + "loss": 0.0561, + "step": 8690 + }, + { + "epoch": 7.69, + "learning_rate": 1.4100156933490699e-05, + "loss": 0.053, + "step": 8691 + }, + { + "epoch": 7.69, + "learning_rate": 1.4098849812196436e-05, + "loss": 0.0501, + "step": 8692 + }, + { + "epoch": 7.69, + "learning_rate": 1.4097542606723634e-05, + "loss": 0.0457, + "step": 8693 + }, + { + "epoch": 7.69, + "learning_rate": 1.4096235317099132e-05, + "loss": 0.0518, + "step": 8694 + }, + { + "epoch": 7.69, + "learning_rate": 1.4094927943349779e-05, + "loss": 0.057, + "step": 8695 + }, + { + "epoch": 7.69, + "learning_rate": 1.4093620485502433e-05, + "loss": 0.046, + "step": 8696 + }, + { + "epoch": 7.7, + "learning_rate": 1.4092312943583934e-05, + "loss": 0.0471, + "step": 8697 + }, + { + "epoch": 7.7, + "learning_rate": 1.4091005317621144e-05, + "loss": 0.0518, + "step": 8698 + }, + { + "epoch": 7.7, + "learning_rate": 1.4089697607640913e-05, + "loss": 0.0423, + "step": 8699 + }, + { + "epoch": 7.7, + "learning_rate": 1.4088389813670102e-05, + "loss": 0.0478, + "step": 8700 + }, + { + "epoch": 7.7, + "learning_rate": 1.4087081935735565e-05, + "loss": 0.0519, + "step": 8701 + }, + { + "epoch": 7.7, + "learning_rate": 1.408577397386416e-05, + "loss": 0.0528, + "step": 8702 + }, + { + "epoch": 7.7, + "learning_rate": 1.4084465928082755e-05, + "loss": 0.0574, + "step": 8703 + }, + { + "epoch": 7.7, + "learning_rate": 1.4083157798418213e-05, + "loss": 0.0534, + "step": 8704 + }, + { + "epoch": 7.7, + "learning_rate": 1.4081849584897394e-05, + "loss": 0.0585, + "step": 8705 + }, + { + "epoch": 7.7, + "learning_rate": 1.4080541287547168e-05, + "loss": 0.0555, + "step": 8706 + }, + { + "epoch": 7.7, + "learning_rate": 1.4079232906394405e-05, + "loss": 0.0594, + "step": 8707 + }, + { + "epoch": 7.7, + "learning_rate": 1.4077924441465973e-05, + "loss": 0.0505, + "step": 8708 + }, + { + "epoch": 7.71, + "learning_rate": 1.4076615892788743e-05, + "loss": 0.0521, + "step": 8709 + }, + { + "epoch": 7.71, + "learning_rate": 1.4075307260389593e-05, + "loss": 0.055, + "step": 8710 + }, + { + "epoch": 7.71, + "learning_rate": 1.4073998544295395e-05, + "loss": 0.0547, + "step": 8711 + }, + { + "epoch": 7.71, + "learning_rate": 1.4072689744533028e-05, + "loss": 0.0473, + "step": 8712 + }, + { + "epoch": 7.71, + "learning_rate": 1.4071380861129372e-05, + "loss": 0.0472, + "step": 8713 + }, + { + "epoch": 7.71, + "learning_rate": 1.4070071894111306e-05, + "loss": 0.055, + "step": 8714 + }, + { + "epoch": 7.71, + "learning_rate": 1.406876284350571e-05, + "loss": 0.0516, + "step": 8715 + }, + { + "epoch": 7.71, + "learning_rate": 1.4067453709339471e-05, + "loss": 0.0524, + "step": 8716 + }, + { + "epoch": 7.71, + "learning_rate": 1.4066144491639477e-05, + "loss": 0.0541, + "step": 8717 + }, + { + "epoch": 7.71, + "learning_rate": 1.4064835190432612e-05, + "loss": 0.0591, + "step": 8718 + }, + { + "epoch": 7.71, + "learning_rate": 1.4063525805745768e-05, + "loss": 0.0528, + "step": 8719 + }, + { + "epoch": 7.72, + "learning_rate": 1.4062216337605831e-05, + "loss": 0.0491, + "step": 8720 + }, + { + "epoch": 7.72, + "learning_rate": 1.4060906786039703e-05, + "loss": 0.0579, + "step": 8721 + }, + { + "epoch": 7.72, + "learning_rate": 1.4059597151074264e-05, + "loss": 0.0525, + "step": 8722 + }, + { + "epoch": 7.72, + "learning_rate": 1.4058287432736424e-05, + "loss": 0.0593, + "step": 8723 + }, + { + "epoch": 7.72, + "learning_rate": 1.4056977631053074e-05, + "loss": 0.051, + "step": 8724 + }, + { + "epoch": 7.72, + "learning_rate": 1.4055667746051116e-05, + "loss": 0.0452, + "step": 8725 + }, + { + "epoch": 7.72, + "learning_rate": 1.4054357777757451e-05, + "loss": 0.0519, + "step": 8726 + }, + { + "epoch": 7.72, + "learning_rate": 1.4053047726198979e-05, + "loss": 0.0471, + "step": 8727 + }, + { + "epoch": 7.72, + "learning_rate": 1.4051737591402608e-05, + "loss": 0.0474, + "step": 8728 + }, + { + "epoch": 7.72, + "learning_rate": 1.4050427373395241e-05, + "loss": 0.0566, + "step": 8729 + }, + { + "epoch": 7.72, + "learning_rate": 1.4049117072203791e-05, + "loss": 0.0503, + "step": 8730 + }, + { + "epoch": 7.73, + "learning_rate": 1.4047806687855163e-05, + "loss": 0.0463, + "step": 8731 + }, + { + "epoch": 7.73, + "learning_rate": 1.4046496220376273e-05, + "loss": 0.0528, + "step": 8732 + }, + { + "epoch": 7.73, + "learning_rate": 1.4045185669794032e-05, + "loss": 0.0569, + "step": 8733 + }, + { + "epoch": 7.73, + "learning_rate": 1.4043875036135353e-05, + "loss": 0.0499, + "step": 8734 + }, + { + "epoch": 7.73, + "learning_rate": 1.4042564319427156e-05, + "loss": 0.0582, + "step": 8735 + }, + { + "epoch": 7.73, + "learning_rate": 1.4041253519696357e-05, + "loss": 0.0492, + "step": 8736 + }, + { + "epoch": 7.73, + "learning_rate": 1.4039942636969877e-05, + "loss": 0.0546, + "step": 8737 + }, + { + "epoch": 7.73, + "learning_rate": 1.4038631671274637e-05, + "loss": 0.0563, + "step": 8738 + }, + { + "epoch": 7.73, + "learning_rate": 1.4037320622637563e-05, + "loss": 0.0545, + "step": 8739 + }, + { + "epoch": 7.73, + "learning_rate": 1.4036009491085576e-05, + "loss": 0.0469, + "step": 8740 + }, + { + "epoch": 7.73, + "learning_rate": 1.4034698276645605e-05, + "loss": 0.0432, + "step": 8741 + }, + { + "epoch": 7.73, + "learning_rate": 1.403338697934458e-05, + "loss": 0.0566, + "step": 8742 + }, + { + "epoch": 7.74, + "learning_rate": 1.4032075599209427e-05, + "loss": 0.0576, + "step": 8743 + }, + { + "epoch": 7.74, + "learning_rate": 1.4030764136267084e-05, + "loss": 0.0515, + "step": 8744 + }, + { + "epoch": 7.74, + "learning_rate": 1.4029452590544482e-05, + "loss": 0.0593, + "step": 8745 + }, + { + "epoch": 7.74, + "learning_rate": 1.4028140962068554e-05, + "loss": 0.049, + "step": 8746 + }, + { + "epoch": 7.74, + "learning_rate": 1.4026829250866238e-05, + "loss": 0.0523, + "step": 8747 + }, + { + "epoch": 7.74, + "learning_rate": 1.4025517456964473e-05, + "loss": 0.061, + "step": 8748 + }, + { + "epoch": 7.74, + "learning_rate": 1.4024205580390205e-05, + "loss": 0.052, + "step": 8749 + }, + { + "epoch": 7.74, + "learning_rate": 1.4022893621170368e-05, + "loss": 0.0474, + "step": 8750 + }, + { + "epoch": 7.74, + "learning_rate": 1.4021581579331909e-05, + "loss": 0.0547, + "step": 8751 + }, + { + "epoch": 7.74, + "learning_rate": 1.4020269454901774e-05, + "loss": 0.0511, + "step": 8752 + }, + { + "epoch": 7.74, + "learning_rate": 1.4018957247906913e-05, + "loss": 0.0624, + "step": 8753 + }, + { + "epoch": 7.75, + "learning_rate": 1.4017644958374264e-05, + "loss": 0.0495, + "step": 8754 + }, + { + "epoch": 7.75, + "learning_rate": 1.401633258633079e-05, + "loss": 0.0581, + "step": 8755 + }, + { + "epoch": 7.75, + "learning_rate": 1.4015020131803443e-05, + "loss": 0.0519, + "step": 8756 + }, + { + "epoch": 7.75, + "learning_rate": 1.4013707594819169e-05, + "loss": 0.0573, + "step": 8757 + }, + { + "epoch": 7.75, + "learning_rate": 1.4012394975404926e-05, + "loss": 0.0425, + "step": 8758 + }, + { + "epoch": 7.75, + "learning_rate": 1.4011082273587676e-05, + "loss": 0.0549, + "step": 8759 + }, + { + "epoch": 7.75, + "learning_rate": 1.4009769489394374e-05, + "loss": 0.05, + "step": 8760 + }, + { + "epoch": 7.75, + "learning_rate": 1.400845662285198e-05, + "loss": 0.0506, + "step": 8761 + }, + { + "epoch": 7.75, + "learning_rate": 1.400714367398746e-05, + "loss": 0.0536, + "step": 8762 + }, + { + "epoch": 7.75, + "learning_rate": 1.400583064282778e-05, + "loss": 0.0471, + "step": 8763 + }, + { + "epoch": 7.75, + "learning_rate": 1.40045175293999e-05, + "loss": 0.0554, + "step": 8764 + }, + { + "epoch": 7.76, + "learning_rate": 1.4003204333730787e-05, + "loss": 0.0598, + "step": 8765 + }, + { + "epoch": 7.76, + "learning_rate": 1.4001891055847416e-05, + "loss": 0.0559, + "step": 8766 + }, + { + "epoch": 7.76, + "learning_rate": 1.4000577695776754e-05, + "loss": 0.0499, + "step": 8767 + }, + { + "epoch": 7.76, + "learning_rate": 1.3999264253545777e-05, + "loss": 0.0498, + "step": 8768 + }, + { + "epoch": 7.76, + "learning_rate": 1.3997950729181456e-05, + "loss": 0.0476, + "step": 8769 + }, + { + "epoch": 7.76, + "learning_rate": 1.3996637122710768e-05, + "loss": 0.0545, + "step": 8770 + }, + { + "epoch": 7.76, + "learning_rate": 1.399532343416069e-05, + "loss": 0.0522, + "step": 8771 + }, + { + "epoch": 7.76, + "learning_rate": 1.3994009663558204e-05, + "loss": 0.0535, + "step": 8772 + }, + { + "epoch": 7.76, + "learning_rate": 1.3992695810930288e-05, + "loss": 0.0487, + "step": 8773 + }, + { + "epoch": 7.76, + "learning_rate": 1.3991381876303925e-05, + "loss": 0.0444, + "step": 8774 + }, + { + "epoch": 7.76, + "learning_rate": 1.39900678597061e-05, + "loss": 0.0513, + "step": 8775 + }, + { + "epoch": 7.76, + "learning_rate": 1.3988753761163802e-05, + "loss": 0.0477, + "step": 8776 + }, + { + "epoch": 7.77, + "learning_rate": 1.398743958070402e-05, + "loss": 0.0525, + "step": 8777 + }, + { + "epoch": 7.77, + "learning_rate": 1.3986125318353732e-05, + "loss": 0.0483, + "step": 8778 + }, + { + "epoch": 7.77, + "learning_rate": 1.3984810974139939e-05, + "loss": 0.0527, + "step": 8779 + }, + { + "epoch": 7.77, + "learning_rate": 1.3983496548089635e-05, + "loss": 0.0564, + "step": 8780 + }, + { + "epoch": 7.77, + "learning_rate": 1.3982182040229808e-05, + "loss": 0.053, + "step": 8781 + }, + { + "epoch": 7.77, + "learning_rate": 1.3980867450587459e-05, + "loss": 0.0504, + "step": 8782 + }, + { + "epoch": 7.77, + "learning_rate": 1.3979552779189582e-05, + "loss": 0.0497, + "step": 8783 + }, + { + "epoch": 7.77, + "learning_rate": 1.3978238026063185e-05, + "loss": 0.0507, + "step": 8784 + }, + { + "epoch": 7.77, + "learning_rate": 1.3976923191235258e-05, + "loss": 0.0599, + "step": 8785 + }, + { + "epoch": 7.77, + "learning_rate": 1.397560827473281e-05, + "loss": 0.0482, + "step": 8786 + }, + { + "epoch": 7.77, + "learning_rate": 1.3974293276582844e-05, + "loss": 0.0561, + "step": 8787 + }, + { + "epoch": 7.78, + "learning_rate": 1.3972978196812367e-05, + "loss": 0.0555, + "step": 8788 + }, + { + "epoch": 7.78, + "learning_rate": 1.3971663035448389e-05, + "loss": 0.0533, + "step": 8789 + }, + { + "epoch": 7.78, + "learning_rate": 1.3970347792517916e-05, + "loss": 0.0463, + "step": 8790 + }, + { + "epoch": 7.78, + "learning_rate": 1.3969032468047962e-05, + "loss": 0.0564, + "step": 8791 + }, + { + "epoch": 7.78, + "learning_rate": 1.3967717062065538e-05, + "loss": 0.0584, + "step": 8792 + }, + { + "epoch": 7.78, + "learning_rate": 1.3966401574597656e-05, + "loss": 0.05, + "step": 8793 + }, + { + "epoch": 7.78, + "learning_rate": 1.3965086005671343e-05, + "loss": 0.0487, + "step": 8794 + }, + { + "epoch": 7.78, + "learning_rate": 1.3963770355313604e-05, + "loss": 0.0441, + "step": 8795 + }, + { + "epoch": 7.78, + "learning_rate": 1.3962454623551464e-05, + "loss": 0.0567, + "step": 8796 + }, + { + "epoch": 7.78, + "learning_rate": 1.3961138810411947e-05, + "loss": 0.0571, + "step": 8797 + }, + { + "epoch": 7.78, + "learning_rate": 1.3959822915922074e-05, + "loss": 0.0565, + "step": 8798 + }, + { + "epoch": 7.79, + "learning_rate": 1.395850694010887e-05, + "loss": 0.0561, + "step": 8799 + }, + { + "epoch": 7.79, + "learning_rate": 1.3957190882999357e-05, + "loss": 0.0554, + "step": 8800 + }, + { + "epoch": 7.79, + "learning_rate": 1.395587474462057e-05, + "loss": 0.0457, + "step": 8801 + }, + { + "epoch": 7.79, + "learning_rate": 1.3954558524999535e-05, + "loss": 0.0505, + "step": 8802 + }, + { + "epoch": 7.79, + "learning_rate": 1.3953242224163282e-05, + "loss": 0.0493, + "step": 8803 + }, + { + "epoch": 7.79, + "learning_rate": 1.3951925842138846e-05, + "loss": 0.0529, + "step": 8804 + }, + { + "epoch": 7.79, + "learning_rate": 1.3950609378953263e-05, + "loss": 0.0537, + "step": 8805 + }, + { + "epoch": 7.79, + "learning_rate": 1.3949292834633568e-05, + "loss": 0.0497, + "step": 8806 + }, + { + "epoch": 7.79, + "learning_rate": 1.3947976209206794e-05, + "loss": 0.0522, + "step": 8807 + }, + { + "epoch": 7.79, + "learning_rate": 1.3946659502699993e-05, + "loss": 0.0551, + "step": 8808 + }, + { + "epoch": 7.79, + "learning_rate": 1.3945342715140195e-05, + "loss": 0.0528, + "step": 8809 + }, + { + "epoch": 7.79, + "learning_rate": 1.3944025846554447e-05, + "loss": 0.0491, + "step": 8810 + }, + { + "epoch": 7.8, + "learning_rate": 1.3942708896969795e-05, + "loss": 0.0537, + "step": 8811 + }, + { + "epoch": 7.8, + "learning_rate": 1.3941391866413283e-05, + "loss": 0.051, + "step": 8812 + }, + { + "epoch": 7.8, + "learning_rate": 1.3940074754911956e-05, + "loss": 0.0503, + "step": 8813 + }, + { + "epoch": 7.8, + "learning_rate": 1.3938757562492873e-05, + "loss": 0.0562, + "step": 8814 + }, + { + "epoch": 7.8, + "learning_rate": 1.393744028918308e-05, + "loss": 0.0465, + "step": 8815 + }, + { + "epoch": 7.8, + "learning_rate": 1.3936122935009628e-05, + "loss": 0.0578, + "step": 8816 + }, + { + "epoch": 7.8, + "learning_rate": 1.3934805499999572e-05, + "loss": 0.056, + "step": 8817 + }, + { + "epoch": 7.8, + "learning_rate": 1.3933487984179973e-05, + "loss": 0.0574, + "step": 8818 + }, + { + "epoch": 7.8, + "learning_rate": 1.3932170387577882e-05, + "loss": 0.0468, + "step": 8819 + }, + { + "epoch": 7.8, + "learning_rate": 1.3930852710220366e-05, + "loss": 0.0512, + "step": 8820 + }, + { + "epoch": 7.8, + "learning_rate": 1.392953495213448e-05, + "loss": 0.0545, + "step": 8821 + }, + { + "epoch": 7.81, + "learning_rate": 1.3928217113347292e-05, + "loss": 0.0473, + "step": 8822 + }, + { + "epoch": 7.81, + "learning_rate": 1.3926899193885865e-05, + "loss": 0.0641, + "step": 8823 + }, + { + "epoch": 7.81, + "learning_rate": 1.3925581193777263e-05, + "loss": 0.0514, + "step": 8824 + }, + { + "epoch": 7.81, + "learning_rate": 1.3924263113048555e-05, + "loss": 0.0545, + "step": 8825 + }, + { + "epoch": 7.81, + "learning_rate": 1.3922944951726811e-05, + "loss": 0.0521, + "step": 8826 + }, + { + "epoch": 7.81, + "learning_rate": 1.3921626709839102e-05, + "loss": 0.0586, + "step": 8827 + }, + { + "epoch": 7.81, + "learning_rate": 1.3920308387412502e-05, + "loss": 0.0481, + "step": 8828 + }, + { + "epoch": 7.81, + "learning_rate": 1.3918989984474087e-05, + "loss": 0.0448, + "step": 8829 + }, + { + "epoch": 7.81, + "learning_rate": 1.3917671501050927e-05, + "loss": 0.0501, + "step": 8830 + }, + { + "epoch": 7.81, + "learning_rate": 1.3916352937170106e-05, + "loss": 0.0457, + "step": 8831 + }, + { + "epoch": 7.81, + "learning_rate": 1.3915034292858698e-05, + "loss": 0.0513, + "step": 8832 + }, + { + "epoch": 7.82, + "learning_rate": 1.3913715568143791e-05, + "loss": 0.0566, + "step": 8833 + }, + { + "epoch": 7.82, + "learning_rate": 1.3912396763052463e-05, + "loss": 0.0524, + "step": 8834 + }, + { + "epoch": 7.82, + "learning_rate": 1.39110778776118e-05, + "loss": 0.0529, + "step": 8835 + }, + { + "epoch": 7.82, + "learning_rate": 1.390975891184889e-05, + "loss": 0.0534, + "step": 8836 + }, + { + "epoch": 7.82, + "learning_rate": 1.3908439865790814e-05, + "loss": 0.0521, + "step": 8837 + }, + { + "epoch": 7.82, + "learning_rate": 1.390712073946467e-05, + "loss": 0.0579, + "step": 8838 + }, + { + "epoch": 7.82, + "learning_rate": 1.3905801532897539e-05, + "loss": 0.0469, + "step": 8839 + }, + { + "epoch": 7.82, + "learning_rate": 1.3904482246116527e-05, + "loss": 0.0486, + "step": 8840 + }, + { + "epoch": 7.82, + "learning_rate": 1.3903162879148715e-05, + "loss": 0.0499, + "step": 8841 + }, + { + "epoch": 7.82, + "learning_rate": 1.3901843432021207e-05, + "loss": 0.0514, + "step": 8842 + }, + { + "epoch": 7.82, + "learning_rate": 1.3900523904761099e-05, + "loss": 0.0566, + "step": 8843 + }, + { + "epoch": 7.83, + "learning_rate": 1.3899204297395492e-05, + "loss": 0.0514, + "step": 8844 + }, + { + "epoch": 7.83, + "learning_rate": 1.389788460995148e-05, + "loss": 0.054, + "step": 8845 + }, + { + "epoch": 7.83, + "learning_rate": 1.3896564842456172e-05, + "loss": 0.058, + "step": 8846 + }, + { + "epoch": 7.83, + "learning_rate": 1.3895244994936674e-05, + "loss": 0.0552, + "step": 8847 + }, + { + "epoch": 7.83, + "learning_rate": 1.3893925067420086e-05, + "loss": 0.0542, + "step": 8848 + }, + { + "epoch": 7.83, + "learning_rate": 1.3892605059933517e-05, + "loss": 0.0507, + "step": 8849 + }, + { + "epoch": 7.83, + "learning_rate": 1.3891284972504078e-05, + "loss": 0.0527, + "step": 8850 + }, + { + "epoch": 7.83, + "learning_rate": 1.388996480515888e-05, + "loss": 0.0571, + "step": 8851 + }, + { + "epoch": 7.83, + "learning_rate": 1.388864455792503e-05, + "loss": 0.0588, + "step": 8852 + }, + { + "epoch": 7.83, + "learning_rate": 1.388732423082965e-05, + "loss": 0.0509, + "step": 8853 + }, + { + "epoch": 7.83, + "learning_rate": 1.3886003823899854e-05, + "loss": 0.0568, + "step": 8854 + }, + { + "epoch": 7.83, + "learning_rate": 1.3884683337162755e-05, + "loss": 0.0509, + "step": 8855 + }, + { + "epoch": 7.84, + "learning_rate": 1.3883362770645474e-05, + "loss": 0.0519, + "step": 8856 + }, + { + "epoch": 7.84, + "learning_rate": 1.3882042124375133e-05, + "loss": 0.051, + "step": 8857 + }, + { + "epoch": 7.84, + "learning_rate": 1.3880721398378851e-05, + "loss": 0.0482, + "step": 8858 + }, + { + "epoch": 7.84, + "learning_rate": 1.3879400592683756e-05, + "loss": 0.0509, + "step": 8859 + }, + { + "epoch": 7.84, + "learning_rate": 1.3878079707316971e-05, + "loss": 0.0523, + "step": 8860 + }, + { + "epoch": 7.84, + "learning_rate": 1.3876758742305625e-05, + "loss": 0.0533, + "step": 8861 + }, + { + "epoch": 7.84, + "learning_rate": 1.3875437697676846e-05, + "loss": 0.0587, + "step": 8862 + }, + { + "epoch": 7.84, + "learning_rate": 1.3874116573457763e-05, + "loss": 0.0529, + "step": 8863 + }, + { + "epoch": 7.84, + "learning_rate": 1.3872795369675509e-05, + "loss": 0.0545, + "step": 8864 + }, + { + "epoch": 7.84, + "learning_rate": 1.387147408635722e-05, + "loss": 0.0622, + "step": 8865 + }, + { + "epoch": 7.84, + "learning_rate": 1.3870152723530026e-05, + "loss": 0.0553, + "step": 8866 + }, + { + "epoch": 7.85, + "learning_rate": 1.386883128122107e-05, + "loss": 0.0598, + "step": 8867 + }, + { + "epoch": 7.85, + "learning_rate": 1.3867509759457488e-05, + "loss": 0.0604, + "step": 8868 + }, + { + "epoch": 7.85, + "learning_rate": 1.3866188158266419e-05, + "loss": 0.0506, + "step": 8869 + }, + { + "epoch": 7.85, + "learning_rate": 1.3864866477675003e-05, + "loss": 0.063, + "step": 8870 + }, + { + "epoch": 7.85, + "learning_rate": 1.386354471771039e-05, + "loss": 0.0513, + "step": 8871 + }, + { + "epoch": 7.85, + "learning_rate": 1.386222287839972e-05, + "loss": 0.0551, + "step": 8872 + }, + { + "epoch": 7.85, + "learning_rate": 1.3860900959770142e-05, + "loss": 0.052, + "step": 8873 + }, + { + "epoch": 7.85, + "learning_rate": 1.3859578961848805e-05, + "loss": 0.0567, + "step": 8874 + }, + { + "epoch": 7.85, + "learning_rate": 1.3858256884662859e-05, + "loss": 0.055, + "step": 8875 + }, + { + "epoch": 7.85, + "learning_rate": 1.3856934728239452e-05, + "loss": 0.0648, + "step": 8876 + }, + { + "epoch": 7.85, + "learning_rate": 1.3855612492605739e-05, + "loss": 0.046, + "step": 8877 + }, + { + "epoch": 7.86, + "learning_rate": 1.3854290177788876e-05, + "loss": 0.0541, + "step": 8878 + }, + { + "epoch": 7.86, + "learning_rate": 1.385296778381602e-05, + "loss": 0.0529, + "step": 8879 + }, + { + "epoch": 7.86, + "learning_rate": 1.3851645310714327e-05, + "loss": 0.0564, + "step": 8880 + }, + { + "epoch": 7.86, + "learning_rate": 1.385032275851096e-05, + "loss": 0.0541, + "step": 8881 + }, + { + "epoch": 7.86, + "learning_rate": 1.384900012723308e-05, + "loss": 0.0586, + "step": 8882 + }, + { + "epoch": 7.86, + "learning_rate": 1.3847677416907845e-05, + "loss": 0.0571, + "step": 8883 + }, + { + "epoch": 7.86, + "learning_rate": 1.3846354627562426e-05, + "loss": 0.0519, + "step": 8884 + }, + { + "epoch": 7.86, + "learning_rate": 1.3845031759223983e-05, + "loss": 0.0529, + "step": 8885 + }, + { + "epoch": 7.86, + "learning_rate": 1.3843708811919689e-05, + "loss": 0.0608, + "step": 8886 + }, + { + "epoch": 7.86, + "learning_rate": 1.3842385785676713e-05, + "loss": 0.0549, + "step": 8887 + }, + { + "epoch": 7.86, + "learning_rate": 1.3841062680522224e-05, + "loss": 0.0515, + "step": 8888 + }, + { + "epoch": 7.86, + "learning_rate": 1.3839739496483397e-05, + "loss": 0.0562, + "step": 8889 + }, + { + "epoch": 7.87, + "learning_rate": 1.3838416233587404e-05, + "loss": 0.0519, + "step": 8890 + }, + { + "epoch": 7.87, + "learning_rate": 1.3837092891861419e-05, + "loss": 0.0597, + "step": 8891 + }, + { + "epoch": 7.87, + "learning_rate": 1.3835769471332628e-05, + "loss": 0.056, + "step": 8892 + }, + { + "epoch": 7.87, + "learning_rate": 1.3834445972028202e-05, + "loss": 0.0554, + "step": 8893 + }, + { + "epoch": 7.87, + "learning_rate": 1.3833122393975327e-05, + "loss": 0.0568, + "step": 8894 + }, + { + "epoch": 7.87, + "learning_rate": 1.3831798737201182e-05, + "loss": 0.059, + "step": 8895 + }, + { + "epoch": 7.87, + "learning_rate": 1.3830475001732952e-05, + "loss": 0.0575, + "step": 8896 + }, + { + "epoch": 7.87, + "learning_rate": 1.3829151187597825e-05, + "loss": 0.0541, + "step": 8897 + }, + { + "epoch": 7.87, + "learning_rate": 1.3827827294822984e-05, + "loss": 0.0509, + "step": 8898 + }, + { + "epoch": 7.87, + "learning_rate": 1.3826503323435623e-05, + "loss": 0.0586, + "step": 8899 + }, + { + "epoch": 7.87, + "learning_rate": 1.3825179273462927e-05, + "loss": 0.0541, + "step": 8900 + }, + { + "epoch": 7.88, + "learning_rate": 1.3823855144932093e-05, + "loss": 0.0528, + "step": 8901 + }, + { + "epoch": 7.88, + "learning_rate": 1.3822530937870311e-05, + "loss": 0.0528, + "step": 8902 + }, + { + "epoch": 7.88, + "learning_rate": 1.3821206652304781e-05, + "loss": 0.0659, + "step": 8903 + }, + { + "epoch": 7.88, + "learning_rate": 1.3819882288262693e-05, + "loss": 0.0521, + "step": 8904 + }, + { + "epoch": 7.88, + "learning_rate": 1.3818557845771254e-05, + "loss": 0.059, + "step": 8905 + }, + { + "epoch": 7.88, + "learning_rate": 1.381723332485766e-05, + "loss": 0.0567, + "step": 8906 + }, + { + "epoch": 7.88, + "learning_rate": 1.3815908725549111e-05, + "loss": 0.0616, + "step": 8907 + }, + { + "epoch": 7.88, + "learning_rate": 1.3814584047872814e-05, + "loss": 0.0529, + "step": 8908 + }, + { + "epoch": 7.88, + "learning_rate": 1.3813259291855971e-05, + "loss": 0.0523, + "step": 8909 + }, + { + "epoch": 7.88, + "learning_rate": 1.3811934457525794e-05, + "loss": 0.0564, + "step": 8910 + }, + { + "epoch": 7.88, + "learning_rate": 1.3810609544909479e-05, + "loss": 0.0501, + "step": 8911 + }, + { + "epoch": 7.89, + "learning_rate": 1.380928455403425e-05, + "loss": 0.0567, + "step": 8912 + }, + { + "epoch": 7.89, + "learning_rate": 1.3807959484927313e-05, + "loss": 0.0608, + "step": 8913 + }, + { + "epoch": 7.89, + "learning_rate": 1.3806634337615881e-05, + "loss": 0.0485, + "step": 8914 + }, + { + "epoch": 7.89, + "learning_rate": 1.3805309112127168e-05, + "loss": 0.0535, + "step": 8915 + }, + { + "epoch": 7.89, + "learning_rate": 1.3803983808488388e-05, + "loss": 0.0492, + "step": 8916 + }, + { + "epoch": 7.89, + "learning_rate": 1.3802658426726765e-05, + "loss": 0.0615, + "step": 8917 + }, + { + "epoch": 7.89, + "learning_rate": 1.3801332966869514e-05, + "loss": 0.0486, + "step": 8918 + }, + { + "epoch": 7.89, + "learning_rate": 1.3800007428943855e-05, + "loss": 0.0535, + "step": 8919 + }, + { + "epoch": 7.89, + "learning_rate": 1.3798681812977019e-05, + "loss": 0.0542, + "step": 8920 + }, + { + "epoch": 7.89, + "learning_rate": 1.379735611899622e-05, + "loss": 0.0585, + "step": 8921 + }, + { + "epoch": 7.89, + "learning_rate": 1.379603034702869e-05, + "loss": 0.0528, + "step": 8922 + }, + { + "epoch": 7.89, + "learning_rate": 1.3794704497101656e-05, + "loss": 0.0558, + "step": 8923 + }, + { + "epoch": 7.9, + "learning_rate": 1.3793378569242343e-05, + "loss": 0.065, + "step": 8924 + }, + { + "epoch": 7.9, + "learning_rate": 1.3792052563477987e-05, + "loss": 0.052, + "step": 8925 + }, + { + "epoch": 7.9, + "learning_rate": 1.3790726479835816e-05, + "loss": 0.0566, + "step": 8926 + }, + { + "epoch": 7.9, + "learning_rate": 1.378940031834307e-05, + "loss": 0.0497, + "step": 8927 + }, + { + "epoch": 7.9, + "learning_rate": 1.3788074079026976e-05, + "loss": 0.0591, + "step": 8928 + }, + { + "epoch": 7.9, + "learning_rate": 1.3786747761914779e-05, + "loss": 0.0566, + "step": 8929 + }, + { + "epoch": 7.9, + "learning_rate": 1.3785421367033714e-05, + "loss": 0.05, + "step": 8930 + }, + { + "epoch": 7.9, + "learning_rate": 1.378409489441102e-05, + "loss": 0.053, + "step": 8931 + }, + { + "epoch": 7.9, + "learning_rate": 1.378276834407394e-05, + "loss": 0.0472, + "step": 8932 + }, + { + "epoch": 7.9, + "learning_rate": 1.378144171604972e-05, + "loss": 0.0587, + "step": 8933 + }, + { + "epoch": 7.9, + "learning_rate": 1.3780115010365603e-05, + "loss": 0.0523, + "step": 8934 + }, + { + "epoch": 7.91, + "learning_rate": 1.3778788227048836e-05, + "loss": 0.0572, + "step": 8935 + }, + { + "epoch": 7.91, + "learning_rate": 1.3777461366126667e-05, + "loss": 0.0494, + "step": 8936 + }, + { + "epoch": 7.91, + "learning_rate": 1.3776134427626345e-05, + "loss": 0.0558, + "step": 8937 + }, + { + "epoch": 7.91, + "learning_rate": 1.3774807411575123e-05, + "loss": 0.056, + "step": 8938 + }, + { + "epoch": 7.91, + "learning_rate": 1.3773480318000254e-05, + "loss": 0.0542, + "step": 8939 + }, + { + "epoch": 7.91, + "learning_rate": 1.3772153146928995e-05, + "loss": 0.0513, + "step": 8940 + }, + { + "epoch": 7.91, + "learning_rate": 1.3770825898388598e-05, + "loss": 0.0611, + "step": 8941 + }, + { + "epoch": 7.91, + "learning_rate": 1.3769498572406321e-05, + "loss": 0.0519, + "step": 8942 + }, + { + "epoch": 7.91, + "learning_rate": 1.3768171169009423e-05, + "loss": 0.0561, + "step": 8943 + }, + { + "epoch": 7.91, + "learning_rate": 1.3766843688225174e-05, + "loss": 0.049, + "step": 8944 + }, + { + "epoch": 7.91, + "learning_rate": 1.3765516130080824e-05, + "loss": 0.0555, + "step": 8945 + }, + { + "epoch": 7.92, + "learning_rate": 1.3764188494603646e-05, + "loss": 0.0475, + "step": 8946 + }, + { + "epoch": 7.92, + "learning_rate": 1.37628607818209e-05, + "loss": 0.0517, + "step": 8947 + }, + { + "epoch": 7.92, + "learning_rate": 1.3761532991759859e-05, + "loss": 0.0542, + "step": 8948 + }, + { + "epoch": 7.92, + "learning_rate": 1.3760205124447788e-05, + "loss": 0.0549, + "step": 8949 + }, + { + "epoch": 7.92, + "learning_rate": 1.3758877179911953e-05, + "loss": 0.055, + "step": 8950 + }, + { + "epoch": 7.92, + "learning_rate": 1.375754915817964e-05, + "loss": 0.0516, + "step": 8951 + }, + { + "epoch": 7.92, + "learning_rate": 1.375622105927811e-05, + "loss": 0.0613, + "step": 8952 + }, + { + "epoch": 7.92, + "learning_rate": 1.3754892883234643e-05, + "loss": 0.0593, + "step": 8953 + }, + { + "epoch": 7.92, + "learning_rate": 1.3753564630076515e-05, + "loss": 0.0475, + "step": 8954 + }, + { + "epoch": 7.92, + "learning_rate": 1.3752236299831007e-05, + "loss": 0.0575, + "step": 8955 + }, + { + "epoch": 7.92, + "learning_rate": 1.3750907892525396e-05, + "loss": 0.0625, + "step": 8956 + }, + { + "epoch": 7.93, + "learning_rate": 1.3749579408186963e-05, + "loss": 0.0486, + "step": 8957 + }, + { + "epoch": 7.93, + "learning_rate": 1.3748250846842997e-05, + "loss": 0.047, + "step": 8958 + }, + { + "epoch": 7.93, + "learning_rate": 1.374692220852078e-05, + "loss": 0.0541, + "step": 8959 + }, + { + "epoch": 7.93, + "learning_rate": 1.3745593493247594e-05, + "loss": 0.0534, + "step": 8960 + }, + { + "epoch": 7.93, + "learning_rate": 1.3744264701050728e-05, + "loss": 0.0572, + "step": 8961 + }, + { + "epoch": 7.93, + "learning_rate": 1.374293583195748e-05, + "loss": 0.0612, + "step": 8962 + }, + { + "epoch": 7.93, + "learning_rate": 1.3741606885995128e-05, + "loss": 0.0522, + "step": 8963 + }, + { + "epoch": 7.93, + "learning_rate": 1.3740277863190977e-05, + "loss": 0.0534, + "step": 8964 + }, + { + "epoch": 7.93, + "learning_rate": 1.3738948763572312e-05, + "loss": 0.0582, + "step": 8965 + }, + { + "epoch": 7.93, + "learning_rate": 1.3737619587166438e-05, + "loss": 0.0488, + "step": 8966 + }, + { + "epoch": 7.93, + "learning_rate": 1.3736290334000643e-05, + "loss": 0.0583, + "step": 8967 + }, + { + "epoch": 7.93, + "learning_rate": 1.3734961004102231e-05, + "loss": 0.0571, + "step": 8968 + }, + { + "epoch": 7.94, + "learning_rate": 1.3733631597498503e-05, + "loss": 0.063, + "step": 8969 + }, + { + "epoch": 7.94, + "learning_rate": 1.373230211421676e-05, + "loss": 0.0542, + "step": 8970 + }, + { + "epoch": 7.94, + "learning_rate": 1.3730972554284305e-05, + "loss": 0.051, + "step": 8971 + }, + { + "epoch": 7.94, + "learning_rate": 1.3729642917728444e-05, + "loss": 0.0644, + "step": 8972 + }, + { + "epoch": 7.94, + "learning_rate": 1.3728313204576486e-05, + "loss": 0.0525, + "step": 8973 + }, + { + "epoch": 7.94, + "learning_rate": 1.3726983414855737e-05, + "loss": 0.0554, + "step": 8974 + }, + { + "epoch": 7.94, + "learning_rate": 1.3725653548593507e-05, + "loss": 0.0566, + "step": 8975 + }, + { + "epoch": 7.94, + "learning_rate": 1.3724323605817106e-05, + "loss": 0.0537, + "step": 8976 + }, + { + "epoch": 7.94, + "learning_rate": 1.3722993586553853e-05, + "loss": 0.0533, + "step": 8977 + }, + { + "epoch": 7.94, + "learning_rate": 1.3721663490831056e-05, + "loss": 0.0588, + "step": 8978 + }, + { + "epoch": 7.94, + "learning_rate": 1.3720333318676036e-05, + "loss": 0.0504, + "step": 8979 + }, + { + "epoch": 7.95, + "learning_rate": 1.371900307011611e-05, + "loss": 0.0566, + "step": 8980 + }, + { + "epoch": 7.95, + "learning_rate": 1.3717672745178597e-05, + "loss": 0.0554, + "step": 8981 + }, + { + "epoch": 7.95, + "learning_rate": 1.3716342343890814e-05, + "loss": 0.0566, + "step": 8982 + }, + { + "epoch": 7.95, + "learning_rate": 1.3715011866280092e-05, + "loss": 0.0654, + "step": 8983 + }, + { + "epoch": 7.95, + "learning_rate": 1.3713681312373747e-05, + "loss": 0.0518, + "step": 8984 + }, + { + "epoch": 7.95, + "learning_rate": 1.3712350682199112e-05, + "loss": 0.0616, + "step": 8985 + }, + { + "epoch": 7.95, + "learning_rate": 1.3711019975783509e-05, + "loss": 0.0573, + "step": 8986 + }, + { + "epoch": 7.95, + "learning_rate": 1.370968919315427e-05, + "loss": 0.0537, + "step": 8987 + }, + { + "epoch": 7.95, + "learning_rate": 1.3708358334338723e-05, + "loss": 0.0511, + "step": 8988 + }, + { + "epoch": 7.95, + "learning_rate": 1.3707027399364196e-05, + "loss": 0.0641, + "step": 8989 + }, + { + "epoch": 7.95, + "learning_rate": 1.3705696388258033e-05, + "loss": 0.0563, + "step": 8990 + }, + { + "epoch": 7.96, + "learning_rate": 1.3704365301047564e-05, + "loss": 0.055, + "step": 8991 + }, + { + "epoch": 7.96, + "learning_rate": 1.3703034137760123e-05, + "loss": 0.0571, + "step": 8992 + }, + { + "epoch": 7.96, + "learning_rate": 1.3701702898423051e-05, + "loss": 0.0521, + "step": 8993 + }, + { + "epoch": 7.96, + "learning_rate": 1.370037158306369e-05, + "loss": 0.0592, + "step": 8994 + }, + { + "epoch": 7.96, + "learning_rate": 1.3699040191709373e-05, + "loss": 0.0438, + "step": 8995 + }, + { + "epoch": 7.96, + "learning_rate": 1.3697708724387453e-05, + "loss": 0.0506, + "step": 8996 + }, + { + "epoch": 7.96, + "learning_rate": 1.369637718112527e-05, + "loss": 0.053, + "step": 8997 + }, + { + "epoch": 7.96, + "learning_rate": 1.3695045561950172e-05, + "loss": 0.0626, + "step": 8998 + }, + { + "epoch": 7.96, + "learning_rate": 1.36937138668895e-05, + "loss": 0.0542, + "step": 8999 + }, + { + "epoch": 7.96, + "learning_rate": 1.369238209597061e-05, + "loss": 0.0559, + "step": 9000 + }, + { + "epoch": 7.96, + "learning_rate": 1.3691050249220854e-05, + "loss": 0.0511, + "step": 9001 + }, + { + "epoch": 7.96, + "learning_rate": 1.3689718326667576e-05, + "loss": 0.0569, + "step": 9002 + }, + { + "epoch": 7.97, + "learning_rate": 1.3688386328338137e-05, + "loss": 0.0537, + "step": 9003 + }, + { + "epoch": 7.97, + "learning_rate": 1.3687054254259891e-05, + "loss": 0.0536, + "step": 9004 + }, + { + "epoch": 7.97, + "learning_rate": 1.3685722104460195e-05, + "loss": 0.0585, + "step": 9005 + }, + { + "epoch": 7.97, + "learning_rate": 1.3684389878966405e-05, + "loss": 0.0558, + "step": 9006 + }, + { + "epoch": 7.97, + "learning_rate": 1.3683057577805883e-05, + "loss": 0.0596, + "step": 9007 + }, + { + "epoch": 7.97, + "learning_rate": 1.368172520100599e-05, + "loss": 0.0574, + "step": 9008 + }, + { + "epoch": 7.97, + "learning_rate": 1.3680392748594092e-05, + "loss": 0.0543, + "step": 9009 + }, + { + "epoch": 7.97, + "learning_rate": 1.3679060220597549e-05, + "loss": 0.0575, + "step": 9010 + }, + { + "epoch": 7.97, + "learning_rate": 1.367772761704373e-05, + "loss": 0.0537, + "step": 9011 + }, + { + "epoch": 7.97, + "learning_rate": 1.3676394937960003e-05, + "loss": 0.048, + "step": 9012 + }, + { + "epoch": 7.97, + "learning_rate": 1.3675062183373737e-05, + "loss": 0.0534, + "step": 9013 + }, + { + "epoch": 7.98, + "learning_rate": 1.3673729353312301e-05, + "loss": 0.0446, + "step": 9014 + }, + { + "epoch": 7.98, + "learning_rate": 1.3672396447803072e-05, + "loss": 0.0547, + "step": 9015 + }, + { + "epoch": 7.98, + "learning_rate": 1.367106346687342e-05, + "loss": 0.0588, + "step": 9016 + }, + { + "epoch": 7.98, + "learning_rate": 1.3669730410550721e-05, + "loss": 0.053, + "step": 9017 + }, + { + "epoch": 7.98, + "learning_rate": 1.3668397278862355e-05, + "loss": 0.0576, + "step": 9018 + }, + { + "epoch": 7.98, + "learning_rate": 1.3667064071835699e-05, + "loss": 0.0588, + "step": 9019 + }, + { + "epoch": 7.98, + "learning_rate": 1.366573078949813e-05, + "loss": 0.0578, + "step": 9020 + }, + { + "epoch": 7.98, + "learning_rate": 1.3664397431877034e-05, + "loss": 0.0476, + "step": 9021 + }, + { + "epoch": 7.98, + "learning_rate": 1.3663063998999793e-05, + "loss": 0.0498, + "step": 9022 + }, + { + "epoch": 7.98, + "learning_rate": 1.3661730490893793e-05, + "loss": 0.0603, + "step": 9023 + }, + { + "epoch": 7.98, + "learning_rate": 1.3660396907586417e-05, + "loss": 0.0553, + "step": 9024 + }, + { + "epoch": 7.99, + "learning_rate": 1.3659063249105058e-05, + "loss": 0.0515, + "step": 9025 + }, + { + "epoch": 7.99, + "learning_rate": 1.36577295154771e-05, + "loss": 0.0547, + "step": 9026 + }, + { + "epoch": 7.99, + "learning_rate": 1.3656395706729937e-05, + "loss": 0.0504, + "step": 9027 + }, + { + "epoch": 7.99, + "learning_rate": 1.3655061822890962e-05, + "loss": 0.0559, + "step": 9028 + }, + { + "epoch": 7.99, + "learning_rate": 1.3653727863987569e-05, + "loss": 0.0526, + "step": 9029 + }, + { + "epoch": 7.99, + "learning_rate": 1.3652393830047152e-05, + "loss": 0.0547, + "step": 9030 + }, + { + "epoch": 7.99, + "learning_rate": 1.3651059721097108e-05, + "loss": 0.0585, + "step": 9031 + }, + { + "epoch": 7.99, + "learning_rate": 1.3649725537164842e-05, + "loss": 0.0575, + "step": 9032 + }, + { + "epoch": 7.99, + "learning_rate": 1.3648391278277747e-05, + "loss": 0.0561, + "step": 9033 + }, + { + "epoch": 7.99, + "learning_rate": 1.3647056944463227e-05, + "loss": 0.0555, + "step": 9034 + }, + { + "epoch": 7.99, + "learning_rate": 1.3645722535748682e-05, + "loss": 0.0587, + "step": 9035 + }, + { + "epoch": 7.99, + "learning_rate": 1.3644388052161524e-05, + "loss": 0.0581, + "step": 9036 + }, + { + "epoch": 8.0, + "learning_rate": 1.3643053493729155e-05, + "loss": 0.0681, + "step": 9037 + }, + { + "epoch": 8.0, + "learning_rate": 1.3641718860478985e-05, + "loss": 0.0532, + "step": 9038 + }, + { + "epoch": 8.0, + "learning_rate": 1.3640384152438424e-05, + "loss": 0.0561, + "step": 9039 + }, + { + "epoch": 8.0, + "learning_rate": 1.3639049369634878e-05, + "loss": 0.0538, + "step": 9040 + }, + { + "epoch": 8.0, + "learning_rate": 1.363771451209576e-05, + "loss": 0.0568, + "step": 9041 + }, + { + "epoch": 8.0, + "learning_rate": 1.3636379579848493e-05, + "loss": 0.0476, + "step": 9042 + }, + { + "epoch": 8.0, + "learning_rate": 1.3635044572920486e-05, + "loss": 0.0354, + "step": 9043 + }, + { + "epoch": 8.0, + "learning_rate": 1.3633709491339155e-05, + "loss": 0.0285, + "step": 9044 + }, + { + "epoch": 8.0, + "learning_rate": 1.3632374335131922e-05, + "loss": 0.0261, + "step": 9045 + }, + { + "epoch": 8.0, + "learning_rate": 1.3631039104326208e-05, + "loss": 0.0246, + "step": 9046 + }, + { + "epoch": 8.0, + "learning_rate": 1.3629703798949429e-05, + "loss": 0.0276, + "step": 9047 + }, + { + "epoch": 8.01, + "learning_rate": 1.362836841902901e-05, + "loss": 0.033, + "step": 9048 + }, + { + "epoch": 8.01, + "learning_rate": 1.3627032964592383e-05, + "loss": 0.03, + "step": 9049 + }, + { + "epoch": 8.01, + "learning_rate": 1.3625697435666967e-05, + "loss": 0.024, + "step": 9050 + }, + { + "epoch": 8.01, + "learning_rate": 1.3624361832280193e-05, + "loss": 0.0279, + "step": 9051 + }, + { + "epoch": 8.01, + "learning_rate": 1.362302615445949e-05, + "loss": 0.0286, + "step": 9052 + }, + { + "epoch": 8.01, + "learning_rate": 1.3621690402232289e-05, + "loss": 0.0333, + "step": 9053 + }, + { + "epoch": 8.01, + "learning_rate": 1.3620354575626018e-05, + "loss": 0.0259, + "step": 9054 + }, + { + "epoch": 8.01, + "learning_rate": 1.3619018674668118e-05, + "loss": 0.0298, + "step": 9055 + }, + { + "epoch": 8.01, + "learning_rate": 1.3617682699386024e-05, + "loss": 0.0266, + "step": 9056 + }, + { + "epoch": 8.01, + "learning_rate": 1.3616346649807168e-05, + "loss": 0.0224, + "step": 9057 + }, + { + "epoch": 8.01, + "learning_rate": 1.3615010525958991e-05, + "loss": 0.0231, + "step": 9058 + }, + { + "epoch": 8.02, + "learning_rate": 1.3613674327868932e-05, + "loss": 0.0262, + "step": 9059 + }, + { + "epoch": 8.02, + "learning_rate": 1.361233805556444e-05, + "loss": 0.0301, + "step": 9060 + }, + { + "epoch": 8.02, + "learning_rate": 1.3611001709072946e-05, + "loss": 0.0298, + "step": 9061 + }, + { + "epoch": 8.02, + "learning_rate": 1.3609665288421903e-05, + "loss": 0.0293, + "step": 9062 + }, + { + "epoch": 8.02, + "learning_rate": 1.3608328793638758e-05, + "loss": 0.0255, + "step": 9063 + }, + { + "epoch": 8.02, + "learning_rate": 1.3606992224750952e-05, + "loss": 0.0246, + "step": 9064 + }, + { + "epoch": 8.02, + "learning_rate": 1.3605655581785941e-05, + "loss": 0.0258, + "step": 9065 + }, + { + "epoch": 8.02, + "learning_rate": 1.3604318864771171e-05, + "loss": 0.0319, + "step": 9066 + }, + { + "epoch": 8.02, + "learning_rate": 1.3602982073734097e-05, + "loss": 0.0303, + "step": 9067 + }, + { + "epoch": 8.02, + "learning_rate": 1.3601645208702173e-05, + "loss": 0.0298, + "step": 9068 + }, + { + "epoch": 8.02, + "learning_rate": 1.3600308269702854e-05, + "loss": 0.0281, + "step": 9069 + }, + { + "epoch": 8.02, + "learning_rate": 1.3598971256763596e-05, + "loss": 0.0286, + "step": 9070 + }, + { + "epoch": 8.03, + "learning_rate": 1.3597634169911854e-05, + "loss": 0.0275, + "step": 9071 + }, + { + "epoch": 8.03, + "learning_rate": 1.3596297009175097e-05, + "loss": 0.0256, + "step": 9072 + }, + { + "epoch": 8.03, + "learning_rate": 1.3594959774580779e-05, + "loss": 0.0284, + "step": 9073 + }, + { + "epoch": 8.03, + "learning_rate": 1.3593622466156365e-05, + "loss": 0.0295, + "step": 9074 + }, + { + "epoch": 8.03, + "learning_rate": 1.3592285083929318e-05, + "loss": 0.0274, + "step": 9075 + }, + { + "epoch": 8.03, + "learning_rate": 1.3590947627927105e-05, + "loss": 0.0238, + "step": 9076 + }, + { + "epoch": 8.03, + "learning_rate": 1.3589610098177197e-05, + "loss": 0.0249, + "step": 9077 + }, + { + "epoch": 8.03, + "learning_rate": 1.3588272494707057e-05, + "loss": 0.0253, + "step": 9078 + }, + { + "epoch": 8.03, + "learning_rate": 1.3586934817544161e-05, + "loss": 0.0312, + "step": 9079 + }, + { + "epoch": 8.03, + "learning_rate": 1.3585597066715973e-05, + "loss": 0.0244, + "step": 9080 + }, + { + "epoch": 8.03, + "learning_rate": 1.358425924224998e-05, + "loss": 0.0254, + "step": 9081 + }, + { + "epoch": 8.04, + "learning_rate": 1.3582921344173645e-05, + "loss": 0.0326, + "step": 9082 + }, + { + "epoch": 8.04, + "learning_rate": 1.358158337251445e-05, + "loss": 0.0275, + "step": 9083 + }, + { + "epoch": 8.04, + "learning_rate": 1.3580245327299872e-05, + "loss": 0.0257, + "step": 9084 + }, + { + "epoch": 8.04, + "learning_rate": 1.3578907208557388e-05, + "loss": 0.0288, + "step": 9085 + }, + { + "epoch": 8.04, + "learning_rate": 1.3577569016314482e-05, + "loss": 0.0289, + "step": 9086 + }, + { + "epoch": 8.04, + "learning_rate": 1.3576230750598635e-05, + "loss": 0.0371, + "step": 9087 + }, + { + "epoch": 8.04, + "learning_rate": 1.3574892411437334e-05, + "loss": 0.0342, + "step": 9088 + }, + { + "epoch": 8.04, + "learning_rate": 1.3573553998858061e-05, + "loss": 0.0312, + "step": 9089 + }, + { + "epoch": 8.04, + "learning_rate": 1.3572215512888307e-05, + "loss": 0.0335, + "step": 9090 + }, + { + "epoch": 8.04, + "learning_rate": 1.3570876953555558e-05, + "loss": 0.0242, + "step": 9091 + }, + { + "epoch": 8.04, + "learning_rate": 1.3569538320887305e-05, + "loss": 0.0261, + "step": 9092 + }, + { + "epoch": 8.05, + "learning_rate": 1.3568199614911038e-05, + "loss": 0.0288, + "step": 9093 + }, + { + "epoch": 8.05, + "learning_rate": 1.3566860835654252e-05, + "loss": 0.0284, + "step": 9094 + }, + { + "epoch": 8.05, + "learning_rate": 1.356552198314444e-05, + "loss": 0.0322, + "step": 9095 + }, + { + "epoch": 8.05, + "learning_rate": 1.3564183057409101e-05, + "loss": 0.0263, + "step": 9096 + }, + { + "epoch": 8.05, + "learning_rate": 1.356284405847573e-05, + "loss": 0.0291, + "step": 9097 + }, + { + "epoch": 8.05, + "learning_rate": 1.3561504986371827e-05, + "loss": 0.029, + "step": 9098 + }, + { + "epoch": 8.05, + "learning_rate": 1.3560165841124894e-05, + "loss": 0.0323, + "step": 9099 + }, + { + "epoch": 8.05, + "learning_rate": 1.355882662276243e-05, + "loss": 0.0262, + "step": 9100 + }, + { + "epoch": 8.05, + "learning_rate": 1.3557487331311941e-05, + "loss": 0.0265, + "step": 9101 + }, + { + "epoch": 8.05, + "learning_rate": 1.3556147966800935e-05, + "loss": 0.0262, + "step": 9102 + }, + { + "epoch": 8.05, + "learning_rate": 1.355480852925691e-05, + "loss": 0.0279, + "step": 9103 + }, + { + "epoch": 8.06, + "learning_rate": 1.3553469018707385e-05, + "loss": 0.0224, + "step": 9104 + }, + { + "epoch": 8.06, + "learning_rate": 1.3552129435179861e-05, + "loss": 0.0265, + "step": 9105 + }, + { + "epoch": 8.06, + "learning_rate": 1.3550789778701853e-05, + "loss": 0.0237, + "step": 9106 + }, + { + "epoch": 8.06, + "learning_rate": 1.3549450049300875e-05, + "loss": 0.0281, + "step": 9107 + }, + { + "epoch": 8.06, + "learning_rate": 1.3548110247004437e-05, + "loss": 0.0344, + "step": 9108 + }, + { + "epoch": 8.06, + "learning_rate": 1.3546770371840059e-05, + "loss": 0.0275, + "step": 9109 + }, + { + "epoch": 8.06, + "learning_rate": 1.3545430423835257e-05, + "loss": 0.0271, + "step": 9110 + }, + { + "epoch": 8.06, + "learning_rate": 1.3544090403017547e-05, + "loss": 0.0266, + "step": 9111 + }, + { + "epoch": 8.06, + "learning_rate": 1.354275030941445e-05, + "loss": 0.0287, + "step": 9112 + }, + { + "epoch": 8.06, + "learning_rate": 1.354141014305349e-05, + "loss": 0.0263, + "step": 9113 + }, + { + "epoch": 8.06, + "learning_rate": 1.354006990396219e-05, + "loss": 0.0227, + "step": 9114 + }, + { + "epoch": 8.06, + "learning_rate": 1.3538729592168071e-05, + "loss": 0.0262, + "step": 9115 + }, + { + "epoch": 8.07, + "learning_rate": 1.3537389207698665e-05, + "loss": 0.0246, + "step": 9116 + }, + { + "epoch": 8.07, + "learning_rate": 1.3536048750581494e-05, + "loss": 0.0309, + "step": 9117 + }, + { + "epoch": 8.07, + "learning_rate": 1.3534708220844088e-05, + "loss": 0.0239, + "step": 9118 + }, + { + "epoch": 8.07, + "learning_rate": 1.3533367618513981e-05, + "loss": 0.0268, + "step": 9119 + }, + { + "epoch": 8.07, + "learning_rate": 1.3532026943618703e-05, + "loss": 0.0272, + "step": 9120 + }, + { + "epoch": 8.07, + "learning_rate": 1.3530686196185788e-05, + "loss": 0.0286, + "step": 9121 + }, + { + "epoch": 8.07, + "learning_rate": 1.3529345376242771e-05, + "loss": 0.0274, + "step": 9122 + }, + { + "epoch": 8.07, + "learning_rate": 1.3528004483817187e-05, + "loss": 0.0229, + "step": 9123 + }, + { + "epoch": 8.07, + "learning_rate": 1.3526663518936576e-05, + "loss": 0.0309, + "step": 9124 + }, + { + "epoch": 8.07, + "learning_rate": 1.3525322481628478e-05, + "loss": 0.0232, + "step": 9125 + }, + { + "epoch": 8.07, + "learning_rate": 1.3523981371920432e-05, + "loss": 0.0223, + "step": 9126 + }, + { + "epoch": 8.08, + "learning_rate": 1.352264018983998e-05, + "loss": 0.0241, + "step": 9127 + }, + { + "epoch": 8.08, + "learning_rate": 1.3521298935414669e-05, + "loss": 0.0278, + "step": 9128 + }, + { + "epoch": 8.08, + "learning_rate": 1.3519957608672043e-05, + "loss": 0.0254, + "step": 9129 + }, + { + "epoch": 8.08, + "learning_rate": 1.351861620963965e-05, + "loss": 0.0232, + "step": 9130 + }, + { + "epoch": 8.08, + "learning_rate": 1.3517274738345036e-05, + "loss": 0.0256, + "step": 9131 + }, + { + "epoch": 8.08, + "learning_rate": 1.351593319481575e-05, + "loss": 0.0256, + "step": 9132 + }, + { + "epoch": 8.08, + "learning_rate": 1.351459157907935e-05, + "loss": 0.0241, + "step": 9133 + }, + { + "epoch": 8.08, + "learning_rate": 1.3513249891163384e-05, + "loss": 0.0315, + "step": 9134 + }, + { + "epoch": 8.08, + "learning_rate": 1.3511908131095407e-05, + "loss": 0.0282, + "step": 9135 + }, + { + "epoch": 8.08, + "learning_rate": 1.3510566298902975e-05, + "loss": 0.0239, + "step": 9136 + }, + { + "epoch": 8.08, + "learning_rate": 1.3509224394613644e-05, + "loss": 0.0268, + "step": 9137 + }, + { + "epoch": 8.09, + "learning_rate": 1.3507882418254977e-05, + "loss": 0.0251, + "step": 9138 + }, + { + "epoch": 8.09, + "learning_rate": 1.3506540369854525e-05, + "loss": 0.0256, + "step": 9139 + }, + { + "epoch": 8.09, + "learning_rate": 1.3505198249439863e-05, + "loss": 0.0256, + "step": 9140 + }, + { + "epoch": 8.09, + "learning_rate": 1.3503856057038547e-05, + "loss": 0.0303, + "step": 9141 + }, + { + "epoch": 8.09, + "learning_rate": 1.350251379267814e-05, + "loss": 0.0286, + "step": 9142 + }, + { + "epoch": 8.09, + "learning_rate": 1.3501171456386213e-05, + "loss": 0.0312, + "step": 9143 + }, + { + "epoch": 8.09, + "learning_rate": 1.3499829048190332e-05, + "loss": 0.0265, + "step": 9144 + }, + { + "epoch": 8.09, + "learning_rate": 1.349848656811806e-05, + "loss": 0.0267, + "step": 9145 + }, + { + "epoch": 8.09, + "learning_rate": 1.3497144016196976e-05, + "loss": 0.0259, + "step": 9146 + }, + { + "epoch": 8.09, + "learning_rate": 1.3495801392454652e-05, + "loss": 0.027, + "step": 9147 + }, + { + "epoch": 8.09, + "learning_rate": 1.3494458696918656e-05, + "loss": 0.0234, + "step": 9148 + }, + { + "epoch": 8.09, + "learning_rate": 1.3493115929616566e-05, + "loss": 0.0274, + "step": 9149 + }, + { + "epoch": 8.1, + "learning_rate": 1.3491773090575962e-05, + "loss": 0.0277, + "step": 9150 + }, + { + "epoch": 8.1, + "learning_rate": 1.3490430179824416e-05, + "loss": 0.0226, + "step": 9151 + }, + { + "epoch": 8.1, + "learning_rate": 1.3489087197389507e-05, + "loss": 0.0284, + "step": 9152 + }, + { + "epoch": 8.1, + "learning_rate": 1.3487744143298822e-05, + "loss": 0.0264, + "step": 9153 + }, + { + "epoch": 8.1, + "learning_rate": 1.3486401017579945e-05, + "loss": 0.0252, + "step": 9154 + }, + { + "epoch": 8.1, + "learning_rate": 1.348505782026045e-05, + "loss": 0.0271, + "step": 9155 + }, + { + "epoch": 8.1, + "learning_rate": 1.3483714551367931e-05, + "loss": 0.0293, + "step": 9156 + }, + { + "epoch": 8.1, + "learning_rate": 1.3482371210929968e-05, + "loss": 0.0267, + "step": 9157 + }, + { + "epoch": 8.1, + "learning_rate": 1.3481027798974155e-05, + "loss": 0.03, + "step": 9158 + }, + { + "epoch": 8.1, + "learning_rate": 1.3479684315528079e-05, + "loss": 0.025, + "step": 9159 + }, + { + "epoch": 8.1, + "learning_rate": 1.3478340760619333e-05, + "loss": 0.0275, + "step": 9160 + }, + { + "epoch": 8.11, + "learning_rate": 1.3476997134275512e-05, + "loss": 0.0271, + "step": 9161 + }, + { + "epoch": 8.11, + "learning_rate": 1.3475653436524203e-05, + "loss": 0.0254, + "step": 9162 + }, + { + "epoch": 8.11, + "learning_rate": 1.3474309667393006e-05, + "loss": 0.0211, + "step": 9163 + }, + { + "epoch": 8.11, + "learning_rate": 1.3472965826909518e-05, + "loss": 0.0311, + "step": 9164 + }, + { + "epoch": 8.11, + "learning_rate": 1.347162191510134e-05, + "loss": 0.0235, + "step": 9165 + }, + { + "epoch": 8.11, + "learning_rate": 1.3470277931996067e-05, + "loss": 0.0283, + "step": 9166 + }, + { + "epoch": 8.11, + "learning_rate": 1.3468933877621304e-05, + "loss": 0.0235, + "step": 9167 + }, + { + "epoch": 8.11, + "learning_rate": 1.3467589752004656e-05, + "loss": 0.0265, + "step": 9168 + }, + { + "epoch": 8.11, + "learning_rate": 1.346624555517372e-05, + "loss": 0.0256, + "step": 9169 + }, + { + "epoch": 8.11, + "learning_rate": 1.3464901287156109e-05, + "loss": 0.0271, + "step": 9170 + }, + { + "epoch": 8.11, + "learning_rate": 1.3463556947979428e-05, + "loss": 0.0306, + "step": 9171 + }, + { + "epoch": 8.12, + "learning_rate": 1.3462212537671284e-05, + "loss": 0.022, + "step": 9172 + }, + { + "epoch": 8.12, + "learning_rate": 1.3460868056259289e-05, + "loss": 0.0258, + "step": 9173 + }, + { + "epoch": 8.12, + "learning_rate": 1.3459523503771056e-05, + "loss": 0.0197, + "step": 9174 + }, + { + "epoch": 8.12, + "learning_rate": 1.3458178880234198e-05, + "loss": 0.0249, + "step": 9175 + }, + { + "epoch": 8.12, + "learning_rate": 1.3456834185676328e-05, + "loss": 0.0313, + "step": 9176 + }, + { + "epoch": 8.12, + "learning_rate": 1.3455489420125062e-05, + "loss": 0.0238, + "step": 9177 + }, + { + "epoch": 8.12, + "learning_rate": 1.3454144583608019e-05, + "loss": 0.0258, + "step": 9178 + }, + { + "epoch": 8.12, + "learning_rate": 1.3452799676152817e-05, + "loss": 0.0277, + "step": 9179 + }, + { + "epoch": 8.12, + "learning_rate": 1.345145469778708e-05, + "loss": 0.0311, + "step": 9180 + }, + { + "epoch": 8.12, + "learning_rate": 1.3450109648538421e-05, + "loss": 0.0298, + "step": 9181 + }, + { + "epoch": 8.12, + "learning_rate": 1.3448764528434474e-05, + "loss": 0.0252, + "step": 9182 + }, + { + "epoch": 8.12, + "learning_rate": 1.3447419337502861e-05, + "loss": 0.0269, + "step": 9183 + }, + { + "epoch": 8.13, + "learning_rate": 1.3446074075771202e-05, + "loss": 0.0263, + "step": 9184 + }, + { + "epoch": 8.13, + "learning_rate": 1.3444728743267132e-05, + "loss": 0.0269, + "step": 9185 + }, + { + "epoch": 8.13, + "learning_rate": 1.3443383340018277e-05, + "loss": 0.0271, + "step": 9186 + }, + { + "epoch": 8.13, + "learning_rate": 1.3442037866052268e-05, + "loss": 0.0292, + "step": 9187 + }, + { + "epoch": 8.13, + "learning_rate": 1.3440692321396738e-05, + "loss": 0.0314, + "step": 9188 + }, + { + "epoch": 8.13, + "learning_rate": 1.3439346706079324e-05, + "loss": 0.0321, + "step": 9189 + }, + { + "epoch": 8.13, + "learning_rate": 1.3438001020127651e-05, + "loss": 0.0267, + "step": 9190 + }, + { + "epoch": 8.13, + "learning_rate": 1.3436655263569363e-05, + "loss": 0.0324, + "step": 9191 + }, + { + "epoch": 8.13, + "learning_rate": 1.3435309436432101e-05, + "loss": 0.0265, + "step": 9192 + }, + { + "epoch": 8.13, + "learning_rate": 1.3433963538743496e-05, + "loss": 0.0292, + "step": 9193 + }, + { + "epoch": 8.13, + "learning_rate": 1.3432617570531194e-05, + "loss": 0.0291, + "step": 9194 + }, + { + "epoch": 8.14, + "learning_rate": 1.3431271531822836e-05, + "loss": 0.028, + "step": 9195 + }, + { + "epoch": 8.14, + "learning_rate": 1.3429925422646068e-05, + "loss": 0.0275, + "step": 9196 + }, + { + "epoch": 8.14, + "learning_rate": 1.342857924302853e-05, + "loss": 0.029, + "step": 9197 + }, + { + "epoch": 8.14, + "learning_rate": 1.3427232992997871e-05, + "loss": 0.0307, + "step": 9198 + }, + { + "epoch": 8.14, + "learning_rate": 1.3425886672581744e-05, + "loss": 0.0284, + "step": 9199 + }, + { + "epoch": 8.14, + "learning_rate": 1.3424540281807791e-05, + "loss": 0.0285, + "step": 9200 + }, + { + "epoch": 8.14, + "learning_rate": 1.3423193820703668e-05, + "loss": 0.0269, + "step": 9201 + }, + { + "epoch": 8.14, + "learning_rate": 1.3421847289297028e-05, + "loss": 0.0299, + "step": 9202 + }, + { + "epoch": 8.14, + "learning_rate": 1.342050068761552e-05, + "loss": 0.0292, + "step": 9203 + }, + { + "epoch": 8.14, + "learning_rate": 1.3419154015686802e-05, + "loss": 0.0317, + "step": 9204 + }, + { + "epoch": 8.14, + "learning_rate": 1.3417807273538533e-05, + "loss": 0.0283, + "step": 9205 + }, + { + "epoch": 8.15, + "learning_rate": 1.3416460461198364e-05, + "loss": 0.0293, + "step": 9206 + }, + { + "epoch": 8.15, + "learning_rate": 1.3415113578693965e-05, + "loss": 0.0252, + "step": 9207 + }, + { + "epoch": 8.15, + "learning_rate": 1.341376662605299e-05, + "loss": 0.0266, + "step": 9208 + }, + { + "epoch": 8.15, + "learning_rate": 1.3412419603303104e-05, + "loss": 0.0249, + "step": 9209 + }, + { + "epoch": 8.15, + "learning_rate": 1.3411072510471969e-05, + "loss": 0.0251, + "step": 9210 + }, + { + "epoch": 8.15, + "learning_rate": 1.340972534758725e-05, + "loss": 0.0282, + "step": 9211 + }, + { + "epoch": 8.15, + "learning_rate": 1.3408378114676616e-05, + "loss": 0.028, + "step": 9212 + }, + { + "epoch": 8.15, + "learning_rate": 1.3407030811767738e-05, + "loss": 0.0227, + "step": 9213 + }, + { + "epoch": 8.15, + "learning_rate": 1.3405683438888281e-05, + "loss": 0.0285, + "step": 9214 + }, + { + "epoch": 8.15, + "learning_rate": 1.3404335996065916e-05, + "loss": 0.0279, + "step": 9215 + }, + { + "epoch": 8.15, + "learning_rate": 1.3402988483328319e-05, + "loss": 0.0265, + "step": 9216 + }, + { + "epoch": 8.16, + "learning_rate": 1.3401640900703159e-05, + "loss": 0.0282, + "step": 9217 + }, + { + "epoch": 8.16, + "learning_rate": 1.3400293248218116e-05, + "loss": 0.0295, + "step": 9218 + }, + { + "epoch": 8.16, + "learning_rate": 1.3398945525900869e-05, + "loss": 0.0273, + "step": 9219 + }, + { + "epoch": 8.16, + "learning_rate": 1.3397597733779088e-05, + "loss": 0.0267, + "step": 9220 + }, + { + "epoch": 8.16, + "learning_rate": 1.3396249871880462e-05, + "loss": 0.0267, + "step": 9221 + }, + { + "epoch": 8.16, + "learning_rate": 1.3394901940232666e-05, + "loss": 0.0309, + "step": 9222 + }, + { + "epoch": 8.16, + "learning_rate": 1.3393553938863382e-05, + "loss": 0.0349, + "step": 9223 + }, + { + "epoch": 8.16, + "learning_rate": 1.3392205867800298e-05, + "loss": 0.0338, + "step": 9224 + }, + { + "epoch": 8.16, + "learning_rate": 1.3390857727071098e-05, + "loss": 0.0276, + "step": 9225 + }, + { + "epoch": 8.16, + "learning_rate": 1.338950951670347e-05, + "loss": 0.024, + "step": 9226 + }, + { + "epoch": 8.16, + "learning_rate": 1.3388161236725099e-05, + "loss": 0.0293, + "step": 9227 + }, + { + "epoch": 8.16, + "learning_rate": 1.338681288716368e-05, + "loss": 0.0296, + "step": 9228 + }, + { + "epoch": 8.17, + "learning_rate": 1.33854644680469e-05, + "loss": 0.0262, + "step": 9229 + }, + { + "epoch": 8.17, + "learning_rate": 1.338411597940245e-05, + "loss": 0.032, + "step": 9230 + }, + { + "epoch": 8.17, + "learning_rate": 1.3382767421258031e-05, + "loss": 0.0285, + "step": 9231 + }, + { + "epoch": 8.17, + "learning_rate": 1.3381418793641331e-05, + "loss": 0.0276, + "step": 9232 + }, + { + "epoch": 8.17, + "learning_rate": 1.3380070096580054e-05, + "loss": 0.0233, + "step": 9233 + }, + { + "epoch": 8.17, + "learning_rate": 1.3378721330101891e-05, + "loss": 0.0253, + "step": 9234 + }, + { + "epoch": 8.17, + "learning_rate": 1.3377372494234548e-05, + "loss": 0.027, + "step": 9235 + }, + { + "epoch": 8.17, + "learning_rate": 1.3376023589005724e-05, + "loss": 0.0258, + "step": 9236 + }, + { + "epoch": 8.17, + "learning_rate": 1.3374674614443117e-05, + "loss": 0.0222, + "step": 9237 + }, + { + "epoch": 8.17, + "learning_rate": 1.337332557057444e-05, + "loss": 0.0239, + "step": 9238 + }, + { + "epoch": 8.17, + "learning_rate": 1.3371976457427391e-05, + "loss": 0.0256, + "step": 9239 + }, + { + "epoch": 8.18, + "learning_rate": 1.3370627275029681e-05, + "loss": 0.0237, + "step": 9240 + }, + { + "epoch": 8.18, + "learning_rate": 1.3369278023409017e-05, + "loss": 0.0312, + "step": 9241 + }, + { + "epoch": 8.18, + "learning_rate": 1.3367928702593109e-05, + "loss": 0.0288, + "step": 9242 + }, + { + "epoch": 8.18, + "learning_rate": 1.3366579312609665e-05, + "loss": 0.0258, + "step": 9243 + }, + { + "epoch": 8.18, + "learning_rate": 1.3365229853486403e-05, + "loss": 0.0343, + "step": 9244 + }, + { + "epoch": 8.18, + "learning_rate": 1.3363880325251036e-05, + "loss": 0.0312, + "step": 9245 + }, + { + "epoch": 8.18, + "learning_rate": 1.3362530727931275e-05, + "loss": 0.0276, + "step": 9246 + }, + { + "epoch": 8.18, + "learning_rate": 1.336118106155484e-05, + "loss": 0.029, + "step": 9247 + }, + { + "epoch": 8.18, + "learning_rate": 1.335983132614945e-05, + "loss": 0.0242, + "step": 9248 + }, + { + "epoch": 8.18, + "learning_rate": 1.3358481521742826e-05, + "loss": 0.0272, + "step": 9249 + }, + { + "epoch": 8.18, + "learning_rate": 1.335713164836268e-05, + "loss": 0.0203, + "step": 9250 + }, + { + "epoch": 8.19, + "learning_rate": 1.3355781706036744e-05, + "loss": 0.0235, + "step": 9251 + }, + { + "epoch": 8.19, + "learning_rate": 1.3354431694792743e-05, + "loss": 0.0318, + "step": 9252 + }, + { + "epoch": 8.19, + "learning_rate": 1.3353081614658393e-05, + "loss": 0.0288, + "step": 9253 + }, + { + "epoch": 8.19, + "learning_rate": 1.335173146566143e-05, + "loss": 0.0304, + "step": 9254 + }, + { + "epoch": 8.19, + "learning_rate": 1.3350381247829575e-05, + "loss": 0.0267, + "step": 9255 + }, + { + "epoch": 8.19, + "learning_rate": 1.3349030961190563e-05, + "loss": 0.0285, + "step": 9256 + }, + { + "epoch": 8.19, + "learning_rate": 1.3347680605772122e-05, + "loss": 0.0281, + "step": 9257 + }, + { + "epoch": 8.19, + "learning_rate": 1.3346330181601985e-05, + "loss": 0.0277, + "step": 9258 + }, + { + "epoch": 8.19, + "learning_rate": 1.334497968870789e-05, + "loss": 0.0251, + "step": 9259 + }, + { + "epoch": 8.19, + "learning_rate": 1.3343629127117565e-05, + "loss": 0.0276, + "step": 9260 + }, + { + "epoch": 8.19, + "learning_rate": 1.334227849685875e-05, + "loss": 0.0273, + "step": 9261 + }, + { + "epoch": 8.19, + "learning_rate": 1.3340927797959182e-05, + "loss": 0.0267, + "step": 9262 + }, + { + "epoch": 8.2, + "learning_rate": 1.3339577030446605e-05, + "loss": 0.0288, + "step": 9263 + }, + { + "epoch": 8.2, + "learning_rate": 1.3338226194348754e-05, + "loss": 0.03, + "step": 9264 + }, + { + "epoch": 8.2, + "learning_rate": 1.3336875289693372e-05, + "loss": 0.0294, + "step": 9265 + }, + { + "epoch": 8.2, + "learning_rate": 1.3335524316508208e-05, + "loss": 0.0252, + "step": 9266 + }, + { + "epoch": 8.2, + "learning_rate": 1.3334173274821001e-05, + "loss": 0.0242, + "step": 9267 + }, + { + "epoch": 8.2, + "learning_rate": 1.33328221646595e-05, + "loss": 0.029, + "step": 9268 + }, + { + "epoch": 8.2, + "learning_rate": 1.3331470986051453e-05, + "loss": 0.026, + "step": 9269 + }, + { + "epoch": 8.2, + "learning_rate": 1.333011973902461e-05, + "loss": 0.0271, + "step": 9270 + }, + { + "epoch": 8.2, + "learning_rate": 1.332876842360672e-05, + "loss": 0.0272, + "step": 9271 + }, + { + "epoch": 8.2, + "learning_rate": 1.3327417039825536e-05, + "loss": 0.0242, + "step": 9272 + }, + { + "epoch": 8.2, + "learning_rate": 1.3326065587708812e-05, + "loss": 0.0303, + "step": 9273 + }, + { + "epoch": 8.21, + "learning_rate": 1.33247140672843e-05, + "loss": 0.0209, + "step": 9274 + }, + { + "epoch": 8.21, + "learning_rate": 1.3323362478579763e-05, + "loss": 0.0285, + "step": 9275 + }, + { + "epoch": 8.21, + "learning_rate": 1.3322010821622951e-05, + "loss": 0.0271, + "step": 9276 + }, + { + "epoch": 8.21, + "learning_rate": 1.3320659096441629e-05, + "loss": 0.0239, + "step": 9277 + }, + { + "epoch": 8.21, + "learning_rate": 1.331930730306355e-05, + "loss": 0.0254, + "step": 9278 + }, + { + "epoch": 8.21, + "learning_rate": 1.3317955441516485e-05, + "loss": 0.0284, + "step": 9279 + }, + { + "epoch": 8.21, + "learning_rate": 1.3316603511828197e-05, + "loss": 0.0283, + "step": 9280 + }, + { + "epoch": 8.21, + "learning_rate": 1.3315251514026442e-05, + "loss": 0.0241, + "step": 9281 + }, + { + "epoch": 8.21, + "learning_rate": 1.331389944813899e-05, + "loss": 0.0265, + "step": 9282 + }, + { + "epoch": 8.21, + "learning_rate": 1.3312547314193614e-05, + "loss": 0.0248, + "step": 9283 + }, + { + "epoch": 8.21, + "learning_rate": 1.3311195112218076e-05, + "loss": 0.0268, + "step": 9284 + }, + { + "epoch": 8.22, + "learning_rate": 1.3309842842240151e-05, + "loss": 0.0302, + "step": 9285 + }, + { + "epoch": 8.22, + "learning_rate": 1.3308490504287605e-05, + "loss": 0.025, + "step": 9286 + }, + { + "epoch": 8.22, + "learning_rate": 1.3307138098388222e-05, + "loss": 0.0237, + "step": 9287 + }, + { + "epoch": 8.22, + "learning_rate": 1.3305785624569762e-05, + "loss": 0.0284, + "step": 9288 + }, + { + "epoch": 8.22, + "learning_rate": 1.3304433082860012e-05, + "loss": 0.0319, + "step": 9289 + }, + { + "epoch": 8.22, + "learning_rate": 1.3303080473286744e-05, + "loss": 0.0288, + "step": 9290 + }, + { + "epoch": 8.22, + "learning_rate": 1.330172779587774e-05, + "loss": 0.0264, + "step": 9291 + }, + { + "epoch": 8.22, + "learning_rate": 1.3300375050660777e-05, + "loss": 0.026, + "step": 9292 + }, + { + "epoch": 8.22, + "learning_rate": 1.3299022237663636e-05, + "loss": 0.0296, + "step": 9293 + }, + { + "epoch": 8.22, + "learning_rate": 1.3297669356914107e-05, + "loss": 0.0271, + "step": 9294 + }, + { + "epoch": 8.22, + "learning_rate": 1.3296316408439962e-05, + "loss": 0.0309, + "step": 9295 + }, + { + "epoch": 8.22, + "learning_rate": 1.3294963392268997e-05, + "loss": 0.0323, + "step": 9296 + }, + { + "epoch": 8.23, + "learning_rate": 1.3293610308428999e-05, + "loss": 0.032, + "step": 9297 + }, + { + "epoch": 8.23, + "learning_rate": 1.329225715694775e-05, + "loss": 0.0281, + "step": 9298 + }, + { + "epoch": 8.23, + "learning_rate": 1.3290903937853043e-05, + "loss": 0.0293, + "step": 9299 + }, + { + "epoch": 8.23, + "learning_rate": 1.3289550651172669e-05, + "loss": 0.0278, + "step": 9300 + }, + { + "epoch": 8.23, + "learning_rate": 1.3288197296934424e-05, + "loss": 0.0303, + "step": 9301 + }, + { + "epoch": 8.23, + "learning_rate": 1.3286843875166093e-05, + "loss": 0.0212, + "step": 9302 + }, + { + "epoch": 8.23, + "learning_rate": 1.328549038589548e-05, + "loss": 0.0296, + "step": 9303 + }, + { + "epoch": 8.23, + "learning_rate": 1.328413682915038e-05, + "loss": 0.0265, + "step": 9304 + }, + { + "epoch": 8.23, + "learning_rate": 1.328278320495859e-05, + "loss": 0.0283, + "step": 9305 + }, + { + "epoch": 8.23, + "learning_rate": 1.3281429513347908e-05, + "loss": 0.0256, + "step": 9306 + }, + { + "epoch": 8.23, + "learning_rate": 1.3280075754346138e-05, + "loss": 0.0237, + "step": 9307 + }, + { + "epoch": 8.24, + "learning_rate": 1.3278721927981077e-05, + "loss": 0.027, + "step": 9308 + }, + { + "epoch": 8.24, + "learning_rate": 1.3277368034280535e-05, + "loss": 0.0237, + "step": 9309 + }, + { + "epoch": 8.24, + "learning_rate": 1.3276014073272317e-05, + "loss": 0.0268, + "step": 9310 + }, + { + "epoch": 8.24, + "learning_rate": 1.3274660044984225e-05, + "loss": 0.0301, + "step": 9311 + }, + { + "epoch": 8.24, + "learning_rate": 1.3273305949444068e-05, + "loss": 0.031, + "step": 9312 + }, + { + "epoch": 8.24, + "learning_rate": 1.3271951786679658e-05, + "loss": 0.0261, + "step": 9313 + }, + { + "epoch": 8.24, + "learning_rate": 1.3270597556718801e-05, + "loss": 0.0297, + "step": 9314 + }, + { + "epoch": 8.24, + "learning_rate": 1.3269243259589312e-05, + "loss": 0.0287, + "step": 9315 + }, + { + "epoch": 8.24, + "learning_rate": 1.3267888895319005e-05, + "loss": 0.0277, + "step": 9316 + }, + { + "epoch": 8.24, + "learning_rate": 1.3266534463935694e-05, + "loss": 0.0323, + "step": 9317 + }, + { + "epoch": 8.24, + "learning_rate": 1.3265179965467197e-05, + "loss": 0.0329, + "step": 9318 + }, + { + "epoch": 8.25, + "learning_rate": 1.3263825399941326e-05, + "loss": 0.0314, + "step": 9319 + }, + { + "epoch": 8.25, + "learning_rate": 1.3262470767385902e-05, + "loss": 0.0353, + "step": 9320 + }, + { + "epoch": 8.25, + "learning_rate": 1.3261116067828748e-05, + "loss": 0.0244, + "step": 9321 + }, + { + "epoch": 8.25, + "learning_rate": 1.3259761301297684e-05, + "loss": 0.0231, + "step": 9322 + }, + { + "epoch": 8.25, + "learning_rate": 1.3258406467820535e-05, + "loss": 0.0316, + "step": 9323 + }, + { + "epoch": 8.25, + "learning_rate": 1.3257051567425121e-05, + "loss": 0.0324, + "step": 9324 + }, + { + "epoch": 8.25, + "learning_rate": 1.3255696600139272e-05, + "loss": 0.0298, + "step": 9325 + }, + { + "epoch": 8.25, + "learning_rate": 1.3254341565990812e-05, + "loss": 0.0271, + "step": 9326 + }, + { + "epoch": 8.25, + "learning_rate": 1.3252986465007571e-05, + "loss": 0.028, + "step": 9327 + }, + { + "epoch": 8.25, + "learning_rate": 1.3251631297217375e-05, + "loss": 0.0251, + "step": 9328 + }, + { + "epoch": 8.25, + "learning_rate": 1.3250276062648065e-05, + "loss": 0.0313, + "step": 9329 + }, + { + "epoch": 8.25, + "learning_rate": 1.3248920761327464e-05, + "loss": 0.0323, + "step": 9330 + }, + { + "epoch": 8.26, + "learning_rate": 1.324756539328341e-05, + "loss": 0.0309, + "step": 9331 + }, + { + "epoch": 8.26, + "learning_rate": 1.3246209958543737e-05, + "loss": 0.0284, + "step": 9332 + }, + { + "epoch": 8.26, + "learning_rate": 1.3244854457136285e-05, + "loss": 0.0285, + "step": 9333 + }, + { + "epoch": 8.26, + "learning_rate": 1.3243498889088886e-05, + "loss": 0.0233, + "step": 9334 + }, + { + "epoch": 8.26, + "learning_rate": 1.3242143254429384e-05, + "loss": 0.0269, + "step": 9335 + }, + { + "epoch": 8.26, + "learning_rate": 1.3240787553185622e-05, + "loss": 0.0288, + "step": 9336 + }, + { + "epoch": 8.26, + "learning_rate": 1.3239431785385438e-05, + "loss": 0.0265, + "step": 9337 + }, + { + "epoch": 8.26, + "learning_rate": 1.3238075951056675e-05, + "loss": 0.0314, + "step": 9338 + }, + { + "epoch": 8.26, + "learning_rate": 1.3236720050227178e-05, + "loss": 0.0287, + "step": 9339 + }, + { + "epoch": 8.26, + "learning_rate": 1.3235364082924797e-05, + "loss": 0.0264, + "step": 9340 + }, + { + "epoch": 8.26, + "learning_rate": 1.3234008049177375e-05, + "loss": 0.027, + "step": 9341 + }, + { + "epoch": 8.27, + "learning_rate": 1.3232651949012767e-05, + "loss": 0.025, + "step": 9342 + }, + { + "epoch": 8.27, + "learning_rate": 1.3231295782458819e-05, + "loss": 0.0336, + "step": 9343 + }, + { + "epoch": 8.27, + "learning_rate": 1.3229939549543382e-05, + "loss": 0.0293, + "step": 9344 + }, + { + "epoch": 8.27, + "learning_rate": 1.3228583250294313e-05, + "loss": 0.0275, + "step": 9345 + }, + { + "epoch": 8.27, + "learning_rate": 1.3227226884739461e-05, + "loss": 0.0289, + "step": 9346 + }, + { + "epoch": 8.27, + "learning_rate": 1.322587045290669e-05, + "loss": 0.0288, + "step": 9347 + }, + { + "epoch": 8.27, + "learning_rate": 1.3224513954823847e-05, + "loss": 0.0248, + "step": 9348 + }, + { + "epoch": 8.27, + "learning_rate": 1.3223157390518797e-05, + "loss": 0.0251, + "step": 9349 + }, + { + "epoch": 8.27, + "learning_rate": 1.3221800760019402e-05, + "loss": 0.0328, + "step": 9350 + }, + { + "epoch": 8.27, + "learning_rate": 1.3220444063353518e-05, + "loss": 0.0337, + "step": 9351 + }, + { + "epoch": 8.27, + "learning_rate": 1.3219087300549007e-05, + "loss": 0.0304, + "step": 9352 + }, + { + "epoch": 8.28, + "learning_rate": 1.3217730471633738e-05, + "loss": 0.032, + "step": 9353 + }, + { + "epoch": 8.28, + "learning_rate": 1.3216373576635572e-05, + "loss": 0.0273, + "step": 9354 + }, + { + "epoch": 8.28, + "learning_rate": 1.321501661558238e-05, + "loss": 0.0269, + "step": 9355 + }, + { + "epoch": 8.28, + "learning_rate": 1.3213659588502025e-05, + "loss": 0.0276, + "step": 9356 + }, + { + "epoch": 8.28, + "learning_rate": 1.3212302495422384e-05, + "loss": 0.0265, + "step": 9357 + }, + { + "epoch": 8.28, + "learning_rate": 1.3210945336371319e-05, + "loss": 0.026, + "step": 9358 + }, + { + "epoch": 8.28, + "learning_rate": 1.3209588111376708e-05, + "loss": 0.0334, + "step": 9359 + }, + { + "epoch": 8.28, + "learning_rate": 1.3208230820466422e-05, + "loss": 0.0282, + "step": 9360 + }, + { + "epoch": 8.28, + "learning_rate": 1.3206873463668334e-05, + "loss": 0.0259, + "step": 9361 + }, + { + "epoch": 8.28, + "learning_rate": 1.3205516041010325e-05, + "loss": 0.0311, + "step": 9362 + }, + { + "epoch": 8.28, + "learning_rate": 1.3204158552520267e-05, + "loss": 0.0248, + "step": 9363 + }, + { + "epoch": 8.29, + "learning_rate": 1.3202800998226048e-05, + "loss": 0.0261, + "step": 9364 + }, + { + "epoch": 8.29, + "learning_rate": 1.3201443378155538e-05, + "loss": 0.0281, + "step": 9365 + }, + { + "epoch": 8.29, + "learning_rate": 1.3200085692336621e-05, + "loss": 0.029, + "step": 9366 + }, + { + "epoch": 8.29, + "learning_rate": 1.3198727940797184e-05, + "loss": 0.0207, + "step": 9367 + }, + { + "epoch": 8.29, + "learning_rate": 1.319737012356511e-05, + "loss": 0.0269, + "step": 9368 + }, + { + "epoch": 8.29, + "learning_rate": 1.3196012240668283e-05, + "loss": 0.0266, + "step": 9369 + }, + { + "epoch": 8.29, + "learning_rate": 1.3194654292134589e-05, + "loss": 0.031, + "step": 9370 + }, + { + "epoch": 8.29, + "learning_rate": 1.3193296277991922e-05, + "loss": 0.0284, + "step": 9371 + }, + { + "epoch": 8.29, + "learning_rate": 1.3191938198268165e-05, + "loss": 0.0252, + "step": 9372 + }, + { + "epoch": 8.29, + "learning_rate": 1.3190580052991214e-05, + "loss": 0.0286, + "step": 9373 + }, + { + "epoch": 8.29, + "learning_rate": 1.3189221842188955e-05, + "loss": 0.0304, + "step": 9374 + }, + { + "epoch": 8.29, + "learning_rate": 1.3187863565889287e-05, + "loss": 0.0332, + "step": 9375 + }, + { + "epoch": 8.3, + "learning_rate": 1.3186505224120105e-05, + "loss": 0.0297, + "step": 9376 + }, + { + "epoch": 8.3, + "learning_rate": 1.3185146816909304e-05, + "loss": 0.0241, + "step": 9377 + }, + { + "epoch": 8.3, + "learning_rate": 1.3183788344284784e-05, + "loss": 0.0265, + "step": 9378 + }, + { + "epoch": 8.3, + "learning_rate": 1.3182429806274442e-05, + "loss": 0.026, + "step": 9379 + }, + { + "epoch": 8.3, + "learning_rate": 1.3181071202906176e-05, + "loss": 0.0322, + "step": 9380 + }, + { + "epoch": 8.3, + "learning_rate": 1.317971253420789e-05, + "loss": 0.0284, + "step": 9381 + }, + { + "epoch": 8.3, + "learning_rate": 1.3178353800207491e-05, + "loss": 0.0243, + "step": 9382 + }, + { + "epoch": 8.3, + "learning_rate": 1.3176995000932877e-05, + "loss": 0.0294, + "step": 9383 + }, + { + "epoch": 8.3, + "learning_rate": 1.317563613641196e-05, + "loss": 0.023, + "step": 9384 + }, + { + "epoch": 8.3, + "learning_rate": 1.3174277206672643e-05, + "loss": 0.0287, + "step": 9385 + }, + { + "epoch": 8.3, + "learning_rate": 1.3172918211742836e-05, + "loss": 0.0289, + "step": 9386 + }, + { + "epoch": 8.31, + "learning_rate": 1.3171559151650443e-05, + "loss": 0.0242, + "step": 9387 + }, + { + "epoch": 8.31, + "learning_rate": 1.3170200026423387e-05, + "loss": 0.0288, + "step": 9388 + }, + { + "epoch": 8.31, + "learning_rate": 1.316884083608957e-05, + "loss": 0.0318, + "step": 9389 + }, + { + "epoch": 8.31, + "learning_rate": 1.3167481580676915e-05, + "loss": 0.0273, + "step": 9390 + }, + { + "epoch": 8.31, + "learning_rate": 1.3166122260213327e-05, + "loss": 0.0228, + "step": 9391 + }, + { + "epoch": 8.31, + "learning_rate": 1.3164762874726733e-05, + "loss": 0.0311, + "step": 9392 + }, + { + "epoch": 8.31, + "learning_rate": 1.3163403424245039e-05, + "loss": 0.029, + "step": 9393 + }, + { + "epoch": 8.31, + "learning_rate": 1.3162043908796174e-05, + "loss": 0.0282, + "step": 9394 + }, + { + "epoch": 8.31, + "learning_rate": 1.3160684328408056e-05, + "loss": 0.0267, + "step": 9395 + }, + { + "epoch": 8.31, + "learning_rate": 1.3159324683108606e-05, + "loss": 0.0289, + "step": 9396 + }, + { + "epoch": 8.31, + "learning_rate": 1.3157964972925745e-05, + "loss": 0.0267, + "step": 9397 + }, + { + "epoch": 8.32, + "learning_rate": 1.31566051978874e-05, + "loss": 0.0293, + "step": 9398 + }, + { + "epoch": 8.32, + "learning_rate": 1.31552453580215e-05, + "loss": 0.0268, + "step": 9399 + }, + { + "epoch": 8.32, + "learning_rate": 1.3153885453355964e-05, + "loss": 0.0249, + "step": 9400 + }, + { + "epoch": 8.32, + "learning_rate": 1.3152525483918725e-05, + "loss": 0.0301, + "step": 9401 + }, + { + "epoch": 8.32, + "learning_rate": 1.315116544973772e-05, + "loss": 0.0305, + "step": 9402 + }, + { + "epoch": 8.32, + "learning_rate": 1.3149805350840868e-05, + "loss": 0.0317, + "step": 9403 + }, + { + "epoch": 8.32, + "learning_rate": 1.3148445187256107e-05, + "loss": 0.028, + "step": 9404 + }, + { + "epoch": 8.32, + "learning_rate": 1.3147084959011371e-05, + "loss": 0.0308, + "step": 9405 + }, + { + "epoch": 8.32, + "learning_rate": 1.3145724666134597e-05, + "loss": 0.0294, + "step": 9406 + }, + { + "epoch": 8.32, + "learning_rate": 1.3144364308653716e-05, + "loss": 0.0272, + "step": 9407 + }, + { + "epoch": 8.32, + "learning_rate": 1.314300388659667e-05, + "loss": 0.0246, + "step": 9408 + }, + { + "epoch": 8.32, + "learning_rate": 1.31416433999914e-05, + "loss": 0.0279, + "step": 9409 + }, + { + "epoch": 8.33, + "learning_rate": 1.3140282848865841e-05, + "loss": 0.0298, + "step": 9410 + }, + { + "epoch": 8.33, + "learning_rate": 1.313892223324794e-05, + "loss": 0.0265, + "step": 9411 + }, + { + "epoch": 8.33, + "learning_rate": 1.3137561553165635e-05, + "loss": 0.0254, + "step": 9412 + }, + { + "epoch": 8.33, + "learning_rate": 1.3136200808646872e-05, + "loss": 0.0241, + "step": 9413 + }, + { + "epoch": 8.33, + "learning_rate": 1.31348399997196e-05, + "loss": 0.0238, + "step": 9414 + }, + { + "epoch": 8.33, + "learning_rate": 1.3133479126411763e-05, + "loss": 0.0259, + "step": 9415 + }, + { + "epoch": 8.33, + "learning_rate": 1.3132118188751313e-05, + "loss": 0.0269, + "step": 9416 + }, + { + "epoch": 8.33, + "learning_rate": 1.3130757186766196e-05, + "loss": 0.0264, + "step": 9417 + }, + { + "epoch": 8.33, + "learning_rate": 1.3129396120484361e-05, + "loss": 0.0317, + "step": 9418 + }, + { + "epoch": 8.33, + "learning_rate": 1.3128034989933767e-05, + "loss": 0.0295, + "step": 9419 + }, + { + "epoch": 8.33, + "learning_rate": 1.3126673795142362e-05, + "loss": 0.0269, + "step": 9420 + }, + { + "epoch": 8.34, + "learning_rate": 1.3125312536138104e-05, + "loss": 0.0293, + "step": 9421 + }, + { + "epoch": 8.34, + "learning_rate": 1.312395121294895e-05, + "loss": 0.0218, + "step": 9422 + }, + { + "epoch": 8.34, + "learning_rate": 1.3122589825602856e-05, + "loss": 0.0243, + "step": 9423 + }, + { + "epoch": 8.34, + "learning_rate": 1.3121228374127779e-05, + "loss": 0.0281, + "step": 9424 + }, + { + "epoch": 8.34, + "learning_rate": 1.3119866858551682e-05, + "loss": 0.0337, + "step": 9425 + }, + { + "epoch": 8.34, + "learning_rate": 1.3118505278902527e-05, + "loss": 0.0297, + "step": 9426 + }, + { + "epoch": 8.34, + "learning_rate": 1.3117143635208274e-05, + "loss": 0.0252, + "step": 9427 + }, + { + "epoch": 8.34, + "learning_rate": 1.3115781927496892e-05, + "loss": 0.0233, + "step": 9428 + }, + { + "epoch": 8.34, + "learning_rate": 1.3114420155796341e-05, + "loss": 0.0293, + "step": 9429 + }, + { + "epoch": 8.34, + "learning_rate": 1.3113058320134593e-05, + "loss": 0.0291, + "step": 9430 + }, + { + "epoch": 8.34, + "learning_rate": 1.3111696420539613e-05, + "loss": 0.0356, + "step": 9431 + }, + { + "epoch": 8.35, + "learning_rate": 1.3110334457039366e-05, + "loss": 0.0295, + "step": 9432 + }, + { + "epoch": 8.35, + "learning_rate": 1.3108972429661838e-05, + "loss": 0.023, + "step": 9433 + }, + { + "epoch": 8.35, + "learning_rate": 1.3107610338434984e-05, + "loss": 0.0271, + "step": 9434 + }, + { + "epoch": 8.35, + "learning_rate": 1.3106248183386787e-05, + "loss": 0.0302, + "step": 9435 + }, + { + "epoch": 8.35, + "learning_rate": 1.3104885964545217e-05, + "loss": 0.029, + "step": 9436 + }, + { + "epoch": 8.35, + "learning_rate": 1.3103523681938257e-05, + "loss": 0.0272, + "step": 9437 + }, + { + "epoch": 8.35, + "learning_rate": 1.3102161335593877e-05, + "loss": 0.0239, + "step": 9438 + }, + { + "epoch": 8.35, + "learning_rate": 1.3100798925540055e-05, + "loss": 0.0298, + "step": 9439 + }, + { + "epoch": 8.35, + "learning_rate": 1.3099436451804781e-05, + "loss": 0.0325, + "step": 9440 + }, + { + "epoch": 8.35, + "learning_rate": 1.3098073914416025e-05, + "loss": 0.0268, + "step": 9441 + }, + { + "epoch": 8.35, + "learning_rate": 1.3096711313401775e-05, + "loss": 0.0292, + "step": 9442 + }, + { + "epoch": 8.35, + "learning_rate": 1.3095348648790013e-05, + "loss": 0.026, + "step": 9443 + }, + { + "epoch": 8.36, + "learning_rate": 1.3093985920608729e-05, + "loss": 0.0274, + "step": 9444 + }, + { + "epoch": 8.36, + "learning_rate": 1.3092623128885902e-05, + "loss": 0.0294, + "step": 9445 + }, + { + "epoch": 8.36, + "learning_rate": 1.3091260273649525e-05, + "loss": 0.031, + "step": 9446 + }, + { + "epoch": 8.36, + "learning_rate": 1.3089897354927586e-05, + "loss": 0.0241, + "step": 9447 + }, + { + "epoch": 8.36, + "learning_rate": 1.3088534372748077e-05, + "loss": 0.0276, + "step": 9448 + }, + { + "epoch": 8.36, + "learning_rate": 1.3087171327138983e-05, + "loss": 0.0258, + "step": 9449 + }, + { + "epoch": 8.36, + "learning_rate": 1.3085808218128307e-05, + "loss": 0.0308, + "step": 9450 + }, + { + "epoch": 8.36, + "learning_rate": 1.3084445045744036e-05, + "loss": 0.0328, + "step": 9451 + }, + { + "epoch": 8.36, + "learning_rate": 1.3083081810014165e-05, + "loss": 0.0257, + "step": 9452 + }, + { + "epoch": 8.36, + "learning_rate": 1.3081718510966696e-05, + "loss": 0.0264, + "step": 9453 + }, + { + "epoch": 8.36, + "learning_rate": 1.3080355148629625e-05, + "loss": 0.0265, + "step": 9454 + }, + { + "epoch": 8.37, + "learning_rate": 1.3078991723030954e-05, + "loss": 0.0303, + "step": 9455 + }, + { + "epoch": 8.37, + "learning_rate": 1.3077628234198679e-05, + "loss": 0.0316, + "step": 9456 + }, + { + "epoch": 8.37, + "learning_rate": 1.3076264682160803e-05, + "loss": 0.0357, + "step": 9457 + }, + { + "epoch": 8.37, + "learning_rate": 1.3074901066945334e-05, + "loss": 0.0266, + "step": 9458 + }, + { + "epoch": 8.37, + "learning_rate": 1.307353738858027e-05, + "loss": 0.0299, + "step": 9459 + }, + { + "epoch": 8.37, + "learning_rate": 1.3072173647093625e-05, + "loss": 0.0341, + "step": 9460 + }, + { + "epoch": 8.37, + "learning_rate": 1.3070809842513396e-05, + "loss": 0.0301, + "step": 9461 + }, + { + "epoch": 8.37, + "learning_rate": 1.3069445974867606e-05, + "loss": 0.0264, + "step": 9462 + }, + { + "epoch": 8.37, + "learning_rate": 1.3068082044184249e-05, + "loss": 0.0294, + "step": 9463 + }, + { + "epoch": 8.37, + "learning_rate": 1.3066718050491347e-05, + "loss": 0.0301, + "step": 9464 + }, + { + "epoch": 8.37, + "learning_rate": 1.3065353993816908e-05, + "loss": 0.0312, + "step": 9465 + }, + { + "epoch": 8.38, + "learning_rate": 1.3063989874188944e-05, + "loss": 0.0309, + "step": 9466 + }, + { + "epoch": 8.38, + "learning_rate": 1.3062625691635477e-05, + "loss": 0.0231, + "step": 9467 + }, + { + "epoch": 8.38, + "learning_rate": 1.3061261446184518e-05, + "loss": 0.0316, + "step": 9468 + }, + { + "epoch": 8.38, + "learning_rate": 1.305989713786409e-05, + "loss": 0.0323, + "step": 9469 + }, + { + "epoch": 8.38, + "learning_rate": 1.3058532766702204e-05, + "loss": 0.0263, + "step": 9470 + }, + { + "epoch": 8.38, + "learning_rate": 1.3057168332726881e-05, + "loss": 0.0236, + "step": 9471 + }, + { + "epoch": 8.38, + "learning_rate": 1.3055803835966153e-05, + "loss": 0.0256, + "step": 9472 + }, + { + "epoch": 8.38, + "learning_rate": 1.305443927644803e-05, + "loss": 0.0304, + "step": 9473 + }, + { + "epoch": 8.38, + "learning_rate": 1.3053074654200545e-05, + "loss": 0.0289, + "step": 9474 + }, + { + "epoch": 8.38, + "learning_rate": 1.3051709969251718e-05, + "loss": 0.027, + "step": 9475 + }, + { + "epoch": 8.38, + "learning_rate": 1.3050345221629578e-05, + "loss": 0.0236, + "step": 9476 + }, + { + "epoch": 8.39, + "learning_rate": 1.3048980411362156e-05, + "loss": 0.0321, + "step": 9477 + }, + { + "epoch": 8.39, + "learning_rate": 1.3047615538477472e-05, + "loss": 0.0275, + "step": 9478 + }, + { + "epoch": 8.39, + "learning_rate": 1.3046250603003567e-05, + "loss": 0.025, + "step": 9479 + }, + { + "epoch": 8.39, + "learning_rate": 1.3044885604968466e-05, + "loss": 0.0258, + "step": 9480 + }, + { + "epoch": 8.39, + "learning_rate": 1.3043520544400208e-05, + "loss": 0.0271, + "step": 9481 + }, + { + "epoch": 8.39, + "learning_rate": 1.3042155421326821e-05, + "loss": 0.0269, + "step": 9482 + }, + { + "epoch": 8.39, + "learning_rate": 1.3040790235776344e-05, + "loss": 0.0285, + "step": 9483 + }, + { + "epoch": 8.39, + "learning_rate": 1.3039424987776812e-05, + "loss": 0.0284, + "step": 9484 + }, + { + "epoch": 8.39, + "learning_rate": 1.3038059677356267e-05, + "loss": 0.0272, + "step": 9485 + }, + { + "epoch": 8.39, + "learning_rate": 1.3036694304542748e-05, + "loss": 0.0343, + "step": 9486 + }, + { + "epoch": 8.39, + "learning_rate": 1.3035328869364292e-05, + "loss": 0.0261, + "step": 9487 + }, + { + "epoch": 8.39, + "learning_rate": 1.3033963371848944e-05, + "loss": 0.0214, + "step": 9488 + }, + { + "epoch": 8.4, + "learning_rate": 1.3032597812024745e-05, + "loss": 0.0273, + "step": 9489 + }, + { + "epoch": 8.4, + "learning_rate": 1.3031232189919744e-05, + "loss": 0.0268, + "step": 9490 + }, + { + "epoch": 8.4, + "learning_rate": 1.3029866505561981e-05, + "loss": 0.0278, + "step": 9491 + }, + { + "epoch": 8.4, + "learning_rate": 1.3028500758979507e-05, + "loss": 0.0318, + "step": 9492 + }, + { + "epoch": 8.4, + "learning_rate": 1.3027134950200373e-05, + "loss": 0.0263, + "step": 9493 + }, + { + "epoch": 8.4, + "learning_rate": 1.3025769079252624e-05, + "loss": 0.0307, + "step": 9494 + }, + { + "epoch": 8.4, + "learning_rate": 1.3024403146164312e-05, + "loss": 0.032, + "step": 9495 + }, + { + "epoch": 8.4, + "learning_rate": 1.302303715096349e-05, + "loss": 0.0311, + "step": 9496 + }, + { + "epoch": 8.4, + "learning_rate": 1.3021671093678217e-05, + "loss": 0.0309, + "step": 9497 + }, + { + "epoch": 8.4, + "learning_rate": 1.3020304974336535e-05, + "loss": 0.0262, + "step": 9498 + }, + { + "epoch": 8.4, + "learning_rate": 1.301893879296651e-05, + "loss": 0.03, + "step": 9499 + }, + { + "epoch": 8.41, + "learning_rate": 1.30175725495962e-05, + "loss": 0.0308, + "step": 9500 + }, + { + "epoch": 8.41, + "learning_rate": 1.301620624425366e-05, + "loss": 0.0261, + "step": 9501 + }, + { + "epoch": 8.41, + "learning_rate": 1.3014839876966947e-05, + "loss": 0.0324, + "step": 9502 + }, + { + "epoch": 8.41, + "learning_rate": 1.301347344776413e-05, + "loss": 0.028, + "step": 9503 + }, + { + "epoch": 8.41, + "learning_rate": 1.3012106956673265e-05, + "loss": 0.0255, + "step": 9504 + }, + { + "epoch": 8.41, + "learning_rate": 1.301074040372242e-05, + "loss": 0.0288, + "step": 9505 + }, + { + "epoch": 8.41, + "learning_rate": 1.3009373788939656e-05, + "loss": 0.0294, + "step": 9506 + }, + { + "epoch": 8.41, + "learning_rate": 1.3008007112353048e-05, + "loss": 0.0289, + "step": 9507 + }, + { + "epoch": 8.41, + "learning_rate": 1.3006640373990652e-05, + "loss": 0.0306, + "step": 9508 + }, + { + "epoch": 8.41, + "learning_rate": 1.3005273573880541e-05, + "loss": 0.029, + "step": 9509 + }, + { + "epoch": 8.41, + "learning_rate": 1.3003906712050789e-05, + "loss": 0.0284, + "step": 9510 + }, + { + "epoch": 8.42, + "learning_rate": 1.3002539788529465e-05, + "loss": 0.0268, + "step": 9511 + }, + { + "epoch": 8.42, + "learning_rate": 1.300117280334464e-05, + "loss": 0.033, + "step": 9512 + }, + { + "epoch": 8.42, + "learning_rate": 1.2999805756524388e-05, + "loss": 0.0349, + "step": 9513 + }, + { + "epoch": 8.42, + "learning_rate": 1.299843864809679e-05, + "loss": 0.0284, + "step": 9514 + }, + { + "epoch": 8.42, + "learning_rate": 1.2997071478089914e-05, + "loss": 0.0259, + "step": 9515 + }, + { + "epoch": 8.42, + "learning_rate": 1.2995704246531842e-05, + "loss": 0.0263, + "step": 9516 + }, + { + "epoch": 8.42, + "learning_rate": 1.2994336953450652e-05, + "loss": 0.0286, + "step": 9517 + }, + { + "epoch": 8.42, + "learning_rate": 1.2992969598874428e-05, + "loss": 0.0282, + "step": 9518 + }, + { + "epoch": 8.42, + "learning_rate": 1.2991602182831247e-05, + "loss": 0.0282, + "step": 9519 + }, + { + "epoch": 8.42, + "learning_rate": 1.2990234705349192e-05, + "loss": 0.0302, + "step": 9520 + }, + { + "epoch": 8.42, + "learning_rate": 1.298886716645635e-05, + "loss": 0.0418, + "step": 9521 + }, + { + "epoch": 8.42, + "learning_rate": 1.2987499566180803e-05, + "loss": 0.0258, + "step": 9522 + }, + { + "epoch": 8.43, + "learning_rate": 1.298613190455064e-05, + "loss": 0.0305, + "step": 9523 + }, + { + "epoch": 8.43, + "learning_rate": 1.2984764181593948e-05, + "loss": 0.0265, + "step": 9524 + }, + { + "epoch": 8.43, + "learning_rate": 1.2983396397338814e-05, + "loss": 0.0326, + "step": 9525 + }, + { + "epoch": 8.43, + "learning_rate": 1.2982028551813332e-05, + "loss": 0.033, + "step": 9526 + }, + { + "epoch": 8.43, + "learning_rate": 1.2980660645045593e-05, + "loss": 0.0296, + "step": 9527 + }, + { + "epoch": 8.43, + "learning_rate": 1.297929267706369e-05, + "loss": 0.0287, + "step": 9528 + }, + { + "epoch": 8.43, + "learning_rate": 1.2977924647895712e-05, + "loss": 0.0286, + "step": 9529 + }, + { + "epoch": 8.43, + "learning_rate": 1.2976556557569758e-05, + "loss": 0.0343, + "step": 9530 + }, + { + "epoch": 8.43, + "learning_rate": 1.297518840611393e-05, + "loss": 0.0283, + "step": 9531 + }, + { + "epoch": 8.43, + "learning_rate": 1.2973820193556316e-05, + "loss": 0.0292, + "step": 9532 + }, + { + "epoch": 8.43, + "learning_rate": 1.2972451919925022e-05, + "loss": 0.0248, + "step": 9533 + }, + { + "epoch": 8.44, + "learning_rate": 1.2971083585248145e-05, + "loss": 0.0291, + "step": 9534 + }, + { + "epoch": 8.44, + "learning_rate": 1.2969715189553791e-05, + "loss": 0.0311, + "step": 9535 + }, + { + "epoch": 8.44, + "learning_rate": 1.2968346732870058e-05, + "loss": 0.03, + "step": 9536 + }, + { + "epoch": 8.44, + "learning_rate": 1.2966978215225047e-05, + "loss": 0.0267, + "step": 9537 + }, + { + "epoch": 8.44, + "learning_rate": 1.2965609636646876e-05, + "loss": 0.0289, + "step": 9538 + }, + { + "epoch": 8.44, + "learning_rate": 1.2964240997163642e-05, + "loss": 0.0336, + "step": 9539 + }, + { + "epoch": 8.44, + "learning_rate": 1.2962872296803454e-05, + "loss": 0.0248, + "step": 9540 + }, + { + "epoch": 8.44, + "learning_rate": 1.2961503535594422e-05, + "loss": 0.0274, + "step": 9541 + }, + { + "epoch": 8.44, + "learning_rate": 1.2960134713564657e-05, + "loss": 0.0301, + "step": 9542 + }, + { + "epoch": 8.44, + "learning_rate": 1.295876583074227e-05, + "loss": 0.0308, + "step": 9543 + }, + { + "epoch": 8.44, + "learning_rate": 1.2957396887155373e-05, + "loss": 0.0273, + "step": 9544 + }, + { + "epoch": 8.45, + "learning_rate": 1.2956027882832083e-05, + "loss": 0.0262, + "step": 9545 + }, + { + "epoch": 8.45, + "learning_rate": 1.2954658817800514e-05, + "loss": 0.0293, + "step": 9546 + }, + { + "epoch": 8.45, + "learning_rate": 1.2953289692088781e-05, + "loss": 0.0293, + "step": 9547 + }, + { + "epoch": 8.45, + "learning_rate": 1.2951920505725002e-05, + "loss": 0.0259, + "step": 9548 + }, + { + "epoch": 8.45, + "learning_rate": 1.29505512587373e-05, + "loss": 0.0271, + "step": 9549 + }, + { + "epoch": 8.45, + "learning_rate": 1.294918195115379e-05, + "loss": 0.0263, + "step": 9550 + }, + { + "epoch": 8.45, + "learning_rate": 1.2947812583002597e-05, + "loss": 0.0351, + "step": 9551 + }, + { + "epoch": 8.45, + "learning_rate": 1.2946443154311847e-05, + "loss": 0.0318, + "step": 9552 + }, + { + "epoch": 8.45, + "learning_rate": 1.2945073665109656e-05, + "loss": 0.03, + "step": 9553 + }, + { + "epoch": 8.45, + "learning_rate": 1.2943704115424153e-05, + "loss": 0.0288, + "step": 9554 + }, + { + "epoch": 8.45, + "learning_rate": 1.2942334505283469e-05, + "loss": 0.0302, + "step": 9555 + }, + { + "epoch": 8.45, + "learning_rate": 1.2940964834715723e-05, + "loss": 0.028, + "step": 9556 + }, + { + "epoch": 8.46, + "learning_rate": 1.2939595103749054e-05, + "loss": 0.0259, + "step": 9557 + }, + { + "epoch": 8.46, + "learning_rate": 1.2938225312411585e-05, + "loss": 0.024, + "step": 9558 + }, + { + "epoch": 8.46, + "learning_rate": 1.2936855460731452e-05, + "loss": 0.0278, + "step": 9559 + }, + { + "epoch": 8.46, + "learning_rate": 1.2935485548736785e-05, + "loss": 0.028, + "step": 9560 + }, + { + "epoch": 8.46, + "learning_rate": 1.2934115576455717e-05, + "loss": 0.0275, + "step": 9561 + }, + { + "epoch": 8.46, + "learning_rate": 1.2932745543916387e-05, + "loss": 0.0296, + "step": 9562 + }, + { + "epoch": 8.46, + "learning_rate": 1.2931375451146928e-05, + "loss": 0.0282, + "step": 9563 + }, + { + "epoch": 8.46, + "learning_rate": 1.2930005298175481e-05, + "loss": 0.0335, + "step": 9564 + }, + { + "epoch": 8.46, + "learning_rate": 1.2928635085030183e-05, + "loss": 0.0321, + "step": 9565 + }, + { + "epoch": 8.46, + "learning_rate": 1.2927264811739175e-05, + "loss": 0.0301, + "step": 9566 + }, + { + "epoch": 8.46, + "learning_rate": 1.2925894478330598e-05, + "loss": 0.0243, + "step": 9567 + }, + { + "epoch": 8.47, + "learning_rate": 1.2924524084832595e-05, + "loss": 0.0305, + "step": 9568 + }, + { + "epoch": 8.47, + "learning_rate": 1.2923153631273306e-05, + "loss": 0.0232, + "step": 9569 + }, + { + "epoch": 8.47, + "learning_rate": 1.2921783117680887e-05, + "loss": 0.0284, + "step": 9570 + }, + { + "epoch": 8.47, + "learning_rate": 1.2920412544083472e-05, + "loss": 0.0256, + "step": 9571 + }, + { + "epoch": 8.47, + "learning_rate": 1.2919041910509213e-05, + "loss": 0.036, + "step": 9572 + }, + { + "epoch": 8.47, + "learning_rate": 1.291767121698626e-05, + "loss": 0.035, + "step": 9573 + }, + { + "epoch": 8.47, + "learning_rate": 1.2916300463542769e-05, + "loss": 0.0245, + "step": 9574 + }, + { + "epoch": 8.47, + "learning_rate": 1.291492965020688e-05, + "loss": 0.0267, + "step": 9575 + }, + { + "epoch": 8.47, + "learning_rate": 1.291355877700675e-05, + "loss": 0.0287, + "step": 9576 + }, + { + "epoch": 8.47, + "learning_rate": 1.2912187843970536e-05, + "loss": 0.0278, + "step": 9577 + }, + { + "epoch": 8.47, + "learning_rate": 1.2910816851126389e-05, + "loss": 0.031, + "step": 9578 + }, + { + "epoch": 8.48, + "learning_rate": 1.2909445798502467e-05, + "loss": 0.0325, + "step": 9579 + }, + { + "epoch": 8.48, + "learning_rate": 1.2908074686126926e-05, + "loss": 0.0287, + "step": 9580 + }, + { + "epoch": 8.48, + "learning_rate": 1.290670351402793e-05, + "loss": 0.0323, + "step": 9581 + }, + { + "epoch": 8.48, + "learning_rate": 1.2905332282233629e-05, + "loss": 0.0267, + "step": 9582 + }, + { + "epoch": 8.48, + "learning_rate": 1.2903960990772193e-05, + "loss": 0.0301, + "step": 9583 + }, + { + "epoch": 8.48, + "learning_rate": 1.2902589639671783e-05, + "loss": 0.0239, + "step": 9584 + }, + { + "epoch": 8.48, + "learning_rate": 1.2901218228960556e-05, + "loss": 0.025, + "step": 9585 + }, + { + "epoch": 8.48, + "learning_rate": 1.2899846758666685e-05, + "loss": 0.0322, + "step": 9586 + }, + { + "epoch": 8.48, + "learning_rate": 1.2898475228818333e-05, + "loss": 0.0256, + "step": 9587 + }, + { + "epoch": 8.48, + "learning_rate": 1.2897103639443666e-05, + "loss": 0.0276, + "step": 9588 + }, + { + "epoch": 8.48, + "learning_rate": 1.2895731990570855e-05, + "loss": 0.0281, + "step": 9589 + }, + { + "epoch": 8.48, + "learning_rate": 1.2894360282228065e-05, + "loss": 0.0265, + "step": 9590 + }, + { + "epoch": 8.49, + "learning_rate": 1.2892988514443474e-05, + "loss": 0.0291, + "step": 9591 + }, + { + "epoch": 8.49, + "learning_rate": 1.2891616687245248e-05, + "loss": 0.0318, + "step": 9592 + }, + { + "epoch": 8.49, + "learning_rate": 1.2890244800661562e-05, + "loss": 0.0259, + "step": 9593 + }, + { + "epoch": 8.49, + "learning_rate": 1.2888872854720592e-05, + "loss": 0.0288, + "step": 9594 + }, + { + "epoch": 8.49, + "learning_rate": 1.2887500849450515e-05, + "loss": 0.0358, + "step": 9595 + }, + { + "epoch": 8.49, + "learning_rate": 1.2886128784879504e-05, + "loss": 0.0285, + "step": 9596 + }, + { + "epoch": 8.49, + "learning_rate": 1.2884756661035737e-05, + "loss": 0.0295, + "step": 9597 + }, + { + "epoch": 8.49, + "learning_rate": 1.2883384477947401e-05, + "loss": 0.0298, + "step": 9598 + }, + { + "epoch": 8.49, + "learning_rate": 1.288201223564267e-05, + "loss": 0.0283, + "step": 9599 + }, + { + "epoch": 8.49, + "learning_rate": 1.2880639934149725e-05, + "loss": 0.0301, + "step": 9600 + }, + { + "epoch": 8.49, + "learning_rate": 1.2879267573496752e-05, + "loss": 0.0231, + "step": 9601 + }, + { + "epoch": 8.5, + "learning_rate": 1.2877895153711935e-05, + "loss": 0.0219, + "step": 9602 + }, + { + "epoch": 8.5, + "learning_rate": 1.2876522674823461e-05, + "loss": 0.0287, + "step": 9603 + }, + { + "epoch": 8.5, + "learning_rate": 1.2875150136859513e-05, + "loss": 0.0313, + "step": 9604 + }, + { + "epoch": 8.5, + "learning_rate": 1.2873777539848284e-05, + "loss": 0.0339, + "step": 9605 + }, + { + "epoch": 8.5, + "learning_rate": 1.2872404883817957e-05, + "loss": 0.031, + "step": 9606 + }, + { + "epoch": 8.5, + "learning_rate": 1.2871032168796726e-05, + "loss": 0.0313, + "step": 9607 + }, + { + "epoch": 8.5, + "learning_rate": 1.2869659394812783e-05, + "loss": 0.0232, + "step": 9608 + }, + { + "epoch": 8.5, + "learning_rate": 1.286828656189432e-05, + "loss": 0.0277, + "step": 9609 + }, + { + "epoch": 8.5, + "learning_rate": 1.2866913670069532e-05, + "loss": 0.0267, + "step": 9610 + }, + { + "epoch": 8.5, + "learning_rate": 1.2865540719366612e-05, + "loss": 0.0304, + "step": 9611 + }, + { + "epoch": 8.5, + "learning_rate": 1.286416770981376e-05, + "loss": 0.0272, + "step": 9612 + }, + { + "epoch": 8.51, + "learning_rate": 1.2862794641439169e-05, + "loss": 0.0256, + "step": 9613 + }, + { + "epoch": 8.51, + "learning_rate": 1.2861421514271042e-05, + "loss": 0.0254, + "step": 9614 + }, + { + "epoch": 8.51, + "learning_rate": 1.2860048328337575e-05, + "loss": 0.0288, + "step": 9615 + }, + { + "epoch": 8.51, + "learning_rate": 1.2858675083666975e-05, + "loss": 0.0295, + "step": 9616 + }, + { + "epoch": 8.51, + "learning_rate": 1.2857301780287436e-05, + "loss": 0.0321, + "step": 9617 + }, + { + "epoch": 8.51, + "learning_rate": 1.2855928418227171e-05, + "loss": 0.0347, + "step": 9618 + }, + { + "epoch": 8.51, + "learning_rate": 1.285455499751438e-05, + "loss": 0.0272, + "step": 9619 + }, + { + "epoch": 8.51, + "learning_rate": 1.285318151817727e-05, + "loss": 0.0292, + "step": 9620 + }, + { + "epoch": 8.51, + "learning_rate": 1.2851807980244044e-05, + "loss": 0.0244, + "step": 9621 + }, + { + "epoch": 8.51, + "learning_rate": 1.285043438374292e-05, + "loss": 0.0261, + "step": 9622 + }, + { + "epoch": 8.51, + "learning_rate": 1.2849060728702098e-05, + "loss": 0.0266, + "step": 9623 + }, + { + "epoch": 8.52, + "learning_rate": 1.2847687015149796e-05, + "loss": 0.0318, + "step": 9624 + }, + { + "epoch": 8.52, + "learning_rate": 1.284631324311422e-05, + "loss": 0.0267, + "step": 9625 + }, + { + "epoch": 8.52, + "learning_rate": 1.2844939412623592e-05, + "loss": 0.0328, + "step": 9626 + }, + { + "epoch": 8.52, + "learning_rate": 1.2843565523706119e-05, + "loss": 0.0306, + "step": 9627 + }, + { + "epoch": 8.52, + "learning_rate": 1.2842191576390016e-05, + "loss": 0.0293, + "step": 9628 + }, + { + "epoch": 8.52, + "learning_rate": 1.2840817570703506e-05, + "loss": 0.032, + "step": 9629 + }, + { + "epoch": 8.52, + "learning_rate": 1.2839443506674803e-05, + "loss": 0.0258, + "step": 9630 + }, + { + "epoch": 8.52, + "learning_rate": 1.2838069384332127e-05, + "loss": 0.0306, + "step": 9631 + }, + { + "epoch": 8.52, + "learning_rate": 1.2836695203703697e-05, + "loss": 0.028, + "step": 9632 + }, + { + "epoch": 8.52, + "learning_rate": 1.2835320964817739e-05, + "loss": 0.0268, + "step": 9633 + }, + { + "epoch": 8.52, + "learning_rate": 1.283394666770247e-05, + "loss": 0.0327, + "step": 9634 + }, + { + "epoch": 8.52, + "learning_rate": 1.283257231238612e-05, + "loss": 0.0268, + "step": 9635 + }, + { + "epoch": 8.53, + "learning_rate": 1.2831197898896912e-05, + "loss": 0.0322, + "step": 9636 + }, + { + "epoch": 8.53, + "learning_rate": 1.2829823427263071e-05, + "loss": 0.029, + "step": 9637 + }, + { + "epoch": 8.53, + "learning_rate": 1.2828448897512826e-05, + "loss": 0.0319, + "step": 9638 + }, + { + "epoch": 8.53, + "learning_rate": 1.2827074309674405e-05, + "loss": 0.0381, + "step": 9639 + }, + { + "epoch": 8.53, + "learning_rate": 1.2825699663776043e-05, + "loss": 0.0304, + "step": 9640 + }, + { + "epoch": 8.53, + "learning_rate": 1.282432495984596e-05, + "loss": 0.0331, + "step": 9641 + }, + { + "epoch": 8.53, + "learning_rate": 1.2822950197912398e-05, + "loss": 0.032, + "step": 9642 + }, + { + "epoch": 8.53, + "learning_rate": 1.2821575378003592e-05, + "loss": 0.0319, + "step": 9643 + }, + { + "epoch": 8.53, + "learning_rate": 1.2820200500147771e-05, + "loss": 0.031, + "step": 9644 + }, + { + "epoch": 8.53, + "learning_rate": 1.2818825564373169e-05, + "loss": 0.0322, + "step": 9645 + }, + { + "epoch": 8.53, + "learning_rate": 1.2817450570708032e-05, + "loss": 0.0273, + "step": 9646 + }, + { + "epoch": 8.54, + "learning_rate": 1.281607551918059e-05, + "loss": 0.0258, + "step": 9647 + }, + { + "epoch": 8.54, + "learning_rate": 1.2814700409819088e-05, + "loss": 0.0293, + "step": 9648 + }, + { + "epoch": 8.54, + "learning_rate": 1.2813325242651766e-05, + "loss": 0.0306, + "step": 9649 + }, + { + "epoch": 8.54, + "learning_rate": 1.2811950017706865e-05, + "loss": 0.0287, + "step": 9650 + }, + { + "epoch": 8.54, + "learning_rate": 1.2810574735012626e-05, + "loss": 0.0362, + "step": 9651 + }, + { + "epoch": 8.54, + "learning_rate": 1.2809199394597297e-05, + "loss": 0.0233, + "step": 9652 + }, + { + "epoch": 8.54, + "learning_rate": 1.280782399648912e-05, + "loss": 0.0281, + "step": 9653 + }, + { + "epoch": 8.54, + "learning_rate": 1.2806448540716344e-05, + "loss": 0.0346, + "step": 9654 + }, + { + "epoch": 8.54, + "learning_rate": 1.2805073027307217e-05, + "loss": 0.0305, + "step": 9655 + }, + { + "epoch": 8.54, + "learning_rate": 1.2803697456289987e-05, + "loss": 0.0284, + "step": 9656 + }, + { + "epoch": 8.54, + "learning_rate": 1.2802321827692907e-05, + "loss": 0.0278, + "step": 9657 + }, + { + "epoch": 8.55, + "learning_rate": 1.2800946141544226e-05, + "loss": 0.0331, + "step": 9658 + }, + { + "epoch": 8.55, + "learning_rate": 1.2799570397872197e-05, + "loss": 0.0302, + "step": 9659 + }, + { + "epoch": 8.55, + "learning_rate": 1.2798194596705071e-05, + "loss": 0.0317, + "step": 9660 + }, + { + "epoch": 8.55, + "learning_rate": 1.2796818738071108e-05, + "loss": 0.0301, + "step": 9661 + }, + { + "epoch": 8.55, + "learning_rate": 1.2795442821998561e-05, + "loss": 0.0271, + "step": 9662 + }, + { + "epoch": 8.55, + "learning_rate": 1.2794066848515687e-05, + "loss": 0.0309, + "step": 9663 + }, + { + "epoch": 8.55, + "learning_rate": 1.279269081765075e-05, + "loss": 0.0285, + "step": 9664 + }, + { + "epoch": 8.55, + "learning_rate": 1.2791314729432001e-05, + "loss": 0.03, + "step": 9665 + }, + { + "epoch": 8.55, + "learning_rate": 1.2789938583887707e-05, + "loss": 0.0309, + "step": 9666 + }, + { + "epoch": 8.55, + "learning_rate": 1.2788562381046127e-05, + "loss": 0.0287, + "step": 9667 + }, + { + "epoch": 8.55, + "learning_rate": 1.2787186120935529e-05, + "loss": 0.0288, + "step": 9668 + }, + { + "epoch": 8.55, + "learning_rate": 1.278580980358417e-05, + "loss": 0.0285, + "step": 9669 + }, + { + "epoch": 8.56, + "learning_rate": 1.278443342902032e-05, + "loss": 0.0264, + "step": 9670 + }, + { + "epoch": 8.56, + "learning_rate": 1.278305699727225e-05, + "loss": 0.0286, + "step": 9671 + }, + { + "epoch": 8.56, + "learning_rate": 1.278168050836822e-05, + "loss": 0.0304, + "step": 9672 + }, + { + "epoch": 8.56, + "learning_rate": 1.2780303962336502e-05, + "loss": 0.0288, + "step": 9673 + }, + { + "epoch": 8.56, + "learning_rate": 1.2778927359205366e-05, + "loss": 0.0315, + "step": 9674 + }, + { + "epoch": 8.56, + "learning_rate": 1.2777550699003085e-05, + "loss": 0.0324, + "step": 9675 + }, + { + "epoch": 8.56, + "learning_rate": 1.2776173981757931e-05, + "loss": 0.0318, + "step": 9676 + }, + { + "epoch": 8.56, + "learning_rate": 1.2774797207498178e-05, + "loss": 0.0309, + "step": 9677 + }, + { + "epoch": 8.56, + "learning_rate": 1.2773420376252101e-05, + "loss": 0.0252, + "step": 9678 + }, + { + "epoch": 8.56, + "learning_rate": 1.2772043488047973e-05, + "loss": 0.0346, + "step": 9679 + }, + { + "epoch": 8.56, + "learning_rate": 1.2770666542914073e-05, + "loss": 0.0261, + "step": 9680 + }, + { + "epoch": 8.57, + "learning_rate": 1.2769289540878687e-05, + "loss": 0.0274, + "step": 9681 + }, + { + "epoch": 8.57, + "learning_rate": 1.2767912481970083e-05, + "loss": 0.0255, + "step": 9682 + }, + { + "epoch": 8.57, + "learning_rate": 1.2766535366216548e-05, + "loss": 0.0326, + "step": 9683 + }, + { + "epoch": 8.57, + "learning_rate": 1.2765158193646363e-05, + "loss": 0.0299, + "step": 9684 + }, + { + "epoch": 8.57, + "learning_rate": 1.2763780964287813e-05, + "loss": 0.0309, + "step": 9685 + }, + { + "epoch": 8.57, + "learning_rate": 1.276240367816918e-05, + "loss": 0.0258, + "step": 9686 + }, + { + "epoch": 8.57, + "learning_rate": 1.2761026335318744e-05, + "loss": 0.0281, + "step": 9687 + }, + { + "epoch": 8.57, + "learning_rate": 1.2759648935764802e-05, + "loss": 0.0282, + "step": 9688 + }, + { + "epoch": 8.57, + "learning_rate": 1.275827147953564e-05, + "loss": 0.0298, + "step": 9689 + }, + { + "epoch": 8.57, + "learning_rate": 1.275689396665954e-05, + "loss": 0.0299, + "step": 9690 + }, + { + "epoch": 8.57, + "learning_rate": 1.2755516397164798e-05, + "loss": 0.0284, + "step": 9691 + }, + { + "epoch": 8.58, + "learning_rate": 1.2754138771079706e-05, + "loss": 0.0345, + "step": 9692 + }, + { + "epoch": 8.58, + "learning_rate": 1.2752761088432548e-05, + "loss": 0.0331, + "step": 9693 + }, + { + "epoch": 8.58, + "learning_rate": 1.275138334925163e-05, + "loss": 0.0319, + "step": 9694 + }, + { + "epoch": 8.58, + "learning_rate": 1.2750005553565235e-05, + "loss": 0.0331, + "step": 9695 + }, + { + "epoch": 8.58, + "learning_rate": 1.274862770140167e-05, + "loss": 0.0363, + "step": 9696 + }, + { + "epoch": 8.58, + "learning_rate": 1.2747249792789225e-05, + "loss": 0.0268, + "step": 9697 + }, + { + "epoch": 8.58, + "learning_rate": 1.2745871827756197e-05, + "loss": 0.0305, + "step": 9698 + }, + { + "epoch": 8.58, + "learning_rate": 1.274449380633089e-05, + "loss": 0.0367, + "step": 9699 + }, + { + "epoch": 8.58, + "learning_rate": 1.2743115728541604e-05, + "loss": 0.0291, + "step": 9700 + }, + { + "epoch": 8.58, + "learning_rate": 1.274173759441664e-05, + "loss": 0.027, + "step": 9701 + }, + { + "epoch": 8.58, + "learning_rate": 1.2740359403984299e-05, + "loss": 0.0314, + "step": 9702 + }, + { + "epoch": 8.58, + "learning_rate": 1.2738981157272887e-05, + "loss": 0.0293, + "step": 9703 + }, + { + "epoch": 8.59, + "learning_rate": 1.273760285431071e-05, + "loss": 0.0316, + "step": 9704 + }, + { + "epoch": 8.59, + "learning_rate": 1.2736224495126073e-05, + "loss": 0.0301, + "step": 9705 + }, + { + "epoch": 8.59, + "learning_rate": 1.2734846079747283e-05, + "loss": 0.0326, + "step": 9706 + }, + { + "epoch": 8.59, + "learning_rate": 1.2733467608202647e-05, + "loss": 0.0339, + "step": 9707 + }, + { + "epoch": 8.59, + "learning_rate": 1.273208908052048e-05, + "loss": 0.0265, + "step": 9708 + }, + { + "epoch": 8.59, + "learning_rate": 1.2730710496729088e-05, + "loss": 0.0327, + "step": 9709 + }, + { + "epoch": 8.59, + "learning_rate": 1.272933185685679e-05, + "loss": 0.0317, + "step": 9710 + }, + { + "epoch": 8.59, + "learning_rate": 1.272795316093189e-05, + "loss": 0.0275, + "step": 9711 + }, + { + "epoch": 8.59, + "learning_rate": 1.272657440898271e-05, + "loss": 0.033, + "step": 9712 + }, + { + "epoch": 8.59, + "learning_rate": 1.2725195601037558e-05, + "loss": 0.0243, + "step": 9713 + }, + { + "epoch": 8.59, + "learning_rate": 1.272381673712476e-05, + "loss": 0.0321, + "step": 9714 + }, + { + "epoch": 8.6, + "learning_rate": 1.2722437817272626e-05, + "loss": 0.0281, + "step": 9715 + }, + { + "epoch": 8.6, + "learning_rate": 1.2721058841509482e-05, + "loss": 0.0346, + "step": 9716 + }, + { + "epoch": 8.6, + "learning_rate": 1.2719679809863643e-05, + "loss": 0.0245, + "step": 9717 + }, + { + "epoch": 8.6, + "learning_rate": 1.2718300722363431e-05, + "loss": 0.0323, + "step": 9718 + }, + { + "epoch": 8.6, + "learning_rate": 1.2716921579037167e-05, + "loss": 0.0271, + "step": 9719 + }, + { + "epoch": 8.6, + "learning_rate": 1.271554237991318e-05, + "loss": 0.0292, + "step": 9720 + }, + { + "epoch": 8.6, + "learning_rate": 1.2714163125019791e-05, + "loss": 0.0285, + "step": 9721 + }, + { + "epoch": 8.6, + "learning_rate": 1.2712783814385326e-05, + "loss": 0.0292, + "step": 9722 + }, + { + "epoch": 8.6, + "learning_rate": 1.2711404448038112e-05, + "loss": 0.0265, + "step": 9723 + }, + { + "epoch": 8.6, + "learning_rate": 1.271002502600648e-05, + "loss": 0.0319, + "step": 9724 + }, + { + "epoch": 8.6, + "learning_rate": 1.2708645548318757e-05, + "loss": 0.0325, + "step": 9725 + }, + { + "epoch": 8.61, + "learning_rate": 1.270726601500327e-05, + "loss": 0.0325, + "step": 9726 + }, + { + "epoch": 8.61, + "learning_rate": 1.2705886426088359e-05, + "loss": 0.0364, + "step": 9727 + }, + { + "epoch": 8.61, + "learning_rate": 1.270450678160235e-05, + "loss": 0.0301, + "step": 9728 + }, + { + "epoch": 8.61, + "learning_rate": 1.2703127081573578e-05, + "loss": 0.0288, + "step": 9729 + }, + { + "epoch": 8.61, + "learning_rate": 1.2701747326030379e-05, + "loss": 0.0318, + "step": 9730 + }, + { + "epoch": 8.61, + "learning_rate": 1.2700367515001093e-05, + "loss": 0.0291, + "step": 9731 + }, + { + "epoch": 8.61, + "learning_rate": 1.2698987648514046e-05, + "loss": 0.0248, + "step": 9732 + }, + { + "epoch": 8.61, + "learning_rate": 1.2697607726597589e-05, + "loss": 0.0337, + "step": 9733 + }, + { + "epoch": 8.61, + "learning_rate": 1.2696227749280059e-05, + "loss": 0.0357, + "step": 9734 + }, + { + "epoch": 8.61, + "learning_rate": 1.2694847716589791e-05, + "loss": 0.0305, + "step": 9735 + }, + { + "epoch": 8.61, + "learning_rate": 1.2693467628555131e-05, + "loss": 0.0315, + "step": 9736 + }, + { + "epoch": 8.62, + "learning_rate": 1.269208748520442e-05, + "loss": 0.027, + "step": 9737 + }, + { + "epoch": 8.62, + "learning_rate": 1.2690707286566006e-05, + "loss": 0.0323, + "step": 9738 + }, + { + "epoch": 8.62, + "learning_rate": 1.268932703266823e-05, + "loss": 0.0324, + "step": 9739 + }, + { + "epoch": 8.62, + "learning_rate": 1.268794672353944e-05, + "loss": 0.0264, + "step": 9740 + }, + { + "epoch": 8.62, + "learning_rate": 1.2686566359207986e-05, + "loss": 0.0297, + "step": 9741 + }, + { + "epoch": 8.62, + "learning_rate": 1.2685185939702213e-05, + "loss": 0.0309, + "step": 9742 + }, + { + "epoch": 8.62, + "learning_rate": 1.2683805465050472e-05, + "loss": 0.0298, + "step": 9743 + }, + { + "epoch": 8.62, + "learning_rate": 1.2682424935281112e-05, + "loss": 0.0309, + "step": 9744 + }, + { + "epoch": 8.62, + "learning_rate": 1.2681044350422492e-05, + "loss": 0.0372, + "step": 9745 + }, + { + "epoch": 8.62, + "learning_rate": 1.2679663710502956e-05, + "loss": 0.0311, + "step": 9746 + }, + { + "epoch": 8.62, + "learning_rate": 1.2678283015550865e-05, + "loss": 0.0337, + "step": 9747 + }, + { + "epoch": 8.62, + "learning_rate": 1.2676902265594575e-05, + "loss": 0.0377, + "step": 9748 + }, + { + "epoch": 8.63, + "learning_rate": 1.267552146066244e-05, + "loss": 0.0319, + "step": 9749 + }, + { + "epoch": 8.63, + "learning_rate": 1.2674140600782811e-05, + "loss": 0.0308, + "step": 9750 + }, + { + "epoch": 8.63, + "learning_rate": 1.267275968598406e-05, + "loss": 0.0318, + "step": 9751 + }, + { + "epoch": 8.63, + "learning_rate": 1.2671378716294539e-05, + "loss": 0.0318, + "step": 9752 + }, + { + "epoch": 8.63, + "learning_rate": 1.266999769174261e-05, + "loss": 0.0323, + "step": 9753 + }, + { + "epoch": 8.63, + "learning_rate": 1.2668616612356636e-05, + "loss": 0.0312, + "step": 9754 + }, + { + "epoch": 8.63, + "learning_rate": 1.2667235478164983e-05, + "loss": 0.0285, + "step": 9755 + }, + { + "epoch": 8.63, + "learning_rate": 1.266585428919601e-05, + "loss": 0.0269, + "step": 9756 + }, + { + "epoch": 8.63, + "learning_rate": 1.2664473045478087e-05, + "loss": 0.0354, + "step": 9757 + }, + { + "epoch": 8.63, + "learning_rate": 1.2663091747039577e-05, + "loss": 0.0337, + "step": 9758 + }, + { + "epoch": 8.63, + "learning_rate": 1.2661710393908852e-05, + "loss": 0.0273, + "step": 9759 + }, + { + "epoch": 8.64, + "learning_rate": 1.2660328986114281e-05, + "loss": 0.0341, + "step": 9760 + }, + { + "epoch": 8.64, + "learning_rate": 1.2658947523684229e-05, + "loss": 0.0289, + "step": 9761 + }, + { + "epoch": 8.64, + "learning_rate": 1.2657566006647075e-05, + "loss": 0.0297, + "step": 9762 + }, + { + "epoch": 8.64, + "learning_rate": 1.2656184435031182e-05, + "loss": 0.032, + "step": 9763 + }, + { + "epoch": 8.64, + "learning_rate": 1.2654802808864933e-05, + "loss": 0.0325, + "step": 9764 + }, + { + "epoch": 8.64, + "learning_rate": 1.2653421128176696e-05, + "loss": 0.0364, + "step": 9765 + }, + { + "epoch": 8.64, + "learning_rate": 1.2652039392994846e-05, + "loss": 0.031, + "step": 9766 + }, + { + "epoch": 8.64, + "learning_rate": 1.2650657603347765e-05, + "loss": 0.0286, + "step": 9767 + }, + { + "epoch": 8.64, + "learning_rate": 1.2649275759263828e-05, + "loss": 0.0253, + "step": 9768 + }, + { + "epoch": 8.64, + "learning_rate": 1.2647893860771419e-05, + "loss": 0.0324, + "step": 9769 + }, + { + "epoch": 8.64, + "learning_rate": 1.2646511907898909e-05, + "loss": 0.0308, + "step": 9770 + }, + { + "epoch": 8.65, + "learning_rate": 1.2645129900674685e-05, + "loss": 0.033, + "step": 9771 + }, + { + "epoch": 8.65, + "learning_rate": 1.2643747839127132e-05, + "loss": 0.0348, + "step": 9772 + }, + { + "epoch": 8.65, + "learning_rate": 1.2642365723284626e-05, + "loss": 0.0282, + "step": 9773 + }, + { + "epoch": 8.65, + "learning_rate": 1.2640983553175556e-05, + "loss": 0.0325, + "step": 9774 + }, + { + "epoch": 8.65, + "learning_rate": 1.263960132882831e-05, + "loss": 0.0294, + "step": 9775 + }, + { + "epoch": 8.65, + "learning_rate": 1.2638219050271274e-05, + "loss": 0.0253, + "step": 9776 + }, + { + "epoch": 8.65, + "learning_rate": 1.2636836717532832e-05, + "loss": 0.0276, + "step": 9777 + }, + { + "epoch": 8.65, + "learning_rate": 1.2635454330641375e-05, + "loss": 0.0304, + "step": 9778 + }, + { + "epoch": 8.65, + "learning_rate": 1.2634071889625297e-05, + "loss": 0.0291, + "step": 9779 + }, + { + "epoch": 8.65, + "learning_rate": 1.2632689394512983e-05, + "loss": 0.0313, + "step": 9780 + }, + { + "epoch": 8.65, + "learning_rate": 1.2631306845332832e-05, + "loss": 0.028, + "step": 9781 + }, + { + "epoch": 8.65, + "learning_rate": 1.2629924242113231e-05, + "loss": 0.0289, + "step": 9782 + }, + { + "epoch": 8.66, + "learning_rate": 1.262854158488258e-05, + "loss": 0.028, + "step": 9783 + }, + { + "epoch": 8.66, + "learning_rate": 1.2627158873669272e-05, + "loss": 0.0261, + "step": 9784 + }, + { + "epoch": 8.66, + "learning_rate": 1.2625776108501703e-05, + "loss": 0.0318, + "step": 9785 + }, + { + "epoch": 8.66, + "learning_rate": 1.262439328940828e-05, + "loss": 0.0311, + "step": 9786 + }, + { + "epoch": 8.66, + "learning_rate": 1.2623010416417389e-05, + "loss": 0.0307, + "step": 9787 + }, + { + "epoch": 8.66, + "learning_rate": 1.2621627489557435e-05, + "loss": 0.0266, + "step": 9788 + }, + { + "epoch": 8.66, + "learning_rate": 1.2620244508856822e-05, + "loss": 0.0262, + "step": 9789 + }, + { + "epoch": 8.66, + "learning_rate": 1.2618861474343953e-05, + "loss": 0.0297, + "step": 9790 + }, + { + "epoch": 8.66, + "learning_rate": 1.2617478386047225e-05, + "loss": 0.0301, + "step": 9791 + }, + { + "epoch": 8.66, + "learning_rate": 1.2616095243995048e-05, + "loss": 0.0323, + "step": 9792 + }, + { + "epoch": 8.66, + "learning_rate": 1.2614712048215832e-05, + "loss": 0.0276, + "step": 9793 + }, + { + "epoch": 8.67, + "learning_rate": 1.2613328798737975e-05, + "loss": 0.0301, + "step": 9794 + }, + { + "epoch": 8.67, + "learning_rate": 1.2611945495589885e-05, + "loss": 0.0317, + "step": 9795 + }, + { + "epoch": 8.67, + "learning_rate": 1.2610562138799977e-05, + "loss": 0.0335, + "step": 9796 + }, + { + "epoch": 8.67, + "learning_rate": 1.260917872839666e-05, + "loss": 0.0282, + "step": 9797 + }, + { + "epoch": 8.67, + "learning_rate": 1.2607795264408344e-05, + "loss": 0.0288, + "step": 9798 + }, + { + "epoch": 8.67, + "learning_rate": 1.2606411746863441e-05, + "loss": 0.0308, + "step": 9799 + }, + { + "epoch": 8.67, + "learning_rate": 1.2605028175790365e-05, + "loss": 0.0337, + "step": 9800 + }, + { + "epoch": 8.67, + "learning_rate": 1.260364455121753e-05, + "loss": 0.0372, + "step": 9801 + }, + { + "epoch": 8.67, + "learning_rate": 1.2602260873173352e-05, + "loss": 0.0271, + "step": 9802 + }, + { + "epoch": 8.67, + "learning_rate": 1.2600877141686247e-05, + "loss": 0.0272, + "step": 9803 + }, + { + "epoch": 8.67, + "learning_rate": 1.2599493356784636e-05, + "loss": 0.0334, + "step": 9804 + }, + { + "epoch": 8.68, + "learning_rate": 1.2598109518496933e-05, + "loss": 0.0361, + "step": 9805 + }, + { + "epoch": 8.68, + "learning_rate": 1.259672562685156e-05, + "loss": 0.0316, + "step": 9806 + }, + { + "epoch": 8.68, + "learning_rate": 1.2595341681876942e-05, + "loss": 0.0306, + "step": 9807 + }, + { + "epoch": 8.68, + "learning_rate": 1.2593957683601497e-05, + "loss": 0.0321, + "step": 9808 + }, + { + "epoch": 8.68, + "learning_rate": 1.2592573632053649e-05, + "loss": 0.0274, + "step": 9809 + }, + { + "epoch": 8.68, + "learning_rate": 1.2591189527261818e-05, + "loss": 0.0337, + "step": 9810 + }, + { + "epoch": 8.68, + "learning_rate": 1.258980536925444e-05, + "loss": 0.0288, + "step": 9811 + }, + { + "epoch": 8.68, + "learning_rate": 1.2588421158059933e-05, + "loss": 0.0327, + "step": 9812 + }, + { + "epoch": 8.68, + "learning_rate": 1.258703689370673e-05, + "loss": 0.0333, + "step": 9813 + }, + { + "epoch": 8.68, + "learning_rate": 1.2585652576223257e-05, + "loss": 0.0318, + "step": 9814 + }, + { + "epoch": 8.68, + "learning_rate": 1.2584268205637944e-05, + "loss": 0.0352, + "step": 9815 + }, + { + "epoch": 8.68, + "learning_rate": 1.2582883781979222e-05, + "loss": 0.0339, + "step": 9816 + }, + { + "epoch": 8.69, + "learning_rate": 1.258149930527552e-05, + "loss": 0.0357, + "step": 9817 + }, + { + "epoch": 8.69, + "learning_rate": 1.258011477555528e-05, + "loss": 0.0322, + "step": 9818 + }, + { + "epoch": 8.69, + "learning_rate": 1.2578730192846926e-05, + "loss": 0.0274, + "step": 9819 + }, + { + "epoch": 8.69, + "learning_rate": 1.2577345557178902e-05, + "loss": 0.0393, + "step": 9820 + }, + { + "epoch": 8.69, + "learning_rate": 1.2575960868579638e-05, + "loss": 0.0315, + "step": 9821 + }, + { + "epoch": 8.69, + "learning_rate": 1.2574576127077576e-05, + "loss": 0.0334, + "step": 9822 + }, + { + "epoch": 8.69, + "learning_rate": 1.2573191332701149e-05, + "loss": 0.0302, + "step": 9823 + }, + { + "epoch": 8.69, + "learning_rate": 1.25718064854788e-05, + "loss": 0.0343, + "step": 9824 + }, + { + "epoch": 8.69, + "learning_rate": 1.2570421585438975e-05, + "loss": 0.0309, + "step": 9825 + }, + { + "epoch": 8.69, + "learning_rate": 1.2569036632610107e-05, + "loss": 0.0311, + "step": 9826 + }, + { + "epoch": 8.69, + "learning_rate": 1.2567651627020645e-05, + "loss": 0.0283, + "step": 9827 + }, + { + "epoch": 8.7, + "learning_rate": 1.2566266568699028e-05, + "loss": 0.0297, + "step": 9828 + }, + { + "epoch": 8.7, + "learning_rate": 1.2564881457673708e-05, + "loss": 0.0313, + "step": 9829 + }, + { + "epoch": 8.7, + "learning_rate": 1.2563496293973122e-05, + "loss": 0.0283, + "step": 9830 + }, + { + "epoch": 8.7, + "learning_rate": 1.2562111077625723e-05, + "loss": 0.032, + "step": 9831 + }, + { + "epoch": 8.7, + "learning_rate": 1.2560725808659964e-05, + "loss": 0.0358, + "step": 9832 + }, + { + "epoch": 8.7, + "learning_rate": 1.2559340487104285e-05, + "loss": 0.0335, + "step": 9833 + }, + { + "epoch": 8.7, + "learning_rate": 1.2557955112987142e-05, + "loss": 0.0277, + "step": 9834 + }, + { + "epoch": 8.7, + "learning_rate": 1.2556569686336982e-05, + "loss": 0.0285, + "step": 9835 + }, + { + "epoch": 8.7, + "learning_rate": 1.2555184207182264e-05, + "loss": 0.0303, + "step": 9836 + }, + { + "epoch": 8.7, + "learning_rate": 1.2553798675551437e-05, + "loss": 0.0342, + "step": 9837 + }, + { + "epoch": 8.7, + "learning_rate": 1.2552413091472957e-05, + "loss": 0.0311, + "step": 9838 + }, + { + "epoch": 8.71, + "learning_rate": 1.2551027454975282e-05, + "loss": 0.0335, + "step": 9839 + }, + { + "epoch": 8.71, + "learning_rate": 1.2549641766086867e-05, + "loss": 0.0297, + "step": 9840 + }, + { + "epoch": 8.71, + "learning_rate": 1.254825602483617e-05, + "loss": 0.0274, + "step": 9841 + }, + { + "epoch": 8.71, + "learning_rate": 1.2546870231251651e-05, + "loss": 0.0332, + "step": 9842 + }, + { + "epoch": 8.71, + "learning_rate": 1.2545484385361768e-05, + "loss": 0.0335, + "step": 9843 + }, + { + "epoch": 8.71, + "learning_rate": 1.2544098487194984e-05, + "loss": 0.03, + "step": 9844 + }, + { + "epoch": 8.71, + "learning_rate": 1.2542712536779762e-05, + "loss": 0.0319, + "step": 9845 + }, + { + "epoch": 8.71, + "learning_rate": 1.2541326534144566e-05, + "loss": 0.0302, + "step": 9846 + }, + { + "epoch": 8.71, + "learning_rate": 1.253994047931786e-05, + "loss": 0.0332, + "step": 9847 + }, + { + "epoch": 8.71, + "learning_rate": 1.2538554372328107e-05, + "loss": 0.0368, + "step": 9848 + }, + { + "epoch": 8.71, + "learning_rate": 1.2537168213203775e-05, + "loss": 0.0269, + "step": 9849 + }, + { + "epoch": 8.71, + "learning_rate": 1.2535782001973331e-05, + "loss": 0.0313, + "step": 9850 + }, + { + "epoch": 8.72, + "learning_rate": 1.2534395738665245e-05, + "loss": 0.0292, + "step": 9851 + }, + { + "epoch": 8.72, + "learning_rate": 1.253300942330799e-05, + "loss": 0.0313, + "step": 9852 + }, + { + "epoch": 8.72, + "learning_rate": 1.2531623055930031e-05, + "loss": 0.0347, + "step": 9853 + }, + { + "epoch": 8.72, + "learning_rate": 1.2530236636559845e-05, + "loss": 0.0322, + "step": 9854 + }, + { + "epoch": 8.72, + "learning_rate": 1.25288501652259e-05, + "loss": 0.0281, + "step": 9855 + }, + { + "epoch": 8.72, + "learning_rate": 1.2527463641956673e-05, + "loss": 0.0277, + "step": 9856 + }, + { + "epoch": 8.72, + "learning_rate": 1.2526077066780639e-05, + "loss": 0.0317, + "step": 9857 + }, + { + "epoch": 8.72, + "learning_rate": 1.2524690439726275e-05, + "loss": 0.0305, + "step": 9858 + }, + { + "epoch": 8.72, + "learning_rate": 1.2523303760822057e-05, + "loss": 0.0304, + "step": 9859 + }, + { + "epoch": 8.72, + "learning_rate": 1.2521917030096466e-05, + "loss": 0.0353, + "step": 9860 + }, + { + "epoch": 8.72, + "learning_rate": 1.2520530247577978e-05, + "loss": 0.0368, + "step": 9861 + }, + { + "epoch": 8.73, + "learning_rate": 1.2519143413295074e-05, + "loss": 0.0325, + "step": 9862 + }, + { + "epoch": 8.73, + "learning_rate": 1.2517756527276236e-05, + "loss": 0.0331, + "step": 9863 + }, + { + "epoch": 8.73, + "learning_rate": 1.2516369589549949e-05, + "loss": 0.0319, + "step": 9864 + }, + { + "epoch": 8.73, + "learning_rate": 1.2514982600144694e-05, + "loss": 0.0311, + "step": 9865 + }, + { + "epoch": 8.73, + "learning_rate": 1.2513595559088955e-05, + "loss": 0.0325, + "step": 9866 + }, + { + "epoch": 8.73, + "learning_rate": 1.2512208466411222e-05, + "loss": 0.0348, + "step": 9867 + }, + { + "epoch": 8.73, + "learning_rate": 1.2510821322139979e-05, + "loss": 0.0304, + "step": 9868 + }, + { + "epoch": 8.73, + "learning_rate": 1.250943412630371e-05, + "loss": 0.0282, + "step": 9869 + }, + { + "epoch": 8.73, + "learning_rate": 1.2508046878930912e-05, + "loss": 0.0292, + "step": 9870 + }, + { + "epoch": 8.73, + "learning_rate": 1.2506659580050071e-05, + "loss": 0.0289, + "step": 9871 + }, + { + "epoch": 8.73, + "learning_rate": 1.2505272229689677e-05, + "loss": 0.0351, + "step": 9872 + }, + { + "epoch": 8.74, + "learning_rate": 1.2503884827878226e-05, + "loss": 0.0286, + "step": 9873 + }, + { + "epoch": 8.74, + "learning_rate": 1.2502497374644209e-05, + "loss": 0.0336, + "step": 9874 + }, + { + "epoch": 8.74, + "learning_rate": 1.2501109870016117e-05, + "loss": 0.0298, + "step": 9875 + }, + { + "epoch": 8.74, + "learning_rate": 1.2499722314022447e-05, + "loss": 0.0357, + "step": 9876 + }, + { + "epoch": 8.74, + "learning_rate": 1.2498334706691702e-05, + "loss": 0.0274, + "step": 9877 + }, + { + "epoch": 8.74, + "learning_rate": 1.249694704805237e-05, + "loss": 0.0388, + "step": 9878 + }, + { + "epoch": 8.74, + "learning_rate": 1.2495559338132956e-05, + "loss": 0.0351, + "step": 9879 + }, + { + "epoch": 8.74, + "learning_rate": 1.2494171576961956e-05, + "loss": 0.0325, + "step": 9880 + }, + { + "epoch": 8.74, + "learning_rate": 1.2492783764567875e-05, + "loss": 0.0259, + "step": 9881 + }, + { + "epoch": 8.74, + "learning_rate": 1.2491395900979207e-05, + "loss": 0.0359, + "step": 9882 + }, + { + "epoch": 8.74, + "learning_rate": 1.249000798622446e-05, + "loss": 0.0324, + "step": 9883 + }, + { + "epoch": 8.75, + "learning_rate": 1.248862002033214e-05, + "loss": 0.0299, + "step": 9884 + }, + { + "epoch": 8.75, + "learning_rate": 1.2487232003330748e-05, + "loss": 0.0354, + "step": 9885 + }, + { + "epoch": 8.75, + "learning_rate": 1.2485843935248787e-05, + "loss": 0.0337, + "step": 9886 + }, + { + "epoch": 8.75, + "learning_rate": 1.2484455816114772e-05, + "loss": 0.0287, + "step": 9887 + }, + { + "epoch": 8.75, + "learning_rate": 1.2483067645957206e-05, + "loss": 0.0302, + "step": 9888 + }, + { + "epoch": 8.75, + "learning_rate": 1.2481679424804596e-05, + "loss": 0.0302, + "step": 9889 + }, + { + "epoch": 8.75, + "learning_rate": 1.2480291152685454e-05, + "loss": 0.0341, + "step": 9890 + }, + { + "epoch": 8.75, + "learning_rate": 1.2478902829628296e-05, + "loss": 0.0311, + "step": 9891 + }, + { + "epoch": 8.75, + "learning_rate": 1.2477514455661628e-05, + "loss": 0.0328, + "step": 9892 + }, + { + "epoch": 8.75, + "learning_rate": 1.2476126030813964e-05, + "loss": 0.0361, + "step": 9893 + }, + { + "epoch": 8.75, + "learning_rate": 1.247473755511382e-05, + "loss": 0.0337, + "step": 9894 + }, + { + "epoch": 8.75, + "learning_rate": 1.247334902858971e-05, + "loss": 0.0314, + "step": 9895 + }, + { + "epoch": 8.76, + "learning_rate": 1.2471960451270151e-05, + "loss": 0.0347, + "step": 9896 + }, + { + "epoch": 8.76, + "learning_rate": 1.2470571823183662e-05, + "loss": 0.0319, + "step": 9897 + }, + { + "epoch": 8.76, + "learning_rate": 1.246918314435876e-05, + "loss": 0.0333, + "step": 9898 + }, + { + "epoch": 8.76, + "learning_rate": 1.2467794414823962e-05, + "loss": 0.03, + "step": 9899 + }, + { + "epoch": 8.76, + "learning_rate": 1.2466405634607792e-05, + "loss": 0.0295, + "step": 9900 + }, + { + "epoch": 8.76, + "learning_rate": 1.2465016803738768e-05, + "loss": 0.0284, + "step": 9901 + }, + { + "epoch": 8.76, + "learning_rate": 1.2463627922245417e-05, + "loss": 0.0286, + "step": 9902 + }, + { + "epoch": 8.76, + "learning_rate": 1.246223899015626e-05, + "loss": 0.0326, + "step": 9903 + }, + { + "epoch": 8.76, + "learning_rate": 1.246085000749982e-05, + "loss": 0.0358, + "step": 9904 + }, + { + "epoch": 8.76, + "learning_rate": 1.2459460974304629e-05, + "loss": 0.0328, + "step": 9905 + }, + { + "epoch": 8.76, + "learning_rate": 1.2458071890599205e-05, + "loss": 0.0365, + "step": 9906 + }, + { + "epoch": 8.77, + "learning_rate": 1.2456682756412083e-05, + "loss": 0.0291, + "step": 9907 + }, + { + "epoch": 8.77, + "learning_rate": 1.2455293571771786e-05, + "loss": 0.034, + "step": 9908 + }, + { + "epoch": 8.77, + "learning_rate": 1.245390433670685e-05, + "loss": 0.0343, + "step": 9909 + }, + { + "epoch": 8.77, + "learning_rate": 1.24525150512458e-05, + "loss": 0.0301, + "step": 9910 + }, + { + "epoch": 8.77, + "learning_rate": 1.2451125715417173e-05, + "loss": 0.0349, + "step": 9911 + }, + { + "epoch": 8.77, + "learning_rate": 1.2449736329249502e-05, + "loss": 0.0362, + "step": 9912 + }, + { + "epoch": 8.77, + "learning_rate": 1.2448346892771315e-05, + "loss": 0.0306, + "step": 9913 + }, + { + "epoch": 8.77, + "learning_rate": 1.244695740601115e-05, + "loss": 0.0337, + "step": 9914 + }, + { + "epoch": 8.77, + "learning_rate": 1.2445567868997546e-05, + "loss": 0.034, + "step": 9915 + }, + { + "epoch": 8.77, + "learning_rate": 1.2444178281759037e-05, + "loss": 0.0313, + "step": 9916 + }, + { + "epoch": 8.77, + "learning_rate": 1.2442788644324159e-05, + "loss": 0.0306, + "step": 9917 + }, + { + "epoch": 8.78, + "learning_rate": 1.2441398956721458e-05, + "loss": 0.0321, + "step": 9918 + }, + { + "epoch": 8.78, + "learning_rate": 1.244000921897947e-05, + "loss": 0.0268, + "step": 9919 + }, + { + "epoch": 8.78, + "learning_rate": 1.2438619431126734e-05, + "loss": 0.0289, + "step": 9920 + }, + { + "epoch": 8.78, + "learning_rate": 1.2437229593191792e-05, + "loss": 0.0314, + "step": 9921 + }, + { + "epoch": 8.78, + "learning_rate": 1.2435839705203196e-05, + "loss": 0.0324, + "step": 9922 + }, + { + "epoch": 8.78, + "learning_rate": 1.2434449767189482e-05, + "loss": 0.0332, + "step": 9923 + }, + { + "epoch": 8.78, + "learning_rate": 1.2433059779179197e-05, + "loss": 0.0358, + "step": 9924 + }, + { + "epoch": 8.78, + "learning_rate": 1.2431669741200887e-05, + "loss": 0.0291, + "step": 9925 + }, + { + "epoch": 8.78, + "learning_rate": 1.2430279653283103e-05, + "loss": 0.0324, + "step": 9926 + }, + { + "epoch": 8.78, + "learning_rate": 1.2428889515454387e-05, + "loss": 0.0324, + "step": 9927 + }, + { + "epoch": 8.78, + "learning_rate": 1.2427499327743293e-05, + "loss": 0.0279, + "step": 9928 + }, + { + "epoch": 8.78, + "learning_rate": 1.242610909017837e-05, + "loss": 0.027, + "step": 9929 + }, + { + "epoch": 8.79, + "learning_rate": 1.2424718802788172e-05, + "loss": 0.0362, + "step": 9930 + }, + { + "epoch": 8.79, + "learning_rate": 1.2423328465601248e-05, + "loss": 0.0283, + "step": 9931 + }, + { + "epoch": 8.79, + "learning_rate": 1.2421938078646151e-05, + "loss": 0.0383, + "step": 9932 + }, + { + "epoch": 8.79, + "learning_rate": 1.2420547641951444e-05, + "loss": 0.0257, + "step": 9933 + }, + { + "epoch": 8.79, + "learning_rate": 1.241915715554567e-05, + "loss": 0.031, + "step": 9934 + }, + { + "epoch": 8.79, + "learning_rate": 1.241776661945739e-05, + "loss": 0.031, + "step": 9935 + }, + { + "epoch": 8.79, + "learning_rate": 1.2416376033715167e-05, + "loss": 0.0381, + "step": 9936 + }, + { + "epoch": 8.79, + "learning_rate": 1.2414985398347557e-05, + "loss": 0.0323, + "step": 9937 + }, + { + "epoch": 8.79, + "learning_rate": 1.2413594713383115e-05, + "loss": 0.0296, + "step": 9938 + }, + { + "epoch": 8.79, + "learning_rate": 1.2412203978850406e-05, + "loss": 0.0298, + "step": 9939 + }, + { + "epoch": 8.79, + "learning_rate": 1.2410813194777993e-05, + "loss": 0.0313, + "step": 9940 + }, + { + "epoch": 8.8, + "learning_rate": 1.2409422361194432e-05, + "loss": 0.0304, + "step": 9941 + }, + { + "epoch": 8.8, + "learning_rate": 1.2408031478128293e-05, + "loss": 0.0301, + "step": 9942 + }, + { + "epoch": 8.8, + "learning_rate": 1.240664054560814e-05, + "loss": 0.0337, + "step": 9943 + }, + { + "epoch": 8.8, + "learning_rate": 1.2405249563662539e-05, + "loss": 0.0303, + "step": 9944 + }, + { + "epoch": 8.8, + "learning_rate": 1.2403858532320053e-05, + "loss": 0.0292, + "step": 9945 + }, + { + "epoch": 8.8, + "learning_rate": 1.240246745160925e-05, + "loss": 0.0343, + "step": 9946 + }, + { + "epoch": 8.8, + "learning_rate": 1.2401076321558704e-05, + "loss": 0.0318, + "step": 9947 + }, + { + "epoch": 8.8, + "learning_rate": 1.2399685142196982e-05, + "loss": 0.0306, + "step": 9948 + }, + { + "epoch": 8.8, + "learning_rate": 1.2398293913552652e-05, + "loss": 0.0307, + "step": 9949 + }, + { + "epoch": 8.8, + "learning_rate": 1.2396902635654288e-05, + "loss": 0.0302, + "step": 9950 + }, + { + "epoch": 8.8, + "learning_rate": 1.2395511308530467e-05, + "loss": 0.0278, + "step": 9951 + }, + { + "epoch": 8.81, + "learning_rate": 1.2394119932209758e-05, + "loss": 0.0297, + "step": 9952 + }, + { + "epoch": 8.81, + "learning_rate": 1.2392728506720734e-05, + "loss": 0.0298, + "step": 9953 + }, + { + "epoch": 8.81, + "learning_rate": 1.2391337032091977e-05, + "loss": 0.0375, + "step": 9954 + }, + { + "epoch": 8.81, + "learning_rate": 1.2389945508352059e-05, + "loss": 0.035, + "step": 9955 + }, + { + "epoch": 8.81, + "learning_rate": 1.2388553935529559e-05, + "loss": 0.0333, + "step": 9956 + }, + { + "epoch": 8.81, + "learning_rate": 1.2387162313653056e-05, + "loss": 0.0267, + "step": 9957 + }, + { + "epoch": 8.81, + "learning_rate": 1.2385770642751134e-05, + "loss": 0.0358, + "step": 9958 + }, + { + "epoch": 8.81, + "learning_rate": 1.2384378922852367e-05, + "loss": 0.0347, + "step": 9959 + }, + { + "epoch": 8.81, + "learning_rate": 1.2382987153985337e-05, + "loss": 0.0323, + "step": 9960 + }, + { + "epoch": 8.81, + "learning_rate": 1.2381595336178635e-05, + "loss": 0.0275, + "step": 9961 + }, + { + "epoch": 8.81, + "learning_rate": 1.2380203469460837e-05, + "loss": 0.0283, + "step": 9962 + }, + { + "epoch": 8.81, + "learning_rate": 1.2378811553860532e-05, + "loss": 0.0256, + "step": 9963 + }, + { + "epoch": 8.82, + "learning_rate": 1.2377419589406304e-05, + "loss": 0.0325, + "step": 9964 + }, + { + "epoch": 8.82, + "learning_rate": 1.2376027576126744e-05, + "loss": 0.0314, + "step": 9965 + }, + { + "epoch": 8.82, + "learning_rate": 1.2374635514050432e-05, + "loss": 0.0293, + "step": 9966 + }, + { + "epoch": 8.82, + "learning_rate": 1.2373243403205963e-05, + "loss": 0.0354, + "step": 9967 + }, + { + "epoch": 8.82, + "learning_rate": 1.2371851243621926e-05, + "loss": 0.0241, + "step": 9968 + }, + { + "epoch": 8.82, + "learning_rate": 1.237045903532691e-05, + "loss": 0.03, + "step": 9969 + }, + { + "epoch": 8.82, + "learning_rate": 1.2369066778349512e-05, + "loss": 0.0277, + "step": 9970 + }, + { + "epoch": 8.82, + "learning_rate": 1.2367674472718318e-05, + "loss": 0.0369, + "step": 9971 + }, + { + "epoch": 8.82, + "learning_rate": 1.2366282118461928e-05, + "loss": 0.036, + "step": 9972 + }, + { + "epoch": 8.82, + "learning_rate": 1.2364889715608932e-05, + "loss": 0.0323, + "step": 9973 + }, + { + "epoch": 8.82, + "learning_rate": 1.2363497264187928e-05, + "loss": 0.0319, + "step": 9974 + }, + { + "epoch": 8.83, + "learning_rate": 1.2362104764227514e-05, + "loss": 0.0308, + "step": 9975 + }, + { + "epoch": 8.83, + "learning_rate": 1.2360712215756286e-05, + "loss": 0.0323, + "step": 9976 + }, + { + "epoch": 8.83, + "learning_rate": 1.2359319618802843e-05, + "loss": 0.0285, + "step": 9977 + }, + { + "epoch": 8.83, + "learning_rate": 1.2357926973395789e-05, + "loss": 0.0321, + "step": 9978 + }, + { + "epoch": 8.83, + "learning_rate": 1.2356534279563721e-05, + "loss": 0.0375, + "step": 9979 + }, + { + "epoch": 8.83, + "learning_rate": 1.2355141537335239e-05, + "loss": 0.0316, + "step": 9980 + }, + { + "epoch": 8.83, + "learning_rate": 1.2353748746738949e-05, + "loss": 0.0329, + "step": 9981 + }, + { + "epoch": 8.83, + "learning_rate": 1.2352355907803457e-05, + "loss": 0.0322, + "step": 9982 + }, + { + "epoch": 8.83, + "learning_rate": 1.2350963020557366e-05, + "loss": 0.0362, + "step": 9983 + }, + { + "epoch": 8.83, + "learning_rate": 1.2349570085029276e-05, + "loss": 0.0311, + "step": 9984 + }, + { + "epoch": 8.83, + "learning_rate": 1.2348177101247802e-05, + "loss": 0.0294, + "step": 9985 + }, + { + "epoch": 8.84, + "learning_rate": 1.2346784069241552e-05, + "loss": 0.0293, + "step": 9986 + }, + { + "epoch": 8.84, + "learning_rate": 1.2345390989039125e-05, + "loss": 0.0315, + "step": 9987 + }, + { + "epoch": 8.84, + "learning_rate": 1.2343997860669143e-05, + "loss": 0.0334, + "step": 9988 + }, + { + "epoch": 8.84, + "learning_rate": 1.2342604684160211e-05, + "loss": 0.0291, + "step": 9989 + }, + { + "epoch": 8.84, + "learning_rate": 1.234121145954094e-05, + "loss": 0.0321, + "step": 9990 + }, + { + "epoch": 8.84, + "learning_rate": 1.2339818186839945e-05, + "loss": 0.0271, + "step": 9991 + }, + { + "epoch": 8.84, + "learning_rate": 1.2338424866085838e-05, + "loss": 0.0342, + "step": 9992 + }, + { + "epoch": 8.84, + "learning_rate": 1.2337031497307235e-05, + "loss": 0.0301, + "step": 9993 + }, + { + "epoch": 8.84, + "learning_rate": 1.2335638080532752e-05, + "loss": 0.0322, + "step": 9994 + }, + { + "epoch": 8.84, + "learning_rate": 1.2334244615791004e-05, + "loss": 0.0343, + "step": 9995 + }, + { + "epoch": 8.84, + "learning_rate": 1.2332851103110613e-05, + "loss": 0.0332, + "step": 9996 + }, + { + "epoch": 8.85, + "learning_rate": 1.2331457542520193e-05, + "loss": 0.0336, + "step": 9997 + }, + { + "epoch": 8.85, + "learning_rate": 1.2330063934048364e-05, + "loss": 0.0343, + "step": 9998 + }, + { + "epoch": 8.85, + "learning_rate": 1.2328670277723749e-05, + "loss": 0.0359, + "step": 9999 + }, + { + "epoch": 8.85, + "learning_rate": 1.232727657357497e-05, + "loss": 0.0308, + "step": 10000 + }, + { + "epoch": 8.85, + "learning_rate": 1.2325882821630645e-05, + "loss": 0.0369, + "step": 10001 + }, + { + "epoch": 8.85, + "learning_rate": 1.2324489021919405e-05, + "loss": 0.0306, + "step": 10002 + }, + { + "epoch": 8.85, + "learning_rate": 1.232309517446987e-05, + "loss": 0.0346, + "step": 10003 + }, + { + "epoch": 8.85, + "learning_rate": 1.2321701279310666e-05, + "loss": 0.0326, + "step": 10004 + }, + { + "epoch": 8.85, + "learning_rate": 1.232030733647042e-05, + "loss": 0.0285, + "step": 10005 + }, + { + "epoch": 8.85, + "learning_rate": 1.2318913345977758e-05, + "loss": 0.0359, + "step": 10006 + }, + { + "epoch": 8.85, + "learning_rate": 1.2317519307861311e-05, + "loss": 0.0293, + "step": 10007 + }, + { + "epoch": 8.85, + "learning_rate": 1.2316125222149709e-05, + "loss": 0.029, + "step": 10008 + }, + { + "epoch": 8.86, + "learning_rate": 1.2314731088871578e-05, + "loss": 0.0347, + "step": 10009 + }, + { + "epoch": 8.86, + "learning_rate": 1.2313336908055557e-05, + "loss": 0.0307, + "step": 10010 + }, + { + "epoch": 8.86, + "learning_rate": 1.231194267973027e-05, + "loss": 0.0335, + "step": 10011 + }, + { + "epoch": 8.86, + "learning_rate": 1.2310548403924356e-05, + "loss": 0.0304, + "step": 10012 + }, + { + "epoch": 8.86, + "learning_rate": 1.2309154080666446e-05, + "loss": 0.0333, + "step": 10013 + }, + { + "epoch": 8.86, + "learning_rate": 1.2307759709985179e-05, + "loss": 0.0289, + "step": 10014 + }, + { + "epoch": 8.86, + "learning_rate": 1.2306365291909187e-05, + "loss": 0.0306, + "step": 10015 + }, + { + "epoch": 8.86, + "learning_rate": 1.2304970826467114e-05, + "loss": 0.0319, + "step": 10016 + }, + { + "epoch": 8.86, + "learning_rate": 1.2303576313687593e-05, + "loss": 0.0288, + "step": 10017 + }, + { + "epoch": 8.86, + "learning_rate": 1.2302181753599262e-05, + "loss": 0.0317, + "step": 10018 + }, + { + "epoch": 8.86, + "learning_rate": 1.2300787146230762e-05, + "loss": 0.033, + "step": 10019 + }, + { + "epoch": 8.87, + "learning_rate": 1.2299392491610742e-05, + "loss": 0.0365, + "step": 10020 + }, + { + "epoch": 8.87, + "learning_rate": 1.2297997789767835e-05, + "loss": 0.0345, + "step": 10021 + }, + { + "epoch": 8.87, + "learning_rate": 1.2296603040730686e-05, + "loss": 0.0295, + "step": 10022 + }, + { + "epoch": 8.87, + "learning_rate": 1.2295208244527942e-05, + "loss": 0.0333, + "step": 10023 + }, + { + "epoch": 8.87, + "learning_rate": 1.2293813401188246e-05, + "loss": 0.0265, + "step": 10024 + }, + { + "epoch": 8.87, + "learning_rate": 1.2292418510740242e-05, + "loss": 0.0311, + "step": 10025 + }, + { + "epoch": 8.87, + "learning_rate": 1.2291023573212582e-05, + "loss": 0.0323, + "step": 10026 + }, + { + "epoch": 8.87, + "learning_rate": 1.228962858863391e-05, + "loss": 0.0317, + "step": 10027 + }, + { + "epoch": 8.87, + "learning_rate": 1.2288233557032878e-05, + "loss": 0.0335, + "step": 10028 + }, + { + "epoch": 8.87, + "learning_rate": 1.2286838478438132e-05, + "loss": 0.0324, + "step": 10029 + }, + { + "epoch": 8.87, + "learning_rate": 1.2285443352878327e-05, + "loss": 0.0337, + "step": 10030 + }, + { + "epoch": 8.88, + "learning_rate": 1.2284048180382115e-05, + "loss": 0.033, + "step": 10031 + }, + { + "epoch": 8.88, + "learning_rate": 1.2282652960978142e-05, + "loss": 0.0335, + "step": 10032 + }, + { + "epoch": 8.88, + "learning_rate": 1.228125769469507e-05, + "loss": 0.0291, + "step": 10033 + }, + { + "epoch": 8.88, + "learning_rate": 1.2279862381561551e-05, + "loss": 0.033, + "step": 10034 + }, + { + "epoch": 8.88, + "learning_rate": 1.227846702160624e-05, + "loss": 0.0264, + "step": 10035 + }, + { + "epoch": 8.88, + "learning_rate": 1.2277071614857791e-05, + "loss": 0.0319, + "step": 10036 + }, + { + "epoch": 8.88, + "learning_rate": 1.2275676161344865e-05, + "loss": 0.0287, + "step": 10037 + }, + { + "epoch": 8.88, + "learning_rate": 1.2274280661096123e-05, + "loss": 0.0313, + "step": 10038 + }, + { + "epoch": 8.88, + "learning_rate": 1.2272885114140219e-05, + "loss": 0.0292, + "step": 10039 + }, + { + "epoch": 8.88, + "learning_rate": 1.2271489520505814e-05, + "loss": 0.0338, + "step": 10040 + }, + { + "epoch": 8.88, + "learning_rate": 1.2270093880221576e-05, + "loss": 0.0336, + "step": 10041 + }, + { + "epoch": 8.88, + "learning_rate": 1.2268698193316162e-05, + "loss": 0.0304, + "step": 10042 + }, + { + "epoch": 8.89, + "learning_rate": 1.2267302459818233e-05, + "loss": 0.035, + "step": 10043 + }, + { + "epoch": 8.89, + "learning_rate": 1.2265906679756458e-05, + "loss": 0.0347, + "step": 10044 + }, + { + "epoch": 8.89, + "learning_rate": 1.2264510853159504e-05, + "loss": 0.0333, + "step": 10045 + }, + { + "epoch": 8.89, + "learning_rate": 1.226311498005603e-05, + "loss": 0.0347, + "step": 10046 + }, + { + "epoch": 8.89, + "learning_rate": 1.226171906047471e-05, + "loss": 0.0311, + "step": 10047 + }, + { + "epoch": 8.89, + "learning_rate": 1.226032309444421e-05, + "loss": 0.034, + "step": 10048 + }, + { + "epoch": 8.89, + "learning_rate": 1.2258927081993197e-05, + "loss": 0.0289, + "step": 10049 + }, + { + "epoch": 8.89, + "learning_rate": 1.2257531023150344e-05, + "loss": 0.0293, + "step": 10050 + }, + { + "epoch": 8.89, + "learning_rate": 1.225613491794432e-05, + "loss": 0.0298, + "step": 10051 + }, + { + "epoch": 8.89, + "learning_rate": 1.2254738766403795e-05, + "loss": 0.0328, + "step": 10052 + }, + { + "epoch": 8.89, + "learning_rate": 1.2253342568557449e-05, + "loss": 0.0314, + "step": 10053 + }, + { + "epoch": 8.9, + "learning_rate": 1.2251946324433947e-05, + "loss": 0.0345, + "step": 10054 + }, + { + "epoch": 8.9, + "learning_rate": 1.2250550034061974e-05, + "loss": 0.0354, + "step": 10055 + }, + { + "epoch": 8.9, + "learning_rate": 1.2249153697470198e-05, + "loss": 0.0271, + "step": 10056 + }, + { + "epoch": 8.9, + "learning_rate": 1.2247757314687296e-05, + "loss": 0.0308, + "step": 10057 + }, + { + "epoch": 8.9, + "learning_rate": 1.2246360885741945e-05, + "loss": 0.03, + "step": 10058 + }, + { + "epoch": 8.9, + "learning_rate": 1.2244964410662832e-05, + "loss": 0.032, + "step": 10059 + }, + { + "epoch": 8.9, + "learning_rate": 1.224356788947863e-05, + "loss": 0.0313, + "step": 10060 + }, + { + "epoch": 8.9, + "learning_rate": 1.2242171322218016e-05, + "loss": 0.0353, + "step": 10061 + }, + { + "epoch": 8.9, + "learning_rate": 1.2240774708909677e-05, + "loss": 0.0369, + "step": 10062 + }, + { + "epoch": 8.9, + "learning_rate": 1.2239378049582298e-05, + "loss": 0.0323, + "step": 10063 + }, + { + "epoch": 8.9, + "learning_rate": 1.2237981344264556e-05, + "loss": 0.0314, + "step": 10064 + }, + { + "epoch": 8.91, + "learning_rate": 1.2236584592985134e-05, + "loss": 0.0293, + "step": 10065 + }, + { + "epoch": 8.91, + "learning_rate": 1.2235187795772725e-05, + "loss": 0.0366, + "step": 10066 + }, + { + "epoch": 8.91, + "learning_rate": 1.223379095265601e-05, + "loss": 0.0346, + "step": 10067 + }, + { + "epoch": 8.91, + "learning_rate": 1.2232394063663678e-05, + "loss": 0.0342, + "step": 10068 + }, + { + "epoch": 8.91, + "learning_rate": 1.2230997128824416e-05, + "loss": 0.0301, + "step": 10069 + }, + { + "epoch": 8.91, + "learning_rate": 1.2229600148166915e-05, + "loss": 0.0283, + "step": 10070 + }, + { + "epoch": 8.91, + "learning_rate": 1.222820312171986e-05, + "loss": 0.0324, + "step": 10071 + }, + { + "epoch": 8.91, + "learning_rate": 1.2226806049511945e-05, + "loss": 0.0259, + "step": 10072 + }, + { + "epoch": 8.91, + "learning_rate": 1.2225408931571865e-05, + "loss": 0.0307, + "step": 10073 + }, + { + "epoch": 8.91, + "learning_rate": 1.2224011767928309e-05, + "loss": 0.0327, + "step": 10074 + }, + { + "epoch": 8.91, + "learning_rate": 1.222261455860997e-05, + "loss": 0.0361, + "step": 10075 + }, + { + "epoch": 8.91, + "learning_rate": 1.2221217303645546e-05, + "loss": 0.0371, + "step": 10076 + }, + { + "epoch": 8.92, + "learning_rate": 1.221982000306373e-05, + "loss": 0.0294, + "step": 10077 + }, + { + "epoch": 8.92, + "learning_rate": 1.2218422656893216e-05, + "loss": 0.0346, + "step": 10078 + }, + { + "epoch": 8.92, + "learning_rate": 1.2217025265162707e-05, + "loss": 0.0338, + "step": 10079 + }, + { + "epoch": 8.92, + "learning_rate": 1.2215627827900902e-05, + "loss": 0.0374, + "step": 10080 + }, + { + "epoch": 8.92, + "learning_rate": 1.2214230345136494e-05, + "loss": 0.0339, + "step": 10081 + }, + { + "epoch": 8.92, + "learning_rate": 1.2212832816898188e-05, + "loss": 0.0291, + "step": 10082 + }, + { + "epoch": 8.92, + "learning_rate": 1.2211435243214684e-05, + "loss": 0.0307, + "step": 10083 + }, + { + "epoch": 8.92, + "learning_rate": 1.2210037624114683e-05, + "loss": 0.0302, + "step": 10084 + }, + { + "epoch": 8.92, + "learning_rate": 1.220863995962689e-05, + "loss": 0.0308, + "step": 10085 + }, + { + "epoch": 8.92, + "learning_rate": 1.2207242249780006e-05, + "loss": 0.0302, + "step": 10086 + }, + { + "epoch": 8.92, + "learning_rate": 1.2205844494602741e-05, + "loss": 0.0311, + "step": 10087 + }, + { + "epoch": 8.93, + "learning_rate": 1.2204446694123797e-05, + "loss": 0.0351, + "step": 10088 + }, + { + "epoch": 8.93, + "learning_rate": 1.220304884837188e-05, + "loss": 0.0299, + "step": 10089 + }, + { + "epoch": 8.93, + "learning_rate": 1.2201650957375701e-05, + "loss": 0.0324, + "step": 10090 + }, + { + "epoch": 8.93, + "learning_rate": 1.2200253021163966e-05, + "loss": 0.0338, + "step": 10091 + }, + { + "epoch": 8.93, + "learning_rate": 1.2198855039765384e-05, + "loss": 0.0288, + "step": 10092 + }, + { + "epoch": 8.93, + "learning_rate": 1.219745701320867e-05, + "loss": 0.0338, + "step": 10093 + }, + { + "epoch": 8.93, + "learning_rate": 1.2196058941522532e-05, + "loss": 0.0343, + "step": 10094 + }, + { + "epoch": 8.93, + "learning_rate": 1.2194660824735682e-05, + "loss": 0.0361, + "step": 10095 + }, + { + "epoch": 8.93, + "learning_rate": 1.2193262662876834e-05, + "loss": 0.0353, + "step": 10096 + }, + { + "epoch": 8.93, + "learning_rate": 1.2191864455974702e-05, + "loss": 0.0312, + "step": 10097 + }, + { + "epoch": 8.93, + "learning_rate": 1.2190466204058003e-05, + "loss": 0.0297, + "step": 10098 + }, + { + "epoch": 8.94, + "learning_rate": 1.2189067907155449e-05, + "loss": 0.0309, + "step": 10099 + }, + { + "epoch": 8.94, + "learning_rate": 1.2187669565295761e-05, + "loss": 0.0344, + "step": 10100 + }, + { + "epoch": 8.94, + "learning_rate": 1.2186271178507658e-05, + "loss": 0.0322, + "step": 10101 + }, + { + "epoch": 8.94, + "learning_rate": 1.2184872746819853e-05, + "loss": 0.0301, + "step": 10102 + }, + { + "epoch": 8.94, + "learning_rate": 1.2183474270261071e-05, + "loss": 0.0337, + "step": 10103 + }, + { + "epoch": 8.94, + "learning_rate": 1.2182075748860028e-05, + "loss": 0.0367, + "step": 10104 + }, + { + "epoch": 8.94, + "learning_rate": 1.2180677182645449e-05, + "loss": 0.0337, + "step": 10105 + }, + { + "epoch": 8.94, + "learning_rate": 1.2179278571646056e-05, + "loss": 0.0326, + "step": 10106 + }, + { + "epoch": 8.94, + "learning_rate": 1.2177879915890571e-05, + "loss": 0.0328, + "step": 10107 + }, + { + "epoch": 8.94, + "learning_rate": 1.2176481215407725e-05, + "loss": 0.0338, + "step": 10108 + }, + { + "epoch": 8.94, + "learning_rate": 1.2175082470226233e-05, + "loss": 0.0333, + "step": 10109 + }, + { + "epoch": 8.94, + "learning_rate": 1.2173683680374824e-05, + "loss": 0.0347, + "step": 10110 + }, + { + "epoch": 8.95, + "learning_rate": 1.2172284845882233e-05, + "loss": 0.0338, + "step": 10111 + }, + { + "epoch": 8.95, + "learning_rate": 1.2170885966777178e-05, + "loss": 0.0298, + "step": 10112 + }, + { + "epoch": 8.95, + "learning_rate": 1.2169487043088392e-05, + "loss": 0.0258, + "step": 10113 + }, + { + "epoch": 8.95, + "learning_rate": 1.2168088074844606e-05, + "loss": 0.0299, + "step": 10114 + }, + { + "epoch": 8.95, + "learning_rate": 1.2166689062074552e-05, + "loss": 0.0323, + "step": 10115 + }, + { + "epoch": 8.95, + "learning_rate": 1.2165290004806957e-05, + "loss": 0.0323, + "step": 10116 + }, + { + "epoch": 8.95, + "learning_rate": 1.2163890903070555e-05, + "loss": 0.0346, + "step": 10117 + }, + { + "epoch": 8.95, + "learning_rate": 1.216249175689408e-05, + "loss": 0.0277, + "step": 10118 + }, + { + "epoch": 8.95, + "learning_rate": 1.216109256630627e-05, + "loss": 0.0329, + "step": 10119 + }, + { + "epoch": 8.95, + "learning_rate": 1.2159693331335856e-05, + "loss": 0.0342, + "step": 10120 + }, + { + "epoch": 8.95, + "learning_rate": 1.2158294052011574e-05, + "loss": 0.0351, + "step": 10121 + }, + { + "epoch": 8.96, + "learning_rate": 1.2156894728362167e-05, + "loss": 0.0269, + "step": 10122 + }, + { + "epoch": 8.96, + "learning_rate": 1.2155495360416363e-05, + "loss": 0.0354, + "step": 10123 + }, + { + "epoch": 8.96, + "learning_rate": 1.2154095948202909e-05, + "loss": 0.0315, + "step": 10124 + }, + { + "epoch": 8.96, + "learning_rate": 1.2152696491750545e-05, + "loss": 0.0333, + "step": 10125 + }, + { + "epoch": 8.96, + "learning_rate": 1.2151296991088006e-05, + "loss": 0.0374, + "step": 10126 + }, + { + "epoch": 8.96, + "learning_rate": 1.2149897446244038e-05, + "loss": 0.0328, + "step": 10127 + }, + { + "epoch": 8.96, + "learning_rate": 1.2148497857247383e-05, + "loss": 0.03, + "step": 10128 + }, + { + "epoch": 8.96, + "learning_rate": 1.2147098224126785e-05, + "loss": 0.0421, + "step": 10129 + }, + { + "epoch": 8.96, + "learning_rate": 1.2145698546910984e-05, + "loss": 0.0347, + "step": 10130 + }, + { + "epoch": 8.96, + "learning_rate": 1.2144298825628732e-05, + "loss": 0.0341, + "step": 10131 + }, + { + "epoch": 8.96, + "learning_rate": 1.2142899060308775e-05, + "loss": 0.0303, + "step": 10132 + }, + { + "epoch": 8.97, + "learning_rate": 1.2141499250979853e-05, + "loss": 0.0313, + "step": 10133 + }, + { + "epoch": 8.97, + "learning_rate": 1.2140099397670722e-05, + "loss": 0.0314, + "step": 10134 + }, + { + "epoch": 8.97, + "learning_rate": 1.2138699500410123e-05, + "loss": 0.0316, + "step": 10135 + }, + { + "epoch": 8.97, + "learning_rate": 1.2137299559226814e-05, + "loss": 0.0333, + "step": 10136 + }, + { + "epoch": 8.97, + "learning_rate": 1.2135899574149539e-05, + "loss": 0.0322, + "step": 10137 + }, + { + "epoch": 8.97, + "learning_rate": 1.2134499545207052e-05, + "loss": 0.0316, + "step": 10138 + }, + { + "epoch": 8.97, + "learning_rate": 1.213309947242811e-05, + "loss": 0.0365, + "step": 10139 + }, + { + "epoch": 8.97, + "learning_rate": 1.213169935584146e-05, + "loss": 0.0296, + "step": 10140 + }, + { + "epoch": 8.97, + "learning_rate": 1.2130299195475858e-05, + "loss": 0.0347, + "step": 10141 + }, + { + "epoch": 8.97, + "learning_rate": 1.2128898991360063e-05, + "loss": 0.037, + "step": 10142 + }, + { + "epoch": 8.97, + "learning_rate": 1.2127498743522826e-05, + "loss": 0.0336, + "step": 10143 + }, + { + "epoch": 8.98, + "learning_rate": 1.2126098451992907e-05, + "loss": 0.0317, + "step": 10144 + }, + { + "epoch": 8.98, + "learning_rate": 1.2124698116799063e-05, + "loss": 0.0317, + "step": 10145 + }, + { + "epoch": 8.98, + "learning_rate": 1.2123297737970054e-05, + "loss": 0.0339, + "step": 10146 + }, + { + "epoch": 8.98, + "learning_rate": 1.2121897315534642e-05, + "loss": 0.0369, + "step": 10147 + }, + { + "epoch": 8.98, + "learning_rate": 1.2120496849521578e-05, + "loss": 0.031, + "step": 10148 + }, + { + "epoch": 8.98, + "learning_rate": 1.2119096339959633e-05, + "loss": 0.0323, + "step": 10149 + }, + { + "epoch": 8.98, + "learning_rate": 1.2117695786877567e-05, + "loss": 0.0324, + "step": 10150 + }, + { + "epoch": 8.98, + "learning_rate": 1.2116295190304142e-05, + "loss": 0.0344, + "step": 10151 + }, + { + "epoch": 8.98, + "learning_rate": 1.2114894550268124e-05, + "loss": 0.0377, + "step": 10152 + }, + { + "epoch": 8.98, + "learning_rate": 1.2113493866798277e-05, + "loss": 0.0333, + "step": 10153 + }, + { + "epoch": 8.98, + "learning_rate": 1.211209313992337e-05, + "loss": 0.0356, + "step": 10154 + }, + { + "epoch": 8.98, + "learning_rate": 1.2110692369672162e-05, + "loss": 0.0263, + "step": 10155 + }, + { + "epoch": 8.99, + "learning_rate": 1.2109291556073426e-05, + "loss": 0.0344, + "step": 10156 + }, + { + "epoch": 8.99, + "learning_rate": 1.2107890699155934e-05, + "loss": 0.0351, + "step": 10157 + }, + { + "epoch": 8.99, + "learning_rate": 1.2106489798948449e-05, + "loss": 0.0332, + "step": 10158 + }, + { + "epoch": 8.99, + "learning_rate": 1.2105088855479745e-05, + "loss": 0.0306, + "step": 10159 + }, + { + "epoch": 8.99, + "learning_rate": 1.2103687868778596e-05, + "loss": 0.0302, + "step": 10160 + }, + { + "epoch": 8.99, + "learning_rate": 1.2102286838873766e-05, + "loss": 0.0282, + "step": 10161 + }, + { + "epoch": 8.99, + "learning_rate": 1.2100885765794034e-05, + "loss": 0.0317, + "step": 10162 + }, + { + "epoch": 8.99, + "learning_rate": 1.2099484649568176e-05, + "loss": 0.0305, + "step": 10163 + }, + { + "epoch": 8.99, + "learning_rate": 1.209808349022496e-05, + "loss": 0.0352, + "step": 10164 + }, + { + "epoch": 8.99, + "learning_rate": 1.209668228779317e-05, + "loss": 0.0373, + "step": 10165 + }, + { + "epoch": 8.99, + "learning_rate": 1.2095281042301576e-05, + "loss": 0.0322, + "step": 10166 + }, + { + "epoch": 9.0, + "learning_rate": 1.209387975377896e-05, + "loss": 0.0368, + "step": 10167 + }, + { + "epoch": 9.0, + "learning_rate": 1.20924784222541e-05, + "loss": 0.0305, + "step": 10168 + }, + { + "epoch": 9.0, + "learning_rate": 1.2091077047755766e-05, + "loss": 0.0392, + "step": 10169 + }, + { + "epoch": 9.0, + "learning_rate": 1.2089675630312755e-05, + "loss": 0.0388, + "step": 10170 + }, + { + "epoch": 9.0, + "learning_rate": 1.2088274169953833e-05, + "loss": 0.037, + "step": 10171 + }, + { + "epoch": 9.0, + "learning_rate": 1.2086872666707788e-05, + "loss": 0.0334, + "step": 10172 + }, + { + "epoch": 9.0, + "learning_rate": 1.2085471120603404e-05, + "loss": 0.0195, + "step": 10173 + }, + { + "epoch": 9.0, + "learning_rate": 1.2084069531669467e-05, + "loss": 0.0179, + "step": 10174 + }, + { + "epoch": 9.0, + "learning_rate": 1.2082667899934753e-05, + "loss": 0.0179, + "step": 10175 + }, + { + "epoch": 9.0, + "learning_rate": 1.2081266225428052e-05, + "loss": 0.0177, + "step": 10176 + }, + { + "epoch": 9.0, + "learning_rate": 1.2079864508178151e-05, + "loss": 0.0176, + "step": 10177 + }, + { + "epoch": 9.01, + "learning_rate": 1.2078462748213844e-05, + "loss": 0.0163, + "step": 10178 + }, + { + "epoch": 9.01, + "learning_rate": 1.2077060945563905e-05, + "loss": 0.0164, + "step": 10179 + }, + { + "epoch": 9.01, + "learning_rate": 1.2075659100257134e-05, + "loss": 0.0136, + "step": 10180 + }, + { + "epoch": 9.01, + "learning_rate": 1.2074257212322316e-05, + "loss": 0.0171, + "step": 10181 + }, + { + "epoch": 9.01, + "learning_rate": 1.207285528178824e-05, + "loss": 0.017, + "step": 10182 + }, + { + "epoch": 9.01, + "learning_rate": 1.2071453308683703e-05, + "loss": 0.0161, + "step": 10183 + }, + { + "epoch": 9.01, + "learning_rate": 1.2070051293037493e-05, + "loss": 0.0171, + "step": 10184 + }, + { + "epoch": 9.01, + "learning_rate": 1.2068649234878408e-05, + "loss": 0.0167, + "step": 10185 + }, + { + "epoch": 9.01, + "learning_rate": 1.2067247134235238e-05, + "loss": 0.0181, + "step": 10186 + }, + { + "epoch": 9.01, + "learning_rate": 1.206584499113678e-05, + "loss": 0.0169, + "step": 10187 + }, + { + "epoch": 9.01, + "learning_rate": 1.2064442805611827e-05, + "loss": 0.0161, + "step": 10188 + }, + { + "epoch": 9.01, + "learning_rate": 1.206304057768918e-05, + "loss": 0.0166, + "step": 10189 + }, + { + "epoch": 9.02, + "learning_rate": 1.2061638307397635e-05, + "loss": 0.0172, + "step": 10190 + }, + { + "epoch": 9.02, + "learning_rate": 1.2060235994765992e-05, + "loss": 0.0182, + "step": 10191 + }, + { + "epoch": 9.02, + "learning_rate": 1.205883363982305e-05, + "loss": 0.0161, + "step": 10192 + }, + { + "epoch": 9.02, + "learning_rate": 1.2057431242597606e-05, + "loss": 0.0183, + "step": 10193 + }, + { + "epoch": 9.02, + "learning_rate": 1.2056028803118462e-05, + "loss": 0.0157, + "step": 10194 + }, + { + "epoch": 9.02, + "learning_rate": 1.2054626321414425e-05, + "loss": 0.0211, + "step": 10195 + }, + { + "epoch": 9.02, + "learning_rate": 1.2053223797514291e-05, + "loss": 0.0157, + "step": 10196 + }, + { + "epoch": 9.02, + "learning_rate": 1.205182123144687e-05, + "loss": 0.0165, + "step": 10197 + }, + { + "epoch": 9.02, + "learning_rate": 1.2050418623240962e-05, + "loss": 0.0163, + "step": 10198 + }, + { + "epoch": 9.02, + "learning_rate": 1.204901597292538e-05, + "loss": 0.0177, + "step": 10199 + }, + { + "epoch": 9.02, + "learning_rate": 1.204761328052892e-05, + "loss": 0.0178, + "step": 10200 + }, + { + "epoch": 9.03, + "learning_rate": 1.2046210546080395e-05, + "loss": 0.0183, + "step": 10201 + }, + { + "epoch": 9.03, + "learning_rate": 1.2044807769608611e-05, + "loss": 0.0146, + "step": 10202 + }, + { + "epoch": 9.03, + "learning_rate": 1.2043404951142378e-05, + "loss": 0.0189, + "step": 10203 + }, + { + "epoch": 9.03, + "learning_rate": 1.204200209071051e-05, + "loss": 0.0161, + "step": 10204 + }, + { + "epoch": 9.03, + "learning_rate": 1.2040599188341811e-05, + "loss": 0.0137, + "step": 10205 + }, + { + "epoch": 9.03, + "learning_rate": 1.2039196244065097e-05, + "loss": 0.0151, + "step": 10206 + }, + { + "epoch": 9.03, + "learning_rate": 1.2037793257909179e-05, + "loss": 0.016, + "step": 10207 + }, + { + "epoch": 9.03, + "learning_rate": 1.2036390229902866e-05, + "loss": 0.0141, + "step": 10208 + }, + { + "epoch": 9.03, + "learning_rate": 1.203498716007498e-05, + "loss": 0.0214, + "step": 10209 + }, + { + "epoch": 9.03, + "learning_rate": 1.2033584048454332e-05, + "loss": 0.018, + "step": 10210 + }, + { + "epoch": 9.03, + "learning_rate": 1.2032180895069738e-05, + "loss": 0.0169, + "step": 10211 + }, + { + "epoch": 9.04, + "learning_rate": 1.2030777699950013e-05, + "loss": 0.0191, + "step": 10212 + }, + { + "epoch": 9.04, + "learning_rate": 1.2029374463123979e-05, + "loss": 0.0164, + "step": 10213 + }, + { + "epoch": 9.04, + "learning_rate": 1.2027971184620451e-05, + "loss": 0.0137, + "step": 10214 + }, + { + "epoch": 9.04, + "learning_rate": 1.2026567864468249e-05, + "loss": 0.0192, + "step": 10215 + }, + { + "epoch": 9.04, + "learning_rate": 1.2025164502696193e-05, + "loss": 0.0126, + "step": 10216 + }, + { + "epoch": 9.04, + "learning_rate": 1.2023761099333104e-05, + "loss": 0.0179, + "step": 10217 + }, + { + "epoch": 9.04, + "learning_rate": 1.2022357654407803e-05, + "loss": 0.0169, + "step": 10218 + }, + { + "epoch": 9.04, + "learning_rate": 1.2020954167949115e-05, + "loss": 0.0161, + "step": 10219 + }, + { + "epoch": 9.04, + "learning_rate": 1.2019550639985866e-05, + "loss": 0.0162, + "step": 10220 + }, + { + "epoch": 9.04, + "learning_rate": 1.201814707054687e-05, + "loss": 0.0164, + "step": 10221 + }, + { + "epoch": 9.04, + "learning_rate": 1.2016743459660963e-05, + "loss": 0.0146, + "step": 10222 + }, + { + "epoch": 9.04, + "learning_rate": 1.2015339807356969e-05, + "loss": 0.0151, + "step": 10223 + }, + { + "epoch": 9.05, + "learning_rate": 1.201393611366371e-05, + "loss": 0.0165, + "step": 10224 + }, + { + "epoch": 9.05, + "learning_rate": 1.2012532378610017e-05, + "loss": 0.015, + "step": 10225 + }, + { + "epoch": 9.05, + "learning_rate": 1.2011128602224719e-05, + "loss": 0.0171, + "step": 10226 + }, + { + "epoch": 9.05, + "learning_rate": 1.200972478453665e-05, + "loss": 0.0157, + "step": 10227 + }, + { + "epoch": 9.05, + "learning_rate": 1.2008320925574627e-05, + "loss": 0.0176, + "step": 10228 + }, + { + "epoch": 9.05, + "learning_rate": 1.2006917025367493e-05, + "loss": 0.0195, + "step": 10229 + }, + { + "epoch": 9.05, + "learning_rate": 1.200551308394408e-05, + "loss": 0.0168, + "step": 10230 + }, + { + "epoch": 9.05, + "learning_rate": 1.2004109101333215e-05, + "loss": 0.0193, + "step": 10231 + }, + { + "epoch": 9.05, + "learning_rate": 1.2002705077563735e-05, + "loss": 0.0164, + "step": 10232 + }, + { + "epoch": 9.05, + "learning_rate": 1.2001301012664475e-05, + "loss": 0.0209, + "step": 10233 + }, + { + "epoch": 9.05, + "learning_rate": 1.1999896906664267e-05, + "loss": 0.0149, + "step": 10234 + }, + { + "epoch": 9.06, + "learning_rate": 1.199849275959195e-05, + "loss": 0.0149, + "step": 10235 + }, + { + "epoch": 9.06, + "learning_rate": 1.1997088571476363e-05, + "loss": 0.0171, + "step": 10236 + }, + { + "epoch": 9.06, + "learning_rate": 1.199568434234634e-05, + "loss": 0.0156, + "step": 10237 + }, + { + "epoch": 9.06, + "learning_rate": 1.1994280072230724e-05, + "loss": 0.0165, + "step": 10238 + }, + { + "epoch": 9.06, + "learning_rate": 1.1992875761158352e-05, + "loss": 0.0189, + "step": 10239 + }, + { + "epoch": 9.06, + "learning_rate": 1.1991471409158062e-05, + "loss": 0.0153, + "step": 10240 + }, + { + "epoch": 9.06, + "learning_rate": 1.19900670162587e-05, + "loss": 0.0156, + "step": 10241 + }, + { + "epoch": 9.06, + "learning_rate": 1.1988662582489105e-05, + "loss": 0.0143, + "step": 10242 + }, + { + "epoch": 9.06, + "learning_rate": 1.1987258107878121e-05, + "loss": 0.0161, + "step": 10243 + }, + { + "epoch": 9.06, + "learning_rate": 1.1985853592454598e-05, + "loss": 0.0174, + "step": 10244 + }, + { + "epoch": 9.06, + "learning_rate": 1.198444903624737e-05, + "loss": 0.0175, + "step": 10245 + }, + { + "epoch": 9.07, + "learning_rate": 1.1983044439285287e-05, + "loss": 0.0146, + "step": 10246 + }, + { + "epoch": 9.07, + "learning_rate": 1.1981639801597196e-05, + "loss": 0.016, + "step": 10247 + }, + { + "epoch": 9.07, + "learning_rate": 1.1980235123211945e-05, + "loss": 0.0234, + "step": 10248 + }, + { + "epoch": 9.07, + "learning_rate": 1.197883040415838e-05, + "loss": 0.0134, + "step": 10249 + }, + { + "epoch": 9.07, + "learning_rate": 1.1977425644465353e-05, + "loss": 0.0146, + "step": 10250 + }, + { + "epoch": 9.07, + "learning_rate": 1.197602084416171e-05, + "loss": 0.0189, + "step": 10251 + }, + { + "epoch": 9.07, + "learning_rate": 1.1974616003276304e-05, + "loss": 0.0168, + "step": 10252 + }, + { + "epoch": 9.07, + "learning_rate": 1.1973211121837984e-05, + "loss": 0.0191, + "step": 10253 + }, + { + "epoch": 9.07, + "learning_rate": 1.1971806199875604e-05, + "loss": 0.0149, + "step": 10254 + }, + { + "epoch": 9.07, + "learning_rate": 1.1970401237418018e-05, + "loss": 0.0161, + "step": 10255 + }, + { + "epoch": 9.07, + "learning_rate": 1.196899623449408e-05, + "loss": 0.0179, + "step": 10256 + }, + { + "epoch": 9.08, + "learning_rate": 1.196759119113264e-05, + "loss": 0.0162, + "step": 10257 + }, + { + "epoch": 9.08, + "learning_rate": 1.1966186107362558e-05, + "loss": 0.0162, + "step": 10258 + }, + { + "epoch": 9.08, + "learning_rate": 1.1964780983212692e-05, + "loss": 0.0159, + "step": 10259 + }, + { + "epoch": 9.08, + "learning_rate": 1.196337581871189e-05, + "loss": 0.0179, + "step": 10260 + }, + { + "epoch": 9.08, + "learning_rate": 1.1961970613889022e-05, + "loss": 0.0171, + "step": 10261 + }, + { + "epoch": 9.08, + "learning_rate": 1.196056536877294e-05, + "loss": 0.0176, + "step": 10262 + }, + { + "epoch": 9.08, + "learning_rate": 1.1959160083392504e-05, + "loss": 0.016, + "step": 10263 + }, + { + "epoch": 9.08, + "learning_rate": 1.1957754757776576e-05, + "loss": 0.0169, + "step": 10264 + }, + { + "epoch": 9.08, + "learning_rate": 1.195634939195402e-05, + "loss": 0.0181, + "step": 10265 + }, + { + "epoch": 9.08, + "learning_rate": 1.1954943985953693e-05, + "loss": 0.0171, + "step": 10266 + }, + { + "epoch": 9.08, + "learning_rate": 1.1953538539804457e-05, + "loss": 0.0146, + "step": 10267 + }, + { + "epoch": 9.08, + "learning_rate": 1.1952133053535181e-05, + "loss": 0.0198, + "step": 10268 + }, + { + "epoch": 9.09, + "learning_rate": 1.1950727527174729e-05, + "loss": 0.0162, + "step": 10269 + }, + { + "epoch": 9.09, + "learning_rate": 1.1949321960751962e-05, + "loss": 0.0188, + "step": 10270 + }, + { + "epoch": 9.09, + "learning_rate": 1.194791635429575e-05, + "loss": 0.0181, + "step": 10271 + }, + { + "epoch": 9.09, + "learning_rate": 1.1946510707834962e-05, + "loss": 0.0154, + "step": 10272 + }, + { + "epoch": 9.09, + "learning_rate": 1.1945105021398458e-05, + "loss": 0.0151, + "step": 10273 + }, + { + "epoch": 9.09, + "learning_rate": 1.1943699295015114e-05, + "loss": 0.0142, + "step": 10274 + }, + { + "epoch": 9.09, + "learning_rate": 1.1942293528713802e-05, + "loss": 0.0171, + "step": 10275 + }, + { + "epoch": 9.09, + "learning_rate": 1.1940887722523382e-05, + "loss": 0.0172, + "step": 10276 + }, + { + "epoch": 9.09, + "learning_rate": 1.1939481876472734e-05, + "loss": 0.0148, + "step": 10277 + }, + { + "epoch": 9.09, + "learning_rate": 1.1938075990590725e-05, + "loss": 0.016, + "step": 10278 + }, + { + "epoch": 9.09, + "learning_rate": 1.1936670064906232e-05, + "loss": 0.0196, + "step": 10279 + }, + { + "epoch": 9.1, + "learning_rate": 1.1935264099448125e-05, + "loss": 0.0171, + "step": 10280 + }, + { + "epoch": 9.1, + "learning_rate": 1.1933858094245281e-05, + "loss": 0.0201, + "step": 10281 + }, + { + "epoch": 9.1, + "learning_rate": 1.1932452049326576e-05, + "loss": 0.0141, + "step": 10282 + }, + { + "epoch": 9.1, + "learning_rate": 1.1931045964720882e-05, + "loss": 0.0148, + "step": 10283 + }, + { + "epoch": 9.1, + "learning_rate": 1.1929639840457077e-05, + "loss": 0.0171, + "step": 10284 + }, + { + "epoch": 9.1, + "learning_rate": 1.1928233676564042e-05, + "loss": 0.0157, + "step": 10285 + }, + { + "epoch": 9.1, + "learning_rate": 1.1926827473070652e-05, + "loss": 0.0145, + "step": 10286 + }, + { + "epoch": 9.1, + "learning_rate": 1.1925421230005792e-05, + "loss": 0.0161, + "step": 10287 + }, + { + "epoch": 9.1, + "learning_rate": 1.1924014947398335e-05, + "loss": 0.0152, + "step": 10288 + }, + { + "epoch": 9.1, + "learning_rate": 1.1922608625277167e-05, + "loss": 0.0161, + "step": 10289 + }, + { + "epoch": 9.1, + "learning_rate": 1.1921202263671166e-05, + "loss": 0.0165, + "step": 10290 + }, + { + "epoch": 9.11, + "learning_rate": 1.1919795862609218e-05, + "loss": 0.0182, + "step": 10291 + }, + { + "epoch": 9.11, + "learning_rate": 1.1918389422120202e-05, + "loss": 0.0152, + "step": 10292 + }, + { + "epoch": 9.11, + "learning_rate": 1.1916982942233008e-05, + "loss": 0.0177, + "step": 10293 + }, + { + "epoch": 9.11, + "learning_rate": 1.1915576422976518e-05, + "loss": 0.0164, + "step": 10294 + }, + { + "epoch": 9.11, + "learning_rate": 1.1914169864379618e-05, + "loss": 0.0152, + "step": 10295 + }, + { + "epoch": 9.11, + "learning_rate": 1.1912763266471196e-05, + "loss": 0.0182, + "step": 10296 + }, + { + "epoch": 9.11, + "learning_rate": 1.1911356629280135e-05, + "loss": 0.0151, + "step": 10297 + }, + { + "epoch": 9.11, + "learning_rate": 1.190994995283533e-05, + "loss": 0.0167, + "step": 10298 + }, + { + "epoch": 9.11, + "learning_rate": 1.1908543237165663e-05, + "loss": 0.016, + "step": 10299 + }, + { + "epoch": 9.11, + "learning_rate": 1.190713648230003e-05, + "loss": 0.014, + "step": 10300 + }, + { + "epoch": 9.11, + "learning_rate": 1.1905729688267317e-05, + "loss": 0.0151, + "step": 10301 + }, + { + "epoch": 9.11, + "learning_rate": 1.190432285509642e-05, + "loss": 0.015, + "step": 10302 + }, + { + "epoch": 9.12, + "learning_rate": 1.1902915982816225e-05, + "loss": 0.0169, + "step": 10303 + }, + { + "epoch": 9.12, + "learning_rate": 1.1901509071455634e-05, + "loss": 0.0133, + "step": 10304 + }, + { + "epoch": 9.12, + "learning_rate": 1.1900102121043533e-05, + "loss": 0.0187, + "step": 10305 + }, + { + "epoch": 9.12, + "learning_rate": 1.189869513160882e-05, + "loss": 0.0148, + "step": 10306 + }, + { + "epoch": 9.12, + "learning_rate": 1.1897288103180391e-05, + "loss": 0.0159, + "step": 10307 + }, + { + "epoch": 9.12, + "learning_rate": 1.189588103578714e-05, + "loss": 0.0166, + "step": 10308 + }, + { + "epoch": 9.12, + "learning_rate": 1.1894473929457966e-05, + "loss": 0.0185, + "step": 10309 + }, + { + "epoch": 9.12, + "learning_rate": 1.1893066784221765e-05, + "loss": 0.0143, + "step": 10310 + }, + { + "epoch": 9.12, + "learning_rate": 1.1891659600107442e-05, + "loss": 0.0167, + "step": 10311 + }, + { + "epoch": 9.12, + "learning_rate": 1.1890252377143887e-05, + "loss": 0.0131, + "step": 10312 + }, + { + "epoch": 9.12, + "learning_rate": 1.1888845115360004e-05, + "loss": 0.0149, + "step": 10313 + }, + { + "epoch": 9.13, + "learning_rate": 1.1887437814784699e-05, + "loss": 0.0171, + "step": 10314 + }, + { + "epoch": 9.13, + "learning_rate": 1.1886030475446866e-05, + "loss": 0.0151, + "step": 10315 + }, + { + "epoch": 9.13, + "learning_rate": 1.1884623097375413e-05, + "loss": 0.0171, + "step": 10316 + }, + { + "epoch": 9.13, + "learning_rate": 1.1883215680599243e-05, + "loss": 0.0139, + "step": 10317 + }, + { + "epoch": 9.13, + "learning_rate": 1.188180822514726e-05, + "loss": 0.016, + "step": 10318 + }, + { + "epoch": 9.13, + "learning_rate": 1.1880400731048366e-05, + "loss": 0.0145, + "step": 10319 + }, + { + "epoch": 9.13, + "learning_rate": 1.187899319833147e-05, + "loss": 0.0152, + "step": 10320 + }, + { + "epoch": 9.13, + "learning_rate": 1.1877585627025479e-05, + "loss": 0.0154, + "step": 10321 + }, + { + "epoch": 9.13, + "learning_rate": 1.1876178017159298e-05, + "loss": 0.0164, + "step": 10322 + }, + { + "epoch": 9.13, + "learning_rate": 1.1874770368761836e-05, + "loss": 0.0156, + "step": 10323 + }, + { + "epoch": 9.13, + "learning_rate": 1.1873362681862004e-05, + "loss": 0.0171, + "step": 10324 + }, + { + "epoch": 9.14, + "learning_rate": 1.1871954956488713e-05, + "loss": 0.0189, + "step": 10325 + }, + { + "epoch": 9.14, + "learning_rate": 1.1870547192670866e-05, + "loss": 0.0174, + "step": 10326 + }, + { + "epoch": 9.14, + "learning_rate": 1.186913939043738e-05, + "loss": 0.0138, + "step": 10327 + }, + { + "epoch": 9.14, + "learning_rate": 1.1867731549817172e-05, + "loss": 0.0161, + "step": 10328 + }, + { + "epoch": 9.14, + "learning_rate": 1.1866323670839144e-05, + "loss": 0.0158, + "step": 10329 + }, + { + "epoch": 9.14, + "learning_rate": 1.1864915753532217e-05, + "loss": 0.0178, + "step": 10330 + }, + { + "epoch": 9.14, + "learning_rate": 1.1863507797925306e-05, + "loss": 0.0162, + "step": 10331 + }, + { + "epoch": 9.14, + "learning_rate": 1.1862099804047323e-05, + "loss": 0.0148, + "step": 10332 + }, + { + "epoch": 9.14, + "learning_rate": 1.1860691771927185e-05, + "loss": 0.0176, + "step": 10333 + }, + { + "epoch": 9.14, + "learning_rate": 1.185928370159381e-05, + "loss": 0.0171, + "step": 10334 + }, + { + "epoch": 9.14, + "learning_rate": 1.1857875593076116e-05, + "loss": 0.0178, + "step": 10335 + }, + { + "epoch": 9.14, + "learning_rate": 1.1856467446403016e-05, + "loss": 0.0166, + "step": 10336 + }, + { + "epoch": 9.15, + "learning_rate": 1.185505926160344e-05, + "loss": 0.0188, + "step": 10337 + }, + { + "epoch": 9.15, + "learning_rate": 1.1853651038706298e-05, + "loss": 0.0174, + "step": 10338 + }, + { + "epoch": 9.15, + "learning_rate": 1.1852242777740515e-05, + "loss": 0.0162, + "step": 10339 + }, + { + "epoch": 9.15, + "learning_rate": 1.1850834478735012e-05, + "loss": 0.0134, + "step": 10340 + }, + { + "epoch": 9.15, + "learning_rate": 1.1849426141718714e-05, + "loss": 0.0124, + "step": 10341 + }, + { + "epoch": 9.15, + "learning_rate": 1.1848017766720541e-05, + "loss": 0.0165, + "step": 10342 + }, + { + "epoch": 9.15, + "learning_rate": 1.1846609353769418e-05, + "loss": 0.0169, + "step": 10343 + }, + { + "epoch": 9.15, + "learning_rate": 1.184520090289427e-05, + "loss": 0.0157, + "step": 10344 + }, + { + "epoch": 9.15, + "learning_rate": 1.184379241412402e-05, + "loss": 0.0164, + "step": 10345 + }, + { + "epoch": 9.15, + "learning_rate": 1.1842383887487597e-05, + "loss": 0.0182, + "step": 10346 + }, + { + "epoch": 9.15, + "learning_rate": 1.1840975323013928e-05, + "loss": 0.0151, + "step": 10347 + }, + { + "epoch": 9.16, + "learning_rate": 1.1839566720731939e-05, + "loss": 0.0164, + "step": 10348 + }, + { + "epoch": 9.16, + "learning_rate": 1.1838158080670564e-05, + "loss": 0.0147, + "step": 10349 + }, + { + "epoch": 9.16, + "learning_rate": 1.1836749402858724e-05, + "loss": 0.0165, + "step": 10350 + }, + { + "epoch": 9.16, + "learning_rate": 1.1835340687325355e-05, + "loss": 0.0148, + "step": 10351 + }, + { + "epoch": 9.16, + "learning_rate": 1.1833931934099388e-05, + "loss": 0.0189, + "step": 10352 + }, + { + "epoch": 9.16, + "learning_rate": 1.1832523143209751e-05, + "loss": 0.0161, + "step": 10353 + }, + { + "epoch": 9.16, + "learning_rate": 1.1831114314685379e-05, + "loss": 0.0145, + "step": 10354 + }, + { + "epoch": 9.16, + "learning_rate": 1.1829705448555205e-05, + "loss": 0.0157, + "step": 10355 + }, + { + "epoch": 9.16, + "learning_rate": 1.1828296544848165e-05, + "loss": 0.0159, + "step": 10356 + }, + { + "epoch": 9.16, + "learning_rate": 1.1826887603593191e-05, + "loss": 0.0155, + "step": 10357 + }, + { + "epoch": 9.16, + "learning_rate": 1.1825478624819216e-05, + "loss": 0.0154, + "step": 10358 + }, + { + "epoch": 9.17, + "learning_rate": 1.1824069608555184e-05, + "loss": 0.0162, + "step": 10359 + }, + { + "epoch": 9.17, + "learning_rate": 1.1822660554830025e-05, + "loss": 0.0188, + "step": 10360 + }, + { + "epoch": 9.17, + "learning_rate": 1.1821251463672684e-05, + "loss": 0.0151, + "step": 10361 + }, + { + "epoch": 9.17, + "learning_rate": 1.181984233511209e-05, + "loss": 0.0177, + "step": 10362 + }, + { + "epoch": 9.17, + "learning_rate": 1.1818433169177193e-05, + "loss": 0.0188, + "step": 10363 + }, + { + "epoch": 9.17, + "learning_rate": 1.1817023965896925e-05, + "loss": 0.0161, + "step": 10364 + }, + { + "epoch": 9.17, + "learning_rate": 1.1815614725300229e-05, + "loss": 0.0158, + "step": 10365 + }, + { + "epoch": 9.17, + "learning_rate": 1.181420544741605e-05, + "loss": 0.015, + "step": 10366 + }, + { + "epoch": 9.17, + "learning_rate": 1.1812796132273328e-05, + "loss": 0.0159, + "step": 10367 + }, + { + "epoch": 9.17, + "learning_rate": 1.1811386779901006e-05, + "loss": 0.016, + "step": 10368 + }, + { + "epoch": 9.17, + "learning_rate": 1.180997739032803e-05, + "loss": 0.0165, + "step": 10369 + }, + { + "epoch": 9.17, + "learning_rate": 1.1808567963583341e-05, + "loss": 0.017, + "step": 10370 + }, + { + "epoch": 9.18, + "learning_rate": 1.1807158499695887e-05, + "loss": 0.0148, + "step": 10371 + }, + { + "epoch": 9.18, + "learning_rate": 1.1805748998694616e-05, + "loss": 0.0169, + "step": 10372 + }, + { + "epoch": 9.18, + "learning_rate": 1.1804339460608473e-05, + "loss": 0.0189, + "step": 10373 + }, + { + "epoch": 9.18, + "learning_rate": 1.1802929885466406e-05, + "loss": 0.0175, + "step": 10374 + }, + { + "epoch": 9.18, + "learning_rate": 1.1801520273297364e-05, + "loss": 0.0162, + "step": 10375 + }, + { + "epoch": 9.18, + "learning_rate": 1.1800110624130294e-05, + "loss": 0.0162, + "step": 10376 + }, + { + "epoch": 9.18, + "learning_rate": 1.1798700937994151e-05, + "loss": 0.0167, + "step": 10377 + }, + { + "epoch": 9.18, + "learning_rate": 1.1797291214917882e-05, + "loss": 0.0162, + "step": 10378 + }, + { + "epoch": 9.18, + "learning_rate": 1.1795881454930438e-05, + "loss": 0.0151, + "step": 10379 + }, + { + "epoch": 9.18, + "learning_rate": 1.1794471658060777e-05, + "loss": 0.0175, + "step": 10380 + }, + { + "epoch": 9.18, + "learning_rate": 1.1793061824337845e-05, + "loss": 0.0146, + "step": 10381 + }, + { + "epoch": 9.19, + "learning_rate": 1.1791651953790602e-05, + "loss": 0.0179, + "step": 10382 + }, + { + "epoch": 9.19, + "learning_rate": 1.1790242046448e-05, + "loss": 0.0177, + "step": 10383 + }, + { + "epoch": 9.19, + "learning_rate": 1.1788832102338992e-05, + "loss": 0.0208, + "step": 10384 + }, + { + "epoch": 9.19, + "learning_rate": 1.1787422121492538e-05, + "loss": 0.0185, + "step": 10385 + }, + { + "epoch": 9.19, + "learning_rate": 1.1786012103937592e-05, + "loss": 0.0177, + "step": 10386 + }, + { + "epoch": 9.19, + "learning_rate": 1.1784602049703115e-05, + "loss": 0.0166, + "step": 10387 + }, + { + "epoch": 9.19, + "learning_rate": 1.1783191958818064e-05, + "loss": 0.0169, + "step": 10388 + }, + { + "epoch": 9.19, + "learning_rate": 1.1781781831311397e-05, + "loss": 0.0194, + "step": 10389 + }, + { + "epoch": 9.19, + "learning_rate": 1.1780371667212073e-05, + "loss": 0.0159, + "step": 10390 + }, + { + "epoch": 9.19, + "learning_rate": 1.1778961466549054e-05, + "loss": 0.0164, + "step": 10391 + }, + { + "epoch": 9.19, + "learning_rate": 1.1777551229351306e-05, + "loss": 0.0178, + "step": 10392 + }, + { + "epoch": 9.2, + "learning_rate": 1.1776140955647784e-05, + "loss": 0.0157, + "step": 10393 + }, + { + "epoch": 9.2, + "learning_rate": 1.1774730645467456e-05, + "loss": 0.0163, + "step": 10394 + }, + { + "epoch": 9.2, + "learning_rate": 1.1773320298839284e-05, + "loss": 0.015, + "step": 10395 + }, + { + "epoch": 9.2, + "learning_rate": 1.177190991579223e-05, + "loss": 0.0203, + "step": 10396 + }, + { + "epoch": 9.2, + "learning_rate": 1.1770499496355262e-05, + "loss": 0.0158, + "step": 10397 + }, + { + "epoch": 9.2, + "learning_rate": 1.1769089040557344e-05, + "loss": 0.016, + "step": 10398 + }, + { + "epoch": 9.2, + "learning_rate": 1.1767678548427446e-05, + "loss": 0.0155, + "step": 10399 + }, + { + "epoch": 9.2, + "learning_rate": 1.1766268019994533e-05, + "loss": 0.0171, + "step": 10400 + }, + { + "epoch": 9.2, + "learning_rate": 1.1764857455287575e-05, + "loss": 0.0166, + "step": 10401 + }, + { + "epoch": 9.2, + "learning_rate": 1.176344685433554e-05, + "loss": 0.0174, + "step": 10402 + }, + { + "epoch": 9.2, + "learning_rate": 1.1762036217167395e-05, + "loss": 0.0173, + "step": 10403 + }, + { + "epoch": 9.21, + "learning_rate": 1.1760625543812112e-05, + "loss": 0.019, + "step": 10404 + }, + { + "epoch": 9.21, + "learning_rate": 1.1759214834298665e-05, + "loss": 0.0151, + "step": 10405 + }, + { + "epoch": 9.21, + "learning_rate": 1.1757804088656022e-05, + "loss": 0.015, + "step": 10406 + }, + { + "epoch": 9.21, + "learning_rate": 1.1756393306913158e-05, + "loss": 0.0151, + "step": 10407 + }, + { + "epoch": 9.21, + "learning_rate": 1.1754982489099047e-05, + "loss": 0.0204, + "step": 10408 + }, + { + "epoch": 9.21, + "learning_rate": 1.1753571635242662e-05, + "loss": 0.0161, + "step": 10409 + }, + { + "epoch": 9.21, + "learning_rate": 1.1752160745372974e-05, + "loss": 0.0167, + "step": 10410 + }, + { + "epoch": 9.21, + "learning_rate": 1.1750749819518967e-05, + "loss": 0.0142, + "step": 10411 + }, + { + "epoch": 9.21, + "learning_rate": 1.174933885770961e-05, + "loss": 0.0141, + "step": 10412 + }, + { + "epoch": 9.21, + "learning_rate": 1.1747927859973881e-05, + "loss": 0.017, + "step": 10413 + }, + { + "epoch": 9.21, + "learning_rate": 1.1746516826340763e-05, + "loss": 0.0154, + "step": 10414 + }, + { + "epoch": 9.21, + "learning_rate": 1.1745105756839235e-05, + "loss": 0.0164, + "step": 10415 + }, + { + "epoch": 9.22, + "learning_rate": 1.1743694651498266e-05, + "loss": 0.0158, + "step": 10416 + }, + { + "epoch": 9.22, + "learning_rate": 1.1742283510346842e-05, + "loss": 0.018, + "step": 10417 + }, + { + "epoch": 9.22, + "learning_rate": 1.1740872333413947e-05, + "loss": 0.0187, + "step": 10418 + }, + { + "epoch": 9.22, + "learning_rate": 1.173946112072856e-05, + "loss": 0.0144, + "step": 10419 + }, + { + "epoch": 9.22, + "learning_rate": 1.1738049872319662e-05, + "loss": 0.0147, + "step": 10420 + }, + { + "epoch": 9.22, + "learning_rate": 1.1736638588216236e-05, + "loss": 0.0185, + "step": 10421 + }, + { + "epoch": 9.22, + "learning_rate": 1.1735227268447272e-05, + "loss": 0.0151, + "step": 10422 + }, + { + "epoch": 9.22, + "learning_rate": 1.1733815913041742e-05, + "loss": 0.0163, + "step": 10423 + }, + { + "epoch": 9.22, + "learning_rate": 1.173240452202864e-05, + "loss": 0.0166, + "step": 10424 + }, + { + "epoch": 9.22, + "learning_rate": 1.1730993095436951e-05, + "loss": 0.0171, + "step": 10425 + }, + { + "epoch": 9.22, + "learning_rate": 1.1729581633295664e-05, + "loss": 0.0158, + "step": 10426 + }, + { + "epoch": 9.23, + "learning_rate": 1.1728170135633758e-05, + "loss": 0.014, + "step": 10427 + }, + { + "epoch": 9.23, + "learning_rate": 1.1726758602480228e-05, + "loss": 0.0189, + "step": 10428 + }, + { + "epoch": 9.23, + "learning_rate": 1.1725347033864063e-05, + "loss": 0.0156, + "step": 10429 + }, + { + "epoch": 9.23, + "learning_rate": 1.1723935429814249e-05, + "loss": 0.0192, + "step": 10430 + }, + { + "epoch": 9.23, + "learning_rate": 1.1722523790359777e-05, + "loss": 0.0185, + "step": 10431 + }, + { + "epoch": 9.23, + "learning_rate": 1.1721112115529637e-05, + "loss": 0.0159, + "step": 10432 + }, + { + "epoch": 9.23, + "learning_rate": 1.171970040535283e-05, + "loss": 0.0172, + "step": 10433 + }, + { + "epoch": 9.23, + "learning_rate": 1.1718288659858334e-05, + "loss": 0.0159, + "step": 10434 + }, + { + "epoch": 9.23, + "learning_rate": 1.1716876879075152e-05, + "loss": 0.0161, + "step": 10435 + }, + { + "epoch": 9.23, + "learning_rate": 1.1715465063032274e-05, + "loss": 0.0168, + "step": 10436 + }, + { + "epoch": 9.23, + "learning_rate": 1.1714053211758696e-05, + "loss": 0.019, + "step": 10437 + }, + { + "epoch": 9.24, + "learning_rate": 1.1712641325283414e-05, + "loss": 0.0175, + "step": 10438 + }, + { + "epoch": 9.24, + "learning_rate": 1.1711229403635423e-05, + "loss": 0.0147, + "step": 10439 + }, + { + "epoch": 9.24, + "learning_rate": 1.1709817446843721e-05, + "loss": 0.0169, + "step": 10440 + }, + { + "epoch": 9.24, + "learning_rate": 1.1708405454937303e-05, + "loss": 0.0164, + "step": 10441 + }, + { + "epoch": 9.24, + "learning_rate": 1.1706993427945168e-05, + "loss": 0.0172, + "step": 10442 + }, + { + "epoch": 9.24, + "learning_rate": 1.1705581365896317e-05, + "loss": 0.017, + "step": 10443 + }, + { + "epoch": 9.24, + "learning_rate": 1.1704169268819747e-05, + "loss": 0.0174, + "step": 10444 + }, + { + "epoch": 9.24, + "learning_rate": 1.170275713674446e-05, + "loss": 0.0154, + "step": 10445 + }, + { + "epoch": 9.24, + "learning_rate": 1.1701344969699457e-05, + "loss": 0.0161, + "step": 10446 + }, + { + "epoch": 9.24, + "learning_rate": 1.1699932767713742e-05, + "loss": 0.0181, + "step": 10447 + }, + { + "epoch": 9.24, + "learning_rate": 1.1698520530816313e-05, + "loss": 0.0196, + "step": 10448 + }, + { + "epoch": 9.24, + "learning_rate": 1.1697108259036176e-05, + "loss": 0.0186, + "step": 10449 + }, + { + "epoch": 9.25, + "learning_rate": 1.1695695952402335e-05, + "loss": 0.015, + "step": 10450 + }, + { + "epoch": 9.25, + "learning_rate": 1.1694283610943793e-05, + "loss": 0.0174, + "step": 10451 + }, + { + "epoch": 9.25, + "learning_rate": 1.1692871234689558e-05, + "loss": 0.0136, + "step": 10452 + }, + { + "epoch": 9.25, + "learning_rate": 1.1691458823668633e-05, + "loss": 0.0175, + "step": 10453 + }, + { + "epoch": 9.25, + "learning_rate": 1.169004637791003e-05, + "loss": 0.0178, + "step": 10454 + }, + { + "epoch": 9.25, + "learning_rate": 1.168863389744275e-05, + "loss": 0.0176, + "step": 10455 + }, + { + "epoch": 9.25, + "learning_rate": 1.1687221382295801e-05, + "loss": 0.0177, + "step": 10456 + }, + { + "epoch": 9.25, + "learning_rate": 1.1685808832498202e-05, + "loss": 0.0171, + "step": 10457 + }, + { + "epoch": 9.25, + "learning_rate": 1.1684396248078952e-05, + "loss": 0.0229, + "step": 10458 + }, + { + "epoch": 9.25, + "learning_rate": 1.1682983629067068e-05, + "loss": 0.0172, + "step": 10459 + }, + { + "epoch": 9.25, + "learning_rate": 1.1681570975491558e-05, + "loss": 0.0175, + "step": 10460 + }, + { + "epoch": 9.26, + "learning_rate": 1.1680158287381435e-05, + "loss": 0.0197, + "step": 10461 + }, + { + "epoch": 9.26, + "learning_rate": 1.167874556476571e-05, + "loss": 0.0165, + "step": 10462 + }, + { + "epoch": 9.26, + "learning_rate": 1.1677332807673396e-05, + "loss": 0.0175, + "step": 10463 + }, + { + "epoch": 9.26, + "learning_rate": 1.167592001613351e-05, + "loss": 0.015, + "step": 10464 + }, + { + "epoch": 9.26, + "learning_rate": 1.1674507190175065e-05, + "loss": 0.0167, + "step": 10465 + }, + { + "epoch": 9.26, + "learning_rate": 1.1673094329827074e-05, + "loss": 0.0158, + "step": 10466 + }, + { + "epoch": 9.26, + "learning_rate": 1.1671681435118558e-05, + "loss": 0.0176, + "step": 10467 + }, + { + "epoch": 9.26, + "learning_rate": 1.1670268506078533e-05, + "loss": 0.0153, + "step": 10468 + }, + { + "epoch": 9.26, + "learning_rate": 1.1668855542736008e-05, + "loss": 0.0167, + "step": 10469 + }, + { + "epoch": 9.26, + "learning_rate": 1.1667442545120011e-05, + "loss": 0.0133, + "step": 10470 + }, + { + "epoch": 9.26, + "learning_rate": 1.1666029513259561e-05, + "loss": 0.0136, + "step": 10471 + }, + { + "epoch": 9.27, + "learning_rate": 1.1664616447183669e-05, + "loss": 0.0173, + "step": 10472 + }, + { + "epoch": 9.27, + "learning_rate": 1.1663203346921363e-05, + "loss": 0.0181, + "step": 10473 + }, + { + "epoch": 9.27, + "learning_rate": 1.1661790212501662e-05, + "loss": 0.0172, + "step": 10474 + }, + { + "epoch": 9.27, + "learning_rate": 1.1660377043953588e-05, + "loss": 0.0144, + "step": 10475 + }, + { + "epoch": 9.27, + "learning_rate": 1.165896384130616e-05, + "loss": 0.0196, + "step": 10476 + }, + { + "epoch": 9.27, + "learning_rate": 1.1657550604588404e-05, + "loss": 0.0183, + "step": 10477 + }, + { + "epoch": 9.27, + "learning_rate": 1.1656137333829345e-05, + "loss": 0.015, + "step": 10478 + }, + { + "epoch": 9.27, + "learning_rate": 1.1654724029058007e-05, + "loss": 0.0181, + "step": 10479 + }, + { + "epoch": 9.27, + "learning_rate": 1.1653310690303412e-05, + "loss": 0.0145, + "step": 10480 + }, + { + "epoch": 9.27, + "learning_rate": 1.1651897317594586e-05, + "loss": 0.018, + "step": 10481 + }, + { + "epoch": 9.27, + "learning_rate": 1.1650483910960562e-05, + "loss": 0.0165, + "step": 10482 + }, + { + "epoch": 9.27, + "learning_rate": 1.1649070470430362e-05, + "loss": 0.0176, + "step": 10483 + }, + { + "epoch": 9.28, + "learning_rate": 1.1647656996033012e-05, + "loss": 0.0145, + "step": 10484 + }, + { + "epoch": 9.28, + "learning_rate": 1.1646243487797548e-05, + "loss": 0.0146, + "step": 10485 + }, + { + "epoch": 9.28, + "learning_rate": 1.1644829945752994e-05, + "loss": 0.0173, + "step": 10486 + }, + { + "epoch": 9.28, + "learning_rate": 1.164341636992838e-05, + "loss": 0.016, + "step": 10487 + }, + { + "epoch": 9.28, + "learning_rate": 1.1642002760352737e-05, + "loss": 0.0138, + "step": 10488 + }, + { + "epoch": 9.28, + "learning_rate": 1.16405891170551e-05, + "loss": 0.0149, + "step": 10489 + }, + { + "epoch": 9.28, + "learning_rate": 1.1639175440064496e-05, + "loss": 0.0174, + "step": 10490 + }, + { + "epoch": 9.28, + "learning_rate": 1.1637761729409962e-05, + "loss": 0.0162, + "step": 10491 + }, + { + "epoch": 9.28, + "learning_rate": 1.163634798512053e-05, + "loss": 0.0167, + "step": 10492 + }, + { + "epoch": 9.28, + "learning_rate": 1.1634934207225234e-05, + "loss": 0.0169, + "step": 10493 + }, + { + "epoch": 9.28, + "learning_rate": 1.1633520395753108e-05, + "loss": 0.0163, + "step": 10494 + }, + { + "epoch": 9.29, + "learning_rate": 1.1632106550733189e-05, + "loss": 0.0168, + "step": 10495 + }, + { + "epoch": 9.29, + "learning_rate": 1.1630692672194512e-05, + "loss": 0.0185, + "step": 10496 + }, + { + "epoch": 9.29, + "learning_rate": 1.1629278760166116e-05, + "loss": 0.0144, + "step": 10497 + }, + { + "epoch": 9.29, + "learning_rate": 1.1627864814677037e-05, + "loss": 0.0215, + "step": 10498 + }, + { + "epoch": 9.29, + "learning_rate": 1.1626450835756317e-05, + "loss": 0.0161, + "step": 10499 + }, + { + "epoch": 9.29, + "learning_rate": 1.162503682343299e-05, + "loss": 0.0161, + "step": 10500 + }, + { + "epoch": 9.29, + "learning_rate": 1.1623622777736096e-05, + "loss": 0.0162, + "step": 10501 + }, + { + "epoch": 9.29, + "learning_rate": 1.162220869869468e-05, + "loss": 0.0196, + "step": 10502 + }, + { + "epoch": 9.29, + "learning_rate": 1.1620794586337778e-05, + "loss": 0.0142, + "step": 10503 + }, + { + "epoch": 9.29, + "learning_rate": 1.1619380440694435e-05, + "loss": 0.017, + "step": 10504 + }, + { + "epoch": 9.29, + "learning_rate": 1.1617966261793691e-05, + "loss": 0.0152, + "step": 10505 + }, + { + "epoch": 9.3, + "learning_rate": 1.1616552049664593e-05, + "loss": 0.0177, + "step": 10506 + }, + { + "epoch": 9.3, + "learning_rate": 1.1615137804336183e-05, + "loss": 0.0169, + "step": 10507 + }, + { + "epoch": 9.3, + "learning_rate": 1.1613723525837501e-05, + "loss": 0.0166, + "step": 10508 + }, + { + "epoch": 9.3, + "learning_rate": 1.1612309214197599e-05, + "loss": 0.0131, + "step": 10509 + }, + { + "epoch": 9.3, + "learning_rate": 1.1610894869445522e-05, + "loss": 0.0142, + "step": 10510 + }, + { + "epoch": 9.3, + "learning_rate": 1.160948049161031e-05, + "loss": 0.016, + "step": 10511 + }, + { + "epoch": 9.3, + "learning_rate": 1.1608066080721019e-05, + "loss": 0.0165, + "step": 10512 + }, + { + "epoch": 9.3, + "learning_rate": 1.1606651636806691e-05, + "loss": 0.0164, + "step": 10513 + }, + { + "epoch": 9.3, + "learning_rate": 1.1605237159896376e-05, + "loss": 0.0163, + "step": 10514 + }, + { + "epoch": 9.3, + "learning_rate": 1.1603822650019124e-05, + "loss": 0.0174, + "step": 10515 + }, + { + "epoch": 9.3, + "learning_rate": 1.1602408107203986e-05, + "loss": 0.0166, + "step": 10516 + }, + { + "epoch": 9.31, + "learning_rate": 1.160099353148001e-05, + "loss": 0.0194, + "step": 10517 + }, + { + "epoch": 9.31, + "learning_rate": 1.1599578922876247e-05, + "loss": 0.0193, + "step": 10518 + }, + { + "epoch": 9.31, + "learning_rate": 1.1598164281421753e-05, + "loss": 0.0166, + "step": 10519 + }, + { + "epoch": 9.31, + "learning_rate": 1.1596749607145579e-05, + "loss": 0.0164, + "step": 10520 + }, + { + "epoch": 9.31, + "learning_rate": 1.1595334900076773e-05, + "loss": 0.0198, + "step": 10521 + }, + { + "epoch": 9.31, + "learning_rate": 1.1593920160244396e-05, + "loss": 0.0217, + "step": 10522 + }, + { + "epoch": 9.31, + "learning_rate": 1.1592505387677502e-05, + "loss": 0.0171, + "step": 10523 + }, + { + "epoch": 9.31, + "learning_rate": 1.1591090582405142e-05, + "loss": 0.0167, + "step": 10524 + }, + { + "epoch": 9.31, + "learning_rate": 1.1589675744456377e-05, + "loss": 0.0207, + "step": 10525 + }, + { + "epoch": 9.31, + "learning_rate": 1.158826087386026e-05, + "loss": 0.0194, + "step": 10526 + }, + { + "epoch": 9.31, + "learning_rate": 1.1586845970645851e-05, + "loss": 0.0155, + "step": 10527 + }, + { + "epoch": 9.31, + "learning_rate": 1.1585431034842201e-05, + "loss": 0.0163, + "step": 10528 + }, + { + "epoch": 9.32, + "learning_rate": 1.1584016066478378e-05, + "loss": 0.0181, + "step": 10529 + }, + { + "epoch": 9.32, + "learning_rate": 1.1582601065583441e-05, + "loss": 0.0156, + "step": 10530 + }, + { + "epoch": 9.32, + "learning_rate": 1.1581186032186442e-05, + "loss": 0.0168, + "step": 10531 + }, + { + "epoch": 9.32, + "learning_rate": 1.1579770966316449e-05, + "loss": 0.017, + "step": 10532 + }, + { + "epoch": 9.32, + "learning_rate": 1.1578355868002518e-05, + "loss": 0.0158, + "step": 10533 + }, + { + "epoch": 9.32, + "learning_rate": 1.1576940737273717e-05, + "loss": 0.0154, + "step": 10534 + }, + { + "epoch": 9.32, + "learning_rate": 1.1575525574159103e-05, + "loss": 0.0171, + "step": 10535 + }, + { + "epoch": 9.32, + "learning_rate": 1.1574110378687742e-05, + "loss": 0.0177, + "step": 10536 + }, + { + "epoch": 9.32, + "learning_rate": 1.1572695150888702e-05, + "loss": 0.0137, + "step": 10537 + }, + { + "epoch": 9.32, + "learning_rate": 1.1571279890791038e-05, + "loss": 0.0186, + "step": 10538 + }, + { + "epoch": 9.32, + "learning_rate": 1.1569864598423823e-05, + "loss": 0.017, + "step": 10539 + }, + { + "epoch": 9.33, + "learning_rate": 1.1568449273816123e-05, + "loss": 0.018, + "step": 10540 + }, + { + "epoch": 9.33, + "learning_rate": 1.1567033916997e-05, + "loss": 0.0193, + "step": 10541 + }, + { + "epoch": 9.33, + "learning_rate": 1.1565618527995524e-05, + "loss": 0.0154, + "step": 10542 + }, + { + "epoch": 9.33, + "learning_rate": 1.1564203106840763e-05, + "loss": 0.0186, + "step": 10543 + }, + { + "epoch": 9.33, + "learning_rate": 1.156278765356179e-05, + "loss": 0.0216, + "step": 10544 + }, + { + "epoch": 9.33, + "learning_rate": 1.1561372168187666e-05, + "loss": 0.0158, + "step": 10545 + }, + { + "epoch": 9.33, + "learning_rate": 1.1559956650747465e-05, + "loss": 0.0218, + "step": 10546 + }, + { + "epoch": 9.33, + "learning_rate": 1.1558541101270255e-05, + "loss": 0.0185, + "step": 10547 + }, + { + "epoch": 9.33, + "learning_rate": 1.1557125519785115e-05, + "loss": 0.0205, + "step": 10548 + }, + { + "epoch": 9.33, + "learning_rate": 1.1555709906321111e-05, + "loss": 0.0158, + "step": 10549 + }, + { + "epoch": 9.33, + "learning_rate": 1.1554294260907314e-05, + "loss": 0.0186, + "step": 10550 + }, + { + "epoch": 9.34, + "learning_rate": 1.1552878583572803e-05, + "loss": 0.0195, + "step": 10551 + }, + { + "epoch": 9.34, + "learning_rate": 1.1551462874346648e-05, + "loss": 0.0183, + "step": 10552 + }, + { + "epoch": 9.34, + "learning_rate": 1.1550047133257922e-05, + "loss": 0.0195, + "step": 10553 + }, + { + "epoch": 9.34, + "learning_rate": 1.15486313603357e-05, + "loss": 0.017, + "step": 10554 + }, + { + "epoch": 9.34, + "learning_rate": 1.1547215555609067e-05, + "loss": 0.017, + "step": 10555 + }, + { + "epoch": 9.34, + "learning_rate": 1.1545799719107089e-05, + "loss": 0.0182, + "step": 10556 + }, + { + "epoch": 9.34, + "learning_rate": 1.1544383850858849e-05, + "loss": 0.0209, + "step": 10557 + }, + { + "epoch": 9.34, + "learning_rate": 1.1542967950893423e-05, + "loss": 0.0181, + "step": 10558 + }, + { + "epoch": 9.34, + "learning_rate": 1.154155201923989e-05, + "loss": 0.0159, + "step": 10559 + }, + { + "epoch": 9.34, + "learning_rate": 1.1540136055927324e-05, + "loss": 0.0165, + "step": 10560 + }, + { + "epoch": 9.34, + "learning_rate": 1.1538720060984812e-05, + "loss": 0.0176, + "step": 10561 + }, + { + "epoch": 9.34, + "learning_rate": 1.1537304034441435e-05, + "loss": 0.0175, + "step": 10562 + }, + { + "epoch": 9.35, + "learning_rate": 1.1535887976326267e-05, + "loss": 0.0199, + "step": 10563 + }, + { + "epoch": 9.35, + "learning_rate": 1.1534471886668394e-05, + "loss": 0.0177, + "step": 10564 + }, + { + "epoch": 9.35, + "learning_rate": 1.1533055765496898e-05, + "loss": 0.02, + "step": 10565 + }, + { + "epoch": 9.35, + "learning_rate": 1.1531639612840868e-05, + "loss": 0.016, + "step": 10566 + }, + { + "epoch": 9.35, + "learning_rate": 1.1530223428729372e-05, + "loss": 0.0198, + "step": 10567 + }, + { + "epoch": 9.35, + "learning_rate": 1.1528807213191511e-05, + "loss": 0.0188, + "step": 10568 + }, + { + "epoch": 9.35, + "learning_rate": 1.1527390966256362e-05, + "loss": 0.0181, + "step": 10569 + }, + { + "epoch": 9.35, + "learning_rate": 1.1525974687953012e-05, + "loss": 0.0212, + "step": 10570 + }, + { + "epoch": 9.35, + "learning_rate": 1.1524558378310547e-05, + "loss": 0.0164, + "step": 10571 + }, + { + "epoch": 9.35, + "learning_rate": 1.152314203735805e-05, + "loss": 0.0186, + "step": 10572 + }, + { + "epoch": 9.35, + "learning_rate": 1.1521725665124618e-05, + "loss": 0.015, + "step": 10573 + }, + { + "epoch": 9.36, + "learning_rate": 1.1520309261639331e-05, + "loss": 0.0174, + "step": 10574 + }, + { + "epoch": 9.36, + "learning_rate": 1.1518892826931279e-05, + "loss": 0.0191, + "step": 10575 + }, + { + "epoch": 9.36, + "learning_rate": 1.1517476361029556e-05, + "loss": 0.0207, + "step": 10576 + }, + { + "epoch": 9.36, + "learning_rate": 1.151605986396325e-05, + "loss": 0.0153, + "step": 10577 + }, + { + "epoch": 9.36, + "learning_rate": 1.1514643335761449e-05, + "loss": 0.0215, + "step": 10578 + }, + { + "epoch": 9.36, + "learning_rate": 1.1513226776453244e-05, + "loss": 0.0142, + "step": 10579 + }, + { + "epoch": 9.36, + "learning_rate": 1.151181018606773e-05, + "loss": 0.0178, + "step": 10580 + }, + { + "epoch": 9.36, + "learning_rate": 1.1510393564634e-05, + "loss": 0.0177, + "step": 10581 + }, + { + "epoch": 9.36, + "learning_rate": 1.1508976912181149e-05, + "loss": 0.0174, + "step": 10582 + }, + { + "epoch": 9.36, + "learning_rate": 1.1507560228738268e-05, + "loss": 0.0152, + "step": 10583 + }, + { + "epoch": 9.36, + "learning_rate": 1.150614351433445e-05, + "loss": 0.0162, + "step": 10584 + }, + { + "epoch": 9.37, + "learning_rate": 1.1504726768998791e-05, + "loss": 0.0158, + "step": 10585 + }, + { + "epoch": 9.37, + "learning_rate": 1.1503309992760387e-05, + "loss": 0.0161, + "step": 10586 + }, + { + "epoch": 9.37, + "learning_rate": 1.1501893185648338e-05, + "loss": 0.0158, + "step": 10587 + }, + { + "epoch": 9.37, + "learning_rate": 1.1500476347691738e-05, + "loss": 0.0183, + "step": 10588 + }, + { + "epoch": 9.37, + "learning_rate": 1.1499059478919685e-05, + "loss": 0.017, + "step": 10589 + }, + { + "epoch": 9.37, + "learning_rate": 1.1497642579361281e-05, + "loss": 0.0151, + "step": 10590 + }, + { + "epoch": 9.37, + "learning_rate": 1.1496225649045618e-05, + "loss": 0.0181, + "step": 10591 + }, + { + "epoch": 9.37, + "learning_rate": 1.1494808688001799e-05, + "loss": 0.0174, + "step": 10592 + }, + { + "epoch": 9.37, + "learning_rate": 1.1493391696258927e-05, + "loss": 0.0177, + "step": 10593 + }, + { + "epoch": 9.37, + "learning_rate": 1.1491974673846097e-05, + "loss": 0.019, + "step": 10594 + }, + { + "epoch": 9.37, + "learning_rate": 1.1490557620792418e-05, + "loss": 0.0216, + "step": 10595 + }, + { + "epoch": 9.37, + "learning_rate": 1.1489140537126988e-05, + "loss": 0.0222, + "step": 10596 + }, + { + "epoch": 9.38, + "learning_rate": 1.1487723422878912e-05, + "loss": 0.0165, + "step": 10597 + }, + { + "epoch": 9.38, + "learning_rate": 1.1486306278077286e-05, + "loss": 0.0216, + "step": 10598 + }, + { + "epoch": 9.38, + "learning_rate": 1.148488910275122e-05, + "loss": 0.0155, + "step": 10599 + }, + { + "epoch": 9.38, + "learning_rate": 1.1483471896929824e-05, + "loss": 0.0205, + "step": 10600 + }, + { + "epoch": 9.38, + "learning_rate": 1.1482054660642194e-05, + "loss": 0.0163, + "step": 10601 + }, + { + "epoch": 9.38, + "learning_rate": 1.148063739391744e-05, + "loss": 0.0145, + "step": 10602 + }, + { + "epoch": 9.38, + "learning_rate": 1.1479220096784666e-05, + "loss": 0.0175, + "step": 10603 + }, + { + "epoch": 9.38, + "learning_rate": 1.1477802769272988e-05, + "loss": 0.0217, + "step": 10604 + }, + { + "epoch": 9.38, + "learning_rate": 1.1476385411411502e-05, + "loss": 0.0186, + "step": 10605 + }, + { + "epoch": 9.38, + "learning_rate": 1.147496802322932e-05, + "loss": 0.0175, + "step": 10606 + }, + { + "epoch": 9.38, + "learning_rate": 1.1473550604755557e-05, + "loss": 0.0205, + "step": 10607 + }, + { + "epoch": 9.39, + "learning_rate": 1.1472133156019317e-05, + "loss": 0.0189, + "step": 10608 + }, + { + "epoch": 9.39, + "learning_rate": 1.1470715677049709e-05, + "loss": 0.0175, + "step": 10609 + }, + { + "epoch": 9.39, + "learning_rate": 1.1469298167875848e-05, + "loss": 0.0171, + "step": 10610 + }, + { + "epoch": 9.39, + "learning_rate": 1.1467880628526849e-05, + "loss": 0.0154, + "step": 10611 + }, + { + "epoch": 9.39, + "learning_rate": 1.1466463059031813e-05, + "loss": 0.0195, + "step": 10612 + }, + { + "epoch": 9.39, + "learning_rate": 1.1465045459419858e-05, + "loss": 0.0187, + "step": 10613 + }, + { + "epoch": 9.39, + "learning_rate": 1.1463627829720106e-05, + "loss": 0.018, + "step": 10614 + }, + { + "epoch": 9.39, + "learning_rate": 1.1462210169961658e-05, + "loss": 0.0204, + "step": 10615 + }, + { + "epoch": 9.39, + "learning_rate": 1.1460792480173635e-05, + "loss": 0.0159, + "step": 10616 + }, + { + "epoch": 9.39, + "learning_rate": 1.145937476038515e-05, + "loss": 0.0191, + "step": 10617 + }, + { + "epoch": 9.39, + "learning_rate": 1.1457957010625327e-05, + "loss": 0.0164, + "step": 10618 + }, + { + "epoch": 9.4, + "learning_rate": 1.1456539230923266e-05, + "loss": 0.0178, + "step": 10619 + }, + { + "epoch": 9.4, + "learning_rate": 1.14551214213081e-05, + "loss": 0.0165, + "step": 10620 + }, + { + "epoch": 9.4, + "learning_rate": 1.1453703581808942e-05, + "loss": 0.0143, + "step": 10621 + }, + { + "epoch": 9.4, + "learning_rate": 1.1452285712454905e-05, + "loss": 0.0184, + "step": 10622 + }, + { + "epoch": 9.4, + "learning_rate": 1.1450867813275112e-05, + "loss": 0.0146, + "step": 10623 + }, + { + "epoch": 9.4, + "learning_rate": 1.1449449884298685e-05, + "loss": 0.0198, + "step": 10624 + }, + { + "epoch": 9.4, + "learning_rate": 1.144803192555474e-05, + "loss": 0.0158, + "step": 10625 + }, + { + "epoch": 9.4, + "learning_rate": 1.1446613937072397e-05, + "loss": 0.0148, + "step": 10626 + }, + { + "epoch": 9.4, + "learning_rate": 1.1445195918880782e-05, + "loss": 0.0151, + "step": 10627 + }, + { + "epoch": 9.4, + "learning_rate": 1.1443777871009019e-05, + "loss": 0.0186, + "step": 10628 + }, + { + "epoch": 9.4, + "learning_rate": 1.1442359793486222e-05, + "loss": 0.017, + "step": 10629 + }, + { + "epoch": 9.4, + "learning_rate": 1.1440941686341518e-05, + "loss": 0.0172, + "step": 10630 + }, + { + "epoch": 9.41, + "learning_rate": 1.1439523549604032e-05, + "loss": 0.0188, + "step": 10631 + }, + { + "epoch": 9.41, + "learning_rate": 1.1438105383302887e-05, + "loss": 0.0182, + "step": 10632 + }, + { + "epoch": 9.41, + "learning_rate": 1.143668718746721e-05, + "loss": 0.0168, + "step": 10633 + }, + { + "epoch": 9.41, + "learning_rate": 1.1435268962126127e-05, + "loss": 0.0167, + "step": 10634 + }, + { + "epoch": 9.41, + "learning_rate": 1.1433850707308763e-05, + "loss": 0.0207, + "step": 10635 + }, + { + "epoch": 9.41, + "learning_rate": 1.1432432423044243e-05, + "loss": 0.0201, + "step": 10636 + }, + { + "epoch": 9.41, + "learning_rate": 1.1431014109361696e-05, + "loss": 0.0189, + "step": 10637 + }, + { + "epoch": 9.41, + "learning_rate": 1.142959576629025e-05, + "loss": 0.016, + "step": 10638 + }, + { + "epoch": 9.41, + "learning_rate": 1.1428177393859032e-05, + "loss": 0.0188, + "step": 10639 + }, + { + "epoch": 9.41, + "learning_rate": 1.1426758992097176e-05, + "loss": 0.0195, + "step": 10640 + }, + { + "epoch": 9.41, + "learning_rate": 1.1425340561033809e-05, + "loss": 0.0168, + "step": 10641 + }, + { + "epoch": 9.42, + "learning_rate": 1.1423922100698061e-05, + "loss": 0.0178, + "step": 10642 + }, + { + "epoch": 9.42, + "learning_rate": 1.1422503611119065e-05, + "loss": 0.0145, + "step": 10643 + }, + { + "epoch": 9.42, + "learning_rate": 1.142108509232595e-05, + "loss": 0.019, + "step": 10644 + }, + { + "epoch": 9.42, + "learning_rate": 1.1419666544347847e-05, + "loss": 0.0189, + "step": 10645 + }, + { + "epoch": 9.42, + "learning_rate": 1.1418247967213894e-05, + "loss": 0.0178, + "step": 10646 + }, + { + "epoch": 9.42, + "learning_rate": 1.141682936095322e-05, + "loss": 0.0198, + "step": 10647 + }, + { + "epoch": 9.42, + "learning_rate": 1.1415410725594963e-05, + "loss": 0.0181, + "step": 10648 + }, + { + "epoch": 9.42, + "learning_rate": 1.1413992061168258e-05, + "loss": 0.0188, + "step": 10649 + }, + { + "epoch": 9.42, + "learning_rate": 1.1412573367702235e-05, + "loss": 0.0198, + "step": 10650 + }, + { + "epoch": 9.42, + "learning_rate": 1.1411154645226032e-05, + "loss": 0.0173, + "step": 10651 + }, + { + "epoch": 9.42, + "learning_rate": 1.1409735893768787e-05, + "loss": 0.0187, + "step": 10652 + }, + { + "epoch": 9.43, + "learning_rate": 1.1408317113359638e-05, + "loss": 0.0187, + "step": 10653 + }, + { + "epoch": 9.43, + "learning_rate": 1.1406898304027718e-05, + "loss": 0.015, + "step": 10654 + }, + { + "epoch": 9.43, + "learning_rate": 1.140547946580217e-05, + "loss": 0.0176, + "step": 10655 + }, + { + "epoch": 9.43, + "learning_rate": 1.1404060598712132e-05, + "loss": 0.0162, + "step": 10656 + }, + { + "epoch": 9.43, + "learning_rate": 1.140264170278674e-05, + "loss": 0.0174, + "step": 10657 + }, + { + "epoch": 9.43, + "learning_rate": 1.1401222778055136e-05, + "loss": 0.0184, + "step": 10658 + }, + { + "epoch": 9.43, + "learning_rate": 1.1399803824546464e-05, + "loss": 0.0173, + "step": 10659 + }, + { + "epoch": 9.43, + "learning_rate": 1.139838484228986e-05, + "loss": 0.0193, + "step": 10660 + }, + { + "epoch": 9.43, + "learning_rate": 1.1396965831314471e-05, + "loss": 0.0187, + "step": 10661 + }, + { + "epoch": 9.43, + "learning_rate": 1.1395546791649434e-05, + "loss": 0.0184, + "step": 10662 + }, + { + "epoch": 9.43, + "learning_rate": 1.1394127723323898e-05, + "loss": 0.0185, + "step": 10663 + }, + { + "epoch": 9.44, + "learning_rate": 1.1392708626366999e-05, + "loss": 0.0152, + "step": 10664 + }, + { + "epoch": 9.44, + "learning_rate": 1.1391289500807883e-05, + "loss": 0.0157, + "step": 10665 + }, + { + "epoch": 9.44, + "learning_rate": 1.1389870346675702e-05, + "loss": 0.0205, + "step": 10666 + }, + { + "epoch": 9.44, + "learning_rate": 1.1388451163999596e-05, + "loss": 0.0213, + "step": 10667 + }, + { + "epoch": 9.44, + "learning_rate": 1.1387031952808708e-05, + "loss": 0.0169, + "step": 10668 + }, + { + "epoch": 9.44, + "learning_rate": 1.1385612713132191e-05, + "loss": 0.0164, + "step": 10669 + }, + { + "epoch": 9.44, + "learning_rate": 1.138419344499919e-05, + "loss": 0.0172, + "step": 10670 + }, + { + "epoch": 9.44, + "learning_rate": 1.1382774148438847e-05, + "loss": 0.0169, + "step": 10671 + }, + { + "epoch": 9.44, + "learning_rate": 1.1381354823480315e-05, + "loss": 0.0184, + "step": 10672 + }, + { + "epoch": 9.44, + "learning_rate": 1.1379935470152746e-05, + "loss": 0.0218, + "step": 10673 + }, + { + "epoch": 9.44, + "learning_rate": 1.1378516088485285e-05, + "loss": 0.0191, + "step": 10674 + }, + { + "epoch": 9.44, + "learning_rate": 1.1377096678507083e-05, + "loss": 0.019, + "step": 10675 + }, + { + "epoch": 9.45, + "learning_rate": 1.137567724024729e-05, + "loss": 0.0177, + "step": 10676 + }, + { + "epoch": 9.45, + "learning_rate": 1.1374257773735056e-05, + "loss": 0.0178, + "step": 10677 + }, + { + "epoch": 9.45, + "learning_rate": 1.1372838278999537e-05, + "loss": 0.0179, + "step": 10678 + }, + { + "epoch": 9.45, + "learning_rate": 1.1371418756069881e-05, + "loss": 0.0186, + "step": 10679 + }, + { + "epoch": 9.45, + "learning_rate": 1.1369999204975245e-05, + "loss": 0.0175, + "step": 10680 + }, + { + "epoch": 9.45, + "learning_rate": 1.1368579625744777e-05, + "loss": 0.0146, + "step": 10681 + }, + { + "epoch": 9.45, + "learning_rate": 1.1367160018407638e-05, + "loss": 0.0188, + "step": 10682 + }, + { + "epoch": 9.45, + "learning_rate": 1.1365740382992975e-05, + "loss": 0.0188, + "step": 10683 + }, + { + "epoch": 9.45, + "learning_rate": 1.1364320719529949e-05, + "loss": 0.0177, + "step": 10684 + }, + { + "epoch": 9.45, + "learning_rate": 1.1362901028047714e-05, + "loss": 0.0148, + "step": 10685 + }, + { + "epoch": 9.45, + "learning_rate": 1.1361481308575427e-05, + "loss": 0.02, + "step": 10686 + }, + { + "epoch": 9.46, + "learning_rate": 1.1360061561142241e-05, + "loss": 0.0176, + "step": 10687 + }, + { + "epoch": 9.46, + "learning_rate": 1.1358641785777322e-05, + "loss": 0.0171, + "step": 10688 + }, + { + "epoch": 9.46, + "learning_rate": 1.135722198250982e-05, + "loss": 0.0175, + "step": 10689 + }, + { + "epoch": 9.46, + "learning_rate": 1.1355802151368895e-05, + "loss": 0.0161, + "step": 10690 + }, + { + "epoch": 9.46, + "learning_rate": 1.135438229238371e-05, + "loss": 0.0174, + "step": 10691 + }, + { + "epoch": 9.46, + "learning_rate": 1.1352962405583421e-05, + "loss": 0.0183, + "step": 10692 + }, + { + "epoch": 9.46, + "learning_rate": 1.135154249099719e-05, + "loss": 0.0208, + "step": 10693 + }, + { + "epoch": 9.46, + "learning_rate": 1.1350122548654179e-05, + "loss": 0.0184, + "step": 10694 + }, + { + "epoch": 9.46, + "learning_rate": 1.1348702578583548e-05, + "loss": 0.0176, + "step": 10695 + }, + { + "epoch": 9.46, + "learning_rate": 1.1347282580814457e-05, + "loss": 0.0175, + "step": 10696 + }, + { + "epoch": 9.46, + "learning_rate": 1.1345862555376073e-05, + "loss": 0.0174, + "step": 10697 + }, + { + "epoch": 9.47, + "learning_rate": 1.1344442502297559e-05, + "loss": 0.0187, + "step": 10698 + }, + { + "epoch": 9.47, + "learning_rate": 1.1343022421608074e-05, + "loss": 0.019, + "step": 10699 + }, + { + "epoch": 9.47, + "learning_rate": 1.1341602313336786e-05, + "loss": 0.0153, + "step": 10700 + }, + { + "epoch": 9.47, + "learning_rate": 1.1340182177512862e-05, + "loss": 0.0172, + "step": 10701 + }, + { + "epoch": 9.47, + "learning_rate": 1.1338762014165464e-05, + "loss": 0.0199, + "step": 10702 + }, + { + "epoch": 9.47, + "learning_rate": 1.1337341823323758e-05, + "loss": 0.0175, + "step": 10703 + }, + { + "epoch": 9.47, + "learning_rate": 1.1335921605016908e-05, + "loss": 0.0182, + "step": 10704 + }, + { + "epoch": 9.47, + "learning_rate": 1.133450135927409e-05, + "loss": 0.0179, + "step": 10705 + }, + { + "epoch": 9.47, + "learning_rate": 1.1333081086124465e-05, + "loss": 0.0181, + "step": 10706 + }, + { + "epoch": 9.47, + "learning_rate": 1.1331660785597203e-05, + "loss": 0.0165, + "step": 10707 + }, + { + "epoch": 9.47, + "learning_rate": 1.1330240457721471e-05, + "loss": 0.0184, + "step": 10708 + }, + { + "epoch": 9.47, + "learning_rate": 1.1328820102526444e-05, + "loss": 0.016, + "step": 10709 + }, + { + "epoch": 9.48, + "learning_rate": 1.1327399720041282e-05, + "loss": 0.0177, + "step": 10710 + }, + { + "epoch": 9.48, + "learning_rate": 1.1325979310295162e-05, + "loss": 0.0205, + "step": 10711 + }, + { + "epoch": 9.48, + "learning_rate": 1.1324558873317262e-05, + "loss": 0.0212, + "step": 10712 + }, + { + "epoch": 9.48, + "learning_rate": 1.132313840913674e-05, + "loss": 0.0178, + "step": 10713 + }, + { + "epoch": 9.48, + "learning_rate": 1.1321717917782777e-05, + "loss": 0.0188, + "step": 10714 + }, + { + "epoch": 9.48, + "learning_rate": 1.1320297399284544e-05, + "loss": 0.0168, + "step": 10715 + }, + { + "epoch": 9.48, + "learning_rate": 1.1318876853671214e-05, + "loss": 0.0195, + "step": 10716 + }, + { + "epoch": 9.48, + "learning_rate": 1.1317456280971956e-05, + "loss": 0.0195, + "step": 10717 + }, + { + "epoch": 9.48, + "learning_rate": 1.1316035681215953e-05, + "loss": 0.019, + "step": 10718 + }, + { + "epoch": 9.48, + "learning_rate": 1.1314615054432378e-05, + "loss": 0.0189, + "step": 10719 + }, + { + "epoch": 9.48, + "learning_rate": 1.1313194400650403e-05, + "loss": 0.0202, + "step": 10720 + }, + { + "epoch": 9.49, + "learning_rate": 1.1311773719899204e-05, + "loss": 0.0188, + "step": 10721 + }, + { + "epoch": 9.49, + "learning_rate": 1.1310353012207961e-05, + "loss": 0.0183, + "step": 10722 + }, + { + "epoch": 9.49, + "learning_rate": 1.130893227760585e-05, + "loss": 0.0189, + "step": 10723 + }, + { + "epoch": 9.49, + "learning_rate": 1.130751151612205e-05, + "loss": 0.019, + "step": 10724 + }, + { + "epoch": 9.49, + "learning_rate": 1.1306090727785734e-05, + "loss": 0.017, + "step": 10725 + }, + { + "epoch": 9.49, + "learning_rate": 1.130466991262609e-05, + "loss": 0.0169, + "step": 10726 + }, + { + "epoch": 9.49, + "learning_rate": 1.1303249070672288e-05, + "loss": 0.0156, + "step": 10727 + }, + { + "epoch": 9.49, + "learning_rate": 1.1301828201953516e-05, + "loss": 0.0159, + "step": 10728 + }, + { + "epoch": 9.49, + "learning_rate": 1.1300407306498947e-05, + "loss": 0.0195, + "step": 10729 + }, + { + "epoch": 9.49, + "learning_rate": 1.1298986384337767e-05, + "loss": 0.0163, + "step": 10730 + }, + { + "epoch": 9.49, + "learning_rate": 1.1297565435499158e-05, + "loss": 0.0178, + "step": 10731 + }, + { + "epoch": 9.5, + "learning_rate": 1.12961444600123e-05, + "loss": 0.0199, + "step": 10732 + }, + { + "epoch": 9.5, + "learning_rate": 1.1294723457906377e-05, + "loss": 0.0171, + "step": 10733 + }, + { + "epoch": 9.5, + "learning_rate": 1.1293302429210571e-05, + "loss": 0.0169, + "step": 10734 + }, + { + "epoch": 9.5, + "learning_rate": 1.1291881373954066e-05, + "loss": 0.018, + "step": 10735 + }, + { + "epoch": 9.5, + "learning_rate": 1.1290460292166045e-05, + "loss": 0.0177, + "step": 10736 + }, + { + "epoch": 9.5, + "learning_rate": 1.12890391838757e-05, + "loss": 0.0181, + "step": 10737 + }, + { + "epoch": 9.5, + "learning_rate": 1.1287618049112208e-05, + "loss": 0.017, + "step": 10738 + }, + { + "epoch": 9.5, + "learning_rate": 1.1286196887904756e-05, + "loss": 0.0177, + "step": 10739 + }, + { + "epoch": 9.5, + "learning_rate": 1.128477570028254e-05, + "loss": 0.0203, + "step": 10740 + }, + { + "epoch": 9.5, + "learning_rate": 1.1283354486274734e-05, + "loss": 0.0188, + "step": 10741 + }, + { + "epoch": 9.5, + "learning_rate": 1.1281933245910532e-05, + "loss": 0.0182, + "step": 10742 + }, + { + "epoch": 9.5, + "learning_rate": 1.1280511979219125e-05, + "loss": 0.0196, + "step": 10743 + }, + { + "epoch": 9.51, + "learning_rate": 1.1279090686229695e-05, + "loss": 0.0201, + "step": 10744 + }, + { + "epoch": 9.51, + "learning_rate": 1.1277669366971435e-05, + "loss": 0.0164, + "step": 10745 + }, + { + "epoch": 9.51, + "learning_rate": 1.1276248021473537e-05, + "loss": 0.0168, + "step": 10746 + }, + { + "epoch": 9.51, + "learning_rate": 1.127482664976519e-05, + "loss": 0.0164, + "step": 10747 + }, + { + "epoch": 9.51, + "learning_rate": 1.127340525187558e-05, + "loss": 0.0177, + "step": 10748 + }, + { + "epoch": 9.51, + "learning_rate": 1.1271983827833902e-05, + "loss": 0.0173, + "step": 10749 + }, + { + "epoch": 9.51, + "learning_rate": 1.1270562377669351e-05, + "loss": 0.0198, + "step": 10750 + }, + { + "epoch": 9.51, + "learning_rate": 1.1269140901411115e-05, + "loss": 0.0204, + "step": 10751 + }, + { + "epoch": 9.51, + "learning_rate": 1.1267719399088388e-05, + "loss": 0.0187, + "step": 10752 + }, + { + "epoch": 9.51, + "learning_rate": 1.1266297870730365e-05, + "loss": 0.0185, + "step": 10753 + }, + { + "epoch": 9.51, + "learning_rate": 1.126487631636624e-05, + "loss": 0.0172, + "step": 10754 + }, + { + "epoch": 9.52, + "learning_rate": 1.1263454736025206e-05, + "loss": 0.02, + "step": 10755 + }, + { + "epoch": 9.52, + "learning_rate": 1.1262033129736455e-05, + "loss": 0.0189, + "step": 10756 + }, + { + "epoch": 9.52, + "learning_rate": 1.1260611497529195e-05, + "loss": 0.0196, + "step": 10757 + }, + { + "epoch": 9.52, + "learning_rate": 1.125918983943261e-05, + "loss": 0.017, + "step": 10758 + }, + { + "epoch": 9.52, + "learning_rate": 1.12577681554759e-05, + "loss": 0.0234, + "step": 10759 + }, + { + "epoch": 9.52, + "learning_rate": 1.1256346445688262e-05, + "loss": 0.0162, + "step": 10760 + }, + { + "epoch": 9.52, + "learning_rate": 1.1254924710098898e-05, + "loss": 0.0164, + "step": 10761 + }, + { + "epoch": 9.52, + "learning_rate": 1.1253502948736998e-05, + "loss": 0.0204, + "step": 10762 + }, + { + "epoch": 9.52, + "learning_rate": 1.1252081161631769e-05, + "loss": 0.0188, + "step": 10763 + }, + { + "epoch": 9.52, + "learning_rate": 1.125065934881241e-05, + "loss": 0.0158, + "step": 10764 + }, + { + "epoch": 9.52, + "learning_rate": 1.1249237510308115e-05, + "loss": 0.0184, + "step": 10765 + }, + { + "epoch": 9.53, + "learning_rate": 1.1247815646148088e-05, + "loss": 0.0167, + "step": 10766 + }, + { + "epoch": 9.53, + "learning_rate": 1.1246393756361532e-05, + "loss": 0.0206, + "step": 10767 + }, + { + "epoch": 9.53, + "learning_rate": 1.1244971840977645e-05, + "loss": 0.0182, + "step": 10768 + }, + { + "epoch": 9.53, + "learning_rate": 1.1243549900025628e-05, + "loss": 0.0207, + "step": 10769 + }, + { + "epoch": 9.53, + "learning_rate": 1.1242127933534689e-05, + "loss": 0.0179, + "step": 10770 + }, + { + "epoch": 9.53, + "learning_rate": 1.1240705941534027e-05, + "loss": 0.0149, + "step": 10771 + }, + { + "epoch": 9.53, + "learning_rate": 1.1239283924052846e-05, + "loss": 0.0183, + "step": 10772 + }, + { + "epoch": 9.53, + "learning_rate": 1.1237861881120351e-05, + "loss": 0.0182, + "step": 10773 + }, + { + "epoch": 9.53, + "learning_rate": 1.1236439812765745e-05, + "loss": 0.018, + "step": 10774 + }, + { + "epoch": 9.53, + "learning_rate": 1.123501771901824e-05, + "loss": 0.0163, + "step": 10775 + }, + { + "epoch": 9.53, + "learning_rate": 1.1233595599907028e-05, + "loss": 0.0173, + "step": 10776 + }, + { + "epoch": 9.54, + "learning_rate": 1.1232173455461329e-05, + "loss": 0.0161, + "step": 10777 + }, + { + "epoch": 9.54, + "learning_rate": 1.1230751285710344e-05, + "loss": 0.016, + "step": 10778 + }, + { + "epoch": 9.54, + "learning_rate": 1.1229329090683278e-05, + "loss": 0.0172, + "step": 10779 + }, + { + "epoch": 9.54, + "learning_rate": 1.1227906870409343e-05, + "loss": 0.0193, + "step": 10780 + }, + { + "epoch": 9.54, + "learning_rate": 1.1226484624917747e-05, + "loss": 0.0211, + "step": 10781 + }, + { + "epoch": 9.54, + "learning_rate": 1.1225062354237694e-05, + "loss": 0.0159, + "step": 10782 + }, + { + "epoch": 9.54, + "learning_rate": 1.1223640058398397e-05, + "loss": 0.0186, + "step": 10783 + }, + { + "epoch": 9.54, + "learning_rate": 1.1222217737429066e-05, + "loss": 0.0208, + "step": 10784 + }, + { + "epoch": 9.54, + "learning_rate": 1.1220795391358914e-05, + "loss": 0.0162, + "step": 10785 + }, + { + "epoch": 9.54, + "learning_rate": 1.1219373020217148e-05, + "loss": 0.0183, + "step": 10786 + }, + { + "epoch": 9.54, + "learning_rate": 1.1217950624032979e-05, + "loss": 0.0142, + "step": 10787 + }, + { + "epoch": 9.54, + "learning_rate": 1.1216528202835619e-05, + "loss": 0.021, + "step": 10788 + }, + { + "epoch": 9.55, + "learning_rate": 1.121510575665428e-05, + "loss": 0.0226, + "step": 10789 + }, + { + "epoch": 9.55, + "learning_rate": 1.121368328551818e-05, + "loss": 0.0175, + "step": 10790 + }, + { + "epoch": 9.55, + "learning_rate": 1.1212260789456528e-05, + "loss": 0.0193, + "step": 10791 + }, + { + "epoch": 9.55, + "learning_rate": 1.1210838268498538e-05, + "loss": 0.0166, + "step": 10792 + }, + { + "epoch": 9.55, + "learning_rate": 1.120941572267343e-05, + "loss": 0.0195, + "step": 10793 + }, + { + "epoch": 9.55, + "learning_rate": 1.1207993152010407e-05, + "loss": 0.0201, + "step": 10794 + }, + { + "epoch": 9.55, + "learning_rate": 1.1206570556538693e-05, + "loss": 0.0175, + "step": 10795 + }, + { + "epoch": 9.55, + "learning_rate": 1.1205147936287508e-05, + "loss": 0.0168, + "step": 10796 + }, + { + "epoch": 9.55, + "learning_rate": 1.1203725291286061e-05, + "loss": 0.0152, + "step": 10797 + }, + { + "epoch": 9.55, + "learning_rate": 1.120230262156357e-05, + "loss": 0.0212, + "step": 10798 + }, + { + "epoch": 9.55, + "learning_rate": 1.1200879927149256e-05, + "loss": 0.0166, + "step": 10799 + }, + { + "epoch": 9.56, + "learning_rate": 1.1199457208072335e-05, + "loss": 0.0154, + "step": 10800 + }, + { + "epoch": 9.56, + "learning_rate": 1.1198034464362022e-05, + "loss": 0.0195, + "step": 10801 + }, + { + "epoch": 9.56, + "learning_rate": 1.1196611696047541e-05, + "loss": 0.018, + "step": 10802 + }, + { + "epoch": 9.56, + "learning_rate": 1.1195188903158112e-05, + "loss": 0.0142, + "step": 10803 + }, + { + "epoch": 9.56, + "learning_rate": 1.1193766085722953e-05, + "loss": 0.0175, + "step": 10804 + }, + { + "epoch": 9.56, + "learning_rate": 1.1192343243771282e-05, + "loss": 0.016, + "step": 10805 + }, + { + "epoch": 9.56, + "learning_rate": 1.1190920377332324e-05, + "loss": 0.0145, + "step": 10806 + }, + { + "epoch": 9.56, + "learning_rate": 1.1189497486435301e-05, + "loss": 0.0195, + "step": 10807 + }, + { + "epoch": 9.56, + "learning_rate": 1.1188074571109431e-05, + "loss": 0.0175, + "step": 10808 + }, + { + "epoch": 9.56, + "learning_rate": 1.1186651631383941e-05, + "loss": 0.0168, + "step": 10809 + }, + { + "epoch": 9.56, + "learning_rate": 1.1185228667288052e-05, + "loss": 0.0184, + "step": 10810 + }, + { + "epoch": 9.57, + "learning_rate": 1.1183805678850988e-05, + "loss": 0.0192, + "step": 10811 + }, + { + "epoch": 9.57, + "learning_rate": 1.118238266610197e-05, + "loss": 0.0194, + "step": 10812 + }, + { + "epoch": 9.57, + "learning_rate": 1.1180959629070228e-05, + "loss": 0.0211, + "step": 10813 + }, + { + "epoch": 9.57, + "learning_rate": 1.1179536567784984e-05, + "loss": 0.0187, + "step": 10814 + }, + { + "epoch": 9.57, + "learning_rate": 1.117811348227546e-05, + "loss": 0.0174, + "step": 10815 + }, + { + "epoch": 9.57, + "learning_rate": 1.1176690372570888e-05, + "loss": 0.0174, + "step": 10816 + }, + { + "epoch": 9.57, + "learning_rate": 1.1175267238700497e-05, + "loss": 0.0175, + "step": 10817 + }, + { + "epoch": 9.57, + "learning_rate": 1.1173844080693509e-05, + "loss": 0.0161, + "step": 10818 + }, + { + "epoch": 9.57, + "learning_rate": 1.1172420898579145e-05, + "loss": 0.0179, + "step": 10819 + }, + { + "epoch": 9.57, + "learning_rate": 1.1170997692386648e-05, + "loss": 0.0171, + "step": 10820 + }, + { + "epoch": 9.57, + "learning_rate": 1.1169574462145234e-05, + "loss": 0.0173, + "step": 10821 + }, + { + "epoch": 9.57, + "learning_rate": 1.1168151207884139e-05, + "loss": 0.0212, + "step": 10822 + }, + { + "epoch": 9.58, + "learning_rate": 1.1166727929632588e-05, + "loss": 0.0217, + "step": 10823 + }, + { + "epoch": 9.58, + "learning_rate": 1.1165304627419817e-05, + "loss": 0.021, + "step": 10824 + }, + { + "epoch": 9.58, + "learning_rate": 1.1163881301275052e-05, + "loss": 0.019, + "step": 10825 + }, + { + "epoch": 9.58, + "learning_rate": 1.1162457951227523e-05, + "loss": 0.0195, + "step": 10826 + }, + { + "epoch": 9.58, + "learning_rate": 1.1161034577306464e-05, + "loss": 0.0215, + "step": 10827 + }, + { + "epoch": 9.58, + "learning_rate": 1.1159611179541107e-05, + "loss": 0.0151, + "step": 10828 + }, + { + "epoch": 9.58, + "learning_rate": 1.1158187757960684e-05, + "loss": 0.0161, + "step": 10829 + }, + { + "epoch": 9.58, + "learning_rate": 1.1156764312594429e-05, + "loss": 0.0166, + "step": 10830 + }, + { + "epoch": 9.58, + "learning_rate": 1.1155340843471574e-05, + "loss": 0.0182, + "step": 10831 + }, + { + "epoch": 9.58, + "learning_rate": 1.115391735062135e-05, + "loss": 0.02, + "step": 10832 + }, + { + "epoch": 9.58, + "learning_rate": 1.1152493834072997e-05, + "loss": 0.0171, + "step": 10833 + }, + { + "epoch": 9.59, + "learning_rate": 1.1151070293855748e-05, + "loss": 0.0178, + "step": 10834 + }, + { + "epoch": 9.59, + "learning_rate": 1.1149646729998837e-05, + "loss": 0.0197, + "step": 10835 + }, + { + "epoch": 9.59, + "learning_rate": 1.1148223142531502e-05, + "loss": 0.0209, + "step": 10836 + }, + { + "epoch": 9.59, + "learning_rate": 1.1146799531482976e-05, + "loss": 0.017, + "step": 10837 + }, + { + "epoch": 9.59, + "learning_rate": 1.1145375896882501e-05, + "loss": 0.0186, + "step": 10838 + }, + { + "epoch": 9.59, + "learning_rate": 1.1143952238759312e-05, + "loss": 0.0176, + "step": 10839 + }, + { + "epoch": 9.59, + "learning_rate": 1.1142528557142645e-05, + "loss": 0.0179, + "step": 10840 + }, + { + "epoch": 9.59, + "learning_rate": 1.114110485206174e-05, + "loss": 0.0166, + "step": 10841 + }, + { + "epoch": 9.59, + "learning_rate": 1.1139681123545833e-05, + "loss": 0.0194, + "step": 10842 + }, + { + "epoch": 9.59, + "learning_rate": 1.1138257371624168e-05, + "loss": 0.019, + "step": 10843 + }, + { + "epoch": 9.59, + "learning_rate": 1.113683359632598e-05, + "loss": 0.0174, + "step": 10844 + }, + { + "epoch": 9.6, + "learning_rate": 1.1135409797680516e-05, + "loss": 0.0215, + "step": 10845 + }, + { + "epoch": 9.6, + "learning_rate": 1.113398597571701e-05, + "loss": 0.0186, + "step": 10846 + }, + { + "epoch": 9.6, + "learning_rate": 1.1132562130464704e-05, + "loss": 0.0176, + "step": 10847 + }, + { + "epoch": 9.6, + "learning_rate": 1.1131138261952845e-05, + "loss": 0.0202, + "step": 10848 + }, + { + "epoch": 9.6, + "learning_rate": 1.1129714370210669e-05, + "loss": 0.0184, + "step": 10849 + }, + { + "epoch": 9.6, + "learning_rate": 1.1128290455267421e-05, + "loss": 0.019, + "step": 10850 + }, + { + "epoch": 9.6, + "learning_rate": 1.1126866517152345e-05, + "loss": 0.019, + "step": 10851 + }, + { + "epoch": 9.6, + "learning_rate": 1.1125442555894686e-05, + "loss": 0.0208, + "step": 10852 + }, + { + "epoch": 9.6, + "learning_rate": 1.112401857152368e-05, + "loss": 0.0163, + "step": 10853 + }, + { + "epoch": 9.6, + "learning_rate": 1.1122594564068579e-05, + "loss": 0.0199, + "step": 10854 + }, + { + "epoch": 9.6, + "learning_rate": 1.112117053355863e-05, + "loss": 0.019, + "step": 10855 + }, + { + "epoch": 9.6, + "learning_rate": 1.1119746480023072e-05, + "loss": 0.0192, + "step": 10856 + }, + { + "epoch": 9.61, + "learning_rate": 1.1118322403491155e-05, + "loss": 0.0199, + "step": 10857 + }, + { + "epoch": 9.61, + "learning_rate": 1.1116898303992123e-05, + "loss": 0.0188, + "step": 10858 + }, + { + "epoch": 9.61, + "learning_rate": 1.1115474181555227e-05, + "loss": 0.0211, + "step": 10859 + }, + { + "epoch": 9.61, + "learning_rate": 1.1114050036209706e-05, + "loss": 0.0202, + "step": 10860 + }, + { + "epoch": 9.61, + "learning_rate": 1.1112625867984815e-05, + "loss": 0.0182, + "step": 10861 + }, + { + "epoch": 9.61, + "learning_rate": 1.1111201676909804e-05, + "loss": 0.0202, + "step": 10862 + }, + { + "epoch": 9.61, + "learning_rate": 1.1109777463013915e-05, + "loss": 0.017, + "step": 10863 + }, + { + "epoch": 9.61, + "learning_rate": 1.11083532263264e-05, + "loss": 0.018, + "step": 10864 + }, + { + "epoch": 9.61, + "learning_rate": 1.1106928966876512e-05, + "loss": 0.0159, + "step": 10865 + }, + { + "epoch": 9.61, + "learning_rate": 1.11055046846935e-05, + "loss": 0.0154, + "step": 10866 + }, + { + "epoch": 9.61, + "learning_rate": 1.1104080379806609e-05, + "loss": 0.0188, + "step": 10867 + }, + { + "epoch": 9.62, + "learning_rate": 1.1102656052245093e-05, + "loss": 0.0167, + "step": 10868 + }, + { + "epoch": 9.62, + "learning_rate": 1.1101231702038211e-05, + "loss": 0.0204, + "step": 10869 + }, + { + "epoch": 9.62, + "learning_rate": 1.1099807329215204e-05, + "loss": 0.019, + "step": 10870 + }, + { + "epoch": 9.62, + "learning_rate": 1.109838293380533e-05, + "loss": 0.0192, + "step": 10871 + }, + { + "epoch": 9.62, + "learning_rate": 1.1096958515837841e-05, + "loss": 0.0184, + "step": 10872 + }, + { + "epoch": 9.62, + "learning_rate": 1.1095534075341992e-05, + "loss": 0.019, + "step": 10873 + }, + { + "epoch": 9.62, + "learning_rate": 1.1094109612347035e-05, + "loss": 0.019, + "step": 10874 + }, + { + "epoch": 9.62, + "learning_rate": 1.1092685126882226e-05, + "loss": 0.0205, + "step": 10875 + }, + { + "epoch": 9.62, + "learning_rate": 1.109126061897682e-05, + "loss": 0.0198, + "step": 10876 + }, + { + "epoch": 9.62, + "learning_rate": 1.1089836088660069e-05, + "loss": 0.0191, + "step": 10877 + }, + { + "epoch": 9.62, + "learning_rate": 1.108841153596123e-05, + "loss": 0.0219, + "step": 10878 + }, + { + "epoch": 9.63, + "learning_rate": 1.108698696090956e-05, + "loss": 0.0211, + "step": 10879 + }, + { + "epoch": 9.63, + "learning_rate": 1.1085562363534317e-05, + "loss": 0.0154, + "step": 10880 + }, + { + "epoch": 9.63, + "learning_rate": 1.1084137743864755e-05, + "loss": 0.0182, + "step": 10881 + }, + { + "epoch": 9.63, + "learning_rate": 1.1082713101930136e-05, + "loss": 0.0201, + "step": 10882 + }, + { + "epoch": 9.63, + "learning_rate": 1.1081288437759716e-05, + "loss": 0.0211, + "step": 10883 + }, + { + "epoch": 9.63, + "learning_rate": 1.107986375138275e-05, + "loss": 0.0205, + "step": 10884 + }, + { + "epoch": 9.63, + "learning_rate": 1.1078439042828502e-05, + "loss": 0.0213, + "step": 10885 + }, + { + "epoch": 9.63, + "learning_rate": 1.107701431212623e-05, + "loss": 0.0193, + "step": 10886 + }, + { + "epoch": 9.63, + "learning_rate": 1.1075589559305189e-05, + "loss": 0.0196, + "step": 10887 + }, + { + "epoch": 9.63, + "learning_rate": 1.1074164784394645e-05, + "loss": 0.0204, + "step": 10888 + }, + { + "epoch": 9.63, + "learning_rate": 1.1072739987423859e-05, + "loss": 0.0182, + "step": 10889 + }, + { + "epoch": 9.63, + "learning_rate": 1.107131516842209e-05, + "loss": 0.0179, + "step": 10890 + }, + { + "epoch": 9.64, + "learning_rate": 1.10698903274186e-05, + "loss": 0.0192, + "step": 10891 + }, + { + "epoch": 9.64, + "learning_rate": 1.1068465464442651e-05, + "loss": 0.0205, + "step": 10892 + }, + { + "epoch": 9.64, + "learning_rate": 1.1067040579523505e-05, + "loss": 0.0166, + "step": 10893 + }, + { + "epoch": 9.64, + "learning_rate": 1.1065615672690426e-05, + "loss": 0.0182, + "step": 10894 + }, + { + "epoch": 9.64, + "learning_rate": 1.1064190743972676e-05, + "loss": 0.0208, + "step": 10895 + }, + { + "epoch": 9.64, + "learning_rate": 1.1062765793399522e-05, + "loss": 0.0171, + "step": 10896 + }, + { + "epoch": 9.64, + "learning_rate": 1.1061340821000228e-05, + "loss": 0.0185, + "step": 10897 + }, + { + "epoch": 9.64, + "learning_rate": 1.1059915826804056e-05, + "loss": 0.0202, + "step": 10898 + }, + { + "epoch": 9.64, + "learning_rate": 1.105849081084027e-05, + "loss": 0.0208, + "step": 10899 + }, + { + "epoch": 9.64, + "learning_rate": 1.1057065773138142e-05, + "loss": 0.0158, + "step": 10900 + }, + { + "epoch": 9.64, + "learning_rate": 1.1055640713726933e-05, + "loss": 0.0202, + "step": 10901 + }, + { + "epoch": 9.65, + "learning_rate": 1.1054215632635912e-05, + "loss": 0.0169, + "step": 10902 + }, + { + "epoch": 9.65, + "learning_rate": 1.1052790529894343e-05, + "loss": 0.0228, + "step": 10903 + }, + { + "epoch": 9.65, + "learning_rate": 1.1051365405531497e-05, + "loss": 0.0175, + "step": 10904 + }, + { + "epoch": 9.65, + "learning_rate": 1.1049940259576642e-05, + "loss": 0.0154, + "step": 10905 + }, + { + "epoch": 9.65, + "learning_rate": 1.1048515092059043e-05, + "loss": 0.0146, + "step": 10906 + }, + { + "epoch": 9.65, + "learning_rate": 1.104708990300797e-05, + "loss": 0.0183, + "step": 10907 + }, + { + "epoch": 9.65, + "learning_rate": 1.1045664692452695e-05, + "loss": 0.0164, + "step": 10908 + }, + { + "epoch": 9.65, + "learning_rate": 1.1044239460422485e-05, + "loss": 0.0217, + "step": 10909 + }, + { + "epoch": 9.65, + "learning_rate": 1.1042814206946612e-05, + "loss": 0.0178, + "step": 10910 + }, + { + "epoch": 9.65, + "learning_rate": 1.1041388932054346e-05, + "loss": 0.0211, + "step": 10911 + }, + { + "epoch": 9.65, + "learning_rate": 1.1039963635774954e-05, + "loss": 0.0216, + "step": 10912 + }, + { + "epoch": 9.66, + "learning_rate": 1.1038538318137715e-05, + "loss": 0.0199, + "step": 10913 + }, + { + "epoch": 9.66, + "learning_rate": 1.1037112979171894e-05, + "loss": 0.0173, + "step": 10914 + }, + { + "epoch": 9.66, + "learning_rate": 1.1035687618906769e-05, + "loss": 0.0181, + "step": 10915 + }, + { + "epoch": 9.66, + "learning_rate": 1.1034262237371608e-05, + "loss": 0.0178, + "step": 10916 + }, + { + "epoch": 9.66, + "learning_rate": 1.1032836834595689e-05, + "loss": 0.0221, + "step": 10917 + }, + { + "epoch": 9.66, + "learning_rate": 1.1031411410608279e-05, + "loss": 0.0203, + "step": 10918 + }, + { + "epoch": 9.66, + "learning_rate": 1.1029985965438658e-05, + "loss": 0.0183, + "step": 10919 + }, + { + "epoch": 9.66, + "learning_rate": 1.1028560499116099e-05, + "loss": 0.0201, + "step": 10920 + }, + { + "epoch": 9.66, + "learning_rate": 1.1027135011669877e-05, + "loss": 0.0183, + "step": 10921 + }, + { + "epoch": 9.66, + "learning_rate": 1.1025709503129268e-05, + "loss": 0.0191, + "step": 10922 + }, + { + "epoch": 9.66, + "learning_rate": 1.1024283973523544e-05, + "loss": 0.0177, + "step": 10923 + }, + { + "epoch": 9.67, + "learning_rate": 1.1022858422881986e-05, + "loss": 0.022, + "step": 10924 + }, + { + "epoch": 9.67, + "learning_rate": 1.1021432851233867e-05, + "loss": 0.0174, + "step": 10925 + }, + { + "epoch": 9.67, + "learning_rate": 1.1020007258608468e-05, + "loss": 0.0167, + "step": 10926 + }, + { + "epoch": 9.67, + "learning_rate": 1.101858164503506e-05, + "loss": 0.0203, + "step": 10927 + }, + { + "epoch": 9.67, + "learning_rate": 1.1017156010542929e-05, + "loss": 0.0177, + "step": 10928 + }, + { + "epoch": 9.67, + "learning_rate": 1.101573035516135e-05, + "loss": 0.0183, + "step": 10929 + }, + { + "epoch": 9.67, + "learning_rate": 1.1014304678919602e-05, + "loss": 0.0168, + "step": 10930 + }, + { + "epoch": 9.67, + "learning_rate": 1.1012878981846964e-05, + "loss": 0.0182, + "step": 10931 + }, + { + "epoch": 9.67, + "learning_rate": 1.1011453263972713e-05, + "loss": 0.0169, + "step": 10932 + }, + { + "epoch": 9.67, + "learning_rate": 1.1010027525326134e-05, + "loss": 0.0174, + "step": 10933 + }, + { + "epoch": 9.67, + "learning_rate": 1.1008601765936504e-05, + "loss": 0.0173, + "step": 10934 + }, + { + "epoch": 9.67, + "learning_rate": 1.1007175985833106e-05, + "loss": 0.0182, + "step": 10935 + }, + { + "epoch": 9.68, + "learning_rate": 1.1005750185045224e-05, + "loss": 0.0184, + "step": 10936 + }, + { + "epoch": 9.68, + "learning_rate": 1.1004324363602133e-05, + "loss": 0.0198, + "step": 10937 + }, + { + "epoch": 9.68, + "learning_rate": 1.100289852153312e-05, + "loss": 0.0203, + "step": 10938 + }, + { + "epoch": 9.68, + "learning_rate": 1.1001472658867463e-05, + "loss": 0.019, + "step": 10939 + }, + { + "epoch": 9.68, + "learning_rate": 1.1000046775634452e-05, + "loss": 0.02, + "step": 10940 + }, + { + "epoch": 9.68, + "learning_rate": 1.0998620871863365e-05, + "loss": 0.0186, + "step": 10941 + }, + { + "epoch": 9.68, + "learning_rate": 1.0997194947583489e-05, + "loss": 0.0189, + "step": 10942 + }, + { + "epoch": 9.68, + "learning_rate": 1.099576900282411e-05, + "loss": 0.0225, + "step": 10943 + }, + { + "epoch": 9.68, + "learning_rate": 1.0994343037614507e-05, + "loss": 0.0182, + "step": 10944 + }, + { + "epoch": 9.68, + "learning_rate": 1.0992917051983966e-05, + "loss": 0.019, + "step": 10945 + }, + { + "epoch": 9.68, + "learning_rate": 1.0991491045961782e-05, + "loss": 0.0183, + "step": 10946 + }, + { + "epoch": 9.69, + "learning_rate": 1.0990065019577231e-05, + "loss": 0.0188, + "step": 10947 + }, + { + "epoch": 9.69, + "learning_rate": 1.0988638972859603e-05, + "loss": 0.0186, + "step": 10948 + }, + { + "epoch": 9.69, + "learning_rate": 1.0987212905838182e-05, + "loss": 0.0193, + "step": 10949 + }, + { + "epoch": 9.69, + "learning_rate": 1.0985786818542261e-05, + "loss": 0.0204, + "step": 10950 + }, + { + "epoch": 9.69, + "learning_rate": 1.0984360711001123e-05, + "loss": 0.0167, + "step": 10951 + }, + { + "epoch": 9.69, + "learning_rate": 1.0982934583244056e-05, + "loss": 0.0215, + "step": 10952 + }, + { + "epoch": 9.69, + "learning_rate": 1.0981508435300352e-05, + "loss": 0.0214, + "step": 10953 + }, + { + "epoch": 9.69, + "learning_rate": 1.0980082267199299e-05, + "loss": 0.0162, + "step": 10954 + }, + { + "epoch": 9.69, + "learning_rate": 1.0978656078970184e-05, + "loss": 0.0173, + "step": 10955 + }, + { + "epoch": 9.69, + "learning_rate": 1.0977229870642298e-05, + "loss": 0.0181, + "step": 10956 + }, + { + "epoch": 9.69, + "learning_rate": 1.0975803642244933e-05, + "loss": 0.0214, + "step": 10957 + }, + { + "epoch": 9.7, + "learning_rate": 1.0974377393807376e-05, + "loss": 0.0207, + "step": 10958 + }, + { + "epoch": 9.7, + "learning_rate": 1.0972951125358922e-05, + "loss": 0.0193, + "step": 10959 + }, + { + "epoch": 9.7, + "learning_rate": 1.097152483692886e-05, + "loss": 0.0207, + "step": 10960 + }, + { + "epoch": 9.7, + "learning_rate": 1.0970098528546482e-05, + "loss": 0.0159, + "step": 10961 + }, + { + "epoch": 9.7, + "learning_rate": 1.0968672200241081e-05, + "loss": 0.0204, + "step": 10962 + }, + { + "epoch": 9.7, + "learning_rate": 1.096724585204195e-05, + "loss": 0.0186, + "step": 10963 + }, + { + "epoch": 9.7, + "learning_rate": 1.0965819483978381e-05, + "loss": 0.0174, + "step": 10964 + }, + { + "epoch": 9.7, + "learning_rate": 1.0964393096079666e-05, + "loss": 0.0203, + "step": 10965 + }, + { + "epoch": 9.7, + "learning_rate": 1.0962966688375103e-05, + "loss": 0.0173, + "step": 10966 + }, + { + "epoch": 9.7, + "learning_rate": 1.0961540260893984e-05, + "loss": 0.0194, + "step": 10967 + }, + { + "epoch": 9.7, + "learning_rate": 1.0960113813665603e-05, + "loss": 0.0163, + "step": 10968 + }, + { + "epoch": 9.7, + "learning_rate": 1.0958687346719257e-05, + "loss": 0.0207, + "step": 10969 + }, + { + "epoch": 9.71, + "learning_rate": 1.0957260860084237e-05, + "loss": 0.0184, + "step": 10970 + }, + { + "epoch": 9.71, + "learning_rate": 1.0955834353789845e-05, + "loss": 0.0191, + "step": 10971 + }, + { + "epoch": 9.71, + "learning_rate": 1.0954407827865375e-05, + "loss": 0.0223, + "step": 10972 + }, + { + "epoch": 9.71, + "learning_rate": 1.0952981282340123e-05, + "loss": 0.0191, + "step": 10973 + }, + { + "epoch": 9.71, + "learning_rate": 1.0951554717243386e-05, + "loss": 0.0186, + "step": 10974 + }, + { + "epoch": 9.71, + "learning_rate": 1.0950128132604463e-05, + "loss": 0.0187, + "step": 10975 + }, + { + "epoch": 9.71, + "learning_rate": 1.094870152845265e-05, + "loss": 0.019, + "step": 10976 + }, + { + "epoch": 9.71, + "learning_rate": 1.0947274904817247e-05, + "loss": 0.0191, + "step": 10977 + }, + { + "epoch": 9.71, + "learning_rate": 1.0945848261727552e-05, + "loss": 0.0195, + "step": 10978 + }, + { + "epoch": 9.71, + "learning_rate": 1.0944421599212863e-05, + "loss": 0.0194, + "step": 10979 + }, + { + "epoch": 9.71, + "learning_rate": 1.094299491730248e-05, + "loss": 0.0168, + "step": 10980 + }, + { + "epoch": 9.72, + "learning_rate": 1.0941568216025707e-05, + "loss": 0.0184, + "step": 10981 + }, + { + "epoch": 9.72, + "learning_rate": 1.094014149541184e-05, + "loss": 0.0192, + "step": 10982 + }, + { + "epoch": 9.72, + "learning_rate": 1.0938714755490179e-05, + "loss": 0.0217, + "step": 10983 + }, + { + "epoch": 9.72, + "learning_rate": 1.0937287996290026e-05, + "loss": 0.0205, + "step": 10984 + }, + { + "epoch": 9.72, + "learning_rate": 1.0935861217840684e-05, + "loss": 0.0189, + "step": 10985 + }, + { + "epoch": 9.72, + "learning_rate": 1.0934434420171455e-05, + "loss": 0.0235, + "step": 10986 + }, + { + "epoch": 9.72, + "learning_rate": 1.093300760331164e-05, + "loss": 0.0187, + "step": 10987 + }, + { + "epoch": 9.72, + "learning_rate": 1.0931580767290544e-05, + "loss": 0.0182, + "step": 10988 + }, + { + "epoch": 9.72, + "learning_rate": 1.0930153912137467e-05, + "loss": 0.0236, + "step": 10989 + }, + { + "epoch": 9.72, + "learning_rate": 1.0928727037881712e-05, + "loss": 0.0195, + "step": 10990 + }, + { + "epoch": 9.72, + "learning_rate": 1.0927300144552586e-05, + "loss": 0.0178, + "step": 10991 + }, + { + "epoch": 9.73, + "learning_rate": 1.092587323217939e-05, + "loss": 0.0224, + "step": 10992 + }, + { + "epoch": 9.73, + "learning_rate": 1.0924446300791436e-05, + "loss": 0.0196, + "step": 10993 + }, + { + "epoch": 9.73, + "learning_rate": 1.0923019350418019e-05, + "loss": 0.0187, + "step": 10994 + }, + { + "epoch": 9.73, + "learning_rate": 1.0921592381088453e-05, + "loss": 0.0154, + "step": 10995 + }, + { + "epoch": 9.73, + "learning_rate": 1.0920165392832036e-05, + "loss": 0.0188, + "step": 10996 + }, + { + "epoch": 9.73, + "learning_rate": 1.0918738385678079e-05, + "loss": 0.0179, + "step": 10997 + }, + { + "epoch": 9.73, + "learning_rate": 1.091731135965589e-05, + "loss": 0.0193, + "step": 10998 + }, + { + "epoch": 9.73, + "learning_rate": 1.091588431479477e-05, + "loss": 0.0188, + "step": 10999 + }, + { + "epoch": 9.73, + "learning_rate": 1.0914457251124031e-05, + "loss": 0.0211, + "step": 11000 + }, + { + "epoch": 9.73, + "learning_rate": 1.091303016867298e-05, + "loss": 0.0173, + "step": 11001 + }, + { + "epoch": 9.73, + "learning_rate": 1.0911603067470928e-05, + "loss": 0.0194, + "step": 11002 + }, + { + "epoch": 9.73, + "learning_rate": 1.0910175947547178e-05, + "loss": 0.0209, + "step": 11003 + }, + { + "epoch": 9.74, + "learning_rate": 1.090874880893104e-05, + "loss": 0.0171, + "step": 11004 + }, + { + "epoch": 9.74, + "learning_rate": 1.090732165165183e-05, + "loss": 0.0193, + "step": 11005 + }, + { + "epoch": 9.74, + "learning_rate": 1.0905894475738847e-05, + "loss": 0.0187, + "step": 11006 + }, + { + "epoch": 9.74, + "learning_rate": 1.090446728122141e-05, + "loss": 0.0207, + "step": 11007 + }, + { + "epoch": 9.74, + "learning_rate": 1.0903040068128825e-05, + "loss": 0.0204, + "step": 11008 + }, + { + "epoch": 9.74, + "learning_rate": 1.0901612836490404e-05, + "loss": 0.0194, + "step": 11009 + }, + { + "epoch": 9.74, + "learning_rate": 1.0900185586335456e-05, + "loss": 0.0166, + "step": 11010 + }, + { + "epoch": 9.74, + "learning_rate": 1.0898758317693297e-05, + "loss": 0.022, + "step": 11011 + }, + { + "epoch": 9.74, + "learning_rate": 1.0897331030593237e-05, + "loss": 0.0189, + "step": 11012 + }, + { + "epoch": 9.74, + "learning_rate": 1.0895903725064587e-05, + "loss": 0.0166, + "step": 11013 + }, + { + "epoch": 9.74, + "learning_rate": 1.089447640113666e-05, + "loss": 0.0224, + "step": 11014 + }, + { + "epoch": 9.75, + "learning_rate": 1.0893049058838772e-05, + "loss": 0.0184, + "step": 11015 + }, + { + "epoch": 9.75, + "learning_rate": 1.0891621698200234e-05, + "loss": 0.0178, + "step": 11016 + }, + { + "epoch": 9.75, + "learning_rate": 1.0890194319250356e-05, + "loss": 0.0183, + "step": 11017 + }, + { + "epoch": 9.75, + "learning_rate": 1.0888766922018462e-05, + "loss": 0.0216, + "step": 11018 + }, + { + "epoch": 9.75, + "learning_rate": 1.0887339506533858e-05, + "loss": 0.0166, + "step": 11019 + }, + { + "epoch": 9.75, + "learning_rate": 1.0885912072825863e-05, + "loss": 0.0199, + "step": 11020 + }, + { + "epoch": 9.75, + "learning_rate": 1.0884484620923792e-05, + "loss": 0.0208, + "step": 11021 + }, + { + "epoch": 9.75, + "learning_rate": 1.0883057150856959e-05, + "loss": 0.018, + "step": 11022 + }, + { + "epoch": 9.75, + "learning_rate": 1.088162966265468e-05, + "loss": 0.0228, + "step": 11023 + }, + { + "epoch": 9.75, + "learning_rate": 1.0880202156346275e-05, + "loss": 0.0191, + "step": 11024 + }, + { + "epoch": 9.75, + "learning_rate": 1.0878774631961057e-05, + "loss": 0.0173, + "step": 11025 + }, + { + "epoch": 9.76, + "learning_rate": 1.0877347089528349e-05, + "loss": 0.0197, + "step": 11026 + }, + { + "epoch": 9.76, + "learning_rate": 1.087591952907746e-05, + "loss": 0.0216, + "step": 11027 + }, + { + "epoch": 9.76, + "learning_rate": 1.0874491950637715e-05, + "loss": 0.0187, + "step": 11028 + }, + { + "epoch": 9.76, + "learning_rate": 1.0873064354238429e-05, + "loss": 0.0195, + "step": 11029 + }, + { + "epoch": 9.76, + "learning_rate": 1.0871636739908922e-05, + "loss": 0.0196, + "step": 11030 + }, + { + "epoch": 9.76, + "learning_rate": 1.087020910767851e-05, + "loss": 0.021, + "step": 11031 + }, + { + "epoch": 9.76, + "learning_rate": 1.0868781457576517e-05, + "loss": 0.021, + "step": 11032 + }, + { + "epoch": 9.76, + "learning_rate": 1.086735378963226e-05, + "loss": 0.0176, + "step": 11033 + }, + { + "epoch": 9.76, + "learning_rate": 1.0865926103875062e-05, + "loss": 0.0224, + "step": 11034 + }, + { + "epoch": 9.76, + "learning_rate": 1.0864498400334241e-05, + "loss": 0.018, + "step": 11035 + }, + { + "epoch": 9.76, + "learning_rate": 1.0863070679039115e-05, + "loss": 0.0191, + "step": 11036 + }, + { + "epoch": 9.77, + "learning_rate": 1.0861642940019012e-05, + "loss": 0.0179, + "step": 11037 + }, + { + "epoch": 9.77, + "learning_rate": 1.0860215183303252e-05, + "loss": 0.0185, + "step": 11038 + }, + { + "epoch": 9.77, + "learning_rate": 1.0858787408921152e-05, + "loss": 0.0187, + "step": 11039 + }, + { + "epoch": 9.77, + "learning_rate": 1.0857359616902039e-05, + "loss": 0.0178, + "step": 11040 + }, + { + "epoch": 9.77, + "learning_rate": 1.0855931807275235e-05, + "loss": 0.0176, + "step": 11041 + }, + { + "epoch": 9.77, + "learning_rate": 1.0854503980070062e-05, + "loss": 0.0212, + "step": 11042 + }, + { + "epoch": 9.77, + "learning_rate": 1.0853076135315841e-05, + "loss": 0.0214, + "step": 11043 + }, + { + "epoch": 9.77, + "learning_rate": 1.0851648273041903e-05, + "loss": 0.0163, + "step": 11044 + }, + { + "epoch": 9.77, + "learning_rate": 1.0850220393277566e-05, + "loss": 0.0189, + "step": 11045 + }, + { + "epoch": 9.77, + "learning_rate": 1.0848792496052159e-05, + "loss": 0.0233, + "step": 11046 + }, + { + "epoch": 9.77, + "learning_rate": 1.0847364581395001e-05, + "loss": 0.0213, + "step": 11047 + }, + { + "epoch": 9.77, + "learning_rate": 1.0845936649335424e-05, + "loss": 0.0201, + "step": 11048 + }, + { + "epoch": 9.78, + "learning_rate": 1.0844508699902748e-05, + "loss": 0.0194, + "step": 11049 + }, + { + "epoch": 9.78, + "learning_rate": 1.08430807331263e-05, + "loss": 0.0201, + "step": 11050 + }, + { + "epoch": 9.78, + "learning_rate": 1.084165274903541e-05, + "loss": 0.0204, + "step": 11051 + }, + { + "epoch": 9.78, + "learning_rate": 1.0840224747659402e-05, + "loss": 0.0204, + "step": 11052 + }, + { + "epoch": 9.78, + "learning_rate": 1.0838796729027601e-05, + "loss": 0.0192, + "step": 11053 + }, + { + "epoch": 9.78, + "learning_rate": 1.083736869316934e-05, + "loss": 0.0193, + "step": 11054 + }, + { + "epoch": 9.78, + "learning_rate": 1.0835940640113942e-05, + "loss": 0.0228, + "step": 11055 + }, + { + "epoch": 9.78, + "learning_rate": 1.0834512569890733e-05, + "loss": 0.0196, + "step": 11056 + }, + { + "epoch": 9.78, + "learning_rate": 1.0833084482529048e-05, + "loss": 0.0193, + "step": 11057 + }, + { + "epoch": 9.78, + "learning_rate": 1.0831656378058212e-05, + "loss": 0.0185, + "step": 11058 + }, + { + "epoch": 9.78, + "learning_rate": 1.0830228256507555e-05, + "loss": 0.0193, + "step": 11059 + }, + { + "epoch": 9.79, + "learning_rate": 1.0828800117906409e-05, + "loss": 0.0173, + "step": 11060 + }, + { + "epoch": 9.79, + "learning_rate": 1.0827371962284097e-05, + "loss": 0.0172, + "step": 11061 + }, + { + "epoch": 9.79, + "learning_rate": 1.0825943789669955e-05, + "loss": 0.0181, + "step": 11062 + }, + { + "epoch": 9.79, + "learning_rate": 1.0824515600093311e-05, + "loss": 0.0209, + "step": 11063 + }, + { + "epoch": 9.79, + "learning_rate": 1.0823087393583497e-05, + "loss": 0.0234, + "step": 11064 + }, + { + "epoch": 9.79, + "learning_rate": 1.0821659170169847e-05, + "loss": 0.017, + "step": 11065 + }, + { + "epoch": 9.79, + "learning_rate": 1.0820230929881686e-05, + "loss": 0.0209, + "step": 11066 + }, + { + "epoch": 9.79, + "learning_rate": 1.081880267274835e-05, + "loss": 0.0164, + "step": 11067 + }, + { + "epoch": 9.79, + "learning_rate": 1.0817374398799173e-05, + "loss": 0.0182, + "step": 11068 + }, + { + "epoch": 9.79, + "learning_rate": 1.0815946108063483e-05, + "loss": 0.0202, + "step": 11069 + }, + { + "epoch": 9.79, + "learning_rate": 1.0814517800570614e-05, + "loss": 0.0162, + "step": 11070 + }, + { + "epoch": 9.8, + "learning_rate": 1.0813089476349903e-05, + "loss": 0.0184, + "step": 11071 + }, + { + "epoch": 9.8, + "learning_rate": 1.0811661135430682e-05, + "loss": 0.0248, + "step": 11072 + }, + { + "epoch": 9.8, + "learning_rate": 1.0810232777842285e-05, + "loss": 0.021, + "step": 11073 + }, + { + "epoch": 9.8, + "learning_rate": 1.0808804403614044e-05, + "loss": 0.022, + "step": 11074 + }, + { + "epoch": 9.8, + "learning_rate": 1.0807376012775295e-05, + "loss": 0.0177, + "step": 11075 + }, + { + "epoch": 9.8, + "learning_rate": 1.0805947605355373e-05, + "loss": 0.02, + "step": 11076 + }, + { + "epoch": 9.8, + "learning_rate": 1.0804519181383615e-05, + "loss": 0.0185, + "step": 11077 + }, + { + "epoch": 9.8, + "learning_rate": 1.0803090740889356e-05, + "loss": 0.0178, + "step": 11078 + }, + { + "epoch": 9.8, + "learning_rate": 1.080166228390193e-05, + "loss": 0.0194, + "step": 11079 + }, + { + "epoch": 9.8, + "learning_rate": 1.0800233810450676e-05, + "loss": 0.02, + "step": 11080 + }, + { + "epoch": 9.8, + "learning_rate": 1.0798805320564929e-05, + "loss": 0.0206, + "step": 11081 + }, + { + "epoch": 9.8, + "learning_rate": 1.0797376814274028e-05, + "loss": 0.0196, + "step": 11082 + }, + { + "epoch": 9.81, + "learning_rate": 1.0795948291607305e-05, + "loss": 0.0175, + "step": 11083 + }, + { + "epoch": 9.81, + "learning_rate": 1.0794519752594107e-05, + "loss": 0.0251, + "step": 11084 + }, + { + "epoch": 9.81, + "learning_rate": 1.0793091197263764e-05, + "loss": 0.017, + "step": 11085 + }, + { + "epoch": 9.81, + "learning_rate": 1.0791662625645618e-05, + "loss": 0.0185, + "step": 11086 + }, + { + "epoch": 9.81, + "learning_rate": 1.0790234037769008e-05, + "loss": 0.0197, + "step": 11087 + }, + { + "epoch": 9.81, + "learning_rate": 1.078880543366327e-05, + "loss": 0.02, + "step": 11088 + }, + { + "epoch": 9.81, + "learning_rate": 1.0787376813357747e-05, + "loss": 0.0205, + "step": 11089 + }, + { + "epoch": 9.81, + "learning_rate": 1.0785948176881775e-05, + "loss": 0.0194, + "step": 11090 + }, + { + "epoch": 9.81, + "learning_rate": 1.0784519524264699e-05, + "loss": 0.0176, + "step": 11091 + }, + { + "epoch": 9.81, + "learning_rate": 1.0783090855535853e-05, + "loss": 0.0193, + "step": 11092 + }, + { + "epoch": 9.81, + "learning_rate": 1.0781662170724588e-05, + "loss": 0.021, + "step": 11093 + }, + { + "epoch": 9.82, + "learning_rate": 1.0780233469860236e-05, + "loss": 0.0263, + "step": 11094 + }, + { + "epoch": 9.82, + "learning_rate": 1.0778804752972134e-05, + "loss": 0.0235, + "step": 11095 + }, + { + "epoch": 9.82, + "learning_rate": 1.0777376020089638e-05, + "loss": 0.0219, + "step": 11096 + }, + { + "epoch": 9.82, + "learning_rate": 1.0775947271242083e-05, + "loss": 0.0192, + "step": 11097 + }, + { + "epoch": 9.82, + "learning_rate": 1.0774518506458806e-05, + "loss": 0.0234, + "step": 11098 + }, + { + "epoch": 9.82, + "learning_rate": 1.0773089725769158e-05, + "loss": 0.0192, + "step": 11099 + }, + { + "epoch": 9.82, + "learning_rate": 1.0771660929202478e-05, + "loss": 0.0215, + "step": 11100 + }, + { + "epoch": 9.82, + "learning_rate": 1.0770232116788111e-05, + "loss": 0.0177, + "step": 11101 + }, + { + "epoch": 9.82, + "learning_rate": 1.0768803288555398e-05, + "loss": 0.0213, + "step": 11102 + }, + { + "epoch": 9.82, + "learning_rate": 1.0767374444533687e-05, + "loss": 0.0207, + "step": 11103 + }, + { + "epoch": 9.82, + "learning_rate": 1.076594558475232e-05, + "loss": 0.0194, + "step": 11104 + }, + { + "epoch": 9.83, + "learning_rate": 1.076451670924064e-05, + "loss": 0.02, + "step": 11105 + }, + { + "epoch": 9.83, + "learning_rate": 1.0763087818027993e-05, + "loss": 0.0209, + "step": 11106 + }, + { + "epoch": 9.83, + "learning_rate": 1.0761658911143728e-05, + "loss": 0.0188, + "step": 11107 + }, + { + "epoch": 9.83, + "learning_rate": 1.0760229988617186e-05, + "loss": 0.0191, + "step": 11108 + }, + { + "epoch": 9.83, + "learning_rate": 1.0758801050477714e-05, + "loss": 0.0196, + "step": 11109 + }, + { + "epoch": 9.83, + "learning_rate": 1.075737209675466e-05, + "loss": 0.0172, + "step": 11110 + }, + { + "epoch": 9.83, + "learning_rate": 1.075594312747737e-05, + "loss": 0.0187, + "step": 11111 + }, + { + "epoch": 9.83, + "learning_rate": 1.075451414267519e-05, + "loss": 0.0202, + "step": 11112 + }, + { + "epoch": 9.83, + "learning_rate": 1.0753085142377466e-05, + "loss": 0.0189, + "step": 11113 + }, + { + "epoch": 9.83, + "learning_rate": 1.0751656126613552e-05, + "loss": 0.024, + "step": 11114 + }, + { + "epoch": 9.83, + "learning_rate": 1.0750227095412784e-05, + "loss": 0.0229, + "step": 11115 + }, + { + "epoch": 9.83, + "learning_rate": 1.0748798048804521e-05, + "loss": 0.0176, + "step": 11116 + }, + { + "epoch": 9.84, + "learning_rate": 1.0747368986818109e-05, + "loss": 0.0199, + "step": 11117 + }, + { + "epoch": 9.84, + "learning_rate": 1.0745939909482894e-05, + "loss": 0.0174, + "step": 11118 + }, + { + "epoch": 9.84, + "learning_rate": 1.0744510816828226e-05, + "loss": 0.0174, + "step": 11119 + }, + { + "epoch": 9.84, + "learning_rate": 1.0743081708883454e-05, + "loss": 0.0226, + "step": 11120 + }, + { + "epoch": 9.84, + "learning_rate": 1.074165258567793e-05, + "loss": 0.02, + "step": 11121 + }, + { + "epoch": 9.84, + "learning_rate": 1.0740223447241003e-05, + "loss": 0.0214, + "step": 11122 + }, + { + "epoch": 9.84, + "learning_rate": 1.0738794293602024e-05, + "loss": 0.02, + "step": 11123 + }, + { + "epoch": 9.84, + "learning_rate": 1.0737365124790344e-05, + "loss": 0.0198, + "step": 11124 + }, + { + "epoch": 9.84, + "learning_rate": 1.0735935940835311e-05, + "loss": 0.0204, + "step": 11125 + }, + { + "epoch": 9.84, + "learning_rate": 1.0734506741766278e-05, + "loss": 0.0162, + "step": 11126 + }, + { + "epoch": 9.84, + "learning_rate": 1.0733077527612597e-05, + "loss": 0.0204, + "step": 11127 + }, + { + "epoch": 9.85, + "learning_rate": 1.0731648298403621e-05, + "loss": 0.02, + "step": 11128 + }, + { + "epoch": 9.85, + "learning_rate": 1.0730219054168699e-05, + "loss": 0.0187, + "step": 11129 + }, + { + "epoch": 9.85, + "learning_rate": 1.0728789794937187e-05, + "loss": 0.0195, + "step": 11130 + }, + { + "epoch": 9.85, + "learning_rate": 1.0727360520738436e-05, + "loss": 0.0188, + "step": 11131 + }, + { + "epoch": 9.85, + "learning_rate": 1.0725931231601801e-05, + "loss": 0.0192, + "step": 11132 + }, + { + "epoch": 9.85, + "learning_rate": 1.0724501927556632e-05, + "loss": 0.02, + "step": 11133 + }, + { + "epoch": 9.85, + "learning_rate": 1.0723072608632286e-05, + "loss": 0.0225, + "step": 11134 + }, + { + "epoch": 9.85, + "learning_rate": 1.0721643274858116e-05, + "loss": 0.02, + "step": 11135 + }, + { + "epoch": 9.85, + "learning_rate": 1.0720213926263476e-05, + "loss": 0.0223, + "step": 11136 + }, + { + "epoch": 9.85, + "learning_rate": 1.071878456287772e-05, + "loss": 0.0169, + "step": 11137 + }, + { + "epoch": 9.85, + "learning_rate": 1.0717355184730207e-05, + "loss": 0.0203, + "step": 11138 + }, + { + "epoch": 9.86, + "learning_rate": 1.0715925791850287e-05, + "loss": 0.0196, + "step": 11139 + }, + { + "epoch": 9.86, + "learning_rate": 1.071449638426732e-05, + "loss": 0.0203, + "step": 11140 + }, + { + "epoch": 9.86, + "learning_rate": 1.0713066962010656e-05, + "loss": 0.0201, + "step": 11141 + }, + { + "epoch": 9.86, + "learning_rate": 1.0711637525109657e-05, + "loss": 0.0199, + "step": 11142 + }, + { + "epoch": 9.86, + "learning_rate": 1.0710208073593678e-05, + "loss": 0.0184, + "step": 11143 + }, + { + "epoch": 9.86, + "learning_rate": 1.0708778607492077e-05, + "loss": 0.019, + "step": 11144 + }, + { + "epoch": 9.86, + "learning_rate": 1.0707349126834208e-05, + "loss": 0.0192, + "step": 11145 + }, + { + "epoch": 9.86, + "learning_rate": 1.0705919631649429e-05, + "loss": 0.0201, + "step": 11146 + }, + { + "epoch": 9.86, + "learning_rate": 1.0704490121967098e-05, + "loss": 0.0176, + "step": 11147 + }, + { + "epoch": 9.86, + "learning_rate": 1.0703060597816576e-05, + "loss": 0.0204, + "step": 11148 + }, + { + "epoch": 9.86, + "learning_rate": 1.0701631059227218e-05, + "loss": 0.0192, + "step": 11149 + }, + { + "epoch": 9.86, + "learning_rate": 1.0700201506228383e-05, + "loss": 0.0213, + "step": 11150 + }, + { + "epoch": 9.87, + "learning_rate": 1.069877193884943e-05, + "loss": 0.021, + "step": 11151 + }, + { + "epoch": 9.87, + "learning_rate": 1.0697342357119719e-05, + "loss": 0.018, + "step": 11152 + }, + { + "epoch": 9.87, + "learning_rate": 1.069591276106861e-05, + "loss": 0.0208, + "step": 11153 + }, + { + "epoch": 9.87, + "learning_rate": 1.0694483150725458e-05, + "loss": 0.0197, + "step": 11154 + }, + { + "epoch": 9.87, + "learning_rate": 1.069305352611963e-05, + "loss": 0.0173, + "step": 11155 + }, + { + "epoch": 9.87, + "learning_rate": 1.0691623887280488e-05, + "loss": 0.0223, + "step": 11156 + }, + { + "epoch": 9.87, + "learning_rate": 1.0690194234237382e-05, + "loss": 0.0192, + "step": 11157 + }, + { + "epoch": 9.87, + "learning_rate": 1.0688764567019679e-05, + "loss": 0.0221, + "step": 11158 + }, + { + "epoch": 9.87, + "learning_rate": 1.068733488565674e-05, + "loss": 0.0195, + "step": 11159 + }, + { + "epoch": 9.87, + "learning_rate": 1.0685905190177927e-05, + "loss": 0.0192, + "step": 11160 + }, + { + "epoch": 9.87, + "learning_rate": 1.0684475480612602e-05, + "loss": 0.0196, + "step": 11161 + }, + { + "epoch": 9.88, + "learning_rate": 1.0683045756990127e-05, + "loss": 0.0217, + "step": 11162 + }, + { + "epoch": 9.88, + "learning_rate": 1.0681616019339864e-05, + "loss": 0.0181, + "step": 11163 + }, + { + "epoch": 9.88, + "learning_rate": 1.0680186267691175e-05, + "loss": 0.0197, + "step": 11164 + }, + { + "epoch": 9.88, + "learning_rate": 1.0678756502073424e-05, + "loss": 0.0222, + "step": 11165 + }, + { + "epoch": 9.88, + "learning_rate": 1.0677326722515973e-05, + "loss": 0.0212, + "step": 11166 + }, + { + "epoch": 9.88, + "learning_rate": 1.0675896929048186e-05, + "loss": 0.0187, + "step": 11167 + }, + { + "epoch": 9.88, + "learning_rate": 1.0674467121699428e-05, + "loss": 0.0224, + "step": 11168 + }, + { + "epoch": 9.88, + "learning_rate": 1.0673037300499064e-05, + "loss": 0.0197, + "step": 11169 + }, + { + "epoch": 9.88, + "learning_rate": 1.0671607465476457e-05, + "loss": 0.0226, + "step": 11170 + }, + { + "epoch": 9.88, + "learning_rate": 1.0670177616660969e-05, + "loss": 0.0191, + "step": 11171 + }, + { + "epoch": 9.88, + "learning_rate": 1.0668747754081968e-05, + "loss": 0.021, + "step": 11172 + }, + { + "epoch": 9.89, + "learning_rate": 1.0667317877768819e-05, + "loss": 0.0205, + "step": 11173 + }, + { + "epoch": 9.89, + "learning_rate": 1.0665887987750885e-05, + "loss": 0.0216, + "step": 11174 + }, + { + "epoch": 9.89, + "learning_rate": 1.0664458084057537e-05, + "loss": 0.0238, + "step": 11175 + }, + { + "epoch": 9.89, + "learning_rate": 1.0663028166718137e-05, + "loss": 0.0199, + "step": 11176 + }, + { + "epoch": 9.89, + "learning_rate": 1.0661598235762054e-05, + "loss": 0.021, + "step": 11177 + }, + { + "epoch": 9.89, + "learning_rate": 1.066016829121865e-05, + "loss": 0.0218, + "step": 11178 + }, + { + "epoch": 9.89, + "learning_rate": 1.0658738333117298e-05, + "loss": 0.02, + "step": 11179 + }, + { + "epoch": 9.89, + "learning_rate": 1.0657308361487359e-05, + "loss": 0.0159, + "step": 11180 + }, + { + "epoch": 9.89, + "learning_rate": 1.0655878376358206e-05, + "loss": 0.0215, + "step": 11181 + }, + { + "epoch": 9.89, + "learning_rate": 1.0654448377759204e-05, + "loss": 0.0248, + "step": 11182 + }, + { + "epoch": 9.89, + "learning_rate": 1.0653018365719721e-05, + "loss": 0.019, + "step": 11183 + }, + { + "epoch": 9.9, + "learning_rate": 1.0651588340269127e-05, + "loss": 0.0227, + "step": 11184 + }, + { + "epoch": 9.9, + "learning_rate": 1.065015830143679e-05, + "loss": 0.0214, + "step": 11185 + }, + { + "epoch": 9.9, + "learning_rate": 1.0648728249252076e-05, + "loss": 0.0189, + "step": 11186 + }, + { + "epoch": 9.9, + "learning_rate": 1.0647298183744359e-05, + "loss": 0.0182, + "step": 11187 + }, + { + "epoch": 9.9, + "learning_rate": 1.0645868104943005e-05, + "loss": 0.0209, + "step": 11188 + }, + { + "epoch": 9.9, + "learning_rate": 1.0644438012877382e-05, + "loss": 0.0218, + "step": 11189 + }, + { + "epoch": 9.9, + "learning_rate": 1.0643007907576865e-05, + "loss": 0.0255, + "step": 11190 + }, + { + "epoch": 9.9, + "learning_rate": 1.0641577789070825e-05, + "loss": 0.0209, + "step": 11191 + }, + { + "epoch": 9.9, + "learning_rate": 1.0640147657388627e-05, + "loss": 0.02, + "step": 11192 + }, + { + "epoch": 9.9, + "learning_rate": 1.063871751255964e-05, + "loss": 0.0225, + "step": 11193 + }, + { + "epoch": 9.9, + "learning_rate": 1.0637287354613244e-05, + "loss": 0.0222, + "step": 11194 + }, + { + "epoch": 9.9, + "learning_rate": 1.06358571835788e-05, + "loss": 0.0214, + "step": 11195 + }, + { + "epoch": 9.91, + "learning_rate": 1.0634426999485692e-05, + "loss": 0.0227, + "step": 11196 + }, + { + "epoch": 9.91, + "learning_rate": 1.063299680236328e-05, + "loss": 0.0246, + "step": 11197 + }, + { + "epoch": 9.91, + "learning_rate": 1.0631566592240944e-05, + "loss": 0.0214, + "step": 11198 + }, + { + "epoch": 9.91, + "learning_rate": 1.063013636914805e-05, + "loss": 0.0216, + "step": 11199 + }, + { + "epoch": 9.91, + "learning_rate": 1.0628706133113976e-05, + "loss": 0.0193, + "step": 11200 + }, + { + "epoch": 9.91, + "learning_rate": 1.0627275884168094e-05, + "loss": 0.0203, + "step": 11201 + }, + { + "epoch": 9.91, + "learning_rate": 1.0625845622339774e-05, + "loss": 0.0209, + "step": 11202 + }, + { + "epoch": 9.91, + "learning_rate": 1.0624415347658392e-05, + "loss": 0.025, + "step": 11203 + }, + { + "epoch": 9.91, + "learning_rate": 1.062298506015332e-05, + "loss": 0.0195, + "step": 11204 + }, + { + "epoch": 9.91, + "learning_rate": 1.062155475985394e-05, + "loss": 0.0209, + "step": 11205 + }, + { + "epoch": 9.91, + "learning_rate": 1.0620124446789613e-05, + "loss": 0.019, + "step": 11206 + }, + { + "epoch": 9.92, + "learning_rate": 1.0618694120989721e-05, + "loss": 0.0183, + "step": 11207 + }, + { + "epoch": 9.92, + "learning_rate": 1.061726378248364e-05, + "loss": 0.0213, + "step": 11208 + }, + { + "epoch": 9.92, + "learning_rate": 1.061583343130074e-05, + "loss": 0.019, + "step": 11209 + }, + { + "epoch": 9.92, + "learning_rate": 1.06144030674704e-05, + "loss": 0.0199, + "step": 11210 + }, + { + "epoch": 9.92, + "learning_rate": 1.0612972691021994e-05, + "loss": 0.0216, + "step": 11211 + }, + { + "epoch": 9.92, + "learning_rate": 1.0611542301984901e-05, + "loss": 0.0195, + "step": 11212 + }, + { + "epoch": 9.92, + "learning_rate": 1.0610111900388491e-05, + "loss": 0.0193, + "step": 11213 + }, + { + "epoch": 9.92, + "learning_rate": 1.0608681486262147e-05, + "loss": 0.021, + "step": 11214 + }, + { + "epoch": 9.92, + "learning_rate": 1.0607251059635241e-05, + "loss": 0.0216, + "step": 11215 + }, + { + "epoch": 9.92, + "learning_rate": 1.0605820620537151e-05, + "loss": 0.018, + "step": 11216 + }, + { + "epoch": 9.92, + "learning_rate": 1.0604390168997255e-05, + "loss": 0.0188, + "step": 11217 + }, + { + "epoch": 9.93, + "learning_rate": 1.0602959705044929e-05, + "loss": 0.0197, + "step": 11218 + }, + { + "epoch": 9.93, + "learning_rate": 1.060152922870955e-05, + "loss": 0.0212, + "step": 11219 + }, + { + "epoch": 9.93, + "learning_rate": 1.0600098740020499e-05, + "loss": 0.0206, + "step": 11220 + }, + { + "epoch": 9.93, + "learning_rate": 1.0598668239007153e-05, + "loss": 0.0189, + "step": 11221 + }, + { + "epoch": 9.93, + "learning_rate": 1.059723772569889e-05, + "loss": 0.0188, + "step": 11222 + }, + { + "epoch": 9.93, + "learning_rate": 1.0595807200125085e-05, + "loss": 0.0219, + "step": 11223 + }, + { + "epoch": 9.93, + "learning_rate": 1.0594376662315122e-05, + "loss": 0.0219, + "step": 11224 + }, + { + "epoch": 9.93, + "learning_rate": 1.0592946112298377e-05, + "loss": 0.0179, + "step": 11225 + }, + { + "epoch": 9.93, + "learning_rate": 1.0591515550104233e-05, + "loss": 0.0202, + "step": 11226 + }, + { + "epoch": 9.93, + "learning_rate": 1.0590084975762064e-05, + "loss": 0.0213, + "step": 11227 + }, + { + "epoch": 9.93, + "learning_rate": 1.0588654389301254e-05, + "loss": 0.0199, + "step": 11228 + }, + { + "epoch": 9.93, + "learning_rate": 1.0587223790751185e-05, + "loss": 0.0196, + "step": 11229 + }, + { + "epoch": 9.94, + "learning_rate": 1.058579318014123e-05, + "loss": 0.0211, + "step": 11230 + }, + { + "epoch": 9.94, + "learning_rate": 1.0584362557500778e-05, + "loss": 0.0215, + "step": 11231 + }, + { + "epoch": 9.94, + "learning_rate": 1.0582931922859203e-05, + "loss": 0.0189, + "step": 11232 + }, + { + "epoch": 9.94, + "learning_rate": 1.058150127624589e-05, + "loss": 0.019, + "step": 11233 + }, + { + "epoch": 9.94, + "learning_rate": 1.0580070617690222e-05, + "loss": 0.0189, + "step": 11234 + }, + { + "epoch": 9.94, + "learning_rate": 1.0578639947221574e-05, + "loss": 0.0189, + "step": 11235 + }, + { + "epoch": 9.94, + "learning_rate": 1.0577209264869334e-05, + "loss": 0.0178, + "step": 11236 + }, + { + "epoch": 9.94, + "learning_rate": 1.0575778570662882e-05, + "loss": 0.0251, + "step": 11237 + }, + { + "epoch": 9.94, + "learning_rate": 1.0574347864631598e-05, + "loss": 0.0207, + "step": 11238 + }, + { + "epoch": 9.94, + "learning_rate": 1.057291714680487e-05, + "loss": 0.0237, + "step": 11239 + }, + { + "epoch": 9.94, + "learning_rate": 1.0571486417212077e-05, + "loss": 0.0186, + "step": 11240 + }, + { + "epoch": 9.95, + "learning_rate": 1.0570055675882602e-05, + "loss": 0.0173, + "step": 11241 + }, + { + "epoch": 9.95, + "learning_rate": 1.056862492284583e-05, + "loss": 0.0216, + "step": 11242 + }, + { + "epoch": 9.95, + "learning_rate": 1.0567194158131144e-05, + "loss": 0.0205, + "step": 11243 + }, + { + "epoch": 9.95, + "learning_rate": 1.0565763381767926e-05, + "loss": 0.0215, + "step": 11244 + }, + { + "epoch": 9.95, + "learning_rate": 1.056433259378556e-05, + "loss": 0.0223, + "step": 11245 + }, + { + "epoch": 9.95, + "learning_rate": 1.0562901794213434e-05, + "loss": 0.0204, + "step": 11246 + }, + { + "epoch": 9.95, + "learning_rate": 1.056147098308093e-05, + "loss": 0.0231, + "step": 11247 + }, + { + "epoch": 9.95, + "learning_rate": 1.056004016041743e-05, + "loss": 0.0231, + "step": 11248 + }, + { + "epoch": 9.95, + "learning_rate": 1.0558609326252325e-05, + "loss": 0.019, + "step": 11249 + }, + { + "epoch": 9.95, + "learning_rate": 1.0557178480614998e-05, + "loss": 0.0179, + "step": 11250 + }, + { + "epoch": 9.95, + "learning_rate": 1.055574762353483e-05, + "loss": 0.0201, + "step": 11251 + }, + { + "epoch": 9.96, + "learning_rate": 1.0554316755041209e-05, + "loss": 0.0239, + "step": 11252 + }, + { + "epoch": 9.96, + "learning_rate": 1.0552885875163527e-05, + "loss": 0.0174, + "step": 11253 + }, + { + "epoch": 9.96, + "learning_rate": 1.0551454983931164e-05, + "loss": 0.0217, + "step": 11254 + }, + { + "epoch": 9.96, + "learning_rate": 1.0550024081373504e-05, + "loss": 0.0205, + "step": 11255 + }, + { + "epoch": 9.96, + "learning_rate": 1.054859316751994e-05, + "loss": 0.0194, + "step": 11256 + }, + { + "epoch": 9.96, + "learning_rate": 1.0547162242399858e-05, + "loss": 0.0271, + "step": 11257 + }, + { + "epoch": 9.96, + "learning_rate": 1.0545731306042637e-05, + "loss": 0.0189, + "step": 11258 + }, + { + "epoch": 9.96, + "learning_rate": 1.0544300358477676e-05, + "loss": 0.0205, + "step": 11259 + }, + { + "epoch": 9.96, + "learning_rate": 1.0542869399734354e-05, + "loss": 0.0193, + "step": 11260 + }, + { + "epoch": 9.96, + "learning_rate": 1.0541438429842064e-05, + "loss": 0.0201, + "step": 11261 + }, + { + "epoch": 9.96, + "learning_rate": 1.054000744883019e-05, + "loss": 0.019, + "step": 11262 + }, + { + "epoch": 9.96, + "learning_rate": 1.0538576456728121e-05, + "loss": 0.0188, + "step": 11263 + }, + { + "epoch": 9.97, + "learning_rate": 1.053714545356525e-05, + "loss": 0.0222, + "step": 11264 + }, + { + "epoch": 9.97, + "learning_rate": 1.0535714439370957e-05, + "loss": 0.0185, + "step": 11265 + }, + { + "epoch": 9.97, + "learning_rate": 1.0534283414174637e-05, + "loss": 0.0201, + "step": 11266 + }, + { + "epoch": 9.97, + "learning_rate": 1.053285237800568e-05, + "loss": 0.0212, + "step": 11267 + }, + { + "epoch": 9.97, + "learning_rate": 1.0531421330893471e-05, + "loss": 0.0212, + "step": 11268 + }, + { + "epoch": 9.97, + "learning_rate": 1.0529990272867405e-05, + "loss": 0.0231, + "step": 11269 + }, + { + "epoch": 9.97, + "learning_rate": 1.0528559203956868e-05, + "loss": 0.0201, + "step": 11270 + }, + { + "epoch": 9.97, + "learning_rate": 1.0527128124191249e-05, + "loss": 0.021, + "step": 11271 + }, + { + "epoch": 9.97, + "learning_rate": 1.052569703359994e-05, + "loss": 0.0191, + "step": 11272 + }, + { + "epoch": 9.97, + "learning_rate": 1.0524265932212332e-05, + "loss": 0.0191, + "step": 11273 + }, + { + "epoch": 9.97, + "learning_rate": 1.052283482005782e-05, + "loss": 0.0239, + "step": 11274 + }, + { + "epoch": 9.98, + "learning_rate": 1.0521403697165784e-05, + "loss": 0.0231, + "step": 11275 + }, + { + "epoch": 9.98, + "learning_rate": 1.0519972563565624e-05, + "loss": 0.0231, + "step": 11276 + }, + { + "epoch": 9.98, + "learning_rate": 1.0518541419286725e-05, + "loss": 0.0188, + "step": 11277 + }, + { + "epoch": 9.98, + "learning_rate": 1.0517110264358485e-05, + "loss": 0.0223, + "step": 11278 + }, + { + "epoch": 9.98, + "learning_rate": 1.0515679098810292e-05, + "loss": 0.0198, + "step": 11279 + }, + { + "epoch": 9.98, + "learning_rate": 1.0514247922671541e-05, + "loss": 0.0207, + "step": 11280 + }, + { + "epoch": 9.98, + "learning_rate": 1.0512816735971621e-05, + "loss": 0.018, + "step": 11281 + }, + { + "epoch": 9.98, + "learning_rate": 1.0511385538739927e-05, + "loss": 0.0198, + "step": 11282 + }, + { + "epoch": 9.98, + "learning_rate": 1.0509954331005848e-05, + "loss": 0.0218, + "step": 11283 + }, + { + "epoch": 9.98, + "learning_rate": 1.0508523112798777e-05, + "loss": 0.0201, + "step": 11284 + }, + { + "epoch": 9.98, + "learning_rate": 1.0507091884148115e-05, + "loss": 0.0201, + "step": 11285 + }, + { + "epoch": 9.99, + "learning_rate": 1.0505660645083246e-05, + "loss": 0.0189, + "step": 11286 + }, + { + "epoch": 9.99, + "learning_rate": 1.0504229395633566e-05, + "loss": 0.0228, + "step": 11287 + }, + { + "epoch": 9.99, + "learning_rate": 1.0502798135828472e-05, + "loss": 0.0223, + "step": 11288 + }, + { + "epoch": 9.99, + "learning_rate": 1.0501366865697358e-05, + "loss": 0.0185, + "step": 11289 + }, + { + "epoch": 9.99, + "learning_rate": 1.0499935585269612e-05, + "loss": 0.0177, + "step": 11290 + }, + { + "epoch": 9.99, + "learning_rate": 1.0498504294574632e-05, + "loss": 0.0191, + "step": 11291 + }, + { + "epoch": 9.99, + "learning_rate": 1.0497072993641818e-05, + "loss": 0.0178, + "step": 11292 + }, + { + "epoch": 9.99, + "learning_rate": 1.0495641682500555e-05, + "loss": 0.0234, + "step": 11293 + }, + { + "epoch": 9.99, + "learning_rate": 1.0494210361180242e-05, + "loss": 0.0256, + "step": 11294 + }, + { + "epoch": 9.99, + "learning_rate": 1.0492779029710277e-05, + "loss": 0.0235, + "step": 11295 + }, + { + "epoch": 9.99, + "learning_rate": 1.0491347688120055e-05, + "loss": 0.024, + "step": 11296 + }, + { + "epoch": 10.0, + "learning_rate": 1.0489916336438964e-05, + "loss": 0.0189, + "step": 11297 + }, + { + "epoch": 10.0, + "learning_rate": 1.0488484974696409e-05, + "loss": 0.0203, + "step": 11298 + }, + { + "epoch": 10.0, + "learning_rate": 1.0487053602921784e-05, + "loss": 0.0229, + "step": 11299 + }, + { + "epoch": 10.0, + "learning_rate": 1.0485622221144485e-05, + "loss": 0.0177, + "step": 11300 + }, + { + "epoch": 10.0, + "learning_rate": 1.0484190829393903e-05, + "loss": 0.0201, + "step": 11301 + }, + { + "epoch": 10.0, + "learning_rate": 1.0482759427699443e-05, + "loss": 0.021, + "step": 11302 + }, + { + "epoch": 10.0, + "learning_rate": 1.0481328016090498e-05, + "loss": 0.0176, + "step": 11303 + }, + { + "epoch": 10.0, + "learning_rate": 1.0479896594596461e-05, + "loss": 0.0099, + "step": 11304 + }, + { + "epoch": 10.0, + "learning_rate": 1.0478465163246736e-05, + "loss": 0.0102, + "step": 11305 + }, + { + "epoch": 10.0, + "learning_rate": 1.047703372207072e-05, + "loss": 0.0109, + "step": 11306 + }, + { + "epoch": 10.0, + "learning_rate": 1.0475602271097805e-05, + "loss": 0.012, + "step": 11307 + }, + { + "epoch": 10.0, + "learning_rate": 1.0474170810357393e-05, + "loss": 0.0111, + "step": 11308 + }, + { + "epoch": 10.01, + "learning_rate": 1.047273933987888e-05, + "loss": 0.0107, + "step": 11309 + }, + { + "epoch": 10.01, + "learning_rate": 1.0471307859691668e-05, + "loss": 0.011, + "step": 11310 + }, + { + "epoch": 10.01, + "learning_rate": 1.0469876369825155e-05, + "loss": 0.0106, + "step": 11311 + }, + { + "epoch": 10.01, + "learning_rate": 1.0468444870308733e-05, + "loss": 0.0097, + "step": 11312 + }, + { + "epoch": 10.01, + "learning_rate": 1.046701336117181e-05, + "loss": 0.0108, + "step": 11313 + }, + { + "epoch": 10.01, + "learning_rate": 1.0465581842443779e-05, + "loss": 0.0116, + "step": 11314 + }, + { + "epoch": 10.01, + "learning_rate": 1.046415031415404e-05, + "loss": 0.0108, + "step": 11315 + }, + { + "epoch": 10.01, + "learning_rate": 1.0462718776331995e-05, + "loss": 0.0143, + "step": 11316 + }, + { + "epoch": 10.01, + "learning_rate": 1.046128722900704e-05, + "loss": 0.0109, + "step": 11317 + }, + { + "epoch": 10.01, + "learning_rate": 1.0459855672208579e-05, + "loss": 0.0116, + "step": 11318 + }, + { + "epoch": 10.01, + "learning_rate": 1.0458424105966007e-05, + "loss": 0.0101, + "step": 11319 + }, + { + "epoch": 10.02, + "learning_rate": 1.0456992530308732e-05, + "loss": 0.0108, + "step": 11320 + }, + { + "epoch": 10.02, + "learning_rate": 1.0455560945266147e-05, + "loss": 0.0104, + "step": 11321 + }, + { + "epoch": 10.02, + "learning_rate": 1.0454129350867655e-05, + "loss": 0.01, + "step": 11322 + }, + { + "epoch": 10.02, + "learning_rate": 1.0452697747142658e-05, + "loss": 0.0101, + "step": 11323 + }, + { + "epoch": 10.02, + "learning_rate": 1.0451266134120555e-05, + "loss": 0.011, + "step": 11324 + }, + { + "epoch": 10.02, + "learning_rate": 1.0449834511830747e-05, + "loss": 0.0122, + "step": 11325 + }, + { + "epoch": 10.02, + "learning_rate": 1.044840288030264e-05, + "loss": 0.0102, + "step": 11326 + }, + { + "epoch": 10.02, + "learning_rate": 1.0446971239565631e-05, + "loss": 0.0113, + "step": 11327 + }, + { + "epoch": 10.02, + "learning_rate": 1.0445539589649123e-05, + "loss": 0.0109, + "step": 11328 + }, + { + "epoch": 10.02, + "learning_rate": 1.0444107930582517e-05, + "loss": 0.0123, + "step": 11329 + }, + { + "epoch": 10.02, + "learning_rate": 1.0442676262395217e-05, + "loss": 0.0101, + "step": 11330 + }, + { + "epoch": 10.03, + "learning_rate": 1.0441244585116624e-05, + "loss": 0.0103, + "step": 11331 + }, + { + "epoch": 10.03, + "learning_rate": 1.0439812898776141e-05, + "loss": 0.0109, + "step": 11332 + }, + { + "epoch": 10.03, + "learning_rate": 1.0438381203403171e-05, + "loss": 0.0101, + "step": 11333 + }, + { + "epoch": 10.03, + "learning_rate": 1.0436949499027119e-05, + "loss": 0.0119, + "step": 11334 + }, + { + "epoch": 10.03, + "learning_rate": 1.0435517785677382e-05, + "loss": 0.0107, + "step": 11335 + }, + { + "epoch": 10.03, + "learning_rate": 1.0434086063383366e-05, + "loss": 0.0116, + "step": 11336 + }, + { + "epoch": 10.03, + "learning_rate": 1.043265433217448e-05, + "loss": 0.0103, + "step": 11337 + }, + { + "epoch": 10.03, + "learning_rate": 1.043122259208012e-05, + "loss": 0.0089, + "step": 11338 + }, + { + "epoch": 10.03, + "learning_rate": 1.0429790843129695e-05, + "loss": 0.0099, + "step": 11339 + }, + { + "epoch": 10.03, + "learning_rate": 1.0428359085352604e-05, + "loss": 0.0099, + "step": 11340 + }, + { + "epoch": 10.03, + "learning_rate": 1.0426927318778257e-05, + "loss": 0.0099, + "step": 11341 + }, + { + "epoch": 10.03, + "learning_rate": 1.0425495543436053e-05, + "loss": 0.0111, + "step": 11342 + }, + { + "epoch": 10.04, + "learning_rate": 1.0424063759355396e-05, + "loss": 0.0106, + "step": 11343 + }, + { + "epoch": 10.04, + "learning_rate": 1.0422631966565699e-05, + "loss": 0.0096, + "step": 11344 + }, + { + "epoch": 10.04, + "learning_rate": 1.0421200165096358e-05, + "loss": 0.0106, + "step": 11345 + }, + { + "epoch": 10.04, + "learning_rate": 1.0419768354976782e-05, + "loss": 0.0102, + "step": 11346 + }, + { + "epoch": 10.04, + "learning_rate": 1.0418336536236377e-05, + "loss": 0.0094, + "step": 11347 + }, + { + "epoch": 10.04, + "learning_rate": 1.041690470890455e-05, + "loss": 0.0099, + "step": 11348 + }, + { + "epoch": 10.04, + "learning_rate": 1.0415472873010696e-05, + "loss": 0.0109, + "step": 11349 + }, + { + "epoch": 10.04, + "learning_rate": 1.0414041028584234e-05, + "loss": 0.0113, + "step": 11350 + }, + { + "epoch": 10.04, + "learning_rate": 1.0412609175654566e-05, + "loss": 0.0104, + "step": 11351 + }, + { + "epoch": 10.04, + "learning_rate": 1.0411177314251094e-05, + "loss": 0.011, + "step": 11352 + }, + { + "epoch": 10.04, + "learning_rate": 1.0409745444403225e-05, + "loss": 0.0106, + "step": 11353 + }, + { + "epoch": 10.05, + "learning_rate": 1.0408313566140371e-05, + "loss": 0.0148, + "step": 11354 + }, + { + "epoch": 10.05, + "learning_rate": 1.0406881679491936e-05, + "loss": 0.0112, + "step": 11355 + }, + { + "epoch": 10.05, + "learning_rate": 1.040544978448732e-05, + "loss": 0.0106, + "step": 11356 + }, + { + "epoch": 10.05, + "learning_rate": 1.040401788115594e-05, + "loss": 0.01, + "step": 11357 + }, + { + "epoch": 10.05, + "learning_rate": 1.04025859695272e-05, + "loss": 0.0101, + "step": 11358 + }, + { + "epoch": 10.05, + "learning_rate": 1.0401154049630503e-05, + "loss": 0.0101, + "step": 11359 + }, + { + "epoch": 10.05, + "learning_rate": 1.0399722121495262e-05, + "loss": 0.0108, + "step": 11360 + }, + { + "epoch": 10.05, + "learning_rate": 1.0398290185150881e-05, + "loss": 0.0099, + "step": 11361 + }, + { + "epoch": 10.05, + "learning_rate": 1.039685824062677e-05, + "loss": 0.0109, + "step": 11362 + }, + { + "epoch": 10.05, + "learning_rate": 1.0395426287952337e-05, + "loss": 0.012, + "step": 11363 + }, + { + "epoch": 10.05, + "learning_rate": 1.0393994327156988e-05, + "loss": 0.0102, + "step": 11364 + }, + { + "epoch": 10.06, + "learning_rate": 1.0392562358270138e-05, + "loss": 0.0105, + "step": 11365 + }, + { + "epoch": 10.06, + "learning_rate": 1.0391130381321187e-05, + "loss": 0.0104, + "step": 11366 + }, + { + "epoch": 10.06, + "learning_rate": 1.0389698396339545e-05, + "loss": 0.0112, + "step": 11367 + }, + { + "epoch": 10.06, + "learning_rate": 1.0388266403354625e-05, + "loss": 0.0098, + "step": 11368 + }, + { + "epoch": 10.06, + "learning_rate": 1.0386834402395834e-05, + "loss": 0.0086, + "step": 11369 + }, + { + "epoch": 10.06, + "learning_rate": 1.0385402393492579e-05, + "loss": 0.0114, + "step": 11370 + }, + { + "epoch": 10.06, + "learning_rate": 1.0383970376674273e-05, + "loss": 0.011, + "step": 11371 + }, + { + "epoch": 10.06, + "learning_rate": 1.0382538351970326e-05, + "loss": 0.0124, + "step": 11372 + }, + { + "epoch": 10.06, + "learning_rate": 1.0381106319410144e-05, + "loss": 0.0117, + "step": 11373 + }, + { + "epoch": 10.06, + "learning_rate": 1.0379674279023138e-05, + "loss": 0.0116, + "step": 11374 + }, + { + "epoch": 10.06, + "learning_rate": 1.0378242230838718e-05, + "loss": 0.0109, + "step": 11375 + }, + { + "epoch": 10.06, + "learning_rate": 1.0376810174886294e-05, + "loss": 0.0119, + "step": 11376 + }, + { + "epoch": 10.07, + "learning_rate": 1.0375378111195276e-05, + "loss": 0.0119, + "step": 11377 + }, + { + "epoch": 10.07, + "learning_rate": 1.0373946039795075e-05, + "loss": 0.0091, + "step": 11378 + }, + { + "epoch": 10.07, + "learning_rate": 1.0372513960715108e-05, + "loss": 0.0103, + "step": 11379 + }, + { + "epoch": 10.07, + "learning_rate": 1.0371081873984774e-05, + "loss": 0.0103, + "step": 11380 + }, + { + "epoch": 10.07, + "learning_rate": 1.0369649779633491e-05, + "loss": 0.011, + "step": 11381 + }, + { + "epoch": 10.07, + "learning_rate": 1.0368217677690666e-05, + "loss": 0.0107, + "step": 11382 + }, + { + "epoch": 10.07, + "learning_rate": 1.0366785568185716e-05, + "loss": 0.0093, + "step": 11383 + }, + { + "epoch": 10.07, + "learning_rate": 1.0365353451148048e-05, + "loss": 0.0085, + "step": 11384 + }, + { + "epoch": 10.07, + "learning_rate": 1.0363921326607073e-05, + "loss": 0.0115, + "step": 11385 + }, + { + "epoch": 10.07, + "learning_rate": 1.0362489194592209e-05, + "loss": 0.0097, + "step": 11386 + }, + { + "epoch": 10.07, + "learning_rate": 1.0361057055132862e-05, + "loss": 0.0114, + "step": 11387 + }, + { + "epoch": 10.08, + "learning_rate": 1.035962490825844e-05, + "loss": 0.0098, + "step": 11388 + }, + { + "epoch": 10.08, + "learning_rate": 1.0358192753998369e-05, + "loss": 0.0103, + "step": 11389 + }, + { + "epoch": 10.08, + "learning_rate": 1.0356760592382047e-05, + "loss": 0.0112, + "step": 11390 + }, + { + "epoch": 10.08, + "learning_rate": 1.0355328423438894e-05, + "loss": 0.0085, + "step": 11391 + }, + { + "epoch": 10.08, + "learning_rate": 1.035389624719832e-05, + "loss": 0.0104, + "step": 11392 + }, + { + "epoch": 10.08, + "learning_rate": 1.0352464063689742e-05, + "loss": 0.01, + "step": 11393 + }, + { + "epoch": 10.08, + "learning_rate": 1.0351031872942568e-05, + "loss": 0.012, + "step": 11394 + }, + { + "epoch": 10.08, + "learning_rate": 1.0349599674986208e-05, + "loss": 0.0138, + "step": 11395 + }, + { + "epoch": 10.08, + "learning_rate": 1.0348167469850084e-05, + "loss": 0.0123, + "step": 11396 + }, + { + "epoch": 10.08, + "learning_rate": 1.0346735257563606e-05, + "loss": 0.0103, + "step": 11397 + }, + { + "epoch": 10.08, + "learning_rate": 1.0345303038156187e-05, + "loss": 0.0096, + "step": 11398 + }, + { + "epoch": 10.09, + "learning_rate": 1.034387081165724e-05, + "loss": 0.0097, + "step": 11399 + }, + { + "epoch": 10.09, + "learning_rate": 1.0342438578096178e-05, + "loss": 0.0121, + "step": 11400 + }, + { + "epoch": 10.09, + "learning_rate": 1.0341006337502417e-05, + "loss": 0.0091, + "step": 11401 + }, + { + "epoch": 10.09, + "learning_rate": 1.0339574089905369e-05, + "loss": 0.0104, + "step": 11402 + }, + { + "epoch": 10.09, + "learning_rate": 1.0338141835334447e-05, + "loss": 0.0111, + "step": 11403 + }, + { + "epoch": 10.09, + "learning_rate": 1.0336709573819075e-05, + "loss": 0.0105, + "step": 11404 + }, + { + "epoch": 10.09, + "learning_rate": 1.0335277305388655e-05, + "loss": 0.0098, + "step": 11405 + }, + { + "epoch": 10.09, + "learning_rate": 1.033384503007261e-05, + "loss": 0.009, + "step": 11406 + }, + { + "epoch": 10.09, + "learning_rate": 1.0332412747900349e-05, + "loss": 0.0118, + "step": 11407 + }, + { + "epoch": 10.09, + "learning_rate": 1.033098045890129e-05, + "loss": 0.011, + "step": 11408 + }, + { + "epoch": 10.09, + "learning_rate": 1.032954816310485e-05, + "loss": 0.0112, + "step": 11409 + }, + { + "epoch": 10.09, + "learning_rate": 1.0328115860540439e-05, + "loss": 0.0098, + "step": 11410 + }, + { + "epoch": 10.1, + "learning_rate": 1.0326683551237479e-05, + "loss": 0.01, + "step": 11411 + }, + { + "epoch": 10.1, + "learning_rate": 1.0325251235225381e-05, + "loss": 0.0094, + "step": 11412 + }, + { + "epoch": 10.1, + "learning_rate": 1.0323818912533561e-05, + "loss": 0.012, + "step": 11413 + }, + { + "epoch": 10.1, + "learning_rate": 1.0322386583191435e-05, + "loss": 0.0115, + "step": 11414 + }, + { + "epoch": 10.1, + "learning_rate": 1.0320954247228418e-05, + "loss": 0.0113, + "step": 11415 + }, + { + "epoch": 10.1, + "learning_rate": 1.0319521904673928e-05, + "loss": 0.0127, + "step": 11416 + }, + { + "epoch": 10.1, + "learning_rate": 1.0318089555557382e-05, + "loss": 0.011, + "step": 11417 + }, + { + "epoch": 10.1, + "learning_rate": 1.0316657199908195e-05, + "loss": 0.0105, + "step": 11418 + }, + { + "epoch": 10.1, + "learning_rate": 1.0315224837755781e-05, + "loss": 0.0124, + "step": 11419 + }, + { + "epoch": 10.1, + "learning_rate": 1.031379246912956e-05, + "loss": 0.012, + "step": 11420 + }, + { + "epoch": 10.1, + "learning_rate": 1.0312360094058948e-05, + "loss": 0.0102, + "step": 11421 + }, + { + "epoch": 10.11, + "learning_rate": 1.031092771257336e-05, + "loss": 0.0102, + "step": 11422 + }, + { + "epoch": 10.11, + "learning_rate": 1.0309495324702215e-05, + "loss": 0.0108, + "step": 11423 + }, + { + "epoch": 10.11, + "learning_rate": 1.0308062930474928e-05, + "loss": 0.0093, + "step": 11424 + }, + { + "epoch": 10.11, + "learning_rate": 1.0306630529920923e-05, + "loss": 0.0103, + "step": 11425 + }, + { + "epoch": 10.11, + "learning_rate": 1.0305198123069608e-05, + "loss": 0.0111, + "step": 11426 + }, + { + "epoch": 10.11, + "learning_rate": 1.0303765709950404e-05, + "loss": 0.0102, + "step": 11427 + }, + { + "epoch": 10.11, + "learning_rate": 1.030233329059273e-05, + "loss": 0.0143, + "step": 11428 + }, + { + "epoch": 10.11, + "learning_rate": 1.0300900865026004e-05, + "loss": 0.0115, + "step": 11429 + }, + { + "epoch": 10.11, + "learning_rate": 1.0299468433279642e-05, + "loss": 0.012, + "step": 11430 + }, + { + "epoch": 10.11, + "learning_rate": 1.0298035995383063e-05, + "loss": 0.0103, + "step": 11431 + }, + { + "epoch": 10.11, + "learning_rate": 1.0296603551365688e-05, + "loss": 0.0103, + "step": 11432 + }, + { + "epoch": 10.12, + "learning_rate": 1.0295171101256927e-05, + "loss": 0.0107, + "step": 11433 + }, + { + "epoch": 10.12, + "learning_rate": 1.0293738645086205e-05, + "loss": 0.01, + "step": 11434 + }, + { + "epoch": 10.12, + "learning_rate": 1.029230618288294e-05, + "loss": 0.0096, + "step": 11435 + }, + { + "epoch": 10.12, + "learning_rate": 1.029087371467655e-05, + "loss": 0.0099, + "step": 11436 + }, + { + "epoch": 10.12, + "learning_rate": 1.0289441240496454e-05, + "loss": 0.01, + "step": 11437 + }, + { + "epoch": 10.12, + "learning_rate": 1.0288008760372069e-05, + "loss": 0.0118, + "step": 11438 + }, + { + "epoch": 10.12, + "learning_rate": 1.0286576274332818e-05, + "loss": 0.0108, + "step": 11439 + }, + { + "epoch": 10.12, + "learning_rate": 1.0285143782408116e-05, + "loss": 0.0104, + "step": 11440 + }, + { + "epoch": 10.12, + "learning_rate": 1.028371128462738e-05, + "loss": 0.01, + "step": 11441 + }, + { + "epoch": 10.12, + "learning_rate": 1.028227878102004e-05, + "loss": 0.0101, + "step": 11442 + }, + { + "epoch": 10.12, + "learning_rate": 1.0280846271615506e-05, + "loss": 0.0101, + "step": 11443 + }, + { + "epoch": 10.13, + "learning_rate": 1.02794137564432e-05, + "loss": 0.013, + "step": 11444 + }, + { + "epoch": 10.13, + "learning_rate": 1.0277981235532541e-05, + "loss": 0.0111, + "step": 11445 + }, + { + "epoch": 10.13, + "learning_rate": 1.0276548708912953e-05, + "loss": 0.0092, + "step": 11446 + }, + { + "epoch": 10.13, + "learning_rate": 1.0275116176613848e-05, + "loss": 0.0114, + "step": 11447 + }, + { + "epoch": 10.13, + "learning_rate": 1.0273683638664653e-05, + "loss": 0.01, + "step": 11448 + }, + { + "epoch": 10.13, + "learning_rate": 1.0272251095094789e-05, + "loss": 0.0099, + "step": 11449 + }, + { + "epoch": 10.13, + "learning_rate": 1.0270818545933672e-05, + "loss": 0.012, + "step": 11450 + }, + { + "epoch": 10.13, + "learning_rate": 1.0269385991210722e-05, + "loss": 0.0109, + "step": 11451 + }, + { + "epoch": 10.13, + "learning_rate": 1.0267953430955365e-05, + "loss": 0.011, + "step": 11452 + }, + { + "epoch": 10.13, + "learning_rate": 1.0266520865197015e-05, + "loss": 0.0087, + "step": 11453 + }, + { + "epoch": 10.13, + "learning_rate": 1.0265088293965095e-05, + "loss": 0.012, + "step": 11454 + }, + { + "epoch": 10.13, + "learning_rate": 1.0263655717289028e-05, + "loss": 0.0107, + "step": 11455 + }, + { + "epoch": 10.14, + "learning_rate": 1.0262223135198235e-05, + "loss": 0.0095, + "step": 11456 + }, + { + "epoch": 10.14, + "learning_rate": 1.0260790547722135e-05, + "loss": 0.0101, + "step": 11457 + }, + { + "epoch": 10.14, + "learning_rate": 1.025935795489015e-05, + "loss": 0.01, + "step": 11458 + }, + { + "epoch": 10.14, + "learning_rate": 1.0257925356731699e-05, + "loss": 0.0083, + "step": 11459 + }, + { + "epoch": 10.14, + "learning_rate": 1.0256492753276208e-05, + "loss": 0.0102, + "step": 11460 + }, + { + "epoch": 10.14, + "learning_rate": 1.0255060144553094e-05, + "loss": 0.0107, + "step": 11461 + }, + { + "epoch": 10.14, + "learning_rate": 1.0253627530591786e-05, + "loss": 0.0107, + "step": 11462 + }, + { + "epoch": 10.14, + "learning_rate": 1.0252194911421698e-05, + "loss": 0.0092, + "step": 11463 + }, + { + "epoch": 10.14, + "learning_rate": 1.0250762287072254e-05, + "loss": 0.0108, + "step": 11464 + }, + { + "epoch": 10.14, + "learning_rate": 1.0249329657572874e-05, + "loss": 0.0141, + "step": 11465 + }, + { + "epoch": 10.14, + "learning_rate": 1.0247897022952986e-05, + "loss": 0.0102, + "step": 11466 + }, + { + "epoch": 10.15, + "learning_rate": 1.024646438324201e-05, + "loss": 0.01, + "step": 11467 + }, + { + "epoch": 10.15, + "learning_rate": 1.0245031738469364e-05, + "loss": 0.0097, + "step": 11468 + }, + { + "epoch": 10.15, + "learning_rate": 1.0243599088664473e-05, + "loss": 0.0121, + "step": 11469 + }, + { + "epoch": 10.15, + "learning_rate": 1.0242166433856764e-05, + "loss": 0.0113, + "step": 11470 + }, + { + "epoch": 10.15, + "learning_rate": 1.0240733774075654e-05, + "loss": 0.0078, + "step": 11471 + }, + { + "epoch": 10.15, + "learning_rate": 1.0239301109350564e-05, + "loss": 0.0092, + "step": 11472 + }, + { + "epoch": 10.15, + "learning_rate": 1.0237868439710923e-05, + "loss": 0.0106, + "step": 11473 + }, + { + "epoch": 10.15, + "learning_rate": 1.0236435765186147e-05, + "loss": 0.0094, + "step": 11474 + }, + { + "epoch": 10.15, + "learning_rate": 1.0235003085805668e-05, + "loss": 0.0103, + "step": 11475 + }, + { + "epoch": 10.15, + "learning_rate": 1.0233570401598903e-05, + "loss": 0.0099, + "step": 11476 + }, + { + "epoch": 10.15, + "learning_rate": 1.0232137712595276e-05, + "loss": 0.0103, + "step": 11477 + }, + { + "epoch": 10.16, + "learning_rate": 1.023070501882421e-05, + "loss": 0.0123, + "step": 11478 + }, + { + "epoch": 10.16, + "learning_rate": 1.0229272320315127e-05, + "loss": 0.0119, + "step": 11479 + }, + { + "epoch": 10.16, + "learning_rate": 1.0227839617097455e-05, + "loss": 0.0108, + "step": 11480 + }, + { + "epoch": 10.16, + "learning_rate": 1.0226406909200613e-05, + "loss": 0.0105, + "step": 11481 + }, + { + "epoch": 10.16, + "learning_rate": 1.0224974196654027e-05, + "loss": 0.0095, + "step": 11482 + }, + { + "epoch": 10.16, + "learning_rate": 1.022354147948712e-05, + "loss": 0.0121, + "step": 11483 + }, + { + "epoch": 10.16, + "learning_rate": 1.022210875772932e-05, + "loss": 0.0119, + "step": 11484 + }, + { + "epoch": 10.16, + "learning_rate": 1.0220676031410045e-05, + "loss": 0.0105, + "step": 11485 + }, + { + "epoch": 10.16, + "learning_rate": 1.021924330055872e-05, + "loss": 0.0102, + "step": 11486 + }, + { + "epoch": 10.16, + "learning_rate": 1.0217810565204772e-05, + "loss": 0.0115, + "step": 11487 + }, + { + "epoch": 10.16, + "learning_rate": 1.0216377825377623e-05, + "loss": 0.0102, + "step": 11488 + }, + { + "epoch": 10.16, + "learning_rate": 1.0214945081106697e-05, + "loss": 0.0105, + "step": 11489 + }, + { + "epoch": 10.17, + "learning_rate": 1.0213512332421422e-05, + "loss": 0.0108, + "step": 11490 + }, + { + "epoch": 10.17, + "learning_rate": 1.021207957935122e-05, + "loss": 0.0107, + "step": 11491 + }, + { + "epoch": 10.17, + "learning_rate": 1.0210646821925514e-05, + "loss": 0.0123, + "step": 11492 + }, + { + "epoch": 10.17, + "learning_rate": 1.020921406017373e-05, + "loss": 0.011, + "step": 11493 + }, + { + "epoch": 10.17, + "learning_rate": 1.0207781294125297e-05, + "loss": 0.0103, + "step": 11494 + }, + { + "epoch": 10.17, + "learning_rate": 1.020634852380963e-05, + "loss": 0.0112, + "step": 11495 + }, + { + "epoch": 10.17, + "learning_rate": 1.0204915749256164e-05, + "loss": 0.0111, + "step": 11496 + }, + { + "epoch": 10.17, + "learning_rate": 1.0203482970494319e-05, + "loss": 0.0101, + "step": 11497 + }, + { + "epoch": 10.17, + "learning_rate": 1.0202050187553523e-05, + "loss": 0.0121, + "step": 11498 + }, + { + "epoch": 10.17, + "learning_rate": 1.0200617400463195e-05, + "loss": 0.0122, + "step": 11499 + }, + { + "epoch": 10.17, + "learning_rate": 1.0199184609252767e-05, + "loss": 0.0133, + "step": 11500 + }, + { + "epoch": 10.18, + "learning_rate": 1.0197751813951666e-05, + "loss": 0.0108, + "step": 11501 + }, + { + "epoch": 10.18, + "learning_rate": 1.019631901458931e-05, + "loss": 0.0113, + "step": 11502 + }, + { + "epoch": 10.18, + "learning_rate": 1.0194886211195127e-05, + "loss": 0.0129, + "step": 11503 + }, + { + "epoch": 10.18, + "learning_rate": 1.0193453403798546e-05, + "loss": 0.0127, + "step": 11504 + }, + { + "epoch": 10.18, + "learning_rate": 1.0192020592428994e-05, + "loss": 0.0089, + "step": 11505 + }, + { + "epoch": 10.18, + "learning_rate": 1.0190587777115886e-05, + "loss": 0.0125, + "step": 11506 + }, + { + "epoch": 10.18, + "learning_rate": 1.0189154957888657e-05, + "loss": 0.0101, + "step": 11507 + }, + { + "epoch": 10.18, + "learning_rate": 1.0187722134776734e-05, + "loss": 0.0105, + "step": 11508 + }, + { + "epoch": 10.18, + "learning_rate": 1.0186289307809541e-05, + "loss": 0.0117, + "step": 11509 + }, + { + "epoch": 10.18, + "learning_rate": 1.01848564770165e-05, + "loss": 0.0109, + "step": 11510 + }, + { + "epoch": 10.18, + "learning_rate": 1.0183423642427042e-05, + "loss": 0.0102, + "step": 11511 + }, + { + "epoch": 10.19, + "learning_rate": 1.018199080407059e-05, + "loss": 0.0114, + "step": 11512 + }, + { + "epoch": 10.19, + "learning_rate": 1.0180557961976573e-05, + "loss": 0.0105, + "step": 11513 + }, + { + "epoch": 10.19, + "learning_rate": 1.017912511617442e-05, + "loss": 0.0134, + "step": 11514 + }, + { + "epoch": 10.19, + "learning_rate": 1.0177692266693554e-05, + "loss": 0.0096, + "step": 11515 + }, + { + "epoch": 10.19, + "learning_rate": 1.0176259413563398e-05, + "loss": 0.0106, + "step": 11516 + }, + { + "epoch": 10.19, + "learning_rate": 1.0174826556813383e-05, + "loss": 0.0094, + "step": 11517 + }, + { + "epoch": 10.19, + "learning_rate": 1.0173393696472938e-05, + "loss": 0.0088, + "step": 11518 + }, + { + "epoch": 10.19, + "learning_rate": 1.0171960832571483e-05, + "loss": 0.0094, + "step": 11519 + }, + { + "epoch": 10.19, + "learning_rate": 1.0170527965138452e-05, + "loss": 0.0106, + "step": 11520 + }, + { + "epoch": 10.19, + "learning_rate": 1.0169095094203268e-05, + "loss": 0.0109, + "step": 11521 + }, + { + "epoch": 10.19, + "learning_rate": 1.0167662219795358e-05, + "loss": 0.0099, + "step": 11522 + }, + { + "epoch": 10.19, + "learning_rate": 1.0166229341944154e-05, + "loss": 0.0112, + "step": 11523 + }, + { + "epoch": 10.2, + "learning_rate": 1.0164796460679076e-05, + "loss": 0.013, + "step": 11524 + }, + { + "epoch": 10.2, + "learning_rate": 1.0163363576029552e-05, + "loss": 0.0093, + "step": 11525 + }, + { + "epoch": 10.2, + "learning_rate": 1.0161930688025018e-05, + "loss": 0.0101, + "step": 11526 + }, + { + "epoch": 10.2, + "learning_rate": 1.0160497796694891e-05, + "loss": 0.0097, + "step": 11527 + }, + { + "epoch": 10.2, + "learning_rate": 1.0159064902068604e-05, + "loss": 0.0126, + "step": 11528 + }, + { + "epoch": 10.2, + "learning_rate": 1.015763200417558e-05, + "loss": 0.0121, + "step": 11529 + }, + { + "epoch": 10.2, + "learning_rate": 1.0156199103045255e-05, + "loss": 0.0104, + "step": 11530 + }, + { + "epoch": 10.2, + "learning_rate": 1.0154766198707047e-05, + "loss": 0.0117, + "step": 11531 + }, + { + "epoch": 10.2, + "learning_rate": 1.0153333291190386e-05, + "loss": 0.0122, + "step": 11532 + }, + { + "epoch": 10.2, + "learning_rate": 1.0151900380524707e-05, + "loss": 0.0104, + "step": 11533 + }, + { + "epoch": 10.2, + "learning_rate": 1.0150467466739432e-05, + "loss": 0.0116, + "step": 11534 + }, + { + "epoch": 10.21, + "learning_rate": 1.0149034549863988e-05, + "loss": 0.0106, + "step": 11535 + }, + { + "epoch": 10.21, + "learning_rate": 1.0147601629927803e-05, + "loss": 0.0113, + "step": 11536 + }, + { + "epoch": 10.21, + "learning_rate": 1.014616870696031e-05, + "loss": 0.01, + "step": 11537 + }, + { + "epoch": 10.21, + "learning_rate": 1.014473578099093e-05, + "loss": 0.0106, + "step": 11538 + }, + { + "epoch": 10.21, + "learning_rate": 1.0143302852049097e-05, + "loss": 0.01, + "step": 11539 + }, + { + "epoch": 10.21, + "learning_rate": 1.0141869920164241e-05, + "loss": 0.0117, + "step": 11540 + }, + { + "epoch": 10.21, + "learning_rate": 1.0140436985365783e-05, + "loss": 0.0095, + "step": 11541 + }, + { + "epoch": 10.21, + "learning_rate": 1.0139004047683152e-05, + "loss": 0.0104, + "step": 11542 + }, + { + "epoch": 10.21, + "learning_rate": 1.0137571107145783e-05, + "loss": 0.0106, + "step": 11543 + }, + { + "epoch": 10.21, + "learning_rate": 1.01361381637831e-05, + "loss": 0.0126, + "step": 11544 + }, + { + "epoch": 10.21, + "learning_rate": 1.0134705217624528e-05, + "loss": 0.0136, + "step": 11545 + }, + { + "epoch": 10.22, + "learning_rate": 1.0133272268699503e-05, + "loss": 0.0094, + "step": 11546 + }, + { + "epoch": 10.22, + "learning_rate": 1.0131839317037453e-05, + "loss": 0.0107, + "step": 11547 + }, + { + "epoch": 10.22, + "learning_rate": 1.01304063626678e-05, + "loss": 0.0098, + "step": 11548 + }, + { + "epoch": 10.22, + "learning_rate": 1.0128973405619977e-05, + "loss": 0.0097, + "step": 11549 + }, + { + "epoch": 10.22, + "learning_rate": 1.0127540445923414e-05, + "loss": 0.0127, + "step": 11550 + }, + { + "epoch": 10.22, + "learning_rate": 1.0126107483607539e-05, + "loss": 0.0115, + "step": 11551 + }, + { + "epoch": 10.22, + "learning_rate": 1.0124674518701778e-05, + "loss": 0.0134, + "step": 11552 + }, + { + "epoch": 10.22, + "learning_rate": 1.0123241551235563e-05, + "loss": 0.0116, + "step": 11553 + }, + { + "epoch": 10.22, + "learning_rate": 1.0121808581238325e-05, + "loss": 0.0124, + "step": 11554 + }, + { + "epoch": 10.22, + "learning_rate": 1.0120375608739488e-05, + "loss": 0.009, + "step": 11555 + }, + { + "epoch": 10.22, + "learning_rate": 1.0118942633768485e-05, + "loss": 0.0134, + "step": 11556 + }, + { + "epoch": 10.23, + "learning_rate": 1.011750965635474e-05, + "loss": 0.0112, + "step": 11557 + }, + { + "epoch": 10.23, + "learning_rate": 1.0116076676527689e-05, + "loss": 0.0107, + "step": 11558 + }, + { + "epoch": 10.23, + "learning_rate": 1.0114643694316756e-05, + "loss": 0.01, + "step": 11559 + }, + { + "epoch": 10.23, + "learning_rate": 1.0113210709751376e-05, + "loss": 0.0125, + "step": 11560 + }, + { + "epoch": 10.23, + "learning_rate": 1.0111777722860974e-05, + "loss": 0.0123, + "step": 11561 + }, + { + "epoch": 10.23, + "learning_rate": 1.011034473367498e-05, + "loss": 0.0115, + "step": 11562 + }, + { + "epoch": 10.23, + "learning_rate": 1.010891174222282e-05, + "loss": 0.0101, + "step": 11563 + }, + { + "epoch": 10.23, + "learning_rate": 1.010747874853393e-05, + "loss": 0.0116, + "step": 11564 + }, + { + "epoch": 10.23, + "learning_rate": 1.0106045752637736e-05, + "loss": 0.0111, + "step": 11565 + }, + { + "epoch": 10.23, + "learning_rate": 1.010461275456367e-05, + "loss": 0.0119, + "step": 11566 + }, + { + "epoch": 10.23, + "learning_rate": 1.0103179754341159e-05, + "loss": 0.0119, + "step": 11567 + }, + { + "epoch": 10.23, + "learning_rate": 1.0101746751999634e-05, + "loss": 0.0107, + "step": 11568 + }, + { + "epoch": 10.24, + "learning_rate": 1.0100313747568526e-05, + "loss": 0.0106, + "step": 11569 + }, + { + "epoch": 10.24, + "learning_rate": 1.0098880741077262e-05, + "loss": 0.0117, + "step": 11570 + }, + { + "epoch": 10.24, + "learning_rate": 1.009744773255527e-05, + "loss": 0.0112, + "step": 11571 + }, + { + "epoch": 10.24, + "learning_rate": 1.0096014722031987e-05, + "loss": 0.0119, + "step": 11572 + }, + { + "epoch": 10.24, + "learning_rate": 1.0094581709536835e-05, + "loss": 0.0105, + "step": 11573 + }, + { + "epoch": 10.24, + "learning_rate": 1.0093148695099251e-05, + "loss": 0.0092, + "step": 11574 + }, + { + "epoch": 10.24, + "learning_rate": 1.0091715678748661e-05, + "loss": 0.0088, + "step": 11575 + }, + { + "epoch": 10.24, + "learning_rate": 1.0090282660514496e-05, + "loss": 0.0105, + "step": 11576 + }, + { + "epoch": 10.24, + "learning_rate": 1.0088849640426183e-05, + "loss": 0.0107, + "step": 11577 + }, + { + "epoch": 10.24, + "learning_rate": 1.008741661851316e-05, + "loss": 0.0104, + "step": 11578 + }, + { + "epoch": 10.24, + "learning_rate": 1.0085983594804847e-05, + "loss": 0.0108, + "step": 11579 + }, + { + "epoch": 10.25, + "learning_rate": 1.008455056933068e-05, + "loss": 0.0098, + "step": 11580 + }, + { + "epoch": 10.25, + "learning_rate": 1.0083117542120092e-05, + "loss": 0.0112, + "step": 11581 + }, + { + "epoch": 10.25, + "learning_rate": 1.0081684513202507e-05, + "loss": 0.0108, + "step": 11582 + }, + { + "epoch": 10.25, + "learning_rate": 1.0080251482607357e-05, + "loss": 0.0099, + "step": 11583 + }, + { + "epoch": 10.25, + "learning_rate": 1.0078818450364072e-05, + "loss": 0.0116, + "step": 11584 + }, + { + "epoch": 10.25, + "learning_rate": 1.0077385416502087e-05, + "loss": 0.0119, + "step": 11585 + }, + { + "epoch": 10.25, + "learning_rate": 1.007595238105083e-05, + "loss": 0.0107, + "step": 11586 + }, + { + "epoch": 10.25, + "learning_rate": 1.0074519344039726e-05, + "loss": 0.0107, + "step": 11587 + }, + { + "epoch": 10.25, + "learning_rate": 1.0073086305498211e-05, + "loss": 0.0102, + "step": 11588 + }, + { + "epoch": 10.25, + "learning_rate": 1.0071653265455718e-05, + "loss": 0.009, + "step": 11589 + }, + { + "epoch": 10.25, + "learning_rate": 1.0070220223941671e-05, + "loss": 0.0102, + "step": 11590 + }, + { + "epoch": 10.26, + "learning_rate": 1.00687871809855e-05, + "loss": 0.0083, + "step": 11591 + }, + { + "epoch": 10.26, + "learning_rate": 1.0067354136616645e-05, + "loss": 0.0106, + "step": 11592 + }, + { + "epoch": 10.26, + "learning_rate": 1.0065921090864528e-05, + "loss": 0.011, + "step": 11593 + }, + { + "epoch": 10.26, + "learning_rate": 1.006448804375858e-05, + "loss": 0.0121, + "step": 11594 + }, + { + "epoch": 10.26, + "learning_rate": 1.0063054995328236e-05, + "loss": 0.0127, + "step": 11595 + }, + { + "epoch": 10.26, + "learning_rate": 1.0061621945602926e-05, + "loss": 0.0096, + "step": 11596 + }, + { + "epoch": 10.26, + "learning_rate": 1.0060188894612073e-05, + "loss": 0.0102, + "step": 11597 + }, + { + "epoch": 10.26, + "learning_rate": 1.0058755842385118e-05, + "loss": 0.0124, + "step": 11598 + }, + { + "epoch": 10.26, + "learning_rate": 1.005732278895149e-05, + "loss": 0.0126, + "step": 11599 + }, + { + "epoch": 10.26, + "learning_rate": 1.0055889734340614e-05, + "loss": 0.0116, + "step": 11600 + }, + { + "epoch": 10.26, + "learning_rate": 1.0054456678581926e-05, + "loss": 0.0096, + "step": 11601 + }, + { + "epoch": 10.26, + "learning_rate": 1.0053023621704854e-05, + "loss": 0.0109, + "step": 11602 + }, + { + "epoch": 10.27, + "learning_rate": 1.005159056373883e-05, + "loss": 0.0113, + "step": 11603 + }, + { + "epoch": 10.27, + "learning_rate": 1.0050157504713282e-05, + "loss": 0.0101, + "step": 11604 + }, + { + "epoch": 10.27, + "learning_rate": 1.0048724444657647e-05, + "loss": 0.0103, + "step": 11605 + }, + { + "epoch": 10.27, + "learning_rate": 1.0047291383601354e-05, + "loss": 0.0107, + "step": 11606 + }, + { + "epoch": 10.27, + "learning_rate": 1.0045858321573829e-05, + "loss": 0.0103, + "step": 11607 + }, + { + "epoch": 10.27, + "learning_rate": 1.0044425258604509e-05, + "loss": 0.0107, + "step": 11608 + }, + { + "epoch": 10.27, + "learning_rate": 1.004299219472282e-05, + "loss": 0.0109, + "step": 11609 + }, + { + "epoch": 10.27, + "learning_rate": 1.0041559129958197e-05, + "loss": 0.0112, + "step": 11610 + }, + { + "epoch": 10.27, + "learning_rate": 1.0040126064340067e-05, + "loss": 0.0124, + "step": 11611 + }, + { + "epoch": 10.27, + "learning_rate": 1.0038692997897868e-05, + "loss": 0.0104, + "step": 11612 + }, + { + "epoch": 10.27, + "learning_rate": 1.0037259930661026e-05, + "loss": 0.0116, + "step": 11613 + }, + { + "epoch": 10.28, + "learning_rate": 1.0035826862658968e-05, + "loss": 0.0113, + "step": 11614 + }, + { + "epoch": 10.28, + "learning_rate": 1.0034393793921133e-05, + "loss": 0.0104, + "step": 11615 + }, + { + "epoch": 10.28, + "learning_rate": 1.0032960724476947e-05, + "loss": 0.013, + "step": 11616 + }, + { + "epoch": 10.28, + "learning_rate": 1.0031527654355843e-05, + "loss": 0.0103, + "step": 11617 + }, + { + "epoch": 10.28, + "learning_rate": 1.0030094583587255e-05, + "loss": 0.0098, + "step": 11618 + }, + { + "epoch": 10.28, + "learning_rate": 1.0028661512200607e-05, + "loss": 0.0099, + "step": 11619 + }, + { + "epoch": 10.28, + "learning_rate": 1.0027228440225341e-05, + "loss": 0.0114, + "step": 11620 + }, + { + "epoch": 10.28, + "learning_rate": 1.0025795367690876e-05, + "loss": 0.0115, + "step": 11621 + }, + { + "epoch": 10.28, + "learning_rate": 1.0024362294626648e-05, + "loss": 0.0108, + "step": 11622 + }, + { + "epoch": 10.28, + "learning_rate": 1.002292922106209e-05, + "loss": 0.0105, + "step": 11623 + }, + { + "epoch": 10.28, + "learning_rate": 1.0021496147026632e-05, + "loss": 0.0109, + "step": 11624 + }, + { + "epoch": 10.29, + "learning_rate": 1.0020063072549706e-05, + "loss": 0.011, + "step": 11625 + }, + { + "epoch": 10.29, + "learning_rate": 1.001862999766074e-05, + "loss": 0.0115, + "step": 11626 + }, + { + "epoch": 10.29, + "learning_rate": 1.0017196922389171e-05, + "loss": 0.0111, + "step": 11627 + }, + { + "epoch": 10.29, + "learning_rate": 1.0015763846764426e-05, + "loss": 0.0107, + "step": 11628 + }, + { + "epoch": 10.29, + "learning_rate": 1.0014330770815937e-05, + "loss": 0.0099, + "step": 11629 + }, + { + "epoch": 10.29, + "learning_rate": 1.0012897694573134e-05, + "loss": 0.0124, + "step": 11630 + }, + { + "epoch": 10.29, + "learning_rate": 1.001146461806545e-05, + "loss": 0.0106, + "step": 11631 + }, + { + "epoch": 10.29, + "learning_rate": 1.0010031541322316e-05, + "loss": 0.0108, + "step": 11632 + }, + { + "epoch": 10.29, + "learning_rate": 1.0008598464373163e-05, + "loss": 0.0117, + "step": 11633 + }, + { + "epoch": 10.29, + "learning_rate": 1.0007165387247425e-05, + "loss": 0.0096, + "step": 11634 + }, + { + "epoch": 10.29, + "learning_rate": 1.0005732309974527e-05, + "loss": 0.0094, + "step": 11635 + }, + { + "epoch": 10.29, + "learning_rate": 1.0004299232583903e-05, + "loss": 0.0113, + "step": 11636 + }, + { + "epoch": 10.3, + "learning_rate": 1.0002866155104986e-05, + "loss": 0.0103, + "step": 11637 + }, + { + "epoch": 10.3, + "learning_rate": 1.000143307756721e-05, + "loss": 0.0101, + "step": 11638 + }, + { + "epoch": 10.3, + "learning_rate": 1e-05, + "loss": 0.0128, + "step": 11639 + }, + { + "epoch": 10.3, + "learning_rate": 9.99856692243279e-06, + "loss": 0.0087, + "step": 11640 + }, + { + "epoch": 10.3, + "learning_rate": 9.997133844895016e-06, + "loss": 0.0135, + "step": 11641 + }, + { + "epoch": 10.3, + "learning_rate": 9.995700767416097e-06, + "loss": 0.0126, + "step": 11642 + }, + { + "epoch": 10.3, + "learning_rate": 9.994267690025478e-06, + "loss": 0.0122, + "step": 11643 + }, + { + "epoch": 10.3, + "learning_rate": 9.992834612752577e-06, + "loss": 0.0106, + "step": 11644 + }, + { + "epoch": 10.3, + "learning_rate": 9.991401535626842e-06, + "loss": 0.0111, + "step": 11645 + }, + { + "epoch": 10.3, + "learning_rate": 9.989968458677687e-06, + "loss": 0.0107, + "step": 11646 + }, + { + "epoch": 10.3, + "learning_rate": 9.98853538193455e-06, + "loss": 0.0108, + "step": 11647 + }, + { + "epoch": 10.31, + "learning_rate": 9.987102305426869e-06, + "loss": 0.0109, + "step": 11648 + }, + { + "epoch": 10.31, + "learning_rate": 9.985669229184066e-06, + "loss": 0.0109, + "step": 11649 + }, + { + "epoch": 10.31, + "learning_rate": 9.984236153235579e-06, + "loss": 0.0103, + "step": 11650 + }, + { + "epoch": 10.31, + "learning_rate": 9.98280307761083e-06, + "loss": 0.0134, + "step": 11651 + }, + { + "epoch": 10.31, + "learning_rate": 9.981370002339263e-06, + "loss": 0.0114, + "step": 11652 + }, + { + "epoch": 10.31, + "learning_rate": 9.979936927450299e-06, + "loss": 0.0103, + "step": 11653 + }, + { + "epoch": 10.31, + "learning_rate": 9.978503852973368e-06, + "loss": 0.012, + "step": 11654 + }, + { + "epoch": 10.31, + "learning_rate": 9.977070778937913e-06, + "loss": 0.0101, + "step": 11655 + }, + { + "epoch": 10.31, + "learning_rate": 9.975637705373354e-06, + "loss": 0.01, + "step": 11656 + }, + { + "epoch": 10.31, + "learning_rate": 9.97420463230913e-06, + "loss": 0.0124, + "step": 11657 + }, + { + "epoch": 10.31, + "learning_rate": 9.972771559774664e-06, + "loss": 0.0113, + "step": 11658 + }, + { + "epoch": 10.32, + "learning_rate": 9.971338487799393e-06, + "loss": 0.0111, + "step": 11659 + }, + { + "epoch": 10.32, + "learning_rate": 9.969905416412748e-06, + "loss": 0.0103, + "step": 11660 + }, + { + "epoch": 10.32, + "learning_rate": 9.968472345644155e-06, + "loss": 0.0108, + "step": 11661 + }, + { + "epoch": 10.32, + "learning_rate": 9.967039275523055e-06, + "loss": 0.0112, + "step": 11662 + }, + { + "epoch": 10.32, + "learning_rate": 9.965606206078869e-06, + "loss": 0.0123, + "step": 11663 + }, + { + "epoch": 10.32, + "learning_rate": 9.964173137341035e-06, + "loss": 0.0124, + "step": 11664 + }, + { + "epoch": 10.32, + "learning_rate": 9.962740069338979e-06, + "loss": 0.0133, + "step": 11665 + }, + { + "epoch": 10.32, + "learning_rate": 9.961307002102134e-06, + "loss": 0.0116, + "step": 11666 + }, + { + "epoch": 10.32, + "learning_rate": 9.959873935659935e-06, + "loss": 0.0106, + "step": 11667 + }, + { + "epoch": 10.32, + "learning_rate": 9.958440870041805e-06, + "loss": 0.0114, + "step": 11668 + }, + { + "epoch": 10.32, + "learning_rate": 9.957007805277183e-06, + "loss": 0.013, + "step": 11669 + }, + { + "epoch": 10.32, + "learning_rate": 9.955574741395495e-06, + "loss": 0.0113, + "step": 11670 + }, + { + "epoch": 10.33, + "learning_rate": 9.954141678426176e-06, + "loss": 0.0116, + "step": 11671 + }, + { + "epoch": 10.33, + "learning_rate": 9.95270861639865e-06, + "loss": 0.0087, + "step": 11672 + }, + { + "epoch": 10.33, + "learning_rate": 9.951275555342353e-06, + "loss": 0.0105, + "step": 11673 + }, + { + "epoch": 10.33, + "learning_rate": 9.94984249528672e-06, + "loss": 0.0093, + "step": 11674 + }, + { + "epoch": 10.33, + "learning_rate": 9.948409436261173e-06, + "loss": 0.0109, + "step": 11675 + }, + { + "epoch": 10.33, + "learning_rate": 9.94697637829515e-06, + "loss": 0.0113, + "step": 11676 + }, + { + "epoch": 10.33, + "learning_rate": 9.945543321418077e-06, + "loss": 0.0095, + "step": 11677 + }, + { + "epoch": 10.33, + "learning_rate": 9.944110265659391e-06, + "loss": 0.0111, + "step": 11678 + }, + { + "epoch": 10.33, + "learning_rate": 9.942677211048514e-06, + "loss": 0.0095, + "step": 11679 + }, + { + "epoch": 10.33, + "learning_rate": 9.941244157614882e-06, + "loss": 0.0113, + "step": 11680 + }, + { + "epoch": 10.33, + "learning_rate": 9.939811105387928e-06, + "loss": 0.013, + "step": 11681 + }, + { + "epoch": 10.34, + "learning_rate": 9.938378054397077e-06, + "loss": 0.0122, + "step": 11682 + }, + { + "epoch": 10.34, + "learning_rate": 9.936945004671767e-06, + "loss": 0.0113, + "step": 11683 + }, + { + "epoch": 10.34, + "learning_rate": 9.935511956241422e-06, + "loss": 0.0129, + "step": 11684 + }, + { + "epoch": 10.34, + "learning_rate": 9.934078909135474e-06, + "loss": 0.0103, + "step": 11685 + }, + { + "epoch": 10.34, + "learning_rate": 9.932645863383358e-06, + "loss": 0.0142, + "step": 11686 + }, + { + "epoch": 10.34, + "learning_rate": 9.9312128190145e-06, + "loss": 0.0143, + "step": 11687 + }, + { + "epoch": 10.34, + "learning_rate": 9.929779776058334e-06, + "loss": 0.0106, + "step": 11688 + }, + { + "epoch": 10.34, + "learning_rate": 9.928346734544284e-06, + "loss": 0.0109, + "step": 11689 + }, + { + "epoch": 10.34, + "learning_rate": 9.92691369450179e-06, + "loss": 0.0125, + "step": 11690 + }, + { + "epoch": 10.34, + "learning_rate": 9.925480655960275e-06, + "loss": 0.0118, + "step": 11691 + }, + { + "epoch": 10.34, + "learning_rate": 9.924047618949172e-06, + "loss": 0.0115, + "step": 11692 + }, + { + "epoch": 10.35, + "learning_rate": 9.922614583497914e-06, + "loss": 0.0107, + "step": 11693 + }, + { + "epoch": 10.35, + "learning_rate": 9.921181549635928e-06, + "loss": 0.0119, + "step": 11694 + }, + { + "epoch": 10.35, + "learning_rate": 9.919748517392646e-06, + "loss": 0.0096, + "step": 11695 + }, + { + "epoch": 10.35, + "learning_rate": 9.918315486797496e-06, + "loss": 0.0104, + "step": 11696 + }, + { + "epoch": 10.35, + "learning_rate": 9.916882457879913e-06, + "loss": 0.0129, + "step": 11697 + }, + { + "epoch": 10.35, + "learning_rate": 9.915449430669322e-06, + "loss": 0.011, + "step": 11698 + }, + { + "epoch": 10.35, + "learning_rate": 9.914016405195153e-06, + "loss": 0.0098, + "step": 11699 + }, + { + "epoch": 10.35, + "learning_rate": 9.912583381486845e-06, + "loss": 0.0114, + "step": 11700 + }, + { + "epoch": 10.35, + "learning_rate": 9.911150359573818e-06, + "loss": 0.0116, + "step": 11701 + }, + { + "epoch": 10.35, + "learning_rate": 9.909717339485509e-06, + "loss": 0.0125, + "step": 11702 + }, + { + "epoch": 10.35, + "learning_rate": 9.90828432125134e-06, + "loss": 0.0103, + "step": 11703 + }, + { + "epoch": 10.36, + "learning_rate": 9.906851304900752e-06, + "loss": 0.0124, + "step": 11704 + }, + { + "epoch": 10.36, + "learning_rate": 9.905418290463167e-06, + "loss": 0.0129, + "step": 11705 + }, + { + "epoch": 10.36, + "learning_rate": 9.903985277968015e-06, + "loss": 0.011, + "step": 11706 + }, + { + "epoch": 10.36, + "learning_rate": 9.902552267444732e-06, + "loss": 0.0119, + "step": 11707 + }, + { + "epoch": 10.36, + "learning_rate": 9.901119258922742e-06, + "loss": 0.0101, + "step": 11708 + }, + { + "epoch": 10.36, + "learning_rate": 9.89968625243148e-06, + "loss": 0.0113, + "step": 11709 + }, + { + "epoch": 10.36, + "learning_rate": 9.898253248000367e-06, + "loss": 0.0107, + "step": 11710 + }, + { + "epoch": 10.36, + "learning_rate": 9.896820245658841e-06, + "loss": 0.0111, + "step": 11711 + }, + { + "epoch": 10.36, + "learning_rate": 9.895387245436332e-06, + "loss": 0.0097, + "step": 11712 + }, + { + "epoch": 10.36, + "learning_rate": 9.893954247362263e-06, + "loss": 0.0112, + "step": 11713 + }, + { + "epoch": 10.36, + "learning_rate": 9.892521251466072e-06, + "loss": 0.0115, + "step": 11714 + }, + { + "epoch": 10.36, + "learning_rate": 9.89108825777718e-06, + "loss": 0.0097, + "step": 11715 + }, + { + "epoch": 10.37, + "learning_rate": 9.889655266325027e-06, + "loss": 0.0122, + "step": 11716 + }, + { + "epoch": 10.37, + "learning_rate": 9.88822227713903e-06, + "loss": 0.0106, + "step": 11717 + }, + { + "epoch": 10.37, + "learning_rate": 9.886789290248624e-06, + "loss": 0.012, + "step": 11718 + }, + { + "epoch": 10.37, + "learning_rate": 9.885356305683245e-06, + "loss": 0.0088, + "step": 11719 + }, + { + "epoch": 10.37, + "learning_rate": 9.883923323472311e-06, + "loss": 0.0111, + "step": 11720 + }, + { + "epoch": 10.37, + "learning_rate": 9.882490343645261e-06, + "loss": 0.0114, + "step": 11721 + }, + { + "epoch": 10.37, + "learning_rate": 9.881057366231519e-06, + "loss": 0.0126, + "step": 11722 + }, + { + "epoch": 10.37, + "learning_rate": 9.879624391260515e-06, + "loss": 0.0139, + "step": 11723 + }, + { + "epoch": 10.37, + "learning_rate": 9.878191418761678e-06, + "loss": 0.0102, + "step": 11724 + }, + { + "epoch": 10.37, + "learning_rate": 9.876758448764437e-06, + "loss": 0.0126, + "step": 11725 + }, + { + "epoch": 10.37, + "learning_rate": 9.875325481298224e-06, + "loss": 0.0119, + "step": 11726 + }, + { + "epoch": 10.38, + "learning_rate": 9.873892516392463e-06, + "loss": 0.0113, + "step": 11727 + }, + { + "epoch": 10.38, + "learning_rate": 9.872459554076589e-06, + "loss": 0.0118, + "step": 11728 + }, + { + "epoch": 10.38, + "learning_rate": 9.871026594380024e-06, + "loss": 0.0104, + "step": 11729 + }, + { + "epoch": 10.38, + "learning_rate": 9.869593637332205e-06, + "loss": 0.0108, + "step": 11730 + }, + { + "epoch": 10.38, + "learning_rate": 9.86816068296255e-06, + "loss": 0.0097, + "step": 11731 + }, + { + "epoch": 10.38, + "learning_rate": 9.866727731300497e-06, + "loss": 0.0108, + "step": 11732 + }, + { + "epoch": 10.38, + "learning_rate": 9.865294782375474e-06, + "loss": 0.0121, + "step": 11733 + }, + { + "epoch": 10.38, + "learning_rate": 9.863861836216903e-06, + "loss": 0.0112, + "step": 11734 + }, + { + "epoch": 10.38, + "learning_rate": 9.862428892854222e-06, + "loss": 0.0127, + "step": 11735 + }, + { + "epoch": 10.38, + "learning_rate": 9.860995952316851e-06, + "loss": 0.0092, + "step": 11736 + }, + { + "epoch": 10.38, + "learning_rate": 9.859563014634219e-06, + "loss": 0.0098, + "step": 11737 + }, + { + "epoch": 10.39, + "learning_rate": 9.858130079835762e-06, + "loss": 0.0131, + "step": 11738 + }, + { + "epoch": 10.39, + "learning_rate": 9.856697147950903e-06, + "loss": 0.01, + "step": 11739 + }, + { + "epoch": 10.39, + "learning_rate": 9.855264219009071e-06, + "loss": 0.0126, + "step": 11740 + }, + { + "epoch": 10.39, + "learning_rate": 9.853831293039691e-06, + "loss": 0.0133, + "step": 11741 + }, + { + "epoch": 10.39, + "learning_rate": 9.8523983700722e-06, + "loss": 0.0097, + "step": 11742 + }, + { + "epoch": 10.39, + "learning_rate": 9.850965450136016e-06, + "loss": 0.0109, + "step": 11743 + }, + { + "epoch": 10.39, + "learning_rate": 9.84953253326057e-06, + "loss": 0.0127, + "step": 11744 + }, + { + "epoch": 10.39, + "learning_rate": 9.848099619475295e-06, + "loss": 0.0114, + "step": 11745 + }, + { + "epoch": 10.39, + "learning_rate": 9.846666708809615e-06, + "loss": 0.0115, + "step": 11746 + }, + { + "epoch": 10.39, + "learning_rate": 9.845233801292959e-06, + "loss": 0.0127, + "step": 11747 + }, + { + "epoch": 10.39, + "learning_rate": 9.843800896954749e-06, + "loss": 0.012, + "step": 11748 + }, + { + "epoch": 10.39, + "learning_rate": 9.842367995824424e-06, + "loss": 0.0098, + "step": 11749 + }, + { + "epoch": 10.4, + "learning_rate": 9.840935097931401e-06, + "loss": 0.0126, + "step": 11750 + }, + { + "epoch": 10.4, + "learning_rate": 9.83950220330511e-06, + "loss": 0.011, + "step": 11751 + }, + { + "epoch": 10.4, + "learning_rate": 9.838069311974986e-06, + "loss": 0.0103, + "step": 11752 + }, + { + "epoch": 10.4, + "learning_rate": 9.836636423970448e-06, + "loss": 0.0098, + "step": 11753 + }, + { + "epoch": 10.4, + "learning_rate": 9.83520353932093e-06, + "loss": 0.01, + "step": 11754 + }, + { + "epoch": 10.4, + "learning_rate": 9.83377065805585e-06, + "loss": 0.0106, + "step": 11755 + }, + { + "epoch": 10.4, + "learning_rate": 9.832337780204643e-06, + "loss": 0.0126, + "step": 11756 + }, + { + "epoch": 10.4, + "learning_rate": 9.830904905796734e-06, + "loss": 0.0128, + "step": 11757 + }, + { + "epoch": 10.4, + "learning_rate": 9.829472034861548e-06, + "loss": 0.011, + "step": 11758 + }, + { + "epoch": 10.4, + "learning_rate": 9.82803916742852e-06, + "loss": 0.0106, + "step": 11759 + }, + { + "epoch": 10.4, + "learning_rate": 9.826606303527065e-06, + "loss": 0.0108, + "step": 11760 + }, + { + "epoch": 10.41, + "learning_rate": 9.825173443186622e-06, + "loss": 0.0113, + "step": 11761 + }, + { + "epoch": 10.41, + "learning_rate": 9.823740586436605e-06, + "loss": 0.0122, + "step": 11762 + }, + { + "epoch": 10.41, + "learning_rate": 9.82230773330645e-06, + "loss": 0.0113, + "step": 11763 + }, + { + "epoch": 10.41, + "learning_rate": 9.820874883825583e-06, + "loss": 0.0108, + "step": 11764 + }, + { + "epoch": 10.41, + "learning_rate": 9.819442038023427e-06, + "loss": 0.0101, + "step": 11765 + }, + { + "epoch": 10.41, + "learning_rate": 9.818009195929411e-06, + "loss": 0.0108, + "step": 11766 + }, + { + "epoch": 10.41, + "learning_rate": 9.816576357572963e-06, + "loss": 0.0126, + "step": 11767 + }, + { + "epoch": 10.41, + "learning_rate": 9.815143522983506e-06, + "loss": 0.0106, + "step": 11768 + }, + { + "epoch": 10.41, + "learning_rate": 9.813710692190464e-06, + "loss": 0.0112, + "step": 11769 + }, + { + "epoch": 10.41, + "learning_rate": 9.812277865223269e-06, + "loss": 0.0101, + "step": 11770 + }, + { + "epoch": 10.41, + "learning_rate": 9.810845042111345e-06, + "loss": 0.0116, + "step": 11771 + }, + { + "epoch": 10.42, + "learning_rate": 9.809412222884115e-06, + "loss": 0.0113, + "step": 11772 + }, + { + "epoch": 10.42, + "learning_rate": 9.807979407571013e-06, + "loss": 0.0112, + "step": 11773 + }, + { + "epoch": 10.42, + "learning_rate": 9.806546596201456e-06, + "loss": 0.0103, + "step": 11774 + }, + { + "epoch": 10.42, + "learning_rate": 9.805113788804876e-06, + "loss": 0.0115, + "step": 11775 + }, + { + "epoch": 10.42, + "learning_rate": 9.803680985410693e-06, + "loss": 0.0122, + "step": 11776 + }, + { + "epoch": 10.42, + "learning_rate": 9.802248186048336e-06, + "loss": 0.0103, + "step": 11777 + }, + { + "epoch": 10.42, + "learning_rate": 9.800815390747234e-06, + "loss": 0.0132, + "step": 11778 + }, + { + "epoch": 10.42, + "learning_rate": 9.799382599536804e-06, + "loss": 0.0118, + "step": 11779 + }, + { + "epoch": 10.42, + "learning_rate": 9.797949812446482e-06, + "loss": 0.0122, + "step": 11780 + }, + { + "epoch": 10.42, + "learning_rate": 9.796517029505683e-06, + "loss": 0.0097, + "step": 11781 + }, + { + "epoch": 10.42, + "learning_rate": 9.79508425074384e-06, + "loss": 0.01, + "step": 11782 + }, + { + "epoch": 10.42, + "learning_rate": 9.793651476190371e-06, + "loss": 0.0112, + "step": 11783 + }, + { + "epoch": 10.43, + "learning_rate": 9.792218705874707e-06, + "loss": 0.0101, + "step": 11784 + }, + { + "epoch": 10.43, + "learning_rate": 9.790785939826274e-06, + "loss": 0.0125, + "step": 11785 + }, + { + "epoch": 10.43, + "learning_rate": 9.789353178074487e-06, + "loss": 0.0104, + "step": 11786 + }, + { + "epoch": 10.43, + "learning_rate": 9.787920420648784e-06, + "loss": 0.0102, + "step": 11787 + }, + { + "epoch": 10.43, + "learning_rate": 9.786487667578582e-06, + "loss": 0.0113, + "step": 11788 + }, + { + "epoch": 10.43, + "learning_rate": 9.785054918893303e-06, + "loss": 0.0121, + "step": 11789 + }, + { + "epoch": 10.43, + "learning_rate": 9.78362217462238e-06, + "loss": 0.0135, + "step": 11790 + }, + { + "epoch": 10.43, + "learning_rate": 9.78218943479523e-06, + "loss": 0.0128, + "step": 11791 + }, + { + "epoch": 10.43, + "learning_rate": 9.780756699441286e-06, + "loss": 0.0128, + "step": 11792 + }, + { + "epoch": 10.43, + "learning_rate": 9.779323968589957e-06, + "loss": 0.012, + "step": 11793 + }, + { + "epoch": 10.43, + "learning_rate": 9.777891242270685e-06, + "loss": 0.0098, + "step": 11794 + }, + { + "epoch": 10.44, + "learning_rate": 9.776458520512882e-06, + "loss": 0.0115, + "step": 11795 + }, + { + "epoch": 10.44, + "learning_rate": 9.775025803345973e-06, + "loss": 0.012, + "step": 11796 + }, + { + "epoch": 10.44, + "learning_rate": 9.77359309079939e-06, + "loss": 0.0126, + "step": 11797 + }, + { + "epoch": 10.44, + "learning_rate": 9.77216038290255e-06, + "loss": 0.0117, + "step": 11798 + }, + { + "epoch": 10.44, + "learning_rate": 9.770727679684878e-06, + "loss": 0.011, + "step": 11799 + }, + { + "epoch": 10.44, + "learning_rate": 9.769294981175795e-06, + "loss": 0.0113, + "step": 11800 + }, + { + "epoch": 10.44, + "learning_rate": 9.76786228740473e-06, + "loss": 0.0108, + "step": 11801 + }, + { + "epoch": 10.44, + "learning_rate": 9.7664295984011e-06, + "loss": 0.0136, + "step": 11802 + }, + { + "epoch": 10.44, + "learning_rate": 9.764996914194333e-06, + "loss": 0.0108, + "step": 11803 + }, + { + "epoch": 10.44, + "learning_rate": 9.763564234813854e-06, + "loss": 0.0139, + "step": 11804 + }, + { + "epoch": 10.44, + "learning_rate": 9.762131560289082e-06, + "loss": 0.0128, + "step": 11805 + }, + { + "epoch": 10.45, + "learning_rate": 9.760698890649441e-06, + "loss": 0.0121, + "step": 11806 + }, + { + "epoch": 10.45, + "learning_rate": 9.759266225924351e-06, + "loss": 0.012, + "step": 11807 + }, + { + "epoch": 10.45, + "learning_rate": 9.757833566143241e-06, + "loss": 0.0126, + "step": 11808 + }, + { + "epoch": 10.45, + "learning_rate": 9.75640091133553e-06, + "loss": 0.0103, + "step": 11809 + }, + { + "epoch": 10.45, + "learning_rate": 9.754968261530638e-06, + "loss": 0.0142, + "step": 11810 + }, + { + "epoch": 10.45, + "learning_rate": 9.753535616757994e-06, + "loss": 0.0099, + "step": 11811 + }, + { + "epoch": 10.45, + "learning_rate": 9.752102977047016e-06, + "loss": 0.0118, + "step": 11812 + }, + { + "epoch": 10.45, + "learning_rate": 9.750670342427129e-06, + "loss": 0.0127, + "step": 11813 + }, + { + "epoch": 10.45, + "learning_rate": 9.74923771292775e-06, + "loss": 0.0107, + "step": 11814 + }, + { + "epoch": 10.45, + "learning_rate": 9.747805088578307e-06, + "loss": 0.0095, + "step": 11815 + }, + { + "epoch": 10.45, + "learning_rate": 9.746372469408218e-06, + "loss": 0.0112, + "step": 11816 + }, + { + "epoch": 10.46, + "learning_rate": 9.744939855446904e-06, + "loss": 0.0106, + "step": 11817 + }, + { + "epoch": 10.46, + "learning_rate": 9.743507246723794e-06, + "loss": 0.0139, + "step": 11818 + }, + { + "epoch": 10.46, + "learning_rate": 9.742074643268303e-06, + "loss": 0.0111, + "step": 11819 + }, + { + "epoch": 10.46, + "learning_rate": 9.740642045109855e-06, + "loss": 0.0105, + "step": 11820 + }, + { + "epoch": 10.46, + "learning_rate": 9.739209452277868e-06, + "loss": 0.0129, + "step": 11821 + }, + { + "epoch": 10.46, + "learning_rate": 9.737776864801767e-06, + "loss": 0.012, + "step": 11822 + }, + { + "epoch": 10.46, + "learning_rate": 9.736344282710974e-06, + "loss": 0.0114, + "step": 11823 + }, + { + "epoch": 10.46, + "learning_rate": 9.734911706034905e-06, + "loss": 0.0098, + "step": 11824 + }, + { + "epoch": 10.46, + "learning_rate": 9.733479134802988e-06, + "loss": 0.0109, + "step": 11825 + }, + { + "epoch": 10.46, + "learning_rate": 9.73204656904464e-06, + "loss": 0.0126, + "step": 11826 + }, + { + "epoch": 10.46, + "learning_rate": 9.730614008789283e-06, + "loss": 0.0099, + "step": 11827 + }, + { + "epoch": 10.46, + "learning_rate": 9.729181454066331e-06, + "loss": 0.0108, + "step": 11828 + }, + { + "epoch": 10.47, + "learning_rate": 9.727748904905213e-06, + "loss": 0.0125, + "step": 11829 + }, + { + "epoch": 10.47, + "learning_rate": 9.726316361335349e-06, + "loss": 0.0105, + "step": 11830 + }, + { + "epoch": 10.47, + "learning_rate": 9.724883823386151e-06, + "loss": 0.0121, + "step": 11831 + }, + { + "epoch": 10.47, + "learning_rate": 9.723451291087052e-06, + "loss": 0.0127, + "step": 11832 + }, + { + "epoch": 10.47, + "learning_rate": 9.72201876446746e-06, + "loss": 0.0124, + "step": 11833 + }, + { + "epoch": 10.47, + "learning_rate": 9.720586243556805e-06, + "loss": 0.0108, + "step": 11834 + }, + { + "epoch": 10.47, + "learning_rate": 9.719153728384497e-06, + "loss": 0.0125, + "step": 11835 + }, + { + "epoch": 10.47, + "learning_rate": 9.717721218979963e-06, + "loss": 0.0113, + "step": 11836 + }, + { + "epoch": 10.47, + "learning_rate": 9.716288715372622e-06, + "loss": 0.0114, + "step": 11837 + }, + { + "epoch": 10.47, + "learning_rate": 9.714856217591887e-06, + "loss": 0.0115, + "step": 11838 + }, + { + "epoch": 10.47, + "learning_rate": 9.713423725667187e-06, + "loss": 0.0139, + "step": 11839 + }, + { + "epoch": 10.48, + "learning_rate": 9.711991239627933e-06, + "loss": 0.0122, + "step": 11840 + }, + { + "epoch": 10.48, + "learning_rate": 9.710558759503552e-06, + "loss": 0.0126, + "step": 11841 + }, + { + "epoch": 10.48, + "learning_rate": 9.709126285323453e-06, + "loss": 0.0116, + "step": 11842 + }, + { + "epoch": 10.48, + "learning_rate": 9.707693817117063e-06, + "loss": 0.0114, + "step": 11843 + }, + { + "epoch": 10.48, + "learning_rate": 9.7062613549138e-06, + "loss": 0.0137, + "step": 11844 + }, + { + "epoch": 10.48, + "learning_rate": 9.704828898743076e-06, + "loss": 0.0112, + "step": 11845 + }, + { + "epoch": 10.48, + "learning_rate": 9.70339644863432e-06, + "loss": 0.0118, + "step": 11846 + }, + { + "epoch": 10.48, + "learning_rate": 9.70196400461694e-06, + "loss": 0.0111, + "step": 11847 + }, + { + "epoch": 10.48, + "learning_rate": 9.70053156672036e-06, + "loss": 0.0116, + "step": 11848 + }, + { + "epoch": 10.48, + "learning_rate": 9.699099134974e-06, + "loss": 0.0127, + "step": 11849 + }, + { + "epoch": 10.48, + "learning_rate": 9.697666709407272e-06, + "loss": 0.0116, + "step": 11850 + }, + { + "epoch": 10.49, + "learning_rate": 9.6962342900496e-06, + "loss": 0.0123, + "step": 11851 + }, + { + "epoch": 10.49, + "learning_rate": 9.694801876930395e-06, + "loss": 0.0115, + "step": 11852 + }, + { + "epoch": 10.49, + "learning_rate": 9.693369470079082e-06, + "loss": 0.0125, + "step": 11853 + }, + { + "epoch": 10.49, + "learning_rate": 9.691937069525073e-06, + "loss": 0.011, + "step": 11854 + }, + { + "epoch": 10.49, + "learning_rate": 9.690504675297785e-06, + "loss": 0.0101, + "step": 11855 + }, + { + "epoch": 10.49, + "learning_rate": 9.689072287426641e-06, + "loss": 0.0127, + "step": 11856 + }, + { + "epoch": 10.49, + "learning_rate": 9.687639905941055e-06, + "loss": 0.0102, + "step": 11857 + }, + { + "epoch": 10.49, + "learning_rate": 9.686207530870444e-06, + "loss": 0.0111, + "step": 11858 + }, + { + "epoch": 10.49, + "learning_rate": 9.68477516224422e-06, + "loss": 0.0105, + "step": 11859 + }, + { + "epoch": 10.49, + "learning_rate": 9.68334280009181e-06, + "loss": 0.0123, + "step": 11860 + }, + { + "epoch": 10.49, + "learning_rate": 9.681910444442621e-06, + "loss": 0.0114, + "step": 11861 + }, + { + "epoch": 10.49, + "learning_rate": 9.680478095326072e-06, + "loss": 0.0116, + "step": 11862 + }, + { + "epoch": 10.5, + "learning_rate": 9.679045752771583e-06, + "loss": 0.0108, + "step": 11863 + }, + { + "epoch": 10.5, + "learning_rate": 9.677613416808568e-06, + "loss": 0.0123, + "step": 11864 + }, + { + "epoch": 10.5, + "learning_rate": 9.676181087466444e-06, + "loss": 0.0121, + "step": 11865 + }, + { + "epoch": 10.5, + "learning_rate": 9.674748764774622e-06, + "loss": 0.0115, + "step": 11866 + }, + { + "epoch": 10.5, + "learning_rate": 9.673316448762526e-06, + "loss": 0.0112, + "step": 11867 + }, + { + "epoch": 10.5, + "learning_rate": 9.671884139459563e-06, + "loss": 0.0107, + "step": 11868 + }, + { + "epoch": 10.5, + "learning_rate": 9.670451836895151e-06, + "loss": 0.0122, + "step": 11869 + }, + { + "epoch": 10.5, + "learning_rate": 9.669019541098711e-06, + "loss": 0.0126, + "step": 11870 + }, + { + "epoch": 10.5, + "learning_rate": 9.667587252099655e-06, + "loss": 0.0117, + "step": 11871 + }, + { + "epoch": 10.5, + "learning_rate": 9.666154969927396e-06, + "loss": 0.0131, + "step": 11872 + }, + { + "epoch": 10.5, + "learning_rate": 9.664722694611346e-06, + "loss": 0.0122, + "step": 11873 + }, + { + "epoch": 10.51, + "learning_rate": 9.663290426180926e-06, + "loss": 0.0143, + "step": 11874 + }, + { + "epoch": 10.51, + "learning_rate": 9.661858164665554e-06, + "loss": 0.0106, + "step": 11875 + }, + { + "epoch": 10.51, + "learning_rate": 9.660425910094633e-06, + "loss": 0.0096, + "step": 11876 + }, + { + "epoch": 10.51, + "learning_rate": 9.658993662497588e-06, + "loss": 0.0137, + "step": 11877 + }, + { + "epoch": 10.51, + "learning_rate": 9.657561421903823e-06, + "loss": 0.0114, + "step": 11878 + }, + { + "epoch": 10.51, + "learning_rate": 9.656129188342766e-06, + "loss": 0.01, + "step": 11879 + }, + { + "epoch": 10.51, + "learning_rate": 9.654696961843816e-06, + "loss": 0.0108, + "step": 11880 + }, + { + "epoch": 10.51, + "learning_rate": 9.653264742436394e-06, + "loss": 0.012, + "step": 11881 + }, + { + "epoch": 10.51, + "learning_rate": 9.651832530149918e-06, + "loss": 0.0112, + "step": 11882 + }, + { + "epoch": 10.51, + "learning_rate": 9.650400325013792e-06, + "loss": 0.0135, + "step": 11883 + }, + { + "epoch": 10.51, + "learning_rate": 9.648968127057437e-06, + "loss": 0.0104, + "step": 11884 + }, + { + "epoch": 10.52, + "learning_rate": 9.64753593631026e-06, + "loss": 0.0113, + "step": 11885 + }, + { + "epoch": 10.52, + "learning_rate": 9.646103752801684e-06, + "loss": 0.0138, + "step": 11886 + }, + { + "epoch": 10.52, + "learning_rate": 9.644671576561109e-06, + "loss": 0.0119, + "step": 11887 + }, + { + "epoch": 10.52, + "learning_rate": 9.643239407617954e-06, + "loss": 0.0118, + "step": 11888 + }, + { + "epoch": 10.52, + "learning_rate": 9.641807246001635e-06, + "loss": 0.0122, + "step": 11889 + }, + { + "epoch": 10.52, + "learning_rate": 9.640375091741559e-06, + "loss": 0.012, + "step": 11890 + }, + { + "epoch": 10.52, + "learning_rate": 9.638942944867143e-06, + "loss": 0.0112, + "step": 11891 + }, + { + "epoch": 10.52, + "learning_rate": 9.637510805407794e-06, + "loss": 0.0133, + "step": 11892 + }, + { + "epoch": 10.52, + "learning_rate": 9.636078673392932e-06, + "loss": 0.0126, + "step": 11893 + }, + { + "epoch": 10.52, + "learning_rate": 9.634646548851956e-06, + "loss": 0.0116, + "step": 11894 + }, + { + "epoch": 10.52, + "learning_rate": 9.633214431814286e-06, + "loss": 0.011, + "step": 11895 + }, + { + "epoch": 10.52, + "learning_rate": 9.631782322309337e-06, + "loss": 0.0123, + "step": 11896 + }, + { + "epoch": 10.53, + "learning_rate": 9.630350220366514e-06, + "loss": 0.0135, + "step": 11897 + }, + { + "epoch": 10.53, + "learning_rate": 9.628918126015232e-06, + "loss": 0.0117, + "step": 11898 + }, + { + "epoch": 10.53, + "learning_rate": 9.627486039284897e-06, + "loss": 0.0117, + "step": 11899 + }, + { + "epoch": 10.53, + "learning_rate": 9.626053960204923e-06, + "loss": 0.0138, + "step": 11900 + }, + { + "epoch": 10.53, + "learning_rate": 9.624621888804728e-06, + "loss": 0.0124, + "step": 11901 + }, + { + "epoch": 10.53, + "learning_rate": 9.623189825113708e-06, + "loss": 0.0114, + "step": 11902 + }, + { + "epoch": 10.53, + "learning_rate": 9.621757769161286e-06, + "loss": 0.012, + "step": 11903 + }, + { + "epoch": 10.53, + "learning_rate": 9.620325720976867e-06, + "loss": 0.0128, + "step": 11904 + }, + { + "epoch": 10.53, + "learning_rate": 9.618893680589861e-06, + "loss": 0.0122, + "step": 11905 + }, + { + "epoch": 10.53, + "learning_rate": 9.617461648029677e-06, + "loss": 0.0118, + "step": 11906 + }, + { + "epoch": 10.53, + "learning_rate": 9.616029623325729e-06, + "loss": 0.0107, + "step": 11907 + }, + { + "epoch": 10.54, + "learning_rate": 9.614597606507423e-06, + "loss": 0.0118, + "step": 11908 + }, + { + "epoch": 10.54, + "learning_rate": 9.613165597604168e-06, + "loss": 0.0113, + "step": 11909 + }, + { + "epoch": 10.54, + "learning_rate": 9.611733596645378e-06, + "loss": 0.0118, + "step": 11910 + }, + { + "epoch": 10.54, + "learning_rate": 9.610301603660457e-06, + "loss": 0.0112, + "step": 11911 + }, + { + "epoch": 10.54, + "learning_rate": 9.608869618678818e-06, + "loss": 0.0101, + "step": 11912 + }, + { + "epoch": 10.54, + "learning_rate": 9.607437641729866e-06, + "loss": 0.0118, + "step": 11913 + }, + { + "epoch": 10.54, + "learning_rate": 9.606005672843011e-06, + "loss": 0.0102, + "step": 11914 + }, + { + "epoch": 10.54, + "learning_rate": 9.604573712047665e-06, + "loss": 0.0139, + "step": 11915 + }, + { + "epoch": 10.54, + "learning_rate": 9.60314175937323e-06, + "loss": 0.0119, + "step": 11916 + }, + { + "epoch": 10.54, + "learning_rate": 9.60170981484912e-06, + "loss": 0.0126, + "step": 11917 + }, + { + "epoch": 10.54, + "learning_rate": 9.600277878504742e-06, + "loss": 0.0137, + "step": 11918 + }, + { + "epoch": 10.55, + "learning_rate": 9.598845950369502e-06, + "loss": 0.0116, + "step": 11919 + }, + { + "epoch": 10.55, + "learning_rate": 9.597414030472804e-06, + "loss": 0.0122, + "step": 11920 + }, + { + "epoch": 10.55, + "learning_rate": 9.595982118844062e-06, + "loss": 0.0122, + "step": 11921 + }, + { + "epoch": 10.55, + "learning_rate": 9.594550215512683e-06, + "loss": 0.0132, + "step": 11922 + }, + { + "epoch": 10.55, + "learning_rate": 9.593118320508067e-06, + "loss": 0.0121, + "step": 11923 + }, + { + "epoch": 10.55, + "learning_rate": 9.591686433859632e-06, + "loss": 0.0109, + "step": 11924 + }, + { + "epoch": 10.55, + "learning_rate": 9.590254555596777e-06, + "loss": 0.0122, + "step": 11925 + }, + { + "epoch": 10.55, + "learning_rate": 9.588822685748908e-06, + "loss": 0.011, + "step": 11926 + }, + { + "epoch": 10.55, + "learning_rate": 9.587390824345437e-06, + "loss": 0.0136, + "step": 11927 + }, + { + "epoch": 10.55, + "learning_rate": 9.585958971415766e-06, + "loss": 0.011, + "step": 11928 + }, + { + "epoch": 10.55, + "learning_rate": 9.584527126989305e-06, + "loss": 0.0125, + "step": 11929 + }, + { + "epoch": 10.55, + "learning_rate": 9.583095291095454e-06, + "loss": 0.0102, + "step": 11930 + }, + { + "epoch": 10.56, + "learning_rate": 9.581663463763626e-06, + "loss": 0.0108, + "step": 11931 + }, + { + "epoch": 10.56, + "learning_rate": 9.58023164502322e-06, + "loss": 0.0119, + "step": 11932 + }, + { + "epoch": 10.56, + "learning_rate": 9.578799834903642e-06, + "loss": 0.0119, + "step": 11933 + }, + { + "epoch": 10.56, + "learning_rate": 9.577368033434305e-06, + "loss": 0.0123, + "step": 11934 + }, + { + "epoch": 10.56, + "learning_rate": 9.575936240644604e-06, + "loss": 0.0129, + "step": 11935 + }, + { + "epoch": 10.56, + "learning_rate": 9.574504456563952e-06, + "loss": 0.0139, + "step": 11936 + }, + { + "epoch": 10.56, + "learning_rate": 9.573072681221747e-06, + "loss": 0.0129, + "step": 11937 + }, + { + "epoch": 10.56, + "learning_rate": 9.571640914647399e-06, + "loss": 0.0181, + "step": 11938 + }, + { + "epoch": 10.56, + "learning_rate": 9.570209156870309e-06, + "loss": 0.0122, + "step": 11939 + }, + { + "epoch": 10.56, + "learning_rate": 9.56877740791988e-06, + "loss": 0.0141, + "step": 11940 + }, + { + "epoch": 10.56, + "learning_rate": 9.567345667825523e-06, + "loss": 0.0122, + "step": 11941 + }, + { + "epoch": 10.57, + "learning_rate": 9.565913936616634e-06, + "loss": 0.0108, + "step": 11942 + }, + { + "epoch": 10.57, + "learning_rate": 9.564482214322623e-06, + "loss": 0.0135, + "step": 11943 + }, + { + "epoch": 10.57, + "learning_rate": 9.563050500972883e-06, + "loss": 0.0157, + "step": 11944 + }, + { + "epoch": 10.57, + "learning_rate": 9.561618796596832e-06, + "loss": 0.0123, + "step": 11945 + }, + { + "epoch": 10.57, + "learning_rate": 9.56018710122386e-06, + "loss": 0.0115, + "step": 11946 + }, + { + "epoch": 10.57, + "learning_rate": 9.558755414883376e-06, + "loss": 0.0123, + "step": 11947 + }, + { + "epoch": 10.57, + "learning_rate": 9.557323737604785e-06, + "loss": 0.0112, + "step": 11948 + }, + { + "epoch": 10.57, + "learning_rate": 9.555892069417485e-06, + "loss": 0.0129, + "step": 11949 + }, + { + "epoch": 10.57, + "learning_rate": 9.554460410350882e-06, + "loss": 0.0132, + "step": 11950 + }, + { + "epoch": 10.57, + "learning_rate": 9.55302876043437e-06, + "loss": 0.0136, + "step": 11951 + }, + { + "epoch": 10.57, + "learning_rate": 9.551597119697362e-06, + "loss": 0.0118, + "step": 11952 + }, + { + "epoch": 10.58, + "learning_rate": 9.550165488169255e-06, + "loss": 0.0098, + "step": 11953 + }, + { + "epoch": 10.58, + "learning_rate": 9.548733865879446e-06, + "loss": 0.0136, + "step": 11954 + }, + { + "epoch": 10.58, + "learning_rate": 9.547302252857346e-06, + "loss": 0.0105, + "step": 11955 + }, + { + "epoch": 10.58, + "learning_rate": 9.545870649132348e-06, + "loss": 0.0145, + "step": 11956 + }, + { + "epoch": 10.58, + "learning_rate": 9.544439054733858e-06, + "loss": 0.0112, + "step": 11957 + }, + { + "epoch": 10.58, + "learning_rate": 9.543007469691271e-06, + "loss": 0.0137, + "step": 11958 + }, + { + "epoch": 10.58, + "learning_rate": 9.541575894033993e-06, + "loss": 0.0126, + "step": 11959 + }, + { + "epoch": 10.58, + "learning_rate": 9.540144327791426e-06, + "loss": 0.0116, + "step": 11960 + }, + { + "epoch": 10.58, + "learning_rate": 9.53871277099296e-06, + "loss": 0.0125, + "step": 11961 + }, + { + "epoch": 10.58, + "learning_rate": 9.537281223668009e-06, + "loss": 0.0108, + "step": 11962 + }, + { + "epoch": 10.58, + "learning_rate": 9.535849685845962e-06, + "loss": 0.0127, + "step": 11963 + }, + { + "epoch": 10.59, + "learning_rate": 9.534418157556226e-06, + "loss": 0.0111, + "step": 11964 + }, + { + "epoch": 10.59, + "learning_rate": 9.532986638828192e-06, + "loss": 0.0117, + "step": 11965 + }, + { + "epoch": 10.59, + "learning_rate": 9.531555129691267e-06, + "loss": 0.0112, + "step": 11966 + }, + { + "epoch": 10.59, + "learning_rate": 9.530123630174849e-06, + "loss": 0.0137, + "step": 11967 + }, + { + "epoch": 10.59, + "learning_rate": 9.528692140308332e-06, + "loss": 0.0132, + "step": 11968 + }, + { + "epoch": 10.59, + "learning_rate": 9.527260660121121e-06, + "loss": 0.0125, + "step": 11969 + }, + { + "epoch": 10.59, + "learning_rate": 9.525829189642609e-06, + "loss": 0.0137, + "step": 11970 + }, + { + "epoch": 10.59, + "learning_rate": 9.524397728902199e-06, + "loss": 0.012, + "step": 11971 + }, + { + "epoch": 10.59, + "learning_rate": 9.522966277929283e-06, + "loss": 0.0143, + "step": 11972 + }, + { + "epoch": 10.59, + "learning_rate": 9.521534836753264e-06, + "loss": 0.0131, + "step": 11973 + }, + { + "epoch": 10.59, + "learning_rate": 9.520103405403542e-06, + "loss": 0.0115, + "step": 11974 + }, + { + "epoch": 10.59, + "learning_rate": 9.518671983909504e-06, + "loss": 0.0113, + "step": 11975 + }, + { + "epoch": 10.6, + "learning_rate": 9.51724057230056e-06, + "loss": 0.0124, + "step": 11976 + }, + { + "epoch": 10.6, + "learning_rate": 9.515809170606099e-06, + "loss": 0.0115, + "step": 11977 + }, + { + "epoch": 10.6, + "learning_rate": 9.514377778855521e-06, + "loss": 0.0131, + "step": 11978 + }, + { + "epoch": 10.6, + "learning_rate": 9.512946397078218e-06, + "loss": 0.0106, + "step": 11979 + }, + { + "epoch": 10.6, + "learning_rate": 9.511515025303591e-06, + "loss": 0.0135, + "step": 11980 + }, + { + "epoch": 10.6, + "learning_rate": 9.51008366356104e-06, + "loss": 0.0123, + "step": 11981 + }, + { + "epoch": 10.6, + "learning_rate": 9.508652311879948e-06, + "loss": 0.0106, + "step": 11982 + }, + { + "epoch": 10.6, + "learning_rate": 9.507220970289727e-06, + "loss": 0.0126, + "step": 11983 + }, + { + "epoch": 10.6, + "learning_rate": 9.505789638819761e-06, + "loss": 0.0142, + "step": 11984 + }, + { + "epoch": 10.6, + "learning_rate": 9.504358317499447e-06, + "loss": 0.0125, + "step": 11985 + }, + { + "epoch": 10.6, + "learning_rate": 9.502927006358187e-06, + "loss": 0.0134, + "step": 11986 + }, + { + "epoch": 10.61, + "learning_rate": 9.50149570542537e-06, + "loss": 0.012, + "step": 11987 + }, + { + "epoch": 10.61, + "learning_rate": 9.500064414730393e-06, + "loss": 0.0143, + "step": 11988 + }, + { + "epoch": 10.61, + "learning_rate": 9.498633134302645e-06, + "loss": 0.0121, + "step": 11989 + }, + { + "epoch": 10.61, + "learning_rate": 9.49720186417153e-06, + "loss": 0.0148, + "step": 11990 + }, + { + "epoch": 10.61, + "learning_rate": 9.495770604366435e-06, + "loss": 0.011, + "step": 11991 + }, + { + "epoch": 10.61, + "learning_rate": 9.494339354916756e-06, + "loss": 0.0116, + "step": 11992 + }, + { + "epoch": 10.61, + "learning_rate": 9.492908115851888e-06, + "loss": 0.012, + "step": 11993 + }, + { + "epoch": 10.61, + "learning_rate": 9.491476887201223e-06, + "loss": 0.0108, + "step": 11994 + }, + { + "epoch": 10.61, + "learning_rate": 9.490045668994157e-06, + "loss": 0.0127, + "step": 11995 + }, + { + "epoch": 10.61, + "learning_rate": 9.488614461260076e-06, + "loss": 0.0122, + "step": 11996 + }, + { + "epoch": 10.61, + "learning_rate": 9.487183264028384e-06, + "loss": 0.0104, + "step": 11997 + }, + { + "epoch": 10.62, + "learning_rate": 9.485752077328462e-06, + "loss": 0.0133, + "step": 11998 + }, + { + "epoch": 10.62, + "learning_rate": 9.484320901189708e-06, + "loss": 0.0117, + "step": 11999 + }, + { + "epoch": 10.62, + "learning_rate": 9.482889735641517e-06, + "loss": 0.0138, + "step": 12000 + }, + { + "epoch": 3.71, + "learning_rate": 1.876131222165888e-05, + "loss": 0.7864, + "step": 12001 + }, + { + "epoch": 3.71, + "learning_rate": 1.8761071117362533e-05, + "loss": 0.5691, + "step": 12002 + }, + { + "epoch": 3.71, + "learning_rate": 1.8760829991153158e-05, + "loss": 0.4313, + "step": 12003 + }, + { + "epoch": 3.71, + "learning_rate": 1.8760588843031345e-05, + "loss": 0.4293, + "step": 12004 + }, + { + "epoch": 3.71, + "learning_rate": 1.87603476729977e-05, + "loss": 0.4511, + "step": 12005 + }, + { + "epoch": 3.71, + "learning_rate": 1.876010648105283e-05, + "loss": 0.4028, + "step": 12006 + }, + { + "epoch": 3.71, + "learning_rate": 1.8759865267197333e-05, + "loss": 0.4048, + "step": 12007 + }, + { + "epoch": 3.71, + "learning_rate": 1.875962403143182e-05, + "loss": 0.4008, + "step": 12008 + }, + { + "epoch": 3.71, + "learning_rate": 1.875938277375689e-05, + "loss": 0.3572, + "step": 12009 + }, + { + "epoch": 3.71, + "learning_rate": 1.875914149417314e-05, + "loss": 0.4004, + "step": 12010 + }, + { + "epoch": 3.71, + "learning_rate": 1.8758900192681186e-05, + "loss": 0.3985, + "step": 12011 + }, + { + "epoch": 3.71, + "learning_rate": 1.875865886928162e-05, + "loss": 0.3755, + "step": 12012 + }, + { + "epoch": 3.71, + "learning_rate": 1.8758417523975052e-05, + "loss": 0.3839, + "step": 12013 + }, + { + "epoch": 3.71, + "learning_rate": 1.8758176156762085e-05, + "loss": 0.374, + "step": 12014 + }, + { + "epoch": 3.71, + "learning_rate": 1.8757934767643326e-05, + "loss": 0.3788, + "step": 12015 + }, + { + "epoch": 3.71, + "learning_rate": 1.875769335661937e-05, + "loss": 0.3954, + "step": 12016 + }, + { + "epoch": 3.71, + "learning_rate": 1.8757451923690822e-05, + "loss": 0.3757, + "step": 12017 + }, + { + "epoch": 3.71, + "learning_rate": 1.8757210468858294e-05, + "loss": 0.3461, + "step": 12018 + }, + { + "epoch": 3.71, + "learning_rate": 1.8756968992122386e-05, + "loss": 0.4207, + "step": 12019 + }, + { + "epoch": 3.71, + "learning_rate": 1.8756727493483702e-05, + "loss": 0.3939, + "step": 12020 + }, + { + "epoch": 3.71, + "learning_rate": 1.8756485972942844e-05, + "loss": 0.3967, + "step": 12021 + }, + { + "epoch": 3.71, + "learning_rate": 1.8756244430500418e-05, + "loss": 0.3965, + "step": 12022 + }, + { + "epoch": 3.71, + "learning_rate": 1.8756002866157027e-05, + "loss": 0.3997, + "step": 12023 + }, + { + "epoch": 3.71, + "learning_rate": 1.8755761279913277e-05, + "loss": 0.3714, + "step": 12024 + }, + { + "epoch": 3.71, + "learning_rate": 1.875551967176977e-05, + "loss": 0.3631, + "step": 12025 + }, + { + "epoch": 3.71, + "learning_rate": 1.8755278041727113e-05, + "loss": 0.4003, + "step": 12026 + }, + { + "epoch": 3.71, + "learning_rate": 1.8755036389785905e-05, + "loss": 0.4069, + "step": 12027 + }, + { + "epoch": 3.71, + "learning_rate": 1.8754794715946758e-05, + "loss": 0.3875, + "step": 12028 + }, + { + "epoch": 3.71, + "learning_rate": 1.875455302021027e-05, + "loss": 0.3789, + "step": 12029 + }, + { + "epoch": 3.72, + "learning_rate": 1.875431130257705e-05, + "loss": 0.3987, + "step": 12030 + }, + { + "epoch": 3.72, + "learning_rate": 1.8754069563047702e-05, + "loss": 0.375, + "step": 12031 + }, + { + "epoch": 3.72, + "learning_rate": 1.8753827801622827e-05, + "loss": 0.4013, + "step": 12032 + }, + { + "epoch": 3.72, + "learning_rate": 1.875358601830303e-05, + "loss": 0.4063, + "step": 12033 + }, + { + "epoch": 3.72, + "learning_rate": 1.875334421308892e-05, + "loss": 0.4024, + "step": 12034 + }, + { + "epoch": 3.72, + "learning_rate": 1.87531023859811e-05, + "loss": 0.3943, + "step": 12035 + }, + { + "epoch": 3.72, + "learning_rate": 1.8752860536980178e-05, + "loss": 0.3897, + "step": 12036 + }, + { + "epoch": 3.72, + "learning_rate": 1.8752618666086747e-05, + "loss": 0.433, + "step": 12037 + }, + { + "epoch": 3.72, + "learning_rate": 1.8752376773301427e-05, + "loss": 0.4076, + "step": 12038 + }, + { + "epoch": 3.72, + "learning_rate": 1.8752134858624816e-05, + "loss": 0.4112, + "step": 12039 + }, + { + "epoch": 3.72, + "learning_rate": 1.875189292205752e-05, + "loss": 0.3923, + "step": 12040 + }, + { + "epoch": 3.72, + "learning_rate": 1.875165096360014e-05, + "loss": 0.402, + "step": 12041 + }, + { + "epoch": 3.72, + "learning_rate": 1.8751408983253284e-05, + "loss": 0.4193, + "step": 12042 + }, + { + "epoch": 3.72, + "learning_rate": 1.8751166981017562e-05, + "loss": 0.4586, + "step": 12043 + }, + { + "epoch": 3.72, + "learning_rate": 1.8750924956893574e-05, + "loss": 0.4231, + "step": 12044 + }, + { + "epoch": 3.72, + "learning_rate": 1.8750682910881926e-05, + "loss": 0.3969, + "step": 12045 + }, + { + "epoch": 3.72, + "learning_rate": 1.875044084298322e-05, + "loss": 0.4323, + "step": 12046 + }, + { + "epoch": 3.72, + "learning_rate": 1.875019875319807e-05, + "loss": 0.4124, + "step": 12047 + }, + { + "epoch": 3.72, + "learning_rate": 1.874995664152708e-05, + "loss": 0.3908, + "step": 12048 + }, + { + "epoch": 3.72, + "learning_rate": 1.8749714507970845e-05, + "loss": 0.3796, + "step": 12049 + }, + { + "epoch": 3.72, + "learning_rate": 1.8749472352529984e-05, + "loss": 0.4071, + "step": 12050 + }, + { + "epoch": 3.72, + "learning_rate": 1.8749230175205094e-05, + "loss": 0.4197, + "step": 12051 + }, + { + "epoch": 3.72, + "learning_rate": 1.8748987975996787e-05, + "loss": 0.4331, + "step": 12052 + }, + { + "epoch": 3.72, + "learning_rate": 1.874874575490566e-05, + "loss": 0.4112, + "step": 12053 + }, + { + "epoch": 3.72, + "learning_rate": 1.874850351193233e-05, + "loss": 0.4007, + "step": 12054 + }, + { + "epoch": 3.72, + "learning_rate": 1.8748261247077395e-05, + "loss": 0.4119, + "step": 12055 + }, + { + "epoch": 3.72, + "learning_rate": 1.8748018960341463e-05, + "loss": 0.4109, + "step": 12056 + }, + { + "epoch": 3.72, + "learning_rate": 1.874777665172514e-05, + "loss": 0.3981, + "step": 12057 + }, + { + "epoch": 3.72, + "learning_rate": 1.8747534321229032e-05, + "loss": 0.4166, + "step": 12058 + }, + { + "epoch": 3.72, + "learning_rate": 1.8747291968853742e-05, + "loss": 0.4192, + "step": 12059 + }, + { + "epoch": 3.72, + "learning_rate": 1.8747049594599883e-05, + "loss": 0.3893, + "step": 12060 + }, + { + "epoch": 3.72, + "learning_rate": 1.8746807198468057e-05, + "loss": 0.4041, + "step": 12061 + }, + { + "epoch": 3.73, + "learning_rate": 1.874656478045887e-05, + "loss": 0.4162, + "step": 12062 + }, + { + "epoch": 3.73, + "learning_rate": 1.8746322340572928e-05, + "loss": 0.4074, + "step": 12063 + }, + { + "epoch": 3.73, + "learning_rate": 1.8746079878810844e-05, + "loss": 0.3927, + "step": 12064 + }, + { + "epoch": 3.73, + "learning_rate": 1.8745837395173214e-05, + "loss": 0.4181, + "step": 12065 + }, + { + "epoch": 3.73, + "learning_rate": 1.874559488966065e-05, + "loss": 0.4179, + "step": 12066 + }, + { + "epoch": 3.73, + "learning_rate": 1.874535236227376e-05, + "loss": 0.4155, + "step": 12067 + }, + { + "epoch": 3.73, + "learning_rate": 1.8745109813013145e-05, + "loss": 0.3905, + "step": 12068 + }, + { + "epoch": 3.73, + "learning_rate": 1.874486724187942e-05, + "loss": 0.381, + "step": 12069 + }, + { + "epoch": 3.73, + "learning_rate": 1.8744624648873183e-05, + "loss": 0.3986, + "step": 12070 + }, + { + "epoch": 3.73, + "learning_rate": 1.874438203399505e-05, + "loss": 0.3778, + "step": 12071 + }, + { + "epoch": 3.73, + "learning_rate": 1.874413939724562e-05, + "loss": 0.3996, + "step": 12072 + }, + { + "epoch": 3.73, + "learning_rate": 1.87438967386255e-05, + "loss": 0.4096, + "step": 12073 + }, + { + "epoch": 3.73, + "learning_rate": 1.8743654058135302e-05, + "loss": 0.3862, + "step": 12074 + }, + { + "epoch": 3.73, + "learning_rate": 1.8743411355775628e-05, + "loss": 0.3978, + "step": 12075 + }, + { + "epoch": 3.73, + "learning_rate": 1.8743168631547094e-05, + "loss": 0.4055, + "step": 12076 + }, + { + "epoch": 3.73, + "learning_rate": 1.8742925885450294e-05, + "loss": 0.4027, + "step": 12077 + }, + { + "epoch": 3.73, + "learning_rate": 1.8742683117485844e-05, + "loss": 0.4023, + "step": 12078 + }, + { + "epoch": 3.73, + "learning_rate": 1.874244032765435e-05, + "loss": 0.3832, + "step": 12079 + }, + { + "epoch": 3.73, + "learning_rate": 1.8742197515956415e-05, + "loss": 0.4139, + "step": 12080 + }, + { + "epoch": 3.73, + "learning_rate": 1.8741954682392655e-05, + "loss": 0.4016, + "step": 12081 + }, + { + "epoch": 3.73, + "learning_rate": 1.8741711826963668e-05, + "loss": 0.4033, + "step": 12082 + }, + { + "epoch": 3.73, + "learning_rate": 1.8741468949670067e-05, + "loss": 0.4212, + "step": 12083 + }, + { + "epoch": 3.73, + "learning_rate": 1.8741226050512455e-05, + "loss": 0.3976, + "step": 12084 + }, + { + "epoch": 3.73, + "learning_rate": 1.8740983129491445e-05, + "loss": 0.3902, + "step": 12085 + }, + { + "epoch": 3.73, + "learning_rate": 1.874074018660764e-05, + "loss": 0.3885, + "step": 12086 + }, + { + "epoch": 3.73, + "learning_rate": 1.8740497221861652e-05, + "loss": 0.3887, + "step": 12087 + }, + { + "epoch": 3.73, + "learning_rate": 1.8740254235254082e-05, + "loss": 0.4141, + "step": 12088 + }, + { + "epoch": 3.73, + "learning_rate": 1.8740011226785547e-05, + "loss": 0.4055, + "step": 12089 + }, + { + "epoch": 3.73, + "learning_rate": 1.8739768196456646e-05, + "loss": 0.3817, + "step": 12090 + }, + { + "epoch": 3.73, + "learning_rate": 1.873952514426799e-05, + "loss": 0.3977, + "step": 12091 + }, + { + "epoch": 3.73, + "learning_rate": 1.8739282070220193e-05, + "loss": 0.3841, + "step": 12092 + }, + { + "epoch": 3.73, + "learning_rate": 1.8739038974313856e-05, + "loss": 0.3997, + "step": 12093 + }, + { + "epoch": 3.73, + "learning_rate": 1.8738795856549587e-05, + "loss": 0.3794, + "step": 12094 + }, + { + "epoch": 3.74, + "learning_rate": 1.8738552716927995e-05, + "loss": 0.3844, + "step": 12095 + }, + { + "epoch": 3.74, + "learning_rate": 1.873830955544969e-05, + "loss": 0.382, + "step": 12096 + }, + { + "epoch": 3.74, + "learning_rate": 1.873806637211528e-05, + "loss": 0.3895, + "step": 12097 + }, + { + "epoch": 3.74, + "learning_rate": 1.873782316692537e-05, + "loss": 0.389, + "step": 12098 + }, + { + "epoch": 3.74, + "learning_rate": 1.8737579939880573e-05, + "loss": 0.3808, + "step": 12099 + }, + { + "epoch": 3.74, + "learning_rate": 1.8737336690981492e-05, + "loss": 0.3864, + "step": 12100 + }, + { + "epoch": 3.74, + "learning_rate": 1.873709342022874e-05, + "loss": 0.4019, + "step": 12101 + }, + { + "epoch": 3.74, + "learning_rate": 1.8736850127622922e-05, + "loss": 0.3952, + "step": 12102 + }, + { + "epoch": 3.74, + "learning_rate": 1.8736606813164653e-05, + "loss": 0.3953, + "step": 12103 + }, + { + "epoch": 3.74, + "learning_rate": 1.8736363476854533e-05, + "loss": 0.3727, + "step": 12104 + }, + { + "epoch": 3.74, + "learning_rate": 1.8736120118693175e-05, + "loss": 0.3787, + "step": 12105 + }, + { + "epoch": 3.74, + "learning_rate": 1.873587673868119e-05, + "loss": 0.3811, + "step": 12106 + }, + { + "epoch": 3.74, + "learning_rate": 1.873563333681918e-05, + "loss": 0.3969, + "step": 12107 + }, + { + "epoch": 3.74, + "learning_rate": 1.8735389913107758e-05, + "loss": 0.3929, + "step": 12108 + }, + { + "epoch": 3.74, + "learning_rate": 1.8735146467547535e-05, + "loss": 0.4186, + "step": 12109 + }, + { + "epoch": 3.74, + "learning_rate": 1.8734903000139117e-05, + "loss": 0.3935, + "step": 12110 + }, + { + "epoch": 3.74, + "learning_rate": 1.8734659510883114e-05, + "loss": 0.3928, + "step": 12111 + }, + { + "epoch": 3.74, + "learning_rate": 1.8734415999780132e-05, + "loss": 0.3841, + "step": 12112 + }, + { + "epoch": 3.74, + "learning_rate": 1.8734172466830785e-05, + "loss": 0.3957, + "step": 12113 + }, + { + "epoch": 3.74, + "learning_rate": 1.873392891203568e-05, + "loss": 0.3813, + "step": 12114 + }, + { + "epoch": 3.74, + "learning_rate": 1.873368533539542e-05, + "loss": 0.3787, + "step": 12115 + }, + { + "epoch": 3.74, + "learning_rate": 1.8733441736910625e-05, + "loss": 0.4058, + "step": 12116 + }, + { + "epoch": 3.74, + "learning_rate": 1.87331981165819e-05, + "loss": 0.4107, + "step": 12117 + }, + { + "epoch": 3.74, + "learning_rate": 1.8732954474409855e-05, + "loss": 0.4011, + "step": 12118 + }, + { + "epoch": 3.74, + "learning_rate": 1.8732710810395095e-05, + "loss": 0.3828, + "step": 12119 + }, + { + "epoch": 3.74, + "learning_rate": 1.873246712453823e-05, + "loss": 0.4058, + "step": 12120 + }, + { + "epoch": 3.74, + "learning_rate": 1.8732223416839875e-05, + "loss": 0.3654, + "step": 12121 + }, + { + "epoch": 3.74, + "learning_rate": 1.873197968730064e-05, + "loss": 0.4067, + "step": 12122 + }, + { + "epoch": 3.74, + "learning_rate": 1.8731735935921128e-05, + "loss": 0.3975, + "step": 12123 + }, + { + "epoch": 3.74, + "learning_rate": 1.873149216270195e-05, + "loss": 0.3796, + "step": 12124 + }, + { + "epoch": 3.74, + "learning_rate": 1.873124836764372e-05, + "loss": 0.3676, + "step": 12125 + }, + { + "epoch": 3.74, + "learning_rate": 1.873100455074704e-05, + "loss": 0.3682, + "step": 12126 + }, + { + "epoch": 3.75, + "learning_rate": 1.8730760712012535e-05, + "loss": 0.3795, + "step": 12127 + }, + { + "epoch": 3.75, + "learning_rate": 1.8730516851440802e-05, + "loss": 0.3963, + "step": 12128 + }, + { + "epoch": 3.75, + "learning_rate": 1.8730272969032447e-05, + "loss": 0.3849, + "step": 12129 + }, + { + "epoch": 3.75, + "learning_rate": 1.8730029064788094e-05, + "loss": 0.3982, + "step": 12130 + }, + { + "epoch": 3.75, + "learning_rate": 1.8729785138708344e-05, + "loss": 0.3867, + "step": 12131 + }, + { + "epoch": 3.75, + "learning_rate": 1.872954119079381e-05, + "loss": 0.3735, + "step": 12132 + }, + { + "epoch": 3.75, + "learning_rate": 1.8729297221045098e-05, + "loss": 0.3799, + "step": 12133 + }, + { + "epoch": 3.75, + "learning_rate": 1.8729053229462826e-05, + "loss": 0.3958, + "step": 12134 + }, + { + "epoch": 3.75, + "learning_rate": 1.8728809216047595e-05, + "loss": 0.3949, + "step": 12135 + }, + { + "epoch": 3.75, + "learning_rate": 1.8728565180800026e-05, + "loss": 0.3641, + "step": 12136 + }, + { + "epoch": 3.75, + "learning_rate": 1.872832112372072e-05, + "loss": 0.3536, + "step": 12137 + }, + { + "epoch": 3.75, + "learning_rate": 1.872807704481029e-05, + "loss": 0.3711, + "step": 12138 + }, + { + "epoch": 3.75, + "learning_rate": 1.872783294406935e-05, + "loss": 0.3797, + "step": 12139 + }, + { + "epoch": 3.75, + "learning_rate": 1.872758882149851e-05, + "loss": 0.3801, + "step": 12140 + }, + { + "epoch": 3.75, + "learning_rate": 1.872734467709837e-05, + "loss": 0.3632, + "step": 12141 + }, + { + "epoch": 3.75, + "learning_rate": 1.8727100510869557e-05, + "loss": 0.3889, + "step": 12142 + }, + { + "epoch": 3.75, + "learning_rate": 1.872685632281267e-05, + "loss": 0.3668, + "step": 12143 + }, + { + "epoch": 3.75, + "learning_rate": 1.8726612112928327e-05, + "loss": 0.3819, + "step": 12144 + }, + { + "epoch": 3.75, + "learning_rate": 1.8726367881217134e-05, + "loss": 0.3775, + "step": 12145 + }, + { + "epoch": 3.75, + "learning_rate": 1.87261236276797e-05, + "loss": 0.3588, + "step": 12146 + }, + { + "epoch": 3.75, + "learning_rate": 1.872587935231664e-05, + "loss": 0.3755, + "step": 12147 + }, + { + "epoch": 3.75, + "learning_rate": 1.872563505512857e-05, + "loss": 0.3686, + "step": 12148 + }, + { + "epoch": 3.75, + "learning_rate": 1.872539073611609e-05, + "loss": 0.364, + "step": 12149 + }, + { + "epoch": 3.75, + "learning_rate": 1.8725146395279818e-05, + "loss": 0.3856, + "step": 12150 + }, + { + "epoch": 3.75, + "learning_rate": 1.8724902032620363e-05, + "loss": 0.3775, + "step": 12151 + }, + { + "epoch": 3.75, + "learning_rate": 1.872465764813834e-05, + "loss": 0.3802, + "step": 12152 + }, + { + "epoch": 3.75, + "learning_rate": 1.8724413241834353e-05, + "loss": 0.3847, + "step": 12153 + }, + { + "epoch": 3.75, + "learning_rate": 1.8724168813709016e-05, + "loss": 0.3393, + "step": 12154 + }, + { + "epoch": 3.75, + "learning_rate": 1.8723924363762945e-05, + "loss": 0.3754, + "step": 12155 + }, + { + "epoch": 3.75, + "learning_rate": 1.8723679891996747e-05, + "loss": 0.394, + "step": 12156 + }, + { + "epoch": 3.75, + "learning_rate": 1.8723435398411034e-05, + "loss": 0.3692, + "step": 12157 + }, + { + "epoch": 3.75, + "learning_rate": 1.872319088300642e-05, + "loss": 0.3838, + "step": 12158 + }, + { + "epoch": 3.76, + "learning_rate": 1.872294634578351e-05, + "loss": 0.3748, + "step": 12159 + }, + { + "epoch": 3.76, + "learning_rate": 1.8722701786742926e-05, + "loss": 0.3855, + "step": 12160 + }, + { + "epoch": 3.76, + "learning_rate": 1.872245720588527e-05, + "loss": 0.3611, + "step": 12161 + }, + { + "epoch": 3.76, + "learning_rate": 1.872221260321116e-05, + "loss": 0.3619, + "step": 12162 + }, + { + "epoch": 3.76, + "learning_rate": 1.87219679787212e-05, + "loss": 0.3696, + "step": 12163 + }, + { + "epoch": 3.76, + "learning_rate": 1.8721723332416014e-05, + "loss": 0.3725, + "step": 12164 + }, + { + "epoch": 3.76, + "learning_rate": 1.8721478664296207e-05, + "loss": 0.3655, + "step": 12165 + }, + { + "epoch": 3.76, + "learning_rate": 1.872123397436239e-05, + "loss": 0.372, + "step": 12166 + }, + { + "epoch": 3.76, + "learning_rate": 1.872098926261517e-05, + "loss": 0.406, + "step": 12167 + }, + { + "epoch": 3.76, + "learning_rate": 1.8720744529055172e-05, + "loss": 0.3772, + "step": 12168 + }, + { + "epoch": 3.76, + "learning_rate": 1.8720499773683e-05, + "loss": 0.3659, + "step": 12169 + }, + { + "epoch": 3.76, + "learning_rate": 1.8720254996499268e-05, + "loss": 0.364, + "step": 12170 + }, + { + "epoch": 3.76, + "learning_rate": 1.8720010197504588e-05, + "loss": 0.3612, + "step": 12171 + }, + { + "epoch": 3.76, + "learning_rate": 1.871976537669957e-05, + "loss": 0.3566, + "step": 12172 + }, + { + "epoch": 3.76, + "learning_rate": 1.8719520534084828e-05, + "loss": 0.3707, + "step": 12173 + }, + { + "epoch": 3.76, + "learning_rate": 1.8719275669660976e-05, + "loss": 0.3881, + "step": 12174 + }, + { + "epoch": 3.76, + "learning_rate": 1.8719030783428627e-05, + "loss": 0.3802, + "step": 12175 + }, + { + "epoch": 3.76, + "learning_rate": 1.871878587538839e-05, + "loss": 0.3648, + "step": 12176 + }, + { + "epoch": 3.76, + "learning_rate": 1.871854094554088e-05, + "loss": 0.3609, + "step": 12177 + }, + { + "epoch": 3.76, + "learning_rate": 1.8718295993886708e-05, + "loss": 0.3706, + "step": 12178 + }, + { + "epoch": 3.76, + "learning_rate": 1.871805102042649e-05, + "loss": 0.3626, + "step": 12179 + }, + { + "epoch": 3.76, + "learning_rate": 1.871780602516083e-05, + "loss": 0.3556, + "step": 12180 + }, + { + "epoch": 3.76, + "learning_rate": 1.8717561008090356e-05, + "loss": 0.3594, + "step": 12181 + }, + { + "epoch": 3.76, + "learning_rate": 1.8717315969215667e-05, + "loss": 0.3773, + "step": 12182 + }, + { + "epoch": 3.76, + "learning_rate": 1.871707090853738e-05, + "loss": 0.3653, + "step": 12183 + }, + { + "epoch": 3.76, + "learning_rate": 1.871682582605611e-05, + "loss": 0.3631, + "step": 12184 + }, + { + "epoch": 3.76, + "learning_rate": 1.871658072177247e-05, + "loss": 0.3847, + "step": 12185 + }, + { + "epoch": 3.76, + "learning_rate": 1.8716335595687072e-05, + "loss": 0.3735, + "step": 12186 + }, + { + "epoch": 3.76, + "learning_rate": 1.8716090447800527e-05, + "loss": 0.3618, + "step": 12187 + }, + { + "epoch": 3.76, + "learning_rate": 1.871584527811345e-05, + "loss": 0.3482, + "step": 12188 + }, + { + "epoch": 3.76, + "learning_rate": 1.8715600086626457e-05, + "loss": 0.3401, + "step": 12189 + }, + { + "epoch": 3.76, + "learning_rate": 1.8715354873340152e-05, + "loss": 0.3709, + "step": 12190 + }, + { + "epoch": 3.76, + "learning_rate": 1.8715109638255163e-05, + "loss": 0.3825, + "step": 12191 + }, + { + "epoch": 3.77, + "learning_rate": 1.871486438137209e-05, + "loss": 0.3521, + "step": 12192 + }, + { + "epoch": 3.77, + "learning_rate": 1.8714619102691555e-05, + "loss": 0.3662, + "step": 12193 + }, + { + "epoch": 3.77, + "learning_rate": 1.8714373802214165e-05, + "loss": 0.3759, + "step": 12194 + }, + { + "epoch": 3.77, + "learning_rate": 1.8714128479940538e-05, + "loss": 0.3842, + "step": 12195 + }, + { + "epoch": 3.77, + "learning_rate": 1.871388313587129e-05, + "loss": 0.3687, + "step": 12196 + }, + { + "epoch": 3.77, + "learning_rate": 1.871363777000702e-05, + "loss": 0.3418, + "step": 12197 + }, + { + "epoch": 3.77, + "learning_rate": 1.8713392382348363e-05, + "loss": 0.3765, + "step": 12198 + }, + { + "epoch": 3.77, + "learning_rate": 1.8713146972895922e-05, + "loss": 0.3449, + "step": 12199 + }, + { + "epoch": 3.77, + "learning_rate": 1.8712901541650307e-05, + "loss": 0.358, + "step": 12200 + }, + { + "epoch": 3.77, + "learning_rate": 1.871265608861214e-05, + "loss": 0.3683, + "step": 12201 + }, + { + "epoch": 3.77, + "learning_rate": 1.8712410613782027e-05, + "loss": 0.364, + "step": 12202 + }, + { + "epoch": 3.77, + "learning_rate": 1.871216511716059e-05, + "loss": 0.3746, + "step": 12203 + }, + { + "epoch": 3.77, + "learning_rate": 1.8711919598748435e-05, + "loss": 0.3711, + "step": 12204 + }, + { + "epoch": 3.77, + "learning_rate": 1.8711674058546183e-05, + "loss": 0.3618, + "step": 12205 + }, + { + "epoch": 3.77, + "learning_rate": 1.8711428496554443e-05, + "loss": 0.3628, + "step": 12206 + }, + { + "epoch": 3.77, + "learning_rate": 1.8711182912773833e-05, + "loss": 0.3517, + "step": 12207 + }, + { + "epoch": 3.77, + "learning_rate": 1.8710937307204967e-05, + "loss": 0.3722, + "step": 12208 + }, + { + "epoch": 3.77, + "learning_rate": 1.8710691679848456e-05, + "loss": 0.3495, + "step": 12209 + }, + { + "epoch": 3.77, + "learning_rate": 1.871044603070492e-05, + "loss": 0.363, + "step": 12210 + }, + { + "epoch": 3.77, + "learning_rate": 1.8710200359774963e-05, + "loss": 0.3483, + "step": 12211 + }, + { + "epoch": 3.77, + "learning_rate": 1.870995466705921e-05, + "loss": 0.3878, + "step": 12212 + }, + { + "epoch": 3.77, + "learning_rate": 1.8709708952558274e-05, + "loss": 0.3389, + "step": 12213 + }, + { + "epoch": 3.77, + "learning_rate": 1.8709463216272766e-05, + "loss": 0.3315, + "step": 12214 + }, + { + "epoch": 3.77, + "learning_rate": 1.87092174582033e-05, + "loss": 0.3688, + "step": 12215 + }, + { + "epoch": 3.77, + "learning_rate": 1.8708971678350494e-05, + "loss": 0.3728, + "step": 12216 + }, + { + "epoch": 3.77, + "learning_rate": 1.8708725876714958e-05, + "loss": 0.3429, + "step": 12217 + }, + { + "epoch": 3.77, + "learning_rate": 1.8708480053297316e-05, + "loss": 0.3542, + "step": 12218 + }, + { + "epoch": 3.77, + "learning_rate": 1.8708234208098175e-05, + "loss": 0.3697, + "step": 12219 + }, + { + "epoch": 3.77, + "learning_rate": 1.870798834111815e-05, + "loss": 0.3735, + "step": 12220 + }, + { + "epoch": 3.77, + "learning_rate": 1.870774245235786e-05, + "loss": 0.3782, + "step": 12221 + }, + { + "epoch": 3.77, + "learning_rate": 1.870749654181792e-05, + "loss": 0.3643, + "step": 12222 + }, + { + "epoch": 3.77, + "learning_rate": 1.8707250609498938e-05, + "loss": 0.3639, + "step": 12223 + }, + { + "epoch": 3.78, + "learning_rate": 1.8707004655401535e-05, + "loss": 0.3802, + "step": 12224 + }, + { + "epoch": 3.78, + "learning_rate": 1.8706758679526328e-05, + "loss": 0.3485, + "step": 12225 + }, + { + "epoch": 3.78, + "learning_rate": 1.870651268187393e-05, + "loss": 0.3544, + "step": 12226 + }, + { + "epoch": 3.78, + "learning_rate": 1.8706266662444954e-05, + "loss": 0.375, + "step": 12227 + }, + { + "epoch": 3.78, + "learning_rate": 1.8706020621240016e-05, + "loss": 0.3702, + "step": 12228 + }, + { + "epoch": 3.78, + "learning_rate": 1.8705774558259736e-05, + "loss": 0.3606, + "step": 12229 + }, + { + "epoch": 3.78, + "learning_rate": 1.870552847350472e-05, + "loss": 0.3589, + "step": 12230 + }, + { + "epoch": 3.78, + "learning_rate": 1.8705282366975597e-05, + "loss": 0.3725, + "step": 12231 + }, + { + "epoch": 3.78, + "learning_rate": 1.870503623867297e-05, + "loss": 0.3477, + "step": 12232 + }, + { + "epoch": 3.78, + "learning_rate": 1.870479008859746e-05, + "loss": 0.3607, + "step": 12233 + }, + { + "epoch": 3.78, + "learning_rate": 1.8704543916749682e-05, + "loss": 0.3564, + "step": 12234 + }, + { + "epoch": 3.78, + "learning_rate": 1.8704297723130253e-05, + "loss": 0.3589, + "step": 12235 + }, + { + "epoch": 3.78, + "learning_rate": 1.870405150773979e-05, + "loss": 0.345, + "step": 12236 + }, + { + "epoch": 3.78, + "learning_rate": 1.8703805270578904e-05, + "loss": 0.3621, + "step": 12237 + }, + { + "epoch": 3.78, + "learning_rate": 1.8703559011648217e-05, + "loss": 0.3618, + "step": 12238 + }, + { + "epoch": 3.78, + "learning_rate": 1.8703312730948336e-05, + "loss": 0.376, + "step": 12239 + }, + { + "epoch": 3.78, + "learning_rate": 1.8703066428479888e-05, + "loss": 0.3795, + "step": 12240 + }, + { + "epoch": 3.78, + "learning_rate": 1.8702820104243482e-05, + "loss": 0.3431, + "step": 12241 + }, + { + "epoch": 3.78, + "learning_rate": 1.8702573758239733e-05, + "loss": 0.3727, + "step": 12242 + }, + { + "epoch": 3.78, + "learning_rate": 1.8702327390469262e-05, + "loss": 0.3539, + "step": 12243 + }, + { + "epoch": 3.78, + "learning_rate": 1.870208100093268e-05, + "loss": 0.3781, + "step": 12244 + }, + { + "epoch": 3.78, + "learning_rate": 1.870183458963061e-05, + "loss": 0.3669, + "step": 12245 + }, + { + "epoch": 3.78, + "learning_rate": 1.8701588156563664e-05, + "loss": 0.3636, + "step": 12246 + }, + { + "epoch": 3.78, + "learning_rate": 1.8701341701732457e-05, + "loss": 0.3498, + "step": 12247 + }, + { + "epoch": 3.78, + "learning_rate": 1.870109522513761e-05, + "loss": 0.3444, + "step": 12248 + }, + { + "epoch": 3.78, + "learning_rate": 1.8700848726779734e-05, + "loss": 0.3744, + "step": 12249 + }, + { + "epoch": 3.78, + "learning_rate": 1.8700602206659448e-05, + "loss": 0.3447, + "step": 12250 + }, + { + "epoch": 3.78, + "learning_rate": 1.870035566477737e-05, + "loss": 0.402, + "step": 12251 + }, + { + "epoch": 3.78, + "learning_rate": 1.870010910113412e-05, + "loss": 0.3623, + "step": 12252 + }, + { + "epoch": 3.78, + "learning_rate": 1.8699862515730304e-05, + "loss": 0.3792, + "step": 12253 + }, + { + "epoch": 3.78, + "learning_rate": 1.8699615908566547e-05, + "loss": 0.3814, + "step": 12254 + }, + { + "epoch": 3.78, + "learning_rate": 1.8699369279643466e-05, + "loss": 0.3607, + "step": 12255 + }, + { + "epoch": 3.79, + "learning_rate": 1.8699122628961674e-05, + "loss": 0.3639, + "step": 12256 + }, + { + "epoch": 3.79, + "learning_rate": 1.869887595652179e-05, + "loss": 0.3622, + "step": 12257 + }, + { + "epoch": 3.79, + "learning_rate": 1.8698629262324434e-05, + "loss": 0.3579, + "step": 12258 + }, + { + "epoch": 3.79, + "learning_rate": 1.8698382546370215e-05, + "loss": 0.34, + "step": 12259 + }, + { + "epoch": 3.79, + "learning_rate": 1.8698135808659755e-05, + "loss": 0.3424, + "step": 12260 + }, + { + "epoch": 3.79, + "learning_rate": 1.8697889049193674e-05, + "loss": 0.3561, + "step": 12261 + }, + { + "epoch": 3.79, + "learning_rate": 1.8697642267972585e-05, + "loss": 0.3602, + "step": 12262 + }, + { + "epoch": 3.79, + "learning_rate": 1.8697395464997105e-05, + "loss": 0.3393, + "step": 12263 + }, + { + "epoch": 3.79, + "learning_rate": 1.8697148640267853e-05, + "loss": 0.3513, + "step": 12264 + }, + { + "epoch": 3.79, + "learning_rate": 1.8696901793785444e-05, + "loss": 0.3821, + "step": 12265 + }, + { + "epoch": 3.79, + "learning_rate": 1.86966549255505e-05, + "loss": 0.3646, + "step": 12266 + }, + { + "epoch": 3.79, + "learning_rate": 1.869640803556364e-05, + "loss": 0.3503, + "step": 12267 + }, + { + "epoch": 3.79, + "learning_rate": 1.8696161123825472e-05, + "loss": 0.3487, + "step": 12268 + }, + { + "epoch": 3.79, + "learning_rate": 1.8695914190336618e-05, + "loss": 0.3377, + "step": 12269 + }, + { + "epoch": 3.79, + "learning_rate": 1.86956672350977e-05, + "loss": 0.3304, + "step": 12270 + }, + { + "epoch": 3.79, + "learning_rate": 1.869542025810933e-05, + "loss": 0.3863, + "step": 12271 + }, + { + "epoch": 3.79, + "learning_rate": 1.8695173259372127e-05, + "loss": 0.3798, + "step": 12272 + }, + { + "epoch": 3.79, + "learning_rate": 1.8694926238886714e-05, + "loss": 0.346, + "step": 12273 + }, + { + "epoch": 3.79, + "learning_rate": 1.86946791966537e-05, + "loss": 0.3699, + "step": 12274 + }, + { + "epoch": 3.79, + "learning_rate": 1.869443213267371e-05, + "loss": 0.3485, + "step": 12275 + }, + { + "epoch": 3.79, + "learning_rate": 1.869418504694736e-05, + "loss": 0.3433, + "step": 12276 + }, + { + "epoch": 3.79, + "learning_rate": 1.8693937939475265e-05, + "loss": 0.3429, + "step": 12277 + }, + { + "epoch": 3.79, + "learning_rate": 1.8693690810258046e-05, + "loss": 0.3493, + "step": 12278 + }, + { + "epoch": 3.79, + "learning_rate": 1.869344365929632e-05, + "loss": 0.3371, + "step": 12279 + }, + { + "epoch": 3.79, + "learning_rate": 1.869319648659071e-05, + "loss": 0.3623, + "step": 12280 + }, + { + "epoch": 3.79, + "learning_rate": 1.8692949292141825e-05, + "loss": 0.3703, + "step": 12281 + }, + { + "epoch": 3.79, + "learning_rate": 1.8692702075950294e-05, + "loss": 0.3585, + "step": 12282 + }, + { + "epoch": 3.79, + "learning_rate": 1.8692454838016724e-05, + "loss": 0.3284, + "step": 12283 + }, + { + "epoch": 3.79, + "learning_rate": 1.8692207578341743e-05, + "loss": 0.343, + "step": 12284 + }, + { + "epoch": 3.79, + "learning_rate": 1.8691960296925967e-05, + "loss": 0.3462, + "step": 12285 + }, + { + "epoch": 3.79, + "learning_rate": 1.869171299377001e-05, + "loss": 0.3683, + "step": 12286 + }, + { + "epoch": 3.79, + "learning_rate": 1.869146566887449e-05, + "loss": 0.3431, + "step": 12287 + }, + { + "epoch": 3.79, + "learning_rate": 1.8691218322240035e-05, + "loss": 0.3804, + "step": 12288 + }, + { + "epoch": 3.8, + "learning_rate": 1.8690970953867254e-05, + "loss": 0.3636, + "step": 12289 + }, + { + "epoch": 3.8, + "learning_rate": 1.869072356375677e-05, + "loss": 0.3384, + "step": 12290 + }, + { + "epoch": 3.8, + "learning_rate": 1.8690476151909204e-05, + "loss": 0.3597, + "step": 12291 + }, + { + "epoch": 3.8, + "learning_rate": 1.869022871832517e-05, + "loss": 0.3805, + "step": 12292 + }, + { + "epoch": 3.8, + "learning_rate": 1.868998126300529e-05, + "loss": 0.3502, + "step": 12293 + }, + { + "epoch": 3.8, + "learning_rate": 1.868973378595018e-05, + "loss": 0.3506, + "step": 12294 + }, + { + "epoch": 3.8, + "learning_rate": 1.8689486287160462e-05, + "loss": 0.3407, + "step": 12295 + }, + { + "epoch": 3.8, + "learning_rate": 1.8689238766636755e-05, + "loss": 0.3423, + "step": 12296 + }, + { + "epoch": 3.8, + "learning_rate": 1.8688991224379677e-05, + "loss": 0.3523, + "step": 12297 + }, + { + "epoch": 3.8, + "learning_rate": 1.8688743660389844e-05, + "loss": 0.3442, + "step": 12298 + }, + { + "epoch": 3.8, + "learning_rate": 1.868849607466788e-05, + "loss": 0.3599, + "step": 12299 + }, + { + "epoch": 3.8, + "learning_rate": 1.868824846721441e-05, + "loss": 0.3714, + "step": 12300 + }, + { + "epoch": 3.8, + "learning_rate": 1.8688000838030035e-05, + "loss": 0.3199, + "step": 12301 + }, + { + "epoch": 3.8, + "learning_rate": 1.868775318711539e-05, + "loss": 0.3747, + "step": 12302 + }, + { + "epoch": 3.8, + "learning_rate": 1.868750551447109e-05, + "loss": 0.36, + "step": 12303 + }, + { + "epoch": 3.8, + "learning_rate": 1.8687257820097752e-05, + "loss": 0.3532, + "step": 12304 + }, + { + "epoch": 3.8, + "learning_rate": 1.8687010103995998e-05, + "loss": 0.3527, + "step": 12305 + }, + { + "epoch": 3.8, + "learning_rate": 1.868676236616645e-05, + "loss": 0.3449, + "step": 12306 + }, + { + "epoch": 3.8, + "learning_rate": 1.8686514606609726e-05, + "loss": 0.3282, + "step": 12307 + }, + { + "epoch": 3.8, + "learning_rate": 1.868626682532644e-05, + "loss": 0.3432, + "step": 12308 + }, + { + "epoch": 3.8, + "learning_rate": 1.868601902231722e-05, + "loss": 0.348, + "step": 12309 + }, + { + "epoch": 3.8, + "learning_rate": 1.868577119758268e-05, + "loss": 0.3552, + "step": 12310 + }, + { + "epoch": 3.8, + "learning_rate": 1.868552335112344e-05, + "loss": 0.3482, + "step": 12311 + }, + { + "epoch": 3.8, + "learning_rate": 1.8685275482940128e-05, + "loss": 0.3541, + "step": 12312 + }, + { + "epoch": 3.8, + "learning_rate": 1.8685027593033352e-05, + "loss": 0.3565, + "step": 12313 + }, + { + "epoch": 3.8, + "learning_rate": 1.8684779681403742e-05, + "loss": 0.3214, + "step": 12314 + }, + { + "epoch": 3.8, + "learning_rate": 1.868453174805191e-05, + "loss": 0.3541, + "step": 12315 + }, + { + "epoch": 3.8, + "learning_rate": 1.8684283792978486e-05, + "loss": 0.3483, + "step": 12316 + }, + { + "epoch": 3.8, + "learning_rate": 1.868403581618408e-05, + "loss": 0.3644, + "step": 12317 + }, + { + "epoch": 3.8, + "learning_rate": 1.868378781766932e-05, + "loss": 0.3485, + "step": 12318 + }, + { + "epoch": 3.8, + "learning_rate": 1.868353979743482e-05, + "loss": 0.3617, + "step": 12319 + }, + { + "epoch": 3.8, + "learning_rate": 1.8683291755481205e-05, + "loss": 0.343, + "step": 12320 + }, + { + "epoch": 3.81, + "learning_rate": 1.868304369180909e-05, + "loss": 0.3506, + "step": 12321 + }, + { + "epoch": 3.81, + "learning_rate": 1.8682795606419103e-05, + "loss": 0.345, + "step": 12322 + }, + { + "epoch": 3.81, + "learning_rate": 1.8682547499311856e-05, + "loss": 0.3471, + "step": 12323 + }, + { + "epoch": 3.81, + "learning_rate": 1.868229937048798e-05, + "loss": 0.3277, + "step": 12324 + }, + { + "epoch": 3.81, + "learning_rate": 1.8682051219948084e-05, + "loss": 0.3358, + "step": 12325 + }, + { + "epoch": 3.81, + "learning_rate": 1.86818030476928e-05, + "loss": 0.34, + "step": 12326 + }, + { + "epoch": 3.81, + "learning_rate": 1.8681554853722737e-05, + "loss": 0.3388, + "step": 12327 + }, + { + "epoch": 3.81, + "learning_rate": 1.8681306638038525e-05, + "loss": 0.3548, + "step": 12328 + }, + { + "epoch": 3.81, + "learning_rate": 1.8681058400640785e-05, + "loss": 0.352, + "step": 12329 + }, + { + "epoch": 3.81, + "learning_rate": 1.868081014153013e-05, + "loss": 0.3453, + "step": 12330 + }, + { + "epoch": 3.81, + "learning_rate": 1.8680561860707188e-05, + "loss": 0.331, + "step": 12331 + }, + { + "epoch": 3.81, + "learning_rate": 1.8680313558172574e-05, + "loss": 0.346, + "step": 12332 + }, + { + "epoch": 3.81, + "learning_rate": 1.8680065233926917e-05, + "loss": 0.3501, + "step": 12333 + }, + { + "epoch": 3.81, + "learning_rate": 1.867981688797083e-05, + "loss": 0.3319, + "step": 12334 + }, + { + "epoch": 3.81, + "learning_rate": 1.8679568520304942e-05, + "loss": 0.3383, + "step": 12335 + }, + { + "epoch": 3.81, + "learning_rate": 1.8679320130929864e-05, + "loss": 0.3638, + "step": 12336 + }, + { + "epoch": 3.81, + "learning_rate": 1.867907171984623e-05, + "loss": 0.3488, + "step": 12337 + }, + { + "epoch": 3.81, + "learning_rate": 1.867882328705465e-05, + "loss": 0.3494, + "step": 12338 + }, + { + "epoch": 3.81, + "learning_rate": 1.8678574832555755e-05, + "loss": 0.3493, + "step": 12339 + }, + { + "epoch": 3.81, + "learning_rate": 1.8678326356350157e-05, + "loss": 0.3813, + "step": 12340 + }, + { + "epoch": 3.81, + "learning_rate": 1.8678077858438483e-05, + "loss": 0.3414, + "step": 12341 + }, + { + "epoch": 3.81, + "learning_rate": 1.8677829338821353e-05, + "loss": 0.342, + "step": 12342 + }, + { + "epoch": 3.81, + "learning_rate": 1.867758079749939e-05, + "loss": 0.3522, + "step": 12343 + }, + { + "epoch": 3.81, + "learning_rate": 1.8677332234473217e-05, + "loss": 0.3352, + "step": 12344 + }, + { + "epoch": 3.81, + "learning_rate": 1.8677083649743447e-05, + "loss": 0.337, + "step": 12345 + }, + { + "epoch": 3.81, + "learning_rate": 1.8676835043310712e-05, + "loss": 0.3685, + "step": 12346 + }, + { + "epoch": 3.81, + "learning_rate": 1.8676586415175634e-05, + "loss": 0.334, + "step": 12347 + }, + { + "epoch": 3.81, + "learning_rate": 1.8676337765338822e-05, + "loss": 0.3421, + "step": 12348 + }, + { + "epoch": 3.81, + "learning_rate": 1.8676089093800915e-05, + "loss": 0.3689, + "step": 12349 + }, + { + "epoch": 3.81, + "learning_rate": 1.8675840400562522e-05, + "loss": 0.3286, + "step": 12350 + }, + { + "epoch": 3.81, + "learning_rate": 1.8675591685624273e-05, + "loss": 0.346, + "step": 12351 + }, + { + "epoch": 3.81, + "learning_rate": 1.8675342948986785e-05, + "loss": 0.3352, + "step": 12352 + }, + { + "epoch": 3.81, + "learning_rate": 1.867509419065068e-05, + "loss": 0.3464, + "step": 12353 + }, + { + "epoch": 3.82, + "learning_rate": 1.8674845410616588e-05, + "loss": 0.3364, + "step": 12354 + }, + { + "epoch": 3.82, + "learning_rate": 1.867459660888512e-05, + "loss": 0.3472, + "step": 12355 + }, + { + "epoch": 3.82, + "learning_rate": 1.8674347785456905e-05, + "loss": 0.346, + "step": 12356 + }, + { + "epoch": 3.82, + "learning_rate": 1.8674098940332565e-05, + "loss": 0.3891, + "step": 12357 + }, + { + "epoch": 3.82, + "learning_rate": 1.8673850073512723e-05, + "loss": 0.3334, + "step": 12358 + }, + { + "epoch": 3.82, + "learning_rate": 1.8673601184997996e-05, + "loss": 0.3434, + "step": 12359 + }, + { + "epoch": 3.82, + "learning_rate": 1.8673352274789013e-05, + "loss": 0.3524, + "step": 12360 + }, + { + "epoch": 3.82, + "learning_rate": 1.8673103342886395e-05, + "loss": 0.3402, + "step": 12361 + }, + { + "epoch": 3.82, + "learning_rate": 1.8672854389290762e-05, + "loss": 0.3518, + "step": 12362 + }, + { + "epoch": 3.82, + "learning_rate": 1.8672605414002737e-05, + "loss": 0.3352, + "step": 12363 + }, + { + "epoch": 3.82, + "learning_rate": 1.8672356417022947e-05, + "loss": 0.3447, + "step": 12364 + }, + { + "epoch": 3.82, + "learning_rate": 1.8672107398352012e-05, + "loss": 0.3247, + "step": 12365 + }, + { + "epoch": 3.82, + "learning_rate": 1.8671858357990552e-05, + "loss": 0.3549, + "step": 12366 + }, + { + "epoch": 3.82, + "learning_rate": 1.8671609295939194e-05, + "loss": 0.3448, + "step": 12367 + }, + { + "epoch": 3.82, + "learning_rate": 1.8671360212198558e-05, + "loss": 0.3382, + "step": 12368 + }, + { + "epoch": 3.82, + "learning_rate": 1.867111110676927e-05, + "loss": 0.3623, + "step": 12369 + }, + { + "epoch": 3.82, + "learning_rate": 1.867086197965195e-05, + "loss": 0.3262, + "step": 12370 + }, + { + "epoch": 3.82, + "learning_rate": 1.867061283084723e-05, + "loss": 0.3452, + "step": 12371 + }, + { + "epoch": 3.82, + "learning_rate": 1.867036366035572e-05, + "loss": 0.3302, + "step": 12372 + }, + { + "epoch": 3.82, + "learning_rate": 1.8670114468178045e-05, + "loss": 0.3325, + "step": 12373 + }, + { + "epoch": 3.82, + "learning_rate": 1.866986525431484e-05, + "loss": 0.3716, + "step": 12374 + }, + { + "epoch": 3.82, + "learning_rate": 1.8669616018766715e-05, + "loss": 0.3333, + "step": 12375 + }, + { + "epoch": 3.82, + "learning_rate": 1.8669366761534304e-05, + "loss": 0.3462, + "step": 12376 + }, + { + "epoch": 3.82, + "learning_rate": 1.8669117482618218e-05, + "loss": 0.3428, + "step": 12377 + }, + { + "epoch": 3.82, + "learning_rate": 1.8668868182019096e-05, + "loss": 0.3447, + "step": 12378 + }, + { + "epoch": 3.82, + "learning_rate": 1.866861885973755e-05, + "loss": 0.3417, + "step": 12379 + }, + { + "epoch": 3.82, + "learning_rate": 1.866836951577421e-05, + "loss": 0.3531, + "step": 12380 + }, + { + "epoch": 3.82, + "learning_rate": 1.8668120150129695e-05, + "loss": 0.3418, + "step": 12381 + }, + { + "epoch": 3.82, + "learning_rate": 1.866787076280463e-05, + "loss": 0.3517, + "step": 12382 + }, + { + "epoch": 3.82, + "learning_rate": 1.866762135379964e-05, + "loss": 0.3606, + "step": 12383 + }, + { + "epoch": 3.82, + "learning_rate": 1.8667371923115345e-05, + "loss": 0.3536, + "step": 12384 + }, + { + "epoch": 3.82, + "learning_rate": 1.8667122470752374e-05, + "loss": 0.338, + "step": 12385 + }, + { + "epoch": 3.83, + "learning_rate": 1.866687299671135e-05, + "loss": 0.3334, + "step": 12386 + }, + { + "epoch": 3.83, + "learning_rate": 1.8666623500992895e-05, + "loss": 0.3389, + "step": 12387 + }, + { + "epoch": 3.83, + "learning_rate": 1.8666373983597638e-05, + "loss": 0.3505, + "step": 12388 + }, + { + "epoch": 3.83, + "learning_rate": 1.8666124444526194e-05, + "loss": 0.3322, + "step": 12389 + }, + { + "epoch": 3.83, + "learning_rate": 1.866587488377919e-05, + "loss": 0.3437, + "step": 12390 + }, + { + "epoch": 3.83, + "learning_rate": 1.8665625301357258e-05, + "loss": 0.3421, + "step": 12391 + }, + { + "epoch": 3.83, + "learning_rate": 1.8665375697261016e-05, + "loss": 0.3452, + "step": 12392 + }, + { + "epoch": 3.83, + "learning_rate": 1.8665126071491088e-05, + "loss": 0.3153, + "step": 12393 + }, + { + "epoch": 3.83, + "learning_rate": 1.8664876424048098e-05, + "loss": 0.3443, + "step": 12394 + }, + { + "epoch": 3.83, + "learning_rate": 1.866462675493267e-05, + "loss": 0.333, + "step": 12395 + }, + { + "epoch": 3.83, + "learning_rate": 1.8664377064145433e-05, + "loss": 0.3319, + "step": 12396 + }, + { + "epoch": 3.83, + "learning_rate": 1.866412735168701e-05, + "loss": 0.3564, + "step": 12397 + }, + { + "epoch": 3.83, + "learning_rate": 1.866387761755802e-05, + "loss": 0.3248, + "step": 12398 + }, + { + "epoch": 3.83, + "learning_rate": 1.8663627861759095e-05, + "loss": 0.3374, + "step": 12399 + }, + { + "epoch": 3.83, + "learning_rate": 1.866337808429086e-05, + "loss": 0.3565, + "step": 12400 + }, + { + "epoch": 3.83, + "learning_rate": 1.866312828515393e-05, + "loss": 0.3399, + "step": 12401 + }, + { + "epoch": 3.83, + "learning_rate": 1.8662878464348937e-05, + "loss": 0.339, + "step": 12402 + }, + { + "epoch": 3.83, + "learning_rate": 1.8662628621876506e-05, + "loss": 0.3271, + "step": 12403 + }, + { + "epoch": 3.83, + "learning_rate": 1.866237875773726e-05, + "loss": 0.3247, + "step": 12404 + }, + { + "epoch": 3.83, + "learning_rate": 1.866212887193183e-05, + "loss": 0.3279, + "step": 12405 + }, + { + "epoch": 3.83, + "learning_rate": 1.866187896446083e-05, + "loss": 0.3296, + "step": 12406 + }, + { + "epoch": 3.83, + "learning_rate": 1.8661629035324893e-05, + "loss": 0.3541, + "step": 12407 + }, + { + "epoch": 3.83, + "learning_rate": 1.8661379084524642e-05, + "loss": 0.3551, + "step": 12408 + }, + { + "epoch": 3.83, + "learning_rate": 1.86611291120607e-05, + "loss": 0.3393, + "step": 12409 + }, + { + "epoch": 3.83, + "learning_rate": 1.8660879117933697e-05, + "loss": 0.3202, + "step": 12410 + }, + { + "epoch": 3.83, + "learning_rate": 1.8660629102144257e-05, + "loss": 0.362, + "step": 12411 + }, + { + "epoch": 3.83, + "learning_rate": 1.8660379064693003e-05, + "loss": 0.3505, + "step": 12412 + }, + { + "epoch": 3.83, + "learning_rate": 1.866012900558056e-05, + "loss": 0.3319, + "step": 12413 + }, + { + "epoch": 3.83, + "learning_rate": 1.8659878924807554e-05, + "loss": 0.3232, + "step": 12414 + }, + { + "epoch": 3.83, + "learning_rate": 1.8659628822374612e-05, + "loss": 0.3304, + "step": 12415 + }, + { + "epoch": 3.83, + "learning_rate": 1.865937869828236e-05, + "loss": 0.3488, + "step": 12416 + }, + { + "epoch": 3.83, + "learning_rate": 1.8659128552531422e-05, + "loss": 0.3539, + "step": 12417 + }, + { + "epoch": 3.84, + "learning_rate": 1.8658878385122423e-05, + "loss": 0.3427, + "step": 12418 + }, + { + "epoch": 3.84, + "learning_rate": 1.865862819605599e-05, + "loss": 0.3272, + "step": 12419 + }, + { + "epoch": 3.84, + "learning_rate": 1.865837798533275e-05, + "loss": 0.3257, + "step": 12420 + }, + { + "epoch": 3.84, + "learning_rate": 1.8658127752953327e-05, + "loss": 0.332, + "step": 12421 + }, + { + "epoch": 3.84, + "learning_rate": 1.8657877498918347e-05, + "loss": 0.3407, + "step": 12422 + }, + { + "epoch": 3.84, + "learning_rate": 1.8657627223228435e-05, + "loss": 0.3576, + "step": 12423 + }, + { + "epoch": 3.84, + "learning_rate": 1.8657376925884223e-05, + "loss": 0.3357, + "step": 12424 + }, + { + "epoch": 3.84, + "learning_rate": 1.865712660688633e-05, + "loss": 0.3029, + "step": 12425 + }, + { + "epoch": 3.84, + "learning_rate": 1.8656876266235383e-05, + "loss": 0.3309, + "step": 12426 + }, + { + "epoch": 3.84, + "learning_rate": 1.8656625903932008e-05, + "loss": 0.3148, + "step": 12427 + }, + { + "epoch": 3.84, + "learning_rate": 1.8656375519976838e-05, + "loss": 0.3299, + "step": 12428 + }, + { + "epoch": 3.84, + "learning_rate": 1.865612511437049e-05, + "loss": 0.336, + "step": 12429 + }, + { + "epoch": 3.84, + "learning_rate": 1.8655874687113592e-05, + "loss": 0.3415, + "step": 12430 + }, + { + "epoch": 3.84, + "learning_rate": 1.865562423820678e-05, + "loss": 0.3554, + "step": 12431 + }, + { + "epoch": 3.84, + "learning_rate": 1.8655373767650667e-05, + "loss": 0.3404, + "step": 12432 + }, + { + "epoch": 3.84, + "learning_rate": 1.865512327544589e-05, + "loss": 0.3347, + "step": 12433 + }, + { + "epoch": 3.84, + "learning_rate": 1.8654872761593066e-05, + "loss": 0.3307, + "step": 12434 + }, + { + "epoch": 3.84, + "learning_rate": 1.8654622226092832e-05, + "loss": 0.3182, + "step": 12435 + }, + { + "epoch": 3.84, + "learning_rate": 1.8654371668945804e-05, + "loss": 0.3139, + "step": 12436 + }, + { + "epoch": 3.84, + "learning_rate": 1.8654121090152616e-05, + "loss": 0.332, + "step": 12437 + }, + { + "epoch": 3.84, + "learning_rate": 1.8653870489713893e-05, + "loss": 0.3336, + "step": 12438 + }, + { + "epoch": 3.84, + "learning_rate": 1.8653619867630263e-05, + "loss": 0.333, + "step": 12439 + }, + { + "epoch": 3.84, + "learning_rate": 1.865336922390235e-05, + "loss": 0.3066, + "step": 12440 + }, + { + "epoch": 3.84, + "learning_rate": 1.8653118558530786e-05, + "loss": 0.3214, + "step": 12441 + }, + { + "epoch": 3.84, + "learning_rate": 1.865286787151619e-05, + "loss": 0.3305, + "step": 12442 + }, + { + "epoch": 3.84, + "learning_rate": 1.8652617162859192e-05, + "loss": 0.3347, + "step": 12443 + }, + { + "epoch": 3.84, + "learning_rate": 1.8652366432560422e-05, + "loss": 0.3252, + "step": 12444 + }, + { + "epoch": 3.84, + "learning_rate": 1.865211568062051e-05, + "loss": 0.3389, + "step": 12445 + }, + { + "epoch": 3.84, + "learning_rate": 1.8651864907040073e-05, + "loss": 0.3357, + "step": 12446 + }, + { + "epoch": 3.84, + "learning_rate": 1.8651614111819744e-05, + "loss": 0.3223, + "step": 12447 + }, + { + "epoch": 3.84, + "learning_rate": 1.8651363294960153e-05, + "loss": 0.3338, + "step": 12448 + }, + { + "epoch": 3.84, + "learning_rate": 1.8651112456461923e-05, + "loss": 0.3355, + "step": 12449 + }, + { + "epoch": 3.84, + "learning_rate": 1.865086159632568e-05, + "loss": 0.3104, + "step": 12450 + }, + { + "epoch": 3.85, + "learning_rate": 1.865061071455206e-05, + "loss": 0.3497, + "step": 12451 + }, + { + "epoch": 3.85, + "learning_rate": 1.865035981114168e-05, + "loss": 0.3432, + "step": 12452 + }, + { + "epoch": 3.85, + "learning_rate": 1.8650108886095174e-05, + "loss": 0.3111, + "step": 12453 + }, + { + "epoch": 3.85, + "learning_rate": 1.864985793941317e-05, + "loss": 0.3373, + "step": 12454 + }, + { + "epoch": 3.85, + "learning_rate": 1.8649606971096293e-05, + "loss": 0.3476, + "step": 12455 + }, + { + "epoch": 3.85, + "learning_rate": 1.864935598114517e-05, + "loss": 0.3122, + "step": 12456 + }, + { + "epoch": 3.85, + "learning_rate": 1.864910496956043e-05, + "loss": 0.3282, + "step": 12457 + }, + { + "epoch": 3.85, + "learning_rate": 1.8648853936342704e-05, + "loss": 0.3185, + "step": 12458 + }, + { + "epoch": 3.85, + "learning_rate": 1.864860288149261e-05, + "loss": 0.3248, + "step": 12459 + }, + { + "epoch": 3.85, + "learning_rate": 1.864835180501079e-05, + "loss": 0.3437, + "step": 12460 + }, + { + "epoch": 3.85, + "learning_rate": 1.864810070689786e-05, + "loss": 0.3481, + "step": 12461 + }, + { + "epoch": 3.85, + "learning_rate": 1.8647849587154456e-05, + "loss": 0.3382, + "step": 12462 + }, + { + "epoch": 3.85, + "learning_rate": 1.8647598445781204e-05, + "loss": 0.3649, + "step": 12463 + }, + { + "epoch": 3.85, + "learning_rate": 1.8647347282778726e-05, + "loss": 0.3383, + "step": 12464 + }, + { + "epoch": 3.85, + "learning_rate": 1.8647096098147658e-05, + "loss": 0.318, + "step": 12465 + }, + { + "epoch": 3.85, + "learning_rate": 1.8646844891888627e-05, + "loss": 0.3612, + "step": 12466 + }, + { + "epoch": 3.85, + "learning_rate": 1.864659366400226e-05, + "loss": 0.3439, + "step": 12467 + }, + { + "epoch": 3.85, + "learning_rate": 1.864634241448918e-05, + "loss": 0.3139, + "step": 12468 + }, + { + "epoch": 3.85, + "learning_rate": 1.8646091143350026e-05, + "loss": 0.3315, + "step": 12469 + }, + { + "epoch": 3.85, + "learning_rate": 1.864583985058542e-05, + "loss": 0.3361, + "step": 12470 + }, + { + "epoch": 3.85, + "learning_rate": 1.864558853619599e-05, + "loss": 0.3175, + "step": 12471 + }, + { + "epoch": 3.85, + "learning_rate": 1.864533720018237e-05, + "loss": 0.3443, + "step": 12472 + }, + { + "epoch": 3.85, + "learning_rate": 1.864508584254518e-05, + "loss": 0.3168, + "step": 12473 + }, + { + "epoch": 3.85, + "learning_rate": 1.8644834463285058e-05, + "loss": 0.336, + "step": 12474 + }, + { + "epoch": 3.85, + "learning_rate": 1.8644583062402623e-05, + "loss": 0.3342, + "step": 12475 + }, + { + "epoch": 3.85, + "learning_rate": 1.8644331639898513e-05, + "loss": 0.3241, + "step": 12476 + }, + { + "epoch": 3.85, + "learning_rate": 1.864408019577335e-05, + "loss": 0.3316, + "step": 12477 + }, + { + "epoch": 3.85, + "learning_rate": 1.864382873002777e-05, + "loss": 0.3421, + "step": 12478 + }, + { + "epoch": 3.85, + "learning_rate": 1.8643577242662396e-05, + "loss": 0.3446, + "step": 12479 + }, + { + "epoch": 3.85, + "learning_rate": 1.864332573367786e-05, + "loss": 0.3121, + "step": 12480 + }, + { + "epoch": 3.85, + "learning_rate": 1.8643074203074784e-05, + "loss": 0.3459, + "step": 12481 + }, + { + "epoch": 3.85, + "learning_rate": 1.8642822650853812e-05, + "loss": 0.3031, + "step": 12482 + }, + { + "epoch": 3.86, + "learning_rate": 1.8642571077015557e-05, + "loss": 0.3213, + "step": 12483 + }, + { + "epoch": 3.86, + "learning_rate": 1.8642319481560658e-05, + "loss": 0.3084, + "step": 12484 + }, + { + "epoch": 3.86, + "learning_rate": 1.8642067864489743e-05, + "loss": 0.3412, + "step": 12485 + }, + { + "epoch": 3.86, + "learning_rate": 1.8641816225803438e-05, + "loss": 0.3408, + "step": 12486 + }, + { + "epoch": 3.86, + "learning_rate": 1.8641564565502373e-05, + "loss": 0.3561, + "step": 12487 + }, + { + "epoch": 3.86, + "learning_rate": 1.8641312883587183e-05, + "loss": 0.338, + "step": 12488 + }, + { + "epoch": 3.86, + "learning_rate": 1.8641061180058493e-05, + "loss": 0.3298, + "step": 12489 + }, + { + "epoch": 3.86, + "learning_rate": 1.864080945491693e-05, + "loss": 0.348, + "step": 12490 + }, + { + "epoch": 3.86, + "learning_rate": 1.8640557708163127e-05, + "loss": 0.3238, + "step": 12491 + }, + { + "epoch": 3.86, + "learning_rate": 1.8640305939797714e-05, + "loss": 0.318, + "step": 12492 + }, + { + "epoch": 3.86, + "learning_rate": 1.864005414982132e-05, + "loss": 0.3378, + "step": 12493 + }, + { + "epoch": 3.86, + "learning_rate": 1.8639802338234577e-05, + "loss": 0.3153, + "step": 12494 + }, + { + "epoch": 3.86, + "learning_rate": 1.863955050503811e-05, + "loss": 0.3352, + "step": 12495 + }, + { + "epoch": 3.86, + "learning_rate": 1.863929865023255e-05, + "loss": 0.3386, + "step": 12496 + }, + { + "epoch": 3.86, + "learning_rate": 1.863904677381853e-05, + "loss": 0.3395, + "step": 12497 + }, + { + "epoch": 3.86, + "learning_rate": 1.863879487579668e-05, + "loss": 0.3232, + "step": 12498 + }, + { + "epoch": 3.86, + "learning_rate": 1.8638542956167626e-05, + "loss": 0.3363, + "step": 12499 + }, + { + "epoch": 3.86, + "learning_rate": 1.8638291014932004e-05, + "loss": 0.3525, + "step": 12500 + }, + { + "epoch": 3.86, + "learning_rate": 1.8638039052090436e-05, + "loss": 0.3204, + "step": 12501 + }, + { + "epoch": 3.86, + "learning_rate": 1.863778706764356e-05, + "loss": 0.3213, + "step": 12502 + }, + { + "epoch": 3.86, + "learning_rate": 1.8637535061592002e-05, + "loss": 0.3271, + "step": 12503 + }, + { + "epoch": 3.86, + "learning_rate": 1.8637283033936394e-05, + "loss": 0.3154, + "step": 12504 + }, + { + "epoch": 3.86, + "learning_rate": 1.8637030984677363e-05, + "loss": 0.3254, + "step": 12505 + }, + { + "epoch": 3.86, + "learning_rate": 1.8636778913815546e-05, + "loss": 0.3548, + "step": 12506 + }, + { + "epoch": 3.86, + "learning_rate": 1.863652682135157e-05, + "loss": 0.3243, + "step": 12507 + }, + { + "epoch": 3.86, + "learning_rate": 1.8636274707286062e-05, + "loss": 0.3296, + "step": 12508 + }, + { + "epoch": 3.86, + "learning_rate": 1.863602257161966e-05, + "loss": 0.3433, + "step": 12509 + }, + { + "epoch": 3.86, + "learning_rate": 1.8635770414352987e-05, + "loss": 0.3593, + "step": 12510 + }, + { + "epoch": 3.86, + "learning_rate": 1.863551823548668e-05, + "loss": 0.3165, + "step": 12511 + }, + { + "epoch": 3.86, + "learning_rate": 1.863526603502136e-05, + "loss": 0.3211, + "step": 12512 + }, + { + "epoch": 3.86, + "learning_rate": 1.8635013812957668e-05, + "loss": 0.3289, + "step": 12513 + }, + { + "epoch": 3.86, + "learning_rate": 1.8634761569296234e-05, + "loss": 0.3391, + "step": 12514 + }, + { + "epoch": 3.86, + "learning_rate": 1.8634509304037686e-05, + "loss": 0.3507, + "step": 12515 + }, + { + "epoch": 3.87, + "learning_rate": 1.8634257017182657e-05, + "loss": 0.3321, + "step": 12516 + }, + { + "epoch": 3.87, + "learning_rate": 1.8634004708731775e-05, + "loss": 0.3396, + "step": 12517 + }, + { + "epoch": 3.87, + "learning_rate": 1.863375237868567e-05, + "loss": 0.2984, + "step": 12518 + }, + { + "epoch": 3.87, + "learning_rate": 1.8633500027044976e-05, + "loss": 0.3288, + "step": 12519 + }, + { + "epoch": 3.87, + "learning_rate": 1.8633247653810327e-05, + "loss": 0.3152, + "step": 12520 + }, + { + "epoch": 3.87, + "learning_rate": 1.863299525898235e-05, + "loss": 0.3368, + "step": 12521 + }, + { + "epoch": 3.87, + "learning_rate": 1.8632742842561674e-05, + "loss": 0.331, + "step": 12522 + }, + { + "epoch": 3.87, + "learning_rate": 1.8632490404548937e-05, + "loss": 0.331, + "step": 12523 + }, + { + "epoch": 3.87, + "learning_rate": 1.8632237944944768e-05, + "loss": 0.3349, + "step": 12524 + }, + { + "epoch": 3.87, + "learning_rate": 1.8631985463749793e-05, + "loss": 0.3306, + "step": 12525 + }, + { + "epoch": 3.87, + "learning_rate": 1.863173296096465e-05, + "loss": 0.3167, + "step": 12526 + }, + { + "epoch": 3.87, + "learning_rate": 1.8631480436589968e-05, + "loss": 0.3367, + "step": 12527 + }, + { + "epoch": 3.87, + "learning_rate": 1.863122789062638e-05, + "loss": 0.3235, + "step": 12528 + }, + { + "epoch": 3.87, + "learning_rate": 1.8630975323074517e-05, + "loss": 0.3363, + "step": 12529 + }, + { + "epoch": 3.87, + "learning_rate": 1.8630722733935012e-05, + "loss": 0.3332, + "step": 12530 + }, + { + "epoch": 3.87, + "learning_rate": 1.8630470123208493e-05, + "loss": 0.3318, + "step": 12531 + }, + { + "epoch": 3.87, + "learning_rate": 1.8630217490895596e-05, + "loss": 0.3201, + "step": 12532 + }, + { + "epoch": 3.87, + "learning_rate": 1.862996483699695e-05, + "loss": 0.3158, + "step": 12533 + }, + { + "epoch": 3.87, + "learning_rate": 1.8629712161513186e-05, + "loss": 0.3444, + "step": 12534 + }, + { + "epoch": 3.87, + "learning_rate": 1.8629459464444943e-05, + "loss": 0.3497, + "step": 12535 + }, + { + "epoch": 3.87, + "learning_rate": 1.8629206745792843e-05, + "loss": 0.321, + "step": 12536 + }, + { + "epoch": 3.87, + "learning_rate": 1.8628954005557524e-05, + "loss": 0.3219, + "step": 12537 + }, + { + "epoch": 3.87, + "learning_rate": 1.862870124373962e-05, + "loss": 0.3247, + "step": 12538 + }, + { + "epoch": 3.87, + "learning_rate": 1.8628448460339758e-05, + "loss": 0.3253, + "step": 12539 + }, + { + "epoch": 3.87, + "learning_rate": 1.8628195655358572e-05, + "loss": 0.3279, + "step": 12540 + }, + { + "epoch": 3.87, + "learning_rate": 1.8627942828796697e-05, + "loss": 0.3241, + "step": 12541 + }, + { + "epoch": 3.87, + "learning_rate": 1.862768998065476e-05, + "loss": 0.3333, + "step": 12542 + }, + { + "epoch": 3.87, + "learning_rate": 1.86274371109334e-05, + "loss": 0.3376, + "step": 12543 + }, + { + "epoch": 3.87, + "learning_rate": 1.8627184219633244e-05, + "loss": 0.3354, + "step": 12544 + }, + { + "epoch": 3.87, + "learning_rate": 1.862693130675493e-05, + "loss": 0.3488, + "step": 12545 + }, + { + "epoch": 3.87, + "learning_rate": 1.8626678372299084e-05, + "loss": 0.3028, + "step": 12546 + }, + { + "epoch": 3.87, + "learning_rate": 1.8626425416266346e-05, + "loss": 0.3221, + "step": 12547 + }, + { + "epoch": 3.88, + "learning_rate": 1.862617243865734e-05, + "loss": 0.366, + "step": 12548 + }, + { + "epoch": 3.88, + "learning_rate": 1.8625919439472707e-05, + "loss": 0.3347, + "step": 12549 + }, + { + "epoch": 3.88, + "learning_rate": 1.8625666418713076e-05, + "loss": 0.3283, + "step": 12550 + }, + { + "epoch": 3.88, + "learning_rate": 1.862541337637908e-05, + "loss": 0.3131, + "step": 12551 + }, + { + "epoch": 3.88, + "learning_rate": 1.862516031247135e-05, + "loss": 0.3327, + "step": 12552 + }, + { + "epoch": 3.88, + "learning_rate": 1.862490722699052e-05, + "loss": 0.3162, + "step": 12553 + }, + { + "epoch": 3.88, + "learning_rate": 1.8624654119937228e-05, + "loss": 0.328, + "step": 12554 + }, + { + "epoch": 3.88, + "learning_rate": 1.86244009913121e-05, + "loss": 0.3467, + "step": 12555 + }, + { + "epoch": 3.88, + "learning_rate": 1.862414784111577e-05, + "loss": 0.3301, + "step": 12556 + }, + { + "epoch": 3.88, + "learning_rate": 1.8623894669348877e-05, + "loss": 0.3342, + "step": 12557 + }, + { + "epoch": 3.88, + "learning_rate": 1.862364147601205e-05, + "loss": 0.3327, + "step": 12558 + }, + { + "epoch": 3.88, + "learning_rate": 1.8623388261105925e-05, + "loss": 0.3187, + "step": 12559 + }, + { + "epoch": 3.88, + "learning_rate": 1.862313502463113e-05, + "loss": 0.3249, + "step": 12560 + }, + { + "epoch": 3.88, + "learning_rate": 1.86228817665883e-05, + "loss": 0.3235, + "step": 12561 + }, + { + "epoch": 3.88, + "learning_rate": 1.8622628486978073e-05, + "loss": 0.3054, + "step": 12562 + }, + { + "epoch": 3.88, + "learning_rate": 1.862237518580108e-05, + "loss": 0.3133, + "step": 12563 + }, + { + "epoch": 3.88, + "learning_rate": 1.862212186305795e-05, + "loss": 0.3388, + "step": 12564 + }, + { + "epoch": 3.88, + "learning_rate": 1.8621868518749324e-05, + "loss": 0.313, + "step": 12565 + }, + { + "epoch": 3.88, + "learning_rate": 1.8621615152875833e-05, + "loss": 0.3239, + "step": 12566 + }, + { + "epoch": 3.88, + "learning_rate": 1.8621361765438105e-05, + "loss": 0.3632, + "step": 12567 + }, + { + "epoch": 3.88, + "learning_rate": 1.8621108356436782e-05, + "loss": 0.3401, + "step": 12568 + }, + { + "epoch": 3.88, + "learning_rate": 1.8620854925872498e-05, + "loss": 0.3145, + "step": 12569 + }, + { + "epoch": 3.88, + "learning_rate": 1.8620601473745882e-05, + "loss": 0.3459, + "step": 12570 + }, + { + "epoch": 3.88, + "learning_rate": 1.8620348000057568e-05, + "loss": 0.3205, + "step": 12571 + }, + { + "epoch": 3.88, + "learning_rate": 1.862009450480819e-05, + "loss": 0.327, + "step": 12572 + }, + { + "epoch": 3.88, + "learning_rate": 1.8619840987998383e-05, + "loss": 0.3472, + "step": 12573 + }, + { + "epoch": 3.88, + "learning_rate": 1.8619587449628783e-05, + "loss": 0.326, + "step": 12574 + }, + { + "epoch": 3.88, + "learning_rate": 1.8619333889700023e-05, + "loss": 0.3212, + "step": 12575 + }, + { + "epoch": 3.88, + "learning_rate": 1.861908030821274e-05, + "loss": 0.3333, + "step": 12576 + }, + { + "epoch": 3.88, + "learning_rate": 1.861882670516756e-05, + "loss": 0.3087, + "step": 12577 + }, + { + "epoch": 3.88, + "learning_rate": 1.8618573080565127e-05, + "loss": 0.3141, + "step": 12578 + }, + { + "epoch": 3.88, + "learning_rate": 1.8618319434406068e-05, + "loss": 0.3445, + "step": 12579 + }, + { + "epoch": 3.89, + "learning_rate": 1.8618065766691016e-05, + "loss": 0.3249, + "step": 12580 + }, + { + "epoch": 3.89, + "learning_rate": 1.8617812077420617e-05, + "loss": 0.3137, + "step": 12581 + }, + { + "epoch": 3.89, + "learning_rate": 1.8617558366595495e-05, + "loss": 0.331, + "step": 12582 + }, + { + "epoch": 3.89, + "learning_rate": 1.8617304634216288e-05, + "loss": 0.3243, + "step": 12583 + }, + { + "epoch": 3.89, + "learning_rate": 1.861705088028363e-05, + "loss": 0.3263, + "step": 12584 + }, + { + "epoch": 3.89, + "learning_rate": 1.8616797104798158e-05, + "loss": 0.3195, + "step": 12585 + }, + { + "epoch": 3.89, + "learning_rate": 1.8616543307760502e-05, + "loss": 0.3336, + "step": 12586 + }, + { + "epoch": 3.89, + "learning_rate": 1.8616289489171298e-05, + "loss": 0.3173, + "step": 12587 + }, + { + "epoch": 3.89, + "learning_rate": 1.8616035649031188e-05, + "loss": 0.3199, + "step": 12588 + }, + { + "epoch": 3.89, + "learning_rate": 1.8615781787340798e-05, + "loss": 0.3332, + "step": 12589 + }, + { + "epoch": 3.89, + "learning_rate": 1.8615527904100768e-05, + "loss": 0.337, + "step": 12590 + }, + { + "epoch": 3.89, + "learning_rate": 1.861527399931173e-05, + "loss": 0.3174, + "step": 12591 + }, + { + "epoch": 3.89, + "learning_rate": 1.8615020072974323e-05, + "loss": 0.3451, + "step": 12592 + }, + { + "epoch": 3.89, + "learning_rate": 1.8614766125089176e-05, + "loss": 0.3273, + "step": 12593 + }, + { + "epoch": 3.89, + "learning_rate": 1.861451215565693e-05, + "loss": 0.3388, + "step": 12594 + }, + { + "epoch": 3.89, + "learning_rate": 1.8614258164678215e-05, + "loss": 0.3238, + "step": 12595 + }, + { + "epoch": 3.89, + "learning_rate": 1.8614004152153673e-05, + "loss": 0.3429, + "step": 12596 + }, + { + "epoch": 3.89, + "learning_rate": 1.8613750118083933e-05, + "loss": 0.3422, + "step": 12597 + }, + { + "epoch": 3.89, + "learning_rate": 1.8613496062469635e-05, + "loss": 0.308, + "step": 12598 + }, + { + "epoch": 3.89, + "learning_rate": 1.8613241985311413e-05, + "loss": 0.308, + "step": 12599 + }, + { + "epoch": 3.89, + "learning_rate": 1.8612987886609898e-05, + "loss": 0.3253, + "step": 12600 + }, + { + "epoch": 3.89, + "learning_rate": 1.861273376636573e-05, + "loss": 0.3168, + "step": 12601 + }, + { + "epoch": 3.89, + "learning_rate": 1.8612479624579545e-05, + "loss": 0.3222, + "step": 12602 + }, + { + "epoch": 3.89, + "learning_rate": 1.8612225461251977e-05, + "loss": 0.3133, + "step": 12603 + }, + { + "epoch": 3.89, + "learning_rate": 1.8611971276383664e-05, + "loss": 0.3401, + "step": 12604 + }, + { + "epoch": 3.89, + "learning_rate": 1.8611717069975238e-05, + "loss": 0.3365, + "step": 12605 + }, + { + "epoch": 3.89, + "learning_rate": 1.861146284202734e-05, + "loss": 0.3268, + "step": 12606 + }, + { + "epoch": 3.89, + "learning_rate": 1.86112085925406e-05, + "loss": 0.3299, + "step": 12607 + }, + { + "epoch": 3.89, + "learning_rate": 1.861095432151566e-05, + "loss": 0.3338, + "step": 12608 + }, + { + "epoch": 3.89, + "learning_rate": 1.861070002895315e-05, + "loss": 0.3271, + "step": 12609 + }, + { + "epoch": 3.89, + "learning_rate": 1.861044571485371e-05, + "loss": 0.298, + "step": 12610 + }, + { + "epoch": 3.89, + "learning_rate": 1.861019137921797e-05, + "loss": 0.331, + "step": 12611 + }, + { + "epoch": 3.89, + "learning_rate": 1.8609937022046578e-05, + "loss": 0.3482, + "step": 12612 + }, + { + "epoch": 3.9, + "learning_rate": 1.8609682643340158e-05, + "loss": 0.3418, + "step": 12613 + }, + { + "epoch": 3.9, + "learning_rate": 1.8609428243099355e-05, + "loss": 0.3216, + "step": 12614 + }, + { + "epoch": 3.9, + "learning_rate": 1.8609173821324804e-05, + "loss": 0.3228, + "step": 12615 + }, + { + "epoch": 3.9, + "learning_rate": 1.8608919378017133e-05, + "loss": 0.3127, + "step": 12616 + }, + { + "epoch": 3.9, + "learning_rate": 1.8608664913176986e-05, + "loss": 0.3393, + "step": 12617 + }, + { + "epoch": 3.9, + "learning_rate": 1.8608410426804998e-05, + "loss": 0.3342, + "step": 12618 + }, + { + "epoch": 3.9, + "learning_rate": 1.860815591890181e-05, + "loss": 0.3157, + "step": 12619 + }, + { + "epoch": 3.9, + "learning_rate": 1.8607901389468048e-05, + "loss": 0.3436, + "step": 12620 + }, + { + "epoch": 3.9, + "learning_rate": 1.8607646838504356e-05, + "loss": 0.3161, + "step": 12621 + }, + { + "epoch": 3.9, + "learning_rate": 1.860739226601137e-05, + "loss": 0.3335, + "step": 12622 + }, + { + "epoch": 3.9, + "learning_rate": 1.8607137671989724e-05, + "loss": 0.3122, + "step": 12623 + }, + { + "epoch": 3.9, + "learning_rate": 1.860688305644006e-05, + "loss": 0.3136, + "step": 12624 + }, + { + "epoch": 3.9, + "learning_rate": 1.8606628419363013e-05, + "loss": 0.3216, + "step": 12625 + }, + { + "epoch": 3.9, + "learning_rate": 1.8606373760759214e-05, + "loss": 0.3004, + "step": 12626 + }, + { + "epoch": 3.9, + "learning_rate": 1.8606119080629307e-05, + "loss": 0.3178, + "step": 12627 + }, + { + "epoch": 3.9, + "learning_rate": 1.8605864378973927e-05, + "loss": 0.3306, + "step": 12628 + }, + { + "epoch": 3.9, + "learning_rate": 1.860560965579371e-05, + "loss": 0.3219, + "step": 12629 + }, + { + "epoch": 3.9, + "learning_rate": 1.8605354911089293e-05, + "loss": 0.3015, + "step": 12630 + }, + { + "epoch": 3.9, + "learning_rate": 1.8605100144861315e-05, + "loss": 0.318, + "step": 12631 + }, + { + "epoch": 3.9, + "learning_rate": 1.860484535711041e-05, + "loss": 0.3144, + "step": 12632 + }, + { + "epoch": 3.9, + "learning_rate": 1.860459054783722e-05, + "loss": 0.3403, + "step": 12633 + }, + { + "epoch": 3.9, + "learning_rate": 1.860433571704238e-05, + "loss": 0.3042, + "step": 12634 + }, + { + "epoch": 3.9, + "learning_rate": 1.8604080864726523e-05, + "loss": 0.3276, + "step": 12635 + }, + { + "epoch": 3.9, + "learning_rate": 1.8603825990890297e-05, + "loss": 0.3051, + "step": 12636 + }, + { + "epoch": 3.9, + "learning_rate": 1.860357109553433e-05, + "loss": 0.3254, + "step": 12637 + }, + { + "epoch": 3.9, + "learning_rate": 1.8603316178659258e-05, + "loss": 0.3334, + "step": 12638 + }, + { + "epoch": 3.9, + "learning_rate": 1.860306124026573e-05, + "loss": 0.3399, + "step": 12639 + }, + { + "epoch": 3.9, + "learning_rate": 1.860280628035437e-05, + "loss": 0.3163, + "step": 12640 + }, + { + "epoch": 3.9, + "learning_rate": 1.8602551298925825e-05, + "loss": 0.3374, + "step": 12641 + }, + { + "epoch": 3.9, + "learning_rate": 1.8602296295980734e-05, + "loss": 0.3205, + "step": 12642 + }, + { + "epoch": 3.9, + "learning_rate": 1.8602041271519726e-05, + "loss": 0.3015, + "step": 12643 + }, + { + "epoch": 3.9, + "learning_rate": 1.8601786225543444e-05, + "loss": 0.3424, + "step": 12644 + }, + { + "epoch": 3.91, + "learning_rate": 1.860153115805253e-05, + "loss": 0.3204, + "step": 12645 + }, + { + "epoch": 3.91, + "learning_rate": 1.8601276069047614e-05, + "loss": 0.3098, + "step": 12646 + }, + { + "epoch": 3.91, + "learning_rate": 1.860102095852934e-05, + "loss": 0.3291, + "step": 12647 + }, + { + "epoch": 3.91, + "learning_rate": 1.8600765826498342e-05, + "loss": 0.3065, + "step": 12648 + }, + { + "epoch": 3.91, + "learning_rate": 1.8600510672955262e-05, + "loss": 0.3286, + "step": 12649 + }, + { + "epoch": 3.91, + "learning_rate": 1.8600255497900734e-05, + "loss": 0.3318, + "step": 12650 + }, + { + "epoch": 3.91, + "learning_rate": 1.86000003013354e-05, + "loss": 0.3326, + "step": 12651 + }, + { + "epoch": 3.91, + "learning_rate": 1.8599745083259897e-05, + "loss": 0.3373, + "step": 12652 + }, + { + "epoch": 3.91, + "learning_rate": 1.8599489843674862e-05, + "loss": 0.3286, + "step": 12653 + }, + { + "epoch": 3.91, + "learning_rate": 1.8599234582580932e-05, + "loss": 0.3263, + "step": 12654 + }, + { + "epoch": 3.91, + "learning_rate": 1.8598979299978753e-05, + "loss": 0.332, + "step": 12655 + }, + { + "epoch": 3.91, + "learning_rate": 1.8598723995868954e-05, + "loss": 0.3174, + "step": 12656 + }, + { + "epoch": 3.91, + "learning_rate": 1.859846867025218e-05, + "loss": 0.3334, + "step": 12657 + }, + { + "epoch": 3.91, + "learning_rate": 1.859821332312907e-05, + "loss": 0.3321, + "step": 12658 + }, + { + "epoch": 3.91, + "learning_rate": 1.8597957954500255e-05, + "loss": 0.3461, + "step": 12659 + }, + { + "epoch": 3.91, + "learning_rate": 1.8597702564366386e-05, + "loss": 0.3248, + "step": 12660 + }, + { + "epoch": 3.91, + "learning_rate": 1.859744715272809e-05, + "loss": 0.3195, + "step": 12661 + }, + { + "epoch": 3.91, + "learning_rate": 1.859719171958601e-05, + "loss": 0.3327, + "step": 12662 + }, + { + "epoch": 3.91, + "learning_rate": 1.8596936264940786e-05, + "loss": 0.3369, + "step": 12663 + }, + { + "epoch": 3.91, + "learning_rate": 1.859668078879306e-05, + "loss": 0.3302, + "step": 12664 + }, + { + "epoch": 3.91, + "learning_rate": 1.8596425291143464e-05, + "loss": 0.3111, + "step": 12665 + }, + { + "epoch": 3.91, + "learning_rate": 1.8596169771992637e-05, + "loss": 0.3126, + "step": 12666 + }, + { + "epoch": 3.91, + "learning_rate": 1.8595914231341226e-05, + "loss": 0.318, + "step": 12667 + }, + { + "epoch": 3.91, + "learning_rate": 1.8595658669189866e-05, + "loss": 0.347, + "step": 12668 + }, + { + "epoch": 3.91, + "learning_rate": 1.8595403085539197e-05, + "loss": 0.3366, + "step": 12669 + }, + { + "epoch": 3.91, + "learning_rate": 1.8595147480389853e-05, + "loss": 0.305, + "step": 12670 + }, + { + "epoch": 3.91, + "learning_rate": 1.859489185374248e-05, + "loss": 0.3238, + "step": 12671 + }, + { + "epoch": 3.91, + "learning_rate": 1.8594636205597717e-05, + "loss": 0.3288, + "step": 12672 + }, + { + "epoch": 3.91, + "learning_rate": 1.85943805359562e-05, + "loss": 0.3216, + "step": 12673 + }, + { + "epoch": 3.91, + "learning_rate": 1.8594124844818567e-05, + "loss": 0.3219, + "step": 12674 + }, + { + "epoch": 3.91, + "learning_rate": 1.859386913218546e-05, + "loss": 0.3262, + "step": 12675 + }, + { + "epoch": 3.91, + "learning_rate": 1.8593613398057523e-05, + "loss": 0.3176, + "step": 12676 + }, + { + "epoch": 3.92, + "learning_rate": 1.859335764243539e-05, + "loss": 0.3255, + "step": 12677 + }, + { + "epoch": 3.92, + "learning_rate": 1.8593101865319703e-05, + "loss": 0.3204, + "step": 12678 + }, + { + "epoch": 3.92, + "learning_rate": 1.8592846066711097e-05, + "loss": 0.3248, + "step": 12679 + }, + { + "epoch": 3.92, + "learning_rate": 1.859259024661022e-05, + "loss": 0.3172, + "step": 12680 + }, + { + "epoch": 3.92, + "learning_rate": 1.8592334405017706e-05, + "loss": 0.328, + "step": 12681 + }, + { + "epoch": 3.92, + "learning_rate": 1.8592078541934195e-05, + "loss": 0.3314, + "step": 12682 + }, + { + "epoch": 3.92, + "learning_rate": 1.859182265736033e-05, + "loss": 0.3142, + "step": 12683 + }, + { + "epoch": 3.92, + "learning_rate": 1.859156675129675e-05, + "loss": 0.3421, + "step": 12684 + }, + { + "epoch": 3.92, + "learning_rate": 1.859131082374409e-05, + "loss": 0.3149, + "step": 12685 + }, + { + "epoch": 3.92, + "learning_rate": 1.8591054874703003e-05, + "loss": 0.3146, + "step": 12686 + }, + { + "epoch": 3.92, + "learning_rate": 1.8590798904174115e-05, + "loss": 0.3314, + "step": 12687 + }, + { + "epoch": 3.92, + "learning_rate": 1.8590542912158074e-05, + "loss": 0.3292, + "step": 12688 + }, + { + "epoch": 3.92, + "learning_rate": 1.8590286898655518e-05, + "loss": 0.3334, + "step": 12689 + }, + { + "epoch": 3.92, + "learning_rate": 1.8590030863667087e-05, + "loss": 0.3199, + "step": 12690 + }, + { + "epoch": 3.92, + "learning_rate": 1.8589774807193425e-05, + "loss": 0.3223, + "step": 12691 + }, + { + "epoch": 3.92, + "learning_rate": 1.8589518729235165e-05, + "loss": 0.3314, + "step": 12692 + }, + { + "epoch": 3.92, + "learning_rate": 1.8589262629792955e-05, + "loss": 0.3206, + "step": 12693 + }, + { + "epoch": 3.92, + "learning_rate": 1.858900650886743e-05, + "loss": 0.3078, + "step": 12694 + }, + { + "epoch": 3.92, + "learning_rate": 1.8588750366459237e-05, + "loss": 0.3298, + "step": 12695 + }, + { + "epoch": 3.92, + "learning_rate": 1.858849420256901e-05, + "loss": 0.3003, + "step": 12696 + }, + { + "epoch": 3.92, + "learning_rate": 1.8588238017197395e-05, + "loss": 0.3141, + "step": 12697 + }, + { + "epoch": 3.92, + "learning_rate": 1.8587981810345027e-05, + "loss": 0.3269, + "step": 12698 + }, + { + "epoch": 3.92, + "learning_rate": 1.8587725582012554e-05, + "loss": 0.3106, + "step": 12699 + }, + { + "epoch": 3.92, + "learning_rate": 1.858746933220061e-05, + "loss": 0.3246, + "step": 12700 + }, + { + "epoch": 3.92, + "learning_rate": 1.858721306090984e-05, + "loss": 0.3189, + "step": 12701 + }, + { + "epoch": 3.92, + "learning_rate": 1.858695676814088e-05, + "loss": 0.3299, + "step": 12702 + }, + { + "epoch": 3.92, + "learning_rate": 1.858670045389438e-05, + "loss": 0.3234, + "step": 12703 + }, + { + "epoch": 3.92, + "learning_rate": 1.8586444118170975e-05, + "loss": 0.3169, + "step": 12704 + }, + { + "epoch": 3.92, + "learning_rate": 1.858618776097131e-05, + "loss": 0.3362, + "step": 12705 + }, + { + "epoch": 3.92, + "learning_rate": 1.8585931382296018e-05, + "loss": 0.2946, + "step": 12706 + }, + { + "epoch": 3.92, + "learning_rate": 1.858567498214575e-05, + "loss": 0.3174, + "step": 12707 + }, + { + "epoch": 3.92, + "learning_rate": 1.858541856052114e-05, + "loss": 0.3045, + "step": 12708 + }, + { + "epoch": 3.92, + "learning_rate": 1.858516211742283e-05, + "loss": 0.3311, + "step": 12709 + }, + { + "epoch": 3.93, + "learning_rate": 1.858490565285147e-05, + "loss": 0.33, + "step": 12710 + }, + { + "epoch": 3.93, + "learning_rate": 1.8584649166807695e-05, + "loss": 0.3008, + "step": 12711 + }, + { + "epoch": 3.93, + "learning_rate": 1.8584392659292143e-05, + "loss": 0.3191, + "step": 12712 + }, + { + "epoch": 3.93, + "learning_rate": 1.8584136130305457e-05, + "loss": 0.3246, + "step": 12713 + }, + { + "epoch": 3.93, + "learning_rate": 1.8583879579848285e-05, + "loss": 0.3059, + "step": 12714 + }, + { + "epoch": 3.93, + "learning_rate": 1.8583623007921265e-05, + "loss": 0.3223, + "step": 12715 + }, + { + "epoch": 3.93, + "learning_rate": 1.8583366414525035e-05, + "loss": 0.316, + "step": 12716 + }, + { + "epoch": 3.93, + "learning_rate": 1.858310979966024e-05, + "loss": 0.3152, + "step": 12717 + }, + { + "epoch": 3.93, + "learning_rate": 1.8582853163327525e-05, + "loss": 0.3046, + "step": 12718 + }, + { + "epoch": 3.93, + "learning_rate": 1.8582596505527528e-05, + "loss": 0.3117, + "step": 12719 + }, + { + "epoch": 3.93, + "learning_rate": 1.858233982626089e-05, + "loss": 0.32, + "step": 12720 + }, + { + "epoch": 3.93, + "learning_rate": 1.858208312552826e-05, + "loss": 0.3166, + "step": 12721 + }, + { + "epoch": 3.93, + "learning_rate": 1.858182640333027e-05, + "loss": 0.3429, + "step": 12722 + }, + { + "epoch": 3.93, + "learning_rate": 1.8581569659667566e-05, + "loss": 0.3189, + "step": 12723 + }, + { + "epoch": 3.93, + "learning_rate": 1.8581312894540793e-05, + "loss": 0.3025, + "step": 12724 + }, + { + "epoch": 3.93, + "learning_rate": 1.8581056107950592e-05, + "loss": 0.319, + "step": 12725 + }, + { + "epoch": 3.93, + "learning_rate": 1.8580799299897606e-05, + "loss": 0.3236, + "step": 12726 + }, + { + "epoch": 3.93, + "learning_rate": 1.8580542470382472e-05, + "loss": 0.335, + "step": 12727 + }, + { + "epoch": 3.93, + "learning_rate": 1.858028561940584e-05, + "loss": 0.313, + "step": 12728 + }, + { + "epoch": 3.93, + "learning_rate": 1.8580028746968346e-05, + "loss": 0.3203, + "step": 12729 + }, + { + "epoch": 3.93, + "learning_rate": 1.8579771853070637e-05, + "loss": 0.3045, + "step": 12730 + }, + { + "epoch": 3.93, + "learning_rate": 1.857951493771335e-05, + "loss": 0.2994, + "step": 12731 + }, + { + "epoch": 3.93, + "learning_rate": 1.8579258000897135e-05, + "loss": 0.3142, + "step": 12732 + }, + { + "epoch": 3.93, + "learning_rate": 1.8579001042622632e-05, + "loss": 0.307, + "step": 12733 + }, + { + "epoch": 3.93, + "learning_rate": 1.8578744062890478e-05, + "loss": 0.3329, + "step": 12734 + }, + { + "epoch": 3.93, + "learning_rate": 1.8578487061701325e-05, + "loss": 0.3146, + "step": 12735 + }, + { + "epoch": 3.93, + "learning_rate": 1.857823003905581e-05, + "loss": 0.3095, + "step": 12736 + }, + { + "epoch": 3.93, + "learning_rate": 1.8577972994954577e-05, + "loss": 0.3042, + "step": 12737 + }, + { + "epoch": 3.93, + "learning_rate": 1.857771592939827e-05, + "loss": 0.3245, + "step": 12738 + }, + { + "epoch": 3.93, + "learning_rate": 1.857745884238753e-05, + "loss": 0.3294, + "step": 12739 + }, + { + "epoch": 3.93, + "learning_rate": 1.8577201733922998e-05, + "loss": 0.2984, + "step": 12740 + }, + { + "epoch": 3.93, + "learning_rate": 1.8576944604005322e-05, + "loss": 0.3214, + "step": 12741 + }, + { + "epoch": 3.94, + "learning_rate": 1.8576687452635144e-05, + "loss": 0.3214, + "step": 12742 + }, + { + "epoch": 3.94, + "learning_rate": 1.857643027981311e-05, + "loss": 0.3077, + "step": 12743 + }, + { + "epoch": 3.94, + "learning_rate": 1.857617308553985e-05, + "loss": 0.3228, + "step": 12744 + }, + { + "epoch": 3.94, + "learning_rate": 1.8575915869816027e-05, + "loss": 0.3548, + "step": 12745 + }, + { + "epoch": 3.94, + "learning_rate": 1.857565863264227e-05, + "loss": 0.3134, + "step": 12746 + }, + { + "epoch": 3.94, + "learning_rate": 1.8575401374019227e-05, + "loss": 0.3263, + "step": 12747 + }, + { + "epoch": 3.94, + "learning_rate": 1.857514409394754e-05, + "loss": 0.3244, + "step": 12748 + }, + { + "epoch": 3.94, + "learning_rate": 1.8574886792427853e-05, + "loss": 0.3145, + "step": 12749 + }, + { + "epoch": 3.94, + "learning_rate": 1.857462946946081e-05, + "loss": 0.334, + "step": 12750 + }, + { + "epoch": 3.94, + "learning_rate": 1.857437212504706e-05, + "loss": 0.3174, + "step": 12751 + }, + { + "epoch": 3.94, + "learning_rate": 1.8574114759187235e-05, + "loss": 0.3188, + "step": 12752 + }, + { + "epoch": 3.94, + "learning_rate": 1.857385737188199e-05, + "loss": 0.3166, + "step": 12753 + }, + { + "epoch": 3.94, + "learning_rate": 1.8573599963131964e-05, + "loss": 0.3521, + "step": 12754 + }, + { + "epoch": 3.94, + "learning_rate": 1.8573342532937798e-05, + "loss": 0.3047, + "step": 12755 + }, + { + "epoch": 3.94, + "learning_rate": 1.857308508130014e-05, + "loss": 0.3232, + "step": 12756 + }, + { + "epoch": 3.94, + "learning_rate": 1.857282760821963e-05, + "loss": 0.3264, + "step": 12757 + }, + { + "epoch": 3.94, + "learning_rate": 1.8572570113696918e-05, + "loss": 0.3375, + "step": 12758 + }, + { + "epoch": 3.94, + "learning_rate": 1.8572312597732643e-05, + "loss": 0.3207, + "step": 12759 + }, + { + "epoch": 3.94, + "learning_rate": 1.857205506032745e-05, + "loss": 0.3391, + "step": 12760 + }, + { + "epoch": 3.94, + "learning_rate": 1.8571797501481983e-05, + "loss": 0.3142, + "step": 12761 + }, + { + "epoch": 3.94, + "learning_rate": 1.857153992119689e-05, + "loss": 0.3346, + "step": 12762 + }, + { + "epoch": 3.94, + "learning_rate": 1.8571282319472808e-05, + "loss": 0.3157, + "step": 12763 + }, + { + "epoch": 3.94, + "learning_rate": 1.857102469631039e-05, + "loss": 0.319, + "step": 12764 + }, + { + "epoch": 3.94, + "learning_rate": 1.8570767051710275e-05, + "loss": 0.325, + "step": 12765 + }, + { + "epoch": 3.94, + "learning_rate": 1.8570509385673107e-05, + "loss": 0.3085, + "step": 12766 + }, + { + "epoch": 3.94, + "learning_rate": 1.8570251698199535e-05, + "loss": 0.3336, + "step": 12767 + }, + { + "epoch": 3.94, + "learning_rate": 1.8569993989290197e-05, + "loss": 0.3308, + "step": 12768 + }, + { + "epoch": 3.94, + "learning_rate": 1.8569736258945742e-05, + "loss": 0.3097, + "step": 12769 + }, + { + "epoch": 3.94, + "learning_rate": 1.8569478507166817e-05, + "loss": 0.3215, + "step": 12770 + }, + { + "epoch": 3.94, + "learning_rate": 1.856922073395406e-05, + "loss": 0.3314, + "step": 12771 + }, + { + "epoch": 3.94, + "learning_rate": 1.8568962939308117e-05, + "loss": 0.3132, + "step": 12772 + }, + { + "epoch": 3.94, + "learning_rate": 1.8568705123229637e-05, + "loss": 0.3385, + "step": 12773 + }, + { + "epoch": 3.94, + "learning_rate": 1.8568447285719262e-05, + "loss": 0.3359, + "step": 12774 + }, + { + "epoch": 3.95, + "learning_rate": 1.8568189426777638e-05, + "loss": 0.322, + "step": 12775 + }, + { + "epoch": 3.95, + "learning_rate": 1.856793154640541e-05, + "loss": 0.3349, + "step": 12776 + }, + { + "epoch": 3.95, + "learning_rate": 1.8567673644603224e-05, + "loss": 0.3261, + "step": 12777 + }, + { + "epoch": 3.95, + "learning_rate": 1.856741572137172e-05, + "loss": 0.3336, + "step": 12778 + }, + { + "epoch": 3.95, + "learning_rate": 1.856715777671155e-05, + "loss": 0.3425, + "step": 12779 + }, + { + "epoch": 3.95, + "learning_rate": 1.8566899810623352e-05, + "loss": 0.3144, + "step": 12780 + }, + { + "epoch": 3.95, + "learning_rate": 1.856664182310778e-05, + "loss": 0.3104, + "step": 12781 + }, + { + "epoch": 3.95, + "learning_rate": 1.8566383814165473e-05, + "loss": 0.2999, + "step": 12782 + }, + { + "epoch": 3.95, + "learning_rate": 1.8566125783797076e-05, + "loss": 0.3258, + "step": 12783 + }, + { + "epoch": 3.95, + "learning_rate": 1.8565867732003235e-05, + "loss": 0.3259, + "step": 12784 + }, + { + "epoch": 3.95, + "learning_rate": 1.8565609658784596e-05, + "loss": 0.33, + "step": 12785 + }, + { + "epoch": 3.95, + "learning_rate": 1.8565351564141808e-05, + "loss": 0.3245, + "step": 12786 + }, + { + "epoch": 3.95, + "learning_rate": 1.856509344807551e-05, + "loss": 0.325, + "step": 12787 + }, + { + "epoch": 3.95, + "learning_rate": 1.8564835310586356e-05, + "loss": 0.3287, + "step": 12788 + }, + { + "epoch": 3.95, + "learning_rate": 1.8564577151674984e-05, + "loss": 0.2911, + "step": 12789 + }, + { + "epoch": 3.95, + "learning_rate": 1.8564318971342043e-05, + "loss": 0.314, + "step": 12790 + }, + { + "epoch": 3.95, + "learning_rate": 1.8564060769588177e-05, + "loss": 0.3409, + "step": 12791 + }, + { + "epoch": 3.95, + "learning_rate": 1.8563802546414035e-05, + "loss": 0.2859, + "step": 12792 + }, + { + "epoch": 3.95, + "learning_rate": 1.8563544301820258e-05, + "loss": 0.2988, + "step": 12793 + }, + { + "epoch": 3.95, + "learning_rate": 1.85632860358075e-05, + "loss": 0.3155, + "step": 12794 + }, + { + "epoch": 3.95, + "learning_rate": 1.8563027748376396e-05, + "loss": 0.3194, + "step": 12795 + }, + { + "epoch": 3.95, + "learning_rate": 1.85627694395276e-05, + "loss": 0.3375, + "step": 12796 + }, + { + "epoch": 3.95, + "learning_rate": 1.856251110926176e-05, + "loss": 0.3141, + "step": 12797 + }, + { + "epoch": 3.95, + "learning_rate": 1.856225275757951e-05, + "loss": 0.3154, + "step": 12798 + }, + { + "epoch": 3.95, + "learning_rate": 1.856199438448151e-05, + "loss": 0.327, + "step": 12799 + }, + { + "epoch": 3.95, + "learning_rate": 1.85617359899684e-05, + "loss": 0.3343, + "step": 12800 + }, + { + "epoch": 3.95, + "learning_rate": 1.8561477574040824e-05, + "loss": 0.2855, + "step": 12801 + }, + { + "epoch": 3.95, + "learning_rate": 1.8561219136699432e-05, + "loss": 0.3134, + "step": 12802 + }, + { + "epoch": 3.95, + "learning_rate": 1.856096067794487e-05, + "loss": 0.3266, + "step": 12803 + }, + { + "epoch": 3.95, + "learning_rate": 1.8560702197777784e-05, + "loss": 0.3213, + "step": 12804 + }, + { + "epoch": 3.95, + "learning_rate": 1.856044369619882e-05, + "loss": 0.3275, + "step": 12805 + }, + { + "epoch": 3.95, + "learning_rate": 1.8560185173208623e-05, + "loss": 0.3266, + "step": 12806 + }, + { + "epoch": 3.96, + "learning_rate": 1.8559926628807847e-05, + "loss": 0.3336, + "step": 12807 + }, + { + "epoch": 3.96, + "learning_rate": 1.855966806299713e-05, + "loss": 0.3236, + "step": 12808 + }, + { + "epoch": 3.96, + "learning_rate": 1.855940947577712e-05, + "loss": 0.3207, + "step": 12809 + }, + { + "epoch": 3.96, + "learning_rate": 1.855915086714847e-05, + "loss": 0.3137, + "step": 12810 + }, + { + "epoch": 3.96, + "learning_rate": 1.855889223711182e-05, + "loss": 0.3232, + "step": 12811 + }, + { + "epoch": 3.96, + "learning_rate": 1.8558633585667822e-05, + "loss": 0.2939, + "step": 12812 + }, + { + "epoch": 3.96, + "learning_rate": 1.8558374912817118e-05, + "loss": 0.2944, + "step": 12813 + }, + { + "epoch": 3.96, + "learning_rate": 1.8558116218560357e-05, + "loss": 0.3305, + "step": 12814 + }, + { + "epoch": 3.96, + "learning_rate": 1.8557857502898185e-05, + "loss": 0.3129, + "step": 12815 + }, + { + "epoch": 3.96, + "learning_rate": 1.8557598765831254e-05, + "loss": 0.3177, + "step": 12816 + }, + { + "epoch": 3.96, + "learning_rate": 1.8557340007360207e-05, + "loss": 0.3151, + "step": 12817 + }, + { + "epoch": 3.96, + "learning_rate": 1.855708122748569e-05, + "loss": 0.3302, + "step": 12818 + }, + { + "epoch": 3.96, + "learning_rate": 1.8556822426208353e-05, + "loss": 0.3347, + "step": 12819 + }, + { + "epoch": 3.96, + "learning_rate": 1.8556563603528844e-05, + "loss": 0.3321, + "step": 12820 + }, + { + "epoch": 3.96, + "learning_rate": 1.8556304759447807e-05, + "loss": 0.3177, + "step": 12821 + }, + { + "epoch": 3.96, + "learning_rate": 1.8556045893965894e-05, + "loss": 0.3404, + "step": 12822 + }, + { + "epoch": 3.96, + "learning_rate": 1.8555787007083744e-05, + "loss": 0.318, + "step": 12823 + }, + { + "epoch": 3.96, + "learning_rate": 1.8555528098802015e-05, + "loss": 0.3022, + "step": 12824 + }, + { + "epoch": 3.96, + "learning_rate": 1.855526916912135e-05, + "loss": 0.3144, + "step": 12825 + }, + { + "epoch": 3.96, + "learning_rate": 1.8555010218042396e-05, + "loss": 0.306, + "step": 12826 + }, + { + "epoch": 3.96, + "learning_rate": 1.8554751245565802e-05, + "loss": 0.3071, + "step": 12827 + }, + { + "epoch": 3.96, + "learning_rate": 1.855449225169221e-05, + "loss": 0.3095, + "step": 12828 + }, + { + "epoch": 3.96, + "learning_rate": 1.8554233236422277e-05, + "loss": 0.324, + "step": 12829 + }, + { + "epoch": 3.96, + "learning_rate": 1.8553974199756645e-05, + "loss": 0.3033, + "step": 12830 + }, + { + "epoch": 3.96, + "learning_rate": 1.8553715141695963e-05, + "loss": 0.3264, + "step": 12831 + }, + { + "epoch": 3.96, + "learning_rate": 1.855345606224088e-05, + "loss": 0.3167, + "step": 12832 + }, + { + "epoch": 3.96, + "learning_rate": 1.8553196961392044e-05, + "loss": 0.329, + "step": 12833 + }, + { + "epoch": 3.96, + "learning_rate": 1.85529378391501e-05, + "loss": 0.3088, + "step": 12834 + }, + { + "epoch": 3.96, + "learning_rate": 1.85526786955157e-05, + "loss": 0.3037, + "step": 12835 + }, + { + "epoch": 3.96, + "learning_rate": 1.8552419530489492e-05, + "loss": 0.3088, + "step": 12836 + }, + { + "epoch": 3.96, + "learning_rate": 1.855216034407212e-05, + "loss": 0.3281, + "step": 12837 + }, + { + "epoch": 3.96, + "learning_rate": 1.8551901136264237e-05, + "loss": 0.327, + "step": 12838 + }, + { + "epoch": 3.97, + "learning_rate": 1.855164190706649e-05, + "loss": 0.312, + "step": 12839 + }, + { + "epoch": 3.97, + "learning_rate": 1.8551382656479527e-05, + "loss": 0.3303, + "step": 12840 + }, + { + "epoch": 3.97, + "learning_rate": 1.8551123384503995e-05, + "loss": 0.3051, + "step": 12841 + }, + { + "epoch": 3.97, + "learning_rate": 1.8550864091140542e-05, + "loss": 0.3198, + "step": 12842 + }, + { + "epoch": 3.97, + "learning_rate": 1.8550604776389823e-05, + "loss": 0.2978, + "step": 12843 + }, + { + "epoch": 3.97, + "learning_rate": 1.855034544025248e-05, + "loss": 0.3048, + "step": 12844 + }, + { + "epoch": 3.97, + "learning_rate": 1.8550086082729165e-05, + "loss": 0.3319, + "step": 12845 + }, + { + "epoch": 3.97, + "learning_rate": 1.854982670382052e-05, + "loss": 0.3056, + "step": 12846 + }, + { + "epoch": 3.97, + "learning_rate": 1.85495673035272e-05, + "loss": 0.3323, + "step": 12847 + }, + { + "epoch": 3.97, + "learning_rate": 1.854930788184986e-05, + "loss": 0.3094, + "step": 12848 + }, + { + "epoch": 3.97, + "learning_rate": 1.8549048438789134e-05, + "loss": 0.3104, + "step": 12849 + }, + { + "epoch": 3.97, + "learning_rate": 1.8548788974345684e-05, + "loss": 0.3245, + "step": 12850 + }, + { + "epoch": 3.97, + "learning_rate": 1.854852948852015e-05, + "loss": 0.315, + "step": 12851 + }, + { + "epoch": 3.97, + "learning_rate": 1.8548269981313187e-05, + "loss": 0.2898, + "step": 12852 + }, + { + "epoch": 3.97, + "learning_rate": 1.854801045272544e-05, + "loss": 0.3152, + "step": 12853 + }, + { + "epoch": 3.97, + "learning_rate": 1.854775090275756e-05, + "loss": 0.2938, + "step": 12854 + }, + { + "epoch": 3.97, + "learning_rate": 1.8547491331410196e-05, + "loss": 0.2891, + "step": 12855 + }, + { + "epoch": 3.97, + "learning_rate": 1.8547231738684e-05, + "loss": 0.3177, + "step": 12856 + }, + { + "epoch": 3.97, + "learning_rate": 1.8546972124579614e-05, + "loss": 0.3355, + "step": 12857 + }, + { + "epoch": 3.97, + "learning_rate": 1.854671248909769e-05, + "loss": 0.3269, + "step": 12858 + }, + { + "epoch": 3.97, + "learning_rate": 1.8546452832238885e-05, + "loss": 0.2809, + "step": 12859 + }, + { + "epoch": 3.97, + "learning_rate": 1.854619315400384e-05, + "loss": 0.3186, + "step": 12860 + }, + { + "epoch": 3.97, + "learning_rate": 1.8545933454393208e-05, + "loss": 0.3138, + "step": 12861 + }, + { + "epoch": 3.97, + "learning_rate": 1.854567373340764e-05, + "loss": 0.3101, + "step": 12862 + }, + { + "epoch": 3.97, + "learning_rate": 1.8545413991047782e-05, + "loss": 0.3142, + "step": 12863 + }, + { + "epoch": 3.97, + "learning_rate": 1.854515422731428e-05, + "loss": 0.3078, + "step": 12864 + }, + { + "epoch": 3.97, + "learning_rate": 1.8544894442207793e-05, + "loss": 0.3026, + "step": 12865 + }, + { + "epoch": 3.97, + "learning_rate": 1.8544634635728966e-05, + "loss": 0.2964, + "step": 12866 + }, + { + "epoch": 3.97, + "learning_rate": 1.854437480787845e-05, + "loss": 0.3073, + "step": 12867 + }, + { + "epoch": 3.97, + "learning_rate": 1.8544114958656893e-05, + "loss": 0.2775, + "step": 12868 + }, + { + "epoch": 3.97, + "learning_rate": 1.854385508806495e-05, + "loss": 0.3222, + "step": 12869 + }, + { + "epoch": 3.97, + "learning_rate": 1.854359519610326e-05, + "loss": 0.3077, + "step": 12870 + }, + { + "epoch": 3.97, + "learning_rate": 1.8543335282772488e-05, + "loss": 0.3189, + "step": 12871 + }, + { + "epoch": 3.98, + "learning_rate": 1.854307534807327e-05, + "loss": 0.3111, + "step": 12872 + }, + { + "epoch": 3.98, + "learning_rate": 1.8542815392006264e-05, + "loss": 0.2982, + "step": 12873 + }, + { + "epoch": 3.98, + "learning_rate": 1.8542555414572122e-05, + "loss": 0.3262, + "step": 12874 + }, + { + "epoch": 3.98, + "learning_rate": 1.854229541577149e-05, + "loss": 0.3217, + "step": 12875 + }, + { + "epoch": 3.98, + "learning_rate": 1.8542035395605012e-05, + "loss": 0.337, + "step": 12876 + }, + { + "epoch": 3.98, + "learning_rate": 1.8541775354073356e-05, + "loss": 0.3086, + "step": 12877 + }, + { + "epoch": 3.98, + "learning_rate": 1.8541515291177153e-05, + "loss": 0.2926, + "step": 12878 + }, + { + "epoch": 3.98, + "learning_rate": 1.854125520691707e-05, + "loss": 0.3252, + "step": 12879 + }, + { + "epoch": 3.98, + "learning_rate": 1.8540995101293743e-05, + "loss": 0.3117, + "step": 12880 + }, + { + "epoch": 3.98, + "learning_rate": 1.8540734974307833e-05, + "loss": 0.3316, + "step": 12881 + }, + { + "epoch": 3.98, + "learning_rate": 1.8540474825959986e-05, + "loss": 0.3403, + "step": 12882 + }, + { + "epoch": 3.98, + "learning_rate": 1.8540214656250855e-05, + "loss": 0.2909, + "step": 12883 + }, + { + "epoch": 3.98, + "learning_rate": 1.853995446518109e-05, + "loss": 0.3387, + "step": 12884 + }, + { + "epoch": 3.98, + "learning_rate": 1.853969425275134e-05, + "loss": 0.3125, + "step": 12885 + }, + { + "epoch": 3.98, + "learning_rate": 1.8539434018962256e-05, + "loss": 0.307, + "step": 12886 + }, + { + "epoch": 3.98, + "learning_rate": 1.8539173763814494e-05, + "loss": 0.2981, + "step": 12887 + }, + { + "epoch": 3.98, + "learning_rate": 1.8538913487308695e-05, + "loss": 0.309, + "step": 12888 + }, + { + "epoch": 3.98, + "learning_rate": 1.8538653189445523e-05, + "loss": 0.3161, + "step": 12889 + }, + { + "epoch": 3.98, + "learning_rate": 1.8538392870225617e-05, + "loss": 0.343, + "step": 12890 + }, + { + "epoch": 3.98, + "learning_rate": 1.8538132529649633e-05, + "loss": 0.3112, + "step": 12891 + }, + { + "epoch": 3.98, + "learning_rate": 1.8537872167718223e-05, + "loss": 0.3253, + "step": 12892 + }, + { + "epoch": 3.98, + "learning_rate": 1.853761178443204e-05, + "loss": 0.3244, + "step": 12893 + }, + { + "epoch": 3.98, + "learning_rate": 1.853735137979173e-05, + "loss": 0.3504, + "step": 12894 + }, + { + "epoch": 3.98, + "learning_rate": 1.853709095379795e-05, + "loss": 0.3062, + "step": 12895 + }, + { + "epoch": 3.98, + "learning_rate": 1.8536830506451347e-05, + "loss": 0.315, + "step": 12896 + }, + { + "epoch": 3.98, + "learning_rate": 1.8536570037752573e-05, + "loss": 0.3176, + "step": 12897 + }, + { + "epoch": 3.98, + "learning_rate": 1.8536309547702277e-05, + "loss": 0.3102, + "step": 12898 + }, + { + "epoch": 3.98, + "learning_rate": 1.853604903630112e-05, + "loss": 0.3359, + "step": 12899 + }, + { + "epoch": 3.98, + "learning_rate": 1.8535788503549744e-05, + "loss": 0.3045, + "step": 12900 + }, + { + "epoch": 3.98, + "learning_rate": 1.8535527949448805e-05, + "loss": 0.2997, + "step": 12901 + }, + { + "epoch": 3.98, + "learning_rate": 1.8535267373998956e-05, + "loss": 0.3179, + "step": 12902 + }, + { + "epoch": 3.98, + "learning_rate": 1.8535006777200845e-05, + "loss": 0.3055, + "step": 12903 + }, + { + "epoch": 3.99, + "learning_rate": 1.8534746159055125e-05, + "loss": 0.3032, + "step": 12904 + }, + { + "epoch": 3.99, + "learning_rate": 1.8534485519562447e-05, + "loss": 0.3132, + "step": 12905 + }, + { + "epoch": 3.99, + "learning_rate": 1.8534224858723467e-05, + "loss": 0.3074, + "step": 12906 + }, + { + "epoch": 3.99, + "learning_rate": 1.853396417653883e-05, + "loss": 0.2951, + "step": 12907 + }, + { + "epoch": 3.99, + "learning_rate": 1.8533703473009198e-05, + "loss": 0.3371, + "step": 12908 + }, + { + "epoch": 3.99, + "learning_rate": 1.853344274813521e-05, + "loss": 0.3043, + "step": 12909 + }, + { + "epoch": 3.99, + "learning_rate": 1.8533182001917528e-05, + "loss": 0.3227, + "step": 12910 + }, + { + "epoch": 3.99, + "learning_rate": 1.8532921234356806e-05, + "loss": 0.3117, + "step": 12911 + }, + { + "epoch": 3.99, + "learning_rate": 1.853266044545369e-05, + "loss": 0.3079, + "step": 12912 + }, + { + "epoch": 3.99, + "learning_rate": 1.853239963520883e-05, + "loss": 0.312, + "step": 12913 + }, + { + "epoch": 3.99, + "learning_rate": 1.8532138803622884e-05, + "loss": 0.3097, + "step": 12914 + }, + { + "epoch": 3.99, + "learning_rate": 1.8531877950696504e-05, + "loss": 0.3072, + "step": 12915 + }, + { + "epoch": 3.99, + "learning_rate": 1.8531617076430338e-05, + "loss": 0.3183, + "step": 12916 + }, + { + "epoch": 3.99, + "learning_rate": 1.8531356180825044e-05, + "loss": 0.3043, + "step": 12917 + }, + { + "epoch": 3.99, + "learning_rate": 1.8531095263881272e-05, + "loss": 0.323, + "step": 12918 + }, + { + "epoch": 3.99, + "learning_rate": 1.8530834325599677e-05, + "loss": 0.3083, + "step": 12919 + }, + { + "epoch": 3.99, + "learning_rate": 1.8530573365980905e-05, + "loss": 0.3207, + "step": 12920 + }, + { + "epoch": 3.99, + "learning_rate": 1.8530312385025617e-05, + "loss": 0.3239, + "step": 12921 + }, + { + "epoch": 3.99, + "learning_rate": 1.8530051382734456e-05, + "loss": 0.3175, + "step": 12922 + }, + { + "epoch": 3.99, + "learning_rate": 1.8529790359108088e-05, + "loss": 0.2979, + "step": 12923 + }, + { + "epoch": 3.99, + "learning_rate": 1.8529529314147155e-05, + "loss": 0.3098, + "step": 12924 + }, + { + "epoch": 3.99, + "learning_rate": 1.8529268247852315e-05, + "loss": 0.3086, + "step": 12925 + }, + { + "epoch": 3.99, + "learning_rate": 1.8529007160224218e-05, + "loss": 0.2988, + "step": 12926 + }, + { + "epoch": 3.99, + "learning_rate": 1.852874605126352e-05, + "loss": 0.3082, + "step": 12927 + }, + { + "epoch": 3.99, + "learning_rate": 1.852848492097087e-05, + "loss": 0.3219, + "step": 12928 + }, + { + "epoch": 3.99, + "learning_rate": 1.8528223769346927e-05, + "loss": 0.3237, + "step": 12929 + }, + { + "epoch": 3.99, + "learning_rate": 1.852796259639234e-05, + "loss": 0.3202, + "step": 12930 + }, + { + "epoch": 3.99, + "learning_rate": 1.852770140210776e-05, + "loss": 0.2918, + "step": 12931 + }, + { + "epoch": 3.99, + "learning_rate": 1.8527440186493847e-05, + "loss": 0.319, + "step": 12932 + }, + { + "epoch": 3.99, + "learning_rate": 1.852717894955125e-05, + "loss": 0.3121, + "step": 12933 + }, + { + "epoch": 3.99, + "learning_rate": 1.852691769128062e-05, + "loss": 0.3175, + "step": 12934 + }, + { + "epoch": 3.99, + "learning_rate": 1.8526656411682617e-05, + "loss": 0.2997, + "step": 12935 + }, + { + "epoch": 4.0, + "learning_rate": 1.852639511075789e-05, + "loss": 0.3307, + "step": 12936 + }, + { + "epoch": 4.0, + "learning_rate": 1.8526133788507096e-05, + "loss": 0.2863, + "step": 12937 + }, + { + "epoch": 4.0, + "learning_rate": 1.8525872444930884e-05, + "loss": 0.3154, + "step": 12938 + }, + { + "epoch": 4.0, + "learning_rate": 1.852561108002991e-05, + "loss": 0.3361, + "step": 12939 + }, + { + "epoch": 4.0, + "learning_rate": 1.852534969380483e-05, + "loss": 0.3051, + "step": 12940 + }, + { + "epoch": 4.0, + "learning_rate": 1.8525088286256293e-05, + "loss": 0.3015, + "step": 12941 + }, + { + "epoch": 4.0, + "learning_rate": 1.8524826857384957e-05, + "loss": 0.3307, + "step": 12942 + }, + { + "epoch": 4.0, + "learning_rate": 1.8524565407191472e-05, + "loss": 0.3236, + "step": 12943 + }, + { + "epoch": 4.0, + "learning_rate": 1.8524303935676497e-05, + "loss": 0.2975, + "step": 12944 + }, + { + "epoch": 4.0, + "learning_rate": 1.852404244284068e-05, + "loss": 0.3108, + "step": 12945 + }, + { + "epoch": 4.0, + "learning_rate": 1.852378092868468e-05, + "loss": 0.2975, + "step": 12946 + }, + { + "epoch": 4.0, + "learning_rate": 1.8523519393209152e-05, + "loss": 0.2958, + "step": 12947 + }, + { + "epoch": 4.0, + "learning_rate": 1.852325783641474e-05, + "loss": 0.3005, + "step": 12948 + }, + { + "epoch": 4.0, + "learning_rate": 1.8522996258302112e-05, + "loss": 0.3001, + "step": 12949 + }, + { + "epoch": 4.0, + "learning_rate": 1.852273465887191e-05, + "loss": 0.3361, + "step": 12950 + }, + { + "epoch": 4.0, + "learning_rate": 1.85224730381248e-05, + "loss": 0.3088, + "step": 12951 + }, + { + "epoch": 4.0, + "learning_rate": 1.852221139606143e-05, + "loss": 0.3046, + "step": 12952 + }, + { + "epoch": 4.0, + "learning_rate": 1.8521949732682453e-05, + "loss": 0.3061, + "step": 12953 + }, + { + "epoch": 4.0, + "learning_rate": 1.8521688047988523e-05, + "loss": 0.2805, + "step": 12954 + }, + { + "epoch": 4.0, + "learning_rate": 1.8521426341980303e-05, + "loss": 0.2581, + "step": 12955 + }, + { + "epoch": 4.0, + "learning_rate": 1.8521164614658436e-05, + "loss": 0.2824, + "step": 12956 + }, + { + "epoch": 4.0, + "learning_rate": 1.8520902866023585e-05, + "loss": 0.2605, + "step": 12957 + }, + { + "epoch": 4.0, + "learning_rate": 1.8520641096076405e-05, + "loss": 0.2736, + "step": 12958 + }, + { + "epoch": 4.0, + "learning_rate": 1.852037930481754e-05, + "loss": 0.3093, + "step": 12959 + }, + { + "epoch": 4.0, + "learning_rate": 1.8520117492247657e-05, + "loss": 0.287, + "step": 12960 + }, + { + "epoch": 4.0, + "learning_rate": 1.8519855658367406e-05, + "loss": 0.2611, + "step": 12961 + }, + { + "epoch": 4.0, + "learning_rate": 1.851959380317744e-05, + "loss": 0.2641, + "step": 12962 + }, + { + "epoch": 4.0, + "learning_rate": 1.8519331926678417e-05, + "loss": 0.2733, + "step": 12963 + }, + { + "epoch": 4.0, + "learning_rate": 1.8519070028870994e-05, + "loss": 0.2661, + "step": 12964 + }, + { + "epoch": 4.0, + "learning_rate": 1.851880810975582e-05, + "loss": 0.2765, + "step": 12965 + }, + { + "epoch": 4.0, + "learning_rate": 1.8518546169333553e-05, + "loss": 0.2816, + "step": 12966 + }, + { + "epoch": 4.0, + "learning_rate": 1.851828420760485e-05, + "loss": 0.2816, + "step": 12967 + }, + { + "epoch": 4.0, + "learning_rate": 1.8518022224570364e-05, + "loss": 0.2735, + "step": 12968 + }, + { + "epoch": 4.01, + "learning_rate": 1.851776022023075e-05, + "loss": 0.2685, + "step": 12969 + }, + { + "epoch": 4.01, + "learning_rate": 1.851749819458666e-05, + "loss": 0.2906, + "step": 12970 + }, + { + "epoch": 4.01, + "learning_rate": 1.8517236147638762e-05, + "loss": 0.2725, + "step": 12971 + }, + { + "epoch": 4.01, + "learning_rate": 1.8516974079387697e-05, + "loss": 0.2823, + "step": 12972 + }, + { + "epoch": 4.01, + "learning_rate": 1.8516711989834132e-05, + "loss": 0.2709, + "step": 12973 + }, + { + "epoch": 4.01, + "learning_rate": 1.8516449878978712e-05, + "loss": 0.2618, + "step": 12974 + }, + { + "epoch": 4.01, + "learning_rate": 1.8516187746822097e-05, + "loss": 0.285, + "step": 12975 + }, + { + "epoch": 4.01, + "learning_rate": 1.851592559336495e-05, + "loss": 0.2915, + "step": 12976 + }, + { + "epoch": 4.01, + "learning_rate": 1.8515663418607913e-05, + "loss": 0.2621, + "step": 12977 + }, + { + "epoch": 4.01, + "learning_rate": 1.851540122255165e-05, + "loss": 0.2661, + "step": 12978 + }, + { + "epoch": 4.01, + "learning_rate": 1.8515139005196816e-05, + "loss": 0.2963, + "step": 12979 + }, + { + "epoch": 4.01, + "learning_rate": 1.8514876766544064e-05, + "loss": 0.2667, + "step": 12980 + }, + { + "epoch": 4.01, + "learning_rate": 1.8514614506594057e-05, + "loss": 0.2769, + "step": 12981 + }, + { + "epoch": 4.01, + "learning_rate": 1.8514352225347446e-05, + "loss": 0.2822, + "step": 12982 + }, + { + "epoch": 4.01, + "learning_rate": 1.8514089922804882e-05, + "loss": 0.2759, + "step": 12983 + }, + { + "epoch": 4.01, + "learning_rate": 1.851382759896703e-05, + "loss": 0.2615, + "step": 12984 + }, + { + "epoch": 4.01, + "learning_rate": 1.8513565253834544e-05, + "loss": 0.2775, + "step": 12985 + }, + { + "epoch": 4.01, + "learning_rate": 1.8513302887408074e-05, + "loss": 0.2689, + "step": 12986 + }, + { + "epoch": 4.01, + "learning_rate": 1.8513040499688283e-05, + "loss": 0.2764, + "step": 12987 + }, + { + "epoch": 4.01, + "learning_rate": 1.8512778090675826e-05, + "loss": 0.2693, + "step": 12988 + }, + { + "epoch": 4.01, + "learning_rate": 1.8512515660371355e-05, + "loss": 0.2786, + "step": 12989 + }, + { + "epoch": 4.01, + "learning_rate": 1.851225320877553e-05, + "loss": 0.2663, + "step": 12990 + }, + { + "epoch": 4.01, + "learning_rate": 1.8511990735889012e-05, + "loss": 0.2647, + "step": 12991 + }, + { + "epoch": 4.01, + "learning_rate": 1.8511728241712447e-05, + "loss": 0.2747, + "step": 12992 + }, + { + "epoch": 4.01, + "learning_rate": 1.85114657262465e-05, + "loss": 0.2657, + "step": 12993 + }, + { + "epoch": 4.01, + "learning_rate": 1.8511203189491826e-05, + "loss": 0.3059, + "step": 12994 + }, + { + "epoch": 4.01, + "learning_rate": 1.8510940631449078e-05, + "loss": 0.2645, + "step": 12995 + }, + { + "epoch": 4.01, + "learning_rate": 1.851067805211892e-05, + "loss": 0.251, + "step": 12996 + }, + { + "epoch": 4.01, + "learning_rate": 1.8510415451501998e-05, + "loss": 0.2622, + "step": 12997 + }, + { + "epoch": 4.01, + "learning_rate": 1.8510152829598976e-05, + "loss": 0.2798, + "step": 12998 + }, + { + "epoch": 4.01, + "learning_rate": 1.850989018641051e-05, + "loss": 0.2531, + "step": 12999 + }, + { + "epoch": 4.01, + "learning_rate": 1.850962752193726e-05, + "loss": 0.2781, + "step": 13000 + }, + { + "epoch": 4.02, + "learning_rate": 1.8509364836179874e-05, + "loss": 0.2841, + "step": 13001 + }, + { + "epoch": 4.02, + "learning_rate": 1.850910212913902e-05, + "loss": 0.3012, + "step": 13002 + }, + { + "epoch": 4.02, + "learning_rate": 1.8508839400815345e-05, + "loss": 0.2829, + "step": 13003 + }, + { + "epoch": 4.02, + "learning_rate": 1.8508576651209513e-05, + "loss": 0.282, + "step": 13004 + }, + { + "epoch": 4.02, + "learning_rate": 1.8508313880322178e-05, + "loss": 0.2907, + "step": 13005 + }, + { + "epoch": 4.02, + "learning_rate": 1.8508051088154e-05, + "loss": 0.2702, + "step": 13006 + }, + { + "epoch": 4.02, + "learning_rate": 1.8507788274705632e-05, + "loss": 0.2746, + "step": 13007 + }, + { + "epoch": 4.02, + "learning_rate": 1.8507525439977736e-05, + "loss": 0.281, + "step": 13008 + }, + { + "epoch": 4.02, + "learning_rate": 1.8507262583970966e-05, + "loss": 0.3014, + "step": 13009 + }, + { + "epoch": 4.02, + "learning_rate": 1.8506999706685983e-05, + "loss": 0.2737, + "step": 13010 + }, + { + "epoch": 4.02, + "learning_rate": 1.850673680812344e-05, + "loss": 0.2506, + "step": 13011 + }, + { + "epoch": 4.02, + "learning_rate": 1.8506473888283996e-05, + "loss": 0.284, + "step": 13012 + }, + { + "epoch": 4.02, + "learning_rate": 1.850621094716831e-05, + "loss": 0.2937, + "step": 13013 + }, + { + "epoch": 4.02, + "learning_rate": 1.850594798477704e-05, + "loss": 0.2581, + "step": 13014 + }, + { + "epoch": 4.02, + "learning_rate": 1.8505685001110843e-05, + "loss": 0.2787, + "step": 13015 + }, + { + "epoch": 4.02, + "learning_rate": 1.8505421996170375e-05, + "loss": 0.2892, + "step": 13016 + }, + { + "epoch": 4.02, + "learning_rate": 1.8505158969956295e-05, + "loss": 0.2746, + "step": 13017 + }, + { + "epoch": 4.02, + "learning_rate": 1.850489592246926e-05, + "loss": 0.2549, + "step": 13018 + }, + { + "epoch": 4.02, + "learning_rate": 1.850463285370993e-05, + "loss": 0.26, + "step": 13019 + }, + { + "epoch": 4.02, + "learning_rate": 1.8504369763678963e-05, + "loss": 0.2749, + "step": 13020 + }, + { + "epoch": 4.02, + "learning_rate": 1.8504106652377015e-05, + "loss": 0.2673, + "step": 13021 + }, + { + "epoch": 4.02, + "learning_rate": 1.8503843519804748e-05, + "loss": 0.2588, + "step": 13022 + }, + { + "epoch": 4.02, + "learning_rate": 1.8503580365962816e-05, + "loss": 0.2751, + "step": 13023 + }, + { + "epoch": 4.02, + "learning_rate": 1.8503317190851877e-05, + "loss": 0.2798, + "step": 13024 + }, + { + "epoch": 4.02, + "learning_rate": 1.850305399447259e-05, + "loss": 0.2741, + "step": 13025 + }, + { + "epoch": 4.02, + "learning_rate": 1.850279077682562e-05, + "loss": 0.2681, + "step": 13026 + }, + { + "epoch": 4.02, + "learning_rate": 1.8502527537911616e-05, + "loss": 0.2978, + "step": 13027 + }, + { + "epoch": 4.02, + "learning_rate": 1.850226427773124e-05, + "loss": 0.283, + "step": 13028 + }, + { + "epoch": 4.02, + "learning_rate": 1.850200099628515e-05, + "loss": 0.2922, + "step": 13029 + }, + { + "epoch": 4.02, + "learning_rate": 1.8501737693574003e-05, + "loss": 0.3019, + "step": 13030 + }, + { + "epoch": 4.02, + "learning_rate": 1.850147436959846e-05, + "loss": 0.2631, + "step": 13031 + }, + { + "epoch": 4.02, + "learning_rate": 1.8501211024359182e-05, + "loss": 0.2743, + "step": 13032 + }, + { + "epoch": 4.02, + "learning_rate": 1.8500947657856822e-05, + "loss": 0.2835, + "step": 13033 + }, + { + "epoch": 4.03, + "learning_rate": 1.850068427009204e-05, + "loss": 0.2677, + "step": 13034 + }, + { + "epoch": 4.03, + "learning_rate": 1.85004208610655e-05, + "loss": 0.2722, + "step": 13035 + }, + { + "epoch": 4.03, + "learning_rate": 1.8500157430777855e-05, + "loss": 0.2581, + "step": 13036 + }, + { + "epoch": 4.03, + "learning_rate": 1.8499893979229765e-05, + "loss": 0.3115, + "step": 13037 + }, + { + "epoch": 4.03, + "learning_rate": 1.849963050642189e-05, + "loss": 0.267, + "step": 13038 + }, + { + "epoch": 4.03, + "learning_rate": 1.849936701235489e-05, + "loss": 0.275, + "step": 13039 + }, + { + "epoch": 4.03, + "learning_rate": 1.8499103497029425e-05, + "loss": 0.2723, + "step": 13040 + }, + { + "epoch": 4.03, + "learning_rate": 1.8498839960446153e-05, + "loss": 0.2724, + "step": 13041 + }, + { + "epoch": 4.03, + "learning_rate": 1.8498576402605724e-05, + "loss": 0.2832, + "step": 13042 + }, + { + "epoch": 4.03, + "learning_rate": 1.8498312823508814e-05, + "loss": 0.2548, + "step": 13043 + }, + { + "epoch": 4.03, + "learning_rate": 1.849804922315607e-05, + "loss": 0.2663, + "step": 13044 + }, + { + "epoch": 4.03, + "learning_rate": 1.8497785601548152e-05, + "loss": 0.2642, + "step": 13045 + }, + { + "epoch": 4.03, + "learning_rate": 1.8497521958685728e-05, + "loss": 0.2758, + "step": 13046 + }, + { + "epoch": 4.03, + "learning_rate": 1.8497258294569448e-05, + "loss": 0.2862, + "step": 13047 + }, + { + "epoch": 4.03, + "learning_rate": 1.8496994609199976e-05, + "loss": 0.27, + "step": 13048 + }, + { + "epoch": 4.03, + "learning_rate": 1.849673090257797e-05, + "loss": 0.2829, + "step": 13049 + }, + { + "epoch": 4.03, + "learning_rate": 1.8496467174704094e-05, + "loss": 0.2897, + "step": 13050 + }, + { + "epoch": 4.03, + "learning_rate": 1.8496203425579e-05, + "loss": 0.2797, + "step": 13051 + }, + { + "epoch": 4.03, + "learning_rate": 1.8495939655203353e-05, + "loss": 0.2837, + "step": 13052 + }, + { + "epoch": 4.03, + "learning_rate": 1.849567586357781e-05, + "loss": 0.3015, + "step": 13053 + }, + { + "epoch": 4.03, + "learning_rate": 1.8495412050703035e-05, + "loss": 0.2876, + "step": 13054 + }, + { + "epoch": 4.03, + "learning_rate": 1.8495148216579684e-05, + "loss": 0.2615, + "step": 13055 + }, + { + "epoch": 4.03, + "learning_rate": 1.8494884361208416e-05, + "loss": 0.3242, + "step": 13056 + }, + { + "epoch": 4.03, + "learning_rate": 1.8494620484589892e-05, + "loss": 0.2823, + "step": 13057 + }, + { + "epoch": 4.03, + "learning_rate": 1.8494356586724777e-05, + "loss": 0.3023, + "step": 13058 + }, + { + "epoch": 4.03, + "learning_rate": 1.8494092667613725e-05, + "loss": 0.2833, + "step": 13059 + }, + { + "epoch": 4.03, + "learning_rate": 1.84938287272574e-05, + "loss": 0.2829, + "step": 13060 + }, + { + "epoch": 4.03, + "learning_rate": 1.8493564765656456e-05, + "loss": 0.2855, + "step": 13061 + }, + { + "epoch": 4.03, + "learning_rate": 1.849330078281156e-05, + "loss": 0.2556, + "step": 13062 + }, + { + "epoch": 4.03, + "learning_rate": 1.849303677872337e-05, + "loss": 0.2777, + "step": 13063 + }, + { + "epoch": 4.03, + "learning_rate": 1.8492772753392544e-05, + "loss": 0.2841, + "step": 13064 + }, + { + "epoch": 4.03, + "learning_rate": 1.8492508706819746e-05, + "loss": 0.2614, + "step": 13065 + }, + { + "epoch": 4.04, + "learning_rate": 1.8492244639005636e-05, + "loss": 0.2682, + "step": 13066 + }, + { + "epoch": 4.04, + "learning_rate": 1.849198054995087e-05, + "loss": 0.2524, + "step": 13067 + }, + { + "epoch": 4.04, + "learning_rate": 1.8491716439656112e-05, + "loss": 0.2654, + "step": 13068 + }, + { + "epoch": 4.04, + "learning_rate": 1.8491452308122024e-05, + "loss": 0.2825, + "step": 13069 + }, + { + "epoch": 4.04, + "learning_rate": 1.8491188155349265e-05, + "loss": 0.2738, + "step": 13070 + }, + { + "epoch": 4.04, + "learning_rate": 1.8490923981338497e-05, + "loss": 0.2896, + "step": 13071 + }, + { + "epoch": 4.04, + "learning_rate": 1.8490659786090377e-05, + "loss": 0.2838, + "step": 13072 + }, + { + "epoch": 4.04, + "learning_rate": 1.849039556960557e-05, + "loss": 0.2936, + "step": 13073 + }, + { + "epoch": 4.04, + "learning_rate": 1.8490131331884737e-05, + "loss": 0.2801, + "step": 13074 + }, + { + "epoch": 4.04, + "learning_rate": 1.8489867072928527e-05, + "loss": 0.2732, + "step": 13075 + }, + { + "epoch": 4.04, + "learning_rate": 1.8489602792737622e-05, + "loss": 0.3008, + "step": 13076 + }, + { + "epoch": 4.04, + "learning_rate": 1.848933849131267e-05, + "loss": 0.2791, + "step": 13077 + }, + { + "epoch": 4.04, + "learning_rate": 1.848907416865433e-05, + "loss": 0.2872, + "step": 13078 + }, + { + "epoch": 4.04, + "learning_rate": 1.8488809824763268e-05, + "loss": 0.2857, + "step": 13079 + }, + { + "epoch": 4.04, + "learning_rate": 1.848854545964015e-05, + "loss": 0.2528, + "step": 13080 + }, + { + "epoch": 4.04, + "learning_rate": 1.8488281073285628e-05, + "loss": 0.3003, + "step": 13081 + }, + { + "epoch": 4.04, + "learning_rate": 1.8488016665700365e-05, + "loss": 0.2909, + "step": 13082 + }, + { + "epoch": 4.04, + "learning_rate": 1.8487752236885027e-05, + "loss": 0.2857, + "step": 13083 + }, + { + "epoch": 4.04, + "learning_rate": 1.8487487786840272e-05, + "loss": 0.2785, + "step": 13084 + }, + { + "epoch": 4.04, + "learning_rate": 1.848722331556676e-05, + "loss": 0.264, + "step": 13085 + }, + { + "epoch": 4.04, + "learning_rate": 1.8486958823065157e-05, + "loss": 0.266, + "step": 13086 + }, + { + "epoch": 4.04, + "learning_rate": 1.8486694309336118e-05, + "loss": 0.3034, + "step": 13087 + }, + { + "epoch": 4.04, + "learning_rate": 1.8486429774380315e-05, + "loss": 0.2542, + "step": 13088 + }, + { + "epoch": 4.04, + "learning_rate": 1.8486165218198398e-05, + "loss": 0.27, + "step": 13089 + }, + { + "epoch": 4.04, + "learning_rate": 1.8485900640791035e-05, + "loss": 0.2745, + "step": 13090 + }, + { + "epoch": 4.04, + "learning_rate": 1.8485636042158886e-05, + "loss": 0.2844, + "step": 13091 + }, + { + "epoch": 4.04, + "learning_rate": 1.848537142230262e-05, + "loss": 0.2918, + "step": 13092 + }, + { + "epoch": 4.04, + "learning_rate": 1.8485106781222885e-05, + "loss": 0.2706, + "step": 13093 + }, + { + "epoch": 4.04, + "learning_rate": 1.848484211892035e-05, + "loss": 0.2632, + "step": 13094 + }, + { + "epoch": 4.04, + "learning_rate": 1.8484577435395683e-05, + "loss": 0.2855, + "step": 13095 + }, + { + "epoch": 4.04, + "learning_rate": 1.8484312730649537e-05, + "loss": 0.262, + "step": 13096 + }, + { + "epoch": 4.04, + "learning_rate": 1.848404800468258e-05, + "loss": 0.274, + "step": 13097 + }, + { + "epoch": 4.05, + "learning_rate": 1.848378325749547e-05, + "loss": 0.3, + "step": 13098 + }, + { + "epoch": 4.05, + "learning_rate": 1.848351848908887e-05, + "loss": 0.2979, + "step": 13099 + }, + { + "epoch": 4.05, + "learning_rate": 1.848325369946344e-05, + "loss": 0.2877, + "step": 13100 + }, + { + "epoch": 4.05, + "learning_rate": 1.8482988888619852e-05, + "loss": 0.261, + "step": 13101 + }, + { + "epoch": 4.05, + "learning_rate": 1.8482724056558756e-05, + "loss": 0.271, + "step": 13102 + }, + { + "epoch": 4.05, + "learning_rate": 1.8482459203280822e-05, + "loss": 0.2804, + "step": 13103 + }, + { + "epoch": 4.05, + "learning_rate": 1.8482194328786712e-05, + "loss": 0.2856, + "step": 13104 + }, + { + "epoch": 4.05, + "learning_rate": 1.8481929433077086e-05, + "loss": 0.2893, + "step": 13105 + }, + { + "epoch": 4.05, + "learning_rate": 1.8481664516152606e-05, + "loss": 0.2964, + "step": 13106 + }, + { + "epoch": 4.05, + "learning_rate": 1.8481399578013938e-05, + "loss": 0.2663, + "step": 13107 + }, + { + "epoch": 4.05, + "learning_rate": 1.848113461866174e-05, + "loss": 0.269, + "step": 13108 + }, + { + "epoch": 4.05, + "learning_rate": 1.8480869638096682e-05, + "loss": 0.2698, + "step": 13109 + }, + { + "epoch": 4.05, + "learning_rate": 1.8480604636319415e-05, + "loss": 0.2607, + "step": 13110 + }, + { + "epoch": 4.05, + "learning_rate": 1.8480339613330614e-05, + "loss": 0.2856, + "step": 13111 + }, + { + "epoch": 4.05, + "learning_rate": 1.8480074569130936e-05, + "loss": 0.2748, + "step": 13112 + }, + { + "epoch": 4.05, + "learning_rate": 1.8479809503721048e-05, + "loss": 0.2926, + "step": 13113 + }, + { + "epoch": 4.05, + "learning_rate": 1.8479544417101607e-05, + "loss": 0.2845, + "step": 13114 + }, + { + "epoch": 4.05, + "learning_rate": 1.8479279309273278e-05, + "loss": 0.2904, + "step": 13115 + }, + { + "epoch": 4.05, + "learning_rate": 1.8479014180236724e-05, + "loss": 0.2941, + "step": 13116 + }, + { + "epoch": 4.05, + "learning_rate": 1.8478749029992614e-05, + "loss": 0.2548, + "step": 13117 + }, + { + "epoch": 4.05, + "learning_rate": 1.8478483858541604e-05, + "loss": 0.2827, + "step": 13118 + }, + { + "epoch": 4.05, + "learning_rate": 1.8478218665884358e-05, + "loss": 0.2647, + "step": 13119 + }, + { + "epoch": 4.05, + "learning_rate": 1.847795345202154e-05, + "loss": 0.2575, + "step": 13120 + }, + { + "epoch": 4.05, + "learning_rate": 1.8477688216953816e-05, + "loss": 0.2745, + "step": 13121 + }, + { + "epoch": 4.05, + "learning_rate": 1.847742296068185e-05, + "loss": 0.289, + "step": 13122 + }, + { + "epoch": 4.05, + "learning_rate": 1.8477157683206298e-05, + "loss": 0.288, + "step": 13123 + }, + { + "epoch": 4.05, + "learning_rate": 1.847689238452783e-05, + "loss": 0.2537, + "step": 13124 + }, + { + "epoch": 4.05, + "learning_rate": 1.847662706464711e-05, + "loss": 0.2776, + "step": 13125 + }, + { + "epoch": 4.05, + "learning_rate": 1.8476361723564795e-05, + "loss": 0.2715, + "step": 13126 + }, + { + "epoch": 4.05, + "learning_rate": 1.8476096361281558e-05, + "loss": 0.2905, + "step": 13127 + }, + { + "epoch": 4.05, + "learning_rate": 1.847583097779806e-05, + "loss": 0.2735, + "step": 13128 + }, + { + "epoch": 4.05, + "learning_rate": 1.8475565573114958e-05, + "loss": 0.2622, + "step": 13129 + }, + { + "epoch": 4.05, + "learning_rate": 1.847530014723292e-05, + "loss": 0.2521, + "step": 13130 + }, + { + "epoch": 4.06, + "learning_rate": 1.847503470015261e-05, + "loss": 0.2734, + "step": 13131 + }, + { + "epoch": 4.06, + "learning_rate": 1.84747692318747e-05, + "loss": 0.2844, + "step": 13132 + }, + { + "epoch": 4.06, + "learning_rate": 1.847450374239984e-05, + "loss": 0.2689, + "step": 13133 + }, + { + "epoch": 4.06, + "learning_rate": 1.84742382317287e-05, + "loss": 0.2645, + "step": 13134 + }, + { + "epoch": 4.06, + "learning_rate": 1.8473972699861948e-05, + "loss": 0.2816, + "step": 13135 + }, + { + "epoch": 4.06, + "learning_rate": 1.8473707146800244e-05, + "loss": 0.2581, + "step": 13136 + }, + { + "epoch": 4.06, + "learning_rate": 1.8473441572544254e-05, + "loss": 0.2738, + "step": 13137 + }, + { + "epoch": 4.06, + "learning_rate": 1.8473175977094636e-05, + "loss": 0.2961, + "step": 13138 + }, + { + "epoch": 4.06, + "learning_rate": 1.8472910360452067e-05, + "loss": 0.2762, + "step": 13139 + }, + { + "epoch": 4.06, + "learning_rate": 1.8472644722617198e-05, + "loss": 0.2438, + "step": 13140 + }, + { + "epoch": 4.06, + "learning_rate": 1.84723790635907e-05, + "loss": 0.2914, + "step": 13141 + }, + { + "epoch": 4.06, + "learning_rate": 1.847211338337324e-05, + "loss": 0.2531, + "step": 13142 + }, + { + "epoch": 4.06, + "learning_rate": 1.8471847681965477e-05, + "loss": 0.2674, + "step": 13143 + }, + { + "epoch": 4.06, + "learning_rate": 1.8471581959368075e-05, + "loss": 0.2752, + "step": 13144 + }, + { + "epoch": 4.06, + "learning_rate": 1.8471316215581704e-05, + "loss": 0.2686, + "step": 13145 + }, + { + "epoch": 4.06, + "learning_rate": 1.847105045060703e-05, + "loss": 0.2785, + "step": 13146 + }, + { + "epoch": 4.06, + "learning_rate": 1.8470784664444708e-05, + "loss": 0.2611, + "step": 13147 + }, + { + "epoch": 4.06, + "learning_rate": 1.847051885709541e-05, + "loss": 0.2596, + "step": 13148 + }, + { + "epoch": 4.06, + "learning_rate": 1.84702530285598e-05, + "loss": 0.286, + "step": 13149 + }, + { + "epoch": 4.06, + "learning_rate": 1.8469987178838544e-05, + "loss": 0.2665, + "step": 13150 + }, + { + "epoch": 4.06, + "learning_rate": 1.8469721307932304e-05, + "loss": 0.2609, + "step": 13151 + }, + { + "epoch": 4.06, + "learning_rate": 1.8469455415841745e-05, + "loss": 0.2688, + "step": 13152 + }, + { + "epoch": 4.06, + "learning_rate": 1.8469189502567534e-05, + "loss": 0.2662, + "step": 13153 + }, + { + "epoch": 4.06, + "learning_rate": 1.8468923568110332e-05, + "loss": 0.2684, + "step": 13154 + }, + { + "epoch": 4.06, + "learning_rate": 1.8468657612470812e-05, + "loss": 0.2635, + "step": 13155 + }, + { + "epoch": 4.06, + "learning_rate": 1.8468391635649637e-05, + "loss": 0.2779, + "step": 13156 + }, + { + "epoch": 4.06, + "learning_rate": 1.8468125637647465e-05, + "loss": 0.2716, + "step": 13157 + }, + { + "epoch": 4.06, + "learning_rate": 1.8467859618464967e-05, + "loss": 0.2724, + "step": 13158 + }, + { + "epoch": 4.06, + "learning_rate": 1.846759357810281e-05, + "loss": 0.2727, + "step": 13159 + }, + { + "epoch": 4.06, + "learning_rate": 1.8467327516561656e-05, + "loss": 0.2556, + "step": 13160 + }, + { + "epoch": 4.06, + "learning_rate": 1.846706143384217e-05, + "loss": 0.2583, + "step": 13161 + }, + { + "epoch": 4.06, + "learning_rate": 1.846679532994502e-05, + "loss": 0.2799, + "step": 13162 + }, + { + "epoch": 4.07, + "learning_rate": 1.8466529204870872e-05, + "loss": 0.2722, + "step": 13163 + }, + { + "epoch": 4.07, + "learning_rate": 1.8466263058620387e-05, + "loss": 0.2698, + "step": 13164 + }, + { + "epoch": 4.07, + "learning_rate": 1.8465996891194238e-05, + "loss": 0.2575, + "step": 13165 + }, + { + "epoch": 4.07, + "learning_rate": 1.8465730702593085e-05, + "loss": 0.2805, + "step": 13166 + }, + { + "epoch": 4.07, + "learning_rate": 1.8465464492817595e-05, + "loss": 0.267, + "step": 13167 + }, + { + "epoch": 4.07, + "learning_rate": 1.8465198261868433e-05, + "loss": 0.2714, + "step": 13168 + }, + { + "epoch": 4.07, + "learning_rate": 1.8464932009746267e-05, + "loss": 0.2649, + "step": 13169 + }, + { + "epoch": 4.07, + "learning_rate": 1.8464665736451763e-05, + "loss": 0.2715, + "step": 13170 + }, + { + "epoch": 4.07, + "learning_rate": 1.8464399441985586e-05, + "loss": 0.2883, + "step": 13171 + }, + { + "epoch": 4.07, + "learning_rate": 1.8464133126348403e-05, + "loss": 0.2686, + "step": 13172 + }, + { + "epoch": 4.07, + "learning_rate": 1.846386678954088e-05, + "loss": 0.2716, + "step": 13173 + }, + { + "epoch": 4.07, + "learning_rate": 1.8463600431563677e-05, + "loss": 0.2677, + "step": 13174 + }, + { + "epoch": 4.07, + "learning_rate": 1.846333405241747e-05, + "loss": 0.2603, + "step": 13175 + }, + { + "epoch": 4.07, + "learning_rate": 1.8463067652102923e-05, + "loss": 0.2808, + "step": 13176 + }, + { + "epoch": 4.07, + "learning_rate": 1.8462801230620697e-05, + "loss": 0.2749, + "step": 13177 + }, + { + "epoch": 4.07, + "learning_rate": 1.8462534787971462e-05, + "loss": 0.2594, + "step": 13178 + }, + { + "epoch": 4.07, + "learning_rate": 1.8462268324155884e-05, + "loss": 0.2616, + "step": 13179 + }, + { + "epoch": 4.07, + "learning_rate": 1.846200183917463e-05, + "loss": 0.2794, + "step": 13180 + }, + { + "epoch": 4.07, + "learning_rate": 1.8461735333028366e-05, + "loss": 0.2892, + "step": 13181 + }, + { + "epoch": 4.07, + "learning_rate": 1.846146880571776e-05, + "loss": 0.2871, + "step": 13182 + }, + { + "epoch": 4.07, + "learning_rate": 1.8461202257243473e-05, + "loss": 0.2737, + "step": 13183 + }, + { + "epoch": 4.07, + "learning_rate": 1.8460935687606182e-05, + "loss": 0.2861, + "step": 13184 + }, + { + "epoch": 4.07, + "learning_rate": 1.846066909680654e-05, + "loss": 0.2609, + "step": 13185 + }, + { + "epoch": 4.07, + "learning_rate": 1.846040248484523e-05, + "loss": 0.2629, + "step": 13186 + }, + { + "epoch": 4.07, + "learning_rate": 1.8460135851722903e-05, + "loss": 0.2475, + "step": 13187 + }, + { + "epoch": 4.07, + "learning_rate": 1.8459869197440237e-05, + "loss": 0.2699, + "step": 13188 + }, + { + "epoch": 4.07, + "learning_rate": 1.8459602521997895e-05, + "loss": 0.2521, + "step": 13189 + }, + { + "epoch": 4.07, + "learning_rate": 1.845933582539654e-05, + "loss": 0.2825, + "step": 13190 + }, + { + "epoch": 4.07, + "learning_rate": 1.845906910763685e-05, + "loss": 0.2863, + "step": 13191 + }, + { + "epoch": 4.07, + "learning_rate": 1.8458802368719482e-05, + "loss": 0.2455, + "step": 13192 + }, + { + "epoch": 4.07, + "learning_rate": 1.8458535608645104e-05, + "loss": 0.2882, + "step": 13193 + }, + { + "epoch": 4.07, + "learning_rate": 1.845826882741439e-05, + "loss": 0.2689, + "step": 13194 + }, + { + "epoch": 4.07, + "learning_rate": 1.8458002025028e-05, + "loss": 0.2841, + "step": 13195 + }, + { + "epoch": 4.08, + "learning_rate": 1.8457735201486607e-05, + "loss": 0.2846, + "step": 13196 + }, + { + "epoch": 4.08, + "learning_rate": 1.8457468356790874e-05, + "loss": 0.269, + "step": 13197 + }, + { + "epoch": 4.08, + "learning_rate": 1.845720149094147e-05, + "loss": 0.2522, + "step": 13198 + }, + { + "epoch": 4.08, + "learning_rate": 1.8456934603939064e-05, + "loss": 0.2882, + "step": 13199 + }, + { + "epoch": 4.08, + "learning_rate": 1.8456667695784324e-05, + "loss": 0.2579, + "step": 13200 + }, + { + "epoch": 4.08, + "learning_rate": 1.845640076647791e-05, + "loss": 0.2617, + "step": 13201 + }, + { + "epoch": 4.08, + "learning_rate": 1.8456133816020497e-05, + "loss": 0.2684, + "step": 13202 + }, + { + "epoch": 4.08, + "learning_rate": 1.8455866844412753e-05, + "loss": 0.2864, + "step": 13203 + }, + { + "epoch": 4.08, + "learning_rate": 1.8455599851655342e-05, + "loss": 0.2872, + "step": 13204 + }, + { + "epoch": 4.08, + "learning_rate": 1.8455332837748934e-05, + "loss": 0.2661, + "step": 13205 + }, + { + "epoch": 4.08, + "learning_rate": 1.8455065802694198e-05, + "loss": 0.258, + "step": 13206 + }, + { + "epoch": 4.08, + "learning_rate": 1.84547987464918e-05, + "loss": 0.2569, + "step": 13207 + }, + { + "epoch": 4.08, + "learning_rate": 1.8454531669142407e-05, + "loss": 0.2815, + "step": 13208 + }, + { + "epoch": 4.08, + "learning_rate": 1.8454264570646688e-05, + "loss": 0.251, + "step": 13209 + }, + { + "epoch": 4.08, + "learning_rate": 1.8453997451005313e-05, + "loss": 0.2782, + "step": 13210 + }, + { + "epoch": 4.08, + "learning_rate": 1.8453730310218944e-05, + "loss": 0.281, + "step": 13211 + }, + { + "epoch": 4.08, + "learning_rate": 1.845346314828826e-05, + "loss": 0.2572, + "step": 13212 + }, + { + "epoch": 4.08, + "learning_rate": 1.845319596521392e-05, + "loss": 0.2455, + "step": 13213 + }, + { + "epoch": 4.08, + "learning_rate": 1.8452928760996593e-05, + "loss": 0.2761, + "step": 13214 + }, + { + "epoch": 4.08, + "learning_rate": 1.8452661535636955e-05, + "loss": 0.2782, + "step": 13215 + }, + { + "epoch": 4.08, + "learning_rate": 1.8452394289135666e-05, + "loss": 0.2634, + "step": 13216 + }, + { + "epoch": 4.08, + "learning_rate": 1.8452127021493393e-05, + "loss": 0.2555, + "step": 13217 + }, + { + "epoch": 4.08, + "learning_rate": 1.8451859732710814e-05, + "loss": 0.2956, + "step": 13218 + }, + { + "epoch": 4.08, + "learning_rate": 1.845159242278859e-05, + "loss": 0.27, + "step": 13219 + }, + { + "epoch": 4.08, + "learning_rate": 1.8451325091727392e-05, + "loss": 0.2812, + "step": 13220 + }, + { + "epoch": 4.08, + "learning_rate": 1.8451057739527887e-05, + "loss": 0.2922, + "step": 13221 + }, + { + "epoch": 4.08, + "learning_rate": 1.845079036619075e-05, + "loss": 0.2682, + "step": 13222 + }, + { + "epoch": 4.08, + "learning_rate": 1.8450522971716643e-05, + "loss": 0.29, + "step": 13223 + }, + { + "epoch": 4.08, + "learning_rate": 1.8450255556106236e-05, + "loss": 0.2706, + "step": 13224 + }, + { + "epoch": 4.08, + "learning_rate": 1.84499881193602e-05, + "loss": 0.2663, + "step": 13225 + }, + { + "epoch": 4.08, + "learning_rate": 1.84497206614792e-05, + "loss": 0.2862, + "step": 13226 + }, + { + "epoch": 4.08, + "learning_rate": 1.844945318246391e-05, + "loss": 0.2684, + "step": 13227 + }, + { + "epoch": 4.09, + "learning_rate": 1.8449185682314992e-05, + "loss": 0.2716, + "step": 13228 + }, + { + "epoch": 4.09, + "learning_rate": 1.844891816103312e-05, + "loss": 0.271, + "step": 13229 + }, + { + "epoch": 4.09, + "learning_rate": 1.8448650618618968e-05, + "loss": 0.3042, + "step": 13230 + }, + { + "epoch": 4.09, + "learning_rate": 1.84483830550732e-05, + "loss": 0.273, + "step": 13231 + }, + { + "epoch": 4.09, + "learning_rate": 1.844811547039648e-05, + "loss": 0.2643, + "step": 13232 + }, + { + "epoch": 4.09, + "learning_rate": 1.8447847864589486e-05, + "loss": 0.2684, + "step": 13233 + }, + { + "epoch": 4.09, + "learning_rate": 1.8447580237652882e-05, + "loss": 0.2813, + "step": 13234 + }, + { + "epoch": 4.09, + "learning_rate": 1.844731258958734e-05, + "loss": 0.2601, + "step": 13235 + }, + { + "epoch": 4.09, + "learning_rate": 1.8447044920393527e-05, + "loss": 0.2526, + "step": 13236 + }, + { + "epoch": 4.09, + "learning_rate": 1.8446777230072114e-05, + "loss": 0.2784, + "step": 13237 + }, + { + "epoch": 4.09, + "learning_rate": 1.844650951862377e-05, + "loss": 0.2821, + "step": 13238 + }, + { + "epoch": 4.09, + "learning_rate": 1.844624178604917e-05, + "loss": 0.2728, + "step": 13239 + }, + { + "epoch": 4.09, + "learning_rate": 1.8445974032348976e-05, + "loss": 0.2894, + "step": 13240 + }, + { + "epoch": 4.09, + "learning_rate": 1.8445706257523862e-05, + "loss": 0.291, + "step": 13241 + }, + { + "epoch": 4.09, + "learning_rate": 1.844543846157449e-05, + "loss": 0.2897, + "step": 13242 + }, + { + "epoch": 4.09, + "learning_rate": 1.844517064450154e-05, + "loss": 0.2783, + "step": 13243 + }, + { + "epoch": 4.09, + "learning_rate": 1.844490280630568e-05, + "loss": 0.2691, + "step": 13244 + }, + { + "epoch": 4.09, + "learning_rate": 1.8444634946987578e-05, + "loss": 0.2573, + "step": 13245 + }, + { + "epoch": 4.09, + "learning_rate": 1.8444367066547898e-05, + "loss": 0.2844, + "step": 13246 + }, + { + "epoch": 4.09, + "learning_rate": 1.8444099164987323e-05, + "loss": 0.2845, + "step": 13247 + }, + { + "epoch": 4.09, + "learning_rate": 1.844383124230651e-05, + "loss": 0.2897, + "step": 13248 + }, + { + "epoch": 4.09, + "learning_rate": 1.844356329850614e-05, + "loss": 0.2565, + "step": 13249 + }, + { + "epoch": 4.09, + "learning_rate": 1.8443295333586874e-05, + "loss": 0.2929, + "step": 13250 + }, + { + "epoch": 4.09, + "learning_rate": 1.844302734754939e-05, + "loss": 0.2818, + "step": 13251 + }, + { + "epoch": 4.09, + "learning_rate": 1.8442759340394352e-05, + "loss": 0.2804, + "step": 13252 + }, + { + "epoch": 4.09, + "learning_rate": 1.8442491312122436e-05, + "loss": 0.2877, + "step": 13253 + }, + { + "epoch": 4.09, + "learning_rate": 1.8442223262734303e-05, + "loss": 0.2745, + "step": 13254 + }, + { + "epoch": 4.09, + "learning_rate": 1.8441955192230635e-05, + "loss": 0.2913, + "step": 13255 + }, + { + "epoch": 4.09, + "learning_rate": 1.84416871006121e-05, + "loss": 0.2717, + "step": 13256 + }, + { + "epoch": 4.09, + "learning_rate": 1.844141898787936e-05, + "loss": 0.2746, + "step": 13257 + }, + { + "epoch": 4.09, + "learning_rate": 1.8441150854033094e-05, + "loss": 0.2702, + "step": 13258 + }, + { + "epoch": 4.09, + "learning_rate": 1.844088269907397e-05, + "loss": 0.2607, + "step": 13259 + }, + { + "epoch": 4.1, + "learning_rate": 1.8440614523002658e-05, + "loss": 0.2867, + "step": 13260 + }, + { + "epoch": 4.1, + "learning_rate": 1.8440346325819832e-05, + "loss": 0.2703, + "step": 13261 + }, + { + "epoch": 4.1, + "learning_rate": 1.8440078107526157e-05, + "loss": 0.2711, + "step": 13262 + }, + { + "epoch": 4.1, + "learning_rate": 1.843980986812231e-05, + "loss": 0.2846, + "step": 13263 + }, + { + "epoch": 4.1, + "learning_rate": 1.843954160760896e-05, + "loss": 0.2948, + "step": 13264 + }, + { + "epoch": 4.1, + "learning_rate": 1.8439273325986777e-05, + "loss": 0.2647, + "step": 13265 + }, + { + "epoch": 4.1, + "learning_rate": 1.8439005023256426e-05, + "loss": 0.2768, + "step": 13266 + }, + { + "epoch": 4.1, + "learning_rate": 1.843873669941859e-05, + "loss": 0.2789, + "step": 13267 + }, + { + "epoch": 4.1, + "learning_rate": 1.8438468354473933e-05, + "loss": 0.2818, + "step": 13268 + }, + { + "epoch": 4.1, + "learning_rate": 1.843819998842313e-05, + "loss": 0.2812, + "step": 13269 + }, + { + "epoch": 4.1, + "learning_rate": 1.843793160126685e-05, + "loss": 0.2643, + "step": 13270 + }, + { + "epoch": 4.1, + "learning_rate": 1.8437663193005758e-05, + "loss": 0.2715, + "step": 13271 + }, + { + "epoch": 4.1, + "learning_rate": 1.8437394763640535e-05, + "loss": 0.2789, + "step": 13272 + }, + { + "epoch": 4.1, + "learning_rate": 1.843712631317185e-05, + "loss": 0.2826, + "step": 13273 + }, + { + "epoch": 4.1, + "learning_rate": 1.843685784160037e-05, + "loss": 0.2795, + "step": 13274 + }, + { + "epoch": 4.1, + "learning_rate": 1.8436589348926775e-05, + "loss": 0.2776, + "step": 13275 + }, + { + "epoch": 4.1, + "learning_rate": 1.8436320835151728e-05, + "loss": 0.2739, + "step": 13276 + }, + { + "epoch": 4.1, + "learning_rate": 1.8436052300275904e-05, + "loss": 0.27, + "step": 13277 + }, + { + "epoch": 4.1, + "learning_rate": 1.8435783744299974e-05, + "loss": 0.261, + "step": 13278 + }, + { + "epoch": 4.1, + "learning_rate": 1.843551516722461e-05, + "loss": 0.2901, + "step": 13279 + }, + { + "epoch": 4.1, + "learning_rate": 1.8435246569050488e-05, + "loss": 0.2712, + "step": 13280 + }, + { + "epoch": 4.1, + "learning_rate": 1.843497794977827e-05, + "loss": 0.2716, + "step": 13281 + }, + { + "epoch": 4.1, + "learning_rate": 1.843470930940864e-05, + "loss": 0.2796, + "step": 13282 + }, + { + "epoch": 4.1, + "learning_rate": 1.843444064794226e-05, + "loss": 0.2736, + "step": 13283 + }, + { + "epoch": 4.1, + "learning_rate": 1.8434171965379802e-05, + "loss": 0.2938, + "step": 13284 + }, + { + "epoch": 4.1, + "learning_rate": 1.8433903261721947e-05, + "loss": 0.2751, + "step": 13285 + }, + { + "epoch": 4.1, + "learning_rate": 1.8433634536969363e-05, + "loss": 0.2796, + "step": 13286 + }, + { + "epoch": 4.1, + "learning_rate": 1.8433365791122714e-05, + "loss": 0.263, + "step": 13287 + }, + { + "epoch": 4.1, + "learning_rate": 1.8433097024182685e-05, + "loss": 0.2853, + "step": 13288 + }, + { + "epoch": 4.1, + "learning_rate": 1.843282823614994e-05, + "loss": 0.2738, + "step": 13289 + }, + { + "epoch": 4.1, + "learning_rate": 1.8432559427025153e-05, + "loss": 0.2818, + "step": 13290 + }, + { + "epoch": 4.1, + "learning_rate": 1.8432290596809e-05, + "loss": 0.2605, + "step": 13291 + }, + { + "epoch": 4.1, + "learning_rate": 1.8432021745502147e-05, + "loss": 0.2877, + "step": 13292 + }, + { + "epoch": 4.11, + "learning_rate": 1.843175287310527e-05, + "loss": 0.2837, + "step": 13293 + }, + { + "epoch": 4.11, + "learning_rate": 1.8431483979619043e-05, + "loss": 0.2706, + "step": 13294 + }, + { + "epoch": 4.11, + "learning_rate": 1.8431215065044136e-05, + "loss": 0.2646, + "step": 13295 + }, + { + "epoch": 4.11, + "learning_rate": 1.843094612938122e-05, + "loss": 0.2765, + "step": 13296 + }, + { + "epoch": 4.11, + "learning_rate": 1.843067717263097e-05, + "loss": 0.2782, + "step": 13297 + }, + { + "epoch": 4.11, + "learning_rate": 1.843040819479406e-05, + "loss": 0.2529, + "step": 13298 + }, + { + "epoch": 4.11, + "learning_rate": 1.8430139195871167e-05, + "loss": 0.2621, + "step": 13299 + }, + { + "epoch": 4.11, + "learning_rate": 1.842987017586295e-05, + "loss": 0.2745, + "step": 13300 + }, + { + "epoch": 4.11, + "learning_rate": 1.8429601134770094e-05, + "loss": 0.2634, + "step": 13301 + }, + { + "epoch": 4.11, + "learning_rate": 1.842933207259327e-05, + "loss": 0.2653, + "step": 13302 + }, + { + "epoch": 4.11, + "learning_rate": 1.8429062989333146e-05, + "loss": 0.2752, + "step": 13303 + }, + { + "epoch": 4.11, + "learning_rate": 1.84287938849904e-05, + "loss": 0.2952, + "step": 13304 + }, + { + "epoch": 4.11, + "learning_rate": 1.84285247595657e-05, + "loss": 0.3009, + "step": 13305 + }, + { + "epoch": 4.11, + "learning_rate": 1.8428255613059724e-05, + "loss": 0.2684, + "step": 13306 + }, + { + "epoch": 4.11, + "learning_rate": 1.8427986445473145e-05, + "loss": 0.278, + "step": 13307 + }, + { + "epoch": 4.11, + "learning_rate": 1.8427717256806633e-05, + "loss": 0.2927, + "step": 13308 + }, + { + "epoch": 4.11, + "learning_rate": 1.8427448047060866e-05, + "loss": 0.2716, + "step": 13309 + }, + { + "epoch": 4.11, + "learning_rate": 1.842717881623651e-05, + "loss": 0.2711, + "step": 13310 + }, + { + "epoch": 4.11, + "learning_rate": 1.8426909564334247e-05, + "loss": 0.2763, + "step": 13311 + }, + { + "epoch": 4.11, + "learning_rate": 1.8426640291354743e-05, + "loss": 0.2686, + "step": 13312 + }, + { + "epoch": 4.11, + "learning_rate": 1.8426370997298674e-05, + "loss": 0.2564, + "step": 13313 + }, + { + "epoch": 4.11, + "learning_rate": 1.8426101682166718e-05, + "loss": 0.263, + "step": 13314 + }, + { + "epoch": 4.11, + "learning_rate": 1.842583234595954e-05, + "loss": 0.2649, + "step": 13315 + }, + { + "epoch": 4.11, + "learning_rate": 1.8425562988677823e-05, + "loss": 0.2715, + "step": 13316 + }, + { + "epoch": 4.11, + "learning_rate": 1.8425293610322237e-05, + "loss": 0.2681, + "step": 13317 + }, + { + "epoch": 4.11, + "learning_rate": 1.842502421089345e-05, + "loss": 0.2809, + "step": 13318 + }, + { + "epoch": 4.11, + "learning_rate": 1.8424754790392146e-05, + "loss": 0.2766, + "step": 13319 + }, + { + "epoch": 4.11, + "learning_rate": 1.842448534881899e-05, + "loss": 0.2774, + "step": 13320 + }, + { + "epoch": 4.11, + "learning_rate": 1.8424215886174658e-05, + "loss": 0.2752, + "step": 13321 + }, + { + "epoch": 4.11, + "learning_rate": 1.842394640245983e-05, + "loss": 0.2934, + "step": 13322 + }, + { + "epoch": 4.11, + "learning_rate": 1.8423676897675172e-05, + "loss": 0.2778, + "step": 13323 + }, + { + "epoch": 4.11, + "learning_rate": 1.8423407371821365e-05, + "loss": 0.2636, + "step": 13324 + }, + { + "epoch": 4.12, + "learning_rate": 1.842313782489908e-05, + "loss": 0.2438, + "step": 13325 + }, + { + "epoch": 4.12, + "learning_rate": 1.842286825690899e-05, + "loss": 0.262, + "step": 13326 + }, + { + "epoch": 4.12, + "learning_rate": 1.842259866785177e-05, + "loss": 0.3007, + "step": 13327 + }, + { + "epoch": 4.12, + "learning_rate": 1.8422329057728095e-05, + "loss": 0.2828, + "step": 13328 + }, + { + "epoch": 4.12, + "learning_rate": 1.8422059426538635e-05, + "loss": 0.2634, + "step": 13329 + }, + { + "epoch": 4.12, + "learning_rate": 1.8421789774284073e-05, + "loss": 0.2985, + "step": 13330 + }, + { + "epoch": 4.12, + "learning_rate": 1.8421520100965078e-05, + "loss": 0.2738, + "step": 13331 + }, + { + "epoch": 4.12, + "learning_rate": 1.8421250406582322e-05, + "loss": 0.2992, + "step": 13332 + }, + { + "epoch": 4.12, + "learning_rate": 1.8420980691136486e-05, + "loss": 0.2671, + "step": 13333 + }, + { + "epoch": 4.12, + "learning_rate": 1.842071095462824e-05, + "loss": 0.2743, + "step": 13334 + }, + { + "epoch": 4.12, + "learning_rate": 1.8420441197058264e-05, + "loss": 0.2707, + "step": 13335 + }, + { + "epoch": 4.12, + "learning_rate": 1.8420171418427223e-05, + "loss": 0.2772, + "step": 13336 + }, + { + "epoch": 4.12, + "learning_rate": 1.84199016187358e-05, + "loss": 0.2976, + "step": 13337 + }, + { + "epoch": 4.12, + "learning_rate": 1.8419631797984668e-05, + "loss": 0.2862, + "step": 13338 + }, + { + "epoch": 4.12, + "learning_rate": 1.84193619561745e-05, + "loss": 0.2663, + "step": 13339 + }, + { + "epoch": 4.12, + "learning_rate": 1.8419092093305974e-05, + "loss": 0.2532, + "step": 13340 + }, + { + "epoch": 4.12, + "learning_rate": 1.8418822209379762e-05, + "loss": 0.2727, + "step": 13341 + }, + { + "epoch": 4.12, + "learning_rate": 1.841855230439654e-05, + "loss": 0.2771, + "step": 13342 + }, + { + "epoch": 4.12, + "learning_rate": 1.8418282378356983e-05, + "loss": 0.263, + "step": 13343 + }, + { + "epoch": 4.12, + "learning_rate": 1.8418012431261765e-05, + "loss": 0.2722, + "step": 13344 + }, + { + "epoch": 4.12, + "learning_rate": 1.8417742463111564e-05, + "loss": 0.2765, + "step": 13345 + }, + { + "epoch": 4.12, + "learning_rate": 1.8417472473907054e-05, + "loss": 0.279, + "step": 13346 + }, + { + "epoch": 4.12, + "learning_rate": 1.841720246364891e-05, + "loss": 0.2643, + "step": 13347 + }, + { + "epoch": 4.12, + "learning_rate": 1.8416932432337807e-05, + "loss": 0.2776, + "step": 13348 + }, + { + "epoch": 4.12, + "learning_rate": 1.8416662379974425e-05, + "loss": 0.2778, + "step": 13349 + }, + { + "epoch": 4.12, + "learning_rate": 1.8416392306559428e-05, + "loss": 0.2608, + "step": 13350 + }, + { + "epoch": 4.12, + "learning_rate": 1.8416122212093504e-05, + "loss": 0.2611, + "step": 13351 + }, + { + "epoch": 4.12, + "learning_rate": 1.841585209657732e-05, + "loss": 0.2786, + "step": 13352 + }, + { + "epoch": 4.12, + "learning_rate": 1.841558196001156e-05, + "loss": 0.2674, + "step": 13353 + }, + { + "epoch": 4.12, + "learning_rate": 1.841531180239689e-05, + "loss": 0.297, + "step": 13354 + }, + { + "epoch": 4.12, + "learning_rate": 1.8415041623733993e-05, + "loss": 0.2807, + "step": 13355 + }, + { + "epoch": 4.12, + "learning_rate": 1.8414771424023537e-05, + "loss": 0.2783, + "step": 13356 + }, + { + "epoch": 4.13, + "learning_rate": 1.8414501203266207e-05, + "loss": 0.2727, + "step": 13357 + }, + { + "epoch": 4.13, + "learning_rate": 1.8414230961462676e-05, + "loss": 0.2669, + "step": 13358 + }, + { + "epoch": 4.13, + "learning_rate": 1.841396069861362e-05, + "loss": 0.267, + "step": 13359 + }, + { + "epoch": 4.13, + "learning_rate": 1.8413690414719707e-05, + "loss": 0.2792, + "step": 13360 + }, + { + "epoch": 4.13, + "learning_rate": 1.8413420109781627e-05, + "loss": 0.2775, + "step": 13361 + }, + { + "epoch": 4.13, + "learning_rate": 1.8413149783800043e-05, + "loss": 0.2836, + "step": 13362 + }, + { + "epoch": 4.13, + "learning_rate": 1.841287943677564e-05, + "loss": 0.2753, + "step": 13363 + }, + { + "epoch": 4.13, + "learning_rate": 1.841260906870909e-05, + "loss": 0.2813, + "step": 13364 + }, + { + "epoch": 4.13, + "learning_rate": 1.841233867960107e-05, + "loss": 0.2721, + "step": 13365 + }, + { + "epoch": 4.13, + "learning_rate": 1.8412068269452258e-05, + "loss": 0.2694, + "step": 13366 + }, + { + "epoch": 4.13, + "learning_rate": 1.8411797838263328e-05, + "loss": 0.2494, + "step": 13367 + }, + { + "epoch": 4.13, + "learning_rate": 1.8411527386034956e-05, + "loss": 0.2547, + "step": 13368 + }, + { + "epoch": 4.13, + "learning_rate": 1.8411256912767824e-05, + "loss": 0.2925, + "step": 13369 + }, + { + "epoch": 4.13, + "learning_rate": 1.84109864184626e-05, + "loss": 0.2602, + "step": 13370 + }, + { + "epoch": 4.13, + "learning_rate": 1.841071590311997e-05, + "loss": 0.2465, + "step": 13371 + }, + { + "epoch": 4.13, + "learning_rate": 1.8410445366740603e-05, + "loss": 0.2895, + "step": 13372 + }, + { + "epoch": 4.13, + "learning_rate": 1.8410174809325176e-05, + "loss": 0.2694, + "step": 13373 + }, + { + "epoch": 4.13, + "learning_rate": 1.840990423087437e-05, + "loss": 0.2991, + "step": 13374 + }, + { + "epoch": 4.13, + "learning_rate": 1.8409633631388856e-05, + "loss": 0.2657, + "step": 13375 + }, + { + "epoch": 4.13, + "learning_rate": 1.840936301086932e-05, + "loss": 0.2531, + "step": 13376 + }, + { + "epoch": 4.13, + "learning_rate": 1.840909236931643e-05, + "loss": 0.2377, + "step": 13377 + }, + { + "epoch": 4.13, + "learning_rate": 1.8408821706730867e-05, + "loss": 0.2879, + "step": 13378 + }, + { + "epoch": 4.13, + "learning_rate": 1.8408551023113308e-05, + "loss": 0.2721, + "step": 13379 + }, + { + "epoch": 4.13, + "learning_rate": 1.8408280318464425e-05, + "loss": 0.2844, + "step": 13380 + }, + { + "epoch": 4.13, + "learning_rate": 1.8408009592784907e-05, + "loss": 0.2743, + "step": 13381 + }, + { + "epoch": 4.13, + "learning_rate": 1.8407738846075418e-05, + "loss": 0.2728, + "step": 13382 + }, + { + "epoch": 4.13, + "learning_rate": 1.8407468078336645e-05, + "loss": 0.2624, + "step": 13383 + }, + { + "epoch": 4.13, + "learning_rate": 1.8407197289569256e-05, + "loss": 0.2687, + "step": 13384 + }, + { + "epoch": 4.13, + "learning_rate": 1.8406926479773935e-05, + "loss": 0.2857, + "step": 13385 + }, + { + "epoch": 4.13, + "learning_rate": 1.8406655648951356e-05, + "loss": 0.2621, + "step": 13386 + }, + { + "epoch": 4.13, + "learning_rate": 1.84063847971022e-05, + "loss": 0.2783, + "step": 13387 + }, + { + "epoch": 4.13, + "learning_rate": 1.8406113924227145e-05, + "loss": 0.2904, + "step": 13388 + }, + { + "epoch": 4.13, + "learning_rate": 1.8405843030326863e-05, + "loss": 0.2931, + "step": 13389 + }, + { + "epoch": 4.14, + "learning_rate": 1.8405572115402034e-05, + "loss": 0.2585, + "step": 13390 + }, + { + "epoch": 4.14, + "learning_rate": 1.8405301179453333e-05, + "loss": 0.266, + "step": 13391 + }, + { + "epoch": 4.14, + "learning_rate": 1.8405030222481446e-05, + "loss": 0.2807, + "step": 13392 + }, + { + "epoch": 4.14, + "learning_rate": 1.8404759244487046e-05, + "loss": 0.2844, + "step": 13393 + }, + { + "epoch": 4.14, + "learning_rate": 1.8404488245470806e-05, + "loss": 0.2916, + "step": 13394 + }, + { + "epoch": 4.14, + "learning_rate": 1.840421722543341e-05, + "loss": 0.2787, + "step": 13395 + }, + { + "epoch": 4.14, + "learning_rate": 1.8403946184375533e-05, + "loss": 0.2927, + "step": 13396 + }, + { + "epoch": 4.14, + "learning_rate": 1.8403675122297856e-05, + "loss": 0.2723, + "step": 13397 + }, + { + "epoch": 4.14, + "learning_rate": 1.8403404039201052e-05, + "loss": 0.2636, + "step": 13398 + }, + { + "epoch": 4.14, + "learning_rate": 1.8403132935085804e-05, + "loss": 0.2814, + "step": 13399 + }, + { + "epoch": 4.14, + "learning_rate": 1.840286180995279e-05, + "loss": 0.2768, + "step": 13400 + }, + { + "epoch": 4.14, + "learning_rate": 1.840259066380268e-05, + "loss": 0.2779, + "step": 13401 + }, + { + "epoch": 4.14, + "learning_rate": 1.840231949663616e-05, + "loss": 0.2627, + "step": 13402 + }, + { + "epoch": 4.14, + "learning_rate": 1.8402048308453908e-05, + "loss": 0.274, + "step": 13403 + }, + { + "epoch": 4.14, + "learning_rate": 1.8401777099256602e-05, + "loss": 0.2922, + "step": 13404 + }, + { + "epoch": 4.14, + "learning_rate": 1.8401505869044918e-05, + "loss": 0.2637, + "step": 13405 + }, + { + "epoch": 4.14, + "learning_rate": 1.8401234617819536e-05, + "loss": 0.2536, + "step": 13406 + }, + { + "epoch": 4.14, + "learning_rate": 1.8400963345581132e-05, + "loss": 0.2619, + "step": 13407 + }, + { + "epoch": 4.14, + "learning_rate": 1.8400692052330386e-05, + "loss": 0.2826, + "step": 13408 + }, + { + "epoch": 4.14, + "learning_rate": 1.8400420738067978e-05, + "loss": 0.2919, + "step": 13409 + }, + { + "epoch": 4.14, + "learning_rate": 1.8400149402794586e-05, + "loss": 0.2751, + "step": 13410 + }, + { + "epoch": 4.14, + "learning_rate": 1.8399878046510887e-05, + "loss": 0.2701, + "step": 13411 + }, + { + "epoch": 4.14, + "learning_rate": 1.8399606669217566e-05, + "loss": 0.2772, + "step": 13412 + }, + { + "epoch": 4.14, + "learning_rate": 1.839933527091529e-05, + "loss": 0.2774, + "step": 13413 + }, + { + "epoch": 4.14, + "learning_rate": 1.8399063851604747e-05, + "loss": 0.2575, + "step": 13414 + }, + { + "epoch": 4.14, + "learning_rate": 1.8398792411286614e-05, + "loss": 0.2875, + "step": 13415 + }, + { + "epoch": 4.14, + "learning_rate": 1.839852094996157e-05, + "loss": 0.2793, + "step": 13416 + }, + { + "epoch": 4.14, + "learning_rate": 1.8398249467630295e-05, + "loss": 0.2665, + "step": 13417 + }, + { + "epoch": 4.14, + "learning_rate": 1.839797796429346e-05, + "loss": 0.2681, + "step": 13418 + }, + { + "epoch": 4.14, + "learning_rate": 1.8397706439951757e-05, + "loss": 0.2796, + "step": 13419 + }, + { + "epoch": 4.14, + "learning_rate": 1.8397434894605856e-05, + "loss": 0.258, + "step": 13420 + }, + { + "epoch": 4.14, + "learning_rate": 1.8397163328256437e-05, + "loss": 0.2823, + "step": 13421 + }, + { + "epoch": 4.15, + "learning_rate": 1.8396891740904183e-05, + "loss": 0.2568, + "step": 13422 + }, + { + "epoch": 4.15, + "learning_rate": 1.839662013254977e-05, + "loss": 0.2801, + "step": 13423 + }, + { + "epoch": 4.15, + "learning_rate": 1.839634850319388e-05, + "loss": 0.2814, + "step": 13424 + }, + { + "epoch": 4.15, + "learning_rate": 1.8396076852837192e-05, + "loss": 0.2716, + "step": 13425 + }, + { + "epoch": 4.15, + "learning_rate": 1.839580518148038e-05, + "loss": 0.2732, + "step": 13426 + }, + { + "epoch": 4.15, + "learning_rate": 1.8395533489124133e-05, + "loss": 0.2621, + "step": 13427 + }, + { + "epoch": 4.15, + "learning_rate": 1.839526177576912e-05, + "loss": 0.2852, + "step": 13428 + }, + { + "epoch": 4.15, + "learning_rate": 1.8394990041416034e-05, + "loss": 0.2501, + "step": 13429 + }, + { + "epoch": 4.15, + "learning_rate": 1.839471828606554e-05, + "loss": 0.2759, + "step": 13430 + }, + { + "epoch": 4.15, + "learning_rate": 1.839444650971833e-05, + "loss": 0.2867, + "step": 13431 + }, + { + "epoch": 4.15, + "learning_rate": 1.839417471237507e-05, + "loss": 0.2947, + "step": 13432 + }, + { + "epoch": 4.15, + "learning_rate": 1.8393902894036454e-05, + "loss": 0.2742, + "step": 13433 + }, + { + "epoch": 4.15, + "learning_rate": 1.8393631054703157e-05, + "loss": 0.267, + "step": 13434 + }, + { + "epoch": 4.15, + "learning_rate": 1.8393359194375854e-05, + "loss": 0.2703, + "step": 13435 + }, + { + "epoch": 4.15, + "learning_rate": 1.8393087313055232e-05, + "loss": 0.2648, + "step": 13436 + }, + { + "epoch": 4.15, + "learning_rate": 1.8392815410741965e-05, + "loss": 0.2922, + "step": 13437 + }, + { + "epoch": 4.15, + "learning_rate": 1.8392543487436736e-05, + "loss": 0.2709, + "step": 13438 + }, + { + "epoch": 4.15, + "learning_rate": 1.8392271543140227e-05, + "loss": 0.2558, + "step": 13439 + }, + { + "epoch": 4.15, + "learning_rate": 1.8391999577853114e-05, + "loss": 0.2664, + "step": 13440 + }, + { + "epoch": 4.15, + "learning_rate": 1.8391727591576083e-05, + "loss": 0.2865, + "step": 13441 + }, + { + "epoch": 4.15, + "learning_rate": 1.839145558430981e-05, + "loss": 0.2818, + "step": 13442 + }, + { + "epoch": 4.15, + "learning_rate": 1.8391183556054973e-05, + "loss": 0.2743, + "step": 13443 + }, + { + "epoch": 4.15, + "learning_rate": 1.8390911506812258e-05, + "loss": 0.2719, + "step": 13444 + }, + { + "epoch": 4.15, + "learning_rate": 1.8390639436582343e-05, + "loss": 0.2875, + "step": 13445 + }, + { + "epoch": 4.15, + "learning_rate": 1.8390367345365906e-05, + "loss": 0.2695, + "step": 13446 + }, + { + "epoch": 4.15, + "learning_rate": 1.8390095233163632e-05, + "loss": 0.2849, + "step": 13447 + }, + { + "epoch": 4.15, + "learning_rate": 1.8389823099976198e-05, + "loss": 0.2619, + "step": 13448 + }, + { + "epoch": 4.15, + "learning_rate": 1.8389550945804288e-05, + "loss": 0.2905, + "step": 13449 + }, + { + "epoch": 4.15, + "learning_rate": 1.838927877064858e-05, + "loss": 0.2769, + "step": 13450 + }, + { + "epoch": 4.15, + "learning_rate": 1.8389006574509755e-05, + "loss": 0.2691, + "step": 13451 + }, + { + "epoch": 4.15, + "learning_rate": 1.8388734357388495e-05, + "loss": 0.2637, + "step": 13452 + }, + { + "epoch": 4.15, + "learning_rate": 1.8388462119285483e-05, + "loss": 0.2653, + "step": 13453 + }, + { + "epoch": 4.15, + "learning_rate": 1.8388189860201394e-05, + "loss": 0.2864, + "step": 13454 + }, + { + "epoch": 4.16, + "learning_rate": 1.838791758013691e-05, + "loss": 0.2709, + "step": 13455 + }, + { + "epoch": 4.16, + "learning_rate": 1.8387645279092717e-05, + "loss": 0.2502, + "step": 13456 + }, + { + "epoch": 4.16, + "learning_rate": 1.83873729570695e-05, + "loss": 0.2766, + "step": 13457 + }, + { + "epoch": 4.16, + "learning_rate": 1.8387100614067925e-05, + "loss": 0.2784, + "step": 13458 + }, + { + "epoch": 4.16, + "learning_rate": 1.8386828250088685e-05, + "loss": 0.279, + "step": 13459 + }, + { + "epoch": 4.16, + "learning_rate": 1.8386555865132454e-05, + "loss": 0.2803, + "step": 13460 + }, + { + "epoch": 4.16, + "learning_rate": 1.838628345919992e-05, + "loss": 0.2689, + "step": 13461 + }, + { + "epoch": 4.16, + "learning_rate": 1.8386011032291762e-05, + "loss": 0.2713, + "step": 13462 + }, + { + "epoch": 4.16, + "learning_rate": 1.838573858440866e-05, + "loss": 0.2785, + "step": 13463 + }, + { + "epoch": 4.16, + "learning_rate": 1.83854661155513e-05, + "loss": 0.266, + "step": 13464 + }, + { + "epoch": 4.16, + "learning_rate": 1.8385193625720354e-05, + "loss": 0.2867, + "step": 13465 + }, + { + "epoch": 4.16, + "learning_rate": 1.838492111491651e-05, + "loss": 0.2557, + "step": 13466 + }, + { + "epoch": 4.16, + "learning_rate": 1.8384648583140454e-05, + "loss": 0.2925, + "step": 13467 + }, + { + "epoch": 4.16, + "learning_rate": 1.8384376030392857e-05, + "loss": 0.2739, + "step": 13468 + }, + { + "epoch": 4.16, + "learning_rate": 1.8384103456674412e-05, + "loss": 0.2518, + "step": 13469 + }, + { + "epoch": 4.16, + "learning_rate": 1.838383086198579e-05, + "loss": 0.284, + "step": 13470 + }, + { + "epoch": 4.16, + "learning_rate": 1.838355824632768e-05, + "loss": 0.2633, + "step": 13471 + }, + { + "epoch": 4.16, + "learning_rate": 1.838328560970076e-05, + "loss": 0.2722, + "step": 13472 + }, + { + "epoch": 4.16, + "learning_rate": 1.8383012952105717e-05, + "loss": 0.27, + "step": 13473 + }, + { + "epoch": 4.16, + "learning_rate": 1.8382740273543228e-05, + "loss": 0.2566, + "step": 13474 + }, + { + "epoch": 4.16, + "learning_rate": 1.8382467574013976e-05, + "loss": 0.2823, + "step": 13475 + }, + { + "epoch": 4.16, + "learning_rate": 1.8382194853518647e-05, + "loss": 0.2841, + "step": 13476 + }, + { + "epoch": 4.16, + "learning_rate": 1.8381922112057917e-05, + "loss": 0.261, + "step": 13477 + }, + { + "epoch": 4.16, + "learning_rate": 1.8381649349632467e-05, + "loss": 0.2479, + "step": 13478 + }, + { + "epoch": 4.16, + "learning_rate": 1.838137656624299e-05, + "loss": 0.2732, + "step": 13479 + }, + { + "epoch": 4.16, + "learning_rate": 1.838110376189016e-05, + "loss": 0.2805, + "step": 13480 + }, + { + "epoch": 4.16, + "learning_rate": 1.8380830936574657e-05, + "loss": 0.267, + "step": 13481 + }, + { + "epoch": 4.16, + "learning_rate": 1.8380558090297175e-05, + "loss": 0.2817, + "step": 13482 + }, + { + "epoch": 4.16, + "learning_rate": 1.838028522305838e-05, + "loss": 0.2896, + "step": 13483 + }, + { + "epoch": 4.16, + "learning_rate": 1.8380012334858968e-05, + "loss": 0.2706, + "step": 13484 + }, + { + "epoch": 4.16, + "learning_rate": 1.8379739425699616e-05, + "loss": 0.272, + "step": 13485 + }, + { + "epoch": 4.16, + "learning_rate": 1.8379466495581006e-05, + "loss": 0.278, + "step": 13486 + }, + { + "epoch": 4.17, + "learning_rate": 1.8379193544503823e-05, + "loss": 0.2773, + "step": 13487 + }, + { + "epoch": 4.17, + "learning_rate": 1.837892057246875e-05, + "loss": 0.2524, + "step": 13488 + }, + { + "epoch": 4.17, + "learning_rate": 1.837864757947647e-05, + "loss": 0.2601, + "step": 13489 + }, + { + "epoch": 4.17, + "learning_rate": 1.837837456552766e-05, + "loss": 0.256, + "step": 13490 + }, + { + "epoch": 4.17, + "learning_rate": 1.8378101530623006e-05, + "loss": 0.2802, + "step": 13491 + }, + { + "epoch": 4.17, + "learning_rate": 1.8377828474763196e-05, + "loss": 0.2714, + "step": 13492 + }, + { + "epoch": 4.17, + "learning_rate": 1.8377555397948908e-05, + "loss": 0.2764, + "step": 13493 + }, + { + "epoch": 4.17, + "learning_rate": 1.8377282300180825e-05, + "loss": 0.2846, + "step": 13494 + }, + { + "epoch": 4.17, + "learning_rate": 1.837700918145963e-05, + "loss": 0.2885, + "step": 13495 + }, + { + "epoch": 4.17, + "learning_rate": 1.837673604178601e-05, + "loss": 0.2657, + "step": 13496 + }, + { + "epoch": 4.17, + "learning_rate": 1.8376462881160645e-05, + "loss": 0.2807, + "step": 13497 + }, + { + "epoch": 4.17, + "learning_rate": 1.837618969958422e-05, + "loss": 0.2689, + "step": 13498 + }, + { + "epoch": 4.17, + "learning_rate": 1.837591649705741e-05, + "loss": 0.2764, + "step": 13499 + }, + { + "epoch": 4.17, + "learning_rate": 1.837564327358091e-05, + "loss": 0.2657, + "step": 13500 + }, + { + "epoch": 4.17, + "learning_rate": 1.8375370029155397e-05, + "loss": 0.2823, + "step": 13501 + }, + { + "epoch": 4.17, + "learning_rate": 1.8375096763781557e-05, + "loss": 0.2784, + "step": 13502 + }, + { + "epoch": 4.17, + "learning_rate": 1.8374823477460074e-05, + "loss": 0.2832, + "step": 13503 + }, + { + "epoch": 4.17, + "learning_rate": 1.8374550170191628e-05, + "loss": 0.2739, + "step": 13504 + }, + { + "epoch": 4.17, + "learning_rate": 1.8374276841976905e-05, + "loss": 0.2692, + "step": 13505 + }, + { + "epoch": 4.17, + "learning_rate": 1.837400349281659e-05, + "loss": 0.2826, + "step": 13506 + }, + { + "epoch": 4.17, + "learning_rate": 1.8373730122711363e-05, + "loss": 0.2862, + "step": 13507 + }, + { + "epoch": 4.17, + "learning_rate": 1.837345673166191e-05, + "loss": 0.2789, + "step": 13508 + }, + { + "epoch": 4.17, + "learning_rate": 1.8373183319668912e-05, + "loss": 0.2342, + "step": 13509 + }, + { + "epoch": 4.17, + "learning_rate": 1.837290988673306e-05, + "loss": 0.2711, + "step": 13510 + }, + { + "epoch": 4.17, + "learning_rate": 1.8372636432855035e-05, + "loss": 0.2837, + "step": 13511 + }, + { + "epoch": 4.17, + "learning_rate": 1.837236295803551e-05, + "loss": 0.2757, + "step": 13512 + }, + { + "epoch": 4.17, + "learning_rate": 1.8372089462275183e-05, + "loss": 0.2675, + "step": 13513 + }, + { + "epoch": 4.17, + "learning_rate": 1.8371815945574734e-05, + "loss": 0.2853, + "step": 13514 + }, + { + "epoch": 4.17, + "learning_rate": 1.837154240793485e-05, + "loss": 0.2715, + "step": 13515 + }, + { + "epoch": 4.17, + "learning_rate": 1.8371268849356207e-05, + "loss": 0.2639, + "step": 13516 + }, + { + "epoch": 4.17, + "learning_rate": 1.8370995269839493e-05, + "loss": 0.2723, + "step": 13517 + }, + { + "epoch": 4.17, + "learning_rate": 1.8370721669385396e-05, + "loss": 0.2806, + "step": 13518 + }, + { + "epoch": 4.18, + "learning_rate": 1.8370448047994595e-05, + "loss": 0.2896, + "step": 13519 + }, + { + "epoch": 4.18, + "learning_rate": 1.8370174405667776e-05, + "loss": 0.2576, + "step": 13520 + }, + { + "epoch": 4.18, + "learning_rate": 1.836990074240563e-05, + "loss": 0.2818, + "step": 13521 + }, + { + "epoch": 4.18, + "learning_rate": 1.836962705820883e-05, + "loss": 0.3001, + "step": 13522 + }, + { + "epoch": 4.18, + "learning_rate": 1.8369353353078066e-05, + "loss": 0.2587, + "step": 13523 + }, + { + "epoch": 4.18, + "learning_rate": 1.8369079627014024e-05, + "loss": 0.2605, + "step": 13524 + }, + { + "epoch": 4.18, + "learning_rate": 1.836880588001739e-05, + "loss": 0.264, + "step": 13525 + }, + { + "epoch": 4.18, + "learning_rate": 1.8368532112088845e-05, + "loss": 0.2795, + "step": 13526 + }, + { + "epoch": 4.18, + "learning_rate": 1.8368258323229074e-05, + "loss": 0.2766, + "step": 13527 + }, + { + "epoch": 4.18, + "learning_rate": 1.8367984513438762e-05, + "loss": 0.2656, + "step": 13528 + }, + { + "epoch": 4.18, + "learning_rate": 1.8367710682718596e-05, + "loss": 0.2627, + "step": 13529 + }, + { + "epoch": 4.18, + "learning_rate": 1.8367436831069258e-05, + "loss": 0.2722, + "step": 13530 + }, + { + "epoch": 4.18, + "learning_rate": 1.8367162958491436e-05, + "loss": 0.2623, + "step": 13531 + }, + { + "epoch": 4.18, + "learning_rate": 1.836688906498581e-05, + "loss": 0.2676, + "step": 13532 + }, + { + "epoch": 4.18, + "learning_rate": 1.836661515055307e-05, + "loss": 0.2803, + "step": 13533 + }, + { + "epoch": 4.18, + "learning_rate": 1.8366341215193904e-05, + "loss": 0.2793, + "step": 13534 + }, + { + "epoch": 4.18, + "learning_rate": 1.836606725890899e-05, + "loss": 0.2753, + "step": 13535 + }, + { + "epoch": 4.18, + "learning_rate": 1.836579328169901e-05, + "loss": 0.2791, + "step": 13536 + }, + { + "epoch": 4.18, + "learning_rate": 1.836551928356466e-05, + "loss": 0.2646, + "step": 13537 + }, + { + "epoch": 4.18, + "learning_rate": 1.8365245264506622e-05, + "loss": 0.2797, + "step": 13538 + }, + { + "epoch": 4.18, + "learning_rate": 1.836497122452558e-05, + "loss": 0.2838, + "step": 13539 + }, + { + "epoch": 4.18, + "learning_rate": 1.8364697163622217e-05, + "loss": 0.2653, + "step": 13540 + }, + { + "epoch": 4.18, + "learning_rate": 1.8364423081797222e-05, + "loss": 0.2953, + "step": 13541 + }, + { + "epoch": 4.18, + "learning_rate": 1.836414897905128e-05, + "loss": 0.2756, + "step": 13542 + }, + { + "epoch": 4.18, + "learning_rate": 1.8363874855385073e-05, + "loss": 0.2631, + "step": 13543 + }, + { + "epoch": 4.18, + "learning_rate": 1.8363600710799293e-05, + "loss": 0.2857, + "step": 13544 + }, + { + "epoch": 4.18, + "learning_rate": 1.836332654529462e-05, + "loss": 0.2803, + "step": 13545 + }, + { + "epoch": 4.18, + "learning_rate": 1.836305235887174e-05, + "loss": 0.2532, + "step": 13546 + }, + { + "epoch": 4.18, + "learning_rate": 1.8362778151531344e-05, + "loss": 0.2607, + "step": 13547 + }, + { + "epoch": 4.18, + "learning_rate": 1.8362503923274112e-05, + "loss": 0.2724, + "step": 13548 + }, + { + "epoch": 4.18, + "learning_rate": 1.8362229674100737e-05, + "loss": 0.2637, + "step": 13549 + }, + { + "epoch": 4.18, + "learning_rate": 1.83619554040119e-05, + "loss": 0.2685, + "step": 13550 + }, + { + "epoch": 4.18, + "learning_rate": 1.8361681113008282e-05, + "loss": 0.2532, + "step": 13551 + }, + { + "epoch": 4.19, + "learning_rate": 1.8361406801090578e-05, + "loss": 0.2799, + "step": 13552 + }, + { + "epoch": 4.19, + "learning_rate": 1.8361132468259468e-05, + "loss": 0.2845, + "step": 13553 + }, + { + "epoch": 4.19, + "learning_rate": 1.8360858114515643e-05, + "loss": 0.264, + "step": 13554 + }, + { + "epoch": 4.19, + "learning_rate": 1.8360583739859788e-05, + "loss": 0.2721, + "step": 13555 + }, + { + "epoch": 4.19, + "learning_rate": 1.8360309344292587e-05, + "loss": 0.2513, + "step": 13556 + }, + { + "epoch": 4.19, + "learning_rate": 1.8360034927814723e-05, + "loss": 0.2657, + "step": 13557 + }, + { + "epoch": 4.19, + "learning_rate": 1.8359760490426893e-05, + "loss": 0.2667, + "step": 13558 + }, + { + "epoch": 4.19, + "learning_rate": 1.8359486032129777e-05, + "loss": 0.2848, + "step": 13559 + }, + { + "epoch": 4.19, + "learning_rate": 1.8359211552924062e-05, + "loss": 0.2838, + "step": 13560 + }, + { + "epoch": 4.19, + "learning_rate": 1.835893705281043e-05, + "loss": 0.278, + "step": 13561 + }, + { + "epoch": 4.19, + "learning_rate": 1.8358662531789572e-05, + "loss": 0.2827, + "step": 13562 + }, + { + "epoch": 4.19, + "learning_rate": 1.8358387989862182e-05, + "loss": 0.2557, + "step": 13563 + }, + { + "epoch": 4.19, + "learning_rate": 1.835811342702893e-05, + "loss": 0.2718, + "step": 13564 + }, + { + "epoch": 4.19, + "learning_rate": 1.8357838843290515e-05, + "loss": 0.2778, + "step": 13565 + }, + { + "epoch": 4.19, + "learning_rate": 1.8357564238647626e-05, + "loss": 0.2726, + "step": 13566 + }, + { + "epoch": 4.19, + "learning_rate": 1.835728961310094e-05, + "loss": 0.2733, + "step": 13567 + }, + { + "epoch": 4.19, + "learning_rate": 1.835701496665115e-05, + "loss": 0.2832, + "step": 13568 + }, + { + "epoch": 4.19, + "learning_rate": 1.8356740299298935e-05, + "loss": 0.2869, + "step": 13569 + }, + { + "epoch": 4.19, + "learning_rate": 1.8356465611044995e-05, + "loss": 0.2776, + "step": 13570 + }, + { + "epoch": 4.19, + "learning_rate": 1.8356190901890008e-05, + "loss": 0.2434, + "step": 13571 + }, + { + "epoch": 4.19, + "learning_rate": 1.8355916171834662e-05, + "loss": 0.2666, + "step": 13572 + }, + { + "epoch": 4.19, + "learning_rate": 1.835564142087965e-05, + "loss": 0.2609, + "step": 13573 + }, + { + "epoch": 4.19, + "learning_rate": 1.835536664902565e-05, + "loss": 0.2615, + "step": 13574 + }, + { + "epoch": 4.19, + "learning_rate": 1.835509185627336e-05, + "loss": 0.2776, + "step": 13575 + }, + { + "epoch": 4.19, + "learning_rate": 1.8354817042623456e-05, + "loss": 0.2646, + "step": 13576 + }, + { + "epoch": 4.19, + "learning_rate": 1.8354542208076632e-05, + "loss": 0.2782, + "step": 13577 + }, + { + "epoch": 4.19, + "learning_rate": 1.8354267352633573e-05, + "loss": 0.274, + "step": 13578 + }, + { + "epoch": 4.19, + "learning_rate": 1.8353992476294973e-05, + "loss": 0.2743, + "step": 13579 + }, + { + "epoch": 4.19, + "learning_rate": 1.835371757906151e-05, + "loss": 0.2786, + "step": 13580 + }, + { + "epoch": 4.19, + "learning_rate": 1.8353442660933877e-05, + "loss": 0.2748, + "step": 13581 + }, + { + "epoch": 4.19, + "learning_rate": 1.835316772191276e-05, + "loss": 0.2984, + "step": 13582 + }, + { + "epoch": 4.19, + "learning_rate": 1.8352892761998845e-05, + "loss": 0.2687, + "step": 13583 + }, + { + "epoch": 4.2, + "learning_rate": 1.8352617781192826e-05, + "loss": 0.264, + "step": 13584 + }, + { + "epoch": 4.2, + "learning_rate": 1.8352342779495384e-05, + "loss": 0.2639, + "step": 13585 + }, + { + "epoch": 4.2, + "learning_rate": 1.8352067756907208e-05, + "loss": 0.2709, + "step": 13586 + }, + { + "epoch": 4.2, + "learning_rate": 1.8351792713428988e-05, + "loss": 0.2702, + "step": 13587 + }, + { + "epoch": 4.2, + "learning_rate": 1.8351517649061414e-05, + "loss": 0.2776, + "step": 13588 + }, + { + "epoch": 4.2, + "learning_rate": 1.8351242563805163e-05, + "loss": 0.2662, + "step": 13589 + }, + { + "epoch": 4.2, + "learning_rate": 1.8350967457660938e-05, + "loss": 0.2744, + "step": 13590 + }, + { + "epoch": 4.2, + "learning_rate": 1.8350692330629423e-05, + "loss": 0.2611, + "step": 13591 + }, + { + "epoch": 4.2, + "learning_rate": 1.8350417182711298e-05, + "loss": 0.2796, + "step": 13592 + }, + { + "epoch": 4.2, + "learning_rate": 1.835014201390726e-05, + "loss": 0.2573, + "step": 13593 + }, + { + "epoch": 4.2, + "learning_rate": 1.834986682421799e-05, + "loss": 0.2477, + "step": 13594 + }, + { + "epoch": 4.2, + "learning_rate": 1.8349591613644186e-05, + "loss": 0.266, + "step": 13595 + }, + { + "epoch": 4.2, + "learning_rate": 1.8349316382186525e-05, + "loss": 0.27, + "step": 13596 + }, + { + "epoch": 4.2, + "learning_rate": 1.83490411298457e-05, + "loss": 0.262, + "step": 13597 + }, + { + "epoch": 4.2, + "learning_rate": 1.8348765856622404e-05, + "loss": 0.2672, + "step": 13598 + }, + { + "epoch": 4.2, + "learning_rate": 1.834849056251732e-05, + "loss": 0.2798, + "step": 13599 + }, + { + "epoch": 4.2, + "learning_rate": 1.834821524753114e-05, + "loss": 0.2683, + "step": 13600 + }, + { + "epoch": 4.2, + "learning_rate": 1.834793991166455e-05, + "loss": 0.2824, + "step": 13601 + }, + { + "epoch": 4.2, + "learning_rate": 1.8347664554918242e-05, + "loss": 0.2644, + "step": 13602 + }, + { + "epoch": 4.2, + "learning_rate": 1.83473891772929e-05, + "loss": 0.2994, + "step": 13603 + }, + { + "epoch": 4.2, + "learning_rate": 1.8347113778789215e-05, + "loss": 0.2688, + "step": 13604 + }, + { + "epoch": 4.2, + "learning_rate": 1.8346838359407876e-05, + "loss": 0.2795, + "step": 13605 + }, + { + "epoch": 4.2, + "learning_rate": 1.8346562919149574e-05, + "loss": 0.2636, + "step": 13606 + }, + { + "epoch": 4.2, + "learning_rate": 1.8346287458014993e-05, + "loss": 0.2924, + "step": 13607 + }, + { + "epoch": 4.2, + "learning_rate": 1.8346011976004827e-05, + "loss": 0.2538, + "step": 13608 + }, + { + "epoch": 4.2, + "learning_rate": 1.834573647311976e-05, + "loss": 0.2825, + "step": 13609 + }, + { + "epoch": 4.2, + "learning_rate": 1.834546094936049e-05, + "loss": 0.2638, + "step": 13610 + }, + { + "epoch": 4.2, + "learning_rate": 1.8345185404727695e-05, + "loss": 0.2751, + "step": 13611 + }, + { + "epoch": 4.2, + "learning_rate": 1.834490983922207e-05, + "loss": 0.2774, + "step": 13612 + }, + { + "epoch": 4.2, + "learning_rate": 1.8344634252844305e-05, + "loss": 0.2934, + "step": 13613 + }, + { + "epoch": 4.2, + "learning_rate": 1.8344358645595087e-05, + "loss": 0.2635, + "step": 13614 + }, + { + "epoch": 4.2, + "learning_rate": 1.8344083017475106e-05, + "loss": 0.2715, + "step": 13615 + }, + { + "epoch": 4.2, + "learning_rate": 1.834380736848505e-05, + "loss": 0.2869, + "step": 13616 + }, + { + "epoch": 4.21, + "learning_rate": 1.834353169862561e-05, + "loss": 0.2612, + "step": 13617 + }, + { + "epoch": 4.21, + "learning_rate": 1.8343256007897475e-05, + "loss": 0.267, + "step": 13618 + }, + { + "epoch": 4.21, + "learning_rate": 1.834298029630134e-05, + "loss": 0.2661, + "step": 13619 + }, + { + "epoch": 4.21, + "learning_rate": 1.8342704563837884e-05, + "loss": 0.2839, + "step": 13620 + }, + { + "epoch": 4.21, + "learning_rate": 1.8342428810507805e-05, + "loss": 0.2708, + "step": 13621 + }, + { + "epoch": 4.21, + "learning_rate": 1.834215303631179e-05, + "loss": 0.2787, + "step": 13622 + }, + { + "epoch": 4.21, + "learning_rate": 1.8341877241250527e-05, + "loss": 0.2688, + "step": 13623 + }, + { + "epoch": 4.21, + "learning_rate": 1.834160142532471e-05, + "loss": 0.2665, + "step": 13624 + }, + { + "epoch": 4.21, + "learning_rate": 1.8341325588535024e-05, + "loss": 0.2631, + "step": 13625 + }, + { + "epoch": 4.21, + "learning_rate": 1.8341049730882162e-05, + "loss": 0.2652, + "step": 13626 + }, + { + "epoch": 4.21, + "learning_rate": 1.8340773852366817e-05, + "loss": 0.2809, + "step": 13627 + }, + { + "epoch": 4.21, + "learning_rate": 1.834049795298967e-05, + "loss": 0.2722, + "step": 13628 + }, + { + "epoch": 4.21, + "learning_rate": 1.8340222032751418e-05, + "loss": 0.2755, + "step": 13629 + }, + { + "epoch": 4.21, + "learning_rate": 1.833994609165275e-05, + "loss": 0.2739, + "step": 13630 + }, + { + "epoch": 4.21, + "learning_rate": 1.8339670129694356e-05, + "loss": 0.2529, + "step": 13631 + }, + { + "epoch": 4.21, + "learning_rate": 1.8339394146876925e-05, + "loss": 0.254, + "step": 13632 + }, + { + "epoch": 4.21, + "learning_rate": 1.833911814320115e-05, + "loss": 0.2693, + "step": 13633 + }, + { + "epoch": 4.21, + "learning_rate": 1.8338842118667716e-05, + "loss": 0.2709, + "step": 13634 + }, + { + "epoch": 4.21, + "learning_rate": 1.8338566073277323e-05, + "loss": 0.2659, + "step": 13635 + }, + { + "epoch": 4.21, + "learning_rate": 1.833829000703065e-05, + "loss": 0.2709, + "step": 13636 + }, + { + "epoch": 4.21, + "learning_rate": 1.8338013919928394e-05, + "loss": 0.2828, + "step": 13637 + }, + { + "epoch": 4.21, + "learning_rate": 1.8337737811971245e-05, + "loss": 0.2521, + "step": 13638 + }, + { + "epoch": 4.21, + "learning_rate": 1.8337461683159894e-05, + "loss": 0.2875, + "step": 13639 + }, + { + "epoch": 4.21, + "learning_rate": 1.833718553349503e-05, + "loss": 0.291, + "step": 13640 + }, + { + "epoch": 4.21, + "learning_rate": 1.8336909362977343e-05, + "loss": 0.2602, + "step": 13641 + }, + { + "epoch": 4.21, + "learning_rate": 1.8336633171607527e-05, + "loss": 0.2686, + "step": 13642 + }, + { + "epoch": 4.21, + "learning_rate": 1.833635695938627e-05, + "loss": 0.2599, + "step": 13643 + }, + { + "epoch": 4.21, + "learning_rate": 1.8336080726314266e-05, + "loss": 0.2823, + "step": 13644 + }, + { + "epoch": 4.21, + "learning_rate": 1.83358044723922e-05, + "loss": 0.2351, + "step": 13645 + }, + { + "epoch": 4.21, + "learning_rate": 1.833552819762077e-05, + "loss": 0.2862, + "step": 13646 + }, + { + "epoch": 4.21, + "learning_rate": 1.8335251902000662e-05, + "loss": 0.2601, + "step": 13647 + }, + { + "epoch": 4.21, + "learning_rate": 1.833497558553257e-05, + "loss": 0.283, + "step": 13648 + }, + { + "epoch": 4.22, + "learning_rate": 1.833469924821718e-05, + "loss": 0.2748, + "step": 13649 + }, + { + "epoch": 4.22, + "learning_rate": 1.833442289005519e-05, + "loss": 0.2794, + "step": 13650 + }, + { + "epoch": 4.22, + "learning_rate": 1.8334146511047287e-05, + "loss": 0.263, + "step": 13651 + }, + { + "epoch": 4.22, + "learning_rate": 1.8333870111194164e-05, + "loss": 0.2646, + "step": 13652 + }, + { + "epoch": 4.22, + "learning_rate": 1.8333593690496513e-05, + "loss": 0.2489, + "step": 13653 + }, + { + "epoch": 4.22, + "learning_rate": 1.8333317248955024e-05, + "loss": 0.2629, + "step": 13654 + }, + { + "epoch": 4.22, + "learning_rate": 1.833304078657039e-05, + "loss": 0.2802, + "step": 13655 + }, + { + "epoch": 4.22, + "learning_rate": 1.8332764303343298e-05, + "loss": 0.2596, + "step": 13656 + }, + { + "epoch": 4.22, + "learning_rate": 1.8332487799274443e-05, + "loss": 0.2463, + "step": 13657 + }, + { + "epoch": 4.22, + "learning_rate": 1.8332211274364516e-05, + "loss": 0.263, + "step": 13658 + }, + { + "epoch": 4.22, + "learning_rate": 1.8331934728614214e-05, + "loss": 0.2656, + "step": 13659 + }, + { + "epoch": 4.22, + "learning_rate": 1.833165816202422e-05, + "loss": 0.2869, + "step": 13660 + }, + { + "epoch": 4.22, + "learning_rate": 1.833138157459523e-05, + "loss": 0.2645, + "step": 13661 + }, + { + "epoch": 4.22, + "learning_rate": 1.833110496632793e-05, + "loss": 0.2547, + "step": 13662 + }, + { + "epoch": 4.22, + "learning_rate": 1.8330828337223024e-05, + "loss": 0.2834, + "step": 13663 + }, + { + "epoch": 4.22, + "learning_rate": 1.8330551687281195e-05, + "loss": 0.2576, + "step": 13664 + }, + { + "epoch": 4.22, + "learning_rate": 1.8330275016503134e-05, + "loss": 0.2651, + "step": 13665 + }, + { + "epoch": 4.22, + "learning_rate": 1.832999832488954e-05, + "loss": 0.2878, + "step": 13666 + }, + { + "epoch": 4.22, + "learning_rate": 1.8329721612441097e-05, + "loss": 0.2897, + "step": 13667 + }, + { + "epoch": 4.22, + "learning_rate": 1.8329444879158503e-05, + "loss": 0.2792, + "step": 13668 + }, + { + "epoch": 4.22, + "learning_rate": 1.832916812504245e-05, + "loss": 0.2937, + "step": 13669 + }, + { + "epoch": 4.22, + "learning_rate": 1.8328891350093624e-05, + "loss": 0.2756, + "step": 13670 + }, + { + "epoch": 4.22, + "learning_rate": 1.8328614554312724e-05, + "loss": 0.2731, + "step": 13671 + }, + { + "epoch": 4.22, + "learning_rate": 1.832833773770044e-05, + "loss": 0.2828, + "step": 13672 + }, + { + "epoch": 4.22, + "learning_rate": 1.8328060900257464e-05, + "loss": 0.2532, + "step": 13673 + }, + { + "epoch": 4.22, + "learning_rate": 1.832778404198449e-05, + "loss": 0.2744, + "step": 13674 + }, + { + "epoch": 4.22, + "learning_rate": 1.832750716288221e-05, + "loss": 0.274, + "step": 13675 + }, + { + "epoch": 4.22, + "learning_rate": 1.832723026295131e-05, + "loss": 0.2867, + "step": 13676 + }, + { + "epoch": 4.22, + "learning_rate": 1.8326953342192492e-05, + "loss": 0.2709, + "step": 13677 + }, + { + "epoch": 4.22, + "learning_rate": 1.8326676400606444e-05, + "loss": 0.2742, + "step": 13678 + }, + { + "epoch": 4.22, + "learning_rate": 1.8326399438193862e-05, + "loss": 0.2617, + "step": 13679 + }, + { + "epoch": 4.22, + "learning_rate": 1.8326122454955434e-05, + "loss": 0.282, + "step": 13680 + }, + { + "epoch": 4.23, + "learning_rate": 1.8325845450891857e-05, + "loss": 0.2678, + "step": 13681 + }, + { + "epoch": 4.23, + "learning_rate": 1.8325568426003825e-05, + "loss": 0.2605, + "step": 13682 + }, + { + "epoch": 4.23, + "learning_rate": 1.832529138029202e-05, + "loss": 0.2779, + "step": 13683 + }, + { + "epoch": 4.23, + "learning_rate": 1.8325014313757148e-05, + "loss": 0.2687, + "step": 13684 + }, + { + "epoch": 4.23, + "learning_rate": 1.8324737226399895e-05, + "loss": 0.2799, + "step": 13685 + }, + { + "epoch": 4.23, + "learning_rate": 1.832446011822096e-05, + "loss": 0.2747, + "step": 13686 + }, + { + "epoch": 4.23, + "learning_rate": 1.8324182989221028e-05, + "loss": 0.2608, + "step": 13687 + }, + { + "epoch": 4.23, + "learning_rate": 1.8323905839400794e-05, + "loss": 0.2515, + "step": 13688 + }, + { + "epoch": 4.23, + "learning_rate": 1.8323628668760957e-05, + "loss": 0.2743, + "step": 13689 + }, + { + "epoch": 4.23, + "learning_rate": 1.8323351477302206e-05, + "loss": 0.2644, + "step": 13690 + }, + { + "epoch": 4.23, + "learning_rate": 1.8323074265025235e-05, + "loss": 0.2919, + "step": 13691 + }, + { + "epoch": 4.23, + "learning_rate": 1.8322797031930735e-05, + "loss": 0.2643, + "step": 13692 + }, + { + "epoch": 4.23, + "learning_rate": 1.8322519778019405e-05, + "loss": 0.2501, + "step": 13693 + }, + { + "epoch": 4.23, + "learning_rate": 1.832224250329193e-05, + "loss": 0.2876, + "step": 13694 + }, + { + "epoch": 4.23, + "learning_rate": 1.8321965207749012e-05, + "loss": 0.2478, + "step": 13695 + }, + { + "epoch": 4.23, + "learning_rate": 1.8321687891391343e-05, + "loss": 0.2681, + "step": 13696 + }, + { + "epoch": 4.23, + "learning_rate": 1.8321410554219615e-05, + "loss": 0.2515, + "step": 13697 + }, + { + "epoch": 4.23, + "learning_rate": 1.832113319623452e-05, + "loss": 0.2782, + "step": 13698 + }, + { + "epoch": 4.23, + "learning_rate": 1.8320855817436752e-05, + "loss": 0.2522, + "step": 13699 + }, + { + "epoch": 4.23, + "learning_rate": 1.8320578417827003e-05, + "loss": 0.2551, + "step": 13700 + }, + { + "epoch": 4.23, + "learning_rate": 1.8320300997405976e-05, + "loss": 0.2796, + "step": 13701 + }, + { + "epoch": 4.23, + "learning_rate": 1.8320023556174356e-05, + "loss": 0.2686, + "step": 13702 + }, + { + "epoch": 4.23, + "learning_rate": 1.831974609413284e-05, + "loss": 0.2672, + "step": 13703 + }, + { + "epoch": 4.23, + "learning_rate": 1.831946861128212e-05, + "loss": 0.2683, + "step": 13704 + }, + { + "epoch": 4.23, + "learning_rate": 1.8319191107622893e-05, + "loss": 0.2721, + "step": 13705 + }, + { + "epoch": 4.23, + "learning_rate": 1.8318913583155852e-05, + "loss": 0.2664, + "step": 13706 + }, + { + "epoch": 4.23, + "learning_rate": 1.831863603788169e-05, + "loss": 0.2813, + "step": 13707 + }, + { + "epoch": 4.23, + "learning_rate": 1.8318358471801105e-05, + "loss": 0.2591, + "step": 13708 + }, + { + "epoch": 4.23, + "learning_rate": 1.8318080884914783e-05, + "loss": 0.2642, + "step": 13709 + }, + { + "epoch": 4.23, + "learning_rate": 1.831780327722343e-05, + "loss": 0.284, + "step": 13710 + }, + { + "epoch": 4.23, + "learning_rate": 1.831752564872773e-05, + "loss": 0.2716, + "step": 13711 + }, + { + "epoch": 4.23, + "learning_rate": 1.831724799942838e-05, + "loss": 0.2521, + "step": 13712 + }, + { + "epoch": 4.23, + "learning_rate": 1.8316970329326077e-05, + "loss": 0.2863, + "step": 13713 + }, + { + "epoch": 4.24, + "learning_rate": 1.8316692638421518e-05, + "loss": 0.2718, + "step": 13714 + }, + { + "epoch": 4.24, + "learning_rate": 1.8316414926715388e-05, + "loss": 0.2549, + "step": 13715 + }, + { + "epoch": 4.24, + "learning_rate": 1.831613719420839e-05, + "loss": 0.2822, + "step": 13716 + }, + { + "epoch": 4.24, + "learning_rate": 1.8315859440901218e-05, + "loss": 0.2633, + "step": 13717 + }, + { + "epoch": 4.24, + "learning_rate": 1.831558166679456e-05, + "loss": 0.2732, + "step": 13718 + }, + { + "epoch": 4.24, + "learning_rate": 1.831530387188912e-05, + "loss": 0.2811, + "step": 13719 + }, + { + "epoch": 4.24, + "learning_rate": 1.8315026056185584e-05, + "loss": 0.2698, + "step": 13720 + }, + { + "epoch": 4.24, + "learning_rate": 1.8314748219684657e-05, + "loss": 0.2682, + "step": 13721 + }, + { + "epoch": 4.24, + "learning_rate": 1.8314470362387028e-05, + "loss": 0.2657, + "step": 13722 + }, + { + "epoch": 4.24, + "learning_rate": 1.8314192484293388e-05, + "loss": 0.2776, + "step": 13723 + }, + { + "epoch": 4.24, + "learning_rate": 1.8313914585404435e-05, + "loss": 0.2664, + "step": 13724 + }, + { + "epoch": 4.24, + "learning_rate": 1.831363666572087e-05, + "loss": 0.284, + "step": 13725 + }, + { + "epoch": 4.24, + "learning_rate": 1.831335872524338e-05, + "loss": 0.2749, + "step": 13726 + }, + { + "epoch": 4.24, + "learning_rate": 1.8313080763972667e-05, + "loss": 0.2945, + "step": 13727 + }, + { + "epoch": 4.24, + "learning_rate": 1.831280278190942e-05, + "loss": 0.2627, + "step": 13728 + }, + { + "epoch": 4.24, + "learning_rate": 1.831252477905434e-05, + "loss": 0.2442, + "step": 13729 + }, + { + "epoch": 4.24, + "learning_rate": 1.8312246755408116e-05, + "loss": 0.2678, + "step": 13730 + }, + { + "epoch": 4.24, + "learning_rate": 1.8311968710971446e-05, + "loss": 0.2758, + "step": 13731 + }, + { + "epoch": 4.24, + "learning_rate": 1.831169064574503e-05, + "loss": 0.2759, + "step": 13732 + }, + { + "epoch": 4.24, + "learning_rate": 1.8311412559729558e-05, + "loss": 0.2896, + "step": 13733 + }, + { + "epoch": 4.24, + "learning_rate": 1.8311134452925726e-05, + "loss": 0.2738, + "step": 13734 + }, + { + "epoch": 4.24, + "learning_rate": 1.8310856325334233e-05, + "loss": 0.2633, + "step": 13735 + }, + { + "epoch": 4.24, + "learning_rate": 1.831057817695577e-05, + "loss": 0.2668, + "step": 13736 + }, + { + "epoch": 4.24, + "learning_rate": 1.8310300007791036e-05, + "loss": 0.2579, + "step": 13737 + }, + { + "epoch": 4.24, + "learning_rate": 1.831002181784073e-05, + "loss": 0.2759, + "step": 13738 + }, + { + "epoch": 4.24, + "learning_rate": 1.8309743607105538e-05, + "loss": 0.2695, + "step": 13739 + }, + { + "epoch": 4.24, + "learning_rate": 1.8309465375586168e-05, + "loss": 0.2952, + "step": 13740 + }, + { + "epoch": 4.24, + "learning_rate": 1.8309187123283306e-05, + "loss": 0.2755, + "step": 13741 + }, + { + "epoch": 4.24, + "learning_rate": 1.8308908850197647e-05, + "loss": 0.2538, + "step": 13742 + }, + { + "epoch": 4.24, + "learning_rate": 1.83086305563299e-05, + "loss": 0.2481, + "step": 13743 + }, + { + "epoch": 4.24, + "learning_rate": 1.8308352241680747e-05, + "loss": 0.2808, + "step": 13744 + }, + { + "epoch": 4.24, + "learning_rate": 1.8308073906250892e-05, + "loss": 0.277, + "step": 13745 + }, + { + "epoch": 4.25, + "learning_rate": 1.8307795550041028e-05, + "loss": 0.259, + "step": 13746 + }, + { + "epoch": 4.25, + "learning_rate": 1.830751717305185e-05, + "loss": 0.2833, + "step": 13747 + }, + { + "epoch": 4.25, + "learning_rate": 1.830723877528406e-05, + "loss": 0.2708, + "step": 13748 + }, + { + "epoch": 4.25, + "learning_rate": 1.830696035673835e-05, + "loss": 0.2727, + "step": 13749 + }, + { + "epoch": 4.25, + "learning_rate": 1.8306681917415415e-05, + "loss": 0.2727, + "step": 13750 + }, + { + "epoch": 4.25, + "learning_rate": 1.8306403457315954e-05, + "loss": 0.2692, + "step": 13751 + }, + { + "epoch": 4.25, + "learning_rate": 1.8306124976440665e-05, + "loss": 0.2333, + "step": 13752 + }, + { + "epoch": 4.25, + "learning_rate": 1.830584647479024e-05, + "loss": 0.2566, + "step": 13753 + }, + { + "epoch": 4.25, + "learning_rate": 1.8305567952365383e-05, + "loss": 0.2876, + "step": 13754 + }, + { + "epoch": 4.25, + "learning_rate": 1.830528940916678e-05, + "loss": 0.2655, + "step": 13755 + }, + { + "epoch": 4.25, + "learning_rate": 1.8305010845195136e-05, + "loss": 0.2578, + "step": 13756 + }, + { + "epoch": 4.25, + "learning_rate": 1.8304732260451144e-05, + "loss": 0.2767, + "step": 13757 + }, + { + "epoch": 4.25, + "learning_rate": 1.8304453654935503e-05, + "loss": 0.2848, + "step": 13758 + }, + { + "epoch": 4.25, + "learning_rate": 1.8304175028648906e-05, + "loss": 0.2536, + "step": 13759 + }, + { + "epoch": 4.25, + "learning_rate": 1.8303896381592055e-05, + "loss": 0.3042, + "step": 13760 + }, + { + "epoch": 4.25, + "learning_rate": 1.8303617713765644e-05, + "loss": 0.2698, + "step": 13761 + }, + { + "epoch": 4.25, + "learning_rate": 1.830333902517037e-05, + "loss": 0.2908, + "step": 13762 + }, + { + "epoch": 4.25, + "learning_rate": 1.8303060315806936e-05, + "loss": 0.2704, + "step": 13763 + }, + { + "epoch": 4.25, + "learning_rate": 1.8302781585676027e-05, + "loss": 0.257, + "step": 13764 + }, + { + "epoch": 4.25, + "learning_rate": 1.830250283477835e-05, + "loss": 0.2676, + "step": 13765 + }, + { + "epoch": 4.25, + "learning_rate": 1.8302224063114598e-05, + "loss": 0.2866, + "step": 13766 + }, + { + "epoch": 4.25, + "learning_rate": 1.830194527068547e-05, + "loss": 0.2722, + "step": 13767 + }, + { + "epoch": 4.25, + "learning_rate": 1.8301666457491665e-05, + "loss": 0.3245, + "step": 13768 + }, + { + "epoch": 4.25, + "learning_rate": 1.8301387623533873e-05, + "loss": 0.2811, + "step": 13769 + }, + { + "epoch": 4.25, + "learning_rate": 1.83011087688128e-05, + "loss": 0.2681, + "step": 13770 + }, + { + "epoch": 4.25, + "learning_rate": 1.830082989332914e-05, + "loss": 0.2649, + "step": 13771 + }, + { + "epoch": 4.25, + "learning_rate": 1.830055099708359e-05, + "loss": 0.2716, + "step": 13772 + }, + { + "epoch": 4.25, + "learning_rate": 1.8300272080076847e-05, + "loss": 0.2445, + "step": 13773 + }, + { + "epoch": 4.25, + "learning_rate": 1.8299993142309608e-05, + "loss": 0.2684, + "step": 13774 + }, + { + "epoch": 4.25, + "learning_rate": 1.8299714183782577e-05, + "loss": 0.2653, + "step": 13775 + }, + { + "epoch": 4.25, + "learning_rate": 1.8299435204496446e-05, + "loss": 0.2912, + "step": 13776 + }, + { + "epoch": 4.25, + "learning_rate": 1.8299156204451912e-05, + "loss": 0.2495, + "step": 13777 + }, + { + "epoch": 4.26, + "learning_rate": 1.8298877183649674e-05, + "loss": 0.2617, + "step": 13778 + }, + { + "epoch": 4.26, + "learning_rate": 1.829859814209043e-05, + "loss": 0.2656, + "step": 13779 + }, + { + "epoch": 4.26, + "learning_rate": 1.829831907977488e-05, + "loss": 0.251, + "step": 13780 + }, + { + "epoch": 4.26, + "learning_rate": 1.8298039996703723e-05, + "loss": 0.2715, + "step": 13781 + }, + { + "epoch": 4.26, + "learning_rate": 1.829776089287765e-05, + "loss": 0.2538, + "step": 13782 + }, + { + "epoch": 4.26, + "learning_rate": 1.8297481768297366e-05, + "loss": 0.2864, + "step": 13783 + }, + { + "epoch": 4.26, + "learning_rate": 1.8297202622963568e-05, + "loss": 0.2828, + "step": 13784 + }, + { + "epoch": 4.26, + "learning_rate": 1.829692345687695e-05, + "loss": 0.2535, + "step": 13785 + }, + { + "epoch": 4.26, + "learning_rate": 1.8296644270038214e-05, + "loss": 0.273, + "step": 13786 + }, + { + "epoch": 4.26, + "learning_rate": 1.829636506244806e-05, + "loss": 0.2862, + "step": 13787 + }, + { + "epoch": 4.26, + "learning_rate": 1.829608583410718e-05, + "loss": 0.2817, + "step": 13788 + }, + { + "epoch": 4.26, + "learning_rate": 1.829580658501628e-05, + "loss": 0.2736, + "step": 13789 + }, + { + "epoch": 4.26, + "learning_rate": 1.8295527315176052e-05, + "loss": 0.2674, + "step": 13790 + }, + { + "epoch": 4.26, + "learning_rate": 1.8295248024587197e-05, + "loss": 0.2593, + "step": 13791 + }, + { + "epoch": 4.26, + "learning_rate": 1.8294968713250415e-05, + "loss": 0.2526, + "step": 13792 + }, + { + "epoch": 4.26, + "learning_rate": 1.8294689381166405e-05, + "loss": 0.2747, + "step": 13793 + }, + { + "epoch": 4.26, + "learning_rate": 1.829441002833586e-05, + "loss": 0.2886, + "step": 13794 + }, + { + "epoch": 4.26, + "learning_rate": 1.8294130654759484e-05, + "loss": 0.289, + "step": 13795 + }, + { + "epoch": 4.26, + "learning_rate": 1.8293851260437976e-05, + "loss": 0.2771, + "step": 13796 + }, + { + "epoch": 4.26, + "learning_rate": 1.8293571845372032e-05, + "loss": 0.2691, + "step": 13797 + }, + { + "epoch": 4.26, + "learning_rate": 1.8293292409562353e-05, + "loss": 0.2499, + "step": 13798 + }, + { + "epoch": 4.26, + "learning_rate": 1.8293012953009636e-05, + "loss": 0.2708, + "step": 13799 + }, + { + "epoch": 4.26, + "learning_rate": 1.8292733475714583e-05, + "loss": 0.2648, + "step": 13800 + }, + { + "epoch": 4.26, + "learning_rate": 1.829245397767789e-05, + "loss": 0.2769, + "step": 13801 + }, + { + "epoch": 4.26, + "learning_rate": 1.8292174458900255e-05, + "loss": 0.2632, + "step": 13802 + }, + { + "epoch": 4.26, + "learning_rate": 1.8291894919382382e-05, + "loss": 0.2589, + "step": 13803 + }, + { + "epoch": 4.26, + "learning_rate": 1.829161535912497e-05, + "loss": 0.2661, + "step": 13804 + }, + { + "epoch": 4.26, + "learning_rate": 1.829133577812871e-05, + "loss": 0.2705, + "step": 13805 + }, + { + "epoch": 4.26, + "learning_rate": 1.8291056176394308e-05, + "loss": 0.2636, + "step": 13806 + }, + { + "epoch": 4.26, + "learning_rate": 1.8290776553922463e-05, + "loss": 0.2901, + "step": 13807 + }, + { + "epoch": 4.26, + "learning_rate": 1.8290496910713876e-05, + "loss": 0.2935, + "step": 13808 + }, + { + "epoch": 4.26, + "learning_rate": 1.8290217246769242e-05, + "loss": 0.2962, + "step": 13809 + }, + { + "epoch": 4.26, + "learning_rate": 1.8289937562089265e-05, + "loss": 0.2573, + "step": 13810 + }, + { + "epoch": 4.27, + "learning_rate": 1.828965785667464e-05, + "loss": 0.2742, + "step": 13811 + }, + { + "epoch": 4.27, + "learning_rate": 1.8289378130526067e-05, + "loss": 0.282, + "step": 13812 + }, + { + "epoch": 4.27, + "learning_rate": 1.828909838364425e-05, + "loss": 0.2571, + "step": 13813 + }, + { + "epoch": 4.27, + "learning_rate": 1.8288818616029887e-05, + "loss": 0.2763, + "step": 13814 + }, + { + "epoch": 4.27, + "learning_rate": 1.8288538827683676e-05, + "loss": 0.2733, + "step": 13815 + }, + { + "epoch": 4.27, + "learning_rate": 1.8288259018606312e-05, + "loss": 0.2642, + "step": 13816 + }, + { + "epoch": 4.27, + "learning_rate": 1.828797918879851e-05, + "loss": 0.2788, + "step": 13817 + }, + { + "epoch": 4.27, + "learning_rate": 1.8287699338260956e-05, + "loss": 0.286, + "step": 13818 + }, + { + "epoch": 4.27, + "learning_rate": 1.8287419466994355e-05, + "loss": 0.268, + "step": 13819 + }, + { + "epoch": 4.27, + "learning_rate": 1.8287139574999405e-05, + "loss": 0.275, + "step": 13820 + }, + { + "epoch": 4.27, + "learning_rate": 1.8286859662276807e-05, + "loss": 0.2734, + "step": 13821 + }, + { + "epoch": 4.27, + "learning_rate": 1.828657972882726e-05, + "loss": 0.2761, + "step": 13822 + }, + { + "epoch": 4.27, + "learning_rate": 1.828629977465147e-05, + "loss": 0.2752, + "step": 13823 + }, + { + "epoch": 4.27, + "learning_rate": 1.828601979975013e-05, + "loss": 0.2654, + "step": 13824 + }, + { + "epoch": 4.27, + "learning_rate": 1.8285739804123946e-05, + "loss": 0.2692, + "step": 13825 + }, + { + "epoch": 4.27, + "learning_rate": 1.8285459787773615e-05, + "loss": 0.2814, + "step": 13826 + }, + { + "epoch": 4.27, + "learning_rate": 1.8285179750699838e-05, + "loss": 0.2625, + "step": 13827 + }, + { + "epoch": 4.27, + "learning_rate": 1.8284899692903314e-05, + "loss": 0.2798, + "step": 13828 + }, + { + "epoch": 4.27, + "learning_rate": 1.8284619614384743e-05, + "loss": 0.2696, + "step": 13829 + }, + { + "epoch": 4.27, + "learning_rate": 1.8284339515144832e-05, + "loss": 0.2607, + "step": 13830 + }, + { + "epoch": 4.27, + "learning_rate": 1.8284059395184273e-05, + "loss": 0.2771, + "step": 13831 + }, + { + "epoch": 4.27, + "learning_rate": 1.828377925450377e-05, + "loss": 0.2861, + "step": 13832 + }, + { + "epoch": 4.27, + "learning_rate": 1.8283499093104028e-05, + "loss": 0.2756, + "step": 13833 + }, + { + "epoch": 4.27, + "learning_rate": 1.828321891098574e-05, + "loss": 0.2712, + "step": 13834 + }, + { + "epoch": 4.27, + "learning_rate": 1.8282938708149615e-05, + "loss": 0.2625, + "step": 13835 + }, + { + "epoch": 4.27, + "learning_rate": 1.8282658484596347e-05, + "loss": 0.2724, + "step": 13836 + }, + { + "epoch": 4.27, + "learning_rate": 1.828237824032664e-05, + "loss": 0.2522, + "step": 13837 + }, + { + "epoch": 4.27, + "learning_rate": 1.8282097975341194e-05, + "loss": 0.2658, + "step": 13838 + }, + { + "epoch": 4.27, + "learning_rate": 1.8281817689640712e-05, + "loss": 0.2633, + "step": 13839 + }, + { + "epoch": 4.27, + "learning_rate": 1.828153738322589e-05, + "loss": 0.2677, + "step": 13840 + }, + { + "epoch": 4.27, + "learning_rate": 1.8281257056097437e-05, + "loss": 0.2709, + "step": 13841 + }, + { + "epoch": 4.27, + "learning_rate": 1.8280976708256046e-05, + "loss": 0.2538, + "step": 13842 + }, + { + "epoch": 4.28, + "learning_rate": 1.8280696339702423e-05, + "loss": 0.2514, + "step": 13843 + }, + { + "epoch": 4.28, + "learning_rate": 1.828041595043727e-05, + "loss": 0.2772, + "step": 13844 + }, + { + "epoch": 4.28, + "learning_rate": 1.8280135540461285e-05, + "loss": 0.2606, + "step": 13845 + }, + { + "epoch": 4.28, + "learning_rate": 1.827985510977517e-05, + "loss": 0.2663, + "step": 13846 + }, + { + "epoch": 4.28, + "learning_rate": 1.8279574658379627e-05, + "loss": 0.2641, + "step": 13847 + }, + { + "epoch": 4.28, + "learning_rate": 1.827929418627536e-05, + "loss": 0.2878, + "step": 13848 + }, + { + "epoch": 4.28, + "learning_rate": 1.8279013693463066e-05, + "loss": 0.2729, + "step": 13849 + }, + { + "epoch": 4.28, + "learning_rate": 1.827873317994345e-05, + "loss": 0.2552, + "step": 13850 + }, + { + "epoch": 4.28, + "learning_rate": 1.827845264571721e-05, + "loss": 0.2731, + "step": 13851 + }, + { + "epoch": 4.28, + "learning_rate": 1.8278172090785053e-05, + "loss": 0.2684, + "step": 13852 + }, + { + "epoch": 4.28, + "learning_rate": 1.8277891515147677e-05, + "loss": 0.2687, + "step": 13853 + }, + { + "epoch": 4.28, + "learning_rate": 1.8277610918805786e-05, + "loss": 0.2557, + "step": 13854 + }, + { + "epoch": 4.28, + "learning_rate": 1.8277330301760076e-05, + "loss": 0.276, + "step": 13855 + }, + { + "epoch": 4.28, + "learning_rate": 1.8277049664011257e-05, + "loss": 0.2785, + "step": 13856 + }, + { + "epoch": 4.28, + "learning_rate": 1.8276769005560025e-05, + "loss": 0.2758, + "step": 13857 + }, + { + "epoch": 4.28, + "learning_rate": 1.8276488326407085e-05, + "loss": 0.262, + "step": 13858 + }, + { + "epoch": 4.28, + "learning_rate": 1.8276207626553136e-05, + "loss": 0.3328, + "step": 13859 + }, + { + "epoch": 4.28, + "learning_rate": 1.8275926905998885e-05, + "loss": 0.2685, + "step": 13860 + }, + { + "epoch": 4.28, + "learning_rate": 1.8275646164745033e-05, + "loss": 0.2767, + "step": 13861 + }, + { + "epoch": 4.28, + "learning_rate": 1.827536540279228e-05, + "loss": 0.2576, + "step": 13862 + }, + { + "epoch": 4.28, + "learning_rate": 1.8275084620141325e-05, + "loss": 0.2427, + "step": 13863 + }, + { + "epoch": 4.28, + "learning_rate": 1.8274803816792876e-05, + "loss": 0.2716, + "step": 13864 + }, + { + "epoch": 4.28, + "learning_rate": 1.8274522992747635e-05, + "loss": 0.2546, + "step": 13865 + }, + { + "epoch": 4.28, + "learning_rate": 1.82742421480063e-05, + "loss": 0.2792, + "step": 13866 + }, + { + "epoch": 4.28, + "learning_rate": 1.827396128256958e-05, + "loss": 0.2638, + "step": 13867 + }, + { + "epoch": 4.28, + "learning_rate": 1.827368039643817e-05, + "loss": 0.2849, + "step": 13868 + }, + { + "epoch": 4.28, + "learning_rate": 1.8273399489612776e-05, + "loss": 0.2864, + "step": 13869 + }, + { + "epoch": 4.28, + "learning_rate": 1.8273118562094105e-05, + "loss": 0.2842, + "step": 13870 + }, + { + "epoch": 4.28, + "learning_rate": 1.8272837613882853e-05, + "loss": 0.2605, + "step": 13871 + }, + { + "epoch": 4.28, + "learning_rate": 1.8272556644979727e-05, + "loss": 0.25, + "step": 13872 + }, + { + "epoch": 4.28, + "learning_rate": 1.8272275655385427e-05, + "loss": 0.2534, + "step": 13873 + }, + { + "epoch": 4.28, + "learning_rate": 1.8271994645100656e-05, + "loss": 0.2726, + "step": 13874 + }, + { + "epoch": 4.28, + "learning_rate": 1.8271713614126116e-05, + "loss": 0.2995, + "step": 13875 + }, + { + "epoch": 4.29, + "learning_rate": 1.8271432562462515e-05, + "loss": 0.2764, + "step": 13876 + }, + { + "epoch": 4.29, + "learning_rate": 1.827115149011055e-05, + "loss": 0.2813, + "step": 13877 + }, + { + "epoch": 4.29, + "learning_rate": 1.827087039707093e-05, + "loss": 0.2783, + "step": 13878 + }, + { + "epoch": 4.29, + "learning_rate": 1.827058928334435e-05, + "loss": 0.2774, + "step": 13879 + }, + { + "epoch": 4.29, + "learning_rate": 1.827030814893152e-05, + "loss": 0.2506, + "step": 13880 + }, + { + "epoch": 4.29, + "learning_rate": 1.8270026993833143e-05, + "loss": 0.2939, + "step": 13881 + }, + { + "epoch": 4.29, + "learning_rate": 1.8269745818049918e-05, + "loss": 0.2673, + "step": 13882 + }, + { + "epoch": 4.29, + "learning_rate": 1.8269464621582548e-05, + "loss": 0.2735, + "step": 13883 + }, + { + "epoch": 4.29, + "learning_rate": 1.8269183404431742e-05, + "loss": 0.2449, + "step": 13884 + }, + { + "epoch": 4.29, + "learning_rate": 1.82689021665982e-05, + "loss": 0.2702, + "step": 13885 + }, + { + "epoch": 4.29, + "learning_rate": 1.8268620908082625e-05, + "loss": 0.2534, + "step": 13886 + }, + { + "epoch": 4.29, + "learning_rate": 1.826833962888572e-05, + "loss": 0.2707, + "step": 13887 + }, + { + "epoch": 4.29, + "learning_rate": 1.826805832900819e-05, + "loss": 0.2778, + "step": 13888 + }, + { + "epoch": 4.29, + "learning_rate": 1.826777700845074e-05, + "loss": 0.2458, + "step": 13889 + }, + { + "epoch": 4.29, + "learning_rate": 1.826749566721407e-05, + "loss": 0.2922, + "step": 13890 + }, + { + "epoch": 4.29, + "learning_rate": 1.8267214305298886e-05, + "loss": 0.2663, + "step": 13891 + }, + { + "epoch": 4.29, + "learning_rate": 1.8266932922705892e-05, + "loss": 0.2846, + "step": 13892 + }, + { + "epoch": 4.29, + "learning_rate": 1.826665151943579e-05, + "loss": 0.2678, + "step": 13893 + }, + { + "epoch": 4.29, + "learning_rate": 1.8266370095489283e-05, + "loss": 0.2657, + "step": 13894 + }, + { + "epoch": 4.29, + "learning_rate": 1.826608865086708e-05, + "loss": 0.2581, + "step": 13895 + }, + { + "epoch": 4.29, + "learning_rate": 1.826580718556988e-05, + "loss": 0.2804, + "step": 13896 + }, + { + "epoch": 4.29, + "learning_rate": 1.8265525699598387e-05, + "loss": 0.2894, + "step": 13897 + }, + { + "epoch": 4.29, + "learning_rate": 1.8265244192953312e-05, + "loss": 0.2753, + "step": 13898 + }, + { + "epoch": 4.29, + "learning_rate": 1.8264962665635348e-05, + "loss": 0.2639, + "step": 13899 + }, + { + "epoch": 4.29, + "learning_rate": 1.8264681117645205e-05, + "loss": 0.2544, + "step": 13900 + }, + { + "epoch": 4.29, + "learning_rate": 1.826439954898359e-05, + "loss": 0.2548, + "step": 13901 + }, + { + "epoch": 4.29, + "learning_rate": 1.8264117959651205e-05, + "loss": 0.253, + "step": 13902 + }, + { + "epoch": 4.29, + "learning_rate": 1.826383634964875e-05, + "loss": 0.2793, + "step": 13903 + }, + { + "epoch": 4.29, + "learning_rate": 1.8263554718976938e-05, + "loss": 0.2746, + "step": 13904 + }, + { + "epoch": 4.29, + "learning_rate": 1.8263273067636463e-05, + "loss": 0.2602, + "step": 13905 + }, + { + "epoch": 4.29, + "learning_rate": 1.826299139562804e-05, + "loss": 0.2712, + "step": 13906 + }, + { + "epoch": 4.29, + "learning_rate": 1.8262709702952367e-05, + "loss": 0.2747, + "step": 13907 + }, + { + "epoch": 4.3, + "learning_rate": 1.826242798961015e-05, + "loss": 0.2711, + "step": 13908 + }, + { + "epoch": 4.3, + "learning_rate": 1.826214625560209e-05, + "loss": 0.2812, + "step": 13909 + }, + { + "epoch": 4.3, + "learning_rate": 1.82618645009289e-05, + "loss": 0.2706, + "step": 13910 + }, + { + "epoch": 4.3, + "learning_rate": 1.8261582725591278e-05, + "loss": 0.279, + "step": 13911 + }, + { + "epoch": 4.3, + "learning_rate": 1.8261300929589932e-05, + "loss": 0.2777, + "step": 13912 + }, + { + "epoch": 4.3, + "learning_rate": 1.826101911292556e-05, + "loss": 0.2529, + "step": 13913 + }, + { + "epoch": 4.3, + "learning_rate": 1.826073727559888e-05, + "loss": 0.2821, + "step": 13914 + }, + { + "epoch": 4.3, + "learning_rate": 1.8260455417610587e-05, + "loss": 0.2596, + "step": 13915 + }, + { + "epoch": 4.3, + "learning_rate": 1.8260173538961387e-05, + "loss": 0.2622, + "step": 13916 + }, + { + "epoch": 4.3, + "learning_rate": 1.8259891639651987e-05, + "loss": 0.2955, + "step": 13917 + }, + { + "epoch": 4.3, + "learning_rate": 1.8259609719683094e-05, + "loss": 0.2779, + "step": 13918 + }, + { + "epoch": 4.3, + "learning_rate": 1.8259327779055406e-05, + "loss": 0.2783, + "step": 13919 + }, + { + "epoch": 4.3, + "learning_rate": 1.8259045817769635e-05, + "loss": 0.2712, + "step": 13920 + }, + { + "epoch": 4.3, + "learning_rate": 1.8258763835826485e-05, + "loss": 0.2499, + "step": 13921 + }, + { + "epoch": 4.3, + "learning_rate": 1.825848183322666e-05, + "loss": 0.2738, + "step": 13922 + }, + { + "epoch": 4.3, + "learning_rate": 1.8258199809970866e-05, + "loss": 0.271, + "step": 13923 + }, + { + "epoch": 4.3, + "learning_rate": 1.8257917766059806e-05, + "loss": 0.2844, + "step": 13924 + }, + { + "epoch": 4.3, + "learning_rate": 1.825763570149419e-05, + "loss": 0.2895, + "step": 13925 + }, + { + "epoch": 4.3, + "learning_rate": 1.825735361627472e-05, + "loss": 0.2583, + "step": 13926 + }, + { + "epoch": 4.3, + "learning_rate": 1.8257071510402104e-05, + "loss": 0.2699, + "step": 13927 + }, + { + "epoch": 4.3, + "learning_rate": 1.8256789383877044e-05, + "loss": 0.2732, + "step": 13928 + }, + { + "epoch": 4.3, + "learning_rate": 1.8256507236700246e-05, + "loss": 0.2555, + "step": 13929 + }, + { + "epoch": 4.3, + "learning_rate": 1.8256225068872423e-05, + "loss": 0.2721, + "step": 13930 + }, + { + "epoch": 4.3, + "learning_rate": 1.825594288039427e-05, + "loss": 0.2668, + "step": 13931 + }, + { + "epoch": 4.3, + "learning_rate": 1.8255660671266498e-05, + "loss": 0.2494, + "step": 13932 + }, + { + "epoch": 4.3, + "learning_rate": 1.8255378441489816e-05, + "loss": 0.2868, + "step": 13933 + }, + { + "epoch": 4.3, + "learning_rate": 1.8255096191064927e-05, + "loss": 0.2369, + "step": 13934 + }, + { + "epoch": 4.3, + "learning_rate": 1.8254813919992536e-05, + "loss": 0.2442, + "step": 13935 + }, + { + "epoch": 4.3, + "learning_rate": 1.8254531628273347e-05, + "loss": 0.2621, + "step": 13936 + }, + { + "epoch": 4.3, + "learning_rate": 1.8254249315908073e-05, + "loss": 0.2669, + "step": 13937 + }, + { + "epoch": 4.3, + "learning_rate": 1.8253966982897417e-05, + "loss": 0.2674, + "step": 13938 + }, + { + "epoch": 4.3, + "learning_rate": 1.825368462924208e-05, + "loss": 0.2735, + "step": 13939 + }, + { + "epoch": 4.31, + "learning_rate": 1.8253402254942774e-05, + "loss": 0.2783, + "step": 13940 + }, + { + "epoch": 4.31, + "learning_rate": 1.8253119860000204e-05, + "loss": 0.2737, + "step": 13941 + }, + { + "epoch": 4.31, + "learning_rate": 1.8252837444415074e-05, + "loss": 0.2619, + "step": 13942 + }, + { + "epoch": 4.31, + "learning_rate": 1.8252555008188097e-05, + "loss": 0.2622, + "step": 13943 + }, + { + "epoch": 4.31, + "learning_rate": 1.825227255131997e-05, + "loss": 0.2721, + "step": 13944 + }, + { + "epoch": 4.31, + "learning_rate": 1.8251990073811407e-05, + "loss": 0.2451, + "step": 13945 + }, + { + "epoch": 4.31, + "learning_rate": 1.825170757566311e-05, + "loss": 0.2672, + "step": 13946 + }, + { + "epoch": 4.31, + "learning_rate": 1.8251425056875787e-05, + "loss": 0.2624, + "step": 13947 + }, + { + "epoch": 4.31, + "learning_rate": 1.8251142517450144e-05, + "loss": 0.2915, + "step": 13948 + }, + { + "epoch": 4.31, + "learning_rate": 1.8250859957386893e-05, + "loss": 0.2605, + "step": 13949 + }, + { + "epoch": 4.31, + "learning_rate": 1.8250577376686734e-05, + "loss": 0.2551, + "step": 13950 + }, + { + "epoch": 4.31, + "learning_rate": 1.8250294775350376e-05, + "loss": 0.2689, + "step": 13951 + }, + { + "epoch": 4.31, + "learning_rate": 1.8250012153378523e-05, + "loss": 0.2842, + "step": 13952 + }, + { + "epoch": 4.31, + "learning_rate": 1.824972951077189e-05, + "loss": 0.2721, + "step": 13953 + }, + { + "epoch": 4.31, + "learning_rate": 1.824944684753118e-05, + "loss": 0.2657, + "step": 13954 + }, + { + "epoch": 4.31, + "learning_rate": 1.8249164163657092e-05, + "loss": 0.2528, + "step": 13955 + }, + { + "epoch": 4.31, + "learning_rate": 1.8248881459150345e-05, + "loss": 0.2683, + "step": 13956 + }, + { + "epoch": 4.31, + "learning_rate": 1.824859873401164e-05, + "loss": 0.2831, + "step": 13957 + }, + { + "epoch": 4.31, + "learning_rate": 1.824831598824168e-05, + "loss": 0.2757, + "step": 13958 + }, + { + "epoch": 4.31, + "learning_rate": 1.8248033221841187e-05, + "loss": 0.2709, + "step": 13959 + }, + { + "epoch": 4.31, + "learning_rate": 1.8247750434810853e-05, + "loss": 0.2771, + "step": 13960 + }, + { + "epoch": 4.31, + "learning_rate": 1.824746762715139e-05, + "loss": 0.2735, + "step": 13961 + }, + { + "epoch": 4.31, + "learning_rate": 1.8247184798863508e-05, + "loss": 0.2976, + "step": 13962 + }, + { + "epoch": 4.31, + "learning_rate": 1.8246901949947914e-05, + "loss": 0.2832, + "step": 13963 + }, + { + "epoch": 4.31, + "learning_rate": 1.8246619080405312e-05, + "loss": 0.2827, + "step": 13964 + }, + { + "epoch": 4.31, + "learning_rate": 1.824633619023641e-05, + "loss": 0.2855, + "step": 13965 + }, + { + "epoch": 4.31, + "learning_rate": 1.824605327944192e-05, + "loss": 0.2467, + "step": 13966 + }, + { + "epoch": 4.31, + "learning_rate": 1.8245770348022547e-05, + "loss": 0.2745, + "step": 13967 + }, + { + "epoch": 4.31, + "learning_rate": 1.8245487395978997e-05, + "loss": 0.2761, + "step": 13968 + }, + { + "epoch": 4.31, + "learning_rate": 1.8245204423311977e-05, + "loss": 0.2678, + "step": 13969 + }, + { + "epoch": 4.31, + "learning_rate": 1.82449214300222e-05, + "loss": 0.2774, + "step": 13970 + }, + { + "epoch": 4.31, + "learning_rate": 1.8244638416110372e-05, + "loss": 0.2572, + "step": 13971 + }, + { + "epoch": 4.31, + "learning_rate": 1.8244355381577197e-05, + "loss": 0.2588, + "step": 13972 + }, + { + "epoch": 4.32, + "learning_rate": 1.8244072326423384e-05, + "loss": 0.2718, + "step": 13973 + }, + { + "epoch": 4.32, + "learning_rate": 1.8243789250649646e-05, + "loss": 0.2596, + "step": 13974 + }, + { + "epoch": 4.32, + "learning_rate": 1.8243506154256686e-05, + "loss": 0.2743, + "step": 13975 + }, + { + "epoch": 4.32, + "learning_rate": 1.8243223037245212e-05, + "loss": 0.2591, + "step": 13976 + }, + { + "epoch": 4.32, + "learning_rate": 1.8242939899615937e-05, + "loss": 0.2867, + "step": 13977 + }, + { + "epoch": 4.32, + "learning_rate": 1.8242656741369565e-05, + "loss": 0.2627, + "step": 13978 + }, + { + "epoch": 4.32, + "learning_rate": 1.8242373562506804e-05, + "loss": 0.2751, + "step": 13979 + }, + { + "epoch": 4.32, + "learning_rate": 1.8242090363028366e-05, + "loss": 0.2676, + "step": 13980 + }, + { + "epoch": 4.32, + "learning_rate": 1.8241807142934954e-05, + "loss": 0.2982, + "step": 13981 + }, + { + "epoch": 4.32, + "learning_rate": 1.824152390222728e-05, + "loss": 0.2597, + "step": 13982 + }, + { + "epoch": 4.32, + "learning_rate": 1.824124064090605e-05, + "loss": 0.2843, + "step": 13983 + }, + { + "epoch": 4.32, + "learning_rate": 1.8240957358971973e-05, + "loss": 0.28, + "step": 13984 + }, + { + "epoch": 4.32, + "learning_rate": 1.8240674056425762e-05, + "loss": 0.2616, + "step": 13985 + }, + { + "epoch": 4.32, + "learning_rate": 1.8240390733268123e-05, + "loss": 0.2506, + "step": 13986 + }, + { + "epoch": 4.32, + "learning_rate": 1.824010738949976e-05, + "loss": 0.247, + "step": 13987 + }, + { + "epoch": 4.32, + "learning_rate": 1.8239824025121388e-05, + "loss": 0.26, + "step": 13988 + }, + { + "epoch": 4.32, + "learning_rate": 1.823954064013371e-05, + "loss": 0.2818, + "step": 13989 + }, + { + "epoch": 4.32, + "learning_rate": 1.8239257234537442e-05, + "loss": 0.258, + "step": 13990 + }, + { + "epoch": 4.32, + "learning_rate": 1.8238973808333288e-05, + "loss": 0.2791, + "step": 13991 + }, + { + "epoch": 4.32, + "learning_rate": 1.8238690361521957e-05, + "loss": 0.2675, + "step": 13992 + }, + { + "epoch": 4.32, + "learning_rate": 1.8238406894104162e-05, + "loss": 0.2628, + "step": 13993 + }, + { + "epoch": 4.32, + "learning_rate": 1.8238123406080602e-05, + "loss": 0.2782, + "step": 13994 + }, + { + "epoch": 4.32, + "learning_rate": 1.8237839897451997e-05, + "loss": 0.2545, + "step": 13995 + }, + { + "epoch": 4.32, + "learning_rate": 1.8237556368219055e-05, + "loss": 0.2584, + "step": 13996 + }, + { + "epoch": 4.32, + "learning_rate": 1.823727281838248e-05, + "loss": 0.2854, + "step": 13997 + }, + { + "epoch": 4.32, + "learning_rate": 1.823698924794298e-05, + "loss": 0.283, + "step": 13998 + }, + { + "epoch": 4.32, + "learning_rate": 1.823670565690127e-05, + "loss": 0.2814, + "step": 13999 + }, + { + "epoch": 4.32, + "learning_rate": 1.823642204525806e-05, + "loss": 0.2829, + "step": 14000 + }, + { + "epoch": 4.32, + "learning_rate": 1.823613841301405e-05, + "loss": 0.2724, + "step": 14001 + }, + { + "epoch": 4.32, + "learning_rate": 1.823585476016996e-05, + "loss": 0.2749, + "step": 14002 + }, + { + "epoch": 4.32, + "learning_rate": 1.823557108672649e-05, + "loss": 0.2776, + "step": 14003 + }, + { + "epoch": 4.32, + "learning_rate": 1.8235287392684358e-05, + "loss": 0.3048, + "step": 14004 + }, + { + "epoch": 4.33, + "learning_rate": 1.8235003678044273e-05, + "loss": 0.2822, + "step": 14005 + }, + { + "epoch": 4.33, + "learning_rate": 1.8234719942806938e-05, + "loss": 0.2909, + "step": 14006 + }, + { + "epoch": 4.33, + "learning_rate": 1.8234436186973068e-05, + "loss": 0.267, + "step": 14007 + }, + { + "epoch": 4.33, + "learning_rate": 1.823415241054337e-05, + "loss": 0.2685, + "step": 14008 + }, + { + "epoch": 4.33, + "learning_rate": 1.8233868613518555e-05, + "loss": 0.2687, + "step": 14009 + }, + { + "epoch": 4.33, + "learning_rate": 1.8233584795899334e-05, + "loss": 0.2667, + "step": 14010 + }, + { + "epoch": 4.33, + "learning_rate": 1.8233300957686418e-05, + "loss": 0.2834, + "step": 14011 + }, + { + "epoch": 4.33, + "learning_rate": 1.823301709888051e-05, + "loss": 0.2807, + "step": 14012 + }, + { + "epoch": 4.33, + "learning_rate": 1.8232733219482326e-05, + "loss": 0.2601, + "step": 14013 + }, + { + "epoch": 4.33, + "learning_rate": 1.8232449319492577e-05, + "loss": 0.2708, + "step": 14014 + }, + { + "epoch": 4.33, + "learning_rate": 1.8232165398911968e-05, + "loss": 0.2922, + "step": 14015 + }, + { + "epoch": 4.33, + "learning_rate": 1.8231881457741215e-05, + "loss": 0.2643, + "step": 14016 + }, + { + "epoch": 4.33, + "learning_rate": 1.8231597495981025e-05, + "loss": 0.2707, + "step": 14017 + }, + { + "epoch": 4.33, + "learning_rate": 1.8231313513632104e-05, + "loss": 0.2635, + "step": 14018 + }, + { + "epoch": 4.33, + "learning_rate": 1.823102951069517e-05, + "loss": 0.2809, + "step": 14019 + }, + { + "epoch": 4.33, + "learning_rate": 1.823074548717093e-05, + "loss": 0.279, + "step": 14020 + }, + { + "epoch": 4.33, + "learning_rate": 1.8230461443060093e-05, + "loss": 0.2455, + "step": 14021 + }, + { + "epoch": 4.33, + "learning_rate": 1.823017737836337e-05, + "loss": 0.2651, + "step": 14022 + }, + { + "epoch": 4.33, + "learning_rate": 1.8229893293081474e-05, + "loss": 0.2836, + "step": 14023 + }, + { + "epoch": 4.33, + "learning_rate": 1.8229609187215112e-05, + "loss": 0.305, + "step": 14024 + }, + { + "epoch": 4.33, + "learning_rate": 1.8229325060765e-05, + "loss": 0.2747, + "step": 14025 + }, + { + "epoch": 4.33, + "learning_rate": 1.8229040913731842e-05, + "loss": 0.2704, + "step": 14026 + }, + { + "epoch": 4.33, + "learning_rate": 1.822875674611635e-05, + "loss": 0.2951, + "step": 14027 + }, + { + "epoch": 4.33, + "learning_rate": 1.822847255791924e-05, + "loss": 0.2653, + "step": 14028 + }, + { + "epoch": 4.33, + "learning_rate": 1.8228188349141218e-05, + "loss": 0.2621, + "step": 14029 + }, + { + "epoch": 4.33, + "learning_rate": 1.8227904119782998e-05, + "loss": 0.2765, + "step": 14030 + }, + { + "epoch": 4.33, + "learning_rate": 1.8227619869845286e-05, + "loss": 0.2881, + "step": 14031 + }, + { + "epoch": 4.33, + "learning_rate": 1.82273355993288e-05, + "loss": 0.2534, + "step": 14032 + }, + { + "epoch": 4.33, + "learning_rate": 1.8227051308234242e-05, + "loss": 0.288, + "step": 14033 + }, + { + "epoch": 4.33, + "learning_rate": 1.8226766996562337e-05, + "loss": 0.2715, + "step": 14034 + }, + { + "epoch": 4.33, + "learning_rate": 1.8226482664313775e-05, + "loss": 0.2773, + "step": 14035 + }, + { + "epoch": 4.33, + "learning_rate": 1.8226198311489288e-05, + "loss": 0.2715, + "step": 14036 + }, + { + "epoch": 4.34, + "learning_rate": 1.8225913938089575e-05, + "loss": 0.2699, + "step": 14037 + }, + { + "epoch": 4.34, + "learning_rate": 1.8225629544115354e-05, + "loss": 0.2701, + "step": 14038 + }, + { + "epoch": 4.34, + "learning_rate": 1.8225345129567333e-05, + "loss": 0.2953, + "step": 14039 + }, + { + "epoch": 4.34, + "learning_rate": 1.8225060694446223e-05, + "loss": 0.2695, + "step": 14040 + }, + { + "epoch": 4.34, + "learning_rate": 1.8224776238752736e-05, + "loss": 0.2626, + "step": 14041 + }, + { + "epoch": 4.34, + "learning_rate": 1.822449176248758e-05, + "loss": 0.271, + "step": 14042 + }, + { + "epoch": 4.34, + "learning_rate": 1.8224207265651474e-05, + "loss": 0.2765, + "step": 14043 + }, + { + "epoch": 4.34, + "learning_rate": 1.8223922748245125e-05, + "loss": 0.2641, + "step": 14044 + }, + { + "epoch": 4.34, + "learning_rate": 1.8223638210269244e-05, + "loss": 0.2676, + "step": 14045 + }, + { + "epoch": 4.34, + "learning_rate": 1.8223353651724545e-05, + "loss": 0.2395, + "step": 14046 + }, + { + "epoch": 4.34, + "learning_rate": 1.8223069072611737e-05, + "loss": 0.2964, + "step": 14047 + }, + { + "epoch": 4.34, + "learning_rate": 1.8222784472931536e-05, + "loss": 0.2778, + "step": 14048 + }, + { + "epoch": 4.34, + "learning_rate": 1.822249985268465e-05, + "loss": 0.2671, + "step": 14049 + }, + { + "epoch": 4.34, + "learning_rate": 1.822221521187179e-05, + "loss": 0.2724, + "step": 14050 + }, + { + "epoch": 4.34, + "learning_rate": 1.8221930550493673e-05, + "loss": 0.2707, + "step": 14051 + }, + { + "epoch": 4.34, + "learning_rate": 1.822164586855101e-05, + "loss": 0.2371, + "step": 14052 + }, + { + "epoch": 4.34, + "learning_rate": 1.8221361166044507e-05, + "loss": 0.2731, + "step": 14053 + }, + { + "epoch": 4.34, + "learning_rate": 1.8221076442974882e-05, + "loss": 0.2774, + "step": 14054 + }, + { + "epoch": 4.34, + "learning_rate": 1.8220791699342845e-05, + "loss": 0.2569, + "step": 14055 + }, + { + "epoch": 4.34, + "learning_rate": 1.822050693514911e-05, + "loss": 0.2602, + "step": 14056 + }, + { + "epoch": 4.34, + "learning_rate": 1.822022215039439e-05, + "loss": 0.2785, + "step": 14057 + }, + { + "epoch": 4.34, + "learning_rate": 1.821993734507939e-05, + "loss": 0.2569, + "step": 14058 + }, + { + "epoch": 4.34, + "learning_rate": 1.821965251920483e-05, + "loss": 0.2683, + "step": 14059 + }, + { + "epoch": 4.34, + "learning_rate": 1.8219367672771416e-05, + "loss": 0.2628, + "step": 14060 + }, + { + "epoch": 4.34, + "learning_rate": 1.8219082805779868e-05, + "loss": 0.2771, + "step": 14061 + }, + { + "epoch": 4.34, + "learning_rate": 1.8218797918230895e-05, + "loss": 0.2605, + "step": 14062 + }, + { + "epoch": 4.34, + "learning_rate": 1.821851301012521e-05, + "loss": 0.2861, + "step": 14063 + }, + { + "epoch": 4.34, + "learning_rate": 1.8218228081463524e-05, + "loss": 0.2585, + "step": 14064 + }, + { + "epoch": 4.34, + "learning_rate": 1.821794313224655e-05, + "loss": 0.2851, + "step": 14065 + }, + { + "epoch": 4.34, + "learning_rate": 1.8217658162475e-05, + "loss": 0.2542, + "step": 14066 + }, + { + "epoch": 4.34, + "learning_rate": 1.821737317214959e-05, + "loss": 0.2803, + "step": 14067 + }, + { + "epoch": 4.34, + "learning_rate": 1.8217088161271034e-05, + "loss": 0.2852, + "step": 14068 + }, + { + "epoch": 4.34, + "learning_rate": 1.8216803129840037e-05, + "loss": 0.2788, + "step": 14069 + }, + { + "epoch": 4.35, + "learning_rate": 1.821651807785732e-05, + "loss": 0.2701, + "step": 14070 + }, + { + "epoch": 4.35, + "learning_rate": 1.821623300532359e-05, + "loss": 0.2474, + "step": 14071 + }, + { + "epoch": 4.35, + "learning_rate": 1.8215947912239564e-05, + "loss": 0.265, + "step": 14072 + }, + { + "epoch": 4.35, + "learning_rate": 1.8215662798605955e-05, + "loss": 0.2977, + "step": 14073 + }, + { + "epoch": 4.35, + "learning_rate": 1.821537766442347e-05, + "loss": 0.2802, + "step": 14074 + }, + { + "epoch": 4.35, + "learning_rate": 1.8215092509692832e-05, + "loss": 0.2416, + "step": 14075 + }, + { + "epoch": 4.35, + "learning_rate": 1.8214807334414747e-05, + "loss": 0.2792, + "step": 14076 + }, + { + "epoch": 4.35, + "learning_rate": 1.821452213858993e-05, + "loss": 0.2827, + "step": 14077 + }, + { + "epoch": 4.35, + "learning_rate": 1.82142369222191e-05, + "loss": 0.2922, + "step": 14078 + }, + { + "epoch": 4.35, + "learning_rate": 1.821395168530296e-05, + "loss": 0.2588, + "step": 14079 + }, + { + "epoch": 4.35, + "learning_rate": 1.8213666427842232e-05, + "loss": 0.2739, + "step": 14080 + }, + { + "epoch": 4.35, + "learning_rate": 1.821338114983762e-05, + "loss": 0.2815, + "step": 14081 + }, + { + "epoch": 4.35, + "learning_rate": 1.8213095851289853e-05, + "loss": 0.2683, + "step": 14082 + }, + { + "epoch": 4.35, + "learning_rate": 1.8212810532199627e-05, + "loss": 0.2776, + "step": 14083 + }, + { + "epoch": 4.35, + "learning_rate": 1.821252519256767e-05, + "loss": 0.2604, + "step": 14084 + }, + { + "epoch": 4.35, + "learning_rate": 1.8212239832394685e-05, + "loss": 0.256, + "step": 14085 + }, + { + "epoch": 4.35, + "learning_rate": 1.8211954451681392e-05, + "loss": 0.2576, + "step": 14086 + }, + { + "epoch": 4.35, + "learning_rate": 1.8211669050428505e-05, + "loss": 0.2767, + "step": 14087 + }, + { + "epoch": 4.35, + "learning_rate": 1.8211383628636733e-05, + "loss": 0.2568, + "step": 14088 + }, + { + "epoch": 4.35, + "learning_rate": 1.8211098186306798e-05, + "loss": 0.2757, + "step": 14089 + }, + { + "epoch": 4.35, + "learning_rate": 1.8210812723439403e-05, + "loss": 0.2909, + "step": 14090 + }, + { + "epoch": 4.35, + "learning_rate": 1.8210527240035268e-05, + "loss": 0.2717, + "step": 14091 + }, + { + "epoch": 4.35, + "learning_rate": 1.821024173609511e-05, + "loss": 0.2599, + "step": 14092 + }, + { + "epoch": 4.35, + "learning_rate": 1.820995621161964e-05, + "loss": 0.2832, + "step": 14093 + }, + { + "epoch": 4.35, + "learning_rate": 1.820967066660957e-05, + "loss": 0.2568, + "step": 14094 + }, + { + "epoch": 4.35, + "learning_rate": 1.8209385101065618e-05, + "loss": 0.2748, + "step": 14095 + }, + { + "epoch": 4.35, + "learning_rate": 1.8209099514988495e-05, + "loss": 0.2667, + "step": 14096 + }, + { + "epoch": 4.35, + "learning_rate": 1.820881390837892e-05, + "loss": 0.2705, + "step": 14097 + }, + { + "epoch": 4.35, + "learning_rate": 1.8208528281237602e-05, + "loss": 0.2592, + "step": 14098 + }, + { + "epoch": 4.35, + "learning_rate": 1.8208242633565257e-05, + "loss": 0.2745, + "step": 14099 + }, + { + "epoch": 4.35, + "learning_rate": 1.82079569653626e-05, + "loss": 0.257, + "step": 14100 + }, + { + "epoch": 4.35, + "learning_rate": 1.8207671276630345e-05, + "loss": 0.2729, + "step": 14101 + }, + { + "epoch": 4.36, + "learning_rate": 1.820738556736921e-05, + "loss": 0.2772, + "step": 14102 + }, + { + "epoch": 4.36, + "learning_rate": 1.8207099837579905e-05, + "loss": 0.2637, + "step": 14103 + }, + { + "epoch": 4.36, + "learning_rate": 1.820681408726315e-05, + "loss": 0.2628, + "step": 14104 + }, + { + "epoch": 4.36, + "learning_rate": 1.820652831641965e-05, + "loss": 0.2609, + "step": 14105 + }, + { + "epoch": 4.36, + "learning_rate": 1.8206242525050127e-05, + "loss": 0.2685, + "step": 14106 + }, + { + "epoch": 4.36, + "learning_rate": 1.8205956713155298e-05, + "loss": 0.2715, + "step": 14107 + }, + { + "epoch": 4.36, + "learning_rate": 1.8205670880735872e-05, + "loss": 0.268, + "step": 14108 + }, + { + "epoch": 4.36, + "learning_rate": 1.820538502779257e-05, + "loss": 0.2652, + "step": 14109 + }, + { + "epoch": 4.36, + "learning_rate": 1.8205099154326096e-05, + "loss": 0.2862, + "step": 14110 + }, + { + "epoch": 4.36, + "learning_rate": 1.820481326033718e-05, + "loss": 0.2828, + "step": 14111 + }, + { + "epoch": 4.36, + "learning_rate": 1.8204527345826526e-05, + "loss": 0.2831, + "step": 14112 + }, + { + "epoch": 4.36, + "learning_rate": 1.8204241410794855e-05, + "loss": 0.2878, + "step": 14113 + }, + { + "epoch": 4.36, + "learning_rate": 1.820395545524288e-05, + "loss": 0.2646, + "step": 14114 + }, + { + "epoch": 4.36, + "learning_rate": 1.8203669479171314e-05, + "loss": 0.2526, + "step": 14115 + }, + { + "epoch": 4.36, + "learning_rate": 1.8203383482580873e-05, + "loss": 0.3073, + "step": 14116 + }, + { + "epoch": 4.36, + "learning_rate": 1.8203097465472276e-05, + "loss": 0.2625, + "step": 14117 + }, + { + "epoch": 4.36, + "learning_rate": 1.8202811427846236e-05, + "loss": 0.2909, + "step": 14118 + }, + { + "epoch": 4.36, + "learning_rate": 1.820252536970347e-05, + "loss": 0.2733, + "step": 14119 + }, + { + "epoch": 4.36, + "learning_rate": 1.820223929104469e-05, + "loss": 0.2814, + "step": 14120 + }, + { + "epoch": 4.36, + "learning_rate": 1.8201953191870612e-05, + "loss": 0.2796, + "step": 14121 + }, + { + "epoch": 4.36, + "learning_rate": 1.8201667072181958e-05, + "loss": 0.2535, + "step": 14122 + }, + { + "epoch": 4.36, + "learning_rate": 1.8201380931979432e-05, + "loss": 0.2784, + "step": 14123 + }, + { + "epoch": 4.36, + "learning_rate": 1.8201094771263764e-05, + "loss": 0.2619, + "step": 14124 + }, + { + "epoch": 4.36, + "learning_rate": 1.8200808590035655e-05, + "loss": 0.2915, + "step": 14125 + }, + { + "epoch": 4.36, + "learning_rate": 1.8200522388295834e-05, + "loss": 0.2547, + "step": 14126 + }, + { + "epoch": 4.36, + "learning_rate": 1.8200236166045008e-05, + "loss": 0.2509, + "step": 14127 + }, + { + "epoch": 4.36, + "learning_rate": 1.8199949923283896e-05, + "loss": 0.2796, + "step": 14128 + }, + { + "epoch": 4.36, + "learning_rate": 1.8199663660013212e-05, + "loss": 0.272, + "step": 14129 + }, + { + "epoch": 4.36, + "learning_rate": 1.819937737623368e-05, + "loss": 0.2639, + "step": 14130 + }, + { + "epoch": 4.36, + "learning_rate": 1.8199091071946e-05, + "loss": 0.2588, + "step": 14131 + }, + { + "epoch": 4.36, + "learning_rate": 1.8198804747150904e-05, + "loss": 0.2687, + "step": 14132 + }, + { + "epoch": 4.36, + "learning_rate": 1.81985184018491e-05, + "loss": 0.2732, + "step": 14133 + }, + { + "epoch": 4.36, + "learning_rate": 1.819823203604131e-05, + "loss": 0.2601, + "step": 14134 + }, + { + "epoch": 4.37, + "learning_rate": 1.819794564972824e-05, + "loss": 0.2652, + "step": 14135 + }, + { + "epoch": 4.37, + "learning_rate": 1.8197659242910616e-05, + "loss": 0.2843, + "step": 14136 + }, + { + "epoch": 4.37, + "learning_rate": 1.8197372815589153e-05, + "loss": 0.2582, + "step": 14137 + }, + { + "epoch": 4.37, + "learning_rate": 1.8197086367764566e-05, + "loss": 0.2643, + "step": 14138 + }, + { + "epoch": 4.37, + "learning_rate": 1.8196799899437563e-05, + "loss": 0.2588, + "step": 14139 + }, + { + "epoch": 4.37, + "learning_rate": 1.8196513410608877e-05, + "loss": 0.2822, + "step": 14140 + }, + { + "epoch": 4.37, + "learning_rate": 1.8196226901279212e-05, + "loss": 0.2621, + "step": 14141 + }, + { + "epoch": 4.37, + "learning_rate": 1.819594037144929e-05, + "loss": 0.282, + "step": 14142 + }, + { + "epoch": 4.37, + "learning_rate": 1.8195653821119825e-05, + "loss": 0.2615, + "step": 14143 + }, + { + "epoch": 4.37, + "learning_rate": 1.8195367250291536e-05, + "loss": 0.2804, + "step": 14144 + }, + { + "epoch": 4.37, + "learning_rate": 1.819508065896514e-05, + "loss": 0.2653, + "step": 14145 + }, + { + "epoch": 4.37, + "learning_rate": 1.8194794047141352e-05, + "loss": 0.264, + "step": 14146 + }, + { + "epoch": 4.37, + "learning_rate": 1.8194507414820887e-05, + "loss": 0.2746, + "step": 14147 + }, + { + "epoch": 4.37, + "learning_rate": 1.8194220762004467e-05, + "loss": 0.2575, + "step": 14148 + }, + { + "epoch": 4.37, + "learning_rate": 1.8193934088692805e-05, + "loss": 0.2641, + "step": 14149 + }, + { + "epoch": 4.37, + "learning_rate": 1.819364739488662e-05, + "loss": 0.263, + "step": 14150 + }, + { + "epoch": 4.37, + "learning_rate": 1.8193360680586628e-05, + "loss": 0.261, + "step": 14151 + }, + { + "epoch": 4.37, + "learning_rate": 1.8193073945793546e-05, + "loss": 0.2702, + "step": 14152 + }, + { + "epoch": 4.37, + "learning_rate": 1.8192787190508095e-05, + "loss": 0.2782, + "step": 14153 + }, + { + "epoch": 4.37, + "learning_rate": 1.8192500414730986e-05, + "loss": 0.2705, + "step": 14154 + }, + { + "epoch": 4.37, + "learning_rate": 1.8192213618462937e-05, + "loss": 0.2567, + "step": 14155 + }, + { + "epoch": 4.37, + "learning_rate": 1.8191926801704673e-05, + "loss": 0.2816, + "step": 14156 + }, + { + "epoch": 4.37, + "learning_rate": 1.81916399644569e-05, + "loss": 0.2589, + "step": 14157 + }, + { + "epoch": 4.37, + "learning_rate": 1.8191353106720346e-05, + "loss": 0.2513, + "step": 14158 + }, + { + "epoch": 4.37, + "learning_rate": 1.8191066228495723e-05, + "loss": 0.2639, + "step": 14159 + }, + { + "epoch": 4.37, + "learning_rate": 1.8190779329783748e-05, + "loss": 0.2632, + "step": 14160 + }, + { + "epoch": 4.37, + "learning_rate": 1.8190492410585143e-05, + "loss": 0.3117, + "step": 14161 + }, + { + "epoch": 4.37, + "learning_rate": 1.819020547090062e-05, + "loss": 0.2841, + "step": 14162 + }, + { + "epoch": 4.37, + "learning_rate": 1.81899185107309e-05, + "loss": 0.2669, + "step": 14163 + }, + { + "epoch": 4.37, + "learning_rate": 1.81896315300767e-05, + "loss": 0.2738, + "step": 14164 + }, + { + "epoch": 4.37, + "learning_rate": 1.8189344528938736e-05, + "loss": 0.248, + "step": 14165 + }, + { + "epoch": 4.37, + "learning_rate": 1.818905750731773e-05, + "loss": 0.2674, + "step": 14166 + }, + { + "epoch": 4.38, + "learning_rate": 1.8188770465214397e-05, + "loss": 0.2654, + "step": 14167 + }, + { + "epoch": 4.38, + "learning_rate": 1.8188483402629455e-05, + "loss": 0.2725, + "step": 14168 + }, + { + "epoch": 4.38, + "learning_rate": 1.8188196319563626e-05, + "loss": 0.2854, + "step": 14169 + }, + { + "epoch": 4.38, + "learning_rate": 1.818790921601762e-05, + "loss": 0.2563, + "step": 14170 + }, + { + "epoch": 4.38, + "learning_rate": 1.818762209199216e-05, + "loss": 0.2698, + "step": 14171 + }, + { + "epoch": 4.38, + "learning_rate": 1.8187334947487966e-05, + "loss": 0.2707, + "step": 14172 + }, + { + "epoch": 4.38, + "learning_rate": 1.8187047782505753e-05, + "loss": 0.2737, + "step": 14173 + }, + { + "epoch": 4.38, + "learning_rate": 1.818676059704624e-05, + "loss": 0.2517, + "step": 14174 + }, + { + "epoch": 4.38, + "learning_rate": 1.8186473391110147e-05, + "loss": 0.266, + "step": 14175 + }, + { + "epoch": 4.38, + "learning_rate": 1.818618616469819e-05, + "loss": 0.2769, + "step": 14176 + }, + { + "epoch": 4.38, + "learning_rate": 1.8185898917811087e-05, + "loss": 0.2518, + "step": 14177 + }, + { + "epoch": 4.38, + "learning_rate": 1.818561165044956e-05, + "loss": 0.2687, + "step": 14178 + }, + { + "epoch": 4.38, + "learning_rate": 1.8185324362614326e-05, + "loss": 0.2556, + "step": 14179 + }, + { + "epoch": 4.38, + "learning_rate": 1.81850370543061e-05, + "loss": 0.2767, + "step": 14180 + }, + { + "epoch": 4.38, + "learning_rate": 1.8184749725525606e-05, + "loss": 0.261, + "step": 14181 + }, + { + "epoch": 4.38, + "learning_rate": 1.8184462376273558e-05, + "loss": 0.2681, + "step": 14182 + }, + { + "epoch": 4.38, + "learning_rate": 1.8184175006550678e-05, + "loss": 0.286, + "step": 14183 + }, + { + "epoch": 4.38, + "learning_rate": 1.818388761635768e-05, + "loss": 0.2579, + "step": 14184 + }, + { + "epoch": 4.38, + "learning_rate": 1.818360020569529e-05, + "loss": 0.2642, + "step": 14185 + }, + { + "epoch": 4.38, + "learning_rate": 1.8183312774564226e-05, + "loss": 0.279, + "step": 14186 + }, + { + "epoch": 4.38, + "learning_rate": 1.81830253229652e-05, + "loss": 0.2679, + "step": 14187 + }, + { + "epoch": 4.38, + "learning_rate": 1.8182737850898937e-05, + "loss": 0.2589, + "step": 14188 + }, + { + "epoch": 4.38, + "learning_rate": 1.8182450358366153e-05, + "loss": 0.2613, + "step": 14189 + }, + { + "epoch": 4.38, + "learning_rate": 1.818216284536757e-05, + "loss": 0.2617, + "step": 14190 + }, + { + "epoch": 4.38, + "learning_rate": 1.8181875311903906e-05, + "loss": 0.2818, + "step": 14191 + }, + { + "epoch": 4.38, + "learning_rate": 1.8181587757975876e-05, + "loss": 0.2456, + "step": 14192 + }, + { + "epoch": 4.38, + "learning_rate": 1.81813001835842e-05, + "loss": 0.2863, + "step": 14193 + }, + { + "epoch": 4.38, + "learning_rate": 1.818101258872961e-05, + "loss": 0.2442, + "step": 14194 + }, + { + "epoch": 4.38, + "learning_rate": 1.818072497341281e-05, + "loss": 0.2666, + "step": 14195 + }, + { + "epoch": 4.38, + "learning_rate": 1.8180437337634523e-05, + "loss": 0.2849, + "step": 14196 + }, + { + "epoch": 4.38, + "learning_rate": 1.818014968139547e-05, + "loss": 0.2816, + "step": 14197 + }, + { + "epoch": 4.38, + "learning_rate": 1.8179862004696372e-05, + "loss": 0.2648, + "step": 14198 + }, + { + "epoch": 4.39, + "learning_rate": 1.817957430753795e-05, + "loss": 0.2674, + "step": 14199 + }, + { + "epoch": 4.39, + "learning_rate": 1.817928658992092e-05, + "loss": 0.2895, + "step": 14200 + }, + { + "epoch": 4.39, + "learning_rate": 1.8178998851846003e-05, + "loss": 0.2637, + "step": 14201 + }, + { + "epoch": 4.39, + "learning_rate": 1.8178711093313916e-05, + "loss": 0.2931, + "step": 14202 + }, + { + "epoch": 4.39, + "learning_rate": 1.8178423314325377e-05, + "loss": 0.2705, + "step": 14203 + }, + { + "epoch": 4.39, + "learning_rate": 1.8178135514881114e-05, + "loss": 0.2627, + "step": 14204 + }, + { + "epoch": 4.39, + "learning_rate": 1.8177847694981845e-05, + "loss": 0.2502, + "step": 14205 + }, + { + "epoch": 4.39, + "learning_rate": 1.8177559854628283e-05, + "loss": 0.2679, + "step": 14206 + }, + { + "epoch": 4.39, + "learning_rate": 1.8177271993821155e-05, + "loss": 0.2532, + "step": 14207 + }, + { + "epoch": 4.39, + "learning_rate": 1.8176984112561177e-05, + "loss": 0.2564, + "step": 14208 + }, + { + "epoch": 4.39, + "learning_rate": 1.8176696210849073e-05, + "loss": 0.2675, + "step": 14209 + }, + { + "epoch": 4.39, + "learning_rate": 1.8176408288685555e-05, + "loss": 0.2831, + "step": 14210 + }, + { + "epoch": 4.39, + "learning_rate": 1.8176120346071352e-05, + "loss": 0.2706, + "step": 14211 + }, + { + "epoch": 4.39, + "learning_rate": 1.8175832383007178e-05, + "loss": 0.2552, + "step": 14212 + }, + { + "epoch": 4.39, + "learning_rate": 1.817554439949376e-05, + "loss": 0.2524, + "step": 14213 + }, + { + "epoch": 4.39, + "learning_rate": 1.8175256395531814e-05, + "loss": 0.2838, + "step": 14214 + }, + { + "epoch": 4.39, + "learning_rate": 1.817496837112206e-05, + "loss": 0.2778, + "step": 14215 + }, + { + "epoch": 4.39, + "learning_rate": 1.817468032626522e-05, + "loss": 0.2657, + "step": 14216 + }, + { + "epoch": 4.39, + "learning_rate": 1.817439226096201e-05, + "loss": 0.2731, + "step": 14217 + }, + { + "epoch": 4.39, + "learning_rate": 1.8174104175213156e-05, + "loss": 0.2559, + "step": 14218 + }, + { + "epoch": 4.39, + "learning_rate": 1.8173816069019378e-05, + "loss": 0.2762, + "step": 14219 + }, + { + "epoch": 4.39, + "learning_rate": 1.817352794238139e-05, + "loss": 0.2642, + "step": 14220 + }, + { + "epoch": 4.39, + "learning_rate": 1.8173239795299923e-05, + "loss": 0.2748, + "step": 14221 + }, + { + "epoch": 4.39, + "learning_rate": 1.8172951627775694e-05, + "loss": 0.2482, + "step": 14222 + }, + { + "epoch": 4.39, + "learning_rate": 1.817266343980942e-05, + "loss": 0.2494, + "step": 14223 + }, + { + "epoch": 4.39, + "learning_rate": 1.817237523140182e-05, + "loss": 0.2818, + "step": 14224 + }, + { + "epoch": 4.39, + "learning_rate": 1.817208700255362e-05, + "loss": 0.2804, + "step": 14225 + }, + { + "epoch": 4.39, + "learning_rate": 1.8171798753265545e-05, + "loss": 0.2675, + "step": 14226 + }, + { + "epoch": 4.39, + "learning_rate": 1.8171510483538307e-05, + "loss": 0.2932, + "step": 14227 + }, + { + "epoch": 4.39, + "learning_rate": 1.8171222193372634e-05, + "loss": 0.2822, + "step": 14228 + }, + { + "epoch": 4.39, + "learning_rate": 1.8170933882769243e-05, + "loss": 0.2495, + "step": 14229 + }, + { + "epoch": 4.39, + "learning_rate": 1.8170645551728857e-05, + "loss": 0.2522, + "step": 14230 + }, + { + "epoch": 4.39, + "learning_rate": 1.8170357200252193e-05, + "loss": 0.2743, + "step": 14231 + }, + { + "epoch": 4.4, + "learning_rate": 1.8170068828339977e-05, + "loss": 0.2537, + "step": 14232 + }, + { + "epoch": 4.4, + "learning_rate": 1.816978043599293e-05, + "loss": 0.2762, + "step": 14233 + }, + { + "epoch": 4.4, + "learning_rate": 1.816949202321177e-05, + "loss": 0.2774, + "step": 14234 + }, + { + "epoch": 4.4, + "learning_rate": 1.8169203589997222e-05, + "loss": 0.2568, + "step": 14235 + }, + { + "epoch": 4.4, + "learning_rate": 1.8168915136350006e-05, + "loss": 0.2711, + "step": 14236 + }, + { + "epoch": 4.4, + "learning_rate": 1.816862666227084e-05, + "loss": 0.2662, + "step": 14237 + }, + { + "epoch": 4.4, + "learning_rate": 1.8168338167760453e-05, + "loss": 0.2711, + "step": 14238 + }, + { + "epoch": 4.4, + "learning_rate": 1.816804965281956e-05, + "loss": 0.2686, + "step": 14239 + }, + { + "epoch": 4.4, + "learning_rate": 1.8167761117448886e-05, + "loss": 0.2681, + "step": 14240 + }, + { + "epoch": 4.4, + "learning_rate": 1.816747256164915e-05, + "loss": 0.283, + "step": 14241 + }, + { + "epoch": 4.4, + "learning_rate": 1.816718398542108e-05, + "loss": 0.2725, + "step": 14242 + }, + { + "epoch": 4.4, + "learning_rate": 1.816689538876539e-05, + "loss": 0.2755, + "step": 14243 + }, + { + "epoch": 4.4, + "learning_rate": 1.8166606771682803e-05, + "loss": 0.2648, + "step": 14244 + }, + { + "epoch": 4.4, + "learning_rate": 1.816631813417405e-05, + "loss": 0.2524, + "step": 14245 + }, + { + "epoch": 4.4, + "learning_rate": 1.816602947623984e-05, + "loss": 0.2745, + "step": 14246 + }, + { + "epoch": 4.4, + "learning_rate": 1.8165740797880903e-05, + "loss": 0.2781, + "step": 14247 + }, + { + "epoch": 4.4, + "learning_rate": 1.8165452099097955e-05, + "loss": 0.2567, + "step": 14248 + }, + { + "epoch": 4.4, + "learning_rate": 1.8165163379891725e-05, + "loss": 0.2703, + "step": 14249 + }, + { + "epoch": 4.4, + "learning_rate": 1.8164874640262937e-05, + "loss": 0.2672, + "step": 14250 + }, + { + "epoch": 4.4, + "learning_rate": 1.81645858802123e-05, + "loss": 0.2484, + "step": 14251 + }, + { + "epoch": 4.4, + "learning_rate": 1.8164297099740545e-05, + "loss": 0.2626, + "step": 14252 + }, + { + "epoch": 4.4, + "learning_rate": 1.81640082988484e-05, + "loss": 0.2626, + "step": 14253 + }, + { + "epoch": 4.4, + "learning_rate": 1.8163719477536578e-05, + "loss": 0.2807, + "step": 14254 + }, + { + "epoch": 4.4, + "learning_rate": 1.8163430635805805e-05, + "loss": 0.2785, + "step": 14255 + }, + { + "epoch": 4.4, + "learning_rate": 1.81631417736568e-05, + "loss": 0.2742, + "step": 14256 + }, + { + "epoch": 4.4, + "learning_rate": 1.8162852891090296e-05, + "loss": 0.2784, + "step": 14257 + }, + { + "epoch": 4.4, + "learning_rate": 1.8162563988107003e-05, + "loss": 0.2817, + "step": 14258 + }, + { + "epoch": 4.4, + "learning_rate": 1.8162275064707648e-05, + "loss": 0.2738, + "step": 14259 + }, + { + "epoch": 4.4, + "learning_rate": 1.816198612089296e-05, + "loss": 0.2576, + "step": 14260 + }, + { + "epoch": 4.4, + "learning_rate": 1.816169715666365e-05, + "loss": 0.2592, + "step": 14261 + }, + { + "epoch": 4.4, + "learning_rate": 1.8161408172020446e-05, + "loss": 0.2666, + "step": 14262 + }, + { + "epoch": 4.4, + "learning_rate": 1.8161119166964075e-05, + "loss": 0.2669, + "step": 14263 + }, + { + "epoch": 4.41, + "learning_rate": 1.8160830141495257e-05, + "loss": 0.2753, + "step": 14264 + }, + { + "epoch": 4.41, + "learning_rate": 1.816054109561471e-05, + "loss": 0.2672, + "step": 14265 + }, + { + "epoch": 4.41, + "learning_rate": 1.8160252029323168e-05, + "loss": 0.2709, + "step": 14266 + }, + { + "epoch": 4.41, + "learning_rate": 1.8159962942621342e-05, + "loss": 0.2552, + "step": 14267 + }, + { + "epoch": 4.41, + "learning_rate": 1.815967383550996e-05, + "loss": 0.2584, + "step": 14268 + }, + { + "epoch": 4.41, + "learning_rate": 1.8159384707989752e-05, + "loss": 0.2663, + "step": 14269 + }, + { + "epoch": 4.41, + "learning_rate": 1.8159095560061427e-05, + "loss": 0.298, + "step": 14270 + }, + { + "epoch": 4.41, + "learning_rate": 1.815880639172572e-05, + "loss": 0.2746, + "step": 14271 + }, + { + "epoch": 4.41, + "learning_rate": 1.8158517202983347e-05, + "loss": 0.2484, + "step": 14272 + }, + { + "epoch": 4.41, + "learning_rate": 1.815822799383504e-05, + "loss": 0.2731, + "step": 14273 + }, + { + "epoch": 4.41, + "learning_rate": 1.8157938764281513e-05, + "loss": 0.252, + "step": 14274 + }, + { + "epoch": 4.41, + "learning_rate": 1.8157649514323492e-05, + "loss": 0.2564, + "step": 14275 + }, + { + "epoch": 4.41, + "learning_rate": 1.8157360243961705e-05, + "loss": 0.2526, + "step": 14276 + }, + { + "epoch": 4.41, + "learning_rate": 1.8157070953196873e-05, + "loss": 0.2518, + "step": 14277 + }, + { + "epoch": 4.41, + "learning_rate": 1.8156781642029714e-05, + "loss": 0.2736, + "step": 14278 + }, + { + "epoch": 4.41, + "learning_rate": 1.815649231046096e-05, + "loss": 0.2451, + "step": 14279 + }, + { + "epoch": 4.41, + "learning_rate": 1.815620295849133e-05, + "loss": 0.2829, + "step": 14280 + }, + { + "epoch": 4.41, + "learning_rate": 1.8155913586121547e-05, + "loss": 0.2708, + "step": 14281 + }, + { + "epoch": 4.41, + "learning_rate": 1.8155624193352338e-05, + "loss": 0.2979, + "step": 14282 + }, + { + "epoch": 4.41, + "learning_rate": 1.8155334780184424e-05, + "loss": 0.2617, + "step": 14283 + }, + { + "epoch": 4.41, + "learning_rate": 1.8155045346618535e-05, + "loss": 0.2699, + "step": 14284 + }, + { + "epoch": 4.41, + "learning_rate": 1.815475589265539e-05, + "loss": 0.2461, + "step": 14285 + }, + { + "epoch": 4.41, + "learning_rate": 1.8154466418295705e-05, + "loss": 0.2649, + "step": 14286 + }, + { + "epoch": 4.41, + "learning_rate": 1.815417692354022e-05, + "loss": 0.2579, + "step": 14287 + }, + { + "epoch": 4.41, + "learning_rate": 1.815388740838965e-05, + "loss": 0.2606, + "step": 14288 + }, + { + "epoch": 4.41, + "learning_rate": 1.8153597872844718e-05, + "loss": 0.2598, + "step": 14289 + }, + { + "epoch": 4.41, + "learning_rate": 1.8153308316906152e-05, + "loss": 0.2892, + "step": 14290 + }, + { + "epoch": 4.41, + "learning_rate": 1.8153018740574678e-05, + "loss": 0.2516, + "step": 14291 + }, + { + "epoch": 4.41, + "learning_rate": 1.815272914385101e-05, + "loss": 0.2597, + "step": 14292 + }, + { + "epoch": 4.41, + "learning_rate": 1.8152439526735884e-05, + "loss": 0.2786, + "step": 14293 + }, + { + "epoch": 4.41, + "learning_rate": 1.815214988923002e-05, + "loss": 0.2647, + "step": 14294 + }, + { + "epoch": 4.41, + "learning_rate": 1.8151860231334143e-05, + "loss": 0.2524, + "step": 14295 + }, + { + "epoch": 4.41, + "learning_rate": 1.8151570553048972e-05, + "loss": 0.2892, + "step": 14296 + }, + { + "epoch": 4.42, + "learning_rate": 1.815128085437524e-05, + "loss": 0.2595, + "step": 14297 + }, + { + "epoch": 4.42, + "learning_rate": 1.8150991135313667e-05, + "loss": 0.2506, + "step": 14298 + }, + { + "epoch": 4.42, + "learning_rate": 1.815070139586498e-05, + "loss": 0.2735, + "step": 14299 + }, + { + "epoch": 4.42, + "learning_rate": 1.81504116360299e-05, + "loss": 0.2498, + "step": 14300 + }, + { + "epoch": 4.42, + "learning_rate": 1.8150121855809156e-05, + "loss": 0.2734, + "step": 14301 + }, + { + "epoch": 4.42, + "learning_rate": 1.814983205520347e-05, + "loss": 0.2703, + "step": 14302 + }, + { + "epoch": 4.42, + "learning_rate": 1.814954223421357e-05, + "loss": 0.2574, + "step": 14303 + }, + { + "epoch": 4.42, + "learning_rate": 1.8149252392840174e-05, + "loss": 0.2629, + "step": 14304 + }, + { + "epoch": 4.42, + "learning_rate": 1.814896253108401e-05, + "loss": 0.2768, + "step": 14305 + }, + { + "epoch": 4.42, + "learning_rate": 1.814867264894581e-05, + "loss": 0.2722, + "step": 14306 + }, + { + "epoch": 4.42, + "learning_rate": 1.8148382746426292e-05, + "loss": 0.2661, + "step": 14307 + }, + { + "epoch": 4.42, + "learning_rate": 1.8148092823526182e-05, + "loss": 0.2811, + "step": 14308 + }, + { + "epoch": 4.42, + "learning_rate": 1.8147802880246205e-05, + "loss": 0.2585, + "step": 14309 + }, + { + "epoch": 4.42, + "learning_rate": 1.8147512916587086e-05, + "loss": 0.2595, + "step": 14310 + }, + { + "epoch": 4.42, + "learning_rate": 1.8147222932549554e-05, + "loss": 0.2669, + "step": 14311 + }, + { + "epoch": 4.42, + "learning_rate": 1.8146932928134327e-05, + "loss": 0.2435, + "step": 14312 + }, + { + "epoch": 4.42, + "learning_rate": 1.814664290334214e-05, + "loss": 0.2492, + "step": 14313 + }, + { + "epoch": 4.42, + "learning_rate": 1.8146352858173712e-05, + "loss": 0.2873, + "step": 14314 + }, + { + "epoch": 4.42, + "learning_rate": 1.8146062792629768e-05, + "loss": 0.3002, + "step": 14315 + }, + { + "epoch": 4.42, + "learning_rate": 1.8145772706711038e-05, + "loss": 0.2655, + "step": 14316 + }, + { + "epoch": 4.42, + "learning_rate": 1.814548260041824e-05, + "loss": 0.2594, + "step": 14317 + }, + { + "epoch": 4.42, + "learning_rate": 1.814519247375211e-05, + "loss": 0.2659, + "step": 14318 + }, + { + "epoch": 4.42, + "learning_rate": 1.8144902326713366e-05, + "loss": 0.2577, + "step": 14319 + }, + { + "epoch": 4.42, + "learning_rate": 1.8144612159302735e-05, + "loss": 0.2659, + "step": 14320 + }, + { + "epoch": 4.42, + "learning_rate": 1.8144321971520945e-05, + "loss": 0.2797, + "step": 14321 + }, + { + "epoch": 4.42, + "learning_rate": 1.8144031763368717e-05, + "loss": 0.2737, + "step": 14322 + }, + { + "epoch": 4.42, + "learning_rate": 1.814374153484678e-05, + "loss": 0.2437, + "step": 14323 + }, + { + "epoch": 4.42, + "learning_rate": 1.8143451285955863e-05, + "loss": 0.2672, + "step": 14324 + }, + { + "epoch": 4.42, + "learning_rate": 1.814316101669669e-05, + "loss": 0.2724, + "step": 14325 + }, + { + "epoch": 4.42, + "learning_rate": 1.814287072706998e-05, + "loss": 0.2867, + "step": 14326 + }, + { + "epoch": 4.42, + "learning_rate": 1.8142580417076472e-05, + "loss": 0.2779, + "step": 14327 + }, + { + "epoch": 4.42, + "learning_rate": 1.8142290086716882e-05, + "loss": 0.2698, + "step": 14328 + }, + { + "epoch": 4.43, + "learning_rate": 1.8141999735991943e-05, + "loss": 0.2806, + "step": 14329 + }, + { + "epoch": 4.43, + "learning_rate": 1.8141709364902374e-05, + "loss": 0.2692, + "step": 14330 + }, + { + "epoch": 4.43, + "learning_rate": 1.8141418973448903e-05, + "loss": 0.2811, + "step": 14331 + }, + { + "epoch": 4.43, + "learning_rate": 1.814112856163226e-05, + "loss": 0.2633, + "step": 14332 + }, + { + "epoch": 4.43, + "learning_rate": 1.814083812945317e-05, + "loss": 0.2544, + "step": 14333 + }, + { + "epoch": 4.43, + "learning_rate": 1.8140547676912362e-05, + "loss": 0.2674, + "step": 14334 + }, + { + "epoch": 4.43, + "learning_rate": 1.8140257204010557e-05, + "loss": 0.2821, + "step": 14335 + }, + { + "epoch": 4.43, + "learning_rate": 1.8139966710748483e-05, + "loss": 0.2807, + "step": 14336 + }, + { + "epoch": 4.43, + "learning_rate": 1.813967619712687e-05, + "loss": 0.295, + "step": 14337 + }, + { + "epoch": 4.43, + "learning_rate": 1.813938566314644e-05, + "loss": 0.2785, + "step": 14338 + }, + { + "epoch": 4.43, + "learning_rate": 1.8139095108807925e-05, + "loss": 0.2861, + "step": 14339 + }, + { + "epoch": 4.43, + "learning_rate": 1.8138804534112045e-05, + "loss": 0.2514, + "step": 14340 + }, + { + "epoch": 4.43, + "learning_rate": 1.8138513939059534e-05, + "loss": 0.2611, + "step": 14341 + }, + { + "epoch": 4.43, + "learning_rate": 1.813822332365111e-05, + "loss": 0.2608, + "step": 14342 + }, + { + "epoch": 4.43, + "learning_rate": 1.813793268788751e-05, + "loss": 0.2722, + "step": 14343 + }, + { + "epoch": 4.43, + "learning_rate": 1.8137642031769457e-05, + "loss": 0.2629, + "step": 14344 + }, + { + "epoch": 4.43, + "learning_rate": 1.8137351355297673e-05, + "loss": 0.2691, + "step": 14345 + }, + { + "epoch": 4.43, + "learning_rate": 1.813706065847289e-05, + "loss": 0.2516, + "step": 14346 + }, + { + "epoch": 4.43, + "learning_rate": 1.8136769941295836e-05, + "loss": 0.2727, + "step": 14347 + }, + { + "epoch": 4.43, + "learning_rate": 1.8136479203767234e-05, + "loss": 0.2624, + "step": 14348 + }, + { + "epoch": 4.43, + "learning_rate": 1.8136188445887818e-05, + "loss": 0.2481, + "step": 14349 + }, + { + "epoch": 4.43, + "learning_rate": 1.8135897667658303e-05, + "loss": 0.2652, + "step": 14350 + }, + { + "epoch": 4.43, + "learning_rate": 1.813560686907943e-05, + "loss": 0.2654, + "step": 14351 + }, + { + "epoch": 4.43, + "learning_rate": 1.813531605015192e-05, + "loss": 0.2708, + "step": 14352 + }, + { + "epoch": 4.43, + "learning_rate": 1.81350252108765e-05, + "loss": 0.2706, + "step": 14353 + }, + { + "epoch": 4.43, + "learning_rate": 1.8134734351253898e-05, + "loss": 0.2589, + "step": 14354 + }, + { + "epoch": 4.43, + "learning_rate": 1.813444347128484e-05, + "loss": 0.2712, + "step": 14355 + }, + { + "epoch": 4.43, + "learning_rate": 1.8134152570970055e-05, + "loss": 0.245, + "step": 14356 + }, + { + "epoch": 4.43, + "learning_rate": 1.8133861650310276e-05, + "loss": 0.2639, + "step": 14357 + }, + { + "epoch": 4.43, + "learning_rate": 1.813357070930622e-05, + "loss": 0.2862, + "step": 14358 + }, + { + "epoch": 4.43, + "learning_rate": 1.8133279747958624e-05, + "loss": 0.2642, + "step": 14359 + }, + { + "epoch": 4.43, + "learning_rate": 1.8132988766268208e-05, + "loss": 0.263, + "step": 14360 + }, + { + "epoch": 4.44, + "learning_rate": 1.8132697764235706e-05, + "loss": 0.269, + "step": 14361 + }, + { + "epoch": 4.44, + "learning_rate": 1.8132406741861846e-05, + "loss": 0.2866, + "step": 14362 + }, + { + "epoch": 4.44, + "learning_rate": 1.813211569914735e-05, + "loss": 0.2602, + "step": 14363 + }, + { + "epoch": 4.44, + "learning_rate": 1.8131824636092948e-05, + "loss": 0.259, + "step": 14364 + }, + { + "epoch": 4.44, + "learning_rate": 1.8131533552699374e-05, + "loss": 0.2581, + "step": 14365 + }, + { + "epoch": 4.44, + "learning_rate": 1.813124244896735e-05, + "loss": 0.2633, + "step": 14366 + }, + { + "epoch": 4.44, + "learning_rate": 1.8130951324897602e-05, + "loss": 0.2239, + "step": 14367 + }, + { + "epoch": 4.44, + "learning_rate": 1.813066018049087e-05, + "loss": 0.253, + "step": 14368 + }, + { + "epoch": 4.44, + "learning_rate": 1.8130369015747867e-05, + "loss": 0.2535, + "step": 14369 + }, + { + "epoch": 4.44, + "learning_rate": 1.813007783066933e-05, + "loss": 0.2803, + "step": 14370 + }, + { + "epoch": 4.44, + "learning_rate": 1.8129786625255983e-05, + "loss": 0.2706, + "step": 14371 + }, + { + "epoch": 4.44, + "learning_rate": 1.812949539950856e-05, + "loss": 0.2343, + "step": 14372 + }, + { + "epoch": 4.44, + "learning_rate": 1.8129204153427787e-05, + "loss": 0.283, + "step": 14373 + }, + { + "epoch": 4.44, + "learning_rate": 1.8128912887014388e-05, + "loss": 0.259, + "step": 14374 + }, + { + "epoch": 4.44, + "learning_rate": 1.8128621600269097e-05, + "loss": 0.2627, + "step": 14375 + }, + { + "epoch": 4.44, + "learning_rate": 1.8128330293192644e-05, + "loss": 0.2702, + "step": 14376 + }, + { + "epoch": 4.44, + "learning_rate": 1.8128038965785754e-05, + "loss": 0.2328, + "step": 14377 + }, + { + "epoch": 4.44, + "learning_rate": 1.8127747618049148e-05, + "loss": 0.2771, + "step": 14378 + }, + { + "epoch": 4.44, + "learning_rate": 1.8127456249983572e-05, + "loss": 0.2661, + "step": 14379 + }, + { + "epoch": 4.44, + "learning_rate": 1.812716486158974e-05, + "loss": 0.2675, + "step": 14380 + }, + { + "epoch": 4.44, + "learning_rate": 1.8126873452868388e-05, + "loss": 0.2655, + "step": 14381 + }, + { + "epoch": 4.44, + "learning_rate": 1.8126582023820245e-05, + "loss": 0.2504, + "step": 14382 + }, + { + "epoch": 4.44, + "learning_rate": 1.8126290574446038e-05, + "loss": 0.294, + "step": 14383 + }, + { + "epoch": 4.44, + "learning_rate": 1.8125999104746496e-05, + "loss": 0.2858, + "step": 14384 + }, + { + "epoch": 4.44, + "learning_rate": 1.8125707614722348e-05, + "loss": 0.2659, + "step": 14385 + }, + { + "epoch": 4.44, + "learning_rate": 1.8125416104374322e-05, + "loss": 0.2787, + "step": 14386 + }, + { + "epoch": 4.44, + "learning_rate": 1.8125124573703146e-05, + "loss": 0.2575, + "step": 14387 + }, + { + "epoch": 4.44, + "learning_rate": 1.8124833022709556e-05, + "loss": 0.2499, + "step": 14388 + }, + { + "epoch": 4.44, + "learning_rate": 1.8124541451394274e-05, + "loss": 0.2528, + "step": 14389 + }, + { + "epoch": 4.44, + "learning_rate": 1.8124249859758034e-05, + "loss": 0.2678, + "step": 14390 + }, + { + "epoch": 4.44, + "learning_rate": 1.8123958247801562e-05, + "loss": 0.2452, + "step": 14391 + }, + { + "epoch": 4.44, + "learning_rate": 1.812366661552559e-05, + "loss": 0.2577, + "step": 14392 + }, + { + "epoch": 4.44, + "learning_rate": 1.8123374962930845e-05, + "loss": 0.2608, + "step": 14393 + }, + { + "epoch": 4.45, + "learning_rate": 1.8123083290018057e-05, + "loss": 0.2622, + "step": 14394 + }, + { + "epoch": 4.45, + "learning_rate": 1.812279159678796e-05, + "loss": 0.2551, + "step": 14395 + }, + { + "epoch": 4.45, + "learning_rate": 1.8122499883241273e-05, + "loss": 0.2643, + "step": 14396 + }, + { + "epoch": 4.45, + "learning_rate": 1.812220814937874e-05, + "loss": 0.2647, + "step": 14397 + }, + { + "epoch": 4.45, + "learning_rate": 1.8121916395201074e-05, + "loss": 0.2793, + "step": 14398 + }, + { + "epoch": 4.45, + "learning_rate": 1.8121624620709022e-05, + "loss": 0.2518, + "step": 14399 + }, + { + "epoch": 4.45, + "learning_rate": 1.81213328259033e-05, + "loss": 0.2708, + "step": 14400 + }, + { + "epoch": 4.45, + "learning_rate": 1.8121041010784647e-05, + "loss": 0.2687, + "step": 14401 + }, + { + "epoch": 4.45, + "learning_rate": 1.812074917535379e-05, + "loss": 0.2445, + "step": 14402 + }, + { + "epoch": 4.45, + "learning_rate": 1.8120457319611456e-05, + "loss": 0.2954, + "step": 14403 + }, + { + "epoch": 4.45, + "learning_rate": 1.8120165443558375e-05, + "loss": 0.2672, + "step": 14404 + }, + { + "epoch": 4.45, + "learning_rate": 1.8119873547195283e-05, + "loss": 0.2593, + "step": 14405 + }, + { + "epoch": 4.45, + "learning_rate": 1.8119581630522903e-05, + "loss": 0.2738, + "step": 14406 + }, + { + "epoch": 4.45, + "learning_rate": 1.811928969354197e-05, + "loss": 0.2739, + "step": 14407 + }, + { + "epoch": 4.45, + "learning_rate": 1.8118997736253214e-05, + "loss": 0.2584, + "step": 14408 + }, + { + "epoch": 4.45, + "learning_rate": 1.8118705758657362e-05, + "loss": 0.2585, + "step": 14409 + }, + { + "epoch": 4.45, + "learning_rate": 1.811841376075515e-05, + "loss": 0.2698, + "step": 14410 + }, + { + "epoch": 4.45, + "learning_rate": 1.81181217425473e-05, + "loss": 0.2599, + "step": 14411 + }, + { + "epoch": 4.45, + "learning_rate": 1.8117829704034545e-05, + "loss": 0.2626, + "step": 14412 + }, + { + "epoch": 4.45, + "learning_rate": 1.8117537645217622e-05, + "loss": 0.2397, + "step": 14413 + }, + { + "epoch": 4.45, + "learning_rate": 1.8117245566097255e-05, + "loss": 0.2846, + "step": 14414 + }, + { + "epoch": 4.45, + "learning_rate": 1.811695346667418e-05, + "loss": 0.2524, + "step": 14415 + }, + { + "epoch": 4.45, + "learning_rate": 1.8116661346949116e-05, + "loss": 0.2624, + "step": 14416 + }, + { + "epoch": 4.45, + "learning_rate": 1.8116369206922807e-05, + "loss": 0.2819, + "step": 14417 + }, + { + "epoch": 4.45, + "learning_rate": 1.811607704659598e-05, + "loss": 0.2779, + "step": 14418 + }, + { + "epoch": 4.45, + "learning_rate": 1.8115784865969358e-05, + "loss": 0.2583, + "step": 14419 + }, + { + "epoch": 4.45, + "learning_rate": 1.8115492665043684e-05, + "loss": 0.2842, + "step": 14420 + }, + { + "epoch": 4.45, + "learning_rate": 1.811520044381968e-05, + "loss": 0.2557, + "step": 14421 + }, + { + "epoch": 4.45, + "learning_rate": 1.811490820229808e-05, + "loss": 0.2753, + "step": 14422 + }, + { + "epoch": 4.45, + "learning_rate": 1.8114615940479613e-05, + "loss": 0.2749, + "step": 14423 + }, + { + "epoch": 4.45, + "learning_rate": 1.811432365836501e-05, + "loss": 0.2586, + "step": 14424 + }, + { + "epoch": 4.45, + "learning_rate": 1.811403135595501e-05, + "loss": 0.2718, + "step": 14425 + }, + { + "epoch": 4.46, + "learning_rate": 1.811373903325033e-05, + "loss": 0.2622, + "step": 14426 + }, + { + "epoch": 4.46, + "learning_rate": 1.8113446690251713e-05, + "loss": 0.2704, + "step": 14427 + }, + { + "epoch": 4.46, + "learning_rate": 1.8113154326959887e-05, + "loss": 0.2652, + "step": 14428 + }, + { + "epoch": 4.46, + "learning_rate": 1.811286194337558e-05, + "loss": 0.2639, + "step": 14429 + }, + { + "epoch": 4.46, + "learning_rate": 1.8112569539499528e-05, + "loss": 0.2853, + "step": 14430 + }, + { + "epoch": 4.46, + "learning_rate": 1.8112277115332457e-05, + "loss": 0.2596, + "step": 14431 + }, + { + "epoch": 4.46, + "learning_rate": 1.8111984670875104e-05, + "loss": 0.2516, + "step": 14432 + }, + { + "epoch": 4.46, + "learning_rate": 1.8111692206128198e-05, + "loss": 0.252, + "step": 14433 + }, + { + "epoch": 4.46, + "learning_rate": 1.8111399721092468e-05, + "loss": 0.2562, + "step": 14434 + }, + { + "epoch": 4.46, + "learning_rate": 1.811110721576865e-05, + "loss": 0.261, + "step": 14435 + }, + { + "epoch": 4.46, + "learning_rate": 1.811081469015747e-05, + "loss": 0.2705, + "step": 14436 + }, + { + "epoch": 4.46, + "learning_rate": 1.8110522144259664e-05, + "loss": 0.2674, + "step": 14437 + }, + { + "epoch": 4.46, + "learning_rate": 1.8110229578075966e-05, + "loss": 0.2517, + "step": 14438 + }, + { + "epoch": 4.46, + "learning_rate": 1.81099369916071e-05, + "loss": 0.2649, + "step": 14439 + }, + { + "epoch": 4.46, + "learning_rate": 1.8109644384853808e-05, + "loss": 0.275, + "step": 14440 + }, + { + "epoch": 4.46, + "learning_rate": 1.8109351757816813e-05, + "loss": 0.2625, + "step": 14441 + }, + { + "epoch": 4.46, + "learning_rate": 1.810905911049685e-05, + "loss": 0.2703, + "step": 14442 + }, + { + "epoch": 4.46, + "learning_rate": 1.8108766442894655e-05, + "loss": 0.263, + "step": 14443 + }, + { + "epoch": 4.46, + "learning_rate": 1.810847375501095e-05, + "loss": 0.2809, + "step": 14444 + }, + { + "epoch": 4.46, + "learning_rate": 1.8108181046846477e-05, + "loss": 0.2578, + "step": 14445 + }, + { + "epoch": 4.46, + "learning_rate": 1.8107888318401965e-05, + "loss": 0.2694, + "step": 14446 + }, + { + "epoch": 4.46, + "learning_rate": 1.8107595569678143e-05, + "loss": 0.2927, + "step": 14447 + }, + { + "epoch": 4.46, + "learning_rate": 1.8107302800675746e-05, + "loss": 0.2679, + "step": 14448 + }, + { + "epoch": 4.46, + "learning_rate": 1.8107010011395506e-05, + "loss": 0.2575, + "step": 14449 + }, + { + "epoch": 4.46, + "learning_rate": 1.810671720183816e-05, + "loss": 0.2695, + "step": 14450 + }, + { + "epoch": 4.46, + "learning_rate": 1.810642437200443e-05, + "loss": 0.2674, + "step": 14451 + }, + { + "epoch": 4.46, + "learning_rate": 1.8106131521895055e-05, + "loss": 0.2555, + "step": 14452 + }, + { + "epoch": 4.46, + "learning_rate": 1.810583865151077e-05, + "loss": 0.273, + "step": 14453 + }, + { + "epoch": 4.46, + "learning_rate": 1.81055457608523e-05, + "loss": 0.2811, + "step": 14454 + }, + { + "epoch": 4.46, + "learning_rate": 1.8105252849920384e-05, + "loss": 0.2802, + "step": 14455 + }, + { + "epoch": 4.46, + "learning_rate": 1.810495991871575e-05, + "loss": 0.2673, + "step": 14456 + }, + { + "epoch": 4.46, + "learning_rate": 1.8104666967239137e-05, + "loss": 0.2728, + "step": 14457 + }, + { + "epoch": 4.47, + "learning_rate": 1.8104373995491272e-05, + "loss": 0.2861, + "step": 14458 + }, + { + "epoch": 4.47, + "learning_rate": 1.8104081003472892e-05, + "loss": 0.2822, + "step": 14459 + }, + { + "epoch": 4.47, + "learning_rate": 1.8103787991184723e-05, + "loss": 0.2756, + "step": 14460 + }, + { + "epoch": 4.47, + "learning_rate": 1.8103494958627502e-05, + "loss": 0.2956, + "step": 14461 + }, + { + "epoch": 4.47, + "learning_rate": 1.8103201905801966e-05, + "loss": 0.2686, + "step": 14462 + }, + { + "epoch": 4.47, + "learning_rate": 1.810290883270884e-05, + "loss": 0.2647, + "step": 14463 + }, + { + "epoch": 4.47, + "learning_rate": 1.8102615739348862e-05, + "loss": 0.2776, + "step": 14464 + }, + { + "epoch": 4.47, + "learning_rate": 1.8102322625722765e-05, + "loss": 0.2648, + "step": 14465 + }, + { + "epoch": 4.47, + "learning_rate": 1.8102029491831283e-05, + "loss": 0.255, + "step": 14466 + }, + { + "epoch": 4.47, + "learning_rate": 1.8101736337675148e-05, + "loss": 0.2728, + "step": 14467 + }, + { + "epoch": 4.47, + "learning_rate": 1.8101443163255087e-05, + "loss": 0.2653, + "step": 14468 + }, + { + "epoch": 4.47, + "learning_rate": 1.8101149968571844e-05, + "loss": 0.2726, + "step": 14469 + }, + { + "epoch": 4.47, + "learning_rate": 1.810085675362615e-05, + "loss": 0.2788, + "step": 14470 + }, + { + "epoch": 4.47, + "learning_rate": 1.810056351841873e-05, + "loss": 0.2782, + "step": 14471 + }, + { + "epoch": 4.47, + "learning_rate": 1.8100270262950324e-05, + "loss": 0.2655, + "step": 14472 + }, + { + "epoch": 4.47, + "learning_rate": 1.8099976987221664e-05, + "loss": 0.2975, + "step": 14473 + }, + { + "epoch": 4.47, + "learning_rate": 1.8099683691233487e-05, + "loss": 0.271, + "step": 14474 + }, + { + "epoch": 4.47, + "learning_rate": 1.809939037498652e-05, + "loss": 0.2613, + "step": 14475 + }, + { + "epoch": 4.47, + "learning_rate": 1.809909703848151e-05, + "loss": 0.267, + "step": 14476 + }, + { + "epoch": 4.47, + "learning_rate": 1.8098803681719172e-05, + "loss": 0.2576, + "step": 14477 + }, + { + "epoch": 4.47, + "learning_rate": 1.809851030470025e-05, + "loss": 0.2614, + "step": 14478 + }, + { + "epoch": 4.47, + "learning_rate": 1.8098216907425478e-05, + "loss": 0.2638, + "step": 14479 + }, + { + "epoch": 4.47, + "learning_rate": 1.809792348989559e-05, + "loss": 0.2654, + "step": 14480 + }, + { + "epoch": 4.47, + "learning_rate": 1.8097630052111313e-05, + "loss": 0.238, + "step": 14481 + }, + { + "epoch": 4.47, + "learning_rate": 1.809733659407339e-05, + "loss": 0.2512, + "step": 14482 + }, + { + "epoch": 4.47, + "learning_rate": 1.8097043115782554e-05, + "loss": 0.2655, + "step": 14483 + }, + { + "epoch": 4.47, + "learning_rate": 1.8096749617239532e-05, + "loss": 0.2775, + "step": 14484 + }, + { + "epoch": 4.47, + "learning_rate": 1.8096456098445068e-05, + "loss": 0.2608, + "step": 14485 + }, + { + "epoch": 4.47, + "learning_rate": 1.8096162559399885e-05, + "loss": 0.2669, + "step": 14486 + }, + { + "epoch": 4.47, + "learning_rate": 1.8095869000104723e-05, + "loss": 0.2688, + "step": 14487 + }, + { + "epoch": 4.47, + "learning_rate": 1.809557542056032e-05, + "loss": 0.2577, + "step": 14488 + }, + { + "epoch": 4.47, + "learning_rate": 1.80952818207674e-05, + "loss": 0.2809, + "step": 14489 + }, + { + "epoch": 4.47, + "learning_rate": 1.809498820072671e-05, + "loss": 0.2573, + "step": 14490 + }, + { + "epoch": 4.48, + "learning_rate": 1.8094694560438975e-05, + "loss": 0.2653, + "step": 14491 + }, + { + "epoch": 4.48, + "learning_rate": 1.8094400899904934e-05, + "loss": 0.2691, + "step": 14492 + }, + { + "epoch": 4.48, + "learning_rate": 1.8094107219125322e-05, + "loss": 0.2553, + "step": 14493 + }, + { + "epoch": 4.48, + "learning_rate": 1.8093813518100867e-05, + "loss": 0.2748, + "step": 14494 + }, + { + "epoch": 4.48, + "learning_rate": 1.809351979683231e-05, + "loss": 0.2587, + "step": 14495 + }, + { + "epoch": 4.48, + "learning_rate": 1.8093226055320382e-05, + "loss": 0.2722, + "step": 14496 + }, + { + "epoch": 4.48, + "learning_rate": 1.8092932293565822e-05, + "loss": 0.257, + "step": 14497 + }, + { + "epoch": 4.48, + "learning_rate": 1.809263851156936e-05, + "loss": 0.2823, + "step": 14498 + }, + { + "epoch": 4.48, + "learning_rate": 1.8092344709331736e-05, + "loss": 0.2725, + "step": 14499 + }, + { + "epoch": 4.48, + "learning_rate": 1.8092050886853683e-05, + "loss": 0.2556, + "step": 14500 + }, + { + "epoch": 4.48, + "learning_rate": 1.809175704413593e-05, + "loss": 0.2623, + "step": 14501 + }, + { + "epoch": 4.48, + "learning_rate": 1.809146318117922e-05, + "loss": 0.2553, + "step": 14502 + }, + { + "epoch": 4.48, + "learning_rate": 1.8091169297984286e-05, + "loss": 0.2846, + "step": 14503 + }, + { + "epoch": 4.48, + "learning_rate": 1.8090875394551858e-05, + "loss": 0.2717, + "step": 14504 + }, + { + "epoch": 4.48, + "learning_rate": 1.809058147088268e-05, + "loss": 0.2755, + "step": 14505 + }, + { + "epoch": 4.48, + "learning_rate": 1.8090287526977475e-05, + "loss": 0.2722, + "step": 14506 + }, + { + "epoch": 4.48, + "learning_rate": 1.808999356283699e-05, + "loss": 0.2463, + "step": 14507 + }, + { + "epoch": 4.48, + "learning_rate": 1.8089699578461955e-05, + "loss": 0.2654, + "step": 14508 + }, + { + "epoch": 4.48, + "learning_rate": 1.8089405573853106e-05, + "loss": 0.2807, + "step": 14509 + }, + { + "epoch": 4.48, + "learning_rate": 1.808911154901118e-05, + "loss": 0.2682, + "step": 14510 + }, + { + "epoch": 4.48, + "learning_rate": 1.8088817503936907e-05, + "loss": 0.2674, + "step": 14511 + }, + { + "epoch": 4.48, + "learning_rate": 1.808852343863103e-05, + "loss": 0.2766, + "step": 14512 + }, + { + "epoch": 4.48, + "learning_rate": 1.8088229353094276e-05, + "loss": 0.2803, + "step": 14513 + }, + { + "epoch": 4.48, + "learning_rate": 1.808793524732739e-05, + "loss": 0.2798, + "step": 14514 + }, + { + "epoch": 4.48, + "learning_rate": 1.8087641121331098e-05, + "loss": 0.2651, + "step": 14515 + }, + { + "epoch": 4.48, + "learning_rate": 1.8087346975106146e-05, + "loss": 0.27, + "step": 14516 + }, + { + "epoch": 4.48, + "learning_rate": 1.8087052808653258e-05, + "loss": 0.2574, + "step": 14517 + }, + { + "epoch": 4.48, + "learning_rate": 1.808675862197318e-05, + "loss": 0.2803, + "step": 14518 + }, + { + "epoch": 4.48, + "learning_rate": 1.808646441506664e-05, + "loss": 0.2728, + "step": 14519 + }, + { + "epoch": 4.48, + "learning_rate": 1.8086170187934386e-05, + "loss": 0.2784, + "step": 14520 + }, + { + "epoch": 4.48, + "learning_rate": 1.8085875940577136e-05, + "loss": 0.2725, + "step": 14521 + }, + { + "epoch": 4.48, + "learning_rate": 1.808558167299564e-05, + "loss": 0.2644, + "step": 14522 + }, + { + "epoch": 4.49, + "learning_rate": 1.8085287385190627e-05, + "loss": 0.2789, + "step": 14523 + }, + { + "epoch": 4.49, + "learning_rate": 1.808499307716284e-05, + "loss": 0.2612, + "step": 14524 + }, + { + "epoch": 4.49, + "learning_rate": 1.8084698748913007e-05, + "loss": 0.2603, + "step": 14525 + }, + { + "epoch": 4.49, + "learning_rate": 1.808440440044187e-05, + "loss": 0.279, + "step": 14526 + }, + { + "epoch": 4.49, + "learning_rate": 1.8084110031750162e-05, + "loss": 0.2798, + "step": 14527 + }, + { + "epoch": 4.49, + "learning_rate": 1.808381564283862e-05, + "loss": 0.2767, + "step": 14528 + }, + { + "epoch": 4.49, + "learning_rate": 1.8083521233707982e-05, + "loss": 0.2468, + "step": 14529 + }, + { + "epoch": 4.49, + "learning_rate": 1.808322680435898e-05, + "loss": 0.2751, + "step": 14530 + }, + { + "epoch": 4.49, + "learning_rate": 1.8082932354792357e-05, + "loss": 0.2628, + "step": 14531 + }, + { + "epoch": 4.49, + "learning_rate": 1.8082637885008846e-05, + "loss": 0.2694, + "step": 14532 + }, + { + "epoch": 4.49, + "learning_rate": 1.8082343395009182e-05, + "loss": 0.2743, + "step": 14533 + }, + { + "epoch": 4.49, + "learning_rate": 1.8082048884794105e-05, + "loss": 0.2702, + "step": 14534 + }, + { + "epoch": 4.49, + "learning_rate": 1.8081754354364346e-05, + "loss": 0.2632, + "step": 14535 + }, + { + "epoch": 4.49, + "learning_rate": 1.8081459803720647e-05, + "loss": 0.2462, + "step": 14536 + }, + { + "epoch": 4.49, + "learning_rate": 1.8081165232863743e-05, + "loss": 0.2786, + "step": 14537 + }, + { + "epoch": 4.49, + "learning_rate": 1.808087064179437e-05, + "loss": 0.2709, + "step": 14538 + }, + { + "epoch": 4.49, + "learning_rate": 1.808057603051327e-05, + "loss": 0.2514, + "step": 14539 + }, + { + "epoch": 4.49, + "learning_rate": 1.808028139902117e-05, + "loss": 0.2745, + "step": 14540 + }, + { + "epoch": 4.49, + "learning_rate": 1.8079986747318817e-05, + "loss": 0.2735, + "step": 14541 + }, + { + "epoch": 4.49, + "learning_rate": 1.807969207540694e-05, + "loss": 0.2748, + "step": 14542 + }, + { + "epoch": 4.49, + "learning_rate": 1.8079397383286278e-05, + "loss": 0.2731, + "step": 14543 + }, + { + "epoch": 4.49, + "learning_rate": 1.8079102670957572e-05, + "loss": 0.2661, + "step": 14544 + }, + { + "epoch": 4.49, + "learning_rate": 1.8078807938421558e-05, + "loss": 0.2591, + "step": 14545 + }, + { + "epoch": 4.49, + "learning_rate": 1.807851318567897e-05, + "loss": 0.278, + "step": 14546 + }, + { + "epoch": 4.49, + "learning_rate": 1.807821841273055e-05, + "loss": 0.264, + "step": 14547 + }, + { + "epoch": 4.49, + "learning_rate": 1.807792361957703e-05, + "loss": 0.2595, + "step": 14548 + }, + { + "epoch": 4.49, + "learning_rate": 1.807762880621915e-05, + "loss": 0.2682, + "step": 14549 + }, + { + "epoch": 4.49, + "learning_rate": 1.8077333972657648e-05, + "loss": 0.2611, + "step": 14550 + }, + { + "epoch": 4.49, + "learning_rate": 1.8077039118893258e-05, + "loss": 0.2597, + "step": 14551 + }, + { + "epoch": 4.49, + "learning_rate": 1.8076744244926722e-05, + "loss": 0.25, + "step": 14552 + }, + { + "epoch": 4.49, + "learning_rate": 1.8076449350758775e-05, + "loss": 0.2667, + "step": 14553 + }, + { + "epoch": 4.49, + "learning_rate": 1.8076154436390157e-05, + "loss": 0.2763, + "step": 14554 + }, + { + "epoch": 4.49, + "learning_rate": 1.80758595018216e-05, + "loss": 0.264, + "step": 14555 + }, + { + "epoch": 4.5, + "learning_rate": 1.807556454705385e-05, + "loss": 0.2504, + "step": 14556 + }, + { + "epoch": 4.5, + "learning_rate": 1.8075269572087636e-05, + "loss": 0.264, + "step": 14557 + }, + { + "epoch": 4.5, + "learning_rate": 1.80749745769237e-05, + "loss": 0.2538, + "step": 14558 + }, + { + "epoch": 4.5, + "learning_rate": 1.8074679561562784e-05, + "loss": 0.2487, + "step": 14559 + }, + { + "epoch": 4.5, + "learning_rate": 1.8074384526005618e-05, + "loss": 0.2771, + "step": 14560 + }, + { + "epoch": 4.5, + "learning_rate": 1.8074089470252943e-05, + "loss": 0.2627, + "step": 14561 + }, + { + "epoch": 4.5, + "learning_rate": 1.80737943943055e-05, + "loss": 0.2795, + "step": 14562 + }, + { + "epoch": 4.5, + "learning_rate": 1.8073499298164023e-05, + "loss": 0.2702, + "step": 14563 + }, + { + "epoch": 4.5, + "learning_rate": 1.8073204181829255e-05, + "loss": 0.276, + "step": 14564 + }, + { + "epoch": 4.5, + "learning_rate": 1.8072909045301926e-05, + "loss": 0.2596, + "step": 14565 + }, + { + "epoch": 4.5, + "learning_rate": 1.8072613888582782e-05, + "loss": 0.273, + "step": 14566 + }, + { + "epoch": 4.5, + "learning_rate": 1.8072318711672558e-05, + "loss": 0.2726, + "step": 14567 + }, + { + "epoch": 4.5, + "learning_rate": 1.8072023514571992e-05, + "loss": 0.2646, + "step": 14568 + }, + { + "epoch": 4.5, + "learning_rate": 1.8071728297281824e-05, + "loss": 0.2608, + "step": 14569 + }, + { + "epoch": 4.5, + "learning_rate": 1.807143305980279e-05, + "loss": 0.269, + "step": 14570 + }, + { + "epoch": 4.5, + "learning_rate": 1.8071137802135632e-05, + "loss": 0.2605, + "step": 14571 + }, + { + "epoch": 4.5, + "learning_rate": 1.8070842524281083e-05, + "loss": 0.264, + "step": 14572 + }, + { + "epoch": 4.5, + "learning_rate": 1.8070547226239886e-05, + "loss": 0.2789, + "step": 14573 + }, + { + "epoch": 4.5, + "learning_rate": 1.8070251908012785e-05, + "loss": 0.2649, + "step": 14574 + }, + { + "epoch": 4.5, + "learning_rate": 1.8069956569600503e-05, + "loss": 0.2617, + "step": 14575 + }, + { + "epoch": 4.5, + "learning_rate": 1.8069661211003792e-05, + "loss": 0.2642, + "step": 14576 + }, + { + "epoch": 4.5, + "learning_rate": 1.8069365832223384e-05, + "loss": 0.2482, + "step": 14577 + }, + { + "epoch": 4.5, + "learning_rate": 1.8069070433260023e-05, + "loss": 0.2686, + "step": 14578 + }, + { + "epoch": 4.5, + "learning_rate": 1.8068775014114443e-05, + "loss": 0.2446, + "step": 14579 + }, + { + "epoch": 4.5, + "learning_rate": 1.8068479574787384e-05, + "loss": 0.2736, + "step": 14580 + }, + { + "epoch": 4.5, + "learning_rate": 1.806818411527959e-05, + "loss": 0.2668, + "step": 14581 + }, + { + "epoch": 4.5, + "learning_rate": 1.8067888635591796e-05, + "loss": 0.2436, + "step": 14582 + }, + { + "epoch": 4.5, + "learning_rate": 1.8067593135724738e-05, + "loss": 0.276, + "step": 14583 + }, + { + "epoch": 4.5, + "learning_rate": 1.806729761567916e-05, + "loss": 0.2815, + "step": 14584 + }, + { + "epoch": 4.5, + "learning_rate": 1.8067002075455796e-05, + "loss": 0.2521, + "step": 14585 + }, + { + "epoch": 4.5, + "learning_rate": 1.806670651505539e-05, + "loss": 0.2807, + "step": 14586 + }, + { + "epoch": 4.5, + "learning_rate": 1.806641093447868e-05, + "loss": 0.2632, + "step": 14587 + }, + { + "epoch": 4.51, + "learning_rate": 1.8066115333726405e-05, + "loss": 0.2541, + "step": 14588 + }, + { + "epoch": 4.51, + "learning_rate": 1.8065819712799307e-05, + "loss": 0.2645, + "step": 14589 + }, + { + "epoch": 4.51, + "learning_rate": 1.806552407169812e-05, + "loss": 0.2655, + "step": 14590 + }, + { + "epoch": 4.51, + "learning_rate": 1.8065228410423588e-05, + "loss": 0.2622, + "step": 14591 + }, + { + "epoch": 4.51, + "learning_rate": 1.8064932728976447e-05, + "loss": 0.254, + "step": 14592 + }, + { + "epoch": 4.51, + "learning_rate": 1.8064637027357437e-05, + "loss": 0.2593, + "step": 14593 + }, + { + "epoch": 4.51, + "learning_rate": 1.8064341305567303e-05, + "loss": 0.2763, + "step": 14594 + }, + { + "epoch": 4.51, + "learning_rate": 1.8064045563606777e-05, + "loss": 0.2491, + "step": 14595 + }, + { + "epoch": 4.51, + "learning_rate": 1.8063749801476603e-05, + "loss": 0.2706, + "step": 14596 + }, + { + "epoch": 4.51, + "learning_rate": 1.8063454019177522e-05, + "loss": 0.2783, + "step": 14597 + }, + { + "epoch": 4.51, + "learning_rate": 1.806315821671027e-05, + "loss": 0.2731, + "step": 14598 + }, + { + "epoch": 4.51, + "learning_rate": 1.806286239407559e-05, + "loss": 0.2691, + "step": 14599 + }, + { + "epoch": 4.51, + "learning_rate": 1.8062566551274222e-05, + "loss": 0.2635, + "step": 14600 + }, + { + "epoch": 4.51, + "learning_rate": 1.80622706883069e-05, + "loss": 0.2735, + "step": 14601 + }, + { + "epoch": 4.51, + "learning_rate": 1.806197480517437e-05, + "loss": 0.2623, + "step": 14602 + }, + { + "epoch": 4.51, + "learning_rate": 1.8061678901877372e-05, + "loss": 0.2688, + "step": 14603 + }, + { + "epoch": 4.51, + "learning_rate": 1.8061382978416645e-05, + "loss": 0.2818, + "step": 14604 + }, + { + "epoch": 4.51, + "learning_rate": 1.806108703479293e-05, + "loss": 0.274, + "step": 14605 + }, + { + "epoch": 4.51, + "learning_rate": 1.8060791071006962e-05, + "loss": 0.2679, + "step": 14606 + }, + { + "epoch": 4.51, + "learning_rate": 1.806049508705949e-05, + "loss": 0.2523, + "step": 14607 + }, + { + "epoch": 4.51, + "learning_rate": 1.8060199082951245e-05, + "loss": 0.2616, + "step": 14608 + }, + { + "epoch": 4.51, + "learning_rate": 1.8059903058682976e-05, + "loss": 0.2633, + "step": 14609 + }, + { + "epoch": 4.51, + "learning_rate": 1.8059607014255417e-05, + "loss": 0.268, + "step": 14610 + }, + { + "epoch": 4.51, + "learning_rate": 1.8059310949669307e-05, + "loss": 0.2855, + "step": 14611 + }, + { + "epoch": 4.51, + "learning_rate": 1.8059014864925396e-05, + "loss": 0.2678, + "step": 14612 + }, + { + "epoch": 4.51, + "learning_rate": 1.8058718760024418e-05, + "loss": 0.2589, + "step": 14613 + }, + { + "epoch": 4.51, + "learning_rate": 1.8058422634967115e-05, + "loss": 0.2617, + "step": 14614 + }, + { + "epoch": 4.51, + "learning_rate": 1.8058126489754227e-05, + "loss": 0.2568, + "step": 14615 + }, + { + "epoch": 4.51, + "learning_rate": 1.8057830324386494e-05, + "loss": 0.2728, + "step": 14616 + }, + { + "epoch": 4.51, + "learning_rate": 1.805753413886466e-05, + "loss": 0.2679, + "step": 14617 + }, + { + "epoch": 4.51, + "learning_rate": 1.8057237933189458e-05, + "loss": 0.2737, + "step": 14618 + }, + { + "epoch": 4.51, + "learning_rate": 1.8056941707361638e-05, + "loss": 0.2555, + "step": 14619 + }, + { + "epoch": 4.52, + "learning_rate": 1.805664546138194e-05, + "loss": 0.2546, + "step": 14620 + }, + { + "epoch": 4.52, + "learning_rate": 1.80563491952511e-05, + "loss": 0.2638, + "step": 14621 + }, + { + "epoch": 4.52, + "learning_rate": 1.805605290896986e-05, + "loss": 0.2756, + "step": 14622 + }, + { + "epoch": 4.52, + "learning_rate": 1.8055756602538964e-05, + "loss": 0.2819, + "step": 14623 + }, + { + "epoch": 4.52, + "learning_rate": 1.805546027595915e-05, + "loss": 0.2848, + "step": 14624 + }, + { + "epoch": 4.52, + "learning_rate": 1.8055163929231157e-05, + "loss": 0.2617, + "step": 14625 + }, + { + "epoch": 4.52, + "learning_rate": 1.8054867562355736e-05, + "loss": 0.2783, + "step": 14626 + }, + { + "epoch": 4.52, + "learning_rate": 1.805457117533362e-05, + "loss": 0.2617, + "step": 14627 + }, + { + "epoch": 4.52, + "learning_rate": 1.8054274768165553e-05, + "loss": 0.2702, + "step": 14628 + }, + { + "epoch": 4.52, + "learning_rate": 1.805397834085228e-05, + "loss": 0.2473, + "step": 14629 + }, + { + "epoch": 4.52, + "learning_rate": 1.805368189339453e-05, + "loss": 0.2614, + "step": 14630 + }, + { + "epoch": 4.52, + "learning_rate": 1.8053385425793056e-05, + "loss": 0.2572, + "step": 14631 + }, + { + "epoch": 4.52, + "learning_rate": 1.8053088938048598e-05, + "loss": 0.2706, + "step": 14632 + }, + { + "epoch": 4.52, + "learning_rate": 1.8052792430161893e-05, + "loss": 0.2741, + "step": 14633 + }, + { + "epoch": 4.52, + "learning_rate": 1.8052495902133687e-05, + "loss": 0.2614, + "step": 14634 + }, + { + "epoch": 4.52, + "learning_rate": 1.805219935396472e-05, + "loss": 0.2514, + "step": 14635 + }, + { + "epoch": 4.52, + "learning_rate": 1.8051902785655735e-05, + "loss": 0.2731, + "step": 14636 + }, + { + "epoch": 4.52, + "learning_rate": 1.805160619720747e-05, + "loss": 0.2439, + "step": 14637 + }, + { + "epoch": 4.52, + "learning_rate": 1.805130958862067e-05, + "loss": 0.2751, + "step": 14638 + }, + { + "epoch": 4.52, + "learning_rate": 1.8051012959896076e-05, + "loss": 0.2694, + "step": 14639 + }, + { + "epoch": 4.52, + "learning_rate": 1.8050716311034432e-05, + "loss": 0.2554, + "step": 14640 + }, + { + "epoch": 4.52, + "learning_rate": 1.8050419642036477e-05, + "loss": 0.2398, + "step": 14641 + }, + { + "epoch": 4.52, + "learning_rate": 1.8050122952902954e-05, + "loss": 0.2728, + "step": 14642 + }, + { + "epoch": 4.52, + "learning_rate": 1.8049826243634606e-05, + "loss": 0.2772, + "step": 14643 + }, + { + "epoch": 4.52, + "learning_rate": 1.8049529514232174e-05, + "loss": 0.2691, + "step": 14644 + }, + { + "epoch": 4.52, + "learning_rate": 1.80492327646964e-05, + "loss": 0.2747, + "step": 14645 + }, + { + "epoch": 4.52, + "learning_rate": 1.8048935995028026e-05, + "loss": 0.2556, + "step": 14646 + }, + { + "epoch": 4.52, + "learning_rate": 1.8048639205227798e-05, + "loss": 0.2709, + "step": 14647 + }, + { + "epoch": 4.52, + "learning_rate": 1.8048342395296452e-05, + "loss": 0.2513, + "step": 14648 + }, + { + "epoch": 4.52, + "learning_rate": 1.8048045565234736e-05, + "loss": 0.2613, + "step": 14649 + }, + { + "epoch": 4.52, + "learning_rate": 1.8047748715043392e-05, + "loss": 0.2608, + "step": 14650 + }, + { + "epoch": 4.52, + "learning_rate": 1.8047451844723155e-05, + "loss": 0.2665, + "step": 14651 + }, + { + "epoch": 4.52, + "learning_rate": 1.8047154954274775e-05, + "loss": 0.2883, + "step": 14652 + }, + { + "epoch": 4.53, + "learning_rate": 1.8046858043699e-05, + "loss": 0.2618, + "step": 14653 + }, + { + "epoch": 4.53, + "learning_rate": 1.8046561112996554e-05, + "loss": 0.2813, + "step": 14654 + }, + { + "epoch": 4.53, + "learning_rate": 1.80462641621682e-05, + "loss": 0.2677, + "step": 14655 + }, + { + "epoch": 4.53, + "learning_rate": 1.8045967191214665e-05, + "loss": 0.2351, + "step": 14656 + }, + { + "epoch": 4.53, + "learning_rate": 1.8045670200136705e-05, + "loss": 0.2915, + "step": 14657 + }, + { + "epoch": 4.53, + "learning_rate": 1.804537318893505e-05, + "loss": 0.2775, + "step": 14658 + }, + { + "epoch": 4.53, + "learning_rate": 1.8045076157610455e-05, + "loss": 0.2642, + "step": 14659 + }, + { + "epoch": 4.53, + "learning_rate": 1.8044779106163653e-05, + "loss": 0.2677, + "step": 14660 + }, + { + "epoch": 4.53, + "learning_rate": 1.8044482034595394e-05, + "loss": 0.2619, + "step": 14661 + }, + { + "epoch": 4.53, + "learning_rate": 1.8044184942906416e-05, + "loss": 0.2622, + "step": 14662 + }, + { + "epoch": 4.53, + "learning_rate": 1.8043887831097465e-05, + "loss": 0.2477, + "step": 14663 + }, + { + "epoch": 4.53, + "learning_rate": 1.8043590699169286e-05, + "loss": 0.2478, + "step": 14664 + }, + { + "epoch": 4.53, + "learning_rate": 1.8043293547122614e-05, + "loss": 0.2722, + "step": 14665 + }, + { + "epoch": 4.53, + "learning_rate": 1.8042996374958205e-05, + "loss": 0.2767, + "step": 14666 + }, + { + "epoch": 4.53, + "learning_rate": 1.804269918267679e-05, + "loss": 0.2701, + "step": 14667 + }, + { + "epoch": 4.53, + "learning_rate": 1.804240197027912e-05, + "loss": 0.2543, + "step": 14668 + }, + { + "epoch": 4.53, + "learning_rate": 1.8042104737765936e-05, + "loss": 0.2684, + "step": 14669 + }, + { + "epoch": 4.53, + "learning_rate": 1.8041807485137978e-05, + "loss": 0.269, + "step": 14670 + }, + { + "epoch": 4.53, + "learning_rate": 1.8041510212395992e-05, + "loss": 0.2748, + "step": 14671 + }, + { + "epoch": 4.53, + "learning_rate": 1.8041212919540728e-05, + "loss": 0.3132, + "step": 14672 + }, + { + "epoch": 4.53, + "learning_rate": 1.804091560657292e-05, + "loss": 0.2622, + "step": 14673 + }, + { + "epoch": 4.53, + "learning_rate": 1.804061827349332e-05, + "loss": 0.2522, + "step": 14674 + }, + { + "epoch": 4.53, + "learning_rate": 1.804032092030266e-05, + "loss": 0.2792, + "step": 14675 + }, + { + "epoch": 4.53, + "learning_rate": 1.8040023547001693e-05, + "loss": 0.2715, + "step": 14676 + }, + { + "epoch": 4.53, + "learning_rate": 1.8039726153591164e-05, + "loss": 0.2599, + "step": 14677 + }, + { + "epoch": 4.53, + "learning_rate": 1.803942874007181e-05, + "loss": 0.273, + "step": 14678 + }, + { + "epoch": 4.53, + "learning_rate": 1.803913130644438e-05, + "loss": 0.2481, + "step": 14679 + }, + { + "epoch": 4.53, + "learning_rate": 1.8038833852709617e-05, + "loss": 0.2552, + "step": 14680 + }, + { + "epoch": 4.53, + "learning_rate": 1.8038536378868264e-05, + "loss": 0.2779, + "step": 14681 + }, + { + "epoch": 4.53, + "learning_rate": 1.8038238884921067e-05, + "loss": 0.2832, + "step": 14682 + }, + { + "epoch": 4.53, + "learning_rate": 1.8037941370868766e-05, + "loss": 0.2667, + "step": 14683 + }, + { + "epoch": 4.53, + "learning_rate": 1.8037643836712107e-05, + "loss": 0.2495, + "step": 14684 + }, + { + "epoch": 4.54, + "learning_rate": 1.8037346282451834e-05, + "loss": 0.2695, + "step": 14685 + }, + { + "epoch": 4.54, + "learning_rate": 1.8037048708088697e-05, + "loss": 0.2833, + "step": 14686 + }, + { + "epoch": 4.54, + "learning_rate": 1.803675111362343e-05, + "loss": 0.2603, + "step": 14687 + }, + { + "epoch": 4.54, + "learning_rate": 1.8036453499056787e-05, + "loss": 0.2721, + "step": 14688 + }, + { + "epoch": 4.54, + "learning_rate": 1.8036155864389505e-05, + "loss": 0.2824, + "step": 14689 + }, + { + "epoch": 4.54, + "learning_rate": 1.803585820962233e-05, + "loss": 0.2716, + "step": 14690 + }, + { + "epoch": 4.54, + "learning_rate": 1.8035560534756014e-05, + "loss": 0.2559, + "step": 14691 + }, + { + "epoch": 4.54, + "learning_rate": 1.803526283979129e-05, + "loss": 0.2782, + "step": 14692 + }, + { + "epoch": 4.54, + "learning_rate": 1.803496512472891e-05, + "loss": 0.2475, + "step": 14693 + }, + { + "epoch": 4.54, + "learning_rate": 1.8034667389569617e-05, + "loss": 0.2648, + "step": 14694 + }, + { + "epoch": 4.54, + "learning_rate": 1.8034369634314158e-05, + "loss": 0.2416, + "step": 14695 + }, + { + "epoch": 4.54, + "learning_rate": 1.803407185896327e-05, + "loss": 0.2584, + "step": 14696 + }, + { + "epoch": 4.54, + "learning_rate": 1.8033774063517705e-05, + "loss": 0.2695, + "step": 14697 + }, + { + "epoch": 4.54, + "learning_rate": 1.8033476247978206e-05, + "loss": 0.2829, + "step": 14698 + }, + { + "epoch": 4.54, + "learning_rate": 1.8033178412345517e-05, + "loss": 0.2487, + "step": 14699 + }, + { + "epoch": 4.54, + "learning_rate": 1.8032880556620383e-05, + "loss": 0.2751, + "step": 14700 + }, + { + "epoch": 4.54, + "learning_rate": 1.8032582680803553e-05, + "loss": 0.2649, + "step": 14701 + }, + { + "epoch": 4.54, + "learning_rate": 1.803228478489577e-05, + "loss": 0.2647, + "step": 14702 + }, + { + "epoch": 4.54, + "learning_rate": 1.8031986868897772e-05, + "loss": 0.2645, + "step": 14703 + }, + { + "epoch": 4.54, + "learning_rate": 1.8031688932810313e-05, + "loss": 0.2783, + "step": 14704 + }, + { + "epoch": 4.54, + "learning_rate": 1.8031390976634132e-05, + "loss": 0.2913, + "step": 14705 + }, + { + "epoch": 4.54, + "learning_rate": 1.8031093000369982e-05, + "loss": 0.2634, + "step": 14706 + }, + { + "epoch": 4.54, + "learning_rate": 1.80307950040186e-05, + "loss": 0.2668, + "step": 14707 + }, + { + "epoch": 4.54, + "learning_rate": 1.803049698758074e-05, + "loss": 0.2653, + "step": 14708 + }, + { + "epoch": 4.54, + "learning_rate": 1.8030198951057135e-05, + "loss": 0.2599, + "step": 14709 + }, + { + "epoch": 4.54, + "learning_rate": 1.8029900894448542e-05, + "loss": 0.2572, + "step": 14710 + }, + { + "epoch": 4.54, + "learning_rate": 1.8029602817755704e-05, + "loss": 0.2648, + "step": 14711 + }, + { + "epoch": 4.54, + "learning_rate": 1.8029304720979362e-05, + "loss": 0.2651, + "step": 14712 + }, + { + "epoch": 4.54, + "learning_rate": 1.8029006604120265e-05, + "loss": 0.2607, + "step": 14713 + }, + { + "epoch": 4.54, + "learning_rate": 1.802870846717916e-05, + "loss": 0.2498, + "step": 14714 + }, + { + "epoch": 4.54, + "learning_rate": 1.8028410310156786e-05, + "loss": 0.2374, + "step": 14715 + }, + { + "epoch": 4.54, + "learning_rate": 1.8028112133053898e-05, + "loss": 0.2586, + "step": 14716 + }, + { + "epoch": 4.55, + "learning_rate": 1.8027813935871236e-05, + "loss": 0.2834, + "step": 14717 + }, + { + "epoch": 4.55, + "learning_rate": 1.8027515718609546e-05, + "loss": 0.2673, + "step": 14718 + }, + { + "epoch": 4.55, + "learning_rate": 1.8027217481269578e-05, + "loss": 0.2488, + "step": 14719 + }, + { + "epoch": 4.55, + "learning_rate": 1.8026919223852072e-05, + "loss": 0.2572, + "step": 14720 + }, + { + "epoch": 4.55, + "learning_rate": 1.8026620946357778e-05, + "loss": 0.265, + "step": 14721 + }, + { + "epoch": 4.55, + "learning_rate": 1.802632264878744e-05, + "loss": 0.2672, + "step": 14722 + }, + { + "epoch": 4.55, + "learning_rate": 1.802602433114181e-05, + "loss": 0.2418, + "step": 14723 + }, + { + "epoch": 4.55, + "learning_rate": 1.8025725993421624e-05, + "loss": 0.2493, + "step": 14724 + }, + { + "epoch": 4.55, + "learning_rate": 1.8025427635627634e-05, + "loss": 0.2806, + "step": 14725 + }, + { + "epoch": 4.55, + "learning_rate": 1.8025129257760587e-05, + "loss": 0.2657, + "step": 14726 + }, + { + "epoch": 4.55, + "learning_rate": 1.802483085982123e-05, + "loss": 0.2457, + "step": 14727 + }, + { + "epoch": 4.55, + "learning_rate": 1.8024532441810306e-05, + "loss": 0.2723, + "step": 14728 + }, + { + "epoch": 4.55, + "learning_rate": 1.802423400372856e-05, + "loss": 0.2719, + "step": 14729 + }, + { + "epoch": 4.55, + "learning_rate": 1.802393554557674e-05, + "loss": 0.2767, + "step": 14730 + }, + { + "epoch": 4.55, + "learning_rate": 1.8023637067355602e-05, + "loss": 0.2786, + "step": 14731 + }, + { + "epoch": 4.55, + "learning_rate": 1.8023338569065877e-05, + "loss": 0.2754, + "step": 14732 + }, + { + "epoch": 4.55, + "learning_rate": 1.802304005070832e-05, + "loss": 0.2679, + "step": 14733 + }, + { + "epoch": 4.55, + "learning_rate": 1.8022741512283678e-05, + "loss": 0.2479, + "step": 14734 + }, + { + "epoch": 4.55, + "learning_rate": 1.8022442953792696e-05, + "loss": 0.2682, + "step": 14735 + }, + { + "epoch": 4.55, + "learning_rate": 1.8022144375236123e-05, + "loss": 0.2839, + "step": 14736 + }, + { + "epoch": 4.55, + "learning_rate": 1.8021845776614698e-05, + "loss": 0.2744, + "step": 14737 + }, + { + "epoch": 4.55, + "learning_rate": 1.8021547157929177e-05, + "loss": 0.2761, + "step": 14738 + }, + { + "epoch": 4.55, + "learning_rate": 1.8021248519180304e-05, + "loss": 0.2569, + "step": 14739 + }, + { + "epoch": 4.55, + "learning_rate": 1.8020949860368827e-05, + "loss": 0.2619, + "step": 14740 + }, + { + "epoch": 4.55, + "learning_rate": 1.802065118149549e-05, + "loss": 0.2834, + "step": 14741 + }, + { + "epoch": 4.55, + "learning_rate": 1.802035248256104e-05, + "loss": 0.272, + "step": 14742 + }, + { + "epoch": 4.55, + "learning_rate": 1.8020053763566228e-05, + "loss": 0.252, + "step": 14743 + }, + { + "epoch": 4.55, + "learning_rate": 1.8019755024511795e-05, + "loss": 0.2603, + "step": 14744 + }, + { + "epoch": 4.55, + "learning_rate": 1.8019456265398498e-05, + "loss": 0.2856, + "step": 14745 + }, + { + "epoch": 4.55, + "learning_rate": 1.8019157486227074e-05, + "loss": 0.2489, + "step": 14746 + }, + { + "epoch": 4.55, + "learning_rate": 1.8018858686998276e-05, + "loss": 0.2729, + "step": 14747 + }, + { + "epoch": 4.55, + "learning_rate": 1.801855986771285e-05, + "loss": 0.2489, + "step": 14748 + }, + { + "epoch": 4.55, + "learning_rate": 1.801826102837154e-05, + "loss": 0.2528, + "step": 14749 + }, + { + "epoch": 4.56, + "learning_rate": 1.80179621689751e-05, + "loss": 0.2618, + "step": 14750 + }, + { + "epoch": 4.56, + "learning_rate": 1.8017663289524275e-05, + "loss": 0.267, + "step": 14751 + }, + { + "epoch": 4.56, + "learning_rate": 1.8017364390019806e-05, + "loss": 0.2527, + "step": 14752 + }, + { + "epoch": 4.56, + "learning_rate": 1.8017065470462453e-05, + "loss": 0.2507, + "step": 14753 + }, + { + "epoch": 4.56, + "learning_rate": 1.8016766530852953e-05, + "loss": 0.265, + "step": 14754 + }, + { + "epoch": 4.56, + "learning_rate": 1.801646757119206e-05, + "loss": 0.2881, + "step": 14755 + }, + { + "epoch": 4.56, + "learning_rate": 1.801616859148052e-05, + "loss": 0.258, + "step": 14756 + }, + { + "epoch": 4.56, + "learning_rate": 1.8015869591719077e-05, + "loss": 0.2612, + "step": 14757 + }, + { + "epoch": 4.56, + "learning_rate": 1.8015570571908486e-05, + "loss": 0.2717, + "step": 14758 + }, + { + "epoch": 4.56, + "learning_rate": 1.801527153204949e-05, + "loss": 0.2699, + "step": 14759 + }, + { + "epoch": 4.56, + "learning_rate": 1.801497247214284e-05, + "loss": 0.2348, + "step": 14760 + }, + { + "epoch": 4.56, + "learning_rate": 1.8014673392189273e-05, + "loss": 0.2633, + "step": 14761 + }, + { + "epoch": 4.56, + "learning_rate": 1.8014374292189555e-05, + "loss": 0.2451, + "step": 14762 + }, + { + "epoch": 4.56, + "learning_rate": 1.8014075172144423e-05, + "loss": 0.2593, + "step": 14763 + }, + { + "epoch": 4.56, + "learning_rate": 1.8013776032054625e-05, + "loss": 0.2575, + "step": 14764 + }, + { + "epoch": 4.56, + "learning_rate": 1.8013476871920917e-05, + "loss": 0.2727, + "step": 14765 + }, + { + "epoch": 4.56, + "learning_rate": 1.8013177691744038e-05, + "loss": 0.2632, + "step": 14766 + }, + { + "epoch": 4.56, + "learning_rate": 1.801287849152474e-05, + "loss": 0.2875, + "step": 14767 + }, + { + "epoch": 4.56, + "learning_rate": 1.8012579271263772e-05, + "loss": 0.2797, + "step": 14768 + }, + { + "epoch": 4.56, + "learning_rate": 1.801228003096188e-05, + "loss": 0.2645, + "step": 14769 + }, + { + "epoch": 4.56, + "learning_rate": 1.8011980770619816e-05, + "loss": 0.281, + "step": 14770 + }, + { + "epoch": 4.56, + "learning_rate": 1.8011681490238327e-05, + "loss": 0.2546, + "step": 14771 + }, + { + "epoch": 4.56, + "learning_rate": 1.801138218981816e-05, + "loss": 0.2779, + "step": 14772 + }, + { + "epoch": 4.56, + "learning_rate": 1.8011082869360067e-05, + "loss": 0.2631, + "step": 14773 + }, + { + "epoch": 4.56, + "learning_rate": 1.801078352886479e-05, + "loss": 0.2573, + "step": 14774 + }, + { + "epoch": 4.56, + "learning_rate": 1.801048416833309e-05, + "loss": 0.2579, + "step": 14775 + }, + { + "epoch": 4.56, + "learning_rate": 1.80101847877657e-05, + "loss": 0.2492, + "step": 14776 + }, + { + "epoch": 4.56, + "learning_rate": 1.8009885387163382e-05, + "loss": 0.279, + "step": 14777 + }, + { + "epoch": 4.56, + "learning_rate": 1.800958596652688e-05, + "loss": 0.2778, + "step": 14778 + }, + { + "epoch": 4.56, + "learning_rate": 1.800928652585694e-05, + "loss": 0.2628, + "step": 14779 + }, + { + "epoch": 4.56, + "learning_rate": 1.8008987065154317e-05, + "loss": 0.2823, + "step": 14780 + }, + { + "epoch": 4.56, + "learning_rate": 1.8008687584419754e-05, + "loss": 0.2657, + "step": 14781 + }, + { + "epoch": 4.57, + "learning_rate": 1.8008388083654003e-05, + "loss": 0.2486, + "step": 14782 + }, + { + "epoch": 4.57, + "learning_rate": 1.8008088562857813e-05, + "loss": 0.2794, + "step": 14783 + }, + { + "epoch": 4.57, + "learning_rate": 1.8007789022031934e-05, + "loss": 0.2699, + "step": 14784 + }, + { + "epoch": 4.57, + "learning_rate": 1.800748946117711e-05, + "loss": 0.2456, + "step": 14785 + }, + { + "epoch": 4.57, + "learning_rate": 1.8007189880294097e-05, + "loss": 0.258, + "step": 14786 + }, + { + "epoch": 4.57, + "learning_rate": 1.8006890279383644e-05, + "loss": 0.2768, + "step": 14787 + }, + { + "epoch": 4.57, + "learning_rate": 1.8006590658446493e-05, + "loss": 0.2585, + "step": 14788 + }, + { + "epoch": 4.57, + "learning_rate": 1.8006291017483403e-05, + "loss": 0.2715, + "step": 14789 + }, + { + "epoch": 4.57, + "learning_rate": 1.800599135649512e-05, + "loss": 0.2474, + "step": 14790 + }, + { + "epoch": 4.57, + "learning_rate": 1.800569167548239e-05, + "loss": 0.2717, + "step": 14791 + }, + { + "epoch": 4.57, + "learning_rate": 1.800539197444596e-05, + "loss": 0.255, + "step": 14792 + }, + { + "epoch": 4.57, + "learning_rate": 1.8005092253386592e-05, + "loss": 0.2708, + "step": 14793 + }, + { + "epoch": 4.57, + "learning_rate": 1.8004792512305024e-05, + "loss": 0.2612, + "step": 14794 + }, + { + "epoch": 4.57, + "learning_rate": 1.8004492751202013e-05, + "loss": 0.2497, + "step": 14795 + }, + { + "epoch": 4.57, + "learning_rate": 1.8004192970078304e-05, + "loss": 0.2563, + "step": 14796 + }, + { + "epoch": 4.57, + "learning_rate": 1.800389316893465e-05, + "loss": 0.2794, + "step": 14797 + }, + { + "epoch": 4.57, + "learning_rate": 1.8003593347771798e-05, + "loss": 0.2676, + "step": 14798 + }, + { + "epoch": 4.57, + "learning_rate": 1.80032935065905e-05, + "loss": 0.2593, + "step": 14799 + }, + { + "epoch": 4.57, + "learning_rate": 1.8002993645391504e-05, + "loss": 0.2711, + "step": 14800 + }, + { + "epoch": 4.57, + "learning_rate": 1.800269376417556e-05, + "loss": 0.2866, + "step": 14801 + }, + { + "epoch": 4.57, + "learning_rate": 1.8002393862943424e-05, + "loss": 0.2606, + "step": 14802 + }, + { + "epoch": 4.57, + "learning_rate": 1.8002093941695837e-05, + "loss": 0.2639, + "step": 14803 + }, + { + "epoch": 4.57, + "learning_rate": 1.8001794000433553e-05, + "loss": 0.2592, + "step": 14804 + }, + { + "epoch": 4.57, + "learning_rate": 1.8001494039157327e-05, + "loss": 0.2736, + "step": 14805 + }, + { + "epoch": 4.57, + "learning_rate": 1.8001194057867902e-05, + "loss": 0.2501, + "step": 14806 + }, + { + "epoch": 4.57, + "learning_rate": 1.8000894056566035e-05, + "loss": 0.2494, + "step": 14807 + }, + { + "epoch": 4.57, + "learning_rate": 1.8000594035252466e-05, + "loss": 0.2747, + "step": 14808 + }, + { + "epoch": 4.57, + "learning_rate": 1.8000293993927958e-05, + "loss": 0.2516, + "step": 14809 + }, + { + "epoch": 4.57, + "learning_rate": 1.7999993932593254e-05, + "loss": 0.2546, + "step": 14810 + }, + { + "epoch": 4.57, + "learning_rate": 1.7999693851249105e-05, + "loss": 0.2851, + "step": 14811 + }, + { + "epoch": 4.57, + "learning_rate": 1.7999393749896263e-05, + "loss": 0.2587, + "step": 14812 + }, + { + "epoch": 4.57, + "learning_rate": 1.799909362853548e-05, + "loss": 0.2433, + "step": 14813 + }, + { + "epoch": 4.57, + "learning_rate": 1.7998793487167502e-05, + "loss": 0.2671, + "step": 14814 + }, + { + "epoch": 4.58, + "learning_rate": 1.799849332579308e-05, + "loss": 0.246, + "step": 14815 + }, + { + "epoch": 4.58, + "learning_rate": 1.7998193144412976e-05, + "loss": 0.2931, + "step": 14816 + }, + { + "epoch": 4.58, + "learning_rate": 1.7997892943027927e-05, + "loss": 0.2633, + "step": 14817 + }, + { + "epoch": 4.58, + "learning_rate": 1.799759272163869e-05, + "loss": 0.2533, + "step": 14818 + }, + { + "epoch": 4.58, + "learning_rate": 1.7997292480246013e-05, + "loss": 0.2646, + "step": 14819 + }, + { + "epoch": 4.58, + "learning_rate": 1.799699221885065e-05, + "loss": 0.2565, + "step": 14820 + }, + { + "epoch": 4.58, + "learning_rate": 1.799669193745335e-05, + "loss": 0.2709, + "step": 14821 + }, + { + "epoch": 4.58, + "learning_rate": 1.799639163605487e-05, + "loss": 0.2604, + "step": 14822 + }, + { + "epoch": 4.58, + "learning_rate": 1.7996091314655952e-05, + "loss": 0.2876, + "step": 14823 + }, + { + "epoch": 4.58, + "learning_rate": 1.799579097325735e-05, + "loss": 0.2698, + "step": 14824 + }, + { + "epoch": 4.58, + "learning_rate": 1.799549061185982e-05, + "loss": 0.2756, + "step": 14825 + }, + { + "epoch": 4.58, + "learning_rate": 1.7995190230464105e-05, + "loss": 0.2603, + "step": 14826 + }, + { + "epoch": 4.58, + "learning_rate": 1.7994889829070966e-05, + "loss": 0.2542, + "step": 14827 + }, + { + "epoch": 4.58, + "learning_rate": 1.7994589407681147e-05, + "loss": 0.2671, + "step": 14828 + }, + { + "epoch": 4.58, + "learning_rate": 1.79942889662954e-05, + "loss": 0.2689, + "step": 14829 + }, + { + "epoch": 4.58, + "learning_rate": 1.799398850491448e-05, + "loss": 0.2396, + "step": 14830 + }, + { + "epoch": 4.58, + "learning_rate": 1.7993688023539138e-05, + "loss": 0.264, + "step": 14831 + }, + { + "epoch": 4.58, + "learning_rate": 1.7993387522170124e-05, + "loss": 0.2757, + "step": 14832 + }, + { + "epoch": 4.58, + "learning_rate": 1.7993087000808188e-05, + "loss": 0.2735, + "step": 14833 + }, + { + "epoch": 4.58, + "learning_rate": 1.7992786459454086e-05, + "loss": 0.2501, + "step": 14834 + }, + { + "epoch": 4.58, + "learning_rate": 1.7992485898108563e-05, + "loss": 0.255, + "step": 14835 + }, + { + "epoch": 4.58, + "learning_rate": 1.7992185316772378e-05, + "loss": 0.2525, + "step": 14836 + }, + { + "epoch": 4.58, + "learning_rate": 1.799188471544628e-05, + "loss": 0.2708, + "step": 14837 + }, + { + "epoch": 4.58, + "learning_rate": 1.799158409413102e-05, + "loss": 0.2747, + "step": 14838 + }, + { + "epoch": 4.58, + "learning_rate": 1.799128345282735e-05, + "loss": 0.2692, + "step": 14839 + }, + { + "epoch": 4.58, + "learning_rate": 1.7990982791536025e-05, + "loss": 0.2463, + "step": 14840 + }, + { + "epoch": 4.58, + "learning_rate": 1.7990682110257792e-05, + "loss": 0.2665, + "step": 14841 + }, + { + "epoch": 4.58, + "learning_rate": 1.7990381408993407e-05, + "loss": 0.2854, + "step": 14842 + }, + { + "epoch": 4.58, + "learning_rate": 1.7990080687743622e-05, + "loss": 0.2786, + "step": 14843 + }, + { + "epoch": 4.58, + "learning_rate": 1.7989779946509185e-05, + "loss": 0.2684, + "step": 14844 + }, + { + "epoch": 4.58, + "learning_rate": 1.7989479185290853e-05, + "loss": 0.2768, + "step": 14845 + }, + { + "epoch": 4.58, + "learning_rate": 1.7989178404089377e-05, + "loss": 0.2649, + "step": 14846 + }, + { + "epoch": 4.59, + "learning_rate": 1.7988877602905506e-05, + "loss": 0.2838, + "step": 14847 + }, + { + "epoch": 4.59, + "learning_rate": 1.7988576781739995e-05, + "loss": 0.2834, + "step": 14848 + }, + { + "epoch": 4.59, + "learning_rate": 1.79882759405936e-05, + "loss": 0.2599, + "step": 14849 + }, + { + "epoch": 4.59, + "learning_rate": 1.798797507946707e-05, + "loss": 0.2507, + "step": 14850 + }, + { + "epoch": 4.59, + "learning_rate": 1.7987674198361153e-05, + "loss": 0.2569, + "step": 14851 + }, + { + "epoch": 4.59, + "learning_rate": 1.798737329727661e-05, + "loss": 0.264, + "step": 14852 + }, + { + "epoch": 4.59, + "learning_rate": 1.7987072376214186e-05, + "loss": 0.2761, + "step": 14853 + }, + { + "epoch": 4.59, + "learning_rate": 1.7986771435174638e-05, + "loss": 0.277, + "step": 14854 + }, + { + "epoch": 4.59, + "learning_rate": 1.7986470474158723e-05, + "loss": 0.2878, + "step": 14855 + }, + { + "epoch": 4.59, + "learning_rate": 1.7986169493167182e-05, + "loss": 0.2779, + "step": 14856 + }, + { + "epoch": 4.59, + "learning_rate": 1.798586849220078e-05, + "loss": 0.2654, + "step": 14857 + }, + { + "epoch": 4.59, + "learning_rate": 1.798556747126026e-05, + "loss": 0.2799, + "step": 14858 + }, + { + "epoch": 4.59, + "learning_rate": 1.798526643034638e-05, + "loss": 0.2466, + "step": 14859 + }, + { + "epoch": 4.59, + "learning_rate": 1.7984965369459894e-05, + "loss": 0.3051, + "step": 14860 + }, + { + "epoch": 4.59, + "learning_rate": 1.798466428860155e-05, + "loss": 0.2807, + "step": 14861 + }, + { + "epoch": 4.59, + "learning_rate": 1.7984363187772106e-05, + "loss": 0.2464, + "step": 14862 + }, + { + "epoch": 4.59, + "learning_rate": 1.7984062066972316e-05, + "loss": 0.2738, + "step": 14863 + }, + { + "epoch": 4.59, + "learning_rate": 1.7983760926202928e-05, + "loss": 0.2642, + "step": 14864 + }, + { + "epoch": 4.59, + "learning_rate": 1.79834597654647e-05, + "loss": 0.2603, + "step": 14865 + }, + { + "epoch": 4.59, + "learning_rate": 1.798315858475838e-05, + "loss": 0.2723, + "step": 14866 + }, + { + "epoch": 4.59, + "learning_rate": 1.7982857384084728e-05, + "loss": 0.2865, + "step": 14867 + }, + { + "epoch": 4.59, + "learning_rate": 1.798255616344449e-05, + "loss": 0.2541, + "step": 14868 + }, + { + "epoch": 4.59, + "learning_rate": 1.7982254922838425e-05, + "loss": 0.2587, + "step": 14869 + }, + { + "epoch": 4.59, + "learning_rate": 1.7981953662267285e-05, + "loss": 0.2546, + "step": 14870 + }, + { + "epoch": 4.59, + "learning_rate": 1.798165238173182e-05, + "loss": 0.2744, + "step": 14871 + }, + { + "epoch": 4.59, + "learning_rate": 1.798135108123279e-05, + "loss": 0.2606, + "step": 14872 + }, + { + "epoch": 4.59, + "learning_rate": 1.7981049760770943e-05, + "loss": 0.2673, + "step": 14873 + }, + { + "epoch": 4.59, + "learning_rate": 1.7980748420347036e-05, + "loss": 0.2659, + "step": 14874 + }, + { + "epoch": 4.59, + "learning_rate": 1.798044705996182e-05, + "loss": 0.2845, + "step": 14875 + }, + { + "epoch": 4.59, + "learning_rate": 1.7980145679616056e-05, + "loss": 0.2591, + "step": 14876 + }, + { + "epoch": 4.59, + "learning_rate": 1.7979844279310487e-05, + "loss": 0.2396, + "step": 14877 + }, + { + "epoch": 4.59, + "learning_rate": 1.7979542859045875e-05, + "loss": 0.2572, + "step": 14878 + }, + { + "epoch": 4.6, + "learning_rate": 1.7979241418822967e-05, + "loss": 0.2853, + "step": 14879 + }, + { + "epoch": 4.6, + "learning_rate": 1.7978939958642523e-05, + "loss": 0.2782, + "step": 14880 + }, + { + "epoch": 4.6, + "learning_rate": 1.7978638478505295e-05, + "loss": 0.268, + "step": 14881 + }, + { + "epoch": 4.6, + "learning_rate": 1.7978336978412035e-05, + "loss": 0.2496, + "step": 14882 + }, + { + "epoch": 4.6, + "learning_rate": 1.79780354583635e-05, + "loss": 0.2651, + "step": 14883 + }, + { + "epoch": 4.6, + "learning_rate": 1.7977733918360446e-05, + "loss": 0.27, + "step": 14884 + }, + { + "epoch": 4.6, + "learning_rate": 1.7977432358403624e-05, + "loss": 0.2585, + "step": 14885 + }, + { + "epoch": 4.6, + "learning_rate": 1.7977130778493785e-05, + "loss": 0.2726, + "step": 14886 + }, + { + "epoch": 4.6, + "learning_rate": 1.797682917863169e-05, + "loss": 0.2582, + "step": 14887 + }, + { + "epoch": 4.6, + "learning_rate": 1.797652755881809e-05, + "loss": 0.2634, + "step": 14888 + }, + { + "epoch": 4.6, + "learning_rate": 1.7976225919053737e-05, + "loss": 0.2584, + "step": 14889 + }, + { + "epoch": 4.6, + "learning_rate": 1.7975924259339392e-05, + "loss": 0.2637, + "step": 14890 + }, + { + "epoch": 4.6, + "learning_rate": 1.7975622579675805e-05, + "loss": 0.2688, + "step": 14891 + }, + { + "epoch": 4.6, + "learning_rate": 1.797532088006373e-05, + "loss": 0.2526, + "step": 14892 + }, + { + "epoch": 4.6, + "learning_rate": 1.7975019160503923e-05, + "loss": 0.2602, + "step": 14893 + }, + { + "epoch": 4.6, + "learning_rate": 1.7974717420997143e-05, + "loss": 0.2513, + "step": 14894 + }, + { + "epoch": 4.6, + "learning_rate": 1.7974415661544132e-05, + "loss": 0.2861, + "step": 14895 + }, + { + "epoch": 4.6, + "learning_rate": 1.7974113882145658e-05, + "loss": 0.2692, + "step": 14896 + }, + { + "epoch": 4.6, + "learning_rate": 1.797381208280247e-05, + "loss": 0.2621, + "step": 14897 + }, + { + "epoch": 4.6, + "learning_rate": 1.7973510263515322e-05, + "loss": 0.2848, + "step": 14898 + }, + { + "epoch": 4.6, + "learning_rate": 1.7973208424284974e-05, + "loss": 0.2747, + "step": 14899 + }, + { + "epoch": 4.6, + "learning_rate": 1.7972906565112175e-05, + "loss": 0.2659, + "step": 14900 + }, + { + "epoch": 4.6, + "learning_rate": 1.797260468599768e-05, + "loss": 0.2702, + "step": 14901 + }, + { + "epoch": 4.6, + "learning_rate": 1.7972302786942254e-05, + "loss": 0.2834, + "step": 14902 + }, + { + "epoch": 4.6, + "learning_rate": 1.7972000867946638e-05, + "loss": 0.2508, + "step": 14903 + }, + { + "epoch": 4.6, + "learning_rate": 1.7971698929011595e-05, + "loss": 0.281, + "step": 14904 + }, + { + "epoch": 4.6, + "learning_rate": 1.797139697013788e-05, + "loss": 0.2671, + "step": 14905 + }, + { + "epoch": 4.6, + "learning_rate": 1.797109499132625e-05, + "loss": 0.2652, + "step": 14906 + }, + { + "epoch": 4.6, + "learning_rate": 1.7970792992577455e-05, + "loss": 0.2509, + "step": 14907 + }, + { + "epoch": 4.6, + "learning_rate": 1.797049097389225e-05, + "loss": 0.2775, + "step": 14908 + }, + { + "epoch": 4.6, + "learning_rate": 1.79701889352714e-05, + "loss": 0.2594, + "step": 14909 + }, + { + "epoch": 4.6, + "learning_rate": 1.796988687671565e-05, + "loss": 0.263, + "step": 14910 + }, + { + "epoch": 4.6, + "learning_rate": 1.7969584798225758e-05, + "loss": 0.2752, + "step": 14911 + }, + { + "epoch": 4.61, + "learning_rate": 1.7969282699802485e-05, + "loss": 0.2579, + "step": 14912 + }, + { + "epoch": 4.61, + "learning_rate": 1.796898058144658e-05, + "loss": 0.2862, + "step": 14913 + }, + { + "epoch": 4.61, + "learning_rate": 1.7968678443158798e-05, + "loss": 0.2648, + "step": 14914 + }, + { + "epoch": 4.61, + "learning_rate": 1.79683762849399e-05, + "loss": 0.2578, + "step": 14915 + }, + { + "epoch": 4.61, + "learning_rate": 1.796807410679064e-05, + "loss": 0.2973, + "step": 14916 + }, + { + "epoch": 4.61, + "learning_rate": 1.7967771908711774e-05, + "loss": 0.2471, + "step": 14917 + }, + { + "epoch": 4.61, + "learning_rate": 1.7967469690704057e-05, + "loss": 0.2553, + "step": 14918 + }, + { + "epoch": 4.61, + "learning_rate": 1.7967167452768248e-05, + "loss": 0.2587, + "step": 14919 + }, + { + "epoch": 4.61, + "learning_rate": 1.7966865194905097e-05, + "loss": 0.2414, + "step": 14920 + }, + { + "epoch": 4.61, + "learning_rate": 1.796656291711536e-05, + "loss": 0.2865, + "step": 14921 + }, + { + "epoch": 4.61, + "learning_rate": 1.7966260619399804e-05, + "loss": 0.2686, + "step": 14922 + }, + { + "epoch": 4.61, + "learning_rate": 1.796595830175917e-05, + "loss": 0.2923, + "step": 14923 + }, + { + "epoch": 4.61, + "learning_rate": 1.7965655964194223e-05, + "loss": 0.2646, + "step": 14924 + }, + { + "epoch": 4.61, + "learning_rate": 1.7965353606705716e-05, + "loss": 0.2443, + "step": 14925 + }, + { + "epoch": 4.61, + "learning_rate": 1.7965051229294412e-05, + "loss": 0.2692, + "step": 14926 + }, + { + "epoch": 4.61, + "learning_rate": 1.7964748831961062e-05, + "loss": 0.2512, + "step": 14927 + }, + { + "epoch": 4.61, + "learning_rate": 1.796444641470642e-05, + "loss": 0.2498, + "step": 14928 + }, + { + "epoch": 4.61, + "learning_rate": 1.796414397753124e-05, + "loss": 0.2827, + "step": 14929 + }, + { + "epoch": 4.61, + "learning_rate": 1.7963841520436292e-05, + "loss": 0.2904, + "step": 14930 + }, + { + "epoch": 4.61, + "learning_rate": 1.796353904342232e-05, + "loss": 0.2641, + "step": 14931 + }, + { + "epoch": 4.61, + "learning_rate": 1.7963236546490082e-05, + "loss": 0.2634, + "step": 14932 + }, + { + "epoch": 4.61, + "learning_rate": 1.7962934029640343e-05, + "loss": 0.2511, + "step": 14933 + }, + { + "epoch": 4.61, + "learning_rate": 1.7962631492873847e-05, + "loss": 0.2535, + "step": 14934 + }, + { + "epoch": 4.61, + "learning_rate": 1.796232893619136e-05, + "loss": 0.2609, + "step": 14935 + }, + { + "epoch": 4.61, + "learning_rate": 1.7962026359593638e-05, + "loss": 0.2539, + "step": 14936 + }, + { + "epoch": 4.61, + "learning_rate": 1.7961723763081432e-05, + "loss": 0.2717, + "step": 14937 + }, + { + "epoch": 4.61, + "learning_rate": 1.7961421146655506e-05, + "loss": 0.2648, + "step": 14938 + }, + { + "epoch": 4.61, + "learning_rate": 1.7961118510316614e-05, + "loss": 0.2581, + "step": 14939 + }, + { + "epoch": 4.61, + "learning_rate": 1.7960815854065513e-05, + "loss": 0.267, + "step": 14940 + }, + { + "epoch": 4.61, + "learning_rate": 1.7960513177902958e-05, + "loss": 0.2563, + "step": 14941 + }, + { + "epoch": 4.61, + "learning_rate": 1.7960210481829707e-05, + "loss": 0.2619, + "step": 14942 + }, + { + "epoch": 4.61, + "learning_rate": 1.795990776584652e-05, + "loss": 0.2611, + "step": 14943 + }, + { + "epoch": 4.62, + "learning_rate": 1.7959605029954148e-05, + "loss": 0.2669, + "step": 14944 + }, + { + "epoch": 4.62, + "learning_rate": 1.7959302274153355e-05, + "loss": 0.2417, + "step": 14945 + }, + { + "epoch": 4.62, + "learning_rate": 1.7958999498444892e-05, + "loss": 0.2549, + "step": 14946 + }, + { + "epoch": 4.62, + "learning_rate": 1.7958696702829525e-05, + "loss": 0.2548, + "step": 14947 + }, + { + "epoch": 4.62, + "learning_rate": 1.7958393887308e-05, + "loss": 0.2639, + "step": 14948 + }, + { + "epoch": 4.62, + "learning_rate": 1.7958091051881085e-05, + "loss": 0.2628, + "step": 14949 + }, + { + "epoch": 4.62, + "learning_rate": 1.7957788196549533e-05, + "loss": 0.2744, + "step": 14950 + }, + { + "epoch": 4.62, + "learning_rate": 1.79574853213141e-05, + "loss": 0.2651, + "step": 14951 + }, + { + "epoch": 4.62, + "learning_rate": 1.7957182426175543e-05, + "loss": 0.2883, + "step": 14952 + }, + { + "epoch": 4.62, + "learning_rate": 1.7956879511134626e-05, + "loss": 0.2755, + "step": 14953 + }, + { + "epoch": 4.62, + "learning_rate": 1.7956576576192097e-05, + "loss": 0.2598, + "step": 14954 + }, + { + "epoch": 4.62, + "learning_rate": 1.7956273621348722e-05, + "loss": 0.2632, + "step": 14955 + }, + { + "epoch": 4.62, + "learning_rate": 1.7955970646605253e-05, + "loss": 0.2508, + "step": 14956 + }, + { + "epoch": 4.62, + "learning_rate": 1.7955667651962453e-05, + "loss": 0.2881, + "step": 14957 + }, + { + "epoch": 4.62, + "learning_rate": 1.7955364637421074e-05, + "loss": 0.2696, + "step": 14958 + }, + { + "epoch": 4.62, + "learning_rate": 1.7955061602981878e-05, + "loss": 0.2701, + "step": 14959 + }, + { + "epoch": 4.62, + "learning_rate": 1.7954758548645627e-05, + "loss": 0.2631, + "step": 14960 + }, + { + "epoch": 4.62, + "learning_rate": 1.795445547441307e-05, + "loss": 0.2767, + "step": 14961 + }, + { + "epoch": 4.62, + "learning_rate": 1.795415238028497e-05, + "loss": 0.2847, + "step": 14962 + }, + { + "epoch": 4.62, + "learning_rate": 1.795384926626208e-05, + "loss": 0.2721, + "step": 14963 + }, + { + "epoch": 4.62, + "learning_rate": 1.7953546132345167e-05, + "loss": 0.2735, + "step": 14964 + }, + { + "epoch": 4.62, + "learning_rate": 1.7953242978534983e-05, + "loss": 0.2722, + "step": 14965 + }, + { + "epoch": 4.62, + "learning_rate": 1.7952939804832284e-05, + "loss": 0.2703, + "step": 14966 + }, + { + "epoch": 4.62, + "learning_rate": 1.795263661123784e-05, + "loss": 0.2608, + "step": 14967 + }, + { + "epoch": 4.62, + "learning_rate": 1.7952333397752396e-05, + "loss": 0.2406, + "step": 14968 + }, + { + "epoch": 4.62, + "learning_rate": 1.7952030164376717e-05, + "loss": 0.2582, + "step": 14969 + }, + { + "epoch": 4.62, + "learning_rate": 1.795172691111156e-05, + "loss": 0.2877, + "step": 14970 + }, + { + "epoch": 4.62, + "learning_rate": 1.7951423637957686e-05, + "loss": 0.2951, + "step": 14971 + }, + { + "epoch": 4.62, + "learning_rate": 1.7951120344915848e-05, + "loss": 0.2781, + "step": 14972 + }, + { + "epoch": 4.62, + "learning_rate": 1.7950817031986808e-05, + "loss": 0.2434, + "step": 14973 + }, + { + "epoch": 4.62, + "learning_rate": 1.7950513699171324e-05, + "loss": 0.2569, + "step": 14974 + }, + { + "epoch": 4.62, + "learning_rate": 1.7950210346470157e-05, + "loss": 0.2367, + "step": 14975 + }, + { + "epoch": 4.62, + "learning_rate": 1.7949906973884065e-05, + "loss": 0.2535, + "step": 14976 + }, + { + "epoch": 4.63, + "learning_rate": 1.7949603581413803e-05, + "loss": 0.2714, + "step": 14977 + }, + { + "epoch": 4.63, + "learning_rate": 1.7949300169060134e-05, + "loss": 0.2587, + "step": 14978 + }, + { + "epoch": 4.63, + "learning_rate": 1.7948996736823816e-05, + "loss": 0.2477, + "step": 14979 + }, + { + "epoch": 4.63, + "learning_rate": 1.7948693284705606e-05, + "loss": 0.2452, + "step": 14980 + }, + { + "epoch": 4.63, + "learning_rate": 1.7948389812706265e-05, + "loss": 0.2581, + "step": 14981 + }, + { + "epoch": 4.63, + "learning_rate": 1.794808632082655e-05, + "loss": 0.2851, + "step": 14982 + }, + { + "epoch": 4.63, + "learning_rate": 1.794778280906722e-05, + "loss": 0.2697, + "step": 14983 + }, + { + "epoch": 4.63, + "learning_rate": 1.794747927742904e-05, + "loss": 0.2789, + "step": 14984 + }, + { + "epoch": 4.63, + "learning_rate": 1.7947175725912763e-05, + "loss": 0.2679, + "step": 14985 + }, + { + "epoch": 4.63, + "learning_rate": 1.794687215451915e-05, + "loss": 0.2521, + "step": 14986 + }, + { + "epoch": 4.63, + "learning_rate": 1.794656856324896e-05, + "loss": 0.2421, + "step": 14987 + }, + { + "epoch": 4.63, + "learning_rate": 1.7946264952102956e-05, + "loss": 0.2637, + "step": 14988 + }, + { + "epoch": 4.63, + "learning_rate": 1.794596132108189e-05, + "loss": 0.2467, + "step": 14989 + }, + { + "epoch": 4.63, + "learning_rate": 1.7945657670186528e-05, + "loss": 0.2637, + "step": 14990 + }, + { + "epoch": 4.63, + "learning_rate": 1.7945353999417624e-05, + "loss": 0.2696, + "step": 14991 + }, + { + "epoch": 4.63, + "learning_rate": 1.794505030877594e-05, + "loss": 0.2513, + "step": 14992 + }, + { + "epoch": 4.63, + "learning_rate": 1.794474659826224e-05, + "loss": 0.2695, + "step": 14993 + }, + { + "epoch": 4.63, + "learning_rate": 1.7944442867877278e-05, + "loss": 0.2736, + "step": 14994 + }, + { + "epoch": 4.63, + "learning_rate": 1.7944139117621814e-05, + "loss": 0.2881, + "step": 14995 + }, + { + "epoch": 4.63, + "learning_rate": 1.794383534749661e-05, + "loss": 0.2825, + "step": 14996 + }, + { + "epoch": 4.63, + "learning_rate": 1.7943531557502425e-05, + "loss": 0.2779, + "step": 14997 + }, + { + "epoch": 4.63, + "learning_rate": 1.7943227747640023e-05, + "loss": 0.2485, + "step": 14998 + }, + { + "epoch": 4.63, + "learning_rate": 1.7942923917910154e-05, + "loss": 0.2468, + "step": 14999 + }, + { + "epoch": 4.63, + "learning_rate": 1.7942620068313585e-05, + "loss": 0.2656, + "step": 15000 + }, + { + "epoch": 4.63, + "learning_rate": 1.7942316198851074e-05, + "loss": 0.2591, + "step": 15001 + }, + { + "epoch": 4.63, + "learning_rate": 1.7942012309523384e-05, + "loss": 0.2423, + "step": 15002 + }, + { + "epoch": 4.63, + "learning_rate": 1.794170840033127e-05, + "loss": 0.2605, + "step": 15003 + }, + { + "epoch": 4.63, + "learning_rate": 1.7941404471275493e-05, + "loss": 0.2732, + "step": 15004 + }, + { + "epoch": 4.63, + "learning_rate": 1.794110052235682e-05, + "loss": 0.2764, + "step": 15005 + }, + { + "epoch": 4.63, + "learning_rate": 1.7940796553576006e-05, + "loss": 0.2535, + "step": 15006 + }, + { + "epoch": 4.63, + "learning_rate": 1.7940492564933808e-05, + "loss": 0.2595, + "step": 15007 + }, + { + "epoch": 4.63, + "learning_rate": 1.7940188556430992e-05, + "loss": 0.2781, + "step": 15008 + }, + { + "epoch": 4.64, + "learning_rate": 1.7939884528068315e-05, + "loss": 0.2684, + "step": 15009 + }, + { + "epoch": 4.64, + "learning_rate": 1.7939580479846542e-05, + "loss": 0.2439, + "step": 15010 + }, + { + "epoch": 4.64, + "learning_rate": 1.7939276411766426e-05, + "loss": 0.2486, + "step": 15011 + }, + { + "epoch": 4.64, + "learning_rate": 1.7938972323828735e-05, + "loss": 0.2594, + "step": 15012 + }, + { + "epoch": 4.64, + "learning_rate": 1.7938668216034222e-05, + "loss": 0.2771, + "step": 15013 + }, + { + "epoch": 4.64, + "learning_rate": 1.7938364088383652e-05, + "loss": 0.2855, + "step": 15014 + }, + { + "epoch": 4.64, + "learning_rate": 1.7938059940877792e-05, + "loss": 0.2587, + "step": 15015 + }, + { + "epoch": 4.64, + "learning_rate": 1.7937755773517392e-05, + "loss": 0.2549, + "step": 15016 + }, + { + "epoch": 4.64, + "learning_rate": 1.7937451586303218e-05, + "loss": 0.2935, + "step": 15017 + }, + { + "epoch": 4.64, + "learning_rate": 1.7937147379236027e-05, + "loss": 0.2844, + "step": 15018 + }, + { + "epoch": 4.64, + "learning_rate": 1.7936843152316587e-05, + "loss": 0.2611, + "step": 15019 + }, + { + "epoch": 4.64, + "learning_rate": 1.7936538905545652e-05, + "loss": 0.2557, + "step": 15020 + }, + { + "epoch": 4.64, + "learning_rate": 1.7936234638923985e-05, + "loss": 0.242, + "step": 15021 + }, + { + "epoch": 4.64, + "learning_rate": 1.7935930352452348e-05, + "loss": 0.2615, + "step": 15022 + }, + { + "epoch": 4.64, + "learning_rate": 1.79356260461315e-05, + "loss": 0.2542, + "step": 15023 + }, + { + "epoch": 4.64, + "learning_rate": 1.7935321719962208e-05, + "loss": 0.2611, + "step": 15024 + }, + { + "epoch": 4.64, + "learning_rate": 1.793501737394523e-05, + "loss": 0.2565, + "step": 15025 + }, + { + "epoch": 4.64, + "learning_rate": 1.7934713008081323e-05, + "loss": 0.2375, + "step": 15026 + }, + { + "epoch": 4.64, + "learning_rate": 1.7934408622371252e-05, + "loss": 0.2652, + "step": 15027 + }, + { + "epoch": 4.64, + "learning_rate": 1.7934104216815778e-05, + "loss": 0.2676, + "step": 15028 + }, + { + "epoch": 4.64, + "learning_rate": 1.7933799791415664e-05, + "loss": 0.25, + "step": 15029 + }, + { + "epoch": 4.64, + "learning_rate": 1.793349534617167e-05, + "loss": 0.2667, + "step": 15030 + }, + { + "epoch": 4.64, + "learning_rate": 1.793319088108455e-05, + "loss": 0.2599, + "step": 15031 + }, + { + "epoch": 4.64, + "learning_rate": 1.7932886396155084e-05, + "loss": 0.2638, + "step": 15032 + }, + { + "epoch": 4.64, + "learning_rate": 1.7932581891384012e-05, + "loss": 0.261, + "step": 15033 + }, + { + "epoch": 4.64, + "learning_rate": 1.7932277366772112e-05, + "loss": 0.2685, + "step": 15034 + }, + { + "epoch": 4.64, + "learning_rate": 1.7931972822320135e-05, + "loss": 0.2802, + "step": 15035 + }, + { + "epoch": 4.64, + "learning_rate": 1.793166825802885e-05, + "loss": 0.2852, + "step": 15036 + }, + { + "epoch": 4.64, + "learning_rate": 1.7931363673899018e-05, + "loss": 0.2604, + "step": 15037 + }, + { + "epoch": 4.64, + "learning_rate": 1.79310590699314e-05, + "loss": 0.2559, + "step": 15038 + }, + { + "epoch": 4.64, + "learning_rate": 1.7930754446126753e-05, + "loss": 0.2577, + "step": 15039 + }, + { + "epoch": 4.64, + "learning_rate": 1.7930449802485842e-05, + "loss": 0.2752, + "step": 15040 + }, + { + "epoch": 4.65, + "learning_rate": 1.7930145139009433e-05, + "loss": 0.2648, + "step": 15041 + }, + { + "epoch": 4.65, + "learning_rate": 1.7929840455698283e-05, + "loss": 0.2611, + "step": 15042 + }, + { + "epoch": 4.65, + "learning_rate": 1.792953575255315e-05, + "loss": 0.243, + "step": 15043 + }, + { + "epoch": 4.65, + "learning_rate": 1.792923102957481e-05, + "loss": 0.271, + "step": 15044 + }, + { + "epoch": 4.65, + "learning_rate": 1.7928926286764016e-05, + "loss": 0.2581, + "step": 15045 + }, + { + "epoch": 4.65, + "learning_rate": 1.792862152412153e-05, + "loss": 0.2496, + "step": 15046 + }, + { + "epoch": 4.65, + "learning_rate": 1.7928316741648113e-05, + "loss": 0.2661, + "step": 15047 + }, + { + "epoch": 4.65, + "learning_rate": 1.792801193934453e-05, + "loss": 0.2835, + "step": 15048 + }, + { + "epoch": 4.65, + "learning_rate": 1.7927707117211545e-05, + "loss": 0.2616, + "step": 15049 + }, + { + "epoch": 4.65, + "learning_rate": 1.792740227524992e-05, + "loss": 0.2731, + "step": 15050 + }, + { + "epoch": 4.65, + "learning_rate": 1.7927097413460415e-05, + "loss": 0.2624, + "step": 15051 + }, + { + "epoch": 4.65, + "learning_rate": 1.7926792531843792e-05, + "loss": 0.2736, + "step": 15052 + }, + { + "epoch": 4.65, + "learning_rate": 1.7926487630400815e-05, + "loss": 0.2705, + "step": 15053 + }, + { + "epoch": 4.65, + "learning_rate": 1.792618270913225e-05, + "loss": 0.252, + "step": 15054 + }, + { + "epoch": 4.65, + "learning_rate": 1.7925877768038852e-05, + "loss": 0.2484, + "step": 15055 + }, + { + "epoch": 4.65, + "learning_rate": 1.792557280712139e-05, + "loss": 0.2558, + "step": 15056 + }, + { + "epoch": 4.65, + "learning_rate": 1.7925267826380626e-05, + "loss": 0.2541, + "step": 15057 + }, + { + "epoch": 4.65, + "learning_rate": 1.792496282581732e-05, + "loss": 0.2809, + "step": 15058 + }, + { + "epoch": 4.65, + "learning_rate": 1.792465780543224e-05, + "loss": 0.2683, + "step": 15059 + }, + { + "epoch": 4.65, + "learning_rate": 1.7924352765226142e-05, + "loss": 0.2612, + "step": 15060 + }, + { + "epoch": 4.65, + "learning_rate": 1.7924047705199793e-05, + "loss": 0.2719, + "step": 15061 + }, + { + "epoch": 4.65, + "learning_rate": 1.7923742625353956e-05, + "loss": 0.2682, + "step": 15062 + }, + { + "epoch": 4.65, + "learning_rate": 1.7923437525689392e-05, + "loss": 0.2903, + "step": 15063 + }, + { + "epoch": 4.65, + "learning_rate": 1.7923132406206866e-05, + "loss": 0.2705, + "step": 15064 + }, + { + "epoch": 4.65, + "learning_rate": 1.7922827266907144e-05, + "loss": 0.259, + "step": 15065 + }, + { + "epoch": 4.65, + "learning_rate": 1.7922522107790984e-05, + "loss": 0.266, + "step": 15066 + }, + { + "epoch": 4.65, + "learning_rate": 1.7922216928859152e-05, + "loss": 0.2682, + "step": 15067 + }, + { + "epoch": 4.65, + "learning_rate": 1.7921911730112407e-05, + "loss": 0.2673, + "step": 15068 + }, + { + "epoch": 4.65, + "learning_rate": 1.7921606511551516e-05, + "loss": 0.2353, + "step": 15069 + }, + { + "epoch": 4.65, + "learning_rate": 1.7921301273177246e-05, + "loss": 0.256, + "step": 15070 + }, + { + "epoch": 4.65, + "learning_rate": 1.7920996014990354e-05, + "loss": 0.2645, + "step": 15071 + }, + { + "epoch": 4.65, + "learning_rate": 1.792069073699161e-05, + "loss": 0.2501, + "step": 15072 + }, + { + "epoch": 4.65, + "learning_rate": 1.792038543918177e-05, + "loss": 0.2698, + "step": 15073 + }, + { + "epoch": 4.66, + "learning_rate": 1.79200801215616e-05, + "loss": 0.2596, + "step": 15074 + }, + { + "epoch": 4.66, + "learning_rate": 1.791977478413187e-05, + "loss": 0.2676, + "step": 15075 + }, + { + "epoch": 4.66, + "learning_rate": 1.7919469426893335e-05, + "loss": 0.2405, + "step": 15076 + }, + { + "epoch": 4.66, + "learning_rate": 1.7919164049846765e-05, + "loss": 0.275, + "step": 15077 + }, + { + "epoch": 4.66, + "learning_rate": 1.7918858652992923e-05, + "loss": 0.2391, + "step": 15078 + }, + { + "epoch": 4.66, + "learning_rate": 1.7918553236332566e-05, + "loss": 0.2437, + "step": 15079 + }, + { + "epoch": 4.66, + "learning_rate": 1.791824779986647e-05, + "loss": 0.2852, + "step": 15080 + }, + { + "epoch": 4.66, + "learning_rate": 1.7917942343595386e-05, + "loss": 0.2399, + "step": 15081 + }, + { + "epoch": 4.66, + "learning_rate": 1.7917636867520087e-05, + "loss": 0.2621, + "step": 15082 + }, + { + "epoch": 4.66, + "learning_rate": 1.7917331371641333e-05, + "loss": 0.2586, + "step": 15083 + }, + { + "epoch": 4.66, + "learning_rate": 1.791702585595989e-05, + "loss": 0.2856, + "step": 15084 + }, + { + "epoch": 4.66, + "learning_rate": 1.791672032047652e-05, + "loss": 0.259, + "step": 15085 + }, + { + "epoch": 4.66, + "learning_rate": 1.791641476519199e-05, + "loss": 0.2682, + "step": 15086 + }, + { + "epoch": 4.66, + "learning_rate": 1.7916109190107062e-05, + "loss": 0.2721, + "step": 15087 + }, + { + "epoch": 4.66, + "learning_rate": 1.79158035952225e-05, + "loss": 0.2602, + "step": 15088 + }, + { + "epoch": 4.66, + "learning_rate": 1.7915497980539072e-05, + "loss": 0.2642, + "step": 15089 + }, + { + "epoch": 4.66, + "learning_rate": 1.7915192346057536e-05, + "loss": 0.2686, + "step": 15090 + }, + { + "epoch": 4.66, + "learning_rate": 1.7914886691778664e-05, + "loss": 0.2429, + "step": 15091 + }, + { + "epoch": 4.66, + "learning_rate": 1.7914581017703217e-05, + "loss": 0.2533, + "step": 15092 + }, + { + "epoch": 4.66, + "learning_rate": 1.7914275323831955e-05, + "loss": 0.2615, + "step": 15093 + }, + { + "epoch": 4.66, + "learning_rate": 1.7913969610165652e-05, + "loss": 0.2554, + "step": 15094 + }, + { + "epoch": 4.66, + "learning_rate": 1.7913663876705067e-05, + "loss": 0.259, + "step": 15095 + }, + { + "epoch": 4.66, + "learning_rate": 1.7913358123450965e-05, + "loss": 0.2529, + "step": 15096 + }, + { + "epoch": 4.66, + "learning_rate": 1.7913052350404108e-05, + "loss": 0.2275, + "step": 15097 + }, + { + "epoch": 4.66, + "learning_rate": 1.7912746557565263e-05, + "loss": 0.2616, + "step": 15098 + }, + { + "epoch": 4.66, + "learning_rate": 1.7912440744935198e-05, + "loss": 0.2884, + "step": 15099 + }, + { + "epoch": 4.66, + "learning_rate": 1.7912134912514676e-05, + "loss": 0.2594, + "step": 15100 + }, + { + "epoch": 4.66, + "learning_rate": 1.7911829060304463e-05, + "loss": 0.2804, + "step": 15101 + }, + { + "epoch": 4.66, + "learning_rate": 1.7911523188305323e-05, + "loss": 0.2772, + "step": 15102 + }, + { + "epoch": 4.66, + "learning_rate": 1.7911217296518014e-05, + "loss": 0.275, + "step": 15103 + }, + { + "epoch": 4.66, + "learning_rate": 1.7910911384943313e-05, + "loss": 0.2616, + "step": 15104 + }, + { + "epoch": 4.66, + "learning_rate": 1.791060545358198e-05, + "loss": 0.2642, + "step": 15105 + }, + { + "epoch": 4.67, + "learning_rate": 1.7910299502434778e-05, + "loss": 0.2616, + "step": 15106 + }, + { + "epoch": 4.67, + "learning_rate": 1.7909993531502475e-05, + "loss": 0.2492, + "step": 15107 + }, + { + "epoch": 4.67, + "learning_rate": 1.7909687540785837e-05, + "loss": 0.2565, + "step": 15108 + }, + { + "epoch": 4.67, + "learning_rate": 1.7909381530285627e-05, + "loss": 0.2757, + "step": 15109 + }, + { + "epoch": 4.67, + "learning_rate": 1.790907550000261e-05, + "loss": 0.2696, + "step": 15110 + }, + { + "epoch": 4.67, + "learning_rate": 1.7908769449937555e-05, + "loss": 0.2469, + "step": 15111 + }, + { + "epoch": 4.67, + "learning_rate": 1.7908463380091217e-05, + "loss": 0.2464, + "step": 15112 + }, + { + "epoch": 4.67, + "learning_rate": 1.7908157290464377e-05, + "loss": 0.2525, + "step": 15113 + }, + { + "epoch": 4.67, + "learning_rate": 1.7907851181057793e-05, + "loss": 0.2648, + "step": 15114 + }, + { + "epoch": 4.67, + "learning_rate": 1.790754505187223e-05, + "loss": 0.2498, + "step": 15115 + }, + { + "epoch": 4.67, + "learning_rate": 1.7907238902908456e-05, + "loss": 0.282, + "step": 15116 + }, + { + "epoch": 4.67, + "learning_rate": 1.7906932734167234e-05, + "loss": 0.26, + "step": 15117 + }, + { + "epoch": 4.67, + "learning_rate": 1.7906626545649328e-05, + "loss": 0.2648, + "step": 15118 + }, + { + "epoch": 4.67, + "learning_rate": 1.7906320337355513e-05, + "loss": 0.2611, + "step": 15119 + }, + { + "epoch": 4.67, + "learning_rate": 1.7906014109286545e-05, + "loss": 0.2645, + "step": 15120 + }, + { + "epoch": 4.67, + "learning_rate": 1.7905707861443193e-05, + "loss": 0.2595, + "step": 15121 + }, + { + "epoch": 4.67, + "learning_rate": 1.7905401593826226e-05, + "loss": 0.2538, + "step": 15122 + }, + { + "epoch": 4.67, + "learning_rate": 1.7905095306436407e-05, + "loss": 0.2638, + "step": 15123 + }, + { + "epoch": 4.67, + "learning_rate": 1.7904788999274504e-05, + "loss": 0.271, + "step": 15124 + }, + { + "epoch": 4.67, + "learning_rate": 1.790448267234128e-05, + "loss": 0.2732, + "step": 15125 + }, + { + "epoch": 4.67, + "learning_rate": 1.7904176325637505e-05, + "loss": 0.2816, + "step": 15126 + }, + { + "epoch": 4.67, + "learning_rate": 1.790386995916394e-05, + "loss": 0.2797, + "step": 15127 + }, + { + "epoch": 4.67, + "learning_rate": 1.7903563572921357e-05, + "loss": 0.2674, + "step": 15128 + }, + { + "epoch": 4.67, + "learning_rate": 1.7903257166910523e-05, + "loss": 0.2584, + "step": 15129 + }, + { + "epoch": 4.67, + "learning_rate": 1.7902950741132197e-05, + "loss": 0.2635, + "step": 15130 + }, + { + "epoch": 4.67, + "learning_rate": 1.790264429558715e-05, + "loss": 0.2552, + "step": 15131 + }, + { + "epoch": 4.67, + "learning_rate": 1.790233783027615e-05, + "loss": 0.271, + "step": 15132 + }, + { + "epoch": 4.67, + "learning_rate": 1.790203134519996e-05, + "loss": 0.2724, + "step": 15133 + }, + { + "epoch": 4.67, + "learning_rate": 1.790172484035935e-05, + "loss": 0.2439, + "step": 15134 + }, + { + "epoch": 4.67, + "learning_rate": 1.7901418315755082e-05, + "loss": 0.2675, + "step": 15135 + }, + { + "epoch": 4.67, + "learning_rate": 1.7901111771387932e-05, + "loss": 0.2494, + "step": 15136 + }, + { + "epoch": 4.67, + "learning_rate": 1.7900805207258652e-05, + "loss": 0.2569, + "step": 15137 + }, + { + "epoch": 4.68, + "learning_rate": 1.7900498623368026e-05, + "loss": 0.2845, + "step": 15138 + }, + { + "epoch": 4.68, + "learning_rate": 1.7900192019716806e-05, + "loss": 0.2717, + "step": 15139 + }, + { + "epoch": 4.68, + "learning_rate": 1.7899885396305767e-05, + "loss": 0.2677, + "step": 15140 + }, + { + "epoch": 4.68, + "learning_rate": 1.7899578753135673e-05, + "loss": 0.276, + "step": 15141 + }, + { + "epoch": 4.68, + "learning_rate": 1.7899272090207294e-05, + "loss": 0.2872, + "step": 15142 + }, + { + "epoch": 4.68, + "learning_rate": 1.789896540752139e-05, + "loss": 0.2508, + "step": 15143 + }, + { + "epoch": 4.68, + "learning_rate": 1.7898658705078737e-05, + "loss": 0.2576, + "step": 15144 + }, + { + "epoch": 4.68, + "learning_rate": 1.78983519828801e-05, + "loss": 0.2869, + "step": 15145 + }, + { + "epoch": 4.68, + "learning_rate": 1.789804524092624e-05, + "loss": 0.2553, + "step": 15146 + }, + { + "epoch": 4.68, + "learning_rate": 1.7897738479217926e-05, + "loss": 0.2566, + "step": 15147 + }, + { + "epoch": 4.68, + "learning_rate": 1.789743169775593e-05, + "loss": 0.2478, + "step": 15148 + }, + { + "epoch": 4.68, + "learning_rate": 1.7897124896541018e-05, + "loss": 0.2754, + "step": 15149 + }, + { + "epoch": 4.68, + "learning_rate": 1.7896818075573957e-05, + "loss": 0.266, + "step": 15150 + }, + { + "epoch": 4.68, + "learning_rate": 1.789651123485551e-05, + "loss": 0.2824, + "step": 15151 + }, + { + "epoch": 4.68, + "learning_rate": 1.7896204374386453e-05, + "loss": 0.2839, + "step": 15152 + }, + { + "epoch": 4.68, + "learning_rate": 1.7895897494167544e-05, + "loss": 0.2622, + "step": 15153 + }, + { + "epoch": 4.68, + "learning_rate": 1.789559059419956e-05, + "loss": 0.2597, + "step": 15154 + }, + { + "epoch": 4.68, + "learning_rate": 1.789528367448326e-05, + "loss": 0.2744, + "step": 15155 + }, + { + "epoch": 4.68, + "learning_rate": 1.7894976735019418e-05, + "loss": 0.2506, + "step": 15156 + }, + { + "epoch": 4.68, + "learning_rate": 1.7894669775808798e-05, + "loss": 0.2639, + "step": 15157 + }, + { + "epoch": 4.68, + "learning_rate": 1.789436279685217e-05, + "loss": 0.2682, + "step": 15158 + }, + { + "epoch": 4.68, + "learning_rate": 1.7894055798150302e-05, + "loss": 0.2909, + "step": 15159 + }, + { + "epoch": 4.68, + "learning_rate": 1.7893748779703958e-05, + "loss": 0.251, + "step": 15160 + }, + { + "epoch": 4.68, + "learning_rate": 1.789344174151391e-05, + "loss": 0.2595, + "step": 15161 + }, + { + "epoch": 4.68, + "learning_rate": 1.789313468358092e-05, + "loss": 0.2724, + "step": 15162 + }, + { + "epoch": 4.68, + "learning_rate": 1.7892827605905767e-05, + "loss": 0.2605, + "step": 15163 + }, + { + "epoch": 4.68, + "learning_rate": 1.789252050848921e-05, + "loss": 0.2711, + "step": 15164 + }, + { + "epoch": 4.68, + "learning_rate": 1.789221339133202e-05, + "loss": 0.2627, + "step": 15165 + }, + { + "epoch": 4.68, + "learning_rate": 1.7891906254434962e-05, + "loss": 0.2576, + "step": 15166 + }, + { + "epoch": 4.68, + "learning_rate": 1.789159909779881e-05, + "loss": 0.256, + "step": 15167 + }, + { + "epoch": 4.68, + "learning_rate": 1.789129192142433e-05, + "loss": 0.2543, + "step": 15168 + }, + { + "epoch": 4.68, + "learning_rate": 1.789098472531229e-05, + "loss": 0.2604, + "step": 15169 + }, + { + "epoch": 4.68, + "learning_rate": 1.7890677509463455e-05, + "loss": 0.2457, + "step": 15170 + }, + { + "epoch": 4.69, + "learning_rate": 1.78903702738786e-05, + "loss": 0.2564, + "step": 15171 + }, + { + "epoch": 4.69, + "learning_rate": 1.7890063018558487e-05, + "loss": 0.2506, + "step": 15172 + }, + { + "epoch": 4.69, + "learning_rate": 1.7889755743503887e-05, + "loss": 0.2617, + "step": 15173 + }, + { + "epoch": 4.69, + "learning_rate": 1.788944844871557e-05, + "loss": 0.2557, + "step": 15174 + }, + { + "epoch": 4.69, + "learning_rate": 1.7889141134194305e-05, + "loss": 0.2659, + "step": 15175 + }, + { + "epoch": 4.69, + "learning_rate": 1.7888833799940854e-05, + "loss": 0.2703, + "step": 15176 + }, + { + "epoch": 4.69, + "learning_rate": 1.7888526445955997e-05, + "loss": 0.2591, + "step": 15177 + }, + { + "epoch": 4.69, + "learning_rate": 1.7888219072240494e-05, + "loss": 0.2876, + "step": 15178 + }, + { + "epoch": 4.69, + "learning_rate": 1.7887911678795116e-05, + "loss": 0.287, + "step": 15179 + }, + { + "epoch": 4.69, + "learning_rate": 1.7887604265620634e-05, + "loss": 0.2724, + "step": 15180 + }, + { + "epoch": 4.69, + "learning_rate": 1.7887296832717812e-05, + "loss": 0.2573, + "step": 15181 + }, + { + "epoch": 4.69, + "learning_rate": 1.7886989380087424e-05, + "loss": 0.2434, + "step": 15182 + }, + { + "epoch": 4.69, + "learning_rate": 1.7886681907730238e-05, + "loss": 0.281, + "step": 15183 + }, + { + "epoch": 4.69, + "learning_rate": 1.788637441564702e-05, + "loss": 0.2762, + "step": 15184 + }, + { + "epoch": 4.69, + "learning_rate": 1.7886066903838543e-05, + "loss": 0.2732, + "step": 15185 + }, + { + "epoch": 4.69, + "learning_rate": 1.7885759372305572e-05, + "loss": 0.2663, + "step": 15186 + }, + { + "epoch": 4.69, + "learning_rate": 1.788545182104888e-05, + "loss": 0.247, + "step": 15187 + }, + { + "epoch": 4.69, + "learning_rate": 1.7885144250069235e-05, + "loss": 0.2627, + "step": 15188 + }, + { + "epoch": 4.69, + "learning_rate": 1.7884836659367408e-05, + "loss": 0.2615, + "step": 15189 + }, + { + "epoch": 4.69, + "learning_rate": 1.7884529048944163e-05, + "loss": 0.2503, + "step": 15190 + }, + { + "epoch": 4.69, + "learning_rate": 1.7884221418800274e-05, + "loss": 0.2729, + "step": 15191 + }, + { + "epoch": 4.69, + "learning_rate": 1.788391376893651e-05, + "loss": 0.2648, + "step": 15192 + }, + { + "epoch": 4.69, + "learning_rate": 1.7883606099353637e-05, + "loss": 0.2911, + "step": 15193 + }, + { + "epoch": 4.69, + "learning_rate": 1.788329841005243e-05, + "loss": 0.2578, + "step": 15194 + }, + { + "epoch": 4.69, + "learning_rate": 1.7882990701033657e-05, + "loss": 0.29, + "step": 15195 + }, + { + "epoch": 4.69, + "learning_rate": 1.7882682972298083e-05, + "loss": 0.2623, + "step": 15196 + }, + { + "epoch": 4.69, + "learning_rate": 1.7882375223846483e-05, + "loss": 0.2413, + "step": 15197 + }, + { + "epoch": 4.69, + "learning_rate": 1.7882067455679625e-05, + "loss": 0.288, + "step": 15198 + }, + { + "epoch": 4.69, + "learning_rate": 1.788175966779828e-05, + "loss": 0.2652, + "step": 15199 + }, + { + "epoch": 4.69, + "learning_rate": 1.7881451860203213e-05, + "loss": 0.2742, + "step": 15200 + }, + { + "epoch": 4.69, + "learning_rate": 1.78811440328952e-05, + "loss": 0.241, + "step": 15201 + }, + { + "epoch": 4.69, + "learning_rate": 1.788083618587501e-05, + "loss": 0.2629, + "step": 15202 + }, + { + "epoch": 4.7, + "learning_rate": 1.7880528319143406e-05, + "loss": 0.2653, + "step": 15203 + }, + { + "epoch": 4.7, + "learning_rate": 1.7880220432701167e-05, + "loss": 0.2625, + "step": 15204 + }, + { + "epoch": 4.7, + "learning_rate": 1.787991252654906e-05, + "loss": 0.2665, + "step": 15205 + }, + { + "epoch": 4.7, + "learning_rate": 1.7879604600687853e-05, + "loss": 0.2527, + "step": 15206 + }, + { + "epoch": 4.7, + "learning_rate": 1.7879296655118316e-05, + "loss": 0.2755, + "step": 15207 + }, + { + "epoch": 4.7, + "learning_rate": 1.7878988689841223e-05, + "loss": 0.2674, + "step": 15208 + }, + { + "epoch": 4.7, + "learning_rate": 1.7878680704857343e-05, + "loss": 0.2583, + "step": 15209 + }, + { + "epoch": 4.7, + "learning_rate": 1.7878372700167444e-05, + "loss": 0.2773, + "step": 15210 + }, + { + "epoch": 4.7, + "learning_rate": 1.7878064675772303e-05, + "loss": 0.2719, + "step": 15211 + }, + { + "epoch": 4.7, + "learning_rate": 1.787775663167268e-05, + "loss": 0.2688, + "step": 15212 + }, + { + "epoch": 4.7, + "learning_rate": 1.787744856786935e-05, + "loss": 0.2657, + "step": 15213 + }, + { + "epoch": 4.7, + "learning_rate": 1.7877140484363087e-05, + "loss": 0.2592, + "step": 15214 + }, + { + "epoch": 4.7, + "learning_rate": 1.787683238115466e-05, + "loss": 0.2766, + "step": 15215 + }, + { + "epoch": 4.7, + "learning_rate": 1.7876524258244834e-05, + "loss": 0.2727, + "step": 15216 + }, + { + "epoch": 4.7, + "learning_rate": 1.7876216115634387e-05, + "loss": 0.2547, + "step": 15217 + }, + { + "epoch": 4.7, + "learning_rate": 1.7875907953324088e-05, + "loss": 0.2878, + "step": 15218 + }, + { + "epoch": 4.7, + "learning_rate": 1.787559977131471e-05, + "loss": 0.2824, + "step": 15219 + }, + { + "epoch": 4.7, + "learning_rate": 1.7875291569607014e-05, + "loss": 0.267, + "step": 15220 + }, + { + "epoch": 4.7, + "learning_rate": 1.787498334820178e-05, + "loss": 0.2546, + "step": 15221 + }, + { + "epoch": 4.7, + "learning_rate": 1.7874675107099776e-05, + "loss": 0.2424, + "step": 15222 + }, + { + "epoch": 4.7, + "learning_rate": 1.7874366846301775e-05, + "loss": 0.2453, + "step": 15223 + }, + { + "epoch": 4.7, + "learning_rate": 1.7874058565808543e-05, + "loss": 0.2591, + "step": 15224 + }, + { + "epoch": 4.7, + "learning_rate": 1.7873750265620857e-05, + "loss": 0.2777, + "step": 15225 + }, + { + "epoch": 4.7, + "learning_rate": 1.7873441945739485e-05, + "loss": 0.2591, + "step": 15226 + }, + { + "epoch": 4.7, + "learning_rate": 1.7873133606165197e-05, + "loss": 0.253, + "step": 15227 + }, + { + "epoch": 4.7, + "learning_rate": 1.787282524689877e-05, + "loss": 0.2718, + "step": 15228 + }, + { + "epoch": 4.7, + "learning_rate": 1.787251686794097e-05, + "loss": 0.2465, + "step": 15229 + }, + { + "epoch": 4.7, + "learning_rate": 1.7872208469292563e-05, + "loss": 0.2678, + "step": 15230 + }, + { + "epoch": 4.7, + "learning_rate": 1.7871900050954335e-05, + "loss": 0.2767, + "step": 15231 + }, + { + "epoch": 4.7, + "learning_rate": 1.7871591612927046e-05, + "loss": 0.2828, + "step": 15232 + }, + { + "epoch": 4.7, + "learning_rate": 1.787128315521147e-05, + "loss": 0.282, + "step": 15233 + }, + { + "epoch": 4.7, + "learning_rate": 1.787097467780838e-05, + "loss": 0.2548, + "step": 15234 + }, + { + "epoch": 4.7, + "learning_rate": 1.7870666180718547e-05, + "loss": 0.258, + "step": 15235 + }, + { + "epoch": 4.71, + "learning_rate": 1.787035766394274e-05, + "loss": 0.2493, + "step": 15236 + }, + { + "epoch": 4.71, + "learning_rate": 1.7870049127481736e-05, + "loss": 0.2757, + "step": 15237 + }, + { + "epoch": 4.71, + "learning_rate": 1.7869740571336302e-05, + "loss": 0.2521, + "step": 15238 + }, + { + "epoch": 4.71, + "learning_rate": 1.7869431995507215e-05, + "loss": 0.2779, + "step": 15239 + }, + { + "epoch": 4.71, + "learning_rate": 1.7869123399995237e-05, + "loss": 0.2569, + "step": 15240 + }, + { + "epoch": 4.71, + "learning_rate": 1.786881478480115e-05, + "loss": 0.2431, + "step": 15241 + }, + { + "epoch": 4.71, + "learning_rate": 1.7868506149925723e-05, + "loss": 0.2679, + "step": 15242 + }, + { + "epoch": 4.71, + "learning_rate": 1.7868197495369724e-05, + "loss": 0.254, + "step": 15243 + }, + { + "epoch": 4.71, + "learning_rate": 1.786788882113393e-05, + "loss": 0.2593, + "step": 15244 + }, + { + "epoch": 4.71, + "learning_rate": 1.786758012721911e-05, + "loss": 0.2522, + "step": 15245 + }, + { + "epoch": 4.71, + "learning_rate": 1.786727141362604e-05, + "loss": 0.2528, + "step": 15246 + }, + { + "epoch": 4.71, + "learning_rate": 1.7866962680355487e-05, + "loss": 0.2784, + "step": 15247 + }, + { + "epoch": 4.71, + "learning_rate": 1.7866653927408223e-05, + "loss": 0.2679, + "step": 15248 + }, + { + "epoch": 4.71, + "learning_rate": 1.7866345154785027e-05, + "loss": 0.2486, + "step": 15249 + }, + { + "epoch": 4.71, + "learning_rate": 1.786603636248667e-05, + "loss": 0.2668, + "step": 15250 + }, + { + "epoch": 4.71, + "learning_rate": 1.7865727550513914e-05, + "loss": 0.244, + "step": 15251 + }, + { + "epoch": 4.71, + "learning_rate": 1.786541871886754e-05, + "loss": 0.2537, + "step": 15252 + }, + { + "epoch": 4.71, + "learning_rate": 1.786510986754832e-05, + "loss": 0.2619, + "step": 15253 + }, + { + "epoch": 4.71, + "learning_rate": 1.786480099655703e-05, + "loss": 0.2646, + "step": 15254 + }, + { + "epoch": 4.71, + "learning_rate": 1.7864492105894432e-05, + "loss": 0.2705, + "step": 15255 + }, + { + "epoch": 4.71, + "learning_rate": 1.7864183195561308e-05, + "loss": 0.2586, + "step": 15256 + }, + { + "epoch": 4.71, + "learning_rate": 1.7863874265558428e-05, + "loss": 0.2613, + "step": 15257 + }, + { + "epoch": 4.71, + "learning_rate": 1.7863565315886566e-05, + "loss": 0.265, + "step": 15258 + }, + { + "epoch": 4.71, + "learning_rate": 1.7863256346546487e-05, + "loss": 0.2577, + "step": 15259 + }, + { + "epoch": 4.71, + "learning_rate": 1.7862947357538973e-05, + "loss": 0.2544, + "step": 15260 + }, + { + "epoch": 4.71, + "learning_rate": 1.786263834886479e-05, + "loss": 0.2542, + "step": 15261 + }, + { + "epoch": 4.71, + "learning_rate": 1.786232932052472e-05, + "loss": 0.2627, + "step": 15262 + }, + { + "epoch": 4.71, + "learning_rate": 1.786202027251953e-05, + "loss": 0.2476, + "step": 15263 + }, + { + "epoch": 4.71, + "learning_rate": 1.786171120484999e-05, + "loss": 0.2739, + "step": 15264 + }, + { + "epoch": 4.71, + "learning_rate": 1.786140211751688e-05, + "loss": 0.2635, + "step": 15265 + }, + { + "epoch": 4.71, + "learning_rate": 1.7861093010520964e-05, + "loss": 0.2618, + "step": 15266 + }, + { + "epoch": 4.71, + "learning_rate": 1.7860783883863028e-05, + "loss": 0.2488, + "step": 15267 + }, + { + "epoch": 4.72, + "learning_rate": 1.7860474737543834e-05, + "loss": 0.269, + "step": 15268 + }, + { + "epoch": 4.72, + "learning_rate": 1.7860165571564158e-05, + "loss": 0.2602, + "step": 15269 + }, + { + "epoch": 4.72, + "learning_rate": 1.7859856385924773e-05, + "loss": 0.2711, + "step": 15270 + }, + { + "epoch": 4.72, + "learning_rate": 1.7859547180626458e-05, + "loss": 0.2476, + "step": 15271 + }, + { + "epoch": 4.72, + "learning_rate": 1.785923795566998e-05, + "loss": 0.2525, + "step": 15272 + }, + { + "epoch": 4.72, + "learning_rate": 1.7858928711056115e-05, + "loss": 0.2619, + "step": 15273 + }, + { + "epoch": 4.72, + "learning_rate": 1.785861944678563e-05, + "loss": 0.2682, + "step": 15274 + }, + { + "epoch": 4.72, + "learning_rate": 1.7858310162859315e-05, + "loss": 0.2979, + "step": 15275 + }, + { + "epoch": 4.72, + "learning_rate": 1.7858000859277927e-05, + "loss": 0.2872, + "step": 15276 + }, + { + "epoch": 4.72, + "learning_rate": 1.7857691536042245e-05, + "loss": 0.2701, + "step": 15277 + }, + { + "epoch": 4.72, + "learning_rate": 1.7857382193153047e-05, + "loss": 0.2671, + "step": 15278 + }, + { + "epoch": 4.72, + "learning_rate": 1.7857072830611098e-05, + "loss": 0.2468, + "step": 15279 + }, + { + "epoch": 4.72, + "learning_rate": 1.785676344841718e-05, + "loss": 0.272, + "step": 15280 + }, + { + "epoch": 4.72, + "learning_rate": 1.7856454046572062e-05, + "loss": 0.2532, + "step": 15281 + }, + { + "epoch": 4.72, + "learning_rate": 1.7856144625076522e-05, + "loss": 0.2553, + "step": 15282 + }, + { + "epoch": 4.72, + "learning_rate": 1.785583518393133e-05, + "loss": 0.2794, + "step": 15283 + }, + { + "epoch": 4.72, + "learning_rate": 1.785552572313726e-05, + "loss": 0.2576, + "step": 15284 + }, + { + "epoch": 4.72, + "learning_rate": 1.7855216242695087e-05, + "loss": 0.2797, + "step": 15285 + }, + { + "epoch": 4.72, + "learning_rate": 1.785490674260559e-05, + "loss": 0.2852, + "step": 15286 + }, + { + "epoch": 4.72, + "learning_rate": 1.7854597222869536e-05, + "loss": 0.2624, + "step": 15287 + }, + { + "epoch": 4.72, + "learning_rate": 1.78542876834877e-05, + "loss": 0.255, + "step": 15288 + }, + { + "epoch": 4.72, + "learning_rate": 1.785397812446086e-05, + "loss": 0.2731, + "step": 15289 + }, + { + "epoch": 4.72, + "learning_rate": 1.785366854578979e-05, + "loss": 0.2483, + "step": 15290 + }, + { + "epoch": 4.72, + "learning_rate": 1.785335894747526e-05, + "loss": 0.2605, + "step": 15291 + }, + { + "epoch": 4.72, + "learning_rate": 1.7853049329518047e-05, + "loss": 0.2677, + "step": 15292 + }, + { + "epoch": 4.72, + "learning_rate": 1.7852739691918923e-05, + "loss": 0.2509, + "step": 15293 + }, + { + "epoch": 4.72, + "learning_rate": 1.7852430034678668e-05, + "loss": 0.2752, + "step": 15294 + }, + { + "epoch": 4.72, + "learning_rate": 1.7852120357798056e-05, + "loss": 0.2541, + "step": 15295 + }, + { + "epoch": 4.72, + "learning_rate": 1.7851810661277854e-05, + "loss": 0.2462, + "step": 15296 + }, + { + "epoch": 4.72, + "learning_rate": 1.7851500945118844e-05, + "loss": 0.2809, + "step": 15297 + }, + { + "epoch": 4.72, + "learning_rate": 1.7851191209321795e-05, + "loss": 0.2533, + "step": 15298 + }, + { + "epoch": 4.72, + "learning_rate": 1.7850881453887487e-05, + "loss": 0.2792, + "step": 15299 + }, + { + "epoch": 4.73, + "learning_rate": 1.7850571678816692e-05, + "loss": 0.278, + "step": 15300 + }, + { + "epoch": 4.73, + "learning_rate": 1.7850261884110186e-05, + "loss": 0.2628, + "step": 15301 + }, + { + "epoch": 4.73, + "learning_rate": 1.7849952069768744e-05, + "loss": 0.2413, + "step": 15302 + }, + { + "epoch": 4.73, + "learning_rate": 1.784964223579314e-05, + "loss": 0.2745, + "step": 15303 + }, + { + "epoch": 4.73, + "learning_rate": 1.784933238218415e-05, + "loss": 0.2814, + "step": 15304 + }, + { + "epoch": 4.73, + "learning_rate": 1.7849022508942543e-05, + "loss": 0.2799, + "step": 15305 + }, + { + "epoch": 4.73, + "learning_rate": 1.7848712616069103e-05, + "loss": 0.2605, + "step": 15306 + }, + { + "epoch": 4.73, + "learning_rate": 1.78484027035646e-05, + "loss": 0.258, + "step": 15307 + }, + { + "epoch": 4.73, + "learning_rate": 1.7848092771429813e-05, + "loss": 0.2757, + "step": 15308 + }, + { + "epoch": 4.73, + "learning_rate": 1.7847782819665512e-05, + "loss": 0.2489, + "step": 15309 + }, + { + "epoch": 4.73, + "learning_rate": 1.7847472848272477e-05, + "loss": 0.2591, + "step": 15310 + }, + { + "epoch": 4.73, + "learning_rate": 1.7847162857251475e-05, + "loss": 0.255, + "step": 15311 + }, + { + "epoch": 4.73, + "learning_rate": 1.7846852846603294e-05, + "loss": 0.2864, + "step": 15312 + }, + { + "epoch": 4.73, + "learning_rate": 1.7846542816328702e-05, + "loss": 0.2749, + "step": 15313 + }, + { + "epoch": 4.73, + "learning_rate": 1.7846232766428475e-05, + "loss": 0.2413, + "step": 15314 + }, + { + "epoch": 4.73, + "learning_rate": 1.7845922696903386e-05, + "loss": 0.2521, + "step": 15315 + }, + { + "epoch": 4.73, + "learning_rate": 1.7845612607754217e-05, + "loss": 0.2607, + "step": 15316 + }, + { + "epoch": 4.73, + "learning_rate": 1.7845302498981738e-05, + "loss": 0.246, + "step": 15317 + }, + { + "epoch": 4.73, + "learning_rate": 1.7844992370586727e-05, + "loss": 0.2574, + "step": 15318 + }, + { + "epoch": 4.73, + "learning_rate": 1.784468222256996e-05, + "loss": 0.2791, + "step": 15319 + }, + { + "epoch": 4.73, + "learning_rate": 1.784437205493221e-05, + "loss": 0.2669, + "step": 15320 + }, + { + "epoch": 4.73, + "learning_rate": 1.7844061867674257e-05, + "loss": 0.2703, + "step": 15321 + }, + { + "epoch": 4.73, + "learning_rate": 1.7843751660796873e-05, + "loss": 0.2631, + "step": 15322 + }, + { + "epoch": 4.73, + "learning_rate": 1.7843441434300834e-05, + "loss": 0.267, + "step": 15323 + }, + { + "epoch": 4.73, + "learning_rate": 1.784313118818692e-05, + "loss": 0.2792, + "step": 15324 + }, + { + "epoch": 4.73, + "learning_rate": 1.7842820922455904e-05, + "loss": 0.2571, + "step": 15325 + }, + { + "epoch": 4.73, + "learning_rate": 1.7842510637108562e-05, + "loss": 0.261, + "step": 15326 + }, + { + "epoch": 4.73, + "learning_rate": 1.784220033214567e-05, + "loss": 0.2658, + "step": 15327 + }, + { + "epoch": 4.73, + "learning_rate": 1.7841890007568004e-05, + "loss": 0.2694, + "step": 15328 + }, + { + "epoch": 4.73, + "learning_rate": 1.7841579663376344e-05, + "loss": 0.2764, + "step": 15329 + }, + { + "epoch": 4.73, + "learning_rate": 1.784126929957146e-05, + "loss": 0.2836, + "step": 15330 + }, + { + "epoch": 4.73, + "learning_rate": 1.7840958916154135e-05, + "loss": 0.2749, + "step": 15331 + }, + { + "epoch": 4.73, + "learning_rate": 1.7840648513125137e-05, + "loss": 0.2655, + "step": 15332 + }, + { + "epoch": 4.74, + "learning_rate": 1.7840338090485253e-05, + "loss": 0.2813, + "step": 15333 + }, + { + "epoch": 4.74, + "learning_rate": 1.784002764823525e-05, + "loss": 0.2686, + "step": 15334 + }, + { + "epoch": 4.74, + "learning_rate": 1.7839717186375903e-05, + "loss": 0.268, + "step": 15335 + }, + { + "epoch": 4.74, + "learning_rate": 1.7839406704908e-05, + "loss": 0.254, + "step": 15336 + }, + { + "epoch": 4.74, + "learning_rate": 1.7839096203832308e-05, + "loss": 0.2851, + "step": 15337 + }, + { + "epoch": 4.74, + "learning_rate": 1.7838785683149607e-05, + "loss": 0.2738, + "step": 15338 + }, + { + "epoch": 4.74, + "learning_rate": 1.7838475142860675e-05, + "loss": 0.2476, + "step": 15339 + }, + { + "epoch": 4.74, + "learning_rate": 1.7838164582966285e-05, + "loss": 0.2727, + "step": 15340 + }, + { + "epoch": 4.74, + "learning_rate": 1.783785400346722e-05, + "loss": 0.2659, + "step": 15341 + }, + { + "epoch": 4.74, + "learning_rate": 1.7837543404364246e-05, + "loss": 0.2332, + "step": 15342 + }, + { + "epoch": 4.74, + "learning_rate": 1.7837232785658153e-05, + "loss": 0.2397, + "step": 15343 + }, + { + "epoch": 4.74, + "learning_rate": 1.7836922147349708e-05, + "loss": 0.2706, + "step": 15344 + }, + { + "epoch": 4.74, + "learning_rate": 1.783661148943969e-05, + "loss": 0.272, + "step": 15345 + }, + { + "epoch": 4.74, + "learning_rate": 1.783630081192888e-05, + "loss": 0.2677, + "step": 15346 + }, + { + "epoch": 4.74, + "learning_rate": 1.7835990114818053e-05, + "loss": 0.2696, + "step": 15347 + }, + { + "epoch": 4.74, + "learning_rate": 1.783567939810798e-05, + "loss": 0.2474, + "step": 15348 + }, + { + "epoch": 4.74, + "learning_rate": 1.7835368661799447e-05, + "loss": 0.2816, + "step": 15349 + }, + { + "epoch": 4.74, + "learning_rate": 1.783505790589323e-05, + "loss": 0.2684, + "step": 15350 + }, + { + "epoch": 4.74, + "learning_rate": 1.7834747130390103e-05, + "loss": 0.2815, + "step": 15351 + }, + { + "epoch": 4.74, + "learning_rate": 1.7834436335290845e-05, + "loss": 0.2808, + "step": 15352 + }, + { + "epoch": 4.74, + "learning_rate": 1.7834125520596232e-05, + "loss": 0.2577, + "step": 15353 + }, + { + "epoch": 4.74, + "learning_rate": 1.783381468630704e-05, + "loss": 0.2715, + "step": 15354 + }, + { + "epoch": 4.74, + "learning_rate": 1.783350383242405e-05, + "loss": 0.2484, + "step": 15355 + }, + { + "epoch": 4.74, + "learning_rate": 1.783319295894804e-05, + "loss": 0.2744, + "step": 15356 + }, + { + "epoch": 4.74, + "learning_rate": 1.7832882065879787e-05, + "loss": 0.2473, + "step": 15357 + }, + { + "epoch": 4.74, + "learning_rate": 1.783257115322006e-05, + "loss": 0.2801, + "step": 15358 + }, + { + "epoch": 4.74, + "learning_rate": 1.783226022096965e-05, + "loss": 0.2631, + "step": 15359 + }, + { + "epoch": 4.74, + "learning_rate": 1.783194926912933e-05, + "loss": 0.2513, + "step": 15360 + }, + { + "epoch": 4.74, + "learning_rate": 1.7831638297699875e-05, + "loss": 0.278, + "step": 15361 + }, + { + "epoch": 4.74, + "learning_rate": 1.7831327306682062e-05, + "loss": 0.2606, + "step": 15362 + }, + { + "epoch": 4.74, + "learning_rate": 1.7831016296076673e-05, + "loss": 0.2715, + "step": 15363 + }, + { + "epoch": 4.74, + "learning_rate": 1.783070526588448e-05, + "loss": 0.2873, + "step": 15364 + }, + { + "epoch": 4.75, + "learning_rate": 1.7830394216106272e-05, + "loss": 0.2629, + "step": 15365 + }, + { + "epoch": 4.75, + "learning_rate": 1.7830083146742814e-05, + "loss": 0.2615, + "step": 15366 + }, + { + "epoch": 4.75, + "learning_rate": 1.7829772057794894e-05, + "loss": 0.2785, + "step": 15367 + }, + { + "epoch": 4.75, + "learning_rate": 1.782946094926328e-05, + "loss": 0.2588, + "step": 15368 + }, + { + "epoch": 4.75, + "learning_rate": 1.782914982114876e-05, + "loss": 0.2705, + "step": 15369 + }, + { + "epoch": 4.75, + "learning_rate": 1.782883867345211e-05, + "loss": 0.2609, + "step": 15370 + }, + { + "epoch": 4.75, + "learning_rate": 1.7828527506174107e-05, + "loss": 0.2625, + "step": 15371 + }, + { + "epoch": 4.75, + "learning_rate": 1.7828216319315524e-05, + "loss": 0.2481, + "step": 15372 + }, + { + "epoch": 4.75, + "learning_rate": 1.7827905112877148e-05, + "loss": 0.2858, + "step": 15373 + }, + { + "epoch": 4.75, + "learning_rate": 1.7827593886859755e-05, + "loss": 0.253, + "step": 15374 + }, + { + "epoch": 4.75, + "learning_rate": 1.782728264126412e-05, + "loss": 0.2567, + "step": 15375 + }, + { + "epoch": 4.75, + "learning_rate": 1.7826971376091022e-05, + "loss": 0.238, + "step": 15376 + }, + { + "epoch": 4.75, + "learning_rate": 1.7826660091341242e-05, + "loss": 0.2637, + "step": 15377 + }, + { + "epoch": 4.75, + "learning_rate": 1.782634878701556e-05, + "loss": 0.2754, + "step": 15378 + }, + { + "epoch": 4.75, + "learning_rate": 1.782603746311475e-05, + "loss": 0.2794, + "step": 15379 + }, + { + "epoch": 4.75, + "learning_rate": 1.782572611963959e-05, + "loss": 0.286, + "step": 15380 + }, + { + "epoch": 4.75, + "learning_rate": 1.7825414756590868e-05, + "loss": 0.2804, + "step": 15381 + }, + { + "epoch": 4.75, + "learning_rate": 1.7825103373969354e-05, + "loss": 0.2685, + "step": 15382 + }, + { + "epoch": 4.75, + "learning_rate": 1.7824791971775826e-05, + "loss": 0.2446, + "step": 15383 + }, + { + "epoch": 4.75, + "learning_rate": 1.782448055001107e-05, + "loss": 0.2635, + "step": 15384 + }, + { + "epoch": 4.75, + "learning_rate": 1.7824169108675858e-05, + "loss": 0.2745, + "step": 15385 + }, + { + "epoch": 4.75, + "learning_rate": 1.7823857647770974e-05, + "loss": 0.2728, + "step": 15386 + }, + { + "epoch": 4.75, + "learning_rate": 1.782354616729719e-05, + "loss": 0.2568, + "step": 15387 + }, + { + "epoch": 4.75, + "learning_rate": 1.78232346672553e-05, + "loss": 0.2791, + "step": 15388 + }, + { + "epoch": 4.75, + "learning_rate": 1.7822923147646067e-05, + "loss": 0.262, + "step": 15389 + }, + { + "epoch": 4.75, + "learning_rate": 1.7822611608470276e-05, + "loss": 0.2357, + "step": 15390 + }, + { + "epoch": 4.75, + "learning_rate": 1.782230004972871e-05, + "loss": 0.2481, + "step": 15391 + }, + { + "epoch": 4.75, + "learning_rate": 1.7821988471422143e-05, + "loss": 0.2796, + "step": 15392 + }, + { + "epoch": 4.75, + "learning_rate": 1.7821676873551353e-05, + "loss": 0.2681, + "step": 15393 + }, + { + "epoch": 4.75, + "learning_rate": 1.7821365256117128e-05, + "loss": 0.2589, + "step": 15394 + }, + { + "epoch": 4.75, + "learning_rate": 1.782105361912024e-05, + "loss": 0.2748, + "step": 15395 + }, + { + "epoch": 4.75, + "learning_rate": 1.782074196256147e-05, + "loss": 0.2492, + "step": 15396 + }, + { + "epoch": 4.75, + "learning_rate": 1.7820430286441598e-05, + "loss": 0.2648, + "step": 15397 + }, + { + "epoch": 4.76, + "learning_rate": 1.7820118590761403e-05, + "loss": 0.2757, + "step": 15398 + }, + { + "epoch": 4.76, + "learning_rate": 1.7819806875521665e-05, + "loss": 0.2702, + "step": 15399 + }, + { + "epoch": 4.76, + "learning_rate": 1.7819495140723165e-05, + "loss": 0.268, + "step": 15400 + }, + { + "epoch": 4.76, + "learning_rate": 1.781918338636668e-05, + "loss": 0.2767, + "step": 15401 + }, + { + "epoch": 4.76, + "learning_rate": 1.7818871612452994e-05, + "loss": 0.2581, + "step": 15402 + }, + { + "epoch": 4.76, + "learning_rate": 1.7818559818982882e-05, + "loss": 0.2623, + "step": 15403 + }, + { + "epoch": 4.76, + "learning_rate": 1.7818248005957125e-05, + "loss": 0.267, + "step": 15404 + }, + { + "epoch": 4.76, + "learning_rate": 1.7817936173376504e-05, + "loss": 0.2671, + "step": 15405 + }, + { + "epoch": 4.76, + "learning_rate": 1.7817624321241798e-05, + "loss": 0.2789, + "step": 15406 + }, + { + "epoch": 4.76, + "learning_rate": 1.781731244955379e-05, + "loss": 0.2626, + "step": 15407 + }, + { + "epoch": 4.76, + "learning_rate": 1.781700055831326e-05, + "loss": 0.2634, + "step": 15408 + }, + { + "epoch": 4.76, + "learning_rate": 1.781668864752098e-05, + "loss": 0.2729, + "step": 15409 + }, + { + "epoch": 4.76, + "learning_rate": 1.781637671717774e-05, + "loss": 0.2745, + "step": 15410 + }, + { + "epoch": 4.76, + "learning_rate": 1.7816064767284316e-05, + "loss": 0.2431, + "step": 15411 + }, + { + "epoch": 4.76, + "learning_rate": 1.7815752797841487e-05, + "loss": 0.2709, + "step": 15412 + }, + { + "epoch": 4.76, + "learning_rate": 1.7815440808850035e-05, + "loss": 0.2665, + "step": 15413 + }, + { + "epoch": 4.76, + "learning_rate": 1.781512880031074e-05, + "loss": 0.267, + "step": 15414 + }, + { + "epoch": 4.76, + "learning_rate": 1.781481677222438e-05, + "loss": 0.2933, + "step": 15415 + }, + { + "epoch": 4.76, + "learning_rate": 1.7814504724591744e-05, + "loss": 0.2788, + "step": 15416 + }, + { + "epoch": 4.76, + "learning_rate": 1.78141926574136e-05, + "loss": 0.2475, + "step": 15417 + }, + { + "epoch": 4.76, + "learning_rate": 1.7813880570690743e-05, + "loss": 0.2797, + "step": 15418 + }, + { + "epoch": 4.76, + "learning_rate": 1.7813568464423937e-05, + "loss": 0.2699, + "step": 15419 + }, + { + "epoch": 4.76, + "learning_rate": 1.7813256338613974e-05, + "loss": 0.2692, + "step": 15420 + }, + { + "epoch": 4.76, + "learning_rate": 1.7812944193261633e-05, + "loss": 0.2712, + "step": 15421 + }, + { + "epoch": 4.76, + "learning_rate": 1.7812632028367696e-05, + "loss": 0.2976, + "step": 15422 + }, + { + "epoch": 4.76, + "learning_rate": 1.7812319843932936e-05, + "loss": 0.2567, + "step": 15423 + }, + { + "epoch": 4.76, + "learning_rate": 1.7812007639958143e-05, + "loss": 0.2659, + "step": 15424 + }, + { + "epoch": 4.76, + "learning_rate": 1.781169541644409e-05, + "loss": 0.2612, + "step": 15425 + }, + { + "epoch": 4.76, + "learning_rate": 1.7811383173391568e-05, + "loss": 0.264, + "step": 15426 + }, + { + "epoch": 4.76, + "learning_rate": 1.781107091080135e-05, + "loss": 0.2707, + "step": 15427 + }, + { + "epoch": 4.76, + "learning_rate": 1.7810758628674217e-05, + "loss": 0.2469, + "step": 15428 + }, + { + "epoch": 4.76, + "learning_rate": 1.7810446327010954e-05, + "loss": 0.2939, + "step": 15429 + }, + { + "epoch": 4.77, + "learning_rate": 1.7810134005812337e-05, + "loss": 0.271, + "step": 15430 + }, + { + "epoch": 4.77, + "learning_rate": 1.7809821665079155e-05, + "loss": 0.2479, + "step": 15431 + }, + { + "epoch": 4.77, + "learning_rate": 1.780950930481218e-05, + "loss": 0.2636, + "step": 15432 + }, + { + "epoch": 4.77, + "learning_rate": 1.78091969250122e-05, + "loss": 0.2718, + "step": 15433 + }, + { + "epoch": 4.77, + "learning_rate": 1.780888452567999e-05, + "loss": 0.2659, + "step": 15434 + }, + { + "epoch": 4.77, + "learning_rate": 1.7808572106816344e-05, + "loss": 0.2599, + "step": 15435 + }, + { + "epoch": 4.77, + "learning_rate": 1.7808259668422028e-05, + "loss": 0.2578, + "step": 15436 + }, + { + "epoch": 4.77, + "learning_rate": 1.7807947210497836e-05, + "loss": 0.267, + "step": 15437 + }, + { + "epoch": 4.77, + "learning_rate": 1.7807634733044537e-05, + "loss": 0.2703, + "step": 15438 + }, + { + "epoch": 4.77, + "learning_rate": 1.7807322236062927e-05, + "loss": 0.2589, + "step": 15439 + }, + { + "epoch": 4.77, + "learning_rate": 1.7807009719553776e-05, + "loss": 0.2632, + "step": 15440 + }, + { + "epoch": 4.77, + "learning_rate": 1.7806697183517872e-05, + "loss": 0.2843, + "step": 15441 + }, + { + "epoch": 4.77, + "learning_rate": 1.780638462795599e-05, + "loss": 0.269, + "step": 15442 + }, + { + "epoch": 4.77, + "learning_rate": 1.7806072052868922e-05, + "loss": 0.2746, + "step": 15443 + }, + { + "epoch": 4.77, + "learning_rate": 1.7805759458257438e-05, + "loss": 0.2606, + "step": 15444 + }, + { + "epoch": 4.77, + "learning_rate": 1.7805446844122332e-05, + "loss": 0.2486, + "step": 15445 + }, + { + "epoch": 4.77, + "learning_rate": 1.7805134210464377e-05, + "loss": 0.2545, + "step": 15446 + }, + { + "epoch": 4.77, + "learning_rate": 1.780482155728436e-05, + "loss": 0.2812, + "step": 15447 + }, + { + "epoch": 4.77, + "learning_rate": 1.7804508884583053e-05, + "loss": 0.2689, + "step": 15448 + }, + { + "epoch": 4.77, + "learning_rate": 1.7804196192361254e-05, + "loss": 0.2514, + "step": 15449 + }, + { + "epoch": 4.77, + "learning_rate": 1.7803883480619736e-05, + "loss": 0.2472, + "step": 15450 + }, + { + "epoch": 4.77, + "learning_rate": 1.780357074935928e-05, + "loss": 0.2694, + "step": 15451 + }, + { + "epoch": 4.77, + "learning_rate": 1.780325799858067e-05, + "loss": 0.2739, + "step": 15452 + }, + { + "epoch": 4.77, + "learning_rate": 1.7802945228284688e-05, + "loss": 0.2527, + "step": 15453 + }, + { + "epoch": 4.77, + "learning_rate": 1.780263243847212e-05, + "loss": 0.2672, + "step": 15454 + }, + { + "epoch": 4.77, + "learning_rate": 1.780231962914374e-05, + "loss": 0.2591, + "step": 15455 + }, + { + "epoch": 4.77, + "learning_rate": 1.780200680030034e-05, + "loss": 0.2598, + "step": 15456 + }, + { + "epoch": 4.77, + "learning_rate": 1.7801693951942694e-05, + "loss": 0.2853, + "step": 15457 + }, + { + "epoch": 4.77, + "learning_rate": 1.7801381084071595e-05, + "loss": 0.24, + "step": 15458 + }, + { + "epoch": 4.77, + "learning_rate": 1.7801068196687814e-05, + "loss": 0.2683, + "step": 15459 + }, + { + "epoch": 4.77, + "learning_rate": 1.780075528979214e-05, + "loss": 0.2729, + "step": 15460 + }, + { + "epoch": 4.77, + "learning_rate": 1.7800442363385352e-05, + "loss": 0.2754, + "step": 15461 + }, + { + "epoch": 4.78, + "learning_rate": 1.780012941746824e-05, + "loss": 0.244, + "step": 15462 + }, + { + "epoch": 4.78, + "learning_rate": 1.7799816452041578e-05, + "loss": 0.2693, + "step": 15463 + }, + { + "epoch": 4.78, + "learning_rate": 1.779950346710615e-05, + "loss": 0.2892, + "step": 15464 + }, + { + "epoch": 4.78, + "learning_rate": 1.7799190462662745e-05, + "loss": 0.2672, + "step": 15465 + }, + { + "epoch": 4.78, + "learning_rate": 1.7798877438712143e-05, + "loss": 0.2732, + "step": 15466 + }, + { + "epoch": 4.78, + "learning_rate": 1.7798564395255125e-05, + "loss": 0.2653, + "step": 15467 + }, + { + "epoch": 4.78, + "learning_rate": 1.7798251332292473e-05, + "loss": 0.2862, + "step": 15468 + }, + { + "epoch": 4.78, + "learning_rate": 1.7797938249824973e-05, + "loss": 0.2588, + "step": 15469 + }, + { + "epoch": 4.78, + "learning_rate": 1.779762514785341e-05, + "loss": 0.2627, + "step": 15470 + }, + { + "epoch": 4.78, + "learning_rate": 1.779731202637856e-05, + "loss": 0.2625, + "step": 15471 + }, + { + "epoch": 4.78, + "learning_rate": 1.7796998885401216e-05, + "loss": 0.2594, + "step": 15472 + }, + { + "epoch": 4.78, + "learning_rate": 1.779668572492215e-05, + "loss": 0.2493, + "step": 15473 + }, + { + "epoch": 4.78, + "learning_rate": 1.7796372544942155e-05, + "loss": 0.2735, + "step": 15474 + }, + { + "epoch": 4.78, + "learning_rate": 1.7796059345462006e-05, + "loss": 0.2601, + "step": 15475 + }, + { + "epoch": 4.78, + "learning_rate": 1.7795746126482496e-05, + "loss": 0.2802, + "step": 15476 + }, + { + "epoch": 4.78, + "learning_rate": 1.7795432888004402e-05, + "loss": 0.2549, + "step": 15477 + }, + { + "epoch": 4.78, + "learning_rate": 1.7795119630028504e-05, + "loss": 0.2875, + "step": 15478 + }, + { + "epoch": 4.78, + "learning_rate": 1.7794806352555595e-05, + "loss": 0.2592, + "step": 15479 + }, + { + "epoch": 4.78, + "learning_rate": 1.7794493055586454e-05, + "loss": 0.2769, + "step": 15480 + }, + { + "epoch": 4.78, + "learning_rate": 1.7794179739121857e-05, + "loss": 0.2574, + "step": 15481 + }, + { + "epoch": 4.78, + "learning_rate": 1.7793866403162603e-05, + "loss": 0.2787, + "step": 15482 + }, + { + "epoch": 4.78, + "learning_rate": 1.7793553047709463e-05, + "loss": 0.2669, + "step": 15483 + }, + { + "epoch": 4.78, + "learning_rate": 1.7793239672763228e-05, + "loss": 0.2879, + "step": 15484 + }, + { + "epoch": 4.78, + "learning_rate": 1.7792926278324677e-05, + "loss": 0.2689, + "step": 15485 + }, + { + "epoch": 4.78, + "learning_rate": 1.7792612864394598e-05, + "loss": 0.2568, + "step": 15486 + }, + { + "epoch": 4.78, + "learning_rate": 1.779229943097377e-05, + "loss": 0.2762, + "step": 15487 + }, + { + "epoch": 4.78, + "learning_rate": 1.7791985978062985e-05, + "loss": 0.2597, + "step": 15488 + }, + { + "epoch": 4.78, + "learning_rate": 1.7791672505663018e-05, + "loss": 0.2717, + "step": 15489 + }, + { + "epoch": 4.78, + "learning_rate": 1.7791359013774658e-05, + "loss": 0.2589, + "step": 15490 + }, + { + "epoch": 4.78, + "learning_rate": 1.7791045502398686e-05, + "loss": 0.2739, + "step": 15491 + }, + { + "epoch": 4.78, + "learning_rate": 1.779073197153589e-05, + "loss": 0.2681, + "step": 15492 + }, + { + "epoch": 4.78, + "learning_rate": 1.7790418421187056e-05, + "loss": 0.2663, + "step": 15493 + }, + { + "epoch": 4.78, + "learning_rate": 1.779010485135296e-05, + "loss": 0.2708, + "step": 15494 + }, + { + "epoch": 4.79, + "learning_rate": 1.778979126203439e-05, + "loss": 0.2556, + "step": 15495 + }, + { + "epoch": 4.79, + "learning_rate": 1.7789477653232134e-05, + "loss": 0.2541, + "step": 15496 + }, + { + "epoch": 4.79, + "learning_rate": 1.7789164024946974e-05, + "loss": 0.2767, + "step": 15497 + }, + { + "epoch": 4.79, + "learning_rate": 1.778885037717969e-05, + "loss": 0.2616, + "step": 15498 + }, + { + "epoch": 4.79, + "learning_rate": 1.7788536709931076e-05, + "loss": 0.27, + "step": 15499 + }, + { + "epoch": 4.79, + "learning_rate": 1.7788223023201906e-05, + "loss": 0.2484, + "step": 15500 + }, + { + "epoch": 4.79, + "learning_rate": 1.7787909316992974e-05, + "loss": 0.2629, + "step": 15501 + }, + { + "epoch": 4.79, + "learning_rate": 1.778759559130506e-05, + "loss": 0.2409, + "step": 15502 + }, + { + "epoch": 4.79, + "learning_rate": 1.7787281846138948e-05, + "loss": 0.2537, + "step": 15503 + }, + { + "epoch": 4.79, + "learning_rate": 1.7786968081495425e-05, + "loss": 0.2899, + "step": 15504 + }, + { + "epoch": 4.79, + "learning_rate": 1.778665429737527e-05, + "loss": 0.2732, + "step": 15505 + }, + { + "epoch": 4.79, + "learning_rate": 1.778634049377928e-05, + "loss": 0.2554, + "step": 15506 + }, + { + "epoch": 4.79, + "learning_rate": 1.7786026670708226e-05, + "loss": 0.2785, + "step": 15507 + }, + { + "epoch": 4.79, + "learning_rate": 1.77857128281629e-05, + "loss": 0.2624, + "step": 15508 + }, + { + "epoch": 4.79, + "learning_rate": 1.778539896614409e-05, + "loss": 0.2611, + "step": 15509 + }, + { + "epoch": 4.79, + "learning_rate": 1.778508508465257e-05, + "loss": 0.2584, + "step": 15510 + }, + { + "epoch": 4.79, + "learning_rate": 1.778477118368914e-05, + "loss": 0.2622, + "step": 15511 + }, + { + "epoch": 4.79, + "learning_rate": 1.7784457263254572e-05, + "loss": 0.2563, + "step": 15512 + }, + { + "epoch": 4.79, + "learning_rate": 1.778414332334966e-05, + "loss": 0.2552, + "step": 15513 + }, + { + "epoch": 4.79, + "learning_rate": 1.7783829363975184e-05, + "loss": 0.2809, + "step": 15514 + }, + { + "epoch": 4.79, + "learning_rate": 1.7783515385131937e-05, + "loss": 0.2639, + "step": 15515 + }, + { + "epoch": 4.79, + "learning_rate": 1.778320138682069e-05, + "loss": 0.2738, + "step": 15516 + }, + { + "epoch": 4.79, + "learning_rate": 1.778288736904224e-05, + "loss": 0.2621, + "step": 15517 + }, + { + "epoch": 4.79, + "learning_rate": 1.778257333179737e-05, + "loss": 0.2763, + "step": 15518 + }, + { + "epoch": 4.79, + "learning_rate": 1.7782259275086864e-05, + "loss": 0.2744, + "step": 15519 + }, + { + "epoch": 4.79, + "learning_rate": 1.7781945198911508e-05, + "loss": 0.2819, + "step": 15520 + }, + { + "epoch": 4.79, + "learning_rate": 1.7781631103272087e-05, + "loss": 0.2452, + "step": 15521 + }, + { + "epoch": 4.79, + "learning_rate": 1.7781316988169388e-05, + "loss": 0.2691, + "step": 15522 + }, + { + "epoch": 4.79, + "learning_rate": 1.7781002853604195e-05, + "loss": 0.2772, + "step": 15523 + }, + { + "epoch": 4.79, + "learning_rate": 1.77806886995773e-05, + "loss": 0.2464, + "step": 15524 + }, + { + "epoch": 4.79, + "learning_rate": 1.7780374526089476e-05, + "loss": 0.2632, + "step": 15525 + }, + { + "epoch": 4.79, + "learning_rate": 1.778006033314152e-05, + "loss": 0.2797, + "step": 15526 + }, + { + "epoch": 4.8, + "learning_rate": 1.7779746120734214e-05, + "loss": 0.2612, + "step": 15527 + }, + { + "epoch": 4.8, + "learning_rate": 1.7779431888868344e-05, + "loss": 0.25, + "step": 15528 + }, + { + "epoch": 4.8, + "learning_rate": 1.7779117637544695e-05, + "loss": 0.255, + "step": 15529 + }, + { + "epoch": 4.8, + "learning_rate": 1.777880336676405e-05, + "loss": 0.2695, + "step": 15530 + }, + { + "epoch": 4.8, + "learning_rate": 1.7778489076527207e-05, + "loss": 0.2523, + "step": 15531 + }, + { + "epoch": 4.8, + "learning_rate": 1.777817476683494e-05, + "loss": 0.266, + "step": 15532 + }, + { + "epoch": 4.8, + "learning_rate": 1.777786043768804e-05, + "loss": 0.2498, + "step": 15533 + }, + { + "epoch": 4.8, + "learning_rate": 1.7777546089087293e-05, + "loss": 0.2746, + "step": 15534 + }, + { + "epoch": 4.8, + "learning_rate": 1.7777231721033484e-05, + "loss": 0.261, + "step": 15535 + }, + { + "epoch": 4.8, + "learning_rate": 1.77769173335274e-05, + "loss": 0.2404, + "step": 15536 + }, + { + "epoch": 4.8, + "learning_rate": 1.777660292656983e-05, + "loss": 0.2618, + "step": 15537 + }, + { + "epoch": 4.8, + "learning_rate": 1.7776288500161553e-05, + "loss": 0.261, + "step": 15538 + }, + { + "epoch": 4.8, + "learning_rate": 1.7775974054303363e-05, + "loss": 0.2646, + "step": 15539 + }, + { + "epoch": 4.8, + "learning_rate": 1.777565958899604e-05, + "loss": 0.2571, + "step": 15540 + }, + { + "epoch": 4.8, + "learning_rate": 1.777534510424038e-05, + "loss": 0.2664, + "step": 15541 + }, + { + "epoch": 4.8, + "learning_rate": 1.777503060003716e-05, + "loss": 0.2634, + "step": 15542 + }, + { + "epoch": 4.8, + "learning_rate": 1.777471607638717e-05, + "loss": 0.2615, + "step": 15543 + }, + { + "epoch": 4.8, + "learning_rate": 1.7774401533291198e-05, + "loss": 0.2598, + "step": 15544 + }, + { + "epoch": 4.8, + "learning_rate": 1.7774086970750032e-05, + "loss": 0.2738, + "step": 15545 + }, + { + "epoch": 4.8, + "learning_rate": 1.7773772388764456e-05, + "loss": 0.2837, + "step": 15546 + }, + { + "epoch": 4.8, + "learning_rate": 1.7773457787335252e-05, + "loss": 0.2561, + "step": 15547 + }, + { + "epoch": 4.8, + "learning_rate": 1.777314316646322e-05, + "loss": 0.2859, + "step": 15548 + }, + { + "epoch": 4.8, + "learning_rate": 1.7772828526149135e-05, + "loss": 0.2607, + "step": 15549 + }, + { + "epoch": 4.8, + "learning_rate": 1.7772513866393785e-05, + "loss": 0.2558, + "step": 15550 + }, + { + "epoch": 4.8, + "learning_rate": 1.7772199187197964e-05, + "loss": 0.253, + "step": 15551 + }, + { + "epoch": 4.8, + "learning_rate": 1.777188448856246e-05, + "loss": 0.2704, + "step": 15552 + }, + { + "epoch": 4.8, + "learning_rate": 1.777156977048805e-05, + "loss": 0.2788, + "step": 15553 + }, + { + "epoch": 4.8, + "learning_rate": 1.7771255032975525e-05, + "loss": 0.2836, + "step": 15554 + }, + { + "epoch": 4.8, + "learning_rate": 1.7770940276025678e-05, + "loss": 0.2661, + "step": 15555 + }, + { + "epoch": 4.8, + "learning_rate": 1.7770625499639288e-05, + "loss": 0.2661, + "step": 15556 + }, + { + "epoch": 4.8, + "learning_rate": 1.7770310703817147e-05, + "loss": 0.2696, + "step": 15557 + }, + { + "epoch": 4.8, + "learning_rate": 1.7769995888560046e-05, + "loss": 0.262, + "step": 15558 + }, + { + "epoch": 4.81, + "learning_rate": 1.7769681053868763e-05, + "loss": 0.2523, + "step": 15559 + }, + { + "epoch": 4.81, + "learning_rate": 1.7769366199744094e-05, + "loss": 0.267, + "step": 15560 + }, + { + "epoch": 4.81, + "learning_rate": 1.7769051326186823e-05, + "loss": 0.2579, + "step": 15561 + }, + { + "epoch": 4.81, + "learning_rate": 1.7768736433197735e-05, + "loss": 0.2586, + "step": 15562 + }, + { + "epoch": 4.81, + "learning_rate": 1.776842152077762e-05, + "loss": 0.2698, + "step": 15563 + }, + { + "epoch": 4.81, + "learning_rate": 1.776810658892727e-05, + "loss": 0.2562, + "step": 15564 + }, + { + "epoch": 4.81, + "learning_rate": 1.7767791637647468e-05, + "loss": 0.233, + "step": 15565 + }, + { + "epoch": 4.81, + "learning_rate": 1.7767476666938997e-05, + "loss": 0.2605, + "step": 15566 + }, + { + "epoch": 4.81, + "learning_rate": 1.7767161676802654e-05, + "loss": 0.2568, + "step": 15567 + }, + { + "epoch": 4.81, + "learning_rate": 1.7766846667239223e-05, + "loss": 0.2788, + "step": 15568 + }, + { + "epoch": 4.81, + "learning_rate": 1.7766531638249495e-05, + "loss": 0.2456, + "step": 15569 + }, + { + "epoch": 4.81, + "learning_rate": 1.776621658983425e-05, + "loss": 0.2605, + "step": 15570 + }, + { + "epoch": 4.81, + "learning_rate": 1.776590152199428e-05, + "loss": 0.2603, + "step": 15571 + }, + { + "epoch": 4.81, + "learning_rate": 1.7765586434730377e-05, + "loss": 0.2884, + "step": 15572 + }, + { + "epoch": 4.81, + "learning_rate": 1.7765271328043326e-05, + "loss": 0.286, + "step": 15573 + }, + { + "epoch": 4.81, + "learning_rate": 1.7764956201933915e-05, + "loss": 0.2533, + "step": 15574 + }, + { + "epoch": 4.81, + "learning_rate": 1.776464105640293e-05, + "loss": 0.2384, + "step": 15575 + }, + { + "epoch": 4.81, + "learning_rate": 1.7764325891451166e-05, + "loss": 0.2727, + "step": 15576 + }, + { + "epoch": 4.81, + "learning_rate": 1.77640107070794e-05, + "loss": 0.2536, + "step": 15577 + }, + { + "epoch": 4.81, + "learning_rate": 1.7763695503288434e-05, + "loss": 0.2564, + "step": 15578 + }, + { + "epoch": 4.81, + "learning_rate": 1.7763380280079046e-05, + "loss": 0.2528, + "step": 15579 + }, + { + "epoch": 4.81, + "learning_rate": 1.776306503745203e-05, + "loss": 0.2713, + "step": 15580 + }, + { + "epoch": 4.81, + "learning_rate": 1.776274977540817e-05, + "loss": 0.2498, + "step": 15581 + }, + { + "epoch": 4.81, + "learning_rate": 1.7762434493948257e-05, + "loss": 0.2568, + "step": 15582 + }, + { + "epoch": 4.81, + "learning_rate": 1.7762119193073082e-05, + "loss": 0.2611, + "step": 15583 + }, + { + "epoch": 4.81, + "learning_rate": 1.7761803872783428e-05, + "loss": 0.249, + "step": 15584 + }, + { + "epoch": 4.81, + "learning_rate": 1.776148853308009e-05, + "loss": 0.2358, + "step": 15585 + }, + { + "epoch": 4.81, + "learning_rate": 1.7761173173963852e-05, + "loss": 0.2621, + "step": 15586 + }, + { + "epoch": 4.81, + "learning_rate": 1.7760857795435505e-05, + "loss": 0.2535, + "step": 15587 + }, + { + "epoch": 4.81, + "learning_rate": 1.7760542397495837e-05, + "loss": 0.2539, + "step": 15588 + }, + { + "epoch": 4.81, + "learning_rate": 1.7760226980145633e-05, + "loss": 0.2531, + "step": 15589 + }, + { + "epoch": 4.81, + "learning_rate": 1.7759911543385692e-05, + "loss": 0.2624, + "step": 15590 + }, + { + "epoch": 4.81, + "learning_rate": 1.7759596087216795e-05, + "loss": 0.2571, + "step": 15591 + }, + { + "epoch": 4.82, + "learning_rate": 1.775928061163973e-05, + "loss": 0.2426, + "step": 15592 + }, + { + "epoch": 4.82, + "learning_rate": 1.7758965116655297e-05, + "loss": 0.2769, + "step": 15593 + }, + { + "epoch": 4.82, + "learning_rate": 1.7758649602264268e-05, + "loss": 0.2559, + "step": 15594 + }, + { + "epoch": 4.82, + "learning_rate": 1.7758334068467444e-05, + "loss": 0.2712, + "step": 15595 + }, + { + "epoch": 4.82, + "learning_rate": 1.7758018515265613e-05, + "loss": 0.2579, + "step": 15596 + }, + { + "epoch": 4.82, + "learning_rate": 1.7757702942659562e-05, + "loss": 0.2642, + "step": 15597 + }, + { + "epoch": 4.82, + "learning_rate": 1.7757387350650083e-05, + "loss": 0.2508, + "step": 15598 + }, + { + "epoch": 4.82, + "learning_rate": 1.775707173923796e-05, + "loss": 0.286, + "step": 15599 + }, + { + "epoch": 4.82, + "learning_rate": 1.7756756108423987e-05, + "loss": 0.2602, + "step": 15600 + }, + { + "epoch": 4.82, + "learning_rate": 1.7756440458208952e-05, + "loss": 0.2663, + "step": 15601 + }, + { + "epoch": 4.82, + "learning_rate": 1.7756124788593644e-05, + "loss": 0.247, + "step": 15602 + }, + { + "epoch": 4.82, + "learning_rate": 1.7755809099578855e-05, + "loss": 0.2431, + "step": 15603 + }, + { + "epoch": 4.82, + "learning_rate": 1.7755493391165375e-05, + "loss": 0.2713, + "step": 15604 + }, + { + "epoch": 4.82, + "learning_rate": 1.7755177663353988e-05, + "loss": 0.2772, + "step": 15605 + }, + { + "epoch": 4.82, + "learning_rate": 1.7754861916145488e-05, + "loss": 0.2764, + "step": 15606 + }, + { + "epoch": 4.82, + "learning_rate": 1.7754546149540665e-05, + "loss": 0.2701, + "step": 15607 + }, + { + "epoch": 4.82, + "learning_rate": 1.7754230363540306e-05, + "loss": 0.2726, + "step": 15608 + }, + { + "epoch": 4.82, + "learning_rate": 1.7753914558145203e-05, + "loss": 0.2632, + "step": 15609 + }, + { + "epoch": 4.82, + "learning_rate": 1.7753598733356145e-05, + "loss": 0.2657, + "step": 15610 + }, + { + "epoch": 4.82, + "learning_rate": 1.7753282889173923e-05, + "loss": 0.2698, + "step": 15611 + }, + { + "epoch": 4.82, + "learning_rate": 1.7752967025599325e-05, + "loss": 0.2805, + "step": 15612 + }, + { + "epoch": 4.82, + "learning_rate": 1.7752651142633145e-05, + "loss": 0.2634, + "step": 15613 + }, + { + "epoch": 4.82, + "learning_rate": 1.775233524027617e-05, + "loss": 0.2593, + "step": 15614 + }, + { + "epoch": 4.82, + "learning_rate": 1.775201931852919e-05, + "loss": 0.255, + "step": 15615 + }, + { + "epoch": 4.82, + "learning_rate": 1.7751703377392995e-05, + "loss": 0.2826, + "step": 15616 + }, + { + "epoch": 4.82, + "learning_rate": 1.7751387416868378e-05, + "loss": 0.2799, + "step": 15617 + }, + { + "epoch": 4.82, + "learning_rate": 1.7751071436956126e-05, + "loss": 0.2585, + "step": 15618 + }, + { + "epoch": 4.82, + "learning_rate": 1.775075543765703e-05, + "loss": 0.2598, + "step": 15619 + }, + { + "epoch": 4.82, + "learning_rate": 1.7750439418971883e-05, + "loss": 0.2635, + "step": 15620 + }, + { + "epoch": 4.82, + "learning_rate": 1.775012338090147e-05, + "loss": 0.2641, + "step": 15621 + }, + { + "epoch": 4.82, + "learning_rate": 1.774980732344659e-05, + "loss": 0.245, + "step": 15622 + }, + { + "epoch": 4.82, + "learning_rate": 1.7749491246608027e-05, + "loss": 0.2728, + "step": 15623 + }, + { + "epoch": 4.83, + "learning_rate": 1.774917515038657e-05, + "loss": 0.2497, + "step": 15624 + }, + { + "epoch": 4.83, + "learning_rate": 1.7748859034783015e-05, + "loss": 0.2492, + "step": 15625 + }, + { + "epoch": 4.83, + "learning_rate": 1.774854289979815e-05, + "loss": 0.2567, + "step": 15626 + }, + { + "epoch": 4.83, + "learning_rate": 1.7748226745432763e-05, + "loss": 0.2545, + "step": 15627 + }, + { + "epoch": 4.83, + "learning_rate": 1.774791057168765e-05, + "loss": 0.2511, + "step": 15628 + }, + { + "epoch": 4.83, + "learning_rate": 1.77475943785636e-05, + "loss": 0.2793, + "step": 15629 + }, + { + "epoch": 4.83, + "learning_rate": 1.7747278166061404e-05, + "loss": 0.2341, + "step": 15630 + }, + { + "epoch": 4.83, + "learning_rate": 1.774696193418185e-05, + "loss": 0.2602, + "step": 15631 + }, + { + "epoch": 4.83, + "learning_rate": 1.774664568292573e-05, + "loss": 0.2819, + "step": 15632 + }, + { + "epoch": 4.83, + "learning_rate": 1.7746329412293842e-05, + "loss": 0.2572, + "step": 15633 + }, + { + "epoch": 4.83, + "learning_rate": 1.7746013122286968e-05, + "loss": 0.2562, + "step": 15634 + }, + { + "epoch": 4.83, + "learning_rate": 1.7745696812905903e-05, + "loss": 0.2529, + "step": 15635 + }, + { + "epoch": 4.83, + "learning_rate": 1.7745380484151435e-05, + "loss": 0.2573, + "step": 15636 + }, + { + "epoch": 4.83, + "learning_rate": 1.7745064136024362e-05, + "loss": 0.2574, + "step": 15637 + }, + { + "epoch": 4.83, + "learning_rate": 1.7744747768525466e-05, + "loss": 0.2696, + "step": 15638 + }, + { + "epoch": 4.83, + "learning_rate": 1.7744431381655547e-05, + "loss": 0.2777, + "step": 15639 + }, + { + "epoch": 4.83, + "learning_rate": 1.7744114975415393e-05, + "loss": 0.2747, + "step": 15640 + }, + { + "epoch": 4.83, + "learning_rate": 1.7743798549805792e-05, + "loss": 0.2767, + "step": 15641 + }, + { + "epoch": 4.83, + "learning_rate": 1.7743482104827542e-05, + "loss": 0.2685, + "step": 15642 + }, + { + "epoch": 4.83, + "learning_rate": 1.774316564048143e-05, + "loss": 0.2474, + "step": 15643 + }, + { + "epoch": 4.83, + "learning_rate": 1.7742849156768244e-05, + "loss": 0.2771, + "step": 15644 + }, + { + "epoch": 4.83, + "learning_rate": 1.7742532653688786e-05, + "loss": 0.2588, + "step": 15645 + }, + { + "epoch": 4.83, + "learning_rate": 1.7742216131243837e-05, + "loss": 0.2655, + "step": 15646 + }, + { + "epoch": 4.83, + "learning_rate": 1.7741899589434196e-05, + "loss": 0.2673, + "step": 15647 + }, + { + "epoch": 4.83, + "learning_rate": 1.774158302826065e-05, + "loss": 0.289, + "step": 15648 + }, + { + "epoch": 4.83, + "learning_rate": 1.7741266447723997e-05, + "loss": 0.2635, + "step": 15649 + }, + { + "epoch": 4.83, + "learning_rate": 1.7740949847825024e-05, + "loss": 0.2548, + "step": 15650 + }, + { + "epoch": 4.83, + "learning_rate": 1.774063322856452e-05, + "loss": 0.2552, + "step": 15651 + }, + { + "epoch": 4.83, + "learning_rate": 1.7740316589943283e-05, + "loss": 0.2366, + "step": 15652 + }, + { + "epoch": 4.83, + "learning_rate": 1.7739999931962102e-05, + "loss": 0.2545, + "step": 15653 + }, + { + "epoch": 4.83, + "learning_rate": 1.773968325462177e-05, + "loss": 0.2738, + "step": 15654 + }, + { + "epoch": 4.83, + "learning_rate": 1.7739366557923078e-05, + "loss": 0.2731, + "step": 15655 + }, + { + "epoch": 4.83, + "learning_rate": 1.7739049841866817e-05, + "loss": 0.2747, + "step": 15656 + }, + { + "epoch": 4.84, + "learning_rate": 1.773873310645378e-05, + "loss": 0.2589, + "step": 15657 + }, + { + "epoch": 4.84, + "learning_rate": 1.7738416351684763e-05, + "loss": 0.2612, + "step": 15658 + }, + { + "epoch": 4.84, + "learning_rate": 1.7738099577560555e-05, + "loss": 0.2527, + "step": 15659 + }, + { + "epoch": 4.84, + "learning_rate": 1.773778278408195e-05, + "loss": 0.2524, + "step": 15660 + }, + { + "epoch": 4.84, + "learning_rate": 1.7737465971249738e-05, + "loss": 0.2699, + "step": 15661 + }, + { + "epoch": 4.84, + "learning_rate": 1.773714913906471e-05, + "loss": 0.2783, + "step": 15662 + }, + { + "epoch": 4.84, + "learning_rate": 1.7736832287527662e-05, + "loss": 0.2777, + "step": 15663 + }, + { + "epoch": 4.84, + "learning_rate": 1.7736515416639386e-05, + "loss": 0.2646, + "step": 15664 + }, + { + "epoch": 4.84, + "learning_rate": 1.7736198526400676e-05, + "loss": 0.2655, + "step": 15665 + }, + { + "epoch": 4.84, + "learning_rate": 1.7735881616812318e-05, + "loss": 0.2746, + "step": 15666 + }, + { + "epoch": 4.84, + "learning_rate": 1.7735564687875112e-05, + "loss": 0.2652, + "step": 15667 + }, + { + "epoch": 4.84, + "learning_rate": 1.7735247739589848e-05, + "loss": 0.2478, + "step": 15668 + }, + { + "epoch": 4.84, + "learning_rate": 1.7734930771957314e-05, + "loss": 0.2729, + "step": 15669 + }, + { + "epoch": 4.84, + "learning_rate": 1.773461378497831e-05, + "loss": 0.2618, + "step": 15670 + }, + { + "epoch": 4.84, + "learning_rate": 1.773429677865363e-05, + "loss": 0.2757, + "step": 15671 + }, + { + "epoch": 4.84, + "learning_rate": 1.773397975298406e-05, + "loss": 0.2635, + "step": 15672 + }, + { + "epoch": 4.84, + "learning_rate": 1.7733662707970397e-05, + "loss": 0.2641, + "step": 15673 + }, + { + "epoch": 4.84, + "learning_rate": 1.7733345643613433e-05, + "loss": 0.2667, + "step": 15674 + }, + { + "epoch": 4.84, + "learning_rate": 1.773302855991396e-05, + "loss": 0.262, + "step": 15675 + }, + { + "epoch": 4.84, + "learning_rate": 1.7732711456872774e-05, + "loss": 0.2666, + "step": 15676 + }, + { + "epoch": 4.84, + "learning_rate": 1.7732394334490665e-05, + "loss": 0.2717, + "step": 15677 + }, + { + "epoch": 4.84, + "learning_rate": 1.7732077192768425e-05, + "loss": 0.2455, + "step": 15678 + }, + { + "epoch": 4.84, + "learning_rate": 1.7731760031706855e-05, + "loss": 0.2698, + "step": 15679 + }, + { + "epoch": 4.84, + "learning_rate": 1.7731442851306736e-05, + "loss": 0.2792, + "step": 15680 + }, + { + "epoch": 4.84, + "learning_rate": 1.7731125651568875e-05, + "loss": 0.2571, + "step": 15681 + }, + { + "epoch": 4.84, + "learning_rate": 1.773080843249406e-05, + "loss": 0.2515, + "step": 15682 + }, + { + "epoch": 4.84, + "learning_rate": 1.7730491194083076e-05, + "loss": 0.2692, + "step": 15683 + }, + { + "epoch": 4.84, + "learning_rate": 1.7730173936336727e-05, + "loss": 0.2745, + "step": 15684 + }, + { + "epoch": 4.84, + "learning_rate": 1.7729856659255803e-05, + "loss": 0.2813, + "step": 15685 + }, + { + "epoch": 4.84, + "learning_rate": 1.77295393628411e-05, + "loss": 0.2875, + "step": 15686 + }, + { + "epoch": 4.84, + "learning_rate": 1.7729222047093405e-05, + "loss": 0.2862, + "step": 15687 + }, + { + "epoch": 4.84, + "learning_rate": 1.7728904712013517e-05, + "loss": 0.2564, + "step": 15688 + }, + { + "epoch": 4.85, + "learning_rate": 1.772858735760223e-05, + "loss": 0.2488, + "step": 15689 + }, + { + "epoch": 4.85, + "learning_rate": 1.7728269983860335e-05, + "loss": 0.2558, + "step": 15690 + }, + { + "epoch": 4.85, + "learning_rate": 1.7727952590788627e-05, + "loss": 0.2456, + "step": 15691 + }, + { + "epoch": 4.85, + "learning_rate": 1.7727635178387902e-05, + "loss": 0.261, + "step": 15692 + }, + { + "epoch": 4.85, + "learning_rate": 1.772731774665895e-05, + "loss": 0.269, + "step": 15693 + }, + { + "epoch": 4.85, + "learning_rate": 1.772700029560257e-05, + "loss": 0.255, + "step": 15694 + }, + { + "epoch": 4.85, + "learning_rate": 1.7726682825219553e-05, + "loss": 0.264, + "step": 15695 + }, + { + "epoch": 4.85, + "learning_rate": 1.7726365335510687e-05, + "loss": 0.2584, + "step": 15696 + }, + { + "epoch": 4.85, + "learning_rate": 1.7726047826476777e-05, + "loss": 0.2676, + "step": 15697 + }, + { + "epoch": 4.85, + "learning_rate": 1.772573029811861e-05, + "loss": 0.2616, + "step": 15698 + }, + { + "epoch": 4.85, + "learning_rate": 1.7725412750436986e-05, + "loss": 0.2671, + "step": 15699 + }, + { + "epoch": 4.85, + "learning_rate": 1.7725095183432693e-05, + "loss": 0.2988, + "step": 15700 + }, + { + "epoch": 4.85, + "learning_rate": 1.772477759710653e-05, + "loss": 0.2868, + "step": 15701 + }, + { + "epoch": 4.85, + "learning_rate": 1.7724459991459286e-05, + "loss": 0.2368, + "step": 15702 + }, + { + "epoch": 4.85, + "learning_rate": 1.772414236649176e-05, + "loss": 0.2582, + "step": 15703 + }, + { + "epoch": 4.85, + "learning_rate": 1.7723824722204747e-05, + "loss": 0.2616, + "step": 15704 + }, + { + "epoch": 4.85, + "learning_rate": 1.772350705859904e-05, + "loss": 0.2673, + "step": 15705 + }, + { + "epoch": 4.85, + "learning_rate": 1.772318937567543e-05, + "loss": 0.2805, + "step": 15706 + }, + { + "epoch": 4.85, + "learning_rate": 1.7722871673434717e-05, + "loss": 0.2444, + "step": 15707 + }, + { + "epoch": 4.85, + "learning_rate": 1.772255395187769e-05, + "loss": 0.2656, + "step": 15708 + }, + { + "epoch": 4.85, + "learning_rate": 1.772223621100515e-05, + "loss": 0.261, + "step": 15709 + }, + { + "epoch": 4.85, + "learning_rate": 1.772191845081789e-05, + "loss": 0.2701, + "step": 15710 + }, + { + "epoch": 4.85, + "learning_rate": 1.77216006713167e-05, + "loss": 0.2606, + "step": 15711 + }, + { + "epoch": 4.85, + "learning_rate": 1.772128287250238e-05, + "loss": 0.2746, + "step": 15712 + }, + { + "epoch": 4.85, + "learning_rate": 1.7720965054375723e-05, + "loss": 0.2621, + "step": 15713 + }, + { + "epoch": 4.85, + "learning_rate": 1.7720647216937528e-05, + "loss": 0.2736, + "step": 15714 + }, + { + "epoch": 4.85, + "learning_rate": 1.772032936018858e-05, + "loss": 0.2511, + "step": 15715 + }, + { + "epoch": 4.85, + "learning_rate": 1.7720011484129684e-05, + "loss": 0.2566, + "step": 15716 + }, + { + "epoch": 4.85, + "learning_rate": 1.771969358876163e-05, + "loss": 0.2606, + "step": 15717 + }, + { + "epoch": 4.85, + "learning_rate": 1.7719375674085215e-05, + "loss": 0.248, + "step": 15718 + }, + { + "epoch": 4.85, + "learning_rate": 1.7719057740101235e-05, + "loss": 0.2652, + "step": 15719 + }, + { + "epoch": 4.85, + "learning_rate": 1.771873978681048e-05, + "loss": 0.2629, + "step": 15720 + }, + { + "epoch": 4.86, + "learning_rate": 1.771842181421375e-05, + "loss": 0.2595, + "step": 15721 + }, + { + "epoch": 4.86, + "learning_rate": 1.771810382231184e-05, + "loss": 0.2566, + "step": 15722 + }, + { + "epoch": 4.86, + "learning_rate": 1.7717785811105547e-05, + "loss": 0.2391, + "step": 15723 + }, + { + "epoch": 4.86, + "learning_rate": 1.771746778059566e-05, + "loss": 0.2443, + "step": 15724 + }, + { + "epoch": 4.86, + "learning_rate": 1.7717149730782982e-05, + "loss": 0.2497, + "step": 15725 + }, + { + "epoch": 4.86, + "learning_rate": 1.7716831661668302e-05, + "loss": 0.2559, + "step": 15726 + }, + { + "epoch": 4.86, + "learning_rate": 1.771651357325242e-05, + "loss": 0.2681, + "step": 15727 + }, + { + "epoch": 4.86, + "learning_rate": 1.771619546553613e-05, + "loss": 0.2807, + "step": 15728 + }, + { + "epoch": 4.86, + "learning_rate": 1.771587733852023e-05, + "loss": 0.2731, + "step": 15729 + }, + { + "epoch": 4.86, + "learning_rate": 1.7715559192205513e-05, + "loss": 0.2789, + "step": 15730 + }, + { + "epoch": 4.86, + "learning_rate": 1.771524102659277e-05, + "loss": 0.2613, + "step": 15731 + }, + { + "epoch": 4.86, + "learning_rate": 1.7714922841682808e-05, + "loss": 0.282, + "step": 15732 + }, + { + "epoch": 4.86, + "learning_rate": 1.7714604637476412e-05, + "loss": 0.2866, + "step": 15733 + }, + { + "epoch": 4.86, + "learning_rate": 1.7714286413974386e-05, + "loss": 0.2482, + "step": 15734 + }, + { + "epoch": 4.86, + "learning_rate": 1.771396817117752e-05, + "loss": 0.2572, + "step": 15735 + }, + { + "epoch": 4.86, + "learning_rate": 1.7713649909086615e-05, + "loss": 0.2661, + "step": 15736 + }, + { + "epoch": 4.86, + "learning_rate": 1.7713331627702466e-05, + "loss": 0.2675, + "step": 15737 + }, + { + "epoch": 4.86, + "learning_rate": 1.771301332702587e-05, + "loss": 0.2669, + "step": 15738 + }, + { + "epoch": 4.86, + "learning_rate": 1.771269500705761e-05, + "loss": 0.2572, + "step": 15739 + }, + { + "epoch": 4.86, + "learning_rate": 1.7712376667798503e-05, + "loss": 0.2512, + "step": 15740 + }, + { + "epoch": 4.86, + "learning_rate": 1.771205830924933e-05, + "loss": 0.2538, + "step": 15741 + }, + { + "epoch": 4.86, + "learning_rate": 1.7711739931410895e-05, + "loss": 0.2724, + "step": 15742 + }, + { + "epoch": 4.86, + "learning_rate": 1.7711421534283994e-05, + "loss": 0.2453, + "step": 15743 + }, + { + "epoch": 4.86, + "learning_rate": 1.771110311786942e-05, + "loss": 0.2551, + "step": 15744 + }, + { + "epoch": 4.86, + "learning_rate": 1.771078468216797e-05, + "loss": 0.252, + "step": 15745 + }, + { + "epoch": 4.86, + "learning_rate": 1.771046622718044e-05, + "loss": 0.2412, + "step": 15746 + }, + { + "epoch": 4.86, + "learning_rate": 1.771014775290763e-05, + "loss": 0.2626, + "step": 15747 + }, + { + "epoch": 4.86, + "learning_rate": 1.7709829259350332e-05, + "loss": 0.2724, + "step": 15748 + }, + { + "epoch": 4.86, + "learning_rate": 1.7709510746509345e-05, + "loss": 0.2474, + "step": 15749 + }, + { + "epoch": 4.86, + "learning_rate": 1.7709192214385467e-05, + "loss": 0.2625, + "step": 15750 + }, + { + "epoch": 4.86, + "learning_rate": 1.770887366297949e-05, + "loss": 0.2774, + "step": 15751 + }, + { + "epoch": 4.86, + "learning_rate": 1.7708555092292217e-05, + "loss": 0.2848, + "step": 15752 + }, + { + "epoch": 4.86, + "learning_rate": 1.7708236502324442e-05, + "loss": 0.259, + "step": 15753 + }, + { + "epoch": 4.87, + "learning_rate": 1.770791789307696e-05, + "loss": 0.2654, + "step": 15754 + }, + { + "epoch": 4.87, + "learning_rate": 1.770759926455057e-05, + "loss": 0.2579, + "step": 15755 + }, + { + "epoch": 4.87, + "learning_rate": 1.770728061674607e-05, + "loss": 0.2434, + "step": 15756 + }, + { + "epoch": 4.87, + "learning_rate": 1.7706961949664255e-05, + "loss": 0.2599, + "step": 15757 + }, + { + "epoch": 4.87, + "learning_rate": 1.770664326330592e-05, + "loss": 0.2707, + "step": 15758 + }, + { + "epoch": 4.87, + "learning_rate": 1.7706324557671865e-05, + "loss": 0.2672, + "step": 15759 + }, + { + "epoch": 4.87, + "learning_rate": 1.7706005832762888e-05, + "loss": 0.2757, + "step": 15760 + }, + { + "epoch": 4.87, + "learning_rate": 1.7705687088579785e-05, + "loss": 0.2702, + "step": 15761 + }, + { + "epoch": 4.87, + "learning_rate": 1.7705368325123352e-05, + "loss": 0.2491, + "step": 15762 + }, + { + "epoch": 4.87, + "learning_rate": 1.770504954239439e-05, + "loss": 0.262, + "step": 15763 + }, + { + "epoch": 4.87, + "learning_rate": 1.7704730740393693e-05, + "loss": 0.2544, + "step": 15764 + }, + { + "epoch": 4.87, + "learning_rate": 1.7704411919122057e-05, + "loss": 0.2646, + "step": 15765 + }, + { + "epoch": 4.87, + "learning_rate": 1.7704093078580283e-05, + "loss": 0.2684, + "step": 15766 + }, + { + "epoch": 4.87, + "learning_rate": 1.770377421876917e-05, + "loss": 0.2482, + "step": 15767 + }, + { + "epoch": 4.87, + "learning_rate": 1.7703455339689507e-05, + "loss": 0.2481, + "step": 15768 + }, + { + "epoch": 4.87, + "learning_rate": 1.77031364413421e-05, + "loss": 0.2677, + "step": 15769 + }, + { + "epoch": 4.87, + "learning_rate": 1.7702817523727745e-05, + "loss": 0.271, + "step": 15770 + }, + { + "epoch": 4.87, + "learning_rate": 1.7702498586847238e-05, + "loss": 0.248, + "step": 15771 + }, + { + "epoch": 4.87, + "learning_rate": 1.7702179630701373e-05, + "loss": 0.2531, + "step": 15772 + }, + { + "epoch": 4.87, + "learning_rate": 1.7701860655290957e-05, + "loss": 0.2837, + "step": 15773 + }, + { + "epoch": 4.87, + "learning_rate": 1.770154166061678e-05, + "loss": 0.2519, + "step": 15774 + }, + { + "epoch": 4.87, + "learning_rate": 1.7701222646679643e-05, + "loss": 0.2698, + "step": 15775 + }, + { + "epoch": 4.87, + "learning_rate": 1.7700903613480346e-05, + "loss": 0.2529, + "step": 15776 + }, + { + "epoch": 4.87, + "learning_rate": 1.7700584561019683e-05, + "loss": 0.267, + "step": 15777 + }, + { + "epoch": 4.87, + "learning_rate": 1.7700265489298453e-05, + "loss": 0.2762, + "step": 15778 + }, + { + "epoch": 4.87, + "learning_rate": 1.7699946398317456e-05, + "loss": 0.268, + "step": 15779 + }, + { + "epoch": 4.87, + "learning_rate": 1.7699627288077487e-05, + "loss": 0.2808, + "step": 15780 + }, + { + "epoch": 4.87, + "learning_rate": 1.7699308158579347e-05, + "loss": 0.2688, + "step": 15781 + }, + { + "epoch": 4.87, + "learning_rate": 1.769898900982383e-05, + "loss": 0.2683, + "step": 15782 + }, + { + "epoch": 4.87, + "learning_rate": 1.769866984181174e-05, + "loss": 0.2562, + "step": 15783 + }, + { + "epoch": 4.87, + "learning_rate": 1.7698350654543873e-05, + "loss": 0.2568, + "step": 15784 + }, + { + "epoch": 4.87, + "learning_rate": 1.7698031448021025e-05, + "loss": 0.2623, + "step": 15785 + }, + { + "epoch": 4.88, + "learning_rate": 1.7697712222243998e-05, + "loss": 0.2711, + "step": 15786 + }, + { + "epoch": 4.88, + "learning_rate": 1.769739297721359e-05, + "loss": 0.2613, + "step": 15787 + }, + { + "epoch": 4.88, + "learning_rate": 1.7697073712930596e-05, + "loss": 0.2738, + "step": 15788 + }, + { + "epoch": 4.88, + "learning_rate": 1.7696754429395815e-05, + "loss": 0.2823, + "step": 15789 + }, + { + "epoch": 4.88, + "learning_rate": 1.769643512661005e-05, + "loss": 0.2587, + "step": 15790 + }, + { + "epoch": 4.88, + "learning_rate": 1.7696115804574095e-05, + "loss": 0.2886, + "step": 15791 + }, + { + "epoch": 4.88, + "learning_rate": 1.7695796463288753e-05, + "loss": 0.2776, + "step": 15792 + }, + { + "epoch": 4.88, + "learning_rate": 1.7695477102754818e-05, + "loss": 0.2271, + "step": 15793 + }, + { + "epoch": 4.88, + "learning_rate": 1.7695157722973095e-05, + "loss": 0.2691, + "step": 15794 + }, + { + "epoch": 4.88, + "learning_rate": 1.7694838323944375e-05, + "loss": 0.2439, + "step": 15795 + }, + { + "epoch": 4.88, + "learning_rate": 1.7694518905669468e-05, + "loss": 0.2535, + "step": 15796 + }, + { + "epoch": 4.88, + "learning_rate": 1.769419946814916e-05, + "loss": 0.2716, + "step": 15797 + }, + { + "epoch": 4.88, + "learning_rate": 1.7693880011384254e-05, + "loss": 0.249, + "step": 15798 + }, + { + "epoch": 4.88, + "learning_rate": 1.7693560535375553e-05, + "loss": 0.2724, + "step": 15799 + }, + { + "epoch": 4.88, + "learning_rate": 1.7693241040123857e-05, + "loss": 0.2621, + "step": 15800 + }, + { + "epoch": 4.88, + "learning_rate": 1.7692921525629957e-05, + "loss": 0.2647, + "step": 15801 + }, + { + "epoch": 4.88, + "learning_rate": 1.769260199189466e-05, + "loss": 0.2693, + "step": 15802 + }, + { + "epoch": 4.88, + "learning_rate": 1.7692282438918762e-05, + "loss": 0.2497, + "step": 15803 + }, + { + "epoch": 4.88, + "learning_rate": 1.769196286670306e-05, + "loss": 0.2502, + "step": 15804 + }, + { + "epoch": 4.88, + "learning_rate": 1.769164327524836e-05, + "loss": 0.2649, + "step": 15805 + }, + { + "epoch": 4.88, + "learning_rate": 1.7691323664555454e-05, + "loss": 0.2572, + "step": 15806 + }, + { + "epoch": 4.88, + "learning_rate": 1.7691004034625146e-05, + "loss": 0.2734, + "step": 15807 + }, + { + "epoch": 4.88, + "learning_rate": 1.7690684385458236e-05, + "loss": 0.2751, + "step": 15808 + }, + { + "epoch": 4.88, + "learning_rate": 1.769036471705552e-05, + "loss": 0.2629, + "step": 15809 + }, + { + "epoch": 4.88, + "learning_rate": 1.7690045029417798e-05, + "loss": 0.2563, + "step": 15810 + }, + { + "epoch": 4.88, + "learning_rate": 1.7689725322545873e-05, + "loss": 0.284, + "step": 15811 + }, + { + "epoch": 4.88, + "learning_rate": 1.768940559644054e-05, + "loss": 0.2626, + "step": 15812 + }, + { + "epoch": 4.88, + "learning_rate": 1.7689085851102604e-05, + "loss": 0.2579, + "step": 15813 + }, + { + "epoch": 4.88, + "learning_rate": 1.768876608653286e-05, + "loss": 0.2496, + "step": 15814 + }, + { + "epoch": 4.88, + "learning_rate": 1.768844630273211e-05, + "loss": 0.2536, + "step": 15815 + }, + { + "epoch": 4.88, + "learning_rate": 1.7688126499701153e-05, + "loss": 0.2728, + "step": 15816 + }, + { + "epoch": 4.88, + "learning_rate": 1.7687806677440793e-05, + "loss": 0.2666, + "step": 15817 + }, + { + "epoch": 4.89, + "learning_rate": 1.7687486835951823e-05, + "loss": 0.2731, + "step": 15818 + }, + { + "epoch": 4.89, + "learning_rate": 1.7687166975235046e-05, + "loss": 0.2538, + "step": 15819 + }, + { + "epoch": 4.89, + "learning_rate": 1.768684709529126e-05, + "loss": 0.264, + "step": 15820 + }, + { + "epoch": 4.89, + "learning_rate": 1.768652719612127e-05, + "loss": 0.2606, + "step": 15821 + }, + { + "epoch": 4.89, + "learning_rate": 1.768620727772588e-05, + "loss": 0.2813, + "step": 15822 + }, + { + "epoch": 4.89, + "learning_rate": 1.7685887340105877e-05, + "loss": 0.2849, + "step": 15823 + }, + { + "epoch": 4.89, + "learning_rate": 1.7685567383262068e-05, + "loss": 0.2376, + "step": 15824 + }, + { + "epoch": 4.89, + "learning_rate": 1.7685247407195253e-05, + "loss": 0.2685, + "step": 15825 + }, + { + "epoch": 4.89, + "learning_rate": 1.7684927411906235e-05, + "loss": 0.2655, + "step": 15826 + }, + { + "epoch": 4.89, + "learning_rate": 1.768460739739581e-05, + "loss": 0.2461, + "step": 15827 + }, + { + "epoch": 4.89, + "learning_rate": 1.768428736366478e-05, + "loss": 0.2779, + "step": 15828 + }, + { + "epoch": 4.89, + "learning_rate": 1.7683967310713947e-05, + "loss": 0.2836, + "step": 15829 + }, + { + "epoch": 4.89, + "learning_rate": 1.768364723854411e-05, + "loss": 0.2576, + "step": 15830 + }, + { + "epoch": 4.89, + "learning_rate": 1.768332714715607e-05, + "loss": 0.2601, + "step": 15831 + }, + { + "epoch": 4.89, + "learning_rate": 1.768300703655063e-05, + "loss": 0.2683, + "step": 15832 + }, + { + "epoch": 4.89, + "learning_rate": 1.768268690672858e-05, + "loss": 0.2869, + "step": 15833 + }, + { + "epoch": 4.89, + "learning_rate": 1.7682366757690737e-05, + "loss": 0.2608, + "step": 15834 + }, + { + "epoch": 4.89, + "learning_rate": 1.768204658943789e-05, + "loss": 0.2668, + "step": 15835 + }, + { + "epoch": 4.89, + "learning_rate": 1.7681726401970844e-05, + "loss": 0.2623, + "step": 15836 + }, + { + "epoch": 4.89, + "learning_rate": 1.7681406195290398e-05, + "loss": 0.2673, + "step": 15837 + }, + { + "epoch": 4.89, + "learning_rate": 1.7681085969397354e-05, + "loss": 0.2673, + "step": 15838 + }, + { + "epoch": 4.89, + "learning_rate": 1.7680765724292516e-05, + "loss": 0.2557, + "step": 15839 + }, + { + "epoch": 4.89, + "learning_rate": 1.768044545997668e-05, + "loss": 0.2547, + "step": 15840 + }, + { + "epoch": 4.89, + "learning_rate": 1.768012517645065e-05, + "loss": 0.2706, + "step": 15841 + }, + { + "epoch": 4.89, + "learning_rate": 1.7679804873715224e-05, + "loss": 0.2581, + "step": 15842 + }, + { + "epoch": 4.89, + "learning_rate": 1.7679484551771206e-05, + "loss": 0.2615, + "step": 15843 + }, + { + "epoch": 4.89, + "learning_rate": 1.76791642106194e-05, + "loss": 0.2691, + "step": 15844 + }, + { + "epoch": 4.89, + "learning_rate": 1.7678843850260602e-05, + "loss": 0.2601, + "step": 15845 + }, + { + "epoch": 4.89, + "learning_rate": 1.7678523470695612e-05, + "loss": 0.254, + "step": 15846 + }, + { + "epoch": 4.89, + "learning_rate": 1.7678203071925235e-05, + "loss": 0.2656, + "step": 15847 + }, + { + "epoch": 4.89, + "learning_rate": 1.7677882653950272e-05, + "loss": 0.2616, + "step": 15848 + }, + { + "epoch": 4.89, + "learning_rate": 1.7677562216771528e-05, + "loss": 0.2619, + "step": 15849 + }, + { + "epoch": 4.89, + "learning_rate": 1.7677241760389798e-05, + "loss": 0.2569, + "step": 15850 + }, + { + "epoch": 4.9, + "learning_rate": 1.7676921284805885e-05, + "loss": 0.2914, + "step": 15851 + }, + { + "epoch": 4.9, + "learning_rate": 1.7676600790020592e-05, + "loss": 0.2649, + "step": 15852 + }, + { + "epoch": 4.9, + "learning_rate": 1.7676280276034723e-05, + "loss": 0.2665, + "step": 15853 + }, + { + "epoch": 4.9, + "learning_rate": 1.7675959742849077e-05, + "loss": 0.2778, + "step": 15854 + }, + { + "epoch": 4.9, + "learning_rate": 1.767563919046445e-05, + "loss": 0.2704, + "step": 15855 + }, + { + "epoch": 4.9, + "learning_rate": 1.7675318618881654e-05, + "loss": 0.2696, + "step": 15856 + }, + { + "epoch": 4.9, + "learning_rate": 1.7674998028101487e-05, + "loss": 0.2507, + "step": 15857 + }, + { + "epoch": 4.9, + "learning_rate": 1.7674677418124745e-05, + "loss": 0.286, + "step": 15858 + }, + { + "epoch": 4.9, + "learning_rate": 1.767435678895224e-05, + "loss": 0.2607, + "step": 15859 + }, + { + "epoch": 4.9, + "learning_rate": 1.7674036140584768e-05, + "loss": 0.2686, + "step": 15860 + }, + { + "epoch": 4.9, + "learning_rate": 1.767371547302313e-05, + "loss": 0.2551, + "step": 15861 + }, + { + "epoch": 4.9, + "learning_rate": 1.767339478626813e-05, + "loss": 0.2794, + "step": 15862 + }, + { + "epoch": 4.9, + "learning_rate": 1.7673074080320574e-05, + "loss": 0.2699, + "step": 15863 + }, + { + "epoch": 4.9, + "learning_rate": 1.7672753355181256e-05, + "loss": 0.2507, + "step": 15864 + }, + { + "epoch": 4.9, + "learning_rate": 1.7672432610850984e-05, + "loss": 0.2536, + "step": 15865 + }, + { + "epoch": 4.9, + "learning_rate": 1.767211184733056e-05, + "loss": 0.2774, + "step": 15866 + }, + { + "epoch": 4.9, + "learning_rate": 1.7671791064620785e-05, + "loss": 0.2569, + "step": 15867 + }, + { + "epoch": 4.9, + "learning_rate": 1.7671470262722457e-05, + "loss": 0.2711, + "step": 15868 + }, + { + "epoch": 4.9, + "learning_rate": 1.7671149441636387e-05, + "loss": 0.2548, + "step": 15869 + }, + { + "epoch": 4.9, + "learning_rate": 1.7670828601363374e-05, + "loss": 0.2329, + "step": 15870 + }, + { + "epoch": 4.9, + "learning_rate": 1.7670507741904214e-05, + "loss": 0.2488, + "step": 15871 + }, + { + "epoch": 4.9, + "learning_rate": 1.767018686325972e-05, + "loss": 0.2714, + "step": 15872 + }, + { + "epoch": 4.9, + "learning_rate": 1.7669865965430687e-05, + "loss": 0.2535, + "step": 15873 + }, + { + "epoch": 4.9, + "learning_rate": 1.7669545048417922e-05, + "loss": 0.2609, + "step": 15874 + }, + { + "epoch": 4.9, + "learning_rate": 1.7669224112222225e-05, + "loss": 0.2505, + "step": 15875 + }, + { + "epoch": 4.9, + "learning_rate": 1.76689031568444e-05, + "loss": 0.2773, + "step": 15876 + }, + { + "epoch": 4.9, + "learning_rate": 1.766858218228525e-05, + "loss": 0.2373, + "step": 15877 + }, + { + "epoch": 4.9, + "learning_rate": 1.7668261188545578e-05, + "loss": 0.2463, + "step": 15878 + }, + { + "epoch": 4.9, + "learning_rate": 1.7667940175626186e-05, + "loss": 0.2599, + "step": 15879 + }, + { + "epoch": 4.9, + "learning_rate": 1.7667619143527875e-05, + "loss": 0.2679, + "step": 15880 + }, + { + "epoch": 4.9, + "learning_rate": 1.766729809225145e-05, + "loss": 0.2676, + "step": 15881 + }, + { + "epoch": 4.9, + "learning_rate": 1.7666977021797714e-05, + "loss": 0.2805, + "step": 15882 + }, + { + "epoch": 4.91, + "learning_rate": 1.7666655932167475e-05, + "loss": 0.2502, + "step": 15883 + }, + { + "epoch": 4.91, + "learning_rate": 1.7666334823361528e-05, + "loss": 0.2658, + "step": 15884 + }, + { + "epoch": 4.91, + "learning_rate": 1.766601369538068e-05, + "loss": 0.2631, + "step": 15885 + }, + { + "epoch": 4.91, + "learning_rate": 1.766569254822573e-05, + "loss": 0.2618, + "step": 15886 + }, + { + "epoch": 4.91, + "learning_rate": 1.7665371381897485e-05, + "loss": 0.2855, + "step": 15887 + }, + { + "epoch": 4.91, + "learning_rate": 1.7665050196396753e-05, + "loss": 0.2668, + "step": 15888 + }, + { + "epoch": 4.91, + "learning_rate": 1.766472899172433e-05, + "loss": 0.2627, + "step": 15889 + }, + { + "epoch": 4.91, + "learning_rate": 1.766440776788102e-05, + "loss": 0.2594, + "step": 15890 + }, + { + "epoch": 4.91, + "learning_rate": 1.7664086524867633e-05, + "loss": 0.2524, + "step": 15891 + }, + { + "epoch": 4.91, + "learning_rate": 1.766376526268496e-05, + "loss": 0.2623, + "step": 15892 + }, + { + "epoch": 4.91, + "learning_rate": 1.766344398133382e-05, + "loss": 0.2725, + "step": 15893 + }, + { + "epoch": 4.91, + "learning_rate": 1.7663122680815007e-05, + "loss": 0.2499, + "step": 15894 + }, + { + "epoch": 4.91, + "learning_rate": 1.7662801361129325e-05, + "loss": 0.27, + "step": 15895 + }, + { + "epoch": 4.91, + "learning_rate": 1.766248002227758e-05, + "loss": 0.2508, + "step": 15896 + }, + { + "epoch": 4.91, + "learning_rate": 1.7662158664260574e-05, + "loss": 0.255, + "step": 15897 + }, + { + "epoch": 4.91, + "learning_rate": 1.7661837287079112e-05, + "loss": 0.2616, + "step": 15898 + }, + { + "epoch": 4.91, + "learning_rate": 1.7661515890733997e-05, + "loss": 0.2698, + "step": 15899 + }, + { + "epoch": 4.91, + "learning_rate": 1.7661194475226036e-05, + "loss": 0.2359, + "step": 15900 + }, + { + "epoch": 4.91, + "learning_rate": 1.7660873040556027e-05, + "loss": 0.2761, + "step": 15901 + }, + { + "epoch": 4.91, + "learning_rate": 1.766055158672478e-05, + "loss": 0.2604, + "step": 15902 + }, + { + "epoch": 4.91, + "learning_rate": 1.7660230113733095e-05, + "loss": 0.2615, + "step": 15903 + }, + { + "epoch": 4.91, + "learning_rate": 1.7659908621581778e-05, + "loss": 0.2543, + "step": 15904 + }, + { + "epoch": 4.91, + "learning_rate": 1.765958711027163e-05, + "loss": 0.2387, + "step": 15905 + }, + { + "epoch": 4.91, + "learning_rate": 1.765926557980346e-05, + "loss": 0.2507, + "step": 15906 + }, + { + "epoch": 4.91, + "learning_rate": 1.7658944030178068e-05, + "loss": 0.2904, + "step": 15907 + }, + { + "epoch": 4.91, + "learning_rate": 1.7658622461396262e-05, + "loss": 0.2776, + "step": 15908 + }, + { + "epoch": 4.91, + "learning_rate": 1.7658300873458844e-05, + "loss": 0.297, + "step": 15909 + }, + { + "epoch": 4.91, + "learning_rate": 1.765797926636662e-05, + "loss": 0.2541, + "step": 15910 + }, + { + "epoch": 4.91, + "learning_rate": 1.765765764012039e-05, + "loss": 0.2815, + "step": 15911 + }, + { + "epoch": 4.91, + "learning_rate": 1.765733599472096e-05, + "loss": 0.256, + "step": 15912 + }, + { + "epoch": 4.91, + "learning_rate": 1.7657014330169142e-05, + "loss": 0.2501, + "step": 15913 + }, + { + "epoch": 4.91, + "learning_rate": 1.765669264646573e-05, + "loss": 0.252, + "step": 15914 + }, + { + "epoch": 4.91, + "learning_rate": 1.7656370943611536e-05, + "loss": 0.2628, + "step": 15915 + }, + { + "epoch": 4.92, + "learning_rate": 1.7656049221607362e-05, + "loss": 0.2602, + "step": 15916 + }, + { + "epoch": 4.92, + "learning_rate": 1.765572748045401e-05, + "loss": 0.2564, + "step": 15917 + }, + { + "epoch": 4.92, + "learning_rate": 1.765540572015229e-05, + "loss": 0.2683, + "step": 15918 + }, + { + "epoch": 4.92, + "learning_rate": 1.7655083940703e-05, + "loss": 0.2736, + "step": 15919 + }, + { + "epoch": 4.92, + "learning_rate": 1.7654762142106953e-05, + "loss": 0.2711, + "step": 15920 + }, + { + "epoch": 4.92, + "learning_rate": 1.765444032436495e-05, + "loss": 0.268, + "step": 15921 + }, + { + "epoch": 4.92, + "learning_rate": 1.7654118487477792e-05, + "loss": 0.2552, + "step": 15922 + }, + { + "epoch": 4.92, + "learning_rate": 1.765379663144629e-05, + "loss": 0.2646, + "step": 15923 + }, + { + "epoch": 4.92, + "learning_rate": 1.7653474756271248e-05, + "loss": 0.251, + "step": 15924 + }, + { + "epoch": 4.92, + "learning_rate": 1.7653152861953468e-05, + "loss": 0.2756, + "step": 15925 + }, + { + "epoch": 4.92, + "learning_rate": 1.7652830948493756e-05, + "loss": 0.2644, + "step": 15926 + }, + { + "epoch": 4.92, + "learning_rate": 1.765250901589292e-05, + "loss": 0.2664, + "step": 15927 + }, + { + "epoch": 4.92, + "learning_rate": 1.765218706415176e-05, + "loss": 0.2856, + "step": 15928 + }, + { + "epoch": 4.92, + "learning_rate": 1.7651865093271084e-05, + "loss": 0.2758, + "step": 15929 + }, + { + "epoch": 4.92, + "learning_rate": 1.7651543103251703e-05, + "loss": 0.2818, + "step": 15930 + }, + { + "epoch": 4.92, + "learning_rate": 1.7651221094094416e-05, + "loss": 0.2758, + "step": 15931 + }, + { + "epoch": 4.92, + "learning_rate": 1.7650899065800024e-05, + "loss": 0.2563, + "step": 15932 + }, + { + "epoch": 4.92, + "learning_rate": 1.7650577018369343e-05, + "loss": 0.2744, + "step": 15933 + }, + { + "epoch": 4.92, + "learning_rate": 1.7650254951803174e-05, + "loss": 0.2622, + "step": 15934 + }, + { + "epoch": 4.92, + "learning_rate": 1.764993286610232e-05, + "loss": 0.2645, + "step": 15935 + }, + { + "epoch": 4.92, + "learning_rate": 1.7649610761267587e-05, + "loss": 0.2721, + "step": 15936 + }, + { + "epoch": 4.92, + "learning_rate": 1.7649288637299788e-05, + "loss": 0.2548, + "step": 15937 + }, + { + "epoch": 4.92, + "learning_rate": 1.764896649419972e-05, + "loss": 0.2551, + "step": 15938 + }, + { + "epoch": 4.92, + "learning_rate": 1.7648644331968186e-05, + "loss": 0.2738, + "step": 15939 + }, + { + "epoch": 4.92, + "learning_rate": 1.7648322150606004e-05, + "loss": 0.2571, + "step": 15940 + }, + { + "epoch": 4.92, + "learning_rate": 1.7647999950113975e-05, + "loss": 0.2507, + "step": 15941 + }, + { + "epoch": 4.92, + "learning_rate": 1.76476777304929e-05, + "loss": 0.2611, + "step": 15942 + }, + { + "epoch": 4.92, + "learning_rate": 1.764735549174359e-05, + "loss": 0.2436, + "step": 15943 + }, + { + "epoch": 4.92, + "learning_rate": 1.7647033233866846e-05, + "loss": 0.2852, + "step": 15944 + }, + { + "epoch": 4.92, + "learning_rate": 1.7646710956863477e-05, + "loss": 0.2708, + "step": 15945 + }, + { + "epoch": 4.92, + "learning_rate": 1.764638866073429e-05, + "loss": 0.2789, + "step": 15946 + }, + { + "epoch": 4.92, + "learning_rate": 1.764606634548009e-05, + "loss": 0.2757, + "step": 15947 + }, + { + "epoch": 4.93, + "learning_rate": 1.7645744011101688e-05, + "loss": 0.2576, + "step": 15948 + }, + { + "epoch": 4.93, + "learning_rate": 1.7645421657599883e-05, + "loss": 0.2711, + "step": 15949 + }, + { + "epoch": 4.93, + "learning_rate": 1.7645099284975482e-05, + "loss": 0.2742, + "step": 15950 + }, + { + "epoch": 4.93, + "learning_rate": 1.7644776893229293e-05, + "loss": 0.2572, + "step": 15951 + }, + { + "epoch": 4.93, + "learning_rate": 1.7644454482362127e-05, + "loss": 0.2453, + "step": 15952 + }, + { + "epoch": 4.93, + "learning_rate": 1.764413205237478e-05, + "loss": 0.2715, + "step": 15953 + }, + { + "epoch": 4.93, + "learning_rate": 1.7643809603268073e-05, + "loss": 0.258, + "step": 15954 + }, + { + "epoch": 4.93, + "learning_rate": 1.7643487135042797e-05, + "loss": 0.2673, + "step": 15955 + }, + { + "epoch": 4.93, + "learning_rate": 1.7643164647699768e-05, + "loss": 0.256, + "step": 15956 + }, + { + "epoch": 4.93, + "learning_rate": 1.7642842141239788e-05, + "loss": 0.2579, + "step": 15957 + }, + { + "epoch": 4.93, + "learning_rate": 1.764251961566367e-05, + "loss": 0.2686, + "step": 15958 + }, + { + "epoch": 4.93, + "learning_rate": 1.764219707097221e-05, + "loss": 0.2584, + "step": 15959 + }, + { + "epoch": 4.93, + "learning_rate": 1.764187450716623e-05, + "loss": 0.2636, + "step": 15960 + }, + { + "epoch": 4.93, + "learning_rate": 1.764155192424652e-05, + "loss": 0.2543, + "step": 15961 + }, + { + "epoch": 4.93, + "learning_rate": 1.76412293222139e-05, + "loss": 0.2635, + "step": 15962 + }, + { + "epoch": 4.93, + "learning_rate": 1.7640906701069173e-05, + "loss": 0.2658, + "step": 15963 + }, + { + "epoch": 4.93, + "learning_rate": 1.764058406081314e-05, + "loss": 0.2617, + "step": 15964 + }, + { + "epoch": 4.93, + "learning_rate": 1.764026140144661e-05, + "loss": 0.2524, + "step": 15965 + }, + { + "epoch": 4.93, + "learning_rate": 1.76399387229704e-05, + "loss": 0.2476, + "step": 15966 + }, + { + "epoch": 4.93, + "learning_rate": 1.763961602538531e-05, + "loss": 0.2724, + "step": 15967 + }, + { + "epoch": 4.93, + "learning_rate": 1.763929330869214e-05, + "loss": 0.2557, + "step": 15968 + }, + { + "epoch": 4.93, + "learning_rate": 1.763897057289171e-05, + "loss": 0.2673, + "step": 15969 + }, + { + "epoch": 4.93, + "learning_rate": 1.763864781798482e-05, + "loss": 0.2567, + "step": 15970 + }, + { + "epoch": 4.93, + "learning_rate": 1.763832504397228e-05, + "loss": 0.2379, + "step": 15971 + }, + { + "epoch": 4.93, + "learning_rate": 1.7638002250854894e-05, + "loss": 0.2735, + "step": 15972 + }, + { + "epoch": 4.93, + "learning_rate": 1.763767943863347e-05, + "loss": 0.2661, + "step": 15973 + }, + { + "epoch": 4.93, + "learning_rate": 1.7637356607308818e-05, + "loss": 0.2459, + "step": 15974 + }, + { + "epoch": 4.93, + "learning_rate": 1.7637033756881744e-05, + "loss": 0.2753, + "step": 15975 + }, + { + "epoch": 4.93, + "learning_rate": 1.7636710887353058e-05, + "loss": 0.2656, + "step": 15976 + }, + { + "epoch": 4.93, + "learning_rate": 1.7636387998723562e-05, + "loss": 0.247, + "step": 15977 + }, + { + "epoch": 4.93, + "learning_rate": 1.7636065090994066e-05, + "loss": 0.2603, + "step": 15978 + }, + { + "epoch": 4.93, + "learning_rate": 1.7635742164165383e-05, + "loss": 0.2602, + "step": 15979 + }, + { + "epoch": 4.94, + "learning_rate": 1.7635419218238313e-05, + "loss": 0.2846, + "step": 15980 + }, + { + "epoch": 4.94, + "learning_rate": 1.7635096253213668e-05, + "loss": 0.2565, + "step": 15981 + }, + { + "epoch": 4.94, + "learning_rate": 1.7634773269092253e-05, + "loss": 0.2591, + "step": 15982 + }, + { + "epoch": 4.94, + "learning_rate": 1.763445026587488e-05, + "loss": 0.266, + "step": 15983 + }, + { + "epoch": 4.94, + "learning_rate": 1.7634127243562354e-05, + "loss": 0.2488, + "step": 15984 + }, + { + "epoch": 4.94, + "learning_rate": 1.763380420215548e-05, + "loss": 0.2535, + "step": 15985 + }, + { + "epoch": 4.94, + "learning_rate": 1.763348114165507e-05, + "loss": 0.2633, + "step": 15986 + }, + { + "epoch": 4.94, + "learning_rate": 1.7633158062061936e-05, + "loss": 0.251, + "step": 15987 + }, + { + "epoch": 4.94, + "learning_rate": 1.7632834963376878e-05, + "loss": 0.2688, + "step": 15988 + }, + { + "epoch": 4.94, + "learning_rate": 1.763251184560071e-05, + "loss": 0.257, + "step": 15989 + }, + { + "epoch": 4.94, + "learning_rate": 1.7632188708734233e-05, + "loss": 0.2572, + "step": 15990 + }, + { + "epoch": 4.94, + "learning_rate": 1.7631865552778266e-05, + "loss": 0.265, + "step": 15991 + }, + { + "epoch": 4.94, + "learning_rate": 1.7631542377733608e-05, + "loss": 0.2641, + "step": 15992 + }, + { + "epoch": 4.94, + "learning_rate": 1.7631219183601073e-05, + "loss": 0.2577, + "step": 15993 + }, + { + "epoch": 4.94, + "learning_rate": 1.7630895970381467e-05, + "loss": 0.2688, + "step": 15994 + }, + { + "epoch": 4.94, + "learning_rate": 1.7630572738075593e-05, + "loss": 0.2631, + "step": 15995 + }, + { + "epoch": 4.94, + "learning_rate": 1.763024948668427e-05, + "loss": 0.2483, + "step": 15996 + }, + { + "epoch": 4.94, + "learning_rate": 1.76299262162083e-05, + "loss": 0.2632, + "step": 15997 + }, + { + "epoch": 4.94, + "learning_rate": 1.762960292664849e-05, + "loss": 0.2637, + "step": 15998 + }, + { + "epoch": 4.94, + "learning_rate": 1.7629279618005653e-05, + "loss": 0.2628, + "step": 15999 + }, + { + "epoch": 4.94, + "learning_rate": 1.76289562902806e-05, + "loss": 0.2569, + "step": 16000 + }, + { + "epoch": 4.94, + "learning_rate": 1.7628632943474133e-05, + "loss": 0.2725, + "step": 16001 + }, + { + "epoch": 4.94, + "learning_rate": 1.7628309577587064e-05, + "loss": 0.2788, + "step": 16002 + }, + { + "epoch": 4.94, + "learning_rate": 1.76279861926202e-05, + "loss": 0.246, + "step": 16003 + }, + { + "epoch": 4.94, + "learning_rate": 1.7627662788574355e-05, + "loss": 0.2536, + "step": 16004 + }, + { + "epoch": 4.94, + "learning_rate": 1.7627339365450332e-05, + "loss": 0.2527, + "step": 16005 + }, + { + "epoch": 4.94, + "learning_rate": 1.762701592324894e-05, + "loss": 0.2723, + "step": 16006 + }, + { + "epoch": 4.94, + "learning_rate": 1.7626692461970997e-05, + "loss": 0.2584, + "step": 16007 + }, + { + "epoch": 4.94, + "learning_rate": 1.7626368981617298e-05, + "loss": 0.2441, + "step": 16008 + }, + { + "epoch": 4.94, + "learning_rate": 1.762604548218866e-05, + "loss": 0.2696, + "step": 16009 + }, + { + "epoch": 4.94, + "learning_rate": 1.7625721963685895e-05, + "loss": 0.284, + "step": 16010 + }, + { + "epoch": 4.94, + "learning_rate": 1.7625398426109804e-05, + "loss": 0.2689, + "step": 16011 + }, + { + "epoch": 4.94, + "learning_rate": 1.76250748694612e-05, + "loss": 0.2565, + "step": 16012 + }, + { + "epoch": 4.95, + "learning_rate": 1.76247512937409e-05, + "loss": 0.2611, + "step": 16013 + }, + { + "epoch": 4.95, + "learning_rate": 1.76244276989497e-05, + "loss": 0.2587, + "step": 16014 + }, + { + "epoch": 4.95, + "learning_rate": 1.762410408508842e-05, + "loss": 0.2652, + "step": 16015 + }, + { + "epoch": 4.95, + "learning_rate": 1.7623780452157864e-05, + "loss": 0.2518, + "step": 16016 + }, + { + "epoch": 4.95, + "learning_rate": 1.762345680015884e-05, + "loss": 0.2784, + "step": 16017 + }, + { + "epoch": 4.95, + "learning_rate": 1.7623133129092162e-05, + "loss": 0.2795, + "step": 16018 + }, + { + "epoch": 4.95, + "learning_rate": 1.7622809438958638e-05, + "loss": 0.2932, + "step": 16019 + }, + { + "epoch": 4.95, + "learning_rate": 1.762248572975908e-05, + "loss": 0.2515, + "step": 16020 + }, + { + "epoch": 4.95, + "learning_rate": 1.762216200149429e-05, + "loss": 0.272, + "step": 16021 + }, + { + "epoch": 4.95, + "learning_rate": 1.7621838254165082e-05, + "loss": 0.2632, + "step": 16022 + }, + { + "epoch": 4.95, + "learning_rate": 1.762151448777227e-05, + "loss": 0.2726, + "step": 16023 + }, + { + "epoch": 4.95, + "learning_rate": 1.762119070231666e-05, + "loss": 0.2417, + "step": 16024 + }, + { + "epoch": 4.95, + "learning_rate": 1.762086689779906e-05, + "loss": 0.2487, + "step": 16025 + }, + { + "epoch": 4.95, + "learning_rate": 1.7620543074220286e-05, + "loss": 0.3007, + "step": 16026 + }, + { + "epoch": 4.95, + "learning_rate": 1.762021923158114e-05, + "loss": 0.2715, + "step": 16027 + }, + { + "epoch": 4.95, + "learning_rate": 1.7619895369882436e-05, + "loss": 0.2737, + "step": 16028 + }, + { + "epoch": 4.95, + "learning_rate": 1.7619571489124983e-05, + "loss": 0.2494, + "step": 16029 + }, + { + "epoch": 4.95, + "learning_rate": 1.7619247589309598e-05, + "loss": 0.2594, + "step": 16030 + }, + { + "epoch": 4.95, + "learning_rate": 1.7618923670437075e-05, + "loss": 0.2539, + "step": 16031 + }, + { + "epoch": 4.95, + "learning_rate": 1.761859973250824e-05, + "loss": 0.2556, + "step": 16032 + }, + { + "epoch": 4.95, + "learning_rate": 1.76182757755239e-05, + "loss": 0.2644, + "step": 16033 + }, + { + "epoch": 4.95, + "learning_rate": 1.761795179948486e-05, + "loss": 0.2639, + "step": 16034 + }, + { + "epoch": 4.95, + "learning_rate": 1.7617627804391936e-05, + "loss": 0.254, + "step": 16035 + }, + { + "epoch": 4.95, + "learning_rate": 1.761730379024593e-05, + "loss": 0.2631, + "step": 16036 + }, + { + "epoch": 4.95, + "learning_rate": 1.761697975704766e-05, + "loss": 0.265, + "step": 16037 + }, + { + "epoch": 4.95, + "learning_rate": 1.7616655704797935e-05, + "loss": 0.2659, + "step": 16038 + }, + { + "epoch": 4.95, + "learning_rate": 1.761633163349757e-05, + "loss": 0.2705, + "step": 16039 + }, + { + "epoch": 4.95, + "learning_rate": 1.7616007543147363e-05, + "loss": 0.2697, + "step": 16040 + }, + { + "epoch": 4.95, + "learning_rate": 1.7615683433748132e-05, + "loss": 0.2467, + "step": 16041 + }, + { + "epoch": 4.95, + "learning_rate": 1.761535930530069e-05, + "loss": 0.2616, + "step": 16042 + }, + { + "epoch": 4.95, + "learning_rate": 1.761503515780585e-05, + "loss": 0.2666, + "step": 16043 + }, + { + "epoch": 4.95, + "learning_rate": 1.7614710991264413e-05, + "loss": 0.2703, + "step": 16044 + }, + { + "epoch": 4.96, + "learning_rate": 1.7614386805677194e-05, + "loss": 0.2361, + "step": 16045 + }, + { + "epoch": 4.96, + "learning_rate": 1.761406260104501e-05, + "loss": 0.2498, + "step": 16046 + }, + { + "epoch": 4.96, + "learning_rate": 1.761373837736866e-05, + "loss": 0.2709, + "step": 16047 + }, + { + "epoch": 4.96, + "learning_rate": 1.7613414134648967e-05, + "loss": 0.273, + "step": 16048 + }, + { + "epoch": 4.96, + "learning_rate": 1.7613089872886733e-05, + "loss": 0.2647, + "step": 16049 + }, + { + "epoch": 4.96, + "learning_rate": 1.7612765592082775e-05, + "loss": 0.2549, + "step": 16050 + }, + { + "epoch": 4.96, + "learning_rate": 1.76124412922379e-05, + "loss": 0.2737, + "step": 16051 + }, + { + "epoch": 4.96, + "learning_rate": 1.7612116973352923e-05, + "loss": 0.2709, + "step": 16052 + }, + { + "epoch": 4.96, + "learning_rate": 1.761179263542865e-05, + "loss": 0.2727, + "step": 16053 + }, + { + "epoch": 4.96, + "learning_rate": 1.76114682784659e-05, + "loss": 0.2493, + "step": 16054 + }, + { + "epoch": 4.96, + "learning_rate": 1.7611143902465476e-05, + "loss": 0.264, + "step": 16055 + }, + { + "epoch": 4.96, + "learning_rate": 1.7610819507428195e-05, + "loss": 0.2643, + "step": 16056 + }, + { + "epoch": 4.96, + "learning_rate": 1.7610495093354865e-05, + "loss": 0.2623, + "step": 16057 + }, + { + "epoch": 4.96, + "learning_rate": 1.76101706602463e-05, + "loss": 0.2605, + "step": 16058 + }, + { + "epoch": 4.96, + "learning_rate": 1.7609846208103308e-05, + "loss": 0.278, + "step": 16059 + }, + { + "epoch": 4.96, + "learning_rate": 1.7609521736926703e-05, + "loss": 0.255, + "step": 16060 + }, + { + "epoch": 4.96, + "learning_rate": 1.7609197246717298e-05, + "loss": 0.2536, + "step": 16061 + }, + { + "epoch": 4.96, + "learning_rate": 1.7608872737475904e-05, + "loss": 0.2834, + "step": 16062 + }, + { + "epoch": 4.96, + "learning_rate": 1.760854820920333e-05, + "loss": 0.2595, + "step": 16063 + }, + { + "epoch": 4.96, + "learning_rate": 1.7608223661900386e-05, + "loss": 0.2871, + "step": 16064 + }, + { + "epoch": 4.96, + "learning_rate": 1.760789909556789e-05, + "loss": 0.2583, + "step": 16065 + }, + { + "epoch": 4.96, + "learning_rate": 1.760757451020665e-05, + "loss": 0.2647, + "step": 16066 + }, + { + "epoch": 4.96, + "learning_rate": 1.760724990581748e-05, + "loss": 0.2582, + "step": 16067 + }, + { + "epoch": 4.96, + "learning_rate": 1.7606925282401192e-05, + "loss": 0.247, + "step": 16068 + }, + { + "epoch": 4.96, + "learning_rate": 1.760660063995859e-05, + "loss": 0.2619, + "step": 16069 + }, + { + "epoch": 4.96, + "learning_rate": 1.76062759784905e-05, + "loss": 0.2552, + "step": 16070 + }, + { + "epoch": 4.96, + "learning_rate": 1.760595129799772e-05, + "loss": 0.2752, + "step": 16071 + }, + { + "epoch": 4.96, + "learning_rate": 1.760562659848107e-05, + "loss": 0.2488, + "step": 16072 + }, + { + "epoch": 4.96, + "learning_rate": 1.7605301879941365e-05, + "loss": 0.2564, + "step": 16073 + }, + { + "epoch": 4.96, + "learning_rate": 1.760497714237941e-05, + "loss": 0.2494, + "step": 16074 + }, + { + "epoch": 4.96, + "learning_rate": 1.760465238579602e-05, + "loss": 0.2588, + "step": 16075 + }, + { + "epoch": 4.96, + "learning_rate": 1.760432761019201e-05, + "loss": 0.2569, + "step": 16076 + }, + { + "epoch": 4.96, + "learning_rate": 1.7604002815568186e-05, + "loss": 0.264, + "step": 16077 + }, + { + "epoch": 4.97, + "learning_rate": 1.7603678001925366e-05, + "loss": 0.2758, + "step": 16078 + }, + { + "epoch": 4.97, + "learning_rate": 1.760335316926436e-05, + "loss": 0.2464, + "step": 16079 + }, + { + "epoch": 4.97, + "learning_rate": 1.7603028317585978e-05, + "loss": 0.2724, + "step": 16080 + }, + { + "epoch": 4.97, + "learning_rate": 1.7602703446891037e-05, + "loss": 0.2729, + "step": 16081 + }, + { + "epoch": 4.97, + "learning_rate": 1.7602378557180352e-05, + "loss": 0.264, + "step": 16082 + }, + { + "epoch": 4.97, + "learning_rate": 1.760205364845473e-05, + "loss": 0.2515, + "step": 16083 + }, + { + "epoch": 4.97, + "learning_rate": 1.7601728720714983e-05, + "loss": 0.2672, + "step": 16084 + }, + { + "epoch": 4.97, + "learning_rate": 1.7601403773961928e-05, + "loss": 0.2384, + "step": 16085 + }, + { + "epoch": 4.97, + "learning_rate": 1.7601078808196375e-05, + "loss": 0.2819, + "step": 16086 + }, + { + "epoch": 4.97, + "learning_rate": 1.7600753823419136e-05, + "loss": 0.2605, + "step": 16087 + }, + { + "epoch": 4.97, + "learning_rate": 1.7600428819631027e-05, + "loss": 0.2622, + "step": 16088 + }, + { + "epoch": 4.97, + "learning_rate": 1.760010379683286e-05, + "loss": 0.2353, + "step": 16089 + }, + { + "epoch": 4.97, + "learning_rate": 1.7599778755025444e-05, + "loss": 0.2747, + "step": 16090 + }, + { + "epoch": 4.97, + "learning_rate": 1.7599453694209597e-05, + "loss": 0.2596, + "step": 16091 + }, + { + "epoch": 4.97, + "learning_rate": 1.7599128614386135e-05, + "loss": 0.2294, + "step": 16092 + }, + { + "epoch": 4.97, + "learning_rate": 1.759880351555586e-05, + "loss": 0.2657, + "step": 16093 + }, + { + "epoch": 4.97, + "learning_rate": 1.7598478397719595e-05, + "loss": 0.2664, + "step": 16094 + }, + { + "epoch": 4.97, + "learning_rate": 1.7598153260878147e-05, + "loss": 0.2536, + "step": 16095 + }, + { + "epoch": 4.97, + "learning_rate": 1.7597828105032336e-05, + "loss": 0.2831, + "step": 16096 + }, + { + "epoch": 4.97, + "learning_rate": 1.7597502930182967e-05, + "loss": 0.2609, + "step": 16097 + }, + { + "epoch": 4.97, + "learning_rate": 1.759717773633086e-05, + "loss": 0.2718, + "step": 16098 + }, + { + "epoch": 4.97, + "learning_rate": 1.7596852523476824e-05, + "loss": 0.2484, + "step": 16099 + }, + { + "epoch": 4.97, + "learning_rate": 1.7596527291621674e-05, + "loss": 0.2619, + "step": 16100 + }, + { + "epoch": 4.97, + "learning_rate": 1.7596202040766227e-05, + "loss": 0.2555, + "step": 16101 + }, + { + "epoch": 4.97, + "learning_rate": 1.759587677091129e-05, + "loss": 0.2551, + "step": 16102 + }, + { + "epoch": 4.97, + "learning_rate": 1.759555148205768e-05, + "loss": 0.2491, + "step": 16103 + }, + { + "epoch": 4.97, + "learning_rate": 1.7595226174206212e-05, + "loss": 0.25, + "step": 16104 + }, + { + "epoch": 4.97, + "learning_rate": 1.7594900847357696e-05, + "loss": 0.2685, + "step": 16105 + }, + { + "epoch": 4.97, + "learning_rate": 1.7594575501512952e-05, + "loss": 0.2516, + "step": 16106 + }, + { + "epoch": 4.97, + "learning_rate": 1.7594250136672783e-05, + "loss": 0.263, + "step": 16107 + }, + { + "epoch": 4.97, + "learning_rate": 1.7593924752838015e-05, + "loss": 0.2725, + "step": 16108 + }, + { + "epoch": 4.97, + "learning_rate": 1.759359935000945e-05, + "loss": 0.2629, + "step": 16109 + }, + { + "epoch": 4.98, + "learning_rate": 1.7593273928187915e-05, + "loss": 0.2617, + "step": 16110 + }, + { + "epoch": 4.98, + "learning_rate": 1.7592948487374217e-05, + "loss": 0.2615, + "step": 16111 + }, + { + "epoch": 4.98, + "learning_rate": 1.7592623027569162e-05, + "loss": 0.2471, + "step": 16112 + }, + { + "epoch": 4.98, + "learning_rate": 1.759229754877358e-05, + "loss": 0.2617, + "step": 16113 + }, + { + "epoch": 4.98, + "learning_rate": 1.7591972050988273e-05, + "loss": 0.245, + "step": 16114 + }, + { + "epoch": 4.98, + "learning_rate": 1.759164653421406e-05, + "loss": 0.2587, + "step": 16115 + }, + { + "epoch": 4.98, + "learning_rate": 1.7591320998451755e-05, + "loss": 0.2697, + "step": 16116 + }, + { + "epoch": 4.98, + "learning_rate": 1.759099544370217e-05, + "loss": 0.25, + "step": 16117 + }, + { + "epoch": 4.98, + "learning_rate": 1.7590669869966123e-05, + "loss": 0.2542, + "step": 16118 + }, + { + "epoch": 4.98, + "learning_rate": 1.7590344277244424e-05, + "loss": 0.2464, + "step": 16119 + }, + { + "epoch": 4.98, + "learning_rate": 1.7590018665537895e-05, + "loss": 0.2432, + "step": 16120 + }, + { + "epoch": 4.98, + "learning_rate": 1.7589693034847338e-05, + "loss": 0.283, + "step": 16121 + }, + { + "epoch": 4.98, + "learning_rate": 1.7589367385173577e-05, + "loss": 0.2875, + "step": 16122 + }, + { + "epoch": 4.98, + "learning_rate": 1.7589041716517424e-05, + "loss": 0.2417, + "step": 16123 + }, + { + "epoch": 4.98, + "learning_rate": 1.7588716028879697e-05, + "loss": 0.2749, + "step": 16124 + }, + { + "epoch": 4.98, + "learning_rate": 1.75883903222612e-05, + "loss": 0.2559, + "step": 16125 + }, + { + "epoch": 4.98, + "learning_rate": 1.758806459666276e-05, + "loss": 0.2689, + "step": 16126 + }, + { + "epoch": 4.98, + "learning_rate": 1.7587738852085182e-05, + "loss": 0.272, + "step": 16127 + }, + { + "epoch": 4.98, + "learning_rate": 1.758741308852929e-05, + "loss": 0.2884, + "step": 16128 + }, + { + "epoch": 4.98, + "learning_rate": 1.7587087305995894e-05, + "loss": 0.2745, + "step": 16129 + }, + { + "epoch": 4.98, + "learning_rate": 1.758676150448581e-05, + "loss": 0.2747, + "step": 16130 + }, + { + "epoch": 4.98, + "learning_rate": 1.7586435683999844e-05, + "loss": 0.2662, + "step": 16131 + }, + { + "epoch": 4.98, + "learning_rate": 1.7586109844538827e-05, + "loss": 0.2688, + "step": 16132 + }, + { + "epoch": 4.98, + "learning_rate": 1.758578398610356e-05, + "loss": 0.2508, + "step": 16133 + }, + { + "epoch": 4.98, + "learning_rate": 1.7585458108694867e-05, + "loss": 0.2753, + "step": 16134 + }, + { + "epoch": 4.98, + "learning_rate": 1.7585132212313558e-05, + "loss": 0.2552, + "step": 16135 + }, + { + "epoch": 4.98, + "learning_rate": 1.7584806296960452e-05, + "loss": 0.2679, + "step": 16136 + }, + { + "epoch": 4.98, + "learning_rate": 1.758448036263636e-05, + "loss": 0.257, + "step": 16137 + }, + { + "epoch": 4.98, + "learning_rate": 1.75841544093421e-05, + "loss": 0.2495, + "step": 16138 + }, + { + "epoch": 4.98, + "learning_rate": 1.7583828437078487e-05, + "loss": 0.272, + "step": 16139 + }, + { + "epoch": 4.98, + "learning_rate": 1.7583502445846333e-05, + "loss": 0.2678, + "step": 16140 + }, + { + "epoch": 4.98, + "learning_rate": 1.7583176435646462e-05, + "loss": 0.2534, + "step": 16141 + }, + { + "epoch": 4.99, + "learning_rate": 1.758285040647968e-05, + "loss": 0.2821, + "step": 16142 + }, + { + "epoch": 4.99, + "learning_rate": 1.7582524358346808e-05, + "loss": 0.2588, + "step": 16143 + }, + { + "epoch": 4.99, + "learning_rate": 1.7582198291248654e-05, + "loss": 0.2721, + "step": 16144 + }, + { + "epoch": 4.99, + "learning_rate": 1.7581872205186042e-05, + "loss": 0.2704, + "step": 16145 + }, + { + "epoch": 4.99, + "learning_rate": 1.758154610015979e-05, + "loss": 0.2512, + "step": 16146 + }, + { + "epoch": 4.99, + "learning_rate": 1.75812199761707e-05, + "loss": 0.2709, + "step": 16147 + }, + { + "epoch": 4.99, + "learning_rate": 1.7580893833219602e-05, + "loss": 0.252, + "step": 16148 + }, + { + "epoch": 4.99, + "learning_rate": 1.7580567671307304e-05, + "loss": 0.2523, + "step": 16149 + }, + { + "epoch": 4.99, + "learning_rate": 1.7580241490434625e-05, + "loss": 0.2573, + "step": 16150 + }, + { + "epoch": 4.99, + "learning_rate": 1.757991529060238e-05, + "loss": 0.2408, + "step": 16151 + }, + { + "epoch": 4.99, + "learning_rate": 1.7579589071811382e-05, + "loss": 0.2741, + "step": 16152 + }, + { + "epoch": 4.99, + "learning_rate": 1.757926283406245e-05, + "loss": 0.2606, + "step": 16153 + }, + { + "epoch": 4.99, + "learning_rate": 1.75789365773564e-05, + "loss": 0.2865, + "step": 16154 + }, + { + "epoch": 4.99, + "learning_rate": 1.7578610301694046e-05, + "loss": 0.2519, + "step": 16155 + }, + { + "epoch": 4.99, + "learning_rate": 1.7578284007076205e-05, + "loss": 0.2352, + "step": 16156 + }, + { + "epoch": 4.99, + "learning_rate": 1.7577957693503695e-05, + "loss": 0.2705, + "step": 16157 + }, + { + "epoch": 4.99, + "learning_rate": 1.7577631360977328e-05, + "loss": 0.2786, + "step": 16158 + }, + { + "epoch": 4.99, + "learning_rate": 1.757730500949793e-05, + "loss": 0.2578, + "step": 16159 + }, + { + "epoch": 4.99, + "learning_rate": 1.7576978639066302e-05, + "loss": 0.2762, + "step": 16160 + }, + { + "epoch": 4.99, + "learning_rate": 1.7576652249683276e-05, + "loss": 0.2621, + "step": 16161 + }, + { + "epoch": 4.99, + "learning_rate": 1.7576325841349652e-05, + "loss": 0.2631, + "step": 16162 + }, + { + "epoch": 4.99, + "learning_rate": 1.757599941406626e-05, + "loss": 0.2655, + "step": 16163 + }, + { + "epoch": 4.99, + "learning_rate": 1.757567296783391e-05, + "loss": 0.2612, + "step": 16164 + }, + { + "epoch": 4.99, + "learning_rate": 1.7575346502653424e-05, + "loss": 0.2678, + "step": 16165 + }, + { + "epoch": 4.99, + "learning_rate": 1.7575020018525615e-05, + "loss": 0.2556, + "step": 16166 + }, + { + "epoch": 4.99, + "learning_rate": 1.7574693515451296e-05, + "loss": 0.263, + "step": 16167 + }, + { + "epoch": 4.99, + "learning_rate": 1.7574366993431285e-05, + "loss": 0.2523, + "step": 16168 + }, + { + "epoch": 4.99, + "learning_rate": 1.7574040452466404e-05, + "loss": 0.2892, + "step": 16169 + }, + { + "epoch": 4.99, + "learning_rate": 1.7573713892557468e-05, + "loss": 0.2649, + "step": 16170 + }, + { + "epoch": 4.99, + "learning_rate": 1.757338731370529e-05, + "loss": 0.2636, + "step": 16171 + }, + { + "epoch": 4.99, + "learning_rate": 1.757306071591069e-05, + "loss": 0.2441, + "step": 16172 + }, + { + "epoch": 4.99, + "learning_rate": 1.757273409917448e-05, + "loss": 0.2839, + "step": 16173 + }, + { + "epoch": 4.99, + "learning_rate": 1.7572407463497486e-05, + "loss": 0.2717, + "step": 16174 + }, + { + "epoch": 5.0, + "learning_rate": 1.757208080888052e-05, + "loss": 0.2697, + "step": 16175 + }, + { + "epoch": 5.0, + "learning_rate": 1.7571754135324394e-05, + "loss": 0.2631, + "step": 16176 + }, + { + "epoch": 5.0, + "learning_rate": 1.7571427442829932e-05, + "loss": 0.2718, + "step": 16177 + }, + { + "epoch": 5.0, + "learning_rate": 1.757110073139795e-05, + "loss": 0.2661, + "step": 16178 + }, + { + "epoch": 5.0, + "learning_rate": 1.7570774001029264e-05, + "loss": 0.267, + "step": 16179 + }, + { + "epoch": 5.0, + "learning_rate": 1.757044725172469e-05, + "loss": 0.2667, + "step": 16180 + }, + { + "epoch": 5.0, + "learning_rate": 1.757012048348505e-05, + "loss": 0.261, + "step": 16181 + }, + { + "epoch": 5.0, + "learning_rate": 1.7569793696311156e-05, + "loss": 0.2586, + "step": 16182 + }, + { + "epoch": 5.0, + "learning_rate": 1.7569466890203823e-05, + "loss": 0.2608, + "step": 16183 + }, + { + "epoch": 5.0, + "learning_rate": 1.7569140065163878e-05, + "loss": 0.2264, + "step": 16184 + }, + { + "epoch": 5.0, + "learning_rate": 1.756881322119213e-05, + "loss": 0.2523, + "step": 16185 + }, + { + "epoch": 5.0, + "learning_rate": 1.7568486358289405e-05, + "loss": 0.2669, + "step": 16186 + }, + { + "epoch": 5.0, + "learning_rate": 1.756815947645651e-05, + "loss": 0.2686, + "step": 16187 + }, + { + "epoch": 5.0, + "learning_rate": 1.756783257569427e-05, + "loss": 0.2447, + "step": 16188 + }, + { + "epoch": 5.0, + "learning_rate": 1.7567505656003502e-05, + "loss": 0.2624, + "step": 16189 + }, + { + "epoch": 5.0, + "learning_rate": 1.7567178717385017e-05, + "loss": 0.2413, + "step": 16190 + }, + { + "epoch": 5.0, + "learning_rate": 1.7566851759839642e-05, + "loss": 0.2121, + "step": 16191 + }, + { + "epoch": 5.0, + "learning_rate": 1.756652478336819e-05, + "loss": 0.1893, + "step": 16192 + }, + { + "epoch": 5.0, + "learning_rate": 1.756619778797148e-05, + "loss": 0.18, + "step": 16193 + }, + { + "epoch": 5.0, + "learning_rate": 1.7565870773650328e-05, + "loss": 0.1783, + "step": 16194 + }, + { + "epoch": 5.0, + "learning_rate": 1.7565543740405554e-05, + "loss": 0.1774, + "step": 16195 + }, + { + "epoch": 5.0, + "learning_rate": 1.7565216688237973e-05, + "loss": 0.1813, + "step": 16196 + }, + { + "epoch": 5.0, + "learning_rate": 1.7564889617148407e-05, + "loss": 0.168, + "step": 16197 + }, + { + "epoch": 5.0, + "learning_rate": 1.7564562527137674e-05, + "loss": 0.1649, + "step": 16198 + }, + { + "epoch": 5.0, + "learning_rate": 1.756423541820659e-05, + "loss": 0.179, + "step": 16199 + }, + { + "epoch": 5.0, + "learning_rate": 1.756390829035597e-05, + "loss": 0.1824, + "step": 16200 + }, + { + "epoch": 5.0, + "learning_rate": 1.756358114358664e-05, + "loss": 0.1724, + "step": 16201 + }, + { + "epoch": 5.0, + "learning_rate": 1.7563253977899412e-05, + "loss": 0.1667, + "step": 16202 + }, + { + "epoch": 5.0, + "learning_rate": 1.756292679329511e-05, + "loss": 0.1764, + "step": 16203 + }, + { + "epoch": 5.0, + "learning_rate": 1.756259958977454e-05, + "loss": 0.1781, + "step": 16204 + }, + { + "epoch": 5.0, + "learning_rate": 1.7562272367338534e-05, + "loss": 0.1745, + "step": 16205 + }, + { + "epoch": 5.0, + "learning_rate": 1.756194512598791e-05, + "loss": 0.1762, + "step": 16206 + }, + { + "epoch": 5.01, + "learning_rate": 1.7561617865723476e-05, + "loss": 0.1873, + "step": 16207 + }, + { + "epoch": 5.01, + "learning_rate": 1.7561290586546057e-05, + "loss": 0.1943, + "step": 16208 + }, + { + "epoch": 5.01, + "learning_rate": 1.7560963288456476e-05, + "loss": 0.177, + "step": 16209 + }, + { + "epoch": 5.01, + "learning_rate": 1.7560635971455543e-05, + "loss": 0.177, + "step": 16210 + }, + { + "epoch": 5.01, + "learning_rate": 1.756030863554408e-05, + "loss": 0.1598, + "step": 16211 + }, + { + "epoch": 5.01, + "learning_rate": 1.7559981280722906e-05, + "loss": 0.1641, + "step": 16212 + }, + { + "epoch": 5.01, + "learning_rate": 1.7559653906992843e-05, + "loss": 0.2012, + "step": 16213 + }, + { + "epoch": 5.01, + "learning_rate": 1.7559326514354704e-05, + "loss": 0.1677, + "step": 16214 + }, + { + "epoch": 5.01, + "learning_rate": 1.7558999102809315e-05, + "loss": 0.1749, + "step": 16215 + }, + { + "epoch": 5.01, + "learning_rate": 1.7558671672357483e-05, + "loss": 0.1811, + "step": 16216 + }, + { + "epoch": 5.01, + "learning_rate": 1.7558344223000042e-05, + "loss": 0.1583, + "step": 16217 + }, + { + "epoch": 5.01, + "learning_rate": 1.75580167547378e-05, + "loss": 0.165, + "step": 16218 + }, + { + "epoch": 5.01, + "learning_rate": 1.7557689267571582e-05, + "loss": 0.1828, + "step": 16219 + }, + { + "epoch": 5.01, + "learning_rate": 1.7557361761502202e-05, + "loss": 0.1836, + "step": 16220 + }, + { + "epoch": 5.01, + "learning_rate": 1.755703423653048e-05, + "loss": 0.1614, + "step": 16221 + }, + { + "epoch": 5.01, + "learning_rate": 1.755670669265724e-05, + "loss": 0.175, + "step": 16222 + }, + { + "epoch": 5.01, + "learning_rate": 1.7556379129883296e-05, + "loss": 0.1853, + "step": 16223 + }, + { + "epoch": 5.01, + "learning_rate": 1.7556051548209473e-05, + "loss": 0.168, + "step": 16224 + }, + { + "epoch": 5.01, + "learning_rate": 1.7555723947636583e-05, + "loss": 0.1723, + "step": 16225 + }, + { + "epoch": 5.01, + "learning_rate": 1.7555396328165453e-05, + "loss": 0.1683, + "step": 16226 + }, + { + "epoch": 5.01, + "learning_rate": 1.7555068689796896e-05, + "loss": 0.1726, + "step": 16227 + }, + { + "epoch": 5.01, + "learning_rate": 1.7554741032531736e-05, + "loss": 0.1605, + "step": 16228 + }, + { + "epoch": 5.01, + "learning_rate": 1.755441335637079e-05, + "loss": 0.1764, + "step": 16229 + }, + { + "epoch": 5.01, + "learning_rate": 1.7554085661314883e-05, + "loss": 0.1739, + "step": 16230 + }, + { + "epoch": 5.01, + "learning_rate": 1.7553757947364823e-05, + "loss": 0.1711, + "step": 16231 + }, + { + "epoch": 5.01, + "learning_rate": 1.755343021452144e-05, + "loss": 0.1738, + "step": 16232 + }, + { + "epoch": 5.01, + "learning_rate": 1.755310246278555e-05, + "loss": 0.1962, + "step": 16233 + }, + { + "epoch": 5.01, + "learning_rate": 1.755277469215797e-05, + "loss": 0.1853, + "step": 16234 + }, + { + "epoch": 5.01, + "learning_rate": 1.755244690263953e-05, + "loss": 0.1655, + "step": 16235 + }, + { + "epoch": 5.01, + "learning_rate": 1.7552119094231036e-05, + "loss": 0.1749, + "step": 16236 + }, + { + "epoch": 5.01, + "learning_rate": 1.755179126693332e-05, + "loss": 0.1662, + "step": 16237 + }, + { + "epoch": 5.01, + "learning_rate": 1.7551463420747193e-05, + "loss": 0.1835, + "step": 16238 + }, + { + "epoch": 5.02, + "learning_rate": 1.755113555567348e-05, + "loss": 0.1573, + "step": 16239 + }, + { + "epoch": 5.02, + "learning_rate": 1.7550807671712998e-05, + "loss": 0.1821, + "step": 16240 + }, + { + "epoch": 5.02, + "learning_rate": 1.755047976886657e-05, + "loss": 0.182, + "step": 16241 + }, + { + "epoch": 5.02, + "learning_rate": 1.7550151847135018e-05, + "loss": 0.1597, + "step": 16242 + }, + { + "epoch": 5.02, + "learning_rate": 1.7549823906519155e-05, + "loss": 0.1609, + "step": 16243 + }, + { + "epoch": 5.02, + "learning_rate": 1.7549495947019805e-05, + "loss": 0.1742, + "step": 16244 + }, + { + "epoch": 5.02, + "learning_rate": 1.7549167968637792e-05, + "loss": 0.1775, + "step": 16245 + }, + { + "epoch": 5.02, + "learning_rate": 1.7548839971373932e-05, + "loss": 0.1731, + "step": 16246 + }, + { + "epoch": 5.02, + "learning_rate": 1.7548511955229046e-05, + "loss": 0.1672, + "step": 16247 + }, + { + "epoch": 5.02, + "learning_rate": 1.7548183920203955e-05, + "loss": 0.1755, + "step": 16248 + }, + { + "epoch": 5.02, + "learning_rate": 1.754785586629948e-05, + "loss": 0.1808, + "step": 16249 + }, + { + "epoch": 5.02, + "learning_rate": 1.754752779351644e-05, + "loss": 0.1715, + "step": 16250 + }, + { + "epoch": 5.02, + "learning_rate": 1.7547199701855655e-05, + "loss": 0.1934, + "step": 16251 + }, + { + "epoch": 5.02, + "learning_rate": 1.754687159131795e-05, + "loss": 0.1676, + "step": 16252 + }, + { + "epoch": 5.02, + "learning_rate": 1.7546543461904142e-05, + "loss": 0.1707, + "step": 16253 + }, + { + "epoch": 5.02, + "learning_rate": 1.754621531361505e-05, + "loss": 0.1799, + "step": 16254 + }, + { + "epoch": 5.02, + "learning_rate": 1.75458871464515e-05, + "loss": 0.169, + "step": 16255 + }, + { + "epoch": 5.02, + "learning_rate": 1.754555896041431e-05, + "loss": 0.1715, + "step": 16256 + }, + { + "epoch": 5.02, + "learning_rate": 1.7545230755504296e-05, + "loss": 0.1742, + "step": 16257 + }, + { + "epoch": 5.02, + "learning_rate": 1.7544902531722287e-05, + "loss": 0.1677, + "step": 16258 + }, + { + "epoch": 5.02, + "learning_rate": 1.7544574289069103e-05, + "loss": 0.1661, + "step": 16259 + }, + { + "epoch": 5.02, + "learning_rate": 1.754424602754556e-05, + "loss": 0.1639, + "step": 16260 + }, + { + "epoch": 5.02, + "learning_rate": 1.7543917747152482e-05, + "loss": 0.1813, + "step": 16261 + }, + { + "epoch": 5.02, + "learning_rate": 1.754358944789069e-05, + "loss": 0.1676, + "step": 16262 + }, + { + "epoch": 5.02, + "learning_rate": 1.7543261129761004e-05, + "loss": 0.1646, + "step": 16263 + }, + { + "epoch": 5.02, + "learning_rate": 1.754293279276425e-05, + "loss": 0.1838, + "step": 16264 + }, + { + "epoch": 5.02, + "learning_rate": 1.7542604436901242e-05, + "loss": 0.1828, + "step": 16265 + }, + { + "epoch": 5.02, + "learning_rate": 1.7542276062172802e-05, + "loss": 0.1764, + "step": 16266 + }, + { + "epoch": 5.02, + "learning_rate": 1.754194766857976e-05, + "loss": 0.1931, + "step": 16267 + }, + { + "epoch": 5.02, + "learning_rate": 1.7541619256122926e-05, + "loss": 0.1804, + "step": 16268 + }, + { + "epoch": 5.02, + "learning_rate": 1.754129082480313e-05, + "loss": 0.1715, + "step": 16269 + }, + { + "epoch": 5.02, + "learning_rate": 1.7540962374621188e-05, + "loss": 0.1742, + "step": 16270 + }, + { + "epoch": 5.02, + "learning_rate": 1.7540633905577923e-05, + "loss": 0.1717, + "step": 16271 + }, + { + "epoch": 5.03, + "learning_rate": 1.754030541767416e-05, + "loss": 0.1725, + "step": 16272 + }, + { + "epoch": 5.03, + "learning_rate": 1.753997691091072e-05, + "loss": 0.1837, + "step": 16273 + }, + { + "epoch": 5.03, + "learning_rate": 1.753964838528842e-05, + "loss": 0.1607, + "step": 16274 + }, + { + "epoch": 5.03, + "learning_rate": 1.7539319840808084e-05, + "loss": 0.1828, + "step": 16275 + }, + { + "epoch": 5.03, + "learning_rate": 1.7538991277470532e-05, + "loss": 0.1723, + "step": 16276 + }, + { + "epoch": 5.03, + "learning_rate": 1.7538662695276588e-05, + "loss": 0.1912, + "step": 16277 + }, + { + "epoch": 5.03, + "learning_rate": 1.7538334094227076e-05, + "loss": 0.1776, + "step": 16278 + }, + { + "epoch": 5.03, + "learning_rate": 1.7538005474322815e-05, + "loss": 0.1746, + "step": 16279 + }, + { + "epoch": 5.03, + "learning_rate": 1.753767683556463e-05, + "loss": 0.1665, + "step": 16280 + }, + { + "epoch": 5.03, + "learning_rate": 1.7537348177953335e-05, + "loss": 0.1595, + "step": 16281 + }, + { + "epoch": 5.03, + "learning_rate": 1.753701950148976e-05, + "loss": 0.1791, + "step": 16282 + }, + { + "epoch": 5.03, + "learning_rate": 1.7536690806174728e-05, + "loss": 0.1713, + "step": 16283 + }, + { + "epoch": 5.03, + "learning_rate": 1.7536362092009055e-05, + "loss": 0.1692, + "step": 16284 + }, + { + "epoch": 5.03, + "learning_rate": 1.7536033358993562e-05, + "loss": 0.1738, + "step": 16285 + }, + { + "epoch": 5.03, + "learning_rate": 1.753570460712908e-05, + "loss": 0.1763, + "step": 16286 + }, + { + "epoch": 5.03, + "learning_rate": 1.7535375836416422e-05, + "loss": 0.1704, + "step": 16287 + }, + { + "epoch": 5.03, + "learning_rate": 1.753504704685642e-05, + "loss": 0.1511, + "step": 16288 + }, + { + "epoch": 5.03, + "learning_rate": 1.7534718238449887e-05, + "loss": 0.1832, + "step": 16289 + }, + { + "epoch": 5.03, + "learning_rate": 1.7534389411197653e-05, + "loss": 0.1694, + "step": 16290 + }, + { + "epoch": 5.03, + "learning_rate": 1.7534060565100534e-05, + "loss": 0.1708, + "step": 16291 + }, + { + "epoch": 5.03, + "learning_rate": 1.7533731700159355e-05, + "loss": 0.2014, + "step": 16292 + }, + { + "epoch": 5.03, + "learning_rate": 1.753340281637494e-05, + "loss": 0.1588, + "step": 16293 + }, + { + "epoch": 5.03, + "learning_rate": 1.7533073913748114e-05, + "loss": 0.1852, + "step": 16294 + }, + { + "epoch": 5.03, + "learning_rate": 1.753274499227969e-05, + "loss": 0.1714, + "step": 16295 + }, + { + "epoch": 5.03, + "learning_rate": 1.75324160519705e-05, + "loss": 0.1437, + "step": 16296 + }, + { + "epoch": 5.03, + "learning_rate": 1.7532087092821362e-05, + "loss": 0.1731, + "step": 16297 + }, + { + "epoch": 5.03, + "learning_rate": 1.7531758114833103e-05, + "loss": 0.1776, + "step": 16298 + }, + { + "epoch": 5.03, + "learning_rate": 1.7531429118006542e-05, + "loss": 0.1673, + "step": 16299 + }, + { + "epoch": 5.03, + "learning_rate": 1.7531100102342504e-05, + "loss": 0.1801, + "step": 16300 + }, + { + "epoch": 5.03, + "learning_rate": 1.753077106784181e-05, + "loss": 0.1659, + "step": 16301 + }, + { + "epoch": 5.03, + "learning_rate": 1.7530442014505286e-05, + "loss": 0.1587, + "step": 16302 + }, + { + "epoch": 5.03, + "learning_rate": 1.753011294233375e-05, + "loss": 0.1718, + "step": 16303 + }, + { + "epoch": 5.04, + "learning_rate": 1.7529783851328027e-05, + "loss": 0.1733, + "step": 16304 + }, + { + "epoch": 5.04, + "learning_rate": 1.7529454741488945e-05, + "loss": 0.1796, + "step": 16305 + }, + { + "epoch": 5.04, + "learning_rate": 1.7529125612817322e-05, + "loss": 0.1722, + "step": 16306 + }, + { + "epoch": 5.04, + "learning_rate": 1.7528796465313985e-05, + "loss": 0.1719, + "step": 16307 + }, + { + "epoch": 5.04, + "learning_rate": 1.752846729897975e-05, + "loss": 0.1713, + "step": 16308 + }, + { + "epoch": 5.04, + "learning_rate": 1.752813811381545e-05, + "loss": 0.1718, + "step": 16309 + }, + { + "epoch": 5.04, + "learning_rate": 1.75278089098219e-05, + "loss": 0.1795, + "step": 16310 + }, + { + "epoch": 5.04, + "learning_rate": 1.7527479686999926e-05, + "loss": 0.1621, + "step": 16311 + }, + { + "epoch": 5.04, + "learning_rate": 1.7527150445350358e-05, + "loss": 0.1966, + "step": 16312 + }, + { + "epoch": 5.04, + "learning_rate": 1.752682118487401e-05, + "loss": 0.165, + "step": 16313 + }, + { + "epoch": 5.04, + "learning_rate": 1.752649190557171e-05, + "loss": 0.1836, + "step": 16314 + }, + { + "epoch": 5.04, + "learning_rate": 1.752616260744428e-05, + "loss": 0.1683, + "step": 16315 + }, + { + "epoch": 5.04, + "learning_rate": 1.7525833290492546e-05, + "loss": 0.1586, + "step": 16316 + }, + { + "epoch": 5.04, + "learning_rate": 1.752550395471733e-05, + "loss": 0.1629, + "step": 16317 + }, + { + "epoch": 5.04, + "learning_rate": 1.7525174600119457e-05, + "loss": 0.1781, + "step": 16318 + }, + { + "epoch": 5.04, + "learning_rate": 1.7524845226699747e-05, + "loss": 0.1851, + "step": 16319 + }, + { + "epoch": 5.04, + "learning_rate": 1.7524515834459027e-05, + "loss": 0.1652, + "step": 16320 + }, + { + "epoch": 5.04, + "learning_rate": 1.7524186423398122e-05, + "loss": 0.1677, + "step": 16321 + }, + { + "epoch": 5.04, + "learning_rate": 1.7523856993517852e-05, + "loss": 0.1607, + "step": 16322 + }, + { + "epoch": 5.04, + "learning_rate": 1.752352754481905e-05, + "loss": 0.153, + "step": 16323 + }, + { + "epoch": 5.04, + "learning_rate": 1.7523198077302527e-05, + "loss": 0.1795, + "step": 16324 + }, + { + "epoch": 5.04, + "learning_rate": 1.7522868590969118e-05, + "loss": 0.1734, + "step": 16325 + }, + { + "epoch": 5.04, + "learning_rate": 1.7522539085819637e-05, + "loss": 0.1753, + "step": 16326 + }, + { + "epoch": 5.04, + "learning_rate": 1.7522209561854915e-05, + "loss": 0.1656, + "step": 16327 + }, + { + "epoch": 5.04, + "learning_rate": 1.752188001907578e-05, + "loss": 0.1475, + "step": 16328 + }, + { + "epoch": 5.04, + "learning_rate": 1.752155045748305e-05, + "loss": 0.1819, + "step": 16329 + }, + { + "epoch": 5.04, + "learning_rate": 1.7521220877077544e-05, + "loss": 0.175, + "step": 16330 + }, + { + "epoch": 5.04, + "learning_rate": 1.75208912778601e-05, + "loss": 0.1702, + "step": 16331 + }, + { + "epoch": 5.04, + "learning_rate": 1.7520561659831533e-05, + "loss": 0.1765, + "step": 16332 + }, + { + "epoch": 5.04, + "learning_rate": 1.7520232022992668e-05, + "loss": 0.1649, + "step": 16333 + }, + { + "epoch": 5.04, + "learning_rate": 1.7519902367344332e-05, + "loss": 0.1728, + "step": 16334 + }, + { + "epoch": 5.04, + "learning_rate": 1.751957269288735e-05, + "loss": 0.1654, + "step": 16335 + }, + { + "epoch": 5.04, + "learning_rate": 1.7519242999622543e-05, + "loss": 0.1792, + "step": 16336 + }, + { + "epoch": 5.05, + "learning_rate": 1.751891328755074e-05, + "loss": 0.1748, + "step": 16337 + }, + { + "epoch": 5.05, + "learning_rate": 1.7518583556672762e-05, + "loss": 0.1711, + "step": 16338 + }, + { + "epoch": 5.05, + "learning_rate": 1.7518253806989434e-05, + "loss": 0.1745, + "step": 16339 + }, + { + "epoch": 5.05, + "learning_rate": 1.7517924038501584e-05, + "loss": 0.1789, + "step": 16340 + }, + { + "epoch": 5.05, + "learning_rate": 1.7517594251210033e-05, + "loss": 0.1603, + "step": 16341 + }, + { + "epoch": 5.05, + "learning_rate": 1.7517264445115608e-05, + "loss": 0.1751, + "step": 16342 + }, + { + "epoch": 5.05, + "learning_rate": 1.7516934620219138e-05, + "loss": 0.1646, + "step": 16343 + }, + { + "epoch": 5.05, + "learning_rate": 1.7516604776521437e-05, + "loss": 0.1765, + "step": 16344 + }, + { + "epoch": 5.05, + "learning_rate": 1.7516274914023342e-05, + "loss": 0.1603, + "step": 16345 + }, + { + "epoch": 5.05, + "learning_rate": 1.7515945032725666e-05, + "loss": 0.1706, + "step": 16346 + }, + { + "epoch": 5.05, + "learning_rate": 1.7515615132629245e-05, + "loss": 0.1775, + "step": 16347 + }, + { + "epoch": 5.05, + "learning_rate": 1.7515285213734904e-05, + "loss": 0.159, + "step": 16348 + }, + { + "epoch": 5.05, + "learning_rate": 1.7514955276043458e-05, + "loss": 0.1644, + "step": 16349 + }, + { + "epoch": 5.05, + "learning_rate": 1.751462531955574e-05, + "loss": 0.1718, + "step": 16350 + }, + { + "epoch": 5.05, + "learning_rate": 1.7514295344272573e-05, + "loss": 0.1706, + "step": 16351 + }, + { + "epoch": 5.05, + "learning_rate": 1.751396535019478e-05, + "loss": 0.1835, + "step": 16352 + }, + { + "epoch": 5.05, + "learning_rate": 1.7513635337323194e-05, + "loss": 0.1658, + "step": 16353 + }, + { + "epoch": 5.05, + "learning_rate": 1.7513305305658633e-05, + "loss": 0.1811, + "step": 16354 + }, + { + "epoch": 5.05, + "learning_rate": 1.7512975255201925e-05, + "loss": 0.1548, + "step": 16355 + }, + { + "epoch": 5.05, + "learning_rate": 1.75126451859539e-05, + "loss": 0.1826, + "step": 16356 + }, + { + "epoch": 5.05, + "learning_rate": 1.7512315097915375e-05, + "loss": 0.165, + "step": 16357 + }, + { + "epoch": 5.05, + "learning_rate": 1.751198499108718e-05, + "loss": 0.1827, + "step": 16358 + }, + { + "epoch": 5.05, + "learning_rate": 1.751165486547014e-05, + "loss": 0.1685, + "step": 16359 + }, + { + "epoch": 5.05, + "learning_rate": 1.7511324721065082e-05, + "loss": 0.1803, + "step": 16360 + }, + { + "epoch": 5.05, + "learning_rate": 1.7510994557872832e-05, + "loss": 0.1652, + "step": 16361 + }, + { + "epoch": 5.05, + "learning_rate": 1.7510664375894214e-05, + "loss": 0.1868, + "step": 16362 + }, + { + "epoch": 5.05, + "learning_rate": 1.7510334175130052e-05, + "loss": 0.1897, + "step": 16363 + }, + { + "epoch": 5.05, + "learning_rate": 1.751000395558118e-05, + "loss": 0.1653, + "step": 16364 + }, + { + "epoch": 5.05, + "learning_rate": 1.7509673717248413e-05, + "loss": 0.18, + "step": 16365 + }, + { + "epoch": 5.05, + "learning_rate": 1.7509343460132583e-05, + "loss": 0.1677, + "step": 16366 + }, + { + "epoch": 5.05, + "learning_rate": 1.7509013184234518e-05, + "loss": 0.16, + "step": 16367 + }, + { + "epoch": 5.05, + "learning_rate": 1.750868288955504e-05, + "loss": 0.1714, + "step": 16368 + }, + { + "epoch": 5.06, + "learning_rate": 1.7508352576094977e-05, + "loss": 0.1811, + "step": 16369 + }, + { + "epoch": 5.06, + "learning_rate": 1.7508022243855154e-05, + "loss": 0.1645, + "step": 16370 + }, + { + "epoch": 5.06, + "learning_rate": 1.7507691892836397e-05, + "loss": 0.1557, + "step": 16371 + }, + { + "epoch": 5.06, + "learning_rate": 1.7507361523039536e-05, + "loss": 0.1626, + "step": 16372 + }, + { + "epoch": 5.06, + "learning_rate": 1.7507031134465395e-05, + "loss": 0.1748, + "step": 16373 + }, + { + "epoch": 5.06, + "learning_rate": 1.7506700727114796e-05, + "loss": 0.1715, + "step": 16374 + }, + { + "epoch": 5.06, + "learning_rate": 1.750637030098857e-05, + "loss": 0.1644, + "step": 16375 + }, + { + "epoch": 5.06, + "learning_rate": 1.7506039856087548e-05, + "loss": 0.1785, + "step": 16376 + }, + { + "epoch": 5.06, + "learning_rate": 1.7505709392412545e-05, + "loss": 0.1767, + "step": 16377 + }, + { + "epoch": 5.06, + "learning_rate": 1.75053789099644e-05, + "loss": 0.1932, + "step": 16378 + }, + { + "epoch": 5.06, + "learning_rate": 1.7505048408743928e-05, + "loss": 0.1573, + "step": 16379 + }, + { + "epoch": 5.06, + "learning_rate": 1.7504717888751964e-05, + "loss": 0.1694, + "step": 16380 + }, + { + "epoch": 5.06, + "learning_rate": 1.750438734998933e-05, + "loss": 0.1842, + "step": 16381 + }, + { + "epoch": 5.06, + "learning_rate": 1.7504056792456856e-05, + "loss": 0.1752, + "step": 16382 + }, + { + "epoch": 5.06, + "learning_rate": 1.7503726216155365e-05, + "loss": 0.1667, + "step": 16383 + }, + { + "epoch": 5.06, + "learning_rate": 1.750339562108569e-05, + "loss": 0.171, + "step": 16384 + }, + { + "epoch": 5.06, + "learning_rate": 1.750306500724865e-05, + "loss": 0.1647, + "step": 16385 + }, + { + "epoch": 5.06, + "learning_rate": 1.750273437464508e-05, + "loss": 0.181, + "step": 16386 + }, + { + "epoch": 5.06, + "learning_rate": 1.7502403723275798e-05, + "loss": 0.1792, + "step": 16387 + }, + { + "epoch": 5.06, + "learning_rate": 1.750207305314164e-05, + "loss": 0.1767, + "step": 16388 + }, + { + "epoch": 5.06, + "learning_rate": 1.750174236424343e-05, + "loss": 0.1883, + "step": 16389 + }, + { + "epoch": 5.06, + "learning_rate": 1.7501411656581992e-05, + "loss": 0.165, + "step": 16390 + }, + { + "epoch": 5.06, + "learning_rate": 1.750108093015815e-05, + "loss": 0.1679, + "step": 16391 + }, + { + "epoch": 5.06, + "learning_rate": 1.7500750184972744e-05, + "loss": 0.1747, + "step": 16392 + }, + { + "epoch": 5.06, + "learning_rate": 1.750041942102659e-05, + "loss": 0.181, + "step": 16393 + }, + { + "epoch": 5.06, + "learning_rate": 1.750008863832052e-05, + "loss": 0.1678, + "step": 16394 + }, + { + "epoch": 5.06, + "learning_rate": 1.7499757836855362e-05, + "loss": 0.1656, + "step": 16395 + }, + { + "epoch": 5.06, + "learning_rate": 1.7499427016631944e-05, + "loss": 0.1696, + "step": 16396 + }, + { + "epoch": 5.06, + "learning_rate": 1.7499096177651085e-05, + "loss": 0.1821, + "step": 16397 + }, + { + "epoch": 5.06, + "learning_rate": 1.749876531991362e-05, + "loss": 0.1567, + "step": 16398 + }, + { + "epoch": 5.06, + "learning_rate": 1.7498434443420377e-05, + "loss": 0.1815, + "step": 16399 + }, + { + "epoch": 5.06, + "learning_rate": 1.7498103548172184e-05, + "loss": 0.1802, + "step": 16400 + }, + { + "epoch": 5.07, + "learning_rate": 1.749777263416986e-05, + "loss": 0.1886, + "step": 16401 + }, + { + "epoch": 5.07, + "learning_rate": 1.7497441701414243e-05, + "loss": 0.1631, + "step": 16402 + }, + { + "epoch": 5.07, + "learning_rate": 1.7497110749906162e-05, + "loss": 0.1563, + "step": 16403 + }, + { + "epoch": 5.07, + "learning_rate": 1.7496779779646432e-05, + "loss": 0.1843, + "step": 16404 + }, + { + "epoch": 5.07, + "learning_rate": 1.7496448790635893e-05, + "loss": 0.1878, + "step": 16405 + }, + { + "epoch": 5.07, + "learning_rate": 1.7496117782875365e-05, + "loss": 0.1727, + "step": 16406 + }, + { + "epoch": 5.07, + "learning_rate": 1.749578675636568e-05, + "loss": 0.1736, + "step": 16407 + }, + { + "epoch": 5.07, + "learning_rate": 1.749545571110767e-05, + "loss": 0.176, + "step": 16408 + }, + { + "epoch": 5.07, + "learning_rate": 1.749512464710215e-05, + "loss": 0.1742, + "step": 16409 + }, + { + "epoch": 5.07, + "learning_rate": 1.749479356434996e-05, + "loss": 0.1756, + "step": 16410 + }, + { + "epoch": 5.07, + "learning_rate": 1.7494462462851924e-05, + "loss": 0.1824, + "step": 16411 + }, + { + "epoch": 5.07, + "learning_rate": 1.749413134260887e-05, + "loss": 0.1699, + "step": 16412 + }, + { + "epoch": 5.07, + "learning_rate": 1.749380020362163e-05, + "loss": 0.1772, + "step": 16413 + }, + { + "epoch": 5.07, + "learning_rate": 1.7493469045891025e-05, + "loss": 0.1796, + "step": 16414 + }, + { + "epoch": 5.07, + "learning_rate": 1.7493137869417888e-05, + "loss": 0.1733, + "step": 16415 + }, + { + "epoch": 5.07, + "learning_rate": 1.749280667420305e-05, + "loss": 0.1576, + "step": 16416 + }, + { + "epoch": 5.07, + "learning_rate": 1.749247546024733e-05, + "loss": 0.1695, + "step": 16417 + }, + { + "epoch": 5.07, + "learning_rate": 1.7492144227551568e-05, + "loss": 0.1701, + "step": 16418 + }, + { + "epoch": 5.07, + "learning_rate": 1.749181297611658e-05, + "loss": 0.1806, + "step": 16419 + }, + { + "epoch": 5.07, + "learning_rate": 1.749148170594321e-05, + "loss": 0.1753, + "step": 16420 + }, + { + "epoch": 5.07, + "learning_rate": 1.7491150417032273e-05, + "loss": 0.1723, + "step": 16421 + }, + { + "epoch": 5.07, + "learning_rate": 1.7490819109384602e-05, + "loss": 0.1734, + "step": 16422 + }, + { + "epoch": 5.07, + "learning_rate": 1.749048778300103e-05, + "loss": 0.164, + "step": 16423 + }, + { + "epoch": 5.07, + "learning_rate": 1.7490156437882376e-05, + "loss": 0.1863, + "step": 16424 + }, + { + "epoch": 5.07, + "learning_rate": 1.748982507402948e-05, + "loss": 0.1782, + "step": 16425 + }, + { + "epoch": 5.07, + "learning_rate": 1.7489493691443163e-05, + "loss": 0.176, + "step": 16426 + }, + { + "epoch": 5.07, + "learning_rate": 1.7489162290124256e-05, + "loss": 0.1635, + "step": 16427 + }, + { + "epoch": 5.07, + "learning_rate": 1.7488830870073588e-05, + "loss": 0.1793, + "step": 16428 + }, + { + "epoch": 5.07, + "learning_rate": 1.7488499431291986e-05, + "loss": 0.1768, + "step": 16429 + }, + { + "epoch": 5.07, + "learning_rate": 1.7488167973780287e-05, + "loss": 0.1741, + "step": 16430 + }, + { + "epoch": 5.07, + "learning_rate": 1.748783649753931e-05, + "loss": 0.1606, + "step": 16431 + }, + { + "epoch": 5.07, + "learning_rate": 1.748750500256989e-05, + "loss": 0.1748, + "step": 16432 + }, + { + "epoch": 5.07, + "learning_rate": 1.7487173488872852e-05, + "loss": 0.182, + "step": 16433 + }, + { + "epoch": 5.08, + "learning_rate": 1.748684195644903e-05, + "loss": 0.1737, + "step": 16434 + }, + { + "epoch": 5.08, + "learning_rate": 1.748651040529925e-05, + "loss": 0.1746, + "step": 16435 + }, + { + "epoch": 5.08, + "learning_rate": 1.7486178835424342e-05, + "loss": 0.1716, + "step": 16436 + }, + { + "epoch": 5.08, + "learning_rate": 1.7485847246825133e-05, + "loss": 0.169, + "step": 16437 + }, + { + "epoch": 5.08, + "learning_rate": 1.7485515639502457e-05, + "loss": 0.1777, + "step": 16438 + }, + { + "epoch": 5.08, + "learning_rate": 1.748518401345714e-05, + "loss": 0.1801, + "step": 16439 + }, + { + "epoch": 5.08, + "learning_rate": 1.7484852368690014e-05, + "loss": 0.1541, + "step": 16440 + }, + { + "epoch": 5.08, + "learning_rate": 1.7484520705201908e-05, + "loss": 0.1793, + "step": 16441 + }, + { + "epoch": 5.08, + "learning_rate": 1.748418902299365e-05, + "loss": 0.1798, + "step": 16442 + }, + { + "epoch": 5.08, + "learning_rate": 1.748385732206607e-05, + "loss": 0.1757, + "step": 16443 + }, + { + "epoch": 5.08, + "learning_rate": 1.7483525602419998e-05, + "loss": 0.1574, + "step": 16444 + }, + { + "epoch": 5.08, + "learning_rate": 1.7483193864056263e-05, + "loss": 0.1827, + "step": 16445 + }, + { + "epoch": 5.08, + "learning_rate": 1.748286210697569e-05, + "loss": 0.1797, + "step": 16446 + }, + { + "epoch": 5.08, + "learning_rate": 1.748253033117912e-05, + "loss": 0.1799, + "step": 16447 + }, + { + "epoch": 5.08, + "learning_rate": 1.7482198536667378e-05, + "loss": 0.1692, + "step": 16448 + }, + { + "epoch": 5.08, + "learning_rate": 1.7481866723441292e-05, + "loss": 0.1723, + "step": 16449 + }, + { + "epoch": 5.08, + "learning_rate": 1.7481534891501694e-05, + "loss": 0.1625, + "step": 16450 + }, + { + "epoch": 5.08, + "learning_rate": 1.7481203040849407e-05, + "loss": 0.1621, + "step": 16451 + }, + { + "epoch": 5.08, + "learning_rate": 1.748087117148527e-05, + "loss": 0.1796, + "step": 16452 + }, + { + "epoch": 5.08, + "learning_rate": 1.748053928341011e-05, + "loss": 0.1733, + "step": 16453 + }, + { + "epoch": 5.08, + "learning_rate": 1.7480207376624755e-05, + "loss": 0.1659, + "step": 16454 + }, + { + "epoch": 5.08, + "learning_rate": 1.747987545113004e-05, + "loss": 0.1743, + "step": 16455 + }, + { + "epoch": 5.08, + "learning_rate": 1.747954350692679e-05, + "loss": 0.1722, + "step": 16456 + }, + { + "epoch": 5.08, + "learning_rate": 1.747921154401584e-05, + "loss": 0.1816, + "step": 16457 + }, + { + "epoch": 5.08, + "learning_rate": 1.7478879562398017e-05, + "loss": 0.163, + "step": 16458 + }, + { + "epoch": 5.08, + "learning_rate": 1.747854756207415e-05, + "loss": 0.1792, + "step": 16459 + }, + { + "epoch": 5.08, + "learning_rate": 1.7478215543045073e-05, + "loss": 0.1707, + "step": 16460 + }, + { + "epoch": 5.08, + "learning_rate": 1.7477883505311617e-05, + "loss": 0.1681, + "step": 16461 + }, + { + "epoch": 5.08, + "learning_rate": 1.7477551448874607e-05, + "loss": 0.1665, + "step": 16462 + }, + { + "epoch": 5.08, + "learning_rate": 1.7477219373734878e-05, + "loss": 0.1661, + "step": 16463 + }, + { + "epoch": 5.08, + "learning_rate": 1.7476887279893262e-05, + "loss": 0.1937, + "step": 16464 + }, + { + "epoch": 5.08, + "learning_rate": 1.7476555167350585e-05, + "loss": 0.1666, + "step": 16465 + }, + { + "epoch": 5.09, + "learning_rate": 1.747622303610768e-05, + "loss": 0.1643, + "step": 16466 + }, + { + "epoch": 5.09, + "learning_rate": 1.7475890886165377e-05, + "loss": 0.1653, + "step": 16467 + }, + { + "epoch": 5.09, + "learning_rate": 1.747555871752451e-05, + "loss": 0.1663, + "step": 16468 + }, + { + "epoch": 5.09, + "learning_rate": 1.7475226530185904e-05, + "loss": 0.1765, + "step": 16469 + }, + { + "epoch": 5.09, + "learning_rate": 1.7474894324150393e-05, + "loss": 0.152, + "step": 16470 + }, + { + "epoch": 5.09, + "learning_rate": 1.747456209941881e-05, + "loss": 0.1724, + "step": 16471 + }, + { + "epoch": 5.09, + "learning_rate": 1.7474229855991986e-05, + "loss": 0.1714, + "step": 16472 + }, + { + "epoch": 5.09, + "learning_rate": 1.7473897593870745e-05, + "loss": 0.1788, + "step": 16473 + }, + { + "epoch": 5.09, + "learning_rate": 1.7473565313055926e-05, + "loss": 0.1734, + "step": 16474 + }, + { + "epoch": 5.09, + "learning_rate": 1.7473233013548357e-05, + "loss": 0.1714, + "step": 16475 + }, + { + "epoch": 5.09, + "learning_rate": 1.747290069534887e-05, + "loss": 0.1539, + "step": 16476 + }, + { + "epoch": 5.09, + "learning_rate": 1.7472568358458294e-05, + "loss": 0.1799, + "step": 16477 + }, + { + "epoch": 5.09, + "learning_rate": 1.747223600287746e-05, + "loss": 0.1553, + "step": 16478 + }, + { + "epoch": 5.09, + "learning_rate": 1.7471903628607202e-05, + "loss": 0.1614, + "step": 16479 + }, + { + "epoch": 5.09, + "learning_rate": 1.7471571235648352e-05, + "loss": 0.1557, + "step": 16480 + }, + { + "epoch": 5.09, + "learning_rate": 1.747123882400174e-05, + "loss": 0.1695, + "step": 16481 + }, + { + "epoch": 5.09, + "learning_rate": 1.7470906393668193e-05, + "loss": 0.1795, + "step": 16482 + }, + { + "epoch": 5.09, + "learning_rate": 1.7470573944648546e-05, + "loss": 0.172, + "step": 16483 + }, + { + "epoch": 5.09, + "learning_rate": 1.7470241476943636e-05, + "loss": 0.1713, + "step": 16484 + }, + { + "epoch": 5.09, + "learning_rate": 1.7469908990554287e-05, + "loss": 0.168, + "step": 16485 + }, + { + "epoch": 5.09, + "learning_rate": 1.7469576485481332e-05, + "loss": 0.1743, + "step": 16486 + }, + { + "epoch": 5.09, + "learning_rate": 1.7469243961725606e-05, + "loss": 0.1858, + "step": 16487 + }, + { + "epoch": 5.09, + "learning_rate": 1.746891141928794e-05, + "loss": 0.1841, + "step": 16488 + }, + { + "epoch": 5.09, + "learning_rate": 1.746857885816916e-05, + "loss": 0.1595, + "step": 16489 + }, + { + "epoch": 5.09, + "learning_rate": 1.7468246278370106e-05, + "loss": 0.166, + "step": 16490 + }, + { + "epoch": 5.09, + "learning_rate": 1.7467913679891603e-05, + "loss": 0.1723, + "step": 16491 + }, + { + "epoch": 5.09, + "learning_rate": 1.7467581062734486e-05, + "loss": 0.1698, + "step": 16492 + }, + { + "epoch": 5.09, + "learning_rate": 1.7467248426899587e-05, + "loss": 0.1897, + "step": 16493 + }, + { + "epoch": 5.09, + "learning_rate": 1.746691577238774e-05, + "loss": 0.167, + "step": 16494 + }, + { + "epoch": 5.09, + "learning_rate": 1.7466583099199776e-05, + "loss": 0.1875, + "step": 16495 + }, + { + "epoch": 5.09, + "learning_rate": 1.746625040733652e-05, + "loss": 0.169, + "step": 16496 + }, + { + "epoch": 5.09, + "learning_rate": 1.7465917696798814e-05, + "loss": 0.163, + "step": 16497 + }, + { + "epoch": 5.09, + "learning_rate": 1.7465584967587485e-05, + "loss": 0.1922, + "step": 16498 + }, + { + "epoch": 5.1, + "learning_rate": 1.7465252219703364e-05, + "loss": 0.1638, + "step": 16499 + }, + { + "epoch": 5.1, + "learning_rate": 1.746491945314729e-05, + "loss": 0.1681, + "step": 16500 + }, + { + "epoch": 5.1, + "learning_rate": 1.746458666792009e-05, + "loss": 0.1754, + "step": 16501 + }, + { + "epoch": 5.1, + "learning_rate": 1.7464253864022595e-05, + "loss": 0.1733, + "step": 16502 + }, + { + "epoch": 5.1, + "learning_rate": 1.7463921041455644e-05, + "loss": 0.1798, + "step": 16503 + }, + { + "epoch": 5.1, + "learning_rate": 1.746358820022006e-05, + "loss": 0.1671, + "step": 16504 + }, + { + "epoch": 5.1, + "learning_rate": 1.7463255340316686e-05, + "loss": 0.1777, + "step": 16505 + }, + { + "epoch": 5.1, + "learning_rate": 1.7462922461746345e-05, + "loss": 0.1646, + "step": 16506 + }, + { + "epoch": 5.1, + "learning_rate": 1.7462589564509876e-05, + "loss": 0.1759, + "step": 16507 + }, + { + "epoch": 5.1, + "learning_rate": 1.7462256648608104e-05, + "loss": 0.1882, + "step": 16508 + }, + { + "epoch": 5.1, + "learning_rate": 1.7461923714041872e-05, + "loss": 0.1673, + "step": 16509 + }, + { + "epoch": 5.1, + "learning_rate": 1.746159076081201e-05, + "loss": 0.1823, + "step": 16510 + }, + { + "epoch": 5.1, + "learning_rate": 1.7461257788919342e-05, + "loss": 0.1631, + "step": 16511 + }, + { + "epoch": 5.1, + "learning_rate": 1.7460924798364714e-05, + "loss": 0.1839, + "step": 16512 + }, + { + "epoch": 5.1, + "learning_rate": 1.7460591789148947e-05, + "loss": 0.1683, + "step": 16513 + }, + { + "epoch": 5.1, + "learning_rate": 1.7460258761272882e-05, + "loss": 0.1638, + "step": 16514 + }, + { + "epoch": 5.1, + "learning_rate": 1.745992571473735e-05, + "loss": 0.1904, + "step": 16515 + }, + { + "epoch": 5.1, + "learning_rate": 1.7459592649543183e-05, + "loss": 0.1692, + "step": 16516 + }, + { + "epoch": 5.1, + "learning_rate": 1.7459259565691213e-05, + "loss": 0.1765, + "step": 16517 + }, + { + "epoch": 5.1, + "learning_rate": 1.7458926463182275e-05, + "loss": 0.1858, + "step": 16518 + }, + { + "epoch": 5.1, + "learning_rate": 1.74585933420172e-05, + "loss": 0.1607, + "step": 16519 + }, + { + "epoch": 5.1, + "learning_rate": 1.7458260202196826e-05, + "loss": 0.164, + "step": 16520 + }, + { + "epoch": 5.1, + "learning_rate": 1.7457927043721982e-05, + "loss": 0.1787, + "step": 16521 + }, + { + "epoch": 5.1, + "learning_rate": 1.7457593866593497e-05, + "loss": 0.1774, + "step": 16522 + }, + { + "epoch": 5.1, + "learning_rate": 1.7457260670812215e-05, + "loss": 0.1655, + "step": 16523 + }, + { + "epoch": 5.1, + "learning_rate": 1.7456927456378963e-05, + "loss": 0.1734, + "step": 16524 + }, + { + "epoch": 5.1, + "learning_rate": 1.7456594223294577e-05, + "loss": 0.1768, + "step": 16525 + }, + { + "epoch": 5.1, + "learning_rate": 1.7456260971559884e-05, + "loss": 0.1722, + "step": 16526 + }, + { + "epoch": 5.1, + "learning_rate": 1.7455927701175724e-05, + "loss": 0.163, + "step": 16527 + }, + { + "epoch": 5.1, + "learning_rate": 1.745559441214293e-05, + "loss": 0.1903, + "step": 16528 + }, + { + "epoch": 5.1, + "learning_rate": 1.7455261104462336e-05, + "loss": 0.1737, + "step": 16529 + }, + { + "epoch": 5.1, + "learning_rate": 1.7454927778134774e-05, + "loss": 0.1813, + "step": 16530 + }, + { + "epoch": 5.11, + "learning_rate": 1.7454594433161076e-05, + "loss": 0.1685, + "step": 16531 + }, + { + "epoch": 5.11, + "learning_rate": 1.745426106954208e-05, + "loss": 0.1674, + "step": 16532 + }, + { + "epoch": 5.11, + "learning_rate": 1.7453927687278613e-05, + "loss": 0.1589, + "step": 16533 + }, + { + "epoch": 5.11, + "learning_rate": 1.7453594286371518e-05, + "loss": 0.1721, + "step": 16534 + }, + { + "epoch": 5.11, + "learning_rate": 1.7453260866821624e-05, + "loss": 0.1703, + "step": 16535 + }, + { + "epoch": 5.11, + "learning_rate": 1.745292742862976e-05, + "loss": 0.1761, + "step": 16536 + }, + { + "epoch": 5.11, + "learning_rate": 1.745259397179677e-05, + "loss": 0.1817, + "step": 16537 + }, + { + "epoch": 5.11, + "learning_rate": 1.7452260496323485e-05, + "loss": 0.1795, + "step": 16538 + }, + { + "epoch": 5.11, + "learning_rate": 1.745192700221073e-05, + "loss": 0.1634, + "step": 16539 + }, + { + "epoch": 5.11, + "learning_rate": 1.7451593489459352e-05, + "loss": 0.1785, + "step": 16540 + }, + { + "epoch": 5.11, + "learning_rate": 1.745125995807018e-05, + "loss": 0.1809, + "step": 16541 + }, + { + "epoch": 5.11, + "learning_rate": 1.7450926408044045e-05, + "loss": 0.166, + "step": 16542 + }, + { + "epoch": 5.11, + "learning_rate": 1.7450592839381787e-05, + "loss": 0.1671, + "step": 16543 + }, + { + "epoch": 5.11, + "learning_rate": 1.7450259252084234e-05, + "loss": 0.1884, + "step": 16544 + }, + { + "epoch": 5.11, + "learning_rate": 1.7449925646152225e-05, + "loss": 0.1671, + "step": 16545 + }, + { + "epoch": 5.11, + "learning_rate": 1.7449592021586595e-05, + "loss": 0.1882, + "step": 16546 + }, + { + "epoch": 5.11, + "learning_rate": 1.7449258378388175e-05, + "loss": 0.1757, + "step": 16547 + }, + { + "epoch": 5.11, + "learning_rate": 1.7448924716557802e-05, + "loss": 0.1631, + "step": 16548 + }, + { + "epoch": 5.11, + "learning_rate": 1.744859103609631e-05, + "loss": 0.1817, + "step": 16549 + }, + { + "epoch": 5.11, + "learning_rate": 1.744825733700453e-05, + "loss": 0.1831, + "step": 16550 + }, + { + "epoch": 5.11, + "learning_rate": 1.7447923619283303e-05, + "loss": 0.185, + "step": 16551 + }, + { + "epoch": 5.11, + "learning_rate": 1.744758988293346e-05, + "loss": 0.1754, + "step": 16552 + }, + { + "epoch": 5.11, + "learning_rate": 1.7447256127955837e-05, + "loss": 0.1848, + "step": 16553 + }, + { + "epoch": 5.11, + "learning_rate": 1.7446922354351267e-05, + "loss": 0.1799, + "step": 16554 + }, + { + "epoch": 5.11, + "learning_rate": 1.7446588562120585e-05, + "loss": 0.167, + "step": 16555 + }, + { + "epoch": 5.11, + "learning_rate": 1.7446254751264628e-05, + "loss": 0.1767, + "step": 16556 + }, + { + "epoch": 5.11, + "learning_rate": 1.744592092178423e-05, + "loss": 0.1659, + "step": 16557 + }, + { + "epoch": 5.11, + "learning_rate": 1.7445587073680227e-05, + "loss": 0.1912, + "step": 16558 + }, + { + "epoch": 5.11, + "learning_rate": 1.744525320695345e-05, + "loss": 0.1745, + "step": 16559 + }, + { + "epoch": 5.11, + "learning_rate": 1.744491932160474e-05, + "loss": 0.1718, + "step": 16560 + }, + { + "epoch": 5.11, + "learning_rate": 1.744458541763493e-05, + "loss": 0.1796, + "step": 16561 + }, + { + "epoch": 5.11, + "learning_rate": 1.744425149504485e-05, + "loss": 0.1808, + "step": 16562 + }, + { + "epoch": 5.12, + "learning_rate": 1.744391755383534e-05, + "loss": 0.1563, + "step": 16563 + }, + { + "epoch": 5.12, + "learning_rate": 1.7443583594007235e-05, + "loss": 0.1622, + "step": 16564 + }, + { + "epoch": 5.12, + "learning_rate": 1.7443249615561367e-05, + "loss": 0.1834, + "step": 16565 + }, + { + "epoch": 5.12, + "learning_rate": 1.744291561849858e-05, + "loss": 0.171, + "step": 16566 + }, + { + "epoch": 5.12, + "learning_rate": 1.74425816028197e-05, + "loss": 0.1811, + "step": 16567 + }, + { + "epoch": 5.12, + "learning_rate": 1.7442247568525566e-05, + "loss": 0.1841, + "step": 16568 + }, + { + "epoch": 5.12, + "learning_rate": 1.7441913515617014e-05, + "loss": 0.1733, + "step": 16569 + }, + { + "epoch": 5.12, + "learning_rate": 1.7441579444094877e-05, + "loss": 0.1911, + "step": 16570 + }, + { + "epoch": 5.12, + "learning_rate": 1.7441245353959996e-05, + "loss": 0.187, + "step": 16571 + }, + { + "epoch": 5.12, + "learning_rate": 1.74409112452132e-05, + "loss": 0.1861, + "step": 16572 + }, + { + "epoch": 5.12, + "learning_rate": 1.744057711785533e-05, + "loss": 0.1778, + "step": 16573 + }, + { + "epoch": 5.12, + "learning_rate": 1.744024297188722e-05, + "loss": 0.163, + "step": 16574 + }, + { + "epoch": 5.12, + "learning_rate": 1.7439908807309705e-05, + "loss": 0.1745, + "step": 16575 + }, + { + "epoch": 5.12, + "learning_rate": 1.7439574624123617e-05, + "loss": 0.1719, + "step": 16576 + }, + { + "epoch": 5.12, + "learning_rate": 1.74392404223298e-05, + "loss": 0.1648, + "step": 16577 + }, + { + "epoch": 5.12, + "learning_rate": 1.7438906201929087e-05, + "loss": 0.1671, + "step": 16578 + }, + { + "epoch": 5.12, + "learning_rate": 1.743857196292231e-05, + "loss": 0.1775, + "step": 16579 + }, + { + "epoch": 5.12, + "learning_rate": 1.743823770531031e-05, + "loss": 0.1771, + "step": 16580 + }, + { + "epoch": 5.12, + "learning_rate": 1.7437903429093917e-05, + "loss": 0.1955, + "step": 16581 + }, + { + "epoch": 5.12, + "learning_rate": 1.7437569134273976e-05, + "loss": 0.1922, + "step": 16582 + }, + { + "epoch": 5.12, + "learning_rate": 1.7437234820851317e-05, + "loss": 0.1834, + "step": 16583 + }, + { + "epoch": 5.12, + "learning_rate": 1.7436900488826775e-05, + "loss": 0.1815, + "step": 16584 + }, + { + "epoch": 5.12, + "learning_rate": 1.743656613820119e-05, + "loss": 0.1687, + "step": 16585 + }, + { + "epoch": 5.12, + "learning_rate": 1.7436231768975394e-05, + "loss": 0.1858, + "step": 16586 + }, + { + "epoch": 5.12, + "learning_rate": 1.7435897381150232e-05, + "loss": 0.1832, + "step": 16587 + }, + { + "epoch": 5.12, + "learning_rate": 1.7435562974726527e-05, + "loss": 0.1561, + "step": 16588 + }, + { + "epoch": 5.12, + "learning_rate": 1.7435228549705127e-05, + "loss": 0.1669, + "step": 16589 + }, + { + "epoch": 5.12, + "learning_rate": 1.7434894106086863e-05, + "loss": 0.178, + "step": 16590 + }, + { + "epoch": 5.12, + "learning_rate": 1.7434559643872575e-05, + "loss": 0.1742, + "step": 16591 + }, + { + "epoch": 5.12, + "learning_rate": 1.7434225163063097e-05, + "loss": 0.1866, + "step": 16592 + }, + { + "epoch": 5.12, + "learning_rate": 1.7433890663659264e-05, + "loss": 0.1762, + "step": 16593 + }, + { + "epoch": 5.12, + "learning_rate": 1.7433556145661916e-05, + "loss": 0.1656, + "step": 16594 + }, + { + "epoch": 5.12, + "learning_rate": 1.7433221609071887e-05, + "loss": 0.1666, + "step": 16595 + }, + { + "epoch": 5.13, + "learning_rate": 1.7432887053890016e-05, + "loss": 0.173, + "step": 16596 + }, + { + "epoch": 5.13, + "learning_rate": 1.7432552480117138e-05, + "loss": 0.1567, + "step": 16597 + }, + { + "epoch": 5.13, + "learning_rate": 1.7432217887754092e-05, + "loss": 0.1769, + "step": 16598 + }, + { + "epoch": 5.13, + "learning_rate": 1.7431883276801712e-05, + "loss": 0.1768, + "step": 16599 + }, + { + "epoch": 5.13, + "learning_rate": 1.743154864726084e-05, + "loss": 0.1525, + "step": 16600 + }, + { + "epoch": 5.13, + "learning_rate": 1.7431213999132305e-05, + "loss": 0.1775, + "step": 16601 + }, + { + "epoch": 5.13, + "learning_rate": 1.743087933241695e-05, + "loss": 0.1663, + "step": 16602 + }, + { + "epoch": 5.13, + "learning_rate": 1.743054464711561e-05, + "loss": 0.1549, + "step": 16603 + }, + { + "epoch": 5.13, + "learning_rate": 1.7430209943229123e-05, + "loss": 0.1804, + "step": 16604 + }, + { + "epoch": 5.13, + "learning_rate": 1.7429875220758327e-05, + "loss": 0.1828, + "step": 16605 + }, + { + "epoch": 5.13, + "learning_rate": 1.7429540479704058e-05, + "loss": 0.1753, + "step": 16606 + }, + { + "epoch": 5.13, + "learning_rate": 1.742920572006715e-05, + "loss": 0.1882, + "step": 16607 + }, + { + "epoch": 5.13, + "learning_rate": 1.7428870941848446e-05, + "loss": 0.2043, + "step": 16608 + }, + { + "epoch": 5.13, + "learning_rate": 1.742853614504878e-05, + "loss": 0.1707, + "step": 16609 + }, + { + "epoch": 5.13, + "learning_rate": 1.742820132966899e-05, + "loss": 0.1727, + "step": 16610 + }, + { + "epoch": 5.13, + "learning_rate": 1.7427866495709915e-05, + "loss": 0.1632, + "step": 16611 + }, + { + "epoch": 5.13, + "learning_rate": 1.742753164317239e-05, + "loss": 0.1882, + "step": 16612 + }, + { + "epoch": 5.13, + "learning_rate": 1.7427196772057254e-05, + "loss": 0.1655, + "step": 16613 + }, + { + "epoch": 5.13, + "learning_rate": 1.7426861882365345e-05, + "loss": 0.1857, + "step": 16614 + }, + { + "epoch": 5.13, + "learning_rate": 1.7426526974097496e-05, + "loss": 0.1701, + "step": 16615 + }, + { + "epoch": 5.13, + "learning_rate": 1.7426192047254553e-05, + "loss": 0.1684, + "step": 16616 + }, + { + "epoch": 5.13, + "learning_rate": 1.7425857101837346e-05, + "loss": 0.1596, + "step": 16617 + }, + { + "epoch": 5.13, + "learning_rate": 1.742552213784672e-05, + "loss": 0.1794, + "step": 16618 + }, + { + "epoch": 5.13, + "learning_rate": 1.7425187155283506e-05, + "loss": 0.1731, + "step": 16619 + }, + { + "epoch": 5.13, + "learning_rate": 1.7424852154148546e-05, + "loss": 0.1842, + "step": 16620 + }, + { + "epoch": 5.13, + "learning_rate": 1.7424517134442674e-05, + "loss": 0.1637, + "step": 16621 + }, + { + "epoch": 5.13, + "learning_rate": 1.7424182096166733e-05, + "loss": 0.1826, + "step": 16622 + }, + { + "epoch": 5.13, + "learning_rate": 1.742384703932156e-05, + "loss": 0.1744, + "step": 16623 + }, + { + "epoch": 5.13, + "learning_rate": 1.7423511963907987e-05, + "loss": 0.1767, + "step": 16624 + }, + { + "epoch": 5.13, + "learning_rate": 1.742317686992686e-05, + "loss": 0.1794, + "step": 16625 + }, + { + "epoch": 5.13, + "learning_rate": 1.7422841757379013e-05, + "loss": 0.1748, + "step": 16626 + }, + { + "epoch": 5.13, + "learning_rate": 1.7422506626265283e-05, + "loss": 0.1837, + "step": 16627 + }, + { + "epoch": 5.14, + "learning_rate": 1.7422171476586515e-05, + "loss": 0.1741, + "step": 16628 + }, + { + "epoch": 5.14, + "learning_rate": 1.7421836308343535e-05, + "loss": 0.178, + "step": 16629 + }, + { + "epoch": 5.14, + "learning_rate": 1.7421501121537195e-05, + "loss": 0.1704, + "step": 16630 + }, + { + "epoch": 5.14, + "learning_rate": 1.7421165916168325e-05, + "loss": 0.1766, + "step": 16631 + }, + { + "epoch": 5.14, + "learning_rate": 1.7420830692237767e-05, + "loss": 0.1718, + "step": 16632 + }, + { + "epoch": 5.14, + "learning_rate": 1.7420495449746357e-05, + "loss": 0.1907, + "step": 16633 + }, + { + "epoch": 5.14, + "learning_rate": 1.7420160188694933e-05, + "loss": 0.1562, + "step": 16634 + }, + { + "epoch": 5.14, + "learning_rate": 1.7419824909084336e-05, + "loss": 0.181, + "step": 16635 + }, + { + "epoch": 5.14, + "learning_rate": 1.74194896109154e-05, + "loss": 0.1721, + "step": 16636 + }, + { + "epoch": 5.14, + "learning_rate": 1.7419154294188974e-05, + "loss": 0.1866, + "step": 16637 + }, + { + "epoch": 5.14, + "learning_rate": 1.7418818958905887e-05, + "loss": 0.1666, + "step": 16638 + }, + { + "epoch": 5.14, + "learning_rate": 1.741848360506698e-05, + "loss": 0.1813, + "step": 16639 + }, + { + "epoch": 5.14, + "learning_rate": 1.7418148232673093e-05, + "loss": 0.1777, + "step": 16640 + }, + { + "epoch": 5.14, + "learning_rate": 1.7417812841725063e-05, + "loss": 0.1551, + "step": 16641 + }, + { + "epoch": 5.14, + "learning_rate": 1.7417477432223733e-05, + "loss": 0.1902, + "step": 16642 + }, + { + "epoch": 5.14, + "learning_rate": 1.7417142004169938e-05, + "loss": 0.1659, + "step": 16643 + }, + { + "epoch": 5.14, + "learning_rate": 1.7416806557564515e-05, + "loss": 0.1664, + "step": 16644 + }, + { + "epoch": 5.14, + "learning_rate": 1.7416471092408312e-05, + "loss": 0.1615, + "step": 16645 + }, + { + "epoch": 5.14, + "learning_rate": 1.7416135608702155e-05, + "loss": 0.1584, + "step": 16646 + }, + { + "epoch": 5.14, + "learning_rate": 1.7415800106446895e-05, + "loss": 0.1821, + "step": 16647 + }, + { + "epoch": 5.14, + "learning_rate": 1.7415464585643365e-05, + "loss": 0.1851, + "step": 16648 + }, + { + "epoch": 5.14, + "learning_rate": 1.741512904629241e-05, + "loss": 0.1697, + "step": 16649 + }, + { + "epoch": 5.14, + "learning_rate": 1.7414793488394856e-05, + "loss": 0.1683, + "step": 16650 + }, + { + "epoch": 5.14, + "learning_rate": 1.7414457911951558e-05, + "loss": 0.1787, + "step": 16651 + }, + { + "epoch": 5.14, + "learning_rate": 1.7414122316963347e-05, + "loss": 0.1734, + "step": 16652 + }, + { + "epoch": 5.14, + "learning_rate": 1.741378670343106e-05, + "loss": 0.1852, + "step": 16653 + }, + { + "epoch": 5.14, + "learning_rate": 1.7413451071355544e-05, + "loss": 0.1875, + "step": 16654 + }, + { + "epoch": 5.14, + "learning_rate": 1.7413115420737635e-05, + "loss": 0.1569, + "step": 16655 + }, + { + "epoch": 5.14, + "learning_rate": 1.741277975157817e-05, + "loss": 0.1707, + "step": 16656 + }, + { + "epoch": 5.14, + "learning_rate": 1.7412444063877993e-05, + "loss": 0.1637, + "step": 16657 + }, + { + "epoch": 5.14, + "learning_rate": 1.741210835763794e-05, + "loss": 0.1684, + "step": 16658 + }, + { + "epoch": 5.14, + "learning_rate": 1.7411772632858852e-05, + "loss": 0.1566, + "step": 16659 + }, + { + "epoch": 5.15, + "learning_rate": 1.741143688954157e-05, + "loss": 0.1762, + "step": 16660 + }, + { + "epoch": 5.15, + "learning_rate": 1.741110112768693e-05, + "loss": 0.1774, + "step": 16661 + }, + { + "epoch": 5.15, + "learning_rate": 1.741076534729578e-05, + "loss": 0.1703, + "step": 16662 + }, + { + "epoch": 5.15, + "learning_rate": 1.7410429548368952e-05, + "loss": 0.163, + "step": 16663 + }, + { + "epoch": 5.15, + "learning_rate": 1.7410093730907284e-05, + "loss": 0.1778, + "step": 16664 + }, + { + "epoch": 5.15, + "learning_rate": 1.7409757894911627e-05, + "loss": 0.1559, + "step": 16665 + }, + { + "epoch": 5.15, + "learning_rate": 1.7409422040382807e-05, + "loss": 0.1778, + "step": 16666 + }, + { + "epoch": 5.15, + "learning_rate": 1.7409086167321673e-05, + "loss": 0.1846, + "step": 16667 + }, + { + "epoch": 5.15, + "learning_rate": 1.7408750275729064e-05, + "loss": 0.1751, + "step": 16668 + }, + { + "epoch": 5.15, + "learning_rate": 1.7408414365605823e-05, + "loss": 0.1816, + "step": 16669 + }, + { + "epoch": 5.15, + "learning_rate": 1.740807843695278e-05, + "loss": 0.1648, + "step": 16670 + }, + { + "epoch": 5.15, + "learning_rate": 1.7407742489770785e-05, + "loss": 0.1486, + "step": 16671 + }, + { + "epoch": 5.15, + "learning_rate": 1.7407406524060672e-05, + "loss": 0.1734, + "step": 16672 + }, + { + "epoch": 5.15, + "learning_rate": 1.740707053982329e-05, + "loss": 0.1738, + "step": 16673 + }, + { + "epoch": 5.15, + "learning_rate": 1.740673453705947e-05, + "loss": 0.176, + "step": 16674 + }, + { + "epoch": 5.15, + "learning_rate": 1.740639851577006e-05, + "loss": 0.1704, + "step": 16675 + }, + { + "epoch": 5.15, + "learning_rate": 1.740606247595589e-05, + "loss": 0.1777, + "step": 16676 + }, + { + "epoch": 5.15, + "learning_rate": 1.740572641761781e-05, + "loss": 0.1781, + "step": 16677 + }, + { + "epoch": 5.15, + "learning_rate": 1.7405390340756656e-05, + "loss": 0.183, + "step": 16678 + }, + { + "epoch": 5.15, + "learning_rate": 1.7405054245373273e-05, + "loss": 0.1842, + "step": 16679 + }, + { + "epoch": 5.15, + "learning_rate": 1.7404718131468498e-05, + "loss": 0.1692, + "step": 16680 + }, + { + "epoch": 5.15, + "learning_rate": 1.740438199904317e-05, + "loss": 0.1736, + "step": 16681 + }, + { + "epoch": 5.15, + "learning_rate": 1.7404045848098133e-05, + "loss": 0.1703, + "step": 16682 + }, + { + "epoch": 5.15, + "learning_rate": 1.7403709678634227e-05, + "loss": 0.1693, + "step": 16683 + }, + { + "epoch": 5.15, + "learning_rate": 1.7403373490652294e-05, + "loss": 0.1617, + "step": 16684 + }, + { + "epoch": 5.15, + "learning_rate": 1.7403037284153174e-05, + "loss": 0.1808, + "step": 16685 + }, + { + "epoch": 5.15, + "learning_rate": 1.7402701059137704e-05, + "loss": 0.1825, + "step": 16686 + }, + { + "epoch": 5.15, + "learning_rate": 1.7402364815606733e-05, + "loss": 0.1766, + "step": 16687 + }, + { + "epoch": 5.15, + "learning_rate": 1.7402028553561097e-05, + "loss": 0.1718, + "step": 16688 + }, + { + "epoch": 5.15, + "learning_rate": 1.7401692273001637e-05, + "loss": 0.1825, + "step": 16689 + }, + { + "epoch": 5.15, + "learning_rate": 1.7401355973929192e-05, + "loss": 0.1672, + "step": 16690 + }, + { + "epoch": 5.15, + "learning_rate": 1.7401019656344608e-05, + "loss": 0.1809, + "step": 16691 + }, + { + "epoch": 5.15, + "learning_rate": 1.7400683320248725e-05, + "loss": 0.1878, + "step": 16692 + }, + { + "epoch": 5.16, + "learning_rate": 1.740034696564238e-05, + "loss": 0.168, + "step": 16693 + }, + { + "epoch": 5.16, + "learning_rate": 1.7400010592526418e-05, + "loss": 0.1795, + "step": 16694 + }, + { + "epoch": 5.16, + "learning_rate": 1.739967420090168e-05, + "loss": 0.1888, + "step": 16695 + }, + { + "epoch": 5.16, + "learning_rate": 1.739933779076901e-05, + "loss": 0.1697, + "step": 16696 + }, + { + "epoch": 5.16, + "learning_rate": 1.7399001362129245e-05, + "loss": 0.165, + "step": 16697 + }, + { + "epoch": 5.16, + "learning_rate": 1.7398664914983226e-05, + "loss": 0.1875, + "step": 16698 + }, + { + "epoch": 5.16, + "learning_rate": 1.73983284493318e-05, + "loss": 0.1606, + "step": 16699 + }, + { + "epoch": 5.16, + "learning_rate": 1.7397991965175806e-05, + "loss": 0.1707, + "step": 16700 + }, + { + "epoch": 5.16, + "learning_rate": 1.7397655462516084e-05, + "loss": 0.1944, + "step": 16701 + }, + { + "epoch": 5.16, + "learning_rate": 1.739731894135347e-05, + "loss": 0.1705, + "step": 16702 + }, + { + "epoch": 5.16, + "learning_rate": 1.739698240168882e-05, + "loss": 0.1778, + "step": 16703 + }, + { + "epoch": 5.16, + "learning_rate": 1.7396645843522963e-05, + "loss": 0.179, + "step": 16704 + }, + { + "epoch": 5.16, + "learning_rate": 1.739630926685675e-05, + "loss": 0.1759, + "step": 16705 + }, + { + "epoch": 5.16, + "learning_rate": 1.7395972671691016e-05, + "loss": 0.1754, + "step": 16706 + }, + { + "epoch": 5.16, + "learning_rate": 1.7395636058026607e-05, + "loss": 0.1668, + "step": 16707 + }, + { + "epoch": 5.16, + "learning_rate": 1.739529942586436e-05, + "loss": 0.1739, + "step": 16708 + }, + { + "epoch": 5.16, + "learning_rate": 1.739496277520512e-05, + "loss": 0.1494, + "step": 16709 + }, + { + "epoch": 5.16, + "learning_rate": 1.7394626106049733e-05, + "loss": 0.1932, + "step": 16710 + }, + { + "epoch": 5.16, + "learning_rate": 1.7394289418399036e-05, + "loss": 0.1635, + "step": 16711 + }, + { + "epoch": 5.16, + "learning_rate": 1.7393952712253873e-05, + "loss": 0.1809, + "step": 16712 + }, + { + "epoch": 5.16, + "learning_rate": 1.7393615987615087e-05, + "loss": 0.1727, + "step": 16713 + }, + { + "epoch": 5.16, + "learning_rate": 1.7393279244483515e-05, + "loss": 0.1818, + "step": 16714 + }, + { + "epoch": 5.16, + "learning_rate": 1.7392942482860007e-05, + "loss": 0.1801, + "step": 16715 + }, + { + "epoch": 5.16, + "learning_rate": 1.7392605702745398e-05, + "loss": 0.1732, + "step": 16716 + }, + { + "epoch": 5.16, + "learning_rate": 1.7392268904140537e-05, + "loss": 0.1795, + "step": 16717 + }, + { + "epoch": 5.16, + "learning_rate": 1.7391932087046262e-05, + "loss": 0.1567, + "step": 16718 + }, + { + "epoch": 5.16, + "learning_rate": 1.7391595251463415e-05, + "loss": 0.1738, + "step": 16719 + }, + { + "epoch": 5.16, + "learning_rate": 1.739125839739284e-05, + "loss": 0.1708, + "step": 16720 + }, + { + "epoch": 5.16, + "learning_rate": 1.7390921524835384e-05, + "loss": 0.1609, + "step": 16721 + }, + { + "epoch": 5.16, + "learning_rate": 1.7390584633791883e-05, + "loss": 0.1844, + "step": 16722 + }, + { + "epoch": 5.16, + "learning_rate": 1.7390247724263182e-05, + "loss": 0.1658, + "step": 16723 + }, + { + "epoch": 5.16, + "learning_rate": 1.7389910796250122e-05, + "loss": 0.1778, + "step": 16724 + }, + { + "epoch": 5.17, + "learning_rate": 1.738957384975355e-05, + "loss": 0.1744, + "step": 16725 + }, + { + "epoch": 5.17, + "learning_rate": 1.73892368847743e-05, + "loss": 0.1889, + "step": 16726 + }, + { + "epoch": 5.17, + "learning_rate": 1.7388899901313227e-05, + "loss": 0.1761, + "step": 16727 + }, + { + "epoch": 5.17, + "learning_rate": 1.7388562899371165e-05, + "loss": 0.1854, + "step": 16728 + }, + { + "epoch": 5.17, + "learning_rate": 1.7388225878948965e-05, + "loss": 0.1904, + "step": 16729 + }, + { + "epoch": 5.17, + "learning_rate": 1.7387888840047457e-05, + "loss": 0.1792, + "step": 16730 + }, + { + "epoch": 5.17, + "learning_rate": 1.7387551782667495e-05, + "loss": 0.1901, + "step": 16731 + }, + { + "epoch": 5.17, + "learning_rate": 1.7387214706809916e-05, + "loss": 0.1677, + "step": 16732 + }, + { + "epoch": 5.17, + "learning_rate": 1.7386877612475567e-05, + "loss": 0.1749, + "step": 16733 + }, + { + "epoch": 5.17, + "learning_rate": 1.738654049966529e-05, + "loss": 0.187, + "step": 16734 + }, + { + "epoch": 5.17, + "learning_rate": 1.738620336837993e-05, + "loss": 0.1645, + "step": 16735 + }, + { + "epoch": 5.17, + "learning_rate": 1.7385866218620328e-05, + "loss": 0.1672, + "step": 16736 + }, + { + "epoch": 5.17, + "learning_rate": 1.7385529050387324e-05, + "loss": 0.1865, + "step": 16737 + }, + { + "epoch": 5.17, + "learning_rate": 1.738519186368177e-05, + "loss": 0.175, + "step": 16738 + }, + { + "epoch": 5.17, + "learning_rate": 1.73848546585045e-05, + "loss": 0.1766, + "step": 16739 + }, + { + "epoch": 5.17, + "learning_rate": 1.7384517434856364e-05, + "loss": 0.1797, + "step": 16740 + }, + { + "epoch": 5.17, + "learning_rate": 1.7384180192738204e-05, + "loss": 0.1579, + "step": 16741 + }, + { + "epoch": 5.17, + "learning_rate": 1.7383842932150857e-05, + "loss": 0.1751, + "step": 16742 + }, + { + "epoch": 5.17, + "learning_rate": 1.7383505653095177e-05, + "loss": 0.1699, + "step": 16743 + }, + { + "epoch": 5.17, + "learning_rate": 1.7383168355572e-05, + "loss": 0.1763, + "step": 16744 + }, + { + "epoch": 5.17, + "learning_rate": 1.7382831039582172e-05, + "loss": 0.1753, + "step": 16745 + }, + { + "epoch": 5.17, + "learning_rate": 1.738249370512654e-05, + "loss": 0.1858, + "step": 16746 + }, + { + "epoch": 5.17, + "learning_rate": 1.7382156352205943e-05, + "loss": 0.1769, + "step": 16747 + }, + { + "epoch": 5.17, + "learning_rate": 1.7381818980821225e-05, + "loss": 0.197, + "step": 16748 + }, + { + "epoch": 5.17, + "learning_rate": 1.7381481590973235e-05, + "loss": 0.1705, + "step": 16749 + }, + { + "epoch": 5.17, + "learning_rate": 1.7381144182662813e-05, + "loss": 0.1743, + "step": 16750 + }, + { + "epoch": 5.17, + "learning_rate": 1.73808067558908e-05, + "loss": 0.1723, + "step": 16751 + }, + { + "epoch": 5.17, + "learning_rate": 1.7380469310658044e-05, + "loss": 0.1609, + "step": 16752 + }, + { + "epoch": 5.17, + "learning_rate": 1.738013184696539e-05, + "loss": 0.1827, + "step": 16753 + }, + { + "epoch": 5.17, + "learning_rate": 1.7379794364813678e-05, + "loss": 0.1668, + "step": 16754 + }, + { + "epoch": 5.17, + "learning_rate": 1.7379456864203757e-05, + "loss": 0.1624, + "step": 16755 + }, + { + "epoch": 5.17, + "learning_rate": 1.7379119345136466e-05, + "loss": 0.1656, + "step": 16756 + }, + { + "epoch": 5.17, + "learning_rate": 1.7378781807612652e-05, + "loss": 0.1893, + "step": 16757 + }, + { + "epoch": 5.18, + "learning_rate": 1.737844425163316e-05, + "loss": 0.1749, + "step": 16758 + }, + { + "epoch": 5.18, + "learning_rate": 1.7378106677198832e-05, + "loss": 0.1738, + "step": 16759 + }, + { + "epoch": 5.18, + "learning_rate": 1.7377769084310515e-05, + "loss": 0.1759, + "step": 16760 + }, + { + "epoch": 5.18, + "learning_rate": 1.737743147296905e-05, + "loss": 0.1704, + "step": 16761 + }, + { + "epoch": 5.18, + "learning_rate": 1.7377093843175282e-05, + "loss": 0.1714, + "step": 16762 + }, + { + "epoch": 5.18, + "learning_rate": 1.7376756194930063e-05, + "loss": 0.1646, + "step": 16763 + }, + { + "epoch": 5.18, + "learning_rate": 1.7376418528234226e-05, + "loss": 0.1836, + "step": 16764 + }, + { + "epoch": 5.18, + "learning_rate": 1.737608084308862e-05, + "loss": 0.1897, + "step": 16765 + }, + { + "epoch": 5.18, + "learning_rate": 1.7375743139494097e-05, + "loss": 0.1824, + "step": 16766 + }, + { + "epoch": 5.18, + "learning_rate": 1.737540541745149e-05, + "loss": 0.1832, + "step": 16767 + }, + { + "epoch": 5.18, + "learning_rate": 1.737506767696165e-05, + "loss": 0.1617, + "step": 16768 + }, + { + "epoch": 5.18, + "learning_rate": 1.737472991802542e-05, + "loss": 0.1684, + "step": 16769 + }, + { + "epoch": 5.18, + "learning_rate": 1.7374392140643647e-05, + "loss": 0.172, + "step": 16770 + }, + { + "epoch": 5.18, + "learning_rate": 1.737405434481717e-05, + "loss": 0.1722, + "step": 16771 + }, + { + "epoch": 5.18, + "learning_rate": 1.7373716530546842e-05, + "loss": 0.1644, + "step": 16772 + }, + { + "epoch": 5.18, + "learning_rate": 1.7373378697833506e-05, + "loss": 0.1757, + "step": 16773 + }, + { + "epoch": 5.18, + "learning_rate": 1.7373040846678e-05, + "loss": 0.1771, + "step": 16774 + }, + { + "epoch": 5.18, + "learning_rate": 1.7372702977081178e-05, + "loss": 0.1722, + "step": 16775 + }, + { + "epoch": 5.18, + "learning_rate": 1.737236508904388e-05, + "loss": 0.1835, + "step": 16776 + }, + { + "epoch": 5.18, + "learning_rate": 1.737202718256695e-05, + "loss": 0.179, + "step": 16777 + }, + { + "epoch": 5.18, + "learning_rate": 1.737168925765124e-05, + "loss": 0.1992, + "step": 16778 + }, + { + "epoch": 5.18, + "learning_rate": 1.7371351314297586e-05, + "loss": 0.1829, + "step": 16779 + }, + { + "epoch": 5.18, + "learning_rate": 1.7371013352506838e-05, + "loss": 0.1979, + "step": 16780 + }, + { + "epoch": 5.18, + "learning_rate": 1.7370675372279845e-05, + "loss": 0.1695, + "step": 16781 + }, + { + "epoch": 5.18, + "learning_rate": 1.7370337373617444e-05, + "loss": 0.1728, + "step": 16782 + }, + { + "epoch": 5.18, + "learning_rate": 1.736999935652049e-05, + "loss": 0.1808, + "step": 16783 + }, + { + "epoch": 5.18, + "learning_rate": 1.7369661320989817e-05, + "loss": 0.1779, + "step": 16784 + }, + { + "epoch": 5.18, + "learning_rate": 1.7369323267026286e-05, + "loss": 0.1733, + "step": 16785 + }, + { + "epoch": 5.18, + "learning_rate": 1.7368985194630727e-05, + "loss": 0.1774, + "step": 16786 + }, + { + "epoch": 5.18, + "learning_rate": 1.7368647103803993e-05, + "loss": 0.1758, + "step": 16787 + }, + { + "epoch": 5.18, + "learning_rate": 1.736830899454693e-05, + "loss": 0.1757, + "step": 16788 + }, + { + "epoch": 5.18, + "learning_rate": 1.736797086686038e-05, + "loss": 0.1845, + "step": 16789 + }, + { + "epoch": 5.19, + "learning_rate": 1.7367632720745194e-05, + "loss": 0.1483, + "step": 16790 + }, + { + "epoch": 5.19, + "learning_rate": 1.7367294556202212e-05, + "loss": 0.1751, + "step": 16791 + }, + { + "epoch": 5.19, + "learning_rate": 1.7366956373232286e-05, + "loss": 0.178, + "step": 16792 + }, + { + "epoch": 5.19, + "learning_rate": 1.7366618171836256e-05, + "loss": 0.173, + "step": 16793 + }, + { + "epoch": 5.19, + "learning_rate": 1.736627995201497e-05, + "loss": 0.1858, + "step": 16794 + }, + { + "epoch": 5.19, + "learning_rate": 1.7365941713769272e-05, + "loss": 0.1824, + "step": 16795 + }, + { + "epoch": 5.19, + "learning_rate": 1.7365603457100015e-05, + "loss": 0.1885, + "step": 16796 + }, + { + "epoch": 5.19, + "learning_rate": 1.7365265182008036e-05, + "loss": 0.1639, + "step": 16797 + }, + { + "epoch": 5.19, + "learning_rate": 1.7364926888494192e-05, + "loss": 0.181, + "step": 16798 + }, + { + "epoch": 5.19, + "learning_rate": 1.7364588576559315e-05, + "loss": 0.1689, + "step": 16799 + }, + { + "epoch": 5.19, + "learning_rate": 1.7364250246204264e-05, + "loss": 0.1923, + "step": 16800 + }, + { + "epoch": 5.19, + "learning_rate": 1.7363911897429878e-05, + "loss": 0.1754, + "step": 16801 + }, + { + "epoch": 5.19, + "learning_rate": 1.7363573530237004e-05, + "loss": 0.1744, + "step": 16802 + }, + { + "epoch": 5.19, + "learning_rate": 1.7363235144626494e-05, + "loss": 0.1799, + "step": 16803 + }, + { + "epoch": 5.19, + "learning_rate": 1.7362896740599187e-05, + "loss": 0.1723, + "step": 16804 + }, + { + "epoch": 5.19, + "learning_rate": 1.7362558318155933e-05, + "loss": 0.1665, + "step": 16805 + }, + { + "epoch": 5.19, + "learning_rate": 1.7362219877297577e-05, + "loss": 0.1738, + "step": 16806 + }, + { + "epoch": 5.19, + "learning_rate": 1.7361881418024964e-05, + "loss": 0.1712, + "step": 16807 + }, + { + "epoch": 5.19, + "learning_rate": 1.7361542940338947e-05, + "loss": 0.1662, + "step": 16808 + }, + { + "epoch": 5.19, + "learning_rate": 1.7361204444240365e-05, + "loss": 0.1951, + "step": 16809 + }, + { + "epoch": 5.19, + "learning_rate": 1.736086592973007e-05, + "loss": 0.1764, + "step": 16810 + }, + { + "epoch": 5.19, + "learning_rate": 1.736052739680891e-05, + "loss": 0.1808, + "step": 16811 + }, + { + "epoch": 5.19, + "learning_rate": 1.7360188845477724e-05, + "loss": 0.1962, + "step": 16812 + }, + { + "epoch": 5.19, + "learning_rate": 1.7359850275737366e-05, + "loss": 0.1661, + "step": 16813 + }, + { + "epoch": 5.19, + "learning_rate": 1.7359511687588674e-05, + "loss": 0.1815, + "step": 16814 + }, + { + "epoch": 5.19, + "learning_rate": 1.735917308103251e-05, + "loss": 0.169, + "step": 16815 + }, + { + "epoch": 5.19, + "learning_rate": 1.7358834456069705e-05, + "loss": 0.1843, + "step": 16816 + }, + { + "epoch": 5.19, + "learning_rate": 1.7358495812701116e-05, + "loss": 0.1804, + "step": 16817 + }, + { + "epoch": 5.19, + "learning_rate": 1.7358157150927585e-05, + "loss": 0.1886, + "step": 16818 + }, + { + "epoch": 5.19, + "learning_rate": 1.7357818470749962e-05, + "loss": 0.1843, + "step": 16819 + }, + { + "epoch": 5.19, + "learning_rate": 1.7357479772169092e-05, + "loss": 0.1887, + "step": 16820 + }, + { + "epoch": 5.19, + "learning_rate": 1.7357141055185825e-05, + "loss": 0.1819, + "step": 16821 + }, + { + "epoch": 5.2, + "learning_rate": 1.7356802319801004e-05, + "loss": 0.1822, + "step": 16822 + }, + { + "epoch": 5.2, + "learning_rate": 1.7356463566015484e-05, + "loss": 0.1838, + "step": 16823 + }, + { + "epoch": 5.2, + "learning_rate": 1.73561247938301e-05, + "loss": 0.1811, + "step": 16824 + }, + { + "epoch": 5.2, + "learning_rate": 1.735578600324571e-05, + "loss": 0.1699, + "step": 16825 + }, + { + "epoch": 5.2, + "learning_rate": 1.7355447194263156e-05, + "loss": 0.1784, + "step": 16826 + }, + { + "epoch": 5.2, + "learning_rate": 1.735510836688329e-05, + "loss": 0.1689, + "step": 16827 + }, + { + "epoch": 5.2, + "learning_rate": 1.7354769521106955e-05, + "loss": 0.1603, + "step": 16828 + }, + { + "epoch": 5.2, + "learning_rate": 1.7354430656934996e-05, + "loss": 0.1794, + "step": 16829 + }, + { + "epoch": 5.2, + "learning_rate": 1.735409177436827e-05, + "loss": 0.1892, + "step": 16830 + }, + { + "epoch": 5.2, + "learning_rate": 1.735375287340762e-05, + "loss": 0.1742, + "step": 16831 + }, + { + "epoch": 5.2, + "learning_rate": 1.7353413954053888e-05, + "loss": 0.1744, + "step": 16832 + }, + { + "epoch": 5.2, + "learning_rate": 1.735307501630793e-05, + "loss": 0.1718, + "step": 16833 + }, + { + "epoch": 5.2, + "learning_rate": 1.7352736060170587e-05, + "loss": 0.1615, + "step": 16834 + }, + { + "epoch": 5.2, + "learning_rate": 1.735239708564271e-05, + "loss": 0.1719, + "step": 16835 + }, + { + "epoch": 5.2, + "learning_rate": 1.7352058092725152e-05, + "loss": 0.1826, + "step": 16836 + }, + { + "epoch": 5.2, + "learning_rate": 1.7351719081418752e-05, + "loss": 0.1606, + "step": 16837 + }, + { + "epoch": 5.2, + "learning_rate": 1.735138005172436e-05, + "loss": 0.1819, + "step": 16838 + }, + { + "epoch": 5.2, + "learning_rate": 1.735104100364283e-05, + "loss": 0.1896, + "step": 16839 + }, + { + "epoch": 5.2, + "learning_rate": 1.7350701937175002e-05, + "loss": 0.1756, + "step": 16840 + }, + { + "epoch": 5.2, + "learning_rate": 1.735036285232173e-05, + "loss": 0.1746, + "step": 16841 + }, + { + "epoch": 5.2, + "learning_rate": 1.735002374908386e-05, + "loss": 0.1977, + "step": 16842 + }, + { + "epoch": 5.2, + "learning_rate": 1.7349684627462238e-05, + "loss": 0.182, + "step": 16843 + }, + { + "epoch": 5.2, + "learning_rate": 1.7349345487457717e-05, + "loss": 0.1695, + "step": 16844 + }, + { + "epoch": 5.2, + "learning_rate": 1.734900632907114e-05, + "loss": 0.1663, + "step": 16845 + }, + { + "epoch": 5.2, + "learning_rate": 1.7348667152303356e-05, + "loss": 0.1861, + "step": 16846 + }, + { + "epoch": 5.2, + "learning_rate": 1.734832795715522e-05, + "loss": 0.1778, + "step": 16847 + }, + { + "epoch": 5.2, + "learning_rate": 1.7347988743627576e-05, + "loss": 0.1873, + "step": 16848 + }, + { + "epoch": 5.2, + "learning_rate": 1.7347649511721267e-05, + "loss": 0.1806, + "step": 16849 + }, + { + "epoch": 5.2, + "learning_rate": 1.734731026143715e-05, + "loss": 0.1739, + "step": 16850 + }, + { + "epoch": 5.2, + "learning_rate": 1.734697099277607e-05, + "loss": 0.1751, + "step": 16851 + }, + { + "epoch": 5.2, + "learning_rate": 1.7346631705738872e-05, + "loss": 0.1726, + "step": 16852 + }, + { + "epoch": 5.2, + "learning_rate": 1.734629240032641e-05, + "loss": 0.1774, + "step": 16853 + }, + { + "epoch": 5.2, + "learning_rate": 1.734595307653953e-05, + "loss": 0.1717, + "step": 16854 + }, + { + "epoch": 5.21, + "learning_rate": 1.7345613734379084e-05, + "loss": 0.164, + "step": 16855 + }, + { + "epoch": 5.21, + "learning_rate": 1.7345274373845916e-05, + "loss": 0.164, + "step": 16856 + }, + { + "epoch": 5.21, + "learning_rate": 1.7344934994940882e-05, + "loss": 0.1949, + "step": 16857 + }, + { + "epoch": 5.21, + "learning_rate": 1.734459559766482e-05, + "loss": 0.1743, + "step": 16858 + }, + { + "epoch": 5.21, + "learning_rate": 1.7344256182018587e-05, + "loss": 0.1784, + "step": 16859 + }, + { + "epoch": 5.21, + "learning_rate": 1.734391674800303e-05, + "loss": 0.1756, + "step": 16860 + }, + { + "epoch": 5.21, + "learning_rate": 1.7343577295619e-05, + "loss": 0.1856, + "step": 16861 + }, + { + "epoch": 5.21, + "learning_rate": 1.734323782486734e-05, + "loss": 0.1795, + "step": 16862 + }, + { + "epoch": 5.21, + "learning_rate": 1.7342898335748906e-05, + "loss": 0.178, + "step": 16863 + }, + { + "epoch": 5.21, + "learning_rate": 1.734255882826454e-05, + "loss": 0.1825, + "step": 16864 + }, + { + "epoch": 5.21, + "learning_rate": 1.73422193024151e-05, + "loss": 0.1736, + "step": 16865 + }, + { + "epoch": 5.21, + "learning_rate": 1.7341879758201424e-05, + "loss": 0.1794, + "step": 16866 + }, + { + "epoch": 5.21, + "learning_rate": 1.7341540195624373e-05, + "loss": 0.1722, + "step": 16867 + }, + { + "epoch": 5.21, + "learning_rate": 1.7341200614684792e-05, + "loss": 0.1623, + "step": 16868 + }, + { + "epoch": 5.21, + "learning_rate": 1.7340861015383526e-05, + "loss": 0.1643, + "step": 16869 + }, + { + "epoch": 5.21, + "learning_rate": 1.7340521397721425e-05, + "loss": 0.1711, + "step": 16870 + }, + { + "epoch": 5.21, + "learning_rate": 1.734018176169935e-05, + "loss": 0.1808, + "step": 16871 + }, + { + "epoch": 5.21, + "learning_rate": 1.7339842107318134e-05, + "loss": 0.1806, + "step": 16872 + }, + { + "epoch": 5.21, + "learning_rate": 1.7339502434578637e-05, + "loss": 0.1653, + "step": 16873 + }, + { + "epoch": 5.21, + "learning_rate": 1.7339162743481703e-05, + "loss": 0.1782, + "step": 16874 + }, + { + "epoch": 5.21, + "learning_rate": 1.733882303402819e-05, + "loss": 0.1761, + "step": 16875 + }, + { + "epoch": 5.21, + "learning_rate": 1.7338483306218935e-05, + "loss": 0.1908, + "step": 16876 + }, + { + "epoch": 5.21, + "learning_rate": 1.73381435600548e-05, + "loss": 0.1658, + "step": 16877 + }, + { + "epoch": 5.21, + "learning_rate": 1.7337803795536627e-05, + "loss": 0.1783, + "step": 16878 + }, + { + "epoch": 5.21, + "learning_rate": 1.7337464012665273e-05, + "loss": 0.1596, + "step": 16879 + }, + { + "epoch": 5.21, + "learning_rate": 1.7337124211441578e-05, + "loss": 0.1837, + "step": 16880 + }, + { + "epoch": 5.21, + "learning_rate": 1.73367843918664e-05, + "loss": 0.177, + "step": 16881 + }, + { + "epoch": 5.21, + "learning_rate": 1.7336444553940587e-05, + "loss": 0.1861, + "step": 16882 + }, + { + "epoch": 5.21, + "learning_rate": 1.7336104697664985e-05, + "loss": 0.1824, + "step": 16883 + }, + { + "epoch": 5.21, + "learning_rate": 1.7335764823040447e-05, + "loss": 0.1913, + "step": 16884 + }, + { + "epoch": 5.21, + "learning_rate": 1.7335424930067823e-05, + "loss": 0.196, + "step": 16885 + }, + { + "epoch": 5.21, + "learning_rate": 1.7335085018747965e-05, + "loss": 0.1692, + "step": 16886 + }, + { + "epoch": 5.22, + "learning_rate": 1.733474508908172e-05, + "loss": 0.1942, + "step": 16887 + }, + { + "epoch": 5.22, + "learning_rate": 1.7334405141069944e-05, + "loss": 0.177, + "step": 16888 + }, + { + "epoch": 5.22, + "learning_rate": 1.7334065174713476e-05, + "loss": 0.1729, + "step": 16889 + }, + { + "epoch": 5.22, + "learning_rate": 1.733372519001318e-05, + "loss": 0.1892, + "step": 16890 + }, + { + "epoch": 5.22, + "learning_rate": 1.7333385186969897e-05, + "loss": 0.1597, + "step": 16891 + }, + { + "epoch": 5.22, + "learning_rate": 1.733304516558448e-05, + "loss": 0.1572, + "step": 16892 + }, + { + "epoch": 5.22, + "learning_rate": 1.733270512585778e-05, + "loss": 0.2011, + "step": 16893 + }, + { + "epoch": 5.22, + "learning_rate": 1.7332365067790647e-05, + "loss": 0.2002, + "step": 16894 + }, + { + "epoch": 5.22, + "learning_rate": 1.7332024991383935e-05, + "loss": 0.1761, + "step": 16895 + }, + { + "epoch": 5.22, + "learning_rate": 1.7331684896638485e-05, + "loss": 0.162, + "step": 16896 + }, + { + "epoch": 5.22, + "learning_rate": 1.7331344783555155e-05, + "loss": 0.1691, + "step": 16897 + }, + { + "epoch": 5.22, + "learning_rate": 1.7331004652134798e-05, + "loss": 0.1795, + "step": 16898 + }, + { + "epoch": 5.22, + "learning_rate": 1.7330664502378258e-05, + "loss": 0.1769, + "step": 16899 + }, + { + "epoch": 5.22, + "learning_rate": 1.733032433428639e-05, + "loss": 0.1911, + "step": 16900 + }, + { + "epoch": 5.22, + "learning_rate": 1.7329984147860045e-05, + "loss": 0.1822, + "step": 16901 + }, + { + "epoch": 5.22, + "learning_rate": 1.7329643943100072e-05, + "loss": 0.1755, + "step": 16902 + }, + { + "epoch": 5.22, + "learning_rate": 1.732930372000732e-05, + "loss": 0.2033, + "step": 16903 + }, + { + "epoch": 5.22, + "learning_rate": 1.7328963478582646e-05, + "loss": 0.1841, + "step": 16904 + }, + { + "epoch": 5.22, + "learning_rate": 1.7328623218826898e-05, + "loss": 0.1908, + "step": 16905 + }, + { + "epoch": 5.22, + "learning_rate": 1.732828294074093e-05, + "loss": 0.1826, + "step": 16906 + }, + { + "epoch": 5.22, + "learning_rate": 1.732794264432558e-05, + "loss": 0.169, + "step": 16907 + }, + { + "epoch": 5.22, + "learning_rate": 1.7327602329581718e-05, + "loss": 0.1722, + "step": 16908 + }, + { + "epoch": 5.22, + "learning_rate": 1.7327261996510182e-05, + "loss": 0.1606, + "step": 16909 + }, + { + "epoch": 5.22, + "learning_rate": 1.732692164511183e-05, + "loss": 0.1884, + "step": 16910 + }, + { + "epoch": 5.22, + "learning_rate": 1.7326581275387507e-05, + "loss": 0.1882, + "step": 16911 + }, + { + "epoch": 5.22, + "learning_rate": 1.7326240887338064e-05, + "loss": 0.1727, + "step": 16912 + }, + { + "epoch": 5.22, + "learning_rate": 1.7325900480964365e-05, + "loss": 0.1807, + "step": 16913 + }, + { + "epoch": 5.22, + "learning_rate": 1.732556005626725e-05, + "loss": 0.1908, + "step": 16914 + }, + { + "epoch": 5.22, + "learning_rate": 1.732521961324757e-05, + "loss": 0.1776, + "step": 16915 + }, + { + "epoch": 5.22, + "learning_rate": 1.7324879151906184e-05, + "loss": 0.1874, + "step": 16916 + }, + { + "epoch": 5.22, + "learning_rate": 1.7324538672243938e-05, + "loss": 0.1761, + "step": 16917 + }, + { + "epoch": 5.22, + "learning_rate": 1.7324198174261684e-05, + "loss": 0.1727, + "step": 16918 + }, + { + "epoch": 5.23, + "learning_rate": 1.7323857657960273e-05, + "loss": 0.1726, + "step": 16919 + }, + { + "epoch": 5.23, + "learning_rate": 1.7323517123340565e-05, + "loss": 0.1781, + "step": 16920 + }, + { + "epoch": 5.23, + "learning_rate": 1.7323176570403396e-05, + "loss": 0.1685, + "step": 16921 + }, + { + "epoch": 5.23, + "learning_rate": 1.7322835999149635e-05, + "loss": 0.1912, + "step": 16922 + }, + { + "epoch": 5.23, + "learning_rate": 1.7322495409580117e-05, + "loss": 0.1703, + "step": 16923 + }, + { + "epoch": 5.23, + "learning_rate": 1.7322154801695708e-05, + "loss": 0.1858, + "step": 16924 + }, + { + "epoch": 5.23, + "learning_rate": 1.7321814175497253e-05, + "loss": 0.1819, + "step": 16925 + }, + { + "epoch": 5.23, + "learning_rate": 1.7321473530985608e-05, + "loss": 0.1759, + "step": 16926 + }, + { + "epoch": 5.23, + "learning_rate": 1.732113286816162e-05, + "loss": 0.188, + "step": 16927 + }, + { + "epoch": 5.23, + "learning_rate": 1.7320792187026142e-05, + "loss": 0.1894, + "step": 16928 + }, + { + "epoch": 5.23, + "learning_rate": 1.732045148758003e-05, + "loss": 0.174, + "step": 16929 + }, + { + "epoch": 5.23, + "learning_rate": 1.732011076982413e-05, + "loss": 0.1934, + "step": 16930 + }, + { + "epoch": 5.23, + "learning_rate": 1.73197700337593e-05, + "loss": 0.1781, + "step": 16931 + }, + { + "epoch": 5.23, + "learning_rate": 1.731942927938639e-05, + "loss": 0.1796, + "step": 16932 + }, + { + "epoch": 5.23, + "learning_rate": 1.7319088506706255e-05, + "loss": 0.1677, + "step": 16933 + }, + { + "epoch": 5.23, + "learning_rate": 1.7318747715719743e-05, + "loss": 0.1792, + "step": 16934 + }, + { + "epoch": 5.23, + "learning_rate": 1.7318406906427707e-05, + "loss": 0.176, + "step": 16935 + }, + { + "epoch": 5.23, + "learning_rate": 1.7318066078831e-05, + "loss": 0.1817, + "step": 16936 + }, + { + "epoch": 5.23, + "learning_rate": 1.7317725232930476e-05, + "loss": 0.1744, + "step": 16937 + }, + { + "epoch": 5.23, + "learning_rate": 1.7317384368726985e-05, + "loss": 0.1696, + "step": 16938 + }, + { + "epoch": 5.23, + "learning_rate": 1.7317043486221386e-05, + "loss": 0.1612, + "step": 16939 + }, + { + "epoch": 5.23, + "learning_rate": 1.731670258541452e-05, + "loss": 0.174, + "step": 16940 + }, + { + "epoch": 5.23, + "learning_rate": 1.7316361666307252e-05, + "loss": 0.1821, + "step": 16941 + }, + { + "epoch": 5.23, + "learning_rate": 1.7316020728900426e-05, + "loss": 0.1692, + "step": 16942 + }, + { + "epoch": 5.23, + "learning_rate": 1.73156797731949e-05, + "loss": 0.1834, + "step": 16943 + }, + { + "epoch": 5.23, + "learning_rate": 1.7315338799191524e-05, + "loss": 0.1703, + "step": 16944 + }, + { + "epoch": 5.23, + "learning_rate": 1.731499780689115e-05, + "loss": 0.1675, + "step": 16945 + }, + { + "epoch": 5.23, + "learning_rate": 1.7314656796294632e-05, + "loss": 0.1716, + "step": 16946 + }, + { + "epoch": 5.23, + "learning_rate": 1.7314315767402827e-05, + "loss": 0.1793, + "step": 16947 + }, + { + "epoch": 5.23, + "learning_rate": 1.731397472021658e-05, + "loss": 0.1688, + "step": 16948 + }, + { + "epoch": 5.23, + "learning_rate": 1.731363365473675e-05, + "loss": 0.1727, + "step": 16949 + }, + { + "epoch": 5.23, + "learning_rate": 1.7313292570964185e-05, + "loss": 0.1805, + "step": 16950 + }, + { + "epoch": 5.23, + "learning_rate": 1.7312951468899744e-05, + "loss": 0.182, + "step": 16951 + }, + { + "epoch": 5.24, + "learning_rate": 1.7312610348544278e-05, + "loss": 0.1616, + "step": 16952 + }, + { + "epoch": 5.24, + "learning_rate": 1.7312269209898642e-05, + "loss": 0.1826, + "step": 16953 + }, + { + "epoch": 5.24, + "learning_rate": 1.7311928052963685e-05, + "loss": 0.1883, + "step": 16954 + }, + { + "epoch": 5.24, + "learning_rate": 1.731158687774026e-05, + "loss": 0.1782, + "step": 16955 + }, + { + "epoch": 5.24, + "learning_rate": 1.7311245684229228e-05, + "loss": 0.1861, + "step": 16956 + }, + { + "epoch": 5.24, + "learning_rate": 1.7310904472431432e-05, + "loss": 0.1638, + "step": 16957 + }, + { + "epoch": 5.24, + "learning_rate": 1.7310563242347733e-05, + "loss": 0.1765, + "step": 16958 + }, + { + "epoch": 5.24, + "learning_rate": 1.731022199397898e-05, + "loss": 0.1666, + "step": 16959 + }, + { + "epoch": 5.24, + "learning_rate": 1.7309880727326033e-05, + "loss": 0.1831, + "step": 16960 + }, + { + "epoch": 5.24, + "learning_rate": 1.7309539442389737e-05, + "loss": 0.1701, + "step": 16961 + }, + { + "epoch": 5.24, + "learning_rate": 1.7309198139170947e-05, + "loss": 0.1876, + "step": 16962 + }, + { + "epoch": 5.24, + "learning_rate": 1.7308856817670526e-05, + "loss": 0.1811, + "step": 16963 + }, + { + "epoch": 5.24, + "learning_rate": 1.7308515477889317e-05, + "loss": 0.1945, + "step": 16964 + }, + { + "epoch": 5.24, + "learning_rate": 1.730817411982818e-05, + "loss": 0.1793, + "step": 16965 + }, + { + "epoch": 5.24, + "learning_rate": 1.7307832743487965e-05, + "loss": 0.1732, + "step": 16966 + }, + { + "epoch": 5.24, + "learning_rate": 1.730749134886953e-05, + "loss": 0.1634, + "step": 16967 + }, + { + "epoch": 5.24, + "learning_rate": 1.730714993597372e-05, + "loss": 0.1757, + "step": 16968 + }, + { + "epoch": 5.24, + "learning_rate": 1.73068085048014e-05, + "loss": 0.1831, + "step": 16969 + }, + { + "epoch": 5.24, + "learning_rate": 1.730646705535342e-05, + "loss": 0.1785, + "step": 16970 + }, + { + "epoch": 5.24, + "learning_rate": 1.7306125587630634e-05, + "loss": 0.1878, + "step": 16971 + }, + { + "epoch": 5.24, + "learning_rate": 1.730578410163389e-05, + "loss": 0.1828, + "step": 16972 + }, + { + "epoch": 5.24, + "learning_rate": 1.730544259736405e-05, + "loss": 0.1711, + "step": 16973 + }, + { + "epoch": 5.24, + "learning_rate": 1.730510107482197e-05, + "loss": 0.1631, + "step": 16974 + }, + { + "epoch": 5.24, + "learning_rate": 1.730475953400849e-05, + "loss": 0.1762, + "step": 16975 + }, + { + "epoch": 5.24, + "learning_rate": 1.7304417974924487e-05, + "loss": 0.1844, + "step": 16976 + }, + { + "epoch": 5.24, + "learning_rate": 1.7304076397570794e-05, + "loss": 0.1773, + "step": 16977 + }, + { + "epoch": 5.24, + "learning_rate": 1.730373480194827e-05, + "loss": 0.1779, + "step": 16978 + }, + { + "epoch": 5.24, + "learning_rate": 1.7303393188057783e-05, + "loss": 0.1796, + "step": 16979 + }, + { + "epoch": 5.24, + "learning_rate": 1.7303051555900174e-05, + "loss": 0.1744, + "step": 16980 + }, + { + "epoch": 5.24, + "learning_rate": 1.73027099054763e-05, + "loss": 0.1737, + "step": 16981 + }, + { + "epoch": 5.24, + "learning_rate": 1.7302368236787015e-05, + "loss": 0.1727, + "step": 16982 + }, + { + "epoch": 5.24, + "learning_rate": 1.7302026549833178e-05, + "loss": 0.1713, + "step": 16983 + }, + { + "epoch": 5.25, + "learning_rate": 1.730168484461564e-05, + "loss": 0.1821, + "step": 16984 + }, + { + "epoch": 5.25, + "learning_rate": 1.7301343121135257e-05, + "loss": 0.1674, + "step": 16985 + }, + { + "epoch": 5.25, + "learning_rate": 1.7301001379392883e-05, + "loss": 0.1849, + "step": 16986 + }, + { + "epoch": 5.25, + "learning_rate": 1.7300659619389373e-05, + "loss": 0.1664, + "step": 16987 + }, + { + "epoch": 5.25, + "learning_rate": 1.730031784112558e-05, + "loss": 0.1653, + "step": 16988 + }, + { + "epoch": 5.25, + "learning_rate": 1.729997604460236e-05, + "loss": 0.1666, + "step": 16989 + }, + { + "epoch": 5.25, + "learning_rate": 1.7299634229820573e-05, + "loss": 0.1714, + "step": 16990 + }, + { + "epoch": 5.25, + "learning_rate": 1.7299292396781065e-05, + "loss": 0.185, + "step": 16991 + }, + { + "epoch": 5.25, + "learning_rate": 1.72989505454847e-05, + "loss": 0.1828, + "step": 16992 + }, + { + "epoch": 5.25, + "learning_rate": 1.729860867593232e-05, + "loss": 0.1975, + "step": 16993 + }, + { + "epoch": 5.25, + "learning_rate": 1.7298266788124798e-05, + "loss": 0.1733, + "step": 16994 + }, + { + "epoch": 5.25, + "learning_rate": 1.7297924882062975e-05, + "loss": 0.1766, + "step": 16995 + }, + { + "epoch": 5.25, + "learning_rate": 1.7297582957747708e-05, + "loss": 0.1761, + "step": 16996 + }, + { + "epoch": 5.25, + "learning_rate": 1.7297241015179864e-05, + "loss": 0.1815, + "step": 16997 + }, + { + "epoch": 5.25, + "learning_rate": 1.7296899054360282e-05, + "loss": 0.1649, + "step": 16998 + }, + { + "epoch": 5.25, + "learning_rate": 1.7296557075289823e-05, + "loss": 0.1827, + "step": 16999 + }, + { + "epoch": 5.25, + "learning_rate": 1.729621507796935e-05, + "loss": 0.1839, + "step": 17000 + }, + { + "epoch": 5.25, + "learning_rate": 1.729587306239971e-05, + "loss": 0.1823, + "step": 17001 + }, + { + "epoch": 5.25, + "learning_rate": 1.729553102858176e-05, + "loss": 0.1955, + "step": 17002 + }, + { + "epoch": 5.25, + "learning_rate": 1.7295188976516354e-05, + "loss": 0.1697, + "step": 17003 + }, + { + "epoch": 5.25, + "learning_rate": 1.7294846906204353e-05, + "loss": 0.1736, + "step": 17004 + }, + { + "epoch": 5.25, + "learning_rate": 1.7294504817646612e-05, + "loss": 0.1892, + "step": 17005 + }, + { + "epoch": 5.25, + "learning_rate": 1.729416271084398e-05, + "loss": 0.1833, + "step": 17006 + }, + { + "epoch": 5.25, + "learning_rate": 1.7293820585797315e-05, + "loss": 0.1799, + "step": 17007 + }, + { + "epoch": 5.25, + "learning_rate": 1.7293478442507477e-05, + "loss": 0.1847, + "step": 17008 + }, + { + "epoch": 5.25, + "learning_rate": 1.729313628097532e-05, + "loss": 0.1806, + "step": 17009 + }, + { + "epoch": 5.25, + "learning_rate": 1.72927941012017e-05, + "loss": 0.1849, + "step": 17010 + }, + { + "epoch": 5.25, + "learning_rate": 1.7292451903187468e-05, + "loss": 0.1878, + "step": 17011 + }, + { + "epoch": 5.25, + "learning_rate": 1.7292109686933486e-05, + "loss": 0.1696, + "step": 17012 + }, + { + "epoch": 5.25, + "learning_rate": 1.7291767452440608e-05, + "loss": 0.1763, + "step": 17013 + }, + { + "epoch": 5.25, + "learning_rate": 1.7291425199709688e-05, + "loss": 0.1666, + "step": 17014 + }, + { + "epoch": 5.25, + "learning_rate": 1.7291082928741586e-05, + "loss": 0.1589, + "step": 17015 + }, + { + "epoch": 5.25, + "learning_rate": 1.7290740639537156e-05, + "loss": 0.1785, + "step": 17016 + }, + { + "epoch": 5.26, + "learning_rate": 1.7290398332097252e-05, + "loss": 0.1814, + "step": 17017 + }, + { + "epoch": 5.26, + "learning_rate": 1.729005600642273e-05, + "loss": 0.1753, + "step": 17018 + }, + { + "epoch": 5.26, + "learning_rate": 1.7289713662514454e-05, + "loss": 0.1707, + "step": 17019 + }, + { + "epoch": 5.26, + "learning_rate": 1.728937130037327e-05, + "loss": 0.1829, + "step": 17020 + }, + { + "epoch": 5.26, + "learning_rate": 1.7289028920000038e-05, + "loss": 0.163, + "step": 17021 + }, + { + "epoch": 5.26, + "learning_rate": 1.7288686521395618e-05, + "loss": 0.1723, + "step": 17022 + }, + { + "epoch": 5.26, + "learning_rate": 1.7288344104560863e-05, + "loss": 0.1871, + "step": 17023 + }, + { + "epoch": 5.26, + "learning_rate": 1.728800166949663e-05, + "loss": 0.1694, + "step": 17024 + }, + { + "epoch": 5.26, + "learning_rate": 1.7287659216203776e-05, + "loss": 0.183, + "step": 17025 + }, + { + "epoch": 5.26, + "learning_rate": 1.7287316744683158e-05, + "loss": 0.169, + "step": 17026 + }, + { + "epoch": 5.26, + "learning_rate": 1.728697425493563e-05, + "loss": 0.1712, + "step": 17027 + }, + { + "epoch": 5.26, + "learning_rate": 1.7286631746962052e-05, + "loss": 0.1873, + "step": 17028 + }, + { + "epoch": 5.26, + "learning_rate": 1.728628922076328e-05, + "loss": 0.1838, + "step": 17029 + }, + { + "epoch": 5.26, + "learning_rate": 1.7285946676340164e-05, + "loss": 0.1905, + "step": 17030 + }, + { + "epoch": 5.26, + "learning_rate": 1.7285604113693574e-05, + "loss": 0.1646, + "step": 17031 + }, + { + "epoch": 5.26, + "learning_rate": 1.7285261532824353e-05, + "loss": 0.1696, + "step": 17032 + }, + { + "epoch": 5.26, + "learning_rate": 1.7284918933733366e-05, + "loss": 0.1828, + "step": 17033 + }, + { + "epoch": 5.26, + "learning_rate": 1.7284576316421468e-05, + "loss": 0.1887, + "step": 17034 + }, + { + "epoch": 5.26, + "learning_rate": 1.7284233680889518e-05, + "loss": 0.184, + "step": 17035 + }, + { + "epoch": 5.26, + "learning_rate": 1.728389102713837e-05, + "loss": 0.2017, + "step": 17036 + }, + { + "epoch": 5.26, + "learning_rate": 1.7283548355168883e-05, + "loss": 0.1776, + "step": 17037 + }, + { + "epoch": 5.26, + "learning_rate": 1.728320566498191e-05, + "loss": 0.1842, + "step": 17038 + }, + { + "epoch": 5.26, + "learning_rate": 1.7282862956578315e-05, + "loss": 0.166, + "step": 17039 + }, + { + "epoch": 5.26, + "learning_rate": 1.728252022995895e-05, + "loss": 0.1819, + "step": 17040 + }, + { + "epoch": 5.26, + "learning_rate": 1.7282177485124672e-05, + "loss": 0.1789, + "step": 17041 + }, + { + "epoch": 5.26, + "learning_rate": 1.728183472207634e-05, + "loss": 0.184, + "step": 17042 + }, + { + "epoch": 5.26, + "learning_rate": 1.7281491940814815e-05, + "loss": 0.1765, + "step": 17043 + }, + { + "epoch": 5.26, + "learning_rate": 1.7281149141340946e-05, + "loss": 0.2009, + "step": 17044 + }, + { + "epoch": 5.26, + "learning_rate": 1.7280806323655598e-05, + "loss": 0.1751, + "step": 17045 + }, + { + "epoch": 5.26, + "learning_rate": 1.7280463487759624e-05, + "loss": 0.1728, + "step": 17046 + }, + { + "epoch": 5.26, + "learning_rate": 1.7280120633653885e-05, + "loss": 0.1792, + "step": 17047 + }, + { + "epoch": 5.26, + "learning_rate": 1.727977776133923e-05, + "loss": 0.1766, + "step": 17048 + }, + { + "epoch": 5.27, + "learning_rate": 1.727943487081653e-05, + "loss": 0.158, + "step": 17049 + }, + { + "epoch": 5.27, + "learning_rate": 1.7279091962086633e-05, + "loss": 0.1669, + "step": 17050 + }, + { + "epoch": 5.27, + "learning_rate": 1.7278749035150402e-05, + "loss": 0.1877, + "step": 17051 + }, + { + "epoch": 5.27, + "learning_rate": 1.727840609000869e-05, + "loss": 0.1754, + "step": 17052 + }, + { + "epoch": 5.27, + "learning_rate": 1.7278063126662354e-05, + "loss": 0.1685, + "step": 17053 + }, + { + "epoch": 5.27, + "learning_rate": 1.727772014511226e-05, + "loss": 0.1588, + "step": 17054 + }, + { + "epoch": 5.27, + "learning_rate": 1.7277377145359255e-05, + "loss": 0.1947, + "step": 17055 + }, + { + "epoch": 5.27, + "learning_rate": 1.7277034127404208e-05, + "loss": 0.1793, + "step": 17056 + }, + { + "epoch": 5.27, + "learning_rate": 1.727669109124797e-05, + "loss": 0.1793, + "step": 17057 + }, + { + "epoch": 5.27, + "learning_rate": 1.72763480368914e-05, + "loss": 0.1767, + "step": 17058 + }, + { + "epoch": 5.27, + "learning_rate": 1.7276004964335355e-05, + "loss": 0.191, + "step": 17059 + }, + { + "epoch": 5.27, + "learning_rate": 1.7275661873580696e-05, + "loss": 0.185, + "step": 17060 + }, + { + "epoch": 5.27, + "learning_rate": 1.7275318764628276e-05, + "loss": 0.1513, + "step": 17061 + }, + { + "epoch": 5.27, + "learning_rate": 1.7274975637478963e-05, + "loss": 0.1768, + "step": 17062 + }, + { + "epoch": 5.27, + "learning_rate": 1.7274632492133606e-05, + "loss": 0.1462, + "step": 17063 + }, + { + "epoch": 5.27, + "learning_rate": 1.7274289328593067e-05, + "loss": 0.1865, + "step": 17064 + }, + { + "epoch": 5.27, + "learning_rate": 1.72739461468582e-05, + "loss": 0.178, + "step": 17065 + }, + { + "epoch": 5.27, + "learning_rate": 1.727360294692987e-05, + "loss": 0.1916, + "step": 17066 + }, + { + "epoch": 5.27, + "learning_rate": 1.7273259728808934e-05, + "loss": 0.1804, + "step": 17067 + }, + { + "epoch": 5.27, + "learning_rate": 1.7272916492496244e-05, + "loss": 0.1749, + "step": 17068 + }, + { + "epoch": 5.27, + "learning_rate": 1.727257323799267e-05, + "loss": 0.1925, + "step": 17069 + }, + { + "epoch": 5.27, + "learning_rate": 1.7272229965299058e-05, + "loss": 0.1769, + "step": 17070 + }, + { + "epoch": 5.27, + "learning_rate": 1.7271886674416277e-05, + "loss": 0.1594, + "step": 17071 + }, + { + "epoch": 5.27, + "learning_rate": 1.7271543365345178e-05, + "loss": 0.1695, + "step": 17072 + }, + { + "epoch": 5.27, + "learning_rate": 1.7271200038086625e-05, + "loss": 0.1801, + "step": 17073 + }, + { + "epoch": 5.27, + "learning_rate": 1.727085669264147e-05, + "loss": 0.1822, + "step": 17074 + }, + { + "epoch": 5.27, + "learning_rate": 1.7270513329010584e-05, + "loss": 0.1797, + "step": 17075 + }, + { + "epoch": 5.27, + "learning_rate": 1.727016994719481e-05, + "loss": 0.1733, + "step": 17076 + }, + { + "epoch": 5.27, + "learning_rate": 1.726982654719502e-05, + "loss": 0.1983, + "step": 17077 + }, + { + "epoch": 5.27, + "learning_rate": 1.7269483129012067e-05, + "loss": 0.1668, + "step": 17078 + }, + { + "epoch": 5.27, + "learning_rate": 1.7269139692646807e-05, + "loss": 0.2068, + "step": 17079 + }, + { + "epoch": 5.27, + "learning_rate": 1.726879623810011e-05, + "loss": 0.1936, + "step": 17080 + }, + { + "epoch": 5.28, + "learning_rate": 1.7268452765372823e-05, + "loss": 0.1593, + "step": 17081 + }, + { + "epoch": 5.28, + "learning_rate": 1.726810927446581e-05, + "loss": 0.1938, + "step": 17082 + }, + { + "epoch": 5.28, + "learning_rate": 1.7267765765379932e-05, + "loss": 0.1726, + "step": 17083 + }, + { + "epoch": 5.28, + "learning_rate": 1.7267422238116046e-05, + "loss": 0.169, + "step": 17084 + }, + { + "epoch": 5.28, + "learning_rate": 1.726707869267501e-05, + "loss": 0.1761, + "step": 17085 + }, + { + "epoch": 5.28, + "learning_rate": 1.7266735129057685e-05, + "loss": 0.1941, + "step": 17086 + }, + { + "epoch": 5.28, + "learning_rate": 1.726639154726493e-05, + "loss": 0.1716, + "step": 17087 + }, + { + "epoch": 5.28, + "learning_rate": 1.726604794729761e-05, + "loss": 0.1576, + "step": 17088 + }, + { + "epoch": 5.28, + "learning_rate": 1.726570432915657e-05, + "loss": 0.1811, + "step": 17089 + }, + { + "epoch": 5.28, + "learning_rate": 1.7265360692842684e-05, + "loss": 0.1743, + "step": 17090 + }, + { + "epoch": 5.28, + "learning_rate": 1.7265017038356804e-05, + "loss": 0.173, + "step": 17091 + }, + { + "epoch": 5.28, + "learning_rate": 1.726467336569979e-05, + "loss": 0.1825, + "step": 17092 + }, + { + "epoch": 5.28, + "learning_rate": 1.7264329674872504e-05, + "loss": 0.1878, + "step": 17093 + }, + { + "epoch": 5.28, + "learning_rate": 1.7263985965875805e-05, + "loss": 0.1809, + "step": 17094 + }, + { + "epoch": 5.28, + "learning_rate": 1.7263642238710554e-05, + "loss": 0.1902, + "step": 17095 + }, + { + "epoch": 5.28, + "learning_rate": 1.7263298493377605e-05, + "loss": 0.1709, + "step": 17096 + }, + { + "epoch": 5.28, + "learning_rate": 1.7262954729877823e-05, + "loss": 0.1774, + "step": 17097 + }, + { + "epoch": 5.28, + "learning_rate": 1.726261094821207e-05, + "loss": 0.177, + "step": 17098 + }, + { + "epoch": 5.28, + "learning_rate": 1.7262267148381198e-05, + "loss": 0.1812, + "step": 17099 + }, + { + "epoch": 5.28, + "learning_rate": 1.7261923330386073e-05, + "loss": 0.1676, + "step": 17100 + }, + { + "epoch": 5.28, + "learning_rate": 1.7261579494227553e-05, + "loss": 0.1767, + "step": 17101 + }, + { + "epoch": 5.28, + "learning_rate": 1.72612356399065e-05, + "loss": 0.1868, + "step": 17102 + }, + { + "epoch": 5.28, + "learning_rate": 1.7260891767423768e-05, + "loss": 0.168, + "step": 17103 + }, + { + "epoch": 5.28, + "learning_rate": 1.7260547876780226e-05, + "loss": 0.1706, + "step": 17104 + }, + { + "epoch": 5.28, + "learning_rate": 1.726020396797673e-05, + "loss": 0.1725, + "step": 17105 + }, + { + "epoch": 5.28, + "learning_rate": 1.7259860041014133e-05, + "loss": 0.1755, + "step": 17106 + }, + { + "epoch": 5.28, + "learning_rate": 1.7259516095893308e-05, + "loss": 0.1946, + "step": 17107 + }, + { + "epoch": 5.28, + "learning_rate": 1.7259172132615106e-05, + "loss": 0.1712, + "step": 17108 + }, + { + "epoch": 5.28, + "learning_rate": 1.7258828151180393e-05, + "loss": 0.1766, + "step": 17109 + }, + { + "epoch": 5.28, + "learning_rate": 1.7258484151590028e-05, + "loss": 0.184, + "step": 17110 + }, + { + "epoch": 5.28, + "learning_rate": 1.7258140133844866e-05, + "loss": 0.1779, + "step": 17111 + }, + { + "epoch": 5.28, + "learning_rate": 1.7257796097945776e-05, + "loss": 0.1821, + "step": 17112 + }, + { + "epoch": 5.28, + "learning_rate": 1.725745204389361e-05, + "loss": 0.1811, + "step": 17113 + }, + { + "epoch": 5.29, + "learning_rate": 1.7257107971689238e-05, + "loss": 0.1732, + "step": 17114 + }, + { + "epoch": 5.29, + "learning_rate": 1.725676388133351e-05, + "loss": 0.1766, + "step": 17115 + }, + { + "epoch": 5.29, + "learning_rate": 1.7256419772827296e-05, + "loss": 0.1854, + "step": 17116 + }, + { + "epoch": 5.29, + "learning_rate": 1.7256075646171448e-05, + "loss": 0.1806, + "step": 17117 + }, + { + "epoch": 5.29, + "learning_rate": 1.7255731501366834e-05, + "loss": 0.1758, + "step": 17118 + }, + { + "epoch": 5.29, + "learning_rate": 1.7255387338414316e-05, + "loss": 0.18, + "step": 17119 + }, + { + "epoch": 5.29, + "learning_rate": 1.7255043157314744e-05, + "loss": 0.1822, + "step": 17120 + }, + { + "epoch": 5.29, + "learning_rate": 1.725469895806899e-05, + "loss": 0.1863, + "step": 17121 + }, + { + "epoch": 5.29, + "learning_rate": 1.725435474067791e-05, + "loss": 0.1688, + "step": 17122 + }, + { + "epoch": 5.29, + "learning_rate": 1.7254010505142367e-05, + "loss": 0.1867, + "step": 17123 + }, + { + "epoch": 5.29, + "learning_rate": 1.725366625146322e-05, + "loss": 0.1764, + "step": 17124 + }, + { + "epoch": 5.29, + "learning_rate": 1.725332197964133e-05, + "loss": 0.162, + "step": 17125 + }, + { + "epoch": 5.29, + "learning_rate": 1.7252977689677556e-05, + "loss": 0.174, + "step": 17126 + }, + { + "epoch": 5.29, + "learning_rate": 1.7252633381572766e-05, + "loss": 0.1794, + "step": 17127 + }, + { + "epoch": 5.29, + "learning_rate": 1.7252289055327817e-05, + "loss": 0.1635, + "step": 17128 + }, + { + "epoch": 5.29, + "learning_rate": 1.725194471094357e-05, + "loss": 0.1673, + "step": 17129 + }, + { + "epoch": 5.29, + "learning_rate": 1.7251600348420883e-05, + "loss": 0.1944, + "step": 17130 + }, + { + "epoch": 5.29, + "learning_rate": 1.7251255967760627e-05, + "loss": 0.1603, + "step": 17131 + }, + { + "epoch": 5.29, + "learning_rate": 1.7250911568963653e-05, + "loss": 0.1687, + "step": 17132 + }, + { + "epoch": 5.29, + "learning_rate": 1.7250567152030827e-05, + "loss": 0.1821, + "step": 17133 + }, + { + "epoch": 5.29, + "learning_rate": 1.725022271696301e-05, + "loss": 0.1755, + "step": 17134 + }, + { + "epoch": 5.29, + "learning_rate": 1.7249878263761064e-05, + "loss": 0.1946, + "step": 17135 + }, + { + "epoch": 5.29, + "learning_rate": 1.7249533792425853e-05, + "loss": 0.1772, + "step": 17136 + }, + { + "epoch": 5.29, + "learning_rate": 1.724918930295823e-05, + "loss": 0.1824, + "step": 17137 + }, + { + "epoch": 5.29, + "learning_rate": 1.724884479535907e-05, + "loss": 0.1766, + "step": 17138 + }, + { + "epoch": 5.29, + "learning_rate": 1.724850026962922e-05, + "loss": 0.1808, + "step": 17139 + }, + { + "epoch": 5.29, + "learning_rate": 1.7248155725769555e-05, + "loss": 0.1882, + "step": 17140 + }, + { + "epoch": 5.29, + "learning_rate": 1.7247811163780923e-05, + "loss": 0.1776, + "step": 17141 + }, + { + "epoch": 5.29, + "learning_rate": 1.7247466583664198e-05, + "loss": 0.1853, + "step": 17142 + }, + { + "epoch": 5.29, + "learning_rate": 1.7247121985420235e-05, + "loss": 0.164, + "step": 17143 + }, + { + "epoch": 5.29, + "learning_rate": 1.7246777369049903e-05, + "loss": 0.1625, + "step": 17144 + }, + { + "epoch": 5.29, + "learning_rate": 1.7246432734554055e-05, + "loss": 0.1672, + "step": 17145 + }, + { + "epoch": 5.3, + "learning_rate": 1.724608808193356e-05, + "loss": 0.1933, + "step": 17146 + }, + { + "epoch": 5.3, + "learning_rate": 1.7245743411189272e-05, + "loss": 0.185, + "step": 17147 + }, + { + "epoch": 5.3, + "learning_rate": 1.724539872232206e-05, + "loss": 0.189, + "step": 17148 + }, + { + "epoch": 5.3, + "learning_rate": 1.7245054015332787e-05, + "loss": 0.1877, + "step": 17149 + }, + { + "epoch": 5.3, + "learning_rate": 1.7244709290222313e-05, + "loss": 0.1839, + "step": 17150 + }, + { + "epoch": 5.3, + "learning_rate": 1.7244364546991497e-05, + "loss": 0.1747, + "step": 17151 + }, + { + "epoch": 5.3, + "learning_rate": 1.7244019785641204e-05, + "loss": 0.1722, + "step": 17152 + }, + { + "epoch": 5.3, + "learning_rate": 1.7243675006172296e-05, + "loss": 0.1833, + "step": 17153 + }, + { + "epoch": 5.3, + "learning_rate": 1.7243330208585638e-05, + "loss": 0.166, + "step": 17154 + }, + { + "epoch": 5.3, + "learning_rate": 1.724298539288209e-05, + "loss": 0.1784, + "step": 17155 + }, + { + "epoch": 5.3, + "learning_rate": 1.724264055906251e-05, + "loss": 0.1912, + "step": 17156 + }, + { + "epoch": 5.3, + "learning_rate": 1.724229570712777e-05, + "loss": 0.1853, + "step": 17157 + }, + { + "epoch": 5.3, + "learning_rate": 1.7241950837078726e-05, + "loss": 0.1807, + "step": 17158 + }, + { + "epoch": 5.3, + "learning_rate": 1.7241605948916243e-05, + "loss": 0.1738, + "step": 17159 + }, + { + "epoch": 5.3, + "learning_rate": 1.724126104264118e-05, + "loss": 0.1764, + "step": 17160 + }, + { + "epoch": 5.3, + "learning_rate": 1.7240916118254405e-05, + "loss": 0.1801, + "step": 17161 + }, + { + "epoch": 5.3, + "learning_rate": 1.7240571175756778e-05, + "loss": 0.1771, + "step": 17162 + }, + { + "epoch": 5.3, + "learning_rate": 1.724022621514916e-05, + "loss": 0.1744, + "step": 17163 + }, + { + "epoch": 5.3, + "learning_rate": 1.7239881236432417e-05, + "loss": 0.1792, + "step": 17164 + }, + { + "epoch": 5.3, + "learning_rate": 1.723953623960741e-05, + "loss": 0.1752, + "step": 17165 + }, + { + "epoch": 5.3, + "learning_rate": 1.7239191224675003e-05, + "loss": 0.1746, + "step": 17166 + }, + { + "epoch": 5.3, + "learning_rate": 1.723884619163606e-05, + "loss": 0.1623, + "step": 17167 + }, + { + "epoch": 5.3, + "learning_rate": 1.7238501140491436e-05, + "loss": 0.1815, + "step": 17168 + }, + { + "epoch": 5.3, + "learning_rate": 1.7238156071242007e-05, + "loss": 0.1821, + "step": 17169 + }, + { + "epoch": 5.3, + "learning_rate": 1.7237810983888627e-05, + "loss": 0.1868, + "step": 17170 + }, + { + "epoch": 5.3, + "learning_rate": 1.7237465878432164e-05, + "loss": 0.179, + "step": 17171 + }, + { + "epoch": 5.3, + "learning_rate": 1.7237120754873475e-05, + "loss": 0.1857, + "step": 17172 + }, + { + "epoch": 5.3, + "learning_rate": 1.723677561321343e-05, + "loss": 0.1794, + "step": 17173 + }, + { + "epoch": 5.3, + "learning_rate": 1.7236430453452887e-05, + "loss": 0.1722, + "step": 17174 + }, + { + "epoch": 5.3, + "learning_rate": 1.7236085275592715e-05, + "loss": 0.1613, + "step": 17175 + }, + { + "epoch": 5.3, + "learning_rate": 1.723574007963377e-05, + "loss": 0.1788, + "step": 17176 + }, + { + "epoch": 5.3, + "learning_rate": 1.7235394865576922e-05, + "loss": 0.1704, + "step": 17177 + }, + { + "epoch": 5.3, + "learning_rate": 1.723504963342303e-05, + "loss": 0.1757, + "step": 17178 + }, + { + "epoch": 5.31, + "learning_rate": 1.7234704383172962e-05, + "loss": 0.1838, + "step": 17179 + }, + { + "epoch": 5.31, + "learning_rate": 1.7234359114827578e-05, + "loss": 0.1721, + "step": 17180 + }, + { + "epoch": 5.31, + "learning_rate": 1.723401382838774e-05, + "loss": 0.1772, + "step": 17181 + }, + { + "epoch": 5.31, + "learning_rate": 1.7233668523854316e-05, + "loss": 0.1923, + "step": 17182 + }, + { + "epoch": 5.31, + "learning_rate": 1.7233323201228163e-05, + "loss": 0.1709, + "step": 17183 + }, + { + "epoch": 5.31, + "learning_rate": 1.7232977860510156e-05, + "loss": 0.173, + "step": 17184 + }, + { + "epoch": 5.31, + "learning_rate": 1.723263250170115e-05, + "loss": 0.1924, + "step": 17185 + }, + { + "epoch": 5.31, + "learning_rate": 1.723228712480201e-05, + "loss": 0.1968, + "step": 17186 + }, + { + "epoch": 5.31, + "learning_rate": 1.72319417298136e-05, + "loss": 0.1825, + "step": 17187 + }, + { + "epoch": 5.31, + "learning_rate": 1.723159631673679e-05, + "loss": 0.191, + "step": 17188 + }, + { + "epoch": 5.31, + "learning_rate": 1.7231250885572433e-05, + "loss": 0.1819, + "step": 17189 + }, + { + "epoch": 5.31, + "learning_rate": 1.7230905436321398e-05, + "loss": 0.1644, + "step": 17190 + }, + { + "epoch": 5.31, + "learning_rate": 1.7230559968984555e-05, + "loss": 0.1818, + "step": 17191 + }, + { + "epoch": 5.31, + "learning_rate": 1.723021448356276e-05, + "loss": 0.1977, + "step": 17192 + }, + { + "epoch": 5.31, + "learning_rate": 1.7229868980056878e-05, + "loss": 0.1666, + "step": 17193 + }, + { + "epoch": 5.31, + "learning_rate": 1.7229523458467775e-05, + "loss": 0.1642, + "step": 17194 + }, + { + "epoch": 5.31, + "learning_rate": 1.7229177918796318e-05, + "loss": 0.184, + "step": 17195 + }, + { + "epoch": 5.31, + "learning_rate": 1.722883236104337e-05, + "loss": 0.1911, + "step": 17196 + }, + { + "epoch": 5.31, + "learning_rate": 1.722848678520979e-05, + "loss": 0.1991, + "step": 17197 + }, + { + "epoch": 5.31, + "learning_rate": 1.7228141191296446e-05, + "loss": 0.1881, + "step": 17198 + }, + { + "epoch": 5.31, + "learning_rate": 1.7227795579304204e-05, + "loss": 0.173, + "step": 17199 + }, + { + "epoch": 5.31, + "learning_rate": 1.7227449949233928e-05, + "loss": 0.1743, + "step": 17200 + }, + { + "epoch": 5.31, + "learning_rate": 1.722710430108648e-05, + "loss": 0.1925, + "step": 17201 + }, + { + "epoch": 5.31, + "learning_rate": 1.7226758634862725e-05, + "loss": 0.1787, + "step": 17202 + }, + { + "epoch": 5.31, + "learning_rate": 1.7226412950563532e-05, + "loss": 0.1766, + "step": 17203 + }, + { + "epoch": 5.31, + "learning_rate": 1.7226067248189758e-05, + "loss": 0.1805, + "step": 17204 + }, + { + "epoch": 5.31, + "learning_rate": 1.7225721527742276e-05, + "loss": 0.1761, + "step": 17205 + }, + { + "epoch": 5.31, + "learning_rate": 1.7225375789221947e-05, + "loss": 0.178, + "step": 17206 + }, + { + "epoch": 5.31, + "learning_rate": 1.722503003262963e-05, + "loss": 0.1684, + "step": 17207 + }, + { + "epoch": 5.31, + "learning_rate": 1.72246842579662e-05, + "loss": 0.1824, + "step": 17208 + }, + { + "epoch": 5.31, + "learning_rate": 1.7224338465232512e-05, + "loss": 0.1791, + "step": 17209 + }, + { + "epoch": 5.31, + "learning_rate": 1.722399265442944e-05, + "loss": 0.1765, + "step": 17210 + }, + { + "epoch": 5.32, + "learning_rate": 1.7223646825557845e-05, + "loss": 0.1883, + "step": 17211 + }, + { + "epoch": 5.32, + "learning_rate": 1.722330097861859e-05, + "loss": 0.1616, + "step": 17212 + }, + { + "epoch": 5.32, + "learning_rate": 1.7222955113612544e-05, + "loss": 0.1837, + "step": 17213 + }, + { + "epoch": 5.32, + "learning_rate": 1.7222609230540567e-05, + "loss": 0.1762, + "step": 17214 + }, + { + "epoch": 5.32, + "learning_rate": 1.722226332940353e-05, + "loss": 0.1954, + "step": 17215 + }, + { + "epoch": 5.32, + "learning_rate": 1.722191741020229e-05, + "loss": 0.182, + "step": 17216 + }, + { + "epoch": 5.32, + "learning_rate": 1.722157147293772e-05, + "loss": 0.1736, + "step": 17217 + }, + { + "epoch": 5.32, + "learning_rate": 1.7221225517610686e-05, + "loss": 0.1792, + "step": 17218 + }, + { + "epoch": 5.32, + "learning_rate": 1.7220879544222046e-05, + "loss": 0.1812, + "step": 17219 + }, + { + "epoch": 5.32, + "learning_rate": 1.722053355277267e-05, + "loss": 0.1753, + "step": 17220 + }, + { + "epoch": 5.32, + "learning_rate": 1.722018754326342e-05, + "loss": 0.1751, + "step": 17221 + }, + { + "epoch": 5.32, + "learning_rate": 1.721984151569517e-05, + "loss": 0.187, + "step": 17222 + }, + { + "epoch": 5.32, + "learning_rate": 1.7219495470068777e-05, + "loss": 0.1757, + "step": 17223 + }, + { + "epoch": 5.32, + "learning_rate": 1.721914940638511e-05, + "loss": 0.1759, + "step": 17224 + }, + { + "epoch": 5.32, + "learning_rate": 1.721880332464503e-05, + "loss": 0.182, + "step": 17225 + }, + { + "epoch": 5.32, + "learning_rate": 1.721845722484941e-05, + "loss": 0.1817, + "step": 17226 + }, + { + "epoch": 5.32, + "learning_rate": 1.721811110699911e-05, + "loss": 0.1954, + "step": 17227 + }, + { + "epoch": 5.32, + "learning_rate": 1.7217764971094998e-05, + "loss": 0.1777, + "step": 17228 + }, + { + "epoch": 5.32, + "learning_rate": 1.721741881713794e-05, + "loss": 0.1908, + "step": 17229 + }, + { + "epoch": 5.32, + "learning_rate": 1.7217072645128802e-05, + "loss": 0.1875, + "step": 17230 + }, + { + "epoch": 5.32, + "learning_rate": 1.721672645506845e-05, + "loss": 0.1829, + "step": 17231 + }, + { + "epoch": 5.32, + "learning_rate": 1.7216380246957743e-05, + "loss": 0.1874, + "step": 17232 + }, + { + "epoch": 5.32, + "learning_rate": 1.7216034020797558e-05, + "loss": 0.1831, + "step": 17233 + }, + { + "epoch": 5.32, + "learning_rate": 1.721568777658875e-05, + "loss": 0.1835, + "step": 17234 + }, + { + "epoch": 5.32, + "learning_rate": 1.72153415143322e-05, + "loss": 0.1896, + "step": 17235 + }, + { + "epoch": 5.32, + "learning_rate": 1.721499523402876e-05, + "loss": 0.1876, + "step": 17236 + }, + { + "epoch": 5.32, + "learning_rate": 1.72146489356793e-05, + "loss": 0.1667, + "step": 17237 + }, + { + "epoch": 5.32, + "learning_rate": 1.7214302619284688e-05, + "loss": 0.1829, + "step": 17238 + }, + { + "epoch": 5.32, + "learning_rate": 1.721395628484579e-05, + "loss": 0.1921, + "step": 17239 + }, + { + "epoch": 5.32, + "learning_rate": 1.7213609932363472e-05, + "loss": 0.1779, + "step": 17240 + }, + { + "epoch": 5.32, + "learning_rate": 1.72132635618386e-05, + "loss": 0.1767, + "step": 17241 + }, + { + "epoch": 5.32, + "learning_rate": 1.7212917173272037e-05, + "loss": 0.1959, + "step": 17242 + }, + { + "epoch": 5.33, + "learning_rate": 1.7212570766664655e-05, + "loss": 0.1832, + "step": 17243 + }, + { + "epoch": 5.33, + "learning_rate": 1.7212224342017315e-05, + "loss": 0.171, + "step": 17244 + }, + { + "epoch": 5.33, + "learning_rate": 1.721187789933089e-05, + "loss": 0.1842, + "step": 17245 + }, + { + "epoch": 5.33, + "learning_rate": 1.721153143860624e-05, + "loss": 0.1784, + "step": 17246 + }, + { + "epoch": 5.33, + "learning_rate": 1.721118495984424e-05, + "loss": 0.1733, + "step": 17247 + }, + { + "epoch": 5.33, + "learning_rate": 1.7210838463045748e-05, + "loss": 0.1525, + "step": 17248 + }, + { + "epoch": 5.33, + "learning_rate": 1.7210491948211635e-05, + "loss": 0.1748, + "step": 17249 + }, + { + "epoch": 5.33, + "learning_rate": 1.7210145415342764e-05, + "loss": 0.1879, + "step": 17250 + }, + { + "epoch": 5.33, + "learning_rate": 1.7209798864440007e-05, + "loss": 0.1712, + "step": 17251 + }, + { + "epoch": 5.33, + "learning_rate": 1.7209452295504226e-05, + "loss": 0.1775, + "step": 17252 + }, + { + "epoch": 5.33, + "learning_rate": 1.720910570853629e-05, + "loss": 0.1809, + "step": 17253 + }, + { + "epoch": 5.33, + "learning_rate": 1.7208759103537067e-05, + "loss": 0.1901, + "step": 17254 + }, + { + "epoch": 5.33, + "learning_rate": 1.720841248050742e-05, + "loss": 0.1835, + "step": 17255 + }, + { + "epoch": 5.33, + "learning_rate": 1.720806583944822e-05, + "loss": 0.1878, + "step": 17256 + }, + { + "epoch": 5.33, + "learning_rate": 1.7207719180360335e-05, + "loss": 0.1588, + "step": 17257 + }, + { + "epoch": 5.33, + "learning_rate": 1.720737250324463e-05, + "loss": 0.1708, + "step": 17258 + }, + { + "epoch": 5.33, + "learning_rate": 1.7207025808101966e-05, + "loss": 0.189, + "step": 17259 + }, + { + "epoch": 5.33, + "learning_rate": 1.720667909493322e-05, + "loss": 0.1739, + "step": 17260 + }, + { + "epoch": 5.33, + "learning_rate": 1.7206332363739257e-05, + "loss": 0.1797, + "step": 17261 + }, + { + "epoch": 5.33, + "learning_rate": 1.7205985614520943e-05, + "loss": 0.1888, + "step": 17262 + }, + { + "epoch": 5.33, + "learning_rate": 1.720563884727914e-05, + "loss": 0.1876, + "step": 17263 + }, + { + "epoch": 5.33, + "learning_rate": 1.7205292062014722e-05, + "loss": 0.1921, + "step": 17264 + }, + { + "epoch": 5.33, + "learning_rate": 1.7204945258728557e-05, + "loss": 0.1582, + "step": 17265 + }, + { + "epoch": 5.33, + "learning_rate": 1.7204598437421504e-05, + "loss": 0.1844, + "step": 17266 + }, + { + "epoch": 5.33, + "learning_rate": 1.720425159809444e-05, + "loss": 0.1617, + "step": 17267 + }, + { + "epoch": 5.33, + "learning_rate": 1.7203904740748226e-05, + "loss": 0.1835, + "step": 17268 + }, + { + "epoch": 5.33, + "learning_rate": 1.7203557865383738e-05, + "loss": 0.176, + "step": 17269 + }, + { + "epoch": 5.33, + "learning_rate": 1.7203210972001832e-05, + "loss": 0.1704, + "step": 17270 + }, + { + "epoch": 5.33, + "learning_rate": 1.7202864060603387e-05, + "loss": 0.1843, + "step": 17271 + }, + { + "epoch": 5.33, + "learning_rate": 1.720251713118926e-05, + "loss": 0.2019, + "step": 17272 + }, + { + "epoch": 5.33, + "learning_rate": 1.7202170183760326e-05, + "loss": 0.1704, + "step": 17273 + }, + { + "epoch": 5.33, + "learning_rate": 1.720182321831745e-05, + "loss": 0.166, + "step": 17274 + }, + { + "epoch": 5.33, + "learning_rate": 1.7201476234861507e-05, + "loss": 0.1717, + "step": 17275 + }, + { + "epoch": 5.34, + "learning_rate": 1.7201129233393352e-05, + "loss": 0.1875, + "step": 17276 + }, + { + "epoch": 5.34, + "learning_rate": 1.7200782213913858e-05, + "loss": 0.1883, + "step": 17277 + }, + { + "epoch": 5.34, + "learning_rate": 1.72004351764239e-05, + "loss": 0.1693, + "step": 17278 + }, + { + "epoch": 5.34, + "learning_rate": 1.7200088120924337e-05, + "loss": 0.1832, + "step": 17279 + }, + { + "epoch": 5.34, + "learning_rate": 1.719974104741604e-05, + "loss": 0.1897, + "step": 17280 + }, + { + "epoch": 5.34, + "learning_rate": 1.719939395589988e-05, + "loss": 0.1837, + "step": 17281 + }, + { + "epoch": 5.34, + "learning_rate": 1.719904684637672e-05, + "loss": 0.1714, + "step": 17282 + }, + { + "epoch": 5.34, + "learning_rate": 1.7198699718847432e-05, + "loss": 0.1879, + "step": 17283 + }, + { + "epoch": 5.34, + "learning_rate": 1.719835257331288e-05, + "loss": 0.173, + "step": 17284 + }, + { + "epoch": 5.34, + "learning_rate": 1.719800540977394e-05, + "loss": 0.1588, + "step": 17285 + }, + { + "epoch": 5.34, + "learning_rate": 1.7197658228231474e-05, + "loss": 0.1718, + "step": 17286 + }, + { + "epoch": 5.34, + "learning_rate": 1.719731102868635e-05, + "loss": 0.1675, + "step": 17287 + }, + { + "epoch": 5.34, + "learning_rate": 1.719696381113944e-05, + "loss": 0.1655, + "step": 17288 + }, + { + "epoch": 5.34, + "learning_rate": 1.7196616575591615e-05, + "loss": 0.1847, + "step": 17289 + }, + { + "epoch": 5.34, + "learning_rate": 1.7196269322043734e-05, + "loss": 0.1852, + "step": 17290 + }, + { + "epoch": 5.34, + "learning_rate": 1.719592205049667e-05, + "loss": 0.1871, + "step": 17291 + }, + { + "epoch": 5.34, + "learning_rate": 1.7195574760951297e-05, + "loss": 0.1765, + "step": 17292 + }, + { + "epoch": 5.34, + "learning_rate": 1.7195227453408475e-05, + "loss": 0.185, + "step": 17293 + }, + { + "epoch": 5.34, + "learning_rate": 1.719488012786908e-05, + "loss": 0.2041, + "step": 17294 + }, + { + "epoch": 5.34, + "learning_rate": 1.7194532784333976e-05, + "loss": 0.1884, + "step": 17295 + }, + { + "epoch": 5.34, + "learning_rate": 1.7194185422804032e-05, + "loss": 0.1697, + "step": 17296 + }, + { + "epoch": 5.34, + "learning_rate": 1.719383804328012e-05, + "loss": 0.1821, + "step": 17297 + }, + { + "epoch": 5.34, + "learning_rate": 1.719349064576311e-05, + "loss": 0.1802, + "step": 17298 + }, + { + "epoch": 5.34, + "learning_rate": 1.7193143230253863e-05, + "loss": 0.1706, + "step": 17299 + }, + { + "epoch": 5.34, + "learning_rate": 1.7192795796753253e-05, + "loss": 0.1922, + "step": 17300 + }, + { + "epoch": 5.34, + "learning_rate": 1.7192448345262152e-05, + "loss": 0.1873, + "step": 17301 + }, + { + "epoch": 5.34, + "learning_rate": 1.7192100875781423e-05, + "loss": 0.1842, + "step": 17302 + }, + { + "epoch": 5.34, + "learning_rate": 1.719175338831194e-05, + "loss": 0.2122, + "step": 17303 + }, + { + "epoch": 5.34, + "learning_rate": 1.7191405882854567e-05, + "loss": 0.1835, + "step": 17304 + }, + { + "epoch": 5.34, + "learning_rate": 1.7191058359410178e-05, + "loss": 0.1762, + "step": 17305 + }, + { + "epoch": 5.34, + "learning_rate": 1.719071081797964e-05, + "loss": 0.1758, + "step": 17306 + }, + { + "epoch": 5.34, + "learning_rate": 1.7190363258563823e-05, + "loss": 0.159, + "step": 17307 + }, + { + "epoch": 5.35, + "learning_rate": 1.71900156811636e-05, + "loss": 0.1651, + "step": 17308 + }, + { + "epoch": 5.35, + "learning_rate": 1.718966808577983e-05, + "loss": 0.1936, + "step": 17309 + }, + { + "epoch": 5.35, + "learning_rate": 1.7189320472413395e-05, + "loss": 0.2, + "step": 17310 + }, + { + "epoch": 5.35, + "learning_rate": 1.7188972841065154e-05, + "loss": 0.1759, + "step": 17311 + }, + { + "epoch": 5.35, + "learning_rate": 1.7188625191735982e-05, + "loss": 0.1834, + "step": 17312 + }, + { + "epoch": 5.35, + "learning_rate": 1.7188277524426748e-05, + "loss": 0.1961, + "step": 17313 + }, + { + "epoch": 5.35, + "learning_rate": 1.718792983913832e-05, + "loss": 0.1715, + "step": 17314 + }, + { + "epoch": 5.35, + "learning_rate": 1.7187582135871568e-05, + "loss": 0.1888, + "step": 17315 + }, + { + "epoch": 5.35, + "learning_rate": 1.718723441462736e-05, + "loss": 0.194, + "step": 17316 + }, + { + "epoch": 5.35, + "learning_rate": 1.718688667540657e-05, + "loss": 0.1797, + "step": 17317 + }, + { + "epoch": 5.35, + "learning_rate": 1.7186538918210067e-05, + "loss": 0.1732, + "step": 17318 + }, + { + "epoch": 5.35, + "learning_rate": 1.718619114303872e-05, + "loss": 0.1899, + "step": 17319 + }, + { + "epoch": 5.35, + "learning_rate": 1.7185843349893395e-05, + "loss": 0.1782, + "step": 17320 + }, + { + "epoch": 5.35, + "learning_rate": 1.7185495538774967e-05, + "loss": 0.1956, + "step": 17321 + }, + { + "epoch": 5.35, + "learning_rate": 1.7185147709684303e-05, + "loss": 0.172, + "step": 17322 + }, + { + "epoch": 5.35, + "learning_rate": 1.7184799862622276e-05, + "loss": 0.1769, + "step": 17323 + }, + { + "epoch": 5.35, + "learning_rate": 1.7184451997589754e-05, + "loss": 0.1851, + "step": 17324 + }, + { + "epoch": 5.35, + "learning_rate": 1.7184104114587604e-05, + "loss": 0.1818, + "step": 17325 + }, + { + "epoch": 5.35, + "learning_rate": 1.7183756213616704e-05, + "loss": 0.1851, + "step": 17326 + }, + { + "epoch": 5.35, + "learning_rate": 1.7183408294677918e-05, + "loss": 0.1825, + "step": 17327 + }, + { + "epoch": 5.35, + "learning_rate": 1.7183060357772116e-05, + "loss": 0.1719, + "step": 17328 + }, + { + "epoch": 5.35, + "learning_rate": 1.718271240290017e-05, + "loss": 0.1842, + "step": 17329 + }, + { + "epoch": 5.35, + "learning_rate": 1.7182364430062952e-05, + "loss": 0.1708, + "step": 17330 + }, + { + "epoch": 5.35, + "learning_rate": 1.7182016439261332e-05, + "loss": 0.1747, + "step": 17331 + }, + { + "epoch": 5.35, + "learning_rate": 1.7181668430496175e-05, + "loss": 0.186, + "step": 17332 + }, + { + "epoch": 5.35, + "learning_rate": 1.7181320403768357e-05, + "loss": 0.1886, + "step": 17333 + }, + { + "epoch": 5.35, + "learning_rate": 1.7180972359078744e-05, + "loss": 0.1805, + "step": 17334 + }, + { + "epoch": 5.35, + "learning_rate": 1.718062429642821e-05, + "loss": 0.1895, + "step": 17335 + }, + { + "epoch": 5.35, + "learning_rate": 1.7180276215817632e-05, + "loss": 0.1909, + "step": 17336 + }, + { + "epoch": 5.35, + "learning_rate": 1.7179928117247867e-05, + "loss": 0.1765, + "step": 17337 + }, + { + "epoch": 5.35, + "learning_rate": 1.7179580000719794e-05, + "loss": 0.1744, + "step": 17338 + }, + { + "epoch": 5.35, + "learning_rate": 1.7179231866234284e-05, + "loss": 0.1683, + "step": 17339 + }, + { + "epoch": 5.36, + "learning_rate": 1.7178883713792204e-05, + "loss": 0.1818, + "step": 17340 + }, + { + "epoch": 5.36, + "learning_rate": 1.7178535543394425e-05, + "loss": 0.1933, + "step": 17341 + }, + { + "epoch": 5.36, + "learning_rate": 1.717818735504182e-05, + "loss": 0.1747, + "step": 17342 + }, + { + "epoch": 5.36, + "learning_rate": 1.717783914873526e-05, + "loss": 0.1762, + "step": 17343 + }, + { + "epoch": 5.36, + "learning_rate": 1.7177490924475617e-05, + "loss": 0.182, + "step": 17344 + }, + { + "epoch": 5.36, + "learning_rate": 1.7177142682263755e-05, + "loss": 0.1868, + "step": 17345 + }, + { + "epoch": 5.36, + "learning_rate": 1.7176794422100555e-05, + "loss": 0.1761, + "step": 17346 + }, + { + "epoch": 5.36, + "learning_rate": 1.717644614398688e-05, + "loss": 0.1911, + "step": 17347 + }, + { + "epoch": 5.36, + "learning_rate": 1.7176097847923604e-05, + "loss": 0.1722, + "step": 17348 + }, + { + "epoch": 5.36, + "learning_rate": 1.7175749533911602e-05, + "loss": 0.1856, + "step": 17349 + }, + { + "epoch": 5.36, + "learning_rate": 1.717540120195174e-05, + "loss": 0.1821, + "step": 17350 + }, + { + "epoch": 5.36, + "learning_rate": 1.717505285204489e-05, + "loss": 0.1822, + "step": 17351 + }, + { + "epoch": 5.36, + "learning_rate": 1.7174704484191925e-05, + "loss": 0.1684, + "step": 17352 + }, + { + "epoch": 5.36, + "learning_rate": 1.7174356098393718e-05, + "loss": 0.1697, + "step": 17353 + }, + { + "epoch": 5.36, + "learning_rate": 1.717400769465113e-05, + "loss": 0.1923, + "step": 17354 + }, + { + "epoch": 5.36, + "learning_rate": 1.7173659272965047e-05, + "loss": 0.1744, + "step": 17355 + }, + { + "epoch": 5.36, + "learning_rate": 1.717331083333633e-05, + "loss": 0.1935, + "step": 17356 + }, + { + "epoch": 5.36, + "learning_rate": 1.7172962375765858e-05, + "loss": 0.1899, + "step": 17357 + }, + { + "epoch": 5.36, + "learning_rate": 1.71726139002545e-05, + "loss": 0.1979, + "step": 17358 + }, + { + "epoch": 5.36, + "learning_rate": 1.717226540680312e-05, + "loss": 0.1898, + "step": 17359 + }, + { + "epoch": 5.36, + "learning_rate": 1.71719168954126e-05, + "loss": 0.1843, + "step": 17360 + }, + { + "epoch": 5.36, + "learning_rate": 1.7171568366083807e-05, + "loss": 0.1716, + "step": 17361 + }, + { + "epoch": 5.36, + "learning_rate": 1.7171219818817614e-05, + "loss": 0.1744, + "step": 17362 + }, + { + "epoch": 5.36, + "learning_rate": 1.7170871253614894e-05, + "loss": 0.1906, + "step": 17363 + }, + { + "epoch": 5.36, + "learning_rate": 1.7170522670476513e-05, + "loss": 0.1786, + "step": 17364 + }, + { + "epoch": 5.36, + "learning_rate": 1.717017406940335e-05, + "loss": 0.175, + "step": 17365 + }, + { + "epoch": 5.36, + "learning_rate": 1.7169825450396276e-05, + "loss": 0.1866, + "step": 17366 + }, + { + "epoch": 5.36, + "learning_rate": 1.7169476813456158e-05, + "loss": 0.1842, + "step": 17367 + }, + { + "epoch": 5.36, + "learning_rate": 1.716912815858387e-05, + "loss": 0.1871, + "step": 17368 + }, + { + "epoch": 5.36, + "learning_rate": 1.7168779485780283e-05, + "loss": 0.1645, + "step": 17369 + }, + { + "epoch": 5.36, + "learning_rate": 1.716843079504628e-05, + "loss": 0.1847, + "step": 17370 + }, + { + "epoch": 5.36, + "learning_rate": 1.7168082086382717e-05, + "loss": 0.194, + "step": 17371 + }, + { + "epoch": 5.36, + "learning_rate": 1.7167733359790474e-05, + "loss": 0.1779, + "step": 17372 + }, + { + "epoch": 5.37, + "learning_rate": 1.7167384615270422e-05, + "loss": 0.1835, + "step": 17373 + }, + { + "epoch": 5.37, + "learning_rate": 1.7167035852823436e-05, + "loss": 0.1875, + "step": 17374 + }, + { + "epoch": 5.37, + "learning_rate": 1.716668707245038e-05, + "loss": 0.1816, + "step": 17375 + }, + { + "epoch": 5.37, + "learning_rate": 1.716633827415214e-05, + "loss": 0.1883, + "step": 17376 + }, + { + "epoch": 5.37, + "learning_rate": 1.7165989457929577e-05, + "loss": 0.1785, + "step": 17377 + }, + { + "epoch": 5.37, + "learning_rate": 1.7165640623783567e-05, + "loss": 0.1791, + "step": 17378 + }, + { + "epoch": 5.37, + "learning_rate": 1.7165291771714986e-05, + "loss": 0.1955, + "step": 17379 + }, + { + "epoch": 5.37, + "learning_rate": 1.7164942901724703e-05, + "loss": 0.1676, + "step": 17380 + }, + { + "epoch": 5.37, + "learning_rate": 1.7164594013813588e-05, + "loss": 0.1993, + "step": 17381 + }, + { + "epoch": 5.37, + "learning_rate": 1.7164245107982522e-05, + "loss": 0.1644, + "step": 17382 + }, + { + "epoch": 5.37, + "learning_rate": 1.7163896184232366e-05, + "loss": 0.1682, + "step": 17383 + }, + { + "epoch": 5.37, + "learning_rate": 1.7163547242564003e-05, + "loss": 0.1973, + "step": 17384 + }, + { + "epoch": 5.37, + "learning_rate": 1.71631982829783e-05, + "loss": 0.188, + "step": 17385 + }, + { + "epoch": 5.37, + "learning_rate": 1.7162849305476132e-05, + "loss": 0.1934, + "step": 17386 + }, + { + "epoch": 5.37, + "learning_rate": 1.7162500310058372e-05, + "loss": 0.179, + "step": 17387 + }, + { + "epoch": 5.37, + "learning_rate": 1.7162151296725893e-05, + "loss": 0.1799, + "step": 17388 + }, + { + "epoch": 5.37, + "learning_rate": 1.7161802265479564e-05, + "loss": 0.1823, + "step": 17389 + }, + { + "epoch": 5.37, + "learning_rate": 1.7161453216320268e-05, + "loss": 0.181, + "step": 17390 + }, + { + "epoch": 5.37, + "learning_rate": 1.7161104149248867e-05, + "loss": 0.1845, + "step": 17391 + }, + { + "epoch": 5.37, + "learning_rate": 1.7160755064266237e-05, + "loss": 0.1931, + "step": 17392 + }, + { + "epoch": 5.37, + "learning_rate": 1.7160405961373254e-05, + "loss": 0.1883, + "step": 17393 + }, + { + "epoch": 5.37, + "learning_rate": 1.7160056840570792e-05, + "loss": 0.1823, + "step": 17394 + }, + { + "epoch": 5.37, + "learning_rate": 1.715970770185972e-05, + "loss": 0.162, + "step": 17395 + }, + { + "epoch": 5.37, + "learning_rate": 1.715935854524091e-05, + "loss": 0.1697, + "step": 17396 + }, + { + "epoch": 5.37, + "learning_rate": 1.7159009370715243e-05, + "loss": 0.1842, + "step": 17397 + }, + { + "epoch": 5.37, + "learning_rate": 1.7158660178283586e-05, + "loss": 0.2058, + "step": 17398 + }, + { + "epoch": 5.37, + "learning_rate": 1.7158310967946814e-05, + "loss": 0.1751, + "step": 17399 + }, + { + "epoch": 5.37, + "learning_rate": 1.7157961739705803e-05, + "loss": 0.1694, + "step": 17400 + }, + { + "epoch": 5.37, + "learning_rate": 1.7157612493561422e-05, + "loss": 0.1772, + "step": 17401 + }, + { + "epoch": 5.37, + "learning_rate": 1.7157263229514546e-05, + "loss": 0.2089, + "step": 17402 + }, + { + "epoch": 5.37, + "learning_rate": 1.7156913947566048e-05, + "loss": 0.1767, + "step": 17403 + }, + { + "epoch": 5.37, + "learning_rate": 1.715656464771681e-05, + "loss": 0.1862, + "step": 17404 + }, + { + "epoch": 5.38, + "learning_rate": 1.7156215329967693e-05, + "loss": 0.1863, + "step": 17405 + }, + { + "epoch": 5.38, + "learning_rate": 1.7155865994319577e-05, + "loss": 0.1659, + "step": 17406 + }, + { + "epoch": 5.38, + "learning_rate": 1.7155516640773332e-05, + "loss": 0.1724, + "step": 17407 + }, + { + "epoch": 5.38, + "learning_rate": 1.7155167269329837e-05, + "loss": 0.1779, + "step": 17408 + }, + { + "epoch": 5.38, + "learning_rate": 1.7154817879989966e-05, + "loss": 0.1883, + "step": 17409 + }, + { + "epoch": 5.38, + "learning_rate": 1.715446847275459e-05, + "loss": 0.18, + "step": 17410 + }, + { + "epoch": 5.38, + "learning_rate": 1.715411904762458e-05, + "loss": 0.1847, + "step": 17411 + }, + { + "epoch": 5.38, + "learning_rate": 1.715376960460082e-05, + "loss": 0.162, + "step": 17412 + }, + { + "epoch": 5.38, + "learning_rate": 1.715342014368417e-05, + "loss": 0.1687, + "step": 17413 + }, + { + "epoch": 5.38, + "learning_rate": 1.7153070664875515e-05, + "loss": 0.1749, + "step": 17414 + }, + { + "epoch": 5.38, + "learning_rate": 1.7152721168175725e-05, + "loss": 0.1819, + "step": 17415 + }, + { + "epoch": 5.38, + "learning_rate": 1.7152371653585675e-05, + "loss": 0.1761, + "step": 17416 + }, + { + "epoch": 5.38, + "learning_rate": 1.715202212110624e-05, + "loss": 0.1816, + "step": 17417 + }, + { + "epoch": 5.38, + "learning_rate": 1.715167257073829e-05, + "loss": 0.1901, + "step": 17418 + }, + { + "epoch": 5.38, + "learning_rate": 1.7151323002482704e-05, + "loss": 0.1829, + "step": 17419 + }, + { + "epoch": 5.38, + "learning_rate": 1.7150973416340358e-05, + "loss": 0.184, + "step": 17420 + }, + { + "epoch": 5.38, + "learning_rate": 1.7150623812312122e-05, + "loss": 0.1794, + "step": 17421 + }, + { + "epoch": 5.38, + "learning_rate": 1.715027419039887e-05, + "loss": 0.1841, + "step": 17422 + }, + { + "epoch": 5.38, + "learning_rate": 1.714992455060148e-05, + "loss": 0.2038, + "step": 17423 + }, + { + "epoch": 5.38, + "learning_rate": 1.7149574892920823e-05, + "loss": 0.1884, + "step": 17424 + }, + { + "epoch": 5.38, + "learning_rate": 1.7149225217357775e-05, + "loss": 0.1751, + "step": 17425 + }, + { + "epoch": 5.38, + "learning_rate": 1.714887552391321e-05, + "loss": 0.1835, + "step": 17426 + }, + { + "epoch": 5.38, + "learning_rate": 1.7148525812588005e-05, + "loss": 0.1779, + "step": 17427 + }, + { + "epoch": 5.38, + "learning_rate": 1.7148176083383035e-05, + "loss": 0.1774, + "step": 17428 + }, + { + "epoch": 5.38, + "learning_rate": 1.7147826336299168e-05, + "loss": 0.1926, + "step": 17429 + }, + { + "epoch": 5.38, + "learning_rate": 1.7147476571337288e-05, + "loss": 0.1744, + "step": 17430 + }, + { + "epoch": 5.38, + "learning_rate": 1.7147126788498263e-05, + "loss": 0.1928, + "step": 17431 + }, + { + "epoch": 5.38, + "learning_rate": 1.7146776987782973e-05, + "loss": 0.1839, + "step": 17432 + }, + { + "epoch": 5.38, + "learning_rate": 1.7146427169192286e-05, + "loss": 0.1697, + "step": 17433 + }, + { + "epoch": 5.38, + "learning_rate": 1.7146077332727083e-05, + "loss": 0.1883, + "step": 17434 + }, + { + "epoch": 5.38, + "learning_rate": 1.7145727478388242e-05, + "loss": 0.1558, + "step": 17435 + }, + { + "epoch": 5.38, + "learning_rate": 1.714537760617663e-05, + "loss": 0.1943, + "step": 17436 + }, + { + "epoch": 5.38, + "learning_rate": 1.7145027716093122e-05, + "loss": 0.176, + "step": 17437 + }, + { + "epoch": 5.39, + "learning_rate": 1.71446778081386e-05, + "loss": 0.1976, + "step": 17438 + }, + { + "epoch": 5.39, + "learning_rate": 1.7144327882313935e-05, + "loss": 0.1866, + "step": 17439 + }, + { + "epoch": 5.39, + "learning_rate": 1.7143977938620002e-05, + "loss": 0.1788, + "step": 17440 + }, + { + "epoch": 5.39, + "learning_rate": 1.714362797705768e-05, + "loss": 0.1701, + "step": 17441 + }, + { + "epoch": 5.39, + "learning_rate": 1.7143277997627836e-05, + "loss": 0.1925, + "step": 17442 + }, + { + "epoch": 5.39, + "learning_rate": 1.7142928000331357e-05, + "loss": 0.1612, + "step": 17443 + }, + { + "epoch": 5.39, + "learning_rate": 1.7142577985169108e-05, + "loss": 0.1862, + "step": 17444 + }, + { + "epoch": 5.39, + "learning_rate": 1.714222795214197e-05, + "loss": 0.1861, + "step": 17445 + }, + { + "epoch": 5.39, + "learning_rate": 1.7141877901250818e-05, + "loss": 0.1852, + "step": 17446 + }, + { + "epoch": 5.39, + "learning_rate": 1.7141527832496526e-05, + "loss": 0.2009, + "step": 17447 + }, + { + "epoch": 5.39, + "learning_rate": 1.7141177745879973e-05, + "loss": 0.1769, + "step": 17448 + }, + { + "epoch": 5.39, + "learning_rate": 1.714082764140203e-05, + "loss": 0.1838, + "step": 17449 + }, + { + "epoch": 5.39, + "learning_rate": 1.7140477519063572e-05, + "loss": 0.1926, + "step": 17450 + }, + { + "epoch": 5.39, + "learning_rate": 1.714012737886548e-05, + "loss": 0.1763, + "step": 17451 + }, + { + "epoch": 5.39, + "learning_rate": 1.7139777220808627e-05, + "loss": 0.1958, + "step": 17452 + }, + { + "epoch": 5.39, + "learning_rate": 1.713942704489389e-05, + "loss": 0.1805, + "step": 17453 + }, + { + "epoch": 5.39, + "learning_rate": 1.7139076851122142e-05, + "loss": 0.1823, + "step": 17454 + }, + { + "epoch": 5.39, + "learning_rate": 1.713872663949426e-05, + "loss": 0.1859, + "step": 17455 + }, + { + "epoch": 5.39, + "learning_rate": 1.7138376410011122e-05, + "loss": 0.1774, + "step": 17456 + }, + { + "epoch": 5.39, + "learning_rate": 1.7138026162673605e-05, + "loss": 0.1791, + "step": 17457 + }, + { + "epoch": 5.39, + "learning_rate": 1.713767589748258e-05, + "loss": 0.1719, + "step": 17458 + }, + { + "epoch": 5.39, + "learning_rate": 1.7137325614438928e-05, + "loss": 0.168, + "step": 17459 + }, + { + "epoch": 5.39, + "learning_rate": 1.7136975313543517e-05, + "loss": 0.1883, + "step": 17460 + }, + { + "epoch": 5.39, + "learning_rate": 1.7136624994797232e-05, + "loss": 0.1875, + "step": 17461 + }, + { + "epoch": 5.39, + "learning_rate": 1.7136274658200947e-05, + "loss": 0.1706, + "step": 17462 + }, + { + "epoch": 5.39, + "learning_rate": 1.713592430375554e-05, + "loss": 0.1593, + "step": 17463 + }, + { + "epoch": 5.39, + "learning_rate": 1.7135573931461883e-05, + "loss": 0.1812, + "step": 17464 + }, + { + "epoch": 5.39, + "learning_rate": 1.7135223541320855e-05, + "loss": 0.1816, + "step": 17465 + }, + { + "epoch": 5.39, + "learning_rate": 1.713487313333333e-05, + "loss": 0.1745, + "step": 17466 + }, + { + "epoch": 5.39, + "learning_rate": 1.7134522707500187e-05, + "loss": 0.1803, + "step": 17467 + }, + { + "epoch": 5.39, + "learning_rate": 1.71341722638223e-05, + "loss": 0.1849, + "step": 17468 + }, + { + "epoch": 5.39, + "learning_rate": 1.7133821802300547e-05, + "loss": 0.1869, + "step": 17469 + }, + { + "epoch": 5.4, + "learning_rate": 1.7133471322935806e-05, + "loss": 0.1685, + "step": 17470 + }, + { + "epoch": 5.4, + "learning_rate": 1.713312082572895e-05, + "loss": 0.1754, + "step": 17471 + }, + { + "epoch": 5.4, + "learning_rate": 1.7132770310680858e-05, + "loss": 0.1639, + "step": 17472 + }, + { + "epoch": 5.4, + "learning_rate": 1.713241977779241e-05, + "loss": 0.1724, + "step": 17473 + }, + { + "epoch": 5.4, + "learning_rate": 1.7132069227064475e-05, + "loss": 0.1904, + "step": 17474 + }, + { + "epoch": 5.4, + "learning_rate": 1.7131718658497938e-05, + "loss": 0.1775, + "step": 17475 + }, + { + "epoch": 5.4, + "learning_rate": 1.713136807209367e-05, + "loss": 0.1876, + "step": 17476 + }, + { + "epoch": 5.4, + "learning_rate": 1.713101746785255e-05, + "loss": 0.194, + "step": 17477 + }, + { + "epoch": 5.4, + "learning_rate": 1.713066684577545e-05, + "loss": 0.1955, + "step": 17478 + }, + { + "epoch": 5.4, + "learning_rate": 1.713031620586326e-05, + "loss": 0.1762, + "step": 17479 + }, + { + "epoch": 5.4, + "learning_rate": 1.712996554811684e-05, + "loss": 0.1795, + "step": 17480 + }, + { + "epoch": 5.4, + "learning_rate": 1.7129614872537083e-05, + "loss": 0.188, + "step": 17481 + }, + { + "epoch": 5.4, + "learning_rate": 1.7129264179124856e-05, + "loss": 0.1804, + "step": 17482 + }, + { + "epoch": 5.4, + "learning_rate": 1.712891346788104e-05, + "loss": 0.169, + "step": 17483 + }, + { + "epoch": 5.4, + "learning_rate": 1.712856273880651e-05, + "loss": 0.1741, + "step": 17484 + }, + { + "epoch": 5.4, + "learning_rate": 1.7128211991902147e-05, + "loss": 0.1739, + "step": 17485 + }, + { + "epoch": 5.4, + "learning_rate": 1.712786122716882e-05, + "loss": 0.1847, + "step": 17486 + }, + { + "epoch": 5.4, + "learning_rate": 1.7127510444607417e-05, + "loss": 0.1694, + "step": 17487 + }, + { + "epoch": 5.4, + "learning_rate": 1.7127159644218808e-05, + "loss": 0.182, + "step": 17488 + }, + { + "epoch": 5.4, + "learning_rate": 1.7126808826003876e-05, + "loss": 0.1689, + "step": 17489 + }, + { + "epoch": 5.4, + "learning_rate": 1.7126457989963494e-05, + "loss": 0.1756, + "step": 17490 + }, + { + "epoch": 5.4, + "learning_rate": 1.7126107136098538e-05, + "loss": 0.1873, + "step": 17491 + }, + { + "epoch": 5.4, + "learning_rate": 1.712575626440989e-05, + "loss": 0.184, + "step": 17492 + }, + { + "epoch": 5.4, + "learning_rate": 1.7125405374898426e-05, + "loss": 0.1805, + "step": 17493 + }, + { + "epoch": 5.4, + "learning_rate": 1.7125054467565027e-05, + "loss": 0.184, + "step": 17494 + }, + { + "epoch": 5.4, + "learning_rate": 1.7124703542410562e-05, + "loss": 0.17, + "step": 17495 + }, + { + "epoch": 5.4, + "learning_rate": 1.7124352599435913e-05, + "loss": 0.1865, + "step": 17496 + }, + { + "epoch": 5.4, + "learning_rate": 1.7124001638641965e-05, + "loss": 0.1964, + "step": 17497 + }, + { + "epoch": 5.4, + "learning_rate": 1.7123650660029584e-05, + "loss": 0.1919, + "step": 17498 + }, + { + "epoch": 5.4, + "learning_rate": 1.7123299663599658e-05, + "loss": 0.1893, + "step": 17499 + }, + { + "epoch": 5.4, + "learning_rate": 1.712294864935306e-05, + "loss": 0.1775, + "step": 17500 + }, + { + "epoch": 5.4, + "learning_rate": 1.7122597617290662e-05, + "loss": 0.1662, + "step": 17501 + }, + { + "epoch": 5.41, + "learning_rate": 1.7122246567413354e-05, + "loss": 0.1846, + "step": 17502 + }, + { + "epoch": 5.41, + "learning_rate": 1.7121895499722008e-05, + "loss": 0.1856, + "step": 17503 + }, + { + "epoch": 5.41, + "learning_rate": 1.71215444142175e-05, + "loss": 0.1702, + "step": 17504 + }, + { + "epoch": 5.41, + "learning_rate": 1.712119331090071e-05, + "loss": 0.1848, + "step": 17505 + }, + { + "epoch": 5.41, + "learning_rate": 1.712084218977252e-05, + "loss": 0.182, + "step": 17506 + }, + { + "epoch": 5.41, + "learning_rate": 1.7120491050833807e-05, + "loss": 0.1825, + "step": 17507 + }, + { + "epoch": 5.41, + "learning_rate": 1.712013989408544e-05, + "loss": 0.1817, + "step": 17508 + }, + { + "epoch": 5.41, + "learning_rate": 1.7119788719528307e-05, + "loss": 0.1845, + "step": 17509 + }, + { + "epoch": 5.41, + "learning_rate": 1.7119437527163286e-05, + "loss": 0.1812, + "step": 17510 + }, + { + "epoch": 5.41, + "learning_rate": 1.7119086316991254e-05, + "loss": 0.1806, + "step": 17511 + }, + { + "epoch": 5.41, + "learning_rate": 1.7118735089013085e-05, + "loss": 0.1951, + "step": 17512 + }, + { + "epoch": 5.41, + "learning_rate": 1.7118383843229663e-05, + "loss": 0.1692, + "step": 17513 + }, + { + "epoch": 5.41, + "learning_rate": 1.7118032579641866e-05, + "loss": 0.1779, + "step": 17514 + }, + { + "epoch": 5.41, + "learning_rate": 1.711768129825057e-05, + "loss": 0.1848, + "step": 17515 + }, + { + "epoch": 5.41, + "learning_rate": 1.7117329999056654e-05, + "loss": 0.1802, + "step": 17516 + }, + { + "epoch": 5.41, + "learning_rate": 1.7116978682061e-05, + "loss": 0.1788, + "step": 17517 + }, + { + "epoch": 5.41, + "learning_rate": 1.7116627347264483e-05, + "loss": 0.1738, + "step": 17518 + }, + { + "epoch": 5.41, + "learning_rate": 1.711627599466798e-05, + "loss": 0.1794, + "step": 17519 + }, + { + "epoch": 5.41, + "learning_rate": 1.7115924624272378e-05, + "loss": 0.1677, + "step": 17520 + }, + { + "epoch": 5.41, + "learning_rate": 1.7115573236078547e-05, + "loss": 0.1913, + "step": 17521 + }, + { + "epoch": 5.41, + "learning_rate": 1.711522183008737e-05, + "loss": 0.1854, + "step": 17522 + }, + { + "epoch": 5.41, + "learning_rate": 1.711487040629973e-05, + "loss": 0.1844, + "step": 17523 + }, + { + "epoch": 5.41, + "learning_rate": 1.7114518964716496e-05, + "loss": 0.1689, + "step": 17524 + }, + { + "epoch": 5.41, + "learning_rate": 1.7114167505338555e-05, + "loss": 0.1862, + "step": 17525 + }, + { + "epoch": 5.41, + "learning_rate": 1.7113816028166782e-05, + "loss": 0.1994, + "step": 17526 + }, + { + "epoch": 5.41, + "learning_rate": 1.7113464533202056e-05, + "loss": 0.191, + "step": 17527 + }, + { + "epoch": 5.41, + "learning_rate": 1.711311302044526e-05, + "loss": 0.1918, + "step": 17528 + }, + { + "epoch": 5.41, + "learning_rate": 1.7112761489897273e-05, + "loss": 0.1729, + "step": 17529 + }, + { + "epoch": 5.41, + "learning_rate": 1.7112409941558968e-05, + "loss": 0.1903, + "step": 17530 + }, + { + "epoch": 5.41, + "learning_rate": 1.711205837543123e-05, + "loss": 0.1627, + "step": 17531 + }, + { + "epoch": 5.41, + "learning_rate": 1.711170679151494e-05, + "loss": 0.1782, + "step": 17532 + }, + { + "epoch": 5.41, + "learning_rate": 1.7111355189810973e-05, + "loss": 0.17, + "step": 17533 + }, + { + "epoch": 5.41, + "learning_rate": 1.7111003570320207e-05, + "loss": 0.187, + "step": 17534 + }, + { + "epoch": 5.42, + "learning_rate": 1.7110651933043527e-05, + "loss": 0.186, + "step": 17535 + }, + { + "epoch": 5.42, + "learning_rate": 1.7110300277981808e-05, + "loss": 0.1769, + "step": 17536 + }, + { + "epoch": 5.42, + "learning_rate": 1.7109948605135928e-05, + "loss": 0.1897, + "step": 17537 + }, + { + "epoch": 5.42, + "learning_rate": 1.7109596914506777e-05, + "loss": 0.1765, + "step": 17538 + }, + { + "epoch": 5.42, + "learning_rate": 1.710924520609522e-05, + "loss": 0.1684, + "step": 17539 + }, + { + "epoch": 5.42, + "learning_rate": 1.7108893479902148e-05, + "loss": 0.1811, + "step": 17540 + }, + { + "epoch": 5.42, + "learning_rate": 1.7108541735928438e-05, + "loss": 0.1899, + "step": 17541 + }, + { + "epoch": 5.42, + "learning_rate": 1.7108189974174968e-05, + "loss": 0.1723, + "step": 17542 + }, + { + "epoch": 5.42, + "learning_rate": 1.7107838194642618e-05, + "loss": 0.1713, + "step": 17543 + }, + { + "epoch": 5.42, + "learning_rate": 1.7107486397332266e-05, + "loss": 0.1805, + "step": 17544 + }, + { + "epoch": 5.42, + "learning_rate": 1.7107134582244794e-05, + "loss": 0.1795, + "step": 17545 + }, + { + "epoch": 5.42, + "learning_rate": 1.7106782749381085e-05, + "loss": 0.1639, + "step": 17546 + }, + { + "epoch": 5.42, + "learning_rate": 1.7106430898742016e-05, + "loss": 0.1817, + "step": 17547 + }, + { + "epoch": 5.42, + "learning_rate": 1.710607903032847e-05, + "loss": 0.1674, + "step": 17548 + }, + { + "epoch": 5.42, + "learning_rate": 1.710572714414132e-05, + "loss": 0.191, + "step": 17549 + }, + { + "epoch": 5.42, + "learning_rate": 1.710537524018145e-05, + "loss": 0.1838, + "step": 17550 + }, + { + "epoch": 5.42, + "learning_rate": 1.7105023318449744e-05, + "loss": 0.1851, + "step": 17551 + }, + { + "epoch": 5.42, + "learning_rate": 1.7104671378947074e-05, + "loss": 0.2061, + "step": 17552 + }, + { + "epoch": 5.42, + "learning_rate": 1.710431942167433e-05, + "loss": 0.1702, + "step": 17553 + }, + { + "epoch": 5.42, + "learning_rate": 1.7103967446632383e-05, + "loss": 0.1811, + "step": 17554 + }, + { + "epoch": 5.42, + "learning_rate": 1.7103615453822118e-05, + "loss": 0.1687, + "step": 17555 + }, + { + "epoch": 5.42, + "learning_rate": 1.7103263443244418e-05, + "loss": 0.1821, + "step": 17556 + }, + { + "epoch": 5.42, + "learning_rate": 1.710291141490016e-05, + "loss": 0.1972, + "step": 17557 + }, + { + "epoch": 5.42, + "learning_rate": 1.7102559368790223e-05, + "loss": 0.1725, + "step": 17558 + }, + { + "epoch": 5.42, + "learning_rate": 1.7102207304915492e-05, + "loss": 0.2048, + "step": 17559 + }, + { + "epoch": 5.42, + "learning_rate": 1.7101855223276845e-05, + "loss": 0.1872, + "step": 17560 + }, + { + "epoch": 5.42, + "learning_rate": 1.710150312387516e-05, + "loss": 0.1949, + "step": 17561 + }, + { + "epoch": 5.42, + "learning_rate": 1.7101151006711324e-05, + "loss": 0.1982, + "step": 17562 + }, + { + "epoch": 5.42, + "learning_rate": 1.7100798871786213e-05, + "loss": 0.1858, + "step": 17563 + }, + { + "epoch": 5.42, + "learning_rate": 1.710044671910071e-05, + "loss": 0.1861, + "step": 17564 + }, + { + "epoch": 5.42, + "learning_rate": 1.710009454865569e-05, + "loss": 0.1804, + "step": 17565 + }, + { + "epoch": 5.42, + "learning_rate": 1.709974236045204e-05, + "loss": 0.1886, + "step": 17566 + }, + { + "epoch": 5.43, + "learning_rate": 1.7099390154490644e-05, + "loss": 0.1875, + "step": 17567 + }, + { + "epoch": 5.43, + "learning_rate": 1.7099037930772374e-05, + "loss": 0.1859, + "step": 17568 + }, + { + "epoch": 5.43, + "learning_rate": 1.709868568929812e-05, + "loss": 0.1701, + "step": 17569 + }, + { + "epoch": 5.43, + "learning_rate": 1.7098333430068753e-05, + "loss": 0.182, + "step": 17570 + }, + { + "epoch": 5.43, + "learning_rate": 1.7097981153085165e-05, + "loss": 0.1845, + "step": 17571 + }, + { + "epoch": 5.43, + "learning_rate": 1.7097628858348227e-05, + "loss": 0.1888, + "step": 17572 + }, + { + "epoch": 5.43, + "learning_rate": 1.7097276545858827e-05, + "loss": 0.1824, + "step": 17573 + }, + { + "epoch": 5.43, + "learning_rate": 1.7096924215617842e-05, + "loss": 0.1834, + "step": 17574 + }, + { + "epoch": 5.43, + "learning_rate": 1.7096571867626157e-05, + "loss": 0.1932, + "step": 17575 + }, + { + "epoch": 5.43, + "learning_rate": 1.709621950188465e-05, + "loss": 0.18, + "step": 17576 + }, + { + "epoch": 5.43, + "learning_rate": 1.7095867118394203e-05, + "loss": 0.1967, + "step": 17577 + }, + { + "epoch": 5.43, + "learning_rate": 1.7095514717155702e-05, + "loss": 0.1753, + "step": 17578 + }, + { + "epoch": 5.43, + "learning_rate": 1.7095162298170022e-05, + "loss": 0.1783, + "step": 17579 + }, + { + "epoch": 5.43, + "learning_rate": 1.7094809861438046e-05, + "loss": 0.1833, + "step": 17580 + }, + { + "epoch": 5.43, + "learning_rate": 1.7094457406960655e-05, + "loss": 0.1863, + "step": 17581 + }, + { + "epoch": 5.43, + "learning_rate": 1.7094104934738737e-05, + "loss": 0.1985, + "step": 17582 + }, + { + "epoch": 5.43, + "learning_rate": 1.7093752444773163e-05, + "loss": 0.1729, + "step": 17583 + }, + { + "epoch": 5.43, + "learning_rate": 1.7093399937064827e-05, + "loss": 0.1747, + "step": 17584 + }, + { + "epoch": 5.43, + "learning_rate": 1.70930474116146e-05, + "loss": 0.1842, + "step": 17585 + }, + { + "epoch": 5.43, + "learning_rate": 1.709269486842337e-05, + "loss": 0.1789, + "step": 17586 + }, + { + "epoch": 5.43, + "learning_rate": 1.7092342307492012e-05, + "loss": 0.185, + "step": 17587 + }, + { + "epoch": 5.43, + "learning_rate": 1.7091989728821414e-05, + "loss": 0.178, + "step": 17588 + }, + { + "epoch": 5.43, + "learning_rate": 1.7091637132412458e-05, + "loss": 0.1734, + "step": 17589 + }, + { + "epoch": 5.43, + "learning_rate": 1.7091284518266026e-05, + "loss": 0.1792, + "step": 17590 + }, + { + "epoch": 5.43, + "learning_rate": 1.7090931886382992e-05, + "loss": 0.1807, + "step": 17591 + }, + { + "epoch": 5.43, + "learning_rate": 1.709057923676425e-05, + "loss": 0.1807, + "step": 17592 + }, + { + "epoch": 5.43, + "learning_rate": 1.7090226569410674e-05, + "loss": 0.1925, + "step": 17593 + }, + { + "epoch": 5.43, + "learning_rate": 1.7089873884323146e-05, + "loss": 0.1851, + "step": 17594 + }, + { + "epoch": 5.43, + "learning_rate": 1.7089521181502552e-05, + "loss": 0.2041, + "step": 17595 + }, + { + "epoch": 5.43, + "learning_rate": 1.708916846094977e-05, + "loss": 0.1875, + "step": 17596 + }, + { + "epoch": 5.43, + "learning_rate": 1.7088815722665694e-05, + "loss": 0.1819, + "step": 17597 + }, + { + "epoch": 5.43, + "learning_rate": 1.7088462966651188e-05, + "loss": 0.1774, + "step": 17598 + }, + { + "epoch": 5.44, + "learning_rate": 1.7088110192907143e-05, + "loss": 0.1898, + "step": 17599 + }, + { + "epoch": 5.44, + "learning_rate": 1.7087757401434445e-05, + "loss": 0.1684, + "step": 17600 + }, + { + "epoch": 5.44, + "learning_rate": 1.7087404592233974e-05, + "loss": 0.1945, + "step": 17601 + }, + { + "epoch": 5.44, + "learning_rate": 1.708705176530661e-05, + "loss": 0.1868, + "step": 17602 + }, + { + "epoch": 5.44, + "learning_rate": 1.7086698920653234e-05, + "loss": 0.1857, + "step": 17603 + }, + { + "epoch": 5.44, + "learning_rate": 1.7086346058274734e-05, + "loss": 0.1818, + "step": 17604 + }, + { + "epoch": 5.44, + "learning_rate": 1.7085993178171988e-05, + "loss": 0.1911, + "step": 17605 + }, + { + "epoch": 5.44, + "learning_rate": 1.7085640280345887e-05, + "loss": 0.168, + "step": 17606 + }, + { + "epoch": 5.44, + "learning_rate": 1.7085287364797302e-05, + "loss": 0.1807, + "step": 17607 + }, + { + "epoch": 5.44, + "learning_rate": 1.708493443152712e-05, + "loss": 0.1902, + "step": 17608 + }, + { + "epoch": 5.44, + "learning_rate": 1.7084581480536228e-05, + "loss": 0.1932, + "step": 17609 + }, + { + "epoch": 5.44, + "learning_rate": 1.7084228511825504e-05, + "loss": 0.1751, + "step": 17610 + }, + { + "epoch": 5.44, + "learning_rate": 1.7083875525395834e-05, + "loss": 0.1922, + "step": 17611 + }, + { + "epoch": 5.44, + "learning_rate": 1.7083522521248097e-05, + "loss": 0.1839, + "step": 17612 + }, + { + "epoch": 5.44, + "learning_rate": 1.708316949938318e-05, + "loss": 0.1907, + "step": 17613 + }, + { + "epoch": 5.44, + "learning_rate": 1.7082816459801965e-05, + "loss": 0.1828, + "step": 17614 + }, + { + "epoch": 5.44, + "learning_rate": 1.708246340250533e-05, + "loss": 0.1776, + "step": 17615 + }, + { + "epoch": 5.44, + "learning_rate": 1.7082110327494167e-05, + "loss": 0.1829, + "step": 17616 + }, + { + "epoch": 5.44, + "learning_rate": 1.7081757234769353e-05, + "loss": 0.1711, + "step": 17617 + }, + { + "epoch": 5.44, + "learning_rate": 1.7081404124331768e-05, + "loss": 0.1799, + "step": 17618 + }, + { + "epoch": 5.44, + "learning_rate": 1.7081050996182305e-05, + "loss": 0.1794, + "step": 17619 + }, + { + "epoch": 5.44, + "learning_rate": 1.708069785032184e-05, + "loss": 0.1966, + "step": 17620 + }, + { + "epoch": 5.44, + "learning_rate": 1.708034468675126e-05, + "loss": 0.1958, + "step": 17621 + }, + { + "epoch": 5.44, + "learning_rate": 1.7079991505471446e-05, + "loss": 0.1717, + "step": 17622 + }, + { + "epoch": 5.44, + "learning_rate": 1.707963830648328e-05, + "loss": 0.1644, + "step": 17623 + }, + { + "epoch": 5.44, + "learning_rate": 1.707928508978765e-05, + "loss": 0.1838, + "step": 17624 + }, + { + "epoch": 5.44, + "learning_rate": 1.7078931855385436e-05, + "loss": 0.1847, + "step": 17625 + }, + { + "epoch": 5.44, + "learning_rate": 1.7078578603277522e-05, + "loss": 0.1862, + "step": 17626 + }, + { + "epoch": 5.44, + "learning_rate": 1.707822533346479e-05, + "loss": 0.167, + "step": 17627 + }, + { + "epoch": 5.44, + "learning_rate": 1.7077872045948123e-05, + "loss": 0.1729, + "step": 17628 + }, + { + "epoch": 5.44, + "learning_rate": 1.7077518740728415e-05, + "loss": 0.1871, + "step": 17629 + }, + { + "epoch": 5.44, + "learning_rate": 1.7077165417806537e-05, + "loss": 0.1831, + "step": 17630 + }, + { + "epoch": 5.44, + "learning_rate": 1.707681207718338e-05, + "loss": 0.174, + "step": 17631 + }, + { + "epoch": 5.45, + "learning_rate": 1.7076458718859823e-05, + "loss": 0.1903, + "step": 17632 + }, + { + "epoch": 5.45, + "learning_rate": 1.7076105342836752e-05, + "loss": 0.1882, + "step": 17633 + }, + { + "epoch": 5.45, + "learning_rate": 1.707575194911505e-05, + "loss": 0.1894, + "step": 17634 + }, + { + "epoch": 5.45, + "learning_rate": 1.7075398537695607e-05, + "loss": 0.1905, + "step": 17635 + }, + { + "epoch": 5.45, + "learning_rate": 1.7075045108579295e-05, + "loss": 0.1871, + "step": 17636 + }, + { + "epoch": 5.45, + "learning_rate": 1.707469166176701e-05, + "loss": 0.1792, + "step": 17637 + }, + { + "epoch": 5.45, + "learning_rate": 1.707433819725963e-05, + "loss": 0.1897, + "step": 17638 + }, + { + "epoch": 5.45, + "learning_rate": 1.7073984715058037e-05, + "loss": 0.1906, + "step": 17639 + }, + { + "epoch": 5.45, + "learning_rate": 1.7073631215163123e-05, + "loss": 0.178, + "step": 17640 + }, + { + "epoch": 5.45, + "learning_rate": 1.7073277697575764e-05, + "loss": 0.1699, + "step": 17641 + }, + { + "epoch": 5.45, + "learning_rate": 1.7072924162296845e-05, + "loss": 0.1856, + "step": 17642 + }, + { + "epoch": 5.45, + "learning_rate": 1.7072570609327253e-05, + "loss": 0.1775, + "step": 17643 + }, + { + "epoch": 5.45, + "learning_rate": 1.7072217038667876e-05, + "loss": 0.1943, + "step": 17644 + }, + { + "epoch": 5.45, + "learning_rate": 1.707186345031959e-05, + "loss": 0.1899, + "step": 17645 + }, + { + "epoch": 5.45, + "learning_rate": 1.7071509844283287e-05, + "loss": 0.195, + "step": 17646 + }, + { + "epoch": 5.45, + "learning_rate": 1.707115622055985e-05, + "loss": 0.1733, + "step": 17647 + }, + { + "epoch": 5.45, + "learning_rate": 1.7070802579150156e-05, + "loss": 0.1941, + "step": 17648 + }, + { + "epoch": 5.45, + "learning_rate": 1.7070448920055098e-05, + "loss": 0.1803, + "step": 17649 + }, + { + "epoch": 5.45, + "learning_rate": 1.7070095243275558e-05, + "loss": 0.181, + "step": 17650 + }, + { + "epoch": 5.45, + "learning_rate": 1.706974154881242e-05, + "loss": 0.1683, + "step": 17651 + }, + { + "epoch": 5.45, + "learning_rate": 1.706938783666657e-05, + "loss": 0.1799, + "step": 17652 + }, + { + "epoch": 5.45, + "learning_rate": 1.706903410683889e-05, + "loss": 0.1721, + "step": 17653 + }, + { + "epoch": 5.45, + "learning_rate": 1.7068680359330265e-05, + "loss": 0.1948, + "step": 17654 + }, + { + "epoch": 5.45, + "learning_rate": 1.7068326594141583e-05, + "loss": 0.1831, + "step": 17655 + }, + { + "epoch": 5.45, + "learning_rate": 1.7067972811273727e-05, + "loss": 0.1837, + "step": 17656 + }, + { + "epoch": 5.45, + "learning_rate": 1.7067619010727582e-05, + "loss": 0.1855, + "step": 17657 + }, + { + "epoch": 5.45, + "learning_rate": 1.7067265192504032e-05, + "loss": 0.1869, + "step": 17658 + }, + { + "epoch": 5.45, + "learning_rate": 1.7066911356603965e-05, + "loss": 0.1872, + "step": 17659 + }, + { + "epoch": 5.45, + "learning_rate": 1.7066557503028262e-05, + "loss": 0.1898, + "step": 17660 + }, + { + "epoch": 5.45, + "learning_rate": 1.706620363177781e-05, + "loss": 0.1826, + "step": 17661 + }, + { + "epoch": 5.45, + "learning_rate": 1.7065849742853494e-05, + "loss": 0.1808, + "step": 17662 + }, + { + "epoch": 5.45, + "learning_rate": 1.70654958362562e-05, + "loss": 0.1829, + "step": 17663 + }, + { + "epoch": 5.46, + "learning_rate": 1.7065141911986807e-05, + "loss": 0.1807, + "step": 17664 + }, + { + "epoch": 5.46, + "learning_rate": 1.706478797004621e-05, + "loss": 0.188, + "step": 17665 + }, + { + "epoch": 5.46, + "learning_rate": 1.7064434010435292e-05, + "loss": 0.1679, + "step": 17666 + }, + { + "epoch": 5.46, + "learning_rate": 1.706408003315493e-05, + "loss": 0.1796, + "step": 17667 + }, + { + "epoch": 5.46, + "learning_rate": 1.7063726038206023e-05, + "loss": 0.1831, + "step": 17668 + }, + { + "epoch": 5.46, + "learning_rate": 1.7063372025589445e-05, + "loss": 0.1677, + "step": 17669 + }, + { + "epoch": 5.46, + "learning_rate": 1.7063017995306084e-05, + "loss": 0.1696, + "step": 17670 + }, + { + "epoch": 5.46, + "learning_rate": 1.7062663947356828e-05, + "loss": 0.182, + "step": 17671 + }, + { + "epoch": 5.46, + "learning_rate": 1.706230988174256e-05, + "loss": 0.1788, + "step": 17672 + }, + { + "epoch": 5.46, + "learning_rate": 1.706195579846417e-05, + "loss": 0.194, + "step": 17673 + }, + { + "epoch": 5.46, + "learning_rate": 1.7061601697522537e-05, + "loss": 0.1653, + "step": 17674 + }, + { + "epoch": 5.46, + "learning_rate": 1.7061247578918553e-05, + "loss": 0.1961, + "step": 17675 + }, + { + "epoch": 5.46, + "learning_rate": 1.7060893442653098e-05, + "loss": 0.1864, + "step": 17676 + }, + { + "epoch": 5.46, + "learning_rate": 1.7060539288727064e-05, + "loss": 0.1936, + "step": 17677 + }, + { + "epoch": 5.46, + "learning_rate": 1.706018511714133e-05, + "loss": 0.1958, + "step": 17678 + }, + { + "epoch": 5.46, + "learning_rate": 1.7059830927896788e-05, + "loss": 0.1657, + "step": 17679 + }, + { + "epoch": 5.46, + "learning_rate": 1.705947672099432e-05, + "loss": 0.1805, + "step": 17680 + }, + { + "epoch": 5.46, + "learning_rate": 1.7059122496434814e-05, + "loss": 0.1861, + "step": 17681 + }, + { + "epoch": 5.46, + "learning_rate": 1.7058768254219154e-05, + "loss": 0.1863, + "step": 17682 + }, + { + "epoch": 5.46, + "learning_rate": 1.7058413994348228e-05, + "loss": 0.1771, + "step": 17683 + }, + { + "epoch": 5.46, + "learning_rate": 1.705805971682292e-05, + "loss": 0.1897, + "step": 17684 + }, + { + "epoch": 5.46, + "learning_rate": 1.705770542164412e-05, + "loss": 0.195, + "step": 17685 + }, + { + "epoch": 5.46, + "learning_rate": 1.7057351108812708e-05, + "loss": 0.1917, + "step": 17686 + }, + { + "epoch": 5.46, + "learning_rate": 1.7056996778329575e-05, + "loss": 0.1852, + "step": 17687 + }, + { + "epoch": 5.46, + "learning_rate": 1.7056642430195606e-05, + "loss": 0.1822, + "step": 17688 + }, + { + "epoch": 5.46, + "learning_rate": 1.705628806441169e-05, + "loss": 0.1894, + "step": 17689 + }, + { + "epoch": 5.46, + "learning_rate": 1.7055933680978708e-05, + "loss": 0.1859, + "step": 17690 + }, + { + "epoch": 5.46, + "learning_rate": 1.705557927989755e-05, + "loss": 0.1843, + "step": 17691 + }, + { + "epoch": 5.46, + "learning_rate": 1.70552248611691e-05, + "loss": 0.1808, + "step": 17692 + }, + { + "epoch": 5.46, + "learning_rate": 1.7054870424794246e-05, + "loss": 0.1794, + "step": 17693 + }, + { + "epoch": 5.46, + "learning_rate": 1.7054515970773875e-05, + "loss": 0.18, + "step": 17694 + }, + { + "epoch": 5.46, + "learning_rate": 1.7054161499108872e-05, + "loss": 0.175, + "step": 17695 + }, + { + "epoch": 5.46, + "learning_rate": 1.7053807009800126e-05, + "loss": 0.1825, + "step": 17696 + }, + { + "epoch": 5.47, + "learning_rate": 1.7053452502848523e-05, + "loss": 0.1802, + "step": 17697 + }, + { + "epoch": 5.47, + "learning_rate": 1.7053097978254945e-05, + "loss": 0.1893, + "step": 17698 + }, + { + "epoch": 5.47, + "learning_rate": 1.7052743436020284e-05, + "loss": 0.1932, + "step": 17699 + }, + { + "epoch": 5.47, + "learning_rate": 1.7052388876145426e-05, + "loss": 0.176, + "step": 17700 + }, + { + "epoch": 5.47, + "learning_rate": 1.7052034298631256e-05, + "loss": 0.2068, + "step": 17701 + }, + { + "epoch": 5.47, + "learning_rate": 1.7051679703478665e-05, + "loss": 0.2176, + "step": 17702 + }, + { + "epoch": 5.47, + "learning_rate": 1.7051325090688537e-05, + "loss": 0.1842, + "step": 17703 + }, + { + "epoch": 5.47, + "learning_rate": 1.7050970460261753e-05, + "loss": 0.1869, + "step": 17704 + }, + { + "epoch": 5.47, + "learning_rate": 1.7050615812199212e-05, + "loss": 0.1907, + "step": 17705 + }, + { + "epoch": 5.47, + "learning_rate": 1.7050261146501794e-05, + "loss": 0.1873, + "step": 17706 + }, + { + "epoch": 5.47, + "learning_rate": 1.7049906463170383e-05, + "loss": 0.182, + "step": 17707 + }, + { + "epoch": 5.47, + "learning_rate": 1.7049551762205873e-05, + "loss": 0.1908, + "step": 17708 + }, + { + "epoch": 5.47, + "learning_rate": 1.704919704360915e-05, + "loss": 0.1826, + "step": 17709 + }, + { + "epoch": 5.47, + "learning_rate": 1.7048842307381094e-05, + "loss": 0.1946, + "step": 17710 + }, + { + "epoch": 5.47, + "learning_rate": 1.7048487553522603e-05, + "loss": 0.1749, + "step": 17711 + }, + { + "epoch": 5.47, + "learning_rate": 1.7048132782034557e-05, + "loss": 0.1608, + "step": 17712 + }, + { + "epoch": 5.47, + "learning_rate": 1.7047777992917845e-05, + "loss": 0.1964, + "step": 17713 + }, + { + "epoch": 5.47, + "learning_rate": 1.7047423186173358e-05, + "loss": 0.1964, + "step": 17714 + }, + { + "epoch": 5.47, + "learning_rate": 1.7047068361801976e-05, + "loss": 0.1896, + "step": 17715 + }, + { + "epoch": 5.47, + "learning_rate": 1.7046713519804593e-05, + "loss": 0.1798, + "step": 17716 + }, + { + "epoch": 5.47, + "learning_rate": 1.7046358660182095e-05, + "loss": 0.1791, + "step": 17717 + }, + { + "epoch": 5.47, + "learning_rate": 1.7046003782935366e-05, + "loss": 0.1787, + "step": 17718 + }, + { + "epoch": 5.47, + "learning_rate": 1.70456488880653e-05, + "loss": 0.1804, + "step": 17719 + }, + { + "epoch": 5.47, + "learning_rate": 1.7045293975572777e-05, + "loss": 0.1918, + "step": 17720 + }, + { + "epoch": 5.47, + "learning_rate": 1.7044939045458693e-05, + "loss": 0.1852, + "step": 17721 + }, + { + "epoch": 5.47, + "learning_rate": 1.7044584097723928e-05, + "loss": 0.1838, + "step": 17722 + }, + { + "epoch": 5.47, + "learning_rate": 1.7044229132369374e-05, + "loss": 0.1882, + "step": 17723 + }, + { + "epoch": 5.47, + "learning_rate": 1.704387414939592e-05, + "loss": 0.1938, + "step": 17724 + }, + { + "epoch": 5.47, + "learning_rate": 1.7043519148804453e-05, + "loss": 0.1763, + "step": 17725 + }, + { + "epoch": 5.47, + "learning_rate": 1.7043164130595856e-05, + "loss": 0.1751, + "step": 17726 + }, + { + "epoch": 5.47, + "learning_rate": 1.7042809094771023e-05, + "loss": 0.1902, + "step": 17727 + }, + { + "epoch": 5.47, + "learning_rate": 1.704245404133084e-05, + "loss": 0.1663, + "step": 17728 + }, + { + "epoch": 5.48, + "learning_rate": 1.7042098970276196e-05, + "loss": 0.1932, + "step": 17729 + }, + { + "epoch": 5.48, + "learning_rate": 1.7041743881607976e-05, + "loss": 0.1772, + "step": 17730 + }, + { + "epoch": 5.48, + "learning_rate": 1.704138877532707e-05, + "loss": 0.1869, + "step": 17731 + }, + { + "epoch": 5.48, + "learning_rate": 1.704103365143437e-05, + "loss": 0.1716, + "step": 17732 + }, + { + "epoch": 5.48, + "learning_rate": 1.7040678509930755e-05, + "loss": 0.1733, + "step": 17733 + }, + { + "epoch": 5.48, + "learning_rate": 1.7040323350817123e-05, + "loss": 0.1772, + "step": 17734 + }, + { + "epoch": 5.48, + "learning_rate": 1.7039968174094356e-05, + "loss": 0.1901, + "step": 17735 + }, + { + "epoch": 5.48, + "learning_rate": 1.7039612979763347e-05, + "loss": 0.1977, + "step": 17736 + }, + { + "epoch": 5.48, + "learning_rate": 1.7039257767824982e-05, + "loss": 0.1778, + "step": 17737 + }, + { + "epoch": 5.48, + "learning_rate": 1.7038902538280147e-05, + "loss": 0.1624, + "step": 17738 + }, + { + "epoch": 5.48, + "learning_rate": 1.7038547291129735e-05, + "loss": 0.1848, + "step": 17739 + }, + { + "epoch": 5.48, + "learning_rate": 1.703819202637463e-05, + "loss": 0.1672, + "step": 17740 + }, + { + "epoch": 5.48, + "learning_rate": 1.7037836744015726e-05, + "loss": 0.1864, + "step": 17741 + }, + { + "epoch": 5.48, + "learning_rate": 1.7037481444053908e-05, + "loss": 0.1909, + "step": 17742 + }, + { + "epoch": 5.48, + "learning_rate": 1.7037126126490064e-05, + "loss": 0.1942, + "step": 17743 + }, + { + "epoch": 5.48, + "learning_rate": 1.7036770791325085e-05, + "loss": 0.171, + "step": 17744 + }, + { + "epoch": 5.48, + "learning_rate": 1.703641543855986e-05, + "loss": 0.2036, + "step": 17745 + }, + { + "epoch": 5.48, + "learning_rate": 1.703606006819527e-05, + "loss": 0.179, + "step": 17746 + }, + { + "epoch": 5.48, + "learning_rate": 1.703570468023222e-05, + "loss": 0.1703, + "step": 17747 + }, + { + "epoch": 5.48, + "learning_rate": 1.7035349274671585e-05, + "loss": 0.1823, + "step": 17748 + }, + { + "epoch": 5.48, + "learning_rate": 1.7034993851514256e-05, + "loss": 0.1737, + "step": 17749 + }, + { + "epoch": 5.48, + "learning_rate": 1.7034638410761128e-05, + "loss": 0.1823, + "step": 17750 + }, + { + "epoch": 5.48, + "learning_rate": 1.7034282952413087e-05, + "loss": 0.1812, + "step": 17751 + }, + { + "epoch": 5.48, + "learning_rate": 1.703392747647102e-05, + "loss": 0.1778, + "step": 17752 + }, + { + "epoch": 5.48, + "learning_rate": 1.7033571982935812e-05, + "loss": 0.1804, + "step": 17753 + }, + { + "epoch": 5.48, + "learning_rate": 1.7033216471808365e-05, + "loss": 0.1713, + "step": 17754 + }, + { + "epoch": 5.48, + "learning_rate": 1.7032860943089558e-05, + "loss": 0.1852, + "step": 17755 + }, + { + "epoch": 5.48, + "learning_rate": 1.7032505396780282e-05, + "loss": 0.1911, + "step": 17756 + }, + { + "epoch": 5.48, + "learning_rate": 1.7032149832881432e-05, + "loss": 0.1873, + "step": 17757 + }, + { + "epoch": 5.48, + "learning_rate": 1.703179425139389e-05, + "loss": 0.1861, + "step": 17758 + }, + { + "epoch": 5.48, + "learning_rate": 1.7031438652318546e-05, + "loss": 0.1989, + "step": 17759 + }, + { + "epoch": 5.48, + "learning_rate": 1.703108303565629e-05, + "loss": 0.1867, + "step": 17760 + }, + { + "epoch": 5.49, + "learning_rate": 1.703072740140802e-05, + "loss": 0.188, + "step": 17761 + }, + { + "epoch": 5.49, + "learning_rate": 1.7030371749574613e-05, + "loss": 0.1939, + "step": 17762 + }, + { + "epoch": 5.49, + "learning_rate": 1.7030016080156962e-05, + "loss": 0.1823, + "step": 17763 + }, + { + "epoch": 5.49, + "learning_rate": 1.702966039315596e-05, + "loss": 0.1754, + "step": 17764 + }, + { + "epoch": 5.49, + "learning_rate": 1.7029304688572498e-05, + "loss": 0.1884, + "step": 17765 + }, + { + "epoch": 5.49, + "learning_rate": 1.7028948966407462e-05, + "loss": 0.1772, + "step": 17766 + }, + { + "epoch": 5.49, + "learning_rate": 1.7028593226661743e-05, + "loss": 0.1798, + "step": 17767 + }, + { + "epoch": 5.49, + "learning_rate": 1.702823746933623e-05, + "loss": 0.1959, + "step": 17768 + }, + { + "epoch": 5.49, + "learning_rate": 1.7027881694431815e-05, + "loss": 0.1895, + "step": 17769 + }, + { + "epoch": 5.49, + "learning_rate": 1.7027525901949384e-05, + "loss": 0.1992, + "step": 17770 + }, + { + "epoch": 5.49, + "learning_rate": 1.7027170091889827e-05, + "loss": 0.1887, + "step": 17771 + }, + { + "epoch": 5.49, + "learning_rate": 1.702681426425404e-05, + "loss": 0.194, + "step": 17772 + }, + { + "epoch": 5.49, + "learning_rate": 1.702645841904291e-05, + "loss": 0.203, + "step": 17773 + }, + { + "epoch": 5.49, + "learning_rate": 1.702610255625732e-05, + "loss": 0.1808, + "step": 17774 + }, + { + "epoch": 5.49, + "learning_rate": 1.7025746675898168e-05, + "loss": 0.1756, + "step": 17775 + }, + { + "epoch": 5.49, + "learning_rate": 1.7025390777966346e-05, + "loss": 0.1702, + "step": 17776 + }, + { + "epoch": 5.49, + "learning_rate": 1.7025034862462737e-05, + "loss": 0.1875, + "step": 17777 + }, + { + "epoch": 5.49, + "learning_rate": 1.7024678929388236e-05, + "loss": 0.1755, + "step": 17778 + }, + { + "epoch": 5.49, + "learning_rate": 1.702432297874373e-05, + "loss": 0.1812, + "step": 17779 + }, + { + "epoch": 5.49, + "learning_rate": 1.7023967010530112e-05, + "loss": 0.1988, + "step": 17780 + }, + { + "epoch": 5.49, + "learning_rate": 1.702361102474827e-05, + "loss": 0.1916, + "step": 17781 + }, + { + "epoch": 5.49, + "learning_rate": 1.70232550213991e-05, + "loss": 0.1834, + "step": 17782 + }, + { + "epoch": 5.49, + "learning_rate": 1.7022899000483483e-05, + "loss": 0.1771, + "step": 17783 + }, + { + "epoch": 5.49, + "learning_rate": 1.7022542962002318e-05, + "loss": 0.1832, + "step": 17784 + }, + { + "epoch": 5.49, + "learning_rate": 1.702218690595649e-05, + "loss": 0.212, + "step": 17785 + }, + { + "epoch": 5.49, + "learning_rate": 1.7021830832346892e-05, + "loss": 0.1897, + "step": 17786 + }, + { + "epoch": 5.49, + "learning_rate": 1.7021474741174417e-05, + "loss": 0.1813, + "step": 17787 + }, + { + "epoch": 5.49, + "learning_rate": 1.702111863243995e-05, + "loss": 0.187, + "step": 17788 + }, + { + "epoch": 5.49, + "learning_rate": 1.7020762506144386e-05, + "loss": 0.1681, + "step": 17789 + }, + { + "epoch": 5.49, + "learning_rate": 1.7020406362288616e-05, + "loss": 0.191, + "step": 17790 + }, + { + "epoch": 5.49, + "learning_rate": 1.7020050200873528e-05, + "loss": 0.1799, + "step": 17791 + }, + { + "epoch": 5.49, + "learning_rate": 1.7019694021900016e-05, + "loss": 0.1938, + "step": 17792 + }, + { + "epoch": 5.49, + "learning_rate": 1.7019337825368968e-05, + "loss": 0.1824, + "step": 17793 + }, + { + "epoch": 5.5, + "learning_rate": 1.701898161128127e-05, + "loss": 0.184, + "step": 17794 + }, + { + "epoch": 5.5, + "learning_rate": 1.7018625379637828e-05, + "loss": 0.1823, + "step": 17795 + }, + { + "epoch": 5.5, + "learning_rate": 1.7018269130439518e-05, + "loss": 0.1788, + "step": 17796 + }, + { + "epoch": 5.5, + "learning_rate": 1.7017912863687236e-05, + "loss": 0.1719, + "step": 17797 + }, + { + "epoch": 5.5, + "learning_rate": 1.7017556579381877e-05, + "loss": 0.1674, + "step": 17798 + }, + { + "epoch": 5.5, + "learning_rate": 1.7017200277524328e-05, + "loss": 0.1914, + "step": 17799 + }, + { + "epoch": 5.5, + "learning_rate": 1.7016843958115484e-05, + "loss": 0.1871, + "step": 17800 + }, + { + "epoch": 5.5, + "learning_rate": 1.701648762115623e-05, + "loss": 0.1747, + "step": 17801 + }, + { + "epoch": 5.5, + "learning_rate": 1.7016131266647462e-05, + "loss": 0.1812, + "step": 17802 + }, + { + "epoch": 5.5, + "learning_rate": 1.701577489459007e-05, + "loss": 0.1708, + "step": 17803 + }, + { + "epoch": 5.5, + "learning_rate": 1.7015418504984945e-05, + "loss": 0.1824, + "step": 17804 + }, + { + "epoch": 5.5, + "learning_rate": 1.7015062097832978e-05, + "loss": 0.1791, + "step": 17805 + }, + { + "epoch": 5.5, + "learning_rate": 1.7014705673135062e-05, + "loss": 0.1824, + "step": 17806 + }, + { + "epoch": 5.5, + "learning_rate": 1.701434923089209e-05, + "loss": 0.1822, + "step": 17807 + }, + { + "epoch": 5.5, + "learning_rate": 1.7013992771104946e-05, + "loss": 0.2113, + "step": 17808 + }, + { + "epoch": 5.5, + "learning_rate": 1.701363629377453e-05, + "loss": 0.1884, + "step": 17809 + }, + { + "epoch": 5.5, + "learning_rate": 1.701327979890173e-05, + "loss": 0.175, + "step": 17810 + }, + { + "epoch": 5.5, + "learning_rate": 1.7012923286487438e-05, + "loss": 0.208, + "step": 17811 + }, + { + "epoch": 5.5, + "learning_rate": 1.7012566756532546e-05, + "loss": 0.2047, + "step": 17812 + }, + { + "epoch": 5.5, + "learning_rate": 1.7012210209037947e-05, + "loss": 0.1887, + "step": 17813 + }, + { + "epoch": 5.5, + "learning_rate": 1.701185364400453e-05, + "loss": 0.1886, + "step": 17814 + }, + { + "epoch": 5.5, + "learning_rate": 1.701149706143319e-05, + "loss": 0.1819, + "step": 17815 + }, + { + "epoch": 5.5, + "learning_rate": 1.7011140461324816e-05, + "loss": 0.1823, + "step": 17816 + }, + { + "epoch": 5.5, + "learning_rate": 1.70107838436803e-05, + "loss": 0.1567, + "step": 17817 + }, + { + "epoch": 5.5, + "learning_rate": 1.7010427208500534e-05, + "loss": 0.1768, + "step": 17818 + }, + { + "epoch": 5.5, + "learning_rate": 1.701007055578641e-05, + "loss": 0.1798, + "step": 17819 + }, + { + "epoch": 5.5, + "learning_rate": 1.7009713885538824e-05, + "loss": 0.1731, + "step": 17820 + }, + { + "epoch": 5.5, + "learning_rate": 1.7009357197758665e-05, + "loss": 0.1861, + "step": 17821 + }, + { + "epoch": 5.5, + "learning_rate": 1.7009000492446825e-05, + "loss": 0.1793, + "step": 17822 + }, + { + "epoch": 5.5, + "learning_rate": 1.7008643769604198e-05, + "loss": 0.184, + "step": 17823 + }, + { + "epoch": 5.5, + "learning_rate": 1.7008287029231668e-05, + "loss": 0.1878, + "step": 17824 + }, + { + "epoch": 5.5, + "learning_rate": 1.7007930271330137e-05, + "loss": 0.1826, + "step": 17825 + }, + { + "epoch": 5.51, + "learning_rate": 1.7007573495900497e-05, + "loss": 0.195, + "step": 17826 + }, + { + "epoch": 5.51, + "learning_rate": 1.700721670294364e-05, + "loss": 0.1919, + "step": 17827 + }, + { + "epoch": 5.51, + "learning_rate": 1.700685989246045e-05, + "loss": 0.1819, + "step": 17828 + }, + { + "epoch": 5.51, + "learning_rate": 1.7006503064451827e-05, + "loss": 0.181, + "step": 17829 + }, + { + "epoch": 5.51, + "learning_rate": 1.7006146218918663e-05, + "loss": 0.1979, + "step": 17830 + }, + { + "epoch": 5.51, + "learning_rate": 1.7005789355861847e-05, + "loss": 0.1677, + "step": 17831 + }, + { + "epoch": 5.51, + "learning_rate": 1.7005432475282278e-05, + "loss": 0.1884, + "step": 17832 + }, + { + "epoch": 5.51, + "learning_rate": 1.7005075577180843e-05, + "loss": 0.1913, + "step": 17833 + }, + { + "epoch": 5.51, + "learning_rate": 1.7004718661558433e-05, + "loss": 0.1817, + "step": 17834 + }, + { + "epoch": 5.51, + "learning_rate": 1.7004361728415947e-05, + "loss": 0.1696, + "step": 17835 + }, + { + "epoch": 5.51, + "learning_rate": 1.7004004777754274e-05, + "loss": 0.1885, + "step": 17836 + }, + { + "epoch": 5.51, + "learning_rate": 1.700364780957431e-05, + "loss": 0.1567, + "step": 17837 + }, + { + "epoch": 5.51, + "learning_rate": 1.7003290823876947e-05, + "loss": 0.196, + "step": 17838 + }, + { + "epoch": 5.51, + "learning_rate": 1.700293382066307e-05, + "loss": 0.1856, + "step": 17839 + }, + { + "epoch": 5.51, + "learning_rate": 1.7002576799933582e-05, + "loss": 0.1811, + "step": 17840 + }, + { + "epoch": 5.51, + "learning_rate": 1.7002219761689373e-05, + "loss": 0.1821, + "step": 17841 + }, + { + "epoch": 5.51, + "learning_rate": 1.7001862705931333e-05, + "loss": 0.1769, + "step": 17842 + }, + { + "epoch": 5.51, + "learning_rate": 1.7001505632660357e-05, + "loss": 0.1909, + "step": 17843 + }, + { + "epoch": 5.51, + "learning_rate": 1.700114854187734e-05, + "loss": 0.1817, + "step": 17844 + }, + { + "epoch": 5.51, + "learning_rate": 1.7000791433583176e-05, + "loss": 0.1895, + "step": 17845 + }, + { + "epoch": 5.51, + "learning_rate": 1.7000434307778753e-05, + "loss": 0.1871, + "step": 17846 + }, + { + "epoch": 5.51, + "learning_rate": 1.7000077164464966e-05, + "loss": 0.1771, + "step": 17847 + }, + { + "epoch": 5.51, + "learning_rate": 1.6999720003642706e-05, + "loss": 0.1913, + "step": 17848 + }, + { + "epoch": 5.51, + "learning_rate": 1.6999362825312876e-05, + "loss": 0.1842, + "step": 17849 + }, + { + "epoch": 5.51, + "learning_rate": 1.699900562947636e-05, + "loss": 0.1965, + "step": 17850 + }, + { + "epoch": 5.51, + "learning_rate": 1.6998648416134054e-05, + "loss": 0.1772, + "step": 17851 + }, + { + "epoch": 5.51, + "learning_rate": 1.6998291185286856e-05, + "loss": 0.1842, + "step": 17852 + }, + { + "epoch": 5.51, + "learning_rate": 1.699793393693565e-05, + "loss": 0.1837, + "step": 17853 + }, + { + "epoch": 5.51, + "learning_rate": 1.699757667108134e-05, + "loss": 0.1835, + "step": 17854 + }, + { + "epoch": 5.51, + "learning_rate": 1.699721938772481e-05, + "loss": 0.1994, + "step": 17855 + }, + { + "epoch": 5.51, + "learning_rate": 1.699686208686696e-05, + "loss": 0.1819, + "step": 17856 + }, + { + "epoch": 5.51, + "learning_rate": 1.6996504768508683e-05, + "loss": 0.1733, + "step": 17857 + }, + { + "epoch": 5.51, + "learning_rate": 1.699614743265087e-05, + "loss": 0.1768, + "step": 17858 + }, + { + "epoch": 5.52, + "learning_rate": 1.6995790079294417e-05, + "loss": 0.1835, + "step": 17859 + }, + { + "epoch": 5.52, + "learning_rate": 1.6995432708440214e-05, + "loss": 0.1833, + "step": 17860 + }, + { + "epoch": 5.52, + "learning_rate": 1.6995075320089164e-05, + "loss": 0.1795, + "step": 17861 + }, + { + "epoch": 5.52, + "learning_rate": 1.6994717914242147e-05, + "loss": 0.1729, + "step": 17862 + }, + { + "epoch": 5.52, + "learning_rate": 1.699436049090007e-05, + "loss": 0.1776, + "step": 17863 + }, + { + "epoch": 5.52, + "learning_rate": 1.699400305006382e-05, + "loss": 0.1742, + "step": 17864 + }, + { + "epoch": 5.52, + "learning_rate": 1.6993645591734296e-05, + "loss": 0.1815, + "step": 17865 + }, + { + "epoch": 5.52, + "learning_rate": 1.6993288115912382e-05, + "loss": 0.1853, + "step": 17866 + }, + { + "epoch": 5.52, + "learning_rate": 1.6992930622598988e-05, + "loss": 0.1907, + "step": 17867 + }, + { + "epoch": 5.52, + "learning_rate": 1.6992573111794993e-05, + "loss": 0.1775, + "step": 17868 + }, + { + "epoch": 5.52, + "learning_rate": 1.6992215583501296e-05, + "loss": 0.1798, + "step": 17869 + }, + { + "epoch": 5.52, + "learning_rate": 1.6991858037718795e-05, + "loss": 0.1893, + "step": 17870 + }, + { + "epoch": 5.52, + "learning_rate": 1.6991500474448383e-05, + "loss": 0.1797, + "step": 17871 + }, + { + "epoch": 5.52, + "learning_rate": 1.6991142893690953e-05, + "loss": 0.202, + "step": 17872 + }, + { + "epoch": 5.52, + "learning_rate": 1.6990785295447395e-05, + "loss": 0.1724, + "step": 17873 + }, + { + "epoch": 5.52, + "learning_rate": 1.6990427679718614e-05, + "loss": 0.1905, + "step": 17874 + }, + { + "epoch": 5.52, + "learning_rate": 1.6990070046505497e-05, + "loss": 0.1793, + "step": 17875 + }, + { + "epoch": 5.52, + "learning_rate": 1.698971239580894e-05, + "loss": 0.1926, + "step": 17876 + }, + { + "epoch": 5.52, + "learning_rate": 1.698935472762983e-05, + "loss": 0.1879, + "step": 17877 + }, + { + "epoch": 5.52, + "learning_rate": 1.698899704196908e-05, + "loss": 0.1939, + "step": 17878 + }, + { + "epoch": 5.52, + "learning_rate": 1.6988639338827567e-05, + "loss": 0.1849, + "step": 17879 + }, + { + "epoch": 5.52, + "learning_rate": 1.6988281618206196e-05, + "loss": 0.196, + "step": 17880 + }, + { + "epoch": 5.52, + "learning_rate": 1.6987923880105857e-05, + "loss": 0.1851, + "step": 17881 + }, + { + "epoch": 5.52, + "learning_rate": 1.698756612452744e-05, + "loss": 0.1976, + "step": 17882 + }, + { + "epoch": 5.52, + "learning_rate": 1.6987208351471853e-05, + "loss": 0.1918, + "step": 17883 + }, + { + "epoch": 5.52, + "learning_rate": 1.698685056093998e-05, + "loss": 0.1917, + "step": 17884 + }, + { + "epoch": 5.52, + "learning_rate": 1.6986492752932722e-05, + "loss": 0.1976, + "step": 17885 + }, + { + "epoch": 5.52, + "learning_rate": 1.6986134927450973e-05, + "loss": 0.1996, + "step": 17886 + }, + { + "epoch": 5.52, + "learning_rate": 1.698577708449562e-05, + "loss": 0.1738, + "step": 17887 + }, + { + "epoch": 5.52, + "learning_rate": 1.698541922406757e-05, + "loss": 0.1837, + "step": 17888 + }, + { + "epoch": 5.52, + "learning_rate": 1.698506134616771e-05, + "loss": 0.1917, + "step": 17889 + }, + { + "epoch": 5.52, + "learning_rate": 1.6984703450796937e-05, + "loss": 0.1986, + "step": 17890 + }, + { + "epoch": 5.53, + "learning_rate": 1.698434553795615e-05, + "loss": 0.1983, + "step": 17891 + }, + { + "epoch": 5.53, + "learning_rate": 1.6983987607646234e-05, + "loss": 0.1906, + "step": 17892 + }, + { + "epoch": 5.53, + "learning_rate": 1.6983629659868096e-05, + "loss": 0.1914, + "step": 17893 + }, + { + "epoch": 5.53, + "learning_rate": 1.698327169462263e-05, + "loss": 0.187, + "step": 17894 + }, + { + "epoch": 5.53, + "learning_rate": 1.6982913711910723e-05, + "loss": 0.1766, + "step": 17895 + }, + { + "epoch": 5.53, + "learning_rate": 1.6982555711733274e-05, + "loss": 0.1853, + "step": 17896 + }, + { + "epoch": 5.53, + "learning_rate": 1.6982197694091184e-05, + "loss": 0.1664, + "step": 17897 + }, + { + "epoch": 5.53, + "learning_rate": 1.6981839658985345e-05, + "loss": 0.1916, + "step": 17898 + }, + { + "epoch": 5.53, + "learning_rate": 1.6981481606416645e-05, + "loss": 0.1886, + "step": 17899 + }, + { + "epoch": 5.53, + "learning_rate": 1.698112353638599e-05, + "loss": 0.1966, + "step": 17900 + }, + { + "epoch": 5.53, + "learning_rate": 1.698076544889427e-05, + "loss": 0.1851, + "step": 17901 + }, + { + "epoch": 5.53, + "learning_rate": 1.6980407343942387e-05, + "loss": 0.1804, + "step": 17902 + }, + { + "epoch": 5.53, + "learning_rate": 1.698004922153123e-05, + "loss": 0.1791, + "step": 17903 + }, + { + "epoch": 5.53, + "learning_rate": 1.6979691081661692e-05, + "loss": 0.183, + "step": 17904 + }, + { + "epoch": 5.53, + "learning_rate": 1.6979332924334678e-05, + "loss": 0.1851, + "step": 17905 + }, + { + "epoch": 5.53, + "learning_rate": 1.697897474955108e-05, + "loss": 0.1992, + "step": 17906 + }, + { + "epoch": 5.53, + "learning_rate": 1.697861655731179e-05, + "loss": 0.1809, + "step": 17907 + }, + { + "epoch": 5.53, + "learning_rate": 1.6978258347617712e-05, + "loss": 0.1887, + "step": 17908 + }, + { + "epoch": 5.53, + "learning_rate": 1.6977900120469734e-05, + "loss": 0.1596, + "step": 17909 + }, + { + "epoch": 5.53, + "learning_rate": 1.6977541875868754e-05, + "loss": 0.1927, + "step": 17910 + }, + { + "epoch": 5.53, + "learning_rate": 1.697718361381567e-05, + "loss": 0.1902, + "step": 17911 + }, + { + "epoch": 5.53, + "learning_rate": 1.697682533431138e-05, + "loss": 0.1792, + "step": 17912 + }, + { + "epoch": 5.53, + "learning_rate": 1.6976467037356774e-05, + "loss": 0.2001, + "step": 17913 + }, + { + "epoch": 5.53, + "learning_rate": 1.6976108722952755e-05, + "loss": 0.1869, + "step": 17914 + }, + { + "epoch": 5.53, + "learning_rate": 1.6975750391100212e-05, + "loss": 0.1764, + "step": 17915 + }, + { + "epoch": 5.53, + "learning_rate": 1.6975392041800044e-05, + "loss": 0.1793, + "step": 17916 + }, + { + "epoch": 5.53, + "learning_rate": 1.6975033675053153e-05, + "loss": 0.1837, + "step": 17917 + }, + { + "epoch": 5.53, + "learning_rate": 1.6974675290860428e-05, + "loss": 0.1837, + "step": 17918 + }, + { + "epoch": 5.53, + "learning_rate": 1.697431688922277e-05, + "loss": 0.1679, + "step": 17919 + }, + { + "epoch": 5.53, + "learning_rate": 1.6973958470141072e-05, + "loss": 0.1674, + "step": 17920 + }, + { + "epoch": 5.53, + "learning_rate": 1.697360003361623e-05, + "loss": 0.1839, + "step": 17921 + }, + { + "epoch": 5.53, + "learning_rate": 1.6973241579649143e-05, + "loss": 0.1805, + "step": 17922 + }, + { + "epoch": 5.54, + "learning_rate": 1.697288310824071e-05, + "loss": 0.1828, + "step": 17923 + }, + { + "epoch": 5.54, + "learning_rate": 1.6972524619391822e-05, + "loss": 0.1945, + "step": 17924 + }, + { + "epoch": 5.54, + "learning_rate": 1.6972166113103378e-05, + "loss": 0.1723, + "step": 17925 + }, + { + "epoch": 5.54, + "learning_rate": 1.6971807589376277e-05, + "loss": 0.1901, + "step": 17926 + }, + { + "epoch": 5.54, + "learning_rate": 1.697144904821141e-05, + "loss": 0.1877, + "step": 17927 + }, + { + "epoch": 5.54, + "learning_rate": 1.6971090489609682e-05, + "loss": 0.1738, + "step": 17928 + }, + { + "epoch": 5.54, + "learning_rate": 1.6970731913571984e-05, + "loss": 0.1681, + "step": 17929 + }, + { + "epoch": 5.54, + "learning_rate": 1.6970373320099208e-05, + "loss": 0.182, + "step": 17930 + }, + { + "epoch": 5.54, + "learning_rate": 1.6970014709192267e-05, + "loss": 0.1897, + "step": 17931 + }, + { + "epoch": 5.54, + "learning_rate": 1.696965608085204e-05, + "loss": 0.1872, + "step": 17932 + }, + { + "epoch": 5.54, + "learning_rate": 1.6969297435079438e-05, + "loss": 0.1883, + "step": 17933 + }, + { + "epoch": 5.54, + "learning_rate": 1.6968938771875348e-05, + "loss": 0.1854, + "step": 17934 + }, + { + "epoch": 5.54, + "learning_rate": 1.6968580091240672e-05, + "loss": 0.2053, + "step": 17935 + }, + { + "epoch": 5.54, + "learning_rate": 1.6968221393176304e-05, + "loss": 0.1784, + "step": 17936 + }, + { + "epoch": 5.54, + "learning_rate": 1.6967862677683146e-05, + "loss": 0.195, + "step": 17937 + }, + { + "epoch": 5.54, + "learning_rate": 1.6967503944762092e-05, + "loss": 0.1932, + "step": 17938 + }, + { + "epoch": 5.54, + "learning_rate": 1.6967145194414043e-05, + "loss": 0.1847, + "step": 17939 + }, + { + "epoch": 5.54, + "learning_rate": 1.696678642663989e-05, + "loss": 0.1786, + "step": 17940 + }, + { + "epoch": 5.54, + "learning_rate": 1.6966427641440532e-05, + "loss": 0.1794, + "step": 17941 + }, + { + "epoch": 5.54, + "learning_rate": 1.6966068838816873e-05, + "loss": 0.1935, + "step": 17942 + }, + { + "epoch": 5.54, + "learning_rate": 1.69657100187698e-05, + "loss": 0.1822, + "step": 17943 + }, + { + "epoch": 5.54, + "learning_rate": 1.6965351181300217e-05, + "loss": 0.1823, + "step": 17944 + }, + { + "epoch": 5.54, + "learning_rate": 1.696499232640902e-05, + "loss": 0.1831, + "step": 17945 + }, + { + "epoch": 5.54, + "learning_rate": 1.6964633454097108e-05, + "loss": 0.1801, + "step": 17946 + }, + { + "epoch": 5.54, + "learning_rate": 1.6964274564365376e-05, + "loss": 0.171, + "step": 17947 + }, + { + "epoch": 5.54, + "learning_rate": 1.6963915657214727e-05, + "loss": 0.1919, + "step": 17948 + }, + { + "epoch": 5.54, + "learning_rate": 1.696355673264605e-05, + "loss": 0.1963, + "step": 17949 + }, + { + "epoch": 5.54, + "learning_rate": 1.696319779066025e-05, + "loss": 0.1639, + "step": 17950 + }, + { + "epoch": 5.54, + "learning_rate": 1.6962838831258223e-05, + "loss": 0.1981, + "step": 17951 + }, + { + "epoch": 5.54, + "learning_rate": 1.6962479854440865e-05, + "loss": 0.1969, + "step": 17952 + }, + { + "epoch": 5.54, + "learning_rate": 1.6962120860209076e-05, + "loss": 0.2037, + "step": 17953 + }, + { + "epoch": 5.54, + "learning_rate": 1.696176184856375e-05, + "loss": 0.169, + "step": 17954 + }, + { + "epoch": 5.54, + "learning_rate": 1.696140281950579e-05, + "loss": 0.1754, + "step": 17955 + }, + { + "epoch": 5.55, + "learning_rate": 1.6961043773036095e-05, + "loss": 0.1839, + "step": 17956 + }, + { + "epoch": 5.55, + "learning_rate": 1.6960684709155555e-05, + "loss": 0.1798, + "step": 17957 + }, + { + "epoch": 5.55, + "learning_rate": 1.6960325627865076e-05, + "loss": 0.1895, + "step": 17958 + }, + { + "epoch": 5.55, + "learning_rate": 1.6959966529165552e-05, + "loss": 0.1822, + "step": 17959 + }, + { + "epoch": 5.55, + "learning_rate": 1.6959607413057882e-05, + "loss": 0.1757, + "step": 17960 + }, + { + "epoch": 5.55, + "learning_rate": 1.6959248279542963e-05, + "loss": 0.1822, + "step": 17961 + }, + { + "epoch": 5.55, + "learning_rate": 1.6958889128621697e-05, + "loss": 0.1747, + "step": 17962 + }, + { + "epoch": 5.55, + "learning_rate": 1.695852996029498e-05, + "loss": 0.188, + "step": 17963 + }, + { + "epoch": 5.55, + "learning_rate": 1.6958170774563713e-05, + "loss": 0.1677, + "step": 17964 + }, + { + "epoch": 5.55, + "learning_rate": 1.6957811571428784e-05, + "loss": 0.185, + "step": 17965 + }, + { + "epoch": 5.55, + "learning_rate": 1.6957452350891107e-05, + "loss": 0.1806, + "step": 17966 + }, + { + "epoch": 5.55, + "learning_rate": 1.6957093112951567e-05, + "loss": 0.1813, + "step": 17967 + }, + { + "epoch": 5.55, + "learning_rate": 1.695673385761107e-05, + "loss": 0.2135, + "step": 17968 + }, + { + "epoch": 5.55, + "learning_rate": 1.6956374584870515e-05, + "loss": 0.1849, + "step": 17969 + }, + { + "epoch": 5.55, + "learning_rate": 1.6956015294730795e-05, + "loss": 0.1816, + "step": 17970 + }, + { + "epoch": 5.55, + "learning_rate": 1.6955655987192815e-05, + "loss": 0.184, + "step": 17971 + }, + { + "epoch": 5.55, + "learning_rate": 1.6955296662257473e-05, + "loss": 0.1946, + "step": 17972 + }, + { + "epoch": 5.55, + "learning_rate": 1.6954937319925663e-05, + "loss": 0.1827, + "step": 17973 + }, + { + "epoch": 5.55, + "learning_rate": 1.6954577960198283e-05, + "loss": 0.1923, + "step": 17974 + }, + { + "epoch": 5.55, + "learning_rate": 1.6954218583076238e-05, + "loss": 0.1758, + "step": 17975 + }, + { + "epoch": 5.55, + "learning_rate": 1.6953859188560425e-05, + "loss": 0.2028, + "step": 17976 + }, + { + "epoch": 5.55, + "learning_rate": 1.695349977665174e-05, + "loss": 0.1975, + "step": 17977 + }, + { + "epoch": 5.55, + "learning_rate": 1.6953140347351086e-05, + "loss": 0.1653, + "step": 17978 + }, + { + "epoch": 5.55, + "learning_rate": 1.6952780900659355e-05, + "loss": 0.1811, + "step": 17979 + }, + { + "epoch": 5.55, + "learning_rate": 1.695242143657746e-05, + "loss": 0.163, + "step": 17980 + }, + { + "epoch": 5.55, + "learning_rate": 1.695206195510628e-05, + "loss": 0.1773, + "step": 17981 + }, + { + "epoch": 5.55, + "learning_rate": 1.695170245624673e-05, + "loss": 0.1805, + "step": 17982 + }, + { + "epoch": 5.55, + "learning_rate": 1.6951342939999702e-05, + "loss": 0.1955, + "step": 17983 + }, + { + "epoch": 5.55, + "learning_rate": 1.69509834063661e-05, + "loss": 0.1793, + "step": 17984 + }, + { + "epoch": 5.55, + "learning_rate": 1.6950623855346823e-05, + "loss": 0.2052, + "step": 17985 + }, + { + "epoch": 5.55, + "learning_rate": 1.6950264286942766e-05, + "loss": 0.1669, + "step": 17986 + }, + { + "epoch": 5.55, + "learning_rate": 1.694990470115483e-05, + "loss": 0.1896, + "step": 17987 + }, + { + "epoch": 5.56, + "learning_rate": 1.694954509798391e-05, + "loss": 0.1773, + "step": 17988 + }, + { + "epoch": 5.56, + "learning_rate": 1.694918547743092e-05, + "loss": 0.1871, + "step": 17989 + }, + { + "epoch": 5.56, + "learning_rate": 1.6948825839496744e-05, + "loss": 0.1947, + "step": 17990 + }, + { + "epoch": 5.56, + "learning_rate": 1.6948466184182285e-05, + "loss": 0.188, + "step": 17991 + }, + { + "epoch": 5.56, + "learning_rate": 1.6948106511488446e-05, + "loss": 0.1911, + "step": 17992 + }, + { + "epoch": 5.56, + "learning_rate": 1.694774682141613e-05, + "loss": 0.1878, + "step": 17993 + }, + { + "epoch": 5.56, + "learning_rate": 1.694738711396623e-05, + "loss": 0.2, + "step": 17994 + }, + { + "epoch": 5.56, + "learning_rate": 1.6947027389139644e-05, + "loss": 0.1894, + "step": 17995 + }, + { + "epoch": 5.56, + "learning_rate": 1.6946667646937278e-05, + "loss": 0.1923, + "step": 17996 + }, + { + "epoch": 5.56, + "learning_rate": 1.694630788736003e-05, + "loss": 0.1834, + "step": 17997 + }, + { + "epoch": 5.56, + "learning_rate": 1.6945948110408798e-05, + "loss": 0.1971, + "step": 17998 + }, + { + "epoch": 5.56, + "learning_rate": 1.6945588316084483e-05, + "loss": 0.1904, + "step": 17999 + }, + { + "epoch": 5.56, + "learning_rate": 1.6945228504387986e-05, + "loss": 0.1896, + "step": 18000 + }, + { + "epoch": 5.56, + "learning_rate": 1.6944868675320206e-05, + "loss": 0.1841, + "step": 18001 + }, + { + "epoch": 5.56, + "learning_rate": 1.694450882888204e-05, + "loss": 0.1864, + "step": 18002 + }, + { + "epoch": 5.56, + "learning_rate": 1.6944148965074392e-05, + "loss": 0.1946, + "step": 18003 + }, + { + "epoch": 5.56, + "learning_rate": 1.694378908389816e-05, + "loss": 0.1776, + "step": 18004 + }, + { + "epoch": 5.56, + "learning_rate": 1.694342918535425e-05, + "loss": 0.1815, + "step": 18005 + }, + { + "epoch": 5.56, + "learning_rate": 1.694306926944355e-05, + "loss": 0.184, + "step": 18006 + }, + { + "epoch": 5.56, + "learning_rate": 1.694270933616697e-05, + "loss": 0.1615, + "step": 18007 + }, + { + "epoch": 5.56, + "learning_rate": 1.694234938552541e-05, + "loss": 0.1976, + "step": 18008 + }, + { + "epoch": 5.56, + "learning_rate": 1.6941989417519766e-05, + "loss": 0.1871, + "step": 18009 + }, + { + "epoch": 5.56, + "learning_rate": 1.694162943215094e-05, + "loss": 0.2059, + "step": 18010 + }, + { + "epoch": 5.56, + "learning_rate": 1.6941269429419834e-05, + "loss": 0.1851, + "step": 18011 + }, + { + "epoch": 5.56, + "learning_rate": 1.6940909409327347e-05, + "loss": 0.1887, + "step": 18012 + }, + { + "epoch": 5.56, + "learning_rate": 1.6940549371874378e-05, + "loss": 0.1975, + "step": 18013 + }, + { + "epoch": 5.56, + "learning_rate": 1.694018931706183e-05, + "loss": 0.1803, + "step": 18014 + }, + { + "epoch": 5.56, + "learning_rate": 1.6939829244890607e-05, + "loss": 0.1769, + "step": 18015 + }, + { + "epoch": 5.56, + "learning_rate": 1.6939469155361602e-05, + "loss": 0.1987, + "step": 18016 + }, + { + "epoch": 5.56, + "learning_rate": 1.6939109048475716e-05, + "loss": 0.2051, + "step": 18017 + }, + { + "epoch": 5.56, + "learning_rate": 1.6938748924233857e-05, + "loss": 0.1792, + "step": 18018 + }, + { + "epoch": 5.56, + "learning_rate": 1.693838878263692e-05, + "loss": 0.189, + "step": 18019 + }, + { + "epoch": 5.57, + "learning_rate": 1.6938028623685805e-05, + "loss": 0.1878, + "step": 18020 + }, + { + "epoch": 5.57, + "learning_rate": 1.6937668447381418e-05, + "loss": 0.1977, + "step": 18021 + }, + { + "epoch": 5.57, + "learning_rate": 1.6937308253724657e-05, + "loss": 0.1995, + "step": 18022 + }, + { + "epoch": 5.57, + "learning_rate": 1.693694804271642e-05, + "loss": 0.193, + "step": 18023 + }, + { + "epoch": 5.57, + "learning_rate": 1.6936587814357612e-05, + "loss": 0.1986, + "step": 18024 + }, + { + "epoch": 5.57, + "learning_rate": 1.693622756864913e-05, + "loss": 0.1959, + "step": 18025 + }, + { + "epoch": 5.57, + "learning_rate": 1.693586730559188e-05, + "loss": 0.1814, + "step": 18026 + }, + { + "epoch": 5.57, + "learning_rate": 1.6935507025186765e-05, + "loss": 0.2042, + "step": 18027 + }, + { + "epoch": 5.57, + "learning_rate": 1.6935146727434676e-05, + "loss": 0.175, + "step": 18028 + }, + { + "epoch": 5.57, + "learning_rate": 1.6934786412336524e-05, + "loss": 0.1974, + "step": 18029 + }, + { + "epoch": 5.57, + "learning_rate": 1.6934426079893204e-05, + "loss": 0.1917, + "step": 18030 + }, + { + "epoch": 5.57, + "learning_rate": 1.693406573010562e-05, + "loss": 0.1937, + "step": 18031 + }, + { + "epoch": 5.57, + "learning_rate": 1.6933705362974672e-05, + "loss": 0.1822, + "step": 18032 + }, + { + "epoch": 5.57, + "learning_rate": 1.6933344978501266e-05, + "loss": 0.1882, + "step": 18033 + }, + { + "epoch": 5.57, + "learning_rate": 1.6932984576686297e-05, + "loss": 0.1753, + "step": 18034 + }, + { + "epoch": 5.57, + "learning_rate": 1.693262415753067e-05, + "loss": 0.1882, + "step": 18035 + }, + { + "epoch": 5.57, + "learning_rate": 1.6932263721035285e-05, + "loss": 0.1958, + "step": 18036 + }, + { + "epoch": 5.57, + "learning_rate": 1.693190326720104e-05, + "loss": 0.1735, + "step": 18037 + }, + { + "epoch": 5.57, + "learning_rate": 1.693154279602885e-05, + "loss": 0.1912, + "step": 18038 + }, + { + "epoch": 5.57, + "learning_rate": 1.69311823075196e-05, + "loss": 0.1783, + "step": 18039 + }, + { + "epoch": 5.57, + "learning_rate": 1.69308218016742e-05, + "loss": 0.194, + "step": 18040 + }, + { + "epoch": 5.57, + "learning_rate": 1.693046127849355e-05, + "loss": 0.1795, + "step": 18041 + }, + { + "epoch": 5.57, + "learning_rate": 1.6930100737978555e-05, + "loss": 0.1928, + "step": 18042 + }, + { + "epoch": 5.57, + "learning_rate": 1.6929740180130112e-05, + "loss": 0.2001, + "step": 18043 + }, + { + "epoch": 5.57, + "learning_rate": 1.692937960494913e-05, + "loss": 0.1878, + "step": 18044 + }, + { + "epoch": 5.57, + "learning_rate": 1.69290190124365e-05, + "loss": 0.1859, + "step": 18045 + }, + { + "epoch": 5.57, + "learning_rate": 1.6928658402593128e-05, + "loss": 0.1989, + "step": 18046 + }, + { + "epoch": 5.57, + "learning_rate": 1.692829777541992e-05, + "loss": 0.1657, + "step": 18047 + }, + { + "epoch": 5.57, + "learning_rate": 1.6927937130917777e-05, + "loss": 0.1637, + "step": 18048 + }, + { + "epoch": 5.57, + "learning_rate": 1.69275764690876e-05, + "loss": 0.2029, + "step": 18049 + }, + { + "epoch": 5.57, + "learning_rate": 1.692721578993029e-05, + "loss": 0.1816, + "step": 18050 + }, + { + "epoch": 5.57, + "learning_rate": 1.6926855093446747e-05, + "loss": 0.2053, + "step": 18051 + }, + { + "epoch": 5.57, + "learning_rate": 1.6926494379637878e-05, + "loss": 0.191, + "step": 18052 + }, + { + "epoch": 5.58, + "learning_rate": 1.6926133648504587e-05, + "loss": 0.1827, + "step": 18053 + }, + { + "epoch": 5.58, + "learning_rate": 1.6925772900047767e-05, + "loss": 0.1887, + "step": 18054 + }, + { + "epoch": 5.58, + "learning_rate": 1.692541213426833e-05, + "loss": 0.1727, + "step": 18055 + }, + { + "epoch": 5.58, + "learning_rate": 1.6925051351167172e-05, + "loss": 0.1722, + "step": 18056 + }, + { + "epoch": 5.58, + "learning_rate": 1.6924690550745196e-05, + "loss": 0.189, + "step": 18057 + }, + { + "epoch": 5.58, + "learning_rate": 1.6924329733003308e-05, + "loss": 0.172, + "step": 18058 + }, + { + "epoch": 5.58, + "learning_rate": 1.692396889794241e-05, + "loss": 0.1929, + "step": 18059 + }, + { + "epoch": 5.58, + "learning_rate": 1.69236080455634e-05, + "loss": 0.1748, + "step": 18060 + }, + { + "epoch": 5.58, + "learning_rate": 1.6923247175867187e-05, + "loss": 0.1809, + "step": 18061 + }, + { + "epoch": 5.58, + "learning_rate": 1.6922886288854666e-05, + "loss": 0.1673, + "step": 18062 + }, + { + "epoch": 5.58, + "learning_rate": 1.6922525384526745e-05, + "loss": 0.1922, + "step": 18063 + }, + { + "epoch": 5.58, + "learning_rate": 1.6922164462884326e-05, + "loss": 0.1794, + "step": 18064 + }, + { + "epoch": 5.58, + "learning_rate": 1.6921803523928312e-05, + "loss": 0.1844, + "step": 18065 + }, + { + "epoch": 5.58, + "learning_rate": 1.6921442567659603e-05, + "loss": 0.1914, + "step": 18066 + }, + { + "epoch": 5.58, + "learning_rate": 1.6921081594079105e-05, + "loss": 0.1887, + "step": 18067 + }, + { + "epoch": 5.58, + "learning_rate": 1.692072060318772e-05, + "loss": 0.2027, + "step": 18068 + }, + { + "epoch": 5.58, + "learning_rate": 1.6920359594986347e-05, + "loss": 0.1815, + "step": 18069 + }, + { + "epoch": 5.58, + "learning_rate": 1.69199985694759e-05, + "loss": 0.1859, + "step": 18070 + }, + { + "epoch": 5.58, + "learning_rate": 1.6919637526657268e-05, + "loss": 0.2071, + "step": 18071 + }, + { + "epoch": 5.58, + "learning_rate": 1.691927646653136e-05, + "loss": 0.1875, + "step": 18072 + }, + { + "epoch": 5.58, + "learning_rate": 1.691891538909908e-05, + "loss": 0.1845, + "step": 18073 + }, + { + "epoch": 5.58, + "learning_rate": 1.6918554294361332e-05, + "loss": 0.1702, + "step": 18074 + }, + { + "epoch": 5.58, + "learning_rate": 1.691819318231902e-05, + "loss": 0.2009, + "step": 18075 + }, + { + "epoch": 5.58, + "learning_rate": 1.691783205297304e-05, + "loss": 0.1877, + "step": 18076 + }, + { + "epoch": 5.58, + "learning_rate": 1.6917470906324308e-05, + "loss": 0.1796, + "step": 18077 + }, + { + "epoch": 5.58, + "learning_rate": 1.6917109742373715e-05, + "loss": 0.1785, + "step": 18078 + }, + { + "epoch": 5.58, + "learning_rate": 1.6916748561122168e-05, + "loss": 0.1718, + "step": 18079 + }, + { + "epoch": 5.58, + "learning_rate": 1.6916387362570573e-05, + "loss": 0.1753, + "step": 18080 + }, + { + "epoch": 5.58, + "learning_rate": 1.691602614671983e-05, + "loss": 0.1899, + "step": 18081 + }, + { + "epoch": 5.58, + "learning_rate": 1.6915664913570844e-05, + "loss": 0.19, + "step": 18082 + }, + { + "epoch": 5.58, + "learning_rate": 1.6915303663124522e-05, + "loss": 0.1731, + "step": 18083 + }, + { + "epoch": 5.58, + "learning_rate": 1.6914942395381764e-05, + "loss": 0.1759, + "step": 18084 + }, + { + "epoch": 5.59, + "learning_rate": 1.691458111034347e-05, + "loss": 0.1767, + "step": 18085 + }, + { + "epoch": 5.59, + "learning_rate": 1.691421980801055e-05, + "loss": 0.1665, + "step": 18086 + }, + { + "epoch": 5.59, + "learning_rate": 1.6913858488383906e-05, + "loss": 0.1783, + "step": 18087 + }, + { + "epoch": 5.59, + "learning_rate": 1.6913497151464438e-05, + "loss": 0.1771, + "step": 18088 + }, + { + "epoch": 5.59, + "learning_rate": 1.6913135797253056e-05, + "loss": 0.1804, + "step": 18089 + }, + { + "epoch": 5.59, + "learning_rate": 1.691277442575066e-05, + "loss": 0.1937, + "step": 18090 + }, + { + "epoch": 5.59, + "learning_rate": 1.691241303695815e-05, + "loss": 0.1879, + "step": 18091 + }, + { + "epoch": 5.59, + "learning_rate": 1.691205163087644e-05, + "loss": 0.1927, + "step": 18092 + }, + { + "epoch": 5.59, + "learning_rate": 1.6911690207506425e-05, + "loss": 0.1813, + "step": 18093 + }, + { + "epoch": 5.59, + "learning_rate": 1.6911328766849012e-05, + "loss": 0.1889, + "step": 18094 + }, + { + "epoch": 5.59, + "learning_rate": 1.6910967308905107e-05, + "loss": 0.196, + "step": 18095 + }, + { + "epoch": 5.59, + "learning_rate": 1.6910605833675614e-05, + "loss": 0.1797, + "step": 18096 + }, + { + "epoch": 5.59, + "learning_rate": 1.6910244341161432e-05, + "loss": 0.178, + "step": 18097 + }, + { + "epoch": 5.59, + "learning_rate": 1.6909882831363468e-05, + "loss": 0.1843, + "step": 18098 + }, + { + "epoch": 5.59, + "learning_rate": 1.690952130428263e-05, + "loss": 0.194, + "step": 18099 + }, + { + "epoch": 5.59, + "learning_rate": 1.6909159759919815e-05, + "loss": 0.1894, + "step": 18100 + }, + { + "epoch": 5.59, + "learning_rate": 1.6908798198275933e-05, + "loss": 0.1807, + "step": 18101 + }, + { + "epoch": 5.59, + "learning_rate": 1.6908436619351888e-05, + "loss": 0.1808, + "step": 18102 + }, + { + "epoch": 5.59, + "learning_rate": 1.6908075023148584e-05, + "loss": 0.1934, + "step": 18103 + }, + { + "epoch": 5.59, + "learning_rate": 1.6907713409666922e-05, + "loss": 0.1856, + "step": 18104 + }, + { + "epoch": 5.59, + "learning_rate": 1.6907351778907804e-05, + "loss": 0.1714, + "step": 18105 + }, + { + "epoch": 5.59, + "learning_rate": 1.690699013087215e-05, + "loss": 0.1883, + "step": 18106 + }, + { + "epoch": 5.59, + "learning_rate": 1.6906628465560846e-05, + "loss": 0.1944, + "step": 18107 + }, + { + "epoch": 5.59, + "learning_rate": 1.6906266782974808e-05, + "loss": 0.197, + "step": 18108 + }, + { + "epoch": 5.59, + "learning_rate": 1.6905905083114936e-05, + "loss": 0.1774, + "step": 18109 + }, + { + "epoch": 5.59, + "learning_rate": 1.6905543365982137e-05, + "loss": 0.1807, + "step": 18110 + }, + { + "epoch": 5.59, + "learning_rate": 1.6905181631577313e-05, + "loss": 0.1671, + "step": 18111 + }, + { + "epoch": 5.59, + "learning_rate": 1.690481987990137e-05, + "loss": 0.1762, + "step": 18112 + }, + { + "epoch": 5.59, + "learning_rate": 1.6904458110955216e-05, + "loss": 0.1911, + "step": 18113 + }, + { + "epoch": 5.59, + "learning_rate": 1.690409632473975e-05, + "loss": 0.1898, + "step": 18114 + }, + { + "epoch": 5.59, + "learning_rate": 1.690373452125588e-05, + "loss": 0.1854, + "step": 18115 + }, + { + "epoch": 5.59, + "learning_rate": 1.6903372700504513e-05, + "loss": 0.1722, + "step": 18116 + }, + { + "epoch": 5.59, + "learning_rate": 1.690301086248655e-05, + "loss": 0.1834, + "step": 18117 + }, + { + "epoch": 5.6, + "learning_rate": 1.6902649007202898e-05, + "loss": 0.1836, + "step": 18118 + }, + { + "epoch": 5.6, + "learning_rate": 1.690228713465446e-05, + "loss": 0.2025, + "step": 18119 + }, + { + "epoch": 5.6, + "learning_rate": 1.6901925244842148e-05, + "loss": 0.1811, + "step": 18120 + }, + { + "epoch": 5.6, + "learning_rate": 1.690156333776686e-05, + "loss": 0.2068, + "step": 18121 + }, + { + "epoch": 5.6, + "learning_rate": 1.6901201413429503e-05, + "loss": 0.1877, + "step": 18122 + }, + { + "epoch": 5.6, + "learning_rate": 1.690083947183098e-05, + "loss": 0.1921, + "step": 18123 + }, + { + "epoch": 5.6, + "learning_rate": 1.69004775129722e-05, + "loss": 0.1849, + "step": 18124 + }, + { + "epoch": 5.6, + "learning_rate": 1.6900115536854068e-05, + "loss": 0.1875, + "step": 18125 + }, + { + "epoch": 5.6, + "learning_rate": 1.689975354347749e-05, + "loss": 0.1736, + "step": 18126 + }, + { + "epoch": 5.6, + "learning_rate": 1.689939153284337e-05, + "loss": 0.2015, + "step": 18127 + }, + { + "epoch": 5.6, + "learning_rate": 1.689902950495261e-05, + "loss": 0.1935, + "step": 18128 + }, + { + "epoch": 5.6, + "learning_rate": 1.6898667459806124e-05, + "loss": 0.1741, + "step": 18129 + }, + { + "epoch": 5.6, + "learning_rate": 1.6898305397404807e-05, + "loss": 0.1808, + "step": 18130 + }, + { + "epoch": 5.6, + "learning_rate": 1.689794331774957e-05, + "loss": 0.1841, + "step": 18131 + }, + { + "epoch": 5.6, + "learning_rate": 1.6897581220841327e-05, + "loss": 0.1719, + "step": 18132 + }, + { + "epoch": 5.6, + "learning_rate": 1.6897219106680967e-05, + "loss": 0.2013, + "step": 18133 + }, + { + "epoch": 5.6, + "learning_rate": 1.6896856975269406e-05, + "loss": 0.1703, + "step": 18134 + }, + { + "epoch": 5.6, + "learning_rate": 1.6896494826607548e-05, + "loss": 0.1746, + "step": 18135 + }, + { + "epoch": 5.6, + "learning_rate": 1.6896132660696297e-05, + "loss": 0.1797, + "step": 18136 + }, + { + "epoch": 5.6, + "learning_rate": 1.6895770477536565e-05, + "loss": 0.1775, + "step": 18137 + }, + { + "epoch": 5.6, + "learning_rate": 1.689540827712925e-05, + "loss": 0.1745, + "step": 18138 + }, + { + "epoch": 5.6, + "learning_rate": 1.689504605947526e-05, + "loss": 0.1949, + "step": 18139 + }, + { + "epoch": 5.6, + "learning_rate": 1.6894683824575505e-05, + "loss": 0.1895, + "step": 18140 + }, + { + "epoch": 5.6, + "learning_rate": 1.689432157243089e-05, + "loss": 0.1863, + "step": 18141 + }, + { + "epoch": 5.6, + "learning_rate": 1.6893959303042316e-05, + "loss": 0.1799, + "step": 18142 + }, + { + "epoch": 5.6, + "learning_rate": 1.6893597016410693e-05, + "loss": 0.1879, + "step": 18143 + }, + { + "epoch": 5.6, + "learning_rate": 1.6893234712536925e-05, + "loss": 0.186, + "step": 18144 + }, + { + "epoch": 5.6, + "learning_rate": 1.6892872391421923e-05, + "loss": 0.1813, + "step": 18145 + }, + { + "epoch": 5.6, + "learning_rate": 1.689251005306659e-05, + "loss": 0.1957, + "step": 18146 + }, + { + "epoch": 5.6, + "learning_rate": 1.6892147697471827e-05, + "loss": 0.1889, + "step": 18147 + }, + { + "epoch": 5.6, + "learning_rate": 1.689178532463855e-05, + "loss": 0.1888, + "step": 18148 + }, + { + "epoch": 5.6, + "learning_rate": 1.6891422934567662e-05, + "loss": 0.1934, + "step": 18149 + }, + { + "epoch": 5.61, + "learning_rate": 1.6891060527260065e-05, + "loss": 0.201, + "step": 18150 + }, + { + "epoch": 5.61, + "learning_rate": 1.689069810271667e-05, + "loss": 0.1883, + "step": 18151 + }, + { + "epoch": 5.61, + "learning_rate": 1.6890335660938385e-05, + "loss": 0.1846, + "step": 18152 + }, + { + "epoch": 5.61, + "learning_rate": 1.6889973201926107e-05, + "loss": 0.1758, + "step": 18153 + }, + { + "epoch": 5.61, + "learning_rate": 1.6889610725680755e-05, + "loss": 0.1829, + "step": 18154 + }, + { + "epoch": 5.61, + "learning_rate": 1.688924823220323e-05, + "loss": 0.1762, + "step": 18155 + }, + { + "epoch": 5.61, + "learning_rate": 1.6888885721494434e-05, + "loss": 0.1692, + "step": 18156 + }, + { + "epoch": 5.61, + "learning_rate": 1.6888523193555284e-05, + "loss": 0.195, + "step": 18157 + }, + { + "epoch": 5.61, + "learning_rate": 1.688816064838668e-05, + "loss": 0.1865, + "step": 18158 + }, + { + "epoch": 5.61, + "learning_rate": 1.6887798085989527e-05, + "loss": 0.184, + "step": 18159 + }, + { + "epoch": 5.61, + "learning_rate": 1.6887435506364735e-05, + "loss": 0.1939, + "step": 18160 + }, + { + "epoch": 5.61, + "learning_rate": 1.6887072909513214e-05, + "loss": 0.1705, + "step": 18161 + }, + { + "epoch": 5.61, + "learning_rate": 1.6886710295435866e-05, + "loss": 0.1784, + "step": 18162 + }, + { + "epoch": 5.61, + "learning_rate": 1.6886347664133597e-05, + "loss": 0.2058, + "step": 18163 + }, + { + "epoch": 5.61, + "learning_rate": 1.6885985015607317e-05, + "loss": 0.2166, + "step": 18164 + }, + { + "epoch": 5.61, + "learning_rate": 1.6885622349857936e-05, + "loss": 0.169, + "step": 18165 + }, + { + "epoch": 5.61, + "learning_rate": 1.6885259666886356e-05, + "loss": 0.2038, + "step": 18166 + }, + { + "epoch": 5.61, + "learning_rate": 1.6884896966693485e-05, + "loss": 0.1939, + "step": 18167 + }, + { + "epoch": 5.61, + "learning_rate": 1.688453424928023e-05, + "loss": 0.1688, + "step": 18168 + }, + { + "epoch": 5.61, + "learning_rate": 1.68841715146475e-05, + "loss": 0.1916, + "step": 18169 + }, + { + "epoch": 5.61, + "learning_rate": 1.6883808762796203e-05, + "loss": 0.1686, + "step": 18170 + }, + { + "epoch": 5.61, + "learning_rate": 1.6883445993727244e-05, + "loss": 0.2076, + "step": 18171 + }, + { + "epoch": 5.61, + "learning_rate": 1.688308320744153e-05, + "loss": 0.1835, + "step": 18172 + }, + { + "epoch": 5.61, + "learning_rate": 1.688272040393997e-05, + "loss": 0.1939, + "step": 18173 + }, + { + "epoch": 5.61, + "learning_rate": 1.6882357583223474e-05, + "loss": 0.1853, + "step": 18174 + }, + { + "epoch": 5.61, + "learning_rate": 1.6881994745292942e-05, + "loss": 0.1709, + "step": 18175 + }, + { + "epoch": 5.61, + "learning_rate": 1.688163189014929e-05, + "loss": 0.1801, + "step": 18176 + }, + { + "epoch": 5.61, + "learning_rate": 1.6881269017793417e-05, + "loss": 0.1731, + "step": 18177 + }, + { + "epoch": 5.61, + "learning_rate": 1.688090612822624e-05, + "loss": 0.1869, + "step": 18178 + }, + { + "epoch": 5.61, + "learning_rate": 1.6880543221448656e-05, + "loss": 0.1796, + "step": 18179 + }, + { + "epoch": 5.61, + "learning_rate": 1.6880180297461583e-05, + "loss": 0.1635, + "step": 18180 + }, + { + "epoch": 5.61, + "learning_rate": 1.687981735626592e-05, + "loss": 0.1773, + "step": 18181 + }, + { + "epoch": 5.62, + "learning_rate": 1.6879454397862584e-05, + "loss": 0.1777, + "step": 18182 + }, + { + "epoch": 5.62, + "learning_rate": 1.6879091422252475e-05, + "loss": 0.1823, + "step": 18183 + }, + { + "epoch": 5.62, + "learning_rate": 1.6878728429436504e-05, + "loss": 0.1992, + "step": 18184 + }, + { + "epoch": 5.62, + "learning_rate": 1.687836541941558e-05, + "loss": 0.1888, + "step": 18185 + }, + { + "epoch": 5.62, + "learning_rate": 1.687800239219061e-05, + "loss": 0.1867, + "step": 18186 + }, + { + "epoch": 5.62, + "learning_rate": 1.6877639347762498e-05, + "loss": 0.1796, + "step": 18187 + }, + { + "epoch": 5.62, + "learning_rate": 1.6877276286132157e-05, + "loss": 0.1861, + "step": 18188 + }, + { + "epoch": 5.62, + "learning_rate": 1.6876913207300495e-05, + "loss": 0.191, + "step": 18189 + }, + { + "epoch": 5.62, + "learning_rate": 1.6876550111268417e-05, + "loss": 0.1902, + "step": 18190 + }, + { + "epoch": 5.62, + "learning_rate": 1.6876186998036836e-05, + "loss": 0.1834, + "step": 18191 + }, + { + "epoch": 5.62, + "learning_rate": 1.6875823867606654e-05, + "loss": 0.1782, + "step": 18192 + }, + { + "epoch": 5.62, + "learning_rate": 1.6875460719978783e-05, + "loss": 0.2007, + "step": 18193 + }, + { + "epoch": 5.62, + "learning_rate": 1.687509755515413e-05, + "loss": 0.1898, + "step": 18194 + }, + { + "epoch": 5.62, + "learning_rate": 1.6874734373133605e-05, + "loss": 0.1872, + "step": 18195 + }, + { + "epoch": 5.62, + "learning_rate": 1.6874371173918117e-05, + "loss": 0.1855, + "step": 18196 + }, + { + "epoch": 5.62, + "learning_rate": 1.6874007957508572e-05, + "loss": 0.1716, + "step": 18197 + }, + { + "epoch": 5.62, + "learning_rate": 1.6873644723905877e-05, + "loss": 0.1836, + "step": 18198 + }, + { + "epoch": 5.62, + "learning_rate": 1.6873281473110945e-05, + "loss": 0.1826, + "step": 18199 + }, + { + "epoch": 5.62, + "learning_rate": 1.6872918205124683e-05, + "loss": 0.1802, + "step": 18200 + }, + { + "epoch": 5.62, + "learning_rate": 1.6872554919948e-05, + "loss": 0.1791, + "step": 18201 + }, + { + "epoch": 5.62, + "learning_rate": 1.68721916175818e-05, + "loss": 0.1792, + "step": 18202 + }, + { + "epoch": 5.62, + "learning_rate": 1.6871828298027e-05, + "loss": 0.1797, + "step": 18203 + }, + { + "epoch": 5.62, + "learning_rate": 1.68714649612845e-05, + "loss": 0.1884, + "step": 18204 + }, + { + "epoch": 5.62, + "learning_rate": 1.6871101607355215e-05, + "loss": 0.2015, + "step": 18205 + }, + { + "epoch": 5.62, + "learning_rate": 1.6870738236240052e-05, + "loss": 0.1778, + "step": 18206 + }, + { + "epoch": 5.62, + "learning_rate": 1.687037484793992e-05, + "loss": 0.1841, + "step": 18207 + }, + { + "epoch": 5.62, + "learning_rate": 1.6870011442455723e-05, + "loss": 0.1869, + "step": 18208 + }, + { + "epoch": 5.62, + "learning_rate": 1.6869648019788377e-05, + "loss": 0.1882, + "step": 18209 + }, + { + "epoch": 5.62, + "learning_rate": 1.686928457993879e-05, + "loss": 0.1887, + "step": 18210 + }, + { + "epoch": 5.62, + "learning_rate": 1.686892112290787e-05, + "loss": 0.2062, + "step": 18211 + }, + { + "epoch": 5.62, + "learning_rate": 1.6868557648696522e-05, + "loss": 0.1864, + "step": 18212 + }, + { + "epoch": 5.62, + "learning_rate": 1.686819415730566e-05, + "loss": 0.182, + "step": 18213 + }, + { + "epoch": 5.62, + "learning_rate": 1.6867830648736192e-05, + "loss": 0.1881, + "step": 18214 + }, + { + "epoch": 5.63, + "learning_rate": 1.6867467122989025e-05, + "loss": 0.1781, + "step": 18215 + }, + { + "epoch": 5.63, + "learning_rate": 1.6867103580065074e-05, + "loss": 0.1906, + "step": 18216 + }, + { + "epoch": 5.63, + "learning_rate": 1.6866740019965243e-05, + "loss": 0.1919, + "step": 18217 + }, + { + "epoch": 5.63, + "learning_rate": 1.686637644269044e-05, + "loss": 0.1783, + "step": 18218 + }, + { + "epoch": 5.63, + "learning_rate": 1.686601284824158e-05, + "loss": 0.1915, + "step": 18219 + }, + { + "epoch": 5.63, + "learning_rate": 1.686564923661957e-05, + "loss": 0.1779, + "step": 18220 + }, + { + "epoch": 5.63, + "learning_rate": 1.686528560782532e-05, + "loss": 0.1827, + "step": 18221 + }, + { + "epoch": 5.63, + "learning_rate": 1.686492196185973e-05, + "loss": 0.1825, + "step": 18222 + }, + { + "epoch": 5.63, + "learning_rate": 1.686455829872373e-05, + "loss": 0.1922, + "step": 18223 + }, + { + "epoch": 5.63, + "learning_rate": 1.686419461841821e-05, + "loss": 0.1723, + "step": 18224 + }, + { + "epoch": 5.63, + "learning_rate": 1.6863830920944088e-05, + "loss": 0.195, + "step": 18225 + }, + { + "epoch": 5.63, + "learning_rate": 1.686346720630228e-05, + "loss": 0.2014, + "step": 18226 + }, + { + "epoch": 5.63, + "learning_rate": 1.6863103474493677e-05, + "loss": 0.1861, + "step": 18227 + }, + { + "epoch": 5.63, + "learning_rate": 1.686273972551921e-05, + "loss": 0.169, + "step": 18228 + }, + { + "epoch": 5.63, + "learning_rate": 1.6862375959379777e-05, + "loss": 0.1779, + "step": 18229 + }, + { + "epoch": 5.63, + "learning_rate": 1.6862012176076288e-05, + "loss": 0.1783, + "step": 18230 + }, + { + "epoch": 5.63, + "learning_rate": 1.6861648375609658e-05, + "loss": 0.2034, + "step": 18231 + }, + { + "epoch": 5.63, + "learning_rate": 1.686128455798079e-05, + "loss": 0.202, + "step": 18232 + }, + { + "epoch": 5.63, + "learning_rate": 1.6860920723190602e-05, + "loss": 0.2006, + "step": 18233 + }, + { + "epoch": 5.63, + "learning_rate": 1.6860556871239996e-05, + "loss": 0.1871, + "step": 18234 + }, + { + "epoch": 5.63, + "learning_rate": 1.6860193002129887e-05, + "loss": 0.1845, + "step": 18235 + }, + { + "epoch": 5.63, + "learning_rate": 1.6859829115861185e-05, + "loss": 0.2003, + "step": 18236 + }, + { + "epoch": 5.63, + "learning_rate": 1.68594652124348e-05, + "loss": 0.1908, + "step": 18237 + }, + { + "epoch": 5.63, + "learning_rate": 1.685910129185164e-05, + "loss": 0.1873, + "step": 18238 + }, + { + "epoch": 5.63, + "learning_rate": 1.6858737354112616e-05, + "loss": 0.1861, + "step": 18239 + }, + { + "epoch": 5.63, + "learning_rate": 1.6858373399218643e-05, + "loss": 0.1867, + "step": 18240 + }, + { + "epoch": 5.63, + "learning_rate": 1.6858009427170623e-05, + "loss": 0.1807, + "step": 18241 + }, + { + "epoch": 5.63, + "learning_rate": 1.6857645437969474e-05, + "loss": 0.1897, + "step": 18242 + }, + { + "epoch": 5.63, + "learning_rate": 1.68572814316161e-05, + "loss": 0.1804, + "step": 18243 + }, + { + "epoch": 5.63, + "learning_rate": 1.6856917408111415e-05, + "loss": 0.1893, + "step": 18244 + }, + { + "epoch": 5.63, + "learning_rate": 1.685655336745633e-05, + "loss": 0.1732, + "step": 18245 + }, + { + "epoch": 5.63, + "learning_rate": 1.6856189309651752e-05, + "loss": 0.1823, + "step": 18246 + }, + { + "epoch": 5.64, + "learning_rate": 1.6855825234698597e-05, + "loss": 0.1845, + "step": 18247 + }, + { + "epoch": 5.64, + "learning_rate": 1.6855461142597775e-05, + "loss": 0.169, + "step": 18248 + }, + { + "epoch": 5.64, + "learning_rate": 1.6855097033350187e-05, + "loss": 0.1815, + "step": 18249 + }, + { + "epoch": 5.64, + "learning_rate": 1.6854732906956758e-05, + "loss": 0.1832, + "step": 18250 + }, + { + "epoch": 5.64, + "learning_rate": 1.6854368763418386e-05, + "loss": 0.1838, + "step": 18251 + }, + { + "epoch": 5.64, + "learning_rate": 1.685400460273599e-05, + "loss": 0.1789, + "step": 18252 + }, + { + "epoch": 5.64, + "learning_rate": 1.685364042491048e-05, + "loss": 0.1878, + "step": 18253 + }, + { + "epoch": 5.64, + "learning_rate": 1.6853276229942765e-05, + "loss": 0.1658, + "step": 18254 + }, + { + "epoch": 5.64, + "learning_rate": 1.6852912017833752e-05, + "loss": 0.1915, + "step": 18255 + }, + { + "epoch": 5.64, + "learning_rate": 1.685254778858436e-05, + "loss": 0.1878, + "step": 18256 + }, + { + "epoch": 5.64, + "learning_rate": 1.6852183542195498e-05, + "loss": 0.1898, + "step": 18257 + }, + { + "epoch": 5.64, + "learning_rate": 1.6851819278668072e-05, + "loss": 0.1867, + "step": 18258 + }, + { + "epoch": 5.64, + "learning_rate": 1.6851454998002998e-05, + "loss": 0.1841, + "step": 18259 + }, + { + "epoch": 5.64, + "learning_rate": 1.6851090700201183e-05, + "loss": 0.174, + "step": 18260 + }, + { + "epoch": 5.64, + "learning_rate": 1.685072638526354e-05, + "loss": 0.1976, + "step": 18261 + }, + { + "epoch": 5.64, + "learning_rate": 1.6850362053190986e-05, + "loss": 0.1908, + "step": 18262 + }, + { + "epoch": 5.64, + "learning_rate": 1.684999770398442e-05, + "loss": 0.1782, + "step": 18263 + }, + { + "epoch": 5.64, + "learning_rate": 1.6849633337644764e-05, + "loss": 0.2096, + "step": 18264 + }, + { + "epoch": 5.64, + "learning_rate": 1.684926895417293e-05, + "loss": 0.1786, + "step": 18265 + }, + { + "epoch": 5.64, + "learning_rate": 1.684890455356982e-05, + "loss": 0.1674, + "step": 18266 + }, + { + "epoch": 5.64, + "learning_rate": 1.684854013583635e-05, + "loss": 0.1935, + "step": 18267 + }, + { + "epoch": 5.64, + "learning_rate": 1.6848175700973436e-05, + "loss": 0.1988, + "step": 18268 + }, + { + "epoch": 5.64, + "learning_rate": 1.6847811248981982e-05, + "loss": 0.1733, + "step": 18269 + }, + { + "epoch": 5.64, + "learning_rate": 1.6847446779862902e-05, + "loss": 0.2, + "step": 18270 + }, + { + "epoch": 5.64, + "learning_rate": 1.684708229361711e-05, + "loss": 0.1815, + "step": 18271 + }, + { + "epoch": 5.64, + "learning_rate": 1.684671779024552e-05, + "loss": 0.1827, + "step": 18272 + }, + { + "epoch": 5.64, + "learning_rate": 1.684635326974904e-05, + "loss": 0.2122, + "step": 18273 + }, + { + "epoch": 5.64, + "learning_rate": 1.6845988732128576e-05, + "loss": 0.1832, + "step": 18274 + }, + { + "epoch": 5.64, + "learning_rate": 1.684562417738505e-05, + "loss": 0.1744, + "step": 18275 + }, + { + "epoch": 5.64, + "learning_rate": 1.6845259605519365e-05, + "loss": 0.1898, + "step": 18276 + }, + { + "epoch": 5.64, + "learning_rate": 1.684489501653244e-05, + "loss": 0.1745, + "step": 18277 + }, + { + "epoch": 5.64, + "learning_rate": 1.6844530410425186e-05, + "loss": 0.1744, + "step": 18278 + }, + { + "epoch": 5.64, + "learning_rate": 1.684416578719851e-05, + "loss": 0.1859, + "step": 18279 + }, + { + "epoch": 5.65, + "learning_rate": 1.684380114685333e-05, + "loss": 0.1838, + "step": 18280 + }, + { + "epoch": 5.65, + "learning_rate": 1.6843436489390555e-05, + "loss": 0.1676, + "step": 18281 + }, + { + "epoch": 5.65, + "learning_rate": 1.6843071814811098e-05, + "loss": 0.1767, + "step": 18282 + }, + { + "epoch": 5.65, + "learning_rate": 1.6842707123115866e-05, + "loss": 0.1807, + "step": 18283 + }, + { + "epoch": 5.65, + "learning_rate": 1.6842342414305778e-05, + "loss": 0.1707, + "step": 18284 + }, + { + "epoch": 5.65, + "learning_rate": 1.6841977688381744e-05, + "loss": 0.1942, + "step": 18285 + }, + { + "epoch": 5.65, + "learning_rate": 1.684161294534467e-05, + "loss": 0.1608, + "step": 18286 + }, + { + "epoch": 5.65, + "learning_rate": 1.6841248185195485e-05, + "loss": 0.2061, + "step": 18287 + }, + { + "epoch": 5.65, + "learning_rate": 1.6840883407935082e-05, + "loss": 0.1713, + "step": 18288 + }, + { + "epoch": 5.65, + "learning_rate": 1.6840518613564384e-05, + "loss": 0.1867, + "step": 18289 + }, + { + "epoch": 5.65, + "learning_rate": 1.6840153802084304e-05, + "loss": 0.1808, + "step": 18290 + }, + { + "epoch": 5.65, + "learning_rate": 1.683978897349575e-05, + "loss": 0.1901, + "step": 18291 + }, + { + "epoch": 5.65, + "learning_rate": 1.6839424127799636e-05, + "loss": 0.1727, + "step": 18292 + }, + { + "epoch": 5.65, + "learning_rate": 1.6839059264996874e-05, + "loss": 0.175, + "step": 18293 + }, + { + "epoch": 5.65, + "learning_rate": 1.683869438508838e-05, + "loss": 0.1787, + "step": 18294 + }, + { + "epoch": 5.65, + "learning_rate": 1.6838329488075062e-05, + "loss": 0.1681, + "step": 18295 + }, + { + "epoch": 5.65, + "learning_rate": 1.6837964573957835e-05, + "loss": 0.1889, + "step": 18296 + }, + { + "epoch": 5.65, + "learning_rate": 1.6837599642737613e-05, + "loss": 0.1841, + "step": 18297 + }, + { + "epoch": 5.65, + "learning_rate": 1.6837234694415305e-05, + "loss": 0.1867, + "step": 18298 + }, + { + "epoch": 5.65, + "learning_rate": 1.6836869728991825e-05, + "loss": 0.1746, + "step": 18299 + }, + { + "epoch": 5.65, + "learning_rate": 1.6836504746468088e-05, + "loss": 0.1863, + "step": 18300 + }, + { + "epoch": 5.65, + "learning_rate": 1.6836139746845006e-05, + "loss": 0.1876, + "step": 18301 + }, + { + "epoch": 5.65, + "learning_rate": 1.6835774730123493e-05, + "loss": 0.1892, + "step": 18302 + }, + { + "epoch": 5.65, + "learning_rate": 1.683540969630446e-05, + "loss": 0.174, + "step": 18303 + }, + { + "epoch": 5.65, + "learning_rate": 1.683504464538882e-05, + "loss": 0.1957, + "step": 18304 + }, + { + "epoch": 5.65, + "learning_rate": 1.6834679577377487e-05, + "loss": 0.2011, + "step": 18305 + }, + { + "epoch": 5.65, + "learning_rate": 1.6834314492271375e-05, + "loss": 0.1745, + "step": 18306 + }, + { + "epoch": 5.65, + "learning_rate": 1.6833949390071394e-05, + "loss": 0.1856, + "step": 18307 + }, + { + "epoch": 5.65, + "learning_rate": 1.683358427077846e-05, + "loss": 0.1768, + "step": 18308 + }, + { + "epoch": 5.65, + "learning_rate": 1.6833219134393485e-05, + "loss": 0.1932, + "step": 18309 + }, + { + "epoch": 5.65, + "learning_rate": 1.683285398091738e-05, + "loss": 0.1937, + "step": 18310 + }, + { + "epoch": 5.65, + "learning_rate": 1.6832488810351066e-05, + "loss": 0.2059, + "step": 18311 + }, + { + "epoch": 5.66, + "learning_rate": 1.683212362269545e-05, + "loss": 0.2003, + "step": 18312 + }, + { + "epoch": 5.66, + "learning_rate": 1.6831758417951446e-05, + "loss": 0.1979, + "step": 18313 + }, + { + "epoch": 5.66, + "learning_rate": 1.6831393196119966e-05, + "loss": 0.1915, + "step": 18314 + }, + { + "epoch": 5.66, + "learning_rate": 1.6831027957201928e-05, + "loss": 0.1992, + "step": 18315 + }, + { + "epoch": 5.66, + "learning_rate": 1.6830662701198245e-05, + "loss": 0.1891, + "step": 18316 + }, + { + "epoch": 5.66, + "learning_rate": 1.6830297428109824e-05, + "loss": 0.1763, + "step": 18317 + }, + { + "epoch": 5.66, + "learning_rate": 1.6829932137937588e-05, + "loss": 0.1741, + "step": 18318 + }, + { + "epoch": 5.66, + "learning_rate": 1.6829566830682446e-05, + "loss": 0.1869, + "step": 18319 + }, + { + "epoch": 5.66, + "learning_rate": 1.682920150634531e-05, + "loss": 0.1871, + "step": 18320 + }, + { + "epoch": 5.66, + "learning_rate": 1.6828836164927095e-05, + "loss": 0.1791, + "step": 18321 + }, + { + "epoch": 5.66, + "learning_rate": 1.6828470806428713e-05, + "loss": 0.2023, + "step": 18322 + }, + { + "epoch": 5.66, + "learning_rate": 1.6828105430851084e-05, + "loss": 0.1809, + "step": 18323 + }, + { + "epoch": 5.66, + "learning_rate": 1.682774003819512e-05, + "loss": 0.1956, + "step": 18324 + }, + { + "epoch": 5.66, + "learning_rate": 1.6827374628461726e-05, + "loss": 0.1923, + "step": 18325 + }, + { + "epoch": 5.66, + "learning_rate": 1.6827009201651824e-05, + "loss": 0.1972, + "step": 18326 + }, + { + "epoch": 5.66, + "learning_rate": 1.682664375776633e-05, + "loss": 0.1794, + "step": 18327 + }, + { + "epoch": 5.66, + "learning_rate": 1.6826278296806154e-05, + "loss": 0.1871, + "step": 18328 + }, + { + "epoch": 5.66, + "learning_rate": 1.682591281877221e-05, + "loss": 0.175, + "step": 18329 + }, + { + "epoch": 5.66, + "learning_rate": 1.6825547323665413e-05, + "loss": 0.1736, + "step": 18330 + }, + { + "epoch": 5.66, + "learning_rate": 1.682518181148668e-05, + "loss": 0.1787, + "step": 18331 + }, + { + "epoch": 5.66, + "learning_rate": 1.682481628223692e-05, + "loss": 0.1835, + "step": 18332 + }, + { + "epoch": 5.66, + "learning_rate": 1.682445073591705e-05, + "loss": 0.1915, + "step": 18333 + }, + { + "epoch": 5.66, + "learning_rate": 1.6824085172527983e-05, + "loss": 0.1817, + "step": 18334 + }, + { + "epoch": 5.66, + "learning_rate": 1.6823719592070634e-05, + "loss": 0.198, + "step": 18335 + }, + { + "epoch": 5.66, + "learning_rate": 1.6823353994545924e-05, + "loss": 0.1936, + "step": 18336 + }, + { + "epoch": 5.66, + "learning_rate": 1.6822988379954754e-05, + "loss": 0.184, + "step": 18337 + }, + { + "epoch": 5.66, + "learning_rate": 1.682262274829805e-05, + "loss": 0.1788, + "step": 18338 + }, + { + "epoch": 5.66, + "learning_rate": 1.682225709957672e-05, + "loss": 0.1835, + "step": 18339 + }, + { + "epoch": 5.66, + "learning_rate": 1.682189143379168e-05, + "loss": 0.187, + "step": 18340 + }, + { + "epoch": 5.66, + "learning_rate": 1.6821525750943846e-05, + "loss": 0.1849, + "step": 18341 + }, + { + "epoch": 5.66, + "learning_rate": 1.682116005103413e-05, + "loss": 0.2016, + "step": 18342 + }, + { + "epoch": 5.66, + "learning_rate": 1.6820794334063452e-05, + "loss": 0.1755, + "step": 18343 + }, + { + "epoch": 5.67, + "learning_rate": 1.6820428600032725e-05, + "loss": 0.1759, + "step": 18344 + }, + { + "epoch": 5.67, + "learning_rate": 1.6820062848942855e-05, + "loss": 0.18, + "step": 18345 + }, + { + "epoch": 5.67, + "learning_rate": 1.681969708079477e-05, + "loss": 0.1917, + "step": 18346 + }, + { + "epoch": 5.67, + "learning_rate": 1.6819331295589377e-05, + "loss": 0.1934, + "step": 18347 + }, + { + "epoch": 5.67, + "learning_rate": 1.681896549332759e-05, + "loss": 0.184, + "step": 18348 + }, + { + "epoch": 5.67, + "learning_rate": 1.6818599674010333e-05, + "loss": 0.1787, + "step": 18349 + }, + { + "epoch": 5.67, + "learning_rate": 1.6818233837638513e-05, + "loss": 0.1882, + "step": 18350 + }, + { + "epoch": 5.67, + "learning_rate": 1.681786798421304e-05, + "loss": 0.1839, + "step": 18351 + }, + { + "epoch": 5.67, + "learning_rate": 1.681750211373484e-05, + "loss": 0.1866, + "step": 18352 + }, + { + "epoch": 5.67, + "learning_rate": 1.6817136226204828e-05, + "loss": 0.1641, + "step": 18353 + }, + { + "epoch": 5.67, + "learning_rate": 1.6816770321623908e-05, + "loss": 0.178, + "step": 18354 + }, + { + "epoch": 5.67, + "learning_rate": 1.6816404399993005e-05, + "loss": 0.1847, + "step": 18355 + }, + { + "epoch": 5.67, + "learning_rate": 1.6816038461313032e-05, + "loss": 0.195, + "step": 18356 + }, + { + "epoch": 5.67, + "learning_rate": 1.6815672505584902e-05, + "loss": 0.1863, + "step": 18357 + }, + { + "epoch": 5.67, + "learning_rate": 1.6815306532809532e-05, + "loss": 0.1936, + "step": 18358 + }, + { + "epoch": 5.67, + "learning_rate": 1.6814940542987835e-05, + "loss": 0.1716, + "step": 18359 + }, + { + "epoch": 5.67, + "learning_rate": 1.6814574536120734e-05, + "loss": 0.191, + "step": 18360 + }, + { + "epoch": 5.67, + "learning_rate": 1.681420851220914e-05, + "loss": 0.1941, + "step": 18361 + }, + { + "epoch": 5.67, + "learning_rate": 1.6813842471253963e-05, + "loss": 0.1811, + "step": 18362 + }, + { + "epoch": 5.67, + "learning_rate": 1.6813476413256125e-05, + "loss": 0.1999, + "step": 18363 + }, + { + "epoch": 5.67, + "learning_rate": 1.681311033821654e-05, + "loss": 0.196, + "step": 18364 + }, + { + "epoch": 5.67, + "learning_rate": 1.6812744246136122e-05, + "loss": 0.1808, + "step": 18365 + }, + { + "epoch": 5.67, + "learning_rate": 1.681237813701579e-05, + "loss": 0.1681, + "step": 18366 + }, + { + "epoch": 5.67, + "learning_rate": 1.681201201085646e-05, + "loss": 0.1846, + "step": 18367 + }, + { + "epoch": 5.67, + "learning_rate": 1.681164586765904e-05, + "loss": 0.1735, + "step": 18368 + }, + { + "epoch": 5.67, + "learning_rate": 1.6811279707424454e-05, + "loss": 0.1795, + "step": 18369 + }, + { + "epoch": 5.67, + "learning_rate": 1.6810913530153613e-05, + "loss": 0.1926, + "step": 18370 + }, + { + "epoch": 5.67, + "learning_rate": 1.681054733584744e-05, + "loss": 0.1891, + "step": 18371 + }, + { + "epoch": 5.67, + "learning_rate": 1.6810181124506842e-05, + "loss": 0.174, + "step": 18372 + }, + { + "epoch": 5.67, + "learning_rate": 1.6809814896132738e-05, + "loss": 0.1783, + "step": 18373 + }, + { + "epoch": 5.67, + "learning_rate": 1.6809448650726048e-05, + "loss": 0.1737, + "step": 18374 + }, + { + "epoch": 5.67, + "learning_rate": 1.6809082388287684e-05, + "loss": 0.1876, + "step": 18375 + }, + { + "epoch": 5.67, + "learning_rate": 1.680871610881856e-05, + "loss": 0.1717, + "step": 18376 + }, + { + "epoch": 5.68, + "learning_rate": 1.68083498123196e-05, + "loss": 0.1778, + "step": 18377 + }, + { + "epoch": 5.68, + "learning_rate": 1.6807983498791715e-05, + "loss": 0.1863, + "step": 18378 + }, + { + "epoch": 5.68, + "learning_rate": 1.680761716823582e-05, + "loss": 0.1999, + "step": 18379 + }, + { + "epoch": 5.68, + "learning_rate": 1.680725082065283e-05, + "loss": 0.1708, + "step": 18380 + }, + { + "epoch": 5.68, + "learning_rate": 1.680688445604367e-05, + "loss": 0.1871, + "step": 18381 + }, + { + "epoch": 5.68, + "learning_rate": 1.6806518074409247e-05, + "loss": 0.174, + "step": 18382 + }, + { + "epoch": 5.68, + "learning_rate": 1.680615167575048e-05, + "loss": 0.1762, + "step": 18383 + }, + { + "epoch": 5.68, + "learning_rate": 1.6805785260068287e-05, + "loss": 0.1891, + "step": 18384 + }, + { + "epoch": 5.68, + "learning_rate": 1.6805418827363585e-05, + "loss": 0.2186, + "step": 18385 + }, + { + "epoch": 5.68, + "learning_rate": 1.680505237763729e-05, + "loss": 0.1946, + "step": 18386 + }, + { + "epoch": 5.68, + "learning_rate": 1.6804685910890315e-05, + "loss": 0.1904, + "step": 18387 + }, + { + "epoch": 5.68, + "learning_rate": 1.680431942712358e-05, + "loss": 0.2129, + "step": 18388 + }, + { + "epoch": 5.68, + "learning_rate": 1.6803952926338002e-05, + "loss": 0.1868, + "step": 18389 + }, + { + "epoch": 5.68, + "learning_rate": 1.6803586408534498e-05, + "loss": 0.1737, + "step": 18390 + }, + { + "epoch": 5.68, + "learning_rate": 1.680321987371398e-05, + "loss": 0.1747, + "step": 18391 + }, + { + "epoch": 5.68, + "learning_rate": 1.680285332187737e-05, + "loss": 0.1842, + "step": 18392 + }, + { + "epoch": 5.68, + "learning_rate": 1.6802486753025584e-05, + "loss": 0.1811, + "step": 18393 + }, + { + "epoch": 5.68, + "learning_rate": 1.6802120167159537e-05, + "loss": 0.1793, + "step": 18394 + }, + { + "epoch": 5.68, + "learning_rate": 1.680175356428015e-05, + "loss": 0.2141, + "step": 18395 + }, + { + "epoch": 5.68, + "learning_rate": 1.6801386944388332e-05, + "loss": 0.1982, + "step": 18396 + }, + { + "epoch": 5.68, + "learning_rate": 1.6801020307485007e-05, + "loss": 0.1669, + "step": 18397 + }, + { + "epoch": 5.68, + "learning_rate": 1.680065365357109e-05, + "loss": 0.1799, + "step": 18398 + }, + { + "epoch": 5.68, + "learning_rate": 1.6800286982647497e-05, + "loss": 0.1985, + "step": 18399 + }, + { + "epoch": 5.68, + "learning_rate": 1.6799920294715146e-05, + "loss": 0.1931, + "step": 18400 + }, + { + "epoch": 5.68, + "learning_rate": 1.6799553589774956e-05, + "loss": 0.1983, + "step": 18401 + }, + { + "epoch": 5.68, + "learning_rate": 1.6799186867827838e-05, + "loss": 0.1822, + "step": 18402 + }, + { + "epoch": 5.68, + "learning_rate": 1.679882012887472e-05, + "loss": 0.1924, + "step": 18403 + }, + { + "epoch": 5.68, + "learning_rate": 1.679845337291651e-05, + "loss": 0.174, + "step": 18404 + }, + { + "epoch": 5.68, + "learning_rate": 1.6798086599954127e-05, + "loss": 0.1957, + "step": 18405 + }, + { + "epoch": 5.68, + "learning_rate": 1.6797719809988485e-05, + "loss": 0.1809, + "step": 18406 + }, + { + "epoch": 5.68, + "learning_rate": 1.6797353003020514e-05, + "loss": 0.201, + "step": 18407 + }, + { + "epoch": 5.68, + "learning_rate": 1.679698617905112e-05, + "loss": 0.2024, + "step": 18408 + }, + { + "epoch": 5.69, + "learning_rate": 1.6796619338081224e-05, + "loss": 0.1957, + "step": 18409 + }, + { + "epoch": 5.69, + "learning_rate": 1.6796252480111745e-05, + "loss": 0.2042, + "step": 18410 + }, + { + "epoch": 5.69, + "learning_rate": 1.6795885605143596e-05, + "loss": 0.2, + "step": 18411 + }, + { + "epoch": 5.69, + "learning_rate": 1.67955187131777e-05, + "loss": 0.1889, + "step": 18412 + }, + { + "epoch": 5.69, + "learning_rate": 1.6795151804214968e-05, + "loss": 0.1972, + "step": 18413 + }, + { + "epoch": 5.69, + "learning_rate": 1.679478487825633e-05, + "loss": 0.1883, + "step": 18414 + }, + { + "epoch": 5.69, + "learning_rate": 1.679441793530269e-05, + "loss": 0.1912, + "step": 18415 + }, + { + "epoch": 5.69, + "learning_rate": 1.679405097535497e-05, + "loss": 0.1811, + "step": 18416 + }, + { + "epoch": 5.69, + "learning_rate": 1.679368399841409e-05, + "loss": 0.1938, + "step": 18417 + }, + { + "epoch": 5.69, + "learning_rate": 1.6793317004480974e-05, + "loss": 0.1759, + "step": 18418 + }, + { + "epoch": 5.69, + "learning_rate": 1.6792949993556525e-05, + "loss": 0.1958, + "step": 18419 + }, + { + "epoch": 5.69, + "learning_rate": 1.6792582965641676e-05, + "loss": 0.1893, + "step": 18420 + }, + { + "epoch": 5.69, + "learning_rate": 1.6792215920737332e-05, + "loss": 0.1909, + "step": 18421 + }, + { + "epoch": 5.69, + "learning_rate": 1.679184885884442e-05, + "loss": 0.1933, + "step": 18422 + }, + { + "epoch": 5.69, + "learning_rate": 1.6791481779963853e-05, + "loss": 0.2073, + "step": 18423 + }, + { + "epoch": 5.69, + "learning_rate": 1.6791114684096555e-05, + "loss": 0.1792, + "step": 18424 + }, + { + "epoch": 5.69, + "learning_rate": 1.6790747571243438e-05, + "loss": 0.2019, + "step": 18425 + }, + { + "epoch": 5.69, + "learning_rate": 1.6790380441405426e-05, + "loss": 0.1999, + "step": 18426 + }, + { + "epoch": 5.69, + "learning_rate": 1.6790013294583428e-05, + "loss": 0.1885, + "step": 18427 + }, + { + "epoch": 5.69, + "learning_rate": 1.6789646130778375e-05, + "loss": 0.1888, + "step": 18428 + }, + { + "epoch": 5.69, + "learning_rate": 1.6789278949991176e-05, + "loss": 0.1846, + "step": 18429 + }, + { + "epoch": 5.69, + "learning_rate": 1.6788911752222748e-05, + "loss": 0.1866, + "step": 18430 + }, + { + "epoch": 5.69, + "learning_rate": 1.6788544537474017e-05, + "loss": 0.19, + "step": 18431 + }, + { + "epoch": 5.69, + "learning_rate": 1.67881773057459e-05, + "loss": 0.184, + "step": 18432 + }, + { + "epoch": 5.69, + "learning_rate": 1.6787810057039313e-05, + "loss": 0.1755, + "step": 18433 + }, + { + "epoch": 5.69, + "learning_rate": 1.6787442791355174e-05, + "loss": 0.1809, + "step": 18434 + }, + { + "epoch": 5.69, + "learning_rate": 1.67870755086944e-05, + "loss": 0.1955, + "step": 18435 + }, + { + "epoch": 5.69, + "learning_rate": 1.6786708209057914e-05, + "loss": 0.1766, + "step": 18436 + }, + { + "epoch": 5.69, + "learning_rate": 1.6786340892446634e-05, + "loss": 0.1874, + "step": 18437 + }, + { + "epoch": 5.69, + "learning_rate": 1.678597355886148e-05, + "loss": 0.1871, + "step": 18438 + }, + { + "epoch": 5.69, + "learning_rate": 1.6785606208303366e-05, + "loss": 0.1961, + "step": 18439 + }, + { + "epoch": 5.69, + "learning_rate": 1.678523884077321e-05, + "loss": 0.1957, + "step": 18440 + }, + { + "epoch": 5.7, + "learning_rate": 1.678487145627194e-05, + "loss": 0.1743, + "step": 18441 + }, + { + "epoch": 5.7, + "learning_rate": 1.6784504054800463e-05, + "loss": 0.1963, + "step": 18442 + }, + { + "epoch": 5.7, + "learning_rate": 1.6784136636359708e-05, + "loss": 0.1783, + "step": 18443 + }, + { + "epoch": 5.7, + "learning_rate": 1.678376920095059e-05, + "loss": 0.1833, + "step": 18444 + }, + { + "epoch": 5.7, + "learning_rate": 1.6783401748574026e-05, + "loss": 0.1782, + "step": 18445 + }, + { + "epoch": 5.7, + "learning_rate": 1.6783034279230938e-05, + "loss": 0.1853, + "step": 18446 + }, + { + "epoch": 5.7, + "learning_rate": 1.678266679292224e-05, + "loss": 0.189, + "step": 18447 + }, + { + "epoch": 5.7, + "learning_rate": 1.6782299289648863e-05, + "loss": 0.1848, + "step": 18448 + }, + { + "epoch": 5.7, + "learning_rate": 1.6781931769411716e-05, + "loss": 0.1944, + "step": 18449 + }, + { + "epoch": 5.7, + "learning_rate": 1.6781564232211718e-05, + "loss": 0.1906, + "step": 18450 + }, + { + "epoch": 5.7, + "learning_rate": 1.678119667804979e-05, + "loss": 0.193, + "step": 18451 + }, + { + "epoch": 5.7, + "learning_rate": 1.6780829106926857e-05, + "loss": 0.1731, + "step": 18452 + }, + { + "epoch": 5.7, + "learning_rate": 1.678046151884383e-05, + "loss": 0.1945, + "step": 18453 + }, + { + "epoch": 5.7, + "learning_rate": 1.6780093913801634e-05, + "loss": 0.1874, + "step": 18454 + }, + { + "epoch": 5.7, + "learning_rate": 1.677972629180119e-05, + "loss": 0.1878, + "step": 18455 + }, + { + "epoch": 5.7, + "learning_rate": 1.6779358652843406e-05, + "loss": 0.1878, + "step": 18456 + }, + { + "epoch": 5.7, + "learning_rate": 1.6778990996929213e-05, + "loss": 0.1873, + "step": 18457 + }, + { + "epoch": 5.7, + "learning_rate": 1.6778623324059527e-05, + "loss": 0.1949, + "step": 18458 + }, + { + "epoch": 5.7, + "learning_rate": 1.677825563423527e-05, + "loss": 0.1937, + "step": 18459 + }, + { + "epoch": 5.7, + "learning_rate": 1.6777887927457355e-05, + "loss": 0.1921, + "step": 18460 + }, + { + "epoch": 5.7, + "learning_rate": 1.6777520203726712e-05, + "loss": 0.1892, + "step": 18461 + }, + { + "epoch": 5.7, + "learning_rate": 1.677715246304425e-05, + "loss": 0.1853, + "step": 18462 + }, + { + "epoch": 5.7, + "learning_rate": 1.6776784705410896e-05, + "loss": 0.1731, + "step": 18463 + }, + { + "epoch": 5.7, + "learning_rate": 1.6776416930827567e-05, + "loss": 0.1903, + "step": 18464 + }, + { + "epoch": 5.7, + "learning_rate": 1.6776049139295182e-05, + "loss": 0.1746, + "step": 18465 + }, + { + "epoch": 5.7, + "learning_rate": 1.6775681330814664e-05, + "loss": 0.1927, + "step": 18466 + }, + { + "epoch": 5.7, + "learning_rate": 1.677531350538693e-05, + "loss": 0.1827, + "step": 18467 + }, + { + "epoch": 5.7, + "learning_rate": 1.6774945663012902e-05, + "loss": 0.1759, + "step": 18468 + }, + { + "epoch": 5.7, + "learning_rate": 1.6774577803693498e-05, + "loss": 0.2103, + "step": 18469 + }, + { + "epoch": 5.7, + "learning_rate": 1.677420992742964e-05, + "loss": 0.1932, + "step": 18470 + }, + { + "epoch": 5.7, + "learning_rate": 1.677384203422225e-05, + "loss": 0.1928, + "step": 18471 + }, + { + "epoch": 5.7, + "learning_rate": 1.677347412407224e-05, + "loss": 0.195, + "step": 18472 + }, + { + "epoch": 5.7, + "learning_rate": 1.6773106196980538e-05, + "loss": 0.1675, + "step": 18473 + }, + { + "epoch": 5.71, + "learning_rate": 1.6772738252948063e-05, + "loss": 0.1915, + "step": 18474 + }, + { + "epoch": 5.71, + "learning_rate": 1.6772370291975733e-05, + "loss": 0.1974, + "step": 18475 + }, + { + "epoch": 5.71, + "learning_rate": 1.6772002314064472e-05, + "loss": 0.1682, + "step": 18476 + }, + { + "epoch": 5.71, + "learning_rate": 1.6771634319215198e-05, + "loss": 0.1825, + "step": 18477 + }, + { + "epoch": 5.71, + "learning_rate": 1.677126630742883e-05, + "loss": 0.1888, + "step": 18478 + }, + { + "epoch": 5.71, + "learning_rate": 1.677089827870629e-05, + "loss": 0.192, + "step": 18479 + }, + { + "epoch": 5.71, + "learning_rate": 1.67705302330485e-05, + "loss": 0.177, + "step": 18480 + }, + { + "epoch": 5.71, + "learning_rate": 1.6770162170456375e-05, + "loss": 0.1826, + "step": 18481 + }, + { + "epoch": 5.71, + "learning_rate": 1.6769794090930847e-05, + "loss": 0.1721, + "step": 18482 + }, + { + "epoch": 5.71, + "learning_rate": 1.6769425994472826e-05, + "loss": 0.181, + "step": 18483 + }, + { + "epoch": 5.71, + "learning_rate": 1.6769057881083232e-05, + "loss": 0.1818, + "step": 18484 + }, + { + "epoch": 5.71, + "learning_rate": 1.676868975076299e-05, + "loss": 0.1811, + "step": 18485 + }, + { + "epoch": 5.71, + "learning_rate": 1.6768321603513026e-05, + "loss": 0.1855, + "step": 18486 + }, + { + "epoch": 5.71, + "learning_rate": 1.6767953439334252e-05, + "loss": 0.1823, + "step": 18487 + }, + { + "epoch": 5.71, + "learning_rate": 1.6767585258227593e-05, + "loss": 0.1956, + "step": 18488 + }, + { + "epoch": 5.71, + "learning_rate": 1.6767217060193967e-05, + "loss": 0.1874, + "step": 18489 + }, + { + "epoch": 5.71, + "learning_rate": 1.6766848845234298e-05, + "loss": 0.189, + "step": 18490 + }, + { + "epoch": 5.71, + "learning_rate": 1.6766480613349505e-05, + "loss": 0.2011, + "step": 18491 + }, + { + "epoch": 5.71, + "learning_rate": 1.676611236454051e-05, + "loss": 0.1923, + "step": 18492 + }, + { + "epoch": 5.71, + "learning_rate": 1.6765744098808238e-05, + "loss": 0.1896, + "step": 18493 + }, + { + "epoch": 5.71, + "learning_rate": 1.67653758161536e-05, + "loss": 0.1883, + "step": 18494 + }, + { + "epoch": 5.71, + "learning_rate": 1.6765007516577526e-05, + "loss": 0.1904, + "step": 18495 + }, + { + "epoch": 5.71, + "learning_rate": 1.6764639200080934e-05, + "loss": 0.2038, + "step": 18496 + }, + { + "epoch": 5.71, + "learning_rate": 1.6764270866664744e-05, + "loss": 0.1878, + "step": 18497 + }, + { + "epoch": 5.71, + "learning_rate": 1.676390251632988e-05, + "loss": 0.1875, + "step": 18498 + }, + { + "epoch": 5.71, + "learning_rate": 1.6763534149077263e-05, + "loss": 0.1995, + "step": 18499 + }, + { + "epoch": 5.71, + "learning_rate": 1.6763165764907814e-05, + "loss": 0.1887, + "step": 18500 + }, + { + "epoch": 5.71, + "learning_rate": 1.676279736382245e-05, + "loss": 0.1727, + "step": 18501 + }, + { + "epoch": 5.71, + "learning_rate": 1.6762428945822102e-05, + "loss": 0.192, + "step": 18502 + }, + { + "epoch": 5.71, + "learning_rate": 1.6762060510907686e-05, + "loss": 0.1807, + "step": 18503 + }, + { + "epoch": 5.71, + "learning_rate": 1.676169205908012e-05, + "loss": 0.1823, + "step": 18504 + }, + { + "epoch": 5.71, + "learning_rate": 1.676132359034033e-05, + "loss": 0.1991, + "step": 18505 + }, + { + "epoch": 5.72, + "learning_rate": 1.6760955104689235e-05, + "loss": 0.2023, + "step": 18506 + }, + { + "epoch": 5.72, + "learning_rate": 1.676058660212776e-05, + "loss": 0.203, + "step": 18507 + }, + { + "epoch": 5.72, + "learning_rate": 1.676021808265682e-05, + "loss": 0.209, + "step": 18508 + }, + { + "epoch": 5.72, + "learning_rate": 1.6759849546277347e-05, + "loss": 0.1805, + "step": 18509 + }, + { + "epoch": 5.72, + "learning_rate": 1.6759480992990256e-05, + "loss": 0.1795, + "step": 18510 + }, + { + "epoch": 5.72, + "learning_rate": 1.6759112422796468e-05, + "loss": 0.1967, + "step": 18511 + }, + { + "epoch": 5.72, + "learning_rate": 1.6758743835696912e-05, + "loss": 0.1795, + "step": 18512 + }, + { + "epoch": 5.72, + "learning_rate": 1.67583752316925e-05, + "loss": 0.1855, + "step": 18513 + }, + { + "epoch": 5.72, + "learning_rate": 1.6758006610784163e-05, + "loss": 0.1984, + "step": 18514 + }, + { + "epoch": 5.72, + "learning_rate": 1.6757637972972816e-05, + "loss": 0.2063, + "step": 18515 + }, + { + "epoch": 5.72, + "learning_rate": 1.6757269318259384e-05, + "loss": 0.1835, + "step": 18516 + }, + { + "epoch": 5.72, + "learning_rate": 1.675690064664479e-05, + "loss": 0.1854, + "step": 18517 + }, + { + "epoch": 5.72, + "learning_rate": 1.6756531958129954e-05, + "loss": 0.1748, + "step": 18518 + }, + { + "epoch": 5.72, + "learning_rate": 1.67561632527158e-05, + "loss": 0.186, + "step": 18519 + }, + { + "epoch": 5.72, + "learning_rate": 1.675579453040325e-05, + "loss": 0.2077, + "step": 18520 + }, + { + "epoch": 5.72, + "learning_rate": 1.6755425791193226e-05, + "loss": 0.1906, + "step": 18521 + }, + { + "epoch": 5.72, + "learning_rate": 1.675505703508665e-05, + "loss": 0.1947, + "step": 18522 + }, + { + "epoch": 5.72, + "learning_rate": 1.6754688262084443e-05, + "loss": 0.1776, + "step": 18523 + }, + { + "epoch": 5.72, + "learning_rate": 1.6754319472187527e-05, + "loss": 0.1731, + "step": 18524 + }, + { + "epoch": 5.72, + "learning_rate": 1.675395066539683e-05, + "loss": 0.1863, + "step": 18525 + }, + { + "epoch": 5.72, + "learning_rate": 1.675358184171327e-05, + "loss": 0.1932, + "step": 18526 + }, + { + "epoch": 5.72, + "learning_rate": 1.6753213001137768e-05, + "loss": 0.1763, + "step": 18527 + }, + { + "epoch": 5.72, + "learning_rate": 1.675284414367125e-05, + "loss": 0.1778, + "step": 18528 + }, + { + "epoch": 5.72, + "learning_rate": 1.6752475269314635e-05, + "loss": 0.1905, + "step": 18529 + }, + { + "epoch": 5.72, + "learning_rate": 1.675210637806885e-05, + "loss": 0.2078, + "step": 18530 + }, + { + "epoch": 5.72, + "learning_rate": 1.6751737469934813e-05, + "loss": 0.1738, + "step": 18531 + }, + { + "epoch": 5.72, + "learning_rate": 1.6751368544913452e-05, + "loss": 0.1864, + "step": 18532 + }, + { + "epoch": 5.72, + "learning_rate": 1.6750999603005686e-05, + "loss": 0.1666, + "step": 18533 + }, + { + "epoch": 5.72, + "learning_rate": 1.6750630644212437e-05, + "loss": 0.1825, + "step": 18534 + }, + { + "epoch": 5.72, + "learning_rate": 1.6750261668534633e-05, + "loss": 0.1651, + "step": 18535 + }, + { + "epoch": 5.72, + "learning_rate": 1.6749892675973192e-05, + "loss": 0.1889, + "step": 18536 + }, + { + "epoch": 5.72, + "learning_rate": 1.6749523666529036e-05, + "loss": 0.1959, + "step": 18537 + }, + { + "epoch": 5.72, + "learning_rate": 1.6749154640203093e-05, + "loss": 0.1757, + "step": 18538 + }, + { + "epoch": 5.73, + "learning_rate": 1.6748785596996282e-05, + "loss": 0.1893, + "step": 18539 + }, + { + "epoch": 5.73, + "learning_rate": 1.6748416536909527e-05, + "loss": 0.1643, + "step": 18540 + }, + { + "epoch": 5.73, + "learning_rate": 1.6748047459943754e-05, + "loss": 0.188, + "step": 18541 + }, + { + "epoch": 5.73, + "learning_rate": 1.6747678366099883e-05, + "loss": 0.1873, + "step": 18542 + }, + { + "epoch": 5.73, + "learning_rate": 1.674730925537883e-05, + "loss": 0.1852, + "step": 18543 + }, + { + "epoch": 5.73, + "learning_rate": 1.6746940127781534e-05, + "loss": 0.1799, + "step": 18544 + }, + { + "epoch": 5.73, + "learning_rate": 1.6746570983308908e-05, + "loss": 0.1792, + "step": 18545 + }, + { + "epoch": 5.73, + "learning_rate": 1.6746201821961882e-05, + "loss": 0.1899, + "step": 18546 + }, + { + "epoch": 5.73, + "learning_rate": 1.674583264374137e-05, + "loss": 0.1905, + "step": 18547 + }, + { + "epoch": 5.73, + "learning_rate": 1.67454634486483e-05, + "loss": 0.2032, + "step": 18548 + }, + { + "epoch": 5.73, + "learning_rate": 1.6745094236683598e-05, + "loss": 0.2111, + "step": 18549 + }, + { + "epoch": 5.73, + "learning_rate": 1.674472500784818e-05, + "loss": 0.2007, + "step": 18550 + }, + { + "epoch": 5.73, + "learning_rate": 1.6744355762142982e-05, + "loss": 0.1872, + "step": 18551 + }, + { + "epoch": 5.73, + "learning_rate": 1.6743986499568915e-05, + "loss": 0.1822, + "step": 18552 + }, + { + "epoch": 5.73, + "learning_rate": 1.674361722012691e-05, + "loss": 0.1879, + "step": 18553 + }, + { + "epoch": 5.73, + "learning_rate": 1.6743247923817888e-05, + "loss": 0.1775, + "step": 18554 + }, + { + "epoch": 5.73, + "learning_rate": 1.674287861064277e-05, + "loss": 0.1977, + "step": 18555 + }, + { + "epoch": 5.73, + "learning_rate": 1.6742509280602485e-05, + "loss": 0.1836, + "step": 18556 + }, + { + "epoch": 5.73, + "learning_rate": 1.6742139933697954e-05, + "loss": 0.1895, + "step": 18557 + }, + { + "epoch": 5.73, + "learning_rate": 1.6741770569930104e-05, + "loss": 0.2114, + "step": 18558 + }, + { + "epoch": 5.73, + "learning_rate": 1.6741401189299854e-05, + "loss": 0.1903, + "step": 18559 + }, + { + "epoch": 5.73, + "learning_rate": 1.674103179180813e-05, + "loss": 0.1736, + "step": 18560 + }, + { + "epoch": 5.73, + "learning_rate": 1.6740662377455855e-05, + "loss": 0.1858, + "step": 18561 + }, + { + "epoch": 5.73, + "learning_rate": 1.6740292946243956e-05, + "loss": 0.1947, + "step": 18562 + }, + { + "epoch": 5.73, + "learning_rate": 1.6739923498173353e-05, + "loss": 0.1861, + "step": 18563 + }, + { + "epoch": 5.73, + "learning_rate": 1.6739554033244975e-05, + "loss": 0.2006, + "step": 18564 + }, + { + "epoch": 5.73, + "learning_rate": 1.6739184551459743e-05, + "loss": 0.1888, + "step": 18565 + }, + { + "epoch": 5.73, + "learning_rate": 1.6738815052818577e-05, + "loss": 0.1994, + "step": 18566 + }, + { + "epoch": 5.73, + "learning_rate": 1.673844553732241e-05, + "loss": 0.1975, + "step": 18567 + }, + { + "epoch": 5.73, + "learning_rate": 1.673807600497216e-05, + "loss": 0.1829, + "step": 18568 + }, + { + "epoch": 5.73, + "learning_rate": 1.673770645576875e-05, + "loss": 0.1868, + "step": 18569 + }, + { + "epoch": 5.73, + "learning_rate": 1.6737336889713113e-05, + "loss": 0.1776, + "step": 18570 + }, + { + "epoch": 5.74, + "learning_rate": 1.6736967306806168e-05, + "loss": 0.173, + "step": 18571 + }, + { + "epoch": 5.74, + "learning_rate": 1.6736597707048833e-05, + "loss": 0.1789, + "step": 18572 + }, + { + "epoch": 5.74, + "learning_rate": 1.6736228090442042e-05, + "loss": 0.2126, + "step": 18573 + }, + { + "epoch": 5.74, + "learning_rate": 1.6735858456986715e-05, + "loss": 0.1881, + "step": 18574 + }, + { + "epoch": 5.74, + "learning_rate": 1.6735488806683777e-05, + "loss": 0.1918, + "step": 18575 + }, + { + "epoch": 5.74, + "learning_rate": 1.6735119139534154e-05, + "loss": 0.1881, + "step": 18576 + }, + { + "epoch": 5.74, + "learning_rate": 1.673474945553877e-05, + "loss": 0.1863, + "step": 18577 + }, + { + "epoch": 5.74, + "learning_rate": 1.6734379754698546e-05, + "loss": 0.2019, + "step": 18578 + }, + { + "epoch": 5.74, + "learning_rate": 1.6734010037014415e-05, + "loss": 0.1869, + "step": 18579 + }, + { + "epoch": 5.74, + "learning_rate": 1.673364030248729e-05, + "loss": 0.1737, + "step": 18580 + }, + { + "epoch": 5.74, + "learning_rate": 1.673327055111811e-05, + "loss": 0.1804, + "step": 18581 + }, + { + "epoch": 5.74, + "learning_rate": 1.673290078290779e-05, + "loss": 0.1919, + "step": 18582 + }, + { + "epoch": 5.74, + "learning_rate": 1.6732530997857255e-05, + "loss": 0.1836, + "step": 18583 + }, + { + "epoch": 5.74, + "learning_rate": 1.6732161195967434e-05, + "loss": 0.2005, + "step": 18584 + }, + { + "epoch": 5.74, + "learning_rate": 1.673179137723925e-05, + "loss": 0.2074, + "step": 18585 + }, + { + "epoch": 5.74, + "learning_rate": 1.6731421541673624e-05, + "loss": 0.1797, + "step": 18586 + }, + { + "epoch": 5.74, + "learning_rate": 1.6731051689271488e-05, + "loss": 0.1809, + "step": 18587 + }, + { + "epoch": 5.74, + "learning_rate": 1.6730681820033766e-05, + "loss": 0.1892, + "step": 18588 + }, + { + "epoch": 5.74, + "learning_rate": 1.673031193396138e-05, + "loss": 0.1743, + "step": 18589 + }, + { + "epoch": 5.74, + "learning_rate": 1.6729942031055256e-05, + "loss": 0.1884, + "step": 18590 + }, + { + "epoch": 5.74, + "learning_rate": 1.6729572111316318e-05, + "loss": 0.1926, + "step": 18591 + }, + { + "epoch": 5.74, + "learning_rate": 1.6729202174745494e-05, + "loss": 0.1903, + "step": 18592 + }, + { + "epoch": 5.74, + "learning_rate": 1.6728832221343708e-05, + "loss": 0.1755, + "step": 18593 + }, + { + "epoch": 5.74, + "learning_rate": 1.6728462251111882e-05, + "loss": 0.1898, + "step": 18594 + }, + { + "epoch": 5.74, + "learning_rate": 1.672809226405095e-05, + "loss": 0.1959, + "step": 18595 + }, + { + "epoch": 5.74, + "learning_rate": 1.6727722260161832e-05, + "loss": 0.1929, + "step": 18596 + }, + { + "epoch": 5.74, + "learning_rate": 1.672735223944545e-05, + "loss": 0.2008, + "step": 18597 + }, + { + "epoch": 5.74, + "learning_rate": 1.6726982201902736e-05, + "loss": 0.1876, + "step": 18598 + }, + { + "epoch": 5.74, + "learning_rate": 1.6726612147534613e-05, + "loss": 0.1949, + "step": 18599 + }, + { + "epoch": 5.74, + "learning_rate": 1.6726242076342e-05, + "loss": 0.1823, + "step": 18600 + }, + { + "epoch": 5.74, + "learning_rate": 1.6725871988325835e-05, + "loss": 0.1863, + "step": 18601 + }, + { + "epoch": 5.74, + "learning_rate": 1.6725501883487037e-05, + "loss": 0.1877, + "step": 18602 + }, + { + "epoch": 5.75, + "learning_rate": 1.672513176182653e-05, + "loss": 0.1939, + "step": 18603 + }, + { + "epoch": 5.75, + "learning_rate": 1.6724761623345244e-05, + "loss": 0.1853, + "step": 18604 + }, + { + "epoch": 5.75, + "learning_rate": 1.67243914680441e-05, + "loss": 0.1942, + "step": 18605 + }, + { + "epoch": 5.75, + "learning_rate": 1.6724021295924027e-05, + "loss": 0.1884, + "step": 18606 + }, + { + "epoch": 5.75, + "learning_rate": 1.6723651106985953e-05, + "loss": 0.1897, + "step": 18607 + }, + { + "epoch": 5.75, + "learning_rate": 1.67232809012308e-05, + "loss": 0.1804, + "step": 18608 + }, + { + "epoch": 5.75, + "learning_rate": 1.6722910678659493e-05, + "loss": 0.1974, + "step": 18609 + }, + { + "epoch": 5.75, + "learning_rate": 1.6722540439272964e-05, + "loss": 0.1782, + "step": 18610 + }, + { + "epoch": 5.75, + "learning_rate": 1.672217018307213e-05, + "loss": 0.2154, + "step": 18611 + }, + { + "epoch": 5.75, + "learning_rate": 1.6721799910057928e-05, + "loss": 0.1916, + "step": 18612 + }, + { + "epoch": 5.75, + "learning_rate": 1.6721429620231275e-05, + "loss": 0.1719, + "step": 18613 + }, + { + "epoch": 5.75, + "learning_rate": 1.67210593135931e-05, + "loss": 0.1977, + "step": 18614 + }, + { + "epoch": 5.75, + "learning_rate": 1.6720688990144335e-05, + "loss": 0.195, + "step": 18615 + }, + { + "epoch": 5.75, + "learning_rate": 1.6720318649885896e-05, + "loss": 0.1992, + "step": 18616 + }, + { + "epoch": 5.75, + "learning_rate": 1.6719948292818714e-05, + "loss": 0.2022, + "step": 18617 + }, + { + "epoch": 5.75, + "learning_rate": 1.671957791894372e-05, + "loss": 0.1855, + "step": 18618 + }, + { + "epoch": 5.75, + "learning_rate": 1.6719207528261835e-05, + "loss": 0.2022, + "step": 18619 + }, + { + "epoch": 5.75, + "learning_rate": 1.6718837120773984e-05, + "loss": 0.1901, + "step": 18620 + }, + { + "epoch": 5.75, + "learning_rate": 1.6718466696481094e-05, + "loss": 0.1775, + "step": 18621 + }, + { + "epoch": 5.75, + "learning_rate": 1.6718096255384097e-05, + "loss": 0.1877, + "step": 18622 + }, + { + "epoch": 5.75, + "learning_rate": 1.6717725797483915e-05, + "loss": 0.1787, + "step": 18623 + }, + { + "epoch": 5.75, + "learning_rate": 1.6717355322781478e-05, + "loss": 0.195, + "step": 18624 + }, + { + "epoch": 5.75, + "learning_rate": 1.6716984831277706e-05, + "loss": 0.18, + "step": 18625 + }, + { + "epoch": 5.75, + "learning_rate": 1.671661432297353e-05, + "loss": 0.1761, + "step": 18626 + }, + { + "epoch": 5.75, + "learning_rate": 1.6716243797869883e-05, + "loss": 0.1836, + "step": 18627 + }, + { + "epoch": 5.75, + "learning_rate": 1.6715873255967675e-05, + "loss": 0.1761, + "step": 18628 + }, + { + "epoch": 5.75, + "learning_rate": 1.671550269726785e-05, + "loss": 0.1932, + "step": 18629 + }, + { + "epoch": 5.75, + "learning_rate": 1.671513212177133e-05, + "loss": 0.1909, + "step": 18630 + }, + { + "epoch": 5.75, + "learning_rate": 1.6714761529479036e-05, + "loss": 0.1942, + "step": 18631 + }, + { + "epoch": 5.75, + "learning_rate": 1.6714390920391896e-05, + "loss": 0.1732, + "step": 18632 + }, + { + "epoch": 5.75, + "learning_rate": 1.6714020294510843e-05, + "loss": 0.1949, + "step": 18633 + }, + { + "epoch": 5.75, + "learning_rate": 1.6713649651836803e-05, + "loss": 0.2038, + "step": 18634 + }, + { + "epoch": 5.75, + "learning_rate": 1.6713278992370697e-05, + "loss": 0.1905, + "step": 18635 + }, + { + "epoch": 5.76, + "learning_rate": 1.6712908316113457e-05, + "loss": 0.193, + "step": 18636 + }, + { + "epoch": 5.76, + "learning_rate": 1.671253762306601e-05, + "loss": 0.1797, + "step": 18637 + }, + { + "epoch": 5.76, + "learning_rate": 1.6712166913229283e-05, + "loss": 0.1783, + "step": 18638 + }, + { + "epoch": 5.76, + "learning_rate": 1.6711796186604198e-05, + "loss": 0.1658, + "step": 18639 + }, + { + "epoch": 5.76, + "learning_rate": 1.671142544319169e-05, + "loss": 0.1813, + "step": 18640 + }, + { + "epoch": 5.76, + "learning_rate": 1.671105468299268e-05, + "loss": 0.1886, + "step": 18641 + }, + { + "epoch": 5.76, + "learning_rate": 1.67106839060081e-05, + "loss": 0.1884, + "step": 18642 + }, + { + "epoch": 5.76, + "learning_rate": 1.671031311223888e-05, + "loss": 0.1815, + "step": 18643 + }, + { + "epoch": 5.76, + "learning_rate": 1.6709942301685935e-05, + "loss": 0.1841, + "step": 18644 + }, + { + "epoch": 5.76, + "learning_rate": 1.6709571474350205e-05, + "loss": 0.185, + "step": 18645 + }, + { + "epoch": 5.76, + "learning_rate": 1.670920063023261e-05, + "loss": 0.1982, + "step": 18646 + }, + { + "epoch": 5.76, + "learning_rate": 1.6708829769334087e-05, + "loss": 0.1719, + "step": 18647 + }, + { + "epoch": 5.76, + "learning_rate": 1.670845889165555e-05, + "loss": 0.1889, + "step": 18648 + }, + { + "epoch": 5.76, + "learning_rate": 1.6708087997197938e-05, + "loss": 0.1773, + "step": 18649 + }, + { + "epoch": 5.76, + "learning_rate": 1.670771708596217e-05, + "loss": 0.1801, + "step": 18650 + }, + { + "epoch": 5.76, + "learning_rate": 1.6707346157949182e-05, + "loss": 0.2047, + "step": 18651 + }, + { + "epoch": 5.76, + "learning_rate": 1.67069752131599e-05, + "loss": 0.2054, + "step": 18652 + }, + { + "epoch": 5.76, + "learning_rate": 1.6706604251595248e-05, + "loss": 0.1961, + "step": 18653 + }, + { + "epoch": 5.76, + "learning_rate": 1.6706233273256152e-05, + "loss": 0.1745, + "step": 18654 + }, + { + "epoch": 5.76, + "learning_rate": 1.6705862278143548e-05, + "loss": 0.1832, + "step": 18655 + }, + { + "epoch": 5.76, + "learning_rate": 1.6705491266258356e-05, + "loss": 0.191, + "step": 18656 + }, + { + "epoch": 5.76, + "learning_rate": 1.670512023760151e-05, + "loss": 0.1969, + "step": 18657 + }, + { + "epoch": 5.76, + "learning_rate": 1.6704749192173934e-05, + "loss": 0.1958, + "step": 18658 + }, + { + "epoch": 5.76, + "learning_rate": 1.6704378129976554e-05, + "loss": 0.1847, + "step": 18659 + }, + { + "epoch": 5.76, + "learning_rate": 1.6704007051010307e-05, + "loss": 0.1834, + "step": 18660 + }, + { + "epoch": 5.76, + "learning_rate": 1.6703635955276114e-05, + "loss": 0.1775, + "step": 18661 + }, + { + "epoch": 5.76, + "learning_rate": 1.6703264842774904e-05, + "loss": 0.1874, + "step": 18662 + }, + { + "epoch": 5.76, + "learning_rate": 1.6702893713507605e-05, + "loss": 0.188, + "step": 18663 + }, + { + "epoch": 5.76, + "learning_rate": 1.670252256747515e-05, + "loss": 0.1843, + "step": 18664 + }, + { + "epoch": 5.76, + "learning_rate": 1.670215140467846e-05, + "loss": 0.2045, + "step": 18665 + }, + { + "epoch": 5.76, + "learning_rate": 1.6701780225118466e-05, + "loss": 0.1906, + "step": 18666 + }, + { + "epoch": 5.76, + "learning_rate": 1.6701409028796102e-05, + "loss": 0.1882, + "step": 18667 + }, + { + "epoch": 5.77, + "learning_rate": 1.6701037815712287e-05, + "loss": 0.1978, + "step": 18668 + }, + { + "epoch": 5.77, + "learning_rate": 1.6700666585867957e-05, + "loss": 0.185, + "step": 18669 + }, + { + "epoch": 5.77, + "learning_rate": 1.6700295339264037e-05, + "loss": 0.1942, + "step": 18670 + }, + { + "epoch": 5.77, + "learning_rate": 1.669992407590146e-05, + "loss": 0.1895, + "step": 18671 + }, + { + "epoch": 5.77, + "learning_rate": 1.6699552795781146e-05, + "loss": 0.2073, + "step": 18672 + }, + { + "epoch": 5.77, + "learning_rate": 1.6699181498904028e-05, + "loss": 0.1847, + "step": 18673 + }, + { + "epoch": 5.77, + "learning_rate": 1.6698810185271036e-05, + "loss": 0.2023, + "step": 18674 + }, + { + "epoch": 5.77, + "learning_rate": 1.6698438854883103e-05, + "loss": 0.1945, + "step": 18675 + }, + { + "epoch": 5.77, + "learning_rate": 1.6698067507741146e-05, + "loss": 0.1759, + "step": 18676 + }, + { + "epoch": 5.77, + "learning_rate": 1.6697696143846107e-05, + "loss": 0.1954, + "step": 18677 + }, + { + "epoch": 5.77, + "learning_rate": 1.66973247631989e-05, + "loss": 0.199, + "step": 18678 + }, + { + "epoch": 5.77, + "learning_rate": 1.669695336580047e-05, + "loss": 0.1941, + "step": 18679 + }, + { + "epoch": 5.77, + "learning_rate": 1.6696581951651735e-05, + "loss": 0.1859, + "step": 18680 + }, + { + "epoch": 5.77, + "learning_rate": 1.6696210520753625e-05, + "loss": 0.1928, + "step": 18681 + }, + { + "epoch": 5.77, + "learning_rate": 1.6695839073107075e-05, + "loss": 0.1842, + "step": 18682 + }, + { + "epoch": 5.77, + "learning_rate": 1.6695467608713007e-05, + "loss": 0.1969, + "step": 18683 + }, + { + "epoch": 5.77, + "learning_rate": 1.6695096127572355e-05, + "loss": 0.1964, + "step": 18684 + }, + { + "epoch": 5.77, + "learning_rate": 1.6694724629686048e-05, + "loss": 0.1881, + "step": 18685 + }, + { + "epoch": 5.77, + "learning_rate": 1.669435311505501e-05, + "loss": 0.1997, + "step": 18686 + }, + { + "epoch": 5.77, + "learning_rate": 1.6693981583680176e-05, + "loss": 0.1729, + "step": 18687 + }, + { + "epoch": 5.77, + "learning_rate": 1.6693610035562475e-05, + "loss": 0.1835, + "step": 18688 + }, + { + "epoch": 5.77, + "learning_rate": 1.669323847070283e-05, + "loss": 0.1953, + "step": 18689 + }, + { + "epoch": 5.77, + "learning_rate": 1.6692866889102178e-05, + "loss": 0.1774, + "step": 18690 + }, + { + "epoch": 5.77, + "learning_rate": 1.6692495290761447e-05, + "loss": 0.1835, + "step": 18691 + }, + { + "epoch": 5.77, + "learning_rate": 1.6692123675681565e-05, + "loss": 0.1895, + "step": 18692 + }, + { + "epoch": 5.77, + "learning_rate": 1.6691752043863452e-05, + "loss": 0.1855, + "step": 18693 + }, + { + "epoch": 5.77, + "learning_rate": 1.6691380395308057e-05, + "loss": 0.1915, + "step": 18694 + }, + { + "epoch": 5.77, + "learning_rate": 1.6691008730016296e-05, + "loss": 0.1899, + "step": 18695 + }, + { + "epoch": 5.77, + "learning_rate": 1.66906370479891e-05, + "loss": 0.1946, + "step": 18696 + }, + { + "epoch": 5.77, + "learning_rate": 1.66902653492274e-05, + "loss": 0.2009, + "step": 18697 + }, + { + "epoch": 5.77, + "learning_rate": 1.668989363373213e-05, + "loss": 0.1982, + "step": 18698 + }, + { + "epoch": 5.77, + "learning_rate": 1.6689521901504214e-05, + "loss": 0.1991, + "step": 18699 + }, + { + "epoch": 5.78, + "learning_rate": 1.6689150152544582e-05, + "loss": 0.185, + "step": 18700 + }, + { + "epoch": 5.78, + "learning_rate": 1.668877838685417e-05, + "loss": 0.183, + "step": 18701 + }, + { + "epoch": 5.78, + "learning_rate": 1.66884066044339e-05, + "loss": 0.1995, + "step": 18702 + }, + { + "epoch": 5.78, + "learning_rate": 1.6688034805284702e-05, + "loss": 0.1906, + "step": 18703 + }, + { + "epoch": 5.78, + "learning_rate": 1.6687662989407512e-05, + "loss": 0.1873, + "step": 18704 + }, + { + "epoch": 5.78, + "learning_rate": 1.6687291156803258e-05, + "loss": 0.1804, + "step": 18705 + }, + { + "epoch": 5.78, + "learning_rate": 1.6686919307472868e-05, + "loss": 0.1893, + "step": 18706 + }, + { + "epoch": 5.78, + "learning_rate": 1.668654744141727e-05, + "loss": 0.1861, + "step": 18707 + }, + { + "epoch": 5.78, + "learning_rate": 1.6686175558637403e-05, + "loss": 0.1881, + "step": 18708 + }, + { + "epoch": 5.78, + "learning_rate": 1.6685803659134192e-05, + "loss": 0.1959, + "step": 18709 + }, + { + "epoch": 5.78, + "learning_rate": 1.6685431742908562e-05, + "loss": 0.1833, + "step": 18710 + }, + { + "epoch": 5.78, + "learning_rate": 1.668505980996145e-05, + "loss": 0.1856, + "step": 18711 + }, + { + "epoch": 5.78, + "learning_rate": 1.6684687860293784e-05, + "loss": 0.1939, + "step": 18712 + }, + { + "epoch": 5.78, + "learning_rate": 1.6684315893906493e-05, + "loss": 0.1844, + "step": 18713 + }, + { + "epoch": 5.78, + "learning_rate": 1.6683943910800514e-05, + "loss": 0.2006, + "step": 18714 + }, + { + "epoch": 5.78, + "learning_rate": 1.6683571910976767e-05, + "loss": 0.1942, + "step": 18715 + }, + { + "epoch": 5.78, + "learning_rate": 1.6683199894436188e-05, + "loss": 0.1877, + "step": 18716 + }, + { + "epoch": 5.78, + "learning_rate": 1.6682827861179708e-05, + "loss": 0.185, + "step": 18717 + }, + { + "epoch": 5.78, + "learning_rate": 1.668245581120826e-05, + "loss": 0.1761, + "step": 18718 + }, + { + "epoch": 5.78, + "learning_rate": 1.6682083744522764e-05, + "loss": 0.1892, + "step": 18719 + }, + { + "epoch": 5.78, + "learning_rate": 1.6681711661124164e-05, + "loss": 0.1821, + "step": 18720 + }, + { + "epoch": 5.78, + "learning_rate": 1.6681339561013383e-05, + "loss": 0.1946, + "step": 18721 + }, + { + "epoch": 5.78, + "learning_rate": 1.668096744419135e-05, + "loss": 0.1835, + "step": 18722 + }, + { + "epoch": 5.78, + "learning_rate": 1.6680595310659004e-05, + "loss": 0.198, + "step": 18723 + }, + { + "epoch": 5.78, + "learning_rate": 1.668022316041727e-05, + "loss": 0.179, + "step": 18724 + }, + { + "epoch": 5.78, + "learning_rate": 1.6679850993467074e-05, + "loss": 0.1932, + "step": 18725 + }, + { + "epoch": 5.78, + "learning_rate": 1.6679478809809358e-05, + "loss": 0.1962, + "step": 18726 + }, + { + "epoch": 5.78, + "learning_rate": 1.6679106609445045e-05, + "loss": 0.1868, + "step": 18727 + }, + { + "epoch": 5.78, + "learning_rate": 1.6678734392375067e-05, + "loss": 0.1905, + "step": 18728 + }, + { + "epoch": 5.78, + "learning_rate": 1.667836215860036e-05, + "loss": 0.1907, + "step": 18729 + }, + { + "epoch": 5.78, + "learning_rate": 1.6677989908121846e-05, + "loss": 0.1823, + "step": 18730 + }, + { + "epoch": 5.78, + "learning_rate": 1.6677617640940464e-05, + "loss": 0.1949, + "step": 18731 + }, + { + "epoch": 5.78, + "learning_rate": 1.6677245357057144e-05, + "loss": 0.1917, + "step": 18732 + }, + { + "epoch": 5.79, + "learning_rate": 1.6676873056472814e-05, + "loss": 0.2059, + "step": 18733 + }, + { + "epoch": 5.79, + "learning_rate": 1.6676500739188406e-05, + "loss": 0.188, + "step": 18734 + }, + { + "epoch": 5.79, + "learning_rate": 1.6676128405204852e-05, + "loss": 0.2025, + "step": 18735 + }, + { + "epoch": 5.79, + "learning_rate": 1.667575605452308e-05, + "loss": 0.1721, + "step": 18736 + }, + { + "epoch": 5.79, + "learning_rate": 1.667538368714403e-05, + "loss": 0.186, + "step": 18737 + }, + { + "epoch": 5.79, + "learning_rate": 1.6675011303068628e-05, + "loss": 0.1718, + "step": 18738 + }, + { + "epoch": 5.79, + "learning_rate": 1.66746389022978e-05, + "loss": 0.1856, + "step": 18739 + }, + { + "epoch": 5.79, + "learning_rate": 1.6674266484832488e-05, + "loss": 0.1866, + "step": 18740 + }, + { + "epoch": 5.79, + "learning_rate": 1.6673894050673617e-05, + "loss": 0.192, + "step": 18741 + }, + { + "epoch": 5.79, + "learning_rate": 1.667352159982212e-05, + "loss": 0.1888, + "step": 18742 + }, + { + "epoch": 5.79, + "learning_rate": 1.667314913227893e-05, + "loss": 0.1727, + "step": 18743 + }, + { + "epoch": 5.79, + "learning_rate": 1.6672776648044967e-05, + "loss": 0.2042, + "step": 18744 + }, + { + "epoch": 5.79, + "learning_rate": 1.667240414712118e-05, + "loss": 0.1749, + "step": 18745 + }, + { + "epoch": 5.79, + "learning_rate": 1.6672031629508497e-05, + "loss": 0.1932, + "step": 18746 + }, + { + "epoch": 5.79, + "learning_rate": 1.667165909520784e-05, + "loss": 0.1809, + "step": 18747 + }, + { + "epoch": 5.79, + "learning_rate": 1.667128654422015e-05, + "loss": 0.1881, + "step": 18748 + }, + { + "epoch": 5.79, + "learning_rate": 1.6670913976546357e-05, + "loss": 0.193, + "step": 18749 + }, + { + "epoch": 5.79, + "learning_rate": 1.6670541392187386e-05, + "loss": 0.1997, + "step": 18750 + }, + { + "epoch": 5.79, + "learning_rate": 1.6670168791144176e-05, + "loss": 0.1997, + "step": 18751 + }, + { + "epoch": 5.79, + "learning_rate": 1.666979617341766e-05, + "loss": 0.1941, + "step": 18752 + }, + { + "epoch": 5.79, + "learning_rate": 1.6669423539008765e-05, + "loss": 0.1798, + "step": 18753 + }, + { + "epoch": 5.79, + "learning_rate": 1.6669050887918427e-05, + "loss": 0.1925, + "step": 18754 + }, + { + "epoch": 5.79, + "learning_rate": 1.6668678220147575e-05, + "loss": 0.1738, + "step": 18755 + }, + { + "epoch": 5.79, + "learning_rate": 1.6668305535697142e-05, + "loss": 0.1874, + "step": 18756 + }, + { + "epoch": 5.79, + "learning_rate": 1.6667932834568062e-05, + "loss": 0.1822, + "step": 18757 + }, + { + "epoch": 5.79, + "learning_rate": 1.6667560116761266e-05, + "loss": 0.2019, + "step": 18758 + }, + { + "epoch": 5.79, + "learning_rate": 1.6667187382277685e-05, + "loss": 0.2039, + "step": 18759 + }, + { + "epoch": 5.79, + "learning_rate": 1.6666814631118255e-05, + "loss": 0.1896, + "step": 18760 + }, + { + "epoch": 5.79, + "learning_rate": 1.6666441863283904e-05, + "loss": 0.1691, + "step": 18761 + }, + { + "epoch": 5.79, + "learning_rate": 1.6666069078775563e-05, + "loss": 0.1911, + "step": 18762 + }, + { + "epoch": 5.79, + "learning_rate": 1.666569627759417e-05, + "loss": 0.1925, + "step": 18763 + }, + { + "epoch": 5.79, + "learning_rate": 1.6665323459740655e-05, + "loss": 0.1858, + "step": 18764 + }, + { + "epoch": 5.8, + "learning_rate": 1.666495062521595e-05, + "loss": 0.1866, + "step": 18765 + }, + { + "epoch": 5.8, + "learning_rate": 1.6664577774020987e-05, + "loss": 0.1801, + "step": 18766 + }, + { + "epoch": 5.8, + "learning_rate": 1.66642049061567e-05, + "loss": 0.1856, + "step": 18767 + }, + { + "epoch": 5.8, + "learning_rate": 1.666383202162402e-05, + "loss": 0.1892, + "step": 18768 + }, + { + "epoch": 5.8, + "learning_rate": 1.6663459120423882e-05, + "loss": 0.1969, + "step": 18769 + }, + { + "epoch": 5.8, + "learning_rate": 1.666308620255722e-05, + "loss": 0.195, + "step": 18770 + }, + { + "epoch": 5.8, + "learning_rate": 1.6662713268024963e-05, + "loss": 0.1825, + "step": 18771 + }, + { + "epoch": 5.8, + "learning_rate": 1.6662340316828043e-05, + "loss": 0.1846, + "step": 18772 + }, + { + "epoch": 5.8, + "learning_rate": 1.6661967348967393e-05, + "loss": 0.1768, + "step": 18773 + }, + { + "epoch": 5.8, + "learning_rate": 1.6661594364443952e-05, + "loss": 0.1833, + "step": 18774 + }, + { + "epoch": 5.8, + "learning_rate": 1.6661221363258648e-05, + "loss": 0.1853, + "step": 18775 + }, + { + "epoch": 5.8, + "learning_rate": 1.6660848345412412e-05, + "loss": 0.1817, + "step": 18776 + }, + { + "epoch": 5.8, + "learning_rate": 1.666047531090618e-05, + "loss": 0.19, + "step": 18777 + }, + { + "epoch": 5.8, + "learning_rate": 1.6660102259740883e-05, + "loss": 0.1973, + "step": 18778 + }, + { + "epoch": 5.8, + "learning_rate": 1.665972919191746e-05, + "loss": 0.1705, + "step": 18779 + }, + { + "epoch": 5.8, + "learning_rate": 1.6659356107436834e-05, + "loss": 0.1956, + "step": 18780 + }, + { + "epoch": 5.8, + "learning_rate": 1.6658983006299948e-05, + "loss": 0.1889, + "step": 18781 + }, + { + "epoch": 5.8, + "learning_rate": 1.6658609888507727e-05, + "loss": 0.1994, + "step": 18782 + }, + { + "epoch": 5.8, + "learning_rate": 1.665823675406111e-05, + "loss": 0.1823, + "step": 18783 + }, + { + "epoch": 5.8, + "learning_rate": 1.6657863602961034e-05, + "loss": 0.1897, + "step": 18784 + }, + { + "epoch": 5.8, + "learning_rate": 1.6657490435208422e-05, + "loss": 0.1826, + "step": 18785 + }, + { + "epoch": 5.8, + "learning_rate": 1.6657117250804213e-05, + "loss": 0.1838, + "step": 18786 + }, + { + "epoch": 5.8, + "learning_rate": 1.6656744049749338e-05, + "loss": 0.1748, + "step": 18787 + }, + { + "epoch": 5.8, + "learning_rate": 1.6656370832044733e-05, + "loss": 0.1884, + "step": 18788 + }, + { + "epoch": 5.8, + "learning_rate": 1.665599759769133e-05, + "loss": 0.1709, + "step": 18789 + }, + { + "epoch": 5.8, + "learning_rate": 1.6655624346690063e-05, + "loss": 0.204, + "step": 18790 + }, + { + "epoch": 5.8, + "learning_rate": 1.6655251079041868e-05, + "loss": 0.2085, + "step": 18791 + }, + { + "epoch": 5.8, + "learning_rate": 1.6654877794747673e-05, + "loss": 0.1782, + "step": 18792 + }, + { + "epoch": 5.8, + "learning_rate": 1.6654504493808413e-05, + "loss": 0.1814, + "step": 18793 + }, + { + "epoch": 5.8, + "learning_rate": 1.665413117622503e-05, + "loss": 0.1946, + "step": 18794 + }, + { + "epoch": 5.8, + "learning_rate": 1.6653757841998446e-05, + "loss": 0.1977, + "step": 18795 + }, + { + "epoch": 5.8, + "learning_rate": 1.6653384491129606e-05, + "loss": 0.2081, + "step": 18796 + }, + { + "epoch": 5.8, + "learning_rate": 1.6653011123619432e-05, + "loss": 0.1922, + "step": 18797 + }, + { + "epoch": 5.81, + "learning_rate": 1.6652637739468865e-05, + "loss": 0.2013, + "step": 18798 + }, + { + "epoch": 5.81, + "learning_rate": 1.6652264338678837e-05, + "loss": 0.1844, + "step": 18799 + }, + { + "epoch": 5.81, + "learning_rate": 1.6651890921250284e-05, + "loss": 0.189, + "step": 18800 + }, + { + "epoch": 5.81, + "learning_rate": 1.665151748718414e-05, + "loss": 0.2003, + "step": 18801 + }, + { + "epoch": 5.81, + "learning_rate": 1.6651144036481337e-05, + "loss": 0.189, + "step": 18802 + }, + { + "epoch": 5.81, + "learning_rate": 1.6650770569142807e-05, + "loss": 0.1981, + "step": 18803 + }, + { + "epoch": 5.81, + "learning_rate": 1.665039708516949e-05, + "loss": 0.1843, + "step": 18804 + }, + { + "epoch": 5.81, + "learning_rate": 1.6650023584562314e-05, + "loss": 0.1839, + "step": 18805 + }, + { + "epoch": 5.81, + "learning_rate": 1.6649650067322217e-05, + "loss": 0.2039, + "step": 18806 + }, + { + "epoch": 5.81, + "learning_rate": 1.6649276533450133e-05, + "loss": 0.1852, + "step": 18807 + }, + { + "epoch": 5.81, + "learning_rate": 1.6648902982946998e-05, + "loss": 0.2023, + "step": 18808 + }, + { + "epoch": 5.81, + "learning_rate": 1.664852941581374e-05, + "loss": 0.1946, + "step": 18809 + }, + { + "epoch": 5.81, + "learning_rate": 1.66481558320513e-05, + "loss": 0.185, + "step": 18810 + }, + { + "epoch": 5.81, + "learning_rate": 1.6647782231660608e-05, + "loss": 0.189, + "step": 18811 + }, + { + "epoch": 5.81, + "learning_rate": 1.66474086146426e-05, + "loss": 0.1884, + "step": 18812 + }, + { + "epoch": 5.81, + "learning_rate": 1.6647034980998213e-05, + "loss": 0.1846, + "step": 18813 + }, + { + "epoch": 5.81, + "learning_rate": 1.664666133072838e-05, + "loss": 0.205, + "step": 18814 + }, + { + "epoch": 5.81, + "learning_rate": 1.664628766383403e-05, + "loss": 0.1847, + "step": 18815 + }, + { + "epoch": 5.81, + "learning_rate": 1.66459139803161e-05, + "loss": 0.1902, + "step": 18816 + }, + { + "epoch": 5.81, + "learning_rate": 1.6645540280175535e-05, + "loss": 0.1988, + "step": 18817 + }, + { + "epoch": 5.81, + "learning_rate": 1.6645166563413257e-05, + "loss": 0.211, + "step": 18818 + }, + { + "epoch": 5.81, + "learning_rate": 1.6644792830030206e-05, + "loss": 0.1914, + "step": 18819 + }, + { + "epoch": 5.81, + "learning_rate": 1.664441908002732e-05, + "loss": 0.1867, + "step": 18820 + }, + { + "epoch": 5.81, + "learning_rate": 1.6644045313405526e-05, + "loss": 0.1919, + "step": 18821 + }, + { + "epoch": 5.81, + "learning_rate": 1.6643671530165764e-05, + "loss": 0.1827, + "step": 18822 + }, + { + "epoch": 5.81, + "learning_rate": 1.6643297730308967e-05, + "loss": 0.1908, + "step": 18823 + }, + { + "epoch": 5.81, + "learning_rate": 1.664292391383607e-05, + "loss": 0.1785, + "step": 18824 + }, + { + "epoch": 5.81, + "learning_rate": 1.6642550080748012e-05, + "loss": 0.1904, + "step": 18825 + }, + { + "epoch": 5.81, + "learning_rate": 1.6642176231045725e-05, + "loss": 0.1943, + "step": 18826 + }, + { + "epoch": 5.81, + "learning_rate": 1.664180236473014e-05, + "loss": 0.1871, + "step": 18827 + }, + { + "epoch": 5.81, + "learning_rate": 1.6641428481802196e-05, + "loss": 0.1786, + "step": 18828 + }, + { + "epoch": 5.81, + "learning_rate": 1.664105458226283e-05, + "loss": 0.1988, + "step": 18829 + }, + { + "epoch": 5.82, + "learning_rate": 1.6640680666112974e-05, + "loss": 0.1844, + "step": 18830 + }, + { + "epoch": 5.82, + "learning_rate": 1.6640306733353567e-05, + "loss": 0.1732, + "step": 18831 + }, + { + "epoch": 5.82, + "learning_rate": 1.6639932783985538e-05, + "loss": 0.192, + "step": 18832 + }, + { + "epoch": 5.82, + "learning_rate": 1.6639558818009832e-05, + "loss": 0.1781, + "step": 18833 + }, + { + "epoch": 5.82, + "learning_rate": 1.663918483542737e-05, + "loss": 0.1797, + "step": 18834 + }, + { + "epoch": 5.82, + "learning_rate": 1.66388108362391e-05, + "loss": 0.1876, + "step": 18835 + }, + { + "epoch": 5.82, + "learning_rate": 1.6638436820445957e-05, + "loss": 0.1963, + "step": 18836 + }, + { + "epoch": 5.82, + "learning_rate": 1.6638062788048865e-05, + "loss": 0.1889, + "step": 18837 + }, + { + "epoch": 5.82, + "learning_rate": 1.6637688739048775e-05, + "loss": 0.1896, + "step": 18838 + }, + { + "epoch": 5.82, + "learning_rate": 1.6637314673446612e-05, + "loss": 0.1685, + "step": 18839 + }, + { + "epoch": 5.82, + "learning_rate": 1.663694059124331e-05, + "loss": 0.2021, + "step": 18840 + }, + { + "epoch": 5.82, + "learning_rate": 1.6636566492439815e-05, + "loss": 0.1952, + "step": 18841 + }, + { + "epoch": 5.82, + "learning_rate": 1.6636192377037055e-05, + "loss": 0.2165, + "step": 18842 + }, + { + "epoch": 5.82, + "learning_rate": 1.6635818245035966e-05, + "loss": 0.2068, + "step": 18843 + }, + { + "epoch": 5.82, + "learning_rate": 1.6635444096437486e-05, + "loss": 0.202, + "step": 18844 + }, + { + "epoch": 5.82, + "learning_rate": 1.6635069931242552e-05, + "loss": 0.1925, + "step": 18845 + }, + { + "epoch": 5.82, + "learning_rate": 1.6634695749452094e-05, + "loss": 0.1934, + "step": 18846 + }, + { + "epoch": 5.82, + "learning_rate": 1.6634321551067057e-05, + "loss": 0.1949, + "step": 18847 + }, + { + "epoch": 5.82, + "learning_rate": 1.6633947336088367e-05, + "loss": 0.1941, + "step": 18848 + }, + { + "epoch": 5.82, + "learning_rate": 1.6633573104516966e-05, + "loss": 0.1875, + "step": 18849 + }, + { + "epoch": 5.82, + "learning_rate": 1.663319885635379e-05, + "loss": 0.1971, + "step": 18850 + }, + { + "epoch": 5.82, + "learning_rate": 1.6632824591599774e-05, + "loss": 0.1738, + "step": 18851 + }, + { + "epoch": 5.82, + "learning_rate": 1.6632450310255853e-05, + "loss": 0.1822, + "step": 18852 + }, + { + "epoch": 5.82, + "learning_rate": 1.6632076012322965e-05, + "loss": 0.19, + "step": 18853 + }, + { + "epoch": 5.82, + "learning_rate": 1.6631701697802044e-05, + "loss": 0.1865, + "step": 18854 + }, + { + "epoch": 5.82, + "learning_rate": 1.663132736669403e-05, + "loss": 0.1867, + "step": 18855 + }, + { + "epoch": 5.82, + "learning_rate": 1.6630953018999852e-05, + "loss": 0.1891, + "step": 18856 + }, + { + "epoch": 5.82, + "learning_rate": 1.6630578654720455e-05, + "loss": 0.1781, + "step": 18857 + }, + { + "epoch": 5.82, + "learning_rate": 1.6630204273856773e-05, + "loss": 0.1743, + "step": 18858 + }, + { + "epoch": 5.82, + "learning_rate": 1.6629829876409734e-05, + "loss": 0.182, + "step": 18859 + }, + { + "epoch": 5.82, + "learning_rate": 1.6629455462380288e-05, + "loss": 0.1891, + "step": 18860 + }, + { + "epoch": 5.82, + "learning_rate": 1.6629081031769364e-05, + "loss": 0.1928, + "step": 18861 + }, + { + "epoch": 5.83, + "learning_rate": 1.6628706584577897e-05, + "loss": 0.1967, + "step": 18862 + }, + { + "epoch": 5.83, + "learning_rate": 1.6628332120806826e-05, + "loss": 0.1753, + "step": 18863 + }, + { + "epoch": 5.83, + "learning_rate": 1.6627957640457085e-05, + "loss": 0.1792, + "step": 18864 + }, + { + "epoch": 5.83, + "learning_rate": 1.6627583143529618e-05, + "loss": 0.2127, + "step": 18865 + }, + { + "epoch": 5.83, + "learning_rate": 1.6627208630025357e-05, + "loss": 0.1829, + "step": 18866 + }, + { + "epoch": 5.83, + "learning_rate": 1.6626834099945234e-05, + "loss": 0.1884, + "step": 18867 + }, + { + "epoch": 5.83, + "learning_rate": 1.662645955329019e-05, + "loss": 0.1812, + "step": 18868 + }, + { + "epoch": 5.83, + "learning_rate": 1.6626084990061165e-05, + "loss": 0.1947, + "step": 18869 + }, + { + "epoch": 5.83, + "learning_rate": 1.6625710410259097e-05, + "loss": 0.1797, + "step": 18870 + }, + { + "epoch": 5.83, + "learning_rate": 1.662533581388491e-05, + "loss": 0.1953, + "step": 18871 + }, + { + "epoch": 5.83, + "learning_rate": 1.6624961200939557e-05, + "loss": 0.1961, + "step": 18872 + }, + { + "epoch": 5.83, + "learning_rate": 1.6624586571423963e-05, + "loss": 0.1869, + "step": 18873 + }, + { + "epoch": 5.83, + "learning_rate": 1.6624211925339072e-05, + "loss": 0.1895, + "step": 18874 + }, + { + "epoch": 5.83, + "learning_rate": 1.6623837262685818e-05, + "loss": 0.1824, + "step": 18875 + }, + { + "epoch": 5.83, + "learning_rate": 1.662346258346514e-05, + "loss": 0.2128, + "step": 18876 + }, + { + "epoch": 5.83, + "learning_rate": 1.6623087887677974e-05, + "loss": 0.1748, + "step": 18877 + }, + { + "epoch": 5.83, + "learning_rate": 1.6622713175325257e-05, + "loss": 0.1731, + "step": 18878 + }, + { + "epoch": 5.83, + "learning_rate": 1.6622338446407924e-05, + "loss": 0.1788, + "step": 18879 + }, + { + "epoch": 5.83, + "learning_rate": 1.6621963700926916e-05, + "loss": 0.2002, + "step": 18880 + }, + { + "epoch": 5.83, + "learning_rate": 1.662158893888317e-05, + "loss": 0.1862, + "step": 18881 + }, + { + "epoch": 5.83, + "learning_rate": 1.6621214160277622e-05, + "loss": 0.1844, + "step": 18882 + }, + { + "epoch": 5.83, + "learning_rate": 1.662083936511121e-05, + "loss": 0.2118, + "step": 18883 + }, + { + "epoch": 5.83, + "learning_rate": 1.6620464553384872e-05, + "loss": 0.1859, + "step": 18884 + }, + { + "epoch": 5.83, + "learning_rate": 1.6620089725099543e-05, + "loss": 0.1834, + "step": 18885 + }, + { + "epoch": 5.83, + "learning_rate": 1.6619714880256162e-05, + "loss": 0.1897, + "step": 18886 + }, + { + "epoch": 5.83, + "learning_rate": 1.6619340018855666e-05, + "loss": 0.2011, + "step": 18887 + }, + { + "epoch": 5.83, + "learning_rate": 1.6618965140898997e-05, + "loss": 0.188, + "step": 18888 + }, + { + "epoch": 5.83, + "learning_rate": 1.6618590246387085e-05, + "loss": 0.1929, + "step": 18889 + }, + { + "epoch": 5.83, + "learning_rate": 1.6618215335320873e-05, + "loss": 0.1809, + "step": 18890 + }, + { + "epoch": 5.83, + "learning_rate": 1.66178404077013e-05, + "loss": 0.1769, + "step": 18891 + }, + { + "epoch": 5.83, + "learning_rate": 1.6617465463529296e-05, + "loss": 0.2009, + "step": 18892 + }, + { + "epoch": 5.83, + "learning_rate": 1.6617090502805808e-05, + "loss": 0.1923, + "step": 18893 + }, + { + "epoch": 5.83, + "learning_rate": 1.6616715525531767e-05, + "loss": 0.2032, + "step": 18894 + }, + { + "epoch": 5.84, + "learning_rate": 1.661634053170812e-05, + "loss": 0.1874, + "step": 18895 + }, + { + "epoch": 5.84, + "learning_rate": 1.661596552133579e-05, + "loss": 0.1889, + "step": 18896 + }, + { + "epoch": 5.84, + "learning_rate": 1.6615590494415727e-05, + "loss": 0.2023, + "step": 18897 + }, + { + "epoch": 5.84, + "learning_rate": 1.6615215450948866e-05, + "loss": 0.1842, + "step": 18898 + }, + { + "epoch": 5.84, + "learning_rate": 1.6614840390936146e-05, + "loss": 0.1745, + "step": 18899 + }, + { + "epoch": 5.84, + "learning_rate": 1.66144653143785e-05, + "loss": 0.1784, + "step": 18900 + }, + { + "epoch": 5.84, + "learning_rate": 1.661409022127687e-05, + "loss": 0.1677, + "step": 18901 + }, + { + "epoch": 5.84, + "learning_rate": 1.6613715111632198e-05, + "loss": 0.1961, + "step": 18902 + }, + { + "epoch": 5.84, + "learning_rate": 1.6613339985445418e-05, + "loss": 0.1875, + "step": 18903 + }, + { + "epoch": 5.84, + "learning_rate": 1.6612964842717463e-05, + "loss": 0.1777, + "step": 18904 + }, + { + "epoch": 5.84, + "learning_rate": 1.6612589683449283e-05, + "loss": 0.1843, + "step": 18905 + }, + { + "epoch": 5.84, + "learning_rate": 1.661221450764181e-05, + "loss": 0.1993, + "step": 18906 + }, + { + "epoch": 5.84, + "learning_rate": 1.661183931529598e-05, + "loss": 0.1928, + "step": 18907 + }, + { + "epoch": 5.84, + "learning_rate": 1.6611464106412732e-05, + "loss": 0.1711, + "step": 18908 + }, + { + "epoch": 5.84, + "learning_rate": 1.661108888099301e-05, + "loss": 0.1868, + "step": 18909 + }, + { + "epoch": 5.84, + "learning_rate": 1.6610713639037748e-05, + "loss": 0.1865, + "step": 18910 + }, + { + "epoch": 5.84, + "learning_rate": 1.6610338380547885e-05, + "loss": 0.1867, + "step": 18911 + }, + { + "epoch": 5.84, + "learning_rate": 1.6609963105524358e-05, + "loss": 0.2055, + "step": 18912 + }, + { + "epoch": 5.84, + "learning_rate": 1.6609587813968114e-05, + "loss": 0.1799, + "step": 18913 + }, + { + "epoch": 5.84, + "learning_rate": 1.660921250588008e-05, + "loss": 0.1706, + "step": 18914 + }, + { + "epoch": 5.84, + "learning_rate": 1.66088371812612e-05, + "loss": 0.1912, + "step": 18915 + }, + { + "epoch": 5.84, + "learning_rate": 1.6608461840112412e-05, + "loss": 0.1926, + "step": 18916 + }, + { + "epoch": 5.84, + "learning_rate": 1.660808648243466e-05, + "loss": 0.1957, + "step": 18917 + }, + { + "epoch": 5.84, + "learning_rate": 1.6607711108228873e-05, + "loss": 0.2045, + "step": 18918 + }, + { + "epoch": 5.84, + "learning_rate": 1.6607335717496e-05, + "loss": 0.2013, + "step": 18919 + }, + { + "epoch": 5.84, + "learning_rate": 1.6606960310236973e-05, + "loss": 0.1958, + "step": 18920 + }, + { + "epoch": 5.84, + "learning_rate": 1.6606584886452733e-05, + "loss": 0.1819, + "step": 18921 + }, + { + "epoch": 5.84, + "learning_rate": 1.6606209446144222e-05, + "loss": 0.1821, + "step": 18922 + }, + { + "epoch": 5.84, + "learning_rate": 1.6605833989312375e-05, + "loss": 0.1986, + "step": 18923 + }, + { + "epoch": 5.84, + "learning_rate": 1.660545851595813e-05, + "loss": 0.1895, + "step": 18924 + }, + { + "epoch": 5.84, + "learning_rate": 1.6605083026082433e-05, + "loss": 0.198, + "step": 18925 + }, + { + "epoch": 5.84, + "learning_rate": 1.6604707519686216e-05, + "loss": 0.1974, + "step": 18926 + }, + { + "epoch": 5.85, + "learning_rate": 1.660433199677042e-05, + "loss": 0.1917, + "step": 18927 + }, + { + "epoch": 5.85, + "learning_rate": 1.6603956457335987e-05, + "loss": 0.1733, + "step": 18928 + }, + { + "epoch": 5.85, + "learning_rate": 1.6603580901383853e-05, + "loss": 0.1899, + "step": 18929 + }, + { + "epoch": 5.85, + "learning_rate": 1.660320532891496e-05, + "loss": 0.195, + "step": 18930 + }, + { + "epoch": 5.85, + "learning_rate": 1.660282973993024e-05, + "loss": 0.1806, + "step": 18931 + }, + { + "epoch": 5.85, + "learning_rate": 1.6602454134430647e-05, + "loss": 0.1903, + "step": 18932 + }, + { + "epoch": 5.85, + "learning_rate": 1.660207851241711e-05, + "loss": 0.1784, + "step": 18933 + }, + { + "epoch": 5.85, + "learning_rate": 1.660170287389057e-05, + "loss": 0.1958, + "step": 18934 + }, + { + "epoch": 5.85, + "learning_rate": 1.6601327218851965e-05, + "loss": 0.182, + "step": 18935 + }, + { + "epoch": 5.85, + "learning_rate": 1.6600951547302236e-05, + "loss": 0.1835, + "step": 18936 + }, + { + "epoch": 5.85, + "learning_rate": 1.6600575859242327e-05, + "loss": 0.1838, + "step": 18937 + }, + { + "epoch": 5.85, + "learning_rate": 1.660020015467317e-05, + "loss": 0.1646, + "step": 18938 + }, + { + "epoch": 5.85, + "learning_rate": 1.6599824433595714e-05, + "loss": 0.1853, + "step": 18939 + }, + { + "epoch": 5.85, + "learning_rate": 1.659944869601089e-05, + "loss": 0.1865, + "step": 18940 + }, + { + "epoch": 5.85, + "learning_rate": 1.659907294191964e-05, + "loss": 0.1816, + "step": 18941 + }, + { + "epoch": 5.85, + "learning_rate": 1.6598697171322906e-05, + "loss": 0.1718, + "step": 18942 + }, + { + "epoch": 5.85, + "learning_rate": 1.6598321384221627e-05, + "loss": 0.1965, + "step": 18943 + }, + { + "epoch": 5.85, + "learning_rate": 1.6597945580616744e-05, + "loss": 0.18, + "step": 18944 + }, + { + "epoch": 5.85, + "learning_rate": 1.6597569760509193e-05, + "loss": 0.1895, + "step": 18945 + }, + { + "epoch": 5.85, + "learning_rate": 1.659719392389992e-05, + "loss": 0.2022, + "step": 18946 + }, + { + "epoch": 5.85, + "learning_rate": 1.659681807078986e-05, + "loss": 0.1995, + "step": 18947 + }, + { + "epoch": 5.85, + "learning_rate": 1.659644220117995e-05, + "loss": 0.185, + "step": 18948 + }, + { + "epoch": 5.85, + "learning_rate": 1.6596066315071146e-05, + "loss": 0.1749, + "step": 18949 + }, + { + "epoch": 5.85, + "learning_rate": 1.6595690412464368e-05, + "loss": 0.184, + "step": 18950 + }, + { + "epoch": 5.85, + "learning_rate": 1.659531449336057e-05, + "loss": 0.2084, + "step": 18951 + }, + { + "epoch": 5.85, + "learning_rate": 1.6594938557760686e-05, + "loss": 0.1903, + "step": 18952 + }, + { + "epoch": 5.85, + "learning_rate": 1.6594562605665655e-05, + "loss": 0.1824, + "step": 18953 + }, + { + "epoch": 5.85, + "learning_rate": 1.6594186637076424e-05, + "loss": 0.1869, + "step": 18954 + }, + { + "epoch": 5.85, + "learning_rate": 1.659381065199393e-05, + "loss": 0.1812, + "step": 18955 + }, + { + "epoch": 5.85, + "learning_rate": 1.6593434650419106e-05, + "loss": 0.2067, + "step": 18956 + }, + { + "epoch": 5.85, + "learning_rate": 1.6593058632352908e-05, + "loss": 0.2092, + "step": 18957 + }, + { + "epoch": 5.85, + "learning_rate": 1.6592682597796262e-05, + "loss": 0.1872, + "step": 18958 + }, + { + "epoch": 5.85, + "learning_rate": 1.6592306546750118e-05, + "loss": 0.1842, + "step": 18959 + }, + { + "epoch": 5.86, + "learning_rate": 1.6591930479215414e-05, + "loss": 0.1949, + "step": 18960 + }, + { + "epoch": 5.86, + "learning_rate": 1.6591554395193084e-05, + "loss": 0.1994, + "step": 18961 + }, + { + "epoch": 5.86, + "learning_rate": 1.6591178294684078e-05, + "loss": 0.192, + "step": 18962 + }, + { + "epoch": 5.86, + "learning_rate": 1.6590802177689334e-05, + "loss": 0.1955, + "step": 18963 + }, + { + "epoch": 5.86, + "learning_rate": 1.6590426044209788e-05, + "loss": 0.1887, + "step": 18964 + }, + { + "epoch": 5.86, + "learning_rate": 1.6590049894246387e-05, + "loss": 0.2024, + "step": 18965 + }, + { + "epoch": 5.86, + "learning_rate": 1.658967372780007e-05, + "loss": 0.1939, + "step": 18966 + }, + { + "epoch": 5.86, + "learning_rate": 1.6589297544871774e-05, + "loss": 0.2138, + "step": 18967 + }, + { + "epoch": 5.86, + "learning_rate": 1.658892134546245e-05, + "loss": 0.1952, + "step": 18968 + }, + { + "epoch": 5.86, + "learning_rate": 1.6588545129573024e-05, + "loss": 0.1821, + "step": 18969 + }, + { + "epoch": 5.86, + "learning_rate": 1.6588168897204447e-05, + "loss": 0.1881, + "step": 18970 + }, + { + "epoch": 5.86, + "learning_rate": 1.6587792648357658e-05, + "loss": 0.1788, + "step": 18971 + }, + { + "epoch": 5.86, + "learning_rate": 1.65874163830336e-05, + "loss": 0.1939, + "step": 18972 + }, + { + "epoch": 5.86, + "learning_rate": 1.6587040101233212e-05, + "loss": 0.202, + "step": 18973 + }, + { + "epoch": 5.86, + "learning_rate": 1.6586663802957432e-05, + "loss": 0.1881, + "step": 18974 + }, + { + "epoch": 5.86, + "learning_rate": 1.6586287488207207e-05, + "loss": 0.1724, + "step": 18975 + }, + { + "epoch": 5.86, + "learning_rate": 1.6585911156983476e-05, + "loss": 0.197, + "step": 18976 + }, + { + "epoch": 5.86, + "learning_rate": 1.658553480928718e-05, + "loss": 0.187, + "step": 18977 + }, + { + "epoch": 5.86, + "learning_rate": 1.658515844511926e-05, + "loss": 0.185, + "step": 18978 + }, + { + "epoch": 5.86, + "learning_rate": 1.6584782064480656e-05, + "loss": 0.1702, + "step": 18979 + }, + { + "epoch": 5.86, + "learning_rate": 1.6584405667372313e-05, + "loss": 0.1821, + "step": 18980 + }, + { + "epoch": 5.86, + "learning_rate": 1.658402925379517e-05, + "loss": 0.1925, + "step": 18981 + }, + { + "epoch": 5.86, + "learning_rate": 1.658365282375017e-05, + "loss": 0.1689, + "step": 18982 + }, + { + "epoch": 5.86, + "learning_rate": 1.6583276377238255e-05, + "loss": 0.1791, + "step": 18983 + }, + { + "epoch": 5.86, + "learning_rate": 1.658289991426036e-05, + "loss": 0.177, + "step": 18984 + }, + { + "epoch": 5.86, + "learning_rate": 1.6582523434817434e-05, + "loss": 0.1769, + "step": 18985 + }, + { + "epoch": 5.86, + "learning_rate": 1.658214693891042e-05, + "loss": 0.192, + "step": 18986 + }, + { + "epoch": 5.86, + "learning_rate": 1.658177042654025e-05, + "loss": 0.1969, + "step": 18987 + }, + { + "epoch": 5.86, + "learning_rate": 1.6581393897707877e-05, + "loss": 0.1884, + "step": 18988 + }, + { + "epoch": 5.86, + "learning_rate": 1.6581017352414233e-05, + "loss": 0.1907, + "step": 18989 + }, + { + "epoch": 5.86, + "learning_rate": 1.6580640790660266e-05, + "loss": 0.1894, + "step": 18990 + }, + { + "epoch": 5.86, + "learning_rate": 1.6580264212446918e-05, + "loss": 0.1889, + "step": 18991 + }, + { + "epoch": 5.87, + "learning_rate": 1.6579887617775126e-05, + "loss": 0.185, + "step": 18992 + }, + { + "epoch": 5.87, + "learning_rate": 1.6579511006645837e-05, + "loss": 0.1882, + "step": 18993 + }, + { + "epoch": 5.87, + "learning_rate": 1.6579134379059988e-05, + "loss": 0.189, + "step": 18994 + }, + { + "epoch": 5.87, + "learning_rate": 1.6578757735018526e-05, + "loss": 0.1889, + "step": 18995 + }, + { + "epoch": 5.87, + "learning_rate": 1.657838107452239e-05, + "loss": 0.1837, + "step": 18996 + }, + { + "epoch": 5.87, + "learning_rate": 1.6578004397572526e-05, + "loss": 0.1955, + "step": 18997 + }, + { + "epoch": 5.87, + "learning_rate": 1.6577627704169872e-05, + "loss": 0.1834, + "step": 18998 + }, + { + "epoch": 5.87, + "learning_rate": 1.657725099431537e-05, + "loss": 0.1918, + "step": 18999 + }, + { + "epoch": 5.87, + "learning_rate": 1.6576874268009965e-05, + "loss": 0.1813, + "step": 19000 + }, + { + "epoch": 5.87, + "learning_rate": 1.65764975252546e-05, + "loss": 0.189, + "step": 19001 + }, + { + "epoch": 5.87, + "learning_rate": 1.657612076605021e-05, + "loss": 0.1725, + "step": 19002 + }, + { + "epoch": 5.87, + "learning_rate": 1.6575743990397748e-05, + "loss": 0.1846, + "step": 19003 + }, + { + "epoch": 5.87, + "learning_rate": 1.657536719829815e-05, + "loss": 0.1923, + "step": 19004 + }, + { + "epoch": 5.87, + "learning_rate": 1.6574990389752354e-05, + "loss": 0.168, + "step": 19005 + }, + { + "epoch": 5.87, + "learning_rate": 1.6574613564761313e-05, + "loss": 0.1847, + "step": 19006 + }, + { + "epoch": 5.87, + "learning_rate": 1.657423672332596e-05, + "loss": 0.2036, + "step": 19007 + }, + { + "epoch": 5.87, + "learning_rate": 1.657385986544725e-05, + "loss": 0.2197, + "step": 19008 + }, + { + "epoch": 5.87, + "learning_rate": 1.657348299112611e-05, + "loss": 0.1739, + "step": 19009 + }, + { + "epoch": 5.87, + "learning_rate": 1.657310610036349e-05, + "loss": 0.1916, + "step": 19010 + }, + { + "epoch": 5.87, + "learning_rate": 1.657272919316034e-05, + "loss": 0.1896, + "step": 19011 + }, + { + "epoch": 5.87, + "learning_rate": 1.657235226951759e-05, + "loss": 0.19, + "step": 19012 + }, + { + "epoch": 5.87, + "learning_rate": 1.6571975329436187e-05, + "loss": 0.1752, + "step": 19013 + }, + { + "epoch": 5.87, + "learning_rate": 1.6571598372917077e-05, + "loss": 0.1985, + "step": 19014 + }, + { + "epoch": 5.87, + "learning_rate": 1.6571221399961198e-05, + "loss": 0.1884, + "step": 19015 + }, + { + "epoch": 5.87, + "learning_rate": 1.65708444105695e-05, + "loss": 0.1911, + "step": 19016 + }, + { + "epoch": 5.87, + "learning_rate": 1.657046740474292e-05, + "loss": 0.1885, + "step": 19017 + }, + { + "epoch": 5.87, + "learning_rate": 1.65700903824824e-05, + "loss": 0.197, + "step": 19018 + }, + { + "epoch": 5.87, + "learning_rate": 1.656971334378889e-05, + "loss": 0.199, + "step": 19019 + }, + { + "epoch": 5.87, + "learning_rate": 1.656933628866333e-05, + "loss": 0.1805, + "step": 19020 + }, + { + "epoch": 5.87, + "learning_rate": 1.6568959217106658e-05, + "loss": 0.183, + "step": 19021 + }, + { + "epoch": 5.87, + "learning_rate": 1.6568582129119822e-05, + "loss": 0.1667, + "step": 19022 + }, + { + "epoch": 5.87, + "learning_rate": 1.6568205024703762e-05, + "loss": 0.1784, + "step": 19023 + }, + { + "epoch": 5.88, + "learning_rate": 1.6567827903859427e-05, + "loss": 0.1831, + "step": 19024 + }, + { + "epoch": 5.88, + "learning_rate": 1.6567450766587755e-05, + "loss": 0.1814, + "step": 19025 + }, + { + "epoch": 5.88, + "learning_rate": 1.6567073612889692e-05, + "loss": 0.1983, + "step": 19026 + }, + { + "epoch": 5.88, + "learning_rate": 1.6566696442766176e-05, + "loss": 0.1906, + "step": 19027 + }, + { + "epoch": 5.88, + "learning_rate": 1.656631925621816e-05, + "loss": 0.18, + "step": 19028 + }, + { + "epoch": 5.88, + "learning_rate": 1.656594205324658e-05, + "loss": 0.1878, + "step": 19029 + }, + { + "epoch": 5.88, + "learning_rate": 1.656556483385238e-05, + "loss": 0.1877, + "step": 19030 + }, + { + "epoch": 5.88, + "learning_rate": 1.6565187598036506e-05, + "loss": 0.1997, + "step": 19031 + }, + { + "epoch": 5.88, + "learning_rate": 1.6564810345799895e-05, + "loss": 0.1908, + "step": 19032 + }, + { + "epoch": 5.88, + "learning_rate": 1.6564433077143502e-05, + "loss": 0.1908, + "step": 19033 + }, + { + "epoch": 5.88, + "learning_rate": 1.6564055792068264e-05, + "loss": 0.1929, + "step": 19034 + }, + { + "epoch": 5.88, + "learning_rate": 1.6563678490575125e-05, + "loss": 0.182, + "step": 19035 + }, + { + "epoch": 5.88, + "learning_rate": 1.656330117266503e-05, + "loss": 0.1901, + "step": 19036 + }, + { + "epoch": 5.88, + "learning_rate": 1.656292383833892e-05, + "loss": 0.1853, + "step": 19037 + }, + { + "epoch": 5.88, + "learning_rate": 1.6562546487597737e-05, + "loss": 0.1856, + "step": 19038 + }, + { + "epoch": 5.88, + "learning_rate": 1.6562169120442434e-05, + "loss": 0.1839, + "step": 19039 + }, + { + "epoch": 5.88, + "learning_rate": 1.6561791736873947e-05, + "loss": 0.1922, + "step": 19040 + }, + { + "epoch": 5.88, + "learning_rate": 1.656141433689322e-05, + "loss": 0.1914, + "step": 19041 + }, + { + "epoch": 5.88, + "learning_rate": 1.65610369205012e-05, + "loss": 0.1825, + "step": 19042 + }, + { + "epoch": 5.88, + "learning_rate": 1.6560659487698837e-05, + "loss": 0.1986, + "step": 19043 + }, + { + "epoch": 5.88, + "learning_rate": 1.656028203848706e-05, + "loss": 0.1817, + "step": 19044 + }, + { + "epoch": 5.88, + "learning_rate": 1.6559904572866822e-05, + "loss": 0.1878, + "step": 19045 + }, + { + "epoch": 5.88, + "learning_rate": 1.655952709083907e-05, + "loss": 0.1814, + "step": 19046 + }, + { + "epoch": 5.88, + "learning_rate": 1.655914959240474e-05, + "loss": 0.1968, + "step": 19047 + }, + { + "epoch": 5.88, + "learning_rate": 1.6558772077564784e-05, + "loss": 0.1851, + "step": 19048 + }, + { + "epoch": 5.88, + "learning_rate": 1.655839454632014e-05, + "loss": 0.1995, + "step": 19049 + }, + { + "epoch": 5.88, + "learning_rate": 1.6558016998671757e-05, + "loss": 0.2007, + "step": 19050 + }, + { + "epoch": 5.88, + "learning_rate": 1.655763943462058e-05, + "loss": 0.198, + "step": 19051 + }, + { + "epoch": 5.88, + "learning_rate": 1.6557261854167545e-05, + "loss": 0.1888, + "step": 19052 + }, + { + "epoch": 5.88, + "learning_rate": 1.6556884257313604e-05, + "loss": 0.1934, + "step": 19053 + }, + { + "epoch": 5.88, + "learning_rate": 1.65565066440597e-05, + "loss": 0.1909, + "step": 19054 + }, + { + "epoch": 5.88, + "learning_rate": 1.6556129014406775e-05, + "loss": 0.1931, + "step": 19055 + }, + { + "epoch": 5.88, + "learning_rate": 1.6555751368355778e-05, + "loss": 0.1877, + "step": 19056 + }, + { + "epoch": 5.89, + "learning_rate": 1.6555373705907653e-05, + "loss": 0.1942, + "step": 19057 + }, + { + "epoch": 5.89, + "learning_rate": 1.6554996027063342e-05, + "loss": 0.1931, + "step": 19058 + }, + { + "epoch": 5.89, + "learning_rate": 1.6554618331823787e-05, + "loss": 0.1859, + "step": 19059 + }, + { + "epoch": 5.89, + "learning_rate": 1.655424062018994e-05, + "loss": 0.1886, + "step": 19060 + }, + { + "epoch": 5.89, + "learning_rate": 1.6553862892162738e-05, + "loss": 0.1822, + "step": 19061 + }, + { + "epoch": 5.89, + "learning_rate": 1.655348514774313e-05, + "loss": 0.2052, + "step": 19062 + }, + { + "epoch": 5.89, + "learning_rate": 1.6553107386932065e-05, + "loss": 0.1951, + "step": 19063 + }, + { + "epoch": 5.89, + "learning_rate": 1.6552729609730478e-05, + "loss": 0.1851, + "step": 19064 + }, + { + "epoch": 5.89, + "learning_rate": 1.655235181613932e-05, + "loss": 0.182, + "step": 19065 + }, + { + "epoch": 5.89, + "learning_rate": 1.6551974006159538e-05, + "loss": 0.2059, + "step": 19066 + }, + { + "epoch": 5.89, + "learning_rate": 1.6551596179792072e-05, + "loss": 0.187, + "step": 19067 + }, + { + "epoch": 5.89, + "learning_rate": 1.655121833703787e-05, + "loss": 0.1863, + "step": 19068 + }, + { + "epoch": 5.89, + "learning_rate": 1.6550840477897873e-05, + "loss": 0.1943, + "step": 19069 + }, + { + "epoch": 5.89, + "learning_rate": 1.6550462602373033e-05, + "loss": 0.1933, + "step": 19070 + }, + { + "epoch": 5.89, + "learning_rate": 1.6550084710464293e-05, + "loss": 0.2026, + "step": 19071 + }, + { + "epoch": 5.89, + "learning_rate": 1.654970680217259e-05, + "loss": 0.1823, + "step": 19072 + }, + { + "epoch": 5.89, + "learning_rate": 1.6549328877498877e-05, + "loss": 0.1866, + "step": 19073 + }, + { + "epoch": 5.89, + "learning_rate": 1.6548950936444102e-05, + "loss": 0.1929, + "step": 19074 + }, + { + "epoch": 5.89, + "learning_rate": 1.6548572979009204e-05, + "loss": 0.2077, + "step": 19075 + }, + { + "epoch": 5.89, + "learning_rate": 1.6548195005195132e-05, + "loss": 0.1912, + "step": 19076 + }, + { + "epoch": 5.89, + "learning_rate": 1.6547817015002828e-05, + "loss": 0.2115, + "step": 19077 + }, + { + "epoch": 5.89, + "learning_rate": 1.654743900843324e-05, + "loss": 0.1878, + "step": 19078 + }, + { + "epoch": 5.89, + "learning_rate": 1.654706098548731e-05, + "loss": 0.2082, + "step": 19079 + }, + { + "epoch": 5.89, + "learning_rate": 1.654668294616599e-05, + "loss": 0.1926, + "step": 19080 + }, + { + "epoch": 5.89, + "learning_rate": 1.6546304890470222e-05, + "loss": 0.1943, + "step": 19081 + }, + { + "epoch": 5.89, + "learning_rate": 1.654592681840095e-05, + "loss": 0.1809, + "step": 19082 + }, + { + "epoch": 5.89, + "learning_rate": 1.6545548729959124e-05, + "loss": 0.196, + "step": 19083 + }, + { + "epoch": 5.89, + "learning_rate": 1.6545170625145684e-05, + "loss": 0.192, + "step": 19084 + }, + { + "epoch": 5.89, + "learning_rate": 1.654479250396158e-05, + "loss": 0.1865, + "step": 19085 + }, + { + "epoch": 5.89, + "learning_rate": 1.6544414366407756e-05, + "loss": 0.1851, + "step": 19086 + }, + { + "epoch": 5.89, + "learning_rate": 1.6544036212485155e-05, + "loss": 0.1825, + "step": 19087 + }, + { + "epoch": 5.89, + "learning_rate": 1.6543658042194727e-05, + "loss": 0.1755, + "step": 19088 + }, + { + "epoch": 5.9, + "learning_rate": 1.654327985553742e-05, + "loss": 0.1757, + "step": 19089 + }, + { + "epoch": 5.9, + "learning_rate": 1.6542901652514175e-05, + "loss": 0.1817, + "step": 19090 + }, + { + "epoch": 5.9, + "learning_rate": 1.654252343312594e-05, + "loss": 0.1871, + "step": 19091 + }, + { + "epoch": 5.9, + "learning_rate": 1.6542145197373657e-05, + "loss": 0.1756, + "step": 19092 + }, + { + "epoch": 5.9, + "learning_rate": 1.654176694525828e-05, + "loss": 0.1903, + "step": 19093 + }, + { + "epoch": 5.9, + "learning_rate": 1.654138867678075e-05, + "loss": 0.1915, + "step": 19094 + }, + { + "epoch": 5.9, + "learning_rate": 1.6541010391942013e-05, + "loss": 0.1878, + "step": 19095 + }, + { + "epoch": 5.9, + "learning_rate": 1.6540632090743015e-05, + "loss": 0.1817, + "step": 19096 + }, + { + "epoch": 5.9, + "learning_rate": 1.6540253773184705e-05, + "loss": 0.1826, + "step": 19097 + }, + { + "epoch": 5.9, + "learning_rate": 1.6539875439268026e-05, + "loss": 0.1881, + "step": 19098 + }, + { + "epoch": 5.9, + "learning_rate": 1.6539497088993928e-05, + "loss": 0.1779, + "step": 19099 + }, + { + "epoch": 5.9, + "learning_rate": 1.6539118722363353e-05, + "loss": 0.1935, + "step": 19100 + }, + { + "epoch": 5.9, + "learning_rate": 1.653874033937725e-05, + "loss": 0.1778, + "step": 19101 + }, + { + "epoch": 5.9, + "learning_rate": 1.6538361940036566e-05, + "loss": 0.1996, + "step": 19102 + }, + { + "epoch": 5.9, + "learning_rate": 1.653798352434224e-05, + "loss": 0.1746, + "step": 19103 + }, + { + "epoch": 5.9, + "learning_rate": 1.6537605092295233e-05, + "loss": 0.1703, + "step": 19104 + }, + { + "epoch": 5.9, + "learning_rate": 1.653722664389648e-05, + "loss": 0.1832, + "step": 19105 + }, + { + "epoch": 5.9, + "learning_rate": 1.653684817914693e-05, + "loss": 0.1914, + "step": 19106 + }, + { + "epoch": 5.9, + "learning_rate": 1.653646969804753e-05, + "loss": 0.1899, + "step": 19107 + }, + { + "epoch": 5.9, + "learning_rate": 1.6536091200599233e-05, + "loss": 0.1951, + "step": 19108 + }, + { + "epoch": 5.9, + "learning_rate": 1.6535712686802975e-05, + "loss": 0.1916, + "step": 19109 + }, + { + "epoch": 5.9, + "learning_rate": 1.6535334156659706e-05, + "loss": 0.1907, + "step": 19110 + }, + { + "epoch": 5.9, + "learning_rate": 1.653495561017038e-05, + "loss": 0.1881, + "step": 19111 + }, + { + "epoch": 5.9, + "learning_rate": 1.653457704733593e-05, + "loss": 0.1891, + "step": 19112 + }, + { + "epoch": 5.9, + "learning_rate": 1.6534198468157315e-05, + "loss": 0.1971, + "step": 19113 + }, + { + "epoch": 5.9, + "learning_rate": 1.653381987263548e-05, + "loss": 0.1801, + "step": 19114 + }, + { + "epoch": 5.9, + "learning_rate": 1.6533441260771367e-05, + "loss": 0.189, + "step": 19115 + }, + { + "epoch": 5.9, + "learning_rate": 1.6533062632565928e-05, + "loss": 0.1918, + "step": 19116 + }, + { + "epoch": 5.9, + "learning_rate": 1.6532683988020106e-05, + "loss": 0.1775, + "step": 19117 + }, + { + "epoch": 5.9, + "learning_rate": 1.653230532713485e-05, + "loss": 0.186, + "step": 19118 + }, + { + "epoch": 5.9, + "learning_rate": 1.653192664991111e-05, + "loss": 0.2, + "step": 19119 + }, + { + "epoch": 5.9, + "learning_rate": 1.6531547956349825e-05, + "loss": 0.1873, + "step": 19120 + }, + { + "epoch": 5.91, + "learning_rate": 1.653116924645195e-05, + "loss": 0.1903, + "step": 19121 + }, + { + "epoch": 5.91, + "learning_rate": 1.653079052021843e-05, + "loss": 0.1917, + "step": 19122 + }, + { + "epoch": 5.91, + "learning_rate": 1.653041177765021e-05, + "loss": 0.1837, + "step": 19123 + }, + { + "epoch": 5.91, + "learning_rate": 1.653003301874824e-05, + "loss": 0.1844, + "step": 19124 + }, + { + "epoch": 5.91, + "learning_rate": 1.6529654243513468e-05, + "loss": 0.1912, + "step": 19125 + }, + { + "epoch": 5.91, + "learning_rate": 1.652927545194684e-05, + "loss": 0.1861, + "step": 19126 + }, + { + "epoch": 5.91, + "learning_rate": 1.65288966440493e-05, + "loss": 0.185, + "step": 19127 + }, + { + "epoch": 5.91, + "learning_rate": 1.6528517819821796e-05, + "loss": 0.1817, + "step": 19128 + }, + { + "epoch": 5.91, + "learning_rate": 1.6528138979265286e-05, + "loss": 0.1734, + "step": 19129 + }, + { + "epoch": 5.91, + "learning_rate": 1.6527760122380704e-05, + "loss": 0.188, + "step": 19130 + }, + { + "epoch": 5.91, + "learning_rate": 1.6527381249169007e-05, + "loss": 0.1809, + "step": 19131 + }, + { + "epoch": 5.91, + "learning_rate": 1.6527002359631136e-05, + "loss": 0.1817, + "step": 19132 + }, + { + "epoch": 5.91, + "learning_rate": 1.6526623453768043e-05, + "loss": 0.1781, + "step": 19133 + }, + { + "epoch": 5.91, + "learning_rate": 1.6526244531580674e-05, + "loss": 0.1874, + "step": 19134 + }, + { + "epoch": 5.91, + "learning_rate": 1.652586559306998e-05, + "loss": 0.1996, + "step": 19135 + }, + { + "epoch": 5.91, + "learning_rate": 1.65254866382369e-05, + "loss": 0.1816, + "step": 19136 + }, + { + "epoch": 5.91, + "learning_rate": 1.652510766708239e-05, + "loss": 0.1819, + "step": 19137 + }, + { + "epoch": 5.91, + "learning_rate": 1.6524728679607403e-05, + "loss": 0.1953, + "step": 19138 + }, + { + "epoch": 5.91, + "learning_rate": 1.652434967581287e-05, + "loss": 0.185, + "step": 19139 + }, + { + "epoch": 5.91, + "learning_rate": 1.6523970655699752e-05, + "loss": 0.2044, + "step": 19140 + }, + { + "epoch": 5.91, + "learning_rate": 1.6523591619268994e-05, + "loss": 0.1852, + "step": 19141 + }, + { + "epoch": 5.91, + "learning_rate": 1.6523212566521545e-05, + "loss": 0.1903, + "step": 19142 + }, + { + "epoch": 5.91, + "learning_rate": 1.6522833497458348e-05, + "loss": 0.1863, + "step": 19143 + }, + { + "epoch": 5.91, + "learning_rate": 1.6522454412080357e-05, + "loss": 0.1833, + "step": 19144 + }, + { + "epoch": 5.91, + "learning_rate": 1.6522075310388516e-05, + "loss": 0.1875, + "step": 19145 + }, + { + "epoch": 5.91, + "learning_rate": 1.6521696192383775e-05, + "loss": 0.2092, + "step": 19146 + }, + { + "epoch": 5.91, + "learning_rate": 1.6521317058067087e-05, + "loss": 0.1871, + "step": 19147 + }, + { + "epoch": 5.91, + "learning_rate": 1.652093790743939e-05, + "loss": 0.1948, + "step": 19148 + }, + { + "epoch": 5.91, + "learning_rate": 1.652055874050164e-05, + "loss": 0.204, + "step": 19149 + }, + { + "epoch": 5.91, + "learning_rate": 1.6520179557254784e-05, + "loss": 0.1867, + "step": 19150 + }, + { + "epoch": 5.91, + "learning_rate": 1.6519800357699768e-05, + "loss": 0.1927, + "step": 19151 + }, + { + "epoch": 5.91, + "learning_rate": 1.6519421141837545e-05, + "loss": 0.1874, + "step": 19152 + }, + { + "epoch": 5.91, + "learning_rate": 1.651904190966906e-05, + "loss": 0.1816, + "step": 19153 + }, + { + "epoch": 5.92, + "learning_rate": 1.6518662661195258e-05, + "loss": 0.1922, + "step": 19154 + }, + { + "epoch": 5.92, + "learning_rate": 1.6518283396417095e-05, + "loss": 0.2099, + "step": 19155 + }, + { + "epoch": 5.92, + "learning_rate": 1.651790411533552e-05, + "loss": 0.202, + "step": 19156 + }, + { + "epoch": 5.92, + "learning_rate": 1.651752481795147e-05, + "loss": 0.1779, + "step": 19157 + }, + { + "epoch": 5.92, + "learning_rate": 1.6517145504265908e-05, + "loss": 0.1973, + "step": 19158 + }, + { + "epoch": 5.92, + "learning_rate": 1.6516766174279774e-05, + "loss": 0.1867, + "step": 19159 + }, + { + "epoch": 5.92, + "learning_rate": 1.651638682799402e-05, + "loss": 0.1754, + "step": 19160 + }, + { + "epoch": 5.92, + "learning_rate": 1.6516007465409597e-05, + "loss": 0.1751, + "step": 19161 + }, + { + "epoch": 5.92, + "learning_rate": 1.6515628086527443e-05, + "loss": 0.1857, + "step": 19162 + }, + { + "epoch": 5.92, + "learning_rate": 1.651524869134852e-05, + "loss": 0.1845, + "step": 19163 + }, + { + "epoch": 5.92, + "learning_rate": 1.6514869279873772e-05, + "loss": 0.1892, + "step": 19164 + }, + { + "epoch": 5.92, + "learning_rate": 1.6514489852104146e-05, + "loss": 0.1901, + "step": 19165 + }, + { + "epoch": 5.92, + "learning_rate": 1.6514110408040595e-05, + "loss": 0.1738, + "step": 19166 + }, + { + "epoch": 5.92, + "learning_rate": 1.6513730947684063e-05, + "loss": 0.1915, + "step": 19167 + }, + { + "epoch": 5.92, + "learning_rate": 1.6513351471035503e-05, + "loss": 0.1911, + "step": 19168 + }, + { + "epoch": 5.92, + "learning_rate": 1.6512971978095863e-05, + "loss": 0.1948, + "step": 19169 + }, + { + "epoch": 5.92, + "learning_rate": 1.6512592468866096e-05, + "loss": 0.1899, + "step": 19170 + }, + { + "epoch": 5.92, + "learning_rate": 1.651221294334714e-05, + "loss": 0.1814, + "step": 19171 + }, + { + "epoch": 5.92, + "learning_rate": 1.6511833401539957e-05, + "loss": 0.2055, + "step": 19172 + }, + { + "epoch": 5.92, + "learning_rate": 1.651145384344549e-05, + "loss": 0.186, + "step": 19173 + }, + { + "epoch": 5.92, + "learning_rate": 1.6511074269064685e-05, + "loss": 0.177, + "step": 19174 + }, + { + "epoch": 5.92, + "learning_rate": 1.65106946783985e-05, + "loss": 0.1803, + "step": 19175 + }, + { + "epoch": 5.92, + "learning_rate": 1.651031507144788e-05, + "loss": 0.194, + "step": 19176 + }, + { + "epoch": 5.92, + "learning_rate": 1.6509935448213778e-05, + "loss": 0.1863, + "step": 19177 + }, + { + "epoch": 5.92, + "learning_rate": 1.6509555808697136e-05, + "loss": 0.1843, + "step": 19178 + }, + { + "epoch": 5.92, + "learning_rate": 1.6509176152898905e-05, + "loss": 0.1778, + "step": 19179 + }, + { + "epoch": 5.92, + "learning_rate": 1.650879648082004e-05, + "loss": 0.2078, + "step": 19180 + }, + { + "epoch": 5.92, + "learning_rate": 1.650841679246149e-05, + "loss": 0.1927, + "step": 19181 + }, + { + "epoch": 5.92, + "learning_rate": 1.6508037087824197e-05, + "loss": 0.1853, + "step": 19182 + }, + { + "epoch": 5.92, + "learning_rate": 1.6507657366909123e-05, + "loss": 0.1802, + "step": 19183 + }, + { + "epoch": 5.92, + "learning_rate": 1.650727762971721e-05, + "loss": 0.1862, + "step": 19184 + }, + { + "epoch": 5.92, + "learning_rate": 1.6506897876249405e-05, + "loss": 0.1705, + "step": 19185 + }, + { + "epoch": 5.93, + "learning_rate": 1.6506518106506663e-05, + "loss": 0.1833, + "step": 19186 + }, + { + "epoch": 5.93, + "learning_rate": 1.6506138320489934e-05, + "loss": 0.189, + "step": 19187 + }, + { + "epoch": 5.93, + "learning_rate": 1.6505758518200163e-05, + "loss": 0.1896, + "step": 19188 + }, + { + "epoch": 5.93, + "learning_rate": 1.6505378699638307e-05, + "loss": 0.2085, + "step": 19189 + }, + { + "epoch": 5.93, + "learning_rate": 1.650499886480531e-05, + "loss": 0.1898, + "step": 19190 + }, + { + "epoch": 5.93, + "learning_rate": 1.6504619013702123e-05, + "loss": 0.1895, + "step": 19191 + }, + { + "epoch": 5.93, + "learning_rate": 1.6504239146329702e-05, + "loss": 0.1997, + "step": 19192 + }, + { + "epoch": 5.93, + "learning_rate": 1.650385926268899e-05, + "loss": 0.1905, + "step": 19193 + }, + { + "epoch": 5.93, + "learning_rate": 1.650347936278094e-05, + "loss": 0.2108, + "step": 19194 + }, + { + "epoch": 5.93, + "learning_rate": 1.6503099446606502e-05, + "loss": 0.1831, + "step": 19195 + }, + { + "epoch": 5.93, + "learning_rate": 1.6502719514166626e-05, + "loss": 0.1987, + "step": 19196 + }, + { + "epoch": 5.93, + "learning_rate": 1.6502339565462265e-05, + "loss": 0.1822, + "step": 19197 + }, + { + "epoch": 5.93, + "learning_rate": 1.6501959600494365e-05, + "loss": 0.1928, + "step": 19198 + }, + { + "epoch": 5.93, + "learning_rate": 1.6501579619263877e-05, + "loss": 0.1969, + "step": 19199 + }, + { + "epoch": 5.93, + "learning_rate": 1.650119962177175e-05, + "loss": 0.1927, + "step": 19200 + }, + { + "epoch": 5.93, + "learning_rate": 1.6500819608018944e-05, + "loss": 0.1728, + "step": 19201 + }, + { + "epoch": 5.93, + "learning_rate": 1.6500439578006398e-05, + "loss": 0.1913, + "step": 19202 + }, + { + "epoch": 5.93, + "learning_rate": 1.6500059531735066e-05, + "loss": 0.1769, + "step": 19203 + }, + { + "epoch": 5.93, + "learning_rate": 1.64996794692059e-05, + "loss": 0.1912, + "step": 19204 + }, + { + "epoch": 5.93, + "learning_rate": 1.6499299390419854e-05, + "loss": 0.1873, + "step": 19205 + }, + { + "epoch": 5.93, + "learning_rate": 1.6498919295377872e-05, + "loss": 0.1919, + "step": 19206 + }, + { + "epoch": 5.93, + "learning_rate": 1.6498539184080908e-05, + "loss": 0.1835, + "step": 19207 + }, + { + "epoch": 5.93, + "learning_rate": 1.6498159056529914e-05, + "loss": 0.1704, + "step": 19208 + }, + { + "epoch": 5.93, + "learning_rate": 1.6497778912725837e-05, + "loss": 0.1754, + "step": 19209 + }, + { + "epoch": 5.93, + "learning_rate": 1.6497398752669628e-05, + "loss": 0.2059, + "step": 19210 + }, + { + "epoch": 5.93, + "learning_rate": 1.649701857636224e-05, + "loss": 0.1811, + "step": 19211 + }, + { + "epoch": 5.93, + "learning_rate": 1.649663838380463e-05, + "loss": 0.2081, + "step": 19212 + }, + { + "epoch": 5.93, + "learning_rate": 1.6496258174997734e-05, + "loss": 0.1814, + "step": 19213 + }, + { + "epoch": 5.93, + "learning_rate": 1.6495877949942517e-05, + "loss": 0.1905, + "step": 19214 + }, + { + "epoch": 5.93, + "learning_rate": 1.6495497708639924e-05, + "loss": 0.2031, + "step": 19215 + }, + { + "epoch": 5.93, + "learning_rate": 1.64951174510909e-05, + "loss": 0.1918, + "step": 19216 + }, + { + "epoch": 5.93, + "learning_rate": 1.649473717729641e-05, + "loss": 0.1761, + "step": 19217 + }, + { + "epoch": 5.93, + "learning_rate": 1.6494356887257396e-05, + "loss": 0.1776, + "step": 19218 + }, + { + "epoch": 5.94, + "learning_rate": 1.6493976580974812e-05, + "loss": 0.2034, + "step": 19219 + }, + { + "epoch": 5.94, + "learning_rate": 1.6493596258449603e-05, + "loss": 0.1888, + "step": 19220 + }, + { + "epoch": 5.94, + "learning_rate": 1.6493215919682734e-05, + "loss": 0.1986, + "step": 19221 + }, + { + "epoch": 5.94, + "learning_rate": 1.649283556467514e-05, + "loss": 0.198, + "step": 19222 + }, + { + "epoch": 5.94, + "learning_rate": 1.6492455193427782e-05, + "loss": 0.2015, + "step": 19223 + }, + { + "epoch": 5.94, + "learning_rate": 1.649207480594161e-05, + "loss": 0.184, + "step": 19224 + }, + { + "epoch": 5.94, + "learning_rate": 1.6491694402217576e-05, + "loss": 0.1964, + "step": 19225 + }, + { + "epoch": 5.94, + "learning_rate": 1.649131398225663e-05, + "loss": 0.1976, + "step": 19226 + }, + { + "epoch": 5.94, + "learning_rate": 1.649093354605972e-05, + "loss": 0.193, + "step": 19227 + }, + { + "epoch": 5.94, + "learning_rate": 1.6490553093627806e-05, + "loss": 0.1842, + "step": 19228 + }, + { + "epoch": 5.94, + "learning_rate": 1.6490172624961834e-05, + "loss": 0.1926, + "step": 19229 + }, + { + "epoch": 5.94, + "learning_rate": 1.6489792140062753e-05, + "loss": 0.1973, + "step": 19230 + }, + { + "epoch": 5.94, + "learning_rate": 1.6489411638931523e-05, + "loss": 0.1915, + "step": 19231 + }, + { + "epoch": 5.94, + "learning_rate": 1.648903112156909e-05, + "loss": 0.1937, + "step": 19232 + }, + { + "epoch": 5.94, + "learning_rate": 1.6488650587976404e-05, + "loss": 0.1975, + "step": 19233 + }, + { + "epoch": 5.94, + "learning_rate": 1.648827003815442e-05, + "loss": 0.1851, + "step": 19234 + }, + { + "epoch": 5.94, + "learning_rate": 1.648788947210409e-05, + "loss": 0.2023, + "step": 19235 + }, + { + "epoch": 5.94, + "learning_rate": 1.6487508889826366e-05, + "loss": 0.2044, + "step": 19236 + }, + { + "epoch": 5.94, + "learning_rate": 1.64871282913222e-05, + "loss": 0.1824, + "step": 19237 + }, + { + "epoch": 5.94, + "learning_rate": 1.648674767659254e-05, + "loss": 0.1921, + "step": 19238 + }, + { + "epoch": 5.94, + "learning_rate": 1.6486367045638344e-05, + "loss": 0.1921, + "step": 19239 + }, + { + "epoch": 5.94, + "learning_rate": 1.6485986398460557e-05, + "loss": 0.1914, + "step": 19240 + }, + { + "epoch": 5.94, + "learning_rate": 1.648560573506014e-05, + "loss": 0.1868, + "step": 19241 + }, + { + "epoch": 5.94, + "learning_rate": 1.6485225055438033e-05, + "loss": 0.2016, + "step": 19242 + }, + { + "epoch": 5.94, + "learning_rate": 1.6484844359595202e-05, + "loss": 0.1773, + "step": 19243 + }, + { + "epoch": 5.94, + "learning_rate": 1.648446364753259e-05, + "loss": 0.1786, + "step": 19244 + }, + { + "epoch": 5.94, + "learning_rate": 1.6484082919251154e-05, + "loss": 0.2036, + "step": 19245 + }, + { + "epoch": 5.94, + "learning_rate": 1.648370217475184e-05, + "loss": 0.1929, + "step": 19246 + }, + { + "epoch": 5.94, + "learning_rate": 1.6483321414035606e-05, + "loss": 0.1759, + "step": 19247 + }, + { + "epoch": 5.94, + "learning_rate": 1.64829406371034e-05, + "loss": 0.1793, + "step": 19248 + }, + { + "epoch": 5.94, + "learning_rate": 1.6482559843956183e-05, + "loss": 0.19, + "step": 19249 + }, + { + "epoch": 5.94, + "learning_rate": 1.6482179034594898e-05, + "loss": 0.1819, + "step": 19250 + }, + { + "epoch": 5.95, + "learning_rate": 1.64817982090205e-05, + "loss": 0.1614, + "step": 19251 + }, + { + "epoch": 5.95, + "learning_rate": 1.6481417367233944e-05, + "loss": 0.1842, + "step": 19252 + }, + { + "epoch": 5.95, + "learning_rate": 1.6481036509236183e-05, + "loss": 0.1953, + "step": 19253 + }, + { + "epoch": 5.95, + "learning_rate": 1.6480655635028163e-05, + "loss": 0.1714, + "step": 19254 + }, + { + "epoch": 5.95, + "learning_rate": 1.6480274744610846e-05, + "loss": 0.1785, + "step": 19255 + }, + { + "epoch": 5.95, + "learning_rate": 1.6479893837985177e-05, + "loss": 0.195, + "step": 19256 + }, + { + "epoch": 5.95, + "learning_rate": 1.6479512915152113e-05, + "loss": 0.1911, + "step": 19257 + }, + { + "epoch": 5.95, + "learning_rate": 1.6479131976112604e-05, + "loss": 0.1952, + "step": 19258 + }, + { + "epoch": 5.95, + "learning_rate": 1.6478751020867603e-05, + "loss": 0.2056, + "step": 19259 + }, + { + "epoch": 5.95, + "learning_rate": 1.647837004941807e-05, + "loss": 0.1827, + "step": 19260 + }, + { + "epoch": 5.95, + "learning_rate": 1.6477989061764945e-05, + "loss": 0.1857, + "step": 19261 + }, + { + "epoch": 5.95, + "learning_rate": 1.647760805790919e-05, + "loss": 0.1905, + "step": 19262 + }, + { + "epoch": 5.95, + "learning_rate": 1.647722703785176e-05, + "loss": 0.1922, + "step": 19263 + }, + { + "epoch": 5.95, + "learning_rate": 1.6476846001593598e-05, + "loss": 0.1993, + "step": 19264 + }, + { + "epoch": 5.95, + "learning_rate": 1.6476464949135666e-05, + "loss": 0.1937, + "step": 19265 + }, + { + "epoch": 5.95, + "learning_rate": 1.6476083880478914e-05, + "loss": 0.1663, + "step": 19266 + }, + { + "epoch": 5.95, + "learning_rate": 1.6475702795624293e-05, + "loss": 0.2045, + "step": 19267 + }, + { + "epoch": 5.95, + "learning_rate": 1.647532169457276e-05, + "loss": 0.1788, + "step": 19268 + }, + { + "epoch": 5.95, + "learning_rate": 1.6474940577325266e-05, + "loss": 0.1917, + "step": 19269 + }, + { + "epoch": 5.95, + "learning_rate": 1.6474559443882765e-05, + "loss": 0.1926, + "step": 19270 + }, + { + "epoch": 5.95, + "learning_rate": 1.6474178294246207e-05, + "loss": 0.1992, + "step": 19271 + }, + { + "epoch": 5.95, + "learning_rate": 1.6473797128416554e-05, + "loss": 0.1961, + "step": 19272 + }, + { + "epoch": 5.95, + "learning_rate": 1.647341594639475e-05, + "loss": 0.1788, + "step": 19273 + }, + { + "epoch": 5.95, + "learning_rate": 1.6473034748181752e-05, + "loss": 0.1835, + "step": 19274 + }, + { + "epoch": 5.95, + "learning_rate": 1.647265353377851e-05, + "loss": 0.1855, + "step": 19275 + }, + { + "epoch": 5.95, + "learning_rate": 1.647227230318599e-05, + "loss": 0.1852, + "step": 19276 + }, + { + "epoch": 5.95, + "learning_rate": 1.647189105640513e-05, + "loss": 0.1974, + "step": 19277 + }, + { + "epoch": 5.95, + "learning_rate": 1.6471509793436888e-05, + "loss": 0.1948, + "step": 19278 + }, + { + "epoch": 5.95, + "learning_rate": 1.6471128514282226e-05, + "loss": 0.1852, + "step": 19279 + }, + { + "epoch": 5.95, + "learning_rate": 1.647074721894209e-05, + "loss": 0.2041, + "step": 19280 + }, + { + "epoch": 5.95, + "learning_rate": 1.6470365907417433e-05, + "loss": 0.1942, + "step": 19281 + }, + { + "epoch": 5.95, + "learning_rate": 1.646998457970921e-05, + "loss": 0.1992, + "step": 19282 + }, + { + "epoch": 5.96, + "learning_rate": 1.6469603235818378e-05, + "loss": 0.2042, + "step": 19283 + }, + { + "epoch": 5.96, + "learning_rate": 1.6469221875745886e-05, + "loss": 0.1904, + "step": 19284 + }, + { + "epoch": 5.96, + "learning_rate": 1.646884049949269e-05, + "loss": 0.1931, + "step": 19285 + }, + { + "epoch": 5.96, + "learning_rate": 1.6468459107059748e-05, + "loss": 0.1874, + "step": 19286 + }, + { + "epoch": 5.96, + "learning_rate": 1.6468077698448003e-05, + "loss": 0.1821, + "step": 19287 + }, + { + "epoch": 5.96, + "learning_rate": 1.6467696273658426e-05, + "loss": 0.1886, + "step": 19288 + }, + { + "epoch": 5.96, + "learning_rate": 1.6467314832691953e-05, + "loss": 0.1928, + "step": 19289 + }, + { + "epoch": 5.96, + "learning_rate": 1.6466933375549547e-05, + "loss": 0.1984, + "step": 19290 + }, + { + "epoch": 5.96, + "learning_rate": 1.6466551902232165e-05, + "loss": 0.1977, + "step": 19291 + }, + { + "epoch": 5.96, + "learning_rate": 1.646617041274075e-05, + "loss": 0.1941, + "step": 19292 + }, + { + "epoch": 5.96, + "learning_rate": 1.646578890707627e-05, + "loss": 0.2045, + "step": 19293 + }, + { + "epoch": 5.96, + "learning_rate": 1.646540738523967e-05, + "loss": 0.1987, + "step": 19294 + }, + { + "epoch": 5.96, + "learning_rate": 1.646502584723191e-05, + "loss": 0.1948, + "step": 19295 + }, + { + "epoch": 5.96, + "learning_rate": 1.6464644293053937e-05, + "loss": 0.2046, + "step": 19296 + }, + { + "epoch": 5.96, + "learning_rate": 1.6464262722706712e-05, + "loss": 0.2038, + "step": 19297 + }, + { + "epoch": 5.96, + "learning_rate": 1.6463881136191187e-05, + "loss": 0.1827, + "step": 19298 + }, + { + "epoch": 5.96, + "learning_rate": 1.6463499533508316e-05, + "loss": 0.1959, + "step": 19299 + }, + { + "epoch": 5.96, + "learning_rate": 1.6463117914659053e-05, + "loss": 0.1919, + "step": 19300 + }, + { + "epoch": 5.96, + "learning_rate": 1.6462736279644352e-05, + "loss": 0.1795, + "step": 19301 + }, + { + "epoch": 5.96, + "learning_rate": 1.6462354628465173e-05, + "loss": 0.1762, + "step": 19302 + }, + { + "epoch": 5.96, + "learning_rate": 1.6461972961122464e-05, + "loss": 0.1721, + "step": 19303 + }, + { + "epoch": 5.96, + "learning_rate": 1.646159127761718e-05, + "loss": 0.1821, + "step": 19304 + }, + { + "epoch": 5.96, + "learning_rate": 1.646120957795028e-05, + "loss": 0.2327, + "step": 19305 + }, + { + "epoch": 5.96, + "learning_rate": 1.6460827862122718e-05, + "loss": 0.193, + "step": 19306 + }, + { + "epoch": 5.96, + "learning_rate": 1.6460446130135443e-05, + "loss": 0.1952, + "step": 19307 + }, + { + "epoch": 5.96, + "learning_rate": 1.6460064381989416e-05, + "loss": 0.1833, + "step": 19308 + }, + { + "epoch": 5.96, + "learning_rate": 1.6459682617685592e-05, + "loss": 0.1905, + "step": 19309 + }, + { + "epoch": 5.96, + "learning_rate": 1.645930083722492e-05, + "loss": 0.1991, + "step": 19310 + }, + { + "epoch": 5.96, + "learning_rate": 1.645891904060836e-05, + "loss": 0.1843, + "step": 19311 + }, + { + "epoch": 5.96, + "learning_rate": 1.6458537227836867e-05, + "loss": 0.1934, + "step": 19312 + }, + { + "epoch": 5.96, + "learning_rate": 1.6458155398911394e-05, + "loss": 0.1878, + "step": 19313 + }, + { + "epoch": 5.96, + "learning_rate": 1.6457773553832895e-05, + "loss": 0.2077, + "step": 19314 + }, + { + "epoch": 5.96, + "learning_rate": 1.6457391692602325e-05, + "loss": 0.1939, + "step": 19315 + }, + { + "epoch": 5.97, + "learning_rate": 1.6457009815220643e-05, + "loss": 0.2023, + "step": 19316 + }, + { + "epoch": 5.97, + "learning_rate": 1.6456627921688803e-05, + "loss": 0.1854, + "step": 19317 + }, + { + "epoch": 5.97, + "learning_rate": 1.6456246012007755e-05, + "loss": 0.195, + "step": 19318 + }, + { + "epoch": 5.97, + "learning_rate": 1.645586408617846e-05, + "loss": 0.1796, + "step": 19319 + }, + { + "epoch": 5.97, + "learning_rate": 1.6455482144201873e-05, + "loss": 0.1932, + "step": 19320 + }, + { + "epoch": 5.97, + "learning_rate": 1.6455100186078947e-05, + "loss": 0.1898, + "step": 19321 + }, + { + "epoch": 5.97, + "learning_rate": 1.6454718211810637e-05, + "loss": 0.1985, + "step": 19322 + }, + { + "epoch": 5.97, + "learning_rate": 1.6454336221397903e-05, + "loss": 0.1766, + "step": 19323 + }, + { + "epoch": 5.97, + "learning_rate": 1.645395421484169e-05, + "loss": 0.2088, + "step": 19324 + }, + { + "epoch": 5.97, + "learning_rate": 1.6453572192142968e-05, + "loss": 0.1951, + "step": 19325 + }, + { + "epoch": 5.97, + "learning_rate": 1.6453190153302677e-05, + "loss": 0.1756, + "step": 19326 + }, + { + "epoch": 5.97, + "learning_rate": 1.645280809832179e-05, + "loss": 0.1976, + "step": 19327 + }, + { + "epoch": 5.97, + "learning_rate": 1.6452426027201246e-05, + "loss": 0.209, + "step": 19328 + }, + { + "epoch": 5.97, + "learning_rate": 1.6452043939942008e-05, + "loss": 0.1824, + "step": 19329 + }, + { + "epoch": 5.97, + "learning_rate": 1.6451661836545033e-05, + "loss": 0.2216, + "step": 19330 + }, + { + "epoch": 5.97, + "learning_rate": 1.6451279717011278e-05, + "loss": 0.1799, + "step": 19331 + }, + { + "epoch": 5.97, + "learning_rate": 1.645089758134169e-05, + "loss": 0.2008, + "step": 19332 + }, + { + "epoch": 5.97, + "learning_rate": 1.6450515429537233e-05, + "loss": 0.17, + "step": 19333 + }, + { + "epoch": 5.97, + "learning_rate": 1.6450133261598862e-05, + "loss": 0.201, + "step": 19334 + }, + { + "epoch": 5.97, + "learning_rate": 1.644975107752753e-05, + "loss": 0.1979, + "step": 19335 + }, + { + "epoch": 5.97, + "learning_rate": 1.6449368877324192e-05, + "loss": 0.1845, + "step": 19336 + }, + { + "epoch": 5.97, + "learning_rate": 1.644898666098981e-05, + "loss": 0.1962, + "step": 19337 + }, + { + "epoch": 5.97, + "learning_rate": 1.6448604428525333e-05, + "loss": 0.1825, + "step": 19338 + }, + { + "epoch": 5.97, + "learning_rate": 1.6448222179931722e-05, + "loss": 0.1848, + "step": 19339 + }, + { + "epoch": 5.97, + "learning_rate": 1.6447839915209933e-05, + "loss": 0.205, + "step": 19340 + }, + { + "epoch": 5.97, + "learning_rate": 1.6447457634360918e-05, + "loss": 0.1787, + "step": 19341 + }, + { + "epoch": 5.97, + "learning_rate": 1.6447075337385636e-05, + "loss": 0.2014, + "step": 19342 + }, + { + "epoch": 5.97, + "learning_rate": 1.644669302428504e-05, + "loss": 0.2075, + "step": 19343 + }, + { + "epoch": 5.97, + "learning_rate": 1.644631069506009e-05, + "loss": 0.1808, + "step": 19344 + }, + { + "epoch": 5.97, + "learning_rate": 1.6445928349711743e-05, + "loss": 0.1959, + "step": 19345 + }, + { + "epoch": 5.97, + "learning_rate": 1.6445545988240953e-05, + "loss": 0.1978, + "step": 19346 + }, + { + "epoch": 5.97, + "learning_rate": 1.644516361064868e-05, + "loss": 0.191, + "step": 19347 + }, + { + "epoch": 5.98, + "learning_rate": 1.644478121693587e-05, + "loss": 0.1923, + "step": 19348 + }, + { + "epoch": 5.98, + "learning_rate": 1.6444398807103495e-05, + "loss": 0.1948, + "step": 19349 + }, + { + "epoch": 5.98, + "learning_rate": 1.6444016381152498e-05, + "loss": 0.1789, + "step": 19350 + }, + { + "epoch": 5.98, + "learning_rate": 1.644363393908384e-05, + "loss": 0.1923, + "step": 19351 + }, + { + "epoch": 5.98, + "learning_rate": 1.644325148089848e-05, + "loss": 0.1969, + "step": 19352 + }, + { + "epoch": 5.98, + "learning_rate": 1.6442869006597374e-05, + "loss": 0.1701, + "step": 19353 + }, + { + "epoch": 5.98, + "learning_rate": 1.6442486516181477e-05, + "loss": 0.1777, + "step": 19354 + }, + { + "epoch": 5.98, + "learning_rate": 1.6442104009651748e-05, + "loss": 0.2026, + "step": 19355 + }, + { + "epoch": 5.98, + "learning_rate": 1.6441721487009138e-05, + "loss": 0.1859, + "step": 19356 + }, + { + "epoch": 5.98, + "learning_rate": 1.644133894825461e-05, + "loss": 0.1888, + "step": 19357 + }, + { + "epoch": 5.98, + "learning_rate": 1.6440956393389118e-05, + "loss": 0.2075, + "step": 19358 + }, + { + "epoch": 5.98, + "learning_rate": 1.644057382241362e-05, + "loss": 0.1785, + "step": 19359 + }, + { + "epoch": 5.98, + "learning_rate": 1.6440191235329067e-05, + "loss": 0.185, + "step": 19360 + }, + { + "epoch": 5.98, + "learning_rate": 1.643980863213643e-05, + "loss": 0.1841, + "step": 19361 + }, + { + "epoch": 5.98, + "learning_rate": 1.6439426012836654e-05, + "loss": 0.1946, + "step": 19362 + }, + { + "epoch": 5.98, + "learning_rate": 1.6439043377430692e-05, + "loss": 0.1821, + "step": 19363 + }, + { + "epoch": 5.98, + "learning_rate": 1.6438660725919517e-05, + "loss": 0.1858, + "step": 19364 + }, + { + "epoch": 5.98, + "learning_rate": 1.6438278058304074e-05, + "loss": 0.1854, + "step": 19365 + }, + { + "epoch": 5.98, + "learning_rate": 1.643789537458532e-05, + "loss": 0.1962, + "step": 19366 + }, + { + "epoch": 5.98, + "learning_rate": 1.643751267476422e-05, + "loss": 0.1825, + "step": 19367 + }, + { + "epoch": 5.98, + "learning_rate": 1.6437129958841728e-05, + "loss": 0.1781, + "step": 19368 + }, + { + "epoch": 5.98, + "learning_rate": 1.6436747226818794e-05, + "loss": 0.1903, + "step": 19369 + }, + { + "epoch": 5.98, + "learning_rate": 1.6436364478696386e-05, + "loss": 0.1955, + "step": 19370 + }, + { + "epoch": 5.98, + "learning_rate": 1.6435981714475457e-05, + "loss": 0.1917, + "step": 19371 + }, + { + "epoch": 5.98, + "learning_rate": 1.6435598934156957e-05, + "loss": 0.1936, + "step": 19372 + }, + { + "epoch": 5.98, + "learning_rate": 1.6435216137741857e-05, + "loss": 0.1846, + "step": 19373 + }, + { + "epoch": 5.98, + "learning_rate": 1.6434833325231105e-05, + "loss": 0.1919, + "step": 19374 + }, + { + "epoch": 5.98, + "learning_rate": 1.643445049662566e-05, + "loss": 0.1835, + "step": 19375 + }, + { + "epoch": 5.98, + "learning_rate": 1.6434067651926486e-05, + "loss": 0.1902, + "step": 19376 + }, + { + "epoch": 5.98, + "learning_rate": 1.643368479113453e-05, + "loss": 0.2006, + "step": 19377 + }, + { + "epoch": 5.98, + "learning_rate": 1.6433301914250758e-05, + "loss": 0.1894, + "step": 19378 + }, + { + "epoch": 5.98, + "learning_rate": 1.6432919021276124e-05, + "loss": 0.1947, + "step": 19379 + }, + { + "epoch": 5.99, + "learning_rate": 1.6432536112211585e-05, + "loss": 0.2021, + "step": 19380 + }, + { + "epoch": 5.99, + "learning_rate": 1.64321531870581e-05, + "loss": 0.1891, + "step": 19381 + }, + { + "epoch": 5.99, + "learning_rate": 1.643177024581663e-05, + "loss": 0.2028, + "step": 19382 + }, + { + "epoch": 5.99, + "learning_rate": 1.6431387288488127e-05, + "loss": 0.1897, + "step": 19383 + }, + { + "epoch": 5.99, + "learning_rate": 1.643100431507355e-05, + "loss": 0.1883, + "step": 19384 + }, + { + "epoch": 5.99, + "learning_rate": 1.643062132557386e-05, + "loss": 0.2089, + "step": 19385 + }, + { + "epoch": 5.99, + "learning_rate": 1.6430238319990014e-05, + "loss": 0.1794, + "step": 19386 + }, + { + "epoch": 5.99, + "learning_rate": 1.6429855298322968e-05, + "loss": 0.1752, + "step": 19387 + }, + { + "epoch": 5.99, + "learning_rate": 1.642947226057368e-05, + "loss": 0.1936, + "step": 19388 + }, + { + "epoch": 5.99, + "learning_rate": 1.642908920674311e-05, + "loss": 0.1749, + "step": 19389 + }, + { + "epoch": 5.99, + "learning_rate": 1.6428706136832217e-05, + "loss": 0.1791, + "step": 19390 + }, + { + "epoch": 5.99, + "learning_rate": 1.6428323050841953e-05, + "loss": 0.1888, + "step": 19391 + }, + { + "epoch": 5.99, + "learning_rate": 1.6427939948773282e-05, + "loss": 0.1877, + "step": 19392 + }, + { + "epoch": 5.99, + "learning_rate": 1.6427556830627164e-05, + "loss": 0.1902, + "step": 19393 + }, + { + "epoch": 5.99, + "learning_rate": 1.6427173696404553e-05, + "loss": 0.1888, + "step": 19394 + }, + { + "epoch": 5.99, + "learning_rate": 1.642679054610641e-05, + "loss": 0.1882, + "step": 19395 + }, + { + "epoch": 5.99, + "learning_rate": 1.6426407379733688e-05, + "loss": 0.1894, + "step": 19396 + }, + { + "epoch": 5.99, + "learning_rate": 1.642602419728735e-05, + "loss": 0.186, + "step": 19397 + }, + { + "epoch": 5.99, + "learning_rate": 1.6425640998768356e-05, + "loss": 0.2016, + "step": 19398 + }, + { + "epoch": 5.99, + "learning_rate": 1.642525778417766e-05, + "loss": 0.1922, + "step": 19399 + }, + { + "epoch": 5.99, + "learning_rate": 1.642487455351622e-05, + "loss": 0.1994, + "step": 19400 + }, + { + "epoch": 5.99, + "learning_rate": 1.6424491306785e-05, + "loss": 0.1892, + "step": 19401 + }, + { + "epoch": 5.99, + "learning_rate": 1.6424108043984953e-05, + "loss": 0.187, + "step": 19402 + }, + { + "epoch": 5.99, + "learning_rate": 1.6423724765117044e-05, + "loss": 0.1914, + "step": 19403 + }, + { + "epoch": 5.99, + "learning_rate": 1.6423341470182227e-05, + "loss": 0.2092, + "step": 19404 + }, + { + "epoch": 5.99, + "learning_rate": 1.642295815918146e-05, + "loss": 0.1861, + "step": 19405 + }, + { + "epoch": 5.99, + "learning_rate": 1.6422574832115697e-05, + "loss": 0.1971, + "step": 19406 + }, + { + "epoch": 5.99, + "learning_rate": 1.6422191488985912e-05, + "loss": 0.1904, + "step": 19407 + }, + { + "epoch": 5.99, + "learning_rate": 1.6421808129793052e-05, + "loss": 0.1901, + "step": 19408 + }, + { + "epoch": 5.99, + "learning_rate": 1.642142475453808e-05, + "loss": 0.1749, + "step": 19409 + }, + { + "epoch": 5.99, + "learning_rate": 1.642104136322195e-05, + "loss": 0.1828, + "step": 19410 + }, + { + "epoch": 5.99, + "learning_rate": 1.6420657955845628e-05, + "loss": 0.1996, + "step": 19411 + }, + { + "epoch": 5.99, + "learning_rate": 1.642027453241007e-05, + "loss": 0.1948, + "step": 19412 + }, + { + "epoch": 6.0, + "learning_rate": 1.6419891092916232e-05, + "loss": 0.1806, + "step": 19413 + }, + { + "epoch": 6.0, + "learning_rate": 1.6419507637365073e-05, + "loss": 0.1727, + "step": 19414 + }, + { + "epoch": 6.0, + "learning_rate": 1.6419124165757557e-05, + "loss": 0.176, + "step": 19415 + }, + { + "epoch": 6.0, + "learning_rate": 1.641874067809464e-05, + "loss": 0.1856, + "step": 19416 + }, + { + "epoch": 6.0, + "learning_rate": 1.6418357174377285e-05, + "loss": 0.1884, + "step": 19417 + }, + { + "epoch": 6.0, + "learning_rate": 1.6417973654606446e-05, + "loss": 0.1855, + "step": 19418 + }, + { + "epoch": 6.0, + "learning_rate": 1.6417590118783082e-05, + "loss": 0.1751, + "step": 19419 + }, + { + "epoch": 6.0, + "learning_rate": 1.6417206566908156e-05, + "loss": 0.1827, + "step": 19420 + }, + { + "epoch": 6.0, + "learning_rate": 1.6416822998982627e-05, + "loss": 0.187, + "step": 19421 + }, + { + "epoch": 6.0, + "learning_rate": 1.6416439415007456e-05, + "loss": 0.181, + "step": 19422 + }, + { + "epoch": 6.0, + "learning_rate": 1.6416055814983596e-05, + "loss": 0.1969, + "step": 19423 + }, + { + "epoch": 6.0, + "learning_rate": 1.641567219891201e-05, + "loss": 0.1939, + "step": 19424 + }, + { + "epoch": 6.0, + "learning_rate": 1.6415288566793658e-05, + "loss": 0.1896, + "step": 19425 + }, + { + "epoch": 6.0, + "learning_rate": 1.64149049186295e-05, + "loss": 0.1966, + "step": 19426 + }, + { + "epoch": 6.0, + "learning_rate": 1.6414521254420495e-05, + "loss": 0.1932, + "step": 19427 + }, + { + "epoch": 6.0, + "learning_rate": 1.6414137574167603e-05, + "loss": 0.1708, + "step": 19428 + }, + { + "epoch": 6.0, + "learning_rate": 1.641375387787178e-05, + "loss": 0.1498, + "step": 19429 + }, + { + "epoch": 6.0, + "learning_rate": 1.641337016553399e-05, + "loss": 0.1352, + "step": 19430 + }, + { + "epoch": 6.0, + "learning_rate": 1.6412986437155193e-05, + "loss": 0.1245, + "step": 19431 + }, + { + "epoch": 6.0, + "learning_rate": 1.6412602692736346e-05, + "loss": 0.1242, + "step": 19432 + }, + { + "epoch": 6.0, + "learning_rate": 1.6412218932278415e-05, + "loss": 0.1196, + "step": 19433 + }, + { + "epoch": 6.0, + "learning_rate": 1.6411835155782346e-05, + "loss": 0.1092, + "step": 19434 + }, + { + "epoch": 6.0, + "learning_rate": 1.6411451363249113e-05, + "loss": 0.1146, + "step": 19435 + }, + { + "epoch": 6.0, + "learning_rate": 1.641106755467967e-05, + "loss": 0.1149, + "step": 19436 + }, + { + "epoch": 6.0, + "learning_rate": 1.6410683730074982e-05, + "loss": 0.1085, + "step": 19437 + }, + { + "epoch": 6.0, + "learning_rate": 1.6410299889435998e-05, + "loss": 0.1091, + "step": 19438 + }, + { + "epoch": 6.0, + "learning_rate": 1.6409916032763686e-05, + "loss": 0.1219, + "step": 19439 + }, + { + "epoch": 6.0, + "learning_rate": 1.640953216005901e-05, + "loss": 0.1113, + "step": 19440 + }, + { + "epoch": 6.0, + "learning_rate": 1.640914827132292e-05, + "loss": 0.1112, + "step": 19441 + }, + { + "epoch": 6.0, + "learning_rate": 1.6408764366556384e-05, + "loss": 0.118, + "step": 19442 + }, + { + "epoch": 6.0, + "learning_rate": 1.6408380445760357e-05, + "loss": 0.1206, + "step": 19443 + }, + { + "epoch": 6.0, + "learning_rate": 1.6407996508935804e-05, + "loss": 0.1175, + "step": 19444 + }, + { + "epoch": 6.01, + "learning_rate": 1.6407612556083677e-05, + "loss": 0.1246, + "step": 19445 + }, + { + "epoch": 6.01, + "learning_rate": 1.640722858720495e-05, + "loss": 0.112, + "step": 19446 + }, + { + "epoch": 6.01, + "learning_rate": 1.6406844602300572e-05, + "loss": 0.1074, + "step": 19447 + }, + { + "epoch": 6.01, + "learning_rate": 1.640646060137151e-05, + "loss": 0.1053, + "step": 19448 + }, + { + "epoch": 6.01, + "learning_rate": 1.640607658441872e-05, + "loss": 0.1156, + "step": 19449 + }, + { + "epoch": 6.01, + "learning_rate": 1.640569255144316e-05, + "loss": 0.1072, + "step": 19450 + }, + { + "epoch": 6.01, + "learning_rate": 1.64053085024458e-05, + "loss": 0.1142, + "step": 19451 + }, + { + "epoch": 6.01, + "learning_rate": 1.6404924437427596e-05, + "loss": 0.123, + "step": 19452 + }, + { + "epoch": 6.01, + "learning_rate": 1.6404540356389504e-05, + "loss": 0.1151, + "step": 19453 + }, + { + "epoch": 6.01, + "learning_rate": 1.640415625933249e-05, + "loss": 0.1154, + "step": 19454 + }, + { + "epoch": 6.01, + "learning_rate": 1.640377214625751e-05, + "loss": 0.1144, + "step": 19455 + }, + { + "epoch": 6.01, + "learning_rate": 1.6403388017165533e-05, + "loss": 0.1125, + "step": 19456 + }, + { + "epoch": 6.01, + "learning_rate": 1.640300387205751e-05, + "loss": 0.1109, + "step": 19457 + }, + { + "epoch": 6.01, + "learning_rate": 1.640261971093441e-05, + "loss": 0.1076, + "step": 19458 + }, + { + "epoch": 6.01, + "learning_rate": 1.6402235533797188e-05, + "loss": 0.1011, + "step": 19459 + }, + { + "epoch": 6.01, + "learning_rate": 1.640185134064681e-05, + "loss": 0.1121, + "step": 19460 + }, + { + "epoch": 6.01, + "learning_rate": 1.640146713148423e-05, + "loss": 0.1029, + "step": 19461 + }, + { + "epoch": 6.01, + "learning_rate": 1.6401082906310416e-05, + "loss": 0.1116, + "step": 19462 + }, + { + "epoch": 6.01, + "learning_rate": 1.6400698665126328e-05, + "loss": 0.0891, + "step": 19463 + }, + { + "epoch": 6.01, + "learning_rate": 1.6400314407932922e-05, + "loss": 0.1164, + "step": 19464 + }, + { + "epoch": 6.01, + "learning_rate": 1.6399930134731162e-05, + "loss": 0.1042, + "step": 19465 + }, + { + "epoch": 6.01, + "learning_rate": 1.6399545845522014e-05, + "loss": 0.1265, + "step": 19466 + }, + { + "epoch": 6.01, + "learning_rate": 1.639916154030643e-05, + "loss": 0.0979, + "step": 19467 + }, + { + "epoch": 6.01, + "learning_rate": 1.6398777219085377e-05, + "loss": 0.1092, + "step": 19468 + }, + { + "epoch": 6.01, + "learning_rate": 1.639839288185982e-05, + "loss": 0.1083, + "step": 19469 + }, + { + "epoch": 6.01, + "learning_rate": 1.6398008528630707e-05, + "loss": 0.1168, + "step": 19470 + }, + { + "epoch": 6.01, + "learning_rate": 1.639762415939901e-05, + "loss": 0.114, + "step": 19471 + }, + { + "epoch": 6.01, + "learning_rate": 1.639723977416569e-05, + "loss": 0.1017, + "step": 19472 + }, + { + "epoch": 6.01, + "learning_rate": 1.639685537293171e-05, + "loss": 0.1129, + "step": 19473 + }, + { + "epoch": 6.01, + "learning_rate": 1.639647095569802e-05, + "loss": 0.1147, + "step": 19474 + }, + { + "epoch": 6.01, + "learning_rate": 1.6396086522465594e-05, + "loss": 0.1133, + "step": 19475 + }, + { + "epoch": 6.01, + "learning_rate": 1.639570207323539e-05, + "loss": 0.1098, + "step": 19476 + }, + { + "epoch": 6.01, + "learning_rate": 1.639531760800837e-05, + "loss": 0.1074, + "step": 19477 + }, + { + "epoch": 6.02, + "learning_rate": 1.6394933126785492e-05, + "loss": 0.1246, + "step": 19478 + }, + { + "epoch": 6.02, + "learning_rate": 1.6394548629567716e-05, + "loss": 0.124, + "step": 19479 + }, + { + "epoch": 6.02, + "learning_rate": 1.6394164116356013e-05, + "loss": 0.1003, + "step": 19480 + }, + { + "epoch": 6.02, + "learning_rate": 1.6393779587151338e-05, + "loss": 0.0975, + "step": 19481 + }, + { + "epoch": 6.02, + "learning_rate": 1.639339504195465e-05, + "loss": 0.1038, + "step": 19482 + }, + { + "epoch": 6.02, + "learning_rate": 1.6393010480766923e-05, + "loss": 0.1226, + "step": 19483 + }, + { + "epoch": 6.02, + "learning_rate": 1.6392625903589105e-05, + "loss": 0.1062, + "step": 19484 + }, + { + "epoch": 6.02, + "learning_rate": 1.6392241310422163e-05, + "loss": 0.1038, + "step": 19485 + }, + { + "epoch": 6.02, + "learning_rate": 1.6391856701267065e-05, + "loss": 0.1167, + "step": 19486 + }, + { + "epoch": 6.02, + "learning_rate": 1.6391472076124762e-05, + "loss": 0.1108, + "step": 19487 + }, + { + "epoch": 6.02, + "learning_rate": 1.6391087434996224e-05, + "loss": 0.1142, + "step": 19488 + }, + { + "epoch": 6.02, + "learning_rate": 1.639070277788241e-05, + "loss": 0.1119, + "step": 19489 + }, + { + "epoch": 6.02, + "learning_rate": 1.639031810478428e-05, + "loss": 0.0997, + "step": 19490 + }, + { + "epoch": 6.02, + "learning_rate": 1.6389933415702805e-05, + "loss": 0.1039, + "step": 19491 + }, + { + "epoch": 6.02, + "learning_rate": 1.638954871063894e-05, + "loss": 0.116, + "step": 19492 + }, + { + "epoch": 6.02, + "learning_rate": 1.6389163989593645e-05, + "loss": 0.1083, + "step": 19493 + }, + { + "epoch": 6.02, + "learning_rate": 1.6388779252567885e-05, + "loss": 0.1058, + "step": 19494 + }, + { + "epoch": 6.02, + "learning_rate": 1.6388394499562628e-05, + "loss": 0.1031, + "step": 19495 + }, + { + "epoch": 6.02, + "learning_rate": 1.6388009730578827e-05, + "loss": 0.1126, + "step": 19496 + }, + { + "epoch": 6.02, + "learning_rate": 1.638762494561745e-05, + "loss": 0.1275, + "step": 19497 + }, + { + "epoch": 6.02, + "learning_rate": 1.6387240144679455e-05, + "loss": 0.1102, + "step": 19498 + }, + { + "epoch": 6.02, + "learning_rate": 1.638685532776581e-05, + "loss": 0.1046, + "step": 19499 + }, + { + "epoch": 6.02, + "learning_rate": 1.6386470494877476e-05, + "loss": 0.1043, + "step": 19500 + }, + { + "epoch": 6.02, + "learning_rate": 1.638608564601541e-05, + "loss": 0.1041, + "step": 19501 + }, + { + "epoch": 6.02, + "learning_rate": 1.6385700781180586e-05, + "loss": 0.1087, + "step": 19502 + }, + { + "epoch": 6.02, + "learning_rate": 1.6385315900373958e-05, + "loss": 0.1242, + "step": 19503 + }, + { + "epoch": 6.02, + "learning_rate": 1.6384931003596486e-05, + "loss": 0.1007, + "step": 19504 + }, + { + "epoch": 6.02, + "learning_rate": 1.638454609084914e-05, + "loss": 0.1103, + "step": 19505 + }, + { + "epoch": 6.02, + "learning_rate": 1.638416116213288e-05, + "loss": 0.1217, + "step": 19506 + }, + { + "epoch": 6.02, + "learning_rate": 1.6383776217448667e-05, + "loss": 0.1102, + "step": 19507 + }, + { + "epoch": 6.02, + "learning_rate": 1.6383391256797464e-05, + "loss": 0.113, + "step": 19508 + }, + { + "epoch": 6.02, + "learning_rate": 1.638300628018024e-05, + "loss": 0.1104, + "step": 19509 + }, + { + "epoch": 6.03, + "learning_rate": 1.638262128759795e-05, + "loss": 0.103, + "step": 19510 + }, + { + "epoch": 6.03, + "learning_rate": 1.638223627905156e-05, + "loss": 0.105, + "step": 19511 + }, + { + "epoch": 6.03, + "learning_rate": 1.6381851254542033e-05, + "loss": 0.1197, + "step": 19512 + }, + { + "epoch": 6.03, + "learning_rate": 1.6381466214070334e-05, + "loss": 0.11, + "step": 19513 + }, + { + "epoch": 6.03, + "learning_rate": 1.6381081157637422e-05, + "loss": 0.1188, + "step": 19514 + }, + { + "epoch": 6.03, + "learning_rate": 1.6380696085244264e-05, + "loss": 0.1135, + "step": 19515 + }, + { + "epoch": 6.03, + "learning_rate": 1.6380310996891816e-05, + "loss": 0.1012, + "step": 19516 + }, + { + "epoch": 6.03, + "learning_rate": 1.6379925892581054e-05, + "loss": 0.1112, + "step": 19517 + }, + { + "epoch": 6.03, + "learning_rate": 1.637954077231293e-05, + "loss": 0.1087, + "step": 19518 + }, + { + "epoch": 6.03, + "learning_rate": 1.6379155636088412e-05, + "loss": 0.11, + "step": 19519 + }, + { + "epoch": 6.03, + "learning_rate": 1.637877048390846e-05, + "loss": 0.1054, + "step": 19520 + }, + { + "epoch": 6.03, + "learning_rate": 1.637838531577404e-05, + "loss": 0.1115, + "step": 19521 + }, + { + "epoch": 6.03, + "learning_rate": 1.6378000131686116e-05, + "loss": 0.0956, + "step": 19522 + }, + { + "epoch": 6.03, + "learning_rate": 1.6377614931645652e-05, + "loss": 0.1095, + "step": 19523 + }, + { + "epoch": 6.03, + "learning_rate": 1.637722971565361e-05, + "loss": 0.1074, + "step": 19524 + }, + { + "epoch": 6.03, + "learning_rate": 1.637684448371095e-05, + "loss": 0.1131, + "step": 19525 + }, + { + "epoch": 6.03, + "learning_rate": 1.637645923581864e-05, + "loss": 0.1151, + "step": 19526 + }, + { + "epoch": 6.03, + "learning_rate": 1.6376073971977642e-05, + "loss": 0.1182, + "step": 19527 + }, + { + "epoch": 6.03, + "learning_rate": 1.637568869218892e-05, + "loss": 0.0997, + "step": 19528 + }, + { + "epoch": 6.03, + "learning_rate": 1.6375303396453443e-05, + "loss": 0.1076, + "step": 19529 + }, + { + "epoch": 6.03, + "learning_rate": 1.6374918084772166e-05, + "loss": 0.1085, + "step": 19530 + }, + { + "epoch": 6.03, + "learning_rate": 1.6374532757146053e-05, + "loss": 0.1247, + "step": 19531 + }, + { + "epoch": 6.03, + "learning_rate": 1.6374147413576076e-05, + "loss": 0.1061, + "step": 19532 + }, + { + "epoch": 6.03, + "learning_rate": 1.637376205406319e-05, + "loss": 0.1036, + "step": 19533 + }, + { + "epoch": 6.03, + "learning_rate": 1.6373376678608363e-05, + "loss": 0.113, + "step": 19534 + }, + { + "epoch": 6.03, + "learning_rate": 1.637299128721256e-05, + "loss": 0.108, + "step": 19535 + }, + { + "epoch": 6.03, + "learning_rate": 1.637260587987674e-05, + "loss": 0.1047, + "step": 19536 + }, + { + "epoch": 6.03, + "learning_rate": 1.6372220456601876e-05, + "loss": 0.1011, + "step": 19537 + }, + { + "epoch": 6.03, + "learning_rate": 1.6371835017388923e-05, + "loss": 0.1096, + "step": 19538 + }, + { + "epoch": 6.03, + "learning_rate": 1.637144956223885e-05, + "loss": 0.1168, + "step": 19539 + }, + { + "epoch": 6.03, + "learning_rate": 1.637106409115262e-05, + "loss": 0.1213, + "step": 19540 + }, + { + "epoch": 6.03, + "learning_rate": 1.637067860413119e-05, + "loss": 0.1115, + "step": 19541 + }, + { + "epoch": 6.04, + "learning_rate": 1.637029310117554e-05, + "loss": 0.102, + "step": 19542 + }, + { + "epoch": 6.04, + "learning_rate": 1.6369907582286623e-05, + "loss": 0.1125, + "step": 19543 + }, + { + "epoch": 6.04, + "learning_rate": 1.63695220474654e-05, + "loss": 0.1085, + "step": 19544 + }, + { + "epoch": 6.04, + "learning_rate": 1.6369136496712843e-05, + "loss": 0.1087, + "step": 19545 + }, + { + "epoch": 6.04, + "learning_rate": 1.6368750930029916e-05, + "loss": 0.1163, + "step": 19546 + }, + { + "epoch": 6.04, + "learning_rate": 1.6368365347417582e-05, + "loss": 0.097, + "step": 19547 + }, + { + "epoch": 6.04, + "learning_rate": 1.63679797488768e-05, + "loss": 0.1085, + "step": 19548 + }, + { + "epoch": 6.04, + "learning_rate": 1.6367594134408546e-05, + "loss": 0.1171, + "step": 19549 + }, + { + "epoch": 6.04, + "learning_rate": 1.6367208504013775e-05, + "loss": 0.1058, + "step": 19550 + }, + { + "epoch": 6.04, + "learning_rate": 1.636682285769345e-05, + "loss": 0.1145, + "step": 19551 + }, + { + "epoch": 6.04, + "learning_rate": 1.6366437195448544e-05, + "loss": 0.1255, + "step": 19552 + }, + { + "epoch": 6.04, + "learning_rate": 1.6366051517280017e-05, + "loss": 0.1211, + "step": 19553 + }, + { + "epoch": 6.04, + "learning_rate": 1.6365665823188833e-05, + "loss": 0.1072, + "step": 19554 + }, + { + "epoch": 6.04, + "learning_rate": 1.6365280113175958e-05, + "loss": 0.1058, + "step": 19555 + }, + { + "epoch": 6.04, + "learning_rate": 1.636489438724236e-05, + "loss": 0.1, + "step": 19556 + }, + { + "epoch": 6.04, + "learning_rate": 1.6364508645388996e-05, + "loss": 0.1144, + "step": 19557 + }, + { + "epoch": 6.04, + "learning_rate": 1.6364122887616835e-05, + "loss": 0.1257, + "step": 19558 + }, + { + "epoch": 6.04, + "learning_rate": 1.6363737113926845e-05, + "loss": 0.1118, + "step": 19559 + }, + { + "epoch": 6.04, + "learning_rate": 1.6363351324319984e-05, + "loss": 0.1036, + "step": 19560 + }, + { + "epoch": 6.04, + "learning_rate": 1.636296551879722e-05, + "loss": 0.104, + "step": 19561 + }, + { + "epoch": 6.04, + "learning_rate": 1.6362579697359522e-05, + "loss": 0.1075, + "step": 19562 + }, + { + "epoch": 6.04, + "learning_rate": 1.6362193860007854e-05, + "loss": 0.1073, + "step": 19563 + }, + { + "epoch": 6.04, + "learning_rate": 1.6361808006743173e-05, + "loss": 0.1171, + "step": 19564 + }, + { + "epoch": 6.04, + "learning_rate": 1.6361422137566454e-05, + "loss": 0.1092, + "step": 19565 + }, + { + "epoch": 6.04, + "learning_rate": 1.6361036252478658e-05, + "loss": 0.1258, + "step": 19566 + }, + { + "epoch": 6.04, + "learning_rate": 1.6360650351480747e-05, + "loss": 0.1143, + "step": 19567 + }, + { + "epoch": 6.04, + "learning_rate": 1.636026443457369e-05, + "loss": 0.1105, + "step": 19568 + }, + { + "epoch": 6.04, + "learning_rate": 1.6359878501758454e-05, + "loss": 0.1068, + "step": 19569 + }, + { + "epoch": 6.04, + "learning_rate": 1.6359492553036e-05, + "loss": 0.1025, + "step": 19570 + }, + { + "epoch": 6.04, + "learning_rate": 1.6359106588407297e-05, + "loss": 0.1089, + "step": 19571 + }, + { + "epoch": 6.04, + "learning_rate": 1.6358720607873308e-05, + "loss": 0.1069, + "step": 19572 + }, + { + "epoch": 6.04, + "learning_rate": 1.6358334611434997e-05, + "loss": 0.1184, + "step": 19573 + }, + { + "epoch": 6.04, + "learning_rate": 1.6357948599093335e-05, + "loss": 0.1012, + "step": 19574 + }, + { + "epoch": 6.05, + "learning_rate": 1.635756257084928e-05, + "loss": 0.1099, + "step": 19575 + }, + { + "epoch": 6.05, + "learning_rate": 1.6357176526703804e-05, + "loss": 0.1077, + "step": 19576 + }, + { + "epoch": 6.05, + "learning_rate": 1.635679046665787e-05, + "loss": 0.1032, + "step": 19577 + }, + { + "epoch": 6.05, + "learning_rate": 1.635640439071244e-05, + "loss": 0.1065, + "step": 19578 + }, + { + "epoch": 6.05, + "learning_rate": 1.6356018298868487e-05, + "loss": 0.1199, + "step": 19579 + }, + { + "epoch": 6.05, + "learning_rate": 1.6355632191126975e-05, + "loss": 0.1161, + "step": 19580 + }, + { + "epoch": 6.05, + "learning_rate": 1.6355246067488863e-05, + "loss": 0.1134, + "step": 19581 + }, + { + "epoch": 6.05, + "learning_rate": 1.6354859927955124e-05, + "loss": 0.1133, + "step": 19582 + }, + { + "epoch": 6.05, + "learning_rate": 1.635447377252672e-05, + "loss": 0.1136, + "step": 19583 + }, + { + "epoch": 6.05, + "learning_rate": 1.6354087601204617e-05, + "loss": 0.1158, + "step": 19584 + }, + { + "epoch": 6.05, + "learning_rate": 1.6353701413989784e-05, + "loss": 0.1124, + "step": 19585 + }, + { + "epoch": 6.05, + "learning_rate": 1.6353315210883187e-05, + "loss": 0.1261, + "step": 19586 + }, + { + "epoch": 6.05, + "learning_rate": 1.6352928991885787e-05, + "loss": 0.1182, + "step": 19587 + }, + { + "epoch": 6.05, + "learning_rate": 1.6352542756998554e-05, + "loss": 0.1186, + "step": 19588 + }, + { + "epoch": 6.05, + "learning_rate": 1.6352156506222453e-05, + "loss": 0.1069, + "step": 19589 + }, + { + "epoch": 6.05, + "learning_rate": 1.6351770239558447e-05, + "loss": 0.1098, + "step": 19590 + }, + { + "epoch": 6.05, + "learning_rate": 1.6351383957007508e-05, + "loss": 0.1144, + "step": 19591 + }, + { + "epoch": 6.05, + "learning_rate": 1.6350997658570598e-05, + "loss": 0.1068, + "step": 19592 + }, + { + "epoch": 6.05, + "learning_rate": 1.6350611344248687e-05, + "loss": 0.1165, + "step": 19593 + }, + { + "epoch": 6.05, + "learning_rate": 1.635022501404274e-05, + "loss": 0.1146, + "step": 19594 + }, + { + "epoch": 6.05, + "learning_rate": 1.6349838667953717e-05, + "loss": 0.1136, + "step": 19595 + }, + { + "epoch": 6.05, + "learning_rate": 1.634945230598259e-05, + "loss": 0.1299, + "step": 19596 + }, + { + "epoch": 6.05, + "learning_rate": 1.6349065928130324e-05, + "loss": 0.098, + "step": 19597 + }, + { + "epoch": 6.05, + "learning_rate": 1.6348679534397888e-05, + "loss": 0.1168, + "step": 19598 + }, + { + "epoch": 6.05, + "learning_rate": 1.634829312478625e-05, + "loss": 0.0952, + "step": 19599 + }, + { + "epoch": 6.05, + "learning_rate": 1.634790669929637e-05, + "loss": 0.0981, + "step": 19600 + }, + { + "epoch": 6.05, + "learning_rate": 1.6347520257929214e-05, + "loss": 0.1285, + "step": 19601 + }, + { + "epoch": 6.05, + "learning_rate": 1.634713380068576e-05, + "loss": 0.0965, + "step": 19602 + }, + { + "epoch": 6.05, + "learning_rate": 1.634674732756696e-05, + "loss": 0.1258, + "step": 19603 + }, + { + "epoch": 6.05, + "learning_rate": 1.634636083857379e-05, + "loss": 0.1175, + "step": 19604 + }, + { + "epoch": 6.05, + "learning_rate": 1.6345974333707215e-05, + "loss": 0.1131, + "step": 19605 + }, + { + "epoch": 6.05, + "learning_rate": 1.63455878129682e-05, + "loss": 0.1086, + "step": 19606 + }, + { + "epoch": 6.06, + "learning_rate": 1.6345201276357713e-05, + "loss": 0.1118, + "step": 19607 + }, + { + "epoch": 6.06, + "learning_rate": 1.6344814723876716e-05, + "loss": 0.1163, + "step": 19608 + }, + { + "epoch": 6.06, + "learning_rate": 1.6344428155526185e-05, + "loss": 0.116, + "step": 19609 + }, + { + "epoch": 6.06, + "learning_rate": 1.634404157130708e-05, + "loss": 0.126, + "step": 19610 + }, + { + "epoch": 6.06, + "learning_rate": 1.634365497122037e-05, + "loss": 0.1151, + "step": 19611 + }, + { + "epoch": 6.06, + "learning_rate": 1.6343268355267023e-05, + "loss": 0.1038, + "step": 19612 + }, + { + "epoch": 6.06, + "learning_rate": 1.6342881723448e-05, + "loss": 0.1353, + "step": 19613 + }, + { + "epoch": 6.06, + "learning_rate": 1.6342495075764283e-05, + "loss": 0.1051, + "step": 19614 + }, + { + "epoch": 6.06, + "learning_rate": 1.6342108412216823e-05, + "loss": 0.1148, + "step": 19615 + }, + { + "epoch": 6.06, + "learning_rate": 1.6341721732806594e-05, + "loss": 0.1157, + "step": 19616 + }, + { + "epoch": 6.06, + "learning_rate": 1.634133503753456e-05, + "loss": 0.1137, + "step": 19617 + }, + { + "epoch": 6.06, + "learning_rate": 1.6340948326401693e-05, + "loss": 0.0999, + "step": 19618 + }, + { + "epoch": 6.06, + "learning_rate": 1.6340561599408954e-05, + "loss": 0.1059, + "step": 19619 + }, + { + "epoch": 6.06, + "learning_rate": 1.634017485655732e-05, + "loss": 0.1125, + "step": 19620 + }, + { + "epoch": 6.06, + "learning_rate": 1.6339788097847748e-05, + "loss": 0.112, + "step": 19621 + }, + { + "epoch": 6.06, + "learning_rate": 1.633940132328121e-05, + "loss": 0.1007, + "step": 19622 + }, + { + "epoch": 6.06, + "learning_rate": 1.633901453285867e-05, + "loss": 0.1137, + "step": 19623 + }, + { + "epoch": 6.06, + "learning_rate": 1.6338627726581105e-05, + "loss": 0.1171, + "step": 19624 + }, + { + "epoch": 6.06, + "learning_rate": 1.6338240904449474e-05, + "loss": 0.1103, + "step": 19625 + }, + { + "epoch": 6.06, + "learning_rate": 1.6337854066464743e-05, + "loss": 0.1149, + "step": 19626 + }, + { + "epoch": 6.06, + "learning_rate": 1.6337467212627886e-05, + "loss": 0.1109, + "step": 19627 + }, + { + "epoch": 6.06, + "learning_rate": 1.633708034293987e-05, + "loss": 0.1079, + "step": 19628 + }, + { + "epoch": 6.06, + "learning_rate": 1.6336693457401657e-05, + "loss": 0.1065, + "step": 19629 + }, + { + "epoch": 6.06, + "learning_rate": 1.633630655601422e-05, + "loss": 0.1058, + "step": 19630 + }, + { + "epoch": 6.06, + "learning_rate": 1.6335919638778522e-05, + "loss": 0.1103, + "step": 19631 + }, + { + "epoch": 6.06, + "learning_rate": 1.6335532705695533e-05, + "loss": 0.1142, + "step": 19632 + }, + { + "epoch": 6.06, + "learning_rate": 1.6335145756766224e-05, + "loss": 0.1113, + "step": 19633 + }, + { + "epoch": 6.06, + "learning_rate": 1.633475879199156e-05, + "loss": 0.1181, + "step": 19634 + }, + { + "epoch": 6.06, + "learning_rate": 1.6334371811372506e-05, + "loss": 0.118, + "step": 19635 + }, + { + "epoch": 6.06, + "learning_rate": 1.6333984814910035e-05, + "loss": 0.1088, + "step": 19636 + }, + { + "epoch": 6.06, + "learning_rate": 1.633359780260511e-05, + "loss": 0.1024, + "step": 19637 + }, + { + "epoch": 6.06, + "learning_rate": 1.633321077445871e-05, + "loss": 0.1127, + "step": 19638 + }, + { + "epoch": 6.06, + "learning_rate": 1.6332823730471785e-05, + "loss": 0.105, + "step": 19639 + }, + { + "epoch": 6.07, + "learning_rate": 1.6332436670645314e-05, + "loss": 0.1165, + "step": 19640 + }, + { + "epoch": 6.07, + "learning_rate": 1.633204959498027e-05, + "loss": 0.1127, + "step": 19641 + }, + { + "epoch": 6.07, + "learning_rate": 1.633166250347761e-05, + "loss": 0.109, + "step": 19642 + }, + { + "epoch": 6.07, + "learning_rate": 1.6331275396138308e-05, + "loss": 0.1068, + "step": 19643 + }, + { + "epoch": 6.07, + "learning_rate": 1.6330888272963334e-05, + "loss": 0.1169, + "step": 19644 + }, + { + "epoch": 6.07, + "learning_rate": 1.633050113395365e-05, + "loss": 0.1056, + "step": 19645 + }, + { + "epoch": 6.07, + "learning_rate": 1.6330113979110233e-05, + "loss": 0.1189, + "step": 19646 + }, + { + "epoch": 6.07, + "learning_rate": 1.632972680843404e-05, + "loss": 0.1139, + "step": 19647 + }, + { + "epoch": 6.07, + "learning_rate": 1.6329339621926054e-05, + "loss": 0.107, + "step": 19648 + }, + { + "epoch": 6.07, + "learning_rate": 1.6328952419587228e-05, + "loss": 0.1147, + "step": 19649 + }, + { + "epoch": 6.07, + "learning_rate": 1.6328565201418542e-05, + "loss": 0.1067, + "step": 19650 + }, + { + "epoch": 6.07, + "learning_rate": 1.632817796742096e-05, + "loss": 0.1081, + "step": 19651 + }, + { + "epoch": 6.07, + "learning_rate": 1.6327790717595443e-05, + "loss": 0.115, + "step": 19652 + }, + { + "epoch": 6.07, + "learning_rate": 1.6327403451942974e-05, + "loss": 0.115, + "step": 19653 + }, + { + "epoch": 6.07, + "learning_rate": 1.6327016170464515e-05, + "loss": 0.1152, + "step": 19654 + }, + { + "epoch": 6.07, + "learning_rate": 1.632662887316103e-05, + "loss": 0.1184, + "step": 19655 + }, + { + "epoch": 6.07, + "learning_rate": 1.63262415600335e-05, + "loss": 0.0978, + "step": 19656 + }, + { + "epoch": 6.07, + "learning_rate": 1.632585423108288e-05, + "loss": 0.1032, + "step": 19657 + }, + { + "epoch": 6.07, + "learning_rate": 1.6325466886310148e-05, + "loss": 0.1037, + "step": 19658 + }, + { + "epoch": 6.07, + "learning_rate": 1.632507952571627e-05, + "loss": 0.1138, + "step": 19659 + }, + { + "epoch": 6.07, + "learning_rate": 1.632469214930221e-05, + "loss": 0.1071, + "step": 19660 + }, + { + "epoch": 6.07, + "learning_rate": 1.6324304757068948e-05, + "loss": 0.1077, + "step": 19661 + }, + { + "epoch": 6.07, + "learning_rate": 1.632391734901744e-05, + "loss": 0.1225, + "step": 19662 + }, + { + "epoch": 6.07, + "learning_rate": 1.6323529925148663e-05, + "loss": 0.0948, + "step": 19663 + }, + { + "epoch": 6.07, + "learning_rate": 1.632314248546359e-05, + "loss": 0.119, + "step": 19664 + }, + { + "epoch": 6.07, + "learning_rate": 1.6322755029963176e-05, + "loss": 0.1049, + "step": 19665 + }, + { + "epoch": 6.07, + "learning_rate": 1.63223675586484e-05, + "loss": 0.1204, + "step": 19666 + }, + { + "epoch": 6.07, + "learning_rate": 1.6321980071520232e-05, + "loss": 0.1072, + "step": 19667 + }, + { + "epoch": 6.07, + "learning_rate": 1.632159256857964e-05, + "loss": 0.1053, + "step": 19668 + }, + { + "epoch": 6.07, + "learning_rate": 1.632120504982759e-05, + "loss": 0.1132, + "step": 19669 + }, + { + "epoch": 6.07, + "learning_rate": 1.6320817515265054e-05, + "loss": 0.1069, + "step": 19670 + }, + { + "epoch": 6.07, + "learning_rate": 1.6320429964893e-05, + "loss": 0.1038, + "step": 19671 + }, + { + "epoch": 6.08, + "learning_rate": 1.6320042398712396e-05, + "loss": 0.1124, + "step": 19672 + }, + { + "epoch": 6.08, + "learning_rate": 1.6319654816724218e-05, + "loss": 0.1014, + "step": 19673 + }, + { + "epoch": 6.08, + "learning_rate": 1.631926721892943e-05, + "loss": 0.1117, + "step": 19674 + }, + { + "epoch": 6.08, + "learning_rate": 1.6318879605329e-05, + "loss": 0.1108, + "step": 19675 + }, + { + "epoch": 6.08, + "learning_rate": 1.63184919759239e-05, + "loss": 0.1212, + "step": 19676 + }, + { + "epoch": 6.08, + "learning_rate": 1.6318104330715096e-05, + "loss": 0.1153, + "step": 19677 + }, + { + "epoch": 6.08, + "learning_rate": 1.6317716669703566e-05, + "loss": 0.1296, + "step": 19678 + }, + { + "epoch": 6.08, + "learning_rate": 1.6317328992890273e-05, + "loss": 0.0987, + "step": 19679 + }, + { + "epoch": 6.08, + "learning_rate": 1.6316941300276187e-05, + "loss": 0.1141, + "step": 19680 + }, + { + "epoch": 6.08, + "learning_rate": 1.6316553591862277e-05, + "loss": 0.1099, + "step": 19681 + }, + { + "epoch": 6.08, + "learning_rate": 1.6316165867649515e-05, + "loss": 0.1035, + "step": 19682 + }, + { + "epoch": 6.08, + "learning_rate": 1.631577812763887e-05, + "loss": 0.107, + "step": 19683 + }, + { + "epoch": 6.08, + "learning_rate": 1.6315390371831315e-05, + "loss": 0.107, + "step": 19684 + }, + { + "epoch": 6.08, + "learning_rate": 1.6315002600227815e-05, + "loss": 0.1231, + "step": 19685 + }, + { + "epoch": 6.08, + "learning_rate": 1.631461481282934e-05, + "loss": 0.1248, + "step": 19686 + }, + { + "epoch": 6.08, + "learning_rate": 1.6314227009636864e-05, + "loss": 0.1178, + "step": 19687 + }, + { + "epoch": 6.08, + "learning_rate": 1.6313839190651354e-05, + "loss": 0.1038, + "step": 19688 + }, + { + "epoch": 6.08, + "learning_rate": 1.6313451355873783e-05, + "loss": 0.0958, + "step": 19689 + }, + { + "epoch": 6.08, + "learning_rate": 1.6313063505305115e-05, + "loss": 0.1082, + "step": 19690 + }, + { + "epoch": 6.08, + "learning_rate": 1.6312675638946326e-05, + "loss": 0.1094, + "step": 19691 + }, + { + "epoch": 6.08, + "learning_rate": 1.6312287756798382e-05, + "loss": 0.1085, + "step": 19692 + }, + { + "epoch": 6.08, + "learning_rate": 1.6311899858862256e-05, + "loss": 0.1037, + "step": 19693 + }, + { + "epoch": 6.08, + "learning_rate": 1.6311511945138917e-05, + "loss": 0.111, + "step": 19694 + }, + { + "epoch": 6.08, + "learning_rate": 1.6311124015629336e-05, + "loss": 0.1086, + "step": 19695 + }, + { + "epoch": 6.08, + "learning_rate": 1.6310736070334483e-05, + "loss": 0.1203, + "step": 19696 + }, + { + "epoch": 6.08, + "learning_rate": 1.6310348109255327e-05, + "loss": 0.1178, + "step": 19697 + }, + { + "epoch": 6.08, + "learning_rate": 1.630996013239284e-05, + "loss": 0.1156, + "step": 19698 + }, + { + "epoch": 6.08, + "learning_rate": 1.6309572139747992e-05, + "loss": 0.1121, + "step": 19699 + }, + { + "epoch": 6.08, + "learning_rate": 1.630918413132175e-05, + "loss": 0.1152, + "step": 19700 + }, + { + "epoch": 6.08, + "learning_rate": 1.6308796107115093e-05, + "loss": 0.0988, + "step": 19701 + }, + { + "epoch": 6.08, + "learning_rate": 1.6308408067128984e-05, + "loss": 0.1265, + "step": 19702 + }, + { + "epoch": 6.08, + "learning_rate": 1.6308020011364396e-05, + "loss": 0.114, + "step": 19703 + }, + { + "epoch": 6.09, + "learning_rate": 1.63076319398223e-05, + "loss": 0.1, + "step": 19704 + }, + { + "epoch": 6.09, + "learning_rate": 1.6307243852503665e-05, + "loss": 0.1112, + "step": 19705 + }, + { + "epoch": 6.09, + "learning_rate": 1.6306855749409464e-05, + "loss": 0.1113, + "step": 19706 + }, + { + "epoch": 6.09, + "learning_rate": 1.6306467630540664e-05, + "loss": 0.1168, + "step": 19707 + }, + { + "epoch": 6.09, + "learning_rate": 1.6306079495898243e-05, + "loss": 0.1042, + "step": 19708 + }, + { + "epoch": 6.09, + "learning_rate": 1.630569134548316e-05, + "loss": 0.1133, + "step": 19709 + }, + { + "epoch": 6.09, + "learning_rate": 1.63053031792964e-05, + "loss": 0.1019, + "step": 19710 + }, + { + "epoch": 6.09, + "learning_rate": 1.6304914997338922e-05, + "loss": 0.1042, + "step": 19711 + }, + { + "epoch": 6.09, + "learning_rate": 1.6304526799611703e-05, + "loss": 0.1052, + "step": 19712 + }, + { + "epoch": 6.09, + "learning_rate": 1.6304138586115713e-05, + "loss": 0.1101, + "step": 19713 + }, + { + "epoch": 6.09, + "learning_rate": 1.6303750356851922e-05, + "loss": 0.1046, + "step": 19714 + }, + { + "epoch": 6.09, + "learning_rate": 1.6303362111821305e-05, + "loss": 0.1199, + "step": 19715 + }, + { + "epoch": 6.09, + "learning_rate": 1.6302973851024826e-05, + "loss": 0.1123, + "step": 19716 + }, + { + "epoch": 6.09, + "learning_rate": 1.6302585574463458e-05, + "loss": 0.1213, + "step": 19717 + }, + { + "epoch": 6.09, + "learning_rate": 1.6302197282138177e-05, + "loss": 0.107, + "step": 19718 + }, + { + "epoch": 6.09, + "learning_rate": 1.630180897404995e-05, + "loss": 0.1077, + "step": 19719 + }, + { + "epoch": 6.09, + "learning_rate": 1.630142065019975e-05, + "loss": 0.1082, + "step": 19720 + }, + { + "epoch": 6.09, + "learning_rate": 1.630103231058855e-05, + "loss": 0.1031, + "step": 19721 + }, + { + "epoch": 6.09, + "learning_rate": 1.6300643955217315e-05, + "loss": 0.1126, + "step": 19722 + }, + { + "epoch": 6.09, + "learning_rate": 1.6300255584087023e-05, + "loss": 0.1047, + "step": 19723 + }, + { + "epoch": 6.09, + "learning_rate": 1.629986719719864e-05, + "loss": 0.1138, + "step": 19724 + }, + { + "epoch": 6.09, + "learning_rate": 1.629947879455314e-05, + "loss": 0.1059, + "step": 19725 + }, + { + "epoch": 6.09, + "learning_rate": 1.62990903761515e-05, + "loss": 0.1024, + "step": 19726 + }, + { + "epoch": 6.09, + "learning_rate": 1.629870194199468e-05, + "loss": 0.1238, + "step": 19727 + }, + { + "epoch": 6.09, + "learning_rate": 1.629831349208366e-05, + "loss": 0.1134, + "step": 19728 + }, + { + "epoch": 6.09, + "learning_rate": 1.629792502641941e-05, + "loss": 0.1219, + "step": 19729 + }, + { + "epoch": 6.09, + "learning_rate": 1.6297536545002902e-05, + "loss": 0.1116, + "step": 19730 + }, + { + "epoch": 6.09, + "learning_rate": 1.62971480478351e-05, + "loss": 0.1095, + "step": 19731 + }, + { + "epoch": 6.09, + "learning_rate": 1.6296759534916987e-05, + "loss": 0.1083, + "step": 19732 + }, + { + "epoch": 6.09, + "learning_rate": 1.629637100624953e-05, + "loss": 0.1074, + "step": 19733 + }, + { + "epoch": 6.09, + "learning_rate": 1.6295982461833705e-05, + "loss": 0.1171, + "step": 19734 + }, + { + "epoch": 6.09, + "learning_rate": 1.6295593901670473e-05, + "loss": 0.1194, + "step": 19735 + }, + { + "epoch": 6.09, + "learning_rate": 1.6295205325760814e-05, + "loss": 0.1198, + "step": 19736 + }, + { + "epoch": 6.1, + "learning_rate": 1.6294816734105697e-05, + "loss": 0.1152, + "step": 19737 + }, + { + "epoch": 6.1, + "learning_rate": 1.6294428126706098e-05, + "loss": 0.1246, + "step": 19738 + }, + { + "epoch": 6.1, + "learning_rate": 1.6294039503562985e-05, + "loss": 0.1123, + "step": 19739 + }, + { + "epoch": 6.1, + "learning_rate": 1.629365086467733e-05, + "loss": 0.1197, + "step": 19740 + }, + { + "epoch": 6.1, + "learning_rate": 1.629326221005011e-05, + "loss": 0.1115, + "step": 19741 + }, + { + "epoch": 6.1, + "learning_rate": 1.629287353968229e-05, + "loss": 0.1143, + "step": 19742 + }, + { + "epoch": 6.1, + "learning_rate": 1.6292484853574847e-05, + "loss": 0.1158, + "step": 19743 + }, + { + "epoch": 6.1, + "learning_rate": 1.6292096151728753e-05, + "loss": 0.1203, + "step": 19744 + }, + { + "epoch": 6.1, + "learning_rate": 1.6291707434144973e-05, + "loss": 0.1164, + "step": 19745 + }, + { + "epoch": 6.1, + "learning_rate": 1.6291318700824493e-05, + "loss": 0.1182, + "step": 19746 + }, + { + "epoch": 6.1, + "learning_rate": 1.6290929951768273e-05, + "loss": 0.1272, + "step": 19747 + }, + { + "epoch": 6.1, + "learning_rate": 1.629054118697729e-05, + "loss": 0.1227, + "step": 19748 + }, + { + "epoch": 6.1, + "learning_rate": 1.6290152406452518e-05, + "loss": 0.1281, + "step": 19749 + }, + { + "epoch": 6.1, + "learning_rate": 1.6289763610194925e-05, + "loss": 0.1079, + "step": 19750 + }, + { + "epoch": 6.1, + "learning_rate": 1.6289374798205488e-05, + "loss": 0.1073, + "step": 19751 + }, + { + "epoch": 6.1, + "learning_rate": 1.628898597048518e-05, + "loss": 0.1195, + "step": 19752 + }, + { + "epoch": 6.1, + "learning_rate": 1.6288597127034966e-05, + "loss": 0.1141, + "step": 19753 + }, + { + "epoch": 6.1, + "learning_rate": 1.6288208267855826e-05, + "loss": 0.1117, + "step": 19754 + }, + { + "epoch": 6.1, + "learning_rate": 1.628781939294873e-05, + "loss": 0.119, + "step": 19755 + }, + { + "epoch": 6.1, + "learning_rate": 1.628743050231465e-05, + "loss": 0.0962, + "step": 19756 + }, + { + "epoch": 6.1, + "learning_rate": 1.628704159595456e-05, + "loss": 0.1029, + "step": 19757 + }, + { + "epoch": 6.1, + "learning_rate": 1.628665267386943e-05, + "loss": 0.1208, + "step": 19758 + }, + { + "epoch": 6.1, + "learning_rate": 1.628626373606024e-05, + "loss": 0.1061, + "step": 19759 + }, + { + "epoch": 6.1, + "learning_rate": 1.6285874782527958e-05, + "loss": 0.1074, + "step": 19760 + }, + { + "epoch": 6.1, + "learning_rate": 1.6285485813273552e-05, + "loss": 0.1132, + "step": 19761 + }, + { + "epoch": 6.1, + "learning_rate": 1.6285096828298e-05, + "loss": 0.1127, + "step": 19762 + }, + { + "epoch": 6.1, + "learning_rate": 1.628470782760228e-05, + "loss": 0.1157, + "step": 19763 + }, + { + "epoch": 6.1, + "learning_rate": 1.6284318811187355e-05, + "loss": 0.1123, + "step": 19764 + }, + { + "epoch": 6.1, + "learning_rate": 1.62839297790542e-05, + "loss": 0.0961, + "step": 19765 + }, + { + "epoch": 6.1, + "learning_rate": 1.6283540731203794e-05, + "loss": 0.1109, + "step": 19766 + }, + { + "epoch": 6.1, + "learning_rate": 1.6283151667637108e-05, + "loss": 0.1111, + "step": 19767 + }, + { + "epoch": 6.1, + "learning_rate": 1.628276258835511e-05, + "loss": 0.1108, + "step": 19768 + }, + { + "epoch": 6.11, + "learning_rate": 1.628237349335878e-05, + "loss": 0.1057, + "step": 19769 + }, + { + "epoch": 6.11, + "learning_rate": 1.6281984382649086e-05, + "loss": 0.1145, + "step": 19770 + }, + { + "epoch": 6.11, + "learning_rate": 1.6281595256227006e-05, + "loss": 0.0983, + "step": 19771 + }, + { + "epoch": 6.11, + "learning_rate": 1.6281206114093507e-05, + "loss": 0.1265, + "step": 19772 + }, + { + "epoch": 6.11, + "learning_rate": 1.6280816956249567e-05, + "loss": 0.1042, + "step": 19773 + }, + { + "epoch": 6.11, + "learning_rate": 1.628042778269616e-05, + "loss": 0.1101, + "step": 19774 + }, + { + "epoch": 6.11, + "learning_rate": 1.6280038593434258e-05, + "loss": 0.1223, + "step": 19775 + }, + { + "epoch": 6.11, + "learning_rate": 1.627964938846483e-05, + "loss": 0.1047, + "step": 19776 + }, + { + "epoch": 6.11, + "learning_rate": 1.6279260167788857e-05, + "loss": 0.1062, + "step": 19777 + }, + { + "epoch": 6.11, + "learning_rate": 1.627887093140731e-05, + "loss": 0.115, + "step": 19778 + }, + { + "epoch": 6.11, + "learning_rate": 1.6278481679321157e-05, + "loss": 0.0964, + "step": 19779 + }, + { + "epoch": 6.11, + "learning_rate": 1.627809241153138e-05, + "loss": 0.129, + "step": 19780 + }, + { + "epoch": 6.11, + "learning_rate": 1.6277703128038947e-05, + "loss": 0.1156, + "step": 19781 + }, + { + "epoch": 6.11, + "learning_rate": 1.6277313828844835e-05, + "loss": 0.1123, + "step": 19782 + }, + { + "epoch": 6.11, + "learning_rate": 1.6276924513950016e-05, + "loss": 0.1148, + "step": 19783 + }, + { + "epoch": 6.11, + "learning_rate": 1.6276535183355462e-05, + "loss": 0.1077, + "step": 19784 + }, + { + "epoch": 6.11, + "learning_rate": 1.627614583706215e-05, + "loss": 0.1173, + "step": 19785 + }, + { + "epoch": 6.11, + "learning_rate": 1.6275756475071057e-05, + "loss": 0.1154, + "step": 19786 + }, + { + "epoch": 6.11, + "learning_rate": 1.6275367097383147e-05, + "loss": 0.107, + "step": 19787 + }, + { + "epoch": 6.11, + "learning_rate": 1.62749777039994e-05, + "loss": 0.1151, + "step": 19788 + }, + { + "epoch": 6.11, + "learning_rate": 1.627458829492079e-05, + "loss": 0.1036, + "step": 19789 + }, + { + "epoch": 6.11, + "learning_rate": 1.627419887014829e-05, + "loss": 0.118, + "step": 19790 + }, + { + "epoch": 6.11, + "learning_rate": 1.6273809429682875e-05, + "loss": 0.1122, + "step": 19791 + }, + { + "epoch": 6.11, + "learning_rate": 1.6273419973525518e-05, + "loss": 0.1044, + "step": 19792 + }, + { + "epoch": 6.11, + "learning_rate": 1.627303050167719e-05, + "loss": 0.1066, + "step": 19793 + }, + { + "epoch": 6.11, + "learning_rate": 1.6272641014138873e-05, + "loss": 0.1122, + "step": 19794 + }, + { + "epoch": 6.11, + "learning_rate": 1.6272251510911537e-05, + "loss": 0.1065, + "step": 19795 + }, + { + "epoch": 6.11, + "learning_rate": 1.627186199199615e-05, + "loss": 0.1203, + "step": 19796 + }, + { + "epoch": 6.11, + "learning_rate": 1.6271472457393704e-05, + "loss": 0.112, + "step": 19797 + }, + { + "epoch": 6.11, + "learning_rate": 1.6271082907105152e-05, + "loss": 0.1114, + "step": 19798 + }, + { + "epoch": 6.11, + "learning_rate": 1.627069334113148e-05, + "loss": 0.111, + "step": 19799 + }, + { + "epoch": 6.11, + "learning_rate": 1.6270303759473658e-05, + "loss": 0.1121, + "step": 19800 + }, + { + "epoch": 6.12, + "learning_rate": 1.6269914162132667e-05, + "loss": 0.111, + "step": 19801 + }, + { + "epoch": 6.12, + "learning_rate": 1.6269524549109474e-05, + "loss": 0.1163, + "step": 19802 + }, + { + "epoch": 6.12, + "learning_rate": 1.6269134920405058e-05, + "loss": 0.1072, + "step": 19803 + }, + { + "epoch": 6.12, + "learning_rate": 1.626874527602039e-05, + "loss": 0.1141, + "step": 19804 + }, + { + "epoch": 6.12, + "learning_rate": 1.626835561595645e-05, + "loss": 0.1109, + "step": 19805 + }, + { + "epoch": 6.12, + "learning_rate": 1.6267965940214207e-05, + "loss": 0.1083, + "step": 19806 + }, + { + "epoch": 6.12, + "learning_rate": 1.6267576248794638e-05, + "loss": 0.1111, + "step": 19807 + }, + { + "epoch": 6.12, + "learning_rate": 1.626718654169872e-05, + "loss": 0.1146, + "step": 19808 + }, + { + "epoch": 6.12, + "learning_rate": 1.6266796818927426e-05, + "loss": 0.111, + "step": 19809 + }, + { + "epoch": 6.12, + "learning_rate": 1.6266407080481726e-05, + "loss": 0.1112, + "step": 19810 + }, + { + "epoch": 6.12, + "learning_rate": 1.62660173263626e-05, + "loss": 0.1141, + "step": 19811 + }, + { + "epoch": 6.12, + "learning_rate": 1.6265627556571027e-05, + "loss": 0.1158, + "step": 19812 + }, + { + "epoch": 6.12, + "learning_rate": 1.626523777110797e-05, + "loss": 0.1135, + "step": 19813 + }, + { + "epoch": 6.12, + "learning_rate": 1.6264847969974415e-05, + "loss": 0.1023, + "step": 19814 + }, + { + "epoch": 6.12, + "learning_rate": 1.626445815317133e-05, + "loss": 0.1182, + "step": 19815 + }, + { + "epoch": 6.12, + "learning_rate": 1.6264068320699693e-05, + "loss": 0.1178, + "step": 19816 + }, + { + "epoch": 6.12, + "learning_rate": 1.626367847256048e-05, + "loss": 0.1121, + "step": 19817 + }, + { + "epoch": 6.12, + "learning_rate": 1.6263288608754662e-05, + "loss": 0.1154, + "step": 19818 + }, + { + "epoch": 6.12, + "learning_rate": 1.6262898729283222e-05, + "loss": 0.1147, + "step": 19819 + }, + { + "epoch": 6.12, + "learning_rate": 1.6262508834147124e-05, + "loss": 0.1259, + "step": 19820 + }, + { + "epoch": 6.12, + "learning_rate": 1.6262118923347354e-05, + "loss": 0.1062, + "step": 19821 + }, + { + "epoch": 6.12, + "learning_rate": 1.6261728996884877e-05, + "loss": 0.112, + "step": 19822 + }, + { + "epoch": 6.12, + "learning_rate": 1.626133905476068e-05, + "loss": 0.1148, + "step": 19823 + }, + { + "epoch": 6.12, + "learning_rate": 1.6260949096975728e-05, + "loss": 0.1231, + "step": 19824 + }, + { + "epoch": 6.12, + "learning_rate": 1.6260559123531e-05, + "loss": 0.1018, + "step": 19825 + }, + { + "epoch": 6.12, + "learning_rate": 1.6260169134427475e-05, + "loss": 0.1201, + "step": 19826 + }, + { + "epoch": 6.12, + "learning_rate": 1.6259779129666123e-05, + "loss": 0.1097, + "step": 19827 + }, + { + "epoch": 6.12, + "learning_rate": 1.6259389109247923e-05, + "loss": 0.1077, + "step": 19828 + }, + { + "epoch": 6.12, + "learning_rate": 1.625899907317385e-05, + "loss": 0.1127, + "step": 19829 + }, + { + "epoch": 6.12, + "learning_rate": 1.6258609021444874e-05, + "loss": 0.1058, + "step": 19830 + }, + { + "epoch": 6.12, + "learning_rate": 1.625821895406198e-05, + "loss": 0.1157, + "step": 19831 + }, + { + "epoch": 6.12, + "learning_rate": 1.6257828871026137e-05, + "loss": 0.106, + "step": 19832 + }, + { + "epoch": 6.12, + "learning_rate": 1.6257438772338324e-05, + "loss": 0.1031, + "step": 19833 + }, + { + "epoch": 6.13, + "learning_rate": 1.6257048657999512e-05, + "loss": 0.1084, + "step": 19834 + }, + { + "epoch": 6.13, + "learning_rate": 1.625665852801068e-05, + "loss": 0.1194, + "step": 19835 + }, + { + "epoch": 6.13, + "learning_rate": 1.625626838237281e-05, + "loss": 0.1237, + "step": 19836 + }, + { + "epoch": 6.13, + "learning_rate": 1.625587822108687e-05, + "loss": 0.1089, + "step": 19837 + }, + { + "epoch": 6.13, + "learning_rate": 1.625548804415383e-05, + "loss": 0.1162, + "step": 19838 + }, + { + "epoch": 6.13, + "learning_rate": 1.6255097851574682e-05, + "loss": 0.113, + "step": 19839 + }, + { + "epoch": 6.13, + "learning_rate": 1.6254707643350388e-05, + "loss": 0.1084, + "step": 19840 + }, + { + "epoch": 6.13, + "learning_rate": 1.625431741948193e-05, + "loss": 0.1108, + "step": 19841 + }, + { + "epoch": 6.13, + "learning_rate": 1.6253927179970287e-05, + "loss": 0.1104, + "step": 19842 + }, + { + "epoch": 6.13, + "learning_rate": 1.6253536924816435e-05, + "loss": 0.1247, + "step": 19843 + }, + { + "epoch": 6.13, + "learning_rate": 1.625314665402134e-05, + "loss": 0.1219, + "step": 19844 + }, + { + "epoch": 6.13, + "learning_rate": 1.6252756367585984e-05, + "loss": 0.1068, + "step": 19845 + }, + { + "epoch": 6.13, + "learning_rate": 1.625236606551135e-05, + "loss": 0.1203, + "step": 19846 + }, + { + "epoch": 6.13, + "learning_rate": 1.6251975747798397e-05, + "loss": 0.11, + "step": 19847 + }, + { + "epoch": 6.13, + "learning_rate": 1.625158541444812e-05, + "loss": 0.1053, + "step": 19848 + }, + { + "epoch": 6.13, + "learning_rate": 1.625119506546149e-05, + "loss": 0.1114, + "step": 19849 + }, + { + "epoch": 6.13, + "learning_rate": 1.6250804700839477e-05, + "loss": 0.11, + "step": 19850 + }, + { + "epoch": 6.13, + "learning_rate": 1.6250414320583062e-05, + "loss": 0.1244, + "step": 19851 + }, + { + "epoch": 6.13, + "learning_rate": 1.6250023924693222e-05, + "loss": 0.1159, + "step": 19852 + }, + { + "epoch": 6.13, + "learning_rate": 1.624963351317093e-05, + "loss": 0.1142, + "step": 19853 + }, + { + "epoch": 6.13, + "learning_rate": 1.624924308601717e-05, + "loss": 0.1059, + "step": 19854 + }, + { + "epoch": 6.13, + "learning_rate": 1.6248852643232905e-05, + "loss": 0.1201, + "step": 19855 + }, + { + "epoch": 6.13, + "learning_rate": 1.6248462184819128e-05, + "loss": 0.0979, + "step": 19856 + }, + { + "epoch": 6.13, + "learning_rate": 1.6248071710776803e-05, + "loss": 0.1193, + "step": 19857 + }, + { + "epoch": 6.13, + "learning_rate": 1.624768122110691e-05, + "loss": 0.118, + "step": 19858 + }, + { + "epoch": 6.13, + "learning_rate": 1.624729071581043e-05, + "loss": 0.1033, + "step": 19859 + }, + { + "epoch": 6.13, + "learning_rate": 1.6246900194888334e-05, + "loss": 0.1002, + "step": 19860 + }, + { + "epoch": 6.13, + "learning_rate": 1.6246509658341602e-05, + "loss": 0.1101, + "step": 19861 + }, + { + "epoch": 6.13, + "learning_rate": 1.624611910617121e-05, + "loss": 0.117, + "step": 19862 + }, + { + "epoch": 6.13, + "learning_rate": 1.6245728538378135e-05, + "loss": 0.1086, + "step": 19863 + }, + { + "epoch": 6.13, + "learning_rate": 1.6245337954963356e-05, + "loss": 0.1095, + "step": 19864 + }, + { + "epoch": 6.13, + "learning_rate": 1.6244947355927845e-05, + "loss": 0.1089, + "step": 19865 + }, + { + "epoch": 6.14, + "learning_rate": 1.6244556741272583e-05, + "loss": 0.1206, + "step": 19866 + }, + { + "epoch": 6.14, + "learning_rate": 1.6244166110998545e-05, + "loss": 0.1205, + "step": 19867 + }, + { + "epoch": 6.14, + "learning_rate": 1.624377546510671e-05, + "loss": 0.1147, + "step": 19868 + }, + { + "epoch": 6.14, + "learning_rate": 1.6243384803598047e-05, + "loss": 0.1146, + "step": 19869 + }, + { + "epoch": 6.14, + "learning_rate": 1.624299412647355e-05, + "loss": 0.1093, + "step": 19870 + }, + { + "epoch": 6.14, + "learning_rate": 1.624260343373418e-05, + "loss": 0.1129, + "step": 19871 + }, + { + "epoch": 6.14, + "learning_rate": 1.624221272538092e-05, + "loss": 0.1034, + "step": 19872 + }, + { + "epoch": 6.14, + "learning_rate": 1.624182200141475e-05, + "loss": 0.1119, + "step": 19873 + }, + { + "epoch": 6.14, + "learning_rate": 1.6241431261836646e-05, + "loss": 0.1129, + "step": 19874 + }, + { + "epoch": 6.14, + "learning_rate": 1.624104050664758e-05, + "loss": 0.1121, + "step": 19875 + }, + { + "epoch": 6.14, + "learning_rate": 1.6240649735848535e-05, + "loss": 0.1128, + "step": 19876 + }, + { + "epoch": 6.14, + "learning_rate": 1.6240258949440487e-05, + "loss": 0.1251, + "step": 19877 + }, + { + "epoch": 6.14, + "learning_rate": 1.623986814742441e-05, + "loss": 0.1154, + "step": 19878 + }, + { + "epoch": 6.14, + "learning_rate": 1.623947732980129e-05, + "loss": 0.1084, + "step": 19879 + }, + { + "epoch": 6.14, + "learning_rate": 1.62390864965721e-05, + "loss": 0.1115, + "step": 19880 + }, + { + "epoch": 6.14, + "learning_rate": 1.623869564773781e-05, + "loss": 0.124, + "step": 19881 + }, + { + "epoch": 6.14, + "learning_rate": 1.623830478329941e-05, + "loss": 0.1227, + "step": 19882 + }, + { + "epoch": 6.14, + "learning_rate": 1.623791390325787e-05, + "loss": 0.1119, + "step": 19883 + }, + { + "epoch": 6.14, + "learning_rate": 1.623752300761417e-05, + "loss": 0.1139, + "step": 19884 + }, + { + "epoch": 6.14, + "learning_rate": 1.6237132096369288e-05, + "loss": 0.119, + "step": 19885 + }, + { + "epoch": 6.14, + "learning_rate": 1.6236741169524197e-05, + "loss": 0.1289, + "step": 19886 + }, + { + "epoch": 6.14, + "learning_rate": 1.6236350227079883e-05, + "loss": 0.109, + "step": 19887 + }, + { + "epoch": 6.14, + "learning_rate": 1.623595926903732e-05, + "loss": 0.1144, + "step": 19888 + }, + { + "epoch": 6.14, + "learning_rate": 1.6235568295397482e-05, + "loss": 0.1255, + "step": 19889 + }, + { + "epoch": 6.14, + "learning_rate": 1.6235177306161353e-05, + "loss": 0.1042, + "step": 19890 + }, + { + "epoch": 6.14, + "learning_rate": 1.623478630132991e-05, + "loss": 0.1168, + "step": 19891 + }, + { + "epoch": 6.14, + "learning_rate": 1.6234395280904126e-05, + "loss": 0.1131, + "step": 19892 + }, + { + "epoch": 6.14, + "learning_rate": 1.6234004244884982e-05, + "loss": 0.1261, + "step": 19893 + }, + { + "epoch": 6.14, + "learning_rate": 1.623361319327346e-05, + "loss": 0.1244, + "step": 19894 + }, + { + "epoch": 6.14, + "learning_rate": 1.623322212607053e-05, + "loss": 0.1181, + "step": 19895 + }, + { + "epoch": 6.14, + "learning_rate": 1.6232831043277176e-05, + "loss": 0.1072, + "step": 19896 + }, + { + "epoch": 6.14, + "learning_rate": 1.6232439944894374e-05, + "loss": 0.1177, + "step": 19897 + }, + { + "epoch": 6.14, + "learning_rate": 1.6232048830923107e-05, + "loss": 0.1223, + "step": 19898 + }, + { + "epoch": 6.15, + "learning_rate": 1.6231657701364346e-05, + "loss": 0.1178, + "step": 19899 + }, + { + "epoch": 6.15, + "learning_rate": 1.623126655621907e-05, + "loss": 0.117, + "step": 19900 + }, + { + "epoch": 6.15, + "learning_rate": 1.6230875395488264e-05, + "loss": 0.1186, + "step": 19901 + }, + { + "epoch": 6.15, + "learning_rate": 1.6230484219172905e-05, + "loss": 0.1135, + "step": 19902 + }, + { + "epoch": 6.15, + "learning_rate": 1.6230093027273963e-05, + "loss": 0.1148, + "step": 19903 + }, + { + "epoch": 6.15, + "learning_rate": 1.6229701819792426e-05, + "loss": 0.1127, + "step": 19904 + }, + { + "epoch": 6.15, + "learning_rate": 1.6229310596729268e-05, + "loss": 0.1182, + "step": 19905 + }, + { + "epoch": 6.15, + "learning_rate": 1.6228919358085464e-05, + "loss": 0.1212, + "step": 19906 + }, + { + "epoch": 6.15, + "learning_rate": 1.6228528103862e-05, + "loss": 0.1283, + "step": 19907 + }, + { + "epoch": 6.15, + "learning_rate": 1.622813683405985e-05, + "loss": 0.1127, + "step": 19908 + }, + { + "epoch": 6.15, + "learning_rate": 1.6227745548679995e-05, + "loss": 0.1173, + "step": 19909 + }, + { + "epoch": 6.15, + "learning_rate": 1.622735424772341e-05, + "loss": 0.1007, + "step": 19910 + }, + { + "epoch": 6.15, + "learning_rate": 1.6226962931191076e-05, + "loss": 0.1077, + "step": 19911 + }, + { + "epoch": 6.15, + "learning_rate": 1.6226571599083976e-05, + "loss": 0.1154, + "step": 19912 + }, + { + "epoch": 6.15, + "learning_rate": 1.6226180251403085e-05, + "loss": 0.1177, + "step": 19913 + }, + { + "epoch": 6.15, + "learning_rate": 1.6225788888149377e-05, + "loss": 0.1162, + "step": 19914 + }, + { + "epoch": 6.15, + "learning_rate": 1.6225397509323836e-05, + "loss": 0.1064, + "step": 19915 + }, + { + "epoch": 6.15, + "learning_rate": 1.622500611492744e-05, + "loss": 0.1063, + "step": 19916 + }, + { + "epoch": 6.15, + "learning_rate": 1.6224614704961174e-05, + "loss": 0.1261, + "step": 19917 + }, + { + "epoch": 6.15, + "learning_rate": 1.6224223279426007e-05, + "loss": 0.1112, + "step": 19918 + }, + { + "epoch": 6.15, + "learning_rate": 1.6223831838322925e-05, + "loss": 0.1064, + "step": 19919 + }, + { + "epoch": 6.15, + "learning_rate": 1.62234403816529e-05, + "loss": 0.102, + "step": 19920 + }, + { + "epoch": 6.15, + "learning_rate": 1.622304890941692e-05, + "loss": 0.1138, + "step": 19921 + }, + { + "epoch": 6.15, + "learning_rate": 1.6222657421615957e-05, + "loss": 0.1146, + "step": 19922 + }, + { + "epoch": 6.15, + "learning_rate": 1.6222265918250993e-05, + "loss": 0.1056, + "step": 19923 + }, + { + "epoch": 6.15, + "learning_rate": 1.6221874399323007e-05, + "loss": 0.0969, + "step": 19924 + }, + { + "epoch": 6.15, + "learning_rate": 1.622148286483298e-05, + "loss": 0.1067, + "step": 19925 + }, + { + "epoch": 6.15, + "learning_rate": 1.622109131478189e-05, + "loss": 0.1086, + "step": 19926 + }, + { + "epoch": 6.15, + "learning_rate": 1.6220699749170714e-05, + "loss": 0.1165, + "step": 19927 + }, + { + "epoch": 6.15, + "learning_rate": 1.6220308168000433e-05, + "loss": 0.1237, + "step": 19928 + }, + { + "epoch": 6.15, + "learning_rate": 1.6219916571272024e-05, + "loss": 0.1181, + "step": 19929 + }, + { + "epoch": 6.15, + "learning_rate": 1.6219524958986476e-05, + "loss": 0.125, + "step": 19930 + }, + { + "epoch": 6.16, + "learning_rate": 1.6219133331144758e-05, + "loss": 0.1072, + "step": 19931 + }, + { + "epoch": 6.16, + "learning_rate": 1.6218741687747856e-05, + "loss": 0.1187, + "step": 19932 + }, + { + "epoch": 6.16, + "learning_rate": 1.6218350028796742e-05, + "loss": 0.1105, + "step": 19933 + }, + { + "epoch": 6.16, + "learning_rate": 1.6217958354292402e-05, + "loss": 0.1111, + "step": 19934 + }, + { + "epoch": 6.16, + "learning_rate": 1.6217566664235816e-05, + "loss": 0.1142, + "step": 19935 + }, + { + "epoch": 6.16, + "learning_rate": 1.6217174958627963e-05, + "loss": 0.1116, + "step": 19936 + }, + { + "epoch": 6.16, + "learning_rate": 1.6216783237469817e-05, + "loss": 0.1244, + "step": 19937 + }, + { + "epoch": 6.16, + "learning_rate": 1.6216391500762366e-05, + "loss": 0.1057, + "step": 19938 + }, + { + "epoch": 6.16, + "learning_rate": 1.6215999748506582e-05, + "loss": 0.1375, + "step": 19939 + }, + { + "epoch": 6.16, + "learning_rate": 1.6215607980703454e-05, + "loss": 0.1145, + "step": 19940 + }, + { + "epoch": 6.16, + "learning_rate": 1.6215216197353954e-05, + "loss": 0.1187, + "step": 19941 + }, + { + "epoch": 6.16, + "learning_rate": 1.6214824398459066e-05, + "loss": 0.104, + "step": 19942 + }, + { + "epoch": 6.16, + "learning_rate": 1.6214432584019767e-05, + "loss": 0.1195, + "step": 19943 + }, + { + "epoch": 6.16, + "learning_rate": 1.6214040754037038e-05, + "loss": 0.1069, + "step": 19944 + }, + { + "epoch": 6.16, + "learning_rate": 1.6213648908511864e-05, + "loss": 0.124, + "step": 19945 + }, + { + "epoch": 6.16, + "learning_rate": 1.6213257047445217e-05, + "loss": 0.121, + "step": 19946 + }, + { + "epoch": 6.16, + "learning_rate": 1.621286517083808e-05, + "loss": 0.1139, + "step": 19947 + }, + { + "epoch": 6.16, + "learning_rate": 1.6212473278691435e-05, + "loss": 0.0959, + "step": 19948 + }, + { + "epoch": 6.16, + "learning_rate": 1.6212081371006263e-05, + "loss": 0.1076, + "step": 19949 + }, + { + "epoch": 6.16, + "learning_rate": 1.6211689447783543e-05, + "loss": 0.1119, + "step": 19950 + }, + { + "epoch": 6.16, + "learning_rate": 1.621129750902425e-05, + "loss": 0.1094, + "step": 19951 + }, + { + "epoch": 6.16, + "learning_rate": 1.6210905554729376e-05, + "loss": 0.1179, + "step": 19952 + }, + { + "epoch": 6.16, + "learning_rate": 1.6210513584899888e-05, + "loss": 0.1076, + "step": 19953 + }, + { + "epoch": 6.16, + "learning_rate": 1.6210121599536778e-05, + "loss": 0.1085, + "step": 19954 + }, + { + "epoch": 6.16, + "learning_rate": 1.6209729598641018e-05, + "loss": 0.1087, + "step": 19955 + }, + { + "epoch": 6.16, + "learning_rate": 1.620933758221359e-05, + "loss": 0.1104, + "step": 19956 + }, + { + "epoch": 6.16, + "learning_rate": 1.6208945550255482e-05, + "loss": 0.116, + "step": 19957 + }, + { + "epoch": 6.16, + "learning_rate": 1.6208553502767665e-05, + "loss": 0.1139, + "step": 19958 + }, + { + "epoch": 6.16, + "learning_rate": 1.6208161439751126e-05, + "loss": 0.1152, + "step": 19959 + }, + { + "epoch": 6.16, + "learning_rate": 1.620776936120684e-05, + "loss": 0.1039, + "step": 19960 + }, + { + "epoch": 6.16, + "learning_rate": 1.6207377267135788e-05, + "loss": 0.1044, + "step": 19961 + }, + { + "epoch": 6.16, + "learning_rate": 1.6206985157538958e-05, + "loss": 0.1174, + "step": 19962 + }, + { + "epoch": 6.17, + "learning_rate": 1.6206593032417322e-05, + "loss": 0.1228, + "step": 19963 + }, + { + "epoch": 6.17, + "learning_rate": 1.620620089177187e-05, + "loss": 0.1097, + "step": 19964 + }, + { + "epoch": 6.17, + "learning_rate": 1.6205808735603573e-05, + "loss": 0.1116, + "step": 19965 + }, + { + "epoch": 6.17, + "learning_rate": 1.620541656391342e-05, + "loss": 0.1107, + "step": 19966 + }, + { + "epoch": 6.17, + "learning_rate": 1.6205024376702386e-05, + "loss": 0.1042, + "step": 19967 + }, + { + "epoch": 6.17, + "learning_rate": 1.6204632173971458e-05, + "loss": 0.1156, + "step": 19968 + }, + { + "epoch": 6.17, + "learning_rate": 1.620423995572161e-05, + "loss": 0.1175, + "step": 19969 + }, + { + "epoch": 6.17, + "learning_rate": 1.6203847721953826e-05, + "loss": 0.1237, + "step": 19970 + }, + { + "epoch": 6.17, + "learning_rate": 1.6203455472669086e-05, + "loss": 0.1211, + "step": 19971 + }, + { + "epoch": 6.17, + "learning_rate": 1.6203063207868373e-05, + "loss": 0.1037, + "step": 19972 + }, + { + "epoch": 6.17, + "learning_rate": 1.6202670927552673e-05, + "loss": 0.1198, + "step": 19973 + }, + { + "epoch": 6.17, + "learning_rate": 1.6202278631722958e-05, + "loss": 0.1322, + "step": 19974 + }, + { + "epoch": 6.17, + "learning_rate": 1.620188632038021e-05, + "loss": 0.1154, + "step": 19975 + }, + { + "epoch": 6.17, + "learning_rate": 1.620149399352542e-05, + "loss": 0.1209, + "step": 19976 + }, + { + "epoch": 6.17, + "learning_rate": 1.6201101651159556e-05, + "loss": 0.104, + "step": 19977 + }, + { + "epoch": 6.17, + "learning_rate": 1.6200709293283606e-05, + "loss": 0.1042, + "step": 19978 + }, + { + "epoch": 6.17, + "learning_rate": 1.6200316919898552e-05, + "loss": 0.1127, + "step": 19979 + }, + { + "epoch": 6.17, + "learning_rate": 1.619992453100538e-05, + "loss": 0.1098, + "step": 19980 + }, + { + "epoch": 6.17, + "learning_rate": 1.619953212660506e-05, + "loss": 0.1056, + "step": 19981 + }, + { + "epoch": 6.17, + "learning_rate": 1.619913970669858e-05, + "loss": 0.1196, + "step": 19982 + }, + { + "epoch": 6.17, + "learning_rate": 1.6198747271286923e-05, + "loss": 0.1105, + "step": 19983 + }, + { + "epoch": 6.17, + "learning_rate": 1.619835482037107e-05, + "loss": 0.1094, + "step": 19984 + }, + { + "epoch": 6.17, + "learning_rate": 1.6197962353951995e-05, + "loss": 0.1189, + "step": 19985 + }, + { + "epoch": 6.17, + "learning_rate": 1.619756987203069e-05, + "loss": 0.1173, + "step": 19986 + }, + { + "epoch": 6.17, + "learning_rate": 1.6197177374608132e-05, + "loss": 0.1164, + "step": 19987 + }, + { + "epoch": 6.17, + "learning_rate": 1.6196784861685303e-05, + "loss": 0.1129, + "step": 19988 + }, + { + "epoch": 6.17, + "learning_rate": 1.6196392333263183e-05, + "loss": 0.1075, + "step": 19989 + }, + { + "epoch": 6.17, + "learning_rate": 1.619599978934276e-05, + "loss": 0.1119, + "step": 19990 + }, + { + "epoch": 6.17, + "learning_rate": 1.6195607229925007e-05, + "loss": 0.1082, + "step": 19991 + }, + { + "epoch": 6.17, + "learning_rate": 1.6195214655010912e-05, + "loss": 0.1218, + "step": 19992 + }, + { + "epoch": 6.17, + "learning_rate": 1.6194822064601458e-05, + "loss": 0.1098, + "step": 19993 + }, + { + "epoch": 6.17, + "learning_rate": 1.619442945869762e-05, + "loss": 0.1193, + "step": 19994 + }, + { + "epoch": 6.17, + "learning_rate": 1.6194036837300386e-05, + "loss": 0.116, + "step": 19995 + }, + { + "epoch": 6.18, + "learning_rate": 1.6193644200410734e-05, + "loss": 0.1102, + "step": 19996 + }, + { + "epoch": 6.18, + "learning_rate": 1.619325154802965e-05, + "loss": 0.1204, + "step": 19997 + }, + { + "epoch": 6.18, + "learning_rate": 1.6192858880158113e-05, + "loss": 0.1151, + "step": 19998 + }, + { + "epoch": 6.18, + "learning_rate": 1.619246619679711e-05, + "loss": 0.1124, + "step": 19999 + }, + { + "epoch": 6.18, + "learning_rate": 1.6192073497947617e-05, + "loss": 0.11, + "step": 20000 + }, + { + "epoch": 6.18, + "learning_rate": 1.6191680783610618e-05, + "loss": 0.1126, + "step": 20001 + }, + { + "epoch": 6.18, + "learning_rate": 1.6191288053787096e-05, + "loss": 0.1162, + "step": 20002 + }, + { + "epoch": 6.18, + "learning_rate": 1.6190895308478036e-05, + "loss": 0.1069, + "step": 20003 + }, + { + "epoch": 6.18, + "learning_rate": 1.6190502547684418e-05, + "loss": 0.1124, + "step": 20004 + }, + { + "epoch": 6.18, + "learning_rate": 1.619010977140722e-05, + "loss": 0.1103, + "step": 20005 + }, + { + "epoch": 6.18, + "learning_rate": 1.6189716979647433e-05, + "loss": 0.1135, + "step": 20006 + }, + { + "epoch": 6.18, + "learning_rate": 1.618932417240603e-05, + "loss": 0.1091, + "step": 20007 + }, + { + "epoch": 6.18, + "learning_rate": 1.6188931349684e-05, + "loss": 0.1217, + "step": 20008 + }, + { + "epoch": 6.18, + "learning_rate": 1.6188538511482326e-05, + "loss": 0.1088, + "step": 20009 + }, + { + "epoch": 6.18, + "learning_rate": 1.6188145657801987e-05, + "loss": 0.1127, + "step": 20010 + }, + { + "epoch": 6.18, + "learning_rate": 1.6187752788643967e-05, + "loss": 0.1109, + "step": 20011 + }, + { + "epoch": 6.18, + "learning_rate": 1.618735990400925e-05, + "loss": 0.1112, + "step": 20012 + }, + { + "epoch": 6.18, + "learning_rate": 1.6186967003898814e-05, + "loss": 0.1102, + "step": 20013 + }, + { + "epoch": 6.18, + "learning_rate": 1.6186574088313648e-05, + "loss": 0.117, + "step": 20014 + }, + { + "epoch": 6.18, + "learning_rate": 1.6186181157254732e-05, + "loss": 0.1219, + "step": 20015 + }, + { + "epoch": 6.18, + "learning_rate": 1.6185788210723048e-05, + "loss": 0.1013, + "step": 20016 + }, + { + "epoch": 6.18, + "learning_rate": 1.618539524871958e-05, + "loss": 0.1163, + "step": 20017 + }, + { + "epoch": 6.18, + "learning_rate": 1.618500227124531e-05, + "loss": 0.1168, + "step": 20018 + }, + { + "epoch": 6.18, + "learning_rate": 1.618460927830122e-05, + "loss": 0.1171, + "step": 20019 + }, + { + "epoch": 6.18, + "learning_rate": 1.6184216269888296e-05, + "loss": 0.1082, + "step": 20020 + }, + { + "epoch": 6.18, + "learning_rate": 1.6183823246007518e-05, + "loss": 0.1154, + "step": 20021 + }, + { + "epoch": 6.18, + "learning_rate": 1.618343020665987e-05, + "loss": 0.1217, + "step": 20022 + }, + { + "epoch": 6.18, + "learning_rate": 1.6183037151846338e-05, + "loss": 0.1197, + "step": 20023 + }, + { + "epoch": 6.18, + "learning_rate": 1.61826440815679e-05, + "loss": 0.1248, + "step": 20024 + }, + { + "epoch": 6.18, + "learning_rate": 1.6182250995825542e-05, + "loss": 0.1067, + "step": 20025 + }, + { + "epoch": 6.18, + "learning_rate": 1.6181857894620245e-05, + "loss": 0.1264, + "step": 20026 + }, + { + "epoch": 6.18, + "learning_rate": 1.6181464777952998e-05, + "loss": 0.1105, + "step": 20027 + }, + { + "epoch": 6.19, + "learning_rate": 1.6181071645824774e-05, + "loss": 0.1177, + "step": 20028 + }, + { + "epoch": 6.19, + "learning_rate": 1.618067849823657e-05, + "loss": 0.1095, + "step": 20029 + }, + { + "epoch": 6.19, + "learning_rate": 1.6180285335189356e-05, + "loss": 0.1132, + "step": 20030 + }, + { + "epoch": 6.19, + "learning_rate": 1.6179892156684123e-05, + "loss": 0.1194, + "step": 20031 + }, + { + "epoch": 6.19, + "learning_rate": 1.617949896272185e-05, + "loss": 0.1128, + "step": 20032 + }, + { + "epoch": 6.19, + "learning_rate": 1.6179105753303526e-05, + "loss": 0.1154, + "step": 20033 + }, + { + "epoch": 6.19, + "learning_rate": 1.617871252843013e-05, + "loss": 0.1134, + "step": 20034 + }, + { + "epoch": 6.19, + "learning_rate": 1.617831928810265e-05, + "loss": 0.1101, + "step": 20035 + }, + { + "epoch": 6.19, + "learning_rate": 1.6177926032322063e-05, + "loss": 0.1135, + "step": 20036 + }, + { + "epoch": 6.19, + "learning_rate": 1.617753276108936e-05, + "loss": 0.1104, + "step": 20037 + }, + { + "epoch": 6.19, + "learning_rate": 1.617713947440552e-05, + "loss": 0.1171, + "step": 20038 + }, + { + "epoch": 6.19, + "learning_rate": 1.6176746172271522e-05, + "loss": 0.1185, + "step": 20039 + }, + { + "epoch": 6.19, + "learning_rate": 1.6176352854688362e-05, + "loss": 0.1129, + "step": 20040 + }, + { + "epoch": 6.19, + "learning_rate": 1.6175959521657014e-05, + "loss": 0.1202, + "step": 20041 + }, + { + "epoch": 6.19, + "learning_rate": 1.6175566173178466e-05, + "loss": 0.1152, + "step": 20042 + }, + { + "epoch": 6.19, + "learning_rate": 1.61751728092537e-05, + "loss": 0.1075, + "step": 20043 + }, + { + "epoch": 6.19, + "learning_rate": 1.6174779429883697e-05, + "loss": 0.1095, + "step": 20044 + }, + { + "epoch": 6.19, + "learning_rate": 1.617438603506945e-05, + "loss": 0.1118, + "step": 20045 + }, + { + "epoch": 6.19, + "learning_rate": 1.6173992624811935e-05, + "loss": 0.1083, + "step": 20046 + }, + { + "epoch": 6.19, + "learning_rate": 1.617359919911214e-05, + "loss": 0.1241, + "step": 20047 + }, + { + "epoch": 6.19, + "learning_rate": 1.6173205757971048e-05, + "loss": 0.1163, + "step": 20048 + }, + { + "epoch": 6.19, + "learning_rate": 1.617281230138964e-05, + "loss": 0.1074, + "step": 20049 + }, + { + "epoch": 6.19, + "learning_rate": 1.6172418829368902e-05, + "loss": 0.1096, + "step": 20050 + }, + { + "epoch": 6.19, + "learning_rate": 1.617202534190982e-05, + "loss": 0.1127, + "step": 20051 + }, + { + "epoch": 6.19, + "learning_rate": 1.617163183901338e-05, + "loss": 0.1057, + "step": 20052 + }, + { + "epoch": 6.19, + "learning_rate": 1.6171238320680557e-05, + "loss": 0.1095, + "step": 20053 + }, + { + "epoch": 6.19, + "learning_rate": 1.6170844786912346e-05, + "loss": 0.1128, + "step": 20054 + }, + { + "epoch": 6.19, + "learning_rate": 1.6170451237709723e-05, + "loss": 0.1214, + "step": 20055 + }, + { + "epoch": 6.19, + "learning_rate": 1.617005767307368e-05, + "loss": 0.123, + "step": 20056 + }, + { + "epoch": 6.19, + "learning_rate": 1.6169664093005194e-05, + "loss": 0.1271, + "step": 20057 + }, + { + "epoch": 6.19, + "learning_rate": 1.6169270497505255e-05, + "loss": 0.1195, + "step": 20058 + }, + { + "epoch": 6.19, + "learning_rate": 1.6168876886574842e-05, + "loss": 0.1131, + "step": 20059 + }, + { + "epoch": 6.19, + "learning_rate": 1.6168483260214948e-05, + "loss": 0.1122, + "step": 20060 + }, + { + "epoch": 6.2, + "learning_rate": 1.616808961842655e-05, + "loss": 0.1147, + "step": 20061 + }, + { + "epoch": 6.2, + "learning_rate": 1.6167695961210635e-05, + "loss": 0.1093, + "step": 20062 + }, + { + "epoch": 6.2, + "learning_rate": 1.6167302288568186e-05, + "loss": 0.1188, + "step": 20063 + }, + { + "epoch": 6.2, + "learning_rate": 1.616690860050019e-05, + "loss": 0.1108, + "step": 20064 + }, + { + "epoch": 6.2, + "learning_rate": 1.616651489700763e-05, + "loss": 0.111, + "step": 20065 + }, + { + "epoch": 6.2, + "learning_rate": 1.6166121178091494e-05, + "loss": 0.1075, + "step": 20066 + }, + { + "epoch": 6.2, + "learning_rate": 1.6165727443752762e-05, + "loss": 0.1086, + "step": 20067 + }, + { + "epoch": 6.2, + "learning_rate": 1.6165333693992423e-05, + "loss": 0.1128, + "step": 20068 + }, + { + "epoch": 6.2, + "learning_rate": 1.616493992881146e-05, + "loss": 0.1107, + "step": 20069 + }, + { + "epoch": 6.2, + "learning_rate": 1.6164546148210854e-05, + "loss": 0.0988, + "step": 20070 + }, + { + "epoch": 6.2, + "learning_rate": 1.61641523521916e-05, + "loss": 0.1195, + "step": 20071 + }, + { + "epoch": 6.2, + "learning_rate": 1.616375854075467e-05, + "loss": 0.1167, + "step": 20072 + }, + { + "epoch": 6.2, + "learning_rate": 1.616336471390106e-05, + "loss": 0.1293, + "step": 20073 + }, + { + "epoch": 6.2, + "learning_rate": 1.616297087163175e-05, + "loss": 0.1187, + "step": 20074 + }, + { + "epoch": 6.2, + "learning_rate": 1.6162577013947726e-05, + "loss": 0.106, + "step": 20075 + }, + { + "epoch": 6.2, + "learning_rate": 1.616218314084997e-05, + "loss": 0.1131, + "step": 20076 + }, + { + "epoch": 6.2, + "learning_rate": 1.6161789252339472e-05, + "loss": 0.1198, + "step": 20077 + }, + { + "epoch": 6.2, + "learning_rate": 1.6161395348417215e-05, + "loss": 0.1056, + "step": 20078 + }, + { + "epoch": 6.2, + "learning_rate": 1.6161001429084183e-05, + "loss": 0.1145, + "step": 20079 + }, + { + "epoch": 6.2, + "learning_rate": 1.6160607494341365e-05, + "loss": 0.1102, + "step": 20080 + }, + { + "epoch": 6.2, + "learning_rate": 1.6160213544189748e-05, + "loss": 0.1205, + "step": 20081 + }, + { + "epoch": 6.2, + "learning_rate": 1.6159819578630306e-05, + "loss": 0.1162, + "step": 20082 + }, + { + "epoch": 6.2, + "learning_rate": 1.6159425597664037e-05, + "loss": 0.115, + "step": 20083 + }, + { + "epoch": 6.2, + "learning_rate": 1.615903160129192e-05, + "loss": 0.1135, + "step": 20084 + }, + { + "epoch": 6.2, + "learning_rate": 1.6158637589514937e-05, + "loss": 0.1171, + "step": 20085 + }, + { + "epoch": 6.2, + "learning_rate": 1.6158243562334082e-05, + "loss": 0.1133, + "step": 20086 + }, + { + "epoch": 6.2, + "learning_rate": 1.6157849519750337e-05, + "loss": 0.1058, + "step": 20087 + }, + { + "epoch": 6.2, + "learning_rate": 1.615745546176469e-05, + "loss": 0.1191, + "step": 20088 + }, + { + "epoch": 6.2, + "learning_rate": 1.615706138837812e-05, + "loss": 0.1087, + "step": 20089 + }, + { + "epoch": 6.2, + "learning_rate": 1.6156667299591617e-05, + "loss": 0.1191, + "step": 20090 + }, + { + "epoch": 6.2, + "learning_rate": 1.6156273195406163e-05, + "loss": 0.1231, + "step": 20091 + }, + { + "epoch": 6.2, + "learning_rate": 1.6155879075822752e-05, + "loss": 0.1058, + "step": 20092 + }, + { + "epoch": 6.21, + "learning_rate": 1.6155484940842362e-05, + "loss": 0.1259, + "step": 20093 + }, + { + "epoch": 6.21, + "learning_rate": 1.6155090790465983e-05, + "loss": 0.1154, + "step": 20094 + }, + { + "epoch": 6.21, + "learning_rate": 1.61546966246946e-05, + "loss": 0.1154, + "step": 20095 + }, + { + "epoch": 6.21, + "learning_rate": 1.6154302443529197e-05, + "loss": 0.1006, + "step": 20096 + }, + { + "epoch": 6.21, + "learning_rate": 1.6153908246970758e-05, + "loss": 0.1209, + "step": 20097 + }, + { + "epoch": 6.21, + "learning_rate": 1.6153514035020274e-05, + "loss": 0.1097, + "step": 20098 + }, + { + "epoch": 6.21, + "learning_rate": 1.615311980767873e-05, + "loss": 0.1184, + "step": 20099 + }, + { + "epoch": 6.21, + "learning_rate": 1.6152725564947114e-05, + "loss": 0.1205, + "step": 20100 + }, + { + "epoch": 6.21, + "learning_rate": 1.6152331306826405e-05, + "loss": 0.1192, + "step": 20101 + }, + { + "epoch": 6.21, + "learning_rate": 1.6151937033317595e-05, + "loss": 0.1247, + "step": 20102 + }, + { + "epoch": 6.21, + "learning_rate": 1.615154274442167e-05, + "loss": 0.1333, + "step": 20103 + }, + { + "epoch": 6.21, + "learning_rate": 1.6151148440139614e-05, + "loss": 0.112, + "step": 20104 + }, + { + "epoch": 6.21, + "learning_rate": 1.615075412047241e-05, + "loss": 0.1271, + "step": 20105 + }, + { + "epoch": 6.21, + "learning_rate": 1.615035978542105e-05, + "loss": 0.1143, + "step": 20106 + }, + { + "epoch": 6.21, + "learning_rate": 1.614996543498652e-05, + "loss": 0.1078, + "step": 20107 + }, + { + "epoch": 6.21, + "learning_rate": 1.6149571069169804e-05, + "loss": 0.115, + "step": 20108 + }, + { + "epoch": 6.21, + "learning_rate": 1.6149176687971888e-05, + "loss": 0.1127, + "step": 20109 + }, + { + "epoch": 6.21, + "learning_rate": 1.614878229139376e-05, + "loss": 0.1188, + "step": 20110 + }, + { + "epoch": 6.21, + "learning_rate": 1.6148387879436407e-05, + "loss": 0.1226, + "step": 20111 + }, + { + "epoch": 6.21, + "learning_rate": 1.6147993452100813e-05, + "loss": 0.1116, + "step": 20112 + }, + { + "epoch": 6.21, + "learning_rate": 1.614759900938797e-05, + "loss": 0.1207, + "step": 20113 + }, + { + "epoch": 6.21, + "learning_rate": 1.6147204551298856e-05, + "loss": 0.1328, + "step": 20114 + }, + { + "epoch": 6.21, + "learning_rate": 1.6146810077834464e-05, + "loss": 0.1187, + "step": 20115 + }, + { + "epoch": 6.21, + "learning_rate": 1.6146415588995777e-05, + "loss": 0.1057, + "step": 20116 + }, + { + "epoch": 6.21, + "learning_rate": 1.6146021084783788e-05, + "loss": 0.1223, + "step": 20117 + }, + { + "epoch": 6.21, + "learning_rate": 1.6145626565199476e-05, + "loss": 0.1143, + "step": 20118 + }, + { + "epoch": 6.21, + "learning_rate": 1.614523203024383e-05, + "loss": 0.1259, + "step": 20119 + }, + { + "epoch": 6.21, + "learning_rate": 1.6144837479917842e-05, + "loss": 0.109, + "step": 20120 + }, + { + "epoch": 6.21, + "learning_rate": 1.614444291422249e-05, + "loss": 0.1107, + "step": 20121 + }, + { + "epoch": 6.21, + "learning_rate": 1.6144048333158768e-05, + "loss": 0.106, + "step": 20122 + }, + { + "epoch": 6.21, + "learning_rate": 1.6143653736727662e-05, + "loss": 0.1089, + "step": 20123 + }, + { + "epoch": 6.21, + "learning_rate": 1.6143259124930156e-05, + "loss": 0.1193, + "step": 20124 + }, + { + "epoch": 6.22, + "learning_rate": 1.614286449776724e-05, + "loss": 0.1225, + "step": 20125 + }, + { + "epoch": 6.22, + "learning_rate": 1.61424698552399e-05, + "loss": 0.1016, + "step": 20126 + }, + { + "epoch": 6.22, + "learning_rate": 1.6142075197349116e-05, + "loss": 0.1218, + "step": 20127 + }, + { + "epoch": 6.22, + "learning_rate": 1.6141680524095887e-05, + "loss": 0.1128, + "step": 20128 + }, + { + "epoch": 6.22, + "learning_rate": 1.6141285835481193e-05, + "loss": 0.1297, + "step": 20129 + }, + { + "epoch": 6.22, + "learning_rate": 1.6140891131506024e-05, + "loss": 0.111, + "step": 20130 + }, + { + "epoch": 6.22, + "learning_rate": 1.6140496412171367e-05, + "loss": 0.1129, + "step": 20131 + }, + { + "epoch": 6.22, + "learning_rate": 1.6140101677478206e-05, + "loss": 0.1066, + "step": 20132 + }, + { + "epoch": 6.22, + "learning_rate": 1.6139706927427535e-05, + "loss": 0.1039, + "step": 20133 + }, + { + "epoch": 6.22, + "learning_rate": 1.6139312162020336e-05, + "loss": 0.1101, + "step": 20134 + }, + { + "epoch": 6.22, + "learning_rate": 1.6138917381257595e-05, + "loss": 0.1082, + "step": 20135 + }, + { + "epoch": 6.22, + "learning_rate": 1.6138522585140302e-05, + "loss": 0.1226, + "step": 20136 + }, + { + "epoch": 6.22, + "learning_rate": 1.6138127773669446e-05, + "loss": 0.1131, + "step": 20137 + }, + { + "epoch": 6.22, + "learning_rate": 1.6137732946846013e-05, + "loss": 0.1178, + "step": 20138 + }, + { + "epoch": 6.22, + "learning_rate": 1.613733810467099e-05, + "loss": 0.1172, + "step": 20139 + }, + { + "epoch": 6.22, + "learning_rate": 1.6136943247145365e-05, + "loss": 0.1112, + "step": 20140 + }, + { + "epoch": 6.22, + "learning_rate": 1.6136548374270126e-05, + "loss": 0.1193, + "step": 20141 + }, + { + "epoch": 6.22, + "learning_rate": 1.613615348604626e-05, + "loss": 0.1245, + "step": 20142 + }, + { + "epoch": 6.22, + "learning_rate": 1.6135758582474753e-05, + "loss": 0.1187, + "step": 20143 + }, + { + "epoch": 6.22, + "learning_rate": 1.61353636635566e-05, + "loss": 0.1074, + "step": 20144 + }, + { + "epoch": 6.22, + "learning_rate": 1.613496872929278e-05, + "loss": 0.1121, + "step": 20145 + }, + { + "epoch": 6.22, + "learning_rate": 1.6134573779684283e-05, + "loss": 0.1289, + "step": 20146 + }, + { + "epoch": 6.22, + "learning_rate": 1.61341788147321e-05, + "loss": 0.1148, + "step": 20147 + }, + { + "epoch": 6.22, + "learning_rate": 1.6133783834437216e-05, + "loss": 0.1203, + "step": 20148 + }, + { + "epoch": 6.22, + "learning_rate": 1.613338883880062e-05, + "loss": 0.1101, + "step": 20149 + }, + { + "epoch": 6.22, + "learning_rate": 1.61329938278233e-05, + "loss": 0.1147, + "step": 20150 + }, + { + "epoch": 6.22, + "learning_rate": 1.6132598801506248e-05, + "loss": 0.1076, + "step": 20151 + }, + { + "epoch": 6.22, + "learning_rate": 1.613220375985044e-05, + "loss": 0.1109, + "step": 20152 + }, + { + "epoch": 6.22, + "learning_rate": 1.613180870285688e-05, + "loss": 0.1056, + "step": 20153 + }, + { + "epoch": 6.22, + "learning_rate": 1.613141363052654e-05, + "loss": 0.1191, + "step": 20154 + }, + { + "epoch": 6.22, + "learning_rate": 1.613101854286042e-05, + "loss": 0.1152, + "step": 20155 + }, + { + "epoch": 6.22, + "learning_rate": 1.6130623439859507e-05, + "loss": 0.1203, + "step": 20156 + }, + { + "epoch": 6.22, + "learning_rate": 1.6130228321524786e-05, + "loss": 0.1175, + "step": 20157 + }, + { + "epoch": 6.23, + "learning_rate": 1.612983318785724e-05, + "loss": 0.1123, + "step": 20158 + }, + { + "epoch": 6.23, + "learning_rate": 1.612943803885787e-05, + "loss": 0.1166, + "step": 20159 + }, + { + "epoch": 6.23, + "learning_rate": 1.6129042874527653e-05, + "loss": 0.1073, + "step": 20160 + }, + { + "epoch": 6.23, + "learning_rate": 1.6128647694867587e-05, + "loss": 0.1179, + "step": 20161 + }, + { + "epoch": 6.23, + "learning_rate": 1.612825249987865e-05, + "loss": 0.1109, + "step": 20162 + }, + { + "epoch": 6.23, + "learning_rate": 1.6127857289561836e-05, + "loss": 0.1091, + "step": 20163 + }, + { + "epoch": 6.23, + "learning_rate": 1.6127462063918137e-05, + "loss": 0.1148, + "step": 20164 + }, + { + "epoch": 6.23, + "learning_rate": 1.6127066822948535e-05, + "loss": 0.1227, + "step": 20165 + }, + { + "epoch": 6.23, + "learning_rate": 1.6126671566654023e-05, + "loss": 0.1225, + "step": 20166 + }, + { + "epoch": 6.23, + "learning_rate": 1.6126276295035585e-05, + "loss": 0.1162, + "step": 20167 + }, + { + "epoch": 6.23, + "learning_rate": 1.6125881008094215e-05, + "loss": 0.1013, + "step": 20168 + }, + { + "epoch": 6.23, + "learning_rate": 1.61254857058309e-05, + "loss": 0.1049, + "step": 20169 + }, + { + "epoch": 6.23, + "learning_rate": 1.6125090388246627e-05, + "loss": 0.1249, + "step": 20170 + }, + { + "epoch": 6.23, + "learning_rate": 1.6124695055342386e-05, + "loss": 0.12, + "step": 20171 + }, + { + "epoch": 6.23, + "learning_rate": 1.6124299707119165e-05, + "loss": 0.1093, + "step": 20172 + }, + { + "epoch": 6.23, + "learning_rate": 1.6123904343577957e-05, + "loss": 0.1097, + "step": 20173 + }, + { + "epoch": 6.23, + "learning_rate": 1.6123508964719743e-05, + "loss": 0.1126, + "step": 20174 + }, + { + "epoch": 6.23, + "learning_rate": 1.6123113570545517e-05, + "loss": 0.1117, + "step": 20175 + }, + { + "epoch": 6.23, + "learning_rate": 1.6122718161056264e-05, + "loss": 0.1109, + "step": 20176 + }, + { + "epoch": 6.23, + "learning_rate": 1.612232273625298e-05, + "loss": 0.1108, + "step": 20177 + }, + { + "epoch": 6.23, + "learning_rate": 1.6121927296136653e-05, + "loss": 0.1215, + "step": 20178 + }, + { + "epoch": 6.23, + "learning_rate": 1.6121531840708267e-05, + "loss": 0.1176, + "step": 20179 + }, + { + "epoch": 6.23, + "learning_rate": 1.612113636996881e-05, + "loss": 0.1197, + "step": 20180 + }, + { + "epoch": 6.23, + "learning_rate": 1.612074088391928e-05, + "loss": 0.1093, + "step": 20181 + }, + { + "epoch": 6.23, + "learning_rate": 1.6120345382560657e-05, + "loss": 0.1234, + "step": 20182 + }, + { + "epoch": 6.23, + "learning_rate": 1.6119949865893937e-05, + "loss": 0.1241, + "step": 20183 + }, + { + "epoch": 6.23, + "learning_rate": 1.61195543339201e-05, + "loss": 0.1156, + "step": 20184 + }, + { + "epoch": 6.23, + "learning_rate": 1.6119158786640147e-05, + "loss": 0.1306, + "step": 20185 + }, + { + "epoch": 6.23, + "learning_rate": 1.611876322405506e-05, + "loss": 0.1028, + "step": 20186 + }, + { + "epoch": 6.23, + "learning_rate": 1.611836764616583e-05, + "loss": 0.119, + "step": 20187 + }, + { + "epoch": 6.23, + "learning_rate": 1.6117972052973448e-05, + "loss": 0.1042, + "step": 20188 + }, + { + "epoch": 6.23, + "learning_rate": 1.6117576444478903e-05, + "loss": 0.1108, + "step": 20189 + }, + { + "epoch": 6.24, + "learning_rate": 1.611718082068318e-05, + "loss": 0.1237, + "step": 20190 + }, + { + "epoch": 6.24, + "learning_rate": 1.6116785181587272e-05, + "loss": 0.1217, + "step": 20191 + }, + { + "epoch": 6.24, + "learning_rate": 1.611638952719217e-05, + "loss": 0.1114, + "step": 20192 + }, + { + "epoch": 6.24, + "learning_rate": 1.6115993857498863e-05, + "loss": 0.1132, + "step": 20193 + }, + { + "epoch": 6.24, + "learning_rate": 1.611559817250834e-05, + "loss": 0.1269, + "step": 20194 + }, + { + "epoch": 6.24, + "learning_rate": 1.611520247222159e-05, + "loss": 0.1175, + "step": 20195 + }, + { + "epoch": 6.24, + "learning_rate": 1.6114806756639604e-05, + "loss": 0.1079, + "step": 20196 + }, + { + "epoch": 6.24, + "learning_rate": 1.611441102576337e-05, + "loss": 0.1202, + "step": 20197 + }, + { + "epoch": 6.24, + "learning_rate": 1.611401527959388e-05, + "loss": 0.1023, + "step": 20198 + }, + { + "epoch": 6.24, + "learning_rate": 1.611361951813212e-05, + "loss": 0.1176, + "step": 20199 + }, + { + "epoch": 6.24, + "learning_rate": 1.6113223741379082e-05, + "loss": 0.1067, + "step": 20200 + }, + { + "epoch": 6.24, + "learning_rate": 1.611282794933576e-05, + "loss": 0.1206, + "step": 20201 + }, + { + "epoch": 6.24, + "learning_rate": 1.611243214200314e-05, + "loss": 0.1115, + "step": 20202 + }, + { + "epoch": 6.24, + "learning_rate": 1.6112036319382212e-05, + "loss": 0.1108, + "step": 20203 + }, + { + "epoch": 6.24, + "learning_rate": 1.6111640481473964e-05, + "loss": 0.1105, + "step": 20204 + }, + { + "epoch": 6.24, + "learning_rate": 1.6111244628279394e-05, + "loss": 0.1227, + "step": 20205 + }, + { + "epoch": 6.24, + "learning_rate": 1.6110848759799483e-05, + "loss": 0.1152, + "step": 20206 + }, + { + "epoch": 6.24, + "learning_rate": 1.6110452876035223e-05, + "loss": 0.1177, + "step": 20207 + }, + { + "epoch": 6.24, + "learning_rate": 1.6110056976987608e-05, + "loss": 0.1163, + "step": 20208 + }, + { + "epoch": 6.24, + "learning_rate": 1.6109661062657625e-05, + "loss": 0.1177, + "step": 20209 + }, + { + "epoch": 6.24, + "learning_rate": 1.6109265133046266e-05, + "loss": 0.1142, + "step": 20210 + }, + { + "epoch": 6.24, + "learning_rate": 1.610886918815452e-05, + "loss": 0.1276, + "step": 20211 + }, + { + "epoch": 6.24, + "learning_rate": 1.610847322798338e-05, + "loss": 0.1318, + "step": 20212 + }, + { + "epoch": 6.24, + "learning_rate": 1.610807725253383e-05, + "loss": 0.1197, + "step": 20213 + }, + { + "epoch": 6.24, + "learning_rate": 1.610768126180687e-05, + "loss": 0.113, + "step": 20214 + }, + { + "epoch": 6.24, + "learning_rate": 1.6107285255803482e-05, + "loss": 0.1139, + "step": 20215 + }, + { + "epoch": 6.24, + "learning_rate": 1.6106889234524663e-05, + "loss": 0.1197, + "step": 20216 + }, + { + "epoch": 6.24, + "learning_rate": 1.6106493197971397e-05, + "loss": 0.1259, + "step": 20217 + }, + { + "epoch": 6.24, + "learning_rate": 1.6106097146144676e-05, + "loss": 0.1099, + "step": 20218 + }, + { + "epoch": 6.24, + "learning_rate": 1.6105701079045498e-05, + "loss": 0.107, + "step": 20219 + }, + { + "epoch": 6.24, + "learning_rate": 1.6105304996674844e-05, + "loss": 0.1263, + "step": 20220 + }, + { + "epoch": 6.24, + "learning_rate": 1.610490889903371e-05, + "loss": 0.1133, + "step": 20221 + }, + { + "epoch": 6.25, + "learning_rate": 1.6104512786123083e-05, + "loss": 0.1231, + "step": 20222 + }, + { + "epoch": 6.25, + "learning_rate": 1.610411665794396e-05, + "loss": 0.1301, + "step": 20223 + }, + { + "epoch": 6.25, + "learning_rate": 1.6103720514497324e-05, + "loss": 0.1228, + "step": 20224 + }, + { + "epoch": 6.25, + "learning_rate": 1.610332435578417e-05, + "loss": 0.1167, + "step": 20225 + }, + { + "epoch": 6.25, + "learning_rate": 1.610292818180549e-05, + "loss": 0.1123, + "step": 20226 + }, + { + "epoch": 6.25, + "learning_rate": 1.6102531992562276e-05, + "loss": 0.1214, + "step": 20227 + }, + { + "epoch": 6.25, + "learning_rate": 1.6102135788055512e-05, + "loss": 0.1059, + "step": 20228 + }, + { + "epoch": 6.25, + "learning_rate": 1.6101739568286197e-05, + "loss": 0.1227, + "step": 20229 + }, + { + "epoch": 6.25, + "learning_rate": 1.6101343333255317e-05, + "loss": 0.1114, + "step": 20230 + }, + { + "epoch": 6.25, + "learning_rate": 1.6100947082963864e-05, + "loss": 0.1149, + "step": 20231 + }, + { + "epoch": 6.25, + "learning_rate": 1.610055081741283e-05, + "loss": 0.1177, + "step": 20232 + }, + { + "epoch": 6.25, + "learning_rate": 1.610015453660321e-05, + "loss": 0.1082, + "step": 20233 + }, + { + "epoch": 6.25, + "learning_rate": 1.6099758240535984e-05, + "loss": 0.1167, + "step": 20234 + }, + { + "epoch": 6.25, + "learning_rate": 1.6099361929212155e-05, + "loss": 0.1083, + "step": 20235 + }, + { + "epoch": 6.25, + "learning_rate": 1.6098965602632707e-05, + "loss": 0.1174, + "step": 20236 + }, + { + "epoch": 6.25, + "learning_rate": 1.6098569260798633e-05, + "loss": 0.1149, + "step": 20237 + }, + { + "epoch": 6.25, + "learning_rate": 1.6098172903710928e-05, + "loss": 0.1298, + "step": 20238 + }, + { + "epoch": 6.25, + "learning_rate": 1.6097776531370576e-05, + "loss": 0.1181, + "step": 20239 + }, + { + "epoch": 6.25, + "learning_rate": 1.6097380143778572e-05, + "loss": 0.1183, + "step": 20240 + }, + { + "epoch": 6.25, + "learning_rate": 1.6096983740935913e-05, + "loss": 0.1389, + "step": 20241 + }, + { + "epoch": 6.25, + "learning_rate": 1.6096587322843584e-05, + "loss": 0.1057, + "step": 20242 + }, + { + "epoch": 6.25, + "learning_rate": 1.609619088950258e-05, + "loss": 0.1166, + "step": 20243 + }, + { + "epoch": 6.25, + "learning_rate": 1.6095794440913886e-05, + "loss": 0.126, + "step": 20244 + }, + { + "epoch": 6.25, + "learning_rate": 1.6095397977078502e-05, + "loss": 0.1191, + "step": 20245 + }, + { + "epoch": 6.25, + "learning_rate": 1.6095001497997416e-05, + "loss": 0.1229, + "step": 20246 + }, + { + "epoch": 6.25, + "learning_rate": 1.609460500367162e-05, + "loss": 0.1279, + "step": 20247 + }, + { + "epoch": 6.25, + "learning_rate": 1.6094208494102102e-05, + "loss": 0.1214, + "step": 20248 + }, + { + "epoch": 6.25, + "learning_rate": 1.609381196928986e-05, + "loss": 0.1093, + "step": 20249 + }, + { + "epoch": 6.25, + "learning_rate": 1.6093415429235882e-05, + "loss": 0.1208, + "step": 20250 + }, + { + "epoch": 6.25, + "learning_rate": 1.609301887394116e-05, + "loss": 0.1257, + "step": 20251 + }, + { + "epoch": 6.25, + "learning_rate": 1.6092622303406686e-05, + "loss": 0.117, + "step": 20252 + }, + { + "epoch": 6.25, + "learning_rate": 1.6092225717633452e-05, + "loss": 0.1115, + "step": 20253 + }, + { + "epoch": 6.25, + "learning_rate": 1.609182911662245e-05, + "loss": 0.1273, + "step": 20254 + }, + { + "epoch": 6.26, + "learning_rate": 1.609143250037468e-05, + "loss": 0.1145, + "step": 20255 + }, + { + "epoch": 6.26, + "learning_rate": 1.609103586889112e-05, + "loss": 0.1128, + "step": 20256 + }, + { + "epoch": 6.26, + "learning_rate": 1.6090639222172762e-05, + "loss": 0.1245, + "step": 20257 + }, + { + "epoch": 6.26, + "learning_rate": 1.6090242560220614e-05, + "loss": 0.1141, + "step": 20258 + }, + { + "epoch": 6.26, + "learning_rate": 1.6089845883035655e-05, + "loss": 0.1227, + "step": 20259 + }, + { + "epoch": 6.26, + "learning_rate": 1.6089449190618882e-05, + "loss": 0.114, + "step": 20260 + }, + { + "epoch": 6.26, + "learning_rate": 1.6089052482971285e-05, + "loss": 0.1307, + "step": 20261 + }, + { + "epoch": 6.26, + "learning_rate": 1.6088655760093856e-05, + "loss": 0.128, + "step": 20262 + }, + { + "epoch": 6.26, + "learning_rate": 1.608825902198759e-05, + "loss": 0.1118, + "step": 20263 + }, + { + "epoch": 6.26, + "learning_rate": 1.608786226865348e-05, + "loss": 0.1028, + "step": 20264 + }, + { + "epoch": 6.26, + "learning_rate": 1.6087465500092513e-05, + "loss": 0.1109, + "step": 20265 + }, + { + "epoch": 6.26, + "learning_rate": 1.6087068716305683e-05, + "loss": 0.1069, + "step": 20266 + }, + { + "epoch": 6.26, + "learning_rate": 1.608667191729399e-05, + "loss": 0.1225, + "step": 20267 + }, + { + "epoch": 6.26, + "learning_rate": 1.6086275103058414e-05, + "loss": 0.1199, + "step": 20268 + }, + { + "epoch": 6.26, + "learning_rate": 1.6085878273599958e-05, + "loss": 0.1095, + "step": 20269 + }, + { + "epoch": 6.26, + "learning_rate": 1.6085481428919607e-05, + "loss": 0.1174, + "step": 20270 + }, + { + "epoch": 6.26, + "learning_rate": 1.608508456901836e-05, + "loss": 0.1159, + "step": 20271 + }, + { + "epoch": 6.26, + "learning_rate": 1.6084687693897203e-05, + "loss": 0.117, + "step": 20272 + }, + { + "epoch": 6.26, + "learning_rate": 1.6084290803557135e-05, + "loss": 0.1064, + "step": 20273 + }, + { + "epoch": 6.26, + "learning_rate": 1.6083893897999144e-05, + "loss": 0.1095, + "step": 20274 + }, + { + "epoch": 6.26, + "learning_rate": 1.6083496977224227e-05, + "loss": 0.1256, + "step": 20275 + }, + { + "epoch": 6.26, + "learning_rate": 1.6083100041233376e-05, + "loss": 0.1125, + "step": 20276 + }, + { + "epoch": 6.26, + "learning_rate": 1.6082703090027577e-05, + "loss": 0.1227, + "step": 20277 + }, + { + "epoch": 6.26, + "learning_rate": 1.6082306123607833e-05, + "loss": 0.1242, + "step": 20278 + }, + { + "epoch": 6.26, + "learning_rate": 1.6081909141975133e-05, + "loss": 0.1238, + "step": 20279 + }, + { + "epoch": 6.26, + "learning_rate": 1.6081512145130464e-05, + "loss": 0.1159, + "step": 20280 + }, + { + "epoch": 6.26, + "learning_rate": 1.608111513307483e-05, + "loss": 0.1193, + "step": 20281 + }, + { + "epoch": 6.26, + "learning_rate": 1.6080718105809214e-05, + "loss": 0.1157, + "step": 20282 + }, + { + "epoch": 6.26, + "learning_rate": 1.6080321063334612e-05, + "loss": 0.119, + "step": 20283 + }, + { + "epoch": 6.26, + "learning_rate": 1.6079924005652018e-05, + "loss": 0.1156, + "step": 20284 + }, + { + "epoch": 6.26, + "learning_rate": 1.6079526932762424e-05, + "loss": 0.1306, + "step": 20285 + }, + { + "epoch": 6.26, + "learning_rate": 1.607912984466683e-05, + "loss": 0.1159, + "step": 20286 + }, + { + "epoch": 6.27, + "learning_rate": 1.607873274136622e-05, + "loss": 0.1222, + "step": 20287 + }, + { + "epoch": 6.27, + "learning_rate": 1.6078335622861592e-05, + "loss": 0.1023, + "step": 20288 + }, + { + "epoch": 6.27, + "learning_rate": 1.6077938489153936e-05, + "loss": 0.1162, + "step": 20289 + }, + { + "epoch": 6.27, + "learning_rate": 1.6077541340244246e-05, + "loss": 0.1205, + "step": 20290 + }, + { + "epoch": 6.27, + "learning_rate": 1.607714417613352e-05, + "loss": 0.1149, + "step": 20291 + }, + { + "epoch": 6.27, + "learning_rate": 1.607674699682275e-05, + "loss": 0.124, + "step": 20292 + }, + { + "epoch": 6.27, + "learning_rate": 1.6076349802312923e-05, + "loss": 0.1203, + "step": 20293 + }, + { + "epoch": 6.27, + "learning_rate": 1.6075952592605038e-05, + "loss": 0.1178, + "step": 20294 + }, + { + "epoch": 6.27, + "learning_rate": 1.6075555367700085e-05, + "loss": 0.1102, + "step": 20295 + }, + { + "epoch": 6.27, + "learning_rate": 1.6075158127599066e-05, + "loss": 0.1277, + "step": 20296 + }, + { + "epoch": 6.27, + "learning_rate": 1.6074760872302967e-05, + "loss": 0.1108, + "step": 20297 + }, + { + "epoch": 6.27, + "learning_rate": 1.6074363601812777e-05, + "loss": 0.1275, + "step": 20298 + }, + { + "epoch": 6.27, + "learning_rate": 1.60739663161295e-05, + "loss": 0.1128, + "step": 20299 + }, + { + "epoch": 6.27, + "learning_rate": 1.6073569015254128e-05, + "loss": 0.1217, + "step": 20300 + }, + { + "epoch": 6.27, + "learning_rate": 1.6073171699187647e-05, + "loss": 0.1198, + "step": 20301 + }, + { + "epoch": 6.27, + "learning_rate": 1.607277436793106e-05, + "loss": 0.1165, + "step": 20302 + }, + { + "epoch": 6.27, + "learning_rate": 1.6072377021485356e-05, + "loss": 0.1205, + "step": 20303 + }, + { + "epoch": 6.27, + "learning_rate": 1.6071979659851528e-05, + "loss": 0.1162, + "step": 20304 + }, + { + "epoch": 6.27, + "learning_rate": 1.6071582283030572e-05, + "loss": 0.1163, + "step": 20305 + }, + { + "epoch": 6.27, + "learning_rate": 1.607118489102348e-05, + "loss": 0.1122, + "step": 20306 + }, + { + "epoch": 6.27, + "learning_rate": 1.607078748383125e-05, + "loss": 0.1123, + "step": 20307 + }, + { + "epoch": 6.27, + "learning_rate": 1.6070390061454867e-05, + "loss": 0.1255, + "step": 20308 + }, + { + "epoch": 6.27, + "learning_rate": 1.606999262389534e-05, + "loss": 0.1152, + "step": 20309 + }, + { + "epoch": 6.27, + "learning_rate": 1.6069595171153648e-05, + "loss": 0.113, + "step": 20310 + }, + { + "epoch": 6.27, + "learning_rate": 1.6069197703230795e-05, + "loss": 0.1071, + "step": 20311 + }, + { + "epoch": 6.27, + "learning_rate": 1.606880022012777e-05, + "loss": 0.121, + "step": 20312 + }, + { + "epoch": 6.27, + "learning_rate": 1.606840272184557e-05, + "loss": 0.11, + "step": 20313 + }, + { + "epoch": 6.27, + "learning_rate": 1.606800520838519e-05, + "loss": 0.123, + "step": 20314 + }, + { + "epoch": 6.27, + "learning_rate": 1.6067607679747617e-05, + "loss": 0.1189, + "step": 20315 + }, + { + "epoch": 6.27, + "learning_rate": 1.606721013593385e-05, + "loss": 0.1276, + "step": 20316 + }, + { + "epoch": 6.27, + "learning_rate": 1.606681257694489e-05, + "loss": 0.118, + "step": 20317 + }, + { + "epoch": 6.27, + "learning_rate": 1.606641500278172e-05, + "loss": 0.1227, + "step": 20318 + }, + { + "epoch": 6.27, + "learning_rate": 1.606601741344534e-05, + "loss": 0.1163, + "step": 20319 + }, + { + "epoch": 6.28, + "learning_rate": 1.606561980893675e-05, + "loss": 0.1214, + "step": 20320 + }, + { + "epoch": 6.28, + "learning_rate": 1.6065222189256935e-05, + "loss": 0.1099, + "step": 20321 + }, + { + "epoch": 6.28, + "learning_rate": 1.606482455440689e-05, + "loss": 0.1289, + "step": 20322 + }, + { + "epoch": 6.28, + "learning_rate": 1.6064426904387618e-05, + "loss": 0.1115, + "step": 20323 + }, + { + "epoch": 6.28, + "learning_rate": 1.6064029239200102e-05, + "loss": 0.1198, + "step": 20324 + }, + { + "epoch": 6.28, + "learning_rate": 1.6063631558845347e-05, + "loss": 0.1121, + "step": 20325 + }, + { + "epoch": 6.28, + "learning_rate": 1.6063233863324344e-05, + "loss": 0.1209, + "step": 20326 + }, + { + "epoch": 6.28, + "learning_rate": 1.6062836152638085e-05, + "loss": 0.1141, + "step": 20327 + }, + { + "epoch": 6.28, + "learning_rate": 1.6062438426787567e-05, + "loss": 0.1175, + "step": 20328 + }, + { + "epoch": 6.28, + "learning_rate": 1.6062040685773787e-05, + "loss": 0.1068, + "step": 20329 + }, + { + "epoch": 6.28, + "learning_rate": 1.6061642929597735e-05, + "loss": 0.104, + "step": 20330 + }, + { + "epoch": 6.28, + "learning_rate": 1.606124515826041e-05, + "loss": 0.1158, + "step": 20331 + }, + { + "epoch": 6.28, + "learning_rate": 1.6060847371762807e-05, + "loss": 0.1195, + "step": 20332 + }, + { + "epoch": 6.28, + "learning_rate": 1.6060449570105917e-05, + "loss": 0.1142, + "step": 20333 + }, + { + "epoch": 6.28, + "learning_rate": 1.606005175329074e-05, + "loss": 0.1261, + "step": 20334 + }, + { + "epoch": 6.28, + "learning_rate": 1.6059653921318265e-05, + "loss": 0.1125, + "step": 20335 + }, + { + "epoch": 6.28, + "learning_rate": 1.605925607418949e-05, + "loss": 0.1082, + "step": 20336 + }, + { + "epoch": 6.28, + "learning_rate": 1.6058858211905412e-05, + "loss": 0.1083, + "step": 20337 + }, + { + "epoch": 6.28, + "learning_rate": 1.6058460334467025e-05, + "loss": 0.1153, + "step": 20338 + }, + { + "epoch": 6.28, + "learning_rate": 1.605806244187532e-05, + "loss": 0.1134, + "step": 20339 + }, + { + "epoch": 6.28, + "learning_rate": 1.60576645341313e-05, + "loss": 0.1143, + "step": 20340 + }, + { + "epoch": 6.28, + "learning_rate": 1.6057266611235956e-05, + "loss": 0.1199, + "step": 20341 + }, + { + "epoch": 6.28, + "learning_rate": 1.605686867319028e-05, + "loss": 0.1096, + "step": 20342 + }, + { + "epoch": 6.28, + "learning_rate": 1.6056470719995277e-05, + "loss": 0.1147, + "step": 20343 + }, + { + "epoch": 6.28, + "learning_rate": 1.605607275165193e-05, + "loss": 0.1277, + "step": 20344 + }, + { + "epoch": 6.28, + "learning_rate": 1.6055674768161242e-05, + "loss": 0.1194, + "step": 20345 + }, + { + "epoch": 6.28, + "learning_rate": 1.6055276769524208e-05, + "loss": 0.1115, + "step": 20346 + }, + { + "epoch": 6.28, + "learning_rate": 1.6054878755741824e-05, + "loss": 0.122, + "step": 20347 + }, + { + "epoch": 6.28, + "learning_rate": 1.605448072681508e-05, + "loss": 0.1196, + "step": 20348 + }, + { + "epoch": 6.28, + "learning_rate": 1.605408268274498e-05, + "loss": 0.1153, + "step": 20349 + }, + { + "epoch": 6.28, + "learning_rate": 1.605368462353251e-05, + "loss": 0.1226, + "step": 20350 + }, + { + "epoch": 6.28, + "learning_rate": 1.6053286549178676e-05, + "loss": 0.1158, + "step": 20351 + }, + { + "epoch": 6.29, + "learning_rate": 1.6052888459684463e-05, + "loss": 0.118, + "step": 20352 + }, + { + "epoch": 6.29, + "learning_rate": 1.6052490355050874e-05, + "loss": 0.1216, + "step": 20353 + }, + { + "epoch": 6.29, + "learning_rate": 1.6052092235278905e-05, + "loss": 0.1168, + "step": 20354 + }, + { + "epoch": 6.29, + "learning_rate": 1.6051694100369546e-05, + "loss": 0.1233, + "step": 20355 + }, + { + "epoch": 6.29, + "learning_rate": 1.6051295950323797e-05, + "loss": 0.127, + "step": 20356 + }, + { + "epoch": 6.29, + "learning_rate": 1.6050897785142656e-05, + "loss": 0.1265, + "step": 20357 + }, + { + "epoch": 6.29, + "learning_rate": 1.6050499604827114e-05, + "loss": 0.1157, + "step": 20358 + }, + { + "epoch": 6.29, + "learning_rate": 1.6050101409378166e-05, + "loss": 0.1076, + "step": 20359 + }, + { + "epoch": 6.29, + "learning_rate": 1.6049703198796818e-05, + "loss": 0.1225, + "step": 20360 + }, + { + "epoch": 6.29, + "learning_rate": 1.6049304973084054e-05, + "loss": 0.1278, + "step": 20361 + }, + { + "epoch": 6.29, + "learning_rate": 1.6048906732240875e-05, + "loss": 0.117, + "step": 20362 + }, + { + "epoch": 6.29, + "learning_rate": 1.604850847626828e-05, + "loss": 0.1118, + "step": 20363 + }, + { + "epoch": 6.29, + "learning_rate": 1.6048110205167257e-05, + "loss": 0.1342, + "step": 20364 + }, + { + "epoch": 6.29, + "learning_rate": 1.604771191893881e-05, + "loss": 0.1147, + "step": 20365 + }, + { + "epoch": 6.29, + "learning_rate": 1.6047313617583933e-05, + "loss": 0.1104, + "step": 20366 + }, + { + "epoch": 6.29, + "learning_rate": 1.604691530110362e-05, + "loss": 0.1246, + "step": 20367 + }, + { + "epoch": 6.29, + "learning_rate": 1.604651696949887e-05, + "loss": 0.1187, + "step": 20368 + }, + { + "epoch": 6.29, + "learning_rate": 1.6046118622770683e-05, + "loss": 0.121, + "step": 20369 + }, + { + "epoch": 6.29, + "learning_rate": 1.6045720260920042e-05, + "loss": 0.1152, + "step": 20370 + }, + { + "epoch": 6.29, + "learning_rate": 1.604532188394796e-05, + "loss": 0.128, + "step": 20371 + }, + { + "epoch": 6.29, + "learning_rate": 1.6044923491855416e-05, + "loss": 0.1061, + "step": 20372 + }, + { + "epoch": 6.29, + "learning_rate": 1.6044525084643423e-05, + "loss": 0.126, + "step": 20373 + }, + { + "epoch": 6.29, + "learning_rate": 1.604412666231297e-05, + "loss": 0.112, + "step": 20374 + }, + { + "epoch": 6.29, + "learning_rate": 1.604372822486505e-05, + "loss": 0.1158, + "step": 20375 + }, + { + "epoch": 6.29, + "learning_rate": 1.6043329772300666e-05, + "loss": 0.1324, + "step": 20376 + }, + { + "epoch": 6.29, + "learning_rate": 1.6042931304620814e-05, + "loss": 0.1184, + "step": 20377 + }, + { + "epoch": 6.29, + "learning_rate": 1.6042532821826485e-05, + "loss": 0.1104, + "step": 20378 + }, + { + "epoch": 6.29, + "learning_rate": 1.604213432391868e-05, + "loss": 0.1209, + "step": 20379 + }, + { + "epoch": 6.29, + "learning_rate": 1.6041735810898398e-05, + "loss": 0.1305, + "step": 20380 + }, + { + "epoch": 6.29, + "learning_rate": 1.6041337282766628e-05, + "loss": 0.1191, + "step": 20381 + }, + { + "epoch": 6.29, + "learning_rate": 1.6040938739524373e-05, + "loss": 0.1177, + "step": 20382 + }, + { + "epoch": 6.29, + "learning_rate": 1.604054018117263e-05, + "loss": 0.1221, + "step": 20383 + }, + { + "epoch": 6.3, + "learning_rate": 1.6040141607712395e-05, + "loss": 0.1221, + "step": 20384 + }, + { + "epoch": 6.3, + "learning_rate": 1.6039743019144665e-05, + "loss": 0.1198, + "step": 20385 + }, + { + "epoch": 6.3, + "learning_rate": 1.603934441547043e-05, + "loss": 0.1152, + "step": 20386 + }, + { + "epoch": 6.3, + "learning_rate": 1.60389457966907e-05, + "loss": 0.1205, + "step": 20387 + }, + { + "epoch": 6.3, + "learning_rate": 1.6038547162806462e-05, + "loss": 0.1186, + "step": 20388 + }, + { + "epoch": 6.3, + "learning_rate": 1.6038148513818717e-05, + "loss": 0.1161, + "step": 20389 + }, + { + "epoch": 6.3, + "learning_rate": 1.603774984972846e-05, + "loss": 0.1261, + "step": 20390 + }, + { + "epoch": 6.3, + "learning_rate": 1.603735117053669e-05, + "loss": 0.1135, + "step": 20391 + }, + { + "epoch": 6.3, + "learning_rate": 1.6036952476244404e-05, + "loss": 0.1099, + "step": 20392 + }, + { + "epoch": 6.3, + "learning_rate": 1.6036553766852598e-05, + "loss": 0.1304, + "step": 20393 + }, + { + "epoch": 6.3, + "learning_rate": 1.603615504236227e-05, + "loss": 0.11, + "step": 20394 + }, + { + "epoch": 6.3, + "learning_rate": 1.603575630277442e-05, + "loss": 0.108, + "step": 20395 + }, + { + "epoch": 6.3, + "learning_rate": 1.603535754809004e-05, + "loss": 0.1081, + "step": 20396 + }, + { + "epoch": 6.3, + "learning_rate": 1.6034958778310132e-05, + "loss": 0.1367, + "step": 20397 + }, + { + "epoch": 6.3, + "learning_rate": 1.603455999343569e-05, + "loss": 0.1172, + "step": 20398 + }, + { + "epoch": 6.3, + "learning_rate": 1.603416119346771e-05, + "loss": 0.1126, + "step": 20399 + }, + { + "epoch": 6.3, + "learning_rate": 1.6033762378407197e-05, + "loss": 0.1069, + "step": 20400 + }, + { + "epoch": 6.3, + "learning_rate": 1.603336354825514e-05, + "loss": 0.1252, + "step": 20401 + }, + { + "epoch": 6.3, + "learning_rate": 1.6032964703012544e-05, + "loss": 0.1236, + "step": 20402 + }, + { + "epoch": 6.3, + "learning_rate": 1.60325658426804e-05, + "loss": 0.1095, + "step": 20403 + }, + { + "epoch": 6.3, + "learning_rate": 1.6032166967259712e-05, + "loss": 0.1236, + "step": 20404 + }, + { + "epoch": 6.3, + "learning_rate": 1.6031768076751472e-05, + "loss": 0.1206, + "step": 20405 + }, + { + "epoch": 6.3, + "learning_rate": 1.6031369171156677e-05, + "loss": 0.1256, + "step": 20406 + }, + { + "epoch": 6.3, + "learning_rate": 1.603097025047633e-05, + "loss": 0.134, + "step": 20407 + }, + { + "epoch": 6.3, + "learning_rate": 1.6030571314711428e-05, + "loss": 0.1222, + "step": 20408 + }, + { + "epoch": 6.3, + "learning_rate": 1.6030172363862967e-05, + "loss": 0.1337, + "step": 20409 + }, + { + "epoch": 6.3, + "learning_rate": 1.602977339793194e-05, + "loss": 0.1163, + "step": 20410 + }, + { + "epoch": 6.3, + "learning_rate": 1.602937441691936e-05, + "loss": 0.1164, + "step": 20411 + }, + { + "epoch": 6.3, + "learning_rate": 1.6028975420826206e-05, + "loss": 0.1142, + "step": 20412 + }, + { + "epoch": 6.3, + "learning_rate": 1.602857640965349e-05, + "loss": 0.1154, + "step": 20413 + }, + { + "epoch": 6.3, + "learning_rate": 1.60281773834022e-05, + "loss": 0.1151, + "step": 20414 + }, + { + "epoch": 6.3, + "learning_rate": 1.6027778342073343e-05, + "loss": 0.1219, + "step": 20415 + }, + { + "epoch": 6.3, + "learning_rate": 1.602737928566791e-05, + "loss": 0.1179, + "step": 20416 + }, + { + "epoch": 6.31, + "learning_rate": 1.6026980214186907e-05, + "loss": 0.111, + "step": 20417 + }, + { + "epoch": 6.31, + "learning_rate": 1.6026581127631322e-05, + "loss": 0.1036, + "step": 20418 + }, + { + "epoch": 6.31, + "learning_rate": 1.6026182026002163e-05, + "loss": 0.1048, + "step": 20419 + }, + { + "epoch": 6.31, + "learning_rate": 1.602578290930042e-05, + "loss": 0.1171, + "step": 20420 + }, + { + "epoch": 6.31, + "learning_rate": 1.602538377752709e-05, + "loss": 0.1229, + "step": 20421 + }, + { + "epoch": 6.31, + "learning_rate": 1.6024984630683188e-05, + "loss": 0.101, + "step": 20422 + }, + { + "epoch": 6.31, + "learning_rate": 1.6024585468769695e-05, + "loss": 0.1183, + "step": 20423 + }, + { + "epoch": 6.31, + "learning_rate": 1.6024186291787614e-05, + "loss": 0.1137, + "step": 20424 + }, + { + "epoch": 6.31, + "learning_rate": 1.6023787099737945e-05, + "loss": 0.1081, + "step": 20425 + }, + { + "epoch": 6.31, + "learning_rate": 1.6023387892621684e-05, + "loss": 0.113, + "step": 20426 + }, + { + "epoch": 6.31, + "learning_rate": 1.6022988670439835e-05, + "loss": 0.1175, + "step": 20427 + }, + { + "epoch": 6.31, + "learning_rate": 1.602258943319339e-05, + "loss": 0.1211, + "step": 20428 + }, + { + "epoch": 6.31, + "learning_rate": 1.6022190180883354e-05, + "loss": 0.1055, + "step": 20429 + }, + { + "epoch": 6.31, + "learning_rate": 1.6021790913510718e-05, + "loss": 0.1176, + "step": 20430 + }, + { + "epoch": 6.31, + "learning_rate": 1.6021391631076487e-05, + "loss": 0.1291, + "step": 20431 + }, + { + "epoch": 6.31, + "learning_rate": 1.6020992333581652e-05, + "loss": 0.1233, + "step": 20432 + }, + { + "epoch": 6.31, + "learning_rate": 1.602059302102722e-05, + "loss": 0.128, + "step": 20433 + }, + { + "epoch": 6.31, + "learning_rate": 1.6020193693414192e-05, + "loss": 0.1124, + "step": 20434 + }, + { + "epoch": 6.31, + "learning_rate": 1.6019794350743552e-05, + "loss": 0.1068, + "step": 20435 + }, + { + "epoch": 6.31, + "learning_rate": 1.601939499301632e-05, + "loss": 0.1118, + "step": 20436 + }, + { + "epoch": 6.31, + "learning_rate": 1.6018995620233475e-05, + "loss": 0.1291, + "step": 20437 + }, + { + "epoch": 6.31, + "learning_rate": 1.6018596232396024e-05, + "loss": 0.1171, + "step": 20438 + }, + { + "epoch": 6.31, + "learning_rate": 1.601819682950497e-05, + "loss": 0.126, + "step": 20439 + }, + { + "epoch": 6.31, + "learning_rate": 1.6017797411561304e-05, + "loss": 0.125, + "step": 20440 + }, + { + "epoch": 6.31, + "learning_rate": 1.6017397978566033e-05, + "loss": 0.1136, + "step": 20441 + }, + { + "epoch": 6.31, + "learning_rate": 1.601699853052015e-05, + "loss": 0.1217, + "step": 20442 + }, + { + "epoch": 6.31, + "learning_rate": 1.601659906742466e-05, + "loss": 0.1208, + "step": 20443 + }, + { + "epoch": 6.31, + "learning_rate": 1.6016199589280555e-05, + "loss": 0.109, + "step": 20444 + }, + { + "epoch": 6.31, + "learning_rate": 1.6015800096088837e-05, + "loss": 0.1223, + "step": 20445 + }, + { + "epoch": 6.31, + "learning_rate": 1.6015400587850507e-05, + "loss": 0.1276, + "step": 20446 + }, + { + "epoch": 6.31, + "learning_rate": 1.601500106456656e-05, + "loss": 0.113, + "step": 20447 + }, + { + "epoch": 6.31, + "learning_rate": 1.6014601526238002e-05, + "loss": 0.1197, + "step": 20448 + }, + { + "epoch": 6.32, + "learning_rate": 1.6014201972865827e-05, + "loss": 0.1188, + "step": 20449 + }, + { + "epoch": 6.32, + "learning_rate": 1.6013802404451037e-05, + "loss": 0.1257, + "step": 20450 + }, + { + "epoch": 6.32, + "learning_rate": 1.601340282099463e-05, + "loss": 0.1129, + "step": 20451 + }, + { + "epoch": 6.32, + "learning_rate": 1.6013003222497604e-05, + "loss": 0.1081, + "step": 20452 + }, + { + "epoch": 6.32, + "learning_rate": 1.6012603608960962e-05, + "loss": 0.122, + "step": 20453 + }, + { + "epoch": 6.32, + "learning_rate": 1.6012203980385702e-05, + "loss": 0.1197, + "step": 20454 + }, + { + "epoch": 6.32, + "learning_rate": 1.6011804336772825e-05, + "loss": 0.1137, + "step": 20455 + }, + { + "epoch": 6.32, + "learning_rate": 1.6011404678123327e-05, + "loss": 0.1251, + "step": 20456 + }, + { + "epoch": 6.32, + "learning_rate": 1.601100500443821e-05, + "loss": 0.1461, + "step": 20457 + }, + { + "epoch": 6.32, + "learning_rate": 1.601060531571847e-05, + "loss": 0.1242, + "step": 20458 + }, + { + "epoch": 6.32, + "learning_rate": 1.6010205611965114e-05, + "loss": 0.1093, + "step": 20459 + }, + { + "epoch": 6.32, + "learning_rate": 1.6009805893179134e-05, + "loss": 0.1285, + "step": 20460 + }, + { + "epoch": 6.32, + "learning_rate": 1.6009406159361534e-05, + "loss": 0.1145, + "step": 20461 + }, + { + "epoch": 6.32, + "learning_rate": 1.6009006410513314e-05, + "loss": 0.1193, + "step": 20462 + }, + { + "epoch": 6.32, + "learning_rate": 1.6008606646635473e-05, + "loss": 0.1277, + "step": 20463 + }, + { + "epoch": 6.32, + "learning_rate": 1.600820686772901e-05, + "loss": 0.1045, + "step": 20464 + }, + { + "epoch": 6.32, + "learning_rate": 1.600780707379493e-05, + "loss": 0.1135, + "step": 20465 + }, + { + "epoch": 6.32, + "learning_rate": 1.6007407264834224e-05, + "loss": 0.1135, + "step": 20466 + }, + { + "epoch": 6.32, + "learning_rate": 1.60070074408479e-05, + "loss": 0.1339, + "step": 20467 + }, + { + "epoch": 6.32, + "learning_rate": 1.6006607601836953e-05, + "loss": 0.1165, + "step": 20468 + }, + { + "epoch": 6.32, + "learning_rate": 1.6006207747802385e-05, + "loss": 0.1206, + "step": 20469 + }, + { + "epoch": 6.32, + "learning_rate": 1.6005807878745194e-05, + "loss": 0.1225, + "step": 20470 + }, + { + "epoch": 6.32, + "learning_rate": 1.6005407994666385e-05, + "loss": 0.1188, + "step": 20471 + }, + { + "epoch": 6.32, + "learning_rate": 1.6005008095566955e-05, + "loss": 0.1162, + "step": 20472 + }, + { + "epoch": 6.32, + "learning_rate": 1.6004608181447903e-05, + "loss": 0.1176, + "step": 20473 + }, + { + "epoch": 6.32, + "learning_rate": 1.600420825231023e-05, + "loss": 0.1107, + "step": 20474 + }, + { + "epoch": 6.32, + "learning_rate": 1.600380830815494e-05, + "loss": 0.1144, + "step": 20475 + }, + { + "epoch": 6.32, + "learning_rate": 1.600340834898303e-05, + "loss": 0.1135, + "step": 20476 + }, + { + "epoch": 6.32, + "learning_rate": 1.6003008374795495e-05, + "loss": 0.103, + "step": 20477 + }, + { + "epoch": 6.32, + "learning_rate": 1.600260838559335e-05, + "loss": 0.1196, + "step": 20478 + }, + { + "epoch": 6.32, + "learning_rate": 1.6002208381377583e-05, + "loss": 0.1058, + "step": 20479 + }, + { + "epoch": 6.32, + "learning_rate": 1.6001808362149196e-05, + "loss": 0.1217, + "step": 20480 + }, + { + "epoch": 6.33, + "learning_rate": 1.6001408327909196e-05, + "loss": 0.1137, + "step": 20481 + }, + { + "epoch": 6.33, + "learning_rate": 1.6001008278658576e-05, + "loss": 0.1273, + "step": 20482 + }, + { + "epoch": 6.33, + "learning_rate": 1.600060821439834e-05, + "loss": 0.1252, + "step": 20483 + }, + { + "epoch": 6.33, + "learning_rate": 1.600020813512949e-05, + "loss": 0.1174, + "step": 20484 + }, + { + "epoch": 6.33, + "learning_rate": 1.5999808040853023e-05, + "loss": 0.1202, + "step": 20485 + }, + { + "epoch": 6.33, + "learning_rate": 1.5999407931569943e-05, + "loss": 0.1153, + "step": 20486 + }, + { + "epoch": 6.33, + "learning_rate": 1.5999007807281247e-05, + "loss": 0.1191, + "step": 20487 + }, + { + "epoch": 6.33, + "learning_rate": 1.599860766798794e-05, + "loss": 0.1064, + "step": 20488 + }, + { + "epoch": 6.33, + "learning_rate": 1.5998207513691023e-05, + "loss": 0.1192, + "step": 20489 + }, + { + "epoch": 6.33, + "learning_rate": 1.5997807344391494e-05, + "loss": 0.1177, + "step": 20490 + }, + { + "epoch": 6.33, + "learning_rate": 1.599740716009035e-05, + "loss": 0.1149, + "step": 20491 + }, + { + "epoch": 6.33, + "learning_rate": 1.5997006960788604e-05, + "loss": 0.111, + "step": 20492 + }, + { + "epoch": 6.33, + "learning_rate": 1.5996606746487248e-05, + "loss": 0.1167, + "step": 20493 + }, + { + "epoch": 6.33, + "learning_rate": 1.5996206517187283e-05, + "loss": 0.1173, + "step": 20494 + }, + { + "epoch": 6.33, + "learning_rate": 1.5995806272889713e-05, + "loss": 0.1215, + "step": 20495 + }, + { + "epoch": 6.33, + "learning_rate": 1.599540601359554e-05, + "loss": 0.1111, + "step": 20496 + }, + { + "epoch": 6.33, + "learning_rate": 1.5995005739305758e-05, + "loss": 0.1131, + "step": 20497 + }, + { + "epoch": 6.33, + "learning_rate": 1.599460545002138e-05, + "loss": 0.1141, + "step": 20498 + }, + { + "epoch": 6.33, + "learning_rate": 1.5994205145743396e-05, + "loss": 0.1058, + "step": 20499 + }, + { + "epoch": 6.33, + "learning_rate": 1.5993804826472808e-05, + "loss": 0.1136, + "step": 20500 + }, + { + "epoch": 6.33, + "learning_rate": 1.5993404492210628e-05, + "loss": 0.1202, + "step": 20501 + }, + { + "epoch": 6.33, + "learning_rate": 1.5993004142957845e-05, + "loss": 0.121, + "step": 20502 + }, + { + "epoch": 6.33, + "learning_rate": 1.599260377871547e-05, + "loss": 0.1132, + "step": 20503 + }, + { + "epoch": 6.33, + "learning_rate": 1.59922033994845e-05, + "loss": 0.1228, + "step": 20504 + }, + { + "epoch": 6.33, + "learning_rate": 1.5991803005265932e-05, + "loss": 0.1258, + "step": 20505 + }, + { + "epoch": 6.33, + "learning_rate": 1.599140259606077e-05, + "loss": 0.1105, + "step": 20506 + }, + { + "epoch": 6.33, + "learning_rate": 1.5991002171870024e-05, + "loss": 0.1162, + "step": 20507 + }, + { + "epoch": 6.33, + "learning_rate": 1.5990601732694685e-05, + "loss": 0.1231, + "step": 20508 + }, + { + "epoch": 6.33, + "learning_rate": 1.599020127853576e-05, + "loss": 0.1335, + "step": 20509 + }, + { + "epoch": 6.33, + "learning_rate": 1.5989800809394253e-05, + "loss": 0.1253, + "step": 20510 + }, + { + "epoch": 6.33, + "learning_rate": 1.5989400325271155e-05, + "loss": 0.0984, + "step": 20511 + }, + { + "epoch": 6.33, + "learning_rate": 1.5988999826167476e-05, + "loss": 0.1194, + "step": 20512 + }, + { + "epoch": 6.33, + "learning_rate": 1.598859931208422e-05, + "loss": 0.1298, + "step": 20513 + }, + { + "epoch": 6.34, + "learning_rate": 1.598819878302238e-05, + "loss": 0.117, + "step": 20514 + }, + { + "epoch": 6.34, + "learning_rate": 1.5987798238982964e-05, + "loss": 0.1164, + "step": 20515 + }, + { + "epoch": 6.34, + "learning_rate": 1.5987397679966975e-05, + "loss": 0.126, + "step": 20516 + }, + { + "epoch": 6.34, + "learning_rate": 1.598699710597541e-05, + "loss": 0.1211, + "step": 20517 + }, + { + "epoch": 6.34, + "learning_rate": 1.5986596517009273e-05, + "loss": 0.1112, + "step": 20518 + }, + { + "epoch": 6.34, + "learning_rate": 1.5986195913069566e-05, + "loss": 0.1269, + "step": 20519 + }, + { + "epoch": 6.34, + "learning_rate": 1.5985795294157292e-05, + "loss": 0.1264, + "step": 20520 + }, + { + "epoch": 6.34, + "learning_rate": 1.5985394660273453e-05, + "loss": 0.1226, + "step": 20521 + }, + { + "epoch": 6.34, + "learning_rate": 1.5984994011419048e-05, + "loss": 0.1149, + "step": 20522 + }, + { + "epoch": 6.34, + "learning_rate": 1.5984593347595085e-05, + "loss": 0.1096, + "step": 20523 + }, + { + "epoch": 6.34, + "learning_rate": 1.598419266880256e-05, + "loss": 0.1151, + "step": 20524 + }, + { + "epoch": 6.34, + "learning_rate": 1.5983791975042478e-05, + "loss": 0.1265, + "step": 20525 + }, + { + "epoch": 6.34, + "learning_rate": 1.598339126631584e-05, + "loss": 0.118, + "step": 20526 + }, + { + "epoch": 6.34, + "learning_rate": 1.598299054262365e-05, + "loss": 0.1189, + "step": 20527 + }, + { + "epoch": 6.34, + "learning_rate": 1.598258980396691e-05, + "loss": 0.1242, + "step": 20528 + }, + { + "epoch": 6.34, + "learning_rate": 1.5982189050346623e-05, + "loss": 0.1236, + "step": 20529 + }, + { + "epoch": 6.34, + "learning_rate": 1.598178828176379e-05, + "loss": 0.1134, + "step": 20530 + }, + { + "epoch": 6.34, + "learning_rate": 1.598138749821941e-05, + "loss": 0.1201, + "step": 20531 + }, + { + "epoch": 6.34, + "learning_rate": 1.598098669971449e-05, + "loss": 0.1129, + "step": 20532 + }, + { + "epoch": 6.34, + "learning_rate": 1.5980585886250034e-05, + "loss": 0.1179, + "step": 20533 + }, + { + "epoch": 6.34, + "learning_rate": 1.598018505782704e-05, + "loss": 0.1088, + "step": 20534 + }, + { + "epoch": 6.34, + "learning_rate": 1.597978421444651e-05, + "loss": 0.117, + "step": 20535 + }, + { + "epoch": 6.34, + "learning_rate": 1.597938335610945e-05, + "loss": 0.124, + "step": 20536 + }, + { + "epoch": 6.34, + "learning_rate": 1.5978982482816865e-05, + "loss": 0.1256, + "step": 20537 + }, + { + "epoch": 6.34, + "learning_rate": 1.5978581594569754e-05, + "loss": 0.106, + "step": 20538 + }, + { + "epoch": 6.34, + "learning_rate": 1.597818069136912e-05, + "loss": 0.1121, + "step": 20539 + }, + { + "epoch": 6.34, + "learning_rate": 1.5977779773215965e-05, + "loss": 0.1232, + "step": 20540 + }, + { + "epoch": 6.34, + "learning_rate": 1.597737884011129e-05, + "loss": 0.1156, + "step": 20541 + }, + { + "epoch": 6.34, + "learning_rate": 1.59769778920561e-05, + "loss": 0.1154, + "step": 20542 + }, + { + "epoch": 6.34, + "learning_rate": 1.5976576929051405e-05, + "loss": 0.1159, + "step": 20543 + }, + { + "epoch": 6.34, + "learning_rate": 1.5976175951098195e-05, + "loss": 0.1235, + "step": 20544 + }, + { + "epoch": 6.34, + "learning_rate": 1.597577495819748e-05, + "loss": 0.1229, + "step": 20545 + }, + { + "epoch": 6.35, + "learning_rate": 1.597537395035026e-05, + "loss": 0.1201, + "step": 20546 + }, + { + "epoch": 6.35, + "learning_rate": 1.5974972927557546e-05, + "loss": 0.1224, + "step": 20547 + }, + { + "epoch": 6.35, + "learning_rate": 1.597457188982033e-05, + "loss": 0.1189, + "step": 20548 + }, + { + "epoch": 6.35, + "learning_rate": 1.597417083713962e-05, + "loss": 0.115, + "step": 20549 + }, + { + "epoch": 6.35, + "learning_rate": 1.597376976951642e-05, + "loss": 0.124, + "step": 20550 + }, + { + "epoch": 6.35, + "learning_rate": 1.5973368686951734e-05, + "loss": 0.1211, + "step": 20551 + }, + { + "epoch": 6.35, + "learning_rate": 1.5972967589446563e-05, + "loss": 0.1124, + "step": 20552 + }, + { + "epoch": 6.35, + "learning_rate": 1.597256647700191e-05, + "loss": 0.1115, + "step": 20553 + }, + { + "epoch": 6.35, + "learning_rate": 1.5972165349618775e-05, + "loss": 0.125, + "step": 20554 + }, + { + "epoch": 6.35, + "learning_rate": 1.597176420729817e-05, + "loss": 0.119, + "step": 20555 + }, + { + "epoch": 6.35, + "learning_rate": 1.597136305004109e-05, + "loss": 0.1227, + "step": 20556 + }, + { + "epoch": 6.35, + "learning_rate": 1.5970961877848548e-05, + "loss": 0.1122, + "step": 20557 + }, + { + "epoch": 6.35, + "learning_rate": 1.5970560690721538e-05, + "loss": 0.1135, + "step": 20558 + }, + { + "epoch": 6.35, + "learning_rate": 1.5970159488661066e-05, + "loss": 0.114, + "step": 20559 + }, + { + "epoch": 6.35, + "learning_rate": 1.5969758271668134e-05, + "loss": 0.1141, + "step": 20560 + }, + { + "epoch": 6.35, + "learning_rate": 1.596935703974375e-05, + "loss": 0.1156, + "step": 20561 + }, + { + "epoch": 6.35, + "learning_rate": 1.5968955792888917e-05, + "loss": 0.1154, + "step": 20562 + }, + { + "epoch": 6.35, + "learning_rate": 1.5968554531104636e-05, + "loss": 0.1198, + "step": 20563 + }, + { + "epoch": 6.35, + "learning_rate": 1.596815325439191e-05, + "loss": 0.1196, + "step": 20564 + }, + { + "epoch": 6.35, + "learning_rate": 1.5967751962751745e-05, + "loss": 0.1177, + "step": 20565 + }, + { + "epoch": 6.35, + "learning_rate": 1.5967350656185144e-05, + "loss": 0.1135, + "step": 20566 + }, + { + "epoch": 6.35, + "learning_rate": 1.596694933469311e-05, + "loss": 0.1232, + "step": 20567 + }, + { + "epoch": 6.35, + "learning_rate": 1.5966547998276652e-05, + "loss": 0.1146, + "step": 20568 + }, + { + "epoch": 6.35, + "learning_rate": 1.5966146646936764e-05, + "loss": 0.1179, + "step": 20569 + }, + { + "epoch": 6.35, + "learning_rate": 1.5965745280674455e-05, + "loss": 0.1286, + "step": 20570 + }, + { + "epoch": 6.35, + "learning_rate": 1.596534389949073e-05, + "loss": 0.1128, + "step": 20571 + }, + { + "epoch": 6.35, + "learning_rate": 1.5964942503386593e-05, + "loss": 0.1182, + "step": 20572 + }, + { + "epoch": 6.35, + "learning_rate": 1.5964541092363046e-05, + "loss": 0.1173, + "step": 20573 + }, + { + "epoch": 6.35, + "learning_rate": 1.5964139666421093e-05, + "loss": 0.1321, + "step": 20574 + }, + { + "epoch": 6.35, + "learning_rate": 1.596373822556174e-05, + "loss": 0.122, + "step": 20575 + }, + { + "epoch": 6.35, + "learning_rate": 1.596333676978599e-05, + "loss": 0.118, + "step": 20576 + }, + { + "epoch": 6.35, + "learning_rate": 1.5962935299094847e-05, + "loss": 0.1185, + "step": 20577 + }, + { + "epoch": 6.35, + "learning_rate": 1.5962533813489316e-05, + "loss": 0.1229, + "step": 20578 + }, + { + "epoch": 6.36, + "learning_rate": 1.59621323129704e-05, + "loss": 0.1103, + "step": 20579 + }, + { + "epoch": 6.36, + "learning_rate": 1.5961730797539103e-05, + "loss": 0.1222, + "step": 20580 + }, + { + "epoch": 6.36, + "learning_rate": 1.596132926719643e-05, + "loss": 0.1145, + "step": 20581 + }, + { + "epoch": 6.36, + "learning_rate": 1.5960927721943385e-05, + "loss": 0.1221, + "step": 20582 + }, + { + "epoch": 6.36, + "learning_rate": 1.5960526161780974e-05, + "loss": 0.1248, + "step": 20583 + }, + { + "epoch": 6.36, + "learning_rate": 1.59601245867102e-05, + "loss": 0.1182, + "step": 20584 + }, + { + "epoch": 6.36, + "learning_rate": 1.5959722996732064e-05, + "loss": 0.1184, + "step": 20585 + }, + { + "epoch": 6.36, + "learning_rate": 1.5959321391847578e-05, + "loss": 0.116, + "step": 20586 + }, + { + "epoch": 6.36, + "learning_rate": 1.595891977205774e-05, + "loss": 0.1219, + "step": 20587 + }, + { + "epoch": 6.36, + "learning_rate": 1.5958518137363556e-05, + "loss": 0.112, + "step": 20588 + }, + { + "epoch": 6.36, + "learning_rate": 1.5958116487766036e-05, + "loss": 0.1302, + "step": 20589 + }, + { + "epoch": 6.36, + "learning_rate": 1.5957714823266175e-05, + "loss": 0.1152, + "step": 20590 + }, + { + "epoch": 6.36, + "learning_rate": 1.5957313143864985e-05, + "loss": 0.1256, + "step": 20591 + }, + { + "epoch": 6.36, + "learning_rate": 1.5956911449563465e-05, + "loss": 0.1158, + "step": 20592 + }, + { + "epoch": 6.36, + "learning_rate": 1.5956509740362626e-05, + "loss": 0.1163, + "step": 20593 + }, + { + "epoch": 6.36, + "learning_rate": 1.595610801626347e-05, + "loss": 0.1219, + "step": 20594 + }, + { + "epoch": 6.36, + "learning_rate": 1.5955706277267e-05, + "loss": 0.126, + "step": 20595 + }, + { + "epoch": 6.36, + "learning_rate": 1.595530452337422e-05, + "loss": 0.1197, + "step": 20596 + }, + { + "epoch": 6.36, + "learning_rate": 1.5954902754586143e-05, + "loss": 0.133, + "step": 20597 + }, + { + "epoch": 6.36, + "learning_rate": 1.5954500970903768e-05, + "loss": 0.1059, + "step": 20598 + }, + { + "epoch": 6.36, + "learning_rate": 1.5954099172328095e-05, + "loss": 0.1181, + "step": 20599 + }, + { + "epoch": 6.36, + "learning_rate": 1.5953697358860136e-05, + "loss": 0.1187, + "step": 20600 + }, + { + "epoch": 6.36, + "learning_rate": 1.5953295530500894e-05, + "loss": 0.1037, + "step": 20601 + }, + { + "epoch": 6.36, + "learning_rate": 1.5952893687251375e-05, + "loss": 0.1132, + "step": 20602 + }, + { + "epoch": 6.36, + "learning_rate": 1.5952491829112582e-05, + "loss": 0.1185, + "step": 20603 + }, + { + "epoch": 6.36, + "learning_rate": 1.595208995608552e-05, + "loss": 0.1241, + "step": 20604 + }, + { + "epoch": 6.36, + "learning_rate": 1.59516880681712e-05, + "loss": 0.1278, + "step": 20605 + }, + { + "epoch": 6.36, + "learning_rate": 1.5951286165370622e-05, + "loss": 0.1269, + "step": 20606 + }, + { + "epoch": 6.36, + "learning_rate": 1.5950884247684786e-05, + "loss": 0.1173, + "step": 20607 + }, + { + "epoch": 6.36, + "learning_rate": 1.5950482315114708e-05, + "loss": 0.1208, + "step": 20608 + }, + { + "epoch": 6.36, + "learning_rate": 1.5950080367661387e-05, + "loss": 0.1243, + "step": 20609 + }, + { + "epoch": 6.36, + "learning_rate": 1.5949678405325832e-05, + "loss": 0.1183, + "step": 20610 + }, + { + "epoch": 6.37, + "learning_rate": 1.5949276428109043e-05, + "loss": 0.111, + "step": 20611 + }, + { + "epoch": 6.37, + "learning_rate": 1.594887443601203e-05, + "loss": 0.108, + "step": 20612 + }, + { + "epoch": 6.37, + "learning_rate": 1.5948472429035796e-05, + "loss": 0.1104, + "step": 20613 + }, + { + "epoch": 6.37, + "learning_rate": 1.594807040718135e-05, + "loss": 0.1177, + "step": 20614 + }, + { + "epoch": 6.37, + "learning_rate": 1.5947668370449692e-05, + "loss": 0.1314, + "step": 20615 + }, + { + "epoch": 6.37, + "learning_rate": 1.5947266318841835e-05, + "loss": 0.1198, + "step": 20616 + }, + { + "epoch": 6.37, + "learning_rate": 1.5946864252358775e-05, + "loss": 0.1284, + "step": 20617 + }, + { + "epoch": 6.37, + "learning_rate": 1.5946462171001525e-05, + "loss": 0.1213, + "step": 20618 + }, + { + "epoch": 6.37, + "learning_rate": 1.594606007477109e-05, + "loss": 0.1196, + "step": 20619 + }, + { + "epoch": 6.37, + "learning_rate": 1.5945657963668474e-05, + "loss": 0.1164, + "step": 20620 + }, + { + "epoch": 6.37, + "learning_rate": 1.5945255837694678e-05, + "loss": 0.1243, + "step": 20621 + }, + { + "epoch": 6.37, + "learning_rate": 1.594485369685072e-05, + "loss": 0.1262, + "step": 20622 + }, + { + "epoch": 6.37, + "learning_rate": 1.5944451541137595e-05, + "loss": 0.1105, + "step": 20623 + }, + { + "epoch": 6.37, + "learning_rate": 1.594404937055631e-05, + "loss": 0.1299, + "step": 20624 + }, + { + "epoch": 6.37, + "learning_rate": 1.594364718510788e-05, + "loss": 0.1181, + "step": 20625 + }, + { + "epoch": 6.37, + "learning_rate": 1.59432449847933e-05, + "loss": 0.1135, + "step": 20626 + }, + { + "epoch": 6.37, + "learning_rate": 1.594284276961358e-05, + "loss": 0.1276, + "step": 20627 + }, + { + "epoch": 6.37, + "learning_rate": 1.5942440539569726e-05, + "loss": 0.124, + "step": 20628 + }, + { + "epoch": 6.37, + "learning_rate": 1.5942038294662747e-05, + "loss": 0.1189, + "step": 20629 + }, + { + "epoch": 6.37, + "learning_rate": 1.5941636034893643e-05, + "loss": 0.1233, + "step": 20630 + }, + { + "epoch": 6.37, + "learning_rate": 1.5941233760263427e-05, + "loss": 0.1087, + "step": 20631 + }, + { + "epoch": 6.37, + "learning_rate": 1.5940831470773102e-05, + "loss": 0.1128, + "step": 20632 + }, + { + "epoch": 6.37, + "learning_rate": 1.594042916642367e-05, + "loss": 0.1125, + "step": 20633 + }, + { + "epoch": 6.37, + "learning_rate": 1.5940026847216145e-05, + "loss": 0.1147, + "step": 20634 + }, + { + "epoch": 6.37, + "learning_rate": 1.5939624513151528e-05, + "loss": 0.127, + "step": 20635 + }, + { + "epoch": 6.37, + "learning_rate": 1.5939222164230827e-05, + "loss": 0.1318, + "step": 20636 + }, + { + "epoch": 6.37, + "learning_rate": 1.593881980045505e-05, + "loss": 0.1225, + "step": 20637 + }, + { + "epoch": 6.37, + "learning_rate": 1.5938417421825196e-05, + "loss": 0.1126, + "step": 20638 + }, + { + "epoch": 6.37, + "learning_rate": 1.593801502834228e-05, + "loss": 0.1311, + "step": 20639 + }, + { + "epoch": 6.37, + "learning_rate": 1.593761262000731e-05, + "loss": 0.1213, + "step": 20640 + }, + { + "epoch": 6.37, + "learning_rate": 1.593721019682128e-05, + "loss": 0.1271, + "step": 20641 + }, + { + "epoch": 6.37, + "learning_rate": 1.5936807758785208e-05, + "loss": 0.1326, + "step": 20642 + }, + { + "epoch": 6.38, + "learning_rate": 1.59364053059001e-05, + "loss": 0.1239, + "step": 20643 + }, + { + "epoch": 6.38, + "learning_rate": 1.5936002838166955e-05, + "loss": 0.1209, + "step": 20644 + }, + { + "epoch": 6.38, + "learning_rate": 1.5935600355586783e-05, + "loss": 0.1279, + "step": 20645 + }, + { + "epoch": 6.38, + "learning_rate": 1.5935197858160597e-05, + "loss": 0.1244, + "step": 20646 + }, + { + "epoch": 6.38, + "learning_rate": 1.59347953458894e-05, + "loss": 0.1171, + "step": 20647 + }, + { + "epoch": 6.38, + "learning_rate": 1.5934392818774193e-05, + "loss": 0.1094, + "step": 20648 + }, + { + "epoch": 6.38, + "learning_rate": 1.5933990276815988e-05, + "loss": 0.1297, + "step": 20649 + }, + { + "epoch": 6.38, + "learning_rate": 1.593358772001579e-05, + "loss": 0.1214, + "step": 20650 + }, + { + "epoch": 6.38, + "learning_rate": 1.593318514837461e-05, + "loss": 0.123, + "step": 20651 + }, + { + "epoch": 6.38, + "learning_rate": 1.5932782561893446e-05, + "loss": 0.1215, + "step": 20652 + }, + { + "epoch": 6.38, + "learning_rate": 1.5932379960573315e-05, + "loss": 0.113, + "step": 20653 + }, + { + "epoch": 6.38, + "learning_rate": 1.593197734441522e-05, + "loss": 0.121, + "step": 20654 + }, + { + "epoch": 6.38, + "learning_rate": 1.5931574713420165e-05, + "loss": 0.1372, + "step": 20655 + }, + { + "epoch": 6.38, + "learning_rate": 1.593117206758916e-05, + "loss": 0.1274, + "step": 20656 + }, + { + "epoch": 6.38, + "learning_rate": 1.593076940692322e-05, + "loss": 0.1262, + "step": 20657 + }, + { + "epoch": 6.38, + "learning_rate": 1.5930366731423334e-05, + "loss": 0.1181, + "step": 20658 + }, + { + "epoch": 6.38, + "learning_rate": 1.5929964041090524e-05, + "loss": 0.1177, + "step": 20659 + }, + { + "epoch": 6.38, + "learning_rate": 1.592956133592579e-05, + "loss": 0.112, + "step": 20660 + }, + { + "epoch": 6.38, + "learning_rate": 1.5929158615930143e-05, + "loss": 0.1233, + "step": 20661 + }, + { + "epoch": 6.38, + "learning_rate": 1.592875588110459e-05, + "loss": 0.1283, + "step": 20662 + }, + { + "epoch": 6.38, + "learning_rate": 1.5928353131450135e-05, + "loss": 0.123, + "step": 20663 + }, + { + "epoch": 6.38, + "learning_rate": 1.592795036696779e-05, + "loss": 0.1257, + "step": 20664 + }, + { + "epoch": 6.38, + "learning_rate": 1.5927547587658558e-05, + "loss": 0.1175, + "step": 20665 + }, + { + "epoch": 6.38, + "learning_rate": 1.5927144793523446e-05, + "loss": 0.1205, + "step": 20666 + }, + { + "epoch": 6.38, + "learning_rate": 1.5926741984563468e-05, + "loss": 0.119, + "step": 20667 + }, + { + "epoch": 6.38, + "learning_rate": 1.5926339160779627e-05, + "loss": 0.1213, + "step": 20668 + }, + { + "epoch": 6.38, + "learning_rate": 1.5925936322172927e-05, + "loss": 0.1272, + "step": 20669 + }, + { + "epoch": 6.38, + "learning_rate": 1.5925533468744383e-05, + "loss": 0.1251, + "step": 20670 + }, + { + "epoch": 6.38, + "learning_rate": 1.5925130600495e-05, + "loss": 0.1202, + "step": 20671 + }, + { + "epoch": 6.38, + "learning_rate": 1.5924727717425784e-05, + "loss": 0.1232, + "step": 20672 + }, + { + "epoch": 6.38, + "learning_rate": 1.592432481953774e-05, + "loss": 0.1195, + "step": 20673 + }, + { + "epoch": 6.38, + "learning_rate": 1.5923921906831884e-05, + "loss": 0.1173, + "step": 20674 + }, + { + "epoch": 6.38, + "learning_rate": 1.5923518979309217e-05, + "loss": 0.1253, + "step": 20675 + }, + { + "epoch": 6.39, + "learning_rate": 1.5923116036970746e-05, + "loss": 0.1374, + "step": 20676 + }, + { + "epoch": 6.39, + "learning_rate": 1.5922713079817485e-05, + "loss": 0.1148, + "step": 20677 + }, + { + "epoch": 6.39, + "learning_rate": 1.5922310107850438e-05, + "loss": 0.1194, + "step": 20678 + }, + { + "epoch": 6.39, + "learning_rate": 1.592190712107061e-05, + "loss": 0.1238, + "step": 20679 + }, + { + "epoch": 6.39, + "learning_rate": 1.5921504119479016e-05, + "loss": 0.1246, + "step": 20680 + }, + { + "epoch": 6.39, + "learning_rate": 1.5921101103076658e-05, + "loss": 0.1234, + "step": 20681 + }, + { + "epoch": 6.39, + "learning_rate": 1.5920698071864545e-05, + "loss": 0.1102, + "step": 20682 + }, + { + "epoch": 6.39, + "learning_rate": 1.5920295025843687e-05, + "loss": 0.1161, + "step": 20683 + }, + { + "epoch": 6.39, + "learning_rate": 1.5919891965015094e-05, + "loss": 0.1374, + "step": 20684 + }, + { + "epoch": 6.39, + "learning_rate": 1.591948888937977e-05, + "loss": 0.1081, + "step": 20685 + }, + { + "epoch": 6.39, + "learning_rate": 1.5919085798938722e-05, + "loss": 0.1124, + "step": 20686 + }, + { + "epoch": 6.39, + "learning_rate": 1.5918682693692965e-05, + "loss": 0.1321, + "step": 20687 + }, + { + "epoch": 6.39, + "learning_rate": 1.59182795736435e-05, + "loss": 0.1201, + "step": 20688 + }, + { + "epoch": 6.39, + "learning_rate": 1.591787643879134e-05, + "loss": 0.1198, + "step": 20689 + }, + { + "epoch": 6.39, + "learning_rate": 1.591747328913749e-05, + "loss": 0.116, + "step": 20690 + }, + { + "epoch": 6.39, + "learning_rate": 1.5917070124682964e-05, + "loss": 0.1161, + "step": 20691 + }, + { + "epoch": 6.39, + "learning_rate": 1.5916666945428763e-05, + "loss": 0.1168, + "step": 20692 + }, + { + "epoch": 6.39, + "learning_rate": 1.5916263751375898e-05, + "loss": 0.1236, + "step": 20693 + }, + { + "epoch": 6.39, + "learning_rate": 1.591586054252538e-05, + "loss": 0.1257, + "step": 20694 + }, + { + "epoch": 6.39, + "learning_rate": 1.5915457318878217e-05, + "loss": 0.1257, + "step": 20695 + }, + { + "epoch": 6.39, + "learning_rate": 1.5915054080435414e-05, + "loss": 0.1228, + "step": 20696 + }, + { + "epoch": 6.39, + "learning_rate": 1.5914650827197985e-05, + "loss": 0.1222, + "step": 20697 + }, + { + "epoch": 6.39, + "learning_rate": 1.591424755916693e-05, + "loss": 0.1122, + "step": 20698 + }, + { + "epoch": 6.39, + "learning_rate": 1.591384427634327e-05, + "loss": 0.1245, + "step": 20699 + }, + { + "epoch": 6.39, + "learning_rate": 1.5913440978728002e-05, + "loss": 0.1227, + "step": 20700 + }, + { + "epoch": 6.39, + "learning_rate": 1.591303766632214e-05, + "loss": 0.1277, + "step": 20701 + }, + { + "epoch": 6.39, + "learning_rate": 1.5912634339126697e-05, + "loss": 0.1108, + "step": 20702 + }, + { + "epoch": 6.39, + "learning_rate": 1.591223099714267e-05, + "loss": 0.1142, + "step": 20703 + }, + { + "epoch": 6.39, + "learning_rate": 1.5911827640371077e-05, + "loss": 0.1272, + "step": 20704 + }, + { + "epoch": 6.39, + "learning_rate": 1.5911424268812927e-05, + "loss": 0.1113, + "step": 20705 + }, + { + "epoch": 6.39, + "learning_rate": 1.5911020882469227e-05, + "loss": 0.1232, + "step": 20706 + }, + { + "epoch": 6.39, + "learning_rate": 1.5910617481340983e-05, + "loss": 0.1277, + "step": 20707 + }, + { + "epoch": 6.4, + "learning_rate": 1.591021406542921e-05, + "loss": 0.1222, + "step": 20708 + }, + { + "epoch": 6.4, + "learning_rate": 1.5909810634734912e-05, + "loss": 0.1208, + "step": 20709 + }, + { + "epoch": 6.4, + "learning_rate": 1.59094071892591e-05, + "loss": 0.1181, + "step": 20710 + }, + { + "epoch": 6.4, + "learning_rate": 1.5909003729002783e-05, + "loss": 0.1113, + "step": 20711 + }, + { + "epoch": 6.4, + "learning_rate": 1.5908600253966968e-05, + "loss": 0.1412, + "step": 20712 + }, + { + "epoch": 6.4, + "learning_rate": 1.5908196764152668e-05, + "loss": 0.1304, + "step": 20713 + }, + { + "epoch": 6.4, + "learning_rate": 1.5907793259560888e-05, + "loss": 0.1235, + "step": 20714 + }, + { + "epoch": 6.4, + "learning_rate": 1.5907389740192642e-05, + "loss": 0.1163, + "step": 20715 + }, + { + "epoch": 6.4, + "learning_rate": 1.5906986206048937e-05, + "loss": 0.1301, + "step": 20716 + }, + { + "epoch": 6.4, + "learning_rate": 1.590658265713078e-05, + "loss": 0.114, + "step": 20717 + }, + { + "epoch": 6.4, + "learning_rate": 1.5906179093439185e-05, + "loss": 0.1223, + "step": 20718 + }, + { + "epoch": 6.4, + "learning_rate": 1.590577551497516e-05, + "loss": 0.1313, + "step": 20719 + }, + { + "epoch": 6.4, + "learning_rate": 1.590537192173971e-05, + "loss": 0.124, + "step": 20720 + }, + { + "epoch": 6.4, + "learning_rate": 1.5904968313733848e-05, + "loss": 0.11, + "step": 20721 + }, + { + "epoch": 6.4, + "learning_rate": 1.5904564690958584e-05, + "loss": 0.1156, + "step": 20722 + }, + { + "epoch": 6.4, + "learning_rate": 1.5904161053414924e-05, + "loss": 0.12, + "step": 20723 + }, + { + "epoch": 6.4, + "learning_rate": 1.5903757401103884e-05, + "loss": 0.1169, + "step": 20724 + }, + { + "epoch": 6.4, + "learning_rate": 1.5903353734026472e-05, + "loss": 0.1206, + "step": 20725 + }, + { + "epoch": 6.4, + "learning_rate": 1.590295005218369e-05, + "loss": 0.1142, + "step": 20726 + }, + { + "epoch": 6.4, + "learning_rate": 1.590254635557656e-05, + "loss": 0.132, + "step": 20727 + }, + { + "epoch": 6.4, + "learning_rate": 1.5902142644206076e-05, + "loss": 0.1293, + "step": 20728 + }, + { + "epoch": 6.4, + "learning_rate": 1.5901738918073263e-05, + "loss": 0.126, + "step": 20729 + }, + { + "epoch": 6.4, + "learning_rate": 1.5901335177179125e-05, + "loss": 0.1257, + "step": 20730 + }, + { + "epoch": 6.4, + "learning_rate": 1.590093142152467e-05, + "loss": 0.1296, + "step": 20731 + }, + { + "epoch": 6.4, + "learning_rate": 1.5900527651110905e-05, + "loss": 0.1223, + "step": 20732 + }, + { + "epoch": 6.4, + "learning_rate": 1.590012386593885e-05, + "loss": 0.1266, + "step": 20733 + }, + { + "epoch": 6.4, + "learning_rate": 1.5899720066009506e-05, + "loss": 0.1153, + "step": 20734 + }, + { + "epoch": 6.4, + "learning_rate": 1.5899316251323887e-05, + "loss": 0.1202, + "step": 20735 + }, + { + "epoch": 6.4, + "learning_rate": 1.5898912421883005e-05, + "loss": 0.1212, + "step": 20736 + }, + { + "epoch": 6.4, + "learning_rate": 1.589850857768786e-05, + "loss": 0.113, + "step": 20737 + }, + { + "epoch": 6.4, + "learning_rate": 1.5898104718739474e-05, + "loss": 0.1112, + "step": 20738 + }, + { + "epoch": 6.4, + "learning_rate": 1.5897700845038854e-05, + "loss": 0.118, + "step": 20739 + }, + { + "epoch": 6.4, + "learning_rate": 1.5897296956587006e-05, + "loss": 0.1159, + "step": 20740 + }, + { + "epoch": 6.41, + "learning_rate": 1.5896893053384944e-05, + "loss": 0.1179, + "step": 20741 + }, + { + "epoch": 6.41, + "learning_rate": 1.5896489135433676e-05, + "loss": 0.1233, + "step": 20742 + }, + { + "epoch": 6.41, + "learning_rate": 1.5896085202734216e-05, + "loss": 0.1232, + "step": 20743 + }, + { + "epoch": 6.41, + "learning_rate": 1.5895681255287567e-05, + "loss": 0.1184, + "step": 20744 + }, + { + "epoch": 6.41, + "learning_rate": 1.5895277293094745e-05, + "loss": 0.1099, + "step": 20745 + }, + { + "epoch": 6.41, + "learning_rate": 1.589487331615676e-05, + "loss": 0.1222, + "step": 20746 + }, + { + "epoch": 6.41, + "learning_rate": 1.5894469324474622e-05, + "loss": 0.141, + "step": 20747 + }, + { + "epoch": 6.41, + "learning_rate": 1.589406531804934e-05, + "loss": 0.1167, + "step": 20748 + }, + { + "epoch": 6.41, + "learning_rate": 1.5893661296881927e-05, + "loss": 0.1294, + "step": 20749 + }, + { + "epoch": 6.41, + "learning_rate": 1.5893257260973394e-05, + "loss": 0.1213, + "step": 20750 + }, + { + "epoch": 6.41, + "learning_rate": 1.5892853210324745e-05, + "loss": 0.1186, + "step": 20751 + }, + { + "epoch": 6.41, + "learning_rate": 1.5892449144936998e-05, + "loss": 0.1062, + "step": 20752 + }, + { + "epoch": 6.41, + "learning_rate": 1.5892045064811162e-05, + "loss": 0.1238, + "step": 20753 + }, + { + "epoch": 6.41, + "learning_rate": 1.5891640969948244e-05, + "loss": 0.124, + "step": 20754 + }, + { + "epoch": 6.41, + "learning_rate": 1.589123686034926e-05, + "loss": 0.1241, + "step": 20755 + }, + { + "epoch": 6.41, + "learning_rate": 1.5890832736015217e-05, + "loss": 0.104, + "step": 20756 + }, + { + "epoch": 6.41, + "learning_rate": 1.5890428596947126e-05, + "loss": 0.1273, + "step": 20757 + }, + { + "epoch": 6.41, + "learning_rate": 1.5890024443146e-05, + "loss": 0.1171, + "step": 20758 + }, + { + "epoch": 6.41, + "learning_rate": 1.5889620274612848e-05, + "loss": 0.1239, + "step": 20759 + }, + { + "epoch": 6.41, + "learning_rate": 1.588921609134868e-05, + "loss": 0.1117, + "step": 20760 + }, + { + "epoch": 6.41, + "learning_rate": 1.5888811893354512e-05, + "loss": 0.1251, + "step": 20761 + }, + { + "epoch": 6.41, + "learning_rate": 1.5888407680631347e-05, + "loss": 0.121, + "step": 20762 + }, + { + "epoch": 6.41, + "learning_rate": 1.5888003453180204e-05, + "loss": 0.1174, + "step": 20763 + }, + { + "epoch": 6.41, + "learning_rate": 1.588759921100209e-05, + "loss": 0.1275, + "step": 20764 + }, + { + "epoch": 6.41, + "learning_rate": 1.5887194954098016e-05, + "loss": 0.1122, + "step": 20765 + }, + { + "epoch": 6.41, + "learning_rate": 1.5886790682468992e-05, + "loss": 0.1097, + "step": 20766 + }, + { + "epoch": 6.41, + "learning_rate": 1.5886386396116034e-05, + "loss": 0.1238, + "step": 20767 + }, + { + "epoch": 6.41, + "learning_rate": 1.588598209504015e-05, + "loss": 0.1195, + "step": 20768 + }, + { + "epoch": 6.41, + "learning_rate": 1.588557777924235e-05, + "loss": 0.1251, + "step": 20769 + }, + { + "epoch": 6.41, + "learning_rate": 1.5885173448723647e-05, + "loss": 0.1262, + "step": 20770 + }, + { + "epoch": 6.41, + "learning_rate": 1.5884769103485047e-05, + "loss": 0.1197, + "step": 20771 + }, + { + "epoch": 6.41, + "learning_rate": 1.588436474352757e-05, + "loss": 0.119, + "step": 20772 + }, + { + "epoch": 6.42, + "learning_rate": 1.5883960368852226e-05, + "loss": 0.1213, + "step": 20773 + }, + { + "epoch": 6.42, + "learning_rate": 1.5883555979460018e-05, + "loss": 0.118, + "step": 20774 + }, + { + "epoch": 6.42, + "learning_rate": 1.588315157535197e-05, + "loss": 0.1274, + "step": 20775 + }, + { + "epoch": 6.42, + "learning_rate": 1.5882747156529085e-05, + "loss": 0.1163, + "step": 20776 + }, + { + "epoch": 6.42, + "learning_rate": 1.5882342722992372e-05, + "loss": 0.1155, + "step": 20777 + }, + { + "epoch": 6.42, + "learning_rate": 1.5881938274742853e-05, + "loss": 0.1214, + "step": 20778 + }, + { + "epoch": 6.42, + "learning_rate": 1.5881533811781527e-05, + "loss": 0.1119, + "step": 20779 + }, + { + "epoch": 6.42, + "learning_rate": 1.5881129334109417e-05, + "loss": 0.1192, + "step": 20780 + }, + { + "epoch": 6.42, + "learning_rate": 1.588072484172753e-05, + "loss": 0.1229, + "step": 20781 + }, + { + "epoch": 6.42, + "learning_rate": 1.5880320334636875e-05, + "loss": 0.1168, + "step": 20782 + }, + { + "epoch": 6.42, + "learning_rate": 1.587991581283847e-05, + "loss": 0.1188, + "step": 20783 + }, + { + "epoch": 6.42, + "learning_rate": 1.5879511276333318e-05, + "loss": 0.121, + "step": 20784 + }, + { + "epoch": 6.42, + "learning_rate": 1.587910672512244e-05, + "loss": 0.124, + "step": 20785 + }, + { + "epoch": 6.42, + "learning_rate": 1.5878702159206842e-05, + "loss": 0.1208, + "step": 20786 + }, + { + "epoch": 6.42, + "learning_rate": 1.587829757858754e-05, + "loss": 0.1326, + "step": 20787 + }, + { + "epoch": 6.42, + "learning_rate": 1.5877892983265543e-05, + "loss": 0.1201, + "step": 20788 + }, + { + "epoch": 6.42, + "learning_rate": 1.5877488373241862e-05, + "loss": 0.1206, + "step": 20789 + }, + { + "epoch": 6.42, + "learning_rate": 1.587708374851751e-05, + "loss": 0.1091, + "step": 20790 + }, + { + "epoch": 6.42, + "learning_rate": 1.58766791090935e-05, + "loss": 0.1307, + "step": 20791 + }, + { + "epoch": 6.42, + "learning_rate": 1.5876274454970847e-05, + "loss": 0.124, + "step": 20792 + }, + { + "epoch": 6.42, + "learning_rate": 1.5875869786150557e-05, + "loss": 0.1231, + "step": 20793 + }, + { + "epoch": 6.42, + "learning_rate": 1.5875465102633642e-05, + "loss": 0.1196, + "step": 20794 + }, + { + "epoch": 6.42, + "learning_rate": 1.5875060404421123e-05, + "loss": 0.1263, + "step": 20795 + }, + { + "epoch": 6.42, + "learning_rate": 1.5874655691514004e-05, + "loss": 0.1272, + "step": 20796 + }, + { + "epoch": 6.42, + "learning_rate": 1.5874250963913297e-05, + "loss": 0.1189, + "step": 20797 + }, + { + "epoch": 6.42, + "learning_rate": 1.587384622162002e-05, + "loss": 0.123, + "step": 20798 + }, + { + "epoch": 6.42, + "learning_rate": 1.587344146463518e-05, + "loss": 0.1177, + "step": 20799 + }, + { + "epoch": 6.42, + "learning_rate": 1.5873036692959796e-05, + "loss": 0.1337, + "step": 20800 + }, + { + "epoch": 6.42, + "learning_rate": 1.5872631906594877e-05, + "loss": 0.1239, + "step": 20801 + }, + { + "epoch": 6.42, + "learning_rate": 1.5872227105541427e-05, + "loss": 0.1172, + "step": 20802 + }, + { + "epoch": 6.42, + "learning_rate": 1.587182228980047e-05, + "loss": 0.123, + "step": 20803 + }, + { + "epoch": 6.42, + "learning_rate": 1.5871417459373016e-05, + "loss": 0.1214, + "step": 20804 + }, + { + "epoch": 6.43, + "learning_rate": 1.5871012614260074e-05, + "loss": 0.1416, + "step": 20805 + }, + { + "epoch": 6.43, + "learning_rate": 1.587060775446266e-05, + "loss": 0.1288, + "step": 20806 + }, + { + "epoch": 6.43, + "learning_rate": 1.5870202879981785e-05, + "loss": 0.1152, + "step": 20807 + }, + { + "epoch": 6.43, + "learning_rate": 1.586979799081846e-05, + "loss": 0.1167, + "step": 20808 + }, + { + "epoch": 6.43, + "learning_rate": 1.58693930869737e-05, + "loss": 0.1466, + "step": 20809 + }, + { + "epoch": 6.43, + "learning_rate": 1.586898816844852e-05, + "loss": 0.1241, + "step": 20810 + }, + { + "epoch": 6.43, + "learning_rate": 1.5868583235243925e-05, + "loss": 0.117, + "step": 20811 + }, + { + "epoch": 6.43, + "learning_rate": 1.586817828736094e-05, + "loss": 0.1191, + "step": 20812 + }, + { + "epoch": 6.43, + "learning_rate": 1.5867773324800567e-05, + "loss": 0.121, + "step": 20813 + }, + { + "epoch": 6.43, + "learning_rate": 1.586736834756382e-05, + "loss": 0.1278, + "step": 20814 + }, + { + "epoch": 6.43, + "learning_rate": 1.586696335565172e-05, + "loss": 0.1203, + "step": 20815 + }, + { + "epoch": 6.43, + "learning_rate": 1.586655834906527e-05, + "loss": 0.1355, + "step": 20816 + }, + { + "epoch": 6.43, + "learning_rate": 1.586615332780549e-05, + "loss": 0.119, + "step": 20817 + }, + { + "epoch": 6.43, + "learning_rate": 1.5865748291873392e-05, + "loss": 0.1119, + "step": 20818 + }, + { + "epoch": 6.43, + "learning_rate": 1.5865343241269986e-05, + "loss": 0.1087, + "step": 20819 + }, + { + "epoch": 6.43, + "learning_rate": 1.5864938175996287e-05, + "loss": 0.1213, + "step": 20820 + }, + { + "epoch": 6.43, + "learning_rate": 1.586453309605331e-05, + "loss": 0.12, + "step": 20821 + }, + { + "epoch": 6.43, + "learning_rate": 1.586412800144206e-05, + "loss": 0.1048, + "step": 20822 + }, + { + "epoch": 6.43, + "learning_rate": 1.5863722892163563e-05, + "loss": 0.1181, + "step": 20823 + }, + { + "epoch": 6.43, + "learning_rate": 1.5863317768218823e-05, + "loss": 0.1112, + "step": 20824 + }, + { + "epoch": 6.43, + "learning_rate": 1.5862912629608853e-05, + "loss": 0.1124, + "step": 20825 + }, + { + "epoch": 6.43, + "learning_rate": 1.5862507476334675e-05, + "loss": 0.107, + "step": 20826 + }, + { + "epoch": 6.43, + "learning_rate": 1.586210230839729e-05, + "loss": 0.1134, + "step": 20827 + }, + { + "epoch": 6.43, + "learning_rate": 1.586169712579772e-05, + "loss": 0.1254, + "step": 20828 + }, + { + "epoch": 6.43, + "learning_rate": 1.586129192853698e-05, + "loss": 0.1214, + "step": 20829 + }, + { + "epoch": 6.43, + "learning_rate": 1.5860886716616078e-05, + "loss": 0.1151, + "step": 20830 + }, + { + "epoch": 6.43, + "learning_rate": 1.5860481490036027e-05, + "loss": 0.1272, + "step": 20831 + }, + { + "epoch": 6.43, + "learning_rate": 1.5860076248797848e-05, + "loss": 0.127, + "step": 20832 + }, + { + "epoch": 6.43, + "learning_rate": 1.5859670992902546e-05, + "loss": 0.1317, + "step": 20833 + }, + { + "epoch": 6.43, + "learning_rate": 1.5859265722351137e-05, + "loss": 0.1298, + "step": 20834 + }, + { + "epoch": 6.43, + "learning_rate": 1.5858860437144636e-05, + "loss": 0.1191, + "step": 20835 + }, + { + "epoch": 6.43, + "learning_rate": 1.5858455137284055e-05, + "loss": 0.123, + "step": 20836 + }, + { + "epoch": 6.43, + "learning_rate": 1.5858049822770417e-05, + "loss": 0.112, + "step": 20837 + }, + { + "epoch": 6.44, + "learning_rate": 1.5857644493604722e-05, + "loss": 0.119, + "step": 20838 + }, + { + "epoch": 6.44, + "learning_rate": 1.585723914978799e-05, + "loss": 0.1241, + "step": 20839 + }, + { + "epoch": 6.44, + "learning_rate": 1.5856833791321236e-05, + "loss": 0.1121, + "step": 20840 + }, + { + "epoch": 6.44, + "learning_rate": 1.585642841820547e-05, + "loss": 0.1203, + "step": 20841 + }, + { + "epoch": 6.44, + "learning_rate": 1.585602303044171e-05, + "loss": 0.0966, + "step": 20842 + }, + { + "epoch": 6.44, + "learning_rate": 1.5855617628030967e-05, + "loss": 0.1253, + "step": 20843 + }, + { + "epoch": 6.44, + "learning_rate": 1.585521221097426e-05, + "loss": 0.117, + "step": 20844 + }, + { + "epoch": 6.44, + "learning_rate": 1.5854806779272594e-05, + "loss": 0.1174, + "step": 20845 + }, + { + "epoch": 6.44, + "learning_rate": 1.5854401332926996e-05, + "loss": 0.1204, + "step": 20846 + }, + { + "epoch": 6.44, + "learning_rate": 1.5853995871938464e-05, + "loss": 0.1118, + "step": 20847 + }, + { + "epoch": 6.44, + "learning_rate": 1.5853590396308027e-05, + "loss": 0.124, + "step": 20848 + }, + { + "epoch": 6.44, + "learning_rate": 1.585318490603669e-05, + "loss": 0.129, + "step": 20849 + }, + { + "epoch": 6.44, + "learning_rate": 1.5852779401125467e-05, + "loss": 0.1299, + "step": 20850 + }, + { + "epoch": 6.44, + "learning_rate": 1.585237388157538e-05, + "loss": 0.1185, + "step": 20851 + }, + { + "epoch": 6.44, + "learning_rate": 1.585196834738744e-05, + "loss": 0.1195, + "step": 20852 + }, + { + "epoch": 6.44, + "learning_rate": 1.5851562798562654e-05, + "loss": 0.1162, + "step": 20853 + }, + { + "epoch": 6.44, + "learning_rate": 1.5851157235102045e-05, + "loss": 0.1185, + "step": 20854 + }, + { + "epoch": 6.44, + "learning_rate": 1.5850751657006625e-05, + "loss": 0.1091, + "step": 20855 + }, + { + "epoch": 6.44, + "learning_rate": 1.5850346064277406e-05, + "loss": 0.1177, + "step": 20856 + }, + { + "epoch": 6.44, + "learning_rate": 1.5849940456915408e-05, + "loss": 0.1218, + "step": 20857 + }, + { + "epoch": 6.44, + "learning_rate": 1.5849534834921637e-05, + "loss": 0.122, + "step": 20858 + }, + { + "epoch": 6.44, + "learning_rate": 1.5849129198297118e-05, + "loss": 0.1199, + "step": 20859 + }, + { + "epoch": 6.44, + "learning_rate": 1.584872354704286e-05, + "loss": 0.125, + "step": 20860 + }, + { + "epoch": 6.44, + "learning_rate": 1.5848317881159873e-05, + "loss": 0.1145, + "step": 20861 + }, + { + "epoch": 6.44, + "learning_rate": 1.5847912200649177e-05, + "loss": 0.1162, + "step": 20862 + }, + { + "epoch": 6.44, + "learning_rate": 1.584750650551179e-05, + "loss": 0.1263, + "step": 20863 + }, + { + "epoch": 6.44, + "learning_rate": 1.5847100795748717e-05, + "loss": 0.1295, + "step": 20864 + }, + { + "epoch": 6.44, + "learning_rate": 1.5846695071360986e-05, + "loss": 0.1293, + "step": 20865 + }, + { + "epoch": 6.44, + "learning_rate": 1.5846289332349597e-05, + "loss": 0.1279, + "step": 20866 + }, + { + "epoch": 6.44, + "learning_rate": 1.5845883578715577e-05, + "loss": 0.1232, + "step": 20867 + }, + { + "epoch": 6.44, + "learning_rate": 1.584547781045993e-05, + "loss": 0.1222, + "step": 20868 + }, + { + "epoch": 6.44, + "learning_rate": 1.5845072027583684e-05, + "loss": 0.1293, + "step": 20869 + }, + { + "epoch": 6.45, + "learning_rate": 1.584466623008784e-05, + "loss": 0.1299, + "step": 20870 + }, + { + "epoch": 6.45, + "learning_rate": 1.5844260417973426e-05, + "loss": 0.1225, + "step": 20871 + }, + { + "epoch": 6.45, + "learning_rate": 1.584385459124145e-05, + "loss": 0.1189, + "step": 20872 + }, + { + "epoch": 6.45, + "learning_rate": 1.5843448749892925e-05, + "loss": 0.1159, + "step": 20873 + }, + { + "epoch": 6.45, + "learning_rate": 1.5843042893928868e-05, + "loss": 0.1275, + "step": 20874 + }, + { + "epoch": 6.45, + "learning_rate": 1.5842637023350297e-05, + "loss": 0.1275, + "step": 20875 + }, + { + "epoch": 6.45, + "learning_rate": 1.5842231138158223e-05, + "loss": 0.1178, + "step": 20876 + }, + { + "epoch": 6.45, + "learning_rate": 1.584182523835367e-05, + "loss": 0.125, + "step": 20877 + }, + { + "epoch": 6.45, + "learning_rate": 1.584141932393764e-05, + "loss": 0.125, + "step": 20878 + }, + { + "epoch": 6.45, + "learning_rate": 1.5841013394911156e-05, + "loss": 0.1329, + "step": 20879 + }, + { + "epoch": 6.45, + "learning_rate": 1.5840607451275235e-05, + "loss": 0.1143, + "step": 20880 + }, + { + "epoch": 6.45, + "learning_rate": 1.5840201493030886e-05, + "loss": 0.1168, + "step": 20881 + }, + { + "epoch": 6.45, + "learning_rate": 1.5839795520179128e-05, + "loss": 0.1244, + "step": 20882 + }, + { + "epoch": 6.45, + "learning_rate": 1.583938953272098e-05, + "loss": 0.1212, + "step": 20883 + }, + { + "epoch": 6.45, + "learning_rate": 1.583898353065745e-05, + "loss": 0.1321, + "step": 20884 + }, + { + "epoch": 6.45, + "learning_rate": 1.583857751398956e-05, + "loss": 0.117, + "step": 20885 + }, + { + "epoch": 6.45, + "learning_rate": 1.583817148271832e-05, + "loss": 0.1301, + "step": 20886 + }, + { + "epoch": 6.45, + "learning_rate": 1.583776543684475e-05, + "loss": 0.1219, + "step": 20887 + }, + { + "epoch": 6.45, + "learning_rate": 1.5837359376369864e-05, + "loss": 0.113, + "step": 20888 + }, + { + "epoch": 6.45, + "learning_rate": 1.5836953301294677e-05, + "loss": 0.1329, + "step": 20889 + }, + { + "epoch": 6.45, + "learning_rate": 1.5836547211620206e-05, + "loss": 0.135, + "step": 20890 + }, + { + "epoch": 6.45, + "learning_rate": 1.583614110734746e-05, + "loss": 0.133, + "step": 20891 + }, + { + "epoch": 6.45, + "learning_rate": 1.5835734988477473e-05, + "loss": 0.1306, + "step": 20892 + }, + { + "epoch": 6.45, + "learning_rate": 1.583532885501124e-05, + "loss": 0.1243, + "step": 20893 + }, + { + "epoch": 6.45, + "learning_rate": 1.5834922706949785e-05, + "loss": 0.1176, + "step": 20894 + }, + { + "epoch": 6.45, + "learning_rate": 1.583451654429412e-05, + "loss": 0.1117, + "step": 20895 + }, + { + "epoch": 6.45, + "learning_rate": 1.5834110367045274e-05, + "loss": 0.1172, + "step": 20896 + }, + { + "epoch": 6.45, + "learning_rate": 1.5833704175204254e-05, + "loss": 0.1197, + "step": 20897 + }, + { + "epoch": 6.45, + "learning_rate": 1.583329796877207e-05, + "loss": 0.1237, + "step": 20898 + }, + { + "epoch": 6.45, + "learning_rate": 1.5832891747749746e-05, + "loss": 0.1077, + "step": 20899 + }, + { + "epoch": 6.45, + "learning_rate": 1.5832485512138295e-05, + "loss": 0.109, + "step": 20900 + }, + { + "epoch": 6.45, + "learning_rate": 1.5832079261938735e-05, + "loss": 0.1274, + "step": 20901 + }, + { + "epoch": 6.46, + "learning_rate": 1.5831672997152085e-05, + "loss": 0.1266, + "step": 20902 + }, + { + "epoch": 6.46, + "learning_rate": 1.583126671777935e-05, + "loss": 0.1301, + "step": 20903 + }, + { + "epoch": 6.46, + "learning_rate": 1.5830860423821556e-05, + "loss": 0.1085, + "step": 20904 + }, + { + "epoch": 6.46, + "learning_rate": 1.583045411527972e-05, + "loss": 0.1229, + "step": 20905 + }, + { + "epoch": 6.46, + "learning_rate": 1.583004779215485e-05, + "loss": 0.1237, + "step": 20906 + }, + { + "epoch": 6.46, + "learning_rate": 1.582964145444797e-05, + "loss": 0.1253, + "step": 20907 + }, + { + "epoch": 6.46, + "learning_rate": 1.582923510216009e-05, + "loss": 0.1131, + "step": 20908 + }, + { + "epoch": 6.46, + "learning_rate": 1.5828828735292235e-05, + "loss": 0.1196, + "step": 20909 + }, + { + "epoch": 6.46, + "learning_rate": 1.5828422353845414e-05, + "loss": 0.1083, + "step": 20910 + }, + { + "epoch": 6.46, + "learning_rate": 1.5828015957820645e-05, + "loss": 0.1287, + "step": 20911 + }, + { + "epoch": 6.46, + "learning_rate": 1.5827609547218946e-05, + "loss": 0.1269, + "step": 20912 + }, + { + "epoch": 6.46, + "learning_rate": 1.5827203122041332e-05, + "loss": 0.1233, + "step": 20913 + }, + { + "epoch": 6.46, + "learning_rate": 1.582679668228882e-05, + "loss": 0.1205, + "step": 20914 + }, + { + "epoch": 6.46, + "learning_rate": 1.582639022796243e-05, + "loss": 0.1185, + "step": 20915 + }, + { + "epoch": 6.46, + "learning_rate": 1.582598375906317e-05, + "loss": 0.108, + "step": 20916 + }, + { + "epoch": 6.46, + "learning_rate": 1.5825577275592066e-05, + "loss": 0.1179, + "step": 20917 + }, + { + "epoch": 6.46, + "learning_rate": 1.5825170777550127e-05, + "loss": 0.1248, + "step": 20918 + }, + { + "epoch": 6.46, + "learning_rate": 1.5824764264938377e-05, + "loss": 0.126, + "step": 20919 + }, + { + "epoch": 6.46, + "learning_rate": 1.582435773775783e-05, + "loss": 0.1286, + "step": 20920 + }, + { + "epoch": 6.46, + "learning_rate": 1.5823951196009498e-05, + "loss": 0.1315, + "step": 20921 + }, + { + "epoch": 6.46, + "learning_rate": 1.5823544639694405e-05, + "loss": 0.1146, + "step": 20922 + }, + { + "epoch": 6.46, + "learning_rate": 1.582313806881356e-05, + "loss": 0.1285, + "step": 20923 + }, + { + "epoch": 6.46, + "learning_rate": 1.582273148336799e-05, + "loss": 0.1177, + "step": 20924 + }, + { + "epoch": 6.46, + "learning_rate": 1.5822324883358706e-05, + "loss": 0.1292, + "step": 20925 + }, + { + "epoch": 6.46, + "learning_rate": 1.5821918268786723e-05, + "loss": 0.1219, + "step": 20926 + }, + { + "epoch": 6.46, + "learning_rate": 1.582151163965306e-05, + "loss": 0.1139, + "step": 20927 + }, + { + "epoch": 6.46, + "learning_rate": 1.582110499595874e-05, + "loss": 0.1222, + "step": 20928 + }, + { + "epoch": 6.46, + "learning_rate": 1.582069833770477e-05, + "loss": 0.1181, + "step": 20929 + }, + { + "epoch": 6.46, + "learning_rate": 1.582029166489217e-05, + "loss": 0.1113, + "step": 20930 + }, + { + "epoch": 6.46, + "learning_rate": 1.5819884977521965e-05, + "loss": 0.1177, + "step": 20931 + }, + { + "epoch": 6.46, + "learning_rate": 1.5819478275595163e-05, + "loss": 0.1311, + "step": 20932 + }, + { + "epoch": 6.46, + "learning_rate": 1.5819071559112784e-05, + "loss": 0.1441, + "step": 20933 + }, + { + "epoch": 6.46, + "learning_rate": 1.5818664828075845e-05, + "loss": 0.1334, + "step": 20934 + }, + { + "epoch": 6.47, + "learning_rate": 1.5818258082485365e-05, + "loss": 0.1168, + "step": 20935 + }, + { + "epoch": 6.47, + "learning_rate": 1.581785132234236e-05, + "loss": 0.1309, + "step": 20936 + }, + { + "epoch": 6.47, + "learning_rate": 1.581744454764785e-05, + "loss": 0.1178, + "step": 20937 + }, + { + "epoch": 6.47, + "learning_rate": 1.5817037758402847e-05, + "loss": 0.1263, + "step": 20938 + }, + { + "epoch": 6.47, + "learning_rate": 1.5816630954608374e-05, + "loss": 0.1279, + "step": 20939 + }, + { + "epoch": 6.47, + "learning_rate": 1.5816224136265445e-05, + "loss": 0.1213, + "step": 20940 + }, + { + "epoch": 6.47, + "learning_rate": 1.5815817303375077e-05, + "loss": 0.1142, + "step": 20941 + }, + { + "epoch": 6.47, + "learning_rate": 1.581541045593829e-05, + "loss": 0.1094, + "step": 20942 + }, + { + "epoch": 6.47, + "learning_rate": 1.5815003593956103e-05, + "loss": 0.1172, + "step": 20943 + }, + { + "epoch": 6.47, + "learning_rate": 1.5814596717429532e-05, + "loss": 0.1277, + "step": 20944 + }, + { + "epoch": 6.47, + "learning_rate": 1.5814189826359592e-05, + "loss": 0.1244, + "step": 20945 + }, + { + "epoch": 6.47, + "learning_rate": 1.58137829207473e-05, + "loss": 0.1297, + "step": 20946 + }, + { + "epoch": 6.47, + "learning_rate": 1.581337600059368e-05, + "loss": 0.1215, + "step": 20947 + }, + { + "epoch": 6.47, + "learning_rate": 1.5812969065899747e-05, + "loss": 0.13, + "step": 20948 + }, + { + "epoch": 6.47, + "learning_rate": 1.5812562116666518e-05, + "loss": 0.1155, + "step": 20949 + }, + { + "epoch": 6.47, + "learning_rate": 1.5812155152895008e-05, + "loss": 0.1155, + "step": 20950 + }, + { + "epoch": 6.47, + "learning_rate": 1.5811748174586238e-05, + "loss": 0.12, + "step": 20951 + }, + { + "epoch": 6.47, + "learning_rate": 1.581134118174123e-05, + "loss": 0.1134, + "step": 20952 + }, + { + "epoch": 6.47, + "learning_rate": 1.5810934174360998e-05, + "loss": 0.1298, + "step": 20953 + }, + { + "epoch": 6.47, + "learning_rate": 1.5810527152446555e-05, + "loss": 0.1277, + "step": 20954 + }, + { + "epoch": 6.47, + "learning_rate": 1.5810120115998927e-05, + "loss": 0.1233, + "step": 20955 + }, + { + "epoch": 6.47, + "learning_rate": 1.5809713065019128e-05, + "loss": 0.1307, + "step": 20956 + }, + { + "epoch": 6.47, + "learning_rate": 1.5809305999508176e-05, + "loss": 0.1188, + "step": 20957 + }, + { + "epoch": 6.47, + "learning_rate": 1.580889891946709e-05, + "loss": 0.1214, + "step": 20958 + }, + { + "epoch": 6.47, + "learning_rate": 1.580849182489689e-05, + "loss": 0.1135, + "step": 20959 + }, + { + "epoch": 6.47, + "learning_rate": 1.580808471579859e-05, + "loss": 0.1251, + "step": 20960 + }, + { + "epoch": 6.47, + "learning_rate": 1.5807677592173213e-05, + "loss": 0.1139, + "step": 20961 + }, + { + "epoch": 6.47, + "learning_rate": 1.5807270454021777e-05, + "loss": 0.0995, + "step": 20962 + }, + { + "epoch": 6.47, + "learning_rate": 1.5806863301345298e-05, + "loss": 0.1195, + "step": 20963 + }, + { + "epoch": 6.47, + "learning_rate": 1.5806456134144792e-05, + "loss": 0.1338, + "step": 20964 + }, + { + "epoch": 6.47, + "learning_rate": 1.5806048952421283e-05, + "loss": 0.1243, + "step": 20965 + }, + { + "epoch": 6.47, + "learning_rate": 1.5805641756175784e-05, + "loss": 0.1202, + "step": 20966 + }, + { + "epoch": 6.48, + "learning_rate": 1.5805234545409314e-05, + "loss": 0.1223, + "step": 20967 + }, + { + "epoch": 6.48, + "learning_rate": 1.58048273201229e-05, + "loss": 0.1163, + "step": 20968 + }, + { + "epoch": 6.48, + "learning_rate": 1.580442008031755e-05, + "loss": 0.1265, + "step": 20969 + }, + { + "epoch": 6.48, + "learning_rate": 1.5804012825994285e-05, + "loss": 0.1268, + "step": 20970 + }, + { + "epoch": 6.48, + "learning_rate": 1.5803605557154128e-05, + "loss": 0.1254, + "step": 20971 + }, + { + "epoch": 6.48, + "learning_rate": 1.5803198273798094e-05, + "loss": 0.1181, + "step": 20972 + }, + { + "epoch": 6.48, + "learning_rate": 1.5802790975927208e-05, + "loss": 0.1022, + "step": 20973 + }, + { + "epoch": 6.48, + "learning_rate": 1.5802383663542477e-05, + "loss": 0.1324, + "step": 20974 + }, + { + "epoch": 6.48, + "learning_rate": 1.5801976336644927e-05, + "loss": 0.1192, + "step": 20975 + }, + { + "epoch": 6.48, + "learning_rate": 1.5801568995235575e-05, + "loss": 0.1232, + "step": 20976 + }, + { + "epoch": 6.48, + "learning_rate": 1.5801161639315444e-05, + "loss": 0.1134, + "step": 20977 + }, + { + "epoch": 6.48, + "learning_rate": 1.580075426888555e-05, + "loss": 0.1314, + "step": 20978 + }, + { + "epoch": 6.48, + "learning_rate": 1.580034688394691e-05, + "loss": 0.1145, + "step": 20979 + }, + { + "epoch": 6.48, + "learning_rate": 1.5799939484500543e-05, + "loss": 0.124, + "step": 20980 + }, + { + "epoch": 6.48, + "learning_rate": 1.579953207054747e-05, + "loss": 0.117, + "step": 20981 + }, + { + "epoch": 6.48, + "learning_rate": 1.5799124642088713e-05, + "loss": 0.1212, + "step": 20982 + }, + { + "epoch": 6.48, + "learning_rate": 1.5798717199125284e-05, + "loss": 0.1321, + "step": 20983 + }, + { + "epoch": 6.48, + "learning_rate": 1.5798309741658205e-05, + "loss": 0.135, + "step": 20984 + }, + { + "epoch": 6.48, + "learning_rate": 1.57979022696885e-05, + "loss": 0.1116, + "step": 20985 + }, + { + "epoch": 6.48, + "learning_rate": 1.579749478321718e-05, + "loss": 0.1348, + "step": 20986 + }, + { + "epoch": 6.48, + "learning_rate": 1.5797087282245272e-05, + "loss": 0.1156, + "step": 20987 + }, + { + "epoch": 6.48, + "learning_rate": 1.5796679766773787e-05, + "loss": 0.1327, + "step": 20988 + }, + { + "epoch": 6.48, + "learning_rate": 1.579627223680375e-05, + "loss": 0.1253, + "step": 20989 + }, + { + "epoch": 6.48, + "learning_rate": 1.5795864692336183e-05, + "loss": 0.1139, + "step": 20990 + }, + { + "epoch": 6.48, + "learning_rate": 1.5795457133372097e-05, + "loss": 0.1173, + "step": 20991 + }, + { + "epoch": 6.48, + "learning_rate": 1.5795049559912516e-05, + "loss": 0.1126, + "step": 20992 + }, + { + "epoch": 6.48, + "learning_rate": 1.579464197195846e-05, + "loss": 0.125, + "step": 20993 + }, + { + "epoch": 6.48, + "learning_rate": 1.579423436951095e-05, + "loss": 0.1191, + "step": 20994 + }, + { + "epoch": 6.48, + "learning_rate": 1.5793826752571e-05, + "loss": 0.1205, + "step": 20995 + }, + { + "epoch": 6.48, + "learning_rate": 1.579341912113963e-05, + "loss": 0.1337, + "step": 20996 + }, + { + "epoch": 6.48, + "learning_rate": 1.5793011475217867e-05, + "loss": 0.1092, + "step": 20997 + }, + { + "epoch": 6.48, + "learning_rate": 1.579260381480672e-05, + "loss": 0.1289, + "step": 20998 + }, + { + "epoch": 6.48, + "learning_rate": 1.579219613990722e-05, + "loss": 0.1255, + "step": 20999 + }, + { + "epoch": 6.49, + "learning_rate": 1.579178845052038e-05, + "loss": 0.1227, + "step": 21000 + }, + { + "epoch": 6.49, + "learning_rate": 1.579138074664722e-05, + "loss": 0.1149, + "step": 21001 + }, + { + "epoch": 6.49, + "learning_rate": 1.579097302828876e-05, + "loss": 0.1203, + "step": 21002 + }, + { + "epoch": 6.49, + "learning_rate": 1.5790565295446022e-05, + "loss": 0.1112, + "step": 21003 + }, + { + "epoch": 6.49, + "learning_rate": 1.5790157548120023e-05, + "loss": 0.1283, + "step": 21004 + }, + { + "epoch": 6.49, + "learning_rate": 1.578974978631178e-05, + "loss": 0.1268, + "step": 21005 + }, + { + "epoch": 6.49, + "learning_rate": 1.578934201002232e-05, + "loss": 0.1195, + "step": 21006 + }, + { + "epoch": 6.49, + "learning_rate": 1.5788934219252663e-05, + "loss": 0.127, + "step": 21007 + }, + { + "epoch": 6.49, + "learning_rate": 1.5788526414003824e-05, + "loss": 0.1263, + "step": 21008 + }, + { + "epoch": 6.49, + "learning_rate": 1.578811859427682e-05, + "loss": 0.1235, + "step": 21009 + }, + { + "epoch": 6.49, + "learning_rate": 1.578771076007268e-05, + "loss": 0.1208, + "step": 21010 + }, + { + "epoch": 6.49, + "learning_rate": 1.578730291139242e-05, + "loss": 0.1365, + "step": 21011 + }, + { + "epoch": 6.49, + "learning_rate": 1.578689504823706e-05, + "loss": 0.1184, + "step": 21012 + }, + { + "epoch": 6.49, + "learning_rate": 1.5786487170607618e-05, + "loss": 0.1241, + "step": 21013 + }, + { + "epoch": 6.49, + "learning_rate": 1.5786079278505114e-05, + "loss": 0.1203, + "step": 21014 + }, + { + "epoch": 6.49, + "learning_rate": 1.5785671371930576e-05, + "loss": 0.1221, + "step": 21015 + }, + { + "epoch": 6.49, + "learning_rate": 1.5785263450885014e-05, + "loss": 0.1072, + "step": 21016 + }, + { + "epoch": 6.49, + "learning_rate": 1.5784855515369457e-05, + "loss": 0.1138, + "step": 21017 + }, + { + "epoch": 6.49, + "learning_rate": 1.578444756538492e-05, + "loss": 0.1229, + "step": 21018 + }, + { + "epoch": 6.49, + "learning_rate": 1.5784039600932424e-05, + "loss": 0.1257, + "step": 21019 + }, + { + "epoch": 6.49, + "learning_rate": 1.5783631622012987e-05, + "loss": 0.1211, + "step": 21020 + }, + { + "epoch": 6.49, + "learning_rate": 1.5783223628627638e-05, + "loss": 0.1122, + "step": 21021 + }, + { + "epoch": 6.49, + "learning_rate": 1.578281562077739e-05, + "loss": 0.1207, + "step": 21022 + }, + { + "epoch": 6.49, + "learning_rate": 1.5782407598463264e-05, + "loss": 0.1229, + "step": 21023 + }, + { + "epoch": 6.49, + "learning_rate": 1.578199956168628e-05, + "loss": 0.1194, + "step": 21024 + }, + { + "epoch": 6.49, + "learning_rate": 1.5781591510447465e-05, + "loss": 0.1318, + "step": 21025 + }, + { + "epoch": 6.49, + "learning_rate": 1.5781183444747833e-05, + "loss": 0.1125, + "step": 21026 + }, + { + "epoch": 6.49, + "learning_rate": 1.578077536458841e-05, + "loss": 0.1197, + "step": 21027 + }, + { + "epoch": 6.49, + "learning_rate": 1.578036726997021e-05, + "loss": 0.1346, + "step": 21028 + }, + { + "epoch": 6.49, + "learning_rate": 1.5779959160894257e-05, + "loss": 0.12, + "step": 21029 + }, + { + "epoch": 6.49, + "learning_rate": 1.5779551037361573e-05, + "loss": 0.1228, + "step": 21030 + }, + { + "epoch": 6.49, + "learning_rate": 1.5779142899373177e-05, + "loss": 0.1295, + "step": 21031 + }, + { + "epoch": 6.5, + "learning_rate": 1.577873474693009e-05, + "loss": 0.1305, + "step": 21032 + }, + { + "epoch": 6.5, + "learning_rate": 1.5778326580033335e-05, + "loss": 0.1234, + "step": 21033 + }, + { + "epoch": 6.5, + "learning_rate": 1.577791839868393e-05, + "loss": 0.1178, + "step": 21034 + }, + { + "epoch": 6.5, + "learning_rate": 1.57775102028829e-05, + "loss": 0.131, + "step": 21035 + }, + { + "epoch": 6.5, + "learning_rate": 1.577710199263126e-05, + "loss": 0.1243, + "step": 21036 + }, + { + "epoch": 6.5, + "learning_rate": 1.5776693767930036e-05, + "loss": 0.1064, + "step": 21037 + }, + { + "epoch": 6.5, + "learning_rate": 1.5776285528780245e-05, + "loss": 0.1233, + "step": 21038 + }, + { + "epoch": 6.5, + "learning_rate": 1.5775877275182915e-05, + "loss": 0.123, + "step": 21039 + }, + { + "epoch": 6.5, + "learning_rate": 1.5775469007139058e-05, + "loss": 0.1297, + "step": 21040 + }, + { + "epoch": 6.5, + "learning_rate": 1.57750607246497e-05, + "loss": 0.1294, + "step": 21041 + }, + { + "epoch": 6.5, + "learning_rate": 1.5774652427715865e-05, + "loss": 0.1238, + "step": 21042 + }, + { + "epoch": 6.5, + "learning_rate": 1.5774244116338565e-05, + "loss": 0.1228, + "step": 21043 + }, + { + "epoch": 6.5, + "learning_rate": 1.5773835790518838e-05, + "loss": 0.1066, + "step": 21044 + }, + { + "epoch": 6.5, + "learning_rate": 1.5773427450257684e-05, + "loss": 0.1193, + "step": 21045 + }, + { + "epoch": 6.5, + "learning_rate": 1.577301909555614e-05, + "loss": 0.1248, + "step": 21046 + }, + { + "epoch": 6.5, + "learning_rate": 1.577261072641522e-05, + "loss": 0.1193, + "step": 21047 + }, + { + "epoch": 6.5, + "learning_rate": 1.577220234283595e-05, + "loss": 0.1169, + "step": 21048 + }, + { + "epoch": 6.5, + "learning_rate": 1.5771793944819348e-05, + "loss": 0.1236, + "step": 21049 + }, + { + "epoch": 6.5, + "learning_rate": 1.5771385532366437e-05, + "loss": 0.1233, + "step": 21050 + }, + { + "epoch": 6.5, + "learning_rate": 1.5770977105478237e-05, + "loss": 0.1279, + "step": 21051 + }, + { + "epoch": 6.5, + "learning_rate": 1.5770568664155773e-05, + "loss": 0.1258, + "step": 21052 + }, + { + "epoch": 6.5, + "learning_rate": 1.5770160208400064e-05, + "loss": 0.1123, + "step": 21053 + }, + { + "epoch": 6.5, + "learning_rate": 1.576975173821213e-05, + "loss": 0.1247, + "step": 21054 + }, + { + "epoch": 6.5, + "learning_rate": 1.5769343253592993e-05, + "loss": 0.126, + "step": 21055 + }, + { + "epoch": 6.5, + "learning_rate": 1.5768934754543682e-05, + "loss": 0.1199, + "step": 21056 + }, + { + "epoch": 6.5, + "learning_rate": 1.576852624106521e-05, + "loss": 0.1321, + "step": 21057 + }, + { + "epoch": 6.5, + "learning_rate": 1.57681177131586e-05, + "loss": 0.1191, + "step": 21058 + }, + { + "epoch": 6.5, + "learning_rate": 1.5767709170824878e-05, + "loss": 0.1171, + "step": 21059 + }, + { + "epoch": 6.5, + "learning_rate": 1.576730061406506e-05, + "loss": 0.1285, + "step": 21060 + }, + { + "epoch": 6.5, + "learning_rate": 1.5766892042880173e-05, + "loss": 0.1375, + "step": 21061 + }, + { + "epoch": 6.5, + "learning_rate": 1.5766483457271237e-05, + "loss": 0.1229, + "step": 21062 + }, + { + "epoch": 6.5, + "learning_rate": 1.5766074857239274e-05, + "loss": 0.119, + "step": 21063 + }, + { + "epoch": 6.51, + "learning_rate": 1.576566624278531e-05, + "loss": 0.1235, + "step": 21064 + }, + { + "epoch": 6.51, + "learning_rate": 1.576525761391036e-05, + "loss": 0.1216, + "step": 21065 + }, + { + "epoch": 6.51, + "learning_rate": 1.576484897061545e-05, + "loss": 0.1196, + "step": 21066 + }, + { + "epoch": 6.51, + "learning_rate": 1.57644403129016e-05, + "loss": 0.1092, + "step": 21067 + }, + { + "epoch": 6.51, + "learning_rate": 1.576403164076983e-05, + "loss": 0.1284, + "step": 21068 + }, + { + "epoch": 6.51, + "learning_rate": 1.5763622954221175e-05, + "loss": 0.1244, + "step": 21069 + }, + { + "epoch": 6.51, + "learning_rate": 1.576321425325664e-05, + "loss": 0.133, + "step": 21070 + }, + { + "epoch": 6.51, + "learning_rate": 1.5762805537877256e-05, + "loss": 0.1142, + "step": 21071 + }, + { + "epoch": 6.51, + "learning_rate": 1.5762396808084047e-05, + "loss": 0.124, + "step": 21072 + }, + { + "epoch": 6.51, + "learning_rate": 1.5761988063878034e-05, + "loss": 0.1201, + "step": 21073 + }, + { + "epoch": 6.51, + "learning_rate": 1.5761579305260233e-05, + "loss": 0.1311, + "step": 21074 + }, + { + "epoch": 6.51, + "learning_rate": 1.5761170532231674e-05, + "loss": 0.132, + "step": 21075 + }, + { + "epoch": 6.51, + "learning_rate": 1.5760761744793377e-05, + "loss": 0.1328, + "step": 21076 + }, + { + "epoch": 6.51, + "learning_rate": 1.5760352942946365e-05, + "loss": 0.1119, + "step": 21077 + }, + { + "epoch": 6.51, + "learning_rate": 1.5759944126691658e-05, + "loss": 0.1294, + "step": 21078 + }, + { + "epoch": 6.51, + "learning_rate": 1.5759535296030276e-05, + "loss": 0.1346, + "step": 21079 + }, + { + "epoch": 6.51, + "learning_rate": 1.5759126450963252e-05, + "loss": 0.1218, + "step": 21080 + }, + { + "epoch": 6.51, + "learning_rate": 1.57587175914916e-05, + "loss": 0.1341, + "step": 21081 + }, + { + "epoch": 6.51, + "learning_rate": 1.5758308717616345e-05, + "loss": 0.1284, + "step": 21082 + }, + { + "epoch": 6.51, + "learning_rate": 1.575789982933851e-05, + "loss": 0.1259, + "step": 21083 + }, + { + "epoch": 6.51, + "learning_rate": 1.5757490926659122e-05, + "loss": 0.1199, + "step": 21084 + }, + { + "epoch": 6.51, + "learning_rate": 1.575708200957919e-05, + "loss": 0.12, + "step": 21085 + }, + { + "epoch": 6.51, + "learning_rate": 1.5756673078099752e-05, + "loss": 0.1174, + "step": 21086 + }, + { + "epoch": 6.51, + "learning_rate": 1.575626413222182e-05, + "loss": 0.119, + "step": 21087 + }, + { + "epoch": 6.51, + "learning_rate": 1.5755855171946428e-05, + "loss": 0.1246, + "step": 21088 + }, + { + "epoch": 6.51, + "learning_rate": 1.5755446197274587e-05, + "loss": 0.1304, + "step": 21089 + }, + { + "epoch": 6.51, + "learning_rate": 1.5755037208207328e-05, + "loss": 0.1159, + "step": 21090 + }, + { + "epoch": 6.51, + "learning_rate": 1.575462820474567e-05, + "loss": 0.1216, + "step": 21091 + }, + { + "epoch": 6.51, + "learning_rate": 1.575421918689064e-05, + "loss": 0.1331, + "step": 21092 + }, + { + "epoch": 6.51, + "learning_rate": 1.5753810154643255e-05, + "loss": 0.1168, + "step": 21093 + }, + { + "epoch": 6.51, + "learning_rate": 1.575340110800454e-05, + "loss": 0.1339, + "step": 21094 + }, + { + "epoch": 6.51, + "learning_rate": 1.5752992046975524e-05, + "loss": 0.1235, + "step": 21095 + }, + { + "epoch": 6.51, + "learning_rate": 1.5752582971557226e-05, + "loss": 0.125, + "step": 21096 + }, + { + "epoch": 6.52, + "learning_rate": 1.5752173881750664e-05, + "loss": 0.1266, + "step": 21097 + }, + { + "epoch": 6.52, + "learning_rate": 1.575176477755687e-05, + "loss": 0.1354, + "step": 21098 + }, + { + "epoch": 6.52, + "learning_rate": 1.575135565897686e-05, + "loss": 0.1216, + "step": 21099 + }, + { + "epoch": 6.52, + "learning_rate": 1.5750946526011663e-05, + "loss": 0.1323, + "step": 21100 + }, + { + "epoch": 6.52, + "learning_rate": 1.5750537378662297e-05, + "loss": 0.1277, + "step": 21101 + }, + { + "epoch": 6.52, + "learning_rate": 1.5750128216929793e-05, + "loss": 0.1254, + "step": 21102 + }, + { + "epoch": 6.52, + "learning_rate": 1.5749719040815165e-05, + "loss": 0.1185, + "step": 21103 + }, + { + "epoch": 6.52, + "learning_rate": 1.574930985031944e-05, + "loss": 0.1294, + "step": 21104 + }, + { + "epoch": 6.52, + "learning_rate": 1.5748900645443647e-05, + "loss": 0.1207, + "step": 21105 + }, + { + "epoch": 6.52, + "learning_rate": 1.5748491426188804e-05, + "loss": 0.1158, + "step": 21106 + }, + { + "epoch": 6.52, + "learning_rate": 1.5748082192555935e-05, + "loss": 0.1284, + "step": 21107 + }, + { + "epoch": 6.52, + "learning_rate": 1.5747672944546065e-05, + "loss": 0.1108, + "step": 21108 + }, + { + "epoch": 6.52, + "learning_rate": 1.5747263682160213e-05, + "loss": 0.117, + "step": 21109 + }, + { + "epoch": 6.52, + "learning_rate": 1.574685440539941e-05, + "loss": 0.1012, + "step": 21110 + }, + { + "epoch": 6.52, + "learning_rate": 1.5746445114264672e-05, + "loss": 0.1201, + "step": 21111 + }, + { + "epoch": 6.52, + "learning_rate": 1.5746035808757033e-05, + "loss": 0.1122, + "step": 21112 + }, + { + "epoch": 6.52, + "learning_rate": 1.5745626488877505e-05, + "loss": 0.1275, + "step": 21113 + }, + { + "epoch": 6.52, + "learning_rate": 1.5745217154627118e-05, + "loss": 0.1249, + "step": 21114 + }, + { + "epoch": 6.52, + "learning_rate": 1.5744807806006898e-05, + "loss": 0.1346, + "step": 21115 + }, + { + "epoch": 6.52, + "learning_rate": 1.5744398443017865e-05, + "loss": 0.1275, + "step": 21116 + }, + { + "epoch": 6.52, + "learning_rate": 1.574398906566104e-05, + "loss": 0.1337, + "step": 21117 + }, + { + "epoch": 6.52, + "learning_rate": 1.5743579673937453e-05, + "loss": 0.1213, + "step": 21118 + }, + { + "epoch": 6.52, + "learning_rate": 1.5743170267848125e-05, + "loss": 0.1229, + "step": 21119 + }, + { + "epoch": 6.52, + "learning_rate": 1.5742760847394083e-05, + "loss": 0.1225, + "step": 21120 + }, + { + "epoch": 6.52, + "learning_rate": 1.5742351412576348e-05, + "loss": 0.1224, + "step": 21121 + }, + { + "epoch": 6.52, + "learning_rate": 1.5741941963395943e-05, + "loss": 0.1289, + "step": 21122 + }, + { + "epoch": 6.52, + "learning_rate": 1.5741532499853894e-05, + "loss": 0.1369, + "step": 21123 + }, + { + "epoch": 6.52, + "learning_rate": 1.574112302195123e-05, + "loss": 0.1284, + "step": 21124 + }, + { + "epoch": 6.52, + "learning_rate": 1.5740713529688966e-05, + "loss": 0.1465, + "step": 21125 + }, + { + "epoch": 6.52, + "learning_rate": 1.574030402306813e-05, + "loss": 0.1176, + "step": 21126 + }, + { + "epoch": 6.52, + "learning_rate": 1.573989450208975e-05, + "loss": 0.1241, + "step": 21127 + }, + { + "epoch": 6.52, + "learning_rate": 1.573948496675484e-05, + "loss": 0.124, + "step": 21128 + }, + { + "epoch": 6.53, + "learning_rate": 1.5739075417064435e-05, + "loss": 0.1321, + "step": 21129 + }, + { + "epoch": 6.53, + "learning_rate": 1.5738665853019556e-05, + "loss": 0.1268, + "step": 21130 + }, + { + "epoch": 6.53, + "learning_rate": 1.5738256274621232e-05, + "loss": 0.1144, + "step": 21131 + }, + { + "epoch": 6.53, + "learning_rate": 1.5737846681870473e-05, + "loss": 0.1162, + "step": 21132 + }, + { + "epoch": 6.53, + "learning_rate": 1.5737437074768317e-05, + "loss": 0.1228, + "step": 21133 + }, + { + "epoch": 6.53, + "learning_rate": 1.5737027453315786e-05, + "loss": 0.1285, + "step": 21134 + }, + { + "epoch": 6.53, + "learning_rate": 1.5736617817513904e-05, + "loss": 0.1203, + "step": 21135 + }, + { + "epoch": 6.53, + "learning_rate": 1.5736208167363694e-05, + "loss": 0.116, + "step": 21136 + }, + { + "epoch": 6.53, + "learning_rate": 1.573579850286618e-05, + "loss": 0.1288, + "step": 21137 + }, + { + "epoch": 6.53, + "learning_rate": 1.5735388824022385e-05, + "loss": 0.1201, + "step": 21138 + }, + { + "epoch": 6.53, + "learning_rate": 1.573497913083334e-05, + "loss": 0.1175, + "step": 21139 + }, + { + "epoch": 6.53, + "learning_rate": 1.5734569423300065e-05, + "loss": 0.1259, + "step": 21140 + }, + { + "epoch": 6.53, + "learning_rate": 1.5734159701423586e-05, + "loss": 0.1138, + "step": 21141 + }, + { + "epoch": 6.53, + "learning_rate": 1.5733749965204928e-05, + "loss": 0.1218, + "step": 21142 + }, + { + "epoch": 6.53, + "learning_rate": 1.5733340214645115e-05, + "loss": 0.1239, + "step": 21143 + }, + { + "epoch": 6.53, + "learning_rate": 1.5732930449745173e-05, + "loss": 0.1152, + "step": 21144 + }, + { + "epoch": 6.53, + "learning_rate": 1.5732520670506128e-05, + "loss": 0.1102, + "step": 21145 + }, + { + "epoch": 6.53, + "learning_rate": 1.5732110876929e-05, + "loss": 0.1172, + "step": 21146 + }, + { + "epoch": 6.53, + "learning_rate": 1.5731701069014818e-05, + "loss": 0.1202, + "step": 21147 + }, + { + "epoch": 6.53, + "learning_rate": 1.573129124676461e-05, + "loss": 0.1356, + "step": 21148 + }, + { + "epoch": 6.53, + "learning_rate": 1.573088141017939e-05, + "loss": 0.1383, + "step": 21149 + }, + { + "epoch": 6.53, + "learning_rate": 1.5730471559260197e-05, + "loss": 0.1291, + "step": 21150 + }, + { + "epoch": 6.53, + "learning_rate": 1.5730061694008047e-05, + "loss": 0.1231, + "step": 21151 + }, + { + "epoch": 6.53, + "learning_rate": 1.5729651814423967e-05, + "loss": 0.124, + "step": 21152 + }, + { + "epoch": 6.53, + "learning_rate": 1.5729241920508983e-05, + "loss": 0.1188, + "step": 21153 + }, + { + "epoch": 6.53, + "learning_rate": 1.572883201226412e-05, + "loss": 0.1287, + "step": 21154 + }, + { + "epoch": 6.53, + "learning_rate": 1.5728422089690405e-05, + "loss": 0.1299, + "step": 21155 + }, + { + "epoch": 6.53, + "learning_rate": 1.5728012152788862e-05, + "loss": 0.1202, + "step": 21156 + }, + { + "epoch": 6.53, + "learning_rate": 1.5727602201560513e-05, + "loss": 0.133, + "step": 21157 + }, + { + "epoch": 6.53, + "learning_rate": 1.5727192236006387e-05, + "loss": 0.1218, + "step": 21158 + }, + { + "epoch": 6.53, + "learning_rate": 1.5726782256127507e-05, + "loss": 0.1288, + "step": 21159 + }, + { + "epoch": 6.53, + "learning_rate": 1.5726372261924904e-05, + "loss": 0.1224, + "step": 21160 + }, + { + "epoch": 6.54, + "learning_rate": 1.5725962253399597e-05, + "loss": 0.1171, + "step": 21161 + }, + { + "epoch": 6.54, + "learning_rate": 1.5725552230552613e-05, + "loss": 0.1274, + "step": 21162 + }, + { + "epoch": 6.54, + "learning_rate": 1.5725142193384982e-05, + "loss": 0.1306, + "step": 21163 + }, + { + "epoch": 6.54, + "learning_rate": 1.5724732141897724e-05, + "loss": 0.1135, + "step": 21164 + }, + { + "epoch": 6.54, + "learning_rate": 1.5724322076091868e-05, + "loss": 0.1214, + "step": 21165 + }, + { + "epoch": 6.54, + "learning_rate": 1.5723911995968438e-05, + "loss": 0.1244, + "step": 21166 + }, + { + "epoch": 6.54, + "learning_rate": 1.572350190152846e-05, + "loss": 0.1213, + "step": 21167 + }, + { + "epoch": 6.54, + "learning_rate": 1.572309179277296e-05, + "loss": 0.1325, + "step": 21168 + }, + { + "epoch": 6.54, + "learning_rate": 1.5722681669702963e-05, + "loss": 0.1296, + "step": 21169 + }, + { + "epoch": 6.54, + "learning_rate": 1.5722271532319496e-05, + "loss": 0.1227, + "step": 21170 + }, + { + "epoch": 6.54, + "learning_rate": 1.5721861380623585e-05, + "loss": 0.121, + "step": 21171 + }, + { + "epoch": 6.54, + "learning_rate": 1.5721451214616252e-05, + "loss": 0.1215, + "step": 21172 + }, + { + "epoch": 6.54, + "learning_rate": 1.572104103429853e-05, + "loss": 0.1189, + "step": 21173 + }, + { + "epoch": 6.54, + "learning_rate": 1.5720630839671437e-05, + "loss": 0.1199, + "step": 21174 + }, + { + "epoch": 6.54, + "learning_rate": 1.5720220630736003e-05, + "loss": 0.1266, + "step": 21175 + }, + { + "epoch": 6.54, + "learning_rate": 1.571981040749326e-05, + "loss": 0.118, + "step": 21176 + }, + { + "epoch": 6.54, + "learning_rate": 1.5719400169944222e-05, + "loss": 0.1224, + "step": 21177 + }, + { + "epoch": 6.54, + "learning_rate": 1.571898991808992e-05, + "loss": 0.1111, + "step": 21178 + }, + { + "epoch": 6.54, + "learning_rate": 1.5718579651931384e-05, + "loss": 0.1034, + "step": 21179 + }, + { + "epoch": 6.54, + "learning_rate": 1.571816937146964e-05, + "loss": 0.1142, + "step": 21180 + }, + { + "epoch": 6.54, + "learning_rate": 1.5717759076705706e-05, + "loss": 0.1242, + "step": 21181 + }, + { + "epoch": 6.54, + "learning_rate": 1.5717348767640618e-05, + "loss": 0.1121, + "step": 21182 + }, + { + "epoch": 6.54, + "learning_rate": 1.5716938444275397e-05, + "loss": 0.1294, + "step": 21183 + }, + { + "epoch": 6.54, + "learning_rate": 1.5716528106611068e-05, + "loss": 0.1159, + "step": 21184 + }, + { + "epoch": 6.54, + "learning_rate": 1.571611775464866e-05, + "loss": 0.1217, + "step": 21185 + }, + { + "epoch": 6.54, + "learning_rate": 1.5715707388389203e-05, + "loss": 0.1281, + "step": 21186 + }, + { + "epoch": 6.54, + "learning_rate": 1.5715297007833713e-05, + "loss": 0.1321, + "step": 21187 + }, + { + "epoch": 6.54, + "learning_rate": 1.571488661298323e-05, + "loss": 0.1254, + "step": 21188 + }, + { + "epoch": 6.54, + "learning_rate": 1.5714476203838768e-05, + "loss": 0.1207, + "step": 21189 + }, + { + "epoch": 6.54, + "learning_rate": 1.5714065780401358e-05, + "loss": 0.1211, + "step": 21190 + }, + { + "epoch": 6.54, + "learning_rate": 1.5713655342672033e-05, + "loss": 0.121, + "step": 21191 + }, + { + "epoch": 6.54, + "learning_rate": 1.5713244890651808e-05, + "loss": 0.1237, + "step": 21192 + }, + { + "epoch": 6.54, + "learning_rate": 1.5712834424341717e-05, + "loss": 0.1153, + "step": 21193 + }, + { + "epoch": 6.55, + "learning_rate": 1.5712423943742787e-05, + "loss": 0.1271, + "step": 21194 + }, + { + "epoch": 6.55, + "learning_rate": 1.571201344885604e-05, + "loss": 0.124, + "step": 21195 + }, + { + "epoch": 6.55, + "learning_rate": 1.5711602939682508e-05, + "loss": 0.1153, + "step": 21196 + }, + { + "epoch": 6.55, + "learning_rate": 1.5711192416223216e-05, + "loss": 0.1217, + "step": 21197 + }, + { + "epoch": 6.55, + "learning_rate": 1.5710781878479188e-05, + "loss": 0.1249, + "step": 21198 + }, + { + "epoch": 6.55, + "learning_rate": 1.5710371326451453e-05, + "loss": 0.1365, + "step": 21199 + }, + { + "epoch": 6.55, + "learning_rate": 1.5709960760141042e-05, + "loss": 0.1168, + "step": 21200 + }, + { + "epoch": 6.55, + "learning_rate": 1.5709550179548968e-05, + "loss": 0.1229, + "step": 21201 + }, + { + "epoch": 6.55, + "learning_rate": 1.5709139584676278e-05, + "loss": 0.1495, + "step": 21202 + }, + { + "epoch": 6.55, + "learning_rate": 1.5708728975523984e-05, + "loss": 0.1323, + "step": 21203 + }, + { + "epoch": 6.55, + "learning_rate": 1.5708318352093117e-05, + "loss": 0.1225, + "step": 21204 + }, + { + "epoch": 6.55, + "learning_rate": 1.5707907714384706e-05, + "loss": 0.1193, + "step": 21205 + }, + { + "epoch": 6.55, + "learning_rate": 1.5707497062399776e-05, + "loss": 0.1139, + "step": 21206 + }, + { + "epoch": 6.55, + "learning_rate": 1.5707086396139355e-05, + "loss": 0.1256, + "step": 21207 + }, + { + "epoch": 6.55, + "learning_rate": 1.570667571560447e-05, + "loss": 0.1305, + "step": 21208 + }, + { + "epoch": 6.55, + "learning_rate": 1.5706265020796146e-05, + "loss": 0.1245, + "step": 21209 + }, + { + "epoch": 6.55, + "learning_rate": 1.5705854311715418e-05, + "loss": 0.1283, + "step": 21210 + }, + { + "epoch": 6.55, + "learning_rate": 1.5705443588363307e-05, + "loss": 0.1169, + "step": 21211 + }, + { + "epoch": 6.55, + "learning_rate": 1.5705032850740834e-05, + "loss": 0.1142, + "step": 21212 + }, + { + "epoch": 6.55, + "learning_rate": 1.5704622098849042e-05, + "loss": 0.1231, + "step": 21213 + }, + { + "epoch": 6.55, + "learning_rate": 1.5704211332688946e-05, + "loss": 0.1284, + "step": 21214 + }, + { + "epoch": 6.55, + "learning_rate": 1.5703800552261575e-05, + "loss": 0.117, + "step": 21215 + }, + { + "epoch": 6.55, + "learning_rate": 1.570338975756796e-05, + "loss": 0.1147, + "step": 21216 + }, + { + "epoch": 6.55, + "learning_rate": 1.5702978948609127e-05, + "loss": 0.1246, + "step": 21217 + }, + { + "epoch": 6.55, + "learning_rate": 1.5702568125386104e-05, + "loss": 0.1306, + "step": 21218 + }, + { + "epoch": 6.55, + "learning_rate": 1.5702157287899918e-05, + "loss": 0.1193, + "step": 21219 + }, + { + "epoch": 6.55, + "learning_rate": 1.5701746436151598e-05, + "loss": 0.1296, + "step": 21220 + }, + { + "epoch": 6.55, + "learning_rate": 1.570133557014217e-05, + "loss": 0.1236, + "step": 21221 + }, + { + "epoch": 6.55, + "learning_rate": 1.5700924689872658e-05, + "loss": 0.1235, + "step": 21222 + }, + { + "epoch": 6.55, + "learning_rate": 1.5700513795344095e-05, + "loss": 0.1292, + "step": 21223 + }, + { + "epoch": 6.55, + "learning_rate": 1.5700102886557508e-05, + "loss": 0.1193, + "step": 21224 + }, + { + "epoch": 6.55, + "learning_rate": 1.5699691963513927e-05, + "loss": 0.1304, + "step": 21225 + }, + { + "epoch": 6.56, + "learning_rate": 1.5699281026214374e-05, + "loss": 0.1234, + "step": 21226 + }, + { + "epoch": 6.56, + "learning_rate": 1.5698870074659877e-05, + "loss": 0.1252, + "step": 21227 + }, + { + "epoch": 6.56, + "learning_rate": 1.5698459108851472e-05, + "loss": 0.1295, + "step": 21228 + }, + { + "epoch": 6.56, + "learning_rate": 1.5698048128790176e-05, + "loss": 0.1208, + "step": 21229 + }, + { + "epoch": 6.56, + "learning_rate": 1.569763713447703e-05, + "loss": 0.1207, + "step": 21230 + }, + { + "epoch": 6.56, + "learning_rate": 1.5697226125913044e-05, + "loss": 0.1242, + "step": 21231 + }, + { + "epoch": 6.56, + "learning_rate": 1.5696815103099264e-05, + "loss": 0.1187, + "step": 21232 + }, + { + "epoch": 6.56, + "learning_rate": 1.569640406603671e-05, + "loss": 0.1411, + "step": 21233 + }, + { + "epoch": 6.56, + "learning_rate": 1.569599301472641e-05, + "loss": 0.1308, + "step": 21234 + }, + { + "epoch": 6.56, + "learning_rate": 1.569558194916939e-05, + "loss": 0.1337, + "step": 21235 + }, + { + "epoch": 6.56, + "learning_rate": 1.569517086936668e-05, + "loss": 0.1234, + "step": 21236 + }, + { + "epoch": 6.56, + "learning_rate": 1.569475977531931e-05, + "loss": 0.1185, + "step": 21237 + }, + { + "epoch": 6.56, + "learning_rate": 1.569434866702831e-05, + "loss": 0.1273, + "step": 21238 + }, + { + "epoch": 6.56, + "learning_rate": 1.5693937544494703e-05, + "loss": 0.1316, + "step": 21239 + }, + { + "epoch": 6.56, + "learning_rate": 1.569352640771952e-05, + "loss": 0.1327, + "step": 21240 + }, + { + "epoch": 6.56, + "learning_rate": 1.569311525670379e-05, + "loss": 0.1309, + "step": 21241 + }, + { + "epoch": 6.56, + "learning_rate": 1.569270409144854e-05, + "loss": 0.1342, + "step": 21242 + }, + { + "epoch": 6.56, + "learning_rate": 1.5692292911954797e-05, + "loss": 0.109, + "step": 21243 + }, + { + "epoch": 6.56, + "learning_rate": 1.5691881718223593e-05, + "loss": 0.1073, + "step": 21244 + }, + { + "epoch": 6.56, + "learning_rate": 1.5691470510255956e-05, + "loss": 0.123, + "step": 21245 + }, + { + "epoch": 6.56, + "learning_rate": 1.569105928805291e-05, + "loss": 0.1207, + "step": 21246 + }, + { + "epoch": 6.56, + "learning_rate": 1.569064805161549e-05, + "loss": 0.114, + "step": 21247 + }, + { + "epoch": 6.56, + "learning_rate": 1.569023680094472e-05, + "loss": 0.1219, + "step": 21248 + }, + { + "epoch": 6.56, + "learning_rate": 1.5689825536041628e-05, + "loss": 0.1292, + "step": 21249 + }, + { + "epoch": 6.56, + "learning_rate": 1.568941425690725e-05, + "loss": 0.116, + "step": 21250 + }, + { + "epoch": 6.56, + "learning_rate": 1.56890029635426e-05, + "loss": 0.1242, + "step": 21251 + }, + { + "epoch": 6.56, + "learning_rate": 1.5688591655948724e-05, + "loss": 0.1223, + "step": 21252 + }, + { + "epoch": 6.56, + "learning_rate": 1.5688180334126636e-05, + "loss": 0.1293, + "step": 21253 + }, + { + "epoch": 6.56, + "learning_rate": 1.568776899807738e-05, + "loss": 0.1294, + "step": 21254 + }, + { + "epoch": 6.56, + "learning_rate": 1.568735764780197e-05, + "loss": 0.1438, + "step": 21255 + }, + { + "epoch": 6.56, + "learning_rate": 1.5686946283301445e-05, + "loss": 0.114, + "step": 21256 + }, + { + "epoch": 6.56, + "learning_rate": 1.5686534904576824e-05, + "loss": 0.1243, + "step": 21257 + }, + { + "epoch": 6.56, + "learning_rate": 1.568612351162915e-05, + "loss": 0.121, + "step": 21258 + }, + { + "epoch": 6.57, + "learning_rate": 1.5685712104459438e-05, + "loss": 0.1206, + "step": 21259 + }, + { + "epoch": 6.57, + "learning_rate": 1.5685300683068728e-05, + "loss": 0.1293, + "step": 21260 + }, + { + "epoch": 6.57, + "learning_rate": 1.568488924745804e-05, + "loss": 0.1373, + "step": 21261 + }, + { + "epoch": 6.57, + "learning_rate": 1.5684477797628408e-05, + "loss": 0.1186, + "step": 21262 + }, + { + "epoch": 6.57, + "learning_rate": 1.568406633358086e-05, + "loss": 0.1156, + "step": 21263 + }, + { + "epoch": 6.57, + "learning_rate": 1.5683654855316426e-05, + "loss": 0.1133, + "step": 21264 + }, + { + "epoch": 6.57, + "learning_rate": 1.5683243362836135e-05, + "loss": 0.12, + "step": 21265 + }, + { + "epoch": 6.57, + "learning_rate": 1.5682831856141018e-05, + "loss": 0.1261, + "step": 21266 + }, + { + "epoch": 6.57, + "learning_rate": 1.56824203352321e-05, + "loss": 0.1283, + "step": 21267 + }, + { + "epoch": 6.57, + "learning_rate": 1.568200880011041e-05, + "loss": 0.1207, + "step": 21268 + }, + { + "epoch": 6.57, + "learning_rate": 1.568159725077698e-05, + "loss": 0.1218, + "step": 21269 + }, + { + "epoch": 6.57, + "learning_rate": 1.5681185687232844e-05, + "loss": 0.1154, + "step": 21270 + }, + { + "epoch": 6.57, + "learning_rate": 1.568077410947902e-05, + "loss": 0.1151, + "step": 21271 + }, + { + "epoch": 6.57, + "learning_rate": 1.5680362517516547e-05, + "loss": 0.1196, + "step": 21272 + }, + { + "epoch": 6.57, + "learning_rate": 1.567995091134645e-05, + "loss": 0.1242, + "step": 21273 + }, + { + "epoch": 6.57, + "learning_rate": 1.567953929096976e-05, + "loss": 0.1254, + "step": 21274 + }, + { + "epoch": 6.57, + "learning_rate": 1.567912765638751e-05, + "loss": 0.1296, + "step": 21275 + }, + { + "epoch": 6.57, + "learning_rate": 1.567871600760072e-05, + "loss": 0.1308, + "step": 21276 + }, + { + "epoch": 6.57, + "learning_rate": 1.567830434461043e-05, + "loss": 0.1321, + "step": 21277 + }, + { + "epoch": 6.57, + "learning_rate": 1.5677892667417665e-05, + "loss": 0.1377, + "step": 21278 + }, + { + "epoch": 6.57, + "learning_rate": 1.5677480976023457e-05, + "loss": 0.1325, + "step": 21279 + }, + { + "epoch": 6.57, + "learning_rate": 1.567706927042883e-05, + "loss": 0.1258, + "step": 21280 + }, + { + "epoch": 6.57, + "learning_rate": 1.5676657550634815e-05, + "loss": 0.117, + "step": 21281 + }, + { + "epoch": 6.57, + "learning_rate": 1.567624581664245e-05, + "loss": 0.1288, + "step": 21282 + }, + { + "epoch": 6.57, + "learning_rate": 1.5675834068452754e-05, + "loss": 0.1226, + "step": 21283 + }, + { + "epoch": 6.57, + "learning_rate": 1.5675422306066762e-05, + "loss": 0.1152, + "step": 21284 + }, + { + "epoch": 6.57, + "learning_rate": 1.5675010529485505e-05, + "loss": 0.1157, + "step": 21285 + }, + { + "epoch": 6.57, + "learning_rate": 1.5674598738710012e-05, + "loss": 0.1211, + "step": 21286 + }, + { + "epoch": 6.57, + "learning_rate": 1.5674186933741313e-05, + "loss": 0.1156, + "step": 21287 + }, + { + "epoch": 6.57, + "learning_rate": 1.5673775114580438e-05, + "loss": 0.1115, + "step": 21288 + }, + { + "epoch": 6.57, + "learning_rate": 1.5673363281228417e-05, + "loss": 0.1291, + "step": 21289 + }, + { + "epoch": 6.57, + "learning_rate": 1.5672951433686273e-05, + "loss": 0.1186, + "step": 21290 + }, + { + "epoch": 6.58, + "learning_rate": 1.567253957195505e-05, + "loss": 0.1239, + "step": 21291 + }, + { + "epoch": 6.58, + "learning_rate": 1.567212769603577e-05, + "loss": 0.1105, + "step": 21292 + }, + { + "epoch": 6.58, + "learning_rate": 1.5671715805929463e-05, + "loss": 0.1222, + "step": 21293 + }, + { + "epoch": 6.58, + "learning_rate": 1.567130390163716e-05, + "loss": 0.1169, + "step": 21294 + }, + { + "epoch": 6.58, + "learning_rate": 1.567089198315989e-05, + "loss": 0.139, + "step": 21295 + }, + { + "epoch": 6.58, + "learning_rate": 1.567048005049869e-05, + "loss": 0.1347, + "step": 21296 + }, + { + "epoch": 6.58, + "learning_rate": 1.567006810365458e-05, + "loss": 0.1175, + "step": 21297 + }, + { + "epoch": 6.58, + "learning_rate": 1.56696561426286e-05, + "loss": 0.1257, + "step": 21298 + }, + { + "epoch": 6.58, + "learning_rate": 1.566924416742177e-05, + "loss": 0.1323, + "step": 21299 + }, + { + "epoch": 6.58, + "learning_rate": 1.566883217803513e-05, + "loss": 0.1233, + "step": 21300 + }, + { + "epoch": 6.58, + "learning_rate": 1.5668420174469707e-05, + "loss": 0.1206, + "step": 21301 + }, + { + "epoch": 6.58, + "learning_rate": 1.566800815672653e-05, + "loss": 0.1271, + "step": 21302 + }, + { + "epoch": 6.58, + "learning_rate": 1.5667596124806633e-05, + "loss": 0.1146, + "step": 21303 + }, + { + "epoch": 6.58, + "learning_rate": 1.5667184078711042e-05, + "loss": 0.1208, + "step": 21304 + }, + { + "epoch": 6.58, + "learning_rate": 1.566677201844079e-05, + "loss": 0.1172, + "step": 21305 + }, + { + "epoch": 6.58, + "learning_rate": 1.566635994399691e-05, + "loss": 0.1397, + "step": 21306 + }, + { + "epoch": 6.58, + "learning_rate": 1.566594785538043e-05, + "loss": 0.1195, + "step": 21307 + }, + { + "epoch": 6.58, + "learning_rate": 1.566553575259238e-05, + "loss": 0.1205, + "step": 21308 + }, + { + "epoch": 6.58, + "learning_rate": 1.566512363563379e-05, + "loss": 0.1292, + "step": 21309 + }, + { + "epoch": 6.58, + "learning_rate": 1.5664711504505694e-05, + "loss": 0.1229, + "step": 21310 + }, + { + "epoch": 6.58, + "learning_rate": 1.566429935920912e-05, + "loss": 0.1255, + "step": 21311 + }, + { + "epoch": 6.58, + "learning_rate": 1.5663887199745103e-05, + "loss": 0.1207, + "step": 21312 + }, + { + "epoch": 6.58, + "learning_rate": 1.566347502611467e-05, + "loss": 0.1182, + "step": 21313 + }, + { + "epoch": 6.58, + "learning_rate": 1.5663062838318854e-05, + "loss": 0.1133, + "step": 21314 + }, + { + "epoch": 6.58, + "learning_rate": 1.5662650636358684e-05, + "loss": 0.1097, + "step": 21315 + }, + { + "epoch": 6.58, + "learning_rate": 1.566223842023519e-05, + "loss": 0.1356, + "step": 21316 + }, + { + "epoch": 6.58, + "learning_rate": 1.5661826189949406e-05, + "loss": 0.1259, + "step": 21317 + }, + { + "epoch": 6.58, + "learning_rate": 1.5661413945502365e-05, + "loss": 0.1201, + "step": 21318 + }, + { + "epoch": 6.58, + "learning_rate": 1.566100168689509e-05, + "loss": 0.1391, + "step": 21319 + }, + { + "epoch": 6.58, + "learning_rate": 1.566058941412862e-05, + "loss": 0.1266, + "step": 21320 + }, + { + "epoch": 6.58, + "learning_rate": 1.5660177127203986e-05, + "loss": 0.1135, + "step": 21321 + }, + { + "epoch": 6.58, + "learning_rate": 1.565976482612221e-05, + "loss": 0.1321, + "step": 21322 + }, + { + "epoch": 6.59, + "learning_rate": 1.5659352510884337e-05, + "loss": 0.1127, + "step": 21323 + }, + { + "epoch": 6.59, + "learning_rate": 1.5658940181491388e-05, + "loss": 0.1223, + "step": 21324 + }, + { + "epoch": 6.59, + "learning_rate": 1.56585278379444e-05, + "loss": 0.1126, + "step": 21325 + }, + { + "epoch": 6.59, + "learning_rate": 1.5658115480244397e-05, + "loss": 0.1353, + "step": 21326 + }, + { + "epoch": 6.59, + "learning_rate": 1.565770310839242e-05, + "loss": 0.1312, + "step": 21327 + }, + { + "epoch": 6.59, + "learning_rate": 1.5657290722389494e-05, + "loss": 0.1229, + "step": 21328 + }, + { + "epoch": 6.59, + "learning_rate": 1.565687832223665e-05, + "loss": 0.1376, + "step": 21329 + }, + { + "epoch": 6.59, + "learning_rate": 1.5656465907934924e-05, + "loss": 0.124, + "step": 21330 + }, + { + "epoch": 6.59, + "learning_rate": 1.5656053479485343e-05, + "loss": 0.1207, + "step": 21331 + }, + { + "epoch": 6.59, + "learning_rate": 1.565564103688894e-05, + "loss": 0.1227, + "step": 21332 + }, + { + "epoch": 6.59, + "learning_rate": 1.5655228580146752e-05, + "loss": 0.1246, + "step": 21333 + }, + { + "epoch": 6.59, + "learning_rate": 1.56548161092598e-05, + "loss": 0.1319, + "step": 21334 + }, + { + "epoch": 6.59, + "learning_rate": 1.565440362422913e-05, + "loss": 0.1216, + "step": 21335 + }, + { + "epoch": 6.59, + "learning_rate": 1.565399112505576e-05, + "loss": 0.1176, + "step": 21336 + }, + { + "epoch": 6.59, + "learning_rate": 1.5653578611740722e-05, + "loss": 0.1318, + "step": 21337 + }, + { + "epoch": 6.59, + "learning_rate": 1.5653166084285062e-05, + "loss": 0.1227, + "step": 21338 + }, + { + "epoch": 6.59, + "learning_rate": 1.5652753542689793e-05, + "loss": 0.1228, + "step": 21339 + }, + { + "epoch": 6.59, + "learning_rate": 1.565234098695596e-05, + "loss": 0.1279, + "step": 21340 + }, + { + "epoch": 6.59, + "learning_rate": 1.5651928417084595e-05, + "loss": 0.1292, + "step": 21341 + }, + { + "epoch": 6.59, + "learning_rate": 1.5651515833076726e-05, + "loss": 0.1331, + "step": 21342 + }, + { + "epoch": 6.59, + "learning_rate": 1.565110323493338e-05, + "loss": 0.1159, + "step": 21343 + }, + { + "epoch": 6.59, + "learning_rate": 1.56506906226556e-05, + "loss": 0.1148, + "step": 21344 + }, + { + "epoch": 6.59, + "learning_rate": 1.5650277996244406e-05, + "loss": 0.1335, + "step": 21345 + }, + { + "epoch": 6.59, + "learning_rate": 1.5649865355700842e-05, + "loss": 0.12, + "step": 21346 + }, + { + "epoch": 6.59, + "learning_rate": 1.5649452701025933e-05, + "loss": 0.1168, + "step": 21347 + }, + { + "epoch": 6.59, + "learning_rate": 1.564904003222071e-05, + "loss": 0.1272, + "step": 21348 + }, + { + "epoch": 6.59, + "learning_rate": 1.564862734928621e-05, + "loss": 0.1302, + "step": 21349 + }, + { + "epoch": 6.59, + "learning_rate": 1.564821465222346e-05, + "loss": 0.1233, + "step": 21350 + }, + { + "epoch": 6.59, + "learning_rate": 1.5647801941033495e-05, + "loss": 0.1281, + "step": 21351 + }, + { + "epoch": 6.59, + "learning_rate": 1.564738921571735e-05, + "loss": 0.1166, + "step": 21352 + }, + { + "epoch": 6.59, + "learning_rate": 1.564697647627605e-05, + "loss": 0.1204, + "step": 21353 + }, + { + "epoch": 6.59, + "learning_rate": 1.5646563722710638e-05, + "loss": 0.1129, + "step": 21354 + }, + { + "epoch": 6.59, + "learning_rate": 1.5646150955022136e-05, + "loss": 0.119, + "step": 21355 + }, + { + "epoch": 6.6, + "learning_rate": 1.5645738173211582e-05, + "loss": 0.1275, + "step": 21356 + }, + { + "epoch": 6.6, + "learning_rate": 1.5645325377280007e-05, + "loss": 0.1185, + "step": 21357 + }, + { + "epoch": 6.6, + "learning_rate": 1.5644912567228447e-05, + "loss": 0.1221, + "step": 21358 + }, + { + "epoch": 6.6, + "learning_rate": 1.5644499743057925e-05, + "loss": 0.1254, + "step": 21359 + }, + { + "epoch": 6.6, + "learning_rate": 1.5644086904769484e-05, + "loss": 0.127, + "step": 21360 + }, + { + "epoch": 6.6, + "learning_rate": 1.564367405236415e-05, + "loss": 0.1186, + "step": 21361 + }, + { + "epoch": 6.6, + "learning_rate": 1.564326118584296e-05, + "loss": 0.1223, + "step": 21362 + }, + { + "epoch": 6.6, + "learning_rate": 1.564284830520694e-05, + "loss": 0.1185, + "step": 21363 + }, + { + "epoch": 6.6, + "learning_rate": 1.564243541045713e-05, + "loss": 0.1292, + "step": 21364 + }, + { + "epoch": 6.6, + "learning_rate": 1.5642022501594562e-05, + "loss": 0.1176, + "step": 21365 + }, + { + "epoch": 6.6, + "learning_rate": 1.5641609578620265e-05, + "loss": 0.1166, + "step": 21366 + }, + { + "epoch": 6.6, + "learning_rate": 1.564119664153527e-05, + "loss": 0.1279, + "step": 21367 + }, + { + "epoch": 6.6, + "learning_rate": 1.564078369034062e-05, + "loss": 0.1265, + "step": 21368 + }, + { + "epoch": 6.6, + "learning_rate": 1.5640370725037338e-05, + "loss": 0.1295, + "step": 21369 + }, + { + "epoch": 6.6, + "learning_rate": 1.563995774562646e-05, + "loss": 0.1288, + "step": 21370 + }, + { + "epoch": 6.6, + "learning_rate": 1.5639544752109016e-05, + "loss": 0.1236, + "step": 21371 + }, + { + "epoch": 6.6, + "learning_rate": 1.563913174448605e-05, + "loss": 0.1359, + "step": 21372 + }, + { + "epoch": 6.6, + "learning_rate": 1.5638718722758576e-05, + "loss": 0.116, + "step": 21373 + }, + { + "epoch": 6.6, + "learning_rate": 1.5638305686927646e-05, + "loss": 0.128, + "step": 21374 + }, + { + "epoch": 6.6, + "learning_rate": 1.5637892636994285e-05, + "loss": 0.1353, + "step": 21375 + }, + { + "epoch": 6.6, + "learning_rate": 1.5637479572959523e-05, + "loss": 0.1214, + "step": 21376 + }, + { + "epoch": 6.6, + "learning_rate": 1.5637066494824396e-05, + "loss": 0.1155, + "step": 21377 + }, + { + "epoch": 6.6, + "learning_rate": 1.5636653402589942e-05, + "loss": 0.1265, + "step": 21378 + }, + { + "epoch": 6.6, + "learning_rate": 1.5636240296257187e-05, + "loss": 0.1272, + "step": 21379 + }, + { + "epoch": 6.6, + "learning_rate": 1.5635827175827164e-05, + "loss": 0.1298, + "step": 21380 + }, + { + "epoch": 6.6, + "learning_rate": 1.5635414041300914e-05, + "loss": 0.1233, + "step": 21381 + }, + { + "epoch": 6.6, + "learning_rate": 1.5635000892679463e-05, + "loss": 0.1303, + "step": 21382 + }, + { + "epoch": 6.6, + "learning_rate": 1.563458772996385e-05, + "loss": 0.1328, + "step": 21383 + }, + { + "epoch": 6.6, + "learning_rate": 1.5634174553155102e-05, + "loss": 0.1232, + "step": 21384 + }, + { + "epoch": 6.6, + "learning_rate": 1.5633761362254256e-05, + "loss": 0.1174, + "step": 21385 + }, + { + "epoch": 6.6, + "learning_rate": 1.563334815726235e-05, + "loss": 0.1209, + "step": 21386 + }, + { + "epoch": 6.6, + "learning_rate": 1.5632934938180405e-05, + "loss": 0.1334, + "step": 21387 + }, + { + "epoch": 6.61, + "learning_rate": 1.563252170500947e-05, + "loss": 0.1258, + "step": 21388 + }, + { + "epoch": 6.61, + "learning_rate": 1.5632108457750565e-05, + "loss": 0.1221, + "step": 21389 + }, + { + "epoch": 6.61, + "learning_rate": 1.5631695196404732e-05, + "loss": 0.1293, + "step": 21390 + }, + { + "epoch": 6.61, + "learning_rate": 1.5631281920973003e-05, + "loss": 0.1354, + "step": 21391 + }, + { + "epoch": 6.61, + "learning_rate": 1.563086863145641e-05, + "loss": 0.1204, + "step": 21392 + }, + { + "epoch": 6.61, + "learning_rate": 1.5630455327855987e-05, + "loss": 0.1222, + "step": 21393 + }, + { + "epoch": 6.61, + "learning_rate": 1.563004201017277e-05, + "loss": 0.1196, + "step": 21394 + }, + { + "epoch": 6.61, + "learning_rate": 1.562962867840779e-05, + "loss": 0.1246, + "step": 21395 + }, + { + "epoch": 6.61, + "learning_rate": 1.562921533256208e-05, + "loss": 0.1215, + "step": 21396 + }, + { + "epoch": 6.61, + "learning_rate": 1.562880197263668e-05, + "loss": 0.1137, + "step": 21397 + }, + { + "epoch": 6.61, + "learning_rate": 1.562838859863262e-05, + "loss": 0.1197, + "step": 21398 + }, + { + "epoch": 6.61, + "learning_rate": 1.562797521055093e-05, + "loss": 0.1277, + "step": 21399 + }, + { + "epoch": 6.61, + "learning_rate": 1.5627561808392645e-05, + "loss": 0.1273, + "step": 21400 + }, + { + "epoch": 6.61, + "learning_rate": 1.5627148392158805e-05, + "loss": 0.1195, + "step": 21401 + }, + { + "epoch": 6.61, + "learning_rate": 1.5626734961850442e-05, + "loss": 0.1127, + "step": 21402 + }, + { + "epoch": 6.61, + "learning_rate": 1.5626321517468586e-05, + "loss": 0.1231, + "step": 21403 + }, + { + "epoch": 6.61, + "learning_rate": 1.5625908059014274e-05, + "loss": 0.1429, + "step": 21404 + }, + { + "epoch": 6.61, + "learning_rate": 1.5625494586488542e-05, + "loss": 0.1161, + "step": 21405 + }, + { + "epoch": 6.61, + "learning_rate": 1.562508109989242e-05, + "loss": 0.1169, + "step": 21406 + }, + { + "epoch": 6.61, + "learning_rate": 1.5624667599226943e-05, + "loss": 0.1205, + "step": 21407 + }, + { + "epoch": 6.61, + "learning_rate": 1.5624254084493152e-05, + "loss": 0.114, + "step": 21408 + }, + { + "epoch": 6.61, + "learning_rate": 1.562384055569207e-05, + "loss": 0.1127, + "step": 21409 + }, + { + "epoch": 6.61, + "learning_rate": 1.562342701282474e-05, + "loss": 0.1283, + "step": 21410 + }, + { + "epoch": 6.61, + "learning_rate": 1.5623013455892192e-05, + "loss": 0.1227, + "step": 21411 + }, + { + "epoch": 6.61, + "learning_rate": 1.562259988489546e-05, + "loss": 0.1197, + "step": 21412 + }, + { + "epoch": 6.61, + "learning_rate": 1.5622186299835585e-05, + "loss": 0.109, + "step": 21413 + }, + { + "epoch": 6.61, + "learning_rate": 1.5621772700713593e-05, + "loss": 0.1317, + "step": 21414 + }, + { + "epoch": 6.61, + "learning_rate": 1.5621359087530522e-05, + "loss": 0.1271, + "step": 21415 + }, + { + "epoch": 6.61, + "learning_rate": 1.5620945460287405e-05, + "loss": 0.1237, + "step": 21416 + }, + { + "epoch": 6.61, + "learning_rate": 1.5620531818985286e-05, + "loss": 0.1283, + "step": 21417 + }, + { + "epoch": 6.61, + "learning_rate": 1.5620118163625185e-05, + "loss": 0.1171, + "step": 21418 + }, + { + "epoch": 6.61, + "learning_rate": 1.5619704494208146e-05, + "loss": 0.1273, + "step": 21419 + }, + { + "epoch": 6.61, + "learning_rate": 1.56192908107352e-05, + "loss": 0.1242, + "step": 21420 + }, + { + "epoch": 6.62, + "learning_rate": 1.561887711320738e-05, + "loss": 0.1036, + "step": 21421 + }, + { + "epoch": 6.62, + "learning_rate": 1.561846340162573e-05, + "loss": 0.1207, + "step": 21422 + }, + { + "epoch": 6.62, + "learning_rate": 1.5618049675991275e-05, + "loss": 0.1321, + "step": 21423 + }, + { + "epoch": 6.62, + "learning_rate": 1.5617635936305053e-05, + "loss": 0.1152, + "step": 21424 + }, + { + "epoch": 6.62, + "learning_rate": 1.5617222182568096e-05, + "loss": 0.1299, + "step": 21425 + }, + { + "epoch": 6.62, + "learning_rate": 1.5616808414781448e-05, + "loss": 0.1234, + "step": 21426 + }, + { + "epoch": 6.62, + "learning_rate": 1.5616394632946134e-05, + "loss": 0.1298, + "step": 21427 + }, + { + "epoch": 6.62, + "learning_rate": 1.5615980837063193e-05, + "loss": 0.128, + "step": 21428 + }, + { + "epoch": 6.62, + "learning_rate": 1.561556702713366e-05, + "loss": 0.1098, + "step": 21429 + }, + { + "epoch": 6.62, + "learning_rate": 1.561515320315857e-05, + "loss": 0.1255, + "step": 21430 + }, + { + "epoch": 6.62, + "learning_rate": 1.5614739365138958e-05, + "loss": 0.1346, + "step": 21431 + }, + { + "epoch": 6.62, + "learning_rate": 1.5614325513075858e-05, + "loss": 0.1301, + "step": 21432 + }, + { + "epoch": 6.62, + "learning_rate": 1.5613911646970304e-05, + "loss": 0.1185, + "step": 21433 + }, + { + "epoch": 6.62, + "learning_rate": 1.5613497766823336e-05, + "loss": 0.1261, + "step": 21434 + }, + { + "epoch": 6.62, + "learning_rate": 1.561308387263598e-05, + "loss": 0.1279, + "step": 21435 + }, + { + "epoch": 6.62, + "learning_rate": 1.5612669964409287e-05, + "loss": 0.122, + "step": 21436 + }, + { + "epoch": 6.62, + "learning_rate": 1.561225604214428e-05, + "loss": 0.1269, + "step": 21437 + }, + { + "epoch": 6.62, + "learning_rate": 1.561184210584199e-05, + "loss": 0.1222, + "step": 21438 + }, + { + "epoch": 6.62, + "learning_rate": 1.5611428155503466e-05, + "loss": 0.1165, + "step": 21439 + }, + { + "epoch": 6.62, + "learning_rate": 1.5611014191129737e-05, + "loss": 0.1263, + "step": 21440 + }, + { + "epoch": 6.62, + "learning_rate": 1.5610600212721834e-05, + "loss": 0.1181, + "step": 21441 + }, + { + "epoch": 6.62, + "learning_rate": 1.56101862202808e-05, + "loss": 0.1109, + "step": 21442 + }, + { + "epoch": 6.62, + "learning_rate": 1.5609772213807668e-05, + "loss": 0.1202, + "step": 21443 + }, + { + "epoch": 6.62, + "learning_rate": 1.560935819330347e-05, + "loss": 0.1239, + "step": 21444 + }, + { + "epoch": 6.62, + "learning_rate": 1.5608944158769244e-05, + "loss": 0.1206, + "step": 21445 + }, + { + "epoch": 6.62, + "learning_rate": 1.5608530110206027e-05, + "loss": 0.1291, + "step": 21446 + }, + { + "epoch": 6.62, + "learning_rate": 1.5608116047614854e-05, + "loss": 0.1202, + "step": 21447 + }, + { + "epoch": 6.62, + "learning_rate": 1.5607701970996757e-05, + "loss": 0.1362, + "step": 21448 + }, + { + "epoch": 6.62, + "learning_rate": 1.5607287880352777e-05, + "loss": 0.1103, + "step": 21449 + }, + { + "epoch": 6.62, + "learning_rate": 1.5606873775683948e-05, + "loss": 0.1229, + "step": 21450 + }, + { + "epoch": 6.62, + "learning_rate": 1.5606459656991302e-05, + "loss": 0.1144, + "step": 21451 + }, + { + "epoch": 6.62, + "learning_rate": 1.560604552427588e-05, + "loss": 0.1237, + "step": 21452 + }, + { + "epoch": 6.63, + "learning_rate": 1.5605631377538712e-05, + "loss": 0.1269, + "step": 21453 + }, + { + "epoch": 6.63, + "learning_rate": 1.560521721678084e-05, + "loss": 0.1141, + "step": 21454 + }, + { + "epoch": 6.63, + "learning_rate": 1.56048030420033e-05, + "loss": 0.1245, + "step": 21455 + }, + { + "epoch": 6.63, + "learning_rate": 1.5604388853207123e-05, + "loss": 0.1185, + "step": 21456 + }, + { + "epoch": 6.63, + "learning_rate": 1.5603974650393348e-05, + "loss": 0.1172, + "step": 21457 + }, + { + "epoch": 6.63, + "learning_rate": 1.560356043356301e-05, + "loss": 0.1216, + "step": 21458 + }, + { + "epoch": 6.63, + "learning_rate": 1.5603146202717145e-05, + "loss": 0.1167, + "step": 21459 + }, + { + "epoch": 6.63, + "learning_rate": 1.560273195785679e-05, + "loss": 0.1253, + "step": 21460 + }, + { + "epoch": 6.63, + "learning_rate": 1.560231769898298e-05, + "loss": 0.1296, + "step": 21461 + }, + { + "epoch": 6.63, + "learning_rate": 1.560190342609675e-05, + "loss": 0.1337, + "step": 21462 + }, + { + "epoch": 6.63, + "learning_rate": 1.560148913919914e-05, + "loss": 0.1219, + "step": 21463 + }, + { + "epoch": 6.63, + "learning_rate": 1.5601074838291185e-05, + "loss": 0.1256, + "step": 21464 + }, + { + "epoch": 6.63, + "learning_rate": 1.5600660523373918e-05, + "loss": 0.1324, + "step": 21465 + }, + { + "epoch": 6.63, + "learning_rate": 1.560024619444838e-05, + "loss": 0.1196, + "step": 21466 + }, + { + "epoch": 6.63, + "learning_rate": 1.5599831851515602e-05, + "loss": 0.1342, + "step": 21467 + }, + { + "epoch": 6.63, + "learning_rate": 1.5599417494576624e-05, + "loss": 0.1191, + "step": 21468 + }, + { + "epoch": 6.63, + "learning_rate": 1.559900312363248e-05, + "loss": 0.1163, + "step": 21469 + }, + { + "epoch": 6.63, + "learning_rate": 1.559858873868421e-05, + "loss": 0.1238, + "step": 21470 + }, + { + "epoch": 6.63, + "learning_rate": 1.559817433973285e-05, + "loss": 0.1259, + "step": 21471 + }, + { + "epoch": 6.63, + "learning_rate": 1.5597759926779432e-05, + "loss": 0.1169, + "step": 21472 + }, + { + "epoch": 6.63, + "learning_rate": 1.5597345499824998e-05, + "loss": 0.1227, + "step": 21473 + }, + { + "epoch": 6.63, + "learning_rate": 1.559693105887058e-05, + "loss": 0.121, + "step": 21474 + }, + { + "epoch": 6.63, + "learning_rate": 1.5596516603917218e-05, + "loss": 0.1175, + "step": 21475 + }, + { + "epoch": 6.63, + "learning_rate": 1.559610213496595e-05, + "loss": 0.1171, + "step": 21476 + }, + { + "epoch": 6.63, + "learning_rate": 1.5595687652017802e-05, + "loss": 0.12, + "step": 21477 + }, + { + "epoch": 6.63, + "learning_rate": 1.5595273155073825e-05, + "loss": 0.1353, + "step": 21478 + }, + { + "epoch": 6.63, + "learning_rate": 1.5594858644135048e-05, + "loss": 0.1209, + "step": 21479 + }, + { + "epoch": 6.63, + "learning_rate": 1.559444411920251e-05, + "loss": 0.1147, + "step": 21480 + }, + { + "epoch": 6.63, + "learning_rate": 1.5594029580277243e-05, + "loss": 0.1224, + "step": 21481 + }, + { + "epoch": 6.63, + "learning_rate": 1.5593615027360293e-05, + "loss": 0.1267, + "step": 21482 + }, + { + "epoch": 6.63, + "learning_rate": 1.5593200460452685e-05, + "loss": 0.1242, + "step": 21483 + }, + { + "epoch": 6.63, + "learning_rate": 1.5592785879555468e-05, + "loss": 0.1109, + "step": 21484 + }, + { + "epoch": 6.64, + "learning_rate": 1.559237128466967e-05, + "loss": 0.1255, + "step": 21485 + }, + { + "epoch": 6.64, + "learning_rate": 1.5591956675796335e-05, + "loss": 0.1189, + "step": 21486 + }, + { + "epoch": 6.64, + "learning_rate": 1.5591542052936496e-05, + "loss": 0.124, + "step": 21487 + }, + { + "epoch": 6.64, + "learning_rate": 1.5591127416091187e-05, + "loss": 0.1275, + "step": 21488 + }, + { + "epoch": 6.64, + "learning_rate": 1.559071276526145e-05, + "loss": 0.1313, + "step": 21489 + }, + { + "epoch": 6.64, + "learning_rate": 1.5590298100448326e-05, + "loss": 0.1234, + "step": 21490 + }, + { + "epoch": 6.64, + "learning_rate": 1.558988342165284e-05, + "loss": 0.1383, + "step": 21491 + }, + { + "epoch": 6.64, + "learning_rate": 1.558946872887604e-05, + "loss": 0.1068, + "step": 21492 + }, + { + "epoch": 6.64, + "learning_rate": 1.5589054022118955e-05, + "loss": 0.1113, + "step": 21493 + }, + { + "epoch": 6.64, + "learning_rate": 1.5588639301382632e-05, + "loss": 0.124, + "step": 21494 + }, + { + "epoch": 6.64, + "learning_rate": 1.5588224566668094e-05, + "loss": 0.1181, + "step": 21495 + }, + { + "epoch": 6.64, + "learning_rate": 1.5587809817976395e-05, + "loss": 0.123, + "step": 21496 + }, + { + "epoch": 6.64, + "learning_rate": 1.5587395055308564e-05, + "loss": 0.1166, + "step": 21497 + }, + { + "epoch": 6.64, + "learning_rate": 1.5586980278665634e-05, + "loss": 0.1268, + "step": 21498 + }, + { + "epoch": 6.64, + "learning_rate": 1.5586565488048653e-05, + "loss": 0.1249, + "step": 21499 + }, + { + "epoch": 6.64, + "learning_rate": 1.558615068345865e-05, + "loss": 0.1288, + "step": 21500 + }, + { + "epoch": 6.64, + "learning_rate": 1.5585735864896667e-05, + "loss": 0.1265, + "step": 21501 + }, + { + "epoch": 6.64, + "learning_rate": 1.558532103236374e-05, + "loss": 0.112, + "step": 21502 + }, + { + "epoch": 6.64, + "learning_rate": 1.5584906185860903e-05, + "loss": 0.1311, + "step": 21503 + }, + { + "epoch": 6.64, + "learning_rate": 1.55844913253892e-05, + "loss": 0.1122, + "step": 21504 + }, + { + "epoch": 6.64, + "learning_rate": 1.5584076450949665e-05, + "loss": 0.116, + "step": 21505 + }, + { + "epoch": 6.64, + "learning_rate": 1.5583661562543337e-05, + "loss": 0.1208, + "step": 21506 + }, + { + "epoch": 6.64, + "learning_rate": 1.558324666017125e-05, + "loss": 0.1149, + "step": 21507 + }, + { + "epoch": 6.64, + "learning_rate": 1.5582831743834445e-05, + "loss": 0.1236, + "step": 21508 + }, + { + "epoch": 6.64, + "learning_rate": 1.5582416813533962e-05, + "loss": 0.1259, + "step": 21509 + }, + { + "epoch": 6.64, + "learning_rate": 1.5582001869270835e-05, + "loss": 0.1283, + "step": 21510 + }, + { + "epoch": 6.64, + "learning_rate": 1.5581586911046105e-05, + "loss": 0.1238, + "step": 21511 + }, + { + "epoch": 6.64, + "learning_rate": 1.5581171938860805e-05, + "loss": 0.1295, + "step": 21512 + }, + { + "epoch": 6.64, + "learning_rate": 1.5580756952715982e-05, + "loss": 0.1251, + "step": 21513 + }, + { + "epoch": 6.64, + "learning_rate": 1.5580341952612663e-05, + "loss": 0.1229, + "step": 21514 + }, + { + "epoch": 6.64, + "learning_rate": 1.557992693855189e-05, + "loss": 0.1263, + "step": 21515 + }, + { + "epoch": 6.64, + "learning_rate": 1.5579511910534705e-05, + "loss": 0.119, + "step": 21516 + }, + { + "epoch": 6.64, + "learning_rate": 1.5579096868562143e-05, + "loss": 0.132, + "step": 21517 + }, + { + "epoch": 6.65, + "learning_rate": 1.5578681812635243e-05, + "loss": 0.1117, + "step": 21518 + }, + { + "epoch": 6.65, + "learning_rate": 1.557826674275504e-05, + "loss": 0.1186, + "step": 21519 + }, + { + "epoch": 6.65, + "learning_rate": 1.5577851658922574e-05, + "loss": 0.115, + "step": 21520 + }, + { + "epoch": 6.65, + "learning_rate": 1.5577436561138886e-05, + "loss": 0.1172, + "step": 21521 + }, + { + "epoch": 6.65, + "learning_rate": 1.557702144940501e-05, + "loss": 0.1213, + "step": 21522 + }, + { + "epoch": 6.65, + "learning_rate": 1.5576606323721985e-05, + "loss": 0.1235, + "step": 21523 + }, + { + "epoch": 6.65, + "learning_rate": 1.557619118409085e-05, + "loss": 0.1369, + "step": 21524 + }, + { + "epoch": 6.65, + "learning_rate": 1.557577603051265e-05, + "loss": 0.1267, + "step": 21525 + }, + { + "epoch": 6.65, + "learning_rate": 1.5575360862988413e-05, + "loss": 0.13, + "step": 21526 + }, + { + "epoch": 6.65, + "learning_rate": 1.557494568151918e-05, + "loss": 0.1194, + "step": 21527 + }, + { + "epoch": 6.65, + "learning_rate": 1.5574530486105995e-05, + "loss": 0.1173, + "step": 21528 + }, + { + "epoch": 6.65, + "learning_rate": 1.5574115276749887e-05, + "loss": 0.1212, + "step": 21529 + }, + { + "epoch": 6.65, + "learning_rate": 1.557370005345191e-05, + "loss": 0.1318, + "step": 21530 + }, + { + "epoch": 6.65, + "learning_rate": 1.5573284816213083e-05, + "loss": 0.1322, + "step": 21531 + }, + { + "epoch": 6.65, + "learning_rate": 1.5572869565034456e-05, + "loss": 0.1205, + "step": 21532 + }, + { + "epoch": 6.65, + "learning_rate": 1.5572454299917068e-05, + "loss": 0.1302, + "step": 21533 + }, + { + "epoch": 6.65, + "learning_rate": 1.5572039020861953e-05, + "loss": 0.1045, + "step": 21534 + }, + { + "epoch": 6.65, + "learning_rate": 1.5571623727870155e-05, + "loss": 0.1272, + "step": 21535 + }, + { + "epoch": 6.65, + "learning_rate": 1.5571208420942706e-05, + "loss": 0.1322, + "step": 21536 + }, + { + "epoch": 6.65, + "learning_rate": 1.5570793100080654e-05, + "loss": 0.1143, + "step": 21537 + }, + { + "epoch": 6.65, + "learning_rate": 1.5570377765285028e-05, + "loss": 0.1255, + "step": 21538 + }, + { + "epoch": 6.65, + "learning_rate": 1.5569962416556873e-05, + "loss": 0.1096, + "step": 21539 + }, + { + "epoch": 6.65, + "learning_rate": 1.5569547053897224e-05, + "loss": 0.1174, + "step": 21540 + }, + { + "epoch": 6.65, + "learning_rate": 1.556913167730713e-05, + "loss": 0.1294, + "step": 21541 + }, + { + "epoch": 6.65, + "learning_rate": 1.556871628678761e-05, + "loss": 0.1282, + "step": 21542 + }, + { + "epoch": 6.65, + "learning_rate": 1.556830088233972e-05, + "loss": 0.116, + "step": 21543 + }, + { + "epoch": 6.65, + "learning_rate": 1.5567885463964495e-05, + "loss": 0.1322, + "step": 21544 + }, + { + "epoch": 6.65, + "learning_rate": 1.5567470031662977e-05, + "loss": 0.1197, + "step": 21545 + }, + { + "epoch": 6.65, + "learning_rate": 1.5567054585436193e-05, + "loss": 0.1217, + "step": 21546 + }, + { + "epoch": 6.65, + "learning_rate": 1.5566639125285193e-05, + "loss": 0.127, + "step": 21547 + }, + { + "epoch": 6.65, + "learning_rate": 1.5566223651211015e-05, + "loss": 0.1261, + "step": 21548 + }, + { + "epoch": 6.65, + "learning_rate": 1.5565808163214695e-05, + "loss": 0.1438, + "step": 21549 + }, + { + "epoch": 6.66, + "learning_rate": 1.5565392661297277e-05, + "loss": 0.1204, + "step": 21550 + }, + { + "epoch": 6.66, + "learning_rate": 1.5564977145459794e-05, + "loss": 0.1329, + "step": 21551 + }, + { + "epoch": 6.66, + "learning_rate": 1.5564561615703286e-05, + "loss": 0.1168, + "step": 21552 + }, + { + "epoch": 6.66, + "learning_rate": 1.5564146072028797e-05, + "loss": 0.1181, + "step": 21553 + }, + { + "epoch": 6.66, + "learning_rate": 1.5563730514437363e-05, + "loss": 0.1186, + "step": 21554 + }, + { + "epoch": 6.66, + "learning_rate": 1.5563314942930022e-05, + "loss": 0.1177, + "step": 21555 + }, + { + "epoch": 6.66, + "learning_rate": 1.556289935750782e-05, + "loss": 0.1352, + "step": 21556 + }, + { + "epoch": 6.66, + "learning_rate": 1.556248375817179e-05, + "loss": 0.1272, + "step": 21557 + }, + { + "epoch": 6.66, + "learning_rate": 1.5562068144922974e-05, + "loss": 0.1188, + "step": 21558 + }, + { + "epoch": 6.66, + "learning_rate": 1.556165251776241e-05, + "loss": 0.1259, + "step": 21559 + }, + { + "epoch": 6.66, + "learning_rate": 1.5561236876691143e-05, + "loss": 0.1134, + "step": 21560 + }, + { + "epoch": 6.66, + "learning_rate": 1.5560821221710202e-05, + "loss": 0.1199, + "step": 21561 + }, + { + "epoch": 6.66, + "learning_rate": 1.556040555282064e-05, + "loss": 0.1217, + "step": 21562 + }, + { + "epoch": 6.66, + "learning_rate": 1.555998987002348e-05, + "loss": 0.1247, + "step": 21563 + }, + { + "epoch": 6.66, + "learning_rate": 1.5559574173319778e-05, + "loss": 0.1341, + "step": 21564 + }, + { + "epoch": 6.66, + "learning_rate": 1.5559158462710565e-05, + "loss": 0.1433, + "step": 21565 + }, + { + "epoch": 6.66, + "learning_rate": 1.5558742738196883e-05, + "loss": 0.1362, + "step": 21566 + }, + { + "epoch": 6.66, + "learning_rate": 1.5558326999779775e-05, + "loss": 0.1224, + "step": 21567 + }, + { + "epoch": 6.66, + "learning_rate": 1.555791124746027e-05, + "loss": 0.1241, + "step": 21568 + }, + { + "epoch": 6.66, + "learning_rate": 1.5557495481239422e-05, + "loss": 0.1159, + "step": 21569 + }, + { + "epoch": 6.66, + "learning_rate": 1.5557079701118264e-05, + "loss": 0.1305, + "step": 21570 + }, + { + "epoch": 6.66, + "learning_rate": 1.555666390709783e-05, + "loss": 0.1243, + "step": 21571 + }, + { + "epoch": 6.66, + "learning_rate": 1.5556248099179172e-05, + "loss": 0.1297, + "step": 21572 + }, + { + "epoch": 6.66, + "learning_rate": 1.5555832277363322e-05, + "loss": 0.1129, + "step": 21573 + }, + { + "epoch": 6.66, + "learning_rate": 1.5555416441651324e-05, + "loss": 0.1284, + "step": 21574 + }, + { + "epoch": 6.66, + "learning_rate": 1.5555000592044215e-05, + "loss": 0.1349, + "step": 21575 + }, + { + "epoch": 6.66, + "learning_rate": 1.5554584728543038e-05, + "loss": 0.1315, + "step": 21576 + }, + { + "epoch": 6.66, + "learning_rate": 1.5554168851148826e-05, + "loss": 0.1358, + "step": 21577 + }, + { + "epoch": 6.66, + "learning_rate": 1.5553752959862627e-05, + "loss": 0.1182, + "step": 21578 + }, + { + "epoch": 6.66, + "learning_rate": 1.555333705468548e-05, + "loss": 0.1147, + "step": 21579 + }, + { + "epoch": 6.66, + "learning_rate": 1.5552921135618424e-05, + "loss": 0.1127, + "step": 21580 + }, + { + "epoch": 6.66, + "learning_rate": 1.55525052026625e-05, + "loss": 0.1233, + "step": 21581 + }, + { + "epoch": 6.67, + "learning_rate": 1.555208925581875e-05, + "loss": 0.1285, + "step": 21582 + }, + { + "epoch": 6.67, + "learning_rate": 1.5551673295088205e-05, + "loss": 0.1161, + "step": 21583 + }, + { + "epoch": 6.67, + "learning_rate": 1.5551257320471917e-05, + "loss": 0.1201, + "step": 21584 + }, + { + "epoch": 6.67, + "learning_rate": 1.5550841331970924e-05, + "loss": 0.1478, + "step": 21585 + }, + { + "epoch": 6.67, + "learning_rate": 1.555042532958626e-05, + "loss": 0.1232, + "step": 21586 + }, + { + "epoch": 6.67, + "learning_rate": 1.5550009313318974e-05, + "loss": 0.1343, + "step": 21587 + }, + { + "epoch": 6.67, + "learning_rate": 1.55495932831701e-05, + "loss": 0.1345, + "step": 21588 + }, + { + "epoch": 6.67, + "learning_rate": 1.554917723914068e-05, + "loss": 0.1291, + "step": 21589 + }, + { + "epoch": 6.67, + "learning_rate": 1.5548761181231758e-05, + "loss": 0.1235, + "step": 21590 + }, + { + "epoch": 6.67, + "learning_rate": 1.5548345109444373e-05, + "loss": 0.1214, + "step": 21591 + }, + { + "epoch": 6.67, + "learning_rate": 1.5547929023779566e-05, + "loss": 0.1266, + "step": 21592 + }, + { + "epoch": 6.67, + "learning_rate": 1.5547512924238373e-05, + "loss": 0.1259, + "step": 21593 + }, + { + "epoch": 6.67, + "learning_rate": 1.554709681082184e-05, + "loss": 0.1253, + "step": 21594 + }, + { + "epoch": 6.67, + "learning_rate": 1.5546680683531004e-05, + "loss": 0.1302, + "step": 21595 + }, + { + "epoch": 6.67, + "learning_rate": 1.5546264542366908e-05, + "loss": 0.1203, + "step": 21596 + }, + { + "epoch": 6.67, + "learning_rate": 1.5545848387330597e-05, + "loss": 0.1299, + "step": 21597 + }, + { + "epoch": 6.67, + "learning_rate": 1.5545432218423108e-05, + "loss": 0.1331, + "step": 21598 + }, + { + "epoch": 6.67, + "learning_rate": 1.5545016035645476e-05, + "loss": 0.1232, + "step": 21599 + }, + { + "epoch": 6.67, + "learning_rate": 1.554459983899875e-05, + "loss": 0.1193, + "step": 21600 + }, + { + "epoch": 6.67, + "learning_rate": 1.554418362848397e-05, + "loss": 0.1197, + "step": 21601 + }, + { + "epoch": 6.67, + "learning_rate": 1.5543767404102172e-05, + "loss": 0.124, + "step": 21602 + }, + { + "epoch": 6.67, + "learning_rate": 1.5543351165854405e-05, + "loss": 0.123, + "step": 21603 + }, + { + "epoch": 6.67, + "learning_rate": 1.5542934913741704e-05, + "loss": 0.1311, + "step": 21604 + }, + { + "epoch": 6.67, + "learning_rate": 1.554251864776511e-05, + "loss": 0.1359, + "step": 21605 + }, + { + "epoch": 6.67, + "learning_rate": 1.5542102367925668e-05, + "loss": 0.1099, + "step": 21606 + }, + { + "epoch": 6.67, + "learning_rate": 1.5541686074224415e-05, + "loss": 0.1168, + "step": 21607 + }, + { + "epoch": 6.67, + "learning_rate": 1.5541269766662397e-05, + "loss": 0.1327, + "step": 21608 + }, + { + "epoch": 6.67, + "learning_rate": 1.554085344524065e-05, + "loss": 0.1248, + "step": 21609 + }, + { + "epoch": 6.67, + "learning_rate": 1.5540437109960224e-05, + "loss": 0.1166, + "step": 21610 + }, + { + "epoch": 6.67, + "learning_rate": 1.5540020760822146e-05, + "loss": 0.1255, + "step": 21611 + }, + { + "epoch": 6.67, + "learning_rate": 1.5539604397827472e-05, + "loss": 0.1251, + "step": 21612 + }, + { + "epoch": 6.67, + "learning_rate": 1.5539188020977234e-05, + "loss": 0.1341, + "step": 21613 + }, + { + "epoch": 6.67, + "learning_rate": 1.5538771630272474e-05, + "loss": 0.1171, + "step": 21614 + }, + { + "epoch": 6.68, + "learning_rate": 1.553835522571424e-05, + "loss": 0.131, + "step": 21615 + }, + { + "epoch": 6.68, + "learning_rate": 1.553793880730357e-05, + "loss": 0.1271, + "step": 21616 + }, + { + "epoch": 6.68, + "learning_rate": 1.55375223750415e-05, + "loss": 0.1222, + "step": 21617 + }, + { + "epoch": 6.68, + "learning_rate": 1.5537105928929084e-05, + "loss": 0.1159, + "step": 21618 + }, + { + "epoch": 6.68, + "learning_rate": 1.553668946896735e-05, + "loss": 0.1225, + "step": 21619 + }, + { + "epoch": 6.68, + "learning_rate": 1.553627299515735e-05, + "loss": 0.1283, + "step": 21620 + }, + { + "epoch": 6.68, + "learning_rate": 1.5535856507500117e-05, + "loss": 0.12, + "step": 21621 + }, + { + "epoch": 6.68, + "learning_rate": 1.55354400059967e-05, + "loss": 0.136, + "step": 21622 + }, + { + "epoch": 6.68, + "learning_rate": 1.5535023490648137e-05, + "loss": 0.1418, + "step": 21623 + }, + { + "epoch": 6.68, + "learning_rate": 1.5534606961455475e-05, + "loss": 0.1249, + "step": 21624 + }, + { + "epoch": 6.68, + "learning_rate": 1.5534190418419745e-05, + "loss": 0.1163, + "step": 21625 + }, + { + "epoch": 6.68, + "learning_rate": 1.5533773861541998e-05, + "loss": 0.1117, + "step": 21626 + }, + { + "epoch": 6.68, + "learning_rate": 1.5533357290823275e-05, + "loss": 0.119, + "step": 21627 + }, + { + "epoch": 6.68, + "learning_rate": 1.5532940706264614e-05, + "loss": 0.1179, + "step": 21628 + }, + { + "epoch": 6.68, + "learning_rate": 1.553252410786706e-05, + "loss": 0.1263, + "step": 21629 + }, + { + "epoch": 6.68, + "learning_rate": 1.5532107495631655e-05, + "loss": 0.1326, + "step": 21630 + }, + { + "epoch": 6.68, + "learning_rate": 1.5531690869559438e-05, + "loss": 0.119, + "step": 21631 + }, + { + "epoch": 6.68, + "learning_rate": 1.5531274229651452e-05, + "loss": 0.1288, + "step": 21632 + }, + { + "epoch": 6.68, + "learning_rate": 1.5530857575908746e-05, + "loss": 0.1229, + "step": 21633 + }, + { + "epoch": 6.68, + "learning_rate": 1.553044090833235e-05, + "loss": 0.1299, + "step": 21634 + }, + { + "epoch": 6.68, + "learning_rate": 1.5530024226923316e-05, + "loss": 0.1178, + "step": 21635 + }, + { + "epoch": 6.68, + "learning_rate": 1.5529607531682683e-05, + "loss": 0.1242, + "step": 21636 + }, + { + "epoch": 6.68, + "learning_rate": 1.5529190822611493e-05, + "loss": 0.1238, + "step": 21637 + }, + { + "epoch": 6.68, + "learning_rate": 1.552877409971079e-05, + "loss": 0.1201, + "step": 21638 + }, + { + "epoch": 6.68, + "learning_rate": 1.5528357362981608e-05, + "loss": 0.1352, + "step": 21639 + }, + { + "epoch": 6.68, + "learning_rate": 1.5527940612425004e-05, + "loss": 0.124, + "step": 21640 + }, + { + "epoch": 6.68, + "learning_rate": 1.5527523848042007e-05, + "loss": 0.128, + "step": 21641 + }, + { + "epoch": 6.68, + "learning_rate": 1.5527107069833663e-05, + "loss": 0.1307, + "step": 21642 + }, + { + "epoch": 6.68, + "learning_rate": 1.552669027780102e-05, + "loss": 0.122, + "step": 21643 + }, + { + "epoch": 6.68, + "learning_rate": 1.5526273471945122e-05, + "loss": 0.123, + "step": 21644 + }, + { + "epoch": 6.68, + "learning_rate": 1.5525856652266997e-05, + "loss": 0.1292, + "step": 21645 + }, + { + "epoch": 6.68, + "learning_rate": 1.55254398187677e-05, + "loss": 0.1082, + "step": 21646 + }, + { + "epoch": 6.69, + "learning_rate": 1.552502297144827e-05, + "loss": 0.1296, + "step": 21647 + }, + { + "epoch": 6.69, + "learning_rate": 1.552460611030975e-05, + "loss": 0.1172, + "step": 21648 + }, + { + "epoch": 6.69, + "learning_rate": 1.5524189235353183e-05, + "loss": 0.1328, + "step": 21649 + }, + { + "epoch": 6.69, + "learning_rate": 1.552377234657961e-05, + "loss": 0.1245, + "step": 21650 + }, + { + "epoch": 6.69, + "learning_rate": 1.5523355443990075e-05, + "loss": 0.1249, + "step": 21651 + }, + { + "epoch": 6.69, + "learning_rate": 1.5522938527585622e-05, + "loss": 0.1189, + "step": 21652 + }, + { + "epoch": 6.69, + "learning_rate": 1.552252159736729e-05, + "loss": 0.1195, + "step": 21653 + }, + { + "epoch": 6.69, + "learning_rate": 1.552210465333613e-05, + "loss": 0.1411, + "step": 21654 + }, + { + "epoch": 6.69, + "learning_rate": 1.552168769549317e-05, + "loss": 0.1239, + "step": 21655 + }, + { + "epoch": 6.69, + "learning_rate": 1.5521270723839467e-05, + "loss": 0.1244, + "step": 21656 + }, + { + "epoch": 6.69, + "learning_rate": 1.552085373837606e-05, + "loss": 0.1097, + "step": 21657 + }, + { + "epoch": 6.69, + "learning_rate": 1.552043673910399e-05, + "loss": 0.1236, + "step": 21658 + }, + { + "epoch": 6.69, + "learning_rate": 1.55200197260243e-05, + "loss": 0.1239, + "step": 21659 + }, + { + "epoch": 6.69, + "learning_rate": 1.5519602699138035e-05, + "loss": 0.1148, + "step": 21660 + }, + { + "epoch": 6.69, + "learning_rate": 1.5519185658446236e-05, + "loss": 0.1236, + "step": 21661 + }, + { + "epoch": 6.69, + "learning_rate": 1.551876860394995e-05, + "loss": 0.1208, + "step": 21662 + }, + { + "epoch": 6.69, + "learning_rate": 1.5518351535650212e-05, + "loss": 0.1267, + "step": 21663 + }, + { + "epoch": 6.69, + "learning_rate": 1.5517934453548073e-05, + "loss": 0.1209, + "step": 21664 + }, + { + "epoch": 6.69, + "learning_rate": 1.5517517357644573e-05, + "loss": 0.1285, + "step": 21665 + }, + { + "epoch": 6.69, + "learning_rate": 1.5517100247940758e-05, + "loss": 0.1227, + "step": 21666 + }, + { + "epoch": 6.69, + "learning_rate": 1.5516683124437665e-05, + "loss": 0.1157, + "step": 21667 + }, + { + "epoch": 6.69, + "learning_rate": 1.5516265987136344e-05, + "loss": 0.1312, + "step": 21668 + }, + { + "epoch": 6.69, + "learning_rate": 1.5515848836037836e-05, + "loss": 0.1117, + "step": 21669 + }, + { + "epoch": 6.69, + "learning_rate": 1.5515431671143183e-05, + "loss": 0.1319, + "step": 21670 + }, + { + "epoch": 6.69, + "learning_rate": 1.5515014492453427e-05, + "loss": 0.1263, + "step": 21671 + }, + { + "epoch": 6.69, + "learning_rate": 1.5514597299969617e-05, + "loss": 0.1168, + "step": 21672 + }, + { + "epoch": 6.69, + "learning_rate": 1.551418009369279e-05, + "loss": 0.1232, + "step": 21673 + }, + { + "epoch": 6.69, + "learning_rate": 1.5513762873623998e-05, + "loss": 0.1245, + "step": 21674 + }, + { + "epoch": 6.69, + "learning_rate": 1.551334563976428e-05, + "loss": 0.1227, + "step": 21675 + }, + { + "epoch": 6.69, + "learning_rate": 1.5512928392114674e-05, + "loss": 0.1192, + "step": 21676 + }, + { + "epoch": 6.69, + "learning_rate": 1.5512511130676233e-05, + "loss": 0.1249, + "step": 21677 + }, + { + "epoch": 6.69, + "learning_rate": 1.5512093855449993e-05, + "loss": 0.1252, + "step": 21678 + }, + { + "epoch": 6.69, + "learning_rate": 1.5511676566437e-05, + "loss": 0.1087, + "step": 21679 + }, + { + "epoch": 6.7, + "learning_rate": 1.55112592636383e-05, + "loss": 0.1216, + "step": 21680 + }, + { + "epoch": 6.7, + "learning_rate": 1.5510841947054934e-05, + "loss": 0.1226, + "step": 21681 + }, + { + "epoch": 6.7, + "learning_rate": 1.551042461668795e-05, + "loss": 0.1226, + "step": 21682 + }, + { + "epoch": 6.7, + "learning_rate": 1.551000727253839e-05, + "loss": 0.1198, + "step": 21683 + }, + { + "epoch": 6.7, + "learning_rate": 1.5509589914607292e-05, + "loss": 0.136, + "step": 21684 + }, + { + "epoch": 6.7, + "learning_rate": 1.550917254289571e-05, + "loss": 0.1137, + "step": 21685 + }, + { + "epoch": 6.7, + "learning_rate": 1.550875515740468e-05, + "loss": 0.1278, + "step": 21686 + }, + { + "epoch": 6.7, + "learning_rate": 1.5508337758135247e-05, + "loss": 0.1294, + "step": 21687 + }, + { + "epoch": 6.7, + "learning_rate": 1.5507920345088462e-05, + "loss": 0.1188, + "step": 21688 + }, + { + "epoch": 6.7, + "learning_rate": 1.5507502918265358e-05, + "loss": 0.1212, + "step": 21689 + }, + { + "epoch": 6.7, + "learning_rate": 1.5507085477666987e-05, + "loss": 0.1057, + "step": 21690 + }, + { + "epoch": 6.7, + "learning_rate": 1.550666802329439e-05, + "loss": 0.143, + "step": 21691 + }, + { + "epoch": 6.7, + "learning_rate": 1.5506250555148613e-05, + "loss": 0.1322, + "step": 21692 + }, + { + "epoch": 6.7, + "learning_rate": 1.5505833073230698e-05, + "loss": 0.1305, + "step": 21693 + }, + { + "epoch": 6.7, + "learning_rate": 1.550541557754169e-05, + "loss": 0.1206, + "step": 21694 + }, + { + "epoch": 6.7, + "learning_rate": 1.5504998068082637e-05, + "loss": 0.1246, + "step": 21695 + }, + { + "epoch": 6.7, + "learning_rate": 1.5504580544854576e-05, + "loss": 0.1236, + "step": 21696 + }, + { + "epoch": 6.7, + "learning_rate": 1.5504163007858557e-05, + "loss": 0.1256, + "step": 21697 + }, + { + "epoch": 6.7, + "learning_rate": 1.550374545709562e-05, + "loss": 0.1147, + "step": 21698 + }, + { + "epoch": 6.7, + "learning_rate": 1.5503327892566814e-05, + "loss": 0.1261, + "step": 21699 + }, + { + "epoch": 6.7, + "learning_rate": 1.5502910314273182e-05, + "loss": 0.1374, + "step": 21700 + }, + { + "epoch": 6.7, + "learning_rate": 1.5502492722215765e-05, + "loss": 0.1223, + "step": 21701 + }, + { + "epoch": 6.7, + "learning_rate": 1.5502075116395612e-05, + "loss": 0.1241, + "step": 21702 + }, + { + "epoch": 6.7, + "learning_rate": 1.5501657496813765e-05, + "loss": 0.1287, + "step": 21703 + }, + { + "epoch": 6.7, + "learning_rate": 1.5501239863471268e-05, + "loss": 0.1245, + "step": 21704 + }, + { + "epoch": 6.7, + "learning_rate": 1.550082221636917e-05, + "loss": 0.1261, + "step": 21705 + }, + { + "epoch": 6.7, + "learning_rate": 1.550040455550851e-05, + "loss": 0.1267, + "step": 21706 + }, + { + "epoch": 6.7, + "learning_rate": 1.5499986880890334e-05, + "loss": 0.1277, + "step": 21707 + }, + { + "epoch": 6.7, + "learning_rate": 1.549956919251569e-05, + "loss": 0.1132, + "step": 21708 + }, + { + "epoch": 6.7, + "learning_rate": 1.549915149038562e-05, + "loss": 0.1195, + "step": 21709 + }, + { + "epoch": 6.7, + "learning_rate": 1.5498733774501165e-05, + "loss": 0.1309, + "step": 21710 + }, + { + "epoch": 6.7, + "learning_rate": 1.5498316044863382e-05, + "loss": 0.121, + "step": 21711 + }, + { + "epoch": 6.71, + "learning_rate": 1.54978983014733e-05, + "loss": 0.1299, + "step": 21712 + }, + { + "epoch": 6.71, + "learning_rate": 1.5497480544331975e-05, + "loss": 0.1341, + "step": 21713 + }, + { + "epoch": 6.71, + "learning_rate": 1.549706277344045e-05, + "loss": 0.1279, + "step": 21714 + }, + { + "epoch": 6.71, + "learning_rate": 1.5496644988799764e-05, + "loss": 0.1168, + "step": 21715 + }, + { + "epoch": 6.71, + "learning_rate": 1.549622719041097e-05, + "loss": 0.1273, + "step": 21716 + }, + { + "epoch": 6.71, + "learning_rate": 1.549580937827511e-05, + "loss": 0.139, + "step": 21717 + }, + { + "epoch": 6.71, + "learning_rate": 1.5495391552393224e-05, + "loss": 0.1278, + "step": 21718 + }, + { + "epoch": 6.71, + "learning_rate": 1.5494973712766366e-05, + "loss": 0.1258, + "step": 21719 + }, + { + "epoch": 6.71, + "learning_rate": 1.5494555859395575e-05, + "loss": 0.1142, + "step": 21720 + }, + { + "epoch": 6.71, + "learning_rate": 1.5494137992281895e-05, + "loss": 0.1263, + "step": 21721 + }, + { + "epoch": 6.71, + "learning_rate": 1.5493720111426376e-05, + "loss": 0.128, + "step": 21722 + }, + { + "epoch": 6.71, + "learning_rate": 1.5493302216830062e-05, + "loss": 0.1197, + "step": 21723 + }, + { + "epoch": 6.71, + "learning_rate": 1.5492884308493995e-05, + "loss": 0.1237, + "step": 21724 + }, + { + "epoch": 6.71, + "learning_rate": 1.5492466386419227e-05, + "loss": 0.1261, + "step": 21725 + }, + { + "epoch": 6.71, + "learning_rate": 1.5492048450606794e-05, + "loss": 0.1177, + "step": 21726 + }, + { + "epoch": 6.71, + "learning_rate": 1.5491630501057747e-05, + "loss": 0.1319, + "step": 21727 + }, + { + "epoch": 6.71, + "learning_rate": 1.5491212537773132e-05, + "loss": 0.1315, + "step": 21728 + }, + { + "epoch": 6.71, + "learning_rate": 1.5490794560753993e-05, + "loss": 0.116, + "step": 21729 + }, + { + "epoch": 6.71, + "learning_rate": 1.5490376570001373e-05, + "loss": 0.1221, + "step": 21730 + }, + { + "epoch": 6.71, + "learning_rate": 1.5489958565516324e-05, + "loss": 0.1217, + "step": 21731 + }, + { + "epoch": 6.71, + "learning_rate": 1.5489540547299884e-05, + "loss": 0.1367, + "step": 21732 + }, + { + "epoch": 6.71, + "learning_rate": 1.54891225153531e-05, + "loss": 0.1173, + "step": 21733 + }, + { + "epoch": 6.71, + "learning_rate": 1.5488704469677025e-05, + "loss": 0.134, + "step": 21734 + }, + { + "epoch": 6.71, + "learning_rate": 1.5488286410272694e-05, + "loss": 0.1247, + "step": 21735 + }, + { + "epoch": 6.71, + "learning_rate": 1.548786833714116e-05, + "loss": 0.115, + "step": 21736 + }, + { + "epoch": 6.71, + "learning_rate": 1.5487450250283467e-05, + "loss": 0.1225, + "step": 21737 + }, + { + "epoch": 6.71, + "learning_rate": 1.548703214970066e-05, + "loss": 0.1222, + "step": 21738 + }, + { + "epoch": 6.71, + "learning_rate": 1.5486614035393783e-05, + "loss": 0.125, + "step": 21739 + }, + { + "epoch": 6.71, + "learning_rate": 1.5486195907363883e-05, + "loss": 0.122, + "step": 21740 + }, + { + "epoch": 6.71, + "learning_rate": 1.5485777765612007e-05, + "loss": 0.1278, + "step": 21741 + }, + { + "epoch": 6.71, + "learning_rate": 1.5485359610139205e-05, + "loss": 0.1211, + "step": 21742 + }, + { + "epoch": 6.71, + "learning_rate": 1.5484941440946515e-05, + "loss": 0.1196, + "step": 21743 + }, + { + "epoch": 6.72, + "learning_rate": 1.548452325803498e-05, + "loss": 0.1206, + "step": 21744 + }, + { + "epoch": 6.72, + "learning_rate": 1.548410506140566e-05, + "loss": 0.1302, + "step": 21745 + }, + { + "epoch": 6.72, + "learning_rate": 1.5483686851059593e-05, + "loss": 0.1271, + "step": 21746 + }, + { + "epoch": 6.72, + "learning_rate": 1.5483268626997823e-05, + "loss": 0.1317, + "step": 21747 + }, + { + "epoch": 6.72, + "learning_rate": 1.5482850389221397e-05, + "loss": 0.1202, + "step": 21748 + }, + { + "epoch": 6.72, + "learning_rate": 1.548243213773136e-05, + "loss": 0.1249, + "step": 21749 + }, + { + "epoch": 6.72, + "learning_rate": 1.5482013872528765e-05, + "loss": 0.1254, + "step": 21750 + }, + { + "epoch": 6.72, + "learning_rate": 1.5481595593614653e-05, + "loss": 0.1144, + "step": 21751 + }, + { + "epoch": 6.72, + "learning_rate": 1.548117730099007e-05, + "loss": 0.1203, + "step": 21752 + }, + { + "epoch": 6.72, + "learning_rate": 1.548075899465606e-05, + "loss": 0.1362, + "step": 21753 + }, + { + "epoch": 6.72, + "learning_rate": 1.5480340674613673e-05, + "loss": 0.1213, + "step": 21754 + }, + { + "epoch": 6.72, + "learning_rate": 1.5479922340863955e-05, + "loss": 0.1285, + "step": 21755 + }, + { + "epoch": 6.72, + "learning_rate": 1.5479503993407953e-05, + "loss": 0.1281, + "step": 21756 + }, + { + "epoch": 6.72, + "learning_rate": 1.547908563224671e-05, + "loss": 0.1199, + "step": 21757 + }, + { + "epoch": 6.72, + "learning_rate": 1.547866725738128e-05, + "loss": 0.1343, + "step": 21758 + }, + { + "epoch": 6.72, + "learning_rate": 1.5478248868812697e-05, + "loss": 0.1262, + "step": 21759 + }, + { + "epoch": 6.72, + "learning_rate": 1.547783046654202e-05, + "loss": 0.1282, + "step": 21760 + }, + { + "epoch": 6.72, + "learning_rate": 1.5477412050570288e-05, + "loss": 0.1149, + "step": 21761 + }, + { + "epoch": 6.72, + "learning_rate": 1.5476993620898547e-05, + "loss": 0.1255, + "step": 21762 + }, + { + "epoch": 6.72, + "learning_rate": 1.5476575177527845e-05, + "loss": 0.129, + "step": 21763 + }, + { + "epoch": 6.72, + "learning_rate": 1.5476156720459234e-05, + "loss": 0.1131, + "step": 21764 + }, + { + "epoch": 6.72, + "learning_rate": 1.5475738249693755e-05, + "loss": 0.1297, + "step": 21765 + }, + { + "epoch": 6.72, + "learning_rate": 1.5475319765232454e-05, + "loss": 0.125, + "step": 21766 + }, + { + "epoch": 6.72, + "learning_rate": 1.5474901267076382e-05, + "loss": 0.12, + "step": 21767 + }, + { + "epoch": 6.72, + "learning_rate": 1.5474482755226583e-05, + "loss": 0.1218, + "step": 21768 + }, + { + "epoch": 6.72, + "learning_rate": 1.5474064229684103e-05, + "loss": 0.1308, + "step": 21769 + }, + { + "epoch": 6.72, + "learning_rate": 1.5473645690449993e-05, + "loss": 0.1204, + "step": 21770 + }, + { + "epoch": 6.72, + "learning_rate": 1.547322713752529e-05, + "loss": 0.1234, + "step": 21771 + }, + { + "epoch": 6.72, + "learning_rate": 1.5472808570911052e-05, + "loss": 0.1171, + "step": 21772 + }, + { + "epoch": 6.72, + "learning_rate": 1.5472389990608323e-05, + "loss": 0.1215, + "step": 21773 + }, + { + "epoch": 6.72, + "learning_rate": 1.5471971396618147e-05, + "loss": 0.1163, + "step": 21774 + }, + { + "epoch": 6.72, + "learning_rate": 1.5471552788941572e-05, + "loss": 0.1348, + "step": 21775 + }, + { + "epoch": 6.72, + "learning_rate": 1.5471134167579646e-05, + "loss": 0.1195, + "step": 21776 + }, + { + "epoch": 6.73, + "learning_rate": 1.5470715532533417e-05, + "loss": 0.13, + "step": 21777 + }, + { + "epoch": 6.73, + "learning_rate": 1.547029688380393e-05, + "loss": 0.1368, + "step": 21778 + }, + { + "epoch": 6.73, + "learning_rate": 1.5469878221392233e-05, + "loss": 0.1192, + "step": 21779 + }, + { + "epoch": 6.73, + "learning_rate": 1.546945954529937e-05, + "loss": 0.1321, + "step": 21780 + }, + { + "epoch": 6.73, + "learning_rate": 1.5469040855526394e-05, + "loss": 0.1158, + "step": 21781 + }, + { + "epoch": 6.73, + "learning_rate": 1.5468622152074347e-05, + "loss": 0.123, + "step": 21782 + }, + { + "epoch": 6.73, + "learning_rate": 1.546820343494428e-05, + "loss": 0.1258, + "step": 21783 + }, + { + "epoch": 6.73, + "learning_rate": 1.546778470413724e-05, + "loss": 0.1251, + "step": 21784 + }, + { + "epoch": 6.73, + "learning_rate": 1.5467365959654273e-05, + "loss": 0.1154, + "step": 21785 + }, + { + "epoch": 6.73, + "learning_rate": 1.5466947201496424e-05, + "loss": 0.1216, + "step": 21786 + }, + { + "epoch": 6.73, + "learning_rate": 1.5466528429664745e-05, + "loss": 0.1211, + "step": 21787 + }, + { + "epoch": 6.73, + "learning_rate": 1.5466109644160285e-05, + "loss": 0.1287, + "step": 21788 + }, + { + "epoch": 6.73, + "learning_rate": 1.5465690844984082e-05, + "loss": 0.1195, + "step": 21789 + }, + { + "epoch": 6.73, + "learning_rate": 1.546527203213719e-05, + "loss": 0.1226, + "step": 21790 + }, + { + "epoch": 6.73, + "learning_rate": 1.546485320562066e-05, + "loss": 0.1301, + "step": 21791 + }, + { + "epoch": 6.73, + "learning_rate": 1.546443436543553e-05, + "loss": 0.1267, + "step": 21792 + }, + { + "epoch": 6.73, + "learning_rate": 1.5464015511582856e-05, + "loss": 0.1262, + "step": 21793 + }, + { + "epoch": 6.73, + "learning_rate": 1.546359664406368e-05, + "loss": 0.1289, + "step": 21794 + }, + { + "epoch": 6.73, + "learning_rate": 1.5463177762879057e-05, + "loss": 0.1222, + "step": 21795 + }, + { + "epoch": 6.73, + "learning_rate": 1.546275886803003e-05, + "loss": 0.1297, + "step": 21796 + }, + { + "epoch": 6.73, + "learning_rate": 1.5462339959517638e-05, + "loss": 0.1337, + "step": 21797 + }, + { + "epoch": 6.73, + "learning_rate": 1.5461921037342948e-05, + "loss": 0.1182, + "step": 21798 + }, + { + "epoch": 6.73, + "learning_rate": 1.546150210150699e-05, + "loss": 0.1279, + "step": 21799 + }, + { + "epoch": 6.73, + "learning_rate": 1.546108315201082e-05, + "loss": 0.123, + "step": 21800 + }, + { + "epoch": 6.73, + "learning_rate": 1.546066418885549e-05, + "loss": 0.1253, + "step": 21801 + }, + { + "epoch": 6.73, + "learning_rate": 1.546024521204204e-05, + "loss": 0.1237, + "step": 21802 + }, + { + "epoch": 6.73, + "learning_rate": 1.5459826221571522e-05, + "loss": 0.1207, + "step": 21803 + }, + { + "epoch": 6.73, + "learning_rate": 1.5459407217444978e-05, + "loss": 0.1318, + "step": 21804 + }, + { + "epoch": 6.73, + "learning_rate": 1.5458988199663466e-05, + "loss": 0.1228, + "step": 21805 + }, + { + "epoch": 6.73, + "learning_rate": 1.5458569168228028e-05, + "loss": 0.1246, + "step": 21806 + }, + { + "epoch": 6.73, + "learning_rate": 1.5458150123139712e-05, + "loss": 0.1264, + "step": 21807 + }, + { + "epoch": 6.73, + "learning_rate": 1.5457731064399567e-05, + "loss": 0.1175, + "step": 21808 + }, + { + "epoch": 6.74, + "learning_rate": 1.5457311992008642e-05, + "loss": 0.1169, + "step": 21809 + }, + { + "epoch": 6.74, + "learning_rate": 1.545689290596798e-05, + "loss": 0.1201, + "step": 21810 + }, + { + "epoch": 6.74, + "learning_rate": 1.545647380627864e-05, + "loss": 0.1257, + "step": 21811 + }, + { + "epoch": 6.74, + "learning_rate": 1.545605469294166e-05, + "loss": 0.1202, + "step": 21812 + }, + { + "epoch": 6.74, + "learning_rate": 1.5455635565958095e-05, + "loss": 0.121, + "step": 21813 + }, + { + "epoch": 6.74, + "learning_rate": 1.5455216425328986e-05, + "loss": 0.13, + "step": 21814 + }, + { + "epoch": 6.74, + "learning_rate": 1.545479727105539e-05, + "loss": 0.1221, + "step": 21815 + }, + { + "epoch": 6.74, + "learning_rate": 1.545437810313835e-05, + "loss": 0.1156, + "step": 21816 + }, + { + "epoch": 6.74, + "learning_rate": 1.5453958921578914e-05, + "loss": 0.1265, + "step": 21817 + }, + { + "epoch": 6.74, + "learning_rate": 1.5453539726378136e-05, + "loss": 0.1265, + "step": 21818 + }, + { + "epoch": 6.74, + "learning_rate": 1.5453120517537054e-05, + "loss": 0.1378, + "step": 21819 + }, + { + "epoch": 6.74, + "learning_rate": 1.545270129505673e-05, + "loss": 0.1312, + "step": 21820 + }, + { + "epoch": 6.74, + "learning_rate": 1.54522820589382e-05, + "loss": 0.1232, + "step": 21821 + }, + { + "epoch": 6.74, + "learning_rate": 1.545186280918252e-05, + "loss": 0.1323, + "step": 21822 + }, + { + "epoch": 6.74, + "learning_rate": 1.5451443545790735e-05, + "loss": 0.1203, + "step": 21823 + }, + { + "epoch": 6.74, + "learning_rate": 1.54510242687639e-05, + "loss": 0.127, + "step": 21824 + }, + { + "epoch": 6.74, + "learning_rate": 1.5450604978103058e-05, + "loss": 0.1263, + "step": 21825 + }, + { + "epoch": 6.74, + "learning_rate": 1.5450185673809253e-05, + "loss": 0.1235, + "step": 21826 + }, + { + "epoch": 6.74, + "learning_rate": 1.5449766355883545e-05, + "loss": 0.1415, + "step": 21827 + }, + { + "epoch": 6.74, + "learning_rate": 1.5449347024326976e-05, + "loss": 0.1419, + "step": 21828 + }, + { + "epoch": 6.74, + "learning_rate": 1.5448927679140596e-05, + "loss": 0.1181, + "step": 21829 + }, + { + "epoch": 6.74, + "learning_rate": 1.5448508320325456e-05, + "loss": 0.114, + "step": 21830 + }, + { + "epoch": 6.74, + "learning_rate": 1.54480889478826e-05, + "loss": 0.1336, + "step": 21831 + }, + { + "epoch": 6.74, + "learning_rate": 1.544766956181308e-05, + "loss": 0.1364, + "step": 21832 + }, + { + "epoch": 6.74, + "learning_rate": 1.544725016211795e-05, + "loss": 0.1226, + "step": 21833 + }, + { + "epoch": 6.74, + "learning_rate": 1.5446830748798248e-05, + "loss": 0.1312, + "step": 21834 + }, + { + "epoch": 6.74, + "learning_rate": 1.544641132185503e-05, + "loss": 0.1273, + "step": 21835 + }, + { + "epoch": 6.74, + "learning_rate": 1.5445991881289344e-05, + "loss": 0.1222, + "step": 21836 + }, + { + "epoch": 6.74, + "learning_rate": 1.5445572427102242e-05, + "loss": 0.1244, + "step": 21837 + }, + { + "epoch": 6.74, + "learning_rate": 1.544515295929477e-05, + "loss": 0.1292, + "step": 21838 + }, + { + "epoch": 6.74, + "learning_rate": 1.5444733477867974e-05, + "loss": 0.1234, + "step": 21839 + }, + { + "epoch": 6.74, + "learning_rate": 1.5444313982822906e-05, + "loss": 0.1343, + "step": 21840 + }, + { + "epoch": 6.74, + "learning_rate": 1.5443894474160617e-05, + "loss": 0.125, + "step": 21841 + }, + { + "epoch": 6.75, + "learning_rate": 1.544347495188216e-05, + "loss": 0.1186, + "step": 21842 + }, + { + "epoch": 6.75, + "learning_rate": 1.544305541598857e-05, + "loss": 0.1179, + "step": 21843 + }, + { + "epoch": 6.75, + "learning_rate": 1.544263586648091e-05, + "loss": 0.1451, + "step": 21844 + }, + { + "epoch": 6.75, + "learning_rate": 1.544221630336023e-05, + "loss": 0.1154, + "step": 21845 + }, + { + "epoch": 6.75, + "learning_rate": 1.5441796726627567e-05, + "loss": 0.1222, + "step": 21846 + }, + { + "epoch": 6.75, + "learning_rate": 1.5441377136283984e-05, + "loss": 0.127, + "step": 21847 + }, + { + "epoch": 6.75, + "learning_rate": 1.544095753233052e-05, + "loss": 0.1248, + "step": 21848 + }, + { + "epoch": 6.75, + "learning_rate": 1.5440537914768227e-05, + "loss": 0.1308, + "step": 21849 + }, + { + "epoch": 6.75, + "learning_rate": 1.544011828359816e-05, + "loss": 0.1323, + "step": 21850 + }, + { + "epoch": 6.75, + "learning_rate": 1.5439698638821365e-05, + "loss": 0.1149, + "step": 21851 + }, + { + "epoch": 6.75, + "learning_rate": 1.543927898043889e-05, + "loss": 0.1302, + "step": 21852 + }, + { + "epoch": 6.75, + "learning_rate": 1.5438859308451788e-05, + "loss": 0.1305, + "step": 21853 + }, + { + "epoch": 6.75, + "learning_rate": 1.5438439622861105e-05, + "loss": 0.1219, + "step": 21854 + }, + { + "epoch": 6.75, + "learning_rate": 1.5438019923667896e-05, + "loss": 0.1228, + "step": 21855 + }, + { + "epoch": 6.75, + "learning_rate": 1.5437600210873205e-05, + "loss": 0.1317, + "step": 21856 + }, + { + "epoch": 6.75, + "learning_rate": 1.5437180484478082e-05, + "loss": 0.1363, + "step": 21857 + }, + { + "epoch": 6.75, + "learning_rate": 1.543676074448358e-05, + "loss": 0.1293, + "step": 21858 + }, + { + "epoch": 6.75, + "learning_rate": 1.5436340990890752e-05, + "loss": 0.1234, + "step": 21859 + }, + { + "epoch": 6.75, + "learning_rate": 1.543592122370064e-05, + "loss": 0.1201, + "step": 21860 + }, + { + "epoch": 6.75, + "learning_rate": 1.5435501442914298e-05, + "loss": 0.1098, + "step": 21861 + }, + { + "epoch": 6.75, + "learning_rate": 1.5435081648532774e-05, + "loss": 0.1242, + "step": 21862 + }, + { + "epoch": 6.75, + "learning_rate": 1.5434661840557123e-05, + "loss": 0.1199, + "step": 21863 + }, + { + "epoch": 6.75, + "learning_rate": 1.543424201898839e-05, + "loss": 0.1213, + "step": 21864 + }, + { + "epoch": 6.75, + "learning_rate": 1.543382218382762e-05, + "loss": 0.129, + "step": 21865 + }, + { + "epoch": 6.75, + "learning_rate": 1.543340233507588e-05, + "loss": 0.1279, + "step": 21866 + }, + { + "epoch": 6.75, + "learning_rate": 1.5432982472734208e-05, + "loss": 0.1237, + "step": 21867 + }, + { + "epoch": 6.75, + "learning_rate": 1.5432562596803648e-05, + "loss": 0.1268, + "step": 21868 + }, + { + "epoch": 6.75, + "learning_rate": 1.5432142707285266e-05, + "loss": 0.1266, + "step": 21869 + }, + { + "epoch": 6.75, + "learning_rate": 1.54317228041801e-05, + "loss": 0.1292, + "step": 21870 + }, + { + "epoch": 6.75, + "learning_rate": 1.5431302887489207e-05, + "loss": 0.1134, + "step": 21871 + }, + { + "epoch": 6.75, + "learning_rate": 1.5430882957213637e-05, + "loss": 0.1252, + "step": 21872 + }, + { + "epoch": 6.75, + "learning_rate": 1.5430463013354433e-05, + "loss": 0.116, + "step": 21873 + }, + { + "epoch": 6.76, + "learning_rate": 1.5430043055912652e-05, + "loss": 0.1213, + "step": 21874 + }, + { + "epoch": 6.76, + "learning_rate": 1.5429623084889346e-05, + "loss": 0.1293, + "step": 21875 + }, + { + "epoch": 6.76, + "learning_rate": 1.542920310028556e-05, + "loss": 0.1229, + "step": 21876 + }, + { + "epoch": 6.76, + "learning_rate": 1.5428783102102345e-05, + "loss": 0.1214, + "step": 21877 + }, + { + "epoch": 6.76, + "learning_rate": 1.5428363090340758e-05, + "loss": 0.1194, + "step": 21878 + }, + { + "epoch": 6.76, + "learning_rate": 1.542794306500184e-05, + "loss": 0.131, + "step": 21879 + }, + { + "epoch": 6.76, + "learning_rate": 1.542752302608665e-05, + "loss": 0.123, + "step": 21880 + }, + { + "epoch": 6.76, + "learning_rate": 1.5427102973596233e-05, + "loss": 0.1269, + "step": 21881 + }, + { + "epoch": 6.76, + "learning_rate": 1.5426682907531642e-05, + "loss": 0.14, + "step": 21882 + }, + { + "epoch": 6.76, + "learning_rate": 1.5426262827893927e-05, + "loss": 0.1236, + "step": 21883 + }, + { + "epoch": 6.76, + "learning_rate": 1.542584273468414e-05, + "loss": 0.1246, + "step": 21884 + }, + { + "epoch": 6.76, + "learning_rate": 1.542542262790333e-05, + "loss": 0.1207, + "step": 21885 + }, + { + "epoch": 6.76, + "learning_rate": 1.5425002507552548e-05, + "loss": 0.1227, + "step": 21886 + }, + { + "epoch": 6.76, + "learning_rate": 1.542458237363285e-05, + "loss": 0.126, + "step": 21887 + }, + { + "epoch": 6.76, + "learning_rate": 1.5424162226145278e-05, + "loss": 0.1207, + "step": 21888 + }, + { + "epoch": 6.76, + "learning_rate": 1.5423742065090885e-05, + "loss": 0.125, + "step": 21889 + }, + { + "epoch": 6.76, + "learning_rate": 1.5423321890470727e-05, + "loss": 0.1301, + "step": 21890 + }, + { + "epoch": 6.76, + "learning_rate": 1.5422901702285852e-05, + "loss": 0.1297, + "step": 21891 + }, + { + "epoch": 6.76, + "learning_rate": 1.5422481500537306e-05, + "loss": 0.1215, + "step": 21892 + }, + { + "epoch": 6.76, + "learning_rate": 1.5422061285226147e-05, + "loss": 0.1227, + "step": 21893 + }, + { + "epoch": 6.76, + "learning_rate": 1.5421641056353428e-05, + "loss": 0.1361, + "step": 21894 + }, + { + "epoch": 6.76, + "learning_rate": 1.5421220813920192e-05, + "loss": 0.131, + "step": 21895 + }, + { + "epoch": 6.76, + "learning_rate": 1.5420800557927497e-05, + "loss": 0.129, + "step": 21896 + }, + { + "epoch": 6.76, + "learning_rate": 1.542038028837639e-05, + "loss": 0.1202, + "step": 21897 + }, + { + "epoch": 6.76, + "learning_rate": 1.541996000526792e-05, + "loss": 0.1057, + "step": 21898 + }, + { + "epoch": 6.76, + "learning_rate": 1.5419539708603142e-05, + "loss": 0.1314, + "step": 21899 + }, + { + "epoch": 6.76, + "learning_rate": 1.541911939838311e-05, + "loss": 0.1264, + "step": 21900 + }, + { + "epoch": 6.76, + "learning_rate": 1.541869907460887e-05, + "loss": 0.1288, + "step": 21901 + }, + { + "epoch": 6.76, + "learning_rate": 1.5418278737281476e-05, + "loss": 0.1138, + "step": 21902 + }, + { + "epoch": 6.76, + "learning_rate": 1.541785838640198e-05, + "loss": 0.1135, + "step": 21903 + }, + { + "epoch": 6.76, + "learning_rate": 1.5417438021971428e-05, + "loss": 0.1143, + "step": 21904 + }, + { + "epoch": 6.76, + "learning_rate": 1.541701764399088e-05, + "loss": 0.1205, + "step": 21905 + }, + { + "epoch": 6.77, + "learning_rate": 1.541659725246138e-05, + "loss": 0.1246, + "step": 21906 + }, + { + "epoch": 6.77, + "learning_rate": 1.5416176847383982e-05, + "loss": 0.1262, + "step": 21907 + }, + { + "epoch": 6.77, + "learning_rate": 1.541575642875974e-05, + "loss": 0.1344, + "step": 21908 + }, + { + "epoch": 6.77, + "learning_rate": 1.5415335996589703e-05, + "loss": 0.1258, + "step": 21909 + }, + { + "epoch": 6.77, + "learning_rate": 1.5414915550874923e-05, + "loss": 0.1278, + "step": 21910 + }, + { + "epoch": 6.77, + "learning_rate": 1.541449509161645e-05, + "loss": 0.123, + "step": 21911 + }, + { + "epoch": 6.77, + "learning_rate": 1.5414074618815337e-05, + "loss": 0.1204, + "step": 21912 + }, + { + "epoch": 6.77, + "learning_rate": 1.5413654132472638e-05, + "loss": 0.125, + "step": 21913 + }, + { + "epoch": 6.77, + "learning_rate": 1.5413233632589403e-05, + "loss": 0.1399, + "step": 21914 + }, + { + "epoch": 6.77, + "learning_rate": 1.541281311916668e-05, + "loss": 0.1344, + "step": 21915 + }, + { + "epoch": 6.77, + "learning_rate": 1.5412392592205528e-05, + "loss": 0.1292, + "step": 21916 + }, + { + "epoch": 6.77, + "learning_rate": 1.541197205170699e-05, + "loss": 0.1422, + "step": 21917 + }, + { + "epoch": 6.77, + "learning_rate": 1.5411551497672127e-05, + "loss": 0.1303, + "step": 21918 + }, + { + "epoch": 6.77, + "learning_rate": 1.5411130930101984e-05, + "loss": 0.124, + "step": 21919 + }, + { + "epoch": 6.77, + "learning_rate": 1.541071034899762e-05, + "loss": 0.1412, + "step": 21920 + }, + { + "epoch": 6.77, + "learning_rate": 1.541028975436008e-05, + "loss": 0.13, + "step": 21921 + }, + { + "epoch": 6.77, + "learning_rate": 1.5409869146190417e-05, + "loss": 0.1429, + "step": 21922 + }, + { + "epoch": 6.77, + "learning_rate": 1.540944852448969e-05, + "loss": 0.1156, + "step": 21923 + }, + { + "epoch": 6.77, + "learning_rate": 1.540902788925894e-05, + "loss": 0.1344, + "step": 21924 + }, + { + "epoch": 6.77, + "learning_rate": 1.5408607240499226e-05, + "loss": 0.1198, + "step": 21925 + }, + { + "epoch": 6.77, + "learning_rate": 1.54081865782116e-05, + "loss": 0.129, + "step": 21926 + }, + { + "epoch": 6.77, + "learning_rate": 1.540776590239711e-05, + "loss": 0.1267, + "step": 21927 + }, + { + "epoch": 6.77, + "learning_rate": 1.5407345213056813e-05, + "loss": 0.1149, + "step": 21928 + }, + { + "epoch": 6.77, + "learning_rate": 1.540692451019176e-05, + "loss": 0.1251, + "step": 21929 + }, + { + "epoch": 6.77, + "learning_rate": 1.5406503793803002e-05, + "loss": 0.1343, + "step": 21930 + }, + { + "epoch": 6.77, + "learning_rate": 1.5406083063891592e-05, + "loss": 0.1305, + "step": 21931 + }, + { + "epoch": 6.77, + "learning_rate": 1.5405662320458585e-05, + "loss": 0.1296, + "step": 21932 + }, + { + "epoch": 6.77, + "learning_rate": 1.5405241563505028e-05, + "loss": 0.1285, + "step": 21933 + }, + { + "epoch": 6.77, + "learning_rate": 1.5404820793031974e-05, + "loss": 0.131, + "step": 21934 + }, + { + "epoch": 6.77, + "learning_rate": 1.5404400009040482e-05, + "loss": 0.1287, + "step": 21935 + }, + { + "epoch": 6.77, + "learning_rate": 1.5403979211531597e-05, + "loss": 0.1261, + "step": 21936 + }, + { + "epoch": 6.77, + "learning_rate": 1.5403558400506374e-05, + "loss": 0.1163, + "step": 21937 + }, + { + "epoch": 6.77, + "learning_rate": 1.5403137575965866e-05, + "loss": 0.1254, + "step": 21938 + }, + { + "epoch": 6.78, + "learning_rate": 1.5402716737911124e-05, + "loss": 0.1228, + "step": 21939 + }, + { + "epoch": 6.78, + "learning_rate": 1.5402295886343207e-05, + "loss": 0.1181, + "step": 21940 + }, + { + "epoch": 6.78, + "learning_rate": 1.540187502126316e-05, + "loss": 0.1227, + "step": 21941 + }, + { + "epoch": 6.78, + "learning_rate": 1.5401454142672037e-05, + "loss": 0.1347, + "step": 21942 + }, + { + "epoch": 6.78, + "learning_rate": 1.5401033250570897e-05, + "loss": 0.1288, + "step": 21943 + }, + { + "epoch": 6.78, + "learning_rate": 1.540061234496078e-05, + "loss": 0.1248, + "step": 21944 + }, + { + "epoch": 6.78, + "learning_rate": 1.5400191425842752e-05, + "loss": 0.1317, + "step": 21945 + }, + { + "epoch": 6.78, + "learning_rate": 1.539977049321786e-05, + "loss": 0.126, + "step": 21946 + }, + { + "epoch": 6.78, + "learning_rate": 1.5399349547087153e-05, + "loss": 0.1262, + "step": 21947 + }, + { + "epoch": 6.78, + "learning_rate": 1.5398928587451694e-05, + "loss": 0.1112, + "step": 21948 + }, + { + "epoch": 6.78, + "learning_rate": 1.5398507614312526e-05, + "loss": 0.123, + "step": 21949 + }, + { + "epoch": 6.78, + "learning_rate": 1.5398086627670705e-05, + "loss": 0.1286, + "step": 21950 + }, + { + "epoch": 6.78, + "learning_rate": 1.5397665627527287e-05, + "loss": 0.1158, + "step": 21951 + }, + { + "epoch": 6.78, + "learning_rate": 1.5397244613883323e-05, + "loss": 0.1305, + "step": 21952 + }, + { + "epoch": 6.78, + "learning_rate": 1.5396823586739866e-05, + "loss": 0.1255, + "step": 21953 + }, + { + "epoch": 6.78, + "learning_rate": 1.539640254609797e-05, + "loss": 0.127, + "step": 21954 + }, + { + "epoch": 6.78, + "learning_rate": 1.539598149195868e-05, + "loss": 0.1193, + "step": 21955 + }, + { + "epoch": 6.78, + "learning_rate": 1.5395560424323065e-05, + "loss": 0.1204, + "step": 21956 + }, + { + "epoch": 6.78, + "learning_rate": 1.5395139343192164e-05, + "loss": 0.1222, + "step": 21957 + }, + { + "epoch": 6.78, + "learning_rate": 1.5394718248567035e-05, + "loss": 0.1247, + "step": 21958 + }, + { + "epoch": 6.78, + "learning_rate": 1.5394297140448733e-05, + "loss": 0.1325, + "step": 21959 + }, + { + "epoch": 6.78, + "learning_rate": 1.539387601883831e-05, + "loss": 0.1194, + "step": 21960 + }, + { + "epoch": 6.78, + "learning_rate": 1.539345488373682e-05, + "loss": 0.1266, + "step": 21961 + }, + { + "epoch": 6.78, + "learning_rate": 1.5393033735145316e-05, + "loss": 0.1389, + "step": 21962 + }, + { + "epoch": 6.78, + "learning_rate": 1.5392612573064852e-05, + "loss": 0.1214, + "step": 21963 + }, + { + "epoch": 6.78, + "learning_rate": 1.539219139749648e-05, + "loss": 0.1336, + "step": 21964 + }, + { + "epoch": 6.78, + "learning_rate": 1.539177020844125e-05, + "loss": 0.1267, + "step": 21965 + }, + { + "epoch": 6.78, + "learning_rate": 1.5391349005900225e-05, + "loss": 0.1163, + "step": 21966 + }, + { + "epoch": 6.78, + "learning_rate": 1.5390927789874448e-05, + "loss": 0.1266, + "step": 21967 + }, + { + "epoch": 6.78, + "learning_rate": 1.5390506560364978e-05, + "loss": 0.1205, + "step": 21968 + }, + { + "epoch": 6.78, + "learning_rate": 1.539008531737287e-05, + "loss": 0.1229, + "step": 21969 + }, + { + "epoch": 6.78, + "learning_rate": 1.5389664060899173e-05, + "loss": 0.1141, + "step": 21970 + }, + { + "epoch": 6.79, + "learning_rate": 1.538924279094495e-05, + "loss": 0.1335, + "step": 21971 + }, + { + "epoch": 6.79, + "learning_rate": 1.5388821507511244e-05, + "loss": 0.1325, + "step": 21972 + }, + { + "epoch": 6.79, + "learning_rate": 1.5388400210599106e-05, + "loss": 0.121, + "step": 21973 + }, + { + "epoch": 6.79, + "learning_rate": 1.5387978900209603e-05, + "loss": 0.1408, + "step": 21974 + }, + { + "epoch": 6.79, + "learning_rate": 1.538755757634378e-05, + "loss": 0.1353, + "step": 21975 + }, + { + "epoch": 6.79, + "learning_rate": 1.5387136239002695e-05, + "loss": 0.1234, + "step": 21976 + }, + { + "epoch": 6.79, + "learning_rate": 1.5386714888187396e-05, + "loss": 0.1199, + "step": 21977 + }, + { + "epoch": 6.79, + "learning_rate": 1.538629352389894e-05, + "loss": 0.1264, + "step": 21978 + }, + { + "epoch": 6.79, + "learning_rate": 1.538587214613839e-05, + "loss": 0.1276, + "step": 21979 + }, + { + "epoch": 6.79, + "learning_rate": 1.5385450754906785e-05, + "loss": 0.1457, + "step": 21980 + }, + { + "epoch": 6.79, + "learning_rate": 1.5385029350205184e-05, + "loss": 0.1187, + "step": 21981 + }, + { + "epoch": 6.79, + "learning_rate": 1.5384607932034646e-05, + "loss": 0.1298, + "step": 21982 + }, + { + "epoch": 6.79, + "learning_rate": 1.538418650039622e-05, + "loss": 0.1242, + "step": 21983 + }, + { + "epoch": 6.79, + "learning_rate": 1.538376505529096e-05, + "loss": 0.1198, + "step": 21984 + }, + { + "epoch": 6.79, + "learning_rate": 1.5383343596719925e-05, + "loss": 0.1371, + "step": 21985 + }, + { + "epoch": 6.79, + "learning_rate": 1.5382922124684163e-05, + "loss": 0.1198, + "step": 21986 + }, + { + "epoch": 6.79, + "learning_rate": 1.5382500639184734e-05, + "loss": 0.1275, + "step": 21987 + }, + { + "epoch": 6.79, + "learning_rate": 1.5382079140222685e-05, + "loss": 0.1194, + "step": 21988 + }, + { + "epoch": 6.79, + "learning_rate": 1.5381657627799077e-05, + "loss": 0.1189, + "step": 21989 + }, + { + "epoch": 6.79, + "learning_rate": 1.5381236101914963e-05, + "loss": 0.1223, + "step": 21990 + }, + { + "epoch": 6.79, + "learning_rate": 1.5380814562571394e-05, + "loss": 0.126, + "step": 21991 + }, + { + "epoch": 6.79, + "learning_rate": 1.5380393009769424e-05, + "loss": 0.1181, + "step": 21992 + }, + { + "epoch": 6.79, + "learning_rate": 1.5379971443510113e-05, + "loss": 0.1311, + "step": 21993 + }, + { + "epoch": 6.79, + "learning_rate": 1.537954986379451e-05, + "loss": 0.1236, + "step": 21994 + }, + { + "epoch": 6.79, + "learning_rate": 1.5379128270623676e-05, + "loss": 0.1372, + "step": 21995 + }, + { + "epoch": 6.79, + "learning_rate": 1.537870666399866e-05, + "loss": 0.1264, + "step": 21996 + }, + { + "epoch": 6.79, + "learning_rate": 1.5378285043920515e-05, + "loss": 0.1266, + "step": 21997 + }, + { + "epoch": 6.79, + "learning_rate": 1.5377863410390298e-05, + "loss": 0.1219, + "step": 21998 + }, + { + "epoch": 6.79, + "learning_rate": 1.5377441763409066e-05, + "loss": 0.125, + "step": 21999 + }, + { + "epoch": 6.79, + "learning_rate": 1.537702010297787e-05, + "loss": 0.1278, + "step": 22000 + }, + { + "epoch": 6.79, + "learning_rate": 1.5376598429097766e-05, + "loss": 0.1271, + "step": 22001 + }, + { + "epoch": 6.79, + "learning_rate": 1.537617674176981e-05, + "loss": 0.1297, + "step": 22002 + }, + { + "epoch": 6.8, + "learning_rate": 1.5375755040995056e-05, + "loss": 0.1264, + "step": 22003 + }, + { + "epoch": 6.8, + "learning_rate": 1.5375333326774552e-05, + "loss": 0.134, + "step": 22004 + }, + { + "epoch": 6.8, + "learning_rate": 1.537491159910937e-05, + "loss": 0.1358, + "step": 22005 + }, + { + "epoch": 6.8, + "learning_rate": 1.5374489858000547e-05, + "loss": 0.1094, + "step": 22006 + }, + { + "epoch": 6.8, + "learning_rate": 1.537406810344914e-05, + "loss": 0.1314, + "step": 22007 + }, + { + "epoch": 6.8, + "learning_rate": 1.5373646335456215e-05, + "loss": 0.131, + "step": 22008 + }, + { + "epoch": 6.8, + "learning_rate": 1.537322455402282e-05, + "loss": 0.1352, + "step": 22009 + }, + { + "epoch": 6.8, + "learning_rate": 1.5372802759150008e-05, + "loss": 0.1249, + "step": 22010 + }, + { + "epoch": 6.8, + "learning_rate": 1.5372380950838838e-05, + "loss": 0.1269, + "step": 22011 + }, + { + "epoch": 6.8, + "learning_rate": 1.5371959129090365e-05, + "loss": 0.127, + "step": 22012 + }, + { + "epoch": 6.8, + "learning_rate": 1.5371537293905638e-05, + "loss": 0.13, + "step": 22013 + }, + { + "epoch": 6.8, + "learning_rate": 1.537111544528572e-05, + "loss": 0.1222, + "step": 22014 + }, + { + "epoch": 6.8, + "learning_rate": 1.537069358323166e-05, + "loss": 0.1219, + "step": 22015 + }, + { + "epoch": 6.8, + "learning_rate": 1.5370271707744517e-05, + "loss": 0.1232, + "step": 22016 + }, + { + "epoch": 6.8, + "learning_rate": 1.5369849818825348e-05, + "loss": 0.1296, + "step": 22017 + }, + { + "epoch": 6.8, + "learning_rate": 1.53694279164752e-05, + "loss": 0.1223, + "step": 22018 + }, + { + "epoch": 6.8, + "learning_rate": 1.5369006000695137e-05, + "loss": 0.1336, + "step": 22019 + }, + { + "epoch": 6.8, + "learning_rate": 1.5368584071486213e-05, + "loss": 0.1352, + "step": 22020 + }, + { + "epoch": 6.8, + "learning_rate": 1.5368162128849475e-05, + "loss": 0.1346, + "step": 22021 + }, + { + "epoch": 6.8, + "learning_rate": 1.5367740172785985e-05, + "loss": 0.1204, + "step": 22022 + }, + { + "epoch": 6.8, + "learning_rate": 1.5367318203296805e-05, + "loss": 0.1269, + "step": 22023 + }, + { + "epoch": 6.8, + "learning_rate": 1.5366896220382973e-05, + "loss": 0.1206, + "step": 22024 + }, + { + "epoch": 6.8, + "learning_rate": 1.5366474224045566e-05, + "loss": 0.1251, + "step": 22025 + }, + { + "epoch": 6.8, + "learning_rate": 1.5366052214285618e-05, + "loss": 0.1206, + "step": 22026 + }, + { + "epoch": 6.8, + "learning_rate": 1.53656301911042e-05, + "loss": 0.1278, + "step": 22027 + }, + { + "epoch": 6.8, + "learning_rate": 1.5365208154502362e-05, + "loss": 0.1289, + "step": 22028 + }, + { + "epoch": 6.8, + "learning_rate": 1.536478610448116e-05, + "loss": 0.1258, + "step": 22029 + }, + { + "epoch": 6.8, + "learning_rate": 1.5364364041041646e-05, + "loss": 0.1305, + "step": 22030 + }, + { + "epoch": 6.8, + "learning_rate": 1.5363941964184884e-05, + "loss": 0.1261, + "step": 22031 + }, + { + "epoch": 6.8, + "learning_rate": 1.536351987391192e-05, + "loss": 0.1234, + "step": 22032 + }, + { + "epoch": 6.8, + "learning_rate": 1.5363097770223817e-05, + "loss": 0.1185, + "step": 22033 + }, + { + "epoch": 6.8, + "learning_rate": 1.536267565312163e-05, + "loss": 0.1265, + "step": 22034 + }, + { + "epoch": 6.8, + "learning_rate": 1.536225352260641e-05, + "loss": 0.1296, + "step": 22035 + }, + { + "epoch": 6.81, + "learning_rate": 1.536183137867922e-05, + "loss": 0.1307, + "step": 22036 + }, + { + "epoch": 6.81, + "learning_rate": 1.5361409221341106e-05, + "loss": 0.1291, + "step": 22037 + }, + { + "epoch": 6.81, + "learning_rate": 1.5360987050593134e-05, + "loss": 0.1322, + "step": 22038 + }, + { + "epoch": 6.81, + "learning_rate": 1.5360564866436356e-05, + "loss": 0.1257, + "step": 22039 + }, + { + "epoch": 6.81, + "learning_rate": 1.5360142668871825e-05, + "loss": 0.1309, + "step": 22040 + }, + { + "epoch": 6.81, + "learning_rate": 1.53597204579006e-05, + "loss": 0.1225, + "step": 22041 + }, + { + "epoch": 6.81, + "learning_rate": 1.535929823352374e-05, + "loss": 0.1288, + "step": 22042 + }, + { + "epoch": 6.81, + "learning_rate": 1.535887599574229e-05, + "loss": 0.1306, + "step": 22043 + }, + { + "epoch": 6.81, + "learning_rate": 1.535845374455732e-05, + "loss": 0.114, + "step": 22044 + }, + { + "epoch": 6.81, + "learning_rate": 1.5358031479969877e-05, + "loss": 0.123, + "step": 22045 + }, + { + "epoch": 6.81, + "learning_rate": 1.535760920198102e-05, + "loss": 0.133, + "step": 22046 + }, + { + "epoch": 6.81, + "learning_rate": 1.5357186910591807e-05, + "loss": 0.135, + "step": 22047 + }, + { + "epoch": 6.81, + "learning_rate": 1.5356764605803293e-05, + "loss": 0.1205, + "step": 22048 + }, + { + "epoch": 6.81, + "learning_rate": 1.535634228761653e-05, + "loss": 0.1382, + "step": 22049 + }, + { + "epoch": 6.81, + "learning_rate": 1.5355919956032584e-05, + "loss": 0.1236, + "step": 22050 + }, + { + "epoch": 6.81, + "learning_rate": 1.5355497611052506e-05, + "loss": 0.1282, + "step": 22051 + }, + { + "epoch": 6.81, + "learning_rate": 1.5355075252677344e-05, + "loss": 0.1191, + "step": 22052 + }, + { + "epoch": 6.81, + "learning_rate": 1.5354652880908166e-05, + "loss": 0.1249, + "step": 22053 + }, + { + "epoch": 6.81, + "learning_rate": 1.5354230495746024e-05, + "loss": 0.1246, + "step": 22054 + }, + { + "epoch": 6.81, + "learning_rate": 1.5353808097191976e-05, + "loss": 0.126, + "step": 22055 + }, + { + "epoch": 6.81, + "learning_rate": 1.5353385685247076e-05, + "loss": 0.1246, + "step": 22056 + }, + { + "epoch": 6.81, + "learning_rate": 1.5352963259912384e-05, + "loss": 0.1381, + "step": 22057 + }, + { + "epoch": 6.81, + "learning_rate": 1.5352540821188954e-05, + "loss": 0.1183, + "step": 22058 + }, + { + "epoch": 6.81, + "learning_rate": 1.5352118369077843e-05, + "loss": 0.1258, + "step": 22059 + }, + { + "epoch": 6.81, + "learning_rate": 1.5351695903580105e-05, + "loss": 0.122, + "step": 22060 + }, + { + "epoch": 6.81, + "learning_rate": 1.5351273424696803e-05, + "loss": 0.1155, + "step": 22061 + }, + { + "epoch": 6.81, + "learning_rate": 1.535085093242899e-05, + "loss": 0.1269, + "step": 22062 + }, + { + "epoch": 6.81, + "learning_rate": 1.5350428426777718e-05, + "loss": 0.1193, + "step": 22063 + }, + { + "epoch": 6.81, + "learning_rate": 1.5350005907744058e-05, + "loss": 0.1199, + "step": 22064 + }, + { + "epoch": 6.81, + "learning_rate": 1.534958337532905e-05, + "loss": 0.1281, + "step": 22065 + }, + { + "epoch": 6.81, + "learning_rate": 1.534916082953376e-05, + "loss": 0.1337, + "step": 22066 + }, + { + "epoch": 6.81, + "learning_rate": 1.5348738270359244e-05, + "loss": 0.1153, + "step": 22067 + }, + { + "epoch": 6.82, + "learning_rate": 1.5348315697806556e-05, + "loss": 0.1262, + "step": 22068 + }, + { + "epoch": 6.82, + "learning_rate": 1.5347893111876755e-05, + "loss": 0.129, + "step": 22069 + }, + { + "epoch": 6.82, + "learning_rate": 1.53474705125709e-05, + "loss": 0.1342, + "step": 22070 + }, + { + "epoch": 6.82, + "learning_rate": 1.5347047899890045e-05, + "loss": 0.1363, + "step": 22071 + }, + { + "epoch": 6.82, + "learning_rate": 1.534662527383525e-05, + "loss": 0.1247, + "step": 22072 + }, + { + "epoch": 6.82, + "learning_rate": 1.5346202634407567e-05, + "loss": 0.127, + "step": 22073 + }, + { + "epoch": 6.82, + "learning_rate": 1.534577998160806e-05, + "loss": 0.1467, + "step": 22074 + }, + { + "epoch": 6.82, + "learning_rate": 1.5345357315437776e-05, + "loss": 0.1367, + "step": 22075 + }, + { + "epoch": 6.82, + "learning_rate": 1.5344934635897784e-05, + "loss": 0.1214, + "step": 22076 + }, + { + "epoch": 6.82, + "learning_rate": 1.5344511942989134e-05, + "loss": 0.1301, + "step": 22077 + }, + { + "epoch": 6.82, + "learning_rate": 1.5344089236712885e-05, + "loss": 0.1288, + "step": 22078 + }, + { + "epoch": 6.82, + "learning_rate": 1.5343666517070094e-05, + "loss": 0.1188, + "step": 22079 + }, + { + "epoch": 6.82, + "learning_rate": 1.5343243784061818e-05, + "loss": 0.14, + "step": 22080 + }, + { + "epoch": 6.82, + "learning_rate": 1.5342821037689113e-05, + "loss": 0.1175, + "step": 22081 + }, + { + "epoch": 6.82, + "learning_rate": 1.5342398277953044e-05, + "loss": 0.1215, + "step": 22082 + }, + { + "epoch": 6.82, + "learning_rate": 1.5341975504854657e-05, + "loss": 0.1187, + "step": 22083 + }, + { + "epoch": 6.82, + "learning_rate": 1.5341552718395013e-05, + "loss": 0.1244, + "step": 22084 + }, + { + "epoch": 6.82, + "learning_rate": 1.5341129918575177e-05, + "loss": 0.1322, + "step": 22085 + }, + { + "epoch": 6.82, + "learning_rate": 1.5340707105396197e-05, + "loss": 0.1319, + "step": 22086 + }, + { + "epoch": 6.82, + "learning_rate": 1.5340284278859136e-05, + "loss": 0.1088, + "step": 22087 + }, + { + "epoch": 6.82, + "learning_rate": 1.5339861438965052e-05, + "loss": 0.1299, + "step": 22088 + }, + { + "epoch": 6.82, + "learning_rate": 1.5339438585714997e-05, + "loss": 0.119, + "step": 22089 + }, + { + "epoch": 6.82, + "learning_rate": 1.5339015719110038e-05, + "loss": 0.1326, + "step": 22090 + }, + { + "epoch": 6.82, + "learning_rate": 1.5338592839151218e-05, + "loss": 0.1302, + "step": 22091 + }, + { + "epoch": 6.82, + "learning_rate": 1.5338169945839612e-05, + "loss": 0.1376, + "step": 22092 + }, + { + "epoch": 6.82, + "learning_rate": 1.5337747039176266e-05, + "loss": 0.1225, + "step": 22093 + }, + { + "epoch": 6.82, + "learning_rate": 1.533732411916224e-05, + "loss": 0.1231, + "step": 22094 + }, + { + "epoch": 6.82, + "learning_rate": 1.5336901185798593e-05, + "loss": 0.1281, + "step": 22095 + }, + { + "epoch": 6.82, + "learning_rate": 1.5336478239086384e-05, + "loss": 0.1285, + "step": 22096 + }, + { + "epoch": 6.82, + "learning_rate": 1.533605527902667e-05, + "loss": 0.1297, + "step": 22097 + }, + { + "epoch": 6.82, + "learning_rate": 1.5335632305620506e-05, + "loss": 0.1323, + "step": 22098 + }, + { + "epoch": 6.82, + "learning_rate": 1.5335209318868954e-05, + "loss": 0.1186, + "step": 22099 + }, + { + "epoch": 6.82, + "learning_rate": 1.5334786318773073e-05, + "loss": 0.1285, + "step": 22100 + }, + { + "epoch": 6.83, + "learning_rate": 1.5334363305333916e-05, + "loss": 0.1211, + "step": 22101 + }, + { + "epoch": 6.83, + "learning_rate": 1.5333940278552543e-05, + "loss": 0.1344, + "step": 22102 + }, + { + "epoch": 6.83, + "learning_rate": 1.5333517238430015e-05, + "loss": 0.1209, + "step": 22103 + }, + { + "epoch": 6.83, + "learning_rate": 1.5333094184967382e-05, + "loss": 0.1091, + "step": 22104 + }, + { + "epoch": 6.83, + "learning_rate": 1.533267111816571e-05, + "loss": 0.131, + "step": 22105 + }, + { + "epoch": 6.83, + "learning_rate": 1.533224803802606e-05, + "loss": 0.1443, + "step": 22106 + }, + { + "epoch": 6.83, + "learning_rate": 1.533182494454948e-05, + "loss": 0.1346, + "step": 22107 + }, + { + "epoch": 6.83, + "learning_rate": 1.5331401837737035e-05, + "loss": 0.1232, + "step": 22108 + }, + { + "epoch": 6.83, + "learning_rate": 1.533097871758978e-05, + "loss": 0.124, + "step": 22109 + }, + { + "epoch": 6.83, + "learning_rate": 1.5330555584108776e-05, + "loss": 0.1182, + "step": 22110 + }, + { + "epoch": 6.83, + "learning_rate": 1.5330132437295082e-05, + "loss": 0.1342, + "step": 22111 + }, + { + "epoch": 6.83, + "learning_rate": 1.5329709277149754e-05, + "loss": 0.1297, + "step": 22112 + }, + { + "epoch": 6.83, + "learning_rate": 1.5329286103673852e-05, + "loss": 0.123, + "step": 22113 + }, + { + "epoch": 6.83, + "learning_rate": 1.5328862916868426e-05, + "loss": 0.1312, + "step": 22114 + }, + { + "epoch": 6.83, + "learning_rate": 1.532843971673455e-05, + "loss": 0.1164, + "step": 22115 + }, + { + "epoch": 6.83, + "learning_rate": 1.5328016503273272e-05, + "loss": 0.1428, + "step": 22116 + }, + { + "epoch": 6.83, + "learning_rate": 1.532759327648565e-05, + "loss": 0.1299, + "step": 22117 + }, + { + "epoch": 6.83, + "learning_rate": 1.5327170036372753e-05, + "loss": 0.1368, + "step": 22118 + }, + { + "epoch": 6.83, + "learning_rate": 1.5326746782935626e-05, + "loss": 0.135, + "step": 22119 + }, + { + "epoch": 6.83, + "learning_rate": 1.5326323516175338e-05, + "loss": 0.1268, + "step": 22120 + }, + { + "epoch": 6.83, + "learning_rate": 1.532590023609294e-05, + "loss": 0.13, + "step": 22121 + }, + { + "epoch": 6.83, + "learning_rate": 1.532547694268949e-05, + "loss": 0.1245, + "step": 22122 + }, + { + "epoch": 6.83, + "learning_rate": 1.5325053635966057e-05, + "loss": 0.1263, + "step": 22123 + }, + { + "epoch": 6.83, + "learning_rate": 1.5324630315923693e-05, + "loss": 0.1238, + "step": 22124 + }, + { + "epoch": 6.83, + "learning_rate": 1.5324206982563458e-05, + "loss": 0.1447, + "step": 22125 + }, + { + "epoch": 6.83, + "learning_rate": 1.5323783635886408e-05, + "loss": 0.1315, + "step": 22126 + }, + { + "epoch": 6.83, + "learning_rate": 1.5323360275893607e-05, + "loss": 0.1304, + "step": 22127 + }, + { + "epoch": 6.83, + "learning_rate": 1.532293690258611e-05, + "loss": 0.1243, + "step": 22128 + }, + { + "epoch": 6.83, + "learning_rate": 1.5322513515964973e-05, + "loss": 0.1213, + "step": 22129 + }, + { + "epoch": 6.83, + "learning_rate": 1.5322090116031262e-05, + "loss": 0.121, + "step": 22130 + }, + { + "epoch": 6.83, + "learning_rate": 1.5321666702786035e-05, + "loss": 0.1317, + "step": 22131 + }, + { + "epoch": 6.83, + "learning_rate": 1.5321243276230345e-05, + "loss": 0.1251, + "step": 22132 + }, + { + "epoch": 6.84, + "learning_rate": 1.5320819836365258e-05, + "loss": 0.1351, + "step": 22133 + }, + { + "epoch": 6.84, + "learning_rate": 1.532039638319183e-05, + "loss": 0.1307, + "step": 22134 + }, + { + "epoch": 6.84, + "learning_rate": 1.531997291671112e-05, + "loss": 0.1168, + "step": 22135 + }, + { + "epoch": 6.84, + "learning_rate": 1.5319549436924187e-05, + "loss": 0.1193, + "step": 22136 + }, + { + "epoch": 6.84, + "learning_rate": 1.5319125943832088e-05, + "loss": 0.1323, + "step": 22137 + }, + { + "epoch": 6.84, + "learning_rate": 1.531870243743589e-05, + "loss": 0.1256, + "step": 22138 + }, + { + "epoch": 6.84, + "learning_rate": 1.5318278917736643e-05, + "loss": 0.1356, + "step": 22139 + }, + { + "epoch": 6.84, + "learning_rate": 1.531785538473541e-05, + "loss": 0.1316, + "step": 22140 + }, + { + "epoch": 6.84, + "learning_rate": 1.5317431838433257e-05, + "loss": 0.1196, + "step": 22141 + }, + { + "epoch": 6.84, + "learning_rate": 1.531700827883123e-05, + "loss": 0.125, + "step": 22142 + }, + { + "epoch": 6.84, + "learning_rate": 1.53165847059304e-05, + "loss": 0.127, + "step": 22143 + }, + { + "epoch": 6.84, + "learning_rate": 1.531616111973182e-05, + "loss": 0.1151, + "step": 22144 + }, + { + "epoch": 6.84, + "learning_rate": 1.5315737520236548e-05, + "loss": 0.1378, + "step": 22145 + }, + { + "epoch": 6.84, + "learning_rate": 1.5315313907445656e-05, + "loss": 0.1285, + "step": 22146 + }, + { + "epoch": 6.84, + "learning_rate": 1.5314890281360185e-05, + "loss": 0.1231, + "step": 22147 + }, + { + "epoch": 6.84, + "learning_rate": 1.531446664198121e-05, + "loss": 0.1368, + "step": 22148 + }, + { + "epoch": 6.84, + "learning_rate": 1.5314042989309784e-05, + "loss": 0.1111, + "step": 22149 + }, + { + "epoch": 6.84, + "learning_rate": 1.5313619323346968e-05, + "loss": 0.1318, + "step": 22150 + }, + { + "epoch": 6.84, + "learning_rate": 1.5313195644093818e-05, + "loss": 0.1246, + "step": 22151 + }, + { + "epoch": 6.84, + "learning_rate": 1.5312771951551396e-05, + "loss": 0.1166, + "step": 22152 + }, + { + "epoch": 6.84, + "learning_rate": 1.5312348245720765e-05, + "loss": 0.1376, + "step": 22153 + }, + { + "epoch": 6.84, + "learning_rate": 1.5311924526602983e-05, + "loss": 0.1268, + "step": 22154 + }, + { + "epoch": 6.84, + "learning_rate": 1.5311500794199102e-05, + "loss": 0.1164, + "step": 22155 + }, + { + "epoch": 6.84, + "learning_rate": 1.5311077048510194e-05, + "loss": 0.1345, + "step": 22156 + }, + { + "epoch": 6.84, + "learning_rate": 1.5310653289537315e-05, + "loss": 0.1243, + "step": 22157 + }, + { + "epoch": 6.84, + "learning_rate": 1.531022951728152e-05, + "loss": 0.1344, + "step": 22158 + }, + { + "epoch": 6.84, + "learning_rate": 1.5309805731743876e-05, + "loss": 0.1151, + "step": 22159 + }, + { + "epoch": 6.84, + "learning_rate": 1.5309381932925436e-05, + "loss": 0.1223, + "step": 22160 + }, + { + "epoch": 6.84, + "learning_rate": 1.5308958120827265e-05, + "loss": 0.1251, + "step": 22161 + }, + { + "epoch": 6.84, + "learning_rate": 1.5308534295450422e-05, + "loss": 0.1274, + "step": 22162 + }, + { + "epoch": 6.84, + "learning_rate": 1.530811045679597e-05, + "loss": 0.1376, + "step": 22163 + }, + { + "epoch": 6.84, + "learning_rate": 1.530768660486496e-05, + "loss": 0.1167, + "step": 22164 + }, + { + "epoch": 6.85, + "learning_rate": 1.530726273965846e-05, + "loss": 0.1194, + "step": 22165 + }, + { + "epoch": 6.85, + "learning_rate": 1.5306838861177528e-05, + "loss": 0.1173, + "step": 22166 + }, + { + "epoch": 6.85, + "learning_rate": 1.5306414969423223e-05, + "loss": 0.1279, + "step": 22167 + }, + { + "epoch": 6.85, + "learning_rate": 1.5305991064396606e-05, + "loss": 0.1302, + "step": 22168 + }, + { + "epoch": 6.85, + "learning_rate": 1.5305567146098737e-05, + "loss": 0.1343, + "step": 22169 + }, + { + "epoch": 6.85, + "learning_rate": 1.530514321453068e-05, + "loss": 0.1156, + "step": 22170 + }, + { + "epoch": 6.85, + "learning_rate": 1.530471926969349e-05, + "loss": 0.1324, + "step": 22171 + }, + { + "epoch": 6.85, + "learning_rate": 1.530429531158823e-05, + "loss": 0.1215, + "step": 22172 + }, + { + "epoch": 6.85, + "learning_rate": 1.530387134021596e-05, + "loss": 0.1337, + "step": 22173 + }, + { + "epoch": 6.85, + "learning_rate": 1.530344735557774e-05, + "loss": 0.1316, + "step": 22174 + }, + { + "epoch": 6.85, + "learning_rate": 1.5303023357674633e-05, + "loss": 0.124, + "step": 22175 + }, + { + "epoch": 6.85, + "learning_rate": 1.5302599346507693e-05, + "loss": 0.1244, + "step": 22176 + }, + { + "epoch": 6.85, + "learning_rate": 1.5302175322077992e-05, + "loss": 0.1171, + "step": 22177 + }, + { + "epoch": 6.85, + "learning_rate": 1.5301751284386578e-05, + "loss": 0.1254, + "step": 22178 + }, + { + "epoch": 6.85, + "learning_rate": 1.530132723343452e-05, + "loss": 0.1229, + "step": 22179 + }, + { + "epoch": 6.85, + "learning_rate": 1.530090316922287e-05, + "loss": 0.1205, + "step": 22180 + }, + { + "epoch": 6.85, + "learning_rate": 1.53004790917527e-05, + "loss": 0.1374, + "step": 22181 + }, + { + "epoch": 6.85, + "learning_rate": 1.5300055001025062e-05, + "loss": 0.1198, + "step": 22182 + }, + { + "epoch": 6.85, + "learning_rate": 1.529963089704102e-05, + "loss": 0.1398, + "step": 22183 + }, + { + "epoch": 6.85, + "learning_rate": 1.529920677980164e-05, + "loss": 0.1226, + "step": 22184 + }, + { + "epoch": 6.85, + "learning_rate": 1.529878264930797e-05, + "loss": 0.1216, + "step": 22185 + }, + { + "epoch": 6.85, + "learning_rate": 1.5298358505561082e-05, + "loss": 0.1345, + "step": 22186 + }, + { + "epoch": 6.85, + "learning_rate": 1.5297934348562034e-05, + "loss": 0.1293, + "step": 22187 + }, + { + "epoch": 6.85, + "learning_rate": 1.5297510178311882e-05, + "loss": 0.1277, + "step": 22188 + }, + { + "epoch": 6.85, + "learning_rate": 1.529708599481169e-05, + "loss": 0.128, + "step": 22189 + }, + { + "epoch": 6.85, + "learning_rate": 1.5296661798062526e-05, + "loss": 0.1335, + "step": 22190 + }, + { + "epoch": 6.85, + "learning_rate": 1.529623758806544e-05, + "loss": 0.1236, + "step": 22191 + }, + { + "epoch": 6.85, + "learning_rate": 1.52958133648215e-05, + "loss": 0.1182, + "step": 22192 + }, + { + "epoch": 6.85, + "learning_rate": 1.5295389128331762e-05, + "loss": 0.1266, + "step": 22193 + }, + { + "epoch": 6.85, + "learning_rate": 1.5294964878597295e-05, + "loss": 0.1286, + "step": 22194 + }, + { + "epoch": 6.85, + "learning_rate": 1.5294540615619152e-05, + "loss": 0.1258, + "step": 22195 + }, + { + "epoch": 6.85, + "learning_rate": 1.5294116339398394e-05, + "loss": 0.1252, + "step": 22196 + }, + { + "epoch": 6.85, + "learning_rate": 1.5293692049936093e-05, + "loss": 0.1275, + "step": 22197 + }, + { + "epoch": 6.86, + "learning_rate": 1.5293267747233297e-05, + "loss": 0.1381, + "step": 22198 + }, + { + "epoch": 6.86, + "learning_rate": 1.5292843431291075e-05, + "loss": 0.1359, + "step": 22199 + }, + { + "epoch": 6.86, + "learning_rate": 1.5292419102110487e-05, + "loss": 0.136, + "step": 22200 + }, + { + "epoch": 6.86, + "learning_rate": 1.529199475969259e-05, + "loss": 0.1228, + "step": 22201 + }, + { + "epoch": 6.86, + "learning_rate": 1.5291570404038452e-05, + "loss": 0.1274, + "step": 22202 + }, + { + "epoch": 6.86, + "learning_rate": 1.5291146035149132e-05, + "loss": 0.1242, + "step": 22203 + }, + { + "epoch": 6.86, + "learning_rate": 1.529072165302569e-05, + "loss": 0.1298, + "step": 22204 + }, + { + "epoch": 6.86, + "learning_rate": 1.5290297257669188e-05, + "loss": 0.1288, + "step": 22205 + }, + { + "epoch": 6.86, + "learning_rate": 1.5289872849080684e-05, + "loss": 0.1209, + "step": 22206 + }, + { + "epoch": 6.86, + "learning_rate": 1.5289448427261248e-05, + "loss": 0.1299, + "step": 22207 + }, + { + "epoch": 6.86, + "learning_rate": 1.5289023992211936e-05, + "loss": 0.1296, + "step": 22208 + }, + { + "epoch": 6.86, + "learning_rate": 1.5288599543933807e-05, + "loss": 0.1238, + "step": 22209 + }, + { + "epoch": 6.86, + "learning_rate": 1.528817508242793e-05, + "loss": 0.1191, + "step": 22210 + }, + { + "epoch": 6.86, + "learning_rate": 1.528775060769536e-05, + "loss": 0.1204, + "step": 22211 + }, + { + "epoch": 6.86, + "learning_rate": 1.528732611973716e-05, + "loss": 0.1261, + "step": 22212 + }, + { + "epoch": 6.86, + "learning_rate": 1.5286901618554396e-05, + "loss": 0.127, + "step": 22213 + }, + { + "epoch": 6.86, + "learning_rate": 1.5286477104148126e-05, + "loss": 0.1164, + "step": 22214 + }, + { + "epoch": 6.86, + "learning_rate": 1.5286052576519414e-05, + "loss": 0.1209, + "step": 22215 + }, + { + "epoch": 6.86, + "learning_rate": 1.5285628035669318e-05, + "loss": 0.1184, + "step": 22216 + }, + { + "epoch": 6.86, + "learning_rate": 1.5285203481598904e-05, + "loss": 0.1184, + "step": 22217 + }, + { + "epoch": 6.86, + "learning_rate": 1.5284778914309233e-05, + "loss": 0.1236, + "step": 22218 + }, + { + "epoch": 6.86, + "learning_rate": 1.5284354333801363e-05, + "loss": 0.1166, + "step": 22219 + }, + { + "epoch": 6.86, + "learning_rate": 1.528392974007636e-05, + "loss": 0.1249, + "step": 22220 + }, + { + "epoch": 6.86, + "learning_rate": 1.5283505133135284e-05, + "loss": 0.1285, + "step": 22221 + }, + { + "epoch": 6.86, + "learning_rate": 1.52830805129792e-05, + "loss": 0.1289, + "step": 22222 + }, + { + "epoch": 6.86, + "learning_rate": 1.528265587960917e-05, + "loss": 0.1259, + "step": 22223 + }, + { + "epoch": 6.86, + "learning_rate": 1.5282231233026247e-05, + "loss": 0.1281, + "step": 22224 + }, + { + "epoch": 6.86, + "learning_rate": 1.5281806573231505e-05, + "loss": 0.1159, + "step": 22225 + }, + { + "epoch": 6.86, + "learning_rate": 1.5281381900226007e-05, + "loss": 0.1339, + "step": 22226 + }, + { + "epoch": 6.86, + "learning_rate": 1.52809572140108e-05, + "loss": 0.127, + "step": 22227 + }, + { + "epoch": 6.86, + "learning_rate": 1.528053251458696e-05, + "loss": 0.1183, + "step": 22228 + }, + { + "epoch": 6.86, + "learning_rate": 1.5280107801955547e-05, + "loss": 0.1259, + "step": 22229 + }, + { + "epoch": 6.87, + "learning_rate": 1.527968307611762e-05, + "loss": 0.1374, + "step": 22230 + }, + { + "epoch": 6.87, + "learning_rate": 1.527925833707424e-05, + "loss": 0.121, + "step": 22231 + }, + { + "epoch": 6.87, + "learning_rate": 1.5278833584826472e-05, + "loss": 0.1159, + "step": 22232 + }, + { + "epoch": 6.87, + "learning_rate": 1.5278408819375385e-05, + "loss": 0.1325, + "step": 22233 + }, + { + "epoch": 6.87, + "learning_rate": 1.527798404072203e-05, + "loss": 0.1234, + "step": 22234 + }, + { + "epoch": 6.87, + "learning_rate": 1.5277559248867474e-05, + "loss": 0.1265, + "step": 22235 + }, + { + "epoch": 6.87, + "learning_rate": 1.527713444381278e-05, + "loss": 0.1359, + "step": 22236 + }, + { + "epoch": 6.87, + "learning_rate": 1.527670962555901e-05, + "loss": 0.1357, + "step": 22237 + }, + { + "epoch": 6.87, + "learning_rate": 1.5276284794107226e-05, + "loss": 0.1395, + "step": 22238 + }, + { + "epoch": 6.87, + "learning_rate": 1.527585994945849e-05, + "loss": 0.133, + "step": 22239 + }, + { + "epoch": 6.87, + "learning_rate": 1.527543509161387e-05, + "loss": 0.1203, + "step": 22240 + }, + { + "epoch": 6.87, + "learning_rate": 1.5275010220574426e-05, + "loss": 0.1219, + "step": 22241 + }, + { + "epoch": 6.87, + "learning_rate": 1.5274585336341215e-05, + "loss": 0.1279, + "step": 22242 + }, + { + "epoch": 6.87, + "learning_rate": 1.5274160438915306e-05, + "loss": 0.133, + "step": 22243 + }, + { + "epoch": 6.87, + "learning_rate": 1.5273735528297758e-05, + "loss": 0.1327, + "step": 22244 + }, + { + "epoch": 6.87, + "learning_rate": 1.5273310604489636e-05, + "loss": 0.114, + "step": 22245 + }, + { + "epoch": 6.87, + "learning_rate": 1.5272885667492005e-05, + "loss": 0.1148, + "step": 22246 + }, + { + "epoch": 6.87, + "learning_rate": 1.5272460717305925e-05, + "loss": 0.1262, + "step": 22247 + }, + { + "epoch": 6.87, + "learning_rate": 1.5272035753932457e-05, + "loss": 0.1251, + "step": 22248 + }, + { + "epoch": 6.87, + "learning_rate": 1.5271610777372668e-05, + "loss": 0.1201, + "step": 22249 + }, + { + "epoch": 6.87, + "learning_rate": 1.5271185787627616e-05, + "loss": 0.1235, + "step": 22250 + }, + { + "epoch": 6.87, + "learning_rate": 1.5270760784698366e-05, + "loss": 0.1185, + "step": 22251 + }, + { + "epoch": 6.87, + "learning_rate": 1.5270335768585988e-05, + "loss": 0.134, + "step": 22252 + }, + { + "epoch": 6.87, + "learning_rate": 1.5269910739291534e-05, + "loss": 0.1397, + "step": 22253 + }, + { + "epoch": 6.87, + "learning_rate": 1.5269485696816075e-05, + "loss": 0.1223, + "step": 22254 + }, + { + "epoch": 6.87, + "learning_rate": 1.5269060641160668e-05, + "loss": 0.1371, + "step": 22255 + }, + { + "epoch": 6.87, + "learning_rate": 1.526863557232638e-05, + "loss": 0.1284, + "step": 22256 + }, + { + "epoch": 6.87, + "learning_rate": 1.526821049031428e-05, + "loss": 0.1134, + "step": 22257 + }, + { + "epoch": 6.87, + "learning_rate": 1.5267785395125415e-05, + "loss": 0.1188, + "step": 22258 + }, + { + "epoch": 6.87, + "learning_rate": 1.5267360286760866e-05, + "loss": 0.1322, + "step": 22259 + }, + { + "epoch": 6.87, + "learning_rate": 1.5266935165221684e-05, + "loss": 0.1221, + "step": 22260 + }, + { + "epoch": 6.87, + "learning_rate": 1.5266510030508935e-05, + "loss": 0.1314, + "step": 22261 + }, + { + "epoch": 6.88, + "learning_rate": 1.526608488262369e-05, + "loss": 0.132, + "step": 22262 + }, + { + "epoch": 6.88, + "learning_rate": 1.5265659721566998e-05, + "loss": 0.1253, + "step": 22263 + }, + { + "epoch": 6.88, + "learning_rate": 1.5265234547339935e-05, + "loss": 0.1254, + "step": 22264 + }, + { + "epoch": 6.88, + "learning_rate": 1.5264809359943562e-05, + "loss": 0.1281, + "step": 22265 + }, + { + "epoch": 6.88, + "learning_rate": 1.5264384159378938e-05, + "loss": 0.1227, + "step": 22266 + }, + { + "epoch": 6.88, + "learning_rate": 1.526395894564713e-05, + "loss": 0.1398, + "step": 22267 + }, + { + "epoch": 6.88, + "learning_rate": 1.5263533718749198e-05, + "loss": 0.1246, + "step": 22268 + }, + { + "epoch": 6.88, + "learning_rate": 1.526310847868621e-05, + "loss": 0.1286, + "step": 22269 + }, + { + "epoch": 6.88, + "learning_rate": 1.526268322545923e-05, + "loss": 0.1237, + "step": 22270 + }, + { + "epoch": 6.88, + "learning_rate": 1.5262257959069314e-05, + "loss": 0.1341, + "step": 22271 + }, + { + "epoch": 6.88, + "learning_rate": 1.5261832679517536e-05, + "loss": 0.1302, + "step": 22272 + }, + { + "epoch": 6.88, + "learning_rate": 1.5261407386804953e-05, + "loss": 0.1272, + "step": 22273 + }, + { + "epoch": 6.88, + "learning_rate": 1.5260982080932632e-05, + "loss": 0.1293, + "step": 22274 + }, + { + "epoch": 6.88, + "learning_rate": 1.5260556761901634e-05, + "loss": 0.1247, + "step": 22275 + }, + { + "epoch": 6.88, + "learning_rate": 1.5260131429713022e-05, + "loss": 0.1305, + "step": 22276 + }, + { + "epoch": 6.88, + "learning_rate": 1.525970608436787e-05, + "loss": 0.1258, + "step": 22277 + }, + { + "epoch": 6.88, + "learning_rate": 1.5259280725867222e-05, + "loss": 0.1304, + "step": 22278 + }, + { + "epoch": 6.88, + "learning_rate": 1.525885535421216e-05, + "loss": 0.1272, + "step": 22279 + }, + { + "epoch": 6.88, + "learning_rate": 1.5258429969403743e-05, + "loss": 0.1366, + "step": 22280 + }, + { + "epoch": 6.88, + "learning_rate": 1.5258004571443029e-05, + "loss": 0.1328, + "step": 22281 + }, + { + "epoch": 6.88, + "learning_rate": 1.525757916033109e-05, + "loss": 0.1232, + "step": 22282 + }, + { + "epoch": 6.88, + "learning_rate": 1.5257153736068988e-05, + "loss": 0.1252, + "step": 22283 + }, + { + "epoch": 6.88, + "learning_rate": 1.5256728298657782e-05, + "loss": 0.1237, + "step": 22284 + }, + { + "epoch": 6.88, + "learning_rate": 1.525630284809854e-05, + "loss": 0.1279, + "step": 22285 + }, + { + "epoch": 6.88, + "learning_rate": 1.5255877384392328e-05, + "loss": 0.1276, + "step": 22286 + }, + { + "epoch": 6.88, + "learning_rate": 1.5255451907540208e-05, + "loss": 0.1344, + "step": 22287 + }, + { + "epoch": 6.88, + "learning_rate": 1.5255026417543245e-05, + "loss": 0.1348, + "step": 22288 + }, + { + "epoch": 6.88, + "learning_rate": 1.5254600914402495e-05, + "loss": 0.1251, + "step": 22289 + }, + { + "epoch": 6.88, + "learning_rate": 1.5254175398119038e-05, + "loss": 0.1167, + "step": 22290 + }, + { + "epoch": 6.88, + "learning_rate": 1.5253749868693928e-05, + "loss": 0.1426, + "step": 22291 + }, + { + "epoch": 6.88, + "learning_rate": 1.5253324326128231e-05, + "loss": 0.1397, + "step": 22292 + }, + { + "epoch": 6.88, + "learning_rate": 1.5252898770423012e-05, + "loss": 0.129, + "step": 22293 + }, + { + "epoch": 6.88, + "learning_rate": 1.5252473201579335e-05, + "loss": 0.1335, + "step": 22294 + }, + { + "epoch": 6.89, + "learning_rate": 1.5252047619598264e-05, + "loss": 0.1221, + "step": 22295 + }, + { + "epoch": 6.89, + "learning_rate": 1.5251622024480863e-05, + "loss": 0.1326, + "step": 22296 + }, + { + "epoch": 6.89, + "learning_rate": 1.52511964162282e-05, + "loss": 0.1278, + "step": 22297 + }, + { + "epoch": 6.89, + "learning_rate": 1.5250770794841336e-05, + "loss": 0.141, + "step": 22298 + }, + { + "epoch": 6.89, + "learning_rate": 1.5250345160321336e-05, + "loss": 0.1305, + "step": 22299 + }, + { + "epoch": 6.89, + "learning_rate": 1.5249919512669266e-05, + "loss": 0.1172, + "step": 22300 + }, + { + "epoch": 6.89, + "learning_rate": 1.5249493851886188e-05, + "loss": 0.134, + "step": 22301 + }, + { + "epoch": 6.89, + "learning_rate": 1.5249068177973173e-05, + "loss": 0.1276, + "step": 22302 + }, + { + "epoch": 6.89, + "learning_rate": 1.5248642490931275e-05, + "loss": 0.1383, + "step": 22303 + }, + { + "epoch": 6.89, + "learning_rate": 1.5248216790761568e-05, + "loss": 0.1248, + "step": 22304 + }, + { + "epoch": 6.89, + "learning_rate": 1.5247791077465112e-05, + "loss": 0.1359, + "step": 22305 + }, + { + "epoch": 6.89, + "learning_rate": 1.5247365351042976e-05, + "loss": 0.1343, + "step": 22306 + }, + { + "epoch": 6.89, + "learning_rate": 1.5246939611496218e-05, + "loss": 0.1298, + "step": 22307 + }, + { + "epoch": 6.89, + "learning_rate": 1.5246513858825914e-05, + "loss": 0.1307, + "step": 22308 + }, + { + "epoch": 6.89, + "learning_rate": 1.5246088093033115e-05, + "loss": 0.1367, + "step": 22309 + }, + { + "epoch": 6.89, + "learning_rate": 1.5245662314118897e-05, + "loss": 0.127, + "step": 22310 + }, + { + "epoch": 6.89, + "learning_rate": 1.5245236522084322e-05, + "loss": 0.1335, + "step": 22311 + }, + { + "epoch": 6.89, + "learning_rate": 1.5244810716930448e-05, + "loss": 0.1209, + "step": 22312 + }, + { + "epoch": 6.89, + "learning_rate": 1.524438489865835e-05, + "loss": 0.1203, + "step": 22313 + }, + { + "epoch": 6.89, + "learning_rate": 1.524395906726909e-05, + "loss": 0.1236, + "step": 22314 + }, + { + "epoch": 6.89, + "learning_rate": 1.5243533222763727e-05, + "loss": 0.1334, + "step": 22315 + }, + { + "epoch": 6.89, + "learning_rate": 1.5243107365143334e-05, + "loss": 0.1297, + "step": 22316 + }, + { + "epoch": 6.89, + "learning_rate": 1.5242681494408973e-05, + "loss": 0.1354, + "step": 22317 + }, + { + "epoch": 6.89, + "learning_rate": 1.524225561056171e-05, + "loss": 0.1183, + "step": 22318 + }, + { + "epoch": 6.89, + "learning_rate": 1.524182971360261e-05, + "loss": 0.1243, + "step": 22319 + }, + { + "epoch": 6.89, + "learning_rate": 1.5241403803532734e-05, + "loss": 0.1277, + "step": 22320 + }, + { + "epoch": 6.89, + "learning_rate": 1.5240977880353156e-05, + "loss": 0.128, + "step": 22321 + }, + { + "epoch": 6.89, + "learning_rate": 1.5240551944064934e-05, + "loss": 0.1126, + "step": 22322 + }, + { + "epoch": 6.89, + "learning_rate": 1.5240125994669137e-05, + "loss": 0.1168, + "step": 22323 + }, + { + "epoch": 6.89, + "learning_rate": 1.5239700032166829e-05, + "loss": 0.1234, + "step": 22324 + }, + { + "epoch": 6.89, + "learning_rate": 1.5239274056559072e-05, + "loss": 0.1342, + "step": 22325 + }, + { + "epoch": 6.89, + "learning_rate": 1.5238848067846941e-05, + "loss": 0.1335, + "step": 22326 + }, + { + "epoch": 6.9, + "learning_rate": 1.523842206603149e-05, + "loss": 0.1266, + "step": 22327 + }, + { + "epoch": 6.9, + "learning_rate": 1.5237996051113793e-05, + "loss": 0.1359, + "step": 22328 + }, + { + "epoch": 6.9, + "learning_rate": 1.5237570023094912e-05, + "loss": 0.1369, + "step": 22329 + }, + { + "epoch": 6.9, + "learning_rate": 1.5237143981975915e-05, + "loss": 0.133, + "step": 22330 + }, + { + "epoch": 6.9, + "learning_rate": 1.5236717927757863e-05, + "loss": 0.1278, + "step": 22331 + }, + { + "epoch": 6.9, + "learning_rate": 1.5236291860441825e-05, + "loss": 0.1348, + "step": 22332 + }, + { + "epoch": 6.9, + "learning_rate": 1.5235865780028865e-05, + "loss": 0.1379, + "step": 22333 + }, + { + "epoch": 6.9, + "learning_rate": 1.5235439686520051e-05, + "loss": 0.1266, + "step": 22334 + }, + { + "epoch": 6.9, + "learning_rate": 1.5235013579916447e-05, + "loss": 0.1186, + "step": 22335 + }, + { + "epoch": 6.9, + "learning_rate": 1.5234587460219122e-05, + "loss": 0.124, + "step": 22336 + }, + { + "epoch": 6.9, + "learning_rate": 1.5234161327429133e-05, + "loss": 0.1312, + "step": 22337 + }, + { + "epoch": 6.9, + "learning_rate": 1.5233735181547555e-05, + "loss": 0.1259, + "step": 22338 + }, + { + "epoch": 6.9, + "learning_rate": 1.5233309022575452e-05, + "loss": 0.1293, + "step": 22339 + }, + { + "epoch": 6.9, + "learning_rate": 1.5232882850513889e-05, + "loss": 0.1366, + "step": 22340 + }, + { + "epoch": 6.9, + "learning_rate": 1.5232456665363931e-05, + "loss": 0.1345, + "step": 22341 + }, + { + "epoch": 6.9, + "learning_rate": 1.5232030467126644e-05, + "loss": 0.1315, + "step": 22342 + }, + { + "epoch": 6.9, + "learning_rate": 1.5231604255803092e-05, + "loss": 0.1261, + "step": 22343 + }, + { + "epoch": 6.9, + "learning_rate": 1.5231178031394347e-05, + "loss": 0.1185, + "step": 22344 + }, + { + "epoch": 6.9, + "learning_rate": 1.5230751793901473e-05, + "loss": 0.1309, + "step": 22345 + }, + { + "epoch": 6.9, + "learning_rate": 1.523032554332553e-05, + "loss": 0.13, + "step": 22346 + }, + { + "epoch": 6.9, + "learning_rate": 1.522989927966759e-05, + "loss": 0.1335, + "step": 22347 + }, + { + "epoch": 6.9, + "learning_rate": 1.5229473002928721e-05, + "loss": 0.1186, + "step": 22348 + }, + { + "epoch": 6.9, + "learning_rate": 1.5229046713109984e-05, + "loss": 0.1259, + "step": 22349 + }, + { + "epoch": 6.9, + "learning_rate": 1.5228620410212447e-05, + "loss": 0.1228, + "step": 22350 + }, + { + "epoch": 6.9, + "learning_rate": 1.5228194094237179e-05, + "loss": 0.1328, + "step": 22351 + }, + { + "epoch": 6.9, + "learning_rate": 1.5227767765185241e-05, + "loss": 0.126, + "step": 22352 + }, + { + "epoch": 6.9, + "learning_rate": 1.5227341423057707e-05, + "loss": 0.1321, + "step": 22353 + }, + { + "epoch": 6.9, + "learning_rate": 1.5226915067855634e-05, + "loss": 0.1354, + "step": 22354 + }, + { + "epoch": 6.9, + "learning_rate": 1.5226488699580096e-05, + "loss": 0.1231, + "step": 22355 + }, + { + "epoch": 6.9, + "learning_rate": 1.5226062318232153e-05, + "loss": 0.1372, + "step": 22356 + }, + { + "epoch": 6.9, + "learning_rate": 1.5225635923812878e-05, + "loss": 0.1356, + "step": 22357 + }, + { + "epoch": 6.9, + "learning_rate": 1.5225209516323333e-05, + "loss": 0.1308, + "step": 22358 + }, + { + "epoch": 6.9, + "learning_rate": 1.5224783095764588e-05, + "loss": 0.1201, + "step": 22359 + }, + { + "epoch": 6.91, + "learning_rate": 1.5224356662137706e-05, + "loss": 0.1199, + "step": 22360 + }, + { + "epoch": 6.91, + "learning_rate": 1.5223930215443754e-05, + "loss": 0.1315, + "step": 22361 + }, + { + "epoch": 6.91, + "learning_rate": 1.5223503755683804e-05, + "loss": 0.1347, + "step": 22362 + }, + { + "epoch": 6.91, + "learning_rate": 1.5223077282858913e-05, + "loss": 0.1155, + "step": 22363 + }, + { + "epoch": 6.91, + "learning_rate": 1.5222650796970155e-05, + "loss": 0.127, + "step": 22364 + }, + { + "epoch": 6.91, + "learning_rate": 1.5222224298018597e-05, + "loss": 0.1365, + "step": 22365 + }, + { + "epoch": 6.91, + "learning_rate": 1.52217977860053e-05, + "loss": 0.1203, + "step": 22366 + }, + { + "epoch": 6.91, + "learning_rate": 1.5221371260931337e-05, + "loss": 0.1285, + "step": 22367 + }, + { + "epoch": 6.91, + "learning_rate": 1.522094472279777e-05, + "loss": 0.1286, + "step": 22368 + }, + { + "epoch": 6.91, + "learning_rate": 1.5220518171605672e-05, + "loss": 0.1161, + "step": 22369 + }, + { + "epoch": 6.91, + "learning_rate": 1.5220091607356105e-05, + "loss": 0.1252, + "step": 22370 + }, + { + "epoch": 6.91, + "learning_rate": 1.5219665030050132e-05, + "loss": 0.123, + "step": 22371 + }, + { + "epoch": 6.91, + "learning_rate": 1.521923843968883e-05, + "loss": 0.139, + "step": 22372 + }, + { + "epoch": 6.91, + "learning_rate": 1.5218811836273258e-05, + "loss": 0.1295, + "step": 22373 + }, + { + "epoch": 6.91, + "learning_rate": 1.5218385219804483e-05, + "loss": 0.1216, + "step": 22374 + }, + { + "epoch": 6.91, + "learning_rate": 1.5217958590283582e-05, + "loss": 0.1422, + "step": 22375 + }, + { + "epoch": 6.91, + "learning_rate": 1.521753194771161e-05, + "loss": 0.1268, + "step": 22376 + }, + { + "epoch": 6.91, + "learning_rate": 1.521710529208964e-05, + "loss": 0.1309, + "step": 22377 + }, + { + "epoch": 6.91, + "learning_rate": 1.5216678623418739e-05, + "loss": 0.1276, + "step": 22378 + }, + { + "epoch": 6.91, + "learning_rate": 1.5216251941699971e-05, + "loss": 0.1239, + "step": 22379 + }, + { + "epoch": 6.91, + "learning_rate": 1.5215825246934408e-05, + "loss": 0.1278, + "step": 22380 + }, + { + "epoch": 6.91, + "learning_rate": 1.5215398539123114e-05, + "loss": 0.1315, + "step": 22381 + }, + { + "epoch": 6.91, + "learning_rate": 1.5214971818267154e-05, + "loss": 0.1255, + "step": 22382 + }, + { + "epoch": 6.91, + "learning_rate": 1.5214545084367602e-05, + "loss": 0.1263, + "step": 22383 + }, + { + "epoch": 6.91, + "learning_rate": 1.521411833742552e-05, + "loss": 0.1183, + "step": 22384 + }, + { + "epoch": 6.91, + "learning_rate": 1.5213691577441978e-05, + "loss": 0.1439, + "step": 22385 + }, + { + "epoch": 6.91, + "learning_rate": 1.5213264804418042e-05, + "loss": 0.1264, + "step": 22386 + }, + { + "epoch": 6.91, + "learning_rate": 1.521283801835478e-05, + "loss": 0.1206, + "step": 22387 + }, + { + "epoch": 6.91, + "learning_rate": 1.521241121925326e-05, + "loss": 0.1342, + "step": 22388 + }, + { + "epoch": 6.91, + "learning_rate": 1.5211984407114549e-05, + "loss": 0.121, + "step": 22389 + }, + { + "epoch": 6.91, + "learning_rate": 1.5211557581939715e-05, + "loss": 0.1233, + "step": 22390 + }, + { + "epoch": 6.91, + "learning_rate": 1.521113074372982e-05, + "loss": 0.126, + "step": 22391 + }, + { + "epoch": 6.92, + "learning_rate": 1.5210703892485941e-05, + "loss": 0.119, + "step": 22392 + }, + { + "epoch": 6.92, + "learning_rate": 1.5210277028209141e-05, + "loss": 0.1315, + "step": 22393 + }, + { + "epoch": 6.92, + "learning_rate": 1.5209850150900486e-05, + "loss": 0.1249, + "step": 22394 + }, + { + "epoch": 6.92, + "learning_rate": 1.520942326056105e-05, + "loss": 0.1401, + "step": 22395 + }, + { + "epoch": 6.92, + "learning_rate": 1.5208996357191892e-05, + "loss": 0.136, + "step": 22396 + }, + { + "epoch": 6.92, + "learning_rate": 1.5208569440794083e-05, + "loss": 0.1188, + "step": 22397 + }, + { + "epoch": 6.92, + "learning_rate": 1.5208142511368697e-05, + "loss": 0.1328, + "step": 22398 + }, + { + "epoch": 6.92, + "learning_rate": 1.5207715568916794e-05, + "loss": 0.1203, + "step": 22399 + }, + { + "epoch": 6.92, + "learning_rate": 1.5207288613439444e-05, + "loss": 0.1217, + "step": 22400 + }, + { + "epoch": 6.92, + "learning_rate": 1.5206861644937717e-05, + "loss": 0.1053, + "step": 22401 + }, + { + "epoch": 6.92, + "learning_rate": 1.5206434663412673e-05, + "loss": 0.1406, + "step": 22402 + }, + { + "epoch": 6.92, + "learning_rate": 1.5206007668865392e-05, + "loss": 0.1316, + "step": 22403 + }, + { + "epoch": 6.92, + "learning_rate": 1.5205580661296937e-05, + "loss": 0.1364, + "step": 22404 + }, + { + "epoch": 6.92, + "learning_rate": 1.5205153640708372e-05, + "loss": 0.1283, + "step": 22405 + }, + { + "epoch": 6.92, + "learning_rate": 1.5204726607100773e-05, + "loss": 0.1189, + "step": 22406 + }, + { + "epoch": 6.92, + "learning_rate": 1.52042995604752e-05, + "loss": 0.1229, + "step": 22407 + }, + { + "epoch": 6.92, + "learning_rate": 1.5203872500832723e-05, + "loss": 0.1258, + "step": 22408 + }, + { + "epoch": 6.92, + "learning_rate": 1.5203445428174415e-05, + "loss": 0.1296, + "step": 22409 + }, + { + "epoch": 6.92, + "learning_rate": 1.520301834250134e-05, + "loss": 0.1326, + "step": 22410 + }, + { + "epoch": 6.92, + "learning_rate": 1.520259124381457e-05, + "loss": 0.1293, + "step": 22411 + }, + { + "epoch": 6.92, + "learning_rate": 1.5202164132115167e-05, + "loss": 0.1307, + "step": 22412 + }, + { + "epoch": 6.92, + "learning_rate": 1.5201737007404203e-05, + "loss": 0.1307, + "step": 22413 + }, + { + "epoch": 6.92, + "learning_rate": 1.5201309869682745e-05, + "loss": 0.123, + "step": 22414 + }, + { + "epoch": 6.92, + "learning_rate": 1.5200882718951863e-05, + "loss": 0.1281, + "step": 22415 + }, + { + "epoch": 6.92, + "learning_rate": 1.5200455555212626e-05, + "loss": 0.1324, + "step": 22416 + }, + { + "epoch": 6.92, + "learning_rate": 1.5200028378466101e-05, + "loss": 0.1229, + "step": 22417 + }, + { + "epoch": 6.92, + "learning_rate": 1.5199601188713356e-05, + "loss": 0.1265, + "step": 22418 + }, + { + "epoch": 6.92, + "learning_rate": 1.519917398595546e-05, + "loss": 0.1292, + "step": 22419 + }, + { + "epoch": 6.92, + "learning_rate": 1.519874677019348e-05, + "loss": 0.1321, + "step": 22420 + }, + { + "epoch": 6.92, + "learning_rate": 1.5198319541428493e-05, + "loss": 0.1272, + "step": 22421 + }, + { + "epoch": 6.92, + "learning_rate": 1.5197892299661551e-05, + "loss": 0.126, + "step": 22422 + }, + { + "epoch": 6.92, + "learning_rate": 1.5197465044893738e-05, + "loss": 0.1202, + "step": 22423 + }, + { + "epoch": 6.93, + "learning_rate": 1.5197037777126119e-05, + "loss": 0.1176, + "step": 22424 + }, + { + "epoch": 6.93, + "learning_rate": 1.5196610496359754e-05, + "loss": 0.1238, + "step": 22425 + }, + { + "epoch": 6.93, + "learning_rate": 1.5196183202595723e-05, + "loss": 0.1223, + "step": 22426 + }, + { + "epoch": 6.93, + "learning_rate": 1.5195755895835089e-05, + "loss": 0.1263, + "step": 22427 + }, + { + "epoch": 6.93, + "learning_rate": 1.519532857607892e-05, + "loss": 0.1247, + "step": 22428 + }, + { + "epoch": 6.93, + "learning_rate": 1.519490124332829e-05, + "loss": 0.1211, + "step": 22429 + }, + { + "epoch": 6.93, + "learning_rate": 1.5194473897584266e-05, + "loss": 0.1185, + "step": 22430 + }, + { + "epoch": 6.93, + "learning_rate": 1.519404653884791e-05, + "loss": 0.119, + "step": 22431 + }, + { + "epoch": 6.93, + "learning_rate": 1.5193619167120298e-05, + "loss": 0.1226, + "step": 22432 + }, + { + "epoch": 6.93, + "learning_rate": 1.5193191782402496e-05, + "loss": 0.1259, + "step": 22433 + }, + { + "epoch": 6.93, + "learning_rate": 1.5192764384695578e-05, + "loss": 0.1312, + "step": 22434 + }, + { + "epoch": 6.93, + "learning_rate": 1.5192336974000608e-05, + "loss": 0.1282, + "step": 22435 + }, + { + "epoch": 6.93, + "learning_rate": 1.5191909550318655e-05, + "loss": 0.1351, + "step": 22436 + }, + { + "epoch": 6.93, + "learning_rate": 1.5191482113650789e-05, + "loss": 0.1193, + "step": 22437 + }, + { + "epoch": 6.93, + "learning_rate": 1.5191054663998079e-05, + "loss": 0.124, + "step": 22438 + }, + { + "epoch": 6.93, + "learning_rate": 1.5190627201361596e-05, + "loss": 0.1228, + "step": 22439 + }, + { + "epoch": 6.93, + "learning_rate": 1.519019972574241e-05, + "loss": 0.114, + "step": 22440 + }, + { + "epoch": 6.93, + "learning_rate": 1.5189772237141585e-05, + "loss": 0.1304, + "step": 22441 + }, + { + "epoch": 6.93, + "learning_rate": 1.5189344735560192e-05, + "loss": 0.1202, + "step": 22442 + }, + { + "epoch": 6.93, + "learning_rate": 1.5188917220999301e-05, + "loss": 0.1148, + "step": 22443 + }, + { + "epoch": 6.93, + "learning_rate": 1.5188489693459984e-05, + "loss": 0.1322, + "step": 22444 + }, + { + "epoch": 6.93, + "learning_rate": 1.5188062152943305e-05, + "loss": 0.1183, + "step": 22445 + }, + { + "epoch": 6.93, + "learning_rate": 1.5187634599450341e-05, + "loss": 0.1313, + "step": 22446 + }, + { + "epoch": 6.93, + "learning_rate": 1.5187207032982153e-05, + "loss": 0.1341, + "step": 22447 + }, + { + "epoch": 6.93, + "learning_rate": 1.5186779453539815e-05, + "loss": 0.1198, + "step": 22448 + }, + { + "epoch": 6.93, + "learning_rate": 1.5186351861124398e-05, + "loss": 0.1291, + "step": 22449 + }, + { + "epoch": 6.93, + "learning_rate": 1.5185924255736964e-05, + "loss": 0.1215, + "step": 22450 + }, + { + "epoch": 6.93, + "learning_rate": 1.5185496637378592e-05, + "loss": 0.1509, + "step": 22451 + }, + { + "epoch": 6.93, + "learning_rate": 1.5185069006050346e-05, + "loss": 0.1223, + "step": 22452 + }, + { + "epoch": 6.93, + "learning_rate": 1.5184641361753297e-05, + "loss": 0.1289, + "step": 22453 + }, + { + "epoch": 6.93, + "learning_rate": 1.5184213704488514e-05, + "loss": 0.116, + "step": 22454 + }, + { + "epoch": 6.93, + "learning_rate": 1.5183786034257067e-05, + "loss": 0.1298, + "step": 22455 + }, + { + "epoch": 6.93, + "learning_rate": 1.5183358351060023e-05, + "loss": 0.1284, + "step": 22456 + }, + { + "epoch": 6.94, + "learning_rate": 1.5182930654898458e-05, + "loss": 0.1288, + "step": 22457 + }, + { + "epoch": 6.94, + "learning_rate": 1.5182502945773436e-05, + "loss": 0.1258, + "step": 22458 + }, + { + "epoch": 6.94, + "learning_rate": 1.5182075223686028e-05, + "loss": 0.1259, + "step": 22459 + }, + { + "epoch": 6.94, + "learning_rate": 1.5181647488637308e-05, + "loss": 0.1241, + "step": 22460 + }, + { + "epoch": 6.94, + "learning_rate": 1.5181219740628341e-05, + "loss": 0.1154, + "step": 22461 + }, + { + "epoch": 6.94, + "learning_rate": 1.5180791979660198e-05, + "loss": 0.1325, + "step": 22462 + }, + { + "epoch": 6.94, + "learning_rate": 1.5180364205733948e-05, + "loss": 0.1397, + "step": 22463 + }, + { + "epoch": 6.94, + "learning_rate": 1.5179936418850667e-05, + "loss": 0.1412, + "step": 22464 + }, + { + "epoch": 6.94, + "learning_rate": 1.5179508619011416e-05, + "loss": 0.1262, + "step": 22465 + }, + { + "epoch": 6.94, + "learning_rate": 1.517908080621727e-05, + "loss": 0.1238, + "step": 22466 + }, + { + "epoch": 6.94, + "learning_rate": 1.51786529804693e-05, + "loss": 0.1235, + "step": 22467 + }, + { + "epoch": 6.94, + "learning_rate": 1.5178225141768572e-05, + "loss": 0.1408, + "step": 22468 + }, + { + "epoch": 6.94, + "learning_rate": 1.5177797290116161e-05, + "loss": 0.1353, + "step": 22469 + }, + { + "epoch": 6.94, + "learning_rate": 1.5177369425513134e-05, + "loss": 0.1426, + "step": 22470 + }, + { + "epoch": 6.94, + "learning_rate": 1.517694154796056e-05, + "loss": 0.1294, + "step": 22471 + }, + { + "epoch": 6.94, + "learning_rate": 1.5176513657459511e-05, + "loss": 0.1258, + "step": 22472 + }, + { + "epoch": 6.94, + "learning_rate": 1.5176085754011058e-05, + "loss": 0.125, + "step": 22473 + }, + { + "epoch": 6.94, + "learning_rate": 1.517565783761627e-05, + "loss": 0.121, + "step": 22474 + }, + { + "epoch": 6.94, + "learning_rate": 1.517522990827622e-05, + "loss": 0.1335, + "step": 22475 + }, + { + "epoch": 6.94, + "learning_rate": 1.5174801965991974e-05, + "loss": 0.1302, + "step": 22476 + }, + { + "epoch": 6.94, + "learning_rate": 1.5174374010764603e-05, + "loss": 0.1395, + "step": 22477 + }, + { + "epoch": 6.94, + "learning_rate": 1.5173946042595184e-05, + "loss": 0.1284, + "step": 22478 + }, + { + "epoch": 6.94, + "learning_rate": 1.5173518061484777e-05, + "loss": 0.1259, + "step": 22479 + }, + { + "epoch": 6.94, + "learning_rate": 1.5173090067434464e-05, + "loss": 0.1271, + "step": 22480 + }, + { + "epoch": 6.94, + "learning_rate": 1.5172662060445302e-05, + "loss": 0.1463, + "step": 22481 + }, + { + "epoch": 6.94, + "learning_rate": 1.517223404051837e-05, + "loss": 0.1223, + "step": 22482 + }, + { + "epoch": 6.94, + "learning_rate": 1.517180600765474e-05, + "loss": 0.1288, + "step": 22483 + }, + { + "epoch": 6.94, + "learning_rate": 1.5171377961855477e-05, + "loss": 0.1224, + "step": 22484 + }, + { + "epoch": 6.94, + "learning_rate": 1.5170949903121661e-05, + "loss": 0.1295, + "step": 22485 + }, + { + "epoch": 6.94, + "learning_rate": 1.517052183145435e-05, + "loss": 0.1189, + "step": 22486 + }, + { + "epoch": 6.94, + "learning_rate": 1.5170093746854621e-05, + "loss": 0.1275, + "step": 22487 + }, + { + "epoch": 6.94, + "learning_rate": 1.5169665649323549e-05, + "loss": 0.1305, + "step": 22488 + }, + { + "epoch": 6.95, + "learning_rate": 1.5169237538862197e-05, + "loss": 0.1182, + "step": 22489 + }, + { + "epoch": 6.95, + "learning_rate": 1.5168809415471638e-05, + "loss": 0.1296, + "step": 22490 + }, + { + "epoch": 6.95, + "learning_rate": 1.5168381279152949e-05, + "loss": 0.1298, + "step": 22491 + }, + { + "epoch": 6.95, + "learning_rate": 1.516795312990719e-05, + "loss": 0.1309, + "step": 22492 + }, + { + "epoch": 6.95, + "learning_rate": 1.5167524967735441e-05, + "loss": 0.1313, + "step": 22493 + }, + { + "epoch": 6.95, + "learning_rate": 1.516709679263877e-05, + "loss": 0.1223, + "step": 22494 + }, + { + "epoch": 6.95, + "learning_rate": 1.5166668604618244e-05, + "loss": 0.1284, + "step": 22495 + }, + { + "epoch": 6.95, + "learning_rate": 1.5166240403674939e-05, + "loss": 0.1147, + "step": 22496 + }, + { + "epoch": 6.95, + "learning_rate": 1.5165812189809925e-05, + "loss": 0.1358, + "step": 22497 + }, + { + "epoch": 6.95, + "learning_rate": 1.5165383963024271e-05, + "loss": 0.1262, + "step": 22498 + }, + { + "epoch": 6.95, + "learning_rate": 1.5164955723319052e-05, + "loss": 0.1367, + "step": 22499 + }, + { + "epoch": 6.95, + "learning_rate": 1.5164527470695335e-05, + "loss": 0.1255, + "step": 22500 + }, + { + "epoch": 6.95, + "learning_rate": 1.5164099205154195e-05, + "loss": 0.1341, + "step": 22501 + }, + { + "epoch": 6.95, + "learning_rate": 1.51636709266967e-05, + "loss": 0.1307, + "step": 22502 + }, + { + "epoch": 6.95, + "learning_rate": 1.516324263532392e-05, + "loss": 0.1192, + "step": 22503 + }, + { + "epoch": 6.95, + "learning_rate": 1.5162814331036932e-05, + "loss": 0.1343, + "step": 22504 + }, + { + "epoch": 6.95, + "learning_rate": 1.5162386013836802e-05, + "loss": 0.1331, + "step": 22505 + }, + { + "epoch": 6.95, + "learning_rate": 1.5161957683724604e-05, + "loss": 0.1324, + "step": 22506 + }, + { + "epoch": 6.95, + "learning_rate": 1.5161529340701405e-05, + "loss": 0.1258, + "step": 22507 + }, + { + "epoch": 6.95, + "learning_rate": 1.5161100984768282e-05, + "loss": 0.1303, + "step": 22508 + }, + { + "epoch": 6.95, + "learning_rate": 1.5160672615926307e-05, + "loss": 0.1246, + "step": 22509 + }, + { + "epoch": 6.95, + "learning_rate": 1.5160244234176542e-05, + "loss": 0.1304, + "step": 22510 + }, + { + "epoch": 6.95, + "learning_rate": 1.5159815839520073e-05, + "loss": 0.1315, + "step": 22511 + }, + { + "epoch": 6.95, + "learning_rate": 1.5159387431957959e-05, + "loss": 0.1294, + "step": 22512 + }, + { + "epoch": 6.95, + "learning_rate": 1.5158959011491274e-05, + "loss": 0.1278, + "step": 22513 + }, + { + "epoch": 6.95, + "learning_rate": 1.5158530578121096e-05, + "loss": 0.1373, + "step": 22514 + }, + { + "epoch": 6.95, + "learning_rate": 1.5158102131848486e-05, + "loss": 0.1333, + "step": 22515 + }, + { + "epoch": 6.95, + "learning_rate": 1.5157673672674529e-05, + "loss": 0.1211, + "step": 22516 + }, + { + "epoch": 6.95, + "learning_rate": 1.5157245200600286e-05, + "loss": 0.1214, + "step": 22517 + }, + { + "epoch": 6.95, + "learning_rate": 1.5156816715626832e-05, + "loss": 0.1315, + "step": 22518 + }, + { + "epoch": 6.95, + "learning_rate": 1.515638821775524e-05, + "loss": 0.1265, + "step": 22519 + }, + { + "epoch": 6.95, + "learning_rate": 1.5155959706986578e-05, + "loss": 0.1351, + "step": 22520 + }, + { + "epoch": 6.95, + "learning_rate": 1.5155531183321923e-05, + "loss": 0.1124, + "step": 22521 + }, + { + "epoch": 6.96, + "learning_rate": 1.5155102646762343e-05, + "loss": 0.1131, + "step": 22522 + }, + { + "epoch": 6.96, + "learning_rate": 1.5154674097308912e-05, + "loss": 0.1337, + "step": 22523 + }, + { + "epoch": 6.96, + "learning_rate": 1.5154245534962702e-05, + "loss": 0.1284, + "step": 22524 + }, + { + "epoch": 6.96, + "learning_rate": 1.5153816959724781e-05, + "loss": 0.1255, + "step": 22525 + }, + { + "epoch": 6.96, + "learning_rate": 1.5153388371596226e-05, + "loss": 0.1247, + "step": 22526 + }, + { + "epoch": 6.96, + "learning_rate": 1.5152959770578103e-05, + "loss": 0.1202, + "step": 22527 + }, + { + "epoch": 6.96, + "learning_rate": 1.5152531156671492e-05, + "loss": 0.1339, + "step": 22528 + }, + { + "epoch": 6.96, + "learning_rate": 1.5152102529877461e-05, + "loss": 0.1372, + "step": 22529 + }, + { + "epoch": 6.96, + "learning_rate": 1.5151673890197078e-05, + "loss": 0.1213, + "step": 22530 + }, + { + "epoch": 6.96, + "learning_rate": 1.5151245237631422e-05, + "loss": 0.1091, + "step": 22531 + }, + { + "epoch": 6.96, + "learning_rate": 1.5150816572181562e-05, + "loss": 0.1275, + "step": 22532 + }, + { + "epoch": 6.96, + "learning_rate": 1.5150387893848568e-05, + "loss": 0.1276, + "step": 22533 + }, + { + "epoch": 6.96, + "learning_rate": 1.5149959202633517e-05, + "loss": 0.1313, + "step": 22534 + }, + { + "epoch": 6.96, + "learning_rate": 1.5149530498537477e-05, + "loss": 0.1277, + "step": 22535 + }, + { + "epoch": 6.96, + "learning_rate": 1.5149101781561523e-05, + "loss": 0.1178, + "step": 22536 + }, + { + "epoch": 6.96, + "learning_rate": 1.514867305170673e-05, + "loss": 0.127, + "step": 22537 + }, + { + "epoch": 6.96, + "learning_rate": 1.514824430897416e-05, + "loss": 0.1091, + "step": 22538 + }, + { + "epoch": 6.96, + "learning_rate": 1.5147815553364895e-05, + "loss": 0.1213, + "step": 22539 + }, + { + "epoch": 6.96, + "learning_rate": 1.5147386784880006e-05, + "loss": 0.1278, + "step": 22540 + }, + { + "epoch": 6.96, + "learning_rate": 1.514695800352056e-05, + "loss": 0.125, + "step": 22541 + }, + { + "epoch": 6.96, + "learning_rate": 1.5146529209287637e-05, + "loss": 0.1393, + "step": 22542 + }, + { + "epoch": 6.96, + "learning_rate": 1.5146100402182304e-05, + "loss": 0.1359, + "step": 22543 + }, + { + "epoch": 6.96, + "learning_rate": 1.5145671582205635e-05, + "loss": 0.1279, + "step": 22544 + }, + { + "epoch": 6.96, + "learning_rate": 1.5145242749358703e-05, + "loss": 0.1263, + "step": 22545 + }, + { + "epoch": 6.96, + "learning_rate": 1.5144813903642582e-05, + "loss": 0.1208, + "step": 22546 + }, + { + "epoch": 6.96, + "learning_rate": 1.5144385045058344e-05, + "loss": 0.1276, + "step": 22547 + }, + { + "epoch": 6.96, + "learning_rate": 1.5143956173607057e-05, + "loss": 0.1322, + "step": 22548 + }, + { + "epoch": 6.96, + "learning_rate": 1.5143527289289797e-05, + "loss": 0.1231, + "step": 22549 + }, + { + "epoch": 6.96, + "learning_rate": 1.514309839210764e-05, + "loss": 0.1192, + "step": 22550 + }, + { + "epoch": 6.96, + "learning_rate": 1.5142669482061655e-05, + "loss": 0.1285, + "step": 22551 + }, + { + "epoch": 6.96, + "learning_rate": 1.5142240559152916e-05, + "loss": 0.1185, + "step": 22552 + }, + { + "epoch": 6.96, + "learning_rate": 1.5141811623382495e-05, + "loss": 0.1331, + "step": 22553 + }, + { + "epoch": 6.97, + "learning_rate": 1.5141382674751466e-05, + "loss": 0.1343, + "step": 22554 + }, + { + "epoch": 6.97, + "learning_rate": 1.51409537132609e-05, + "loss": 0.125, + "step": 22555 + }, + { + "epoch": 6.97, + "learning_rate": 1.5140524738911872e-05, + "loss": 0.122, + "step": 22556 + }, + { + "epoch": 6.97, + "learning_rate": 1.5140095751705453e-05, + "loss": 0.1094, + "step": 22557 + }, + { + "epoch": 6.97, + "learning_rate": 1.5139666751642716e-05, + "loss": 0.1189, + "step": 22558 + }, + { + "epoch": 6.97, + "learning_rate": 1.5139237738724738e-05, + "loss": 0.1218, + "step": 22559 + }, + { + "epoch": 6.97, + "learning_rate": 1.513880871295259e-05, + "loss": 0.1145, + "step": 22560 + }, + { + "epoch": 6.97, + "learning_rate": 1.5138379674327342e-05, + "loss": 0.1232, + "step": 22561 + }, + { + "epoch": 6.97, + "learning_rate": 1.5137950622850068e-05, + "loss": 0.1191, + "step": 22562 + }, + { + "epoch": 6.97, + "learning_rate": 1.5137521558521846e-05, + "loss": 0.1361, + "step": 22563 + }, + { + "epoch": 6.97, + "learning_rate": 1.513709248134374e-05, + "loss": 0.1316, + "step": 22564 + }, + { + "epoch": 6.97, + "learning_rate": 1.5136663391316835e-05, + "loss": 0.143, + "step": 22565 + }, + { + "epoch": 6.97, + "learning_rate": 1.5136234288442193e-05, + "loss": 0.1204, + "step": 22566 + }, + { + "epoch": 6.97, + "learning_rate": 1.5135805172720894e-05, + "loss": 0.113, + "step": 22567 + }, + { + "epoch": 6.97, + "learning_rate": 1.5135376044154013e-05, + "loss": 0.1225, + "step": 22568 + }, + { + "epoch": 6.97, + "learning_rate": 1.5134946902742615e-05, + "loss": 0.124, + "step": 22569 + }, + { + "epoch": 6.97, + "learning_rate": 1.5134517748487781e-05, + "loss": 0.1186, + "step": 22570 + }, + { + "epoch": 6.97, + "learning_rate": 1.5134088581390581e-05, + "loss": 0.131, + "step": 22571 + }, + { + "epoch": 6.97, + "learning_rate": 1.5133659401452087e-05, + "loss": 0.1236, + "step": 22572 + }, + { + "epoch": 6.97, + "learning_rate": 1.5133230208673378e-05, + "loss": 0.1372, + "step": 22573 + }, + { + "epoch": 6.97, + "learning_rate": 1.5132801003055522e-05, + "loss": 0.1265, + "step": 22574 + }, + { + "epoch": 6.97, + "learning_rate": 1.5132371784599595e-05, + "loss": 0.1222, + "step": 22575 + }, + { + "epoch": 6.97, + "learning_rate": 1.513194255330667e-05, + "loss": 0.1262, + "step": 22576 + }, + { + "epoch": 6.97, + "learning_rate": 1.5131513309177818e-05, + "loss": 0.121, + "step": 22577 + }, + { + "epoch": 6.97, + "learning_rate": 1.513108405221412e-05, + "loss": 0.1196, + "step": 22578 + }, + { + "epoch": 6.97, + "learning_rate": 1.5130654782416642e-05, + "loss": 0.1226, + "step": 22579 + }, + { + "epoch": 6.97, + "learning_rate": 1.5130225499786462e-05, + "loss": 0.1259, + "step": 22580 + }, + { + "epoch": 6.97, + "learning_rate": 1.5129796204324651e-05, + "loss": 0.1301, + "step": 22581 + }, + { + "epoch": 6.97, + "learning_rate": 1.5129366896032282e-05, + "loss": 0.1185, + "step": 22582 + }, + { + "epoch": 6.97, + "learning_rate": 1.5128937574910436e-05, + "loss": 0.1275, + "step": 22583 + }, + { + "epoch": 6.97, + "learning_rate": 1.512850824096018e-05, + "loss": 0.1308, + "step": 22584 + }, + { + "epoch": 6.97, + "learning_rate": 1.5128078894182587e-05, + "loss": 0.1162, + "step": 22585 + }, + { + "epoch": 6.98, + "learning_rate": 1.5127649534578734e-05, + "loss": 0.1187, + "step": 22586 + }, + { + "epoch": 6.98, + "learning_rate": 1.5127220162149697e-05, + "loss": 0.1323, + "step": 22587 + }, + { + "epoch": 6.98, + "learning_rate": 1.5126790776896547e-05, + "loss": 0.1295, + "step": 22588 + }, + { + "epoch": 6.98, + "learning_rate": 1.5126361378820356e-05, + "loss": 0.1275, + "step": 22589 + }, + { + "epoch": 6.98, + "learning_rate": 1.5125931967922201e-05, + "loss": 0.1217, + "step": 22590 + }, + { + "epoch": 6.98, + "learning_rate": 1.5125502544203156e-05, + "loss": 0.1351, + "step": 22591 + }, + { + "epoch": 6.98, + "learning_rate": 1.5125073107664293e-05, + "loss": 0.122, + "step": 22592 + }, + { + "epoch": 6.98, + "learning_rate": 1.512464365830669e-05, + "loss": 0.1235, + "step": 22593 + }, + { + "epoch": 6.98, + "learning_rate": 1.5124214196131414e-05, + "loss": 0.1225, + "step": 22594 + }, + { + "epoch": 6.98, + "learning_rate": 1.5123784721139547e-05, + "loss": 0.1347, + "step": 22595 + }, + { + "epoch": 6.98, + "learning_rate": 1.512335523333216e-05, + "loss": 0.1257, + "step": 22596 + }, + { + "epoch": 6.98, + "learning_rate": 1.5122925732710325e-05, + "loss": 0.1276, + "step": 22597 + }, + { + "epoch": 6.98, + "learning_rate": 1.5122496219275121e-05, + "loss": 0.1257, + "step": 22598 + }, + { + "epoch": 6.98, + "learning_rate": 1.5122066693027616e-05, + "loss": 0.1251, + "step": 22599 + }, + { + "epoch": 6.98, + "learning_rate": 1.5121637153968891e-05, + "loss": 0.1264, + "step": 22600 + }, + { + "epoch": 6.98, + "learning_rate": 1.5121207602100017e-05, + "loss": 0.1264, + "step": 22601 + }, + { + "epoch": 6.98, + "learning_rate": 1.5120778037422069e-05, + "loss": 0.1321, + "step": 22602 + }, + { + "epoch": 6.98, + "learning_rate": 1.512034845993612e-05, + "loss": 0.1322, + "step": 22603 + }, + { + "epoch": 6.98, + "learning_rate": 1.5119918869643247e-05, + "loss": 0.1222, + "step": 22604 + }, + { + "epoch": 6.98, + "learning_rate": 1.5119489266544522e-05, + "loss": 0.1255, + "step": 22605 + }, + { + "epoch": 6.98, + "learning_rate": 1.5119059650641022e-05, + "loss": 0.1262, + "step": 22606 + }, + { + "epoch": 6.98, + "learning_rate": 1.5118630021933815e-05, + "loss": 0.1183, + "step": 22607 + }, + { + "epoch": 6.98, + "learning_rate": 1.5118200380423986e-05, + "loss": 0.1191, + "step": 22608 + }, + { + "epoch": 6.98, + "learning_rate": 1.5117770726112603e-05, + "loss": 0.1331, + "step": 22609 + }, + { + "epoch": 6.98, + "learning_rate": 1.5117341059000743e-05, + "loss": 0.144, + "step": 22610 + }, + { + "epoch": 6.98, + "learning_rate": 1.5116911379089478e-05, + "loss": 0.1365, + "step": 22611 + }, + { + "epoch": 6.98, + "learning_rate": 1.5116481686379887e-05, + "loss": 0.1339, + "step": 22612 + }, + { + "epoch": 6.98, + "learning_rate": 1.5116051980873038e-05, + "loss": 0.1145, + "step": 22613 + }, + { + "epoch": 6.98, + "learning_rate": 1.5115622262570014e-05, + "loss": 0.1315, + "step": 22614 + }, + { + "epoch": 6.98, + "learning_rate": 1.5115192531471884e-05, + "loss": 0.1401, + "step": 22615 + }, + { + "epoch": 6.98, + "learning_rate": 1.5114762787579724e-05, + "loss": 0.1289, + "step": 22616 + }, + { + "epoch": 6.98, + "learning_rate": 1.5114333030894607e-05, + "loss": 0.1381, + "step": 22617 + }, + { + "epoch": 6.98, + "learning_rate": 1.5113903261417613e-05, + "loss": 0.1245, + "step": 22618 + }, + { + "epoch": 6.99, + "learning_rate": 1.5113473479149816e-05, + "loss": 0.1266, + "step": 22619 + }, + { + "epoch": 6.99, + "learning_rate": 1.5113043684092286e-05, + "loss": 0.1273, + "step": 22620 + }, + { + "epoch": 6.99, + "learning_rate": 1.5112613876246103e-05, + "loss": 0.1283, + "step": 22621 + }, + { + "epoch": 6.99, + "learning_rate": 1.5112184055612341e-05, + "loss": 0.13, + "step": 22622 + }, + { + "epoch": 6.99, + "learning_rate": 1.5111754222192072e-05, + "loss": 0.1336, + "step": 22623 + }, + { + "epoch": 6.99, + "learning_rate": 1.5111324375986376e-05, + "loss": 0.1296, + "step": 22624 + }, + { + "epoch": 6.99, + "learning_rate": 1.5110894516996324e-05, + "loss": 0.1321, + "step": 22625 + }, + { + "epoch": 6.99, + "learning_rate": 1.511046464522299e-05, + "loss": 0.1285, + "step": 22626 + }, + { + "epoch": 6.99, + "learning_rate": 1.5110034760667458e-05, + "loss": 0.1309, + "step": 22627 + }, + { + "epoch": 6.99, + "learning_rate": 1.510960486333079e-05, + "loss": 0.1302, + "step": 22628 + }, + { + "epoch": 6.99, + "learning_rate": 1.5109174953214073e-05, + "loss": 0.1373, + "step": 22629 + }, + { + "epoch": 6.99, + "learning_rate": 1.5108745030318378e-05, + "loss": 0.1298, + "step": 22630 + }, + { + "epoch": 6.99, + "learning_rate": 1.5108315094644775e-05, + "loss": 0.1281, + "step": 22631 + }, + { + "epoch": 6.99, + "learning_rate": 1.510788514619435e-05, + "loss": 0.132, + "step": 22632 + }, + { + "epoch": 6.99, + "learning_rate": 1.5107455184968171e-05, + "loss": 0.1176, + "step": 22633 + }, + { + "epoch": 6.99, + "learning_rate": 1.5107025210967314e-05, + "loss": 0.1209, + "step": 22634 + }, + { + "epoch": 6.99, + "learning_rate": 1.5106595224192855e-05, + "loss": 0.1199, + "step": 22635 + }, + { + "epoch": 6.99, + "learning_rate": 1.510616522464587e-05, + "loss": 0.127, + "step": 22636 + }, + { + "epoch": 6.99, + "learning_rate": 1.5105735212327437e-05, + "loss": 0.1342, + "step": 22637 + }, + { + "epoch": 6.99, + "learning_rate": 1.5105305187238626e-05, + "loss": 0.1245, + "step": 22638 + }, + { + "epoch": 6.99, + "learning_rate": 1.5104875149380518e-05, + "loss": 0.1329, + "step": 22639 + }, + { + "epoch": 6.99, + "learning_rate": 1.5104445098754184e-05, + "loss": 0.1322, + "step": 22640 + }, + { + "epoch": 6.99, + "learning_rate": 1.5104015035360702e-05, + "loss": 0.1236, + "step": 22641 + }, + { + "epoch": 6.99, + "learning_rate": 1.510358495920115e-05, + "loss": 0.1348, + "step": 22642 + }, + { + "epoch": 6.99, + "learning_rate": 1.5103154870276597e-05, + "loss": 0.124, + "step": 22643 + }, + { + "epoch": 6.99, + "learning_rate": 1.5102724768588126e-05, + "loss": 0.129, + "step": 22644 + }, + { + "epoch": 6.99, + "learning_rate": 1.5102294654136809e-05, + "loss": 0.1397, + "step": 22645 + }, + { + "epoch": 6.99, + "learning_rate": 1.5101864526923721e-05, + "loss": 0.1295, + "step": 22646 + }, + { + "epoch": 6.99, + "learning_rate": 1.5101434386949945e-05, + "loss": 0.1259, + "step": 22647 + }, + { + "epoch": 6.99, + "learning_rate": 1.5101004234216544e-05, + "loss": 0.1358, + "step": 22648 + }, + { + "epoch": 6.99, + "learning_rate": 1.5100574068724602e-05, + "loss": 0.1272, + "step": 22649 + }, + { + "epoch": 6.99, + "learning_rate": 1.51001438904752e-05, + "loss": 0.123, + "step": 22650 + }, + { + "epoch": 7.0, + "learning_rate": 1.50997136994694e-05, + "loss": 0.1178, + "step": 22651 + }, + { + "epoch": 7.0, + "learning_rate": 1.5099283495708292e-05, + "loss": 0.1292, + "step": 22652 + }, + { + "epoch": 7.0, + "learning_rate": 1.5098853279192942e-05, + "loss": 0.1329, + "step": 22653 + }, + { + "epoch": 7.0, + "learning_rate": 1.509842304992443e-05, + "loss": 0.1274, + "step": 22654 + }, + { + "epoch": 7.0, + "learning_rate": 1.5097992807903837e-05, + "loss": 0.1315, + "step": 22655 + }, + { + "epoch": 7.0, + "learning_rate": 1.509756255313223e-05, + "loss": 0.121, + "step": 22656 + }, + { + "epoch": 7.0, + "learning_rate": 1.509713228561069e-05, + "loss": 0.1347, + "step": 22657 + }, + { + "epoch": 7.0, + "learning_rate": 1.5096702005340293e-05, + "loss": 0.1225, + "step": 22658 + }, + { + "epoch": 7.0, + "learning_rate": 1.5096271712322112e-05, + "loss": 0.1298, + "step": 22659 + }, + { + "epoch": 7.0, + "learning_rate": 1.509584140655723e-05, + "loss": 0.1376, + "step": 22660 + }, + { + "epoch": 7.0, + "learning_rate": 1.5095411088046716e-05, + "loss": 0.1301, + "step": 22661 + }, + { + "epoch": 7.0, + "learning_rate": 1.5094980756791653e-05, + "loss": 0.1323, + "step": 22662 + }, + { + "epoch": 7.0, + "learning_rate": 1.5094550412793112e-05, + "loss": 0.1316, + "step": 22663 + }, + { + "epoch": 7.0, + "learning_rate": 1.5094120056052171e-05, + "loss": 0.1231, + "step": 22664 + }, + { + "epoch": 7.0, + "learning_rate": 1.5093689686569905e-05, + "loss": 0.143, + "step": 22665 + }, + { + "epoch": 7.0, + "learning_rate": 1.5093259304347396e-05, + "loss": 0.1249, + "step": 22666 + }, + { + "epoch": 7.0, + "learning_rate": 1.5092828909385713e-05, + "loss": 0.125, + "step": 22667 + }, + { + "epoch": 7.0, + "learning_rate": 1.5092398501685938e-05, + "loss": 0.0713, + "step": 22668 + }, + { + "epoch": 7.0, + "learning_rate": 1.5091968081249145e-05, + "loss": 0.0608, + "step": 22669 + }, + { + "epoch": 7.0, + "learning_rate": 1.5091537648076411e-05, + "loss": 0.0601, + "step": 22670 + }, + { + "epoch": 7.0, + "learning_rate": 1.509110720216881e-05, + "loss": 0.0515, + "step": 22671 + }, + { + "epoch": 7.0, + "learning_rate": 1.5090676743527426e-05, + "loss": 0.0599, + "step": 22672 + }, + { + "epoch": 7.0, + "learning_rate": 1.509024627215333e-05, + "loss": 0.0623, + "step": 22673 + }, + { + "epoch": 7.0, + "learning_rate": 1.5089815788047597e-05, + "loss": 0.0585, + "step": 22674 + }, + { + "epoch": 7.0, + "learning_rate": 1.5089385291211307e-05, + "loss": 0.0637, + "step": 22675 + }, + { + "epoch": 7.0, + "learning_rate": 1.5088954781645542e-05, + "loss": 0.0597, + "step": 22676 + }, + { + "epoch": 7.0, + "learning_rate": 1.5088524259351365e-05, + "loss": 0.0666, + "step": 22677 + }, + { + "epoch": 7.0, + "learning_rate": 1.5088093724329867e-05, + "loss": 0.0692, + "step": 22678 + }, + { + "epoch": 7.0, + "learning_rate": 1.5087663176582112e-05, + "loss": 0.0494, + "step": 22679 + }, + { + "epoch": 7.0, + "learning_rate": 1.5087232616109187e-05, + "loss": 0.0542, + "step": 22680 + }, + { + "epoch": 7.0, + "learning_rate": 1.5086802042912168e-05, + "loss": 0.0583, + "step": 22681 + }, + { + "epoch": 7.0, + "learning_rate": 1.5086371456992124e-05, + "loss": 0.0604, + "step": 22682 + }, + { + "epoch": 7.01, + "learning_rate": 1.5085940858350143e-05, + "loss": 0.0613, + "step": 22683 + }, + { + "epoch": 7.01, + "learning_rate": 1.5085510246987291e-05, + "loss": 0.0582, + "step": 22684 + }, + { + "epoch": 7.01, + "learning_rate": 1.508507962290465e-05, + "loss": 0.0579, + "step": 22685 + }, + { + "epoch": 7.01, + "learning_rate": 1.5084648986103303e-05, + "loss": 0.0647, + "step": 22686 + }, + { + "epoch": 7.01, + "learning_rate": 1.508421833658432e-05, + "loss": 0.0585, + "step": 22687 + }, + { + "epoch": 7.01, + "learning_rate": 1.5083787674348776e-05, + "loss": 0.0584, + "step": 22688 + }, + { + "epoch": 7.01, + "learning_rate": 1.5083356999397754e-05, + "loss": 0.0586, + "step": 22689 + }, + { + "epoch": 7.01, + "learning_rate": 1.5082926311732328e-05, + "loss": 0.0563, + "step": 22690 + }, + { + "epoch": 7.01, + "learning_rate": 1.5082495611353578e-05, + "loss": 0.0661, + "step": 22691 + }, + { + "epoch": 7.01, + "learning_rate": 1.5082064898262578e-05, + "loss": 0.0575, + "step": 22692 + }, + { + "epoch": 7.01, + "learning_rate": 1.5081634172460409e-05, + "loss": 0.0619, + "step": 22693 + }, + { + "epoch": 7.01, + "learning_rate": 1.5081203433948144e-05, + "loss": 0.0615, + "step": 22694 + }, + { + "epoch": 7.01, + "learning_rate": 1.5080772682726863e-05, + "loss": 0.0637, + "step": 22695 + }, + { + "epoch": 7.01, + "learning_rate": 1.508034191879764e-05, + "loss": 0.061, + "step": 22696 + }, + { + "epoch": 7.01, + "learning_rate": 1.507991114216156e-05, + "loss": 0.0571, + "step": 22697 + }, + { + "epoch": 7.01, + "learning_rate": 1.5079480352819693e-05, + "loss": 0.0547, + "step": 22698 + }, + { + "epoch": 7.01, + "learning_rate": 1.507904955077312e-05, + "loss": 0.0555, + "step": 22699 + }, + { + "epoch": 7.01, + "learning_rate": 1.5078618736022919e-05, + "loss": 0.0574, + "step": 22700 + }, + { + "epoch": 7.01, + "learning_rate": 1.5078187908570167e-05, + "loss": 0.0531, + "step": 22701 + }, + { + "epoch": 7.01, + "learning_rate": 1.5077757068415934e-05, + "loss": 0.0608, + "step": 22702 + }, + { + "epoch": 7.01, + "learning_rate": 1.507732621556131e-05, + "loss": 0.057, + "step": 22703 + }, + { + "epoch": 7.01, + "learning_rate": 1.5076895350007367e-05, + "loss": 0.06, + "step": 22704 + }, + { + "epoch": 7.01, + "learning_rate": 1.5076464471755183e-05, + "loss": 0.0577, + "step": 22705 + }, + { + "epoch": 7.01, + "learning_rate": 1.5076033580805836e-05, + "loss": 0.0503, + "step": 22706 + }, + { + "epoch": 7.01, + "learning_rate": 1.5075602677160402e-05, + "loss": 0.0617, + "step": 22707 + }, + { + "epoch": 7.01, + "learning_rate": 1.5075171760819959e-05, + "loss": 0.0634, + "step": 22708 + }, + { + "epoch": 7.01, + "learning_rate": 1.5074740831785586e-05, + "loss": 0.0584, + "step": 22709 + }, + { + "epoch": 7.01, + "learning_rate": 1.5074309890058362e-05, + "loss": 0.053, + "step": 22710 + }, + { + "epoch": 7.01, + "learning_rate": 1.5073878935639363e-05, + "loss": 0.0585, + "step": 22711 + }, + { + "epoch": 7.01, + "learning_rate": 1.5073447968529667e-05, + "loss": 0.0554, + "step": 22712 + }, + { + "epoch": 7.01, + "learning_rate": 1.507301698873035e-05, + "loss": 0.0614, + "step": 22713 + }, + { + "epoch": 7.01, + "learning_rate": 1.5072585996242496e-05, + "loss": 0.0547, + "step": 22714 + }, + { + "epoch": 7.01, + "learning_rate": 1.5072154991067178e-05, + "loss": 0.0671, + "step": 22715 + }, + { + "epoch": 7.02, + "learning_rate": 1.5071723973205474e-05, + "loss": 0.0651, + "step": 22716 + }, + { + "epoch": 7.02, + "learning_rate": 1.5071292942658465e-05, + "loss": 0.0654, + "step": 22717 + }, + { + "epoch": 7.02, + "learning_rate": 1.5070861899427227e-05, + "loss": 0.0574, + "step": 22718 + }, + { + "epoch": 7.02, + "learning_rate": 1.5070430843512837e-05, + "loss": 0.0601, + "step": 22719 + }, + { + "epoch": 7.02, + "learning_rate": 1.5069999774916374e-05, + "loss": 0.054, + "step": 22720 + }, + { + "epoch": 7.02, + "learning_rate": 1.506956869363892e-05, + "loss": 0.0573, + "step": 22721 + }, + { + "epoch": 7.02, + "learning_rate": 1.506913759968155e-05, + "loss": 0.0541, + "step": 22722 + }, + { + "epoch": 7.02, + "learning_rate": 1.5068706493045339e-05, + "loss": 0.0587, + "step": 22723 + }, + { + "epoch": 7.02, + "learning_rate": 1.5068275373731371e-05, + "loss": 0.0614, + "step": 22724 + }, + { + "epoch": 7.02, + "learning_rate": 1.5067844241740722e-05, + "loss": 0.0531, + "step": 22725 + }, + { + "epoch": 7.02, + "learning_rate": 1.506741309707447e-05, + "loss": 0.0528, + "step": 22726 + }, + { + "epoch": 7.02, + "learning_rate": 1.5066981939733693e-05, + "loss": 0.0604, + "step": 22727 + }, + { + "epoch": 7.02, + "learning_rate": 1.506655076971947e-05, + "loss": 0.059, + "step": 22728 + }, + { + "epoch": 7.02, + "learning_rate": 1.506611958703288e-05, + "loss": 0.0605, + "step": 22729 + }, + { + "epoch": 7.02, + "learning_rate": 1.5065688391675002e-05, + "loss": 0.0587, + "step": 22730 + }, + { + "epoch": 7.02, + "learning_rate": 1.5065257183646913e-05, + "loss": 0.0555, + "step": 22731 + }, + { + "epoch": 7.02, + "learning_rate": 1.5064825962949693e-05, + "loss": 0.0658, + "step": 22732 + }, + { + "epoch": 7.02, + "learning_rate": 1.5064394729584415e-05, + "loss": 0.0593, + "step": 22733 + }, + { + "epoch": 7.02, + "learning_rate": 1.5063963483552164e-05, + "loss": 0.0613, + "step": 22734 + }, + { + "epoch": 7.02, + "learning_rate": 1.506353222485402e-05, + "loss": 0.065, + "step": 22735 + }, + { + "epoch": 7.02, + "learning_rate": 1.5063100953491051e-05, + "loss": 0.0631, + "step": 22736 + }, + { + "epoch": 7.02, + "learning_rate": 1.5062669669464351e-05, + "loss": 0.0626, + "step": 22737 + }, + { + "epoch": 7.02, + "learning_rate": 1.5062238372774989e-05, + "loss": 0.0591, + "step": 22738 + }, + { + "epoch": 7.02, + "learning_rate": 1.5061807063424043e-05, + "loss": 0.0527, + "step": 22739 + }, + { + "epoch": 7.02, + "learning_rate": 1.5061375741412597e-05, + "loss": 0.0626, + "step": 22740 + }, + { + "epoch": 7.02, + "learning_rate": 1.5060944406741723e-05, + "loss": 0.0566, + "step": 22741 + }, + { + "epoch": 7.02, + "learning_rate": 1.5060513059412509e-05, + "loss": 0.0591, + "step": 22742 + }, + { + "epoch": 7.02, + "learning_rate": 1.5060081699426026e-05, + "loss": 0.0596, + "step": 22743 + }, + { + "epoch": 7.02, + "learning_rate": 1.5059650326783355e-05, + "loss": 0.0615, + "step": 22744 + }, + { + "epoch": 7.02, + "learning_rate": 1.5059218941485578e-05, + "loss": 0.0568, + "step": 22745 + }, + { + "epoch": 7.02, + "learning_rate": 1.5058787543533771e-05, + "loss": 0.0667, + "step": 22746 + }, + { + "epoch": 7.02, + "learning_rate": 1.5058356132929013e-05, + "loss": 0.0583, + "step": 22747 + }, + { + "epoch": 7.03, + "learning_rate": 1.5057924709672385e-05, + "loss": 0.0564, + "step": 22748 + }, + { + "epoch": 7.03, + "learning_rate": 1.5057493273764962e-05, + "loss": 0.0596, + "step": 22749 + }, + { + "epoch": 7.03, + "learning_rate": 1.5057061825207829e-05, + "loss": 0.0555, + "step": 22750 + }, + { + "epoch": 7.03, + "learning_rate": 1.5056630364002061e-05, + "loss": 0.0568, + "step": 22751 + }, + { + "epoch": 7.03, + "learning_rate": 1.5056198890148736e-05, + "loss": 0.0577, + "step": 22752 + }, + { + "epoch": 7.03, + "learning_rate": 1.505576740364894e-05, + "loss": 0.0688, + "step": 22753 + }, + { + "epoch": 7.03, + "learning_rate": 1.5055335904503744e-05, + "loss": 0.0598, + "step": 22754 + }, + { + "epoch": 7.03, + "learning_rate": 1.5054904392714234e-05, + "loss": 0.053, + "step": 22755 + }, + { + "epoch": 7.03, + "learning_rate": 1.5054472868281482e-05, + "loss": 0.0556, + "step": 22756 + }, + { + "epoch": 7.03, + "learning_rate": 1.5054041331206573e-05, + "loss": 0.0599, + "step": 22757 + }, + { + "epoch": 7.03, + "learning_rate": 1.5053609781490589e-05, + "loss": 0.063, + "step": 22758 + }, + { + "epoch": 7.03, + "learning_rate": 1.50531782191346e-05, + "loss": 0.0552, + "step": 22759 + }, + { + "epoch": 7.03, + "learning_rate": 1.505274664413969e-05, + "loss": 0.0633, + "step": 22760 + }, + { + "epoch": 7.03, + "learning_rate": 1.5052315056506941e-05, + "loss": 0.0604, + "step": 22761 + }, + { + "epoch": 7.03, + "learning_rate": 1.505188345623743e-05, + "loss": 0.0625, + "step": 22762 + }, + { + "epoch": 7.03, + "learning_rate": 1.505145184333224e-05, + "loss": 0.0609, + "step": 22763 + }, + { + "epoch": 7.03, + "learning_rate": 1.5051020217792442e-05, + "loss": 0.0658, + "step": 22764 + }, + { + "epoch": 7.03, + "learning_rate": 1.5050588579619128e-05, + "loss": 0.0652, + "step": 22765 + }, + { + "epoch": 7.03, + "learning_rate": 1.5050156928813367e-05, + "loss": 0.0594, + "step": 22766 + }, + { + "epoch": 7.03, + "learning_rate": 1.5049725265376243e-05, + "loss": 0.0564, + "step": 22767 + }, + { + "epoch": 7.03, + "learning_rate": 1.5049293589308835e-05, + "loss": 0.0567, + "step": 22768 + }, + { + "epoch": 7.03, + "learning_rate": 1.5048861900612224e-05, + "loss": 0.0584, + "step": 22769 + }, + { + "epoch": 7.03, + "learning_rate": 1.5048430199287484e-05, + "loss": 0.058, + "step": 22770 + }, + { + "epoch": 7.03, + "learning_rate": 1.5047998485335705e-05, + "loss": 0.0577, + "step": 22771 + }, + { + "epoch": 7.03, + "learning_rate": 1.5047566758757959e-05, + "loss": 0.0611, + "step": 22772 + }, + { + "epoch": 7.03, + "learning_rate": 1.5047135019555325e-05, + "loss": 0.0544, + "step": 22773 + }, + { + "epoch": 7.03, + "learning_rate": 1.5046703267728891e-05, + "loss": 0.0513, + "step": 22774 + }, + { + "epoch": 7.03, + "learning_rate": 1.5046271503279727e-05, + "loss": 0.0569, + "step": 22775 + }, + { + "epoch": 7.03, + "learning_rate": 1.5045839726208921e-05, + "loss": 0.0575, + "step": 22776 + }, + { + "epoch": 7.03, + "learning_rate": 1.5045407936517547e-05, + "loss": 0.0635, + "step": 22777 + }, + { + "epoch": 7.03, + "learning_rate": 1.504497613420669e-05, + "loss": 0.0562, + "step": 22778 + }, + { + "epoch": 7.03, + "learning_rate": 1.5044544319277426e-05, + "loss": 0.061, + "step": 22779 + }, + { + "epoch": 7.03, + "learning_rate": 1.5044112491730837e-05, + "loss": 0.0601, + "step": 22780 + }, + { + "epoch": 7.04, + "learning_rate": 1.5043680651568002e-05, + "loss": 0.0525, + "step": 22781 + }, + { + "epoch": 7.04, + "learning_rate": 1.5043248798790003e-05, + "loss": 0.0595, + "step": 22782 + }, + { + "epoch": 7.04, + "learning_rate": 1.5042816933397917e-05, + "loss": 0.0562, + "step": 22783 + }, + { + "epoch": 7.04, + "learning_rate": 1.5042385055392827e-05, + "loss": 0.0577, + "step": 22784 + }, + { + "epoch": 7.04, + "learning_rate": 1.5041953164775814e-05, + "loss": 0.058, + "step": 22785 + }, + { + "epoch": 7.04, + "learning_rate": 1.5041521261547956e-05, + "loss": 0.0579, + "step": 22786 + }, + { + "epoch": 7.04, + "learning_rate": 1.5041089345710332e-05, + "loss": 0.055, + "step": 22787 + }, + { + "epoch": 7.04, + "learning_rate": 1.5040657417264024e-05, + "loss": 0.0553, + "step": 22788 + }, + { + "epoch": 7.04, + "learning_rate": 1.5040225476210116e-05, + "loss": 0.0551, + "step": 22789 + }, + { + "epoch": 7.04, + "learning_rate": 1.5039793522549682e-05, + "loss": 0.0615, + "step": 22790 + }, + { + "epoch": 7.04, + "learning_rate": 1.5039361556283805e-05, + "loss": 0.0584, + "step": 22791 + }, + { + "epoch": 7.04, + "learning_rate": 1.5038929577413567e-05, + "loss": 0.0631, + "step": 22792 + }, + { + "epoch": 7.04, + "learning_rate": 1.5038497585940044e-05, + "loss": 0.0593, + "step": 22793 + }, + { + "epoch": 7.04, + "learning_rate": 1.5038065581864323e-05, + "loss": 0.06, + "step": 22794 + }, + { + "epoch": 7.04, + "learning_rate": 1.5037633565187478e-05, + "loss": 0.0626, + "step": 22795 + }, + { + "epoch": 7.04, + "learning_rate": 1.5037201535910597e-05, + "loss": 0.0541, + "step": 22796 + }, + { + "epoch": 7.04, + "learning_rate": 1.5036769494034753e-05, + "loss": 0.0606, + "step": 22797 + }, + { + "epoch": 7.04, + "learning_rate": 1.503633743956103e-05, + "loss": 0.0638, + "step": 22798 + }, + { + "epoch": 7.04, + "learning_rate": 1.503590537249051e-05, + "loss": 0.0611, + "step": 22799 + }, + { + "epoch": 7.04, + "learning_rate": 1.503547329282427e-05, + "loss": 0.0575, + "step": 22800 + }, + { + "epoch": 7.04, + "learning_rate": 1.5035041200563397e-05, + "loss": 0.0616, + "step": 22801 + }, + { + "epoch": 7.04, + "learning_rate": 1.5034609095708963e-05, + "loss": 0.0594, + "step": 22802 + }, + { + "epoch": 7.04, + "learning_rate": 1.5034176978262056e-05, + "loss": 0.057, + "step": 22803 + }, + { + "epoch": 7.04, + "learning_rate": 1.5033744848223752e-05, + "loss": 0.0555, + "step": 22804 + }, + { + "epoch": 7.04, + "learning_rate": 1.5033312705595135e-05, + "loss": 0.0495, + "step": 22805 + }, + { + "epoch": 7.04, + "learning_rate": 1.5032880550377288e-05, + "loss": 0.0618, + "step": 22806 + }, + { + "epoch": 7.04, + "learning_rate": 1.5032448382571284e-05, + "loss": 0.0599, + "step": 22807 + }, + { + "epoch": 7.04, + "learning_rate": 1.503201620217821e-05, + "loss": 0.0555, + "step": 22808 + }, + { + "epoch": 7.04, + "learning_rate": 1.5031584009199147e-05, + "loss": 0.0613, + "step": 22809 + }, + { + "epoch": 7.04, + "learning_rate": 1.5031151803635174e-05, + "loss": 0.0538, + "step": 22810 + }, + { + "epoch": 7.04, + "learning_rate": 1.5030719585487373e-05, + "loss": 0.0586, + "step": 22811 + }, + { + "epoch": 7.04, + "learning_rate": 1.5030287354756824e-05, + "loss": 0.0559, + "step": 22812 + }, + { + "epoch": 7.05, + "learning_rate": 1.5029855111444611e-05, + "loss": 0.0569, + "step": 22813 + }, + { + "epoch": 7.05, + "learning_rate": 1.5029422855551812e-05, + "loss": 0.0586, + "step": 22814 + }, + { + "epoch": 7.05, + "learning_rate": 1.5028990587079509e-05, + "loss": 0.0675, + "step": 22815 + }, + { + "epoch": 7.05, + "learning_rate": 1.5028558306028783e-05, + "loss": 0.0666, + "step": 22816 + }, + { + "epoch": 7.05, + "learning_rate": 1.5028126012400717e-05, + "loss": 0.0613, + "step": 22817 + }, + { + "epoch": 7.05, + "learning_rate": 1.5027693706196387e-05, + "loss": 0.0654, + "step": 22818 + }, + { + "epoch": 7.05, + "learning_rate": 1.502726138741688e-05, + "loss": 0.0524, + "step": 22819 + }, + { + "epoch": 7.05, + "learning_rate": 1.5026829056063279e-05, + "loss": 0.0587, + "step": 22820 + }, + { + "epoch": 7.05, + "learning_rate": 1.5026396712136655e-05, + "loss": 0.0578, + "step": 22821 + }, + { + "epoch": 7.05, + "learning_rate": 1.50259643556381e-05, + "loss": 0.0613, + "step": 22822 + }, + { + "epoch": 7.05, + "learning_rate": 1.5025531986568691e-05, + "loss": 0.0534, + "step": 22823 + }, + { + "epoch": 7.05, + "learning_rate": 1.502509960492951e-05, + "loss": 0.0594, + "step": 22824 + }, + { + "epoch": 7.05, + "learning_rate": 1.502466721072164e-05, + "loss": 0.0636, + "step": 22825 + }, + { + "epoch": 7.05, + "learning_rate": 1.5024234803946156e-05, + "loss": 0.0608, + "step": 22826 + }, + { + "epoch": 7.05, + "learning_rate": 1.502380238460415e-05, + "loss": 0.0637, + "step": 22827 + }, + { + "epoch": 7.05, + "learning_rate": 1.5023369952696695e-05, + "loss": 0.0676, + "step": 22828 + }, + { + "epoch": 7.05, + "learning_rate": 1.5022937508224874e-05, + "loss": 0.0649, + "step": 22829 + }, + { + "epoch": 7.05, + "learning_rate": 1.5022505051189775e-05, + "loss": 0.0616, + "step": 22830 + }, + { + "epoch": 7.05, + "learning_rate": 1.502207258159247e-05, + "loss": 0.0662, + "step": 22831 + }, + { + "epoch": 7.05, + "learning_rate": 1.502164009943405e-05, + "loss": 0.0591, + "step": 22832 + }, + { + "epoch": 7.05, + "learning_rate": 1.5021207604715588e-05, + "loss": 0.0594, + "step": 22833 + }, + { + "epoch": 7.05, + "learning_rate": 1.5020775097438171e-05, + "loss": 0.0661, + "step": 22834 + }, + { + "epoch": 7.05, + "learning_rate": 1.502034257760288e-05, + "loss": 0.0625, + "step": 22835 + }, + { + "epoch": 7.05, + "learning_rate": 1.5019910045210798e-05, + "loss": 0.0566, + "step": 22836 + }, + { + "epoch": 7.05, + "learning_rate": 1.5019477500263003e-05, + "loss": 0.0557, + "step": 22837 + }, + { + "epoch": 7.05, + "learning_rate": 1.501904494276058e-05, + "loss": 0.0591, + "step": 22838 + }, + { + "epoch": 7.05, + "learning_rate": 1.501861237270461e-05, + "loss": 0.053, + "step": 22839 + }, + { + "epoch": 7.05, + "learning_rate": 1.5018179790096179e-05, + "loss": 0.0578, + "step": 22840 + }, + { + "epoch": 7.05, + "learning_rate": 1.5017747194936361e-05, + "loss": 0.0499, + "step": 22841 + }, + { + "epoch": 7.05, + "learning_rate": 1.5017314587226244e-05, + "loss": 0.06, + "step": 22842 + }, + { + "epoch": 7.05, + "learning_rate": 1.5016881966966907e-05, + "loss": 0.0604, + "step": 22843 + }, + { + "epoch": 7.05, + "learning_rate": 1.501644933415943e-05, + "loss": 0.06, + "step": 22844 + }, + { + "epoch": 7.06, + "learning_rate": 1.5016016688804906e-05, + "loss": 0.0677, + "step": 22845 + }, + { + "epoch": 7.06, + "learning_rate": 1.5015584030904404e-05, + "loss": 0.0581, + "step": 22846 + }, + { + "epoch": 7.06, + "learning_rate": 1.5015151360459013e-05, + "loss": 0.0638, + "step": 22847 + }, + { + "epoch": 7.06, + "learning_rate": 1.5014718677469816e-05, + "loss": 0.0599, + "step": 22848 + }, + { + "epoch": 7.06, + "learning_rate": 1.5014285981937886e-05, + "loss": 0.0577, + "step": 22849 + }, + { + "epoch": 7.06, + "learning_rate": 1.5013853273864319e-05, + "loss": 0.0471, + "step": 22850 + }, + { + "epoch": 7.06, + "learning_rate": 1.5013420553250187e-05, + "loss": 0.0568, + "step": 22851 + }, + { + "epoch": 7.06, + "learning_rate": 1.5012987820096574e-05, + "loss": 0.0667, + "step": 22852 + }, + { + "epoch": 7.06, + "learning_rate": 1.501255507440457e-05, + "loss": 0.0567, + "step": 22853 + }, + { + "epoch": 7.06, + "learning_rate": 1.5012122316175248e-05, + "loss": 0.0548, + "step": 22854 + }, + { + "epoch": 7.06, + "learning_rate": 1.5011689545409694e-05, + "loss": 0.058, + "step": 22855 + }, + { + "epoch": 7.06, + "learning_rate": 1.501125676210899e-05, + "loss": 0.0603, + "step": 22856 + }, + { + "epoch": 7.06, + "learning_rate": 1.5010823966274219e-05, + "loss": 0.0596, + "step": 22857 + }, + { + "epoch": 7.06, + "learning_rate": 1.5010391157906465e-05, + "loss": 0.0598, + "step": 22858 + }, + { + "epoch": 7.06, + "learning_rate": 1.5009958337006809e-05, + "loss": 0.0597, + "step": 22859 + }, + { + "epoch": 7.06, + "learning_rate": 1.5009525503576331e-05, + "loss": 0.0541, + "step": 22860 + }, + { + "epoch": 7.06, + "learning_rate": 1.5009092657616117e-05, + "loss": 0.0541, + "step": 22861 + }, + { + "epoch": 7.06, + "learning_rate": 1.500865979912725e-05, + "loss": 0.0586, + "step": 22862 + }, + { + "epoch": 7.06, + "learning_rate": 1.500822692811081e-05, + "loss": 0.0584, + "step": 22863 + }, + { + "epoch": 7.06, + "learning_rate": 1.5007794044567883e-05, + "loss": 0.0615, + "step": 22864 + }, + { + "epoch": 7.06, + "learning_rate": 1.5007361148499546e-05, + "loss": 0.0552, + "step": 22865 + }, + { + "epoch": 7.06, + "learning_rate": 1.5006928239906888e-05, + "loss": 0.064, + "step": 22866 + }, + { + "epoch": 7.06, + "learning_rate": 1.5006495318790988e-05, + "loss": 0.0609, + "step": 22867 + }, + { + "epoch": 7.06, + "learning_rate": 1.5006062385152933e-05, + "loss": 0.0605, + "step": 22868 + }, + { + "epoch": 7.06, + "learning_rate": 1.50056294389938e-05, + "loss": 0.0576, + "step": 22869 + }, + { + "epoch": 7.06, + "learning_rate": 1.5005196480314675e-05, + "loss": 0.0605, + "step": 22870 + }, + { + "epoch": 7.06, + "learning_rate": 1.5004763509116642e-05, + "loss": 0.061, + "step": 22871 + }, + { + "epoch": 7.06, + "learning_rate": 1.5004330525400781e-05, + "loss": 0.0673, + "step": 22872 + }, + { + "epoch": 7.06, + "learning_rate": 1.5003897529168176e-05, + "loss": 0.0554, + "step": 22873 + }, + { + "epoch": 7.06, + "learning_rate": 1.5003464520419915e-05, + "loss": 0.0597, + "step": 22874 + }, + { + "epoch": 7.06, + "learning_rate": 1.5003031499157073e-05, + "loss": 0.0602, + "step": 22875 + }, + { + "epoch": 7.06, + "learning_rate": 1.5002598465380737e-05, + "loss": 0.0572, + "step": 22876 + }, + { + "epoch": 7.06, + "learning_rate": 1.500216541909199e-05, + "loss": 0.0578, + "step": 22877 + }, + { + "epoch": 7.07, + "learning_rate": 1.5001732360291917e-05, + "loss": 0.0668, + "step": 22878 + }, + { + "epoch": 7.07, + "learning_rate": 1.5001299288981597e-05, + "loss": 0.0567, + "step": 22879 + }, + { + "epoch": 7.07, + "learning_rate": 1.5000866205162114e-05, + "loss": 0.064, + "step": 22880 + }, + { + "epoch": 7.07, + "learning_rate": 1.5000433108834558e-05, + "loss": 0.0622, + "step": 22881 + }, + { + "epoch": 7.07, + "learning_rate": 1.5000000000000002e-05, + "loss": 0.064, + "step": 22882 + }, + { + "epoch": 7.07, + "learning_rate": 1.4999566878659533e-05, + "loss": 0.0518, + "step": 22883 + }, + { + "epoch": 7.07, + "learning_rate": 1.499913374481424e-05, + "loss": 0.054, + "step": 22884 + }, + { + "epoch": 7.07, + "learning_rate": 1.4998700598465199e-05, + "loss": 0.0599, + "step": 22885 + }, + { + "epoch": 7.07, + "learning_rate": 1.4998267439613496e-05, + "loss": 0.0549, + "step": 22886 + }, + { + "epoch": 7.07, + "learning_rate": 1.4997834268260217e-05, + "loss": 0.0584, + "step": 22887 + }, + { + "epoch": 7.07, + "learning_rate": 1.4997401084406438e-05, + "loss": 0.0602, + "step": 22888 + }, + { + "epoch": 7.07, + "learning_rate": 1.499696788805325e-05, + "loss": 0.0558, + "step": 22889 + }, + { + "epoch": 7.07, + "learning_rate": 1.4996534679201735e-05, + "loss": 0.0624, + "step": 22890 + }, + { + "epoch": 7.07, + "learning_rate": 1.4996101457852973e-05, + "loss": 0.0565, + "step": 22891 + }, + { + "epoch": 7.07, + "learning_rate": 1.4995668224008053e-05, + "loss": 0.0591, + "step": 22892 + }, + { + "epoch": 7.07, + "learning_rate": 1.4995234977668053e-05, + "loss": 0.058, + "step": 22893 + }, + { + "epoch": 7.07, + "learning_rate": 1.4994801718834062e-05, + "loss": 0.0588, + "step": 22894 + }, + { + "epoch": 7.07, + "learning_rate": 1.499436844750716e-05, + "loss": 0.0555, + "step": 22895 + }, + { + "epoch": 7.07, + "learning_rate": 1.4993935163688429e-05, + "loss": 0.056, + "step": 22896 + }, + { + "epoch": 7.07, + "learning_rate": 1.4993501867378957e-05, + "loss": 0.0573, + "step": 22897 + }, + { + "epoch": 7.07, + "learning_rate": 1.4993068558579826e-05, + "loss": 0.0586, + "step": 22898 + }, + { + "epoch": 7.07, + "learning_rate": 1.4992635237292123e-05, + "loss": 0.0589, + "step": 22899 + }, + { + "epoch": 7.07, + "learning_rate": 1.4992201903516926e-05, + "loss": 0.0587, + "step": 22900 + }, + { + "epoch": 7.07, + "learning_rate": 1.4991768557255319e-05, + "loss": 0.065, + "step": 22901 + }, + { + "epoch": 7.07, + "learning_rate": 1.4991335198508394e-05, + "loss": 0.0644, + "step": 22902 + }, + { + "epoch": 7.07, + "learning_rate": 1.4990901827277222e-05, + "loss": 0.0573, + "step": 22903 + }, + { + "epoch": 7.07, + "learning_rate": 1.4990468443562902e-05, + "loss": 0.0624, + "step": 22904 + }, + { + "epoch": 7.07, + "learning_rate": 1.4990035047366504e-05, + "loss": 0.0669, + "step": 22905 + }, + { + "epoch": 7.07, + "learning_rate": 1.4989601638689121e-05, + "loss": 0.0698, + "step": 22906 + }, + { + "epoch": 7.07, + "learning_rate": 1.4989168217531835e-05, + "loss": 0.0541, + "step": 22907 + }, + { + "epoch": 7.07, + "learning_rate": 1.4988734783895727e-05, + "loss": 0.0515, + "step": 22908 + }, + { + "epoch": 7.07, + "learning_rate": 1.4988301337781885e-05, + "loss": 0.0725, + "step": 22909 + }, + { + "epoch": 7.08, + "learning_rate": 1.4987867879191394e-05, + "loss": 0.0562, + "step": 22910 + }, + { + "epoch": 7.08, + "learning_rate": 1.498743440812533e-05, + "loss": 0.0537, + "step": 22911 + }, + { + "epoch": 7.08, + "learning_rate": 1.4987000924584788e-05, + "loss": 0.0629, + "step": 22912 + }, + { + "epoch": 7.08, + "learning_rate": 1.4986567428570844e-05, + "loss": 0.06, + "step": 22913 + }, + { + "epoch": 7.08, + "learning_rate": 1.4986133920084586e-05, + "loss": 0.0605, + "step": 22914 + }, + { + "epoch": 7.08, + "learning_rate": 1.49857003991271e-05, + "loss": 0.0549, + "step": 22915 + }, + { + "epoch": 7.08, + "learning_rate": 1.4985266865699464e-05, + "loss": 0.055, + "step": 22916 + }, + { + "epoch": 7.08, + "learning_rate": 1.4984833319802769e-05, + "loss": 0.0641, + "step": 22917 + }, + { + "epoch": 7.08, + "learning_rate": 1.4984399761438095e-05, + "loss": 0.057, + "step": 22918 + }, + { + "epoch": 7.08, + "learning_rate": 1.4983966190606531e-05, + "loss": 0.065, + "step": 22919 + }, + { + "epoch": 7.08, + "learning_rate": 1.4983532607309154e-05, + "loss": 0.0634, + "step": 22920 + }, + { + "epoch": 7.08, + "learning_rate": 1.4983099011547058e-05, + "loss": 0.0602, + "step": 22921 + }, + { + "epoch": 7.08, + "learning_rate": 1.498266540332132e-05, + "loss": 0.0532, + "step": 22922 + }, + { + "epoch": 7.08, + "learning_rate": 1.4982231782633027e-05, + "loss": 0.0579, + "step": 22923 + }, + { + "epoch": 7.08, + "learning_rate": 1.4981798149483264e-05, + "loss": 0.0586, + "step": 22924 + }, + { + "epoch": 7.08, + "learning_rate": 1.4981364503873116e-05, + "loss": 0.0679, + "step": 22925 + }, + { + "epoch": 7.08, + "learning_rate": 1.4980930845803665e-05, + "loss": 0.0593, + "step": 22926 + }, + { + "epoch": 7.08, + "learning_rate": 1.4980497175275996e-05, + "loss": 0.0574, + "step": 22927 + }, + { + "epoch": 7.08, + "learning_rate": 1.49800634922912e-05, + "loss": 0.0675, + "step": 22928 + }, + { + "epoch": 7.08, + "learning_rate": 1.4979629796850352e-05, + "loss": 0.0555, + "step": 22929 + }, + { + "epoch": 7.08, + "learning_rate": 1.4979196088954546e-05, + "loss": 0.0527, + "step": 22930 + }, + { + "epoch": 7.08, + "learning_rate": 1.497876236860486e-05, + "loss": 0.0555, + "step": 22931 + }, + { + "epoch": 7.08, + "learning_rate": 1.4978328635802382e-05, + "loss": 0.0608, + "step": 22932 + }, + { + "epoch": 7.08, + "learning_rate": 1.4977894890548197e-05, + "loss": 0.0563, + "step": 22933 + }, + { + "epoch": 7.08, + "learning_rate": 1.4977461132843388e-05, + "loss": 0.065, + "step": 22934 + }, + { + "epoch": 7.08, + "learning_rate": 1.497702736268904e-05, + "loss": 0.0591, + "step": 22935 + }, + { + "epoch": 7.08, + "learning_rate": 1.497659358008624e-05, + "loss": 0.0661, + "step": 22936 + }, + { + "epoch": 7.08, + "learning_rate": 1.4976159785036068e-05, + "loss": 0.0616, + "step": 22937 + }, + { + "epoch": 7.08, + "learning_rate": 1.497572597753962e-05, + "loss": 0.0619, + "step": 22938 + }, + { + "epoch": 7.08, + "learning_rate": 1.497529215759797e-05, + "loss": 0.0567, + "step": 22939 + }, + { + "epoch": 7.08, + "learning_rate": 1.4974858325212208e-05, + "loss": 0.0613, + "step": 22940 + }, + { + "epoch": 7.08, + "learning_rate": 1.4974424480383415e-05, + "loss": 0.0585, + "step": 22941 + }, + { + "epoch": 7.09, + "learning_rate": 1.497399062311268e-05, + "loss": 0.0672, + "step": 22942 + }, + { + "epoch": 7.09, + "learning_rate": 1.4973556753401088e-05, + "loss": 0.0624, + "step": 22943 + }, + { + "epoch": 7.09, + "learning_rate": 1.4973122871249723e-05, + "loss": 0.0601, + "step": 22944 + }, + { + "epoch": 7.09, + "learning_rate": 1.4972688976659673e-05, + "loss": 0.0584, + "step": 22945 + }, + { + "epoch": 7.09, + "learning_rate": 1.4972255069632018e-05, + "loss": 0.0555, + "step": 22946 + }, + { + "epoch": 7.09, + "learning_rate": 1.4971821150167847e-05, + "loss": 0.0556, + "step": 22947 + }, + { + "epoch": 7.09, + "learning_rate": 1.4971387218268246e-05, + "loss": 0.0604, + "step": 22948 + }, + { + "epoch": 7.09, + "learning_rate": 1.4970953273934297e-05, + "loss": 0.0581, + "step": 22949 + }, + { + "epoch": 7.09, + "learning_rate": 1.4970519317167086e-05, + "loss": 0.0606, + "step": 22950 + }, + { + "epoch": 7.09, + "learning_rate": 1.4970085347967702e-05, + "loss": 0.06, + "step": 22951 + }, + { + "epoch": 7.09, + "learning_rate": 1.4969651366337228e-05, + "loss": 0.0654, + "step": 22952 + }, + { + "epoch": 7.09, + "learning_rate": 1.4969217372276752e-05, + "loss": 0.0601, + "step": 22953 + }, + { + "epoch": 7.09, + "learning_rate": 1.4968783365787351e-05, + "loss": 0.0556, + "step": 22954 + }, + { + "epoch": 7.09, + "learning_rate": 1.4968349346870118e-05, + "loss": 0.0639, + "step": 22955 + }, + { + "epoch": 7.09, + "learning_rate": 1.496791531552614e-05, + "loss": 0.07, + "step": 22956 + }, + { + "epoch": 7.09, + "learning_rate": 1.49674812717565e-05, + "loss": 0.063, + "step": 22957 + }, + { + "epoch": 7.09, + "learning_rate": 1.4967047215562283e-05, + "loss": 0.0536, + "step": 22958 + }, + { + "epoch": 7.09, + "learning_rate": 1.496661314694457e-05, + "loss": 0.0583, + "step": 22959 + }, + { + "epoch": 7.09, + "learning_rate": 1.4966179065904456e-05, + "loss": 0.0618, + "step": 22960 + }, + { + "epoch": 7.09, + "learning_rate": 1.4965744972443024e-05, + "loss": 0.0622, + "step": 22961 + }, + { + "epoch": 7.09, + "learning_rate": 1.4965310866561354e-05, + "loss": 0.0621, + "step": 22962 + }, + { + "epoch": 7.09, + "learning_rate": 1.496487674826054e-05, + "loss": 0.0544, + "step": 22963 + }, + { + "epoch": 7.09, + "learning_rate": 1.496444261754166e-05, + "loss": 0.0628, + "step": 22964 + }, + { + "epoch": 7.09, + "learning_rate": 1.4964008474405804e-05, + "loss": 0.0588, + "step": 22965 + }, + { + "epoch": 7.09, + "learning_rate": 1.4963574318854061e-05, + "loss": 0.0577, + "step": 22966 + }, + { + "epoch": 7.09, + "learning_rate": 1.4963140150887512e-05, + "loss": 0.0617, + "step": 22967 + }, + { + "epoch": 7.09, + "learning_rate": 1.496270597050724e-05, + "loss": 0.0625, + "step": 22968 + }, + { + "epoch": 7.09, + "learning_rate": 1.4962271777714339e-05, + "loss": 0.0595, + "step": 22969 + }, + { + "epoch": 7.09, + "learning_rate": 1.4961837572509892e-05, + "loss": 0.0565, + "step": 22970 + }, + { + "epoch": 7.09, + "learning_rate": 1.496140335489498e-05, + "loss": 0.0584, + "step": 22971 + }, + { + "epoch": 7.09, + "learning_rate": 1.49609691248707e-05, + "loss": 0.066, + "step": 22972 + }, + { + "epoch": 7.09, + "learning_rate": 1.4960534882438125e-05, + "loss": 0.0631, + "step": 22973 + }, + { + "epoch": 7.09, + "learning_rate": 1.496010062759835e-05, + "loss": 0.0606, + "step": 22974 + }, + { + "epoch": 7.1, + "learning_rate": 1.495966636035246e-05, + "loss": 0.0603, + "step": 22975 + }, + { + "epoch": 7.1, + "learning_rate": 1.4959232080701538e-05, + "loss": 0.0651, + "step": 22976 + }, + { + "epoch": 7.1, + "learning_rate": 1.4958797788646673e-05, + "loss": 0.0634, + "step": 22977 + }, + { + "epoch": 7.1, + "learning_rate": 1.4958363484188948e-05, + "loss": 0.0627, + "step": 22978 + }, + { + "epoch": 7.1, + "learning_rate": 1.4957929167329455e-05, + "loss": 0.0594, + "step": 22979 + }, + { + "epoch": 7.1, + "learning_rate": 1.4957494838069276e-05, + "loss": 0.0628, + "step": 22980 + }, + { + "epoch": 7.1, + "learning_rate": 1.4957060496409497e-05, + "loss": 0.0585, + "step": 22981 + }, + { + "epoch": 7.1, + "learning_rate": 1.4956626142351205e-05, + "loss": 0.0605, + "step": 22982 + }, + { + "epoch": 7.1, + "learning_rate": 1.495619177589549e-05, + "loss": 0.063, + "step": 22983 + }, + { + "epoch": 7.1, + "learning_rate": 1.4955757397043434e-05, + "loss": 0.0745, + "step": 22984 + }, + { + "epoch": 7.1, + "learning_rate": 1.4955323005796123e-05, + "loss": 0.0587, + "step": 22985 + }, + { + "epoch": 7.1, + "learning_rate": 1.4954888602154647e-05, + "loss": 0.0637, + "step": 22986 + }, + { + "epoch": 7.1, + "learning_rate": 1.4954454186120093e-05, + "loss": 0.0714, + "step": 22987 + }, + { + "epoch": 7.1, + "learning_rate": 1.4954019757693541e-05, + "loss": 0.06, + "step": 22988 + }, + { + "epoch": 7.1, + "learning_rate": 1.4953585316876085e-05, + "loss": 0.0587, + "step": 22989 + }, + { + "epoch": 7.1, + "learning_rate": 1.4953150863668806e-05, + "loss": 0.0584, + "step": 22990 + }, + { + "epoch": 7.1, + "learning_rate": 1.4952716398072795e-05, + "loss": 0.0615, + "step": 22991 + }, + { + "epoch": 7.1, + "learning_rate": 1.4952281920089138e-05, + "loss": 0.0582, + "step": 22992 + }, + { + "epoch": 7.1, + "learning_rate": 1.4951847429718918e-05, + "loss": 0.0609, + "step": 22993 + }, + { + "epoch": 7.1, + "learning_rate": 1.4951412926963228e-05, + "loss": 0.0598, + "step": 22994 + }, + { + "epoch": 7.1, + "learning_rate": 1.495097841182315e-05, + "loss": 0.0569, + "step": 22995 + }, + { + "epoch": 7.1, + "learning_rate": 1.4950543884299769e-05, + "loss": 0.0589, + "step": 22996 + }, + { + "epoch": 7.1, + "learning_rate": 1.495010934439418e-05, + "loss": 0.0653, + "step": 22997 + }, + { + "epoch": 7.1, + "learning_rate": 1.4949674792107462e-05, + "loss": 0.062, + "step": 22998 + }, + { + "epoch": 7.1, + "learning_rate": 1.4949240227440705e-05, + "loss": 0.0643, + "step": 22999 + }, + { + "epoch": 7.1, + "learning_rate": 1.4948805650394993e-05, + "loss": 0.0532, + "step": 23000 + }, + { + "epoch": 7.1, + "learning_rate": 1.4948371060971418e-05, + "loss": 0.0616, + "step": 23001 + }, + { + "epoch": 7.1, + "learning_rate": 1.4947936459171063e-05, + "loss": 0.0579, + "step": 23002 + }, + { + "epoch": 7.1, + "learning_rate": 1.4947501844995018e-05, + "loss": 0.0599, + "step": 23003 + }, + { + "epoch": 7.1, + "learning_rate": 1.4947067218444367e-05, + "loss": 0.0621, + "step": 23004 + }, + { + "epoch": 7.1, + "learning_rate": 1.49466325795202e-05, + "loss": 0.0599, + "step": 23005 + }, + { + "epoch": 7.1, + "learning_rate": 1.4946197928223603e-05, + "loss": 0.0534, + "step": 23006 + }, + { + "epoch": 7.11, + "learning_rate": 1.4945763264555661e-05, + "loss": 0.0612, + "step": 23007 + }, + { + "epoch": 7.11, + "learning_rate": 1.4945328588517464e-05, + "loss": 0.0562, + "step": 23008 + }, + { + "epoch": 7.11, + "learning_rate": 1.4944893900110098e-05, + "loss": 0.0599, + "step": 23009 + }, + { + "epoch": 7.11, + "learning_rate": 1.494445919933465e-05, + "loss": 0.0621, + "step": 23010 + }, + { + "epoch": 7.11, + "learning_rate": 1.4944024486192211e-05, + "loss": 0.0626, + "step": 23011 + }, + { + "epoch": 7.11, + "learning_rate": 1.4943589760683863e-05, + "loss": 0.0597, + "step": 23012 + }, + { + "epoch": 7.11, + "learning_rate": 1.4943155022810692e-05, + "loss": 0.0712, + "step": 23013 + }, + { + "epoch": 7.11, + "learning_rate": 1.4942720272573791e-05, + "loss": 0.0577, + "step": 23014 + }, + { + "epoch": 7.11, + "learning_rate": 1.4942285509974248e-05, + "loss": 0.0615, + "step": 23015 + }, + { + "epoch": 7.11, + "learning_rate": 1.4941850735013143e-05, + "loss": 0.0652, + "step": 23016 + }, + { + "epoch": 7.11, + "learning_rate": 1.4941415947691573e-05, + "loss": 0.0602, + "step": 23017 + }, + { + "epoch": 7.11, + "learning_rate": 1.4940981148010618e-05, + "loss": 0.0566, + "step": 23018 + }, + { + "epoch": 7.11, + "learning_rate": 1.4940546335971364e-05, + "loss": 0.0692, + "step": 23019 + }, + { + "epoch": 7.11, + "learning_rate": 1.4940111511574908e-05, + "loss": 0.0584, + "step": 23020 + }, + { + "epoch": 7.11, + "learning_rate": 1.4939676674822333e-05, + "loss": 0.0719, + "step": 23021 + }, + { + "epoch": 7.11, + "learning_rate": 1.4939241825714718e-05, + "loss": 0.0638, + "step": 23022 + }, + { + "epoch": 7.11, + "learning_rate": 1.4938806964253166e-05, + "loss": 0.0596, + "step": 23023 + }, + { + "epoch": 7.11, + "learning_rate": 1.4938372090438752e-05, + "loss": 0.0575, + "step": 23024 + }, + { + "epoch": 7.11, + "learning_rate": 1.4937937204272572e-05, + "loss": 0.0548, + "step": 23025 + }, + { + "epoch": 7.11, + "learning_rate": 1.4937502305755712e-05, + "loss": 0.0579, + "step": 23026 + }, + { + "epoch": 7.11, + "learning_rate": 1.4937067394889253e-05, + "loss": 0.0557, + "step": 23027 + }, + { + "epoch": 7.11, + "learning_rate": 1.493663247167429e-05, + "loss": 0.0615, + "step": 23028 + }, + { + "epoch": 7.11, + "learning_rate": 1.4936197536111912e-05, + "loss": 0.063, + "step": 23029 + }, + { + "epoch": 7.11, + "learning_rate": 1.49357625882032e-05, + "loss": 0.0706, + "step": 23030 + }, + { + "epoch": 7.11, + "learning_rate": 1.4935327627949246e-05, + "loss": 0.0571, + "step": 23031 + }, + { + "epoch": 7.11, + "learning_rate": 1.493489265535114e-05, + "loss": 0.0606, + "step": 23032 + }, + { + "epoch": 7.11, + "learning_rate": 1.4934457670409964e-05, + "loss": 0.0615, + "step": 23033 + }, + { + "epoch": 7.11, + "learning_rate": 1.4934022673126809e-05, + "loss": 0.0619, + "step": 23034 + }, + { + "epoch": 7.11, + "learning_rate": 1.4933587663502766e-05, + "loss": 0.0643, + "step": 23035 + }, + { + "epoch": 7.11, + "learning_rate": 1.4933152641538919e-05, + "loss": 0.0636, + "step": 23036 + }, + { + "epoch": 7.11, + "learning_rate": 1.4932717607236358e-05, + "loss": 0.0504, + "step": 23037 + }, + { + "epoch": 7.11, + "learning_rate": 1.493228256059617e-05, + "loss": 0.0579, + "step": 23038 + }, + { + "epoch": 7.11, + "learning_rate": 1.4931847501619446e-05, + "loss": 0.0605, + "step": 23039 + }, + { + "epoch": 7.12, + "learning_rate": 1.4931412430307269e-05, + "loss": 0.0605, + "step": 23040 + }, + { + "epoch": 7.12, + "learning_rate": 1.4930977346660731e-05, + "loss": 0.0543, + "step": 23041 + }, + { + "epoch": 7.12, + "learning_rate": 1.4930542250680919e-05, + "loss": 0.0548, + "step": 23042 + }, + { + "epoch": 7.12, + "learning_rate": 1.4930107142368925e-05, + "loss": 0.0573, + "step": 23043 + }, + { + "epoch": 7.12, + "learning_rate": 1.492967202172583e-05, + "loss": 0.0543, + "step": 23044 + }, + { + "epoch": 7.12, + "learning_rate": 1.4929236888752728e-05, + "loss": 0.0648, + "step": 23045 + }, + { + "epoch": 7.12, + "learning_rate": 1.4928801743450706e-05, + "loss": 0.0607, + "step": 23046 + }, + { + "epoch": 7.12, + "learning_rate": 1.4928366585820849e-05, + "loss": 0.0555, + "step": 23047 + }, + { + "epoch": 7.12, + "learning_rate": 1.4927931415864249e-05, + "loss": 0.0617, + "step": 23048 + }, + { + "epoch": 7.12, + "learning_rate": 1.4927496233581995e-05, + "loss": 0.0603, + "step": 23049 + }, + { + "epoch": 7.12, + "learning_rate": 1.4927061038975172e-05, + "loss": 0.0617, + "step": 23050 + }, + { + "epoch": 7.12, + "learning_rate": 1.4926625832044874e-05, + "loss": 0.0676, + "step": 23051 + }, + { + "epoch": 7.12, + "learning_rate": 1.4926190612792186e-05, + "loss": 0.0601, + "step": 23052 + }, + { + "epoch": 7.12, + "learning_rate": 1.4925755381218195e-05, + "loss": 0.0578, + "step": 23053 + }, + { + "epoch": 7.12, + "learning_rate": 1.492532013732399e-05, + "loss": 0.0605, + "step": 23054 + }, + { + "epoch": 7.12, + "learning_rate": 1.4924884881110661e-05, + "loss": 0.059, + "step": 23055 + }, + { + "epoch": 7.12, + "learning_rate": 1.49244496125793e-05, + "loss": 0.0581, + "step": 23056 + }, + { + "epoch": 7.12, + "learning_rate": 1.4924014331730994e-05, + "loss": 0.056, + "step": 23057 + }, + { + "epoch": 7.12, + "learning_rate": 1.4923579038566826e-05, + "loss": 0.0565, + "step": 23058 + }, + { + "epoch": 7.12, + "learning_rate": 1.492314373308789e-05, + "loss": 0.0583, + "step": 23059 + }, + { + "epoch": 7.12, + "learning_rate": 1.4922708415295272e-05, + "loss": 0.0553, + "step": 23060 + }, + { + "epoch": 7.12, + "learning_rate": 1.4922273085190065e-05, + "loss": 0.0645, + "step": 23061 + }, + { + "epoch": 7.12, + "learning_rate": 1.4921837742773355e-05, + "loss": 0.0587, + "step": 23062 + }, + { + "epoch": 7.12, + "learning_rate": 1.4921402388046228e-05, + "loss": 0.064, + "step": 23063 + }, + { + "epoch": 7.12, + "learning_rate": 1.492096702100978e-05, + "loss": 0.0586, + "step": 23064 + }, + { + "epoch": 7.12, + "learning_rate": 1.4920531641665093e-05, + "loss": 0.0647, + "step": 23065 + }, + { + "epoch": 7.12, + "learning_rate": 1.492009625001326e-05, + "loss": 0.0621, + "step": 23066 + }, + { + "epoch": 7.12, + "learning_rate": 1.491966084605537e-05, + "loss": 0.0666, + "step": 23067 + }, + { + "epoch": 7.12, + "learning_rate": 1.491922542979251e-05, + "loss": 0.0527, + "step": 23068 + }, + { + "epoch": 7.12, + "learning_rate": 1.4918790001225771e-05, + "loss": 0.0632, + "step": 23069 + }, + { + "epoch": 7.12, + "learning_rate": 1.4918354560356239e-05, + "loss": 0.0599, + "step": 23070 + }, + { + "epoch": 7.12, + "learning_rate": 1.4917919107185005e-05, + "loss": 0.061, + "step": 23071 + }, + { + "epoch": 7.13, + "learning_rate": 1.491748364171316e-05, + "loss": 0.0713, + "step": 23072 + }, + { + "epoch": 7.13, + "learning_rate": 1.491704816394179e-05, + "loss": 0.0634, + "step": 23073 + }, + { + "epoch": 7.13, + "learning_rate": 1.491661267387199e-05, + "loss": 0.0539, + "step": 23074 + }, + { + "epoch": 7.13, + "learning_rate": 1.4916177171504837e-05, + "loss": 0.0578, + "step": 23075 + }, + { + "epoch": 7.13, + "learning_rate": 1.4915741656841434e-05, + "loss": 0.0564, + "step": 23076 + }, + { + "epoch": 7.13, + "learning_rate": 1.4915306129882866e-05, + "loss": 0.0607, + "step": 23077 + }, + { + "epoch": 7.13, + "learning_rate": 1.4914870590630217e-05, + "loss": 0.0551, + "step": 23078 + }, + { + "epoch": 7.13, + "learning_rate": 1.4914435039084583e-05, + "loss": 0.06, + "step": 23079 + }, + { + "epoch": 7.13, + "learning_rate": 1.491399947524705e-05, + "loss": 0.068, + "step": 23080 + }, + { + "epoch": 7.13, + "learning_rate": 1.4913563899118705e-05, + "loss": 0.0567, + "step": 23081 + }, + { + "epoch": 7.13, + "learning_rate": 1.4913128310700644e-05, + "loss": 0.0586, + "step": 23082 + }, + { + "epoch": 7.13, + "learning_rate": 1.4912692709993952e-05, + "loss": 0.0592, + "step": 23083 + }, + { + "epoch": 7.13, + "learning_rate": 1.4912257096999718e-05, + "loss": 0.0597, + "step": 23084 + }, + { + "epoch": 7.13, + "learning_rate": 1.4911821471719034e-05, + "loss": 0.0611, + "step": 23085 + }, + { + "epoch": 7.13, + "learning_rate": 1.4911385834152991e-05, + "loss": 0.0661, + "step": 23086 + }, + { + "epoch": 7.13, + "learning_rate": 1.4910950184302673e-05, + "loss": 0.0568, + "step": 23087 + }, + { + "epoch": 7.13, + "learning_rate": 1.4910514522169175e-05, + "loss": 0.066, + "step": 23088 + }, + { + "epoch": 7.13, + "learning_rate": 1.4910078847753584e-05, + "loss": 0.0596, + "step": 23089 + }, + { + "epoch": 7.13, + "learning_rate": 1.490964316105699e-05, + "loss": 0.0639, + "step": 23090 + }, + { + "epoch": 7.13, + "learning_rate": 1.4909207462080483e-05, + "loss": 0.0635, + "step": 23091 + }, + { + "epoch": 7.13, + "learning_rate": 1.4908771750825152e-05, + "loss": 0.061, + "step": 23092 + }, + { + "epoch": 7.13, + "learning_rate": 1.4908336027292087e-05, + "loss": 0.0573, + "step": 23093 + }, + { + "epoch": 7.13, + "learning_rate": 1.4907900291482382e-05, + "loss": 0.0601, + "step": 23094 + }, + { + "epoch": 7.13, + "learning_rate": 1.4907464543397118e-05, + "loss": 0.061, + "step": 23095 + }, + { + "epoch": 7.13, + "learning_rate": 1.4907028783037394e-05, + "loss": 0.0622, + "step": 23096 + }, + { + "epoch": 7.13, + "learning_rate": 1.4906593010404299e-05, + "loss": 0.0604, + "step": 23097 + }, + { + "epoch": 7.13, + "learning_rate": 1.4906157225498912e-05, + "loss": 0.0672, + "step": 23098 + }, + { + "epoch": 7.13, + "learning_rate": 1.4905721428322335e-05, + "loss": 0.0569, + "step": 23099 + }, + { + "epoch": 7.13, + "learning_rate": 1.4905285618875658e-05, + "loss": 0.0596, + "step": 23100 + }, + { + "epoch": 7.13, + "learning_rate": 1.490484979715996e-05, + "loss": 0.0603, + "step": 23101 + }, + { + "epoch": 7.13, + "learning_rate": 1.4904413963176343e-05, + "loss": 0.0619, + "step": 23102 + }, + { + "epoch": 7.13, + "learning_rate": 1.4903978116925888e-05, + "loss": 0.056, + "step": 23103 + }, + { + "epoch": 7.14, + "learning_rate": 1.4903542258409692e-05, + "loss": 0.0632, + "step": 23104 + }, + { + "epoch": 7.14, + "learning_rate": 1.4903106387628842e-05, + "loss": 0.0578, + "step": 23105 + }, + { + "epoch": 7.14, + "learning_rate": 1.4902670504584427e-05, + "loss": 0.061, + "step": 23106 + }, + { + "epoch": 7.14, + "learning_rate": 1.4902234609277542e-05, + "loss": 0.0583, + "step": 23107 + }, + { + "epoch": 7.14, + "learning_rate": 1.4901798701709273e-05, + "loss": 0.0574, + "step": 23108 + }, + { + "epoch": 7.14, + "learning_rate": 1.4901362781880708e-05, + "loss": 0.0582, + "step": 23109 + }, + { + "epoch": 7.14, + "learning_rate": 1.4900926849792948e-05, + "loss": 0.0568, + "step": 23110 + }, + { + "epoch": 7.14, + "learning_rate": 1.4900490905447068e-05, + "loss": 0.0536, + "step": 23111 + }, + { + "epoch": 7.14, + "learning_rate": 1.4900054948844172e-05, + "loss": 0.0627, + "step": 23112 + }, + { + "epoch": 7.14, + "learning_rate": 1.4899618979985344e-05, + "loss": 0.0592, + "step": 23113 + }, + { + "epoch": 7.14, + "learning_rate": 1.4899182998871672e-05, + "loss": 0.0568, + "step": 23114 + }, + { + "epoch": 7.14, + "learning_rate": 1.4898747005504253e-05, + "loss": 0.0587, + "step": 23115 + }, + { + "epoch": 7.14, + "learning_rate": 1.4898310999884173e-05, + "loss": 0.0657, + "step": 23116 + }, + { + "epoch": 7.14, + "learning_rate": 1.4897874982012525e-05, + "loss": 0.06, + "step": 23117 + }, + { + "epoch": 7.14, + "learning_rate": 1.4897438951890398e-05, + "loss": 0.0519, + "step": 23118 + }, + { + "epoch": 7.14, + "learning_rate": 1.4897002909518883e-05, + "loss": 0.0599, + "step": 23119 + }, + { + "epoch": 7.14, + "learning_rate": 1.4896566854899069e-05, + "loss": 0.0585, + "step": 23120 + }, + { + "epoch": 7.14, + "learning_rate": 1.4896130788032049e-05, + "loss": 0.0633, + "step": 23121 + }, + { + "epoch": 7.14, + "learning_rate": 1.4895694708918913e-05, + "loss": 0.0622, + "step": 23122 + }, + { + "epoch": 7.14, + "learning_rate": 1.4895258617560752e-05, + "loss": 0.0564, + "step": 23123 + }, + { + "epoch": 7.14, + "learning_rate": 1.4894822513958657e-05, + "loss": 0.0557, + "step": 23124 + }, + { + "epoch": 7.14, + "learning_rate": 1.4894386398113716e-05, + "loss": 0.0559, + "step": 23125 + }, + { + "epoch": 7.14, + "learning_rate": 1.4893950270027024e-05, + "loss": 0.056, + "step": 23126 + }, + { + "epoch": 7.14, + "learning_rate": 1.489351412969967e-05, + "loss": 0.0624, + "step": 23127 + }, + { + "epoch": 7.14, + "learning_rate": 1.4893077977132744e-05, + "loss": 0.0604, + "step": 23128 + }, + { + "epoch": 7.14, + "learning_rate": 1.4892641812327335e-05, + "loss": 0.0596, + "step": 23129 + }, + { + "epoch": 7.14, + "learning_rate": 1.4892205635284538e-05, + "loss": 0.0585, + "step": 23130 + }, + { + "epoch": 7.14, + "learning_rate": 1.4891769446005446e-05, + "loss": 0.0611, + "step": 23131 + }, + { + "epoch": 7.14, + "learning_rate": 1.4891333244491142e-05, + "loss": 0.0583, + "step": 23132 + }, + { + "epoch": 7.14, + "learning_rate": 1.4890897030742724e-05, + "loss": 0.0612, + "step": 23133 + }, + { + "epoch": 7.14, + "learning_rate": 1.489046080476128e-05, + "loss": 0.0602, + "step": 23134 + }, + { + "epoch": 7.14, + "learning_rate": 1.4890024566547897e-05, + "loss": 0.0661, + "step": 23135 + }, + { + "epoch": 7.14, + "learning_rate": 1.4889588316103678e-05, + "loss": 0.0682, + "step": 23136 + }, + { + "epoch": 7.15, + "learning_rate": 1.4889152053429703e-05, + "loss": 0.0646, + "step": 23137 + }, + { + "epoch": 7.15, + "learning_rate": 1.4888715778527067e-05, + "loss": 0.0587, + "step": 23138 + }, + { + "epoch": 7.15, + "learning_rate": 1.4888279491396863e-05, + "loss": 0.0641, + "step": 23139 + }, + { + "epoch": 7.15, + "learning_rate": 1.4887843192040176e-05, + "loss": 0.0661, + "step": 23140 + }, + { + "epoch": 7.15, + "learning_rate": 1.4887406880458106e-05, + "loss": 0.0667, + "step": 23141 + }, + { + "epoch": 7.15, + "learning_rate": 1.4886970556651741e-05, + "loss": 0.0644, + "step": 23142 + }, + { + "epoch": 7.15, + "learning_rate": 1.4886534220622169e-05, + "loss": 0.0664, + "step": 23143 + }, + { + "epoch": 7.15, + "learning_rate": 1.4886097872370482e-05, + "loss": 0.067, + "step": 23144 + }, + { + "epoch": 7.15, + "learning_rate": 1.4885661511897776e-05, + "loss": 0.0618, + "step": 23145 + }, + { + "epoch": 7.15, + "learning_rate": 1.4885225139205138e-05, + "loss": 0.0696, + "step": 23146 + }, + { + "epoch": 7.15, + "learning_rate": 1.488478875429366e-05, + "loss": 0.0567, + "step": 23147 + }, + { + "epoch": 7.15, + "learning_rate": 1.4884352357164435e-05, + "loss": 0.0592, + "step": 23148 + }, + { + "epoch": 7.15, + "learning_rate": 1.4883915947818554e-05, + "loss": 0.0566, + "step": 23149 + }, + { + "epoch": 7.15, + "learning_rate": 1.488347952625711e-05, + "loss": 0.0713, + "step": 23150 + }, + { + "epoch": 7.15, + "learning_rate": 1.4883043092481196e-05, + "loss": 0.0605, + "step": 23151 + }, + { + "epoch": 7.15, + "learning_rate": 1.4882606646491893e-05, + "loss": 0.0611, + "step": 23152 + }, + { + "epoch": 7.15, + "learning_rate": 1.4882170188290304e-05, + "loss": 0.0646, + "step": 23153 + }, + { + "epoch": 7.15, + "learning_rate": 1.4881733717877516e-05, + "loss": 0.0633, + "step": 23154 + }, + { + "epoch": 7.15, + "learning_rate": 1.4881297235254622e-05, + "loss": 0.0565, + "step": 23155 + }, + { + "epoch": 7.15, + "learning_rate": 1.4880860740422716e-05, + "loss": 0.0558, + "step": 23156 + }, + { + "epoch": 7.15, + "learning_rate": 1.4880424233382883e-05, + "loss": 0.0597, + "step": 23157 + }, + { + "epoch": 7.15, + "learning_rate": 1.487998771413622e-05, + "loss": 0.0621, + "step": 23158 + }, + { + "epoch": 7.15, + "learning_rate": 1.487955118268382e-05, + "loss": 0.063, + "step": 23159 + }, + { + "epoch": 7.15, + "learning_rate": 1.4879114639026768e-05, + "loss": 0.0579, + "step": 23160 + }, + { + "epoch": 7.15, + "learning_rate": 1.4878678083166166e-05, + "loss": 0.062, + "step": 23161 + }, + { + "epoch": 7.15, + "learning_rate": 1.4878241515103095e-05, + "loss": 0.0618, + "step": 23162 + }, + { + "epoch": 7.15, + "learning_rate": 1.4877804934838654e-05, + "loss": 0.0625, + "step": 23163 + }, + { + "epoch": 7.15, + "learning_rate": 1.4877368342373936e-05, + "loss": 0.057, + "step": 23164 + }, + { + "epoch": 7.15, + "learning_rate": 1.4876931737710028e-05, + "loss": 0.0574, + "step": 23165 + }, + { + "epoch": 7.15, + "learning_rate": 1.4876495120848024e-05, + "loss": 0.061, + "step": 23166 + }, + { + "epoch": 7.15, + "learning_rate": 1.4876058491789018e-05, + "loss": 0.0648, + "step": 23167 + }, + { + "epoch": 7.15, + "learning_rate": 1.4875621850534096e-05, + "loss": 0.0577, + "step": 23168 + }, + { + "epoch": 7.16, + "learning_rate": 1.4875185197084358e-05, + "loss": 0.0589, + "step": 23169 + }, + { + "epoch": 7.16, + "learning_rate": 1.4874748531440895e-05, + "loss": 0.0612, + "step": 23170 + }, + { + "epoch": 7.16, + "learning_rate": 1.4874311853604792e-05, + "loss": 0.0703, + "step": 23171 + }, + { + "epoch": 7.16, + "learning_rate": 1.4873875163577148e-05, + "loss": 0.0607, + "step": 23172 + }, + { + "epoch": 7.16, + "learning_rate": 1.4873438461359052e-05, + "loss": 0.0647, + "step": 23173 + }, + { + "epoch": 7.16, + "learning_rate": 1.48730017469516e-05, + "loss": 0.0549, + "step": 23174 + }, + { + "epoch": 7.16, + "learning_rate": 1.487256502035588e-05, + "loss": 0.0639, + "step": 23175 + }, + { + "epoch": 7.16, + "learning_rate": 1.4872128281572989e-05, + "loss": 0.0619, + "step": 23176 + }, + { + "epoch": 7.16, + "learning_rate": 1.487169153060401e-05, + "loss": 0.0733, + "step": 23177 + }, + { + "epoch": 7.16, + "learning_rate": 1.4871254767450047e-05, + "loss": 0.0568, + "step": 23178 + }, + { + "epoch": 7.16, + "learning_rate": 1.4870817992112188e-05, + "loss": 0.0606, + "step": 23179 + }, + { + "epoch": 7.16, + "learning_rate": 1.4870381204591524e-05, + "loss": 0.0566, + "step": 23180 + }, + { + "epoch": 7.16, + "learning_rate": 1.4869944404889147e-05, + "loss": 0.0622, + "step": 23181 + }, + { + "epoch": 7.16, + "learning_rate": 1.4869507593006153e-05, + "loss": 0.0606, + "step": 23182 + }, + { + "epoch": 7.16, + "learning_rate": 1.486907076894363e-05, + "loss": 0.0567, + "step": 23183 + }, + { + "epoch": 7.16, + "learning_rate": 1.4868633932702675e-05, + "loss": 0.0648, + "step": 23184 + }, + { + "epoch": 7.16, + "learning_rate": 1.4868197084284375e-05, + "loss": 0.0701, + "step": 23185 + }, + { + "epoch": 7.16, + "learning_rate": 1.4867760223689828e-05, + "loss": 0.063, + "step": 23186 + }, + { + "epoch": 7.16, + "learning_rate": 1.486732335092013e-05, + "loss": 0.0613, + "step": 23187 + }, + { + "epoch": 7.16, + "learning_rate": 1.486688646597636e-05, + "loss": 0.0627, + "step": 23188 + }, + { + "epoch": 7.16, + "learning_rate": 1.4866449568859624e-05, + "loss": 0.0663, + "step": 23189 + }, + { + "epoch": 7.16, + "learning_rate": 1.4866012659571011e-05, + "loss": 0.0603, + "step": 23190 + }, + { + "epoch": 7.16, + "learning_rate": 1.4865575738111609e-05, + "loss": 0.0578, + "step": 23191 + }, + { + "epoch": 7.16, + "learning_rate": 1.486513880448252e-05, + "loss": 0.0588, + "step": 23192 + }, + { + "epoch": 7.16, + "learning_rate": 1.4864701858684827e-05, + "loss": 0.0583, + "step": 23193 + }, + { + "epoch": 7.16, + "learning_rate": 1.4864264900719628e-05, + "loss": 0.0546, + "step": 23194 + }, + { + "epoch": 7.16, + "learning_rate": 1.4863827930588018e-05, + "loss": 0.0553, + "step": 23195 + }, + { + "epoch": 7.16, + "learning_rate": 1.4863390948291086e-05, + "loss": 0.0672, + "step": 23196 + }, + { + "epoch": 7.16, + "learning_rate": 1.4862953953829924e-05, + "loss": 0.06, + "step": 23197 + }, + { + "epoch": 7.16, + "learning_rate": 1.4862516947205628e-05, + "loss": 0.068, + "step": 23198 + }, + { + "epoch": 7.16, + "learning_rate": 1.486207992841929e-05, + "loss": 0.0653, + "step": 23199 + }, + { + "epoch": 7.16, + "learning_rate": 1.4861642897472006e-05, + "loss": 0.0656, + "step": 23200 + }, + { + "epoch": 7.16, + "learning_rate": 1.4861205854364864e-05, + "loss": 0.0622, + "step": 23201 + }, + { + "epoch": 7.17, + "learning_rate": 1.486076879909896e-05, + "loss": 0.0558, + "step": 23202 + }, + { + "epoch": 7.17, + "learning_rate": 1.4860331731675388e-05, + "loss": 0.058, + "step": 23203 + }, + { + "epoch": 7.17, + "learning_rate": 1.485989465209524e-05, + "loss": 0.0672, + "step": 23204 + }, + { + "epoch": 7.17, + "learning_rate": 1.4859457560359606e-05, + "loss": 0.064, + "step": 23205 + }, + { + "epoch": 7.17, + "learning_rate": 1.4859020456469583e-05, + "loss": 0.0651, + "step": 23206 + }, + { + "epoch": 7.17, + "learning_rate": 1.4858583340426264e-05, + "loss": 0.0708, + "step": 23207 + }, + { + "epoch": 7.17, + "learning_rate": 1.4858146212230744e-05, + "loss": 0.0557, + "step": 23208 + }, + { + "epoch": 7.17, + "learning_rate": 1.4857709071884111e-05, + "loss": 0.0613, + "step": 23209 + }, + { + "epoch": 7.17, + "learning_rate": 1.4857271919387469e-05, + "loss": 0.064, + "step": 23210 + }, + { + "epoch": 7.17, + "learning_rate": 1.4856834754741895e-05, + "loss": 0.0625, + "step": 23211 + }, + { + "epoch": 7.17, + "learning_rate": 1.4856397577948495e-05, + "loss": 0.0604, + "step": 23212 + }, + { + "epoch": 7.17, + "learning_rate": 1.4855960389008362e-05, + "loss": 0.0647, + "step": 23213 + }, + { + "epoch": 7.17, + "learning_rate": 1.485552318792258e-05, + "loss": 0.0665, + "step": 23214 + }, + { + "epoch": 7.17, + "learning_rate": 1.4855085974692254e-05, + "loss": 0.064, + "step": 23215 + }, + { + "epoch": 7.17, + "learning_rate": 1.485464874931847e-05, + "loss": 0.0666, + "step": 23216 + }, + { + "epoch": 7.17, + "learning_rate": 1.4854211511802324e-05, + "loss": 0.0636, + "step": 23217 + }, + { + "epoch": 7.17, + "learning_rate": 1.485377426214491e-05, + "loss": 0.0646, + "step": 23218 + }, + { + "epoch": 7.17, + "learning_rate": 1.4853337000347323e-05, + "loss": 0.0689, + "step": 23219 + }, + { + "epoch": 7.17, + "learning_rate": 1.4852899726410655e-05, + "loss": 0.0643, + "step": 23220 + }, + { + "epoch": 7.17, + "learning_rate": 1.4852462440335997e-05, + "loss": 0.0595, + "step": 23221 + }, + { + "epoch": 7.17, + "learning_rate": 1.4852025142124444e-05, + "loss": 0.0521, + "step": 23222 + }, + { + "epoch": 7.17, + "learning_rate": 1.4851587831777097e-05, + "loss": 0.0595, + "step": 23223 + }, + { + "epoch": 7.17, + "learning_rate": 1.4851150509295042e-05, + "loss": 0.0619, + "step": 23224 + }, + { + "epoch": 7.17, + "learning_rate": 1.4850713174679373e-05, + "loss": 0.0638, + "step": 23225 + }, + { + "epoch": 7.17, + "learning_rate": 1.4850275827931186e-05, + "loss": 0.0673, + "step": 23226 + }, + { + "epoch": 7.17, + "learning_rate": 1.4849838469051574e-05, + "loss": 0.0632, + "step": 23227 + }, + { + "epoch": 7.17, + "learning_rate": 1.4849401098041634e-05, + "loss": 0.0601, + "step": 23228 + }, + { + "epoch": 7.17, + "learning_rate": 1.4848963714902453e-05, + "loss": 0.0587, + "step": 23229 + }, + { + "epoch": 7.17, + "learning_rate": 1.4848526319635133e-05, + "loss": 0.0666, + "step": 23230 + }, + { + "epoch": 7.17, + "learning_rate": 1.4848088912240764e-05, + "loss": 0.0664, + "step": 23231 + }, + { + "epoch": 7.17, + "learning_rate": 1.484765149272044e-05, + "loss": 0.0665, + "step": 23232 + }, + { + "epoch": 7.17, + "learning_rate": 1.4847214061075255e-05, + "loss": 0.0661, + "step": 23233 + }, + { + "epoch": 7.18, + "learning_rate": 1.4846776617306305e-05, + "loss": 0.0676, + "step": 23234 + }, + { + "epoch": 7.18, + "learning_rate": 1.484633916141468e-05, + "loss": 0.0607, + "step": 23235 + }, + { + "epoch": 7.18, + "learning_rate": 1.4845901693401478e-05, + "loss": 0.0657, + "step": 23236 + }, + { + "epoch": 7.18, + "learning_rate": 1.4845464213267792e-05, + "loss": 0.0603, + "step": 23237 + }, + { + "epoch": 7.18, + "learning_rate": 1.4845026721014716e-05, + "loss": 0.0644, + "step": 23238 + }, + { + "epoch": 7.18, + "learning_rate": 1.4844589216643345e-05, + "loss": 0.0574, + "step": 23239 + }, + { + "epoch": 7.18, + "learning_rate": 1.4844151700154775e-05, + "loss": 0.0647, + "step": 23240 + }, + { + "epoch": 7.18, + "learning_rate": 1.4843714171550096e-05, + "loss": 0.0562, + "step": 23241 + }, + { + "epoch": 7.18, + "learning_rate": 1.4843276630830403e-05, + "loss": 0.06, + "step": 23242 + }, + { + "epoch": 7.18, + "learning_rate": 1.484283907799679e-05, + "loss": 0.0569, + "step": 23243 + }, + { + "epoch": 7.18, + "learning_rate": 1.484240151305036e-05, + "loss": 0.062, + "step": 23244 + }, + { + "epoch": 7.18, + "learning_rate": 1.4841963935992196e-05, + "loss": 0.0665, + "step": 23245 + }, + { + "epoch": 7.18, + "learning_rate": 1.4841526346823401e-05, + "loss": 0.0656, + "step": 23246 + }, + { + "epoch": 7.18, + "learning_rate": 1.4841088745545061e-05, + "loss": 0.0658, + "step": 23247 + }, + { + "epoch": 7.18, + "learning_rate": 1.4840651132158274e-05, + "loss": 0.0667, + "step": 23248 + }, + { + "epoch": 7.18, + "learning_rate": 1.4840213506664141e-05, + "loss": 0.0649, + "step": 23249 + }, + { + "epoch": 7.18, + "learning_rate": 1.4839775869063749e-05, + "loss": 0.0603, + "step": 23250 + }, + { + "epoch": 7.18, + "learning_rate": 1.4839338219358195e-05, + "loss": 0.067, + "step": 23251 + }, + { + "epoch": 7.18, + "learning_rate": 1.483890055754857e-05, + "loss": 0.0607, + "step": 23252 + }, + { + "epoch": 7.18, + "learning_rate": 1.4838462883635973e-05, + "loss": 0.0657, + "step": 23253 + }, + { + "epoch": 7.18, + "learning_rate": 1.4838025197621502e-05, + "loss": 0.0583, + "step": 23254 + }, + { + "epoch": 7.18, + "learning_rate": 1.4837587499506247e-05, + "loss": 0.0659, + "step": 23255 + }, + { + "epoch": 7.18, + "learning_rate": 1.48371497892913e-05, + "loss": 0.0627, + "step": 23256 + }, + { + "epoch": 7.18, + "learning_rate": 1.483671206697776e-05, + "loss": 0.0643, + "step": 23257 + }, + { + "epoch": 7.18, + "learning_rate": 1.4836274332566722e-05, + "loss": 0.0746, + "step": 23258 + }, + { + "epoch": 7.18, + "learning_rate": 1.483583658605928e-05, + "loss": 0.0635, + "step": 23259 + }, + { + "epoch": 7.18, + "learning_rate": 1.4835398827456528e-05, + "loss": 0.063, + "step": 23260 + }, + { + "epoch": 7.18, + "learning_rate": 1.4834961056759562e-05, + "loss": 0.0656, + "step": 23261 + }, + { + "epoch": 7.18, + "learning_rate": 1.4834523273969476e-05, + "loss": 0.0611, + "step": 23262 + }, + { + "epoch": 7.18, + "learning_rate": 1.4834085479087368e-05, + "loss": 0.0647, + "step": 23263 + }, + { + "epoch": 7.18, + "learning_rate": 1.4833647672114332e-05, + "loss": 0.0629, + "step": 23264 + }, + { + "epoch": 7.18, + "learning_rate": 1.4833209853051454e-05, + "loss": 0.0686, + "step": 23265 + }, + { + "epoch": 7.19, + "learning_rate": 1.4832772021899842e-05, + "loss": 0.0574, + "step": 23266 + }, + { + "epoch": 7.19, + "learning_rate": 1.4832334178660584e-05, + "loss": 0.0695, + "step": 23267 + }, + { + "epoch": 7.19, + "learning_rate": 1.4831896323334775e-05, + "loss": 0.0597, + "step": 23268 + }, + { + "epoch": 7.19, + "learning_rate": 1.4831458455923517e-05, + "loss": 0.0637, + "step": 23269 + }, + { + "epoch": 7.19, + "learning_rate": 1.4831020576427897e-05, + "loss": 0.0595, + "step": 23270 + }, + { + "epoch": 7.19, + "learning_rate": 1.4830582684849014e-05, + "loss": 0.0594, + "step": 23271 + }, + { + "epoch": 7.19, + "learning_rate": 1.4830144781187963e-05, + "loss": 0.0605, + "step": 23272 + }, + { + "epoch": 7.19, + "learning_rate": 1.4829706865445837e-05, + "loss": 0.0641, + "step": 23273 + }, + { + "epoch": 7.19, + "learning_rate": 1.4829268937623737e-05, + "loss": 0.0627, + "step": 23274 + }, + { + "epoch": 7.19, + "learning_rate": 1.4828830997722751e-05, + "loss": 0.0581, + "step": 23275 + }, + { + "epoch": 7.19, + "learning_rate": 1.4828393045743978e-05, + "loss": 0.0604, + "step": 23276 + }, + { + "epoch": 7.19, + "learning_rate": 1.4827955081688516e-05, + "loss": 0.0652, + "step": 23277 + }, + { + "epoch": 7.19, + "learning_rate": 1.4827517105557459e-05, + "loss": 0.0637, + "step": 23278 + }, + { + "epoch": 7.19, + "learning_rate": 1.4827079117351895e-05, + "loss": 0.052, + "step": 23279 + }, + { + "epoch": 7.19, + "learning_rate": 1.482664111707293e-05, + "loss": 0.0749, + "step": 23280 + }, + { + "epoch": 7.19, + "learning_rate": 1.4826203104721657e-05, + "loss": 0.0604, + "step": 23281 + }, + { + "epoch": 7.19, + "learning_rate": 1.4825765080299166e-05, + "loss": 0.0578, + "step": 23282 + }, + { + "epoch": 7.19, + "learning_rate": 1.482532704380656e-05, + "loss": 0.0666, + "step": 23283 + }, + { + "epoch": 7.19, + "learning_rate": 1.4824888995244926e-05, + "loss": 0.0588, + "step": 23284 + }, + { + "epoch": 7.19, + "learning_rate": 1.4824450934615368e-05, + "loss": 0.0619, + "step": 23285 + }, + { + "epoch": 7.19, + "learning_rate": 1.4824012861918977e-05, + "loss": 0.0611, + "step": 23286 + }, + { + "epoch": 7.19, + "learning_rate": 1.4823574777156853e-05, + "loss": 0.0529, + "step": 23287 + }, + { + "epoch": 7.19, + "learning_rate": 1.4823136680330086e-05, + "loss": 0.0613, + "step": 23288 + }, + { + "epoch": 7.19, + "learning_rate": 1.4822698571439772e-05, + "loss": 0.0616, + "step": 23289 + }, + { + "epoch": 7.19, + "learning_rate": 1.4822260450487013e-05, + "loss": 0.0646, + "step": 23290 + }, + { + "epoch": 7.19, + "learning_rate": 1.4821822317472903e-05, + "loss": 0.0623, + "step": 23291 + }, + { + "epoch": 7.19, + "learning_rate": 1.4821384172398531e-05, + "loss": 0.0671, + "step": 23292 + }, + { + "epoch": 7.19, + "learning_rate": 1.4820946015265e-05, + "loss": 0.0602, + "step": 23293 + }, + { + "epoch": 7.19, + "learning_rate": 1.4820507846073404e-05, + "loss": 0.0666, + "step": 23294 + }, + { + "epoch": 7.19, + "learning_rate": 1.4820069664824841e-05, + "loss": 0.0599, + "step": 23295 + }, + { + "epoch": 7.19, + "learning_rate": 1.48196314715204e-05, + "loss": 0.06, + "step": 23296 + }, + { + "epoch": 7.19, + "learning_rate": 1.4819193266161182e-05, + "loss": 0.0676, + "step": 23297 + }, + { + "epoch": 7.19, + "learning_rate": 1.4818755048748287e-05, + "loss": 0.06, + "step": 23298 + }, + { + "epoch": 7.2, + "learning_rate": 1.4818316819282803e-05, + "loss": 0.0671, + "step": 23299 + }, + { + "epoch": 7.2, + "learning_rate": 1.4817878577765831e-05, + "loss": 0.0537, + "step": 23300 + }, + { + "epoch": 7.2, + "learning_rate": 1.4817440324198465e-05, + "loss": 0.0674, + "step": 23301 + }, + { + "epoch": 7.2, + "learning_rate": 1.4817002058581804e-05, + "loss": 0.0648, + "step": 23302 + }, + { + "epoch": 7.2, + "learning_rate": 1.4816563780916942e-05, + "loss": 0.0673, + "step": 23303 + }, + { + "epoch": 7.2, + "learning_rate": 1.4816125491204974e-05, + "loss": 0.0632, + "step": 23304 + }, + { + "epoch": 7.2, + "learning_rate": 1.4815687189446998e-05, + "loss": 0.0637, + "step": 23305 + }, + { + "epoch": 7.2, + "learning_rate": 1.4815248875644112e-05, + "loss": 0.0648, + "step": 23306 + }, + { + "epoch": 7.2, + "learning_rate": 1.4814810549797407e-05, + "loss": 0.0614, + "step": 23307 + }, + { + "epoch": 7.2, + "learning_rate": 1.4814372211907986e-05, + "loss": 0.0652, + "step": 23308 + }, + { + "epoch": 7.2, + "learning_rate": 1.4813933861976942e-05, + "loss": 0.0579, + "step": 23309 + }, + { + "epoch": 7.2, + "learning_rate": 1.4813495500005368e-05, + "loss": 0.0616, + "step": 23310 + }, + { + "epoch": 7.2, + "learning_rate": 1.4813057125994365e-05, + "loss": 0.07, + "step": 23311 + }, + { + "epoch": 7.2, + "learning_rate": 1.481261873994503e-05, + "loss": 0.0636, + "step": 23312 + }, + { + "epoch": 7.2, + "learning_rate": 1.4812180341858458e-05, + "loss": 0.0592, + "step": 23313 + }, + { + "epoch": 7.2, + "learning_rate": 1.4811741931735744e-05, + "loss": 0.0633, + "step": 23314 + }, + { + "epoch": 7.2, + "learning_rate": 1.4811303509577984e-05, + "loss": 0.0586, + "step": 23315 + }, + { + "epoch": 7.2, + "learning_rate": 1.4810865075386278e-05, + "loss": 0.0612, + "step": 23316 + }, + { + "epoch": 7.2, + "learning_rate": 1.4810426629161722e-05, + "loss": 0.0634, + "step": 23317 + }, + { + "epoch": 7.2, + "learning_rate": 1.4809988170905412e-05, + "loss": 0.0699, + "step": 23318 + }, + { + "epoch": 7.2, + "learning_rate": 1.4809549700618442e-05, + "loss": 0.0576, + "step": 23319 + }, + { + "epoch": 7.2, + "learning_rate": 1.4809111218301912e-05, + "loss": 0.0684, + "step": 23320 + }, + { + "epoch": 7.2, + "learning_rate": 1.4808672723956918e-05, + "loss": 0.0545, + "step": 23321 + }, + { + "epoch": 7.2, + "learning_rate": 1.4808234217584556e-05, + "loss": 0.0666, + "step": 23322 + }, + { + "epoch": 7.2, + "learning_rate": 1.4807795699185925e-05, + "loss": 0.0592, + "step": 23323 + }, + { + "epoch": 7.2, + "learning_rate": 1.4807357168762118e-05, + "loss": 0.0672, + "step": 23324 + }, + { + "epoch": 7.2, + "learning_rate": 1.4806918626314235e-05, + "loss": 0.0649, + "step": 23325 + }, + { + "epoch": 7.2, + "learning_rate": 1.4806480071843373e-05, + "loss": 0.0621, + "step": 23326 + }, + { + "epoch": 7.2, + "learning_rate": 1.4806041505350623e-05, + "loss": 0.066, + "step": 23327 + }, + { + "epoch": 7.2, + "learning_rate": 1.480560292683709e-05, + "loss": 0.063, + "step": 23328 + }, + { + "epoch": 7.2, + "learning_rate": 1.480516433630387e-05, + "loss": 0.0619, + "step": 23329 + }, + { + "epoch": 7.2, + "learning_rate": 1.4804725733752053e-05, + "loss": 0.0615, + "step": 23330 + }, + { + "epoch": 7.21, + "learning_rate": 1.4804287119182743e-05, + "loss": 0.0687, + "step": 23331 + }, + { + "epoch": 7.21, + "learning_rate": 1.4803848492597033e-05, + "loss": 0.0653, + "step": 23332 + }, + { + "epoch": 7.21, + "learning_rate": 1.4803409853996023e-05, + "loss": 0.0582, + "step": 23333 + }, + { + "epoch": 7.21, + "learning_rate": 1.4802971203380811e-05, + "loss": 0.0625, + "step": 23334 + }, + { + "epoch": 7.21, + "learning_rate": 1.4802532540752488e-05, + "loss": 0.06, + "step": 23335 + }, + { + "epoch": 7.21, + "learning_rate": 1.4802093866112159e-05, + "loss": 0.0688, + "step": 23336 + }, + { + "epoch": 7.21, + "learning_rate": 1.4801655179460914e-05, + "loss": 0.0617, + "step": 23337 + }, + { + "epoch": 7.21, + "learning_rate": 1.4801216480799854e-05, + "loss": 0.0658, + "step": 23338 + }, + { + "epoch": 7.21, + "learning_rate": 1.480077777013008e-05, + "loss": 0.0654, + "step": 23339 + }, + { + "epoch": 7.21, + "learning_rate": 1.4800339047452681e-05, + "loss": 0.0682, + "step": 23340 + }, + { + "epoch": 7.21, + "learning_rate": 1.4799900312768758e-05, + "loss": 0.0657, + "step": 23341 + }, + { + "epoch": 7.21, + "learning_rate": 1.4799461566079411e-05, + "loss": 0.0624, + "step": 23342 + }, + { + "epoch": 7.21, + "learning_rate": 1.4799022807385734e-05, + "loss": 0.0644, + "step": 23343 + }, + { + "epoch": 7.21, + "learning_rate": 1.4798584036688828e-05, + "loss": 0.0571, + "step": 23344 + }, + { + "epoch": 7.21, + "learning_rate": 1.4798145253989786e-05, + "loss": 0.0632, + "step": 23345 + }, + { + "epoch": 7.21, + "learning_rate": 1.4797706459289706e-05, + "loss": 0.059, + "step": 23346 + }, + { + "epoch": 7.21, + "learning_rate": 1.4797267652589691e-05, + "loss": 0.0647, + "step": 23347 + }, + { + "epoch": 7.21, + "learning_rate": 1.4796828833890833e-05, + "loss": 0.0694, + "step": 23348 + }, + { + "epoch": 7.21, + "learning_rate": 1.4796390003194231e-05, + "loss": 0.0608, + "step": 23349 + }, + { + "epoch": 7.21, + "learning_rate": 1.4795951160500983e-05, + "loss": 0.0611, + "step": 23350 + }, + { + "epoch": 7.21, + "learning_rate": 1.4795512305812184e-05, + "loss": 0.0647, + "step": 23351 + }, + { + "epoch": 7.21, + "learning_rate": 1.4795073439128937e-05, + "loss": 0.0782, + "step": 23352 + }, + { + "epoch": 7.21, + "learning_rate": 1.4794634560452337e-05, + "loss": 0.0582, + "step": 23353 + }, + { + "epoch": 7.21, + "learning_rate": 1.4794195669783484e-05, + "loss": 0.0567, + "step": 23354 + }, + { + "epoch": 7.21, + "learning_rate": 1.4793756767123468e-05, + "loss": 0.0546, + "step": 23355 + }, + { + "epoch": 7.21, + "learning_rate": 1.4793317852473392e-05, + "loss": 0.0674, + "step": 23356 + }, + { + "epoch": 7.21, + "learning_rate": 1.4792878925834357e-05, + "loss": 0.0676, + "step": 23357 + }, + { + "epoch": 7.21, + "learning_rate": 1.4792439987207457e-05, + "loss": 0.0511, + "step": 23358 + }, + { + "epoch": 7.21, + "learning_rate": 1.4792001036593791e-05, + "loss": 0.065, + "step": 23359 + }, + { + "epoch": 7.21, + "learning_rate": 1.4791562073994454e-05, + "loss": 0.0643, + "step": 23360 + }, + { + "epoch": 7.21, + "learning_rate": 1.4791123099410546e-05, + "loss": 0.0633, + "step": 23361 + }, + { + "epoch": 7.21, + "learning_rate": 1.4790684112843168e-05, + "loss": 0.062, + "step": 23362 + }, + { + "epoch": 7.22, + "learning_rate": 1.4790245114293416e-05, + "loss": 0.0673, + "step": 23363 + }, + { + "epoch": 7.22, + "learning_rate": 1.4789806103762383e-05, + "loss": 0.067, + "step": 23364 + }, + { + "epoch": 7.22, + "learning_rate": 1.4789367081251174e-05, + "loss": 0.0722, + "step": 23365 + }, + { + "epoch": 7.22, + "learning_rate": 1.4788928046760882e-05, + "loss": 0.0537, + "step": 23366 + }, + { + "epoch": 7.22, + "learning_rate": 1.4788489000292612e-05, + "loss": 0.0687, + "step": 23367 + }, + { + "epoch": 7.22, + "learning_rate": 1.4788049941847456e-05, + "loss": 0.0553, + "step": 23368 + }, + { + "epoch": 7.22, + "learning_rate": 1.4787610871426511e-05, + "loss": 0.064, + "step": 23369 + }, + { + "epoch": 7.22, + "learning_rate": 1.478717178903088e-05, + "loss": 0.0583, + "step": 23370 + }, + { + "epoch": 7.22, + "learning_rate": 1.478673269466166e-05, + "loss": 0.0615, + "step": 23371 + }, + { + "epoch": 7.22, + "learning_rate": 1.4786293588319946e-05, + "loss": 0.0618, + "step": 23372 + }, + { + "epoch": 7.22, + "learning_rate": 1.4785854470006842e-05, + "loss": 0.0579, + "step": 23373 + }, + { + "epoch": 7.22, + "learning_rate": 1.4785415339723441e-05, + "loss": 0.0694, + "step": 23374 + }, + { + "epoch": 7.22, + "learning_rate": 1.4784976197470843e-05, + "loss": 0.0626, + "step": 23375 + }, + { + "epoch": 7.22, + "learning_rate": 1.478453704325015e-05, + "loss": 0.0672, + "step": 23376 + }, + { + "epoch": 7.22, + "learning_rate": 1.4784097877062455e-05, + "loss": 0.0667, + "step": 23377 + }, + { + "epoch": 7.22, + "learning_rate": 1.4783658698908857e-05, + "loss": 0.0616, + "step": 23378 + }, + { + "epoch": 7.22, + "learning_rate": 1.4783219508790458e-05, + "loss": 0.0596, + "step": 23379 + }, + { + "epoch": 7.22, + "learning_rate": 1.4782780306708357e-05, + "loss": 0.0599, + "step": 23380 + }, + { + "epoch": 7.22, + "learning_rate": 1.4782341092663646e-05, + "loss": 0.0626, + "step": 23381 + }, + { + "epoch": 7.22, + "learning_rate": 1.478190186665743e-05, + "loss": 0.0654, + "step": 23382 + }, + { + "epoch": 7.22, + "learning_rate": 1.4781462628690803e-05, + "loss": 0.0621, + "step": 23383 + }, + { + "epoch": 7.22, + "learning_rate": 1.4781023378764868e-05, + "loss": 0.0653, + "step": 23384 + }, + { + "epoch": 7.22, + "learning_rate": 1.4780584116880723e-05, + "loss": 0.0598, + "step": 23385 + }, + { + "epoch": 7.22, + "learning_rate": 1.4780144843039461e-05, + "loss": 0.0637, + "step": 23386 + }, + { + "epoch": 7.22, + "learning_rate": 1.4779705557242187e-05, + "loss": 0.0655, + "step": 23387 + }, + { + "epoch": 7.22, + "learning_rate": 1.477926625949e-05, + "loss": 0.0627, + "step": 23388 + }, + { + "epoch": 7.22, + "learning_rate": 1.4778826949783991e-05, + "loss": 0.0613, + "step": 23389 + }, + { + "epoch": 7.22, + "learning_rate": 1.4778387628125268e-05, + "loss": 0.0665, + "step": 23390 + }, + { + "epoch": 7.22, + "learning_rate": 1.4777948294514927e-05, + "loss": 0.0637, + "step": 23391 + }, + { + "epoch": 7.22, + "learning_rate": 1.4777508948954063e-05, + "loss": 0.0661, + "step": 23392 + }, + { + "epoch": 7.22, + "learning_rate": 1.477706959144378e-05, + "loss": 0.0667, + "step": 23393 + }, + { + "epoch": 7.22, + "learning_rate": 1.4776630221985173e-05, + "loss": 0.057, + "step": 23394 + }, + { + "epoch": 7.22, + "learning_rate": 1.4776190840579342e-05, + "loss": 0.0581, + "step": 23395 + }, + { + "epoch": 7.23, + "learning_rate": 1.4775751447227388e-05, + "loss": 0.0682, + "step": 23396 + }, + { + "epoch": 7.23, + "learning_rate": 1.477531204193041e-05, + "loss": 0.0567, + "step": 23397 + }, + { + "epoch": 7.23, + "learning_rate": 1.4774872624689502e-05, + "loss": 0.0619, + "step": 23398 + }, + { + "epoch": 7.23, + "learning_rate": 1.4774433195505769e-05, + "loss": 0.0598, + "step": 23399 + }, + { + "epoch": 7.23, + "learning_rate": 1.4773993754380306e-05, + "loss": 0.0715, + "step": 23400 + }, + { + "epoch": 7.23, + "learning_rate": 1.4773554301314217e-05, + "loss": 0.0728, + "step": 23401 + }, + { + "epoch": 7.23, + "learning_rate": 1.4773114836308598e-05, + "loss": 0.0702, + "step": 23402 + }, + { + "epoch": 7.23, + "learning_rate": 1.4772675359364546e-05, + "loss": 0.0658, + "step": 23403 + }, + { + "epoch": 7.23, + "learning_rate": 1.4772235870483163e-05, + "loss": 0.0649, + "step": 23404 + }, + { + "epoch": 7.23, + "learning_rate": 1.4771796369665548e-05, + "loss": 0.0616, + "step": 23405 + }, + { + "epoch": 7.23, + "learning_rate": 1.4771356856912797e-05, + "loss": 0.0554, + "step": 23406 + }, + { + "epoch": 7.23, + "learning_rate": 1.4770917332226016e-05, + "loss": 0.0563, + "step": 23407 + }, + { + "epoch": 7.23, + "learning_rate": 1.4770477795606301e-05, + "loss": 0.0698, + "step": 23408 + }, + { + "epoch": 7.23, + "learning_rate": 1.4770038247054748e-05, + "loss": 0.0602, + "step": 23409 + }, + { + "epoch": 7.23, + "learning_rate": 1.4769598686572462e-05, + "loss": 0.0606, + "step": 23410 + }, + { + "epoch": 7.23, + "learning_rate": 1.4769159114160538e-05, + "loss": 0.0661, + "step": 23411 + }, + { + "epoch": 7.23, + "learning_rate": 1.4768719529820078e-05, + "loss": 0.0657, + "step": 23412 + }, + { + "epoch": 7.23, + "learning_rate": 1.476827993355218e-05, + "loss": 0.0639, + "step": 23413 + }, + { + "epoch": 7.23, + "learning_rate": 1.4767840325357944e-05, + "loss": 0.0615, + "step": 23414 + }, + { + "epoch": 7.23, + "learning_rate": 1.476740070523847e-05, + "loss": 0.0575, + "step": 23415 + }, + { + "epoch": 7.23, + "learning_rate": 1.4766961073194859e-05, + "loss": 0.058, + "step": 23416 + }, + { + "epoch": 7.23, + "learning_rate": 1.4766521429228207e-05, + "loss": 0.06, + "step": 23417 + }, + { + "epoch": 7.23, + "learning_rate": 1.4766081773339618e-05, + "loss": 0.0631, + "step": 23418 + }, + { + "epoch": 7.23, + "learning_rate": 1.4765642105530186e-05, + "loss": 0.0726, + "step": 23419 + }, + { + "epoch": 7.23, + "learning_rate": 1.4765202425801016e-05, + "loss": 0.0662, + "step": 23420 + }, + { + "epoch": 7.23, + "learning_rate": 1.4764762734153206e-05, + "loss": 0.0635, + "step": 23421 + }, + { + "epoch": 7.23, + "learning_rate": 1.4764323030587852e-05, + "loss": 0.0614, + "step": 23422 + }, + { + "epoch": 7.23, + "learning_rate": 1.4763883315106063e-05, + "loss": 0.0667, + "step": 23423 + }, + { + "epoch": 7.23, + "learning_rate": 1.4763443587708927e-05, + "loss": 0.0643, + "step": 23424 + }, + { + "epoch": 7.23, + "learning_rate": 1.4763003848397552e-05, + "loss": 0.066, + "step": 23425 + }, + { + "epoch": 7.23, + "learning_rate": 1.4762564097173036e-05, + "loss": 0.0629, + "step": 23426 + }, + { + "epoch": 7.23, + "learning_rate": 1.4762124334036478e-05, + "loss": 0.0649, + "step": 23427 + }, + { + "epoch": 7.24, + "learning_rate": 1.476168455898898e-05, + "loss": 0.0642, + "step": 23428 + }, + { + "epoch": 7.24, + "learning_rate": 1.4761244772031638e-05, + "loss": 0.0644, + "step": 23429 + }, + { + "epoch": 7.24, + "learning_rate": 1.4760804973165557e-05, + "loss": 0.0635, + "step": 23430 + }, + { + "epoch": 7.24, + "learning_rate": 1.4760365162391831e-05, + "loss": 0.0602, + "step": 23431 + }, + { + "epoch": 7.24, + "learning_rate": 1.4759925339711567e-05, + "loss": 0.0641, + "step": 23432 + }, + { + "epoch": 7.24, + "learning_rate": 1.475948550512586e-05, + "loss": 0.0625, + "step": 23433 + }, + { + "epoch": 7.24, + "learning_rate": 1.4759045658635813e-05, + "loss": 0.0651, + "step": 23434 + }, + { + "epoch": 7.24, + "learning_rate": 1.4758605800242522e-05, + "loss": 0.0615, + "step": 23435 + }, + { + "epoch": 7.24, + "learning_rate": 1.4758165929947093e-05, + "loss": 0.0559, + "step": 23436 + }, + { + "epoch": 7.24, + "learning_rate": 1.4757726047750622e-05, + "loss": 0.0622, + "step": 23437 + }, + { + "epoch": 7.24, + "learning_rate": 1.475728615365421e-05, + "loss": 0.0646, + "step": 23438 + }, + { + "epoch": 7.24, + "learning_rate": 1.475684624765896e-05, + "loss": 0.0672, + "step": 23439 + }, + { + "epoch": 7.24, + "learning_rate": 1.4756406329765964e-05, + "loss": 0.0633, + "step": 23440 + }, + { + "epoch": 7.24, + "learning_rate": 1.4755966399976333e-05, + "loss": 0.0626, + "step": 23441 + }, + { + "epoch": 7.24, + "learning_rate": 1.4755526458291165e-05, + "loss": 0.0601, + "step": 23442 + }, + { + "epoch": 7.24, + "learning_rate": 1.4755086504711553e-05, + "loss": 0.0605, + "step": 23443 + }, + { + "epoch": 7.24, + "learning_rate": 1.4754646539238606e-05, + "loss": 0.0664, + "step": 23444 + }, + { + "epoch": 7.24, + "learning_rate": 1.4754206561873417e-05, + "loss": 0.0693, + "step": 23445 + }, + { + "epoch": 7.24, + "learning_rate": 1.475376657261709e-05, + "loss": 0.0624, + "step": 23446 + }, + { + "epoch": 7.24, + "learning_rate": 1.4753326571470732e-05, + "loss": 0.0601, + "step": 23447 + }, + { + "epoch": 7.24, + "learning_rate": 1.4752886558435431e-05, + "loss": 0.0679, + "step": 23448 + }, + { + "epoch": 7.24, + "learning_rate": 1.4752446533512296e-05, + "loss": 0.0665, + "step": 23449 + }, + { + "epoch": 7.24, + "learning_rate": 1.4752006496702426e-05, + "loss": 0.0725, + "step": 23450 + }, + { + "epoch": 7.24, + "learning_rate": 1.475156644800692e-05, + "loss": 0.0607, + "step": 23451 + }, + { + "epoch": 7.24, + "learning_rate": 1.4751126387426881e-05, + "loss": 0.0605, + "step": 23452 + }, + { + "epoch": 7.24, + "learning_rate": 1.4750686314963407e-05, + "loss": 0.0629, + "step": 23453 + }, + { + "epoch": 7.24, + "learning_rate": 1.4750246230617602e-05, + "loss": 0.0637, + "step": 23454 + }, + { + "epoch": 7.24, + "learning_rate": 1.4749806134390563e-05, + "loss": 0.0566, + "step": 23455 + }, + { + "epoch": 7.24, + "learning_rate": 1.4749366026283393e-05, + "loss": 0.0646, + "step": 23456 + }, + { + "epoch": 7.24, + "learning_rate": 1.4748925906297192e-05, + "loss": 0.0614, + "step": 23457 + }, + { + "epoch": 7.24, + "learning_rate": 1.474848577443306e-05, + "loss": 0.0662, + "step": 23458 + }, + { + "epoch": 7.24, + "learning_rate": 1.4748045630692103e-05, + "loss": 0.0636, + "step": 23459 + }, + { + "epoch": 7.24, + "learning_rate": 1.4747605475075414e-05, + "loss": 0.0639, + "step": 23460 + }, + { + "epoch": 7.25, + "learning_rate": 1.47471653075841e-05, + "loss": 0.0665, + "step": 23461 + }, + { + "epoch": 7.25, + "learning_rate": 1.4746725128219259e-05, + "loss": 0.0612, + "step": 23462 + }, + { + "epoch": 7.25, + "learning_rate": 1.4746284936981991e-05, + "loss": 0.0649, + "step": 23463 + }, + { + "epoch": 7.25, + "learning_rate": 1.47458447338734e-05, + "loss": 0.0646, + "step": 23464 + }, + { + "epoch": 7.25, + "learning_rate": 1.4745404518894586e-05, + "loss": 0.061, + "step": 23465 + }, + { + "epoch": 7.25, + "learning_rate": 1.474496429204665e-05, + "loss": 0.0603, + "step": 23466 + }, + { + "epoch": 7.25, + "learning_rate": 1.4744524053330695e-05, + "loss": 0.0582, + "step": 23467 + }, + { + "epoch": 7.25, + "learning_rate": 1.4744083802747815e-05, + "loss": 0.0687, + "step": 23468 + }, + { + "epoch": 7.25, + "learning_rate": 1.474364354029912e-05, + "loss": 0.0625, + "step": 23469 + }, + { + "epoch": 7.25, + "learning_rate": 1.4743203265985708e-05, + "loss": 0.0653, + "step": 23470 + }, + { + "epoch": 7.25, + "learning_rate": 1.4742762979808675e-05, + "loss": 0.0597, + "step": 23471 + }, + { + "epoch": 7.25, + "learning_rate": 1.4742322681769133e-05, + "loss": 0.0622, + "step": 23472 + }, + { + "epoch": 7.25, + "learning_rate": 1.4741882371868173e-05, + "loss": 0.067, + "step": 23473 + }, + { + "epoch": 7.25, + "learning_rate": 1.4741442050106897e-05, + "loss": 0.0669, + "step": 23474 + }, + { + "epoch": 7.25, + "learning_rate": 1.4741001716486416e-05, + "loss": 0.0662, + "step": 23475 + }, + { + "epoch": 7.25, + "learning_rate": 1.4740561371007825e-05, + "loss": 0.06, + "step": 23476 + }, + { + "epoch": 7.25, + "learning_rate": 1.474012101367222e-05, + "loss": 0.064, + "step": 23477 + }, + { + "epoch": 7.25, + "learning_rate": 1.4739680644480711e-05, + "loss": 0.0654, + "step": 23478 + }, + { + "epoch": 7.25, + "learning_rate": 1.4739240263434396e-05, + "loss": 0.0572, + "step": 23479 + }, + { + "epoch": 7.25, + "learning_rate": 1.4738799870534377e-05, + "loss": 0.0636, + "step": 23480 + }, + { + "epoch": 7.25, + "learning_rate": 1.4738359465781755e-05, + "loss": 0.0621, + "step": 23481 + }, + { + "epoch": 7.25, + "learning_rate": 1.4737919049177632e-05, + "loss": 0.0663, + "step": 23482 + }, + { + "epoch": 7.25, + "learning_rate": 1.4737478620723109e-05, + "loss": 0.0706, + "step": 23483 + }, + { + "epoch": 7.25, + "learning_rate": 1.4737038180419287e-05, + "loss": 0.0621, + "step": 23484 + }, + { + "epoch": 7.25, + "learning_rate": 1.4736597728267268e-05, + "loss": 0.0594, + "step": 23485 + }, + { + "epoch": 7.25, + "learning_rate": 1.4736157264268156e-05, + "loss": 0.0652, + "step": 23486 + }, + { + "epoch": 7.25, + "learning_rate": 1.4735716788423052e-05, + "loss": 0.0698, + "step": 23487 + }, + { + "epoch": 7.25, + "learning_rate": 1.4735276300733055e-05, + "loss": 0.0532, + "step": 23488 + }, + { + "epoch": 7.25, + "learning_rate": 1.4734835801199268e-05, + "loss": 0.062, + "step": 23489 + }, + { + "epoch": 7.25, + "learning_rate": 1.4734395289822791e-05, + "loss": 0.0666, + "step": 23490 + }, + { + "epoch": 7.25, + "learning_rate": 1.4733954766604732e-05, + "loss": 0.0594, + "step": 23491 + }, + { + "epoch": 7.25, + "learning_rate": 1.4733514231546187e-05, + "loss": 0.057, + "step": 23492 + }, + { + "epoch": 7.26, + "learning_rate": 1.473307368464826e-05, + "loss": 0.066, + "step": 23493 + }, + { + "epoch": 7.26, + "learning_rate": 1.473263312591205e-05, + "loss": 0.0616, + "step": 23494 + }, + { + "epoch": 7.26, + "learning_rate": 1.4732192555338665e-05, + "loss": 0.0661, + "step": 23495 + }, + { + "epoch": 7.26, + "learning_rate": 1.47317519729292e-05, + "loss": 0.074, + "step": 23496 + }, + { + "epoch": 7.26, + "learning_rate": 1.4731311378684762e-05, + "loss": 0.0552, + "step": 23497 + }, + { + "epoch": 7.26, + "learning_rate": 1.4730870772606454e-05, + "loss": 0.0591, + "step": 23498 + }, + { + "epoch": 7.26, + "learning_rate": 1.473043015469537e-05, + "loss": 0.0642, + "step": 23499 + }, + { + "epoch": 7.26, + "learning_rate": 1.4729989524952619e-05, + "loss": 0.0661, + "step": 23500 + }, + { + "epoch": 7.26, + "learning_rate": 1.4729548883379305e-05, + "loss": 0.0596, + "step": 23501 + }, + { + "epoch": 7.26, + "learning_rate": 1.4729108229976523e-05, + "loss": 0.0615, + "step": 23502 + }, + { + "epoch": 7.26, + "learning_rate": 1.472866756474538e-05, + "loss": 0.057, + "step": 23503 + }, + { + "epoch": 7.26, + "learning_rate": 1.4728226887686978e-05, + "loss": 0.0656, + "step": 23504 + }, + { + "epoch": 7.26, + "learning_rate": 1.4727786198802414e-05, + "loss": 0.0644, + "step": 23505 + }, + { + "epoch": 7.26, + "learning_rate": 1.47273454980928e-05, + "loss": 0.0639, + "step": 23506 + }, + { + "epoch": 7.26, + "learning_rate": 1.472690478555923e-05, + "loss": 0.0573, + "step": 23507 + }, + { + "epoch": 7.26, + "learning_rate": 1.472646406120281e-05, + "loss": 0.0691, + "step": 23508 + }, + { + "epoch": 7.26, + "learning_rate": 1.472602332502464e-05, + "loss": 0.0649, + "step": 23509 + }, + { + "epoch": 7.26, + "learning_rate": 1.4725582577025823e-05, + "loss": 0.0603, + "step": 23510 + }, + { + "epoch": 7.26, + "learning_rate": 1.4725141817207465e-05, + "loss": 0.0657, + "step": 23511 + }, + { + "epoch": 7.26, + "learning_rate": 1.4724701045570665e-05, + "loss": 0.0674, + "step": 23512 + }, + { + "epoch": 7.26, + "learning_rate": 1.4724260262116524e-05, + "loss": 0.0623, + "step": 23513 + }, + { + "epoch": 7.26, + "learning_rate": 1.4723819466846147e-05, + "loss": 0.0609, + "step": 23514 + }, + { + "epoch": 7.26, + "learning_rate": 1.4723378659760634e-05, + "loss": 0.065, + "step": 23515 + }, + { + "epoch": 7.26, + "learning_rate": 1.4722937840861093e-05, + "loss": 0.0625, + "step": 23516 + }, + { + "epoch": 7.26, + "learning_rate": 1.4722497010148622e-05, + "loss": 0.0667, + "step": 23517 + }, + { + "epoch": 7.26, + "learning_rate": 1.4722056167624324e-05, + "loss": 0.0646, + "step": 23518 + }, + { + "epoch": 7.26, + "learning_rate": 1.4721615313289302e-05, + "loss": 0.0655, + "step": 23519 + }, + { + "epoch": 7.26, + "learning_rate": 1.4721174447144659e-05, + "loss": 0.0636, + "step": 23520 + }, + { + "epoch": 7.26, + "learning_rate": 1.47207335691915e-05, + "loss": 0.0642, + "step": 23521 + }, + { + "epoch": 7.26, + "learning_rate": 1.4720292679430923e-05, + "loss": 0.0679, + "step": 23522 + }, + { + "epoch": 7.26, + "learning_rate": 1.4719851777864032e-05, + "loss": 0.0616, + "step": 23523 + }, + { + "epoch": 7.26, + "learning_rate": 1.4719410864491934e-05, + "loss": 0.0658, + "step": 23524 + }, + { + "epoch": 7.27, + "learning_rate": 1.4718969939315726e-05, + "loss": 0.0564, + "step": 23525 + }, + { + "epoch": 7.27, + "learning_rate": 1.4718529002336517e-05, + "loss": 0.0662, + "step": 23526 + }, + { + "epoch": 7.27, + "learning_rate": 1.4718088053555404e-05, + "loss": 0.0727, + "step": 23527 + }, + { + "epoch": 7.27, + "learning_rate": 1.4717647092973489e-05, + "loss": 0.0596, + "step": 23528 + }, + { + "epoch": 7.27, + "learning_rate": 1.4717206120591883e-05, + "loss": 0.0665, + "step": 23529 + }, + { + "epoch": 7.27, + "learning_rate": 1.4716765136411682e-05, + "loss": 0.0636, + "step": 23530 + }, + { + "epoch": 7.27, + "learning_rate": 1.4716324140433993e-05, + "loss": 0.0644, + "step": 23531 + }, + { + "epoch": 7.27, + "learning_rate": 1.4715883132659916e-05, + "loss": 0.0675, + "step": 23532 + }, + { + "epoch": 7.27, + "learning_rate": 1.4715442113090552e-05, + "loss": 0.0572, + "step": 23533 + }, + { + "epoch": 7.27, + "learning_rate": 1.4715001081727012e-05, + "loss": 0.0647, + "step": 23534 + }, + { + "epoch": 7.27, + "learning_rate": 1.4714560038570391e-05, + "loss": 0.0602, + "step": 23535 + }, + { + "epoch": 7.27, + "learning_rate": 1.4714118983621797e-05, + "loss": 0.0645, + "step": 23536 + }, + { + "epoch": 7.27, + "learning_rate": 1.4713677916882332e-05, + "loss": 0.06, + "step": 23537 + }, + { + "epoch": 7.27, + "learning_rate": 1.4713236838353098e-05, + "loss": 0.0663, + "step": 23538 + }, + { + "epoch": 7.27, + "learning_rate": 1.47127957480352e-05, + "loss": 0.0738, + "step": 23539 + }, + { + "epoch": 7.27, + "learning_rate": 1.471235464592974e-05, + "loss": 0.0619, + "step": 23540 + }, + { + "epoch": 7.27, + "learning_rate": 1.4711913532037821e-05, + "loss": 0.0686, + "step": 23541 + }, + { + "epoch": 7.27, + "learning_rate": 1.4711472406360548e-05, + "loss": 0.0694, + "step": 23542 + }, + { + "epoch": 7.27, + "learning_rate": 1.471103126889902e-05, + "loss": 0.0643, + "step": 23543 + }, + { + "epoch": 7.27, + "learning_rate": 1.4710590119654346e-05, + "loss": 0.0601, + "step": 23544 + }, + { + "epoch": 7.27, + "learning_rate": 1.4710148958627628e-05, + "loss": 0.0579, + "step": 23545 + }, + { + "epoch": 7.27, + "learning_rate": 1.4709707785819967e-05, + "loss": 0.0619, + "step": 23546 + }, + { + "epoch": 7.27, + "learning_rate": 1.4709266601232468e-05, + "loss": 0.0555, + "step": 23547 + }, + { + "epoch": 7.27, + "learning_rate": 1.4708825404866233e-05, + "loss": 0.0588, + "step": 23548 + }, + { + "epoch": 7.27, + "learning_rate": 1.4708384196722368e-05, + "loss": 0.0621, + "step": 23549 + }, + { + "epoch": 7.27, + "learning_rate": 1.4707942976801976e-05, + "loss": 0.0622, + "step": 23550 + }, + { + "epoch": 7.27, + "learning_rate": 1.4707501745106158e-05, + "loss": 0.0648, + "step": 23551 + }, + { + "epoch": 7.27, + "learning_rate": 1.4707060501636024e-05, + "loss": 0.069, + "step": 23552 + }, + { + "epoch": 7.27, + "learning_rate": 1.4706619246392668e-05, + "loss": 0.0585, + "step": 23553 + }, + { + "epoch": 7.27, + "learning_rate": 1.47061779793772e-05, + "loss": 0.0716, + "step": 23554 + }, + { + "epoch": 7.27, + "learning_rate": 1.4705736700590728e-05, + "loss": 0.0621, + "step": 23555 + }, + { + "epoch": 7.27, + "learning_rate": 1.4705295410034341e-05, + "loss": 0.0632, + "step": 23556 + }, + { + "epoch": 7.27, + "learning_rate": 1.4704854107709158e-05, + "loss": 0.0664, + "step": 23557 + }, + { + "epoch": 7.28, + "learning_rate": 1.4704412793616277e-05, + "loss": 0.0683, + "step": 23558 + }, + { + "epoch": 7.28, + "learning_rate": 1.4703971467756799e-05, + "loss": 0.0716, + "step": 23559 + }, + { + "epoch": 7.28, + "learning_rate": 1.4703530130131831e-05, + "loss": 0.0671, + "step": 23560 + }, + { + "epoch": 7.28, + "learning_rate": 1.4703088780742475e-05, + "loss": 0.07, + "step": 23561 + }, + { + "epoch": 7.28, + "learning_rate": 1.470264741958984e-05, + "loss": 0.0582, + "step": 23562 + }, + { + "epoch": 7.28, + "learning_rate": 1.4702206046675025e-05, + "loss": 0.0608, + "step": 23563 + }, + { + "epoch": 7.28, + "learning_rate": 1.4701764661999132e-05, + "loss": 0.0671, + "step": 23564 + }, + { + "epoch": 7.28, + "learning_rate": 1.470132326556327e-05, + "loss": 0.0689, + "step": 23565 + }, + { + "epoch": 7.28, + "learning_rate": 1.4700881857368543e-05, + "loss": 0.0656, + "step": 23566 + }, + { + "epoch": 7.28, + "learning_rate": 1.470044043741605e-05, + "loss": 0.0532, + "step": 23567 + }, + { + "epoch": 7.28, + "learning_rate": 1.46999990057069e-05, + "loss": 0.0701, + "step": 23568 + }, + { + "epoch": 7.28, + "learning_rate": 1.4699557562242195e-05, + "loss": 0.0565, + "step": 23569 + }, + { + "epoch": 7.28, + "learning_rate": 1.4699116107023036e-05, + "loss": 0.0617, + "step": 23570 + }, + { + "epoch": 7.28, + "learning_rate": 1.4698674640050534e-05, + "loss": 0.064, + "step": 23571 + }, + { + "epoch": 7.28, + "learning_rate": 1.469823316132579e-05, + "loss": 0.07, + "step": 23572 + }, + { + "epoch": 7.28, + "learning_rate": 1.4697791670849908e-05, + "loss": 0.0679, + "step": 23573 + }, + { + "epoch": 7.28, + "learning_rate": 1.4697350168623991e-05, + "loss": 0.0615, + "step": 23574 + }, + { + "epoch": 7.28, + "learning_rate": 1.4696908654649148e-05, + "loss": 0.0719, + "step": 23575 + }, + { + "epoch": 7.28, + "learning_rate": 1.4696467128926472e-05, + "loss": 0.0753, + "step": 23576 + }, + { + "epoch": 7.28, + "learning_rate": 1.469602559145708e-05, + "loss": 0.0679, + "step": 23577 + }, + { + "epoch": 7.28, + "learning_rate": 1.4695584042242073e-05, + "loss": 0.0685, + "step": 23578 + }, + { + "epoch": 7.28, + "learning_rate": 1.4695142481282551e-05, + "loss": 0.0643, + "step": 23579 + }, + { + "epoch": 7.28, + "learning_rate": 1.4694700908579625e-05, + "loss": 0.0598, + "step": 23580 + }, + { + "epoch": 7.28, + "learning_rate": 1.4694259324134391e-05, + "loss": 0.0647, + "step": 23581 + }, + { + "epoch": 7.28, + "learning_rate": 1.4693817727947961e-05, + "loss": 0.0676, + "step": 23582 + }, + { + "epoch": 7.28, + "learning_rate": 1.4693376120021438e-05, + "loss": 0.0646, + "step": 23583 + }, + { + "epoch": 7.28, + "learning_rate": 1.4692934500355922e-05, + "loss": 0.0714, + "step": 23584 + }, + { + "epoch": 7.28, + "learning_rate": 1.4692492868952522e-05, + "loss": 0.0647, + "step": 23585 + }, + { + "epoch": 7.28, + "learning_rate": 1.4692051225812345e-05, + "loss": 0.065, + "step": 23586 + }, + { + "epoch": 7.28, + "learning_rate": 1.4691609570936486e-05, + "loss": 0.0649, + "step": 23587 + }, + { + "epoch": 7.28, + "learning_rate": 1.4691167904326062e-05, + "loss": 0.0596, + "step": 23588 + }, + { + "epoch": 7.28, + "learning_rate": 1.4690726225982169e-05, + "loss": 0.0621, + "step": 23589 + }, + { + "epoch": 7.29, + "learning_rate": 1.469028453590591e-05, + "loss": 0.0704, + "step": 23590 + }, + { + "epoch": 7.29, + "learning_rate": 1.46898428340984e-05, + "loss": 0.0635, + "step": 23591 + }, + { + "epoch": 7.29, + "learning_rate": 1.4689401120560733e-05, + "loss": 0.0654, + "step": 23592 + }, + { + "epoch": 7.29, + "learning_rate": 1.4688959395294023e-05, + "loss": 0.0653, + "step": 23593 + }, + { + "epoch": 7.29, + "learning_rate": 1.4688517658299366e-05, + "loss": 0.0704, + "step": 23594 + }, + { + "epoch": 7.29, + "learning_rate": 1.4688075909577873e-05, + "loss": 0.067, + "step": 23595 + }, + { + "epoch": 7.29, + "learning_rate": 1.4687634149130648e-05, + "loss": 0.063, + "step": 23596 + }, + { + "epoch": 7.29, + "learning_rate": 1.4687192376958795e-05, + "loss": 0.0694, + "step": 23597 + }, + { + "epoch": 7.29, + "learning_rate": 1.4686750593063416e-05, + "loss": 0.07, + "step": 23598 + }, + { + "epoch": 7.29, + "learning_rate": 1.4686308797445623e-05, + "loss": 0.0602, + "step": 23599 + }, + { + "epoch": 7.29, + "learning_rate": 1.4685866990106514e-05, + "loss": 0.0633, + "step": 23600 + }, + { + "epoch": 7.29, + "learning_rate": 1.46854251710472e-05, + "loss": 0.056, + "step": 23601 + }, + { + "epoch": 7.29, + "learning_rate": 1.4684983340268779e-05, + "loss": 0.0607, + "step": 23602 + }, + { + "epoch": 7.29, + "learning_rate": 1.4684541497772364e-05, + "loss": 0.0737, + "step": 23603 + }, + { + "epoch": 7.29, + "learning_rate": 1.4684099643559053e-05, + "loss": 0.0684, + "step": 23604 + }, + { + "epoch": 7.29, + "learning_rate": 1.4683657777629958e-05, + "loss": 0.0636, + "step": 23605 + }, + { + "epoch": 7.29, + "learning_rate": 1.468321589998618e-05, + "loss": 0.0614, + "step": 23606 + }, + { + "epoch": 7.29, + "learning_rate": 1.4682774010628822e-05, + "loss": 0.062, + "step": 23607 + }, + { + "epoch": 7.29, + "learning_rate": 1.4682332109558993e-05, + "loss": 0.0631, + "step": 23608 + }, + { + "epoch": 7.29, + "learning_rate": 1.4681890196777802e-05, + "loss": 0.0636, + "step": 23609 + }, + { + "epoch": 7.29, + "learning_rate": 1.4681448272286343e-05, + "loss": 0.0665, + "step": 23610 + }, + { + "epoch": 7.29, + "learning_rate": 1.4681006336085733e-05, + "loss": 0.0705, + "step": 23611 + }, + { + "epoch": 7.29, + "learning_rate": 1.4680564388177068e-05, + "loss": 0.0583, + "step": 23612 + }, + { + "epoch": 7.29, + "learning_rate": 1.4680122428561458e-05, + "loss": 0.0658, + "step": 23613 + }, + { + "epoch": 7.29, + "learning_rate": 1.4679680457240013e-05, + "loss": 0.067, + "step": 23614 + }, + { + "epoch": 7.29, + "learning_rate": 1.4679238474213829e-05, + "loss": 0.059, + "step": 23615 + }, + { + "epoch": 7.29, + "learning_rate": 1.4678796479484021e-05, + "loss": 0.0746, + "step": 23616 + }, + { + "epoch": 7.29, + "learning_rate": 1.4678354473051686e-05, + "loss": 0.0768, + "step": 23617 + }, + { + "epoch": 7.29, + "learning_rate": 1.4677912454917933e-05, + "loss": 0.0723, + "step": 23618 + }, + { + "epoch": 7.29, + "learning_rate": 1.467747042508387e-05, + "loss": 0.0613, + "step": 23619 + }, + { + "epoch": 7.29, + "learning_rate": 1.4677028383550598e-05, + "loss": 0.0655, + "step": 23620 + }, + { + "epoch": 7.29, + "learning_rate": 1.4676586330319227e-05, + "loss": 0.0629, + "step": 23621 + }, + { + "epoch": 7.29, + "learning_rate": 1.4676144265390859e-05, + "loss": 0.0692, + "step": 23622 + }, + { + "epoch": 7.3, + "learning_rate": 1.4675702188766603e-05, + "loss": 0.065, + "step": 23623 + }, + { + "epoch": 7.3, + "learning_rate": 1.467526010044756e-05, + "loss": 0.067, + "step": 23624 + }, + { + "epoch": 7.3, + "learning_rate": 1.4674818000434843e-05, + "loss": 0.0635, + "step": 23625 + }, + { + "epoch": 7.3, + "learning_rate": 1.4674375888729551e-05, + "loss": 0.0583, + "step": 23626 + }, + { + "epoch": 7.3, + "learning_rate": 1.4673933765332793e-05, + "loss": 0.0644, + "step": 23627 + }, + { + "epoch": 7.3, + "learning_rate": 1.4673491630245674e-05, + "loss": 0.0626, + "step": 23628 + }, + { + "epoch": 7.3, + "learning_rate": 1.4673049483469299e-05, + "loss": 0.065, + "step": 23629 + }, + { + "epoch": 7.3, + "learning_rate": 1.4672607325004775e-05, + "loss": 0.0673, + "step": 23630 + }, + { + "epoch": 7.3, + "learning_rate": 1.4672165154853209e-05, + "loss": 0.0647, + "step": 23631 + }, + { + "epoch": 7.3, + "learning_rate": 1.4671722973015706e-05, + "loss": 0.0623, + "step": 23632 + }, + { + "epoch": 7.3, + "learning_rate": 1.467128077949337e-05, + "loss": 0.0606, + "step": 23633 + }, + { + "epoch": 7.3, + "learning_rate": 1.4670838574287309e-05, + "loss": 0.0626, + "step": 23634 + }, + { + "epoch": 7.3, + "learning_rate": 1.467039635739863e-05, + "loss": 0.0676, + "step": 23635 + }, + { + "epoch": 7.3, + "learning_rate": 1.4669954128828439e-05, + "loss": 0.0735, + "step": 23636 + }, + { + "epoch": 7.3, + "learning_rate": 1.466951188857784e-05, + "loss": 0.0622, + "step": 23637 + }, + { + "epoch": 7.3, + "learning_rate": 1.4669069636647939e-05, + "loss": 0.0595, + "step": 23638 + }, + { + "epoch": 7.3, + "learning_rate": 1.4668627373039845e-05, + "loss": 0.073, + "step": 23639 + }, + { + "epoch": 7.3, + "learning_rate": 1.4668185097754663e-05, + "loss": 0.0693, + "step": 23640 + }, + { + "epoch": 7.3, + "learning_rate": 1.4667742810793495e-05, + "loss": 0.0607, + "step": 23641 + }, + { + "epoch": 7.3, + "learning_rate": 1.4667300512157456e-05, + "loss": 0.0699, + "step": 23642 + }, + { + "epoch": 7.3, + "learning_rate": 1.4666858201847643e-05, + "loss": 0.0638, + "step": 23643 + }, + { + "epoch": 7.3, + "learning_rate": 1.4666415879865166e-05, + "loss": 0.0653, + "step": 23644 + }, + { + "epoch": 7.3, + "learning_rate": 1.4665973546211137e-05, + "loss": 0.0729, + "step": 23645 + }, + { + "epoch": 7.3, + "learning_rate": 1.4665531200886649e-05, + "loss": 0.0615, + "step": 23646 + }, + { + "epoch": 7.3, + "learning_rate": 1.4665088843892823e-05, + "loss": 0.068, + "step": 23647 + }, + { + "epoch": 7.3, + "learning_rate": 1.4664646475230757e-05, + "loss": 0.0687, + "step": 23648 + }, + { + "epoch": 7.3, + "learning_rate": 1.4664204094901558e-05, + "loss": 0.064, + "step": 23649 + }, + { + "epoch": 7.3, + "learning_rate": 1.4663761702906336e-05, + "loss": 0.0638, + "step": 23650 + }, + { + "epoch": 7.3, + "learning_rate": 1.4663319299246194e-05, + "loss": 0.0652, + "step": 23651 + }, + { + "epoch": 7.3, + "learning_rate": 1.4662876883922241e-05, + "loss": 0.0647, + "step": 23652 + }, + { + "epoch": 7.3, + "learning_rate": 1.4662434456935584e-05, + "loss": 0.0595, + "step": 23653 + }, + { + "epoch": 7.3, + "learning_rate": 1.4661992018287325e-05, + "loss": 0.0612, + "step": 23654 + }, + { + "epoch": 7.31, + "learning_rate": 1.4661549567978574e-05, + "loss": 0.0679, + "step": 23655 + }, + { + "epoch": 7.31, + "learning_rate": 1.4661107106010439e-05, + "loss": 0.063, + "step": 23656 + }, + { + "epoch": 7.31, + "learning_rate": 1.4660664632384026e-05, + "loss": 0.0758, + "step": 23657 + }, + { + "epoch": 7.31, + "learning_rate": 1.4660222147100435e-05, + "loss": 0.0694, + "step": 23658 + }, + { + "epoch": 7.31, + "learning_rate": 1.4659779650160783e-05, + "loss": 0.0642, + "step": 23659 + }, + { + "epoch": 7.31, + "learning_rate": 1.4659337141566172e-05, + "loss": 0.0665, + "step": 23660 + }, + { + "epoch": 7.31, + "learning_rate": 1.465889462131771e-05, + "loss": 0.0661, + "step": 23661 + }, + { + "epoch": 7.31, + "learning_rate": 1.46584520894165e-05, + "loss": 0.0696, + "step": 23662 + }, + { + "epoch": 7.31, + "learning_rate": 1.4658009545863651e-05, + "loss": 0.066, + "step": 23663 + }, + { + "epoch": 7.31, + "learning_rate": 1.4657566990660272e-05, + "loss": 0.0628, + "step": 23664 + }, + { + "epoch": 7.31, + "learning_rate": 1.4657124423807471e-05, + "loss": 0.0631, + "step": 23665 + }, + { + "epoch": 7.31, + "learning_rate": 1.4656681845306348e-05, + "loss": 0.0635, + "step": 23666 + }, + { + "epoch": 7.31, + "learning_rate": 1.4656239255158018e-05, + "loss": 0.062, + "step": 23667 + }, + { + "epoch": 7.31, + "learning_rate": 1.4655796653363585e-05, + "loss": 0.0669, + "step": 23668 + }, + { + "epoch": 7.31, + "learning_rate": 1.4655354039924152e-05, + "loss": 0.062, + "step": 23669 + }, + { + "epoch": 7.31, + "learning_rate": 1.4654911414840833e-05, + "loss": 0.0687, + "step": 23670 + }, + { + "epoch": 7.31, + "learning_rate": 1.465446877811473e-05, + "loss": 0.0633, + "step": 23671 + }, + { + "epoch": 7.31, + "learning_rate": 1.4654026129746948e-05, + "loss": 0.0663, + "step": 23672 + }, + { + "epoch": 7.31, + "learning_rate": 1.4653583469738604e-05, + "loss": 0.0607, + "step": 23673 + }, + { + "epoch": 7.31, + "learning_rate": 1.4653140798090795e-05, + "loss": 0.0638, + "step": 23674 + }, + { + "epoch": 7.31, + "learning_rate": 1.4652698114804634e-05, + "loss": 0.0614, + "step": 23675 + }, + { + "epoch": 7.31, + "learning_rate": 1.4652255419881226e-05, + "loss": 0.0621, + "step": 23676 + }, + { + "epoch": 7.31, + "learning_rate": 1.4651812713321673e-05, + "loss": 0.0658, + "step": 23677 + }, + { + "epoch": 7.31, + "learning_rate": 1.4651369995127095e-05, + "loss": 0.0619, + "step": 23678 + }, + { + "epoch": 7.31, + "learning_rate": 1.4650927265298594e-05, + "loss": 0.0654, + "step": 23679 + }, + { + "epoch": 7.31, + "learning_rate": 1.465048452383727e-05, + "loss": 0.0675, + "step": 23680 + }, + { + "epoch": 7.31, + "learning_rate": 1.465004177074424e-05, + "loss": 0.0617, + "step": 23681 + }, + { + "epoch": 7.31, + "learning_rate": 1.4649599006020605e-05, + "loss": 0.0562, + "step": 23682 + }, + { + "epoch": 7.31, + "learning_rate": 1.4649156229667474e-05, + "loss": 0.0619, + "step": 23683 + }, + { + "epoch": 7.31, + "learning_rate": 1.4648713441685955e-05, + "loss": 0.0639, + "step": 23684 + }, + { + "epoch": 7.31, + "learning_rate": 1.4648270642077159e-05, + "loss": 0.0649, + "step": 23685 + }, + { + "epoch": 7.31, + "learning_rate": 1.464782783084219e-05, + "loss": 0.065, + "step": 23686 + }, + { + "epoch": 7.32, + "learning_rate": 1.4647385007982153e-05, + "loss": 0.0634, + "step": 23687 + }, + { + "epoch": 7.32, + "learning_rate": 1.4646942173498162e-05, + "loss": 0.0664, + "step": 23688 + }, + { + "epoch": 7.32, + "learning_rate": 1.4646499327391319e-05, + "loss": 0.0643, + "step": 23689 + }, + { + "epoch": 7.32, + "learning_rate": 1.4646056469662732e-05, + "loss": 0.0691, + "step": 23690 + }, + { + "epoch": 7.32, + "learning_rate": 1.4645613600313515e-05, + "loss": 0.0652, + "step": 23691 + }, + { + "epoch": 7.32, + "learning_rate": 1.4645170719344766e-05, + "loss": 0.0654, + "step": 23692 + }, + { + "epoch": 7.32, + "learning_rate": 1.46447278267576e-05, + "loss": 0.0657, + "step": 23693 + }, + { + "epoch": 7.32, + "learning_rate": 1.4644284922553125e-05, + "loss": 0.0687, + "step": 23694 + }, + { + "epoch": 7.32, + "learning_rate": 1.4643842006732443e-05, + "loss": 0.0612, + "step": 23695 + }, + { + "epoch": 7.32, + "learning_rate": 1.4643399079296668e-05, + "loss": 0.0652, + "step": 23696 + }, + { + "epoch": 7.32, + "learning_rate": 1.4642956140246902e-05, + "loss": 0.0717, + "step": 23697 + }, + { + "epoch": 7.32, + "learning_rate": 1.4642513189584256e-05, + "loss": 0.068, + "step": 23698 + }, + { + "epoch": 7.32, + "learning_rate": 1.4642070227309841e-05, + "loss": 0.0612, + "step": 23699 + }, + { + "epoch": 7.32, + "learning_rate": 1.4641627253424758e-05, + "loss": 0.0629, + "step": 23700 + }, + { + "epoch": 7.32, + "learning_rate": 1.4641184267930122e-05, + "loss": 0.0679, + "step": 23701 + }, + { + "epoch": 7.32, + "learning_rate": 1.4640741270827037e-05, + "loss": 0.0697, + "step": 23702 + }, + { + "epoch": 7.32, + "learning_rate": 1.4640298262116608e-05, + "loss": 0.0689, + "step": 23703 + }, + { + "epoch": 7.32, + "learning_rate": 1.4639855241799951e-05, + "loss": 0.0719, + "step": 23704 + }, + { + "epoch": 7.32, + "learning_rate": 1.4639412209878168e-05, + "loss": 0.0671, + "step": 23705 + }, + { + "epoch": 7.32, + "learning_rate": 1.4638969166352368e-05, + "loss": 0.0666, + "step": 23706 + }, + { + "epoch": 7.32, + "learning_rate": 1.463852611122366e-05, + "loss": 0.0635, + "step": 23707 + }, + { + "epoch": 7.32, + "learning_rate": 1.4638083044493155e-05, + "loss": 0.0576, + "step": 23708 + }, + { + "epoch": 7.32, + "learning_rate": 1.4637639966161957e-05, + "loss": 0.0705, + "step": 23709 + }, + { + "epoch": 7.32, + "learning_rate": 1.4637196876231174e-05, + "loss": 0.0684, + "step": 23710 + }, + { + "epoch": 7.32, + "learning_rate": 1.4636753774701917e-05, + "loss": 0.0585, + "step": 23711 + }, + { + "epoch": 7.32, + "learning_rate": 1.4636310661575293e-05, + "loss": 0.0705, + "step": 23712 + }, + { + "epoch": 7.32, + "learning_rate": 1.463586753685241e-05, + "loss": 0.062, + "step": 23713 + }, + { + "epoch": 7.32, + "learning_rate": 1.4635424400534377e-05, + "loss": 0.0672, + "step": 23714 + }, + { + "epoch": 7.32, + "learning_rate": 1.4634981252622304e-05, + "loss": 0.0606, + "step": 23715 + }, + { + "epoch": 7.32, + "learning_rate": 1.4634538093117296e-05, + "loss": 0.07, + "step": 23716 + }, + { + "epoch": 7.32, + "learning_rate": 1.4634094922020464e-05, + "loss": 0.0726, + "step": 23717 + }, + { + "epoch": 7.32, + "learning_rate": 1.4633651739332912e-05, + "loss": 0.0658, + "step": 23718 + }, + { + "epoch": 7.32, + "learning_rate": 1.4633208545055757e-05, + "loss": 0.0664, + "step": 23719 + }, + { + "epoch": 7.33, + "learning_rate": 1.4632765339190096e-05, + "loss": 0.0668, + "step": 23720 + }, + { + "epoch": 7.33, + "learning_rate": 1.4632322121737048e-05, + "loss": 0.0659, + "step": 23721 + }, + { + "epoch": 7.33, + "learning_rate": 1.463187889269772e-05, + "loss": 0.0678, + "step": 23722 + }, + { + "epoch": 7.33, + "learning_rate": 1.4631435652073211e-05, + "loss": 0.0598, + "step": 23723 + }, + { + "epoch": 7.33, + "learning_rate": 1.4630992399864643e-05, + "loss": 0.0644, + "step": 23724 + }, + { + "epoch": 7.33, + "learning_rate": 1.4630549136073116e-05, + "loss": 0.0665, + "step": 23725 + }, + { + "epoch": 7.33, + "learning_rate": 1.4630105860699742e-05, + "loss": 0.0667, + "step": 23726 + }, + { + "epoch": 7.33, + "learning_rate": 1.4629662573745628e-05, + "loss": 0.0654, + "step": 23727 + }, + { + "epoch": 7.33, + "learning_rate": 1.4629219275211881e-05, + "loss": 0.0644, + "step": 23728 + }, + { + "epoch": 7.33, + "learning_rate": 1.4628775965099617e-05, + "loss": 0.0649, + "step": 23729 + }, + { + "epoch": 7.33, + "learning_rate": 1.4628332643409938e-05, + "loss": 0.0628, + "step": 23730 + }, + { + "epoch": 7.33, + "learning_rate": 1.4627889310143952e-05, + "loss": 0.0638, + "step": 23731 + }, + { + "epoch": 7.33, + "learning_rate": 1.4627445965302775e-05, + "loss": 0.0639, + "step": 23732 + }, + { + "epoch": 7.33, + "learning_rate": 1.4627002608887511e-05, + "loss": 0.0633, + "step": 23733 + }, + { + "epoch": 7.33, + "learning_rate": 1.4626559240899268e-05, + "loss": 0.0648, + "step": 23734 + }, + { + "epoch": 7.33, + "learning_rate": 1.4626115861339156e-05, + "loss": 0.0685, + "step": 23735 + }, + { + "epoch": 7.33, + "learning_rate": 1.4625672470208287e-05, + "loss": 0.0642, + "step": 23736 + }, + { + "epoch": 7.33, + "learning_rate": 1.4625229067507766e-05, + "loss": 0.0678, + "step": 23737 + }, + { + "epoch": 7.33, + "learning_rate": 1.4624785653238704e-05, + "loss": 0.0624, + "step": 23738 + }, + { + "epoch": 7.33, + "learning_rate": 1.4624342227402208e-05, + "loss": 0.0614, + "step": 23739 + }, + { + "epoch": 7.33, + "learning_rate": 1.4623898789999392e-05, + "loss": 0.0622, + "step": 23740 + }, + { + "epoch": 7.33, + "learning_rate": 1.4623455341031358e-05, + "loss": 0.0635, + "step": 23741 + }, + { + "epoch": 7.33, + "learning_rate": 1.4623011880499221e-05, + "loss": 0.0661, + "step": 23742 + }, + { + "epoch": 7.33, + "learning_rate": 1.4622568408404088e-05, + "loss": 0.0654, + "step": 23743 + }, + { + "epoch": 7.33, + "learning_rate": 1.4622124924747067e-05, + "loss": 0.0707, + "step": 23744 + }, + { + "epoch": 7.33, + "learning_rate": 1.4621681429529271e-05, + "loss": 0.0703, + "step": 23745 + }, + { + "epoch": 7.33, + "learning_rate": 1.4621237922751804e-05, + "loss": 0.0621, + "step": 23746 + }, + { + "epoch": 7.33, + "learning_rate": 1.4620794404415778e-05, + "loss": 0.0611, + "step": 23747 + }, + { + "epoch": 7.33, + "learning_rate": 1.4620350874522307e-05, + "loss": 0.0683, + "step": 23748 + }, + { + "epoch": 7.33, + "learning_rate": 1.4619907333072492e-05, + "loss": 0.0633, + "step": 23749 + }, + { + "epoch": 7.33, + "learning_rate": 1.4619463780067449e-05, + "loss": 0.0644, + "step": 23750 + }, + { + "epoch": 7.33, + "learning_rate": 1.461902021550828e-05, + "loss": 0.065, + "step": 23751 + }, + { + "epoch": 7.34, + "learning_rate": 1.46185766393961e-05, + "loss": 0.0702, + "step": 23752 + }, + { + "epoch": 7.34, + "learning_rate": 1.4618133051732022e-05, + "loss": 0.0593, + "step": 23753 + }, + { + "epoch": 7.34, + "learning_rate": 1.4617689452517146e-05, + "loss": 0.0661, + "step": 23754 + }, + { + "epoch": 7.34, + "learning_rate": 1.4617245841752587e-05, + "loss": 0.0643, + "step": 23755 + }, + { + "epoch": 7.34, + "learning_rate": 1.4616802219439456e-05, + "loss": 0.0682, + "step": 23756 + }, + { + "epoch": 7.34, + "learning_rate": 1.4616358585578858e-05, + "loss": 0.0663, + "step": 23757 + }, + { + "epoch": 7.34, + "learning_rate": 1.461591494017191e-05, + "loss": 0.062, + "step": 23758 + }, + { + "epoch": 7.34, + "learning_rate": 1.4615471283219711e-05, + "loss": 0.07, + "step": 23759 + }, + { + "epoch": 7.34, + "learning_rate": 1.461502761472338e-05, + "loss": 0.062, + "step": 23760 + }, + { + "epoch": 7.34, + "learning_rate": 1.4614583934684024e-05, + "loss": 0.0676, + "step": 23761 + }, + { + "epoch": 7.34, + "learning_rate": 1.4614140243102748e-05, + "loss": 0.0598, + "step": 23762 + }, + { + "epoch": 7.34, + "learning_rate": 1.461369653998067e-05, + "loss": 0.063, + "step": 23763 + }, + { + "epoch": 7.34, + "learning_rate": 1.4613252825318893e-05, + "loss": 0.0624, + "step": 23764 + }, + { + "epoch": 7.34, + "learning_rate": 1.461280909911853e-05, + "loss": 0.0707, + "step": 23765 + }, + { + "epoch": 7.34, + "learning_rate": 1.4612365361380691e-05, + "loss": 0.0694, + "step": 23766 + }, + { + "epoch": 7.34, + "learning_rate": 1.4611921612106483e-05, + "loss": 0.0644, + "step": 23767 + }, + { + "epoch": 7.34, + "learning_rate": 1.461147785129702e-05, + "loss": 0.0587, + "step": 23768 + }, + { + "epoch": 7.34, + "learning_rate": 1.4611034078953407e-05, + "loss": 0.062, + "step": 23769 + }, + { + "epoch": 7.34, + "learning_rate": 1.4610590295076761e-05, + "loss": 0.0624, + "step": 23770 + }, + { + "epoch": 7.34, + "learning_rate": 1.4610146499668183e-05, + "loss": 0.0628, + "step": 23771 + }, + { + "epoch": 7.34, + "learning_rate": 1.4609702692728791e-05, + "loss": 0.0609, + "step": 23772 + }, + { + "epoch": 7.34, + "learning_rate": 1.4609258874259692e-05, + "loss": 0.0603, + "step": 23773 + }, + { + "epoch": 7.34, + "learning_rate": 1.4608815044261992e-05, + "loss": 0.0641, + "step": 23774 + }, + { + "epoch": 7.34, + "learning_rate": 1.4608371202736809e-05, + "loss": 0.0638, + "step": 23775 + }, + { + "epoch": 7.34, + "learning_rate": 1.4607927349685247e-05, + "loss": 0.0704, + "step": 23776 + }, + { + "epoch": 7.34, + "learning_rate": 1.4607483485108417e-05, + "loss": 0.068, + "step": 23777 + }, + { + "epoch": 7.34, + "learning_rate": 1.4607039609007437e-05, + "loss": 0.0715, + "step": 23778 + }, + { + "epoch": 7.34, + "learning_rate": 1.4606595721383404e-05, + "loss": 0.072, + "step": 23779 + }, + { + "epoch": 7.34, + "learning_rate": 1.4606151822237435e-05, + "loss": 0.0675, + "step": 23780 + }, + { + "epoch": 7.34, + "learning_rate": 1.4605707911570646e-05, + "loss": 0.07, + "step": 23781 + }, + { + "epoch": 7.34, + "learning_rate": 1.4605263989384135e-05, + "loss": 0.0669, + "step": 23782 + }, + { + "epoch": 7.34, + "learning_rate": 1.4604820055679024e-05, + "loss": 0.0632, + "step": 23783 + }, + { + "epoch": 7.35, + "learning_rate": 1.4604376110456415e-05, + "loss": 0.0634, + "step": 23784 + }, + { + "epoch": 7.35, + "learning_rate": 1.4603932153717422e-05, + "loss": 0.0673, + "step": 23785 + }, + { + "epoch": 7.35, + "learning_rate": 1.4603488185463155e-05, + "loss": 0.0622, + "step": 23786 + }, + { + "epoch": 7.35, + "learning_rate": 1.4603044205694725e-05, + "loss": 0.0608, + "step": 23787 + }, + { + "epoch": 7.35, + "learning_rate": 1.4602600214413243e-05, + "loss": 0.0621, + "step": 23788 + }, + { + "epoch": 7.35, + "learning_rate": 1.4602156211619815e-05, + "loss": 0.0615, + "step": 23789 + }, + { + "epoch": 7.35, + "learning_rate": 1.4601712197315557e-05, + "loss": 0.0644, + "step": 23790 + }, + { + "epoch": 7.35, + "learning_rate": 1.4601268171501577e-05, + "loss": 0.0679, + "step": 23791 + }, + { + "epoch": 7.35, + "learning_rate": 1.4600824134178989e-05, + "loss": 0.0694, + "step": 23792 + }, + { + "epoch": 7.35, + "learning_rate": 1.4600380085348897e-05, + "loss": 0.0686, + "step": 23793 + }, + { + "epoch": 7.35, + "learning_rate": 1.4599936025012416e-05, + "loss": 0.0619, + "step": 23794 + }, + { + "epoch": 7.35, + "learning_rate": 1.4599491953170656e-05, + "loss": 0.0607, + "step": 23795 + }, + { + "epoch": 7.35, + "learning_rate": 1.4599047869824729e-05, + "loss": 0.0634, + "step": 23796 + }, + { + "epoch": 7.35, + "learning_rate": 1.4598603774975744e-05, + "loss": 0.0644, + "step": 23797 + }, + { + "epoch": 7.35, + "learning_rate": 1.4598159668624811e-05, + "loss": 0.0686, + "step": 23798 + }, + { + "epoch": 7.35, + "learning_rate": 1.4597715550773044e-05, + "loss": 0.0627, + "step": 23799 + }, + { + "epoch": 7.35, + "learning_rate": 1.459727142142155e-05, + "loss": 0.0696, + "step": 23800 + }, + { + "epoch": 7.35, + "learning_rate": 1.4596827280571444e-05, + "loss": 0.0616, + "step": 23801 + }, + { + "epoch": 7.35, + "learning_rate": 1.4596383128223832e-05, + "loss": 0.0623, + "step": 23802 + }, + { + "epoch": 7.35, + "learning_rate": 1.4595938964379827e-05, + "loss": 0.0676, + "step": 23803 + }, + { + "epoch": 7.35, + "learning_rate": 1.4595494789040545e-05, + "loss": 0.0597, + "step": 23804 + }, + { + "epoch": 7.35, + "learning_rate": 1.4595050602207088e-05, + "loss": 0.0692, + "step": 23805 + }, + { + "epoch": 7.35, + "learning_rate": 1.4594606403880573e-05, + "loss": 0.0691, + "step": 23806 + }, + { + "epoch": 7.35, + "learning_rate": 1.4594162194062107e-05, + "loss": 0.0694, + "step": 23807 + }, + { + "epoch": 7.35, + "learning_rate": 1.4593717972752805e-05, + "loss": 0.0719, + "step": 23808 + }, + { + "epoch": 7.35, + "learning_rate": 1.4593273739953779e-05, + "loss": 0.0682, + "step": 23809 + }, + { + "epoch": 7.35, + "learning_rate": 1.4592829495666135e-05, + "loss": 0.0629, + "step": 23810 + }, + { + "epoch": 7.35, + "learning_rate": 1.4592385239890988e-05, + "loss": 0.0612, + "step": 23811 + }, + { + "epoch": 7.35, + "learning_rate": 1.4591940972629449e-05, + "loss": 0.0657, + "step": 23812 + }, + { + "epoch": 7.35, + "learning_rate": 1.4591496693882622e-05, + "loss": 0.0744, + "step": 23813 + }, + { + "epoch": 7.35, + "learning_rate": 1.4591052403651634e-05, + "loss": 0.0614, + "step": 23814 + }, + { + "epoch": 7.35, + "learning_rate": 1.459060810193758e-05, + "loss": 0.0702, + "step": 23815 + }, + { + "epoch": 7.35, + "learning_rate": 1.4590163788741577e-05, + "loss": 0.0717, + "step": 23816 + }, + { + "epoch": 7.36, + "learning_rate": 1.4589719464064743e-05, + "loss": 0.0569, + "step": 23817 + }, + { + "epoch": 7.36, + "learning_rate": 1.4589275127908178e-05, + "loss": 0.0666, + "step": 23818 + }, + { + "epoch": 7.36, + "learning_rate": 1.4588830780273e-05, + "loss": 0.0694, + "step": 23819 + }, + { + "epoch": 7.36, + "learning_rate": 1.458838642116032e-05, + "loss": 0.0612, + "step": 23820 + }, + { + "epoch": 7.36, + "learning_rate": 1.458794205057125e-05, + "loss": 0.0641, + "step": 23821 + }, + { + "epoch": 7.36, + "learning_rate": 1.4587497668506899e-05, + "loss": 0.0761, + "step": 23822 + }, + { + "epoch": 7.36, + "learning_rate": 1.458705327496838e-05, + "loss": 0.0649, + "step": 23823 + }, + { + "epoch": 7.36, + "learning_rate": 1.4586608869956802e-05, + "loss": 0.0623, + "step": 23824 + }, + { + "epoch": 7.36, + "learning_rate": 1.4586164453473279e-05, + "loss": 0.0648, + "step": 23825 + }, + { + "epoch": 7.36, + "learning_rate": 1.4585720025518924e-05, + "loss": 0.0692, + "step": 23826 + }, + { + "epoch": 7.36, + "learning_rate": 1.4585275586094847e-05, + "loss": 0.0754, + "step": 23827 + }, + { + "epoch": 7.36, + "learning_rate": 1.4584831135202158e-05, + "loss": 0.0696, + "step": 23828 + }, + { + "epoch": 7.36, + "learning_rate": 1.458438667284197e-05, + "loss": 0.0654, + "step": 23829 + }, + { + "epoch": 7.36, + "learning_rate": 1.4583942199015398e-05, + "loss": 0.0674, + "step": 23830 + }, + { + "epoch": 7.36, + "learning_rate": 1.4583497713723546e-05, + "loss": 0.0636, + "step": 23831 + }, + { + "epoch": 7.36, + "learning_rate": 1.4583053216967536e-05, + "loss": 0.0598, + "step": 23832 + }, + { + "epoch": 7.36, + "learning_rate": 1.4582608708748468e-05, + "loss": 0.0648, + "step": 23833 + }, + { + "epoch": 7.36, + "learning_rate": 1.4582164189067463e-05, + "loss": 0.0613, + "step": 23834 + }, + { + "epoch": 7.36, + "learning_rate": 1.458171965792563e-05, + "loss": 0.0717, + "step": 23835 + }, + { + "epoch": 7.36, + "learning_rate": 1.4581275115324078e-05, + "loss": 0.0704, + "step": 23836 + }, + { + "epoch": 7.36, + "learning_rate": 1.4580830561263924e-05, + "loss": 0.0681, + "step": 23837 + }, + { + "epoch": 7.36, + "learning_rate": 1.4580385995746275e-05, + "loss": 0.0717, + "step": 23838 + }, + { + "epoch": 7.36, + "learning_rate": 1.4579941418772245e-05, + "loss": 0.0715, + "step": 23839 + }, + { + "epoch": 7.36, + "learning_rate": 1.457949683034295e-05, + "loss": 0.0673, + "step": 23840 + }, + { + "epoch": 7.36, + "learning_rate": 1.4579052230459492e-05, + "loss": 0.0667, + "step": 23841 + }, + { + "epoch": 7.36, + "learning_rate": 1.4578607619122994e-05, + "loss": 0.0637, + "step": 23842 + }, + { + "epoch": 7.36, + "learning_rate": 1.4578162996334564e-05, + "loss": 0.0631, + "step": 23843 + }, + { + "epoch": 7.36, + "learning_rate": 1.4577718362095308e-05, + "loss": 0.0706, + "step": 23844 + }, + { + "epoch": 7.36, + "learning_rate": 1.457727371640635e-05, + "loss": 0.0604, + "step": 23845 + }, + { + "epoch": 7.36, + "learning_rate": 1.4576829059268791e-05, + "loss": 0.069, + "step": 23846 + }, + { + "epoch": 7.36, + "learning_rate": 1.4576384390683748e-05, + "loss": 0.0642, + "step": 23847 + }, + { + "epoch": 7.36, + "learning_rate": 1.4575939710652336e-05, + "loss": 0.0662, + "step": 23848 + }, + { + "epoch": 7.37, + "learning_rate": 1.4575495019175663e-05, + "loss": 0.0756, + "step": 23849 + }, + { + "epoch": 7.37, + "learning_rate": 1.457505031625484e-05, + "loss": 0.0661, + "step": 23850 + }, + { + "epoch": 7.37, + "learning_rate": 1.4574605601890985e-05, + "loss": 0.0618, + "step": 23851 + }, + { + "epoch": 7.37, + "learning_rate": 1.4574160876085204e-05, + "loss": 0.069, + "step": 23852 + }, + { + "epoch": 7.37, + "learning_rate": 1.4573716138838613e-05, + "loss": 0.0753, + "step": 23853 + }, + { + "epoch": 7.37, + "learning_rate": 1.4573271390152326e-05, + "loss": 0.069, + "step": 23854 + }, + { + "epoch": 7.37, + "learning_rate": 1.4572826630027453e-05, + "loss": 0.068, + "step": 23855 + }, + { + "epoch": 7.37, + "learning_rate": 1.4572381858465103e-05, + "loss": 0.0659, + "step": 23856 + }, + { + "epoch": 7.37, + "learning_rate": 1.4571937075466395e-05, + "loss": 0.0625, + "step": 23857 + }, + { + "epoch": 7.37, + "learning_rate": 1.4571492281032438e-05, + "loss": 0.068, + "step": 23858 + }, + { + "epoch": 7.37, + "learning_rate": 1.4571047475164343e-05, + "loss": 0.0694, + "step": 23859 + }, + { + "epoch": 7.37, + "learning_rate": 1.4570602657863229e-05, + "loss": 0.0616, + "step": 23860 + }, + { + "epoch": 7.37, + "learning_rate": 1.45701578291302e-05, + "loss": 0.073, + "step": 23861 + }, + { + "epoch": 7.37, + "learning_rate": 1.4569712988966375e-05, + "loss": 0.0609, + "step": 23862 + }, + { + "epoch": 7.37, + "learning_rate": 1.4569268137372864e-05, + "loss": 0.0603, + "step": 23863 + }, + { + "epoch": 7.37, + "learning_rate": 1.4568823274350778e-05, + "loss": 0.0685, + "step": 23864 + }, + { + "epoch": 7.37, + "learning_rate": 1.4568378399901235e-05, + "loss": 0.0704, + "step": 23865 + }, + { + "epoch": 7.37, + "learning_rate": 1.4567933514025346e-05, + "loss": 0.0664, + "step": 23866 + }, + { + "epoch": 7.37, + "learning_rate": 1.4567488616724214e-05, + "loss": 0.0642, + "step": 23867 + }, + { + "epoch": 7.37, + "learning_rate": 1.4567043707998968e-05, + "loss": 0.0651, + "step": 23868 + }, + { + "epoch": 7.37, + "learning_rate": 1.456659878785071e-05, + "loss": 0.0715, + "step": 23869 + }, + { + "epoch": 7.37, + "learning_rate": 1.456615385628055e-05, + "loss": 0.0682, + "step": 23870 + }, + { + "epoch": 7.37, + "learning_rate": 1.4565708913289616e-05, + "loss": 0.0724, + "step": 23871 + }, + { + "epoch": 7.37, + "learning_rate": 1.4565263958879004e-05, + "loss": 0.07, + "step": 23872 + }, + { + "epoch": 7.37, + "learning_rate": 1.4564818993049839e-05, + "loss": 0.0723, + "step": 23873 + }, + { + "epoch": 7.37, + "learning_rate": 1.4564374015803227e-05, + "loss": 0.0659, + "step": 23874 + }, + { + "epoch": 7.37, + "learning_rate": 1.4563929027140283e-05, + "loss": 0.0669, + "step": 23875 + }, + { + "epoch": 7.37, + "learning_rate": 1.456348402706212e-05, + "loss": 0.069, + "step": 23876 + }, + { + "epoch": 7.37, + "learning_rate": 1.456303901556985e-05, + "loss": 0.0661, + "step": 23877 + }, + { + "epoch": 7.37, + "learning_rate": 1.4562593992664588e-05, + "loss": 0.0644, + "step": 23878 + }, + { + "epoch": 7.37, + "learning_rate": 1.4562148958347448e-05, + "loss": 0.0677, + "step": 23879 + }, + { + "epoch": 7.37, + "learning_rate": 1.456170391261954e-05, + "loss": 0.0699, + "step": 23880 + }, + { + "epoch": 7.37, + "learning_rate": 1.456125885548198e-05, + "loss": 0.0603, + "step": 23881 + }, + { + "epoch": 7.38, + "learning_rate": 1.4560813786935877e-05, + "loss": 0.066, + "step": 23882 + }, + { + "epoch": 7.38, + "learning_rate": 1.456036870698235e-05, + "loss": 0.0699, + "step": 23883 + }, + { + "epoch": 7.38, + "learning_rate": 1.4559923615622506e-05, + "loss": 0.0723, + "step": 23884 + }, + { + "epoch": 7.38, + "learning_rate": 1.4559478512857462e-05, + "loss": 0.0608, + "step": 23885 + }, + { + "epoch": 7.38, + "learning_rate": 1.4559033398688331e-05, + "loss": 0.0657, + "step": 23886 + }, + { + "epoch": 7.38, + "learning_rate": 1.4558588273116228e-05, + "loss": 0.0688, + "step": 23887 + }, + { + "epoch": 7.38, + "learning_rate": 1.4558143136142262e-05, + "loss": 0.0733, + "step": 23888 + }, + { + "epoch": 7.38, + "learning_rate": 1.4557697987767547e-05, + "loss": 0.0669, + "step": 23889 + }, + { + "epoch": 7.38, + "learning_rate": 1.4557252827993202e-05, + "loss": 0.0649, + "step": 23890 + }, + { + "epoch": 7.38, + "learning_rate": 1.4556807656820335e-05, + "loss": 0.0716, + "step": 23891 + }, + { + "epoch": 7.38, + "learning_rate": 1.455636247425006e-05, + "loss": 0.0698, + "step": 23892 + }, + { + "epoch": 7.38, + "learning_rate": 1.455591728028349e-05, + "loss": 0.072, + "step": 23893 + }, + { + "epoch": 7.38, + "learning_rate": 1.4555472074921746e-05, + "loss": 0.0704, + "step": 23894 + }, + { + "epoch": 7.38, + "learning_rate": 1.455502685816593e-05, + "loss": 0.0717, + "step": 23895 + }, + { + "epoch": 7.38, + "learning_rate": 1.4554581630017161e-05, + "loss": 0.0586, + "step": 23896 + }, + { + "epoch": 7.38, + "learning_rate": 1.4554136390476556e-05, + "loss": 0.0682, + "step": 23897 + }, + { + "epoch": 7.38, + "learning_rate": 1.4553691139545223e-05, + "loss": 0.0613, + "step": 23898 + }, + { + "epoch": 7.38, + "learning_rate": 1.4553245877224281e-05, + "loss": 0.0673, + "step": 23899 + }, + { + "epoch": 7.38, + "learning_rate": 1.4552800603514836e-05, + "loss": 0.0666, + "step": 23900 + }, + { + "epoch": 7.38, + "learning_rate": 1.4552355318418008e-05, + "loss": 0.0642, + "step": 23901 + }, + { + "epoch": 7.38, + "learning_rate": 1.455191002193491e-05, + "loss": 0.0748, + "step": 23902 + }, + { + "epoch": 7.38, + "learning_rate": 1.4551464714066655e-05, + "loss": 0.0651, + "step": 23903 + }, + { + "epoch": 7.38, + "learning_rate": 1.4551019394814354e-05, + "loss": 0.063, + "step": 23904 + }, + { + "epoch": 7.38, + "learning_rate": 1.4550574064179125e-05, + "loss": 0.0677, + "step": 23905 + }, + { + "epoch": 7.38, + "learning_rate": 1.455012872216208e-05, + "loss": 0.0611, + "step": 23906 + }, + { + "epoch": 7.38, + "learning_rate": 1.4549683368764336e-05, + "loss": 0.0697, + "step": 23907 + }, + { + "epoch": 7.38, + "learning_rate": 1.4549238003987001e-05, + "loss": 0.0685, + "step": 23908 + }, + { + "epoch": 7.38, + "learning_rate": 1.4548792627831193e-05, + "loss": 0.0583, + "step": 23909 + }, + { + "epoch": 7.38, + "learning_rate": 1.4548347240298024e-05, + "loss": 0.0717, + "step": 23910 + }, + { + "epoch": 7.38, + "learning_rate": 1.454790184138861e-05, + "loss": 0.0659, + "step": 23911 + }, + { + "epoch": 7.38, + "learning_rate": 1.4547456431104063e-05, + "loss": 0.063, + "step": 23912 + }, + { + "epoch": 7.38, + "learning_rate": 1.45470110094455e-05, + "loss": 0.0655, + "step": 23913 + }, + { + "epoch": 7.39, + "learning_rate": 1.4546565576414032e-05, + "loss": 0.0634, + "step": 23914 + }, + { + "epoch": 7.39, + "learning_rate": 1.4546120132010775e-05, + "loss": 0.0698, + "step": 23915 + }, + { + "epoch": 7.39, + "learning_rate": 1.454567467623684e-05, + "loss": 0.0556, + "step": 23916 + }, + { + "epoch": 7.39, + "learning_rate": 1.4545229209093348e-05, + "loss": 0.0628, + "step": 23917 + }, + { + "epoch": 7.39, + "learning_rate": 1.4544783730581404e-05, + "loss": 0.0658, + "step": 23918 + }, + { + "epoch": 7.39, + "learning_rate": 1.454433824070213e-05, + "loss": 0.0688, + "step": 23919 + }, + { + "epoch": 7.39, + "learning_rate": 1.4543892739456635e-05, + "loss": 0.0672, + "step": 23920 + }, + { + "epoch": 7.39, + "learning_rate": 1.4543447226846037e-05, + "loss": 0.0612, + "step": 23921 + }, + { + "epoch": 7.39, + "learning_rate": 1.4543001702871449e-05, + "loss": 0.0654, + "step": 23922 + }, + { + "epoch": 7.39, + "learning_rate": 1.4542556167533983e-05, + "loss": 0.0667, + "step": 23923 + }, + { + "epoch": 7.39, + "learning_rate": 1.4542110620834757e-05, + "loss": 0.0667, + "step": 23924 + }, + { + "epoch": 7.39, + "learning_rate": 1.4541665062774885e-05, + "loss": 0.0737, + "step": 23925 + }, + { + "epoch": 7.39, + "learning_rate": 1.4541219493355478e-05, + "loss": 0.0688, + "step": 23926 + }, + { + "epoch": 7.39, + "learning_rate": 1.4540773912577657e-05, + "loss": 0.0663, + "step": 23927 + }, + { + "epoch": 7.39, + "learning_rate": 1.4540328320442529e-05, + "loss": 0.0684, + "step": 23928 + }, + { + "epoch": 7.39, + "learning_rate": 1.453988271695121e-05, + "loss": 0.0606, + "step": 23929 + }, + { + "epoch": 7.39, + "learning_rate": 1.453943710210482e-05, + "loss": 0.0693, + "step": 23930 + }, + { + "epoch": 7.39, + "learning_rate": 1.453899147590447e-05, + "loss": 0.0667, + "step": 23931 + }, + { + "epoch": 7.39, + "learning_rate": 1.4538545838351272e-05, + "loss": 0.0636, + "step": 23932 + }, + { + "epoch": 7.39, + "learning_rate": 1.4538100189446343e-05, + "loss": 0.0728, + "step": 23933 + }, + { + "epoch": 7.39, + "learning_rate": 1.4537654529190799e-05, + "loss": 0.061, + "step": 23934 + }, + { + "epoch": 7.39, + "learning_rate": 1.4537208857585752e-05, + "loss": 0.0699, + "step": 23935 + }, + { + "epoch": 7.39, + "learning_rate": 1.453676317463232e-05, + "loss": 0.0642, + "step": 23936 + }, + { + "epoch": 7.39, + "learning_rate": 1.4536317480331615e-05, + "loss": 0.0813, + "step": 23937 + }, + { + "epoch": 7.39, + "learning_rate": 1.4535871774684753e-05, + "loss": 0.0699, + "step": 23938 + }, + { + "epoch": 7.39, + "learning_rate": 1.4535426057692848e-05, + "loss": 0.0658, + "step": 23939 + }, + { + "epoch": 7.39, + "learning_rate": 1.4534980329357014e-05, + "loss": 0.0671, + "step": 23940 + }, + { + "epoch": 7.39, + "learning_rate": 1.4534534589678369e-05, + "loss": 0.0612, + "step": 23941 + }, + { + "epoch": 7.39, + "learning_rate": 1.4534088838658025e-05, + "loss": 0.0675, + "step": 23942 + }, + { + "epoch": 7.39, + "learning_rate": 1.4533643076297098e-05, + "loss": 0.0633, + "step": 23943 + }, + { + "epoch": 7.39, + "learning_rate": 1.4533197302596701e-05, + "loss": 0.0703, + "step": 23944 + }, + { + "epoch": 7.39, + "learning_rate": 1.4532751517557953e-05, + "loss": 0.0724, + "step": 23945 + }, + { + "epoch": 7.4, + "learning_rate": 1.4532305721181968e-05, + "loss": 0.0668, + "step": 23946 + }, + { + "epoch": 7.4, + "learning_rate": 1.4531859913469856e-05, + "loss": 0.0632, + "step": 23947 + }, + { + "epoch": 7.4, + "learning_rate": 1.453141409442274e-05, + "loss": 0.0617, + "step": 23948 + }, + { + "epoch": 7.4, + "learning_rate": 1.4530968264041728e-05, + "loss": 0.0707, + "step": 23949 + }, + { + "epoch": 7.4, + "learning_rate": 1.453052242232794e-05, + "loss": 0.0652, + "step": 23950 + }, + { + "epoch": 7.4, + "learning_rate": 1.4530076569282488e-05, + "loss": 0.07, + "step": 23951 + }, + { + "epoch": 7.4, + "learning_rate": 1.4529630704906486e-05, + "loss": 0.062, + "step": 23952 + }, + { + "epoch": 7.4, + "learning_rate": 1.4529184829201055e-05, + "loss": 0.0736, + "step": 23953 + }, + { + "epoch": 7.4, + "learning_rate": 1.4528738942167305e-05, + "loss": 0.0676, + "step": 23954 + }, + { + "epoch": 7.4, + "learning_rate": 1.4528293043806352e-05, + "loss": 0.0628, + "step": 23955 + }, + { + "epoch": 7.4, + "learning_rate": 1.4527847134119316e-05, + "loss": 0.0633, + "step": 23956 + }, + { + "epoch": 7.4, + "learning_rate": 1.4527401213107303e-05, + "loss": 0.0713, + "step": 23957 + }, + { + "epoch": 7.4, + "learning_rate": 1.4526955280771437e-05, + "loss": 0.0687, + "step": 23958 + }, + { + "epoch": 7.4, + "learning_rate": 1.452650933711283e-05, + "loss": 0.0664, + "step": 23959 + }, + { + "epoch": 7.4, + "learning_rate": 1.4526063382132595e-05, + "loss": 0.0706, + "step": 23960 + }, + { + "epoch": 7.4, + "learning_rate": 1.4525617415831854e-05, + "loss": 0.0691, + "step": 23961 + }, + { + "epoch": 7.4, + "learning_rate": 1.4525171438211718e-05, + "loss": 0.0632, + "step": 23962 + }, + { + "epoch": 7.4, + "learning_rate": 1.4524725449273302e-05, + "loss": 0.0705, + "step": 23963 + }, + { + "epoch": 7.4, + "learning_rate": 1.4524279449017722e-05, + "loss": 0.0675, + "step": 23964 + }, + { + "epoch": 7.4, + "learning_rate": 1.4523833437446093e-05, + "loss": 0.0671, + "step": 23965 + }, + { + "epoch": 7.4, + "learning_rate": 1.4523387414559534e-05, + "loss": 0.0673, + "step": 23966 + }, + { + "epoch": 7.4, + "learning_rate": 1.4522941380359154e-05, + "loss": 0.069, + "step": 23967 + }, + { + "epoch": 7.4, + "learning_rate": 1.4522495334846076e-05, + "loss": 0.0725, + "step": 23968 + }, + { + "epoch": 7.4, + "learning_rate": 1.452204927802141e-05, + "loss": 0.0605, + "step": 23969 + }, + { + "epoch": 7.4, + "learning_rate": 1.4521603209886277e-05, + "loss": 0.0675, + "step": 23970 + }, + { + "epoch": 7.4, + "learning_rate": 1.452115713044179e-05, + "loss": 0.0666, + "step": 23971 + }, + { + "epoch": 7.4, + "learning_rate": 1.4520711039689062e-05, + "loss": 0.0678, + "step": 23972 + }, + { + "epoch": 7.4, + "learning_rate": 1.452026493762921e-05, + "loss": 0.0664, + "step": 23973 + }, + { + "epoch": 7.4, + "learning_rate": 1.4519818824263352e-05, + "loss": 0.0642, + "step": 23974 + }, + { + "epoch": 7.4, + "learning_rate": 1.4519372699592604e-05, + "loss": 0.0675, + "step": 23975 + }, + { + "epoch": 7.4, + "learning_rate": 1.4518926563618083e-05, + "loss": 0.0637, + "step": 23976 + }, + { + "epoch": 7.4, + "learning_rate": 1.4518480416340897e-05, + "loss": 0.0675, + "step": 23977 + }, + { + "epoch": 7.4, + "learning_rate": 1.451803425776217e-05, + "loss": 0.0646, + "step": 23978 + }, + { + "epoch": 7.41, + "learning_rate": 1.4517588087883016e-05, + "loss": 0.0644, + "step": 23979 + }, + { + "epoch": 7.41, + "learning_rate": 1.4517141906704549e-05, + "loss": 0.0685, + "step": 23980 + }, + { + "epoch": 7.41, + "learning_rate": 1.4516695714227887e-05, + "loss": 0.0672, + "step": 23981 + }, + { + "epoch": 7.41, + "learning_rate": 1.4516249510454145e-05, + "loss": 0.0597, + "step": 23982 + }, + { + "epoch": 7.41, + "learning_rate": 1.4515803295384437e-05, + "loss": 0.0632, + "step": 23983 + }, + { + "epoch": 7.41, + "learning_rate": 1.4515357069019886e-05, + "loss": 0.059, + "step": 23984 + }, + { + "epoch": 7.41, + "learning_rate": 1.4514910831361602e-05, + "loss": 0.0647, + "step": 23985 + }, + { + "epoch": 7.41, + "learning_rate": 1.45144645824107e-05, + "loss": 0.0644, + "step": 23986 + }, + { + "epoch": 7.41, + "learning_rate": 1.45140183221683e-05, + "loss": 0.0684, + "step": 23987 + }, + { + "epoch": 7.41, + "learning_rate": 1.4513572050635514e-05, + "loss": 0.0664, + "step": 23988 + }, + { + "epoch": 7.41, + "learning_rate": 1.4513125767813468e-05, + "loss": 0.0704, + "step": 23989 + }, + { + "epoch": 7.41, + "learning_rate": 1.4512679473703266e-05, + "loss": 0.0701, + "step": 23990 + }, + { + "epoch": 7.41, + "learning_rate": 1.4512233168306031e-05, + "loss": 0.0614, + "step": 23991 + }, + { + "epoch": 7.41, + "learning_rate": 1.4511786851622877e-05, + "loss": 0.0731, + "step": 23992 + }, + { + "epoch": 7.41, + "learning_rate": 1.4511340523654922e-05, + "loss": 0.0682, + "step": 23993 + }, + { + "epoch": 7.41, + "learning_rate": 1.4510894184403281e-05, + "loss": 0.0647, + "step": 23994 + }, + { + "epoch": 7.41, + "learning_rate": 1.4510447833869072e-05, + "loss": 0.0654, + "step": 23995 + }, + { + "epoch": 7.41, + "learning_rate": 1.451000147205341e-05, + "loss": 0.0661, + "step": 23996 + }, + { + "epoch": 7.41, + "learning_rate": 1.450955509895741e-05, + "loss": 0.0642, + "step": 23997 + }, + { + "epoch": 7.41, + "learning_rate": 1.4509108714582193e-05, + "loss": 0.067, + "step": 23998 + }, + { + "epoch": 7.41, + "learning_rate": 1.4508662318928872e-05, + "loss": 0.0645, + "step": 23999 + }, + { + "epoch": 7.41, + "learning_rate": 1.4508215911998562e-05, + "loss": 0.0656, + "step": 24000 + }, + { + "epoch": 7.41, + "learning_rate": 1.4507769493792384e-05, + "loss": 0.065, + "step": 24001 + }, + { + "epoch": 7.41, + "learning_rate": 1.4507323064311453e-05, + "loss": 0.0618, + "step": 24002 + }, + { + "epoch": 7.41, + "learning_rate": 1.4506876623556883e-05, + "loss": 0.0682, + "step": 24003 + }, + { + "epoch": 7.41, + "learning_rate": 1.450643017152979e-05, + "loss": 0.07, + "step": 24004 + }, + { + "epoch": 7.41, + "learning_rate": 1.45059837082313e-05, + "loss": 0.0709, + "step": 24005 + }, + { + "epoch": 7.41, + "learning_rate": 1.4505537233662517e-05, + "loss": 0.0663, + "step": 24006 + }, + { + "epoch": 7.41, + "learning_rate": 1.4505090747824568e-05, + "loss": 0.0677, + "step": 24007 + }, + { + "epoch": 7.41, + "learning_rate": 1.4504644250718563e-05, + "loss": 0.0696, + "step": 24008 + }, + { + "epoch": 7.41, + "learning_rate": 1.450419774234562e-05, + "loss": 0.0766, + "step": 24009 + }, + { + "epoch": 7.41, + "learning_rate": 1.4503751222706859e-05, + "loss": 0.0645, + "step": 24010 + }, + { + "epoch": 7.42, + "learning_rate": 1.4503304691803392e-05, + "loss": 0.0682, + "step": 24011 + }, + { + "epoch": 7.42, + "learning_rate": 1.4502858149636342e-05, + "loss": 0.0603, + "step": 24012 + }, + { + "epoch": 7.42, + "learning_rate": 1.4502411596206822e-05, + "loss": 0.0733, + "step": 24013 + }, + { + "epoch": 7.42, + "learning_rate": 1.4501965031515948e-05, + "loss": 0.068, + "step": 24014 + }, + { + "epoch": 7.42, + "learning_rate": 1.450151845556484e-05, + "loss": 0.0691, + "step": 24015 + }, + { + "epoch": 7.42, + "learning_rate": 1.4501071868354613e-05, + "loss": 0.0741, + "step": 24016 + }, + { + "epoch": 7.42, + "learning_rate": 1.450062526988638e-05, + "loss": 0.0619, + "step": 24017 + }, + { + "epoch": 7.42, + "learning_rate": 1.4500178660161269e-05, + "loss": 0.0657, + "step": 24018 + }, + { + "epoch": 7.42, + "learning_rate": 1.4499732039180385e-05, + "loss": 0.0594, + "step": 24019 + }, + { + "epoch": 7.42, + "learning_rate": 1.4499285406944854e-05, + "loss": 0.068, + "step": 24020 + }, + { + "epoch": 7.42, + "learning_rate": 1.449883876345579e-05, + "loss": 0.0701, + "step": 24021 + }, + { + "epoch": 7.42, + "learning_rate": 1.4498392108714307e-05, + "loss": 0.0651, + "step": 24022 + }, + { + "epoch": 7.42, + "learning_rate": 1.4497945442721526e-05, + "loss": 0.073, + "step": 24023 + }, + { + "epoch": 7.42, + "learning_rate": 1.4497498765478564e-05, + "loss": 0.0717, + "step": 24024 + }, + { + "epoch": 7.42, + "learning_rate": 1.4497052076986536e-05, + "loss": 0.0702, + "step": 24025 + }, + { + "epoch": 7.42, + "learning_rate": 1.449660537724656e-05, + "loss": 0.0678, + "step": 24026 + }, + { + "epoch": 7.42, + "learning_rate": 1.4496158666259754e-05, + "loss": 0.0787, + "step": 24027 + }, + { + "epoch": 7.42, + "learning_rate": 1.4495711944027235e-05, + "loss": 0.0686, + "step": 24028 + }, + { + "epoch": 7.42, + "learning_rate": 1.4495265210550123e-05, + "loss": 0.0651, + "step": 24029 + }, + { + "epoch": 7.42, + "learning_rate": 1.4494818465829532e-05, + "loss": 0.069, + "step": 24030 + }, + { + "epoch": 7.42, + "learning_rate": 1.4494371709866577e-05, + "loss": 0.0756, + "step": 24031 + }, + { + "epoch": 7.42, + "learning_rate": 1.449392494266238e-05, + "loss": 0.0618, + "step": 24032 + }, + { + "epoch": 7.42, + "learning_rate": 1.4493478164218063e-05, + "loss": 0.0623, + "step": 24033 + }, + { + "epoch": 7.42, + "learning_rate": 1.449303137453473e-05, + "loss": 0.0625, + "step": 24034 + }, + { + "epoch": 7.42, + "learning_rate": 1.449258457361351e-05, + "loss": 0.0665, + "step": 24035 + }, + { + "epoch": 7.42, + "learning_rate": 1.4492137761455514e-05, + "loss": 0.0652, + "step": 24036 + }, + { + "epoch": 7.42, + "learning_rate": 1.4491690938061862e-05, + "loss": 0.0669, + "step": 24037 + }, + { + "epoch": 7.42, + "learning_rate": 1.4491244103433675e-05, + "loss": 0.0714, + "step": 24038 + }, + { + "epoch": 7.42, + "learning_rate": 1.4490797257572062e-05, + "loss": 0.0643, + "step": 24039 + }, + { + "epoch": 7.42, + "learning_rate": 1.4490350400478152e-05, + "loss": 0.0672, + "step": 24040 + }, + { + "epoch": 7.42, + "learning_rate": 1.4489903532153053e-05, + "loss": 0.0682, + "step": 24041 + }, + { + "epoch": 7.42, + "learning_rate": 1.4489456652597886e-05, + "loss": 0.0642, + "step": 24042 + }, + { + "epoch": 7.43, + "learning_rate": 1.4489009761813773e-05, + "loss": 0.0784, + "step": 24043 + }, + { + "epoch": 7.43, + "learning_rate": 1.4488562859801825e-05, + "loss": 0.0734, + "step": 24044 + }, + { + "epoch": 7.43, + "learning_rate": 1.4488115946563165e-05, + "loss": 0.075, + "step": 24045 + }, + { + "epoch": 7.43, + "learning_rate": 1.4487669022098905e-05, + "loss": 0.0665, + "step": 24046 + }, + { + "epoch": 7.43, + "learning_rate": 1.4487222086410167e-05, + "loss": 0.0678, + "step": 24047 + }, + { + "epoch": 7.43, + "learning_rate": 1.4486775139498068e-05, + "loss": 0.0748, + "step": 24048 + }, + { + "epoch": 7.43, + "learning_rate": 1.4486328181363729e-05, + "loss": 0.0657, + "step": 24049 + }, + { + "epoch": 7.43, + "learning_rate": 1.4485881212008262e-05, + "loss": 0.0602, + "step": 24050 + }, + { + "epoch": 7.43, + "learning_rate": 1.448543423143279e-05, + "loss": 0.0634, + "step": 24051 + }, + { + "epoch": 7.43, + "learning_rate": 1.4484987239638427e-05, + "loss": 0.0636, + "step": 24052 + }, + { + "epoch": 7.43, + "learning_rate": 1.4484540236626292e-05, + "loss": 0.0656, + "step": 24053 + }, + { + "epoch": 7.43, + "learning_rate": 1.4484093222397506e-05, + "loss": 0.0615, + "step": 24054 + }, + { + "epoch": 7.43, + "learning_rate": 1.4483646196953186e-05, + "loss": 0.0641, + "step": 24055 + }, + { + "epoch": 7.43, + "learning_rate": 1.4483199160294446e-05, + "loss": 0.0592, + "step": 24056 + }, + { + "epoch": 7.43, + "learning_rate": 1.4482752112422409e-05, + "loss": 0.0695, + "step": 24057 + }, + { + "epoch": 7.43, + "learning_rate": 1.448230505333819e-05, + "loss": 0.0679, + "step": 24058 + }, + { + "epoch": 7.43, + "learning_rate": 1.4481857983042911e-05, + "loss": 0.0573, + "step": 24059 + }, + { + "epoch": 7.43, + "learning_rate": 1.4481410901537687e-05, + "loss": 0.0637, + "step": 24060 + }, + { + "epoch": 7.43, + "learning_rate": 1.4480963808823636e-05, + "loss": 0.0679, + "step": 24061 + }, + { + "epoch": 7.43, + "learning_rate": 1.4480516704901878e-05, + "loss": 0.069, + "step": 24062 + }, + { + "epoch": 7.43, + "learning_rate": 1.448006958977353e-05, + "loss": 0.0605, + "step": 24063 + }, + { + "epoch": 7.43, + "learning_rate": 1.4479622463439711e-05, + "loss": 0.0647, + "step": 24064 + }, + { + "epoch": 7.43, + "learning_rate": 1.4479175325901537e-05, + "loss": 0.0669, + "step": 24065 + }, + { + "epoch": 7.43, + "learning_rate": 1.4478728177160135e-05, + "loss": 0.0637, + "step": 24066 + }, + { + "epoch": 7.43, + "learning_rate": 1.4478281017216612e-05, + "loss": 0.0623, + "step": 24067 + }, + { + "epoch": 7.43, + "learning_rate": 1.4477833846072089e-05, + "loss": 0.069, + "step": 24068 + }, + { + "epoch": 7.43, + "learning_rate": 1.4477386663727692e-05, + "loss": 0.0662, + "step": 24069 + }, + { + "epoch": 7.43, + "learning_rate": 1.447693947018453e-05, + "loss": 0.0743, + "step": 24070 + }, + { + "epoch": 7.43, + "learning_rate": 1.4476492265443731e-05, + "loss": 0.0635, + "step": 24071 + }, + { + "epoch": 7.43, + "learning_rate": 1.4476045049506406e-05, + "loss": 0.0668, + "step": 24072 + }, + { + "epoch": 7.43, + "learning_rate": 1.4475597822373673e-05, + "loss": 0.0663, + "step": 24073 + }, + { + "epoch": 7.43, + "learning_rate": 1.4475150584046657e-05, + "loss": 0.0754, + "step": 24074 + }, + { + "epoch": 7.43, + "learning_rate": 1.4474703334526473e-05, + "loss": 0.0649, + "step": 24075 + }, + { + "epoch": 7.44, + "learning_rate": 1.4474256073814238e-05, + "loss": 0.0709, + "step": 24076 + }, + { + "epoch": 7.44, + "learning_rate": 1.4473808801911074e-05, + "loss": 0.0682, + "step": 24077 + }, + { + "epoch": 7.44, + "learning_rate": 1.4473361518818098e-05, + "loss": 0.0731, + "step": 24078 + }, + { + "epoch": 7.44, + "learning_rate": 1.4472914224536427e-05, + "loss": 0.0717, + "step": 24079 + }, + { + "epoch": 7.44, + "learning_rate": 1.4472466919067185e-05, + "loss": 0.0623, + "step": 24080 + }, + { + "epoch": 7.44, + "learning_rate": 1.4472019602411487e-05, + "loss": 0.0696, + "step": 24081 + }, + { + "epoch": 7.44, + "learning_rate": 1.4471572274570452e-05, + "loss": 0.0634, + "step": 24082 + }, + { + "epoch": 7.44, + "learning_rate": 1.4471124935545195e-05, + "loss": 0.0728, + "step": 24083 + }, + { + "epoch": 7.44, + "learning_rate": 1.4470677585336845e-05, + "loss": 0.0696, + "step": 24084 + }, + { + "epoch": 7.44, + "learning_rate": 1.447023022394651e-05, + "loss": 0.0685, + "step": 24085 + }, + { + "epoch": 7.44, + "learning_rate": 1.4469782851375318e-05, + "loss": 0.0653, + "step": 24086 + }, + { + "epoch": 7.44, + "learning_rate": 1.446933546762438e-05, + "loss": 0.063, + "step": 24087 + }, + { + "epoch": 7.44, + "learning_rate": 1.4468888072694822e-05, + "loss": 0.0667, + "step": 24088 + }, + { + "epoch": 7.44, + "learning_rate": 1.4468440666587761e-05, + "loss": 0.07, + "step": 24089 + }, + { + "epoch": 7.44, + "learning_rate": 1.446799324930431e-05, + "loss": 0.0677, + "step": 24090 + }, + { + "epoch": 7.44, + "learning_rate": 1.4467545820845597e-05, + "loss": 0.0707, + "step": 24091 + }, + { + "epoch": 7.44, + "learning_rate": 1.4467098381212736e-05, + "loss": 0.068, + "step": 24092 + }, + { + "epoch": 7.44, + "learning_rate": 1.4466650930406847e-05, + "loss": 0.067, + "step": 24093 + }, + { + "epoch": 7.44, + "learning_rate": 1.446620346842905e-05, + "loss": 0.0651, + "step": 24094 + }, + { + "epoch": 7.44, + "learning_rate": 1.4465755995280464e-05, + "loss": 0.067, + "step": 24095 + }, + { + "epoch": 7.44, + "learning_rate": 1.4465308510962204e-05, + "loss": 0.0646, + "step": 24096 + }, + { + "epoch": 7.44, + "learning_rate": 1.4464861015475398e-05, + "loss": 0.0638, + "step": 24097 + }, + { + "epoch": 7.44, + "learning_rate": 1.4464413508821157e-05, + "loss": 0.0659, + "step": 24098 + }, + { + "epoch": 7.44, + "learning_rate": 1.4463965991000603e-05, + "loss": 0.0739, + "step": 24099 + }, + { + "epoch": 7.44, + "learning_rate": 1.4463518462014859e-05, + "loss": 0.0676, + "step": 24100 + }, + { + "epoch": 7.44, + "learning_rate": 1.4463070921865039e-05, + "loss": 0.0698, + "step": 24101 + }, + { + "epoch": 7.44, + "learning_rate": 1.4462623370552266e-05, + "loss": 0.0721, + "step": 24102 + }, + { + "epoch": 7.44, + "learning_rate": 1.4462175808077657e-05, + "loss": 0.0623, + "step": 24103 + }, + { + "epoch": 7.44, + "learning_rate": 1.4461728234442332e-05, + "loss": 0.0664, + "step": 24104 + }, + { + "epoch": 7.44, + "learning_rate": 1.4461280649647411e-05, + "loss": 0.0594, + "step": 24105 + }, + { + "epoch": 7.44, + "learning_rate": 1.4460833053694014e-05, + "loss": 0.0708, + "step": 24106 + }, + { + "epoch": 7.44, + "learning_rate": 1.446038544658326e-05, + "loss": 0.0671, + "step": 24107 + }, + { + "epoch": 7.45, + "learning_rate": 1.4459937828316268e-05, + "loss": 0.0644, + "step": 24108 + }, + { + "epoch": 7.45, + "learning_rate": 1.445949019889416e-05, + "loss": 0.0672, + "step": 24109 + }, + { + "epoch": 7.45, + "learning_rate": 1.4459042558318052e-05, + "loss": 0.0721, + "step": 24110 + }, + { + "epoch": 7.45, + "learning_rate": 1.4458594906589065e-05, + "loss": 0.0665, + "step": 24111 + }, + { + "epoch": 7.45, + "learning_rate": 1.4458147243708318e-05, + "loss": 0.0719, + "step": 24112 + }, + { + "epoch": 7.45, + "learning_rate": 1.4457699569676934e-05, + "loss": 0.0627, + "step": 24113 + }, + { + "epoch": 7.45, + "learning_rate": 1.4457251884496031e-05, + "loss": 0.0647, + "step": 24114 + }, + { + "epoch": 7.45, + "learning_rate": 1.4456804188166727e-05, + "loss": 0.0635, + "step": 24115 + }, + { + "epoch": 7.45, + "learning_rate": 1.445635648069014e-05, + "loss": 0.0698, + "step": 24116 + }, + { + "epoch": 7.45, + "learning_rate": 1.4455908762067394e-05, + "loss": 0.0696, + "step": 24117 + }, + { + "epoch": 7.45, + "learning_rate": 1.445546103229961e-05, + "loss": 0.0697, + "step": 24118 + }, + { + "epoch": 7.45, + "learning_rate": 1.4455013291387903e-05, + "loss": 0.0715, + "step": 24119 + }, + { + "epoch": 7.45, + "learning_rate": 1.4454565539333399e-05, + "loss": 0.068, + "step": 24120 + }, + { + "epoch": 7.45, + "learning_rate": 1.4454117776137207e-05, + "loss": 0.0716, + "step": 24121 + }, + { + "epoch": 7.45, + "learning_rate": 1.445367000180046e-05, + "loss": 0.0708, + "step": 24122 + }, + { + "epoch": 7.45, + "learning_rate": 1.4453222216324272e-05, + "loss": 0.0613, + "step": 24123 + }, + { + "epoch": 7.45, + "learning_rate": 1.4452774419709759e-05, + "loss": 0.0594, + "step": 24124 + }, + { + "epoch": 7.45, + "learning_rate": 1.4452326611958048e-05, + "loss": 0.0675, + "step": 24125 + }, + { + "epoch": 7.45, + "learning_rate": 1.4451878793070255e-05, + "loss": 0.0754, + "step": 24126 + }, + { + "epoch": 7.45, + "learning_rate": 1.44514309630475e-05, + "loss": 0.0645, + "step": 24127 + }, + { + "epoch": 7.45, + "learning_rate": 1.4450983121890907e-05, + "loss": 0.0614, + "step": 24128 + }, + { + "epoch": 7.45, + "learning_rate": 1.4450535269601594e-05, + "loss": 0.0594, + "step": 24129 + }, + { + "epoch": 7.45, + "learning_rate": 1.4450087406180677e-05, + "loss": 0.0665, + "step": 24130 + }, + { + "epoch": 7.45, + "learning_rate": 1.4449639531629282e-05, + "loss": 0.0726, + "step": 24131 + }, + { + "epoch": 7.45, + "learning_rate": 1.4449191645948526e-05, + "loss": 0.0682, + "step": 24132 + }, + { + "epoch": 7.45, + "learning_rate": 1.444874374913953e-05, + "loss": 0.0702, + "step": 24133 + }, + { + "epoch": 7.45, + "learning_rate": 1.4448295841203414e-05, + "loss": 0.0623, + "step": 24134 + }, + { + "epoch": 7.45, + "learning_rate": 1.4447847922141301e-05, + "loss": 0.0716, + "step": 24135 + }, + { + "epoch": 7.45, + "learning_rate": 1.4447399991954307e-05, + "loss": 0.0602, + "step": 24136 + }, + { + "epoch": 7.45, + "learning_rate": 1.4446952050643557e-05, + "loss": 0.07, + "step": 24137 + }, + { + "epoch": 7.45, + "learning_rate": 1.4446504098210166e-05, + "loss": 0.0739, + "step": 24138 + }, + { + "epoch": 7.45, + "learning_rate": 1.444605613465526e-05, + "loss": 0.0706, + "step": 24139 + }, + { + "epoch": 7.45, + "learning_rate": 1.4445608159979956e-05, + "loss": 0.0721, + "step": 24140 + }, + { + "epoch": 7.46, + "learning_rate": 1.4445160174185372e-05, + "loss": 0.0724, + "step": 24141 + }, + { + "epoch": 7.46, + "learning_rate": 1.4444712177272636e-05, + "loss": 0.0643, + "step": 24142 + }, + { + "epoch": 7.46, + "learning_rate": 1.4444264169242861e-05, + "loss": 0.0601, + "step": 24143 + }, + { + "epoch": 7.46, + "learning_rate": 1.4443816150097172e-05, + "loss": 0.0729, + "step": 24144 + }, + { + "epoch": 7.46, + "learning_rate": 1.4443368119836687e-05, + "loss": 0.0673, + "step": 24145 + }, + { + "epoch": 7.46, + "learning_rate": 1.4442920078462532e-05, + "loss": 0.0605, + "step": 24146 + }, + { + "epoch": 7.46, + "learning_rate": 1.4442472025975818e-05, + "loss": 0.0742, + "step": 24147 + }, + { + "epoch": 7.46, + "learning_rate": 1.4442023962377674e-05, + "loss": 0.0713, + "step": 24148 + }, + { + "epoch": 7.46, + "learning_rate": 1.4441575887669221e-05, + "loss": 0.0641, + "step": 24149 + }, + { + "epoch": 7.46, + "learning_rate": 1.4441127801851571e-05, + "loss": 0.0704, + "step": 24150 + }, + { + "epoch": 7.46, + "learning_rate": 1.4440679704925855e-05, + "loss": 0.0608, + "step": 24151 + }, + { + "epoch": 7.46, + "learning_rate": 1.4440231596893184e-05, + "loss": 0.071, + "step": 24152 + }, + { + "epoch": 7.46, + "learning_rate": 1.4439783477754687e-05, + "loss": 0.0623, + "step": 24153 + }, + { + "epoch": 7.46, + "learning_rate": 1.4439335347511485e-05, + "loss": 0.0651, + "step": 24154 + }, + { + "epoch": 7.46, + "learning_rate": 1.443888720616469e-05, + "loss": 0.0719, + "step": 24155 + }, + { + "epoch": 7.46, + "learning_rate": 1.4438439053715432e-05, + "loss": 0.0777, + "step": 24156 + }, + { + "epoch": 7.46, + "learning_rate": 1.4437990890164826e-05, + "loss": 0.0622, + "step": 24157 + }, + { + "epoch": 7.46, + "learning_rate": 1.4437542715513994e-05, + "loss": 0.0626, + "step": 24158 + }, + { + "epoch": 7.46, + "learning_rate": 1.4437094529764065e-05, + "loss": 0.0631, + "step": 24159 + }, + { + "epoch": 7.46, + "learning_rate": 1.4436646332916148e-05, + "loss": 0.0672, + "step": 24160 + }, + { + "epoch": 7.46, + "learning_rate": 1.443619812497137e-05, + "loss": 0.0629, + "step": 24161 + }, + { + "epoch": 7.46, + "learning_rate": 1.4435749905930853e-05, + "loss": 0.0657, + "step": 24162 + }, + { + "epoch": 7.46, + "learning_rate": 1.4435301675795715e-05, + "loss": 0.0661, + "step": 24163 + }, + { + "epoch": 7.46, + "learning_rate": 1.443485343456708e-05, + "loss": 0.0647, + "step": 24164 + }, + { + "epoch": 7.46, + "learning_rate": 1.4434405182246065e-05, + "loss": 0.0683, + "step": 24165 + }, + { + "epoch": 7.46, + "learning_rate": 1.4433956918833796e-05, + "loss": 0.0656, + "step": 24166 + }, + { + "epoch": 7.46, + "learning_rate": 1.443350864433139e-05, + "loss": 0.0627, + "step": 24167 + }, + { + "epoch": 7.46, + "learning_rate": 1.4433060358739973e-05, + "loss": 0.0747, + "step": 24168 + }, + { + "epoch": 7.46, + "learning_rate": 1.4432612062060663e-05, + "loss": 0.0673, + "step": 24169 + }, + { + "epoch": 7.46, + "learning_rate": 1.4432163754294579e-05, + "loss": 0.0703, + "step": 24170 + }, + { + "epoch": 7.46, + "learning_rate": 1.4431715435442849e-05, + "loss": 0.0714, + "step": 24171 + }, + { + "epoch": 7.46, + "learning_rate": 1.4431267105506588e-05, + "loss": 0.0629, + "step": 24172 + }, + { + "epoch": 7.47, + "learning_rate": 1.4430818764486918e-05, + "loss": 0.0674, + "step": 24173 + }, + { + "epoch": 7.47, + "learning_rate": 1.4430370412384966e-05, + "loss": 0.073, + "step": 24174 + }, + { + "epoch": 7.47, + "learning_rate": 1.4429922049201847e-05, + "loss": 0.0688, + "step": 24175 + }, + { + "epoch": 7.47, + "learning_rate": 1.4429473674938686e-05, + "loss": 0.0663, + "step": 24176 + }, + { + "epoch": 7.47, + "learning_rate": 1.4429025289596606e-05, + "loss": 0.0691, + "step": 24177 + }, + { + "epoch": 7.47, + "learning_rate": 1.4428576893176721e-05, + "loss": 0.0671, + "step": 24178 + }, + { + "epoch": 7.47, + "learning_rate": 1.4428128485680159e-05, + "loss": 0.0672, + "step": 24179 + }, + { + "epoch": 7.47, + "learning_rate": 1.4427680067108043e-05, + "loss": 0.0649, + "step": 24180 + }, + { + "epoch": 7.47, + "learning_rate": 1.4427231637461488e-05, + "loss": 0.0726, + "step": 24181 + }, + { + "epoch": 7.47, + "learning_rate": 1.442678319674162e-05, + "loss": 0.0664, + "step": 24182 + }, + { + "epoch": 7.47, + "learning_rate": 1.4426334744949559e-05, + "loss": 0.0589, + "step": 24183 + }, + { + "epoch": 7.47, + "learning_rate": 1.4425886282086432e-05, + "loss": 0.0664, + "step": 24184 + }, + { + "epoch": 7.47, + "learning_rate": 1.4425437808153353e-05, + "loss": 0.0703, + "step": 24185 + }, + { + "epoch": 7.47, + "learning_rate": 1.4424989323151443e-05, + "loss": 0.07, + "step": 24186 + }, + { + "epoch": 7.47, + "learning_rate": 1.4424540827081835e-05, + "loss": 0.0655, + "step": 24187 + }, + { + "epoch": 7.47, + "learning_rate": 1.442409231994564e-05, + "loss": 0.0672, + "step": 24188 + }, + { + "epoch": 7.47, + "learning_rate": 1.4423643801743982e-05, + "loss": 0.0673, + "step": 24189 + }, + { + "epoch": 7.47, + "learning_rate": 1.4423195272477986e-05, + "loss": 0.0738, + "step": 24190 + }, + { + "epoch": 7.47, + "learning_rate": 1.4422746732148772e-05, + "loss": 0.0648, + "step": 24191 + }, + { + "epoch": 7.47, + "learning_rate": 1.442229818075746e-05, + "loss": 0.0723, + "step": 24192 + }, + { + "epoch": 7.47, + "learning_rate": 1.4421849618305175e-05, + "loss": 0.0642, + "step": 24193 + }, + { + "epoch": 7.47, + "learning_rate": 1.4421401044793037e-05, + "loss": 0.0664, + "step": 24194 + }, + { + "epoch": 7.47, + "learning_rate": 1.4420952460222169e-05, + "loss": 0.0676, + "step": 24195 + }, + { + "epoch": 7.47, + "learning_rate": 1.4420503864593692e-05, + "loss": 0.0627, + "step": 24196 + }, + { + "epoch": 7.47, + "learning_rate": 1.4420055257908727e-05, + "loss": 0.063, + "step": 24197 + }, + { + "epoch": 7.47, + "learning_rate": 1.44196066401684e-05, + "loss": 0.0683, + "step": 24198 + }, + { + "epoch": 7.47, + "learning_rate": 1.441915801137383e-05, + "loss": 0.0746, + "step": 24199 + }, + { + "epoch": 7.47, + "learning_rate": 1.4418709371526141e-05, + "loss": 0.067, + "step": 24200 + }, + { + "epoch": 7.47, + "learning_rate": 1.441826072062645e-05, + "loss": 0.0695, + "step": 24201 + }, + { + "epoch": 7.47, + "learning_rate": 1.4417812058675889e-05, + "loss": 0.0717, + "step": 24202 + }, + { + "epoch": 7.47, + "learning_rate": 1.441736338567557e-05, + "loss": 0.0679, + "step": 24203 + }, + { + "epoch": 7.47, + "learning_rate": 1.441691470162662e-05, + "loss": 0.0646, + "step": 24204 + }, + { + "epoch": 7.48, + "learning_rate": 1.4416466006530165e-05, + "loss": 0.0643, + "step": 24205 + }, + { + "epoch": 7.48, + "learning_rate": 1.4416017300387318e-05, + "loss": 0.0636, + "step": 24206 + }, + { + "epoch": 7.48, + "learning_rate": 1.4415568583199208e-05, + "loss": 0.0746, + "step": 24207 + }, + { + "epoch": 7.48, + "learning_rate": 1.4415119854966956e-05, + "loss": 0.0625, + "step": 24208 + }, + { + "epoch": 7.48, + "learning_rate": 1.4414671115691683e-05, + "loss": 0.0678, + "step": 24209 + }, + { + "epoch": 7.48, + "learning_rate": 1.4414222365374513e-05, + "loss": 0.0591, + "step": 24210 + }, + { + "epoch": 7.48, + "learning_rate": 1.4413773604016567e-05, + "loss": 0.0667, + "step": 24211 + }, + { + "epoch": 7.48, + "learning_rate": 1.4413324831618969e-05, + "loss": 0.0729, + "step": 24212 + }, + { + "epoch": 7.48, + "learning_rate": 1.4412876048182842e-05, + "loss": 0.0688, + "step": 24213 + }, + { + "epoch": 7.48, + "learning_rate": 1.4412427253709305e-05, + "loss": 0.0676, + "step": 24214 + }, + { + "epoch": 7.48, + "learning_rate": 1.4411978448199485e-05, + "loss": 0.0612, + "step": 24215 + }, + { + "epoch": 7.48, + "learning_rate": 1.44115296316545e-05, + "loss": 0.0777, + "step": 24216 + }, + { + "epoch": 7.48, + "learning_rate": 1.4411080804075472e-05, + "loss": 0.0728, + "step": 24217 + }, + { + "epoch": 7.48, + "learning_rate": 1.441063196546353e-05, + "loss": 0.0725, + "step": 24218 + }, + { + "epoch": 7.48, + "learning_rate": 1.4410183115819794e-05, + "loss": 0.0692, + "step": 24219 + }, + { + "epoch": 7.48, + "learning_rate": 1.4409734255145385e-05, + "loss": 0.0728, + "step": 24220 + }, + { + "epoch": 7.48, + "learning_rate": 1.4409285383441426e-05, + "loss": 0.0635, + "step": 24221 + }, + { + "epoch": 7.48, + "learning_rate": 1.4408836500709038e-05, + "loss": 0.0661, + "step": 24222 + }, + { + "epoch": 7.48, + "learning_rate": 1.4408387606949348e-05, + "loss": 0.0716, + "step": 24223 + }, + { + "epoch": 7.48, + "learning_rate": 1.4407938702163475e-05, + "loss": 0.0683, + "step": 24224 + }, + { + "epoch": 7.48, + "learning_rate": 1.4407489786352544e-05, + "loss": 0.0675, + "step": 24225 + }, + { + "epoch": 7.48, + "learning_rate": 1.4407040859517678e-05, + "loss": 0.0659, + "step": 24226 + }, + { + "epoch": 7.48, + "learning_rate": 1.4406591921659998e-05, + "loss": 0.0684, + "step": 24227 + }, + { + "epoch": 7.48, + "learning_rate": 1.4406142972780632e-05, + "loss": 0.0624, + "step": 24228 + }, + { + "epoch": 7.48, + "learning_rate": 1.4405694012880691e-05, + "loss": 0.0678, + "step": 24229 + }, + { + "epoch": 7.48, + "learning_rate": 1.4405245041961311e-05, + "loss": 0.0673, + "step": 24230 + }, + { + "epoch": 7.48, + "learning_rate": 1.4404796060023611e-05, + "loss": 0.0669, + "step": 24231 + }, + { + "epoch": 7.48, + "learning_rate": 1.4404347067068706e-05, + "loss": 0.0674, + "step": 24232 + }, + { + "epoch": 7.48, + "learning_rate": 1.4403898063097735e-05, + "loss": 0.0806, + "step": 24233 + }, + { + "epoch": 7.48, + "learning_rate": 1.4403449048111804e-05, + "loss": 0.0643, + "step": 24234 + }, + { + "epoch": 7.48, + "learning_rate": 1.4403000022112047e-05, + "loss": 0.0614, + "step": 24235 + }, + { + "epoch": 7.48, + "learning_rate": 1.4402550985099583e-05, + "loss": 0.0724, + "step": 24236 + }, + { + "epoch": 7.48, + "learning_rate": 1.4402101937075536e-05, + "loss": 0.0616, + "step": 24237 + }, + { + "epoch": 7.49, + "learning_rate": 1.4401652878041033e-05, + "loss": 0.0717, + "step": 24238 + }, + { + "epoch": 7.49, + "learning_rate": 1.4401203807997188e-05, + "loss": 0.0715, + "step": 24239 + }, + { + "epoch": 7.49, + "learning_rate": 1.440075472694513e-05, + "loss": 0.0758, + "step": 24240 + }, + { + "epoch": 7.49, + "learning_rate": 1.4400305634885985e-05, + "loss": 0.0708, + "step": 24241 + }, + { + "epoch": 7.49, + "learning_rate": 1.439985653182087e-05, + "loss": 0.0717, + "step": 24242 + }, + { + "epoch": 7.49, + "learning_rate": 1.4399407417750912e-05, + "loss": 0.0779, + "step": 24243 + }, + { + "epoch": 7.49, + "learning_rate": 1.4398958292677236e-05, + "loss": 0.0694, + "step": 24244 + }, + { + "epoch": 7.49, + "learning_rate": 1.4398509156600961e-05, + "loss": 0.0699, + "step": 24245 + }, + { + "epoch": 7.49, + "learning_rate": 1.4398060009523214e-05, + "loss": 0.0643, + "step": 24246 + }, + { + "epoch": 7.49, + "learning_rate": 1.4397610851445115e-05, + "loss": 0.0674, + "step": 24247 + }, + { + "epoch": 7.49, + "learning_rate": 1.4397161682367789e-05, + "loss": 0.0718, + "step": 24248 + }, + { + "epoch": 7.49, + "learning_rate": 1.4396712502292359e-05, + "loss": 0.0673, + "step": 24249 + }, + { + "epoch": 7.49, + "learning_rate": 1.4396263311219951e-05, + "loss": 0.0631, + "step": 24250 + }, + { + "epoch": 7.49, + "learning_rate": 1.4395814109151685e-05, + "loss": 0.0663, + "step": 24251 + }, + { + "epoch": 7.49, + "learning_rate": 1.4395364896088687e-05, + "loss": 0.0682, + "step": 24252 + }, + { + "epoch": 7.49, + "learning_rate": 1.4394915672032079e-05, + "loss": 0.0731, + "step": 24253 + }, + { + "epoch": 7.49, + "learning_rate": 1.4394466436982987e-05, + "loss": 0.0671, + "step": 24254 + }, + { + "epoch": 7.49, + "learning_rate": 1.4394017190942534e-05, + "loss": 0.0597, + "step": 24255 + }, + { + "epoch": 7.49, + "learning_rate": 1.4393567933911838e-05, + "loss": 0.0689, + "step": 24256 + }, + { + "epoch": 7.49, + "learning_rate": 1.4393118665892031e-05, + "loss": 0.0733, + "step": 24257 + }, + { + "epoch": 7.49, + "learning_rate": 1.439266938688423e-05, + "loss": 0.0674, + "step": 24258 + }, + { + "epoch": 7.49, + "learning_rate": 1.4392220096889567e-05, + "loss": 0.0682, + "step": 24259 + }, + { + "epoch": 7.49, + "learning_rate": 1.4391770795909155e-05, + "loss": 0.0659, + "step": 24260 + }, + { + "epoch": 7.49, + "learning_rate": 1.4391321483944126e-05, + "loss": 0.072, + "step": 24261 + }, + { + "epoch": 7.49, + "learning_rate": 1.4390872160995601e-05, + "loss": 0.0711, + "step": 24262 + }, + { + "epoch": 7.49, + "learning_rate": 1.43904228270647e-05, + "loss": 0.0662, + "step": 24263 + }, + { + "epoch": 7.49, + "learning_rate": 1.4389973482152557e-05, + "loss": 0.0715, + "step": 24264 + }, + { + "epoch": 7.49, + "learning_rate": 1.4389524126260285e-05, + "loss": 0.0743, + "step": 24265 + }, + { + "epoch": 7.49, + "learning_rate": 1.4389074759389015e-05, + "loss": 0.0676, + "step": 24266 + }, + { + "epoch": 7.49, + "learning_rate": 1.4388625381539869e-05, + "loss": 0.0614, + "step": 24267 + }, + { + "epoch": 7.49, + "learning_rate": 1.4388175992713967e-05, + "loss": 0.073, + "step": 24268 + }, + { + "epoch": 7.49, + "learning_rate": 1.438772659291244e-05, + "loss": 0.07, + "step": 24269 + }, + { + "epoch": 7.5, + "learning_rate": 1.4387277182136408e-05, + "loss": 0.0651, + "step": 24270 + }, + { + "epoch": 7.5, + "learning_rate": 1.4386827760386992e-05, + "loss": 0.0671, + "step": 24271 + }, + { + "epoch": 7.5, + "learning_rate": 1.4386378327665324e-05, + "loss": 0.0587, + "step": 24272 + }, + { + "epoch": 7.5, + "learning_rate": 1.4385928883972522e-05, + "loss": 0.0762, + "step": 24273 + }, + { + "epoch": 7.5, + "learning_rate": 1.4385479429309712e-05, + "loss": 0.0711, + "step": 24274 + }, + { + "epoch": 7.5, + "learning_rate": 1.4385029963678018e-05, + "loss": 0.0768, + "step": 24275 + }, + { + "epoch": 7.5, + "learning_rate": 1.4384580487078566e-05, + "loss": 0.0706, + "step": 24276 + }, + { + "epoch": 7.5, + "learning_rate": 1.4384130999512475e-05, + "loss": 0.0588, + "step": 24277 + }, + { + "epoch": 7.5, + "learning_rate": 1.4383681500980875e-05, + "loss": 0.0632, + "step": 24278 + }, + { + "epoch": 7.5, + "learning_rate": 1.438323199148489e-05, + "loss": 0.0639, + "step": 24279 + }, + { + "epoch": 7.5, + "learning_rate": 1.4382782471025638e-05, + "loss": 0.063, + "step": 24280 + }, + { + "epoch": 7.5, + "learning_rate": 1.4382332939604248e-05, + "loss": 0.0653, + "step": 24281 + }, + { + "epoch": 7.5, + "learning_rate": 1.4381883397221847e-05, + "loss": 0.0661, + "step": 24282 + }, + { + "epoch": 7.5, + "learning_rate": 1.4381433843879555e-05, + "loss": 0.0721, + "step": 24283 + }, + { + "epoch": 7.5, + "learning_rate": 1.4380984279578498e-05, + "loss": 0.065, + "step": 24284 + }, + { + "epoch": 7.5, + "learning_rate": 1.4380534704319802e-05, + "loss": 0.064, + "step": 24285 + }, + { + "epoch": 7.5, + "learning_rate": 1.4380085118104588e-05, + "loss": 0.067, + "step": 24286 + }, + { + "epoch": 7.5, + "learning_rate": 1.4379635520933983e-05, + "loss": 0.0635, + "step": 24287 + }, + { + "epoch": 7.5, + "learning_rate": 1.4379185912809108e-05, + "loss": 0.0673, + "step": 24288 + }, + { + "epoch": 7.5, + "learning_rate": 1.4378736293731092e-05, + "loss": 0.0674, + "step": 24289 + }, + { + "epoch": 7.5, + "learning_rate": 1.437828666370106e-05, + "loss": 0.0696, + "step": 24290 + }, + { + "epoch": 7.5, + "learning_rate": 1.4377837022720132e-05, + "loss": 0.063, + "step": 24291 + }, + { + "epoch": 7.5, + "learning_rate": 1.4377387370789437e-05, + "loss": 0.0694, + "step": 24292 + }, + { + "epoch": 7.5, + "learning_rate": 1.4376937707910097e-05, + "loss": 0.068, + "step": 24293 + }, + { + "epoch": 7.5, + "learning_rate": 1.4376488034083236e-05, + "loss": 0.0692, + "step": 24294 + }, + { + "epoch": 7.5, + "learning_rate": 1.4376038349309982e-05, + "loss": 0.0762, + "step": 24295 + }, + { + "epoch": 7.5, + "learning_rate": 1.437558865359146e-05, + "loss": 0.0762, + "step": 24296 + }, + { + "epoch": 7.5, + "learning_rate": 1.4375138946928789e-05, + "loss": 0.0651, + "step": 24297 + }, + { + "epoch": 7.5, + "learning_rate": 1.4374689229323098e-05, + "loss": 0.074, + "step": 24298 + }, + { + "epoch": 7.5, + "learning_rate": 1.4374239500775508e-05, + "loss": 0.0663, + "step": 24299 + }, + { + "epoch": 7.5, + "learning_rate": 1.4373789761287156e-05, + "loss": 0.0623, + "step": 24300 + }, + { + "epoch": 7.5, + "learning_rate": 1.4373340010859152e-05, + "loss": 0.0655, + "step": 24301 + }, + { + "epoch": 7.5, + "learning_rate": 1.4372890249492628e-05, + "loss": 0.075, + "step": 24302 + }, + { + "epoch": 7.51, + "learning_rate": 1.4372440477188707e-05, + "loss": 0.0689, + "step": 24303 + }, + { + "epoch": 7.51, + "learning_rate": 1.4371990693948517e-05, + "loss": 0.0649, + "step": 24304 + }, + { + "epoch": 7.51, + "learning_rate": 1.437154089977318e-05, + "loss": 0.0677, + "step": 24305 + }, + { + "epoch": 7.51, + "learning_rate": 1.437109109466382e-05, + "loss": 0.0724, + "step": 24306 + }, + { + "epoch": 7.51, + "learning_rate": 1.4370641278621567e-05, + "loss": 0.0659, + "step": 24307 + }, + { + "epoch": 7.51, + "learning_rate": 1.4370191451647541e-05, + "loss": 0.0647, + "step": 24308 + }, + { + "epoch": 7.51, + "learning_rate": 1.4369741613742872e-05, + "loss": 0.0682, + "step": 24309 + }, + { + "epoch": 7.51, + "learning_rate": 1.436929176490868e-05, + "loss": 0.0707, + "step": 24310 + }, + { + "epoch": 7.51, + "learning_rate": 1.4368841905146091e-05, + "loss": 0.0659, + "step": 24311 + }, + { + "epoch": 7.51, + "learning_rate": 1.4368392034456234e-05, + "loss": 0.0677, + "step": 24312 + }, + { + "epoch": 7.51, + "learning_rate": 1.4367942152840231e-05, + "loss": 0.0647, + "step": 24313 + }, + { + "epoch": 7.51, + "learning_rate": 1.4367492260299205e-05, + "loss": 0.0648, + "step": 24314 + }, + { + "epoch": 7.51, + "learning_rate": 1.4367042356834289e-05, + "loss": 0.0691, + "step": 24315 + }, + { + "epoch": 7.51, + "learning_rate": 1.43665924424466e-05, + "loss": 0.0719, + "step": 24316 + }, + { + "epoch": 7.51, + "learning_rate": 1.436614251713727e-05, + "loss": 0.0672, + "step": 24317 + }, + { + "epoch": 7.51, + "learning_rate": 1.4365692580907421e-05, + "loss": 0.0722, + "step": 24318 + }, + { + "epoch": 7.51, + "learning_rate": 1.4365242633758177e-05, + "loss": 0.0763, + "step": 24319 + }, + { + "epoch": 7.51, + "learning_rate": 1.4364792675690664e-05, + "loss": 0.0657, + "step": 24320 + }, + { + "epoch": 7.51, + "learning_rate": 1.436434270670601e-05, + "loss": 0.0782, + "step": 24321 + }, + { + "epoch": 7.51, + "learning_rate": 1.4363892726805338e-05, + "loss": 0.0701, + "step": 24322 + }, + { + "epoch": 7.51, + "learning_rate": 1.4363442735989776e-05, + "loss": 0.0603, + "step": 24323 + }, + { + "epoch": 7.51, + "learning_rate": 1.4362992734260449e-05, + "loss": 0.0682, + "step": 24324 + }, + { + "epoch": 7.51, + "learning_rate": 1.4362542721618476e-05, + "loss": 0.0656, + "step": 24325 + }, + { + "epoch": 7.51, + "learning_rate": 1.4362092698064992e-05, + "loss": 0.0718, + "step": 24326 + }, + { + "epoch": 7.51, + "learning_rate": 1.4361642663601118e-05, + "loss": 0.0743, + "step": 24327 + }, + { + "epoch": 7.51, + "learning_rate": 1.4361192618227981e-05, + "loss": 0.0688, + "step": 24328 + }, + { + "epoch": 7.51, + "learning_rate": 1.4360742561946705e-05, + "loss": 0.0636, + "step": 24329 + }, + { + "epoch": 7.51, + "learning_rate": 1.4360292494758414e-05, + "loss": 0.0762, + "step": 24330 + }, + { + "epoch": 7.51, + "learning_rate": 1.435984241666424e-05, + "loss": 0.0609, + "step": 24331 + }, + { + "epoch": 7.51, + "learning_rate": 1.4359392327665305e-05, + "loss": 0.0697, + "step": 24332 + }, + { + "epoch": 7.51, + "learning_rate": 1.4358942227762734e-05, + "loss": 0.0707, + "step": 24333 + }, + { + "epoch": 7.51, + "learning_rate": 1.4358492116957652e-05, + "loss": 0.0709, + "step": 24334 + }, + { + "epoch": 7.52, + "learning_rate": 1.4358041995251186e-05, + "loss": 0.0699, + "step": 24335 + }, + { + "epoch": 7.52, + "learning_rate": 1.4357591862644462e-05, + "loss": 0.066, + "step": 24336 + }, + { + "epoch": 7.52, + "learning_rate": 1.4357141719138608e-05, + "loss": 0.0695, + "step": 24337 + }, + { + "epoch": 7.52, + "learning_rate": 1.4356691564734746e-05, + "loss": 0.073, + "step": 24338 + }, + { + "epoch": 7.52, + "learning_rate": 1.4356241399434006e-05, + "loss": 0.0653, + "step": 24339 + }, + { + "epoch": 7.52, + "learning_rate": 1.435579122323751e-05, + "loss": 0.071, + "step": 24340 + }, + { + "epoch": 7.52, + "learning_rate": 1.4355341036146389e-05, + "loss": 0.0694, + "step": 24341 + }, + { + "epoch": 7.52, + "learning_rate": 1.4354890838161759e-05, + "loss": 0.0729, + "step": 24342 + }, + { + "epoch": 7.52, + "learning_rate": 1.4354440629284756e-05, + "loss": 0.0673, + "step": 24343 + }, + { + "epoch": 7.52, + "learning_rate": 1.4353990409516506e-05, + "loss": 0.0657, + "step": 24344 + }, + { + "epoch": 7.52, + "learning_rate": 1.4353540178858127e-05, + "loss": 0.0666, + "step": 24345 + }, + { + "epoch": 7.52, + "learning_rate": 1.4353089937310754e-05, + "loss": 0.0675, + "step": 24346 + }, + { + "epoch": 7.52, + "learning_rate": 1.4352639684875507e-05, + "loss": 0.0678, + "step": 24347 + }, + { + "epoch": 7.52, + "learning_rate": 1.4352189421553513e-05, + "loss": 0.0757, + "step": 24348 + }, + { + "epoch": 7.52, + "learning_rate": 1.4351739147345903e-05, + "loss": 0.0719, + "step": 24349 + }, + { + "epoch": 7.52, + "learning_rate": 1.4351288862253795e-05, + "loss": 0.0588, + "step": 24350 + }, + { + "epoch": 7.52, + "learning_rate": 1.4350838566278324e-05, + "loss": 0.0681, + "step": 24351 + }, + { + "epoch": 7.52, + "learning_rate": 1.4350388259420611e-05, + "loss": 0.064, + "step": 24352 + }, + { + "epoch": 7.52, + "learning_rate": 1.4349937941681782e-05, + "loss": 0.0701, + "step": 24353 + }, + { + "epoch": 7.52, + "learning_rate": 1.4349487613062969e-05, + "loss": 0.0663, + "step": 24354 + }, + { + "epoch": 7.52, + "learning_rate": 1.4349037273565291e-05, + "loss": 0.0699, + "step": 24355 + }, + { + "epoch": 7.52, + "learning_rate": 1.4348586923189878e-05, + "loss": 0.072, + "step": 24356 + }, + { + "epoch": 7.52, + "learning_rate": 1.4348136561937855e-05, + "loss": 0.0675, + "step": 24357 + }, + { + "epoch": 7.52, + "learning_rate": 1.4347686189810351e-05, + "loss": 0.0785, + "step": 24358 + }, + { + "epoch": 7.52, + "learning_rate": 1.434723580680849e-05, + "loss": 0.0702, + "step": 24359 + }, + { + "epoch": 7.52, + "learning_rate": 1.43467854129334e-05, + "loss": 0.0705, + "step": 24360 + }, + { + "epoch": 7.52, + "learning_rate": 1.4346335008186205e-05, + "loss": 0.0697, + "step": 24361 + }, + { + "epoch": 7.52, + "learning_rate": 1.4345884592568035e-05, + "loss": 0.0693, + "step": 24362 + }, + { + "epoch": 7.52, + "learning_rate": 1.4345434166080015e-05, + "loss": 0.0666, + "step": 24363 + }, + { + "epoch": 7.52, + "learning_rate": 1.4344983728723272e-05, + "loss": 0.0675, + "step": 24364 + }, + { + "epoch": 7.52, + "learning_rate": 1.4344533280498931e-05, + "loss": 0.0742, + "step": 24365 + }, + { + "epoch": 7.52, + "learning_rate": 1.4344082821408122e-05, + "loss": 0.064, + "step": 24366 + }, + { + "epoch": 7.53, + "learning_rate": 1.4343632351451966e-05, + "loss": 0.0621, + "step": 24367 + }, + { + "epoch": 7.53, + "learning_rate": 1.4343181870631595e-05, + "loss": 0.0703, + "step": 24368 + }, + { + "epoch": 7.53, + "learning_rate": 1.4342731378948137e-05, + "loss": 0.0732, + "step": 24369 + }, + { + "epoch": 7.53, + "learning_rate": 1.4342280876402712e-05, + "loss": 0.0677, + "step": 24370 + }, + { + "epoch": 7.53, + "learning_rate": 1.4341830362996452e-05, + "loss": 0.0716, + "step": 24371 + }, + { + "epoch": 7.53, + "learning_rate": 1.4341379838730483e-05, + "loss": 0.0689, + "step": 24372 + }, + { + "epoch": 7.53, + "learning_rate": 1.4340929303605929e-05, + "loss": 0.0691, + "step": 24373 + }, + { + "epoch": 7.53, + "learning_rate": 1.434047875762392e-05, + "loss": 0.0695, + "step": 24374 + }, + { + "epoch": 7.53, + "learning_rate": 1.4340028200785582e-05, + "loss": 0.0703, + "step": 24375 + }, + { + "epoch": 7.53, + "learning_rate": 1.4339577633092042e-05, + "loss": 0.0789, + "step": 24376 + }, + { + "epoch": 7.53, + "learning_rate": 1.4339127054544428e-05, + "loss": 0.0725, + "step": 24377 + }, + { + "epoch": 7.53, + "learning_rate": 1.4338676465143864e-05, + "loss": 0.0708, + "step": 24378 + }, + { + "epoch": 7.53, + "learning_rate": 1.4338225864891478e-05, + "loss": 0.0757, + "step": 24379 + }, + { + "epoch": 7.53, + "learning_rate": 1.4337775253788401e-05, + "loss": 0.0694, + "step": 24380 + }, + { + "epoch": 7.53, + "learning_rate": 1.4337324631835755e-05, + "loss": 0.0683, + "step": 24381 + }, + { + "epoch": 7.53, + "learning_rate": 1.4336873999034671e-05, + "loss": 0.0644, + "step": 24382 + }, + { + "epoch": 7.53, + "learning_rate": 1.4336423355386273e-05, + "loss": 0.0649, + "step": 24383 + }, + { + "epoch": 7.53, + "learning_rate": 1.4335972700891688e-05, + "loss": 0.0736, + "step": 24384 + }, + { + "epoch": 7.53, + "learning_rate": 1.4335522035552045e-05, + "loss": 0.0613, + "step": 24385 + }, + { + "epoch": 7.53, + "learning_rate": 1.4335071359368471e-05, + "loss": 0.0727, + "step": 24386 + }, + { + "epoch": 7.53, + "learning_rate": 1.4334620672342095e-05, + "loss": 0.0671, + "step": 24387 + }, + { + "epoch": 7.53, + "learning_rate": 1.4334169974474037e-05, + "loss": 0.0615, + "step": 24388 + }, + { + "epoch": 7.53, + "learning_rate": 1.4333719265765434e-05, + "loss": 0.0696, + "step": 24389 + }, + { + "epoch": 7.53, + "learning_rate": 1.4333268546217407e-05, + "loss": 0.0668, + "step": 24390 + }, + { + "epoch": 7.53, + "learning_rate": 1.4332817815831083e-05, + "loss": 0.0731, + "step": 24391 + }, + { + "epoch": 7.53, + "learning_rate": 1.4332367074607594e-05, + "loss": 0.0732, + "step": 24392 + }, + { + "epoch": 7.53, + "learning_rate": 1.4331916322548066e-05, + "loss": 0.0699, + "step": 24393 + }, + { + "epoch": 7.53, + "learning_rate": 1.433146555965362e-05, + "loss": 0.0722, + "step": 24394 + }, + { + "epoch": 7.53, + "learning_rate": 1.4331014785925397e-05, + "loss": 0.0629, + "step": 24395 + }, + { + "epoch": 7.53, + "learning_rate": 1.4330564001364509e-05, + "loss": 0.0732, + "step": 24396 + }, + { + "epoch": 7.53, + "learning_rate": 1.4330113205972091e-05, + "loss": 0.069, + "step": 24397 + }, + { + "epoch": 7.53, + "learning_rate": 1.4329662399749272e-05, + "loss": 0.0674, + "step": 24398 + }, + { + "epoch": 7.53, + "learning_rate": 1.4329211582697178e-05, + "loss": 0.0675, + "step": 24399 + }, + { + "epoch": 7.54, + "learning_rate": 1.4328760754816934e-05, + "loss": 0.0707, + "step": 24400 + }, + { + "epoch": 7.54, + "learning_rate": 1.4328309916109673e-05, + "loss": 0.0647, + "step": 24401 + }, + { + "epoch": 7.54, + "learning_rate": 1.4327859066576517e-05, + "loss": 0.0636, + "step": 24402 + }, + { + "epoch": 7.54, + "learning_rate": 1.43274082062186e-05, + "loss": 0.07, + "step": 24403 + }, + { + "epoch": 7.54, + "learning_rate": 1.4326957335037041e-05, + "loss": 0.0698, + "step": 24404 + }, + { + "epoch": 7.54, + "learning_rate": 1.4326506453032974e-05, + "loss": 0.0728, + "step": 24405 + }, + { + "epoch": 7.54, + "learning_rate": 1.4326055560207529e-05, + "loss": 0.0657, + "step": 24406 + }, + { + "epoch": 7.54, + "learning_rate": 1.4325604656561822e-05, + "loss": 0.0732, + "step": 24407 + }, + { + "epoch": 7.54, + "learning_rate": 1.4325153742096998e-05, + "loss": 0.072, + "step": 24408 + }, + { + "epoch": 7.54, + "learning_rate": 1.4324702816814168e-05, + "loss": 0.0676, + "step": 24409 + }, + { + "epoch": 7.54, + "learning_rate": 1.432425188071447e-05, + "loss": 0.0755, + "step": 24410 + }, + { + "epoch": 7.54, + "learning_rate": 1.4323800933799033e-05, + "loss": 0.0643, + "step": 24411 + }, + { + "epoch": 7.54, + "learning_rate": 1.4323349976068977e-05, + "loss": 0.069, + "step": 24412 + }, + { + "epoch": 7.54, + "learning_rate": 1.4322899007525437e-05, + "loss": 0.0687, + "step": 24413 + }, + { + "epoch": 7.54, + "learning_rate": 1.4322448028169536e-05, + "loss": 0.0684, + "step": 24414 + }, + { + "epoch": 7.54, + "learning_rate": 1.4321997038002402e-05, + "loss": 0.0697, + "step": 24415 + }, + { + "epoch": 7.54, + "learning_rate": 1.4321546037025171e-05, + "loss": 0.0642, + "step": 24416 + }, + { + "epoch": 7.54, + "learning_rate": 1.432109502523896e-05, + "loss": 0.0637, + "step": 24417 + }, + { + "epoch": 7.54, + "learning_rate": 1.4320644002644906e-05, + "loss": 0.0745, + "step": 24418 + }, + { + "epoch": 7.54, + "learning_rate": 1.4320192969244132e-05, + "loss": 0.0596, + "step": 24419 + }, + { + "epoch": 7.54, + "learning_rate": 1.4319741925037765e-05, + "loss": 0.0636, + "step": 24420 + }, + { + "epoch": 7.54, + "learning_rate": 1.4319290870026939e-05, + "loss": 0.0793, + "step": 24421 + }, + { + "epoch": 7.54, + "learning_rate": 1.4318839804212776e-05, + "loss": 0.0726, + "step": 24422 + }, + { + "epoch": 7.54, + "learning_rate": 1.4318388727596408e-05, + "loss": 0.0723, + "step": 24423 + }, + { + "epoch": 7.54, + "learning_rate": 1.4317937640178962e-05, + "loss": 0.0658, + "step": 24424 + }, + { + "epoch": 7.54, + "learning_rate": 1.4317486541961568e-05, + "loss": 0.0703, + "step": 24425 + }, + { + "epoch": 7.54, + "learning_rate": 1.4317035432945352e-05, + "loss": 0.0734, + "step": 24426 + }, + { + "epoch": 7.54, + "learning_rate": 1.431658431313144e-05, + "loss": 0.0709, + "step": 24427 + }, + { + "epoch": 7.54, + "learning_rate": 1.4316133182520969e-05, + "loss": 0.0673, + "step": 24428 + }, + { + "epoch": 7.54, + "learning_rate": 1.4315682041115055e-05, + "loss": 0.0691, + "step": 24429 + }, + { + "epoch": 7.54, + "learning_rate": 1.4315230888914837e-05, + "loss": 0.0696, + "step": 24430 + }, + { + "epoch": 7.54, + "learning_rate": 1.4314779725921442e-05, + "loss": 0.0714, + "step": 24431 + }, + { + "epoch": 7.55, + "learning_rate": 1.4314328552135992e-05, + "loss": 0.0664, + "step": 24432 + }, + { + "epoch": 7.55, + "learning_rate": 1.431387736755962e-05, + "loss": 0.0677, + "step": 24433 + }, + { + "epoch": 7.55, + "learning_rate": 1.4313426172193454e-05, + "loss": 0.0645, + "step": 24434 + }, + { + "epoch": 7.55, + "learning_rate": 1.4312974966038622e-05, + "loss": 0.0632, + "step": 24435 + }, + { + "epoch": 7.55, + "learning_rate": 1.4312523749096257e-05, + "loss": 0.0758, + "step": 24436 + }, + { + "epoch": 7.55, + "learning_rate": 1.431207252136748e-05, + "loss": 0.065, + "step": 24437 + }, + { + "epoch": 7.55, + "learning_rate": 1.4311621282853422e-05, + "loss": 0.0712, + "step": 24438 + }, + { + "epoch": 7.55, + "learning_rate": 1.4311170033555214e-05, + "loss": 0.067, + "step": 24439 + }, + { + "epoch": 7.55, + "learning_rate": 1.4310718773473985e-05, + "loss": 0.064, + "step": 24440 + }, + { + "epoch": 7.55, + "learning_rate": 1.4310267502610859e-05, + "loss": 0.0728, + "step": 24441 + }, + { + "epoch": 7.55, + "learning_rate": 1.430981622096697e-05, + "loss": 0.0661, + "step": 24442 + }, + { + "epoch": 7.55, + "learning_rate": 1.4309364928543445e-05, + "loss": 0.0745, + "step": 24443 + }, + { + "epoch": 7.55, + "learning_rate": 1.4308913625341411e-05, + "loss": 0.074, + "step": 24444 + }, + { + "epoch": 7.55, + "learning_rate": 1.4308462311362e-05, + "loss": 0.0763, + "step": 24445 + }, + { + "epoch": 7.55, + "learning_rate": 1.4308010986606335e-05, + "loss": 0.0617, + "step": 24446 + }, + { + "epoch": 7.55, + "learning_rate": 1.4307559651075554e-05, + "loss": 0.0751, + "step": 24447 + }, + { + "epoch": 7.55, + "learning_rate": 1.4307108304770777e-05, + "loss": 0.0735, + "step": 24448 + }, + { + "epoch": 7.55, + "learning_rate": 1.4306656947693136e-05, + "loss": 0.0721, + "step": 24449 + }, + { + "epoch": 7.55, + "learning_rate": 1.4306205579843764e-05, + "loss": 0.0725, + "step": 24450 + }, + { + "epoch": 7.55, + "learning_rate": 1.4305754201223783e-05, + "loss": 0.0681, + "step": 24451 + }, + { + "epoch": 7.55, + "learning_rate": 1.4305302811834328e-05, + "loss": 0.0633, + "step": 24452 + }, + { + "epoch": 7.55, + "learning_rate": 1.4304851411676524e-05, + "loss": 0.0688, + "step": 24453 + }, + { + "epoch": 7.55, + "learning_rate": 1.4304400000751501e-05, + "loss": 0.0658, + "step": 24454 + }, + { + "epoch": 7.55, + "learning_rate": 1.430394857906039e-05, + "loss": 0.057, + "step": 24455 + }, + { + "epoch": 7.55, + "learning_rate": 1.4303497146604316e-05, + "loss": 0.0751, + "step": 24456 + }, + { + "epoch": 7.55, + "learning_rate": 1.4303045703384414e-05, + "loss": 0.0683, + "step": 24457 + }, + { + "epoch": 7.55, + "learning_rate": 1.4302594249401809e-05, + "loss": 0.0668, + "step": 24458 + }, + { + "epoch": 7.55, + "learning_rate": 1.430214278465763e-05, + "loss": 0.0688, + "step": 24459 + }, + { + "epoch": 7.55, + "learning_rate": 1.430169130915301e-05, + "loss": 0.0717, + "step": 24460 + }, + { + "epoch": 7.55, + "learning_rate": 1.4301239822889072e-05, + "loss": 0.0704, + "step": 24461 + }, + { + "epoch": 7.55, + "learning_rate": 1.4300788325866952e-05, + "loss": 0.07, + "step": 24462 + }, + { + "epoch": 7.55, + "learning_rate": 1.430033681808777e-05, + "loss": 0.0641, + "step": 24463 + }, + { + "epoch": 7.56, + "learning_rate": 1.4299885299552667e-05, + "loss": 0.0704, + "step": 24464 + }, + { + "epoch": 7.56, + "learning_rate": 1.4299433770262768e-05, + "loss": 0.0686, + "step": 24465 + }, + { + "epoch": 7.56, + "learning_rate": 1.4298982230219193e-05, + "loss": 0.0643, + "step": 24466 + }, + { + "epoch": 7.56, + "learning_rate": 1.4298530679423088e-05, + "loss": 0.0701, + "step": 24467 + }, + { + "epoch": 7.56, + "learning_rate": 1.429807911787557e-05, + "loss": 0.0643, + "step": 24468 + }, + { + "epoch": 7.56, + "learning_rate": 1.4297627545577771e-05, + "loss": 0.0638, + "step": 24469 + }, + { + "epoch": 7.56, + "learning_rate": 1.4297175962530822e-05, + "loss": 0.064, + "step": 24470 + }, + { + "epoch": 7.56, + "learning_rate": 1.4296724368735855e-05, + "loss": 0.0655, + "step": 24471 + }, + { + "epoch": 7.56, + "learning_rate": 1.4296272764193995e-05, + "loss": 0.0738, + "step": 24472 + }, + { + "epoch": 7.56, + "learning_rate": 1.4295821148906373e-05, + "loss": 0.0748, + "step": 24473 + }, + { + "epoch": 7.56, + "learning_rate": 1.4295369522874118e-05, + "loss": 0.0732, + "step": 24474 + }, + { + "epoch": 7.56, + "learning_rate": 1.429491788609836e-05, + "loss": 0.072, + "step": 24475 + }, + { + "epoch": 7.56, + "learning_rate": 1.4294466238580232e-05, + "loss": 0.0848, + "step": 24476 + }, + { + "epoch": 7.56, + "learning_rate": 1.4294014580320857e-05, + "loss": 0.0775, + "step": 24477 + }, + { + "epoch": 7.56, + "learning_rate": 1.429356291132137e-05, + "loss": 0.0634, + "step": 24478 + }, + { + "epoch": 7.56, + "learning_rate": 1.42931112315829e-05, + "loss": 0.0803, + "step": 24479 + }, + { + "epoch": 7.56, + "learning_rate": 1.4292659541106575e-05, + "loss": 0.075, + "step": 24480 + }, + { + "epoch": 7.56, + "learning_rate": 1.4292207839893526e-05, + "loss": 0.0632, + "step": 24481 + }, + { + "epoch": 7.56, + "learning_rate": 1.429175612794488e-05, + "loss": 0.0635, + "step": 24482 + }, + { + "epoch": 7.56, + "learning_rate": 1.4291304405261773e-05, + "loss": 0.0769, + "step": 24483 + }, + { + "epoch": 7.56, + "learning_rate": 1.4290852671845328e-05, + "loss": 0.0728, + "step": 24484 + }, + { + "epoch": 7.56, + "learning_rate": 1.4290400927696682e-05, + "loss": 0.0676, + "step": 24485 + }, + { + "epoch": 7.56, + "learning_rate": 1.4289949172816955e-05, + "loss": 0.0743, + "step": 24486 + }, + { + "epoch": 7.56, + "learning_rate": 1.4289497407207284e-05, + "loss": 0.0705, + "step": 24487 + }, + { + "epoch": 7.56, + "learning_rate": 1.42890456308688e-05, + "loss": 0.0664, + "step": 24488 + }, + { + "epoch": 7.56, + "learning_rate": 1.428859384380263e-05, + "loss": 0.0659, + "step": 24489 + }, + { + "epoch": 7.56, + "learning_rate": 1.4288142046009906e-05, + "loss": 0.077, + "step": 24490 + }, + { + "epoch": 7.56, + "learning_rate": 1.4287690237491756e-05, + "loss": 0.0699, + "step": 24491 + }, + { + "epoch": 7.56, + "learning_rate": 1.4287238418249306e-05, + "loss": 0.0667, + "step": 24492 + }, + { + "epoch": 7.56, + "learning_rate": 1.4286786588283696e-05, + "loss": 0.0715, + "step": 24493 + }, + { + "epoch": 7.56, + "learning_rate": 1.4286334747596047e-05, + "loss": 0.0707, + "step": 24494 + }, + { + "epoch": 7.56, + "learning_rate": 1.4285882896187498e-05, + "loss": 0.0659, + "step": 24495 + }, + { + "epoch": 7.56, + "learning_rate": 1.4285431034059171e-05, + "loss": 0.0744, + "step": 24496 + }, + { + "epoch": 7.57, + "learning_rate": 1.4284979161212198e-05, + "loss": 0.0688, + "step": 24497 + }, + { + "epoch": 7.57, + "learning_rate": 1.4284527277647712e-05, + "loss": 0.0682, + "step": 24498 + }, + { + "epoch": 7.57, + "learning_rate": 1.4284075383366845e-05, + "loss": 0.068, + "step": 24499 + }, + { + "epoch": 7.57, + "learning_rate": 1.428362347837072e-05, + "loss": 0.0783, + "step": 24500 + }, + { + "epoch": 7.57, + "learning_rate": 1.4283171562660471e-05, + "loss": 0.071, + "step": 24501 + }, + { + "epoch": 7.57, + "learning_rate": 1.4282719636237233e-05, + "loss": 0.0774, + "step": 24502 + }, + { + "epoch": 7.57, + "learning_rate": 1.4282267699102128e-05, + "loss": 0.0703, + "step": 24503 + }, + { + "epoch": 7.57, + "learning_rate": 1.4281815751256295e-05, + "loss": 0.0648, + "step": 24504 + }, + { + "epoch": 7.57, + "learning_rate": 1.4281363792700855e-05, + "loss": 0.0666, + "step": 24505 + }, + { + "epoch": 7.57, + "learning_rate": 1.4280911823436945e-05, + "loss": 0.0667, + "step": 24506 + }, + { + "epoch": 7.57, + "learning_rate": 1.4280459843465693e-05, + "loss": 0.0651, + "step": 24507 + }, + { + "epoch": 7.57, + "learning_rate": 1.428000785278823e-05, + "loss": 0.0746, + "step": 24508 + }, + { + "epoch": 7.57, + "learning_rate": 1.4279555851405689e-05, + "loss": 0.0663, + "step": 24509 + }, + { + "epoch": 7.57, + "learning_rate": 1.4279103839319198e-05, + "loss": 0.0708, + "step": 24510 + }, + { + "epoch": 7.57, + "learning_rate": 1.4278651816529885e-05, + "loss": 0.0689, + "step": 24511 + }, + { + "epoch": 7.57, + "learning_rate": 1.4278199783038887e-05, + "loss": 0.0748, + "step": 24512 + }, + { + "epoch": 7.57, + "learning_rate": 1.4277747738847327e-05, + "loss": 0.0684, + "step": 24513 + }, + { + "epoch": 7.57, + "learning_rate": 1.4277295683956343e-05, + "loss": 0.0684, + "step": 24514 + }, + { + "epoch": 7.57, + "learning_rate": 1.4276843618367062e-05, + "loss": 0.0693, + "step": 24515 + }, + { + "epoch": 7.57, + "learning_rate": 1.4276391542080617e-05, + "loss": 0.0751, + "step": 24516 + }, + { + "epoch": 7.57, + "learning_rate": 1.4275939455098131e-05, + "loss": 0.0767, + "step": 24517 + }, + { + "epoch": 7.57, + "learning_rate": 1.4275487357420743e-05, + "loss": 0.0704, + "step": 24518 + }, + { + "epoch": 7.57, + "learning_rate": 1.4275035249049584e-05, + "loss": 0.0704, + "step": 24519 + }, + { + "epoch": 7.57, + "learning_rate": 1.427458312998578e-05, + "loss": 0.0696, + "step": 24520 + }, + { + "epoch": 7.57, + "learning_rate": 1.4274131000230465e-05, + "loss": 0.0713, + "step": 24521 + }, + { + "epoch": 7.57, + "learning_rate": 1.4273678859784767e-05, + "loss": 0.0633, + "step": 24522 + }, + { + "epoch": 7.57, + "learning_rate": 1.4273226708649819e-05, + "loss": 0.0673, + "step": 24523 + }, + { + "epoch": 7.57, + "learning_rate": 1.4272774546826753e-05, + "loss": 0.0634, + "step": 24524 + }, + { + "epoch": 7.57, + "learning_rate": 1.4272322374316698e-05, + "loss": 0.069, + "step": 24525 + }, + { + "epoch": 7.57, + "learning_rate": 1.4271870191120787e-05, + "loss": 0.0729, + "step": 24526 + }, + { + "epoch": 7.57, + "learning_rate": 1.4271417997240146e-05, + "loss": 0.0658, + "step": 24527 + }, + { + "epoch": 7.57, + "learning_rate": 1.4270965792675911e-05, + "loss": 0.077, + "step": 24528 + }, + { + "epoch": 7.58, + "learning_rate": 1.4270513577429213e-05, + "loss": 0.0741, + "step": 24529 + }, + { + "epoch": 7.58, + "learning_rate": 1.4270061351501181e-05, + "loss": 0.0733, + "step": 24530 + }, + { + "epoch": 7.58, + "learning_rate": 1.4269609114892946e-05, + "loss": 0.0739, + "step": 24531 + }, + { + "epoch": 7.58, + "learning_rate": 1.426915686760564e-05, + "loss": 0.0676, + "step": 24532 + }, + { + "epoch": 7.58, + "learning_rate": 1.4268704609640395e-05, + "loss": 0.0683, + "step": 24533 + }, + { + "epoch": 7.58, + "learning_rate": 1.4268252340998342e-05, + "loss": 0.068, + "step": 24534 + }, + { + "epoch": 7.58, + "learning_rate": 1.4267800061680608e-05, + "loss": 0.0701, + "step": 24535 + }, + { + "epoch": 7.58, + "learning_rate": 1.426734777168833e-05, + "loss": 0.0713, + "step": 24536 + }, + { + "epoch": 7.58, + "learning_rate": 1.4266895471022637e-05, + "loss": 0.0722, + "step": 24537 + }, + { + "epoch": 7.58, + "learning_rate": 1.4266443159684659e-05, + "loss": 0.0725, + "step": 24538 + }, + { + "epoch": 7.58, + "learning_rate": 1.4265990837675532e-05, + "loss": 0.0751, + "step": 24539 + }, + { + "epoch": 7.58, + "learning_rate": 1.4265538504996378e-05, + "loss": 0.07, + "step": 24540 + }, + { + "epoch": 7.58, + "learning_rate": 1.4265086161648335e-05, + "loss": 0.0744, + "step": 24541 + }, + { + "epoch": 7.58, + "learning_rate": 1.426463380763254e-05, + "loss": 0.0655, + "step": 24542 + }, + { + "epoch": 7.58, + "learning_rate": 1.4264181442950111e-05, + "loss": 0.0638, + "step": 24543 + }, + { + "epoch": 7.58, + "learning_rate": 1.4263729067602192e-05, + "loss": 0.0671, + "step": 24544 + }, + { + "epoch": 7.58, + "learning_rate": 1.4263276681589903e-05, + "loss": 0.0688, + "step": 24545 + }, + { + "epoch": 7.58, + "learning_rate": 1.4262824284914384e-05, + "loss": 0.0612, + "step": 24546 + }, + { + "epoch": 7.58, + "learning_rate": 1.4262371877576769e-05, + "loss": 0.07, + "step": 24547 + }, + { + "epoch": 7.58, + "learning_rate": 1.4261919459578178e-05, + "loss": 0.0758, + "step": 24548 + }, + { + "epoch": 7.58, + "learning_rate": 1.4261467030919754e-05, + "loss": 0.0678, + "step": 24549 + }, + { + "epoch": 7.58, + "learning_rate": 1.426101459160262e-05, + "loss": 0.0712, + "step": 24550 + }, + { + "epoch": 7.58, + "learning_rate": 1.4260562141627912e-05, + "loss": 0.071, + "step": 24551 + }, + { + "epoch": 7.58, + "learning_rate": 1.4260109680996763e-05, + "loss": 0.0717, + "step": 24552 + }, + { + "epoch": 7.58, + "learning_rate": 1.42596572097103e-05, + "loss": 0.0744, + "step": 24553 + }, + { + "epoch": 7.58, + "learning_rate": 1.4259204727769658e-05, + "loss": 0.0629, + "step": 24554 + }, + { + "epoch": 7.58, + "learning_rate": 1.425875223517597e-05, + "loss": 0.075, + "step": 24555 + }, + { + "epoch": 7.58, + "learning_rate": 1.4258299731930363e-05, + "loss": 0.0661, + "step": 24556 + }, + { + "epoch": 7.58, + "learning_rate": 1.4257847218033973e-05, + "loss": 0.0747, + "step": 24557 + }, + { + "epoch": 7.58, + "learning_rate": 1.4257394693487931e-05, + "loss": 0.0705, + "step": 24558 + }, + { + "epoch": 7.58, + "learning_rate": 1.425694215829337e-05, + "loss": 0.0703, + "step": 24559 + }, + { + "epoch": 7.58, + "learning_rate": 1.4256489612451416e-05, + "loss": 0.0753, + "step": 24560 + }, + { + "epoch": 7.58, + "learning_rate": 1.4256037055963208e-05, + "loss": 0.0721, + "step": 24561 + }, + { + "epoch": 7.59, + "learning_rate": 1.4255584488829874e-05, + "loss": 0.0713, + "step": 24562 + }, + { + "epoch": 7.59, + "learning_rate": 1.425513191105255e-05, + "loss": 0.0648, + "step": 24563 + }, + { + "epoch": 7.59, + "learning_rate": 1.4254679322632361e-05, + "loss": 0.0719, + "step": 24564 + }, + { + "epoch": 7.59, + "learning_rate": 1.4254226723570446e-05, + "loss": 0.0678, + "step": 24565 + }, + { + "epoch": 7.59, + "learning_rate": 1.4253774113867933e-05, + "loss": 0.0739, + "step": 24566 + }, + { + "epoch": 7.59, + "learning_rate": 1.4253321493525953e-05, + "loss": 0.0698, + "step": 24567 + }, + { + "epoch": 7.59, + "learning_rate": 1.4252868862545644e-05, + "loss": 0.0688, + "step": 24568 + }, + { + "epoch": 7.59, + "learning_rate": 1.4252416220928132e-05, + "loss": 0.0707, + "step": 24569 + }, + { + "epoch": 7.59, + "learning_rate": 1.4251963568674553e-05, + "loss": 0.0711, + "step": 24570 + }, + { + "epoch": 7.59, + "learning_rate": 1.4251510905786034e-05, + "loss": 0.0637, + "step": 24571 + }, + { + "epoch": 7.59, + "learning_rate": 1.4251058232263712e-05, + "loss": 0.0724, + "step": 24572 + }, + { + "epoch": 7.59, + "learning_rate": 1.4250605548108722e-05, + "loss": 0.0674, + "step": 24573 + }, + { + "epoch": 7.59, + "learning_rate": 1.4250152853322187e-05, + "loss": 0.0744, + "step": 24574 + }, + { + "epoch": 7.59, + "learning_rate": 1.424970014790525e-05, + "loss": 0.0696, + "step": 24575 + }, + { + "epoch": 7.59, + "learning_rate": 1.4249247431859033e-05, + "loss": 0.0649, + "step": 24576 + }, + { + "epoch": 7.59, + "learning_rate": 1.4248794705184675e-05, + "loss": 0.0697, + "step": 24577 + }, + { + "epoch": 7.59, + "learning_rate": 1.4248341967883308e-05, + "loss": 0.0687, + "step": 24578 + }, + { + "epoch": 7.59, + "learning_rate": 1.424788921995606e-05, + "loss": 0.0631, + "step": 24579 + }, + { + "epoch": 7.59, + "learning_rate": 1.424743646140407e-05, + "loss": 0.0753, + "step": 24580 + }, + { + "epoch": 7.59, + "learning_rate": 1.4246983692228462e-05, + "loss": 0.0717, + "step": 24581 + }, + { + "epoch": 7.59, + "learning_rate": 1.4246530912430374e-05, + "loss": 0.0762, + "step": 24582 + }, + { + "epoch": 7.59, + "learning_rate": 1.424607812201094e-05, + "loss": 0.071, + "step": 24583 + }, + { + "epoch": 7.59, + "learning_rate": 1.424562532097129e-05, + "loss": 0.0684, + "step": 24584 + }, + { + "epoch": 7.59, + "learning_rate": 1.4245172509312557e-05, + "loss": 0.075, + "step": 24585 + }, + { + "epoch": 7.59, + "learning_rate": 1.4244719687035874e-05, + "loss": 0.0608, + "step": 24586 + }, + { + "epoch": 7.59, + "learning_rate": 1.424426685414237e-05, + "loss": 0.0721, + "step": 24587 + }, + { + "epoch": 7.59, + "learning_rate": 1.4243814010633181e-05, + "loss": 0.073, + "step": 24588 + }, + { + "epoch": 7.59, + "learning_rate": 1.4243361156509439e-05, + "loss": 0.0711, + "step": 24589 + }, + { + "epoch": 7.59, + "learning_rate": 1.424290829177228e-05, + "loss": 0.0689, + "step": 24590 + }, + { + "epoch": 7.59, + "learning_rate": 1.4242455416422828e-05, + "loss": 0.0683, + "step": 24591 + }, + { + "epoch": 7.59, + "learning_rate": 1.4242002530462227e-05, + "loss": 0.0637, + "step": 24592 + }, + { + "epoch": 7.59, + "learning_rate": 1.42415496338916e-05, + "loss": 0.0651, + "step": 24593 + }, + { + "epoch": 7.6, + "learning_rate": 1.4241096726712087e-05, + "loss": 0.071, + "step": 24594 + }, + { + "epoch": 7.6, + "learning_rate": 1.4240643808924814e-05, + "loss": 0.0623, + "step": 24595 + }, + { + "epoch": 7.6, + "learning_rate": 1.4240190880530919e-05, + "loss": 0.0784, + "step": 24596 + }, + { + "epoch": 7.6, + "learning_rate": 1.4239737941531532e-05, + "loss": 0.0687, + "step": 24597 + }, + { + "epoch": 7.6, + "learning_rate": 1.4239284991927793e-05, + "loss": 0.0719, + "step": 24598 + }, + { + "epoch": 7.6, + "learning_rate": 1.4238832031720822e-05, + "loss": 0.0789, + "step": 24599 + }, + { + "epoch": 7.6, + "learning_rate": 1.4238379060911762e-05, + "loss": 0.0699, + "step": 24600 + }, + { + "epoch": 7.6, + "learning_rate": 1.4237926079501744e-05, + "loss": 0.0689, + "step": 24601 + }, + { + "epoch": 7.6, + "learning_rate": 1.4237473087491895e-05, + "loss": 0.0712, + "step": 24602 + }, + { + "epoch": 7.6, + "learning_rate": 1.423702008488336e-05, + "loss": 0.0681, + "step": 24603 + }, + { + "epoch": 7.6, + "learning_rate": 1.4236567071677261e-05, + "loss": 0.067, + "step": 24604 + }, + { + "epoch": 7.6, + "learning_rate": 1.4236114047874732e-05, + "loss": 0.0718, + "step": 24605 + }, + { + "epoch": 7.6, + "learning_rate": 1.4235661013476916e-05, + "loss": 0.0742, + "step": 24606 + }, + { + "epoch": 7.6, + "learning_rate": 1.4235207968484934e-05, + "loss": 0.0695, + "step": 24607 + }, + { + "epoch": 7.6, + "learning_rate": 1.4234754912899925e-05, + "loss": 0.0712, + "step": 24608 + }, + { + "epoch": 7.6, + "learning_rate": 1.4234301846723024e-05, + "loss": 0.0723, + "step": 24609 + }, + { + "epoch": 7.6, + "learning_rate": 1.4233848769955358e-05, + "loss": 0.0739, + "step": 24610 + }, + { + "epoch": 7.6, + "learning_rate": 1.423339568259807e-05, + "loss": 0.0654, + "step": 24611 + }, + { + "epoch": 7.6, + "learning_rate": 1.4232942584652283e-05, + "loss": 0.0772, + "step": 24612 + }, + { + "epoch": 7.6, + "learning_rate": 1.4232489476119135e-05, + "loss": 0.0667, + "step": 24613 + }, + { + "epoch": 7.6, + "learning_rate": 1.423203635699976e-05, + "loss": 0.066, + "step": 24614 + }, + { + "epoch": 7.6, + "learning_rate": 1.4231583227295289e-05, + "loss": 0.0685, + "step": 24615 + }, + { + "epoch": 7.6, + "learning_rate": 1.4231130087006857e-05, + "loss": 0.0718, + "step": 24616 + }, + { + "epoch": 7.6, + "learning_rate": 1.4230676936135597e-05, + "loss": 0.0719, + "step": 24617 + }, + { + "epoch": 7.6, + "learning_rate": 1.4230223774682643e-05, + "loss": 0.0684, + "step": 24618 + }, + { + "epoch": 7.6, + "learning_rate": 1.4229770602649127e-05, + "loss": 0.0713, + "step": 24619 + }, + { + "epoch": 7.6, + "learning_rate": 1.4229317420036184e-05, + "loss": 0.0688, + "step": 24620 + }, + { + "epoch": 7.6, + "learning_rate": 1.4228864226844946e-05, + "loss": 0.0667, + "step": 24621 + }, + { + "epoch": 7.6, + "learning_rate": 1.4228411023076548e-05, + "loss": 0.0737, + "step": 24622 + }, + { + "epoch": 7.6, + "learning_rate": 1.422795780873212e-05, + "loss": 0.0754, + "step": 24623 + }, + { + "epoch": 7.6, + "learning_rate": 1.4227504583812803e-05, + "loss": 0.0663, + "step": 24624 + }, + { + "epoch": 7.6, + "learning_rate": 1.4227051348319722e-05, + "loss": 0.0657, + "step": 24625 + }, + { + "epoch": 7.61, + "learning_rate": 1.4226598102254017e-05, + "loss": 0.0741, + "step": 24626 + }, + { + "epoch": 7.61, + "learning_rate": 1.4226144845616818e-05, + "loss": 0.0641, + "step": 24627 + }, + { + "epoch": 7.61, + "learning_rate": 1.4225691578409259e-05, + "loss": 0.0632, + "step": 24628 + }, + { + "epoch": 7.61, + "learning_rate": 1.422523830063248e-05, + "loss": 0.0629, + "step": 24629 + }, + { + "epoch": 7.61, + "learning_rate": 1.4224785012287602e-05, + "loss": 0.0774, + "step": 24630 + }, + { + "epoch": 7.61, + "learning_rate": 1.422433171337577e-05, + "loss": 0.0716, + "step": 24631 + }, + { + "epoch": 7.61, + "learning_rate": 1.4223878403898114e-05, + "loss": 0.0797, + "step": 24632 + }, + { + "epoch": 7.61, + "learning_rate": 1.4223425083855766e-05, + "loss": 0.0678, + "step": 24633 + }, + { + "epoch": 7.61, + "learning_rate": 1.4222971753249866e-05, + "loss": 0.0693, + "step": 24634 + }, + { + "epoch": 7.61, + "learning_rate": 1.4222518412081538e-05, + "loss": 0.0772, + "step": 24635 + }, + { + "epoch": 7.61, + "learning_rate": 1.4222065060351922e-05, + "loss": 0.0732, + "step": 24636 + }, + { + "epoch": 7.61, + "learning_rate": 1.4221611698062154e-05, + "loss": 0.0622, + "step": 24637 + }, + { + "epoch": 7.61, + "learning_rate": 1.4221158325213364e-05, + "loss": 0.0687, + "step": 24638 + }, + { + "epoch": 7.61, + "learning_rate": 1.422070494180669e-05, + "loss": 0.0713, + "step": 24639 + }, + { + "epoch": 7.61, + "learning_rate": 1.4220251547843257e-05, + "loss": 0.0708, + "step": 24640 + }, + { + "epoch": 7.61, + "learning_rate": 1.4219798143324209e-05, + "loss": 0.066, + "step": 24641 + }, + { + "epoch": 7.61, + "learning_rate": 1.4219344728250674e-05, + "loss": 0.0646, + "step": 24642 + }, + { + "epoch": 7.61, + "learning_rate": 1.4218891302623792e-05, + "loss": 0.0708, + "step": 24643 + }, + { + "epoch": 7.61, + "learning_rate": 1.4218437866444691e-05, + "loss": 0.073, + "step": 24644 + }, + { + "epoch": 7.61, + "learning_rate": 1.4217984419714508e-05, + "loss": 0.0662, + "step": 24645 + }, + { + "epoch": 7.61, + "learning_rate": 1.4217530962434376e-05, + "loss": 0.0665, + "step": 24646 + }, + { + "epoch": 7.61, + "learning_rate": 1.4217077494605432e-05, + "loss": 0.0643, + "step": 24647 + }, + { + "epoch": 7.61, + "learning_rate": 1.4216624016228803e-05, + "loss": 0.0738, + "step": 24648 + }, + { + "epoch": 7.61, + "learning_rate": 1.4216170527305632e-05, + "loss": 0.0685, + "step": 24649 + }, + { + "epoch": 7.61, + "learning_rate": 1.4215717027837048e-05, + "loss": 0.0746, + "step": 24650 + }, + { + "epoch": 7.61, + "learning_rate": 1.421526351782419e-05, + "loss": 0.0723, + "step": 24651 + }, + { + "epoch": 7.61, + "learning_rate": 1.4214809997268189e-05, + "loss": 0.0684, + "step": 24652 + }, + { + "epoch": 7.61, + "learning_rate": 1.4214356466170173e-05, + "loss": 0.0694, + "step": 24653 + }, + { + "epoch": 7.61, + "learning_rate": 1.4213902924531288e-05, + "loss": 0.0743, + "step": 24654 + }, + { + "epoch": 7.61, + "learning_rate": 1.4213449372352666e-05, + "loss": 0.0752, + "step": 24655 + }, + { + "epoch": 7.61, + "learning_rate": 1.4212995809635432e-05, + "loss": 0.0735, + "step": 24656 + }, + { + "epoch": 7.61, + "learning_rate": 1.4212542236380734e-05, + "loss": 0.0741, + "step": 24657 + }, + { + "epoch": 7.61, + "learning_rate": 1.4212088652589691e-05, + "loss": 0.0703, + "step": 24658 + }, + { + "epoch": 7.62, + "learning_rate": 1.4211635058263451e-05, + "loss": 0.0746, + "step": 24659 + }, + { + "epoch": 7.62, + "learning_rate": 1.4211181453403145e-05, + "loss": 0.0654, + "step": 24660 + }, + { + "epoch": 7.62, + "learning_rate": 1.4210727838009903e-05, + "loss": 0.0724, + "step": 24661 + }, + { + "epoch": 7.62, + "learning_rate": 1.4210274212084865e-05, + "loss": 0.0695, + "step": 24662 + }, + { + "epoch": 7.62, + "learning_rate": 1.4209820575629163e-05, + "loss": 0.066, + "step": 24663 + }, + { + "epoch": 7.62, + "learning_rate": 1.420936692864393e-05, + "loss": 0.0784, + "step": 24664 + }, + { + "epoch": 7.62, + "learning_rate": 1.4208913271130308e-05, + "loss": 0.0673, + "step": 24665 + }, + { + "epoch": 7.62, + "learning_rate": 1.420845960308942e-05, + "loss": 0.0767, + "step": 24666 + }, + { + "epoch": 7.62, + "learning_rate": 1.4208005924522405e-05, + "loss": 0.0773, + "step": 24667 + }, + { + "epoch": 7.62, + "learning_rate": 1.4207552235430409e-05, + "loss": 0.0679, + "step": 24668 + }, + { + "epoch": 7.62, + "learning_rate": 1.420709853581455e-05, + "loss": 0.076, + "step": 24669 + }, + { + "epoch": 7.62, + "learning_rate": 1.4206644825675973e-05, + "loss": 0.0728, + "step": 24670 + }, + { + "epoch": 7.62, + "learning_rate": 1.4206191105015809e-05, + "loss": 0.079, + "step": 24671 + }, + { + "epoch": 7.62, + "learning_rate": 1.4205737373835196e-05, + "loss": 0.0636, + "step": 24672 + }, + { + "epoch": 7.62, + "learning_rate": 1.4205283632135265e-05, + "loss": 0.0699, + "step": 24673 + }, + { + "epoch": 7.62, + "learning_rate": 1.4204829879917152e-05, + "loss": 0.067, + "step": 24674 + }, + { + "epoch": 7.62, + "learning_rate": 1.4204376117181992e-05, + "loss": 0.0733, + "step": 24675 + }, + { + "epoch": 7.62, + "learning_rate": 1.4203922343930923e-05, + "loss": 0.07, + "step": 24676 + }, + { + "epoch": 7.62, + "learning_rate": 1.4203468560165076e-05, + "loss": 0.0706, + "step": 24677 + }, + { + "epoch": 7.62, + "learning_rate": 1.4203014765885588e-05, + "loss": 0.0661, + "step": 24678 + }, + { + "epoch": 7.62, + "learning_rate": 1.4202560961093595e-05, + "loss": 0.0711, + "step": 24679 + }, + { + "epoch": 7.62, + "learning_rate": 1.4202107145790227e-05, + "loss": 0.0618, + "step": 24680 + }, + { + "epoch": 7.62, + "learning_rate": 1.4201653319976624e-05, + "loss": 0.0741, + "step": 24681 + }, + { + "epoch": 7.62, + "learning_rate": 1.420119948365392e-05, + "loss": 0.0623, + "step": 24682 + }, + { + "epoch": 7.62, + "learning_rate": 1.4200745636823252e-05, + "loss": 0.0622, + "step": 24683 + }, + { + "epoch": 7.62, + "learning_rate": 1.4200291779485748e-05, + "loss": 0.0707, + "step": 24684 + }, + { + "epoch": 7.62, + "learning_rate": 1.4199837911642554e-05, + "loss": 0.0673, + "step": 24685 + }, + { + "epoch": 7.62, + "learning_rate": 1.4199384033294796e-05, + "loss": 0.0701, + "step": 24686 + }, + { + "epoch": 7.62, + "learning_rate": 1.4198930144443613e-05, + "loss": 0.0715, + "step": 24687 + }, + { + "epoch": 7.62, + "learning_rate": 1.4198476245090141e-05, + "loss": 0.0778, + "step": 24688 + }, + { + "epoch": 7.62, + "learning_rate": 1.4198022335235512e-05, + "loss": 0.0629, + "step": 24689 + }, + { + "epoch": 7.62, + "learning_rate": 1.4197568414880865e-05, + "loss": 0.0691, + "step": 24690 + }, + { + "epoch": 7.63, + "learning_rate": 1.4197114484027335e-05, + "loss": 0.0664, + "step": 24691 + }, + { + "epoch": 7.63, + "learning_rate": 1.419666054267605e-05, + "loss": 0.0703, + "step": 24692 + }, + { + "epoch": 7.63, + "learning_rate": 1.419620659082816e-05, + "loss": 0.0714, + "step": 24693 + }, + { + "epoch": 7.63, + "learning_rate": 1.4195752628484787e-05, + "loss": 0.0696, + "step": 24694 + }, + { + "epoch": 7.63, + "learning_rate": 1.4195298655647071e-05, + "loss": 0.0744, + "step": 24695 + }, + { + "epoch": 7.63, + "learning_rate": 1.4194844672316153e-05, + "loss": 0.0603, + "step": 24696 + }, + { + "epoch": 7.63, + "learning_rate": 1.4194390678493157e-05, + "loss": 0.0646, + "step": 24697 + }, + { + "epoch": 7.63, + "learning_rate": 1.419393667417923e-05, + "loss": 0.0803, + "step": 24698 + }, + { + "epoch": 7.63, + "learning_rate": 1.41934826593755e-05, + "loss": 0.0678, + "step": 24699 + }, + { + "epoch": 7.63, + "learning_rate": 1.4193028634083104e-05, + "loss": 0.0633, + "step": 24700 + }, + { + "epoch": 7.63, + "learning_rate": 1.419257459830318e-05, + "loss": 0.0706, + "step": 24701 + }, + { + "epoch": 7.63, + "learning_rate": 1.4192120552036863e-05, + "loss": 0.0702, + "step": 24702 + }, + { + "epoch": 7.63, + "learning_rate": 1.4191666495285286e-05, + "loss": 0.0661, + "step": 24703 + }, + { + "epoch": 7.63, + "learning_rate": 1.4191212428049587e-05, + "loss": 0.0712, + "step": 24704 + }, + { + "epoch": 7.63, + "learning_rate": 1.4190758350330902e-05, + "loss": 0.064, + "step": 24705 + }, + { + "epoch": 7.63, + "learning_rate": 1.4190304262130368e-05, + "loss": 0.0705, + "step": 24706 + }, + { + "epoch": 7.63, + "learning_rate": 1.4189850163449115e-05, + "loss": 0.0727, + "step": 24707 + }, + { + "epoch": 7.63, + "learning_rate": 1.4189396054288285e-05, + "loss": 0.0727, + "step": 24708 + }, + { + "epoch": 7.63, + "learning_rate": 1.418894193464901e-05, + "loss": 0.0724, + "step": 24709 + }, + { + "epoch": 7.63, + "learning_rate": 1.4188487804532426e-05, + "loss": 0.0686, + "step": 24710 + }, + { + "epoch": 7.63, + "learning_rate": 1.4188033663939673e-05, + "loss": 0.0763, + "step": 24711 + }, + { + "epoch": 7.63, + "learning_rate": 1.4187579512871884e-05, + "loss": 0.0657, + "step": 24712 + }, + { + "epoch": 7.63, + "learning_rate": 1.4187125351330193e-05, + "loss": 0.0723, + "step": 24713 + }, + { + "epoch": 7.63, + "learning_rate": 1.4186671179315741e-05, + "loss": 0.0697, + "step": 24714 + }, + { + "epoch": 7.63, + "learning_rate": 1.4186216996829655e-05, + "loss": 0.0741, + "step": 24715 + }, + { + "epoch": 7.63, + "learning_rate": 1.418576280387308e-05, + "loss": 0.0675, + "step": 24716 + }, + { + "epoch": 7.63, + "learning_rate": 1.4185308600447151e-05, + "loss": 0.0682, + "step": 24717 + }, + { + "epoch": 7.63, + "learning_rate": 1.4184854386552997e-05, + "loss": 0.0701, + "step": 24718 + }, + { + "epoch": 7.63, + "learning_rate": 1.4184400162191765e-05, + "loss": 0.0746, + "step": 24719 + }, + { + "epoch": 7.63, + "learning_rate": 1.4183945927364583e-05, + "loss": 0.0721, + "step": 24720 + }, + { + "epoch": 7.63, + "learning_rate": 1.4183491682072584e-05, + "loss": 0.065, + "step": 24721 + }, + { + "epoch": 7.63, + "learning_rate": 1.4183037426316914e-05, + "loss": 0.0685, + "step": 24722 + }, + { + "epoch": 7.64, + "learning_rate": 1.4182583160098702e-05, + "loss": 0.0735, + "step": 24723 + }, + { + "epoch": 7.64, + "learning_rate": 1.418212888341909e-05, + "loss": 0.0695, + "step": 24724 + }, + { + "epoch": 7.64, + "learning_rate": 1.418167459627921e-05, + "loss": 0.0668, + "step": 24725 + }, + { + "epoch": 7.64, + "learning_rate": 1.4181220298680196e-05, + "loss": 0.0735, + "step": 24726 + }, + { + "epoch": 7.64, + "learning_rate": 1.4180765990623191e-05, + "loss": 0.0704, + "step": 24727 + }, + { + "epoch": 7.64, + "learning_rate": 1.4180311672109326e-05, + "loss": 0.0632, + "step": 24728 + }, + { + "epoch": 7.64, + "learning_rate": 1.417985734313974e-05, + "loss": 0.0705, + "step": 24729 + }, + { + "epoch": 7.64, + "learning_rate": 1.4179403003715568e-05, + "loss": 0.0689, + "step": 24730 + }, + { + "epoch": 7.64, + "learning_rate": 1.4178948653837944e-05, + "loss": 0.0704, + "step": 24731 + }, + { + "epoch": 7.64, + "learning_rate": 1.4178494293508012e-05, + "loss": 0.0621, + "step": 24732 + }, + { + "epoch": 7.64, + "learning_rate": 1.41780399227269e-05, + "loss": 0.0655, + "step": 24733 + }, + { + "epoch": 7.64, + "learning_rate": 1.4177585541495751e-05, + "loss": 0.0645, + "step": 24734 + }, + { + "epoch": 7.64, + "learning_rate": 1.4177131149815697e-05, + "loss": 0.0658, + "step": 24735 + }, + { + "epoch": 7.64, + "learning_rate": 1.4176676747687877e-05, + "loss": 0.0666, + "step": 24736 + }, + { + "epoch": 7.64, + "learning_rate": 1.4176222335113427e-05, + "loss": 0.0684, + "step": 24737 + }, + { + "epoch": 7.64, + "learning_rate": 1.417576791209348e-05, + "loss": 0.0731, + "step": 24738 + }, + { + "epoch": 7.64, + "learning_rate": 1.417531347862918e-05, + "loss": 0.0674, + "step": 24739 + }, + { + "epoch": 7.64, + "learning_rate": 1.4174859034721658e-05, + "loss": 0.0665, + "step": 24740 + }, + { + "epoch": 7.64, + "learning_rate": 1.417440458037205e-05, + "loss": 0.0699, + "step": 24741 + }, + { + "epoch": 7.64, + "learning_rate": 1.4173950115581498e-05, + "loss": 0.0732, + "step": 24742 + }, + { + "epoch": 7.64, + "learning_rate": 1.4173495640351132e-05, + "loss": 0.071, + "step": 24743 + }, + { + "epoch": 7.64, + "learning_rate": 1.4173041154682094e-05, + "loss": 0.0672, + "step": 24744 + }, + { + "epoch": 7.64, + "learning_rate": 1.4172586658575522e-05, + "loss": 0.0713, + "step": 24745 + }, + { + "epoch": 7.64, + "learning_rate": 1.4172132152032545e-05, + "loss": 0.0728, + "step": 24746 + }, + { + "epoch": 7.64, + "learning_rate": 1.4171677635054308e-05, + "loss": 0.0713, + "step": 24747 + }, + { + "epoch": 7.64, + "learning_rate": 1.4171223107641943e-05, + "loss": 0.075, + "step": 24748 + }, + { + "epoch": 7.64, + "learning_rate": 1.4170768569796588e-05, + "loss": 0.0741, + "step": 24749 + }, + { + "epoch": 7.64, + "learning_rate": 1.417031402151938e-05, + "loss": 0.0676, + "step": 24750 + }, + { + "epoch": 7.64, + "learning_rate": 1.4169859462811454e-05, + "loss": 0.0674, + "step": 24751 + }, + { + "epoch": 7.64, + "learning_rate": 1.4169404893673952e-05, + "loss": 0.0815, + "step": 24752 + }, + { + "epoch": 7.64, + "learning_rate": 1.4168950314108007e-05, + "loss": 0.0649, + "step": 24753 + }, + { + "epoch": 7.64, + "learning_rate": 1.4168495724114756e-05, + "loss": 0.0741, + "step": 24754 + }, + { + "epoch": 7.64, + "learning_rate": 1.416804112369534e-05, + "loss": 0.0642, + "step": 24755 + }, + { + "epoch": 7.65, + "learning_rate": 1.416758651285089e-05, + "loss": 0.0733, + "step": 24756 + }, + { + "epoch": 7.65, + "learning_rate": 1.4167131891582547e-05, + "loss": 0.0682, + "step": 24757 + }, + { + "epoch": 7.65, + "learning_rate": 1.4166677259891448e-05, + "loss": 0.0699, + "step": 24758 + }, + { + "epoch": 7.65, + "learning_rate": 1.4166222617778727e-05, + "loss": 0.0731, + "step": 24759 + }, + { + "epoch": 7.65, + "learning_rate": 1.4165767965245525e-05, + "loss": 0.0627, + "step": 24760 + }, + { + "epoch": 7.65, + "learning_rate": 1.4165313302292976e-05, + "loss": 0.0626, + "step": 24761 + }, + { + "epoch": 7.65, + "learning_rate": 1.416485862892222e-05, + "loss": 0.0712, + "step": 24762 + }, + { + "epoch": 7.65, + "learning_rate": 1.4164403945134393e-05, + "loss": 0.0717, + "step": 24763 + }, + { + "epoch": 7.65, + "learning_rate": 1.4163949250930631e-05, + "loss": 0.0706, + "step": 24764 + }, + { + "epoch": 7.65, + "learning_rate": 1.4163494546312073e-05, + "loss": 0.0656, + "step": 24765 + }, + { + "epoch": 7.65, + "learning_rate": 1.4163039831279857e-05, + "loss": 0.0675, + "step": 24766 + }, + { + "epoch": 7.65, + "learning_rate": 1.4162585105835118e-05, + "loss": 0.0649, + "step": 24767 + }, + { + "epoch": 7.65, + "learning_rate": 1.4162130369978997e-05, + "loss": 0.0671, + "step": 24768 + }, + { + "epoch": 7.65, + "learning_rate": 1.4161675623712623e-05, + "loss": 0.057, + "step": 24769 + }, + { + "epoch": 7.65, + "learning_rate": 1.4161220867037142e-05, + "loss": 0.0707, + "step": 24770 + }, + { + "epoch": 7.65, + "learning_rate": 1.4160766099953693e-05, + "loss": 0.0693, + "step": 24771 + }, + { + "epoch": 7.65, + "learning_rate": 1.4160311322463402e-05, + "loss": 0.0789, + "step": 24772 + }, + { + "epoch": 7.65, + "learning_rate": 1.415985653456742e-05, + "loss": 0.069, + "step": 24773 + }, + { + "epoch": 7.65, + "learning_rate": 1.4159401736266874e-05, + "loss": 0.0709, + "step": 24774 + }, + { + "epoch": 7.65, + "learning_rate": 1.4158946927562904e-05, + "loss": 0.0686, + "step": 24775 + }, + { + "epoch": 7.65, + "learning_rate": 1.4158492108456656e-05, + "loss": 0.0712, + "step": 24776 + }, + { + "epoch": 7.65, + "learning_rate": 1.4158037278949253e-05, + "loss": 0.0679, + "step": 24777 + }, + { + "epoch": 7.65, + "learning_rate": 1.4157582439041848e-05, + "loss": 0.0823, + "step": 24778 + }, + { + "epoch": 7.65, + "learning_rate": 1.4157127588735567e-05, + "loss": 0.0727, + "step": 24779 + }, + { + "epoch": 7.65, + "learning_rate": 1.4156672728031548e-05, + "loss": 0.0704, + "step": 24780 + }, + { + "epoch": 7.65, + "learning_rate": 1.4156217856930939e-05, + "loss": 0.0751, + "step": 24781 + }, + { + "epoch": 7.65, + "learning_rate": 1.4155762975434869e-05, + "loss": 0.0691, + "step": 24782 + }, + { + "epoch": 7.65, + "learning_rate": 1.4155308083544477e-05, + "loss": 0.0663, + "step": 24783 + }, + { + "epoch": 7.65, + "learning_rate": 1.41548531812609e-05, + "loss": 0.0739, + "step": 24784 + }, + { + "epoch": 7.65, + "learning_rate": 1.4154398268585282e-05, + "loss": 0.0791, + "step": 24785 + }, + { + "epoch": 7.65, + "learning_rate": 1.415394334551875e-05, + "loss": 0.0642, + "step": 24786 + }, + { + "epoch": 7.65, + "learning_rate": 1.4153488412062453e-05, + "loss": 0.076, + "step": 24787 + }, + { + "epoch": 7.66, + "learning_rate": 1.4153033468217521e-05, + "loss": 0.0747, + "step": 24788 + }, + { + "epoch": 7.66, + "learning_rate": 1.4152578513985095e-05, + "loss": 0.0647, + "step": 24789 + }, + { + "epoch": 7.66, + "learning_rate": 1.4152123549366317e-05, + "loss": 0.0643, + "step": 24790 + }, + { + "epoch": 7.66, + "learning_rate": 1.4151668574362316e-05, + "loss": 0.0688, + "step": 24791 + }, + { + "epoch": 7.66, + "learning_rate": 1.4151213588974236e-05, + "loss": 0.0694, + "step": 24792 + }, + { + "epoch": 7.66, + "learning_rate": 1.4150758593203216e-05, + "loss": 0.0764, + "step": 24793 + }, + { + "epoch": 7.66, + "learning_rate": 1.415030358705039e-05, + "loss": 0.0686, + "step": 24794 + }, + { + "epoch": 7.66, + "learning_rate": 1.4149848570516894e-05, + "loss": 0.0751, + "step": 24795 + }, + { + "epoch": 7.66, + "learning_rate": 1.4149393543603878e-05, + "loss": 0.069, + "step": 24796 + }, + { + "epoch": 7.66, + "learning_rate": 1.4148938506312464e-05, + "loss": 0.0726, + "step": 24797 + }, + { + "epoch": 7.66, + "learning_rate": 1.4148483458643801e-05, + "loss": 0.0698, + "step": 24798 + }, + { + "epoch": 7.66, + "learning_rate": 1.4148028400599026e-05, + "loss": 0.0724, + "step": 24799 + }, + { + "epoch": 7.66, + "learning_rate": 1.4147573332179272e-05, + "loss": 0.0656, + "step": 24800 + }, + { + "epoch": 7.66, + "learning_rate": 1.4147118253385683e-05, + "loss": 0.0726, + "step": 24801 + }, + { + "epoch": 7.66, + "learning_rate": 1.4146663164219397e-05, + "loss": 0.0673, + "step": 24802 + }, + { + "epoch": 7.66, + "learning_rate": 1.4146208064681544e-05, + "loss": 0.0703, + "step": 24803 + }, + { + "epoch": 7.66, + "learning_rate": 1.4145752954773273e-05, + "loss": 0.0751, + "step": 24804 + }, + { + "epoch": 7.66, + "learning_rate": 1.4145297834495714e-05, + "loss": 0.0714, + "step": 24805 + }, + { + "epoch": 7.66, + "learning_rate": 1.4144842703850015e-05, + "loss": 0.0656, + "step": 24806 + }, + { + "epoch": 7.66, + "learning_rate": 1.4144387562837306e-05, + "loss": 0.0772, + "step": 24807 + }, + { + "epoch": 7.66, + "learning_rate": 1.4143932411458725e-05, + "loss": 0.0695, + "step": 24808 + }, + { + "epoch": 7.66, + "learning_rate": 1.4143477249715416e-05, + "loss": 0.0675, + "step": 24809 + }, + { + "epoch": 7.66, + "learning_rate": 1.4143022077608515e-05, + "loss": 0.0681, + "step": 24810 + }, + { + "epoch": 7.66, + "learning_rate": 1.4142566895139158e-05, + "loss": 0.0697, + "step": 24811 + }, + { + "epoch": 7.66, + "learning_rate": 1.4142111702308488e-05, + "loss": 0.0635, + "step": 24812 + }, + { + "epoch": 7.66, + "learning_rate": 1.4141656499117637e-05, + "loss": 0.0721, + "step": 24813 + }, + { + "epoch": 7.66, + "learning_rate": 1.4141201285567751e-05, + "loss": 0.0628, + "step": 24814 + }, + { + "epoch": 7.66, + "learning_rate": 1.4140746061659968e-05, + "loss": 0.0753, + "step": 24815 + }, + { + "epoch": 7.66, + "learning_rate": 1.4140290827395417e-05, + "loss": 0.0669, + "step": 24816 + }, + { + "epoch": 7.66, + "learning_rate": 1.4139835582775248e-05, + "loss": 0.0681, + "step": 24817 + }, + { + "epoch": 7.66, + "learning_rate": 1.4139380327800596e-05, + "loss": 0.0721, + "step": 24818 + }, + { + "epoch": 7.66, + "learning_rate": 1.4138925062472594e-05, + "loss": 0.0706, + "step": 24819 + }, + { + "epoch": 7.66, + "learning_rate": 1.413846978679239e-05, + "loss": 0.0685, + "step": 24820 + }, + { + "epoch": 7.67, + "learning_rate": 1.4138014500761117e-05, + "loss": 0.0717, + "step": 24821 + }, + { + "epoch": 7.67, + "learning_rate": 1.4137559204379915e-05, + "loss": 0.0772, + "step": 24822 + }, + { + "epoch": 7.67, + "learning_rate": 1.4137103897649924e-05, + "loss": 0.0711, + "step": 24823 + }, + { + "epoch": 7.67, + "learning_rate": 1.4136648580572278e-05, + "loss": 0.0682, + "step": 24824 + }, + { + "epoch": 7.67, + "learning_rate": 1.4136193253148123e-05, + "loss": 0.071, + "step": 24825 + }, + { + "epoch": 7.67, + "learning_rate": 1.4135737915378593e-05, + "loss": 0.0745, + "step": 24826 + }, + { + "epoch": 7.67, + "learning_rate": 1.413528256726483e-05, + "loss": 0.0699, + "step": 24827 + }, + { + "epoch": 7.67, + "learning_rate": 1.4134827208807966e-05, + "loss": 0.0685, + "step": 24828 + }, + { + "epoch": 7.67, + "learning_rate": 1.4134371840009149e-05, + "loss": 0.07, + "step": 24829 + }, + { + "epoch": 7.67, + "learning_rate": 1.4133916460869514e-05, + "loss": 0.068, + "step": 24830 + }, + { + "epoch": 7.67, + "learning_rate": 1.4133461071390198e-05, + "loss": 0.0636, + "step": 24831 + }, + { + "epoch": 7.67, + "learning_rate": 1.4133005671572346e-05, + "loss": 0.0703, + "step": 24832 + }, + { + "epoch": 7.67, + "learning_rate": 1.413255026141709e-05, + "loss": 0.0753, + "step": 24833 + }, + { + "epoch": 7.67, + "learning_rate": 1.413209484092557e-05, + "loss": 0.0683, + "step": 24834 + }, + { + "epoch": 7.67, + "learning_rate": 1.4131639410098932e-05, + "loss": 0.0687, + "step": 24835 + }, + { + "epoch": 7.67, + "learning_rate": 1.4131183968938306e-05, + "loss": 0.0683, + "step": 24836 + }, + { + "epoch": 7.67, + "learning_rate": 1.4130728517444838e-05, + "loss": 0.068, + "step": 24837 + }, + { + "epoch": 7.67, + "learning_rate": 1.4130273055619663e-05, + "loss": 0.0689, + "step": 24838 + }, + { + "epoch": 7.67, + "learning_rate": 1.412981758346392e-05, + "loss": 0.069, + "step": 24839 + }, + { + "epoch": 7.67, + "learning_rate": 1.4129362100978753e-05, + "loss": 0.0684, + "step": 24840 + }, + { + "epoch": 7.67, + "learning_rate": 1.41289066081653e-05, + "loss": 0.0629, + "step": 24841 + }, + { + "epoch": 7.67, + "learning_rate": 1.4128451105024696e-05, + "loss": 0.068, + "step": 24842 + }, + { + "epoch": 7.67, + "learning_rate": 1.4127995591558082e-05, + "loss": 0.0702, + "step": 24843 + }, + { + "epoch": 7.67, + "learning_rate": 1.4127540067766599e-05, + "loss": 0.0751, + "step": 24844 + }, + { + "epoch": 7.67, + "learning_rate": 1.4127084533651387e-05, + "loss": 0.0733, + "step": 24845 + }, + { + "epoch": 7.67, + "learning_rate": 1.4126628989213581e-05, + "loss": 0.0768, + "step": 24846 + }, + { + "epoch": 7.67, + "learning_rate": 1.4126173434454325e-05, + "loss": 0.0698, + "step": 24847 + }, + { + "epoch": 7.67, + "learning_rate": 1.4125717869374755e-05, + "loss": 0.0754, + "step": 24848 + }, + { + "epoch": 7.67, + "learning_rate": 1.4125262293976014e-05, + "loss": 0.0629, + "step": 24849 + }, + { + "epoch": 7.67, + "learning_rate": 1.4124806708259242e-05, + "loss": 0.071, + "step": 24850 + }, + { + "epoch": 7.67, + "learning_rate": 1.412435111222557e-05, + "loss": 0.0695, + "step": 24851 + }, + { + "epoch": 7.67, + "learning_rate": 1.4123895505876149e-05, + "loss": 0.0721, + "step": 24852 + }, + { + "epoch": 7.68, + "learning_rate": 1.4123439889212111e-05, + "loss": 0.0793, + "step": 24853 + }, + { + "epoch": 7.68, + "learning_rate": 1.4122984262234595e-05, + "loss": 0.0733, + "step": 24854 + }, + { + "epoch": 7.68, + "learning_rate": 1.412252862494475e-05, + "loss": 0.0625, + "step": 24855 + }, + { + "epoch": 7.68, + "learning_rate": 1.4122072977343701e-05, + "loss": 0.0696, + "step": 24856 + }, + { + "epoch": 7.68, + "learning_rate": 1.4121617319432601e-05, + "loss": 0.0757, + "step": 24857 + }, + { + "epoch": 7.68, + "learning_rate": 1.4121161651212585e-05, + "loss": 0.064, + "step": 24858 + }, + { + "epoch": 7.68, + "learning_rate": 1.4120705972684787e-05, + "loss": 0.0744, + "step": 24859 + }, + { + "epoch": 7.68, + "learning_rate": 1.4120250283850359e-05, + "loss": 0.0783, + "step": 24860 + }, + { + "epoch": 7.68, + "learning_rate": 1.4119794584710428e-05, + "loss": 0.0741, + "step": 24861 + }, + { + "epoch": 7.68, + "learning_rate": 1.411933887526614e-05, + "loss": 0.0693, + "step": 24862 + }, + { + "epoch": 7.68, + "learning_rate": 1.4118883155518637e-05, + "loss": 0.0645, + "step": 24863 + }, + { + "epoch": 7.68, + "learning_rate": 1.4118427425469053e-05, + "loss": 0.0745, + "step": 24864 + }, + { + "epoch": 7.68, + "learning_rate": 1.4117971685118532e-05, + "loss": 0.0761, + "step": 24865 + }, + { + "epoch": 7.68, + "learning_rate": 1.4117515934468214e-05, + "loss": 0.0814, + "step": 24866 + }, + { + "epoch": 7.68, + "learning_rate": 1.4117060173519234e-05, + "loss": 0.0748, + "step": 24867 + }, + { + "epoch": 7.68, + "learning_rate": 1.4116604402272737e-05, + "loss": 0.0718, + "step": 24868 + }, + { + "epoch": 7.68, + "learning_rate": 1.4116148620729864e-05, + "loss": 0.0697, + "step": 24869 + }, + { + "epoch": 7.68, + "learning_rate": 1.4115692828891749e-05, + "loss": 0.063, + "step": 24870 + }, + { + "epoch": 7.68, + "learning_rate": 1.4115237026759539e-05, + "loss": 0.0712, + "step": 24871 + }, + { + "epoch": 7.68, + "learning_rate": 1.411478121433437e-05, + "loss": 0.0728, + "step": 24872 + }, + { + "epoch": 7.68, + "learning_rate": 1.411432539161738e-05, + "loss": 0.0716, + "step": 24873 + }, + { + "epoch": 7.68, + "learning_rate": 1.4113869558609713e-05, + "loss": 0.0678, + "step": 24874 + }, + { + "epoch": 7.68, + "learning_rate": 1.4113413715312509e-05, + "loss": 0.0735, + "step": 24875 + }, + { + "epoch": 7.68, + "learning_rate": 1.4112957861726908e-05, + "loss": 0.0673, + "step": 24876 + }, + { + "epoch": 7.68, + "learning_rate": 1.4112501997854047e-05, + "loss": 0.0744, + "step": 24877 + }, + { + "epoch": 7.68, + "learning_rate": 1.411204612369507e-05, + "loss": 0.073, + "step": 24878 + }, + { + "epoch": 7.68, + "learning_rate": 1.4111590239251113e-05, + "loss": 0.0724, + "step": 24879 + }, + { + "epoch": 7.68, + "learning_rate": 1.4111134344523324e-05, + "loss": 0.0712, + "step": 24880 + }, + { + "epoch": 7.68, + "learning_rate": 1.4110678439512835e-05, + "loss": 0.0695, + "step": 24881 + }, + { + "epoch": 7.68, + "learning_rate": 1.411022252422079e-05, + "loss": 0.0632, + "step": 24882 + }, + { + "epoch": 7.68, + "learning_rate": 1.4109766598648327e-05, + "loss": 0.0711, + "step": 24883 + }, + { + "epoch": 7.68, + "learning_rate": 1.4109310662796591e-05, + "loss": 0.0655, + "step": 24884 + }, + { + "epoch": 7.69, + "learning_rate": 1.4108854716666715e-05, + "loss": 0.0721, + "step": 24885 + }, + { + "epoch": 7.69, + "learning_rate": 1.410839876025985e-05, + "loss": 0.0703, + "step": 24886 + }, + { + "epoch": 7.69, + "learning_rate": 1.4107942793577126e-05, + "loss": 0.0692, + "step": 24887 + }, + { + "epoch": 7.69, + "learning_rate": 1.4107486816619689e-05, + "loss": 0.0744, + "step": 24888 + }, + { + "epoch": 7.69, + "learning_rate": 1.410703082938868e-05, + "loss": 0.0625, + "step": 24889 + }, + { + "epoch": 7.69, + "learning_rate": 1.4106574831885234e-05, + "loss": 0.0696, + "step": 24890 + }, + { + "epoch": 7.69, + "learning_rate": 1.4106118824110499e-05, + "loss": 0.0689, + "step": 24891 + }, + { + "epoch": 7.69, + "learning_rate": 1.410566280606561e-05, + "loss": 0.0692, + "step": 24892 + }, + { + "epoch": 7.69, + "learning_rate": 1.4105206777751708e-05, + "loss": 0.0698, + "step": 24893 + }, + { + "epoch": 7.69, + "learning_rate": 1.410475073916994e-05, + "loss": 0.0759, + "step": 24894 + }, + { + "epoch": 7.69, + "learning_rate": 1.4104294690321439e-05, + "loss": 0.0682, + "step": 24895 + }, + { + "epoch": 7.69, + "learning_rate": 1.4103838631207349e-05, + "loss": 0.0732, + "step": 24896 + }, + { + "epoch": 7.69, + "learning_rate": 1.4103382561828809e-05, + "loss": 0.0693, + "step": 24897 + }, + { + "epoch": 7.69, + "learning_rate": 1.410292648218696e-05, + "loss": 0.0723, + "step": 24898 + }, + { + "epoch": 7.69, + "learning_rate": 1.4102470392282946e-05, + "loss": 0.0646, + "step": 24899 + }, + { + "epoch": 7.69, + "learning_rate": 1.4102014292117904e-05, + "loss": 0.0709, + "step": 24900 + }, + { + "epoch": 7.69, + "learning_rate": 1.4101558181692976e-05, + "loss": 0.0697, + "step": 24901 + }, + { + "epoch": 7.69, + "learning_rate": 1.4101102061009301e-05, + "loss": 0.0641, + "step": 24902 + }, + { + "epoch": 7.69, + "learning_rate": 1.4100645930068026e-05, + "loss": 0.0698, + "step": 24903 + }, + { + "epoch": 7.69, + "learning_rate": 1.4100189788870284e-05, + "loss": 0.0695, + "step": 24904 + }, + { + "epoch": 7.69, + "learning_rate": 1.4099733637417221e-05, + "loss": 0.0673, + "step": 24905 + }, + { + "epoch": 7.69, + "learning_rate": 1.4099277475709977e-05, + "loss": 0.0719, + "step": 24906 + }, + { + "epoch": 7.69, + "learning_rate": 1.4098821303749693e-05, + "loss": 0.0751, + "step": 24907 + }, + { + "epoch": 7.69, + "learning_rate": 1.4098365121537508e-05, + "loss": 0.076, + "step": 24908 + }, + { + "epoch": 7.69, + "learning_rate": 1.4097908929074566e-05, + "loss": 0.0716, + "step": 24909 + }, + { + "epoch": 7.69, + "learning_rate": 1.4097452726362002e-05, + "loss": 0.0682, + "step": 24910 + }, + { + "epoch": 7.69, + "learning_rate": 1.4096996513400965e-05, + "loss": 0.0683, + "step": 24911 + }, + { + "epoch": 7.69, + "learning_rate": 1.4096540290192592e-05, + "loss": 0.0682, + "step": 24912 + }, + { + "epoch": 7.69, + "learning_rate": 1.4096084056738023e-05, + "loss": 0.0731, + "step": 24913 + }, + { + "epoch": 7.69, + "learning_rate": 1.4095627813038405e-05, + "loss": 0.0745, + "step": 24914 + }, + { + "epoch": 7.69, + "learning_rate": 1.4095171559094872e-05, + "loss": 0.0682, + "step": 24915 + }, + { + "epoch": 7.69, + "learning_rate": 1.4094715294908565e-05, + "loss": 0.0702, + "step": 24916 + }, + { + "epoch": 7.69, + "learning_rate": 1.4094259020480631e-05, + "loss": 0.0736, + "step": 24917 + }, + { + "epoch": 7.7, + "learning_rate": 1.409380273581221e-05, + "loss": 0.0649, + "step": 24918 + }, + { + "epoch": 7.7, + "learning_rate": 1.4093346440904439e-05, + "loss": 0.0675, + "step": 24919 + }, + { + "epoch": 7.7, + "learning_rate": 1.4092890135758464e-05, + "loss": 0.0708, + "step": 24920 + }, + { + "epoch": 7.7, + "learning_rate": 1.4092433820375422e-05, + "loss": 0.062, + "step": 24921 + }, + { + "epoch": 7.7, + "learning_rate": 1.409197749475646e-05, + "loss": 0.0765, + "step": 24922 + }, + { + "epoch": 7.7, + "learning_rate": 1.4091521158902713e-05, + "loss": 0.0737, + "step": 24923 + }, + { + "epoch": 7.7, + "learning_rate": 1.4091064812815325e-05, + "loss": 0.0708, + "step": 24924 + }, + { + "epoch": 7.7, + "learning_rate": 1.4090608456495441e-05, + "loss": 0.0657, + "step": 24925 + }, + { + "epoch": 7.7, + "learning_rate": 1.4090152089944196e-05, + "loss": 0.0735, + "step": 24926 + }, + { + "epoch": 7.7, + "learning_rate": 1.4089695713162737e-05, + "loss": 0.0697, + "step": 24927 + }, + { + "epoch": 7.7, + "learning_rate": 1.40892393261522e-05, + "loss": 0.062, + "step": 24928 + }, + { + "epoch": 7.7, + "learning_rate": 1.408878292891373e-05, + "loss": 0.0744, + "step": 24929 + }, + { + "epoch": 7.7, + "learning_rate": 1.4088326521448473e-05, + "loss": 0.0767, + "step": 24930 + }, + { + "epoch": 7.7, + "learning_rate": 1.408787010375756e-05, + "loss": 0.0749, + "step": 24931 + }, + { + "epoch": 7.7, + "learning_rate": 1.4087413675842143e-05, + "loss": 0.0706, + "step": 24932 + }, + { + "epoch": 7.7, + "learning_rate": 1.4086957237703356e-05, + "loss": 0.0783, + "step": 24933 + }, + { + "epoch": 7.7, + "learning_rate": 1.4086500789342343e-05, + "loss": 0.0658, + "step": 24934 + }, + { + "epoch": 7.7, + "learning_rate": 1.408604433076025e-05, + "loss": 0.0707, + "step": 24935 + }, + { + "epoch": 7.7, + "learning_rate": 1.408558786195821e-05, + "loss": 0.069, + "step": 24936 + }, + { + "epoch": 7.7, + "learning_rate": 1.4085131382937371e-05, + "loss": 0.0728, + "step": 24937 + }, + { + "epoch": 7.7, + "learning_rate": 1.4084674893698875e-05, + "loss": 0.0765, + "step": 24938 + }, + { + "epoch": 7.7, + "learning_rate": 1.4084218394243861e-05, + "loss": 0.0687, + "step": 24939 + }, + { + "epoch": 7.7, + "learning_rate": 1.4083761884573475e-05, + "loss": 0.0676, + "step": 24940 + }, + { + "epoch": 7.7, + "learning_rate": 1.4083305364688848e-05, + "loss": 0.0725, + "step": 24941 + }, + { + "epoch": 7.7, + "learning_rate": 1.4082848834591136e-05, + "loss": 0.0708, + "step": 24942 + }, + { + "epoch": 7.7, + "learning_rate": 1.4082392294281474e-05, + "loss": 0.0689, + "step": 24943 + }, + { + "epoch": 7.7, + "learning_rate": 1.4081935743761002e-05, + "loss": 0.0718, + "step": 24944 + }, + { + "epoch": 7.7, + "learning_rate": 1.4081479183030867e-05, + "loss": 0.0653, + "step": 24945 + }, + { + "epoch": 7.7, + "learning_rate": 1.4081022612092206e-05, + "loss": 0.069, + "step": 24946 + }, + { + "epoch": 7.7, + "learning_rate": 1.4080566030946161e-05, + "loss": 0.0627, + "step": 24947 + }, + { + "epoch": 7.7, + "learning_rate": 1.4080109439593881e-05, + "loss": 0.073, + "step": 24948 + }, + { + "epoch": 7.7, + "learning_rate": 1.4079652838036499e-05, + "loss": 0.0782, + "step": 24949 + }, + { + "epoch": 7.71, + "learning_rate": 1.4079196226275165e-05, + "loss": 0.0711, + "step": 24950 + }, + { + "epoch": 7.71, + "learning_rate": 1.4078739604311014e-05, + "loss": 0.0744, + "step": 24951 + }, + { + "epoch": 7.71, + "learning_rate": 1.4078282972145192e-05, + "loss": 0.0688, + "step": 24952 + }, + { + "epoch": 7.71, + "learning_rate": 1.4077826329778841e-05, + "loss": 0.066, + "step": 24953 + }, + { + "epoch": 7.71, + "learning_rate": 1.4077369677213104e-05, + "loss": 0.0688, + "step": 24954 + }, + { + "epoch": 7.71, + "learning_rate": 1.4076913014449121e-05, + "loss": 0.0713, + "step": 24955 + }, + { + "epoch": 7.71, + "learning_rate": 1.4076456341488034e-05, + "loss": 0.0762, + "step": 24956 + }, + { + "epoch": 7.71, + "learning_rate": 1.4075999658330986e-05, + "loss": 0.0735, + "step": 24957 + }, + { + "epoch": 7.71, + "learning_rate": 1.4075542964979118e-05, + "loss": 0.0695, + "step": 24958 + }, + { + "epoch": 7.71, + "learning_rate": 1.4075086261433577e-05, + "loss": 0.0762, + "step": 24959 + }, + { + "epoch": 7.71, + "learning_rate": 1.40746295476955e-05, + "loss": 0.0712, + "step": 24960 + }, + { + "epoch": 7.71, + "learning_rate": 1.4074172823766033e-05, + "loss": 0.0686, + "step": 24961 + }, + { + "epoch": 7.71, + "learning_rate": 1.4073716089646314e-05, + "loss": 0.0722, + "step": 24962 + }, + { + "epoch": 7.71, + "learning_rate": 1.4073259345337488e-05, + "loss": 0.065, + "step": 24963 + }, + { + "epoch": 7.71, + "learning_rate": 1.4072802590840701e-05, + "loss": 0.0762, + "step": 24964 + }, + { + "epoch": 7.71, + "learning_rate": 1.407234582615709e-05, + "loss": 0.0689, + "step": 24965 + }, + { + "epoch": 7.71, + "learning_rate": 1.40718890512878e-05, + "loss": 0.0696, + "step": 24966 + }, + { + "epoch": 7.71, + "learning_rate": 1.4071432266233971e-05, + "loss": 0.0733, + "step": 24967 + }, + { + "epoch": 7.71, + "learning_rate": 1.4070975470996748e-05, + "loss": 0.0789, + "step": 24968 + }, + { + "epoch": 7.71, + "learning_rate": 1.4070518665577275e-05, + "loss": 0.0736, + "step": 24969 + }, + { + "epoch": 7.71, + "learning_rate": 1.4070061849976691e-05, + "loss": 0.0684, + "step": 24970 + }, + { + "epoch": 7.71, + "learning_rate": 1.406960502419614e-05, + "loss": 0.0716, + "step": 24971 + }, + { + "epoch": 7.71, + "learning_rate": 1.4069148188236764e-05, + "loss": 0.0718, + "step": 24972 + }, + { + "epoch": 7.71, + "learning_rate": 1.4068691342099706e-05, + "loss": 0.0734, + "step": 24973 + }, + { + "epoch": 7.71, + "learning_rate": 1.4068234485786109e-05, + "loss": 0.0717, + "step": 24974 + }, + { + "epoch": 7.71, + "learning_rate": 1.4067777619297116e-05, + "loss": 0.0715, + "step": 24975 + }, + { + "epoch": 7.71, + "learning_rate": 1.406732074263387e-05, + "loss": 0.0696, + "step": 24976 + }, + { + "epoch": 7.71, + "learning_rate": 1.4066863855797512e-05, + "loss": 0.0637, + "step": 24977 + }, + { + "epoch": 7.71, + "learning_rate": 1.4066406958789185e-05, + "loss": 0.0704, + "step": 24978 + }, + { + "epoch": 7.71, + "learning_rate": 1.4065950051610036e-05, + "loss": 0.0668, + "step": 24979 + }, + { + "epoch": 7.71, + "learning_rate": 1.40654931342612e-05, + "loss": 0.0725, + "step": 24980 + }, + { + "epoch": 7.71, + "learning_rate": 1.4065036206743827e-05, + "loss": 0.0732, + "step": 24981 + }, + { + "epoch": 7.71, + "learning_rate": 1.4064579269059055e-05, + "loss": 0.071, + "step": 24982 + }, + { + "epoch": 7.72, + "learning_rate": 1.4064122321208031e-05, + "loss": 0.0729, + "step": 24983 + }, + { + "epoch": 7.72, + "learning_rate": 1.4063665363191895e-05, + "loss": 0.0733, + "step": 24984 + }, + { + "epoch": 7.72, + "learning_rate": 1.4063208395011789e-05, + "loss": 0.0642, + "step": 24985 + }, + { + "epoch": 7.72, + "learning_rate": 1.406275141666886e-05, + "loss": 0.074, + "step": 24986 + }, + { + "epoch": 7.72, + "learning_rate": 1.4062294428164248e-05, + "loss": 0.0743, + "step": 24987 + }, + { + "epoch": 7.72, + "learning_rate": 1.4061837429499097e-05, + "loss": 0.0704, + "step": 24988 + }, + { + "epoch": 7.72, + "learning_rate": 1.4061380420674549e-05, + "loss": 0.069, + "step": 24989 + }, + { + "epoch": 7.72, + "learning_rate": 1.4060923401691749e-05, + "loss": 0.0692, + "step": 24990 + }, + { + "epoch": 7.72, + "learning_rate": 1.4060466372551837e-05, + "loss": 0.0753, + "step": 24991 + }, + { + "epoch": 7.72, + "learning_rate": 1.4060009333255959e-05, + "loss": 0.075, + "step": 24992 + }, + { + "epoch": 7.72, + "learning_rate": 1.4059552283805257e-05, + "loss": 0.0719, + "step": 24993 + }, + { + "epoch": 7.72, + "learning_rate": 1.4059095224200877e-05, + "loss": 0.0716, + "step": 24994 + }, + { + "epoch": 7.72, + "learning_rate": 1.4058638154443956e-05, + "loss": 0.0771, + "step": 24995 + }, + { + "epoch": 7.72, + "learning_rate": 1.4058181074535642e-05, + "loss": 0.0752, + "step": 24996 + }, + { + "epoch": 7.72, + "learning_rate": 1.405772398447708e-05, + "loss": 0.0712, + "step": 24997 + }, + { + "epoch": 7.72, + "learning_rate": 1.4057266884269402e-05, + "loss": 0.0704, + "step": 24998 + }, + { + "epoch": 7.72, + "learning_rate": 1.4056809773913767e-05, + "loss": 0.0689, + "step": 24999 + }, + { + "epoch": 7.72, + "learning_rate": 1.4056352653411309e-05, + "loss": 0.0732, + "step": 25000 + }, + { + "epoch": 7.72, + "learning_rate": 1.405589552276317e-05, + "loss": 0.0694, + "step": 25001 + }, + { + "epoch": 7.72, + "learning_rate": 1.40554383819705e-05, + "loss": 0.0729, + "step": 25002 + }, + { + "epoch": 7.72, + "learning_rate": 1.4054981231034436e-05, + "loss": 0.0713, + "step": 25003 + }, + { + "epoch": 7.72, + "learning_rate": 1.405452406995613e-05, + "loss": 0.0702, + "step": 25004 + }, + { + "epoch": 7.72, + "learning_rate": 1.4054066898736716e-05, + "loss": 0.0747, + "step": 25005 + }, + { + "epoch": 7.72, + "learning_rate": 1.405360971737734e-05, + "loss": 0.0724, + "step": 25006 + }, + { + "epoch": 7.72, + "learning_rate": 1.405315252587915e-05, + "loss": 0.0778, + "step": 25007 + }, + { + "epoch": 7.72, + "learning_rate": 1.4052695324243284e-05, + "loss": 0.0747, + "step": 25008 + }, + { + "epoch": 7.72, + "learning_rate": 1.4052238112470888e-05, + "loss": 0.0672, + "step": 25009 + }, + { + "epoch": 7.72, + "learning_rate": 1.4051780890563107e-05, + "loss": 0.0747, + "step": 25010 + }, + { + "epoch": 7.72, + "learning_rate": 1.405132365852108e-05, + "loss": 0.0744, + "step": 25011 + }, + { + "epoch": 7.72, + "learning_rate": 1.4050866416345957e-05, + "loss": 0.0694, + "step": 25012 + }, + { + "epoch": 7.72, + "learning_rate": 1.4050409164038875e-05, + "loss": 0.0758, + "step": 25013 + }, + { + "epoch": 7.72, + "learning_rate": 1.4049951901600985e-05, + "loss": 0.0752, + "step": 25014 + }, + { + "epoch": 7.73, + "learning_rate": 1.4049494629033423e-05, + "loss": 0.0694, + "step": 25015 + }, + { + "epoch": 7.73, + "learning_rate": 1.4049037346337337e-05, + "loss": 0.0733, + "step": 25016 + }, + { + "epoch": 7.73, + "learning_rate": 1.4048580053513871e-05, + "loss": 0.0728, + "step": 25017 + }, + { + "epoch": 7.73, + "learning_rate": 1.4048122750564169e-05, + "loss": 0.0684, + "step": 25018 + }, + { + "epoch": 7.73, + "learning_rate": 1.404766543748937e-05, + "loss": 0.0754, + "step": 25019 + }, + { + "epoch": 7.73, + "learning_rate": 1.4047208114290625e-05, + "loss": 0.0702, + "step": 25020 + }, + { + "epoch": 7.73, + "learning_rate": 1.4046750780969074e-05, + "loss": 0.075, + "step": 25021 + }, + { + "epoch": 7.73, + "learning_rate": 1.404629343752586e-05, + "loss": 0.0717, + "step": 25022 + }, + { + "epoch": 7.73, + "learning_rate": 1.4045836083962128e-05, + "loss": 0.0768, + "step": 25023 + }, + { + "epoch": 7.73, + "learning_rate": 1.4045378720279021e-05, + "loss": 0.0752, + "step": 25024 + }, + { + "epoch": 7.73, + "learning_rate": 1.404492134647769e-05, + "loss": 0.069, + "step": 25025 + }, + { + "epoch": 7.73, + "learning_rate": 1.4044463962559266e-05, + "loss": 0.0658, + "step": 25026 + }, + { + "epoch": 7.73, + "learning_rate": 1.4044006568524902e-05, + "loss": 0.0688, + "step": 25027 + }, + { + "epoch": 7.73, + "learning_rate": 1.404354916437574e-05, + "loss": 0.0665, + "step": 25028 + }, + { + "epoch": 7.73, + "learning_rate": 1.4043091750112923e-05, + "loss": 0.0728, + "step": 25029 + }, + { + "epoch": 7.73, + "learning_rate": 1.40426343257376e-05, + "loss": 0.0765, + "step": 25030 + }, + { + "epoch": 7.73, + "learning_rate": 1.404217689125091e-05, + "loss": 0.0714, + "step": 25031 + }, + { + "epoch": 7.73, + "learning_rate": 1.4041719446653993e-05, + "loss": 0.0704, + "step": 25032 + }, + { + "epoch": 7.73, + "learning_rate": 1.4041261991948005e-05, + "loss": 0.0683, + "step": 25033 + }, + { + "epoch": 7.73, + "learning_rate": 1.404080452713408e-05, + "loss": 0.0825, + "step": 25034 + }, + { + "epoch": 7.73, + "learning_rate": 1.4040347052213368e-05, + "loss": 0.0751, + "step": 25035 + }, + { + "epoch": 7.73, + "learning_rate": 1.4039889567187011e-05, + "loss": 0.0744, + "step": 25036 + }, + { + "epoch": 7.73, + "learning_rate": 1.403943207205615e-05, + "loss": 0.0691, + "step": 25037 + }, + { + "epoch": 7.73, + "learning_rate": 1.4038974566821937e-05, + "loss": 0.0613, + "step": 25038 + }, + { + "epoch": 7.73, + "learning_rate": 1.4038517051485511e-05, + "loss": 0.0772, + "step": 25039 + }, + { + "epoch": 7.73, + "learning_rate": 1.4038059526048016e-05, + "loss": 0.0661, + "step": 25040 + }, + { + "epoch": 7.73, + "learning_rate": 1.4037601990510598e-05, + "loss": 0.0746, + "step": 25041 + }, + { + "epoch": 7.73, + "learning_rate": 1.4037144444874403e-05, + "loss": 0.0718, + "step": 25042 + }, + { + "epoch": 7.73, + "learning_rate": 1.403668688914057e-05, + "loss": 0.0695, + "step": 25043 + }, + { + "epoch": 7.73, + "learning_rate": 1.4036229323310249e-05, + "loss": 0.0673, + "step": 25044 + }, + { + "epoch": 7.73, + "learning_rate": 1.403577174738458e-05, + "loss": 0.061, + "step": 25045 + }, + { + "epoch": 7.73, + "learning_rate": 1.4035314161364712e-05, + "loss": 0.0657, + "step": 25046 + }, + { + "epoch": 7.74, + "learning_rate": 1.4034856565251787e-05, + "loss": 0.0656, + "step": 25047 + }, + { + "epoch": 7.74, + "learning_rate": 1.4034398959046951e-05, + "loss": 0.0675, + "step": 25048 + }, + { + "epoch": 7.74, + "learning_rate": 1.4033941342751345e-05, + "loss": 0.0788, + "step": 25049 + }, + { + "epoch": 7.74, + "learning_rate": 1.4033483716366117e-05, + "loss": 0.0752, + "step": 25050 + }, + { + "epoch": 7.74, + "learning_rate": 1.4033026079892409e-05, + "loss": 0.0699, + "step": 25051 + }, + { + "epoch": 7.74, + "learning_rate": 1.4032568433331369e-05, + "loss": 0.0733, + "step": 25052 + }, + { + "epoch": 7.74, + "learning_rate": 1.4032110776684142e-05, + "loss": 0.0696, + "step": 25053 + }, + { + "epoch": 7.74, + "learning_rate": 1.4031653109951866e-05, + "loss": 0.0735, + "step": 25054 + }, + { + "epoch": 7.74, + "learning_rate": 1.4031195433135692e-05, + "loss": 0.073, + "step": 25055 + }, + { + "epoch": 7.74, + "learning_rate": 1.4030737746236764e-05, + "loss": 0.0775, + "step": 25056 + }, + { + "epoch": 7.74, + "learning_rate": 1.4030280049256223e-05, + "loss": 0.0682, + "step": 25057 + }, + { + "epoch": 7.74, + "learning_rate": 1.4029822342195221e-05, + "loss": 0.0675, + "step": 25058 + }, + { + "epoch": 7.74, + "learning_rate": 1.4029364625054895e-05, + "loss": 0.0667, + "step": 25059 + }, + { + "epoch": 7.74, + "learning_rate": 1.4028906897836395e-05, + "loss": 0.0701, + "step": 25060 + }, + { + "epoch": 7.74, + "learning_rate": 1.4028449160540862e-05, + "loss": 0.0744, + "step": 25061 + }, + { + "epoch": 7.74, + "learning_rate": 1.4027991413169443e-05, + "loss": 0.0734, + "step": 25062 + }, + { + "epoch": 7.74, + "learning_rate": 1.4027533655723286e-05, + "loss": 0.0728, + "step": 25063 + }, + { + "epoch": 7.74, + "learning_rate": 1.4027075888203529e-05, + "loss": 0.0702, + "step": 25064 + }, + { + "epoch": 7.74, + "learning_rate": 1.4026618110611324e-05, + "loss": 0.0709, + "step": 25065 + }, + { + "epoch": 7.74, + "learning_rate": 1.402616032294781e-05, + "loss": 0.0682, + "step": 25066 + }, + { + "epoch": 7.74, + "learning_rate": 1.4025702525214135e-05, + "loss": 0.0644, + "step": 25067 + }, + { + "epoch": 7.74, + "learning_rate": 1.4025244717411446e-05, + "loss": 0.072, + "step": 25068 + }, + { + "epoch": 7.74, + "learning_rate": 1.4024786899540884e-05, + "loss": 0.0682, + "step": 25069 + }, + { + "epoch": 7.74, + "learning_rate": 1.4024329071603595e-05, + "loss": 0.074, + "step": 25070 + }, + { + "epoch": 7.74, + "learning_rate": 1.4023871233600725e-05, + "loss": 0.0704, + "step": 25071 + }, + { + "epoch": 7.74, + "learning_rate": 1.4023413385533422e-05, + "loss": 0.0726, + "step": 25072 + }, + { + "epoch": 7.74, + "learning_rate": 1.4022955527402826e-05, + "loss": 0.0719, + "step": 25073 + }, + { + "epoch": 7.74, + "learning_rate": 1.4022497659210083e-05, + "loss": 0.0751, + "step": 25074 + }, + { + "epoch": 7.74, + "learning_rate": 1.4022039780956345e-05, + "loss": 0.067, + "step": 25075 + }, + { + "epoch": 7.74, + "learning_rate": 1.4021581892642745e-05, + "loss": 0.0681, + "step": 25076 + }, + { + "epoch": 7.74, + "learning_rate": 1.402112399427044e-05, + "loss": 0.0723, + "step": 25077 + }, + { + "epoch": 7.74, + "learning_rate": 1.402066608584057e-05, + "loss": 0.0701, + "step": 25078 + }, + { + "epoch": 7.74, + "learning_rate": 1.4020208167354281e-05, + "loss": 0.0732, + "step": 25079 + }, + { + "epoch": 7.75, + "learning_rate": 1.4019750238812716e-05, + "loss": 0.0696, + "step": 25080 + }, + { + "epoch": 7.75, + "learning_rate": 1.4019292300217024e-05, + "loss": 0.0636, + "step": 25081 + }, + { + "epoch": 7.75, + "learning_rate": 1.4018834351568348e-05, + "loss": 0.0764, + "step": 25082 + }, + { + "epoch": 7.75, + "learning_rate": 1.4018376392867835e-05, + "loss": 0.0679, + "step": 25083 + }, + { + "epoch": 7.75, + "learning_rate": 1.4017918424116631e-05, + "loss": 0.0767, + "step": 25084 + }, + { + "epoch": 7.75, + "learning_rate": 1.4017460445315878e-05, + "loss": 0.0695, + "step": 25085 + }, + { + "epoch": 7.75, + "learning_rate": 1.4017002456466725e-05, + "loss": 0.0778, + "step": 25086 + }, + { + "epoch": 7.75, + "learning_rate": 1.4016544457570316e-05, + "loss": 0.0702, + "step": 25087 + }, + { + "epoch": 7.75, + "learning_rate": 1.4016086448627795e-05, + "loss": 0.0721, + "step": 25088 + }, + { + "epoch": 7.75, + "learning_rate": 1.4015628429640314e-05, + "loss": 0.0768, + "step": 25089 + }, + { + "epoch": 7.75, + "learning_rate": 1.401517040060901e-05, + "loss": 0.07, + "step": 25090 + }, + { + "epoch": 7.75, + "learning_rate": 1.401471236153503e-05, + "loss": 0.0733, + "step": 25091 + }, + { + "epoch": 7.75, + "learning_rate": 1.4014254312419527e-05, + "loss": 0.0776, + "step": 25092 + }, + { + "epoch": 7.75, + "learning_rate": 1.4013796253263641e-05, + "loss": 0.0653, + "step": 25093 + }, + { + "epoch": 7.75, + "learning_rate": 1.4013338184068517e-05, + "loss": 0.0697, + "step": 25094 + }, + { + "epoch": 7.75, + "learning_rate": 1.4012880104835302e-05, + "loss": 0.0755, + "step": 25095 + }, + { + "epoch": 7.75, + "learning_rate": 1.4012422015565144e-05, + "loss": 0.0715, + "step": 25096 + }, + { + "epoch": 7.75, + "learning_rate": 1.4011963916259186e-05, + "loss": 0.0727, + "step": 25097 + }, + { + "epoch": 7.75, + "learning_rate": 1.4011505806918573e-05, + "loss": 0.0705, + "step": 25098 + }, + { + "epoch": 7.75, + "learning_rate": 1.4011047687544452e-05, + "loss": 0.069, + "step": 25099 + }, + { + "epoch": 7.75, + "learning_rate": 1.4010589558137972e-05, + "loss": 0.0723, + "step": 25100 + }, + { + "epoch": 7.75, + "learning_rate": 1.4010131418700274e-05, + "loss": 0.0739, + "step": 25101 + }, + { + "epoch": 7.75, + "learning_rate": 1.4009673269232507e-05, + "loss": 0.0777, + "step": 25102 + }, + { + "epoch": 7.75, + "learning_rate": 1.4009215109735814e-05, + "loss": 0.0781, + "step": 25103 + }, + { + "epoch": 7.75, + "learning_rate": 1.4008756940211345e-05, + "loss": 0.0722, + "step": 25104 + }, + { + "epoch": 7.75, + "learning_rate": 1.4008298760660241e-05, + "loss": 0.067, + "step": 25105 + }, + { + "epoch": 7.75, + "learning_rate": 1.4007840571083655e-05, + "loss": 0.0797, + "step": 25106 + }, + { + "epoch": 7.75, + "learning_rate": 1.4007382371482728e-05, + "loss": 0.0719, + "step": 25107 + }, + { + "epoch": 7.75, + "learning_rate": 1.4006924161858601e-05, + "loss": 0.0761, + "step": 25108 + }, + { + "epoch": 7.75, + "learning_rate": 1.400646594221243e-05, + "loss": 0.0653, + "step": 25109 + }, + { + "epoch": 7.75, + "learning_rate": 1.4006007712545359e-05, + "loss": 0.0697, + "step": 25110 + }, + { + "epoch": 7.75, + "learning_rate": 1.4005549472858529e-05, + "loss": 0.0697, + "step": 25111 + }, + { + "epoch": 7.76, + "learning_rate": 1.4005091223153091e-05, + "loss": 0.0786, + "step": 25112 + }, + { + "epoch": 7.76, + "learning_rate": 1.400463296343019e-05, + "loss": 0.0742, + "step": 25113 + }, + { + "epoch": 7.76, + "learning_rate": 1.4004174693690966e-05, + "loss": 0.0729, + "step": 25114 + }, + { + "epoch": 7.76, + "learning_rate": 1.4003716413936577e-05, + "loss": 0.068, + "step": 25115 + }, + { + "epoch": 7.76, + "learning_rate": 1.400325812416816e-05, + "loss": 0.0724, + "step": 25116 + }, + { + "epoch": 7.76, + "learning_rate": 1.4002799824386867e-05, + "loss": 0.0776, + "step": 25117 + }, + { + "epoch": 7.76, + "learning_rate": 1.400234151459384e-05, + "loss": 0.0664, + "step": 25118 + }, + { + "epoch": 7.76, + "learning_rate": 1.4001883194790225e-05, + "loss": 0.0703, + "step": 25119 + }, + { + "epoch": 7.76, + "learning_rate": 1.4001424864977173e-05, + "loss": 0.0686, + "step": 25120 + }, + { + "epoch": 7.76, + "learning_rate": 1.4000966525155825e-05, + "loss": 0.073, + "step": 25121 + }, + { + "epoch": 7.76, + "learning_rate": 1.4000508175327332e-05, + "loss": 0.0636, + "step": 25122 + }, + { + "epoch": 7.76, + "learning_rate": 1.4000049815492837e-05, + "loss": 0.0695, + "step": 25123 + }, + { + "epoch": 7.76, + "learning_rate": 1.3999591445653491e-05, + "loss": 0.077, + "step": 25124 + }, + { + "epoch": 7.76, + "learning_rate": 1.3999133065810435e-05, + "loss": 0.0637, + "step": 25125 + }, + { + "epoch": 7.76, + "learning_rate": 1.3998674675964815e-05, + "loss": 0.0762, + "step": 25126 + }, + { + "epoch": 7.76, + "learning_rate": 1.3998216276117784e-05, + "loss": 0.0723, + "step": 25127 + }, + { + "epoch": 7.76, + "learning_rate": 1.3997757866270484e-05, + "loss": 0.0723, + "step": 25128 + }, + { + "epoch": 7.76, + "learning_rate": 1.3997299446424064e-05, + "loss": 0.076, + "step": 25129 + }, + { + "epoch": 7.76, + "learning_rate": 1.3996841016579667e-05, + "loss": 0.0776, + "step": 25130 + }, + { + "epoch": 7.76, + "learning_rate": 1.3996382576738441e-05, + "loss": 0.0702, + "step": 25131 + }, + { + "epoch": 7.76, + "learning_rate": 1.3995924126901534e-05, + "loss": 0.0681, + "step": 25132 + }, + { + "epoch": 7.76, + "learning_rate": 1.3995465667070094e-05, + "loss": 0.072, + "step": 25133 + }, + { + "epoch": 7.76, + "learning_rate": 1.3995007197245262e-05, + "loss": 0.0739, + "step": 25134 + }, + { + "epoch": 7.76, + "learning_rate": 1.3994548717428191e-05, + "loss": 0.0734, + "step": 25135 + }, + { + "epoch": 7.76, + "learning_rate": 1.3994090227620025e-05, + "loss": 0.0799, + "step": 25136 + }, + { + "epoch": 7.76, + "learning_rate": 1.399363172782191e-05, + "loss": 0.0739, + "step": 25137 + }, + { + "epoch": 7.76, + "learning_rate": 1.3993173218034994e-05, + "loss": 0.07, + "step": 25138 + }, + { + "epoch": 7.76, + "learning_rate": 1.3992714698260423e-05, + "loss": 0.0671, + "step": 25139 + }, + { + "epoch": 7.76, + "learning_rate": 1.3992256168499344e-05, + "loss": 0.0703, + "step": 25140 + }, + { + "epoch": 7.76, + "learning_rate": 1.3991797628752908e-05, + "loss": 0.065, + "step": 25141 + }, + { + "epoch": 7.76, + "learning_rate": 1.3991339079022253e-05, + "loss": 0.0717, + "step": 25142 + }, + { + "epoch": 7.76, + "learning_rate": 1.3990880519308535e-05, + "loss": 0.0644, + "step": 25143 + }, + { + "epoch": 7.77, + "learning_rate": 1.3990421949612894e-05, + "loss": 0.0766, + "step": 25144 + }, + { + "epoch": 7.77, + "learning_rate": 1.3989963369936478e-05, + "loss": 0.0637, + "step": 25145 + }, + { + "epoch": 7.77, + "learning_rate": 1.398950478028044e-05, + "loss": 0.0647, + "step": 25146 + }, + { + "epoch": 7.77, + "learning_rate": 1.3989046180645922e-05, + "loss": 0.0683, + "step": 25147 + }, + { + "epoch": 7.77, + "learning_rate": 1.3988587571034071e-05, + "loss": 0.075, + "step": 25148 + }, + { + "epoch": 7.77, + "learning_rate": 1.3988128951446035e-05, + "loss": 0.068, + "step": 25149 + }, + { + "epoch": 7.77, + "learning_rate": 1.398767032188296e-05, + "loss": 0.0758, + "step": 25150 + }, + { + "epoch": 7.77, + "learning_rate": 1.3987211682345997e-05, + "loss": 0.0709, + "step": 25151 + }, + { + "epoch": 7.77, + "learning_rate": 1.398675303283629e-05, + "loss": 0.0715, + "step": 25152 + }, + { + "epoch": 7.77, + "learning_rate": 1.3986294373354986e-05, + "loss": 0.0705, + "step": 25153 + }, + { + "epoch": 7.77, + "learning_rate": 1.3985835703903232e-05, + "loss": 0.0775, + "step": 25154 + }, + { + "epoch": 7.77, + "learning_rate": 1.3985377024482177e-05, + "loss": 0.0749, + "step": 25155 + }, + { + "epoch": 7.77, + "learning_rate": 1.3984918335092968e-05, + "loss": 0.0676, + "step": 25156 + }, + { + "epoch": 7.77, + "learning_rate": 1.398445963573675e-05, + "loss": 0.0641, + "step": 25157 + }, + { + "epoch": 7.77, + "learning_rate": 1.3984000926414671e-05, + "loss": 0.0722, + "step": 25158 + }, + { + "epoch": 7.77, + "learning_rate": 1.3983542207127878e-05, + "loss": 0.0645, + "step": 25159 + }, + { + "epoch": 7.77, + "learning_rate": 1.3983083477877522e-05, + "loss": 0.0764, + "step": 25160 + }, + { + "epoch": 7.77, + "learning_rate": 1.398262473866475e-05, + "loss": 0.0673, + "step": 25161 + }, + { + "epoch": 7.77, + "learning_rate": 1.3982165989490701e-05, + "loss": 0.0728, + "step": 25162 + }, + { + "epoch": 7.77, + "learning_rate": 1.3981707230356532e-05, + "loss": 0.0708, + "step": 25163 + }, + { + "epoch": 7.77, + "learning_rate": 1.3981248461263388e-05, + "loss": 0.0805, + "step": 25164 + }, + { + "epoch": 7.77, + "learning_rate": 1.3980789682212413e-05, + "loss": 0.067, + "step": 25165 + }, + { + "epoch": 7.77, + "learning_rate": 1.3980330893204758e-05, + "loss": 0.0774, + "step": 25166 + }, + { + "epoch": 7.77, + "learning_rate": 1.3979872094241568e-05, + "loss": 0.0835, + "step": 25167 + }, + { + "epoch": 7.77, + "learning_rate": 1.3979413285323993e-05, + "loss": 0.079, + "step": 25168 + }, + { + "epoch": 7.77, + "learning_rate": 1.3978954466453182e-05, + "loss": 0.0696, + "step": 25169 + }, + { + "epoch": 7.77, + "learning_rate": 1.3978495637630277e-05, + "loss": 0.074, + "step": 25170 + }, + { + "epoch": 7.77, + "learning_rate": 1.3978036798856431e-05, + "loss": 0.0736, + "step": 25171 + }, + { + "epoch": 7.77, + "learning_rate": 1.3977577950132788e-05, + "loss": 0.0754, + "step": 25172 + }, + { + "epoch": 7.77, + "learning_rate": 1.3977119091460496e-05, + "loss": 0.0689, + "step": 25173 + }, + { + "epoch": 7.77, + "learning_rate": 1.3976660222840708e-05, + "loss": 0.0742, + "step": 25174 + }, + { + "epoch": 7.77, + "learning_rate": 1.3976201344274564e-05, + "loss": 0.0756, + "step": 25175 + }, + { + "epoch": 7.77, + "learning_rate": 1.3975742455763217e-05, + "loss": 0.0678, + "step": 25176 + }, + { + "epoch": 7.78, + "learning_rate": 1.3975283557307813e-05, + "loss": 0.0733, + "step": 25177 + }, + { + "epoch": 7.78, + "learning_rate": 1.3974824648909497e-05, + "loss": 0.0732, + "step": 25178 + }, + { + "epoch": 7.78, + "learning_rate": 1.397436573056942e-05, + "loss": 0.0695, + "step": 25179 + }, + { + "epoch": 7.78, + "learning_rate": 1.3973906802288733e-05, + "loss": 0.0735, + "step": 25180 + }, + { + "epoch": 7.78, + "learning_rate": 1.3973447864068575e-05, + "loss": 0.0776, + "step": 25181 + }, + { + "epoch": 7.78, + "learning_rate": 1.3972988915910104e-05, + "loss": 0.0694, + "step": 25182 + }, + { + "epoch": 7.78, + "learning_rate": 1.3972529957814462e-05, + "loss": 0.0725, + "step": 25183 + }, + { + "epoch": 7.78, + "learning_rate": 1.3972070989782797e-05, + "loss": 0.0709, + "step": 25184 + }, + { + "epoch": 7.78, + "learning_rate": 1.3971612011816258e-05, + "loss": 0.0744, + "step": 25185 + }, + { + "epoch": 7.78, + "learning_rate": 1.3971153023915993e-05, + "loss": 0.0644, + "step": 25186 + }, + { + "epoch": 7.78, + "learning_rate": 1.3970694026083152e-05, + "loss": 0.0682, + "step": 25187 + }, + { + "epoch": 7.78, + "learning_rate": 1.3970235018318878e-05, + "loss": 0.0785, + "step": 25188 + }, + { + "epoch": 7.78, + "learning_rate": 1.3969776000624325e-05, + "loss": 0.079, + "step": 25189 + }, + { + "epoch": 7.78, + "learning_rate": 1.3969316973000635e-05, + "loss": 0.0742, + "step": 25190 + }, + { + "epoch": 7.78, + "learning_rate": 1.396885793544896e-05, + "loss": 0.0751, + "step": 25191 + }, + { + "epoch": 7.78, + "learning_rate": 1.396839888797045e-05, + "loss": 0.0821, + "step": 25192 + }, + { + "epoch": 7.78, + "learning_rate": 1.3967939830566248e-05, + "loss": 0.067, + "step": 25193 + }, + { + "epoch": 7.78, + "learning_rate": 1.3967480763237506e-05, + "loss": 0.0666, + "step": 25194 + }, + { + "epoch": 7.78, + "learning_rate": 1.3967021685985373e-05, + "loss": 0.0805, + "step": 25195 + }, + { + "epoch": 7.78, + "learning_rate": 1.3966562598810991e-05, + "loss": 0.0679, + "step": 25196 + }, + { + "epoch": 7.78, + "learning_rate": 1.3966103501715516e-05, + "loss": 0.0717, + "step": 25197 + }, + { + "epoch": 7.78, + "learning_rate": 1.3965644394700088e-05, + "loss": 0.0721, + "step": 25198 + }, + { + "epoch": 7.78, + "learning_rate": 1.3965185277765865e-05, + "loss": 0.0663, + "step": 25199 + }, + { + "epoch": 7.78, + "learning_rate": 1.396472615091399e-05, + "loss": 0.069, + "step": 25200 + }, + { + "epoch": 7.78, + "learning_rate": 1.3964267014145607e-05, + "loss": 0.0787, + "step": 25201 + }, + { + "epoch": 7.78, + "learning_rate": 1.3963807867461877e-05, + "loss": 0.0687, + "step": 25202 + }, + { + "epoch": 7.78, + "learning_rate": 1.3963348710863936e-05, + "loss": 0.0787, + "step": 25203 + }, + { + "epoch": 7.78, + "learning_rate": 1.3962889544352933e-05, + "loss": 0.068, + "step": 25204 + }, + { + "epoch": 7.78, + "learning_rate": 1.3962430367930027e-05, + "loss": 0.0683, + "step": 25205 + }, + { + "epoch": 7.78, + "learning_rate": 1.396197118159636e-05, + "loss": 0.0767, + "step": 25206 + }, + { + "epoch": 7.78, + "learning_rate": 1.3961511985353075e-05, + "loss": 0.0696, + "step": 25207 + }, + { + "epoch": 7.78, + "learning_rate": 1.3961052779201329e-05, + "loss": 0.0719, + "step": 25208 + }, + { + "epoch": 7.79, + "learning_rate": 1.3960593563142268e-05, + "loss": 0.0749, + "step": 25209 + }, + { + "epoch": 7.79, + "learning_rate": 1.396013433717704e-05, + "loss": 0.0704, + "step": 25210 + }, + { + "epoch": 7.79, + "learning_rate": 1.3959675101306793e-05, + "loss": 0.0697, + "step": 25211 + }, + { + "epoch": 7.79, + "learning_rate": 1.3959215855532677e-05, + "loss": 0.0747, + "step": 25212 + }, + { + "epoch": 7.79, + "learning_rate": 1.395875659985584e-05, + "loss": 0.0735, + "step": 25213 + }, + { + "epoch": 7.79, + "learning_rate": 1.3958297334277431e-05, + "loss": 0.0725, + "step": 25214 + }, + { + "epoch": 7.79, + "learning_rate": 1.3957838058798599e-05, + "loss": 0.065, + "step": 25215 + }, + { + "epoch": 7.79, + "learning_rate": 1.395737877342049e-05, + "loss": 0.0786, + "step": 25216 + }, + { + "epoch": 7.79, + "learning_rate": 1.3956919478144255e-05, + "loss": 0.0692, + "step": 25217 + }, + { + "epoch": 7.79, + "learning_rate": 1.3956460172971045e-05, + "loss": 0.0773, + "step": 25218 + }, + { + "epoch": 7.79, + "learning_rate": 1.3956000857902006e-05, + "loss": 0.0732, + "step": 25219 + }, + { + "epoch": 7.79, + "learning_rate": 1.3955541532938286e-05, + "loss": 0.0697, + "step": 25220 + }, + { + "epoch": 7.79, + "learning_rate": 1.3955082198081035e-05, + "loss": 0.0726, + "step": 25221 + }, + { + "epoch": 7.79, + "learning_rate": 1.3954622853331403e-05, + "loss": 0.0755, + "step": 25222 + }, + { + "epoch": 7.79, + "learning_rate": 1.3954163498690539e-05, + "loss": 0.0746, + "step": 25223 + }, + { + "epoch": 7.79, + "learning_rate": 1.3953704134159588e-05, + "loss": 0.0751, + "step": 25224 + }, + { + "epoch": 7.79, + "learning_rate": 1.3953244759739703e-05, + "loss": 0.0668, + "step": 25225 + }, + { + "epoch": 7.79, + "learning_rate": 1.3952785375432036e-05, + "loss": 0.0714, + "step": 25226 + }, + { + "epoch": 7.79, + "learning_rate": 1.3952325981237724e-05, + "loss": 0.0692, + "step": 25227 + }, + { + "epoch": 7.79, + "learning_rate": 1.3951866577157931e-05, + "loss": 0.074, + "step": 25228 + }, + { + "epoch": 7.79, + "learning_rate": 1.3951407163193795e-05, + "loss": 0.0653, + "step": 25229 + }, + { + "epoch": 7.79, + "learning_rate": 1.395094773934647e-05, + "loss": 0.0757, + "step": 25230 + }, + { + "epoch": 7.79, + "learning_rate": 1.3950488305617104e-05, + "loss": 0.0685, + "step": 25231 + }, + { + "epoch": 7.79, + "learning_rate": 1.3950028862006845e-05, + "loss": 0.0744, + "step": 25232 + }, + { + "epoch": 7.79, + "learning_rate": 1.3949569408516848e-05, + "loss": 0.072, + "step": 25233 + }, + { + "epoch": 7.79, + "learning_rate": 1.3949109945148254e-05, + "loss": 0.0732, + "step": 25234 + }, + { + "epoch": 7.79, + "learning_rate": 1.3948650471902215e-05, + "loss": 0.0782, + "step": 25235 + }, + { + "epoch": 7.79, + "learning_rate": 1.3948190988779881e-05, + "loss": 0.072, + "step": 25236 + }, + { + "epoch": 7.79, + "learning_rate": 1.3947731495782404e-05, + "loss": 0.0669, + "step": 25237 + }, + { + "epoch": 7.79, + "learning_rate": 1.3947271992910927e-05, + "loss": 0.0692, + "step": 25238 + }, + { + "epoch": 7.79, + "learning_rate": 1.3946812480166604e-05, + "loss": 0.0676, + "step": 25239 + }, + { + "epoch": 7.79, + "learning_rate": 1.3946352957550584e-05, + "loss": 0.0653, + "step": 25240 + }, + { + "epoch": 7.79, + "learning_rate": 1.3945893425064014e-05, + "loss": 0.0725, + "step": 25241 + }, + { + "epoch": 7.8, + "learning_rate": 1.3945433882708048e-05, + "loss": 0.0766, + "step": 25242 + }, + { + "epoch": 7.8, + "learning_rate": 1.394497433048383e-05, + "loss": 0.0683, + "step": 25243 + }, + { + "epoch": 7.8, + "learning_rate": 1.3944514768392511e-05, + "loss": 0.0656, + "step": 25244 + }, + { + "epoch": 7.8, + "learning_rate": 1.3944055196435243e-05, + "loss": 0.0701, + "step": 25245 + }, + { + "epoch": 7.8, + "learning_rate": 1.3943595614613172e-05, + "loss": 0.0745, + "step": 25246 + }, + { + "epoch": 7.8, + "learning_rate": 1.3943136022927451e-05, + "loss": 0.072, + "step": 25247 + }, + { + "epoch": 7.8, + "learning_rate": 1.3942676421379224e-05, + "loss": 0.0719, + "step": 25248 + }, + { + "epoch": 7.8, + "learning_rate": 1.3942216809969646e-05, + "loss": 0.0734, + "step": 25249 + }, + { + "epoch": 7.8, + "learning_rate": 1.3941757188699867e-05, + "loss": 0.07, + "step": 25250 + }, + { + "epoch": 7.8, + "learning_rate": 1.3941297557571033e-05, + "loss": 0.0746, + "step": 25251 + }, + { + "epoch": 7.8, + "learning_rate": 1.3940837916584293e-05, + "loss": 0.0728, + "step": 25252 + }, + { + "epoch": 7.8, + "learning_rate": 1.3940378265740801e-05, + "loss": 0.0694, + "step": 25253 + }, + { + "epoch": 7.8, + "learning_rate": 1.3939918605041705e-05, + "loss": 0.0672, + "step": 25254 + }, + { + "epoch": 7.8, + "learning_rate": 1.393945893448815e-05, + "loss": 0.081, + "step": 25255 + }, + { + "epoch": 7.8, + "learning_rate": 1.3938999254081296e-05, + "loss": 0.0796, + "step": 25256 + }, + { + "epoch": 7.8, + "learning_rate": 1.3938539563822283e-05, + "loss": 0.0654, + "step": 25257 + }, + { + "epoch": 7.8, + "learning_rate": 1.393807986371226e-05, + "loss": 0.0673, + "step": 25258 + }, + { + "epoch": 7.8, + "learning_rate": 1.3937620153752387e-05, + "loss": 0.0707, + "step": 25259 + }, + { + "epoch": 7.8, + "learning_rate": 1.3937160433943807e-05, + "loss": 0.0698, + "step": 25260 + }, + { + "epoch": 7.8, + "learning_rate": 1.3936700704287667e-05, + "loss": 0.0793, + "step": 25261 + }, + { + "epoch": 7.8, + "learning_rate": 1.3936240964785125e-05, + "loss": 0.076, + "step": 25262 + }, + { + "epoch": 7.8, + "learning_rate": 1.393578121543732e-05, + "loss": 0.0741, + "step": 25263 + }, + { + "epoch": 7.8, + "learning_rate": 1.3935321456245414e-05, + "loss": 0.0754, + "step": 25264 + }, + { + "epoch": 7.8, + "learning_rate": 1.393486168721055e-05, + "loss": 0.0651, + "step": 25265 + }, + { + "epoch": 7.8, + "learning_rate": 1.3934401908333878e-05, + "loss": 0.0787, + "step": 25266 + }, + { + "epoch": 7.8, + "learning_rate": 1.3933942119616553e-05, + "loss": 0.0655, + "step": 25267 + }, + { + "epoch": 7.8, + "learning_rate": 1.3933482321059718e-05, + "loss": 0.0721, + "step": 25268 + }, + { + "epoch": 7.8, + "learning_rate": 1.3933022512664525e-05, + "loss": 0.0695, + "step": 25269 + }, + { + "epoch": 7.8, + "learning_rate": 1.3932562694432127e-05, + "loss": 0.0729, + "step": 25270 + }, + { + "epoch": 7.8, + "learning_rate": 1.3932102866363674e-05, + "loss": 0.0683, + "step": 25271 + }, + { + "epoch": 7.8, + "learning_rate": 1.3931643028460314e-05, + "loss": 0.0711, + "step": 25272 + }, + { + "epoch": 7.8, + "learning_rate": 1.3931183180723195e-05, + "loss": 0.0713, + "step": 25273 + }, + { + "epoch": 7.81, + "learning_rate": 1.3930723323153473e-05, + "loss": 0.0668, + "step": 25274 + }, + { + "epoch": 7.81, + "learning_rate": 1.3930263455752293e-05, + "loss": 0.0712, + "step": 25275 + }, + { + "epoch": 7.81, + "learning_rate": 1.392980357852081e-05, + "loss": 0.07, + "step": 25276 + }, + { + "epoch": 7.81, + "learning_rate": 1.392934369146017e-05, + "loss": 0.0743, + "step": 25277 + }, + { + "epoch": 7.81, + "learning_rate": 1.3928883794571521e-05, + "loss": 0.0708, + "step": 25278 + }, + { + "epoch": 7.81, + "learning_rate": 1.3928423887856022e-05, + "loss": 0.0704, + "step": 25279 + }, + { + "epoch": 7.81, + "learning_rate": 1.3927963971314817e-05, + "loss": 0.0746, + "step": 25280 + }, + { + "epoch": 7.81, + "learning_rate": 1.3927504044949056e-05, + "loss": 0.0674, + "step": 25281 + }, + { + "epoch": 7.81, + "learning_rate": 1.3927044108759895e-05, + "loss": 0.0598, + "step": 25282 + }, + { + "epoch": 7.81, + "learning_rate": 1.3926584162748476e-05, + "loss": 0.0758, + "step": 25283 + }, + { + "epoch": 7.81, + "learning_rate": 1.3926124206915957e-05, + "loss": 0.0699, + "step": 25284 + }, + { + "epoch": 7.81, + "learning_rate": 1.3925664241263484e-05, + "loss": 0.0732, + "step": 25285 + }, + { + "epoch": 7.81, + "learning_rate": 1.3925204265792208e-05, + "loss": 0.0752, + "step": 25286 + }, + { + "epoch": 7.81, + "learning_rate": 1.3924744280503281e-05, + "loss": 0.0741, + "step": 25287 + }, + { + "epoch": 7.81, + "learning_rate": 1.3924284285397853e-05, + "loss": 0.0715, + "step": 25288 + }, + { + "epoch": 7.81, + "learning_rate": 1.3923824280477072e-05, + "loss": 0.0662, + "step": 25289 + }, + { + "epoch": 7.81, + "learning_rate": 1.3923364265742097e-05, + "loss": 0.0708, + "step": 25290 + }, + { + "epoch": 7.81, + "learning_rate": 1.3922904241194066e-05, + "loss": 0.0683, + "step": 25291 + }, + { + "epoch": 7.81, + "learning_rate": 1.3922444206834139e-05, + "loss": 0.0684, + "step": 25292 + }, + { + "epoch": 7.81, + "learning_rate": 1.3921984162663463e-05, + "loss": 0.0688, + "step": 25293 + }, + { + "epoch": 7.81, + "learning_rate": 1.3921524108683188e-05, + "loss": 0.0696, + "step": 25294 + }, + { + "epoch": 7.81, + "learning_rate": 1.3921064044894469e-05, + "loss": 0.0714, + "step": 25295 + }, + { + "epoch": 7.81, + "learning_rate": 1.3920603971298449e-05, + "loss": 0.0685, + "step": 25296 + }, + { + "epoch": 7.81, + "learning_rate": 1.3920143887896287e-05, + "loss": 0.0717, + "step": 25297 + }, + { + "epoch": 7.81, + "learning_rate": 1.391968379468913e-05, + "loss": 0.0688, + "step": 25298 + }, + { + "epoch": 7.81, + "learning_rate": 1.3919223691678128e-05, + "loss": 0.0712, + "step": 25299 + }, + { + "epoch": 7.81, + "learning_rate": 1.3918763578864432e-05, + "loss": 0.0747, + "step": 25300 + }, + { + "epoch": 7.81, + "learning_rate": 1.3918303456249196e-05, + "loss": 0.0676, + "step": 25301 + }, + { + "epoch": 7.81, + "learning_rate": 1.3917843323833566e-05, + "loss": 0.0721, + "step": 25302 + }, + { + "epoch": 7.81, + "learning_rate": 1.3917383181618696e-05, + "loss": 0.0705, + "step": 25303 + }, + { + "epoch": 7.81, + "learning_rate": 1.3916923029605736e-05, + "loss": 0.0668, + "step": 25304 + }, + { + "epoch": 7.81, + "learning_rate": 1.391646286779584e-05, + "loss": 0.0749, + "step": 25305 + }, + { + "epoch": 7.82, + "learning_rate": 1.3916002696190151e-05, + "loss": 0.0726, + "step": 25306 + }, + { + "epoch": 7.82, + "learning_rate": 1.3915542514789828e-05, + "loss": 0.0736, + "step": 25307 + }, + { + "epoch": 7.82, + "learning_rate": 1.391508232359602e-05, + "loss": 0.0714, + "step": 25308 + }, + { + "epoch": 7.82, + "learning_rate": 1.3914622122609873e-05, + "loss": 0.0735, + "step": 25309 + }, + { + "epoch": 7.82, + "learning_rate": 1.3914161911832546e-05, + "loss": 0.073, + "step": 25310 + }, + { + "epoch": 7.82, + "learning_rate": 1.3913701691265184e-05, + "loss": 0.0768, + "step": 25311 + }, + { + "epoch": 7.82, + "learning_rate": 1.3913241460908941e-05, + "loss": 0.07, + "step": 25312 + }, + { + "epoch": 7.82, + "learning_rate": 1.3912781220764968e-05, + "loss": 0.0715, + "step": 25313 + }, + { + "epoch": 7.82, + "learning_rate": 1.3912320970834414e-05, + "loss": 0.0682, + "step": 25314 + }, + { + "epoch": 7.82, + "learning_rate": 1.3911860711118434e-05, + "loss": 0.0672, + "step": 25315 + }, + { + "epoch": 7.82, + "learning_rate": 1.3911400441618175e-05, + "loss": 0.0767, + "step": 25316 + }, + { + "epoch": 7.82, + "learning_rate": 1.391094016233479e-05, + "loss": 0.075, + "step": 25317 + }, + { + "epoch": 7.82, + "learning_rate": 1.3910479873269433e-05, + "loss": 0.071, + "step": 25318 + }, + { + "epoch": 7.82, + "learning_rate": 1.391001957442325e-05, + "loss": 0.0729, + "step": 25319 + }, + { + "epoch": 7.82, + "learning_rate": 1.3909559265797397e-05, + "loss": 0.0664, + "step": 25320 + }, + { + "epoch": 7.82, + "learning_rate": 1.390909894739302e-05, + "loss": 0.0695, + "step": 25321 + }, + { + "epoch": 7.82, + "learning_rate": 1.3908638619211274e-05, + "loss": 0.0744, + "step": 25322 + }, + { + "epoch": 7.82, + "learning_rate": 1.3908178281253312e-05, + "loss": 0.0734, + "step": 25323 + }, + { + "epoch": 7.82, + "learning_rate": 1.3907717933520282e-05, + "loss": 0.0748, + "step": 25324 + }, + { + "epoch": 7.82, + "learning_rate": 1.3907257576013338e-05, + "loss": 0.0733, + "step": 25325 + }, + { + "epoch": 7.82, + "learning_rate": 1.3906797208733628e-05, + "loss": 0.0706, + "step": 25326 + }, + { + "epoch": 7.82, + "learning_rate": 1.3906336831682308e-05, + "loss": 0.0716, + "step": 25327 + }, + { + "epoch": 7.82, + "learning_rate": 1.3905876444860526e-05, + "loss": 0.0731, + "step": 25328 + }, + { + "epoch": 7.82, + "learning_rate": 1.3905416048269436e-05, + "loss": 0.0702, + "step": 25329 + }, + { + "epoch": 7.82, + "learning_rate": 1.3904955641910185e-05, + "loss": 0.0703, + "step": 25330 + }, + { + "epoch": 7.82, + "learning_rate": 1.390449522578393e-05, + "loss": 0.0687, + "step": 25331 + }, + { + "epoch": 7.82, + "learning_rate": 1.3904034799891819e-05, + "loss": 0.0721, + "step": 25332 + }, + { + "epoch": 7.82, + "learning_rate": 1.3903574364235008e-05, + "loss": 0.0654, + "step": 25333 + }, + { + "epoch": 7.82, + "learning_rate": 1.3903113918814644e-05, + "loss": 0.0772, + "step": 25334 + }, + { + "epoch": 7.82, + "learning_rate": 1.3902653463631879e-05, + "loss": 0.0671, + "step": 25335 + }, + { + "epoch": 7.82, + "learning_rate": 1.3902192998687866e-05, + "loss": 0.0717, + "step": 25336 + }, + { + "epoch": 7.82, + "learning_rate": 1.3901732523983755e-05, + "loss": 0.0681, + "step": 25337 + }, + { + "epoch": 7.82, + "learning_rate": 1.3901272039520704e-05, + "loss": 0.0683, + "step": 25338 + }, + { + "epoch": 7.83, + "learning_rate": 1.3900811545299858e-05, + "loss": 0.0719, + "step": 25339 + }, + { + "epoch": 7.83, + "learning_rate": 1.390035104132237e-05, + "loss": 0.0701, + "step": 25340 + }, + { + "epoch": 7.83, + "learning_rate": 1.3899890527589394e-05, + "loss": 0.0757, + "step": 25341 + }, + { + "epoch": 7.83, + "learning_rate": 1.3899430004102079e-05, + "loss": 0.0702, + "step": 25342 + }, + { + "epoch": 7.83, + "learning_rate": 1.3898969470861575e-05, + "loss": 0.0715, + "step": 25343 + }, + { + "epoch": 7.83, + "learning_rate": 1.3898508927869045e-05, + "loss": 0.0728, + "step": 25344 + }, + { + "epoch": 7.83, + "learning_rate": 1.3898048375125628e-05, + "loss": 0.0724, + "step": 25345 + }, + { + "epoch": 7.83, + "learning_rate": 1.3897587812632483e-05, + "loss": 0.0817, + "step": 25346 + }, + { + "epoch": 7.83, + "learning_rate": 1.389712724039076e-05, + "loss": 0.0761, + "step": 25347 + }, + { + "epoch": 7.83, + "learning_rate": 1.3896666658401607e-05, + "loss": 0.076, + "step": 25348 + }, + { + "epoch": 7.83, + "learning_rate": 1.3896206066666186e-05, + "loss": 0.0754, + "step": 25349 + }, + { + "epoch": 7.83, + "learning_rate": 1.3895745465185639e-05, + "loss": 0.0686, + "step": 25350 + }, + { + "epoch": 7.83, + "learning_rate": 1.3895284853961125e-05, + "loss": 0.0651, + "step": 25351 + }, + { + "epoch": 7.83, + "learning_rate": 1.3894824232993792e-05, + "loss": 0.0743, + "step": 25352 + }, + { + "epoch": 7.83, + "learning_rate": 1.389436360228479e-05, + "loss": 0.0733, + "step": 25353 + }, + { + "epoch": 7.83, + "learning_rate": 1.3893902961835278e-05, + "loss": 0.0766, + "step": 25354 + }, + { + "epoch": 7.83, + "learning_rate": 1.3893442311646403e-05, + "loss": 0.0746, + "step": 25355 + }, + { + "epoch": 7.83, + "learning_rate": 1.389298165171932e-05, + "loss": 0.0691, + "step": 25356 + }, + { + "epoch": 7.83, + "learning_rate": 1.3892520982055177e-05, + "loss": 0.0732, + "step": 25357 + }, + { + "epoch": 7.83, + "learning_rate": 1.3892060302655132e-05, + "loss": 0.0672, + "step": 25358 + }, + { + "epoch": 7.83, + "learning_rate": 1.3891599613520334e-05, + "loss": 0.0685, + "step": 25359 + }, + { + "epoch": 7.83, + "learning_rate": 1.3891138914651934e-05, + "loss": 0.0729, + "step": 25360 + }, + { + "epoch": 7.83, + "learning_rate": 1.3890678206051087e-05, + "loss": 0.0721, + "step": 25361 + }, + { + "epoch": 7.83, + "learning_rate": 1.3890217487718945e-05, + "loss": 0.0709, + "step": 25362 + }, + { + "epoch": 7.83, + "learning_rate": 1.3889756759656659e-05, + "loss": 0.0684, + "step": 25363 + }, + { + "epoch": 7.83, + "learning_rate": 1.3889296021865381e-05, + "loss": 0.0671, + "step": 25364 + }, + { + "epoch": 7.83, + "learning_rate": 1.3888835274346264e-05, + "loss": 0.0749, + "step": 25365 + }, + { + "epoch": 7.83, + "learning_rate": 1.388837451710046e-05, + "loss": 0.0722, + "step": 25366 + }, + { + "epoch": 7.83, + "learning_rate": 1.3887913750129127e-05, + "loss": 0.071, + "step": 25367 + }, + { + "epoch": 7.83, + "learning_rate": 1.3887452973433406e-05, + "loss": 0.0774, + "step": 25368 + }, + { + "epoch": 7.83, + "learning_rate": 1.3886992187014464e-05, + "loss": 0.072, + "step": 25369 + }, + { + "epoch": 7.83, + "learning_rate": 1.388653139087344e-05, + "loss": 0.0723, + "step": 25370 + }, + { + "epoch": 7.84, + "learning_rate": 1.3886070585011488e-05, + "loss": 0.0694, + "step": 25371 + }, + { + "epoch": 7.84, + "learning_rate": 1.3885609769429773e-05, + "loss": 0.0767, + "step": 25372 + }, + { + "epoch": 7.84, + "learning_rate": 1.3885148944129437e-05, + "loss": 0.0705, + "step": 25373 + }, + { + "epoch": 7.84, + "learning_rate": 1.3884688109111633e-05, + "loss": 0.0795, + "step": 25374 + }, + { + "epoch": 7.84, + "learning_rate": 1.3884227264377516e-05, + "loss": 0.0674, + "step": 25375 + }, + { + "epoch": 7.84, + "learning_rate": 1.3883766409928238e-05, + "loss": 0.0695, + "step": 25376 + }, + { + "epoch": 7.84, + "learning_rate": 1.3883305545764953e-05, + "loss": 0.077, + "step": 25377 + }, + { + "epoch": 7.84, + "learning_rate": 1.3882844671888811e-05, + "loss": 0.0741, + "step": 25378 + }, + { + "epoch": 7.84, + "learning_rate": 1.3882383788300968e-05, + "loss": 0.0684, + "step": 25379 + }, + { + "epoch": 7.84, + "learning_rate": 1.3881922895002573e-05, + "loss": 0.0699, + "step": 25380 + }, + { + "epoch": 7.84, + "learning_rate": 1.3881461991994782e-05, + "loss": 0.071, + "step": 25381 + }, + { + "epoch": 7.84, + "learning_rate": 1.388100107927875e-05, + "loss": 0.0768, + "step": 25382 + }, + { + "epoch": 7.84, + "learning_rate": 1.3880540156855623e-05, + "loss": 0.0778, + "step": 25383 + }, + { + "epoch": 7.84, + "learning_rate": 1.3880079224726557e-05, + "loss": 0.08, + "step": 25384 + }, + { + "epoch": 7.84, + "learning_rate": 1.3879618282892703e-05, + "loss": 0.0762, + "step": 25385 + }, + { + "epoch": 7.84, + "learning_rate": 1.387915733135522e-05, + "loss": 0.069, + "step": 25386 + }, + { + "epoch": 7.84, + "learning_rate": 1.3878696370115257e-05, + "loss": 0.0768, + "step": 25387 + }, + { + "epoch": 7.84, + "learning_rate": 1.3878235399173964e-05, + "loss": 0.0708, + "step": 25388 + }, + { + "epoch": 7.84, + "learning_rate": 1.38777744185325e-05, + "loss": 0.0769, + "step": 25389 + }, + { + "epoch": 7.84, + "learning_rate": 1.3877313428192015e-05, + "loss": 0.0706, + "step": 25390 + }, + { + "epoch": 7.84, + "learning_rate": 1.3876852428153658e-05, + "loss": 0.0718, + "step": 25391 + }, + { + "epoch": 7.84, + "learning_rate": 1.3876391418418589e-05, + "loss": 0.0709, + "step": 25392 + }, + { + "epoch": 7.84, + "learning_rate": 1.3875930398987957e-05, + "loss": 0.0809, + "step": 25393 + }, + { + "epoch": 7.84, + "learning_rate": 1.3875469369862915e-05, + "loss": 0.0604, + "step": 25394 + }, + { + "epoch": 7.84, + "learning_rate": 1.3875008331044622e-05, + "loss": 0.0794, + "step": 25395 + }, + { + "epoch": 7.84, + "learning_rate": 1.387454728253422e-05, + "loss": 0.074, + "step": 25396 + }, + { + "epoch": 7.84, + "learning_rate": 1.3874086224332873e-05, + "loss": 0.0785, + "step": 25397 + }, + { + "epoch": 7.84, + "learning_rate": 1.3873625156441731e-05, + "loss": 0.0727, + "step": 25398 + }, + { + "epoch": 7.84, + "learning_rate": 1.387316407886194e-05, + "loss": 0.0689, + "step": 25399 + }, + { + "epoch": 7.84, + "learning_rate": 1.3872702991594667e-05, + "loss": 0.0652, + "step": 25400 + }, + { + "epoch": 7.84, + "learning_rate": 1.3872241894641052e-05, + "loss": 0.0738, + "step": 25401 + }, + { + "epoch": 7.84, + "learning_rate": 1.3871780788002254e-05, + "loss": 0.066, + "step": 25402 + }, + { + "epoch": 7.84, + "learning_rate": 1.3871319671679428e-05, + "loss": 0.0715, + "step": 25403 + }, + { + "epoch": 7.85, + "learning_rate": 1.3870858545673724e-05, + "loss": 0.0737, + "step": 25404 + }, + { + "epoch": 7.85, + "learning_rate": 1.3870397409986298e-05, + "loss": 0.0753, + "step": 25405 + }, + { + "epoch": 7.85, + "learning_rate": 1.38699362646183e-05, + "loss": 0.0748, + "step": 25406 + }, + { + "epoch": 7.85, + "learning_rate": 1.386947510957089e-05, + "loss": 0.0645, + "step": 25407 + }, + { + "epoch": 7.85, + "learning_rate": 1.3869013944845211e-05, + "loss": 0.0714, + "step": 25408 + }, + { + "epoch": 7.85, + "learning_rate": 1.3868552770442427e-05, + "loss": 0.0763, + "step": 25409 + }, + { + "epoch": 7.85, + "learning_rate": 1.3868091586363686e-05, + "loss": 0.0687, + "step": 25410 + }, + { + "epoch": 7.85, + "learning_rate": 1.386763039261014e-05, + "loss": 0.0733, + "step": 25411 + }, + { + "epoch": 7.85, + "learning_rate": 1.3867169189182947e-05, + "loss": 0.069, + "step": 25412 + }, + { + "epoch": 7.85, + "learning_rate": 1.386670797608326e-05, + "loss": 0.0735, + "step": 25413 + }, + { + "epoch": 7.85, + "learning_rate": 1.386624675331223e-05, + "loss": 0.0794, + "step": 25414 + }, + { + "epoch": 7.85, + "learning_rate": 1.3865785520871011e-05, + "loss": 0.0685, + "step": 25415 + }, + { + "epoch": 7.85, + "learning_rate": 1.3865324278760757e-05, + "loss": 0.0788, + "step": 25416 + }, + { + "epoch": 7.85, + "learning_rate": 1.3864863026982623e-05, + "loss": 0.0669, + "step": 25417 + }, + { + "epoch": 7.85, + "learning_rate": 1.3864401765537763e-05, + "loss": 0.0733, + "step": 25418 + }, + { + "epoch": 7.85, + "learning_rate": 1.3863940494427323e-05, + "loss": 0.075, + "step": 25419 + }, + { + "epoch": 7.85, + "learning_rate": 1.3863479213652468e-05, + "loss": 0.0706, + "step": 25420 + }, + { + "epoch": 7.85, + "learning_rate": 1.3863017923214351e-05, + "loss": 0.0643, + "step": 25421 + }, + { + "epoch": 7.85, + "learning_rate": 1.3862556623114114e-05, + "loss": 0.079, + "step": 25422 + }, + { + "epoch": 7.85, + "learning_rate": 1.3862095313352924e-05, + "loss": 0.0707, + "step": 25423 + }, + { + "epoch": 7.85, + "learning_rate": 1.3861633993931926e-05, + "loss": 0.0746, + "step": 25424 + }, + { + "epoch": 7.85, + "learning_rate": 1.3861172664852276e-05, + "loss": 0.0706, + "step": 25425 + }, + { + "epoch": 7.85, + "learning_rate": 1.3860711326115133e-05, + "loss": 0.0734, + "step": 25426 + }, + { + "epoch": 7.85, + "learning_rate": 1.3860249977721643e-05, + "loss": 0.0695, + "step": 25427 + }, + { + "epoch": 7.85, + "learning_rate": 1.3859788619672966e-05, + "loss": 0.0677, + "step": 25428 + }, + { + "epoch": 7.85, + "learning_rate": 1.3859327251970254e-05, + "loss": 0.0717, + "step": 25429 + }, + { + "epoch": 7.85, + "learning_rate": 1.3858865874614657e-05, + "loss": 0.0684, + "step": 25430 + }, + { + "epoch": 7.85, + "learning_rate": 1.3858404487607337e-05, + "loss": 0.0707, + "step": 25431 + }, + { + "epoch": 7.85, + "learning_rate": 1.3857943090949442e-05, + "loss": 0.0632, + "step": 25432 + }, + { + "epoch": 7.85, + "learning_rate": 1.3857481684642127e-05, + "loss": 0.0796, + "step": 25433 + }, + { + "epoch": 7.85, + "learning_rate": 1.3857020268686548e-05, + "loss": 0.0718, + "step": 25434 + }, + { + "epoch": 7.85, + "learning_rate": 1.3856558843083857e-05, + "loss": 0.074, + "step": 25435 + }, + { + "epoch": 7.86, + "learning_rate": 1.385609740783521e-05, + "loss": 0.077, + "step": 25436 + }, + { + "epoch": 7.86, + "learning_rate": 1.3855635962941758e-05, + "loss": 0.0726, + "step": 25437 + }, + { + "epoch": 7.86, + "learning_rate": 1.3855174508404658e-05, + "loss": 0.0678, + "step": 25438 + }, + { + "epoch": 7.86, + "learning_rate": 1.3854713044225063e-05, + "loss": 0.0711, + "step": 25439 + }, + { + "epoch": 7.86, + "learning_rate": 1.385425157040413e-05, + "loss": 0.0715, + "step": 25440 + }, + { + "epoch": 7.86, + "learning_rate": 1.385379008694301e-05, + "loss": 0.0696, + "step": 25441 + }, + { + "epoch": 7.86, + "learning_rate": 1.3853328593842856e-05, + "loss": 0.0697, + "step": 25442 + }, + { + "epoch": 7.86, + "learning_rate": 1.3852867091104826e-05, + "loss": 0.0799, + "step": 25443 + }, + { + "epoch": 7.86, + "learning_rate": 1.3852405578730072e-05, + "loss": 0.0697, + "step": 25444 + }, + { + "epoch": 7.86, + "learning_rate": 1.3851944056719751e-05, + "loss": 0.0673, + "step": 25445 + }, + { + "epoch": 7.86, + "learning_rate": 1.3851482525075013e-05, + "loss": 0.0681, + "step": 25446 + }, + { + "epoch": 7.86, + "learning_rate": 1.3851020983797014e-05, + "loss": 0.0762, + "step": 25447 + }, + { + "epoch": 7.86, + "learning_rate": 1.3850559432886911e-05, + "loss": 0.0755, + "step": 25448 + }, + { + "epoch": 7.86, + "learning_rate": 1.3850097872345858e-05, + "loss": 0.0755, + "step": 25449 + }, + { + "epoch": 7.86, + "learning_rate": 1.3849636302175005e-05, + "loss": 0.0684, + "step": 25450 + }, + { + "epoch": 7.86, + "learning_rate": 1.3849174722375512e-05, + "loss": 0.0624, + "step": 25451 + }, + { + "epoch": 7.86, + "learning_rate": 1.384871313294853e-05, + "loss": 0.0771, + "step": 25452 + }, + { + "epoch": 7.86, + "learning_rate": 1.3848251533895214e-05, + "loss": 0.0647, + "step": 25453 + }, + { + "epoch": 7.86, + "learning_rate": 1.3847789925216719e-05, + "loss": 0.076, + "step": 25454 + }, + { + "epoch": 7.86, + "learning_rate": 1.3847328306914201e-05, + "loss": 0.077, + "step": 25455 + }, + { + "epoch": 7.86, + "learning_rate": 1.384686667898881e-05, + "loss": 0.0823, + "step": 25456 + }, + { + "epoch": 7.86, + "learning_rate": 1.3846405041441709e-05, + "loss": 0.0698, + "step": 25457 + }, + { + "epoch": 7.86, + "learning_rate": 1.3845943394274043e-05, + "loss": 0.0718, + "step": 25458 + }, + { + "epoch": 7.86, + "learning_rate": 1.3845481737486972e-05, + "loss": 0.0798, + "step": 25459 + }, + { + "epoch": 7.86, + "learning_rate": 1.3845020071081652e-05, + "loss": 0.073, + "step": 25460 + }, + { + "epoch": 7.86, + "learning_rate": 1.384455839505923e-05, + "loss": 0.0712, + "step": 25461 + }, + { + "epoch": 7.86, + "learning_rate": 1.384409670942087e-05, + "loss": 0.0603, + "step": 25462 + }, + { + "epoch": 7.86, + "learning_rate": 1.3843635014167727e-05, + "loss": 0.0681, + "step": 25463 + }, + { + "epoch": 7.86, + "learning_rate": 1.3843173309300946e-05, + "loss": 0.0728, + "step": 25464 + }, + { + "epoch": 7.86, + "learning_rate": 1.384271159482169e-05, + "loss": 0.0816, + "step": 25465 + }, + { + "epoch": 7.86, + "learning_rate": 1.384224987073111e-05, + "loss": 0.0764, + "step": 25466 + }, + { + "epoch": 7.86, + "learning_rate": 1.3841788137030363e-05, + "loss": 0.067, + "step": 25467 + }, + { + "epoch": 7.87, + "learning_rate": 1.3841326393720604e-05, + "loss": 0.0639, + "step": 25468 + }, + { + "epoch": 7.87, + "learning_rate": 1.3840864640802986e-05, + "loss": 0.0688, + "step": 25469 + }, + { + "epoch": 7.87, + "learning_rate": 1.3840402878278666e-05, + "loss": 0.0719, + "step": 25470 + }, + { + "epoch": 7.87, + "learning_rate": 1.3839941106148795e-05, + "loss": 0.0748, + "step": 25471 + }, + { + "epoch": 7.87, + "learning_rate": 1.3839479324414538e-05, + "loss": 0.0699, + "step": 25472 + }, + { + "epoch": 7.87, + "learning_rate": 1.3839017533077035e-05, + "loss": 0.0802, + "step": 25473 + }, + { + "epoch": 7.87, + "learning_rate": 1.3838555732137451e-05, + "loss": 0.0728, + "step": 25474 + }, + { + "epoch": 7.87, + "learning_rate": 1.383809392159694e-05, + "loss": 0.0759, + "step": 25475 + }, + { + "epoch": 7.87, + "learning_rate": 1.3837632101456658e-05, + "loss": 0.073, + "step": 25476 + }, + { + "epoch": 7.87, + "learning_rate": 1.383717027171776e-05, + "loss": 0.0686, + "step": 25477 + }, + { + "epoch": 7.87, + "learning_rate": 1.3836708432381391e-05, + "loss": 0.0752, + "step": 25478 + }, + { + "epoch": 7.87, + "learning_rate": 1.383624658344872e-05, + "loss": 0.0727, + "step": 25479 + }, + { + "epoch": 7.87, + "learning_rate": 1.3835784724920898e-05, + "loss": 0.0735, + "step": 25480 + }, + { + "epoch": 7.87, + "learning_rate": 1.3835322856799074e-05, + "loss": 0.0706, + "step": 25481 + }, + { + "epoch": 7.87, + "learning_rate": 1.383486097908441e-05, + "loss": 0.0758, + "step": 25482 + }, + { + "epoch": 7.87, + "learning_rate": 1.3834399091778061e-05, + "loss": 0.0675, + "step": 25483 + }, + { + "epoch": 7.87, + "learning_rate": 1.383393719488118e-05, + "loss": 0.069, + "step": 25484 + }, + { + "epoch": 7.87, + "learning_rate": 1.3833475288394922e-05, + "loss": 0.0729, + "step": 25485 + }, + { + "epoch": 7.87, + "learning_rate": 1.3833013372320445e-05, + "loss": 0.0806, + "step": 25486 + }, + { + "epoch": 7.87, + "learning_rate": 1.3832551446658897e-05, + "loss": 0.0677, + "step": 25487 + }, + { + "epoch": 7.87, + "learning_rate": 1.3832089511411444e-05, + "loss": 0.0699, + "step": 25488 + }, + { + "epoch": 7.87, + "learning_rate": 1.3831627566579236e-05, + "loss": 0.0749, + "step": 25489 + }, + { + "epoch": 7.87, + "learning_rate": 1.3831165612163427e-05, + "loss": 0.0703, + "step": 25490 + }, + { + "epoch": 7.87, + "learning_rate": 1.3830703648165176e-05, + "loss": 0.0639, + "step": 25491 + }, + { + "epoch": 7.87, + "learning_rate": 1.3830241674585632e-05, + "loss": 0.0748, + "step": 25492 + }, + { + "epoch": 7.87, + "learning_rate": 1.382977969142596e-05, + "loss": 0.0859, + "step": 25493 + }, + { + "epoch": 7.87, + "learning_rate": 1.3829317698687308e-05, + "loss": 0.0676, + "step": 25494 + }, + { + "epoch": 7.87, + "learning_rate": 1.3828855696370834e-05, + "loss": 0.0695, + "step": 25495 + }, + { + "epoch": 7.87, + "learning_rate": 1.3828393684477694e-05, + "loss": 0.0773, + "step": 25496 + }, + { + "epoch": 7.87, + "learning_rate": 1.3827931663009042e-05, + "loss": 0.0697, + "step": 25497 + }, + { + "epoch": 7.87, + "learning_rate": 1.3827469631966037e-05, + "loss": 0.0772, + "step": 25498 + }, + { + "epoch": 7.87, + "learning_rate": 1.382700759134983e-05, + "loss": 0.0749, + "step": 25499 + }, + { + "epoch": 7.87, + "learning_rate": 1.382654554116158e-05, + "loss": 0.0653, + "step": 25500 + }, + { + "epoch": 7.88, + "learning_rate": 1.3826083481402444e-05, + "loss": 0.0766, + "step": 25501 + }, + { + "epoch": 7.88, + "learning_rate": 1.3825621412073571e-05, + "loss": 0.0767, + "step": 25502 + }, + { + "epoch": 7.88, + "learning_rate": 1.3825159333176126e-05, + "loss": 0.0697, + "step": 25503 + }, + { + "epoch": 7.88, + "learning_rate": 1.3824697244711256e-05, + "loss": 0.0746, + "step": 25504 + }, + { + "epoch": 7.88, + "learning_rate": 1.382423514668012e-05, + "loss": 0.0722, + "step": 25505 + }, + { + "epoch": 7.88, + "learning_rate": 1.3823773039083878e-05, + "loss": 0.0738, + "step": 25506 + }, + { + "epoch": 7.88, + "learning_rate": 1.3823310921923681e-05, + "loss": 0.0735, + "step": 25507 + }, + { + "epoch": 7.88, + "learning_rate": 1.3822848795200688e-05, + "loss": 0.0653, + "step": 25508 + }, + { + "epoch": 7.88, + "learning_rate": 1.3822386658916047e-05, + "loss": 0.0808, + "step": 25509 + }, + { + "epoch": 7.88, + "learning_rate": 1.3821924513070924e-05, + "loss": 0.0778, + "step": 25510 + }, + { + "epoch": 7.88, + "learning_rate": 1.3821462357666471e-05, + "loss": 0.081, + "step": 25511 + }, + { + "epoch": 7.88, + "learning_rate": 1.382100019270384e-05, + "loss": 0.0767, + "step": 25512 + }, + { + "epoch": 7.88, + "learning_rate": 1.3820538018184195e-05, + "loss": 0.0853, + "step": 25513 + }, + { + "epoch": 7.88, + "learning_rate": 1.3820075834108686e-05, + "loss": 0.0752, + "step": 25514 + }, + { + "epoch": 7.88, + "learning_rate": 1.3819613640478469e-05, + "loss": 0.0657, + "step": 25515 + }, + { + "epoch": 7.88, + "learning_rate": 1.3819151437294704e-05, + "loss": 0.0769, + "step": 25516 + }, + { + "epoch": 7.88, + "learning_rate": 1.3818689224558543e-05, + "loss": 0.0775, + "step": 25517 + }, + { + "epoch": 7.88, + "learning_rate": 1.3818227002271146e-05, + "loss": 0.0733, + "step": 25518 + }, + { + "epoch": 7.88, + "learning_rate": 1.3817764770433666e-05, + "loss": 0.0813, + "step": 25519 + }, + { + "epoch": 7.88, + "learning_rate": 1.3817302529047258e-05, + "loss": 0.0797, + "step": 25520 + }, + { + "epoch": 7.88, + "learning_rate": 1.3816840278113082e-05, + "loss": 0.0736, + "step": 25521 + }, + { + "epoch": 7.88, + "learning_rate": 1.3816378017632292e-05, + "loss": 0.071, + "step": 25522 + }, + { + "epoch": 7.88, + "learning_rate": 1.3815915747606043e-05, + "loss": 0.0685, + "step": 25523 + }, + { + "epoch": 7.88, + "learning_rate": 1.3815453468035495e-05, + "loss": 0.0705, + "step": 25524 + }, + { + "epoch": 7.88, + "learning_rate": 1.38149911789218e-05, + "loss": 0.0762, + "step": 25525 + }, + { + "epoch": 7.88, + "learning_rate": 1.3814528880266118e-05, + "loss": 0.0777, + "step": 25526 + }, + { + "epoch": 7.88, + "learning_rate": 1.3814066572069602e-05, + "loss": 0.0757, + "step": 25527 + }, + { + "epoch": 7.88, + "learning_rate": 1.381360425433341e-05, + "loss": 0.0663, + "step": 25528 + }, + { + "epoch": 7.88, + "learning_rate": 1.38131419270587e-05, + "loss": 0.0833, + "step": 25529 + }, + { + "epoch": 7.88, + "learning_rate": 1.3812679590246625e-05, + "loss": 0.0715, + "step": 25530 + }, + { + "epoch": 7.88, + "learning_rate": 1.3812217243898344e-05, + "loss": 0.073, + "step": 25531 + }, + { + "epoch": 7.88, + "learning_rate": 1.3811754888015011e-05, + "loss": 0.073, + "step": 25532 + }, + { + "epoch": 7.89, + "learning_rate": 1.3811292522597786e-05, + "loss": 0.0786, + "step": 25533 + }, + { + "epoch": 7.89, + "learning_rate": 1.3810830147647823e-05, + "loss": 0.0773, + "step": 25534 + }, + { + "epoch": 7.89, + "learning_rate": 1.3810367763166274e-05, + "loss": 0.0763, + "step": 25535 + }, + { + "epoch": 7.89, + "learning_rate": 1.3809905369154306e-05, + "loss": 0.0748, + "step": 25536 + }, + { + "epoch": 7.89, + "learning_rate": 1.3809442965613069e-05, + "loss": 0.0712, + "step": 25537 + }, + { + "epoch": 7.89, + "learning_rate": 1.3808980552543716e-05, + "loss": 0.0733, + "step": 25538 + }, + { + "epoch": 7.89, + "learning_rate": 1.3808518129947413e-05, + "loss": 0.0761, + "step": 25539 + }, + { + "epoch": 7.89, + "learning_rate": 1.3808055697825311e-05, + "loss": 0.0704, + "step": 25540 + }, + { + "epoch": 7.89, + "learning_rate": 1.3807593256178561e-05, + "loss": 0.0751, + "step": 25541 + }, + { + "epoch": 7.89, + "learning_rate": 1.3807130805008333e-05, + "loss": 0.0788, + "step": 25542 + }, + { + "epoch": 7.89, + "learning_rate": 1.3806668344315773e-05, + "loss": 0.0771, + "step": 25543 + }, + { + "epoch": 7.89, + "learning_rate": 1.3806205874102044e-05, + "loss": 0.072, + "step": 25544 + }, + { + "epoch": 7.89, + "learning_rate": 1.3805743394368298e-05, + "loss": 0.0728, + "step": 25545 + }, + { + "epoch": 7.89, + "learning_rate": 1.380528090511569e-05, + "loss": 0.0697, + "step": 25546 + }, + { + "epoch": 7.89, + "learning_rate": 1.3804818406345386e-05, + "loss": 0.0659, + "step": 25547 + }, + { + "epoch": 7.89, + "learning_rate": 1.3804355898058537e-05, + "loss": 0.0712, + "step": 25548 + }, + { + "epoch": 7.89, + "learning_rate": 1.3803893380256296e-05, + "loss": 0.0734, + "step": 25549 + }, + { + "epoch": 7.89, + "learning_rate": 1.3803430852939827e-05, + "loss": 0.0638, + "step": 25550 + }, + { + "epoch": 7.89, + "learning_rate": 1.3802968316110284e-05, + "loss": 0.0689, + "step": 25551 + }, + { + "epoch": 7.89, + "learning_rate": 1.3802505769768822e-05, + "loss": 0.0739, + "step": 25552 + }, + { + "epoch": 7.89, + "learning_rate": 1.38020432139166e-05, + "loss": 0.0845, + "step": 25553 + }, + { + "epoch": 7.89, + "learning_rate": 1.3801580648554773e-05, + "loss": 0.0737, + "step": 25554 + }, + { + "epoch": 7.89, + "learning_rate": 1.3801118073684502e-05, + "loss": 0.0738, + "step": 25555 + }, + { + "epoch": 7.89, + "learning_rate": 1.380065548930694e-05, + "loss": 0.0697, + "step": 25556 + }, + { + "epoch": 7.89, + "learning_rate": 1.3800192895423245e-05, + "loss": 0.0683, + "step": 25557 + }, + { + "epoch": 7.89, + "learning_rate": 1.3799730292034576e-05, + "loss": 0.0779, + "step": 25558 + }, + { + "epoch": 7.89, + "learning_rate": 1.3799267679142088e-05, + "loss": 0.0862, + "step": 25559 + }, + { + "epoch": 7.89, + "learning_rate": 1.3798805056746938e-05, + "loss": 0.0783, + "step": 25560 + }, + { + "epoch": 7.89, + "learning_rate": 1.3798342424850284e-05, + "loss": 0.0754, + "step": 25561 + }, + { + "epoch": 7.89, + "learning_rate": 1.3797879783453285e-05, + "loss": 0.0806, + "step": 25562 + }, + { + "epoch": 7.89, + "learning_rate": 1.3797417132557091e-05, + "loss": 0.068, + "step": 25563 + }, + { + "epoch": 7.89, + "learning_rate": 1.3796954472162866e-05, + "loss": 0.0754, + "step": 25564 + }, + { + "epoch": 7.9, + "learning_rate": 1.379649180227177e-05, + "loss": 0.0726, + "step": 25565 + }, + { + "epoch": 7.9, + "learning_rate": 1.3796029122884949e-05, + "loss": 0.0703, + "step": 25566 + }, + { + "epoch": 7.9, + "learning_rate": 1.3795566434003574e-05, + "loss": 0.0823, + "step": 25567 + }, + { + "epoch": 7.9, + "learning_rate": 1.379510373562879e-05, + "loss": 0.0662, + "step": 25568 + }, + { + "epoch": 7.9, + "learning_rate": 1.3794641027761758e-05, + "loss": 0.0661, + "step": 25569 + }, + { + "epoch": 7.9, + "learning_rate": 1.379417831040364e-05, + "loss": 0.0815, + "step": 25570 + }, + { + "epoch": 7.9, + "learning_rate": 1.379371558355559e-05, + "loss": 0.0768, + "step": 25571 + }, + { + "epoch": 7.9, + "learning_rate": 1.3793252847218764e-05, + "loss": 0.0675, + "step": 25572 + }, + { + "epoch": 7.9, + "learning_rate": 1.379279010139432e-05, + "loss": 0.0717, + "step": 25573 + }, + { + "epoch": 7.9, + "learning_rate": 1.3792327346083414e-05, + "loss": 0.0675, + "step": 25574 + }, + { + "epoch": 7.9, + "learning_rate": 1.3791864581287211e-05, + "loss": 0.0813, + "step": 25575 + }, + { + "epoch": 7.9, + "learning_rate": 1.3791401807006862e-05, + "loss": 0.0694, + "step": 25576 + }, + { + "epoch": 7.9, + "learning_rate": 1.3790939023243523e-05, + "loss": 0.0755, + "step": 25577 + }, + { + "epoch": 7.9, + "learning_rate": 1.3790476229998357e-05, + "loss": 0.0733, + "step": 25578 + }, + { + "epoch": 7.9, + "learning_rate": 1.3790013427272517e-05, + "loss": 0.0705, + "step": 25579 + }, + { + "epoch": 7.9, + "learning_rate": 1.3789550615067161e-05, + "loss": 0.0753, + "step": 25580 + }, + { + "epoch": 7.9, + "learning_rate": 1.3789087793383452e-05, + "loss": 0.0671, + "step": 25581 + }, + { + "epoch": 7.9, + "learning_rate": 1.378862496222254e-05, + "loss": 0.0737, + "step": 25582 + }, + { + "epoch": 7.9, + "learning_rate": 1.3788162121585585e-05, + "loss": 0.0697, + "step": 25583 + }, + { + "epoch": 7.9, + "learning_rate": 1.3787699271473747e-05, + "loss": 0.0696, + "step": 25584 + }, + { + "epoch": 7.9, + "learning_rate": 1.3787236411888183e-05, + "loss": 0.0722, + "step": 25585 + }, + { + "epoch": 7.9, + "learning_rate": 1.378677354283005e-05, + "loss": 0.0738, + "step": 25586 + }, + { + "epoch": 7.9, + "learning_rate": 1.3786310664300505e-05, + "loss": 0.0724, + "step": 25587 + }, + { + "epoch": 7.9, + "learning_rate": 1.3785847776300707e-05, + "loss": 0.073, + "step": 25588 + }, + { + "epoch": 7.9, + "learning_rate": 1.378538487883181e-05, + "loss": 0.0788, + "step": 25589 + }, + { + "epoch": 7.9, + "learning_rate": 1.3784921971894979e-05, + "loss": 0.065, + "step": 25590 + }, + { + "epoch": 7.9, + "learning_rate": 1.3784459055491366e-05, + "loss": 0.0725, + "step": 25591 + }, + { + "epoch": 7.9, + "learning_rate": 1.378399612962213e-05, + "loss": 0.0763, + "step": 25592 + }, + { + "epoch": 7.9, + "learning_rate": 1.3783533194288434e-05, + "loss": 0.0744, + "step": 25593 + }, + { + "epoch": 7.9, + "learning_rate": 1.3783070249491427e-05, + "loss": 0.0736, + "step": 25594 + }, + { + "epoch": 7.9, + "learning_rate": 1.3782607295232272e-05, + "loss": 0.0692, + "step": 25595 + }, + { + "epoch": 7.9, + "learning_rate": 1.3782144331512126e-05, + "loss": 0.0654, + "step": 25596 + }, + { + "epoch": 7.9, + "learning_rate": 1.3781681358332147e-05, + "loss": 0.0672, + "step": 25597 + }, + { + "epoch": 7.91, + "learning_rate": 1.3781218375693497e-05, + "loss": 0.0765, + "step": 25598 + }, + { + "epoch": 7.91, + "learning_rate": 1.3780755383597326e-05, + "loss": 0.0739, + "step": 25599 + }, + { + "epoch": 7.91, + "learning_rate": 1.3780292382044796e-05, + "loss": 0.0774, + "step": 25600 + }, + { + "epoch": 7.91, + "learning_rate": 1.3779829371037068e-05, + "loss": 0.0798, + "step": 25601 + }, + { + "epoch": 7.91, + "learning_rate": 1.3779366350575296e-05, + "loss": 0.0745, + "step": 25602 + }, + { + "epoch": 7.91, + "learning_rate": 1.3778903320660639e-05, + "loss": 0.0723, + "step": 25603 + }, + { + "epoch": 7.91, + "learning_rate": 1.3778440281294256e-05, + "loss": 0.0728, + "step": 25604 + }, + { + "epoch": 7.91, + "learning_rate": 1.3777977232477306e-05, + "loss": 0.0652, + "step": 25605 + }, + { + "epoch": 7.91, + "learning_rate": 1.3777514174210945e-05, + "loss": 0.0758, + "step": 25606 + }, + { + "epoch": 7.91, + "learning_rate": 1.3777051106496331e-05, + "loss": 0.0776, + "step": 25607 + }, + { + "epoch": 7.91, + "learning_rate": 1.3776588029334623e-05, + "loss": 0.0734, + "step": 25608 + }, + { + "epoch": 7.91, + "learning_rate": 1.377612494272698e-05, + "loss": 0.0742, + "step": 25609 + }, + { + "epoch": 7.91, + "learning_rate": 1.3775661846674562e-05, + "loss": 0.0743, + "step": 25610 + }, + { + "epoch": 7.91, + "learning_rate": 1.3775198741178524e-05, + "loss": 0.0704, + "step": 25611 + }, + { + "epoch": 7.91, + "learning_rate": 1.3774735626240023e-05, + "loss": 0.0733, + "step": 25612 + }, + { + "epoch": 7.91, + "learning_rate": 1.3774272501860223e-05, + "loss": 0.0716, + "step": 25613 + }, + { + "epoch": 7.91, + "learning_rate": 1.377380936804028e-05, + "loss": 0.0834, + "step": 25614 + }, + { + "epoch": 7.91, + "learning_rate": 1.3773346224781348e-05, + "loss": 0.0768, + "step": 25615 + }, + { + "epoch": 7.91, + "learning_rate": 1.3772883072084591e-05, + "loss": 0.0691, + "step": 25616 + }, + { + "epoch": 7.91, + "learning_rate": 1.3772419909951162e-05, + "loss": 0.0779, + "step": 25617 + }, + { + "epoch": 7.91, + "learning_rate": 1.3771956738382226e-05, + "loss": 0.0871, + "step": 25618 + }, + { + "epoch": 7.91, + "learning_rate": 1.377149355737894e-05, + "loss": 0.0746, + "step": 25619 + }, + { + "epoch": 7.91, + "learning_rate": 1.3771030366942455e-05, + "loss": 0.0757, + "step": 25620 + }, + { + "epoch": 7.91, + "learning_rate": 1.377056716707394e-05, + "loss": 0.0715, + "step": 25621 + }, + { + "epoch": 7.91, + "learning_rate": 1.3770103957774548e-05, + "loss": 0.0743, + "step": 25622 + }, + { + "epoch": 7.91, + "learning_rate": 1.3769640739045434e-05, + "loss": 0.0736, + "step": 25623 + }, + { + "epoch": 7.91, + "learning_rate": 1.3769177510887765e-05, + "loss": 0.0799, + "step": 25624 + }, + { + "epoch": 7.91, + "learning_rate": 1.3768714273302694e-05, + "loss": 0.0713, + "step": 25625 + }, + { + "epoch": 7.91, + "learning_rate": 1.3768251026291384e-05, + "loss": 0.0744, + "step": 25626 + }, + { + "epoch": 7.91, + "learning_rate": 1.376778776985499e-05, + "loss": 0.0761, + "step": 25627 + }, + { + "epoch": 7.91, + "learning_rate": 1.3767324503994668e-05, + "loss": 0.071, + "step": 25628 + }, + { + "epoch": 7.91, + "learning_rate": 1.3766861228711586e-05, + "loss": 0.0801, + "step": 25629 + }, + { + "epoch": 7.92, + "learning_rate": 1.3766397944006892e-05, + "loss": 0.0811, + "step": 25630 + }, + { + "epoch": 7.92, + "learning_rate": 1.3765934649881754e-05, + "loss": 0.0746, + "step": 25631 + }, + { + "epoch": 7.92, + "learning_rate": 1.3765471346337323e-05, + "loss": 0.0695, + "step": 25632 + }, + { + "epoch": 7.92, + "learning_rate": 1.3765008033374763e-05, + "loss": 0.0727, + "step": 25633 + }, + { + "epoch": 7.92, + "learning_rate": 1.3764544710995231e-05, + "loss": 0.0696, + "step": 25634 + }, + { + "epoch": 7.92, + "learning_rate": 1.3764081379199887e-05, + "loss": 0.08, + "step": 25635 + }, + { + "epoch": 7.92, + "learning_rate": 1.3763618037989888e-05, + "loss": 0.0762, + "step": 25636 + }, + { + "epoch": 7.92, + "learning_rate": 1.3763154687366393e-05, + "loss": 0.0661, + "step": 25637 + }, + { + "epoch": 7.92, + "learning_rate": 1.3762691327330565e-05, + "loss": 0.0616, + "step": 25638 + }, + { + "epoch": 7.92, + "learning_rate": 1.3762227957883557e-05, + "loss": 0.0767, + "step": 25639 + }, + { + "epoch": 7.92, + "learning_rate": 1.3761764579026528e-05, + "loss": 0.0675, + "step": 25640 + }, + { + "epoch": 7.92, + "learning_rate": 1.3761301190760645e-05, + "loss": 0.0701, + "step": 25641 + }, + { + "epoch": 7.92, + "learning_rate": 1.3760837793087059e-05, + "loss": 0.0679, + "step": 25642 + }, + { + "epoch": 7.92, + "learning_rate": 1.3760374386006931e-05, + "loss": 0.0771, + "step": 25643 + }, + { + "epoch": 7.92, + "learning_rate": 1.3759910969521424e-05, + "loss": 0.0759, + "step": 25644 + }, + { + "epoch": 7.92, + "learning_rate": 1.375944754363169e-05, + "loss": 0.0724, + "step": 25645 + }, + { + "epoch": 7.92, + "learning_rate": 1.3758984108338895e-05, + "loss": 0.0704, + "step": 25646 + }, + { + "epoch": 7.92, + "learning_rate": 1.3758520663644195e-05, + "loss": 0.0685, + "step": 25647 + }, + { + "epoch": 7.92, + "learning_rate": 1.3758057209548747e-05, + "loss": 0.0766, + "step": 25648 + }, + { + "epoch": 7.92, + "learning_rate": 1.3757593746053714e-05, + "loss": 0.0715, + "step": 25649 + }, + { + "epoch": 7.92, + "learning_rate": 1.3757130273160254e-05, + "loss": 0.0688, + "step": 25650 + }, + { + "epoch": 7.92, + "learning_rate": 1.3756666790869523e-05, + "loss": 0.0787, + "step": 25651 + }, + { + "epoch": 7.92, + "learning_rate": 1.375620329918269e-05, + "loss": 0.0771, + "step": 25652 + }, + { + "epoch": 7.92, + "learning_rate": 1.3755739798100902e-05, + "loss": 0.0791, + "step": 25653 + }, + { + "epoch": 7.92, + "learning_rate": 1.3755276287625322e-05, + "loss": 0.0763, + "step": 25654 + }, + { + "epoch": 7.92, + "learning_rate": 1.3754812767757118e-05, + "loss": 0.068, + "step": 25655 + }, + { + "epoch": 7.92, + "learning_rate": 1.3754349238497438e-05, + "loss": 0.076, + "step": 25656 + }, + { + "epoch": 7.92, + "learning_rate": 1.3753885699847447e-05, + "loss": 0.0731, + "step": 25657 + }, + { + "epoch": 7.92, + "learning_rate": 1.3753422151808302e-05, + "loss": 0.082, + "step": 25658 + }, + { + "epoch": 7.92, + "learning_rate": 1.3752958594381163e-05, + "loss": 0.0724, + "step": 25659 + }, + { + "epoch": 7.92, + "learning_rate": 1.3752495027567193e-05, + "loss": 0.0712, + "step": 25660 + }, + { + "epoch": 7.92, + "learning_rate": 1.3752031451367547e-05, + "loss": 0.0783, + "step": 25661 + }, + { + "epoch": 7.92, + "learning_rate": 1.3751567865783384e-05, + "loss": 0.0728, + "step": 25662 + }, + { + "epoch": 7.93, + "learning_rate": 1.3751104270815866e-05, + "loss": 0.0732, + "step": 25663 + }, + { + "epoch": 7.93, + "learning_rate": 1.3750640666466154e-05, + "loss": 0.0733, + "step": 25664 + }, + { + "epoch": 7.93, + "learning_rate": 1.3750177052735405e-05, + "loss": 0.0735, + "step": 25665 + }, + { + "epoch": 7.93, + "learning_rate": 1.3749713429624781e-05, + "loss": 0.0759, + "step": 25666 + }, + { + "epoch": 7.93, + "learning_rate": 1.3749249797135439e-05, + "loss": 0.0767, + "step": 25667 + }, + { + "epoch": 7.93, + "learning_rate": 1.3748786155268537e-05, + "loss": 0.0808, + "step": 25668 + }, + { + "epoch": 7.93, + "learning_rate": 1.3748322504025238e-05, + "loss": 0.0707, + "step": 25669 + }, + { + "epoch": 7.93, + "learning_rate": 1.3747858843406702e-05, + "loss": 0.0743, + "step": 25670 + }, + { + "epoch": 7.93, + "learning_rate": 1.3747395173414085e-05, + "loss": 0.0705, + "step": 25671 + }, + { + "epoch": 7.93, + "learning_rate": 1.374693149404855e-05, + "loss": 0.0721, + "step": 25672 + }, + { + "epoch": 7.93, + "learning_rate": 1.374646780531126e-05, + "loss": 0.0696, + "step": 25673 + }, + { + "epoch": 7.93, + "learning_rate": 1.3746004107203366e-05, + "loss": 0.0656, + "step": 25674 + }, + { + "epoch": 7.93, + "learning_rate": 1.3745540399726034e-05, + "loss": 0.0705, + "step": 25675 + }, + { + "epoch": 7.93, + "learning_rate": 1.3745076682880421e-05, + "loss": 0.0673, + "step": 25676 + }, + { + "epoch": 7.93, + "learning_rate": 1.374461295666769e-05, + "loss": 0.0706, + "step": 25677 + }, + { + "epoch": 7.93, + "learning_rate": 1.3744149221089001e-05, + "loss": 0.0664, + "step": 25678 + }, + { + "epoch": 7.93, + "learning_rate": 1.3743685476145508e-05, + "loss": 0.0716, + "step": 25679 + }, + { + "epoch": 7.93, + "learning_rate": 1.3743221721838376e-05, + "loss": 0.074, + "step": 25680 + }, + { + "epoch": 7.93, + "learning_rate": 1.3742757958168765e-05, + "loss": 0.0671, + "step": 25681 + }, + { + "epoch": 7.93, + "learning_rate": 1.374229418513783e-05, + "loss": 0.0723, + "step": 25682 + }, + { + "epoch": 7.93, + "learning_rate": 1.374183040274674e-05, + "loss": 0.0698, + "step": 25683 + }, + { + "epoch": 7.93, + "learning_rate": 1.3741366610996648e-05, + "loss": 0.0774, + "step": 25684 + }, + { + "epoch": 7.93, + "learning_rate": 1.3740902809888712e-05, + "loss": 0.074, + "step": 25685 + }, + { + "epoch": 7.93, + "learning_rate": 1.3740438999424099e-05, + "loss": 0.0701, + "step": 25686 + }, + { + "epoch": 7.93, + "learning_rate": 1.3739975179603965e-05, + "loss": 0.071, + "step": 25687 + }, + { + "epoch": 7.93, + "learning_rate": 1.3739511350429471e-05, + "loss": 0.0718, + "step": 25688 + }, + { + "epoch": 7.93, + "learning_rate": 1.3739047511901777e-05, + "loss": 0.0745, + "step": 25689 + }, + { + "epoch": 7.93, + "learning_rate": 1.3738583664022044e-05, + "loss": 0.0732, + "step": 25690 + }, + { + "epoch": 7.93, + "learning_rate": 1.3738119806791432e-05, + "loss": 0.0787, + "step": 25691 + }, + { + "epoch": 7.93, + "learning_rate": 1.3737655940211099e-05, + "loss": 0.0718, + "step": 25692 + }, + { + "epoch": 7.93, + "learning_rate": 1.3737192064282207e-05, + "loss": 0.0778, + "step": 25693 + }, + { + "epoch": 7.93, + "learning_rate": 1.3736728179005917e-05, + "loss": 0.0769, + "step": 25694 + }, + { + "epoch": 7.94, + "learning_rate": 1.3736264284383386e-05, + "loss": 0.0743, + "step": 25695 + }, + { + "epoch": 7.94, + "learning_rate": 1.373580038041578e-05, + "loss": 0.0837, + "step": 25696 + }, + { + "epoch": 7.94, + "learning_rate": 1.3735336467104254e-05, + "loss": 0.0714, + "step": 25697 + }, + { + "epoch": 7.94, + "learning_rate": 1.3734872544449971e-05, + "loss": 0.0737, + "step": 25698 + }, + { + "epoch": 7.94, + "learning_rate": 1.3734408612454088e-05, + "loss": 0.0696, + "step": 25699 + }, + { + "epoch": 7.94, + "learning_rate": 1.3733944671117771e-05, + "loss": 0.0759, + "step": 25700 + }, + { + "epoch": 7.94, + "learning_rate": 1.3733480720442178e-05, + "loss": 0.0685, + "step": 25701 + }, + { + "epoch": 7.94, + "learning_rate": 1.3733016760428466e-05, + "loss": 0.0722, + "step": 25702 + }, + { + "epoch": 7.94, + "learning_rate": 1.3732552791077798e-05, + "loss": 0.0678, + "step": 25703 + }, + { + "epoch": 7.94, + "learning_rate": 1.3732088812391338e-05, + "loss": 0.0702, + "step": 25704 + }, + { + "epoch": 7.94, + "learning_rate": 1.373162482437024e-05, + "loss": 0.0731, + "step": 25705 + }, + { + "epoch": 7.94, + "learning_rate": 1.373116082701567e-05, + "loss": 0.0744, + "step": 25706 + }, + { + "epoch": 7.94, + "learning_rate": 1.3730696820328783e-05, + "loss": 0.0759, + "step": 25707 + }, + { + "epoch": 7.94, + "learning_rate": 1.3730232804310744e-05, + "loss": 0.0755, + "step": 25708 + }, + { + "epoch": 7.94, + "learning_rate": 1.3729768778962716e-05, + "loss": 0.0696, + "step": 25709 + }, + { + "epoch": 7.94, + "learning_rate": 1.3729304744285852e-05, + "loss": 0.074, + "step": 25710 + }, + { + "epoch": 7.94, + "learning_rate": 1.3728840700281319e-05, + "loss": 0.0656, + "step": 25711 + }, + { + "epoch": 7.94, + "learning_rate": 1.3728376646950275e-05, + "loss": 0.0794, + "step": 25712 + }, + { + "epoch": 7.94, + "learning_rate": 1.3727912584293877e-05, + "loss": 0.0723, + "step": 25713 + }, + { + "epoch": 7.94, + "learning_rate": 1.3727448512313295e-05, + "loss": 0.0725, + "step": 25714 + }, + { + "epoch": 7.94, + "learning_rate": 1.3726984431009682e-05, + "loss": 0.0774, + "step": 25715 + }, + { + "epoch": 7.94, + "learning_rate": 1.3726520340384203e-05, + "loss": 0.0772, + "step": 25716 + }, + { + "epoch": 7.94, + "learning_rate": 1.3726056240438015e-05, + "loss": 0.0734, + "step": 25717 + }, + { + "epoch": 7.94, + "learning_rate": 1.372559213117228e-05, + "loss": 0.0755, + "step": 25718 + }, + { + "epoch": 7.94, + "learning_rate": 1.3725128012588163e-05, + "loss": 0.0798, + "step": 25719 + }, + { + "epoch": 7.94, + "learning_rate": 1.3724663884686817e-05, + "loss": 0.0721, + "step": 25720 + }, + { + "epoch": 7.94, + "learning_rate": 1.372419974746941e-05, + "loss": 0.0688, + "step": 25721 + }, + { + "epoch": 7.94, + "learning_rate": 1.37237356009371e-05, + "loss": 0.0714, + "step": 25722 + }, + { + "epoch": 7.94, + "learning_rate": 1.3723271445091048e-05, + "loss": 0.077, + "step": 25723 + }, + { + "epoch": 7.94, + "learning_rate": 1.3722807279932415e-05, + "loss": 0.0629, + "step": 25724 + }, + { + "epoch": 7.94, + "learning_rate": 1.3722343105462361e-05, + "loss": 0.0731, + "step": 25725 + }, + { + "epoch": 7.94, + "learning_rate": 1.372187892168205e-05, + "loss": 0.0722, + "step": 25726 + }, + { + "epoch": 7.95, + "learning_rate": 1.3721414728592639e-05, + "loss": 0.0704, + "step": 25727 + }, + { + "epoch": 7.95, + "learning_rate": 1.3720950526195291e-05, + "loss": 0.0744, + "step": 25728 + }, + { + "epoch": 7.95, + "learning_rate": 1.372048631449117e-05, + "loss": 0.07, + "step": 25729 + }, + { + "epoch": 7.95, + "learning_rate": 1.372002209348143e-05, + "loss": 0.0794, + "step": 25730 + }, + { + "epoch": 7.95, + "learning_rate": 1.3719557863167238e-05, + "loss": 0.076, + "step": 25731 + }, + { + "epoch": 7.95, + "learning_rate": 1.3719093623549755e-05, + "loss": 0.0731, + "step": 25732 + }, + { + "epoch": 7.95, + "learning_rate": 1.3718629374630139e-05, + "loss": 0.0705, + "step": 25733 + }, + { + "epoch": 7.95, + "learning_rate": 1.3718165116409553e-05, + "loss": 0.0792, + "step": 25734 + }, + { + "epoch": 7.95, + "learning_rate": 1.371770084888916e-05, + "loss": 0.068, + "step": 25735 + }, + { + "epoch": 7.95, + "learning_rate": 1.3717236572070115e-05, + "loss": 0.0721, + "step": 25736 + }, + { + "epoch": 7.95, + "learning_rate": 1.3716772285953585e-05, + "loss": 0.0684, + "step": 25737 + }, + { + "epoch": 7.95, + "learning_rate": 1.3716307990540729e-05, + "loss": 0.0813, + "step": 25738 + }, + { + "epoch": 7.95, + "learning_rate": 1.371584368583271e-05, + "loss": 0.0675, + "step": 25739 + }, + { + "epoch": 7.95, + "learning_rate": 1.3715379371830691e-05, + "loss": 0.0727, + "step": 25740 + }, + { + "epoch": 7.95, + "learning_rate": 1.3714915048535824e-05, + "loss": 0.0783, + "step": 25741 + }, + { + "epoch": 7.95, + "learning_rate": 1.3714450715949283e-05, + "loss": 0.0684, + "step": 25742 + }, + { + "epoch": 7.95, + "learning_rate": 1.371398637407222e-05, + "loss": 0.0732, + "step": 25743 + }, + { + "epoch": 7.95, + "learning_rate": 1.3713522022905799e-05, + "loss": 0.0809, + "step": 25744 + }, + { + "epoch": 7.95, + "learning_rate": 1.3713057662451186e-05, + "loss": 0.0745, + "step": 25745 + }, + { + "epoch": 7.95, + "learning_rate": 1.3712593292709535e-05, + "loss": 0.0751, + "step": 25746 + }, + { + "epoch": 7.95, + "learning_rate": 1.3712128913682013e-05, + "loss": 0.0795, + "step": 25747 + }, + { + "epoch": 7.95, + "learning_rate": 1.371166452536978e-05, + "loss": 0.0743, + "step": 25748 + }, + { + "epoch": 7.95, + "learning_rate": 1.3711200127773994e-05, + "loss": 0.0796, + "step": 25749 + }, + { + "epoch": 7.95, + "learning_rate": 1.3710735720895821e-05, + "loss": 0.0747, + "step": 25750 + }, + { + "epoch": 7.95, + "learning_rate": 1.3710271304736422e-05, + "loss": 0.0796, + "step": 25751 + }, + { + "epoch": 7.95, + "learning_rate": 1.3709806879296956e-05, + "loss": 0.0737, + "step": 25752 + }, + { + "epoch": 7.95, + "learning_rate": 1.3709342444578589e-05, + "loss": 0.0657, + "step": 25753 + }, + { + "epoch": 7.95, + "learning_rate": 1.3708878000582477e-05, + "loss": 0.0798, + "step": 25754 + }, + { + "epoch": 7.95, + "learning_rate": 1.3708413547309786e-05, + "loss": 0.0708, + "step": 25755 + }, + { + "epoch": 7.95, + "learning_rate": 1.3707949084761678e-05, + "loss": 0.0661, + "step": 25756 + }, + { + "epoch": 7.95, + "learning_rate": 1.370748461293931e-05, + "loss": 0.0788, + "step": 25757 + }, + { + "epoch": 7.95, + "learning_rate": 1.3707020131843849e-05, + "loss": 0.0728, + "step": 25758 + }, + { + "epoch": 7.95, + "learning_rate": 1.3706555641476456e-05, + "loss": 0.0741, + "step": 25759 + }, + { + "epoch": 7.96, + "learning_rate": 1.370609114183829e-05, + "loss": 0.0774, + "step": 25760 + }, + { + "epoch": 7.96, + "learning_rate": 1.370562663293051e-05, + "loss": 0.0696, + "step": 25761 + }, + { + "epoch": 7.96, + "learning_rate": 1.3705162114754287e-05, + "loss": 0.0708, + "step": 25762 + }, + { + "epoch": 7.96, + "learning_rate": 1.3704697587310778e-05, + "loss": 0.0743, + "step": 25763 + }, + { + "epoch": 7.96, + "learning_rate": 1.370423305060114e-05, + "loss": 0.0696, + "step": 25764 + }, + { + "epoch": 7.96, + "learning_rate": 1.3703768504626544e-05, + "loss": 0.067, + "step": 25765 + }, + { + "epoch": 7.96, + "learning_rate": 1.3703303949388147e-05, + "loss": 0.0752, + "step": 25766 + }, + { + "epoch": 7.96, + "learning_rate": 1.3702839384887108e-05, + "loss": 0.0672, + "step": 25767 + }, + { + "epoch": 7.96, + "learning_rate": 1.3702374811124597e-05, + "loss": 0.0721, + "step": 25768 + }, + { + "epoch": 7.96, + "learning_rate": 1.3701910228101767e-05, + "loss": 0.0737, + "step": 25769 + }, + { + "epoch": 7.96, + "learning_rate": 1.3701445635819788e-05, + "loss": 0.0771, + "step": 25770 + }, + { + "epoch": 7.96, + "learning_rate": 1.3700981034279814e-05, + "loss": 0.0825, + "step": 25771 + }, + { + "epoch": 7.96, + "learning_rate": 1.3700516423483012e-05, + "loss": 0.0735, + "step": 25772 + }, + { + "epoch": 7.96, + "learning_rate": 1.3700051803430548e-05, + "loss": 0.0745, + "step": 25773 + }, + { + "epoch": 7.96, + "learning_rate": 1.3699587174123577e-05, + "loss": 0.075, + "step": 25774 + }, + { + "epoch": 7.96, + "learning_rate": 1.3699122535563265e-05, + "loss": 0.0745, + "step": 25775 + }, + { + "epoch": 7.96, + "learning_rate": 1.369865788775077e-05, + "loss": 0.0635, + "step": 25776 + }, + { + "epoch": 7.96, + "learning_rate": 1.3698193230687258e-05, + "loss": 0.0715, + "step": 25777 + }, + { + "epoch": 7.96, + "learning_rate": 1.3697728564373893e-05, + "loss": 0.0804, + "step": 25778 + }, + { + "epoch": 7.96, + "learning_rate": 1.3697263888811832e-05, + "loss": 0.0676, + "step": 25779 + }, + { + "epoch": 7.96, + "learning_rate": 1.3696799204002239e-05, + "loss": 0.0706, + "step": 25780 + }, + { + "epoch": 7.96, + "learning_rate": 1.3696334509946278e-05, + "loss": 0.0741, + "step": 25781 + }, + { + "epoch": 7.96, + "learning_rate": 1.3695869806645111e-05, + "loss": 0.0715, + "step": 25782 + }, + { + "epoch": 7.96, + "learning_rate": 1.3695405094099897e-05, + "loss": 0.0717, + "step": 25783 + }, + { + "epoch": 7.96, + "learning_rate": 1.3694940372311802e-05, + "loss": 0.0725, + "step": 25784 + }, + { + "epoch": 7.96, + "learning_rate": 1.3694475641281987e-05, + "loss": 0.073, + "step": 25785 + }, + { + "epoch": 7.96, + "learning_rate": 1.3694010901011616e-05, + "loss": 0.0662, + "step": 25786 + }, + { + "epoch": 7.96, + "learning_rate": 1.369354615150185e-05, + "loss": 0.076, + "step": 25787 + }, + { + "epoch": 7.96, + "learning_rate": 1.369308139275385e-05, + "loss": 0.076, + "step": 25788 + }, + { + "epoch": 7.96, + "learning_rate": 1.3692616624768782e-05, + "loss": 0.0735, + "step": 25789 + }, + { + "epoch": 7.96, + "learning_rate": 1.3692151847547803e-05, + "loss": 0.0764, + "step": 25790 + }, + { + "epoch": 7.96, + "learning_rate": 1.3691687061092083e-05, + "loss": 0.0791, + "step": 25791 + }, + { + "epoch": 7.97, + "learning_rate": 1.3691222265402777e-05, + "loss": 0.0697, + "step": 25792 + }, + { + "epoch": 7.97, + "learning_rate": 1.3690757460481053e-05, + "loss": 0.0706, + "step": 25793 + }, + { + "epoch": 7.97, + "learning_rate": 1.3690292646328072e-05, + "loss": 0.0689, + "step": 25794 + }, + { + "epoch": 7.97, + "learning_rate": 1.368982782294499e-05, + "loss": 0.0757, + "step": 25795 + }, + { + "epoch": 7.97, + "learning_rate": 1.3689362990332984e-05, + "loss": 0.0736, + "step": 25796 + }, + { + "epoch": 7.97, + "learning_rate": 1.3688898148493204e-05, + "loss": 0.0755, + "step": 25797 + }, + { + "epoch": 7.97, + "learning_rate": 1.3688433297426813e-05, + "loss": 0.0722, + "step": 25798 + }, + { + "epoch": 7.97, + "learning_rate": 1.3687968437134984e-05, + "loss": 0.0686, + "step": 25799 + }, + { + "epoch": 7.97, + "learning_rate": 1.3687503567618872e-05, + "loss": 0.0667, + "step": 25800 + }, + { + "epoch": 7.97, + "learning_rate": 1.368703868887964e-05, + "loss": 0.0741, + "step": 25801 + }, + { + "epoch": 7.97, + "learning_rate": 1.3686573800918452e-05, + "loss": 0.0713, + "step": 25802 + }, + { + "epoch": 7.97, + "learning_rate": 1.3686108903736468e-05, + "loss": 0.0725, + "step": 25803 + }, + { + "epoch": 7.97, + "learning_rate": 1.3685643997334859e-05, + "loss": 0.0753, + "step": 25804 + }, + { + "epoch": 7.97, + "learning_rate": 1.368517908171478e-05, + "loss": 0.0644, + "step": 25805 + }, + { + "epoch": 7.97, + "learning_rate": 1.3684714156877393e-05, + "loss": 0.0671, + "step": 25806 + }, + { + "epoch": 7.97, + "learning_rate": 1.3684249222823866e-05, + "loss": 0.0835, + "step": 25807 + }, + { + "epoch": 7.97, + "learning_rate": 1.368378427955536e-05, + "loss": 0.0774, + "step": 25808 + }, + { + "epoch": 7.97, + "learning_rate": 1.3683319327073035e-05, + "loss": 0.0632, + "step": 25809 + }, + { + "epoch": 7.97, + "learning_rate": 1.368285436537806e-05, + "loss": 0.0711, + "step": 25810 + }, + { + "epoch": 7.97, + "learning_rate": 1.3682389394471591e-05, + "loss": 0.0712, + "step": 25811 + }, + { + "epoch": 7.97, + "learning_rate": 1.3681924414354798e-05, + "loss": 0.0708, + "step": 25812 + }, + { + "epoch": 7.97, + "learning_rate": 1.368145942502884e-05, + "loss": 0.0694, + "step": 25813 + }, + { + "epoch": 7.97, + "learning_rate": 1.368099442649488e-05, + "loss": 0.0695, + "step": 25814 + }, + { + "epoch": 7.97, + "learning_rate": 1.368052941875408e-05, + "loss": 0.0672, + "step": 25815 + }, + { + "epoch": 7.97, + "learning_rate": 1.3680064401807607e-05, + "loss": 0.0738, + "step": 25816 + }, + { + "epoch": 7.97, + "learning_rate": 1.3679599375656621e-05, + "loss": 0.077, + "step": 25817 + }, + { + "epoch": 7.97, + "learning_rate": 1.3679134340302285e-05, + "loss": 0.0722, + "step": 25818 + }, + { + "epoch": 7.97, + "learning_rate": 1.3678669295745763e-05, + "loss": 0.0717, + "step": 25819 + }, + { + "epoch": 7.97, + "learning_rate": 1.3678204241988217e-05, + "loss": 0.0731, + "step": 25820 + }, + { + "epoch": 7.97, + "learning_rate": 1.3677739179030813e-05, + "loss": 0.0681, + "step": 25821 + }, + { + "epoch": 7.97, + "learning_rate": 1.3677274106874713e-05, + "loss": 0.0741, + "step": 25822 + }, + { + "epoch": 7.97, + "learning_rate": 1.3676809025521078e-05, + "loss": 0.0739, + "step": 25823 + }, + { + "epoch": 7.98, + "learning_rate": 1.3676343934971077e-05, + "loss": 0.0735, + "step": 25824 + }, + { + "epoch": 7.98, + "learning_rate": 1.3675878835225866e-05, + "loss": 0.0723, + "step": 25825 + }, + { + "epoch": 7.98, + "learning_rate": 1.367541372628661e-05, + "loss": 0.073, + "step": 25826 + }, + { + "epoch": 7.98, + "learning_rate": 1.3674948608154479e-05, + "loss": 0.0763, + "step": 25827 + }, + { + "epoch": 7.98, + "learning_rate": 1.3674483480830627e-05, + "loss": 0.0731, + "step": 25828 + }, + { + "epoch": 7.98, + "learning_rate": 1.3674018344316224e-05, + "loss": 0.0725, + "step": 25829 + }, + { + "epoch": 7.98, + "learning_rate": 1.367355319861243e-05, + "loss": 0.0771, + "step": 25830 + }, + { + "epoch": 7.98, + "learning_rate": 1.3673088043720409e-05, + "loss": 0.076, + "step": 25831 + }, + { + "epoch": 7.98, + "learning_rate": 1.3672622879641324e-05, + "loss": 0.0728, + "step": 25832 + }, + { + "epoch": 7.98, + "learning_rate": 1.3672157706376342e-05, + "loss": 0.0817, + "step": 25833 + }, + { + "epoch": 7.98, + "learning_rate": 1.367169252392662e-05, + "loss": 0.0685, + "step": 25834 + }, + { + "epoch": 7.98, + "learning_rate": 1.367122733229333e-05, + "loss": 0.0808, + "step": 25835 + }, + { + "epoch": 7.98, + "learning_rate": 1.3670762131477629e-05, + "loss": 0.0752, + "step": 25836 + }, + { + "epoch": 7.98, + "learning_rate": 1.3670296921480681e-05, + "loss": 0.0828, + "step": 25837 + }, + { + "epoch": 7.98, + "learning_rate": 1.3669831702303654e-05, + "loss": 0.083, + "step": 25838 + }, + { + "epoch": 7.98, + "learning_rate": 1.3669366473947704e-05, + "loss": 0.0695, + "step": 25839 + }, + { + "epoch": 7.98, + "learning_rate": 1.3668901236414002e-05, + "loss": 0.0732, + "step": 25840 + }, + { + "epoch": 7.98, + "learning_rate": 1.366843598970371e-05, + "loss": 0.0781, + "step": 25841 + }, + { + "epoch": 7.98, + "learning_rate": 1.3667970733817988e-05, + "loss": 0.0721, + "step": 25842 + }, + { + "epoch": 7.98, + "learning_rate": 1.3667505468758002e-05, + "loss": 0.0731, + "step": 25843 + }, + { + "epoch": 7.98, + "learning_rate": 1.3667040194524919e-05, + "loss": 0.0755, + "step": 25844 + }, + { + "epoch": 7.98, + "learning_rate": 1.3666574911119898e-05, + "loss": 0.0879, + "step": 25845 + }, + { + "epoch": 7.98, + "learning_rate": 1.3666109618544103e-05, + "loss": 0.0758, + "step": 25846 + }, + { + "epoch": 7.98, + "learning_rate": 1.3665644316798702e-05, + "loss": 0.0729, + "step": 25847 + }, + { + "epoch": 7.98, + "learning_rate": 1.3665179005884855e-05, + "loss": 0.07, + "step": 25848 + }, + { + "epoch": 7.98, + "learning_rate": 1.3664713685803723e-05, + "loss": 0.0744, + "step": 25849 + }, + { + "epoch": 7.98, + "learning_rate": 1.366424835655648e-05, + "loss": 0.0776, + "step": 25850 + }, + { + "epoch": 7.98, + "learning_rate": 1.366378301814428e-05, + "loss": 0.0722, + "step": 25851 + }, + { + "epoch": 7.98, + "learning_rate": 1.366331767056829e-05, + "loss": 0.0658, + "step": 25852 + }, + { + "epoch": 7.98, + "learning_rate": 1.3662852313829676e-05, + "loss": 0.0746, + "step": 25853 + }, + { + "epoch": 7.98, + "learning_rate": 1.3662386947929598e-05, + "loss": 0.0772, + "step": 25854 + }, + { + "epoch": 7.98, + "learning_rate": 1.3661921572869226e-05, + "loss": 0.0823, + "step": 25855 + }, + { + "epoch": 7.98, + "learning_rate": 1.3661456188649717e-05, + "loss": 0.0761, + "step": 25856 + }, + { + "epoch": 7.99, + "learning_rate": 1.3660990795272237e-05, + "loss": 0.0729, + "step": 25857 + }, + { + "epoch": 7.99, + "learning_rate": 1.3660525392737959e-05, + "loss": 0.0751, + "step": 25858 + }, + { + "epoch": 7.99, + "learning_rate": 1.3660059981048033e-05, + "loss": 0.0673, + "step": 25859 + }, + { + "epoch": 7.99, + "learning_rate": 1.3659594560203628e-05, + "loss": 0.0669, + "step": 25860 + }, + { + "epoch": 7.99, + "learning_rate": 1.3659129130205912e-05, + "loss": 0.0733, + "step": 25861 + }, + { + "epoch": 7.99, + "learning_rate": 1.3658663691056047e-05, + "loss": 0.0753, + "step": 25862 + }, + { + "epoch": 7.99, + "learning_rate": 1.3658198242755196e-05, + "loss": 0.0774, + "step": 25863 + }, + { + "epoch": 7.99, + "learning_rate": 1.3657732785304526e-05, + "loss": 0.0754, + "step": 25864 + }, + { + "epoch": 7.99, + "learning_rate": 1.3657267318705196e-05, + "loss": 0.0808, + "step": 25865 + }, + { + "epoch": 7.99, + "learning_rate": 1.3656801842958375e-05, + "loss": 0.0713, + "step": 25866 + }, + { + "epoch": 7.99, + "learning_rate": 1.3656336358065225e-05, + "loss": 0.0785, + "step": 25867 + }, + { + "epoch": 7.99, + "learning_rate": 1.3655870864026912e-05, + "loss": 0.0731, + "step": 25868 + }, + { + "epoch": 7.99, + "learning_rate": 1.3655405360844597e-05, + "loss": 0.0638, + "step": 25869 + }, + { + "epoch": 7.99, + "learning_rate": 1.3654939848519451e-05, + "loss": 0.0745, + "step": 25870 + }, + { + "epoch": 7.99, + "learning_rate": 1.365447432705263e-05, + "loss": 0.0762, + "step": 25871 + }, + { + "epoch": 7.99, + "learning_rate": 1.3654008796445304e-05, + "loss": 0.0823, + "step": 25872 + }, + { + "epoch": 7.99, + "learning_rate": 1.3653543256698635e-05, + "loss": 0.0693, + "step": 25873 + }, + { + "epoch": 7.99, + "learning_rate": 1.3653077707813787e-05, + "loss": 0.0732, + "step": 25874 + }, + { + "epoch": 7.99, + "learning_rate": 1.3652612149791927e-05, + "loss": 0.0707, + "step": 25875 + }, + { + "epoch": 7.99, + "learning_rate": 1.3652146582634218e-05, + "loss": 0.0695, + "step": 25876 + }, + { + "epoch": 7.99, + "learning_rate": 1.3651681006341822e-05, + "loss": 0.0718, + "step": 25877 + }, + { + "epoch": 7.99, + "learning_rate": 1.3651215420915906e-05, + "loss": 0.077, + "step": 25878 + }, + { + "epoch": 7.99, + "learning_rate": 1.3650749826357637e-05, + "loss": 0.0709, + "step": 25879 + }, + { + "epoch": 7.99, + "learning_rate": 1.3650284222668174e-05, + "loss": 0.0827, + "step": 25880 + }, + { + "epoch": 7.99, + "learning_rate": 1.3649818609848686e-05, + "loss": 0.0696, + "step": 25881 + }, + { + "epoch": 7.99, + "learning_rate": 1.3649352987900336e-05, + "loss": 0.0693, + "step": 25882 + }, + { + "epoch": 7.99, + "learning_rate": 1.3648887356824288e-05, + "loss": 0.0735, + "step": 25883 + }, + { + "epoch": 7.99, + "learning_rate": 1.3648421716621707e-05, + "loss": 0.073, + "step": 25884 + }, + { + "epoch": 7.99, + "learning_rate": 1.3647956067293756e-05, + "loss": 0.08, + "step": 25885 + }, + { + "epoch": 7.99, + "learning_rate": 1.3647490408841604e-05, + "loss": 0.0705, + "step": 25886 + }, + { + "epoch": 7.99, + "learning_rate": 1.3647024741266415e-05, + "loss": 0.0684, + "step": 25887 + }, + { + "epoch": 7.99, + "learning_rate": 1.3646559064569349e-05, + "loss": 0.0812, + "step": 25888 + }, + { + "epoch": 8.0, + "learning_rate": 1.3646093378751574e-05, + "loss": 0.0702, + "step": 25889 + }, + { + "epoch": 8.0, + "learning_rate": 1.3645627683814256e-05, + "loss": 0.0845, + "step": 25890 + }, + { + "epoch": 8.0, + "learning_rate": 1.3645161979758554e-05, + "loss": 0.0719, + "step": 25891 + }, + { + "epoch": 8.0, + "learning_rate": 1.3644696266585642e-05, + "loss": 0.0695, + "step": 25892 + }, + { + "epoch": 8.0, + "learning_rate": 1.3644230544296678e-05, + "loss": 0.0752, + "step": 25893 + }, + { + "epoch": 8.0, + "learning_rate": 1.3643764812892828e-05, + "loss": 0.0759, + "step": 25894 + }, + { + "epoch": 8.0, + "learning_rate": 1.3643299072375258e-05, + "loss": 0.0756, + "step": 25895 + }, + { + "epoch": 8.0, + "learning_rate": 1.3642833322745133e-05, + "loss": 0.0726, + "step": 25896 + }, + { + "epoch": 8.0, + "learning_rate": 1.3642367564003618e-05, + "loss": 0.0651, + "step": 25897 + }, + { + "epoch": 8.0, + "learning_rate": 1.3641901796151878e-05, + "loss": 0.0653, + "step": 25898 + }, + { + "epoch": 8.0, + "learning_rate": 1.3641436019191076e-05, + "loss": 0.0726, + "step": 25899 + }, + { + "epoch": 8.0, + "learning_rate": 1.3640970233122376e-05, + "loss": 0.0797, + "step": 25900 + }, + { + "epoch": 8.0, + "learning_rate": 1.3640504437946949e-05, + "loss": 0.0767, + "step": 25901 + }, + { + "epoch": 8.0, + "learning_rate": 1.3640038633665955e-05, + "loss": 0.0777, + "step": 25902 + }, + { + "epoch": 8.0, + "learning_rate": 1.3639572820280563e-05, + "loss": 0.0707, + "step": 25903 + }, + { + "epoch": 8.0, + "learning_rate": 1.3639106997791933e-05, + "loss": 0.0736, + "step": 25904 + }, + { + "epoch": 8.0, + "learning_rate": 1.3638641166201231e-05, + "loss": 0.0644, + "step": 25905 + }, + { + "epoch": 8.0, + "learning_rate": 1.3638175325509626e-05, + "loss": 0.0388, + "step": 25906 + }, + { + "epoch": 8.0, + "learning_rate": 1.3637709475718284e-05, + "loss": 0.0319, + "step": 25907 + }, + { + "epoch": 8.0, + "learning_rate": 1.3637243616828362e-05, + "loss": 0.0335, + "step": 25908 + }, + { + "epoch": 8.0, + "learning_rate": 1.3636777748841032e-05, + "loss": 0.0351, + "step": 25909 + }, + { + "epoch": 8.0, + "learning_rate": 1.363631187175746e-05, + "loss": 0.0327, + "step": 25910 + }, + { + "epoch": 8.0, + "learning_rate": 1.3635845985578803e-05, + "loss": 0.0287, + "step": 25911 + }, + { + "epoch": 8.0, + "learning_rate": 1.3635380090306238e-05, + "loss": 0.0326, + "step": 25912 + }, + { + "epoch": 8.0, + "learning_rate": 1.3634914185940922e-05, + "loss": 0.0353, + "step": 25913 + }, + { + "epoch": 8.0, + "learning_rate": 1.3634448272484022e-05, + "loss": 0.0333, + "step": 25914 + }, + { + "epoch": 8.0, + "learning_rate": 1.3633982349936705e-05, + "loss": 0.0274, + "step": 25915 + }, + { + "epoch": 8.0, + "learning_rate": 1.3633516418300134e-05, + "loss": 0.029, + "step": 25916 + }, + { + "epoch": 8.0, + "learning_rate": 1.3633050477575478e-05, + "loss": 0.0294, + "step": 25917 + }, + { + "epoch": 8.0, + "learning_rate": 1.3632584527763898e-05, + "loss": 0.0309, + "step": 25918 + }, + { + "epoch": 8.0, + "learning_rate": 1.3632118568866562e-05, + "loss": 0.0314, + "step": 25919 + }, + { + "epoch": 8.0, + "learning_rate": 1.3631652600884635e-05, + "loss": 0.0321, + "step": 25920 + }, + { + "epoch": 8.0, + "learning_rate": 1.3631186623819284e-05, + "loss": 0.0282, + "step": 25921 + }, + { + "epoch": 8.01, + "learning_rate": 1.3630720637671671e-05, + "loss": 0.0313, + "step": 25922 + }, + { + "epoch": 8.01, + "learning_rate": 1.3630254642442964e-05, + "loss": 0.029, + "step": 25923 + }, + { + "epoch": 8.01, + "learning_rate": 1.362978863813433e-05, + "loss": 0.0295, + "step": 25924 + }, + { + "epoch": 8.01, + "learning_rate": 1.362932262474693e-05, + "loss": 0.0311, + "step": 25925 + }, + { + "epoch": 8.01, + "learning_rate": 1.3628856602281932e-05, + "loss": 0.0293, + "step": 25926 + }, + { + "epoch": 8.01, + "learning_rate": 1.3628390570740506e-05, + "loss": 0.032, + "step": 25927 + }, + { + "epoch": 8.01, + "learning_rate": 1.3627924530123808e-05, + "loss": 0.0301, + "step": 25928 + }, + { + "epoch": 8.01, + "learning_rate": 1.3627458480433011e-05, + "loss": 0.0338, + "step": 25929 + }, + { + "epoch": 8.01, + "learning_rate": 1.3626992421669281e-05, + "loss": 0.0344, + "step": 25930 + }, + { + "epoch": 8.01, + "learning_rate": 1.3626526353833777e-05, + "loss": 0.0289, + "step": 25931 + }, + { + "epoch": 8.01, + "learning_rate": 1.3626060276927673e-05, + "loss": 0.0303, + "step": 25932 + }, + { + "epoch": 8.01, + "learning_rate": 1.3625594190952127e-05, + "loss": 0.0306, + "step": 25933 + }, + { + "epoch": 8.01, + "learning_rate": 1.3625128095908312e-05, + "loss": 0.0316, + "step": 25934 + }, + { + "epoch": 8.01, + "learning_rate": 1.3624661991797392e-05, + "loss": 0.0315, + "step": 25935 + }, + { + "epoch": 8.01, + "learning_rate": 1.3624195878620526e-05, + "loss": 0.0283, + "step": 25936 + }, + { + "epoch": 8.01, + "learning_rate": 1.362372975637889e-05, + "loss": 0.0312, + "step": 25937 + }, + { + "epoch": 8.01, + "learning_rate": 1.3623263625073645e-05, + "loss": 0.0325, + "step": 25938 + }, + { + "epoch": 8.01, + "learning_rate": 1.362279748470595e-05, + "loss": 0.0276, + "step": 25939 + }, + { + "epoch": 8.01, + "learning_rate": 1.3622331335276986e-05, + "loss": 0.029, + "step": 25940 + }, + { + "epoch": 8.01, + "learning_rate": 1.3621865176787906e-05, + "loss": 0.0335, + "step": 25941 + }, + { + "epoch": 8.01, + "learning_rate": 1.3621399009239881e-05, + "loss": 0.0303, + "step": 25942 + }, + { + "epoch": 8.01, + "learning_rate": 1.3620932832634078e-05, + "loss": 0.0275, + "step": 25943 + }, + { + "epoch": 8.01, + "learning_rate": 1.3620466646971661e-05, + "loss": 0.0294, + "step": 25944 + }, + { + "epoch": 8.01, + "learning_rate": 1.3620000452253796e-05, + "loss": 0.028, + "step": 25945 + }, + { + "epoch": 8.01, + "learning_rate": 1.3619534248481649e-05, + "loss": 0.0303, + "step": 25946 + }, + { + "epoch": 8.01, + "learning_rate": 1.361906803565639e-05, + "loss": 0.0299, + "step": 25947 + }, + { + "epoch": 8.01, + "learning_rate": 1.3618601813779177e-05, + "loss": 0.0311, + "step": 25948 + }, + { + "epoch": 8.01, + "learning_rate": 1.3618135582851184e-05, + "loss": 0.0319, + "step": 25949 + }, + { + "epoch": 8.01, + "learning_rate": 1.3617669342873574e-05, + "loss": 0.0275, + "step": 25950 + }, + { + "epoch": 8.01, + "learning_rate": 1.3617203093847512e-05, + "loss": 0.0268, + "step": 25951 + }, + { + "epoch": 8.01, + "learning_rate": 1.3616736835774166e-05, + "loss": 0.0332, + "step": 25952 + }, + { + "epoch": 8.01, + "learning_rate": 1.3616270568654702e-05, + "loss": 0.03, + "step": 25953 + }, + { + "epoch": 8.02, + "learning_rate": 1.3615804292490284e-05, + "loss": 0.0285, + "step": 25954 + }, + { + "epoch": 8.02, + "learning_rate": 1.3615338007282082e-05, + "loss": 0.0295, + "step": 25955 + }, + { + "epoch": 8.02, + "learning_rate": 1.3614871713031259e-05, + "loss": 0.0298, + "step": 25956 + }, + { + "epoch": 8.02, + "learning_rate": 1.3614405409738983e-05, + "loss": 0.0282, + "step": 25957 + }, + { + "epoch": 8.02, + "learning_rate": 1.3613939097406421e-05, + "loss": 0.033, + "step": 25958 + }, + { + "epoch": 8.02, + "learning_rate": 1.3613472776034735e-05, + "loss": 0.0291, + "step": 25959 + }, + { + "epoch": 8.02, + "learning_rate": 1.3613006445625097e-05, + "loss": 0.0339, + "step": 25960 + }, + { + "epoch": 8.02, + "learning_rate": 1.3612540106178673e-05, + "loss": 0.0268, + "step": 25961 + }, + { + "epoch": 8.02, + "learning_rate": 1.3612073757696622e-05, + "loss": 0.0301, + "step": 25962 + }, + { + "epoch": 8.02, + "learning_rate": 1.361160740018012e-05, + "loss": 0.031, + "step": 25963 + }, + { + "epoch": 8.02, + "learning_rate": 1.3611141033630328e-05, + "loss": 0.0278, + "step": 25964 + }, + { + "epoch": 8.02, + "learning_rate": 1.3610674658048413e-05, + "loss": 0.0293, + "step": 25965 + }, + { + "epoch": 8.02, + "learning_rate": 1.3610208273435543e-05, + "loss": 0.0305, + "step": 25966 + }, + { + "epoch": 8.02, + "learning_rate": 1.3609741879792882e-05, + "loss": 0.0301, + "step": 25967 + }, + { + "epoch": 8.02, + "learning_rate": 1.36092754771216e-05, + "loss": 0.0306, + "step": 25968 + }, + { + "epoch": 8.02, + "learning_rate": 1.360880906542286e-05, + "loss": 0.0307, + "step": 25969 + }, + { + "epoch": 8.02, + "learning_rate": 1.360834264469783e-05, + "loss": 0.031, + "step": 25970 + }, + { + "epoch": 8.02, + "learning_rate": 1.360787621494768e-05, + "loss": 0.0305, + "step": 25971 + }, + { + "epoch": 8.02, + "learning_rate": 1.3607409776173572e-05, + "loss": 0.034, + "step": 25972 + }, + { + "epoch": 8.02, + "learning_rate": 1.3606943328376674e-05, + "loss": 0.0267, + "step": 25973 + }, + { + "epoch": 8.02, + "learning_rate": 1.3606476871558151e-05, + "loss": 0.03, + "step": 25974 + }, + { + "epoch": 8.02, + "learning_rate": 1.3606010405719175e-05, + "loss": 0.0297, + "step": 25975 + }, + { + "epoch": 8.02, + "learning_rate": 1.3605543930860908e-05, + "loss": 0.0295, + "step": 25976 + }, + { + "epoch": 8.02, + "learning_rate": 1.3605077446984516e-05, + "loss": 0.0275, + "step": 25977 + }, + { + "epoch": 8.02, + "learning_rate": 1.360461095409117e-05, + "loss": 0.0298, + "step": 25978 + }, + { + "epoch": 8.02, + "learning_rate": 1.3604144452182033e-05, + "loss": 0.0296, + "step": 25979 + }, + { + "epoch": 8.02, + "learning_rate": 1.3603677941258275e-05, + "loss": 0.0287, + "step": 25980 + }, + { + "epoch": 8.02, + "learning_rate": 1.3603211421321063e-05, + "loss": 0.0337, + "step": 25981 + }, + { + "epoch": 8.02, + "learning_rate": 1.3602744892371558e-05, + "loss": 0.0273, + "step": 25982 + }, + { + "epoch": 8.02, + "learning_rate": 1.3602278354410931e-05, + "loss": 0.0299, + "step": 25983 + }, + { + "epoch": 8.02, + "learning_rate": 1.3601811807440353e-05, + "loss": 0.0324, + "step": 25984 + }, + { + "epoch": 8.02, + "learning_rate": 1.3601345251460983e-05, + "loss": 0.0264, + "step": 25985 + }, + { + "epoch": 8.03, + "learning_rate": 1.3600878686473995e-05, + "loss": 0.0298, + "step": 25986 + }, + { + "epoch": 8.03, + "learning_rate": 1.3600412112480548e-05, + "loss": 0.03, + "step": 25987 + }, + { + "epoch": 8.03, + "learning_rate": 1.3599945529481815e-05, + "loss": 0.0312, + "step": 25988 + }, + { + "epoch": 8.03, + "learning_rate": 1.3599478937478965e-05, + "loss": 0.0326, + "step": 25989 + }, + { + "epoch": 8.03, + "learning_rate": 1.3599012336473158e-05, + "loss": 0.0288, + "step": 25990 + }, + { + "epoch": 8.03, + "learning_rate": 1.3598545726465568e-05, + "loss": 0.0322, + "step": 25991 + }, + { + "epoch": 8.03, + "learning_rate": 1.3598079107457358e-05, + "loss": 0.0305, + "step": 25992 + }, + { + "epoch": 8.03, + "learning_rate": 1.359761247944969e-05, + "loss": 0.029, + "step": 25993 + }, + { + "epoch": 8.03, + "learning_rate": 1.3597145842443747e-05, + "loss": 0.0278, + "step": 25994 + }, + { + "epoch": 8.03, + "learning_rate": 1.359667919644068e-05, + "loss": 0.0326, + "step": 25995 + }, + { + "epoch": 8.03, + "learning_rate": 1.3596212541441662e-05, + "loss": 0.0308, + "step": 25996 + }, + { + "epoch": 8.03, + "learning_rate": 1.3595745877447861e-05, + "loss": 0.0325, + "step": 25997 + }, + { + "epoch": 8.03, + "learning_rate": 1.3595279204460446e-05, + "loss": 0.0275, + "step": 25998 + }, + { + "epoch": 8.03, + "learning_rate": 1.3594812522480581e-05, + "loss": 0.0277, + "step": 25999 + }, + { + "epoch": 8.03, + "learning_rate": 1.3594345831509435e-05, + "loss": 0.0304, + "step": 26000 + }, + { + "epoch": 8.03, + "learning_rate": 1.3593879131548169e-05, + "loss": 0.0297, + "step": 26001 + }, + { + "epoch": 8.03, + "learning_rate": 1.3593412422597962e-05, + "loss": 0.0297, + "step": 26002 + }, + { + "epoch": 8.03, + "learning_rate": 1.3592945704659975e-05, + "loss": 0.031, + "step": 26003 + }, + { + "epoch": 8.03, + "learning_rate": 1.3592478977735373e-05, + "loss": 0.0329, + "step": 26004 + }, + { + "epoch": 8.03, + "learning_rate": 1.3592012241825327e-05, + "loss": 0.0301, + "step": 26005 + }, + { + "epoch": 8.03, + "learning_rate": 1.3591545496931003e-05, + "loss": 0.0282, + "step": 26006 + }, + { + "epoch": 8.03, + "learning_rate": 1.3591078743053567e-05, + "loss": 0.0271, + "step": 26007 + }, + { + "epoch": 8.03, + "learning_rate": 1.359061198019419e-05, + "loss": 0.0293, + "step": 26008 + }, + { + "epoch": 8.03, + "learning_rate": 1.3590145208354037e-05, + "loss": 0.0314, + "step": 26009 + }, + { + "epoch": 8.03, + "learning_rate": 1.3589678427534276e-05, + "loss": 0.0307, + "step": 26010 + }, + { + "epoch": 8.03, + "learning_rate": 1.3589211637736075e-05, + "loss": 0.0307, + "step": 26011 + }, + { + "epoch": 8.03, + "learning_rate": 1.3588744838960604e-05, + "loss": 0.0296, + "step": 26012 + }, + { + "epoch": 8.03, + "learning_rate": 1.3588278031209022e-05, + "loss": 0.0319, + "step": 26013 + }, + { + "epoch": 8.03, + "learning_rate": 1.3587811214482502e-05, + "loss": 0.0332, + "step": 26014 + }, + { + "epoch": 8.03, + "learning_rate": 1.3587344388782215e-05, + "loss": 0.0278, + "step": 26015 + }, + { + "epoch": 8.03, + "learning_rate": 1.3586877554109326e-05, + "loss": 0.0301, + "step": 26016 + }, + { + "epoch": 8.03, + "learning_rate": 1.3586410710465003e-05, + "loss": 0.0322, + "step": 26017 + }, + { + "epoch": 8.03, + "learning_rate": 1.3585943857850408e-05, + "loss": 0.029, + "step": 26018 + }, + { + "epoch": 8.04, + "learning_rate": 1.3585476996266715e-05, + "loss": 0.0301, + "step": 26019 + }, + { + "epoch": 8.04, + "learning_rate": 1.3585010125715092e-05, + "loss": 0.0326, + "step": 26020 + }, + { + "epoch": 8.04, + "learning_rate": 1.3584543246196702e-05, + "loss": 0.0328, + "step": 26021 + }, + { + "epoch": 8.04, + "learning_rate": 1.3584076357712719e-05, + "loss": 0.0293, + "step": 26022 + }, + { + "epoch": 8.04, + "learning_rate": 1.3583609460264306e-05, + "loss": 0.0288, + "step": 26023 + }, + { + "epoch": 8.04, + "learning_rate": 1.358314255385263e-05, + "loss": 0.0292, + "step": 26024 + }, + { + "epoch": 8.04, + "learning_rate": 1.3582675638478864e-05, + "loss": 0.0337, + "step": 26025 + }, + { + "epoch": 8.04, + "learning_rate": 1.3582208714144171e-05, + "loss": 0.0289, + "step": 26026 + }, + { + "epoch": 8.04, + "learning_rate": 1.3581741780849723e-05, + "loss": 0.0311, + "step": 26027 + }, + { + "epoch": 8.04, + "learning_rate": 1.3581274838596682e-05, + "loss": 0.0293, + "step": 26028 + }, + { + "epoch": 8.04, + "learning_rate": 1.3580807887386223e-05, + "loss": 0.0329, + "step": 26029 + }, + { + "epoch": 8.04, + "learning_rate": 1.3580340927219507e-05, + "loss": 0.0298, + "step": 26030 + }, + { + "epoch": 8.04, + "learning_rate": 1.3579873958097706e-05, + "loss": 0.0332, + "step": 26031 + }, + { + "epoch": 8.04, + "learning_rate": 1.357940698002199e-05, + "loss": 0.0399, + "step": 26032 + }, + { + "epoch": 8.04, + "learning_rate": 1.357893999299352e-05, + "loss": 0.0302, + "step": 26033 + }, + { + "epoch": 8.04, + "learning_rate": 1.3578472997013472e-05, + "loss": 0.0284, + "step": 26034 + }, + { + "epoch": 8.04, + "learning_rate": 1.357800599208301e-05, + "loss": 0.0302, + "step": 26035 + }, + { + "epoch": 8.04, + "learning_rate": 1.3577538978203301e-05, + "loss": 0.0333, + "step": 26036 + }, + { + "epoch": 8.04, + "learning_rate": 1.3577071955375515e-05, + "loss": 0.0305, + "step": 26037 + }, + { + "epoch": 8.04, + "learning_rate": 1.357660492360082e-05, + "loss": 0.028, + "step": 26038 + }, + { + "epoch": 8.04, + "learning_rate": 1.3576137882880383e-05, + "loss": 0.035, + "step": 26039 + }, + { + "epoch": 8.04, + "learning_rate": 1.3575670833215372e-05, + "loss": 0.0335, + "step": 26040 + }, + { + "epoch": 8.04, + "learning_rate": 1.3575203774606958e-05, + "loss": 0.0302, + "step": 26041 + }, + { + "epoch": 8.04, + "learning_rate": 1.3574736707056308e-05, + "loss": 0.0285, + "step": 26042 + }, + { + "epoch": 8.04, + "learning_rate": 1.3574269630564589e-05, + "loss": 0.0279, + "step": 26043 + }, + { + "epoch": 8.04, + "learning_rate": 1.3573802545132969e-05, + "loss": 0.0305, + "step": 26044 + }, + { + "epoch": 8.04, + "learning_rate": 1.3573335450762615e-05, + "loss": 0.0316, + "step": 26045 + }, + { + "epoch": 8.04, + "learning_rate": 1.3572868347454701e-05, + "loss": 0.0344, + "step": 26046 + }, + { + "epoch": 8.04, + "learning_rate": 1.3572401235210389e-05, + "loss": 0.0272, + "step": 26047 + }, + { + "epoch": 8.04, + "learning_rate": 1.3571934114030851e-05, + "loss": 0.0306, + "step": 26048 + }, + { + "epoch": 8.04, + "learning_rate": 1.3571466983917252e-05, + "loss": 0.0279, + "step": 26049 + }, + { + "epoch": 8.04, + "learning_rate": 1.3570999844870767e-05, + "loss": 0.0317, + "step": 26050 + }, + { + "epoch": 8.05, + "learning_rate": 1.357053269689256e-05, + "loss": 0.0288, + "step": 26051 + }, + { + "epoch": 8.05, + "learning_rate": 1.3570065539983794e-05, + "loss": 0.0284, + "step": 26052 + }, + { + "epoch": 8.05, + "learning_rate": 1.3569598374145646e-05, + "loss": 0.0327, + "step": 26053 + }, + { + "epoch": 8.05, + "learning_rate": 1.3569131199379284e-05, + "loss": 0.0366, + "step": 26054 + }, + { + "epoch": 8.05, + "learning_rate": 1.356866401568587e-05, + "loss": 0.0339, + "step": 26055 + }, + { + "epoch": 8.05, + "learning_rate": 1.356819682306658e-05, + "loss": 0.032, + "step": 26056 + }, + { + "epoch": 8.05, + "learning_rate": 1.3567729621522576e-05, + "loss": 0.0282, + "step": 26057 + }, + { + "epoch": 8.05, + "learning_rate": 1.356726241105503e-05, + "loss": 0.0286, + "step": 26058 + }, + { + "epoch": 8.05, + "learning_rate": 1.3566795191665113e-05, + "loss": 0.0262, + "step": 26059 + }, + { + "epoch": 8.05, + "learning_rate": 1.3566327963353986e-05, + "loss": 0.0259, + "step": 26060 + }, + { + "epoch": 8.05, + "learning_rate": 1.3565860726122827e-05, + "loss": 0.0277, + "step": 26061 + }, + { + "epoch": 8.05, + "learning_rate": 1.3565393479972797e-05, + "loss": 0.0343, + "step": 26062 + }, + { + "epoch": 8.05, + "learning_rate": 1.3564926224905066e-05, + "loss": 0.0347, + "step": 26063 + }, + { + "epoch": 8.05, + "learning_rate": 1.3564458960920808e-05, + "loss": 0.0282, + "step": 26064 + }, + { + "epoch": 8.05, + "learning_rate": 1.3563991688021185e-05, + "loss": 0.0293, + "step": 26065 + }, + { + "epoch": 8.05, + "learning_rate": 1.3563524406207371e-05, + "loss": 0.0316, + "step": 26066 + }, + { + "epoch": 8.05, + "learning_rate": 1.3563057115480531e-05, + "loss": 0.0259, + "step": 26067 + }, + { + "epoch": 8.05, + "learning_rate": 1.3562589815841838e-05, + "loss": 0.0323, + "step": 26068 + }, + { + "epoch": 8.05, + "learning_rate": 1.3562122507292454e-05, + "loss": 0.0269, + "step": 26069 + }, + { + "epoch": 8.05, + "learning_rate": 1.3561655189833554e-05, + "loss": 0.0313, + "step": 26070 + }, + { + "epoch": 8.05, + "learning_rate": 1.3561187863466307e-05, + "loss": 0.0292, + "step": 26071 + }, + { + "epoch": 8.05, + "learning_rate": 1.3560720528191875e-05, + "loss": 0.0331, + "step": 26072 + }, + { + "epoch": 8.05, + "learning_rate": 1.3560253184011436e-05, + "loss": 0.0305, + "step": 26073 + }, + { + "epoch": 8.05, + "learning_rate": 1.3559785830926152e-05, + "loss": 0.032, + "step": 26074 + }, + { + "epoch": 8.05, + "learning_rate": 1.3559318468937192e-05, + "loss": 0.0294, + "step": 26075 + }, + { + "epoch": 8.05, + "learning_rate": 1.3558851098045733e-05, + "loss": 0.0268, + "step": 26076 + }, + { + "epoch": 8.05, + "learning_rate": 1.3558383718252937e-05, + "loss": 0.0316, + "step": 26077 + }, + { + "epoch": 8.05, + "learning_rate": 1.355791632955997e-05, + "loss": 0.0333, + "step": 26078 + }, + { + "epoch": 8.05, + "learning_rate": 1.3557448931968012e-05, + "loss": 0.0308, + "step": 26079 + }, + { + "epoch": 8.05, + "learning_rate": 1.355698152547822e-05, + "loss": 0.0366, + "step": 26080 + }, + { + "epoch": 8.05, + "learning_rate": 1.355651411009177e-05, + "loss": 0.0295, + "step": 26081 + }, + { + "epoch": 8.05, + "learning_rate": 1.3556046685809829e-05, + "loss": 0.0287, + "step": 26082 + }, + { + "epoch": 8.05, + "learning_rate": 1.3555579252633564e-05, + "loss": 0.0314, + "step": 26083 + }, + { + "epoch": 8.06, + "learning_rate": 1.3555111810564152e-05, + "loss": 0.0314, + "step": 26084 + }, + { + "epoch": 8.06, + "learning_rate": 1.3554644359602755e-05, + "loss": 0.0296, + "step": 26085 + }, + { + "epoch": 8.06, + "learning_rate": 1.3554176899750544e-05, + "loss": 0.0296, + "step": 26086 + }, + { + "epoch": 8.06, + "learning_rate": 1.3553709431008688e-05, + "loss": 0.0267, + "step": 26087 + }, + { + "epoch": 8.06, + "learning_rate": 1.3553241953378357e-05, + "loss": 0.0326, + "step": 26088 + }, + { + "epoch": 8.06, + "learning_rate": 1.355277446686072e-05, + "loss": 0.0259, + "step": 26089 + }, + { + "epoch": 8.06, + "learning_rate": 1.3552306971456946e-05, + "loss": 0.0291, + "step": 26090 + }, + { + "epoch": 8.06, + "learning_rate": 1.3551839467168204e-05, + "loss": 0.0277, + "step": 26091 + }, + { + "epoch": 8.06, + "learning_rate": 1.3551371953995664e-05, + "loss": 0.0323, + "step": 26092 + }, + { + "epoch": 8.06, + "learning_rate": 1.3550904431940494e-05, + "loss": 0.0303, + "step": 26093 + }, + { + "epoch": 8.06, + "learning_rate": 1.3550436901003866e-05, + "loss": 0.0308, + "step": 26094 + }, + { + "epoch": 8.06, + "learning_rate": 1.3549969361186945e-05, + "loss": 0.0285, + "step": 26095 + }, + { + "epoch": 8.06, + "learning_rate": 1.3549501812490905e-05, + "loss": 0.0263, + "step": 26096 + }, + { + "epoch": 8.06, + "learning_rate": 1.3549034254916915e-05, + "loss": 0.028, + "step": 26097 + }, + { + "epoch": 8.06, + "learning_rate": 1.354856668846614e-05, + "loss": 0.0295, + "step": 26098 + }, + { + "epoch": 8.06, + "learning_rate": 1.3548099113139757e-05, + "loss": 0.0277, + "step": 26099 + }, + { + "epoch": 8.06, + "learning_rate": 1.3547631528938926e-05, + "loss": 0.0286, + "step": 26100 + }, + { + "epoch": 8.06, + "learning_rate": 1.3547163935864825e-05, + "loss": 0.0277, + "step": 26101 + }, + { + "epoch": 8.06, + "learning_rate": 1.354669633391862e-05, + "loss": 0.0303, + "step": 26102 + }, + { + "epoch": 8.06, + "learning_rate": 1.3546228723101477e-05, + "loss": 0.028, + "step": 26103 + }, + { + "epoch": 8.06, + "learning_rate": 1.3545761103414573e-05, + "loss": 0.0336, + "step": 26104 + }, + { + "epoch": 8.06, + "learning_rate": 1.3545293474859074e-05, + "loss": 0.0316, + "step": 26105 + }, + { + "epoch": 8.06, + "learning_rate": 1.3544825837436145e-05, + "loss": 0.0304, + "step": 26106 + }, + { + "epoch": 8.06, + "learning_rate": 1.3544358191146964e-05, + "loss": 0.0328, + "step": 26107 + }, + { + "epoch": 8.06, + "learning_rate": 1.3543890535992695e-05, + "loss": 0.0324, + "step": 26108 + }, + { + "epoch": 8.06, + "learning_rate": 1.3543422871974508e-05, + "loss": 0.0293, + "step": 26109 + }, + { + "epoch": 8.06, + "learning_rate": 1.3542955199093579e-05, + "loss": 0.0278, + "step": 26110 + }, + { + "epoch": 8.06, + "learning_rate": 1.3542487517351069e-05, + "loss": 0.0281, + "step": 26111 + }, + { + "epoch": 8.06, + "learning_rate": 1.3542019826748152e-05, + "loss": 0.0283, + "step": 26112 + }, + { + "epoch": 8.06, + "learning_rate": 1.3541552127285997e-05, + "loss": 0.0333, + "step": 26113 + }, + { + "epoch": 8.06, + "learning_rate": 1.3541084418965773e-05, + "loss": 0.0313, + "step": 26114 + }, + { + "epoch": 8.06, + "learning_rate": 1.3540616701788656e-05, + "loss": 0.0315, + "step": 26115 + }, + { + "epoch": 8.07, + "learning_rate": 1.3540148975755806e-05, + "loss": 0.0322, + "step": 26116 + }, + { + "epoch": 8.07, + "learning_rate": 1.3539681240868401e-05, + "loss": 0.0325, + "step": 26117 + }, + { + "epoch": 8.07, + "learning_rate": 1.3539213497127606e-05, + "loss": 0.0273, + "step": 26118 + }, + { + "epoch": 8.07, + "learning_rate": 1.3538745744534594e-05, + "loss": 0.0262, + "step": 26119 + }, + { + "epoch": 8.07, + "learning_rate": 1.353827798309053e-05, + "loss": 0.0289, + "step": 26120 + }, + { + "epoch": 8.07, + "learning_rate": 1.3537810212796591e-05, + "loss": 0.0289, + "step": 26121 + }, + { + "epoch": 8.07, + "learning_rate": 1.3537342433653942e-05, + "loss": 0.03, + "step": 26122 + }, + { + "epoch": 8.07, + "learning_rate": 1.3536874645663754e-05, + "loss": 0.0331, + "step": 26123 + }, + { + "epoch": 8.07, + "learning_rate": 1.3536406848827198e-05, + "loss": 0.0295, + "step": 26124 + }, + { + "epoch": 8.07, + "learning_rate": 1.3535939043145445e-05, + "loss": 0.0291, + "step": 26125 + }, + { + "epoch": 8.07, + "learning_rate": 1.353547122861966e-05, + "loss": 0.0295, + "step": 26126 + }, + { + "epoch": 8.07, + "learning_rate": 1.3535003405251018e-05, + "loss": 0.032, + "step": 26127 + }, + { + "epoch": 8.07, + "learning_rate": 1.353453557304069e-05, + "loss": 0.0344, + "step": 26128 + }, + { + "epoch": 8.07, + "learning_rate": 1.353406773198984e-05, + "loss": 0.0323, + "step": 26129 + }, + { + "epoch": 8.07, + "learning_rate": 1.3533599882099646e-05, + "loss": 0.0321, + "step": 26130 + }, + { + "epoch": 8.07, + "learning_rate": 1.3533132023371272e-05, + "loss": 0.0317, + "step": 26131 + }, + { + "epoch": 8.07, + "learning_rate": 1.3532664155805888e-05, + "loss": 0.0307, + "step": 26132 + }, + { + "epoch": 8.07, + "learning_rate": 1.3532196279404673e-05, + "loss": 0.0276, + "step": 26133 + }, + { + "epoch": 8.07, + "learning_rate": 1.3531728394168784e-05, + "loss": 0.0271, + "step": 26134 + }, + { + "epoch": 8.07, + "learning_rate": 1.3531260500099403e-05, + "loss": 0.0309, + "step": 26135 + }, + { + "epoch": 8.07, + "learning_rate": 1.3530792597197695e-05, + "loss": 0.0262, + "step": 26136 + }, + { + "epoch": 8.07, + "learning_rate": 1.3530324685464827e-05, + "loss": 0.0268, + "step": 26137 + }, + { + "epoch": 8.07, + "learning_rate": 1.3529856764901977e-05, + "loss": 0.0283, + "step": 26138 + }, + { + "epoch": 8.07, + "learning_rate": 1.3529388835510311e-05, + "loss": 0.0315, + "step": 26139 + }, + { + "epoch": 8.07, + "learning_rate": 1.3528920897290998e-05, + "loss": 0.0314, + "step": 26140 + }, + { + "epoch": 8.07, + "learning_rate": 1.3528452950245213e-05, + "loss": 0.031, + "step": 26141 + }, + { + "epoch": 8.07, + "learning_rate": 1.352798499437412e-05, + "loss": 0.0334, + "step": 26142 + }, + { + "epoch": 8.07, + "learning_rate": 1.3527517029678893e-05, + "loss": 0.0318, + "step": 26143 + }, + { + "epoch": 8.07, + "learning_rate": 1.3527049056160705e-05, + "loss": 0.0269, + "step": 26144 + }, + { + "epoch": 8.07, + "learning_rate": 1.3526581073820724e-05, + "loss": 0.0319, + "step": 26145 + }, + { + "epoch": 8.07, + "learning_rate": 1.3526113082660119e-05, + "loss": 0.0319, + "step": 26146 + }, + { + "epoch": 8.07, + "learning_rate": 1.3525645082680063e-05, + "loss": 0.0308, + "step": 26147 + }, + { + "epoch": 8.08, + "learning_rate": 1.3525177073881726e-05, + "loss": 0.0285, + "step": 26148 + }, + { + "epoch": 8.08, + "learning_rate": 1.3524709056266277e-05, + "loss": 0.0306, + "step": 26149 + }, + { + "epoch": 8.08, + "learning_rate": 1.3524241029834888e-05, + "loss": 0.0283, + "step": 26150 + }, + { + "epoch": 8.08, + "learning_rate": 1.352377299458873e-05, + "loss": 0.0274, + "step": 26151 + }, + { + "epoch": 8.08, + "learning_rate": 1.3523304950528973e-05, + "loss": 0.0294, + "step": 26152 + }, + { + "epoch": 8.08, + "learning_rate": 1.3522836897656788e-05, + "loss": 0.0286, + "step": 26153 + }, + { + "epoch": 8.08, + "learning_rate": 1.3522368835973345e-05, + "loss": 0.0286, + "step": 26154 + }, + { + "epoch": 8.08, + "learning_rate": 1.3521900765479814e-05, + "loss": 0.031, + "step": 26155 + }, + { + "epoch": 8.08, + "learning_rate": 1.3521432686177369e-05, + "loss": 0.0324, + "step": 26156 + }, + { + "epoch": 8.08, + "learning_rate": 1.3520964598067177e-05, + "loss": 0.0307, + "step": 26157 + }, + { + "epoch": 8.08, + "learning_rate": 1.352049650115041e-05, + "loss": 0.0299, + "step": 26158 + }, + { + "epoch": 8.08, + "learning_rate": 1.3520028395428242e-05, + "loss": 0.0285, + "step": 26159 + }, + { + "epoch": 8.08, + "learning_rate": 1.3519560280901839e-05, + "loss": 0.0308, + "step": 26160 + }, + { + "epoch": 8.08, + "learning_rate": 1.3519092157572376e-05, + "loss": 0.0299, + "step": 26161 + }, + { + "epoch": 8.08, + "learning_rate": 1.3518624025441016e-05, + "loss": 0.03, + "step": 26162 + }, + { + "epoch": 8.08, + "learning_rate": 1.3518155884508938e-05, + "loss": 0.0293, + "step": 26163 + }, + { + "epoch": 8.08, + "learning_rate": 1.3517687734777314e-05, + "loss": 0.0333, + "step": 26164 + }, + { + "epoch": 8.08, + "learning_rate": 1.3517219576247307e-05, + "loss": 0.0283, + "step": 26165 + }, + { + "epoch": 8.08, + "learning_rate": 1.3516751408920095e-05, + "loss": 0.0274, + "step": 26166 + }, + { + "epoch": 8.08, + "learning_rate": 1.3516283232796848e-05, + "loss": 0.0327, + "step": 26167 + }, + { + "epoch": 8.08, + "learning_rate": 1.3515815047878728e-05, + "loss": 0.0358, + "step": 26168 + }, + { + "epoch": 8.08, + "learning_rate": 1.351534685416692e-05, + "loss": 0.0295, + "step": 26169 + }, + { + "epoch": 8.08, + "learning_rate": 1.3514878651662589e-05, + "loss": 0.03, + "step": 26170 + }, + { + "epoch": 8.08, + "learning_rate": 1.3514410440366901e-05, + "loss": 0.0299, + "step": 26171 + }, + { + "epoch": 8.08, + "learning_rate": 1.3513942220281033e-05, + "loss": 0.0327, + "step": 26172 + }, + { + "epoch": 8.08, + "learning_rate": 1.3513473991406157e-05, + "loss": 0.0299, + "step": 26173 + }, + { + "epoch": 8.08, + "learning_rate": 1.3513005753743438e-05, + "loss": 0.0326, + "step": 26174 + }, + { + "epoch": 8.08, + "learning_rate": 1.3512537507294052e-05, + "loss": 0.0309, + "step": 26175 + }, + { + "epoch": 8.08, + "learning_rate": 1.351206925205917e-05, + "loss": 0.0318, + "step": 26176 + }, + { + "epoch": 8.08, + "learning_rate": 1.3511600988039963e-05, + "loss": 0.0292, + "step": 26177 + }, + { + "epoch": 8.08, + "learning_rate": 1.35111327152376e-05, + "loss": 0.0265, + "step": 26178 + }, + { + "epoch": 8.08, + "learning_rate": 1.3510664433653253e-05, + "loss": 0.0263, + "step": 26179 + }, + { + "epoch": 8.08, + "learning_rate": 1.3510196143288097e-05, + "loss": 0.0322, + "step": 26180 + }, + { + "epoch": 8.09, + "learning_rate": 1.3509727844143297e-05, + "loss": 0.028, + "step": 26181 + }, + { + "epoch": 8.09, + "learning_rate": 1.3509259536220029e-05, + "loss": 0.0289, + "step": 26182 + }, + { + "epoch": 8.09, + "learning_rate": 1.3508791219519461e-05, + "loss": 0.0319, + "step": 26183 + }, + { + "epoch": 8.09, + "learning_rate": 1.3508322894042772e-05, + "loss": 0.0314, + "step": 26184 + }, + { + "epoch": 8.09, + "learning_rate": 1.3507854559791121e-05, + "loss": 0.0291, + "step": 26185 + }, + { + "epoch": 8.09, + "learning_rate": 1.3507386216765688e-05, + "loss": 0.0324, + "step": 26186 + }, + { + "epoch": 8.09, + "learning_rate": 1.3506917864967644e-05, + "loss": 0.0312, + "step": 26187 + }, + { + "epoch": 8.09, + "learning_rate": 1.3506449504398156e-05, + "loss": 0.0297, + "step": 26188 + }, + { + "epoch": 8.09, + "learning_rate": 1.3505981135058401e-05, + "loss": 0.0342, + "step": 26189 + }, + { + "epoch": 8.09, + "learning_rate": 1.3505512756949546e-05, + "loss": 0.0295, + "step": 26190 + }, + { + "epoch": 8.09, + "learning_rate": 1.3505044370072761e-05, + "loss": 0.0305, + "step": 26191 + }, + { + "epoch": 8.09, + "learning_rate": 1.3504575974429228e-05, + "loss": 0.0317, + "step": 26192 + }, + { + "epoch": 8.09, + "learning_rate": 1.3504107570020108e-05, + "loss": 0.0314, + "step": 26193 + }, + { + "epoch": 8.09, + "learning_rate": 1.3503639156846575e-05, + "loss": 0.029, + "step": 26194 + }, + { + "epoch": 8.09, + "learning_rate": 1.3503170734909803e-05, + "loss": 0.0318, + "step": 26195 + }, + { + "epoch": 8.09, + "learning_rate": 1.3502702304210957e-05, + "loss": 0.0317, + "step": 26196 + }, + { + "epoch": 8.09, + "learning_rate": 1.3502233864751223e-05, + "loss": 0.033, + "step": 26197 + }, + { + "epoch": 8.09, + "learning_rate": 1.3501765416531756e-05, + "loss": 0.027, + "step": 26198 + }, + { + "epoch": 8.09, + "learning_rate": 1.3501296959553739e-05, + "loss": 0.0294, + "step": 26199 + }, + { + "epoch": 8.09, + "learning_rate": 1.3500828493818336e-05, + "loss": 0.0282, + "step": 26200 + }, + { + "epoch": 8.09, + "learning_rate": 1.3500360019326723e-05, + "loss": 0.0334, + "step": 26201 + }, + { + "epoch": 8.09, + "learning_rate": 1.3499891536080074e-05, + "loss": 0.0324, + "step": 26202 + }, + { + "epoch": 8.09, + "learning_rate": 1.3499423044079557e-05, + "loss": 0.0294, + "step": 26203 + }, + { + "epoch": 8.09, + "learning_rate": 1.3498954543326343e-05, + "loss": 0.0345, + "step": 26204 + }, + { + "epoch": 8.09, + "learning_rate": 1.3498486033821605e-05, + "loss": 0.0309, + "step": 26205 + }, + { + "epoch": 8.09, + "learning_rate": 1.3498017515566519e-05, + "loss": 0.0328, + "step": 26206 + }, + { + "epoch": 8.09, + "learning_rate": 1.349754898856225e-05, + "loss": 0.0274, + "step": 26207 + }, + { + "epoch": 8.09, + "learning_rate": 1.3497080452809975e-05, + "loss": 0.0274, + "step": 26208 + }, + { + "epoch": 8.09, + "learning_rate": 1.3496611908310862e-05, + "loss": 0.0303, + "step": 26209 + }, + { + "epoch": 8.09, + "learning_rate": 1.3496143355066086e-05, + "loss": 0.0313, + "step": 26210 + }, + { + "epoch": 8.09, + "learning_rate": 1.3495674793076819e-05, + "loss": 0.0263, + "step": 26211 + }, + { + "epoch": 8.09, + "learning_rate": 1.3495206222344228e-05, + "loss": 0.0286, + "step": 26212 + }, + { + "epoch": 8.1, + "learning_rate": 1.3494737642869493e-05, + "loss": 0.0308, + "step": 26213 + }, + { + "epoch": 8.1, + "learning_rate": 1.3494269054653778e-05, + "loss": 0.0302, + "step": 26214 + }, + { + "epoch": 8.1, + "learning_rate": 1.3493800457698266e-05, + "loss": 0.0294, + "step": 26215 + }, + { + "epoch": 8.1, + "learning_rate": 1.3493331852004112e-05, + "loss": 0.0271, + "step": 26216 + }, + { + "epoch": 8.1, + "learning_rate": 1.3492863237572504e-05, + "loss": 0.0299, + "step": 26217 + }, + { + "epoch": 8.1, + "learning_rate": 1.349239461440461e-05, + "loss": 0.0278, + "step": 26218 + }, + { + "epoch": 8.1, + "learning_rate": 1.3491925982501592e-05, + "loss": 0.0293, + "step": 26219 + }, + { + "epoch": 8.1, + "learning_rate": 1.3491457341864637e-05, + "loss": 0.0322, + "step": 26220 + }, + { + "epoch": 8.1, + "learning_rate": 1.3490988692494909e-05, + "loss": 0.0323, + "step": 26221 + }, + { + "epoch": 8.1, + "learning_rate": 1.349052003439358e-05, + "loss": 0.0335, + "step": 26222 + }, + { + "epoch": 8.1, + "learning_rate": 1.3490051367561825e-05, + "loss": 0.0324, + "step": 26223 + }, + { + "epoch": 8.1, + "learning_rate": 1.3489582692000815e-05, + "loss": 0.0302, + "step": 26224 + }, + { + "epoch": 8.1, + "learning_rate": 1.3489114007711721e-05, + "loss": 0.0302, + "step": 26225 + }, + { + "epoch": 8.1, + "learning_rate": 1.3488645314695718e-05, + "loss": 0.0281, + "step": 26226 + }, + { + "epoch": 8.1, + "learning_rate": 1.3488176612953976e-05, + "loss": 0.03, + "step": 26227 + }, + { + "epoch": 8.1, + "learning_rate": 1.3487707902487668e-05, + "loss": 0.0311, + "step": 26228 + }, + { + "epoch": 8.1, + "learning_rate": 1.3487239183297967e-05, + "loss": 0.0312, + "step": 26229 + }, + { + "epoch": 8.1, + "learning_rate": 1.3486770455386045e-05, + "loss": 0.029, + "step": 26230 + }, + { + "epoch": 8.1, + "learning_rate": 1.3486301718753071e-05, + "loss": 0.0311, + "step": 26231 + }, + { + "epoch": 8.1, + "learning_rate": 1.3485832973400225e-05, + "loss": 0.0303, + "step": 26232 + }, + { + "epoch": 8.1, + "learning_rate": 1.3485364219328671e-05, + "loss": 0.029, + "step": 26233 + }, + { + "epoch": 8.1, + "learning_rate": 1.3484895456539588e-05, + "loss": 0.0323, + "step": 26234 + }, + { + "epoch": 8.1, + "learning_rate": 1.3484426685034146e-05, + "loss": 0.0284, + "step": 26235 + }, + { + "epoch": 8.1, + "learning_rate": 1.3483957904813516e-05, + "loss": 0.0334, + "step": 26236 + }, + { + "epoch": 8.1, + "learning_rate": 1.3483489115878871e-05, + "loss": 0.0337, + "step": 26237 + }, + { + "epoch": 8.1, + "learning_rate": 1.348302031823139e-05, + "loss": 0.0313, + "step": 26238 + }, + { + "epoch": 8.1, + "learning_rate": 1.3482551511872233e-05, + "loss": 0.0291, + "step": 26239 + }, + { + "epoch": 8.1, + "learning_rate": 1.3482082696802582e-05, + "loss": 0.0284, + "step": 26240 + }, + { + "epoch": 8.1, + "learning_rate": 1.3481613873023612e-05, + "loss": 0.0262, + "step": 26241 + }, + { + "epoch": 8.1, + "learning_rate": 1.3481145040536481e-05, + "loss": 0.0301, + "step": 26242 + }, + { + "epoch": 8.1, + "learning_rate": 1.348067619934238e-05, + "loss": 0.031, + "step": 26243 + }, + { + "epoch": 8.1, + "learning_rate": 1.3480207349442468e-05, + "loss": 0.03, + "step": 26244 + }, + { + "epoch": 8.11, + "learning_rate": 1.3479738490837923e-05, + "loss": 0.0332, + "step": 26245 + }, + { + "epoch": 8.11, + "learning_rate": 1.3479269623529921e-05, + "loss": 0.032, + "step": 26246 + }, + { + "epoch": 8.11, + "learning_rate": 1.3478800747519624e-05, + "loss": 0.0334, + "step": 26247 + }, + { + "epoch": 8.11, + "learning_rate": 1.347833186280822e-05, + "loss": 0.0276, + "step": 26248 + }, + { + "epoch": 8.11, + "learning_rate": 1.3477862969396868e-05, + "loss": 0.0291, + "step": 26249 + }, + { + "epoch": 8.11, + "learning_rate": 1.3477394067286747e-05, + "loss": 0.0308, + "step": 26250 + }, + { + "epoch": 8.11, + "learning_rate": 1.3476925156479033e-05, + "loss": 0.0251, + "step": 26251 + }, + { + "epoch": 8.11, + "learning_rate": 1.3476456236974892e-05, + "loss": 0.0311, + "step": 26252 + }, + { + "epoch": 8.11, + "learning_rate": 1.3475987308775502e-05, + "loss": 0.0329, + "step": 26253 + }, + { + "epoch": 8.11, + "learning_rate": 1.347551837188203e-05, + "loss": 0.0316, + "step": 26254 + }, + { + "epoch": 8.11, + "learning_rate": 1.3475049426295656e-05, + "loss": 0.0295, + "step": 26255 + }, + { + "epoch": 8.11, + "learning_rate": 1.3474580472017548e-05, + "loss": 0.0334, + "step": 26256 + }, + { + "epoch": 8.11, + "learning_rate": 1.3474111509048882e-05, + "loss": 0.0265, + "step": 26257 + }, + { + "epoch": 8.11, + "learning_rate": 1.3473642537390828e-05, + "loss": 0.0307, + "step": 26258 + }, + { + "epoch": 8.11, + "learning_rate": 1.3473173557044561e-05, + "loss": 0.0322, + "step": 26259 + }, + { + "epoch": 8.11, + "learning_rate": 1.3472704568011253e-05, + "loss": 0.0329, + "step": 26260 + }, + { + "epoch": 8.11, + "learning_rate": 1.3472235570292078e-05, + "loss": 0.0336, + "step": 26261 + }, + { + "epoch": 8.11, + "learning_rate": 1.347176656388821e-05, + "loss": 0.0326, + "step": 26262 + }, + { + "epoch": 8.11, + "learning_rate": 1.3471297548800816e-05, + "loss": 0.0308, + "step": 26263 + }, + { + "epoch": 8.11, + "learning_rate": 1.3470828525031077e-05, + "loss": 0.0333, + "step": 26264 + }, + { + "epoch": 8.11, + "learning_rate": 1.3470359492580162e-05, + "loss": 0.0333, + "step": 26265 + }, + { + "epoch": 8.11, + "learning_rate": 1.3469890451449246e-05, + "loss": 0.0319, + "step": 26266 + }, + { + "epoch": 8.11, + "learning_rate": 1.3469421401639499e-05, + "loss": 0.0284, + "step": 26267 + }, + { + "epoch": 8.11, + "learning_rate": 1.34689523431521e-05, + "loss": 0.0261, + "step": 26268 + }, + { + "epoch": 8.11, + "learning_rate": 1.3468483275988218e-05, + "loss": 0.0313, + "step": 26269 + }, + { + "epoch": 8.11, + "learning_rate": 1.3468014200149022e-05, + "loss": 0.032, + "step": 26270 + }, + { + "epoch": 8.11, + "learning_rate": 1.3467545115635694e-05, + "loss": 0.0286, + "step": 26271 + }, + { + "epoch": 8.11, + "learning_rate": 1.3467076022449403e-05, + "loss": 0.0297, + "step": 26272 + }, + { + "epoch": 8.11, + "learning_rate": 1.346660692059132e-05, + "loss": 0.0331, + "step": 26273 + }, + { + "epoch": 8.11, + "learning_rate": 1.3466137810062625e-05, + "loss": 0.0306, + "step": 26274 + }, + { + "epoch": 8.11, + "learning_rate": 1.3465668690864485e-05, + "loss": 0.031, + "step": 26275 + }, + { + "epoch": 8.11, + "learning_rate": 1.3465199562998072e-05, + "loss": 0.0284, + "step": 26276 + }, + { + "epoch": 8.11, + "learning_rate": 1.3464730426464569e-05, + "loss": 0.0285, + "step": 26277 + }, + { + "epoch": 8.12, + "learning_rate": 1.3464261281265138e-05, + "loss": 0.0332, + "step": 26278 + }, + { + "epoch": 8.12, + "learning_rate": 1.3463792127400963e-05, + "loss": 0.039, + "step": 26279 + }, + { + "epoch": 8.12, + "learning_rate": 1.3463322964873208e-05, + "loss": 0.0299, + "step": 26280 + }, + { + "epoch": 8.12, + "learning_rate": 1.346285379368305e-05, + "loss": 0.0318, + "step": 26281 + }, + { + "epoch": 8.12, + "learning_rate": 1.3462384613831668e-05, + "loss": 0.0307, + "step": 26282 + }, + { + "epoch": 8.12, + "learning_rate": 1.3461915425320227e-05, + "loss": 0.0284, + "step": 26283 + }, + { + "epoch": 8.12, + "learning_rate": 1.3461446228149904e-05, + "loss": 0.03, + "step": 26284 + }, + { + "epoch": 8.12, + "learning_rate": 1.3460977022321872e-05, + "loss": 0.0344, + "step": 26285 + }, + { + "epoch": 8.12, + "learning_rate": 1.346050780783731e-05, + "loss": 0.0292, + "step": 26286 + }, + { + "epoch": 8.12, + "learning_rate": 1.3460038584697381e-05, + "loss": 0.0292, + "step": 26287 + }, + { + "epoch": 8.12, + "learning_rate": 1.3459569352903268e-05, + "loss": 0.0315, + "step": 26288 + }, + { + "epoch": 8.12, + "learning_rate": 1.3459100112456137e-05, + "loss": 0.0317, + "step": 26289 + }, + { + "epoch": 8.12, + "learning_rate": 1.345863086335717e-05, + "loss": 0.0281, + "step": 26290 + }, + { + "epoch": 8.12, + "learning_rate": 1.3458161605607533e-05, + "loss": 0.032, + "step": 26291 + }, + { + "epoch": 8.12, + "learning_rate": 1.3457692339208408e-05, + "loss": 0.0324, + "step": 26292 + }, + { + "epoch": 8.12, + "learning_rate": 1.345722306416096e-05, + "loss": 0.0307, + "step": 26293 + }, + { + "epoch": 8.12, + "learning_rate": 1.3456753780466367e-05, + "loss": 0.0289, + "step": 26294 + }, + { + "epoch": 8.12, + "learning_rate": 1.3456284488125802e-05, + "loss": 0.0325, + "step": 26295 + }, + { + "epoch": 8.12, + "learning_rate": 1.3455815187140439e-05, + "loss": 0.0313, + "step": 26296 + }, + { + "epoch": 8.12, + "learning_rate": 1.3455345877511454e-05, + "loss": 0.0304, + "step": 26297 + }, + { + "epoch": 8.12, + "learning_rate": 1.3454876559240017e-05, + "loss": 0.0297, + "step": 26298 + }, + { + "epoch": 8.12, + "learning_rate": 1.3454407232327304e-05, + "loss": 0.0338, + "step": 26299 + }, + { + "epoch": 8.12, + "learning_rate": 1.3453937896774489e-05, + "loss": 0.0312, + "step": 26300 + }, + { + "epoch": 8.12, + "learning_rate": 1.3453468552582745e-05, + "loss": 0.0306, + "step": 26301 + }, + { + "epoch": 8.12, + "learning_rate": 1.3452999199753244e-05, + "loss": 0.0305, + "step": 26302 + }, + { + "epoch": 8.12, + "learning_rate": 1.3452529838287167e-05, + "loss": 0.0263, + "step": 26303 + }, + { + "epoch": 8.12, + "learning_rate": 1.345206046818568e-05, + "loss": 0.0268, + "step": 26304 + }, + { + "epoch": 8.12, + "learning_rate": 1.3451591089449963e-05, + "loss": 0.0276, + "step": 26305 + }, + { + "epoch": 8.12, + "learning_rate": 1.3451121702081183e-05, + "loss": 0.0339, + "step": 26306 + }, + { + "epoch": 8.12, + "learning_rate": 1.3450652306080517e-05, + "loss": 0.0312, + "step": 26307 + }, + { + "epoch": 8.12, + "learning_rate": 1.3450182901449147e-05, + "loss": 0.0306, + "step": 26308 + }, + { + "epoch": 8.12, + "learning_rate": 1.3449713488188237e-05, + "loss": 0.0305, + "step": 26309 + }, + { + "epoch": 8.13, + "learning_rate": 1.3449244066298963e-05, + "loss": 0.0309, + "step": 26310 + }, + { + "epoch": 8.13, + "learning_rate": 1.3448774635782503e-05, + "loss": 0.0269, + "step": 26311 + }, + { + "epoch": 8.13, + "learning_rate": 1.3448305196640023e-05, + "loss": 0.0314, + "step": 26312 + }, + { + "epoch": 8.13, + "learning_rate": 1.3447835748872709e-05, + "loss": 0.0308, + "step": 26313 + }, + { + "epoch": 8.13, + "learning_rate": 1.3447366292481727e-05, + "loss": 0.0314, + "step": 26314 + }, + { + "epoch": 8.13, + "learning_rate": 1.3446896827468252e-05, + "loss": 0.031, + "step": 26315 + }, + { + "epoch": 8.13, + "learning_rate": 1.3446427353833463e-05, + "loss": 0.0274, + "step": 26316 + }, + { + "epoch": 8.13, + "learning_rate": 1.3445957871578526e-05, + "loss": 0.0317, + "step": 26317 + }, + { + "epoch": 8.13, + "learning_rate": 1.344548838070462e-05, + "loss": 0.0315, + "step": 26318 + }, + { + "epoch": 8.13, + "learning_rate": 1.3445018881212924e-05, + "loss": 0.0303, + "step": 26319 + }, + { + "epoch": 8.13, + "learning_rate": 1.3444549373104604e-05, + "loss": 0.0318, + "step": 26320 + }, + { + "epoch": 8.13, + "learning_rate": 1.3444079856380837e-05, + "loss": 0.0292, + "step": 26321 + }, + { + "epoch": 8.13, + "learning_rate": 1.3443610331042799e-05, + "loss": 0.0275, + "step": 26322 + }, + { + "epoch": 8.13, + "learning_rate": 1.3443140797091666e-05, + "loss": 0.031, + "step": 26323 + }, + { + "epoch": 8.13, + "learning_rate": 1.3442671254528605e-05, + "loss": 0.0322, + "step": 26324 + }, + { + "epoch": 8.13, + "learning_rate": 1.3442201703354798e-05, + "loss": 0.0293, + "step": 26325 + }, + { + "epoch": 8.13, + "learning_rate": 1.3441732143571415e-05, + "loss": 0.0291, + "step": 26326 + }, + { + "epoch": 8.13, + "learning_rate": 1.3441262575179634e-05, + "loss": 0.0295, + "step": 26327 + }, + { + "epoch": 8.13, + "learning_rate": 1.344079299818063e-05, + "loss": 0.0323, + "step": 26328 + }, + { + "epoch": 8.13, + "learning_rate": 1.3440323412575571e-05, + "loss": 0.0324, + "step": 26329 + }, + { + "epoch": 8.13, + "learning_rate": 1.3439853818365635e-05, + "loss": 0.028, + "step": 26330 + }, + { + "epoch": 8.13, + "learning_rate": 1.3439384215552003e-05, + "loss": 0.0294, + "step": 26331 + }, + { + "epoch": 8.13, + "learning_rate": 1.3438914604135837e-05, + "loss": 0.029, + "step": 26332 + }, + { + "epoch": 8.13, + "learning_rate": 1.3438444984118323e-05, + "loss": 0.0308, + "step": 26333 + }, + { + "epoch": 8.13, + "learning_rate": 1.343797535550063e-05, + "loss": 0.0322, + "step": 26334 + }, + { + "epoch": 8.13, + "learning_rate": 1.3437505718283933e-05, + "loss": 0.0277, + "step": 26335 + }, + { + "epoch": 8.13, + "learning_rate": 1.3437036072469409e-05, + "loss": 0.0319, + "step": 26336 + }, + { + "epoch": 8.13, + "learning_rate": 1.3436566418058229e-05, + "loss": 0.0291, + "step": 26337 + }, + { + "epoch": 8.13, + "learning_rate": 1.3436096755051568e-05, + "loss": 0.0272, + "step": 26338 + }, + { + "epoch": 8.13, + "learning_rate": 1.3435627083450604e-05, + "loss": 0.0317, + "step": 26339 + }, + { + "epoch": 8.13, + "learning_rate": 1.3435157403256512e-05, + "loss": 0.03, + "step": 26340 + }, + { + "epoch": 8.13, + "learning_rate": 1.3434687714470463e-05, + "loss": 0.03, + "step": 26341 + }, + { + "epoch": 8.13, + "learning_rate": 1.3434218017093632e-05, + "loss": 0.031, + "step": 26342 + }, + { + "epoch": 8.14, + "learning_rate": 1.3433748311127197e-05, + "loss": 0.0279, + "step": 26343 + }, + { + "epoch": 8.14, + "learning_rate": 1.3433278596572332e-05, + "loss": 0.0287, + "step": 26344 + }, + { + "epoch": 8.14, + "learning_rate": 1.343280887343021e-05, + "loss": 0.0304, + "step": 26345 + }, + { + "epoch": 8.14, + "learning_rate": 1.3432339141702007e-05, + "loss": 0.0269, + "step": 26346 + }, + { + "epoch": 8.14, + "learning_rate": 1.3431869401388898e-05, + "loss": 0.0332, + "step": 26347 + }, + { + "epoch": 8.14, + "learning_rate": 1.3431399652492057e-05, + "loss": 0.0294, + "step": 26348 + }, + { + "epoch": 8.14, + "learning_rate": 1.343092989501266e-05, + "loss": 0.0319, + "step": 26349 + }, + { + "epoch": 8.14, + "learning_rate": 1.3430460128951883e-05, + "loss": 0.0292, + "step": 26350 + }, + { + "epoch": 8.14, + "learning_rate": 1.3429990354310898e-05, + "loss": 0.0309, + "step": 26351 + }, + { + "epoch": 8.14, + "learning_rate": 1.342952057109088e-05, + "loss": 0.0309, + "step": 26352 + }, + { + "epoch": 8.14, + "learning_rate": 1.3429050779293008e-05, + "loss": 0.03, + "step": 26353 + }, + { + "epoch": 8.14, + "learning_rate": 1.3428580978918455e-05, + "loss": 0.0295, + "step": 26354 + }, + { + "epoch": 8.14, + "learning_rate": 1.3428111169968394e-05, + "loss": 0.0322, + "step": 26355 + }, + { + "epoch": 8.14, + "learning_rate": 1.3427641352444001e-05, + "loss": 0.03, + "step": 26356 + }, + { + "epoch": 8.14, + "learning_rate": 1.3427171526346456e-05, + "loss": 0.0317, + "step": 26357 + }, + { + "epoch": 8.14, + "learning_rate": 1.3426701691676924e-05, + "loss": 0.0326, + "step": 26358 + }, + { + "epoch": 8.14, + "learning_rate": 1.3426231848436593e-05, + "loss": 0.0324, + "step": 26359 + }, + { + "epoch": 8.14, + "learning_rate": 1.3425761996626626e-05, + "loss": 0.0323, + "step": 26360 + }, + { + "epoch": 8.14, + "learning_rate": 1.3425292136248202e-05, + "loss": 0.0334, + "step": 26361 + }, + { + "epoch": 8.14, + "learning_rate": 1.3424822267302504e-05, + "loss": 0.033, + "step": 26362 + }, + { + "epoch": 8.14, + "learning_rate": 1.3424352389790697e-05, + "loss": 0.0325, + "step": 26363 + }, + { + "epoch": 8.14, + "learning_rate": 1.3423882503713959e-05, + "loss": 0.0304, + "step": 26364 + }, + { + "epoch": 8.14, + "learning_rate": 1.3423412609073468e-05, + "loss": 0.03, + "step": 26365 + }, + { + "epoch": 8.14, + "learning_rate": 1.3422942705870397e-05, + "loss": 0.036, + "step": 26366 + }, + { + "epoch": 8.14, + "learning_rate": 1.3422472794105923e-05, + "loss": 0.0343, + "step": 26367 + }, + { + "epoch": 8.14, + "learning_rate": 1.342200287378122e-05, + "loss": 0.0298, + "step": 26368 + }, + { + "epoch": 8.14, + "learning_rate": 1.3421532944897465e-05, + "loss": 0.0314, + "step": 26369 + }, + { + "epoch": 8.14, + "learning_rate": 1.342106300745583e-05, + "loss": 0.0341, + "step": 26370 + }, + { + "epoch": 8.14, + "learning_rate": 1.3420593061457493e-05, + "loss": 0.0292, + "step": 26371 + }, + { + "epoch": 8.14, + "learning_rate": 1.3420123106903629e-05, + "loss": 0.0291, + "step": 26372 + }, + { + "epoch": 8.14, + "learning_rate": 1.3419653143795413e-05, + "loss": 0.0287, + "step": 26373 + }, + { + "epoch": 8.14, + "learning_rate": 1.341918317213402e-05, + "loss": 0.0318, + "step": 26374 + }, + { + "epoch": 8.15, + "learning_rate": 1.3418713191920627e-05, + "loss": 0.0275, + "step": 26375 + }, + { + "epoch": 8.15, + "learning_rate": 1.341824320315641e-05, + "loss": 0.0274, + "step": 26376 + }, + { + "epoch": 8.15, + "learning_rate": 1.3417773205842542e-05, + "loss": 0.0311, + "step": 26377 + }, + { + "epoch": 8.15, + "learning_rate": 1.3417303199980199e-05, + "loss": 0.0346, + "step": 26378 + }, + { + "epoch": 8.15, + "learning_rate": 1.3416833185570558e-05, + "loss": 0.0335, + "step": 26379 + }, + { + "epoch": 8.15, + "learning_rate": 1.3416363162614796e-05, + "loss": 0.0291, + "step": 26380 + }, + { + "epoch": 8.15, + "learning_rate": 1.3415893131114084e-05, + "loss": 0.0298, + "step": 26381 + }, + { + "epoch": 8.15, + "learning_rate": 1.3415423091069604e-05, + "loss": 0.0301, + "step": 26382 + }, + { + "epoch": 8.15, + "learning_rate": 1.3414953042482522e-05, + "loss": 0.0317, + "step": 26383 + }, + { + "epoch": 8.15, + "learning_rate": 1.3414482985354025e-05, + "loss": 0.0303, + "step": 26384 + }, + { + "epoch": 8.15, + "learning_rate": 1.3414012919685282e-05, + "loss": 0.0309, + "step": 26385 + }, + { + "epoch": 8.15, + "learning_rate": 1.3413542845477467e-05, + "loss": 0.0295, + "step": 26386 + }, + { + "epoch": 8.15, + "learning_rate": 1.3413072762731763e-05, + "loss": 0.0353, + "step": 26387 + }, + { + "epoch": 8.15, + "learning_rate": 1.341260267144934e-05, + "loss": 0.0322, + "step": 26388 + }, + { + "epoch": 8.15, + "learning_rate": 1.3412132571631373e-05, + "loss": 0.0284, + "step": 26389 + }, + { + "epoch": 8.15, + "learning_rate": 1.3411662463279043e-05, + "loss": 0.0302, + "step": 26390 + }, + { + "epoch": 8.15, + "learning_rate": 1.341119234639352e-05, + "loss": 0.0304, + "step": 26391 + }, + { + "epoch": 8.15, + "learning_rate": 1.3410722220975987e-05, + "loss": 0.0332, + "step": 26392 + }, + { + "epoch": 8.15, + "learning_rate": 1.3410252087027614e-05, + "loss": 0.0281, + "step": 26393 + }, + { + "epoch": 8.15, + "learning_rate": 1.3409781944549573e-05, + "loss": 0.0311, + "step": 26394 + }, + { + "epoch": 8.15, + "learning_rate": 1.3409311793543054e-05, + "loss": 0.03, + "step": 26395 + }, + { + "epoch": 8.15, + "learning_rate": 1.340884163400922e-05, + "loss": 0.0334, + "step": 26396 + }, + { + "epoch": 8.15, + "learning_rate": 1.3408371465949252e-05, + "loss": 0.0326, + "step": 26397 + }, + { + "epoch": 8.15, + "learning_rate": 1.3407901289364324e-05, + "loss": 0.03, + "step": 26398 + }, + { + "epoch": 8.15, + "learning_rate": 1.3407431104255615e-05, + "loss": 0.0322, + "step": 26399 + }, + { + "epoch": 8.15, + "learning_rate": 1.3406960910624301e-05, + "loss": 0.0311, + "step": 26400 + }, + { + "epoch": 8.15, + "learning_rate": 1.3406490708471553e-05, + "loss": 0.028, + "step": 26401 + }, + { + "epoch": 8.15, + "learning_rate": 1.340602049779855e-05, + "loss": 0.0272, + "step": 26402 + }, + { + "epoch": 8.15, + "learning_rate": 1.3405550278606472e-05, + "loss": 0.0329, + "step": 26403 + }, + { + "epoch": 8.15, + "learning_rate": 1.340508005089649e-05, + "loss": 0.0317, + "step": 26404 + }, + { + "epoch": 8.15, + "learning_rate": 1.3404609814669782e-05, + "loss": 0.0315, + "step": 26405 + }, + { + "epoch": 8.15, + "learning_rate": 1.3404139569927524e-05, + "loss": 0.0304, + "step": 26406 + }, + { + "epoch": 8.16, + "learning_rate": 1.3403669316670891e-05, + "loss": 0.0302, + "step": 26407 + }, + { + "epoch": 8.16, + "learning_rate": 1.340319905490106e-05, + "loss": 0.0291, + "step": 26408 + }, + { + "epoch": 8.16, + "learning_rate": 1.3402728784619207e-05, + "loss": 0.0337, + "step": 26409 + }, + { + "epoch": 8.16, + "learning_rate": 1.3402258505826511e-05, + "loss": 0.0343, + "step": 26410 + }, + { + "epoch": 8.16, + "learning_rate": 1.3401788218524146e-05, + "loss": 0.0296, + "step": 26411 + }, + { + "epoch": 8.16, + "learning_rate": 1.3401317922713286e-05, + "loss": 0.0299, + "step": 26412 + }, + { + "epoch": 8.16, + "learning_rate": 1.3400847618395111e-05, + "loss": 0.034, + "step": 26413 + }, + { + "epoch": 8.16, + "learning_rate": 1.3400377305570795e-05, + "loss": 0.0281, + "step": 26414 + }, + { + "epoch": 8.16, + "learning_rate": 1.3399906984241516e-05, + "loss": 0.0319, + "step": 26415 + }, + { + "epoch": 8.16, + "learning_rate": 1.339943665440845e-05, + "loss": 0.0272, + "step": 26416 + }, + { + "epoch": 8.16, + "learning_rate": 1.339896631607277e-05, + "loss": 0.0316, + "step": 26417 + }, + { + "epoch": 8.16, + "learning_rate": 1.3398495969235661e-05, + "loss": 0.0356, + "step": 26418 + }, + { + "epoch": 8.16, + "learning_rate": 1.3398025613898289e-05, + "loss": 0.0279, + "step": 26419 + }, + { + "epoch": 8.16, + "learning_rate": 1.3397555250061833e-05, + "loss": 0.0323, + "step": 26420 + }, + { + "epoch": 8.16, + "learning_rate": 1.3397084877727477e-05, + "loss": 0.0354, + "step": 26421 + }, + { + "epoch": 8.16, + "learning_rate": 1.3396614496896391e-05, + "loss": 0.0296, + "step": 26422 + }, + { + "epoch": 8.16, + "learning_rate": 1.3396144107569753e-05, + "loss": 0.0333, + "step": 26423 + }, + { + "epoch": 8.16, + "learning_rate": 1.3395673709748738e-05, + "loss": 0.0298, + "step": 26424 + }, + { + "epoch": 8.16, + "learning_rate": 1.339520330343452e-05, + "loss": 0.0316, + "step": 26425 + }, + { + "epoch": 8.16, + "learning_rate": 1.3394732888628286e-05, + "loss": 0.0258, + "step": 26426 + }, + { + "epoch": 8.16, + "learning_rate": 1.3394262465331203e-05, + "loss": 0.0328, + "step": 26427 + }, + { + "epoch": 8.16, + "learning_rate": 1.339379203354445e-05, + "loss": 0.0306, + "step": 26428 + }, + { + "epoch": 8.16, + "learning_rate": 1.3393321593269203e-05, + "loss": 0.0325, + "step": 26429 + }, + { + "epoch": 8.16, + "learning_rate": 1.3392851144506643e-05, + "loss": 0.0281, + "step": 26430 + }, + { + "epoch": 8.16, + "learning_rate": 1.339238068725794e-05, + "loss": 0.0323, + "step": 26431 + }, + { + "epoch": 8.16, + "learning_rate": 1.3391910221524276e-05, + "loss": 0.0301, + "step": 26432 + }, + { + "epoch": 8.16, + "learning_rate": 1.3391439747306826e-05, + "loss": 0.0297, + "step": 26433 + }, + { + "epoch": 8.16, + "learning_rate": 1.3390969264606765e-05, + "loss": 0.0297, + "step": 26434 + }, + { + "epoch": 8.16, + "learning_rate": 1.3390498773425274e-05, + "loss": 0.0349, + "step": 26435 + }, + { + "epoch": 8.16, + "learning_rate": 1.3390028273763527e-05, + "loss": 0.0329, + "step": 26436 + }, + { + "epoch": 8.16, + "learning_rate": 1.3389557765622698e-05, + "loss": 0.0291, + "step": 26437 + }, + { + "epoch": 8.16, + "learning_rate": 1.338908724900397e-05, + "loss": 0.0294, + "step": 26438 + }, + { + "epoch": 8.16, + "learning_rate": 1.3388616723908515e-05, + "loss": 0.0305, + "step": 26439 + }, + { + "epoch": 8.17, + "learning_rate": 1.3388146190337513e-05, + "loss": 0.0293, + "step": 26440 + }, + { + "epoch": 8.17, + "learning_rate": 1.338767564829214e-05, + "loss": 0.0322, + "step": 26441 + }, + { + "epoch": 8.17, + "learning_rate": 1.3387205097773569e-05, + "loss": 0.0284, + "step": 26442 + }, + { + "epoch": 8.17, + "learning_rate": 1.3386734538782982e-05, + "loss": 0.0333, + "step": 26443 + }, + { + "epoch": 8.17, + "learning_rate": 1.3386263971321554e-05, + "loss": 0.0345, + "step": 26444 + }, + { + "epoch": 8.17, + "learning_rate": 1.338579339539046e-05, + "loss": 0.0324, + "step": 26445 + }, + { + "epoch": 8.17, + "learning_rate": 1.3385322810990884e-05, + "loss": 0.0364, + "step": 26446 + }, + { + "epoch": 8.17, + "learning_rate": 1.3384852218123996e-05, + "loss": 0.0335, + "step": 26447 + }, + { + "epoch": 8.17, + "learning_rate": 1.3384381616790974e-05, + "loss": 0.0296, + "step": 26448 + }, + { + "epoch": 8.17, + "learning_rate": 1.3383911006992998e-05, + "loss": 0.0318, + "step": 26449 + }, + { + "epoch": 8.17, + "learning_rate": 1.3383440388731244e-05, + "loss": 0.0311, + "step": 26450 + }, + { + "epoch": 8.17, + "learning_rate": 1.3382969762006886e-05, + "loss": 0.0309, + "step": 26451 + }, + { + "epoch": 8.17, + "learning_rate": 1.3382499126821105e-05, + "loss": 0.0317, + "step": 26452 + }, + { + "epoch": 8.17, + "learning_rate": 1.3382028483175076e-05, + "loss": 0.0325, + "step": 26453 + }, + { + "epoch": 8.17, + "learning_rate": 1.3381557831069978e-05, + "loss": 0.0362, + "step": 26454 + }, + { + "epoch": 8.17, + "learning_rate": 1.3381087170506986e-05, + "loss": 0.0315, + "step": 26455 + }, + { + "epoch": 8.17, + "learning_rate": 1.338061650148728e-05, + "loss": 0.0267, + "step": 26456 + }, + { + "epoch": 8.17, + "learning_rate": 1.3380145824012032e-05, + "loss": 0.0306, + "step": 26457 + }, + { + "epoch": 8.17, + "learning_rate": 1.3379675138082427e-05, + "loss": 0.032, + "step": 26458 + }, + { + "epoch": 8.17, + "learning_rate": 1.3379204443699636e-05, + "loss": 0.0334, + "step": 26459 + }, + { + "epoch": 8.17, + "learning_rate": 1.3378733740864838e-05, + "loss": 0.029, + "step": 26460 + }, + { + "epoch": 8.17, + "learning_rate": 1.3378263029579213e-05, + "loss": 0.0293, + "step": 26461 + }, + { + "epoch": 8.17, + "learning_rate": 1.3377792309843933e-05, + "loss": 0.0293, + "step": 26462 + }, + { + "epoch": 8.17, + "learning_rate": 1.3377321581660178e-05, + "loss": 0.0296, + "step": 26463 + }, + { + "epoch": 8.17, + "learning_rate": 1.3376850845029129e-05, + "loss": 0.0309, + "step": 26464 + }, + { + "epoch": 8.17, + "learning_rate": 1.3376380099951958e-05, + "loss": 0.0285, + "step": 26465 + }, + { + "epoch": 8.17, + "learning_rate": 1.3375909346429845e-05, + "loss": 0.035, + "step": 26466 + }, + { + "epoch": 8.17, + "learning_rate": 1.3375438584463968e-05, + "loss": 0.0297, + "step": 26467 + }, + { + "epoch": 8.17, + "learning_rate": 1.3374967814055501e-05, + "loss": 0.0324, + "step": 26468 + }, + { + "epoch": 8.17, + "learning_rate": 1.3374497035205627e-05, + "loss": 0.0327, + "step": 26469 + }, + { + "epoch": 8.17, + "learning_rate": 1.337402624791552e-05, + "loss": 0.0293, + "step": 26470 + }, + { + "epoch": 8.17, + "learning_rate": 1.3373555452186356e-05, + "loss": 0.0324, + "step": 26471 + }, + { + "epoch": 8.18, + "learning_rate": 1.3373084648019316e-05, + "loss": 0.0297, + "step": 26472 + }, + { + "epoch": 8.18, + "learning_rate": 1.3372613835415574e-05, + "loss": 0.0307, + "step": 26473 + }, + { + "epoch": 8.18, + "learning_rate": 1.337214301437631e-05, + "loss": 0.0306, + "step": 26474 + }, + { + "epoch": 8.18, + "learning_rate": 1.3371672184902704e-05, + "loss": 0.0347, + "step": 26475 + }, + { + "epoch": 8.18, + "learning_rate": 1.3371201346995928e-05, + "loss": 0.0366, + "step": 26476 + }, + { + "epoch": 8.18, + "learning_rate": 1.3370730500657168e-05, + "loss": 0.0282, + "step": 26477 + }, + { + "epoch": 8.18, + "learning_rate": 1.337025964588759e-05, + "loss": 0.0312, + "step": 26478 + }, + { + "epoch": 8.18, + "learning_rate": 1.336978878268838e-05, + "loss": 0.0325, + "step": 26479 + }, + { + "epoch": 8.18, + "learning_rate": 1.3369317911060716e-05, + "loss": 0.0347, + "step": 26480 + }, + { + "epoch": 8.18, + "learning_rate": 1.336884703100577e-05, + "loss": 0.0284, + "step": 26481 + }, + { + "epoch": 8.18, + "learning_rate": 1.3368376142524723e-05, + "loss": 0.0279, + "step": 26482 + }, + { + "epoch": 8.18, + "learning_rate": 1.3367905245618755e-05, + "loss": 0.0335, + "step": 26483 + }, + { + "epoch": 8.18, + "learning_rate": 1.336743434028904e-05, + "loss": 0.032, + "step": 26484 + }, + { + "epoch": 8.18, + "learning_rate": 1.3366963426536759e-05, + "loss": 0.027, + "step": 26485 + }, + { + "epoch": 8.18, + "learning_rate": 1.3366492504363086e-05, + "loss": 0.0304, + "step": 26486 + }, + { + "epoch": 8.18, + "learning_rate": 1.3366021573769205e-05, + "loss": 0.0315, + "step": 26487 + }, + { + "epoch": 8.18, + "learning_rate": 1.3365550634756288e-05, + "loss": 0.0305, + "step": 26488 + }, + { + "epoch": 8.18, + "learning_rate": 1.3365079687325515e-05, + "loss": 0.0313, + "step": 26489 + }, + { + "epoch": 8.18, + "learning_rate": 1.3364608731478064e-05, + "loss": 0.0319, + "step": 26490 + }, + { + "epoch": 8.18, + "learning_rate": 1.3364137767215112e-05, + "loss": 0.0307, + "step": 26491 + }, + { + "epoch": 8.18, + "learning_rate": 1.3363666794537839e-05, + "loss": 0.027, + "step": 26492 + }, + { + "epoch": 8.18, + "learning_rate": 1.3363195813447422e-05, + "loss": 0.0325, + "step": 26493 + }, + { + "epoch": 8.18, + "learning_rate": 1.3362724823945039e-05, + "loss": 0.0347, + "step": 26494 + }, + { + "epoch": 8.18, + "learning_rate": 1.336225382603187e-05, + "loss": 0.0314, + "step": 26495 + }, + { + "epoch": 8.18, + "learning_rate": 1.3361782819709086e-05, + "loss": 0.0356, + "step": 26496 + }, + { + "epoch": 8.18, + "learning_rate": 1.3361311804977872e-05, + "loss": 0.0295, + "step": 26497 + }, + { + "epoch": 8.18, + "learning_rate": 1.3360840781839408e-05, + "loss": 0.0326, + "step": 26498 + }, + { + "epoch": 8.18, + "learning_rate": 1.3360369750294861e-05, + "loss": 0.0311, + "step": 26499 + }, + { + "epoch": 8.18, + "learning_rate": 1.3359898710345423e-05, + "loss": 0.0344, + "step": 26500 + }, + { + "epoch": 8.18, + "learning_rate": 1.335942766199226e-05, + "loss": 0.0333, + "step": 26501 + }, + { + "epoch": 8.18, + "learning_rate": 1.3358956605236559e-05, + "loss": 0.0332, + "step": 26502 + }, + { + "epoch": 8.18, + "learning_rate": 1.3358485540079496e-05, + "loss": 0.028, + "step": 26503 + }, + { + "epoch": 8.18, + "learning_rate": 1.3358014466522247e-05, + "loss": 0.0324, + "step": 26504 + }, + { + "epoch": 8.19, + "learning_rate": 1.335754338456599e-05, + "loss": 0.0306, + "step": 26505 + }, + { + "epoch": 8.19, + "learning_rate": 1.3357072294211907e-05, + "loss": 0.0297, + "step": 26506 + }, + { + "epoch": 8.19, + "learning_rate": 1.335660119546117e-05, + "loss": 0.0285, + "step": 26507 + }, + { + "epoch": 8.19, + "learning_rate": 1.3356130088314965e-05, + "loss": 0.0338, + "step": 26508 + }, + { + "epoch": 8.19, + "learning_rate": 1.3355658972774463e-05, + "loss": 0.0359, + "step": 26509 + }, + { + "epoch": 8.19, + "learning_rate": 1.335518784884085e-05, + "loss": 0.026, + "step": 26510 + }, + { + "epoch": 8.19, + "learning_rate": 1.3354716716515297e-05, + "loss": 0.0312, + "step": 26511 + }, + { + "epoch": 8.19, + "learning_rate": 1.3354245575798986e-05, + "loss": 0.034, + "step": 26512 + }, + { + "epoch": 8.19, + "learning_rate": 1.3353774426693096e-05, + "loss": 0.033, + "step": 26513 + }, + { + "epoch": 8.19, + "learning_rate": 1.3353303269198805e-05, + "loss": 0.0313, + "step": 26514 + }, + { + "epoch": 8.19, + "learning_rate": 1.335283210331729e-05, + "loss": 0.0297, + "step": 26515 + }, + { + "epoch": 8.19, + "learning_rate": 1.335236092904973e-05, + "loss": 0.0289, + "step": 26516 + }, + { + "epoch": 8.19, + "learning_rate": 1.3351889746397303e-05, + "loss": 0.0344, + "step": 26517 + }, + { + "epoch": 8.19, + "learning_rate": 1.335141855536119e-05, + "loss": 0.031, + "step": 26518 + }, + { + "epoch": 8.19, + "learning_rate": 1.335094735594257e-05, + "loss": 0.0364, + "step": 26519 + }, + { + "epoch": 8.19, + "learning_rate": 1.3350476148142616e-05, + "loss": 0.0284, + "step": 26520 + }, + { + "epoch": 8.19, + "learning_rate": 1.3350004931962512e-05, + "loss": 0.0307, + "step": 26521 + }, + { + "epoch": 8.19, + "learning_rate": 1.3349533707403432e-05, + "loss": 0.0351, + "step": 26522 + }, + { + "epoch": 8.19, + "learning_rate": 1.334906247446656e-05, + "loss": 0.0319, + "step": 26523 + }, + { + "epoch": 8.19, + "learning_rate": 1.3348591233153073e-05, + "loss": 0.0326, + "step": 26524 + }, + { + "epoch": 8.19, + "learning_rate": 1.3348119983464145e-05, + "loss": 0.0332, + "step": 26525 + }, + { + "epoch": 8.19, + "learning_rate": 1.3347648725400961e-05, + "loss": 0.0328, + "step": 26526 + }, + { + "epoch": 8.19, + "learning_rate": 1.3347177458964694e-05, + "loss": 0.0347, + "step": 26527 + }, + { + "epoch": 8.19, + "learning_rate": 1.3346706184156528e-05, + "loss": 0.03, + "step": 26528 + }, + { + "epoch": 8.19, + "learning_rate": 1.3346234900977642e-05, + "loss": 0.0291, + "step": 26529 + }, + { + "epoch": 8.19, + "learning_rate": 1.3345763609429208e-05, + "loss": 0.0287, + "step": 26530 + }, + { + "epoch": 8.19, + "learning_rate": 1.3345292309512412e-05, + "loss": 0.0343, + "step": 26531 + }, + { + "epoch": 8.19, + "learning_rate": 1.3344821001228427e-05, + "loss": 0.0327, + "step": 26532 + }, + { + "epoch": 8.19, + "learning_rate": 1.3344349684578433e-05, + "loss": 0.03, + "step": 26533 + }, + { + "epoch": 8.19, + "learning_rate": 1.3343878359563615e-05, + "loss": 0.0293, + "step": 26534 + }, + { + "epoch": 8.19, + "learning_rate": 1.3343407026185147e-05, + "loss": 0.0329, + "step": 26535 + }, + { + "epoch": 8.19, + "learning_rate": 1.3342935684444207e-05, + "loss": 0.0313, + "step": 26536 + }, + { + "epoch": 8.2, + "learning_rate": 1.3342464334341973e-05, + "loss": 0.0308, + "step": 26537 + }, + { + "epoch": 8.2, + "learning_rate": 1.3341992975879627e-05, + "loss": 0.0338, + "step": 26538 + }, + { + "epoch": 8.2, + "learning_rate": 1.334152160905835e-05, + "loss": 0.0306, + "step": 26539 + }, + { + "epoch": 8.2, + "learning_rate": 1.3341050233879315e-05, + "loss": 0.0355, + "step": 26540 + }, + { + "epoch": 8.2, + "learning_rate": 1.3340578850343706e-05, + "loss": 0.0337, + "step": 26541 + }, + { + "epoch": 8.2, + "learning_rate": 1.3340107458452699e-05, + "loss": 0.0312, + "step": 26542 + }, + { + "epoch": 8.2, + "learning_rate": 1.3339636058207473e-05, + "loss": 0.0295, + "step": 26543 + }, + { + "epoch": 8.2, + "learning_rate": 1.3339164649609209e-05, + "loss": 0.0304, + "step": 26544 + }, + { + "epoch": 8.2, + "learning_rate": 1.3338693232659086e-05, + "loss": 0.0301, + "step": 26545 + }, + { + "epoch": 8.2, + "learning_rate": 1.3338221807358283e-05, + "loss": 0.0325, + "step": 26546 + }, + { + "epoch": 8.2, + "learning_rate": 1.3337750373707975e-05, + "loss": 0.0336, + "step": 26547 + }, + { + "epoch": 8.2, + "learning_rate": 1.3337278931709347e-05, + "loss": 0.0325, + "step": 26548 + }, + { + "epoch": 8.2, + "learning_rate": 1.3336807481363576e-05, + "loss": 0.0311, + "step": 26549 + }, + { + "epoch": 8.2, + "learning_rate": 1.3336336022671838e-05, + "loss": 0.0274, + "step": 26550 + }, + { + "epoch": 8.2, + "learning_rate": 1.3335864555635318e-05, + "loss": 0.032, + "step": 26551 + }, + { + "epoch": 8.2, + "learning_rate": 1.3335393080255195e-05, + "loss": 0.0311, + "step": 26552 + }, + { + "epoch": 8.2, + "learning_rate": 1.3334921596532639e-05, + "loss": 0.0306, + "step": 26553 + }, + { + "epoch": 8.2, + "learning_rate": 1.3334450104468841e-05, + "loss": 0.0354, + "step": 26554 + }, + { + "epoch": 8.2, + "learning_rate": 1.333397860406497e-05, + "loss": 0.0325, + "step": 26555 + }, + { + "epoch": 8.2, + "learning_rate": 1.3333507095322214e-05, + "loss": 0.0353, + "step": 26556 + }, + { + "epoch": 8.2, + "learning_rate": 1.3333035578241751e-05, + "loss": 0.0364, + "step": 26557 + }, + { + "epoch": 8.2, + "learning_rate": 1.3332564052824752e-05, + "loss": 0.0285, + "step": 26558 + }, + { + "epoch": 8.2, + "learning_rate": 1.3332092519072406e-05, + "loss": 0.0339, + "step": 26559 + }, + { + "epoch": 8.2, + "learning_rate": 1.333162097698589e-05, + "loss": 0.0322, + "step": 26560 + }, + { + "epoch": 8.2, + "learning_rate": 1.3331149426566381e-05, + "loss": 0.0305, + "step": 26561 + }, + { + "epoch": 8.2, + "learning_rate": 1.3330677867815061e-05, + "loss": 0.0288, + "step": 26562 + }, + { + "epoch": 8.2, + "learning_rate": 1.3330206300733108e-05, + "loss": 0.0277, + "step": 26563 + }, + { + "epoch": 8.2, + "learning_rate": 1.3329734725321697e-05, + "loss": 0.0314, + "step": 26564 + }, + { + "epoch": 8.2, + "learning_rate": 1.3329263141582018e-05, + "loss": 0.0318, + "step": 26565 + }, + { + "epoch": 8.2, + "learning_rate": 1.3328791549515242e-05, + "loss": 0.0343, + "step": 26566 + }, + { + "epoch": 8.2, + "learning_rate": 1.3328319949122553e-05, + "loss": 0.0313, + "step": 26567 + }, + { + "epoch": 8.2, + "learning_rate": 1.3327848340405128e-05, + "loss": 0.0371, + "step": 26568 + }, + { + "epoch": 8.21, + "learning_rate": 1.3327376723364145e-05, + "loss": 0.0359, + "step": 26569 + }, + { + "epoch": 8.21, + "learning_rate": 1.3326905098000788e-05, + "loss": 0.0314, + "step": 26570 + }, + { + "epoch": 8.21, + "learning_rate": 1.3326433464316235e-05, + "loss": 0.0317, + "step": 26571 + }, + { + "epoch": 8.21, + "learning_rate": 1.3325961822311663e-05, + "loss": 0.0338, + "step": 26572 + }, + { + "epoch": 8.21, + "learning_rate": 1.3325490171988255e-05, + "loss": 0.0304, + "step": 26573 + }, + { + "epoch": 8.21, + "learning_rate": 1.332501851334719e-05, + "loss": 0.0311, + "step": 26574 + }, + { + "epoch": 8.21, + "learning_rate": 1.3324546846389648e-05, + "loss": 0.035, + "step": 26575 + }, + { + "epoch": 8.21, + "learning_rate": 1.3324075171116807e-05, + "loss": 0.0318, + "step": 26576 + }, + { + "epoch": 8.21, + "learning_rate": 1.3323603487529847e-05, + "loss": 0.0315, + "step": 26577 + }, + { + "epoch": 8.21, + "learning_rate": 1.332313179562995e-05, + "loss": 0.0288, + "step": 26578 + }, + { + "epoch": 8.21, + "learning_rate": 1.3322660095418295e-05, + "loss": 0.0382, + "step": 26579 + }, + { + "epoch": 8.21, + "learning_rate": 1.332218838689606e-05, + "loss": 0.0306, + "step": 26580 + }, + { + "epoch": 8.21, + "learning_rate": 1.3321716670064424e-05, + "loss": 0.0296, + "step": 26581 + }, + { + "epoch": 8.21, + "learning_rate": 1.332124494492457e-05, + "loss": 0.0317, + "step": 26582 + }, + { + "epoch": 8.21, + "learning_rate": 1.3320773211477678e-05, + "loss": 0.0341, + "step": 26583 + }, + { + "epoch": 8.21, + "learning_rate": 1.3320301469724924e-05, + "loss": 0.03, + "step": 26584 + }, + { + "epoch": 8.21, + "learning_rate": 1.3319829719667495e-05, + "loss": 0.0331, + "step": 26585 + }, + { + "epoch": 8.21, + "learning_rate": 1.3319357961306563e-05, + "loss": 0.0357, + "step": 26586 + }, + { + "epoch": 8.21, + "learning_rate": 1.3318886194643308e-05, + "loss": 0.0296, + "step": 26587 + }, + { + "epoch": 8.21, + "learning_rate": 1.331841441967892e-05, + "loss": 0.0328, + "step": 26588 + }, + { + "epoch": 8.21, + "learning_rate": 1.3317942636414568e-05, + "loss": 0.0331, + "step": 26589 + }, + { + "epoch": 8.21, + "learning_rate": 1.331747084485144e-05, + "loss": 0.0303, + "step": 26590 + }, + { + "epoch": 8.21, + "learning_rate": 1.3316999044990708e-05, + "loss": 0.0344, + "step": 26591 + }, + { + "epoch": 8.21, + "learning_rate": 1.3316527236833557e-05, + "loss": 0.0313, + "step": 26592 + }, + { + "epoch": 8.21, + "learning_rate": 1.3316055420381169e-05, + "loss": 0.0295, + "step": 26593 + }, + { + "epoch": 8.21, + "learning_rate": 1.331558359563472e-05, + "loss": 0.0316, + "step": 26594 + }, + { + "epoch": 8.21, + "learning_rate": 1.3315111762595391e-05, + "loss": 0.0367, + "step": 26595 + }, + { + "epoch": 8.21, + "learning_rate": 1.3314639921264365e-05, + "loss": 0.0289, + "step": 26596 + }, + { + "epoch": 8.21, + "learning_rate": 1.3314168071642819e-05, + "loss": 0.0324, + "step": 26597 + }, + { + "epoch": 8.21, + "learning_rate": 1.3313696213731932e-05, + "loss": 0.0312, + "step": 26598 + }, + { + "epoch": 8.21, + "learning_rate": 1.3313224347532889e-05, + "loss": 0.0362, + "step": 26599 + }, + { + "epoch": 8.21, + "learning_rate": 1.3312752473046869e-05, + "loss": 0.0333, + "step": 26600 + }, + { + "epoch": 8.21, + "learning_rate": 1.3312280590275047e-05, + "loss": 0.033, + "step": 26601 + }, + { + "epoch": 8.22, + "learning_rate": 1.3311808699218609e-05, + "loss": 0.0358, + "step": 26602 + }, + { + "epoch": 8.22, + "learning_rate": 1.3311336799878734e-05, + "loss": 0.0358, + "step": 26603 + }, + { + "epoch": 8.22, + "learning_rate": 1.33108648922566e-05, + "loss": 0.0352, + "step": 26604 + }, + { + "epoch": 8.22, + "learning_rate": 1.3310392976353393e-05, + "loss": 0.0323, + "step": 26605 + }, + { + "epoch": 8.22, + "learning_rate": 1.3309921052170284e-05, + "loss": 0.0344, + "step": 26606 + }, + { + "epoch": 8.22, + "learning_rate": 1.3309449119708462e-05, + "loss": 0.0316, + "step": 26607 + }, + { + "epoch": 8.22, + "learning_rate": 1.3308977178969103e-05, + "loss": 0.033, + "step": 26608 + }, + { + "epoch": 8.22, + "learning_rate": 1.330850522995339e-05, + "loss": 0.0304, + "step": 26609 + }, + { + "epoch": 8.22, + "learning_rate": 1.3308033272662502e-05, + "loss": 0.0346, + "step": 26610 + }, + { + "epoch": 8.22, + "learning_rate": 1.3307561307097619e-05, + "loss": 0.0292, + "step": 26611 + }, + { + "epoch": 8.22, + "learning_rate": 1.3307089333259919e-05, + "loss": 0.0347, + "step": 26612 + }, + { + "epoch": 8.22, + "learning_rate": 1.3306617351150589e-05, + "loss": 0.0329, + "step": 26613 + }, + { + "epoch": 8.22, + "learning_rate": 1.3306145360770807e-05, + "loss": 0.0333, + "step": 26614 + }, + { + "epoch": 8.22, + "learning_rate": 1.3305673362121747e-05, + "loss": 0.0335, + "step": 26615 + }, + { + "epoch": 8.22, + "learning_rate": 1.33052013552046e-05, + "loss": 0.0321, + "step": 26616 + }, + { + "epoch": 8.22, + "learning_rate": 1.3304729340020539e-05, + "loss": 0.0322, + "step": 26617 + }, + { + "epoch": 8.22, + "learning_rate": 1.3304257316570746e-05, + "loss": 0.0379, + "step": 26618 + }, + { + "epoch": 8.22, + "learning_rate": 1.3303785284856408e-05, + "loss": 0.0323, + "step": 26619 + }, + { + "epoch": 8.22, + "learning_rate": 1.3303313244878693e-05, + "loss": 0.0339, + "step": 26620 + }, + { + "epoch": 8.22, + "learning_rate": 1.3302841196638797e-05, + "loss": 0.0294, + "step": 26621 + }, + { + "epoch": 8.22, + "learning_rate": 1.330236914013789e-05, + "loss": 0.0354, + "step": 26622 + }, + { + "epoch": 8.22, + "learning_rate": 1.3301897075377151e-05, + "loss": 0.0345, + "step": 26623 + }, + { + "epoch": 8.22, + "learning_rate": 1.330142500235777e-05, + "loss": 0.0323, + "step": 26624 + }, + { + "epoch": 8.22, + "learning_rate": 1.330095292108092e-05, + "loss": 0.0321, + "step": 26625 + }, + { + "epoch": 8.22, + "learning_rate": 1.3300480831547788e-05, + "loss": 0.0343, + "step": 26626 + }, + { + "epoch": 8.22, + "learning_rate": 1.3300008733759548e-05, + "loss": 0.0286, + "step": 26627 + }, + { + "epoch": 8.22, + "learning_rate": 1.3299536627717386e-05, + "loss": 0.0341, + "step": 26628 + }, + { + "epoch": 8.22, + "learning_rate": 1.3299064513422485e-05, + "loss": 0.0318, + "step": 26629 + }, + { + "epoch": 8.22, + "learning_rate": 1.3298592390876015e-05, + "loss": 0.0249, + "step": 26630 + }, + { + "epoch": 8.22, + "learning_rate": 1.3298120260079168e-05, + "loss": 0.0324, + "step": 26631 + }, + { + "epoch": 8.22, + "learning_rate": 1.3297648121033118e-05, + "loss": 0.0279, + "step": 26632 + }, + { + "epoch": 8.22, + "learning_rate": 1.3297175973739051e-05, + "loss": 0.0318, + "step": 26633 + }, + { + "epoch": 8.23, + "learning_rate": 1.3296703818198147e-05, + "loss": 0.0365, + "step": 26634 + }, + { + "epoch": 8.23, + "learning_rate": 1.329623165441158e-05, + "loss": 0.034, + "step": 26635 + }, + { + "epoch": 8.23, + "learning_rate": 1.329575948238054e-05, + "loss": 0.0314, + "step": 26636 + }, + { + "epoch": 8.23, + "learning_rate": 1.3295287302106204e-05, + "loss": 0.0325, + "step": 26637 + }, + { + "epoch": 8.23, + "learning_rate": 1.3294815113589754e-05, + "loss": 0.0331, + "step": 26638 + }, + { + "epoch": 8.23, + "learning_rate": 1.3294342916832373e-05, + "loss": 0.04, + "step": 26639 + }, + { + "epoch": 8.23, + "learning_rate": 1.3293870711835233e-05, + "loss": 0.0334, + "step": 26640 + }, + { + "epoch": 8.23, + "learning_rate": 1.3293398498599524e-05, + "loss": 0.0368, + "step": 26641 + }, + { + "epoch": 8.23, + "learning_rate": 1.3292926277126428e-05, + "loss": 0.0311, + "step": 26642 + }, + { + "epoch": 8.23, + "learning_rate": 1.3292454047417119e-05, + "loss": 0.0319, + "step": 26643 + }, + { + "epoch": 8.23, + "learning_rate": 1.3291981809472785e-05, + "loss": 0.0327, + "step": 26644 + }, + { + "epoch": 8.23, + "learning_rate": 1.3291509563294602e-05, + "loss": 0.0355, + "step": 26645 + }, + { + "epoch": 8.23, + "learning_rate": 1.3291037308883752e-05, + "loss": 0.0317, + "step": 26646 + }, + { + "epoch": 8.23, + "learning_rate": 1.3290565046241421e-05, + "loss": 0.0385, + "step": 26647 + }, + { + "epoch": 8.23, + "learning_rate": 1.3290092775368786e-05, + "loss": 0.032, + "step": 26648 + }, + { + "epoch": 8.23, + "learning_rate": 1.3289620496267026e-05, + "loss": 0.0273, + "step": 26649 + }, + { + "epoch": 8.23, + "learning_rate": 1.3289148208937328e-05, + "loss": 0.0298, + "step": 26650 + }, + { + "epoch": 8.23, + "learning_rate": 1.3288675913380869e-05, + "loss": 0.0315, + "step": 26651 + }, + { + "epoch": 8.23, + "learning_rate": 1.328820360959883e-05, + "loss": 0.0331, + "step": 26652 + }, + { + "epoch": 8.23, + "learning_rate": 1.3287731297592396e-05, + "loss": 0.0329, + "step": 26653 + }, + { + "epoch": 8.23, + "learning_rate": 1.3287258977362747e-05, + "loss": 0.0315, + "step": 26654 + }, + { + "epoch": 8.23, + "learning_rate": 1.3286786648911063e-05, + "loss": 0.0332, + "step": 26655 + }, + { + "epoch": 8.23, + "learning_rate": 1.3286314312238527e-05, + "loss": 0.0327, + "step": 26656 + }, + { + "epoch": 8.23, + "learning_rate": 1.3285841967346318e-05, + "loss": 0.034, + "step": 26657 + }, + { + "epoch": 8.23, + "learning_rate": 1.328536961423562e-05, + "loss": 0.0306, + "step": 26658 + }, + { + "epoch": 8.23, + "learning_rate": 1.3284897252907613e-05, + "loss": 0.0342, + "step": 26659 + }, + { + "epoch": 8.23, + "learning_rate": 1.3284424883363478e-05, + "loss": 0.0309, + "step": 26660 + }, + { + "epoch": 8.23, + "learning_rate": 1.32839525056044e-05, + "loss": 0.0323, + "step": 26661 + }, + { + "epoch": 8.23, + "learning_rate": 1.3283480119631555e-05, + "loss": 0.0308, + "step": 26662 + }, + { + "epoch": 8.23, + "learning_rate": 1.3283007725446129e-05, + "loss": 0.0304, + "step": 26663 + }, + { + "epoch": 8.23, + "learning_rate": 1.3282535323049302e-05, + "loss": 0.036, + "step": 26664 + }, + { + "epoch": 8.23, + "learning_rate": 1.3282062912442255e-05, + "loss": 0.0338, + "step": 26665 + }, + { + "epoch": 8.24, + "learning_rate": 1.328159049362617e-05, + "loss": 0.0325, + "step": 26666 + }, + { + "epoch": 8.24, + "learning_rate": 1.3281118066602228e-05, + "loss": 0.0309, + "step": 26667 + }, + { + "epoch": 8.24, + "learning_rate": 1.3280645631371614e-05, + "loss": 0.0303, + "step": 26668 + }, + { + "epoch": 8.24, + "learning_rate": 1.3280173187935501e-05, + "loss": 0.0303, + "step": 26669 + }, + { + "epoch": 8.24, + "learning_rate": 1.3279700736295083e-05, + "loss": 0.0326, + "step": 26670 + }, + { + "epoch": 8.24, + "learning_rate": 1.327922827645153e-05, + "loss": 0.0323, + "step": 26671 + }, + { + "epoch": 8.24, + "learning_rate": 1.3278755808406032e-05, + "loss": 0.0357, + "step": 26672 + }, + { + "epoch": 8.24, + "learning_rate": 1.3278283332159769e-05, + "loss": 0.0285, + "step": 26673 + }, + { + "epoch": 8.24, + "learning_rate": 1.3277810847713917e-05, + "loss": 0.0336, + "step": 26674 + }, + { + "epoch": 8.24, + "learning_rate": 1.3277338355069667e-05, + "loss": 0.0347, + "step": 26675 + }, + { + "epoch": 8.24, + "learning_rate": 1.3276865854228197e-05, + "loss": 0.0326, + "step": 26676 + }, + { + "epoch": 8.24, + "learning_rate": 1.3276393345190681e-05, + "loss": 0.0361, + "step": 26677 + }, + { + "epoch": 8.24, + "learning_rate": 1.3275920827958313e-05, + "loss": 0.0319, + "step": 26678 + }, + { + "epoch": 8.24, + "learning_rate": 1.3275448302532267e-05, + "loss": 0.0302, + "step": 26679 + }, + { + "epoch": 8.24, + "learning_rate": 1.3274975768913728e-05, + "loss": 0.0336, + "step": 26680 + }, + { + "epoch": 8.24, + "learning_rate": 1.3274503227103878e-05, + "loss": 0.0355, + "step": 26681 + }, + { + "epoch": 8.24, + "learning_rate": 1.3274030677103897e-05, + "loss": 0.0356, + "step": 26682 + }, + { + "epoch": 8.24, + "learning_rate": 1.327355811891497e-05, + "loss": 0.0317, + "step": 26683 + }, + { + "epoch": 8.24, + "learning_rate": 1.3273085552538276e-05, + "loss": 0.0327, + "step": 26684 + }, + { + "epoch": 8.24, + "learning_rate": 1.3272612977975e-05, + "loss": 0.0328, + "step": 26685 + }, + { + "epoch": 8.24, + "learning_rate": 1.327214039522632e-05, + "loss": 0.0355, + "step": 26686 + }, + { + "epoch": 8.24, + "learning_rate": 1.327166780429342e-05, + "loss": 0.032, + "step": 26687 + }, + { + "epoch": 8.24, + "learning_rate": 1.3271195205177483e-05, + "loss": 0.0348, + "step": 26688 + }, + { + "epoch": 8.24, + "learning_rate": 1.3270722597879688e-05, + "loss": 0.0308, + "step": 26689 + }, + { + "epoch": 8.24, + "learning_rate": 1.3270249982401219e-05, + "loss": 0.0335, + "step": 26690 + }, + { + "epoch": 8.24, + "learning_rate": 1.3269777358743261e-05, + "loss": 0.0376, + "step": 26691 + }, + { + "epoch": 8.24, + "learning_rate": 1.3269304726906993e-05, + "loss": 0.0322, + "step": 26692 + }, + { + "epoch": 8.24, + "learning_rate": 1.32688320868936e-05, + "loss": 0.0328, + "step": 26693 + }, + { + "epoch": 8.24, + "learning_rate": 1.3268359438704257e-05, + "loss": 0.0303, + "step": 26694 + }, + { + "epoch": 8.24, + "learning_rate": 1.326788678234015e-05, + "loss": 0.0348, + "step": 26695 + }, + { + "epoch": 8.24, + "learning_rate": 1.3267414117802469e-05, + "loss": 0.0347, + "step": 26696 + }, + { + "epoch": 8.24, + "learning_rate": 1.3266941445092384e-05, + "loss": 0.0336, + "step": 26697 + }, + { + "epoch": 8.24, + "learning_rate": 1.3266468764211084e-05, + "loss": 0.0349, + "step": 26698 + }, + { + "epoch": 8.25, + "learning_rate": 1.3265996075159751e-05, + "loss": 0.0311, + "step": 26699 + }, + { + "epoch": 8.25, + "learning_rate": 1.3265523377939564e-05, + "loss": 0.0312, + "step": 26700 + }, + { + "epoch": 8.25, + "learning_rate": 1.326505067255171e-05, + "loss": 0.0334, + "step": 26701 + }, + { + "epoch": 8.25, + "learning_rate": 1.3264577958997364e-05, + "loss": 0.0304, + "step": 26702 + }, + { + "epoch": 8.25, + "learning_rate": 1.3264105237277718e-05, + "loss": 0.032, + "step": 26703 + }, + { + "epoch": 8.25, + "learning_rate": 1.3263632507393949e-05, + "loss": 0.035, + "step": 26704 + }, + { + "epoch": 8.25, + "learning_rate": 1.3263159769347236e-05, + "loss": 0.0364, + "step": 26705 + }, + { + "epoch": 8.25, + "learning_rate": 1.3262687023138769e-05, + "loss": 0.0303, + "step": 26706 + }, + { + "epoch": 8.25, + "learning_rate": 1.3262214268769727e-05, + "loss": 0.0309, + "step": 26707 + }, + { + "epoch": 8.25, + "learning_rate": 1.326174150624129e-05, + "loss": 0.0336, + "step": 26708 + }, + { + "epoch": 8.25, + "learning_rate": 1.3261268735554642e-05, + "loss": 0.0296, + "step": 26709 + }, + { + "epoch": 8.25, + "learning_rate": 1.3260795956710968e-05, + "loss": 0.0326, + "step": 26710 + }, + { + "epoch": 8.25, + "learning_rate": 1.3260323169711447e-05, + "loss": 0.0293, + "step": 26711 + }, + { + "epoch": 8.25, + "learning_rate": 1.3259850374557264e-05, + "loss": 0.0308, + "step": 26712 + }, + { + "epoch": 8.25, + "learning_rate": 1.3259377571249602e-05, + "loss": 0.0285, + "step": 26713 + }, + { + "epoch": 8.25, + "learning_rate": 1.325890475978964e-05, + "loss": 0.0327, + "step": 26714 + }, + { + "epoch": 8.25, + "learning_rate": 1.3258431940178565e-05, + "loss": 0.0346, + "step": 26715 + }, + { + "epoch": 8.25, + "learning_rate": 1.3257959112417554e-05, + "loss": 0.0303, + "step": 26716 + }, + { + "epoch": 8.25, + "learning_rate": 1.3257486276507797e-05, + "loss": 0.0316, + "step": 26717 + }, + { + "epoch": 8.25, + "learning_rate": 1.325701343245047e-05, + "loss": 0.0342, + "step": 26718 + }, + { + "epoch": 8.25, + "learning_rate": 1.325654058024676e-05, + "loss": 0.039, + "step": 26719 + }, + { + "epoch": 8.25, + "learning_rate": 1.3256067719897845e-05, + "loss": 0.0338, + "step": 26720 + }, + { + "epoch": 8.25, + "learning_rate": 1.3255594851404914e-05, + "loss": 0.0355, + "step": 26721 + }, + { + "epoch": 8.25, + "learning_rate": 1.3255121974769145e-05, + "loss": 0.0324, + "step": 26722 + }, + { + "epoch": 8.25, + "learning_rate": 1.3254649089991722e-05, + "loss": 0.0323, + "step": 26723 + }, + { + "epoch": 8.25, + "learning_rate": 1.3254176197073832e-05, + "loss": 0.0317, + "step": 26724 + }, + { + "epoch": 8.25, + "learning_rate": 1.3253703296016648e-05, + "loss": 0.0352, + "step": 26725 + }, + { + "epoch": 8.25, + "learning_rate": 1.325323038682136e-05, + "loss": 0.0318, + "step": 26726 + }, + { + "epoch": 8.25, + "learning_rate": 1.3252757469489153e-05, + "loss": 0.03, + "step": 26727 + }, + { + "epoch": 8.25, + "learning_rate": 1.3252284544021201e-05, + "loss": 0.032, + "step": 26728 + }, + { + "epoch": 8.25, + "learning_rate": 1.3251811610418699e-05, + "loss": 0.0313, + "step": 26729 + }, + { + "epoch": 8.25, + "learning_rate": 1.3251338668682818e-05, + "loss": 0.0315, + "step": 26730 + }, + { + "epoch": 8.26, + "learning_rate": 1.3250865718814746e-05, + "loss": 0.033, + "step": 26731 + }, + { + "epoch": 8.26, + "learning_rate": 1.3250392760815668e-05, + "loss": 0.0327, + "step": 26732 + }, + { + "epoch": 8.26, + "learning_rate": 1.3249919794686764e-05, + "loss": 0.0317, + "step": 26733 + }, + { + "epoch": 8.26, + "learning_rate": 1.3249446820429218e-05, + "loss": 0.0348, + "step": 26734 + }, + { + "epoch": 8.26, + "learning_rate": 1.3248973838044212e-05, + "loss": 0.0312, + "step": 26735 + }, + { + "epoch": 8.26, + "learning_rate": 1.3248500847532927e-05, + "loss": 0.0284, + "step": 26736 + }, + { + "epoch": 8.26, + "learning_rate": 1.3248027848896557e-05, + "loss": 0.0339, + "step": 26737 + }, + { + "epoch": 8.26, + "learning_rate": 1.3247554842136273e-05, + "loss": 0.0363, + "step": 26738 + }, + { + "epoch": 8.26, + "learning_rate": 1.324708182725326e-05, + "loss": 0.0318, + "step": 26739 + }, + { + "epoch": 8.26, + "learning_rate": 1.3246608804248705e-05, + "loss": 0.0322, + "step": 26740 + }, + { + "epoch": 8.26, + "learning_rate": 1.3246135773123787e-05, + "loss": 0.0334, + "step": 26741 + }, + { + "epoch": 8.26, + "learning_rate": 1.3245662733879693e-05, + "loss": 0.0329, + "step": 26742 + }, + { + "epoch": 8.26, + "learning_rate": 1.3245189686517605e-05, + "loss": 0.0388, + "step": 26743 + }, + { + "epoch": 8.26, + "learning_rate": 1.3244716631038705e-05, + "loss": 0.0326, + "step": 26744 + }, + { + "epoch": 8.26, + "learning_rate": 1.3244243567444177e-05, + "loss": 0.0329, + "step": 26745 + }, + { + "epoch": 8.26, + "learning_rate": 1.3243770495735204e-05, + "loss": 0.0309, + "step": 26746 + }, + { + "epoch": 8.26, + "learning_rate": 1.3243297415912973e-05, + "loss": 0.0357, + "step": 26747 + }, + { + "epoch": 8.26, + "learning_rate": 1.3242824327978659e-05, + "loss": 0.0336, + "step": 26748 + }, + { + "epoch": 8.26, + "learning_rate": 1.324235123193345e-05, + "loss": 0.0347, + "step": 26749 + }, + { + "epoch": 8.26, + "learning_rate": 1.3241878127778533e-05, + "loss": 0.0338, + "step": 26750 + }, + { + "epoch": 8.26, + "learning_rate": 1.3241405015515082e-05, + "loss": 0.0306, + "step": 26751 + }, + { + "epoch": 8.26, + "learning_rate": 1.324093189514429e-05, + "loss": 0.0335, + "step": 26752 + }, + { + "epoch": 8.26, + "learning_rate": 1.3240458766667335e-05, + "loss": 0.0293, + "step": 26753 + }, + { + "epoch": 8.26, + "learning_rate": 1.32399856300854e-05, + "loss": 0.0344, + "step": 26754 + }, + { + "epoch": 8.26, + "learning_rate": 1.3239512485399675e-05, + "loss": 0.0315, + "step": 26755 + }, + { + "epoch": 8.26, + "learning_rate": 1.3239039332611332e-05, + "loss": 0.0362, + "step": 26756 + }, + { + "epoch": 8.26, + "learning_rate": 1.3238566171721565e-05, + "loss": 0.0341, + "step": 26757 + }, + { + "epoch": 8.26, + "learning_rate": 1.3238093002731553e-05, + "loss": 0.0337, + "step": 26758 + }, + { + "epoch": 8.26, + "learning_rate": 1.3237619825642476e-05, + "loss": 0.0325, + "step": 26759 + }, + { + "epoch": 8.26, + "learning_rate": 1.3237146640455526e-05, + "loss": 0.0327, + "step": 26760 + }, + { + "epoch": 8.26, + "learning_rate": 1.3236673447171882e-05, + "loss": 0.0354, + "step": 26761 + }, + { + "epoch": 8.26, + "learning_rate": 1.3236200245792726e-05, + "loss": 0.0304, + "step": 26762 + }, + { + "epoch": 8.26, + "learning_rate": 1.3235727036319241e-05, + "loss": 0.0299, + "step": 26763 + }, + { + "epoch": 8.27, + "learning_rate": 1.3235253818752614e-05, + "loss": 0.033, + "step": 26764 + }, + { + "epoch": 8.27, + "learning_rate": 1.3234780593094028e-05, + "loss": 0.0355, + "step": 26765 + }, + { + "epoch": 8.27, + "learning_rate": 1.3234307359344665e-05, + "loss": 0.0336, + "step": 26766 + }, + { + "epoch": 8.27, + "learning_rate": 1.3233834117505708e-05, + "loss": 0.0351, + "step": 26767 + }, + { + "epoch": 8.27, + "learning_rate": 1.3233360867578345e-05, + "loss": 0.0358, + "step": 26768 + }, + { + "epoch": 8.27, + "learning_rate": 1.3232887609563753e-05, + "loss": 0.0287, + "step": 26769 + }, + { + "epoch": 8.27, + "learning_rate": 1.3232414343463123e-05, + "loss": 0.0344, + "step": 26770 + }, + { + "epoch": 8.27, + "learning_rate": 1.3231941069277632e-05, + "loss": 0.0299, + "step": 26771 + }, + { + "epoch": 8.27, + "learning_rate": 1.3231467787008469e-05, + "loss": 0.0355, + "step": 26772 + }, + { + "epoch": 8.27, + "learning_rate": 1.3230994496656814e-05, + "loss": 0.0371, + "step": 26773 + }, + { + "epoch": 8.27, + "learning_rate": 1.3230521198223855e-05, + "loss": 0.034, + "step": 26774 + }, + { + "epoch": 8.27, + "learning_rate": 1.3230047891710771e-05, + "loss": 0.0309, + "step": 26775 + }, + { + "epoch": 8.27, + "learning_rate": 1.3229574577118751e-05, + "loss": 0.0341, + "step": 26776 + }, + { + "epoch": 8.27, + "learning_rate": 1.3229101254448973e-05, + "loss": 0.0318, + "step": 26777 + }, + { + "epoch": 8.27, + "learning_rate": 1.3228627923702625e-05, + "loss": 0.0344, + "step": 26778 + }, + { + "epoch": 8.27, + "learning_rate": 1.322815458488089e-05, + "loss": 0.0363, + "step": 26779 + }, + { + "epoch": 8.27, + "learning_rate": 1.322768123798495e-05, + "loss": 0.0306, + "step": 26780 + }, + { + "epoch": 8.27, + "learning_rate": 1.3227207883015996e-05, + "loss": 0.0315, + "step": 26781 + }, + { + "epoch": 8.27, + "learning_rate": 1.32267345199752e-05, + "loss": 0.0308, + "step": 26782 + }, + { + "epoch": 8.27, + "learning_rate": 1.3226261148863754e-05, + "loss": 0.0333, + "step": 26783 + }, + { + "epoch": 8.27, + "learning_rate": 1.3225787769682841e-05, + "loss": 0.0281, + "step": 26784 + }, + { + "epoch": 8.27, + "learning_rate": 1.3225314382433645e-05, + "loss": 0.033, + "step": 26785 + }, + { + "epoch": 8.27, + "learning_rate": 1.3224840987117352e-05, + "loss": 0.0349, + "step": 26786 + }, + { + "epoch": 8.27, + "learning_rate": 1.3224367583735135e-05, + "loss": 0.0329, + "step": 26787 + }, + { + "epoch": 8.27, + "learning_rate": 1.3223894172288195e-05, + "loss": 0.0432, + "step": 26788 + }, + { + "epoch": 8.27, + "learning_rate": 1.3223420752777705e-05, + "loss": 0.0296, + "step": 26789 + }, + { + "epoch": 8.27, + "learning_rate": 1.322294732520485e-05, + "loss": 0.0342, + "step": 26790 + }, + { + "epoch": 8.27, + "learning_rate": 1.3222473889570819e-05, + "loss": 0.0319, + "step": 26791 + }, + { + "epoch": 8.27, + "learning_rate": 1.322200044587679e-05, + "loss": 0.0323, + "step": 26792 + }, + { + "epoch": 8.27, + "learning_rate": 1.3221526994123952e-05, + "loss": 0.0287, + "step": 26793 + }, + { + "epoch": 8.27, + "learning_rate": 1.3221053534313488e-05, + "loss": 0.0332, + "step": 26794 + }, + { + "epoch": 8.27, + "learning_rate": 1.322058006644658e-05, + "loss": 0.0275, + "step": 26795 + }, + { + "epoch": 8.28, + "learning_rate": 1.3220106590524415e-05, + "loss": 0.036, + "step": 26796 + }, + { + "epoch": 8.28, + "learning_rate": 1.3219633106548178e-05, + "loss": 0.0329, + "step": 26797 + }, + { + "epoch": 8.28, + "learning_rate": 1.3219159614519049e-05, + "loss": 0.033, + "step": 26798 + }, + { + "epoch": 8.28, + "learning_rate": 1.3218686114438213e-05, + "loss": 0.0322, + "step": 26799 + }, + { + "epoch": 8.28, + "learning_rate": 1.3218212606306857e-05, + "loss": 0.034, + "step": 26800 + }, + { + "epoch": 8.28, + "learning_rate": 1.3217739090126168e-05, + "loss": 0.0301, + "step": 26801 + }, + { + "epoch": 8.28, + "learning_rate": 1.3217265565897322e-05, + "loss": 0.0345, + "step": 26802 + }, + { + "epoch": 8.28, + "learning_rate": 1.3216792033621507e-05, + "loss": 0.0328, + "step": 26803 + }, + { + "epoch": 8.28, + "learning_rate": 1.3216318493299913e-05, + "loss": 0.035, + "step": 26804 + }, + { + "epoch": 8.28, + "learning_rate": 1.3215844944933718e-05, + "loss": 0.0348, + "step": 26805 + }, + { + "epoch": 8.28, + "learning_rate": 1.3215371388524112e-05, + "loss": 0.0343, + "step": 26806 + }, + { + "epoch": 8.28, + "learning_rate": 1.3214897824072269e-05, + "loss": 0.0323, + "step": 26807 + }, + { + "epoch": 8.28, + "learning_rate": 1.3214424251579382e-05, + "loss": 0.0333, + "step": 26808 + }, + { + "epoch": 8.28, + "learning_rate": 1.3213950671046639e-05, + "loss": 0.0298, + "step": 26809 + }, + { + "epoch": 8.28, + "learning_rate": 1.3213477082475212e-05, + "loss": 0.0338, + "step": 26810 + }, + { + "epoch": 8.28, + "learning_rate": 1.3213003485866298e-05, + "loss": 0.0379, + "step": 26811 + }, + { + "epoch": 8.28, + "learning_rate": 1.3212529881221073e-05, + "loss": 0.0356, + "step": 26812 + }, + { + "epoch": 8.28, + "learning_rate": 1.3212056268540723e-05, + "loss": 0.0329, + "step": 26813 + }, + { + "epoch": 8.28, + "learning_rate": 1.3211582647826439e-05, + "loss": 0.0318, + "step": 26814 + }, + { + "epoch": 8.28, + "learning_rate": 1.32111090190794e-05, + "loss": 0.0328, + "step": 26815 + }, + { + "epoch": 8.28, + "learning_rate": 1.321063538230079e-05, + "loss": 0.0384, + "step": 26816 + }, + { + "epoch": 8.28, + "learning_rate": 1.3210161737491798e-05, + "loss": 0.035, + "step": 26817 + }, + { + "epoch": 8.28, + "learning_rate": 1.3209688084653603e-05, + "loss": 0.0347, + "step": 26818 + }, + { + "epoch": 8.28, + "learning_rate": 1.3209214423787396e-05, + "loss": 0.031, + "step": 26819 + }, + { + "epoch": 8.28, + "learning_rate": 1.3208740754894355e-05, + "loss": 0.0305, + "step": 26820 + }, + { + "epoch": 8.28, + "learning_rate": 1.3208267077975668e-05, + "loss": 0.0347, + "step": 26821 + }, + { + "epoch": 8.28, + "learning_rate": 1.3207793393032522e-05, + "loss": 0.0318, + "step": 26822 + }, + { + "epoch": 8.28, + "learning_rate": 1.3207319700066102e-05, + "loss": 0.0303, + "step": 26823 + }, + { + "epoch": 8.28, + "learning_rate": 1.3206845999077587e-05, + "loss": 0.0351, + "step": 26824 + }, + { + "epoch": 8.28, + "learning_rate": 1.3206372290068164e-05, + "loss": 0.0306, + "step": 26825 + }, + { + "epoch": 8.28, + "learning_rate": 1.3205898573039022e-05, + "loss": 0.0408, + "step": 26826 + }, + { + "epoch": 8.28, + "learning_rate": 1.3205424847991341e-05, + "loss": 0.0341, + "step": 26827 + }, + { + "epoch": 8.29, + "learning_rate": 1.320495111492631e-05, + "loss": 0.0323, + "step": 26828 + }, + { + "epoch": 8.29, + "learning_rate": 1.3204477373845109e-05, + "loss": 0.0322, + "step": 26829 + }, + { + "epoch": 8.29, + "learning_rate": 1.3204003624748926e-05, + "loss": 0.029, + "step": 26830 + }, + { + "epoch": 8.29, + "learning_rate": 1.3203529867638947e-05, + "loss": 0.0322, + "step": 26831 + }, + { + "epoch": 8.29, + "learning_rate": 1.3203056102516359e-05, + "loss": 0.0351, + "step": 26832 + }, + { + "epoch": 8.29, + "learning_rate": 1.3202582329382336e-05, + "loss": 0.032, + "step": 26833 + }, + { + "epoch": 8.29, + "learning_rate": 1.3202108548238072e-05, + "loss": 0.0339, + "step": 26834 + }, + { + "epoch": 8.29, + "learning_rate": 1.3201634759084754e-05, + "loss": 0.033, + "step": 26835 + }, + { + "epoch": 8.29, + "learning_rate": 1.3201160961923563e-05, + "loss": 0.0352, + "step": 26836 + }, + { + "epoch": 8.29, + "learning_rate": 1.3200687156755685e-05, + "loss": 0.0355, + "step": 26837 + }, + { + "epoch": 8.29, + "learning_rate": 1.3200213343582301e-05, + "loss": 0.0371, + "step": 26838 + }, + { + "epoch": 8.29, + "learning_rate": 1.3199739522404602e-05, + "loss": 0.0363, + "step": 26839 + }, + { + "epoch": 8.29, + "learning_rate": 1.3199265693223773e-05, + "loss": 0.0339, + "step": 26840 + }, + { + "epoch": 8.29, + "learning_rate": 1.3198791856040994e-05, + "loss": 0.0326, + "step": 26841 + }, + { + "epoch": 8.29, + "learning_rate": 1.3198318010857456e-05, + "loss": 0.0337, + "step": 26842 + }, + { + "epoch": 8.29, + "learning_rate": 1.3197844157674337e-05, + "loss": 0.0371, + "step": 26843 + }, + { + "epoch": 8.29, + "learning_rate": 1.3197370296492829e-05, + "loss": 0.0301, + "step": 26844 + }, + { + "epoch": 8.29, + "learning_rate": 1.3196896427314117e-05, + "loss": 0.0351, + "step": 26845 + }, + { + "epoch": 8.29, + "learning_rate": 1.3196422550139381e-05, + "loss": 0.0332, + "step": 26846 + }, + { + "epoch": 8.29, + "learning_rate": 1.3195948664969808e-05, + "loss": 0.035, + "step": 26847 + }, + { + "epoch": 8.29, + "learning_rate": 1.3195474771806587e-05, + "loss": 0.0345, + "step": 26848 + }, + { + "epoch": 8.29, + "learning_rate": 1.3195000870650897e-05, + "loss": 0.033, + "step": 26849 + }, + { + "epoch": 8.29, + "learning_rate": 1.3194526961503932e-05, + "loss": 0.0336, + "step": 26850 + }, + { + "epoch": 8.29, + "learning_rate": 1.3194053044366872e-05, + "loss": 0.0325, + "step": 26851 + }, + { + "epoch": 8.29, + "learning_rate": 1.31935791192409e-05, + "loss": 0.0342, + "step": 26852 + }, + { + "epoch": 8.29, + "learning_rate": 1.3193105186127206e-05, + "loss": 0.0321, + "step": 26853 + }, + { + "epoch": 8.29, + "learning_rate": 1.3192631245026975e-05, + "loss": 0.0306, + "step": 26854 + }, + { + "epoch": 8.29, + "learning_rate": 1.3192157295941388e-05, + "loss": 0.0327, + "step": 26855 + }, + { + "epoch": 8.29, + "learning_rate": 1.3191683338871632e-05, + "loss": 0.0317, + "step": 26856 + }, + { + "epoch": 8.29, + "learning_rate": 1.3191209373818899e-05, + "loss": 0.034, + "step": 26857 + }, + { + "epoch": 8.29, + "learning_rate": 1.3190735400784365e-05, + "loss": 0.0342, + "step": 26858 + }, + { + "epoch": 8.29, + "learning_rate": 1.3190261419769222e-05, + "loss": 0.0304, + "step": 26859 + }, + { + "epoch": 8.29, + "learning_rate": 1.3189787430774651e-05, + "loss": 0.031, + "step": 26860 + }, + { + "epoch": 8.3, + "learning_rate": 1.3189313433801842e-05, + "loss": 0.0303, + "step": 26861 + }, + { + "epoch": 8.3, + "learning_rate": 1.3188839428851978e-05, + "loss": 0.0301, + "step": 26862 + }, + { + "epoch": 8.3, + "learning_rate": 1.3188365415926247e-05, + "loss": 0.0304, + "step": 26863 + }, + { + "epoch": 8.3, + "learning_rate": 1.318789139502583e-05, + "loss": 0.033, + "step": 26864 + }, + { + "epoch": 8.3, + "learning_rate": 1.3187417366151913e-05, + "loss": 0.0337, + "step": 26865 + }, + { + "epoch": 8.3, + "learning_rate": 1.3186943329305688e-05, + "loss": 0.034, + "step": 26866 + }, + { + "epoch": 8.3, + "learning_rate": 1.3186469284488335e-05, + "loss": 0.0331, + "step": 26867 + }, + { + "epoch": 8.3, + "learning_rate": 1.3185995231701043e-05, + "loss": 0.0379, + "step": 26868 + }, + { + "epoch": 8.3, + "learning_rate": 1.3185521170944991e-05, + "loss": 0.0324, + "step": 26869 + }, + { + "epoch": 8.3, + "learning_rate": 1.3185047102221373e-05, + "loss": 0.0347, + "step": 26870 + }, + { + "epoch": 8.3, + "learning_rate": 1.3184573025531372e-05, + "loss": 0.0342, + "step": 26871 + }, + { + "epoch": 8.3, + "learning_rate": 1.3184098940876169e-05, + "loss": 0.0295, + "step": 26872 + }, + { + "epoch": 8.3, + "learning_rate": 1.318362484825696e-05, + "loss": 0.0327, + "step": 26873 + }, + { + "epoch": 8.3, + "learning_rate": 1.318315074767492e-05, + "loss": 0.0391, + "step": 26874 + }, + { + "epoch": 8.3, + "learning_rate": 1.318267663913124e-05, + "loss": 0.0379, + "step": 26875 + }, + { + "epoch": 8.3, + "learning_rate": 1.3182202522627107e-05, + "loss": 0.0322, + "step": 26876 + }, + { + "epoch": 8.3, + "learning_rate": 1.3181728398163705e-05, + "loss": 0.033, + "step": 26877 + }, + { + "epoch": 8.3, + "learning_rate": 1.3181254265742218e-05, + "loss": 0.0368, + "step": 26878 + }, + { + "epoch": 8.3, + "learning_rate": 1.3180780125363835e-05, + "loss": 0.0369, + "step": 26879 + }, + { + "epoch": 8.3, + "learning_rate": 1.318030597702974e-05, + "loss": 0.0333, + "step": 26880 + }, + { + "epoch": 8.3, + "learning_rate": 1.3179831820741121e-05, + "loss": 0.0333, + "step": 26881 + }, + { + "epoch": 8.3, + "learning_rate": 1.3179357656499161e-05, + "loss": 0.0337, + "step": 26882 + }, + { + "epoch": 8.3, + "learning_rate": 1.3178883484305049e-05, + "loss": 0.0362, + "step": 26883 + }, + { + "epoch": 8.3, + "learning_rate": 1.3178409304159967e-05, + "loss": 0.0343, + "step": 26884 + }, + { + "epoch": 8.3, + "learning_rate": 1.3177935116065105e-05, + "loss": 0.0367, + "step": 26885 + }, + { + "epoch": 8.3, + "learning_rate": 1.317746092002165e-05, + "loss": 0.0352, + "step": 26886 + }, + { + "epoch": 8.3, + "learning_rate": 1.3176986716030784e-05, + "loss": 0.0329, + "step": 26887 + }, + { + "epoch": 8.3, + "learning_rate": 1.3176512504093694e-05, + "loss": 0.0345, + "step": 26888 + }, + { + "epoch": 8.3, + "learning_rate": 1.317603828421157e-05, + "loss": 0.0343, + "step": 26889 + }, + { + "epoch": 8.3, + "learning_rate": 1.317556405638559e-05, + "loss": 0.0346, + "step": 26890 + }, + { + "epoch": 8.3, + "learning_rate": 1.3175089820616951e-05, + "loss": 0.0334, + "step": 26891 + }, + { + "epoch": 8.3, + "learning_rate": 1.3174615576906829e-05, + "loss": 0.034, + "step": 26892 + }, + { + "epoch": 8.31, + "learning_rate": 1.3174141325256415e-05, + "loss": 0.032, + "step": 26893 + }, + { + "epoch": 8.31, + "learning_rate": 1.3173667065666897e-05, + "loss": 0.0339, + "step": 26894 + }, + { + "epoch": 8.31, + "learning_rate": 1.3173192798139454e-05, + "loss": 0.0302, + "step": 26895 + }, + { + "epoch": 8.31, + "learning_rate": 1.3172718522675283e-05, + "loss": 0.0396, + "step": 26896 + }, + { + "epoch": 8.31, + "learning_rate": 1.3172244239275562e-05, + "loss": 0.0347, + "step": 26897 + }, + { + "epoch": 8.31, + "learning_rate": 1.3171769947941475e-05, + "loss": 0.0355, + "step": 26898 + }, + { + "epoch": 8.31, + "learning_rate": 1.3171295648674218e-05, + "loss": 0.0331, + "step": 26899 + }, + { + "epoch": 8.31, + "learning_rate": 1.3170821341474972e-05, + "loss": 0.0315, + "step": 26900 + }, + { + "epoch": 8.31, + "learning_rate": 1.3170347026344924e-05, + "loss": 0.0322, + "step": 26901 + }, + { + "epoch": 8.31, + "learning_rate": 1.3169872703285257e-05, + "loss": 0.0339, + "step": 26902 + }, + { + "epoch": 8.31, + "learning_rate": 1.316939837229716e-05, + "loss": 0.0313, + "step": 26903 + }, + { + "epoch": 8.31, + "learning_rate": 1.3168924033381822e-05, + "loss": 0.0368, + "step": 26904 + }, + { + "epoch": 8.31, + "learning_rate": 1.3168449686540426e-05, + "loss": 0.0338, + "step": 26905 + }, + { + "epoch": 8.31, + "learning_rate": 1.316797533177416e-05, + "loss": 0.0355, + "step": 26906 + }, + { + "epoch": 8.31, + "learning_rate": 1.316750096908421e-05, + "loss": 0.0331, + "step": 26907 + }, + { + "epoch": 8.31, + "learning_rate": 1.3167026598471761e-05, + "loss": 0.0321, + "step": 26908 + }, + { + "epoch": 8.31, + "learning_rate": 1.3166552219938002e-05, + "loss": 0.0349, + "step": 26909 + }, + { + "epoch": 8.31, + "learning_rate": 1.316607783348412e-05, + "loss": 0.034, + "step": 26910 + }, + { + "epoch": 8.31, + "learning_rate": 1.3165603439111297e-05, + "loss": 0.0352, + "step": 26911 + }, + { + "epoch": 8.31, + "learning_rate": 1.3165129036820724e-05, + "loss": 0.0348, + "step": 26912 + }, + { + "epoch": 8.31, + "learning_rate": 1.3164654626613582e-05, + "loss": 0.0341, + "step": 26913 + }, + { + "epoch": 8.31, + "learning_rate": 1.3164180208491067e-05, + "loss": 0.033, + "step": 26914 + }, + { + "epoch": 8.31, + "learning_rate": 1.3163705782454357e-05, + "loss": 0.0314, + "step": 26915 + }, + { + "epoch": 8.31, + "learning_rate": 1.3163231348504643e-05, + "loss": 0.0335, + "step": 26916 + }, + { + "epoch": 8.31, + "learning_rate": 1.3162756906643111e-05, + "loss": 0.0349, + "step": 26917 + }, + { + "epoch": 8.31, + "learning_rate": 1.3162282456870946e-05, + "loss": 0.0327, + "step": 26918 + }, + { + "epoch": 8.31, + "learning_rate": 1.3161807999189335e-05, + "loss": 0.033, + "step": 26919 + }, + { + "epoch": 8.31, + "learning_rate": 1.3161333533599468e-05, + "loss": 0.0289, + "step": 26920 + }, + { + "epoch": 8.31, + "learning_rate": 1.3160859060102528e-05, + "loss": 0.0344, + "step": 26921 + }, + { + "epoch": 8.31, + "learning_rate": 1.3160384578699706e-05, + "loss": 0.0337, + "step": 26922 + }, + { + "epoch": 8.31, + "learning_rate": 1.3159910089392181e-05, + "loss": 0.0332, + "step": 26923 + }, + { + "epoch": 8.31, + "learning_rate": 1.3159435592181144e-05, + "loss": 0.0337, + "step": 26924 + }, + { + "epoch": 8.32, + "learning_rate": 1.3158961087067788e-05, + "loss": 0.0342, + "step": 26925 + }, + { + "epoch": 8.32, + "learning_rate": 1.3158486574053288e-05, + "loss": 0.034, + "step": 26926 + }, + { + "epoch": 8.32, + "learning_rate": 1.3158012053138842e-05, + "loss": 0.0311, + "step": 26927 + }, + { + "epoch": 8.32, + "learning_rate": 1.3157537524325629e-05, + "loss": 0.0347, + "step": 26928 + }, + { + "epoch": 8.32, + "learning_rate": 1.3157062987614839e-05, + "loss": 0.0338, + "step": 26929 + }, + { + "epoch": 8.32, + "learning_rate": 1.3156588443007661e-05, + "loss": 0.0337, + "step": 26930 + }, + { + "epoch": 8.32, + "learning_rate": 1.3156113890505275e-05, + "loss": 0.0383, + "step": 26931 + }, + { + "epoch": 8.32, + "learning_rate": 1.3155639330108878e-05, + "loss": 0.0314, + "step": 26932 + }, + { + "epoch": 8.32, + "learning_rate": 1.3155164761819648e-05, + "loss": 0.036, + "step": 26933 + }, + { + "epoch": 8.32, + "learning_rate": 1.3154690185638774e-05, + "loss": 0.0353, + "step": 26934 + }, + { + "epoch": 8.32, + "learning_rate": 1.3154215601567449e-05, + "loss": 0.0328, + "step": 26935 + }, + { + "epoch": 8.32, + "learning_rate": 1.3153741009606852e-05, + "loss": 0.0377, + "step": 26936 + }, + { + "epoch": 8.32, + "learning_rate": 1.3153266409758177e-05, + "loss": 0.0307, + "step": 26937 + }, + { + "epoch": 8.32, + "learning_rate": 1.3152791802022605e-05, + "loss": 0.0379, + "step": 26938 + }, + { + "epoch": 8.32, + "learning_rate": 1.3152317186401324e-05, + "loss": 0.0332, + "step": 26939 + }, + { + "epoch": 8.32, + "learning_rate": 1.3151842562895525e-05, + "loss": 0.0335, + "step": 26940 + }, + { + "epoch": 8.32, + "learning_rate": 1.3151367931506393e-05, + "loss": 0.0304, + "step": 26941 + }, + { + "epoch": 8.32, + "learning_rate": 1.3150893292235114e-05, + "loss": 0.0328, + "step": 26942 + }, + { + "epoch": 8.32, + "learning_rate": 1.3150418645082877e-05, + "loss": 0.035, + "step": 26943 + }, + { + "epoch": 8.32, + "learning_rate": 1.314994399005087e-05, + "loss": 0.0314, + "step": 26944 + }, + { + "epoch": 8.32, + "learning_rate": 1.3149469327140276e-05, + "loss": 0.0341, + "step": 26945 + }, + { + "epoch": 8.32, + "learning_rate": 1.3148994656352283e-05, + "loss": 0.0326, + "step": 26946 + }, + { + "epoch": 8.32, + "learning_rate": 1.3148519977688084e-05, + "loss": 0.0304, + "step": 26947 + }, + { + "epoch": 8.32, + "learning_rate": 1.3148045291148861e-05, + "loss": 0.0331, + "step": 26948 + }, + { + "epoch": 8.32, + "learning_rate": 1.3147570596735801e-05, + "loss": 0.0331, + "step": 26949 + }, + { + "epoch": 8.32, + "learning_rate": 1.3147095894450097e-05, + "loss": 0.0339, + "step": 26950 + }, + { + "epoch": 8.32, + "learning_rate": 1.3146621184292927e-05, + "loss": 0.0374, + "step": 26951 + }, + { + "epoch": 8.32, + "learning_rate": 1.3146146466265486e-05, + "loss": 0.0324, + "step": 26952 + }, + { + "epoch": 8.32, + "learning_rate": 1.3145671740368962e-05, + "loss": 0.0345, + "step": 26953 + }, + { + "epoch": 8.32, + "learning_rate": 1.3145197006604534e-05, + "loss": 0.0339, + "step": 26954 + }, + { + "epoch": 8.32, + "learning_rate": 1.3144722264973397e-05, + "loss": 0.0365, + "step": 26955 + }, + { + "epoch": 8.32, + "learning_rate": 1.3144247515476736e-05, + "loss": 0.0323, + "step": 26956 + }, + { + "epoch": 8.32, + "learning_rate": 1.3143772758115736e-05, + "loss": 0.0382, + "step": 26957 + }, + { + "epoch": 8.33, + "learning_rate": 1.3143297992891592e-05, + "loss": 0.0327, + "step": 26958 + }, + { + "epoch": 8.33, + "learning_rate": 1.3142823219805482e-05, + "loss": 0.0336, + "step": 26959 + }, + { + "epoch": 8.33, + "learning_rate": 1.3142348438858601e-05, + "loss": 0.0314, + "step": 26960 + }, + { + "epoch": 8.33, + "learning_rate": 1.3141873650052133e-05, + "loss": 0.0311, + "step": 26961 + }, + { + "epoch": 8.33, + "learning_rate": 1.3141398853387264e-05, + "loss": 0.0333, + "step": 26962 + }, + { + "epoch": 8.33, + "learning_rate": 1.3140924048865182e-05, + "loss": 0.0337, + "step": 26963 + }, + { + "epoch": 8.33, + "learning_rate": 1.314044923648708e-05, + "loss": 0.0344, + "step": 26964 + }, + { + "epoch": 8.33, + "learning_rate": 1.313997441625414e-05, + "loss": 0.0369, + "step": 26965 + }, + { + "epoch": 8.33, + "learning_rate": 1.3139499588167553e-05, + "loss": 0.0343, + "step": 26966 + }, + { + "epoch": 8.33, + "learning_rate": 1.3139024752228501e-05, + "loss": 0.0382, + "step": 26967 + }, + { + "epoch": 8.33, + "learning_rate": 1.3138549908438178e-05, + "loss": 0.0342, + "step": 26968 + }, + { + "epoch": 8.33, + "learning_rate": 1.313807505679777e-05, + "loss": 0.0297, + "step": 26969 + }, + { + "epoch": 8.33, + "learning_rate": 1.3137600197308462e-05, + "loss": 0.0354, + "step": 26970 + }, + { + "epoch": 8.33, + "learning_rate": 1.3137125329971446e-05, + "loss": 0.0313, + "step": 26971 + }, + { + "epoch": 8.33, + "learning_rate": 1.3136650454787904e-05, + "loss": 0.0351, + "step": 26972 + }, + { + "epoch": 8.33, + "learning_rate": 1.3136175571759031e-05, + "loss": 0.0366, + "step": 26973 + }, + { + "epoch": 8.33, + "learning_rate": 1.313570068088601e-05, + "loss": 0.0326, + "step": 26974 + }, + { + "epoch": 8.33, + "learning_rate": 1.3135225782170026e-05, + "loss": 0.0307, + "step": 26975 + }, + { + "epoch": 8.33, + "learning_rate": 1.3134750875612276e-05, + "loss": 0.035, + "step": 26976 + }, + { + "epoch": 8.33, + "learning_rate": 1.3134275961213938e-05, + "loss": 0.0354, + "step": 26977 + }, + { + "epoch": 8.33, + "learning_rate": 1.3133801038976206e-05, + "loss": 0.0378, + "step": 26978 + }, + { + "epoch": 8.33, + "learning_rate": 1.3133326108900268e-05, + "loss": 0.0341, + "step": 26979 + }, + { + "epoch": 8.33, + "learning_rate": 1.3132851170987306e-05, + "loss": 0.0359, + "step": 26980 + }, + { + "epoch": 8.33, + "learning_rate": 1.3132376225238516e-05, + "loss": 0.0408, + "step": 26981 + }, + { + "epoch": 8.33, + "learning_rate": 1.3131901271655077e-05, + "loss": 0.0374, + "step": 26982 + }, + { + "epoch": 8.33, + "learning_rate": 1.3131426310238182e-05, + "loss": 0.0352, + "step": 26983 + }, + { + "epoch": 8.33, + "learning_rate": 1.3130951340989025e-05, + "loss": 0.0388, + "step": 26984 + }, + { + "epoch": 8.33, + "learning_rate": 1.313047636390878e-05, + "loss": 0.0342, + "step": 26985 + }, + { + "epoch": 8.33, + "learning_rate": 1.3130001378998649e-05, + "loss": 0.0375, + "step": 26986 + }, + { + "epoch": 8.33, + "learning_rate": 1.312952638625981e-05, + "loss": 0.0352, + "step": 26987 + }, + { + "epoch": 8.33, + "learning_rate": 1.3129051385693453e-05, + "loss": 0.0324, + "step": 26988 + }, + { + "epoch": 8.33, + "learning_rate": 1.3128576377300773e-05, + "loss": 0.0368, + "step": 26989 + }, + { + "epoch": 8.34, + "learning_rate": 1.312810136108295e-05, + "loss": 0.0367, + "step": 26990 + }, + { + "epoch": 8.34, + "learning_rate": 1.3127626337041175e-05, + "loss": 0.0346, + "step": 26991 + }, + { + "epoch": 8.34, + "learning_rate": 1.3127151305176634e-05, + "loss": 0.0377, + "step": 26992 + }, + { + "epoch": 8.34, + "learning_rate": 1.312667626549052e-05, + "loss": 0.0354, + "step": 26993 + }, + { + "epoch": 8.34, + "learning_rate": 1.3126201217984018e-05, + "loss": 0.0337, + "step": 26994 + }, + { + "epoch": 8.34, + "learning_rate": 1.3125726162658317e-05, + "loss": 0.0349, + "step": 26995 + }, + { + "epoch": 8.34, + "learning_rate": 1.3125251099514605e-05, + "loss": 0.0336, + "step": 26996 + }, + { + "epoch": 8.34, + "learning_rate": 1.3124776028554066e-05, + "loss": 0.0391, + "step": 26997 + }, + { + "epoch": 8.34, + "learning_rate": 1.3124300949777897e-05, + "loss": 0.031, + "step": 26998 + }, + { + "epoch": 8.34, + "learning_rate": 1.3123825863187278e-05, + "loss": 0.0285, + "step": 26999 + }, + { + "epoch": 8.34, + "learning_rate": 1.3123350768783404e-05, + "loss": 0.0326, + "step": 27000 + }, + { + "epoch": 8.34, + "learning_rate": 1.3122875666567458e-05, + "loss": 0.0341, + "step": 27001 + }, + { + "epoch": 8.34, + "learning_rate": 1.3122400556540631e-05, + "loss": 0.0333, + "step": 27002 + }, + { + "epoch": 8.34, + "learning_rate": 1.312192543870411e-05, + "loss": 0.0329, + "step": 27003 + }, + { + "epoch": 8.34, + "learning_rate": 1.3121450313059087e-05, + "loss": 0.0326, + "step": 27004 + }, + { + "epoch": 8.34, + "learning_rate": 1.3120975179606743e-05, + "loss": 0.0365, + "step": 27005 + }, + { + "epoch": 8.34, + "learning_rate": 1.3120500038348274e-05, + "loss": 0.0356, + "step": 27006 + }, + { + "epoch": 8.34, + "learning_rate": 1.3120024889284865e-05, + "loss": 0.0312, + "step": 27007 + }, + { + "epoch": 8.34, + "learning_rate": 1.3119549732417703e-05, + "loss": 0.0325, + "step": 27008 + }, + { + "epoch": 8.34, + "learning_rate": 1.311907456774798e-05, + "loss": 0.0352, + "step": 27009 + }, + { + "epoch": 8.34, + "learning_rate": 1.3118599395276884e-05, + "loss": 0.0339, + "step": 27010 + }, + { + "epoch": 8.34, + "learning_rate": 1.3118124215005596e-05, + "loss": 0.0311, + "step": 27011 + }, + { + "epoch": 8.34, + "learning_rate": 1.3117649026935318e-05, + "loss": 0.0321, + "step": 27012 + }, + { + "epoch": 8.34, + "learning_rate": 1.3117173831067225e-05, + "loss": 0.0344, + "step": 27013 + }, + { + "epoch": 8.34, + "learning_rate": 1.3116698627402515e-05, + "loss": 0.0309, + "step": 27014 + }, + { + "epoch": 8.34, + "learning_rate": 1.3116223415942372e-05, + "loss": 0.0336, + "step": 27015 + }, + { + "epoch": 8.34, + "learning_rate": 1.3115748196687986e-05, + "loss": 0.0377, + "step": 27016 + }, + { + "epoch": 8.34, + "learning_rate": 1.3115272969640546e-05, + "loss": 0.0357, + "step": 27017 + }, + { + "epoch": 8.34, + "learning_rate": 1.3114797734801241e-05, + "loss": 0.035, + "step": 27018 + }, + { + "epoch": 8.34, + "learning_rate": 1.3114322492171258e-05, + "loss": 0.0322, + "step": 27019 + }, + { + "epoch": 8.34, + "learning_rate": 1.3113847241751787e-05, + "loss": 0.033, + "step": 27020 + }, + { + "epoch": 8.34, + "learning_rate": 1.3113371983544014e-05, + "loss": 0.0357, + "step": 27021 + }, + { + "epoch": 8.34, + "learning_rate": 1.3112896717549133e-05, + "loss": 0.0313, + "step": 27022 + }, + { + "epoch": 8.35, + "learning_rate": 1.311242144376833e-05, + "loss": 0.0366, + "step": 27023 + }, + { + "epoch": 8.35, + "learning_rate": 1.3111946162202789e-05, + "loss": 0.0333, + "step": 27024 + }, + { + "epoch": 8.35, + "learning_rate": 1.3111470872853704e-05, + "loss": 0.0345, + "step": 27025 + }, + { + "epoch": 8.35, + "learning_rate": 1.3110995575722265e-05, + "loss": 0.0327, + "step": 27026 + }, + { + "epoch": 8.35, + "learning_rate": 1.3110520270809656e-05, + "loss": 0.0336, + "step": 27027 + }, + { + "epoch": 8.35, + "learning_rate": 1.3110044958117071e-05, + "loss": 0.0284, + "step": 27028 + }, + { + "epoch": 8.35, + "learning_rate": 1.3109569637645695e-05, + "loss": 0.0324, + "step": 27029 + }, + { + "epoch": 8.35, + "learning_rate": 1.3109094309396719e-05, + "loss": 0.0344, + "step": 27030 + }, + { + "epoch": 8.35, + "learning_rate": 1.3108618973371333e-05, + "loss": 0.0367, + "step": 27031 + }, + { + "epoch": 8.35, + "learning_rate": 1.310814362957072e-05, + "loss": 0.0329, + "step": 27032 + }, + { + "epoch": 8.35, + "learning_rate": 1.3107668277996073e-05, + "loss": 0.0338, + "step": 27033 + }, + { + "epoch": 8.35, + "learning_rate": 1.3107192918648584e-05, + "loss": 0.0324, + "step": 27034 + }, + { + "epoch": 8.35, + "learning_rate": 1.310671755152944e-05, + "loss": 0.0366, + "step": 27035 + }, + { + "epoch": 8.35, + "learning_rate": 1.3106242176639822e-05, + "loss": 0.0347, + "step": 27036 + }, + { + "epoch": 8.35, + "learning_rate": 1.310576679398093e-05, + "loss": 0.037, + "step": 27037 + }, + { + "epoch": 8.35, + "learning_rate": 1.310529140355395e-05, + "loss": 0.0343, + "step": 27038 + }, + { + "epoch": 8.35, + "learning_rate": 1.3104816005360066e-05, + "loss": 0.0345, + "step": 27039 + }, + { + "epoch": 8.35, + "learning_rate": 1.3104340599400475e-05, + "loss": 0.0343, + "step": 27040 + }, + { + "epoch": 8.35, + "learning_rate": 1.310386518567636e-05, + "loss": 0.0349, + "step": 27041 + }, + { + "epoch": 8.35, + "learning_rate": 1.3103389764188912e-05, + "loss": 0.0343, + "step": 27042 + }, + { + "epoch": 8.35, + "learning_rate": 1.3102914334939322e-05, + "loss": 0.0349, + "step": 27043 + }, + { + "epoch": 8.35, + "learning_rate": 1.3102438897928776e-05, + "loss": 0.0347, + "step": 27044 + }, + { + "epoch": 8.35, + "learning_rate": 1.3101963453158464e-05, + "loss": 0.0321, + "step": 27045 + }, + { + "epoch": 8.35, + "learning_rate": 1.3101488000629576e-05, + "loss": 0.0342, + "step": 27046 + }, + { + "epoch": 8.35, + "learning_rate": 1.3101012540343298e-05, + "loss": 0.0319, + "step": 27047 + }, + { + "epoch": 8.35, + "learning_rate": 1.3100537072300827e-05, + "loss": 0.0333, + "step": 27048 + }, + { + "epoch": 8.35, + "learning_rate": 1.3100061596503346e-05, + "loss": 0.0328, + "step": 27049 + }, + { + "epoch": 8.35, + "learning_rate": 1.3099586112952043e-05, + "loss": 0.0328, + "step": 27050 + }, + { + "epoch": 8.35, + "learning_rate": 1.3099110621648112e-05, + "loss": 0.0379, + "step": 27051 + }, + { + "epoch": 8.35, + "learning_rate": 1.309863512259274e-05, + "loss": 0.0383, + "step": 27052 + }, + { + "epoch": 8.35, + "learning_rate": 1.3098159615787115e-05, + "loss": 0.0353, + "step": 27053 + }, + { + "epoch": 8.35, + "learning_rate": 1.3097684101232429e-05, + "loss": 0.0322, + "step": 27054 + }, + { + "epoch": 8.36, + "learning_rate": 1.309720857892987e-05, + "loss": 0.0365, + "step": 27055 + }, + { + "epoch": 8.36, + "learning_rate": 1.3096733048880628e-05, + "loss": 0.0342, + "step": 27056 + }, + { + "epoch": 8.36, + "learning_rate": 1.309625751108589e-05, + "loss": 0.0352, + "step": 27057 + }, + { + "epoch": 8.36, + "learning_rate": 1.309578196554685e-05, + "loss": 0.0331, + "step": 27058 + }, + { + "epoch": 8.36, + "learning_rate": 1.309530641226469e-05, + "loss": 0.0333, + "step": 27059 + }, + { + "epoch": 8.36, + "learning_rate": 1.3094830851240608e-05, + "loss": 0.0316, + "step": 27060 + }, + { + "epoch": 8.36, + "learning_rate": 1.309435528247579e-05, + "loss": 0.0346, + "step": 27061 + }, + { + "epoch": 8.36, + "learning_rate": 1.3093879705971422e-05, + "loss": 0.0301, + "step": 27062 + }, + { + "epoch": 8.36, + "learning_rate": 1.3093404121728699e-05, + "loss": 0.0346, + "step": 27063 + }, + { + "epoch": 8.36, + "learning_rate": 1.3092928529748808e-05, + "loss": 0.0346, + "step": 27064 + }, + { + "epoch": 8.36, + "learning_rate": 1.3092452930032936e-05, + "loss": 0.0376, + "step": 27065 + }, + { + "epoch": 8.36, + "learning_rate": 1.3091977322582279e-05, + "loss": 0.0323, + "step": 27066 + }, + { + "epoch": 8.36, + "learning_rate": 1.309150170739802e-05, + "loss": 0.0331, + "step": 27067 + }, + { + "epoch": 8.36, + "learning_rate": 1.3091026084481353e-05, + "loss": 0.0355, + "step": 27068 + }, + { + "epoch": 8.36, + "learning_rate": 1.3090550453833466e-05, + "loss": 0.0361, + "step": 27069 + }, + { + "epoch": 8.36, + "learning_rate": 1.3090074815455545e-05, + "loss": 0.0322, + "step": 27070 + }, + { + "epoch": 8.36, + "learning_rate": 1.308959916934879e-05, + "loss": 0.0348, + "step": 27071 + }, + { + "epoch": 8.36, + "learning_rate": 1.308912351551438e-05, + "loss": 0.036, + "step": 27072 + }, + { + "epoch": 8.36, + "learning_rate": 1.3088647853953509e-05, + "loss": 0.0313, + "step": 27073 + }, + { + "epoch": 8.36, + "learning_rate": 1.3088172184667365e-05, + "loss": 0.041, + "step": 27074 + }, + { + "epoch": 8.36, + "learning_rate": 1.308769650765714e-05, + "loss": 0.0333, + "step": 27075 + }, + { + "epoch": 8.36, + "learning_rate": 1.3087220822924023e-05, + "loss": 0.0331, + "step": 27076 + }, + { + "epoch": 8.36, + "learning_rate": 1.3086745130469206e-05, + "loss": 0.038, + "step": 27077 + }, + { + "epoch": 8.36, + "learning_rate": 1.308626943029387e-05, + "loss": 0.0368, + "step": 27078 + }, + { + "epoch": 8.36, + "learning_rate": 1.3085793722399219e-05, + "loss": 0.032, + "step": 27079 + }, + { + "epoch": 8.36, + "learning_rate": 1.3085318006786429e-05, + "loss": 0.0335, + "step": 27080 + }, + { + "epoch": 8.36, + "learning_rate": 1.30848422834567e-05, + "loss": 0.0345, + "step": 27081 + }, + { + "epoch": 8.36, + "learning_rate": 1.3084366552411217e-05, + "loss": 0.0395, + "step": 27082 + }, + { + "epoch": 8.36, + "learning_rate": 1.308389081365117e-05, + "loss": 0.0376, + "step": 27083 + }, + { + "epoch": 8.36, + "learning_rate": 1.308341506717775e-05, + "loss": 0.0332, + "step": 27084 + }, + { + "epoch": 8.36, + "learning_rate": 1.3082939312992145e-05, + "loss": 0.0371, + "step": 27085 + }, + { + "epoch": 8.36, + "learning_rate": 1.3082463551095547e-05, + "loss": 0.0347, + "step": 27086 + }, + { + "epoch": 8.37, + "learning_rate": 1.3081987781489147e-05, + "loss": 0.0361, + "step": 27087 + }, + { + "epoch": 8.37, + "learning_rate": 1.3081512004174132e-05, + "loss": 0.0337, + "step": 27088 + }, + { + "epoch": 8.37, + "learning_rate": 1.3081036219151697e-05, + "loss": 0.0383, + "step": 27089 + }, + { + "epoch": 8.37, + "learning_rate": 1.3080560426423023e-05, + "loss": 0.0391, + "step": 27090 + }, + { + "epoch": 8.37, + "learning_rate": 1.3080084625989308e-05, + "loss": 0.0341, + "step": 27091 + }, + { + "epoch": 8.37, + "learning_rate": 1.3079608817851742e-05, + "loss": 0.0322, + "step": 27092 + }, + { + "epoch": 8.37, + "learning_rate": 1.3079133002011509e-05, + "loss": 0.0367, + "step": 27093 + }, + { + "epoch": 8.37, + "learning_rate": 1.3078657178469804e-05, + "loss": 0.0332, + "step": 27094 + }, + { + "epoch": 8.37, + "learning_rate": 1.3078181347227814e-05, + "loss": 0.0315, + "step": 27095 + }, + { + "epoch": 8.37, + "learning_rate": 1.3077705508286734e-05, + "loss": 0.0329, + "step": 27096 + }, + { + "epoch": 8.37, + "learning_rate": 1.3077229661647752e-05, + "loss": 0.0289, + "step": 27097 + }, + { + "epoch": 8.37, + "learning_rate": 1.3076753807312052e-05, + "loss": 0.0387, + "step": 27098 + }, + { + "epoch": 8.37, + "learning_rate": 1.3076277945280835e-05, + "loss": 0.0318, + "step": 27099 + }, + { + "epoch": 8.37, + "learning_rate": 1.3075802075555286e-05, + "loss": 0.0329, + "step": 27100 + }, + { + "epoch": 8.37, + "learning_rate": 1.3075326198136588e-05, + "loss": 0.0309, + "step": 27101 + }, + { + "epoch": 8.37, + "learning_rate": 1.3074850313025946e-05, + "loss": 0.0384, + "step": 27102 + }, + { + "epoch": 8.37, + "learning_rate": 1.307437442022454e-05, + "loss": 0.0376, + "step": 27103 + }, + { + "epoch": 8.37, + "learning_rate": 1.3073898519733563e-05, + "loss": 0.0344, + "step": 27104 + }, + { + "epoch": 8.37, + "learning_rate": 1.3073422611554204e-05, + "loss": 0.0351, + "step": 27105 + }, + { + "epoch": 8.37, + "learning_rate": 1.3072946695687656e-05, + "loss": 0.0376, + "step": 27106 + }, + { + "epoch": 8.37, + "learning_rate": 1.3072470772135106e-05, + "loss": 0.0365, + "step": 27107 + }, + { + "epoch": 8.37, + "learning_rate": 1.3071994840897748e-05, + "loss": 0.0347, + "step": 27108 + }, + { + "epoch": 8.37, + "learning_rate": 1.307151890197677e-05, + "loss": 0.0333, + "step": 27109 + }, + { + "epoch": 8.37, + "learning_rate": 1.3071042955373363e-05, + "loss": 0.0324, + "step": 27110 + }, + { + "epoch": 8.37, + "learning_rate": 1.3070567001088716e-05, + "loss": 0.0339, + "step": 27111 + }, + { + "epoch": 8.37, + "learning_rate": 1.3070091039124022e-05, + "loss": 0.0335, + "step": 27112 + }, + { + "epoch": 8.37, + "learning_rate": 1.3069615069480473e-05, + "loss": 0.0345, + "step": 27113 + }, + { + "epoch": 8.37, + "learning_rate": 1.3069139092159253e-05, + "loss": 0.033, + "step": 27114 + }, + { + "epoch": 8.37, + "learning_rate": 1.3068663107161558e-05, + "loss": 0.033, + "step": 27115 + }, + { + "epoch": 8.37, + "learning_rate": 1.3068187114488576e-05, + "loss": 0.0363, + "step": 27116 + }, + { + "epoch": 8.37, + "learning_rate": 1.30677111141415e-05, + "loss": 0.0312, + "step": 27117 + }, + { + "epoch": 8.37, + "learning_rate": 1.3067235106121517e-05, + "loss": 0.0337, + "step": 27118 + }, + { + "epoch": 8.37, + "learning_rate": 1.3066759090429821e-05, + "loss": 0.0352, + "step": 27119 + }, + { + "epoch": 8.38, + "learning_rate": 1.3066283067067602e-05, + "loss": 0.0352, + "step": 27120 + }, + { + "epoch": 8.38, + "learning_rate": 1.3065807036036046e-05, + "loss": 0.0344, + "step": 27121 + }, + { + "epoch": 8.38, + "learning_rate": 1.3065330997336352e-05, + "loss": 0.0331, + "step": 27122 + }, + { + "epoch": 8.38, + "learning_rate": 1.3064854950969706e-05, + "loss": 0.0349, + "step": 27123 + }, + { + "epoch": 8.38, + "learning_rate": 1.3064378896937294e-05, + "loss": 0.0346, + "step": 27124 + }, + { + "epoch": 8.38, + "learning_rate": 1.3063902835240317e-05, + "loss": 0.037, + "step": 27125 + }, + { + "epoch": 8.38, + "learning_rate": 1.3063426765879958e-05, + "loss": 0.0361, + "step": 27126 + }, + { + "epoch": 8.38, + "learning_rate": 1.3062950688857408e-05, + "loss": 0.0355, + "step": 27127 + }, + { + "epoch": 8.38, + "learning_rate": 1.306247460417386e-05, + "loss": 0.0311, + "step": 27128 + }, + { + "epoch": 8.38, + "learning_rate": 1.3061998511830505e-05, + "loss": 0.0375, + "step": 27129 + }, + { + "epoch": 8.38, + "learning_rate": 1.3061522411828536e-05, + "loss": 0.035, + "step": 27130 + }, + { + "epoch": 8.38, + "learning_rate": 1.3061046304169138e-05, + "loss": 0.0379, + "step": 27131 + }, + { + "epoch": 8.38, + "learning_rate": 1.3060570188853505e-05, + "loss": 0.0362, + "step": 27132 + }, + { + "epoch": 8.38, + "learning_rate": 1.3060094065882832e-05, + "loss": 0.0355, + "step": 27133 + }, + { + "epoch": 8.38, + "learning_rate": 1.3059617935258299e-05, + "loss": 0.0348, + "step": 27134 + }, + { + "epoch": 8.38, + "learning_rate": 1.3059141796981107e-05, + "loss": 0.0354, + "step": 27135 + }, + { + "epoch": 8.38, + "learning_rate": 1.3058665651052444e-05, + "loss": 0.0381, + "step": 27136 + }, + { + "epoch": 8.38, + "learning_rate": 1.3058189497473498e-05, + "loss": 0.0356, + "step": 27137 + }, + { + "epoch": 8.38, + "learning_rate": 1.3057713336245466e-05, + "loss": 0.0355, + "step": 27138 + }, + { + "epoch": 8.38, + "learning_rate": 1.3057237167369532e-05, + "loss": 0.0405, + "step": 27139 + }, + { + "epoch": 8.38, + "learning_rate": 1.3056760990846891e-05, + "loss": 0.0353, + "step": 27140 + }, + { + "epoch": 8.38, + "learning_rate": 1.3056284806678734e-05, + "loss": 0.0326, + "step": 27141 + }, + { + "epoch": 8.38, + "learning_rate": 1.305580861486625e-05, + "loss": 0.0333, + "step": 27142 + }, + { + "epoch": 8.38, + "learning_rate": 1.3055332415410634e-05, + "loss": 0.0357, + "step": 27143 + }, + { + "epoch": 8.38, + "learning_rate": 1.3054856208313072e-05, + "loss": 0.0385, + "step": 27144 + }, + { + "epoch": 8.38, + "learning_rate": 1.3054379993574757e-05, + "loss": 0.0335, + "step": 27145 + }, + { + "epoch": 8.38, + "learning_rate": 1.305390377119688e-05, + "loss": 0.0304, + "step": 27146 + }, + { + "epoch": 8.38, + "learning_rate": 1.3053427541180634e-05, + "loss": 0.0304, + "step": 27147 + }, + { + "epoch": 8.38, + "learning_rate": 1.3052951303527212e-05, + "loss": 0.0345, + "step": 27148 + }, + { + "epoch": 8.38, + "learning_rate": 1.3052475058237797e-05, + "loss": 0.0353, + "step": 27149 + }, + { + "epoch": 8.38, + "learning_rate": 1.3051998805313586e-05, + "loss": 0.0284, + "step": 27150 + }, + { + "epoch": 8.38, + "learning_rate": 1.3051522544755773e-05, + "loss": 0.0322, + "step": 27151 + }, + { + "epoch": 8.39, + "learning_rate": 1.3051046276565539e-05, + "loss": 0.0346, + "step": 27152 + }, + { + "epoch": 8.39, + "learning_rate": 1.305057000074409e-05, + "loss": 0.0317, + "step": 27153 + }, + { + "epoch": 8.39, + "learning_rate": 1.3050093717292604e-05, + "loss": 0.0337, + "step": 27154 + }, + { + "epoch": 8.39, + "learning_rate": 1.3049617426212276e-05, + "loss": 0.0352, + "step": 27155 + }, + { + "epoch": 8.39, + "learning_rate": 1.3049141127504304e-05, + "loss": 0.0371, + "step": 27156 + }, + { + "epoch": 8.39, + "learning_rate": 1.304866482116987e-05, + "loss": 0.0364, + "step": 27157 + }, + { + "epoch": 8.39, + "learning_rate": 1.3048188507210168e-05, + "loss": 0.0329, + "step": 27158 + }, + { + "epoch": 8.39, + "learning_rate": 1.3047712185626393e-05, + "loss": 0.037, + "step": 27159 + }, + { + "epoch": 8.39, + "learning_rate": 1.3047235856419731e-05, + "loss": 0.0329, + "step": 27160 + }, + { + "epoch": 8.39, + "learning_rate": 1.304675951959138e-05, + "loss": 0.0327, + "step": 27161 + }, + { + "epoch": 8.39, + "learning_rate": 1.3046283175142526e-05, + "loss": 0.035, + "step": 27162 + }, + { + "epoch": 8.39, + "learning_rate": 1.3045806823074366e-05, + "loss": 0.0388, + "step": 27163 + }, + { + "epoch": 8.39, + "learning_rate": 1.3045330463388082e-05, + "loss": 0.0414, + "step": 27164 + }, + { + "epoch": 8.39, + "learning_rate": 1.3044854096084873e-05, + "loss": 0.0366, + "step": 27165 + }, + { + "epoch": 8.39, + "learning_rate": 1.3044377721165929e-05, + "loss": 0.0334, + "step": 27166 + }, + { + "epoch": 8.39, + "learning_rate": 1.304390133863244e-05, + "loss": 0.0352, + "step": 27167 + }, + { + "epoch": 8.39, + "learning_rate": 1.3043424948485602e-05, + "loss": 0.0394, + "step": 27168 + }, + { + "epoch": 8.39, + "learning_rate": 1.30429485507266e-05, + "loss": 0.031, + "step": 27169 + }, + { + "epoch": 8.39, + "learning_rate": 1.3042472145356628e-05, + "loss": 0.0344, + "step": 27170 + }, + { + "epoch": 8.39, + "learning_rate": 1.304199573237688e-05, + "loss": 0.0326, + "step": 27171 + }, + { + "epoch": 8.39, + "learning_rate": 1.3041519311788544e-05, + "loss": 0.0356, + "step": 27172 + }, + { + "epoch": 8.39, + "learning_rate": 1.3041042883592816e-05, + "loss": 0.0345, + "step": 27173 + }, + { + "epoch": 8.39, + "learning_rate": 1.3040566447790885e-05, + "loss": 0.037, + "step": 27174 + }, + { + "epoch": 8.39, + "learning_rate": 1.3040090004383941e-05, + "loss": 0.0364, + "step": 27175 + }, + { + "epoch": 8.39, + "learning_rate": 1.3039613553373176e-05, + "loss": 0.0354, + "step": 27176 + }, + { + "epoch": 8.39, + "learning_rate": 1.3039137094759786e-05, + "loss": 0.0375, + "step": 27177 + }, + { + "epoch": 8.39, + "learning_rate": 1.3038660628544959e-05, + "loss": 0.0347, + "step": 27178 + }, + { + "epoch": 8.39, + "learning_rate": 1.303818415472989e-05, + "loss": 0.0373, + "step": 27179 + }, + { + "epoch": 8.39, + "learning_rate": 1.3037707673315763e-05, + "loss": 0.0373, + "step": 27180 + }, + { + "epoch": 8.39, + "learning_rate": 1.3037231184303777e-05, + "loss": 0.0375, + "step": 27181 + }, + { + "epoch": 8.39, + "learning_rate": 1.3036754687695128e-05, + "loss": 0.0332, + "step": 27182 + }, + { + "epoch": 8.39, + "learning_rate": 1.3036278183490993e-05, + "loss": 0.0354, + "step": 27183 + }, + { + "epoch": 8.39, + "learning_rate": 1.3035801671692578e-05, + "loss": 0.0385, + "step": 27184 + }, + { + "epoch": 8.4, + "learning_rate": 1.3035325152301068e-05, + "loss": 0.0338, + "step": 27185 + }, + { + "epoch": 8.4, + "learning_rate": 1.3034848625317652e-05, + "loss": 0.0335, + "step": 27186 + }, + { + "epoch": 8.4, + "learning_rate": 1.3034372090743533e-05, + "loss": 0.0334, + "step": 27187 + }, + { + "epoch": 8.4, + "learning_rate": 1.303389554857989e-05, + "loss": 0.0339, + "step": 27188 + }, + { + "epoch": 8.4, + "learning_rate": 1.3033418998827925e-05, + "loss": 0.0322, + "step": 27189 + }, + { + "epoch": 8.4, + "learning_rate": 1.3032942441488822e-05, + "loss": 0.0343, + "step": 27190 + }, + { + "epoch": 8.4, + "learning_rate": 1.303246587656378e-05, + "loss": 0.0325, + "step": 27191 + }, + { + "epoch": 8.4, + "learning_rate": 1.3031989304053987e-05, + "loss": 0.0369, + "step": 27192 + }, + { + "epoch": 8.4, + "learning_rate": 1.3031512723960635e-05, + "loss": 0.0351, + "step": 27193 + }, + { + "epoch": 8.4, + "learning_rate": 1.3031036136284917e-05, + "loss": 0.0333, + "step": 27194 + }, + { + "epoch": 8.4, + "learning_rate": 1.3030559541028027e-05, + "loss": 0.0396, + "step": 27195 + }, + { + "epoch": 8.4, + "learning_rate": 1.3030082938191151e-05, + "loss": 0.037, + "step": 27196 + }, + { + "epoch": 8.4, + "learning_rate": 1.3029606327775489e-05, + "loss": 0.0318, + "step": 27197 + }, + { + "epoch": 8.4, + "learning_rate": 1.3029129709782225e-05, + "loss": 0.0336, + "step": 27198 + }, + { + "epoch": 8.4, + "learning_rate": 1.3028653084212557e-05, + "loss": 0.0338, + "step": 27199 + }, + { + "epoch": 8.4, + "learning_rate": 1.3028176451067675e-05, + "loss": 0.0361, + "step": 27200 + }, + { + "epoch": 8.4, + "learning_rate": 1.302769981034877e-05, + "loss": 0.0455, + "step": 27201 + }, + { + "epoch": 8.4, + "learning_rate": 1.3027223162057041e-05, + "loss": 0.0368, + "step": 27202 + }, + { + "epoch": 8.4, + "learning_rate": 1.3026746506193668e-05, + "loss": 0.0401, + "step": 27203 + }, + { + "epoch": 8.4, + "learning_rate": 1.3026269842759854e-05, + "loss": 0.0337, + "step": 27204 + }, + { + "epoch": 8.4, + "learning_rate": 1.3025793171756788e-05, + "loss": 0.0349, + "step": 27205 + }, + { + "epoch": 8.4, + "learning_rate": 1.3025316493185658e-05, + "loss": 0.038, + "step": 27206 + }, + { + "epoch": 8.4, + "learning_rate": 1.3024839807047662e-05, + "loss": 0.0314, + "step": 27207 + }, + { + "epoch": 8.4, + "learning_rate": 1.302436311334399e-05, + "loss": 0.04, + "step": 27208 + }, + { + "epoch": 8.4, + "learning_rate": 1.302388641207583e-05, + "loss": 0.0321, + "step": 27209 + }, + { + "epoch": 8.4, + "learning_rate": 1.3023409703244382e-05, + "loss": 0.0373, + "step": 27210 + }, + { + "epoch": 8.4, + "learning_rate": 1.3022932986850834e-05, + "loss": 0.0317, + "step": 27211 + }, + { + "epoch": 8.4, + "learning_rate": 1.3022456262896381e-05, + "loss": 0.0345, + "step": 27212 + }, + { + "epoch": 8.4, + "learning_rate": 1.3021979531382214e-05, + "loss": 0.0314, + "step": 27213 + }, + { + "epoch": 8.4, + "learning_rate": 1.302150279230952e-05, + "loss": 0.0347, + "step": 27214 + }, + { + "epoch": 8.4, + "learning_rate": 1.3021026045679503e-05, + "loss": 0.0378, + "step": 27215 + }, + { + "epoch": 8.4, + "learning_rate": 1.3020549291493345e-05, + "loss": 0.0341, + "step": 27216 + }, + { + "epoch": 8.41, + "learning_rate": 1.3020072529752243e-05, + "loss": 0.0323, + "step": 27217 + }, + { + "epoch": 8.41, + "learning_rate": 1.301959576045739e-05, + "loss": 0.0319, + "step": 27218 + }, + { + "epoch": 8.41, + "learning_rate": 1.3019118983609978e-05, + "loss": 0.0343, + "step": 27219 + }, + { + "epoch": 8.41, + "learning_rate": 1.3018642199211196e-05, + "loss": 0.0344, + "step": 27220 + }, + { + "epoch": 8.41, + "learning_rate": 1.301816540726224e-05, + "loss": 0.0378, + "step": 27221 + }, + { + "epoch": 8.41, + "learning_rate": 1.3017688607764303e-05, + "loss": 0.0343, + "step": 27222 + }, + { + "epoch": 8.41, + "learning_rate": 1.3017211800718575e-05, + "loss": 0.0356, + "step": 27223 + }, + { + "epoch": 8.41, + "learning_rate": 1.301673498612625e-05, + "loss": 0.0386, + "step": 27224 + }, + { + "epoch": 8.41, + "learning_rate": 1.301625816398852e-05, + "loss": 0.0394, + "step": 27225 + }, + { + "epoch": 8.41, + "learning_rate": 1.3015781334306579e-05, + "loss": 0.0364, + "step": 27226 + }, + { + "epoch": 8.41, + "learning_rate": 1.301530449708162e-05, + "loss": 0.0324, + "step": 27227 + }, + { + "epoch": 8.41, + "learning_rate": 1.3014827652314831e-05, + "loss": 0.0372, + "step": 27228 + }, + { + "epoch": 8.41, + "learning_rate": 1.3014350800007413e-05, + "loss": 0.0323, + "step": 27229 + }, + { + "epoch": 8.41, + "learning_rate": 1.301387394016055e-05, + "loss": 0.0364, + "step": 27230 + }, + { + "epoch": 8.41, + "learning_rate": 1.3013397072775443e-05, + "loss": 0.0364, + "step": 27231 + }, + { + "epoch": 8.41, + "learning_rate": 1.3012920197853276e-05, + "loss": 0.0329, + "step": 27232 + }, + { + "epoch": 8.41, + "learning_rate": 1.3012443315395249e-05, + "loss": 0.0339, + "step": 27233 + }, + { + "epoch": 8.41, + "learning_rate": 1.3011966425402549e-05, + "loss": 0.037, + "step": 27234 + }, + { + "epoch": 8.41, + "learning_rate": 1.3011489527876373e-05, + "loss": 0.0371, + "step": 27235 + }, + { + "epoch": 8.41, + "learning_rate": 1.3011012622817916e-05, + "loss": 0.0377, + "step": 27236 + }, + { + "epoch": 8.41, + "learning_rate": 1.301053571022836e-05, + "loss": 0.0311, + "step": 27237 + }, + { + "epoch": 8.41, + "learning_rate": 1.3010058790108912e-05, + "loss": 0.0357, + "step": 27238 + }, + { + "epoch": 8.41, + "learning_rate": 1.3009581862460754e-05, + "loss": 0.0391, + "step": 27239 + }, + { + "epoch": 8.41, + "learning_rate": 1.3009104927285082e-05, + "loss": 0.0346, + "step": 27240 + }, + { + "epoch": 8.41, + "learning_rate": 1.3008627984583093e-05, + "loss": 0.0384, + "step": 27241 + }, + { + "epoch": 8.41, + "learning_rate": 1.3008151034355974e-05, + "loss": 0.0332, + "step": 27242 + }, + { + "epoch": 8.41, + "learning_rate": 1.300767407660492e-05, + "loss": 0.0379, + "step": 27243 + }, + { + "epoch": 8.41, + "learning_rate": 1.3007197111331129e-05, + "loss": 0.0326, + "step": 27244 + }, + { + "epoch": 8.41, + "learning_rate": 1.3006720138535784e-05, + "loss": 0.0368, + "step": 27245 + }, + { + "epoch": 8.41, + "learning_rate": 1.3006243158220088e-05, + "loss": 0.0324, + "step": 27246 + }, + { + "epoch": 8.41, + "learning_rate": 1.300576617038523e-05, + "loss": 0.0326, + "step": 27247 + }, + { + "epoch": 8.41, + "learning_rate": 1.30052891750324e-05, + "loss": 0.0289, + "step": 27248 + }, + { + "epoch": 8.42, + "learning_rate": 1.3004812172162793e-05, + "loss": 0.0341, + "step": 27249 + }, + { + "epoch": 8.42, + "learning_rate": 1.3004335161777603e-05, + "loss": 0.039, + "step": 27250 + }, + { + "epoch": 8.42, + "learning_rate": 1.3003858143878025e-05, + "loss": 0.0324, + "step": 27251 + }, + { + "epoch": 8.42, + "learning_rate": 1.3003381118465248e-05, + "loss": 0.0339, + "step": 27252 + }, + { + "epoch": 8.42, + "learning_rate": 1.3002904085540468e-05, + "loss": 0.0358, + "step": 27253 + }, + { + "epoch": 8.42, + "learning_rate": 1.3002427045104877e-05, + "loss": 0.0328, + "step": 27254 + }, + { + "epoch": 8.42, + "learning_rate": 1.3001949997159668e-05, + "loss": 0.0349, + "step": 27255 + }, + { + "epoch": 8.42, + "learning_rate": 1.3001472941706037e-05, + "loss": 0.0346, + "step": 27256 + }, + { + "epoch": 8.42, + "learning_rate": 1.300099587874517e-05, + "loss": 0.0327, + "step": 27257 + }, + { + "epoch": 8.42, + "learning_rate": 1.3000518808278265e-05, + "loss": 0.035, + "step": 27258 + }, + { + "epoch": 8.42, + "learning_rate": 1.3000041730306521e-05, + "loss": 0.0381, + "step": 27259 + }, + { + "epoch": 8.42, + "learning_rate": 1.2999564644831119e-05, + "loss": 0.0324, + "step": 27260 + }, + { + "epoch": 8.42, + "learning_rate": 1.2999087551853266e-05, + "loss": 0.0369, + "step": 27261 + }, + { + "epoch": 8.42, + "learning_rate": 1.299861045137414e-05, + "loss": 0.0381, + "step": 27262 + }, + { + "epoch": 8.42, + "learning_rate": 1.2998133343394948e-05, + "loss": 0.0356, + "step": 27263 + }, + { + "epoch": 8.42, + "learning_rate": 1.2997656227916877e-05, + "loss": 0.0356, + "step": 27264 + }, + { + "epoch": 8.42, + "learning_rate": 1.2997179104941118e-05, + "loss": 0.039, + "step": 27265 + }, + { + "epoch": 8.42, + "learning_rate": 1.2996701974468871e-05, + "loss": 0.0351, + "step": 27266 + }, + { + "epoch": 8.42, + "learning_rate": 1.2996224836501322e-05, + "loss": 0.034, + "step": 27267 + }, + { + "epoch": 8.42, + "learning_rate": 1.299574769103967e-05, + "loss": 0.0343, + "step": 27268 + }, + { + "epoch": 8.42, + "learning_rate": 1.299527053808511e-05, + "loss": 0.0373, + "step": 27269 + }, + { + "epoch": 8.42, + "learning_rate": 1.2994793377638829e-05, + "loss": 0.0364, + "step": 27270 + }, + { + "epoch": 8.42, + "learning_rate": 1.2994316209702023e-05, + "loss": 0.0385, + "step": 27271 + }, + { + "epoch": 8.42, + "learning_rate": 1.2993839034275885e-05, + "loss": 0.0367, + "step": 27272 + }, + { + "epoch": 8.42, + "learning_rate": 1.2993361851361613e-05, + "loss": 0.0374, + "step": 27273 + }, + { + "epoch": 8.42, + "learning_rate": 1.2992884660960393e-05, + "loss": 0.0365, + "step": 27274 + }, + { + "epoch": 8.42, + "learning_rate": 1.2992407463073426e-05, + "loss": 0.0331, + "step": 27275 + }, + { + "epoch": 8.42, + "learning_rate": 1.29919302577019e-05, + "loss": 0.0356, + "step": 27276 + }, + { + "epoch": 8.42, + "learning_rate": 1.2991453044847014e-05, + "loss": 0.0336, + "step": 27277 + }, + { + "epoch": 8.42, + "learning_rate": 1.2990975824509955e-05, + "loss": 0.0381, + "step": 27278 + }, + { + "epoch": 8.42, + "learning_rate": 1.299049859669192e-05, + "loss": 0.0385, + "step": 27279 + }, + { + "epoch": 8.42, + "learning_rate": 1.2990021361394103e-05, + "loss": 0.0343, + "step": 27280 + }, + { + "epoch": 8.42, + "learning_rate": 1.2989544118617698e-05, + "loss": 0.0321, + "step": 27281 + }, + { + "epoch": 8.43, + "learning_rate": 1.2989066868363898e-05, + "loss": 0.0391, + "step": 27282 + }, + { + "epoch": 8.43, + "learning_rate": 1.2988589610633896e-05, + "loss": 0.039, + "step": 27283 + }, + { + "epoch": 8.43, + "learning_rate": 1.2988112345428887e-05, + "loss": 0.0359, + "step": 27284 + }, + { + "epoch": 8.43, + "learning_rate": 1.2987635072750062e-05, + "loss": 0.0364, + "step": 27285 + }, + { + "epoch": 8.43, + "learning_rate": 1.298715779259862e-05, + "loss": 0.0339, + "step": 27286 + }, + { + "epoch": 8.43, + "learning_rate": 1.2986680504975753e-05, + "loss": 0.036, + "step": 27287 + }, + { + "epoch": 8.43, + "learning_rate": 1.2986203209882646e-05, + "loss": 0.0361, + "step": 27288 + }, + { + "epoch": 8.43, + "learning_rate": 1.2985725907320506e-05, + "loss": 0.0395, + "step": 27289 + }, + { + "epoch": 8.43, + "learning_rate": 1.2985248597290521e-05, + "loss": 0.0361, + "step": 27290 + }, + { + "epoch": 8.43, + "learning_rate": 1.298477127979388e-05, + "loss": 0.0363, + "step": 27291 + }, + { + "epoch": 8.43, + "learning_rate": 1.2984293954831786e-05, + "loss": 0.0379, + "step": 27292 + }, + { + "epoch": 8.43, + "learning_rate": 1.2983816622405425e-05, + "loss": 0.0348, + "step": 27293 + }, + { + "epoch": 8.43, + "learning_rate": 1.2983339282515996e-05, + "loss": 0.0363, + "step": 27294 + }, + { + "epoch": 8.43, + "learning_rate": 1.2982861935164695e-05, + "loss": 0.034, + "step": 27295 + }, + { + "epoch": 8.43, + "learning_rate": 1.2982384580352707e-05, + "loss": 0.0376, + "step": 27296 + }, + { + "epoch": 8.43, + "learning_rate": 1.2981907218081235e-05, + "loss": 0.0381, + "step": 27297 + }, + { + "epoch": 8.43, + "learning_rate": 1.2981429848351468e-05, + "loss": 0.0352, + "step": 27298 + }, + { + "epoch": 8.43, + "learning_rate": 1.2980952471164598e-05, + "loss": 0.034, + "step": 27299 + }, + { + "epoch": 8.43, + "learning_rate": 1.2980475086521826e-05, + "loss": 0.0421, + "step": 27300 + }, + { + "epoch": 8.43, + "learning_rate": 1.2979997694424342e-05, + "loss": 0.0375, + "step": 27301 + }, + { + "epoch": 8.43, + "learning_rate": 1.297952029487334e-05, + "loss": 0.0364, + "step": 27302 + }, + { + "epoch": 8.43, + "learning_rate": 1.2979042887870015e-05, + "loss": 0.0365, + "step": 27303 + }, + { + "epoch": 8.43, + "learning_rate": 1.2978565473415558e-05, + "loss": 0.0347, + "step": 27304 + }, + { + "epoch": 8.43, + "learning_rate": 1.2978088051511166e-05, + "loss": 0.0381, + "step": 27305 + }, + { + "epoch": 8.43, + "learning_rate": 1.2977610622158032e-05, + "loss": 0.037, + "step": 27306 + }, + { + "epoch": 8.43, + "learning_rate": 1.2977133185357353e-05, + "loss": 0.0338, + "step": 27307 + }, + { + "epoch": 8.43, + "learning_rate": 1.297665574111032e-05, + "loss": 0.0383, + "step": 27308 + }, + { + "epoch": 8.43, + "learning_rate": 1.2976178289418128e-05, + "loss": 0.0357, + "step": 27309 + }, + { + "epoch": 8.43, + "learning_rate": 1.2975700830281971e-05, + "loss": 0.0372, + "step": 27310 + }, + { + "epoch": 8.43, + "learning_rate": 1.2975223363703044e-05, + "loss": 0.0366, + "step": 27311 + }, + { + "epoch": 8.43, + "learning_rate": 1.2974745889682541e-05, + "loss": 0.0365, + "step": 27312 + }, + { + "epoch": 8.43, + "learning_rate": 1.2974268408221655e-05, + "loss": 0.0369, + "step": 27313 + }, + { + "epoch": 8.44, + "learning_rate": 1.297379091932158e-05, + "loss": 0.0346, + "step": 27314 + }, + { + "epoch": 8.44, + "learning_rate": 1.2973313422983516e-05, + "loss": 0.0362, + "step": 27315 + }, + { + "epoch": 8.44, + "learning_rate": 1.2972835919208648e-05, + "loss": 0.0309, + "step": 27316 + }, + { + "epoch": 8.44, + "learning_rate": 1.2972358407998178e-05, + "loss": 0.0342, + "step": 27317 + }, + { + "epoch": 8.44, + "learning_rate": 1.2971880889353299e-05, + "loss": 0.0377, + "step": 27318 + }, + { + "epoch": 8.44, + "learning_rate": 1.29714033632752e-05, + "loss": 0.0343, + "step": 27319 + }, + { + "epoch": 8.44, + "learning_rate": 1.2970925829765083e-05, + "loss": 0.0386, + "step": 27320 + }, + { + "epoch": 8.44, + "learning_rate": 1.2970448288824135e-05, + "loss": 0.0379, + "step": 27321 + }, + { + "epoch": 8.44, + "learning_rate": 1.2969970740453552e-05, + "loss": 0.0361, + "step": 27322 + }, + { + "epoch": 8.44, + "learning_rate": 1.2969493184654539e-05, + "loss": 0.0322, + "step": 27323 + }, + { + "epoch": 8.44, + "learning_rate": 1.2969015621428271e-05, + "loss": 0.0382, + "step": 27324 + }, + { + "epoch": 8.44, + "learning_rate": 1.2968538050775963e-05, + "loss": 0.0395, + "step": 27325 + }, + { + "epoch": 8.44, + "learning_rate": 1.2968060472698796e-05, + "loss": 0.0318, + "step": 27326 + }, + { + "epoch": 8.44, + "learning_rate": 1.2967582887197967e-05, + "loss": 0.0387, + "step": 27327 + }, + { + "epoch": 8.44, + "learning_rate": 1.2967105294274676e-05, + "loss": 0.0379, + "step": 27328 + }, + { + "epoch": 8.44, + "learning_rate": 1.296662769393011e-05, + "loss": 0.0348, + "step": 27329 + }, + { + "epoch": 8.44, + "learning_rate": 1.2966150086165468e-05, + "loss": 0.0401, + "step": 27330 + }, + { + "epoch": 8.44, + "learning_rate": 1.2965672470981945e-05, + "loss": 0.034, + "step": 27331 + }, + { + "epoch": 8.44, + "learning_rate": 1.296519484838073e-05, + "loss": 0.0354, + "step": 27332 + }, + { + "epoch": 8.44, + "learning_rate": 1.2964717218363028e-05, + "loss": 0.0343, + "step": 27333 + }, + { + "epoch": 8.44, + "learning_rate": 1.2964239580930022e-05, + "loss": 0.0372, + "step": 27334 + }, + { + "epoch": 8.44, + "learning_rate": 1.2963761936082915e-05, + "loss": 0.0352, + "step": 27335 + }, + { + "epoch": 8.44, + "learning_rate": 1.2963284283822898e-05, + "loss": 0.0346, + "step": 27336 + }, + { + "epoch": 8.44, + "learning_rate": 1.2962806624151168e-05, + "loss": 0.0313, + "step": 27337 + }, + { + "epoch": 8.44, + "learning_rate": 1.2962328957068917e-05, + "loss": 0.0338, + "step": 27338 + }, + { + "epoch": 8.44, + "learning_rate": 1.296185128257734e-05, + "loss": 0.0357, + "step": 27339 + }, + { + "epoch": 8.44, + "learning_rate": 1.2961373600677633e-05, + "loss": 0.0364, + "step": 27340 + }, + { + "epoch": 8.44, + "learning_rate": 1.2960895911370993e-05, + "loss": 0.035, + "step": 27341 + }, + { + "epoch": 8.44, + "learning_rate": 1.296041821465861e-05, + "loss": 0.0358, + "step": 27342 + }, + { + "epoch": 8.44, + "learning_rate": 1.2959940510541683e-05, + "loss": 0.0338, + "step": 27343 + }, + { + "epoch": 8.44, + "learning_rate": 1.2959462799021403e-05, + "loss": 0.041, + "step": 27344 + }, + { + "epoch": 8.44, + "learning_rate": 1.2958985080098967e-05, + "loss": 0.0364, + "step": 27345 + }, + { + "epoch": 8.45, + "learning_rate": 1.2958507353775571e-05, + "loss": 0.0358, + "step": 27346 + }, + { + "epoch": 8.45, + "learning_rate": 1.2958029620052407e-05, + "loss": 0.0378, + "step": 27347 + }, + { + "epoch": 8.45, + "learning_rate": 1.2957551878930672e-05, + "loss": 0.0362, + "step": 27348 + }, + { + "epoch": 8.45, + "learning_rate": 1.2957074130411561e-05, + "loss": 0.0325, + "step": 27349 + }, + { + "epoch": 8.45, + "learning_rate": 1.2956596374496266e-05, + "loss": 0.0339, + "step": 27350 + }, + { + "epoch": 8.45, + "learning_rate": 1.2956118611185988e-05, + "loss": 0.0341, + "step": 27351 + }, + { + "epoch": 8.45, + "learning_rate": 1.2955640840481916e-05, + "loss": 0.0353, + "step": 27352 + }, + { + "epoch": 8.45, + "learning_rate": 1.2955163062385245e-05, + "loss": 0.0333, + "step": 27353 + }, + { + "epoch": 8.45, + "learning_rate": 1.2954685276897177e-05, + "loss": 0.0378, + "step": 27354 + }, + { + "epoch": 8.45, + "learning_rate": 1.29542074840189e-05, + "loss": 0.0344, + "step": 27355 + }, + { + "epoch": 8.45, + "learning_rate": 1.295372968375161e-05, + "loss": 0.0383, + "step": 27356 + }, + { + "epoch": 8.45, + "learning_rate": 1.2953251876096504e-05, + "loss": 0.036, + "step": 27357 + }, + { + "epoch": 8.45, + "learning_rate": 1.2952774061054773e-05, + "loss": 0.0329, + "step": 27358 + }, + { + "epoch": 8.45, + "learning_rate": 1.2952296238627622e-05, + "loss": 0.0393, + "step": 27359 + }, + { + "epoch": 8.45, + "learning_rate": 1.2951818408816237e-05, + "loss": 0.0374, + "step": 27360 + }, + { + "epoch": 8.45, + "learning_rate": 1.2951340571621816e-05, + "loss": 0.0335, + "step": 27361 + }, + { + "epoch": 8.45, + "learning_rate": 1.2950862727045554e-05, + "loss": 0.0354, + "step": 27362 + }, + { + "epoch": 8.45, + "learning_rate": 1.2950384875088644e-05, + "loss": 0.0341, + "step": 27363 + }, + { + "epoch": 8.45, + "learning_rate": 1.2949907015752286e-05, + "loss": 0.0367, + "step": 27364 + }, + { + "epoch": 8.45, + "learning_rate": 1.294942914903767e-05, + "loss": 0.0357, + "step": 27365 + }, + { + "epoch": 8.45, + "learning_rate": 1.2948951274945995e-05, + "loss": 0.0363, + "step": 27366 + }, + { + "epoch": 8.45, + "learning_rate": 1.2948473393478455e-05, + "loss": 0.0411, + "step": 27367 + }, + { + "epoch": 8.45, + "learning_rate": 1.2947995504636248e-05, + "loss": 0.0355, + "step": 27368 + }, + { + "epoch": 8.45, + "learning_rate": 1.2947517608420565e-05, + "loss": 0.0376, + "step": 27369 + }, + { + "epoch": 8.45, + "learning_rate": 1.29470397048326e-05, + "loss": 0.0367, + "step": 27370 + }, + { + "epoch": 8.45, + "learning_rate": 1.2946561793873553e-05, + "loss": 0.0353, + "step": 27371 + }, + { + "epoch": 8.45, + "learning_rate": 1.294608387554462e-05, + "loss": 0.0356, + "step": 27372 + }, + { + "epoch": 8.45, + "learning_rate": 1.294560594984699e-05, + "loss": 0.0378, + "step": 27373 + }, + { + "epoch": 8.45, + "learning_rate": 1.2945128016781865e-05, + "loss": 0.0368, + "step": 27374 + }, + { + "epoch": 8.45, + "learning_rate": 1.2944650076350433e-05, + "loss": 0.0348, + "step": 27375 + }, + { + "epoch": 8.45, + "learning_rate": 1.2944172128553898e-05, + "loss": 0.0338, + "step": 27376 + }, + { + "epoch": 8.45, + "learning_rate": 1.2943694173393455e-05, + "loss": 0.0358, + "step": 27377 + }, + { + "epoch": 8.45, + "learning_rate": 1.294321621087029e-05, + "loss": 0.0362, + "step": 27378 + }, + { + "epoch": 8.46, + "learning_rate": 1.2942738240985606e-05, + "loss": 0.0395, + "step": 27379 + }, + { + "epoch": 8.46, + "learning_rate": 1.2942260263740598e-05, + "loss": 0.038, + "step": 27380 + }, + { + "epoch": 8.46, + "learning_rate": 1.294178227913646e-05, + "loss": 0.0393, + "step": 27381 + }, + { + "epoch": 8.46, + "learning_rate": 1.2941304287174388e-05, + "loss": 0.0358, + "step": 27382 + }, + { + "epoch": 8.46, + "learning_rate": 1.294082628785558e-05, + "loss": 0.0378, + "step": 27383 + }, + { + "epoch": 8.46, + "learning_rate": 1.2940348281181222e-05, + "loss": 0.0341, + "step": 27384 + }, + { + "epoch": 8.46, + "learning_rate": 1.2939870267152524e-05, + "loss": 0.0346, + "step": 27385 + }, + { + "epoch": 8.46, + "learning_rate": 1.293939224577067e-05, + "loss": 0.0363, + "step": 27386 + }, + { + "epoch": 8.46, + "learning_rate": 1.2938914217036862e-05, + "loss": 0.0346, + "step": 27387 + }, + { + "epoch": 8.46, + "learning_rate": 1.2938436180952292e-05, + "loss": 0.0337, + "step": 27388 + }, + { + "epoch": 8.46, + "learning_rate": 1.2937958137518156e-05, + "loss": 0.0357, + "step": 27389 + }, + { + "epoch": 8.46, + "learning_rate": 1.2937480086735655e-05, + "loss": 0.0397, + "step": 27390 + }, + { + "epoch": 8.46, + "learning_rate": 1.2937002028605979e-05, + "loss": 0.0357, + "step": 27391 + }, + { + "epoch": 8.46, + "learning_rate": 1.2936523963130326e-05, + "loss": 0.0379, + "step": 27392 + }, + { + "epoch": 8.46, + "learning_rate": 1.2936045890309888e-05, + "loss": 0.0375, + "step": 27393 + }, + { + "epoch": 8.46, + "learning_rate": 1.2935567810145865e-05, + "loss": 0.037, + "step": 27394 + }, + { + "epoch": 8.46, + "learning_rate": 1.2935089722639451e-05, + "loss": 0.0369, + "step": 27395 + }, + { + "epoch": 8.46, + "learning_rate": 1.2934611627791845e-05, + "loss": 0.0373, + "step": 27396 + }, + { + "epoch": 8.46, + "learning_rate": 1.2934133525604238e-05, + "loss": 0.0338, + "step": 27397 + }, + { + "epoch": 8.46, + "learning_rate": 1.2933655416077827e-05, + "loss": 0.0328, + "step": 27398 + }, + { + "epoch": 8.46, + "learning_rate": 1.2933177299213808e-05, + "loss": 0.038, + "step": 27399 + }, + { + "epoch": 8.46, + "learning_rate": 1.2932699175013383e-05, + "loss": 0.0383, + "step": 27400 + }, + { + "epoch": 8.46, + "learning_rate": 1.2932221043477737e-05, + "loss": 0.0356, + "step": 27401 + }, + { + "epoch": 8.46, + "learning_rate": 1.2931742904608074e-05, + "loss": 0.0355, + "step": 27402 + }, + { + "epoch": 8.46, + "learning_rate": 1.2931264758405589e-05, + "loss": 0.0383, + "step": 27403 + }, + { + "epoch": 8.46, + "learning_rate": 1.293078660487147e-05, + "loss": 0.0385, + "step": 27404 + }, + { + "epoch": 8.46, + "learning_rate": 1.2930308444006925e-05, + "loss": 0.036, + "step": 27405 + }, + { + "epoch": 8.46, + "learning_rate": 1.292983027581314e-05, + "loss": 0.0379, + "step": 27406 + }, + { + "epoch": 8.46, + "learning_rate": 1.2929352100291317e-05, + "loss": 0.0359, + "step": 27407 + }, + { + "epoch": 8.46, + "learning_rate": 1.2928873917442653e-05, + "loss": 0.0328, + "step": 27408 + }, + { + "epoch": 8.46, + "learning_rate": 1.2928395727268334e-05, + "loss": 0.0371, + "step": 27409 + }, + { + "epoch": 8.46, + "learning_rate": 1.292791752976957e-05, + "loss": 0.0313, + "step": 27410 + }, + { + "epoch": 8.47, + "learning_rate": 1.2927439324947549e-05, + "loss": 0.0375, + "step": 27411 + }, + { + "epoch": 8.47, + "learning_rate": 1.2926961112803464e-05, + "loss": 0.0363, + "step": 27412 + }, + { + "epoch": 8.47, + "learning_rate": 1.292648289333852e-05, + "loss": 0.0319, + "step": 27413 + }, + { + "epoch": 8.47, + "learning_rate": 1.2926004666553908e-05, + "loss": 0.0334, + "step": 27414 + }, + { + "epoch": 8.47, + "learning_rate": 1.2925526432450823e-05, + "loss": 0.0397, + "step": 27415 + }, + { + "epoch": 8.47, + "learning_rate": 1.2925048191030465e-05, + "loss": 0.0346, + "step": 27416 + }, + { + "epoch": 8.47, + "learning_rate": 1.2924569942294025e-05, + "loss": 0.0365, + "step": 27417 + }, + { + "epoch": 8.47, + "learning_rate": 1.2924091686242703e-05, + "loss": 0.0358, + "step": 27418 + }, + { + "epoch": 8.47, + "learning_rate": 1.2923613422877697e-05, + "loss": 0.0382, + "step": 27419 + }, + { + "epoch": 8.47, + "learning_rate": 1.2923135152200197e-05, + "loss": 0.0375, + "step": 27420 + }, + { + "epoch": 8.47, + "learning_rate": 1.2922656874211406e-05, + "loss": 0.0399, + "step": 27421 + }, + { + "epoch": 8.47, + "learning_rate": 1.2922178588912516e-05, + "loss": 0.0359, + "step": 27422 + }, + { + "epoch": 8.47, + "learning_rate": 1.2921700296304724e-05, + "loss": 0.0384, + "step": 27423 + }, + { + "epoch": 8.47, + "learning_rate": 1.2921221996389227e-05, + "loss": 0.0342, + "step": 27424 + }, + { + "epoch": 8.47, + "learning_rate": 1.2920743689167218e-05, + "loss": 0.0378, + "step": 27425 + }, + { + "epoch": 8.47, + "learning_rate": 1.29202653746399e-05, + "loss": 0.0364, + "step": 27426 + }, + { + "epoch": 8.47, + "learning_rate": 1.2919787052808466e-05, + "loss": 0.0389, + "step": 27427 + }, + { + "epoch": 8.47, + "learning_rate": 1.2919308723674108e-05, + "loss": 0.0396, + "step": 27428 + }, + { + "epoch": 8.47, + "learning_rate": 1.291883038723803e-05, + "loss": 0.0401, + "step": 27429 + }, + { + "epoch": 8.47, + "learning_rate": 1.2918352043501425e-05, + "loss": 0.0354, + "step": 27430 + }, + { + "epoch": 8.47, + "learning_rate": 1.291787369246549e-05, + "loss": 0.0397, + "step": 27431 + }, + { + "epoch": 8.47, + "learning_rate": 1.2917395334131415e-05, + "loss": 0.0374, + "step": 27432 + }, + { + "epoch": 8.47, + "learning_rate": 1.2916916968500406e-05, + "loss": 0.0386, + "step": 27433 + }, + { + "epoch": 8.47, + "learning_rate": 1.2916438595573659e-05, + "loss": 0.0337, + "step": 27434 + }, + { + "epoch": 8.47, + "learning_rate": 1.291596021535236e-05, + "loss": 0.039, + "step": 27435 + }, + { + "epoch": 8.47, + "learning_rate": 1.2915481827837719e-05, + "loss": 0.0363, + "step": 27436 + }, + { + "epoch": 8.47, + "learning_rate": 1.2915003433030924e-05, + "loss": 0.0371, + "step": 27437 + }, + { + "epoch": 8.47, + "learning_rate": 1.2914525030933172e-05, + "loss": 0.0366, + "step": 27438 + }, + { + "epoch": 8.47, + "learning_rate": 1.2914046621545665e-05, + "loss": 0.0318, + "step": 27439 + }, + { + "epoch": 8.47, + "learning_rate": 1.2913568204869591e-05, + "loss": 0.0369, + "step": 27440 + }, + { + "epoch": 8.47, + "learning_rate": 1.2913089780906156e-05, + "loss": 0.0369, + "step": 27441 + }, + { + "epoch": 8.47, + "learning_rate": 1.2912611349656552e-05, + "loss": 0.0405, + "step": 27442 + }, + { + "epoch": 8.47, + "learning_rate": 1.2912132911121971e-05, + "loss": 0.0344, + "step": 27443 + }, + { + "epoch": 8.48, + "learning_rate": 1.291165446530362e-05, + "loss": 0.0345, + "step": 27444 + }, + { + "epoch": 8.48, + "learning_rate": 1.2911176012202689e-05, + "loss": 0.0367, + "step": 27445 + }, + { + "epoch": 8.48, + "learning_rate": 1.2910697551820373e-05, + "loss": 0.0406, + "step": 27446 + }, + { + "epoch": 8.48, + "learning_rate": 1.2910219084157874e-05, + "loss": 0.0349, + "step": 27447 + }, + { + "epoch": 8.48, + "learning_rate": 1.2909740609216383e-05, + "loss": 0.0366, + "step": 27448 + }, + { + "epoch": 8.48, + "learning_rate": 1.2909262126997105e-05, + "loss": 0.0332, + "step": 27449 + }, + { + "epoch": 8.48, + "learning_rate": 1.2908783637501227e-05, + "loss": 0.0377, + "step": 27450 + }, + { + "epoch": 8.48, + "learning_rate": 1.2908305140729955e-05, + "loss": 0.0321, + "step": 27451 + }, + { + "epoch": 8.48, + "learning_rate": 1.290782663668448e-05, + "loss": 0.0359, + "step": 27452 + }, + { + "epoch": 8.48, + "learning_rate": 1.2907348125365998e-05, + "loss": 0.0387, + "step": 27453 + }, + { + "epoch": 8.48, + "learning_rate": 1.2906869606775711e-05, + "loss": 0.0342, + "step": 27454 + }, + { + "epoch": 8.48, + "learning_rate": 1.2906391080914809e-05, + "loss": 0.034, + "step": 27455 + }, + { + "epoch": 8.48, + "learning_rate": 1.2905912547784497e-05, + "loss": 0.0331, + "step": 27456 + }, + { + "epoch": 8.48, + "learning_rate": 1.2905434007385964e-05, + "loss": 0.0353, + "step": 27457 + }, + { + "epoch": 8.48, + "learning_rate": 1.2904955459720415e-05, + "loss": 0.0398, + "step": 27458 + }, + { + "epoch": 8.48, + "learning_rate": 1.290447690478904e-05, + "loss": 0.0357, + "step": 27459 + }, + { + "epoch": 8.48, + "learning_rate": 1.2903998342593038e-05, + "loss": 0.0384, + "step": 27460 + }, + { + "epoch": 8.48, + "learning_rate": 1.2903519773133607e-05, + "loss": 0.0364, + "step": 27461 + }, + { + "epoch": 8.48, + "learning_rate": 1.2903041196411945e-05, + "loss": 0.0429, + "step": 27462 + }, + { + "epoch": 8.48, + "learning_rate": 1.2902562612429244e-05, + "loss": 0.0355, + "step": 27463 + }, + { + "epoch": 8.48, + "learning_rate": 1.2902084021186709e-05, + "loss": 0.0361, + "step": 27464 + }, + { + "epoch": 8.48, + "learning_rate": 1.290160542268553e-05, + "loss": 0.0356, + "step": 27465 + }, + { + "epoch": 8.48, + "learning_rate": 1.2901126816926905e-05, + "loss": 0.0419, + "step": 27466 + }, + { + "epoch": 8.48, + "learning_rate": 1.2900648203912036e-05, + "loss": 0.0368, + "step": 27467 + }, + { + "epoch": 8.48, + "learning_rate": 1.2900169583642115e-05, + "loss": 0.034, + "step": 27468 + }, + { + "epoch": 8.48, + "learning_rate": 1.2899690956118343e-05, + "loss": 0.0357, + "step": 27469 + }, + { + "epoch": 8.48, + "learning_rate": 1.2899212321341911e-05, + "loss": 0.0376, + "step": 27470 + }, + { + "epoch": 8.48, + "learning_rate": 1.2898733679314021e-05, + "loss": 0.0356, + "step": 27471 + }, + { + "epoch": 8.48, + "learning_rate": 1.2898255030035873e-05, + "loss": 0.0374, + "step": 27472 + }, + { + "epoch": 8.48, + "learning_rate": 1.289777637350866e-05, + "loss": 0.0379, + "step": 27473 + }, + { + "epoch": 8.48, + "learning_rate": 1.2897297709733576e-05, + "loss": 0.0336, + "step": 27474 + }, + { + "epoch": 8.48, + "learning_rate": 1.2896819038711825e-05, + "loss": 0.041, + "step": 27475 + }, + { + "epoch": 8.49, + "learning_rate": 1.28963403604446e-05, + "loss": 0.0374, + "step": 27476 + }, + { + "epoch": 8.49, + "learning_rate": 1.28958616749331e-05, + "loss": 0.0352, + "step": 27477 + }, + { + "epoch": 8.49, + "learning_rate": 1.2895382982178522e-05, + "loss": 0.0385, + "step": 27478 + }, + { + "epoch": 8.49, + "learning_rate": 1.2894904282182062e-05, + "loss": 0.0416, + "step": 27479 + }, + { + "epoch": 8.49, + "learning_rate": 1.289442557494492e-05, + "loss": 0.0365, + "step": 27480 + }, + { + "epoch": 8.49, + "learning_rate": 1.2893946860468289e-05, + "loss": 0.0433, + "step": 27481 + }, + { + "epoch": 8.49, + "learning_rate": 1.289346813875337e-05, + "loss": 0.0336, + "step": 27482 + }, + { + "epoch": 8.49, + "learning_rate": 1.2892989409801362e-05, + "loss": 0.0347, + "step": 27483 + }, + { + "epoch": 8.49, + "learning_rate": 1.289251067361346e-05, + "loss": 0.0315, + "step": 27484 + }, + { + "epoch": 8.49, + "learning_rate": 1.289203193019086e-05, + "loss": 0.0369, + "step": 27485 + }, + { + "epoch": 8.49, + "learning_rate": 1.2891553179534757e-05, + "loss": 0.0353, + "step": 27486 + }, + { + "epoch": 8.49, + "learning_rate": 1.2891074421646357e-05, + "loss": 0.0377, + "step": 27487 + }, + { + "epoch": 8.49, + "learning_rate": 1.289059565652685e-05, + "loss": 0.0395, + "step": 27488 + }, + { + "epoch": 8.49, + "learning_rate": 1.2890116884177437e-05, + "loss": 0.0355, + "step": 27489 + }, + { + "epoch": 8.49, + "learning_rate": 1.2889638104599316e-05, + "loss": 0.0406, + "step": 27490 + }, + { + "epoch": 8.49, + "learning_rate": 1.288915931779368e-05, + "loss": 0.0372, + "step": 27491 + }, + { + "epoch": 8.49, + "learning_rate": 1.2888680523761731e-05, + "loss": 0.0385, + "step": 27492 + }, + { + "epoch": 8.49, + "learning_rate": 1.2888201722504668e-05, + "loss": 0.0396, + "step": 27493 + }, + { + "epoch": 8.49, + "learning_rate": 1.2887722914023679e-05, + "loss": 0.0367, + "step": 27494 + }, + { + "epoch": 8.49, + "learning_rate": 1.2887244098319976e-05, + "loss": 0.0378, + "step": 27495 + }, + { + "epoch": 8.49, + "learning_rate": 1.2886765275394746e-05, + "loss": 0.0334, + "step": 27496 + }, + { + "epoch": 8.49, + "learning_rate": 1.2886286445249185e-05, + "loss": 0.0354, + "step": 27497 + }, + { + "epoch": 8.49, + "learning_rate": 1.2885807607884501e-05, + "loss": 0.036, + "step": 27498 + }, + { + "epoch": 8.49, + "learning_rate": 1.2885328763301885e-05, + "loss": 0.0396, + "step": 27499 + }, + { + "epoch": 8.49, + "learning_rate": 1.2884849911502532e-05, + "loss": 0.0353, + "step": 27500 + }, + { + "epoch": 8.49, + "learning_rate": 1.2884371052487647e-05, + "loss": 0.0343, + "step": 27501 + }, + { + "epoch": 8.49, + "learning_rate": 1.2883892186258422e-05, + "loss": 0.0339, + "step": 27502 + }, + { + "epoch": 8.49, + "learning_rate": 1.2883413312816057e-05, + "loss": 0.0341, + "step": 27503 + }, + { + "epoch": 8.49, + "learning_rate": 1.2882934432161749e-05, + "loss": 0.0337, + "step": 27504 + }, + { + "epoch": 8.49, + "learning_rate": 1.2882455544296697e-05, + "loss": 0.0343, + "step": 27505 + }, + { + "epoch": 8.49, + "learning_rate": 1.2881976649222096e-05, + "loss": 0.0407, + "step": 27506 + }, + { + "epoch": 8.49, + "learning_rate": 1.2881497746939149e-05, + "loss": 0.0337, + "step": 27507 + }, + { + "epoch": 8.5, + "learning_rate": 1.2881018837449049e-05, + "loss": 0.0397, + "step": 27508 + }, + { + "epoch": 8.5, + "learning_rate": 1.2880539920752994e-05, + "loss": 0.0329, + "step": 27509 + }, + { + "epoch": 8.5, + "learning_rate": 1.2880060996852186e-05, + "loss": 0.0376, + "step": 27510 + }, + { + "epoch": 8.5, + "learning_rate": 1.2879582065747817e-05, + "loss": 0.0358, + "step": 27511 + }, + { + "epoch": 8.5, + "learning_rate": 1.287910312744109e-05, + "loss": 0.0336, + "step": 27512 + }, + { + "epoch": 8.5, + "learning_rate": 1.2878624181933203e-05, + "loss": 0.0346, + "step": 27513 + }, + { + "epoch": 8.5, + "learning_rate": 1.2878145229225348e-05, + "loss": 0.0378, + "step": 27514 + }, + { + "epoch": 8.5, + "learning_rate": 1.2877666269318729e-05, + "loss": 0.0394, + "step": 27515 + }, + { + "epoch": 8.5, + "learning_rate": 1.2877187302214544e-05, + "loss": 0.036, + "step": 27516 + }, + { + "epoch": 8.5, + "learning_rate": 1.2876708327913983e-05, + "loss": 0.0339, + "step": 27517 + }, + { + "epoch": 8.5, + "learning_rate": 1.2876229346418256e-05, + "loss": 0.0353, + "step": 27518 + }, + { + "epoch": 8.5, + "learning_rate": 1.287575035772855e-05, + "loss": 0.0352, + "step": 27519 + }, + { + "epoch": 8.5, + "learning_rate": 1.2875271361846069e-05, + "loss": 0.0341, + "step": 27520 + }, + { + "epoch": 8.5, + "learning_rate": 1.2874792358772013e-05, + "loss": 0.0378, + "step": 27521 + }, + { + "epoch": 8.5, + "learning_rate": 1.2874313348507573e-05, + "loss": 0.0383, + "step": 27522 + }, + { + "epoch": 8.5, + "learning_rate": 1.2873834331053954e-05, + "loss": 0.0373, + "step": 27523 + }, + { + "epoch": 8.5, + "learning_rate": 1.2873355306412347e-05, + "loss": 0.0375, + "step": 27524 + }, + { + "epoch": 8.5, + "learning_rate": 1.2872876274583956e-05, + "loss": 0.0428, + "step": 27525 + }, + { + "epoch": 8.5, + "learning_rate": 1.287239723556998e-05, + "loss": 0.0352, + "step": 27526 + }, + { + "epoch": 8.5, + "learning_rate": 1.2871918189371612e-05, + "loss": 0.0374, + "step": 27527 + }, + { + "epoch": 8.5, + "learning_rate": 1.2871439135990056e-05, + "loss": 0.0354, + "step": 27528 + }, + { + "epoch": 8.5, + "learning_rate": 1.2870960075426503e-05, + "loss": 0.0384, + "step": 27529 + }, + { + "epoch": 8.5, + "learning_rate": 1.2870481007682158e-05, + "loss": 0.0307, + "step": 27530 + }, + { + "epoch": 8.5, + "learning_rate": 1.2870001932758216e-05, + "loss": 0.0361, + "step": 27531 + }, + { + "epoch": 8.5, + "learning_rate": 1.2869522850655876e-05, + "loss": 0.0369, + "step": 27532 + }, + { + "epoch": 8.5, + "learning_rate": 1.2869043761376335e-05, + "loss": 0.0377, + "step": 27533 + }, + { + "epoch": 8.5, + "learning_rate": 1.2868564664920791e-05, + "loss": 0.037, + "step": 27534 + }, + { + "epoch": 8.5, + "learning_rate": 1.2868085561290447e-05, + "loss": 0.0357, + "step": 27535 + }, + { + "epoch": 8.5, + "learning_rate": 1.2867606450486494e-05, + "loss": 0.0376, + "step": 27536 + }, + { + "epoch": 8.5, + "learning_rate": 1.2867127332510139e-05, + "loss": 0.0371, + "step": 27537 + }, + { + "epoch": 8.5, + "learning_rate": 1.286664820736257e-05, + "loss": 0.0355, + "step": 27538 + }, + { + "epoch": 8.5, + "learning_rate": 1.2866169075044996e-05, + "loss": 0.037, + "step": 27539 + }, + { + "epoch": 8.5, + "learning_rate": 1.2865689935558608e-05, + "loss": 0.0332, + "step": 27540 + }, + { + "epoch": 8.51, + "learning_rate": 1.2865210788904606e-05, + "loss": 0.0339, + "step": 27541 + }, + { + "epoch": 8.51, + "learning_rate": 1.2864731635084191e-05, + "loss": 0.0395, + "step": 27542 + }, + { + "epoch": 8.51, + "learning_rate": 1.2864252474098557e-05, + "loss": 0.0381, + "step": 27543 + }, + { + "epoch": 8.51, + "learning_rate": 1.286377330594891e-05, + "loss": 0.0341, + "step": 27544 + }, + { + "epoch": 8.51, + "learning_rate": 1.286329413063644e-05, + "loss": 0.0348, + "step": 27545 + }, + { + "epoch": 8.51, + "learning_rate": 1.286281494816235e-05, + "loss": 0.0389, + "step": 27546 + }, + { + "epoch": 8.51, + "learning_rate": 1.286233575852784e-05, + "loss": 0.0373, + "step": 27547 + }, + { + "epoch": 8.51, + "learning_rate": 1.2861856561734101e-05, + "loss": 0.0364, + "step": 27548 + }, + { + "epoch": 8.51, + "learning_rate": 1.286137735778234e-05, + "loss": 0.0366, + "step": 27549 + }, + { + "epoch": 8.51, + "learning_rate": 1.2860898146673752e-05, + "loss": 0.0397, + "step": 27550 + }, + { + "epoch": 8.51, + "learning_rate": 1.2860418928409534e-05, + "loss": 0.0381, + "step": 27551 + }, + { + "epoch": 8.51, + "learning_rate": 1.2859939702990892e-05, + "loss": 0.033, + "step": 27552 + }, + { + "epoch": 8.51, + "learning_rate": 1.2859460470419012e-05, + "loss": 0.0373, + "step": 27553 + }, + { + "epoch": 8.51, + "learning_rate": 1.2858981230695107e-05, + "loss": 0.0388, + "step": 27554 + }, + { + "epoch": 8.51, + "learning_rate": 1.2858501983820364e-05, + "loss": 0.0392, + "step": 27555 + }, + { + "epoch": 8.51, + "learning_rate": 1.2858022729795984e-05, + "loss": 0.0392, + "step": 27556 + }, + { + "epoch": 8.51, + "learning_rate": 1.2857543468623175e-05, + "loss": 0.0382, + "step": 27557 + }, + { + "epoch": 8.51, + "learning_rate": 1.2857064200303125e-05, + "loss": 0.0361, + "step": 27558 + }, + { + "epoch": 8.51, + "learning_rate": 1.2856584924837034e-05, + "loss": 0.0386, + "step": 27559 + }, + { + "epoch": 8.51, + "learning_rate": 1.2856105642226107e-05, + "loss": 0.0354, + "step": 27560 + }, + { + "epoch": 8.51, + "learning_rate": 1.2855626352471535e-05, + "loss": 0.0376, + "step": 27561 + }, + { + "epoch": 8.51, + "learning_rate": 1.2855147055574521e-05, + "loss": 0.037, + "step": 27562 + }, + { + "epoch": 8.51, + "learning_rate": 1.2854667751536268e-05, + "loss": 0.0363, + "step": 27563 + }, + { + "epoch": 8.51, + "learning_rate": 1.2854188440357967e-05, + "loss": 0.0325, + "step": 27564 + }, + { + "epoch": 8.51, + "learning_rate": 1.285370912204082e-05, + "loss": 0.041, + "step": 27565 + }, + { + "epoch": 8.51, + "learning_rate": 1.2853229796586027e-05, + "loss": 0.036, + "step": 27566 + }, + { + "epoch": 8.51, + "learning_rate": 1.2852750463994786e-05, + "loss": 0.0357, + "step": 27567 + }, + { + "epoch": 8.51, + "learning_rate": 1.2852271124268295e-05, + "loss": 0.0327, + "step": 27568 + }, + { + "epoch": 8.51, + "learning_rate": 1.2851791777407752e-05, + "loss": 0.0367, + "step": 27569 + }, + { + "epoch": 8.51, + "learning_rate": 1.285131242341436e-05, + "loss": 0.0372, + "step": 27570 + }, + { + "epoch": 8.51, + "learning_rate": 1.2850833062289315e-05, + "loss": 0.0373, + "step": 27571 + }, + { + "epoch": 8.51, + "learning_rate": 1.285035369403382e-05, + "loss": 0.0361, + "step": 27572 + }, + { + "epoch": 8.52, + "learning_rate": 1.2849874318649063e-05, + "loss": 0.0349, + "step": 27573 + }, + { + "epoch": 8.52, + "learning_rate": 1.2849394936136254e-05, + "loss": 0.0341, + "step": 27574 + }, + { + "epoch": 8.52, + "learning_rate": 1.2848915546496592e-05, + "loss": 0.0399, + "step": 27575 + }, + { + "epoch": 8.52, + "learning_rate": 1.2848436149731267e-05, + "loss": 0.0415, + "step": 27576 + }, + { + "epoch": 8.52, + "learning_rate": 1.284795674584149e-05, + "loss": 0.0374, + "step": 27577 + }, + { + "epoch": 8.52, + "learning_rate": 1.2847477334828449e-05, + "loss": 0.035, + "step": 27578 + }, + { + "epoch": 8.52, + "learning_rate": 1.2846997916693346e-05, + "loss": 0.0375, + "step": 27579 + }, + { + "epoch": 8.52, + "learning_rate": 1.2846518491437388e-05, + "loss": 0.0374, + "step": 27580 + }, + { + "epoch": 8.52, + "learning_rate": 1.2846039059061766e-05, + "loss": 0.0354, + "step": 27581 + }, + { + "epoch": 8.52, + "learning_rate": 1.284555961956768e-05, + "loss": 0.0361, + "step": 27582 + }, + { + "epoch": 8.52, + "learning_rate": 1.284508017295633e-05, + "loss": 0.0362, + "step": 27583 + }, + { + "epoch": 8.52, + "learning_rate": 1.2844600719228917e-05, + "loss": 0.0399, + "step": 27584 + }, + { + "epoch": 8.52, + "learning_rate": 1.2844121258386637e-05, + "loss": 0.0373, + "step": 27585 + }, + { + "epoch": 8.52, + "learning_rate": 1.2843641790430695e-05, + "loss": 0.0375, + "step": 27586 + }, + { + "epoch": 8.52, + "learning_rate": 1.2843162315362281e-05, + "loss": 0.0319, + "step": 27587 + }, + { + "epoch": 8.52, + "learning_rate": 1.2842682833182602e-05, + "loss": 0.0363, + "step": 27588 + }, + { + "epoch": 8.52, + "learning_rate": 1.2842203343892854e-05, + "loss": 0.0349, + "step": 27589 + }, + { + "epoch": 8.52, + "learning_rate": 1.2841723847494239e-05, + "loss": 0.0398, + "step": 27590 + }, + { + "epoch": 8.52, + "learning_rate": 1.2841244343987951e-05, + "loss": 0.0402, + "step": 27591 + }, + { + "epoch": 8.52, + "learning_rate": 1.2840764833375197e-05, + "loss": 0.0347, + "step": 27592 + }, + { + "epoch": 8.52, + "learning_rate": 1.2840285315657169e-05, + "loss": 0.0413, + "step": 27593 + }, + { + "epoch": 8.52, + "learning_rate": 1.283980579083507e-05, + "loss": 0.0323, + "step": 27594 + }, + { + "epoch": 8.52, + "learning_rate": 1.2839326258910098e-05, + "loss": 0.0351, + "step": 27595 + }, + { + "epoch": 8.52, + "learning_rate": 1.2838846719883455e-05, + "loss": 0.0409, + "step": 27596 + }, + { + "epoch": 8.52, + "learning_rate": 1.2838367173756336e-05, + "loss": 0.0379, + "step": 27597 + }, + { + "epoch": 8.52, + "learning_rate": 1.2837887620529948e-05, + "loss": 0.0361, + "step": 27598 + }, + { + "epoch": 8.52, + "learning_rate": 1.2837408060205481e-05, + "loss": 0.0348, + "step": 27599 + }, + { + "epoch": 8.52, + "learning_rate": 1.2836928492784137e-05, + "loss": 0.0389, + "step": 27600 + }, + { + "epoch": 8.52, + "learning_rate": 1.2836448918267123e-05, + "loss": 0.0433, + "step": 27601 + }, + { + "epoch": 8.52, + "learning_rate": 1.2835969336655629e-05, + "loss": 0.0364, + "step": 27602 + }, + { + "epoch": 8.52, + "learning_rate": 1.2835489747950863e-05, + "loss": 0.0334, + "step": 27603 + }, + { + "epoch": 8.52, + "learning_rate": 1.2835010152154013e-05, + "loss": 0.0378, + "step": 27604 + }, + { + "epoch": 8.53, + "learning_rate": 1.2834530549266288e-05, + "loss": 0.0383, + "step": 27605 + }, + { + "epoch": 8.53, + "learning_rate": 1.2834050939288889e-05, + "loss": 0.0367, + "step": 27606 + }, + { + "epoch": 8.53, + "learning_rate": 1.2833571322223008e-05, + "loss": 0.0405, + "step": 27607 + }, + { + "epoch": 8.53, + "learning_rate": 1.283309169806985e-05, + "loss": 0.0377, + "step": 27608 + }, + { + "epoch": 8.53, + "learning_rate": 1.2832612066830614e-05, + "loss": 0.0372, + "step": 27609 + }, + { + "epoch": 8.53, + "learning_rate": 1.2832132428506493e-05, + "loss": 0.037, + "step": 27610 + }, + { + "epoch": 8.53, + "learning_rate": 1.28316527830987e-05, + "loss": 0.0349, + "step": 27611 + }, + { + "epoch": 8.53, + "learning_rate": 1.2831173130608423e-05, + "loss": 0.0359, + "step": 27612 + }, + { + "epoch": 8.53, + "learning_rate": 1.2830693471036867e-05, + "loss": 0.0342, + "step": 27613 + }, + { + "epoch": 8.53, + "learning_rate": 1.2830213804385228e-05, + "loss": 0.0379, + "step": 27614 + }, + { + "epoch": 8.53, + "learning_rate": 1.282973413065471e-05, + "loss": 0.0357, + "step": 27615 + }, + { + "epoch": 8.53, + "learning_rate": 1.2829254449846508e-05, + "loss": 0.0393, + "step": 27616 + }, + { + "epoch": 8.53, + "learning_rate": 1.2828774761961826e-05, + "loss": 0.036, + "step": 27617 + }, + { + "epoch": 8.53, + "learning_rate": 1.2828295067001863e-05, + "loss": 0.037, + "step": 27618 + }, + { + "epoch": 8.53, + "learning_rate": 1.2827815364967819e-05, + "loss": 0.0343, + "step": 27619 + }, + { + "epoch": 8.53, + "learning_rate": 1.2827335655860893e-05, + "loss": 0.0391, + "step": 27620 + }, + { + "epoch": 8.53, + "learning_rate": 1.2826855939682283e-05, + "loss": 0.0379, + "step": 27621 + }, + { + "epoch": 8.53, + "learning_rate": 1.2826376216433192e-05, + "loss": 0.037, + "step": 27622 + }, + { + "epoch": 8.53, + "learning_rate": 1.282589648611482e-05, + "loss": 0.0367, + "step": 27623 + }, + { + "epoch": 8.53, + "learning_rate": 1.2825416748728363e-05, + "loss": 0.0417, + "step": 27624 + }, + { + "epoch": 8.53, + "learning_rate": 1.2824937004275024e-05, + "loss": 0.0406, + "step": 27625 + }, + { + "epoch": 8.53, + "learning_rate": 1.2824457252756003e-05, + "loss": 0.0382, + "step": 27626 + }, + { + "epoch": 8.53, + "learning_rate": 1.2823977494172498e-05, + "loss": 0.0361, + "step": 27627 + }, + { + "epoch": 8.53, + "learning_rate": 1.2823497728525711e-05, + "loss": 0.0337, + "step": 27628 + }, + { + "epoch": 8.53, + "learning_rate": 1.2823017955816844e-05, + "loss": 0.0317, + "step": 27629 + }, + { + "epoch": 8.53, + "learning_rate": 1.2822538176047087e-05, + "loss": 0.0346, + "step": 27630 + }, + { + "epoch": 8.53, + "learning_rate": 1.2822058389217655e-05, + "loss": 0.0373, + "step": 27631 + }, + { + "epoch": 8.53, + "learning_rate": 1.2821578595329735e-05, + "loss": 0.037, + "step": 27632 + }, + { + "epoch": 8.53, + "learning_rate": 1.2821098794384535e-05, + "loss": 0.0395, + "step": 27633 + }, + { + "epoch": 8.53, + "learning_rate": 1.2820618986383253e-05, + "loss": 0.032, + "step": 27634 + }, + { + "epoch": 8.53, + "learning_rate": 1.2820139171327084e-05, + "loss": 0.0351, + "step": 27635 + }, + { + "epoch": 8.53, + "learning_rate": 1.2819659349217237e-05, + "loss": 0.0375, + "step": 27636 + }, + { + "epoch": 8.53, + "learning_rate": 1.2819179520054907e-05, + "loss": 0.0344, + "step": 27637 + }, + { + "epoch": 8.54, + "learning_rate": 1.2818699683841293e-05, + "loss": 0.0363, + "step": 27638 + }, + { + "epoch": 8.54, + "learning_rate": 1.28182198405776e-05, + "loss": 0.0364, + "step": 27639 + }, + { + "epoch": 8.54, + "learning_rate": 1.2817739990265024e-05, + "loss": 0.0392, + "step": 27640 + }, + { + "epoch": 8.54, + "learning_rate": 1.2817260132904762e-05, + "loss": 0.0362, + "step": 27641 + }, + { + "epoch": 8.54, + "learning_rate": 1.2816780268498024e-05, + "loss": 0.0343, + "step": 27642 + }, + { + "epoch": 8.54, + "learning_rate": 1.2816300397046004e-05, + "loss": 0.0385, + "step": 27643 + }, + { + "epoch": 8.54, + "learning_rate": 1.2815820518549903e-05, + "loss": 0.0348, + "step": 27644 + }, + { + "epoch": 8.54, + "learning_rate": 1.281534063301092e-05, + "loss": 0.0341, + "step": 27645 + }, + { + "epoch": 8.54, + "learning_rate": 1.2814860740430257e-05, + "loss": 0.0377, + "step": 27646 + }, + { + "epoch": 8.54, + "learning_rate": 1.2814380840809113e-05, + "loss": 0.034, + "step": 27647 + }, + { + "epoch": 8.54, + "learning_rate": 1.281390093414869e-05, + "loss": 0.0396, + "step": 27648 + }, + { + "epoch": 8.54, + "learning_rate": 1.2813421020450187e-05, + "loss": 0.0386, + "step": 27649 + }, + { + "epoch": 8.54, + "learning_rate": 1.2812941099714807e-05, + "loss": 0.0381, + "step": 27650 + }, + { + "epoch": 8.54, + "learning_rate": 1.2812461171943746e-05, + "loss": 0.0401, + "step": 27651 + }, + { + "epoch": 8.54, + "learning_rate": 1.2811981237138207e-05, + "loss": 0.0384, + "step": 27652 + }, + { + "epoch": 8.54, + "learning_rate": 1.281150129529939e-05, + "loss": 0.0369, + "step": 27653 + }, + { + "epoch": 8.54, + "learning_rate": 1.2811021346428495e-05, + "loss": 0.0339, + "step": 27654 + }, + { + "epoch": 8.54, + "learning_rate": 1.2810541390526725e-05, + "loss": 0.0378, + "step": 27655 + }, + { + "epoch": 8.54, + "learning_rate": 1.2810061427595277e-05, + "loss": 0.0365, + "step": 27656 + }, + { + "epoch": 8.54, + "learning_rate": 1.2809581457635355e-05, + "loss": 0.0326, + "step": 27657 + }, + { + "epoch": 8.54, + "learning_rate": 1.2809101480648153e-05, + "loss": 0.0378, + "step": 27658 + }, + { + "epoch": 8.54, + "learning_rate": 1.2808621496634879e-05, + "loss": 0.0373, + "step": 27659 + }, + { + "epoch": 8.54, + "learning_rate": 1.2808141505596732e-05, + "loss": 0.0362, + "step": 27660 + }, + { + "epoch": 8.54, + "learning_rate": 1.2807661507534906e-05, + "loss": 0.0367, + "step": 27661 + }, + { + "epoch": 8.54, + "learning_rate": 1.2807181502450611e-05, + "loss": 0.0388, + "step": 27662 + }, + { + "epoch": 8.54, + "learning_rate": 1.2806701490345042e-05, + "loss": 0.0392, + "step": 27663 + }, + { + "epoch": 8.54, + "learning_rate": 1.2806221471219398e-05, + "loss": 0.0389, + "step": 27664 + }, + { + "epoch": 8.54, + "learning_rate": 1.2805741445074884e-05, + "loss": 0.0396, + "step": 27665 + }, + { + "epoch": 8.54, + "learning_rate": 1.2805261411912699e-05, + "loss": 0.0358, + "step": 27666 + }, + { + "epoch": 8.54, + "learning_rate": 1.2804781371734042e-05, + "loss": 0.0347, + "step": 27667 + }, + { + "epoch": 8.54, + "learning_rate": 1.2804301324540118e-05, + "loss": 0.036, + "step": 27668 + }, + { + "epoch": 8.54, + "learning_rate": 1.2803821270332122e-05, + "loss": 0.0404, + "step": 27669 + }, + { + "epoch": 8.55, + "learning_rate": 1.2803341209111263e-05, + "loss": 0.036, + "step": 27670 + }, + { + "epoch": 8.55, + "learning_rate": 1.280286114087873e-05, + "loss": 0.0403, + "step": 27671 + }, + { + "epoch": 8.55, + "learning_rate": 1.2802381065635734e-05, + "loss": 0.0378, + "step": 27672 + }, + { + "epoch": 8.55, + "learning_rate": 1.2801900983383471e-05, + "loss": 0.0412, + "step": 27673 + }, + { + "epoch": 8.55, + "learning_rate": 1.2801420894123141e-05, + "loss": 0.0372, + "step": 27674 + }, + { + "epoch": 8.55, + "learning_rate": 1.2800940797855948e-05, + "loss": 0.0387, + "step": 27675 + }, + { + "epoch": 8.55, + "learning_rate": 1.280046069458309e-05, + "loss": 0.0401, + "step": 27676 + }, + { + "epoch": 8.55, + "learning_rate": 1.2799980584305771e-05, + "loss": 0.0372, + "step": 27677 + }, + { + "epoch": 8.55, + "learning_rate": 1.2799500467025188e-05, + "loss": 0.0373, + "step": 27678 + }, + { + "epoch": 8.55, + "learning_rate": 1.2799020342742545e-05, + "loss": 0.0392, + "step": 27679 + }, + { + "epoch": 8.55, + "learning_rate": 1.279854021145904e-05, + "loss": 0.0384, + "step": 27680 + }, + { + "epoch": 8.55, + "learning_rate": 1.2798060073175877e-05, + "loss": 0.0336, + "step": 27681 + }, + { + "epoch": 8.55, + "learning_rate": 1.2797579927894255e-05, + "loss": 0.0345, + "step": 27682 + }, + { + "epoch": 8.55, + "learning_rate": 1.2797099775615377e-05, + "loss": 0.0388, + "step": 27683 + }, + { + "epoch": 8.55, + "learning_rate": 1.2796619616340438e-05, + "loss": 0.0379, + "step": 27684 + }, + { + "epoch": 8.55, + "learning_rate": 1.2796139450070646e-05, + "loss": 0.037, + "step": 27685 + }, + { + "epoch": 8.55, + "learning_rate": 1.2795659276807199e-05, + "loss": 0.0374, + "step": 27686 + }, + { + "epoch": 8.55, + "learning_rate": 1.2795179096551298e-05, + "loss": 0.0372, + "step": 27687 + }, + { + "epoch": 8.55, + "learning_rate": 1.2794698909304146e-05, + "loss": 0.0413, + "step": 27688 + }, + { + "epoch": 8.55, + "learning_rate": 1.279421871506694e-05, + "loss": 0.039, + "step": 27689 + }, + { + "epoch": 8.55, + "learning_rate": 1.2793738513840884e-05, + "loss": 0.0392, + "step": 27690 + }, + { + "epoch": 8.55, + "learning_rate": 1.279325830562718e-05, + "loss": 0.0358, + "step": 27691 + }, + { + "epoch": 8.55, + "learning_rate": 1.2792778090427025e-05, + "loss": 0.0367, + "step": 27692 + }, + { + "epoch": 8.55, + "learning_rate": 1.2792297868241625e-05, + "loss": 0.0366, + "step": 27693 + }, + { + "epoch": 8.55, + "learning_rate": 1.279181763907218e-05, + "loss": 0.0354, + "step": 27694 + }, + { + "epoch": 8.55, + "learning_rate": 1.2791337402919883e-05, + "loss": 0.036, + "step": 27695 + }, + { + "epoch": 8.55, + "learning_rate": 1.2790857159785949e-05, + "loss": 0.0379, + "step": 27696 + }, + { + "epoch": 8.55, + "learning_rate": 1.2790376909671572e-05, + "loss": 0.0387, + "step": 27697 + }, + { + "epoch": 8.55, + "learning_rate": 1.2789896652577949e-05, + "loss": 0.0415, + "step": 27698 + }, + { + "epoch": 8.55, + "learning_rate": 1.2789416388506288e-05, + "loss": 0.0352, + "step": 27699 + }, + { + "epoch": 8.55, + "learning_rate": 1.2788936117457787e-05, + "loss": 0.0396, + "step": 27700 + }, + { + "epoch": 8.55, + "learning_rate": 1.2788455839433649e-05, + "loss": 0.0373, + "step": 27701 + }, + { + "epoch": 8.55, + "learning_rate": 1.2787975554435075e-05, + "loss": 0.0402, + "step": 27702 + }, + { + "epoch": 8.56, + "learning_rate": 1.2787495262463266e-05, + "loss": 0.0368, + "step": 27703 + }, + { + "epoch": 8.56, + "learning_rate": 1.278701496351942e-05, + "loss": 0.0425, + "step": 27704 + }, + { + "epoch": 8.56, + "learning_rate": 1.2786534657604744e-05, + "loss": 0.0373, + "step": 27705 + }, + { + "epoch": 8.56, + "learning_rate": 1.2786054344720436e-05, + "loss": 0.0362, + "step": 27706 + }, + { + "epoch": 8.56, + "learning_rate": 1.2785574024867695e-05, + "loss": 0.0372, + "step": 27707 + }, + { + "epoch": 8.56, + "learning_rate": 1.2785093698047727e-05, + "loss": 0.0371, + "step": 27708 + }, + { + "epoch": 8.56, + "learning_rate": 1.2784613364261733e-05, + "loss": 0.0338, + "step": 27709 + }, + { + "epoch": 8.56, + "learning_rate": 1.2784133023510914e-05, + "loss": 0.0377, + "step": 27710 + }, + { + "epoch": 8.56, + "learning_rate": 1.278365267579647e-05, + "loss": 0.0363, + "step": 27711 + }, + { + "epoch": 8.56, + "learning_rate": 1.27831723211196e-05, + "loss": 0.0356, + "step": 27712 + }, + { + "epoch": 8.56, + "learning_rate": 1.278269195948151e-05, + "loss": 0.0357, + "step": 27713 + }, + { + "epoch": 8.56, + "learning_rate": 1.2782211590883402e-05, + "loss": 0.0366, + "step": 27714 + }, + { + "epoch": 8.56, + "learning_rate": 1.2781731215326475e-05, + "loss": 0.0375, + "step": 27715 + }, + { + "epoch": 8.56, + "learning_rate": 1.2781250832811929e-05, + "loss": 0.0347, + "step": 27716 + }, + { + "epoch": 8.56, + "learning_rate": 1.2780770443340966e-05, + "loss": 0.0412, + "step": 27717 + }, + { + "epoch": 8.56, + "learning_rate": 1.2780290046914791e-05, + "loss": 0.0375, + "step": 27718 + }, + { + "epoch": 8.56, + "learning_rate": 1.2779809643534607e-05, + "loss": 0.0349, + "step": 27719 + }, + { + "epoch": 8.56, + "learning_rate": 1.2779329233201605e-05, + "loss": 0.0365, + "step": 27720 + }, + { + "epoch": 8.56, + "learning_rate": 1.2778848815917e-05, + "loss": 0.0356, + "step": 27721 + }, + { + "epoch": 8.56, + "learning_rate": 1.2778368391681984e-05, + "loss": 0.0385, + "step": 27722 + }, + { + "epoch": 8.56, + "learning_rate": 1.2777887960497762e-05, + "loss": 0.0362, + "step": 27723 + }, + { + "epoch": 8.56, + "learning_rate": 1.2777407522365537e-05, + "loss": 0.0363, + "step": 27724 + }, + { + "epoch": 8.56, + "learning_rate": 1.2776927077286507e-05, + "loss": 0.0407, + "step": 27725 + }, + { + "epoch": 8.56, + "learning_rate": 1.2776446625261877e-05, + "loss": 0.0361, + "step": 27726 + }, + { + "epoch": 8.56, + "learning_rate": 1.2775966166292849e-05, + "loss": 0.0356, + "step": 27727 + }, + { + "epoch": 8.56, + "learning_rate": 1.2775485700380621e-05, + "loss": 0.0376, + "step": 27728 + }, + { + "epoch": 8.56, + "learning_rate": 1.2775005227526398e-05, + "loss": 0.0369, + "step": 27729 + }, + { + "epoch": 8.56, + "learning_rate": 1.277452474773138e-05, + "loss": 0.0409, + "step": 27730 + }, + { + "epoch": 8.56, + "learning_rate": 1.2774044260996772e-05, + "loss": 0.0383, + "step": 27731 + }, + { + "epoch": 8.56, + "learning_rate": 1.2773563767323772e-05, + "loss": 0.0352, + "step": 27732 + }, + { + "epoch": 8.56, + "learning_rate": 1.2773083266713582e-05, + "loss": 0.037, + "step": 27733 + }, + { + "epoch": 8.56, + "learning_rate": 1.2772602759167405e-05, + "loss": 0.0368, + "step": 27734 + }, + { + "epoch": 8.57, + "learning_rate": 1.2772122244686442e-05, + "loss": 0.0424, + "step": 27735 + }, + { + "epoch": 8.57, + "learning_rate": 1.27716417232719e-05, + "loss": 0.0419, + "step": 27736 + }, + { + "epoch": 8.57, + "learning_rate": 1.2771161194924972e-05, + "loss": 0.0366, + "step": 27737 + }, + { + "epoch": 8.57, + "learning_rate": 1.2770680659646865e-05, + "loss": 0.0366, + "step": 27738 + }, + { + "epoch": 8.57, + "learning_rate": 1.2770200117438782e-05, + "loss": 0.0391, + "step": 27739 + }, + { + "epoch": 8.57, + "learning_rate": 1.2769719568301924e-05, + "loss": 0.0355, + "step": 27740 + }, + { + "epoch": 8.57, + "learning_rate": 1.2769239012237491e-05, + "loss": 0.0368, + "step": 27741 + }, + { + "epoch": 8.57, + "learning_rate": 1.2768758449246687e-05, + "loss": 0.0357, + "step": 27742 + }, + { + "epoch": 8.57, + "learning_rate": 1.276827787933071e-05, + "loss": 0.0421, + "step": 27743 + }, + { + "epoch": 8.57, + "learning_rate": 1.2767797302490768e-05, + "loss": 0.0421, + "step": 27744 + }, + { + "epoch": 8.57, + "learning_rate": 1.2767316718728062e-05, + "loss": 0.0397, + "step": 27745 + }, + { + "epoch": 8.57, + "learning_rate": 1.2766836128043787e-05, + "loss": 0.0353, + "step": 27746 + }, + { + "epoch": 8.57, + "learning_rate": 1.2766355530439156e-05, + "loss": 0.0368, + "step": 27747 + }, + { + "epoch": 8.57, + "learning_rate": 1.2765874925915362e-05, + "loss": 0.0349, + "step": 27748 + }, + { + "epoch": 8.57, + "learning_rate": 1.2765394314473608e-05, + "loss": 0.0349, + "step": 27749 + }, + { + "epoch": 8.57, + "learning_rate": 1.2764913696115104e-05, + "loss": 0.0359, + "step": 27750 + }, + { + "epoch": 8.57, + "learning_rate": 1.2764433070841041e-05, + "loss": 0.0372, + "step": 27751 + }, + { + "epoch": 8.57, + "learning_rate": 1.2763952438652631e-05, + "loss": 0.0353, + "step": 27752 + }, + { + "epoch": 8.57, + "learning_rate": 1.276347179955107e-05, + "loss": 0.0369, + "step": 27753 + }, + { + "epoch": 8.57, + "learning_rate": 1.2762991153537561e-05, + "loss": 0.0349, + "step": 27754 + }, + { + "epoch": 8.57, + "learning_rate": 1.276251050061331e-05, + "loss": 0.0367, + "step": 27755 + }, + { + "epoch": 8.57, + "learning_rate": 1.2762029840779513e-05, + "loss": 0.039, + "step": 27756 + }, + { + "epoch": 8.57, + "learning_rate": 1.2761549174037378e-05, + "loss": 0.0375, + "step": 27757 + }, + { + "epoch": 8.57, + "learning_rate": 1.2761068500388105e-05, + "loss": 0.0421, + "step": 27758 + }, + { + "epoch": 8.57, + "learning_rate": 1.2760587819832895e-05, + "loss": 0.0327, + "step": 27759 + }, + { + "epoch": 8.57, + "learning_rate": 1.276010713237295e-05, + "loss": 0.0385, + "step": 27760 + }, + { + "epoch": 8.57, + "learning_rate": 1.2759626438009475e-05, + "loss": 0.0375, + "step": 27761 + }, + { + "epoch": 8.57, + "learning_rate": 1.2759145736743671e-05, + "loss": 0.0369, + "step": 27762 + }, + { + "epoch": 8.57, + "learning_rate": 1.275866502857674e-05, + "loss": 0.0344, + "step": 27763 + }, + { + "epoch": 8.57, + "learning_rate": 1.2758184313509888e-05, + "loss": 0.0386, + "step": 27764 + }, + { + "epoch": 8.57, + "learning_rate": 1.2757703591544313e-05, + "loss": 0.032, + "step": 27765 + }, + { + "epoch": 8.57, + "learning_rate": 1.2757222862681214e-05, + "loss": 0.0335, + "step": 27766 + }, + { + "epoch": 8.58, + "learning_rate": 1.27567421269218e-05, + "loss": 0.0351, + "step": 27767 + }, + { + "epoch": 8.58, + "learning_rate": 1.275626138426727e-05, + "loss": 0.0407, + "step": 27768 + }, + { + "epoch": 8.58, + "learning_rate": 1.275578063471883e-05, + "loss": 0.0371, + "step": 27769 + }, + { + "epoch": 8.58, + "learning_rate": 1.2755299878277679e-05, + "loss": 0.0353, + "step": 27770 + }, + { + "epoch": 8.58, + "learning_rate": 1.2754819114945018e-05, + "loss": 0.0332, + "step": 27771 + }, + { + "epoch": 8.58, + "learning_rate": 1.2754338344722055e-05, + "loss": 0.0363, + "step": 27772 + }, + { + "epoch": 8.58, + "learning_rate": 1.275385756760999e-05, + "loss": 0.0349, + "step": 27773 + }, + { + "epoch": 8.58, + "learning_rate": 1.275337678361002e-05, + "loss": 0.0369, + "step": 27774 + }, + { + "epoch": 8.58, + "learning_rate": 1.275289599272336e-05, + "loss": 0.0378, + "step": 27775 + }, + { + "epoch": 8.58, + "learning_rate": 1.2752415194951202e-05, + "loss": 0.0368, + "step": 27776 + }, + { + "epoch": 8.58, + "learning_rate": 1.2751934390294747e-05, + "loss": 0.0375, + "step": 27777 + }, + { + "epoch": 8.58, + "learning_rate": 1.2751453578755208e-05, + "loss": 0.0363, + "step": 27778 + }, + { + "epoch": 8.58, + "learning_rate": 1.2750972760333779e-05, + "loss": 0.0372, + "step": 27779 + }, + { + "epoch": 8.58, + "learning_rate": 1.2750491935031666e-05, + "loss": 0.0347, + "step": 27780 + }, + { + "epoch": 8.58, + "learning_rate": 1.2750011102850073e-05, + "loss": 0.0363, + "step": 27781 + }, + { + "epoch": 8.58, + "learning_rate": 1.2749530263790196e-05, + "loss": 0.0419, + "step": 27782 + }, + { + "epoch": 8.58, + "learning_rate": 1.2749049417853247e-05, + "loss": 0.0324, + "step": 27783 + }, + { + "epoch": 8.58, + "learning_rate": 1.2748568565040422e-05, + "loss": 0.0346, + "step": 27784 + }, + { + "epoch": 8.58, + "learning_rate": 1.2748087705352924e-05, + "loss": 0.0395, + "step": 27785 + }, + { + "epoch": 8.58, + "learning_rate": 1.2747606838791962e-05, + "loss": 0.04, + "step": 27786 + }, + { + "epoch": 8.58, + "learning_rate": 1.2747125965358729e-05, + "loss": 0.0342, + "step": 27787 + }, + { + "epoch": 8.58, + "learning_rate": 1.2746645085054436e-05, + "loss": 0.0346, + "step": 27788 + }, + { + "epoch": 8.58, + "learning_rate": 1.2746164197880281e-05, + "loss": 0.0384, + "step": 27789 + }, + { + "epoch": 8.58, + "learning_rate": 1.274568330383747e-05, + "loss": 0.0364, + "step": 27790 + }, + { + "epoch": 8.58, + "learning_rate": 1.2745202402927203e-05, + "loss": 0.0357, + "step": 27791 + }, + { + "epoch": 8.58, + "learning_rate": 1.2744721495150684e-05, + "loss": 0.0325, + "step": 27792 + }, + { + "epoch": 8.58, + "learning_rate": 1.2744240580509118e-05, + "loss": 0.0359, + "step": 27793 + }, + { + "epoch": 8.58, + "learning_rate": 1.2743759659003704e-05, + "loss": 0.0367, + "step": 27794 + }, + { + "epoch": 8.58, + "learning_rate": 1.2743278730635647e-05, + "loss": 0.0407, + "step": 27795 + }, + { + "epoch": 8.58, + "learning_rate": 1.2742797795406151e-05, + "loss": 0.0345, + "step": 27796 + }, + { + "epoch": 8.58, + "learning_rate": 1.2742316853316416e-05, + "loss": 0.0358, + "step": 27797 + }, + { + "epoch": 8.58, + "learning_rate": 1.2741835904367645e-05, + "loss": 0.036, + "step": 27798 + }, + { + "epoch": 8.58, + "learning_rate": 1.2741354948561044e-05, + "loss": 0.0376, + "step": 27799 + }, + { + "epoch": 8.59, + "learning_rate": 1.2740873985897815e-05, + "loss": 0.0369, + "step": 27800 + }, + { + "epoch": 8.59, + "learning_rate": 1.2740393016379163e-05, + "loss": 0.0436, + "step": 27801 + }, + { + "epoch": 8.59, + "learning_rate": 1.2739912040006282e-05, + "loss": 0.037, + "step": 27802 + }, + { + "epoch": 8.59, + "learning_rate": 1.2739431056780383e-05, + "loss": 0.0343, + "step": 27803 + }, + { + "epoch": 8.59, + "learning_rate": 1.2738950066702672e-05, + "loss": 0.0366, + "step": 27804 + }, + { + "epoch": 8.59, + "learning_rate": 1.273846906977434e-05, + "loss": 0.0347, + "step": 27805 + }, + { + "epoch": 8.59, + "learning_rate": 1.2737988065996602e-05, + "loss": 0.0404, + "step": 27806 + }, + { + "epoch": 8.59, + "learning_rate": 1.2737507055370654e-05, + "loss": 0.0428, + "step": 27807 + }, + { + "epoch": 8.59, + "learning_rate": 1.2737026037897704e-05, + "loss": 0.0384, + "step": 27808 + }, + { + "epoch": 8.59, + "learning_rate": 1.2736545013578953e-05, + "loss": 0.0355, + "step": 27809 + }, + { + "epoch": 8.59, + "learning_rate": 1.2736063982415603e-05, + "loss": 0.0397, + "step": 27810 + }, + { + "epoch": 8.59, + "learning_rate": 1.2735582944408856e-05, + "loss": 0.0393, + "step": 27811 + }, + { + "epoch": 8.59, + "learning_rate": 1.2735101899559919e-05, + "loss": 0.0352, + "step": 27812 + }, + { + "epoch": 8.59, + "learning_rate": 1.2734620847869992e-05, + "loss": 0.0372, + "step": 27813 + }, + { + "epoch": 8.59, + "learning_rate": 1.273413978934028e-05, + "loss": 0.0393, + "step": 27814 + }, + { + "epoch": 8.59, + "learning_rate": 1.2733658723971987e-05, + "loss": 0.0385, + "step": 27815 + }, + { + "epoch": 8.59, + "learning_rate": 1.2733177651766312e-05, + "loss": 0.0333, + "step": 27816 + }, + { + "epoch": 8.59, + "learning_rate": 1.2732696572724463e-05, + "loss": 0.0391, + "step": 27817 + }, + { + "epoch": 8.59, + "learning_rate": 1.2732215486847644e-05, + "loss": 0.0363, + "step": 27818 + }, + { + "epoch": 8.59, + "learning_rate": 1.2731734394137051e-05, + "loss": 0.0374, + "step": 27819 + }, + { + "epoch": 8.59, + "learning_rate": 1.2731253294593894e-05, + "loss": 0.0381, + "step": 27820 + }, + { + "epoch": 8.59, + "learning_rate": 1.2730772188219378e-05, + "loss": 0.0423, + "step": 27821 + }, + { + "epoch": 8.59, + "learning_rate": 1.2730291075014698e-05, + "loss": 0.04, + "step": 27822 + }, + { + "epoch": 8.59, + "learning_rate": 1.2729809954981063e-05, + "loss": 0.0358, + "step": 27823 + }, + { + "epoch": 8.59, + "learning_rate": 1.2729328828119678e-05, + "loss": 0.0388, + "step": 27824 + }, + { + "epoch": 8.59, + "learning_rate": 1.272884769443174e-05, + "loss": 0.0356, + "step": 27825 + }, + { + "epoch": 8.59, + "learning_rate": 1.2728366553918458e-05, + "loss": 0.0399, + "step": 27826 + }, + { + "epoch": 8.59, + "learning_rate": 1.2727885406581035e-05, + "loss": 0.0423, + "step": 27827 + }, + { + "epoch": 8.59, + "learning_rate": 1.272740425242067e-05, + "loss": 0.0384, + "step": 27828 + }, + { + "epoch": 8.59, + "learning_rate": 1.2726923091438575e-05, + "loss": 0.0366, + "step": 27829 + }, + { + "epoch": 8.59, + "learning_rate": 1.2726441923635942e-05, + "loss": 0.0367, + "step": 27830 + }, + { + "epoch": 8.59, + "learning_rate": 1.2725960749013982e-05, + "loss": 0.0355, + "step": 27831 + }, + { + "epoch": 8.6, + "learning_rate": 1.2725479567573897e-05, + "loss": 0.0393, + "step": 27832 + }, + { + "epoch": 8.6, + "learning_rate": 1.272499837931689e-05, + "loss": 0.0341, + "step": 27833 + }, + { + "epoch": 8.6, + "learning_rate": 1.2724517184244167e-05, + "loss": 0.0416, + "step": 27834 + }, + { + "epoch": 8.6, + "learning_rate": 1.2724035982356931e-05, + "loss": 0.036, + "step": 27835 + }, + { + "epoch": 8.6, + "learning_rate": 1.2723554773656379e-05, + "loss": 0.0404, + "step": 27836 + }, + { + "epoch": 8.6, + "learning_rate": 1.2723073558143724e-05, + "loss": 0.0356, + "step": 27837 + }, + { + "epoch": 8.6, + "learning_rate": 1.2722592335820165e-05, + "loss": 0.0401, + "step": 27838 + }, + { + "epoch": 8.6, + "learning_rate": 1.2722111106686905e-05, + "loss": 0.0359, + "step": 27839 + }, + { + "epoch": 8.6, + "learning_rate": 1.272162987074515e-05, + "loss": 0.0358, + "step": 27840 + }, + { + "epoch": 8.6, + "learning_rate": 1.2721148627996098e-05, + "loss": 0.0373, + "step": 27841 + }, + { + "epoch": 8.6, + "learning_rate": 1.2720667378440961e-05, + "loss": 0.0383, + "step": 27842 + }, + { + "epoch": 8.6, + "learning_rate": 1.2720186122080938e-05, + "loss": 0.0396, + "step": 27843 + }, + { + "epoch": 8.6, + "learning_rate": 1.2719704858917232e-05, + "loss": 0.0345, + "step": 27844 + }, + { + "epoch": 8.6, + "learning_rate": 1.2719223588951051e-05, + "loss": 0.0363, + "step": 27845 + }, + { + "epoch": 8.6, + "learning_rate": 1.2718742312183592e-05, + "loss": 0.0337, + "step": 27846 + }, + { + "epoch": 8.6, + "learning_rate": 1.2718261028616066e-05, + "loss": 0.0369, + "step": 27847 + }, + { + "epoch": 8.6, + "learning_rate": 1.2717779738249671e-05, + "loss": 0.0381, + "step": 27848 + }, + { + "epoch": 8.6, + "learning_rate": 1.2717298441085615e-05, + "loss": 0.0375, + "step": 27849 + }, + { + "epoch": 8.6, + "learning_rate": 1.27168171371251e-05, + "loss": 0.0371, + "step": 27850 + }, + { + "epoch": 8.6, + "learning_rate": 1.2716335826369326e-05, + "loss": 0.0386, + "step": 27851 + }, + { + "epoch": 8.6, + "learning_rate": 1.2715854508819505e-05, + "loss": 0.0376, + "step": 27852 + }, + { + "epoch": 8.6, + "learning_rate": 1.2715373184476835e-05, + "loss": 0.0381, + "step": 27853 + }, + { + "epoch": 8.6, + "learning_rate": 1.271489185334252e-05, + "loss": 0.0369, + "step": 27854 + }, + { + "epoch": 8.6, + "learning_rate": 1.271441051541777e-05, + "loss": 0.0383, + "step": 27855 + }, + { + "epoch": 8.6, + "learning_rate": 1.2713929170703781e-05, + "loss": 0.0364, + "step": 27856 + }, + { + "epoch": 8.6, + "learning_rate": 1.2713447819201758e-05, + "loss": 0.0354, + "step": 27857 + }, + { + "epoch": 8.6, + "learning_rate": 1.2712966460912913e-05, + "loss": 0.0404, + "step": 27858 + }, + { + "epoch": 8.6, + "learning_rate": 1.2712485095838435e-05, + "loss": 0.0374, + "step": 27859 + }, + { + "epoch": 8.6, + "learning_rate": 1.2712003723979548e-05, + "loss": 0.0354, + "step": 27860 + }, + { + "epoch": 8.6, + "learning_rate": 1.2711522345337439e-05, + "loss": 0.0361, + "step": 27861 + }, + { + "epoch": 8.6, + "learning_rate": 1.2711040959913317e-05, + "loss": 0.0358, + "step": 27862 + }, + { + "epoch": 8.6, + "learning_rate": 1.271055956770839e-05, + "loss": 0.0387, + "step": 27863 + }, + { + "epoch": 8.6, + "learning_rate": 1.2710078168723854e-05, + "loss": 0.0376, + "step": 27864 + }, + { + "epoch": 8.61, + "learning_rate": 1.2709596762960924e-05, + "loss": 0.0408, + "step": 27865 + }, + { + "epoch": 8.61, + "learning_rate": 1.2709115350420797e-05, + "loss": 0.0398, + "step": 27866 + }, + { + "epoch": 8.61, + "learning_rate": 1.2708633931104676e-05, + "loss": 0.0367, + "step": 27867 + }, + { + "epoch": 8.61, + "learning_rate": 1.270815250501377e-05, + "loss": 0.0369, + "step": 27868 + }, + { + "epoch": 8.61, + "learning_rate": 1.2707671072149282e-05, + "loss": 0.0374, + "step": 27869 + }, + { + "epoch": 8.61, + "learning_rate": 1.2707189632512411e-05, + "loss": 0.0385, + "step": 27870 + }, + { + "epoch": 8.61, + "learning_rate": 1.2706708186104369e-05, + "loss": 0.0413, + "step": 27871 + }, + { + "epoch": 8.61, + "learning_rate": 1.2706226732926352e-05, + "loss": 0.0361, + "step": 27872 + }, + { + "epoch": 8.61, + "learning_rate": 1.270574527297957e-05, + "loss": 0.0431, + "step": 27873 + }, + { + "epoch": 8.61, + "learning_rate": 1.2705263806265227e-05, + "loss": 0.0363, + "step": 27874 + }, + { + "epoch": 8.61, + "learning_rate": 1.2704782332784525e-05, + "loss": 0.0365, + "step": 27875 + }, + { + "epoch": 8.61, + "learning_rate": 1.2704300852538666e-05, + "loss": 0.04, + "step": 27876 + }, + { + "epoch": 8.61, + "learning_rate": 1.270381936552886e-05, + "loss": 0.0435, + "step": 27877 + }, + { + "epoch": 8.61, + "learning_rate": 1.2703337871756311e-05, + "loss": 0.0414, + "step": 27878 + }, + { + "epoch": 8.61, + "learning_rate": 1.2702856371222216e-05, + "loss": 0.038, + "step": 27879 + }, + { + "epoch": 8.61, + "learning_rate": 1.270237486392779e-05, + "loss": 0.037, + "step": 27880 + }, + { + "epoch": 8.61, + "learning_rate": 1.2701893349874225e-05, + "loss": 0.0383, + "step": 27881 + }, + { + "epoch": 8.61, + "learning_rate": 1.2701411829062735e-05, + "loss": 0.0335, + "step": 27882 + }, + { + "epoch": 8.61, + "learning_rate": 1.2700930301494524e-05, + "loss": 0.0426, + "step": 27883 + }, + { + "epoch": 8.61, + "learning_rate": 1.270044876717079e-05, + "loss": 0.0396, + "step": 27884 + }, + { + "epoch": 8.61, + "learning_rate": 1.2699967226092742e-05, + "loss": 0.0373, + "step": 27885 + }, + { + "epoch": 8.61, + "learning_rate": 1.2699485678261587e-05, + "loss": 0.0406, + "step": 27886 + }, + { + "epoch": 8.61, + "learning_rate": 1.269900412367852e-05, + "loss": 0.0339, + "step": 27887 + }, + { + "epoch": 8.61, + "learning_rate": 1.2698522562344758e-05, + "loss": 0.0392, + "step": 27888 + }, + { + "epoch": 8.61, + "learning_rate": 1.2698040994261494e-05, + "loss": 0.0364, + "step": 27889 + }, + { + "epoch": 8.61, + "learning_rate": 1.2697559419429937e-05, + "loss": 0.0366, + "step": 27890 + }, + { + "epoch": 8.61, + "learning_rate": 1.2697077837851294e-05, + "loss": 0.0402, + "step": 27891 + }, + { + "epoch": 8.61, + "learning_rate": 1.2696596249526767e-05, + "loss": 0.0387, + "step": 27892 + }, + { + "epoch": 8.61, + "learning_rate": 1.269611465445756e-05, + "loss": 0.0369, + "step": 27893 + }, + { + "epoch": 8.61, + "learning_rate": 1.269563305264488e-05, + "loss": 0.0366, + "step": 27894 + }, + { + "epoch": 8.61, + "learning_rate": 1.269515144408993e-05, + "loss": 0.0372, + "step": 27895 + }, + { + "epoch": 8.61, + "learning_rate": 1.2694669828793913e-05, + "loss": 0.0371, + "step": 27896 + }, + { + "epoch": 8.62, + "learning_rate": 1.2694188206758039e-05, + "loss": 0.0411, + "step": 27897 + }, + { + "epoch": 8.62, + "learning_rate": 1.2693706577983502e-05, + "loss": 0.0385, + "step": 27898 + }, + { + "epoch": 8.62, + "learning_rate": 1.269322494247152e-05, + "loss": 0.0399, + "step": 27899 + }, + { + "epoch": 8.62, + "learning_rate": 1.2692743300223288e-05, + "loss": 0.0386, + "step": 27900 + }, + { + "epoch": 8.62, + "learning_rate": 1.2692261651240016e-05, + "loss": 0.0381, + "step": 27901 + }, + { + "epoch": 8.62, + "learning_rate": 1.2691779995522905e-05, + "loss": 0.0356, + "step": 27902 + }, + { + "epoch": 8.62, + "learning_rate": 1.2691298333073161e-05, + "loss": 0.0367, + "step": 27903 + }, + { + "epoch": 8.62, + "learning_rate": 1.2690816663891992e-05, + "loss": 0.0377, + "step": 27904 + }, + { + "epoch": 8.62, + "learning_rate": 1.2690334987980598e-05, + "loss": 0.0359, + "step": 27905 + }, + { + "epoch": 8.62, + "learning_rate": 1.2689853305340183e-05, + "loss": 0.041, + "step": 27906 + }, + { + "epoch": 8.62, + "learning_rate": 1.2689371615971958e-05, + "loss": 0.0386, + "step": 27907 + }, + { + "epoch": 8.62, + "learning_rate": 1.2688889919877121e-05, + "loss": 0.038, + "step": 27908 + }, + { + "epoch": 8.62, + "learning_rate": 1.2688408217056884e-05, + "loss": 0.0385, + "step": 27909 + }, + { + "epoch": 8.62, + "learning_rate": 1.2687926507512442e-05, + "loss": 0.0351, + "step": 27910 + }, + { + "epoch": 8.62, + "learning_rate": 1.268744479124501e-05, + "loss": 0.0392, + "step": 27911 + }, + { + "epoch": 8.62, + "learning_rate": 1.2686963068255786e-05, + "loss": 0.0397, + "step": 27912 + }, + { + "epoch": 8.62, + "learning_rate": 1.2686481338545977e-05, + "loss": 0.0368, + "step": 27913 + }, + { + "epoch": 8.62, + "learning_rate": 1.2685999602116792e-05, + "loss": 0.0363, + "step": 27914 + }, + { + "epoch": 8.62, + "learning_rate": 1.2685517858969428e-05, + "loss": 0.0409, + "step": 27915 + }, + { + "epoch": 8.62, + "learning_rate": 1.2685036109105096e-05, + "loss": 0.038, + "step": 27916 + }, + { + "epoch": 8.62, + "learning_rate": 1.2684554352525e-05, + "loss": 0.0375, + "step": 27917 + }, + { + "epoch": 8.62, + "learning_rate": 1.2684072589230341e-05, + "loss": 0.0347, + "step": 27918 + }, + { + "epoch": 8.62, + "learning_rate": 1.2683590819222329e-05, + "loss": 0.0355, + "step": 27919 + }, + { + "epoch": 8.62, + "learning_rate": 1.2683109042502167e-05, + "loss": 0.0383, + "step": 27920 + }, + { + "epoch": 8.62, + "learning_rate": 1.2682627259071056e-05, + "loss": 0.0381, + "step": 27921 + }, + { + "epoch": 8.62, + "learning_rate": 1.2682145468930211e-05, + "loss": 0.0351, + "step": 27922 + }, + { + "epoch": 8.62, + "learning_rate": 1.2681663672080828e-05, + "loss": 0.0391, + "step": 27923 + }, + { + "epoch": 8.62, + "learning_rate": 1.2681181868524116e-05, + "loss": 0.0362, + "step": 27924 + }, + { + "epoch": 8.62, + "learning_rate": 1.2680700058261278e-05, + "loss": 0.0363, + "step": 27925 + }, + { + "epoch": 8.62, + "learning_rate": 1.268021824129352e-05, + "loss": 0.0357, + "step": 27926 + }, + { + "epoch": 8.62, + "learning_rate": 1.2679736417622048e-05, + "loss": 0.0372, + "step": 27927 + }, + { + "epoch": 8.62, + "learning_rate": 1.2679254587248066e-05, + "loss": 0.0354, + "step": 27928 + }, + { + "epoch": 8.63, + "learning_rate": 1.2678772750172778e-05, + "loss": 0.0388, + "step": 27929 + }, + { + "epoch": 8.63, + "learning_rate": 1.2678290906397395e-05, + "loss": 0.039, + "step": 27930 + }, + { + "epoch": 8.63, + "learning_rate": 1.2677809055923116e-05, + "loss": 0.0359, + "step": 27931 + }, + { + "epoch": 8.63, + "learning_rate": 1.2677327198751148e-05, + "loss": 0.0396, + "step": 27932 + }, + { + "epoch": 8.63, + "learning_rate": 1.2676845334882695e-05, + "loss": 0.0407, + "step": 27933 + }, + { + "epoch": 8.63, + "learning_rate": 1.2676363464318965e-05, + "loss": 0.0365, + "step": 27934 + }, + { + "epoch": 8.63, + "learning_rate": 1.2675881587061161e-05, + "loss": 0.0376, + "step": 27935 + }, + { + "epoch": 8.63, + "learning_rate": 1.2675399703110492e-05, + "loss": 0.0357, + "step": 27936 + }, + { + "epoch": 8.63, + "learning_rate": 1.2674917812468154e-05, + "loss": 0.0392, + "step": 27937 + }, + { + "epoch": 8.63, + "learning_rate": 1.2674435915135366e-05, + "loss": 0.038, + "step": 27938 + }, + { + "epoch": 8.63, + "learning_rate": 1.2673954011113321e-05, + "loss": 0.0381, + "step": 27939 + }, + { + "epoch": 8.63, + "learning_rate": 1.2673472100403235e-05, + "loss": 0.0375, + "step": 27940 + }, + { + "epoch": 8.63, + "learning_rate": 1.26729901830063e-05, + "loss": 0.0382, + "step": 27941 + }, + { + "epoch": 8.63, + "learning_rate": 1.2672508258923733e-05, + "loss": 0.0406, + "step": 27942 + }, + { + "epoch": 8.63, + "learning_rate": 1.2672026328156736e-05, + "loss": 0.0372, + "step": 27943 + }, + { + "epoch": 8.63, + "learning_rate": 1.2671544390706511e-05, + "loss": 0.038, + "step": 27944 + }, + { + "epoch": 8.63, + "learning_rate": 1.2671062446574271e-05, + "loss": 0.0376, + "step": 27945 + }, + { + "epoch": 8.63, + "learning_rate": 1.267058049576121e-05, + "loss": 0.035, + "step": 27946 + }, + { + "epoch": 8.63, + "learning_rate": 1.2670098538268545e-05, + "loss": 0.038, + "step": 27947 + }, + { + "epoch": 8.63, + "learning_rate": 1.2669616574097478e-05, + "loss": 0.0394, + "step": 27948 + }, + { + "epoch": 8.63, + "learning_rate": 1.266913460324921e-05, + "loss": 0.0329, + "step": 27949 + }, + { + "epoch": 8.63, + "learning_rate": 1.2668652625724951e-05, + "loss": 0.0373, + "step": 27950 + }, + { + "epoch": 8.63, + "learning_rate": 1.2668170641525905e-05, + "loss": 0.0386, + "step": 27951 + }, + { + "epoch": 8.63, + "learning_rate": 1.2667688650653274e-05, + "loss": 0.0383, + "step": 27952 + }, + { + "epoch": 8.63, + "learning_rate": 1.2667206653108272e-05, + "loss": 0.0365, + "step": 27953 + }, + { + "epoch": 8.63, + "learning_rate": 1.2666724648892097e-05, + "loss": 0.0372, + "step": 27954 + }, + { + "epoch": 8.63, + "learning_rate": 1.2666242638005959e-05, + "loss": 0.0362, + "step": 27955 + }, + { + "epoch": 8.63, + "learning_rate": 1.266576062045106e-05, + "loss": 0.0416, + "step": 27956 + }, + { + "epoch": 8.63, + "learning_rate": 1.2665278596228608e-05, + "loss": 0.0426, + "step": 27957 + }, + { + "epoch": 8.63, + "learning_rate": 1.2664796565339808e-05, + "loss": 0.0349, + "step": 27958 + }, + { + "epoch": 8.63, + "learning_rate": 1.2664314527785865e-05, + "loss": 0.0348, + "step": 27959 + }, + { + "epoch": 8.63, + "learning_rate": 1.2663832483567989e-05, + "loss": 0.0395, + "step": 27960 + }, + { + "epoch": 8.63, + "learning_rate": 1.2663350432687379e-05, + "loss": 0.0377, + "step": 27961 + }, + { + "epoch": 8.64, + "learning_rate": 1.2662868375145244e-05, + "loss": 0.037, + "step": 27962 + }, + { + "epoch": 8.64, + "learning_rate": 1.2662386310942789e-05, + "loss": 0.035, + "step": 27963 + }, + { + "epoch": 8.64, + "learning_rate": 1.2661904240081222e-05, + "loss": 0.0366, + "step": 27964 + }, + { + "epoch": 8.64, + "learning_rate": 1.2661422162561746e-05, + "loss": 0.0412, + "step": 27965 + }, + { + "epoch": 8.64, + "learning_rate": 1.2660940078385568e-05, + "loss": 0.0372, + "step": 27966 + }, + { + "epoch": 8.64, + "learning_rate": 1.2660457987553893e-05, + "loss": 0.0394, + "step": 27967 + }, + { + "epoch": 8.64, + "learning_rate": 1.265997589006793e-05, + "loss": 0.0342, + "step": 27968 + }, + { + "epoch": 8.64, + "learning_rate": 1.2659493785928879e-05, + "loss": 0.0371, + "step": 27969 + }, + { + "epoch": 8.64, + "learning_rate": 1.2659011675137948e-05, + "loss": 0.0389, + "step": 27970 + }, + { + "epoch": 8.64, + "learning_rate": 1.2658529557696349e-05, + "loss": 0.0377, + "step": 27971 + }, + { + "epoch": 8.64, + "learning_rate": 1.2658047433605276e-05, + "loss": 0.0351, + "step": 27972 + }, + { + "epoch": 8.64, + "learning_rate": 1.265756530286595e-05, + "loss": 0.0378, + "step": 27973 + }, + { + "epoch": 8.64, + "learning_rate": 1.265708316547956e-05, + "loss": 0.0381, + "step": 27974 + }, + { + "epoch": 8.64, + "learning_rate": 1.2656601021447323e-05, + "loss": 0.0389, + "step": 27975 + }, + { + "epoch": 8.64, + "learning_rate": 1.2656118870770444e-05, + "loss": 0.0391, + "step": 27976 + }, + { + "epoch": 8.64, + "learning_rate": 1.2655636713450129e-05, + "loss": 0.0382, + "step": 27977 + }, + { + "epoch": 8.64, + "learning_rate": 1.2655154549487579e-05, + "loss": 0.0351, + "step": 27978 + }, + { + "epoch": 8.64, + "learning_rate": 1.2654672378884003e-05, + "loss": 0.0399, + "step": 27979 + }, + { + "epoch": 8.64, + "learning_rate": 1.2654190201640605e-05, + "loss": 0.0403, + "step": 27980 + }, + { + "epoch": 8.64, + "learning_rate": 1.2653708017758599e-05, + "loss": 0.0376, + "step": 27981 + }, + { + "epoch": 8.64, + "learning_rate": 1.2653225827239181e-05, + "loss": 0.0358, + "step": 27982 + }, + { + "epoch": 8.64, + "learning_rate": 1.2652743630083563e-05, + "loss": 0.0407, + "step": 27983 + }, + { + "epoch": 8.64, + "learning_rate": 1.2652261426292948e-05, + "loss": 0.0384, + "step": 27984 + }, + { + "epoch": 8.64, + "learning_rate": 1.2651779215868548e-05, + "loss": 0.0392, + "step": 27985 + }, + { + "epoch": 8.64, + "learning_rate": 1.2651296998811559e-05, + "loss": 0.0386, + "step": 27986 + }, + { + "epoch": 8.64, + "learning_rate": 1.2650814775123195e-05, + "loss": 0.0337, + "step": 27987 + }, + { + "epoch": 8.64, + "learning_rate": 1.265033254480466e-05, + "loss": 0.0352, + "step": 27988 + }, + { + "epoch": 8.64, + "learning_rate": 1.264985030785716e-05, + "loss": 0.039, + "step": 27989 + }, + { + "epoch": 8.64, + "learning_rate": 1.26493680642819e-05, + "loss": 0.0356, + "step": 27990 + }, + { + "epoch": 8.64, + "learning_rate": 1.2648885814080087e-05, + "loss": 0.0372, + "step": 27991 + }, + { + "epoch": 8.64, + "learning_rate": 1.2648403557252929e-05, + "loss": 0.0462, + "step": 27992 + }, + { + "epoch": 8.64, + "learning_rate": 1.264792129380163e-05, + "loss": 0.036, + "step": 27993 + }, + { + "epoch": 8.65, + "learning_rate": 1.2647439023727399e-05, + "loss": 0.0333, + "step": 27994 + }, + { + "epoch": 8.65, + "learning_rate": 1.2646956747031434e-05, + "loss": 0.0379, + "step": 27995 + }, + { + "epoch": 8.65, + "learning_rate": 1.2646474463714954e-05, + "loss": 0.0366, + "step": 27996 + }, + { + "epoch": 8.65, + "learning_rate": 1.2645992173779153e-05, + "loss": 0.0414, + "step": 27997 + }, + { + "epoch": 8.65, + "learning_rate": 1.2645509877225246e-05, + "loss": 0.0374, + "step": 27998 + }, + { + "epoch": 8.65, + "learning_rate": 1.264502757405444e-05, + "loss": 0.0381, + "step": 27999 + }, + { + "epoch": 8.65, + "learning_rate": 1.264454526426793e-05, + "loss": 0.0381, + "step": 28000 + }, + { + "epoch": 8.65, + "learning_rate": 1.2644062947866935e-05, + "loss": 0.0359, + "step": 28001 + }, + { + "epoch": 8.65, + "learning_rate": 1.2643580624852657e-05, + "loss": 0.0399, + "step": 28002 + }, + { + "epoch": 8.65, + "learning_rate": 1.2643098295226297e-05, + "loss": 0.0364, + "step": 28003 + }, + { + "epoch": 8.65, + "learning_rate": 1.264261595898907e-05, + "loss": 0.038, + "step": 28004 + }, + { + "epoch": 8.65, + "learning_rate": 1.2642133616142178e-05, + "loss": 0.0367, + "step": 28005 + }, + { + "epoch": 8.65, + "learning_rate": 1.2641651266686825e-05, + "loss": 0.0378, + "step": 28006 + }, + { + "epoch": 8.65, + "learning_rate": 1.2641168910624226e-05, + "loss": 0.0393, + "step": 28007 + }, + { + "epoch": 8.65, + "learning_rate": 1.2640686547955579e-05, + "loss": 0.0406, + "step": 28008 + }, + { + "epoch": 8.65, + "learning_rate": 1.2640204178682092e-05, + "loss": 0.033, + "step": 28009 + }, + { + "epoch": 8.65, + "learning_rate": 1.2639721802804974e-05, + "loss": 0.0336, + "step": 28010 + }, + { + "epoch": 8.65, + "learning_rate": 1.2639239420325429e-05, + "loss": 0.0405, + "step": 28011 + }, + { + "epoch": 8.65, + "learning_rate": 1.2638757031244666e-05, + "loss": 0.0378, + "step": 28012 + }, + { + "epoch": 8.65, + "learning_rate": 1.263827463556389e-05, + "loss": 0.0384, + "step": 28013 + }, + { + "epoch": 8.65, + "learning_rate": 1.263779223328431e-05, + "loss": 0.0383, + "step": 28014 + }, + { + "epoch": 8.65, + "learning_rate": 1.2637309824407127e-05, + "loss": 0.0398, + "step": 28015 + }, + { + "epoch": 8.65, + "learning_rate": 1.2636827408933554e-05, + "loss": 0.0408, + "step": 28016 + }, + { + "epoch": 8.65, + "learning_rate": 1.2636344986864792e-05, + "loss": 0.0366, + "step": 28017 + }, + { + "epoch": 8.65, + "learning_rate": 1.2635862558202052e-05, + "loss": 0.0396, + "step": 28018 + }, + { + "epoch": 8.65, + "learning_rate": 1.2635380122946539e-05, + "loss": 0.0381, + "step": 28019 + }, + { + "epoch": 8.65, + "learning_rate": 1.263489768109946e-05, + "loss": 0.0426, + "step": 28020 + }, + { + "epoch": 8.65, + "learning_rate": 1.263441523266202e-05, + "loss": 0.04, + "step": 28021 + }, + { + "epoch": 8.65, + "learning_rate": 1.2633932777635431e-05, + "loss": 0.0365, + "step": 28022 + }, + { + "epoch": 8.65, + "learning_rate": 1.263345031602089e-05, + "loss": 0.0364, + "step": 28023 + }, + { + "epoch": 8.65, + "learning_rate": 1.2632967847819613e-05, + "loss": 0.0383, + "step": 28024 + }, + { + "epoch": 8.65, + "learning_rate": 1.2632485373032804e-05, + "loss": 0.0404, + "step": 28025 + }, + { + "epoch": 8.66, + "learning_rate": 1.2632002891661666e-05, + "loss": 0.0411, + "step": 28026 + }, + { + "epoch": 8.66, + "learning_rate": 1.263152040370741e-05, + "loss": 0.0378, + "step": 28027 + }, + { + "epoch": 8.66, + "learning_rate": 1.263103790917124e-05, + "loss": 0.0379, + "step": 28028 + }, + { + "epoch": 8.66, + "learning_rate": 1.2630555408054366e-05, + "loss": 0.036, + "step": 28029 + }, + { + "epoch": 8.66, + "learning_rate": 1.2630072900357994e-05, + "loss": 0.0441, + "step": 28030 + }, + { + "epoch": 8.66, + "learning_rate": 1.2629590386083326e-05, + "loss": 0.0387, + "step": 28031 + }, + { + "epoch": 8.66, + "learning_rate": 1.2629107865231579e-05, + "loss": 0.0382, + "step": 28032 + }, + { + "epoch": 8.66, + "learning_rate": 1.262862533780395e-05, + "loss": 0.0359, + "step": 28033 + }, + { + "epoch": 8.66, + "learning_rate": 1.2628142803801648e-05, + "loss": 0.0393, + "step": 28034 + }, + { + "epoch": 8.66, + "learning_rate": 1.2627660263225885e-05, + "loss": 0.0417, + "step": 28035 + }, + { + "epoch": 8.66, + "learning_rate": 1.2627177716077863e-05, + "loss": 0.0384, + "step": 28036 + }, + { + "epoch": 8.66, + "learning_rate": 1.2626695162358791e-05, + "loss": 0.037, + "step": 28037 + }, + { + "epoch": 8.66, + "learning_rate": 1.2626212602069874e-05, + "loss": 0.0399, + "step": 28038 + }, + { + "epoch": 8.66, + "learning_rate": 1.262573003521232e-05, + "loss": 0.0381, + "step": 28039 + }, + { + "epoch": 8.66, + "learning_rate": 1.2625247461787337e-05, + "loss": 0.0353, + "step": 28040 + }, + { + "epoch": 8.66, + "learning_rate": 1.2624764881796133e-05, + "loss": 0.0355, + "step": 28041 + }, + { + "epoch": 8.66, + "learning_rate": 1.2624282295239911e-05, + "loss": 0.0383, + "step": 28042 + }, + { + "epoch": 8.66, + "learning_rate": 1.262379970211988e-05, + "loss": 0.0405, + "step": 28043 + }, + { + "epoch": 8.66, + "learning_rate": 1.2623317102437249e-05, + "loss": 0.0372, + "step": 28044 + }, + { + "epoch": 8.66, + "learning_rate": 1.2622834496193224e-05, + "loss": 0.0391, + "step": 28045 + }, + { + "epoch": 8.66, + "learning_rate": 1.262235188338901e-05, + "loss": 0.0357, + "step": 28046 + }, + { + "epoch": 8.66, + "learning_rate": 1.2621869264025816e-05, + "loss": 0.0408, + "step": 28047 + }, + { + "epoch": 8.66, + "learning_rate": 1.2621386638104848e-05, + "loss": 0.0394, + "step": 28048 + }, + { + "epoch": 8.66, + "learning_rate": 1.2620904005627317e-05, + "loss": 0.0371, + "step": 28049 + }, + { + "epoch": 8.66, + "learning_rate": 1.2620421366594424e-05, + "loss": 0.0405, + "step": 28050 + }, + { + "epoch": 8.66, + "learning_rate": 1.2619938721007379e-05, + "loss": 0.036, + "step": 28051 + }, + { + "epoch": 8.66, + "learning_rate": 1.261945606886739e-05, + "loss": 0.0365, + "step": 28052 + }, + { + "epoch": 8.66, + "learning_rate": 1.2618973410175668e-05, + "loss": 0.0366, + "step": 28053 + }, + { + "epoch": 8.66, + "learning_rate": 1.2618490744933409e-05, + "loss": 0.0407, + "step": 28054 + }, + { + "epoch": 8.66, + "learning_rate": 1.2618008073141829e-05, + "loss": 0.0396, + "step": 28055 + }, + { + "epoch": 8.66, + "learning_rate": 1.2617525394802137e-05, + "loss": 0.0381, + "step": 28056 + }, + { + "epoch": 8.66, + "learning_rate": 1.2617042709915533e-05, + "loss": 0.0344, + "step": 28057 + }, + { + "epoch": 8.66, + "learning_rate": 1.261656001848323e-05, + "loss": 0.0432, + "step": 28058 + }, + { + "epoch": 8.67, + "learning_rate": 1.2616077320506432e-05, + "loss": 0.0443, + "step": 28059 + }, + { + "epoch": 8.67, + "learning_rate": 1.2615594615986346e-05, + "loss": 0.034, + "step": 28060 + }, + { + "epoch": 8.67, + "learning_rate": 1.2615111904924184e-05, + "loss": 0.0392, + "step": 28061 + }, + { + "epoch": 8.67, + "learning_rate": 1.2614629187321145e-05, + "loss": 0.0361, + "step": 28062 + }, + { + "epoch": 8.67, + "learning_rate": 1.2614146463178447e-05, + "loss": 0.0413, + "step": 28063 + }, + { + "epoch": 8.67, + "learning_rate": 1.2613663732497292e-05, + "loss": 0.0395, + "step": 28064 + }, + { + "epoch": 8.67, + "learning_rate": 1.2613180995278882e-05, + "loss": 0.037, + "step": 28065 + }, + { + "epoch": 8.67, + "learning_rate": 1.2612698251524433e-05, + "loss": 0.0403, + "step": 28066 + }, + { + "epoch": 8.67, + "learning_rate": 1.261221550123515e-05, + "loss": 0.0383, + "step": 28067 + }, + { + "epoch": 8.67, + "learning_rate": 1.261173274441224e-05, + "loss": 0.0363, + "step": 28068 + }, + { + "epoch": 8.67, + "learning_rate": 1.2611249981056908e-05, + "loss": 0.0401, + "step": 28069 + }, + { + "epoch": 8.67, + "learning_rate": 1.2610767211170365e-05, + "loss": 0.0346, + "step": 28070 + }, + { + "epoch": 8.67, + "learning_rate": 1.2610284434753814e-05, + "loss": 0.0406, + "step": 28071 + }, + { + "epoch": 8.67, + "learning_rate": 1.2609801651808469e-05, + "loss": 0.035, + "step": 28072 + }, + { + "epoch": 8.67, + "learning_rate": 1.2609318862335533e-05, + "loss": 0.0399, + "step": 28073 + }, + { + "epoch": 8.67, + "learning_rate": 1.2608836066336214e-05, + "loss": 0.0367, + "step": 28074 + }, + { + "epoch": 8.67, + "learning_rate": 1.260835326381172e-05, + "loss": 0.0389, + "step": 28075 + }, + { + "epoch": 8.67, + "learning_rate": 1.260787045476326e-05, + "loss": 0.0411, + "step": 28076 + }, + { + "epoch": 8.67, + "learning_rate": 1.260738763919204e-05, + "loss": 0.038, + "step": 28077 + }, + { + "epoch": 8.67, + "learning_rate": 1.2606904817099266e-05, + "loss": 0.0416, + "step": 28078 + }, + { + "epoch": 8.67, + "learning_rate": 1.2606421988486151e-05, + "loss": 0.0378, + "step": 28079 + }, + { + "epoch": 8.67, + "learning_rate": 1.2605939153353896e-05, + "loss": 0.0398, + "step": 28080 + }, + { + "epoch": 8.67, + "learning_rate": 1.2605456311703716e-05, + "loss": 0.0374, + "step": 28081 + }, + { + "epoch": 8.67, + "learning_rate": 1.260497346353681e-05, + "loss": 0.0371, + "step": 28082 + }, + { + "epoch": 8.67, + "learning_rate": 1.2604490608854391e-05, + "loss": 0.0377, + "step": 28083 + }, + { + "epoch": 8.67, + "learning_rate": 1.2604007747657669e-05, + "loss": 0.036, + "step": 28084 + }, + { + "epoch": 8.67, + "learning_rate": 1.2603524879947846e-05, + "loss": 0.04, + "step": 28085 + }, + { + "epoch": 8.67, + "learning_rate": 1.2603042005726135e-05, + "loss": 0.0357, + "step": 28086 + }, + { + "epoch": 8.67, + "learning_rate": 1.2602559124993738e-05, + "loss": 0.0389, + "step": 28087 + }, + { + "epoch": 8.67, + "learning_rate": 1.2602076237751866e-05, + "loss": 0.0402, + "step": 28088 + }, + { + "epoch": 8.67, + "learning_rate": 1.2601593344001732e-05, + "loss": 0.0388, + "step": 28089 + }, + { + "epoch": 8.67, + "learning_rate": 1.2601110443744533e-05, + "loss": 0.0435, + "step": 28090 + }, + { + "epoch": 8.68, + "learning_rate": 1.2600627536981485e-05, + "loss": 0.041, + "step": 28091 + }, + { + "epoch": 8.68, + "learning_rate": 1.2600144623713792e-05, + "loss": 0.0394, + "step": 28092 + }, + { + "epoch": 8.68, + "learning_rate": 1.259966170394266e-05, + "loss": 0.0374, + "step": 28093 + }, + { + "epoch": 8.68, + "learning_rate": 1.2599178777669305e-05, + "loss": 0.0361, + "step": 28094 + }, + { + "epoch": 8.68, + "learning_rate": 1.2598695844894931e-05, + "loss": 0.0381, + "step": 28095 + }, + { + "epoch": 8.68, + "learning_rate": 1.2598212905620741e-05, + "loss": 0.0383, + "step": 28096 + }, + { + "epoch": 8.68, + "learning_rate": 1.2597729959847947e-05, + "loss": 0.0389, + "step": 28097 + }, + { + "epoch": 8.68, + "learning_rate": 1.2597247007577757e-05, + "loss": 0.0383, + "step": 28098 + }, + { + "epoch": 8.68, + "learning_rate": 1.2596764048811379e-05, + "loss": 0.0383, + "step": 28099 + }, + { + "epoch": 8.68, + "learning_rate": 1.259628108355002e-05, + "loss": 0.0393, + "step": 28100 + }, + { + "epoch": 8.68, + "learning_rate": 1.2595798111794886e-05, + "loss": 0.0438, + "step": 28101 + }, + { + "epoch": 8.68, + "learning_rate": 1.2595315133547191e-05, + "loss": 0.0399, + "step": 28102 + }, + { + "epoch": 8.68, + "learning_rate": 1.2594832148808138e-05, + "loss": 0.0359, + "step": 28103 + }, + { + "epoch": 8.68, + "learning_rate": 1.2594349157578938e-05, + "loss": 0.0381, + "step": 28104 + }, + { + "epoch": 8.68, + "learning_rate": 1.2593866159860798e-05, + "loss": 0.0388, + "step": 28105 + }, + { + "epoch": 8.68, + "learning_rate": 1.2593383155654922e-05, + "loss": 0.0368, + "step": 28106 + }, + { + "epoch": 8.68, + "learning_rate": 1.2592900144962526e-05, + "loss": 0.0354, + "step": 28107 + }, + { + "epoch": 8.68, + "learning_rate": 1.259241712778481e-05, + "loss": 0.0405, + "step": 28108 + }, + { + "epoch": 8.68, + "learning_rate": 1.2591934104122987e-05, + "loss": 0.0405, + "step": 28109 + }, + { + "epoch": 8.68, + "learning_rate": 1.2591451073978264e-05, + "loss": 0.0366, + "step": 28110 + }, + { + "epoch": 8.68, + "learning_rate": 1.2590968037351852e-05, + "loss": 0.0431, + "step": 28111 + }, + { + "epoch": 8.68, + "learning_rate": 1.2590484994244956e-05, + "loss": 0.0385, + "step": 28112 + }, + { + "epoch": 8.68, + "learning_rate": 1.259000194465878e-05, + "loss": 0.036, + "step": 28113 + }, + { + "epoch": 8.68, + "learning_rate": 1.2589518888594538e-05, + "loss": 0.0391, + "step": 28114 + }, + { + "epoch": 8.68, + "learning_rate": 1.2589035826053442e-05, + "loss": 0.0383, + "step": 28115 + }, + { + "epoch": 8.68, + "learning_rate": 1.258855275703669e-05, + "loss": 0.0363, + "step": 28116 + }, + { + "epoch": 8.68, + "learning_rate": 1.2588069681545499e-05, + "loss": 0.043, + "step": 28117 + }, + { + "epoch": 8.68, + "learning_rate": 1.2587586599581072e-05, + "loss": 0.0379, + "step": 28118 + }, + { + "epoch": 8.68, + "learning_rate": 1.2587103511144615e-05, + "loss": 0.0373, + "step": 28119 + }, + { + "epoch": 8.68, + "learning_rate": 1.2586620416237347e-05, + "loss": 0.0405, + "step": 28120 + }, + { + "epoch": 8.68, + "learning_rate": 1.2586137314860467e-05, + "loss": 0.0417, + "step": 28121 + }, + { + "epoch": 8.68, + "learning_rate": 1.2585654207015186e-05, + "loss": 0.0342, + "step": 28122 + }, + { + "epoch": 8.68, + "learning_rate": 1.2585171092702711e-05, + "loss": 0.0415, + "step": 28123 + }, + { + "epoch": 8.69, + "learning_rate": 1.2584687971924252e-05, + "loss": 0.0427, + "step": 28124 + }, + { + "epoch": 8.69, + "learning_rate": 1.2584204844681018e-05, + "loss": 0.0399, + "step": 28125 + }, + { + "epoch": 8.69, + "learning_rate": 1.2583721710974216e-05, + "loss": 0.0402, + "step": 28126 + }, + { + "epoch": 8.69, + "learning_rate": 1.2583238570805055e-05, + "loss": 0.0346, + "step": 28127 + }, + { + "epoch": 8.69, + "learning_rate": 1.2582755424174741e-05, + "loss": 0.0406, + "step": 28128 + }, + { + "epoch": 8.69, + "learning_rate": 1.2582272271084489e-05, + "loss": 0.0402, + "step": 28129 + }, + { + "epoch": 8.69, + "learning_rate": 1.2581789111535498e-05, + "loss": 0.0403, + "step": 28130 + }, + { + "epoch": 8.69, + "learning_rate": 1.2581305945528986e-05, + "loss": 0.0409, + "step": 28131 + }, + { + "epoch": 8.69, + "learning_rate": 1.2580822773066154e-05, + "loss": 0.0456, + "step": 28132 + }, + { + "epoch": 8.69, + "learning_rate": 1.2580339594148214e-05, + "loss": 0.0376, + "step": 28133 + }, + { + "epoch": 8.69, + "learning_rate": 1.2579856408776373e-05, + "loss": 0.0398, + "step": 28134 + }, + { + "epoch": 8.69, + "learning_rate": 1.2579373216951844e-05, + "loss": 0.0385, + "step": 28135 + }, + { + "epoch": 8.69, + "learning_rate": 1.257889001867583e-05, + "loss": 0.0391, + "step": 28136 + }, + { + "epoch": 8.69, + "learning_rate": 1.2578406813949542e-05, + "loss": 0.0387, + "step": 28137 + }, + { + "epoch": 8.69, + "learning_rate": 1.2577923602774188e-05, + "loss": 0.0412, + "step": 28138 + }, + { + "epoch": 8.69, + "learning_rate": 1.2577440385150975e-05, + "loss": 0.0392, + "step": 28139 + }, + { + "epoch": 8.69, + "learning_rate": 1.257695716108112e-05, + "loss": 0.0377, + "step": 28140 + }, + { + "epoch": 8.69, + "learning_rate": 1.257647393056582e-05, + "loss": 0.0352, + "step": 28141 + }, + { + "epoch": 8.69, + "learning_rate": 1.2575990693606289e-05, + "loss": 0.0356, + "step": 28142 + }, + { + "epoch": 8.69, + "learning_rate": 1.2575507450203737e-05, + "loss": 0.0379, + "step": 28143 + }, + { + "epoch": 8.69, + "learning_rate": 1.2575024200359367e-05, + "loss": 0.038, + "step": 28144 + }, + { + "epoch": 8.69, + "learning_rate": 1.2574540944074397e-05, + "loss": 0.0381, + "step": 28145 + }, + { + "epoch": 8.69, + "learning_rate": 1.257405768135003e-05, + "loss": 0.0372, + "step": 28146 + }, + { + "epoch": 8.69, + "learning_rate": 1.257357441218747e-05, + "loss": 0.0464, + "step": 28147 + }, + { + "epoch": 8.69, + "learning_rate": 1.2573091136587937e-05, + "loss": 0.0385, + "step": 28148 + }, + { + "epoch": 8.69, + "learning_rate": 1.2572607854552633e-05, + "loss": 0.0351, + "step": 28149 + }, + { + "epoch": 8.69, + "learning_rate": 1.2572124566082764e-05, + "loss": 0.0386, + "step": 28150 + }, + { + "epoch": 8.69, + "learning_rate": 1.2571641271179545e-05, + "loss": 0.0366, + "step": 28151 + }, + { + "epoch": 8.69, + "learning_rate": 1.2571157969844181e-05, + "loss": 0.0403, + "step": 28152 + }, + { + "epoch": 8.69, + "learning_rate": 1.2570674662077883e-05, + "loss": 0.0383, + "step": 28153 + }, + { + "epoch": 8.69, + "learning_rate": 1.2570191347881857e-05, + "loss": 0.0341, + "step": 28154 + }, + { + "epoch": 8.69, + "learning_rate": 1.2569708027257316e-05, + "loss": 0.037, + "step": 28155 + }, + { + "epoch": 8.7, + "learning_rate": 1.2569224700205465e-05, + "loss": 0.0369, + "step": 28156 + }, + { + "epoch": 8.7, + "learning_rate": 1.2568741366727515e-05, + "loss": 0.0338, + "step": 28157 + }, + { + "epoch": 8.7, + "learning_rate": 1.2568258026824674e-05, + "loss": 0.0383, + "step": 28158 + }, + { + "epoch": 8.7, + "learning_rate": 1.2567774680498151e-05, + "loss": 0.038, + "step": 28159 + }, + { + "epoch": 8.7, + "learning_rate": 1.2567291327749156e-05, + "loss": 0.0428, + "step": 28160 + }, + { + "epoch": 8.7, + "learning_rate": 1.2566807968578898e-05, + "loss": 0.0386, + "step": 28161 + }, + { + "epoch": 8.7, + "learning_rate": 1.2566324602988584e-05, + "loss": 0.0393, + "step": 28162 + }, + { + "epoch": 8.7, + "learning_rate": 1.2565841230979423e-05, + "loss": 0.0398, + "step": 28163 + }, + { + "epoch": 8.7, + "learning_rate": 1.2565357852552626e-05, + "loss": 0.0376, + "step": 28164 + }, + { + "epoch": 8.7, + "learning_rate": 1.2564874467709402e-05, + "loss": 0.0345, + "step": 28165 + }, + { + "epoch": 8.7, + "learning_rate": 1.256439107645096e-05, + "loss": 0.042, + "step": 28166 + }, + { + "epoch": 8.7, + "learning_rate": 1.2563907678778505e-05, + "loss": 0.0334, + "step": 28167 + }, + { + "epoch": 8.7, + "learning_rate": 1.256342427469325e-05, + "loss": 0.0419, + "step": 28168 + }, + { + "epoch": 8.7, + "learning_rate": 1.2562940864196407e-05, + "loss": 0.0351, + "step": 28169 + }, + { + "epoch": 8.7, + "learning_rate": 1.2562457447289176e-05, + "loss": 0.0407, + "step": 28170 + }, + { + "epoch": 8.7, + "learning_rate": 1.2561974023972775e-05, + "loss": 0.04, + "step": 28171 + }, + { + "epoch": 8.7, + "learning_rate": 1.256149059424841e-05, + "loss": 0.037, + "step": 28172 + }, + { + "epoch": 8.7, + "learning_rate": 1.2561007158117287e-05, + "loss": 0.0345, + "step": 28173 + }, + { + "epoch": 8.7, + "learning_rate": 1.256052371558062e-05, + "loss": 0.0401, + "step": 28174 + }, + { + "epoch": 8.7, + "learning_rate": 1.2560040266639615e-05, + "loss": 0.038, + "step": 28175 + }, + { + "epoch": 8.7, + "learning_rate": 1.2559556811295486e-05, + "loss": 0.0364, + "step": 28176 + }, + { + "epoch": 8.7, + "learning_rate": 1.2559073349549436e-05, + "loss": 0.0393, + "step": 28177 + }, + { + "epoch": 8.7, + "learning_rate": 1.2558589881402675e-05, + "loss": 0.0403, + "step": 28178 + }, + { + "epoch": 8.7, + "learning_rate": 1.2558106406856417e-05, + "loss": 0.0395, + "step": 28179 + }, + { + "epoch": 8.7, + "learning_rate": 1.2557622925911867e-05, + "loss": 0.0395, + "step": 28180 + }, + { + "epoch": 8.7, + "learning_rate": 1.2557139438570237e-05, + "loss": 0.0378, + "step": 28181 + }, + { + "epoch": 8.7, + "learning_rate": 1.2556655944832731e-05, + "loss": 0.037, + "step": 28182 + }, + { + "epoch": 8.7, + "learning_rate": 1.2556172444700565e-05, + "loss": 0.0373, + "step": 28183 + }, + { + "epoch": 8.7, + "learning_rate": 1.2555688938174946e-05, + "loss": 0.0397, + "step": 28184 + }, + { + "epoch": 8.7, + "learning_rate": 1.2555205425257082e-05, + "loss": 0.0401, + "step": 28185 + }, + { + "epoch": 8.7, + "learning_rate": 1.2554721905948184e-05, + "loss": 0.0362, + "step": 28186 + }, + { + "epoch": 8.7, + "learning_rate": 1.255423838024946e-05, + "loss": 0.0386, + "step": 28187 + }, + { + "epoch": 8.71, + "learning_rate": 1.255375484816212e-05, + "loss": 0.0393, + "step": 28188 + }, + { + "epoch": 8.71, + "learning_rate": 1.2553271309687373e-05, + "loss": 0.0367, + "step": 28189 + }, + { + "epoch": 8.71, + "learning_rate": 1.2552787764826428e-05, + "loss": 0.043, + "step": 28190 + }, + { + "epoch": 8.71, + "learning_rate": 1.2552304213580495e-05, + "loss": 0.0363, + "step": 28191 + }, + { + "epoch": 8.71, + "learning_rate": 1.2551820655950783e-05, + "loss": 0.0397, + "step": 28192 + }, + { + "epoch": 8.71, + "learning_rate": 1.2551337091938507e-05, + "loss": 0.0369, + "step": 28193 + }, + { + "epoch": 8.71, + "learning_rate": 1.2550853521544867e-05, + "loss": 0.0382, + "step": 28194 + }, + { + "epoch": 8.71, + "learning_rate": 1.2550369944771079e-05, + "loss": 0.0388, + "step": 28195 + }, + { + "epoch": 8.71, + "learning_rate": 1.2549886361618348e-05, + "loss": 0.0365, + "step": 28196 + }, + { + "epoch": 8.71, + "learning_rate": 1.2549402772087893e-05, + "loss": 0.0359, + "step": 28197 + }, + { + "epoch": 8.71, + "learning_rate": 1.254891917618091e-05, + "loss": 0.0401, + "step": 28198 + }, + { + "epoch": 8.71, + "learning_rate": 1.2548435573898616e-05, + "loss": 0.0396, + "step": 28199 + }, + { + "epoch": 8.71, + "learning_rate": 1.2547951965242223e-05, + "loss": 0.0371, + "step": 28200 + }, + { + "epoch": 8.71, + "learning_rate": 1.2547468350212932e-05, + "loss": 0.0404, + "step": 28201 + }, + { + "epoch": 8.71, + "learning_rate": 1.2546984728811964e-05, + "loss": 0.0376, + "step": 28202 + }, + { + "epoch": 8.71, + "learning_rate": 1.2546501101040521e-05, + "loss": 0.0402, + "step": 28203 + }, + { + "epoch": 8.71, + "learning_rate": 1.2546017466899812e-05, + "loss": 0.0323, + "step": 28204 + }, + { + "epoch": 8.71, + "learning_rate": 1.2545533826391051e-05, + "loss": 0.0379, + "step": 28205 + }, + { + "epoch": 8.71, + "learning_rate": 1.2545050179515446e-05, + "loss": 0.0387, + "step": 28206 + }, + { + "epoch": 8.71, + "learning_rate": 1.2544566526274205e-05, + "loss": 0.036, + "step": 28207 + }, + { + "epoch": 8.71, + "learning_rate": 1.254408286666854e-05, + "loss": 0.0401, + "step": 28208 + }, + { + "epoch": 8.71, + "learning_rate": 1.2543599200699656e-05, + "loss": 0.0378, + "step": 28209 + }, + { + "epoch": 8.71, + "learning_rate": 1.2543115528368773e-05, + "loss": 0.0401, + "step": 28210 + }, + { + "epoch": 8.71, + "learning_rate": 1.254263184967709e-05, + "loss": 0.04, + "step": 28211 + }, + { + "epoch": 8.71, + "learning_rate": 1.254214816462582e-05, + "loss": 0.0433, + "step": 28212 + }, + { + "epoch": 8.71, + "learning_rate": 1.2541664473216175e-05, + "loss": 0.0357, + "step": 28213 + }, + { + "epoch": 8.71, + "learning_rate": 1.2541180775449364e-05, + "loss": 0.0384, + "step": 28214 + }, + { + "epoch": 8.71, + "learning_rate": 1.2540697071326598e-05, + "loss": 0.0371, + "step": 28215 + }, + { + "epoch": 8.71, + "learning_rate": 1.2540213360849083e-05, + "loss": 0.0366, + "step": 28216 + }, + { + "epoch": 8.71, + "learning_rate": 1.2539729644018032e-05, + "loss": 0.0389, + "step": 28217 + }, + { + "epoch": 8.71, + "learning_rate": 1.2539245920834653e-05, + "loss": 0.0368, + "step": 28218 + }, + { + "epoch": 8.71, + "learning_rate": 1.2538762191300157e-05, + "loss": 0.0372, + "step": 28219 + }, + { + "epoch": 8.71, + "learning_rate": 1.2538278455415758e-05, + "loss": 0.0414, + "step": 28220 + }, + { + "epoch": 8.72, + "learning_rate": 1.2537794713182655e-05, + "loss": 0.0377, + "step": 28221 + }, + { + "epoch": 8.72, + "learning_rate": 1.2537310964602067e-05, + "loss": 0.0398, + "step": 28222 + }, + { + "epoch": 8.72, + "learning_rate": 1.2536827209675204e-05, + "loss": 0.0367, + "step": 28223 + }, + { + "epoch": 8.72, + "learning_rate": 1.253634344840327e-05, + "loss": 0.0369, + "step": 28224 + }, + { + "epoch": 8.72, + "learning_rate": 1.253585968078748e-05, + "loss": 0.0376, + "step": 28225 + }, + { + "epoch": 8.72, + "learning_rate": 1.2535375906829042e-05, + "loss": 0.0395, + "step": 28226 + }, + { + "epoch": 8.72, + "learning_rate": 1.2534892126529167e-05, + "loss": 0.0374, + "step": 28227 + }, + { + "epoch": 8.72, + "learning_rate": 1.2534408339889067e-05, + "loss": 0.0407, + "step": 28228 + }, + { + "epoch": 8.72, + "learning_rate": 1.2533924546909944e-05, + "loss": 0.041, + "step": 28229 + }, + { + "epoch": 8.72, + "learning_rate": 1.2533440747593018e-05, + "loss": 0.0414, + "step": 28230 + }, + { + "epoch": 8.72, + "learning_rate": 1.2532956941939492e-05, + "loss": 0.0357, + "step": 28231 + }, + { + "epoch": 8.72, + "learning_rate": 1.2532473129950577e-05, + "loss": 0.0435, + "step": 28232 + }, + { + "epoch": 8.72, + "learning_rate": 1.253198931162749e-05, + "loss": 0.0379, + "step": 28233 + }, + { + "epoch": 8.72, + "learning_rate": 1.2531505486971434e-05, + "loss": 0.0347, + "step": 28234 + }, + { + "epoch": 8.72, + "learning_rate": 1.2531021655983619e-05, + "loss": 0.0406, + "step": 28235 + }, + { + "epoch": 8.72, + "learning_rate": 1.253053781866526e-05, + "loss": 0.0407, + "step": 28236 + }, + { + "epoch": 8.72, + "learning_rate": 1.2530053975017563e-05, + "loss": 0.0377, + "step": 28237 + }, + { + "epoch": 8.72, + "learning_rate": 1.2529570125041739e-05, + "loss": 0.037, + "step": 28238 + }, + { + "epoch": 8.72, + "learning_rate": 1.2529086268738999e-05, + "loss": 0.0357, + "step": 28239 + }, + { + "epoch": 8.72, + "learning_rate": 1.2528602406110552e-05, + "loss": 0.0415, + "step": 28240 + }, + { + "epoch": 8.72, + "learning_rate": 1.2528118537157613e-05, + "loss": 0.0335, + "step": 28241 + }, + { + "epoch": 8.72, + "learning_rate": 1.2527634661881386e-05, + "loss": 0.0404, + "step": 28242 + }, + { + "epoch": 8.72, + "learning_rate": 1.252715078028308e-05, + "loss": 0.0402, + "step": 28243 + }, + { + "epoch": 8.72, + "learning_rate": 1.2526666892363915e-05, + "loss": 0.0388, + "step": 28244 + }, + { + "epoch": 8.72, + "learning_rate": 1.2526182998125091e-05, + "loss": 0.0395, + "step": 28245 + }, + { + "epoch": 8.72, + "learning_rate": 1.2525699097567824e-05, + "loss": 0.0371, + "step": 28246 + }, + { + "epoch": 8.72, + "learning_rate": 1.2525215190693325e-05, + "loss": 0.038, + "step": 28247 + }, + { + "epoch": 8.72, + "learning_rate": 1.25247312775028e-05, + "loss": 0.0375, + "step": 28248 + }, + { + "epoch": 8.72, + "learning_rate": 1.2524247357997462e-05, + "loss": 0.0383, + "step": 28249 + }, + { + "epoch": 8.72, + "learning_rate": 1.2523763432178521e-05, + "loss": 0.0379, + "step": 28250 + }, + { + "epoch": 8.72, + "learning_rate": 1.252327950004719e-05, + "loss": 0.0366, + "step": 28251 + }, + { + "epoch": 8.72, + "learning_rate": 1.2522795561604673e-05, + "loss": 0.0389, + "step": 28252 + }, + { + "epoch": 8.73, + "learning_rate": 1.2522311616852183e-05, + "loss": 0.0379, + "step": 28253 + }, + { + "epoch": 8.73, + "learning_rate": 1.2521827665790937e-05, + "loss": 0.0366, + "step": 28254 + }, + { + "epoch": 8.73, + "learning_rate": 1.2521343708422134e-05, + "loss": 0.0363, + "step": 28255 + }, + { + "epoch": 8.73, + "learning_rate": 1.2520859744746995e-05, + "loss": 0.0403, + "step": 28256 + }, + { + "epoch": 8.73, + "learning_rate": 1.2520375774766725e-05, + "loss": 0.0371, + "step": 28257 + }, + { + "epoch": 8.73, + "learning_rate": 1.2519891798482534e-05, + "loss": 0.0386, + "step": 28258 + }, + { + "epoch": 8.73, + "learning_rate": 1.2519407815895637e-05, + "loss": 0.0378, + "step": 28259 + }, + { + "epoch": 8.73, + "learning_rate": 1.2518923827007236e-05, + "loss": 0.0364, + "step": 28260 + }, + { + "epoch": 8.73, + "learning_rate": 1.2518439831818554e-05, + "loss": 0.0423, + "step": 28261 + }, + { + "epoch": 8.73, + "learning_rate": 1.2517955830330792e-05, + "loss": 0.0358, + "step": 28262 + }, + { + "epoch": 8.73, + "learning_rate": 1.251747182254516e-05, + "loss": 0.0402, + "step": 28263 + }, + { + "epoch": 8.73, + "learning_rate": 1.2516987808462875e-05, + "loss": 0.0353, + "step": 28264 + }, + { + "epoch": 8.73, + "learning_rate": 1.2516503788085146e-05, + "loss": 0.0388, + "step": 28265 + }, + { + "epoch": 8.73, + "learning_rate": 1.2516019761413179e-05, + "loss": 0.0379, + "step": 28266 + }, + { + "epoch": 8.73, + "learning_rate": 1.2515535728448187e-05, + "loss": 0.0399, + "step": 28267 + }, + { + "epoch": 8.73, + "learning_rate": 1.2515051689191384e-05, + "loss": 0.0371, + "step": 28268 + }, + { + "epoch": 8.73, + "learning_rate": 1.2514567643643975e-05, + "loss": 0.0407, + "step": 28269 + }, + { + "epoch": 8.73, + "learning_rate": 1.2514083591807178e-05, + "loss": 0.0414, + "step": 28270 + }, + { + "epoch": 8.73, + "learning_rate": 1.2513599533682194e-05, + "loss": 0.0399, + "step": 28271 + }, + { + "epoch": 8.73, + "learning_rate": 1.2513115469270242e-05, + "loss": 0.0406, + "step": 28272 + }, + { + "epoch": 8.73, + "learning_rate": 1.2512631398572532e-05, + "loss": 0.0338, + "step": 28273 + }, + { + "epoch": 8.73, + "learning_rate": 1.2512147321590269e-05, + "loss": 0.0397, + "step": 28274 + }, + { + "epoch": 8.73, + "learning_rate": 1.251166323832467e-05, + "loss": 0.0377, + "step": 28275 + }, + { + "epoch": 8.73, + "learning_rate": 1.2511179148776942e-05, + "loss": 0.039, + "step": 28276 + }, + { + "epoch": 8.73, + "learning_rate": 1.2510695052948295e-05, + "loss": 0.0363, + "step": 28277 + }, + { + "epoch": 8.73, + "learning_rate": 1.2510210950839945e-05, + "loss": 0.0421, + "step": 28278 + }, + { + "epoch": 8.73, + "learning_rate": 1.25097268424531e-05, + "loss": 0.0405, + "step": 28279 + }, + { + "epoch": 8.73, + "learning_rate": 1.2509242727788966e-05, + "loss": 0.0371, + "step": 28280 + }, + { + "epoch": 8.73, + "learning_rate": 1.250875860684876e-05, + "loss": 0.036, + "step": 28281 + }, + { + "epoch": 8.73, + "learning_rate": 1.2508274479633695e-05, + "loss": 0.039, + "step": 28282 + }, + { + "epoch": 8.73, + "learning_rate": 1.2507790346144974e-05, + "loss": 0.0376, + "step": 28283 + }, + { + "epoch": 8.73, + "learning_rate": 1.2507306206383816e-05, + "loss": 0.042, + "step": 28284 + }, + { + "epoch": 8.73, + "learning_rate": 1.2506822060351425e-05, + "loss": 0.0396, + "step": 28285 + }, + { + "epoch": 8.74, + "learning_rate": 1.2506337908049012e-05, + "loss": 0.0391, + "step": 28286 + }, + { + "epoch": 8.74, + "learning_rate": 1.2505853749477796e-05, + "loss": 0.0371, + "step": 28287 + }, + { + "epoch": 8.74, + "learning_rate": 1.250536958463898e-05, + "loss": 0.0369, + "step": 28288 + }, + { + "epoch": 8.74, + "learning_rate": 1.2504885413533775e-05, + "loss": 0.0354, + "step": 28289 + }, + { + "epoch": 8.74, + "learning_rate": 1.2504401236163398e-05, + "loss": 0.0405, + "step": 28290 + }, + { + "epoch": 8.74, + "learning_rate": 1.2503917052529055e-05, + "loss": 0.0368, + "step": 28291 + }, + { + "epoch": 8.74, + "learning_rate": 1.2503432862631964e-05, + "loss": 0.0396, + "step": 28292 + }, + { + "epoch": 8.74, + "learning_rate": 1.2502948666473327e-05, + "loss": 0.0364, + "step": 28293 + }, + { + "epoch": 8.74, + "learning_rate": 1.2502464464054358e-05, + "loss": 0.0369, + "step": 28294 + }, + { + "epoch": 8.74, + "learning_rate": 1.250198025537627e-05, + "loss": 0.038, + "step": 28295 + }, + { + "epoch": 8.74, + "learning_rate": 1.2501496040440273e-05, + "loss": 0.0384, + "step": 28296 + }, + { + "epoch": 8.74, + "learning_rate": 1.250101181924758e-05, + "loss": 0.0403, + "step": 28297 + }, + { + "epoch": 8.74, + "learning_rate": 1.2500527591799396e-05, + "loss": 0.0409, + "step": 28298 + }, + { + "epoch": 8.74, + "learning_rate": 1.2500043358096941e-05, + "loss": 0.0373, + "step": 28299 + }, + { + "epoch": 8.74, + "learning_rate": 1.2499559118141417e-05, + "loss": 0.037, + "step": 28300 + }, + { + "epoch": 8.74, + "learning_rate": 1.2499074871934043e-05, + "loss": 0.0377, + "step": 28301 + }, + { + "epoch": 8.74, + "learning_rate": 1.2498590619476025e-05, + "loss": 0.0357, + "step": 28302 + }, + { + "epoch": 8.74, + "learning_rate": 1.2498106360768577e-05, + "loss": 0.0361, + "step": 28303 + }, + { + "epoch": 8.74, + "learning_rate": 1.2497622095812912e-05, + "loss": 0.0397, + "step": 28304 + }, + { + "epoch": 8.74, + "learning_rate": 1.2497137824610234e-05, + "loss": 0.0385, + "step": 28305 + }, + { + "epoch": 8.74, + "learning_rate": 1.249665354716176e-05, + "loss": 0.0444, + "step": 28306 + }, + { + "epoch": 8.74, + "learning_rate": 1.2496169263468703e-05, + "loss": 0.0319, + "step": 28307 + }, + { + "epoch": 8.74, + "learning_rate": 1.2495684973532269e-05, + "loss": 0.0394, + "step": 28308 + }, + { + "epoch": 8.74, + "learning_rate": 1.2495200677353671e-05, + "loss": 0.0399, + "step": 28309 + }, + { + "epoch": 8.74, + "learning_rate": 1.2494716374934126e-05, + "loss": 0.0385, + "step": 28310 + }, + { + "epoch": 8.74, + "learning_rate": 1.2494232066274833e-05, + "loss": 0.0413, + "step": 28311 + }, + { + "epoch": 8.74, + "learning_rate": 1.2493747751377014e-05, + "loss": 0.0426, + "step": 28312 + }, + { + "epoch": 8.74, + "learning_rate": 1.249326343024188e-05, + "loss": 0.0401, + "step": 28313 + }, + { + "epoch": 8.74, + "learning_rate": 1.2492779102870636e-05, + "loss": 0.0413, + "step": 28314 + }, + { + "epoch": 8.74, + "learning_rate": 1.2492294769264499e-05, + "loss": 0.0411, + "step": 28315 + }, + { + "epoch": 8.74, + "learning_rate": 1.2491810429424676e-05, + "loss": 0.0411, + "step": 28316 + }, + { + "epoch": 8.74, + "learning_rate": 1.249132608335238e-05, + "loss": 0.0396, + "step": 28317 + }, + { + "epoch": 8.75, + "learning_rate": 1.2490841731048825e-05, + "loss": 0.0325, + "step": 28318 + }, + { + "epoch": 8.75, + "learning_rate": 1.2490357372515221e-05, + "loss": 0.041, + "step": 28319 + }, + { + "epoch": 8.75, + "learning_rate": 1.2489873007752777e-05, + "loss": 0.0365, + "step": 28320 + }, + { + "epoch": 8.75, + "learning_rate": 1.248938863676271e-05, + "loss": 0.0356, + "step": 28321 + }, + { + "epoch": 8.75, + "learning_rate": 1.2488904259546222e-05, + "loss": 0.044, + "step": 28322 + }, + { + "epoch": 8.75, + "learning_rate": 1.2488419876104537e-05, + "loss": 0.0393, + "step": 28323 + }, + { + "epoch": 8.75, + "learning_rate": 1.2487935486438855e-05, + "loss": 0.0477, + "step": 28324 + }, + { + "epoch": 8.75, + "learning_rate": 1.2487451090550395e-05, + "loss": 0.0375, + "step": 28325 + }, + { + "epoch": 8.75, + "learning_rate": 1.2486966688440364e-05, + "loss": 0.0401, + "step": 28326 + }, + { + "epoch": 8.75, + "learning_rate": 1.248648228010998e-05, + "loss": 0.0411, + "step": 28327 + }, + { + "epoch": 8.75, + "learning_rate": 1.2485997865560447e-05, + "loss": 0.0392, + "step": 28328 + }, + { + "epoch": 8.75, + "learning_rate": 1.248551344479298e-05, + "loss": 0.0388, + "step": 28329 + }, + { + "epoch": 8.75, + "learning_rate": 1.2485029017808792e-05, + "loss": 0.0381, + "step": 28330 + }, + { + "epoch": 8.75, + "learning_rate": 1.248454458460909e-05, + "loss": 0.0372, + "step": 28331 + }, + { + "epoch": 8.75, + "learning_rate": 1.2484060145195093e-05, + "loss": 0.0422, + "step": 28332 + }, + { + "epoch": 8.75, + "learning_rate": 1.248357569956801e-05, + "loss": 0.0351, + "step": 28333 + }, + { + "epoch": 8.75, + "learning_rate": 1.2483091247729044e-05, + "loss": 0.0363, + "step": 28334 + }, + { + "epoch": 8.75, + "learning_rate": 1.248260678967942e-05, + "loss": 0.036, + "step": 28335 + }, + { + "epoch": 8.75, + "learning_rate": 1.2482122325420343e-05, + "loss": 0.0384, + "step": 28336 + }, + { + "epoch": 8.75, + "learning_rate": 1.2481637854953021e-05, + "loss": 0.0408, + "step": 28337 + }, + { + "epoch": 8.75, + "learning_rate": 1.2481153378278675e-05, + "loss": 0.0391, + "step": 28338 + }, + { + "epoch": 8.75, + "learning_rate": 1.2480668895398506e-05, + "loss": 0.0384, + "step": 28339 + }, + { + "epoch": 8.75, + "learning_rate": 1.2480184406313738e-05, + "loss": 0.0437, + "step": 28340 + }, + { + "epoch": 8.75, + "learning_rate": 1.2479699911025574e-05, + "loss": 0.0393, + "step": 28341 + }, + { + "epoch": 8.75, + "learning_rate": 1.2479215409535226e-05, + "loss": 0.0376, + "step": 28342 + }, + { + "epoch": 8.75, + "learning_rate": 1.2478730901843914e-05, + "loss": 0.0397, + "step": 28343 + }, + { + "epoch": 8.75, + "learning_rate": 1.247824638795284e-05, + "loss": 0.0372, + "step": 28344 + }, + { + "epoch": 8.75, + "learning_rate": 1.2477761867863216e-05, + "loss": 0.0394, + "step": 28345 + }, + { + "epoch": 8.75, + "learning_rate": 1.2477277341576263e-05, + "loss": 0.0377, + "step": 28346 + }, + { + "epoch": 8.75, + "learning_rate": 1.2476792809093188e-05, + "loss": 0.0387, + "step": 28347 + }, + { + "epoch": 8.75, + "learning_rate": 1.24763082704152e-05, + "loss": 0.0378, + "step": 28348 + }, + { + "epoch": 8.75, + "learning_rate": 1.2475823725543514e-05, + "loss": 0.0388, + "step": 28349 + }, + { + "epoch": 8.76, + "learning_rate": 1.2475339174479342e-05, + "loss": 0.0374, + "step": 28350 + }, + { + "epoch": 8.76, + "learning_rate": 1.2474854617223893e-05, + "loss": 0.0379, + "step": 28351 + }, + { + "epoch": 8.76, + "learning_rate": 1.2474370053778384e-05, + "loss": 0.0407, + "step": 28352 + }, + { + "epoch": 8.76, + "learning_rate": 1.2473885484144022e-05, + "loss": 0.0408, + "step": 28353 + }, + { + "epoch": 8.76, + "learning_rate": 1.2473400908322022e-05, + "loss": 0.0386, + "step": 28354 + }, + { + "epoch": 8.76, + "learning_rate": 1.2472916326313596e-05, + "loss": 0.042, + "step": 28355 + }, + { + "epoch": 8.76, + "learning_rate": 1.2472431738119953e-05, + "loss": 0.0379, + "step": 28356 + }, + { + "epoch": 8.76, + "learning_rate": 1.247194714374231e-05, + "loss": 0.0365, + "step": 28357 + }, + { + "epoch": 8.76, + "learning_rate": 1.2471462543181873e-05, + "loss": 0.0409, + "step": 28358 + }, + { + "epoch": 8.76, + "learning_rate": 1.247097793643986e-05, + "loss": 0.0375, + "step": 28359 + }, + { + "epoch": 8.76, + "learning_rate": 1.2470493323517481e-05, + "loss": 0.0424, + "step": 28360 + }, + { + "epoch": 8.76, + "learning_rate": 1.2470008704415946e-05, + "loss": 0.0345, + "step": 28361 + }, + { + "epoch": 8.76, + "learning_rate": 1.2469524079136471e-05, + "loss": 0.0376, + "step": 28362 + }, + { + "epoch": 8.76, + "learning_rate": 1.2469039447680262e-05, + "loss": 0.0335, + "step": 28363 + }, + { + "epoch": 8.76, + "learning_rate": 1.2468554810048541e-05, + "loss": 0.0399, + "step": 28364 + }, + { + "epoch": 8.76, + "learning_rate": 1.2468070166242508e-05, + "loss": 0.0358, + "step": 28365 + }, + { + "epoch": 8.76, + "learning_rate": 1.2467585516263383e-05, + "loss": 0.0422, + "step": 28366 + }, + { + "epoch": 8.76, + "learning_rate": 1.246710086011238e-05, + "loss": 0.0369, + "step": 28367 + }, + { + "epoch": 8.76, + "learning_rate": 1.2466616197790701e-05, + "loss": 0.0436, + "step": 28368 + }, + { + "epoch": 8.76, + "learning_rate": 1.2466131529299573e-05, + "loss": 0.0374, + "step": 28369 + }, + { + "epoch": 8.76, + "learning_rate": 1.2465646854640196e-05, + "loss": 0.0386, + "step": 28370 + }, + { + "epoch": 8.76, + "learning_rate": 1.2465162173813785e-05, + "loss": 0.042, + "step": 28371 + }, + { + "epoch": 8.76, + "learning_rate": 1.2464677486821558e-05, + "loss": 0.0424, + "step": 28372 + }, + { + "epoch": 8.76, + "learning_rate": 1.2464192793664718e-05, + "loss": 0.0398, + "step": 28373 + }, + { + "epoch": 8.76, + "learning_rate": 1.2463708094344487e-05, + "loss": 0.0434, + "step": 28374 + }, + { + "epoch": 8.76, + "learning_rate": 1.2463223388862071e-05, + "loss": 0.0364, + "step": 28375 + }, + { + "epoch": 8.76, + "learning_rate": 1.2462738677218682e-05, + "loss": 0.0377, + "step": 28376 + }, + { + "epoch": 8.76, + "learning_rate": 1.2462253959415538e-05, + "loss": 0.0384, + "step": 28377 + }, + { + "epoch": 8.76, + "learning_rate": 1.2461769235453846e-05, + "loss": 0.0399, + "step": 28378 + }, + { + "epoch": 8.76, + "learning_rate": 1.2461284505334822e-05, + "loss": 0.0376, + "step": 28379 + }, + { + "epoch": 8.76, + "learning_rate": 1.2460799769059673e-05, + "loss": 0.0335, + "step": 28380 + }, + { + "epoch": 8.76, + "learning_rate": 1.2460315026629617e-05, + "loss": 0.0386, + "step": 28381 + }, + { + "epoch": 8.76, + "learning_rate": 1.2459830278045864e-05, + "loss": 0.0374, + "step": 28382 + }, + { + "epoch": 8.77, + "learning_rate": 1.2459345523309627e-05, + "loss": 0.0381, + "step": 28383 + }, + { + "epoch": 8.77, + "learning_rate": 1.2458860762422119e-05, + "loss": 0.0411, + "step": 28384 + }, + { + "epoch": 8.77, + "learning_rate": 1.245837599538455e-05, + "loss": 0.0418, + "step": 28385 + }, + { + "epoch": 8.77, + "learning_rate": 1.2457891222198135e-05, + "loss": 0.0379, + "step": 28386 + }, + { + "epoch": 8.77, + "learning_rate": 1.2457406442864087e-05, + "loss": 0.0385, + "step": 28387 + }, + { + "epoch": 8.77, + "learning_rate": 1.2456921657383616e-05, + "loss": 0.0361, + "step": 28388 + }, + { + "epoch": 8.77, + "learning_rate": 1.2456436865757935e-05, + "loss": 0.0353, + "step": 28389 + }, + { + "epoch": 8.77, + "learning_rate": 1.245595206798826e-05, + "loss": 0.0384, + "step": 28390 + }, + { + "epoch": 8.77, + "learning_rate": 1.2455467264075799e-05, + "loss": 0.0424, + "step": 28391 + }, + { + "epoch": 8.77, + "learning_rate": 1.2454982454021768e-05, + "loss": 0.0417, + "step": 28392 + }, + { + "epoch": 8.77, + "learning_rate": 1.2454497637827376e-05, + "loss": 0.04, + "step": 28393 + }, + { + "epoch": 8.77, + "learning_rate": 1.2454012815493839e-05, + "loss": 0.0375, + "step": 28394 + }, + { + "epoch": 8.77, + "learning_rate": 1.245352798702237e-05, + "loss": 0.0387, + "step": 28395 + }, + { + "epoch": 8.77, + "learning_rate": 1.2453043152414175e-05, + "loss": 0.0416, + "step": 28396 + }, + { + "epoch": 8.77, + "learning_rate": 1.2452558311670477e-05, + "loss": 0.0366, + "step": 28397 + }, + { + "epoch": 8.77, + "learning_rate": 1.2452073464792482e-05, + "loss": 0.0389, + "step": 28398 + }, + { + "epoch": 8.77, + "learning_rate": 1.24515886117814e-05, + "loss": 0.0421, + "step": 28399 + }, + { + "epoch": 8.77, + "learning_rate": 1.2451103752638454e-05, + "loss": 0.0356, + "step": 28400 + }, + { + "epoch": 8.77, + "learning_rate": 1.2450618887364848e-05, + "loss": 0.0421, + "step": 28401 + }, + { + "epoch": 8.77, + "learning_rate": 1.2450134015961796e-05, + "loss": 0.0382, + "step": 28402 + }, + { + "epoch": 8.77, + "learning_rate": 1.2449649138430512e-05, + "loss": 0.0423, + "step": 28403 + }, + { + "epoch": 8.77, + "learning_rate": 1.2449164254772207e-05, + "loss": 0.0371, + "step": 28404 + }, + { + "epoch": 8.77, + "learning_rate": 1.2448679364988099e-05, + "loss": 0.0394, + "step": 28405 + }, + { + "epoch": 8.77, + "learning_rate": 1.2448194469079398e-05, + "loss": 0.035, + "step": 28406 + }, + { + "epoch": 8.77, + "learning_rate": 1.2447709567047312e-05, + "loss": 0.0425, + "step": 28407 + }, + { + "epoch": 8.77, + "learning_rate": 1.2447224658893063e-05, + "loss": 0.0392, + "step": 28408 + }, + { + "epoch": 8.77, + "learning_rate": 1.2446739744617852e-05, + "loss": 0.0377, + "step": 28409 + }, + { + "epoch": 8.77, + "learning_rate": 1.2446254824222905e-05, + "loss": 0.0367, + "step": 28410 + }, + { + "epoch": 8.77, + "learning_rate": 1.2445769897709425e-05, + "loss": 0.0439, + "step": 28411 + }, + { + "epoch": 8.77, + "learning_rate": 1.244528496507863e-05, + "loss": 0.0358, + "step": 28412 + }, + { + "epoch": 8.77, + "learning_rate": 1.2444800026331732e-05, + "loss": 0.0399, + "step": 28413 + }, + { + "epoch": 8.77, + "learning_rate": 1.244431508146994e-05, + "loss": 0.0371, + "step": 28414 + }, + { + "epoch": 8.78, + "learning_rate": 1.2443830130494472e-05, + "loss": 0.0374, + "step": 28415 + }, + { + "epoch": 8.78, + "learning_rate": 1.244334517340654e-05, + "loss": 0.0389, + "step": 28416 + }, + { + "epoch": 8.78, + "learning_rate": 1.2442860210207355e-05, + "loss": 0.044, + "step": 28417 + }, + { + "epoch": 8.78, + "learning_rate": 1.2442375240898135e-05, + "loss": 0.0394, + "step": 28418 + }, + { + "epoch": 8.78, + "learning_rate": 1.2441890265480083e-05, + "loss": 0.0418, + "step": 28419 + }, + { + "epoch": 8.78, + "learning_rate": 1.244140528395442e-05, + "loss": 0.0402, + "step": 28420 + }, + { + "epoch": 8.78, + "learning_rate": 1.2440920296322357e-05, + "loss": 0.0401, + "step": 28421 + }, + { + "epoch": 8.78, + "learning_rate": 1.2440435302585108e-05, + "loss": 0.0407, + "step": 28422 + }, + { + "epoch": 8.78, + "learning_rate": 1.2439950302743888e-05, + "loss": 0.0383, + "step": 28423 + }, + { + "epoch": 8.78, + "learning_rate": 1.2439465296799902e-05, + "loss": 0.0386, + "step": 28424 + }, + { + "epoch": 8.78, + "learning_rate": 1.243898028475437e-05, + "loss": 0.0393, + "step": 28425 + }, + { + "epoch": 8.78, + "learning_rate": 1.2438495266608505e-05, + "loss": 0.0417, + "step": 28426 + }, + { + "epoch": 8.78, + "learning_rate": 1.2438010242363517e-05, + "loss": 0.0413, + "step": 28427 + }, + { + "epoch": 8.78, + "learning_rate": 1.2437525212020623e-05, + "loss": 0.0378, + "step": 28428 + }, + { + "epoch": 8.78, + "learning_rate": 1.2437040175581032e-05, + "loss": 0.0355, + "step": 28429 + }, + { + "epoch": 8.78, + "learning_rate": 1.2436555133045958e-05, + "loss": 0.0367, + "step": 28430 + }, + { + "epoch": 8.78, + "learning_rate": 1.2436070084416619e-05, + "loss": 0.0404, + "step": 28431 + }, + { + "epoch": 8.78, + "learning_rate": 1.2435585029694221e-05, + "loss": 0.0402, + "step": 28432 + }, + { + "epoch": 8.78, + "learning_rate": 1.2435099968879983e-05, + "loss": 0.0383, + "step": 28433 + }, + { + "epoch": 8.78, + "learning_rate": 1.2434614901975112e-05, + "loss": 0.035, + "step": 28434 + }, + { + "epoch": 8.78, + "learning_rate": 1.2434129828980828e-05, + "loss": 0.0368, + "step": 28435 + }, + { + "epoch": 8.78, + "learning_rate": 1.2433644749898342e-05, + "loss": 0.0356, + "step": 28436 + }, + { + "epoch": 8.78, + "learning_rate": 1.2433159664728864e-05, + "loss": 0.0425, + "step": 28437 + }, + { + "epoch": 8.78, + "learning_rate": 1.243267457347361e-05, + "loss": 0.0366, + "step": 28438 + }, + { + "epoch": 8.78, + "learning_rate": 1.2432189476133795e-05, + "loss": 0.0401, + "step": 28439 + }, + { + "epoch": 8.78, + "learning_rate": 1.2431704372710632e-05, + "loss": 0.0398, + "step": 28440 + }, + { + "epoch": 8.78, + "learning_rate": 1.243121926320533e-05, + "loss": 0.0392, + "step": 28441 + }, + { + "epoch": 8.78, + "learning_rate": 1.2430734147619105e-05, + "loss": 0.0393, + "step": 28442 + }, + { + "epoch": 8.78, + "learning_rate": 1.2430249025953173e-05, + "loss": 0.038, + "step": 28443 + }, + { + "epoch": 8.78, + "learning_rate": 1.2429763898208745e-05, + "loss": 0.0387, + "step": 28444 + }, + { + "epoch": 8.78, + "learning_rate": 1.2429278764387032e-05, + "loss": 0.0408, + "step": 28445 + }, + { + "epoch": 8.78, + "learning_rate": 1.2428793624489253e-05, + "loss": 0.0404, + "step": 28446 + }, + { + "epoch": 8.79, + "learning_rate": 1.2428308478516613e-05, + "loss": 0.037, + "step": 28447 + }, + { + "epoch": 8.79, + "learning_rate": 1.2427823326470331e-05, + "loss": 0.0385, + "step": 28448 + }, + { + "epoch": 8.79, + "learning_rate": 1.2427338168351626e-05, + "loss": 0.0417, + "step": 28449 + }, + { + "epoch": 8.79, + "learning_rate": 1.2426853004161701e-05, + "loss": 0.0379, + "step": 28450 + }, + { + "epoch": 8.79, + "learning_rate": 1.2426367833901777e-05, + "loss": 0.0355, + "step": 28451 + }, + { + "epoch": 8.79, + "learning_rate": 1.2425882657573063e-05, + "loss": 0.0379, + "step": 28452 + }, + { + "epoch": 8.79, + "learning_rate": 1.242539747517677e-05, + "loss": 0.0374, + "step": 28453 + }, + { + "epoch": 8.79, + "learning_rate": 1.2424912286714122e-05, + "loss": 0.0355, + "step": 28454 + }, + { + "epoch": 8.79, + "learning_rate": 1.2424427092186319e-05, + "loss": 0.0391, + "step": 28455 + }, + { + "epoch": 8.79, + "learning_rate": 1.2423941891594587e-05, + "loss": 0.033, + "step": 28456 + }, + { + "epoch": 8.79, + "learning_rate": 1.2423456684940137e-05, + "loss": 0.04, + "step": 28457 + }, + { + "epoch": 8.79, + "learning_rate": 1.2422971472224172e-05, + "loss": 0.0367, + "step": 28458 + }, + { + "epoch": 8.79, + "learning_rate": 1.2422486253447918e-05, + "loss": 0.0384, + "step": 28459 + }, + { + "epoch": 8.79, + "learning_rate": 1.2422001028612585e-05, + "loss": 0.0385, + "step": 28460 + }, + { + "epoch": 8.79, + "learning_rate": 1.2421515797719381e-05, + "loss": 0.0381, + "step": 28461 + }, + { + "epoch": 8.79, + "learning_rate": 1.2421030560769529e-05, + "loss": 0.0373, + "step": 28462 + }, + { + "epoch": 8.79, + "learning_rate": 1.2420545317764236e-05, + "loss": 0.0437, + "step": 28463 + }, + { + "epoch": 8.79, + "learning_rate": 1.242006006870472e-05, + "loss": 0.0407, + "step": 28464 + }, + { + "epoch": 8.79, + "learning_rate": 1.2419574813592191e-05, + "loss": 0.0408, + "step": 28465 + }, + { + "epoch": 8.79, + "learning_rate": 1.2419089552427864e-05, + "loss": 0.0401, + "step": 28466 + }, + { + "epoch": 8.79, + "learning_rate": 1.241860428521295e-05, + "loss": 0.0386, + "step": 28467 + }, + { + "epoch": 8.79, + "learning_rate": 1.2418119011948668e-05, + "loss": 0.0412, + "step": 28468 + }, + { + "epoch": 8.79, + "learning_rate": 1.241763373263623e-05, + "loss": 0.0415, + "step": 28469 + }, + { + "epoch": 8.79, + "learning_rate": 1.2417148447276847e-05, + "loss": 0.0392, + "step": 28470 + }, + { + "epoch": 8.79, + "learning_rate": 1.2416663155871738e-05, + "loss": 0.04, + "step": 28471 + }, + { + "epoch": 8.79, + "learning_rate": 1.2416177858422112e-05, + "loss": 0.0388, + "step": 28472 + }, + { + "epoch": 8.79, + "learning_rate": 1.2415692554929182e-05, + "loss": 0.0401, + "step": 28473 + }, + { + "epoch": 8.79, + "learning_rate": 1.2415207245394168e-05, + "loss": 0.0381, + "step": 28474 + }, + { + "epoch": 8.79, + "learning_rate": 1.2414721929818279e-05, + "loss": 0.0425, + "step": 28475 + }, + { + "epoch": 8.79, + "learning_rate": 1.241423660820273e-05, + "loss": 0.038, + "step": 28476 + }, + { + "epoch": 8.79, + "learning_rate": 1.2413751280548736e-05, + "loss": 0.0358, + "step": 28477 + }, + { + "epoch": 8.79, + "learning_rate": 1.2413265946857508e-05, + "loss": 0.0417, + "step": 28478 + }, + { + "epoch": 8.79, + "learning_rate": 1.2412780607130261e-05, + "loss": 0.0356, + "step": 28479 + }, + { + "epoch": 8.8, + "learning_rate": 1.2412295261368212e-05, + "loss": 0.0386, + "step": 28480 + }, + { + "epoch": 8.8, + "learning_rate": 1.241180990957257e-05, + "loss": 0.0412, + "step": 28481 + }, + { + "epoch": 8.8, + "learning_rate": 1.2411324551744555e-05, + "loss": 0.0399, + "step": 28482 + }, + { + "epoch": 8.8, + "learning_rate": 1.2410839187885375e-05, + "loss": 0.0391, + "step": 28483 + }, + { + "epoch": 8.8, + "learning_rate": 1.2410353817996247e-05, + "loss": 0.0391, + "step": 28484 + }, + { + "epoch": 8.8, + "learning_rate": 1.2409868442078386e-05, + "loss": 0.0408, + "step": 28485 + }, + { + "epoch": 8.8, + "learning_rate": 1.2409383060133e-05, + "loss": 0.0398, + "step": 28486 + }, + { + "epoch": 8.8, + "learning_rate": 1.2408897672161312e-05, + "loss": 0.0352, + "step": 28487 + }, + { + "epoch": 8.8, + "learning_rate": 1.240841227816453e-05, + "loss": 0.0378, + "step": 28488 + }, + { + "epoch": 8.8, + "learning_rate": 1.2407926878143867e-05, + "loss": 0.0368, + "step": 28489 + }, + { + "epoch": 8.8, + "learning_rate": 1.2407441472100545e-05, + "loss": 0.0429, + "step": 28490 + }, + { + "epoch": 8.8, + "learning_rate": 1.240695606003577e-05, + "loss": 0.0407, + "step": 28491 + }, + { + "epoch": 8.8, + "learning_rate": 1.2406470641950758e-05, + "loss": 0.0388, + "step": 28492 + }, + { + "epoch": 8.8, + "learning_rate": 1.2405985217846725e-05, + "loss": 0.0423, + "step": 28493 + }, + { + "epoch": 8.8, + "learning_rate": 1.2405499787724887e-05, + "loss": 0.0379, + "step": 28494 + }, + { + "epoch": 8.8, + "learning_rate": 1.240501435158645e-05, + "loss": 0.0373, + "step": 28495 + }, + { + "epoch": 8.8, + "learning_rate": 1.2404528909432636e-05, + "loss": 0.0401, + "step": 28496 + }, + { + "epoch": 8.8, + "learning_rate": 1.2404043461264657e-05, + "loss": 0.0408, + "step": 28497 + }, + { + "epoch": 8.8, + "learning_rate": 1.2403558007083727e-05, + "loss": 0.0396, + "step": 28498 + }, + { + "epoch": 8.8, + "learning_rate": 1.240307254689106e-05, + "loss": 0.0325, + "step": 28499 + }, + { + "epoch": 8.8, + "learning_rate": 1.2402587080687869e-05, + "loss": 0.0383, + "step": 28500 + }, + { + "epoch": 8.8, + "learning_rate": 1.240210160847537e-05, + "loss": 0.0396, + "step": 28501 + }, + { + "epoch": 8.8, + "learning_rate": 1.2401616130254777e-05, + "loss": 0.0368, + "step": 28502 + }, + { + "epoch": 8.8, + "learning_rate": 1.2401130646027303e-05, + "loss": 0.0374, + "step": 28503 + }, + { + "epoch": 8.8, + "learning_rate": 1.2400645155794166e-05, + "loss": 0.0405, + "step": 28504 + }, + { + "epoch": 8.8, + "learning_rate": 1.2400159659556577e-05, + "loss": 0.0393, + "step": 28505 + }, + { + "epoch": 8.8, + "learning_rate": 1.2399674157315748e-05, + "loss": 0.0385, + "step": 28506 + }, + { + "epoch": 8.8, + "learning_rate": 1.2399188649072898e-05, + "loss": 0.0421, + "step": 28507 + }, + { + "epoch": 8.8, + "learning_rate": 1.2398703134829241e-05, + "loss": 0.0373, + "step": 28508 + }, + { + "epoch": 8.8, + "learning_rate": 1.2398217614585987e-05, + "loss": 0.0375, + "step": 28509 + }, + { + "epoch": 8.8, + "learning_rate": 1.2397732088344356e-05, + "loss": 0.0382, + "step": 28510 + }, + { + "epoch": 8.8, + "learning_rate": 1.239724655610556e-05, + "loss": 0.0389, + "step": 28511 + }, + { + "epoch": 8.81, + "learning_rate": 1.239676101787081e-05, + "loss": 0.0332, + "step": 28512 + }, + { + "epoch": 8.81, + "learning_rate": 1.2396275473641329e-05, + "loss": 0.0367, + "step": 28513 + }, + { + "epoch": 8.81, + "learning_rate": 1.2395789923418322e-05, + "loss": 0.0398, + "step": 28514 + }, + { + "epoch": 8.81, + "learning_rate": 1.2395304367203005e-05, + "loss": 0.0382, + "step": 28515 + }, + { + "epoch": 8.81, + "learning_rate": 1.23948188049966e-05, + "loss": 0.0355, + "step": 28516 + }, + { + "epoch": 8.81, + "learning_rate": 1.2394333236800315e-05, + "loss": 0.0391, + "step": 28517 + }, + { + "epoch": 8.81, + "learning_rate": 1.2393847662615364e-05, + "loss": 0.039, + "step": 28518 + }, + { + "epoch": 8.81, + "learning_rate": 1.2393362082442965e-05, + "loss": 0.0379, + "step": 28519 + }, + { + "epoch": 8.81, + "learning_rate": 1.239287649628433e-05, + "loss": 0.0413, + "step": 28520 + }, + { + "epoch": 8.81, + "learning_rate": 1.2392390904140674e-05, + "loss": 0.0379, + "step": 28521 + }, + { + "epoch": 8.81, + "learning_rate": 1.2391905306013215e-05, + "loss": 0.0368, + "step": 28522 + }, + { + "epoch": 8.81, + "learning_rate": 1.2391419701903162e-05, + "loss": 0.0414, + "step": 28523 + }, + { + "epoch": 8.81, + "learning_rate": 1.2390934091811732e-05, + "loss": 0.0413, + "step": 28524 + }, + { + "epoch": 8.81, + "learning_rate": 1.239044847574014e-05, + "loss": 0.0409, + "step": 28525 + }, + { + "epoch": 8.81, + "learning_rate": 1.23899628536896e-05, + "loss": 0.0364, + "step": 28526 + }, + { + "epoch": 8.81, + "learning_rate": 1.2389477225661328e-05, + "loss": 0.0435, + "step": 28527 + }, + { + "epoch": 8.81, + "learning_rate": 1.2388991591656539e-05, + "loss": 0.0368, + "step": 28528 + }, + { + "epoch": 8.81, + "learning_rate": 1.2388505951676443e-05, + "loss": 0.0358, + "step": 28529 + }, + { + "epoch": 8.81, + "learning_rate": 1.238802030572226e-05, + "loss": 0.043, + "step": 28530 + }, + { + "epoch": 8.81, + "learning_rate": 1.2387534653795204e-05, + "loss": 0.0351, + "step": 28531 + }, + { + "epoch": 8.81, + "learning_rate": 1.2387048995896485e-05, + "loss": 0.0437, + "step": 28532 + }, + { + "epoch": 8.81, + "learning_rate": 1.2386563332027323e-05, + "loss": 0.0421, + "step": 28533 + }, + { + "epoch": 8.81, + "learning_rate": 1.2386077662188929e-05, + "loss": 0.0329, + "step": 28534 + }, + { + "epoch": 8.81, + "learning_rate": 1.2385591986382521e-05, + "loss": 0.0414, + "step": 28535 + }, + { + "epoch": 8.81, + "learning_rate": 1.2385106304609315e-05, + "loss": 0.0394, + "step": 28536 + }, + { + "epoch": 8.81, + "learning_rate": 1.2384620616870519e-05, + "loss": 0.0431, + "step": 28537 + }, + { + "epoch": 8.81, + "learning_rate": 1.2384134923167355e-05, + "loss": 0.0411, + "step": 28538 + }, + { + "epoch": 8.81, + "learning_rate": 1.2383649223501033e-05, + "loss": 0.0396, + "step": 28539 + }, + { + "epoch": 8.81, + "learning_rate": 1.238316351787277e-05, + "loss": 0.0401, + "step": 28540 + }, + { + "epoch": 8.81, + "learning_rate": 1.238267780628378e-05, + "loss": 0.0374, + "step": 28541 + }, + { + "epoch": 8.81, + "learning_rate": 1.2382192088735278e-05, + "loss": 0.0365, + "step": 28542 + }, + { + "epoch": 8.81, + "learning_rate": 1.238170636522848e-05, + "loss": 0.0387, + "step": 28543 + }, + { + "epoch": 8.81, + "learning_rate": 1.23812206357646e-05, + "loss": 0.0426, + "step": 28544 + }, + { + "epoch": 8.82, + "learning_rate": 1.2380734900344853e-05, + "loss": 0.0385, + "step": 28545 + }, + { + "epoch": 8.82, + "learning_rate": 1.2380249158970452e-05, + "loss": 0.0399, + "step": 28546 + }, + { + "epoch": 8.82, + "learning_rate": 1.2379763411642615e-05, + "loss": 0.0383, + "step": 28547 + }, + { + "epoch": 8.82, + "learning_rate": 1.2379277658362556e-05, + "loss": 0.0368, + "step": 28548 + }, + { + "epoch": 8.82, + "learning_rate": 1.2378791899131489e-05, + "loss": 0.0364, + "step": 28549 + }, + { + "epoch": 8.82, + "learning_rate": 1.237830613395063e-05, + "loss": 0.0411, + "step": 28550 + }, + { + "epoch": 8.82, + "learning_rate": 1.2377820362821193e-05, + "loss": 0.0421, + "step": 28551 + }, + { + "epoch": 8.82, + "learning_rate": 1.2377334585744393e-05, + "loss": 0.0384, + "step": 28552 + }, + { + "epoch": 8.82, + "learning_rate": 1.2376848802721448e-05, + "loss": 0.0357, + "step": 28553 + }, + { + "epoch": 8.82, + "learning_rate": 1.237636301375357e-05, + "loss": 0.0397, + "step": 28554 + }, + { + "epoch": 8.82, + "learning_rate": 1.2375877218841972e-05, + "loss": 0.0407, + "step": 28555 + }, + { + "epoch": 8.82, + "learning_rate": 1.2375391417987875e-05, + "loss": 0.0369, + "step": 28556 + }, + { + "epoch": 8.82, + "learning_rate": 1.2374905611192487e-05, + "loss": 0.04, + "step": 28557 + }, + { + "epoch": 8.82, + "learning_rate": 1.2374419798457029e-05, + "loss": 0.0395, + "step": 28558 + }, + { + "epoch": 8.82, + "learning_rate": 1.2373933979782716e-05, + "loss": 0.0364, + "step": 28559 + }, + { + "epoch": 8.82, + "learning_rate": 1.237344815517076e-05, + "loss": 0.0409, + "step": 28560 + }, + { + "epoch": 8.82, + "learning_rate": 1.2372962324622374e-05, + "loss": 0.0407, + "step": 28561 + }, + { + "epoch": 8.82, + "learning_rate": 1.2372476488138782e-05, + "loss": 0.0366, + "step": 28562 + }, + { + "epoch": 8.82, + "learning_rate": 1.237199064572119e-05, + "loss": 0.0399, + "step": 28563 + }, + { + "epoch": 8.82, + "learning_rate": 1.2371504797370817e-05, + "loss": 0.0411, + "step": 28564 + }, + { + "epoch": 8.82, + "learning_rate": 1.2371018943088882e-05, + "loss": 0.0396, + "step": 28565 + }, + { + "epoch": 8.82, + "learning_rate": 1.237053308287659e-05, + "loss": 0.0383, + "step": 28566 + }, + { + "epoch": 8.82, + "learning_rate": 1.2370047216735166e-05, + "loss": 0.0379, + "step": 28567 + }, + { + "epoch": 8.82, + "learning_rate": 1.2369561344665818e-05, + "loss": 0.0352, + "step": 28568 + }, + { + "epoch": 8.82, + "learning_rate": 1.2369075466669768e-05, + "loss": 0.0373, + "step": 28569 + }, + { + "epoch": 8.82, + "learning_rate": 1.236858958274823e-05, + "loss": 0.0388, + "step": 28570 + }, + { + "epoch": 8.82, + "learning_rate": 1.2368103692902413e-05, + "loss": 0.0392, + "step": 28571 + }, + { + "epoch": 8.82, + "learning_rate": 1.2367617797133542e-05, + "loss": 0.0424, + "step": 28572 + }, + { + "epoch": 8.82, + "learning_rate": 1.2367131895442824e-05, + "loss": 0.039, + "step": 28573 + }, + { + "epoch": 8.82, + "learning_rate": 1.2366645987831474e-05, + "loss": 0.0416, + "step": 28574 + }, + { + "epoch": 8.82, + "learning_rate": 1.2366160074300716e-05, + "loss": 0.0425, + "step": 28575 + }, + { + "epoch": 8.82, + "learning_rate": 1.236567415485176e-05, + "loss": 0.0391, + "step": 28576 + }, + { + "epoch": 8.83, + "learning_rate": 1.2365188229485818e-05, + "loss": 0.0384, + "step": 28577 + }, + { + "epoch": 8.83, + "learning_rate": 1.2364702298204111e-05, + "loss": 0.0371, + "step": 28578 + }, + { + "epoch": 8.83, + "learning_rate": 1.2364216361007853e-05, + "loss": 0.0384, + "step": 28579 + }, + { + "epoch": 8.83, + "learning_rate": 1.2363730417898257e-05, + "loss": 0.043, + "step": 28580 + }, + { + "epoch": 8.83, + "learning_rate": 1.236324446887654e-05, + "loss": 0.04, + "step": 28581 + }, + { + "epoch": 8.83, + "learning_rate": 1.2362758513943918e-05, + "loss": 0.0381, + "step": 28582 + }, + { + "epoch": 8.83, + "learning_rate": 1.2362272553101607e-05, + "loss": 0.04, + "step": 28583 + }, + { + "epoch": 8.83, + "learning_rate": 1.2361786586350818e-05, + "loss": 0.038, + "step": 28584 + }, + { + "epoch": 8.83, + "learning_rate": 1.2361300613692775e-05, + "loss": 0.0384, + "step": 28585 + }, + { + "epoch": 8.83, + "learning_rate": 1.2360814635128686e-05, + "loss": 0.0358, + "step": 28586 + }, + { + "epoch": 8.83, + "learning_rate": 1.236032865065977e-05, + "loss": 0.0373, + "step": 28587 + }, + { + "epoch": 8.83, + "learning_rate": 1.235984266028724e-05, + "loss": 0.0373, + "step": 28588 + }, + { + "epoch": 8.83, + "learning_rate": 1.2359356664012314e-05, + "loss": 0.0384, + "step": 28589 + }, + { + "epoch": 8.83, + "learning_rate": 1.235887066183621e-05, + "loss": 0.0376, + "step": 28590 + }, + { + "epoch": 8.83, + "learning_rate": 1.2358384653760132e-05, + "loss": 0.0424, + "step": 28591 + }, + { + "epoch": 8.83, + "learning_rate": 1.2357898639785309e-05, + "loss": 0.0389, + "step": 28592 + }, + { + "epoch": 8.83, + "learning_rate": 1.2357412619912954e-05, + "loss": 0.0389, + "step": 28593 + }, + { + "epoch": 8.83, + "learning_rate": 1.2356926594144274e-05, + "loss": 0.0382, + "step": 28594 + }, + { + "epoch": 8.83, + "learning_rate": 1.2356440562480496e-05, + "loss": 0.0412, + "step": 28595 + }, + { + "epoch": 8.83, + "learning_rate": 1.2355954524922829e-05, + "loss": 0.039, + "step": 28596 + }, + { + "epoch": 8.83, + "learning_rate": 1.2355468481472485e-05, + "loss": 0.0411, + "step": 28597 + }, + { + "epoch": 8.83, + "learning_rate": 1.235498243213069e-05, + "loss": 0.0411, + "step": 28598 + }, + { + "epoch": 8.83, + "learning_rate": 1.2354496376898654e-05, + "loss": 0.0333, + "step": 28599 + }, + { + "epoch": 8.83, + "learning_rate": 1.2354010315777594e-05, + "loss": 0.0409, + "step": 28600 + }, + { + "epoch": 8.83, + "learning_rate": 1.2353524248768722e-05, + "loss": 0.0435, + "step": 28601 + }, + { + "epoch": 8.83, + "learning_rate": 1.2353038175873258e-05, + "loss": 0.0372, + "step": 28602 + }, + { + "epoch": 8.83, + "learning_rate": 1.2352552097092417e-05, + "loss": 0.0405, + "step": 28603 + }, + { + "epoch": 8.83, + "learning_rate": 1.2352066012427413e-05, + "loss": 0.041, + "step": 28604 + }, + { + "epoch": 8.83, + "learning_rate": 1.2351579921879465e-05, + "loss": 0.0358, + "step": 28605 + }, + { + "epoch": 8.83, + "learning_rate": 1.2351093825449784e-05, + "loss": 0.0438, + "step": 28606 + }, + { + "epoch": 8.83, + "learning_rate": 1.2350607723139589e-05, + "loss": 0.0395, + "step": 28607 + }, + { + "epoch": 8.83, + "learning_rate": 1.2350121614950097e-05, + "loss": 0.0455, + "step": 28608 + }, + { + "epoch": 8.84, + "learning_rate": 1.234963550088252e-05, + "loss": 0.0413, + "step": 28609 + }, + { + "epoch": 8.84, + "learning_rate": 1.2349149380938076e-05, + "loss": 0.0408, + "step": 28610 + }, + { + "epoch": 8.84, + "learning_rate": 1.2348663255117983e-05, + "loss": 0.0432, + "step": 28611 + }, + { + "epoch": 8.84, + "learning_rate": 1.2348177123423455e-05, + "loss": 0.0419, + "step": 28612 + }, + { + "epoch": 8.84, + "learning_rate": 1.2347690985855704e-05, + "loss": 0.0338, + "step": 28613 + }, + { + "epoch": 8.84, + "learning_rate": 1.2347204842415954e-05, + "loss": 0.0459, + "step": 28614 + }, + { + "epoch": 8.84, + "learning_rate": 1.2346718693105415e-05, + "loss": 0.0437, + "step": 28615 + }, + { + "epoch": 8.84, + "learning_rate": 1.2346232537925305e-05, + "loss": 0.037, + "step": 28616 + }, + { + "epoch": 8.84, + "learning_rate": 1.2345746376876839e-05, + "loss": 0.0378, + "step": 28617 + }, + { + "epoch": 8.84, + "learning_rate": 1.2345260209961232e-05, + "loss": 0.0407, + "step": 28618 + }, + { + "epoch": 8.84, + "learning_rate": 1.2344774037179703e-05, + "loss": 0.0408, + "step": 28619 + }, + { + "epoch": 8.84, + "learning_rate": 1.2344287858533468e-05, + "loss": 0.0395, + "step": 28620 + }, + { + "epoch": 8.84, + "learning_rate": 1.2343801674023742e-05, + "loss": 0.0435, + "step": 28621 + }, + { + "epoch": 8.84, + "learning_rate": 1.2343315483651734e-05, + "loss": 0.0381, + "step": 28622 + }, + { + "epoch": 8.84, + "learning_rate": 1.2342829287418671e-05, + "loss": 0.0417, + "step": 28623 + }, + { + "epoch": 8.84, + "learning_rate": 1.2342343085325767e-05, + "loss": 0.0394, + "step": 28624 + }, + { + "epoch": 8.84, + "learning_rate": 1.2341856877374232e-05, + "loss": 0.0429, + "step": 28625 + }, + { + "epoch": 8.84, + "learning_rate": 1.2341370663565289e-05, + "loss": 0.04, + "step": 28626 + }, + { + "epoch": 8.84, + "learning_rate": 1.2340884443900149e-05, + "loss": 0.0421, + "step": 28627 + }, + { + "epoch": 8.84, + "learning_rate": 1.2340398218380028e-05, + "loss": 0.0394, + "step": 28628 + }, + { + "epoch": 8.84, + "learning_rate": 1.2339911987006148e-05, + "loss": 0.0437, + "step": 28629 + }, + { + "epoch": 8.84, + "learning_rate": 1.233942574977972e-05, + "loss": 0.041, + "step": 28630 + }, + { + "epoch": 8.84, + "learning_rate": 1.2338939506701961e-05, + "loss": 0.0397, + "step": 28631 + }, + { + "epoch": 8.84, + "learning_rate": 1.2338453257774088e-05, + "loss": 0.0411, + "step": 28632 + }, + { + "epoch": 8.84, + "learning_rate": 1.2337967002997315e-05, + "loss": 0.0346, + "step": 28633 + }, + { + "epoch": 8.84, + "learning_rate": 1.2337480742372865e-05, + "loss": 0.0446, + "step": 28634 + }, + { + "epoch": 8.84, + "learning_rate": 1.2336994475901944e-05, + "loss": 0.04, + "step": 28635 + }, + { + "epoch": 8.84, + "learning_rate": 1.2336508203585778e-05, + "loss": 0.0403, + "step": 28636 + }, + { + "epoch": 8.84, + "learning_rate": 1.2336021925425575e-05, + "loss": 0.0367, + "step": 28637 + }, + { + "epoch": 8.84, + "learning_rate": 1.2335535641422558e-05, + "loss": 0.0401, + "step": 28638 + }, + { + "epoch": 8.84, + "learning_rate": 1.2335049351577939e-05, + "loss": 0.0402, + "step": 28639 + }, + { + "epoch": 8.84, + "learning_rate": 1.2334563055892934e-05, + "loss": 0.0424, + "step": 28640 + }, + { + "epoch": 8.84, + "learning_rate": 1.2334076754368765e-05, + "loss": 0.0392, + "step": 28641 + }, + { + "epoch": 8.85, + "learning_rate": 1.233359044700664e-05, + "loss": 0.0393, + "step": 28642 + }, + { + "epoch": 8.85, + "learning_rate": 1.2333104133807783e-05, + "loss": 0.0427, + "step": 28643 + }, + { + "epoch": 8.85, + "learning_rate": 1.2332617814773407e-05, + "loss": 0.0369, + "step": 28644 + }, + { + "epoch": 8.85, + "learning_rate": 1.2332131489904725e-05, + "loss": 0.0443, + "step": 28645 + }, + { + "epoch": 8.85, + "learning_rate": 1.2331645159202958e-05, + "loss": 0.0419, + "step": 28646 + }, + { + "epoch": 8.85, + "learning_rate": 1.2331158822669327e-05, + "loss": 0.0372, + "step": 28647 + }, + { + "epoch": 8.85, + "learning_rate": 1.2330672480305034e-05, + "loss": 0.0433, + "step": 28648 + }, + { + "epoch": 8.85, + "learning_rate": 1.233018613211131e-05, + "loss": 0.037, + "step": 28649 + }, + { + "epoch": 8.85, + "learning_rate": 1.2329699778089362e-05, + "loss": 0.0393, + "step": 28650 + }, + { + "epoch": 8.85, + "learning_rate": 1.2329213418240411e-05, + "loss": 0.0421, + "step": 28651 + }, + { + "epoch": 8.85, + "learning_rate": 1.2328727052565674e-05, + "loss": 0.035, + "step": 28652 + }, + { + "epoch": 8.85, + "learning_rate": 1.2328240681066363e-05, + "loss": 0.0397, + "step": 28653 + }, + { + "epoch": 8.85, + "learning_rate": 1.2327754303743702e-05, + "loss": 0.0393, + "step": 28654 + }, + { + "epoch": 8.85, + "learning_rate": 1.23272679205989e-05, + "loss": 0.042, + "step": 28655 + }, + { + "epoch": 8.85, + "learning_rate": 1.2326781531633174e-05, + "loss": 0.0436, + "step": 28656 + }, + { + "epoch": 8.85, + "learning_rate": 1.2326295136847746e-05, + "loss": 0.0405, + "step": 28657 + }, + { + "epoch": 8.85, + "learning_rate": 1.232580873624383e-05, + "loss": 0.0427, + "step": 28658 + }, + { + "epoch": 8.85, + "learning_rate": 1.2325322329822641e-05, + "loss": 0.0363, + "step": 28659 + }, + { + "epoch": 8.85, + "learning_rate": 1.2324835917585396e-05, + "loss": 0.0427, + "step": 28660 + }, + { + "epoch": 8.85, + "learning_rate": 1.2324349499533314e-05, + "loss": 0.0394, + "step": 28661 + }, + { + "epoch": 8.85, + "learning_rate": 1.2323863075667611e-05, + "loss": 0.0379, + "step": 28662 + }, + { + "epoch": 8.85, + "learning_rate": 1.23233766459895e-05, + "loss": 0.044, + "step": 28663 + }, + { + "epoch": 8.85, + "learning_rate": 1.2322890210500201e-05, + "loss": 0.0379, + "step": 28664 + }, + { + "epoch": 8.85, + "learning_rate": 1.232240376920093e-05, + "loss": 0.041, + "step": 28665 + }, + { + "epoch": 8.85, + "learning_rate": 1.2321917322092902e-05, + "loss": 0.0446, + "step": 28666 + }, + { + "epoch": 8.85, + "learning_rate": 1.2321430869177337e-05, + "loss": 0.0424, + "step": 28667 + }, + { + "epoch": 8.85, + "learning_rate": 1.232094441045545e-05, + "loss": 0.0395, + "step": 28668 + }, + { + "epoch": 8.85, + "learning_rate": 1.2320457945928456e-05, + "loss": 0.0385, + "step": 28669 + }, + { + "epoch": 8.85, + "learning_rate": 1.2319971475597576e-05, + "loss": 0.037, + "step": 28670 + }, + { + "epoch": 8.85, + "learning_rate": 1.2319484999464025e-05, + "loss": 0.0374, + "step": 28671 + }, + { + "epoch": 8.85, + "learning_rate": 1.2318998517529014e-05, + "loss": 0.0394, + "step": 28672 + }, + { + "epoch": 8.85, + "learning_rate": 1.231851202979377e-05, + "loss": 0.0378, + "step": 28673 + }, + { + "epoch": 8.86, + "learning_rate": 1.2318025536259501e-05, + "loss": 0.0401, + "step": 28674 + }, + { + "epoch": 8.86, + "learning_rate": 1.2317539036927433e-05, + "loss": 0.0415, + "step": 28675 + }, + { + "epoch": 8.86, + "learning_rate": 1.231705253179877e-05, + "loss": 0.0376, + "step": 28676 + }, + { + "epoch": 8.86, + "learning_rate": 1.2316566020874738e-05, + "loss": 0.0331, + "step": 28677 + }, + { + "epoch": 8.86, + "learning_rate": 1.2316079504156554e-05, + "loss": 0.0371, + "step": 28678 + }, + { + "epoch": 8.86, + "learning_rate": 1.2315592981645432e-05, + "loss": 0.0378, + "step": 28679 + }, + { + "epoch": 8.86, + "learning_rate": 1.231510645334259e-05, + "loss": 0.0404, + "step": 28680 + }, + { + "epoch": 8.86, + "learning_rate": 1.2314619919249244e-05, + "loss": 0.0387, + "step": 28681 + }, + { + "epoch": 8.86, + "learning_rate": 1.2314133379366609e-05, + "loss": 0.0409, + "step": 28682 + }, + { + "epoch": 8.86, + "learning_rate": 1.231364683369591e-05, + "loss": 0.038, + "step": 28683 + }, + { + "epoch": 8.86, + "learning_rate": 1.2313160282238352e-05, + "loss": 0.0393, + "step": 28684 + }, + { + "epoch": 8.86, + "learning_rate": 1.2312673724995164e-05, + "loss": 0.0407, + "step": 28685 + }, + { + "epoch": 8.86, + "learning_rate": 1.2312187161967553e-05, + "loss": 0.0391, + "step": 28686 + }, + { + "epoch": 8.86, + "learning_rate": 1.2311700593156739e-05, + "loss": 0.0422, + "step": 28687 + }, + { + "epoch": 8.86, + "learning_rate": 1.2311214018563947e-05, + "loss": 0.0346, + "step": 28688 + }, + { + "epoch": 8.86, + "learning_rate": 1.2310727438190382e-05, + "loss": 0.0409, + "step": 28689 + }, + { + "epoch": 8.86, + "learning_rate": 1.2310240852037266e-05, + "loss": 0.0405, + "step": 28690 + }, + { + "epoch": 8.86, + "learning_rate": 1.2309754260105818e-05, + "loss": 0.0378, + "step": 28691 + }, + { + "epoch": 8.86, + "learning_rate": 1.2309267662397253e-05, + "loss": 0.0395, + "step": 28692 + }, + { + "epoch": 8.86, + "learning_rate": 1.2308781058912786e-05, + "loss": 0.038, + "step": 28693 + }, + { + "epoch": 8.86, + "learning_rate": 1.230829444965364e-05, + "loss": 0.0398, + "step": 28694 + }, + { + "epoch": 8.86, + "learning_rate": 1.2307807834621026e-05, + "loss": 0.0368, + "step": 28695 + }, + { + "epoch": 8.86, + "learning_rate": 1.2307321213816165e-05, + "loss": 0.0397, + "step": 28696 + }, + { + "epoch": 8.86, + "learning_rate": 1.2306834587240273e-05, + "loss": 0.0376, + "step": 28697 + }, + { + "epoch": 8.86, + "learning_rate": 1.2306347954894566e-05, + "loss": 0.0427, + "step": 28698 + }, + { + "epoch": 8.86, + "learning_rate": 1.2305861316780263e-05, + "loss": 0.0393, + "step": 28699 + }, + { + "epoch": 8.86, + "learning_rate": 1.230537467289858e-05, + "loss": 0.039, + "step": 28700 + }, + { + "epoch": 8.86, + "learning_rate": 1.2304888023250734e-05, + "loss": 0.0348, + "step": 28701 + }, + { + "epoch": 8.86, + "learning_rate": 1.2304401367837943e-05, + "loss": 0.0372, + "step": 28702 + }, + { + "epoch": 8.86, + "learning_rate": 1.2303914706661427e-05, + "loss": 0.0388, + "step": 28703 + }, + { + "epoch": 8.86, + "learning_rate": 1.2303428039722394e-05, + "loss": 0.0357, + "step": 28704 + }, + { + "epoch": 8.86, + "learning_rate": 1.230294136702207e-05, + "loss": 0.0352, + "step": 28705 + }, + { + "epoch": 8.87, + "learning_rate": 1.2302454688561674e-05, + "loss": 0.0413, + "step": 28706 + }, + { + "epoch": 8.87, + "learning_rate": 1.230196800434241e-05, + "loss": 0.0391, + "step": 28707 + }, + { + "epoch": 8.87, + "learning_rate": 1.2301481314365513e-05, + "loss": 0.0387, + "step": 28708 + }, + { + "epoch": 8.87, + "learning_rate": 1.2300994618632187e-05, + "loss": 0.0377, + "step": 28709 + }, + { + "epoch": 8.87, + "learning_rate": 1.2300507917143651e-05, + "loss": 0.0379, + "step": 28710 + }, + { + "epoch": 8.87, + "learning_rate": 1.2300021209901132e-05, + "loss": 0.0385, + "step": 28711 + }, + { + "epoch": 8.87, + "learning_rate": 1.2299534496905837e-05, + "loss": 0.0399, + "step": 28712 + }, + { + "epoch": 8.87, + "learning_rate": 1.2299047778158988e-05, + "loss": 0.0381, + "step": 28713 + }, + { + "epoch": 8.87, + "learning_rate": 1.22985610536618e-05, + "loss": 0.0419, + "step": 28714 + }, + { + "epoch": 8.87, + "learning_rate": 1.2298074323415488e-05, + "loss": 0.0365, + "step": 28715 + }, + { + "epoch": 8.87, + "learning_rate": 1.2297587587421278e-05, + "loss": 0.0388, + "step": 28716 + }, + { + "epoch": 8.87, + "learning_rate": 1.2297100845680381e-05, + "loss": 0.0361, + "step": 28717 + }, + { + "epoch": 8.87, + "learning_rate": 1.2296614098194012e-05, + "loss": 0.0378, + "step": 28718 + }, + { + "epoch": 8.87, + "learning_rate": 1.22961273449634e-05, + "loss": 0.0413, + "step": 28719 + }, + { + "epoch": 8.87, + "learning_rate": 1.229564058598975e-05, + "loss": 0.0359, + "step": 28720 + }, + { + "epoch": 8.87, + "learning_rate": 1.2295153821274286e-05, + "loss": 0.0376, + "step": 28721 + }, + { + "epoch": 8.87, + "learning_rate": 1.229466705081822e-05, + "loss": 0.0434, + "step": 28722 + }, + { + "epoch": 8.87, + "learning_rate": 1.2294180274622778e-05, + "loss": 0.0397, + "step": 28723 + }, + { + "epoch": 8.87, + "learning_rate": 1.229369349268917e-05, + "loss": 0.0431, + "step": 28724 + }, + { + "epoch": 8.87, + "learning_rate": 1.2293206705018616e-05, + "loss": 0.0427, + "step": 28725 + }, + { + "epoch": 8.87, + "learning_rate": 1.2292719911612334e-05, + "loss": 0.0404, + "step": 28726 + }, + { + "epoch": 8.87, + "learning_rate": 1.2292233112471543e-05, + "loss": 0.0351, + "step": 28727 + }, + { + "epoch": 8.87, + "learning_rate": 1.2291746307597457e-05, + "loss": 0.0401, + "step": 28728 + }, + { + "epoch": 8.87, + "learning_rate": 1.22912594969913e-05, + "loss": 0.0398, + "step": 28729 + }, + { + "epoch": 8.87, + "learning_rate": 1.2290772680654276e-05, + "loss": 0.0349, + "step": 28730 + }, + { + "epoch": 8.87, + "learning_rate": 1.2290285858587619e-05, + "loss": 0.0444, + "step": 28731 + }, + { + "epoch": 8.87, + "learning_rate": 1.2289799030792537e-05, + "loss": 0.041, + "step": 28732 + }, + { + "epoch": 8.87, + "learning_rate": 1.228931219727025e-05, + "loss": 0.0385, + "step": 28733 + }, + { + "epoch": 8.87, + "learning_rate": 1.2288825358021979e-05, + "loss": 0.0397, + "step": 28734 + }, + { + "epoch": 8.87, + "learning_rate": 1.2288338513048931e-05, + "loss": 0.0373, + "step": 28735 + }, + { + "epoch": 8.87, + "learning_rate": 1.2287851662352337e-05, + "loss": 0.0409, + "step": 28736 + }, + { + "epoch": 8.87, + "learning_rate": 1.2287364805933408e-05, + "loss": 0.0405, + "step": 28737 + }, + { + "epoch": 8.87, + "learning_rate": 1.2286877943793361e-05, + "loss": 0.0395, + "step": 28738 + }, + { + "epoch": 8.88, + "learning_rate": 1.2286391075933417e-05, + "loss": 0.0432, + "step": 28739 + }, + { + "epoch": 8.88, + "learning_rate": 1.228590420235479e-05, + "loss": 0.0386, + "step": 28740 + }, + { + "epoch": 8.88, + "learning_rate": 1.2285417323058699e-05, + "loss": 0.0387, + "step": 28741 + }, + { + "epoch": 8.88, + "learning_rate": 1.2284930438046365e-05, + "loss": 0.046, + "step": 28742 + }, + { + "epoch": 8.88, + "learning_rate": 1.2284443547319002e-05, + "loss": 0.042, + "step": 28743 + }, + { + "epoch": 8.88, + "learning_rate": 1.2283956650877829e-05, + "loss": 0.0415, + "step": 28744 + }, + { + "epoch": 8.88, + "learning_rate": 1.2283469748724064e-05, + "loss": 0.0436, + "step": 28745 + }, + { + "epoch": 8.88, + "learning_rate": 1.2282982840858924e-05, + "loss": 0.039, + "step": 28746 + }, + { + "epoch": 8.88, + "learning_rate": 1.2282495927283628e-05, + "loss": 0.0373, + "step": 28747 + }, + { + "epoch": 8.88, + "learning_rate": 1.2282009007999394e-05, + "loss": 0.0429, + "step": 28748 + }, + { + "epoch": 8.88, + "learning_rate": 1.2281522083007438e-05, + "loss": 0.0396, + "step": 28749 + }, + { + "epoch": 8.88, + "learning_rate": 1.228103515230898e-05, + "loss": 0.0403, + "step": 28750 + }, + { + "epoch": 8.88, + "learning_rate": 1.2280548215905237e-05, + "loss": 0.0383, + "step": 28751 + }, + { + "epoch": 8.88, + "learning_rate": 1.2280061273797426e-05, + "loss": 0.0393, + "step": 28752 + }, + { + "epoch": 8.88, + "learning_rate": 1.2279574325986768e-05, + "loss": 0.0387, + "step": 28753 + }, + { + "epoch": 8.88, + "learning_rate": 1.2279087372474477e-05, + "loss": 0.036, + "step": 28754 + }, + { + "epoch": 8.88, + "learning_rate": 1.2278600413261772e-05, + "loss": 0.0429, + "step": 28755 + }, + { + "epoch": 8.88, + "learning_rate": 1.2278113448349873e-05, + "loss": 0.0429, + "step": 28756 + }, + { + "epoch": 8.88, + "learning_rate": 1.2277626477739996e-05, + "loss": 0.0366, + "step": 28757 + }, + { + "epoch": 8.88, + "learning_rate": 1.2277139501433362e-05, + "loss": 0.036, + "step": 28758 + }, + { + "epoch": 8.88, + "learning_rate": 1.2276652519431185e-05, + "loss": 0.0395, + "step": 28759 + }, + { + "epoch": 8.88, + "learning_rate": 1.2276165531734687e-05, + "loss": 0.0418, + "step": 28760 + }, + { + "epoch": 8.88, + "learning_rate": 1.227567853834508e-05, + "loss": 0.0417, + "step": 28761 + }, + { + "epoch": 8.88, + "learning_rate": 1.227519153926359e-05, + "loss": 0.0416, + "step": 28762 + }, + { + "epoch": 8.88, + "learning_rate": 1.2274704534491426e-05, + "loss": 0.0422, + "step": 28763 + }, + { + "epoch": 8.88, + "learning_rate": 1.2274217524029814e-05, + "loss": 0.044, + "step": 28764 + }, + { + "epoch": 8.88, + "learning_rate": 1.2273730507879972e-05, + "loss": 0.0411, + "step": 28765 + }, + { + "epoch": 8.88, + "learning_rate": 1.2273243486043111e-05, + "loss": 0.0435, + "step": 28766 + }, + { + "epoch": 8.88, + "learning_rate": 1.2272756458520454e-05, + "loss": 0.0411, + "step": 28767 + }, + { + "epoch": 8.88, + "learning_rate": 1.2272269425313222e-05, + "loss": 0.0412, + "step": 28768 + }, + { + "epoch": 8.88, + "learning_rate": 1.2271782386422626e-05, + "loss": 0.0391, + "step": 28769 + }, + { + "epoch": 8.88, + "learning_rate": 1.2271295341849889e-05, + "loss": 0.0379, + "step": 28770 + }, + { + "epoch": 8.89, + "learning_rate": 1.227080829159623e-05, + "loss": 0.0369, + "step": 28771 + }, + { + "epoch": 8.89, + "learning_rate": 1.2270321235662861e-05, + "loss": 0.0385, + "step": 28772 + }, + { + "epoch": 8.89, + "learning_rate": 1.226983417405101e-05, + "loss": 0.0377, + "step": 28773 + }, + { + "epoch": 8.89, + "learning_rate": 1.2269347106761886e-05, + "loss": 0.0428, + "step": 28774 + }, + { + "epoch": 8.89, + "learning_rate": 1.2268860033796712e-05, + "loss": 0.0378, + "step": 28775 + }, + { + "epoch": 8.89, + "learning_rate": 1.2268372955156704e-05, + "loss": 0.0363, + "step": 28776 + }, + { + "epoch": 8.89, + "learning_rate": 1.2267885870843083e-05, + "loss": 0.0375, + "step": 28777 + }, + { + "epoch": 8.89, + "learning_rate": 1.2267398780857065e-05, + "loss": 0.0398, + "step": 28778 + }, + { + "epoch": 8.89, + "learning_rate": 1.2266911685199869e-05, + "loss": 0.0394, + "step": 28779 + }, + { + "epoch": 8.89, + "learning_rate": 1.2266424583872713e-05, + "loss": 0.0386, + "step": 28780 + }, + { + "epoch": 8.89, + "learning_rate": 1.2265937476876819e-05, + "loss": 0.0388, + "step": 28781 + }, + { + "epoch": 8.89, + "learning_rate": 1.2265450364213398e-05, + "loss": 0.0424, + "step": 28782 + }, + { + "epoch": 8.89, + "learning_rate": 1.2264963245883674e-05, + "loss": 0.04, + "step": 28783 + }, + { + "epoch": 8.89, + "learning_rate": 1.2264476121888865e-05, + "loss": 0.0401, + "step": 28784 + }, + { + "epoch": 8.89, + "learning_rate": 1.2263988992230187e-05, + "loss": 0.0385, + "step": 28785 + }, + { + "epoch": 8.89, + "learning_rate": 1.226350185690886e-05, + "loss": 0.0407, + "step": 28786 + }, + { + "epoch": 8.89, + "learning_rate": 1.2263014715926102e-05, + "loss": 0.0362, + "step": 28787 + }, + { + "epoch": 8.89, + "learning_rate": 1.2262527569283133e-05, + "loss": 0.0386, + "step": 28788 + }, + { + "epoch": 8.89, + "learning_rate": 1.2262040416981165e-05, + "loss": 0.0376, + "step": 28789 + }, + { + "epoch": 8.89, + "learning_rate": 1.2261553259021426e-05, + "loss": 0.0375, + "step": 28790 + }, + { + "epoch": 8.89, + "learning_rate": 1.226106609540513e-05, + "loss": 0.0355, + "step": 28791 + }, + { + "epoch": 8.89, + "learning_rate": 1.226057892613349e-05, + "loss": 0.0364, + "step": 28792 + }, + { + "epoch": 8.89, + "learning_rate": 1.2260091751207737e-05, + "loss": 0.0439, + "step": 28793 + }, + { + "epoch": 8.89, + "learning_rate": 1.2259604570629078e-05, + "loss": 0.0368, + "step": 28794 + }, + { + "epoch": 8.89, + "learning_rate": 1.2259117384398733e-05, + "loss": 0.0394, + "step": 28795 + }, + { + "epoch": 8.89, + "learning_rate": 1.2258630192517931e-05, + "loss": 0.0418, + "step": 28796 + }, + { + "epoch": 8.89, + "learning_rate": 1.2258142994987875e-05, + "loss": 0.0354, + "step": 28797 + }, + { + "epoch": 8.89, + "learning_rate": 1.2257655791809799e-05, + "loss": 0.0397, + "step": 28798 + }, + { + "epoch": 8.89, + "learning_rate": 1.2257168582984911e-05, + "loss": 0.0391, + "step": 28799 + }, + { + "epoch": 8.89, + "learning_rate": 1.2256681368514429e-05, + "loss": 0.0366, + "step": 28800 + }, + { + "epoch": 8.89, + "learning_rate": 1.2256194148399581e-05, + "loss": 0.0425, + "step": 28801 + }, + { + "epoch": 8.89, + "learning_rate": 1.2255706922641576e-05, + "loss": 0.0384, + "step": 28802 + }, + { + "epoch": 8.89, + "learning_rate": 1.2255219691241638e-05, + "loss": 0.0359, + "step": 28803 + }, + { + "epoch": 8.9, + "learning_rate": 1.2254732454200986e-05, + "loss": 0.0393, + "step": 28804 + }, + { + "epoch": 8.9, + "learning_rate": 1.2254245211520834e-05, + "loss": 0.0366, + "step": 28805 + }, + { + "epoch": 8.9, + "learning_rate": 1.2253757963202403e-05, + "loss": 0.0395, + "step": 28806 + }, + { + "epoch": 8.9, + "learning_rate": 1.2253270709246916e-05, + "loss": 0.0416, + "step": 28807 + }, + { + "epoch": 8.9, + "learning_rate": 1.2252783449655586e-05, + "loss": 0.0357, + "step": 28808 + }, + { + "epoch": 8.9, + "learning_rate": 1.2252296184429632e-05, + "loss": 0.038, + "step": 28809 + }, + { + "epoch": 8.9, + "learning_rate": 1.2251808913570277e-05, + "loss": 0.0388, + "step": 28810 + }, + { + "epoch": 8.9, + "learning_rate": 1.2251321637078736e-05, + "loss": 0.0421, + "step": 28811 + }, + { + "epoch": 8.9, + "learning_rate": 1.2250834354956229e-05, + "loss": 0.0402, + "step": 28812 + }, + { + "epoch": 8.9, + "learning_rate": 1.2250347067203976e-05, + "loss": 0.0407, + "step": 28813 + }, + { + "epoch": 8.9, + "learning_rate": 1.2249859773823194e-05, + "loss": 0.0406, + "step": 28814 + }, + { + "epoch": 8.9, + "learning_rate": 1.22493724748151e-05, + "loss": 0.0441, + "step": 28815 + }, + { + "epoch": 8.9, + "learning_rate": 1.2248885170180918e-05, + "loss": 0.0411, + "step": 28816 + }, + { + "epoch": 8.9, + "learning_rate": 1.2248397859921863e-05, + "loss": 0.0421, + "step": 28817 + }, + { + "epoch": 8.9, + "learning_rate": 1.2247910544039154e-05, + "loss": 0.0392, + "step": 28818 + }, + { + "epoch": 8.9, + "learning_rate": 1.2247423222534014e-05, + "loss": 0.0402, + "step": 28819 + }, + { + "epoch": 8.9, + "learning_rate": 1.2246935895407655e-05, + "loss": 0.0407, + "step": 28820 + }, + { + "epoch": 8.9, + "learning_rate": 1.2246448562661301e-05, + "loss": 0.0405, + "step": 28821 + }, + { + "epoch": 8.9, + "learning_rate": 1.224596122429617e-05, + "loss": 0.0399, + "step": 28822 + }, + { + "epoch": 8.9, + "learning_rate": 1.224547388031348e-05, + "loss": 0.0403, + "step": 28823 + }, + { + "epoch": 8.9, + "learning_rate": 1.2244986530714452e-05, + "loss": 0.0373, + "step": 28824 + }, + { + "epoch": 8.9, + "learning_rate": 1.22444991755003e-05, + "loss": 0.0385, + "step": 28825 + }, + { + "epoch": 8.9, + "learning_rate": 1.2244011814672245e-05, + "loss": 0.0395, + "step": 28826 + }, + { + "epoch": 8.9, + "learning_rate": 1.2243524448231512e-05, + "loss": 0.042, + "step": 28827 + }, + { + "epoch": 8.9, + "learning_rate": 1.2243037076179312e-05, + "loss": 0.0422, + "step": 28828 + }, + { + "epoch": 8.9, + "learning_rate": 1.2242549698516868e-05, + "loss": 0.0354, + "step": 28829 + }, + { + "epoch": 8.9, + "learning_rate": 1.2242062315245397e-05, + "loss": 0.0342, + "step": 28830 + }, + { + "epoch": 8.9, + "learning_rate": 1.2241574926366118e-05, + "loss": 0.0412, + "step": 28831 + }, + { + "epoch": 8.9, + "learning_rate": 1.2241087531880256e-05, + "loss": 0.0407, + "step": 28832 + }, + { + "epoch": 8.9, + "learning_rate": 1.2240600131789022e-05, + "loss": 0.0389, + "step": 28833 + }, + { + "epoch": 8.9, + "learning_rate": 1.224011272609364e-05, + "loss": 0.0379, + "step": 28834 + }, + { + "epoch": 8.9, + "learning_rate": 1.2239625314795326e-05, + "loss": 0.043, + "step": 28835 + }, + { + "epoch": 8.91, + "learning_rate": 1.2239137897895301e-05, + "loss": 0.037, + "step": 28836 + }, + { + "epoch": 8.91, + "learning_rate": 1.2238650475394784e-05, + "loss": 0.0405, + "step": 28837 + }, + { + "epoch": 8.91, + "learning_rate": 1.2238163047294996e-05, + "loss": 0.0391, + "step": 28838 + }, + { + "epoch": 8.91, + "learning_rate": 1.2237675613597152e-05, + "loss": 0.0355, + "step": 28839 + }, + { + "epoch": 8.91, + "learning_rate": 1.2237188174302473e-05, + "loss": 0.0355, + "step": 28840 + }, + { + "epoch": 8.91, + "learning_rate": 1.2236700729412176e-05, + "loss": 0.0429, + "step": 28841 + }, + { + "epoch": 8.91, + "learning_rate": 1.223621327892749e-05, + "loss": 0.0419, + "step": 28842 + }, + { + "epoch": 8.91, + "learning_rate": 1.2235725822849618e-05, + "loss": 0.0384, + "step": 28843 + }, + { + "epoch": 8.91, + "learning_rate": 1.223523836117979e-05, + "loss": 0.0417, + "step": 28844 + }, + { + "epoch": 8.91, + "learning_rate": 1.2234750893919225e-05, + "loss": 0.0429, + "step": 28845 + }, + { + "epoch": 8.91, + "learning_rate": 1.2234263421069141e-05, + "loss": 0.0378, + "step": 28846 + }, + { + "epoch": 8.91, + "learning_rate": 1.2233775942630759e-05, + "loss": 0.0401, + "step": 28847 + }, + { + "epoch": 8.91, + "learning_rate": 1.223328845860529e-05, + "loss": 0.0333, + "step": 28848 + }, + { + "epoch": 8.91, + "learning_rate": 1.2232800968993961e-05, + "loss": 0.0461, + "step": 28849 + }, + { + "epoch": 8.91, + "learning_rate": 1.2232313473797995e-05, + "loss": 0.0392, + "step": 28850 + }, + { + "epoch": 8.91, + "learning_rate": 1.2231825973018599e-05, + "loss": 0.0397, + "step": 28851 + }, + { + "epoch": 8.91, + "learning_rate": 1.2231338466657003e-05, + "loss": 0.04, + "step": 28852 + }, + { + "epoch": 8.91, + "learning_rate": 1.2230850954714421e-05, + "loss": 0.0421, + "step": 28853 + }, + { + "epoch": 8.91, + "learning_rate": 1.2230363437192072e-05, + "loss": 0.0441, + "step": 28854 + }, + { + "epoch": 8.91, + "learning_rate": 1.222987591409118e-05, + "loss": 0.039, + "step": 28855 + }, + { + "epoch": 8.91, + "learning_rate": 1.2229388385412961e-05, + "loss": 0.0426, + "step": 28856 + }, + { + "epoch": 8.91, + "learning_rate": 1.2228900851158635e-05, + "loss": 0.0383, + "step": 28857 + }, + { + "epoch": 8.91, + "learning_rate": 1.2228413311329423e-05, + "loss": 0.0451, + "step": 28858 + }, + { + "epoch": 8.91, + "learning_rate": 1.2227925765926541e-05, + "loss": 0.0365, + "step": 28859 + }, + { + "epoch": 8.91, + "learning_rate": 1.222743821495121e-05, + "loss": 0.038, + "step": 28860 + }, + { + "epoch": 8.91, + "learning_rate": 1.2226950658404651e-05, + "loss": 0.0389, + "step": 28861 + }, + { + "epoch": 8.91, + "learning_rate": 1.222646309628808e-05, + "loss": 0.0404, + "step": 28862 + }, + { + "epoch": 8.91, + "learning_rate": 1.2225975528602721e-05, + "loss": 0.0401, + "step": 28863 + }, + { + "epoch": 8.91, + "learning_rate": 1.222548795534979e-05, + "loss": 0.0375, + "step": 28864 + }, + { + "epoch": 8.91, + "learning_rate": 1.222500037653051e-05, + "loss": 0.0443, + "step": 28865 + }, + { + "epoch": 8.91, + "learning_rate": 1.2224512792146096e-05, + "loss": 0.0411, + "step": 28866 + }, + { + "epoch": 8.91, + "learning_rate": 1.222402520219777e-05, + "loss": 0.0398, + "step": 28867 + }, + { + "epoch": 8.92, + "learning_rate": 1.222353760668675e-05, + "loss": 0.0464, + "step": 28868 + }, + { + "epoch": 8.92, + "learning_rate": 1.2223050005614261e-05, + "loss": 0.0395, + "step": 28869 + }, + { + "epoch": 8.92, + "learning_rate": 1.2222562398981515e-05, + "loss": 0.0378, + "step": 28870 + }, + { + "epoch": 8.92, + "learning_rate": 1.2222074786789735e-05, + "loss": 0.0353, + "step": 28871 + }, + { + "epoch": 8.92, + "learning_rate": 1.2221587169040144e-05, + "loss": 0.0399, + "step": 28872 + }, + { + "epoch": 8.92, + "learning_rate": 1.2221099545733956e-05, + "loss": 0.0394, + "step": 28873 + }, + { + "epoch": 8.92, + "learning_rate": 1.222061191687239e-05, + "loss": 0.0355, + "step": 28874 + }, + { + "epoch": 8.92, + "learning_rate": 1.2220124282456674e-05, + "loss": 0.0379, + "step": 28875 + }, + { + "epoch": 8.92, + "learning_rate": 1.221963664248802e-05, + "loss": 0.039, + "step": 28876 + }, + { + "epoch": 8.92, + "learning_rate": 1.221914899696765e-05, + "loss": 0.0389, + "step": 28877 + }, + { + "epoch": 8.92, + "learning_rate": 1.2218661345896784e-05, + "loss": 0.0404, + "step": 28878 + }, + { + "epoch": 8.92, + "learning_rate": 1.2218173689276637e-05, + "loss": 0.04, + "step": 28879 + }, + { + "epoch": 8.92, + "learning_rate": 1.2217686027108437e-05, + "loss": 0.0383, + "step": 28880 + }, + { + "epoch": 8.92, + "learning_rate": 1.2217198359393403e-05, + "loss": 0.0408, + "step": 28881 + }, + { + "epoch": 8.92, + "learning_rate": 1.2216710686132744e-05, + "loss": 0.0345, + "step": 28882 + }, + { + "epoch": 8.92, + "learning_rate": 1.2216223007327695e-05, + "loss": 0.0417, + "step": 28883 + }, + { + "epoch": 8.92, + "learning_rate": 1.2215735322979463e-05, + "loss": 0.0422, + "step": 28884 + }, + { + "epoch": 8.92, + "learning_rate": 1.2215247633089274e-05, + "loss": 0.0396, + "step": 28885 + }, + { + "epoch": 8.92, + "learning_rate": 1.2214759937658347e-05, + "loss": 0.0377, + "step": 28886 + }, + { + "epoch": 8.92, + "learning_rate": 1.2214272236687901e-05, + "loss": 0.0403, + "step": 28887 + }, + { + "epoch": 8.92, + "learning_rate": 1.2213784530179158e-05, + "loss": 0.0396, + "step": 28888 + }, + { + "epoch": 8.92, + "learning_rate": 1.2213296818133333e-05, + "loss": 0.0411, + "step": 28889 + }, + { + "epoch": 8.92, + "learning_rate": 1.221280910055165e-05, + "loss": 0.0399, + "step": 28890 + }, + { + "epoch": 8.92, + "learning_rate": 1.221232137743533e-05, + "loss": 0.046, + "step": 28891 + }, + { + "epoch": 8.92, + "learning_rate": 1.221183364878559e-05, + "loss": 0.038, + "step": 28892 + }, + { + "epoch": 8.92, + "learning_rate": 1.2211345914603648e-05, + "loss": 0.0401, + "step": 28893 + }, + { + "epoch": 8.92, + "learning_rate": 1.2210858174890727e-05, + "loss": 0.0419, + "step": 28894 + }, + { + "epoch": 8.92, + "learning_rate": 1.2210370429648049e-05, + "loss": 0.0409, + "step": 28895 + }, + { + "epoch": 8.92, + "learning_rate": 1.220988267887683e-05, + "loss": 0.0415, + "step": 28896 + }, + { + "epoch": 8.92, + "learning_rate": 1.2209394922578292e-05, + "loss": 0.0407, + "step": 28897 + }, + { + "epoch": 8.92, + "learning_rate": 1.2208907160753653e-05, + "loss": 0.0381, + "step": 28898 + }, + { + "epoch": 8.92, + "learning_rate": 1.2208419393404136e-05, + "loss": 0.0405, + "step": 28899 + }, + { + "epoch": 8.92, + "learning_rate": 1.2207931620530957e-05, + "loss": 0.0452, + "step": 28900 + }, + { + "epoch": 8.93, + "learning_rate": 1.2207443842135342e-05, + "loss": 0.0404, + "step": 28901 + }, + { + "epoch": 8.93, + "learning_rate": 1.2206956058218504e-05, + "loss": 0.0382, + "step": 28902 + }, + { + "epoch": 8.93, + "learning_rate": 1.2206468268781669e-05, + "loss": 0.0398, + "step": 28903 + }, + { + "epoch": 8.93, + "learning_rate": 1.2205980473826053e-05, + "loss": 0.0398, + "step": 28904 + }, + { + "epoch": 8.93, + "learning_rate": 1.2205492673352877e-05, + "loss": 0.0385, + "step": 28905 + }, + { + "epoch": 8.93, + "learning_rate": 1.2205004867363364e-05, + "loss": 0.0477, + "step": 28906 + }, + { + "epoch": 8.93, + "learning_rate": 1.2204517055858729e-05, + "loss": 0.0447, + "step": 28907 + }, + { + "epoch": 8.93, + "learning_rate": 1.2204029238840192e-05, + "loss": 0.0397, + "step": 28908 + }, + { + "epoch": 8.93, + "learning_rate": 1.2203541416308982e-05, + "loss": 0.0378, + "step": 28909 + }, + { + "epoch": 8.93, + "learning_rate": 1.220305358826631e-05, + "loss": 0.0405, + "step": 28910 + }, + { + "epoch": 8.93, + "learning_rate": 1.22025657547134e-05, + "loss": 0.0381, + "step": 28911 + }, + { + "epoch": 8.93, + "learning_rate": 1.2202077915651471e-05, + "loss": 0.0401, + "step": 28912 + }, + { + "epoch": 8.93, + "learning_rate": 1.220159007108174e-05, + "loss": 0.0389, + "step": 28913 + }, + { + "epoch": 8.93, + "learning_rate": 1.2201102221005436e-05, + "loss": 0.0405, + "step": 28914 + }, + { + "epoch": 8.93, + "learning_rate": 1.2200614365423772e-05, + "loss": 0.0361, + "step": 28915 + }, + { + "epoch": 8.93, + "learning_rate": 1.220012650433797e-05, + "loss": 0.0453, + "step": 28916 + }, + { + "epoch": 8.93, + "learning_rate": 1.2199638637749251e-05, + "loss": 0.0415, + "step": 28917 + }, + { + "epoch": 8.93, + "learning_rate": 1.2199150765658834e-05, + "loss": 0.0399, + "step": 28918 + }, + { + "epoch": 8.93, + "learning_rate": 1.219866288806794e-05, + "loss": 0.044, + "step": 28919 + }, + { + "epoch": 8.93, + "learning_rate": 1.2198175004977788e-05, + "loss": 0.0424, + "step": 28920 + }, + { + "epoch": 8.93, + "learning_rate": 1.21976871163896e-05, + "loss": 0.0396, + "step": 28921 + }, + { + "epoch": 8.93, + "learning_rate": 1.2197199222304596e-05, + "loss": 0.0446, + "step": 28922 + }, + { + "epoch": 8.93, + "learning_rate": 1.2196711322723998e-05, + "loss": 0.0374, + "step": 28923 + }, + { + "epoch": 8.93, + "learning_rate": 1.219622341764902e-05, + "loss": 0.0432, + "step": 28924 + }, + { + "epoch": 8.93, + "learning_rate": 1.219573550708089e-05, + "loss": 0.0465, + "step": 28925 + }, + { + "epoch": 8.93, + "learning_rate": 1.2195247591020825e-05, + "loss": 0.0396, + "step": 28926 + }, + { + "epoch": 8.93, + "learning_rate": 1.2194759669470042e-05, + "loss": 0.0407, + "step": 28927 + }, + { + "epoch": 8.93, + "learning_rate": 1.2194271742429769e-05, + "loss": 0.0416, + "step": 28928 + }, + { + "epoch": 8.93, + "learning_rate": 1.2193783809901219e-05, + "loss": 0.0409, + "step": 28929 + }, + { + "epoch": 8.93, + "learning_rate": 1.2193295871885618e-05, + "loss": 0.0404, + "step": 28930 + }, + { + "epoch": 8.93, + "learning_rate": 1.219280792838418e-05, + "loss": 0.0399, + "step": 28931 + }, + { + "epoch": 8.93, + "learning_rate": 1.2192319979398136e-05, + "loss": 0.0382, + "step": 28932 + }, + { + "epoch": 8.94, + "learning_rate": 1.2191832024928693e-05, + "loss": 0.0421, + "step": 28933 + }, + { + "epoch": 8.94, + "learning_rate": 1.2191344064977082e-05, + "loss": 0.0363, + "step": 28934 + }, + { + "epoch": 8.94, + "learning_rate": 1.2190856099544522e-05, + "loss": 0.0418, + "step": 28935 + }, + { + "epoch": 8.94, + "learning_rate": 1.2190368128632226e-05, + "loss": 0.04, + "step": 28936 + }, + { + "epoch": 8.94, + "learning_rate": 1.2189880152241425e-05, + "loss": 0.041, + "step": 28937 + }, + { + "epoch": 8.94, + "learning_rate": 1.218939217037333e-05, + "loss": 0.0399, + "step": 28938 + }, + { + "epoch": 8.94, + "learning_rate": 1.2188904183029167e-05, + "loss": 0.0393, + "step": 28939 + }, + { + "epoch": 8.94, + "learning_rate": 1.2188416190210158e-05, + "loss": 0.0421, + "step": 28940 + }, + { + "epoch": 8.94, + "learning_rate": 1.2187928191917519e-05, + "loss": 0.0382, + "step": 28941 + }, + { + "epoch": 8.94, + "learning_rate": 1.2187440188152473e-05, + "loss": 0.0421, + "step": 28942 + }, + { + "epoch": 8.94, + "learning_rate": 1.2186952178916238e-05, + "loss": 0.0443, + "step": 28943 + }, + { + "epoch": 8.94, + "learning_rate": 1.2186464164210036e-05, + "loss": 0.0448, + "step": 28944 + }, + { + "epoch": 8.94, + "learning_rate": 1.2185976144035094e-05, + "loss": 0.0422, + "step": 28945 + }, + { + "epoch": 8.94, + "learning_rate": 1.2185488118392623e-05, + "loss": 0.0367, + "step": 28946 + }, + { + "epoch": 8.94, + "learning_rate": 1.218500008728385e-05, + "loss": 0.0372, + "step": 28947 + }, + { + "epoch": 8.94, + "learning_rate": 1.2184512050709988e-05, + "loss": 0.0372, + "step": 28948 + }, + { + "epoch": 8.94, + "learning_rate": 1.2184024008672268e-05, + "loss": 0.0429, + "step": 28949 + }, + { + "epoch": 8.94, + "learning_rate": 1.2183535961171904e-05, + "loss": 0.0399, + "step": 28950 + }, + { + "epoch": 8.94, + "learning_rate": 1.2183047908210119e-05, + "loss": 0.0422, + "step": 28951 + }, + { + "epoch": 8.94, + "learning_rate": 1.218255984978813e-05, + "loss": 0.0408, + "step": 28952 + }, + { + "epoch": 8.94, + "learning_rate": 1.2182071785907166e-05, + "loss": 0.0407, + "step": 28953 + }, + { + "epoch": 8.94, + "learning_rate": 1.2181583716568439e-05, + "loss": 0.039, + "step": 28954 + }, + { + "epoch": 8.94, + "learning_rate": 1.2181095641773175e-05, + "loss": 0.0388, + "step": 28955 + }, + { + "epoch": 8.94, + "learning_rate": 1.218060756152259e-05, + "loss": 0.0404, + "step": 28956 + }, + { + "epoch": 8.94, + "learning_rate": 1.2180119475817911e-05, + "loss": 0.039, + "step": 28957 + }, + { + "epoch": 8.94, + "learning_rate": 1.2179631384660356e-05, + "loss": 0.0413, + "step": 28958 + }, + { + "epoch": 8.94, + "learning_rate": 1.217914328805114e-05, + "loss": 0.0369, + "step": 28959 + }, + { + "epoch": 8.94, + "learning_rate": 1.2178655185991497e-05, + "loss": 0.0441, + "step": 28960 + }, + { + "epoch": 8.94, + "learning_rate": 1.2178167078482632e-05, + "loss": 0.0365, + "step": 28961 + }, + { + "epoch": 8.94, + "learning_rate": 1.2177678965525779e-05, + "loss": 0.0383, + "step": 28962 + }, + { + "epoch": 8.94, + "learning_rate": 1.2177190847122154e-05, + "loss": 0.0387, + "step": 28963 + }, + { + "epoch": 8.94, + "learning_rate": 1.2176702723272972e-05, + "loss": 0.0449, + "step": 28964 + }, + { + "epoch": 8.94, + "learning_rate": 1.2176214593979468e-05, + "loss": 0.0388, + "step": 28965 + }, + { + "epoch": 8.95, + "learning_rate": 1.217572645924285e-05, + "loss": 0.0413, + "step": 28966 + }, + { + "epoch": 8.95, + "learning_rate": 1.217523831906434e-05, + "loss": 0.0378, + "step": 28967 + }, + { + "epoch": 8.95, + "learning_rate": 1.2174750173445167e-05, + "loss": 0.04, + "step": 28968 + }, + { + "epoch": 8.95, + "learning_rate": 1.2174262022386544e-05, + "loss": 0.0382, + "step": 28969 + }, + { + "epoch": 8.95, + "learning_rate": 1.2173773865889698e-05, + "loss": 0.0386, + "step": 28970 + }, + { + "epoch": 8.95, + "learning_rate": 1.2173285703955847e-05, + "loss": 0.0364, + "step": 28971 + }, + { + "epoch": 8.95, + "learning_rate": 1.2172797536586209e-05, + "loss": 0.0434, + "step": 28972 + }, + { + "epoch": 8.95, + "learning_rate": 1.2172309363782011e-05, + "loss": 0.0413, + "step": 28973 + }, + { + "epoch": 8.95, + "learning_rate": 1.2171821185544468e-05, + "loss": 0.0387, + "step": 28974 + }, + { + "epoch": 8.95, + "learning_rate": 1.2171333001874808e-05, + "loss": 0.0419, + "step": 28975 + }, + { + "epoch": 8.95, + "learning_rate": 1.2170844812774245e-05, + "loss": 0.0421, + "step": 28976 + }, + { + "epoch": 8.95, + "learning_rate": 1.2170356618244004e-05, + "loss": 0.0409, + "step": 28977 + }, + { + "epoch": 8.95, + "learning_rate": 1.2169868418285306e-05, + "loss": 0.0402, + "step": 28978 + }, + { + "epoch": 8.95, + "learning_rate": 1.216938021289937e-05, + "loss": 0.0428, + "step": 28979 + }, + { + "epoch": 8.95, + "learning_rate": 1.216889200208742e-05, + "loss": 0.0372, + "step": 28980 + }, + { + "epoch": 8.95, + "learning_rate": 1.2168403785850675e-05, + "loss": 0.0372, + "step": 28981 + }, + { + "epoch": 8.95, + "learning_rate": 1.2167915564190356e-05, + "loss": 0.0387, + "step": 28982 + }, + { + "epoch": 8.95, + "learning_rate": 1.2167427337107685e-05, + "loss": 0.0386, + "step": 28983 + }, + { + "epoch": 8.95, + "learning_rate": 1.2166939104603884e-05, + "loss": 0.039, + "step": 28984 + }, + { + "epoch": 8.95, + "learning_rate": 1.216645086668017e-05, + "loss": 0.0369, + "step": 28985 + }, + { + "epoch": 8.95, + "learning_rate": 1.2165962623337773e-05, + "loss": 0.0363, + "step": 28986 + }, + { + "epoch": 8.95, + "learning_rate": 1.2165474374577903e-05, + "loss": 0.0446, + "step": 28987 + }, + { + "epoch": 8.95, + "learning_rate": 1.216498612040179e-05, + "loss": 0.0395, + "step": 28988 + }, + { + "epoch": 8.95, + "learning_rate": 1.2164497860810652e-05, + "loss": 0.0395, + "step": 28989 + }, + { + "epoch": 8.95, + "learning_rate": 1.2164009595805706e-05, + "loss": 0.0389, + "step": 28990 + }, + { + "epoch": 8.95, + "learning_rate": 1.2163521325388181e-05, + "loss": 0.0433, + "step": 28991 + }, + { + "epoch": 8.95, + "learning_rate": 1.2163033049559292e-05, + "loss": 0.0373, + "step": 28992 + }, + { + "epoch": 8.95, + "learning_rate": 1.2162544768320264e-05, + "loss": 0.0406, + "step": 28993 + }, + { + "epoch": 8.95, + "learning_rate": 1.2162056481672319e-05, + "loss": 0.0368, + "step": 28994 + }, + { + "epoch": 8.95, + "learning_rate": 1.2161568189616673e-05, + "loss": 0.041, + "step": 28995 + }, + { + "epoch": 8.95, + "learning_rate": 1.2161079892154555e-05, + "loss": 0.0392, + "step": 28996 + }, + { + "epoch": 8.95, + "learning_rate": 1.2160591589287178e-05, + "loss": 0.0441, + "step": 28997 + }, + { + "epoch": 8.96, + "learning_rate": 1.2160103281015768e-05, + "loss": 0.04, + "step": 28998 + }, + { + "epoch": 8.96, + "learning_rate": 1.215961496734155e-05, + "loss": 0.0392, + "step": 28999 + }, + { + "epoch": 8.96, + "learning_rate": 1.2159126648265736e-05, + "loss": 0.0404, + "step": 29000 + }, + { + "epoch": 8.96, + "learning_rate": 1.2158638323789553e-05, + "loss": 0.0386, + "step": 29001 + }, + { + "epoch": 8.96, + "learning_rate": 1.2158149993914224e-05, + "loss": 0.0386, + "step": 29002 + }, + { + "epoch": 8.96, + "learning_rate": 1.2157661658640967e-05, + "loss": 0.0409, + "step": 29003 + }, + { + "epoch": 8.96, + "learning_rate": 1.2157173317971005e-05, + "loss": 0.0359, + "step": 29004 + }, + { + "epoch": 8.96, + "learning_rate": 1.215668497190556e-05, + "loss": 0.0411, + "step": 29005 + }, + { + "epoch": 8.96, + "learning_rate": 1.2156196620445848e-05, + "loss": 0.0369, + "step": 29006 + }, + { + "epoch": 8.96, + "learning_rate": 1.21557082635931e-05, + "loss": 0.0366, + "step": 29007 + }, + { + "epoch": 8.96, + "learning_rate": 1.2155219901348532e-05, + "loss": 0.0412, + "step": 29008 + }, + { + "epoch": 8.96, + "learning_rate": 1.2154731533713365e-05, + "loss": 0.0386, + "step": 29009 + }, + { + "epoch": 8.96, + "learning_rate": 1.2154243160688819e-05, + "loss": 0.0407, + "step": 29010 + }, + { + "epoch": 8.96, + "learning_rate": 1.2153754782276121e-05, + "loss": 0.039, + "step": 29011 + }, + { + "epoch": 8.96, + "learning_rate": 1.2153266398476489e-05, + "loss": 0.041, + "step": 29012 + }, + { + "epoch": 8.96, + "learning_rate": 1.2152778009291145e-05, + "loss": 0.0437, + "step": 29013 + }, + { + "epoch": 8.96, + "learning_rate": 1.215228961472131e-05, + "loss": 0.0371, + "step": 29014 + }, + { + "epoch": 8.96, + "learning_rate": 1.2151801214768206e-05, + "loss": 0.04, + "step": 29015 + }, + { + "epoch": 8.96, + "learning_rate": 1.2151312809433054e-05, + "loss": 0.0348, + "step": 29016 + }, + { + "epoch": 8.96, + "learning_rate": 1.215082439871708e-05, + "loss": 0.0433, + "step": 29017 + }, + { + "epoch": 8.96, + "learning_rate": 1.2150335982621498e-05, + "loss": 0.0378, + "step": 29018 + }, + { + "epoch": 8.96, + "learning_rate": 1.2149847561147534e-05, + "loss": 0.039, + "step": 29019 + }, + { + "epoch": 8.96, + "learning_rate": 1.2149359134296412e-05, + "loss": 0.0389, + "step": 29020 + }, + { + "epoch": 8.96, + "learning_rate": 1.2148870702069346e-05, + "loss": 0.0349, + "step": 29021 + }, + { + "epoch": 8.96, + "learning_rate": 1.2148382264467567e-05, + "loss": 0.0412, + "step": 29022 + }, + { + "epoch": 8.96, + "learning_rate": 1.2147893821492288e-05, + "loss": 0.0405, + "step": 29023 + }, + { + "epoch": 8.96, + "learning_rate": 1.2147405373144739e-05, + "loss": 0.0444, + "step": 29024 + }, + { + "epoch": 8.96, + "learning_rate": 1.2146916919426135e-05, + "loss": 0.0429, + "step": 29025 + }, + { + "epoch": 8.96, + "learning_rate": 1.2146428460337698e-05, + "loss": 0.0405, + "step": 29026 + }, + { + "epoch": 8.96, + "learning_rate": 1.2145939995880658e-05, + "loss": 0.0447, + "step": 29027 + }, + { + "epoch": 8.96, + "learning_rate": 1.2145451526056227e-05, + "loss": 0.0407, + "step": 29028 + }, + { + "epoch": 8.96, + "learning_rate": 1.2144963050865628e-05, + "loss": 0.0383, + "step": 29029 + }, + { + "epoch": 8.97, + "learning_rate": 1.2144474570310091e-05, + "loss": 0.0385, + "step": 29030 + }, + { + "epoch": 8.97, + "learning_rate": 1.2143986084390829e-05, + "loss": 0.0393, + "step": 29031 + }, + { + "epoch": 8.97, + "learning_rate": 1.2143497593109066e-05, + "loss": 0.0465, + "step": 29032 + }, + { + "epoch": 8.97, + "learning_rate": 1.2143009096466024e-05, + "loss": 0.0416, + "step": 29033 + }, + { + "epoch": 8.97, + "learning_rate": 1.2142520594462927e-05, + "loss": 0.0397, + "step": 29034 + }, + { + "epoch": 8.97, + "learning_rate": 1.2142032087100997e-05, + "loss": 0.0402, + "step": 29035 + }, + { + "epoch": 8.97, + "learning_rate": 1.214154357438145e-05, + "loss": 0.0375, + "step": 29036 + }, + { + "epoch": 8.97, + "learning_rate": 1.2141055056305516e-05, + "loss": 0.0412, + "step": 29037 + }, + { + "epoch": 8.97, + "learning_rate": 1.214056653287441e-05, + "loss": 0.0395, + "step": 29038 + }, + { + "epoch": 8.97, + "learning_rate": 1.2140078004089357e-05, + "loss": 0.0422, + "step": 29039 + }, + { + "epoch": 8.97, + "learning_rate": 1.213958946995158e-05, + "loss": 0.0425, + "step": 29040 + }, + { + "epoch": 8.97, + "learning_rate": 1.2139100930462298e-05, + "loss": 0.0411, + "step": 29041 + }, + { + "epoch": 8.97, + "learning_rate": 1.2138612385622734e-05, + "loss": 0.0429, + "step": 29042 + }, + { + "epoch": 8.97, + "learning_rate": 1.2138123835434113e-05, + "loss": 0.0382, + "step": 29043 + }, + { + "epoch": 8.97, + "learning_rate": 1.2137635279897651e-05, + "loss": 0.0359, + "step": 29044 + }, + { + "epoch": 8.97, + "learning_rate": 1.2137146719014577e-05, + "loss": 0.0399, + "step": 29045 + }, + { + "epoch": 8.97, + "learning_rate": 1.2136658152786104e-05, + "loss": 0.0477, + "step": 29046 + }, + { + "epoch": 8.97, + "learning_rate": 1.2136169581213464e-05, + "loss": 0.0393, + "step": 29047 + }, + { + "epoch": 8.97, + "learning_rate": 1.2135681004297875e-05, + "loss": 0.0451, + "step": 29048 + }, + { + "epoch": 8.97, + "learning_rate": 1.2135192422040551e-05, + "loss": 0.0377, + "step": 29049 + }, + { + "epoch": 8.97, + "learning_rate": 1.213470383444273e-05, + "loss": 0.0419, + "step": 29050 + }, + { + "epoch": 8.97, + "learning_rate": 1.213421524150562e-05, + "loss": 0.0445, + "step": 29051 + }, + { + "epoch": 8.97, + "learning_rate": 1.2133726643230449e-05, + "loss": 0.0393, + "step": 29052 + }, + { + "epoch": 8.97, + "learning_rate": 1.2133238039618443e-05, + "loss": 0.0386, + "step": 29053 + }, + { + "epoch": 8.97, + "learning_rate": 1.2132749430670816e-05, + "loss": 0.0414, + "step": 29054 + }, + { + "epoch": 8.97, + "learning_rate": 1.2132260816388792e-05, + "loss": 0.0366, + "step": 29055 + }, + { + "epoch": 8.97, + "learning_rate": 1.2131772196773597e-05, + "loss": 0.042, + "step": 29056 + }, + { + "epoch": 8.97, + "learning_rate": 1.2131283571826451e-05, + "loss": 0.0385, + "step": 29057 + }, + { + "epoch": 8.97, + "learning_rate": 1.2130794941548576e-05, + "loss": 0.0378, + "step": 29058 + }, + { + "epoch": 8.97, + "learning_rate": 1.2130306305941193e-05, + "loss": 0.0391, + "step": 29059 + }, + { + "epoch": 8.97, + "learning_rate": 1.2129817665005525e-05, + "loss": 0.041, + "step": 29060 + }, + { + "epoch": 8.97, + "learning_rate": 1.2129329018742796e-05, + "loss": 0.0392, + "step": 29061 + }, + { + "epoch": 8.97, + "learning_rate": 1.2128840367154226e-05, + "loss": 0.0358, + "step": 29062 + }, + { + "epoch": 8.98, + "learning_rate": 1.212835171024104e-05, + "loss": 0.0453, + "step": 29063 + }, + { + "epoch": 8.98, + "learning_rate": 1.2127863048004456e-05, + "loss": 0.0426, + "step": 29064 + }, + { + "epoch": 8.98, + "learning_rate": 1.21273743804457e-05, + "loss": 0.0392, + "step": 29065 + }, + { + "epoch": 8.98, + "learning_rate": 1.2126885707565989e-05, + "loss": 0.0385, + "step": 29066 + }, + { + "epoch": 8.98, + "learning_rate": 1.2126397029366554e-05, + "loss": 0.0409, + "step": 29067 + }, + { + "epoch": 8.98, + "learning_rate": 1.212590834584861e-05, + "loss": 0.0392, + "step": 29068 + }, + { + "epoch": 8.98, + "learning_rate": 1.212541965701338e-05, + "loss": 0.0392, + "step": 29069 + }, + { + "epoch": 8.98, + "learning_rate": 1.2124930962862089e-05, + "loss": 0.0448, + "step": 29070 + }, + { + "epoch": 8.98, + "learning_rate": 1.212444226339596e-05, + "loss": 0.0405, + "step": 29071 + }, + { + "epoch": 8.98, + "learning_rate": 1.212395355861621e-05, + "loss": 0.0436, + "step": 29072 + }, + { + "epoch": 8.98, + "learning_rate": 1.2123464848524067e-05, + "loss": 0.0482, + "step": 29073 + }, + { + "epoch": 8.98, + "learning_rate": 1.212297613312075e-05, + "loss": 0.0405, + "step": 29074 + }, + { + "epoch": 8.98, + "learning_rate": 1.2122487412407481e-05, + "loss": 0.0389, + "step": 29075 + }, + { + "epoch": 8.98, + "learning_rate": 1.212199868638549e-05, + "loss": 0.0364, + "step": 29076 + }, + { + "epoch": 8.98, + "learning_rate": 1.2121509955055988e-05, + "loss": 0.0418, + "step": 29077 + }, + { + "epoch": 8.98, + "learning_rate": 1.2121021218420204e-05, + "loss": 0.0399, + "step": 29078 + }, + { + "epoch": 8.98, + "learning_rate": 1.2120532476479361e-05, + "loss": 0.0424, + "step": 29079 + }, + { + "epoch": 8.98, + "learning_rate": 1.2120043729234674e-05, + "loss": 0.0399, + "step": 29080 + }, + { + "epoch": 8.98, + "learning_rate": 1.2119554976687375e-05, + "loss": 0.0414, + "step": 29081 + }, + { + "epoch": 8.98, + "learning_rate": 1.2119066218838684e-05, + "loss": 0.0491, + "step": 29082 + }, + { + "epoch": 8.98, + "learning_rate": 1.2118577455689817e-05, + "loss": 0.0444, + "step": 29083 + }, + { + "epoch": 8.98, + "learning_rate": 1.2118088687242007e-05, + "loss": 0.0402, + "step": 29084 + }, + { + "epoch": 8.98, + "learning_rate": 1.2117599913496468e-05, + "loss": 0.0342, + "step": 29085 + }, + { + "epoch": 8.98, + "learning_rate": 1.2117111134454425e-05, + "loss": 0.0432, + "step": 29086 + }, + { + "epoch": 8.98, + "learning_rate": 1.21166223501171e-05, + "loss": 0.0408, + "step": 29087 + }, + { + "epoch": 8.98, + "learning_rate": 1.2116133560485719e-05, + "loss": 0.0382, + "step": 29088 + }, + { + "epoch": 8.98, + "learning_rate": 1.21156447655615e-05, + "loss": 0.0421, + "step": 29089 + }, + { + "epoch": 8.98, + "learning_rate": 1.2115155965345668e-05, + "loss": 0.0422, + "step": 29090 + }, + { + "epoch": 8.98, + "learning_rate": 1.2114667159839446e-05, + "loss": 0.0391, + "step": 29091 + }, + { + "epoch": 8.98, + "learning_rate": 1.2114178349044054e-05, + "loss": 0.0402, + "step": 29092 + }, + { + "epoch": 8.98, + "learning_rate": 1.2113689532960717e-05, + "loss": 0.041, + "step": 29093 + }, + { + "epoch": 8.98, + "learning_rate": 1.2113200711590657e-05, + "loss": 0.0405, + "step": 29094 + }, + { + "epoch": 8.99, + "learning_rate": 1.2112711884935099e-05, + "loss": 0.0388, + "step": 29095 + }, + { + "epoch": 8.99, + "learning_rate": 1.211222305299526e-05, + "loss": 0.0376, + "step": 29096 + }, + { + "epoch": 8.99, + "learning_rate": 1.2111734215772368e-05, + "loss": 0.0389, + "step": 29097 + }, + { + "epoch": 8.99, + "learning_rate": 1.2111245373267643e-05, + "loss": 0.0461, + "step": 29098 + }, + { + "epoch": 8.99, + "learning_rate": 1.211075652548231e-05, + "loss": 0.0408, + "step": 29099 + }, + { + "epoch": 8.99, + "learning_rate": 1.2110267672417586e-05, + "loss": 0.0436, + "step": 29100 + }, + { + "epoch": 8.99, + "learning_rate": 1.2109778814074699e-05, + "loss": 0.0413, + "step": 29101 + }, + { + "epoch": 8.99, + "learning_rate": 1.2109289950454875e-05, + "loss": 0.0415, + "step": 29102 + }, + { + "epoch": 8.99, + "learning_rate": 1.2108801081559325e-05, + "loss": 0.0389, + "step": 29103 + }, + { + "epoch": 8.99, + "learning_rate": 1.2108312207389283e-05, + "loss": 0.0334, + "step": 29104 + }, + { + "epoch": 8.99, + "learning_rate": 1.2107823327945967e-05, + "loss": 0.0393, + "step": 29105 + }, + { + "epoch": 8.99, + "learning_rate": 1.2107334443230598e-05, + "loss": 0.0401, + "step": 29106 + }, + { + "epoch": 8.99, + "learning_rate": 1.2106845553244407e-05, + "loss": 0.0394, + "step": 29107 + }, + { + "epoch": 8.99, + "learning_rate": 1.2106356657988603e-05, + "loss": 0.0414, + "step": 29108 + }, + { + "epoch": 8.99, + "learning_rate": 1.2105867757464424e-05, + "loss": 0.0361, + "step": 29109 + }, + { + "epoch": 8.99, + "learning_rate": 1.2105378851673083e-05, + "loss": 0.0443, + "step": 29110 + }, + { + "epoch": 8.99, + "learning_rate": 1.2104889940615803e-05, + "loss": 0.0405, + "step": 29111 + }, + { + "epoch": 8.99, + "learning_rate": 1.2104401024293813e-05, + "loss": 0.0423, + "step": 29112 + }, + { + "epoch": 8.99, + "learning_rate": 1.210391210270833e-05, + "loss": 0.041, + "step": 29113 + }, + { + "epoch": 8.99, + "learning_rate": 1.210342317586058e-05, + "loss": 0.0411, + "step": 29114 + }, + { + "epoch": 8.99, + "learning_rate": 1.2102934243751785e-05, + "loss": 0.038, + "step": 29115 + }, + { + "epoch": 8.99, + "learning_rate": 1.2102445306383168e-05, + "loss": 0.0409, + "step": 29116 + }, + { + "epoch": 8.99, + "learning_rate": 1.2101956363755951e-05, + "loss": 0.0437, + "step": 29117 + }, + { + "epoch": 8.99, + "learning_rate": 1.210146741587136e-05, + "loss": 0.0377, + "step": 29118 + }, + { + "epoch": 8.99, + "learning_rate": 1.2100978462730612e-05, + "loss": 0.0416, + "step": 29119 + }, + { + "epoch": 8.99, + "learning_rate": 1.2100489504334938e-05, + "loss": 0.0427, + "step": 29120 + }, + { + "epoch": 8.99, + "learning_rate": 1.2100000540685555e-05, + "loss": 0.0426, + "step": 29121 + }, + { + "epoch": 8.99, + "learning_rate": 1.2099511571783686e-05, + "loss": 0.0426, + "step": 29122 + }, + { + "epoch": 8.99, + "learning_rate": 1.2099022597630556e-05, + "loss": 0.0377, + "step": 29123 + }, + { + "epoch": 8.99, + "learning_rate": 1.2098533618227388e-05, + "loss": 0.0381, + "step": 29124 + }, + { + "epoch": 8.99, + "learning_rate": 1.2098044633575405e-05, + "loss": 0.0411, + "step": 29125 + }, + { + "epoch": 8.99, + "learning_rate": 1.2097555643675832e-05, + "loss": 0.0365, + "step": 29126 + }, + { + "epoch": 9.0, + "learning_rate": 1.2097066648529885e-05, + "loss": 0.0407, + "step": 29127 + }, + { + "epoch": 9.0, + "learning_rate": 1.2096577648138794e-05, + "loss": 0.0322, + "step": 29128 + }, + { + "epoch": 9.0, + "learning_rate": 1.2096088642503782e-05, + "loss": 0.0404, + "step": 29129 + }, + { + "epoch": 9.0, + "learning_rate": 1.2095599631626069e-05, + "loss": 0.0394, + "step": 29130 + }, + { + "epoch": 9.0, + "learning_rate": 1.2095110615506877e-05, + "loss": 0.0444, + "step": 29131 + }, + { + "epoch": 9.0, + "learning_rate": 1.2094621594147432e-05, + "loss": 0.039, + "step": 29132 + }, + { + "epoch": 9.0, + "learning_rate": 1.209413256754896e-05, + "loss": 0.039, + "step": 29133 + }, + { + "epoch": 9.0, + "learning_rate": 1.2093643535712676e-05, + "loss": 0.0429, + "step": 29134 + }, + { + "epoch": 9.0, + "learning_rate": 1.209315449863981e-05, + "loss": 0.0411, + "step": 29135 + }, + { + "epoch": 9.0, + "learning_rate": 1.2092665456331583e-05, + "loss": 0.0429, + "step": 29136 + }, + { + "epoch": 9.0, + "learning_rate": 1.2092176408789214e-05, + "loss": 0.0389, + "step": 29137 + }, + { + "epoch": 9.0, + "learning_rate": 1.2091687356013935e-05, + "loss": 0.0418, + "step": 29138 + }, + { + "epoch": 9.0, + "learning_rate": 1.2091198298006963e-05, + "loss": 0.0416, + "step": 29139 + }, + { + "epoch": 9.0, + "learning_rate": 1.2090709234769522e-05, + "loss": 0.0415, + "step": 29140 + }, + { + "epoch": 9.0, + "learning_rate": 1.2090220166302835e-05, + "loss": 0.0465, + "step": 29141 + }, + { + "epoch": 9.0, + "learning_rate": 1.2089731092608125e-05, + "loss": 0.0415, + "step": 29142 + }, + { + "epoch": 9.0, + "learning_rate": 1.2089242013686622e-05, + "loss": 0.041, + "step": 29143 + }, + { + "epoch": 9.0, + "learning_rate": 1.208875292953954e-05, + "loss": 0.0244, + "step": 29144 + }, + { + "epoch": 9.0, + "learning_rate": 1.2088263840168106e-05, + "loss": 0.018, + "step": 29145 + }, + { + "epoch": 9.0, + "learning_rate": 1.2087774745573544e-05, + "loss": 0.0194, + "step": 29146 + }, + { + "epoch": 9.0, + "learning_rate": 1.2087285645757076e-05, + "loss": 0.0214, + "step": 29147 + }, + { + "epoch": 9.0, + "learning_rate": 1.2086796540719924e-05, + "loss": 0.02, + "step": 29148 + }, + { + "epoch": 9.0, + "learning_rate": 1.2086307430463318e-05, + "loss": 0.0168, + "step": 29149 + }, + { + "epoch": 9.0, + "learning_rate": 1.2085818314988473e-05, + "loss": 0.0178, + "step": 29150 + }, + { + "epoch": 9.0, + "learning_rate": 1.2085329194296617e-05, + "loss": 0.0177, + "step": 29151 + }, + { + "epoch": 9.0, + "learning_rate": 1.2084840068388972e-05, + "loss": 0.017, + "step": 29152 + }, + { + "epoch": 9.0, + "learning_rate": 1.2084350937266765e-05, + "loss": 0.0186, + "step": 29153 + }, + { + "epoch": 9.0, + "learning_rate": 1.2083861800931209e-05, + "loss": 0.0197, + "step": 29154 + }, + { + "epoch": 9.0, + "learning_rate": 1.2083372659383538e-05, + "loss": 0.0159, + "step": 29155 + }, + { + "epoch": 9.0, + "learning_rate": 1.2082883512624974e-05, + "loss": 0.02, + "step": 29156 + }, + { + "epoch": 9.0, + "learning_rate": 1.2082394360656737e-05, + "loss": 0.0207, + "step": 29157 + }, + { + "epoch": 9.0, + "learning_rate": 1.2081905203480054e-05, + "loss": 0.0204, + "step": 29158 + }, + { + "epoch": 9.0, + "learning_rate": 1.2081416041096141e-05, + "loss": 0.0194, + "step": 29159 + }, + { + "epoch": 9.01, + "learning_rate": 1.2080926873506231e-05, + "loss": 0.0188, + "step": 29160 + }, + { + "epoch": 9.01, + "learning_rate": 1.2080437700711544e-05, + "loss": 0.0198, + "step": 29161 + }, + { + "epoch": 9.01, + "learning_rate": 1.20799485227133e-05, + "loss": 0.0167, + "step": 29162 + }, + { + "epoch": 9.01, + "learning_rate": 1.207945933951273e-05, + "loss": 0.0205, + "step": 29163 + }, + { + "epoch": 9.01, + "learning_rate": 1.2078970151111049e-05, + "loss": 0.0183, + "step": 29164 + }, + { + "epoch": 9.01, + "learning_rate": 1.2078480957509483e-05, + "loss": 0.0176, + "step": 29165 + }, + { + "epoch": 9.01, + "learning_rate": 1.207799175870926e-05, + "loss": 0.0196, + "step": 29166 + }, + { + "epoch": 9.01, + "learning_rate": 1.20775025547116e-05, + "loss": 0.0219, + "step": 29167 + }, + { + "epoch": 9.01, + "learning_rate": 1.2077013345517728e-05, + "loss": 0.0176, + "step": 29168 + }, + { + "epoch": 9.01, + "learning_rate": 1.2076524131128867e-05, + "loss": 0.0199, + "step": 29169 + }, + { + "epoch": 9.01, + "learning_rate": 1.2076034911546236e-05, + "loss": 0.0163, + "step": 29170 + }, + { + "epoch": 9.01, + "learning_rate": 1.2075545686771069e-05, + "loss": 0.0183, + "step": 29171 + }, + { + "epoch": 9.01, + "learning_rate": 1.2075056456804579e-05, + "loss": 0.0174, + "step": 29172 + }, + { + "epoch": 9.01, + "learning_rate": 1.2074567221647996e-05, + "loss": 0.0176, + "step": 29173 + }, + { + "epoch": 9.01, + "learning_rate": 1.2074077981302544e-05, + "loss": 0.0174, + "step": 29174 + }, + { + "epoch": 9.01, + "learning_rate": 1.2073588735769442e-05, + "loss": 0.0196, + "step": 29175 + }, + { + "epoch": 9.01, + "learning_rate": 1.2073099485049918e-05, + "loss": 0.0161, + "step": 29176 + }, + { + "epoch": 9.01, + "learning_rate": 1.2072610229145192e-05, + "loss": 0.0198, + "step": 29177 + }, + { + "epoch": 9.01, + "learning_rate": 1.2072120968056492e-05, + "loss": 0.0189, + "step": 29178 + }, + { + "epoch": 9.01, + "learning_rate": 1.2071631701785038e-05, + "loss": 0.0222, + "step": 29179 + }, + { + "epoch": 9.01, + "learning_rate": 1.2071142430332057e-05, + "loss": 0.0167, + "step": 29180 + }, + { + "epoch": 9.01, + "learning_rate": 1.2070653153698771e-05, + "loss": 0.0197, + "step": 29181 + }, + { + "epoch": 9.01, + "learning_rate": 1.20701638718864e-05, + "loss": 0.0191, + "step": 29182 + }, + { + "epoch": 9.01, + "learning_rate": 1.2069674584896175e-05, + "loss": 0.0184, + "step": 29183 + }, + { + "epoch": 9.01, + "learning_rate": 1.2069185292729317e-05, + "loss": 0.019, + "step": 29184 + }, + { + "epoch": 9.01, + "learning_rate": 1.2068695995387048e-05, + "loss": 0.0177, + "step": 29185 + }, + { + "epoch": 9.01, + "learning_rate": 1.2068206692870592e-05, + "loss": 0.0165, + "step": 29186 + }, + { + "epoch": 9.01, + "learning_rate": 1.2067717385181176e-05, + "loss": 0.0184, + "step": 29187 + }, + { + "epoch": 9.01, + "learning_rate": 1.2067228072320019e-05, + "loss": 0.0196, + "step": 29188 + }, + { + "epoch": 9.01, + "learning_rate": 1.2066738754288352e-05, + "loss": 0.0166, + "step": 29189 + }, + { + "epoch": 9.01, + "learning_rate": 1.2066249431087388e-05, + "loss": 0.0164, + "step": 29190 + }, + { + "epoch": 9.01, + "learning_rate": 1.206576010271836e-05, + "loss": 0.0197, + "step": 29191 + }, + { + "epoch": 9.02, + "learning_rate": 1.2065270769182494e-05, + "loss": 0.0192, + "step": 29192 + }, + { + "epoch": 9.02, + "learning_rate": 1.2064781430481004e-05, + "loss": 0.0204, + "step": 29193 + }, + { + "epoch": 9.02, + "learning_rate": 1.2064292086615121e-05, + "loss": 0.017, + "step": 29194 + }, + { + "epoch": 9.02, + "learning_rate": 1.2063802737586065e-05, + "loss": 0.0168, + "step": 29195 + }, + { + "epoch": 9.02, + "learning_rate": 1.2063313383395061e-05, + "loss": 0.017, + "step": 29196 + }, + { + "epoch": 9.02, + "learning_rate": 1.2062824024043338e-05, + "loss": 0.0187, + "step": 29197 + }, + { + "epoch": 9.02, + "learning_rate": 1.2062334659532116e-05, + "loss": 0.0182, + "step": 29198 + }, + { + "epoch": 9.02, + "learning_rate": 1.2061845289862615e-05, + "loss": 0.0166, + "step": 29199 + }, + { + "epoch": 9.02, + "learning_rate": 1.2061355915036066e-05, + "loss": 0.0193, + "step": 29200 + }, + { + "epoch": 9.02, + "learning_rate": 1.2060866535053688e-05, + "loss": 0.0187, + "step": 29201 + }, + { + "epoch": 9.02, + "learning_rate": 1.2060377149916706e-05, + "loss": 0.0194, + "step": 29202 + }, + { + "epoch": 9.02, + "learning_rate": 1.2059887759626348e-05, + "loss": 0.0182, + "step": 29203 + }, + { + "epoch": 9.02, + "learning_rate": 1.2059398364183831e-05, + "loss": 0.0164, + "step": 29204 + }, + { + "epoch": 9.02, + "learning_rate": 1.2058908963590387e-05, + "loss": 0.0198, + "step": 29205 + }, + { + "epoch": 9.02, + "learning_rate": 1.2058419557847234e-05, + "loss": 0.0163, + "step": 29206 + }, + { + "epoch": 9.02, + "learning_rate": 1.2057930146955599e-05, + "loss": 0.0194, + "step": 29207 + }, + { + "epoch": 9.02, + "learning_rate": 1.2057440730916706e-05, + "loss": 0.019, + "step": 29208 + }, + { + "epoch": 9.02, + "learning_rate": 1.2056951309731777e-05, + "loss": 0.0176, + "step": 29209 + }, + { + "epoch": 9.02, + "learning_rate": 1.205646188340204e-05, + "loss": 0.0156, + "step": 29210 + }, + { + "epoch": 9.02, + "learning_rate": 1.2055972451928714e-05, + "loss": 0.0155, + "step": 29211 + }, + { + "epoch": 9.02, + "learning_rate": 1.205548301531303e-05, + "loss": 0.0163, + "step": 29212 + }, + { + "epoch": 9.02, + "learning_rate": 1.2054993573556202e-05, + "loss": 0.0189, + "step": 29213 + }, + { + "epoch": 9.02, + "learning_rate": 1.2054504126659463e-05, + "loss": 0.0173, + "step": 29214 + }, + { + "epoch": 9.02, + "learning_rate": 1.2054014674624038e-05, + "loss": 0.0181, + "step": 29215 + }, + { + "epoch": 9.02, + "learning_rate": 1.2053525217451143e-05, + "loss": 0.0153, + "step": 29216 + }, + { + "epoch": 9.02, + "learning_rate": 1.2053035755142009e-05, + "loss": 0.0191, + "step": 29217 + }, + { + "epoch": 9.02, + "learning_rate": 1.2052546287697857e-05, + "loss": 0.0193, + "step": 29218 + }, + { + "epoch": 9.02, + "learning_rate": 1.2052056815119913e-05, + "loss": 0.0168, + "step": 29219 + }, + { + "epoch": 9.02, + "learning_rate": 1.2051567337409403e-05, + "loss": 0.0195, + "step": 29220 + }, + { + "epoch": 9.02, + "learning_rate": 1.2051077854567543e-05, + "loss": 0.0197, + "step": 29221 + }, + { + "epoch": 9.02, + "learning_rate": 1.2050588366595568e-05, + "loss": 0.0205, + "step": 29222 + }, + { + "epoch": 9.02, + "learning_rate": 1.2050098873494695e-05, + "loss": 0.0201, + "step": 29223 + }, + { + "epoch": 9.02, + "learning_rate": 1.2049609375266152e-05, + "loss": 0.0173, + "step": 29224 + }, + { + "epoch": 9.03, + "learning_rate": 1.2049119871911164e-05, + "loss": 0.0187, + "step": 29225 + }, + { + "epoch": 9.03, + "learning_rate": 1.204863036343095e-05, + "loss": 0.0173, + "step": 29226 + }, + { + "epoch": 9.03, + "learning_rate": 1.204814084982674e-05, + "loss": 0.0165, + "step": 29227 + }, + { + "epoch": 9.03, + "learning_rate": 1.2047651331099754e-05, + "loss": 0.0167, + "step": 29228 + }, + { + "epoch": 9.03, + "learning_rate": 1.2047161807251222e-05, + "loss": 0.0176, + "step": 29229 + }, + { + "epoch": 9.03, + "learning_rate": 1.2046672278282362e-05, + "loss": 0.0186, + "step": 29230 + }, + { + "epoch": 9.03, + "learning_rate": 1.2046182744194403e-05, + "loss": 0.0194, + "step": 29231 + }, + { + "epoch": 9.03, + "learning_rate": 1.2045693204988566e-05, + "loss": 0.0186, + "step": 29232 + }, + { + "epoch": 9.03, + "learning_rate": 1.2045203660666078e-05, + "loss": 0.0179, + "step": 29233 + }, + { + "epoch": 9.03, + "learning_rate": 1.2044714111228164e-05, + "loss": 0.0159, + "step": 29234 + }, + { + "epoch": 9.03, + "learning_rate": 1.2044224556676044e-05, + "loss": 0.0194, + "step": 29235 + }, + { + "epoch": 9.03, + "learning_rate": 1.204373499701095e-05, + "loss": 0.0187, + "step": 29236 + }, + { + "epoch": 9.03, + "learning_rate": 1.20432454322341e-05, + "loss": 0.0191, + "step": 29237 + }, + { + "epoch": 9.03, + "learning_rate": 1.204275586234672e-05, + "loss": 0.0174, + "step": 29238 + }, + { + "epoch": 9.03, + "learning_rate": 1.2042266287350032e-05, + "loss": 0.0206, + "step": 29239 + }, + { + "epoch": 9.03, + "learning_rate": 1.2041776707245267e-05, + "loss": 0.0204, + "step": 29240 + }, + { + "epoch": 9.03, + "learning_rate": 1.2041287122033647e-05, + "loss": 0.0172, + "step": 29241 + }, + { + "epoch": 9.03, + "learning_rate": 1.2040797531716395e-05, + "loss": 0.0171, + "step": 29242 + }, + { + "epoch": 9.03, + "learning_rate": 1.2040307936294738e-05, + "loss": 0.0185, + "step": 29243 + }, + { + "epoch": 9.03, + "learning_rate": 1.2039818335769893e-05, + "loss": 0.0176, + "step": 29244 + }, + { + "epoch": 9.03, + "learning_rate": 1.2039328730143093e-05, + "loss": 0.0187, + "step": 29245 + }, + { + "epoch": 9.03, + "learning_rate": 1.2038839119415561e-05, + "loss": 0.0156, + "step": 29246 + }, + { + "epoch": 9.03, + "learning_rate": 1.203834950358852e-05, + "loss": 0.0172, + "step": 29247 + }, + { + "epoch": 9.03, + "learning_rate": 1.2037859882663197e-05, + "loss": 0.0176, + "step": 29248 + }, + { + "epoch": 9.03, + "learning_rate": 1.2037370256640812e-05, + "loss": 0.0167, + "step": 29249 + }, + { + "epoch": 9.03, + "learning_rate": 1.2036880625522592e-05, + "loss": 0.0175, + "step": 29250 + }, + { + "epoch": 9.03, + "learning_rate": 1.2036390989309762e-05, + "loss": 0.0193, + "step": 29251 + }, + { + "epoch": 9.03, + "learning_rate": 1.203590134800355e-05, + "loss": 0.0175, + "step": 29252 + }, + { + "epoch": 9.03, + "learning_rate": 1.2035411701605175e-05, + "loss": 0.02, + "step": 29253 + }, + { + "epoch": 9.03, + "learning_rate": 1.2034922050115866e-05, + "loss": 0.019, + "step": 29254 + }, + { + "epoch": 9.03, + "learning_rate": 1.203443239353684e-05, + "loss": 0.0196, + "step": 29255 + }, + { + "epoch": 9.03, + "learning_rate": 1.2033942731869335e-05, + "loss": 0.0199, + "step": 29256 + }, + { + "epoch": 9.04, + "learning_rate": 1.2033453065114564e-05, + "loss": 0.0202, + "step": 29257 + }, + { + "epoch": 9.04, + "learning_rate": 1.2032963393273757e-05, + "loss": 0.0187, + "step": 29258 + }, + { + "epoch": 9.04, + "learning_rate": 1.2032473716348139e-05, + "loss": 0.0185, + "step": 29259 + }, + { + "epoch": 9.04, + "learning_rate": 1.203198403433893e-05, + "loss": 0.0172, + "step": 29260 + }, + { + "epoch": 9.04, + "learning_rate": 1.203149434724736e-05, + "loss": 0.0176, + "step": 29261 + }, + { + "epoch": 9.04, + "learning_rate": 1.2031004655074654e-05, + "loss": 0.015, + "step": 29262 + }, + { + "epoch": 9.04, + "learning_rate": 1.2030514957822032e-05, + "loss": 0.0184, + "step": 29263 + }, + { + "epoch": 9.04, + "learning_rate": 1.2030025255490724e-05, + "loss": 0.0162, + "step": 29264 + }, + { + "epoch": 9.04, + "learning_rate": 1.2029535548081955e-05, + "loss": 0.0155, + "step": 29265 + }, + { + "epoch": 9.04, + "learning_rate": 1.2029045835596945e-05, + "loss": 0.0185, + "step": 29266 + }, + { + "epoch": 9.04, + "learning_rate": 1.2028556118036918e-05, + "loss": 0.0191, + "step": 29267 + }, + { + "epoch": 9.04, + "learning_rate": 1.2028066395403104e-05, + "loss": 0.0161, + "step": 29268 + }, + { + "epoch": 9.04, + "learning_rate": 1.202757666769673e-05, + "loss": 0.0156, + "step": 29269 + }, + { + "epoch": 9.04, + "learning_rate": 1.2027086934919013e-05, + "loss": 0.0184, + "step": 29270 + }, + { + "epoch": 9.04, + "learning_rate": 1.2026597197071183e-05, + "loss": 0.0167, + "step": 29271 + }, + { + "epoch": 9.04, + "learning_rate": 1.202610745415446e-05, + "loss": 0.0161, + "step": 29272 + }, + { + "epoch": 9.04, + "learning_rate": 1.202561770617008e-05, + "loss": 0.0162, + "step": 29273 + }, + { + "epoch": 9.04, + "learning_rate": 1.2025127953119258e-05, + "loss": 0.0178, + "step": 29274 + }, + { + "epoch": 9.04, + "learning_rate": 1.2024638195003218e-05, + "loss": 0.0172, + "step": 29275 + }, + { + "epoch": 9.04, + "learning_rate": 1.202414843182319e-05, + "loss": 0.0171, + "step": 29276 + }, + { + "epoch": 9.04, + "learning_rate": 1.20236586635804e-05, + "loss": 0.0183, + "step": 29277 + }, + { + "epoch": 9.04, + "learning_rate": 1.202316889027607e-05, + "loss": 0.0171, + "step": 29278 + }, + { + "epoch": 9.04, + "learning_rate": 1.2022679111911426e-05, + "loss": 0.0154, + "step": 29279 + }, + { + "epoch": 9.04, + "learning_rate": 1.202218932848769e-05, + "loss": 0.0187, + "step": 29280 + }, + { + "epoch": 9.04, + "learning_rate": 1.2021699540006089e-05, + "loss": 0.0153, + "step": 29281 + }, + { + "epoch": 9.04, + "learning_rate": 1.2021209746467855e-05, + "loss": 0.0152, + "step": 29282 + }, + { + "epoch": 9.04, + "learning_rate": 1.2020719947874202e-05, + "loss": 0.0178, + "step": 29283 + }, + { + "epoch": 9.04, + "learning_rate": 1.202023014422636e-05, + "loss": 0.0187, + "step": 29284 + }, + { + "epoch": 9.04, + "learning_rate": 1.2019740335525553e-05, + "loss": 0.0181, + "step": 29285 + }, + { + "epoch": 9.04, + "learning_rate": 1.2019250521773009e-05, + "loss": 0.0185, + "step": 29286 + }, + { + "epoch": 9.04, + "learning_rate": 1.2018760702969951e-05, + "loss": 0.0161, + "step": 29287 + }, + { + "epoch": 9.04, + "learning_rate": 1.2018270879117604e-05, + "loss": 0.0176, + "step": 29288 + }, + { + "epoch": 9.05, + "learning_rate": 1.2017781050217194e-05, + "loss": 0.017, + "step": 29289 + }, + { + "epoch": 9.05, + "learning_rate": 1.2017291216269944e-05, + "loss": 0.0191, + "step": 29290 + }, + { + "epoch": 9.05, + "learning_rate": 1.2016801377277082e-05, + "loss": 0.0168, + "step": 29291 + }, + { + "epoch": 9.05, + "learning_rate": 1.2016311533239831e-05, + "loss": 0.0165, + "step": 29292 + }, + { + "epoch": 9.05, + "learning_rate": 1.2015821684159418e-05, + "loss": 0.0191, + "step": 29293 + }, + { + "epoch": 9.05, + "learning_rate": 1.2015331830037067e-05, + "loss": 0.0157, + "step": 29294 + }, + { + "epoch": 9.05, + "learning_rate": 1.2014841970874003e-05, + "loss": 0.0183, + "step": 29295 + }, + { + "epoch": 9.05, + "learning_rate": 1.2014352106671452e-05, + "loss": 0.0184, + "step": 29296 + }, + { + "epoch": 9.05, + "learning_rate": 1.2013862237430643e-05, + "loss": 0.0195, + "step": 29297 + }, + { + "epoch": 9.05, + "learning_rate": 1.201337236315279e-05, + "loss": 0.0206, + "step": 29298 + }, + { + "epoch": 9.05, + "learning_rate": 1.201288248383913e-05, + "loss": 0.0179, + "step": 29299 + }, + { + "epoch": 9.05, + "learning_rate": 1.2012392599490882e-05, + "loss": 0.0191, + "step": 29300 + }, + { + "epoch": 9.05, + "learning_rate": 1.2011902710109273e-05, + "loss": 0.019, + "step": 29301 + }, + { + "epoch": 9.05, + "learning_rate": 1.2011412815695531e-05, + "loss": 0.0182, + "step": 29302 + }, + { + "epoch": 9.05, + "learning_rate": 1.2010922916250876e-05, + "loss": 0.0188, + "step": 29303 + }, + { + "epoch": 9.05, + "learning_rate": 1.2010433011776536e-05, + "loss": 0.0155, + "step": 29304 + }, + { + "epoch": 9.05, + "learning_rate": 1.200994310227374e-05, + "loss": 0.0181, + "step": 29305 + }, + { + "epoch": 9.05, + "learning_rate": 1.2009453187743705e-05, + "loss": 0.0204, + "step": 29306 + }, + { + "epoch": 9.05, + "learning_rate": 1.2008963268187665e-05, + "loss": 0.0188, + "step": 29307 + }, + { + "epoch": 9.05, + "learning_rate": 1.200847334360684e-05, + "loss": 0.0166, + "step": 29308 + }, + { + "epoch": 9.05, + "learning_rate": 1.2007983414002453e-05, + "loss": 0.0184, + "step": 29309 + }, + { + "epoch": 9.05, + "learning_rate": 1.200749347937574e-05, + "loss": 0.0173, + "step": 29310 + }, + { + "epoch": 9.05, + "learning_rate": 1.2007003539727915e-05, + "loss": 0.0192, + "step": 29311 + }, + { + "epoch": 9.05, + "learning_rate": 1.200651359506021e-05, + "loss": 0.022, + "step": 29312 + }, + { + "epoch": 9.05, + "learning_rate": 1.2006023645373848e-05, + "loss": 0.0171, + "step": 29313 + }, + { + "epoch": 9.05, + "learning_rate": 1.2005533690670054e-05, + "loss": 0.0181, + "step": 29314 + }, + { + "epoch": 9.05, + "learning_rate": 1.2005043730950057e-05, + "loss": 0.0172, + "step": 29315 + }, + { + "epoch": 9.05, + "learning_rate": 1.2004553766215077e-05, + "loss": 0.0168, + "step": 29316 + }, + { + "epoch": 9.05, + "learning_rate": 1.2004063796466344e-05, + "loss": 0.0164, + "step": 29317 + }, + { + "epoch": 9.05, + "learning_rate": 1.200357382170508e-05, + "loss": 0.016, + "step": 29318 + }, + { + "epoch": 9.05, + "learning_rate": 1.2003083841932515e-05, + "loss": 0.0212, + "step": 29319 + }, + { + "epoch": 9.05, + "learning_rate": 1.2002593857149872e-05, + "loss": 0.018, + "step": 29320 + }, + { + "epoch": 9.05, + "learning_rate": 1.2002103867358375e-05, + "loss": 0.0195, + "step": 29321 + }, + { + "epoch": 9.06, + "learning_rate": 1.2001613872559252e-05, + "loss": 0.0224, + "step": 29322 + }, + { + "epoch": 9.06, + "learning_rate": 1.2001123872753727e-05, + "loss": 0.018, + "step": 29323 + }, + { + "epoch": 9.06, + "learning_rate": 1.2000633867943026e-05, + "loss": 0.0155, + "step": 29324 + }, + { + "epoch": 9.06, + "learning_rate": 1.2000143858128374e-05, + "loss": 0.0212, + "step": 29325 + }, + { + "epoch": 9.06, + "learning_rate": 1.1999653843311001e-05, + "loss": 0.0172, + "step": 29326 + }, + { + "epoch": 9.06, + "learning_rate": 1.1999163823492125e-05, + "loss": 0.0156, + "step": 29327 + }, + { + "epoch": 9.06, + "learning_rate": 1.1998673798672979e-05, + "loss": 0.0194, + "step": 29328 + }, + { + "epoch": 9.06, + "learning_rate": 1.1998183768854783e-05, + "loss": 0.0242, + "step": 29329 + }, + { + "epoch": 9.06, + "learning_rate": 1.1997693734038765e-05, + "loss": 0.0174, + "step": 29330 + }, + { + "epoch": 9.06, + "learning_rate": 1.1997203694226155e-05, + "loss": 0.0176, + "step": 29331 + }, + { + "epoch": 9.06, + "learning_rate": 1.1996713649418167e-05, + "loss": 0.0203, + "step": 29332 + }, + { + "epoch": 9.06, + "learning_rate": 1.199622359961604e-05, + "loss": 0.0149, + "step": 29333 + }, + { + "epoch": 9.06, + "learning_rate": 1.1995733544820992e-05, + "loss": 0.0165, + "step": 29334 + }, + { + "epoch": 9.06, + "learning_rate": 1.1995243485034246e-05, + "loss": 0.017, + "step": 29335 + }, + { + "epoch": 9.06, + "learning_rate": 1.1994753420257037e-05, + "loss": 0.0175, + "step": 29336 + }, + { + "epoch": 9.06, + "learning_rate": 1.1994263350490582e-05, + "loss": 0.0188, + "step": 29337 + }, + { + "epoch": 9.06, + "learning_rate": 1.1993773275736116e-05, + "loss": 0.0202, + "step": 29338 + }, + { + "epoch": 9.06, + "learning_rate": 1.1993283195994856e-05, + "loss": 0.0177, + "step": 29339 + }, + { + "epoch": 9.06, + "learning_rate": 1.199279311126803e-05, + "loss": 0.0174, + "step": 29340 + }, + { + "epoch": 9.06, + "learning_rate": 1.199230302155687e-05, + "loss": 0.0171, + "step": 29341 + }, + { + "epoch": 9.06, + "learning_rate": 1.1991812926862594e-05, + "loss": 0.0172, + "step": 29342 + }, + { + "epoch": 9.06, + "learning_rate": 1.1991322827186428e-05, + "loss": 0.02, + "step": 29343 + }, + { + "epoch": 9.06, + "learning_rate": 1.1990832722529603e-05, + "loss": 0.0169, + "step": 29344 + }, + { + "epoch": 9.06, + "learning_rate": 1.1990342612893341e-05, + "loss": 0.0164, + "step": 29345 + }, + { + "epoch": 9.06, + "learning_rate": 1.1989852498278872e-05, + "loss": 0.0171, + "step": 29346 + }, + { + "epoch": 9.06, + "learning_rate": 1.1989362378687418e-05, + "loss": 0.018, + "step": 29347 + }, + { + "epoch": 9.06, + "learning_rate": 1.1988872254120202e-05, + "loss": 0.0187, + "step": 29348 + }, + { + "epoch": 9.06, + "learning_rate": 1.1988382124578458e-05, + "loss": 0.0178, + "step": 29349 + }, + { + "epoch": 9.06, + "learning_rate": 1.1987891990063405e-05, + "loss": 0.019, + "step": 29350 + }, + { + "epoch": 9.06, + "learning_rate": 1.1987401850576275e-05, + "loss": 0.0197, + "step": 29351 + }, + { + "epoch": 9.06, + "learning_rate": 1.1986911706118285e-05, + "loss": 0.0159, + "step": 29352 + }, + { + "epoch": 9.06, + "learning_rate": 1.198642155669067e-05, + "loss": 0.0187, + "step": 29353 + }, + { + "epoch": 9.07, + "learning_rate": 1.1985931402294652e-05, + "loss": 0.0181, + "step": 29354 + }, + { + "epoch": 9.07, + "learning_rate": 1.1985441242931458e-05, + "loss": 0.0199, + "step": 29355 + }, + { + "epoch": 9.07, + "learning_rate": 1.1984951078602313e-05, + "loss": 0.0159, + "step": 29356 + }, + { + "epoch": 9.07, + "learning_rate": 1.1984460909308442e-05, + "loss": 0.0181, + "step": 29357 + }, + { + "epoch": 9.07, + "learning_rate": 1.1983970735051074e-05, + "loss": 0.0196, + "step": 29358 + }, + { + "epoch": 9.07, + "learning_rate": 1.1983480555831434e-05, + "loss": 0.0185, + "step": 29359 + }, + { + "epoch": 9.07, + "learning_rate": 1.1982990371650745e-05, + "loss": 0.0174, + "step": 29360 + }, + { + "epoch": 9.07, + "learning_rate": 1.1982500182510237e-05, + "loss": 0.0171, + "step": 29361 + }, + { + "epoch": 9.07, + "learning_rate": 1.1982009988411135e-05, + "loss": 0.0169, + "step": 29362 + }, + { + "epoch": 9.07, + "learning_rate": 1.1981519789354661e-05, + "loss": 0.0182, + "step": 29363 + }, + { + "epoch": 9.07, + "learning_rate": 1.198102958534205e-05, + "loss": 0.0172, + "step": 29364 + }, + { + "epoch": 9.07, + "learning_rate": 1.1980539376374518e-05, + "loss": 0.0175, + "step": 29365 + }, + { + "epoch": 9.07, + "learning_rate": 1.1980049162453297e-05, + "loss": 0.0174, + "step": 29366 + }, + { + "epoch": 9.07, + "learning_rate": 1.1979558943579614e-05, + "loss": 0.0186, + "step": 29367 + }, + { + "epoch": 9.07, + "learning_rate": 1.1979068719754691e-05, + "loss": 0.018, + "step": 29368 + }, + { + "epoch": 9.07, + "learning_rate": 1.1978578490979755e-05, + "loss": 0.0195, + "step": 29369 + }, + { + "epoch": 9.07, + "learning_rate": 1.1978088257256038e-05, + "loss": 0.0168, + "step": 29370 + }, + { + "epoch": 9.07, + "learning_rate": 1.1977598018584757e-05, + "loss": 0.0199, + "step": 29371 + }, + { + "epoch": 9.07, + "learning_rate": 1.1977107774967142e-05, + "loss": 0.0188, + "step": 29372 + }, + { + "epoch": 9.07, + "learning_rate": 1.1976617526404424e-05, + "loss": 0.0188, + "step": 29373 + }, + { + "epoch": 9.07, + "learning_rate": 1.1976127272897821e-05, + "loss": 0.0161, + "step": 29374 + }, + { + "epoch": 9.07, + "learning_rate": 1.1975637014448567e-05, + "loss": 0.018, + "step": 29375 + }, + { + "epoch": 9.07, + "learning_rate": 1.1975146751057883e-05, + "loss": 0.0171, + "step": 29376 + }, + { + "epoch": 9.07, + "learning_rate": 1.1974656482726996e-05, + "loss": 0.0175, + "step": 29377 + }, + { + "epoch": 9.07, + "learning_rate": 1.1974166209457133e-05, + "loss": 0.0179, + "step": 29378 + }, + { + "epoch": 9.07, + "learning_rate": 1.1973675931249522e-05, + "loss": 0.0172, + "step": 29379 + }, + { + "epoch": 9.07, + "learning_rate": 1.1973185648105386e-05, + "loss": 0.0196, + "step": 29380 + }, + { + "epoch": 9.07, + "learning_rate": 1.1972695360025953e-05, + "loss": 0.0182, + "step": 29381 + }, + { + "epoch": 9.07, + "learning_rate": 1.197220506701245e-05, + "loss": 0.022, + "step": 29382 + }, + { + "epoch": 9.07, + "learning_rate": 1.1971714769066101e-05, + "loss": 0.0186, + "step": 29383 + }, + { + "epoch": 9.07, + "learning_rate": 1.1971224466188134e-05, + "loss": 0.0181, + "step": 29384 + }, + { + "epoch": 9.07, + "learning_rate": 1.1970734158379776e-05, + "loss": 0.0162, + "step": 29385 + }, + { + "epoch": 9.08, + "learning_rate": 1.1970243845642252e-05, + "loss": 0.0181, + "step": 29386 + }, + { + "epoch": 9.08, + "learning_rate": 1.1969753527976788e-05, + "loss": 0.0204, + "step": 29387 + }, + { + "epoch": 9.08, + "learning_rate": 1.1969263205384612e-05, + "loss": 0.0166, + "step": 29388 + }, + { + "epoch": 9.08, + "learning_rate": 1.1968772877866947e-05, + "loss": 0.0182, + "step": 29389 + }, + { + "epoch": 9.08, + "learning_rate": 1.1968282545425028e-05, + "loss": 0.0172, + "step": 29390 + }, + { + "epoch": 9.08, + "learning_rate": 1.1967792208060068e-05, + "loss": 0.0171, + "step": 29391 + }, + { + "epoch": 9.08, + "learning_rate": 1.1967301865773306e-05, + "loss": 0.0177, + "step": 29392 + }, + { + "epoch": 9.08, + "learning_rate": 1.1966811518565961e-05, + "loss": 0.0171, + "step": 29393 + }, + { + "epoch": 9.08, + "learning_rate": 1.196632116643926e-05, + "loss": 0.0187, + "step": 29394 + }, + { + "epoch": 9.08, + "learning_rate": 1.1965830809394437e-05, + "loss": 0.0192, + "step": 29395 + }, + { + "epoch": 9.08, + "learning_rate": 1.196534044743271e-05, + "loss": 0.0168, + "step": 29396 + }, + { + "epoch": 9.08, + "learning_rate": 1.1964850080555306e-05, + "loss": 0.0158, + "step": 29397 + }, + { + "epoch": 9.08, + "learning_rate": 1.1964359708763456e-05, + "loss": 0.0182, + "step": 29398 + }, + { + "epoch": 9.08, + "learning_rate": 1.1963869332058382e-05, + "loss": 0.0179, + "step": 29399 + }, + { + "epoch": 9.08, + "learning_rate": 1.1963378950441314e-05, + "loss": 0.0174, + "step": 29400 + }, + { + "epoch": 9.08, + "learning_rate": 1.1962888563913475e-05, + "loss": 0.019, + "step": 29401 + }, + { + "epoch": 9.08, + "learning_rate": 1.1962398172476095e-05, + "loss": 0.017, + "step": 29402 + }, + { + "epoch": 9.08, + "learning_rate": 1.19619077761304e-05, + "loss": 0.0178, + "step": 29403 + }, + { + "epoch": 9.08, + "learning_rate": 1.1961417374877616e-05, + "loss": 0.0179, + "step": 29404 + }, + { + "epoch": 9.08, + "learning_rate": 1.1960926968718968e-05, + "loss": 0.0192, + "step": 29405 + }, + { + "epoch": 9.08, + "learning_rate": 1.1960436557655686e-05, + "loss": 0.0195, + "step": 29406 + }, + { + "epoch": 9.08, + "learning_rate": 1.1959946141688991e-05, + "loss": 0.0173, + "step": 29407 + }, + { + "epoch": 9.08, + "learning_rate": 1.1959455720820117e-05, + "loss": 0.0156, + "step": 29408 + }, + { + "epoch": 9.08, + "learning_rate": 1.1958965295050284e-05, + "loss": 0.0167, + "step": 29409 + }, + { + "epoch": 9.08, + "learning_rate": 1.1958474864380727e-05, + "loss": 0.0172, + "step": 29410 + }, + { + "epoch": 9.08, + "learning_rate": 1.1957984428812658e-05, + "loss": 0.0164, + "step": 29411 + }, + { + "epoch": 9.08, + "learning_rate": 1.195749398834732e-05, + "loss": 0.0163, + "step": 29412 + }, + { + "epoch": 9.08, + "learning_rate": 1.1957003542985931e-05, + "loss": 0.0165, + "step": 29413 + }, + { + "epoch": 9.08, + "learning_rate": 1.1956513092729718e-05, + "loss": 0.0169, + "step": 29414 + }, + { + "epoch": 9.08, + "learning_rate": 1.1956022637579911e-05, + "loss": 0.0215, + "step": 29415 + }, + { + "epoch": 9.08, + "learning_rate": 1.1955532177537735e-05, + "loss": 0.0167, + "step": 29416 + }, + { + "epoch": 9.08, + "learning_rate": 1.1955041712604411e-05, + "loss": 0.0181, + "step": 29417 + }, + { + "epoch": 9.08, + "learning_rate": 1.1954551242781176e-05, + "loss": 0.0171, + "step": 29418 + }, + { + "epoch": 9.09, + "learning_rate": 1.195406076806925e-05, + "loss": 0.0177, + "step": 29419 + }, + { + "epoch": 9.09, + "learning_rate": 1.1953570288469862e-05, + "loss": 0.0195, + "step": 29420 + }, + { + "epoch": 9.09, + "learning_rate": 1.195307980398424e-05, + "loss": 0.0172, + "step": 29421 + }, + { + "epoch": 9.09, + "learning_rate": 1.1952589314613605e-05, + "loss": 0.0196, + "step": 29422 + }, + { + "epoch": 9.09, + "learning_rate": 1.1952098820359192e-05, + "loss": 0.0172, + "step": 29423 + }, + { + "epoch": 9.09, + "learning_rate": 1.1951608321222223e-05, + "loss": 0.0221, + "step": 29424 + }, + { + "epoch": 9.09, + "learning_rate": 1.1951117817203926e-05, + "loss": 0.0179, + "step": 29425 + }, + { + "epoch": 9.09, + "learning_rate": 1.1950627308305526e-05, + "loss": 0.0197, + "step": 29426 + }, + { + "epoch": 9.09, + "learning_rate": 1.195013679452825e-05, + "loss": 0.0188, + "step": 29427 + }, + { + "epoch": 9.09, + "learning_rate": 1.194964627587333e-05, + "loss": 0.0196, + "step": 29428 + }, + { + "epoch": 9.09, + "learning_rate": 1.1949155752341988e-05, + "loss": 0.016, + "step": 29429 + }, + { + "epoch": 9.09, + "learning_rate": 1.1948665223935449e-05, + "loss": 0.0201, + "step": 29430 + }, + { + "epoch": 9.09, + "learning_rate": 1.1948174690654945e-05, + "loss": 0.0171, + "step": 29431 + }, + { + "epoch": 9.09, + "learning_rate": 1.1947684152501701e-05, + "loss": 0.0166, + "step": 29432 + }, + { + "epoch": 9.09, + "learning_rate": 1.1947193609476944e-05, + "loss": 0.0172, + "step": 29433 + }, + { + "epoch": 9.09, + "learning_rate": 1.1946703061581901e-05, + "loss": 0.0176, + "step": 29434 + }, + { + "epoch": 9.09, + "learning_rate": 1.1946212508817796e-05, + "loss": 0.0194, + "step": 29435 + }, + { + "epoch": 9.09, + "learning_rate": 1.1945721951185862e-05, + "loss": 0.0197, + "step": 29436 + }, + { + "epoch": 9.09, + "learning_rate": 1.194523138868732e-05, + "loss": 0.0174, + "step": 29437 + }, + { + "epoch": 9.09, + "learning_rate": 1.1944740821323399e-05, + "loss": 0.0177, + "step": 29438 + }, + { + "epoch": 9.09, + "learning_rate": 1.1944250249095329e-05, + "loss": 0.0174, + "step": 29439 + }, + { + "epoch": 9.09, + "learning_rate": 1.1943759672004334e-05, + "loss": 0.0196, + "step": 29440 + }, + { + "epoch": 9.09, + "learning_rate": 1.1943269090051644e-05, + "loss": 0.0193, + "step": 29441 + }, + { + "epoch": 9.09, + "learning_rate": 1.1942778503238476e-05, + "loss": 0.0173, + "step": 29442 + }, + { + "epoch": 9.09, + "learning_rate": 1.194228791156607e-05, + "loss": 0.0193, + "step": 29443 + }, + { + "epoch": 9.09, + "learning_rate": 1.1941797315035648e-05, + "loss": 0.0171, + "step": 29444 + }, + { + "epoch": 9.09, + "learning_rate": 1.1941306713648433e-05, + "loss": 0.019, + "step": 29445 + }, + { + "epoch": 9.09, + "learning_rate": 1.1940816107405661e-05, + "loss": 0.0196, + "step": 29446 + }, + { + "epoch": 9.09, + "learning_rate": 1.1940325496308552e-05, + "loss": 0.0166, + "step": 29447 + }, + { + "epoch": 9.09, + "learning_rate": 1.1939834880358332e-05, + "loss": 0.0193, + "step": 29448 + }, + { + "epoch": 9.09, + "learning_rate": 1.1939344259556236e-05, + "loss": 0.0201, + "step": 29449 + }, + { + "epoch": 9.09, + "learning_rate": 1.193885363390348e-05, + "loss": 0.0176, + "step": 29450 + }, + { + "epoch": 9.1, + "learning_rate": 1.1938363003401303e-05, + "loss": 0.02, + "step": 29451 + }, + { + "epoch": 9.1, + "learning_rate": 1.1937872368050926e-05, + "loss": 0.0172, + "step": 29452 + }, + { + "epoch": 9.1, + "learning_rate": 1.1937381727853573e-05, + "loss": 0.019, + "step": 29453 + }, + { + "epoch": 9.1, + "learning_rate": 1.193689108281048e-05, + "loss": 0.0161, + "step": 29454 + }, + { + "epoch": 9.1, + "learning_rate": 1.1936400432922866e-05, + "loss": 0.0195, + "step": 29455 + }, + { + "epoch": 9.1, + "learning_rate": 1.1935909778191962e-05, + "loss": 0.0212, + "step": 29456 + }, + { + "epoch": 9.1, + "learning_rate": 1.1935419118618993e-05, + "loss": 0.0191, + "step": 29457 + }, + { + "epoch": 9.1, + "learning_rate": 1.193492845420519e-05, + "loss": 0.0171, + "step": 29458 + }, + { + "epoch": 9.1, + "learning_rate": 1.1934437784951778e-05, + "loss": 0.0165, + "step": 29459 + }, + { + "epoch": 9.1, + "learning_rate": 1.1933947110859985e-05, + "loss": 0.0177, + "step": 29460 + }, + { + "epoch": 9.1, + "learning_rate": 1.1933456431931034e-05, + "loss": 0.0182, + "step": 29461 + }, + { + "epoch": 9.1, + "learning_rate": 1.1932965748166159e-05, + "loss": 0.0175, + "step": 29462 + }, + { + "epoch": 9.1, + "learning_rate": 1.1932475059566584e-05, + "loss": 0.018, + "step": 29463 + }, + { + "epoch": 9.1, + "learning_rate": 1.1931984366133537e-05, + "loss": 0.0192, + "step": 29464 + }, + { + "epoch": 9.1, + "learning_rate": 1.1931493667868242e-05, + "loss": 0.0198, + "step": 29465 + }, + { + "epoch": 9.1, + "learning_rate": 1.193100296477193e-05, + "loss": 0.0198, + "step": 29466 + }, + { + "epoch": 9.1, + "learning_rate": 1.1930512256845828e-05, + "loss": 0.0176, + "step": 29467 + }, + { + "epoch": 9.1, + "learning_rate": 1.1930021544091161e-05, + "loss": 0.0185, + "step": 29468 + }, + { + "epoch": 9.1, + "learning_rate": 1.1929530826509161e-05, + "loss": 0.0159, + "step": 29469 + }, + { + "epoch": 9.1, + "learning_rate": 1.1929040104101049e-05, + "loss": 0.0167, + "step": 29470 + }, + { + "epoch": 9.1, + "learning_rate": 1.1928549376868057e-05, + "loss": 0.0176, + "step": 29471 + }, + { + "epoch": 9.1, + "learning_rate": 1.1928058644811416e-05, + "loss": 0.0191, + "step": 29472 + }, + { + "epoch": 9.1, + "learning_rate": 1.1927567907932343e-05, + "loss": 0.0179, + "step": 29473 + }, + { + "epoch": 9.1, + "learning_rate": 1.1927077166232074e-05, + "loss": 0.0171, + "step": 29474 + }, + { + "epoch": 9.1, + "learning_rate": 1.1926586419711832e-05, + "loss": 0.0188, + "step": 29475 + }, + { + "epoch": 9.1, + "learning_rate": 1.1926095668372845e-05, + "loss": 0.0168, + "step": 29476 + }, + { + "epoch": 9.1, + "learning_rate": 1.1925604912216345e-05, + "loss": 0.0199, + "step": 29477 + }, + { + "epoch": 9.1, + "learning_rate": 1.1925114151243554e-05, + "loss": 0.0174, + "step": 29478 + }, + { + "epoch": 9.1, + "learning_rate": 1.1924623385455701e-05, + "loss": 0.0195, + "step": 29479 + }, + { + "epoch": 9.1, + "learning_rate": 1.1924132614854014e-05, + "loss": 0.0183, + "step": 29480 + }, + { + "epoch": 9.1, + "learning_rate": 1.192364183943972e-05, + "loss": 0.019, + "step": 29481 + }, + { + "epoch": 9.1, + "learning_rate": 1.1923151059214046e-05, + "loss": 0.0182, + "step": 29482 + }, + { + "epoch": 9.1, + "learning_rate": 1.1922660274178223e-05, + "loss": 0.0187, + "step": 29483 + }, + { + "epoch": 9.11, + "learning_rate": 1.1922169484333474e-05, + "loss": 0.0192, + "step": 29484 + }, + { + "epoch": 9.11, + "learning_rate": 1.1921678689681029e-05, + "loss": 0.0179, + "step": 29485 + }, + { + "epoch": 9.11, + "learning_rate": 1.1921187890222117e-05, + "loss": 0.017, + "step": 29486 + }, + { + "epoch": 9.11, + "learning_rate": 1.1920697085957962e-05, + "loss": 0.018, + "step": 29487 + }, + { + "epoch": 9.11, + "learning_rate": 1.1920206276889791e-05, + "loss": 0.0174, + "step": 29488 + }, + { + "epoch": 9.11, + "learning_rate": 1.1919715463018837e-05, + "loss": 0.019, + "step": 29489 + }, + { + "epoch": 9.11, + "learning_rate": 1.1919224644346325e-05, + "loss": 0.0189, + "step": 29490 + }, + { + "epoch": 9.11, + "learning_rate": 1.191873382087348e-05, + "loss": 0.0196, + "step": 29491 + }, + { + "epoch": 9.11, + "learning_rate": 1.1918242992601531e-05, + "loss": 0.0183, + "step": 29492 + }, + { + "epoch": 9.11, + "learning_rate": 1.191775215953171e-05, + "loss": 0.0187, + "step": 29493 + }, + { + "epoch": 9.11, + "learning_rate": 1.191726132166524e-05, + "loss": 0.0196, + "step": 29494 + }, + { + "epoch": 9.11, + "learning_rate": 1.191677047900335e-05, + "loss": 0.0178, + "step": 29495 + }, + { + "epoch": 9.11, + "learning_rate": 1.1916279631547263e-05, + "loss": 0.0216, + "step": 29496 + }, + { + "epoch": 9.11, + "learning_rate": 1.1915788779298217e-05, + "loss": 0.0198, + "step": 29497 + }, + { + "epoch": 9.11, + "learning_rate": 1.1915297922257431e-05, + "loss": 0.0173, + "step": 29498 + }, + { + "epoch": 9.11, + "learning_rate": 1.1914807060426135e-05, + "loss": 0.0187, + "step": 29499 + }, + { + "epoch": 9.11, + "learning_rate": 1.1914316193805559e-05, + "loss": 0.0209, + "step": 29500 + }, + { + "epoch": 9.11, + "learning_rate": 1.1913825322396926e-05, + "loss": 0.02, + "step": 29501 + }, + { + "epoch": 9.11, + "learning_rate": 1.191333444620147e-05, + "loss": 0.0182, + "step": 29502 + }, + { + "epoch": 9.11, + "learning_rate": 1.1912843565220415e-05, + "loss": 0.018, + "step": 29503 + }, + { + "epoch": 9.11, + "learning_rate": 1.1912352679454988e-05, + "loss": 0.0202, + "step": 29504 + }, + { + "epoch": 9.11, + "learning_rate": 1.1911861788906421e-05, + "loss": 0.0177, + "step": 29505 + }, + { + "epoch": 9.11, + "learning_rate": 1.1911370893575938e-05, + "loss": 0.0211, + "step": 29506 + }, + { + "epoch": 9.11, + "learning_rate": 1.1910879993464763e-05, + "loss": 0.0187, + "step": 29507 + }, + { + "epoch": 9.11, + "learning_rate": 1.1910389088574134e-05, + "loss": 0.0215, + "step": 29508 + }, + { + "epoch": 9.11, + "learning_rate": 1.1909898178905273e-05, + "loss": 0.0168, + "step": 29509 + }, + { + "epoch": 9.11, + "learning_rate": 1.1909407264459408e-05, + "loss": 0.018, + "step": 29510 + }, + { + "epoch": 9.11, + "learning_rate": 1.1908916345237767e-05, + "loss": 0.018, + "step": 29511 + }, + { + "epoch": 9.11, + "learning_rate": 1.1908425421241576e-05, + "loss": 0.0202, + "step": 29512 + }, + { + "epoch": 9.11, + "learning_rate": 1.1907934492472067e-05, + "loss": 0.0183, + "step": 29513 + }, + { + "epoch": 9.11, + "learning_rate": 1.1907443558930465e-05, + "loss": 0.0197, + "step": 29514 + }, + { + "epoch": 9.11, + "learning_rate": 1.1906952620617998e-05, + "loss": 0.0177, + "step": 29515 + }, + { + "epoch": 9.12, + "learning_rate": 1.1906461677535897e-05, + "loss": 0.0155, + "step": 29516 + }, + { + "epoch": 9.12, + "learning_rate": 1.1905970729685386e-05, + "loss": 0.0169, + "step": 29517 + }, + { + "epoch": 9.12, + "learning_rate": 1.1905479777067694e-05, + "loss": 0.0182, + "step": 29518 + }, + { + "epoch": 9.12, + "learning_rate": 1.1904988819684052e-05, + "loss": 0.0231, + "step": 29519 + }, + { + "epoch": 9.12, + "learning_rate": 1.1904497857535683e-05, + "loss": 0.0167, + "step": 29520 + }, + { + "epoch": 9.12, + "learning_rate": 1.1904006890623819e-05, + "loss": 0.0192, + "step": 29521 + }, + { + "epoch": 9.12, + "learning_rate": 1.1903515918949685e-05, + "loss": 0.0192, + "step": 29522 + }, + { + "epoch": 9.12, + "learning_rate": 1.1903024942514514e-05, + "loss": 0.0219, + "step": 29523 + }, + { + "epoch": 9.12, + "learning_rate": 1.1902533961319525e-05, + "loss": 0.0158, + "step": 29524 + }, + { + "epoch": 9.12, + "learning_rate": 1.1902042975365956e-05, + "loss": 0.018, + "step": 29525 + }, + { + "epoch": 9.12, + "learning_rate": 1.1901551984655031e-05, + "loss": 0.0167, + "step": 29526 + }, + { + "epoch": 9.12, + "learning_rate": 1.1901060989187974e-05, + "loss": 0.0204, + "step": 29527 + }, + { + "epoch": 9.12, + "learning_rate": 1.1900569988966019e-05, + "loss": 0.0217, + "step": 29528 + }, + { + "epoch": 9.12, + "learning_rate": 1.190007898399039e-05, + "loss": 0.0197, + "step": 29529 + }, + { + "epoch": 9.12, + "learning_rate": 1.1899587974262317e-05, + "loss": 0.0203, + "step": 29530 + }, + { + "epoch": 9.12, + "learning_rate": 1.1899096959783033e-05, + "loss": 0.0185, + "step": 29531 + }, + { + "epoch": 9.12, + "learning_rate": 1.1898605940553754e-05, + "loss": 0.0178, + "step": 29532 + }, + { + "epoch": 9.12, + "learning_rate": 1.189811491657572e-05, + "loss": 0.0188, + "step": 29533 + }, + { + "epoch": 9.12, + "learning_rate": 1.1897623887850154e-05, + "loss": 0.0204, + "step": 29534 + }, + { + "epoch": 9.12, + "learning_rate": 1.1897132854378282e-05, + "loss": 0.0184, + "step": 29535 + }, + { + "epoch": 9.12, + "learning_rate": 1.1896641816161338e-05, + "loss": 0.0184, + "step": 29536 + }, + { + "epoch": 9.12, + "learning_rate": 1.1896150773200546e-05, + "loss": 0.0185, + "step": 29537 + }, + { + "epoch": 9.12, + "learning_rate": 1.1895659725497131e-05, + "loss": 0.0197, + "step": 29538 + }, + { + "epoch": 9.12, + "learning_rate": 1.189516867305233e-05, + "loss": 0.0193, + "step": 29539 + }, + { + "epoch": 9.12, + "learning_rate": 1.1894677615867365e-05, + "loss": 0.0196, + "step": 29540 + }, + { + "epoch": 9.12, + "learning_rate": 1.1894186553943468e-05, + "loss": 0.0174, + "step": 29541 + }, + { + "epoch": 9.12, + "learning_rate": 1.1893695487281862e-05, + "loss": 0.0176, + "step": 29542 + }, + { + "epoch": 9.12, + "learning_rate": 1.189320441588378e-05, + "loss": 0.0176, + "step": 29543 + }, + { + "epoch": 9.12, + "learning_rate": 1.1892713339750446e-05, + "loss": 0.0206, + "step": 29544 + }, + { + "epoch": 9.12, + "learning_rate": 1.189222225888309e-05, + "loss": 0.0198, + "step": 29545 + }, + { + "epoch": 9.12, + "learning_rate": 1.1891731173282946e-05, + "loss": 0.0175, + "step": 29546 + }, + { + "epoch": 9.12, + "learning_rate": 1.1891240082951234e-05, + "loss": 0.0168, + "step": 29547 + }, + { + "epoch": 9.13, + "learning_rate": 1.1890748987889184e-05, + "loss": 0.0192, + "step": 29548 + }, + { + "epoch": 9.13, + "learning_rate": 1.1890257888098029e-05, + "loss": 0.0197, + "step": 29549 + }, + { + "epoch": 9.13, + "learning_rate": 1.1889766783578993e-05, + "loss": 0.019, + "step": 29550 + }, + { + "epoch": 9.13, + "learning_rate": 1.1889275674333307e-05, + "loss": 0.0177, + "step": 29551 + }, + { + "epoch": 9.13, + "learning_rate": 1.1888784560362197e-05, + "loss": 0.0172, + "step": 29552 + }, + { + "epoch": 9.13, + "learning_rate": 1.1888293441666892e-05, + "loss": 0.0199, + "step": 29553 + }, + { + "epoch": 9.13, + "learning_rate": 1.1887802318248622e-05, + "loss": 0.0191, + "step": 29554 + }, + { + "epoch": 9.13, + "learning_rate": 1.188731119010861e-05, + "loss": 0.0177, + "step": 29555 + }, + { + "epoch": 9.13, + "learning_rate": 1.1886820057248091e-05, + "loss": 0.0179, + "step": 29556 + }, + { + "epoch": 9.13, + "learning_rate": 1.1886328919668296e-05, + "loss": 0.0218, + "step": 29557 + }, + { + "epoch": 9.13, + "learning_rate": 1.1885837777370439e-05, + "loss": 0.0157, + "step": 29558 + }, + { + "epoch": 9.13, + "learning_rate": 1.1885346630355765e-05, + "loss": 0.0189, + "step": 29559 + }, + { + "epoch": 9.13, + "learning_rate": 1.1884855478625491e-05, + "loss": 0.0223, + "step": 29560 + }, + { + "epoch": 9.13, + "learning_rate": 1.1884364322180851e-05, + "loss": 0.0175, + "step": 29561 + }, + { + "epoch": 9.13, + "learning_rate": 1.1883873161023073e-05, + "loss": 0.0167, + "step": 29562 + }, + { + "epoch": 9.13, + "learning_rate": 1.1883381995153385e-05, + "loss": 0.0189, + "step": 29563 + }, + { + "epoch": 9.13, + "learning_rate": 1.1882890824573015e-05, + "loss": 0.0171, + "step": 29564 + }, + { + "epoch": 9.13, + "learning_rate": 1.188239964928319e-05, + "loss": 0.0202, + "step": 29565 + }, + { + "epoch": 9.13, + "learning_rate": 1.1881908469285139e-05, + "loss": 0.0173, + "step": 29566 + }, + { + "epoch": 9.13, + "learning_rate": 1.1881417284580096e-05, + "loss": 0.0218, + "step": 29567 + }, + { + "epoch": 9.13, + "learning_rate": 1.1880926095169282e-05, + "loss": 0.0204, + "step": 29568 + }, + { + "epoch": 9.13, + "learning_rate": 1.188043490105393e-05, + "loss": 0.0205, + "step": 29569 + }, + { + "epoch": 9.13, + "learning_rate": 1.1879943702235268e-05, + "loss": 0.0189, + "step": 29570 + }, + { + "epoch": 9.13, + "learning_rate": 1.1879452498714521e-05, + "loss": 0.0179, + "step": 29571 + }, + { + "epoch": 9.13, + "learning_rate": 1.1878961290492923e-05, + "loss": 0.0163, + "step": 29572 + }, + { + "epoch": 9.13, + "learning_rate": 1.18784700775717e-05, + "loss": 0.0185, + "step": 29573 + }, + { + "epoch": 9.13, + "learning_rate": 1.187797885995208e-05, + "loss": 0.0183, + "step": 29574 + }, + { + "epoch": 9.13, + "learning_rate": 1.1877487637635292e-05, + "loss": 0.0186, + "step": 29575 + }, + { + "epoch": 9.13, + "learning_rate": 1.1876996410622566e-05, + "loss": 0.0172, + "step": 29576 + }, + { + "epoch": 9.13, + "learning_rate": 1.187650517891513e-05, + "loss": 0.0172, + "step": 29577 + }, + { + "epoch": 9.13, + "learning_rate": 1.1876013942514211e-05, + "loss": 0.0189, + "step": 29578 + }, + { + "epoch": 9.13, + "learning_rate": 1.187552270142104e-05, + "loss": 0.0202, + "step": 29579 + }, + { + "epoch": 9.13, + "learning_rate": 1.1875031455636844e-05, + "loss": 0.0194, + "step": 29580 + }, + { + "epoch": 9.14, + "learning_rate": 1.1874540205162853e-05, + "loss": 0.0196, + "step": 29581 + }, + { + "epoch": 9.14, + "learning_rate": 1.1874048950000295e-05, + "loss": 0.0174, + "step": 29582 + }, + { + "epoch": 9.14, + "learning_rate": 1.1873557690150397e-05, + "loss": 0.0194, + "step": 29583 + }, + { + "epoch": 9.14, + "learning_rate": 1.187306642561439e-05, + "loss": 0.0205, + "step": 29584 + }, + { + "epoch": 9.14, + "learning_rate": 1.1872575156393506e-05, + "loss": 0.0215, + "step": 29585 + }, + { + "epoch": 9.14, + "learning_rate": 1.1872083882488965e-05, + "loss": 0.0159, + "step": 29586 + }, + { + "epoch": 9.14, + "learning_rate": 1.1871592603902002e-05, + "loss": 0.0225, + "step": 29587 + }, + { + "epoch": 9.14, + "learning_rate": 1.1871101320633846e-05, + "loss": 0.0198, + "step": 29588 + }, + { + "epoch": 9.14, + "learning_rate": 1.1870610032685723e-05, + "loss": 0.0185, + "step": 29589 + }, + { + "epoch": 9.14, + "learning_rate": 1.1870118740058865e-05, + "loss": 0.0195, + "step": 29590 + }, + { + "epoch": 9.14, + "learning_rate": 1.1869627442754499e-05, + "loss": 0.0167, + "step": 29591 + }, + { + "epoch": 9.14, + "learning_rate": 1.186913614077385e-05, + "loss": 0.0176, + "step": 29592 + }, + { + "epoch": 9.14, + "learning_rate": 1.1868644834118155e-05, + "loss": 0.0195, + "step": 29593 + }, + { + "epoch": 9.14, + "learning_rate": 1.1868153522788638e-05, + "loss": 0.0201, + "step": 29594 + }, + { + "epoch": 9.14, + "learning_rate": 1.1867662206786525e-05, + "loss": 0.0166, + "step": 29595 + }, + { + "epoch": 9.14, + "learning_rate": 1.186717088611305e-05, + "loss": 0.0211, + "step": 29596 + }, + { + "epoch": 9.14, + "learning_rate": 1.186667956076944e-05, + "loss": 0.0184, + "step": 29597 + }, + { + "epoch": 9.14, + "learning_rate": 1.1866188230756925e-05, + "loss": 0.0205, + "step": 29598 + }, + { + "epoch": 9.14, + "learning_rate": 1.186569689607673e-05, + "loss": 0.0193, + "step": 29599 + }, + { + "epoch": 9.14, + "learning_rate": 1.186520555673009e-05, + "loss": 0.0203, + "step": 29600 + }, + { + "epoch": 9.14, + "learning_rate": 1.1864714212718228e-05, + "loss": 0.0166, + "step": 29601 + }, + { + "epoch": 9.14, + "learning_rate": 1.1864222864042378e-05, + "loss": 0.0183, + "step": 29602 + }, + { + "epoch": 9.14, + "learning_rate": 1.1863731510703766e-05, + "loss": 0.0197, + "step": 29603 + }, + { + "epoch": 9.14, + "learning_rate": 1.1863240152703621e-05, + "loss": 0.0195, + "step": 29604 + }, + { + "epoch": 9.14, + "learning_rate": 1.1862748790043173e-05, + "loss": 0.0207, + "step": 29605 + }, + { + "epoch": 9.14, + "learning_rate": 1.1862257422723651e-05, + "loss": 0.0195, + "step": 29606 + }, + { + "epoch": 9.14, + "learning_rate": 1.1861766050746282e-05, + "loss": 0.0159, + "step": 29607 + }, + { + "epoch": 9.14, + "learning_rate": 1.18612746741123e-05, + "loss": 0.0166, + "step": 29608 + }, + { + "epoch": 9.14, + "learning_rate": 1.1860783292822926e-05, + "loss": 0.019, + "step": 29609 + }, + { + "epoch": 9.14, + "learning_rate": 1.1860291906879395e-05, + "loss": 0.0175, + "step": 29610 + }, + { + "epoch": 9.14, + "learning_rate": 1.1859800516282937e-05, + "loss": 0.0185, + "step": 29611 + }, + { + "epoch": 9.14, + "learning_rate": 1.1859309121034774e-05, + "loss": 0.0188, + "step": 29612 + }, + { + "epoch": 9.15, + "learning_rate": 1.1858817721136147e-05, + "loss": 0.0183, + "step": 29613 + }, + { + "epoch": 9.15, + "learning_rate": 1.1858326316588272e-05, + "loss": 0.0194, + "step": 29614 + }, + { + "epoch": 9.15, + "learning_rate": 1.1857834907392383e-05, + "loss": 0.0178, + "step": 29615 + }, + { + "epoch": 9.15, + "learning_rate": 1.1857343493549715e-05, + "loss": 0.0199, + "step": 29616 + }, + { + "epoch": 9.15, + "learning_rate": 1.1856852075061487e-05, + "loss": 0.0196, + "step": 29617 + }, + { + "epoch": 9.15, + "learning_rate": 1.185636065192894e-05, + "loss": 0.0192, + "step": 29618 + }, + { + "epoch": 9.15, + "learning_rate": 1.1855869224153291e-05, + "loss": 0.0201, + "step": 29619 + }, + { + "epoch": 9.15, + "learning_rate": 1.1855377791735774e-05, + "loss": 0.0183, + "step": 29620 + }, + { + "epoch": 9.15, + "learning_rate": 1.1854886354677624e-05, + "loss": 0.0173, + "step": 29621 + }, + { + "epoch": 9.15, + "learning_rate": 1.1854394912980061e-05, + "loss": 0.0192, + "step": 29622 + }, + { + "epoch": 9.15, + "learning_rate": 1.1853903466644318e-05, + "loss": 0.018, + "step": 29623 + }, + { + "epoch": 9.15, + "learning_rate": 1.1853412015671626e-05, + "loss": 0.0221, + "step": 29624 + }, + { + "epoch": 9.15, + "learning_rate": 1.185292056006321e-05, + "loss": 0.0204, + "step": 29625 + }, + { + "epoch": 9.15, + "learning_rate": 1.1852429099820305e-05, + "loss": 0.0191, + "step": 29626 + }, + { + "epoch": 9.15, + "learning_rate": 1.1851937634944136e-05, + "loss": 0.019, + "step": 29627 + }, + { + "epoch": 9.15, + "learning_rate": 1.185144616543593e-05, + "loss": 0.0169, + "step": 29628 + }, + { + "epoch": 9.15, + "learning_rate": 1.1850954691296924e-05, + "loss": 0.0186, + "step": 29629 + }, + { + "epoch": 9.15, + "learning_rate": 1.1850463212528339e-05, + "loss": 0.0186, + "step": 29630 + }, + { + "epoch": 9.15, + "learning_rate": 1.1849971729131408e-05, + "loss": 0.0214, + "step": 29631 + }, + { + "epoch": 9.15, + "learning_rate": 1.1849480241107364e-05, + "loss": 0.0172, + "step": 29632 + }, + { + "epoch": 9.15, + "learning_rate": 1.184898874845743e-05, + "loss": 0.0183, + "step": 29633 + }, + { + "epoch": 9.15, + "learning_rate": 1.1848497251182838e-05, + "loss": 0.0192, + "step": 29634 + }, + { + "epoch": 9.15, + "learning_rate": 1.184800574928482e-05, + "loss": 0.0222, + "step": 29635 + }, + { + "epoch": 9.15, + "learning_rate": 1.1847514242764597e-05, + "loss": 0.0184, + "step": 29636 + }, + { + "epoch": 9.15, + "learning_rate": 1.1847022731623408e-05, + "loss": 0.0207, + "step": 29637 + }, + { + "epoch": 9.15, + "learning_rate": 1.1846531215862478e-05, + "loss": 0.0183, + "step": 29638 + }, + { + "epoch": 9.15, + "learning_rate": 1.1846039695483039e-05, + "loss": 0.0154, + "step": 29639 + }, + { + "epoch": 9.15, + "learning_rate": 1.1845548170486312e-05, + "loss": 0.0177, + "step": 29640 + }, + { + "epoch": 9.15, + "learning_rate": 1.1845056640873536e-05, + "loss": 0.0198, + "step": 29641 + }, + { + "epoch": 9.15, + "learning_rate": 1.1844565106645938e-05, + "loss": 0.0209, + "step": 29642 + }, + { + "epoch": 9.15, + "learning_rate": 1.1844073567804742e-05, + "loss": 0.0186, + "step": 29643 + }, + { + "epoch": 9.15, + "learning_rate": 1.1843582024351186e-05, + "loss": 0.019, + "step": 29644 + }, + { + "epoch": 9.15, + "learning_rate": 1.1843090476286494e-05, + "loss": 0.0196, + "step": 29645 + }, + { + "epoch": 9.16, + "learning_rate": 1.1842598923611892e-05, + "loss": 0.0168, + "step": 29646 + }, + { + "epoch": 9.16, + "learning_rate": 1.1842107366328621e-05, + "loss": 0.0196, + "step": 29647 + }, + { + "epoch": 9.16, + "learning_rate": 1.1841615804437898e-05, + "loss": 0.0202, + "step": 29648 + }, + { + "epoch": 9.16, + "learning_rate": 1.1841124237940962e-05, + "loss": 0.0182, + "step": 29649 + }, + { + "epoch": 9.16, + "learning_rate": 1.1840632666839038e-05, + "loss": 0.0199, + "step": 29650 + }, + { + "epoch": 9.16, + "learning_rate": 1.1840141091133353e-05, + "loss": 0.0192, + "step": 29651 + }, + { + "epoch": 9.16, + "learning_rate": 1.1839649510825142e-05, + "loss": 0.021, + "step": 29652 + }, + { + "epoch": 9.16, + "learning_rate": 1.1839157925915632e-05, + "loss": 0.02, + "step": 29653 + }, + { + "epoch": 9.16, + "learning_rate": 1.1838666336406053e-05, + "loss": 0.0165, + "step": 29654 + }, + { + "epoch": 9.16, + "learning_rate": 1.1838174742297632e-05, + "loss": 0.0182, + "step": 29655 + }, + { + "epoch": 9.16, + "learning_rate": 1.1837683143591602e-05, + "loss": 0.0196, + "step": 29656 + }, + { + "epoch": 9.16, + "learning_rate": 1.183719154028919e-05, + "loss": 0.0173, + "step": 29657 + }, + { + "epoch": 9.16, + "learning_rate": 1.1836699932391629e-05, + "loss": 0.0175, + "step": 29658 + }, + { + "epoch": 9.16, + "learning_rate": 1.1836208319900147e-05, + "loss": 0.0199, + "step": 29659 + }, + { + "epoch": 9.16, + "learning_rate": 1.1835716702815969e-05, + "loss": 0.019, + "step": 29660 + }, + { + "epoch": 9.16, + "learning_rate": 1.1835225081140332e-05, + "loss": 0.0195, + "step": 29661 + }, + { + "epoch": 9.16, + "learning_rate": 1.1834733454874466e-05, + "loss": 0.0198, + "step": 29662 + }, + { + "epoch": 9.16, + "learning_rate": 1.1834241824019587e-05, + "loss": 0.0173, + "step": 29663 + }, + { + "epoch": 9.16, + "learning_rate": 1.1833750188576942e-05, + "loss": 0.0173, + "step": 29664 + }, + { + "epoch": 9.16, + "learning_rate": 1.183325854854775e-05, + "loss": 0.019, + "step": 29665 + }, + { + "epoch": 9.16, + "learning_rate": 1.1832766903933246e-05, + "loss": 0.0182, + "step": 29666 + }, + { + "epoch": 9.16, + "learning_rate": 1.183227525473466e-05, + "loss": 0.0176, + "step": 29667 + }, + { + "epoch": 9.16, + "learning_rate": 1.1831783600953214e-05, + "loss": 0.0197, + "step": 29668 + }, + { + "epoch": 9.16, + "learning_rate": 1.1831291942590146e-05, + "loss": 0.0195, + "step": 29669 + }, + { + "epoch": 9.16, + "learning_rate": 1.1830800279646686e-05, + "loss": 0.0201, + "step": 29670 + }, + { + "epoch": 9.16, + "learning_rate": 1.1830308612124056e-05, + "loss": 0.0169, + "step": 29671 + }, + { + "epoch": 9.16, + "learning_rate": 1.1829816940023492e-05, + "loss": 0.0157, + "step": 29672 + }, + { + "epoch": 9.16, + "learning_rate": 1.1829325263346222e-05, + "loss": 0.0185, + "step": 29673 + }, + { + "epoch": 9.16, + "learning_rate": 1.1828833582093474e-05, + "loss": 0.0174, + "step": 29674 + }, + { + "epoch": 9.16, + "learning_rate": 1.1828341896266482e-05, + "loss": 0.0213, + "step": 29675 + }, + { + "epoch": 9.16, + "learning_rate": 1.1827850205866473e-05, + "loss": 0.0194, + "step": 29676 + }, + { + "epoch": 9.16, + "learning_rate": 1.1827358510894678e-05, + "loss": 0.017, + "step": 29677 + }, + { + "epoch": 9.17, + "learning_rate": 1.1826866811352324e-05, + "loss": 0.0154, + "step": 29678 + }, + { + "epoch": 9.17, + "learning_rate": 1.1826375107240642e-05, + "loss": 0.0184, + "step": 29679 + }, + { + "epoch": 9.17, + "learning_rate": 1.1825883398560867e-05, + "loss": 0.0138, + "step": 29680 + }, + { + "epoch": 9.17, + "learning_rate": 1.1825391685314221e-05, + "loss": 0.0164, + "step": 29681 + }, + { + "epoch": 9.17, + "learning_rate": 1.1824899967501939e-05, + "loss": 0.019, + "step": 29682 + }, + { + "epoch": 9.17, + "learning_rate": 1.182440824512525e-05, + "loss": 0.0193, + "step": 29683 + }, + { + "epoch": 9.17, + "learning_rate": 1.1823916518185381e-05, + "loss": 0.0187, + "step": 29684 + }, + { + "epoch": 9.17, + "learning_rate": 1.1823424786683566e-05, + "loss": 0.0194, + "step": 29685 + }, + { + "epoch": 9.17, + "learning_rate": 1.1822933050621032e-05, + "loss": 0.0215, + "step": 29686 + }, + { + "epoch": 9.17, + "learning_rate": 1.1822441309999011e-05, + "loss": 0.018, + "step": 29687 + }, + { + "epoch": 9.17, + "learning_rate": 1.182194956481873e-05, + "loss": 0.0168, + "step": 29688 + }, + { + "epoch": 9.17, + "learning_rate": 1.1821457815081424e-05, + "loss": 0.0187, + "step": 29689 + }, + { + "epoch": 9.17, + "learning_rate": 1.1820966060788317e-05, + "loss": 0.017, + "step": 29690 + }, + { + "epoch": 9.17, + "learning_rate": 1.1820474301940642e-05, + "loss": 0.0163, + "step": 29691 + }, + { + "epoch": 9.17, + "learning_rate": 1.1819982538539629e-05, + "loss": 0.0204, + "step": 29692 + }, + { + "epoch": 9.17, + "learning_rate": 1.181949077058651e-05, + "loss": 0.0228, + "step": 29693 + }, + { + "epoch": 9.17, + "learning_rate": 1.181899899808251e-05, + "loss": 0.0195, + "step": 29694 + }, + { + "epoch": 9.17, + "learning_rate": 1.1818507221028863e-05, + "loss": 0.0172, + "step": 29695 + }, + { + "epoch": 9.17, + "learning_rate": 1.1818015439426795e-05, + "loss": 0.0168, + "step": 29696 + }, + { + "epoch": 9.17, + "learning_rate": 1.1817523653277543e-05, + "loss": 0.0182, + "step": 29697 + }, + { + "epoch": 9.17, + "learning_rate": 1.1817031862582333e-05, + "loss": 0.0176, + "step": 29698 + }, + { + "epoch": 9.17, + "learning_rate": 1.181654006734239e-05, + "loss": 0.0168, + "step": 29699 + }, + { + "epoch": 9.17, + "learning_rate": 1.1816048267558953e-05, + "loss": 0.0196, + "step": 29700 + }, + { + "epoch": 9.17, + "learning_rate": 1.181555646323325e-05, + "loss": 0.0206, + "step": 29701 + }, + { + "epoch": 9.17, + "learning_rate": 1.1815064654366502e-05, + "loss": 0.0182, + "step": 29702 + }, + { + "epoch": 9.17, + "learning_rate": 1.1814572840959952e-05, + "loss": 0.0195, + "step": 29703 + }, + { + "epoch": 9.17, + "learning_rate": 1.1814081023014823e-05, + "loss": 0.0168, + "step": 29704 + }, + { + "epoch": 9.17, + "learning_rate": 1.1813589200532345e-05, + "loss": 0.0188, + "step": 29705 + }, + { + "epoch": 9.17, + "learning_rate": 1.1813097373513753e-05, + "loss": 0.0188, + "step": 29706 + }, + { + "epoch": 9.17, + "learning_rate": 1.1812605541960272e-05, + "loss": 0.0177, + "step": 29707 + }, + { + "epoch": 9.17, + "learning_rate": 1.1812113705873132e-05, + "loss": 0.0199, + "step": 29708 + }, + { + "epoch": 9.17, + "learning_rate": 1.1811621865253566e-05, + "loss": 0.0173, + "step": 29709 + }, + { + "epoch": 9.18, + "learning_rate": 1.1811130020102806e-05, + "loss": 0.0201, + "step": 29710 + }, + { + "epoch": 9.18, + "learning_rate": 1.1810638170422078e-05, + "loss": 0.0171, + "step": 29711 + }, + { + "epoch": 9.18, + "learning_rate": 1.1810146316212612e-05, + "loss": 0.02, + "step": 29712 + }, + { + "epoch": 9.18, + "learning_rate": 1.1809654457475641e-05, + "loss": 0.0191, + "step": 29713 + }, + { + "epoch": 9.18, + "learning_rate": 1.1809162594212393e-05, + "loss": 0.0196, + "step": 29714 + }, + { + "epoch": 9.18, + "learning_rate": 1.1808670726424101e-05, + "loss": 0.0179, + "step": 29715 + }, + { + "epoch": 9.18, + "learning_rate": 1.1808178854111994e-05, + "loss": 0.0198, + "step": 29716 + }, + { + "epoch": 9.18, + "learning_rate": 1.18076869772773e-05, + "loss": 0.0172, + "step": 29717 + }, + { + "epoch": 9.18, + "learning_rate": 1.1807195095921254e-05, + "loss": 0.0183, + "step": 29718 + }, + { + "epoch": 9.18, + "learning_rate": 1.180670321004508e-05, + "loss": 0.0173, + "step": 29719 + }, + { + "epoch": 9.18, + "learning_rate": 1.1806211319650015e-05, + "loss": 0.018, + "step": 29720 + }, + { + "epoch": 9.18, + "learning_rate": 1.1805719424737285e-05, + "loss": 0.0209, + "step": 29721 + }, + { + "epoch": 9.18, + "learning_rate": 1.1805227525308118e-05, + "loss": 0.0223, + "step": 29722 + }, + { + "epoch": 9.18, + "learning_rate": 1.1804735621363753e-05, + "loss": 0.0177, + "step": 29723 + }, + { + "epoch": 9.18, + "learning_rate": 1.1804243712905414e-05, + "loss": 0.02, + "step": 29724 + }, + { + "epoch": 9.18, + "learning_rate": 1.1803751799934329e-05, + "loss": 0.0203, + "step": 29725 + }, + { + "epoch": 9.18, + "learning_rate": 1.1803259882451737e-05, + "loss": 0.018, + "step": 29726 + }, + { + "epoch": 9.18, + "learning_rate": 1.1802767960458858e-05, + "loss": 0.0172, + "step": 29727 + }, + { + "epoch": 9.18, + "learning_rate": 1.1802276033956927e-05, + "loss": 0.0183, + "step": 29728 + }, + { + "epoch": 9.18, + "learning_rate": 1.180178410294718e-05, + "loss": 0.0162, + "step": 29729 + }, + { + "epoch": 9.18, + "learning_rate": 1.1801292167430837e-05, + "loss": 0.02, + "step": 29730 + }, + { + "epoch": 9.18, + "learning_rate": 1.180080022740914e-05, + "loss": 0.0178, + "step": 29731 + }, + { + "epoch": 9.18, + "learning_rate": 1.1800308282883309e-05, + "loss": 0.0191, + "step": 29732 + }, + { + "epoch": 9.18, + "learning_rate": 1.1799816333854577e-05, + "loss": 0.0227, + "step": 29733 + }, + { + "epoch": 9.18, + "learning_rate": 1.179932438032418e-05, + "loss": 0.0198, + "step": 29734 + }, + { + "epoch": 9.18, + "learning_rate": 1.1798832422293345e-05, + "loss": 0.018, + "step": 29735 + }, + { + "epoch": 9.18, + "learning_rate": 1.17983404597633e-05, + "loss": 0.0186, + "step": 29736 + }, + { + "epoch": 9.18, + "learning_rate": 1.1797848492735275e-05, + "loss": 0.0167, + "step": 29737 + }, + { + "epoch": 9.18, + "learning_rate": 1.1797356521210506e-05, + "loss": 0.0176, + "step": 29738 + }, + { + "epoch": 9.18, + "learning_rate": 1.179686454519022e-05, + "loss": 0.015, + "step": 29739 + }, + { + "epoch": 9.18, + "learning_rate": 1.1796372564675649e-05, + "loss": 0.0213, + "step": 29740 + }, + { + "epoch": 9.18, + "learning_rate": 1.1795880579668023e-05, + "loss": 0.0204, + "step": 29741 + }, + { + "epoch": 9.18, + "learning_rate": 1.1795388590168569e-05, + "loss": 0.0191, + "step": 29742 + }, + { + "epoch": 9.19, + "learning_rate": 1.1794896596178523e-05, + "loss": 0.0199, + "step": 29743 + }, + { + "epoch": 9.19, + "learning_rate": 1.1794404597699112e-05, + "loss": 0.0165, + "step": 29744 + }, + { + "epoch": 9.19, + "learning_rate": 1.1793912594731568e-05, + "loss": 0.0184, + "step": 29745 + }, + { + "epoch": 9.19, + "learning_rate": 1.1793420587277122e-05, + "loss": 0.0183, + "step": 29746 + }, + { + "epoch": 9.19, + "learning_rate": 1.1792928575337004e-05, + "loss": 0.0185, + "step": 29747 + }, + { + "epoch": 9.19, + "learning_rate": 1.1792436558912445e-05, + "loss": 0.0193, + "step": 29748 + }, + { + "epoch": 9.19, + "learning_rate": 1.1791944538004674e-05, + "loss": 0.0165, + "step": 29749 + }, + { + "epoch": 9.19, + "learning_rate": 1.1791452512614925e-05, + "loss": 0.0212, + "step": 29750 + }, + { + "epoch": 9.19, + "learning_rate": 1.1790960482744424e-05, + "loss": 0.0165, + "step": 29751 + }, + { + "epoch": 9.19, + "learning_rate": 1.1790468448394408e-05, + "loss": 0.0183, + "step": 29752 + }, + { + "epoch": 9.19, + "learning_rate": 1.17899764095661e-05, + "loss": 0.0213, + "step": 29753 + }, + { + "epoch": 9.19, + "learning_rate": 1.1789484366260735e-05, + "loss": 0.0201, + "step": 29754 + }, + { + "epoch": 9.19, + "learning_rate": 1.1788992318479546e-05, + "loss": 0.0158, + "step": 29755 + }, + { + "epoch": 9.19, + "learning_rate": 1.1788500266223757e-05, + "loss": 0.0198, + "step": 29756 + }, + { + "epoch": 9.19, + "learning_rate": 1.1788008209494605e-05, + "loss": 0.0173, + "step": 29757 + }, + { + "epoch": 9.19, + "learning_rate": 1.1787516148293318e-05, + "loss": 0.021, + "step": 29758 + }, + { + "epoch": 9.19, + "learning_rate": 1.1787024082621125e-05, + "loss": 0.0189, + "step": 29759 + }, + { + "epoch": 9.19, + "learning_rate": 1.1786532012479264e-05, + "loss": 0.0194, + "step": 29760 + }, + { + "epoch": 9.19, + "learning_rate": 1.1786039937868956e-05, + "loss": 0.0188, + "step": 29761 + }, + { + "epoch": 9.19, + "learning_rate": 1.178554785879144e-05, + "loss": 0.0197, + "step": 29762 + }, + { + "epoch": 9.19, + "learning_rate": 1.178505577524794e-05, + "loss": 0.0174, + "step": 29763 + }, + { + "epoch": 9.19, + "learning_rate": 1.178456368723969e-05, + "loss": 0.0213, + "step": 29764 + }, + { + "epoch": 9.19, + "learning_rate": 1.1784071594767923e-05, + "loss": 0.0201, + "step": 29765 + }, + { + "epoch": 9.19, + "learning_rate": 1.1783579497833866e-05, + "loss": 0.0179, + "step": 29766 + }, + { + "epoch": 9.19, + "learning_rate": 1.178308739643875e-05, + "loss": 0.0202, + "step": 29767 + }, + { + "epoch": 9.19, + "learning_rate": 1.178259529058381e-05, + "loss": 0.0198, + "step": 29768 + }, + { + "epoch": 9.19, + "learning_rate": 1.1782103180270272e-05, + "loss": 0.0191, + "step": 29769 + }, + { + "epoch": 9.19, + "learning_rate": 1.178161106549937e-05, + "loss": 0.0198, + "step": 29770 + }, + { + "epoch": 9.19, + "learning_rate": 1.1781118946272334e-05, + "loss": 0.0177, + "step": 29771 + }, + { + "epoch": 9.19, + "learning_rate": 1.1780626822590393e-05, + "loss": 0.0199, + "step": 29772 + }, + { + "epoch": 9.19, + "learning_rate": 1.178013469445478e-05, + "loss": 0.0206, + "step": 29773 + }, + { + "epoch": 9.19, + "learning_rate": 1.1779642561866727e-05, + "loss": 0.0206, + "step": 29774 + }, + { + "epoch": 9.2, + "learning_rate": 1.1779150424827466e-05, + "loss": 0.0225, + "step": 29775 + }, + { + "epoch": 9.2, + "learning_rate": 1.1778658283338218e-05, + "loss": 0.017, + "step": 29776 + }, + { + "epoch": 9.2, + "learning_rate": 1.1778166137400227e-05, + "loss": 0.019, + "step": 29777 + }, + { + "epoch": 9.2, + "learning_rate": 1.1777673987014715e-05, + "loss": 0.019, + "step": 29778 + }, + { + "epoch": 9.2, + "learning_rate": 1.1777181832182917e-05, + "loss": 0.022, + "step": 29779 + }, + { + "epoch": 9.2, + "learning_rate": 1.1776689672906065e-05, + "loss": 0.023, + "step": 29780 + }, + { + "epoch": 9.2, + "learning_rate": 1.1776197509185385e-05, + "loss": 0.0183, + "step": 29781 + }, + { + "epoch": 9.2, + "learning_rate": 1.1775705341022112e-05, + "loss": 0.0213, + "step": 29782 + }, + { + "epoch": 9.2, + "learning_rate": 1.1775213168417478e-05, + "loss": 0.0199, + "step": 29783 + }, + { + "epoch": 9.2, + "learning_rate": 1.177472099137271e-05, + "loss": 0.0168, + "step": 29784 + }, + { + "epoch": 9.2, + "learning_rate": 1.1774228809889043e-05, + "loss": 0.0202, + "step": 29785 + }, + { + "epoch": 9.2, + "learning_rate": 1.1773736623967707e-05, + "loss": 0.0177, + "step": 29786 + }, + { + "epoch": 9.2, + "learning_rate": 1.1773244433609928e-05, + "loss": 0.0227, + "step": 29787 + }, + { + "epoch": 9.2, + "learning_rate": 1.1772752238816945e-05, + "loss": 0.0193, + "step": 29788 + }, + { + "epoch": 9.2, + "learning_rate": 1.1772260039589983e-05, + "loss": 0.02, + "step": 29789 + }, + { + "epoch": 9.2, + "learning_rate": 1.1771767835930276e-05, + "loss": 0.0186, + "step": 29790 + }, + { + "epoch": 9.2, + "learning_rate": 1.1771275627839054e-05, + "loss": 0.0217, + "step": 29791 + }, + { + "epoch": 9.2, + "learning_rate": 1.177078341531755e-05, + "loss": 0.0217, + "step": 29792 + }, + { + "epoch": 9.2, + "learning_rate": 1.1770291198366995e-05, + "loss": 0.0198, + "step": 29793 + }, + { + "epoch": 9.2, + "learning_rate": 1.1769798976988616e-05, + "loss": 0.02, + "step": 29794 + }, + { + "epoch": 9.2, + "learning_rate": 1.1769306751183645e-05, + "loss": 0.0202, + "step": 29795 + }, + { + "epoch": 9.2, + "learning_rate": 1.176881452095332e-05, + "loss": 0.0188, + "step": 29796 + }, + { + "epoch": 9.2, + "learning_rate": 1.1768322286298863e-05, + "loss": 0.0177, + "step": 29797 + }, + { + "epoch": 9.2, + "learning_rate": 1.1767830047221514e-05, + "loss": 0.0184, + "step": 29798 + }, + { + "epoch": 9.2, + "learning_rate": 1.1767337803722495e-05, + "loss": 0.0177, + "step": 29799 + }, + { + "epoch": 9.2, + "learning_rate": 1.1766845555803046e-05, + "loss": 0.0176, + "step": 29800 + }, + { + "epoch": 9.2, + "learning_rate": 1.1766353303464391e-05, + "loss": 0.0206, + "step": 29801 + }, + { + "epoch": 9.2, + "learning_rate": 1.1765861046707765e-05, + "loss": 0.0183, + "step": 29802 + }, + { + "epoch": 9.2, + "learning_rate": 1.17653687855344e-05, + "loss": 0.0181, + "step": 29803 + }, + { + "epoch": 9.2, + "learning_rate": 1.1764876519945522e-05, + "loss": 0.0189, + "step": 29804 + }, + { + "epoch": 9.2, + "learning_rate": 1.1764384249942369e-05, + "loss": 0.018, + "step": 29805 + }, + { + "epoch": 9.2, + "learning_rate": 1.1763891975526171e-05, + "loss": 0.0205, + "step": 29806 + }, + { + "epoch": 9.21, + "learning_rate": 1.1763399696698152e-05, + "loss": 0.0175, + "step": 29807 + }, + { + "epoch": 9.21, + "learning_rate": 1.1762907413459553e-05, + "loss": 0.0198, + "step": 29808 + }, + { + "epoch": 9.21, + "learning_rate": 1.1762415125811602e-05, + "loss": 0.0205, + "step": 29809 + }, + { + "epoch": 9.21, + "learning_rate": 1.1761922833755523e-05, + "loss": 0.0178, + "step": 29810 + }, + { + "epoch": 9.21, + "learning_rate": 1.1761430537292563e-05, + "loss": 0.0182, + "step": 29811 + }, + { + "epoch": 9.21, + "learning_rate": 1.1760938236423936e-05, + "loss": 0.0199, + "step": 29812 + }, + { + "epoch": 9.21, + "learning_rate": 1.1760445931150883e-05, + "loss": 0.0186, + "step": 29813 + }, + { + "epoch": 9.21, + "learning_rate": 1.1759953621474635e-05, + "loss": 0.02, + "step": 29814 + }, + { + "epoch": 9.21, + "learning_rate": 1.175946130739642e-05, + "loss": 0.0173, + "step": 29815 + }, + { + "epoch": 9.21, + "learning_rate": 1.1758968988917476e-05, + "loss": 0.0186, + "step": 29816 + }, + { + "epoch": 9.21, + "learning_rate": 1.1758476666039027e-05, + "loss": 0.0186, + "step": 29817 + }, + { + "epoch": 9.21, + "learning_rate": 1.1757984338762306e-05, + "loss": 0.0184, + "step": 29818 + }, + { + "epoch": 9.21, + "learning_rate": 1.1757492007088546e-05, + "loss": 0.0191, + "step": 29819 + }, + { + "epoch": 9.21, + "learning_rate": 1.1756999671018977e-05, + "loss": 0.0188, + "step": 29820 + }, + { + "epoch": 9.21, + "learning_rate": 1.1756507330554834e-05, + "loss": 0.0212, + "step": 29821 + }, + { + "epoch": 9.21, + "learning_rate": 1.1756014985697344e-05, + "loss": 0.0194, + "step": 29822 + }, + { + "epoch": 9.21, + "learning_rate": 1.175552263644774e-05, + "loss": 0.0212, + "step": 29823 + }, + { + "epoch": 9.21, + "learning_rate": 1.1755030282807256e-05, + "loss": 0.016, + "step": 29824 + }, + { + "epoch": 9.21, + "learning_rate": 1.1754537924777118e-05, + "loss": 0.0184, + "step": 29825 + }, + { + "epoch": 9.21, + "learning_rate": 1.1754045562358563e-05, + "loss": 0.0185, + "step": 29826 + }, + { + "epoch": 9.21, + "learning_rate": 1.175355319555282e-05, + "loss": 0.0165, + "step": 29827 + }, + { + "epoch": 9.21, + "learning_rate": 1.175306082436112e-05, + "loss": 0.0176, + "step": 29828 + }, + { + "epoch": 9.21, + "learning_rate": 1.1752568448784695e-05, + "loss": 0.0222, + "step": 29829 + }, + { + "epoch": 9.21, + "learning_rate": 1.1752076068824776e-05, + "loss": 0.0204, + "step": 29830 + }, + { + "epoch": 9.21, + "learning_rate": 1.1751583684482598e-05, + "loss": 0.0187, + "step": 29831 + }, + { + "epoch": 9.21, + "learning_rate": 1.1751091295759384e-05, + "loss": 0.0197, + "step": 29832 + }, + { + "epoch": 9.21, + "learning_rate": 1.1750598902656376e-05, + "loss": 0.019, + "step": 29833 + }, + { + "epoch": 9.21, + "learning_rate": 1.1750106505174803e-05, + "loss": 0.0193, + "step": 29834 + }, + { + "epoch": 9.21, + "learning_rate": 1.174961410331589e-05, + "loss": 0.0189, + "step": 29835 + }, + { + "epoch": 9.21, + "learning_rate": 1.1749121697080875e-05, + "loss": 0.0177, + "step": 29836 + }, + { + "epoch": 9.21, + "learning_rate": 1.1748629286470987e-05, + "loss": 0.0192, + "step": 29837 + }, + { + "epoch": 9.21, + "learning_rate": 1.1748136871487456e-05, + "loss": 0.02, + "step": 29838 + }, + { + "epoch": 9.21, + "learning_rate": 1.174764445213152e-05, + "loss": 0.017, + "step": 29839 + }, + { + "epoch": 9.22, + "learning_rate": 1.1747152028404405e-05, + "loss": 0.0183, + "step": 29840 + }, + { + "epoch": 9.22, + "learning_rate": 1.1746659600307342e-05, + "loss": 0.0172, + "step": 29841 + }, + { + "epoch": 9.22, + "learning_rate": 1.1746167167841567e-05, + "loss": 0.0187, + "step": 29842 + }, + { + "epoch": 9.22, + "learning_rate": 1.1745674731008308e-05, + "loss": 0.0204, + "step": 29843 + }, + { + "epoch": 9.22, + "learning_rate": 1.1745182289808799e-05, + "loss": 0.018, + "step": 29844 + }, + { + "epoch": 9.22, + "learning_rate": 1.1744689844244272e-05, + "loss": 0.0211, + "step": 29845 + }, + { + "epoch": 9.22, + "learning_rate": 1.1744197394315953e-05, + "loss": 0.0199, + "step": 29846 + }, + { + "epoch": 9.22, + "learning_rate": 1.1743704940025084e-05, + "loss": 0.0182, + "step": 29847 + }, + { + "epoch": 9.22, + "learning_rate": 1.1743212481372887e-05, + "loss": 0.0224, + "step": 29848 + }, + { + "epoch": 9.22, + "learning_rate": 1.1742720018360598e-05, + "loss": 0.0194, + "step": 29849 + }, + { + "epoch": 9.22, + "learning_rate": 1.1742227550989452e-05, + "loss": 0.0216, + "step": 29850 + }, + { + "epoch": 9.22, + "learning_rate": 1.1741735079260675e-05, + "loss": 0.0194, + "step": 29851 + }, + { + "epoch": 9.22, + "learning_rate": 1.1741242603175498e-05, + "loss": 0.0219, + "step": 29852 + }, + { + "epoch": 9.22, + "learning_rate": 1.1740750122735158e-05, + "loss": 0.0184, + "step": 29853 + }, + { + "epoch": 9.22, + "learning_rate": 1.1740257637940886e-05, + "loss": 0.0202, + "step": 29854 + }, + { + "epoch": 9.22, + "learning_rate": 1.1739765148793909e-05, + "loss": 0.021, + "step": 29855 + }, + { + "epoch": 9.22, + "learning_rate": 1.1739272655295464e-05, + "loss": 0.02, + "step": 29856 + }, + { + "epoch": 9.22, + "learning_rate": 1.1738780157446781e-05, + "loss": 0.021, + "step": 29857 + }, + { + "epoch": 9.22, + "learning_rate": 1.1738287655249093e-05, + "loss": 0.0209, + "step": 29858 + }, + { + "epoch": 9.22, + "learning_rate": 1.1737795148703628e-05, + "loss": 0.0193, + "step": 29859 + }, + { + "epoch": 9.22, + "learning_rate": 1.173730263781162e-05, + "loss": 0.0205, + "step": 29860 + }, + { + "epoch": 9.22, + "learning_rate": 1.1736810122574302e-05, + "loss": 0.0212, + "step": 29861 + }, + { + "epoch": 9.22, + "learning_rate": 1.1736317602992905e-05, + "loss": 0.0198, + "step": 29862 + }, + { + "epoch": 9.22, + "learning_rate": 1.1735825079068664e-05, + "loss": 0.0191, + "step": 29863 + }, + { + "epoch": 9.22, + "learning_rate": 1.1735332550802805e-05, + "loss": 0.0184, + "step": 29864 + }, + { + "epoch": 9.22, + "learning_rate": 1.1734840018196564e-05, + "loss": 0.0192, + "step": 29865 + }, + { + "epoch": 9.22, + "learning_rate": 1.173434748125117e-05, + "loss": 0.0168, + "step": 29866 + }, + { + "epoch": 9.22, + "learning_rate": 1.1733854939967858e-05, + "loss": 0.022, + "step": 29867 + }, + { + "epoch": 9.22, + "learning_rate": 1.1733362394347859e-05, + "loss": 0.0205, + "step": 29868 + }, + { + "epoch": 9.22, + "learning_rate": 1.1732869844392401e-05, + "loss": 0.0192, + "step": 29869 + }, + { + "epoch": 9.22, + "learning_rate": 1.1732377290102725e-05, + "loss": 0.0204, + "step": 29870 + }, + { + "epoch": 9.22, + "learning_rate": 1.1731884731480055e-05, + "loss": 0.0175, + "step": 29871 + }, + { + "epoch": 9.23, + "learning_rate": 1.1731392168525622e-05, + "loss": 0.0193, + "step": 29872 + }, + { + "epoch": 9.23, + "learning_rate": 1.1730899601240666e-05, + "loss": 0.0183, + "step": 29873 + }, + { + "epoch": 9.23, + "learning_rate": 1.1730407029626412e-05, + "loss": 0.0162, + "step": 29874 + }, + { + "epoch": 9.23, + "learning_rate": 1.1729914453684095e-05, + "loss": 0.0167, + "step": 29875 + }, + { + "epoch": 9.23, + "learning_rate": 1.1729421873414948e-05, + "loss": 0.0159, + "step": 29876 + }, + { + "epoch": 9.23, + "learning_rate": 1.1728929288820196e-05, + "loss": 0.0195, + "step": 29877 + }, + { + "epoch": 9.23, + "learning_rate": 1.1728436699901083e-05, + "loss": 0.0185, + "step": 29878 + }, + { + "epoch": 9.23, + "learning_rate": 1.1727944106658833e-05, + "loss": 0.0192, + "step": 29879 + }, + { + "epoch": 9.23, + "learning_rate": 1.1727451509094679e-05, + "loss": 0.0199, + "step": 29880 + }, + { + "epoch": 9.23, + "learning_rate": 1.1726958907209854e-05, + "loss": 0.0183, + "step": 29881 + }, + { + "epoch": 9.23, + "learning_rate": 1.1726466301005588e-05, + "loss": 0.0172, + "step": 29882 + }, + { + "epoch": 9.23, + "learning_rate": 1.1725973690483117e-05, + "loss": 0.02, + "step": 29883 + }, + { + "epoch": 9.23, + "learning_rate": 1.172548107564367e-05, + "loss": 0.0215, + "step": 29884 + }, + { + "epoch": 9.23, + "learning_rate": 1.172498845648848e-05, + "loss": 0.0189, + "step": 29885 + }, + { + "epoch": 9.23, + "learning_rate": 1.172449583301878e-05, + "loss": 0.0199, + "step": 29886 + }, + { + "epoch": 9.23, + "learning_rate": 1.1724003205235798e-05, + "loss": 0.0184, + "step": 29887 + }, + { + "epoch": 9.23, + "learning_rate": 1.1723510573140776e-05, + "loss": 0.019, + "step": 29888 + }, + { + "epoch": 9.23, + "learning_rate": 1.1723017936734933e-05, + "loss": 0.0179, + "step": 29889 + }, + { + "epoch": 9.23, + "learning_rate": 1.172252529601951e-05, + "loss": 0.0234, + "step": 29890 + }, + { + "epoch": 9.23, + "learning_rate": 1.1722032650995743e-05, + "loss": 0.0199, + "step": 29891 + }, + { + "epoch": 9.23, + "learning_rate": 1.172154000166485e-05, + "loss": 0.0195, + "step": 29892 + }, + { + "epoch": 9.23, + "learning_rate": 1.1721047348028076e-05, + "loss": 0.0199, + "step": 29893 + }, + { + "epoch": 9.23, + "learning_rate": 1.1720554690086648e-05, + "loss": 0.0183, + "step": 29894 + }, + { + "epoch": 9.23, + "learning_rate": 1.1720062027841796e-05, + "loss": 0.019, + "step": 29895 + }, + { + "epoch": 9.23, + "learning_rate": 1.171956936129476e-05, + "loss": 0.0193, + "step": 29896 + }, + { + "epoch": 9.23, + "learning_rate": 1.1719076690446763e-05, + "loss": 0.0198, + "step": 29897 + }, + { + "epoch": 9.23, + "learning_rate": 1.1718584015299044e-05, + "loss": 0.0194, + "step": 29898 + }, + { + "epoch": 9.23, + "learning_rate": 1.1718091335852835e-05, + "loss": 0.0178, + "step": 29899 + }, + { + "epoch": 9.23, + "learning_rate": 1.171759865210936e-05, + "loss": 0.0213, + "step": 29900 + }, + { + "epoch": 9.23, + "learning_rate": 1.1717105964069863e-05, + "loss": 0.0199, + "step": 29901 + }, + { + "epoch": 9.23, + "learning_rate": 1.171661327173557e-05, + "loss": 0.0217, + "step": 29902 + }, + { + "epoch": 9.23, + "learning_rate": 1.1716120575107713e-05, + "loss": 0.0202, + "step": 29903 + }, + { + "epoch": 9.23, + "learning_rate": 1.1715627874187527e-05, + "loss": 0.0175, + "step": 29904 + }, + { + "epoch": 9.24, + "learning_rate": 1.1715135168976239e-05, + "loss": 0.0192, + "step": 29905 + }, + { + "epoch": 9.24, + "learning_rate": 1.171464245947509e-05, + "loss": 0.0196, + "step": 29906 + }, + { + "epoch": 9.24, + "learning_rate": 1.1714149745685304e-05, + "loss": 0.0197, + "step": 29907 + }, + { + "epoch": 9.24, + "learning_rate": 1.1713657027608119e-05, + "loss": 0.0198, + "step": 29908 + }, + { + "epoch": 9.24, + "learning_rate": 1.1713164305244762e-05, + "loss": 0.0205, + "step": 29909 + }, + { + "epoch": 9.24, + "learning_rate": 1.1712671578596471e-05, + "loss": 0.0214, + "step": 29910 + }, + { + "epoch": 9.24, + "learning_rate": 1.1712178847664477e-05, + "loss": 0.019, + "step": 29911 + }, + { + "epoch": 9.24, + "learning_rate": 1.1711686112450009e-05, + "loss": 0.0207, + "step": 29912 + }, + { + "epoch": 9.24, + "learning_rate": 1.1711193372954304e-05, + "loss": 0.0193, + "step": 29913 + }, + { + "epoch": 9.24, + "learning_rate": 1.171070062917859e-05, + "loss": 0.0175, + "step": 29914 + }, + { + "epoch": 9.24, + "learning_rate": 1.1710207881124103e-05, + "loss": 0.0222, + "step": 29915 + }, + { + "epoch": 9.24, + "learning_rate": 1.1709715128792075e-05, + "loss": 0.02, + "step": 29916 + }, + { + "epoch": 9.24, + "learning_rate": 1.1709222372183736e-05, + "loss": 0.0196, + "step": 29917 + }, + { + "epoch": 9.24, + "learning_rate": 1.170872961130032e-05, + "loss": 0.0183, + "step": 29918 + }, + { + "epoch": 9.24, + "learning_rate": 1.1708236846143062e-05, + "loss": 0.0194, + "step": 29919 + }, + { + "epoch": 9.24, + "learning_rate": 1.170774407671319e-05, + "loss": 0.0186, + "step": 29920 + }, + { + "epoch": 9.24, + "learning_rate": 1.1707251303011937e-05, + "loss": 0.0215, + "step": 29921 + }, + { + "epoch": 9.24, + "learning_rate": 1.1706758525040543e-05, + "loss": 0.0217, + "step": 29922 + }, + { + "epoch": 9.24, + "learning_rate": 1.1706265742800226e-05, + "loss": 0.0221, + "step": 29923 + }, + { + "epoch": 9.24, + "learning_rate": 1.1705772956292236e-05, + "loss": 0.0205, + "step": 29924 + }, + { + "epoch": 9.24, + "learning_rate": 1.1705280165517792e-05, + "loss": 0.0207, + "step": 29925 + }, + { + "epoch": 9.24, + "learning_rate": 1.170478737047813e-05, + "loss": 0.0227, + "step": 29926 + }, + { + "epoch": 9.24, + "learning_rate": 1.1704294571174489e-05, + "loss": 0.0188, + "step": 29927 + }, + { + "epoch": 9.24, + "learning_rate": 1.1703801767608092e-05, + "loss": 0.0192, + "step": 29928 + }, + { + "epoch": 9.24, + "learning_rate": 1.1703308959780177e-05, + "loss": 0.0209, + "step": 29929 + }, + { + "epoch": 9.24, + "learning_rate": 1.1702816147691978e-05, + "loss": 0.0195, + "step": 29930 + }, + { + "epoch": 9.24, + "learning_rate": 1.1702323331344721e-05, + "loss": 0.0203, + "step": 29931 + }, + { + "epoch": 9.24, + "learning_rate": 1.1701830510739646e-05, + "loss": 0.0216, + "step": 29932 + }, + { + "epoch": 9.24, + "learning_rate": 1.1701337685877982e-05, + "loss": 0.0188, + "step": 29933 + }, + { + "epoch": 9.24, + "learning_rate": 1.1700844856760962e-05, + "loss": 0.0215, + "step": 29934 + }, + { + "epoch": 9.24, + "learning_rate": 1.1700352023389818e-05, + "loss": 0.0194, + "step": 29935 + }, + { + "epoch": 9.24, + "learning_rate": 1.1699859185765783e-05, + "loss": 0.0202, + "step": 29936 + }, + { + "epoch": 9.25, + "learning_rate": 1.1699366343890093e-05, + "loss": 0.0171, + "step": 29937 + }, + { + "epoch": 9.25, + "learning_rate": 1.1698873497763974e-05, + "loss": 0.0205, + "step": 29938 + }, + { + "epoch": 9.25, + "learning_rate": 1.1698380647388666e-05, + "loss": 0.0163, + "step": 29939 + }, + { + "epoch": 9.25, + "learning_rate": 1.1697887792765396e-05, + "loss": 0.0193, + "step": 29940 + }, + { + "epoch": 9.25, + "learning_rate": 1.1697394933895398e-05, + "loss": 0.0202, + "step": 29941 + }, + { + "epoch": 9.25, + "learning_rate": 1.169690207077991e-05, + "loss": 0.0206, + "step": 29942 + }, + { + "epoch": 9.25, + "learning_rate": 1.1696409203420156e-05, + "loss": 0.0198, + "step": 29943 + }, + { + "epoch": 9.25, + "learning_rate": 1.1695916331817374e-05, + "loss": 0.0211, + "step": 29944 + }, + { + "epoch": 9.25, + "learning_rate": 1.1695423455972799e-05, + "loss": 0.0191, + "step": 29945 + }, + { + "epoch": 9.25, + "learning_rate": 1.1694930575887658e-05, + "loss": 0.0183, + "step": 29946 + }, + { + "epoch": 9.25, + "learning_rate": 1.1694437691563188e-05, + "loss": 0.0188, + "step": 29947 + }, + { + "epoch": 9.25, + "learning_rate": 1.1693944803000619e-05, + "loss": 0.019, + "step": 29948 + }, + { + "epoch": 9.25, + "learning_rate": 1.1693451910201183e-05, + "loss": 0.0199, + "step": 29949 + }, + { + "epoch": 9.25, + "learning_rate": 1.169295901316612e-05, + "loss": 0.023, + "step": 29950 + }, + { + "epoch": 9.25, + "learning_rate": 1.1692466111896655e-05, + "loss": 0.02, + "step": 29951 + }, + { + "epoch": 9.25, + "learning_rate": 1.1691973206394023e-05, + "loss": 0.0173, + "step": 29952 + }, + { + "epoch": 9.25, + "learning_rate": 1.169148029665946e-05, + "loss": 0.0193, + "step": 29953 + }, + { + "epoch": 9.25, + "learning_rate": 1.1690987382694191e-05, + "loss": 0.0165, + "step": 29954 + }, + { + "epoch": 9.25, + "learning_rate": 1.169049446449946e-05, + "loss": 0.0209, + "step": 29955 + }, + { + "epoch": 9.25, + "learning_rate": 1.1690001542076493e-05, + "loss": 0.0185, + "step": 29956 + }, + { + "epoch": 9.25, + "learning_rate": 1.1689508615426518e-05, + "loss": 0.0202, + "step": 29957 + }, + { + "epoch": 9.25, + "learning_rate": 1.1689015684550781e-05, + "loss": 0.0173, + "step": 29958 + }, + { + "epoch": 9.25, + "learning_rate": 1.1688522749450503e-05, + "loss": 0.0194, + "step": 29959 + }, + { + "epoch": 9.25, + "learning_rate": 1.1688029810126927e-05, + "loss": 0.021, + "step": 29960 + }, + { + "epoch": 9.25, + "learning_rate": 1.1687536866581275e-05, + "loss": 0.0202, + "step": 29961 + }, + { + "epoch": 9.25, + "learning_rate": 1.1687043918814786e-05, + "loss": 0.0194, + "step": 29962 + }, + { + "epoch": 9.25, + "learning_rate": 1.1686550966828696e-05, + "loss": 0.02, + "step": 29963 + }, + { + "epoch": 9.25, + "learning_rate": 1.1686058010624233e-05, + "loss": 0.0189, + "step": 29964 + }, + { + "epoch": 9.25, + "learning_rate": 1.1685565050202631e-05, + "loss": 0.0185, + "step": 29965 + }, + { + "epoch": 9.25, + "learning_rate": 1.1685072085565123e-05, + "loss": 0.0207, + "step": 29966 + }, + { + "epoch": 9.25, + "learning_rate": 1.1684579116712942e-05, + "loss": 0.022, + "step": 29967 + }, + { + "epoch": 9.25, + "learning_rate": 1.1684086143647322e-05, + "loss": 0.0211, + "step": 29968 + }, + { + "epoch": 9.26, + "learning_rate": 1.1683593166369495e-05, + "loss": 0.0187, + "step": 29969 + }, + { + "epoch": 9.26, + "learning_rate": 1.1683100184880696e-05, + "loss": 0.0203, + "step": 29970 + }, + { + "epoch": 9.26, + "learning_rate": 1.1682607199182154e-05, + "loss": 0.0215, + "step": 29971 + }, + { + "epoch": 9.26, + "learning_rate": 1.1682114209275107e-05, + "loss": 0.0196, + "step": 29972 + }, + { + "epoch": 9.26, + "learning_rate": 1.1681621215160786e-05, + "loss": 0.0179, + "step": 29973 + }, + { + "epoch": 9.26, + "learning_rate": 1.168112821684042e-05, + "loss": 0.0207, + "step": 29974 + }, + { + "epoch": 9.26, + "learning_rate": 1.1680635214315248e-05, + "loss": 0.0201, + "step": 29975 + }, + { + "epoch": 9.26, + "learning_rate": 1.16801422075865e-05, + "loss": 0.0193, + "step": 29976 + }, + { + "epoch": 9.26, + "learning_rate": 1.1679649196655412e-05, + "loss": 0.0188, + "step": 29977 + }, + { + "epoch": 9.26, + "learning_rate": 1.1679156181523214e-05, + "loss": 0.0183, + "step": 29978 + }, + { + "epoch": 9.26, + "learning_rate": 1.1678663162191137e-05, + "loss": 0.0206, + "step": 29979 + }, + { + "epoch": 9.26, + "learning_rate": 1.167817013866042e-05, + "loss": 0.0196, + "step": 29980 + }, + { + "epoch": 9.26, + "learning_rate": 1.1677677110932297e-05, + "loss": 0.0182, + "step": 29981 + }, + { + "epoch": 9.26, + "learning_rate": 1.1677184079007991e-05, + "loss": 0.0176, + "step": 29982 + }, + { + "epoch": 9.26, + "learning_rate": 1.1676691042888746e-05, + "loss": 0.0192, + "step": 29983 + }, + { + "epoch": 9.26, + "learning_rate": 1.167619800257579e-05, + "loss": 0.0187, + "step": 29984 + }, + { + "epoch": 9.26, + "learning_rate": 1.1675704958070356e-05, + "loss": 0.0228, + "step": 29985 + }, + { + "epoch": 9.26, + "learning_rate": 1.1675211909373677e-05, + "loss": 0.0209, + "step": 29986 + }, + { + "epoch": 9.26, + "learning_rate": 1.1674718856486991e-05, + "loss": 0.0199, + "step": 29987 + }, + { + "epoch": 9.26, + "learning_rate": 1.1674225799411528e-05, + "loss": 0.0178, + "step": 29988 + }, + { + "epoch": 9.26, + "learning_rate": 1.1673732738148518e-05, + "loss": 0.019, + "step": 29989 + }, + { + "epoch": 9.26, + "learning_rate": 1.1673239672699195e-05, + "loss": 0.0187, + "step": 29990 + }, + { + "epoch": 9.26, + "learning_rate": 1.16727466030648e-05, + "loss": 0.0211, + "step": 29991 + }, + { + "epoch": 9.26, + "learning_rate": 1.1672253529246558e-05, + "loss": 0.0204, + "step": 29992 + }, + { + "epoch": 9.26, + "learning_rate": 1.1671760451245704e-05, + "loss": 0.0182, + "step": 29993 + }, + { + "epoch": 9.26, + "learning_rate": 1.1671267369063472e-05, + "loss": 0.0208, + "step": 29994 + }, + { + "epoch": 9.26, + "learning_rate": 1.1670774282701099e-05, + "loss": 0.0169, + "step": 29995 + }, + { + "epoch": 9.26, + "learning_rate": 1.167028119215981e-05, + "loss": 0.0191, + "step": 29996 + }, + { + "epoch": 9.26, + "learning_rate": 1.1669788097440846e-05, + "loss": 0.0222, + "step": 29997 + }, + { + "epoch": 9.26, + "learning_rate": 1.1669294998545438e-05, + "loss": 0.016, + "step": 29998 + }, + { + "epoch": 9.26, + "learning_rate": 1.1668801895474818e-05, + "loss": 0.0212, + "step": 29999 + }, + { + "epoch": 9.26, + "learning_rate": 1.1668308788230221e-05, + "loss": 0.0191, + "step": 30000 + }, + { + "epoch": 9.26, + "learning_rate": 1.1667815676812877e-05, + "loss": 0.0199, + "step": 30001 + }, + { + "epoch": 9.27, + "learning_rate": 1.1667322561224022e-05, + "loss": 0.0221, + "step": 30002 + }, + { + "epoch": 9.27, + "learning_rate": 1.1666829441464891e-05, + "loss": 0.0209, + "step": 30003 + }, + { + "epoch": 9.27, + "learning_rate": 1.1666336317536716e-05, + "loss": 0.0173, + "step": 30004 + }, + { + "epoch": 9.27, + "learning_rate": 1.1665843189440727e-05, + "loss": 0.0205, + "step": 30005 + }, + { + "epoch": 9.27, + "learning_rate": 1.1665350057178161e-05, + "loss": 0.0201, + "step": 30006 + }, + { + "epoch": 9.27, + "learning_rate": 1.1664856920750254e-05, + "loss": 0.0205, + "step": 30007 + }, + { + "epoch": 9.27, + "learning_rate": 1.1664363780158233e-05, + "loss": 0.0233, + "step": 30008 + }, + { + "epoch": 9.27, + "learning_rate": 1.1663870635403339e-05, + "loss": 0.0212, + "step": 30009 + }, + { + "epoch": 9.27, + "learning_rate": 1.1663377486486793e-05, + "loss": 0.0208, + "step": 30010 + }, + { + "epoch": 9.27, + "learning_rate": 1.1662884333409843e-05, + "loss": 0.0193, + "step": 30011 + }, + { + "epoch": 9.27, + "learning_rate": 1.1662391176173716e-05, + "loss": 0.0206, + "step": 30012 + }, + { + "epoch": 9.27, + "learning_rate": 1.1661898014779643e-05, + "loss": 0.0215, + "step": 30013 + }, + { + "epoch": 9.27, + "learning_rate": 1.166140484922886e-05, + "loss": 0.0191, + "step": 30014 + }, + { + "epoch": 9.27, + "learning_rate": 1.1660911679522603e-05, + "loss": 0.02, + "step": 30015 + }, + { + "epoch": 9.27, + "learning_rate": 1.1660418505662098e-05, + "loss": 0.0197, + "step": 30016 + }, + { + "epoch": 9.27, + "learning_rate": 1.1659925327648588e-05, + "loss": 0.0184, + "step": 30017 + }, + { + "epoch": 9.27, + "learning_rate": 1.16594321454833e-05, + "loss": 0.0219, + "step": 30018 + }, + { + "epoch": 9.27, + "learning_rate": 1.1658938959167472e-05, + "loss": 0.0203, + "step": 30019 + }, + { + "epoch": 9.27, + "learning_rate": 1.1658445768702334e-05, + "loss": 0.0201, + "step": 30020 + }, + { + "epoch": 9.27, + "learning_rate": 1.1657952574089117e-05, + "loss": 0.0208, + "step": 30021 + }, + { + "epoch": 9.27, + "learning_rate": 1.1657459375329063e-05, + "loss": 0.02, + "step": 30022 + }, + { + "epoch": 9.27, + "learning_rate": 1.1656966172423398e-05, + "loss": 0.0169, + "step": 30023 + }, + { + "epoch": 9.27, + "learning_rate": 1.165647296537336e-05, + "loss": 0.0217, + "step": 30024 + }, + { + "epoch": 9.27, + "learning_rate": 1.165597975418018e-05, + "loss": 0.0211, + "step": 30025 + }, + { + "epoch": 9.27, + "learning_rate": 1.1655486538845094e-05, + "loss": 0.0201, + "step": 30026 + }, + { + "epoch": 9.27, + "learning_rate": 1.1654993319369333e-05, + "loss": 0.0224, + "step": 30027 + }, + { + "epoch": 9.27, + "learning_rate": 1.165450009575413e-05, + "loss": 0.0171, + "step": 30028 + }, + { + "epoch": 9.27, + "learning_rate": 1.1654006868000723e-05, + "loss": 0.0194, + "step": 30029 + }, + { + "epoch": 9.27, + "learning_rate": 1.1653513636110342e-05, + "loss": 0.0221, + "step": 30030 + }, + { + "epoch": 9.27, + "learning_rate": 1.1653020400084223e-05, + "loss": 0.0169, + "step": 30031 + }, + { + "epoch": 9.27, + "learning_rate": 1.16525271599236e-05, + "loss": 0.0212, + "step": 30032 + }, + { + "epoch": 9.27, + "learning_rate": 1.1652033915629702e-05, + "loss": 0.0181, + "step": 30033 + }, + { + "epoch": 9.28, + "learning_rate": 1.1651540667203764e-05, + "loss": 0.021, + "step": 30034 + }, + { + "epoch": 9.28, + "learning_rate": 1.1651047414647028e-05, + "loss": 0.0219, + "step": 30035 + }, + { + "epoch": 9.28, + "learning_rate": 1.1650554157960717e-05, + "loss": 0.0219, + "step": 30036 + }, + { + "epoch": 9.28, + "learning_rate": 1.1650060897146069e-05, + "loss": 0.0208, + "step": 30037 + }, + { + "epoch": 9.28, + "learning_rate": 1.164956763220432e-05, + "loss": 0.0212, + "step": 30038 + }, + { + "epoch": 9.28, + "learning_rate": 1.16490743631367e-05, + "loss": 0.0192, + "step": 30039 + }, + { + "epoch": 9.28, + "learning_rate": 1.1648581089944443e-05, + "loss": 0.0185, + "step": 30040 + }, + { + "epoch": 9.28, + "learning_rate": 1.1648087812628784e-05, + "loss": 0.0196, + "step": 30041 + }, + { + "epoch": 9.28, + "learning_rate": 1.164759453119096e-05, + "loss": 0.0195, + "step": 30042 + }, + { + "epoch": 9.28, + "learning_rate": 1.1647101245632199e-05, + "loss": 0.0218, + "step": 30043 + }, + { + "epoch": 9.28, + "learning_rate": 1.1646607955953738e-05, + "loss": 0.0194, + "step": 30044 + }, + { + "epoch": 9.28, + "learning_rate": 1.164611466215681e-05, + "loss": 0.0213, + "step": 30045 + }, + { + "epoch": 9.28, + "learning_rate": 1.164562136424265e-05, + "loss": 0.0184, + "step": 30046 + }, + { + "epoch": 9.28, + "learning_rate": 1.164512806221249e-05, + "loss": 0.0214, + "step": 30047 + }, + { + "epoch": 9.28, + "learning_rate": 1.1644634756067565e-05, + "loss": 0.0204, + "step": 30048 + }, + { + "epoch": 9.28, + "learning_rate": 1.1644141445809107e-05, + "loss": 0.0216, + "step": 30049 + }, + { + "epoch": 9.28, + "learning_rate": 1.1643648131438354e-05, + "loss": 0.0195, + "step": 30050 + }, + { + "epoch": 9.28, + "learning_rate": 1.1643154812956534e-05, + "loss": 0.022, + "step": 30051 + }, + { + "epoch": 9.28, + "learning_rate": 1.1642661490364886e-05, + "loss": 0.0216, + "step": 30052 + }, + { + "epoch": 9.28, + "learning_rate": 1.1642168163664642e-05, + "loss": 0.0211, + "step": 30053 + }, + { + "epoch": 9.28, + "learning_rate": 1.1641674832857037e-05, + "loss": 0.0222, + "step": 30054 + }, + { + "epoch": 9.28, + "learning_rate": 1.1641181497943301e-05, + "loss": 0.0212, + "step": 30055 + }, + { + "epoch": 9.28, + "learning_rate": 1.1640688158924673e-05, + "loss": 0.0181, + "step": 30056 + }, + { + "epoch": 9.28, + "learning_rate": 1.1640194815802386e-05, + "loss": 0.0193, + "step": 30057 + }, + { + "epoch": 9.28, + "learning_rate": 1.1639701468577668e-05, + "loss": 0.0204, + "step": 30058 + }, + { + "epoch": 9.28, + "learning_rate": 1.1639208117251761e-05, + "loss": 0.0204, + "step": 30059 + }, + { + "epoch": 9.28, + "learning_rate": 1.1638714761825896e-05, + "loss": 0.018, + "step": 30060 + }, + { + "epoch": 9.28, + "learning_rate": 1.1638221402301304e-05, + "loss": 0.0181, + "step": 30061 + }, + { + "epoch": 9.28, + "learning_rate": 1.1637728038679223e-05, + "loss": 0.0205, + "step": 30062 + }, + { + "epoch": 9.28, + "learning_rate": 1.1637234670960888e-05, + "loss": 0.0177, + "step": 30063 + }, + { + "epoch": 9.28, + "learning_rate": 1.1636741299147524e-05, + "loss": 0.0167, + "step": 30064 + }, + { + "epoch": 9.28, + "learning_rate": 1.1636247923240375e-05, + "loss": 0.0219, + "step": 30065 + }, + { + "epoch": 9.28, + "learning_rate": 1.1635754543240676e-05, + "loss": 0.0209, + "step": 30066 + }, + { + "epoch": 9.29, + "learning_rate": 1.163526115914965e-05, + "loss": 0.0216, + "step": 30067 + }, + { + "epoch": 9.29, + "learning_rate": 1.1634767770968542e-05, + "loss": 0.0198, + "step": 30068 + }, + { + "epoch": 9.29, + "learning_rate": 1.1634274378698578e-05, + "loss": 0.0193, + "step": 30069 + }, + { + "epoch": 9.29, + "learning_rate": 1.1633780982340996e-05, + "loss": 0.0222, + "step": 30070 + }, + { + "epoch": 9.29, + "learning_rate": 1.1633287581897032e-05, + "loss": 0.0233, + "step": 30071 + }, + { + "epoch": 9.29, + "learning_rate": 1.1632794177367917e-05, + "loss": 0.0212, + "step": 30072 + }, + { + "epoch": 9.29, + "learning_rate": 1.1632300768754887e-05, + "loss": 0.0168, + "step": 30073 + }, + { + "epoch": 9.29, + "learning_rate": 1.1631807356059173e-05, + "loss": 0.019, + "step": 30074 + }, + { + "epoch": 9.29, + "learning_rate": 1.163131393928201e-05, + "loss": 0.0208, + "step": 30075 + }, + { + "epoch": 9.29, + "learning_rate": 1.1630820518424637e-05, + "loss": 0.023, + "step": 30076 + }, + { + "epoch": 9.29, + "learning_rate": 1.1630327093488283e-05, + "loss": 0.0211, + "step": 30077 + }, + { + "epoch": 9.29, + "learning_rate": 1.1629833664474184e-05, + "loss": 0.0217, + "step": 30078 + }, + { + "epoch": 9.29, + "learning_rate": 1.1629340231383572e-05, + "loss": 0.0201, + "step": 30079 + }, + { + "epoch": 9.29, + "learning_rate": 1.1628846794217685e-05, + "loss": 0.0222, + "step": 30080 + }, + { + "epoch": 9.29, + "learning_rate": 1.1628353352977752e-05, + "loss": 0.0189, + "step": 30081 + }, + { + "epoch": 9.29, + "learning_rate": 1.1627859907665013e-05, + "loss": 0.0202, + "step": 30082 + }, + { + "epoch": 9.29, + "learning_rate": 1.16273664582807e-05, + "loss": 0.0205, + "step": 30083 + }, + { + "epoch": 9.29, + "learning_rate": 1.1626873004826045e-05, + "loss": 0.022, + "step": 30084 + }, + { + "epoch": 9.29, + "learning_rate": 1.1626379547302284e-05, + "loss": 0.02, + "step": 30085 + }, + { + "epoch": 9.29, + "learning_rate": 1.1625886085710654e-05, + "loss": 0.0192, + "step": 30086 + }, + { + "epoch": 9.29, + "learning_rate": 1.1625392620052382e-05, + "loss": 0.0216, + "step": 30087 + }, + { + "epoch": 9.29, + "learning_rate": 1.1624899150328707e-05, + "loss": 0.0178, + "step": 30088 + }, + { + "epoch": 9.29, + "learning_rate": 1.1624405676540867e-05, + "loss": 0.0196, + "step": 30089 + }, + { + "epoch": 9.29, + "learning_rate": 1.1623912198690089e-05, + "loss": 0.0196, + "step": 30090 + }, + { + "epoch": 9.29, + "learning_rate": 1.1623418716777612e-05, + "loss": 0.0209, + "step": 30091 + }, + { + "epoch": 9.29, + "learning_rate": 1.1622925230804664e-05, + "loss": 0.0189, + "step": 30092 + }, + { + "epoch": 9.29, + "learning_rate": 1.1622431740772488e-05, + "loss": 0.0194, + "step": 30093 + }, + { + "epoch": 9.29, + "learning_rate": 1.1621938246682317e-05, + "loss": 0.0199, + "step": 30094 + }, + { + "epoch": 9.29, + "learning_rate": 1.1621444748535378e-05, + "loss": 0.0207, + "step": 30095 + }, + { + "epoch": 9.29, + "learning_rate": 1.1620951246332909e-05, + "loss": 0.0204, + "step": 30096 + }, + { + "epoch": 9.29, + "learning_rate": 1.1620457740076151e-05, + "loss": 0.0199, + "step": 30097 + }, + { + "epoch": 9.29, + "learning_rate": 1.1619964229766327e-05, + "loss": 0.0219, + "step": 30098 + }, + { + "epoch": 9.3, + "learning_rate": 1.1619470715404682e-05, + "loss": 0.0177, + "step": 30099 + }, + { + "epoch": 9.3, + "learning_rate": 1.1618977196992442e-05, + "loss": 0.019, + "step": 30100 + }, + { + "epoch": 9.3, + "learning_rate": 1.1618483674530845e-05, + "loss": 0.0217, + "step": 30101 + }, + { + "epoch": 9.3, + "learning_rate": 1.1617990148021127e-05, + "loss": 0.0239, + "step": 30102 + }, + { + "epoch": 9.3, + "learning_rate": 1.1617496617464519e-05, + "loss": 0.0198, + "step": 30103 + }, + { + "epoch": 9.3, + "learning_rate": 1.1617003082862257e-05, + "loss": 0.0215, + "step": 30104 + }, + { + "epoch": 9.3, + "learning_rate": 1.1616509544215575e-05, + "loss": 0.0215, + "step": 30105 + }, + { + "epoch": 9.3, + "learning_rate": 1.1616016001525707e-05, + "loss": 0.0208, + "step": 30106 + }, + { + "epoch": 9.3, + "learning_rate": 1.1615522454793891e-05, + "loss": 0.0198, + "step": 30107 + }, + { + "epoch": 9.3, + "learning_rate": 1.1615028904021358e-05, + "loss": 0.0206, + "step": 30108 + }, + { + "epoch": 9.3, + "learning_rate": 1.1614535349209342e-05, + "loss": 0.0191, + "step": 30109 + }, + { + "epoch": 9.3, + "learning_rate": 1.1614041790359079e-05, + "loss": 0.0191, + "step": 30110 + }, + { + "epoch": 9.3, + "learning_rate": 1.1613548227471802e-05, + "loss": 0.0229, + "step": 30111 + }, + { + "epoch": 9.3, + "learning_rate": 1.1613054660548749e-05, + "loss": 0.0195, + "step": 30112 + }, + { + "epoch": 9.3, + "learning_rate": 1.161256108959115e-05, + "loss": 0.0185, + "step": 30113 + }, + { + "epoch": 9.3, + "learning_rate": 1.1612067514600242e-05, + "loss": 0.0174, + "step": 30114 + }, + { + "epoch": 9.3, + "learning_rate": 1.1611573935577259e-05, + "loss": 0.0249, + "step": 30115 + }, + { + "epoch": 9.3, + "learning_rate": 1.1611080352523435e-05, + "loss": 0.0212, + "step": 30116 + }, + { + "epoch": 9.3, + "learning_rate": 1.161058676544001e-05, + "loss": 0.02, + "step": 30117 + }, + { + "epoch": 9.3, + "learning_rate": 1.1610093174328207e-05, + "loss": 0.0187, + "step": 30118 + }, + { + "epoch": 9.3, + "learning_rate": 1.160959957918927e-05, + "loss": 0.0206, + "step": 30119 + }, + { + "epoch": 9.3, + "learning_rate": 1.1609105980024436e-05, + "loss": 0.0186, + "step": 30120 + }, + { + "epoch": 9.3, + "learning_rate": 1.1608612376834926e-05, + "loss": 0.0195, + "step": 30121 + }, + { + "epoch": 9.3, + "learning_rate": 1.160811876962199e-05, + "loss": 0.0215, + "step": 30122 + }, + { + "epoch": 9.3, + "learning_rate": 1.1607625158386849e-05, + "loss": 0.02, + "step": 30123 + }, + { + "epoch": 9.3, + "learning_rate": 1.1607131543130747e-05, + "loss": 0.0196, + "step": 30124 + }, + { + "epoch": 9.3, + "learning_rate": 1.160663792385492e-05, + "loss": 0.0209, + "step": 30125 + }, + { + "epoch": 9.3, + "learning_rate": 1.1606144300560591e-05, + "loss": 0.0236, + "step": 30126 + }, + { + "epoch": 9.3, + "learning_rate": 1.160565067324901e-05, + "loss": 0.0193, + "step": 30127 + }, + { + "epoch": 9.3, + "learning_rate": 1.16051570419214e-05, + "loss": 0.0193, + "step": 30128 + }, + { + "epoch": 9.3, + "learning_rate": 1.1604663406578997e-05, + "loss": 0.0207, + "step": 30129 + }, + { + "epoch": 9.3, + "learning_rate": 1.1604169767223043e-05, + "loss": 0.0205, + "step": 30130 + }, + { + "epoch": 9.31, + "learning_rate": 1.1603676123854765e-05, + "loss": 0.0192, + "step": 30131 + }, + { + "epoch": 9.31, + "learning_rate": 1.1603182476475401e-05, + "loss": 0.0213, + "step": 30132 + }, + { + "epoch": 9.31, + "learning_rate": 1.1602688825086185e-05, + "loss": 0.0186, + "step": 30133 + }, + { + "epoch": 9.31, + "learning_rate": 1.1602195169688353e-05, + "loss": 0.0205, + "step": 30134 + }, + { + "epoch": 9.31, + "learning_rate": 1.160170151028314e-05, + "loss": 0.0195, + "step": 30135 + }, + { + "epoch": 9.31, + "learning_rate": 1.1601207846871776e-05, + "loss": 0.0184, + "step": 30136 + }, + { + "epoch": 9.31, + "learning_rate": 1.16007141794555e-05, + "loss": 0.024, + "step": 30137 + }, + { + "epoch": 9.31, + "learning_rate": 1.1600220508035545e-05, + "loss": 0.0202, + "step": 30138 + }, + { + "epoch": 9.31, + "learning_rate": 1.159972683261315e-05, + "loss": 0.0189, + "step": 30139 + }, + { + "epoch": 9.31, + "learning_rate": 1.1599233153189542e-05, + "loss": 0.0208, + "step": 30140 + }, + { + "epoch": 9.31, + "learning_rate": 1.1598739469765963e-05, + "loss": 0.0205, + "step": 30141 + }, + { + "epoch": 9.31, + "learning_rate": 1.1598245782343645e-05, + "loss": 0.0195, + "step": 30142 + }, + { + "epoch": 9.31, + "learning_rate": 1.1597752090923821e-05, + "loss": 0.0208, + "step": 30143 + }, + { + "epoch": 9.31, + "learning_rate": 1.1597258395507728e-05, + "loss": 0.022, + "step": 30144 + }, + { + "epoch": 9.31, + "learning_rate": 1.1596764696096603e-05, + "loss": 0.019, + "step": 30145 + }, + { + "epoch": 9.31, + "learning_rate": 1.1596270992691676e-05, + "loss": 0.0205, + "step": 30146 + }, + { + "epoch": 9.31, + "learning_rate": 1.1595777285294185e-05, + "loss": 0.0224, + "step": 30147 + }, + { + "epoch": 9.31, + "learning_rate": 1.1595283573905367e-05, + "loss": 0.0226, + "step": 30148 + }, + { + "epoch": 9.31, + "learning_rate": 1.1594789858526447e-05, + "loss": 0.0228, + "step": 30149 + }, + { + "epoch": 9.31, + "learning_rate": 1.1594296139158671e-05, + "loss": 0.0202, + "step": 30150 + }, + { + "epoch": 9.31, + "learning_rate": 1.159380241580327e-05, + "loss": 0.0217, + "step": 30151 + }, + { + "epoch": 9.31, + "learning_rate": 1.1593308688461476e-05, + "loss": 0.0191, + "step": 30152 + }, + { + "epoch": 9.31, + "learning_rate": 1.159281495713453e-05, + "loss": 0.0198, + "step": 30153 + }, + { + "epoch": 9.31, + "learning_rate": 1.159232122182366e-05, + "loss": 0.0201, + "step": 30154 + }, + { + "epoch": 9.31, + "learning_rate": 1.1591827482530103e-05, + "loss": 0.0195, + "step": 30155 + }, + { + "epoch": 9.31, + "learning_rate": 1.15913337392551e-05, + "loss": 0.0194, + "step": 30156 + }, + { + "epoch": 9.31, + "learning_rate": 1.1590839991999876e-05, + "loss": 0.023, + "step": 30157 + }, + { + "epoch": 9.31, + "learning_rate": 1.1590346240765675e-05, + "loss": 0.0223, + "step": 30158 + }, + { + "epoch": 9.31, + "learning_rate": 1.1589852485553727e-05, + "loss": 0.0213, + "step": 30159 + }, + { + "epoch": 9.31, + "learning_rate": 1.1589358726365265e-05, + "loss": 0.0189, + "step": 30160 + }, + { + "epoch": 9.31, + "learning_rate": 1.1588864963201532e-05, + "loss": 0.0216, + "step": 30161 + }, + { + "epoch": 9.31, + "learning_rate": 1.1588371196063754e-05, + "loss": 0.0203, + "step": 30162 + }, + { + "epoch": 9.31, + "learning_rate": 1.158787742495317e-05, + "loss": 0.018, + "step": 30163 + }, + { + "epoch": 9.32, + "learning_rate": 1.1587383649871018e-05, + "loss": 0.0214, + "step": 30164 + }, + { + "epoch": 9.32, + "learning_rate": 1.1586889870818528e-05, + "loss": 0.0189, + "step": 30165 + }, + { + "epoch": 9.32, + "learning_rate": 1.1586396087796936e-05, + "loss": 0.0187, + "step": 30166 + }, + { + "epoch": 9.32, + "learning_rate": 1.1585902300807479e-05, + "loss": 0.021, + "step": 30167 + }, + { + "epoch": 9.32, + "learning_rate": 1.1585408509851392e-05, + "loss": 0.0207, + "step": 30168 + }, + { + "epoch": 9.32, + "learning_rate": 1.1584914714929907e-05, + "loss": 0.0198, + "step": 30169 + }, + { + "epoch": 9.32, + "learning_rate": 1.1584420916044264e-05, + "loss": 0.0202, + "step": 30170 + }, + { + "epoch": 9.32, + "learning_rate": 1.1583927113195692e-05, + "loss": 0.0176, + "step": 30171 + }, + { + "epoch": 9.32, + "learning_rate": 1.1583433306385432e-05, + "loss": 0.0205, + "step": 30172 + }, + { + "epoch": 9.32, + "learning_rate": 1.1582939495614716e-05, + "loss": 0.0219, + "step": 30173 + }, + { + "epoch": 9.32, + "learning_rate": 1.158244568088478e-05, + "loss": 0.019, + "step": 30174 + }, + { + "epoch": 9.32, + "learning_rate": 1.1581951862196856e-05, + "loss": 0.0198, + "step": 30175 + }, + { + "epoch": 9.32, + "learning_rate": 1.1581458039552187e-05, + "loss": 0.0191, + "step": 30176 + }, + { + "epoch": 9.32, + "learning_rate": 1.1580964212951997e-05, + "loss": 0.0213, + "step": 30177 + }, + { + "epoch": 9.32, + "learning_rate": 1.158047038239753e-05, + "loss": 0.0185, + "step": 30178 + }, + { + "epoch": 9.32, + "learning_rate": 1.1579976547890021e-05, + "loss": 0.0189, + "step": 30179 + }, + { + "epoch": 9.32, + "learning_rate": 1.1579482709430699e-05, + "loss": 0.0186, + "step": 30180 + }, + { + "epoch": 9.32, + "learning_rate": 1.1578988867020806e-05, + "loss": 0.0222, + "step": 30181 + }, + { + "epoch": 9.32, + "learning_rate": 1.157849502066157e-05, + "loss": 0.0181, + "step": 30182 + }, + { + "epoch": 9.32, + "learning_rate": 1.1578001170354229e-05, + "loss": 0.0197, + "step": 30183 + }, + { + "epoch": 9.32, + "learning_rate": 1.1577507316100026e-05, + "loss": 0.0224, + "step": 30184 + }, + { + "epoch": 9.32, + "learning_rate": 1.1577013457900184e-05, + "loss": 0.022, + "step": 30185 + }, + { + "epoch": 9.32, + "learning_rate": 1.1576519595755946e-05, + "loss": 0.0181, + "step": 30186 + }, + { + "epoch": 9.32, + "learning_rate": 1.1576025729668542e-05, + "loss": 0.019, + "step": 30187 + }, + { + "epoch": 9.32, + "learning_rate": 1.1575531859639211e-05, + "loss": 0.019, + "step": 30188 + }, + { + "epoch": 9.32, + "learning_rate": 1.1575037985669191e-05, + "loss": 0.0218, + "step": 30189 + }, + { + "epoch": 9.32, + "learning_rate": 1.157454410775971e-05, + "loss": 0.0221, + "step": 30190 + }, + { + "epoch": 9.32, + "learning_rate": 1.157405022591201e-05, + "loss": 0.0218, + "step": 30191 + }, + { + "epoch": 9.32, + "learning_rate": 1.1573556340127322e-05, + "loss": 0.0227, + "step": 30192 + }, + { + "epoch": 9.32, + "learning_rate": 1.157306245040688e-05, + "loss": 0.0209, + "step": 30193 + }, + { + "epoch": 9.32, + "learning_rate": 1.1572568556751925e-05, + "loss": 0.0193, + "step": 30194 + }, + { + "epoch": 9.32, + "learning_rate": 1.1572074659163688e-05, + "loss": 0.0208, + "step": 30195 + }, + { + "epoch": 9.33, + "learning_rate": 1.1571580757643405e-05, + "loss": 0.021, + "step": 30196 + }, + { + "epoch": 9.33, + "learning_rate": 1.1571086852192315e-05, + "loss": 0.0198, + "step": 30197 + }, + { + "epoch": 9.33, + "learning_rate": 1.1570592942811647e-05, + "loss": 0.0186, + "step": 30198 + }, + { + "epoch": 9.33, + "learning_rate": 1.1570099029502639e-05, + "loss": 0.0174, + "step": 30199 + }, + { + "epoch": 9.33, + "learning_rate": 1.1569605112266532e-05, + "loss": 0.019, + "step": 30200 + }, + { + "epoch": 9.33, + "learning_rate": 1.1569111191104552e-05, + "loss": 0.0176, + "step": 30201 + }, + { + "epoch": 9.33, + "learning_rate": 1.156861726601794e-05, + "loss": 0.022, + "step": 30202 + }, + { + "epoch": 9.33, + "learning_rate": 1.1568123337007928e-05, + "loss": 0.0214, + "step": 30203 + }, + { + "epoch": 9.33, + "learning_rate": 1.1567629404075755e-05, + "loss": 0.0203, + "step": 30204 + }, + { + "epoch": 9.33, + "learning_rate": 1.1567135467222656e-05, + "loss": 0.0195, + "step": 30205 + }, + { + "epoch": 9.33, + "learning_rate": 1.1566641526449865e-05, + "loss": 0.0217, + "step": 30206 + }, + { + "epoch": 9.33, + "learning_rate": 1.1566147581758618e-05, + "loss": 0.0234, + "step": 30207 + }, + { + "epoch": 9.33, + "learning_rate": 1.1565653633150147e-05, + "loss": 0.0214, + "step": 30208 + }, + { + "epoch": 9.33, + "learning_rate": 1.1565159680625695e-05, + "loss": 0.0219, + "step": 30209 + }, + { + "epoch": 9.33, + "learning_rate": 1.1564665724186492e-05, + "loss": 0.0199, + "step": 30210 + }, + { + "epoch": 9.33, + "learning_rate": 1.1564171763833774e-05, + "loss": 0.0206, + "step": 30211 + }, + { + "epoch": 9.33, + "learning_rate": 1.1563677799568778e-05, + "loss": 0.0229, + "step": 30212 + }, + { + "epoch": 9.33, + "learning_rate": 1.156318383139274e-05, + "loss": 0.024, + "step": 30213 + }, + { + "epoch": 9.33, + "learning_rate": 1.1562689859306889e-05, + "loss": 0.0191, + "step": 30214 + }, + { + "epoch": 9.33, + "learning_rate": 1.156219588331247e-05, + "loss": 0.0196, + "step": 30215 + }, + { + "epoch": 9.33, + "learning_rate": 1.1561701903410714e-05, + "loss": 0.0212, + "step": 30216 + }, + { + "epoch": 9.33, + "learning_rate": 1.1561207919602855e-05, + "loss": 0.021, + "step": 30217 + }, + { + "epoch": 9.33, + "learning_rate": 1.156071393189013e-05, + "loss": 0.0207, + "step": 30218 + }, + { + "epoch": 9.33, + "learning_rate": 1.1560219940273774e-05, + "loss": 0.0204, + "step": 30219 + }, + { + "epoch": 9.33, + "learning_rate": 1.1559725944755027e-05, + "loss": 0.0208, + "step": 30220 + }, + { + "epoch": 9.33, + "learning_rate": 1.1559231945335118e-05, + "loss": 0.0191, + "step": 30221 + }, + { + "epoch": 9.33, + "learning_rate": 1.1558737942015286e-05, + "loss": 0.0201, + "step": 30222 + }, + { + "epoch": 9.33, + "learning_rate": 1.1558243934796767e-05, + "loss": 0.0182, + "step": 30223 + }, + { + "epoch": 9.33, + "learning_rate": 1.1557749923680795e-05, + "loss": 0.0233, + "step": 30224 + }, + { + "epoch": 9.33, + "learning_rate": 1.1557255908668608e-05, + "loss": 0.0198, + "step": 30225 + }, + { + "epoch": 9.33, + "learning_rate": 1.1556761889761437e-05, + "loss": 0.0191, + "step": 30226 + }, + { + "epoch": 9.33, + "learning_rate": 1.1556267866960522e-05, + "loss": 0.0198, + "step": 30227 + }, + { + "epoch": 9.34, + "learning_rate": 1.1555773840267097e-05, + "loss": 0.021, + "step": 30228 + }, + { + "epoch": 9.34, + "learning_rate": 1.1555279809682398e-05, + "loss": 0.0211, + "step": 30229 + }, + { + "epoch": 9.34, + "learning_rate": 1.1554785775207664e-05, + "loss": 0.0225, + "step": 30230 + }, + { + "epoch": 9.34, + "learning_rate": 1.1554291736844121e-05, + "loss": 0.0202, + "step": 30231 + }, + { + "epoch": 9.34, + "learning_rate": 1.1553797694593013e-05, + "loss": 0.0195, + "step": 30232 + }, + { + "epoch": 9.34, + "learning_rate": 1.1553303648455578e-05, + "loss": 0.0225, + "step": 30233 + }, + { + "epoch": 9.34, + "learning_rate": 1.1552809598433041e-05, + "loss": 0.0222, + "step": 30234 + }, + { + "epoch": 9.34, + "learning_rate": 1.1552315544526649e-05, + "loss": 0.022, + "step": 30235 + }, + { + "epoch": 9.34, + "learning_rate": 1.1551821486737626e-05, + "loss": 0.0188, + "step": 30236 + }, + { + "epoch": 9.34, + "learning_rate": 1.1551327425067221e-05, + "loss": 0.018, + "step": 30237 + }, + { + "epoch": 9.34, + "learning_rate": 1.1550833359516663e-05, + "loss": 0.0205, + "step": 30238 + }, + { + "epoch": 9.34, + "learning_rate": 1.1550339290087182e-05, + "loss": 0.0219, + "step": 30239 + }, + { + "epoch": 9.34, + "learning_rate": 1.1549845216780026e-05, + "loss": 0.0207, + "step": 30240 + }, + { + "epoch": 9.34, + "learning_rate": 1.1549351139596423e-05, + "loss": 0.0187, + "step": 30241 + }, + { + "epoch": 9.34, + "learning_rate": 1.1548857058537606e-05, + "loss": 0.0241, + "step": 30242 + }, + { + "epoch": 9.34, + "learning_rate": 1.154836297360482e-05, + "loss": 0.0218, + "step": 30243 + }, + { + "epoch": 9.34, + "learning_rate": 1.1547868884799294e-05, + "loss": 0.02, + "step": 30244 + }, + { + "epoch": 9.34, + "learning_rate": 1.1547374792122266e-05, + "loss": 0.0224, + "step": 30245 + }, + { + "epoch": 9.34, + "learning_rate": 1.154688069557497e-05, + "loss": 0.0192, + "step": 30246 + }, + { + "epoch": 9.34, + "learning_rate": 1.1546386595158646e-05, + "loss": 0.0196, + "step": 30247 + }, + { + "epoch": 9.34, + "learning_rate": 1.1545892490874525e-05, + "loss": 0.02, + "step": 30248 + }, + { + "epoch": 9.34, + "learning_rate": 1.1545398382723845e-05, + "loss": 0.0188, + "step": 30249 + }, + { + "epoch": 9.34, + "learning_rate": 1.1544904270707842e-05, + "loss": 0.0225, + "step": 30250 + }, + { + "epoch": 9.34, + "learning_rate": 1.1544410154827751e-05, + "loss": 0.0206, + "step": 30251 + }, + { + "epoch": 9.34, + "learning_rate": 1.154391603508481e-05, + "loss": 0.0203, + "step": 30252 + }, + { + "epoch": 9.34, + "learning_rate": 1.1543421911480253e-05, + "loss": 0.0229, + "step": 30253 + }, + { + "epoch": 9.34, + "learning_rate": 1.1542927784015314e-05, + "loss": 0.0202, + "step": 30254 + }, + { + "epoch": 9.34, + "learning_rate": 1.1542433652691234e-05, + "loss": 0.0187, + "step": 30255 + }, + { + "epoch": 9.34, + "learning_rate": 1.1541939517509243e-05, + "loss": 0.0187, + "step": 30256 + }, + { + "epoch": 9.34, + "learning_rate": 1.1541445378470583e-05, + "loss": 0.0215, + "step": 30257 + }, + { + "epoch": 9.34, + "learning_rate": 1.1540951235576488e-05, + "loss": 0.0203, + "step": 30258 + }, + { + "epoch": 9.34, + "learning_rate": 1.1540457088828189e-05, + "loss": 0.0224, + "step": 30259 + }, + { + "epoch": 9.34, + "learning_rate": 1.1539962938226929e-05, + "loss": 0.0231, + "step": 30260 + }, + { + "epoch": 9.35, + "learning_rate": 1.1539468783773941e-05, + "loss": 0.021, + "step": 30261 + }, + { + "epoch": 9.35, + "learning_rate": 1.1538974625470458e-05, + "loss": 0.0218, + "step": 30262 + }, + { + "epoch": 9.35, + "learning_rate": 1.153848046331772e-05, + "loss": 0.0237, + "step": 30263 + }, + { + "epoch": 9.35, + "learning_rate": 1.1537986297316966e-05, + "loss": 0.0218, + "step": 30264 + }, + { + "epoch": 9.35, + "learning_rate": 1.1537492127469421e-05, + "loss": 0.0214, + "step": 30265 + }, + { + "epoch": 9.35, + "learning_rate": 1.1536997953776332e-05, + "loss": 0.0223, + "step": 30266 + }, + { + "epoch": 9.35, + "learning_rate": 1.153650377623893e-05, + "loss": 0.0217, + "step": 30267 + }, + { + "epoch": 9.35, + "learning_rate": 1.1536009594858448e-05, + "loss": 0.0199, + "step": 30268 + }, + { + "epoch": 9.35, + "learning_rate": 1.153551540963613e-05, + "loss": 0.0199, + "step": 30269 + }, + { + "epoch": 9.35, + "learning_rate": 1.1535021220573207e-05, + "loss": 0.021, + "step": 30270 + }, + { + "epoch": 9.35, + "learning_rate": 1.1534527027670918e-05, + "loss": 0.0198, + "step": 30271 + }, + { + "epoch": 9.35, + "learning_rate": 1.1534032830930494e-05, + "loss": 0.0183, + "step": 30272 + }, + { + "epoch": 9.35, + "learning_rate": 1.1533538630353174e-05, + "loss": 0.0197, + "step": 30273 + }, + { + "epoch": 9.35, + "learning_rate": 1.1533044425940196e-05, + "loss": 0.0224, + "step": 30274 + }, + { + "epoch": 9.35, + "learning_rate": 1.1532550217692796e-05, + "loss": 0.0195, + "step": 30275 + }, + { + "epoch": 9.35, + "learning_rate": 1.1532056005612204e-05, + "loss": 0.0234, + "step": 30276 + }, + { + "epoch": 9.35, + "learning_rate": 1.1531561789699664e-05, + "loss": 0.0196, + "step": 30277 + }, + { + "epoch": 9.35, + "learning_rate": 1.1531067569956407e-05, + "loss": 0.022, + "step": 30278 + }, + { + "epoch": 9.35, + "learning_rate": 1.1530573346383669e-05, + "loss": 0.0207, + "step": 30279 + }, + { + "epoch": 9.35, + "learning_rate": 1.1530079118982692e-05, + "loss": 0.0204, + "step": 30280 + }, + { + "epoch": 9.35, + "learning_rate": 1.1529584887754703e-05, + "loss": 0.0205, + "step": 30281 + }, + { + "epoch": 9.35, + "learning_rate": 1.1529090652700947e-05, + "loss": 0.0194, + "step": 30282 + }, + { + "epoch": 9.35, + "learning_rate": 1.1528596413822655e-05, + "loss": 0.0222, + "step": 30283 + }, + { + "epoch": 9.35, + "learning_rate": 1.1528102171121067e-05, + "loss": 0.0186, + "step": 30284 + }, + { + "epoch": 9.35, + "learning_rate": 1.1527607924597413e-05, + "loss": 0.023, + "step": 30285 + }, + { + "epoch": 9.35, + "learning_rate": 1.1527113674252935e-05, + "loss": 0.0219, + "step": 30286 + }, + { + "epoch": 9.35, + "learning_rate": 1.1526619420088868e-05, + "loss": 0.021, + "step": 30287 + }, + { + "epoch": 9.35, + "learning_rate": 1.1526125162106446e-05, + "loss": 0.0201, + "step": 30288 + }, + { + "epoch": 9.35, + "learning_rate": 1.1525630900306907e-05, + "loss": 0.0199, + "step": 30289 + }, + { + "epoch": 9.35, + "learning_rate": 1.1525136634691485e-05, + "loss": 0.0234, + "step": 30290 + }, + { + "epoch": 9.35, + "learning_rate": 1.152464236526142e-05, + "loss": 0.0186, + "step": 30291 + }, + { + "epoch": 9.35, + "learning_rate": 1.1524148092017948e-05, + "loss": 0.0231, + "step": 30292 + }, + { + "epoch": 9.36, + "learning_rate": 1.1523653814962299e-05, + "loss": 0.0197, + "step": 30293 + }, + { + "epoch": 9.36, + "learning_rate": 1.1523159534095718e-05, + "loss": 0.0208, + "step": 30294 + }, + { + "epoch": 9.36, + "learning_rate": 1.1522665249419437e-05, + "loss": 0.0196, + "step": 30295 + }, + { + "epoch": 9.36, + "learning_rate": 1.1522170960934688e-05, + "loss": 0.0207, + "step": 30296 + }, + { + "epoch": 9.36, + "learning_rate": 1.1521676668642719e-05, + "loss": 0.0237, + "step": 30297 + }, + { + "epoch": 9.36, + "learning_rate": 1.1521182372544755e-05, + "loss": 0.0195, + "step": 30298 + }, + { + "epoch": 9.36, + "learning_rate": 1.1520688072642037e-05, + "loss": 0.0207, + "step": 30299 + }, + { + "epoch": 9.36, + "learning_rate": 1.1520193768935799e-05, + "loss": 0.022, + "step": 30300 + }, + { + "epoch": 9.36, + "learning_rate": 1.1519699461427278e-05, + "loss": 0.0201, + "step": 30301 + }, + { + "epoch": 9.36, + "learning_rate": 1.1519205150117718e-05, + "loss": 0.0186, + "step": 30302 + }, + { + "epoch": 9.36, + "learning_rate": 1.1518710835008345e-05, + "loss": 0.0209, + "step": 30303 + }, + { + "epoch": 9.36, + "learning_rate": 1.1518216516100398e-05, + "loss": 0.0195, + "step": 30304 + }, + { + "epoch": 9.36, + "learning_rate": 1.1517722193395115e-05, + "loss": 0.0224, + "step": 30305 + }, + { + "epoch": 9.36, + "learning_rate": 1.1517227866893735e-05, + "loss": 0.0236, + "step": 30306 + }, + { + "epoch": 9.36, + "learning_rate": 1.151673353659749e-05, + "loss": 0.0212, + "step": 30307 + }, + { + "epoch": 9.36, + "learning_rate": 1.1516239202507615e-05, + "loss": 0.0214, + "step": 30308 + }, + { + "epoch": 9.36, + "learning_rate": 1.1515744864625352e-05, + "loss": 0.0257, + "step": 30309 + }, + { + "epoch": 9.36, + "learning_rate": 1.1515250522951932e-05, + "loss": 0.0202, + "step": 30310 + }, + { + "epoch": 9.36, + "learning_rate": 1.1514756177488597e-05, + "loss": 0.0195, + "step": 30311 + }, + { + "epoch": 9.36, + "learning_rate": 1.1514261828236579e-05, + "loss": 0.0253, + "step": 30312 + }, + { + "epoch": 9.36, + "learning_rate": 1.1513767475197114e-05, + "loss": 0.0217, + "step": 30313 + }, + { + "epoch": 9.36, + "learning_rate": 1.1513273118371445e-05, + "loss": 0.02, + "step": 30314 + }, + { + "epoch": 9.36, + "learning_rate": 1.1512778757760803e-05, + "loss": 0.0223, + "step": 30315 + }, + { + "epoch": 9.36, + "learning_rate": 1.1512284393366422e-05, + "loss": 0.0197, + "step": 30316 + }, + { + "epoch": 9.36, + "learning_rate": 1.1511790025189545e-05, + "loss": 0.0211, + "step": 30317 + }, + { + "epoch": 9.36, + "learning_rate": 1.1511295653231405e-05, + "loss": 0.0209, + "step": 30318 + }, + { + "epoch": 9.36, + "learning_rate": 1.1510801277493238e-05, + "loss": 0.0233, + "step": 30319 + }, + { + "epoch": 9.36, + "learning_rate": 1.1510306897976284e-05, + "loss": 0.0222, + "step": 30320 + }, + { + "epoch": 9.36, + "learning_rate": 1.1509812514681773e-05, + "loss": 0.0215, + "step": 30321 + }, + { + "epoch": 9.36, + "learning_rate": 1.1509318127610947e-05, + "loss": 0.0212, + "step": 30322 + }, + { + "epoch": 9.36, + "learning_rate": 1.1508823736765043e-05, + "loss": 0.0184, + "step": 30323 + }, + { + "epoch": 9.36, + "learning_rate": 1.1508329342145292e-05, + "loss": 0.0194, + "step": 30324 + }, + { + "epoch": 9.36, + "learning_rate": 1.1507834943752937e-05, + "loss": 0.0217, + "step": 30325 + }, + { + "epoch": 9.37, + "learning_rate": 1.1507340541589211e-05, + "loss": 0.0232, + "step": 30326 + }, + { + "epoch": 9.37, + "learning_rate": 1.150684613565535e-05, + "loss": 0.0211, + "step": 30327 + }, + { + "epoch": 9.37, + "learning_rate": 1.1506351725952596e-05, + "loss": 0.0178, + "step": 30328 + }, + { + "epoch": 9.37, + "learning_rate": 1.1505857312482179e-05, + "loss": 0.0207, + "step": 30329 + }, + { + "epoch": 9.37, + "learning_rate": 1.1505362895245339e-05, + "loss": 0.0205, + "step": 30330 + }, + { + "epoch": 9.37, + "learning_rate": 1.1504868474243311e-05, + "loss": 0.0204, + "step": 30331 + }, + { + "epoch": 9.37, + "learning_rate": 1.150437404947733e-05, + "loss": 0.0217, + "step": 30332 + }, + { + "epoch": 9.37, + "learning_rate": 1.150387962094864e-05, + "loss": 0.0213, + "step": 30333 + }, + { + "epoch": 9.37, + "learning_rate": 1.1503385188658469e-05, + "loss": 0.0231, + "step": 30334 + }, + { + "epoch": 9.37, + "learning_rate": 1.150289075260806e-05, + "loss": 0.0252, + "step": 30335 + }, + { + "epoch": 9.37, + "learning_rate": 1.1502396312798645e-05, + "loss": 0.0229, + "step": 30336 + }, + { + "epoch": 9.37, + "learning_rate": 1.1501901869231465e-05, + "loss": 0.0196, + "step": 30337 + }, + { + "epoch": 9.37, + "learning_rate": 1.1501407421907754e-05, + "loss": 0.0209, + "step": 30338 + }, + { + "epoch": 9.37, + "learning_rate": 1.1500912970828745e-05, + "loss": 0.0216, + "step": 30339 + }, + { + "epoch": 9.37, + "learning_rate": 1.1500418515995683e-05, + "loss": 0.0198, + "step": 30340 + }, + { + "epoch": 9.37, + "learning_rate": 1.1499924057409801e-05, + "loss": 0.0198, + "step": 30341 + }, + { + "epoch": 9.37, + "learning_rate": 1.1499429595072336e-05, + "loss": 0.0194, + "step": 30342 + }, + { + "epoch": 9.37, + "learning_rate": 1.1498935128984524e-05, + "loss": 0.0218, + "step": 30343 + }, + { + "epoch": 9.37, + "learning_rate": 1.1498440659147598e-05, + "loss": 0.021, + "step": 30344 + }, + { + "epoch": 9.37, + "learning_rate": 1.14979461855628e-05, + "loss": 0.0211, + "step": 30345 + }, + { + "epoch": 9.37, + "learning_rate": 1.1497451708231368e-05, + "loss": 0.0232, + "step": 30346 + }, + { + "epoch": 9.37, + "learning_rate": 1.1496957227154532e-05, + "loss": 0.0213, + "step": 30347 + }, + { + "epoch": 9.37, + "learning_rate": 1.149646274233354e-05, + "loss": 0.0214, + "step": 30348 + }, + { + "epoch": 9.37, + "learning_rate": 1.1495968253769616e-05, + "loss": 0.0216, + "step": 30349 + }, + { + "epoch": 9.37, + "learning_rate": 1.1495473761464002e-05, + "loss": 0.0212, + "step": 30350 + }, + { + "epoch": 9.37, + "learning_rate": 1.1494979265417938e-05, + "loss": 0.0232, + "step": 30351 + }, + { + "epoch": 9.37, + "learning_rate": 1.1494484765632657e-05, + "loss": 0.0196, + "step": 30352 + }, + { + "epoch": 9.37, + "learning_rate": 1.1493990262109399e-05, + "loss": 0.02, + "step": 30353 + }, + { + "epoch": 9.37, + "learning_rate": 1.1493495754849397e-05, + "loss": 0.0213, + "step": 30354 + }, + { + "epoch": 9.37, + "learning_rate": 1.1493001243853887e-05, + "loss": 0.0231, + "step": 30355 + }, + { + "epoch": 9.37, + "learning_rate": 1.1492506729124115e-05, + "loss": 0.0202, + "step": 30356 + }, + { + "epoch": 9.37, + "learning_rate": 1.1492012210661308e-05, + "loss": 0.0218, + "step": 30357 + }, + { + "epoch": 9.38, + "learning_rate": 1.1491517688466702e-05, + "loss": 0.0208, + "step": 30358 + }, + { + "epoch": 9.38, + "learning_rate": 1.1491023162541545e-05, + "loss": 0.0208, + "step": 30359 + }, + { + "epoch": 9.38, + "learning_rate": 1.1490528632887066e-05, + "loss": 0.0227, + "step": 30360 + }, + { + "epoch": 9.38, + "learning_rate": 1.14900340995045e-05, + "loss": 0.0227, + "step": 30361 + }, + { + "epoch": 9.38, + "learning_rate": 1.1489539562395088e-05, + "loss": 0.0206, + "step": 30362 + }, + { + "epoch": 9.38, + "learning_rate": 1.1489045021560068e-05, + "loss": 0.0196, + "step": 30363 + }, + { + "epoch": 9.38, + "learning_rate": 1.1488550477000674e-05, + "loss": 0.0221, + "step": 30364 + }, + { + "epoch": 9.38, + "learning_rate": 1.1488055928718143e-05, + "loss": 0.0181, + "step": 30365 + }, + { + "epoch": 9.38, + "learning_rate": 1.1487561376713712e-05, + "loss": 0.0233, + "step": 30366 + }, + { + "epoch": 9.38, + "learning_rate": 1.148706682098862e-05, + "loss": 0.0222, + "step": 30367 + }, + { + "epoch": 9.38, + "learning_rate": 1.1486572261544102e-05, + "loss": 0.0202, + "step": 30368 + }, + { + "epoch": 9.38, + "learning_rate": 1.1486077698381395e-05, + "loss": 0.0203, + "step": 30369 + }, + { + "epoch": 9.38, + "learning_rate": 1.1485583131501739e-05, + "loss": 0.0224, + "step": 30370 + }, + { + "epoch": 9.38, + "learning_rate": 1.1485088560906366e-05, + "loss": 0.0217, + "step": 30371 + }, + { + "epoch": 9.38, + "learning_rate": 1.1484593986596517e-05, + "loss": 0.0232, + "step": 30372 + }, + { + "epoch": 9.38, + "learning_rate": 1.1484099408573428e-05, + "loss": 0.025, + "step": 30373 + }, + { + "epoch": 9.38, + "learning_rate": 1.1483604826838337e-05, + "loss": 0.0196, + "step": 30374 + }, + { + "epoch": 9.38, + "learning_rate": 1.1483110241392475e-05, + "loss": 0.0194, + "step": 30375 + }, + { + "epoch": 9.38, + "learning_rate": 1.1482615652237086e-05, + "loss": 0.0198, + "step": 30376 + }, + { + "epoch": 9.38, + "learning_rate": 1.1482121059373409e-05, + "loss": 0.0194, + "step": 30377 + }, + { + "epoch": 9.38, + "learning_rate": 1.1481626462802671e-05, + "loss": 0.0192, + "step": 30378 + }, + { + "epoch": 9.38, + "learning_rate": 1.1481131862526117e-05, + "loss": 0.022, + "step": 30379 + }, + { + "epoch": 9.38, + "learning_rate": 1.1480637258544984e-05, + "loss": 0.0193, + "step": 30380 + }, + { + "epoch": 9.38, + "learning_rate": 1.1480142650860503e-05, + "loss": 0.0226, + "step": 30381 + }, + { + "epoch": 9.38, + "learning_rate": 1.1479648039473921e-05, + "loss": 0.0204, + "step": 30382 + }, + { + "epoch": 9.38, + "learning_rate": 1.1479153424386464e-05, + "loss": 0.0237, + "step": 30383 + }, + { + "epoch": 9.38, + "learning_rate": 1.147865880559938e-05, + "loss": 0.02, + "step": 30384 + }, + { + "epoch": 9.38, + "learning_rate": 1.1478164183113896e-05, + "loss": 0.021, + "step": 30385 + }, + { + "epoch": 9.38, + "learning_rate": 1.1477669556931253e-05, + "loss": 0.019, + "step": 30386 + }, + { + "epoch": 9.38, + "learning_rate": 1.1477174927052692e-05, + "loss": 0.0193, + "step": 30387 + }, + { + "epoch": 9.38, + "learning_rate": 1.1476680293479447e-05, + "loss": 0.019, + "step": 30388 + }, + { + "epoch": 9.38, + "learning_rate": 1.1476185656212754e-05, + "loss": 0.0217, + "step": 30389 + }, + { + "epoch": 9.39, + "learning_rate": 1.1475691015253852e-05, + "loss": 0.0248, + "step": 30390 + }, + { + "epoch": 9.39, + "learning_rate": 1.1475196370603978e-05, + "loss": 0.0201, + "step": 30391 + }, + { + "epoch": 9.39, + "learning_rate": 1.1474701722264367e-05, + "loss": 0.0228, + "step": 30392 + }, + { + "epoch": 9.39, + "learning_rate": 1.147420707023626e-05, + "loss": 0.0202, + "step": 30393 + }, + { + "epoch": 9.39, + "learning_rate": 1.1473712414520892e-05, + "loss": 0.0208, + "step": 30394 + }, + { + "epoch": 9.39, + "learning_rate": 1.1473217755119498e-05, + "loss": 0.0201, + "step": 30395 + }, + { + "epoch": 9.39, + "learning_rate": 1.147272309203332e-05, + "loss": 0.0211, + "step": 30396 + }, + { + "epoch": 9.39, + "learning_rate": 1.1472228425263594e-05, + "loss": 0.0201, + "step": 30397 + }, + { + "epoch": 9.39, + "learning_rate": 1.1471733754811553e-05, + "loss": 0.0223, + "step": 30398 + }, + { + "epoch": 9.39, + "learning_rate": 1.147123908067844e-05, + "loss": 0.0196, + "step": 30399 + }, + { + "epoch": 9.39, + "learning_rate": 1.147074440286549e-05, + "loss": 0.0205, + "step": 30400 + }, + { + "epoch": 9.39, + "learning_rate": 1.1470249721373939e-05, + "loss": 0.0202, + "step": 30401 + }, + { + "epoch": 9.39, + "learning_rate": 1.1469755036205026e-05, + "loss": 0.0222, + "step": 30402 + }, + { + "epoch": 9.39, + "learning_rate": 1.1469260347359985e-05, + "loss": 0.0174, + "step": 30403 + }, + { + "epoch": 9.39, + "learning_rate": 1.1468765654840059e-05, + "loss": 0.0184, + "step": 30404 + }, + { + "epoch": 9.39, + "learning_rate": 1.1468270958646483e-05, + "loss": 0.0203, + "step": 30405 + }, + { + "epoch": 9.39, + "learning_rate": 1.146777625878049e-05, + "loss": 0.0221, + "step": 30406 + }, + { + "epoch": 9.39, + "learning_rate": 1.1467281555243322e-05, + "loss": 0.0207, + "step": 30407 + }, + { + "epoch": 9.39, + "learning_rate": 1.1466786848036217e-05, + "loss": 0.0211, + "step": 30408 + }, + { + "epoch": 9.39, + "learning_rate": 1.1466292137160406e-05, + "loss": 0.0229, + "step": 30409 + }, + { + "epoch": 9.39, + "learning_rate": 1.1465797422617138e-05, + "loss": 0.0234, + "step": 30410 + }, + { + "epoch": 9.39, + "learning_rate": 1.146530270440764e-05, + "loss": 0.0219, + "step": 30411 + }, + { + "epoch": 9.39, + "learning_rate": 1.1464807982533148e-05, + "loss": 0.0261, + "step": 30412 + }, + { + "epoch": 9.39, + "learning_rate": 1.146431325699491e-05, + "loss": 0.0204, + "step": 30413 + }, + { + "epoch": 9.39, + "learning_rate": 1.1463818527794157e-05, + "loss": 0.0213, + "step": 30414 + }, + { + "epoch": 9.39, + "learning_rate": 1.1463323794932124e-05, + "loss": 0.0217, + "step": 30415 + }, + { + "epoch": 9.39, + "learning_rate": 1.1462829058410054e-05, + "loss": 0.0245, + "step": 30416 + }, + { + "epoch": 9.39, + "learning_rate": 1.1462334318229177e-05, + "loss": 0.0205, + "step": 30417 + }, + { + "epoch": 9.39, + "learning_rate": 1.146183957439074e-05, + "loss": 0.0215, + "step": 30418 + }, + { + "epoch": 9.39, + "learning_rate": 1.1461344826895978e-05, + "loss": 0.0205, + "step": 30419 + }, + { + "epoch": 9.39, + "learning_rate": 1.146085007574612e-05, + "loss": 0.019, + "step": 30420 + }, + { + "epoch": 9.39, + "learning_rate": 1.1460355320942412e-05, + "loss": 0.0223, + "step": 30421 + }, + { + "epoch": 9.39, + "learning_rate": 1.1459860562486089e-05, + "loss": 0.0201, + "step": 30422 + }, + { + "epoch": 9.4, + "learning_rate": 1.1459365800378388e-05, + "loss": 0.0187, + "step": 30423 + }, + { + "epoch": 9.4, + "learning_rate": 1.1458871034620546e-05, + "loss": 0.0211, + "step": 30424 + }, + { + "epoch": 9.4, + "learning_rate": 1.1458376265213805e-05, + "loss": 0.0205, + "step": 30425 + }, + { + "epoch": 9.4, + "learning_rate": 1.1457881492159396e-05, + "loss": 0.0228, + "step": 30426 + }, + { + "epoch": 9.4, + "learning_rate": 1.145738671545856e-05, + "loss": 0.0201, + "step": 30427 + }, + { + "epoch": 9.4, + "learning_rate": 1.1456891935112538e-05, + "loss": 0.0236, + "step": 30428 + }, + { + "epoch": 9.4, + "learning_rate": 1.1456397151122556e-05, + "loss": 0.0188, + "step": 30429 + }, + { + "epoch": 9.4, + "learning_rate": 1.1455902363489863e-05, + "loss": 0.0234, + "step": 30430 + }, + { + "epoch": 9.4, + "learning_rate": 1.1455407572215696e-05, + "loss": 0.0242, + "step": 30431 + }, + { + "epoch": 9.4, + "learning_rate": 1.145491277730128e-05, + "loss": 0.0256, + "step": 30432 + }, + { + "epoch": 9.4, + "learning_rate": 1.1454417978747871e-05, + "loss": 0.0198, + "step": 30433 + }, + { + "epoch": 9.4, + "learning_rate": 1.1453923176556691e-05, + "loss": 0.0199, + "step": 30434 + }, + { + "epoch": 9.4, + "learning_rate": 1.1453428370728987e-05, + "loss": 0.0214, + "step": 30435 + }, + { + "epoch": 9.4, + "learning_rate": 1.1452933561265995e-05, + "loss": 0.0215, + "step": 30436 + }, + { + "epoch": 9.4, + "learning_rate": 1.1452438748168949e-05, + "loss": 0.0209, + "step": 30437 + }, + { + "epoch": 9.4, + "learning_rate": 1.1451943931439092e-05, + "loss": 0.0205, + "step": 30438 + }, + { + "epoch": 9.4, + "learning_rate": 1.1451449111077655e-05, + "loss": 0.0206, + "step": 30439 + }, + { + "epoch": 9.4, + "learning_rate": 1.1450954287085878e-05, + "loss": 0.0217, + "step": 30440 + }, + { + "epoch": 9.4, + "learning_rate": 1.1450459459465004e-05, + "loss": 0.0231, + "step": 30441 + }, + { + "epoch": 9.4, + "learning_rate": 1.1449964628216263e-05, + "loss": 0.0215, + "step": 30442 + }, + { + "epoch": 9.4, + "learning_rate": 1.1449469793340897e-05, + "loss": 0.0201, + "step": 30443 + }, + { + "epoch": 9.4, + "learning_rate": 1.1448974954840142e-05, + "loss": 0.0209, + "step": 30444 + }, + { + "epoch": 9.4, + "learning_rate": 1.1448480112715236e-05, + "loss": 0.0229, + "step": 30445 + }, + { + "epoch": 9.4, + "learning_rate": 1.144798526696742e-05, + "loss": 0.0238, + "step": 30446 + }, + { + "epoch": 9.4, + "learning_rate": 1.1447490417597927e-05, + "loss": 0.023, + "step": 30447 + }, + { + "epoch": 9.4, + "learning_rate": 1.1446995564607994e-05, + "loss": 0.0215, + "step": 30448 + }, + { + "epoch": 9.4, + "learning_rate": 1.1446500707998865e-05, + "loss": 0.0209, + "step": 30449 + }, + { + "epoch": 9.4, + "learning_rate": 1.144600584777177e-05, + "loss": 0.0225, + "step": 30450 + }, + { + "epoch": 9.4, + "learning_rate": 1.1445510983927954e-05, + "loss": 0.0253, + "step": 30451 + }, + { + "epoch": 9.4, + "learning_rate": 1.144501611646865e-05, + "loss": 0.0229, + "step": 30452 + }, + { + "epoch": 9.4, + "learning_rate": 1.1444521245395097e-05, + "loss": 0.0208, + "step": 30453 + }, + { + "epoch": 9.4, + "learning_rate": 1.1444026370708534e-05, + "loss": 0.0213, + "step": 30454 + }, + { + "epoch": 9.41, + "learning_rate": 1.1443531492410196e-05, + "loss": 0.024, + "step": 30455 + }, + { + "epoch": 9.41, + "learning_rate": 1.1443036610501323e-05, + "loss": 0.0227, + "step": 30456 + }, + { + "epoch": 9.41, + "learning_rate": 1.1442541724983153e-05, + "loss": 0.0218, + "step": 30457 + }, + { + "epoch": 9.41, + "learning_rate": 1.1442046835856924e-05, + "loss": 0.0219, + "step": 30458 + }, + { + "epoch": 9.41, + "learning_rate": 1.1441551943123871e-05, + "loss": 0.0217, + "step": 30459 + }, + { + "epoch": 9.41, + "learning_rate": 1.1441057046785233e-05, + "loss": 0.0208, + "step": 30460 + }, + { + "epoch": 9.41, + "learning_rate": 1.1440562146842251e-05, + "loss": 0.0209, + "step": 30461 + }, + { + "epoch": 9.41, + "learning_rate": 1.144006724329616e-05, + "loss": 0.0201, + "step": 30462 + }, + { + "epoch": 9.41, + "learning_rate": 1.1439572336148194e-05, + "loss": 0.0235, + "step": 30463 + }, + { + "epoch": 9.41, + "learning_rate": 1.1439077425399603e-05, + "loss": 0.0214, + "step": 30464 + }, + { + "epoch": 9.41, + "learning_rate": 1.143858251105161e-05, + "loss": 0.02, + "step": 30465 + }, + { + "epoch": 9.41, + "learning_rate": 1.143808759310546e-05, + "loss": 0.0236, + "step": 30466 + }, + { + "epoch": 9.41, + "learning_rate": 1.1437592671562397e-05, + "loss": 0.0233, + "step": 30467 + }, + { + "epoch": 9.41, + "learning_rate": 1.1437097746423644e-05, + "loss": 0.0207, + "step": 30468 + }, + { + "epoch": 9.41, + "learning_rate": 1.1436602817690454e-05, + "loss": 0.0209, + "step": 30469 + }, + { + "epoch": 9.41, + "learning_rate": 1.1436107885364056e-05, + "loss": 0.0236, + "step": 30470 + }, + { + "epoch": 9.41, + "learning_rate": 1.1435612949445687e-05, + "loss": 0.0224, + "step": 30471 + }, + { + "epoch": 9.41, + "learning_rate": 1.1435118009936594e-05, + "loss": 0.0207, + "step": 30472 + }, + { + "epoch": 9.41, + "learning_rate": 1.1434623066838006e-05, + "loss": 0.0208, + "step": 30473 + }, + { + "epoch": 9.41, + "learning_rate": 1.1434128120151164e-05, + "loss": 0.0232, + "step": 30474 + }, + { + "epoch": 9.41, + "learning_rate": 1.1433633169877308e-05, + "loss": 0.0211, + "step": 30475 + }, + { + "epoch": 9.41, + "learning_rate": 1.1433138216017672e-05, + "loss": 0.022, + "step": 30476 + }, + { + "epoch": 9.41, + "learning_rate": 1.1432643258573494e-05, + "loss": 0.0211, + "step": 30477 + }, + { + "epoch": 9.41, + "learning_rate": 1.1432148297546018e-05, + "loss": 0.021, + "step": 30478 + }, + { + "epoch": 9.41, + "learning_rate": 1.1431653332936477e-05, + "loss": 0.0195, + "step": 30479 + }, + { + "epoch": 9.41, + "learning_rate": 1.1431158364746109e-05, + "loss": 0.0237, + "step": 30480 + }, + { + "epoch": 9.41, + "learning_rate": 1.1430663392976151e-05, + "loss": 0.0188, + "step": 30481 + }, + { + "epoch": 9.41, + "learning_rate": 1.1430168417627845e-05, + "loss": 0.0219, + "step": 30482 + }, + { + "epoch": 9.41, + "learning_rate": 1.1429673438702427e-05, + "loss": 0.023, + "step": 30483 + }, + { + "epoch": 9.41, + "learning_rate": 1.1429178456201136e-05, + "loss": 0.0226, + "step": 30484 + }, + { + "epoch": 9.41, + "learning_rate": 1.1428683470125207e-05, + "loss": 0.0215, + "step": 30485 + }, + { + "epoch": 9.41, + "learning_rate": 1.1428188480475879e-05, + "loss": 0.0204, + "step": 30486 + }, + { + "epoch": 9.42, + "learning_rate": 1.1427693487254397e-05, + "loss": 0.0201, + "step": 30487 + }, + { + "epoch": 9.42, + "learning_rate": 1.1427198490461986e-05, + "loss": 0.0213, + "step": 30488 + }, + { + "epoch": 9.42, + "learning_rate": 1.1426703490099896e-05, + "loss": 0.0227, + "step": 30489 + }, + { + "epoch": 9.42, + "learning_rate": 1.1426208486169359e-05, + "loss": 0.0223, + "step": 30490 + }, + { + "epoch": 9.42, + "learning_rate": 1.1425713478671612e-05, + "loss": 0.022, + "step": 30491 + }, + { + "epoch": 9.42, + "learning_rate": 1.1425218467607899e-05, + "loss": 0.0223, + "step": 30492 + }, + { + "epoch": 9.42, + "learning_rate": 1.1424723452979453e-05, + "loss": 0.02, + "step": 30493 + }, + { + "epoch": 9.42, + "learning_rate": 1.1424228434787514e-05, + "loss": 0.0225, + "step": 30494 + }, + { + "epoch": 9.42, + "learning_rate": 1.1423733413033322e-05, + "loss": 0.0254, + "step": 30495 + }, + { + "epoch": 9.42, + "learning_rate": 1.1423238387718112e-05, + "loss": 0.0234, + "step": 30496 + }, + { + "epoch": 9.42, + "learning_rate": 1.1422743358843122e-05, + "loss": 0.0214, + "step": 30497 + }, + { + "epoch": 9.42, + "learning_rate": 1.1422248326409591e-05, + "loss": 0.0208, + "step": 30498 + }, + { + "epoch": 9.42, + "learning_rate": 1.1421753290418756e-05, + "loss": 0.0194, + "step": 30499 + }, + { + "epoch": 9.42, + "learning_rate": 1.142125825087186e-05, + "loss": 0.0186, + "step": 30500 + }, + { + "epoch": 9.42, + "learning_rate": 1.1420763207770138e-05, + "loss": 0.021, + "step": 30501 + }, + { + "epoch": 9.42, + "learning_rate": 1.1420268161114827e-05, + "loss": 0.0214, + "step": 30502 + }, + { + "epoch": 9.42, + "learning_rate": 1.1419773110907167e-05, + "loss": 0.0201, + "step": 30503 + }, + { + "epoch": 9.42, + "learning_rate": 1.1419278057148396e-05, + "loss": 0.0216, + "step": 30504 + }, + { + "epoch": 9.42, + "learning_rate": 1.1418782999839748e-05, + "loss": 0.0232, + "step": 30505 + }, + { + "epoch": 9.42, + "learning_rate": 1.1418287938982468e-05, + "loss": 0.0218, + "step": 30506 + }, + { + "epoch": 9.42, + "learning_rate": 1.141779287457779e-05, + "loss": 0.0224, + "step": 30507 + }, + { + "epoch": 9.42, + "learning_rate": 1.1417297806626955e-05, + "loss": 0.0207, + "step": 30508 + }, + { + "epoch": 9.42, + "learning_rate": 1.1416802735131199e-05, + "loss": 0.0203, + "step": 30509 + }, + { + "epoch": 9.42, + "learning_rate": 1.1416307660091761e-05, + "loss": 0.0219, + "step": 30510 + }, + { + "epoch": 9.42, + "learning_rate": 1.1415812581509878e-05, + "loss": 0.0198, + "step": 30511 + }, + { + "epoch": 9.42, + "learning_rate": 1.141531749938679e-05, + "loss": 0.0232, + "step": 30512 + }, + { + "epoch": 9.42, + "learning_rate": 1.1414822413723739e-05, + "loss": 0.0211, + "step": 30513 + }, + { + "epoch": 9.42, + "learning_rate": 1.1414327324521952e-05, + "loss": 0.0224, + "step": 30514 + }, + { + "epoch": 9.42, + "learning_rate": 1.1413832231782678e-05, + "loss": 0.0226, + "step": 30515 + }, + { + "epoch": 9.42, + "learning_rate": 1.1413337135507153e-05, + "loss": 0.0181, + "step": 30516 + }, + { + "epoch": 9.42, + "learning_rate": 1.141284203569661e-05, + "loss": 0.0209, + "step": 30517 + }, + { + "epoch": 9.42, + "learning_rate": 1.1412346932352296e-05, + "loss": 0.0227, + "step": 30518 + }, + { + "epoch": 9.42, + "learning_rate": 1.1411851825475441e-05, + "loss": 0.0229, + "step": 30519 + }, + { + "epoch": 9.43, + "learning_rate": 1.1411356715067288e-05, + "loss": 0.0239, + "step": 30520 + }, + { + "epoch": 9.43, + "learning_rate": 1.1410861601129077e-05, + "loss": 0.0233, + "step": 30521 + }, + { + "epoch": 9.43, + "learning_rate": 1.141036648366204e-05, + "loss": 0.024, + "step": 30522 + }, + { + "epoch": 9.43, + "learning_rate": 1.1409871362667424e-05, + "loss": 0.0219, + "step": 30523 + }, + { + "epoch": 9.43, + "learning_rate": 1.140937623814646e-05, + "loss": 0.0219, + "step": 30524 + }, + { + "epoch": 9.43, + "learning_rate": 1.1408881110100387e-05, + "loss": 0.0201, + "step": 30525 + }, + { + "epoch": 9.43, + "learning_rate": 1.140838597853045e-05, + "loss": 0.0206, + "step": 30526 + }, + { + "epoch": 9.43, + "learning_rate": 1.140789084343788e-05, + "loss": 0.0204, + "step": 30527 + }, + { + "epoch": 9.43, + "learning_rate": 1.1407395704823916e-05, + "loss": 0.0218, + "step": 30528 + }, + { + "epoch": 9.43, + "learning_rate": 1.14069005626898e-05, + "loss": 0.0218, + "step": 30529 + }, + { + "epoch": 9.43, + "learning_rate": 1.1406405417036768e-05, + "loss": 0.0214, + "step": 30530 + }, + { + "epoch": 9.43, + "learning_rate": 1.1405910267866065e-05, + "loss": 0.0226, + "step": 30531 + }, + { + "epoch": 9.43, + "learning_rate": 1.1405415115178919e-05, + "loss": 0.0229, + "step": 30532 + }, + { + "epoch": 9.43, + "learning_rate": 1.1404919958976574e-05, + "loss": 0.0203, + "step": 30533 + }, + { + "epoch": 9.43, + "learning_rate": 1.140442479926027e-05, + "loss": 0.0258, + "step": 30534 + }, + { + "epoch": 9.43, + "learning_rate": 1.1403929636031242e-05, + "loss": 0.0177, + "step": 30535 + }, + { + "epoch": 9.43, + "learning_rate": 1.140343446929073e-05, + "loss": 0.0223, + "step": 30536 + }, + { + "epoch": 9.43, + "learning_rate": 1.1402939299039972e-05, + "loss": 0.021, + "step": 30537 + }, + { + "epoch": 9.43, + "learning_rate": 1.1402444125280208e-05, + "loss": 0.022, + "step": 30538 + }, + { + "epoch": 9.43, + "learning_rate": 1.1401948948012676e-05, + "loss": 0.0236, + "step": 30539 + }, + { + "epoch": 9.43, + "learning_rate": 1.140145376723861e-05, + "loss": 0.0235, + "step": 30540 + }, + { + "epoch": 9.43, + "learning_rate": 1.1400958582959259e-05, + "loss": 0.0212, + "step": 30541 + }, + { + "epoch": 9.43, + "learning_rate": 1.140046339517585e-05, + "loss": 0.0209, + "step": 30542 + }, + { + "epoch": 9.43, + "learning_rate": 1.1399968203889626e-05, + "loss": 0.0236, + "step": 30543 + }, + { + "epoch": 9.43, + "learning_rate": 1.139947300910183e-05, + "loss": 0.0211, + "step": 30544 + }, + { + "epoch": 9.43, + "learning_rate": 1.1398977810813694e-05, + "loss": 0.0229, + "step": 30545 + }, + { + "epoch": 9.43, + "learning_rate": 1.1398482609026464e-05, + "loss": 0.0192, + "step": 30546 + }, + { + "epoch": 9.43, + "learning_rate": 1.1397987403741366e-05, + "loss": 0.0254, + "step": 30547 + }, + { + "epoch": 9.43, + "learning_rate": 1.1397492194959651e-05, + "loss": 0.0225, + "step": 30548 + }, + { + "epoch": 9.43, + "learning_rate": 1.1396996982682555e-05, + "loss": 0.0221, + "step": 30549 + }, + { + "epoch": 9.43, + "learning_rate": 1.1396501766911312e-05, + "loss": 0.0213, + "step": 30550 + }, + { + "epoch": 9.43, + "learning_rate": 1.1396006547647165e-05, + "loss": 0.0215, + "step": 30551 + }, + { + "epoch": 9.44, + "learning_rate": 1.139551132489135e-05, + "loss": 0.0205, + "step": 30552 + }, + { + "epoch": 9.44, + "learning_rate": 1.1395016098645107e-05, + "loss": 0.0259, + "step": 30553 + }, + { + "epoch": 9.44, + "learning_rate": 1.1394520868909676e-05, + "loss": 0.0217, + "step": 30554 + }, + { + "epoch": 9.44, + "learning_rate": 1.139402563568629e-05, + "loss": 0.0225, + "step": 30555 + }, + { + "epoch": 9.44, + "learning_rate": 1.1393530398976193e-05, + "loss": 0.0216, + "step": 30556 + }, + { + "epoch": 9.44, + "learning_rate": 1.1393035158780625e-05, + "loss": 0.0211, + "step": 30557 + }, + { + "epoch": 9.44, + "learning_rate": 1.139253991510082e-05, + "loss": 0.0241, + "step": 30558 + }, + { + "epoch": 9.44, + "learning_rate": 1.1392044667938018e-05, + "loss": 0.021, + "step": 30559 + }, + { + "epoch": 9.44, + "learning_rate": 1.139154941729346e-05, + "loss": 0.0203, + "step": 30560 + }, + { + "epoch": 9.44, + "learning_rate": 1.139105416316838e-05, + "loss": 0.0213, + "step": 30561 + }, + { + "epoch": 9.44, + "learning_rate": 1.1390558905564022e-05, + "loss": 0.0213, + "step": 30562 + }, + { + "epoch": 9.44, + "learning_rate": 1.1390063644481623e-05, + "loss": 0.0246, + "step": 30563 + }, + { + "epoch": 9.44, + "learning_rate": 1.1389568379922421e-05, + "loss": 0.024, + "step": 30564 + }, + { + "epoch": 9.44, + "learning_rate": 1.1389073111887654e-05, + "loss": 0.0236, + "step": 30565 + }, + { + "epoch": 9.44, + "learning_rate": 1.1388577840378563e-05, + "loss": 0.0215, + "step": 30566 + }, + { + "epoch": 9.44, + "learning_rate": 1.1388082565396386e-05, + "loss": 0.0194, + "step": 30567 + }, + { + "epoch": 9.44, + "learning_rate": 1.138758728694236e-05, + "loss": 0.0246, + "step": 30568 + }, + { + "epoch": 9.44, + "learning_rate": 1.1387092005017726e-05, + "loss": 0.0227, + "step": 30569 + }, + { + "epoch": 9.44, + "learning_rate": 1.1386596719623721e-05, + "loss": 0.0229, + "step": 30570 + }, + { + "epoch": 9.44, + "learning_rate": 1.1386101430761584e-05, + "loss": 0.0216, + "step": 30571 + }, + { + "epoch": 9.44, + "learning_rate": 1.138560613843256e-05, + "loss": 0.021, + "step": 30572 + }, + { + "epoch": 9.44, + "learning_rate": 1.1385110842637874e-05, + "loss": 0.0203, + "step": 30573 + }, + { + "epoch": 9.44, + "learning_rate": 1.1384615543378778e-05, + "loss": 0.0192, + "step": 30574 + }, + { + "epoch": 9.44, + "learning_rate": 1.1384120240656509e-05, + "loss": 0.0204, + "step": 30575 + }, + { + "epoch": 9.44, + "learning_rate": 1.1383624934472295e-05, + "loss": 0.0238, + "step": 30576 + }, + { + "epoch": 9.44, + "learning_rate": 1.138312962482739e-05, + "loss": 0.0193, + "step": 30577 + }, + { + "epoch": 9.44, + "learning_rate": 1.1382634311723022e-05, + "loss": 0.0242, + "step": 30578 + }, + { + "epoch": 9.44, + "learning_rate": 1.1382138995160432e-05, + "loss": 0.0212, + "step": 30579 + }, + { + "epoch": 9.44, + "learning_rate": 1.1381643675140864e-05, + "loss": 0.0191, + "step": 30580 + }, + { + "epoch": 9.44, + "learning_rate": 1.138114835166555e-05, + "loss": 0.0197, + "step": 30581 + }, + { + "epoch": 9.44, + "learning_rate": 1.1380653024735735e-05, + "loss": 0.0219, + "step": 30582 + }, + { + "epoch": 9.44, + "learning_rate": 1.1380157694352652e-05, + "loss": 0.0221, + "step": 30583 + }, + { + "epoch": 9.44, + "learning_rate": 1.1379662360517543e-05, + "loss": 0.0224, + "step": 30584 + }, + { + "epoch": 9.45, + "learning_rate": 1.137916702323165e-05, + "loss": 0.0213, + "step": 30585 + }, + { + "epoch": 9.45, + "learning_rate": 1.1378671682496205e-05, + "loss": 0.022, + "step": 30586 + }, + { + "epoch": 9.45, + "learning_rate": 1.1378176338312452e-05, + "loss": 0.0209, + "step": 30587 + }, + { + "epoch": 9.45, + "learning_rate": 1.137768099068163e-05, + "loss": 0.0223, + "step": 30588 + }, + { + "epoch": 9.45, + "learning_rate": 1.1377185639604976e-05, + "loss": 0.0212, + "step": 30589 + }, + { + "epoch": 9.45, + "learning_rate": 1.137669028508373e-05, + "loss": 0.0193, + "step": 30590 + }, + { + "epoch": 9.45, + "learning_rate": 1.1376194927119126e-05, + "loss": 0.0209, + "step": 30591 + }, + { + "epoch": 9.45, + "learning_rate": 1.1375699565712413e-05, + "loss": 0.0191, + "step": 30592 + }, + { + "epoch": 9.45, + "learning_rate": 1.1375204200864822e-05, + "loss": 0.0219, + "step": 30593 + }, + { + "epoch": 9.45, + "learning_rate": 1.1374708832577595e-05, + "loss": 0.021, + "step": 30594 + }, + { + "epoch": 9.45, + "learning_rate": 1.1374213460851972e-05, + "loss": 0.024, + "step": 30595 + }, + { + "epoch": 9.45, + "learning_rate": 1.1373718085689187e-05, + "loss": 0.0213, + "step": 30596 + }, + { + "epoch": 9.45, + "learning_rate": 1.1373222707090484e-05, + "loss": 0.0241, + "step": 30597 + }, + { + "epoch": 9.45, + "learning_rate": 1.1372727325057102e-05, + "loss": 0.0235, + "step": 30598 + }, + { + "epoch": 9.45, + "learning_rate": 1.1372231939590276e-05, + "loss": 0.022, + "step": 30599 + }, + { + "epoch": 9.45, + "learning_rate": 1.1371736550691252e-05, + "loss": 0.0218, + "step": 30600 + }, + { + "epoch": 9.45, + "learning_rate": 1.1371241158361259e-05, + "loss": 0.0245, + "step": 30601 + }, + { + "epoch": 9.45, + "learning_rate": 1.1370745762601544e-05, + "loss": 0.0222, + "step": 30602 + }, + { + "epoch": 9.45, + "learning_rate": 1.1370250363413349e-05, + "loss": 0.0198, + "step": 30603 + }, + { + "epoch": 9.45, + "learning_rate": 1.13697549607979e-05, + "loss": 0.0233, + "step": 30604 + }, + { + "epoch": 9.45, + "learning_rate": 1.136925955475645e-05, + "loss": 0.0215, + "step": 30605 + }, + { + "epoch": 9.45, + "learning_rate": 1.136876414529023e-05, + "loss": 0.0185, + "step": 30606 + }, + { + "epoch": 9.45, + "learning_rate": 1.1368268732400479e-05, + "loss": 0.0235, + "step": 30607 + }, + { + "epoch": 9.45, + "learning_rate": 1.1367773316088441e-05, + "loss": 0.0183, + "step": 30608 + }, + { + "epoch": 9.45, + "learning_rate": 1.1367277896355351e-05, + "loss": 0.0204, + "step": 30609 + }, + { + "epoch": 9.45, + "learning_rate": 1.136678247320245e-05, + "loss": 0.022, + "step": 30610 + }, + { + "epoch": 9.45, + "learning_rate": 1.1366287046630977e-05, + "loss": 0.0208, + "step": 30611 + }, + { + "epoch": 9.45, + "learning_rate": 1.136579161664217e-05, + "loss": 0.0223, + "step": 30612 + }, + { + "epoch": 9.45, + "learning_rate": 1.136529618323727e-05, + "loss": 0.0204, + "step": 30613 + }, + { + "epoch": 9.45, + "learning_rate": 1.1364800746417517e-05, + "loss": 0.0199, + "step": 30614 + }, + { + "epoch": 9.45, + "learning_rate": 1.1364305306184144e-05, + "loss": 0.025, + "step": 30615 + }, + { + "epoch": 9.45, + "learning_rate": 1.13638098625384e-05, + "loss": 0.0211, + "step": 30616 + }, + { + "epoch": 9.46, + "learning_rate": 1.1363314415481514e-05, + "loss": 0.0207, + "step": 30617 + }, + { + "epoch": 9.46, + "learning_rate": 1.1362818965014733e-05, + "loss": 0.0236, + "step": 30618 + }, + { + "epoch": 9.46, + "learning_rate": 1.1362323511139292e-05, + "loss": 0.0209, + "step": 30619 + }, + { + "epoch": 9.46, + "learning_rate": 1.1361828053856432e-05, + "loss": 0.0212, + "step": 30620 + }, + { + "epoch": 9.46, + "learning_rate": 1.1361332593167391e-05, + "loss": 0.0216, + "step": 30621 + }, + { + "epoch": 9.46, + "learning_rate": 1.136083712907341e-05, + "loss": 0.0205, + "step": 30622 + }, + { + "epoch": 9.46, + "learning_rate": 1.1360341661575725e-05, + "loss": 0.0213, + "step": 30623 + }, + { + "epoch": 9.46, + "learning_rate": 1.1359846190675578e-05, + "loss": 0.0253, + "step": 30624 + }, + { + "epoch": 9.46, + "learning_rate": 1.1359350716374209e-05, + "loss": 0.0215, + "step": 30625 + }, + { + "epoch": 9.46, + "learning_rate": 1.1358855238672857e-05, + "loss": 0.0219, + "step": 30626 + }, + { + "epoch": 9.46, + "learning_rate": 1.1358359757572757e-05, + "loss": 0.0278, + "step": 30627 + }, + { + "epoch": 9.46, + "learning_rate": 1.1357864273075152e-05, + "loss": 0.0222, + "step": 30628 + }, + { + "epoch": 9.46, + "learning_rate": 1.1357368785181282e-05, + "loss": 0.0216, + "step": 30629 + }, + { + "epoch": 9.46, + "learning_rate": 1.1356873293892385e-05, + "loss": 0.0208, + "step": 30630 + }, + { + "epoch": 9.46, + "learning_rate": 1.1356377799209701e-05, + "loss": 0.0195, + "step": 30631 + }, + { + "epoch": 9.46, + "learning_rate": 1.1355882301134467e-05, + "loss": 0.0205, + "step": 30632 + }, + { + "epoch": 9.46, + "learning_rate": 1.1355386799667925e-05, + "loss": 0.0225, + "step": 30633 + }, + { + "epoch": 9.46, + "learning_rate": 1.1354891294811317e-05, + "loss": 0.0207, + "step": 30634 + }, + { + "epoch": 9.46, + "learning_rate": 1.1354395786565873e-05, + "loss": 0.0205, + "step": 30635 + }, + { + "epoch": 9.46, + "learning_rate": 1.135390027493284e-05, + "loss": 0.0236, + "step": 30636 + }, + { + "epoch": 9.46, + "learning_rate": 1.1353404759913459e-05, + "loss": 0.0214, + "step": 30637 + }, + { + "epoch": 9.46, + "learning_rate": 1.1352909241508959e-05, + "loss": 0.0202, + "step": 30638 + }, + { + "epoch": 9.46, + "learning_rate": 1.1352413719720592e-05, + "loss": 0.0211, + "step": 30639 + }, + { + "epoch": 9.46, + "learning_rate": 1.135191819454959e-05, + "loss": 0.0241, + "step": 30640 + }, + { + "epoch": 9.46, + "learning_rate": 1.1351422665997191e-05, + "loss": 0.0226, + "step": 30641 + }, + { + "epoch": 9.46, + "learning_rate": 1.1350927134064642e-05, + "loss": 0.0226, + "step": 30642 + }, + { + "epoch": 9.46, + "learning_rate": 1.1350431598753176e-05, + "loss": 0.0208, + "step": 30643 + }, + { + "epoch": 9.46, + "learning_rate": 1.1349936060064033e-05, + "loss": 0.0199, + "step": 30644 + }, + { + "epoch": 9.46, + "learning_rate": 1.1349440517998455e-05, + "loss": 0.0209, + "step": 30645 + }, + { + "epoch": 9.46, + "learning_rate": 1.1348944972557681e-05, + "loss": 0.0205, + "step": 30646 + }, + { + "epoch": 9.46, + "learning_rate": 1.1348449423742947e-05, + "loss": 0.0216, + "step": 30647 + }, + { + "epoch": 9.46, + "learning_rate": 1.1347953871555497e-05, + "loss": 0.024, + "step": 30648 + }, + { + "epoch": 9.47, + "learning_rate": 1.1347458315996567e-05, + "loss": 0.0201, + "step": 30649 + }, + { + "epoch": 9.47, + "learning_rate": 1.1346962757067399e-05, + "loss": 0.0224, + "step": 30650 + }, + { + "epoch": 9.47, + "learning_rate": 1.1346467194769233e-05, + "loss": 0.0215, + "step": 30651 + }, + { + "epoch": 9.47, + "learning_rate": 1.1345971629103305e-05, + "loss": 0.0222, + "step": 30652 + }, + { + "epoch": 9.47, + "learning_rate": 1.1345476060070858e-05, + "loss": 0.0217, + "step": 30653 + }, + { + "epoch": 9.47, + "learning_rate": 1.1344980487673127e-05, + "loss": 0.0189, + "step": 30654 + }, + { + "epoch": 9.47, + "learning_rate": 1.1344484911911357e-05, + "loss": 0.0216, + "step": 30655 + }, + { + "epoch": 9.47, + "learning_rate": 1.1343989332786785e-05, + "loss": 0.0217, + "step": 30656 + }, + { + "epoch": 9.47, + "learning_rate": 1.1343493750300651e-05, + "loss": 0.0241, + "step": 30657 + }, + { + "epoch": 9.47, + "learning_rate": 1.134299816445419e-05, + "loss": 0.0226, + "step": 30658 + }, + { + "epoch": 9.47, + "learning_rate": 1.134250257524865e-05, + "loss": 0.022, + "step": 30659 + }, + { + "epoch": 9.47, + "learning_rate": 1.1342006982685268e-05, + "loss": 0.0206, + "step": 30660 + }, + { + "epoch": 9.47, + "learning_rate": 1.1341511386765276e-05, + "loss": 0.0202, + "step": 30661 + }, + { + "epoch": 9.47, + "learning_rate": 1.1341015787489924e-05, + "loss": 0.0264, + "step": 30662 + }, + { + "epoch": 9.47, + "learning_rate": 1.1340520184860442e-05, + "loss": 0.0233, + "step": 30663 + }, + { + "epoch": 9.47, + "learning_rate": 1.1340024578878077e-05, + "loss": 0.0218, + "step": 30664 + }, + { + "epoch": 9.47, + "learning_rate": 1.133952896954407e-05, + "loss": 0.0258, + "step": 30665 + }, + { + "epoch": 9.47, + "learning_rate": 1.133903335685965e-05, + "loss": 0.0224, + "step": 30666 + }, + { + "epoch": 9.47, + "learning_rate": 1.133853774082607e-05, + "loss": 0.0223, + "step": 30667 + }, + { + "epoch": 9.47, + "learning_rate": 1.1338042121444559e-05, + "loss": 0.0194, + "step": 30668 + }, + { + "epoch": 9.47, + "learning_rate": 1.1337546498716359e-05, + "loss": 0.022, + "step": 30669 + }, + { + "epoch": 9.47, + "learning_rate": 1.1337050872642716e-05, + "loss": 0.0201, + "step": 30670 + }, + { + "epoch": 9.47, + "learning_rate": 1.1336555243224863e-05, + "loss": 0.0221, + "step": 30671 + }, + { + "epoch": 9.47, + "learning_rate": 1.133605961046404e-05, + "loss": 0.0212, + "step": 30672 + }, + { + "epoch": 9.47, + "learning_rate": 1.133556397436149e-05, + "loss": 0.0206, + "step": 30673 + }, + { + "epoch": 9.47, + "learning_rate": 1.133506833491845e-05, + "loss": 0.0238, + "step": 30674 + }, + { + "epoch": 9.47, + "learning_rate": 1.1334572692136161e-05, + "loss": 0.0228, + "step": 30675 + }, + { + "epoch": 9.47, + "learning_rate": 1.1334077046015862e-05, + "loss": 0.0207, + "step": 30676 + }, + { + "epoch": 9.47, + "learning_rate": 1.1333581396558792e-05, + "loss": 0.021, + "step": 30677 + }, + { + "epoch": 9.47, + "learning_rate": 1.1333085743766193e-05, + "loss": 0.0227, + "step": 30678 + }, + { + "epoch": 9.47, + "learning_rate": 1.1332590087639304e-05, + "loss": 0.022, + "step": 30679 + }, + { + "epoch": 9.47, + "learning_rate": 1.1332094428179363e-05, + "loss": 0.0204, + "step": 30680 + }, + { + "epoch": 9.47, + "learning_rate": 1.133159876538761e-05, + "loss": 0.0205, + "step": 30681 + }, + { + "epoch": 9.48, + "learning_rate": 1.1331103099265287e-05, + "loss": 0.0225, + "step": 30682 + }, + { + "epoch": 9.48, + "learning_rate": 1.1330607429813632e-05, + "loss": 0.0203, + "step": 30683 + }, + { + "epoch": 9.48, + "learning_rate": 1.1330111757033886e-05, + "loss": 0.0221, + "step": 30684 + }, + { + "epoch": 9.48, + "learning_rate": 1.1329616080927287e-05, + "loss": 0.0224, + "step": 30685 + }, + { + "epoch": 9.48, + "learning_rate": 1.1329120401495075e-05, + "loss": 0.0225, + "step": 30686 + }, + { + "epoch": 9.48, + "learning_rate": 1.1328624718738492e-05, + "loss": 0.0207, + "step": 30687 + }, + { + "epoch": 9.48, + "learning_rate": 1.1328129032658777e-05, + "loss": 0.0222, + "step": 30688 + }, + { + "epoch": 9.48, + "learning_rate": 1.1327633343257164e-05, + "loss": 0.0223, + "step": 30689 + }, + { + "epoch": 9.48, + "learning_rate": 1.1327137650534905e-05, + "loss": 0.0229, + "step": 30690 + }, + { + "epoch": 9.48, + "learning_rate": 1.1326641954493229e-05, + "loss": 0.0194, + "step": 30691 + }, + { + "epoch": 9.48, + "learning_rate": 1.1326146255133379e-05, + "loss": 0.02, + "step": 30692 + }, + { + "epoch": 9.48, + "learning_rate": 1.1325650552456598e-05, + "loss": 0.0234, + "step": 30693 + }, + { + "epoch": 9.48, + "learning_rate": 1.1325154846464118e-05, + "loss": 0.0221, + "step": 30694 + }, + { + "epoch": 9.48, + "learning_rate": 1.132465913715719e-05, + "loss": 0.0219, + "step": 30695 + }, + { + "epoch": 9.48, + "learning_rate": 1.1324163424537045e-05, + "loss": 0.0251, + "step": 30696 + }, + { + "epoch": 9.48, + "learning_rate": 1.1323667708604924e-05, + "loss": 0.0231, + "step": 30697 + }, + { + "epoch": 9.48, + "learning_rate": 1.1323171989362071e-05, + "loss": 0.0214, + "step": 30698 + }, + { + "epoch": 9.48, + "learning_rate": 1.1322676266809724e-05, + "loss": 0.0213, + "step": 30699 + }, + { + "epoch": 9.48, + "learning_rate": 1.1322180540949122e-05, + "loss": 0.0197, + "step": 30700 + }, + { + "epoch": 9.48, + "learning_rate": 1.1321684811781504e-05, + "loss": 0.0208, + "step": 30701 + }, + { + "epoch": 9.48, + "learning_rate": 1.1321189079308112e-05, + "loss": 0.0206, + "step": 30702 + }, + { + "epoch": 9.48, + "learning_rate": 1.1320693343530184e-05, + "loss": 0.0214, + "step": 30703 + }, + { + "epoch": 9.48, + "learning_rate": 1.1320197604448963e-05, + "loss": 0.0207, + "step": 30704 + }, + { + "epoch": 9.48, + "learning_rate": 1.1319701862065687e-05, + "loss": 0.0199, + "step": 30705 + }, + { + "epoch": 9.48, + "learning_rate": 1.1319206116381593e-05, + "loss": 0.0207, + "step": 30706 + }, + { + "epoch": 9.48, + "learning_rate": 1.1318710367397927e-05, + "loss": 0.029, + "step": 30707 + }, + { + "epoch": 9.48, + "learning_rate": 1.1318214615115925e-05, + "loss": 0.0247, + "step": 30708 + }, + { + "epoch": 9.48, + "learning_rate": 1.1317718859536828e-05, + "loss": 0.0216, + "step": 30709 + }, + { + "epoch": 9.48, + "learning_rate": 1.1317223100661877e-05, + "loss": 0.0203, + "step": 30710 + }, + { + "epoch": 9.48, + "learning_rate": 1.1316727338492308e-05, + "loss": 0.0217, + "step": 30711 + }, + { + "epoch": 9.48, + "learning_rate": 1.1316231573029364e-05, + "loss": 0.0201, + "step": 30712 + }, + { + "epoch": 9.48, + "learning_rate": 1.1315735804274285e-05, + "loss": 0.023, + "step": 30713 + }, + { + "epoch": 9.49, + "learning_rate": 1.1315240032228314e-05, + "loss": 0.0202, + "step": 30714 + }, + { + "epoch": 9.49, + "learning_rate": 1.1314744256892685e-05, + "loss": 0.0226, + "step": 30715 + }, + { + "epoch": 9.49, + "learning_rate": 1.1314248478268643e-05, + "loss": 0.0202, + "step": 30716 + }, + { + "epoch": 9.49, + "learning_rate": 1.1313752696357421e-05, + "loss": 0.0239, + "step": 30717 + }, + { + "epoch": 9.49, + "learning_rate": 1.1313256911160269e-05, + "loss": 0.0208, + "step": 30718 + }, + { + "epoch": 9.49, + "learning_rate": 1.1312761122678422e-05, + "loss": 0.0216, + "step": 30719 + }, + { + "epoch": 9.49, + "learning_rate": 1.1312265330913115e-05, + "loss": 0.0243, + "step": 30720 + }, + { + "epoch": 9.49, + "learning_rate": 1.1311769535865598e-05, + "loss": 0.0243, + "step": 30721 + }, + { + "epoch": 9.49, + "learning_rate": 1.1311273737537102e-05, + "loss": 0.0225, + "step": 30722 + }, + { + "epoch": 9.49, + "learning_rate": 1.1310777935928874e-05, + "loss": 0.0222, + "step": 30723 + }, + { + "epoch": 9.49, + "learning_rate": 1.1310282131042151e-05, + "loss": 0.0237, + "step": 30724 + }, + { + "epoch": 9.49, + "learning_rate": 1.1309786322878173e-05, + "loss": 0.0214, + "step": 30725 + }, + { + "epoch": 9.49, + "learning_rate": 1.1309290511438183e-05, + "loss": 0.0241, + "step": 30726 + }, + { + "epoch": 9.49, + "learning_rate": 1.1308794696723415e-05, + "loss": 0.0238, + "step": 30727 + }, + { + "epoch": 9.49, + "learning_rate": 1.1308298878735111e-05, + "loss": 0.0225, + "step": 30728 + }, + { + "epoch": 9.49, + "learning_rate": 1.1307803057474518e-05, + "loss": 0.0218, + "step": 30729 + }, + { + "epoch": 9.49, + "learning_rate": 1.130730723294287e-05, + "loss": 0.0227, + "step": 30730 + }, + { + "epoch": 9.49, + "learning_rate": 1.1306811405141407e-05, + "loss": 0.0233, + "step": 30731 + }, + { + "epoch": 9.49, + "learning_rate": 1.1306315574071369e-05, + "loss": 0.0227, + "step": 30732 + }, + { + "epoch": 9.49, + "learning_rate": 1.1305819739733998e-05, + "loss": 0.0201, + "step": 30733 + }, + { + "epoch": 9.49, + "learning_rate": 1.1305323902130536e-05, + "loss": 0.0225, + "step": 30734 + }, + { + "epoch": 9.49, + "learning_rate": 1.130482806126222e-05, + "loss": 0.0211, + "step": 30735 + }, + { + "epoch": 9.49, + "learning_rate": 1.130433221713029e-05, + "loss": 0.0257, + "step": 30736 + }, + { + "epoch": 9.49, + "learning_rate": 1.1303836369735987e-05, + "loss": 0.0226, + "step": 30737 + }, + { + "epoch": 9.49, + "learning_rate": 1.1303340519080552e-05, + "loss": 0.0217, + "step": 30738 + }, + { + "epoch": 9.49, + "learning_rate": 1.1302844665165227e-05, + "loss": 0.0227, + "step": 30739 + }, + { + "epoch": 9.49, + "learning_rate": 1.1302348807991245e-05, + "loss": 0.0217, + "step": 30740 + }, + { + "epoch": 9.49, + "learning_rate": 1.1301852947559856e-05, + "loss": 0.0244, + "step": 30741 + }, + { + "epoch": 9.49, + "learning_rate": 1.1301357083872293e-05, + "loss": 0.0229, + "step": 30742 + }, + { + "epoch": 9.49, + "learning_rate": 1.1300861216929797e-05, + "loss": 0.0228, + "step": 30743 + }, + { + "epoch": 9.49, + "learning_rate": 1.1300365346733613e-05, + "loss": 0.022, + "step": 30744 + }, + { + "epoch": 9.49, + "learning_rate": 1.1299869473284974e-05, + "loss": 0.0234, + "step": 30745 + }, + { + "epoch": 9.49, + "learning_rate": 1.1299373596585129e-05, + "loss": 0.0225, + "step": 30746 + }, + { + "epoch": 9.5, + "learning_rate": 1.1298877716635313e-05, + "loss": 0.0221, + "step": 30747 + }, + { + "epoch": 9.5, + "learning_rate": 1.1298381833436762e-05, + "loss": 0.0203, + "step": 30748 + }, + { + "epoch": 9.5, + "learning_rate": 1.1297885946990727e-05, + "loss": 0.0221, + "step": 30749 + }, + { + "epoch": 9.5, + "learning_rate": 1.129739005729844e-05, + "loss": 0.0209, + "step": 30750 + }, + { + "epoch": 9.5, + "learning_rate": 1.1296894164361143e-05, + "loss": 0.0222, + "step": 30751 + }, + { + "epoch": 9.5, + "learning_rate": 1.129639826818008e-05, + "loss": 0.0232, + "step": 30752 + }, + { + "epoch": 9.5, + "learning_rate": 1.1295902368756487e-05, + "loss": 0.022, + "step": 30753 + }, + { + "epoch": 9.5, + "learning_rate": 1.1295406466091606e-05, + "loss": 0.0224, + "step": 30754 + }, + { + "epoch": 9.5, + "learning_rate": 1.1294910560186676e-05, + "loss": 0.0224, + "step": 30755 + }, + { + "epoch": 9.5, + "learning_rate": 1.1294414651042938e-05, + "loss": 0.0221, + "step": 30756 + }, + { + "epoch": 9.5, + "learning_rate": 1.1293918738661636e-05, + "loss": 0.0187, + "step": 30757 + }, + { + "epoch": 9.5, + "learning_rate": 1.1293422823044003e-05, + "loss": 0.0225, + "step": 30758 + }, + { + "epoch": 9.5, + "learning_rate": 1.1292926904191286e-05, + "loss": 0.0226, + "step": 30759 + }, + { + "epoch": 9.5, + "learning_rate": 1.1292430982104723e-05, + "loss": 0.0205, + "step": 30760 + }, + { + "epoch": 9.5, + "learning_rate": 1.1291935056785555e-05, + "loss": 0.0223, + "step": 30761 + }, + { + "epoch": 9.5, + "learning_rate": 1.129143912823502e-05, + "loss": 0.0226, + "step": 30762 + }, + { + "epoch": 9.5, + "learning_rate": 1.1290943196454362e-05, + "loss": 0.0228, + "step": 30763 + }, + { + "epoch": 9.5, + "learning_rate": 1.1290447261444818e-05, + "loss": 0.0208, + "step": 30764 + }, + { + "epoch": 9.5, + "learning_rate": 1.1289951323207632e-05, + "loss": 0.0226, + "step": 30765 + }, + { + "epoch": 9.5, + "learning_rate": 1.128945538174404e-05, + "loss": 0.0225, + "step": 30766 + }, + { + "epoch": 9.5, + "learning_rate": 1.1288959437055287e-05, + "loss": 0.0263, + "step": 30767 + }, + { + "epoch": 9.5, + "learning_rate": 1.1288463489142612e-05, + "loss": 0.021, + "step": 30768 + }, + { + "epoch": 9.5, + "learning_rate": 1.1287967538007251e-05, + "loss": 0.0204, + "step": 30769 + }, + { + "epoch": 9.5, + "learning_rate": 1.1287471583650453e-05, + "loss": 0.0218, + "step": 30770 + }, + { + "epoch": 9.5, + "learning_rate": 1.1286975626073451e-05, + "loss": 0.0201, + "step": 30771 + }, + { + "epoch": 9.5, + "learning_rate": 1.1286479665277489e-05, + "loss": 0.023, + "step": 30772 + }, + { + "epoch": 9.5, + "learning_rate": 1.1285983701263807e-05, + "loss": 0.0206, + "step": 30773 + }, + { + "epoch": 9.5, + "learning_rate": 1.1285487734033645e-05, + "loss": 0.0235, + "step": 30774 + }, + { + "epoch": 9.5, + "learning_rate": 1.1284991763588245e-05, + "loss": 0.0209, + "step": 30775 + }, + { + "epoch": 9.5, + "learning_rate": 1.1284495789928842e-05, + "loss": 0.021, + "step": 30776 + }, + { + "epoch": 9.5, + "learning_rate": 1.1283999813056683e-05, + "loss": 0.0221, + "step": 30777 + }, + { + "epoch": 9.5, + "learning_rate": 1.1283503832973008e-05, + "loss": 0.022, + "step": 30778 + }, + { + "epoch": 9.51, + "learning_rate": 1.1283007849679052e-05, + "loss": 0.0213, + "step": 30779 + }, + { + "epoch": 9.51, + "learning_rate": 1.1282511863176065e-05, + "loss": 0.0237, + "step": 30780 + }, + { + "epoch": 9.51, + "learning_rate": 1.1282015873465277e-05, + "loss": 0.0226, + "step": 30781 + }, + { + "epoch": 9.51, + "learning_rate": 1.1281519880547936e-05, + "loss": 0.0227, + "step": 30782 + }, + { + "epoch": 9.51, + "learning_rate": 1.128102388442528e-05, + "loss": 0.0201, + "step": 30783 + }, + { + "epoch": 9.51, + "learning_rate": 1.1280527885098549e-05, + "loss": 0.0213, + "step": 30784 + }, + { + "epoch": 9.51, + "learning_rate": 1.1280031882568983e-05, + "loss": 0.0201, + "step": 30785 + }, + { + "epoch": 9.51, + "learning_rate": 1.1279535876837826e-05, + "loss": 0.0233, + "step": 30786 + }, + { + "epoch": 9.51, + "learning_rate": 1.1279039867906314e-05, + "loss": 0.0218, + "step": 30787 + }, + { + "epoch": 9.51, + "learning_rate": 1.1278543855775692e-05, + "loss": 0.0214, + "step": 30788 + }, + { + "epoch": 9.51, + "learning_rate": 1.1278047840447196e-05, + "loss": 0.021, + "step": 30789 + }, + { + "epoch": 9.51, + "learning_rate": 1.1277551821922072e-05, + "loss": 0.0204, + "step": 30790 + }, + { + "epoch": 9.51, + "learning_rate": 1.1277055800201557e-05, + "loss": 0.0221, + "step": 30791 + }, + { + "epoch": 9.51, + "learning_rate": 1.1276559775286893e-05, + "loss": 0.0229, + "step": 30792 + }, + { + "epoch": 9.51, + "learning_rate": 1.127606374717932e-05, + "loss": 0.024, + "step": 30793 + }, + { + "epoch": 9.51, + "learning_rate": 1.1275567715880077e-05, + "loss": 0.024, + "step": 30794 + }, + { + "epoch": 9.51, + "learning_rate": 1.127507168139041e-05, + "loss": 0.018, + "step": 30795 + }, + { + "epoch": 9.51, + "learning_rate": 1.1274575643711554e-05, + "loss": 0.0226, + "step": 30796 + }, + { + "epoch": 9.51, + "learning_rate": 1.1274079602844752e-05, + "loss": 0.0233, + "step": 30797 + }, + { + "epoch": 9.51, + "learning_rate": 1.1273583558791245e-05, + "loss": 0.024, + "step": 30798 + }, + { + "epoch": 9.51, + "learning_rate": 1.1273087511552272e-05, + "loss": 0.0236, + "step": 30799 + }, + { + "epoch": 9.51, + "learning_rate": 1.1272591461129077e-05, + "loss": 0.0212, + "step": 30800 + }, + { + "epoch": 9.51, + "learning_rate": 1.1272095407522899e-05, + "loss": 0.0242, + "step": 30801 + }, + { + "epoch": 9.51, + "learning_rate": 1.1271599350734974e-05, + "loss": 0.0199, + "step": 30802 + }, + { + "epoch": 9.51, + "learning_rate": 1.1271103290766552e-05, + "loss": 0.0234, + "step": 30803 + }, + { + "epoch": 9.51, + "learning_rate": 1.1270607227618865e-05, + "loss": 0.0239, + "step": 30804 + }, + { + "epoch": 9.51, + "learning_rate": 1.127011116129316e-05, + "loss": 0.0197, + "step": 30805 + }, + { + "epoch": 9.51, + "learning_rate": 1.1269615091790676e-05, + "loss": 0.0223, + "step": 30806 + }, + { + "epoch": 9.51, + "learning_rate": 1.126911901911265e-05, + "loss": 0.0224, + "step": 30807 + }, + { + "epoch": 9.51, + "learning_rate": 1.126862294326033e-05, + "loss": 0.0208, + "step": 30808 + }, + { + "epoch": 9.51, + "learning_rate": 1.1268126864234949e-05, + "loss": 0.0208, + "step": 30809 + }, + { + "epoch": 9.51, + "learning_rate": 1.126763078203775e-05, + "loss": 0.0245, + "step": 30810 + }, + { + "epoch": 9.52, + "learning_rate": 1.1267134696669982e-05, + "loss": 0.0241, + "step": 30811 + }, + { + "epoch": 9.52, + "learning_rate": 1.1266638608132873e-05, + "loss": 0.024, + "step": 30812 + }, + { + "epoch": 9.52, + "learning_rate": 1.1266142516427672e-05, + "loss": 0.0258, + "step": 30813 + }, + { + "epoch": 9.52, + "learning_rate": 1.1265646421555618e-05, + "loss": 0.0225, + "step": 30814 + }, + { + "epoch": 9.52, + "learning_rate": 1.1265150323517951e-05, + "loss": 0.0219, + "step": 30815 + }, + { + "epoch": 9.52, + "learning_rate": 1.1264654222315911e-05, + "loss": 0.0244, + "step": 30816 + }, + { + "epoch": 9.52, + "learning_rate": 1.126415811795074e-05, + "loss": 0.0227, + "step": 30817 + }, + { + "epoch": 9.52, + "learning_rate": 1.1263662010423682e-05, + "loss": 0.0222, + "step": 30818 + }, + { + "epoch": 9.52, + "learning_rate": 1.1263165899735973e-05, + "loss": 0.0211, + "step": 30819 + }, + { + "epoch": 9.52, + "learning_rate": 1.1262669785888856e-05, + "loss": 0.0217, + "step": 30820 + }, + { + "epoch": 9.52, + "learning_rate": 1.1262173668883572e-05, + "loss": 0.023, + "step": 30821 + }, + { + "epoch": 9.52, + "learning_rate": 1.126167754872136e-05, + "loss": 0.0232, + "step": 30822 + }, + { + "epoch": 9.52, + "learning_rate": 1.1261181425403463e-05, + "loss": 0.0227, + "step": 30823 + }, + { + "epoch": 9.52, + "learning_rate": 1.1260685298931122e-05, + "loss": 0.0234, + "step": 30824 + }, + { + "epoch": 9.52, + "learning_rate": 1.1260189169305575e-05, + "loss": 0.021, + "step": 30825 + }, + { + "epoch": 9.52, + "learning_rate": 1.1259693036528068e-05, + "loss": 0.0219, + "step": 30826 + }, + { + "epoch": 9.52, + "learning_rate": 1.1259196900599836e-05, + "loss": 0.0238, + "step": 30827 + }, + { + "epoch": 9.52, + "learning_rate": 1.1258700761522126e-05, + "loss": 0.0208, + "step": 30828 + }, + { + "epoch": 9.52, + "learning_rate": 1.1258204619296175e-05, + "loss": 0.023, + "step": 30829 + }, + { + "epoch": 9.52, + "learning_rate": 1.125770847392322e-05, + "loss": 0.0205, + "step": 30830 + }, + { + "epoch": 9.52, + "learning_rate": 1.1257212325404513e-05, + "loss": 0.0218, + "step": 30831 + }, + { + "epoch": 9.52, + "learning_rate": 1.125671617374129e-05, + "loss": 0.0206, + "step": 30832 + }, + { + "epoch": 9.52, + "learning_rate": 1.1256220018934783e-05, + "loss": 0.0231, + "step": 30833 + }, + { + "epoch": 9.52, + "learning_rate": 1.1255723860986247e-05, + "loss": 0.0208, + "step": 30834 + }, + { + "epoch": 9.52, + "learning_rate": 1.1255227699896913e-05, + "loss": 0.0209, + "step": 30835 + }, + { + "epoch": 9.52, + "learning_rate": 1.1254731535668024e-05, + "loss": 0.0228, + "step": 30836 + }, + { + "epoch": 9.52, + "learning_rate": 1.1254235368300827e-05, + "loss": 0.0212, + "step": 30837 + }, + { + "epoch": 9.52, + "learning_rate": 1.1253739197796558e-05, + "loss": 0.0225, + "step": 30838 + }, + { + "epoch": 9.52, + "learning_rate": 1.1253243024156457e-05, + "loss": 0.0209, + "step": 30839 + }, + { + "epoch": 9.52, + "learning_rate": 1.1252746847381768e-05, + "loss": 0.0203, + "step": 30840 + }, + { + "epoch": 9.52, + "learning_rate": 1.1252250667473728e-05, + "loss": 0.0232, + "step": 30841 + }, + { + "epoch": 9.52, + "learning_rate": 1.1251754484433584e-05, + "loss": 0.024, + "step": 30842 + }, + { + "epoch": 9.52, + "learning_rate": 1.1251258298262573e-05, + "loss": 0.022, + "step": 30843 + }, + { + "epoch": 9.53, + "learning_rate": 1.1250762108961934e-05, + "loss": 0.024, + "step": 30844 + }, + { + "epoch": 9.53, + "learning_rate": 1.1250265916532914e-05, + "loss": 0.0238, + "step": 30845 + }, + { + "epoch": 9.53, + "learning_rate": 1.1249769720976749e-05, + "loss": 0.0209, + "step": 30846 + }, + { + "epoch": 9.53, + "learning_rate": 1.1249273522294683e-05, + "loss": 0.0217, + "step": 30847 + }, + { + "epoch": 9.53, + "learning_rate": 1.1248777320487955e-05, + "loss": 0.022, + "step": 30848 + }, + { + "epoch": 9.53, + "learning_rate": 1.1248281115557808e-05, + "loss": 0.0229, + "step": 30849 + }, + { + "epoch": 9.53, + "learning_rate": 1.1247784907505483e-05, + "loss": 0.0217, + "step": 30850 + }, + { + "epoch": 9.53, + "learning_rate": 1.1247288696332219e-05, + "loss": 0.0233, + "step": 30851 + }, + { + "epoch": 9.53, + "learning_rate": 1.1246792482039261e-05, + "loss": 0.0232, + "step": 30852 + }, + { + "epoch": 9.53, + "learning_rate": 1.1246296264627845e-05, + "loss": 0.0214, + "step": 30853 + }, + { + "epoch": 9.53, + "learning_rate": 1.1245800044099215e-05, + "loss": 0.024, + "step": 30854 + }, + { + "epoch": 9.53, + "learning_rate": 1.1245303820454614e-05, + "loss": 0.019, + "step": 30855 + }, + { + "epoch": 9.53, + "learning_rate": 1.1244807593695278e-05, + "loss": 0.0212, + "step": 30856 + }, + { + "epoch": 9.53, + "learning_rate": 1.1244311363822454e-05, + "loss": 0.0241, + "step": 30857 + }, + { + "epoch": 9.53, + "learning_rate": 1.1243815130837376e-05, + "loss": 0.0221, + "step": 30858 + }, + { + "epoch": 9.53, + "learning_rate": 1.1243318894741292e-05, + "loss": 0.0226, + "step": 30859 + }, + { + "epoch": 9.53, + "learning_rate": 1.1242822655535444e-05, + "loss": 0.0215, + "step": 30860 + }, + { + "epoch": 9.53, + "learning_rate": 1.1242326413221063e-05, + "loss": 0.0205, + "step": 30861 + }, + { + "epoch": 9.53, + "learning_rate": 1.1241830167799404e-05, + "loss": 0.0232, + "step": 30862 + }, + { + "epoch": 9.53, + "learning_rate": 1.1241333919271697e-05, + "loss": 0.0241, + "step": 30863 + }, + { + "epoch": 9.53, + "learning_rate": 1.1240837667639188e-05, + "loss": 0.0234, + "step": 30864 + }, + { + "epoch": 9.53, + "learning_rate": 1.1240341412903119e-05, + "loss": 0.0239, + "step": 30865 + }, + { + "epoch": 9.53, + "learning_rate": 1.1239845155064731e-05, + "loss": 0.0217, + "step": 30866 + }, + { + "epoch": 9.53, + "learning_rate": 1.123934889412526e-05, + "loss": 0.0222, + "step": 30867 + }, + { + "epoch": 9.53, + "learning_rate": 1.1238852630085955e-05, + "loss": 0.0234, + "step": 30868 + }, + { + "epoch": 9.53, + "learning_rate": 1.1238356362948052e-05, + "loss": 0.0245, + "step": 30869 + }, + { + "epoch": 9.53, + "learning_rate": 1.1237860092712793e-05, + "loss": 0.0228, + "step": 30870 + }, + { + "epoch": 9.53, + "learning_rate": 1.1237363819381422e-05, + "loss": 0.0227, + "step": 30871 + }, + { + "epoch": 9.53, + "learning_rate": 1.1236867542955179e-05, + "loss": 0.0239, + "step": 30872 + }, + { + "epoch": 9.53, + "learning_rate": 1.1236371263435302e-05, + "loss": 0.0203, + "step": 30873 + }, + { + "epoch": 9.53, + "learning_rate": 1.1235874980823035e-05, + "loss": 0.0242, + "step": 30874 + }, + { + "epoch": 9.53, + "learning_rate": 1.1235378695119623e-05, + "loss": 0.0218, + "step": 30875 + }, + { + "epoch": 9.54, + "learning_rate": 1.12348824063263e-05, + "loss": 0.0208, + "step": 30876 + }, + { + "epoch": 9.54, + "learning_rate": 1.1234386114444313e-05, + "loss": 0.0252, + "step": 30877 + }, + { + "epoch": 9.54, + "learning_rate": 1.1233889819474899e-05, + "loss": 0.0233, + "step": 30878 + }, + { + "epoch": 9.54, + "learning_rate": 1.1233393521419302e-05, + "loss": 0.0214, + "step": 30879 + }, + { + "epoch": 9.54, + "learning_rate": 1.1232897220278764e-05, + "loss": 0.0239, + "step": 30880 + }, + { + "epoch": 9.54, + "learning_rate": 1.1232400916054527e-05, + "loss": 0.0238, + "step": 30881 + }, + { + "epoch": 9.54, + "learning_rate": 1.1231904608747825e-05, + "loss": 0.0216, + "step": 30882 + }, + { + "epoch": 9.54, + "learning_rate": 1.1231408298359911e-05, + "loss": 0.0219, + "step": 30883 + }, + { + "epoch": 9.54, + "learning_rate": 1.1230911984892016e-05, + "loss": 0.0245, + "step": 30884 + }, + { + "epoch": 9.54, + "learning_rate": 1.1230415668345387e-05, + "loss": 0.0258, + "step": 30885 + }, + { + "epoch": 9.54, + "learning_rate": 1.1229919348721268e-05, + "loss": 0.021, + "step": 30886 + }, + { + "epoch": 9.54, + "learning_rate": 1.1229423026020889e-05, + "loss": 0.0233, + "step": 30887 + }, + { + "epoch": 9.54, + "learning_rate": 1.1228926700245503e-05, + "loss": 0.025, + "step": 30888 + }, + { + "epoch": 9.54, + "learning_rate": 1.1228430371396349e-05, + "loss": 0.0249, + "step": 30889 + }, + { + "epoch": 9.54, + "learning_rate": 1.1227934039474659e-05, + "loss": 0.0222, + "step": 30890 + }, + { + "epoch": 9.54, + "learning_rate": 1.122743770448169e-05, + "loss": 0.0205, + "step": 30891 + }, + { + "epoch": 9.54, + "learning_rate": 1.1226941366418672e-05, + "loss": 0.0248, + "step": 30892 + }, + { + "epoch": 9.54, + "learning_rate": 1.1226445025286852e-05, + "loss": 0.0206, + "step": 30893 + }, + { + "epoch": 9.54, + "learning_rate": 1.1225948681087467e-05, + "loss": 0.025, + "step": 30894 + }, + { + "epoch": 9.54, + "learning_rate": 1.1225452333821758e-05, + "loss": 0.0226, + "step": 30895 + }, + { + "epoch": 9.54, + "learning_rate": 1.1224955983490975e-05, + "loss": 0.0265, + "step": 30896 + }, + { + "epoch": 9.54, + "learning_rate": 1.1224459630096351e-05, + "loss": 0.0217, + "step": 30897 + }, + { + "epoch": 9.54, + "learning_rate": 1.1223963273639132e-05, + "loss": 0.0207, + "step": 30898 + }, + { + "epoch": 9.54, + "learning_rate": 1.1223466914120556e-05, + "loss": 0.0225, + "step": 30899 + }, + { + "epoch": 9.54, + "learning_rate": 1.1222970551541865e-05, + "loss": 0.0213, + "step": 30900 + }, + { + "epoch": 9.54, + "learning_rate": 1.1222474185904301e-05, + "loss": 0.0225, + "step": 30901 + }, + { + "epoch": 9.54, + "learning_rate": 1.122197781720911e-05, + "loss": 0.0241, + "step": 30902 + }, + { + "epoch": 9.54, + "learning_rate": 1.1221481445457528e-05, + "loss": 0.0242, + "step": 30903 + }, + { + "epoch": 9.54, + "learning_rate": 1.1220985070650797e-05, + "loss": 0.0225, + "step": 30904 + }, + { + "epoch": 9.54, + "learning_rate": 1.122048869279016e-05, + "loss": 0.0223, + "step": 30905 + }, + { + "epoch": 9.54, + "learning_rate": 1.1219992311876858e-05, + "loss": 0.022, + "step": 30906 + }, + { + "epoch": 9.54, + "learning_rate": 1.1219495927912132e-05, + "loss": 0.0237, + "step": 30907 + }, + { + "epoch": 9.55, + "learning_rate": 1.1218999540897227e-05, + "loss": 0.0244, + "step": 30908 + }, + { + "epoch": 9.55, + "learning_rate": 1.121850315083338e-05, + "loss": 0.0221, + "step": 30909 + }, + { + "epoch": 9.55, + "learning_rate": 1.1218006757721834e-05, + "loss": 0.0251, + "step": 30910 + }, + { + "epoch": 9.55, + "learning_rate": 1.1217510361563833e-05, + "loss": 0.0229, + "step": 30911 + }, + { + "epoch": 9.55, + "learning_rate": 1.1217013962360612e-05, + "loss": 0.0211, + "step": 30912 + }, + { + "epoch": 9.55, + "learning_rate": 1.121651756011342e-05, + "loss": 0.0222, + "step": 30913 + }, + { + "epoch": 9.55, + "learning_rate": 1.1216021154823499e-05, + "loss": 0.0225, + "step": 30914 + }, + { + "epoch": 9.55, + "learning_rate": 1.1215524746492081e-05, + "loss": 0.022, + "step": 30915 + }, + { + "epoch": 9.55, + "learning_rate": 1.1215028335120417e-05, + "loss": 0.0258, + "step": 30916 + }, + { + "epoch": 9.55, + "learning_rate": 1.1214531920709747e-05, + "loss": 0.0202, + "step": 30917 + }, + { + "epoch": 9.55, + "learning_rate": 1.1214035503261309e-05, + "loss": 0.0218, + "step": 30918 + }, + { + "epoch": 9.55, + "learning_rate": 1.1213539082776351e-05, + "loss": 0.0228, + "step": 30919 + }, + { + "epoch": 9.55, + "learning_rate": 1.1213042659256106e-05, + "loss": 0.0222, + "step": 30920 + }, + { + "epoch": 9.55, + "learning_rate": 1.1212546232701818e-05, + "loss": 0.022, + "step": 30921 + }, + { + "epoch": 9.55, + "learning_rate": 1.1212049803114736e-05, + "loss": 0.0229, + "step": 30922 + }, + { + "epoch": 9.55, + "learning_rate": 1.1211553370496092e-05, + "loss": 0.0262, + "step": 30923 + }, + { + "epoch": 9.55, + "learning_rate": 1.1211056934847136e-05, + "loss": 0.0222, + "step": 30924 + }, + { + "epoch": 9.55, + "learning_rate": 1.1210560496169103e-05, + "loss": 0.026, + "step": 30925 + }, + { + "epoch": 9.55, + "learning_rate": 1.1210064054463237e-05, + "loss": 0.0233, + "step": 30926 + }, + { + "epoch": 9.55, + "learning_rate": 1.1209567609730782e-05, + "loss": 0.0253, + "step": 30927 + }, + { + "epoch": 9.55, + "learning_rate": 1.1209071161972977e-05, + "loss": 0.0242, + "step": 30928 + }, + { + "epoch": 9.55, + "learning_rate": 1.1208574711191065e-05, + "loss": 0.0203, + "step": 30929 + }, + { + "epoch": 9.55, + "learning_rate": 1.1208078257386287e-05, + "loss": 0.0228, + "step": 30930 + }, + { + "epoch": 9.55, + "learning_rate": 1.1207581800559886e-05, + "loss": 0.0218, + "step": 30931 + }, + { + "epoch": 9.55, + "learning_rate": 1.12070853407131e-05, + "loss": 0.0216, + "step": 30932 + }, + { + "epoch": 9.55, + "learning_rate": 1.1206588877847175e-05, + "loss": 0.024, + "step": 30933 + }, + { + "epoch": 9.55, + "learning_rate": 1.1206092411963352e-05, + "loss": 0.0226, + "step": 30934 + }, + { + "epoch": 9.55, + "learning_rate": 1.120559594306287e-05, + "loss": 0.0228, + "step": 30935 + }, + { + "epoch": 9.55, + "learning_rate": 1.1205099471146974e-05, + "loss": 0.0206, + "step": 30936 + }, + { + "epoch": 9.55, + "learning_rate": 1.1204602996216906e-05, + "loss": 0.0227, + "step": 30937 + }, + { + "epoch": 9.55, + "learning_rate": 1.12041065182739e-05, + "loss": 0.0241, + "step": 30938 + }, + { + "epoch": 9.55, + "learning_rate": 1.120361003731921e-05, + "loss": 0.0222, + "step": 30939 + }, + { + "epoch": 9.55, + "learning_rate": 1.120311355335407e-05, + "loss": 0.0244, + "step": 30940 + }, + { + "epoch": 9.56, + "learning_rate": 1.1202617066379724e-05, + "loss": 0.0206, + "step": 30941 + }, + { + "epoch": 9.56, + "learning_rate": 1.1202120576397415e-05, + "loss": 0.0226, + "step": 30942 + }, + { + "epoch": 9.56, + "learning_rate": 1.1201624083408378e-05, + "loss": 0.0211, + "step": 30943 + }, + { + "epoch": 9.56, + "learning_rate": 1.1201127587413863e-05, + "loss": 0.0222, + "step": 30944 + }, + { + "epoch": 9.56, + "learning_rate": 1.120063108841511e-05, + "loss": 0.0211, + "step": 30945 + }, + { + "epoch": 9.56, + "learning_rate": 1.1200134586413358e-05, + "loss": 0.0245, + "step": 30946 + }, + { + "epoch": 9.56, + "learning_rate": 1.1199638081409852e-05, + "loss": 0.0211, + "step": 30947 + }, + { + "epoch": 9.56, + "learning_rate": 1.1199141573405831e-05, + "loss": 0.0211, + "step": 30948 + }, + { + "epoch": 9.56, + "learning_rate": 1.1198645062402538e-05, + "loss": 0.0211, + "step": 30949 + }, + { + "epoch": 9.56, + "learning_rate": 1.1198148548401217e-05, + "loss": 0.0206, + "step": 30950 + }, + { + "epoch": 9.56, + "learning_rate": 1.1197652031403108e-05, + "loss": 0.0251, + "step": 30951 + }, + { + "epoch": 9.56, + "learning_rate": 1.119715551140945e-05, + "loss": 0.0228, + "step": 30952 + }, + { + "epoch": 9.56, + "learning_rate": 1.119665898842149e-05, + "loss": 0.0205, + "step": 30953 + }, + { + "epoch": 9.56, + "learning_rate": 1.1196162462440467e-05, + "loss": 0.0206, + "step": 30954 + }, + { + "epoch": 9.56, + "learning_rate": 1.1195665933467623e-05, + "loss": 0.0249, + "step": 30955 + }, + { + "epoch": 9.56, + "learning_rate": 1.1195169401504201e-05, + "loss": 0.0224, + "step": 30956 + }, + { + "epoch": 9.56, + "learning_rate": 1.119467286655144e-05, + "loss": 0.0227, + "step": 30957 + }, + { + "epoch": 9.56, + "learning_rate": 1.1194176328610589e-05, + "loss": 0.0218, + "step": 30958 + }, + { + "epoch": 9.56, + "learning_rate": 1.119367978768288e-05, + "loss": 0.0226, + "step": 30959 + }, + { + "epoch": 9.56, + "learning_rate": 1.1193183243769563e-05, + "loss": 0.0251, + "step": 30960 + }, + { + "epoch": 9.56, + "learning_rate": 1.1192686696871877e-05, + "loss": 0.0242, + "step": 30961 + }, + { + "epoch": 9.56, + "learning_rate": 1.1192190146991064e-05, + "loss": 0.0217, + "step": 30962 + }, + { + "epoch": 9.56, + "learning_rate": 1.1191693594128366e-05, + "loss": 0.0247, + "step": 30963 + }, + { + "epoch": 9.56, + "learning_rate": 1.1191197038285024e-05, + "loss": 0.0217, + "step": 30964 + }, + { + "epoch": 9.56, + "learning_rate": 1.1190700479462283e-05, + "loss": 0.0245, + "step": 30965 + }, + { + "epoch": 9.56, + "learning_rate": 1.1190203917661382e-05, + "loss": 0.0229, + "step": 30966 + }, + { + "epoch": 9.56, + "learning_rate": 1.1189707352883563e-05, + "loss": 0.0246, + "step": 30967 + }, + { + "epoch": 9.56, + "learning_rate": 1.1189210785130072e-05, + "loss": 0.0214, + "step": 30968 + }, + { + "epoch": 9.56, + "learning_rate": 1.1188714214402144e-05, + "loss": 0.0236, + "step": 30969 + }, + { + "epoch": 9.56, + "learning_rate": 1.1188217640701024e-05, + "loss": 0.0223, + "step": 30970 + }, + { + "epoch": 9.56, + "learning_rate": 1.1187721064027961e-05, + "loss": 0.025, + "step": 30971 + }, + { + "epoch": 9.56, + "learning_rate": 1.1187224484384184e-05, + "loss": 0.0218, + "step": 30972 + }, + { + "epoch": 9.57, + "learning_rate": 1.1186727901770948e-05, + "loss": 0.0229, + "step": 30973 + }, + { + "epoch": 9.57, + "learning_rate": 1.1186231316189484e-05, + "loss": 0.0221, + "step": 30974 + }, + { + "epoch": 9.57, + "learning_rate": 1.1185734727641043e-05, + "loss": 0.0222, + "step": 30975 + }, + { + "epoch": 9.57, + "learning_rate": 1.1185238136126863e-05, + "loss": 0.0251, + "step": 30976 + }, + { + "epoch": 9.57, + "learning_rate": 1.1184741541648183e-05, + "loss": 0.0211, + "step": 30977 + }, + { + "epoch": 9.57, + "learning_rate": 1.1184244944206253e-05, + "loss": 0.0196, + "step": 30978 + }, + { + "epoch": 9.57, + "learning_rate": 1.1183748343802307e-05, + "loss": 0.0227, + "step": 30979 + }, + { + "epoch": 9.57, + "learning_rate": 1.1183251740437589e-05, + "loss": 0.0233, + "step": 30980 + }, + { + "epoch": 9.57, + "learning_rate": 1.1182755134113348e-05, + "loss": 0.0228, + "step": 30981 + }, + { + "epoch": 9.57, + "learning_rate": 1.1182258524830816e-05, + "loss": 0.021, + "step": 30982 + }, + { + "epoch": 9.57, + "learning_rate": 1.1181761912591243e-05, + "loss": 0.0207, + "step": 30983 + }, + { + "epoch": 9.57, + "learning_rate": 1.1181265297395865e-05, + "loss": 0.0221, + "step": 30984 + }, + { + "epoch": 9.57, + "learning_rate": 1.1180768679245928e-05, + "loss": 0.022, + "step": 30985 + }, + { + "epoch": 9.57, + "learning_rate": 1.1180272058142675e-05, + "loss": 0.0244, + "step": 30986 + }, + { + "epoch": 9.57, + "learning_rate": 1.1179775434087344e-05, + "loss": 0.0234, + "step": 30987 + }, + { + "epoch": 9.57, + "learning_rate": 1.117927880708118e-05, + "loss": 0.0231, + "step": 30988 + }, + { + "epoch": 9.57, + "learning_rate": 1.1178782177125424e-05, + "loss": 0.023, + "step": 30989 + }, + { + "epoch": 9.57, + "learning_rate": 1.1178285544221318e-05, + "loss": 0.0233, + "step": 30990 + }, + { + "epoch": 9.57, + "learning_rate": 1.1177788908370108e-05, + "loss": 0.0236, + "step": 30991 + }, + { + "epoch": 9.57, + "learning_rate": 1.1177292269573032e-05, + "loss": 0.022, + "step": 30992 + }, + { + "epoch": 9.57, + "learning_rate": 1.1176795627831335e-05, + "loss": 0.0208, + "step": 30993 + }, + { + "epoch": 9.57, + "learning_rate": 1.1176298983146254e-05, + "loss": 0.0225, + "step": 30994 + }, + { + "epoch": 9.57, + "learning_rate": 1.1175802335519035e-05, + "loss": 0.0183, + "step": 30995 + }, + { + "epoch": 9.57, + "learning_rate": 1.1175305684950923e-05, + "loss": 0.0252, + "step": 30996 + }, + { + "epoch": 9.57, + "learning_rate": 1.1174809031443155e-05, + "loss": 0.0227, + "step": 30997 + }, + { + "epoch": 9.57, + "learning_rate": 1.1174312374996973e-05, + "loss": 0.0225, + "step": 30998 + }, + { + "epoch": 9.57, + "learning_rate": 1.1173815715613628e-05, + "loss": 0.0219, + "step": 30999 + }, + { + "epoch": 9.57, + "learning_rate": 1.117331905329435e-05, + "loss": 0.0212, + "step": 31000 + }, + { + "epoch": 9.57, + "learning_rate": 1.117282238804039e-05, + "loss": 0.02, + "step": 31001 + }, + { + "epoch": 9.57, + "learning_rate": 1.1172325719852986e-05, + "loss": 0.0222, + "step": 31002 + }, + { + "epoch": 9.57, + "learning_rate": 1.117182904873338e-05, + "loss": 0.022, + "step": 31003 + }, + { + "epoch": 9.57, + "learning_rate": 1.1171332374682819e-05, + "loss": 0.0234, + "step": 31004 + }, + { + "epoch": 9.57, + "learning_rate": 1.117083569770254e-05, + "loss": 0.0254, + "step": 31005 + }, + { + "epoch": 9.58, + "learning_rate": 1.117033901779379e-05, + "loss": 0.02, + "step": 31006 + }, + { + "epoch": 9.58, + "learning_rate": 1.1169842334957806e-05, + "loss": 0.0235, + "step": 31007 + }, + { + "epoch": 9.58, + "learning_rate": 1.116934564919583e-05, + "loss": 0.0215, + "step": 31008 + }, + { + "epoch": 9.58, + "learning_rate": 1.1168848960509116e-05, + "loss": 0.0225, + "step": 31009 + }, + { + "epoch": 9.58, + "learning_rate": 1.1168352268898891e-05, + "loss": 0.0219, + "step": 31010 + }, + { + "epoch": 9.58, + "learning_rate": 1.1167855574366406e-05, + "loss": 0.0212, + "step": 31011 + }, + { + "epoch": 9.58, + "learning_rate": 1.11673588769129e-05, + "loss": 0.0243, + "step": 31012 + }, + { + "epoch": 9.58, + "learning_rate": 1.1166862176539617e-05, + "loss": 0.0244, + "step": 31013 + }, + { + "epoch": 9.58, + "learning_rate": 1.11663654732478e-05, + "loss": 0.0234, + "step": 31014 + }, + { + "epoch": 9.58, + "learning_rate": 1.1165868767038688e-05, + "loss": 0.0254, + "step": 31015 + }, + { + "epoch": 9.58, + "learning_rate": 1.1165372057913528e-05, + "loss": 0.0215, + "step": 31016 + }, + { + "epoch": 9.58, + "learning_rate": 1.1164875345873558e-05, + "loss": 0.0238, + "step": 31017 + }, + { + "epoch": 9.58, + "learning_rate": 1.1164378630920023e-05, + "loss": 0.0204, + "step": 31018 + }, + { + "epoch": 9.58, + "learning_rate": 1.1163881913054164e-05, + "loss": 0.0228, + "step": 31019 + }, + { + "epoch": 9.58, + "learning_rate": 1.1163385192277226e-05, + "loss": 0.0233, + "step": 31020 + }, + { + "epoch": 9.58, + "learning_rate": 1.1162888468590448e-05, + "loss": 0.0223, + "step": 31021 + }, + { + "epoch": 9.58, + "learning_rate": 1.1162391741995074e-05, + "loss": 0.0214, + "step": 31022 + }, + { + "epoch": 9.58, + "learning_rate": 1.1161895012492345e-05, + "loss": 0.0232, + "step": 31023 + }, + { + "epoch": 9.58, + "learning_rate": 1.1161398280083507e-05, + "loss": 0.0197, + "step": 31024 + }, + { + "epoch": 9.58, + "learning_rate": 1.11609015447698e-05, + "loss": 0.0225, + "step": 31025 + }, + { + "epoch": 9.58, + "learning_rate": 1.1160404806552465e-05, + "loss": 0.0255, + "step": 31026 + }, + { + "epoch": 9.58, + "learning_rate": 1.1159908065432748e-05, + "loss": 0.0246, + "step": 31027 + }, + { + "epoch": 9.58, + "learning_rate": 1.1159411321411885e-05, + "loss": 0.0247, + "step": 31028 + }, + { + "epoch": 9.58, + "learning_rate": 1.1158914574491127e-05, + "loss": 0.0252, + "step": 31029 + }, + { + "epoch": 9.58, + "learning_rate": 1.1158417824671712e-05, + "loss": 0.0212, + "step": 31030 + }, + { + "epoch": 9.58, + "learning_rate": 1.115792107195488e-05, + "loss": 0.0238, + "step": 31031 + }, + { + "epoch": 9.58, + "learning_rate": 1.1157424316341881e-05, + "loss": 0.0205, + "step": 31032 + }, + { + "epoch": 9.58, + "learning_rate": 1.115692755783395e-05, + "loss": 0.0227, + "step": 31033 + }, + { + "epoch": 9.58, + "learning_rate": 1.115643079643233e-05, + "loss": 0.0224, + "step": 31034 + }, + { + "epoch": 9.58, + "learning_rate": 1.1155934032138267e-05, + "loss": 0.0228, + "step": 31035 + }, + { + "epoch": 9.58, + "learning_rate": 1.1155437264953005e-05, + "loss": 0.0198, + "step": 31036 + }, + { + "epoch": 9.58, + "learning_rate": 1.115494049487778e-05, + "loss": 0.0218, + "step": 31037 + }, + { + "epoch": 9.59, + "learning_rate": 1.1154443721913838e-05, + "loss": 0.0205, + "step": 31038 + }, + { + "epoch": 9.59, + "learning_rate": 1.1153946946062421e-05, + "loss": 0.0215, + "step": 31039 + }, + { + "epoch": 9.59, + "learning_rate": 1.1153450167324778e-05, + "loss": 0.0235, + "step": 31040 + }, + { + "epoch": 9.59, + "learning_rate": 1.115295338570214e-05, + "loss": 0.0217, + "step": 31041 + }, + { + "epoch": 9.59, + "learning_rate": 1.1152456601195758e-05, + "loss": 0.0226, + "step": 31042 + }, + { + "epoch": 9.59, + "learning_rate": 1.1151959813806873e-05, + "loss": 0.0233, + "step": 31043 + }, + { + "epoch": 9.59, + "learning_rate": 1.1151463023536723e-05, + "loss": 0.0216, + "step": 31044 + }, + { + "epoch": 9.59, + "learning_rate": 1.1150966230386555e-05, + "loss": 0.0221, + "step": 31045 + }, + { + "epoch": 9.59, + "learning_rate": 1.115046943435761e-05, + "loss": 0.0205, + "step": 31046 + }, + { + "epoch": 9.59, + "learning_rate": 1.1149972635451134e-05, + "loss": 0.0228, + "step": 31047 + }, + { + "epoch": 9.59, + "learning_rate": 1.1149475833668365e-05, + "loss": 0.0227, + "step": 31048 + }, + { + "epoch": 9.59, + "learning_rate": 1.1148979029010547e-05, + "loss": 0.0263, + "step": 31049 + }, + { + "epoch": 9.59, + "learning_rate": 1.1148482221478927e-05, + "loss": 0.0218, + "step": 31050 + }, + { + "epoch": 9.59, + "learning_rate": 1.1147985411074735e-05, + "loss": 0.0235, + "step": 31051 + }, + { + "epoch": 9.59, + "learning_rate": 1.1147488597799227e-05, + "loss": 0.0204, + "step": 31052 + }, + { + "epoch": 9.59, + "learning_rate": 1.1146991781653644e-05, + "loss": 0.0217, + "step": 31053 + }, + { + "epoch": 9.59, + "learning_rate": 1.1146494962639219e-05, + "loss": 0.0215, + "step": 31054 + }, + { + "epoch": 9.59, + "learning_rate": 1.1145998140757205e-05, + "loss": 0.0247, + "step": 31055 + }, + { + "epoch": 9.59, + "learning_rate": 1.1145501316008837e-05, + "loss": 0.0234, + "step": 31056 + }, + { + "epoch": 9.59, + "learning_rate": 1.1145004488395366e-05, + "loss": 0.0228, + "step": 31057 + }, + { + "epoch": 9.59, + "learning_rate": 1.114450765791803e-05, + "loss": 0.0244, + "step": 31058 + }, + { + "epoch": 9.59, + "learning_rate": 1.1144010824578066e-05, + "loss": 0.0242, + "step": 31059 + }, + { + "epoch": 9.59, + "learning_rate": 1.1143513988376727e-05, + "loss": 0.0223, + "step": 31060 + }, + { + "epoch": 9.59, + "learning_rate": 1.1143017149315249e-05, + "loss": 0.023, + "step": 31061 + }, + { + "epoch": 9.59, + "learning_rate": 1.1142520307394875e-05, + "loss": 0.025, + "step": 31062 + }, + { + "epoch": 9.59, + "learning_rate": 1.1142023462616853e-05, + "loss": 0.0218, + "step": 31063 + }, + { + "epoch": 9.59, + "learning_rate": 1.1141526614982421e-05, + "loss": 0.0234, + "step": 31064 + }, + { + "epoch": 9.59, + "learning_rate": 1.1141029764492824e-05, + "loss": 0.0215, + "step": 31065 + }, + { + "epoch": 9.59, + "learning_rate": 1.11405329111493e-05, + "loss": 0.0203, + "step": 31066 + }, + { + "epoch": 9.59, + "learning_rate": 1.1140036054953096e-05, + "loss": 0.0234, + "step": 31067 + }, + { + "epoch": 9.59, + "learning_rate": 1.1139539195905455e-05, + "loss": 0.0209, + "step": 31068 + }, + { + "epoch": 9.59, + "learning_rate": 1.113904233400762e-05, + "loss": 0.0206, + "step": 31069 + }, + { + "epoch": 9.6, + "learning_rate": 1.113854546926083e-05, + "loss": 0.0209, + "step": 31070 + }, + { + "epoch": 9.6, + "learning_rate": 1.113804860166633e-05, + "loss": 0.0239, + "step": 31071 + }, + { + "epoch": 9.6, + "learning_rate": 1.1137551731225365e-05, + "loss": 0.0231, + "step": 31072 + }, + { + "epoch": 9.6, + "learning_rate": 1.1137054857939174e-05, + "loss": 0.0217, + "step": 31073 + }, + { + "epoch": 9.6, + "learning_rate": 1.1136557981809001e-05, + "loss": 0.0239, + "step": 31074 + }, + { + "epoch": 9.6, + "learning_rate": 1.1136061102836092e-05, + "loss": 0.0239, + "step": 31075 + }, + { + "epoch": 9.6, + "learning_rate": 1.1135564221021684e-05, + "loss": 0.0248, + "step": 31076 + }, + { + "epoch": 9.6, + "learning_rate": 1.1135067336367023e-05, + "loss": 0.025, + "step": 31077 + }, + { + "epoch": 9.6, + "learning_rate": 1.1134570448873352e-05, + "loss": 0.0233, + "step": 31078 + }, + { + "epoch": 9.6, + "learning_rate": 1.1134073558541913e-05, + "loss": 0.0225, + "step": 31079 + }, + { + "epoch": 9.6, + "learning_rate": 1.113357666537395e-05, + "loss": 0.0213, + "step": 31080 + }, + { + "epoch": 9.6, + "learning_rate": 1.1133079769370706e-05, + "loss": 0.0255, + "step": 31081 + }, + { + "epoch": 9.6, + "learning_rate": 1.1132582870533422e-05, + "loss": 0.0243, + "step": 31082 + }, + { + "epoch": 9.6, + "learning_rate": 1.113208596886334e-05, + "loss": 0.0223, + "step": 31083 + }, + { + "epoch": 9.6, + "learning_rate": 1.1131589064361707e-05, + "loss": 0.0249, + "step": 31084 + }, + { + "epoch": 9.6, + "learning_rate": 1.1131092157029762e-05, + "loss": 0.0216, + "step": 31085 + }, + { + "epoch": 9.6, + "learning_rate": 1.1130595246868751e-05, + "loss": 0.0244, + "step": 31086 + }, + { + "epoch": 9.6, + "learning_rate": 1.113009833387991e-05, + "loss": 0.0254, + "step": 31087 + }, + { + "epoch": 9.6, + "learning_rate": 1.112960141806449e-05, + "loss": 0.0225, + "step": 31088 + }, + { + "epoch": 9.6, + "learning_rate": 1.1129104499423735e-05, + "loss": 0.0246, + "step": 31089 + }, + { + "epoch": 9.6, + "learning_rate": 1.1128607577958879e-05, + "loss": 0.0195, + "step": 31090 + }, + { + "epoch": 9.6, + "learning_rate": 1.1128110653671172e-05, + "loss": 0.0233, + "step": 31091 + }, + { + "epoch": 9.6, + "learning_rate": 1.1127613726561852e-05, + "loss": 0.0227, + "step": 31092 + }, + { + "epoch": 9.6, + "learning_rate": 1.1127116796632165e-05, + "loss": 0.0228, + "step": 31093 + }, + { + "epoch": 9.6, + "learning_rate": 1.1126619863883355e-05, + "loss": 0.0239, + "step": 31094 + }, + { + "epoch": 9.6, + "learning_rate": 1.1126122928316664e-05, + "loss": 0.0231, + "step": 31095 + }, + { + "epoch": 9.6, + "learning_rate": 1.112562598993333e-05, + "loss": 0.0229, + "step": 31096 + }, + { + "epoch": 9.6, + "learning_rate": 1.1125129048734602e-05, + "loss": 0.0222, + "step": 31097 + }, + { + "epoch": 9.6, + "learning_rate": 1.1124632104721722e-05, + "loss": 0.0221, + "step": 31098 + }, + { + "epoch": 9.6, + "learning_rate": 1.1124135157895932e-05, + "loss": 0.023, + "step": 31099 + }, + { + "epoch": 9.6, + "learning_rate": 1.1123638208258473e-05, + "loss": 0.021, + "step": 31100 + }, + { + "epoch": 9.6, + "learning_rate": 1.1123141255810592e-05, + "loss": 0.0203, + "step": 31101 + }, + { + "epoch": 9.6, + "learning_rate": 1.1122644300553529e-05, + "loss": 0.023, + "step": 31102 + }, + { + "epoch": 9.61, + "learning_rate": 1.1122147342488528e-05, + "loss": 0.0233, + "step": 31103 + }, + { + "epoch": 9.61, + "learning_rate": 1.112165038161683e-05, + "loss": 0.0216, + "step": 31104 + }, + { + "epoch": 9.61, + "learning_rate": 1.1121153417939683e-05, + "loss": 0.0233, + "step": 31105 + }, + { + "epoch": 9.61, + "learning_rate": 1.1120656451458325e-05, + "loss": 0.0239, + "step": 31106 + }, + { + "epoch": 9.61, + "learning_rate": 1.1120159482174002e-05, + "loss": 0.0206, + "step": 31107 + }, + { + "epoch": 9.61, + "learning_rate": 1.1119662510087954e-05, + "loss": 0.0238, + "step": 31108 + }, + { + "epoch": 9.61, + "learning_rate": 1.111916553520143e-05, + "loss": 0.0193, + "step": 31109 + }, + { + "epoch": 9.61, + "learning_rate": 1.1118668557515664e-05, + "loss": 0.026, + "step": 31110 + }, + { + "epoch": 9.61, + "learning_rate": 1.1118171577031904e-05, + "loss": 0.023, + "step": 31111 + }, + { + "epoch": 9.61, + "learning_rate": 1.1117674593751398e-05, + "loss": 0.0237, + "step": 31112 + }, + { + "epoch": 9.61, + "learning_rate": 1.1117177607675378e-05, + "loss": 0.0212, + "step": 31113 + }, + { + "epoch": 9.61, + "learning_rate": 1.1116680618805098e-05, + "loss": 0.0212, + "step": 31114 + }, + { + "epoch": 9.61, + "learning_rate": 1.1116183627141794e-05, + "loss": 0.0222, + "step": 31115 + }, + { + "epoch": 9.61, + "learning_rate": 1.1115686632686709e-05, + "loss": 0.021, + "step": 31116 + }, + { + "epoch": 9.61, + "learning_rate": 1.1115189635441093e-05, + "loss": 0.0248, + "step": 31117 + }, + { + "epoch": 9.61, + "learning_rate": 1.1114692635406179e-05, + "loss": 0.0252, + "step": 31118 + }, + { + "epoch": 9.61, + "learning_rate": 1.1114195632583218e-05, + "loss": 0.0229, + "step": 31119 + }, + { + "epoch": 9.61, + "learning_rate": 1.111369862697345e-05, + "loss": 0.02, + "step": 31120 + }, + { + "epoch": 9.61, + "learning_rate": 1.1113201618578117e-05, + "loss": 0.0265, + "step": 31121 + }, + { + "epoch": 9.61, + "learning_rate": 1.1112704607398469e-05, + "loss": 0.0229, + "step": 31122 + }, + { + "epoch": 9.61, + "learning_rate": 1.111220759343574e-05, + "loss": 0.0223, + "step": 31123 + }, + { + "epoch": 9.61, + "learning_rate": 1.1111710576691177e-05, + "loss": 0.023, + "step": 31124 + }, + { + "epoch": 9.61, + "learning_rate": 1.1111213557166025e-05, + "loss": 0.0223, + "step": 31125 + }, + { + "epoch": 9.61, + "learning_rate": 1.1110716534861523e-05, + "loss": 0.0228, + "step": 31126 + }, + { + "epoch": 9.61, + "learning_rate": 1.1110219509778917e-05, + "loss": 0.0234, + "step": 31127 + }, + { + "epoch": 9.61, + "learning_rate": 1.110972248191945e-05, + "loss": 0.0222, + "step": 31128 + }, + { + "epoch": 9.61, + "learning_rate": 1.1109225451284364e-05, + "loss": 0.0222, + "step": 31129 + }, + { + "epoch": 9.61, + "learning_rate": 1.1108728417874903e-05, + "loss": 0.0222, + "step": 31130 + }, + { + "epoch": 9.61, + "learning_rate": 1.1108231381692312e-05, + "loss": 0.0211, + "step": 31131 + }, + { + "epoch": 9.61, + "learning_rate": 1.1107734342737828e-05, + "loss": 0.0238, + "step": 31132 + }, + { + "epoch": 9.61, + "learning_rate": 1.1107237301012701e-05, + "loss": 0.0227, + "step": 31133 + }, + { + "epoch": 9.61, + "learning_rate": 1.1106740256518171e-05, + "loss": 0.0233, + "step": 31134 + }, + { + "epoch": 9.62, + "learning_rate": 1.1106243209255483e-05, + "loss": 0.0217, + "step": 31135 + }, + { + "epoch": 9.62, + "learning_rate": 1.1105746159225879e-05, + "loss": 0.0239, + "step": 31136 + }, + { + "epoch": 9.62, + "learning_rate": 1.11052491064306e-05, + "loss": 0.0227, + "step": 31137 + }, + { + "epoch": 9.62, + "learning_rate": 1.1104752050870892e-05, + "loss": 0.0223, + "step": 31138 + }, + { + "epoch": 9.62, + "learning_rate": 1.1104254992548e-05, + "loss": 0.0195, + "step": 31139 + }, + { + "epoch": 9.62, + "learning_rate": 1.1103757931463165e-05, + "loss": 0.0221, + "step": 31140 + }, + { + "epoch": 9.62, + "learning_rate": 1.1103260867617625e-05, + "loss": 0.0221, + "step": 31141 + }, + { + "epoch": 9.62, + "learning_rate": 1.1102763801012633e-05, + "loss": 0.0243, + "step": 31142 + }, + { + "epoch": 9.62, + "learning_rate": 1.1102266731649427e-05, + "loss": 0.0222, + "step": 31143 + }, + { + "epoch": 9.62, + "learning_rate": 1.110176965952925e-05, + "loss": 0.0231, + "step": 31144 + }, + { + "epoch": 9.62, + "learning_rate": 1.1101272584653347e-05, + "loss": 0.0233, + "step": 31145 + }, + { + "epoch": 9.62, + "learning_rate": 1.1100775507022959e-05, + "loss": 0.0235, + "step": 31146 + }, + { + "epoch": 9.62, + "learning_rate": 1.1100278426639331e-05, + "loss": 0.0216, + "step": 31147 + }, + { + "epoch": 9.62, + "learning_rate": 1.1099781343503707e-05, + "loss": 0.0201, + "step": 31148 + }, + { + "epoch": 9.62, + "learning_rate": 1.109928425761733e-05, + "loss": 0.0249, + "step": 31149 + }, + { + "epoch": 9.62, + "learning_rate": 1.109878716898144e-05, + "loss": 0.0218, + "step": 31150 + }, + { + "epoch": 9.62, + "learning_rate": 1.1098290077597282e-05, + "loss": 0.0219, + "step": 31151 + }, + { + "epoch": 9.62, + "learning_rate": 1.10977929834661e-05, + "loss": 0.0222, + "step": 31152 + }, + { + "epoch": 9.62, + "learning_rate": 1.1097295886589143e-05, + "loss": 0.0233, + "step": 31153 + }, + { + "epoch": 9.62, + "learning_rate": 1.1096798786967647e-05, + "loss": 0.0233, + "step": 31154 + }, + { + "epoch": 9.62, + "learning_rate": 1.1096301684602855e-05, + "loss": 0.027, + "step": 31155 + }, + { + "epoch": 9.62, + "learning_rate": 1.1095804579496013e-05, + "loss": 0.0219, + "step": 31156 + }, + { + "epoch": 9.62, + "learning_rate": 1.1095307471648365e-05, + "loss": 0.0225, + "step": 31157 + }, + { + "epoch": 9.62, + "learning_rate": 1.109481036106115e-05, + "loss": 0.0217, + "step": 31158 + }, + { + "epoch": 9.62, + "learning_rate": 1.1094313247735618e-05, + "loss": 0.0225, + "step": 31159 + }, + { + "epoch": 9.62, + "learning_rate": 1.1093816131673007e-05, + "loss": 0.0232, + "step": 31160 + }, + { + "epoch": 9.62, + "learning_rate": 1.1093319012874563e-05, + "loss": 0.0196, + "step": 31161 + }, + { + "epoch": 9.62, + "learning_rate": 1.109282189134153e-05, + "loss": 0.0237, + "step": 31162 + }, + { + "epoch": 9.62, + "learning_rate": 1.109232476707515e-05, + "loss": 0.0238, + "step": 31163 + }, + { + "epoch": 9.62, + "learning_rate": 1.1091827640076664e-05, + "loss": 0.0213, + "step": 31164 + }, + { + "epoch": 9.62, + "learning_rate": 1.109133051034732e-05, + "loss": 0.0218, + "step": 31165 + }, + { + "epoch": 9.62, + "learning_rate": 1.1090833377888361e-05, + "loss": 0.0202, + "step": 31166 + }, + { + "epoch": 9.63, + "learning_rate": 1.1090336242701026e-05, + "loss": 0.0217, + "step": 31167 + }, + { + "epoch": 9.63, + "learning_rate": 1.1089839104786565e-05, + "loss": 0.0217, + "step": 31168 + }, + { + "epoch": 9.63, + "learning_rate": 1.1089341964146212e-05, + "loss": 0.0233, + "step": 31169 + }, + { + "epoch": 9.63, + "learning_rate": 1.1088844820781218e-05, + "loss": 0.0249, + "step": 31170 + }, + { + "epoch": 9.63, + "learning_rate": 1.1088347674692827e-05, + "loss": 0.023, + "step": 31171 + }, + { + "epoch": 9.63, + "learning_rate": 1.1087850525882275e-05, + "loss": 0.0233, + "step": 31172 + }, + { + "epoch": 9.63, + "learning_rate": 1.1087353374350815e-05, + "loss": 0.0216, + "step": 31173 + }, + { + "epoch": 9.63, + "learning_rate": 1.1086856220099687e-05, + "loss": 0.0233, + "step": 31174 + }, + { + "epoch": 9.63, + "learning_rate": 1.1086359063130127e-05, + "loss": 0.0221, + "step": 31175 + }, + { + "epoch": 9.63, + "learning_rate": 1.1085861903443392e-05, + "loss": 0.0236, + "step": 31176 + }, + { + "epoch": 9.63, + "learning_rate": 1.1085364741040713e-05, + "loss": 0.0239, + "step": 31177 + }, + { + "epoch": 9.63, + "learning_rate": 1.108486757592334e-05, + "loss": 0.0205, + "step": 31178 + }, + { + "epoch": 9.63, + "learning_rate": 1.108437040809252e-05, + "loss": 0.0238, + "step": 31179 + }, + { + "epoch": 9.63, + "learning_rate": 1.1083873237549487e-05, + "loss": 0.0211, + "step": 31180 + }, + { + "epoch": 9.63, + "learning_rate": 1.108337606429549e-05, + "loss": 0.0232, + "step": 31181 + }, + { + "epoch": 9.63, + "learning_rate": 1.1082878888331772e-05, + "loss": 0.0227, + "step": 31182 + }, + { + "epoch": 9.63, + "learning_rate": 1.1082381709659576e-05, + "loss": 0.0232, + "step": 31183 + }, + { + "epoch": 9.63, + "learning_rate": 1.1081884528280147e-05, + "loss": 0.023, + "step": 31184 + }, + { + "epoch": 9.63, + "learning_rate": 1.1081387344194728e-05, + "loss": 0.0197, + "step": 31185 + }, + { + "epoch": 9.63, + "learning_rate": 1.108089015740456e-05, + "loss": 0.0229, + "step": 31186 + }, + { + "epoch": 9.63, + "learning_rate": 1.108039296791089e-05, + "loss": 0.0216, + "step": 31187 + }, + { + "epoch": 9.63, + "learning_rate": 1.107989577571496e-05, + "loss": 0.0218, + "step": 31188 + }, + { + "epoch": 9.63, + "learning_rate": 1.1079398580818012e-05, + "loss": 0.0211, + "step": 31189 + }, + { + "epoch": 9.63, + "learning_rate": 1.1078901383221293e-05, + "loss": 0.026, + "step": 31190 + }, + { + "epoch": 9.63, + "learning_rate": 1.1078404182926047e-05, + "loss": 0.0227, + "step": 31191 + }, + { + "epoch": 9.63, + "learning_rate": 1.107790697993351e-05, + "loss": 0.022, + "step": 31192 + }, + { + "epoch": 9.63, + "learning_rate": 1.1077409774244934e-05, + "loss": 0.0222, + "step": 31193 + }, + { + "epoch": 9.63, + "learning_rate": 1.1076912565861562e-05, + "loss": 0.0243, + "step": 31194 + }, + { + "epoch": 9.63, + "learning_rate": 1.1076415354784631e-05, + "loss": 0.0212, + "step": 31195 + }, + { + "epoch": 9.63, + "learning_rate": 1.1075918141015391e-05, + "loss": 0.0227, + "step": 31196 + }, + { + "epoch": 9.63, + "learning_rate": 1.1075420924555085e-05, + "loss": 0.0267, + "step": 31197 + }, + { + "epoch": 9.63, + "learning_rate": 1.1074923705404952e-05, + "loss": 0.0219, + "step": 31198 + }, + { + "epoch": 9.63, + "learning_rate": 1.1074426483566242e-05, + "loss": 0.0267, + "step": 31199 + }, + { + "epoch": 9.64, + "learning_rate": 1.1073929259040195e-05, + "loss": 0.0238, + "step": 31200 + }, + { + "epoch": 9.64, + "learning_rate": 1.1073432031828051e-05, + "loss": 0.023, + "step": 31201 + }, + { + "epoch": 9.64, + "learning_rate": 1.1072934801931062e-05, + "loss": 0.0209, + "step": 31202 + }, + { + "epoch": 9.64, + "learning_rate": 1.1072437569350462e-05, + "loss": 0.0238, + "step": 31203 + }, + { + "epoch": 9.64, + "learning_rate": 1.1071940334087507e-05, + "loss": 0.0218, + "step": 31204 + }, + { + "epoch": 9.64, + "learning_rate": 1.107144309614343e-05, + "loss": 0.0222, + "step": 31205 + }, + { + "epoch": 9.64, + "learning_rate": 1.1070945855519478e-05, + "loss": 0.022, + "step": 31206 + }, + { + "epoch": 9.64, + "learning_rate": 1.1070448612216898e-05, + "loss": 0.0242, + "step": 31207 + }, + { + "epoch": 9.64, + "learning_rate": 1.1069951366236928e-05, + "loss": 0.0249, + "step": 31208 + }, + { + "epoch": 9.64, + "learning_rate": 1.1069454117580816e-05, + "loss": 0.0225, + "step": 31209 + }, + { + "epoch": 9.64, + "learning_rate": 1.1068956866249802e-05, + "loss": 0.0239, + "step": 31210 + }, + { + "epoch": 9.64, + "learning_rate": 1.1068459612245135e-05, + "loss": 0.027, + "step": 31211 + }, + { + "epoch": 9.64, + "learning_rate": 1.1067962355568054e-05, + "loss": 0.0237, + "step": 31212 + }, + { + "epoch": 9.64, + "learning_rate": 1.1067465096219803e-05, + "loss": 0.0243, + "step": 31213 + }, + { + "epoch": 9.64, + "learning_rate": 1.106696783420163e-05, + "loss": 0.022, + "step": 31214 + }, + { + "epoch": 9.64, + "learning_rate": 1.1066470569514773e-05, + "loss": 0.0254, + "step": 31215 + }, + { + "epoch": 9.64, + "learning_rate": 1.106597330216048e-05, + "loss": 0.0227, + "step": 31216 + }, + { + "epoch": 9.64, + "learning_rate": 1.1065476032139993e-05, + "loss": 0.0239, + "step": 31217 + }, + { + "epoch": 9.64, + "learning_rate": 1.1064978759454556e-05, + "loss": 0.0247, + "step": 31218 + }, + { + "epoch": 9.64, + "learning_rate": 1.1064481484105413e-05, + "loss": 0.0215, + "step": 31219 + }, + { + "epoch": 9.64, + "learning_rate": 1.1063984206093808e-05, + "loss": 0.0236, + "step": 31220 + }, + { + "epoch": 9.64, + "learning_rate": 1.1063486925420985e-05, + "loss": 0.0217, + "step": 31221 + }, + { + "epoch": 9.64, + "learning_rate": 1.1062989642088186e-05, + "loss": 0.0247, + "step": 31222 + }, + { + "epoch": 9.64, + "learning_rate": 1.1062492356096657e-05, + "loss": 0.0219, + "step": 31223 + }, + { + "epoch": 9.64, + "learning_rate": 1.106199506744764e-05, + "loss": 0.0227, + "step": 31224 + }, + { + "epoch": 9.64, + "learning_rate": 1.1061497776142382e-05, + "loss": 0.0213, + "step": 31225 + }, + { + "epoch": 9.64, + "learning_rate": 1.1061000482182121e-05, + "loss": 0.0233, + "step": 31226 + }, + { + "epoch": 9.64, + "learning_rate": 1.1060503185568105e-05, + "loss": 0.0241, + "step": 31227 + }, + { + "epoch": 9.64, + "learning_rate": 1.106000588630158e-05, + "loss": 0.0222, + "step": 31228 + }, + { + "epoch": 9.64, + "learning_rate": 1.1059508584383782e-05, + "loss": 0.0224, + "step": 31229 + }, + { + "epoch": 9.64, + "learning_rate": 1.1059011279815966e-05, + "loss": 0.0201, + "step": 31230 + }, + { + "epoch": 9.64, + "learning_rate": 1.1058513972599368e-05, + "loss": 0.0239, + "step": 31231 + }, + { + "epoch": 9.65, + "learning_rate": 1.1058016662735227e-05, + "loss": 0.024, + "step": 31232 + }, + { + "epoch": 9.65, + "learning_rate": 1.10575193502248e-05, + "loss": 0.0225, + "step": 31233 + }, + { + "epoch": 9.65, + "learning_rate": 1.1057022035069322e-05, + "loss": 0.022, + "step": 31234 + }, + { + "epoch": 9.65, + "learning_rate": 1.1056524717270041e-05, + "loss": 0.0229, + "step": 31235 + }, + { + "epoch": 9.65, + "learning_rate": 1.1056027396828198e-05, + "loss": 0.0227, + "step": 31236 + }, + { + "epoch": 9.65, + "learning_rate": 1.1055530073745036e-05, + "loss": 0.022, + "step": 31237 + }, + { + "epoch": 9.65, + "learning_rate": 1.1055032748021803e-05, + "loss": 0.0252, + "step": 31238 + }, + { + "epoch": 9.65, + "learning_rate": 1.105453541965974e-05, + "loss": 0.0217, + "step": 31239 + }, + { + "epoch": 9.65, + "learning_rate": 1.105403808866009e-05, + "loss": 0.0254, + "step": 31240 + }, + { + "epoch": 9.65, + "learning_rate": 1.1053540755024101e-05, + "loss": 0.0222, + "step": 31241 + }, + { + "epoch": 9.65, + "learning_rate": 1.1053043418753013e-05, + "loss": 0.0247, + "step": 31242 + }, + { + "epoch": 9.65, + "learning_rate": 1.1052546079848072e-05, + "loss": 0.0249, + "step": 31243 + }, + { + "epoch": 9.65, + "learning_rate": 1.1052048738310522e-05, + "loss": 0.0211, + "step": 31244 + }, + { + "epoch": 9.65, + "learning_rate": 1.1051551394141603e-05, + "loss": 0.0252, + "step": 31245 + }, + { + "epoch": 9.65, + "learning_rate": 1.1051054047342564e-05, + "loss": 0.022, + "step": 31246 + }, + { + "epoch": 9.65, + "learning_rate": 1.1050556697914647e-05, + "loss": 0.0219, + "step": 31247 + }, + { + "epoch": 9.65, + "learning_rate": 1.10500593458591e-05, + "loss": 0.0254, + "step": 31248 + }, + { + "epoch": 9.65, + "learning_rate": 1.1049561991177159e-05, + "loss": 0.0222, + "step": 31249 + }, + { + "epoch": 9.65, + "learning_rate": 1.104906463387007e-05, + "loss": 0.0216, + "step": 31250 + }, + { + "epoch": 9.65, + "learning_rate": 1.1048567273939082e-05, + "loss": 0.0215, + "step": 31251 + }, + { + "epoch": 9.65, + "learning_rate": 1.1048069911385436e-05, + "loss": 0.0225, + "step": 31252 + }, + { + "epoch": 9.65, + "learning_rate": 1.1047572546210376e-05, + "loss": 0.0246, + "step": 31253 + }, + { + "epoch": 9.65, + "learning_rate": 1.1047075178415145e-05, + "loss": 0.0202, + "step": 31254 + }, + { + "epoch": 9.65, + "learning_rate": 1.1046577808000989e-05, + "loss": 0.0243, + "step": 31255 + }, + { + "epoch": 9.65, + "learning_rate": 1.1046080434969153e-05, + "loss": 0.0233, + "step": 31256 + }, + { + "epoch": 9.65, + "learning_rate": 1.1045583059320872e-05, + "loss": 0.0247, + "step": 31257 + }, + { + "epoch": 9.65, + "learning_rate": 1.1045085681057406e-05, + "loss": 0.0249, + "step": 31258 + }, + { + "epoch": 9.65, + "learning_rate": 1.1044588300179986e-05, + "loss": 0.0224, + "step": 31259 + }, + { + "epoch": 9.65, + "learning_rate": 1.1044090916689858e-05, + "loss": 0.0237, + "step": 31260 + }, + { + "epoch": 9.65, + "learning_rate": 1.1043593530588272e-05, + "loss": 0.0257, + "step": 31261 + }, + { + "epoch": 9.65, + "learning_rate": 1.1043096141876465e-05, + "loss": 0.024, + "step": 31262 + }, + { + "epoch": 9.65, + "learning_rate": 1.1042598750555686e-05, + "loss": 0.0233, + "step": 31263 + }, + { + "epoch": 9.65, + "learning_rate": 1.1042101356627178e-05, + "loss": 0.0216, + "step": 31264 + }, + { + "epoch": 9.66, + "learning_rate": 1.1041603960092182e-05, + "loss": 0.0227, + "step": 31265 + }, + { + "epoch": 9.66, + "learning_rate": 1.1041106560951947e-05, + "loss": 0.0241, + "step": 31266 + }, + { + "epoch": 9.66, + "learning_rate": 1.1040609159207713e-05, + "loss": 0.0218, + "step": 31267 + }, + { + "epoch": 9.66, + "learning_rate": 1.1040111754860727e-05, + "loss": 0.0239, + "step": 31268 + }, + { + "epoch": 9.66, + "learning_rate": 1.103961434791223e-05, + "loss": 0.0235, + "step": 31269 + }, + { + "epoch": 9.66, + "learning_rate": 1.103911693836347e-05, + "loss": 0.023, + "step": 31270 + }, + { + "epoch": 9.66, + "learning_rate": 1.1038619526215688e-05, + "loss": 0.0241, + "step": 31271 + }, + { + "epoch": 9.66, + "learning_rate": 1.103812211147013e-05, + "loss": 0.0252, + "step": 31272 + }, + { + "epoch": 9.66, + "learning_rate": 1.1037624694128037e-05, + "loss": 0.0215, + "step": 31273 + }, + { + "epoch": 9.66, + "learning_rate": 1.1037127274190657e-05, + "loss": 0.0231, + "step": 31274 + }, + { + "epoch": 9.66, + "learning_rate": 1.1036629851659233e-05, + "loss": 0.0244, + "step": 31275 + }, + { + "epoch": 9.66, + "learning_rate": 1.1036132426535006e-05, + "loss": 0.0246, + "step": 31276 + }, + { + "epoch": 9.66, + "learning_rate": 1.1035634998819227e-05, + "loss": 0.023, + "step": 31277 + }, + { + "epoch": 9.66, + "learning_rate": 1.1035137568513132e-05, + "loss": 0.0241, + "step": 31278 + }, + { + "epoch": 9.66, + "learning_rate": 1.1034640135617973e-05, + "loss": 0.0226, + "step": 31279 + }, + { + "epoch": 9.66, + "learning_rate": 1.1034142700134986e-05, + "loss": 0.0227, + "step": 31280 + }, + { + "epoch": 9.66, + "learning_rate": 1.1033645262065423e-05, + "loss": 0.027, + "step": 31281 + }, + { + "epoch": 9.66, + "learning_rate": 1.1033147821410526e-05, + "loss": 0.0241, + "step": 31282 + }, + { + "epoch": 9.66, + "learning_rate": 1.1032650378171532e-05, + "loss": 0.0247, + "step": 31283 + }, + { + "epoch": 9.66, + "learning_rate": 1.1032152932349698e-05, + "loss": 0.023, + "step": 31284 + }, + { + "epoch": 9.66, + "learning_rate": 1.1031655483946255e-05, + "loss": 0.0244, + "step": 31285 + }, + { + "epoch": 9.66, + "learning_rate": 1.1031158032962455e-05, + "loss": 0.0211, + "step": 31286 + }, + { + "epoch": 9.66, + "learning_rate": 1.1030660579399543e-05, + "loss": 0.0217, + "step": 31287 + }, + { + "epoch": 9.66, + "learning_rate": 1.103016312325876e-05, + "loss": 0.0249, + "step": 31288 + }, + { + "epoch": 9.66, + "learning_rate": 1.1029665664541352e-05, + "loss": 0.0243, + "step": 31289 + }, + { + "epoch": 9.66, + "learning_rate": 1.1029168203248561e-05, + "loss": 0.0231, + "step": 31290 + }, + { + "epoch": 9.66, + "learning_rate": 1.102867073938163e-05, + "loss": 0.0237, + "step": 31291 + }, + { + "epoch": 9.66, + "learning_rate": 1.1028173272941812e-05, + "loss": 0.0236, + "step": 31292 + }, + { + "epoch": 9.66, + "learning_rate": 1.1027675803930342e-05, + "loss": 0.0238, + "step": 31293 + }, + { + "epoch": 9.66, + "learning_rate": 1.1027178332348467e-05, + "loss": 0.0231, + "step": 31294 + }, + { + "epoch": 9.66, + "learning_rate": 1.1026680858197432e-05, + "loss": 0.0232, + "step": 31295 + }, + { + "epoch": 9.66, + "learning_rate": 1.1026183381478479e-05, + "loss": 0.0239, + "step": 31296 + }, + { + "epoch": 9.67, + "learning_rate": 1.1025685902192857e-05, + "loss": 0.0229, + "step": 31297 + }, + { + "epoch": 9.67, + "learning_rate": 1.1025188420341806e-05, + "loss": 0.0233, + "step": 31298 + }, + { + "epoch": 9.67, + "learning_rate": 1.1024690935926572e-05, + "loss": 0.0232, + "step": 31299 + }, + { + "epoch": 9.67, + "learning_rate": 1.1024193448948398e-05, + "loss": 0.0205, + "step": 31300 + }, + { + "epoch": 9.67, + "learning_rate": 1.1023695959408531e-05, + "loss": 0.0229, + "step": 31301 + }, + { + "epoch": 9.67, + "learning_rate": 1.1023198467308214e-05, + "loss": 0.0243, + "step": 31302 + }, + { + "epoch": 9.67, + "learning_rate": 1.102270097264869e-05, + "loss": 0.0245, + "step": 31303 + }, + { + "epoch": 9.67, + "learning_rate": 1.1022203475431205e-05, + "loss": 0.0239, + "step": 31304 + }, + { + "epoch": 9.67, + "learning_rate": 1.1021705975657003e-05, + "loss": 0.0245, + "step": 31305 + }, + { + "epoch": 9.67, + "learning_rate": 1.1021208473327328e-05, + "loss": 0.0247, + "step": 31306 + }, + { + "epoch": 9.67, + "learning_rate": 1.1020710968443424e-05, + "loss": 0.0241, + "step": 31307 + }, + { + "epoch": 9.67, + "learning_rate": 1.1020213461006535e-05, + "loss": 0.0224, + "step": 31308 + }, + { + "epoch": 9.67, + "learning_rate": 1.1019715951017907e-05, + "loss": 0.0238, + "step": 31309 + }, + { + "epoch": 9.67, + "learning_rate": 1.1019218438478782e-05, + "loss": 0.0189, + "step": 31310 + }, + { + "epoch": 9.67, + "learning_rate": 1.1018720923390407e-05, + "loss": 0.0231, + "step": 31311 + }, + { + "epoch": 9.67, + "learning_rate": 1.1018223405754027e-05, + "loss": 0.0232, + "step": 31312 + }, + { + "epoch": 9.67, + "learning_rate": 1.1017725885570883e-05, + "loss": 0.027, + "step": 31313 + }, + { + "epoch": 9.67, + "learning_rate": 1.1017228362842216e-05, + "loss": 0.0206, + "step": 31314 + }, + { + "epoch": 9.67, + "learning_rate": 1.1016730837569283e-05, + "loss": 0.0213, + "step": 31315 + }, + { + "epoch": 9.67, + "learning_rate": 1.1016233309753315e-05, + "loss": 0.0224, + "step": 31316 + }, + { + "epoch": 9.67, + "learning_rate": 1.1015735779395567e-05, + "loss": 0.0268, + "step": 31317 + }, + { + "epoch": 9.67, + "learning_rate": 1.1015238246497275e-05, + "loss": 0.0233, + "step": 31318 + }, + { + "epoch": 9.67, + "learning_rate": 1.1014740711059686e-05, + "loss": 0.024, + "step": 31319 + }, + { + "epoch": 9.67, + "learning_rate": 1.1014243173084049e-05, + "loss": 0.0242, + "step": 31320 + }, + { + "epoch": 9.67, + "learning_rate": 1.1013745632571604e-05, + "loss": 0.0246, + "step": 31321 + }, + { + "epoch": 9.67, + "learning_rate": 1.1013248089523596e-05, + "loss": 0.0224, + "step": 31322 + }, + { + "epoch": 9.67, + "learning_rate": 1.101275054394127e-05, + "loss": 0.0238, + "step": 31323 + }, + { + "epoch": 9.67, + "learning_rate": 1.101225299582587e-05, + "loss": 0.0241, + "step": 31324 + }, + { + "epoch": 9.67, + "learning_rate": 1.1011755445178639e-05, + "loss": 0.0228, + "step": 31325 + }, + { + "epoch": 9.67, + "learning_rate": 1.1011257892000823e-05, + "loss": 0.0259, + "step": 31326 + }, + { + "epoch": 9.67, + "learning_rate": 1.101076033629367e-05, + "loss": 0.0202, + "step": 31327 + }, + { + "epoch": 9.67, + "learning_rate": 1.1010262778058419e-05, + "loss": 0.0247, + "step": 31328 + }, + { + "epoch": 9.68, + "learning_rate": 1.1009765217296316e-05, + "loss": 0.0227, + "step": 31329 + }, + { + "epoch": 9.68, + "learning_rate": 1.1009267654008607e-05, + "loss": 0.0228, + "step": 31330 + }, + { + "epoch": 9.68, + "learning_rate": 1.1008770088196535e-05, + "loss": 0.0236, + "step": 31331 + }, + { + "epoch": 9.68, + "learning_rate": 1.1008272519861343e-05, + "loss": 0.0232, + "step": 31332 + }, + { + "epoch": 9.68, + "learning_rate": 1.100777494900428e-05, + "loss": 0.0221, + "step": 31333 + }, + { + "epoch": 9.68, + "learning_rate": 1.1007277375626589e-05, + "loss": 0.023, + "step": 31334 + }, + { + "epoch": 9.68, + "learning_rate": 1.100677979972951e-05, + "loss": 0.0245, + "step": 31335 + }, + { + "epoch": 9.68, + "learning_rate": 1.1006282221314292e-05, + "loss": 0.0236, + "step": 31336 + }, + { + "epoch": 9.68, + "learning_rate": 1.1005784640382182e-05, + "loss": 0.0261, + "step": 31337 + }, + { + "epoch": 9.68, + "learning_rate": 1.1005287056934421e-05, + "loss": 0.0232, + "step": 31338 + }, + { + "epoch": 9.68, + "learning_rate": 1.100478947097225e-05, + "loss": 0.0251, + "step": 31339 + }, + { + "epoch": 9.68, + "learning_rate": 1.1004291882496918e-05, + "loss": 0.0251, + "step": 31340 + }, + { + "epoch": 9.68, + "learning_rate": 1.1003794291509673e-05, + "loss": 0.0245, + "step": 31341 + }, + { + "epoch": 9.68, + "learning_rate": 1.100329669801175e-05, + "loss": 0.0256, + "step": 31342 + }, + { + "epoch": 9.68, + "learning_rate": 1.1002799102004401e-05, + "loss": 0.0247, + "step": 31343 + }, + { + "epoch": 9.68, + "learning_rate": 1.100230150348887e-05, + "loss": 0.0248, + "step": 31344 + }, + { + "epoch": 9.68, + "learning_rate": 1.1001803902466397e-05, + "loss": 0.0234, + "step": 31345 + }, + { + "epoch": 9.68, + "learning_rate": 1.1001306298938234e-05, + "loss": 0.0211, + "step": 31346 + }, + { + "epoch": 9.68, + "learning_rate": 1.1000808692905618e-05, + "loss": 0.0266, + "step": 31347 + }, + { + "epoch": 9.68, + "learning_rate": 1.10003110843698e-05, + "loss": 0.0219, + "step": 31348 + }, + { + "epoch": 9.68, + "learning_rate": 1.0999813473332018e-05, + "loss": 0.0233, + "step": 31349 + }, + { + "epoch": 9.68, + "learning_rate": 1.099931585979352e-05, + "loss": 0.0234, + "step": 31350 + }, + { + "epoch": 9.68, + "learning_rate": 1.0998818243755553e-05, + "loss": 0.0227, + "step": 31351 + }, + { + "epoch": 9.68, + "learning_rate": 1.0998320625219358e-05, + "loss": 0.0269, + "step": 31352 + }, + { + "epoch": 9.68, + "learning_rate": 1.0997823004186184e-05, + "loss": 0.0259, + "step": 31353 + }, + { + "epoch": 9.68, + "learning_rate": 1.099732538065727e-05, + "loss": 0.0233, + "step": 31354 + }, + { + "epoch": 9.68, + "learning_rate": 1.0996827754633864e-05, + "loss": 0.0228, + "step": 31355 + }, + { + "epoch": 9.68, + "learning_rate": 1.099633012611721e-05, + "loss": 0.0221, + "step": 31356 + }, + { + "epoch": 9.68, + "learning_rate": 1.0995832495108552e-05, + "loss": 0.0231, + "step": 31357 + }, + { + "epoch": 9.68, + "learning_rate": 1.0995334861609135e-05, + "loss": 0.0243, + "step": 31358 + }, + { + "epoch": 9.68, + "learning_rate": 1.0994837225620205e-05, + "loss": 0.0214, + "step": 31359 + }, + { + "epoch": 9.68, + "learning_rate": 1.0994339587143004e-05, + "loss": 0.0244, + "step": 31360 + }, + { + "epoch": 9.68, + "learning_rate": 1.0993841946178782e-05, + "loss": 0.0226, + "step": 31361 + }, + { + "epoch": 9.69, + "learning_rate": 1.0993344302728776e-05, + "loss": 0.024, + "step": 31362 + }, + { + "epoch": 9.69, + "learning_rate": 1.0992846656794236e-05, + "loss": 0.0219, + "step": 31363 + }, + { + "epoch": 9.69, + "learning_rate": 1.0992349008376406e-05, + "loss": 0.0232, + "step": 31364 + }, + { + "epoch": 9.69, + "learning_rate": 1.099185135747653e-05, + "loss": 0.0259, + "step": 31365 + }, + { + "epoch": 9.69, + "learning_rate": 1.0991353704095855e-05, + "loss": 0.0232, + "step": 31366 + }, + { + "epoch": 9.69, + "learning_rate": 1.0990856048235619e-05, + "loss": 0.024, + "step": 31367 + }, + { + "epoch": 9.69, + "learning_rate": 1.0990358389897073e-05, + "loss": 0.0295, + "step": 31368 + }, + { + "epoch": 9.69, + "learning_rate": 1.0989860729081463e-05, + "loss": 0.0242, + "step": 31369 + }, + { + "epoch": 9.69, + "learning_rate": 1.0989363065790027e-05, + "loss": 0.0222, + "step": 31370 + }, + { + "epoch": 9.69, + "learning_rate": 1.0988865400024017e-05, + "loss": 0.0258, + "step": 31371 + }, + { + "epoch": 9.69, + "learning_rate": 1.098836773178467e-05, + "loss": 0.0255, + "step": 31372 + }, + { + "epoch": 9.69, + "learning_rate": 1.0987870061073235e-05, + "loss": 0.0249, + "step": 31373 + }, + { + "epoch": 9.69, + "learning_rate": 1.0987372387890962e-05, + "loss": 0.0253, + "step": 31374 + }, + { + "epoch": 9.69, + "learning_rate": 1.0986874712239089e-05, + "loss": 0.0248, + "step": 31375 + }, + { + "epoch": 9.69, + "learning_rate": 1.098637703411886e-05, + "loss": 0.0269, + "step": 31376 + }, + { + "epoch": 9.69, + "learning_rate": 1.0985879353531523e-05, + "loss": 0.0244, + "step": 31377 + }, + { + "epoch": 9.69, + "learning_rate": 1.0985381670478323e-05, + "loss": 0.0242, + "step": 31378 + }, + { + "epoch": 9.69, + "learning_rate": 1.0984883984960501e-05, + "loss": 0.0264, + "step": 31379 + }, + { + "epoch": 9.69, + "learning_rate": 1.0984386296979309e-05, + "loss": 0.0235, + "step": 31380 + }, + { + "epoch": 9.69, + "learning_rate": 1.0983888606535984e-05, + "loss": 0.023, + "step": 31381 + }, + { + "epoch": 9.69, + "learning_rate": 1.0983390913631775e-05, + "loss": 0.0228, + "step": 31382 + }, + { + "epoch": 9.69, + "learning_rate": 1.0982893218267924e-05, + "loss": 0.0227, + "step": 31383 + }, + { + "epoch": 9.69, + "learning_rate": 1.098239552044568e-05, + "loss": 0.0231, + "step": 31384 + }, + { + "epoch": 9.69, + "learning_rate": 1.0981897820166284e-05, + "loss": 0.0231, + "step": 31385 + }, + { + "epoch": 9.69, + "learning_rate": 1.0981400117430986e-05, + "loss": 0.0227, + "step": 31386 + }, + { + "epoch": 9.69, + "learning_rate": 1.0980902412241024e-05, + "loss": 0.0218, + "step": 31387 + }, + { + "epoch": 9.69, + "learning_rate": 1.0980404704597647e-05, + "loss": 0.0264, + "step": 31388 + }, + { + "epoch": 9.69, + "learning_rate": 1.09799069945021e-05, + "loss": 0.0236, + "step": 31389 + }, + { + "epoch": 9.69, + "learning_rate": 1.0979409281955625e-05, + "loss": 0.0228, + "step": 31390 + }, + { + "epoch": 9.69, + "learning_rate": 1.097891156695947e-05, + "loss": 0.0225, + "step": 31391 + }, + { + "epoch": 9.69, + "learning_rate": 1.097841384951488e-05, + "loss": 0.023, + "step": 31392 + }, + { + "epoch": 9.69, + "learning_rate": 1.0977916129623094e-05, + "loss": 0.0234, + "step": 31393 + }, + { + "epoch": 9.7, + "learning_rate": 1.0977418407285366e-05, + "loss": 0.0223, + "step": 31394 + }, + { + "epoch": 9.7, + "learning_rate": 1.0976920682502936e-05, + "loss": 0.0218, + "step": 31395 + }, + { + "epoch": 9.7, + "learning_rate": 1.0976422955277047e-05, + "loss": 0.0261, + "step": 31396 + }, + { + "epoch": 9.7, + "learning_rate": 1.0975925225608948e-05, + "loss": 0.0231, + "step": 31397 + }, + { + "epoch": 9.7, + "learning_rate": 1.097542749349988e-05, + "loss": 0.0228, + "step": 31398 + }, + { + "epoch": 9.7, + "learning_rate": 1.0974929758951089e-05, + "loss": 0.024, + "step": 31399 + }, + { + "epoch": 9.7, + "learning_rate": 1.0974432021963826e-05, + "loss": 0.0213, + "step": 31400 + }, + { + "epoch": 9.7, + "learning_rate": 1.0973934282539325e-05, + "loss": 0.0252, + "step": 31401 + }, + { + "epoch": 9.7, + "learning_rate": 1.097343654067884e-05, + "loss": 0.025, + "step": 31402 + }, + { + "epoch": 9.7, + "learning_rate": 1.0972938796383611e-05, + "loss": 0.0252, + "step": 31403 + }, + { + "epoch": 9.7, + "learning_rate": 1.0972441049654885e-05, + "loss": 0.0247, + "step": 31404 + }, + { + "epoch": 9.7, + "learning_rate": 1.097194330049391e-05, + "loss": 0.0235, + "step": 31405 + }, + { + "epoch": 9.7, + "learning_rate": 1.0971445548901925e-05, + "loss": 0.0239, + "step": 31406 + }, + { + "epoch": 9.7, + "learning_rate": 1.0970947794880175e-05, + "loss": 0.0226, + "step": 31407 + }, + { + "epoch": 9.7, + "learning_rate": 1.097045003842991e-05, + "loss": 0.0234, + "step": 31408 + }, + { + "epoch": 9.7, + "learning_rate": 1.0969952279552372e-05, + "loss": 0.0249, + "step": 31409 + }, + { + "epoch": 9.7, + "learning_rate": 1.0969454518248808e-05, + "loss": 0.0256, + "step": 31410 + }, + { + "epoch": 9.7, + "learning_rate": 1.0968956754520459e-05, + "loss": 0.0225, + "step": 31411 + }, + { + "epoch": 9.7, + "learning_rate": 1.0968458988368574e-05, + "loss": 0.0252, + "step": 31412 + }, + { + "epoch": 9.7, + "learning_rate": 1.0967961219794395e-05, + "loss": 0.0234, + "step": 31413 + }, + { + "epoch": 9.7, + "learning_rate": 1.0967463448799169e-05, + "loss": 0.0242, + "step": 31414 + }, + { + "epoch": 9.7, + "learning_rate": 1.096696567538414e-05, + "loss": 0.022, + "step": 31415 + }, + { + "epoch": 9.7, + "learning_rate": 1.0966467899550554e-05, + "loss": 0.0249, + "step": 31416 + }, + { + "epoch": 9.7, + "learning_rate": 1.0965970121299656e-05, + "loss": 0.022, + "step": 31417 + }, + { + "epoch": 9.7, + "learning_rate": 1.096547234063269e-05, + "loss": 0.0241, + "step": 31418 + }, + { + "epoch": 9.7, + "learning_rate": 1.0964974557550903e-05, + "loss": 0.0234, + "step": 31419 + }, + { + "epoch": 9.7, + "learning_rate": 1.096447677205554e-05, + "loss": 0.0248, + "step": 31420 + }, + { + "epoch": 9.7, + "learning_rate": 1.0963978984147839e-05, + "loss": 0.0249, + "step": 31421 + }, + { + "epoch": 9.7, + "learning_rate": 1.0963481193829054e-05, + "loss": 0.0225, + "step": 31422 + }, + { + "epoch": 9.7, + "learning_rate": 1.096298340110043e-05, + "loss": 0.0231, + "step": 31423 + }, + { + "epoch": 9.7, + "learning_rate": 1.0962485605963203e-05, + "loss": 0.0216, + "step": 31424 + }, + { + "epoch": 9.7, + "learning_rate": 1.0961987808418628e-05, + "loss": 0.023, + "step": 31425 + }, + { + "epoch": 9.7, + "learning_rate": 1.0961490008467944e-05, + "loss": 0.0229, + "step": 31426 + }, + { + "epoch": 9.71, + "learning_rate": 1.0960992206112395e-05, + "loss": 0.0233, + "step": 31427 + }, + { + "epoch": 9.71, + "learning_rate": 1.0960494401353236e-05, + "loss": 0.0232, + "step": 31428 + }, + { + "epoch": 9.71, + "learning_rate": 1.0959996594191702e-05, + "loss": 0.0231, + "step": 31429 + }, + { + "epoch": 9.71, + "learning_rate": 1.0959498784629042e-05, + "loss": 0.0236, + "step": 31430 + }, + { + "epoch": 9.71, + "learning_rate": 1.09590009726665e-05, + "loss": 0.0226, + "step": 31431 + }, + { + "epoch": 9.71, + "learning_rate": 1.095850315830532e-05, + "loss": 0.0246, + "step": 31432 + }, + { + "epoch": 9.71, + "learning_rate": 1.0958005341546752e-05, + "loss": 0.0288, + "step": 31433 + }, + { + "epoch": 9.71, + "learning_rate": 1.0957507522392036e-05, + "loss": 0.024, + "step": 31434 + }, + { + "epoch": 9.71, + "learning_rate": 1.0957009700842418e-05, + "loss": 0.0248, + "step": 31435 + }, + { + "epoch": 9.71, + "learning_rate": 1.0956511876899147e-05, + "loss": 0.0221, + "step": 31436 + }, + { + "epoch": 9.71, + "learning_rate": 1.0956014050563466e-05, + "loss": 0.0231, + "step": 31437 + }, + { + "epoch": 9.71, + "learning_rate": 1.0955516221836617e-05, + "loss": 0.0227, + "step": 31438 + }, + { + "epoch": 9.71, + "learning_rate": 1.0955018390719848e-05, + "loss": 0.0226, + "step": 31439 + }, + { + "epoch": 9.71, + "learning_rate": 1.0954520557214403e-05, + "loss": 0.0256, + "step": 31440 + }, + { + "epoch": 9.71, + "learning_rate": 1.0954022721321529e-05, + "loss": 0.0251, + "step": 31441 + }, + { + "epoch": 9.71, + "learning_rate": 1.095352488304247e-05, + "loss": 0.0253, + "step": 31442 + }, + { + "epoch": 9.71, + "learning_rate": 1.0953027042378472e-05, + "loss": 0.0237, + "step": 31443 + }, + { + "epoch": 9.71, + "learning_rate": 1.095252919933078e-05, + "loss": 0.0243, + "step": 31444 + }, + { + "epoch": 9.71, + "learning_rate": 1.095203135390064e-05, + "loss": 0.0231, + "step": 31445 + }, + { + "epoch": 9.71, + "learning_rate": 1.0951533506089291e-05, + "loss": 0.0206, + "step": 31446 + }, + { + "epoch": 9.71, + "learning_rate": 1.0951035655897985e-05, + "loss": 0.0226, + "step": 31447 + }, + { + "epoch": 9.71, + "learning_rate": 1.0950537803327967e-05, + "loss": 0.0244, + "step": 31448 + }, + { + "epoch": 9.71, + "learning_rate": 1.095003994838048e-05, + "loss": 0.0244, + "step": 31449 + }, + { + "epoch": 9.71, + "learning_rate": 1.0949542091056771e-05, + "loss": 0.0235, + "step": 31450 + }, + { + "epoch": 9.71, + "learning_rate": 1.0949044231358083e-05, + "loss": 0.0226, + "step": 31451 + }, + { + "epoch": 9.71, + "learning_rate": 1.094854636928566e-05, + "loss": 0.0216, + "step": 31452 + }, + { + "epoch": 9.71, + "learning_rate": 1.0948048504840751e-05, + "loss": 0.0248, + "step": 31453 + }, + { + "epoch": 9.71, + "learning_rate": 1.0947550638024605e-05, + "loss": 0.0247, + "step": 31454 + }, + { + "epoch": 9.71, + "learning_rate": 1.0947052768838453e-05, + "loss": 0.0232, + "step": 31455 + }, + { + "epoch": 9.71, + "learning_rate": 1.0946554897283557e-05, + "loss": 0.0226, + "step": 31456 + }, + { + "epoch": 9.71, + "learning_rate": 1.0946057023361153e-05, + "loss": 0.0256, + "step": 31457 + }, + { + "epoch": 9.71, + "learning_rate": 1.0945559147072482e-05, + "loss": 0.0206, + "step": 31458 + }, + { + "epoch": 9.72, + "learning_rate": 1.0945061268418801e-05, + "loss": 0.0223, + "step": 31459 + }, + { + "epoch": 9.72, + "learning_rate": 1.0944563387401348e-05, + "loss": 0.0257, + "step": 31460 + }, + { + "epoch": 9.72, + "learning_rate": 1.0944065504021368e-05, + "loss": 0.0223, + "step": 31461 + }, + { + "epoch": 9.72, + "learning_rate": 1.0943567618280108e-05, + "loss": 0.0222, + "step": 31462 + }, + { + "epoch": 9.72, + "learning_rate": 1.0943069730178815e-05, + "loss": 0.0233, + "step": 31463 + }, + { + "epoch": 9.72, + "learning_rate": 1.0942571839718735e-05, + "loss": 0.0212, + "step": 31464 + }, + { + "epoch": 9.72, + "learning_rate": 1.0942073946901106e-05, + "loss": 0.0255, + "step": 31465 + }, + { + "epoch": 9.72, + "learning_rate": 1.094157605172718e-05, + "loss": 0.022, + "step": 31466 + }, + { + "epoch": 9.72, + "learning_rate": 1.0941078154198202e-05, + "loss": 0.0234, + "step": 31467 + }, + { + "epoch": 9.72, + "learning_rate": 1.0940580254315414e-05, + "loss": 0.0262, + "step": 31468 + }, + { + "epoch": 9.72, + "learning_rate": 1.0940082352080064e-05, + "loss": 0.0234, + "step": 31469 + }, + { + "epoch": 9.72, + "learning_rate": 1.0939584447493397e-05, + "loss": 0.0242, + "step": 31470 + }, + { + "epoch": 9.72, + "learning_rate": 1.0939086540556659e-05, + "loss": 0.0258, + "step": 31471 + }, + { + "epoch": 9.72, + "learning_rate": 1.093858863127109e-05, + "loss": 0.0241, + "step": 31472 + }, + { + "epoch": 9.72, + "learning_rate": 1.0938090719637944e-05, + "loss": 0.0241, + "step": 31473 + }, + { + "epoch": 9.72, + "learning_rate": 1.0937592805658459e-05, + "loss": 0.0247, + "step": 31474 + }, + { + "epoch": 9.72, + "learning_rate": 1.0937094889333885e-05, + "loss": 0.0239, + "step": 31475 + }, + { + "epoch": 9.72, + "learning_rate": 1.0936596970665465e-05, + "loss": 0.0268, + "step": 31476 + }, + { + "epoch": 9.72, + "learning_rate": 1.093609904965445e-05, + "loss": 0.0247, + "step": 31477 + }, + { + "epoch": 9.72, + "learning_rate": 1.0935601126302074e-05, + "loss": 0.0228, + "step": 31478 + }, + { + "epoch": 9.72, + "learning_rate": 1.0935103200609589e-05, + "loss": 0.023, + "step": 31479 + }, + { + "epoch": 9.72, + "learning_rate": 1.0934605272578246e-05, + "loss": 0.023, + "step": 31480 + }, + { + "epoch": 9.72, + "learning_rate": 1.093410734220928e-05, + "loss": 0.0237, + "step": 31481 + }, + { + "epoch": 9.72, + "learning_rate": 1.0933609409503944e-05, + "loss": 0.023, + "step": 31482 + }, + { + "epoch": 9.72, + "learning_rate": 1.0933111474463476e-05, + "loss": 0.0227, + "step": 31483 + }, + { + "epoch": 9.72, + "learning_rate": 1.093261353708913e-05, + "loss": 0.0241, + "step": 31484 + }, + { + "epoch": 9.72, + "learning_rate": 1.0932115597382149e-05, + "loss": 0.0235, + "step": 31485 + }, + { + "epoch": 9.72, + "learning_rate": 1.093161765534377e-05, + "loss": 0.0242, + "step": 31486 + }, + { + "epoch": 9.72, + "learning_rate": 1.0931119710975253e-05, + "loss": 0.0226, + "step": 31487 + }, + { + "epoch": 9.72, + "learning_rate": 1.0930621764277834e-05, + "loss": 0.0211, + "step": 31488 + }, + { + "epoch": 9.72, + "learning_rate": 1.0930123815252756e-05, + "loss": 0.0244, + "step": 31489 + }, + { + "epoch": 9.72, + "learning_rate": 1.0929625863901273e-05, + "loss": 0.027, + "step": 31490 + }, + { + "epoch": 9.73, + "learning_rate": 1.0929127910224625e-05, + "loss": 0.0255, + "step": 31491 + }, + { + "epoch": 9.73, + "learning_rate": 1.0928629954224057e-05, + "loss": 0.0245, + "step": 31492 + }, + { + "epoch": 9.73, + "learning_rate": 1.0928131995900817e-05, + "loss": 0.0224, + "step": 31493 + }, + { + "epoch": 9.73, + "learning_rate": 1.0927634035256152e-05, + "loss": 0.0268, + "step": 31494 + }, + { + "epoch": 9.73, + "learning_rate": 1.0927136072291302e-05, + "loss": 0.0254, + "step": 31495 + }, + { + "epoch": 9.73, + "learning_rate": 1.0926638107007517e-05, + "loss": 0.0233, + "step": 31496 + }, + { + "epoch": 9.73, + "learning_rate": 1.092614013940604e-05, + "loss": 0.0232, + "step": 31497 + }, + { + "epoch": 9.73, + "learning_rate": 1.0925642169488117e-05, + "loss": 0.0268, + "step": 31498 + }, + { + "epoch": 9.73, + "learning_rate": 1.0925144197254998e-05, + "loss": 0.0238, + "step": 31499 + }, + { + "epoch": 9.73, + "learning_rate": 1.092464622270792e-05, + "loss": 0.0213, + "step": 31500 + }, + { + "epoch": 9.73, + "learning_rate": 1.0924148245848136e-05, + "loss": 0.0243, + "step": 31501 + }, + { + "epoch": 9.73, + "learning_rate": 1.0923650266676889e-05, + "loss": 0.0217, + "step": 31502 + }, + { + "epoch": 9.73, + "learning_rate": 1.0923152285195422e-05, + "loss": 0.024, + "step": 31503 + }, + { + "epoch": 9.73, + "learning_rate": 1.0922654301404984e-05, + "loss": 0.0235, + "step": 31504 + }, + { + "epoch": 9.73, + "learning_rate": 1.092215631530682e-05, + "loss": 0.0222, + "step": 31505 + }, + { + "epoch": 9.73, + "learning_rate": 1.0921658326902174e-05, + "loss": 0.0235, + "step": 31506 + }, + { + "epoch": 9.73, + "learning_rate": 1.0921160336192292e-05, + "loss": 0.0235, + "step": 31507 + }, + { + "epoch": 9.73, + "learning_rate": 1.092066234317842e-05, + "loss": 0.0277, + "step": 31508 + }, + { + "epoch": 9.73, + "learning_rate": 1.0920164347861804e-05, + "loss": 0.0235, + "step": 31509 + }, + { + "epoch": 9.73, + "learning_rate": 1.0919666350243692e-05, + "loss": 0.021, + "step": 31510 + }, + { + "epoch": 9.73, + "learning_rate": 1.0919168350325322e-05, + "loss": 0.0233, + "step": 31511 + }, + { + "epoch": 9.73, + "learning_rate": 1.0918670348107945e-05, + "loss": 0.0267, + "step": 31512 + }, + { + "epoch": 9.73, + "learning_rate": 1.0918172343592808e-05, + "loss": 0.0222, + "step": 31513 + }, + { + "epoch": 9.73, + "learning_rate": 1.0917674336781153e-05, + "loss": 0.0214, + "step": 31514 + }, + { + "epoch": 9.73, + "learning_rate": 1.0917176327674229e-05, + "loss": 0.0229, + "step": 31515 + }, + { + "epoch": 9.73, + "learning_rate": 1.091667831627328e-05, + "loss": 0.0254, + "step": 31516 + }, + { + "epoch": 9.73, + "learning_rate": 1.0916180302579546e-05, + "loss": 0.0226, + "step": 31517 + }, + { + "epoch": 9.73, + "learning_rate": 1.0915682286594284e-05, + "loss": 0.0211, + "step": 31518 + }, + { + "epoch": 9.73, + "learning_rate": 1.0915184268318731e-05, + "loss": 0.0251, + "step": 31519 + }, + { + "epoch": 9.73, + "learning_rate": 1.0914686247754136e-05, + "loss": 0.0263, + "step": 31520 + }, + { + "epoch": 9.73, + "learning_rate": 1.0914188224901742e-05, + "loss": 0.0243, + "step": 31521 + }, + { + "epoch": 9.73, + "learning_rate": 1.0913690199762798e-05, + "loss": 0.0219, + "step": 31522 + }, + { + "epoch": 9.73, + "learning_rate": 1.0913192172338549e-05, + "loss": 0.0247, + "step": 31523 + }, + { + "epoch": 9.74, + "learning_rate": 1.0912694142630238e-05, + "loss": 0.0264, + "step": 31524 + }, + { + "epoch": 9.74, + "learning_rate": 1.0912196110639114e-05, + "loss": 0.0221, + "step": 31525 + }, + { + "epoch": 9.74, + "learning_rate": 1.091169807636642e-05, + "loss": 0.0206, + "step": 31526 + }, + { + "epoch": 9.74, + "learning_rate": 1.0911200039813403e-05, + "loss": 0.0233, + "step": 31527 + }, + { + "epoch": 9.74, + "learning_rate": 1.091070200098131e-05, + "loss": 0.0282, + "step": 31528 + }, + { + "epoch": 9.74, + "learning_rate": 1.0910203959871384e-05, + "loss": 0.0226, + "step": 31529 + }, + { + "epoch": 9.74, + "learning_rate": 1.0909705916484872e-05, + "loss": 0.0252, + "step": 31530 + }, + { + "epoch": 9.74, + "learning_rate": 1.090920787082302e-05, + "loss": 0.0242, + "step": 31531 + }, + { + "epoch": 9.74, + "learning_rate": 1.0908709822887071e-05, + "loss": 0.0224, + "step": 31532 + }, + { + "epoch": 9.74, + "learning_rate": 1.0908211772678276e-05, + "loss": 0.0223, + "step": 31533 + }, + { + "epoch": 9.74, + "learning_rate": 1.0907713720197877e-05, + "loss": 0.0229, + "step": 31534 + }, + { + "epoch": 9.74, + "learning_rate": 1.0907215665447119e-05, + "loss": 0.0222, + "step": 31535 + }, + { + "epoch": 9.74, + "learning_rate": 1.0906717608427252e-05, + "loss": 0.0245, + "step": 31536 + }, + { + "epoch": 9.74, + "learning_rate": 1.0906219549139516e-05, + "loss": 0.0254, + "step": 31537 + }, + { + "epoch": 9.74, + "learning_rate": 1.0905721487585158e-05, + "loss": 0.0225, + "step": 31538 + }, + { + "epoch": 9.74, + "learning_rate": 1.0905223423765432e-05, + "loss": 0.0248, + "step": 31539 + }, + { + "epoch": 9.74, + "learning_rate": 1.0904725357681572e-05, + "loss": 0.0245, + "step": 31540 + }, + { + "epoch": 9.74, + "learning_rate": 1.090422728933483e-05, + "loss": 0.0202, + "step": 31541 + }, + { + "epoch": 9.74, + "learning_rate": 1.0903729218726451e-05, + "loss": 0.0263, + "step": 31542 + }, + { + "epoch": 9.74, + "learning_rate": 1.0903231145857678e-05, + "loss": 0.0221, + "step": 31543 + }, + { + "epoch": 9.74, + "learning_rate": 1.0902733070729763e-05, + "loss": 0.0254, + "step": 31544 + }, + { + "epoch": 9.74, + "learning_rate": 1.0902234993343943e-05, + "loss": 0.0236, + "step": 31545 + }, + { + "epoch": 9.74, + "learning_rate": 1.0901736913701475e-05, + "loss": 0.0302, + "step": 31546 + }, + { + "epoch": 9.74, + "learning_rate": 1.0901238831803595e-05, + "loss": 0.0232, + "step": 31547 + }, + { + "epoch": 9.74, + "learning_rate": 1.090074074765155e-05, + "loss": 0.0211, + "step": 31548 + }, + { + "epoch": 9.74, + "learning_rate": 1.0900242661246593e-05, + "loss": 0.0231, + "step": 31549 + }, + { + "epoch": 9.74, + "learning_rate": 1.0899744572589963e-05, + "loss": 0.0235, + "step": 31550 + }, + { + "epoch": 9.74, + "learning_rate": 1.0899246481682909e-05, + "loss": 0.0219, + "step": 31551 + }, + { + "epoch": 9.74, + "learning_rate": 1.0898748388526672e-05, + "loss": 0.0233, + "step": 31552 + }, + { + "epoch": 9.74, + "learning_rate": 1.0898250293122502e-05, + "loss": 0.0252, + "step": 31553 + }, + { + "epoch": 9.74, + "learning_rate": 1.0897752195471646e-05, + "loss": 0.0245, + "step": 31554 + }, + { + "epoch": 9.74, + "learning_rate": 1.089725409557535e-05, + "loss": 0.0226, + "step": 31555 + }, + { + "epoch": 9.75, + "learning_rate": 1.0896755993434853e-05, + "loss": 0.0255, + "step": 31556 + }, + { + "epoch": 9.75, + "learning_rate": 1.089625788905141e-05, + "loss": 0.0241, + "step": 31557 + }, + { + "epoch": 9.75, + "learning_rate": 1.089575978242626e-05, + "loss": 0.025, + "step": 31558 + }, + { + "epoch": 9.75, + "learning_rate": 1.0895261673560653e-05, + "loss": 0.0259, + "step": 31559 + }, + { + "epoch": 9.75, + "learning_rate": 1.089476356245583e-05, + "loss": 0.0267, + "step": 31560 + }, + { + "epoch": 9.75, + "learning_rate": 1.0894265449113045e-05, + "loss": 0.0222, + "step": 31561 + }, + { + "epoch": 9.75, + "learning_rate": 1.0893767333533533e-05, + "loss": 0.024, + "step": 31562 + }, + { + "epoch": 9.75, + "learning_rate": 1.0893269215718551e-05, + "loss": 0.0276, + "step": 31563 + }, + { + "epoch": 9.75, + "learning_rate": 1.0892771095669338e-05, + "loss": 0.0223, + "step": 31564 + }, + { + "epoch": 9.75, + "learning_rate": 1.0892272973387141e-05, + "loss": 0.0247, + "step": 31565 + }, + { + "epoch": 9.75, + "learning_rate": 1.0891774848873206e-05, + "loss": 0.0235, + "step": 31566 + }, + { + "epoch": 9.75, + "learning_rate": 1.0891276722128786e-05, + "loss": 0.0256, + "step": 31567 + }, + { + "epoch": 9.75, + "learning_rate": 1.0890778593155112e-05, + "loss": 0.0233, + "step": 31568 + }, + { + "epoch": 9.75, + "learning_rate": 1.0890280461953441e-05, + "loss": 0.0228, + "step": 31569 + }, + { + "epoch": 9.75, + "learning_rate": 1.0889782328525018e-05, + "loss": 0.0243, + "step": 31570 + }, + { + "epoch": 9.75, + "learning_rate": 1.0889284192871083e-05, + "loss": 0.0219, + "step": 31571 + }, + { + "epoch": 9.75, + "learning_rate": 1.0888786054992892e-05, + "loss": 0.0247, + "step": 31572 + }, + { + "epoch": 9.75, + "learning_rate": 1.0888287914891682e-05, + "loss": 0.0257, + "step": 31573 + }, + { + "epoch": 9.75, + "learning_rate": 1.08877897725687e-05, + "loss": 0.0233, + "step": 31574 + }, + { + "epoch": 9.75, + "learning_rate": 1.0887291628025196e-05, + "loss": 0.0214, + "step": 31575 + }, + { + "epoch": 9.75, + "learning_rate": 1.0886793481262414e-05, + "loss": 0.0235, + "step": 31576 + }, + { + "epoch": 9.75, + "learning_rate": 1.0886295332281599e-05, + "loss": 0.0249, + "step": 31577 + }, + { + "epoch": 9.75, + "learning_rate": 1.0885797181083998e-05, + "loss": 0.0212, + "step": 31578 + }, + { + "epoch": 9.75, + "learning_rate": 1.0885299027670855e-05, + "loss": 0.0264, + "step": 31579 + }, + { + "epoch": 9.75, + "learning_rate": 1.0884800872043419e-05, + "loss": 0.0231, + "step": 31580 + }, + { + "epoch": 9.75, + "learning_rate": 1.0884302714202935e-05, + "loss": 0.0218, + "step": 31581 + }, + { + "epoch": 9.75, + "learning_rate": 1.0883804554150648e-05, + "loss": 0.025, + "step": 31582 + }, + { + "epoch": 9.75, + "learning_rate": 1.0883306391887805e-05, + "loss": 0.0251, + "step": 31583 + }, + { + "epoch": 9.75, + "learning_rate": 1.0882808227415651e-05, + "loss": 0.0212, + "step": 31584 + }, + { + "epoch": 9.75, + "learning_rate": 1.0882310060735435e-05, + "loss": 0.0213, + "step": 31585 + }, + { + "epoch": 9.75, + "learning_rate": 1.0881811891848396e-05, + "loss": 0.0259, + "step": 31586 + }, + { + "epoch": 9.75, + "learning_rate": 1.0881313720755789e-05, + "loss": 0.0235, + "step": 31587 + }, + { + "epoch": 9.76, + "learning_rate": 1.0880815547458855e-05, + "loss": 0.0218, + "step": 31588 + }, + { + "epoch": 9.76, + "learning_rate": 1.088031737195884e-05, + "loss": 0.025, + "step": 31589 + }, + { + "epoch": 9.76, + "learning_rate": 1.087981919425699e-05, + "loss": 0.0196, + "step": 31590 + }, + { + "epoch": 9.76, + "learning_rate": 1.087932101435455e-05, + "loss": 0.0247, + "step": 31591 + }, + { + "epoch": 9.76, + "learning_rate": 1.0878822832252771e-05, + "loss": 0.0232, + "step": 31592 + }, + { + "epoch": 9.76, + "learning_rate": 1.0878324647952896e-05, + "loss": 0.0208, + "step": 31593 + }, + { + "epoch": 9.76, + "learning_rate": 1.087782646145617e-05, + "loss": 0.0231, + "step": 31594 + }, + { + "epoch": 9.76, + "learning_rate": 1.087732827276384e-05, + "loss": 0.0262, + "step": 31595 + }, + { + "epoch": 9.76, + "learning_rate": 1.087683008187715e-05, + "loss": 0.0233, + "step": 31596 + }, + { + "epoch": 9.76, + "learning_rate": 1.087633188879735e-05, + "loss": 0.0234, + "step": 31597 + }, + { + "epoch": 9.76, + "learning_rate": 1.0875833693525683e-05, + "loss": 0.0229, + "step": 31598 + }, + { + "epoch": 9.76, + "learning_rate": 1.0875335496063397e-05, + "loss": 0.0251, + "step": 31599 + }, + { + "epoch": 9.76, + "learning_rate": 1.0874837296411737e-05, + "loss": 0.0225, + "step": 31600 + }, + { + "epoch": 9.76, + "learning_rate": 1.087433909457195e-05, + "loss": 0.0243, + "step": 31601 + }, + { + "epoch": 9.76, + "learning_rate": 1.0873840890545279e-05, + "loss": 0.0247, + "step": 31602 + }, + { + "epoch": 9.76, + "learning_rate": 1.0873342684332976e-05, + "loss": 0.0219, + "step": 31603 + }, + { + "epoch": 9.76, + "learning_rate": 1.0872844475936284e-05, + "loss": 0.0232, + "step": 31604 + }, + { + "epoch": 9.76, + "learning_rate": 1.0872346265356446e-05, + "loss": 0.0238, + "step": 31605 + }, + { + "epoch": 9.76, + "learning_rate": 1.0871848052594711e-05, + "loss": 0.0246, + "step": 31606 + }, + { + "epoch": 9.76, + "learning_rate": 1.0871349837652328e-05, + "loss": 0.024, + "step": 31607 + }, + { + "epoch": 9.76, + "learning_rate": 1.0870851620530536e-05, + "loss": 0.0244, + "step": 31608 + }, + { + "epoch": 9.76, + "learning_rate": 1.0870353401230586e-05, + "loss": 0.0209, + "step": 31609 + }, + { + "epoch": 9.76, + "learning_rate": 1.0869855179753725e-05, + "loss": 0.0242, + "step": 31610 + }, + { + "epoch": 9.76, + "learning_rate": 1.0869356956101198e-05, + "loss": 0.0228, + "step": 31611 + }, + { + "epoch": 9.76, + "learning_rate": 1.086885873027425e-05, + "loss": 0.0277, + "step": 31612 + }, + { + "epoch": 9.76, + "learning_rate": 1.0868360502274127e-05, + "loss": 0.0249, + "step": 31613 + }, + { + "epoch": 9.76, + "learning_rate": 1.0867862272102076e-05, + "loss": 0.0223, + "step": 31614 + }, + { + "epoch": 9.76, + "learning_rate": 1.0867364039759346e-05, + "loss": 0.0221, + "step": 31615 + }, + { + "epoch": 9.76, + "learning_rate": 1.0866865805247177e-05, + "loss": 0.0267, + "step": 31616 + }, + { + "epoch": 9.76, + "learning_rate": 1.086636756856682e-05, + "loss": 0.0245, + "step": 31617 + }, + { + "epoch": 9.76, + "learning_rate": 1.086586932971952e-05, + "loss": 0.0254, + "step": 31618 + }, + { + "epoch": 9.76, + "learning_rate": 1.0865371088706522e-05, + "loss": 0.0241, + "step": 31619 + }, + { + "epoch": 9.76, + "learning_rate": 1.0864872845529072e-05, + "loss": 0.0227, + "step": 31620 + }, + { + "epoch": 9.77, + "learning_rate": 1.0864374600188422e-05, + "loss": 0.0259, + "step": 31621 + }, + { + "epoch": 9.77, + "learning_rate": 1.0863876352685807e-05, + "loss": 0.0248, + "step": 31622 + }, + { + "epoch": 9.77, + "learning_rate": 1.0863378103022486e-05, + "loss": 0.0282, + "step": 31623 + }, + { + "epoch": 9.77, + "learning_rate": 1.0862879851199695e-05, + "loss": 0.0223, + "step": 31624 + }, + { + "epoch": 9.77, + "learning_rate": 1.0862381597218683e-05, + "loss": 0.0222, + "step": 31625 + }, + { + "epoch": 9.77, + "learning_rate": 1.0861883341080702e-05, + "loss": 0.0248, + "step": 31626 + }, + { + "epoch": 9.77, + "learning_rate": 1.0861385082786986e-05, + "loss": 0.0239, + "step": 31627 + }, + { + "epoch": 9.77, + "learning_rate": 1.0860886822338796e-05, + "loss": 0.0227, + "step": 31628 + }, + { + "epoch": 9.77, + "learning_rate": 1.086038855973737e-05, + "loss": 0.0231, + "step": 31629 + }, + { + "epoch": 9.77, + "learning_rate": 1.085989029498395e-05, + "loss": 0.0214, + "step": 31630 + }, + { + "epoch": 9.77, + "learning_rate": 1.0859392028079794e-05, + "loss": 0.0256, + "step": 31631 + }, + { + "epoch": 9.77, + "learning_rate": 1.0858893759026139e-05, + "loss": 0.022, + "step": 31632 + }, + { + "epoch": 9.77, + "learning_rate": 1.0858395487824234e-05, + "loss": 0.0219, + "step": 31633 + }, + { + "epoch": 9.77, + "learning_rate": 1.0857897214475325e-05, + "loss": 0.0227, + "step": 31634 + }, + { + "epoch": 9.77, + "learning_rate": 1.0857398938980659e-05, + "loss": 0.0208, + "step": 31635 + }, + { + "epoch": 9.77, + "learning_rate": 1.0856900661341483e-05, + "loss": 0.0264, + "step": 31636 + }, + { + "epoch": 9.77, + "learning_rate": 1.0856402381559041e-05, + "loss": 0.0224, + "step": 31637 + }, + { + "epoch": 9.77, + "learning_rate": 1.085590409963458e-05, + "loss": 0.0237, + "step": 31638 + }, + { + "epoch": 9.77, + "learning_rate": 1.0855405815569346e-05, + "loss": 0.0234, + "step": 31639 + }, + { + "epoch": 9.77, + "learning_rate": 1.0854907529364588e-05, + "loss": 0.0239, + "step": 31640 + }, + { + "epoch": 9.77, + "learning_rate": 1.085440924102155e-05, + "loss": 0.0229, + "step": 31641 + }, + { + "epoch": 9.77, + "learning_rate": 1.085391095054148e-05, + "loss": 0.0264, + "step": 31642 + }, + { + "epoch": 9.77, + "learning_rate": 1.085341265792562e-05, + "loss": 0.022, + "step": 31643 + }, + { + "epoch": 9.77, + "learning_rate": 1.085291436317522e-05, + "loss": 0.026, + "step": 31644 + }, + { + "epoch": 9.77, + "learning_rate": 1.0852416066291526e-05, + "loss": 0.0238, + "step": 31645 + }, + { + "epoch": 9.77, + "learning_rate": 1.0851917767275786e-05, + "loss": 0.0234, + "step": 31646 + }, + { + "epoch": 9.77, + "learning_rate": 1.0851419466129242e-05, + "loss": 0.0211, + "step": 31647 + }, + { + "epoch": 9.77, + "learning_rate": 1.0850921162853143e-05, + "loss": 0.0229, + "step": 31648 + }, + { + "epoch": 9.77, + "learning_rate": 1.0850422857448737e-05, + "loss": 0.022, + "step": 31649 + }, + { + "epoch": 9.77, + "learning_rate": 1.0849924549917264e-05, + "loss": 0.0231, + "step": 31650 + }, + { + "epoch": 9.77, + "learning_rate": 1.0849426240259977e-05, + "loss": 0.0262, + "step": 31651 + }, + { + "epoch": 9.77, + "learning_rate": 1.084892792847812e-05, + "loss": 0.0212, + "step": 31652 + }, + { + "epoch": 9.78, + "learning_rate": 1.084842961457294e-05, + "loss": 0.0254, + "step": 31653 + }, + { + "epoch": 9.78, + "learning_rate": 1.0847931298545685e-05, + "loss": 0.0246, + "step": 31654 + }, + { + "epoch": 9.78, + "learning_rate": 1.0847432980397597e-05, + "loss": 0.0234, + "step": 31655 + }, + { + "epoch": 9.78, + "learning_rate": 1.0846934660129919e-05, + "loss": 0.0222, + "step": 31656 + }, + { + "epoch": 9.78, + "learning_rate": 1.084643633774391e-05, + "loss": 0.0269, + "step": 31657 + }, + { + "epoch": 9.78, + "learning_rate": 1.0845938013240808e-05, + "loss": 0.022, + "step": 31658 + }, + { + "epoch": 9.78, + "learning_rate": 1.084543968662186e-05, + "loss": 0.0253, + "step": 31659 + }, + { + "epoch": 9.78, + "learning_rate": 1.0844941357888314e-05, + "loss": 0.0204, + "step": 31660 + }, + { + "epoch": 9.78, + "learning_rate": 1.0844443027041413e-05, + "loss": 0.0245, + "step": 31661 + }, + { + "epoch": 9.78, + "learning_rate": 1.0843944694082409e-05, + "loss": 0.0253, + "step": 31662 + }, + { + "epoch": 9.78, + "learning_rate": 1.0843446359012544e-05, + "loss": 0.0235, + "step": 31663 + }, + { + "epoch": 9.78, + "learning_rate": 1.0842948021833066e-05, + "loss": 0.0249, + "step": 31664 + }, + { + "epoch": 9.78, + "learning_rate": 1.0842449682545223e-05, + "loss": 0.0223, + "step": 31665 + }, + { + "epoch": 9.78, + "learning_rate": 1.0841951341150256e-05, + "loss": 0.0267, + "step": 31666 + }, + { + "epoch": 9.78, + "learning_rate": 1.0841452997649418e-05, + "loss": 0.0237, + "step": 31667 + }, + { + "epoch": 9.78, + "learning_rate": 1.0840954652043951e-05, + "loss": 0.0227, + "step": 31668 + }, + { + "epoch": 9.78, + "learning_rate": 1.0840456304335103e-05, + "loss": 0.0249, + "step": 31669 + }, + { + "epoch": 9.78, + "learning_rate": 1.083995795452412e-05, + "loss": 0.0256, + "step": 31670 + }, + { + "epoch": 9.78, + "learning_rate": 1.0839459602612252e-05, + "loss": 0.023, + "step": 31671 + }, + { + "epoch": 9.78, + "learning_rate": 1.0838961248600744e-05, + "loss": 0.0219, + "step": 31672 + }, + { + "epoch": 9.78, + "learning_rate": 1.0838462892490833e-05, + "loss": 0.0277, + "step": 31673 + }, + { + "epoch": 9.78, + "learning_rate": 1.0837964534283779e-05, + "loss": 0.0233, + "step": 31674 + }, + { + "epoch": 9.78, + "learning_rate": 1.0837466173980821e-05, + "loss": 0.0229, + "step": 31675 + }, + { + "epoch": 9.78, + "learning_rate": 1.0836967811583208e-05, + "loss": 0.0232, + "step": 31676 + }, + { + "epoch": 9.78, + "learning_rate": 1.0836469447092188e-05, + "loss": 0.0225, + "step": 31677 + }, + { + "epoch": 9.78, + "learning_rate": 1.0835971080509001e-05, + "loss": 0.0235, + "step": 31678 + }, + { + "epoch": 9.78, + "learning_rate": 1.08354727118349e-05, + "loss": 0.0276, + "step": 31679 + }, + { + "epoch": 9.78, + "learning_rate": 1.0834974341071131e-05, + "loss": 0.0207, + "step": 31680 + }, + { + "epoch": 9.78, + "learning_rate": 1.0834475968218936e-05, + "loss": 0.0262, + "step": 31681 + }, + { + "epoch": 9.78, + "learning_rate": 1.0833977593279568e-05, + "loss": 0.0231, + "step": 31682 + }, + { + "epoch": 9.78, + "learning_rate": 1.0833479216254267e-05, + "loss": 0.026, + "step": 31683 + }, + { + "epoch": 9.78, + "learning_rate": 1.083298083714428e-05, + "loss": 0.0231, + "step": 31684 + }, + { + "epoch": 9.78, + "learning_rate": 1.0832482455950864e-05, + "loss": 0.0228, + "step": 31685 + }, + { + "epoch": 9.79, + "learning_rate": 1.0831984072675251e-05, + "loss": 0.0234, + "step": 31686 + }, + { + "epoch": 9.79, + "learning_rate": 1.0831485687318697e-05, + "loss": 0.023, + "step": 31687 + }, + { + "epoch": 9.79, + "learning_rate": 1.0830987299882443e-05, + "loss": 0.0245, + "step": 31688 + }, + { + "epoch": 9.79, + "learning_rate": 1.083048891036774e-05, + "loss": 0.0249, + "step": 31689 + }, + { + "epoch": 9.79, + "learning_rate": 1.0829990518775832e-05, + "loss": 0.0241, + "step": 31690 + }, + { + "epoch": 9.79, + "learning_rate": 1.0829492125107967e-05, + "loss": 0.0237, + "step": 31691 + }, + { + "epoch": 9.79, + "learning_rate": 1.0828993729365392e-05, + "loss": 0.0219, + "step": 31692 + }, + { + "epoch": 9.79, + "learning_rate": 1.0828495331549349e-05, + "loss": 0.0237, + "step": 31693 + }, + { + "epoch": 9.79, + "learning_rate": 1.0827996931661091e-05, + "loss": 0.0245, + "step": 31694 + }, + { + "epoch": 9.79, + "learning_rate": 1.0827498529701861e-05, + "loss": 0.0239, + "step": 31695 + }, + { + "epoch": 9.79, + "learning_rate": 1.0827000125672906e-05, + "loss": 0.0286, + "step": 31696 + }, + { + "epoch": 9.79, + "learning_rate": 1.0826501719575473e-05, + "loss": 0.0238, + "step": 31697 + }, + { + "epoch": 9.79, + "learning_rate": 1.0826003311410807e-05, + "loss": 0.0216, + "step": 31698 + }, + { + "epoch": 9.79, + "learning_rate": 1.0825504901180158e-05, + "loss": 0.0247, + "step": 31699 + }, + { + "epoch": 9.79, + "learning_rate": 1.0825006488884771e-05, + "loss": 0.0224, + "step": 31700 + }, + { + "epoch": 9.79, + "learning_rate": 1.082450807452589e-05, + "loss": 0.0239, + "step": 31701 + }, + { + "epoch": 9.79, + "learning_rate": 1.0824009658104765e-05, + "loss": 0.0235, + "step": 31702 + }, + { + "epoch": 9.79, + "learning_rate": 1.0823511239622643e-05, + "loss": 0.0254, + "step": 31703 + }, + { + "epoch": 9.79, + "learning_rate": 1.0823012819080768e-05, + "loss": 0.0231, + "step": 31704 + }, + { + "epoch": 9.79, + "learning_rate": 1.0822514396480388e-05, + "loss": 0.0236, + "step": 31705 + }, + { + "epoch": 9.79, + "learning_rate": 1.082201597182275e-05, + "loss": 0.0226, + "step": 31706 + }, + { + "epoch": 9.79, + "learning_rate": 1.08215175451091e-05, + "loss": 0.0224, + "step": 31707 + }, + { + "epoch": 9.79, + "learning_rate": 1.0821019116340686e-05, + "loss": 0.0254, + "step": 31708 + }, + { + "epoch": 9.79, + "learning_rate": 1.0820520685518747e-05, + "loss": 0.0246, + "step": 31709 + }, + { + "epoch": 9.79, + "learning_rate": 1.0820022252644543e-05, + "loss": 0.0222, + "step": 31710 + }, + { + "epoch": 9.79, + "learning_rate": 1.0819523817719314e-05, + "loss": 0.0213, + "step": 31711 + }, + { + "epoch": 9.79, + "learning_rate": 1.08190253807443e-05, + "loss": 0.0247, + "step": 31712 + }, + { + "epoch": 9.79, + "learning_rate": 1.0818526941720762e-05, + "loss": 0.0245, + "step": 31713 + }, + { + "epoch": 9.79, + "learning_rate": 1.0818028500649935e-05, + "loss": 0.0234, + "step": 31714 + }, + { + "epoch": 9.79, + "learning_rate": 1.0817530057533068e-05, + "loss": 0.0248, + "step": 31715 + }, + { + "epoch": 9.79, + "learning_rate": 1.0817031612371412e-05, + "loss": 0.0279, + "step": 31716 + }, + { + "epoch": 9.79, + "learning_rate": 1.081653316516621e-05, + "loss": 0.0219, + "step": 31717 + }, + { + "epoch": 9.8, + "learning_rate": 1.0816034715918709e-05, + "loss": 0.0226, + "step": 31718 + }, + { + "epoch": 9.8, + "learning_rate": 1.0815536264630156e-05, + "loss": 0.0215, + "step": 31719 + }, + { + "epoch": 9.8, + "learning_rate": 1.0815037811301798e-05, + "loss": 0.0253, + "step": 31720 + }, + { + "epoch": 9.8, + "learning_rate": 1.0814539355934884e-05, + "loss": 0.0229, + "step": 31721 + }, + { + "epoch": 9.8, + "learning_rate": 1.0814040898530656e-05, + "loss": 0.0262, + "step": 31722 + }, + { + "epoch": 9.8, + "learning_rate": 1.0813542439090366e-05, + "loss": 0.0262, + "step": 31723 + }, + { + "epoch": 9.8, + "learning_rate": 1.0813043977615254e-05, + "loss": 0.023, + "step": 31724 + }, + { + "epoch": 9.8, + "learning_rate": 1.0812545514106574e-05, + "loss": 0.026, + "step": 31725 + }, + { + "epoch": 9.8, + "learning_rate": 1.0812047048565569e-05, + "loss": 0.0216, + "step": 31726 + }, + { + "epoch": 9.8, + "learning_rate": 1.0811548580993484e-05, + "loss": 0.0242, + "step": 31727 + }, + { + "epoch": 9.8, + "learning_rate": 1.081105011139157e-05, + "loss": 0.0274, + "step": 31728 + }, + { + "epoch": 9.8, + "learning_rate": 1.0810551639761072e-05, + "loss": 0.024, + "step": 31729 + }, + { + "epoch": 9.8, + "learning_rate": 1.0810053166103235e-05, + "loss": 0.0211, + "step": 31730 + }, + { + "epoch": 9.8, + "learning_rate": 1.080955469041931e-05, + "loss": 0.0258, + "step": 31731 + }, + { + "epoch": 9.8, + "learning_rate": 1.0809056212710538e-05, + "loss": 0.0243, + "step": 31732 + }, + { + "epoch": 9.8, + "learning_rate": 1.0808557732978171e-05, + "loss": 0.0243, + "step": 31733 + }, + { + "epoch": 9.8, + "learning_rate": 1.0808059251223455e-05, + "loss": 0.0253, + "step": 31734 + }, + { + "epoch": 9.8, + "learning_rate": 1.080756076744763e-05, + "loss": 0.0242, + "step": 31735 + }, + { + "epoch": 9.8, + "learning_rate": 1.0807062281651953e-05, + "loss": 0.024, + "step": 31736 + }, + { + "epoch": 9.8, + "learning_rate": 1.0806563793837665e-05, + "loss": 0.0238, + "step": 31737 + }, + { + "epoch": 9.8, + "learning_rate": 1.080606530400601e-05, + "loss": 0.0241, + "step": 31738 + }, + { + "epoch": 9.8, + "learning_rate": 1.0805566812158245e-05, + "loss": 0.0265, + "step": 31739 + }, + { + "epoch": 9.8, + "learning_rate": 1.0805068318295608e-05, + "loss": 0.0231, + "step": 31740 + }, + { + "epoch": 9.8, + "learning_rate": 1.0804569822419346e-05, + "loss": 0.0261, + "step": 31741 + }, + { + "epoch": 9.8, + "learning_rate": 1.0804071324530712e-05, + "loss": 0.0218, + "step": 31742 + }, + { + "epoch": 9.8, + "learning_rate": 1.0803572824630943e-05, + "loss": 0.0253, + "step": 31743 + }, + { + "epoch": 9.8, + "learning_rate": 1.0803074322721298e-05, + "loss": 0.0224, + "step": 31744 + }, + { + "epoch": 9.8, + "learning_rate": 1.0802575818803017e-05, + "loss": 0.0226, + "step": 31745 + }, + { + "epoch": 9.8, + "learning_rate": 1.0802077312877342e-05, + "loss": 0.0242, + "step": 31746 + }, + { + "epoch": 9.8, + "learning_rate": 1.0801578804945532e-05, + "loss": 0.0237, + "step": 31747 + }, + { + "epoch": 9.8, + "learning_rate": 1.0801080295008824e-05, + "loss": 0.0197, + "step": 31748 + }, + { + "epoch": 9.8, + "learning_rate": 1.0800581783068469e-05, + "loss": 0.0232, + "step": 31749 + }, + { + "epoch": 9.81, + "learning_rate": 1.0800083269125712e-05, + "loss": 0.0281, + "step": 31750 + }, + { + "epoch": 9.81, + "learning_rate": 1.07995847531818e-05, + "loss": 0.0232, + "step": 31751 + }, + { + "epoch": 9.81, + "learning_rate": 1.0799086235237983e-05, + "loss": 0.0232, + "step": 31752 + }, + { + "epoch": 9.81, + "learning_rate": 1.0798587715295503e-05, + "loss": 0.0237, + "step": 31753 + }, + { + "epoch": 9.81, + "learning_rate": 1.0798089193355612e-05, + "loss": 0.0237, + "step": 31754 + }, + { + "epoch": 9.81, + "learning_rate": 1.0797590669419553e-05, + "loss": 0.025, + "step": 31755 + }, + { + "epoch": 9.81, + "learning_rate": 1.0797092143488574e-05, + "loss": 0.0218, + "step": 31756 + }, + { + "epoch": 9.81, + "learning_rate": 1.0796593615563924e-05, + "loss": 0.0224, + "step": 31757 + }, + { + "epoch": 9.81, + "learning_rate": 1.0796095085646847e-05, + "loss": 0.0216, + "step": 31758 + }, + { + "epoch": 9.81, + "learning_rate": 1.079559655373859e-05, + "loss": 0.0252, + "step": 31759 + }, + { + "epoch": 9.81, + "learning_rate": 1.0795098019840402e-05, + "loss": 0.0247, + "step": 31760 + }, + { + "epoch": 9.81, + "learning_rate": 1.0794599483953527e-05, + "loss": 0.0223, + "step": 31761 + }, + { + "epoch": 9.81, + "learning_rate": 1.0794100946079217e-05, + "loss": 0.0236, + "step": 31762 + }, + { + "epoch": 9.81, + "learning_rate": 1.0793602406218712e-05, + "loss": 0.0241, + "step": 31763 + }, + { + "epoch": 9.81, + "learning_rate": 1.0793103864373267e-05, + "loss": 0.0242, + "step": 31764 + }, + { + "epoch": 9.81, + "learning_rate": 1.0792605320544123e-05, + "loss": 0.0257, + "step": 31765 + }, + { + "epoch": 9.81, + "learning_rate": 1.0792106774732527e-05, + "loss": 0.0249, + "step": 31766 + }, + { + "epoch": 9.81, + "learning_rate": 1.0791608226939729e-05, + "loss": 0.0245, + "step": 31767 + }, + { + "epoch": 9.81, + "learning_rate": 1.0791109677166973e-05, + "loss": 0.0226, + "step": 31768 + }, + { + "epoch": 9.81, + "learning_rate": 1.0790611125415506e-05, + "loss": 0.0227, + "step": 31769 + }, + { + "epoch": 9.81, + "learning_rate": 1.0790112571686581e-05, + "loss": 0.0228, + "step": 31770 + }, + { + "epoch": 9.81, + "learning_rate": 1.0789614015981437e-05, + "loss": 0.0243, + "step": 31771 + }, + { + "epoch": 9.81, + "learning_rate": 1.0789115458301327e-05, + "loss": 0.0216, + "step": 31772 + }, + { + "epoch": 9.81, + "learning_rate": 1.0788616898647492e-05, + "loss": 0.0277, + "step": 31773 + }, + { + "epoch": 9.81, + "learning_rate": 1.0788118337021183e-05, + "loss": 0.0239, + "step": 31774 + }, + { + "epoch": 9.81, + "learning_rate": 1.0787619773423648e-05, + "loss": 0.0236, + "step": 31775 + }, + { + "epoch": 9.81, + "learning_rate": 1.0787121207856133e-05, + "loss": 0.0244, + "step": 31776 + }, + { + "epoch": 9.81, + "learning_rate": 1.0786622640319882e-05, + "loss": 0.0235, + "step": 31777 + }, + { + "epoch": 9.81, + "learning_rate": 1.0786124070816144e-05, + "loss": 0.024, + "step": 31778 + }, + { + "epoch": 9.81, + "learning_rate": 1.0785625499346169e-05, + "loss": 0.0258, + "step": 31779 + }, + { + "epoch": 9.81, + "learning_rate": 1.0785126925911199e-05, + "loss": 0.0258, + "step": 31780 + }, + { + "epoch": 9.81, + "learning_rate": 1.0784628350512483e-05, + "loss": 0.0237, + "step": 31781 + }, + { + "epoch": 9.81, + "learning_rate": 1.078412977315127e-05, + "loss": 0.0222, + "step": 31782 + }, + { + "epoch": 9.82, + "learning_rate": 1.0783631193828805e-05, + "loss": 0.023, + "step": 31783 + }, + { + "epoch": 9.82, + "learning_rate": 1.0783132612546334e-05, + "loss": 0.0214, + "step": 31784 + }, + { + "epoch": 9.82, + "learning_rate": 1.0782634029305108e-05, + "loss": 0.0264, + "step": 31785 + }, + { + "epoch": 9.82, + "learning_rate": 1.078213544410637e-05, + "loss": 0.0253, + "step": 31786 + }, + { + "epoch": 9.82, + "learning_rate": 1.0781636856951368e-05, + "loss": 0.0233, + "step": 31787 + }, + { + "epoch": 9.82, + "learning_rate": 1.0781138267841354e-05, + "loss": 0.0229, + "step": 31788 + }, + { + "epoch": 9.82, + "learning_rate": 1.0780639676777564e-05, + "loss": 0.0242, + "step": 31789 + }, + { + "epoch": 9.82, + "learning_rate": 1.0780141083761256e-05, + "loss": 0.0243, + "step": 31790 + }, + { + "epoch": 9.82, + "learning_rate": 1.0779642488793672e-05, + "loss": 0.0264, + "step": 31791 + }, + { + "epoch": 9.82, + "learning_rate": 1.0779143891876058e-05, + "loss": 0.0248, + "step": 31792 + }, + { + "epoch": 9.82, + "learning_rate": 1.077864529300967e-05, + "loss": 0.0227, + "step": 31793 + }, + { + "epoch": 9.82, + "learning_rate": 1.077814669219574e-05, + "loss": 0.0235, + "step": 31794 + }, + { + "epoch": 9.82, + "learning_rate": 1.0777648089435523e-05, + "loss": 0.0252, + "step": 31795 + }, + { + "epoch": 9.82, + "learning_rate": 1.0777149484730274e-05, + "loss": 0.0246, + "step": 31796 + }, + { + "epoch": 9.82, + "learning_rate": 1.0776650878081226e-05, + "loss": 0.0219, + "step": 31797 + }, + { + "epoch": 9.82, + "learning_rate": 1.0776152269489635e-05, + "loss": 0.0229, + "step": 31798 + }, + { + "epoch": 9.82, + "learning_rate": 1.0775653658956746e-05, + "loss": 0.0261, + "step": 31799 + }, + { + "epoch": 9.82, + "learning_rate": 1.0775155046483803e-05, + "loss": 0.021, + "step": 31800 + }, + { + "epoch": 9.82, + "learning_rate": 1.0774656432072059e-05, + "loss": 0.0224, + "step": 31801 + }, + { + "epoch": 9.82, + "learning_rate": 1.0774157815722757e-05, + "loss": 0.0255, + "step": 31802 + }, + { + "epoch": 9.82, + "learning_rate": 1.0773659197437144e-05, + "loss": 0.0261, + "step": 31803 + }, + { + "epoch": 9.82, + "learning_rate": 1.0773160577216468e-05, + "loss": 0.021, + "step": 31804 + }, + { + "epoch": 9.82, + "learning_rate": 1.0772661955061979e-05, + "loss": 0.0198, + "step": 31805 + }, + { + "epoch": 9.82, + "learning_rate": 1.0772163330974918e-05, + "loss": 0.0252, + "step": 31806 + }, + { + "epoch": 9.82, + "learning_rate": 1.0771664704956537e-05, + "loss": 0.0212, + "step": 31807 + }, + { + "epoch": 9.82, + "learning_rate": 1.0771166077008083e-05, + "loss": 0.0219, + "step": 31808 + }, + { + "epoch": 9.82, + "learning_rate": 1.07706674471308e-05, + "loss": 0.0263, + "step": 31809 + }, + { + "epoch": 9.82, + "learning_rate": 1.077016881532594e-05, + "loss": 0.0239, + "step": 31810 + }, + { + "epoch": 9.82, + "learning_rate": 1.0769670181594744e-05, + "loss": 0.0227, + "step": 31811 + }, + { + "epoch": 9.82, + "learning_rate": 1.0769171545938467e-05, + "loss": 0.0281, + "step": 31812 + }, + { + "epoch": 9.82, + "learning_rate": 1.0768672908358349e-05, + "loss": 0.0247, + "step": 31813 + }, + { + "epoch": 9.82, + "learning_rate": 1.0768174268855639e-05, + "loss": 0.0253, + "step": 31814 + }, + { + "epoch": 9.83, + "learning_rate": 1.0767675627431587e-05, + "loss": 0.0242, + "step": 31815 + }, + { + "epoch": 9.83, + "learning_rate": 1.0767176984087437e-05, + "loss": 0.0223, + "step": 31816 + }, + { + "epoch": 9.83, + "learning_rate": 1.0766678338824437e-05, + "loss": 0.0242, + "step": 31817 + }, + { + "epoch": 9.83, + "learning_rate": 1.0766179691643834e-05, + "loss": 0.0256, + "step": 31818 + }, + { + "epoch": 9.83, + "learning_rate": 1.0765681042546879e-05, + "loss": 0.0209, + "step": 31819 + }, + { + "epoch": 9.83, + "learning_rate": 1.0765182391534812e-05, + "loss": 0.0243, + "step": 31820 + }, + { + "epoch": 9.83, + "learning_rate": 1.0764683738608887e-05, + "loss": 0.0219, + "step": 31821 + }, + { + "epoch": 9.83, + "learning_rate": 1.0764185083770347e-05, + "loss": 0.0278, + "step": 31822 + }, + { + "epoch": 9.83, + "learning_rate": 1.076368642702044e-05, + "loss": 0.0264, + "step": 31823 + }, + { + "epoch": 9.83, + "learning_rate": 1.0763187768360419e-05, + "loss": 0.0283, + "step": 31824 + }, + { + "epoch": 9.83, + "learning_rate": 1.0762689107791522e-05, + "loss": 0.0253, + "step": 31825 + }, + { + "epoch": 9.83, + "learning_rate": 1.0762190445315001e-05, + "loss": 0.0224, + "step": 31826 + }, + { + "epoch": 9.83, + "learning_rate": 1.0761691780932105e-05, + "loss": 0.0263, + "step": 31827 + }, + { + "epoch": 9.83, + "learning_rate": 1.0761193114644073e-05, + "loss": 0.0229, + "step": 31828 + }, + { + "epoch": 9.83, + "learning_rate": 1.0760694446452165e-05, + "loss": 0.0243, + "step": 31829 + }, + { + "epoch": 9.83, + "learning_rate": 1.0760195776357618e-05, + "loss": 0.0244, + "step": 31830 + }, + { + "epoch": 9.83, + "learning_rate": 1.0759697104361684e-05, + "loss": 0.0237, + "step": 31831 + }, + { + "epoch": 9.83, + "learning_rate": 1.0759198430465608e-05, + "loss": 0.0227, + "step": 31832 + }, + { + "epoch": 9.83, + "learning_rate": 1.0758699754670638e-05, + "loss": 0.023, + "step": 31833 + }, + { + "epoch": 9.83, + "learning_rate": 1.0758201076978021e-05, + "loss": 0.0221, + "step": 31834 + }, + { + "epoch": 9.83, + "learning_rate": 1.0757702397389006e-05, + "loss": 0.0274, + "step": 31835 + }, + { + "epoch": 9.83, + "learning_rate": 1.0757203715904838e-05, + "loss": 0.0237, + "step": 31836 + }, + { + "epoch": 9.83, + "learning_rate": 1.0756705032526767e-05, + "loss": 0.0247, + "step": 31837 + }, + { + "epoch": 9.83, + "learning_rate": 1.0756206347256038e-05, + "loss": 0.0252, + "step": 31838 + }, + { + "epoch": 9.83, + "learning_rate": 1.0755707660093899e-05, + "loss": 0.0215, + "step": 31839 + }, + { + "epoch": 9.83, + "learning_rate": 1.0755208971041598e-05, + "loss": 0.0213, + "step": 31840 + }, + { + "epoch": 9.83, + "learning_rate": 1.075471028010038e-05, + "loss": 0.0264, + "step": 31841 + }, + { + "epoch": 9.83, + "learning_rate": 1.0754211587271494e-05, + "loss": 0.0267, + "step": 31842 + }, + { + "epoch": 9.83, + "learning_rate": 1.0753712892556189e-05, + "loss": 0.028, + "step": 31843 + }, + { + "epoch": 9.83, + "learning_rate": 1.075321419595571e-05, + "loss": 0.0225, + "step": 31844 + }, + { + "epoch": 9.83, + "learning_rate": 1.0752715497471304e-05, + "loss": 0.0216, + "step": 31845 + }, + { + "epoch": 9.83, + "learning_rate": 1.075221679710422e-05, + "loss": 0.0238, + "step": 31846 + }, + { + "epoch": 9.83, + "learning_rate": 1.0751718094855705e-05, + "loss": 0.023, + "step": 31847 + }, + { + "epoch": 9.84, + "learning_rate": 1.0751219390727003e-05, + "loss": 0.0249, + "step": 31848 + }, + { + "epoch": 9.84, + "learning_rate": 1.0750720684719368e-05, + "loss": 0.0279, + "step": 31849 + }, + { + "epoch": 9.84, + "learning_rate": 1.0750221976834045e-05, + "loss": 0.0217, + "step": 31850 + }, + { + "epoch": 9.84, + "learning_rate": 1.0749723267072274e-05, + "loss": 0.0229, + "step": 31851 + }, + { + "epoch": 9.84, + "learning_rate": 1.0749224555435314e-05, + "loss": 0.0236, + "step": 31852 + }, + { + "epoch": 9.84, + "learning_rate": 1.0748725841924403e-05, + "loss": 0.0233, + "step": 31853 + }, + { + "epoch": 9.84, + "learning_rate": 1.0748227126540793e-05, + "loss": 0.0236, + "step": 31854 + }, + { + "epoch": 9.84, + "learning_rate": 1.0747728409285734e-05, + "loss": 0.025, + "step": 31855 + }, + { + "epoch": 9.84, + "learning_rate": 1.0747229690160464e-05, + "loss": 0.024, + "step": 31856 + }, + { + "epoch": 9.84, + "learning_rate": 1.0746730969166242e-05, + "loss": 0.0232, + "step": 31857 + }, + { + "epoch": 9.84, + "learning_rate": 1.0746232246304306e-05, + "loss": 0.0241, + "step": 31858 + }, + { + "epoch": 9.84, + "learning_rate": 1.0745733521575906e-05, + "loss": 0.025, + "step": 31859 + }, + { + "epoch": 9.84, + "learning_rate": 1.0745234794982293e-05, + "loss": 0.024, + "step": 31860 + }, + { + "epoch": 9.84, + "learning_rate": 1.0744736066524713e-05, + "loss": 0.0249, + "step": 31861 + }, + { + "epoch": 9.84, + "learning_rate": 1.0744237336204408e-05, + "loss": 0.0232, + "step": 31862 + }, + { + "epoch": 9.84, + "learning_rate": 1.0743738604022633e-05, + "loss": 0.0257, + "step": 31863 + }, + { + "epoch": 9.84, + "learning_rate": 1.074323986998063e-05, + "loss": 0.0256, + "step": 31864 + }, + { + "epoch": 9.84, + "learning_rate": 1.074274113407965e-05, + "loss": 0.0229, + "step": 31865 + }, + { + "epoch": 9.84, + "learning_rate": 1.074224239632094e-05, + "loss": 0.0228, + "step": 31866 + }, + { + "epoch": 9.84, + "learning_rate": 1.0741743656705745e-05, + "loss": 0.0241, + "step": 31867 + }, + { + "epoch": 9.84, + "learning_rate": 1.0741244915235314e-05, + "loss": 0.0248, + "step": 31868 + }, + { + "epoch": 9.84, + "learning_rate": 1.0740746171910894e-05, + "loss": 0.0215, + "step": 31869 + }, + { + "epoch": 9.84, + "learning_rate": 1.0740247426733735e-05, + "loss": 0.0235, + "step": 31870 + }, + { + "epoch": 9.84, + "learning_rate": 1.0739748679705078e-05, + "loss": 0.0241, + "step": 31871 + }, + { + "epoch": 9.84, + "learning_rate": 1.0739249930826177e-05, + "loss": 0.0245, + "step": 31872 + }, + { + "epoch": 9.84, + "learning_rate": 1.0738751180098275e-05, + "loss": 0.0257, + "step": 31873 + }, + { + "epoch": 9.84, + "learning_rate": 1.0738252427522625e-05, + "loss": 0.0218, + "step": 31874 + }, + { + "epoch": 9.84, + "learning_rate": 1.073775367310047e-05, + "loss": 0.0222, + "step": 31875 + }, + { + "epoch": 9.84, + "learning_rate": 1.0737254916833055e-05, + "loss": 0.0261, + "step": 31876 + }, + { + "epoch": 9.84, + "learning_rate": 1.0736756158721635e-05, + "loss": 0.0235, + "step": 31877 + }, + { + "epoch": 9.84, + "learning_rate": 1.0736257398767453e-05, + "loss": 0.0254, + "step": 31878 + }, + { + "epoch": 9.84, + "learning_rate": 1.0735758636971756e-05, + "loss": 0.0226, + "step": 31879 + }, + { + "epoch": 9.85, + "learning_rate": 1.0735259873335795e-05, + "loss": 0.0255, + "step": 31880 + }, + { + "epoch": 9.85, + "learning_rate": 1.0734761107860812e-05, + "loss": 0.025, + "step": 31881 + }, + { + "epoch": 9.85, + "learning_rate": 1.0734262340548056e-05, + "loss": 0.0223, + "step": 31882 + }, + { + "epoch": 9.85, + "learning_rate": 1.0733763571398781e-05, + "loss": 0.0266, + "step": 31883 + }, + { + "epoch": 9.85, + "learning_rate": 1.0733264800414225e-05, + "loss": 0.0215, + "step": 31884 + }, + { + "epoch": 9.85, + "learning_rate": 1.0732766027595643e-05, + "loss": 0.024, + "step": 31885 + }, + { + "epoch": 9.85, + "learning_rate": 1.0732267252944277e-05, + "loss": 0.023, + "step": 31886 + }, + { + "epoch": 9.85, + "learning_rate": 1.073176847646138e-05, + "loss": 0.0248, + "step": 31887 + }, + { + "epoch": 9.85, + "learning_rate": 1.0731269698148193e-05, + "loss": 0.024, + "step": 31888 + }, + { + "epoch": 9.85, + "learning_rate": 1.0730770918005969e-05, + "loss": 0.0231, + "step": 31889 + }, + { + "epoch": 9.85, + "learning_rate": 1.0730272136035952e-05, + "loss": 0.0274, + "step": 31890 + }, + { + "epoch": 9.85, + "learning_rate": 1.0729773352239394e-05, + "loss": 0.025, + "step": 31891 + }, + { + "epoch": 9.85, + "learning_rate": 1.0729274566617538e-05, + "loss": 0.0236, + "step": 31892 + }, + { + "epoch": 9.85, + "learning_rate": 1.0728775779171633e-05, + "loss": 0.0245, + "step": 31893 + }, + { + "epoch": 9.85, + "learning_rate": 1.0728276989902928e-05, + "loss": 0.0236, + "step": 31894 + }, + { + "epoch": 9.85, + "learning_rate": 1.072777819881267e-05, + "loss": 0.0234, + "step": 31895 + }, + { + "epoch": 9.85, + "learning_rate": 1.0727279405902104e-05, + "loss": 0.0226, + "step": 31896 + }, + { + "epoch": 9.85, + "learning_rate": 1.072678061117248e-05, + "loss": 0.0246, + "step": 31897 + }, + { + "epoch": 9.85, + "learning_rate": 1.0726281814625046e-05, + "loss": 0.0233, + "step": 31898 + }, + { + "epoch": 9.85, + "learning_rate": 1.0725783016261049e-05, + "loss": 0.0245, + "step": 31899 + }, + { + "epoch": 9.85, + "learning_rate": 1.0725284216081735e-05, + "loss": 0.0225, + "step": 31900 + }, + { + "epoch": 9.85, + "learning_rate": 1.0724785414088357e-05, + "loss": 0.0223, + "step": 31901 + }, + { + "epoch": 9.85, + "learning_rate": 1.0724286610282153e-05, + "loss": 0.0257, + "step": 31902 + }, + { + "epoch": 9.85, + "learning_rate": 1.0723787804664378e-05, + "loss": 0.0202, + "step": 31903 + }, + { + "epoch": 9.85, + "learning_rate": 1.0723288997236277e-05, + "loss": 0.021, + "step": 31904 + }, + { + "epoch": 9.85, + "learning_rate": 1.07227901879991e-05, + "loss": 0.0249, + "step": 31905 + }, + { + "epoch": 9.85, + "learning_rate": 1.0722291376954093e-05, + "loss": 0.0238, + "step": 31906 + }, + { + "epoch": 9.85, + "learning_rate": 1.07217925641025e-05, + "loss": 0.0214, + "step": 31907 + }, + { + "epoch": 9.85, + "learning_rate": 1.0721293749445576e-05, + "loss": 0.0242, + "step": 31908 + }, + { + "epoch": 9.85, + "learning_rate": 1.0720794932984566e-05, + "loss": 0.0249, + "step": 31909 + }, + { + "epoch": 9.85, + "learning_rate": 1.0720296114720711e-05, + "loss": 0.0222, + "step": 31910 + }, + { + "epoch": 9.85, + "learning_rate": 1.071979729465527e-05, + "loss": 0.025, + "step": 31911 + }, + { + "epoch": 9.86, + "learning_rate": 1.0719298472789482e-05, + "loss": 0.0213, + "step": 31912 + }, + { + "epoch": 9.86, + "learning_rate": 1.0718799649124594e-05, + "loss": 0.0225, + "step": 31913 + }, + { + "epoch": 9.86, + "learning_rate": 1.0718300823661862e-05, + "loss": 0.0249, + "step": 31914 + }, + { + "epoch": 9.86, + "learning_rate": 1.0717801996402525e-05, + "loss": 0.0227, + "step": 31915 + }, + { + "epoch": 9.86, + "learning_rate": 1.0717303167347837e-05, + "loss": 0.0254, + "step": 31916 + }, + { + "epoch": 9.86, + "learning_rate": 1.0716804336499042e-05, + "loss": 0.0227, + "step": 31917 + }, + { + "epoch": 9.86, + "learning_rate": 1.0716305503857387e-05, + "loss": 0.0225, + "step": 31918 + }, + { + "epoch": 9.86, + "learning_rate": 1.0715806669424124e-05, + "loss": 0.0269, + "step": 31919 + }, + { + "epoch": 9.86, + "learning_rate": 1.0715307833200497e-05, + "loss": 0.0234, + "step": 31920 + }, + { + "epoch": 9.86, + "learning_rate": 1.0714808995187752e-05, + "loss": 0.0237, + "step": 31921 + }, + { + "epoch": 9.86, + "learning_rate": 1.0714310155387145e-05, + "loss": 0.0224, + "step": 31922 + }, + { + "epoch": 9.86, + "learning_rate": 1.0713811313799914e-05, + "loss": 0.0273, + "step": 31923 + }, + { + "epoch": 9.86, + "learning_rate": 1.071331247042731e-05, + "loss": 0.0256, + "step": 31924 + }, + { + "epoch": 9.86, + "learning_rate": 1.0712813625270585e-05, + "loss": 0.0216, + "step": 31925 + }, + { + "epoch": 9.86, + "learning_rate": 1.0712314778330978e-05, + "loss": 0.0239, + "step": 31926 + }, + { + "epoch": 9.86, + "learning_rate": 1.0711815929609746e-05, + "loss": 0.0205, + "step": 31927 + }, + { + "epoch": 9.86, + "learning_rate": 1.071131707910813e-05, + "loss": 0.0224, + "step": 31928 + }, + { + "epoch": 9.86, + "learning_rate": 1.0710818226827383e-05, + "loss": 0.0259, + "step": 31929 + }, + { + "epoch": 9.86, + "learning_rate": 1.0710319372768748e-05, + "loss": 0.0234, + "step": 31930 + }, + { + "epoch": 9.86, + "learning_rate": 1.0709820516933476e-05, + "loss": 0.0229, + "step": 31931 + }, + { + "epoch": 9.86, + "learning_rate": 1.0709321659322813e-05, + "loss": 0.0236, + "step": 31932 + }, + { + "epoch": 9.86, + "learning_rate": 1.0708822799938005e-05, + "loss": 0.0252, + "step": 31933 + }, + { + "epoch": 9.86, + "learning_rate": 1.0708323938780305e-05, + "loss": 0.0234, + "step": 31934 + }, + { + "epoch": 9.86, + "learning_rate": 1.0707825075850958e-05, + "loss": 0.024, + "step": 31935 + }, + { + "epoch": 9.86, + "learning_rate": 1.0707326211151208e-05, + "loss": 0.0243, + "step": 31936 + }, + { + "epoch": 9.86, + "learning_rate": 1.0706827344682309e-05, + "loss": 0.024, + "step": 31937 + }, + { + "epoch": 9.86, + "learning_rate": 1.0706328476445502e-05, + "loss": 0.0234, + "step": 31938 + }, + { + "epoch": 9.86, + "learning_rate": 1.0705829606442044e-05, + "loss": 0.0256, + "step": 31939 + }, + { + "epoch": 9.86, + "learning_rate": 1.0705330734673174e-05, + "loss": 0.0234, + "step": 31940 + }, + { + "epoch": 9.86, + "learning_rate": 1.0704831861140141e-05, + "loss": 0.0237, + "step": 31941 + }, + { + "epoch": 9.86, + "learning_rate": 1.0704332985844201e-05, + "loss": 0.0244, + "step": 31942 + }, + { + "epoch": 9.86, + "learning_rate": 1.0703834108786593e-05, + "loss": 0.0236, + "step": 31943 + }, + { + "epoch": 9.86, + "learning_rate": 1.0703335229968568e-05, + "loss": 0.0248, + "step": 31944 + }, + { + "epoch": 9.87, + "learning_rate": 1.0702836349391372e-05, + "loss": 0.0241, + "step": 31945 + }, + { + "epoch": 9.87, + "learning_rate": 1.0702337467056254e-05, + "loss": 0.0221, + "step": 31946 + }, + { + "epoch": 9.87, + "learning_rate": 1.0701838582964463e-05, + "loss": 0.025, + "step": 31947 + }, + { + "epoch": 9.87, + "learning_rate": 1.0701339697117245e-05, + "loss": 0.0228, + "step": 31948 + }, + { + "epoch": 9.87, + "learning_rate": 1.070084080951585e-05, + "loss": 0.0245, + "step": 31949 + }, + { + "epoch": 9.87, + "learning_rate": 1.0700341920161522e-05, + "loss": 0.0233, + "step": 31950 + }, + { + "epoch": 9.87, + "learning_rate": 1.0699843029055512e-05, + "loss": 0.0248, + "step": 31951 + }, + { + "epoch": 9.87, + "learning_rate": 1.0699344136199066e-05, + "loss": 0.0221, + "step": 31952 + }, + { + "epoch": 9.87, + "learning_rate": 1.0698845241593434e-05, + "loss": 0.0275, + "step": 31953 + }, + { + "epoch": 9.87, + "learning_rate": 1.0698346345239863e-05, + "loss": 0.0241, + "step": 31954 + }, + { + "epoch": 9.87, + "learning_rate": 1.06978474471396e-05, + "loss": 0.024, + "step": 31955 + }, + { + "epoch": 9.87, + "learning_rate": 1.0697348547293893e-05, + "loss": 0.0219, + "step": 31956 + }, + { + "epoch": 9.87, + "learning_rate": 1.0696849645703991e-05, + "loss": 0.0257, + "step": 31957 + }, + { + "epoch": 9.87, + "learning_rate": 1.069635074237114e-05, + "loss": 0.022, + "step": 31958 + }, + { + "epoch": 9.87, + "learning_rate": 1.0695851837296588e-05, + "loss": 0.0237, + "step": 31959 + }, + { + "epoch": 9.87, + "learning_rate": 1.0695352930481586e-05, + "loss": 0.0232, + "step": 31960 + }, + { + "epoch": 9.87, + "learning_rate": 1.0694854021927376e-05, + "loss": 0.0223, + "step": 31961 + }, + { + "epoch": 9.87, + "learning_rate": 1.0694355111635213e-05, + "loss": 0.0237, + "step": 31962 + }, + { + "epoch": 9.87, + "learning_rate": 1.069385619960634e-05, + "loss": 0.0235, + "step": 31963 + }, + { + "epoch": 9.87, + "learning_rate": 1.0693357285842002e-05, + "loss": 0.0242, + "step": 31964 + }, + { + "epoch": 9.87, + "learning_rate": 1.069285837034346e-05, + "loss": 0.0232, + "step": 31965 + }, + { + "epoch": 9.87, + "learning_rate": 1.0692359453111946e-05, + "loss": 0.0256, + "step": 31966 + }, + { + "epoch": 9.87, + "learning_rate": 1.0691860534148715e-05, + "loss": 0.0223, + "step": 31967 + }, + { + "epoch": 9.87, + "learning_rate": 1.0691361613455019e-05, + "loss": 0.0248, + "step": 31968 + }, + { + "epoch": 9.87, + "learning_rate": 1.0690862691032098e-05, + "loss": 0.022, + "step": 31969 + }, + { + "epoch": 9.87, + "learning_rate": 1.0690363766881202e-05, + "loss": 0.0254, + "step": 31970 + }, + { + "epoch": 9.87, + "learning_rate": 1.0689864841003583e-05, + "loss": 0.0253, + "step": 31971 + }, + { + "epoch": 9.87, + "learning_rate": 1.0689365913400483e-05, + "loss": 0.0232, + "step": 31972 + }, + { + "epoch": 9.87, + "learning_rate": 1.0688866984073158e-05, + "loss": 0.024, + "step": 31973 + }, + { + "epoch": 9.87, + "learning_rate": 1.0688368053022848e-05, + "loss": 0.0256, + "step": 31974 + }, + { + "epoch": 9.87, + "learning_rate": 1.0687869120250804e-05, + "loss": 0.023, + "step": 31975 + }, + { + "epoch": 9.87, + "learning_rate": 1.0687370185758274e-05, + "loss": 0.025, + "step": 31976 + }, + { + "epoch": 9.88, + "learning_rate": 1.0686871249546506e-05, + "loss": 0.0231, + "step": 31977 + }, + { + "epoch": 9.88, + "learning_rate": 1.0686372311616748e-05, + "loss": 0.0214, + "step": 31978 + }, + { + "epoch": 9.88, + "learning_rate": 1.0685873371970248e-05, + "loss": 0.0245, + "step": 31979 + }, + { + "epoch": 9.88, + "learning_rate": 1.0685374430608254e-05, + "loss": 0.0227, + "step": 31980 + }, + { + "epoch": 9.88, + "learning_rate": 1.0684875487532012e-05, + "loss": 0.0238, + "step": 31981 + }, + { + "epoch": 9.88, + "learning_rate": 1.0684376542742771e-05, + "loss": 0.022, + "step": 31982 + }, + { + "epoch": 9.88, + "learning_rate": 1.0683877596241782e-05, + "loss": 0.0266, + "step": 31983 + }, + { + "epoch": 9.88, + "learning_rate": 1.068337864803029e-05, + "loss": 0.0255, + "step": 31984 + }, + { + "epoch": 9.88, + "learning_rate": 1.068287969810954e-05, + "loss": 0.0228, + "step": 31985 + }, + { + "epoch": 9.88, + "learning_rate": 1.0682380746480785e-05, + "loss": 0.0249, + "step": 31986 + }, + { + "epoch": 9.88, + "learning_rate": 1.0681881793145272e-05, + "loss": 0.0276, + "step": 31987 + }, + { + "epoch": 9.88, + "learning_rate": 1.068138283810425e-05, + "loss": 0.0238, + "step": 31988 + }, + { + "epoch": 9.88, + "learning_rate": 1.0680883881358964e-05, + "loss": 0.0249, + "step": 31989 + }, + { + "epoch": 9.88, + "learning_rate": 1.068038492291066e-05, + "loss": 0.0263, + "step": 31990 + }, + { + "epoch": 9.88, + "learning_rate": 1.0679885962760594e-05, + "loss": 0.0221, + "step": 31991 + }, + { + "epoch": 9.88, + "learning_rate": 1.0679387000910006e-05, + "loss": 0.0244, + "step": 31992 + }, + { + "epoch": 9.88, + "learning_rate": 1.067888803736015e-05, + "loss": 0.023, + "step": 31993 + }, + { + "epoch": 9.88, + "learning_rate": 1.067838907211227e-05, + "loss": 0.023, + "step": 31994 + }, + { + "epoch": 9.88, + "learning_rate": 1.0677890105167612e-05, + "loss": 0.0226, + "step": 31995 + }, + { + "epoch": 9.88, + "learning_rate": 1.0677391136527433e-05, + "loss": 0.0259, + "step": 31996 + }, + { + "epoch": 9.88, + "learning_rate": 1.0676892166192971e-05, + "loss": 0.0247, + "step": 31997 + }, + { + "epoch": 9.88, + "learning_rate": 1.0676393194165477e-05, + "loss": 0.0245, + "step": 31998 + }, + { + "epoch": 9.88, + "learning_rate": 1.0675894220446205e-05, + "loss": 0.024, + "step": 31999 + }, + { + "epoch": 9.88, + "learning_rate": 1.0675395245036397e-05, + "loss": 0.026, + "step": 32000 + }, + { + "epoch": 9.88, + "learning_rate": 1.06748962679373e-05, + "loss": 0.0223, + "step": 32001 + }, + { + "epoch": 9.88, + "learning_rate": 1.0674397289150168e-05, + "loss": 0.0225, + "step": 32002 + }, + { + "epoch": 9.88, + "learning_rate": 1.0673898308676239e-05, + "loss": 0.0248, + "step": 32003 + }, + { + "epoch": 9.88, + "learning_rate": 1.0673399326516774e-05, + "loss": 0.0265, + "step": 32004 + }, + { + "epoch": 9.88, + "learning_rate": 1.0672900342673012e-05, + "loss": 0.0231, + "step": 32005 + }, + { + "epoch": 9.88, + "learning_rate": 1.0672401357146203e-05, + "loss": 0.0228, + "step": 32006 + }, + { + "epoch": 9.88, + "learning_rate": 1.0671902369937595e-05, + "loss": 0.0242, + "step": 32007 + }, + { + "epoch": 9.88, + "learning_rate": 1.0671403381048438e-05, + "loss": 0.0243, + "step": 32008 + }, + { + "epoch": 9.89, + "learning_rate": 1.0670904390479977e-05, + "loss": 0.0247, + "step": 32009 + }, + { + "epoch": 9.89, + "learning_rate": 1.0670405398233462e-05, + "loss": 0.0244, + "step": 32010 + }, + { + "epoch": 9.89, + "learning_rate": 1.0669906404310145e-05, + "loss": 0.0248, + "step": 32011 + }, + { + "epoch": 9.89, + "learning_rate": 1.0669407408711265e-05, + "loss": 0.0255, + "step": 32012 + }, + { + "epoch": 9.89, + "learning_rate": 1.0668908411438078e-05, + "loss": 0.0249, + "step": 32013 + }, + { + "epoch": 9.89, + "learning_rate": 1.0668409412491829e-05, + "loss": 0.0258, + "step": 32014 + }, + { + "epoch": 9.89, + "learning_rate": 1.0667910411873762e-05, + "loss": 0.0247, + "step": 32015 + }, + { + "epoch": 9.89, + "learning_rate": 1.0667411409585134e-05, + "loss": 0.027, + "step": 32016 + }, + { + "epoch": 9.89, + "learning_rate": 1.0666912405627188e-05, + "loss": 0.0266, + "step": 32017 + }, + { + "epoch": 9.89, + "learning_rate": 1.0666413400001168e-05, + "loss": 0.0228, + "step": 32018 + }, + { + "epoch": 9.89, + "learning_rate": 1.0665914392708332e-05, + "loss": 0.0238, + "step": 32019 + }, + { + "epoch": 9.89, + "learning_rate": 1.0665415383749917e-05, + "loss": 0.0241, + "step": 32020 + }, + { + "epoch": 9.89, + "learning_rate": 1.0664916373127179e-05, + "loss": 0.021, + "step": 32021 + }, + { + "epoch": 9.89, + "learning_rate": 1.0664417360841367e-05, + "loss": 0.0243, + "step": 32022 + }, + { + "epoch": 9.89, + "learning_rate": 1.0663918346893723e-05, + "loss": 0.0247, + "step": 32023 + }, + { + "epoch": 9.89, + "learning_rate": 1.0663419331285501e-05, + "loss": 0.0233, + "step": 32024 + }, + { + "epoch": 9.89, + "learning_rate": 1.0662920314017943e-05, + "loss": 0.0235, + "step": 32025 + }, + { + "epoch": 9.89, + "learning_rate": 1.06624212950923e-05, + "loss": 0.0251, + "step": 32026 + }, + { + "epoch": 9.89, + "learning_rate": 1.0661922274509825e-05, + "loss": 0.0202, + "step": 32027 + }, + { + "epoch": 9.89, + "learning_rate": 1.0661423252271757e-05, + "loss": 0.0244, + "step": 32028 + }, + { + "epoch": 9.89, + "learning_rate": 1.066092422837935e-05, + "loss": 0.0229, + "step": 32029 + }, + { + "epoch": 9.89, + "learning_rate": 1.0660425202833852e-05, + "loss": 0.0232, + "step": 32030 + }, + { + "epoch": 9.89, + "learning_rate": 1.065992617563651e-05, + "loss": 0.0239, + "step": 32031 + }, + { + "epoch": 9.89, + "learning_rate": 1.065942714678857e-05, + "loss": 0.0235, + "step": 32032 + }, + { + "epoch": 9.89, + "learning_rate": 1.0658928116291285e-05, + "loss": 0.026, + "step": 32033 + }, + { + "epoch": 9.89, + "learning_rate": 1.06584290841459e-05, + "loss": 0.0267, + "step": 32034 + }, + { + "epoch": 9.89, + "learning_rate": 1.0657930050353665e-05, + "loss": 0.0275, + "step": 32035 + }, + { + "epoch": 9.89, + "learning_rate": 1.0657431014915824e-05, + "loss": 0.0234, + "step": 32036 + }, + { + "epoch": 9.89, + "learning_rate": 1.0656931977833631e-05, + "loss": 0.0249, + "step": 32037 + }, + { + "epoch": 9.89, + "learning_rate": 1.065643293910833e-05, + "loss": 0.0307, + "step": 32038 + }, + { + "epoch": 9.89, + "learning_rate": 1.0655933898741169e-05, + "loss": 0.0224, + "step": 32039 + }, + { + "epoch": 9.89, + "learning_rate": 1.06554348567334e-05, + "loss": 0.0261, + "step": 32040 + }, + { + "epoch": 9.89, + "learning_rate": 1.0654935813086267e-05, + "loss": 0.0246, + "step": 32041 + }, + { + "epoch": 9.9, + "learning_rate": 1.0654436767801022e-05, + "loss": 0.0234, + "step": 32042 + }, + { + "epoch": 9.9, + "learning_rate": 1.065393772087891e-05, + "loss": 0.0218, + "step": 32043 + }, + { + "epoch": 9.9, + "learning_rate": 1.0653438672321181e-05, + "loss": 0.023, + "step": 32044 + }, + { + "epoch": 9.9, + "learning_rate": 1.0652939622129084e-05, + "loss": 0.0238, + "step": 32045 + }, + { + "epoch": 9.9, + "learning_rate": 1.0652440570303864e-05, + "loss": 0.0237, + "step": 32046 + }, + { + "epoch": 9.9, + "learning_rate": 1.0651941516846771e-05, + "loss": 0.0243, + "step": 32047 + }, + { + "epoch": 9.9, + "learning_rate": 1.0651442461759057e-05, + "loss": 0.0244, + "step": 32048 + }, + { + "epoch": 9.9, + "learning_rate": 1.0650943405041961e-05, + "loss": 0.0265, + "step": 32049 + }, + { + "epoch": 9.9, + "learning_rate": 1.065044434669674e-05, + "loss": 0.0256, + "step": 32050 + }, + { + "epoch": 9.9, + "learning_rate": 1.0649945286724636e-05, + "loss": 0.0252, + "step": 32051 + }, + { + "epoch": 9.9, + "learning_rate": 1.0649446225126903e-05, + "loss": 0.0215, + "step": 32052 + }, + { + "epoch": 9.9, + "learning_rate": 1.0648947161904787e-05, + "loss": 0.0231, + "step": 32053 + }, + { + "epoch": 9.9, + "learning_rate": 1.0648448097059534e-05, + "loss": 0.0237, + "step": 32054 + }, + { + "epoch": 9.9, + "learning_rate": 1.0647949030592397e-05, + "loss": 0.0212, + "step": 32055 + }, + { + "epoch": 9.9, + "learning_rate": 1.0647449962504622e-05, + "loss": 0.0262, + "step": 32056 + }, + { + "epoch": 9.9, + "learning_rate": 1.064695089279745e-05, + "loss": 0.0286, + "step": 32057 + }, + { + "epoch": 9.9, + "learning_rate": 1.064645182147214e-05, + "loss": 0.0259, + "step": 32058 + }, + { + "epoch": 9.9, + "learning_rate": 1.0645952748529937e-05, + "loss": 0.0242, + "step": 32059 + }, + { + "epoch": 9.9, + "learning_rate": 1.0645453673972088e-05, + "loss": 0.0226, + "step": 32060 + }, + { + "epoch": 9.9, + "learning_rate": 1.0644954597799841e-05, + "loss": 0.0243, + "step": 32061 + }, + { + "epoch": 9.9, + "learning_rate": 1.0644455520014444e-05, + "loss": 0.0221, + "step": 32062 + }, + { + "epoch": 9.9, + "learning_rate": 1.0643956440617147e-05, + "loss": 0.025, + "step": 32063 + }, + { + "epoch": 9.9, + "learning_rate": 1.0643457359609198e-05, + "loss": 0.0232, + "step": 32064 + }, + { + "epoch": 9.9, + "learning_rate": 1.0642958276991844e-05, + "loss": 0.0244, + "step": 32065 + }, + { + "epoch": 9.9, + "learning_rate": 1.0642459192766335e-05, + "loss": 0.0236, + "step": 32066 + }, + { + "epoch": 9.9, + "learning_rate": 1.0641960106933918e-05, + "loss": 0.0216, + "step": 32067 + }, + { + "epoch": 9.9, + "learning_rate": 1.064146101949584e-05, + "loss": 0.0243, + "step": 32068 + }, + { + "epoch": 9.9, + "learning_rate": 1.0640961930453353e-05, + "loss": 0.0265, + "step": 32069 + }, + { + "epoch": 9.9, + "learning_rate": 1.0640462839807704e-05, + "loss": 0.0234, + "step": 32070 + }, + { + "epoch": 9.9, + "learning_rate": 1.0639963747560137e-05, + "loss": 0.0241, + "step": 32071 + }, + { + "epoch": 9.9, + "learning_rate": 1.0639464653711909e-05, + "loss": 0.0229, + "step": 32072 + }, + { + "epoch": 9.9, + "learning_rate": 1.063896555826426e-05, + "loss": 0.022, + "step": 32073 + }, + { + "epoch": 9.91, + "learning_rate": 1.0638466461218442e-05, + "loss": 0.0234, + "step": 32074 + }, + { + "epoch": 9.91, + "learning_rate": 1.0637967362575702e-05, + "loss": 0.0244, + "step": 32075 + }, + { + "epoch": 9.91, + "learning_rate": 1.0637468262337293e-05, + "loss": 0.0252, + "step": 32076 + }, + { + "epoch": 9.91, + "learning_rate": 1.0636969160504456e-05, + "loss": 0.0252, + "step": 32077 + }, + { + "epoch": 9.91, + "learning_rate": 1.0636470057078445e-05, + "loss": 0.0241, + "step": 32078 + }, + { + "epoch": 9.91, + "learning_rate": 1.0635970952060505e-05, + "loss": 0.0261, + "step": 32079 + }, + { + "epoch": 9.91, + "learning_rate": 1.0635471845451883e-05, + "loss": 0.0257, + "step": 32080 + }, + { + "epoch": 9.91, + "learning_rate": 1.0634972737253837e-05, + "loss": 0.0225, + "step": 32081 + }, + { + "epoch": 9.91, + "learning_rate": 1.0634473627467603e-05, + "loss": 0.0227, + "step": 32082 + }, + { + "epoch": 9.91, + "learning_rate": 1.0633974516094436e-05, + "loss": 0.0238, + "step": 32083 + }, + { + "epoch": 9.91, + "learning_rate": 1.0633475403135583e-05, + "loss": 0.0249, + "step": 32084 + }, + { + "epoch": 9.91, + "learning_rate": 1.0632976288592291e-05, + "loss": 0.024, + "step": 32085 + }, + { + "epoch": 9.91, + "learning_rate": 1.0632477172465814e-05, + "loss": 0.0249, + "step": 32086 + }, + { + "epoch": 9.91, + "learning_rate": 1.0631978054757393e-05, + "loss": 0.0234, + "step": 32087 + }, + { + "epoch": 9.91, + "learning_rate": 1.063147893546828e-05, + "loss": 0.0233, + "step": 32088 + }, + { + "epoch": 9.91, + "learning_rate": 1.0630979814599725e-05, + "loss": 0.0222, + "step": 32089 + }, + { + "epoch": 9.91, + "learning_rate": 1.063048069215297e-05, + "loss": 0.0245, + "step": 32090 + }, + { + "epoch": 9.91, + "learning_rate": 1.062998156812927e-05, + "loss": 0.0281, + "step": 32091 + }, + { + "epoch": 9.91, + "learning_rate": 1.0629482442529873e-05, + "loss": 0.024, + "step": 32092 + }, + { + "epoch": 9.91, + "learning_rate": 1.0628983315356026e-05, + "loss": 0.0262, + "step": 32093 + }, + { + "epoch": 9.91, + "learning_rate": 1.0628484186608974e-05, + "loss": 0.0261, + "step": 32094 + }, + { + "epoch": 9.91, + "learning_rate": 1.0627985056289969e-05, + "loss": 0.0231, + "step": 32095 + }, + { + "epoch": 9.91, + "learning_rate": 1.062748592440026e-05, + "loss": 0.0218, + "step": 32096 + }, + { + "epoch": 9.91, + "learning_rate": 1.0626986790941094e-05, + "loss": 0.0259, + "step": 32097 + }, + { + "epoch": 9.91, + "learning_rate": 1.062648765591372e-05, + "loss": 0.0232, + "step": 32098 + }, + { + "epoch": 9.91, + "learning_rate": 1.0625988519319388e-05, + "loss": 0.0227, + "step": 32099 + }, + { + "epoch": 9.91, + "learning_rate": 1.062548938115934e-05, + "loss": 0.0208, + "step": 32100 + }, + { + "epoch": 9.91, + "learning_rate": 1.0624990241434829e-05, + "loss": 0.0241, + "step": 32101 + }, + { + "epoch": 9.91, + "learning_rate": 1.0624491100147108e-05, + "loss": 0.0238, + "step": 32102 + }, + { + "epoch": 9.91, + "learning_rate": 1.0623991957297417e-05, + "loss": 0.0232, + "step": 32103 + }, + { + "epoch": 9.91, + "learning_rate": 1.0623492812887014e-05, + "loss": 0.0259, + "step": 32104 + }, + { + "epoch": 9.91, + "learning_rate": 1.0622993666917135e-05, + "loss": 0.0224, + "step": 32105 + }, + { + "epoch": 9.91, + "learning_rate": 1.0622494519389035e-05, + "loss": 0.0263, + "step": 32106 + }, + { + "epoch": 9.92, + "learning_rate": 1.0621995370303969e-05, + "loss": 0.0215, + "step": 32107 + }, + { + "epoch": 9.92, + "learning_rate": 1.0621496219663172e-05, + "loss": 0.0219, + "step": 32108 + }, + { + "epoch": 9.92, + "learning_rate": 1.0620997067467906e-05, + "loss": 0.0242, + "step": 32109 + }, + { + "epoch": 9.92, + "learning_rate": 1.062049791371941e-05, + "loss": 0.0227, + "step": 32110 + }, + { + "epoch": 9.92, + "learning_rate": 1.0619998758418935e-05, + "loss": 0.0247, + "step": 32111 + }, + { + "epoch": 9.92, + "learning_rate": 1.0619499601567732e-05, + "loss": 0.0223, + "step": 32112 + }, + { + "epoch": 9.92, + "learning_rate": 1.0619000443167045e-05, + "loss": 0.0263, + "step": 32113 + }, + { + "epoch": 9.92, + "learning_rate": 1.0618501283218129e-05, + "loss": 0.0243, + "step": 32114 + }, + { + "epoch": 9.92, + "learning_rate": 1.0618002121722224e-05, + "loss": 0.0237, + "step": 32115 + }, + { + "epoch": 9.92, + "learning_rate": 1.0617502958680584e-05, + "loss": 0.0241, + "step": 32116 + }, + { + "epoch": 9.92, + "learning_rate": 1.0617003794094459e-05, + "loss": 0.0241, + "step": 32117 + }, + { + "epoch": 9.92, + "learning_rate": 1.0616504627965092e-05, + "loss": 0.0265, + "step": 32118 + }, + { + "epoch": 9.92, + "learning_rate": 1.0616005460293734e-05, + "loss": 0.0242, + "step": 32119 + }, + { + "epoch": 9.92, + "learning_rate": 1.0615506291081636e-05, + "loss": 0.0256, + "step": 32120 + }, + { + "epoch": 9.92, + "learning_rate": 1.0615007120330046e-05, + "loss": 0.0243, + "step": 32121 + }, + { + "epoch": 9.92, + "learning_rate": 1.0614507948040207e-05, + "loss": 0.026, + "step": 32122 + }, + { + "epoch": 9.92, + "learning_rate": 1.0614008774213373e-05, + "loss": 0.0236, + "step": 32123 + }, + { + "epoch": 9.92, + "learning_rate": 1.0613509598850793e-05, + "loss": 0.0261, + "step": 32124 + }, + { + "epoch": 9.92, + "learning_rate": 1.0613010421953714e-05, + "loss": 0.0241, + "step": 32125 + }, + { + "epoch": 9.92, + "learning_rate": 1.061251124352338e-05, + "loss": 0.0254, + "step": 32126 + }, + { + "epoch": 9.92, + "learning_rate": 1.061201206356105e-05, + "loss": 0.0248, + "step": 32127 + }, + { + "epoch": 9.92, + "learning_rate": 1.061151288206796e-05, + "loss": 0.0249, + "step": 32128 + }, + { + "epoch": 9.92, + "learning_rate": 1.0611013699045367e-05, + "loss": 0.0224, + "step": 32129 + }, + { + "epoch": 9.92, + "learning_rate": 1.0610514514494518e-05, + "loss": 0.0214, + "step": 32130 + }, + { + "epoch": 9.92, + "learning_rate": 1.0610015328416659e-05, + "loss": 0.0262, + "step": 32131 + }, + { + "epoch": 9.92, + "learning_rate": 1.0609516140813044e-05, + "loss": 0.0247, + "step": 32132 + }, + { + "epoch": 9.92, + "learning_rate": 1.0609016951684913e-05, + "loss": 0.0215, + "step": 32133 + }, + { + "epoch": 9.92, + "learning_rate": 1.0608517761033523e-05, + "loss": 0.0227, + "step": 32134 + }, + { + "epoch": 9.92, + "learning_rate": 1.0608018568860119e-05, + "loss": 0.0245, + "step": 32135 + }, + { + "epoch": 9.92, + "learning_rate": 1.0607519375165947e-05, + "loss": 0.0258, + "step": 32136 + }, + { + "epoch": 9.92, + "learning_rate": 1.0607020179952263e-05, + "loss": 0.0258, + "step": 32137 + }, + { + "epoch": 9.92, + "learning_rate": 1.0606520983220308e-05, + "loss": 0.0235, + "step": 32138 + }, + { + "epoch": 9.93, + "learning_rate": 1.060602178497133e-05, + "loss": 0.0262, + "step": 32139 + }, + { + "epoch": 9.93, + "learning_rate": 1.0605522585206587e-05, + "loss": 0.0241, + "step": 32140 + }, + { + "epoch": 9.93, + "learning_rate": 1.060502338392732e-05, + "loss": 0.0264, + "step": 32141 + }, + { + "epoch": 9.93, + "learning_rate": 1.0604524181134776e-05, + "loss": 0.023, + "step": 32142 + }, + { + "epoch": 9.93, + "learning_rate": 1.0604024976830209e-05, + "loss": 0.0235, + "step": 32143 + }, + { + "epoch": 9.93, + "learning_rate": 1.0603525771014867e-05, + "loss": 0.0221, + "step": 32144 + }, + { + "epoch": 9.93, + "learning_rate": 1.0603026563689994e-05, + "loss": 0.0248, + "step": 32145 + }, + { + "epoch": 9.93, + "learning_rate": 1.0602527354856841e-05, + "loss": 0.0251, + "step": 32146 + }, + { + "epoch": 9.93, + "learning_rate": 1.0602028144516661e-05, + "loss": 0.0245, + "step": 32147 + }, + { + "epoch": 9.93, + "learning_rate": 1.0601528932670697e-05, + "loss": 0.0244, + "step": 32148 + }, + { + "epoch": 9.93, + "learning_rate": 1.06010297193202e-05, + "loss": 0.0236, + "step": 32149 + }, + { + "epoch": 9.93, + "learning_rate": 1.0600530504466415e-05, + "loss": 0.024, + "step": 32150 + }, + { + "epoch": 9.93, + "learning_rate": 1.0600031288110596e-05, + "loss": 0.0188, + "step": 32151 + }, + { + "epoch": 9.93, + "learning_rate": 1.059953207025399e-05, + "loss": 0.0238, + "step": 32152 + }, + { + "epoch": 9.93, + "learning_rate": 1.0599032850897844e-05, + "loss": 0.0261, + "step": 32153 + }, + { + "epoch": 9.93, + "learning_rate": 1.0598533630043408e-05, + "loss": 0.024, + "step": 32154 + }, + { + "epoch": 9.93, + "learning_rate": 1.059803440769193e-05, + "loss": 0.0239, + "step": 32155 + }, + { + "epoch": 9.93, + "learning_rate": 1.0597535183844658e-05, + "loss": 0.0221, + "step": 32156 + }, + { + "epoch": 9.93, + "learning_rate": 1.0597035958502843e-05, + "loss": 0.0269, + "step": 32157 + }, + { + "epoch": 9.93, + "learning_rate": 1.0596536731667735e-05, + "loss": 0.0268, + "step": 32158 + }, + { + "epoch": 9.93, + "learning_rate": 1.0596037503340573e-05, + "loss": 0.0275, + "step": 32159 + }, + { + "epoch": 9.93, + "learning_rate": 1.0595538273522617e-05, + "loss": 0.0211, + "step": 32160 + }, + { + "epoch": 9.93, + "learning_rate": 1.0595039042215112e-05, + "loss": 0.0241, + "step": 32161 + }, + { + "epoch": 9.93, + "learning_rate": 1.0594539809419299e-05, + "loss": 0.0228, + "step": 32162 + }, + { + "epoch": 9.93, + "learning_rate": 1.0594040575136442e-05, + "loss": 0.0224, + "step": 32163 + }, + { + "epoch": 9.93, + "learning_rate": 1.0593541339367777e-05, + "loss": 0.0234, + "step": 32164 + }, + { + "epoch": 9.93, + "learning_rate": 1.0593042102114555e-05, + "loss": 0.0246, + "step": 32165 + }, + { + "epoch": 9.93, + "learning_rate": 1.0592542863378032e-05, + "loss": 0.025, + "step": 32166 + }, + { + "epoch": 9.93, + "learning_rate": 1.0592043623159445e-05, + "loss": 0.026, + "step": 32167 + }, + { + "epoch": 9.93, + "learning_rate": 1.0591544381460055e-05, + "loss": 0.028, + "step": 32168 + }, + { + "epoch": 9.93, + "learning_rate": 1.0591045138281102e-05, + "loss": 0.0226, + "step": 32169 + }, + { + "epoch": 9.93, + "learning_rate": 1.0590545893623833e-05, + "loss": 0.0255, + "step": 32170 + }, + { + "epoch": 9.94, + "learning_rate": 1.059004664748951e-05, + "loss": 0.0231, + "step": 32171 + }, + { + "epoch": 9.94, + "learning_rate": 1.0589547399879365e-05, + "loss": 0.023, + "step": 32172 + }, + { + "epoch": 9.94, + "learning_rate": 1.058904815079466e-05, + "loss": 0.0221, + "step": 32173 + }, + { + "epoch": 9.94, + "learning_rate": 1.0588548900236633e-05, + "loss": 0.0254, + "step": 32174 + }, + { + "epoch": 9.94, + "learning_rate": 1.058804964820654e-05, + "loss": 0.0248, + "step": 32175 + }, + { + "epoch": 9.94, + "learning_rate": 1.0587550394705629e-05, + "loss": 0.0249, + "step": 32176 + }, + { + "epoch": 9.94, + "learning_rate": 1.0587051139735146e-05, + "loss": 0.0244, + "step": 32177 + }, + { + "epoch": 9.94, + "learning_rate": 1.0586551883296341e-05, + "loss": 0.0249, + "step": 32178 + }, + { + "epoch": 9.94, + "learning_rate": 1.0586052625390462e-05, + "loss": 0.0235, + "step": 32179 + }, + { + "epoch": 9.94, + "learning_rate": 1.058555336601876e-05, + "loss": 0.0239, + "step": 32180 + }, + { + "epoch": 9.94, + "learning_rate": 1.0585054105182482e-05, + "loss": 0.025, + "step": 32181 + }, + { + "epoch": 9.94, + "learning_rate": 1.0584554842882875e-05, + "loss": 0.0254, + "step": 32182 + }, + { + "epoch": 9.94, + "learning_rate": 1.0584055579121191e-05, + "loss": 0.026, + "step": 32183 + }, + { + "epoch": 9.94, + "learning_rate": 1.0583556313898678e-05, + "loss": 0.0231, + "step": 32184 + }, + { + "epoch": 9.94, + "learning_rate": 1.0583057047216582e-05, + "loss": 0.023, + "step": 32185 + }, + { + "epoch": 9.94, + "learning_rate": 1.058255777907616e-05, + "loss": 0.0263, + "step": 32186 + }, + { + "epoch": 9.94, + "learning_rate": 1.0582058509478647e-05, + "loss": 0.0253, + "step": 32187 + }, + { + "epoch": 9.94, + "learning_rate": 1.0581559238425306e-05, + "loss": 0.0229, + "step": 32188 + }, + { + "epoch": 9.94, + "learning_rate": 1.0581059965917378e-05, + "loss": 0.0264, + "step": 32189 + }, + { + "epoch": 9.94, + "learning_rate": 1.0580560691956108e-05, + "loss": 0.0287, + "step": 32190 + }, + { + "epoch": 9.94, + "learning_rate": 1.0580061416542755e-05, + "loss": 0.0225, + "step": 32191 + }, + { + "epoch": 9.94, + "learning_rate": 1.0579562139678561e-05, + "loss": 0.0264, + "step": 32192 + }, + { + "epoch": 9.94, + "learning_rate": 1.0579062861364775e-05, + "loss": 0.0235, + "step": 32193 + }, + { + "epoch": 9.94, + "learning_rate": 1.057856358160265e-05, + "loss": 0.0224, + "step": 32194 + }, + { + "epoch": 9.94, + "learning_rate": 1.057806430039343e-05, + "loss": 0.024, + "step": 32195 + }, + { + "epoch": 9.94, + "learning_rate": 1.0577565017738367e-05, + "loss": 0.0238, + "step": 32196 + }, + { + "epoch": 9.94, + "learning_rate": 1.0577065733638707e-05, + "loss": 0.0241, + "step": 32197 + }, + { + "epoch": 9.94, + "learning_rate": 1.0576566448095703e-05, + "loss": 0.0233, + "step": 32198 + }, + { + "epoch": 9.94, + "learning_rate": 1.0576067161110596e-05, + "loss": 0.0234, + "step": 32199 + }, + { + "epoch": 9.94, + "learning_rate": 1.0575567872684644e-05, + "loss": 0.0246, + "step": 32200 + }, + { + "epoch": 9.94, + "learning_rate": 1.0575068582819092e-05, + "loss": 0.0242, + "step": 32201 + }, + { + "epoch": 9.94, + "learning_rate": 1.0574569291515187e-05, + "loss": 0.0255, + "step": 32202 + }, + { + "epoch": 9.94, + "learning_rate": 1.057406999877418e-05, + "loss": 0.0246, + "step": 32203 + }, + { + "epoch": 9.95, + "learning_rate": 1.057357070459732e-05, + "loss": 0.0249, + "step": 32204 + }, + { + "epoch": 9.95, + "learning_rate": 1.0573071408985853e-05, + "loss": 0.0244, + "step": 32205 + }, + { + "epoch": 9.95, + "learning_rate": 1.0572572111941031e-05, + "loss": 0.0233, + "step": 32206 + }, + { + "epoch": 9.95, + "learning_rate": 1.0572072813464103e-05, + "loss": 0.0217, + "step": 32207 + }, + { + "epoch": 9.95, + "learning_rate": 1.0571573513556315e-05, + "loss": 0.0248, + "step": 32208 + }, + { + "epoch": 9.95, + "learning_rate": 1.0571074212218918e-05, + "loss": 0.026, + "step": 32209 + }, + { + "epoch": 9.95, + "learning_rate": 1.0570574909453159e-05, + "loss": 0.0233, + "step": 32210 + }, + { + "epoch": 9.95, + "learning_rate": 1.057007560526029e-05, + "loss": 0.0243, + "step": 32211 + }, + { + "epoch": 9.95, + "learning_rate": 1.056957629964156e-05, + "loss": 0.0259, + "step": 32212 + }, + { + "epoch": 9.95, + "learning_rate": 1.0569076992598208e-05, + "loss": 0.0248, + "step": 32213 + }, + { + "epoch": 9.95, + "learning_rate": 1.0568577684131496e-05, + "loss": 0.0239, + "step": 32214 + }, + { + "epoch": 9.95, + "learning_rate": 1.0568078374242668e-05, + "loss": 0.0258, + "step": 32215 + }, + { + "epoch": 9.95, + "learning_rate": 1.056757906293297e-05, + "loss": 0.0231, + "step": 32216 + }, + { + "epoch": 9.95, + "learning_rate": 1.0567079750203658e-05, + "loss": 0.0233, + "step": 32217 + }, + { + "epoch": 9.95, + "learning_rate": 1.0566580436055971e-05, + "loss": 0.0236, + "step": 32218 + }, + { + "epoch": 9.95, + "learning_rate": 1.0566081120491164e-05, + "loss": 0.0223, + "step": 32219 + }, + { + "epoch": 9.95, + "learning_rate": 1.0565581803510488e-05, + "loss": 0.0242, + "step": 32220 + }, + { + "epoch": 9.95, + "learning_rate": 1.0565082485115184e-05, + "loss": 0.0256, + "step": 32221 + }, + { + "epoch": 9.95, + "learning_rate": 1.056458316530651e-05, + "loss": 0.0247, + "step": 32222 + }, + { + "epoch": 9.95, + "learning_rate": 1.056408384408571e-05, + "loss": 0.0233, + "step": 32223 + }, + { + "epoch": 9.95, + "learning_rate": 1.056358452145403e-05, + "loss": 0.0219, + "step": 32224 + }, + { + "epoch": 9.95, + "learning_rate": 1.0563085197412724e-05, + "loss": 0.0267, + "step": 32225 + }, + { + "epoch": 9.95, + "learning_rate": 1.056258587196304e-05, + "loss": 0.0255, + "step": 32226 + }, + { + "epoch": 9.95, + "learning_rate": 1.0562086545106225e-05, + "loss": 0.0264, + "step": 32227 + }, + { + "epoch": 9.95, + "learning_rate": 1.056158721684353e-05, + "loss": 0.0223, + "step": 32228 + }, + { + "epoch": 9.95, + "learning_rate": 1.0561087887176203e-05, + "loss": 0.0252, + "step": 32229 + }, + { + "epoch": 9.95, + "learning_rate": 1.0560588556105491e-05, + "loss": 0.0236, + "step": 32230 + }, + { + "epoch": 9.95, + "learning_rate": 1.0560089223632648e-05, + "loss": 0.0233, + "step": 32231 + }, + { + "epoch": 9.95, + "learning_rate": 1.0559589889758917e-05, + "loss": 0.0237, + "step": 32232 + }, + { + "epoch": 9.95, + "learning_rate": 1.055909055448555e-05, + "loss": 0.0222, + "step": 32233 + }, + { + "epoch": 9.95, + "learning_rate": 1.0558591217813797e-05, + "loss": 0.0253, + "step": 32234 + }, + { + "epoch": 9.95, + "learning_rate": 1.0558091879744906e-05, + "loss": 0.0258, + "step": 32235 + }, + { + "epoch": 9.96, + "learning_rate": 1.0557592540280121e-05, + "loss": 0.0249, + "step": 32236 + }, + { + "epoch": 9.96, + "learning_rate": 1.0557093199420699e-05, + "loss": 0.022, + "step": 32237 + }, + { + "epoch": 9.96, + "learning_rate": 1.0556593857167885e-05, + "loss": 0.025, + "step": 32238 + }, + { + "epoch": 9.96, + "learning_rate": 1.0556094513522927e-05, + "loss": 0.0259, + "step": 32239 + }, + { + "epoch": 9.96, + "learning_rate": 1.0555595168487078e-05, + "loss": 0.0252, + "step": 32240 + }, + { + "epoch": 9.96, + "learning_rate": 1.055509582206158e-05, + "loss": 0.023, + "step": 32241 + }, + { + "epoch": 9.96, + "learning_rate": 1.0554596474247689e-05, + "loss": 0.0225, + "step": 32242 + }, + { + "epoch": 9.96, + "learning_rate": 1.0554097125046652e-05, + "loss": 0.0261, + "step": 32243 + }, + { + "epoch": 9.96, + "learning_rate": 1.0553597774459713e-05, + "loss": 0.0233, + "step": 32244 + }, + { + "epoch": 9.96, + "learning_rate": 1.055309842248813e-05, + "loss": 0.0239, + "step": 32245 + }, + { + "epoch": 9.96, + "learning_rate": 1.0552599069133145e-05, + "loss": 0.024, + "step": 32246 + }, + { + "epoch": 9.96, + "learning_rate": 1.0552099714396006e-05, + "loss": 0.0242, + "step": 32247 + }, + { + "epoch": 9.96, + "learning_rate": 1.055160035827797e-05, + "loss": 0.0252, + "step": 32248 + }, + { + "epoch": 9.96, + "learning_rate": 1.0551101000780276e-05, + "loss": 0.0236, + "step": 32249 + }, + { + "epoch": 9.96, + "learning_rate": 1.0550601641904181e-05, + "loss": 0.03, + "step": 32250 + }, + { + "epoch": 9.96, + "learning_rate": 1.0550102281650931e-05, + "loss": 0.0262, + "step": 32251 + }, + { + "epoch": 9.96, + "learning_rate": 1.0549602920021771e-05, + "loss": 0.0249, + "step": 32252 + }, + { + "epoch": 9.96, + "learning_rate": 1.0549103557017958e-05, + "loss": 0.0241, + "step": 32253 + }, + { + "epoch": 9.96, + "learning_rate": 1.0548604192640737e-05, + "loss": 0.0213, + "step": 32254 + }, + { + "epoch": 9.96, + "learning_rate": 1.0548104826891352e-05, + "loss": 0.025, + "step": 32255 + }, + { + "epoch": 9.96, + "learning_rate": 1.0547605459771062e-05, + "loss": 0.0219, + "step": 32256 + }, + { + "epoch": 9.96, + "learning_rate": 1.054710609128111e-05, + "loss": 0.0233, + "step": 32257 + }, + { + "epoch": 9.96, + "learning_rate": 1.0546606721422745e-05, + "loss": 0.0238, + "step": 32258 + }, + { + "epoch": 9.96, + "learning_rate": 1.0546107350197217e-05, + "loss": 0.0249, + "step": 32259 + }, + { + "epoch": 9.96, + "learning_rate": 1.0545607977605773e-05, + "loss": 0.0244, + "step": 32260 + }, + { + "epoch": 9.96, + "learning_rate": 1.0545108603649667e-05, + "loss": 0.021, + "step": 32261 + }, + { + "epoch": 9.96, + "learning_rate": 1.0544609228330142e-05, + "loss": 0.0261, + "step": 32262 + }, + { + "epoch": 9.96, + "learning_rate": 1.0544109851648453e-05, + "loss": 0.0245, + "step": 32263 + }, + { + "epoch": 9.96, + "learning_rate": 1.0543610473605846e-05, + "loss": 0.0235, + "step": 32264 + }, + { + "epoch": 9.96, + "learning_rate": 1.0543111094203566e-05, + "loss": 0.024, + "step": 32265 + }, + { + "epoch": 9.96, + "learning_rate": 1.054261171344287e-05, + "loss": 0.0234, + "step": 32266 + }, + { + "epoch": 9.96, + "learning_rate": 1.0542112331325003e-05, + "loss": 0.0265, + "step": 32267 + }, + { + "epoch": 9.97, + "learning_rate": 1.0541612947851212e-05, + "loss": 0.0252, + "step": 32268 + }, + { + "epoch": 9.97, + "learning_rate": 1.054111356302275e-05, + "loss": 0.0238, + "step": 32269 + }, + { + "epoch": 9.97, + "learning_rate": 1.0540614176840862e-05, + "loss": 0.0219, + "step": 32270 + }, + { + "epoch": 9.97, + "learning_rate": 1.0540114789306804e-05, + "loss": 0.0207, + "step": 32271 + }, + { + "epoch": 9.97, + "learning_rate": 1.0539615400421815e-05, + "loss": 0.0266, + "step": 32272 + }, + { + "epoch": 9.97, + "learning_rate": 1.0539116010187151e-05, + "loss": 0.0254, + "step": 32273 + }, + { + "epoch": 9.97, + "learning_rate": 1.0538616618604063e-05, + "loss": 0.0256, + "step": 32274 + }, + { + "epoch": 9.97, + "learning_rate": 1.0538117225673792e-05, + "loss": 0.026, + "step": 32275 + }, + { + "epoch": 9.97, + "learning_rate": 1.0537617831397595e-05, + "loss": 0.0242, + "step": 32276 + }, + { + "epoch": 9.97, + "learning_rate": 1.0537118435776719e-05, + "loss": 0.0253, + "step": 32277 + }, + { + "epoch": 9.97, + "learning_rate": 1.0536619038812405e-05, + "loss": 0.0279, + "step": 32278 + }, + { + "epoch": 9.97, + "learning_rate": 1.0536119640505916e-05, + "loss": 0.023, + "step": 32279 + }, + { + "epoch": 9.97, + "learning_rate": 1.053562024085849e-05, + "loss": 0.0243, + "step": 32280 + }, + { + "epoch": 9.97, + "learning_rate": 1.0535120839871382e-05, + "loss": 0.027, + "step": 32281 + }, + { + "epoch": 9.97, + "learning_rate": 1.0534621437545838e-05, + "loss": 0.0223, + "step": 32282 + }, + { + "epoch": 9.97, + "learning_rate": 1.0534122033883107e-05, + "loss": 0.0241, + "step": 32283 + }, + { + "epoch": 9.97, + "learning_rate": 1.0533622628884444e-05, + "loss": 0.0237, + "step": 32284 + }, + { + "epoch": 9.97, + "learning_rate": 1.0533123222551089e-05, + "loss": 0.0265, + "step": 32285 + }, + { + "epoch": 9.97, + "learning_rate": 1.0532623814884297e-05, + "loss": 0.025, + "step": 32286 + }, + { + "epoch": 9.97, + "learning_rate": 1.0532124405885316e-05, + "loss": 0.0259, + "step": 32287 + }, + { + "epoch": 9.97, + "learning_rate": 1.0531624995555396e-05, + "loss": 0.0254, + "step": 32288 + }, + { + "epoch": 9.97, + "learning_rate": 1.0531125583895782e-05, + "loss": 0.0251, + "step": 32289 + }, + { + "epoch": 9.97, + "learning_rate": 1.0530626170907727e-05, + "loss": 0.026, + "step": 32290 + }, + { + "epoch": 9.97, + "learning_rate": 1.053012675659248e-05, + "loss": 0.0248, + "step": 32291 + }, + { + "epoch": 9.97, + "learning_rate": 1.0529627340951289e-05, + "loss": 0.025, + "step": 32292 + }, + { + "epoch": 9.97, + "learning_rate": 1.0529127923985405e-05, + "loss": 0.024, + "step": 32293 + }, + { + "epoch": 9.97, + "learning_rate": 1.0528628505696072e-05, + "loss": 0.0216, + "step": 32294 + }, + { + "epoch": 9.97, + "learning_rate": 1.0528129086084546e-05, + "loss": 0.0258, + "step": 32295 + }, + { + "epoch": 9.97, + "learning_rate": 1.0527629665152073e-05, + "loss": 0.0237, + "step": 32296 + }, + { + "epoch": 9.97, + "learning_rate": 1.05271302428999e-05, + "loss": 0.0236, + "step": 32297 + }, + { + "epoch": 9.97, + "learning_rate": 1.0526630819329278e-05, + "loss": 0.0234, + "step": 32298 + }, + { + "epoch": 9.97, + "learning_rate": 1.0526131394441457e-05, + "loss": 0.0224, + "step": 32299 + }, + { + "epoch": 9.97, + "learning_rate": 1.0525631968237685e-05, + "loss": 0.0259, + "step": 32300 + }, + { + "epoch": 9.98, + "learning_rate": 1.0525132540719212e-05, + "loss": 0.0234, + "step": 32301 + }, + { + "epoch": 9.98, + "learning_rate": 1.0524633111887289e-05, + "loss": 0.0264, + "step": 32302 + }, + { + "epoch": 9.98, + "learning_rate": 1.0524133681743158e-05, + "loss": 0.0246, + "step": 32303 + }, + { + "epoch": 9.98, + "learning_rate": 1.0523634250288075e-05, + "loss": 0.0243, + "step": 32304 + }, + { + "epoch": 9.98, + "learning_rate": 1.052313481752329e-05, + "loss": 0.0218, + "step": 32305 + }, + { + "epoch": 9.98, + "learning_rate": 1.0522635383450046e-05, + "loss": 0.0247, + "step": 32306 + }, + { + "epoch": 9.98, + "learning_rate": 1.0522135948069598e-05, + "loss": 0.0277, + "step": 32307 + }, + { + "epoch": 9.98, + "learning_rate": 1.0521636511383194e-05, + "loss": 0.0249, + "step": 32308 + }, + { + "epoch": 9.98, + "learning_rate": 1.0521137073392076e-05, + "loss": 0.0246, + "step": 32309 + }, + { + "epoch": 9.98, + "learning_rate": 1.0520637634097504e-05, + "loss": 0.0253, + "step": 32310 + }, + { + "epoch": 9.98, + "learning_rate": 1.0520138193500721e-05, + "loss": 0.0247, + "step": 32311 + }, + { + "epoch": 9.98, + "learning_rate": 1.0519638751602979e-05, + "loss": 0.0235, + "step": 32312 + }, + { + "epoch": 9.98, + "learning_rate": 1.0519139308405523e-05, + "loss": 0.0265, + "step": 32313 + }, + { + "epoch": 9.98, + "learning_rate": 1.0518639863909604e-05, + "loss": 0.0234, + "step": 32314 + }, + { + "epoch": 9.98, + "learning_rate": 1.0518140418116476e-05, + "loss": 0.0258, + "step": 32315 + }, + { + "epoch": 9.98, + "learning_rate": 1.0517640971027383e-05, + "loss": 0.0236, + "step": 32316 + }, + { + "epoch": 9.98, + "learning_rate": 1.0517141522643574e-05, + "loss": 0.0239, + "step": 32317 + }, + { + "epoch": 9.98, + "learning_rate": 1.0516642072966302e-05, + "loss": 0.0239, + "step": 32318 + }, + { + "epoch": 9.98, + "learning_rate": 1.0516142621996812e-05, + "loss": 0.0227, + "step": 32319 + }, + { + "epoch": 9.98, + "learning_rate": 1.0515643169736355e-05, + "loss": 0.0234, + "step": 32320 + }, + { + "epoch": 9.98, + "learning_rate": 1.0515143716186182e-05, + "loss": 0.0238, + "step": 32321 + }, + { + "epoch": 9.98, + "learning_rate": 1.051464426134754e-05, + "loss": 0.0254, + "step": 32322 + }, + { + "epoch": 9.98, + "learning_rate": 1.0514144805221678e-05, + "loss": 0.0229, + "step": 32323 + }, + { + "epoch": 9.98, + "learning_rate": 1.0513645347809846e-05, + "loss": 0.0264, + "step": 32324 + }, + { + "epoch": 9.98, + "learning_rate": 1.05131458891133e-05, + "loss": 0.0234, + "step": 32325 + }, + { + "epoch": 9.98, + "learning_rate": 1.0512646429133274e-05, + "loss": 0.0245, + "step": 32326 + }, + { + "epoch": 9.98, + "learning_rate": 1.0512146967871026e-05, + "loss": 0.0262, + "step": 32327 + }, + { + "epoch": 9.98, + "learning_rate": 1.0511647505327811e-05, + "loss": 0.0246, + "step": 32328 + }, + { + "epoch": 9.98, + "learning_rate": 1.0511148041504867e-05, + "loss": 0.0275, + "step": 32329 + }, + { + "epoch": 9.98, + "learning_rate": 1.0510648576403451e-05, + "loss": 0.0242, + "step": 32330 + }, + { + "epoch": 9.98, + "learning_rate": 1.0510149110024808e-05, + "loss": 0.0246, + "step": 32331 + }, + { + "epoch": 9.98, + "learning_rate": 1.0509649642370188e-05, + "loss": 0.0244, + "step": 32332 + }, + { + "epoch": 9.99, + "learning_rate": 1.0509150173440847e-05, + "loss": 0.0245, + "step": 32333 + }, + { + "epoch": 9.99, + "learning_rate": 1.0508650703238022e-05, + "loss": 0.0243, + "step": 32334 + }, + { + "epoch": 9.99, + "learning_rate": 1.0508151231762973e-05, + "loss": 0.0244, + "step": 32335 + }, + { + "epoch": 9.99, + "learning_rate": 1.0507651759016944e-05, + "loss": 0.0226, + "step": 32336 + }, + { + "epoch": 9.99, + "learning_rate": 1.0507152285001183e-05, + "loss": 0.0216, + "step": 32337 + }, + { + "epoch": 9.99, + "learning_rate": 1.0506652809716946e-05, + "loss": 0.0235, + "step": 32338 + }, + { + "epoch": 9.99, + "learning_rate": 1.0506153333165476e-05, + "loss": 0.023, + "step": 32339 + }, + { + "epoch": 9.99, + "learning_rate": 1.0505653855348024e-05, + "loss": 0.0236, + "step": 32340 + }, + { + "epoch": 9.99, + "learning_rate": 1.050515437626584e-05, + "loss": 0.0258, + "step": 32341 + }, + { + "epoch": 9.99, + "learning_rate": 1.0504654895920172e-05, + "loss": 0.0256, + "step": 32342 + }, + { + "epoch": 9.99, + "learning_rate": 1.0504155414312268e-05, + "loss": 0.0233, + "step": 32343 + }, + { + "epoch": 9.99, + "learning_rate": 1.0503655931443385e-05, + "loss": 0.0238, + "step": 32344 + }, + { + "epoch": 9.99, + "learning_rate": 1.0503156447314761e-05, + "loss": 0.0236, + "step": 32345 + }, + { + "epoch": 9.99, + "learning_rate": 1.0502656961927654e-05, + "loss": 0.0239, + "step": 32346 + }, + { + "epoch": 9.99, + "learning_rate": 1.050215747528331e-05, + "loss": 0.0235, + "step": 32347 + }, + { + "epoch": 9.99, + "learning_rate": 1.0501657987382977e-05, + "loss": 0.0246, + "step": 32348 + }, + { + "epoch": 9.99, + "learning_rate": 1.0501158498227906e-05, + "loss": 0.0259, + "step": 32349 + }, + { + "epoch": 9.99, + "learning_rate": 1.0500659007819348e-05, + "loss": 0.0222, + "step": 32350 + }, + { + "epoch": 9.99, + "learning_rate": 1.050015951615855e-05, + "loss": 0.0221, + "step": 32351 + }, + { + "epoch": 9.99, + "learning_rate": 1.0499660023246761e-05, + "loss": 0.0232, + "step": 32352 + }, + { + "epoch": 9.99, + "learning_rate": 1.049916052908523e-05, + "loss": 0.0252, + "step": 32353 + }, + { + "epoch": 9.99, + "learning_rate": 1.0498661033675211e-05, + "loss": 0.0234, + "step": 32354 + }, + { + "epoch": 9.99, + "learning_rate": 1.0498161537017947e-05, + "loss": 0.0237, + "step": 32355 + }, + { + "epoch": 9.99, + "learning_rate": 1.0497662039114693e-05, + "loss": 0.0247, + "step": 32356 + }, + { + "epoch": 9.99, + "learning_rate": 1.0497162539966691e-05, + "loss": 0.0281, + "step": 32357 + }, + { + "epoch": 9.99, + "learning_rate": 1.0496663039575196e-05, + "loss": 0.0251, + "step": 32358 + }, + { + "epoch": 9.99, + "learning_rate": 1.0496163537941462e-05, + "loss": 0.0253, + "step": 32359 + }, + { + "epoch": 9.99, + "learning_rate": 1.0495664035066724e-05, + "loss": 0.0234, + "step": 32360 + }, + { + "epoch": 9.99, + "learning_rate": 1.0495164530952246e-05, + "loss": 0.0255, + "step": 32361 + }, + { + "epoch": 9.99, + "learning_rate": 1.0494665025599266e-05, + "loss": 0.0221, + "step": 32362 + }, + { + "epoch": 9.99, + "learning_rate": 1.0494165519009043e-05, + "loss": 0.0245, + "step": 32363 + }, + { + "epoch": 9.99, + "learning_rate": 1.0493666011182822e-05, + "loss": 0.0267, + "step": 32364 + }, + { + "epoch": 9.99, + "learning_rate": 1.049316650212185e-05, + "loss": 0.0264, + "step": 32365 + }, + { + "epoch": 10.0, + "learning_rate": 1.049266699182738e-05, + "loss": 0.0216, + "step": 32366 + }, + { + "epoch": 10.0, + "learning_rate": 1.0492167480300658e-05, + "loss": 0.0237, + "step": 32367 + }, + { + "epoch": 10.0, + "learning_rate": 1.0491667967542935e-05, + "loss": 0.0254, + "step": 32368 + }, + { + "epoch": 10.0, + "learning_rate": 1.0491168453555465e-05, + "loss": 0.028, + "step": 32369 + }, + { + "epoch": 10.0, + "learning_rate": 1.049066893833949e-05, + "loss": 0.024, + "step": 32370 + }, + { + "epoch": 10.0, + "learning_rate": 1.0490169421896264e-05, + "loss": 0.0265, + "step": 32371 + }, + { + "epoch": 10.0, + "learning_rate": 1.0489669904227033e-05, + "loss": 0.0239, + "step": 32372 + }, + { + "epoch": 10.0, + "learning_rate": 1.0489170385333049e-05, + "loss": 0.0254, + "step": 32373 + }, + { + "epoch": 10.0, + "learning_rate": 1.0488670865215563e-05, + "loss": 0.0238, + "step": 32374 + }, + { + "epoch": 10.0, + "learning_rate": 1.048817134387582e-05, + "loss": 0.0227, + "step": 32375 + }, + { + "epoch": 10.0, + "learning_rate": 1.048767182131507e-05, + "loss": 0.0255, + "step": 32376 + }, + { + "epoch": 10.0, + "learning_rate": 1.0487172297534565e-05, + "loss": 0.0247, + "step": 32377 + }, + { + "epoch": 10.0, + "learning_rate": 1.0486672772535553e-05, + "loss": 0.0233, + "step": 32378 + }, + { + "epoch": 10.0, + "learning_rate": 1.0486173246319284e-05, + "loss": 0.027, + "step": 32379 + }, + { + "epoch": 10.0, + "learning_rate": 1.0485673718887006e-05, + "loss": 0.0236, + "step": 32380 + }, + { + "epoch": 10.0, + "learning_rate": 1.0485174190239971e-05, + "loss": 0.0236, + "step": 32381 + }, + { + "epoch": 10.0, + "learning_rate": 1.0484674660379426e-05, + "loss": 0.0164, + "step": 32382 + }, + { + "epoch": 10.0, + "learning_rate": 1.0484175129306622e-05, + "loss": 0.0137, + "step": 32383 + }, + { + "epoch": 10.0, + "learning_rate": 1.0483675597022808e-05, + "loss": 0.0114, + "step": 32384 + }, + { + "epoch": 10.0, + "learning_rate": 1.0483176063529232e-05, + "loss": 0.0099, + "step": 32385 + }, + { + "epoch": 10.0, + "learning_rate": 1.0482676528827145e-05, + "loss": 0.012, + "step": 32386 + }, + { + "epoch": 10.0, + "learning_rate": 1.0482176992917798e-05, + "loss": 0.0126, + "step": 32387 + }, + { + "epoch": 10.0, + "learning_rate": 1.0481677455802432e-05, + "loss": 0.0115, + "step": 32388 + }, + { + "epoch": 10.0, + "learning_rate": 1.048117791748231e-05, + "loss": 0.0132, + "step": 32389 + }, + { + "epoch": 10.0, + "learning_rate": 1.0480678377958674e-05, + "loss": 0.0128, + "step": 32390 + }, + { + "epoch": 10.0, + "learning_rate": 1.0480178837232766e-05, + "loss": 0.014, + "step": 32391 + }, + { + "epoch": 10.0, + "learning_rate": 1.0479679295305851e-05, + "loss": 0.0125, + "step": 32392 + }, + { + "epoch": 10.0, + "learning_rate": 1.0479179752179168e-05, + "loss": 0.012, + "step": 32393 + }, + { + "epoch": 10.0, + "learning_rate": 1.0478680207853968e-05, + "loss": 0.0121, + "step": 32394 + }, + { + "epoch": 10.0, + "learning_rate": 1.0478180662331504e-05, + "loss": 0.0124, + "step": 32395 + }, + { + "epoch": 10.0, + "learning_rate": 1.0477681115613019e-05, + "loss": 0.0111, + "step": 32396 + }, + { + "epoch": 10.0, + "learning_rate": 1.047718156769977e-05, + "loss": 0.0117, + "step": 32397 + }, + { + "epoch": 10.01, + "learning_rate": 1.0476682018593003e-05, + "loss": 0.0129, + "step": 32398 + }, + { + "epoch": 10.01, + "learning_rate": 1.0476182468293965e-05, + "loss": 0.0124, + "step": 32399 + }, + { + "epoch": 10.01, + "learning_rate": 1.047568291680391e-05, + "loss": 0.0127, + "step": 32400 + }, + { + "epoch": 10.01, + "learning_rate": 1.0475183364124081e-05, + "loss": 0.0147, + "step": 32401 + }, + { + "epoch": 10.01, + "learning_rate": 1.0474683810255737e-05, + "loss": 0.0109, + "step": 32402 + }, + { + "epoch": 10.01, + "learning_rate": 1.0474184255200119e-05, + "loss": 0.013, + "step": 32403 + }, + { + "epoch": 10.01, + "learning_rate": 1.0473684698958482e-05, + "loss": 0.0139, + "step": 32404 + }, + { + "epoch": 10.01, + "learning_rate": 1.0473185141532069e-05, + "loss": 0.0131, + "step": 32405 + }, + { + "epoch": 10.01, + "learning_rate": 1.0472685582922138e-05, + "loss": 0.0133, + "step": 32406 + }, + { + "epoch": 10.01, + "learning_rate": 1.0472186023129933e-05, + "loss": 0.0118, + "step": 32407 + }, + { + "epoch": 10.01, + "learning_rate": 1.0471686462156702e-05, + "loss": 0.0126, + "step": 32408 + }, + { + "epoch": 10.01, + "learning_rate": 1.04711869000037e-05, + "loss": 0.0109, + "step": 32409 + }, + { + "epoch": 10.01, + "learning_rate": 1.0470687336672177e-05, + "loss": 0.0139, + "step": 32410 + }, + { + "epoch": 10.01, + "learning_rate": 1.0470187772163371e-05, + "loss": 0.014, + "step": 32411 + }, + { + "epoch": 10.01, + "learning_rate": 1.0469688206478546e-05, + "loss": 0.0102, + "step": 32412 + }, + { + "epoch": 10.01, + "learning_rate": 1.0469188639618941e-05, + "loss": 0.0121, + "step": 32413 + }, + { + "epoch": 10.01, + "learning_rate": 1.046868907158581e-05, + "loss": 0.0121, + "step": 32414 + }, + { + "epoch": 10.01, + "learning_rate": 1.0468189502380409e-05, + "loss": 0.0109, + "step": 32415 + }, + { + "epoch": 10.01, + "learning_rate": 1.0467689932003974e-05, + "loss": 0.0127, + "step": 32416 + }, + { + "epoch": 10.01, + "learning_rate": 1.046719036045776e-05, + "loss": 0.0131, + "step": 32417 + }, + { + "epoch": 10.01, + "learning_rate": 1.0466690787743023e-05, + "loss": 0.0131, + "step": 32418 + }, + { + "epoch": 10.01, + "learning_rate": 1.0466191213861001e-05, + "loss": 0.0121, + "step": 32419 + }, + { + "epoch": 10.01, + "learning_rate": 1.0465691638812956e-05, + "loss": 0.0118, + "step": 32420 + }, + { + "epoch": 10.01, + "learning_rate": 1.0465192062600128e-05, + "loss": 0.0125, + "step": 32421 + }, + { + "epoch": 10.01, + "learning_rate": 1.0464692485223769e-05, + "loss": 0.0121, + "step": 32422 + }, + { + "epoch": 10.01, + "learning_rate": 1.0464192906685131e-05, + "loss": 0.0118, + "step": 32423 + }, + { + "epoch": 10.01, + "learning_rate": 1.0463693326985462e-05, + "loss": 0.0117, + "step": 32424 + }, + { + "epoch": 10.01, + "learning_rate": 1.0463193746126013e-05, + "loss": 0.0122, + "step": 32425 + }, + { + "epoch": 10.01, + "learning_rate": 1.046269416410803e-05, + "loss": 0.0117, + "step": 32426 + }, + { + "epoch": 10.01, + "learning_rate": 1.0462194580932763e-05, + "loss": 0.0096, + "step": 32427 + }, + { + "epoch": 10.01, + "learning_rate": 1.0461694996601463e-05, + "loss": 0.0132, + "step": 32428 + }, + { + "epoch": 10.01, + "learning_rate": 1.0461195411115381e-05, + "loss": 0.0121, + "step": 32429 + }, + { + "epoch": 10.02, + "learning_rate": 1.0460695824475766e-05, + "loss": 0.0146, + "step": 32430 + }, + { + "epoch": 10.02, + "learning_rate": 1.0460196236683866e-05, + "loss": 0.0126, + "step": 32431 + }, + { + "epoch": 10.02, + "learning_rate": 1.0459696647740931e-05, + "loss": 0.0116, + "step": 32432 + }, + { + "epoch": 10.02, + "learning_rate": 1.0459197057648212e-05, + "loss": 0.0111, + "step": 32433 + }, + { + "epoch": 10.02, + "learning_rate": 1.0458697466406955e-05, + "loss": 0.0107, + "step": 32434 + }, + { + "epoch": 10.02, + "learning_rate": 1.0458197874018413e-05, + "loss": 0.0107, + "step": 32435 + }, + { + "epoch": 10.02, + "learning_rate": 1.0457698280483835e-05, + "loss": 0.0125, + "step": 32436 + }, + { + "epoch": 10.02, + "learning_rate": 1.0457198685804471e-05, + "loss": 0.0132, + "step": 32437 + }, + { + "epoch": 10.02, + "learning_rate": 1.045669908998157e-05, + "loss": 0.0119, + "step": 32438 + }, + { + "epoch": 10.02, + "learning_rate": 1.045619949301638e-05, + "loss": 0.0124, + "step": 32439 + }, + { + "epoch": 10.02, + "learning_rate": 1.0455699894910149e-05, + "loss": 0.0143, + "step": 32440 + }, + { + "epoch": 10.02, + "learning_rate": 1.0455200295664136e-05, + "loss": 0.0126, + "step": 32441 + }, + { + "epoch": 10.02, + "learning_rate": 1.0454700695279578e-05, + "loss": 0.0128, + "step": 32442 + }, + { + "epoch": 10.02, + "learning_rate": 1.0454201093757735e-05, + "loss": 0.0133, + "step": 32443 + }, + { + "epoch": 10.02, + "learning_rate": 1.0453701491099847e-05, + "loss": 0.0126, + "step": 32444 + }, + { + "epoch": 10.02, + "learning_rate": 1.0453201887307171e-05, + "loss": 0.0111, + "step": 32445 + }, + { + "epoch": 10.02, + "learning_rate": 1.045270228238096e-05, + "loss": 0.0117, + "step": 32446 + }, + { + "epoch": 10.02, + "learning_rate": 1.0452202676322452e-05, + "loss": 0.0121, + "step": 32447 + }, + { + "epoch": 10.02, + "learning_rate": 1.0451703069132906e-05, + "loss": 0.0114, + "step": 32448 + }, + { + "epoch": 10.02, + "learning_rate": 1.0451203460813566e-05, + "loss": 0.0111, + "step": 32449 + }, + { + "epoch": 10.02, + "learning_rate": 1.0450703851365683e-05, + "loss": 0.0118, + "step": 32450 + }, + { + "epoch": 10.02, + "learning_rate": 1.045020424079051e-05, + "loss": 0.0131, + "step": 32451 + }, + { + "epoch": 10.02, + "learning_rate": 1.0449704629089292e-05, + "loss": 0.0103, + "step": 32452 + }, + { + "epoch": 10.02, + "learning_rate": 1.0449205016263282e-05, + "loss": 0.0102, + "step": 32453 + }, + { + "epoch": 10.02, + "learning_rate": 1.0448705402313729e-05, + "loss": 0.0122, + "step": 32454 + }, + { + "epoch": 10.02, + "learning_rate": 1.0448205787241879e-05, + "loss": 0.0137, + "step": 32455 + }, + { + "epoch": 10.02, + "learning_rate": 1.0447706171048986e-05, + "loss": 0.0125, + "step": 32456 + }, + { + "epoch": 10.02, + "learning_rate": 1.0447206553736297e-05, + "loss": 0.0127, + "step": 32457 + }, + { + "epoch": 10.02, + "learning_rate": 1.0446706935305067e-05, + "loss": 0.0121, + "step": 32458 + }, + { + "epoch": 10.02, + "learning_rate": 1.0446207315756538e-05, + "loss": 0.0115, + "step": 32459 + }, + { + "epoch": 10.02, + "learning_rate": 1.0445707695091962e-05, + "loss": 0.0125, + "step": 32460 + }, + { + "epoch": 10.02, + "learning_rate": 1.0445208073312594e-05, + "loss": 0.0113, + "step": 32461 + }, + { + "epoch": 10.02, + "learning_rate": 1.0444708450419675e-05, + "loss": 0.0115, + "step": 32462 + }, + { + "epoch": 10.03, + "learning_rate": 1.0444208826414462e-05, + "loss": 0.012, + "step": 32463 + }, + { + "epoch": 10.03, + "learning_rate": 1.0443709201298202e-05, + "loss": 0.0111, + "step": 32464 + }, + { + "epoch": 10.03, + "learning_rate": 1.0443209575072142e-05, + "loss": 0.0129, + "step": 32465 + }, + { + "epoch": 10.03, + "learning_rate": 1.0442709947737535e-05, + "loss": 0.0113, + "step": 32466 + }, + { + "epoch": 10.03, + "learning_rate": 1.0442210319295631e-05, + "loss": 0.0109, + "step": 32467 + }, + { + "epoch": 10.03, + "learning_rate": 1.0441710689747676e-05, + "loss": 0.0113, + "step": 32468 + }, + { + "epoch": 10.03, + "learning_rate": 1.0441211059094927e-05, + "loss": 0.0134, + "step": 32469 + }, + { + "epoch": 10.03, + "learning_rate": 1.0440711427338622e-05, + "loss": 0.0117, + "step": 32470 + }, + { + "epoch": 10.03, + "learning_rate": 1.044021179448002e-05, + "loss": 0.0125, + "step": 32471 + }, + { + "epoch": 10.03, + "learning_rate": 1.043971216052037e-05, + "loss": 0.013, + "step": 32472 + }, + { + "epoch": 10.03, + "learning_rate": 1.0439212525460915e-05, + "loss": 0.0119, + "step": 32473 + }, + { + "epoch": 10.03, + "learning_rate": 1.0438712889302915e-05, + "loss": 0.012, + "step": 32474 + }, + { + "epoch": 10.03, + "learning_rate": 1.0438213252047613e-05, + "loss": 0.014, + "step": 32475 + }, + { + "epoch": 10.03, + "learning_rate": 1.0437713613696254e-05, + "loss": 0.0109, + "step": 32476 + }, + { + "epoch": 10.03, + "learning_rate": 1.04372139742501e-05, + "loss": 0.0115, + "step": 32477 + }, + { + "epoch": 10.03, + "learning_rate": 1.043671433371039e-05, + "loss": 0.0123, + "step": 32478 + }, + { + "epoch": 10.03, + "learning_rate": 1.0436214692078382e-05, + "loss": 0.013, + "step": 32479 + }, + { + "epoch": 10.03, + "learning_rate": 1.0435715049355319e-05, + "loss": 0.0106, + "step": 32480 + }, + { + "epoch": 10.03, + "learning_rate": 1.0435215405542452e-05, + "loss": 0.0138, + "step": 32481 + }, + { + "epoch": 10.03, + "learning_rate": 1.0434715760641034e-05, + "loss": 0.0125, + "step": 32482 + }, + { + "epoch": 10.03, + "learning_rate": 1.0434216114652311e-05, + "loss": 0.0104, + "step": 32483 + }, + { + "epoch": 10.03, + "learning_rate": 1.0433716467577535e-05, + "loss": 0.0118, + "step": 32484 + }, + { + "epoch": 10.03, + "learning_rate": 1.0433216819417954e-05, + "loss": 0.0119, + "step": 32485 + }, + { + "epoch": 10.03, + "learning_rate": 1.0432717170174822e-05, + "loss": 0.0129, + "step": 32486 + }, + { + "epoch": 10.03, + "learning_rate": 1.0432217519849381e-05, + "loss": 0.0121, + "step": 32487 + }, + { + "epoch": 10.03, + "learning_rate": 1.0431717868442888e-05, + "loss": 0.0134, + "step": 32488 + }, + { + "epoch": 10.03, + "learning_rate": 1.0431218215956588e-05, + "loss": 0.0105, + "step": 32489 + }, + { + "epoch": 10.03, + "learning_rate": 1.0430718562391734e-05, + "loss": 0.0118, + "step": 32490 + }, + { + "epoch": 10.03, + "learning_rate": 1.0430218907749575e-05, + "loss": 0.0103, + "step": 32491 + }, + { + "epoch": 10.03, + "learning_rate": 1.042971925203136e-05, + "loss": 0.0112, + "step": 32492 + }, + { + "epoch": 10.03, + "learning_rate": 1.0429219595238338e-05, + "loss": 0.0097, + "step": 32493 + }, + { + "epoch": 10.03, + "learning_rate": 1.0428719937371758e-05, + "loss": 0.0125, + "step": 32494 + }, + { + "epoch": 10.04, + "learning_rate": 1.0428220278432872e-05, + "loss": 0.0104, + "step": 32495 + }, + { + "epoch": 10.04, + "learning_rate": 1.0427720618422929e-05, + "loss": 0.0114, + "step": 32496 + }, + { + "epoch": 10.04, + "learning_rate": 1.0427220957343183e-05, + "loss": 0.013, + "step": 32497 + }, + { + "epoch": 10.04, + "learning_rate": 1.0426721295194872e-05, + "loss": 0.0111, + "step": 32498 + }, + { + "epoch": 10.04, + "learning_rate": 1.0426221631979259e-05, + "loss": 0.014, + "step": 32499 + }, + { + "epoch": 10.04, + "learning_rate": 1.0425721967697588e-05, + "loss": 0.0105, + "step": 32500 + }, + { + "epoch": 10.04, + "learning_rate": 1.0425222302351104e-05, + "loss": 0.0121, + "step": 32501 + }, + { + "epoch": 10.04, + "learning_rate": 1.0424722635941067e-05, + "loss": 0.0112, + "step": 32502 + }, + { + "epoch": 10.04, + "learning_rate": 1.0424222968468718e-05, + "loss": 0.011, + "step": 32503 + }, + { + "epoch": 10.04, + "learning_rate": 1.0423723299935306e-05, + "loss": 0.016, + "step": 32504 + }, + { + "epoch": 10.04, + "learning_rate": 1.0423223630342092e-05, + "loss": 0.0118, + "step": 32505 + }, + { + "epoch": 10.04, + "learning_rate": 1.0422723959690317e-05, + "loss": 0.0124, + "step": 32506 + }, + { + "epoch": 10.04, + "learning_rate": 1.0422224287981231e-05, + "loss": 0.0127, + "step": 32507 + }, + { + "epoch": 10.04, + "learning_rate": 1.0421724615216084e-05, + "loss": 0.0114, + "step": 32508 + }, + { + "epoch": 10.04, + "learning_rate": 1.042122494139613e-05, + "loss": 0.0136, + "step": 32509 + }, + { + "epoch": 10.04, + "learning_rate": 1.0420725266522612e-05, + "loss": 0.0106, + "step": 32510 + }, + { + "epoch": 10.04, + "learning_rate": 1.0420225590596784e-05, + "loss": 0.013, + "step": 32511 + }, + { + "epoch": 10.04, + "learning_rate": 1.0419725913619894e-05, + "loss": 0.0124, + "step": 32512 + }, + { + "epoch": 10.04, + "learning_rate": 1.0419226235593196e-05, + "loss": 0.0109, + "step": 32513 + }, + { + "epoch": 10.04, + "learning_rate": 1.0418726556517934e-05, + "loss": 0.0102, + "step": 32514 + }, + { + "epoch": 10.04, + "learning_rate": 1.0418226876395364e-05, + "loss": 0.0112, + "step": 32515 + }, + { + "epoch": 10.04, + "learning_rate": 1.041772719522673e-05, + "loss": 0.0138, + "step": 32516 + }, + { + "epoch": 10.04, + "learning_rate": 1.0417227513013283e-05, + "loss": 0.0102, + "step": 32517 + }, + { + "epoch": 10.04, + "learning_rate": 1.0416727829756277e-05, + "loss": 0.0132, + "step": 32518 + }, + { + "epoch": 10.04, + "learning_rate": 1.0416228145456957e-05, + "loss": 0.0106, + "step": 32519 + }, + { + "epoch": 10.04, + "learning_rate": 1.0415728460116575e-05, + "loss": 0.0113, + "step": 32520 + }, + { + "epoch": 10.04, + "learning_rate": 1.0415228773736379e-05, + "loss": 0.0103, + "step": 32521 + }, + { + "epoch": 10.04, + "learning_rate": 1.041472908631762e-05, + "loss": 0.0134, + "step": 32522 + }, + { + "epoch": 10.04, + "learning_rate": 1.041422939786155e-05, + "loss": 0.0107, + "step": 32523 + }, + { + "epoch": 10.04, + "learning_rate": 1.0413729708369416e-05, + "loss": 0.0128, + "step": 32524 + }, + { + "epoch": 10.04, + "learning_rate": 1.0413230017842465e-05, + "loss": 0.0114, + "step": 32525 + }, + { + "epoch": 10.04, + "learning_rate": 1.0412730326281955e-05, + "loss": 0.0117, + "step": 32526 + }, + { + "epoch": 10.04, + "learning_rate": 1.041223063368913e-05, + "loss": 0.0126, + "step": 32527 + }, + { + "epoch": 10.05, + "learning_rate": 1.0411730940065243e-05, + "loss": 0.0118, + "step": 32528 + }, + { + "epoch": 10.05, + "learning_rate": 1.0411231245411538e-05, + "loss": 0.0102, + "step": 32529 + }, + { + "epoch": 10.05, + "learning_rate": 1.041073154972927e-05, + "loss": 0.0134, + "step": 32530 + }, + { + "epoch": 10.05, + "learning_rate": 1.0410231853019689e-05, + "loss": 0.0105, + "step": 32531 + }, + { + "epoch": 10.05, + "learning_rate": 1.040973215528404e-05, + "loss": 0.0122, + "step": 32532 + }, + { + "epoch": 10.05, + "learning_rate": 1.0409232456523578e-05, + "loss": 0.0116, + "step": 32533 + }, + { + "epoch": 10.05, + "learning_rate": 1.0408732756739552e-05, + "loss": 0.0117, + "step": 32534 + }, + { + "epoch": 10.05, + "learning_rate": 1.0408233055933207e-05, + "loss": 0.0113, + "step": 32535 + }, + { + "epoch": 10.05, + "learning_rate": 1.0407733354105802e-05, + "loss": 0.0105, + "step": 32536 + }, + { + "epoch": 10.05, + "learning_rate": 1.0407233651258579e-05, + "loss": 0.0121, + "step": 32537 + }, + { + "epoch": 10.05, + "learning_rate": 1.040673394739279e-05, + "loss": 0.0126, + "step": 32538 + }, + { + "epoch": 10.05, + "learning_rate": 1.0406234242509687e-05, + "loss": 0.0106, + "step": 32539 + }, + { + "epoch": 10.05, + "learning_rate": 1.0405734536610516e-05, + "loss": 0.0126, + "step": 32540 + }, + { + "epoch": 10.05, + "learning_rate": 1.0405234829696529e-05, + "loss": 0.0119, + "step": 32541 + }, + { + "epoch": 10.05, + "learning_rate": 1.0404735121768977e-05, + "loss": 0.0123, + "step": 32542 + }, + { + "epoch": 10.05, + "learning_rate": 1.0404235412829108e-05, + "loss": 0.0113, + "step": 32543 + }, + { + "epoch": 10.05, + "learning_rate": 1.0403735702878173e-05, + "loss": 0.012, + "step": 32544 + }, + { + "epoch": 10.05, + "learning_rate": 1.040323599191742e-05, + "loss": 0.0128, + "step": 32545 + }, + { + "epoch": 10.05, + "learning_rate": 1.0402736279948102e-05, + "loss": 0.0128, + "step": 32546 + }, + { + "epoch": 10.05, + "learning_rate": 1.0402236566971466e-05, + "loss": 0.0099, + "step": 32547 + }, + { + "epoch": 10.05, + "learning_rate": 1.0401736852988762e-05, + "loss": 0.0108, + "step": 32548 + }, + { + "epoch": 10.05, + "learning_rate": 1.0401237138001243e-05, + "loss": 0.0119, + "step": 32549 + }, + { + "epoch": 10.05, + "learning_rate": 1.0400737422010156e-05, + "loss": 0.0116, + "step": 32550 + }, + { + "epoch": 10.05, + "learning_rate": 1.0400237705016754e-05, + "loss": 0.0131, + "step": 32551 + }, + { + "epoch": 10.05, + "learning_rate": 1.0399737987022278e-05, + "loss": 0.0114, + "step": 32552 + }, + { + "epoch": 10.05, + "learning_rate": 1.0399238268027988e-05, + "loss": 0.0129, + "step": 32553 + }, + { + "epoch": 10.05, + "learning_rate": 1.0398738548035135e-05, + "loss": 0.0124, + "step": 32554 + }, + { + "epoch": 10.05, + "learning_rate": 1.0398238827044957e-05, + "loss": 0.0123, + "step": 32555 + }, + { + "epoch": 10.05, + "learning_rate": 1.0397739105058713e-05, + "loss": 0.0108, + "step": 32556 + }, + { + "epoch": 10.05, + "learning_rate": 1.0397239382077654e-05, + "loss": 0.0105, + "step": 32557 + }, + { + "epoch": 10.05, + "learning_rate": 1.0396739658103022e-05, + "loss": 0.013, + "step": 32558 + }, + { + "epoch": 10.05, + "learning_rate": 1.0396239933136076e-05, + "loss": 0.0114, + "step": 32559 + }, + { + "epoch": 10.06, + "learning_rate": 1.0395740207178059e-05, + "loss": 0.0129, + "step": 32560 + }, + { + "epoch": 10.06, + "learning_rate": 1.0395240480230225e-05, + "loss": 0.0121, + "step": 32561 + }, + { + "epoch": 10.06, + "learning_rate": 1.0394740752293823e-05, + "loss": 0.0115, + "step": 32562 + }, + { + "epoch": 10.06, + "learning_rate": 1.03942410233701e-05, + "loss": 0.0113, + "step": 32563 + }, + { + "epoch": 10.06, + "learning_rate": 1.0393741293460311e-05, + "loss": 0.012, + "step": 32564 + }, + { + "epoch": 10.06, + "learning_rate": 1.0393241562565703e-05, + "loss": 0.013, + "step": 32565 + }, + { + "epoch": 10.06, + "learning_rate": 1.0392741830687522e-05, + "loss": 0.0113, + "step": 32566 + }, + { + "epoch": 10.06, + "learning_rate": 1.0392242097827028e-05, + "loss": 0.0116, + "step": 32567 + }, + { + "epoch": 10.06, + "learning_rate": 1.0391742363985462e-05, + "loss": 0.0108, + "step": 32568 + }, + { + "epoch": 10.06, + "learning_rate": 1.0391242629164077e-05, + "loss": 0.012, + "step": 32569 + }, + { + "epoch": 10.06, + "learning_rate": 1.0390742893364123e-05, + "loss": 0.0127, + "step": 32570 + }, + { + "epoch": 10.06, + "learning_rate": 1.039024315658685e-05, + "loss": 0.0116, + "step": 32571 + }, + { + "epoch": 10.06, + "learning_rate": 1.0389743418833507e-05, + "loss": 0.0111, + "step": 32572 + }, + { + "epoch": 10.06, + "learning_rate": 1.0389243680105345e-05, + "loss": 0.0107, + "step": 32573 + }, + { + "epoch": 10.06, + "learning_rate": 1.0388743940403614e-05, + "loss": 0.0161, + "step": 32574 + }, + { + "epoch": 10.06, + "learning_rate": 1.0388244199729563e-05, + "loss": 0.012, + "step": 32575 + }, + { + "epoch": 10.06, + "learning_rate": 1.0387744458084441e-05, + "loss": 0.012, + "step": 32576 + }, + { + "epoch": 10.06, + "learning_rate": 1.0387244715469503e-05, + "loss": 0.0108, + "step": 32577 + }, + { + "epoch": 10.06, + "learning_rate": 1.0386744971885992e-05, + "loss": 0.0124, + "step": 32578 + }, + { + "epoch": 10.06, + "learning_rate": 1.0386245227335161e-05, + "loss": 0.0126, + "step": 32579 + }, + { + "epoch": 10.06, + "learning_rate": 1.038574548181826e-05, + "loss": 0.0135, + "step": 32580 + }, + { + "epoch": 10.06, + "learning_rate": 1.0385245735336542e-05, + "loss": 0.0129, + "step": 32581 + }, + { + "epoch": 10.06, + "learning_rate": 1.0384745987891256e-05, + "loss": 0.0112, + "step": 32582 + }, + { + "epoch": 10.06, + "learning_rate": 1.0384246239483643e-05, + "loss": 0.0142, + "step": 32583 + }, + { + "epoch": 10.06, + "learning_rate": 1.0383746490114965e-05, + "loss": 0.0128, + "step": 32584 + }, + { + "epoch": 10.06, + "learning_rate": 1.038324673978647e-05, + "loss": 0.0134, + "step": 32585 + }, + { + "epoch": 10.06, + "learning_rate": 1.03827469884994e-05, + "loss": 0.0115, + "step": 32586 + }, + { + "epoch": 10.06, + "learning_rate": 1.0382247236255011e-05, + "loss": 0.0127, + "step": 32587 + }, + { + "epoch": 10.06, + "learning_rate": 1.0381747483054554e-05, + "loss": 0.0135, + "step": 32588 + }, + { + "epoch": 10.06, + "learning_rate": 1.0381247728899273e-05, + "loss": 0.0114, + "step": 32589 + }, + { + "epoch": 10.06, + "learning_rate": 1.0380747973790426e-05, + "loss": 0.0122, + "step": 32590 + }, + { + "epoch": 10.06, + "learning_rate": 1.0380248217729254e-05, + "loss": 0.0126, + "step": 32591 + }, + { + "epoch": 10.07, + "learning_rate": 1.0379748460717017e-05, + "loss": 0.0126, + "step": 32592 + }, + { + "epoch": 10.07, + "learning_rate": 1.0379248702754957e-05, + "loss": 0.0118, + "step": 32593 + }, + { + "epoch": 10.07, + "learning_rate": 1.0378748943844326e-05, + "loss": 0.012, + "step": 32594 + }, + { + "epoch": 10.07, + "learning_rate": 1.0378249183986377e-05, + "loss": 0.0126, + "step": 32595 + }, + { + "epoch": 10.07, + "learning_rate": 1.0377749423182358e-05, + "loss": 0.011, + "step": 32596 + }, + { + "epoch": 10.07, + "learning_rate": 1.0377249661433517e-05, + "loss": 0.0127, + "step": 32597 + }, + { + "epoch": 10.07, + "learning_rate": 1.0376749898741108e-05, + "loss": 0.0135, + "step": 32598 + }, + { + "epoch": 10.07, + "learning_rate": 1.0376250135106376e-05, + "loss": 0.0115, + "step": 32599 + }, + { + "epoch": 10.07, + "learning_rate": 1.0375750370530575e-05, + "loss": 0.0131, + "step": 32600 + }, + { + "epoch": 10.07, + "learning_rate": 1.0375250605014955e-05, + "loss": 0.0128, + "step": 32601 + }, + { + "epoch": 10.07, + "learning_rate": 1.0374750838560764e-05, + "loss": 0.0144, + "step": 32602 + }, + { + "epoch": 10.07, + "learning_rate": 1.0374251071169252e-05, + "loss": 0.0129, + "step": 32603 + }, + { + "epoch": 10.07, + "learning_rate": 1.037375130284167e-05, + "loss": 0.0119, + "step": 32604 + }, + { + "epoch": 10.07, + "learning_rate": 1.0373251533579268e-05, + "loss": 0.0125, + "step": 32605 + }, + { + "epoch": 10.07, + "learning_rate": 1.0372751763383295e-05, + "loss": 0.0114, + "step": 32606 + }, + { + "epoch": 10.07, + "learning_rate": 1.0372251992255004e-05, + "loss": 0.0121, + "step": 32607 + }, + { + "epoch": 10.07, + "learning_rate": 1.037175222019564e-05, + "loss": 0.015, + "step": 32608 + }, + { + "epoch": 10.07, + "learning_rate": 1.037125244720646e-05, + "loss": 0.011, + "step": 32609 + }, + { + "epoch": 10.07, + "learning_rate": 1.0370752673288707e-05, + "loss": 0.0113, + "step": 32610 + }, + { + "epoch": 10.07, + "learning_rate": 1.0370252898443634e-05, + "loss": 0.0128, + "step": 32611 + }, + { + "epoch": 10.07, + "learning_rate": 1.0369753122672492e-05, + "loss": 0.0126, + "step": 32612 + }, + { + "epoch": 10.07, + "learning_rate": 1.036925334597653e-05, + "loss": 0.0101, + "step": 32613 + }, + { + "epoch": 10.07, + "learning_rate": 1.0368753568356995e-05, + "loss": 0.0112, + "step": 32614 + }, + { + "epoch": 10.07, + "learning_rate": 1.0368253789815143e-05, + "loss": 0.0128, + "step": 32615 + }, + { + "epoch": 10.07, + "learning_rate": 1.0367754010352225e-05, + "loss": 0.0125, + "step": 32616 + }, + { + "epoch": 10.07, + "learning_rate": 1.036725422996948e-05, + "loss": 0.0119, + "step": 32617 + }, + { + "epoch": 10.07, + "learning_rate": 1.036675444866817e-05, + "loss": 0.0125, + "step": 32618 + }, + { + "epoch": 10.07, + "learning_rate": 1.0366254666449538e-05, + "loss": 0.0117, + "step": 32619 + }, + { + "epoch": 10.07, + "learning_rate": 1.0365754883314834e-05, + "loss": 0.0125, + "step": 32620 + }, + { + "epoch": 10.07, + "learning_rate": 1.0365255099265315e-05, + "loss": 0.0118, + "step": 32621 + }, + { + "epoch": 10.07, + "learning_rate": 1.0364755314302224e-05, + "loss": 0.0121, + "step": 32622 + }, + { + "epoch": 10.07, + "learning_rate": 1.0364255528426814e-05, + "loss": 0.012, + "step": 32623 + }, + { + "epoch": 10.07, + "learning_rate": 1.0363755741640333e-05, + "loss": 0.0113, + "step": 32624 + }, + { + "epoch": 10.08, + "learning_rate": 1.0363255953944031e-05, + "loss": 0.0127, + "step": 32625 + }, + { + "epoch": 10.08, + "learning_rate": 1.0362756165339166e-05, + "loss": 0.0124, + "step": 32626 + }, + { + "epoch": 10.08, + "learning_rate": 1.0362256375826977e-05, + "loss": 0.014, + "step": 32627 + }, + { + "epoch": 10.08, + "learning_rate": 1.036175658540872e-05, + "loss": 0.0124, + "step": 32628 + }, + { + "epoch": 10.08, + "learning_rate": 1.0361256794085643e-05, + "loss": 0.0114, + "step": 32629 + }, + { + "epoch": 10.08, + "learning_rate": 1.0360757001858998e-05, + "loss": 0.0128, + "step": 32630 + }, + { + "epoch": 10.08, + "learning_rate": 1.0360257208730033e-05, + "loss": 0.0122, + "step": 32631 + }, + { + "epoch": 10.08, + "learning_rate": 1.03597574147e-05, + "loss": 0.0119, + "step": 32632 + }, + { + "epoch": 10.08, + "learning_rate": 1.0359257619770147e-05, + "loss": 0.0124, + "step": 32633 + }, + { + "epoch": 10.08, + "learning_rate": 1.0358757823941725e-05, + "loss": 0.0101, + "step": 32634 + }, + { + "epoch": 10.08, + "learning_rate": 1.0358258027215986e-05, + "loss": 0.0133, + "step": 32635 + }, + { + "epoch": 10.08, + "learning_rate": 1.0357758229594179e-05, + "loss": 0.013, + "step": 32636 + }, + { + "epoch": 10.08, + "learning_rate": 1.0357258431077549e-05, + "loss": 0.0121, + "step": 32637 + }, + { + "epoch": 10.08, + "learning_rate": 1.0356758631667352e-05, + "loss": 0.0124, + "step": 32638 + }, + { + "epoch": 10.08, + "learning_rate": 1.035625883136484e-05, + "loss": 0.0117, + "step": 32639 + }, + { + "epoch": 10.08, + "learning_rate": 1.0355759030171256e-05, + "loss": 0.0109, + "step": 32640 + }, + { + "epoch": 10.08, + "learning_rate": 1.0355259228087856e-05, + "loss": 0.0134, + "step": 32641 + }, + { + "epoch": 10.08, + "learning_rate": 1.0354759425115886e-05, + "loss": 0.0125, + "step": 32642 + }, + { + "epoch": 10.08, + "learning_rate": 1.03542596212566e-05, + "loss": 0.0121, + "step": 32643 + }, + { + "epoch": 10.08, + "learning_rate": 1.0353759816511247e-05, + "loss": 0.0119, + "step": 32644 + }, + { + "epoch": 10.08, + "learning_rate": 1.035326001088107e-05, + "loss": 0.012, + "step": 32645 + }, + { + "epoch": 10.08, + "learning_rate": 1.0352760204367333e-05, + "loss": 0.0119, + "step": 32646 + }, + { + "epoch": 10.08, + "learning_rate": 1.0352260396971274e-05, + "loss": 0.0121, + "step": 32647 + }, + { + "epoch": 10.08, + "learning_rate": 1.0351760588694146e-05, + "loss": 0.0139, + "step": 32648 + }, + { + "epoch": 10.08, + "learning_rate": 1.0351260779537207e-05, + "loss": 0.0115, + "step": 32649 + }, + { + "epoch": 10.08, + "learning_rate": 1.0350760969501697e-05, + "loss": 0.0118, + "step": 32650 + }, + { + "epoch": 10.08, + "learning_rate": 1.0350261158588867e-05, + "loss": 0.0126, + "step": 32651 + }, + { + "epoch": 10.08, + "learning_rate": 1.0349761346799973e-05, + "loss": 0.0105, + "step": 32652 + }, + { + "epoch": 10.08, + "learning_rate": 1.0349261534136262e-05, + "loss": 0.0121, + "step": 32653 + }, + { + "epoch": 10.08, + "learning_rate": 1.0348761720598984e-05, + "loss": 0.0116, + "step": 32654 + }, + { + "epoch": 10.08, + "learning_rate": 1.034826190618939e-05, + "loss": 0.0121, + "step": 32655 + }, + { + "epoch": 10.08, + "learning_rate": 1.0347762090908728e-05, + "loss": 0.0108, + "step": 32656 + }, + { + "epoch": 10.09, + "learning_rate": 1.034726227475825e-05, + "loss": 0.0158, + "step": 32657 + }, + { + "epoch": 10.09, + "learning_rate": 1.0346762457739205e-05, + "loss": 0.0126, + "step": 32658 + }, + { + "epoch": 10.09, + "learning_rate": 1.0346262639852844e-05, + "loss": 0.0121, + "step": 32659 + }, + { + "epoch": 10.09, + "learning_rate": 1.0345762821100418e-05, + "loss": 0.0142, + "step": 32660 + }, + { + "epoch": 10.09, + "learning_rate": 1.0345263001483176e-05, + "loss": 0.0136, + "step": 32661 + }, + { + "epoch": 10.09, + "learning_rate": 1.0344763181002369e-05, + "loss": 0.0138, + "step": 32662 + }, + { + "epoch": 10.09, + "learning_rate": 1.0344263359659245e-05, + "loss": 0.0114, + "step": 32663 + }, + { + "epoch": 10.09, + "learning_rate": 1.0343763537455056e-05, + "loss": 0.0132, + "step": 32664 + }, + { + "epoch": 10.09, + "learning_rate": 1.0343263714391052e-05, + "loss": 0.0115, + "step": 32665 + }, + { + "epoch": 10.09, + "learning_rate": 1.0342763890468484e-05, + "loss": 0.0129, + "step": 32666 + }, + { + "epoch": 10.09, + "learning_rate": 1.03422640656886e-05, + "loss": 0.0116, + "step": 32667 + }, + { + "epoch": 10.09, + "learning_rate": 1.034176424005265e-05, + "loss": 0.0107, + "step": 32668 + }, + { + "epoch": 10.09, + "learning_rate": 1.0341264413561885e-05, + "loss": 0.0127, + "step": 32669 + }, + { + "epoch": 10.09, + "learning_rate": 1.0340764586217558e-05, + "loss": 0.0119, + "step": 32670 + }, + { + "epoch": 10.09, + "learning_rate": 1.0340264758020913e-05, + "loss": 0.0113, + "step": 32671 + }, + { + "epoch": 10.09, + "learning_rate": 1.0339764928973209e-05, + "loss": 0.0113, + "step": 32672 + }, + { + "epoch": 10.09, + "learning_rate": 1.0339265099075686e-05, + "loss": 0.0127, + "step": 32673 + }, + { + "epoch": 10.09, + "learning_rate": 1.03387652683296e-05, + "loss": 0.0119, + "step": 32674 + }, + { + "epoch": 10.09, + "learning_rate": 1.0338265436736203e-05, + "loss": 0.0141, + "step": 32675 + }, + { + "epoch": 10.09, + "learning_rate": 1.0337765604296739e-05, + "loss": 0.0148, + "step": 32676 + }, + { + "epoch": 10.09, + "learning_rate": 1.0337265771012466e-05, + "loss": 0.0118, + "step": 32677 + }, + { + "epoch": 10.09, + "learning_rate": 1.0336765936884627e-05, + "loss": 0.0114, + "step": 32678 + }, + { + "epoch": 10.09, + "learning_rate": 1.0336266101914472e-05, + "loss": 0.0118, + "step": 32679 + }, + { + "epoch": 10.09, + "learning_rate": 1.033576626610326e-05, + "loss": 0.0113, + "step": 32680 + }, + { + "epoch": 10.09, + "learning_rate": 1.0335266429452231e-05, + "loss": 0.0134, + "step": 32681 + }, + { + "epoch": 10.09, + "learning_rate": 1.0334766591962641e-05, + "loss": 0.011, + "step": 32682 + }, + { + "epoch": 10.09, + "learning_rate": 1.033426675363574e-05, + "loss": 0.012, + "step": 32683 + }, + { + "epoch": 10.09, + "learning_rate": 1.0333766914472777e-05, + "loss": 0.0141, + "step": 32684 + }, + { + "epoch": 10.09, + "learning_rate": 1.0333267074475e-05, + "loss": 0.0139, + "step": 32685 + }, + { + "epoch": 10.09, + "learning_rate": 1.033276723364366e-05, + "loss": 0.0113, + "step": 32686 + }, + { + "epoch": 10.09, + "learning_rate": 1.0332267391980011e-05, + "loss": 0.0128, + "step": 32687 + }, + { + "epoch": 10.09, + "learning_rate": 1.03317675494853e-05, + "loss": 0.0126, + "step": 32688 + }, + { + "epoch": 10.1, + "learning_rate": 1.0331267706160779e-05, + "loss": 0.0103, + "step": 32689 + }, + { + "epoch": 10.1, + "learning_rate": 1.0330767862007696e-05, + "loss": 0.0109, + "step": 32690 + }, + { + "epoch": 10.1, + "learning_rate": 1.0330268017027301e-05, + "loss": 0.0112, + "step": 32691 + }, + { + "epoch": 10.1, + "learning_rate": 1.0329768171220846e-05, + "loss": 0.0112, + "step": 32692 + }, + { + "epoch": 10.1, + "learning_rate": 1.0329268324589583e-05, + "loss": 0.0128, + "step": 32693 + }, + { + "epoch": 10.1, + "learning_rate": 1.0328768477134756e-05, + "loss": 0.0113, + "step": 32694 + }, + { + "epoch": 10.1, + "learning_rate": 1.0328268628857624e-05, + "loss": 0.0113, + "step": 32695 + }, + { + "epoch": 10.1, + "learning_rate": 1.0327768779759428e-05, + "loss": 0.0117, + "step": 32696 + }, + { + "epoch": 10.1, + "learning_rate": 1.0327268929841424e-05, + "loss": 0.0117, + "step": 32697 + }, + { + "epoch": 10.1, + "learning_rate": 1.0326769079104864e-05, + "loss": 0.0102, + "step": 32698 + }, + { + "epoch": 10.1, + "learning_rate": 1.032626922755099e-05, + "loss": 0.0135, + "step": 32699 + }, + { + "epoch": 10.1, + "learning_rate": 1.0325769375181059e-05, + "loss": 0.012, + "step": 32700 + }, + { + "epoch": 10.1, + "learning_rate": 1.032526952199632e-05, + "loss": 0.0113, + "step": 32701 + }, + { + "epoch": 10.1, + "learning_rate": 1.032476966799802e-05, + "loss": 0.0098, + "step": 32702 + }, + { + "epoch": 10.1, + "learning_rate": 1.0324269813187415e-05, + "loss": 0.0121, + "step": 32703 + }, + { + "epoch": 10.1, + "learning_rate": 1.032376995756575e-05, + "loss": 0.0114, + "step": 32704 + }, + { + "epoch": 10.1, + "learning_rate": 1.032327010113428e-05, + "loss": 0.0132, + "step": 32705 + }, + { + "epoch": 10.1, + "learning_rate": 1.0322770243894248e-05, + "loss": 0.0125, + "step": 32706 + }, + { + "epoch": 10.1, + "learning_rate": 1.0322270385846912e-05, + "loss": 0.0118, + "step": 32707 + }, + { + "epoch": 10.1, + "learning_rate": 1.0321770526993518e-05, + "loss": 0.0141, + "step": 32708 + }, + { + "epoch": 10.1, + "learning_rate": 1.0321270667335318e-05, + "loss": 0.0108, + "step": 32709 + }, + { + "epoch": 10.1, + "learning_rate": 1.0320770806873561e-05, + "loss": 0.0112, + "step": 32710 + }, + { + "epoch": 10.1, + "learning_rate": 1.0320270945609498e-05, + "loss": 0.0104, + "step": 32711 + }, + { + "epoch": 10.1, + "learning_rate": 1.0319771083544379e-05, + "loss": 0.0127, + "step": 32712 + }, + { + "epoch": 10.1, + "learning_rate": 1.0319271220679452e-05, + "loss": 0.0119, + "step": 32713 + }, + { + "epoch": 10.1, + "learning_rate": 1.031877135701597e-05, + "loss": 0.0118, + "step": 32714 + }, + { + "epoch": 10.1, + "learning_rate": 1.0318271492555185e-05, + "loss": 0.0117, + "step": 32715 + }, + { + "epoch": 10.1, + "learning_rate": 1.0317771627298346e-05, + "loss": 0.0116, + "step": 32716 + }, + { + "epoch": 10.1, + "learning_rate": 1.0317271761246698e-05, + "loss": 0.0127, + "step": 32717 + }, + { + "epoch": 10.1, + "learning_rate": 1.0316771894401498e-05, + "loss": 0.012, + "step": 32718 + }, + { + "epoch": 10.1, + "learning_rate": 1.0316272026763993e-05, + "loss": 0.011, + "step": 32719 + }, + { + "epoch": 10.1, + "learning_rate": 1.0315772158335436e-05, + "loss": 0.0106, + "step": 32720 + }, + { + "epoch": 10.1, + "learning_rate": 1.0315272289117076e-05, + "loss": 0.0143, + "step": 32721 + }, + { + "epoch": 10.11, + "learning_rate": 1.0314772419110156e-05, + "loss": 0.0124, + "step": 32722 + }, + { + "epoch": 10.11, + "learning_rate": 1.0314272548315935e-05, + "loss": 0.0132, + "step": 32723 + }, + { + "epoch": 10.11, + "learning_rate": 1.0313772676735665e-05, + "loss": 0.0132, + "step": 32724 + }, + { + "epoch": 10.11, + "learning_rate": 1.0313272804370588e-05, + "loss": 0.0124, + "step": 32725 + }, + { + "epoch": 10.11, + "learning_rate": 1.0312772931221963e-05, + "loss": 0.0122, + "step": 32726 + }, + { + "epoch": 10.11, + "learning_rate": 1.0312273057291034e-05, + "loss": 0.012, + "step": 32727 + }, + { + "epoch": 10.11, + "learning_rate": 1.031177318257905e-05, + "loss": 0.014, + "step": 32728 + }, + { + "epoch": 10.11, + "learning_rate": 1.031127330708727e-05, + "loss": 0.0102, + "step": 32729 + }, + { + "epoch": 10.11, + "learning_rate": 1.0310773430816934e-05, + "loss": 0.0144, + "step": 32730 + }, + { + "epoch": 10.11, + "learning_rate": 1.0310273553769302e-05, + "loss": 0.0128, + "step": 32731 + }, + { + "epoch": 10.11, + "learning_rate": 1.0309773675945616e-05, + "loss": 0.0132, + "step": 32732 + }, + { + "epoch": 10.11, + "learning_rate": 1.0309273797347125e-05, + "loss": 0.0134, + "step": 32733 + }, + { + "epoch": 10.11, + "learning_rate": 1.0308773917975092e-05, + "loss": 0.0106, + "step": 32734 + }, + { + "epoch": 10.11, + "learning_rate": 1.0308274037830754e-05, + "loss": 0.0134, + "step": 32735 + }, + { + "epoch": 10.11, + "learning_rate": 1.030777415691537e-05, + "loss": 0.0115, + "step": 32736 + }, + { + "epoch": 10.11, + "learning_rate": 1.0307274275230184e-05, + "loss": 0.0123, + "step": 32737 + }, + { + "epoch": 10.11, + "learning_rate": 1.0306774392776448e-05, + "loss": 0.0143, + "step": 32738 + }, + { + "epoch": 10.11, + "learning_rate": 1.0306274509555416e-05, + "loss": 0.0146, + "step": 32739 + }, + { + "epoch": 10.11, + "learning_rate": 1.0305774625568334e-05, + "loss": 0.0132, + "step": 32740 + }, + { + "epoch": 10.11, + "learning_rate": 1.0305274740816454e-05, + "loss": 0.012, + "step": 32741 + }, + { + "epoch": 10.11, + "learning_rate": 1.0304774855301028e-05, + "loss": 0.0128, + "step": 32742 + }, + { + "epoch": 10.11, + "learning_rate": 1.0304274969023303e-05, + "loss": 0.0114, + "step": 32743 + }, + { + "epoch": 10.11, + "learning_rate": 1.0303775081984528e-05, + "loss": 0.0126, + "step": 32744 + }, + { + "epoch": 10.11, + "learning_rate": 1.030327519418596e-05, + "loss": 0.0128, + "step": 32745 + }, + { + "epoch": 10.11, + "learning_rate": 1.0302775305628844e-05, + "loss": 0.0118, + "step": 32746 + }, + { + "epoch": 10.11, + "learning_rate": 1.0302275416314433e-05, + "loss": 0.0121, + "step": 32747 + }, + { + "epoch": 10.11, + "learning_rate": 1.0301775526243976e-05, + "loss": 0.0126, + "step": 32748 + }, + { + "epoch": 10.11, + "learning_rate": 1.0301275635418724e-05, + "loss": 0.0133, + "step": 32749 + }, + { + "epoch": 10.11, + "learning_rate": 1.030077574383992e-05, + "loss": 0.0132, + "step": 32750 + }, + { + "epoch": 10.11, + "learning_rate": 1.0300275851508827e-05, + "loss": 0.0113, + "step": 32751 + }, + { + "epoch": 10.11, + "learning_rate": 1.0299775958426691e-05, + "loss": 0.0109, + "step": 32752 + }, + { + "epoch": 10.11, + "learning_rate": 1.0299276064594757e-05, + "loss": 0.0113, + "step": 32753 + }, + { + "epoch": 10.12, + "learning_rate": 1.0298776170014281e-05, + "loss": 0.0128, + "step": 32754 + }, + { + "epoch": 10.12, + "learning_rate": 1.029827627468651e-05, + "loss": 0.0128, + "step": 32755 + }, + { + "epoch": 10.12, + "learning_rate": 1.0297776378612697e-05, + "loss": 0.0146, + "step": 32756 + }, + { + "epoch": 10.12, + "learning_rate": 1.0297276481794092e-05, + "loss": 0.012, + "step": 32757 + }, + { + "epoch": 10.12, + "learning_rate": 1.0296776584231938e-05, + "loss": 0.013, + "step": 32758 + }, + { + "epoch": 10.12, + "learning_rate": 1.02962766859275e-05, + "loss": 0.0118, + "step": 32759 + }, + { + "epoch": 10.12, + "learning_rate": 1.0295776786882015e-05, + "loss": 0.0126, + "step": 32760 + }, + { + "epoch": 10.12, + "learning_rate": 1.0295276887096737e-05, + "loss": 0.0109, + "step": 32761 + }, + { + "epoch": 10.12, + "learning_rate": 1.0294776986572922e-05, + "loss": 0.0124, + "step": 32762 + }, + { + "epoch": 10.12, + "learning_rate": 1.0294277085311814e-05, + "loss": 0.0137, + "step": 32763 + }, + { + "epoch": 10.12, + "learning_rate": 1.0293777183314665e-05, + "loss": 0.0127, + "step": 32764 + }, + { + "epoch": 10.12, + "learning_rate": 1.0293277280582726e-05, + "loss": 0.0119, + "step": 32765 + }, + { + "epoch": 10.12, + "learning_rate": 1.0292777377117247e-05, + "loss": 0.0125, + "step": 32766 + }, + { + "epoch": 10.12, + "learning_rate": 1.0292277472919479e-05, + "loss": 0.0122, + "step": 32767 + }, + { + "epoch": 10.12, + "learning_rate": 1.0291777567990671e-05, + "loss": 0.013, + "step": 32768 + }, + { + "epoch": 10.12, + "learning_rate": 1.0291277662332073e-05, + "loss": 0.0103, + "step": 32769 + }, + { + "epoch": 10.12, + "learning_rate": 1.0290777755944939e-05, + "loss": 0.0128, + "step": 32770 + }, + { + "epoch": 10.12, + "learning_rate": 1.0290277848830515e-05, + "loss": 0.0104, + "step": 32771 + }, + { + "epoch": 10.12, + "learning_rate": 1.0289777940990053e-05, + "loss": 0.011, + "step": 32772 + }, + { + "epoch": 10.12, + "learning_rate": 1.0289278032424804e-05, + "loss": 0.0134, + "step": 32773 + }, + { + "epoch": 10.12, + "learning_rate": 1.0288778123136019e-05, + "loss": 0.0115, + "step": 32774 + }, + { + "epoch": 10.12, + "learning_rate": 1.0288278213124944e-05, + "loss": 0.0116, + "step": 32775 + }, + { + "epoch": 10.12, + "learning_rate": 1.0287778302392837e-05, + "loss": 0.0119, + "step": 32776 + }, + { + "epoch": 10.12, + "learning_rate": 1.028727839094094e-05, + "loss": 0.0122, + "step": 32777 + }, + { + "epoch": 10.12, + "learning_rate": 1.0286778478770509e-05, + "loss": 0.0124, + "step": 32778 + }, + { + "epoch": 10.12, + "learning_rate": 1.0286278565882795e-05, + "loss": 0.0124, + "step": 32779 + }, + { + "epoch": 10.12, + "learning_rate": 1.0285778652279043e-05, + "loss": 0.0117, + "step": 32780 + }, + { + "epoch": 10.12, + "learning_rate": 1.0285278737960507e-05, + "loss": 0.0124, + "step": 32781 + }, + { + "epoch": 10.12, + "learning_rate": 1.0284778822928436e-05, + "loss": 0.013, + "step": 32782 + }, + { + "epoch": 10.12, + "learning_rate": 1.0284278907184086e-05, + "loss": 0.0143, + "step": 32783 + }, + { + "epoch": 10.12, + "learning_rate": 1.0283778990728696e-05, + "loss": 0.0134, + "step": 32784 + }, + { + "epoch": 10.12, + "learning_rate": 1.0283279073563529e-05, + "loss": 0.0128, + "step": 32785 + }, + { + "epoch": 10.12, + "learning_rate": 1.0282779155689826e-05, + "loss": 0.0129, + "step": 32786 + }, + { + "epoch": 10.13, + "learning_rate": 1.028227923710884e-05, + "loss": 0.0132, + "step": 32787 + }, + { + "epoch": 10.13, + "learning_rate": 1.0281779317821825e-05, + "loss": 0.0139, + "step": 32788 + }, + { + "epoch": 10.13, + "learning_rate": 1.0281279397830024e-05, + "loss": 0.0112, + "step": 32789 + }, + { + "epoch": 10.13, + "learning_rate": 1.0280779477134697e-05, + "loss": 0.0107, + "step": 32790 + }, + { + "epoch": 10.13, + "learning_rate": 1.0280279555737086e-05, + "loss": 0.0116, + "step": 32791 + }, + { + "epoch": 10.13, + "learning_rate": 1.0279779633638445e-05, + "loss": 0.0125, + "step": 32792 + }, + { + "epoch": 10.13, + "learning_rate": 1.0279279710840027e-05, + "loss": 0.0117, + "step": 32793 + }, + { + "epoch": 10.13, + "learning_rate": 1.0278779787343079e-05, + "loss": 0.0116, + "step": 32794 + }, + { + "epoch": 10.13, + "learning_rate": 1.0278279863148847e-05, + "loss": 0.0127, + "step": 32795 + }, + { + "epoch": 10.13, + "learning_rate": 1.0277779938258591e-05, + "loss": 0.0104, + "step": 32796 + }, + { + "epoch": 10.13, + "learning_rate": 1.0277280012673557e-05, + "loss": 0.0143, + "step": 32797 + }, + { + "epoch": 10.13, + "learning_rate": 1.0276780086394992e-05, + "loss": 0.0128, + "step": 32798 + }, + { + "epoch": 10.13, + "learning_rate": 1.0276280159424152e-05, + "loss": 0.0122, + "step": 32799 + }, + { + "epoch": 10.13, + "learning_rate": 1.0275780231762283e-05, + "loss": 0.0132, + "step": 32800 + }, + { + "epoch": 10.13, + "learning_rate": 1.0275280303410637e-05, + "loss": 0.0119, + "step": 32801 + }, + { + "epoch": 10.13, + "learning_rate": 1.0274780374370467e-05, + "loss": 0.0124, + "step": 32802 + }, + { + "epoch": 10.13, + "learning_rate": 1.0274280444643023e-05, + "loss": 0.0126, + "step": 32803 + }, + { + "epoch": 10.13, + "learning_rate": 1.0273780514229549e-05, + "loss": 0.0122, + "step": 32804 + }, + { + "epoch": 10.13, + "learning_rate": 1.0273280583131302e-05, + "loss": 0.0138, + "step": 32805 + }, + { + "epoch": 10.13, + "learning_rate": 1.027278065134953e-05, + "loss": 0.0135, + "step": 32806 + }, + { + "epoch": 10.13, + "learning_rate": 1.0272280718885484e-05, + "loss": 0.0134, + "step": 32807 + }, + { + "epoch": 10.13, + "learning_rate": 1.0271780785740416e-05, + "loss": 0.0117, + "step": 32808 + }, + { + "epoch": 10.13, + "learning_rate": 1.027128085191557e-05, + "loss": 0.0129, + "step": 32809 + }, + { + "epoch": 10.13, + "learning_rate": 1.0270780917412204e-05, + "loss": 0.0116, + "step": 32810 + }, + { + "epoch": 10.13, + "learning_rate": 1.0270280982231568e-05, + "loss": 0.0109, + "step": 32811 + }, + { + "epoch": 10.13, + "learning_rate": 1.0269781046374904e-05, + "loss": 0.0117, + "step": 32812 + }, + { + "epoch": 10.13, + "learning_rate": 1.0269281109843475e-05, + "loss": 0.0137, + "step": 32813 + }, + { + "epoch": 10.13, + "learning_rate": 1.0268781172638522e-05, + "loss": 0.0127, + "step": 32814 + }, + { + "epoch": 10.13, + "learning_rate": 1.0268281234761296e-05, + "loss": 0.0138, + "step": 32815 + }, + { + "epoch": 10.13, + "learning_rate": 1.0267781296213056e-05, + "loss": 0.011, + "step": 32816 + }, + { + "epoch": 10.13, + "learning_rate": 1.026728135699504e-05, + "loss": 0.0134, + "step": 32817 + }, + { + "epoch": 10.13, + "learning_rate": 1.0266781417108504e-05, + "loss": 0.013, + "step": 32818 + }, + { + "epoch": 10.14, + "learning_rate": 1.0266281476554705e-05, + "loss": 0.0147, + "step": 32819 + }, + { + "epoch": 10.14, + "learning_rate": 1.026578153533488e-05, + "loss": 0.0109, + "step": 32820 + }, + { + "epoch": 10.14, + "learning_rate": 1.0265281593450293e-05, + "loss": 0.0123, + "step": 32821 + }, + { + "epoch": 10.14, + "learning_rate": 1.0264781650902187e-05, + "loss": 0.0107, + "step": 32822 + }, + { + "epoch": 10.14, + "learning_rate": 1.0264281707691812e-05, + "loss": 0.0138, + "step": 32823 + }, + { + "epoch": 10.14, + "learning_rate": 1.0263781763820422e-05, + "loss": 0.0132, + "step": 32824 + }, + { + "epoch": 10.14, + "learning_rate": 1.0263281819289266e-05, + "loss": 0.0116, + "step": 32825 + }, + { + "epoch": 10.14, + "learning_rate": 1.0262781874099593e-05, + "loss": 0.0114, + "step": 32826 + }, + { + "epoch": 10.14, + "learning_rate": 1.0262281928252656e-05, + "loss": 0.0119, + "step": 32827 + }, + { + "epoch": 10.14, + "learning_rate": 1.02617819817497e-05, + "loss": 0.0128, + "step": 32828 + }, + { + "epoch": 10.14, + "learning_rate": 1.0261282034591984e-05, + "loss": 0.0136, + "step": 32829 + }, + { + "epoch": 10.14, + "learning_rate": 1.0260782086780752e-05, + "loss": 0.0113, + "step": 32830 + }, + { + "epoch": 10.14, + "learning_rate": 1.0260282138317256e-05, + "loss": 0.0129, + "step": 32831 + }, + { + "epoch": 10.14, + "learning_rate": 1.0259782189202748e-05, + "loss": 0.0132, + "step": 32832 + }, + { + "epoch": 10.14, + "learning_rate": 1.0259282239438477e-05, + "loss": 0.0112, + "step": 32833 + }, + { + "epoch": 10.14, + "learning_rate": 1.0258782289025695e-05, + "loss": 0.0126, + "step": 32834 + }, + { + "epoch": 10.14, + "learning_rate": 1.0258282337965648e-05, + "loss": 0.0131, + "step": 32835 + }, + { + "epoch": 10.14, + "learning_rate": 1.0257782386259593e-05, + "loss": 0.0149, + "step": 32836 + }, + { + "epoch": 10.14, + "learning_rate": 1.0257282433908775e-05, + "loss": 0.0142, + "step": 32837 + }, + { + "epoch": 10.14, + "learning_rate": 1.0256782480914449e-05, + "loss": 0.0132, + "step": 32838 + }, + { + "epoch": 10.14, + "learning_rate": 1.0256282527277863e-05, + "loss": 0.0121, + "step": 32839 + }, + { + "epoch": 10.14, + "learning_rate": 1.0255782573000265e-05, + "loss": 0.0124, + "step": 32840 + }, + { + "epoch": 10.14, + "learning_rate": 1.0255282618082909e-05, + "loss": 0.0125, + "step": 32841 + }, + { + "epoch": 10.14, + "learning_rate": 1.0254782662527048e-05, + "loss": 0.0133, + "step": 32842 + }, + { + "epoch": 10.14, + "learning_rate": 1.0254282706333924e-05, + "loss": 0.012, + "step": 32843 + }, + { + "epoch": 10.14, + "learning_rate": 1.0253782749504797e-05, + "loss": 0.0145, + "step": 32844 + }, + { + "epoch": 10.14, + "learning_rate": 1.0253282792040913e-05, + "loss": 0.0123, + "step": 32845 + }, + { + "epoch": 10.14, + "learning_rate": 1.0252782833943517e-05, + "loss": 0.0108, + "step": 32846 + }, + { + "epoch": 10.14, + "learning_rate": 1.025228287521387e-05, + "loss": 0.0137, + "step": 32847 + }, + { + "epoch": 10.14, + "learning_rate": 1.0251782915853217e-05, + "loss": 0.0138, + "step": 32848 + }, + { + "epoch": 10.14, + "learning_rate": 1.0251282955862809e-05, + "loss": 0.0121, + "step": 32849 + }, + { + "epoch": 10.14, + "learning_rate": 1.0250782995243895e-05, + "loss": 0.0108, + "step": 32850 + }, + { + "epoch": 10.15, + "learning_rate": 1.0250283033997728e-05, + "loss": 0.011, + "step": 32851 + }, + { + "epoch": 10.15, + "learning_rate": 1.0249783072125557e-05, + "loss": 0.0144, + "step": 32852 + }, + { + "epoch": 10.15, + "learning_rate": 1.0249283109628634e-05, + "loss": 0.0114, + "step": 32853 + }, + { + "epoch": 10.15, + "learning_rate": 1.0248783146508208e-05, + "loss": 0.012, + "step": 32854 + }, + { + "epoch": 10.15, + "learning_rate": 1.0248283182765529e-05, + "loss": 0.0112, + "step": 32855 + }, + { + "epoch": 10.15, + "learning_rate": 1.0247783218401847e-05, + "loss": 0.0123, + "step": 32856 + }, + { + "epoch": 10.15, + "learning_rate": 1.0247283253418418e-05, + "loss": 0.0131, + "step": 32857 + }, + { + "epoch": 10.15, + "learning_rate": 1.0246783287816486e-05, + "loss": 0.0138, + "step": 32858 + }, + { + "epoch": 10.15, + "learning_rate": 1.0246283321597306e-05, + "loss": 0.0131, + "step": 32859 + }, + { + "epoch": 10.15, + "learning_rate": 1.0245783354762124e-05, + "loss": 0.0135, + "step": 32860 + }, + { + "epoch": 10.15, + "learning_rate": 1.0245283387312193e-05, + "loss": 0.0133, + "step": 32861 + }, + { + "epoch": 10.15, + "learning_rate": 1.0244783419248765e-05, + "loss": 0.0114, + "step": 32862 + }, + { + "epoch": 10.15, + "learning_rate": 1.024428345057309e-05, + "loss": 0.0115, + "step": 32863 + }, + { + "epoch": 10.15, + "learning_rate": 1.0243783481286416e-05, + "loss": 0.0134, + "step": 32864 + }, + { + "epoch": 10.15, + "learning_rate": 1.0243283511389997e-05, + "loss": 0.0127, + "step": 32865 + }, + { + "epoch": 10.15, + "learning_rate": 1.0242783540885077e-05, + "loss": 0.0151, + "step": 32866 + }, + { + "epoch": 10.15, + "learning_rate": 1.0242283569772913e-05, + "loss": 0.0127, + "step": 32867 + }, + { + "epoch": 10.15, + "learning_rate": 1.0241783598054757e-05, + "loss": 0.0133, + "step": 32868 + }, + { + "epoch": 10.15, + "learning_rate": 1.024128362573185e-05, + "loss": 0.0132, + "step": 32869 + }, + { + "epoch": 10.15, + "learning_rate": 1.0240783652805455e-05, + "loss": 0.016, + "step": 32870 + }, + { + "epoch": 10.15, + "learning_rate": 1.0240283679276813e-05, + "loss": 0.0123, + "step": 32871 + }, + { + "epoch": 10.15, + "learning_rate": 1.0239783705147176e-05, + "loss": 0.0108, + "step": 32872 + }, + { + "epoch": 10.15, + "learning_rate": 1.0239283730417802e-05, + "loss": 0.0133, + "step": 32873 + }, + { + "epoch": 10.15, + "learning_rate": 1.023878375508993e-05, + "loss": 0.0139, + "step": 32874 + }, + { + "epoch": 10.15, + "learning_rate": 1.0238283779164819e-05, + "loss": 0.0133, + "step": 32875 + }, + { + "epoch": 10.15, + "learning_rate": 1.0237783802643717e-05, + "loss": 0.011, + "step": 32876 + }, + { + "epoch": 10.15, + "learning_rate": 1.0237283825527871e-05, + "loss": 0.012, + "step": 32877 + }, + { + "epoch": 10.15, + "learning_rate": 1.0236783847818538e-05, + "loss": 0.0116, + "step": 32878 + }, + { + "epoch": 10.15, + "learning_rate": 1.0236283869516965e-05, + "loss": 0.0106, + "step": 32879 + }, + { + "epoch": 10.15, + "learning_rate": 1.0235783890624405e-05, + "loss": 0.0123, + "step": 32880 + }, + { + "epoch": 10.15, + "learning_rate": 1.0235283911142101e-05, + "loss": 0.0128, + "step": 32881 + }, + { + "epoch": 10.15, + "learning_rate": 1.0234783931071312e-05, + "loss": 0.0129, + "step": 32882 + }, + { + "epoch": 10.15, + "learning_rate": 1.0234283950413286e-05, + "loss": 0.0123, + "step": 32883 + }, + { + "epoch": 10.16, + "learning_rate": 1.0233783969169273e-05, + "loss": 0.0128, + "step": 32884 + }, + { + "epoch": 10.16, + "learning_rate": 1.0233283987340525e-05, + "loss": 0.012, + "step": 32885 + }, + { + "epoch": 10.16, + "learning_rate": 1.023278400492829e-05, + "loss": 0.0124, + "step": 32886 + }, + { + "epoch": 10.16, + "learning_rate": 1.0232284021933818e-05, + "loss": 0.0109, + "step": 32887 + }, + { + "epoch": 10.16, + "learning_rate": 1.0231784038358363e-05, + "loss": 0.0126, + "step": 32888 + }, + { + "epoch": 10.16, + "learning_rate": 1.0231284054203174e-05, + "loss": 0.0165, + "step": 32889 + }, + { + "epoch": 10.16, + "learning_rate": 1.0230784069469502e-05, + "loss": 0.013, + "step": 32890 + }, + { + "epoch": 10.16, + "learning_rate": 1.0230284084158595e-05, + "loss": 0.0126, + "step": 32891 + }, + { + "epoch": 10.16, + "learning_rate": 1.0229784098271707e-05, + "loss": 0.0128, + "step": 32892 + }, + { + "epoch": 10.16, + "learning_rate": 1.0229284111810087e-05, + "loss": 0.0142, + "step": 32893 + }, + { + "epoch": 10.16, + "learning_rate": 1.0228784124774984e-05, + "loss": 0.0124, + "step": 32894 + }, + { + "epoch": 10.16, + "learning_rate": 1.022828413716765e-05, + "loss": 0.0121, + "step": 32895 + }, + { + "epoch": 10.16, + "learning_rate": 1.022778414898934e-05, + "loss": 0.0129, + "step": 32896 + }, + { + "epoch": 10.16, + "learning_rate": 1.0227284160241296e-05, + "loss": 0.012, + "step": 32897 + }, + { + "epoch": 10.16, + "learning_rate": 1.0226784170924775e-05, + "loss": 0.0142, + "step": 32898 + }, + { + "epoch": 10.16, + "learning_rate": 1.0226284181041026e-05, + "loss": 0.0141, + "step": 32899 + }, + { + "epoch": 10.16, + "learning_rate": 1.0225784190591294e-05, + "loss": 0.0128, + "step": 32900 + }, + { + "epoch": 10.16, + "learning_rate": 1.0225284199576842e-05, + "loss": 0.013, + "step": 32901 + }, + { + "epoch": 10.16, + "learning_rate": 1.0224784207998905e-05, + "loss": 0.0144, + "step": 32902 + }, + { + "epoch": 10.16, + "learning_rate": 1.0224284215858748e-05, + "loss": 0.0108, + "step": 32903 + }, + { + "epoch": 10.16, + "learning_rate": 1.0223784223157613e-05, + "loss": 0.0107, + "step": 32904 + }, + { + "epoch": 10.16, + "learning_rate": 1.0223284229896753e-05, + "loss": 0.0133, + "step": 32905 + }, + { + "epoch": 10.16, + "learning_rate": 1.0222784236077421e-05, + "loss": 0.013, + "step": 32906 + }, + { + "epoch": 10.16, + "learning_rate": 1.0222284241700862e-05, + "loss": 0.0142, + "step": 32907 + }, + { + "epoch": 10.16, + "learning_rate": 1.022178424676833e-05, + "loss": 0.0112, + "step": 32908 + }, + { + "epoch": 10.16, + "learning_rate": 1.0221284251281075e-05, + "loss": 0.0118, + "step": 32909 + }, + { + "epoch": 10.16, + "learning_rate": 1.0220784255240348e-05, + "loss": 0.0126, + "step": 32910 + }, + { + "epoch": 10.16, + "learning_rate": 1.02202842586474e-05, + "loss": 0.0127, + "step": 32911 + }, + { + "epoch": 10.16, + "learning_rate": 1.0219784261503478e-05, + "loss": 0.0105, + "step": 32912 + }, + { + "epoch": 10.16, + "learning_rate": 1.021928426380984e-05, + "loss": 0.0132, + "step": 32913 + }, + { + "epoch": 10.16, + "learning_rate": 1.0218784265567727e-05, + "loss": 0.0123, + "step": 32914 + }, + { + "epoch": 10.16, + "learning_rate": 1.0218284266778398e-05, + "loss": 0.0119, + "step": 32915 + }, + { + "epoch": 10.17, + "learning_rate": 1.0217784267443101e-05, + "loss": 0.0119, + "step": 32916 + }, + { + "epoch": 10.17, + "learning_rate": 1.0217284267563084e-05, + "loss": 0.0108, + "step": 32917 + }, + { + "epoch": 10.17, + "learning_rate": 1.0216784267139599e-05, + "loss": 0.0142, + "step": 32918 + }, + { + "epoch": 10.17, + "learning_rate": 1.0216284266173897e-05, + "loss": 0.0117, + "step": 32919 + }, + { + "epoch": 10.17, + "learning_rate": 1.021578426466723e-05, + "loss": 0.0132, + "step": 32920 + }, + { + "epoch": 10.17, + "learning_rate": 1.0215284262620846e-05, + "loss": 0.0122, + "step": 32921 + }, + { + "epoch": 10.17, + "learning_rate": 1.0214784260036e-05, + "loss": 0.0124, + "step": 32922 + }, + { + "epoch": 10.17, + "learning_rate": 1.0214284256913935e-05, + "loss": 0.0122, + "step": 32923 + }, + { + "epoch": 10.17, + "learning_rate": 1.0213784253255909e-05, + "loss": 0.014, + "step": 32924 + }, + { + "epoch": 10.17, + "learning_rate": 1.0213284249063168e-05, + "loss": 0.0123, + "step": 32925 + }, + { + "epoch": 10.17, + "learning_rate": 1.0212784244336965e-05, + "loss": 0.0118, + "step": 32926 + }, + { + "epoch": 10.17, + "learning_rate": 1.021228423907855e-05, + "loss": 0.0144, + "step": 32927 + }, + { + "epoch": 10.17, + "learning_rate": 1.021178423328917e-05, + "loss": 0.0137, + "step": 32928 + }, + { + "epoch": 10.17, + "learning_rate": 1.0211284226970084e-05, + "loss": 0.0132, + "step": 32929 + }, + { + "epoch": 10.17, + "learning_rate": 1.0210784220122537e-05, + "loss": 0.011, + "step": 32930 + }, + { + "epoch": 10.17, + "learning_rate": 1.0210284212747777e-05, + "loss": 0.0127, + "step": 32931 + }, + { + "epoch": 10.17, + "learning_rate": 1.0209784204847059e-05, + "loss": 0.0134, + "step": 32932 + }, + { + "epoch": 10.17, + "learning_rate": 1.0209284196421633e-05, + "loss": 0.012, + "step": 32933 + }, + { + "epoch": 10.17, + "learning_rate": 1.020878418747275e-05, + "loss": 0.0122, + "step": 32934 + }, + { + "epoch": 10.17, + "learning_rate": 1.020828417800166e-05, + "loss": 0.0126, + "step": 32935 + }, + { + "epoch": 10.17, + "learning_rate": 1.0207784168009609e-05, + "loss": 0.0136, + "step": 32936 + }, + { + "epoch": 10.17, + "learning_rate": 1.0207284157497856e-05, + "loss": 0.013, + "step": 32937 + }, + { + "epoch": 10.17, + "learning_rate": 1.0206784146467646e-05, + "loss": 0.0145, + "step": 32938 + }, + { + "epoch": 10.17, + "learning_rate": 1.0206284134920233e-05, + "loss": 0.0115, + "step": 32939 + }, + { + "epoch": 10.17, + "learning_rate": 1.0205784122856863e-05, + "loss": 0.0146, + "step": 32940 + }, + { + "epoch": 10.17, + "learning_rate": 1.020528411027879e-05, + "loss": 0.0118, + "step": 32941 + }, + { + "epoch": 10.17, + "learning_rate": 1.0204784097187267e-05, + "loss": 0.0129, + "step": 32942 + }, + { + "epoch": 10.17, + "learning_rate": 1.0204284083583537e-05, + "loss": 0.0123, + "step": 32943 + }, + { + "epoch": 10.17, + "learning_rate": 1.0203784069468858e-05, + "loss": 0.0121, + "step": 32944 + }, + { + "epoch": 10.17, + "learning_rate": 1.0203284054844478e-05, + "loss": 0.0116, + "step": 32945 + }, + { + "epoch": 10.17, + "learning_rate": 1.0202784039711647e-05, + "loss": 0.0126, + "step": 32946 + }, + { + "epoch": 10.17, + "learning_rate": 1.0202284024071616e-05, + "loss": 0.0135, + "step": 32947 + }, + { + "epoch": 10.18, + "learning_rate": 1.0201784007925635e-05, + "loss": 0.0152, + "step": 32948 + }, + { + "epoch": 10.18, + "learning_rate": 1.0201283991274955e-05, + "loss": 0.0118, + "step": 32949 + }, + { + "epoch": 10.18, + "learning_rate": 1.0200783974120831e-05, + "loss": 0.0122, + "step": 32950 + }, + { + "epoch": 10.18, + "learning_rate": 1.0200283956464505e-05, + "loss": 0.0129, + "step": 32951 + }, + { + "epoch": 10.18, + "learning_rate": 1.0199783938307234e-05, + "loss": 0.0116, + "step": 32952 + }, + { + "epoch": 10.18, + "learning_rate": 1.0199283919650267e-05, + "loss": 0.0123, + "step": 32953 + }, + { + "epoch": 10.18, + "learning_rate": 1.0198783900494853e-05, + "loss": 0.0158, + "step": 32954 + }, + { + "epoch": 10.18, + "learning_rate": 1.0198283880842247e-05, + "loss": 0.0128, + "step": 32955 + }, + { + "epoch": 10.18, + "learning_rate": 1.0197783860693696e-05, + "loss": 0.0144, + "step": 32956 + }, + { + "epoch": 10.18, + "learning_rate": 1.0197283840050451e-05, + "loss": 0.0125, + "step": 32957 + }, + { + "epoch": 10.18, + "learning_rate": 1.0196783818913765e-05, + "loss": 0.0142, + "step": 32958 + }, + { + "epoch": 10.18, + "learning_rate": 1.0196283797284882e-05, + "loss": 0.0109, + "step": 32959 + }, + { + "epoch": 10.18, + "learning_rate": 1.0195783775165063e-05, + "loss": 0.0109, + "step": 32960 + }, + { + "epoch": 10.18, + "learning_rate": 1.0195283752555552e-05, + "loss": 0.011, + "step": 32961 + }, + { + "epoch": 10.18, + "learning_rate": 1.0194783729457598e-05, + "loss": 0.0138, + "step": 32962 + }, + { + "epoch": 10.18, + "learning_rate": 1.0194283705872457e-05, + "loss": 0.0134, + "step": 32963 + }, + { + "epoch": 10.18, + "learning_rate": 1.0193783681801375e-05, + "loss": 0.0141, + "step": 32964 + }, + { + "epoch": 10.18, + "learning_rate": 1.0193283657245605e-05, + "loss": 0.0128, + "step": 32965 + }, + { + "epoch": 10.18, + "learning_rate": 1.0192783632206398e-05, + "loss": 0.0143, + "step": 32966 + }, + { + "epoch": 10.18, + "learning_rate": 1.0192283606685003e-05, + "loss": 0.0103, + "step": 32967 + }, + { + "epoch": 10.18, + "learning_rate": 1.0191783580682673e-05, + "loss": 0.0123, + "step": 32968 + }, + { + "epoch": 10.18, + "learning_rate": 1.0191283554200656e-05, + "loss": 0.0125, + "step": 32969 + }, + { + "epoch": 10.18, + "learning_rate": 1.0190783527240204e-05, + "loss": 0.0119, + "step": 32970 + }, + { + "epoch": 10.18, + "learning_rate": 1.0190283499802566e-05, + "loss": 0.0125, + "step": 32971 + }, + { + "epoch": 10.18, + "learning_rate": 1.0189783471889e-05, + "loss": 0.0128, + "step": 32972 + }, + { + "epoch": 10.18, + "learning_rate": 1.0189283443500747e-05, + "loss": 0.0136, + "step": 32973 + }, + { + "epoch": 10.18, + "learning_rate": 1.018878341463906e-05, + "loss": 0.0117, + "step": 32974 + }, + { + "epoch": 10.18, + "learning_rate": 1.0188283385305193e-05, + "loss": 0.014, + "step": 32975 + }, + { + "epoch": 10.18, + "learning_rate": 1.0187783355500397e-05, + "loss": 0.0122, + "step": 32976 + }, + { + "epoch": 10.18, + "learning_rate": 1.0187283325225917e-05, + "loss": 0.0136, + "step": 32977 + }, + { + "epoch": 10.18, + "learning_rate": 1.018678329448301e-05, + "loss": 0.0156, + "step": 32978 + }, + { + "epoch": 10.18, + "learning_rate": 1.018628326327292e-05, + "loss": 0.0115, + "step": 32979 + }, + { + "epoch": 10.18, + "learning_rate": 1.0185783231596906e-05, + "loss": 0.0125, + "step": 32980 + }, + { + "epoch": 10.19, + "learning_rate": 1.0185283199456216e-05, + "loss": 0.0136, + "step": 32981 + }, + { + "epoch": 10.19, + "learning_rate": 1.018478316685209e-05, + "loss": 0.0142, + "step": 32982 + }, + { + "epoch": 10.19, + "learning_rate": 1.0184283133785796e-05, + "loss": 0.0103, + "step": 32983 + }, + { + "epoch": 10.19, + "learning_rate": 1.0183783100258571e-05, + "loss": 0.0148, + "step": 32984 + }, + { + "epoch": 10.19, + "learning_rate": 1.0183283066271675e-05, + "loss": 0.0124, + "step": 32985 + }, + { + "epoch": 10.19, + "learning_rate": 1.0182783031826354e-05, + "loss": 0.0114, + "step": 32986 + }, + { + "epoch": 10.19, + "learning_rate": 1.0182282996923855e-05, + "loss": 0.0109, + "step": 32987 + }, + { + "epoch": 10.19, + "learning_rate": 1.0181782961565438e-05, + "loss": 0.0113, + "step": 32988 + }, + { + "epoch": 10.19, + "learning_rate": 1.018128292575235e-05, + "loss": 0.0118, + "step": 32989 + }, + { + "epoch": 10.19, + "learning_rate": 1.0180782889485834e-05, + "loss": 0.0126, + "step": 32990 + }, + { + "epoch": 10.19, + "learning_rate": 1.018028285276715e-05, + "loss": 0.0143, + "step": 32991 + }, + { + "epoch": 10.19, + "learning_rate": 1.0179782815597548e-05, + "loss": 0.0124, + "step": 32992 + }, + { + "epoch": 10.19, + "learning_rate": 1.0179282777978275e-05, + "loss": 0.013, + "step": 32993 + }, + { + "epoch": 10.19, + "learning_rate": 1.0178782739910582e-05, + "loss": 0.0179, + "step": 32994 + }, + { + "epoch": 10.19, + "learning_rate": 1.0178282701395721e-05, + "loss": 0.0129, + "step": 32995 + }, + { + "epoch": 10.19, + "learning_rate": 1.017778266243494e-05, + "loss": 0.0137, + "step": 32996 + }, + { + "epoch": 10.19, + "learning_rate": 1.0177282623029496e-05, + "loss": 0.0136, + "step": 32997 + }, + { + "epoch": 10.19, + "learning_rate": 1.0176782583180635e-05, + "loss": 0.0128, + "step": 32998 + }, + { + "epoch": 10.19, + "learning_rate": 1.0176282542889608e-05, + "loss": 0.0121, + "step": 32999 + }, + { + "epoch": 10.19, + "learning_rate": 1.0175782502157668e-05, + "loss": 0.0125, + "step": 33000 + }, + { + "epoch": 10.19, + "learning_rate": 1.017528246098606e-05, + "loss": 0.0107, + "step": 33001 + }, + { + "epoch": 10.19, + "learning_rate": 1.0174782419376041e-05, + "loss": 0.0112, + "step": 33002 + }, + { + "epoch": 10.19, + "learning_rate": 1.0174282377328859e-05, + "loss": 0.0144, + "step": 33003 + }, + { + "epoch": 10.19, + "learning_rate": 1.0173782334845766e-05, + "loss": 0.0114, + "step": 33004 + }, + { + "epoch": 10.19, + "learning_rate": 1.017328229192801e-05, + "loss": 0.0124, + "step": 33005 + }, + { + "epoch": 10.19, + "learning_rate": 1.0172782248576847e-05, + "loss": 0.0137, + "step": 33006 + }, + { + "epoch": 10.19, + "learning_rate": 1.0172282204793518e-05, + "loss": 0.0111, + "step": 33007 + }, + { + "epoch": 10.19, + "learning_rate": 1.0171782160579282e-05, + "loss": 0.0123, + "step": 33008 + }, + { + "epoch": 10.19, + "learning_rate": 1.0171282115935393e-05, + "loss": 0.0142, + "step": 33009 + }, + { + "epoch": 10.19, + "learning_rate": 1.0170782070863088e-05, + "loss": 0.0129, + "step": 33010 + }, + { + "epoch": 10.19, + "learning_rate": 1.0170282025363631e-05, + "loss": 0.0126, + "step": 33011 + }, + { + "epoch": 10.19, + "learning_rate": 1.0169781979438266e-05, + "loss": 0.0099, + "step": 33012 + }, + { + "epoch": 10.2, + "learning_rate": 1.0169281933088245e-05, + "loss": 0.0127, + "step": 33013 + }, + { + "epoch": 10.2, + "learning_rate": 1.016878188631482e-05, + "loss": 0.0138, + "step": 33014 + }, + { + "epoch": 10.2, + "learning_rate": 1.016828183911924e-05, + "loss": 0.0115, + "step": 33015 + }, + { + "epoch": 10.2, + "learning_rate": 1.0167781791502757e-05, + "loss": 0.0124, + "step": 33016 + }, + { + "epoch": 10.2, + "learning_rate": 1.0167281743466622e-05, + "loss": 0.0144, + "step": 33017 + }, + { + "epoch": 10.2, + "learning_rate": 1.016678169501208e-05, + "loss": 0.0113, + "step": 33018 + }, + { + "epoch": 10.2, + "learning_rate": 1.0166281646140392e-05, + "loss": 0.0125, + "step": 33019 + }, + { + "epoch": 10.2, + "learning_rate": 1.0165781596852801e-05, + "loss": 0.0116, + "step": 33020 + }, + { + "epoch": 10.2, + "learning_rate": 1.0165281547150563e-05, + "loss": 0.0126, + "step": 33021 + }, + { + "epoch": 10.2, + "learning_rate": 1.0164781497034921e-05, + "loss": 0.0127, + "step": 33022 + }, + { + "epoch": 10.2, + "learning_rate": 1.0164281446507133e-05, + "loss": 0.0146, + "step": 33023 + }, + { + "epoch": 10.2, + "learning_rate": 1.0163781395568446e-05, + "loss": 0.0127, + "step": 33024 + }, + { + "epoch": 10.2, + "learning_rate": 1.0163281344220113e-05, + "loss": 0.0126, + "step": 33025 + }, + { + "epoch": 10.2, + "learning_rate": 1.0162781292463384e-05, + "loss": 0.0131, + "step": 33026 + }, + { + "epoch": 10.2, + "learning_rate": 1.0162281240299507e-05, + "loss": 0.0139, + "step": 33027 + }, + { + "epoch": 10.2, + "learning_rate": 1.0161781187729738e-05, + "loss": 0.0164, + "step": 33028 + }, + { + "epoch": 10.2, + "learning_rate": 1.0161281134755324e-05, + "loss": 0.0133, + "step": 33029 + }, + { + "epoch": 10.2, + "learning_rate": 1.0160781081377515e-05, + "loss": 0.0118, + "step": 33030 + }, + { + "epoch": 10.2, + "learning_rate": 1.0160281027597563e-05, + "loss": 0.0135, + "step": 33031 + }, + { + "epoch": 10.2, + "learning_rate": 1.0159780973416722e-05, + "loss": 0.0129, + "step": 33032 + }, + { + "epoch": 10.2, + "learning_rate": 1.0159280918836237e-05, + "loss": 0.0127, + "step": 33033 + }, + { + "epoch": 10.2, + "learning_rate": 1.015878086385736e-05, + "loss": 0.0128, + "step": 33034 + }, + { + "epoch": 10.2, + "learning_rate": 1.0158280808481345e-05, + "loss": 0.0128, + "step": 33035 + }, + { + "epoch": 10.2, + "learning_rate": 1.015778075270944e-05, + "loss": 0.012, + "step": 33036 + }, + { + "epoch": 10.2, + "learning_rate": 1.01572806965429e-05, + "loss": 0.014, + "step": 33037 + }, + { + "epoch": 10.2, + "learning_rate": 1.0156780639982968e-05, + "loss": 0.0163, + "step": 33038 + }, + { + "epoch": 10.2, + "learning_rate": 1.0156280583030899e-05, + "loss": 0.0141, + "step": 33039 + }, + { + "epoch": 10.2, + "learning_rate": 1.0155780525687948e-05, + "loss": 0.0122, + "step": 33040 + }, + { + "epoch": 10.2, + "learning_rate": 1.0155280467955357e-05, + "loss": 0.0139, + "step": 33041 + }, + { + "epoch": 10.2, + "learning_rate": 1.0154780409834386e-05, + "loss": 0.0129, + "step": 33042 + }, + { + "epoch": 10.2, + "learning_rate": 1.0154280351326277e-05, + "loss": 0.013, + "step": 33043 + }, + { + "epoch": 10.2, + "learning_rate": 1.0153780292432282e-05, + "loss": 0.0102, + "step": 33044 + }, + { + "epoch": 10.2, + "learning_rate": 1.0153280233153662e-05, + "loss": 0.0144, + "step": 33045 + }, + { + "epoch": 10.21, + "learning_rate": 1.0152780173491657e-05, + "loss": 0.0131, + "step": 33046 + }, + { + "epoch": 10.21, + "learning_rate": 1.0152280113447518e-05, + "loss": 0.0122, + "step": 33047 + }, + { + "epoch": 10.21, + "learning_rate": 1.0151780053022503e-05, + "loss": 0.0095, + "step": 33048 + }, + { + "epoch": 10.21, + "learning_rate": 1.0151279992217853e-05, + "loss": 0.0118, + "step": 33049 + }, + { + "epoch": 10.21, + "learning_rate": 1.0150779931034831e-05, + "loss": 0.0113, + "step": 33050 + }, + { + "epoch": 10.21, + "learning_rate": 1.0150279869474678e-05, + "loss": 0.0138, + "step": 33051 + }, + { + "epoch": 10.21, + "learning_rate": 1.0149779807538645e-05, + "loss": 0.0142, + "step": 33052 + }, + { + "epoch": 10.21, + "learning_rate": 1.0149279745227987e-05, + "loss": 0.0137, + "step": 33053 + }, + { + "epoch": 10.21, + "learning_rate": 1.0148779682543954e-05, + "loss": 0.0118, + "step": 33054 + }, + { + "epoch": 10.21, + "learning_rate": 1.0148279619487795e-05, + "loss": 0.0126, + "step": 33055 + }, + { + "epoch": 10.21, + "learning_rate": 1.0147779556060762e-05, + "loss": 0.0132, + "step": 33056 + }, + { + "epoch": 10.21, + "learning_rate": 1.0147279492264107e-05, + "loss": 0.014, + "step": 33057 + }, + { + "epoch": 10.21, + "learning_rate": 1.0146779428099076e-05, + "loss": 0.0146, + "step": 33058 + }, + { + "epoch": 10.21, + "learning_rate": 1.0146279363566925e-05, + "loss": 0.0141, + "step": 33059 + }, + { + "epoch": 10.21, + "learning_rate": 1.0145779298668906e-05, + "loss": 0.0123, + "step": 33060 + }, + { + "epoch": 10.21, + "learning_rate": 1.0145279233406258e-05, + "loss": 0.0127, + "step": 33061 + }, + { + "epoch": 10.21, + "learning_rate": 1.0144779167780245e-05, + "loss": 0.0141, + "step": 33062 + }, + { + "epoch": 10.21, + "learning_rate": 1.0144279101792115e-05, + "loss": 0.0129, + "step": 33063 + }, + { + "epoch": 10.21, + "learning_rate": 1.0143779035443111e-05, + "loss": 0.0139, + "step": 33064 + }, + { + "epoch": 10.21, + "learning_rate": 1.0143278968734495e-05, + "loss": 0.0114, + "step": 33065 + }, + { + "epoch": 10.21, + "learning_rate": 1.0142778901667508e-05, + "loss": 0.0131, + "step": 33066 + }, + { + "epoch": 10.21, + "learning_rate": 1.0142278834243406e-05, + "loss": 0.0131, + "step": 33067 + }, + { + "epoch": 10.21, + "learning_rate": 1.014177876646344e-05, + "loss": 0.0153, + "step": 33068 + }, + { + "epoch": 10.21, + "learning_rate": 1.0141278698328858e-05, + "loss": 0.0145, + "step": 33069 + }, + { + "epoch": 10.21, + "learning_rate": 1.0140778629840916e-05, + "loss": 0.0143, + "step": 33070 + }, + { + "epoch": 10.21, + "learning_rate": 1.0140278561000858e-05, + "loss": 0.0111, + "step": 33071 + }, + { + "epoch": 10.21, + "learning_rate": 1.0139778491809935e-05, + "loss": 0.0116, + "step": 33072 + }, + { + "epoch": 10.21, + "learning_rate": 1.0139278422269405e-05, + "loss": 0.0131, + "step": 33073 + }, + { + "epoch": 10.21, + "learning_rate": 1.0138778352380512e-05, + "loss": 0.0125, + "step": 33074 + }, + { + "epoch": 10.21, + "learning_rate": 1.0138278282144507e-05, + "loss": 0.0117, + "step": 33075 + }, + { + "epoch": 10.21, + "learning_rate": 1.0137778211562648e-05, + "loss": 0.0138, + "step": 33076 + }, + { + "epoch": 10.21, + "learning_rate": 1.0137278140636177e-05, + "loss": 0.0114, + "step": 33077 + }, + { + "epoch": 10.22, + "learning_rate": 1.0136778069366351e-05, + "loss": 0.0134, + "step": 33078 + }, + { + "epoch": 10.22, + "learning_rate": 1.0136277997754415e-05, + "loss": 0.0119, + "step": 33079 + }, + { + "epoch": 10.22, + "learning_rate": 1.0135777925801625e-05, + "loss": 0.0128, + "step": 33080 + }, + { + "epoch": 10.22, + "learning_rate": 1.0135277853509229e-05, + "loss": 0.0137, + "step": 33081 + }, + { + "epoch": 10.22, + "learning_rate": 1.0134777780878477e-05, + "loss": 0.0127, + "step": 33082 + }, + { + "epoch": 10.22, + "learning_rate": 1.0134277707910622e-05, + "loss": 0.0116, + "step": 33083 + }, + { + "epoch": 10.22, + "learning_rate": 1.0133777634606915e-05, + "loss": 0.0139, + "step": 33084 + }, + { + "epoch": 10.22, + "learning_rate": 1.0133277560968603e-05, + "loss": 0.0143, + "step": 33085 + }, + { + "epoch": 10.22, + "learning_rate": 1.0132777486996944e-05, + "loss": 0.0144, + "step": 33086 + }, + { + "epoch": 10.22, + "learning_rate": 1.0132277412693181e-05, + "loss": 0.0137, + "step": 33087 + }, + { + "epoch": 10.22, + "learning_rate": 1.0131777338058568e-05, + "loss": 0.0133, + "step": 33088 + }, + { + "epoch": 10.22, + "learning_rate": 1.0131277263094357e-05, + "loss": 0.0137, + "step": 33089 + }, + { + "epoch": 10.22, + "learning_rate": 1.0130777187801799e-05, + "loss": 0.0141, + "step": 33090 + }, + { + "epoch": 10.22, + "learning_rate": 1.0130277112182144e-05, + "loss": 0.0129, + "step": 33091 + }, + { + "epoch": 10.22, + "learning_rate": 1.0129777036236637e-05, + "loss": 0.0125, + "step": 33092 + }, + { + "epoch": 10.22, + "learning_rate": 1.0129276959966536e-05, + "loss": 0.013, + "step": 33093 + }, + { + "epoch": 10.22, + "learning_rate": 1.0128776883373093e-05, + "loss": 0.0124, + "step": 33094 + }, + { + "epoch": 10.22, + "learning_rate": 1.012827680645755e-05, + "loss": 0.0152, + "step": 33095 + }, + { + "epoch": 10.22, + "learning_rate": 1.012777672922117e-05, + "loss": 0.0135, + "step": 33096 + }, + { + "epoch": 10.22, + "learning_rate": 1.0127276651665194e-05, + "loss": 0.0131, + "step": 33097 + }, + { + "epoch": 10.22, + "learning_rate": 1.0126776573790873e-05, + "loss": 0.0137, + "step": 33098 + }, + { + "epoch": 10.22, + "learning_rate": 1.0126276495599465e-05, + "loss": 0.0124, + "step": 33099 + }, + { + "epoch": 10.22, + "learning_rate": 1.0125776417092213e-05, + "loss": 0.0138, + "step": 33100 + }, + { + "epoch": 10.22, + "learning_rate": 1.0125276338270375e-05, + "loss": 0.0118, + "step": 33101 + }, + { + "epoch": 10.22, + "learning_rate": 1.0124776259135196e-05, + "loss": 0.0112, + "step": 33102 + }, + { + "epoch": 10.22, + "learning_rate": 1.0124276179687926e-05, + "loss": 0.0141, + "step": 33103 + }, + { + "epoch": 10.22, + "learning_rate": 1.0123776099929822e-05, + "loss": 0.0134, + "step": 33104 + }, + { + "epoch": 10.22, + "learning_rate": 1.0123276019862131e-05, + "loss": 0.014, + "step": 33105 + }, + { + "epoch": 10.22, + "learning_rate": 1.0122775939486105e-05, + "loss": 0.014, + "step": 33106 + }, + { + "epoch": 10.22, + "learning_rate": 1.0122275858802993e-05, + "loss": 0.0111, + "step": 33107 + }, + { + "epoch": 10.22, + "learning_rate": 1.0121775777814047e-05, + "loss": 0.013, + "step": 33108 + }, + { + "epoch": 10.22, + "learning_rate": 1.0121275696520516e-05, + "loss": 0.0138, + "step": 33109 + }, + { + "epoch": 10.23, + "learning_rate": 1.0120775614923654e-05, + "loss": 0.0125, + "step": 33110 + }, + { + "epoch": 10.23, + "learning_rate": 1.012027553302471e-05, + "loss": 0.0125, + "step": 33111 + }, + { + "epoch": 10.23, + "learning_rate": 1.0119775450824934e-05, + "loss": 0.0124, + "step": 33112 + }, + { + "epoch": 10.23, + "learning_rate": 1.0119275368325579e-05, + "loss": 0.0121, + "step": 33113 + }, + { + "epoch": 10.23, + "learning_rate": 1.0118775285527893e-05, + "loss": 0.0124, + "step": 33114 + }, + { + "epoch": 10.23, + "learning_rate": 1.011827520243313e-05, + "loss": 0.015, + "step": 33115 + }, + { + "epoch": 10.23, + "learning_rate": 1.0117775119042539e-05, + "loss": 0.0127, + "step": 33116 + }, + { + "epoch": 10.23, + "learning_rate": 1.011727503535737e-05, + "loss": 0.0166, + "step": 33117 + }, + { + "epoch": 10.23, + "learning_rate": 1.0116774951378877e-05, + "loss": 0.0116, + "step": 33118 + }, + { + "epoch": 10.23, + "learning_rate": 1.0116274867108305e-05, + "loss": 0.0124, + "step": 33119 + }, + { + "epoch": 10.23, + "learning_rate": 1.011577478254691e-05, + "loss": 0.0115, + "step": 33120 + }, + { + "epoch": 10.23, + "learning_rate": 1.011527469769594e-05, + "loss": 0.0136, + "step": 33121 + }, + { + "epoch": 10.23, + "learning_rate": 1.0114774612556652e-05, + "loss": 0.0133, + "step": 33122 + }, + { + "epoch": 10.23, + "learning_rate": 1.0114274527130285e-05, + "loss": 0.0116, + "step": 33123 + }, + { + "epoch": 10.23, + "learning_rate": 1.01137744414181e-05, + "loss": 0.0126, + "step": 33124 + }, + { + "epoch": 10.23, + "learning_rate": 1.0113274355421346e-05, + "loss": 0.0121, + "step": 33125 + }, + { + "epoch": 10.23, + "learning_rate": 1.0112774269141268e-05, + "loss": 0.0135, + "step": 33126 + }, + { + "epoch": 10.23, + "learning_rate": 1.0112274182579124e-05, + "loss": 0.0128, + "step": 33127 + }, + { + "epoch": 10.23, + "learning_rate": 1.0111774095736162e-05, + "loss": 0.0175, + "step": 33128 + }, + { + "epoch": 10.23, + "learning_rate": 1.011127400861363e-05, + "loss": 0.0143, + "step": 33129 + }, + { + "epoch": 10.23, + "learning_rate": 1.0110773921212784e-05, + "loss": 0.0137, + "step": 33130 + }, + { + "epoch": 10.23, + "learning_rate": 1.0110273833534869e-05, + "loss": 0.0114, + "step": 33131 + }, + { + "epoch": 10.23, + "learning_rate": 1.0109773745581143e-05, + "loss": 0.0123, + "step": 33132 + }, + { + "epoch": 10.23, + "learning_rate": 1.0109273657352852e-05, + "loss": 0.0139, + "step": 33133 + }, + { + "epoch": 10.23, + "learning_rate": 1.0108773568851244e-05, + "loss": 0.0164, + "step": 33134 + }, + { + "epoch": 10.23, + "learning_rate": 1.0108273480077577e-05, + "loss": 0.0154, + "step": 33135 + }, + { + "epoch": 10.23, + "learning_rate": 1.0107773391033098e-05, + "loss": 0.013, + "step": 33136 + }, + { + "epoch": 10.23, + "learning_rate": 1.0107273301719058e-05, + "loss": 0.0129, + "step": 33137 + }, + { + "epoch": 10.23, + "learning_rate": 1.0106773212136707e-05, + "loss": 0.0177, + "step": 33138 + }, + { + "epoch": 10.23, + "learning_rate": 1.0106273122287298e-05, + "loss": 0.013, + "step": 33139 + }, + { + "epoch": 10.23, + "learning_rate": 1.0105773032172078e-05, + "loss": 0.0132, + "step": 33140 + }, + { + "epoch": 10.23, + "learning_rate": 1.0105272941792302e-05, + "loss": 0.012, + "step": 33141 + }, + { + "epoch": 10.23, + "learning_rate": 1.0104772851149221e-05, + "loss": 0.0112, + "step": 33142 + }, + { + "epoch": 10.24, + "learning_rate": 1.010427276024408e-05, + "loss": 0.0138, + "step": 33143 + }, + { + "epoch": 10.24, + "learning_rate": 1.0103772669078135e-05, + "loss": 0.0153, + "step": 33144 + }, + { + "epoch": 10.24, + "learning_rate": 1.010327257765264e-05, + "loss": 0.0118, + "step": 33145 + }, + { + "epoch": 10.24, + "learning_rate": 1.0102772485968837e-05, + "loss": 0.0122, + "step": 33146 + }, + { + "epoch": 10.24, + "learning_rate": 1.010227239402798e-05, + "loss": 0.0126, + "step": 33147 + }, + { + "epoch": 10.24, + "learning_rate": 1.0101772301831325e-05, + "loss": 0.0141, + "step": 33148 + }, + { + "epoch": 10.24, + "learning_rate": 1.0101272209380117e-05, + "loss": 0.0139, + "step": 33149 + }, + { + "epoch": 10.24, + "learning_rate": 1.010077211667561e-05, + "loss": 0.0139, + "step": 33150 + }, + { + "epoch": 10.24, + "learning_rate": 1.0100272023719051e-05, + "loss": 0.0148, + "step": 33151 + }, + { + "epoch": 10.24, + "learning_rate": 1.0099771930511695e-05, + "loss": 0.0151, + "step": 33152 + }, + { + "epoch": 10.24, + "learning_rate": 1.0099271837054793e-05, + "loss": 0.0136, + "step": 33153 + }, + { + "epoch": 10.24, + "learning_rate": 1.0098771743349592e-05, + "loss": 0.0135, + "step": 33154 + }, + { + "epoch": 10.24, + "learning_rate": 1.0098271649397347e-05, + "loss": 0.0125, + "step": 33155 + }, + { + "epoch": 10.24, + "learning_rate": 1.0097771555199303e-05, + "loss": 0.0133, + "step": 33156 + }, + { + "epoch": 10.24, + "learning_rate": 1.0097271460756714e-05, + "loss": 0.0121, + "step": 33157 + }, + { + "epoch": 10.24, + "learning_rate": 1.0096771366070837e-05, + "loss": 0.0153, + "step": 33158 + }, + { + "epoch": 10.24, + "learning_rate": 1.0096271271142913e-05, + "loss": 0.0142, + "step": 33159 + }, + { + "epoch": 10.24, + "learning_rate": 1.0095771175974198e-05, + "loss": 0.0133, + "step": 33160 + }, + { + "epoch": 10.24, + "learning_rate": 1.009527108056594e-05, + "loss": 0.0122, + "step": 33161 + }, + { + "epoch": 10.24, + "learning_rate": 1.0094770984919393e-05, + "loss": 0.0124, + "step": 33162 + }, + { + "epoch": 10.24, + "learning_rate": 1.0094270889035809e-05, + "loss": 0.0129, + "step": 33163 + }, + { + "epoch": 10.24, + "learning_rate": 1.0093770792916433e-05, + "loss": 0.0168, + "step": 33164 + }, + { + "epoch": 10.24, + "learning_rate": 1.009327069656252e-05, + "loss": 0.0151, + "step": 33165 + }, + { + "epoch": 10.24, + "learning_rate": 1.009277059997532e-05, + "loss": 0.0143, + "step": 33166 + }, + { + "epoch": 10.24, + "learning_rate": 1.0092270503156083e-05, + "loss": 0.0149, + "step": 33167 + }, + { + "epoch": 10.24, + "learning_rate": 1.0091770406106062e-05, + "loss": 0.014, + "step": 33168 + }, + { + "epoch": 10.24, + "learning_rate": 1.0091270308826506e-05, + "loss": 0.014, + "step": 33169 + }, + { + "epoch": 10.24, + "learning_rate": 1.0090770211318665e-05, + "loss": 0.0137, + "step": 33170 + }, + { + "epoch": 10.24, + "learning_rate": 1.0090270113583793e-05, + "loss": 0.014, + "step": 33171 + }, + { + "epoch": 10.24, + "learning_rate": 1.0089770015623139e-05, + "loss": 0.0129, + "step": 33172 + }, + { + "epoch": 10.24, + "learning_rate": 1.0089269917437953e-05, + "loss": 0.0127, + "step": 33173 + }, + { + "epoch": 10.24, + "learning_rate": 1.0088769819029487e-05, + "loss": 0.0135, + "step": 33174 + }, + { + "epoch": 10.25, + "learning_rate": 1.008826972039899e-05, + "loss": 0.014, + "step": 33175 + }, + { + "epoch": 10.25, + "learning_rate": 1.008776962154772e-05, + "loss": 0.0144, + "step": 33176 + }, + { + "epoch": 10.25, + "learning_rate": 1.0087269522476914e-05, + "loss": 0.0125, + "step": 33177 + }, + { + "epoch": 10.25, + "learning_rate": 1.0086769423187837e-05, + "loss": 0.0174, + "step": 33178 + }, + { + "epoch": 10.25, + "learning_rate": 1.0086269323681734e-05, + "loss": 0.014, + "step": 33179 + }, + { + "epoch": 10.25, + "learning_rate": 1.0085769223959851e-05, + "loss": 0.0122, + "step": 33180 + }, + { + "epoch": 10.25, + "learning_rate": 1.0085269124023447e-05, + "loss": 0.0132, + "step": 33181 + }, + { + "epoch": 10.25, + "learning_rate": 1.0084769023873767e-05, + "loss": 0.0131, + "step": 33182 + }, + { + "epoch": 10.25, + "learning_rate": 1.0084268923512065e-05, + "loss": 0.013, + "step": 33183 + }, + { + "epoch": 10.25, + "learning_rate": 1.0083768822939594e-05, + "loss": 0.0126, + "step": 33184 + }, + { + "epoch": 10.25, + "learning_rate": 1.0083268722157597e-05, + "loss": 0.0122, + "step": 33185 + }, + { + "epoch": 10.25, + "learning_rate": 1.0082768621167336e-05, + "loss": 0.0142, + "step": 33186 + }, + { + "epoch": 10.25, + "learning_rate": 1.008226851997005e-05, + "loss": 0.0128, + "step": 33187 + }, + { + "epoch": 10.25, + "learning_rate": 1.0081768418566996e-05, + "loss": 0.0141, + "step": 33188 + }, + { + "epoch": 10.25, + "learning_rate": 1.0081268316959428e-05, + "loss": 0.0138, + "step": 33189 + }, + { + "epoch": 10.25, + "learning_rate": 1.008076821514859e-05, + "loss": 0.0153, + "step": 33190 + }, + { + "epoch": 10.25, + "learning_rate": 1.0080268113135736e-05, + "loss": 0.013, + "step": 33191 + }, + { + "epoch": 10.25, + "learning_rate": 1.0079768010922118e-05, + "loss": 0.0141, + "step": 33192 + }, + { + "epoch": 10.25, + "learning_rate": 1.0079267908508986e-05, + "loss": 0.0133, + "step": 33193 + }, + { + "epoch": 10.25, + "learning_rate": 1.0078767805897589e-05, + "loss": 0.0131, + "step": 33194 + }, + { + "epoch": 10.25, + "learning_rate": 1.0078267703089179e-05, + "loss": 0.0117, + "step": 33195 + }, + { + "epoch": 10.25, + "learning_rate": 1.007776760008501e-05, + "loss": 0.0141, + "step": 33196 + }, + { + "epoch": 10.25, + "learning_rate": 1.0077267496886328e-05, + "loss": 0.0158, + "step": 33197 + }, + { + "epoch": 10.25, + "learning_rate": 1.0076767393494385e-05, + "loss": 0.0136, + "step": 33198 + }, + { + "epoch": 10.25, + "learning_rate": 1.0076267289910433e-05, + "loss": 0.0132, + "step": 33199 + }, + { + "epoch": 10.25, + "learning_rate": 1.0075767186135723e-05, + "loss": 0.0125, + "step": 33200 + }, + { + "epoch": 10.25, + "learning_rate": 1.0075267082171508e-05, + "loss": 0.0142, + "step": 33201 + }, + { + "epoch": 10.25, + "learning_rate": 1.0074766978019033e-05, + "loss": 0.0149, + "step": 33202 + }, + { + "epoch": 10.25, + "learning_rate": 1.0074266873679555e-05, + "loss": 0.0131, + "step": 33203 + }, + { + "epoch": 10.25, + "learning_rate": 1.0073766769154321e-05, + "loss": 0.0132, + "step": 33204 + }, + { + "epoch": 10.25, + "learning_rate": 1.0073266664444581e-05, + "loss": 0.0152, + "step": 33205 + }, + { + "epoch": 10.25, + "learning_rate": 1.0072766559551588e-05, + "loss": 0.0132, + "step": 33206 + }, + { + "epoch": 10.25, + "learning_rate": 1.0072266454476596e-05, + "loss": 0.0123, + "step": 33207 + }, + { + "epoch": 10.26, + "learning_rate": 1.0071766349220847e-05, + "loss": 0.013, + "step": 33208 + }, + { + "epoch": 10.26, + "learning_rate": 1.0071266243785603e-05, + "loss": 0.0132, + "step": 33209 + }, + { + "epoch": 10.26, + "learning_rate": 1.0070766138172106e-05, + "loss": 0.0129, + "step": 33210 + }, + { + "epoch": 10.26, + "learning_rate": 1.0070266032381608e-05, + "loss": 0.016, + "step": 33211 + }, + { + "epoch": 10.26, + "learning_rate": 1.0069765926415366e-05, + "loss": 0.0141, + "step": 33212 + }, + { + "epoch": 10.26, + "learning_rate": 1.0069265820274624e-05, + "loss": 0.0132, + "step": 33213 + }, + { + "epoch": 10.26, + "learning_rate": 1.0068765713960638e-05, + "loss": 0.013, + "step": 33214 + }, + { + "epoch": 10.26, + "learning_rate": 1.0068265607474654e-05, + "loss": 0.0144, + "step": 33215 + }, + { + "epoch": 10.26, + "learning_rate": 1.0067765500817923e-05, + "loss": 0.0126, + "step": 33216 + }, + { + "epoch": 10.26, + "learning_rate": 1.0067265393991704e-05, + "loss": 0.0118, + "step": 33217 + }, + { + "epoch": 10.26, + "learning_rate": 1.006676528699724e-05, + "loss": 0.0143, + "step": 33218 + }, + { + "epoch": 10.26, + "learning_rate": 1.006626517983578e-05, + "loss": 0.0153, + "step": 33219 + }, + { + "epoch": 10.26, + "learning_rate": 1.0065765072508584e-05, + "loss": 0.0129, + "step": 33220 + }, + { + "epoch": 10.26, + "learning_rate": 1.0065264965016895e-05, + "loss": 0.0132, + "step": 33221 + }, + { + "epoch": 10.26, + "learning_rate": 1.0064764857361966e-05, + "loss": 0.0126, + "step": 33222 + }, + { + "epoch": 10.26, + "learning_rate": 1.006426474954505e-05, + "loss": 0.0129, + "step": 33223 + }, + { + "epoch": 10.26, + "learning_rate": 1.0063764641567394e-05, + "loss": 0.0153, + "step": 33224 + }, + { + "epoch": 10.26, + "learning_rate": 1.0063264533430253e-05, + "loss": 0.0123, + "step": 33225 + }, + { + "epoch": 10.26, + "learning_rate": 1.0062764425134875e-05, + "loss": 0.0137, + "step": 33226 + }, + { + "epoch": 10.26, + "learning_rate": 1.006226431668251e-05, + "loss": 0.0122, + "step": 33227 + }, + { + "epoch": 10.26, + "learning_rate": 1.0061764208074413e-05, + "loss": 0.0144, + "step": 33228 + }, + { + "epoch": 10.26, + "learning_rate": 1.0061264099311831e-05, + "loss": 0.0159, + "step": 33229 + }, + { + "epoch": 10.26, + "learning_rate": 1.0060763990396019e-05, + "loss": 0.0132, + "step": 33230 + }, + { + "epoch": 10.26, + "learning_rate": 1.0060263881328223e-05, + "loss": 0.0141, + "step": 33231 + }, + { + "epoch": 10.26, + "learning_rate": 1.0059763772109693e-05, + "loss": 0.0137, + "step": 33232 + }, + { + "epoch": 10.26, + "learning_rate": 1.0059263662741688e-05, + "loss": 0.0126, + "step": 33233 + }, + { + "epoch": 10.26, + "learning_rate": 1.0058763553225453e-05, + "loss": 0.0124, + "step": 33234 + }, + { + "epoch": 10.26, + "learning_rate": 1.0058263443562239e-05, + "loss": 0.0116, + "step": 33235 + }, + { + "epoch": 10.26, + "learning_rate": 1.0057763333753295e-05, + "loss": 0.0134, + "step": 33236 + }, + { + "epoch": 10.26, + "learning_rate": 1.0057263223799876e-05, + "loss": 0.0145, + "step": 33237 + }, + { + "epoch": 10.26, + "learning_rate": 1.0056763113703233e-05, + "loss": 0.0138, + "step": 33238 + }, + { + "epoch": 10.26, + "learning_rate": 1.0056263003464613e-05, + "loss": 0.0121, + "step": 33239 + }, + { + "epoch": 10.27, + "learning_rate": 1.0055762893085272e-05, + "loss": 0.0138, + "step": 33240 + }, + { + "epoch": 10.27, + "learning_rate": 1.0055262782566455e-05, + "loss": 0.0125, + "step": 33241 + }, + { + "epoch": 10.27, + "learning_rate": 1.0054762671909416e-05, + "loss": 0.0137, + "step": 33242 + }, + { + "epoch": 10.27, + "learning_rate": 1.0054262561115406e-05, + "loss": 0.015, + "step": 33243 + }, + { + "epoch": 10.27, + "learning_rate": 1.0053762450185675e-05, + "loss": 0.0135, + "step": 33244 + }, + { + "epoch": 10.27, + "learning_rate": 1.0053262339121475e-05, + "loss": 0.0139, + "step": 33245 + }, + { + "epoch": 10.27, + "learning_rate": 1.0052762227924056e-05, + "loss": 0.0117, + "step": 33246 + }, + { + "epoch": 10.27, + "learning_rate": 1.0052262116594666e-05, + "loss": 0.0114, + "step": 33247 + }, + { + "epoch": 10.27, + "learning_rate": 1.0051762005134565e-05, + "loss": 0.0154, + "step": 33248 + }, + { + "epoch": 10.27, + "learning_rate": 1.0051261893544992e-05, + "loss": 0.0154, + "step": 33249 + }, + { + "epoch": 10.27, + "learning_rate": 1.0050761781827208e-05, + "loss": 0.0144, + "step": 33250 + }, + { + "epoch": 10.27, + "learning_rate": 1.0050261669982457e-05, + "loss": 0.012, + "step": 33251 + }, + { + "epoch": 10.27, + "learning_rate": 1.0049761558011992e-05, + "loss": 0.0143, + "step": 33252 + }, + { + "epoch": 10.27, + "learning_rate": 1.0049261445917067e-05, + "loss": 0.0111, + "step": 33253 + }, + { + "epoch": 10.27, + "learning_rate": 1.0048761333698929e-05, + "loss": 0.0149, + "step": 33254 + }, + { + "epoch": 10.27, + "learning_rate": 1.0048261221358828e-05, + "loss": 0.0145, + "step": 33255 + }, + { + "epoch": 10.27, + "learning_rate": 1.0047761108898017e-05, + "loss": 0.0128, + "step": 33256 + }, + { + "epoch": 10.27, + "learning_rate": 1.0047260996317749e-05, + "loss": 0.0129, + "step": 33257 + }, + { + "epoch": 10.27, + "learning_rate": 1.0046760883619276e-05, + "loss": 0.0137, + "step": 33258 + }, + { + "epoch": 10.27, + "learning_rate": 1.0046260770803837e-05, + "loss": 0.0159, + "step": 33259 + }, + { + "epoch": 10.27, + "learning_rate": 1.0045760657872696e-05, + "loss": 0.0133, + "step": 33260 + }, + { + "epoch": 10.27, + "learning_rate": 1.00452605448271e-05, + "loss": 0.0137, + "step": 33261 + }, + { + "epoch": 10.27, + "learning_rate": 1.0044760431668296e-05, + "loss": 0.0134, + "step": 33262 + }, + { + "epoch": 10.27, + "learning_rate": 1.0044260318397542e-05, + "loss": 0.0135, + "step": 33263 + }, + { + "epoch": 10.27, + "learning_rate": 1.0043760205016082e-05, + "loss": 0.0149, + "step": 33264 + }, + { + "epoch": 10.27, + "learning_rate": 1.004326009152517e-05, + "loss": 0.0181, + "step": 33265 + }, + { + "epoch": 10.27, + "learning_rate": 1.004275997792606e-05, + "loss": 0.0126, + "step": 33266 + }, + { + "epoch": 10.27, + "learning_rate": 1.0042259864219994e-05, + "loss": 0.0117, + "step": 33267 + }, + { + "epoch": 10.27, + "learning_rate": 1.0041759750408233e-05, + "loss": 0.0123, + "step": 33268 + }, + { + "epoch": 10.27, + "learning_rate": 1.0041259636492022e-05, + "loss": 0.0135, + "step": 33269 + }, + { + "epoch": 10.27, + "learning_rate": 1.0040759522472609e-05, + "loss": 0.013, + "step": 33270 + }, + { + "epoch": 10.27, + "learning_rate": 1.0040259408351256e-05, + "loss": 0.0143, + "step": 33271 + }, + { + "epoch": 10.28, + "learning_rate": 1.0039759294129204e-05, + "loss": 0.0129, + "step": 33272 + }, + { + "epoch": 10.28, + "learning_rate": 1.0039259179807705e-05, + "loss": 0.0144, + "step": 33273 + }, + { + "epoch": 10.28, + "learning_rate": 1.0038759065388013e-05, + "loss": 0.0154, + "step": 33274 + }, + { + "epoch": 10.28, + "learning_rate": 1.0038258950871375e-05, + "loss": 0.0143, + "step": 33275 + }, + { + "epoch": 10.28, + "learning_rate": 1.0037758836259048e-05, + "loss": 0.0133, + "step": 33276 + }, + { + "epoch": 10.28, + "learning_rate": 1.0037258721552278e-05, + "loss": 0.0168, + "step": 33277 + }, + { + "epoch": 10.28, + "learning_rate": 1.0036758606752318e-05, + "loss": 0.0158, + "step": 33278 + }, + { + "epoch": 10.28, + "learning_rate": 1.0036258491860415e-05, + "loss": 0.0148, + "step": 33279 + }, + { + "epoch": 10.28, + "learning_rate": 1.0035758376877826e-05, + "loss": 0.0148, + "step": 33280 + }, + { + "epoch": 10.28, + "learning_rate": 1.0035258261805799e-05, + "loss": 0.0144, + "step": 33281 + }, + { + "epoch": 10.28, + "learning_rate": 1.0034758146645582e-05, + "loss": 0.0169, + "step": 33282 + }, + { + "epoch": 10.28, + "learning_rate": 1.0034258031398429e-05, + "loss": 0.012, + "step": 33283 + }, + { + "epoch": 10.28, + "learning_rate": 1.0033757916065591e-05, + "loss": 0.0134, + "step": 33284 + }, + { + "epoch": 10.28, + "learning_rate": 1.003325780064832e-05, + "loss": 0.0142, + "step": 33285 + }, + { + "epoch": 10.28, + "learning_rate": 1.0032757685147862e-05, + "loss": 0.0136, + "step": 33286 + }, + { + "epoch": 10.28, + "learning_rate": 1.0032257569565473e-05, + "loss": 0.0127, + "step": 33287 + }, + { + "epoch": 10.28, + "learning_rate": 1.0031757453902402e-05, + "loss": 0.0123, + "step": 33288 + }, + { + "epoch": 10.28, + "learning_rate": 1.0031257338159904e-05, + "loss": 0.0133, + "step": 33289 + }, + { + "epoch": 10.28, + "learning_rate": 1.0030757222339218e-05, + "loss": 0.011, + "step": 33290 + }, + { + "epoch": 10.28, + "learning_rate": 1.0030257106441606e-05, + "loss": 0.0135, + "step": 33291 + }, + { + "epoch": 10.28, + "learning_rate": 1.0029756990468317e-05, + "loss": 0.0168, + "step": 33292 + }, + { + "epoch": 10.28, + "learning_rate": 1.0029256874420596e-05, + "loss": 0.0136, + "step": 33293 + }, + { + "epoch": 10.28, + "learning_rate": 1.0028756758299703e-05, + "loss": 0.0137, + "step": 33294 + }, + { + "epoch": 10.28, + "learning_rate": 1.002825664210688e-05, + "loss": 0.0155, + "step": 33295 + }, + { + "epoch": 10.28, + "learning_rate": 1.0027756525843384e-05, + "loss": 0.0143, + "step": 33296 + }, + { + "epoch": 10.28, + "learning_rate": 1.0027256409510466e-05, + "loss": 0.0144, + "step": 33297 + }, + { + "epoch": 10.28, + "learning_rate": 1.002675629310937e-05, + "loss": 0.0143, + "step": 33298 + }, + { + "epoch": 10.28, + "learning_rate": 1.0026256176641356e-05, + "loss": 0.0119, + "step": 33299 + }, + { + "epoch": 10.28, + "learning_rate": 1.002575606010767e-05, + "loss": 0.0115, + "step": 33300 + }, + { + "epoch": 10.28, + "learning_rate": 1.002525594350956e-05, + "loss": 0.0118, + "step": 33301 + }, + { + "epoch": 10.28, + "learning_rate": 1.0024755826848285e-05, + "loss": 0.014, + "step": 33302 + }, + { + "epoch": 10.28, + "learning_rate": 1.0024255710125088e-05, + "loss": 0.0145, + "step": 33303 + }, + { + "epoch": 10.28, + "learning_rate": 1.0023755593341222e-05, + "loss": 0.0127, + "step": 33304 + }, + { + "epoch": 10.29, + "learning_rate": 1.0023255476497942e-05, + "loss": 0.013, + "step": 33305 + }, + { + "epoch": 10.29, + "learning_rate": 1.0022755359596495e-05, + "loss": 0.0137, + "step": 33306 + }, + { + "epoch": 10.29, + "learning_rate": 1.002225524263813e-05, + "loss": 0.0139, + "step": 33307 + }, + { + "epoch": 10.29, + "learning_rate": 1.0021755125624105e-05, + "loss": 0.0147, + "step": 33308 + }, + { + "epoch": 10.29, + "learning_rate": 1.0021255008555662e-05, + "loss": 0.0127, + "step": 33309 + }, + { + "epoch": 10.29, + "learning_rate": 1.0020754891434058e-05, + "loss": 0.0134, + "step": 33310 + }, + { + "epoch": 10.29, + "learning_rate": 1.0020254774260542e-05, + "loss": 0.0126, + "step": 33311 + }, + { + "epoch": 10.29, + "learning_rate": 1.0019754657036367e-05, + "loss": 0.0118, + "step": 33312 + }, + { + "epoch": 10.29, + "learning_rate": 1.0019254539762782e-05, + "loss": 0.0133, + "step": 33313 + }, + { + "epoch": 10.29, + "learning_rate": 1.0018754422441035e-05, + "loss": 0.013, + "step": 33314 + }, + { + "epoch": 10.29, + "learning_rate": 1.0018254305072382e-05, + "loss": 0.0133, + "step": 33315 + }, + { + "epoch": 10.29, + "learning_rate": 1.0017754187658071e-05, + "loss": 0.0127, + "step": 33316 + }, + { + "epoch": 10.29, + "learning_rate": 1.0017254070199355e-05, + "loss": 0.0149, + "step": 33317 + }, + { + "epoch": 10.29, + "learning_rate": 1.001675395269748e-05, + "loss": 0.0119, + "step": 33318 + }, + { + "epoch": 10.29, + "learning_rate": 1.0016253835153702e-05, + "loss": 0.012, + "step": 33319 + }, + { + "epoch": 10.29, + "learning_rate": 1.0015753717569274e-05, + "loss": 0.0158, + "step": 33320 + }, + { + "epoch": 10.29, + "learning_rate": 1.0015253599945436e-05, + "loss": 0.0127, + "step": 33321 + }, + { + "epoch": 10.29, + "learning_rate": 1.0014753482283453e-05, + "loss": 0.0146, + "step": 33322 + }, + { + "epoch": 10.29, + "learning_rate": 1.0014253364584566e-05, + "loss": 0.0139, + "step": 33323 + }, + { + "epoch": 10.29, + "learning_rate": 1.0013753246850024e-05, + "loss": 0.0117, + "step": 33324 + }, + { + "epoch": 10.29, + "learning_rate": 1.0013253129081092e-05, + "loss": 0.0118, + "step": 33325 + }, + { + "epoch": 10.29, + "learning_rate": 1.0012753011279004e-05, + "loss": 0.0113, + "step": 33326 + }, + { + "epoch": 10.29, + "learning_rate": 1.0012252893445021e-05, + "loss": 0.0146, + "step": 33327 + }, + { + "epoch": 10.29, + "learning_rate": 1.001175277558039e-05, + "loss": 0.0159, + "step": 33328 + }, + { + "epoch": 10.29, + "learning_rate": 1.0011252657686363e-05, + "loss": 0.0122, + "step": 33329 + }, + { + "epoch": 10.29, + "learning_rate": 1.0010752539764195e-05, + "loss": 0.0143, + "step": 33330 + }, + { + "epoch": 10.29, + "learning_rate": 1.001025242181513e-05, + "loss": 0.0123, + "step": 33331 + }, + { + "epoch": 10.29, + "learning_rate": 1.0009752303840419e-05, + "loss": 0.013, + "step": 33332 + }, + { + "epoch": 10.29, + "learning_rate": 1.000925218584132e-05, + "loss": 0.0134, + "step": 33333 + }, + { + "epoch": 10.29, + "learning_rate": 1.0008752067819079e-05, + "loss": 0.0127, + "step": 33334 + }, + { + "epoch": 10.29, + "learning_rate": 1.0008251949774948e-05, + "loss": 0.0125, + "step": 33335 + }, + { + "epoch": 10.29, + "learning_rate": 1.0007751831710176e-05, + "loss": 0.0144, + "step": 33336 + }, + { + "epoch": 10.3, + "learning_rate": 1.0007251713626014e-05, + "loss": 0.0144, + "step": 33337 + }, + { + "epoch": 10.3, + "learning_rate": 1.0006751595523717e-05, + "loss": 0.0134, + "step": 33338 + }, + { + "epoch": 10.3, + "learning_rate": 1.0006251477404529e-05, + "loss": 0.0137, + "step": 33339 + }, + { + "epoch": 10.3, + "learning_rate": 1.0005751359269708e-05, + "loss": 0.0128, + "step": 33340 + }, + { + "epoch": 10.3, + "learning_rate": 1.0005251241120502e-05, + "loss": 0.0139, + "step": 33341 + }, + { + "epoch": 10.3, + "learning_rate": 1.0004751122958161e-05, + "loss": 0.0131, + "step": 33342 + }, + { + "epoch": 10.3, + "learning_rate": 1.0004251004783938e-05, + "loss": 0.014, + "step": 33343 + }, + { + "epoch": 10.3, + "learning_rate": 1.000375088659908e-05, + "loss": 0.0132, + "step": 33344 + }, + { + "epoch": 10.3, + "learning_rate": 1.000325076840484e-05, + "loss": 0.0134, + "step": 33345 + }, + { + "epoch": 10.3, + "learning_rate": 1.000275065020247e-05, + "loss": 0.0128, + "step": 33346 + }, + { + "epoch": 10.3, + "learning_rate": 1.000225053199322e-05, + "loss": 0.0113, + "step": 33347 + }, + { + "epoch": 10.3, + "learning_rate": 1.0001750413778345e-05, + "loss": 0.014, + "step": 33348 + }, + { + "epoch": 10.3, + "learning_rate": 1.0001250295559086e-05, + "loss": 0.0133, + "step": 33349 + }, + { + "epoch": 10.3, + "learning_rate": 1.0000750177336702e-05, + "loss": 0.0136, + "step": 33350 + }, + { + "epoch": 10.3, + "learning_rate": 1.0000250059112447e-05, + "loss": 0.0153, + "step": 33351 + }, + { + "epoch": 10.3, + "learning_rate": 9.99974994088756e-06, + "loss": 0.0144, + "step": 33352 + }, + { + "epoch": 10.3, + "learning_rate": 9.9992498226633e-06, + "loss": 0.0181, + "step": 33353 + }, + { + "epoch": 10.3, + "learning_rate": 9.998749704440914e-06, + "loss": 0.0144, + "step": 33354 + }, + { + "epoch": 10.3, + "learning_rate": 9.99824958622166e-06, + "loss": 0.0132, + "step": 33355 + }, + { + "epoch": 10.3, + "learning_rate": 9.99774946800678e-06, + "loss": 0.0142, + "step": 33356 + }, + { + "epoch": 10.3, + "learning_rate": 9.99724934979753e-06, + "loss": 0.015, + "step": 33357 + }, + { + "epoch": 10.3, + "learning_rate": 9.996749231595162e-06, + "loss": 0.0131, + "step": 33358 + }, + { + "epoch": 10.3, + "learning_rate": 9.996249113400925e-06, + "loss": 0.0142, + "step": 33359 + }, + { + "epoch": 10.3, + "learning_rate": 9.995748995216065e-06, + "loss": 0.0125, + "step": 33360 + }, + { + "epoch": 10.3, + "learning_rate": 9.995248877041844e-06, + "loss": 0.0158, + "step": 33361 + }, + { + "epoch": 10.3, + "learning_rate": 9.994748758879502e-06, + "loss": 0.0128, + "step": 33362 + }, + { + "epoch": 10.3, + "learning_rate": 9.994248640730293e-06, + "loss": 0.0137, + "step": 33363 + }, + { + "epoch": 10.3, + "learning_rate": 9.993748522595475e-06, + "loss": 0.0147, + "step": 33364 + }, + { + "epoch": 10.3, + "learning_rate": 9.993248404476287e-06, + "loss": 0.0143, + "step": 33365 + }, + { + "epoch": 10.3, + "learning_rate": 9.992748286373989e-06, + "loss": 0.013, + "step": 33366 + }, + { + "epoch": 10.3, + "learning_rate": 9.99224816828983e-06, + "loss": 0.0121, + "step": 33367 + }, + { + "epoch": 10.3, + "learning_rate": 9.991748050225057e-06, + "loss": 0.0133, + "step": 33368 + }, + { + "epoch": 10.31, + "learning_rate": 9.991247932180925e-06, + "loss": 0.0143, + "step": 33369 + }, + { + "epoch": 10.31, + "learning_rate": 9.99074781415868e-06, + "loss": 0.013, + "step": 33370 + }, + { + "epoch": 10.31, + "learning_rate": 9.990247696159584e-06, + "loss": 0.0126, + "step": 33371 + }, + { + "epoch": 10.31, + "learning_rate": 9.989747578184873e-06, + "loss": 0.0124, + "step": 33372 + }, + { + "epoch": 10.31, + "learning_rate": 9.989247460235809e-06, + "loss": 0.0122, + "step": 33373 + }, + { + "epoch": 10.31, + "learning_rate": 9.98874734231364e-06, + "loss": 0.0137, + "step": 33374 + }, + { + "epoch": 10.31, + "learning_rate": 9.988247224419611e-06, + "loss": 0.0137, + "step": 33375 + }, + { + "epoch": 10.31, + "learning_rate": 9.98774710655498e-06, + "loss": 0.0124, + "step": 33376 + }, + { + "epoch": 10.31, + "learning_rate": 9.987246988721001e-06, + "loss": 0.0124, + "step": 33377 + }, + { + "epoch": 10.31, + "learning_rate": 9.986746870918913e-06, + "loss": 0.0159, + "step": 33378 + }, + { + "epoch": 10.31, + "learning_rate": 9.986246753149976e-06, + "loss": 0.0135, + "step": 33379 + }, + { + "epoch": 10.31, + "learning_rate": 9.985746635415439e-06, + "loss": 0.0147, + "step": 33380 + }, + { + "epoch": 10.31, + "learning_rate": 9.98524651771655e-06, + "loss": 0.0125, + "step": 33381 + }, + { + "epoch": 10.31, + "learning_rate": 9.984746400054564e-06, + "loss": 0.0143, + "step": 33382 + }, + { + "epoch": 10.31, + "learning_rate": 9.984246282430732e-06, + "loss": 0.0145, + "step": 33383 + }, + { + "epoch": 10.31, + "learning_rate": 9.9837461648463e-06, + "loss": 0.0147, + "step": 33384 + }, + { + "epoch": 10.31, + "learning_rate": 9.98324604730252e-06, + "loss": 0.0151, + "step": 33385 + }, + { + "epoch": 10.31, + "learning_rate": 9.98274592980065e-06, + "loss": 0.0169, + "step": 33386 + }, + { + "epoch": 10.31, + "learning_rate": 9.982245812341932e-06, + "loss": 0.0116, + "step": 33387 + }, + { + "epoch": 10.31, + "learning_rate": 9.981745694927618e-06, + "loss": 0.0151, + "step": 33388 + }, + { + "epoch": 10.31, + "learning_rate": 9.981245577558968e-06, + "loss": 0.0132, + "step": 33389 + }, + { + "epoch": 10.31, + "learning_rate": 9.980745460237223e-06, + "loss": 0.013, + "step": 33390 + }, + { + "epoch": 10.31, + "learning_rate": 9.980245342963633e-06, + "loss": 0.0118, + "step": 33391 + }, + { + "epoch": 10.31, + "learning_rate": 9.979745225739461e-06, + "loss": 0.0148, + "step": 33392 + }, + { + "epoch": 10.31, + "learning_rate": 9.979245108565943e-06, + "loss": 0.0125, + "step": 33393 + }, + { + "epoch": 10.31, + "learning_rate": 9.97874499144434e-06, + "loss": 0.0124, + "step": 33394 + }, + { + "epoch": 10.31, + "learning_rate": 9.978244874375902e-06, + "loss": 0.0141, + "step": 33395 + }, + { + "epoch": 10.31, + "learning_rate": 9.977744757361872e-06, + "loss": 0.0137, + "step": 33396 + }, + { + "epoch": 10.31, + "learning_rate": 9.977244640403509e-06, + "loss": 0.0133, + "step": 33397 + }, + { + "epoch": 10.31, + "learning_rate": 9.976744523502063e-06, + "loss": 0.0133, + "step": 33398 + }, + { + "epoch": 10.31, + "learning_rate": 9.97624440665878e-06, + "loss": 0.0152, + "step": 33399 + }, + { + "epoch": 10.31, + "learning_rate": 9.975744289874916e-06, + "loss": 0.0147, + "step": 33400 + }, + { + "epoch": 10.31, + "learning_rate": 9.975244173151716e-06, + "loss": 0.0129, + "step": 33401 + }, + { + "epoch": 10.32, + "learning_rate": 9.974744056490445e-06, + "loss": 0.0149, + "step": 33402 + }, + { + "epoch": 10.32, + "learning_rate": 9.974243939892334e-06, + "loss": 0.014, + "step": 33403 + }, + { + "epoch": 10.32, + "learning_rate": 9.973743823358646e-06, + "loss": 0.0139, + "step": 33404 + }, + { + "epoch": 10.32, + "learning_rate": 9.973243706890634e-06, + "loss": 0.0141, + "step": 33405 + }, + { + "epoch": 10.32, + "learning_rate": 9.972743590489537e-06, + "loss": 0.0163, + "step": 33406 + }, + { + "epoch": 10.32, + "learning_rate": 9.972243474156616e-06, + "loss": 0.0139, + "step": 33407 + }, + { + "epoch": 10.32, + "learning_rate": 9.971743357893124e-06, + "loss": 0.0138, + "step": 33408 + }, + { + "epoch": 10.32, + "learning_rate": 9.971243241700299e-06, + "loss": 0.0137, + "step": 33409 + }, + { + "epoch": 10.32, + "learning_rate": 9.970743125579404e-06, + "loss": 0.0142, + "step": 33410 + }, + { + "epoch": 10.32, + "learning_rate": 9.970243009531688e-06, + "loss": 0.0135, + "step": 33411 + }, + { + "epoch": 10.32, + "learning_rate": 9.969742893558397e-06, + "loss": 0.0136, + "step": 33412 + }, + { + "epoch": 10.32, + "learning_rate": 9.969242777660784e-06, + "loss": 0.0151, + "step": 33413 + }, + { + "epoch": 10.32, + "learning_rate": 9.968742661840103e-06, + "loss": 0.014, + "step": 33414 + }, + { + "epoch": 10.32, + "learning_rate": 9.9682425460976e-06, + "loss": 0.0135, + "step": 33415 + }, + { + "epoch": 10.32, + "learning_rate": 9.967742430434526e-06, + "loss": 0.0117, + "step": 33416 + }, + { + "epoch": 10.32, + "learning_rate": 9.96724231485214e-06, + "loss": 0.0148, + "step": 33417 + }, + { + "epoch": 10.32, + "learning_rate": 9.966742199351683e-06, + "loss": 0.0131, + "step": 33418 + }, + { + "epoch": 10.32, + "learning_rate": 9.966242083934408e-06, + "loss": 0.0159, + "step": 33419 + }, + { + "epoch": 10.32, + "learning_rate": 9.965741968601573e-06, + "loss": 0.0138, + "step": 33420 + }, + { + "epoch": 10.32, + "learning_rate": 9.965241853354421e-06, + "loss": 0.0133, + "step": 33421 + }, + { + "epoch": 10.32, + "learning_rate": 9.964741738194206e-06, + "loss": 0.0133, + "step": 33422 + }, + { + "epoch": 10.32, + "learning_rate": 9.964241623122179e-06, + "loss": 0.0143, + "step": 33423 + }, + { + "epoch": 10.32, + "learning_rate": 9.963741508139588e-06, + "loss": 0.0123, + "step": 33424 + }, + { + "epoch": 10.32, + "learning_rate": 9.963241393247685e-06, + "loss": 0.0154, + "step": 33425 + }, + { + "epoch": 10.32, + "learning_rate": 9.962741278447727e-06, + "loss": 0.0134, + "step": 33426 + }, + { + "epoch": 10.32, + "learning_rate": 9.962241163740955e-06, + "loss": 0.0119, + "step": 33427 + }, + { + "epoch": 10.32, + "learning_rate": 9.961741049128626e-06, + "loss": 0.0145, + "step": 33428 + }, + { + "epoch": 10.32, + "learning_rate": 9.961240934611993e-06, + "loss": 0.0121, + "step": 33429 + }, + { + "epoch": 10.32, + "learning_rate": 9.960740820192298e-06, + "loss": 0.0132, + "step": 33430 + }, + { + "epoch": 10.32, + "learning_rate": 9.960240705870801e-06, + "loss": 0.0145, + "step": 33431 + }, + { + "epoch": 10.32, + "learning_rate": 9.95974059164875e-06, + "loss": 0.0143, + "step": 33432 + }, + { + "epoch": 10.32, + "learning_rate": 9.959240477527393e-06, + "loss": 0.0157, + "step": 33433 + }, + { + "epoch": 10.33, + "learning_rate": 9.958740363507982e-06, + "loss": 0.0122, + "step": 33434 + }, + { + "epoch": 10.33, + "learning_rate": 9.95824024959177e-06, + "loss": 0.0131, + "step": 33435 + }, + { + "epoch": 10.33, + "learning_rate": 9.957740135780009e-06, + "loss": 0.0139, + "step": 33436 + }, + { + "epoch": 10.33, + "learning_rate": 9.957240022073942e-06, + "loss": 0.0146, + "step": 33437 + }, + { + "epoch": 10.33, + "learning_rate": 9.95673990847483e-06, + "loss": 0.013, + "step": 33438 + }, + { + "epoch": 10.33, + "learning_rate": 9.956239794983923e-06, + "loss": 0.0126, + "step": 33439 + }, + { + "epoch": 10.33, + "learning_rate": 9.95573968160246e-06, + "loss": 0.0142, + "step": 33440 + }, + { + "epoch": 10.33, + "learning_rate": 9.955239568331704e-06, + "loss": 0.0155, + "step": 33441 + }, + { + "epoch": 10.33, + "learning_rate": 9.954739455172903e-06, + "loss": 0.0131, + "step": 33442 + }, + { + "epoch": 10.33, + "learning_rate": 9.954239342127306e-06, + "loss": 0.0134, + "step": 33443 + }, + { + "epoch": 10.33, + "learning_rate": 9.953739229196163e-06, + "loss": 0.0131, + "step": 33444 + }, + { + "epoch": 10.33, + "learning_rate": 9.953239116380731e-06, + "loss": 0.0146, + "step": 33445 + }, + { + "epoch": 10.33, + "learning_rate": 9.952739003682254e-06, + "loss": 0.015, + "step": 33446 + }, + { + "epoch": 10.33, + "learning_rate": 9.952238891101981e-06, + "loss": 0.0122, + "step": 33447 + }, + { + "epoch": 10.33, + "learning_rate": 9.951738778641175e-06, + "loss": 0.0146, + "step": 33448 + }, + { + "epoch": 10.33, + "learning_rate": 9.951238666301074e-06, + "loss": 0.0147, + "step": 33449 + }, + { + "epoch": 10.33, + "learning_rate": 9.950738554082933e-06, + "loss": 0.0139, + "step": 33450 + }, + { + "epoch": 10.33, + "learning_rate": 9.950238441988011e-06, + "loss": 0.0141, + "step": 33451 + }, + { + "epoch": 10.33, + "learning_rate": 9.949738330017546e-06, + "loss": 0.0144, + "step": 33452 + }, + { + "epoch": 10.33, + "learning_rate": 9.949238218172795e-06, + "loss": 0.0145, + "step": 33453 + }, + { + "epoch": 10.33, + "learning_rate": 9.948738106455012e-06, + "loss": 0.0139, + "step": 33454 + }, + { + "epoch": 10.33, + "learning_rate": 9.948237994865438e-06, + "loss": 0.0123, + "step": 33455 + }, + { + "epoch": 10.33, + "learning_rate": 9.947737883405334e-06, + "loss": 0.0142, + "step": 33456 + }, + { + "epoch": 10.33, + "learning_rate": 9.947237772075949e-06, + "loss": 0.0138, + "step": 33457 + }, + { + "epoch": 10.33, + "learning_rate": 9.946737660878528e-06, + "loss": 0.0134, + "step": 33458 + }, + { + "epoch": 10.33, + "learning_rate": 9.946237549814327e-06, + "loss": 0.012, + "step": 33459 + }, + { + "epoch": 10.33, + "learning_rate": 9.945737438884599e-06, + "loss": 0.0113, + "step": 33460 + }, + { + "epoch": 10.33, + "learning_rate": 9.94523732809059e-06, + "loss": 0.0137, + "step": 33461 + }, + { + "epoch": 10.33, + "learning_rate": 9.944737217433548e-06, + "loss": 0.0144, + "step": 33462 + }, + { + "epoch": 10.33, + "learning_rate": 9.944237106914733e-06, + "loss": 0.012, + "step": 33463 + }, + { + "epoch": 10.33, + "learning_rate": 9.94373699653539e-06, + "loss": 0.0133, + "step": 33464 + }, + { + "epoch": 10.33, + "learning_rate": 9.943236886296768e-06, + "loss": 0.013, + "step": 33465 + }, + { + "epoch": 10.33, + "learning_rate": 9.942736776200126e-06, + "loss": 0.0133, + "step": 33466 + }, + { + "epoch": 10.34, + "learning_rate": 9.942236666246707e-06, + "loss": 0.0154, + "step": 33467 + }, + { + "epoch": 10.34, + "learning_rate": 9.941736556437763e-06, + "loss": 0.0156, + "step": 33468 + }, + { + "epoch": 10.34, + "learning_rate": 9.941236446774549e-06, + "loss": 0.0134, + "step": 33469 + }, + { + "epoch": 10.34, + "learning_rate": 9.940736337258316e-06, + "loss": 0.0134, + "step": 33470 + }, + { + "epoch": 10.34, + "learning_rate": 9.940236227890308e-06, + "loss": 0.0151, + "step": 33471 + }, + { + "epoch": 10.34, + "learning_rate": 9.939736118671778e-06, + "loss": 0.0145, + "step": 33472 + }, + { + "epoch": 10.34, + "learning_rate": 9.939236009603985e-06, + "loss": 0.0145, + "step": 33473 + }, + { + "epoch": 10.34, + "learning_rate": 9.93873590068817e-06, + "loss": 0.0113, + "step": 33474 + }, + { + "epoch": 10.34, + "learning_rate": 9.938235791925588e-06, + "loss": 0.0147, + "step": 33475 + }, + { + "epoch": 10.34, + "learning_rate": 9.937735683317491e-06, + "loss": 0.015, + "step": 33476 + }, + { + "epoch": 10.34, + "learning_rate": 9.937235574865128e-06, + "loss": 0.0147, + "step": 33477 + }, + { + "epoch": 10.34, + "learning_rate": 9.936735466569747e-06, + "loss": 0.015, + "step": 33478 + }, + { + "epoch": 10.34, + "learning_rate": 9.936235358432609e-06, + "loss": 0.0155, + "step": 33479 + }, + { + "epoch": 10.34, + "learning_rate": 9.935735250454953e-06, + "loss": 0.0158, + "step": 33480 + }, + { + "epoch": 10.34, + "learning_rate": 9.935235142638036e-06, + "loss": 0.0135, + "step": 33481 + }, + { + "epoch": 10.34, + "learning_rate": 9.93473503498311e-06, + "loss": 0.0158, + "step": 33482 + }, + { + "epoch": 10.34, + "learning_rate": 9.93423492749142e-06, + "loss": 0.0133, + "step": 33483 + }, + { + "epoch": 10.34, + "learning_rate": 9.933734820164221e-06, + "loss": 0.0121, + "step": 33484 + }, + { + "epoch": 10.34, + "learning_rate": 9.933234713002766e-06, + "loss": 0.012, + "step": 33485 + }, + { + "epoch": 10.34, + "learning_rate": 9.932734606008298e-06, + "loss": 0.0138, + "step": 33486 + }, + { + "epoch": 10.34, + "learning_rate": 9.932234499182077e-06, + "loss": 0.0143, + "step": 33487 + }, + { + "epoch": 10.34, + "learning_rate": 9.931734392525352e-06, + "loss": 0.0144, + "step": 33488 + }, + { + "epoch": 10.34, + "learning_rate": 9.931234286039366e-06, + "loss": 0.0118, + "step": 33489 + }, + { + "epoch": 10.34, + "learning_rate": 9.930734179725378e-06, + "loss": 0.0128, + "step": 33490 + }, + { + "epoch": 10.34, + "learning_rate": 9.930234073584639e-06, + "loss": 0.0141, + "step": 33491 + }, + { + "epoch": 10.34, + "learning_rate": 9.929733967618395e-06, + "loss": 0.0144, + "step": 33492 + }, + { + "epoch": 10.34, + "learning_rate": 9.929233861827897e-06, + "loss": 0.0135, + "step": 33493 + }, + { + "epoch": 10.34, + "learning_rate": 9.928733756214402e-06, + "loss": 0.0154, + "step": 33494 + }, + { + "epoch": 10.34, + "learning_rate": 9.928233650779155e-06, + "loss": 0.0124, + "step": 33495 + }, + { + "epoch": 10.34, + "learning_rate": 9.927733545523408e-06, + "loss": 0.0142, + "step": 33496 + }, + { + "epoch": 10.34, + "learning_rate": 9.927233440448416e-06, + "loss": 0.0136, + "step": 33497 + }, + { + "epoch": 10.34, + "learning_rate": 9.926733335555424e-06, + "loss": 0.0134, + "step": 33498 + }, + { + "epoch": 10.35, + "learning_rate": 9.926233230845682e-06, + "loss": 0.0137, + "step": 33499 + }, + { + "epoch": 10.35, + "learning_rate": 9.925733126320447e-06, + "loss": 0.012, + "step": 33500 + }, + { + "epoch": 10.35, + "learning_rate": 9.92523302198097e-06, + "loss": 0.0147, + "step": 33501 + }, + { + "epoch": 10.35, + "learning_rate": 9.924732917828496e-06, + "loss": 0.0144, + "step": 33502 + }, + { + "epoch": 10.35, + "learning_rate": 9.924232813864277e-06, + "loss": 0.0157, + "step": 33503 + }, + { + "epoch": 10.35, + "learning_rate": 9.923732710089568e-06, + "loss": 0.0129, + "step": 33504 + }, + { + "epoch": 10.35, + "learning_rate": 9.923232606505619e-06, + "loss": 0.0133, + "step": 33505 + }, + { + "epoch": 10.35, + "learning_rate": 9.922732503113674e-06, + "loss": 0.0132, + "step": 33506 + }, + { + "epoch": 10.35, + "learning_rate": 9.922232399914994e-06, + "loss": 0.0152, + "step": 33507 + }, + { + "epoch": 10.35, + "learning_rate": 9.921732296910823e-06, + "loss": 0.0135, + "step": 33508 + }, + { + "epoch": 10.35, + "learning_rate": 9.921232194102411e-06, + "loss": 0.0115, + "step": 33509 + }, + { + "epoch": 10.35, + "learning_rate": 9.92073209149102e-06, + "loss": 0.0144, + "step": 33510 + }, + { + "epoch": 10.35, + "learning_rate": 9.920231989077884e-06, + "loss": 0.0141, + "step": 33511 + }, + { + "epoch": 10.35, + "learning_rate": 9.919731886864266e-06, + "loss": 0.0127, + "step": 33512 + }, + { + "epoch": 10.35, + "learning_rate": 9.919231784851415e-06, + "loss": 0.0155, + "step": 33513 + }, + { + "epoch": 10.35, + "learning_rate": 9.918731683040576e-06, + "loss": 0.0127, + "step": 33514 + }, + { + "epoch": 10.35, + "learning_rate": 9.918231581433004e-06, + "loss": 0.0151, + "step": 33515 + }, + { + "epoch": 10.35, + "learning_rate": 9.917731480029954e-06, + "loss": 0.012, + "step": 33516 + }, + { + "epoch": 10.35, + "learning_rate": 9.917231378832669e-06, + "loss": 0.0151, + "step": 33517 + }, + { + "epoch": 10.35, + "learning_rate": 9.916731277842403e-06, + "loss": 0.0134, + "step": 33518 + }, + { + "epoch": 10.35, + "learning_rate": 9.91623117706041e-06, + "loss": 0.0135, + "step": 33519 + }, + { + "epoch": 10.35, + "learning_rate": 9.915731076487938e-06, + "loss": 0.0135, + "step": 33520 + }, + { + "epoch": 10.35, + "learning_rate": 9.915230976126233e-06, + "loss": 0.013, + "step": 33521 + }, + { + "epoch": 10.35, + "learning_rate": 9.914730875976557e-06, + "loss": 0.0137, + "step": 33522 + }, + { + "epoch": 10.35, + "learning_rate": 9.914230776040152e-06, + "loss": 0.014, + "step": 33523 + }, + { + "epoch": 10.35, + "learning_rate": 9.91373067631827e-06, + "loss": 0.0144, + "step": 33524 + }, + { + "epoch": 10.35, + "learning_rate": 9.913230576812167e-06, + "loss": 0.0135, + "step": 33525 + }, + { + "epoch": 10.35, + "learning_rate": 9.912730477523087e-06, + "loss": 0.0146, + "step": 33526 + }, + { + "epoch": 10.35, + "learning_rate": 9.912230378452283e-06, + "loss": 0.0135, + "step": 33527 + }, + { + "epoch": 10.35, + "learning_rate": 9.911730279601011e-06, + "loss": 0.014, + "step": 33528 + }, + { + "epoch": 10.35, + "learning_rate": 9.911230180970515e-06, + "loss": 0.0138, + "step": 33529 + }, + { + "epoch": 10.35, + "learning_rate": 9.910730082562048e-06, + "loss": 0.0136, + "step": 33530 + }, + { + "epoch": 10.36, + "learning_rate": 9.910229984376866e-06, + "loss": 0.012, + "step": 33531 + }, + { + "epoch": 10.36, + "learning_rate": 9.909729886416209e-06, + "loss": 0.0142, + "step": 33532 + }, + { + "epoch": 10.36, + "learning_rate": 9.909229788681336e-06, + "loss": 0.0137, + "step": 33533 + }, + { + "epoch": 10.36, + "learning_rate": 9.908729691173494e-06, + "loss": 0.0135, + "step": 33534 + }, + { + "epoch": 10.36, + "learning_rate": 9.908229593893941e-06, + "loss": 0.013, + "step": 33535 + }, + { + "epoch": 10.36, + "learning_rate": 9.90772949684392e-06, + "loss": 0.0131, + "step": 33536 + }, + { + "epoch": 10.36, + "learning_rate": 9.90722940002468e-06, + "loss": 0.0143, + "step": 33537 + }, + { + "epoch": 10.36, + "learning_rate": 9.906729303437484e-06, + "loss": 0.0114, + "step": 33538 + }, + { + "epoch": 10.36, + "learning_rate": 9.90622920708357e-06, + "loss": 0.0127, + "step": 33539 + }, + { + "epoch": 10.36, + "learning_rate": 9.905729110964194e-06, + "loss": 0.0129, + "step": 33540 + }, + { + "epoch": 10.36, + "learning_rate": 9.90522901508061e-06, + "loss": 0.0144, + "step": 33541 + }, + { + "epoch": 10.36, + "learning_rate": 9.904728919434063e-06, + "loss": 0.0129, + "step": 33542 + }, + { + "epoch": 10.36, + "learning_rate": 9.904228824025805e-06, + "loss": 0.0131, + "step": 33543 + }, + { + "epoch": 10.36, + "learning_rate": 9.903728728857092e-06, + "loss": 0.0147, + "step": 33544 + }, + { + "epoch": 10.36, + "learning_rate": 9.903228633929167e-06, + "loss": 0.0138, + "step": 33545 + }, + { + "epoch": 10.36, + "learning_rate": 9.902728539243286e-06, + "loss": 0.0156, + "step": 33546 + }, + { + "epoch": 10.36, + "learning_rate": 9.902228444800702e-06, + "loss": 0.0161, + "step": 33547 + }, + { + "epoch": 10.36, + "learning_rate": 9.901728350602658e-06, + "loss": 0.0151, + "step": 33548 + }, + { + "epoch": 10.36, + "learning_rate": 9.90122825665041e-06, + "loss": 0.0122, + "step": 33549 + }, + { + "epoch": 10.36, + "learning_rate": 9.900728162945212e-06, + "loss": 0.0129, + "step": 33550 + }, + { + "epoch": 10.36, + "learning_rate": 9.900228069488308e-06, + "loss": 0.0159, + "step": 33551 + }, + { + "epoch": 10.36, + "learning_rate": 9.899727976280949e-06, + "loss": 0.013, + "step": 33552 + }, + { + "epoch": 10.36, + "learning_rate": 9.899227883324395e-06, + "loss": 0.0136, + "step": 33553 + }, + { + "epoch": 10.36, + "learning_rate": 9.898727790619887e-06, + "loss": 0.0143, + "step": 33554 + }, + { + "epoch": 10.36, + "learning_rate": 9.898227698168677e-06, + "loss": 0.0136, + "step": 33555 + }, + { + "epoch": 10.36, + "learning_rate": 9.897727605972021e-06, + "loss": 0.0116, + "step": 33556 + }, + { + "epoch": 10.36, + "learning_rate": 9.897227514031166e-06, + "loss": 0.0139, + "step": 33557 + }, + { + "epoch": 10.36, + "learning_rate": 9.896727422347363e-06, + "loss": 0.0126, + "step": 33558 + }, + { + "epoch": 10.36, + "learning_rate": 9.896227330921868e-06, + "loss": 0.0136, + "step": 33559 + }, + { + "epoch": 10.36, + "learning_rate": 9.895727239755923e-06, + "loss": 0.0144, + "step": 33560 + }, + { + "epoch": 10.36, + "learning_rate": 9.895227148850784e-06, + "loss": 0.0127, + "step": 33561 + }, + { + "epoch": 10.36, + "learning_rate": 9.894727058207702e-06, + "loss": 0.0145, + "step": 33562 + }, + { + "epoch": 10.36, + "learning_rate": 9.894226967827925e-06, + "loss": 0.0143, + "step": 33563 + }, + { + "epoch": 10.37, + "learning_rate": 9.893726877712705e-06, + "loss": 0.0146, + "step": 33564 + }, + { + "epoch": 10.37, + "learning_rate": 9.893226787863293e-06, + "loss": 0.0123, + "step": 33565 + }, + { + "epoch": 10.37, + "learning_rate": 9.892726698280945e-06, + "loss": 0.0155, + "step": 33566 + }, + { + "epoch": 10.37, + "learning_rate": 9.892226608966905e-06, + "loss": 0.015, + "step": 33567 + }, + { + "epoch": 10.37, + "learning_rate": 9.891726519922423e-06, + "loss": 0.0112, + "step": 33568 + }, + { + "epoch": 10.37, + "learning_rate": 9.89122643114876e-06, + "loss": 0.015, + "step": 33569 + }, + { + "epoch": 10.37, + "learning_rate": 9.890726342647151e-06, + "loss": 0.0143, + "step": 33570 + }, + { + "epoch": 10.37, + "learning_rate": 9.89022625441886e-06, + "loss": 0.0141, + "step": 33571 + }, + { + "epoch": 10.37, + "learning_rate": 9.889726166465133e-06, + "loss": 0.0121, + "step": 33572 + }, + { + "epoch": 10.37, + "learning_rate": 9.889226078787218e-06, + "loss": 0.0145, + "step": 33573 + }, + { + "epoch": 10.37, + "learning_rate": 9.888725991386371e-06, + "loss": 0.0126, + "step": 33574 + }, + { + "epoch": 10.37, + "learning_rate": 9.888225904263843e-06, + "loss": 0.0125, + "step": 33575 + }, + { + "epoch": 10.37, + "learning_rate": 9.887725817420877e-06, + "loss": 0.0124, + "step": 33576 + }, + { + "epoch": 10.37, + "learning_rate": 9.887225730858732e-06, + "loss": 0.0137, + "step": 33577 + }, + { + "epoch": 10.37, + "learning_rate": 9.886725644578659e-06, + "loss": 0.0159, + "step": 33578 + }, + { + "epoch": 10.37, + "learning_rate": 9.886225558581903e-06, + "loss": 0.0133, + "step": 33579 + }, + { + "epoch": 10.37, + "learning_rate": 9.885725472869715e-06, + "loss": 0.0143, + "step": 33580 + }, + { + "epoch": 10.37, + "learning_rate": 9.885225387443353e-06, + "loss": 0.0147, + "step": 33581 + }, + { + "epoch": 10.37, + "learning_rate": 9.884725302304062e-06, + "loss": 0.0129, + "step": 33582 + }, + { + "epoch": 10.37, + "learning_rate": 9.884225217453091e-06, + "loss": 0.0125, + "step": 33583 + }, + { + "epoch": 10.37, + "learning_rate": 9.883725132891699e-06, + "loss": 0.0129, + "step": 33584 + }, + { + "epoch": 10.37, + "learning_rate": 9.883225048621128e-06, + "loss": 0.0156, + "step": 33585 + }, + { + "epoch": 10.37, + "learning_rate": 9.88272496464263e-06, + "loss": 0.0124, + "step": 33586 + }, + { + "epoch": 10.37, + "learning_rate": 9.882224880957465e-06, + "loss": 0.0133, + "step": 33587 + }, + { + "epoch": 10.37, + "learning_rate": 9.881724797566873e-06, + "loss": 0.013, + "step": 33588 + }, + { + "epoch": 10.37, + "learning_rate": 9.881224714472108e-06, + "loss": 0.0143, + "step": 33589 + }, + { + "epoch": 10.37, + "learning_rate": 9.880724631674426e-06, + "loss": 0.0143, + "step": 33590 + }, + { + "epoch": 10.37, + "learning_rate": 9.880224549175068e-06, + "loss": 0.0129, + "step": 33591 + }, + { + "epoch": 10.37, + "learning_rate": 9.879724466975293e-06, + "loss": 0.0172, + "step": 33592 + }, + { + "epoch": 10.37, + "learning_rate": 9.87922438507635e-06, + "loss": 0.015, + "step": 33593 + }, + { + "epoch": 10.37, + "learning_rate": 9.878724303479487e-06, + "loss": 0.0132, + "step": 33594 + }, + { + "epoch": 10.37, + "learning_rate": 9.878224222185956e-06, + "loss": 0.0134, + "step": 33595 + }, + { + "epoch": 10.38, + "learning_rate": 9.877724141197012e-06, + "loss": 0.0148, + "step": 33596 + }, + { + "epoch": 10.38, + "learning_rate": 9.877224060513899e-06, + "loss": 0.0142, + "step": 33597 + }, + { + "epoch": 10.38, + "learning_rate": 9.87672398013787e-06, + "loss": 0.0122, + "step": 33598 + }, + { + "epoch": 10.38, + "learning_rate": 9.876223900070178e-06, + "loss": 0.0128, + "step": 33599 + }, + { + "epoch": 10.38, + "learning_rate": 9.875723820312077e-06, + "loss": 0.0144, + "step": 33600 + }, + { + "epoch": 10.38, + "learning_rate": 9.875223740864807e-06, + "loss": 0.0147, + "step": 33601 + }, + { + "epoch": 10.38, + "learning_rate": 9.874723661729628e-06, + "loss": 0.0146, + "step": 33602 + }, + { + "epoch": 10.38, + "learning_rate": 9.87422358290779e-06, + "loss": 0.0133, + "step": 33603 + }, + { + "epoch": 10.38, + "learning_rate": 9.873723504400537e-06, + "loss": 0.0131, + "step": 33604 + }, + { + "epoch": 10.38, + "learning_rate": 9.873223426209127e-06, + "loss": 0.0128, + "step": 33605 + }, + { + "epoch": 10.38, + "learning_rate": 9.872723348334811e-06, + "loss": 0.0129, + "step": 33606 + }, + { + "epoch": 10.38, + "learning_rate": 9.872223270778832e-06, + "loss": 0.0129, + "step": 33607 + }, + { + "epoch": 10.38, + "learning_rate": 9.87172319354245e-06, + "loss": 0.0139, + "step": 33608 + }, + { + "epoch": 10.38, + "learning_rate": 9.871223116626912e-06, + "loss": 0.0138, + "step": 33609 + }, + { + "epoch": 10.38, + "learning_rate": 9.870723040033467e-06, + "loss": 0.0148, + "step": 33610 + }, + { + "epoch": 10.38, + "learning_rate": 9.870222963763363e-06, + "loss": 0.0117, + "step": 33611 + }, + { + "epoch": 10.38, + "learning_rate": 9.869722887817861e-06, + "loss": 0.0145, + "step": 33612 + }, + { + "epoch": 10.38, + "learning_rate": 9.869222812198204e-06, + "loss": 0.0146, + "step": 33613 + }, + { + "epoch": 10.38, + "learning_rate": 9.868722736905643e-06, + "loss": 0.0128, + "step": 33614 + }, + { + "epoch": 10.38, + "learning_rate": 9.868222661941435e-06, + "loss": 0.0139, + "step": 33615 + }, + { + "epoch": 10.38, + "learning_rate": 9.867722587306822e-06, + "loss": 0.0147, + "step": 33616 + }, + { + "epoch": 10.38, + "learning_rate": 9.867222513003058e-06, + "loss": 0.0164, + "step": 33617 + }, + { + "epoch": 10.38, + "learning_rate": 9.866722439031402e-06, + "loss": 0.0132, + "step": 33618 + }, + { + "epoch": 10.38, + "learning_rate": 9.866222365393087e-06, + "loss": 0.0121, + "step": 33619 + }, + { + "epoch": 10.38, + "learning_rate": 9.86572229208938e-06, + "loss": 0.0117, + "step": 33620 + }, + { + "epoch": 10.38, + "learning_rate": 9.865222219121528e-06, + "loss": 0.014, + "step": 33621 + }, + { + "epoch": 10.38, + "learning_rate": 9.864722146490775e-06, + "loss": 0.0132, + "step": 33622 + }, + { + "epoch": 10.38, + "learning_rate": 9.864222074198378e-06, + "loss": 0.0122, + "step": 33623 + }, + { + "epoch": 10.38, + "learning_rate": 9.86372200224559e-06, + "loss": 0.0125, + "step": 33624 + }, + { + "epoch": 10.38, + "learning_rate": 9.863221930633652e-06, + "loss": 0.0134, + "step": 33625 + }, + { + "epoch": 10.38, + "learning_rate": 9.862721859363825e-06, + "loss": 0.0142, + "step": 33626 + }, + { + "epoch": 10.38, + "learning_rate": 9.862221788437357e-06, + "loss": 0.0131, + "step": 33627 + }, + { + "epoch": 10.38, + "learning_rate": 9.861721717855496e-06, + "loss": 0.0125, + "step": 33628 + }, + { + "epoch": 10.39, + "learning_rate": 9.861221647619491e-06, + "loss": 0.0131, + "step": 33629 + }, + { + "epoch": 10.39, + "learning_rate": 9.860721577730598e-06, + "loss": 0.0132, + "step": 33630 + }, + { + "epoch": 10.39, + "learning_rate": 9.860221508190068e-06, + "loss": 0.0109, + "step": 33631 + }, + { + "epoch": 10.39, + "learning_rate": 9.859721438999146e-06, + "loss": 0.0159, + "step": 33632 + }, + { + "epoch": 10.39, + "learning_rate": 9.859221370159088e-06, + "loss": 0.0148, + "step": 33633 + }, + { + "epoch": 10.39, + "learning_rate": 9.858721301671145e-06, + "loss": 0.0165, + "step": 33634 + }, + { + "epoch": 10.39, + "learning_rate": 9.85822123353656e-06, + "loss": 0.012, + "step": 33635 + }, + { + "epoch": 10.39, + "learning_rate": 9.857721165756594e-06, + "loss": 0.0143, + "step": 33636 + }, + { + "epoch": 10.39, + "learning_rate": 9.857221098332496e-06, + "loss": 0.0137, + "step": 33637 + }, + { + "epoch": 10.39, + "learning_rate": 9.856721031265508e-06, + "loss": 0.0122, + "step": 33638 + }, + { + "epoch": 10.39, + "learning_rate": 9.85622096455689e-06, + "loss": 0.0131, + "step": 33639 + }, + { + "epoch": 10.39, + "learning_rate": 9.85572089820789e-06, + "loss": 0.0134, + "step": 33640 + }, + { + "epoch": 10.39, + "learning_rate": 9.855220832219759e-06, + "loss": 0.0143, + "step": 33641 + }, + { + "epoch": 10.39, + "learning_rate": 9.854720766593742e-06, + "loss": 0.013, + "step": 33642 + }, + { + "epoch": 10.39, + "learning_rate": 9.854220701331101e-06, + "loss": 0.0154, + "step": 33643 + }, + { + "epoch": 10.39, + "learning_rate": 9.853720636433079e-06, + "loss": 0.0146, + "step": 33644 + }, + { + "epoch": 10.39, + "learning_rate": 9.853220571900924e-06, + "loss": 0.0147, + "step": 33645 + }, + { + "epoch": 10.39, + "learning_rate": 9.852720507735897e-06, + "loss": 0.0178, + "step": 33646 + }, + { + "epoch": 10.39, + "learning_rate": 9.85222044393924e-06, + "loss": 0.0136, + "step": 33647 + }, + { + "epoch": 10.39, + "learning_rate": 9.851720380512205e-06, + "loss": 0.015, + "step": 33648 + }, + { + "epoch": 10.39, + "learning_rate": 9.85122031745605e-06, + "loss": 0.0134, + "step": 33649 + }, + { + "epoch": 10.39, + "learning_rate": 9.850720254772015e-06, + "loss": 0.016, + "step": 33650 + }, + { + "epoch": 10.39, + "learning_rate": 9.850220192461357e-06, + "loss": 0.014, + "step": 33651 + }, + { + "epoch": 10.39, + "learning_rate": 9.849720130525329e-06, + "loss": 0.0141, + "step": 33652 + }, + { + "epoch": 10.39, + "learning_rate": 9.849220068965174e-06, + "loss": 0.015, + "step": 33653 + }, + { + "epoch": 10.39, + "learning_rate": 9.848720007782148e-06, + "loss": 0.0142, + "step": 33654 + }, + { + "epoch": 10.39, + "learning_rate": 9.848219946977502e-06, + "loss": 0.0161, + "step": 33655 + }, + { + "epoch": 10.39, + "learning_rate": 9.847719886552483e-06, + "loss": 0.0138, + "step": 33656 + }, + { + "epoch": 10.39, + "learning_rate": 9.847219826508346e-06, + "loss": 0.0153, + "step": 33657 + }, + { + "epoch": 10.39, + "learning_rate": 9.846719766846343e-06, + "loss": 0.0165, + "step": 33658 + }, + { + "epoch": 10.39, + "learning_rate": 9.84621970756772e-06, + "loss": 0.0171, + "step": 33659 + }, + { + "epoch": 10.39, + "learning_rate": 9.845719648673726e-06, + "loss": 0.0142, + "step": 33660 + }, + { + "epoch": 10.4, + "learning_rate": 9.84521959016562e-06, + "loss": 0.0146, + "step": 33661 + }, + { + "epoch": 10.4, + "learning_rate": 9.844719532044646e-06, + "loss": 0.0147, + "step": 33662 + }, + { + "epoch": 10.4, + "learning_rate": 9.844219474312055e-06, + "loss": 0.0132, + "step": 33663 + }, + { + "epoch": 10.4, + "learning_rate": 9.843719416969101e-06, + "loss": 0.0132, + "step": 33664 + }, + { + "epoch": 10.4, + "learning_rate": 9.843219360017036e-06, + "loss": 0.0141, + "step": 33665 + }, + { + "epoch": 10.4, + "learning_rate": 9.842719303457104e-06, + "loss": 0.015, + "step": 33666 + }, + { + "epoch": 10.4, + "learning_rate": 9.84221924729056e-06, + "loss": 0.0129, + "step": 33667 + }, + { + "epoch": 10.4, + "learning_rate": 9.841719191518659e-06, + "loss": 0.0149, + "step": 33668 + }, + { + "epoch": 10.4, + "learning_rate": 9.841219136142644e-06, + "loss": 0.0153, + "step": 33669 + }, + { + "epoch": 10.4, + "learning_rate": 9.840719081163765e-06, + "loss": 0.0159, + "step": 33670 + }, + { + "epoch": 10.4, + "learning_rate": 9.840219026583283e-06, + "loss": 0.0148, + "step": 33671 + }, + { + "epoch": 10.4, + "learning_rate": 9.83971897240244e-06, + "loss": 0.013, + "step": 33672 + }, + { + "epoch": 10.4, + "learning_rate": 9.839218918622486e-06, + "loss": 0.0138, + "step": 33673 + }, + { + "epoch": 10.4, + "learning_rate": 9.83871886524468e-06, + "loss": 0.0142, + "step": 33674 + }, + { + "epoch": 10.4, + "learning_rate": 9.838218812270265e-06, + "loss": 0.014, + "step": 33675 + }, + { + "epoch": 10.4, + "learning_rate": 9.837718759700493e-06, + "loss": 0.0143, + "step": 33676 + }, + { + "epoch": 10.4, + "learning_rate": 9.837218707536618e-06, + "loss": 0.0131, + "step": 33677 + }, + { + "epoch": 10.4, + "learning_rate": 9.836718655779888e-06, + "loss": 0.0129, + "step": 33678 + }, + { + "epoch": 10.4, + "learning_rate": 9.836218604431556e-06, + "loss": 0.014, + "step": 33679 + }, + { + "epoch": 10.4, + "learning_rate": 9.835718553492872e-06, + "loss": 0.016, + "step": 33680 + }, + { + "epoch": 10.4, + "learning_rate": 9.83521850296508e-06, + "loss": 0.0147, + "step": 33681 + }, + { + "epoch": 10.4, + "learning_rate": 9.834718452849442e-06, + "loss": 0.0135, + "step": 33682 + }, + { + "epoch": 10.4, + "learning_rate": 9.834218403147202e-06, + "loss": 0.0176, + "step": 33683 + }, + { + "epoch": 10.4, + "learning_rate": 9.83371835385961e-06, + "loss": 0.0157, + "step": 33684 + }, + { + "epoch": 10.4, + "learning_rate": 9.83321830498792e-06, + "loss": 0.0138, + "step": 33685 + }, + { + "epoch": 10.4, + "learning_rate": 9.832718256533383e-06, + "loss": 0.013, + "step": 33686 + }, + { + "epoch": 10.4, + "learning_rate": 9.832218208497244e-06, + "loss": 0.0147, + "step": 33687 + }, + { + "epoch": 10.4, + "learning_rate": 9.831718160880763e-06, + "loss": 0.0185, + "step": 33688 + }, + { + "epoch": 10.4, + "learning_rate": 9.831218113685184e-06, + "loss": 0.0128, + "step": 33689 + }, + { + "epoch": 10.4, + "learning_rate": 9.830718066911759e-06, + "loss": 0.0128, + "step": 33690 + }, + { + "epoch": 10.4, + "learning_rate": 9.830218020561735e-06, + "loss": 0.0158, + "step": 33691 + }, + { + "epoch": 10.4, + "learning_rate": 9.829717974636374e-06, + "loss": 0.016, + "step": 33692 + }, + { + "epoch": 10.41, + "learning_rate": 9.829217929136915e-06, + "loss": 0.0141, + "step": 33693 + }, + { + "epoch": 10.41, + "learning_rate": 9.828717884064612e-06, + "loss": 0.015, + "step": 33694 + }, + { + "epoch": 10.41, + "learning_rate": 9.82821783942072e-06, + "loss": 0.0135, + "step": 33695 + }, + { + "epoch": 10.41, + "learning_rate": 9.827717795206485e-06, + "loss": 0.0132, + "step": 33696 + }, + { + "epoch": 10.41, + "learning_rate": 9.827217751423158e-06, + "loss": 0.014, + "step": 33697 + }, + { + "epoch": 10.41, + "learning_rate": 9.826717708071992e-06, + "loss": 0.016, + "step": 33698 + }, + { + "epoch": 10.41, + "learning_rate": 9.826217665154237e-06, + "loss": 0.0148, + "step": 33699 + }, + { + "epoch": 10.41, + "learning_rate": 9.825717622671144e-06, + "loss": 0.0129, + "step": 33700 + }, + { + "epoch": 10.41, + "learning_rate": 9.825217580623959e-06, + "loss": 0.0156, + "step": 33701 + }, + { + "epoch": 10.41, + "learning_rate": 9.824717539013943e-06, + "loss": 0.0131, + "step": 33702 + }, + { + "epoch": 10.41, + "learning_rate": 9.824217497842337e-06, + "loss": 0.0135, + "step": 33703 + }, + { + "epoch": 10.41, + "learning_rate": 9.823717457110392e-06, + "loss": 0.0118, + "step": 33704 + }, + { + "epoch": 10.41, + "learning_rate": 9.823217416819368e-06, + "loss": 0.0143, + "step": 33705 + }, + { + "epoch": 10.41, + "learning_rate": 9.822717376970507e-06, + "loss": 0.0165, + "step": 33706 + }, + { + "epoch": 10.41, + "learning_rate": 9.82221733756506e-06, + "loss": 0.0156, + "step": 33707 + }, + { + "epoch": 10.41, + "learning_rate": 9.821717298604285e-06, + "loss": 0.0126, + "step": 33708 + }, + { + "epoch": 10.41, + "learning_rate": 9.821217260089422e-06, + "loss": 0.0131, + "step": 33709 + }, + { + "epoch": 10.41, + "learning_rate": 9.820717222021729e-06, + "loss": 0.014, + "step": 33710 + }, + { + "epoch": 10.41, + "learning_rate": 9.820217184402457e-06, + "loss": 0.0169, + "step": 33711 + }, + { + "epoch": 10.41, + "learning_rate": 9.819717147232851e-06, + "loss": 0.0128, + "step": 33712 + }, + { + "epoch": 10.41, + "learning_rate": 9.819217110514168e-06, + "loss": 0.0147, + "step": 33713 + }, + { + "epoch": 10.41, + "learning_rate": 9.818717074247657e-06, + "loss": 0.0161, + "step": 33714 + }, + { + "epoch": 10.41, + "learning_rate": 9.818217038434564e-06, + "loss": 0.0144, + "step": 33715 + }, + { + "epoch": 10.41, + "learning_rate": 9.817717003076145e-06, + "loss": 0.0134, + "step": 33716 + }, + { + "epoch": 10.41, + "learning_rate": 9.817216968173651e-06, + "loss": 0.012, + "step": 33717 + }, + { + "epoch": 10.41, + "learning_rate": 9.816716933728329e-06, + "loss": 0.0133, + "step": 33718 + }, + { + "epoch": 10.41, + "learning_rate": 9.816216899741429e-06, + "loss": 0.0156, + "step": 33719 + }, + { + "epoch": 10.41, + "learning_rate": 9.815716866214209e-06, + "loss": 0.017, + "step": 33720 + }, + { + "epoch": 10.41, + "learning_rate": 9.815216833147911e-06, + "loss": 0.0157, + "step": 33721 + }, + { + "epoch": 10.41, + "learning_rate": 9.81471680054379e-06, + "loss": 0.0134, + "step": 33722 + }, + { + "epoch": 10.41, + "learning_rate": 9.814216768403098e-06, + "loss": 0.0152, + "step": 33723 + }, + { + "epoch": 10.41, + "learning_rate": 9.813716736727082e-06, + "loss": 0.0147, + "step": 33724 + }, + { + "epoch": 10.41, + "learning_rate": 9.813216705516993e-06, + "loss": 0.0171, + "step": 33725 + }, + { + "epoch": 10.42, + "learning_rate": 9.812716674774087e-06, + "loss": 0.0147, + "step": 33726 + }, + { + "epoch": 10.42, + "learning_rate": 9.812216644499608e-06, + "loss": 0.0155, + "step": 33727 + }, + { + "epoch": 10.42, + "learning_rate": 9.81171661469481e-06, + "loss": 0.0146, + "step": 33728 + }, + { + "epoch": 10.42, + "learning_rate": 9.811216585360942e-06, + "loss": 0.0167, + "step": 33729 + }, + { + "epoch": 10.42, + "learning_rate": 9.810716556499258e-06, + "loss": 0.0148, + "step": 33730 + }, + { + "epoch": 10.42, + "learning_rate": 9.810216528111006e-06, + "loss": 0.0136, + "step": 33731 + }, + { + "epoch": 10.42, + "learning_rate": 9.809716500197432e-06, + "loss": 0.0145, + "step": 33732 + }, + { + "epoch": 10.42, + "learning_rate": 9.8092164727598e-06, + "loss": 0.0138, + "step": 33733 + }, + { + "epoch": 10.42, + "learning_rate": 9.808716445799348e-06, + "loss": 0.0162, + "step": 33734 + }, + { + "epoch": 10.42, + "learning_rate": 9.808216419317329e-06, + "loss": 0.015, + "step": 33735 + }, + { + "epoch": 10.42, + "learning_rate": 9.807716393315e-06, + "loss": 0.0164, + "step": 33736 + }, + { + "epoch": 10.42, + "learning_rate": 9.807216367793607e-06, + "loss": 0.014, + "step": 33737 + }, + { + "epoch": 10.42, + "learning_rate": 9.806716342754399e-06, + "loss": 0.0127, + "step": 33738 + }, + { + "epoch": 10.42, + "learning_rate": 9.806216318198631e-06, + "loss": 0.0134, + "step": 33739 + }, + { + "epoch": 10.42, + "learning_rate": 9.805716294127548e-06, + "loss": 0.0158, + "step": 33740 + }, + { + "epoch": 10.42, + "learning_rate": 9.805216270542404e-06, + "loss": 0.0143, + "step": 33741 + }, + { + "epoch": 10.42, + "learning_rate": 9.804716247444455e-06, + "loss": 0.0135, + "step": 33742 + }, + { + "epoch": 10.42, + "learning_rate": 9.804216224834939e-06, + "loss": 0.0145, + "step": 33743 + }, + { + "epoch": 10.42, + "learning_rate": 9.803716202715118e-06, + "loss": 0.0138, + "step": 33744 + }, + { + "epoch": 10.42, + "learning_rate": 9.80321618108624e-06, + "loss": 0.0128, + "step": 33745 + }, + { + "epoch": 10.42, + "learning_rate": 9.80271615994955e-06, + "loss": 0.0174, + "step": 33746 + }, + { + "epoch": 10.42, + "learning_rate": 9.802216139306306e-06, + "loss": 0.016, + "step": 33747 + }, + { + "epoch": 10.42, + "learning_rate": 9.801716119157756e-06, + "loss": 0.0161, + "step": 33748 + }, + { + "epoch": 10.42, + "learning_rate": 9.801216099505149e-06, + "loss": 0.0149, + "step": 33749 + }, + { + "epoch": 10.42, + "learning_rate": 9.800716080349735e-06, + "loss": 0.0167, + "step": 33750 + }, + { + "epoch": 10.42, + "learning_rate": 9.80021606169277e-06, + "loss": 0.0161, + "step": 33751 + }, + { + "epoch": 10.42, + "learning_rate": 9.799716043535499e-06, + "loss": 0.0156, + "step": 33752 + }, + { + "epoch": 10.42, + "learning_rate": 9.799216025879172e-06, + "loss": 0.0135, + "step": 33753 + }, + { + "epoch": 10.42, + "learning_rate": 9.798716008725048e-06, + "loss": 0.0144, + "step": 33754 + }, + { + "epoch": 10.42, + "learning_rate": 9.79821599207437e-06, + "loss": 0.0147, + "step": 33755 + }, + { + "epoch": 10.42, + "learning_rate": 9.797715975928386e-06, + "loss": 0.0129, + "step": 33756 + }, + { + "epoch": 10.42, + "learning_rate": 9.79721596028836e-06, + "loss": 0.0151, + "step": 33757 + }, + { + "epoch": 10.43, + "learning_rate": 9.796715945155526e-06, + "loss": 0.0124, + "step": 33758 + }, + { + "epoch": 10.43, + "learning_rate": 9.796215930531145e-06, + "loss": 0.0134, + "step": 33759 + }, + { + "epoch": 10.43, + "learning_rate": 9.795715916416468e-06, + "loss": 0.0165, + "step": 33760 + }, + { + "epoch": 10.43, + "learning_rate": 9.795215902812738e-06, + "loss": 0.0152, + "step": 33761 + }, + { + "epoch": 10.43, + "learning_rate": 9.794715889721213e-06, + "loss": 0.0139, + "step": 33762 + }, + { + "epoch": 10.43, + "learning_rate": 9.794215877143137e-06, + "loss": 0.014, + "step": 33763 + }, + { + "epoch": 10.43, + "learning_rate": 9.793715865079772e-06, + "loss": 0.0129, + "step": 33764 + }, + { + "epoch": 10.43, + "learning_rate": 9.793215853532355e-06, + "loss": 0.0163, + "step": 33765 + }, + { + "epoch": 10.43, + "learning_rate": 9.792715842502144e-06, + "loss": 0.0127, + "step": 33766 + }, + { + "epoch": 10.43, + "learning_rate": 9.792215831990395e-06, + "loss": 0.0138, + "step": 33767 + }, + { + "epoch": 10.43, + "learning_rate": 9.791715821998344e-06, + "loss": 0.015, + "step": 33768 + }, + { + "epoch": 10.43, + "learning_rate": 9.791215812527252e-06, + "loss": 0.014, + "step": 33769 + }, + { + "epoch": 10.43, + "learning_rate": 9.790715803578372e-06, + "loss": 0.0134, + "step": 33770 + }, + { + "epoch": 10.43, + "learning_rate": 9.790215795152942e-06, + "loss": 0.0173, + "step": 33771 + }, + { + "epoch": 10.43, + "learning_rate": 9.789715787252225e-06, + "loss": 0.0146, + "step": 33772 + }, + { + "epoch": 10.43, + "learning_rate": 9.789215779877469e-06, + "loss": 0.0131, + "step": 33773 + }, + { + "epoch": 10.43, + "learning_rate": 9.788715773029918e-06, + "loss": 0.0145, + "step": 33774 + }, + { + "epoch": 10.43, + "learning_rate": 9.78821576671083e-06, + "loss": 0.016, + "step": 33775 + }, + { + "epoch": 10.43, + "learning_rate": 9.787715760921454e-06, + "loss": 0.0144, + "step": 33776 + }, + { + "epoch": 10.43, + "learning_rate": 9.787215755663038e-06, + "loss": 0.013, + "step": 33777 + }, + { + "epoch": 10.43, + "learning_rate": 9.786715750936834e-06, + "loss": 0.0157, + "step": 33778 + }, + { + "epoch": 10.43, + "learning_rate": 9.786215746744096e-06, + "loss": 0.0137, + "step": 33779 + }, + { + "epoch": 10.43, + "learning_rate": 9.785715743086068e-06, + "loss": 0.0141, + "step": 33780 + }, + { + "epoch": 10.43, + "learning_rate": 9.785215739964002e-06, + "loss": 0.0131, + "step": 33781 + }, + { + "epoch": 10.43, + "learning_rate": 9.784715737379156e-06, + "loss": 0.015, + "step": 33782 + }, + { + "epoch": 10.43, + "learning_rate": 9.784215735332772e-06, + "loss": 0.0162, + "step": 33783 + }, + { + "epoch": 10.43, + "learning_rate": 9.783715733826103e-06, + "loss": 0.0156, + "step": 33784 + }, + { + "epoch": 10.43, + "learning_rate": 9.783215732860403e-06, + "loss": 0.0143, + "step": 33785 + }, + { + "epoch": 10.43, + "learning_rate": 9.78271573243692e-06, + "loss": 0.0141, + "step": 33786 + }, + { + "epoch": 10.43, + "learning_rate": 9.782215732556904e-06, + "loss": 0.0124, + "step": 33787 + }, + { + "epoch": 10.43, + "learning_rate": 9.781715733221607e-06, + "loss": 0.0134, + "step": 33788 + }, + { + "epoch": 10.43, + "learning_rate": 9.781215734432275e-06, + "loss": 0.0129, + "step": 33789 + }, + { + "epoch": 10.44, + "learning_rate": 9.780715736190164e-06, + "loss": 0.0127, + "step": 33790 + }, + { + "epoch": 10.44, + "learning_rate": 9.780215738496525e-06, + "loss": 0.0145, + "step": 33791 + }, + { + "epoch": 10.44, + "learning_rate": 9.779715741352604e-06, + "loss": 0.0135, + "step": 33792 + }, + { + "epoch": 10.44, + "learning_rate": 9.779215744759655e-06, + "loss": 0.0147, + "step": 33793 + }, + { + "epoch": 10.44, + "learning_rate": 9.778715748718925e-06, + "loss": 0.0138, + "step": 33794 + }, + { + "epoch": 10.44, + "learning_rate": 9.778215753231673e-06, + "loss": 0.013, + "step": 33795 + }, + { + "epoch": 10.44, + "learning_rate": 9.777715758299142e-06, + "loss": 0.0155, + "step": 33796 + }, + { + "epoch": 10.44, + "learning_rate": 9.777215763922582e-06, + "loss": 0.0136, + "step": 33797 + }, + { + "epoch": 10.44, + "learning_rate": 9.776715770103252e-06, + "loss": 0.0143, + "step": 33798 + }, + { + "epoch": 10.44, + "learning_rate": 9.776215776842389e-06, + "loss": 0.0123, + "step": 33799 + }, + { + "epoch": 10.44, + "learning_rate": 9.775715784141254e-06, + "loss": 0.0137, + "step": 33800 + }, + { + "epoch": 10.44, + "learning_rate": 9.775215792001097e-06, + "loss": 0.0159, + "step": 33801 + }, + { + "epoch": 10.44, + "learning_rate": 9.774715800423163e-06, + "loss": 0.0154, + "step": 33802 + }, + { + "epoch": 10.44, + "learning_rate": 9.774215809408706e-06, + "loss": 0.0167, + "step": 33803 + }, + { + "epoch": 10.44, + "learning_rate": 9.773715818958979e-06, + "loss": 0.0164, + "step": 33804 + }, + { + "epoch": 10.44, + "learning_rate": 9.773215829075228e-06, + "loss": 0.0152, + "step": 33805 + }, + { + "epoch": 10.44, + "learning_rate": 9.772715839758704e-06, + "loss": 0.016, + "step": 33806 + }, + { + "epoch": 10.44, + "learning_rate": 9.772215851010665e-06, + "loss": 0.0148, + "step": 33807 + }, + { + "epoch": 10.44, + "learning_rate": 9.771715862832352e-06, + "loss": 0.0156, + "step": 33808 + }, + { + "epoch": 10.44, + "learning_rate": 9.771215875225018e-06, + "loss": 0.0155, + "step": 33809 + }, + { + "epoch": 10.44, + "learning_rate": 9.770715888189916e-06, + "loss": 0.0147, + "step": 33810 + }, + { + "epoch": 10.44, + "learning_rate": 9.770215901728297e-06, + "loss": 0.0133, + "step": 33811 + }, + { + "epoch": 10.44, + "learning_rate": 9.769715915841406e-06, + "loss": 0.0133, + "step": 33812 + }, + { + "epoch": 10.44, + "learning_rate": 9.769215930530503e-06, + "loss": 0.0131, + "step": 33813 + }, + { + "epoch": 10.44, + "learning_rate": 9.76871594579683e-06, + "loss": 0.0146, + "step": 33814 + }, + { + "epoch": 10.44, + "learning_rate": 9.768215961641636e-06, + "loss": 0.0159, + "step": 33815 + }, + { + "epoch": 10.44, + "learning_rate": 9.767715978066187e-06, + "loss": 0.0154, + "step": 33816 + }, + { + "epoch": 10.44, + "learning_rate": 9.767215995071714e-06, + "loss": 0.0141, + "step": 33817 + }, + { + "epoch": 10.44, + "learning_rate": 9.766716012659478e-06, + "loss": 0.0166, + "step": 33818 + }, + { + "epoch": 10.44, + "learning_rate": 9.76621603083073e-06, + "loss": 0.0136, + "step": 33819 + }, + { + "epoch": 10.44, + "learning_rate": 9.765716049586716e-06, + "loss": 0.0173, + "step": 33820 + }, + { + "epoch": 10.44, + "learning_rate": 9.76521606892869e-06, + "loss": 0.013, + "step": 33821 + }, + { + "epoch": 10.44, + "learning_rate": 9.764716088857904e-06, + "loss": 0.0155, + "step": 33822 + }, + { + "epoch": 10.45, + "learning_rate": 9.7642161093756e-06, + "loss": 0.0144, + "step": 33823 + }, + { + "epoch": 10.45, + "learning_rate": 9.763716130483037e-06, + "loss": 0.0151, + "step": 33824 + }, + { + "epoch": 10.45, + "learning_rate": 9.763216152181467e-06, + "loss": 0.0146, + "step": 33825 + }, + { + "epoch": 10.45, + "learning_rate": 9.762716174472132e-06, + "loss": 0.0138, + "step": 33826 + }, + { + "epoch": 10.45, + "learning_rate": 9.762216197356286e-06, + "loss": 0.014, + "step": 33827 + }, + { + "epoch": 10.45, + "learning_rate": 9.761716220835183e-06, + "loss": 0.0157, + "step": 33828 + }, + { + "epoch": 10.45, + "learning_rate": 9.761216244910074e-06, + "loss": 0.0158, + "step": 33829 + }, + { + "epoch": 10.45, + "learning_rate": 9.760716269582201e-06, + "loss": 0.0154, + "step": 33830 + }, + { + "epoch": 10.45, + "learning_rate": 9.760216294852823e-06, + "loss": 0.015, + "step": 33831 + }, + { + "epoch": 10.45, + "learning_rate": 9.759716320723192e-06, + "loss": 0.0148, + "step": 33832 + }, + { + "epoch": 10.45, + "learning_rate": 9.759216347194546e-06, + "loss": 0.0154, + "step": 33833 + }, + { + "epoch": 10.45, + "learning_rate": 9.75871637426815e-06, + "loss": 0.0159, + "step": 33834 + }, + { + "epoch": 10.45, + "learning_rate": 9.758216401945248e-06, + "loss": 0.0141, + "step": 33835 + }, + { + "epoch": 10.45, + "learning_rate": 9.75771643022709e-06, + "loss": 0.0149, + "step": 33836 + }, + { + "epoch": 10.45, + "learning_rate": 9.757216459114925e-06, + "loss": 0.0139, + "step": 33837 + }, + { + "epoch": 10.45, + "learning_rate": 9.756716488610008e-06, + "loss": 0.014, + "step": 33838 + }, + { + "epoch": 10.45, + "learning_rate": 9.756216518713589e-06, + "loss": 0.0166, + "step": 33839 + }, + { + "epoch": 10.45, + "learning_rate": 9.755716549426912e-06, + "loss": 0.015, + "step": 33840 + }, + { + "epoch": 10.45, + "learning_rate": 9.755216580751238e-06, + "loss": 0.0144, + "step": 33841 + }, + { + "epoch": 10.45, + "learning_rate": 9.754716612687808e-06, + "loss": 0.0147, + "step": 33842 + }, + { + "epoch": 10.45, + "learning_rate": 9.754216645237877e-06, + "loss": 0.0151, + "step": 33843 + }, + { + "epoch": 10.45, + "learning_rate": 9.753716678402699e-06, + "loss": 0.0157, + "step": 33844 + }, + { + "epoch": 10.45, + "learning_rate": 9.753216712183517e-06, + "loss": 0.0158, + "step": 33845 + }, + { + "epoch": 10.45, + "learning_rate": 9.752716746581585e-06, + "loss": 0.0149, + "step": 33846 + }, + { + "epoch": 10.45, + "learning_rate": 9.752216781598156e-06, + "loss": 0.0162, + "step": 33847 + }, + { + "epoch": 10.45, + "learning_rate": 9.751716817234474e-06, + "loss": 0.0156, + "step": 33848 + }, + { + "epoch": 10.45, + "learning_rate": 9.751216853491797e-06, + "loss": 0.0141, + "step": 33849 + }, + { + "epoch": 10.45, + "learning_rate": 9.750716890371371e-06, + "loss": 0.0136, + "step": 33850 + }, + { + "epoch": 10.45, + "learning_rate": 9.750216927874445e-06, + "loss": 0.0143, + "step": 33851 + }, + { + "epoch": 10.45, + "learning_rate": 9.749716966002275e-06, + "loss": 0.0149, + "step": 33852 + }, + { + "epoch": 10.45, + "learning_rate": 9.74921700475611e-06, + "loss": 0.0152, + "step": 33853 + }, + { + "epoch": 10.45, + "learning_rate": 9.748717044137193e-06, + "loss": 0.0144, + "step": 33854 + }, + { + "epoch": 10.46, + "learning_rate": 9.748217084146785e-06, + "loss": 0.0128, + "step": 33855 + }, + { + "epoch": 10.46, + "learning_rate": 9.747717124786134e-06, + "loss": 0.0148, + "step": 33856 + }, + { + "epoch": 10.46, + "learning_rate": 9.747217166056485e-06, + "loss": 0.0156, + "step": 33857 + }, + { + "epoch": 10.46, + "learning_rate": 9.746717207959092e-06, + "loss": 0.0151, + "step": 33858 + }, + { + "epoch": 10.46, + "learning_rate": 9.746217250495205e-06, + "loss": 0.0125, + "step": 33859 + }, + { + "epoch": 10.46, + "learning_rate": 9.745717293666078e-06, + "loss": 0.016, + "step": 33860 + }, + { + "epoch": 10.46, + "learning_rate": 9.745217337472954e-06, + "loss": 0.0152, + "step": 33861 + }, + { + "epoch": 10.46, + "learning_rate": 9.74471738191709e-06, + "loss": 0.0138, + "step": 33862 + }, + { + "epoch": 10.46, + "learning_rate": 9.744217426999738e-06, + "loss": 0.0132, + "step": 33863 + }, + { + "epoch": 10.46, + "learning_rate": 9.74371747272214e-06, + "loss": 0.0142, + "step": 33864 + }, + { + "epoch": 10.46, + "learning_rate": 9.743217519085551e-06, + "loss": 0.0151, + "step": 33865 + }, + { + "epoch": 10.46, + "learning_rate": 9.742717566091227e-06, + "loss": 0.0148, + "step": 33866 + }, + { + "epoch": 10.46, + "learning_rate": 9.74221761374041e-06, + "loss": 0.0151, + "step": 33867 + }, + { + "epoch": 10.46, + "learning_rate": 9.741717662034352e-06, + "loss": 0.0145, + "step": 33868 + }, + { + "epoch": 10.46, + "learning_rate": 9.741217710974308e-06, + "loss": 0.0138, + "step": 33869 + }, + { + "epoch": 10.46, + "learning_rate": 9.740717760561525e-06, + "loss": 0.0154, + "step": 33870 + }, + { + "epoch": 10.46, + "learning_rate": 9.740217810797252e-06, + "loss": 0.0152, + "step": 33871 + }, + { + "epoch": 10.46, + "learning_rate": 9.739717861682747e-06, + "loss": 0.0142, + "step": 33872 + }, + { + "epoch": 10.46, + "learning_rate": 9.739217913219251e-06, + "loss": 0.0156, + "step": 33873 + }, + { + "epoch": 10.46, + "learning_rate": 9.738717965408018e-06, + "loss": 0.0135, + "step": 33874 + }, + { + "epoch": 10.46, + "learning_rate": 9.738218018250304e-06, + "loss": 0.0159, + "step": 33875 + }, + { + "epoch": 10.46, + "learning_rate": 9.737718071747349e-06, + "loss": 0.0146, + "step": 33876 + }, + { + "epoch": 10.46, + "learning_rate": 9.73721812590041e-06, + "loss": 0.0148, + "step": 33877 + }, + { + "epoch": 10.46, + "learning_rate": 9.73671818071074e-06, + "loss": 0.0177, + "step": 33878 + }, + { + "epoch": 10.46, + "learning_rate": 9.73621823617958e-06, + "loss": 0.0138, + "step": 33879 + }, + { + "epoch": 10.46, + "learning_rate": 9.73571829230819e-06, + "loss": 0.0154, + "step": 33880 + }, + { + "epoch": 10.46, + "learning_rate": 9.735218349097818e-06, + "loss": 0.0142, + "step": 33881 + }, + { + "epoch": 10.46, + "learning_rate": 9.734718406549709e-06, + "loss": 0.0133, + "step": 33882 + }, + { + "epoch": 10.46, + "learning_rate": 9.734218464665119e-06, + "loss": 0.0145, + "step": 33883 + }, + { + "epoch": 10.46, + "learning_rate": 9.7337185234453e-06, + "loss": 0.0156, + "step": 33884 + }, + { + "epoch": 10.46, + "learning_rate": 9.733218582891499e-06, + "loss": 0.0131, + "step": 33885 + }, + { + "epoch": 10.46, + "learning_rate": 9.732718643004962e-06, + "loss": 0.0149, + "step": 33886 + }, + { + "epoch": 10.46, + "learning_rate": 9.73221870378695e-06, + "loss": 0.013, + "step": 33887 + }, + { + "epoch": 10.47, + "learning_rate": 9.731718765238707e-06, + "loss": 0.0133, + "step": 33888 + }, + { + "epoch": 10.47, + "learning_rate": 9.73121882736148e-06, + "loss": 0.0147, + "step": 33889 + }, + { + "epoch": 10.47, + "learning_rate": 9.73071889015653e-06, + "loss": 0.0144, + "step": 33890 + }, + { + "epoch": 10.47, + "learning_rate": 9.730218953625098e-06, + "loss": 0.0166, + "step": 33891 + }, + { + "epoch": 10.47, + "learning_rate": 9.729719017768433e-06, + "loss": 0.0136, + "step": 33892 + }, + { + "epoch": 10.47, + "learning_rate": 9.729219082587796e-06, + "loss": 0.0128, + "step": 33893 + }, + { + "epoch": 10.47, + "learning_rate": 9.728719148084432e-06, + "loss": 0.0143, + "step": 33894 + }, + { + "epoch": 10.47, + "learning_rate": 9.728219214259586e-06, + "loss": 0.0141, + "step": 33895 + }, + { + "epoch": 10.47, + "learning_rate": 9.727719281114516e-06, + "loss": 0.0149, + "step": 33896 + }, + { + "epoch": 10.47, + "learning_rate": 9.727219348650475e-06, + "loss": 0.0148, + "step": 33897 + }, + { + "epoch": 10.47, + "learning_rate": 9.726719416868701e-06, + "loss": 0.0139, + "step": 33898 + }, + { + "epoch": 10.47, + "learning_rate": 9.726219485770451e-06, + "loss": 0.0152, + "step": 33899 + }, + { + "epoch": 10.47, + "learning_rate": 9.725719555356984e-06, + "loss": 0.0145, + "step": 33900 + }, + { + "epoch": 10.47, + "learning_rate": 9.725219625629534e-06, + "loss": 0.0136, + "step": 33901 + }, + { + "epoch": 10.47, + "learning_rate": 9.724719696589363e-06, + "loss": 0.0148, + "step": 33902 + }, + { + "epoch": 10.47, + "learning_rate": 9.724219768237719e-06, + "loss": 0.0151, + "step": 33903 + }, + { + "epoch": 10.47, + "learning_rate": 9.72371984057585e-06, + "loss": 0.0151, + "step": 33904 + }, + { + "epoch": 10.47, + "learning_rate": 9.72321991360501e-06, + "loss": 0.0148, + "step": 33905 + }, + { + "epoch": 10.47, + "learning_rate": 9.722719987326448e-06, + "loss": 0.0151, + "step": 33906 + }, + { + "epoch": 10.47, + "learning_rate": 9.72222006174141e-06, + "loss": 0.0153, + "step": 33907 + }, + { + "epoch": 10.47, + "learning_rate": 9.721720136851154e-06, + "loss": 0.0146, + "step": 33908 + }, + { + "epoch": 10.47, + "learning_rate": 9.721220212656928e-06, + "loss": 0.0141, + "step": 33909 + }, + { + "epoch": 10.47, + "learning_rate": 9.720720289159977e-06, + "loss": 0.0146, + "step": 33910 + }, + { + "epoch": 10.47, + "learning_rate": 9.720220366361555e-06, + "loss": 0.0152, + "step": 33911 + }, + { + "epoch": 10.47, + "learning_rate": 9.719720444262919e-06, + "loss": 0.0139, + "step": 33912 + }, + { + "epoch": 10.47, + "learning_rate": 9.719220522865307e-06, + "loss": 0.0153, + "step": 33913 + }, + { + "epoch": 10.47, + "learning_rate": 9.718720602169976e-06, + "loss": 0.0158, + "step": 33914 + }, + { + "epoch": 10.47, + "learning_rate": 9.71822068217818e-06, + "loss": 0.017, + "step": 33915 + }, + { + "epoch": 10.47, + "learning_rate": 9.717720762891164e-06, + "loss": 0.0157, + "step": 33916 + }, + { + "epoch": 10.47, + "learning_rate": 9.717220844310177e-06, + "loss": 0.0161, + "step": 33917 + }, + { + "epoch": 10.47, + "learning_rate": 9.716720926436476e-06, + "loss": 0.0155, + "step": 33918 + }, + { + "epoch": 10.47, + "learning_rate": 9.716221009271307e-06, + "loss": 0.0168, + "step": 33919 + }, + { + "epoch": 10.48, + "learning_rate": 9.715721092815917e-06, + "loss": 0.0158, + "step": 33920 + }, + { + "epoch": 10.48, + "learning_rate": 9.715221177071566e-06, + "loss": 0.0139, + "step": 33921 + }, + { + "epoch": 10.48, + "learning_rate": 9.714721262039496e-06, + "loss": 0.0164, + "step": 33922 + }, + { + "epoch": 10.48, + "learning_rate": 9.714221347720959e-06, + "loss": 0.016, + "step": 33923 + }, + { + "epoch": 10.48, + "learning_rate": 9.713721434117212e-06, + "loss": 0.0163, + "step": 33924 + }, + { + "epoch": 10.48, + "learning_rate": 9.713221521229493e-06, + "loss": 0.0143, + "step": 33925 + }, + { + "epoch": 10.48, + "learning_rate": 9.712721609059063e-06, + "loss": 0.014, + "step": 33926 + }, + { + "epoch": 10.48, + "learning_rate": 9.712221697607164e-06, + "loss": 0.0123, + "step": 33927 + }, + { + "epoch": 10.48, + "learning_rate": 9.711721786875058e-06, + "loss": 0.0155, + "step": 33928 + }, + { + "epoch": 10.48, + "learning_rate": 9.711221876863984e-06, + "loss": 0.0182, + "step": 33929 + }, + { + "epoch": 10.48, + "learning_rate": 9.710721967575196e-06, + "loss": 0.0167, + "step": 33930 + }, + { + "epoch": 10.48, + "learning_rate": 9.710222059009949e-06, + "loss": 0.0153, + "step": 33931 + }, + { + "epoch": 10.48, + "learning_rate": 9.709722151169489e-06, + "loss": 0.014, + "step": 33932 + }, + { + "epoch": 10.48, + "learning_rate": 9.709222244055061e-06, + "loss": 0.0147, + "step": 33933 + }, + { + "epoch": 10.48, + "learning_rate": 9.70872233766793e-06, + "loss": 0.0133, + "step": 33934 + }, + { + "epoch": 10.48, + "learning_rate": 9.708222432009332e-06, + "loss": 0.0141, + "step": 33935 + }, + { + "epoch": 10.48, + "learning_rate": 9.707722527080524e-06, + "loss": 0.0166, + "step": 33936 + }, + { + "epoch": 10.48, + "learning_rate": 9.707222622882758e-06, + "loss": 0.015, + "step": 33937 + }, + { + "epoch": 10.48, + "learning_rate": 9.706722719417276e-06, + "loss": 0.0136, + "step": 33938 + }, + { + "epoch": 10.48, + "learning_rate": 9.706222816685338e-06, + "loss": 0.0146, + "step": 33939 + }, + { + "epoch": 10.48, + "learning_rate": 9.705722914688192e-06, + "loss": 0.0132, + "step": 33940 + }, + { + "epoch": 10.48, + "learning_rate": 9.705223013427081e-06, + "loss": 0.0172, + "step": 33941 + }, + { + "epoch": 10.48, + "learning_rate": 9.704723112903265e-06, + "loss": 0.0165, + "step": 33942 + }, + { + "epoch": 10.48, + "learning_rate": 9.70422321311799e-06, + "loss": 0.0161, + "step": 33943 + }, + { + "epoch": 10.48, + "learning_rate": 9.703723314072505e-06, + "loss": 0.0129, + "step": 33944 + }, + { + "epoch": 10.48, + "learning_rate": 9.703223415768062e-06, + "loss": 0.0148, + "step": 33945 + }, + { + "epoch": 10.48, + "learning_rate": 9.702723518205915e-06, + "loss": 0.0147, + "step": 33946 + }, + { + "epoch": 10.48, + "learning_rate": 9.702223621387308e-06, + "loss": 0.015, + "step": 33947 + }, + { + "epoch": 10.48, + "learning_rate": 9.701723725313491e-06, + "loss": 0.0164, + "step": 33948 + }, + { + "epoch": 10.48, + "learning_rate": 9.701223829985724e-06, + "loss": 0.0139, + "step": 33949 + }, + { + "epoch": 10.48, + "learning_rate": 9.700723935405246e-06, + "loss": 0.0145, + "step": 33950 + }, + { + "epoch": 10.48, + "learning_rate": 9.70022404157331e-06, + "loss": 0.0132, + "step": 33951 + }, + { + "epoch": 10.49, + "learning_rate": 9.699724148491174e-06, + "loss": 0.0156, + "step": 33952 + }, + { + "epoch": 10.49, + "learning_rate": 9.699224256160081e-06, + "loss": 0.0178, + "step": 33953 + }, + { + "epoch": 10.49, + "learning_rate": 9.69872436458128e-06, + "loss": 0.0147, + "step": 33954 + }, + { + "epoch": 10.49, + "learning_rate": 9.698224473756031e-06, + "loss": 0.0153, + "step": 33955 + }, + { + "epoch": 10.49, + "learning_rate": 9.69772458368557e-06, + "loss": 0.0133, + "step": 33956 + }, + { + "epoch": 10.49, + "learning_rate": 9.697224694371159e-06, + "loss": 0.0158, + "step": 33957 + }, + { + "epoch": 10.49, + "learning_rate": 9.696724805814041e-06, + "loss": 0.0135, + "step": 33958 + }, + { + "epoch": 10.49, + "learning_rate": 9.696224918015473e-06, + "loss": 0.0138, + "step": 33959 + }, + { + "epoch": 10.49, + "learning_rate": 9.6957250309767e-06, + "loss": 0.0156, + "step": 33960 + }, + { + "epoch": 10.49, + "learning_rate": 9.695225144698974e-06, + "loss": 0.0147, + "step": 33961 + }, + { + "epoch": 10.49, + "learning_rate": 9.694725259183548e-06, + "loss": 0.0155, + "step": 33962 + }, + { + "epoch": 10.49, + "learning_rate": 9.69422537443167e-06, + "loss": 0.0158, + "step": 33963 + }, + { + "epoch": 10.49, + "learning_rate": 9.693725490444586e-06, + "loss": 0.0154, + "step": 33964 + }, + { + "epoch": 10.49, + "learning_rate": 9.693225607223557e-06, + "loss": 0.0152, + "step": 33965 + }, + { + "epoch": 10.49, + "learning_rate": 9.692725724769821e-06, + "loss": 0.0142, + "step": 33966 + }, + { + "epoch": 10.49, + "learning_rate": 9.692225843084634e-06, + "loss": 0.0122, + "step": 33967 + }, + { + "epoch": 10.49, + "learning_rate": 9.69172596216925e-06, + "loss": 0.0142, + "step": 33968 + }, + { + "epoch": 10.49, + "learning_rate": 9.691226082024911e-06, + "loss": 0.0127, + "step": 33969 + }, + { + "epoch": 10.49, + "learning_rate": 9.690726202652875e-06, + "loss": 0.0167, + "step": 33970 + }, + { + "epoch": 10.49, + "learning_rate": 9.69022632405439e-06, + "loss": 0.0142, + "step": 33971 + }, + { + "epoch": 10.49, + "learning_rate": 9.689726446230701e-06, + "loss": 0.0163, + "step": 33972 + }, + { + "epoch": 10.49, + "learning_rate": 9.689226569183067e-06, + "loss": 0.0165, + "step": 33973 + }, + { + "epoch": 10.49, + "learning_rate": 9.688726692912735e-06, + "loss": 0.0153, + "step": 33974 + }, + { + "epoch": 10.49, + "learning_rate": 9.68822681742095e-06, + "loss": 0.0172, + "step": 33975 + }, + { + "epoch": 10.49, + "learning_rate": 9.687726942708968e-06, + "loss": 0.0162, + "step": 33976 + }, + { + "epoch": 10.49, + "learning_rate": 9.687227068778042e-06, + "loss": 0.0172, + "step": 33977 + }, + { + "epoch": 10.49, + "learning_rate": 9.686727195629414e-06, + "loss": 0.0188, + "step": 33978 + }, + { + "epoch": 10.49, + "learning_rate": 9.686227323264337e-06, + "loss": 0.0163, + "step": 33979 + }, + { + "epoch": 10.49, + "learning_rate": 9.685727451684066e-06, + "loss": 0.0158, + "step": 33980 + }, + { + "epoch": 10.49, + "learning_rate": 9.685227580889846e-06, + "loss": 0.0149, + "step": 33981 + }, + { + "epoch": 10.49, + "learning_rate": 9.684727710882929e-06, + "loss": 0.0157, + "step": 33982 + }, + { + "epoch": 10.49, + "learning_rate": 9.684227841664568e-06, + "loss": 0.014, + "step": 33983 + }, + { + "epoch": 10.49, + "learning_rate": 9.683727973236009e-06, + "loss": 0.0133, + "step": 33984 + }, + { + "epoch": 10.5, + "learning_rate": 9.683228105598504e-06, + "loss": 0.015, + "step": 33985 + }, + { + "epoch": 10.5, + "learning_rate": 9.682728238753307e-06, + "loss": 0.0145, + "step": 33986 + }, + { + "epoch": 10.5, + "learning_rate": 9.682228372701658e-06, + "loss": 0.0148, + "step": 33987 + }, + { + "epoch": 10.5, + "learning_rate": 9.681728507444817e-06, + "loss": 0.0142, + "step": 33988 + }, + { + "epoch": 10.5, + "learning_rate": 9.681228642984033e-06, + "loss": 0.0159, + "step": 33989 + }, + { + "epoch": 10.5, + "learning_rate": 9.68072877932055e-06, + "loss": 0.0155, + "step": 33990 + }, + { + "epoch": 10.5, + "learning_rate": 9.680228916455624e-06, + "loss": 0.0136, + "step": 33991 + }, + { + "epoch": 10.5, + "learning_rate": 9.679729054390504e-06, + "loss": 0.0148, + "step": 33992 + }, + { + "epoch": 10.5, + "learning_rate": 9.679229193126442e-06, + "loss": 0.014, + "step": 33993 + }, + { + "epoch": 10.5, + "learning_rate": 9.678729332664684e-06, + "loss": 0.0164, + "step": 33994 + }, + { + "epoch": 10.5, + "learning_rate": 9.678229473006484e-06, + "loss": 0.0129, + "step": 33995 + }, + { + "epoch": 10.5, + "learning_rate": 9.677729614153093e-06, + "loss": 0.0152, + "step": 33996 + }, + { + "epoch": 10.5, + "learning_rate": 9.677229756105753e-06, + "loss": 0.0147, + "step": 33997 + }, + { + "epoch": 10.5, + "learning_rate": 9.676729898865725e-06, + "loss": 0.0147, + "step": 33998 + }, + { + "epoch": 10.5, + "learning_rate": 9.676230042434254e-06, + "loss": 0.0151, + "step": 33999 + }, + { + "epoch": 10.5, + "learning_rate": 9.675730186812588e-06, + "loss": 0.0158, + "step": 34000 + }, + { + "epoch": 10.5, + "learning_rate": 9.67523033200198e-06, + "loss": 0.0159, + "step": 34001 + }, + { + "epoch": 10.5, + "learning_rate": 9.674730478003685e-06, + "loss": 0.0161, + "step": 34002 + }, + { + "epoch": 10.5, + "learning_rate": 9.674230624818943e-06, + "loss": 0.0162, + "step": 34003 + }, + { + "epoch": 10.5, + "learning_rate": 9.673730772449012e-06, + "loss": 0.0156, + "step": 34004 + }, + { + "epoch": 10.5, + "learning_rate": 9.673230920895143e-06, + "loss": 0.0153, + "step": 34005 + }, + { + "epoch": 10.5, + "learning_rate": 9.672731070158578e-06, + "loss": 0.0132, + "step": 34006 + }, + { + "epoch": 10.5, + "learning_rate": 9.672231220240572e-06, + "loss": 0.0157, + "step": 34007 + }, + { + "epoch": 10.5, + "learning_rate": 9.671731371142379e-06, + "loss": 0.0157, + "step": 34008 + }, + { + "epoch": 10.5, + "learning_rate": 9.671231522865245e-06, + "loss": 0.0159, + "step": 34009 + }, + { + "epoch": 10.5, + "learning_rate": 9.670731675410418e-06, + "loss": 0.0148, + "step": 34010 + }, + { + "epoch": 10.5, + "learning_rate": 9.670231828779156e-06, + "loss": 0.0133, + "step": 34011 + }, + { + "epoch": 10.5, + "learning_rate": 9.669731982972702e-06, + "loss": 0.0172, + "step": 34012 + }, + { + "epoch": 10.5, + "learning_rate": 9.669232137992306e-06, + "loss": 0.0139, + "step": 34013 + }, + { + "epoch": 10.5, + "learning_rate": 9.668732293839226e-06, + "loss": 0.0138, + "step": 34014 + }, + { + "epoch": 10.5, + "learning_rate": 9.668232450514703e-06, + "loss": 0.0175, + "step": 34015 + }, + { + "epoch": 10.5, + "learning_rate": 9.667732608019992e-06, + "loss": 0.015, + "step": 34016 + }, + { + "epoch": 10.51, + "learning_rate": 9.667232766356344e-06, + "loss": 0.016, + "step": 34017 + }, + { + "epoch": 10.51, + "learning_rate": 9.666732925525005e-06, + "loss": 0.015, + "step": 34018 + }, + { + "epoch": 10.51, + "learning_rate": 9.666233085527228e-06, + "loss": 0.0154, + "step": 34019 + }, + { + "epoch": 10.51, + "learning_rate": 9.665733246364266e-06, + "loss": 0.0124, + "step": 34020 + }, + { + "epoch": 10.51, + "learning_rate": 9.66523340803736e-06, + "loss": 0.0151, + "step": 34021 + }, + { + "epoch": 10.51, + "learning_rate": 9.66473357054777e-06, + "loss": 0.0132, + "step": 34022 + }, + { + "epoch": 10.51, + "learning_rate": 9.66423373389674e-06, + "loss": 0.0137, + "step": 34023 + }, + { + "epoch": 10.51, + "learning_rate": 9.663733898085531e-06, + "loss": 0.0154, + "step": 34024 + }, + { + "epoch": 10.51, + "learning_rate": 9.663234063115377e-06, + "loss": 0.0153, + "step": 34025 + }, + { + "epoch": 10.51, + "learning_rate": 9.662734228987539e-06, + "loss": 0.0152, + "step": 34026 + }, + { + "epoch": 10.51, + "learning_rate": 9.662234395703264e-06, + "loss": 0.015, + "step": 34027 + }, + { + "epoch": 10.51, + "learning_rate": 9.661734563263799e-06, + "loss": 0.0165, + "step": 34028 + }, + { + "epoch": 10.51, + "learning_rate": 9.6612347316704e-06, + "loss": 0.0148, + "step": 34029 + }, + { + "epoch": 10.51, + "learning_rate": 9.660734900924318e-06, + "loss": 0.0144, + "step": 34030 + }, + { + "epoch": 10.51, + "learning_rate": 9.660235071026794e-06, + "loss": 0.0156, + "step": 34031 + }, + { + "epoch": 10.51, + "learning_rate": 9.659735241979087e-06, + "loss": 0.0141, + "step": 34032 + }, + { + "epoch": 10.51, + "learning_rate": 9.659235413782447e-06, + "loss": 0.0154, + "step": 34033 + }, + { + "epoch": 10.51, + "learning_rate": 9.658735586438118e-06, + "loss": 0.0152, + "step": 34034 + }, + { + "epoch": 10.51, + "learning_rate": 9.658235759947351e-06, + "loss": 0.0141, + "step": 34035 + }, + { + "epoch": 10.51, + "learning_rate": 9.657735934311405e-06, + "loss": 0.0144, + "step": 34036 + }, + { + "epoch": 10.51, + "learning_rate": 9.657236109531521e-06, + "loss": 0.0147, + "step": 34037 + }, + { + "epoch": 10.51, + "learning_rate": 9.65673628560895e-06, + "loss": 0.0135, + "step": 34038 + }, + { + "epoch": 10.51, + "learning_rate": 9.656236462544947e-06, + "loss": 0.0148, + "step": 34039 + }, + { + "epoch": 10.51, + "learning_rate": 9.655736640340757e-06, + "loss": 0.0139, + "step": 34040 + }, + { + "epoch": 10.51, + "learning_rate": 9.655236818997633e-06, + "loss": 0.0131, + "step": 34041 + }, + { + "epoch": 10.51, + "learning_rate": 9.654736998516825e-06, + "loss": 0.0141, + "step": 34042 + }, + { + "epoch": 10.51, + "learning_rate": 9.654237178899584e-06, + "loss": 0.0136, + "step": 34043 + }, + { + "epoch": 10.51, + "learning_rate": 9.653737360147157e-06, + "loss": 0.0142, + "step": 34044 + }, + { + "epoch": 10.51, + "learning_rate": 9.6532375422608e-06, + "loss": 0.0169, + "step": 34045 + }, + { + "epoch": 10.51, + "learning_rate": 9.652737725241754e-06, + "loss": 0.0165, + "step": 34046 + }, + { + "epoch": 10.51, + "learning_rate": 9.652237909091275e-06, + "loss": 0.017, + "step": 34047 + }, + { + "epoch": 10.51, + "learning_rate": 9.651738093810617e-06, + "loss": 0.017, + "step": 34048 + }, + { + "epoch": 10.52, + "learning_rate": 9.651238279401018e-06, + "loss": 0.0153, + "step": 34049 + }, + { + "epoch": 10.52, + "learning_rate": 9.65073846586374e-06, + "loss": 0.0153, + "step": 34050 + }, + { + "epoch": 10.52, + "learning_rate": 9.650238653200032e-06, + "loss": 0.0143, + "step": 34051 + }, + { + "epoch": 10.52, + "learning_rate": 9.649738841411134e-06, + "loss": 0.0168, + "step": 34052 + }, + { + "epoch": 10.52, + "learning_rate": 9.649239030498308e-06, + "loss": 0.0149, + "step": 34053 + }, + { + "epoch": 10.52, + "learning_rate": 9.6487392204628e-06, + "loss": 0.0152, + "step": 34054 + }, + { + "epoch": 10.52, + "learning_rate": 9.648239411305857e-06, + "loss": 0.0136, + "step": 34055 + }, + { + "epoch": 10.52, + "learning_rate": 9.647739603028728e-06, + "loss": 0.0167, + "step": 34056 + }, + { + "epoch": 10.52, + "learning_rate": 9.64723979563267e-06, + "loss": 0.0178, + "step": 34057 + }, + { + "epoch": 10.52, + "learning_rate": 9.646739989118931e-06, + "loss": 0.0144, + "step": 34058 + }, + { + "epoch": 10.52, + "learning_rate": 9.646240183488756e-06, + "loss": 0.0126, + "step": 34059 + }, + { + "epoch": 10.52, + "learning_rate": 9.645740378743402e-06, + "loss": 0.0136, + "step": 34060 + }, + { + "epoch": 10.52, + "learning_rate": 9.645240574884117e-06, + "loss": 0.0139, + "step": 34061 + }, + { + "epoch": 10.52, + "learning_rate": 9.644740771912145e-06, + "loss": 0.0171, + "step": 34062 + }, + { + "epoch": 10.52, + "learning_rate": 9.644240969828746e-06, + "loss": 0.0146, + "step": 34063 + }, + { + "epoch": 10.52, + "learning_rate": 9.643741168635164e-06, + "loss": 0.0164, + "step": 34064 + }, + { + "epoch": 10.52, + "learning_rate": 9.64324136833265e-06, + "loss": 0.0141, + "step": 34065 + }, + { + "epoch": 10.52, + "learning_rate": 9.642741568922451e-06, + "loss": 0.0133, + "step": 34066 + }, + { + "epoch": 10.52, + "learning_rate": 9.642241770405826e-06, + "loss": 0.0161, + "step": 34067 + }, + { + "epoch": 10.52, + "learning_rate": 9.641741972784018e-06, + "loss": 0.0157, + "step": 34068 + }, + { + "epoch": 10.52, + "learning_rate": 9.641242176058275e-06, + "loss": 0.016, + "step": 34069 + }, + { + "epoch": 10.52, + "learning_rate": 9.640742380229857e-06, + "loss": 0.0169, + "step": 34070 + }, + { + "epoch": 10.52, + "learning_rate": 9.640242585300003e-06, + "loss": 0.0187, + "step": 34071 + }, + { + "epoch": 10.52, + "learning_rate": 9.639742791269966e-06, + "loss": 0.0146, + "step": 34072 + }, + { + "epoch": 10.52, + "learning_rate": 9.639242998141007e-06, + "loss": 0.0145, + "step": 34073 + }, + { + "epoch": 10.52, + "learning_rate": 9.638743205914359e-06, + "loss": 0.0168, + "step": 34074 + }, + { + "epoch": 10.52, + "learning_rate": 9.638243414591284e-06, + "loss": 0.0153, + "step": 34075 + }, + { + "epoch": 10.52, + "learning_rate": 9.637743624173028e-06, + "loss": 0.0135, + "step": 34076 + }, + { + "epoch": 10.52, + "learning_rate": 9.637243834660838e-06, + "loss": 0.0147, + "step": 34077 + }, + { + "epoch": 10.52, + "learning_rate": 9.636744046055969e-06, + "loss": 0.0131, + "step": 34078 + }, + { + "epoch": 10.52, + "learning_rate": 9.636244258359672e-06, + "loss": 0.0132, + "step": 34079 + }, + { + "epoch": 10.52, + "learning_rate": 9.63574447157319e-06, + "loss": 0.0149, + "step": 34080 + }, + { + "epoch": 10.52, + "learning_rate": 9.635244685697778e-06, + "loss": 0.0142, + "step": 34081 + }, + { + "epoch": 10.53, + "learning_rate": 9.63474490073469e-06, + "loss": 0.0154, + "step": 34082 + }, + { + "epoch": 10.53, + "learning_rate": 9.63424511668517e-06, + "loss": 0.0139, + "step": 34083 + }, + { + "epoch": 10.53, + "learning_rate": 9.633745333550465e-06, + "loss": 0.0152, + "step": 34084 + }, + { + "epoch": 10.53, + "learning_rate": 9.633245551331835e-06, + "loss": 0.0156, + "step": 34085 + }, + { + "epoch": 10.53, + "learning_rate": 9.632745770030524e-06, + "loss": 0.0173, + "step": 34086 + }, + { + "epoch": 10.53, + "learning_rate": 9.63224598964778e-06, + "loss": 0.0162, + "step": 34087 + }, + { + "epoch": 10.53, + "learning_rate": 9.631746210184857e-06, + "loss": 0.0151, + "step": 34088 + }, + { + "epoch": 10.53, + "learning_rate": 9.631246431643007e-06, + "loss": 0.0131, + "step": 34089 + }, + { + "epoch": 10.53, + "learning_rate": 9.630746654023471e-06, + "loss": 0.0162, + "step": 34090 + }, + { + "epoch": 10.53, + "learning_rate": 9.63024687732751e-06, + "loss": 0.0144, + "step": 34091 + }, + { + "epoch": 10.53, + "learning_rate": 9.62974710155637e-06, + "loss": 0.0145, + "step": 34092 + }, + { + "epoch": 10.53, + "learning_rate": 9.629247326711297e-06, + "loss": 0.012, + "step": 34093 + }, + { + "epoch": 10.53, + "learning_rate": 9.62874755279354e-06, + "loss": 0.0169, + "step": 34094 + }, + { + "epoch": 10.53, + "learning_rate": 9.628247779804361e-06, + "loss": 0.0138, + "step": 34095 + }, + { + "epoch": 10.53, + "learning_rate": 9.627748007744999e-06, + "loss": 0.0138, + "step": 34096 + }, + { + "epoch": 10.53, + "learning_rate": 9.627248236616705e-06, + "loss": 0.0165, + "step": 34097 + }, + { + "epoch": 10.53, + "learning_rate": 9.626748466420734e-06, + "loss": 0.0156, + "step": 34098 + }, + { + "epoch": 10.53, + "learning_rate": 9.626248697158334e-06, + "loss": 0.0141, + "step": 34099 + }, + { + "epoch": 10.53, + "learning_rate": 9.62574892883075e-06, + "loss": 0.0151, + "step": 34100 + }, + { + "epoch": 10.53, + "learning_rate": 9.62524916143924e-06, + "loss": 0.0126, + "step": 34101 + }, + { + "epoch": 10.53, + "learning_rate": 9.624749394985048e-06, + "loss": 0.0123, + "step": 34102 + }, + { + "epoch": 10.53, + "learning_rate": 9.624249629469427e-06, + "loss": 0.0144, + "step": 34103 + }, + { + "epoch": 10.53, + "learning_rate": 9.62374986489363e-06, + "loss": 0.0145, + "step": 34104 + }, + { + "epoch": 10.53, + "learning_rate": 9.623250101258896e-06, + "loss": 0.0143, + "step": 34105 + }, + { + "epoch": 10.53, + "learning_rate": 9.622750338566486e-06, + "loss": 0.0135, + "step": 34106 + }, + { + "epoch": 10.53, + "learning_rate": 9.622250576817647e-06, + "loss": 0.0145, + "step": 34107 + }, + { + "epoch": 10.53, + "learning_rate": 9.621750816013625e-06, + "loss": 0.015, + "step": 34108 + }, + { + "epoch": 10.53, + "learning_rate": 9.621251056155675e-06, + "loss": 0.0142, + "step": 34109 + }, + { + "epoch": 10.53, + "learning_rate": 9.620751297245048e-06, + "loss": 0.0152, + "step": 34110 + }, + { + "epoch": 10.53, + "learning_rate": 9.620251539282987e-06, + "loss": 0.0167, + "step": 34111 + }, + { + "epoch": 10.53, + "learning_rate": 9.619751782270746e-06, + "loss": 0.0158, + "step": 34112 + }, + { + "epoch": 10.53, + "learning_rate": 9.61925202620958e-06, + "loss": 0.0147, + "step": 34113 + }, + { + "epoch": 10.54, + "learning_rate": 9.61875227110073e-06, + "loss": 0.0146, + "step": 34114 + }, + { + "epoch": 10.54, + "learning_rate": 9.61825251694545e-06, + "loss": 0.0143, + "step": 34115 + }, + { + "epoch": 10.54, + "learning_rate": 9.617752763744994e-06, + "loss": 0.0163, + "step": 34116 + }, + { + "epoch": 10.54, + "learning_rate": 9.617253011500605e-06, + "loss": 0.0159, + "step": 34117 + }, + { + "epoch": 10.54, + "learning_rate": 9.616753260213533e-06, + "loss": 0.015, + "step": 34118 + }, + { + "epoch": 10.54, + "learning_rate": 9.616253509885036e-06, + "loss": 0.0148, + "step": 34119 + }, + { + "epoch": 10.54, + "learning_rate": 9.615753760516358e-06, + "loss": 0.016, + "step": 34120 + }, + { + "epoch": 10.54, + "learning_rate": 9.615254012108746e-06, + "loss": 0.0155, + "step": 34121 + }, + { + "epoch": 10.54, + "learning_rate": 9.614754264663458e-06, + "loss": 0.0168, + "step": 34122 + }, + { + "epoch": 10.54, + "learning_rate": 9.614254518181741e-06, + "loss": 0.0134, + "step": 34123 + }, + { + "epoch": 10.54, + "learning_rate": 9.613754772664842e-06, + "loss": 0.0132, + "step": 34124 + }, + { + "epoch": 10.54, + "learning_rate": 9.61325502811401e-06, + "loss": 0.0176, + "step": 34125 + }, + { + "epoch": 10.54, + "learning_rate": 9.612755284530502e-06, + "loss": 0.0158, + "step": 34126 + }, + { + "epoch": 10.54, + "learning_rate": 9.612255541915562e-06, + "loss": 0.015, + "step": 34127 + }, + { + "epoch": 10.54, + "learning_rate": 9.611755800270439e-06, + "loss": 0.015, + "step": 34128 + }, + { + "epoch": 10.54, + "learning_rate": 9.61125605959639e-06, + "loss": 0.0157, + "step": 34129 + }, + { + "epoch": 10.54, + "learning_rate": 9.610756319894658e-06, + "loss": 0.0133, + "step": 34130 + }, + { + "epoch": 10.54, + "learning_rate": 9.610256581166495e-06, + "loss": 0.0154, + "step": 34131 + }, + { + "epoch": 10.54, + "learning_rate": 9.609756843413156e-06, + "loss": 0.0173, + "step": 34132 + }, + { + "epoch": 10.54, + "learning_rate": 9.60925710663588e-06, + "loss": 0.014, + "step": 34133 + }, + { + "epoch": 10.54, + "learning_rate": 9.608757370835926e-06, + "loss": 0.0161, + "step": 34134 + }, + { + "epoch": 10.54, + "learning_rate": 9.608257636014543e-06, + "loss": 0.0165, + "step": 34135 + }, + { + "epoch": 10.54, + "learning_rate": 9.607757902172975e-06, + "loss": 0.0144, + "step": 34136 + }, + { + "epoch": 10.54, + "learning_rate": 9.607258169312478e-06, + "loss": 0.0118, + "step": 34137 + }, + { + "epoch": 10.54, + "learning_rate": 9.606758437434303e-06, + "loss": 0.0162, + "step": 34138 + }, + { + "epoch": 10.54, + "learning_rate": 9.60625870653969e-06, + "loss": 0.0152, + "step": 34139 + }, + { + "epoch": 10.54, + "learning_rate": 9.6057589766299e-06, + "loss": 0.0158, + "step": 34140 + }, + { + "epoch": 10.54, + "learning_rate": 9.605259247706182e-06, + "loss": 0.0163, + "step": 34141 + }, + { + "epoch": 10.54, + "learning_rate": 9.604759519769779e-06, + "loss": 0.0162, + "step": 34142 + }, + { + "epoch": 10.54, + "learning_rate": 9.604259792821942e-06, + "loss": 0.0153, + "step": 34143 + }, + { + "epoch": 10.54, + "learning_rate": 9.603760066863927e-06, + "loss": 0.0137, + "step": 34144 + }, + { + "epoch": 10.54, + "learning_rate": 9.60326034189698e-06, + "loss": 0.0152, + "step": 34145 + }, + { + "epoch": 10.54, + "learning_rate": 9.602760617922349e-06, + "loss": 0.0178, + "step": 34146 + }, + { + "epoch": 10.55, + "learning_rate": 9.60226089494129e-06, + "loss": 0.0155, + "step": 34147 + }, + { + "epoch": 10.55, + "learning_rate": 9.601761172955046e-06, + "loss": 0.0154, + "step": 34148 + }, + { + "epoch": 10.55, + "learning_rate": 9.601261451964869e-06, + "loss": 0.0149, + "step": 34149 + }, + { + "epoch": 10.55, + "learning_rate": 9.600761731972013e-06, + "loss": 0.0142, + "step": 34150 + }, + { + "epoch": 10.55, + "learning_rate": 9.600262012977723e-06, + "loss": 0.0169, + "step": 34151 + }, + { + "epoch": 10.55, + "learning_rate": 9.59976229498325e-06, + "loss": 0.0148, + "step": 34152 + }, + { + "epoch": 10.55, + "learning_rate": 9.59926257798985e-06, + "loss": 0.0155, + "step": 34153 + }, + { + "epoch": 10.55, + "learning_rate": 9.59876286199876e-06, + "loss": 0.015, + "step": 34154 + }, + { + "epoch": 10.55, + "learning_rate": 9.59826314701124e-06, + "loss": 0.0154, + "step": 34155 + }, + { + "epoch": 10.55, + "learning_rate": 9.597763433028535e-06, + "loss": 0.0144, + "step": 34156 + }, + { + "epoch": 10.55, + "learning_rate": 9.597263720051901e-06, + "loss": 0.0139, + "step": 34157 + }, + { + "epoch": 10.55, + "learning_rate": 9.596764008082582e-06, + "loss": 0.0151, + "step": 34158 + }, + { + "epoch": 10.55, + "learning_rate": 9.596264297121827e-06, + "loss": 0.0134, + "step": 34159 + }, + { + "epoch": 10.55, + "learning_rate": 9.595764587170895e-06, + "loss": 0.0135, + "step": 34160 + }, + { + "epoch": 10.55, + "learning_rate": 9.595264878231025e-06, + "loss": 0.0152, + "step": 34161 + }, + { + "epoch": 10.55, + "learning_rate": 9.594765170303471e-06, + "loss": 0.0174, + "step": 34162 + }, + { + "epoch": 10.55, + "learning_rate": 9.594265463389489e-06, + "loss": 0.0149, + "step": 34163 + }, + { + "epoch": 10.55, + "learning_rate": 9.593765757490317e-06, + "loss": 0.0135, + "step": 34164 + }, + { + "epoch": 10.55, + "learning_rate": 9.593266052607213e-06, + "loss": 0.0128, + "step": 34165 + }, + { + "epoch": 10.55, + "learning_rate": 9.592766348741426e-06, + "loss": 0.0137, + "step": 34166 + }, + { + "epoch": 10.55, + "learning_rate": 9.5922666458942e-06, + "loss": 0.0146, + "step": 34167 + }, + { + "epoch": 10.55, + "learning_rate": 9.591766944066793e-06, + "loss": 0.0154, + "step": 34168 + }, + { + "epoch": 10.55, + "learning_rate": 9.591267243260453e-06, + "loss": 0.0163, + "step": 34169 + }, + { + "epoch": 10.55, + "learning_rate": 9.590767543476423e-06, + "loss": 0.0141, + "step": 34170 + }, + { + "epoch": 10.55, + "learning_rate": 9.590267844715962e-06, + "loss": 0.0157, + "step": 34171 + }, + { + "epoch": 10.55, + "learning_rate": 9.589768146980316e-06, + "loss": 0.0135, + "step": 34172 + }, + { + "epoch": 10.55, + "learning_rate": 9.589268450270735e-06, + "loss": 0.0145, + "step": 34173 + }, + { + "epoch": 10.55, + "learning_rate": 9.588768754588464e-06, + "loss": 0.0157, + "step": 34174 + }, + { + "epoch": 10.55, + "learning_rate": 9.588269059934763e-06, + "loss": 0.0151, + "step": 34175 + }, + { + "epoch": 10.55, + "learning_rate": 9.587769366310872e-06, + "loss": 0.0168, + "step": 34176 + }, + { + "epoch": 10.55, + "learning_rate": 9.587269673718045e-06, + "loss": 0.0145, + "step": 34177 + }, + { + "epoch": 10.55, + "learning_rate": 9.586769982157536e-06, + "loss": 0.0143, + "step": 34178 + }, + { + "epoch": 10.56, + "learning_rate": 9.586270291630589e-06, + "loss": 0.0159, + "step": 34179 + }, + { + "epoch": 10.56, + "learning_rate": 9.585770602138451e-06, + "loss": 0.0138, + "step": 34180 + }, + { + "epoch": 10.56, + "learning_rate": 9.585270913682384e-06, + "loss": 0.0142, + "step": 34181 + }, + { + "epoch": 10.56, + "learning_rate": 9.584771226263624e-06, + "loss": 0.0151, + "step": 34182 + }, + { + "epoch": 10.56, + "learning_rate": 9.584271539883428e-06, + "loss": 0.0167, + "step": 34183 + }, + { + "epoch": 10.56, + "learning_rate": 9.583771854543048e-06, + "loss": 0.0171, + "step": 34184 + }, + { + "epoch": 10.56, + "learning_rate": 9.583272170243726e-06, + "loss": 0.0173, + "step": 34185 + }, + { + "epoch": 10.56, + "learning_rate": 9.582772486986718e-06, + "loss": 0.015, + "step": 34186 + }, + { + "epoch": 10.56, + "learning_rate": 9.58227280477327e-06, + "loss": 0.0154, + "step": 34187 + }, + { + "epoch": 10.56, + "learning_rate": 9.58177312360464e-06, + "loss": 0.0144, + "step": 34188 + }, + { + "epoch": 10.56, + "learning_rate": 9.581273443482067e-06, + "loss": 0.0149, + "step": 34189 + }, + { + "epoch": 10.56, + "learning_rate": 9.580773764406804e-06, + "loss": 0.016, + "step": 34190 + }, + { + "epoch": 10.56, + "learning_rate": 9.58027408638011e-06, + "loss": 0.0157, + "step": 34191 + }, + { + "epoch": 10.56, + "learning_rate": 9.579774409403219e-06, + "loss": 0.0156, + "step": 34192 + }, + { + "epoch": 10.56, + "learning_rate": 9.579274733477392e-06, + "loss": 0.0177, + "step": 34193 + }, + { + "epoch": 10.56, + "learning_rate": 9.578775058603877e-06, + "loss": 0.0139, + "step": 34194 + }, + { + "epoch": 10.56, + "learning_rate": 9.57827538478392e-06, + "loss": 0.0152, + "step": 34195 + }, + { + "epoch": 10.56, + "learning_rate": 9.577775712018774e-06, + "loss": 0.0143, + "step": 34196 + }, + { + "epoch": 10.56, + "learning_rate": 9.577276040309688e-06, + "loss": 0.0125, + "step": 34197 + }, + { + "epoch": 10.56, + "learning_rate": 9.57677636965791e-06, + "loss": 0.0151, + "step": 34198 + }, + { + "epoch": 10.56, + "learning_rate": 9.576276700064692e-06, + "loss": 0.015, + "step": 34199 + }, + { + "epoch": 10.56, + "learning_rate": 9.575777031531289e-06, + "loss": 0.0173, + "step": 34200 + }, + { + "epoch": 10.56, + "learning_rate": 9.575277364058937e-06, + "loss": 0.0148, + "step": 34201 + }, + { + "epoch": 10.56, + "learning_rate": 9.574777697648898e-06, + "loss": 0.0147, + "step": 34202 + }, + { + "epoch": 10.56, + "learning_rate": 9.574278032302417e-06, + "loss": 0.0163, + "step": 34203 + }, + { + "epoch": 10.56, + "learning_rate": 9.573778368020745e-06, + "loss": 0.0154, + "step": 34204 + }, + { + "epoch": 10.56, + "learning_rate": 9.573278704805126e-06, + "loss": 0.0147, + "step": 34205 + }, + { + "epoch": 10.56, + "learning_rate": 9.572779042656822e-06, + "loss": 0.0172, + "step": 34206 + }, + { + "epoch": 10.56, + "learning_rate": 9.572279381577073e-06, + "loss": 0.0149, + "step": 34207 + }, + { + "epoch": 10.56, + "learning_rate": 9.571779721567128e-06, + "loss": 0.0163, + "step": 34208 + }, + { + "epoch": 10.56, + "learning_rate": 9.571280062628244e-06, + "loss": 0.0128, + "step": 34209 + }, + { + "epoch": 10.56, + "learning_rate": 9.570780404761665e-06, + "loss": 0.0166, + "step": 34210 + }, + { + "epoch": 10.57, + "learning_rate": 9.570280747968642e-06, + "loss": 0.0133, + "step": 34211 + }, + { + "epoch": 10.57, + "learning_rate": 9.56978109225043e-06, + "loss": 0.0123, + "step": 34212 + }, + { + "epoch": 10.57, + "learning_rate": 9.569281437608267e-06, + "loss": 0.0149, + "step": 34213 + }, + { + "epoch": 10.57, + "learning_rate": 9.568781784043414e-06, + "loss": 0.0173, + "step": 34214 + }, + { + "epoch": 10.57, + "learning_rate": 9.568282131557117e-06, + "loss": 0.0123, + "step": 34215 + }, + { + "epoch": 10.57, + "learning_rate": 9.56778248015062e-06, + "loss": 0.014, + "step": 34216 + }, + { + "epoch": 10.57, + "learning_rate": 9.567282829825181e-06, + "loss": 0.0167, + "step": 34217 + }, + { + "epoch": 10.57, + "learning_rate": 9.56678318058205e-06, + "loss": 0.0157, + "step": 34218 + }, + { + "epoch": 10.57, + "learning_rate": 9.566283532422468e-06, + "loss": 0.0161, + "step": 34219 + }, + { + "epoch": 10.57, + "learning_rate": 9.56578388534769e-06, + "loss": 0.0162, + "step": 34220 + }, + { + "epoch": 10.57, + "learning_rate": 9.565284239358966e-06, + "loss": 0.016, + "step": 34221 + }, + { + "epoch": 10.57, + "learning_rate": 9.564784594457553e-06, + "loss": 0.0162, + "step": 34222 + }, + { + "epoch": 10.57, + "learning_rate": 9.564284950644684e-06, + "loss": 0.0152, + "step": 34223 + }, + { + "epoch": 10.57, + "learning_rate": 9.563785307921622e-06, + "loss": 0.0148, + "step": 34224 + }, + { + "epoch": 10.57, + "learning_rate": 9.563285666289612e-06, + "loss": 0.0135, + "step": 34225 + }, + { + "epoch": 10.57, + "learning_rate": 9.562786025749901e-06, + "loss": 0.0183, + "step": 34226 + }, + { + "epoch": 10.57, + "learning_rate": 9.562286386303745e-06, + "loss": 0.0155, + "step": 34227 + }, + { + "epoch": 10.57, + "learning_rate": 9.561786747952394e-06, + "loss": 0.0144, + "step": 34228 + }, + { + "epoch": 10.57, + "learning_rate": 9.561287110697088e-06, + "loss": 0.0141, + "step": 34229 + }, + { + "epoch": 10.57, + "learning_rate": 9.560787474539083e-06, + "loss": 0.0141, + "step": 34230 + }, + { + "epoch": 10.57, + "learning_rate": 9.560287839479634e-06, + "loss": 0.0166, + "step": 34231 + }, + { + "epoch": 10.57, + "learning_rate": 9.559788205519983e-06, + "loss": 0.0137, + "step": 34232 + }, + { + "epoch": 10.57, + "learning_rate": 9.559288572661378e-06, + "loss": 0.016, + "step": 34233 + }, + { + "epoch": 10.57, + "learning_rate": 9.55878894090508e-06, + "loss": 0.014, + "step": 34234 + }, + { + "epoch": 10.57, + "learning_rate": 9.558289310252327e-06, + "loss": 0.0146, + "step": 34235 + }, + { + "epoch": 10.57, + "learning_rate": 9.55778968070437e-06, + "loss": 0.0156, + "step": 34236 + }, + { + "epoch": 10.57, + "learning_rate": 9.557290052262467e-06, + "loss": 0.0162, + "step": 34237 + }, + { + "epoch": 10.57, + "learning_rate": 9.556790424927862e-06, + "loss": 0.0162, + "step": 34238 + }, + { + "epoch": 10.57, + "learning_rate": 9.5562907987018e-06, + "loss": 0.0138, + "step": 34239 + }, + { + "epoch": 10.57, + "learning_rate": 9.55579117358554e-06, + "loss": 0.0157, + "step": 34240 + }, + { + "epoch": 10.57, + "learning_rate": 9.555291549580326e-06, + "loss": 0.016, + "step": 34241 + }, + { + "epoch": 10.57, + "learning_rate": 9.55479192668741e-06, + "loss": 0.0141, + "step": 34242 + }, + { + "epoch": 10.57, + "learning_rate": 9.554292304908042e-06, + "loss": 0.0146, + "step": 34243 + }, + { + "epoch": 10.58, + "learning_rate": 9.553792684243465e-06, + "loss": 0.0156, + "step": 34244 + }, + { + "epoch": 10.58, + "learning_rate": 9.553293064694938e-06, + "loss": 0.0164, + "step": 34245 + }, + { + "epoch": 10.58, + "learning_rate": 9.552793446263706e-06, + "loss": 0.0162, + "step": 34246 + }, + { + "epoch": 10.58, + "learning_rate": 9.552293828951017e-06, + "loss": 0.0142, + "step": 34247 + }, + { + "epoch": 10.58, + "learning_rate": 9.551794212758124e-06, + "loss": 0.0162, + "step": 34248 + }, + { + "epoch": 10.58, + "learning_rate": 9.551294597686278e-06, + "loss": 0.0161, + "step": 34249 + }, + { + "epoch": 10.58, + "learning_rate": 9.550794983736722e-06, + "loss": 0.0135, + "step": 34250 + }, + { + "epoch": 10.58, + "learning_rate": 9.550295370910712e-06, + "loss": 0.016, + "step": 34251 + }, + { + "epoch": 10.58, + "learning_rate": 9.549795759209494e-06, + "loss": 0.0144, + "step": 34252 + }, + { + "epoch": 10.58, + "learning_rate": 9.549296148634322e-06, + "loss": 0.0154, + "step": 34253 + }, + { + "epoch": 10.58, + "learning_rate": 9.548796539186437e-06, + "loss": 0.0147, + "step": 34254 + }, + { + "epoch": 10.58, + "learning_rate": 9.548296930867099e-06, + "loss": 0.0157, + "step": 34255 + }, + { + "epoch": 10.58, + "learning_rate": 9.547797323677553e-06, + "loss": 0.0147, + "step": 34256 + }, + { + "epoch": 10.58, + "learning_rate": 9.547297717619045e-06, + "loss": 0.0136, + "step": 34257 + }, + { + "epoch": 10.58, + "learning_rate": 9.546798112692827e-06, + "loss": 0.018, + "step": 34258 + }, + { + "epoch": 10.58, + "learning_rate": 9.546298508900154e-06, + "loss": 0.014, + "step": 34259 + }, + { + "epoch": 10.58, + "learning_rate": 9.545798906242269e-06, + "loss": 0.0167, + "step": 34260 + }, + { + "epoch": 10.58, + "learning_rate": 9.545299304720423e-06, + "loss": 0.0164, + "step": 34261 + }, + { + "epoch": 10.58, + "learning_rate": 9.54479970433587e-06, + "loss": 0.0136, + "step": 34262 + }, + { + "epoch": 10.58, + "learning_rate": 9.544300105089853e-06, + "loss": 0.0146, + "step": 34263 + }, + { + "epoch": 10.58, + "learning_rate": 9.543800506983622e-06, + "loss": 0.0131, + "step": 34264 + }, + { + "epoch": 10.58, + "learning_rate": 9.543300910018435e-06, + "loss": 0.0139, + "step": 34265 + }, + { + "epoch": 10.58, + "learning_rate": 9.542801314195532e-06, + "loss": 0.0157, + "step": 34266 + }, + { + "epoch": 10.58, + "learning_rate": 9.542301719516165e-06, + "loss": 0.0168, + "step": 34267 + }, + { + "epoch": 10.58, + "learning_rate": 9.54180212598159e-06, + "loss": 0.0179, + "step": 34268 + }, + { + "epoch": 10.58, + "learning_rate": 9.541302533593047e-06, + "loss": 0.0162, + "step": 34269 + }, + { + "epoch": 10.58, + "learning_rate": 9.54080294235179e-06, + "loss": 0.0137, + "step": 34270 + }, + { + "epoch": 10.58, + "learning_rate": 9.540303352259074e-06, + "loss": 0.0168, + "step": 34271 + }, + { + "epoch": 10.58, + "learning_rate": 9.539803763316137e-06, + "loss": 0.013, + "step": 34272 + }, + { + "epoch": 10.58, + "learning_rate": 9.539304175524237e-06, + "loss": 0.0138, + "step": 34273 + }, + { + "epoch": 10.58, + "learning_rate": 9.538804588884624e-06, + "loss": 0.0173, + "step": 34274 + }, + { + "epoch": 10.58, + "learning_rate": 9.538305003398539e-06, + "loss": 0.017, + "step": 34275 + }, + { + "epoch": 10.59, + "learning_rate": 9.537805419067239e-06, + "loss": 0.0151, + "step": 34276 + }, + { + "epoch": 10.59, + "learning_rate": 9.537305835891977e-06, + "loss": 0.014, + "step": 34277 + }, + { + "epoch": 10.59, + "learning_rate": 9.536806253873992e-06, + "loss": 0.0136, + "step": 34278 + }, + { + "epoch": 10.59, + "learning_rate": 9.53630667301454e-06, + "loss": 0.0148, + "step": 34279 + }, + { + "epoch": 10.59, + "learning_rate": 9.535807093314872e-06, + "loss": 0.0161, + "step": 34280 + }, + { + "epoch": 10.59, + "learning_rate": 9.535307514776234e-06, + "loss": 0.0173, + "step": 34281 + }, + { + "epoch": 10.59, + "learning_rate": 9.534807937399875e-06, + "loss": 0.014, + "step": 34282 + }, + { + "epoch": 10.59, + "learning_rate": 9.534308361187049e-06, + "loss": 0.0146, + "step": 34283 + }, + { + "epoch": 10.59, + "learning_rate": 9.533808786139e-06, + "loss": 0.0159, + "step": 34284 + }, + { + "epoch": 10.59, + "learning_rate": 9.53330921225698e-06, + "loss": 0.0173, + "step": 34285 + }, + { + "epoch": 10.59, + "learning_rate": 9.53280963954224e-06, + "loss": 0.0126, + "step": 34286 + }, + { + "epoch": 10.59, + "learning_rate": 9.532310067996032e-06, + "loss": 0.0154, + "step": 34287 + }, + { + "epoch": 10.59, + "learning_rate": 9.531810497619595e-06, + "loss": 0.0149, + "step": 34288 + }, + { + "epoch": 10.59, + "learning_rate": 9.53131092841419e-06, + "loss": 0.0139, + "step": 34289 + }, + { + "epoch": 10.59, + "learning_rate": 9.53081136038106e-06, + "loss": 0.0135, + "step": 34290 + }, + { + "epoch": 10.59, + "learning_rate": 9.530311793521459e-06, + "loss": 0.0159, + "step": 34291 + }, + { + "epoch": 10.59, + "learning_rate": 9.529812227836629e-06, + "loss": 0.0154, + "step": 34292 + }, + { + "epoch": 10.59, + "learning_rate": 9.529312663327828e-06, + "loss": 0.0141, + "step": 34293 + }, + { + "epoch": 10.59, + "learning_rate": 9.528813099996302e-06, + "loss": 0.0161, + "step": 34294 + }, + { + "epoch": 10.59, + "learning_rate": 9.528313537843296e-06, + "loss": 0.0152, + "step": 34295 + }, + { + "epoch": 10.59, + "learning_rate": 9.52781397687007e-06, + "loss": 0.0156, + "step": 34296 + }, + { + "epoch": 10.59, + "learning_rate": 9.527314417077866e-06, + "loss": 0.0202, + "step": 34297 + }, + { + "epoch": 10.59, + "learning_rate": 9.52681485846793e-06, + "loss": 0.0164, + "step": 34298 + }, + { + "epoch": 10.59, + "learning_rate": 9.526315301041522e-06, + "loss": 0.0145, + "step": 34299 + }, + { + "epoch": 10.59, + "learning_rate": 9.525815744799883e-06, + "loss": 0.017, + "step": 34300 + }, + { + "epoch": 10.59, + "learning_rate": 9.525316189744268e-06, + "loss": 0.015, + "step": 34301 + }, + { + "epoch": 10.59, + "learning_rate": 9.524816635875924e-06, + "loss": 0.0131, + "step": 34302 + }, + { + "epoch": 10.59, + "learning_rate": 9.524317083196094e-06, + "loss": 0.0162, + "step": 34303 + }, + { + "epoch": 10.59, + "learning_rate": 9.523817531706037e-06, + "loss": 0.0166, + "step": 34304 + }, + { + "epoch": 10.59, + "learning_rate": 9.523317981407003e-06, + "loss": 0.0136, + "step": 34305 + }, + { + "epoch": 10.59, + "learning_rate": 9.522818432300233e-06, + "loss": 0.0146, + "step": 34306 + }, + { + "epoch": 10.59, + "learning_rate": 9.522318884386981e-06, + "loss": 0.0157, + "step": 34307 + }, + { + "epoch": 10.59, + "learning_rate": 9.521819337668501e-06, + "loss": 0.0164, + "step": 34308 + }, + { + "epoch": 10.6, + "learning_rate": 9.521319792146034e-06, + "loss": 0.0159, + "step": 34309 + }, + { + "epoch": 10.6, + "learning_rate": 9.520820247820834e-06, + "loss": 0.0153, + "step": 34310 + }, + { + "epoch": 10.6, + "learning_rate": 9.520320704694154e-06, + "loss": 0.0159, + "step": 34311 + }, + { + "epoch": 10.6, + "learning_rate": 9.519821162767236e-06, + "loss": 0.0152, + "step": 34312 + }, + { + "epoch": 10.6, + "learning_rate": 9.519321622041331e-06, + "loss": 0.0177, + "step": 34313 + }, + { + "epoch": 10.6, + "learning_rate": 9.518822082517695e-06, + "loss": 0.0131, + "step": 34314 + }, + { + "epoch": 10.6, + "learning_rate": 9.51832254419757e-06, + "loss": 0.013, + "step": 34315 + }, + { + "epoch": 10.6, + "learning_rate": 9.517823007082205e-06, + "loss": 0.0151, + "step": 34316 + }, + { + "epoch": 10.6, + "learning_rate": 9.517323471172855e-06, + "loss": 0.0143, + "step": 34317 + }, + { + "epoch": 10.6, + "learning_rate": 9.516823936470771e-06, + "loss": 0.0154, + "step": 34318 + }, + { + "epoch": 10.6, + "learning_rate": 9.516324402977193e-06, + "loss": 0.0147, + "step": 34319 + }, + { + "epoch": 10.6, + "learning_rate": 9.515824870693378e-06, + "loss": 0.0148, + "step": 34320 + }, + { + "epoch": 10.6, + "learning_rate": 9.515325339620576e-06, + "loss": 0.0145, + "step": 34321 + }, + { + "epoch": 10.6, + "learning_rate": 9.51482580976003e-06, + "loss": 0.0131, + "step": 34322 + }, + { + "epoch": 10.6, + "learning_rate": 9.514326281112994e-06, + "loss": 0.0161, + "step": 34323 + }, + { + "epoch": 10.6, + "learning_rate": 9.513826753680719e-06, + "loss": 0.014, + "step": 34324 + }, + { + "epoch": 10.6, + "learning_rate": 9.51332722746445e-06, + "loss": 0.0164, + "step": 34325 + }, + { + "epoch": 10.6, + "learning_rate": 9.512827702465437e-06, + "loss": 0.0153, + "step": 34326 + }, + { + "epoch": 10.6, + "learning_rate": 9.512328178684933e-06, + "loss": 0.0142, + "step": 34327 + }, + { + "epoch": 10.6, + "learning_rate": 9.511828656124185e-06, + "loss": 0.0156, + "step": 34328 + }, + { + "epoch": 10.6, + "learning_rate": 9.511329134784439e-06, + "loss": 0.0187, + "step": 34329 + }, + { + "epoch": 10.6, + "learning_rate": 9.510829614666956e-06, + "loss": 0.0157, + "step": 34330 + }, + { + "epoch": 10.6, + "learning_rate": 9.51033009577297e-06, + "loss": 0.0137, + "step": 34331 + }, + { + "epoch": 10.6, + "learning_rate": 9.50983057810374e-06, + "loss": 0.0136, + "step": 34332 + }, + { + "epoch": 10.6, + "learning_rate": 9.509331061660514e-06, + "loss": 0.0148, + "step": 34333 + }, + { + "epoch": 10.6, + "learning_rate": 9.508831546444537e-06, + "loss": 0.0159, + "step": 34334 + }, + { + "epoch": 10.6, + "learning_rate": 9.508332032457065e-06, + "loss": 0.0152, + "step": 34335 + }, + { + "epoch": 10.6, + "learning_rate": 9.507832519699347e-06, + "loss": 0.0153, + "step": 34336 + }, + { + "epoch": 10.6, + "learning_rate": 9.507333008172623e-06, + "loss": 0.0141, + "step": 34337 + }, + { + "epoch": 10.6, + "learning_rate": 9.506833497878152e-06, + "loss": 0.0139, + "step": 34338 + }, + { + "epoch": 10.6, + "learning_rate": 9.506333988817182e-06, + "loss": 0.0143, + "step": 34339 + }, + { + "epoch": 10.6, + "learning_rate": 9.50583448099096e-06, + "loss": 0.0146, + "step": 34340 + }, + { + "epoch": 10.61, + "learning_rate": 9.505334974400732e-06, + "loss": 0.0157, + "step": 34341 + }, + { + "epoch": 10.61, + "learning_rate": 9.504835469047759e-06, + "loss": 0.0151, + "step": 34342 + }, + { + "epoch": 10.61, + "learning_rate": 9.504335964933278e-06, + "loss": 0.0167, + "step": 34343 + }, + { + "epoch": 10.61, + "learning_rate": 9.503836462058542e-06, + "loss": 0.0144, + "step": 34344 + }, + { + "epoch": 10.61, + "learning_rate": 9.503336960424805e-06, + "loss": 0.0169, + "step": 34345 + }, + { + "epoch": 10.61, + "learning_rate": 9.502837460033312e-06, + "loss": 0.0163, + "step": 34346 + }, + { + "epoch": 10.61, + "learning_rate": 9.502337960885309e-06, + "loss": 0.0165, + "step": 34347 + }, + { + "epoch": 10.61, + "learning_rate": 9.501838462982056e-06, + "loss": 0.0136, + "step": 34348 + }, + { + "epoch": 10.61, + "learning_rate": 9.501338966324792e-06, + "loss": 0.0164, + "step": 34349 + }, + { + "epoch": 10.61, + "learning_rate": 9.500839470914773e-06, + "loss": 0.0177, + "step": 34350 + }, + { + "epoch": 10.61, + "learning_rate": 9.50033997675324e-06, + "loss": 0.0145, + "step": 34351 + }, + { + "epoch": 10.61, + "learning_rate": 9.499840483841453e-06, + "loss": 0.0133, + "step": 34352 + }, + { + "epoch": 10.61, + "learning_rate": 9.499340992180655e-06, + "loss": 0.0149, + "step": 34353 + }, + { + "epoch": 10.61, + "learning_rate": 9.498841501772094e-06, + "loss": 0.0162, + "step": 34354 + }, + { + "epoch": 10.61, + "learning_rate": 9.498342012617025e-06, + "loss": 0.0136, + "step": 34355 + }, + { + "epoch": 10.61, + "learning_rate": 9.497842524716695e-06, + "loss": 0.0158, + "step": 34356 + }, + { + "epoch": 10.61, + "learning_rate": 9.497343038072348e-06, + "loss": 0.0169, + "step": 34357 + }, + { + "epoch": 10.61, + "learning_rate": 9.496843552685242e-06, + "loss": 0.0152, + "step": 34358 + }, + { + "epoch": 10.61, + "learning_rate": 9.49634406855662e-06, + "loss": 0.0138, + "step": 34359 + }, + { + "epoch": 10.61, + "learning_rate": 9.495844585687733e-06, + "loss": 0.0131, + "step": 34360 + }, + { + "epoch": 10.61, + "learning_rate": 9.495345104079834e-06, + "loss": 0.0147, + "step": 34361 + }, + { + "epoch": 10.61, + "learning_rate": 9.494845623734163e-06, + "loss": 0.0158, + "step": 34362 + }, + { + "epoch": 10.61, + "learning_rate": 9.49434614465198e-06, + "loss": 0.0176, + "step": 34363 + }, + { + "epoch": 10.61, + "learning_rate": 9.49384666683453e-06, + "loss": 0.0187, + "step": 34364 + }, + { + "epoch": 10.61, + "learning_rate": 9.493347190283056e-06, + "loss": 0.0157, + "step": 34365 + }, + { + "epoch": 10.61, + "learning_rate": 9.492847714998817e-06, + "loss": 0.018, + "step": 34366 + }, + { + "epoch": 10.61, + "learning_rate": 9.49234824098306e-06, + "loss": 0.0161, + "step": 34367 + }, + { + "epoch": 10.61, + "learning_rate": 9.491848768237029e-06, + "loss": 0.016, + "step": 34368 + }, + { + "epoch": 10.61, + "learning_rate": 9.491349296761978e-06, + "loss": 0.0137, + "step": 34369 + }, + { + "epoch": 10.61, + "learning_rate": 9.49084982655916e-06, + "loss": 0.0163, + "step": 34370 + }, + { + "epoch": 10.61, + "learning_rate": 9.490350357629814e-06, + "loss": 0.0167, + "step": 34371 + }, + { + "epoch": 10.61, + "learning_rate": 9.489850889975194e-06, + "loss": 0.0165, + "step": 34372 + }, + { + "epoch": 10.62, + "learning_rate": 9.489351423596554e-06, + "loss": 0.0143, + "step": 34373 + }, + { + "epoch": 10.62, + "learning_rate": 9.488851958495139e-06, + "loss": 0.0157, + "step": 34374 + }, + { + "epoch": 10.62, + "learning_rate": 9.488352494672192e-06, + "loss": 0.0154, + "step": 34375 + }, + { + "epoch": 10.62, + "learning_rate": 9.487853032128977e-06, + "loss": 0.0157, + "step": 34376 + }, + { + "epoch": 10.62, + "learning_rate": 9.487353570866731e-06, + "loss": 0.0139, + "step": 34377 + }, + { + "epoch": 10.62, + "learning_rate": 9.486854110886706e-06, + "loss": 0.0162, + "step": 34378 + }, + { + "epoch": 10.62, + "learning_rate": 9.486354652190157e-06, + "loss": 0.0156, + "step": 34379 + }, + { + "epoch": 10.62, + "learning_rate": 9.485855194778323e-06, + "loss": 0.0153, + "step": 34380 + }, + { + "epoch": 10.62, + "learning_rate": 9.485355738652464e-06, + "loss": 0.0151, + "step": 34381 + }, + { + "epoch": 10.62, + "learning_rate": 9.484856283813823e-06, + "loss": 0.0146, + "step": 34382 + }, + { + "epoch": 10.62, + "learning_rate": 9.484356830263646e-06, + "loss": 0.014, + "step": 34383 + }, + { + "epoch": 10.62, + "learning_rate": 9.483857378003191e-06, + "loss": 0.018, + "step": 34384 + }, + { + "epoch": 10.62, + "learning_rate": 9.4833579270337e-06, + "loss": 0.0162, + "step": 34385 + }, + { + "epoch": 10.62, + "learning_rate": 9.482858477356428e-06, + "loss": 0.0158, + "step": 34386 + }, + { + "epoch": 10.62, + "learning_rate": 9.48235902897262e-06, + "loss": 0.0152, + "step": 34387 + }, + { + "epoch": 10.62, + "learning_rate": 9.481859581883524e-06, + "loss": 0.0166, + "step": 34388 + }, + { + "epoch": 10.62, + "learning_rate": 9.4813601360904e-06, + "loss": 0.0168, + "step": 34389 + }, + { + "epoch": 10.62, + "learning_rate": 9.48086069159448e-06, + "loss": 0.0138, + "step": 34390 + }, + { + "epoch": 10.62, + "learning_rate": 9.480361248397025e-06, + "loss": 0.0127, + "step": 34391 + }, + { + "epoch": 10.62, + "learning_rate": 9.479861806499284e-06, + "loss": 0.0139, + "step": 34392 + }, + { + "epoch": 10.62, + "learning_rate": 9.479362365902498e-06, + "loss": 0.016, + "step": 34393 + }, + { + "epoch": 10.62, + "learning_rate": 9.478862926607926e-06, + "loss": 0.0176, + "step": 34394 + }, + { + "epoch": 10.62, + "learning_rate": 9.478363488616813e-06, + "loss": 0.0148, + "step": 34395 + }, + { + "epoch": 10.62, + "learning_rate": 9.477864051930405e-06, + "loss": 0.0159, + "step": 34396 + }, + { + "epoch": 10.62, + "learning_rate": 9.477364616549956e-06, + "loss": 0.0152, + "step": 34397 + }, + { + "epoch": 10.62, + "learning_rate": 9.476865182476714e-06, + "loss": 0.0165, + "step": 34398 + }, + { + "epoch": 10.62, + "learning_rate": 9.476365749711928e-06, + "loss": 0.0144, + "step": 34399 + }, + { + "epoch": 10.62, + "learning_rate": 9.475866318256842e-06, + "loss": 0.0171, + "step": 34400 + }, + { + "epoch": 10.62, + "learning_rate": 9.475366888112716e-06, + "loss": 0.0167, + "step": 34401 + }, + { + "epoch": 10.62, + "learning_rate": 9.474867459280791e-06, + "loss": 0.0159, + "step": 34402 + }, + { + "epoch": 10.62, + "learning_rate": 9.474368031762315e-06, + "loss": 0.015, + "step": 34403 + }, + { + "epoch": 10.62, + "learning_rate": 9.473868605558547e-06, + "loss": 0.0177, + "step": 34404 + }, + { + "epoch": 10.62, + "learning_rate": 9.473369180670725e-06, + "loss": 0.0157, + "step": 34405 + }, + { + "epoch": 10.63, + "learning_rate": 9.472869757100102e-06, + "loss": 0.0157, + "step": 34406 + }, + { + "epoch": 10.63, + "learning_rate": 9.472370334847932e-06, + "loss": 0.0148, + "step": 34407 + }, + { + "epoch": 10.63, + "learning_rate": 9.471870913915456e-06, + "loss": 0.0148, + "step": 34408 + }, + { + "epoch": 10.63, + "learning_rate": 9.47137149430393e-06, + "loss": 0.0147, + "step": 34409 + }, + { + "epoch": 10.63, + "learning_rate": 9.470872076014601e-06, + "loss": 0.0135, + "step": 34410 + }, + { + "epoch": 10.63, + "learning_rate": 9.470372659048713e-06, + "loss": 0.0144, + "step": 34411 + }, + { + "epoch": 10.63, + "learning_rate": 9.469873243407521e-06, + "loss": 0.0137, + "step": 34412 + }, + { + "epoch": 10.63, + "learning_rate": 9.469373829092277e-06, + "loss": 0.0163, + "step": 34413 + }, + { + "epoch": 10.63, + "learning_rate": 9.46887441610422e-06, + "loss": 0.0155, + "step": 34414 + }, + { + "epoch": 10.63, + "learning_rate": 9.468375004444608e-06, + "loss": 0.0173, + "step": 34415 + }, + { + "epoch": 10.63, + "learning_rate": 9.467875594114684e-06, + "loss": 0.0148, + "step": 34416 + }, + { + "epoch": 10.63, + "learning_rate": 9.467376185115706e-06, + "loss": 0.0144, + "step": 34417 + }, + { + "epoch": 10.63, + "learning_rate": 9.466876777448913e-06, + "loss": 0.0208, + "step": 34418 + }, + { + "epoch": 10.63, + "learning_rate": 9.466377371115556e-06, + "loss": 0.0151, + "step": 34419 + }, + { + "epoch": 10.63, + "learning_rate": 9.465877966116895e-06, + "loss": 0.0147, + "step": 34420 + }, + { + "epoch": 10.63, + "learning_rate": 9.465378562454164e-06, + "loss": 0.0174, + "step": 34421 + }, + { + "epoch": 10.63, + "learning_rate": 9.46487916012862e-06, + "loss": 0.0145, + "step": 34422 + }, + { + "epoch": 10.63, + "learning_rate": 9.464379759141515e-06, + "loss": 0.0155, + "step": 34423 + }, + { + "epoch": 10.63, + "learning_rate": 9.463880359494086e-06, + "loss": 0.0155, + "step": 34424 + }, + { + "epoch": 10.63, + "learning_rate": 9.463380961187595e-06, + "loss": 0.0127, + "step": 34425 + }, + { + "epoch": 10.63, + "learning_rate": 9.462881564223288e-06, + "loss": 0.0165, + "step": 34426 + }, + { + "epoch": 10.63, + "learning_rate": 9.462382168602406e-06, + "loss": 0.0149, + "step": 34427 + }, + { + "epoch": 10.63, + "learning_rate": 9.461882774326208e-06, + "loss": 0.0163, + "step": 34428 + }, + { + "epoch": 10.63, + "learning_rate": 9.461383381395942e-06, + "loss": 0.0151, + "step": 34429 + }, + { + "epoch": 10.63, + "learning_rate": 9.46088398981285e-06, + "loss": 0.0146, + "step": 34430 + }, + { + "epoch": 10.63, + "learning_rate": 9.460384599578185e-06, + "loss": 0.0199, + "step": 34431 + }, + { + "epoch": 10.63, + "learning_rate": 9.459885210693201e-06, + "loss": 0.0156, + "step": 34432 + }, + { + "epoch": 10.63, + "learning_rate": 9.45938582315914e-06, + "loss": 0.0132, + "step": 34433 + }, + { + "epoch": 10.63, + "learning_rate": 9.458886436977252e-06, + "loss": 0.0158, + "step": 34434 + }, + { + "epoch": 10.63, + "learning_rate": 9.458387052148791e-06, + "loss": 0.0143, + "step": 34435 + }, + { + "epoch": 10.63, + "learning_rate": 9.457887668675e-06, + "loss": 0.0154, + "step": 34436 + }, + { + "epoch": 10.63, + "learning_rate": 9.45738828655713e-06, + "loss": 0.0174, + "step": 34437 + }, + { + "epoch": 10.64, + "learning_rate": 9.456888905796437e-06, + "loss": 0.0149, + "step": 34438 + }, + { + "epoch": 10.64, + "learning_rate": 9.45638952639416e-06, + "loss": 0.0149, + "step": 34439 + }, + { + "epoch": 10.64, + "learning_rate": 9.455890148351549e-06, + "loss": 0.0152, + "step": 34440 + }, + { + "epoch": 10.64, + "learning_rate": 9.455390771669861e-06, + "loss": 0.0154, + "step": 34441 + }, + { + "epoch": 10.64, + "learning_rate": 9.454891396350337e-06, + "loss": 0.0165, + "step": 34442 + }, + { + "epoch": 10.64, + "learning_rate": 9.454392022394228e-06, + "loss": 0.0178, + "step": 34443 + }, + { + "epoch": 10.64, + "learning_rate": 9.453892649802788e-06, + "loss": 0.0185, + "step": 34444 + }, + { + "epoch": 10.64, + "learning_rate": 9.453393278577258e-06, + "loss": 0.0148, + "step": 34445 + }, + { + "epoch": 10.64, + "learning_rate": 9.452893908718894e-06, + "loss": 0.0171, + "step": 34446 + }, + { + "epoch": 10.64, + "learning_rate": 9.452394540228942e-06, + "loss": 0.0144, + "step": 34447 + }, + { + "epoch": 10.64, + "learning_rate": 9.45189517310865e-06, + "loss": 0.0144, + "step": 34448 + }, + { + "epoch": 10.64, + "learning_rate": 9.451395807359268e-06, + "loss": 0.0159, + "step": 34449 + }, + { + "epoch": 10.64, + "learning_rate": 9.450896442982043e-06, + "loss": 0.0153, + "step": 34450 + }, + { + "epoch": 10.64, + "learning_rate": 9.450397079978232e-06, + "loss": 0.0145, + "step": 34451 + }, + { + "epoch": 10.64, + "learning_rate": 9.449897718349072e-06, + "loss": 0.0154, + "step": 34452 + }, + { + "epoch": 10.64, + "learning_rate": 9.449398358095822e-06, + "loss": 0.0155, + "step": 34453 + }, + { + "epoch": 10.64, + "learning_rate": 9.448898999219728e-06, + "loss": 0.0142, + "step": 34454 + }, + { + "epoch": 10.64, + "learning_rate": 9.448399641722034e-06, + "loss": 0.0147, + "step": 34455 + }, + { + "epoch": 10.64, + "learning_rate": 9.447900285603995e-06, + "loss": 0.0149, + "step": 34456 + }, + { + "epoch": 10.64, + "learning_rate": 9.44740093086686e-06, + "loss": 0.016, + "step": 34457 + }, + { + "epoch": 10.64, + "learning_rate": 9.446901577511872e-06, + "loss": 0.0146, + "step": 34458 + }, + { + "epoch": 10.64, + "learning_rate": 9.446402225540287e-06, + "loss": 0.0158, + "step": 34459 + }, + { + "epoch": 10.64, + "learning_rate": 9.445902874953351e-06, + "loss": 0.0138, + "step": 34460 + }, + { + "epoch": 10.64, + "learning_rate": 9.445403525752313e-06, + "loss": 0.0149, + "step": 34461 + }, + { + "epoch": 10.64, + "learning_rate": 9.44490417793842e-06, + "loss": 0.0156, + "step": 34462 + }, + { + "epoch": 10.64, + "learning_rate": 9.444404831512925e-06, + "loss": 0.0145, + "step": 34463 + }, + { + "epoch": 10.64, + "learning_rate": 9.443905486477074e-06, + "loss": 0.0178, + "step": 34464 + }, + { + "epoch": 10.64, + "learning_rate": 9.443406142832115e-06, + "loss": 0.0142, + "step": 34465 + }, + { + "epoch": 10.64, + "learning_rate": 9.442906800579303e-06, + "loss": 0.0148, + "step": 34466 + }, + { + "epoch": 10.64, + "learning_rate": 9.442407459719882e-06, + "loss": 0.0172, + "step": 34467 + }, + { + "epoch": 10.64, + "learning_rate": 9.441908120255096e-06, + "loss": 0.0156, + "step": 34468 + }, + { + "epoch": 10.64, + "learning_rate": 9.441408782186208e-06, + "loss": 0.0177, + "step": 34469 + }, + { + "epoch": 10.65, + "learning_rate": 9.440909445514452e-06, + "loss": 0.0154, + "step": 34470 + }, + { + "epoch": 10.65, + "learning_rate": 9.440410110241087e-06, + "loss": 0.0161, + "step": 34471 + }, + { + "epoch": 10.65, + "learning_rate": 9.439910776367358e-06, + "loss": 0.0151, + "step": 34472 + }, + { + "epoch": 10.65, + "learning_rate": 9.43941144389451e-06, + "loss": 0.0159, + "step": 34473 + }, + { + "epoch": 10.65, + "learning_rate": 9.4389121128238e-06, + "loss": 0.0145, + "step": 34474 + }, + { + "epoch": 10.65, + "learning_rate": 9.438412783156475e-06, + "loss": 0.0154, + "step": 34475 + }, + { + "epoch": 10.65, + "learning_rate": 9.437913454893778e-06, + "loss": 0.014, + "step": 34476 + }, + { + "epoch": 10.65, + "learning_rate": 9.437414128036964e-06, + "loss": 0.0146, + "step": 34477 + }, + { + "epoch": 10.65, + "learning_rate": 9.43691480258728e-06, + "loss": 0.0131, + "step": 34478 + }, + { + "epoch": 10.65, + "learning_rate": 9.436415478545974e-06, + "loss": 0.0135, + "step": 34479 + }, + { + "epoch": 10.65, + "learning_rate": 9.435916155914294e-06, + "loss": 0.0167, + "step": 34480 + }, + { + "epoch": 10.65, + "learning_rate": 9.435416834693493e-06, + "loss": 0.0154, + "step": 34481 + }, + { + "epoch": 10.65, + "learning_rate": 9.43491751488482e-06, + "loss": 0.0154, + "step": 34482 + }, + { + "epoch": 10.65, + "learning_rate": 9.434418196489516e-06, + "loss": 0.013, + "step": 34483 + }, + { + "epoch": 10.65, + "learning_rate": 9.433918879508836e-06, + "loss": 0.0172, + "step": 34484 + }, + { + "epoch": 10.65, + "learning_rate": 9.433419563944034e-06, + "loss": 0.0156, + "step": 34485 + }, + { + "epoch": 10.65, + "learning_rate": 9.432920249796344e-06, + "loss": 0.0175, + "step": 34486 + }, + { + "epoch": 10.65, + "learning_rate": 9.43242093706703e-06, + "loss": 0.0158, + "step": 34487 + }, + { + "epoch": 10.65, + "learning_rate": 9.431921625757336e-06, + "loss": 0.0157, + "step": 34488 + }, + { + "epoch": 10.65, + "learning_rate": 9.431422315868506e-06, + "loss": 0.0159, + "step": 34489 + }, + { + "epoch": 10.65, + "learning_rate": 9.430923007401792e-06, + "loss": 0.0176, + "step": 34490 + }, + { + "epoch": 10.65, + "learning_rate": 9.430423700358447e-06, + "loss": 0.0169, + "step": 34491 + }, + { + "epoch": 10.65, + "learning_rate": 9.429924394739713e-06, + "loss": 0.0179, + "step": 34492 + }, + { + "epoch": 10.65, + "learning_rate": 9.429425090546841e-06, + "loss": 0.0161, + "step": 34493 + }, + { + "epoch": 10.65, + "learning_rate": 9.428925787781086e-06, + "loss": 0.014, + "step": 34494 + }, + { + "epoch": 10.65, + "learning_rate": 9.428426486443689e-06, + "loss": 0.0152, + "step": 34495 + }, + { + "epoch": 10.65, + "learning_rate": 9.427927186535898e-06, + "loss": 0.0134, + "step": 34496 + }, + { + "epoch": 10.65, + "learning_rate": 9.42742788805897e-06, + "loss": 0.0155, + "step": 34497 + }, + { + "epoch": 10.65, + "learning_rate": 9.42692859101415e-06, + "loss": 0.0152, + "step": 34498 + }, + { + "epoch": 10.65, + "learning_rate": 9.426429295402684e-06, + "loss": 0.0172, + "step": 34499 + }, + { + "epoch": 10.65, + "learning_rate": 9.425930001225825e-06, + "loss": 0.0137, + "step": 34500 + }, + { + "epoch": 10.65, + "learning_rate": 9.425430708484815e-06, + "loss": 0.0147, + "step": 34501 + }, + { + "epoch": 10.65, + "learning_rate": 9.424931417180911e-06, + "loss": 0.0147, + "step": 34502 + }, + { + "epoch": 10.66, + "learning_rate": 9.42443212731536e-06, + "loss": 0.0154, + "step": 34503 + }, + { + "epoch": 10.66, + "learning_rate": 9.423932838889405e-06, + "loss": 0.0141, + "step": 34504 + }, + { + "epoch": 10.66, + "learning_rate": 9.423433551904302e-06, + "loss": 0.0147, + "step": 34505 + }, + { + "epoch": 10.66, + "learning_rate": 9.422934266361298e-06, + "loss": 0.0149, + "step": 34506 + }, + { + "epoch": 10.66, + "learning_rate": 9.422434982261636e-06, + "loss": 0.0159, + "step": 34507 + }, + { + "epoch": 10.66, + "learning_rate": 9.421935699606573e-06, + "loss": 0.0152, + "step": 34508 + }, + { + "epoch": 10.66, + "learning_rate": 9.421436418397355e-06, + "loss": 0.0151, + "step": 34509 + }, + { + "epoch": 10.66, + "learning_rate": 9.420937138635227e-06, + "loss": 0.0153, + "step": 34510 + }, + { + "epoch": 10.66, + "learning_rate": 9.42043786032144e-06, + "loss": 0.0156, + "step": 34511 + }, + { + "epoch": 10.66, + "learning_rate": 9.419938583457248e-06, + "loss": 0.0152, + "step": 34512 + }, + { + "epoch": 10.66, + "learning_rate": 9.419439308043896e-06, + "loss": 0.0152, + "step": 34513 + }, + { + "epoch": 10.66, + "learning_rate": 9.418940034082625e-06, + "loss": 0.0161, + "step": 34514 + }, + { + "epoch": 10.66, + "learning_rate": 9.418440761574696e-06, + "loss": 0.0161, + "step": 34515 + }, + { + "epoch": 10.66, + "learning_rate": 9.417941490521354e-06, + "loss": 0.0147, + "step": 34516 + }, + { + "epoch": 10.66, + "learning_rate": 9.417442220923842e-06, + "loss": 0.0163, + "step": 34517 + }, + { + "epoch": 10.66, + "learning_rate": 9.416942952783416e-06, + "loss": 0.0165, + "step": 34518 + }, + { + "epoch": 10.66, + "learning_rate": 9.416443686101325e-06, + "loss": 0.0158, + "step": 34519 + }, + { + "epoch": 10.66, + "learning_rate": 9.415944420878812e-06, + "loss": 0.017, + "step": 34520 + }, + { + "epoch": 10.66, + "learning_rate": 9.415445157117125e-06, + "loss": 0.0166, + "step": 34521 + }, + { + "epoch": 10.66, + "learning_rate": 9.414945894817522e-06, + "loss": 0.0136, + "step": 34522 + }, + { + "epoch": 10.66, + "learning_rate": 9.414446633981244e-06, + "loss": 0.0151, + "step": 34523 + }, + { + "epoch": 10.66, + "learning_rate": 9.413947374609538e-06, + "loss": 0.0158, + "step": 34524 + }, + { + "epoch": 10.66, + "learning_rate": 9.413448116703662e-06, + "loss": 0.0175, + "step": 34525 + }, + { + "epoch": 10.66, + "learning_rate": 9.412948860264858e-06, + "loss": 0.018, + "step": 34526 + }, + { + "epoch": 10.66, + "learning_rate": 9.412449605294373e-06, + "loss": 0.0147, + "step": 34527 + }, + { + "epoch": 10.66, + "learning_rate": 9.411950351793465e-06, + "loss": 0.0163, + "step": 34528 + }, + { + "epoch": 10.66, + "learning_rate": 9.411451099763368e-06, + "loss": 0.0147, + "step": 34529 + }, + { + "epoch": 10.66, + "learning_rate": 9.410951849205344e-06, + "loss": 0.0151, + "step": 34530 + }, + { + "epoch": 10.66, + "learning_rate": 9.410452600120639e-06, + "loss": 0.0148, + "step": 34531 + }, + { + "epoch": 10.66, + "learning_rate": 9.409953352510494e-06, + "loss": 0.0158, + "step": 34532 + }, + { + "epoch": 10.66, + "learning_rate": 9.409454106376167e-06, + "loss": 0.0151, + "step": 34533 + }, + { + "epoch": 10.66, + "learning_rate": 9.408954861718904e-06, + "loss": 0.0164, + "step": 34534 + }, + { + "epoch": 10.67, + "learning_rate": 9.408455618539948e-06, + "loss": 0.0156, + "step": 34535 + }, + { + "epoch": 10.67, + "learning_rate": 9.407956376840555e-06, + "loss": 0.0141, + "step": 34536 + }, + { + "epoch": 10.67, + "learning_rate": 9.407457136621974e-06, + "loss": 0.0129, + "step": 34537 + }, + { + "epoch": 10.67, + "learning_rate": 9.406957897885447e-06, + "loss": 0.0153, + "step": 34538 + }, + { + "epoch": 10.67, + "learning_rate": 9.406458660632225e-06, + "loss": 0.0159, + "step": 34539 + }, + { + "epoch": 10.67, + "learning_rate": 9.405959424863563e-06, + "loss": 0.016, + "step": 34540 + }, + { + "epoch": 10.67, + "learning_rate": 9.405460190580703e-06, + "loss": 0.0162, + "step": 34541 + }, + { + "epoch": 10.67, + "learning_rate": 9.404960957784892e-06, + "loss": 0.0158, + "step": 34542 + }, + { + "epoch": 10.67, + "learning_rate": 9.404461726477387e-06, + "loss": 0.0157, + "step": 34543 + }, + { + "epoch": 10.67, + "learning_rate": 9.40396249665943e-06, + "loss": 0.015, + "step": 34544 + }, + { + "epoch": 10.67, + "learning_rate": 9.40346326833227e-06, + "loss": 0.0137, + "step": 34545 + }, + { + "epoch": 10.67, + "learning_rate": 9.402964041497158e-06, + "loss": 0.0138, + "step": 34546 + }, + { + "epoch": 10.67, + "learning_rate": 9.402464816155344e-06, + "loss": 0.0177, + "step": 34547 + }, + { + "epoch": 10.67, + "learning_rate": 9.401965592308073e-06, + "loss": 0.0133, + "step": 34548 + }, + { + "epoch": 10.67, + "learning_rate": 9.401466369956593e-06, + "loss": 0.0134, + "step": 34549 + }, + { + "epoch": 10.67, + "learning_rate": 9.400967149102158e-06, + "loss": 0.0148, + "step": 34550 + }, + { + "epoch": 10.67, + "learning_rate": 9.400467929746013e-06, + "loss": 0.0154, + "step": 34551 + }, + { + "epoch": 10.67, + "learning_rate": 9.399968711889404e-06, + "loss": 0.0161, + "step": 34552 + }, + { + "epoch": 10.67, + "learning_rate": 9.399469495533587e-06, + "loss": 0.0159, + "step": 34553 + }, + { + "epoch": 10.67, + "learning_rate": 9.398970280679804e-06, + "loss": 0.0148, + "step": 34554 + }, + { + "epoch": 10.67, + "learning_rate": 9.398471067329304e-06, + "loss": 0.0169, + "step": 34555 + }, + { + "epoch": 10.67, + "learning_rate": 9.397971855483342e-06, + "loss": 0.0163, + "step": 34556 + }, + { + "epoch": 10.67, + "learning_rate": 9.39747264514316e-06, + "loss": 0.0147, + "step": 34557 + }, + { + "epoch": 10.67, + "learning_rate": 9.396973436310008e-06, + "loss": 0.0152, + "step": 34558 + }, + { + "epoch": 10.67, + "learning_rate": 9.396474228985138e-06, + "loss": 0.0146, + "step": 34559 + }, + { + "epoch": 10.67, + "learning_rate": 9.395975023169793e-06, + "loss": 0.0153, + "step": 34560 + }, + { + "epoch": 10.67, + "learning_rate": 9.395475818865226e-06, + "loss": 0.0156, + "step": 34561 + }, + { + "epoch": 10.67, + "learning_rate": 9.394976616072687e-06, + "loss": 0.0156, + "step": 34562 + }, + { + "epoch": 10.67, + "learning_rate": 9.394477414793417e-06, + "loss": 0.0176, + "step": 34563 + }, + { + "epoch": 10.67, + "learning_rate": 9.39397821502867e-06, + "loss": 0.015, + "step": 34564 + }, + { + "epoch": 10.67, + "learning_rate": 9.393479016779697e-06, + "loss": 0.0152, + "step": 34565 + }, + { + "epoch": 10.67, + "learning_rate": 9.39297982004774e-06, + "loss": 0.015, + "step": 34566 + }, + { + "epoch": 10.67, + "learning_rate": 9.392480624834052e-06, + "loss": 0.0151, + "step": 34567 + }, + { + "epoch": 10.68, + "learning_rate": 9.391981431139884e-06, + "loss": 0.0157, + "step": 34568 + }, + { + "epoch": 10.68, + "learning_rate": 9.39148223896648e-06, + "loss": 0.0156, + "step": 34569 + }, + { + "epoch": 10.68, + "learning_rate": 9.390983048315089e-06, + "loss": 0.0148, + "step": 34570 + }, + { + "epoch": 10.68, + "learning_rate": 9.390483859186961e-06, + "loss": 0.0167, + "step": 34571 + }, + { + "epoch": 10.68, + "learning_rate": 9.389984671583345e-06, + "loss": 0.0176, + "step": 34572 + }, + { + "epoch": 10.68, + "learning_rate": 9.389485485505483e-06, + "loss": 0.0147, + "step": 34573 + }, + { + "epoch": 10.68, + "learning_rate": 9.388986300954636e-06, + "loss": 0.0158, + "step": 34574 + }, + { + "epoch": 10.68, + "learning_rate": 9.388487117932044e-06, + "loss": 0.0161, + "step": 34575 + }, + { + "epoch": 10.68, + "learning_rate": 9.387987936438954e-06, + "loss": 0.0125, + "step": 34576 + }, + { + "epoch": 10.68, + "learning_rate": 9.387488756476624e-06, + "loss": 0.0153, + "step": 34577 + }, + { + "epoch": 10.68, + "learning_rate": 9.38698957804629e-06, + "loss": 0.0176, + "step": 34578 + }, + { + "epoch": 10.68, + "learning_rate": 9.38649040114921e-06, + "loss": 0.0157, + "step": 34579 + }, + { + "epoch": 10.68, + "learning_rate": 9.385991225786625e-06, + "loss": 0.0172, + "step": 34580 + }, + { + "epoch": 10.68, + "learning_rate": 9.385492051959794e-06, + "loss": 0.0151, + "step": 34581 + }, + { + "epoch": 10.68, + "learning_rate": 9.384992879669959e-06, + "loss": 0.0151, + "step": 34582 + }, + { + "epoch": 10.68, + "learning_rate": 9.384493708918364e-06, + "loss": 0.0156, + "step": 34583 + }, + { + "epoch": 10.68, + "learning_rate": 9.383994539706269e-06, + "loss": 0.0137, + "step": 34584 + }, + { + "epoch": 10.68, + "learning_rate": 9.383495372034913e-06, + "loss": 0.0165, + "step": 34585 + }, + { + "epoch": 10.68, + "learning_rate": 9.382996205905543e-06, + "loss": 0.0162, + "step": 34586 + }, + { + "epoch": 10.68, + "learning_rate": 9.382497041319421e-06, + "loss": 0.0141, + "step": 34587 + }, + { + "epoch": 10.68, + "learning_rate": 9.38199787827778e-06, + "loss": 0.0134, + "step": 34588 + }, + { + "epoch": 10.68, + "learning_rate": 9.381498716781877e-06, + "loss": 0.0158, + "step": 34589 + }, + { + "epoch": 10.68, + "learning_rate": 9.380999556832959e-06, + "loss": 0.0171, + "step": 34590 + }, + { + "epoch": 10.68, + "learning_rate": 9.380500398432272e-06, + "loss": 0.0167, + "step": 34591 + }, + { + "epoch": 10.68, + "learning_rate": 9.380001241581067e-06, + "loss": 0.0165, + "step": 34592 + }, + { + "epoch": 10.68, + "learning_rate": 9.379502086280595e-06, + "loss": 0.0147, + "step": 34593 + }, + { + "epoch": 10.68, + "learning_rate": 9.379002932532097e-06, + "loss": 0.0158, + "step": 34594 + }, + { + "epoch": 10.68, + "learning_rate": 9.37850378033683e-06, + "loss": 0.0163, + "step": 34595 + }, + { + "epoch": 10.68, + "learning_rate": 9.378004629696036e-06, + "loss": 0.0174, + "step": 34596 + }, + { + "epoch": 10.68, + "learning_rate": 9.377505480610967e-06, + "loss": 0.0168, + "step": 34597 + }, + { + "epoch": 10.68, + "learning_rate": 9.377006333082867e-06, + "loss": 0.0151, + "step": 34598 + }, + { + "epoch": 10.68, + "learning_rate": 9.376507187112993e-06, + "loss": 0.0154, + "step": 34599 + }, + { + "epoch": 10.69, + "learning_rate": 9.376008042702585e-06, + "loss": 0.0163, + "step": 34600 + }, + { + "epoch": 10.69, + "learning_rate": 9.375508899852894e-06, + "loss": 0.014, + "step": 34601 + }, + { + "epoch": 10.69, + "learning_rate": 9.375009758565173e-06, + "loss": 0.0158, + "step": 34602 + }, + { + "epoch": 10.69, + "learning_rate": 9.374510618840664e-06, + "loss": 0.0158, + "step": 34603 + }, + { + "epoch": 10.69, + "learning_rate": 9.374011480680615e-06, + "loss": 0.0161, + "step": 34604 + }, + { + "epoch": 10.69, + "learning_rate": 9.373512344086285e-06, + "loss": 0.0172, + "step": 34605 + }, + { + "epoch": 10.69, + "learning_rate": 9.37301320905891e-06, + "loss": 0.0167, + "step": 34606 + }, + { + "epoch": 10.69, + "learning_rate": 9.372514075599742e-06, + "loss": 0.016, + "step": 34607 + }, + { + "epoch": 10.69, + "learning_rate": 9.372014943710035e-06, + "loss": 0.0163, + "step": 34608 + }, + { + "epoch": 10.69, + "learning_rate": 9.371515813391029e-06, + "loss": 0.0158, + "step": 34609 + }, + { + "epoch": 10.69, + "learning_rate": 9.37101668464398e-06, + "loss": 0.0161, + "step": 34610 + }, + { + "epoch": 10.69, + "learning_rate": 9.37051755747013e-06, + "loss": 0.0144, + "step": 34611 + }, + { + "epoch": 10.69, + "learning_rate": 9.370018431870732e-06, + "loss": 0.0181, + "step": 34612 + }, + { + "epoch": 10.69, + "learning_rate": 9.369519307847031e-06, + "loss": 0.0156, + "step": 34613 + }, + { + "epoch": 10.69, + "learning_rate": 9.369020185400277e-06, + "loss": 0.0156, + "step": 34614 + }, + { + "epoch": 10.69, + "learning_rate": 9.368521064531723e-06, + "loss": 0.0169, + "step": 34615 + }, + { + "epoch": 10.69, + "learning_rate": 9.36802194524261e-06, + "loss": 0.016, + "step": 34616 + }, + { + "epoch": 10.69, + "learning_rate": 9.36752282753419e-06, + "loss": 0.0145, + "step": 34617 + }, + { + "epoch": 10.69, + "learning_rate": 9.367023711407712e-06, + "loss": 0.0161, + "step": 34618 + }, + { + "epoch": 10.69, + "learning_rate": 9.366524596864419e-06, + "loss": 0.0163, + "step": 34619 + }, + { + "epoch": 10.69, + "learning_rate": 9.366025483905567e-06, + "loss": 0.0177, + "step": 34620 + }, + { + "epoch": 10.69, + "learning_rate": 9.365526372532402e-06, + "loss": 0.0154, + "step": 34621 + }, + { + "epoch": 10.69, + "learning_rate": 9.365027262746168e-06, + "loss": 0.0156, + "step": 34622 + }, + { + "epoch": 10.69, + "learning_rate": 9.364528154548117e-06, + "loss": 0.0163, + "step": 34623 + }, + { + "epoch": 10.69, + "learning_rate": 9.3640290479395e-06, + "loss": 0.0158, + "step": 34624 + }, + { + "epoch": 10.69, + "learning_rate": 9.363529942921558e-06, + "loss": 0.0161, + "step": 34625 + }, + { + "epoch": 10.69, + "learning_rate": 9.363030839495545e-06, + "loss": 0.0162, + "step": 34626 + }, + { + "epoch": 10.69, + "learning_rate": 9.362531737662712e-06, + "loss": 0.0153, + "step": 34627 + }, + { + "epoch": 10.69, + "learning_rate": 9.3620326374243e-06, + "loss": 0.0143, + "step": 34628 + }, + { + "epoch": 10.69, + "learning_rate": 9.36153353878156e-06, + "loss": 0.0143, + "step": 34629 + }, + { + "epoch": 10.69, + "learning_rate": 9.361034441735743e-06, + "loss": 0.0155, + "step": 34630 + }, + { + "epoch": 10.69, + "learning_rate": 9.360535346288096e-06, + "loss": 0.0158, + "step": 34631 + }, + { + "epoch": 10.7, + "learning_rate": 9.360036252439862e-06, + "loss": 0.0173, + "step": 34632 + }, + { + "epoch": 10.7, + "learning_rate": 9.3595371601923e-06, + "loss": 0.0192, + "step": 34633 + }, + { + "epoch": 10.7, + "learning_rate": 9.35903806954665e-06, + "loss": 0.0172, + "step": 34634 + }, + { + "epoch": 10.7, + "learning_rate": 9.35853898050416e-06, + "loss": 0.016, + "step": 34635 + }, + { + "epoch": 10.7, + "learning_rate": 9.358039893066087e-06, + "loss": 0.0146, + "step": 34636 + }, + { + "epoch": 10.7, + "learning_rate": 9.357540807233669e-06, + "loss": 0.0149, + "step": 34637 + }, + { + "epoch": 10.7, + "learning_rate": 9.357041723008158e-06, + "loss": 0.0151, + "step": 34638 + }, + { + "epoch": 10.7, + "learning_rate": 9.356542640390807e-06, + "loss": 0.0163, + "step": 34639 + }, + { + "epoch": 10.7, + "learning_rate": 9.356043559382855e-06, + "loss": 0.0153, + "step": 34640 + }, + { + "epoch": 10.7, + "learning_rate": 9.355544479985557e-06, + "loss": 0.0147, + "step": 34641 + }, + { + "epoch": 10.7, + "learning_rate": 9.355045402200164e-06, + "loss": 0.0157, + "step": 34642 + }, + { + "epoch": 10.7, + "learning_rate": 9.354546326027915e-06, + "loss": 0.0155, + "step": 34643 + }, + { + "epoch": 10.7, + "learning_rate": 9.354047251470064e-06, + "loss": 0.0157, + "step": 34644 + }, + { + "epoch": 10.7, + "learning_rate": 9.353548178527858e-06, + "loss": 0.0147, + "step": 34645 + }, + { + "epoch": 10.7, + "learning_rate": 9.353049107202552e-06, + "loss": 0.0181, + "step": 34646 + }, + { + "epoch": 10.7, + "learning_rate": 9.352550037495383e-06, + "loss": 0.0168, + "step": 34647 + }, + { + "epoch": 10.7, + "learning_rate": 9.352050969407605e-06, + "loss": 0.0136, + "step": 34648 + }, + { + "epoch": 10.7, + "learning_rate": 9.351551902940467e-06, + "loss": 0.015, + "step": 34649 + }, + { + "epoch": 10.7, + "learning_rate": 9.351052838095214e-06, + "loss": 0.0167, + "step": 34650 + }, + { + "epoch": 10.7, + "learning_rate": 9.350553774873097e-06, + "loss": 0.0172, + "step": 34651 + }, + { + "epoch": 10.7, + "learning_rate": 9.350054713275365e-06, + "loss": 0.0163, + "step": 34652 + }, + { + "epoch": 10.7, + "learning_rate": 9.349555653303263e-06, + "loss": 0.0163, + "step": 34653 + }, + { + "epoch": 10.7, + "learning_rate": 9.34905659495804e-06, + "loss": 0.0149, + "step": 34654 + }, + { + "epoch": 10.7, + "learning_rate": 9.34855753824095e-06, + "loss": 0.0155, + "step": 34655 + }, + { + "epoch": 10.7, + "learning_rate": 9.348058483153232e-06, + "loss": 0.0152, + "step": 34656 + }, + { + "epoch": 10.7, + "learning_rate": 9.347559429696138e-06, + "loss": 0.016, + "step": 34657 + }, + { + "epoch": 10.7, + "learning_rate": 9.34706037787092e-06, + "loss": 0.0138, + "step": 34658 + }, + { + "epoch": 10.7, + "learning_rate": 9.346561327678822e-06, + "loss": 0.0149, + "step": 34659 + }, + { + "epoch": 10.7, + "learning_rate": 9.346062279121091e-06, + "loss": 0.0153, + "step": 34660 + }, + { + "epoch": 10.7, + "learning_rate": 9.345563232198981e-06, + "loss": 0.0152, + "step": 34661 + }, + { + "epoch": 10.7, + "learning_rate": 9.345064186913735e-06, + "loss": 0.0145, + "step": 34662 + }, + { + "epoch": 10.7, + "learning_rate": 9.344565143266602e-06, + "loss": 0.0138, + "step": 34663 + }, + { + "epoch": 10.7, + "learning_rate": 9.344066101258833e-06, + "loss": 0.0145, + "step": 34664 + }, + { + "epoch": 10.71, + "learning_rate": 9.343567060891673e-06, + "loss": 0.0147, + "step": 34665 + }, + { + "epoch": 10.71, + "learning_rate": 9.343068022166372e-06, + "loss": 0.0166, + "step": 34666 + }, + { + "epoch": 10.71, + "learning_rate": 9.342568985084181e-06, + "loss": 0.0171, + "step": 34667 + }, + { + "epoch": 10.71, + "learning_rate": 9.34206994964634e-06, + "loss": 0.0164, + "step": 34668 + }, + { + "epoch": 10.71, + "learning_rate": 9.341570915854102e-06, + "loss": 0.0156, + "step": 34669 + }, + { + "epoch": 10.71, + "learning_rate": 9.34107188370872e-06, + "loss": 0.0153, + "step": 34670 + }, + { + "epoch": 10.71, + "learning_rate": 9.340572853211431e-06, + "loss": 0.0173, + "step": 34671 + }, + { + "epoch": 10.71, + "learning_rate": 9.340073824363493e-06, + "loss": 0.0147, + "step": 34672 + }, + { + "epoch": 10.71, + "learning_rate": 9.339574797166153e-06, + "loss": 0.0145, + "step": 34673 + }, + { + "epoch": 10.71, + "learning_rate": 9.339075771620652e-06, + "loss": 0.0153, + "step": 34674 + }, + { + "epoch": 10.71, + "learning_rate": 9.338576747728244e-06, + "loss": 0.0161, + "step": 34675 + }, + { + "epoch": 10.71, + "learning_rate": 9.338077725490182e-06, + "loss": 0.0144, + "step": 34676 + }, + { + "epoch": 10.71, + "learning_rate": 9.337578704907703e-06, + "loss": 0.0178, + "step": 34677 + }, + { + "epoch": 10.71, + "learning_rate": 9.33707968598206e-06, + "loss": 0.0156, + "step": 34678 + }, + { + "epoch": 10.71, + "learning_rate": 9.336580668714504e-06, + "loss": 0.0136, + "step": 34679 + }, + { + "epoch": 10.71, + "learning_rate": 9.33608165310628e-06, + "loss": 0.015, + "step": 34680 + }, + { + "epoch": 10.71, + "learning_rate": 9.335582639158636e-06, + "loss": 0.0152, + "step": 34681 + }, + { + "epoch": 10.71, + "learning_rate": 9.335083626872821e-06, + "loss": 0.0149, + "step": 34682 + }, + { + "epoch": 10.71, + "learning_rate": 9.334584616250086e-06, + "loss": 0.0185, + "step": 34683 + }, + { + "epoch": 10.71, + "learning_rate": 9.334085607291673e-06, + "loss": 0.0158, + "step": 34684 + }, + { + "epoch": 10.71, + "learning_rate": 9.333586599998832e-06, + "loss": 0.0146, + "step": 34685 + }, + { + "epoch": 10.71, + "learning_rate": 9.333087594372817e-06, + "loss": 0.0154, + "step": 34686 + }, + { + "epoch": 10.71, + "learning_rate": 9.332588590414871e-06, + "loss": 0.0158, + "step": 34687 + }, + { + "epoch": 10.71, + "learning_rate": 9.332089588126239e-06, + "loss": 0.0133, + "step": 34688 + }, + { + "epoch": 10.71, + "learning_rate": 9.331590587508176e-06, + "loss": 0.0154, + "step": 34689 + }, + { + "epoch": 10.71, + "learning_rate": 9.331091588561926e-06, + "loss": 0.0151, + "step": 34690 + }, + { + "epoch": 10.71, + "learning_rate": 9.330592591288735e-06, + "loss": 0.0144, + "step": 34691 + }, + { + "epoch": 10.71, + "learning_rate": 9.33009359568986e-06, + "loss": 0.0151, + "step": 34692 + }, + { + "epoch": 10.71, + "learning_rate": 9.32959460176654e-06, + "loss": 0.0143, + "step": 34693 + }, + { + "epoch": 10.71, + "learning_rate": 9.329095609520023e-06, + "loss": 0.0132, + "step": 34694 + }, + { + "epoch": 10.71, + "learning_rate": 9.328596618951567e-06, + "loss": 0.0142, + "step": 34695 + }, + { + "epoch": 10.71, + "learning_rate": 9.328097630062407e-06, + "loss": 0.0157, + "step": 34696 + }, + { + "epoch": 10.72, + "learning_rate": 9.3275986428538e-06, + "loss": 0.0152, + "step": 34697 + }, + { + "epoch": 10.72, + "learning_rate": 9.327099657326994e-06, + "loss": 0.0144, + "step": 34698 + }, + { + "epoch": 10.72, + "learning_rate": 9.32660067348323e-06, + "loss": 0.0172, + "step": 34699 + }, + { + "epoch": 10.72, + "learning_rate": 9.326101691323763e-06, + "loss": 0.0153, + "step": 34700 + }, + { + "epoch": 10.72, + "learning_rate": 9.32560271084984e-06, + "loss": 0.0152, + "step": 34701 + }, + { + "epoch": 10.72, + "learning_rate": 9.325103732062702e-06, + "loss": 0.0179, + "step": 34702 + }, + { + "epoch": 10.72, + "learning_rate": 9.324604754963606e-06, + "loss": 0.0171, + "step": 34703 + }, + { + "epoch": 10.72, + "learning_rate": 9.3241057795538e-06, + "loss": 0.0152, + "step": 34704 + }, + { + "epoch": 10.72, + "learning_rate": 9.323606805834525e-06, + "loss": 0.0155, + "step": 34705 + }, + { + "epoch": 10.72, + "learning_rate": 9.32310783380703e-06, + "loss": 0.0174, + "step": 34706 + }, + { + "epoch": 10.72, + "learning_rate": 9.322608863472572e-06, + "loss": 0.0152, + "step": 34707 + }, + { + "epoch": 10.72, + "learning_rate": 9.32210989483239e-06, + "loss": 0.0157, + "step": 34708 + }, + { + "epoch": 10.72, + "learning_rate": 9.321610927887734e-06, + "loss": 0.0147, + "step": 34709 + }, + { + "epoch": 10.72, + "learning_rate": 9.321111962639852e-06, + "loss": 0.0175, + "step": 34710 + }, + { + "epoch": 10.72, + "learning_rate": 9.320612999089996e-06, + "loss": 0.016, + "step": 34711 + }, + { + "epoch": 10.72, + "learning_rate": 9.320114037239408e-06, + "loss": 0.0163, + "step": 34712 + }, + { + "epoch": 10.72, + "learning_rate": 9.319615077089338e-06, + "loss": 0.0149, + "step": 34713 + }, + { + "epoch": 10.72, + "learning_rate": 9.319116118641041e-06, + "loss": 0.0139, + "step": 34714 + }, + { + "epoch": 10.72, + "learning_rate": 9.31861716189575e-06, + "loss": 0.0144, + "step": 34715 + }, + { + "epoch": 10.72, + "learning_rate": 9.318118206854727e-06, + "loss": 0.0158, + "step": 34716 + }, + { + "epoch": 10.72, + "learning_rate": 9.317619253519217e-06, + "loss": 0.017, + "step": 34717 + }, + { + "epoch": 10.72, + "learning_rate": 9.317120301890463e-06, + "loss": 0.0149, + "step": 34718 + }, + { + "epoch": 10.72, + "learning_rate": 9.316621351969712e-06, + "loss": 0.0142, + "step": 34719 + }, + { + "epoch": 10.72, + "learning_rate": 9.316122403758223e-06, + "loss": 0.0146, + "step": 34720 + }, + { + "epoch": 10.72, + "learning_rate": 9.31562345725723e-06, + "loss": 0.0157, + "step": 34721 + }, + { + "epoch": 10.72, + "learning_rate": 9.315124512467988e-06, + "loss": 0.0151, + "step": 34722 + }, + { + "epoch": 10.72, + "learning_rate": 9.31462556939175e-06, + "loss": 0.0173, + "step": 34723 + }, + { + "epoch": 10.72, + "learning_rate": 9.314126628029755e-06, + "loss": 0.0151, + "step": 34724 + }, + { + "epoch": 10.72, + "learning_rate": 9.313627688383252e-06, + "loss": 0.0153, + "step": 34725 + }, + { + "epoch": 10.72, + "learning_rate": 9.313128750453499e-06, + "loss": 0.0143, + "step": 34726 + }, + { + "epoch": 10.72, + "learning_rate": 9.312629814241727e-06, + "loss": 0.0154, + "step": 34727 + }, + { + "epoch": 10.72, + "learning_rate": 9.312130879749199e-06, + "loss": 0.0137, + "step": 34728 + }, + { + "epoch": 10.73, + "learning_rate": 9.311631946977157e-06, + "loss": 0.0157, + "step": 34729 + }, + { + "epoch": 10.73, + "learning_rate": 9.311133015926845e-06, + "loss": 0.016, + "step": 34730 + }, + { + "epoch": 10.73, + "learning_rate": 9.310634086599519e-06, + "loss": 0.0152, + "step": 34731 + }, + { + "epoch": 10.73, + "learning_rate": 9.310135158996422e-06, + "loss": 0.0174, + "step": 34732 + }, + { + "epoch": 10.73, + "learning_rate": 9.3096362331188e-06, + "loss": 0.0158, + "step": 34733 + }, + { + "epoch": 10.73, + "learning_rate": 9.309137308967907e-06, + "loss": 0.015, + "step": 34734 + }, + { + "epoch": 10.73, + "learning_rate": 9.308638386544986e-06, + "loss": 0.0161, + "step": 34735 + }, + { + "epoch": 10.73, + "learning_rate": 9.308139465851289e-06, + "loss": 0.016, + "step": 34736 + }, + { + "epoch": 10.73, + "learning_rate": 9.307640546888056e-06, + "loss": 0.0176, + "step": 34737 + }, + { + "epoch": 10.73, + "learning_rate": 9.307141629656546e-06, + "loss": 0.0159, + "step": 34738 + }, + { + "epoch": 10.73, + "learning_rate": 9.306642714158e-06, + "loss": 0.0164, + "step": 34739 + }, + { + "epoch": 10.73, + "learning_rate": 9.306143800393663e-06, + "loss": 0.0144, + "step": 34740 + }, + { + "epoch": 10.73, + "learning_rate": 9.30564488836479e-06, + "loss": 0.0163, + "step": 34741 + }, + { + "epoch": 10.73, + "learning_rate": 9.305145978072627e-06, + "loss": 0.0146, + "step": 34742 + }, + { + "epoch": 10.73, + "learning_rate": 9.304647069518417e-06, + "loss": 0.0148, + "step": 34743 + }, + { + "epoch": 10.73, + "learning_rate": 9.304148162703412e-06, + "loss": 0.0161, + "step": 34744 + }, + { + "epoch": 10.73, + "learning_rate": 9.303649257628863e-06, + "loss": 0.0145, + "step": 34745 + }, + { + "epoch": 10.73, + "learning_rate": 9.303150354296014e-06, + "loss": 0.0146, + "step": 34746 + }, + { + "epoch": 10.73, + "learning_rate": 9.302651452706109e-06, + "loss": 0.0165, + "step": 34747 + }, + { + "epoch": 10.73, + "learning_rate": 9.302152552860403e-06, + "loss": 0.0156, + "step": 34748 + }, + { + "epoch": 10.73, + "learning_rate": 9.30165365476014e-06, + "loss": 0.0138, + "step": 34749 + }, + { + "epoch": 10.73, + "learning_rate": 9.301154758406566e-06, + "loss": 0.0146, + "step": 34750 + }, + { + "epoch": 10.73, + "learning_rate": 9.300655863800936e-06, + "loss": 0.0149, + "step": 34751 + }, + { + "epoch": 10.73, + "learning_rate": 9.300156970944492e-06, + "loss": 0.0157, + "step": 34752 + }, + { + "epoch": 10.73, + "learning_rate": 9.29965807983848e-06, + "loss": 0.0151, + "step": 34753 + }, + { + "epoch": 10.73, + "learning_rate": 9.299159190484154e-06, + "loss": 0.0141, + "step": 34754 + }, + { + "epoch": 10.73, + "learning_rate": 9.298660302882758e-06, + "loss": 0.0166, + "step": 34755 + }, + { + "epoch": 10.73, + "learning_rate": 9.29816141703554e-06, + "loss": 0.0165, + "step": 34756 + }, + { + "epoch": 10.73, + "learning_rate": 9.29766253294375e-06, + "loss": 0.014, + "step": 34757 + }, + { + "epoch": 10.73, + "learning_rate": 9.297163650608631e-06, + "loss": 0.0154, + "step": 34758 + }, + { + "epoch": 10.73, + "learning_rate": 9.296664770031435e-06, + "loss": 0.0157, + "step": 34759 + }, + { + "epoch": 10.73, + "learning_rate": 9.296165891213412e-06, + "loss": 0.0158, + "step": 34760 + }, + { + "epoch": 10.73, + "learning_rate": 9.295667014155802e-06, + "loss": 0.0126, + "step": 34761 + }, + { + "epoch": 10.74, + "learning_rate": 9.295168138859859e-06, + "loss": 0.0137, + "step": 34762 + }, + { + "epoch": 10.74, + "learning_rate": 9.294669265326831e-06, + "loss": 0.0162, + "step": 34763 + }, + { + "epoch": 10.74, + "learning_rate": 9.29417039355796e-06, + "loss": 0.0146, + "step": 34764 + }, + { + "epoch": 10.74, + "learning_rate": 9.293671523554498e-06, + "loss": 0.0151, + "step": 34765 + }, + { + "epoch": 10.74, + "learning_rate": 9.293172655317696e-06, + "loss": 0.0154, + "step": 34766 + }, + { + "epoch": 10.74, + "learning_rate": 9.292673788848797e-06, + "loss": 0.0148, + "step": 34767 + }, + { + "epoch": 10.74, + "learning_rate": 9.292174924149045e-06, + "loss": 0.016, + "step": 34768 + }, + { + "epoch": 10.74, + "learning_rate": 9.291676061219698e-06, + "loss": 0.0163, + "step": 34769 + }, + { + "epoch": 10.74, + "learning_rate": 9.291177200061998e-06, + "loss": 0.0147, + "step": 34770 + }, + { + "epoch": 10.74, + "learning_rate": 9.290678340677189e-06, + "loss": 0.0161, + "step": 34771 + }, + { + "epoch": 10.74, + "learning_rate": 9.290179483066527e-06, + "loss": 0.0172, + "step": 34772 + }, + { + "epoch": 10.74, + "learning_rate": 9.289680627231256e-06, + "loss": 0.0194, + "step": 34773 + }, + { + "epoch": 10.74, + "learning_rate": 9.289181773172618e-06, + "loss": 0.0165, + "step": 34774 + }, + { + "epoch": 10.74, + "learning_rate": 9.28868292089187e-06, + "loss": 0.0174, + "step": 34775 + }, + { + "epoch": 10.74, + "learning_rate": 9.288184070390257e-06, + "loss": 0.0145, + "step": 34776 + }, + { + "epoch": 10.74, + "learning_rate": 9.287685221669024e-06, + "loss": 0.0171, + "step": 34777 + }, + { + "epoch": 10.74, + "learning_rate": 9.287186374729417e-06, + "loss": 0.0153, + "step": 34778 + }, + { + "epoch": 10.74, + "learning_rate": 9.286687529572693e-06, + "loss": 0.0171, + "step": 34779 + }, + { + "epoch": 10.74, + "learning_rate": 9.286188686200091e-06, + "loss": 0.0152, + "step": 34780 + }, + { + "epoch": 10.74, + "learning_rate": 9.285689844612857e-06, + "loss": 0.0159, + "step": 34781 + }, + { + "epoch": 10.74, + "learning_rate": 9.285191004812249e-06, + "loss": 0.0134, + "step": 34782 + }, + { + "epoch": 10.74, + "learning_rate": 9.284692166799508e-06, + "loss": 0.0161, + "step": 34783 + }, + { + "epoch": 10.74, + "learning_rate": 9.284193330575878e-06, + "loss": 0.014, + "step": 34784 + }, + { + "epoch": 10.74, + "learning_rate": 9.283694496142618e-06, + "loss": 0.0154, + "step": 34785 + }, + { + "epoch": 10.74, + "learning_rate": 9.283195663500961e-06, + "loss": 0.0191, + "step": 34786 + }, + { + "epoch": 10.74, + "learning_rate": 9.282696832652167e-06, + "loss": 0.0156, + "step": 34787 + }, + { + "epoch": 10.74, + "learning_rate": 9.28219800359748e-06, + "loss": 0.0151, + "step": 34788 + }, + { + "epoch": 10.74, + "learning_rate": 9.281699176338141e-06, + "loss": 0.0143, + "step": 34789 + }, + { + "epoch": 10.74, + "learning_rate": 9.281200350875408e-06, + "loss": 0.016, + "step": 34790 + }, + { + "epoch": 10.74, + "learning_rate": 9.280701527210525e-06, + "loss": 0.0148, + "step": 34791 + }, + { + "epoch": 10.74, + "learning_rate": 9.280202705344734e-06, + "loss": 0.0138, + "step": 34792 + }, + { + "epoch": 10.74, + "learning_rate": 9.27970388527929e-06, + "loss": 0.0164, + "step": 34793 + }, + { + "epoch": 10.75, + "learning_rate": 9.27920506701544e-06, + "loss": 0.0186, + "step": 34794 + }, + { + "epoch": 10.75, + "learning_rate": 9.278706250554427e-06, + "loss": 0.0138, + "step": 34795 + }, + { + "epoch": 10.75, + "learning_rate": 9.2782074358975e-06, + "loss": 0.0148, + "step": 34796 + }, + { + "epoch": 10.75, + "learning_rate": 9.27770862304591e-06, + "loss": 0.0137, + "step": 34797 + }, + { + "epoch": 10.75, + "learning_rate": 9.277209812000904e-06, + "loss": 0.0143, + "step": 34798 + }, + { + "epoch": 10.75, + "learning_rate": 9.276711002763723e-06, + "loss": 0.0144, + "step": 34799 + }, + { + "epoch": 10.75, + "learning_rate": 9.276212195335625e-06, + "loss": 0.0162, + "step": 34800 + }, + { + "epoch": 10.75, + "learning_rate": 9.27571338971785e-06, + "loss": 0.0154, + "step": 34801 + }, + { + "epoch": 10.75, + "learning_rate": 9.275214585911647e-06, + "loss": 0.0169, + "step": 34802 + }, + { + "epoch": 10.75, + "learning_rate": 9.274715783918266e-06, + "loss": 0.0158, + "step": 34803 + }, + { + "epoch": 10.75, + "learning_rate": 9.274216983738954e-06, + "loss": 0.0159, + "step": 34804 + }, + { + "epoch": 10.75, + "learning_rate": 9.273718185374956e-06, + "loss": 0.0153, + "step": 34805 + }, + { + "epoch": 10.75, + "learning_rate": 9.273219388827523e-06, + "loss": 0.0159, + "step": 34806 + }, + { + "epoch": 10.75, + "learning_rate": 9.272720594097898e-06, + "loss": 0.0136, + "step": 34807 + }, + { + "epoch": 10.75, + "learning_rate": 9.272221801187333e-06, + "loss": 0.0134, + "step": 34808 + }, + { + "epoch": 10.75, + "learning_rate": 9.271723010097072e-06, + "loss": 0.0157, + "step": 34809 + }, + { + "epoch": 10.75, + "learning_rate": 9.271224220828368e-06, + "loss": 0.0156, + "step": 34810 + }, + { + "epoch": 10.75, + "learning_rate": 9.270725433382465e-06, + "loss": 0.0151, + "step": 34811 + }, + { + "epoch": 10.75, + "learning_rate": 9.270226647760605e-06, + "loss": 0.0184, + "step": 34812 + }, + { + "epoch": 10.75, + "learning_rate": 9.26972786396405e-06, + "loss": 0.0137, + "step": 34813 + }, + { + "epoch": 10.75, + "learning_rate": 9.269229081994033e-06, + "loss": 0.0163, + "step": 34814 + }, + { + "epoch": 10.75, + "learning_rate": 9.268730301851809e-06, + "loss": 0.0146, + "step": 34815 + }, + { + "epoch": 10.75, + "learning_rate": 9.268231523538627e-06, + "loss": 0.0173, + "step": 34816 + }, + { + "epoch": 10.75, + "learning_rate": 9.267732747055726e-06, + "loss": 0.0188, + "step": 34817 + }, + { + "epoch": 10.75, + "learning_rate": 9.26723397240436e-06, + "loss": 0.0143, + "step": 34818 + }, + { + "epoch": 10.75, + "learning_rate": 9.266735199585778e-06, + "loss": 0.0156, + "step": 34819 + }, + { + "epoch": 10.75, + "learning_rate": 9.266236428601222e-06, + "loss": 0.0153, + "step": 34820 + }, + { + "epoch": 10.75, + "learning_rate": 9.265737659451944e-06, + "loss": 0.0154, + "step": 34821 + }, + { + "epoch": 10.75, + "learning_rate": 9.265238892139193e-06, + "loss": 0.0152, + "step": 34822 + }, + { + "epoch": 10.75, + "learning_rate": 9.264740126664208e-06, + "loss": 0.0152, + "step": 34823 + }, + { + "epoch": 10.75, + "learning_rate": 9.264241363028246e-06, + "loss": 0.0146, + "step": 34824 + }, + { + "epoch": 10.75, + "learning_rate": 9.26374260123255e-06, + "loss": 0.014, + "step": 34825 + }, + { + "epoch": 10.75, + "learning_rate": 9.263243841278367e-06, + "loss": 0.0151, + "step": 34826 + }, + { + "epoch": 10.76, + "learning_rate": 9.262745083166945e-06, + "loss": 0.015, + "step": 34827 + }, + { + "epoch": 10.76, + "learning_rate": 9.262246326899535e-06, + "loss": 0.0176, + "step": 34828 + }, + { + "epoch": 10.76, + "learning_rate": 9.261747572477378e-06, + "loss": 0.0144, + "step": 34829 + }, + { + "epoch": 10.76, + "learning_rate": 9.261248819901725e-06, + "loss": 0.0168, + "step": 34830 + }, + { + "epoch": 10.76, + "learning_rate": 9.260750069173828e-06, + "loss": 0.0148, + "step": 34831 + }, + { + "epoch": 10.76, + "learning_rate": 9.260251320294926e-06, + "loss": 0.0161, + "step": 34832 + }, + { + "epoch": 10.76, + "learning_rate": 9.259752573266269e-06, + "loss": 0.0143, + "step": 34833 + }, + { + "epoch": 10.76, + "learning_rate": 9.259253828089112e-06, + "loss": 0.0157, + "step": 34834 + }, + { + "epoch": 10.76, + "learning_rate": 9.25875508476469e-06, + "loss": 0.0155, + "step": 34835 + }, + { + "epoch": 10.76, + "learning_rate": 9.258256343294258e-06, + "loss": 0.0153, + "step": 34836 + }, + { + "epoch": 10.76, + "learning_rate": 9.257757603679066e-06, + "loss": 0.0161, + "step": 34837 + }, + { + "epoch": 10.76, + "learning_rate": 9.257258865920353e-06, + "loss": 0.0166, + "step": 34838 + }, + { + "epoch": 10.76, + "learning_rate": 9.25676013001937e-06, + "loss": 0.0154, + "step": 34839 + }, + { + "epoch": 10.76, + "learning_rate": 9.256261395977372e-06, + "loss": 0.0159, + "step": 34840 + }, + { + "epoch": 10.76, + "learning_rate": 9.255762663795594e-06, + "loss": 0.0158, + "step": 34841 + }, + { + "epoch": 10.76, + "learning_rate": 9.255263933475292e-06, + "loss": 0.0153, + "step": 34842 + }, + { + "epoch": 10.76, + "learning_rate": 9.254765205017707e-06, + "loss": 0.0152, + "step": 34843 + }, + { + "epoch": 10.76, + "learning_rate": 9.254266478424098e-06, + "loss": 0.0144, + "step": 34844 + }, + { + "epoch": 10.76, + "learning_rate": 9.253767753695697e-06, + "loss": 0.0151, + "step": 34845 + }, + { + "epoch": 10.76, + "learning_rate": 9.253269030833763e-06, + "loss": 0.0139, + "step": 34846 + }, + { + "epoch": 10.76, + "learning_rate": 9.25277030983954e-06, + "loss": 0.0169, + "step": 34847 + }, + { + "epoch": 10.76, + "learning_rate": 9.25227159071427e-06, + "loss": 0.0152, + "step": 34848 + }, + { + "epoch": 10.76, + "learning_rate": 9.251772873459208e-06, + "loss": 0.0163, + "step": 34849 + }, + { + "epoch": 10.76, + "learning_rate": 9.2512741580756e-06, + "loss": 0.0151, + "step": 34850 + }, + { + "epoch": 10.76, + "learning_rate": 9.25077544456469e-06, + "loss": 0.0175, + "step": 34851 + }, + { + "epoch": 10.76, + "learning_rate": 9.250276732927727e-06, + "loss": 0.0178, + "step": 34852 + }, + { + "epoch": 10.76, + "learning_rate": 9.24977802316596e-06, + "loss": 0.0148, + "step": 34853 + }, + { + "epoch": 10.76, + "learning_rate": 9.249279315280634e-06, + "loss": 0.0154, + "step": 34854 + }, + { + "epoch": 10.76, + "learning_rate": 9.248780609272997e-06, + "loss": 0.0149, + "step": 34855 + }, + { + "epoch": 10.76, + "learning_rate": 9.248281905144299e-06, + "loss": 0.0175, + "step": 34856 + }, + { + "epoch": 10.76, + "learning_rate": 9.247783202895784e-06, + "loss": 0.0147, + "step": 34857 + }, + { + "epoch": 10.76, + "learning_rate": 9.247284502528698e-06, + "loss": 0.0148, + "step": 34858 + }, + { + "epoch": 10.77, + "learning_rate": 9.246785804044294e-06, + "loss": 0.0174, + "step": 34859 + }, + { + "epoch": 10.77, + "learning_rate": 9.246287107443815e-06, + "loss": 0.015, + "step": 34860 + }, + { + "epoch": 10.77, + "learning_rate": 9.245788412728505e-06, + "loss": 0.0139, + "step": 34861 + }, + { + "epoch": 10.77, + "learning_rate": 9.245289719899623e-06, + "loss": 0.0176, + "step": 34862 + }, + { + "epoch": 10.77, + "learning_rate": 9.244791028958407e-06, + "loss": 0.0155, + "step": 34863 + }, + { + "epoch": 10.77, + "learning_rate": 9.244292339906104e-06, + "loss": 0.0155, + "step": 34864 + }, + { + "epoch": 10.77, + "learning_rate": 9.243793652743967e-06, + "loss": 0.0144, + "step": 34865 + }, + { + "epoch": 10.77, + "learning_rate": 9.243294967473235e-06, + "loss": 0.0174, + "step": 34866 + }, + { + "epoch": 10.77, + "learning_rate": 9.242796284095164e-06, + "loss": 0.015, + "step": 34867 + }, + { + "epoch": 10.77, + "learning_rate": 9.242297602610999e-06, + "loss": 0.0153, + "step": 34868 + }, + { + "epoch": 10.77, + "learning_rate": 9.241798923021982e-06, + "loss": 0.0152, + "step": 34869 + }, + { + "epoch": 10.77, + "learning_rate": 9.241300245329365e-06, + "loss": 0.0156, + "step": 34870 + }, + { + "epoch": 10.77, + "learning_rate": 9.240801569534397e-06, + "loss": 0.0161, + "step": 34871 + }, + { + "epoch": 10.77, + "learning_rate": 9.24030289563832e-06, + "loss": 0.0164, + "step": 34872 + }, + { + "epoch": 10.77, + "learning_rate": 9.239804223642385e-06, + "loss": 0.0154, + "step": 34873 + }, + { + "epoch": 10.77, + "learning_rate": 9.239305553547839e-06, + "loss": 0.0155, + "step": 34874 + }, + { + "epoch": 10.77, + "learning_rate": 9.238806885355928e-06, + "loss": 0.0152, + "step": 34875 + }, + { + "epoch": 10.77, + "learning_rate": 9.238308219067899e-06, + "loss": 0.0152, + "step": 34876 + }, + { + "epoch": 10.77, + "learning_rate": 9.237809554685e-06, + "loss": 0.0145, + "step": 34877 + }, + { + "epoch": 10.77, + "learning_rate": 9.237310892208482e-06, + "loss": 0.0159, + "step": 34878 + }, + { + "epoch": 10.77, + "learning_rate": 9.236812231639583e-06, + "loss": 0.0162, + "step": 34879 + }, + { + "epoch": 10.77, + "learning_rate": 9.23631357297956e-06, + "loss": 0.015, + "step": 34880 + }, + { + "epoch": 10.77, + "learning_rate": 9.235814916229656e-06, + "loss": 0.0145, + "step": 34881 + }, + { + "epoch": 10.77, + "learning_rate": 9.235316261391115e-06, + "loss": 0.0148, + "step": 34882 + }, + { + "epoch": 10.77, + "learning_rate": 9.23481760846519e-06, + "loss": 0.0164, + "step": 34883 + }, + { + "epoch": 10.77, + "learning_rate": 9.234318957453126e-06, + "loss": 0.0143, + "step": 34884 + }, + { + "epoch": 10.77, + "learning_rate": 9.233820308356169e-06, + "loss": 0.0152, + "step": 34885 + }, + { + "epoch": 10.77, + "learning_rate": 9.233321661175564e-06, + "loss": 0.0153, + "step": 34886 + }, + { + "epoch": 10.77, + "learning_rate": 9.232823015912568e-06, + "loss": 0.0149, + "step": 34887 + }, + { + "epoch": 10.77, + "learning_rate": 9.232324372568418e-06, + "loss": 0.0161, + "step": 34888 + }, + { + "epoch": 10.77, + "learning_rate": 9.231825731144361e-06, + "loss": 0.0179, + "step": 34889 + }, + { + "epoch": 10.77, + "learning_rate": 9.231327091641655e-06, + "loss": 0.0151, + "step": 34890 + }, + { + "epoch": 10.78, + "learning_rate": 9.230828454061537e-06, + "loss": 0.0155, + "step": 34891 + }, + { + "epoch": 10.78, + "learning_rate": 9.230329818405254e-06, + "loss": 0.0167, + "step": 34892 + }, + { + "epoch": 10.78, + "learning_rate": 9.229831184674064e-06, + "loss": 0.0153, + "step": 34893 + }, + { + "epoch": 10.78, + "learning_rate": 9.229332552869202e-06, + "loss": 0.0145, + "step": 34894 + }, + { + "epoch": 10.78, + "learning_rate": 9.22883392299192e-06, + "loss": 0.0157, + "step": 34895 + }, + { + "epoch": 10.78, + "learning_rate": 9.228335295043466e-06, + "loss": 0.0159, + "step": 34896 + }, + { + "epoch": 10.78, + "learning_rate": 9.227836669025084e-06, + "loss": 0.0158, + "step": 34897 + }, + { + "epoch": 10.78, + "learning_rate": 9.227338044938025e-06, + "loss": 0.0146, + "step": 34898 + }, + { + "epoch": 10.78, + "learning_rate": 9.226839422783537e-06, + "loss": 0.0147, + "step": 34899 + }, + { + "epoch": 10.78, + "learning_rate": 9.226340802562858e-06, + "loss": 0.0151, + "step": 34900 + }, + { + "epoch": 10.78, + "learning_rate": 9.225842184277248e-06, + "loss": 0.0152, + "step": 34901 + }, + { + "epoch": 10.78, + "learning_rate": 9.225343567927946e-06, + "loss": 0.0159, + "step": 34902 + }, + { + "epoch": 10.78, + "learning_rate": 9.2248449535162e-06, + "loss": 0.0153, + "step": 34903 + }, + { + "epoch": 10.78, + "learning_rate": 9.224346341043257e-06, + "loss": 0.0166, + "step": 34904 + }, + { + "epoch": 10.78, + "learning_rate": 9.223847730510369e-06, + "loss": 0.0168, + "step": 34905 + }, + { + "epoch": 10.78, + "learning_rate": 9.223349121918778e-06, + "loss": 0.0132, + "step": 34906 + }, + { + "epoch": 10.78, + "learning_rate": 9.22285051526973e-06, + "loss": 0.0149, + "step": 34907 + }, + { + "epoch": 10.78, + "learning_rate": 9.222351910564475e-06, + "loss": 0.0173, + "step": 34908 + }, + { + "epoch": 10.78, + "learning_rate": 9.221853307804265e-06, + "loss": 0.018, + "step": 34909 + }, + { + "epoch": 10.78, + "learning_rate": 9.221354706990336e-06, + "loss": 0.0172, + "step": 34910 + }, + { + "epoch": 10.78, + "learning_rate": 9.220856108123942e-06, + "loss": 0.0157, + "step": 34911 + }, + { + "epoch": 10.78, + "learning_rate": 9.220357511206332e-06, + "loss": 0.017, + "step": 34912 + }, + { + "epoch": 10.78, + "learning_rate": 9.219858916238747e-06, + "loss": 0.0145, + "step": 34913 + }, + { + "epoch": 10.78, + "learning_rate": 9.219360323222437e-06, + "loss": 0.0158, + "step": 34914 + }, + { + "epoch": 10.78, + "learning_rate": 9.218861732158653e-06, + "loss": 0.0179, + "step": 34915 + }, + { + "epoch": 10.78, + "learning_rate": 9.218363143048634e-06, + "loss": 0.0166, + "step": 34916 + }, + { + "epoch": 10.78, + "learning_rate": 9.21786455589363e-06, + "loss": 0.0169, + "step": 34917 + }, + { + "epoch": 10.78, + "learning_rate": 9.217365970694896e-06, + "loss": 0.0156, + "step": 34918 + }, + { + "epoch": 10.78, + "learning_rate": 9.21686738745367e-06, + "loss": 0.0137, + "step": 34919 + }, + { + "epoch": 10.78, + "learning_rate": 9.216368806171196e-06, + "loss": 0.0155, + "step": 34920 + }, + { + "epoch": 10.78, + "learning_rate": 9.215870226848732e-06, + "loss": 0.017, + "step": 34921 + }, + { + "epoch": 10.78, + "learning_rate": 9.21537164948752e-06, + "loss": 0.0152, + "step": 34922 + }, + { + "epoch": 10.78, + "learning_rate": 9.214873074088805e-06, + "loss": 0.0151, + "step": 34923 + }, + { + "epoch": 10.79, + "learning_rate": 9.214374500653838e-06, + "loss": 0.0172, + "step": 34924 + }, + { + "epoch": 10.79, + "learning_rate": 9.213875929183859e-06, + "loss": 0.0152, + "step": 34925 + }, + { + "epoch": 10.79, + "learning_rate": 9.213377359680121e-06, + "loss": 0.016, + "step": 34926 + }, + { + "epoch": 10.79, + "learning_rate": 9.212878792143873e-06, + "loss": 0.0154, + "step": 34927 + }, + { + "epoch": 10.79, + "learning_rate": 9.212380226576354e-06, + "loss": 0.0178, + "step": 34928 + }, + { + "epoch": 10.79, + "learning_rate": 9.211881662978819e-06, + "loss": 0.0149, + "step": 34929 + }, + { + "epoch": 10.79, + "learning_rate": 9.211383101352513e-06, + "loss": 0.0157, + "step": 34930 + }, + { + "epoch": 10.79, + "learning_rate": 9.210884541698678e-06, + "loss": 0.016, + "step": 34931 + }, + { + "epoch": 10.79, + "learning_rate": 9.210385984018564e-06, + "loss": 0.0162, + "step": 34932 + }, + { + "epoch": 10.79, + "learning_rate": 9.209887428313424e-06, + "loss": 0.0174, + "step": 34933 + }, + { + "epoch": 10.79, + "learning_rate": 9.209388874584495e-06, + "loss": 0.0145, + "step": 34934 + }, + { + "epoch": 10.79, + "learning_rate": 9.208890322833028e-06, + "loss": 0.017, + "step": 34935 + }, + { + "epoch": 10.79, + "learning_rate": 9.208391773060276e-06, + "loss": 0.0149, + "step": 34936 + }, + { + "epoch": 10.79, + "learning_rate": 9.207893225267477e-06, + "loss": 0.0164, + "step": 34937 + }, + { + "epoch": 10.79, + "learning_rate": 9.207394679455879e-06, + "loss": 0.0148, + "step": 34938 + }, + { + "epoch": 10.79, + "learning_rate": 9.206896135626735e-06, + "loss": 0.0164, + "step": 34939 + }, + { + "epoch": 10.79, + "learning_rate": 9.20639759378129e-06, + "loss": 0.0152, + "step": 34940 + }, + { + "epoch": 10.79, + "learning_rate": 9.205899053920784e-06, + "loss": 0.0148, + "step": 34941 + }, + { + "epoch": 10.79, + "learning_rate": 9.205400516046471e-06, + "loss": 0.0145, + "step": 34942 + }, + { + "epoch": 10.79, + "learning_rate": 9.204901980159601e-06, + "loss": 0.0189, + "step": 34943 + }, + { + "epoch": 10.79, + "learning_rate": 9.204403446261413e-06, + "loss": 0.0175, + "step": 34944 + }, + { + "epoch": 10.79, + "learning_rate": 9.203904914353155e-06, + "loss": 0.0166, + "step": 34945 + }, + { + "epoch": 10.79, + "learning_rate": 9.203406384436078e-06, + "loss": 0.0145, + "step": 34946 + }, + { + "epoch": 10.79, + "learning_rate": 9.202907856511428e-06, + "loss": 0.0164, + "step": 34947 + }, + { + "epoch": 10.79, + "learning_rate": 9.202409330580447e-06, + "loss": 0.0142, + "step": 34948 + }, + { + "epoch": 10.79, + "learning_rate": 9.20191080664439e-06, + "loss": 0.0167, + "step": 34949 + }, + { + "epoch": 10.79, + "learning_rate": 9.201412284704498e-06, + "loss": 0.0172, + "step": 34950 + }, + { + "epoch": 10.79, + "learning_rate": 9.200913764762019e-06, + "loss": 0.0136, + "step": 34951 + }, + { + "epoch": 10.79, + "learning_rate": 9.200415246818205e-06, + "loss": 0.0154, + "step": 34952 + }, + { + "epoch": 10.79, + "learning_rate": 9.199916730874291e-06, + "loss": 0.0169, + "step": 34953 + }, + { + "epoch": 10.79, + "learning_rate": 9.199418216931534e-06, + "loss": 0.0151, + "step": 34954 + }, + { + "epoch": 10.79, + "learning_rate": 9.19891970499118e-06, + "loss": 0.013, + "step": 34955 + }, + { + "epoch": 10.8, + "learning_rate": 9.198421195054472e-06, + "loss": 0.0153, + "step": 34956 + }, + { + "epoch": 10.8, + "learning_rate": 9.197922687122658e-06, + "loss": 0.0153, + "step": 34957 + }, + { + "epoch": 10.8, + "learning_rate": 9.197424181196988e-06, + "loss": 0.0163, + "step": 34958 + }, + { + "epoch": 10.8, + "learning_rate": 9.196925677278703e-06, + "loss": 0.0156, + "step": 34959 + }, + { + "epoch": 10.8, + "learning_rate": 9.196427175369057e-06, + "loss": 0.0168, + "step": 34960 + }, + { + "epoch": 10.8, + "learning_rate": 9.195928675469293e-06, + "loss": 0.015, + "step": 34961 + }, + { + "epoch": 10.8, + "learning_rate": 9.195430177580658e-06, + "loss": 0.016, + "step": 34962 + }, + { + "epoch": 10.8, + "learning_rate": 9.194931681704395e-06, + "loss": 0.0151, + "step": 34963 + }, + { + "epoch": 10.8, + "learning_rate": 9.19443318784176e-06, + "loss": 0.015, + "step": 34964 + }, + { + "epoch": 10.8, + "learning_rate": 9.193934695993991e-06, + "loss": 0.0176, + "step": 34965 + }, + { + "epoch": 10.8, + "learning_rate": 9.193436206162337e-06, + "loss": 0.0138, + "step": 34966 + }, + { + "epoch": 10.8, + "learning_rate": 9.192937718348052e-06, + "loss": 0.0161, + "step": 34967 + }, + { + "epoch": 10.8, + "learning_rate": 9.192439232552373e-06, + "loss": 0.0169, + "step": 34968 + }, + { + "epoch": 10.8, + "learning_rate": 9.19194074877655e-06, + "loss": 0.0182, + "step": 34969 + }, + { + "epoch": 10.8, + "learning_rate": 9.191442267021832e-06, + "loss": 0.015, + "step": 34970 + }, + { + "epoch": 10.8, + "learning_rate": 9.190943787289465e-06, + "loss": 0.0164, + "step": 34971 + }, + { + "epoch": 10.8, + "learning_rate": 9.190445309580692e-06, + "loss": 0.0171, + "step": 34972 + }, + { + "epoch": 10.8, + "learning_rate": 9.189946833896765e-06, + "loss": 0.0179, + "step": 34973 + }, + { + "epoch": 10.8, + "learning_rate": 9.18944836023893e-06, + "loss": 0.0155, + "step": 34974 + }, + { + "epoch": 10.8, + "learning_rate": 9.188949888608433e-06, + "loss": 0.017, + "step": 34975 + }, + { + "epoch": 10.8, + "learning_rate": 9.188451419006516e-06, + "loss": 0.0145, + "step": 34976 + }, + { + "epoch": 10.8, + "learning_rate": 9.187952951434435e-06, + "loss": 0.0148, + "step": 34977 + }, + { + "epoch": 10.8, + "learning_rate": 9.187454485893429e-06, + "loss": 0.017, + "step": 34978 + }, + { + "epoch": 10.8, + "learning_rate": 9.186956022384745e-06, + "loss": 0.0154, + "step": 34979 + }, + { + "epoch": 10.8, + "learning_rate": 9.186457560909639e-06, + "loss": 0.0168, + "step": 34980 + }, + { + "epoch": 10.8, + "learning_rate": 9.185959101469346e-06, + "loss": 0.0158, + "step": 34981 + }, + { + "epoch": 10.8, + "learning_rate": 9.185460644065118e-06, + "loss": 0.016, + "step": 34982 + }, + { + "epoch": 10.8, + "learning_rate": 9.184962188698207e-06, + "loss": 0.0172, + "step": 34983 + }, + { + "epoch": 10.8, + "learning_rate": 9.184463735369846e-06, + "loss": 0.0145, + "step": 34984 + }, + { + "epoch": 10.8, + "learning_rate": 9.183965284081294e-06, + "loss": 0.016, + "step": 34985 + }, + { + "epoch": 10.8, + "learning_rate": 9.183466834833796e-06, + "loss": 0.0151, + "step": 34986 + }, + { + "epoch": 10.8, + "learning_rate": 9.182968387628591e-06, + "loss": 0.0135, + "step": 34987 + }, + { + "epoch": 10.8, + "learning_rate": 9.182469942466934e-06, + "loss": 0.0165, + "step": 34988 + }, + { + "epoch": 10.81, + "learning_rate": 9.181971499350071e-06, + "loss": 0.0148, + "step": 34989 + }, + { + "epoch": 10.81, + "learning_rate": 9.181473058279243e-06, + "loss": 0.0144, + "step": 34990 + }, + { + "epoch": 10.81, + "learning_rate": 9.1809746192557e-06, + "loss": 0.0164, + "step": 34991 + }, + { + "epoch": 10.81, + "learning_rate": 9.180476182280691e-06, + "loss": 0.0146, + "step": 34992 + }, + { + "epoch": 10.81, + "learning_rate": 9.17997774735546e-06, + "loss": 0.0148, + "step": 34993 + }, + { + "epoch": 10.81, + "learning_rate": 9.179479314481253e-06, + "loss": 0.0164, + "step": 34994 + }, + { + "epoch": 10.81, + "learning_rate": 9.178980883659321e-06, + "loss": 0.0141, + "step": 34995 + }, + { + "epoch": 10.81, + "learning_rate": 9.178482454890905e-06, + "loss": 0.0158, + "step": 34996 + }, + { + "epoch": 10.81, + "learning_rate": 9.177984028177251e-06, + "loss": 0.0173, + "step": 34997 + }, + { + "epoch": 10.81, + "learning_rate": 9.177485603519615e-06, + "loss": 0.0154, + "step": 34998 + }, + { + "epoch": 10.81, + "learning_rate": 9.176987180919236e-06, + "loss": 0.0139, + "step": 34999 + }, + { + "epoch": 10.81, + "learning_rate": 9.176488760377358e-06, + "loss": 0.0135, + "step": 35000 + }, + { + "epoch": 10.81, + "learning_rate": 9.17599034189524e-06, + "loss": 0.0145, + "step": 35001 + }, + { + "epoch": 10.81, + "learning_rate": 9.175491925474113e-06, + "loss": 0.0181, + "step": 35002 + }, + { + "epoch": 10.81, + "learning_rate": 9.174993511115234e-06, + "loss": 0.0161, + "step": 35003 + }, + { + "epoch": 10.81, + "learning_rate": 9.174495098819842e-06, + "loss": 0.0167, + "step": 35004 + }, + { + "epoch": 10.81, + "learning_rate": 9.173996688589195e-06, + "loss": 0.016, + "step": 35005 + }, + { + "epoch": 10.81, + "learning_rate": 9.17349828042453e-06, + "loss": 0.0149, + "step": 35006 + }, + { + "epoch": 10.81, + "learning_rate": 9.172999874327096e-06, + "loss": 0.0163, + "step": 35007 + }, + { + "epoch": 10.81, + "learning_rate": 9.172501470298142e-06, + "loss": 0.0153, + "step": 35008 + }, + { + "epoch": 10.81, + "learning_rate": 9.172003068338912e-06, + "loss": 0.0158, + "step": 35009 + }, + { + "epoch": 10.81, + "learning_rate": 9.171504668450651e-06, + "loss": 0.015, + "step": 35010 + }, + { + "epoch": 10.81, + "learning_rate": 9.171006270634613e-06, + "loss": 0.0139, + "step": 35011 + }, + { + "epoch": 10.81, + "learning_rate": 9.170507874892036e-06, + "loss": 0.0161, + "step": 35012 + }, + { + "epoch": 10.81, + "learning_rate": 9.170009481224171e-06, + "loss": 0.016, + "step": 35013 + }, + { + "epoch": 10.81, + "learning_rate": 9.169511089632265e-06, + "loss": 0.0169, + "step": 35014 + }, + { + "epoch": 10.81, + "learning_rate": 9.16901270011756e-06, + "loss": 0.0178, + "step": 35015 + }, + { + "epoch": 10.81, + "learning_rate": 9.168514312681307e-06, + "loss": 0.0149, + "step": 35016 + }, + { + "epoch": 10.81, + "learning_rate": 9.168015927324754e-06, + "loss": 0.0127, + "step": 35017 + }, + { + "epoch": 10.81, + "learning_rate": 9.16751754404914e-06, + "loss": 0.0172, + "step": 35018 + }, + { + "epoch": 10.81, + "learning_rate": 9.167019162855719e-06, + "loss": 0.0126, + "step": 35019 + }, + { + "epoch": 10.81, + "learning_rate": 9.166520783745738e-06, + "loss": 0.0153, + "step": 35020 + }, + { + "epoch": 10.82, + "learning_rate": 9.166022406720436e-06, + "loss": 0.0137, + "step": 35021 + }, + { + "epoch": 10.82, + "learning_rate": 9.165524031781065e-06, + "loss": 0.015, + "step": 35022 + }, + { + "epoch": 10.82, + "learning_rate": 9.165025658928874e-06, + "loss": 0.0177, + "step": 35023 + }, + { + "epoch": 10.82, + "learning_rate": 9.164527288165102e-06, + "loss": 0.0169, + "step": 35024 + }, + { + "epoch": 10.82, + "learning_rate": 9.164028919490999e-06, + "loss": 0.0147, + "step": 35025 + }, + { + "epoch": 10.82, + "learning_rate": 9.163530552907817e-06, + "loss": 0.0163, + "step": 35026 + }, + { + "epoch": 10.82, + "learning_rate": 9.163032188416795e-06, + "loss": 0.0159, + "step": 35027 + }, + { + "epoch": 10.82, + "learning_rate": 9.16253382601918e-06, + "loss": 0.015, + "step": 35028 + }, + { + "epoch": 10.82, + "learning_rate": 9.162035465716225e-06, + "loss": 0.0154, + "step": 35029 + }, + { + "epoch": 10.82, + "learning_rate": 9.16153710750917e-06, + "loss": 0.0151, + "step": 35030 + }, + { + "epoch": 10.82, + "learning_rate": 9.16103875139926e-06, + "loss": 0.0137, + "step": 35031 + }, + { + "epoch": 10.82, + "learning_rate": 9.160540397387754e-06, + "loss": 0.0155, + "step": 35032 + }, + { + "epoch": 10.82, + "learning_rate": 9.160042045475881e-06, + "loss": 0.0141, + "step": 35033 + }, + { + "epoch": 10.82, + "learning_rate": 9.159543695664899e-06, + "loss": 0.0165, + "step": 35034 + }, + { + "epoch": 10.82, + "learning_rate": 9.159045347956054e-06, + "loss": 0.0158, + "step": 35035 + }, + { + "epoch": 10.82, + "learning_rate": 9.158547002350585e-06, + "loss": 0.014, + "step": 35036 + }, + { + "epoch": 10.82, + "learning_rate": 9.158048658849747e-06, + "loss": 0.0158, + "step": 35037 + }, + { + "epoch": 10.82, + "learning_rate": 9.157550317454779e-06, + "loss": 0.0161, + "step": 35038 + }, + { + "epoch": 10.82, + "learning_rate": 9.157051978166936e-06, + "loss": 0.0168, + "step": 35039 + }, + { + "epoch": 10.82, + "learning_rate": 9.156553640987458e-06, + "loss": 0.0169, + "step": 35040 + }, + { + "epoch": 10.82, + "learning_rate": 9.156055305917591e-06, + "loss": 0.0179, + "step": 35041 + }, + { + "epoch": 10.82, + "learning_rate": 9.15555697295859e-06, + "loss": 0.0171, + "step": 35042 + }, + { + "epoch": 10.82, + "learning_rate": 9.15505864211169e-06, + "loss": 0.0156, + "step": 35043 + }, + { + "epoch": 10.82, + "learning_rate": 9.154560313378143e-06, + "loss": 0.0158, + "step": 35044 + }, + { + "epoch": 10.82, + "learning_rate": 9.154061986759197e-06, + "loss": 0.0152, + "step": 35045 + }, + { + "epoch": 10.82, + "learning_rate": 9.153563662256092e-06, + "loss": 0.0175, + "step": 35046 + }, + { + "epoch": 10.82, + "learning_rate": 9.153065339870081e-06, + "loss": 0.0152, + "step": 35047 + }, + { + "epoch": 10.82, + "learning_rate": 9.15256701960241e-06, + "loss": 0.0161, + "step": 35048 + }, + { + "epoch": 10.82, + "learning_rate": 9.152068701454319e-06, + "loss": 0.0149, + "step": 35049 + }, + { + "epoch": 10.82, + "learning_rate": 9.15157038542706e-06, + "loss": 0.0169, + "step": 35050 + }, + { + "epoch": 10.82, + "learning_rate": 9.151072071521883e-06, + "loss": 0.0178, + "step": 35051 + }, + { + "epoch": 10.82, + "learning_rate": 9.150573759740025e-06, + "loss": 0.0163, + "step": 35052 + }, + { + "epoch": 10.83, + "learning_rate": 9.150075450082738e-06, + "loss": 0.0149, + "step": 35053 + }, + { + "epoch": 10.83, + "learning_rate": 9.149577142551268e-06, + "loss": 0.0171, + "step": 35054 + }, + { + "epoch": 10.83, + "learning_rate": 9.149078837146862e-06, + "loss": 0.0161, + "step": 35055 + }, + { + "epoch": 10.83, + "learning_rate": 9.14858053387076e-06, + "loss": 0.0172, + "step": 35056 + }, + { + "epoch": 10.83, + "learning_rate": 9.148082232724219e-06, + "loss": 0.014, + "step": 35057 + }, + { + "epoch": 10.83, + "learning_rate": 9.147583933708476e-06, + "loss": 0.0206, + "step": 35058 + }, + { + "epoch": 10.83, + "learning_rate": 9.147085636824779e-06, + "loss": 0.0158, + "step": 35059 + }, + { + "epoch": 10.83, + "learning_rate": 9.146587342074382e-06, + "loss": 0.014, + "step": 35060 + }, + { + "epoch": 10.83, + "learning_rate": 9.146089049458523e-06, + "loss": 0.0171, + "step": 35061 + }, + { + "epoch": 10.83, + "learning_rate": 9.145590758978452e-06, + "loss": 0.0151, + "step": 35062 + }, + { + "epoch": 10.83, + "learning_rate": 9.145092470635415e-06, + "loss": 0.0152, + "step": 35063 + }, + { + "epoch": 10.83, + "learning_rate": 9.144594184430656e-06, + "loss": 0.0157, + "step": 35064 + }, + { + "epoch": 10.83, + "learning_rate": 9.144095900365422e-06, + "loss": 0.016, + "step": 35065 + }, + { + "epoch": 10.83, + "learning_rate": 9.143597618440964e-06, + "loss": 0.0153, + "step": 35066 + }, + { + "epoch": 10.83, + "learning_rate": 9.14309933865852e-06, + "loss": 0.0145, + "step": 35067 + }, + { + "epoch": 10.83, + "learning_rate": 9.142601061019343e-06, + "loss": 0.0168, + "step": 35068 + }, + { + "epoch": 10.83, + "learning_rate": 9.14210278552468e-06, + "loss": 0.0138, + "step": 35069 + }, + { + "epoch": 10.83, + "learning_rate": 9.14160451217577e-06, + "loss": 0.018, + "step": 35070 + }, + { + "epoch": 10.83, + "learning_rate": 9.141106240973864e-06, + "loss": 0.0162, + "step": 35071 + }, + { + "epoch": 10.83, + "learning_rate": 9.14060797192021e-06, + "loss": 0.0167, + "step": 35072 + }, + { + "epoch": 10.83, + "learning_rate": 9.140109705016053e-06, + "loss": 0.0172, + "step": 35073 + }, + { + "epoch": 10.83, + "learning_rate": 9.139611440262633e-06, + "loss": 0.0188, + "step": 35074 + }, + { + "epoch": 10.83, + "learning_rate": 9.139113177661206e-06, + "loss": 0.015, + "step": 35075 + }, + { + "epoch": 10.83, + "learning_rate": 9.138614917213016e-06, + "loss": 0.0161, + "step": 35076 + }, + { + "epoch": 10.83, + "learning_rate": 9.138116658919303e-06, + "loss": 0.0151, + "step": 35077 + }, + { + "epoch": 10.83, + "learning_rate": 9.137618402781318e-06, + "loss": 0.0155, + "step": 35078 + }, + { + "epoch": 10.83, + "learning_rate": 9.13712014880031e-06, + "loss": 0.0145, + "step": 35079 + }, + { + "epoch": 10.83, + "learning_rate": 9.136621896977517e-06, + "loss": 0.0165, + "step": 35080 + }, + { + "epoch": 10.83, + "learning_rate": 9.136123647314193e-06, + "loss": 0.0177, + "step": 35081 + }, + { + "epoch": 10.83, + "learning_rate": 9.135625399811584e-06, + "loss": 0.0135, + "step": 35082 + }, + { + "epoch": 10.83, + "learning_rate": 9.135127154470931e-06, + "loss": 0.015, + "step": 35083 + }, + { + "epoch": 10.83, + "learning_rate": 9.13462891129348e-06, + "loss": 0.0179, + "step": 35084 + }, + { + "epoch": 10.83, + "learning_rate": 9.134130670280483e-06, + "loss": 0.0152, + "step": 35085 + }, + { + "epoch": 10.84, + "learning_rate": 9.133632431433183e-06, + "loss": 0.014, + "step": 35086 + }, + { + "epoch": 10.84, + "learning_rate": 9.133134194752824e-06, + "loss": 0.0145, + "step": 35087 + }, + { + "epoch": 10.84, + "learning_rate": 9.132635960240658e-06, + "loss": 0.016, + "step": 35088 + }, + { + "epoch": 10.84, + "learning_rate": 9.132137727897926e-06, + "loss": 0.0161, + "step": 35089 + }, + { + "epoch": 10.84, + "learning_rate": 9.131639497725873e-06, + "loss": 0.0142, + "step": 35090 + }, + { + "epoch": 10.84, + "learning_rate": 9.131141269725755e-06, + "loss": 0.0162, + "step": 35091 + }, + { + "epoch": 10.84, + "learning_rate": 9.130643043898805e-06, + "loss": 0.0172, + "step": 35092 + }, + { + "epoch": 10.84, + "learning_rate": 9.130144820246277e-06, + "loss": 0.0171, + "step": 35093 + }, + { + "epoch": 10.84, + "learning_rate": 9.129646598769417e-06, + "loss": 0.0153, + "step": 35094 + }, + { + "epoch": 10.84, + "learning_rate": 9.129148379469466e-06, + "loss": 0.0166, + "step": 35095 + }, + { + "epoch": 10.84, + "learning_rate": 9.128650162347677e-06, + "loss": 0.0162, + "step": 35096 + }, + { + "epoch": 10.84, + "learning_rate": 9.128151947405292e-06, + "loss": 0.0148, + "step": 35097 + }, + { + "epoch": 10.84, + "learning_rate": 9.127653734643556e-06, + "loss": 0.0168, + "step": 35098 + }, + { + "epoch": 10.84, + "learning_rate": 9.12715552406372e-06, + "loss": 0.0158, + "step": 35099 + }, + { + "epoch": 10.84, + "learning_rate": 9.126657315667029e-06, + "loss": 0.0165, + "step": 35100 + }, + { + "epoch": 10.84, + "learning_rate": 9.126159109454723e-06, + "loss": 0.0161, + "step": 35101 + }, + { + "epoch": 10.84, + "learning_rate": 9.125660905428053e-06, + "loss": 0.0155, + "step": 35102 + }, + { + "epoch": 10.84, + "learning_rate": 9.125162703588265e-06, + "loss": 0.0153, + "step": 35103 + }, + { + "epoch": 10.84, + "learning_rate": 9.124664503936606e-06, + "loss": 0.0149, + "step": 35104 + }, + { + "epoch": 10.84, + "learning_rate": 9.124166306474318e-06, + "loss": 0.0149, + "step": 35105 + }, + { + "epoch": 10.84, + "learning_rate": 9.123668111202652e-06, + "loss": 0.0166, + "step": 35106 + }, + { + "epoch": 10.84, + "learning_rate": 9.123169918122853e-06, + "loss": 0.0151, + "step": 35107 + }, + { + "epoch": 10.84, + "learning_rate": 9.122671727236163e-06, + "loss": 0.0185, + "step": 35108 + }, + { + "epoch": 10.84, + "learning_rate": 9.122173538543832e-06, + "loss": 0.0163, + "step": 35109 + }, + { + "epoch": 10.84, + "learning_rate": 9.121675352047108e-06, + "loss": 0.0149, + "step": 35110 + }, + { + "epoch": 10.84, + "learning_rate": 9.121177167747232e-06, + "loss": 0.0154, + "step": 35111 + }, + { + "epoch": 10.84, + "learning_rate": 9.12067898564545e-06, + "loss": 0.0168, + "step": 35112 + }, + { + "epoch": 10.84, + "learning_rate": 9.120180805743013e-06, + "loss": 0.0152, + "step": 35113 + }, + { + "epoch": 10.84, + "learning_rate": 9.119682628041165e-06, + "loss": 0.017, + "step": 35114 + }, + { + "epoch": 10.84, + "learning_rate": 9.119184452541147e-06, + "loss": 0.0192, + "step": 35115 + }, + { + "epoch": 10.84, + "learning_rate": 9.118686279244213e-06, + "loss": 0.0149, + "step": 35116 + }, + { + "epoch": 10.84, + "learning_rate": 9.118188108151605e-06, + "loss": 0.0156, + "step": 35117 + }, + { + "epoch": 10.85, + "learning_rate": 9.117689939264567e-06, + "loss": 0.0179, + "step": 35118 + }, + { + "epoch": 10.85, + "learning_rate": 9.11719177258435e-06, + "loss": 0.015, + "step": 35119 + }, + { + "epoch": 10.85, + "learning_rate": 9.116693608112196e-06, + "loss": 0.016, + "step": 35120 + }, + { + "epoch": 10.85, + "learning_rate": 9.116195445849353e-06, + "loss": 0.0153, + "step": 35121 + }, + { + "epoch": 10.85, + "learning_rate": 9.11569728579707e-06, + "loss": 0.0143, + "step": 35122 + }, + { + "epoch": 10.85, + "learning_rate": 9.115199127956583e-06, + "loss": 0.016, + "step": 35123 + }, + { + "epoch": 10.85, + "learning_rate": 9.114700972329147e-06, + "loss": 0.0149, + "step": 35124 + }, + { + "epoch": 10.85, + "learning_rate": 9.114202818916007e-06, + "loss": 0.0141, + "step": 35125 + }, + { + "epoch": 10.85, + "learning_rate": 9.113704667718405e-06, + "loss": 0.0158, + "step": 35126 + }, + { + "epoch": 10.85, + "learning_rate": 9.113206518737589e-06, + "loss": 0.0145, + "step": 35127 + }, + { + "epoch": 10.85, + "learning_rate": 9.112708371974809e-06, + "loss": 0.0143, + "step": 35128 + }, + { + "epoch": 10.85, + "learning_rate": 9.112210227431302e-06, + "loss": 0.0175, + "step": 35129 + }, + { + "epoch": 10.85, + "learning_rate": 9.111712085108321e-06, + "loss": 0.0181, + "step": 35130 + }, + { + "epoch": 10.85, + "learning_rate": 9.111213945007113e-06, + "loss": 0.0154, + "step": 35131 + }, + { + "epoch": 10.85, + "learning_rate": 9.110715807128919e-06, + "loss": 0.0162, + "step": 35132 + }, + { + "epoch": 10.85, + "learning_rate": 9.110217671474984e-06, + "loss": 0.0189, + "step": 35133 + }, + { + "epoch": 10.85, + "learning_rate": 9.109719538046562e-06, + "loss": 0.0157, + "step": 35134 + }, + { + "epoch": 10.85, + "learning_rate": 9.109221406844892e-06, + "loss": 0.0159, + "step": 35135 + }, + { + "epoch": 10.85, + "learning_rate": 9.10872327787122e-06, + "loss": 0.0138, + "step": 35136 + }, + { + "epoch": 10.85, + "learning_rate": 9.108225151126792e-06, + "loss": 0.0153, + "step": 35137 + }, + { + "epoch": 10.85, + "learning_rate": 9.107727026612862e-06, + "loss": 0.0154, + "step": 35138 + }, + { + "epoch": 10.85, + "learning_rate": 9.107228904330664e-06, + "loss": 0.0166, + "step": 35139 + }, + { + "epoch": 10.85, + "learning_rate": 9.10673078428145e-06, + "loss": 0.0174, + "step": 35140 + }, + { + "epoch": 10.85, + "learning_rate": 9.106232666466469e-06, + "loss": 0.0158, + "step": 35141 + }, + { + "epoch": 10.85, + "learning_rate": 9.10573455088696e-06, + "loss": 0.0156, + "step": 35142 + }, + { + "epoch": 10.85, + "learning_rate": 9.10523643754417e-06, + "loss": 0.02, + "step": 35143 + }, + { + "epoch": 10.85, + "learning_rate": 9.10473832643935e-06, + "loss": 0.0184, + "step": 35144 + }, + { + "epoch": 10.85, + "learning_rate": 9.104240217573743e-06, + "loss": 0.0149, + "step": 35145 + }, + { + "epoch": 10.85, + "learning_rate": 9.10374211094859e-06, + "loss": 0.0151, + "step": 35146 + }, + { + "epoch": 10.85, + "learning_rate": 9.103244006565149e-06, + "loss": 0.0166, + "step": 35147 + }, + { + "epoch": 10.85, + "learning_rate": 9.102745904424655e-06, + "loss": 0.0161, + "step": 35148 + }, + { + "epoch": 10.85, + "learning_rate": 9.102247804528354e-06, + "loss": 0.014, + "step": 35149 + }, + { + "epoch": 10.86, + "learning_rate": 9.101749706877501e-06, + "loss": 0.0157, + "step": 35150 + }, + { + "epoch": 10.86, + "learning_rate": 9.10125161147333e-06, + "loss": 0.0159, + "step": 35151 + }, + { + "epoch": 10.86, + "learning_rate": 9.100753518317095e-06, + "loss": 0.0157, + "step": 35152 + }, + { + "epoch": 10.86, + "learning_rate": 9.100255427410042e-06, + "loss": 0.0162, + "step": 35153 + }, + { + "epoch": 10.86, + "learning_rate": 9.099757338753408e-06, + "loss": 0.0169, + "step": 35154 + }, + { + "epoch": 10.86, + "learning_rate": 9.099259252348451e-06, + "loss": 0.0166, + "step": 35155 + }, + { + "epoch": 10.86, + "learning_rate": 9.09876116819641e-06, + "loss": 0.0168, + "step": 35156 + }, + { + "epoch": 10.86, + "learning_rate": 9.098263086298528e-06, + "loss": 0.0163, + "step": 35157 + }, + { + "epoch": 10.86, + "learning_rate": 9.097765006656057e-06, + "loss": 0.0155, + "step": 35158 + }, + { + "epoch": 10.86, + "learning_rate": 9.097266929270242e-06, + "loss": 0.0158, + "step": 35159 + }, + { + "epoch": 10.86, + "learning_rate": 9.096768854142325e-06, + "loss": 0.0146, + "step": 35160 + }, + { + "epoch": 10.86, + "learning_rate": 9.096270781273552e-06, + "loss": 0.0189, + "step": 35161 + }, + { + "epoch": 10.86, + "learning_rate": 9.095772710665175e-06, + "loss": 0.0144, + "step": 35162 + }, + { + "epoch": 10.86, + "learning_rate": 9.095274642318433e-06, + "loss": 0.0163, + "step": 35163 + }, + { + "epoch": 10.86, + "learning_rate": 9.09477657623457e-06, + "loss": 0.0192, + "step": 35164 + }, + { + "epoch": 10.86, + "learning_rate": 9.094278512414843e-06, + "loss": 0.0139, + "step": 35165 + }, + { + "epoch": 10.86, + "learning_rate": 9.093780450860487e-06, + "loss": 0.0143, + "step": 35166 + }, + { + "epoch": 10.86, + "learning_rate": 9.093282391572751e-06, + "loss": 0.0148, + "step": 35167 + }, + { + "epoch": 10.86, + "learning_rate": 9.092784334552883e-06, + "loss": 0.0146, + "step": 35168 + }, + { + "epoch": 10.86, + "learning_rate": 9.092286279802128e-06, + "loss": 0.018, + "step": 35169 + }, + { + "epoch": 10.86, + "learning_rate": 9.091788227321727e-06, + "loss": 0.0137, + "step": 35170 + }, + { + "epoch": 10.86, + "learning_rate": 9.091290177112929e-06, + "loss": 0.0145, + "step": 35171 + }, + { + "epoch": 10.86, + "learning_rate": 9.090792129176984e-06, + "loss": 0.0159, + "step": 35172 + }, + { + "epoch": 10.86, + "learning_rate": 9.090294083515131e-06, + "loss": 0.0149, + "step": 35173 + }, + { + "epoch": 10.86, + "learning_rate": 9.089796040128618e-06, + "loss": 0.0148, + "step": 35174 + }, + { + "epoch": 10.86, + "learning_rate": 9.089297999018693e-06, + "loss": 0.017, + "step": 35175 + }, + { + "epoch": 10.86, + "learning_rate": 9.088799960186599e-06, + "loss": 0.0181, + "step": 35176 + }, + { + "epoch": 10.86, + "learning_rate": 9.08830192363358e-06, + "loss": 0.0174, + "step": 35177 + }, + { + "epoch": 10.86, + "learning_rate": 9.087803889360889e-06, + "loss": 0.0143, + "step": 35178 + }, + { + "epoch": 10.86, + "learning_rate": 9.087305857369764e-06, + "loss": 0.018, + "step": 35179 + }, + { + "epoch": 10.86, + "learning_rate": 9.086807827661454e-06, + "loss": 0.013, + "step": 35180 + }, + { + "epoch": 10.86, + "learning_rate": 9.086309800237207e-06, + "loss": 0.0162, + "step": 35181 + }, + { + "epoch": 10.86, + "learning_rate": 9.08581177509826e-06, + "loss": 0.0159, + "step": 35182 + }, + { + "epoch": 10.87, + "learning_rate": 9.085313752245867e-06, + "loss": 0.0166, + "step": 35183 + }, + { + "epoch": 10.87, + "learning_rate": 9.084815731681274e-06, + "loss": 0.0147, + "step": 35184 + }, + { + "epoch": 10.87, + "learning_rate": 9.08431771340572e-06, + "loss": 0.0177, + "step": 35185 + }, + { + "epoch": 10.87, + "learning_rate": 9.083819697420455e-06, + "loss": 0.0146, + "step": 35186 + }, + { + "epoch": 10.87, + "learning_rate": 9.083321683726727e-06, + "loss": 0.0179, + "step": 35187 + }, + { + "epoch": 10.87, + "learning_rate": 9.082823672325773e-06, + "loss": 0.0179, + "step": 35188 + }, + { + "epoch": 10.87, + "learning_rate": 9.082325663218849e-06, + "loss": 0.0156, + "step": 35189 + }, + { + "epoch": 10.87, + "learning_rate": 9.081827656407195e-06, + "loss": 0.0161, + "step": 35190 + }, + { + "epoch": 10.87, + "learning_rate": 9.081329651892059e-06, + "loss": 0.0162, + "step": 35191 + }, + { + "epoch": 10.87, + "learning_rate": 9.08083164967468e-06, + "loss": 0.0149, + "step": 35192 + }, + { + "epoch": 10.87, + "learning_rate": 9.080333649756315e-06, + "loss": 0.0178, + "step": 35193 + }, + { + "epoch": 10.87, + "learning_rate": 9.0798356521382e-06, + "loss": 0.0167, + "step": 35194 + }, + { + "epoch": 10.87, + "learning_rate": 9.079337656821581e-06, + "loss": 0.0141, + "step": 35195 + }, + { + "epoch": 10.87, + "learning_rate": 9.078839663807712e-06, + "loss": 0.016, + "step": 35196 + }, + { + "epoch": 10.87, + "learning_rate": 9.07834167309783e-06, + "loss": 0.0174, + "step": 35197 + }, + { + "epoch": 10.87, + "learning_rate": 9.077843684693181e-06, + "loss": 0.0144, + "step": 35198 + }, + { + "epoch": 10.87, + "learning_rate": 9.077345698595021e-06, + "loss": 0.0174, + "step": 35199 + }, + { + "epoch": 10.87, + "learning_rate": 9.076847714804581e-06, + "loss": 0.0152, + "step": 35200 + }, + { + "epoch": 10.87, + "learning_rate": 9.076349733323115e-06, + "loss": 0.0152, + "step": 35201 + }, + { + "epoch": 10.87, + "learning_rate": 9.075851754151864e-06, + "loss": 0.0172, + "step": 35202 + }, + { + "epoch": 10.87, + "learning_rate": 9.075353777292082e-06, + "loss": 0.016, + "step": 35203 + }, + { + "epoch": 10.87, + "learning_rate": 9.074855802745007e-06, + "loss": 0.0161, + "step": 35204 + }, + { + "epoch": 10.87, + "learning_rate": 9.074357830511881e-06, + "loss": 0.0148, + "step": 35205 + }, + { + "epoch": 10.87, + "learning_rate": 9.073859860593963e-06, + "loss": 0.0163, + "step": 35206 + }, + { + "epoch": 10.87, + "learning_rate": 9.073361892992486e-06, + "loss": 0.0147, + "step": 35207 + }, + { + "epoch": 10.87, + "learning_rate": 9.0728639277087e-06, + "loss": 0.0153, + "step": 35208 + }, + { + "epoch": 10.87, + "learning_rate": 9.072365964743855e-06, + "loss": 0.0169, + "step": 35209 + }, + { + "epoch": 10.87, + "learning_rate": 9.071868004099185e-06, + "loss": 0.0168, + "step": 35210 + }, + { + "epoch": 10.87, + "learning_rate": 9.071370045775945e-06, + "loss": 0.018, + "step": 35211 + }, + { + "epoch": 10.87, + "learning_rate": 9.07087208977538e-06, + "loss": 0.0146, + "step": 35212 + }, + { + "epoch": 10.87, + "learning_rate": 9.070374136098729e-06, + "loss": 0.0149, + "step": 35213 + }, + { + "epoch": 10.87, + "learning_rate": 9.069876184747244e-06, + "loss": 0.0159, + "step": 35214 + }, + { + "epoch": 10.88, + "learning_rate": 9.069378235722173e-06, + "loss": 0.0163, + "step": 35215 + }, + { + "epoch": 10.88, + "learning_rate": 9.068880289024749e-06, + "loss": 0.0149, + "step": 35216 + }, + { + "epoch": 10.88, + "learning_rate": 9.06838234465623e-06, + "loss": 0.0156, + "step": 35217 + }, + { + "epoch": 10.88, + "learning_rate": 9.067884402617856e-06, + "loss": 0.0161, + "step": 35218 + }, + { + "epoch": 10.88, + "learning_rate": 9.067386462910874e-06, + "loss": 0.018, + "step": 35219 + }, + { + "epoch": 10.88, + "learning_rate": 9.066888525536525e-06, + "loss": 0.0155, + "step": 35220 + }, + { + "epoch": 10.88, + "learning_rate": 9.06639059049606e-06, + "loss": 0.0161, + "step": 35221 + }, + { + "epoch": 10.88, + "learning_rate": 9.065892657790724e-06, + "loss": 0.014, + "step": 35222 + }, + { + "epoch": 10.88, + "learning_rate": 9.065394727421756e-06, + "loss": 0.0172, + "step": 35223 + }, + { + "epoch": 10.88, + "learning_rate": 9.064896799390413e-06, + "loss": 0.0177, + "step": 35224 + }, + { + "epoch": 10.88, + "learning_rate": 9.06439887369793e-06, + "loss": 0.0153, + "step": 35225 + }, + { + "epoch": 10.88, + "learning_rate": 9.063900950345554e-06, + "loss": 0.0161, + "step": 35226 + }, + { + "epoch": 10.88, + "learning_rate": 9.063403029334537e-06, + "loss": 0.0151, + "step": 35227 + }, + { + "epoch": 10.88, + "learning_rate": 9.062905110666116e-06, + "loss": 0.0153, + "step": 35228 + }, + { + "epoch": 10.88, + "learning_rate": 9.062407194341543e-06, + "loss": 0.0146, + "step": 35229 + }, + { + "epoch": 10.88, + "learning_rate": 9.061909280362063e-06, + "loss": 0.0168, + "step": 35230 + }, + { + "epoch": 10.88, + "learning_rate": 9.061411368728912e-06, + "loss": 0.0164, + "step": 35231 + }, + { + "epoch": 10.88, + "learning_rate": 9.060913459443346e-06, + "loss": 0.0173, + "step": 35232 + }, + { + "epoch": 10.88, + "learning_rate": 9.060415552506605e-06, + "loss": 0.0149, + "step": 35233 + }, + { + "epoch": 10.88, + "learning_rate": 9.059917647919938e-06, + "loss": 0.0141, + "step": 35234 + }, + { + "epoch": 10.88, + "learning_rate": 9.059419745684588e-06, + "loss": 0.0171, + "step": 35235 + }, + { + "epoch": 10.88, + "learning_rate": 9.0589218458018e-06, + "loss": 0.0165, + "step": 35236 + }, + { + "epoch": 10.88, + "learning_rate": 9.058423948272821e-06, + "loss": 0.0175, + "step": 35237 + }, + { + "epoch": 10.88, + "learning_rate": 9.057926053098896e-06, + "loss": 0.0166, + "step": 35238 + }, + { + "epoch": 10.88, + "learning_rate": 9.057428160281267e-06, + "loss": 0.0153, + "step": 35239 + }, + { + "epoch": 10.88, + "learning_rate": 9.056930269821188e-06, + "loss": 0.0179, + "step": 35240 + }, + { + "epoch": 10.88, + "learning_rate": 9.056432381719893e-06, + "loss": 0.0149, + "step": 35241 + }, + { + "epoch": 10.88, + "learning_rate": 9.055934495978635e-06, + "loss": 0.0142, + "step": 35242 + }, + { + "epoch": 10.88, + "learning_rate": 9.055436612598657e-06, + "loss": 0.0159, + "step": 35243 + }, + { + "epoch": 10.88, + "learning_rate": 9.054938731581202e-06, + "loss": 0.0155, + "step": 35244 + }, + { + "epoch": 10.88, + "learning_rate": 9.05444085292752e-06, + "loss": 0.0152, + "step": 35245 + }, + { + "epoch": 10.88, + "learning_rate": 9.053942976638854e-06, + "loss": 0.0134, + "step": 35246 + }, + { + "epoch": 10.88, + "learning_rate": 9.053445102716447e-06, + "loss": 0.0152, + "step": 35247 + }, + { + "epoch": 10.89, + "learning_rate": 9.052947231161547e-06, + "loss": 0.015, + "step": 35248 + }, + { + "epoch": 10.89, + "learning_rate": 9.052449361975402e-06, + "loss": 0.0151, + "step": 35249 + }, + { + "epoch": 10.89, + "learning_rate": 9.05195149515925e-06, + "loss": 0.0154, + "step": 35250 + }, + { + "epoch": 10.89, + "learning_rate": 9.05145363071434e-06, + "loss": 0.0158, + "step": 35251 + }, + { + "epoch": 10.89, + "learning_rate": 9.050955768641922e-06, + "loss": 0.015, + "step": 35252 + }, + { + "epoch": 10.89, + "learning_rate": 9.050457908943232e-06, + "loss": 0.017, + "step": 35253 + }, + { + "epoch": 10.89, + "learning_rate": 9.049960051619521e-06, + "loss": 0.0162, + "step": 35254 + }, + { + "epoch": 10.89, + "learning_rate": 9.049462196672036e-06, + "loss": 0.0169, + "step": 35255 + }, + { + "epoch": 10.89, + "learning_rate": 9.048964344102016e-06, + "loss": 0.0169, + "step": 35256 + }, + { + "epoch": 10.89, + "learning_rate": 9.048466493910709e-06, + "loss": 0.0136, + "step": 35257 + }, + { + "epoch": 10.89, + "learning_rate": 9.047968646099368e-06, + "loss": 0.0172, + "step": 35258 + }, + { + "epoch": 10.89, + "learning_rate": 9.047470800669224e-06, + "loss": 0.0162, + "step": 35259 + }, + { + "epoch": 10.89, + "learning_rate": 9.04697295762153e-06, + "loss": 0.0167, + "step": 35260 + }, + { + "epoch": 10.89, + "learning_rate": 9.046475116957534e-06, + "loss": 0.016, + "step": 35261 + }, + { + "epoch": 10.89, + "learning_rate": 9.045977278678473e-06, + "loss": 0.0157, + "step": 35262 + }, + { + "epoch": 10.89, + "learning_rate": 9.0454794427856e-06, + "loss": 0.0162, + "step": 35263 + }, + { + "epoch": 10.89, + "learning_rate": 9.044981609280157e-06, + "loss": 0.0162, + "step": 35264 + }, + { + "epoch": 10.89, + "learning_rate": 9.044483778163387e-06, + "loss": 0.0154, + "step": 35265 + }, + { + "epoch": 10.89, + "learning_rate": 9.043985949436538e-06, + "loss": 0.0155, + "step": 35266 + }, + { + "epoch": 10.89, + "learning_rate": 9.043488123100853e-06, + "loss": 0.0162, + "step": 35267 + }, + { + "epoch": 10.89, + "learning_rate": 9.042990299157584e-06, + "loss": 0.0162, + "step": 35268 + }, + { + "epoch": 10.89, + "learning_rate": 9.042492477607965e-06, + "loss": 0.0146, + "step": 35269 + }, + { + "epoch": 10.89, + "learning_rate": 9.04199465845325e-06, + "loss": 0.0167, + "step": 35270 + }, + { + "epoch": 10.89, + "learning_rate": 9.041496841694684e-06, + "loss": 0.0168, + "step": 35271 + }, + { + "epoch": 10.89, + "learning_rate": 9.040999027333503e-06, + "loss": 0.0152, + "step": 35272 + }, + { + "epoch": 10.89, + "learning_rate": 9.040501215370961e-06, + "loss": 0.0162, + "step": 35273 + }, + { + "epoch": 10.89, + "learning_rate": 9.040003405808303e-06, + "loss": 0.0161, + "step": 35274 + }, + { + "epoch": 10.89, + "learning_rate": 9.039505598646767e-06, + "loss": 0.0152, + "step": 35275 + }, + { + "epoch": 10.89, + "learning_rate": 9.039007793887605e-06, + "loss": 0.0154, + "step": 35276 + }, + { + "epoch": 10.89, + "learning_rate": 9.038509991532061e-06, + "loss": 0.0134, + "step": 35277 + }, + { + "epoch": 10.89, + "learning_rate": 9.038012191581375e-06, + "loss": 0.016, + "step": 35278 + }, + { + "epoch": 10.89, + "learning_rate": 9.037514394036799e-06, + "loss": 0.0159, + "step": 35279 + }, + { + "epoch": 10.9, + "learning_rate": 9.037016598899577e-06, + "loss": 0.0153, + "step": 35280 + }, + { + "epoch": 10.9, + "learning_rate": 9.03651880617095e-06, + "loss": 0.015, + "step": 35281 + }, + { + "epoch": 10.9, + "learning_rate": 9.036021015852163e-06, + "loss": 0.016, + "step": 35282 + }, + { + "epoch": 10.9, + "learning_rate": 9.035523227944465e-06, + "loss": 0.0165, + "step": 35283 + }, + { + "epoch": 10.9, + "learning_rate": 9.0350254424491e-06, + "loss": 0.0143, + "step": 35284 + }, + { + "epoch": 10.9, + "learning_rate": 9.034527659367311e-06, + "loss": 0.0163, + "step": 35285 + }, + { + "epoch": 10.9, + "learning_rate": 9.034029878700346e-06, + "loss": 0.0161, + "step": 35286 + }, + { + "epoch": 10.9, + "learning_rate": 9.033532100449448e-06, + "loss": 0.0154, + "step": 35287 + }, + { + "epoch": 10.9, + "learning_rate": 9.033034324615861e-06, + "loss": 0.0144, + "step": 35288 + }, + { + "epoch": 10.9, + "learning_rate": 9.032536551200836e-06, + "loss": 0.0159, + "step": 35289 + }, + { + "epoch": 10.9, + "learning_rate": 9.032038780205609e-06, + "loss": 0.014, + "step": 35290 + }, + { + "epoch": 10.9, + "learning_rate": 9.031541011631431e-06, + "loss": 0.0151, + "step": 35291 + }, + { + "epoch": 10.9, + "learning_rate": 9.031043245479547e-06, + "loss": 0.0169, + "step": 35292 + }, + { + "epoch": 10.9, + "learning_rate": 9.030545481751196e-06, + "loss": 0.0156, + "step": 35293 + }, + { + "epoch": 10.9, + "learning_rate": 9.03004772044763e-06, + "loss": 0.0153, + "step": 35294 + }, + { + "epoch": 10.9, + "learning_rate": 9.029549961570094e-06, + "loss": 0.0166, + "step": 35295 + }, + { + "epoch": 10.9, + "learning_rate": 9.029052205119828e-06, + "loss": 0.0181, + "step": 35296 + }, + { + "epoch": 10.9, + "learning_rate": 9.02855445109808e-06, + "loss": 0.0155, + "step": 35297 + }, + { + "epoch": 10.9, + "learning_rate": 9.028056699506095e-06, + "loss": 0.015, + "step": 35298 + }, + { + "epoch": 10.9, + "learning_rate": 9.027558950345117e-06, + "loss": 0.0205, + "step": 35299 + }, + { + "epoch": 10.9, + "learning_rate": 9.02706120361639e-06, + "loss": 0.0171, + "step": 35300 + }, + { + "epoch": 10.9, + "learning_rate": 9.026563459321163e-06, + "loss": 0.0163, + "step": 35301 + }, + { + "epoch": 10.9, + "learning_rate": 9.026065717460678e-06, + "loss": 0.0162, + "step": 35302 + }, + { + "epoch": 10.9, + "learning_rate": 9.025567978036178e-06, + "loss": 0.0145, + "step": 35303 + }, + { + "epoch": 10.9, + "learning_rate": 9.025070241048911e-06, + "loss": 0.0149, + "step": 35304 + }, + { + "epoch": 10.9, + "learning_rate": 9.024572506500124e-06, + "loss": 0.0146, + "step": 35305 + }, + { + "epoch": 10.9, + "learning_rate": 9.024074774391056e-06, + "loss": 0.0158, + "step": 35306 + }, + { + "epoch": 10.9, + "learning_rate": 9.023577044722955e-06, + "loss": 0.0159, + "step": 35307 + }, + { + "epoch": 10.9, + "learning_rate": 9.023079317497069e-06, + "loss": 0.0157, + "step": 35308 + }, + { + "epoch": 10.9, + "learning_rate": 9.022581592714637e-06, + "loss": 0.0192, + "step": 35309 + }, + { + "epoch": 10.9, + "learning_rate": 9.022083870376906e-06, + "loss": 0.016, + "step": 35310 + }, + { + "epoch": 10.9, + "learning_rate": 9.021586150485124e-06, + "loss": 0.0156, + "step": 35311 + }, + { + "epoch": 10.91, + "learning_rate": 9.021088433040532e-06, + "loss": 0.0181, + "step": 35312 + }, + { + "epoch": 10.91, + "learning_rate": 9.020590718044375e-06, + "loss": 0.0153, + "step": 35313 + }, + { + "epoch": 10.91, + "learning_rate": 9.020093005497904e-06, + "loss": 0.0155, + "step": 35314 + }, + { + "epoch": 10.91, + "learning_rate": 9.019595295402356e-06, + "loss": 0.0161, + "step": 35315 + }, + { + "epoch": 10.91, + "learning_rate": 9.019097587758978e-06, + "loss": 0.0154, + "step": 35316 + }, + { + "epoch": 10.91, + "learning_rate": 9.018599882569018e-06, + "loss": 0.016, + "step": 35317 + }, + { + "epoch": 10.91, + "learning_rate": 9.018102179833717e-06, + "loss": 0.0166, + "step": 35318 + }, + { + "epoch": 10.91, + "learning_rate": 9.017604479554323e-06, + "loss": 0.0142, + "step": 35319 + }, + { + "epoch": 10.91, + "learning_rate": 9.01710678173208e-06, + "loss": 0.0165, + "step": 35320 + }, + { + "epoch": 10.91, + "learning_rate": 9.016609086368228e-06, + "loss": 0.0133, + "step": 35321 + }, + { + "epoch": 10.91, + "learning_rate": 9.016111393464019e-06, + "loss": 0.0147, + "step": 35322 + }, + { + "epoch": 10.91, + "learning_rate": 9.015613703020696e-06, + "loss": 0.0169, + "step": 35323 + }, + { + "epoch": 10.91, + "learning_rate": 9.0151160150395e-06, + "loss": 0.0162, + "step": 35324 + }, + { + "epoch": 10.91, + "learning_rate": 9.01461832952168e-06, + "loss": 0.0176, + "step": 35325 + }, + { + "epoch": 10.91, + "learning_rate": 9.014120646468482e-06, + "loss": 0.0176, + "step": 35326 + }, + { + "epoch": 10.91, + "learning_rate": 9.013622965881143e-06, + "loss": 0.0154, + "step": 35327 + }, + { + "epoch": 10.91, + "learning_rate": 9.013125287760914e-06, + "loss": 0.0154, + "step": 35328 + }, + { + "epoch": 10.91, + "learning_rate": 9.012627612109042e-06, + "loss": 0.0146, + "step": 35329 + }, + { + "epoch": 10.91, + "learning_rate": 9.012129938926766e-06, + "loss": 0.0175, + "step": 35330 + }, + { + "epoch": 10.91, + "learning_rate": 9.011632268215332e-06, + "loss": 0.0166, + "step": 35331 + }, + { + "epoch": 10.91, + "learning_rate": 9.011134599975987e-06, + "loss": 0.0163, + "step": 35332 + }, + { + "epoch": 10.91, + "learning_rate": 9.010636934209976e-06, + "loss": 0.0174, + "step": 35333 + }, + { + "epoch": 10.91, + "learning_rate": 9.01013927091854e-06, + "loss": 0.0144, + "step": 35334 + }, + { + "epoch": 10.91, + "learning_rate": 9.009641610102927e-06, + "loss": 0.0161, + "step": 35335 + }, + { + "epoch": 10.91, + "learning_rate": 9.009143951764384e-06, + "loss": 0.0159, + "step": 35336 + }, + { + "epoch": 10.91, + "learning_rate": 9.00864629590415e-06, + "loss": 0.0154, + "step": 35337 + }, + { + "epoch": 10.91, + "learning_rate": 9.008148642523472e-06, + "loss": 0.0154, + "step": 35338 + }, + { + "epoch": 10.91, + "learning_rate": 9.007650991623597e-06, + "loss": 0.0149, + "step": 35339 + }, + { + "epoch": 10.91, + "learning_rate": 9.007153343205767e-06, + "loss": 0.0158, + "step": 35340 + }, + { + "epoch": 10.91, + "learning_rate": 9.006655697271225e-06, + "loss": 0.0154, + "step": 35341 + }, + { + "epoch": 10.91, + "learning_rate": 9.006158053821223e-06, + "loss": 0.0173, + "step": 35342 + }, + { + "epoch": 10.91, + "learning_rate": 9.005660412856997e-06, + "loss": 0.0174, + "step": 35343 + }, + { + "epoch": 10.91, + "learning_rate": 9.005162774379796e-06, + "loss": 0.0151, + "step": 35344 + }, + { + "epoch": 10.92, + "learning_rate": 9.004665138390868e-06, + "loss": 0.0136, + "step": 35345 + }, + { + "epoch": 10.92, + "learning_rate": 9.004167504891453e-06, + "loss": 0.0167, + "step": 35346 + }, + { + "epoch": 10.92, + "learning_rate": 9.003669873882792e-06, + "loss": 0.0176, + "step": 35347 + }, + { + "epoch": 10.92, + "learning_rate": 9.003172245366141e-06, + "loss": 0.0167, + "step": 35348 + }, + { + "epoch": 10.92, + "learning_rate": 9.002674619342734e-06, + "loss": 0.0148, + "step": 35349 + }, + { + "epoch": 10.92, + "learning_rate": 9.00217699581382e-06, + "loss": 0.0158, + "step": 35350 + }, + { + "epoch": 10.92, + "learning_rate": 9.001679374780646e-06, + "loss": 0.0145, + "step": 35351 + }, + { + "epoch": 10.92, + "learning_rate": 9.001181756244448e-06, + "loss": 0.0161, + "step": 35352 + }, + { + "epoch": 10.92, + "learning_rate": 9.000684140206482e-06, + "loss": 0.0175, + "step": 35353 + }, + { + "epoch": 10.92, + "learning_rate": 9.000186526667987e-06, + "loss": 0.0181, + "step": 35354 + }, + { + "epoch": 10.92, + "learning_rate": 8.999688915630205e-06, + "loss": 0.0154, + "step": 35355 + }, + { + "epoch": 10.92, + "learning_rate": 8.999191307094384e-06, + "loss": 0.016, + "step": 35356 + }, + { + "epoch": 10.92, + "learning_rate": 8.998693701061772e-06, + "loss": 0.0145, + "step": 35357 + }, + { + "epoch": 10.92, + "learning_rate": 8.998196097533606e-06, + "loss": 0.0173, + "step": 35358 + }, + { + "epoch": 10.92, + "learning_rate": 8.997698496511132e-06, + "loss": 0.0154, + "step": 35359 + }, + { + "epoch": 10.92, + "learning_rate": 8.997200897995602e-06, + "loss": 0.0162, + "step": 35360 + }, + { + "epoch": 10.92, + "learning_rate": 8.996703301988253e-06, + "loss": 0.0154, + "step": 35361 + }, + { + "epoch": 10.92, + "learning_rate": 8.996205708490332e-06, + "loss": 0.015, + "step": 35362 + }, + { + "epoch": 10.92, + "learning_rate": 8.995708117503085e-06, + "loss": 0.0147, + "step": 35363 + }, + { + "epoch": 10.92, + "learning_rate": 8.995210529027753e-06, + "loss": 0.0172, + "step": 35364 + }, + { + "epoch": 10.92, + "learning_rate": 8.994712943065582e-06, + "loss": 0.0155, + "step": 35365 + }, + { + "epoch": 10.92, + "learning_rate": 8.99421535961782e-06, + "loss": 0.0158, + "step": 35366 + }, + { + "epoch": 10.92, + "learning_rate": 8.99371777868571e-06, + "loss": 0.0158, + "step": 35367 + }, + { + "epoch": 10.92, + "learning_rate": 8.993220200270492e-06, + "loss": 0.0171, + "step": 35368 + }, + { + "epoch": 10.92, + "learning_rate": 8.992722624373413e-06, + "loss": 0.0159, + "step": 35369 + }, + { + "epoch": 10.92, + "learning_rate": 8.992225050995724e-06, + "loss": 0.015, + "step": 35370 + }, + { + "epoch": 10.92, + "learning_rate": 8.991727480138659e-06, + "loss": 0.0179, + "step": 35371 + }, + { + "epoch": 10.92, + "learning_rate": 8.991229911803467e-06, + "loss": 0.0134, + "step": 35372 + }, + { + "epoch": 10.92, + "learning_rate": 8.990732345991398e-06, + "loss": 0.0169, + "step": 35373 + }, + { + "epoch": 10.92, + "learning_rate": 8.990234782703687e-06, + "loss": 0.0159, + "step": 35374 + }, + { + "epoch": 10.92, + "learning_rate": 8.989737221941583e-06, + "loss": 0.0153, + "step": 35375 + }, + { + "epoch": 10.92, + "learning_rate": 8.989239663706334e-06, + "loss": 0.0155, + "step": 35376 + }, + { + "epoch": 10.93, + "learning_rate": 8.988742107999178e-06, + "loss": 0.0184, + "step": 35377 + }, + { + "epoch": 10.93, + "learning_rate": 8.988244554821363e-06, + "loss": 0.0152, + "step": 35378 + }, + { + "epoch": 10.93, + "learning_rate": 8.987747004174137e-06, + "loss": 0.0147, + "step": 35379 + }, + { + "epoch": 10.93, + "learning_rate": 8.987249456058732e-06, + "loss": 0.0166, + "step": 35380 + }, + { + "epoch": 10.93, + "learning_rate": 8.986751910476407e-06, + "loss": 0.0173, + "step": 35381 + }, + { + "epoch": 10.93, + "learning_rate": 8.986254367428401e-06, + "loss": 0.0173, + "step": 35382 + }, + { + "epoch": 10.93, + "learning_rate": 8.985756826915953e-06, + "loss": 0.0145, + "step": 35383 + }, + { + "epoch": 10.93, + "learning_rate": 8.985259288940314e-06, + "loss": 0.016, + "step": 35384 + }, + { + "epoch": 10.93, + "learning_rate": 8.98476175350273e-06, + "loss": 0.0152, + "step": 35385 + }, + { + "epoch": 10.93, + "learning_rate": 8.984264220604437e-06, + "loss": 0.016, + "step": 35386 + }, + { + "epoch": 10.93, + "learning_rate": 8.983766690246685e-06, + "loss": 0.0153, + "step": 35387 + }, + { + "epoch": 10.93, + "learning_rate": 8.983269162430722e-06, + "loss": 0.015, + "step": 35388 + }, + { + "epoch": 10.93, + "learning_rate": 8.982771637157785e-06, + "loss": 0.0155, + "step": 35389 + }, + { + "epoch": 10.93, + "learning_rate": 8.98227411442912e-06, + "loss": 0.0168, + "step": 35390 + }, + { + "epoch": 10.93, + "learning_rate": 8.981776594245978e-06, + "loss": 0.0176, + "step": 35391 + }, + { + "epoch": 10.93, + "learning_rate": 8.981279076609598e-06, + "loss": 0.016, + "step": 35392 + }, + { + "epoch": 10.93, + "learning_rate": 8.98078156152122e-06, + "loss": 0.0144, + "step": 35393 + }, + { + "epoch": 10.93, + "learning_rate": 8.980284048982098e-06, + "loss": 0.0162, + "step": 35394 + }, + { + "epoch": 10.93, + "learning_rate": 8.97978653899347e-06, + "loss": 0.0138, + "step": 35395 + }, + { + "epoch": 10.93, + "learning_rate": 8.979289031556579e-06, + "loss": 0.0178, + "step": 35396 + }, + { + "epoch": 10.93, + "learning_rate": 8.978791526672674e-06, + "loss": 0.014, + "step": 35397 + }, + { + "epoch": 10.93, + "learning_rate": 8.978294024343e-06, + "loss": 0.0145, + "step": 35398 + }, + { + "epoch": 10.93, + "learning_rate": 8.977796524568798e-06, + "loss": 0.0175, + "step": 35399 + }, + { + "epoch": 10.93, + "learning_rate": 8.977299027351309e-06, + "loss": 0.0166, + "step": 35400 + }, + { + "epoch": 10.93, + "learning_rate": 8.97680153269179e-06, + "loss": 0.0145, + "step": 35401 + }, + { + "epoch": 10.93, + "learning_rate": 8.97630404059147e-06, + "loss": 0.0149, + "step": 35402 + }, + { + "epoch": 10.93, + "learning_rate": 8.975806551051602e-06, + "loss": 0.0159, + "step": 35403 + }, + { + "epoch": 10.93, + "learning_rate": 8.975309064073431e-06, + "loss": 0.0158, + "step": 35404 + }, + { + "epoch": 10.93, + "learning_rate": 8.974811579658198e-06, + "loss": 0.0169, + "step": 35405 + }, + { + "epoch": 10.93, + "learning_rate": 8.974314097807145e-06, + "loss": 0.0172, + "step": 35406 + }, + { + "epoch": 10.93, + "learning_rate": 8.973816618521526e-06, + "loss": 0.0176, + "step": 35407 + }, + { + "epoch": 10.93, + "learning_rate": 8.973319141802573e-06, + "loss": 0.0165, + "step": 35408 + }, + { + "epoch": 10.93, + "learning_rate": 8.972821667651538e-06, + "loss": 0.0163, + "step": 35409 + }, + { + "epoch": 10.94, + "learning_rate": 8.972324196069663e-06, + "loss": 0.0171, + "step": 35410 + }, + { + "epoch": 10.94, + "learning_rate": 8.971826727058191e-06, + "loss": 0.017, + "step": 35411 + }, + { + "epoch": 10.94, + "learning_rate": 8.97132926061837e-06, + "loss": 0.0148, + "step": 35412 + }, + { + "epoch": 10.94, + "learning_rate": 8.970831796751444e-06, + "loss": 0.0162, + "step": 35413 + }, + { + "epoch": 10.94, + "learning_rate": 8.970334335458651e-06, + "loss": 0.015, + "step": 35414 + }, + { + "epoch": 10.94, + "learning_rate": 8.969836876741242e-06, + "loss": 0.0165, + "step": 35415 + }, + { + "epoch": 10.94, + "learning_rate": 8.96933942060046e-06, + "loss": 0.0157, + "step": 35416 + }, + { + "epoch": 10.94, + "learning_rate": 8.968841967037546e-06, + "loss": 0.0169, + "step": 35417 + }, + { + "epoch": 10.94, + "learning_rate": 8.968344516053746e-06, + "loss": 0.0144, + "step": 35418 + }, + { + "epoch": 10.94, + "learning_rate": 8.967847067650308e-06, + "loss": 0.0209, + "step": 35419 + }, + { + "epoch": 10.94, + "learning_rate": 8.967349621828471e-06, + "loss": 0.0154, + "step": 35420 + }, + { + "epoch": 10.94, + "learning_rate": 8.966852178589478e-06, + "loss": 0.0143, + "step": 35421 + }, + { + "epoch": 10.94, + "learning_rate": 8.96635473793458e-06, + "loss": 0.0165, + "step": 35422 + }, + { + "epoch": 10.94, + "learning_rate": 8.965857299865016e-06, + "loss": 0.0167, + "step": 35423 + }, + { + "epoch": 10.94, + "learning_rate": 8.965359864382029e-06, + "loss": 0.0171, + "step": 35424 + }, + { + "epoch": 10.94, + "learning_rate": 8.96486243148687e-06, + "loss": 0.0173, + "step": 35425 + }, + { + "epoch": 10.94, + "learning_rate": 8.964365001180777e-06, + "loss": 0.0143, + "step": 35426 + }, + { + "epoch": 10.94, + "learning_rate": 8.963867573464996e-06, + "loss": 0.0167, + "step": 35427 + }, + { + "epoch": 10.94, + "learning_rate": 8.963370148340773e-06, + "loss": 0.0162, + "step": 35428 + }, + { + "epoch": 10.94, + "learning_rate": 8.962872725809346e-06, + "loss": 0.0192, + "step": 35429 + }, + { + "epoch": 10.94, + "learning_rate": 8.962375305871965e-06, + "loss": 0.0164, + "step": 35430 + }, + { + "epoch": 10.94, + "learning_rate": 8.961877888529872e-06, + "loss": 0.0176, + "step": 35431 + }, + { + "epoch": 10.94, + "learning_rate": 8.961380473784315e-06, + "loss": 0.0176, + "step": 35432 + }, + { + "epoch": 10.94, + "learning_rate": 8.960883061636532e-06, + "loss": 0.0174, + "step": 35433 + }, + { + "epoch": 10.94, + "learning_rate": 8.96038565208777e-06, + "loss": 0.018, + "step": 35434 + }, + { + "epoch": 10.94, + "learning_rate": 8.959888245139276e-06, + "loss": 0.0164, + "step": 35435 + }, + { + "epoch": 10.94, + "learning_rate": 8.95939084079229e-06, + "loss": 0.0176, + "step": 35436 + }, + { + "epoch": 10.94, + "learning_rate": 8.958893439048057e-06, + "loss": 0.0152, + "step": 35437 + }, + { + "epoch": 10.94, + "learning_rate": 8.958396039907821e-06, + "loss": 0.0142, + "step": 35438 + }, + { + "epoch": 10.94, + "learning_rate": 8.957898643372825e-06, + "loss": 0.015, + "step": 35439 + }, + { + "epoch": 10.94, + "learning_rate": 8.957401249444316e-06, + "loss": 0.0157, + "step": 35440 + }, + { + "epoch": 10.94, + "learning_rate": 8.95690385812354e-06, + "loss": 0.0164, + "step": 35441 + }, + { + "epoch": 10.95, + "learning_rate": 8.956406469411732e-06, + "loss": 0.0169, + "step": 35442 + }, + { + "epoch": 10.95, + "learning_rate": 8.955909083310144e-06, + "loss": 0.0134, + "step": 35443 + }, + { + "epoch": 10.95, + "learning_rate": 8.95541169982002e-06, + "loss": 0.0147, + "step": 35444 + }, + { + "epoch": 10.95, + "learning_rate": 8.954914318942599e-06, + "loss": 0.0156, + "step": 35445 + }, + { + "epoch": 10.95, + "learning_rate": 8.954416940679127e-06, + "loss": 0.0151, + "step": 35446 + }, + { + "epoch": 10.95, + "learning_rate": 8.953919565030854e-06, + "loss": 0.0195, + "step": 35447 + }, + { + "epoch": 10.95, + "learning_rate": 8.953422191999015e-06, + "loss": 0.0161, + "step": 35448 + }, + { + "epoch": 10.95, + "learning_rate": 8.952924821584856e-06, + "loss": 0.0169, + "step": 35449 + }, + { + "epoch": 10.95, + "learning_rate": 8.952427453789627e-06, + "loss": 0.0152, + "step": 35450 + }, + { + "epoch": 10.95, + "learning_rate": 8.951930088614566e-06, + "loss": 0.0146, + "step": 35451 + }, + { + "epoch": 10.95, + "learning_rate": 8.951432726060918e-06, + "loss": 0.0146, + "step": 35452 + }, + { + "epoch": 10.95, + "learning_rate": 8.950935366129932e-06, + "loss": 0.0133, + "step": 35453 + }, + { + "epoch": 10.95, + "learning_rate": 8.950438008822846e-06, + "loss": 0.016, + "step": 35454 + }, + { + "epoch": 10.95, + "learning_rate": 8.949940654140902e-06, + "loss": 0.0183, + "step": 35455 + }, + { + "epoch": 10.95, + "learning_rate": 8.949443302085356e-06, + "loss": 0.016, + "step": 35456 + }, + { + "epoch": 10.95, + "learning_rate": 8.948945952657439e-06, + "loss": 0.0163, + "step": 35457 + }, + { + "epoch": 10.95, + "learning_rate": 8.9484486058584e-06, + "loss": 0.0177, + "step": 35458 + }, + { + "epoch": 10.95, + "learning_rate": 8.947951261689485e-06, + "loss": 0.0156, + "step": 35459 + }, + { + "epoch": 10.95, + "learning_rate": 8.947453920151931e-06, + "loss": 0.0141, + "step": 35460 + }, + { + "epoch": 10.95, + "learning_rate": 8.94695658124699e-06, + "loss": 0.0151, + "step": 35461 + }, + { + "epoch": 10.95, + "learning_rate": 8.9464592449759e-06, + "loss": 0.0153, + "step": 35462 + }, + { + "epoch": 10.95, + "learning_rate": 8.945961911339913e-06, + "loss": 0.0136, + "step": 35463 + }, + { + "epoch": 10.95, + "learning_rate": 8.945464580340262e-06, + "loss": 0.0146, + "step": 35464 + }, + { + "epoch": 10.95, + "learning_rate": 8.944967251978198e-06, + "loss": 0.0186, + "step": 35465 + }, + { + "epoch": 10.95, + "learning_rate": 8.944469926254969e-06, + "loss": 0.0184, + "step": 35466 + }, + { + "epoch": 10.95, + "learning_rate": 8.943972603171805e-06, + "loss": 0.0163, + "step": 35467 + }, + { + "epoch": 10.95, + "learning_rate": 8.943475282729962e-06, + "loss": 0.014, + "step": 35468 + }, + { + "epoch": 10.95, + "learning_rate": 8.942977964930682e-06, + "loss": 0.0151, + "step": 35469 + }, + { + "epoch": 10.95, + "learning_rate": 8.942480649775201e-06, + "loss": 0.0157, + "step": 35470 + }, + { + "epoch": 10.95, + "learning_rate": 8.941983337264772e-06, + "loss": 0.0164, + "step": 35471 + }, + { + "epoch": 10.95, + "learning_rate": 8.941486027400639e-06, + "loss": 0.0156, + "step": 35472 + }, + { + "epoch": 10.95, + "learning_rate": 8.940988720184036e-06, + "loss": 0.0141, + "step": 35473 + }, + { + "epoch": 10.96, + "learning_rate": 8.940491415616217e-06, + "loss": 0.0154, + "step": 35474 + }, + { + "epoch": 10.96, + "learning_rate": 8.939994113698424e-06, + "loss": 0.0162, + "step": 35475 + }, + { + "epoch": 10.96, + "learning_rate": 8.939496814431896e-06, + "loss": 0.0175, + "step": 35476 + }, + { + "epoch": 10.96, + "learning_rate": 8.93899951781788e-06, + "loss": 0.0172, + "step": 35477 + }, + { + "epoch": 10.96, + "learning_rate": 8.938502223857623e-06, + "loss": 0.0159, + "step": 35478 + }, + { + "epoch": 10.96, + "learning_rate": 8.938004932552362e-06, + "loss": 0.0161, + "step": 35479 + }, + { + "epoch": 10.96, + "learning_rate": 8.937507643903343e-06, + "loss": 0.015, + "step": 35480 + }, + { + "epoch": 10.96, + "learning_rate": 8.937010357911817e-06, + "loss": 0.0161, + "step": 35481 + }, + { + "epoch": 10.96, + "learning_rate": 8.936513074579019e-06, + "loss": 0.0154, + "step": 35482 + }, + { + "epoch": 10.96, + "learning_rate": 8.936015793906192e-06, + "loss": 0.0167, + "step": 35483 + }, + { + "epoch": 10.96, + "learning_rate": 8.935518515894589e-06, + "loss": 0.0169, + "step": 35484 + }, + { + "epoch": 10.96, + "learning_rate": 8.935021240545447e-06, + "loss": 0.0144, + "step": 35485 + }, + { + "epoch": 10.96, + "learning_rate": 8.934523967860009e-06, + "loss": 0.0149, + "step": 35486 + }, + { + "epoch": 10.96, + "learning_rate": 8.934026697839526e-06, + "loss": 0.0172, + "step": 35487 + }, + { + "epoch": 10.96, + "learning_rate": 8.93352943048523e-06, + "loss": 0.0162, + "step": 35488 + }, + { + "epoch": 10.96, + "learning_rate": 8.933032165798375e-06, + "loss": 0.0175, + "step": 35489 + }, + { + "epoch": 10.96, + "learning_rate": 8.932534903780202e-06, + "loss": 0.0158, + "step": 35490 + }, + { + "epoch": 10.96, + "learning_rate": 8.93203764443195e-06, + "loss": 0.0166, + "step": 35491 + }, + { + "epoch": 10.96, + "learning_rate": 8.931540387754868e-06, + "loss": 0.0147, + "step": 35492 + }, + { + "epoch": 10.96, + "learning_rate": 8.931043133750203e-06, + "loss": 0.0163, + "step": 35493 + }, + { + "epoch": 10.96, + "learning_rate": 8.930545882419187e-06, + "loss": 0.0154, + "step": 35494 + }, + { + "epoch": 10.96, + "learning_rate": 8.930048633763074e-06, + "loss": 0.0172, + "step": 35495 + }, + { + "epoch": 10.96, + "learning_rate": 8.929551387783102e-06, + "loss": 0.016, + "step": 35496 + }, + { + "epoch": 10.96, + "learning_rate": 8.929054144480525e-06, + "loss": 0.017, + "step": 35497 + }, + { + "epoch": 10.96, + "learning_rate": 8.928556903856572e-06, + "loss": 0.0169, + "step": 35498 + }, + { + "epoch": 10.96, + "learning_rate": 8.928059665912495e-06, + "loss": 0.0163, + "step": 35499 + }, + { + "epoch": 10.96, + "learning_rate": 8.92756243064954e-06, + "loss": 0.0156, + "step": 35500 + }, + { + "epoch": 10.96, + "learning_rate": 8.927065198068942e-06, + "loss": 0.0131, + "step": 35501 + }, + { + "epoch": 10.96, + "learning_rate": 8.92656796817195e-06, + "loss": 0.0165, + "step": 35502 + }, + { + "epoch": 10.96, + "learning_rate": 8.926070740959811e-06, + "loss": 0.0137, + "step": 35503 + }, + { + "epoch": 10.96, + "learning_rate": 8.925573516433761e-06, + "loss": 0.0157, + "step": 35504 + }, + { + "epoch": 10.96, + "learning_rate": 8.925076294595048e-06, + "loss": 0.0172, + "step": 35505 + }, + { + "epoch": 10.96, + "learning_rate": 8.92457907544492e-06, + "loss": 0.0147, + "step": 35506 + }, + { + "epoch": 10.97, + "learning_rate": 8.924081858984612e-06, + "loss": 0.0142, + "step": 35507 + }, + { + "epoch": 10.97, + "learning_rate": 8.923584645215369e-06, + "loss": 0.0139, + "step": 35508 + }, + { + "epoch": 10.97, + "learning_rate": 8.923087434138442e-06, + "loss": 0.0162, + "step": 35509 + }, + { + "epoch": 10.97, + "learning_rate": 8.922590225755068e-06, + "loss": 0.0153, + "step": 35510 + }, + { + "epoch": 10.97, + "learning_rate": 8.92209302006649e-06, + "loss": 0.0147, + "step": 35511 + }, + { + "epoch": 10.97, + "learning_rate": 8.921595817073958e-06, + "loss": 0.0151, + "step": 35512 + }, + { + "epoch": 10.97, + "learning_rate": 8.921098616778709e-06, + "loss": 0.0157, + "step": 35513 + }, + { + "epoch": 10.97, + "learning_rate": 8.920601419181988e-06, + "loss": 0.0146, + "step": 35514 + }, + { + "epoch": 10.97, + "learning_rate": 8.920104224285045e-06, + "loss": 0.0152, + "step": 35515 + }, + { + "epoch": 10.97, + "learning_rate": 8.919607032089114e-06, + "loss": 0.0159, + "step": 35516 + }, + { + "epoch": 10.97, + "learning_rate": 8.919109842595442e-06, + "loss": 0.0173, + "step": 35517 + }, + { + "epoch": 10.97, + "learning_rate": 8.918612655805279e-06, + "loss": 0.0145, + "step": 35518 + }, + { + "epoch": 10.97, + "learning_rate": 8.918115471719856e-06, + "loss": 0.014, + "step": 35519 + }, + { + "epoch": 10.97, + "learning_rate": 8.917618290340426e-06, + "loss": 0.0174, + "step": 35520 + }, + { + "epoch": 10.97, + "learning_rate": 8.917121111668233e-06, + "loss": 0.0171, + "step": 35521 + }, + { + "epoch": 10.97, + "learning_rate": 8.916623935704513e-06, + "loss": 0.015, + "step": 35522 + }, + { + "epoch": 10.97, + "learning_rate": 8.916126762450516e-06, + "loss": 0.0156, + "step": 35523 + }, + { + "epoch": 10.97, + "learning_rate": 8.915629591907487e-06, + "loss": 0.0155, + "step": 35524 + }, + { + "epoch": 10.97, + "learning_rate": 8.915132424076662e-06, + "loss": 0.016, + "step": 35525 + }, + { + "epoch": 10.97, + "learning_rate": 8.914635258959288e-06, + "loss": 0.0156, + "step": 35526 + }, + { + "epoch": 10.97, + "learning_rate": 8.914138096556613e-06, + "loss": 0.0157, + "step": 35527 + }, + { + "epoch": 10.97, + "learning_rate": 8.913640936869875e-06, + "loss": 0.0182, + "step": 35528 + }, + { + "epoch": 10.97, + "learning_rate": 8.913143779900318e-06, + "loss": 0.0161, + "step": 35529 + }, + { + "epoch": 10.97, + "learning_rate": 8.912646625649186e-06, + "loss": 0.0154, + "step": 35530 + }, + { + "epoch": 10.97, + "learning_rate": 8.912149474117727e-06, + "loss": 0.0141, + "step": 35531 + }, + { + "epoch": 10.97, + "learning_rate": 8.911652325307176e-06, + "loss": 0.015, + "step": 35532 + }, + { + "epoch": 10.97, + "learning_rate": 8.911155179218784e-06, + "loss": 0.0159, + "step": 35533 + }, + { + "epoch": 10.97, + "learning_rate": 8.910658035853793e-06, + "loss": 0.0144, + "step": 35534 + }, + { + "epoch": 10.97, + "learning_rate": 8.910160895213439e-06, + "loss": 0.0167, + "step": 35535 + }, + { + "epoch": 10.97, + "learning_rate": 8.909663757298976e-06, + "loss": 0.0143, + "step": 35536 + }, + { + "epoch": 10.97, + "learning_rate": 8.909166622111644e-06, + "loss": 0.015, + "step": 35537 + }, + { + "epoch": 10.97, + "learning_rate": 8.908669489652681e-06, + "loss": 0.0167, + "step": 35538 + }, + { + "epoch": 10.98, + "learning_rate": 8.908172359923334e-06, + "loss": 0.0157, + "step": 35539 + }, + { + "epoch": 10.98, + "learning_rate": 8.907675232924853e-06, + "loss": 0.0149, + "step": 35540 + }, + { + "epoch": 10.98, + "learning_rate": 8.907178108658472e-06, + "loss": 0.0139, + "step": 35541 + }, + { + "epoch": 10.98, + "learning_rate": 8.906680987125437e-06, + "loss": 0.0155, + "step": 35542 + }, + { + "epoch": 10.98, + "learning_rate": 8.906183868326994e-06, + "loss": 0.0173, + "step": 35543 + }, + { + "epoch": 10.98, + "learning_rate": 8.905686752264386e-06, + "loss": 0.0161, + "step": 35544 + }, + { + "epoch": 10.98, + "learning_rate": 8.905189638938849e-06, + "loss": 0.0147, + "step": 35545 + }, + { + "epoch": 10.98, + "learning_rate": 8.904692528351642e-06, + "loss": 0.0161, + "step": 35546 + }, + { + "epoch": 10.98, + "learning_rate": 8.90419542050399e-06, + "loss": 0.0156, + "step": 35547 + }, + { + "epoch": 10.98, + "learning_rate": 8.903698315397148e-06, + "loss": 0.0149, + "step": 35548 + }, + { + "epoch": 10.98, + "learning_rate": 8.90320121303236e-06, + "loss": 0.0148, + "step": 35549 + }, + { + "epoch": 10.98, + "learning_rate": 8.902704113410859e-06, + "loss": 0.0157, + "step": 35550 + }, + { + "epoch": 10.98, + "learning_rate": 8.902207016533899e-06, + "loss": 0.0165, + "step": 35551 + }, + { + "epoch": 10.98, + "learning_rate": 8.901709922402721e-06, + "loss": 0.0153, + "step": 35552 + }, + { + "epoch": 10.98, + "learning_rate": 8.901212831018564e-06, + "loss": 0.0157, + "step": 35553 + }, + { + "epoch": 10.98, + "learning_rate": 8.900715742382676e-06, + "loss": 0.015, + "step": 35554 + }, + { + "epoch": 10.98, + "learning_rate": 8.900218656496298e-06, + "loss": 0.0197, + "step": 35555 + }, + { + "epoch": 10.98, + "learning_rate": 8.899721573360674e-06, + "loss": 0.0167, + "step": 35556 + }, + { + "epoch": 10.98, + "learning_rate": 8.899224492977043e-06, + "loss": 0.0177, + "step": 35557 + }, + { + "epoch": 10.98, + "learning_rate": 8.898727415346658e-06, + "loss": 0.0163, + "step": 35558 + }, + { + "epoch": 10.98, + "learning_rate": 8.898230340470756e-06, + "loss": 0.0177, + "step": 35559 + }, + { + "epoch": 10.98, + "learning_rate": 8.897733268350576e-06, + "loss": 0.0174, + "step": 35560 + }, + { + "epoch": 10.98, + "learning_rate": 8.897236198987369e-06, + "loss": 0.0175, + "step": 35561 + }, + { + "epoch": 10.98, + "learning_rate": 8.896739132382377e-06, + "loss": 0.0163, + "step": 35562 + }, + { + "epoch": 10.98, + "learning_rate": 8.896242068536837e-06, + "loss": 0.0151, + "step": 35563 + }, + { + "epoch": 10.98, + "learning_rate": 8.895745007452001e-06, + "loss": 0.0162, + "step": 35564 + }, + { + "epoch": 10.98, + "learning_rate": 8.89524794912911e-06, + "loss": 0.0178, + "step": 35565 + }, + { + "epoch": 10.98, + "learning_rate": 8.894750893569403e-06, + "loss": 0.0198, + "step": 35566 + }, + { + "epoch": 10.98, + "learning_rate": 8.894253840774121e-06, + "loss": 0.0175, + "step": 35567 + }, + { + "epoch": 10.98, + "learning_rate": 8.89375679074452e-06, + "loss": 0.0158, + "step": 35568 + }, + { + "epoch": 10.98, + "learning_rate": 8.89325974348183e-06, + "loss": 0.018, + "step": 35569 + }, + { + "epoch": 10.98, + "learning_rate": 8.892762698987299e-06, + "loss": 0.0128, + "step": 35570 + }, + { + "epoch": 10.99, + "learning_rate": 8.892265657262173e-06, + "loss": 0.0167, + "step": 35571 + }, + { + "epoch": 10.99, + "learning_rate": 8.891768618307693e-06, + "loss": 0.0155, + "step": 35572 + }, + { + "epoch": 10.99, + "learning_rate": 8.891271582125097e-06, + "loss": 0.0163, + "step": 35573 + }, + { + "epoch": 10.99, + "learning_rate": 8.890774548715638e-06, + "loss": 0.0172, + "step": 35574 + }, + { + "epoch": 10.99, + "learning_rate": 8.890277518080552e-06, + "loss": 0.0161, + "step": 35575 + }, + { + "epoch": 10.99, + "learning_rate": 8.889780490221085e-06, + "loss": 0.0143, + "step": 35576 + }, + { + "epoch": 10.99, + "learning_rate": 8.889283465138482e-06, + "loss": 0.0156, + "step": 35577 + }, + { + "epoch": 10.99, + "learning_rate": 8.888786442833979e-06, + "loss": 0.0165, + "step": 35578 + }, + { + "epoch": 10.99, + "learning_rate": 8.888289423308824e-06, + "loss": 0.0155, + "step": 35579 + }, + { + "epoch": 10.99, + "learning_rate": 8.887792406564264e-06, + "loss": 0.017, + "step": 35580 + }, + { + "epoch": 10.99, + "learning_rate": 8.887295392601533e-06, + "loss": 0.0145, + "step": 35581 + }, + { + "epoch": 10.99, + "learning_rate": 8.886798381421883e-06, + "loss": 0.0174, + "step": 35582 + }, + { + "epoch": 10.99, + "learning_rate": 8.886301373026553e-06, + "loss": 0.0148, + "step": 35583 + }, + { + "epoch": 10.99, + "learning_rate": 8.885804367416783e-06, + "loss": 0.0184, + "step": 35584 + }, + { + "epoch": 10.99, + "learning_rate": 8.885307364593823e-06, + "loss": 0.015, + "step": 35585 + }, + { + "epoch": 10.99, + "learning_rate": 8.884810364558914e-06, + "loss": 0.0153, + "step": 35586 + }, + { + "epoch": 10.99, + "learning_rate": 8.884313367313294e-06, + "loss": 0.0147, + "step": 35587 + }, + { + "epoch": 10.99, + "learning_rate": 8.88381637285821e-06, + "loss": 0.0167, + "step": 35588 + }, + { + "epoch": 10.99, + "learning_rate": 8.883319381194907e-06, + "loss": 0.0158, + "step": 35589 + }, + { + "epoch": 10.99, + "learning_rate": 8.882822392324625e-06, + "loss": 0.016, + "step": 35590 + }, + { + "epoch": 10.99, + "learning_rate": 8.882325406248606e-06, + "loss": 0.0366, + "step": 35591 + }, + { + "epoch": 10.99, + "learning_rate": 8.881828422968098e-06, + "loss": 0.0168, + "step": 35592 + }, + { + "epoch": 10.99, + "learning_rate": 8.88133144248434e-06, + "loss": 0.0152, + "step": 35593 + }, + { + "epoch": 10.99, + "learning_rate": 8.880834464798574e-06, + "loss": 0.0164, + "step": 35594 + }, + { + "epoch": 10.99, + "learning_rate": 8.880337489912047e-06, + "loss": 0.0146, + "step": 35595 + }, + { + "epoch": 10.99, + "learning_rate": 8.879840517826002e-06, + "loss": 0.0168, + "step": 35596 + }, + { + "epoch": 10.99, + "learning_rate": 8.879343548541678e-06, + "loss": 0.018, + "step": 35597 + }, + { + "epoch": 10.99, + "learning_rate": 8.878846582060317e-06, + "loss": 0.0163, + "step": 35598 + }, + { + "epoch": 10.99, + "learning_rate": 8.878349618383171e-06, + "loss": 0.0151, + "step": 35599 + }, + { + "epoch": 10.99, + "learning_rate": 8.877852657511476e-06, + "loss": 0.0168, + "step": 35600 + }, + { + "epoch": 10.99, + "learning_rate": 8.877355699446471e-06, + "loss": 0.0153, + "step": 35601 + }, + { + "epoch": 10.99, + "learning_rate": 8.876858744189412e-06, + "loss": 0.0192, + "step": 35602 + }, + { + "epoch": 10.99, + "learning_rate": 8.876361791741528e-06, + "loss": 0.0163, + "step": 35603 + }, + { + "epoch": 11.0, + "learning_rate": 8.87586484210407e-06, + "loss": 0.0182, + "step": 35604 + }, + { + "epoch": 11.0, + "learning_rate": 8.875367895278283e-06, + "loss": 0.0152, + "step": 35605 + }, + { + "epoch": 11.0, + "learning_rate": 8.8748709512654e-06, + "loss": 0.0174, + "step": 35606 + }, + { + "epoch": 11.0, + "learning_rate": 8.874374010066671e-06, + "loss": 0.017, + "step": 35607 + }, + { + "epoch": 11.0, + "learning_rate": 8.873877071683343e-06, + "loss": 0.0166, + "step": 35608 + }, + { + "epoch": 11.0, + "learning_rate": 8.873380136116647e-06, + "loss": 0.0163, + "step": 35609 + }, + { + "epoch": 11.0, + "learning_rate": 8.872883203367836e-06, + "loss": 0.0188, + "step": 35610 + }, + { + "epoch": 11.0, + "learning_rate": 8.872386273438151e-06, + "loss": 0.015, + "step": 35611 + }, + { + "epoch": 11.0, + "learning_rate": 8.871889346328832e-06, + "loss": 0.0163, + "step": 35612 + }, + { + "epoch": 11.0, + "learning_rate": 8.871392422041123e-06, + "loss": 0.0164, + "step": 35613 + }, + { + "epoch": 11.0, + "learning_rate": 8.87089550057627e-06, + "loss": 0.0177, + "step": 35614 + }, + { + "epoch": 11.0, + "learning_rate": 8.870398581935511e-06, + "loss": 0.016, + "step": 35615 + }, + { + "epoch": 11.0, + "learning_rate": 8.86990166612009e-06, + "loss": 0.016, + "step": 35616 + }, + { + "epoch": 11.0, + "learning_rate": 8.869404753131254e-06, + "loss": 0.0156, + "step": 35617 + }, + { + "epoch": 11.0, + "learning_rate": 8.868907842970242e-06, + "loss": 0.0158, + "step": 35618 + }, + { + "epoch": 11.0, + "learning_rate": 8.868410935638294e-06, + "loss": 0.0164, + "step": 35619 + }, + { + "epoch": 11.0, + "learning_rate": 8.867914031136664e-06, + "loss": 0.0116, + "step": 35620 + }, + { + "epoch": 11.0, + "learning_rate": 8.867417129466583e-06, + "loss": 0.0101, + "step": 35621 + }, + { + "epoch": 11.0, + "learning_rate": 8.866920230629295e-06, + "loss": 0.0086, + "step": 35622 + }, + { + "epoch": 11.0, + "learning_rate": 8.866423334626053e-06, + "loss": 0.0091, + "step": 35623 + }, + { + "epoch": 11.0, + "learning_rate": 8.865926441458089e-06, + "loss": 0.0078, + "step": 35624 + }, + { + "epoch": 11.0, + "learning_rate": 8.86542955112665e-06, + "loss": 0.0085, + "step": 35625 + }, + { + "epoch": 11.0, + "learning_rate": 8.864932663632978e-06, + "loss": 0.0085, + "step": 35626 + }, + { + "epoch": 11.0, + "learning_rate": 8.864435778978319e-06, + "loss": 0.0082, + "step": 35627 + }, + { + "epoch": 11.0, + "learning_rate": 8.863938897163913e-06, + "loss": 0.01, + "step": 35628 + }, + { + "epoch": 11.0, + "learning_rate": 8.863442018191e-06, + "loss": 0.0094, + "step": 35629 + }, + { + "epoch": 11.0, + "learning_rate": 8.86294514206083e-06, + "loss": 0.0096, + "step": 35630 + }, + { + "epoch": 11.0, + "learning_rate": 8.862448268774638e-06, + "loss": 0.0094, + "step": 35631 + }, + { + "epoch": 11.0, + "learning_rate": 8.861951398333671e-06, + "loss": 0.0093, + "step": 35632 + }, + { + "epoch": 11.0, + "learning_rate": 8.861454530739173e-06, + "loss": 0.0086, + "step": 35633 + }, + { + "epoch": 11.0, + "learning_rate": 8.860957665992383e-06, + "loss": 0.0086, + "step": 35634 + }, + { + "epoch": 11.0, + "learning_rate": 8.860460804094546e-06, + "loss": 0.0081, + "step": 35635 + }, + { + "epoch": 11.01, + "learning_rate": 8.859963945046908e-06, + "loss": 0.0087, + "step": 35636 + }, + { + "epoch": 11.01, + "learning_rate": 8.859467088850704e-06, + "loss": 0.009, + "step": 35637 + }, + { + "epoch": 11.01, + "learning_rate": 8.858970235507181e-06, + "loss": 0.0084, + "step": 35638 + }, + { + "epoch": 11.01, + "learning_rate": 8.858473385017584e-06, + "loss": 0.0089, + "step": 35639 + }, + { + "epoch": 11.01, + "learning_rate": 8.857976537383148e-06, + "loss": 0.0082, + "step": 35640 + }, + { + "epoch": 11.01, + "learning_rate": 8.857479692605126e-06, + "loss": 0.0079, + "step": 35641 + }, + { + "epoch": 11.01, + "learning_rate": 8.856982850684756e-06, + "loss": 0.0077, + "step": 35642 + }, + { + "epoch": 11.01, + "learning_rate": 8.856486011623275e-06, + "loss": 0.01, + "step": 35643 + }, + { + "epoch": 11.01, + "learning_rate": 8.855989175421936e-06, + "loss": 0.0089, + "step": 35644 + }, + { + "epoch": 11.01, + "learning_rate": 8.855492342081976e-06, + "loss": 0.008, + "step": 35645 + }, + { + "epoch": 11.01, + "learning_rate": 8.854995511604638e-06, + "loss": 0.0114, + "step": 35646 + }, + { + "epoch": 11.01, + "learning_rate": 8.854498683991162e-06, + "loss": 0.0119, + "step": 35647 + }, + { + "epoch": 11.01, + "learning_rate": 8.8540018592428e-06, + "loss": 0.0075, + "step": 35648 + }, + { + "epoch": 11.01, + "learning_rate": 8.853505037360783e-06, + "loss": 0.0096, + "step": 35649 + }, + { + "epoch": 11.01, + "learning_rate": 8.853008218346359e-06, + "loss": 0.0077, + "step": 35650 + }, + { + "epoch": 11.01, + "learning_rate": 8.852511402200775e-06, + "loss": 0.0089, + "step": 35651 + }, + { + "epoch": 11.01, + "learning_rate": 8.852014588925267e-06, + "loss": 0.0082, + "step": 35652 + }, + { + "epoch": 11.01, + "learning_rate": 8.851517778521077e-06, + "loss": 0.0074, + "step": 35653 + }, + { + "epoch": 11.01, + "learning_rate": 8.851020970989458e-06, + "loss": 0.01, + "step": 35654 + }, + { + "epoch": 11.01, + "learning_rate": 8.850524166331638e-06, + "loss": 0.0096, + "step": 35655 + }, + { + "epoch": 11.01, + "learning_rate": 8.85002736454887e-06, + "loss": 0.0092, + "step": 35656 + }, + { + "epoch": 11.01, + "learning_rate": 8.849530565642393e-06, + "loss": 0.0093, + "step": 35657 + }, + { + "epoch": 11.01, + "learning_rate": 8.849033769613446e-06, + "loss": 0.0089, + "step": 35658 + }, + { + "epoch": 11.01, + "learning_rate": 8.848536976463278e-06, + "loss": 0.0083, + "step": 35659 + }, + { + "epoch": 11.01, + "learning_rate": 8.848040186193129e-06, + "loss": 0.0083, + "step": 35660 + }, + { + "epoch": 11.01, + "learning_rate": 8.847543398804244e-06, + "loss": 0.0078, + "step": 35661 + }, + { + "epoch": 11.01, + "learning_rate": 8.847046614297861e-06, + "loss": 0.0077, + "step": 35662 + }, + { + "epoch": 11.01, + "learning_rate": 8.846549832675224e-06, + "loss": 0.0083, + "step": 35663 + }, + { + "epoch": 11.01, + "learning_rate": 8.84605305393758e-06, + "loss": 0.0084, + "step": 35664 + }, + { + "epoch": 11.01, + "learning_rate": 8.845556278086163e-06, + "loss": 0.0081, + "step": 35665 + }, + { + "epoch": 11.01, + "learning_rate": 8.845059505122224e-06, + "loss": 0.0079, + "step": 35666 + }, + { + "epoch": 11.01, + "learning_rate": 8.844562735047002e-06, + "loss": 0.008, + "step": 35667 + }, + { + "epoch": 11.01, + "learning_rate": 8.844065967861735e-06, + "loss": 0.0074, + "step": 35668 + }, + { + "epoch": 11.02, + "learning_rate": 8.843569203567672e-06, + "loss": 0.0096, + "step": 35669 + }, + { + "epoch": 11.02, + "learning_rate": 8.843072442166056e-06, + "loss": 0.0082, + "step": 35670 + }, + { + "epoch": 11.02, + "learning_rate": 8.842575683658122e-06, + "loss": 0.0079, + "step": 35671 + }, + { + "epoch": 11.02, + "learning_rate": 8.84207892804512e-06, + "loss": 0.009, + "step": 35672 + }, + { + "epoch": 11.02, + "learning_rate": 8.841582175328293e-06, + "loss": 0.009, + "step": 35673 + }, + { + "epoch": 11.02, + "learning_rate": 8.841085425508876e-06, + "loss": 0.0091, + "step": 35674 + }, + { + "epoch": 11.02, + "learning_rate": 8.840588678588115e-06, + "loss": 0.0088, + "step": 35675 + }, + { + "epoch": 11.02, + "learning_rate": 8.840091934567257e-06, + "loss": 0.0081, + "step": 35676 + }, + { + "epoch": 11.02, + "learning_rate": 8.839595193447538e-06, + "loss": 0.0086, + "step": 35677 + }, + { + "epoch": 11.02, + "learning_rate": 8.839098455230201e-06, + "loss": 0.0081, + "step": 35678 + }, + { + "epoch": 11.02, + "learning_rate": 8.838601719916495e-06, + "loss": 0.0122, + "step": 35679 + }, + { + "epoch": 11.02, + "learning_rate": 8.838104987507656e-06, + "loss": 0.0087, + "step": 35680 + }, + { + "epoch": 11.02, + "learning_rate": 8.837608258004926e-06, + "loss": 0.009, + "step": 35681 + }, + { + "epoch": 11.02, + "learning_rate": 8.837111531409554e-06, + "loss": 0.009, + "step": 35682 + }, + { + "epoch": 11.02, + "learning_rate": 8.836614807722778e-06, + "loss": 0.0087, + "step": 35683 + }, + { + "epoch": 11.02, + "learning_rate": 8.836118086945837e-06, + "loss": 0.0098, + "step": 35684 + }, + { + "epoch": 11.02, + "learning_rate": 8.835621369079982e-06, + "loss": 0.0089, + "step": 35685 + }, + { + "epoch": 11.02, + "learning_rate": 8.835124654126445e-06, + "loss": 0.0083, + "step": 35686 + }, + { + "epoch": 11.02, + "learning_rate": 8.834627942086475e-06, + "loss": 0.0091, + "step": 35687 + }, + { + "epoch": 11.02, + "learning_rate": 8.834131232961317e-06, + "loss": 0.0102, + "step": 35688 + }, + { + "epoch": 11.02, + "learning_rate": 8.833634526752203e-06, + "loss": 0.0082, + "step": 35689 + }, + { + "epoch": 11.02, + "learning_rate": 8.833137823460384e-06, + "loss": 0.0074, + "step": 35690 + }, + { + "epoch": 11.02, + "learning_rate": 8.8326411230871e-06, + "loss": 0.0091, + "step": 35691 + }, + { + "epoch": 11.02, + "learning_rate": 8.832144425633597e-06, + "loss": 0.0085, + "step": 35692 + }, + { + "epoch": 11.02, + "learning_rate": 8.831647731101112e-06, + "loss": 0.0073, + "step": 35693 + }, + { + "epoch": 11.02, + "learning_rate": 8.831151039490889e-06, + "loss": 0.0102, + "step": 35694 + }, + { + "epoch": 11.02, + "learning_rate": 8.830654350804171e-06, + "loss": 0.0079, + "step": 35695 + }, + { + "epoch": 11.02, + "learning_rate": 8.830157665042196e-06, + "loss": 0.0079, + "step": 35696 + }, + { + "epoch": 11.02, + "learning_rate": 8.829660982206212e-06, + "loss": 0.0094, + "step": 35697 + }, + { + "epoch": 11.02, + "learning_rate": 8.829164302297463e-06, + "loss": 0.0089, + "step": 35698 + }, + { + "epoch": 11.02, + "learning_rate": 8.828667625317183e-06, + "loss": 0.0089, + "step": 35699 + }, + { + "epoch": 11.02, + "learning_rate": 8.82817095126662e-06, + "loss": 0.0088, + "step": 35700 + }, + { + "epoch": 11.03, + "learning_rate": 8.827674280147019e-06, + "loss": 0.0089, + "step": 35701 + }, + { + "epoch": 11.03, + "learning_rate": 8.827177611959613e-06, + "loss": 0.0074, + "step": 35702 + }, + { + "epoch": 11.03, + "learning_rate": 8.826680946705652e-06, + "loss": 0.0088, + "step": 35703 + }, + { + "epoch": 11.03, + "learning_rate": 8.826184284386377e-06, + "loss": 0.0082, + "step": 35704 + }, + { + "epoch": 11.03, + "learning_rate": 8.825687625003029e-06, + "loss": 0.0086, + "step": 35705 + }, + { + "epoch": 11.03, + "learning_rate": 8.825190968556846e-06, + "loss": 0.0074, + "step": 35706 + }, + { + "epoch": 11.03, + "learning_rate": 8.824694315049082e-06, + "loss": 0.007, + "step": 35707 + }, + { + "epoch": 11.03, + "learning_rate": 8.824197664480968e-06, + "loss": 0.008, + "step": 35708 + }, + { + "epoch": 11.03, + "learning_rate": 8.823701016853748e-06, + "loss": 0.0083, + "step": 35709 + }, + { + "epoch": 11.03, + "learning_rate": 8.82320437216867e-06, + "loss": 0.0104, + "step": 35710 + }, + { + "epoch": 11.03, + "learning_rate": 8.822707730426972e-06, + "loss": 0.0094, + "step": 35711 + }, + { + "epoch": 11.03, + "learning_rate": 8.822211091629891e-06, + "loss": 0.0085, + "step": 35712 + }, + { + "epoch": 11.03, + "learning_rate": 8.821714455778685e-06, + "loss": 0.0098, + "step": 35713 + }, + { + "epoch": 11.03, + "learning_rate": 8.82121782287458e-06, + "loss": 0.0084, + "step": 35714 + }, + { + "epoch": 11.03, + "learning_rate": 8.820721192918822e-06, + "loss": 0.0075, + "step": 35715 + }, + { + "epoch": 11.03, + "learning_rate": 8.820224565912661e-06, + "loss": 0.0076, + "step": 35716 + }, + { + "epoch": 11.03, + "learning_rate": 8.819727941857329e-06, + "loss": 0.0075, + "step": 35717 + }, + { + "epoch": 11.03, + "learning_rate": 8.819231320754074e-06, + "loss": 0.011, + "step": 35718 + }, + { + "epoch": 11.03, + "learning_rate": 8.81873470260414e-06, + "loss": 0.006, + "step": 35719 + }, + { + "epoch": 11.03, + "learning_rate": 8.81823808740876e-06, + "loss": 0.0073, + "step": 35720 + }, + { + "epoch": 11.03, + "learning_rate": 8.817741475169186e-06, + "loss": 0.0076, + "step": 35721 + }, + { + "epoch": 11.03, + "learning_rate": 8.817244865886658e-06, + "loss": 0.0086, + "step": 35722 + }, + { + "epoch": 11.03, + "learning_rate": 8.816748259562413e-06, + "loss": 0.0093, + "step": 35723 + }, + { + "epoch": 11.03, + "learning_rate": 8.816251656197696e-06, + "loss": 0.0079, + "step": 35724 + }, + { + "epoch": 11.03, + "learning_rate": 8.815755055793752e-06, + "loss": 0.0083, + "step": 35725 + }, + { + "epoch": 11.03, + "learning_rate": 8.81525845835182e-06, + "loss": 0.0086, + "step": 35726 + }, + { + "epoch": 11.03, + "learning_rate": 8.81476186387314e-06, + "loss": 0.0074, + "step": 35727 + }, + { + "epoch": 11.03, + "learning_rate": 8.814265272358959e-06, + "loss": 0.008, + "step": 35728 + }, + { + "epoch": 11.03, + "learning_rate": 8.81376868381052e-06, + "loss": 0.0066, + "step": 35729 + }, + { + "epoch": 11.03, + "learning_rate": 8.813272098229055e-06, + "loss": 0.0097, + "step": 35730 + }, + { + "epoch": 11.03, + "learning_rate": 8.812775515615816e-06, + "loss": 0.0086, + "step": 35731 + }, + { + "epoch": 11.03, + "learning_rate": 8.812278935972044e-06, + "loss": 0.0081, + "step": 35732 + }, + { + "epoch": 11.04, + "learning_rate": 8.811782359298977e-06, + "loss": 0.0087, + "step": 35733 + }, + { + "epoch": 11.04, + "learning_rate": 8.811285785597858e-06, + "loss": 0.0095, + "step": 35734 + }, + { + "epoch": 11.04, + "learning_rate": 8.810789214869933e-06, + "loss": 0.0094, + "step": 35735 + }, + { + "epoch": 11.04, + "learning_rate": 8.81029264711644e-06, + "loss": 0.0083, + "step": 35736 + }, + { + "epoch": 11.04, + "learning_rate": 8.80979608233862e-06, + "loss": 0.008, + "step": 35737 + }, + { + "epoch": 11.04, + "learning_rate": 8.809299520537719e-06, + "loss": 0.0078, + "step": 35738 + }, + { + "epoch": 11.04, + "learning_rate": 8.808802961714977e-06, + "loss": 0.0084, + "step": 35739 + }, + { + "epoch": 11.04, + "learning_rate": 8.808306405871634e-06, + "loss": 0.0081, + "step": 35740 + }, + { + "epoch": 11.04, + "learning_rate": 8.807809853008938e-06, + "loss": 0.0088, + "step": 35741 + }, + { + "epoch": 11.04, + "learning_rate": 8.807313303128125e-06, + "loss": 0.0087, + "step": 35742 + }, + { + "epoch": 11.04, + "learning_rate": 8.806816756230438e-06, + "loss": 0.0072, + "step": 35743 + }, + { + "epoch": 11.04, + "learning_rate": 8.806320212317123e-06, + "loss": 0.0114, + "step": 35744 + }, + { + "epoch": 11.04, + "learning_rate": 8.805823671389415e-06, + "loss": 0.0067, + "step": 35745 + }, + { + "epoch": 11.04, + "learning_rate": 8.805327133448561e-06, + "loss": 0.0091, + "step": 35746 + }, + { + "epoch": 11.04, + "learning_rate": 8.804830598495804e-06, + "loss": 0.0096, + "step": 35747 + }, + { + "epoch": 11.04, + "learning_rate": 8.80433406653238e-06, + "loss": 0.0084, + "step": 35748 + }, + { + "epoch": 11.04, + "learning_rate": 8.803837537559536e-06, + "loss": 0.0082, + "step": 35749 + }, + { + "epoch": 11.04, + "learning_rate": 8.803341011578515e-06, + "loss": 0.0096, + "step": 35750 + }, + { + "epoch": 11.04, + "learning_rate": 8.802844488590552e-06, + "loss": 0.008, + "step": 35751 + }, + { + "epoch": 11.04, + "learning_rate": 8.802347968596896e-06, + "loss": 0.0112, + "step": 35752 + }, + { + "epoch": 11.04, + "learning_rate": 8.801851451598788e-06, + "loss": 0.0079, + "step": 35753 + }, + { + "epoch": 11.04, + "learning_rate": 8.801354937597465e-06, + "loss": 0.0075, + "step": 35754 + }, + { + "epoch": 11.04, + "learning_rate": 8.80085842659417e-06, + "loss": 0.0095, + "step": 35755 + }, + { + "epoch": 11.04, + "learning_rate": 8.800361918590153e-06, + "loss": 0.0077, + "step": 35756 + }, + { + "epoch": 11.04, + "learning_rate": 8.799865413586645e-06, + "loss": 0.009, + "step": 35757 + }, + { + "epoch": 11.04, + "learning_rate": 8.799368911584891e-06, + "loss": 0.0088, + "step": 35758 + }, + { + "epoch": 11.04, + "learning_rate": 8.798872412586138e-06, + "loss": 0.0088, + "step": 35759 + }, + { + "epoch": 11.04, + "learning_rate": 8.798375916591625e-06, + "loss": 0.0078, + "step": 35760 + }, + { + "epoch": 11.04, + "learning_rate": 8.797879423602588e-06, + "loss": 0.0078, + "step": 35761 + }, + { + "epoch": 11.04, + "learning_rate": 8.797382933620278e-06, + "loss": 0.0094, + "step": 35762 + }, + { + "epoch": 11.04, + "learning_rate": 8.796886446645934e-06, + "loss": 0.0088, + "step": 35763 + }, + { + "epoch": 11.04, + "learning_rate": 8.796389962680794e-06, + "loss": 0.0083, + "step": 35764 + }, + { + "epoch": 11.04, + "learning_rate": 8.795893481726098e-06, + "loss": 0.0102, + "step": 35765 + }, + { + "epoch": 11.05, + "learning_rate": 8.795397003783099e-06, + "loss": 0.0087, + "step": 35766 + }, + { + "epoch": 11.05, + "learning_rate": 8.794900528853028e-06, + "loss": 0.0089, + "step": 35767 + }, + { + "epoch": 11.05, + "learning_rate": 8.79440405693713e-06, + "loss": 0.0082, + "step": 35768 + }, + { + "epoch": 11.05, + "learning_rate": 8.793907588036652e-06, + "loss": 0.0087, + "step": 35769 + }, + { + "epoch": 11.05, + "learning_rate": 8.793411122152827e-06, + "loss": 0.0081, + "step": 35770 + }, + { + "epoch": 11.05, + "learning_rate": 8.7929146592869e-06, + "loss": 0.0079, + "step": 35771 + }, + { + "epoch": 11.05, + "learning_rate": 8.79241819944012e-06, + "loss": 0.0092, + "step": 35772 + }, + { + "epoch": 11.05, + "learning_rate": 8.791921742613714e-06, + "loss": 0.0083, + "step": 35773 + }, + { + "epoch": 11.05, + "learning_rate": 8.791425288808936e-06, + "loss": 0.0074, + "step": 35774 + }, + { + "epoch": 11.05, + "learning_rate": 8.790928838027026e-06, + "loss": 0.0082, + "step": 35775 + }, + { + "epoch": 11.05, + "learning_rate": 8.79043239026922e-06, + "loss": 0.0097, + "step": 35776 + }, + { + "epoch": 11.05, + "learning_rate": 8.789935945536765e-06, + "loss": 0.0075, + "step": 35777 + }, + { + "epoch": 11.05, + "learning_rate": 8.7894395038309e-06, + "loss": 0.0078, + "step": 35778 + }, + { + "epoch": 11.05, + "learning_rate": 8.788943065152867e-06, + "loss": 0.0082, + "step": 35779 + }, + { + "epoch": 11.05, + "learning_rate": 8.78844662950391e-06, + "loss": 0.0086, + "step": 35780 + }, + { + "epoch": 11.05, + "learning_rate": 8.78795019688527e-06, + "loss": 0.0105, + "step": 35781 + }, + { + "epoch": 11.05, + "learning_rate": 8.787453767298185e-06, + "loss": 0.0086, + "step": 35782 + }, + { + "epoch": 11.05, + "learning_rate": 8.786957340743897e-06, + "loss": 0.0071, + "step": 35783 + }, + { + "epoch": 11.05, + "learning_rate": 8.786460917223656e-06, + "loss": 0.0087, + "step": 35784 + }, + { + "epoch": 11.05, + "learning_rate": 8.785964496738694e-06, + "loss": 0.0066, + "step": 35785 + }, + { + "epoch": 11.05, + "learning_rate": 8.785468079290254e-06, + "loss": 0.0087, + "step": 35786 + }, + { + "epoch": 11.05, + "learning_rate": 8.784971664879585e-06, + "loss": 0.009, + "step": 35787 + }, + { + "epoch": 11.05, + "learning_rate": 8.784475253507922e-06, + "loss": 0.0078, + "step": 35788 + }, + { + "epoch": 11.05, + "learning_rate": 8.783978845176504e-06, + "loss": 0.0073, + "step": 35789 + }, + { + "epoch": 11.05, + "learning_rate": 8.783482439886579e-06, + "loss": 0.0082, + "step": 35790 + }, + { + "epoch": 11.05, + "learning_rate": 8.78298603763939e-06, + "loss": 0.0087, + "step": 35791 + }, + { + "epoch": 11.05, + "learning_rate": 8.782489638436169e-06, + "loss": 0.0082, + "step": 35792 + }, + { + "epoch": 11.05, + "learning_rate": 8.781993242278168e-06, + "loss": 0.0096, + "step": 35793 + }, + { + "epoch": 11.05, + "learning_rate": 8.781496849166625e-06, + "loss": 0.0077, + "step": 35794 + }, + { + "epoch": 11.05, + "learning_rate": 8.781000459102777e-06, + "loss": 0.0081, + "step": 35795 + }, + { + "epoch": 11.05, + "learning_rate": 8.780504072087868e-06, + "loss": 0.0078, + "step": 35796 + }, + { + "epoch": 11.05, + "learning_rate": 8.780007688123146e-06, + "loss": 0.0082, + "step": 35797 + }, + { + "epoch": 11.06, + "learning_rate": 8.779511307209844e-06, + "loss": 0.0077, + "step": 35798 + }, + { + "epoch": 11.06, + "learning_rate": 8.779014929349205e-06, + "loss": 0.0065, + "step": 35799 + }, + { + "epoch": 11.06, + "learning_rate": 8.778518554542476e-06, + "loss": 0.0081, + "step": 35800 + }, + { + "epoch": 11.06, + "learning_rate": 8.778022182790892e-06, + "loss": 0.0076, + "step": 35801 + }, + { + "epoch": 11.06, + "learning_rate": 8.777525814095697e-06, + "loss": 0.0075, + "step": 35802 + }, + { + "epoch": 11.06, + "learning_rate": 8.77702944845814e-06, + "loss": 0.0081, + "step": 35803 + }, + { + "epoch": 11.06, + "learning_rate": 8.776533085879447e-06, + "loss": 0.0079, + "step": 35804 + }, + { + "epoch": 11.06, + "learning_rate": 8.776036726360872e-06, + "loss": 0.0085, + "step": 35805 + }, + { + "epoch": 11.06, + "learning_rate": 8.775540369903654e-06, + "loss": 0.009, + "step": 35806 + }, + { + "epoch": 11.06, + "learning_rate": 8.775044016509026e-06, + "loss": 0.0073, + "step": 35807 + }, + { + "epoch": 11.06, + "learning_rate": 8.77454766617824e-06, + "loss": 0.0091, + "step": 35808 + }, + { + "epoch": 11.06, + "learning_rate": 8.774051318912538e-06, + "loss": 0.0074, + "step": 35809 + }, + { + "epoch": 11.06, + "learning_rate": 8.773554974713151e-06, + "loss": 0.0098, + "step": 35810 + }, + { + "epoch": 11.06, + "learning_rate": 8.77305863358133e-06, + "loss": 0.0086, + "step": 35811 + }, + { + "epoch": 11.06, + "learning_rate": 8.772562295518314e-06, + "loss": 0.0081, + "step": 35812 + }, + { + "epoch": 11.06, + "learning_rate": 8.772065960525343e-06, + "loss": 0.0083, + "step": 35813 + }, + { + "epoch": 11.06, + "learning_rate": 8.771569628603656e-06, + "loss": 0.0087, + "step": 35814 + }, + { + "epoch": 11.06, + "learning_rate": 8.771073299754502e-06, + "loss": 0.007, + "step": 35815 + }, + { + "epoch": 11.06, + "learning_rate": 8.770576973979113e-06, + "loss": 0.0066, + "step": 35816 + }, + { + "epoch": 11.06, + "learning_rate": 8.770080651278737e-06, + "loss": 0.0105, + "step": 35817 + }, + { + "epoch": 11.06, + "learning_rate": 8.769584331654617e-06, + "loss": 0.0096, + "step": 35818 + }, + { + "epoch": 11.06, + "learning_rate": 8.769088015107987e-06, + "loss": 0.0073, + "step": 35819 + }, + { + "epoch": 11.06, + "learning_rate": 8.76859170164009e-06, + "loss": 0.0082, + "step": 35820 + }, + { + "epoch": 11.06, + "learning_rate": 8.768095391252179e-06, + "loss": 0.0089, + "step": 35821 + }, + { + "epoch": 11.06, + "learning_rate": 8.767599083945478e-06, + "loss": 0.0099, + "step": 35822 + }, + { + "epoch": 11.06, + "learning_rate": 8.767102779721238e-06, + "loss": 0.0069, + "step": 35823 + }, + { + "epoch": 11.06, + "learning_rate": 8.766606478580696e-06, + "loss": 0.0093, + "step": 35824 + }, + { + "epoch": 11.06, + "learning_rate": 8.766110180525104e-06, + "loss": 0.0082, + "step": 35825 + }, + { + "epoch": 11.06, + "learning_rate": 8.76561388555569e-06, + "loss": 0.0083, + "step": 35826 + }, + { + "epoch": 11.06, + "learning_rate": 8.7651175936737e-06, + "loss": 0.01, + "step": 35827 + }, + { + "epoch": 11.06, + "learning_rate": 8.764621304880382e-06, + "loss": 0.0074, + "step": 35828 + }, + { + "epoch": 11.06, + "learning_rate": 8.764125019176966e-06, + "loss": 0.0093, + "step": 35829 + }, + { + "epoch": 11.07, + "learning_rate": 8.7636287365647e-06, + "loss": 0.0077, + "step": 35830 + }, + { + "epoch": 11.07, + "learning_rate": 8.763132457044824e-06, + "loss": 0.009, + "step": 35831 + }, + { + "epoch": 11.07, + "learning_rate": 8.76263618061858e-06, + "loss": 0.0078, + "step": 35832 + }, + { + "epoch": 11.07, + "learning_rate": 8.762139907287209e-06, + "loss": 0.0084, + "step": 35833 + }, + { + "epoch": 11.07, + "learning_rate": 8.761643637051954e-06, + "loss": 0.008, + "step": 35834 + }, + { + "epoch": 11.07, + "learning_rate": 8.761147369914049e-06, + "loss": 0.0084, + "step": 35835 + }, + { + "epoch": 11.07, + "learning_rate": 8.760651105874743e-06, + "loss": 0.0078, + "step": 35836 + }, + { + "epoch": 11.07, + "learning_rate": 8.760154844935276e-06, + "loss": 0.0075, + "step": 35837 + }, + { + "epoch": 11.07, + "learning_rate": 8.759658587096883e-06, + "loss": 0.008, + "step": 35838 + }, + { + "epoch": 11.07, + "learning_rate": 8.759162332360814e-06, + "loss": 0.008, + "step": 35839 + }, + { + "epoch": 11.07, + "learning_rate": 8.758666080728308e-06, + "loss": 0.0085, + "step": 35840 + }, + { + "epoch": 11.07, + "learning_rate": 8.7581698322006e-06, + "loss": 0.0089, + "step": 35841 + }, + { + "epoch": 11.07, + "learning_rate": 8.757673586778937e-06, + "loss": 0.0073, + "step": 35842 + }, + { + "epoch": 11.07, + "learning_rate": 8.757177344464561e-06, + "loss": 0.0071, + "step": 35843 + }, + { + "epoch": 11.07, + "learning_rate": 8.756681105258711e-06, + "loss": 0.0077, + "step": 35844 + }, + { + "epoch": 11.07, + "learning_rate": 8.756184869162625e-06, + "loss": 0.0074, + "step": 35845 + }, + { + "epoch": 11.07, + "learning_rate": 8.755688636177551e-06, + "loss": 0.0071, + "step": 35846 + }, + { + "epoch": 11.07, + "learning_rate": 8.755192406304725e-06, + "loss": 0.0073, + "step": 35847 + }, + { + "epoch": 11.07, + "learning_rate": 8.75469617954539e-06, + "loss": 0.0081, + "step": 35848 + }, + { + "epoch": 11.07, + "learning_rate": 8.754199955900788e-06, + "loss": 0.0092, + "step": 35849 + }, + { + "epoch": 11.07, + "learning_rate": 8.753703735372159e-06, + "loss": 0.0098, + "step": 35850 + }, + { + "epoch": 11.07, + "learning_rate": 8.75320751796074e-06, + "loss": 0.0076, + "step": 35851 + }, + { + "epoch": 11.07, + "learning_rate": 8.752711303667786e-06, + "loss": 0.0086, + "step": 35852 + }, + { + "epoch": 11.07, + "learning_rate": 8.75221509249452e-06, + "loss": 0.0084, + "step": 35853 + }, + { + "epoch": 11.07, + "learning_rate": 8.751718884442193e-06, + "loss": 0.0075, + "step": 35854 + }, + { + "epoch": 11.07, + "learning_rate": 8.751222679512045e-06, + "loss": 0.0091, + "step": 35855 + }, + { + "epoch": 11.07, + "learning_rate": 8.75072647770532e-06, + "loss": 0.0087, + "step": 35856 + }, + { + "epoch": 11.07, + "learning_rate": 8.750230279023253e-06, + "loss": 0.0058, + "step": 35857 + }, + { + "epoch": 11.07, + "learning_rate": 8.749734083467087e-06, + "loss": 0.008, + "step": 35858 + }, + { + "epoch": 11.07, + "learning_rate": 8.749237891038068e-06, + "loss": 0.0086, + "step": 35859 + }, + { + "epoch": 11.07, + "learning_rate": 8.74874170173743e-06, + "loss": 0.0084, + "step": 35860 + }, + { + "epoch": 11.07, + "learning_rate": 8.748245515566417e-06, + "loss": 0.0074, + "step": 35861 + }, + { + "epoch": 11.07, + "learning_rate": 8.747749332526275e-06, + "loss": 0.0095, + "step": 35862 + }, + { + "epoch": 11.08, + "learning_rate": 8.747253152618235e-06, + "loss": 0.0088, + "step": 35863 + }, + { + "epoch": 11.08, + "learning_rate": 8.746756975843545e-06, + "loss": 0.0081, + "step": 35864 + }, + { + "epoch": 11.08, + "learning_rate": 8.746260802203447e-06, + "loss": 0.0082, + "step": 35865 + }, + { + "epoch": 11.08, + "learning_rate": 8.745764631699174e-06, + "loss": 0.0088, + "step": 35866 + }, + { + "epoch": 11.08, + "learning_rate": 8.745268464331976e-06, + "loss": 0.008, + "step": 35867 + }, + { + "epoch": 11.08, + "learning_rate": 8.744772300103092e-06, + "loss": 0.0066, + "step": 35868 + }, + { + "epoch": 11.08, + "learning_rate": 8.744276139013756e-06, + "loss": 0.0075, + "step": 35869 + }, + { + "epoch": 11.08, + "learning_rate": 8.743779981065218e-06, + "loss": 0.0097, + "step": 35870 + }, + { + "epoch": 11.08, + "learning_rate": 8.743283826258717e-06, + "loss": 0.009, + "step": 35871 + }, + { + "epoch": 11.08, + "learning_rate": 8.74278767459549e-06, + "loss": 0.009, + "step": 35872 + }, + { + "epoch": 11.08, + "learning_rate": 8.74229152607678e-06, + "loss": 0.0085, + "step": 35873 + }, + { + "epoch": 11.08, + "learning_rate": 8.74179538070383e-06, + "loss": 0.0068, + "step": 35874 + }, + { + "epoch": 11.08, + "learning_rate": 8.741299238477879e-06, + "loss": 0.0064, + "step": 35875 + }, + { + "epoch": 11.08, + "learning_rate": 8.740803099400164e-06, + "loss": 0.0076, + "step": 35876 + }, + { + "epoch": 11.08, + "learning_rate": 8.740306963471935e-06, + "loss": 0.0106, + "step": 35877 + }, + { + "epoch": 11.08, + "learning_rate": 8.739810830694427e-06, + "loss": 0.0083, + "step": 35878 + }, + { + "epoch": 11.08, + "learning_rate": 8.73931470106888e-06, + "loss": 0.0073, + "step": 35879 + }, + { + "epoch": 11.08, + "learning_rate": 8.73881857459654e-06, + "loss": 0.0079, + "step": 35880 + }, + { + "epoch": 11.08, + "learning_rate": 8.738322451278643e-06, + "loss": 0.0107, + "step": 35881 + }, + { + "epoch": 11.08, + "learning_rate": 8.737826331116432e-06, + "loss": 0.0084, + "step": 35882 + }, + { + "epoch": 11.08, + "learning_rate": 8.73733021411115e-06, + "loss": 0.0105, + "step": 35883 + }, + { + "epoch": 11.08, + "learning_rate": 8.73683410026403e-06, + "loss": 0.0082, + "step": 35884 + }, + { + "epoch": 11.08, + "learning_rate": 8.736337989576321e-06, + "loss": 0.0092, + "step": 35885 + }, + { + "epoch": 11.08, + "learning_rate": 8.735841882049263e-06, + "loss": 0.008, + "step": 35886 + }, + { + "epoch": 11.08, + "learning_rate": 8.73534577768409e-06, + "loss": 0.0073, + "step": 35887 + }, + { + "epoch": 11.08, + "learning_rate": 8.734849676482052e-06, + "loss": 0.0087, + "step": 35888 + }, + { + "epoch": 11.08, + "learning_rate": 8.734353578444384e-06, + "loss": 0.0104, + "step": 35889 + }, + { + "epoch": 11.08, + "learning_rate": 8.73385748357233e-06, + "loss": 0.0083, + "step": 35890 + }, + { + "epoch": 11.08, + "learning_rate": 8.733361391867128e-06, + "loss": 0.007, + "step": 35891 + }, + { + "epoch": 11.08, + "learning_rate": 8.732865303330022e-06, + "loss": 0.0089, + "step": 35892 + }, + { + "epoch": 11.08, + "learning_rate": 8.732369217962252e-06, + "loss": 0.0081, + "step": 35893 + }, + { + "epoch": 11.08, + "learning_rate": 8.731873135765053e-06, + "loss": 0.0089, + "step": 35894 + }, + { + "epoch": 11.09, + "learning_rate": 8.731377056739674e-06, + "loss": 0.0085, + "step": 35895 + }, + { + "epoch": 11.09, + "learning_rate": 8.730880980887353e-06, + "loss": 0.0089, + "step": 35896 + }, + { + "epoch": 11.09, + "learning_rate": 8.730384908209326e-06, + "loss": 0.0088, + "step": 35897 + }, + { + "epoch": 11.09, + "learning_rate": 8.729888838706842e-06, + "loss": 0.0086, + "step": 35898 + }, + { + "epoch": 11.09, + "learning_rate": 8.729392772381138e-06, + "loss": 0.0064, + "step": 35899 + }, + { + "epoch": 11.09, + "learning_rate": 8.72889670923345e-06, + "loss": 0.0089, + "step": 35900 + }, + { + "epoch": 11.09, + "learning_rate": 8.728400649265026e-06, + "loss": 0.0086, + "step": 35901 + }, + { + "epoch": 11.09, + "learning_rate": 8.727904592477106e-06, + "loss": 0.0077, + "step": 35902 + }, + { + "epoch": 11.09, + "learning_rate": 8.727408538870927e-06, + "loss": 0.0087, + "step": 35903 + }, + { + "epoch": 11.09, + "learning_rate": 8.726912488447728e-06, + "loss": 0.0069, + "step": 35904 + }, + { + "epoch": 11.09, + "learning_rate": 8.726416441208758e-06, + "loss": 0.0089, + "step": 35905 + }, + { + "epoch": 11.09, + "learning_rate": 8.72592039715525e-06, + "loss": 0.0084, + "step": 35906 + }, + { + "epoch": 11.09, + "learning_rate": 8.725424356288446e-06, + "loss": 0.0091, + "step": 35907 + }, + { + "epoch": 11.09, + "learning_rate": 8.724928318609593e-06, + "loss": 0.0093, + "step": 35908 + }, + { + "epoch": 11.09, + "learning_rate": 8.724432284119924e-06, + "loss": 0.0071, + "step": 35909 + }, + { + "epoch": 11.09, + "learning_rate": 8.723936252820681e-06, + "loss": 0.0084, + "step": 35910 + }, + { + "epoch": 11.09, + "learning_rate": 8.72344022471311e-06, + "loss": 0.0089, + "step": 35911 + }, + { + "epoch": 11.09, + "learning_rate": 8.722944199798444e-06, + "loss": 0.0084, + "step": 35912 + }, + { + "epoch": 11.09, + "learning_rate": 8.722448178077931e-06, + "loss": 0.0087, + "step": 35913 + }, + { + "epoch": 11.09, + "learning_rate": 8.721952159552807e-06, + "loss": 0.0087, + "step": 35914 + }, + { + "epoch": 11.09, + "learning_rate": 8.72145614422431e-06, + "loss": 0.0082, + "step": 35915 + }, + { + "epoch": 11.09, + "learning_rate": 8.720960132093688e-06, + "loss": 0.008, + "step": 35916 + }, + { + "epoch": 11.09, + "learning_rate": 8.72046412316218e-06, + "loss": 0.0076, + "step": 35917 + }, + { + "epoch": 11.09, + "learning_rate": 8.719968117431018e-06, + "loss": 0.008, + "step": 35918 + }, + { + "epoch": 11.09, + "learning_rate": 8.719472114901454e-06, + "loss": 0.0082, + "step": 35919 + }, + { + "epoch": 11.09, + "learning_rate": 8.718976115574722e-06, + "loss": 0.0086, + "step": 35920 + }, + { + "epoch": 11.09, + "learning_rate": 8.718480119452069e-06, + "loss": 0.009, + "step": 35921 + }, + { + "epoch": 11.09, + "learning_rate": 8.717984126534725e-06, + "loss": 0.0086, + "step": 35922 + }, + { + "epoch": 11.09, + "learning_rate": 8.717488136823939e-06, + "loss": 0.0066, + "step": 35923 + }, + { + "epoch": 11.09, + "learning_rate": 8.716992150320951e-06, + "loss": 0.0079, + "step": 35924 + }, + { + "epoch": 11.09, + "learning_rate": 8.716496167026994e-06, + "loss": 0.0093, + "step": 35925 + }, + { + "epoch": 11.09, + "learning_rate": 8.716000186943318e-06, + "loss": 0.0078, + "step": 35926 + }, + { + "epoch": 11.09, + "learning_rate": 8.715504210071161e-06, + "loss": 0.0073, + "step": 35927 + }, + { + "epoch": 11.1, + "learning_rate": 8.71500823641176e-06, + "loss": 0.0092, + "step": 35928 + }, + { + "epoch": 11.1, + "learning_rate": 8.714512265966357e-06, + "loss": 0.0073, + "step": 35929 + }, + { + "epoch": 11.1, + "learning_rate": 8.714016298736198e-06, + "loss": 0.0094, + "step": 35930 + }, + { + "epoch": 11.1, + "learning_rate": 8.713520334722515e-06, + "loss": 0.008, + "step": 35931 + }, + { + "epoch": 11.1, + "learning_rate": 8.71302437392655e-06, + "loss": 0.0072, + "step": 35932 + }, + { + "epoch": 11.1, + "learning_rate": 8.71252841634955e-06, + "loss": 0.0087, + "step": 35933 + }, + { + "epoch": 11.1, + "learning_rate": 8.71203246199275e-06, + "loss": 0.0073, + "step": 35934 + }, + { + "epoch": 11.1, + "learning_rate": 8.71153651085739e-06, + "loss": 0.0086, + "step": 35935 + }, + { + "epoch": 11.1, + "learning_rate": 8.711040562944717e-06, + "loss": 0.0097, + "step": 35936 + }, + { + "epoch": 11.1, + "learning_rate": 8.710544618255961e-06, + "loss": 0.0082, + "step": 35937 + }, + { + "epoch": 11.1, + "learning_rate": 8.710048676792368e-06, + "loss": 0.0078, + "step": 35938 + }, + { + "epoch": 11.1, + "learning_rate": 8.709552738555183e-06, + "loss": 0.0081, + "step": 35939 + }, + { + "epoch": 11.1, + "learning_rate": 8.709056803545641e-06, + "loss": 0.0079, + "step": 35940 + }, + { + "epoch": 11.1, + "learning_rate": 8.708560871764982e-06, + "loss": 0.0096, + "step": 35941 + }, + { + "epoch": 11.1, + "learning_rate": 8.70806494321445e-06, + "loss": 0.0083, + "step": 35942 + }, + { + "epoch": 11.1, + "learning_rate": 8.70756901789528e-06, + "loss": 0.0081, + "step": 35943 + }, + { + "epoch": 11.1, + "learning_rate": 8.707073095808716e-06, + "loss": 0.0089, + "step": 35944 + }, + { + "epoch": 11.1, + "learning_rate": 8.706577176956002e-06, + "loss": 0.0089, + "step": 35945 + }, + { + "epoch": 11.1, + "learning_rate": 8.706081261338368e-06, + "loss": 0.009, + "step": 35946 + }, + { + "epoch": 11.1, + "learning_rate": 8.705585348957063e-06, + "loss": 0.009, + "step": 35947 + }, + { + "epoch": 11.1, + "learning_rate": 8.70508943981333e-06, + "loss": 0.008, + "step": 35948 + }, + { + "epoch": 11.1, + "learning_rate": 8.7045935339084e-06, + "loss": 0.0085, + "step": 35949 + }, + { + "epoch": 11.1, + "learning_rate": 8.704097631243517e-06, + "loss": 0.0078, + "step": 35950 + }, + { + "epoch": 11.1, + "learning_rate": 8.703601731819926e-06, + "loss": 0.0079, + "step": 35951 + }, + { + "epoch": 11.1, + "learning_rate": 8.703105835638862e-06, + "loss": 0.0099, + "step": 35952 + }, + { + "epoch": 11.1, + "learning_rate": 8.702609942701563e-06, + "loss": 0.0098, + "step": 35953 + }, + { + "epoch": 11.1, + "learning_rate": 8.702114053009276e-06, + "loss": 0.008, + "step": 35954 + }, + { + "epoch": 11.1, + "learning_rate": 8.701618166563241e-06, + "loss": 0.0082, + "step": 35955 + }, + { + "epoch": 11.1, + "learning_rate": 8.701122283364692e-06, + "loss": 0.0079, + "step": 35956 + }, + { + "epoch": 11.1, + "learning_rate": 8.700626403414873e-06, + "loss": 0.0084, + "step": 35957 + }, + { + "epoch": 11.1, + "learning_rate": 8.700130526715028e-06, + "loss": 0.0071, + "step": 35958 + }, + { + "epoch": 11.1, + "learning_rate": 8.69963465326639e-06, + "loss": 0.0078, + "step": 35959 + }, + { + "epoch": 11.11, + "learning_rate": 8.699138783070205e-06, + "loss": 0.0088, + "step": 35960 + }, + { + "epoch": 11.11, + "learning_rate": 8.698642916127712e-06, + "loss": 0.0075, + "step": 35961 + }, + { + "epoch": 11.11, + "learning_rate": 8.69814705244015e-06, + "loss": 0.0082, + "step": 35962 + }, + { + "epoch": 11.11, + "learning_rate": 8.697651192008756e-06, + "loss": 0.0096, + "step": 35963 + }, + { + "epoch": 11.11, + "learning_rate": 8.697155334834778e-06, + "loss": 0.0097, + "step": 35964 + }, + { + "epoch": 11.11, + "learning_rate": 8.69665948091945e-06, + "loss": 0.0085, + "step": 35965 + }, + { + "epoch": 11.11, + "learning_rate": 8.696163630264015e-06, + "loss": 0.0077, + "step": 35966 + }, + { + "epoch": 11.11, + "learning_rate": 8.695667782869714e-06, + "loss": 0.0118, + "step": 35967 + }, + { + "epoch": 11.11, + "learning_rate": 8.695171938737784e-06, + "loss": 0.008, + "step": 35968 + }, + { + "epoch": 11.11, + "learning_rate": 8.694676097869466e-06, + "loss": 0.009, + "step": 35969 + }, + { + "epoch": 11.11, + "learning_rate": 8.694180260266005e-06, + "loss": 0.0082, + "step": 35970 + }, + { + "epoch": 11.11, + "learning_rate": 8.693684425928633e-06, + "loss": 0.0091, + "step": 35971 + }, + { + "epoch": 11.11, + "learning_rate": 8.693188594858597e-06, + "loss": 0.0095, + "step": 35972 + }, + { + "epoch": 11.11, + "learning_rate": 8.692692767057135e-06, + "loss": 0.008, + "step": 35973 + }, + { + "epoch": 11.11, + "learning_rate": 8.692196942525485e-06, + "loss": 0.0087, + "step": 35974 + }, + { + "epoch": 11.11, + "learning_rate": 8.691701121264889e-06, + "loss": 0.0075, + "step": 35975 + }, + { + "epoch": 11.11, + "learning_rate": 8.69120530327659e-06, + "loss": 0.0076, + "step": 35976 + }, + { + "epoch": 11.11, + "learning_rate": 8.690709488561822e-06, + "loss": 0.0081, + "step": 35977 + }, + { + "epoch": 11.11, + "learning_rate": 8.690213677121829e-06, + "loss": 0.0078, + "step": 35978 + }, + { + "epoch": 11.11, + "learning_rate": 8.689717868957854e-06, + "loss": 0.0078, + "step": 35979 + }, + { + "epoch": 11.11, + "learning_rate": 8.68922206407113e-06, + "loss": 0.008, + "step": 35980 + }, + { + "epoch": 11.11, + "learning_rate": 8.6887262624629e-06, + "loss": 0.0086, + "step": 35981 + }, + { + "epoch": 11.11, + "learning_rate": 8.688230464134407e-06, + "loss": 0.0067, + "step": 35982 + }, + { + "epoch": 11.11, + "learning_rate": 8.687734669086888e-06, + "loss": 0.0081, + "step": 35983 + }, + { + "epoch": 11.11, + "learning_rate": 8.687238877321583e-06, + "loss": 0.0083, + "step": 35984 + }, + { + "epoch": 11.11, + "learning_rate": 8.686743088839735e-06, + "loss": 0.0074, + "step": 35985 + }, + { + "epoch": 11.11, + "learning_rate": 8.68624730364258e-06, + "loss": 0.008, + "step": 35986 + }, + { + "epoch": 11.11, + "learning_rate": 8.68575152173136e-06, + "loss": 0.0088, + "step": 35987 + }, + { + "epoch": 11.11, + "learning_rate": 8.685255743107315e-06, + "loss": 0.0092, + "step": 35988 + }, + { + "epoch": 11.11, + "learning_rate": 8.68475996777169e-06, + "loss": 0.0078, + "step": 35989 + }, + { + "epoch": 11.11, + "learning_rate": 8.684264195725716e-06, + "loss": 0.008, + "step": 35990 + }, + { + "epoch": 11.11, + "learning_rate": 8.683768426970636e-06, + "loss": 0.0066, + "step": 35991 + }, + { + "epoch": 11.12, + "learning_rate": 8.683272661507696e-06, + "loss": 0.0087, + "step": 35992 + }, + { + "epoch": 11.12, + "learning_rate": 8.682776899338128e-06, + "loss": 0.008, + "step": 35993 + }, + { + "epoch": 11.12, + "learning_rate": 8.682281140463172e-06, + "loss": 0.008, + "step": 35994 + }, + { + "epoch": 11.12, + "learning_rate": 8.681785384884078e-06, + "loss": 0.0094, + "step": 35995 + }, + { + "epoch": 11.12, + "learning_rate": 8.681289632602075e-06, + "loss": 0.0088, + "step": 35996 + }, + { + "epoch": 11.12, + "learning_rate": 8.680793883618405e-06, + "loss": 0.0096, + "step": 35997 + }, + { + "epoch": 11.12, + "learning_rate": 8.680298137934316e-06, + "loss": 0.0073, + "step": 35998 + }, + { + "epoch": 11.12, + "learning_rate": 8.67980239555104e-06, + "loss": 0.0072, + "step": 35999 + }, + { + "epoch": 11.12, + "learning_rate": 8.679306656469817e-06, + "loss": 0.0092, + "step": 36000 + }, + { + "epoch": 11.12, + "learning_rate": 8.678810920691894e-06, + "loss": 0.0078, + "step": 36001 + }, + { + "epoch": 11.12, + "learning_rate": 8.678315188218499e-06, + "loss": 0.0081, + "step": 36002 + }, + { + "epoch": 11.12, + "learning_rate": 8.677819459050882e-06, + "loss": 0.0074, + "step": 36003 + }, + { + "epoch": 11.12, + "learning_rate": 8.677323733190281e-06, + "loss": 0.0084, + "step": 36004 + }, + { + "epoch": 11.12, + "learning_rate": 8.67682801063793e-06, + "loss": 0.0089, + "step": 36005 + }, + { + "epoch": 11.12, + "learning_rate": 8.676332291395078e-06, + "loss": 0.0089, + "step": 36006 + }, + { + "epoch": 11.12, + "learning_rate": 8.67583657546296e-06, + "loss": 0.0077, + "step": 36007 + }, + { + "epoch": 11.12, + "learning_rate": 8.675340862842813e-06, + "loss": 0.0077, + "step": 36008 + }, + { + "epoch": 11.12, + "learning_rate": 8.674845153535882e-06, + "loss": 0.0079, + "step": 36009 + }, + { + "epoch": 11.12, + "learning_rate": 8.674349447543407e-06, + "loss": 0.0091, + "step": 36010 + }, + { + "epoch": 11.12, + "learning_rate": 8.673853744866625e-06, + "loss": 0.0089, + "step": 36011 + }, + { + "epoch": 11.12, + "learning_rate": 8.673358045506773e-06, + "loss": 0.0088, + "step": 36012 + }, + { + "epoch": 11.12, + "learning_rate": 8.6728623494651e-06, + "loss": 0.0076, + "step": 36013 + }, + { + "epoch": 11.12, + "learning_rate": 8.672366656742837e-06, + "loss": 0.0107, + "step": 36014 + }, + { + "epoch": 11.12, + "learning_rate": 8.671870967341225e-06, + "loss": 0.0087, + "step": 36015 + }, + { + "epoch": 11.12, + "learning_rate": 8.671375281261511e-06, + "loss": 0.0088, + "step": 36016 + }, + { + "epoch": 11.12, + "learning_rate": 8.670879598504928e-06, + "loss": 0.0079, + "step": 36017 + }, + { + "epoch": 11.12, + "learning_rate": 8.670383919072714e-06, + "loss": 0.0079, + "step": 36018 + }, + { + "epoch": 11.12, + "learning_rate": 8.669888242966116e-06, + "loss": 0.0077, + "step": 36019 + }, + { + "epoch": 11.12, + "learning_rate": 8.66939257018637e-06, + "loss": 0.0087, + "step": 36020 + }, + { + "epoch": 11.12, + "learning_rate": 8.668896900734716e-06, + "loss": 0.0069, + "step": 36021 + }, + { + "epoch": 11.12, + "learning_rate": 8.66840123461239e-06, + "loss": 0.0084, + "step": 36022 + }, + { + "epoch": 11.12, + "learning_rate": 8.66790557182064e-06, + "loss": 0.0115, + "step": 36023 + }, + { + "epoch": 11.12, + "learning_rate": 8.667409912360701e-06, + "loss": 0.0083, + "step": 36024 + }, + { + "epoch": 11.13, + "learning_rate": 8.666914256233807e-06, + "loss": 0.0081, + "step": 36025 + }, + { + "epoch": 11.13, + "learning_rate": 8.66641860344121e-06, + "loss": 0.009, + "step": 36026 + }, + { + "epoch": 11.13, + "learning_rate": 8.665922953984141e-06, + "loss": 0.0101, + "step": 36027 + }, + { + "epoch": 11.13, + "learning_rate": 8.66542730786384e-06, + "loss": 0.009, + "step": 36028 + }, + { + "epoch": 11.13, + "learning_rate": 8.664931665081555e-06, + "loss": 0.0083, + "step": 36029 + }, + { + "epoch": 11.13, + "learning_rate": 8.664436025638513e-06, + "loss": 0.0068, + "step": 36030 + }, + { + "epoch": 11.13, + "learning_rate": 8.663940389535963e-06, + "loss": 0.0098, + "step": 36031 + }, + { + "epoch": 11.13, + "learning_rate": 8.663444756775142e-06, + "loss": 0.0086, + "step": 36032 + }, + { + "epoch": 11.13, + "learning_rate": 8.662949127357288e-06, + "loss": 0.0087, + "step": 36033 + }, + { + "epoch": 11.13, + "learning_rate": 8.662453501283641e-06, + "loss": 0.0079, + "step": 36034 + }, + { + "epoch": 11.13, + "learning_rate": 8.661957878555446e-06, + "loss": 0.0083, + "step": 36035 + }, + { + "epoch": 11.13, + "learning_rate": 8.661462259173933e-06, + "loss": 0.0083, + "step": 36036 + }, + { + "epoch": 11.13, + "learning_rate": 8.660966643140349e-06, + "loss": 0.0086, + "step": 36037 + }, + { + "epoch": 11.13, + "learning_rate": 8.660471030455935e-06, + "loss": 0.0098, + "step": 36038 + }, + { + "epoch": 11.13, + "learning_rate": 8.659975421121925e-06, + "loss": 0.0089, + "step": 36039 + }, + { + "epoch": 11.13, + "learning_rate": 8.659479815139558e-06, + "loss": 0.0079, + "step": 36040 + }, + { + "epoch": 11.13, + "learning_rate": 8.658984212510083e-06, + "loss": 0.0091, + "step": 36041 + }, + { + "epoch": 11.13, + "learning_rate": 8.658488613234728e-06, + "loss": 0.0083, + "step": 36042 + }, + { + "epoch": 11.13, + "learning_rate": 8.657993017314736e-06, + "loss": 0.0096, + "step": 36043 + }, + { + "epoch": 11.13, + "learning_rate": 8.657497424751353e-06, + "loss": 0.0102, + "step": 36044 + }, + { + "epoch": 11.13, + "learning_rate": 8.657001835545811e-06, + "loss": 0.0087, + "step": 36045 + }, + { + "epoch": 11.13, + "learning_rate": 8.656506249699352e-06, + "loss": 0.0092, + "step": 36046 + }, + { + "epoch": 11.13, + "learning_rate": 8.656010667213218e-06, + "loss": 0.0087, + "step": 36047 + }, + { + "epoch": 11.13, + "learning_rate": 8.655515088088646e-06, + "loss": 0.0086, + "step": 36048 + }, + { + "epoch": 11.13, + "learning_rate": 8.655019512326875e-06, + "loss": 0.0073, + "step": 36049 + }, + { + "epoch": 11.13, + "learning_rate": 8.654523939929147e-06, + "loss": 0.0107, + "step": 36050 + }, + { + "epoch": 11.13, + "learning_rate": 8.654028370896699e-06, + "loss": 0.0089, + "step": 36051 + }, + { + "epoch": 11.13, + "learning_rate": 8.65353280523077e-06, + "loss": 0.0102, + "step": 36052 + }, + { + "epoch": 11.13, + "learning_rate": 8.6530372429326e-06, + "loss": 0.0093, + "step": 36053 + }, + { + "epoch": 11.13, + "learning_rate": 8.652541684003434e-06, + "loss": 0.0086, + "step": 36054 + }, + { + "epoch": 11.13, + "learning_rate": 8.652046128444507e-06, + "loss": 0.0086, + "step": 36055 + }, + { + "epoch": 11.13, + "learning_rate": 8.651550576257053e-06, + "loss": 0.0085, + "step": 36056 + }, + { + "epoch": 11.14, + "learning_rate": 8.651055027442324e-06, + "loss": 0.0093, + "step": 36057 + }, + { + "epoch": 11.14, + "learning_rate": 8.650559482001548e-06, + "loss": 0.0073, + "step": 36058 + }, + { + "epoch": 11.14, + "learning_rate": 8.650063939935967e-06, + "loss": 0.0097, + "step": 36059 + }, + { + "epoch": 11.14, + "learning_rate": 8.64956840124683e-06, + "loss": 0.0101, + "step": 36060 + }, + { + "epoch": 11.14, + "learning_rate": 8.649072865935362e-06, + "loss": 0.0083, + "step": 36061 + }, + { + "epoch": 11.14, + "learning_rate": 8.64857733400281e-06, + "loss": 0.0097, + "step": 36062 + }, + { + "epoch": 11.14, + "learning_rate": 8.648081805450417e-06, + "loss": 0.0088, + "step": 36063 + }, + { + "epoch": 11.14, + "learning_rate": 8.647586280279413e-06, + "loss": 0.0088, + "step": 36064 + }, + { + "epoch": 11.14, + "learning_rate": 8.647090758491043e-06, + "loss": 0.0069, + "step": 36065 + }, + { + "epoch": 11.14, + "learning_rate": 8.646595240086548e-06, + "loss": 0.0079, + "step": 36066 + }, + { + "epoch": 11.14, + "learning_rate": 8.646099725067161e-06, + "loss": 0.0089, + "step": 36067 + }, + { + "epoch": 11.14, + "learning_rate": 8.645604213434129e-06, + "loss": 0.0092, + "step": 36068 + }, + { + "epoch": 11.14, + "learning_rate": 8.64510870518869e-06, + "loss": 0.0075, + "step": 36069 + }, + { + "epoch": 11.14, + "learning_rate": 8.644613200332077e-06, + "loss": 0.0076, + "step": 36070 + }, + { + "epoch": 11.14, + "learning_rate": 8.644117698865533e-06, + "loss": 0.0085, + "step": 36071 + }, + { + "epoch": 11.14, + "learning_rate": 8.643622200790302e-06, + "loss": 0.0091, + "step": 36072 + }, + { + "epoch": 11.14, + "learning_rate": 8.643126706107618e-06, + "loss": 0.0086, + "step": 36073 + }, + { + "epoch": 11.14, + "learning_rate": 8.642631214818718e-06, + "loss": 0.0078, + "step": 36074 + }, + { + "epoch": 11.14, + "learning_rate": 8.64213572692485e-06, + "loss": 0.0087, + "step": 36075 + }, + { + "epoch": 11.14, + "learning_rate": 8.641640242427246e-06, + "loss": 0.0097, + "step": 36076 + }, + { + "epoch": 11.14, + "learning_rate": 8.641144761327145e-06, + "loss": 0.0086, + "step": 36077 + }, + { + "epoch": 11.14, + "learning_rate": 8.640649283625796e-06, + "loss": 0.0069, + "step": 36078 + }, + { + "epoch": 11.14, + "learning_rate": 8.640153809324425e-06, + "loss": 0.0089, + "step": 36079 + }, + { + "epoch": 11.14, + "learning_rate": 8.639658338424277e-06, + "loss": 0.0096, + "step": 36080 + }, + { + "epoch": 11.14, + "learning_rate": 8.639162870926596e-06, + "loss": 0.0075, + "step": 36081 + }, + { + "epoch": 11.14, + "learning_rate": 8.638667406832612e-06, + "loss": 0.0111, + "step": 36082 + }, + { + "epoch": 11.14, + "learning_rate": 8.638171946143571e-06, + "loss": 0.0075, + "step": 36083 + }, + { + "epoch": 11.14, + "learning_rate": 8.63767648886071e-06, + "loss": 0.0074, + "step": 36084 + }, + { + "epoch": 11.14, + "learning_rate": 8.637181034985268e-06, + "loss": 0.0083, + "step": 36085 + }, + { + "epoch": 11.14, + "learning_rate": 8.636685584518488e-06, + "loss": 0.0073, + "step": 36086 + }, + { + "epoch": 11.14, + "learning_rate": 8.636190137461602e-06, + "loss": 0.0097, + "step": 36087 + }, + { + "epoch": 11.14, + "learning_rate": 8.635694693815859e-06, + "loss": 0.0078, + "step": 36088 + }, + { + "epoch": 11.14, + "learning_rate": 8.635199253582486e-06, + "loss": 0.009, + "step": 36089 + }, + { + "epoch": 11.15, + "learning_rate": 8.634703816762731e-06, + "loss": 0.0086, + "step": 36090 + }, + { + "epoch": 11.15, + "learning_rate": 8.634208383357833e-06, + "loss": 0.0079, + "step": 36091 + }, + { + "epoch": 11.15, + "learning_rate": 8.633712953369024e-06, + "loss": 0.0076, + "step": 36092 + }, + { + "epoch": 11.15, + "learning_rate": 8.633217526797551e-06, + "loss": 0.0078, + "step": 36093 + }, + { + "epoch": 11.15, + "learning_rate": 8.632722103644654e-06, + "loss": 0.0078, + "step": 36094 + }, + { + "epoch": 11.15, + "learning_rate": 8.632226683911562e-06, + "loss": 0.0082, + "step": 36095 + }, + { + "epoch": 11.15, + "learning_rate": 8.631731267599523e-06, + "loss": 0.0089, + "step": 36096 + }, + { + "epoch": 11.15, + "learning_rate": 8.631235854709777e-06, + "loss": 0.0102, + "step": 36097 + }, + { + "epoch": 11.15, + "learning_rate": 8.630740445243553e-06, + "loss": 0.0083, + "step": 36098 + }, + { + "epoch": 11.15, + "learning_rate": 8.630245039202102e-06, + "loss": 0.0076, + "step": 36099 + }, + { + "epoch": 11.15, + "learning_rate": 8.629749636586656e-06, + "loss": 0.0088, + "step": 36100 + }, + { + "epoch": 11.15, + "learning_rate": 8.629254237398457e-06, + "loss": 0.0083, + "step": 36101 + }, + { + "epoch": 11.15, + "learning_rate": 8.62875884163874e-06, + "loss": 0.0091, + "step": 36102 + }, + { + "epoch": 11.15, + "learning_rate": 8.628263449308754e-06, + "loss": 0.0083, + "step": 36103 + }, + { + "epoch": 11.15, + "learning_rate": 8.627768060409725e-06, + "loss": 0.0081, + "step": 36104 + }, + { + "epoch": 11.15, + "learning_rate": 8.6272726749429e-06, + "loss": 0.008, + "step": 36105 + }, + { + "epoch": 11.15, + "learning_rate": 8.626777292909518e-06, + "loss": 0.0084, + "step": 36106 + }, + { + "epoch": 11.15, + "learning_rate": 8.626281914310816e-06, + "loss": 0.008, + "step": 36107 + }, + { + "epoch": 11.15, + "learning_rate": 8.625786539148031e-06, + "loss": 0.007, + "step": 36108 + }, + { + "epoch": 11.15, + "learning_rate": 8.62529116742241e-06, + "loss": 0.0086, + "step": 36109 + }, + { + "epoch": 11.15, + "learning_rate": 8.624795799135181e-06, + "loss": 0.0081, + "step": 36110 + }, + { + "epoch": 11.15, + "learning_rate": 8.62430043428759e-06, + "loss": 0.0097, + "step": 36111 + }, + { + "epoch": 11.15, + "learning_rate": 8.623805072880877e-06, + "loss": 0.0086, + "step": 36112 + }, + { + "epoch": 11.15, + "learning_rate": 8.623309714916274e-06, + "loss": 0.008, + "step": 36113 + }, + { + "epoch": 11.15, + "learning_rate": 8.622814360395028e-06, + "loss": 0.0092, + "step": 36114 + }, + { + "epoch": 11.15, + "learning_rate": 8.622319009318376e-06, + "loss": 0.0094, + "step": 36115 + }, + { + "epoch": 11.15, + "learning_rate": 8.62182366168755e-06, + "loss": 0.0074, + "step": 36116 + }, + { + "epoch": 11.15, + "learning_rate": 8.621328317503798e-06, + "loss": 0.0092, + "step": 36117 + }, + { + "epoch": 11.15, + "learning_rate": 8.620832976768352e-06, + "loss": 0.0066, + "step": 36118 + }, + { + "epoch": 11.15, + "learning_rate": 8.62033763948246e-06, + "loss": 0.0083, + "step": 36119 + }, + { + "epoch": 11.15, + "learning_rate": 8.619842305647351e-06, + "loss": 0.0094, + "step": 36120 + }, + { + "epoch": 11.15, + "learning_rate": 8.619346975264269e-06, + "loss": 0.008, + "step": 36121 + }, + { + "epoch": 11.16, + "learning_rate": 8.618851648334455e-06, + "loss": 0.0093, + "step": 36122 + }, + { + "epoch": 11.16, + "learning_rate": 8.61835632485914e-06, + "loss": 0.0092, + "step": 36123 + }, + { + "epoch": 11.16, + "learning_rate": 8.61786100483957e-06, + "loss": 0.0081, + "step": 36124 + }, + { + "epoch": 11.16, + "learning_rate": 8.617365688276983e-06, + "loss": 0.0094, + "step": 36125 + }, + { + "epoch": 11.16, + "learning_rate": 8.616870375172614e-06, + "loss": 0.0084, + "step": 36126 + }, + { + "epoch": 11.16, + "learning_rate": 8.616375065527705e-06, + "loss": 0.0079, + "step": 36127 + }, + { + "epoch": 11.16, + "learning_rate": 8.615879759343498e-06, + "loss": 0.0078, + "step": 36128 + }, + { + "epoch": 11.16, + "learning_rate": 8.615384456621223e-06, + "loss": 0.0081, + "step": 36129 + }, + { + "epoch": 11.16, + "learning_rate": 8.614889157362126e-06, + "loss": 0.008, + "step": 36130 + }, + { + "epoch": 11.16, + "learning_rate": 8.614393861567446e-06, + "loss": 0.0087, + "step": 36131 + }, + { + "epoch": 11.16, + "learning_rate": 8.613898569238418e-06, + "loss": 0.011, + "step": 36132 + }, + { + "epoch": 11.16, + "learning_rate": 8.613403280376279e-06, + "loss": 0.0068, + "step": 36133 + }, + { + "epoch": 11.16, + "learning_rate": 8.612907994982277e-06, + "loss": 0.0089, + "step": 36134 + }, + { + "epoch": 11.16, + "learning_rate": 8.612412713057643e-06, + "loss": 0.008, + "step": 36135 + }, + { + "epoch": 11.16, + "learning_rate": 8.611917434603614e-06, + "loss": 0.008, + "step": 36136 + }, + { + "epoch": 11.16, + "learning_rate": 8.61142215962144e-06, + "loss": 0.0086, + "step": 36137 + }, + { + "epoch": 11.16, + "learning_rate": 8.610926888112348e-06, + "loss": 0.0074, + "step": 36138 + }, + { + "epoch": 11.16, + "learning_rate": 8.610431620077582e-06, + "loss": 0.0092, + "step": 36139 + }, + { + "epoch": 11.16, + "learning_rate": 8.609936355518382e-06, + "loss": 0.0104, + "step": 36140 + }, + { + "epoch": 11.16, + "learning_rate": 8.60944109443598e-06, + "loss": 0.0079, + "step": 36141 + }, + { + "epoch": 11.16, + "learning_rate": 8.608945836831621e-06, + "loss": 0.0108, + "step": 36142 + }, + { + "epoch": 11.16, + "learning_rate": 8.608450582706547e-06, + "loss": 0.0107, + "step": 36143 + }, + { + "epoch": 11.16, + "learning_rate": 8.607955332061984e-06, + "loss": 0.0077, + "step": 36144 + }, + { + "epoch": 11.16, + "learning_rate": 8.607460084899184e-06, + "loss": 0.0079, + "step": 36145 + }, + { + "epoch": 11.16, + "learning_rate": 8.606964841219381e-06, + "loss": 0.009, + "step": 36146 + }, + { + "epoch": 11.16, + "learning_rate": 8.606469601023808e-06, + "loss": 0.0088, + "step": 36147 + }, + { + "epoch": 11.16, + "learning_rate": 8.605974364313711e-06, + "loss": 0.0094, + "step": 36148 + }, + { + "epoch": 11.16, + "learning_rate": 8.605479131090329e-06, + "loss": 0.0106, + "step": 36149 + }, + { + "epoch": 11.16, + "learning_rate": 8.604983901354898e-06, + "loss": 0.0073, + "step": 36150 + }, + { + "epoch": 11.16, + "learning_rate": 8.604488675108652e-06, + "loss": 0.0079, + "step": 36151 + }, + { + "epoch": 11.16, + "learning_rate": 8.603993452352836e-06, + "loss": 0.0085, + "step": 36152 + }, + { + "epoch": 11.16, + "learning_rate": 8.60349823308869e-06, + "loss": 0.007, + "step": 36153 + }, + { + "epoch": 11.17, + "learning_rate": 8.603003017317447e-06, + "loss": 0.0096, + "step": 36154 + }, + { + "epoch": 11.17, + "learning_rate": 8.602507805040349e-06, + "loss": 0.0093, + "step": 36155 + }, + { + "epoch": 11.17, + "learning_rate": 8.602012596258636e-06, + "loss": 0.0095, + "step": 36156 + }, + { + "epoch": 11.17, + "learning_rate": 8.60151739097354e-06, + "loss": 0.0088, + "step": 36157 + }, + { + "epoch": 11.17, + "learning_rate": 8.601022189186306e-06, + "loss": 0.0088, + "step": 36158 + }, + { + "epoch": 11.17, + "learning_rate": 8.600526990898172e-06, + "loss": 0.0082, + "step": 36159 + }, + { + "epoch": 11.17, + "learning_rate": 8.600031796110376e-06, + "loss": 0.0094, + "step": 36160 + }, + { + "epoch": 11.17, + "learning_rate": 8.599536604824152e-06, + "loss": 0.0093, + "step": 36161 + }, + { + "epoch": 11.17, + "learning_rate": 8.599041417040745e-06, + "loss": 0.0073, + "step": 36162 + }, + { + "epoch": 11.17, + "learning_rate": 8.598546232761391e-06, + "loss": 0.0109, + "step": 36163 + }, + { + "epoch": 11.17, + "learning_rate": 8.598051051987326e-06, + "loss": 0.0087, + "step": 36164 + }, + { + "epoch": 11.17, + "learning_rate": 8.597555874719795e-06, + "loss": 0.0102, + "step": 36165 + }, + { + "epoch": 11.17, + "learning_rate": 8.59706070096003e-06, + "loss": 0.0065, + "step": 36166 + }, + { + "epoch": 11.17, + "learning_rate": 8.596565530709272e-06, + "loss": 0.0082, + "step": 36167 + }, + { + "epoch": 11.17, + "learning_rate": 8.596070363968763e-06, + "loss": 0.0089, + "step": 36168 + }, + { + "epoch": 11.17, + "learning_rate": 8.595575200739734e-06, + "loss": 0.0083, + "step": 36169 + }, + { + "epoch": 11.17, + "learning_rate": 8.595080041023427e-06, + "loss": 0.0073, + "step": 36170 + }, + { + "epoch": 11.17, + "learning_rate": 8.594584884821086e-06, + "loss": 0.009, + "step": 36171 + }, + { + "epoch": 11.17, + "learning_rate": 8.594089732133939e-06, + "loss": 0.0081, + "step": 36172 + }, + { + "epoch": 11.17, + "learning_rate": 8.593594582963232e-06, + "loss": 0.0082, + "step": 36173 + }, + { + "epoch": 11.17, + "learning_rate": 8.593099437310203e-06, + "loss": 0.0088, + "step": 36174 + }, + { + "epoch": 11.17, + "learning_rate": 8.592604295176087e-06, + "loss": 0.0078, + "step": 36175 + }, + { + "epoch": 11.17, + "learning_rate": 8.592109156562126e-06, + "loss": 0.0084, + "step": 36176 + }, + { + "epoch": 11.17, + "learning_rate": 8.591614021469557e-06, + "loss": 0.0093, + "step": 36177 + }, + { + "epoch": 11.17, + "learning_rate": 8.591118889899617e-06, + "loss": 0.0086, + "step": 36178 + }, + { + "epoch": 11.17, + "learning_rate": 8.590623761853542e-06, + "loss": 0.0077, + "step": 36179 + }, + { + "epoch": 11.17, + "learning_rate": 8.590128637332581e-06, + "loss": 0.0075, + "step": 36180 + }, + { + "epoch": 11.17, + "learning_rate": 8.589633516337963e-06, + "loss": 0.0071, + "step": 36181 + }, + { + "epoch": 11.17, + "learning_rate": 8.589138398870925e-06, + "loss": 0.008, + "step": 36182 + }, + { + "epoch": 11.17, + "learning_rate": 8.588643284932712e-06, + "loss": 0.0125, + "step": 36183 + }, + { + "epoch": 11.17, + "learning_rate": 8.588148174524562e-06, + "loss": 0.0097, + "step": 36184 + }, + { + "epoch": 11.17, + "learning_rate": 8.587653067647706e-06, + "loss": 0.0104, + "step": 36185 + }, + { + "epoch": 11.17, + "learning_rate": 8.58715796430339e-06, + "loss": 0.0097, + "step": 36186 + }, + { + "epoch": 11.18, + "learning_rate": 8.586662864492852e-06, + "loss": 0.0086, + "step": 36187 + }, + { + "epoch": 11.18, + "learning_rate": 8.586167768217325e-06, + "loss": 0.0081, + "step": 36188 + }, + { + "epoch": 11.18, + "learning_rate": 8.585672675478048e-06, + "loss": 0.0095, + "step": 36189 + }, + { + "epoch": 11.18, + "learning_rate": 8.585177586276268e-06, + "loss": 0.0086, + "step": 36190 + }, + { + "epoch": 11.18, + "learning_rate": 8.584682500613213e-06, + "loss": 0.0081, + "step": 36191 + }, + { + "epoch": 11.18, + "learning_rate": 8.584187418490122e-06, + "loss": 0.0091, + "step": 36192 + }, + { + "epoch": 11.18, + "learning_rate": 8.583692339908242e-06, + "loss": 0.0084, + "step": 36193 + }, + { + "epoch": 11.18, + "learning_rate": 8.583197264868805e-06, + "loss": 0.0086, + "step": 36194 + }, + { + "epoch": 11.18, + "learning_rate": 8.582702193373047e-06, + "loss": 0.0094, + "step": 36195 + }, + { + "epoch": 11.18, + "learning_rate": 8.582207125422211e-06, + "loss": 0.0095, + "step": 36196 + }, + { + "epoch": 11.18, + "learning_rate": 8.581712061017534e-06, + "loss": 0.0082, + "step": 36197 + }, + { + "epoch": 11.18, + "learning_rate": 8.581217000160253e-06, + "loss": 0.0098, + "step": 36198 + }, + { + "epoch": 11.18, + "learning_rate": 8.580721942851611e-06, + "loss": 0.0109, + "step": 36199 + }, + { + "epoch": 11.18, + "learning_rate": 8.580226889092837e-06, + "loss": 0.009, + "step": 36200 + }, + { + "epoch": 11.18, + "learning_rate": 8.579731838885176e-06, + "loss": 0.0089, + "step": 36201 + }, + { + "epoch": 11.18, + "learning_rate": 8.579236792229867e-06, + "loss": 0.0082, + "step": 36202 + }, + { + "epoch": 11.18, + "learning_rate": 8.578741749128141e-06, + "loss": 0.0089, + "step": 36203 + }, + { + "epoch": 11.18, + "learning_rate": 8.578246709581244e-06, + "loss": 0.008, + "step": 36204 + }, + { + "epoch": 11.18, + "learning_rate": 8.577751673590414e-06, + "loss": 0.0094, + "step": 36205 + }, + { + "epoch": 11.18, + "learning_rate": 8.577256641156881e-06, + "loss": 0.0087, + "step": 36206 + }, + { + "epoch": 11.18, + "learning_rate": 8.576761612281892e-06, + "loss": 0.0079, + "step": 36207 + }, + { + "epoch": 11.18, + "learning_rate": 8.576266586966683e-06, + "loss": 0.0093, + "step": 36208 + }, + { + "epoch": 11.18, + "learning_rate": 8.57577156521249e-06, + "loss": 0.0087, + "step": 36209 + }, + { + "epoch": 11.18, + "learning_rate": 8.575276547020549e-06, + "loss": 0.0097, + "step": 36210 + }, + { + "epoch": 11.18, + "learning_rate": 8.574781532392104e-06, + "loss": 0.0091, + "step": 36211 + }, + { + "epoch": 11.18, + "learning_rate": 8.57428652132839e-06, + "loss": 0.009, + "step": 36212 + }, + { + "epoch": 11.18, + "learning_rate": 8.573791513830645e-06, + "loss": 0.009, + "step": 36213 + }, + { + "epoch": 11.18, + "learning_rate": 8.57329650990011e-06, + "loss": 0.0083, + "step": 36214 + }, + { + "epoch": 11.18, + "learning_rate": 8.572801509538017e-06, + "loss": 0.0119, + "step": 36215 + }, + { + "epoch": 11.18, + "learning_rate": 8.572306512745607e-06, + "loss": 0.0072, + "step": 36216 + }, + { + "epoch": 11.18, + "learning_rate": 8.571811519524121e-06, + "loss": 0.0088, + "step": 36217 + }, + { + "epoch": 11.18, + "learning_rate": 8.571316529874795e-06, + "loss": 0.0101, + "step": 36218 + }, + { + "epoch": 11.19, + "learning_rate": 8.570821543798869e-06, + "loss": 0.0103, + "step": 36219 + }, + { + "epoch": 11.19, + "learning_rate": 8.570326561297575e-06, + "loss": 0.0088, + "step": 36220 + }, + { + "epoch": 11.19, + "learning_rate": 8.569831582372158e-06, + "loss": 0.0092, + "step": 36221 + }, + { + "epoch": 11.19, + "learning_rate": 8.569336607023852e-06, + "loss": 0.0085, + "step": 36222 + }, + { + "epoch": 11.19, + "learning_rate": 8.568841635253893e-06, + "loss": 0.0086, + "step": 36223 + }, + { + "epoch": 11.19, + "learning_rate": 8.568346667063528e-06, + "loss": 0.0099, + "step": 36224 + }, + { + "epoch": 11.19, + "learning_rate": 8.567851702453985e-06, + "loss": 0.0075, + "step": 36225 + }, + { + "epoch": 11.19, + "learning_rate": 8.567356741426504e-06, + "loss": 0.0096, + "step": 36226 + }, + { + "epoch": 11.19, + "learning_rate": 8.566861783982335e-06, + "loss": 0.0101, + "step": 36227 + }, + { + "epoch": 11.19, + "learning_rate": 8.566366830122697e-06, + "loss": 0.0076, + "step": 36228 + }, + { + "epoch": 11.19, + "learning_rate": 8.565871879848838e-06, + "loss": 0.008, + "step": 36229 + }, + { + "epoch": 11.19, + "learning_rate": 8.565376933161999e-06, + "loss": 0.008, + "step": 36230 + }, + { + "epoch": 11.19, + "learning_rate": 8.56488199006341e-06, + "loss": 0.0096, + "step": 36231 + }, + { + "epoch": 11.19, + "learning_rate": 8.564387050554313e-06, + "loss": 0.0091, + "step": 36232 + }, + { + "epoch": 11.19, + "learning_rate": 8.56389211463595e-06, + "loss": 0.0104, + "step": 36233 + }, + { + "epoch": 11.19, + "learning_rate": 8.56339718230955e-06, + "loss": 0.0098, + "step": 36234 + }, + { + "epoch": 11.19, + "learning_rate": 8.562902253576356e-06, + "loss": 0.0089, + "step": 36235 + }, + { + "epoch": 11.19, + "learning_rate": 8.56240732843761e-06, + "loss": 0.0087, + "step": 36236 + }, + { + "epoch": 11.19, + "learning_rate": 8.561912406894541e-06, + "loss": 0.0083, + "step": 36237 + }, + { + "epoch": 11.19, + "learning_rate": 8.561417488948392e-06, + "loss": 0.0089, + "step": 36238 + }, + { + "epoch": 11.19, + "learning_rate": 8.560922574600404e-06, + "loss": 0.0086, + "step": 36239 + }, + { + "epoch": 11.19, + "learning_rate": 8.560427663851807e-06, + "loss": 0.0094, + "step": 36240 + }, + { + "epoch": 11.19, + "learning_rate": 8.559932756703841e-06, + "loss": 0.0076, + "step": 36241 + }, + { + "epoch": 11.19, + "learning_rate": 8.559437853157752e-06, + "loss": 0.0091, + "step": 36242 + }, + { + "epoch": 11.19, + "learning_rate": 8.558942953214768e-06, + "loss": 0.0079, + "step": 36243 + }, + { + "epoch": 11.19, + "learning_rate": 8.55844805687613e-06, + "loss": 0.0079, + "step": 36244 + }, + { + "epoch": 11.19, + "learning_rate": 8.55795316414308e-06, + "loss": 0.0071, + "step": 36245 + }, + { + "epoch": 11.19, + "learning_rate": 8.557458275016849e-06, + "loss": 0.009, + "step": 36246 + }, + { + "epoch": 11.19, + "learning_rate": 8.556963389498678e-06, + "loss": 0.0098, + "step": 36247 + }, + { + "epoch": 11.19, + "learning_rate": 8.556468507589804e-06, + "loss": 0.0097, + "step": 36248 + }, + { + "epoch": 11.19, + "learning_rate": 8.55597362929147e-06, + "loss": 0.0088, + "step": 36249 + }, + { + "epoch": 11.19, + "learning_rate": 8.555478754604906e-06, + "loss": 0.009, + "step": 36250 + }, + { + "epoch": 11.2, + "learning_rate": 8.55498388353135e-06, + "loss": 0.0099, + "step": 36251 + }, + { + "epoch": 11.2, + "learning_rate": 8.55448901607205e-06, + "loss": 0.012, + "step": 36252 + }, + { + "epoch": 11.2, + "learning_rate": 8.553994152228231e-06, + "loss": 0.009, + "step": 36253 + }, + { + "epoch": 11.2, + "learning_rate": 8.553499292001137e-06, + "loss": 0.0098, + "step": 36254 + }, + { + "epoch": 11.2, + "learning_rate": 8.553004435392008e-06, + "loss": 0.0097, + "step": 36255 + }, + { + "epoch": 11.2, + "learning_rate": 8.552509582402078e-06, + "loss": 0.0096, + "step": 36256 + }, + { + "epoch": 11.2, + "learning_rate": 8.552014733032584e-06, + "loss": 0.0095, + "step": 36257 + }, + { + "epoch": 11.2, + "learning_rate": 8.551519887284767e-06, + "loss": 0.0077, + "step": 36258 + }, + { + "epoch": 11.2, + "learning_rate": 8.551025045159861e-06, + "loss": 0.0075, + "step": 36259 + }, + { + "epoch": 11.2, + "learning_rate": 8.550530206659106e-06, + "loss": 0.0071, + "step": 36260 + }, + { + "epoch": 11.2, + "learning_rate": 8.550035371783742e-06, + "loss": 0.0076, + "step": 36261 + }, + { + "epoch": 11.2, + "learning_rate": 8.549540540535e-06, + "loss": 0.0089, + "step": 36262 + }, + { + "epoch": 11.2, + "learning_rate": 8.549045712914123e-06, + "loss": 0.0085, + "step": 36263 + }, + { + "epoch": 11.2, + "learning_rate": 8.54855088892235e-06, + "loss": 0.0088, + "step": 36264 + }, + { + "epoch": 11.2, + "learning_rate": 8.548056068560912e-06, + "loss": 0.0094, + "step": 36265 + }, + { + "epoch": 11.2, + "learning_rate": 8.547561251831051e-06, + "loss": 0.013, + "step": 36266 + }, + { + "epoch": 11.2, + "learning_rate": 8.547066438734009e-06, + "loss": 0.0083, + "step": 36267 + }, + { + "epoch": 11.2, + "learning_rate": 8.546571629271015e-06, + "loss": 0.0074, + "step": 36268 + }, + { + "epoch": 11.2, + "learning_rate": 8.546076823443307e-06, + "loss": 0.013, + "step": 36269 + }, + { + "epoch": 11.2, + "learning_rate": 8.545582021252134e-06, + "loss": 0.008, + "step": 36270 + }, + { + "epoch": 11.2, + "learning_rate": 8.545087222698721e-06, + "loss": 0.0083, + "step": 36271 + }, + { + "epoch": 11.2, + "learning_rate": 8.544592427784308e-06, + "loss": 0.0099, + "step": 36272 + }, + { + "epoch": 11.2, + "learning_rate": 8.54409763651014e-06, + "loss": 0.0082, + "step": 36273 + }, + { + "epoch": 11.2, + "learning_rate": 8.543602848877447e-06, + "loss": 0.0097, + "step": 36274 + }, + { + "epoch": 11.2, + "learning_rate": 8.543108064887467e-06, + "loss": 0.0093, + "step": 36275 + }, + { + "epoch": 11.2, + "learning_rate": 8.542613284541446e-06, + "loss": 0.0093, + "step": 36276 + }, + { + "epoch": 11.2, + "learning_rate": 8.542118507840606e-06, + "loss": 0.0094, + "step": 36277 + }, + { + "epoch": 11.2, + "learning_rate": 8.541623734786199e-06, + "loss": 0.0091, + "step": 36278 + }, + { + "epoch": 11.2, + "learning_rate": 8.541128965379457e-06, + "loss": 0.0073, + "step": 36279 + }, + { + "epoch": 11.2, + "learning_rate": 8.540634199621614e-06, + "loss": 0.0098, + "step": 36280 + }, + { + "epoch": 11.2, + "learning_rate": 8.540139437513913e-06, + "loss": 0.0093, + "step": 36281 + }, + { + "epoch": 11.2, + "learning_rate": 8.539644679057588e-06, + "loss": 0.009, + "step": 36282 + }, + { + "epoch": 11.2, + "learning_rate": 8.539149924253882e-06, + "loss": 0.0094, + "step": 36283 + }, + { + "epoch": 11.21, + "learning_rate": 8.538655173104028e-06, + "loss": 0.0099, + "step": 36284 + }, + { + "epoch": 11.21, + "learning_rate": 8.53816042560926e-06, + "loss": 0.0104, + "step": 36285 + }, + { + "epoch": 11.21, + "learning_rate": 8.537665681770824e-06, + "loss": 0.009, + "step": 36286 + }, + { + "epoch": 11.21, + "learning_rate": 8.537170941589949e-06, + "loss": 0.009, + "step": 36287 + }, + { + "epoch": 11.21, + "learning_rate": 8.536676205067878e-06, + "loss": 0.0086, + "step": 36288 + }, + { + "epoch": 11.21, + "learning_rate": 8.53618147220585e-06, + "loss": 0.0085, + "step": 36289 + }, + { + "epoch": 11.21, + "learning_rate": 8.53568674300509e-06, + "loss": 0.0092, + "step": 36290 + }, + { + "epoch": 11.21, + "learning_rate": 8.535192017466852e-06, + "loss": 0.0093, + "step": 36291 + }, + { + "epoch": 11.21, + "learning_rate": 8.534697295592367e-06, + "loss": 0.009, + "step": 36292 + }, + { + "epoch": 11.21, + "learning_rate": 8.534202577382866e-06, + "loss": 0.0078, + "step": 36293 + }, + { + "epoch": 11.21, + "learning_rate": 8.533707862839594e-06, + "loss": 0.0085, + "step": 36294 + }, + { + "epoch": 11.21, + "learning_rate": 8.533213151963788e-06, + "loss": 0.0098, + "step": 36295 + }, + { + "epoch": 11.21, + "learning_rate": 8.532718444756682e-06, + "loss": 0.0077, + "step": 36296 + }, + { + "epoch": 11.21, + "learning_rate": 8.532223741219512e-06, + "loss": 0.0076, + "step": 36297 + }, + { + "epoch": 11.21, + "learning_rate": 8.531729041353523e-06, + "loss": 0.0093, + "step": 36298 + }, + { + "epoch": 11.21, + "learning_rate": 8.531234345159945e-06, + "loss": 0.0074, + "step": 36299 + }, + { + "epoch": 11.21, + "learning_rate": 8.530739652640014e-06, + "loss": 0.0083, + "step": 36300 + }, + { + "epoch": 11.21, + "learning_rate": 8.530244963794978e-06, + "loss": 0.0093, + "step": 36301 + }, + { + "epoch": 11.21, + "learning_rate": 8.529750278626064e-06, + "loss": 0.0079, + "step": 36302 + }, + { + "epoch": 11.21, + "learning_rate": 8.529255597134511e-06, + "loss": 0.0079, + "step": 36303 + }, + { + "epoch": 11.21, + "learning_rate": 8.528760919321562e-06, + "loss": 0.0077, + "step": 36304 + }, + { + "epoch": 11.21, + "learning_rate": 8.528266245188448e-06, + "loss": 0.0095, + "step": 36305 + }, + { + "epoch": 11.21, + "learning_rate": 8.527771574736409e-06, + "loss": 0.0097, + "step": 36306 + }, + { + "epoch": 11.21, + "learning_rate": 8.527276907966685e-06, + "loss": 0.0088, + "step": 36307 + }, + { + "epoch": 11.21, + "learning_rate": 8.526782244880503e-06, + "loss": 0.008, + "step": 36308 + }, + { + "epoch": 11.21, + "learning_rate": 8.526287585479112e-06, + "loss": 0.0091, + "step": 36309 + }, + { + "epoch": 11.21, + "learning_rate": 8.525792929763745e-06, + "loss": 0.0089, + "step": 36310 + }, + { + "epoch": 11.21, + "learning_rate": 8.525298277735634e-06, + "loss": 0.0082, + "step": 36311 + }, + { + "epoch": 11.21, + "learning_rate": 8.524803629396026e-06, + "loss": 0.0129, + "step": 36312 + }, + { + "epoch": 11.21, + "learning_rate": 8.524308984746148e-06, + "loss": 0.0106, + "step": 36313 + }, + { + "epoch": 11.21, + "learning_rate": 8.523814343787249e-06, + "loss": 0.009, + "step": 36314 + }, + { + "epoch": 11.21, + "learning_rate": 8.523319706520556e-06, + "loss": 0.0088, + "step": 36315 + }, + { + "epoch": 11.22, + "learning_rate": 8.522825072947307e-06, + "loss": 0.0078, + "step": 36316 + }, + { + "epoch": 11.22, + "learning_rate": 8.52233044306875e-06, + "loss": 0.0081, + "step": 36317 + }, + { + "epoch": 11.22, + "learning_rate": 8.521835816886107e-06, + "loss": 0.0096, + "step": 36318 + }, + { + "epoch": 11.22, + "learning_rate": 8.521341194400624e-06, + "loss": 0.0081, + "step": 36319 + }, + { + "epoch": 11.22, + "learning_rate": 8.520846575613539e-06, + "loss": 0.009, + "step": 36320 + }, + { + "epoch": 11.22, + "learning_rate": 8.520351960526082e-06, + "loss": 0.009, + "step": 36321 + }, + { + "epoch": 11.22, + "learning_rate": 8.519857349139498e-06, + "loss": 0.0086, + "step": 36322 + }, + { + "epoch": 11.22, + "learning_rate": 8.519362741455021e-06, + "loss": 0.0092, + "step": 36323 + }, + { + "epoch": 11.22, + "learning_rate": 8.518868137473884e-06, + "loss": 0.008, + "step": 36324 + }, + { + "epoch": 11.22, + "learning_rate": 8.51837353719733e-06, + "loss": 0.0099, + "step": 36325 + }, + { + "epoch": 11.22, + "learning_rate": 8.517878940626596e-06, + "loss": 0.0091, + "step": 36326 + }, + { + "epoch": 11.22, + "learning_rate": 8.517384347762916e-06, + "loss": 0.0082, + "step": 36327 + }, + { + "epoch": 11.22, + "learning_rate": 8.516889758607525e-06, + "loss": 0.0076, + "step": 36328 + }, + { + "epoch": 11.22, + "learning_rate": 8.51639517316167e-06, + "loss": 0.0082, + "step": 36329 + }, + { + "epoch": 11.22, + "learning_rate": 8.515900591426575e-06, + "loss": 0.0089, + "step": 36330 + }, + { + "epoch": 11.22, + "learning_rate": 8.515406013403484e-06, + "loss": 0.01, + "step": 36331 + }, + { + "epoch": 11.22, + "learning_rate": 8.514911439093635e-06, + "loss": 0.0097, + "step": 36332 + }, + { + "epoch": 11.22, + "learning_rate": 8.514416868498265e-06, + "loss": 0.0084, + "step": 36333 + }, + { + "epoch": 11.22, + "learning_rate": 8.513922301618605e-06, + "loss": 0.0107, + "step": 36334 + }, + { + "epoch": 11.22, + "learning_rate": 8.513427738455903e-06, + "loss": 0.009, + "step": 36335 + }, + { + "epoch": 11.22, + "learning_rate": 8.512933179011382e-06, + "loss": 0.0096, + "step": 36336 + }, + { + "epoch": 11.22, + "learning_rate": 8.51243862328629e-06, + "loss": 0.0102, + "step": 36337 + }, + { + "epoch": 11.22, + "learning_rate": 8.511944071281862e-06, + "loss": 0.0113, + "step": 36338 + }, + { + "epoch": 11.22, + "learning_rate": 8.511449522999328e-06, + "loss": 0.0083, + "step": 36339 + }, + { + "epoch": 11.22, + "learning_rate": 8.510954978439934e-06, + "loss": 0.0093, + "step": 36340 + }, + { + "epoch": 11.22, + "learning_rate": 8.510460437604915e-06, + "loss": 0.0087, + "step": 36341 + }, + { + "epoch": 11.22, + "learning_rate": 8.509965900495501e-06, + "loss": 0.009, + "step": 36342 + }, + { + "epoch": 11.22, + "learning_rate": 8.509471367112937e-06, + "loss": 0.0106, + "step": 36343 + }, + { + "epoch": 11.22, + "learning_rate": 8.50897683745846e-06, + "loss": 0.0103, + "step": 36344 + }, + { + "epoch": 11.22, + "learning_rate": 8.5084823115333e-06, + "loss": 0.0085, + "step": 36345 + }, + { + "epoch": 11.22, + "learning_rate": 8.507987789338696e-06, + "loss": 0.0087, + "step": 36346 + }, + { + "epoch": 11.22, + "learning_rate": 8.507493270875889e-06, + "loss": 0.0084, + "step": 36347 + }, + { + "epoch": 11.22, + "learning_rate": 8.506998756146115e-06, + "loss": 0.0086, + "step": 36348 + }, + { + "epoch": 11.23, + "learning_rate": 8.506504245150607e-06, + "loss": 0.0103, + "step": 36349 + }, + { + "epoch": 11.23, + "learning_rate": 8.506009737890603e-06, + "loss": 0.0086, + "step": 36350 + }, + { + "epoch": 11.23, + "learning_rate": 8.505515234367346e-06, + "loss": 0.0085, + "step": 36351 + }, + { + "epoch": 11.23, + "learning_rate": 8.505020734582063e-06, + "loss": 0.0095, + "step": 36352 + }, + { + "epoch": 11.23, + "learning_rate": 8.504526238536e-06, + "loss": 0.0087, + "step": 36353 + }, + { + "epoch": 11.23, + "learning_rate": 8.504031746230389e-06, + "loss": 0.0091, + "step": 36354 + }, + { + "epoch": 11.23, + "learning_rate": 8.503537257666462e-06, + "loss": 0.0079, + "step": 36355 + }, + { + "epoch": 11.23, + "learning_rate": 8.503042772845466e-06, + "loss": 0.0086, + "step": 36356 + }, + { + "epoch": 11.23, + "learning_rate": 8.502548291768635e-06, + "loss": 0.0095, + "step": 36357 + }, + { + "epoch": 11.23, + "learning_rate": 8.502053814437203e-06, + "loss": 0.0087, + "step": 36358 + }, + { + "epoch": 11.23, + "learning_rate": 8.501559340852404e-06, + "loss": 0.0079, + "step": 36359 + }, + { + "epoch": 11.23, + "learning_rate": 8.501064871015481e-06, + "loss": 0.0102, + "step": 36360 + }, + { + "epoch": 11.23, + "learning_rate": 8.500570404927669e-06, + "loss": 0.01, + "step": 36361 + }, + { + "epoch": 11.23, + "learning_rate": 8.500075942590198e-06, + "loss": 0.0093, + "step": 36362 + }, + { + "epoch": 11.23, + "learning_rate": 8.499581484004318e-06, + "loss": 0.0104, + "step": 36363 + }, + { + "epoch": 11.23, + "learning_rate": 8.499087029171256e-06, + "loss": 0.0077, + "step": 36364 + }, + { + "epoch": 11.23, + "learning_rate": 8.498592578092248e-06, + "loss": 0.0091, + "step": 36365 + }, + { + "epoch": 11.23, + "learning_rate": 8.49809813076854e-06, + "loss": 0.0082, + "step": 36366 + }, + { + "epoch": 11.23, + "learning_rate": 8.497603687201357e-06, + "loss": 0.0098, + "step": 36367 + }, + { + "epoch": 11.23, + "learning_rate": 8.497109247391944e-06, + "loss": 0.009, + "step": 36368 + }, + { + "epoch": 11.23, + "learning_rate": 8.496614811341534e-06, + "loss": 0.007, + "step": 36369 + }, + { + "epoch": 11.23, + "learning_rate": 8.496120379051363e-06, + "loss": 0.0084, + "step": 36370 + }, + { + "epoch": 11.23, + "learning_rate": 8.495625950522671e-06, + "loss": 0.0089, + "step": 36371 + }, + { + "epoch": 11.23, + "learning_rate": 8.495131525756695e-06, + "loss": 0.0096, + "step": 36372 + }, + { + "epoch": 11.23, + "learning_rate": 8.494637104754665e-06, + "loss": 0.01, + "step": 36373 + }, + { + "epoch": 11.23, + "learning_rate": 8.494142687517823e-06, + "loss": 0.0085, + "step": 36374 + }, + { + "epoch": 11.23, + "learning_rate": 8.493648274047409e-06, + "loss": 0.0087, + "step": 36375 + }, + { + "epoch": 11.23, + "learning_rate": 8.493153864344652e-06, + "loss": 0.0083, + "step": 36376 + }, + { + "epoch": 11.23, + "learning_rate": 8.49265945841079e-06, + "loss": 0.0074, + "step": 36377 + }, + { + "epoch": 11.23, + "learning_rate": 8.492165056247064e-06, + "loss": 0.0082, + "step": 36378 + }, + { + "epoch": 11.23, + "learning_rate": 8.491670657854711e-06, + "loss": 0.0085, + "step": 36379 + }, + { + "epoch": 11.23, + "learning_rate": 8.49117626323496e-06, + "loss": 0.0083, + "step": 36380 + }, + { + "epoch": 11.24, + "learning_rate": 8.490681872389054e-06, + "loss": 0.0083, + "step": 36381 + }, + { + "epoch": 11.24, + "learning_rate": 8.49018748531823e-06, + "loss": 0.0082, + "step": 36382 + }, + { + "epoch": 11.24, + "learning_rate": 8.48969310202372e-06, + "loss": 0.0095, + "step": 36383 + }, + { + "epoch": 11.24, + "learning_rate": 8.489198722506762e-06, + "loss": 0.0082, + "step": 36384 + }, + { + "epoch": 11.24, + "learning_rate": 8.488704346768599e-06, + "loss": 0.0101, + "step": 36385 + }, + { + "epoch": 11.24, + "learning_rate": 8.488209974810458e-06, + "loss": 0.0088, + "step": 36386 + }, + { + "epoch": 11.24, + "learning_rate": 8.487715606633578e-06, + "loss": 0.0079, + "step": 36387 + }, + { + "epoch": 11.24, + "learning_rate": 8.487221242239202e-06, + "loss": 0.0083, + "step": 36388 + }, + { + "epoch": 11.24, + "learning_rate": 8.486726881628557e-06, + "loss": 0.0089, + "step": 36389 + }, + { + "epoch": 11.24, + "learning_rate": 8.486232524802884e-06, + "loss": 0.0093, + "step": 36390 + }, + { + "epoch": 11.24, + "learning_rate": 8.485738171763424e-06, + "loss": 0.009, + "step": 36391 + }, + { + "epoch": 11.24, + "learning_rate": 8.485243822511407e-06, + "loss": 0.0101, + "step": 36392 + }, + { + "epoch": 11.24, + "learning_rate": 8.484749477048067e-06, + "loss": 0.0112, + "step": 36393 + }, + { + "epoch": 11.24, + "learning_rate": 8.484255135374652e-06, + "loss": 0.0089, + "step": 36394 + }, + { + "epoch": 11.24, + "learning_rate": 8.483760797492388e-06, + "loss": 0.0081, + "step": 36395 + }, + { + "epoch": 11.24, + "learning_rate": 8.483266463402516e-06, + "loss": 0.0114, + "step": 36396 + }, + { + "epoch": 11.24, + "learning_rate": 8.48277213310627e-06, + "loss": 0.012, + "step": 36397 + }, + { + "epoch": 11.24, + "learning_rate": 8.482277806604887e-06, + "loss": 0.008, + "step": 36398 + }, + { + "epoch": 11.24, + "learning_rate": 8.481783483899603e-06, + "loss": 0.0089, + "step": 36399 + }, + { + "epoch": 11.24, + "learning_rate": 8.48128916499166e-06, + "loss": 0.0087, + "step": 36400 + }, + { + "epoch": 11.24, + "learning_rate": 8.480794849882285e-06, + "loss": 0.0082, + "step": 36401 + }, + { + "epoch": 11.24, + "learning_rate": 8.48030053857272e-06, + "loss": 0.01, + "step": 36402 + }, + { + "epoch": 11.24, + "learning_rate": 8.479806231064204e-06, + "loss": 0.0093, + "step": 36403 + }, + { + "epoch": 11.24, + "learning_rate": 8.479311927357966e-06, + "loss": 0.0104, + "step": 36404 + }, + { + "epoch": 11.24, + "learning_rate": 8.478817627455249e-06, + "loss": 0.0107, + "step": 36405 + }, + { + "epoch": 11.24, + "learning_rate": 8.478323331357286e-06, + "loss": 0.0088, + "step": 36406 + }, + { + "epoch": 11.24, + "learning_rate": 8.477829039065313e-06, + "loss": 0.0102, + "step": 36407 + }, + { + "epoch": 11.24, + "learning_rate": 8.477334750580566e-06, + "loss": 0.0105, + "step": 36408 + }, + { + "epoch": 11.24, + "learning_rate": 8.476840465904285e-06, + "loss": 0.0094, + "step": 36409 + }, + { + "epoch": 11.24, + "learning_rate": 8.476346185037705e-06, + "loss": 0.0081, + "step": 36410 + }, + { + "epoch": 11.24, + "learning_rate": 8.475851907982056e-06, + "loss": 0.0107, + "step": 36411 + }, + { + "epoch": 11.24, + "learning_rate": 8.475357634738582e-06, + "loss": 0.0089, + "step": 36412 + }, + { + "epoch": 11.25, + "learning_rate": 8.474863365308518e-06, + "loss": 0.0095, + "step": 36413 + }, + { + "epoch": 11.25, + "learning_rate": 8.474369099693096e-06, + "loss": 0.0097, + "step": 36414 + }, + { + "epoch": 11.25, + "learning_rate": 8.473874837893556e-06, + "loss": 0.0101, + "step": 36415 + }, + { + "epoch": 11.25, + "learning_rate": 8.473380579911137e-06, + "loss": 0.0088, + "step": 36416 + }, + { + "epoch": 11.25, + "learning_rate": 8.472886325747069e-06, + "loss": 0.0082, + "step": 36417 + }, + { + "epoch": 11.25, + "learning_rate": 8.472392075402589e-06, + "loss": 0.01, + "step": 36418 + }, + { + "epoch": 11.25, + "learning_rate": 8.471897828878938e-06, + "loss": 0.0093, + "step": 36419 + }, + { + "epoch": 11.25, + "learning_rate": 8.471403586177348e-06, + "loss": 0.0084, + "step": 36420 + }, + { + "epoch": 11.25, + "learning_rate": 8.470909347299055e-06, + "loss": 0.0077, + "step": 36421 + }, + { + "epoch": 11.25, + "learning_rate": 8.4704151122453e-06, + "loss": 0.0089, + "step": 36422 + }, + { + "epoch": 11.25, + "learning_rate": 8.469920881017313e-06, + "loss": 0.009, + "step": 36423 + }, + { + "epoch": 11.25, + "learning_rate": 8.469426653616331e-06, + "loss": 0.0096, + "step": 36424 + }, + { + "epoch": 11.25, + "learning_rate": 8.4689324300436e-06, + "loss": 0.0101, + "step": 36425 + }, + { + "epoch": 11.25, + "learning_rate": 8.46843821030034e-06, + "loss": 0.01, + "step": 36426 + }, + { + "epoch": 11.25, + "learning_rate": 8.467943994387798e-06, + "loss": 0.0092, + "step": 36427 + }, + { + "epoch": 11.25, + "learning_rate": 8.467449782307211e-06, + "loss": 0.0071, + "step": 36428 + }, + { + "epoch": 11.25, + "learning_rate": 8.466955574059806e-06, + "loss": 0.0098, + "step": 36429 + }, + { + "epoch": 11.25, + "learning_rate": 8.466461369646828e-06, + "loss": 0.008, + "step": 36430 + }, + { + "epoch": 11.25, + "learning_rate": 8.46596716906951e-06, + "loss": 0.0084, + "step": 36431 + }, + { + "epoch": 11.25, + "learning_rate": 8.465472972329085e-06, + "loss": 0.0104, + "step": 36432 + }, + { + "epoch": 11.25, + "learning_rate": 8.464978779426793e-06, + "loss": 0.0079, + "step": 36433 + }, + { + "epoch": 11.25, + "learning_rate": 8.464484590363873e-06, + "loss": 0.0084, + "step": 36434 + }, + { + "epoch": 11.25, + "learning_rate": 8.463990405141554e-06, + "loss": 0.0089, + "step": 36435 + }, + { + "epoch": 11.25, + "learning_rate": 8.463496223761073e-06, + "loss": 0.0095, + "step": 36436 + }, + { + "epoch": 11.25, + "learning_rate": 8.463002046223673e-06, + "loss": 0.0103, + "step": 36437 + }, + { + "epoch": 11.25, + "learning_rate": 8.462507872530582e-06, + "loss": 0.0085, + "step": 36438 + }, + { + "epoch": 11.25, + "learning_rate": 8.462013702683038e-06, + "loss": 0.0087, + "step": 36439 + }, + { + "epoch": 11.25, + "learning_rate": 8.461519536682282e-06, + "loss": 0.0097, + "step": 36440 + }, + { + "epoch": 11.25, + "learning_rate": 8.461025374529544e-06, + "loss": 0.0088, + "step": 36441 + }, + { + "epoch": 11.25, + "learning_rate": 8.46053121622606e-06, + "loss": 0.0083, + "step": 36442 + }, + { + "epoch": 11.25, + "learning_rate": 8.460037061773074e-06, + "loss": 0.0096, + "step": 36443 + }, + { + "epoch": 11.25, + "learning_rate": 8.459542911171813e-06, + "loss": 0.0092, + "step": 36444 + }, + { + "epoch": 11.25, + "learning_rate": 8.459048764423516e-06, + "loss": 0.0093, + "step": 36445 + }, + { + "epoch": 11.26, + "learning_rate": 8.458554621529417e-06, + "loss": 0.0077, + "step": 36446 + }, + { + "epoch": 11.26, + "learning_rate": 8.458060482490758e-06, + "loss": 0.0077, + "step": 36447 + }, + { + "epoch": 11.26, + "learning_rate": 8.457566347308769e-06, + "loss": 0.0097, + "step": 36448 + }, + { + "epoch": 11.26, + "learning_rate": 8.457072215984686e-06, + "loss": 0.0078, + "step": 36449 + }, + { + "epoch": 11.26, + "learning_rate": 8.456578088519752e-06, + "loss": 0.0088, + "step": 36450 + }, + { + "epoch": 11.26, + "learning_rate": 8.456083964915194e-06, + "loss": 0.0081, + "step": 36451 + }, + { + "epoch": 11.26, + "learning_rate": 8.45558984517225e-06, + "loss": 0.0084, + "step": 36452 + }, + { + "epoch": 11.26, + "learning_rate": 8.45509572929216e-06, + "loss": 0.0116, + "step": 36453 + }, + { + "epoch": 11.26, + "learning_rate": 8.454601617276158e-06, + "loss": 0.0087, + "step": 36454 + }, + { + "epoch": 11.26, + "learning_rate": 8.454107509125479e-06, + "loss": 0.0087, + "step": 36455 + }, + { + "epoch": 11.26, + "learning_rate": 8.45361340484136e-06, + "loss": 0.0104, + "step": 36456 + }, + { + "epoch": 11.26, + "learning_rate": 8.453119304425031e-06, + "loss": 0.0083, + "step": 36457 + }, + { + "epoch": 11.26, + "learning_rate": 8.452625207877738e-06, + "loss": 0.0102, + "step": 36458 + }, + { + "epoch": 11.26, + "learning_rate": 8.45213111520071e-06, + "loss": 0.0092, + "step": 36459 + }, + { + "epoch": 11.26, + "learning_rate": 8.451637026395181e-06, + "loss": 0.0114, + "step": 36460 + }, + { + "epoch": 11.26, + "learning_rate": 8.451142941462395e-06, + "loss": 0.0084, + "step": 36461 + }, + { + "epoch": 11.26, + "learning_rate": 8.450648860403582e-06, + "loss": 0.0096, + "step": 36462 + }, + { + "epoch": 11.26, + "learning_rate": 8.450154783219975e-06, + "loss": 0.0117, + "step": 36463 + }, + { + "epoch": 11.26, + "learning_rate": 8.449660709912818e-06, + "loss": 0.0092, + "step": 36464 + }, + { + "epoch": 11.26, + "learning_rate": 8.449166640483342e-06, + "loss": 0.0095, + "step": 36465 + }, + { + "epoch": 11.26, + "learning_rate": 8.448672574932782e-06, + "loss": 0.0104, + "step": 36466 + }, + { + "epoch": 11.26, + "learning_rate": 8.448178513262372e-06, + "loss": 0.0085, + "step": 36467 + }, + { + "epoch": 11.26, + "learning_rate": 8.447684455473356e-06, + "loss": 0.0091, + "step": 36468 + }, + { + "epoch": 11.26, + "learning_rate": 8.447190401566962e-06, + "loss": 0.0097, + "step": 36469 + }, + { + "epoch": 11.26, + "learning_rate": 8.446696351544425e-06, + "loss": 0.0101, + "step": 36470 + }, + { + "epoch": 11.26, + "learning_rate": 8.446202305406988e-06, + "loss": 0.0106, + "step": 36471 + }, + { + "epoch": 11.26, + "learning_rate": 8.445708263155882e-06, + "loss": 0.0096, + "step": 36472 + }, + { + "epoch": 11.26, + "learning_rate": 8.44521422479234e-06, + "loss": 0.0094, + "step": 36473 + }, + { + "epoch": 11.26, + "learning_rate": 8.444720190317607e-06, + "loss": 0.0128, + "step": 36474 + }, + { + "epoch": 11.26, + "learning_rate": 8.444226159732906e-06, + "loss": 0.0093, + "step": 36475 + }, + { + "epoch": 11.26, + "learning_rate": 8.44373213303948e-06, + "loss": 0.0082, + "step": 36476 + }, + { + "epoch": 11.26, + "learning_rate": 8.443238110238563e-06, + "loss": 0.0104, + "step": 36477 + }, + { + "epoch": 11.27, + "learning_rate": 8.442744091331397e-06, + "loss": 0.0094, + "step": 36478 + }, + { + "epoch": 11.27, + "learning_rate": 8.442250076319207e-06, + "loss": 0.0107, + "step": 36479 + }, + { + "epoch": 11.27, + "learning_rate": 8.441756065203233e-06, + "loss": 0.0089, + "step": 36480 + }, + { + "epoch": 11.27, + "learning_rate": 8.441262057984715e-06, + "loss": 0.0096, + "step": 36481 + }, + { + "epoch": 11.27, + "learning_rate": 8.440768054664885e-06, + "loss": 0.0098, + "step": 36482 + }, + { + "epoch": 11.27, + "learning_rate": 8.440274055244975e-06, + "loss": 0.0078, + "step": 36483 + }, + { + "epoch": 11.27, + "learning_rate": 8.43978005972623e-06, + "loss": 0.0102, + "step": 36484 + }, + { + "epoch": 11.27, + "learning_rate": 8.439286068109873e-06, + "loss": 0.0092, + "step": 36485 + }, + { + "epoch": 11.27, + "learning_rate": 8.43879208039715e-06, + "loss": 0.0091, + "step": 36486 + }, + { + "epoch": 11.27, + "learning_rate": 8.438298096589293e-06, + "loss": 0.0085, + "step": 36487 + }, + { + "epoch": 11.27, + "learning_rate": 8.437804116687533e-06, + "loss": 0.0101, + "step": 36488 + }, + { + "epoch": 11.27, + "learning_rate": 8.437310140693113e-06, + "loss": 0.0104, + "step": 36489 + }, + { + "epoch": 11.27, + "learning_rate": 8.436816168607267e-06, + "loss": 0.009, + "step": 36490 + }, + { + "epoch": 11.27, + "learning_rate": 8.436322200431225e-06, + "loss": 0.0094, + "step": 36491 + }, + { + "epoch": 11.27, + "learning_rate": 8.435828236166228e-06, + "loss": 0.0081, + "step": 36492 + }, + { + "epoch": 11.27, + "learning_rate": 8.435334275813513e-06, + "loss": 0.0083, + "step": 36493 + }, + { + "epoch": 11.27, + "learning_rate": 8.434840319374308e-06, + "loss": 0.0081, + "step": 36494 + }, + { + "epoch": 11.27, + "learning_rate": 8.434346366849853e-06, + "loss": 0.0106, + "step": 36495 + }, + { + "epoch": 11.27, + "learning_rate": 8.433852418241386e-06, + "loss": 0.0097, + "step": 36496 + }, + { + "epoch": 11.27, + "learning_rate": 8.43335847355014e-06, + "loss": 0.0096, + "step": 36497 + }, + { + "epoch": 11.27, + "learning_rate": 8.432864532777346e-06, + "loss": 0.0098, + "step": 36498 + }, + { + "epoch": 11.27, + "learning_rate": 8.432370595924247e-06, + "loss": 0.0086, + "step": 36499 + }, + { + "epoch": 11.27, + "learning_rate": 8.431876662992074e-06, + "loss": 0.0095, + "step": 36500 + }, + { + "epoch": 11.27, + "learning_rate": 8.431382733982061e-06, + "loss": 0.0091, + "step": 36501 + }, + { + "epoch": 11.27, + "learning_rate": 8.430888808895453e-06, + "loss": 0.0108, + "step": 36502 + }, + { + "epoch": 11.27, + "learning_rate": 8.430394887733473e-06, + "loss": 0.0108, + "step": 36503 + }, + { + "epoch": 11.27, + "learning_rate": 8.429900970497363e-06, + "loss": 0.0111, + "step": 36504 + }, + { + "epoch": 11.27, + "learning_rate": 8.429407057188358e-06, + "loss": 0.0093, + "step": 36505 + }, + { + "epoch": 11.27, + "learning_rate": 8.428913147807689e-06, + "loss": 0.0106, + "step": 36506 + }, + { + "epoch": 11.27, + "learning_rate": 8.428419242356596e-06, + "loss": 0.0095, + "step": 36507 + }, + { + "epoch": 11.27, + "learning_rate": 8.427925340836317e-06, + "loss": 0.0085, + "step": 36508 + }, + { + "epoch": 11.27, + "learning_rate": 8.427431443248077e-06, + "loss": 0.0102, + "step": 36509 + }, + { + "epoch": 11.27, + "learning_rate": 8.426937549593122e-06, + "loss": 0.0066, + "step": 36510 + }, + { + "epoch": 11.28, + "learning_rate": 8.42644365987268e-06, + "loss": 0.0103, + "step": 36511 + }, + { + "epoch": 11.28, + "learning_rate": 8.425949774087994e-06, + "loss": 0.0103, + "step": 36512 + }, + { + "epoch": 11.28, + "learning_rate": 8.425455892240291e-06, + "loss": 0.0094, + "step": 36513 + }, + { + "epoch": 11.28, + "learning_rate": 8.424962014330812e-06, + "loss": 0.0089, + "step": 36514 + }, + { + "epoch": 11.28, + "learning_rate": 8.424468140360792e-06, + "loss": 0.0095, + "step": 36515 + }, + { + "epoch": 11.28, + "learning_rate": 8.42397427033146e-06, + "loss": 0.01, + "step": 36516 + }, + { + "epoch": 11.28, + "learning_rate": 8.423480404244057e-06, + "loss": 0.0087, + "step": 36517 + }, + { + "epoch": 11.28, + "learning_rate": 8.42298654209982e-06, + "loss": 0.0094, + "step": 36518 + }, + { + "epoch": 11.28, + "learning_rate": 8.422492683899978e-06, + "loss": 0.0083, + "step": 36519 + }, + { + "epoch": 11.28, + "learning_rate": 8.42199882964577e-06, + "loss": 0.0095, + "step": 36520 + }, + { + "epoch": 11.28, + "learning_rate": 8.421504979338435e-06, + "loss": 0.0098, + "step": 36521 + }, + { + "epoch": 11.28, + "learning_rate": 8.421011132979199e-06, + "loss": 0.0099, + "step": 36522 + }, + { + "epoch": 11.28, + "learning_rate": 8.420517290569303e-06, + "loss": 0.0093, + "step": 36523 + }, + { + "epoch": 11.28, + "learning_rate": 8.420023452109984e-06, + "loss": 0.0109, + "step": 36524 + }, + { + "epoch": 11.28, + "learning_rate": 8.419529617602471e-06, + "loss": 0.0086, + "step": 36525 + }, + { + "epoch": 11.28, + "learning_rate": 8.419035787048003e-06, + "loss": 0.0078, + "step": 36526 + }, + { + "epoch": 11.28, + "learning_rate": 8.418541960447818e-06, + "loss": 0.0096, + "step": 36527 + }, + { + "epoch": 11.28, + "learning_rate": 8.418048137803146e-06, + "loss": 0.0078, + "step": 36528 + }, + { + "epoch": 11.28, + "learning_rate": 8.41755431911522e-06, + "loss": 0.0095, + "step": 36529 + }, + { + "epoch": 11.28, + "learning_rate": 8.417060504385287e-06, + "loss": 0.0097, + "step": 36530 + }, + { + "epoch": 11.28, + "learning_rate": 8.416566693614571e-06, + "loss": 0.0091, + "step": 36531 + }, + { + "epoch": 11.28, + "learning_rate": 8.416072886804308e-06, + "loss": 0.0092, + "step": 36532 + }, + { + "epoch": 11.28, + "learning_rate": 8.415579083955741e-06, + "loss": 0.0108, + "step": 36533 + }, + { + "epoch": 11.28, + "learning_rate": 8.415085285070095e-06, + "loss": 0.0101, + "step": 36534 + }, + { + "epoch": 11.28, + "learning_rate": 8.414591490148611e-06, + "loss": 0.0073, + "step": 36535 + }, + { + "epoch": 11.28, + "learning_rate": 8.414097699192526e-06, + "loss": 0.0108, + "step": 36536 + }, + { + "epoch": 11.28, + "learning_rate": 8.413603912203066e-06, + "loss": 0.0103, + "step": 36537 + }, + { + "epoch": 11.28, + "learning_rate": 8.413110129181476e-06, + "loss": 0.0081, + "step": 36538 + }, + { + "epoch": 11.28, + "learning_rate": 8.412616350128989e-06, + "loss": 0.0092, + "step": 36539 + }, + { + "epoch": 11.28, + "learning_rate": 8.412122575046831e-06, + "loss": 0.0077, + "step": 36540 + }, + { + "epoch": 11.28, + "learning_rate": 8.411628803936249e-06, + "loss": 0.0085, + "step": 36541 + }, + { + "epoch": 11.28, + "learning_rate": 8.41113503679847e-06, + "loss": 0.0101, + "step": 36542 + }, + { + "epoch": 11.29, + "learning_rate": 8.410641273634738e-06, + "loss": 0.0075, + "step": 36543 + }, + { + "epoch": 11.29, + "learning_rate": 8.410147514446277e-06, + "loss": 0.0109, + "step": 36544 + }, + { + "epoch": 11.29, + "learning_rate": 8.409653759234328e-06, + "loss": 0.0086, + "step": 36545 + }, + { + "epoch": 11.29, + "learning_rate": 8.409160008000128e-06, + "loss": 0.0081, + "step": 36546 + }, + { + "epoch": 11.29, + "learning_rate": 8.408666260744903e-06, + "loss": 0.0092, + "step": 36547 + }, + { + "epoch": 11.29, + "learning_rate": 8.408172517469897e-06, + "loss": 0.0103, + "step": 36548 + }, + { + "epoch": 11.29, + "learning_rate": 8.407678778176345e-06, + "loss": 0.0083, + "step": 36549 + }, + { + "epoch": 11.29, + "learning_rate": 8.407185042865473e-06, + "loss": 0.0087, + "step": 36550 + }, + { + "epoch": 11.29, + "learning_rate": 8.406691311538526e-06, + "loss": 0.0102, + "step": 36551 + }, + { + "epoch": 11.29, + "learning_rate": 8.406197584196734e-06, + "loss": 0.0084, + "step": 36552 + }, + { + "epoch": 11.29, + "learning_rate": 8.405703860841332e-06, + "loss": 0.0082, + "step": 36553 + }, + { + "epoch": 11.29, + "learning_rate": 8.405210141473553e-06, + "loss": 0.0086, + "step": 36554 + }, + { + "epoch": 11.29, + "learning_rate": 8.404716426094638e-06, + "loss": 0.0081, + "step": 36555 + }, + { + "epoch": 11.29, + "learning_rate": 8.404222714705818e-06, + "loss": 0.0098, + "step": 36556 + }, + { + "epoch": 11.29, + "learning_rate": 8.403729007308324e-06, + "loss": 0.008, + "step": 36557 + }, + { + "epoch": 11.29, + "learning_rate": 8.4032353039034e-06, + "loss": 0.0079, + "step": 36558 + }, + { + "epoch": 11.29, + "learning_rate": 8.402741604492273e-06, + "loss": 0.0092, + "step": 36559 + }, + { + "epoch": 11.29, + "learning_rate": 8.402247909076179e-06, + "loss": 0.0105, + "step": 36560 + }, + { + "epoch": 11.29, + "learning_rate": 8.401754217656358e-06, + "loss": 0.0086, + "step": 36561 + }, + { + "epoch": 11.29, + "learning_rate": 8.40126053023404e-06, + "loss": 0.0079, + "step": 36562 + }, + { + "epoch": 11.29, + "learning_rate": 8.40076684681046e-06, + "loss": 0.0089, + "step": 36563 + }, + { + "epoch": 11.29, + "learning_rate": 8.400273167386857e-06, + "loss": 0.0073, + "step": 36564 + }, + { + "epoch": 11.29, + "learning_rate": 8.399779491964457e-06, + "loss": 0.0083, + "step": 36565 + }, + { + "epoch": 11.29, + "learning_rate": 8.399285820544504e-06, + "loss": 0.0088, + "step": 36566 + }, + { + "epoch": 11.29, + "learning_rate": 8.39879215312823e-06, + "loss": 0.0082, + "step": 36567 + }, + { + "epoch": 11.29, + "learning_rate": 8.398298489716866e-06, + "loss": 0.0099, + "step": 36568 + }, + { + "epoch": 11.29, + "learning_rate": 8.39780483031165e-06, + "loss": 0.0083, + "step": 36569 + }, + { + "epoch": 11.29, + "learning_rate": 8.39731117491382e-06, + "loss": 0.0074, + "step": 36570 + }, + { + "epoch": 11.29, + "learning_rate": 8.3968175235246e-06, + "loss": 0.007, + "step": 36571 + }, + { + "epoch": 11.29, + "learning_rate": 8.396323876145237e-06, + "loss": 0.0087, + "step": 36572 + }, + { + "epoch": 11.29, + "learning_rate": 8.395830232776962e-06, + "loss": 0.0079, + "step": 36573 + }, + { + "epoch": 11.29, + "learning_rate": 8.395336593421006e-06, + "loss": 0.0097, + "step": 36574 + }, + { + "epoch": 11.3, + "learning_rate": 8.394842958078604e-06, + "loss": 0.0101, + "step": 36575 + }, + { + "epoch": 11.3, + "learning_rate": 8.394349326750992e-06, + "loss": 0.0087, + "step": 36576 + }, + { + "epoch": 11.3, + "learning_rate": 8.39385569943941e-06, + "loss": 0.0096, + "step": 36577 + }, + { + "epoch": 11.3, + "learning_rate": 8.393362076145083e-06, + "loss": 0.009, + "step": 36578 + }, + { + "epoch": 11.3, + "learning_rate": 8.392868456869253e-06, + "loss": 0.0095, + "step": 36579 + }, + { + "epoch": 11.3, + "learning_rate": 8.392374841613153e-06, + "loss": 0.0089, + "step": 36580 + }, + { + "epoch": 11.3, + "learning_rate": 8.391881230378015e-06, + "loss": 0.0105, + "step": 36581 + }, + { + "epoch": 11.3, + "learning_rate": 8.391387623165075e-06, + "loss": 0.0077, + "step": 36582 + }, + { + "epoch": 11.3, + "learning_rate": 8.390894019975571e-06, + "loss": 0.0085, + "step": 36583 + }, + { + "epoch": 11.3, + "learning_rate": 8.390400420810732e-06, + "loss": 0.0089, + "step": 36584 + }, + { + "epoch": 11.3, + "learning_rate": 8.389906825671793e-06, + "loss": 0.0086, + "step": 36585 + }, + { + "epoch": 11.3, + "learning_rate": 8.389413234559995e-06, + "loss": 0.009, + "step": 36586 + }, + { + "epoch": 11.3, + "learning_rate": 8.388919647476566e-06, + "loss": 0.0082, + "step": 36587 + }, + { + "epoch": 11.3, + "learning_rate": 8.388426064422741e-06, + "loss": 0.0096, + "step": 36588 + }, + { + "epoch": 11.3, + "learning_rate": 8.387932485399761e-06, + "loss": 0.008, + "step": 36589 + }, + { + "epoch": 11.3, + "learning_rate": 8.387438910408853e-06, + "loss": 0.0101, + "step": 36590 + }, + { + "epoch": 11.3, + "learning_rate": 8.386945339451253e-06, + "loss": 0.0099, + "step": 36591 + }, + { + "epoch": 11.3, + "learning_rate": 8.386451772528203e-06, + "loss": 0.0094, + "step": 36592 + }, + { + "epoch": 11.3, + "learning_rate": 8.385958209640925e-06, + "loss": 0.0096, + "step": 36593 + }, + { + "epoch": 11.3, + "learning_rate": 8.385464650790661e-06, + "loss": 0.0088, + "step": 36594 + }, + { + "epoch": 11.3, + "learning_rate": 8.384971095978648e-06, + "loss": 0.0085, + "step": 36595 + }, + { + "epoch": 11.3, + "learning_rate": 8.384477545206112e-06, + "loss": 0.0074, + "step": 36596 + }, + { + "epoch": 11.3, + "learning_rate": 8.383983998474295e-06, + "loss": 0.0098, + "step": 36597 + }, + { + "epoch": 11.3, + "learning_rate": 8.38349045578443e-06, + "loss": 0.0093, + "step": 36598 + }, + { + "epoch": 11.3, + "learning_rate": 8.382996917137746e-06, + "loss": 0.0095, + "step": 36599 + }, + { + "epoch": 11.3, + "learning_rate": 8.382503382535484e-06, + "loss": 0.0089, + "step": 36600 + }, + { + "epoch": 11.3, + "learning_rate": 8.382009851978878e-06, + "loss": 0.0101, + "step": 36601 + }, + { + "epoch": 11.3, + "learning_rate": 8.381516325469159e-06, + "loss": 0.0082, + "step": 36602 + }, + { + "epoch": 11.3, + "learning_rate": 8.38102280300756e-06, + "loss": 0.0078, + "step": 36603 + }, + { + "epoch": 11.3, + "learning_rate": 8.380529284595323e-06, + "loss": 0.0093, + "step": 36604 + }, + { + "epoch": 11.3, + "learning_rate": 8.380035770233676e-06, + "loss": 0.009, + "step": 36605 + }, + { + "epoch": 11.3, + "learning_rate": 8.379542259923852e-06, + "loss": 0.0089, + "step": 36606 + }, + { + "epoch": 11.3, + "learning_rate": 8.37904875366709e-06, + "loss": 0.0094, + "step": 36607 + }, + { + "epoch": 11.31, + "learning_rate": 8.378555251464626e-06, + "loss": 0.0092, + "step": 36608 + }, + { + "epoch": 11.31, + "learning_rate": 8.378061753317685e-06, + "loss": 0.0094, + "step": 36609 + }, + { + "epoch": 11.31, + "learning_rate": 8.377568259227512e-06, + "loss": 0.0095, + "step": 36610 + }, + { + "epoch": 11.31, + "learning_rate": 8.377074769195338e-06, + "loss": 0.0095, + "step": 36611 + }, + { + "epoch": 11.31, + "learning_rate": 8.376581283222391e-06, + "loss": 0.0084, + "step": 36612 + }, + { + "epoch": 11.31, + "learning_rate": 8.376087801309913e-06, + "loss": 0.0087, + "step": 36613 + }, + { + "epoch": 11.31, + "learning_rate": 8.375594323459138e-06, + "loss": 0.0096, + "step": 36614 + }, + { + "epoch": 11.31, + "learning_rate": 8.375100849671294e-06, + "loss": 0.0102, + "step": 36615 + }, + { + "epoch": 11.31, + "learning_rate": 8.37460737994762e-06, + "loss": 0.0102, + "step": 36616 + }, + { + "epoch": 11.31, + "learning_rate": 8.374113914289351e-06, + "loss": 0.0081, + "step": 36617 + }, + { + "epoch": 11.31, + "learning_rate": 8.373620452697718e-06, + "loss": 0.0086, + "step": 36618 + }, + { + "epoch": 11.31, + "learning_rate": 8.373126995173955e-06, + "loss": 0.0093, + "step": 36619 + }, + { + "epoch": 11.31, + "learning_rate": 8.372633541719303e-06, + "loss": 0.0102, + "step": 36620 + }, + { + "epoch": 11.31, + "learning_rate": 8.372140092334989e-06, + "loss": 0.009, + "step": 36621 + }, + { + "epoch": 11.31, + "learning_rate": 8.371646647022246e-06, + "loss": 0.0103, + "step": 36622 + }, + { + "epoch": 11.31, + "learning_rate": 8.371153205782321e-06, + "loss": 0.0078, + "step": 36623 + }, + { + "epoch": 11.31, + "learning_rate": 8.37065976861643e-06, + "loss": 0.01, + "step": 36624 + }, + { + "epoch": 11.31, + "learning_rate": 8.37016633552582e-06, + "loss": 0.0087, + "step": 36625 + }, + { + "epoch": 11.31, + "learning_rate": 8.369672906511722e-06, + "loss": 0.0101, + "step": 36626 + }, + { + "epoch": 11.31, + "learning_rate": 8.369179481575366e-06, + "loss": 0.0101, + "step": 36627 + }, + { + "epoch": 11.31, + "learning_rate": 8.368686060717992e-06, + "loss": 0.0088, + "step": 36628 + }, + { + "epoch": 11.31, + "learning_rate": 8.368192643940832e-06, + "loss": 0.0105, + "step": 36629 + }, + { + "epoch": 11.31, + "learning_rate": 8.367699231245116e-06, + "loss": 0.0084, + "step": 36630 + }, + { + "epoch": 11.31, + "learning_rate": 8.367205822632085e-06, + "loss": 0.0099, + "step": 36631 + }, + { + "epoch": 11.31, + "learning_rate": 8.366712418102973e-06, + "loss": 0.0087, + "step": 36632 + }, + { + "epoch": 11.31, + "learning_rate": 8.366219017659007e-06, + "loss": 0.0098, + "step": 36633 + }, + { + "epoch": 11.31, + "learning_rate": 8.365725621301423e-06, + "loss": 0.0078, + "step": 36634 + }, + { + "epoch": 11.31, + "learning_rate": 8.365232229031463e-06, + "loss": 0.0079, + "step": 36635 + }, + { + "epoch": 11.31, + "learning_rate": 8.364738840850354e-06, + "loss": 0.0077, + "step": 36636 + }, + { + "epoch": 11.31, + "learning_rate": 8.364245456759329e-06, + "loss": 0.0099, + "step": 36637 + }, + { + "epoch": 11.31, + "learning_rate": 8.363752076759626e-06, + "loss": 0.0093, + "step": 36638 + }, + { + "epoch": 11.31, + "learning_rate": 8.363258700852477e-06, + "loss": 0.0092, + "step": 36639 + }, + { + "epoch": 11.32, + "learning_rate": 8.362765329039115e-06, + "loss": 0.0092, + "step": 36640 + }, + { + "epoch": 11.32, + "learning_rate": 8.362271961320777e-06, + "loss": 0.0113, + "step": 36641 + }, + { + "epoch": 11.32, + "learning_rate": 8.361778597698697e-06, + "loss": 0.0097, + "step": 36642 + }, + { + "epoch": 11.32, + "learning_rate": 8.361285238174108e-06, + "loss": 0.0105, + "step": 36643 + }, + { + "epoch": 11.32, + "learning_rate": 8.360791882748239e-06, + "loss": 0.0105, + "step": 36644 + }, + { + "epoch": 11.32, + "learning_rate": 8.360298531422333e-06, + "loss": 0.0097, + "step": 36645 + }, + { + "epoch": 11.32, + "learning_rate": 8.359805184197617e-06, + "loss": 0.0095, + "step": 36646 + }, + { + "epoch": 11.32, + "learning_rate": 8.359311841075327e-06, + "loss": 0.0099, + "step": 36647 + }, + { + "epoch": 11.32, + "learning_rate": 8.3588185020567e-06, + "loss": 0.0103, + "step": 36648 + }, + { + "epoch": 11.32, + "learning_rate": 8.358325167142966e-06, + "loss": 0.009, + "step": 36649 + }, + { + "epoch": 11.32, + "learning_rate": 8.357831836335358e-06, + "loss": 0.0095, + "step": 36650 + }, + { + "epoch": 11.32, + "learning_rate": 8.357338509635116e-06, + "loss": 0.0094, + "step": 36651 + }, + { + "epoch": 11.32, + "learning_rate": 8.356845187043468e-06, + "loss": 0.0095, + "step": 36652 + }, + { + "epoch": 11.32, + "learning_rate": 8.35635186856165e-06, + "loss": 0.0091, + "step": 36653 + }, + { + "epoch": 11.32, + "learning_rate": 8.355858554190897e-06, + "loss": 0.0096, + "step": 36654 + }, + { + "epoch": 11.32, + "learning_rate": 8.355365243932438e-06, + "loss": 0.008, + "step": 36655 + }, + { + "epoch": 11.32, + "learning_rate": 8.354871937787512e-06, + "loss": 0.0079, + "step": 36656 + }, + { + "epoch": 11.32, + "learning_rate": 8.354378635757354e-06, + "loss": 0.0089, + "step": 36657 + }, + { + "epoch": 11.32, + "learning_rate": 8.353885337843191e-06, + "loss": 0.0101, + "step": 36658 + }, + { + "epoch": 11.32, + "learning_rate": 8.353392044046264e-06, + "loss": 0.0101, + "step": 36659 + }, + { + "epoch": 11.32, + "learning_rate": 8.352898754367806e-06, + "loss": 0.011, + "step": 36660 + }, + { + "epoch": 11.32, + "learning_rate": 8.352405468809043e-06, + "loss": 0.0109, + "step": 36661 + }, + { + "epoch": 11.32, + "learning_rate": 8.351912187371216e-06, + "loss": 0.008, + "step": 36662 + }, + { + "epoch": 11.32, + "learning_rate": 8.351418910055562e-06, + "loss": 0.0091, + "step": 36663 + }, + { + "epoch": 11.32, + "learning_rate": 8.350925636863305e-06, + "loss": 0.0095, + "step": 36664 + }, + { + "epoch": 11.32, + "learning_rate": 8.350432367795681e-06, + "loss": 0.0108, + "step": 36665 + }, + { + "epoch": 11.32, + "learning_rate": 8.349939102853935e-06, + "loss": 0.0092, + "step": 36666 + }, + { + "epoch": 11.32, + "learning_rate": 8.349445842039288e-06, + "loss": 0.0088, + "step": 36667 + }, + { + "epoch": 11.32, + "learning_rate": 8.348952585352975e-06, + "loss": 0.009, + "step": 36668 + }, + { + "epoch": 11.32, + "learning_rate": 8.348459332796237e-06, + "loss": 0.0088, + "step": 36669 + }, + { + "epoch": 11.32, + "learning_rate": 8.347966084370303e-06, + "loss": 0.0095, + "step": 36670 + }, + { + "epoch": 11.32, + "learning_rate": 8.347472840076402e-06, + "loss": 0.0097, + "step": 36671 + }, + { + "epoch": 11.33, + "learning_rate": 8.346979599915782e-06, + "loss": 0.0075, + "step": 36672 + }, + { + "epoch": 11.33, + "learning_rate": 8.346486363889661e-06, + "loss": 0.011, + "step": 36673 + }, + { + "epoch": 11.33, + "learning_rate": 8.34599313199928e-06, + "loss": 0.0106, + "step": 36674 + }, + { + "epoch": 11.33, + "learning_rate": 8.345499904245871e-06, + "loss": 0.0107, + "step": 36675 + }, + { + "epoch": 11.33, + "learning_rate": 8.345006680630672e-06, + "loss": 0.0089, + "step": 36676 + }, + { + "epoch": 11.33, + "learning_rate": 8.344513461154911e-06, + "loss": 0.0096, + "step": 36677 + }, + { + "epoch": 11.33, + "learning_rate": 8.344020245819822e-06, + "loss": 0.0076, + "step": 36678 + }, + { + "epoch": 11.33, + "learning_rate": 8.343527034626644e-06, + "loss": 0.0117, + "step": 36679 + }, + { + "epoch": 11.33, + "learning_rate": 8.343033827576604e-06, + "loss": 0.0097, + "step": 36680 + }, + { + "epoch": 11.33, + "learning_rate": 8.342540624670938e-06, + "loss": 0.0093, + "step": 36681 + }, + { + "epoch": 11.33, + "learning_rate": 8.342047425910886e-06, + "loss": 0.0095, + "step": 36682 + }, + { + "epoch": 11.33, + "learning_rate": 8.34155423129767e-06, + "loss": 0.0082, + "step": 36683 + }, + { + "epoch": 11.33, + "learning_rate": 8.341061040832532e-06, + "loss": 0.009, + "step": 36684 + }, + { + "epoch": 11.33, + "learning_rate": 8.340567854516703e-06, + "loss": 0.0099, + "step": 36685 + }, + { + "epoch": 11.33, + "learning_rate": 8.340074672351415e-06, + "loss": 0.0107, + "step": 36686 + }, + { + "epoch": 11.33, + "learning_rate": 8.339581494337903e-06, + "loss": 0.0094, + "step": 36687 + }, + { + "epoch": 11.33, + "learning_rate": 8.339088320477402e-06, + "loss": 0.01, + "step": 36688 + }, + { + "epoch": 11.33, + "learning_rate": 8.338595150771141e-06, + "loss": 0.0092, + "step": 36689 + }, + { + "epoch": 11.33, + "learning_rate": 8.338101985220359e-06, + "loss": 0.0079, + "step": 36690 + }, + { + "epoch": 11.33, + "learning_rate": 8.337608823826289e-06, + "loss": 0.0092, + "step": 36691 + }, + { + "epoch": 11.33, + "learning_rate": 8.33711566659016e-06, + "loss": 0.0091, + "step": 36692 + }, + { + "epoch": 11.33, + "learning_rate": 8.336622513513207e-06, + "loss": 0.0091, + "step": 36693 + }, + { + "epoch": 11.33, + "learning_rate": 8.336129364596668e-06, + "loss": 0.0089, + "step": 36694 + }, + { + "epoch": 11.33, + "learning_rate": 8.335636219841769e-06, + "loss": 0.0087, + "step": 36695 + }, + { + "epoch": 11.33, + "learning_rate": 8.335143079249748e-06, + "loss": 0.0097, + "step": 36696 + }, + { + "epoch": 11.33, + "learning_rate": 8.33464994282184e-06, + "loss": 0.0082, + "step": 36697 + }, + { + "epoch": 11.33, + "learning_rate": 8.334156810559275e-06, + "loss": 0.0099, + "step": 36698 + }, + { + "epoch": 11.33, + "learning_rate": 8.333663682463287e-06, + "loss": 0.0087, + "step": 36699 + }, + { + "epoch": 11.33, + "learning_rate": 8.333170558535112e-06, + "loss": 0.0092, + "step": 36700 + }, + { + "epoch": 11.33, + "learning_rate": 8.33267743877598e-06, + "loss": 0.01, + "step": 36701 + }, + { + "epoch": 11.33, + "learning_rate": 8.332184323187126e-06, + "loss": 0.0093, + "step": 36702 + }, + { + "epoch": 11.33, + "learning_rate": 8.331691211769786e-06, + "loss": 0.0089, + "step": 36703 + }, + { + "epoch": 11.33, + "learning_rate": 8.331198104525186e-06, + "loss": 0.0085, + "step": 36704 + }, + { + "epoch": 11.34, + "learning_rate": 8.330705001454566e-06, + "loss": 0.009, + "step": 36705 + }, + { + "epoch": 11.34, + "learning_rate": 8.330211902559154e-06, + "loss": 0.0104, + "step": 36706 + }, + { + "epoch": 11.34, + "learning_rate": 8.32971880784019e-06, + "loss": 0.0104, + "step": 36707 + }, + { + "epoch": 11.34, + "learning_rate": 8.329225717298906e-06, + "loss": 0.0086, + "step": 36708 + }, + { + "epoch": 11.34, + "learning_rate": 8.328732630936527e-06, + "loss": 0.0086, + "step": 36709 + }, + { + "epoch": 11.34, + "learning_rate": 8.328239548754299e-06, + "loss": 0.0113, + "step": 36710 + }, + { + "epoch": 11.34, + "learning_rate": 8.327746470753447e-06, + "loss": 0.0115, + "step": 36711 + }, + { + "epoch": 11.34, + "learning_rate": 8.327253396935205e-06, + "loss": 0.0105, + "step": 36712 + }, + { + "epoch": 11.34, + "learning_rate": 8.326760327300809e-06, + "loss": 0.0132, + "step": 36713 + }, + { + "epoch": 11.34, + "learning_rate": 8.326267261851486e-06, + "loss": 0.0102, + "step": 36714 + }, + { + "epoch": 11.34, + "learning_rate": 8.325774200588477e-06, + "loss": 0.01, + "step": 36715 + }, + { + "epoch": 11.34, + "learning_rate": 8.325281143513014e-06, + "loss": 0.0091, + "step": 36716 + }, + { + "epoch": 11.34, + "learning_rate": 8.324788090626324e-06, + "loss": 0.0098, + "step": 36717 + }, + { + "epoch": 11.34, + "learning_rate": 8.324295041929646e-06, + "loss": 0.0099, + "step": 36718 + }, + { + "epoch": 11.34, + "learning_rate": 8.323801997424215e-06, + "loss": 0.0093, + "step": 36719 + }, + { + "epoch": 11.34, + "learning_rate": 8.323308957111258e-06, + "loss": 0.0104, + "step": 36720 + }, + { + "epoch": 11.34, + "learning_rate": 8.32281592099201e-06, + "loss": 0.0089, + "step": 36721 + }, + { + "epoch": 11.34, + "learning_rate": 8.32232288906771e-06, + "loss": 0.0101, + "step": 36722 + }, + { + "epoch": 11.34, + "learning_rate": 8.321829861339583e-06, + "loss": 0.0096, + "step": 36723 + }, + { + "epoch": 11.34, + "learning_rate": 8.321336837808861e-06, + "loss": 0.0106, + "step": 36724 + }, + { + "epoch": 11.34, + "learning_rate": 8.320843818476791e-06, + "loss": 0.0135, + "step": 36725 + }, + { + "epoch": 11.34, + "learning_rate": 8.320350803344593e-06, + "loss": 0.0097, + "step": 36726 + }, + { + "epoch": 11.34, + "learning_rate": 8.3198577924135e-06, + "loss": 0.01, + "step": 36727 + }, + { + "epoch": 11.34, + "learning_rate": 8.319364785684755e-06, + "loss": 0.0081, + "step": 36728 + }, + { + "epoch": 11.34, + "learning_rate": 8.318871783159582e-06, + "loss": 0.011, + "step": 36729 + }, + { + "epoch": 11.34, + "learning_rate": 8.318378784839216e-06, + "loss": 0.0093, + "step": 36730 + }, + { + "epoch": 11.34, + "learning_rate": 8.317885790724898e-06, + "loss": 0.0093, + "step": 36731 + }, + { + "epoch": 11.34, + "learning_rate": 8.317392800817848e-06, + "loss": 0.0089, + "step": 36732 + }, + { + "epoch": 11.34, + "learning_rate": 8.316899815119308e-06, + "loss": 0.0109, + "step": 36733 + }, + { + "epoch": 11.34, + "learning_rate": 8.31640683363051e-06, + "loss": 0.0102, + "step": 36734 + }, + { + "epoch": 11.34, + "learning_rate": 8.31591385635268e-06, + "loss": 0.0083, + "step": 36735 + }, + { + "epoch": 11.34, + "learning_rate": 8.31542088328706e-06, + "loss": 0.0102, + "step": 36736 + }, + { + "epoch": 11.35, + "learning_rate": 8.314927914434882e-06, + "loss": 0.0098, + "step": 36737 + }, + { + "epoch": 11.35, + "learning_rate": 8.314434949797372e-06, + "loss": 0.0086, + "step": 36738 + }, + { + "epoch": 11.35, + "learning_rate": 8.31394198937577e-06, + "loss": 0.01, + "step": 36739 + }, + { + "epoch": 11.35, + "learning_rate": 8.313449033171304e-06, + "loss": 0.0094, + "step": 36740 + }, + { + "epoch": 11.35, + "learning_rate": 8.312956081185217e-06, + "loss": 0.0093, + "step": 36741 + }, + { + "epoch": 11.35, + "learning_rate": 8.312463133418727e-06, + "loss": 0.0117, + "step": 36742 + }, + { + "epoch": 11.35, + "learning_rate": 8.311970189873078e-06, + "loss": 0.0082, + "step": 36743 + }, + { + "epoch": 11.35, + "learning_rate": 8.3114772505495e-06, + "loss": 0.0101, + "step": 36744 + }, + { + "epoch": 11.35, + "learning_rate": 8.310984315449222e-06, + "loss": 0.0091, + "step": 36745 + }, + { + "epoch": 11.35, + "learning_rate": 8.310491384573483e-06, + "loss": 0.0094, + "step": 36746 + }, + { + "epoch": 11.35, + "learning_rate": 8.309998457923514e-06, + "loss": 0.0102, + "step": 36747 + }, + { + "epoch": 11.35, + "learning_rate": 8.309505535500542e-06, + "loss": 0.0089, + "step": 36748 + }, + { + "epoch": 11.35, + "learning_rate": 8.30901261730581e-06, + "loss": 0.0091, + "step": 36749 + }, + { + "epoch": 11.35, + "learning_rate": 8.308519703340546e-06, + "loss": 0.0101, + "step": 36750 + }, + { + "epoch": 11.35, + "learning_rate": 8.308026793605982e-06, + "loss": 0.0093, + "step": 36751 + }, + { + "epoch": 11.35, + "learning_rate": 8.307533888103347e-06, + "loss": 0.0102, + "step": 36752 + }, + { + "epoch": 11.35, + "learning_rate": 8.307040986833885e-06, + "loss": 0.0089, + "step": 36753 + }, + { + "epoch": 11.35, + "learning_rate": 8.306548089798818e-06, + "loss": 0.011, + "step": 36754 + }, + { + "epoch": 11.35, + "learning_rate": 8.306055196999382e-06, + "loss": 0.0116, + "step": 36755 + }, + { + "epoch": 11.35, + "learning_rate": 8.305562308436817e-06, + "loss": 0.0102, + "step": 36756 + }, + { + "epoch": 11.35, + "learning_rate": 8.305069424112346e-06, + "loss": 0.0086, + "step": 36757 + }, + { + "epoch": 11.35, + "learning_rate": 8.304576544027203e-06, + "loss": 0.0109, + "step": 36758 + }, + { + "epoch": 11.35, + "learning_rate": 8.304083668182627e-06, + "loss": 0.0084, + "step": 36759 + }, + { + "epoch": 11.35, + "learning_rate": 8.303590796579847e-06, + "loss": 0.0113, + "step": 36760 + }, + { + "epoch": 11.35, + "learning_rate": 8.303097929220094e-06, + "loss": 0.0104, + "step": 36761 + }, + { + "epoch": 11.35, + "learning_rate": 8.302605066104605e-06, + "loss": 0.0088, + "step": 36762 + }, + { + "epoch": 11.35, + "learning_rate": 8.302112207234607e-06, + "loss": 0.0089, + "step": 36763 + }, + { + "epoch": 11.35, + "learning_rate": 8.301619352611338e-06, + "loss": 0.0095, + "step": 36764 + }, + { + "epoch": 11.35, + "learning_rate": 8.30112650223603e-06, + "loss": 0.0093, + "step": 36765 + }, + { + "epoch": 11.35, + "learning_rate": 8.300633656109912e-06, + "loss": 0.0093, + "step": 36766 + }, + { + "epoch": 11.35, + "learning_rate": 8.300140814234219e-06, + "loss": 0.0082, + "step": 36767 + }, + { + "epoch": 11.35, + "learning_rate": 8.299647976610189e-06, + "loss": 0.01, + "step": 36768 + }, + { + "epoch": 11.35, + "learning_rate": 8.299155143239042e-06, + "loss": 0.0079, + "step": 36769 + }, + { + "epoch": 11.36, + "learning_rate": 8.298662314122021e-06, + "loss": 0.0099, + "step": 36770 + }, + { + "epoch": 11.36, + "learning_rate": 8.298169489260357e-06, + "loss": 0.0092, + "step": 36771 + }, + { + "epoch": 11.36, + "learning_rate": 8.297676668655284e-06, + "loss": 0.0105, + "step": 36772 + }, + { + "epoch": 11.36, + "learning_rate": 8.297183852308025e-06, + "loss": 0.0109, + "step": 36773 + }, + { + "epoch": 11.36, + "learning_rate": 8.296691040219825e-06, + "loss": 0.0093, + "step": 36774 + }, + { + "epoch": 11.36, + "learning_rate": 8.296198232391912e-06, + "loss": 0.0081, + "step": 36775 + }, + { + "epoch": 11.36, + "learning_rate": 8.295705428825513e-06, + "loss": 0.0111, + "step": 36776 + }, + { + "epoch": 11.36, + "learning_rate": 8.295212629521869e-06, + "loss": 0.0106, + "step": 36777 + }, + { + "epoch": 11.36, + "learning_rate": 8.294719834482212e-06, + "loss": 0.0092, + "step": 36778 + }, + { + "epoch": 11.36, + "learning_rate": 8.294227043707767e-06, + "loss": 0.0121, + "step": 36779 + }, + { + "epoch": 11.36, + "learning_rate": 8.293734257199772e-06, + "loss": 0.0089, + "step": 36780 + }, + { + "epoch": 11.36, + "learning_rate": 8.293241474959462e-06, + "loss": 0.0115, + "step": 36781 + }, + { + "epoch": 11.36, + "learning_rate": 8.292748696988065e-06, + "loss": 0.0073, + "step": 36782 + }, + { + "epoch": 11.36, + "learning_rate": 8.292255923286811e-06, + "loss": 0.0081, + "step": 36783 + }, + { + "epoch": 11.36, + "learning_rate": 8.291763153856943e-06, + "loss": 0.0083, + "step": 36784 + }, + { + "epoch": 11.36, + "learning_rate": 8.291270388699683e-06, + "loss": 0.0109, + "step": 36785 + }, + { + "epoch": 11.36, + "learning_rate": 8.290777627816266e-06, + "loss": 0.0091, + "step": 36786 + }, + { + "epoch": 11.36, + "learning_rate": 8.290284871207929e-06, + "loss": 0.0087, + "step": 36787 + }, + { + "epoch": 11.36, + "learning_rate": 8.2897921188759e-06, + "loss": 0.0107, + "step": 36788 + }, + { + "epoch": 11.36, + "learning_rate": 8.289299370821412e-06, + "loss": 0.0087, + "step": 36789 + }, + { + "epoch": 11.36, + "learning_rate": 8.288806627045703e-06, + "loss": 0.0125, + "step": 36790 + }, + { + "epoch": 11.36, + "learning_rate": 8.288313887549993e-06, + "loss": 0.0085, + "step": 36791 + }, + { + "epoch": 11.36, + "learning_rate": 8.287821152335526e-06, + "loss": 0.009, + "step": 36792 + }, + { + "epoch": 11.36, + "learning_rate": 8.287328421403534e-06, + "loss": 0.0108, + "step": 36793 + }, + { + "epoch": 11.36, + "learning_rate": 8.28683569475524e-06, + "loss": 0.0102, + "step": 36794 + }, + { + "epoch": 11.36, + "learning_rate": 8.286342972391886e-06, + "loss": 0.0084, + "step": 36795 + }, + { + "epoch": 11.36, + "learning_rate": 8.285850254314701e-06, + "loss": 0.0095, + "step": 36796 + }, + { + "epoch": 11.36, + "learning_rate": 8.285357540524915e-06, + "loss": 0.0084, + "step": 36797 + }, + { + "epoch": 11.36, + "learning_rate": 8.284864831023763e-06, + "loss": 0.0093, + "step": 36798 + }, + { + "epoch": 11.36, + "learning_rate": 8.284372125812478e-06, + "loss": 0.0095, + "step": 36799 + }, + { + "epoch": 11.36, + "learning_rate": 8.283879424892292e-06, + "loss": 0.0088, + "step": 36800 + }, + { + "epoch": 11.36, + "learning_rate": 8.283386728264431e-06, + "loss": 0.0112, + "step": 36801 + }, + { + "epoch": 11.37, + "learning_rate": 8.28289403593014e-06, + "loss": 0.0086, + "step": 36802 + }, + { + "epoch": 11.37, + "learning_rate": 8.282401347890641e-06, + "loss": 0.0101, + "step": 36803 + }, + { + "epoch": 11.37, + "learning_rate": 8.281908664147168e-06, + "loss": 0.0131, + "step": 36804 + }, + { + "epoch": 11.37, + "learning_rate": 8.281415984700957e-06, + "loss": 0.0095, + "step": 36805 + }, + { + "epoch": 11.37, + "learning_rate": 8.280923309553239e-06, + "loss": 0.0088, + "step": 36806 + }, + { + "epoch": 11.37, + "learning_rate": 8.280430638705243e-06, + "loss": 0.0097, + "step": 36807 + }, + { + "epoch": 11.37, + "learning_rate": 8.279937972158204e-06, + "loss": 0.0111, + "step": 36808 + }, + { + "epoch": 11.37, + "learning_rate": 8.279445309913357e-06, + "loss": 0.0091, + "step": 36809 + }, + { + "epoch": 11.37, + "learning_rate": 8.278952651971927e-06, + "loss": 0.0093, + "step": 36810 + }, + { + "epoch": 11.37, + "learning_rate": 8.278459998335151e-06, + "loss": 0.011, + "step": 36811 + }, + { + "epoch": 11.37, + "learning_rate": 8.277967349004263e-06, + "loss": 0.0114, + "step": 36812 + }, + { + "epoch": 11.37, + "learning_rate": 8.27747470398049e-06, + "loss": 0.011, + "step": 36813 + }, + { + "epoch": 11.37, + "learning_rate": 8.276982063265067e-06, + "loss": 0.0094, + "step": 36814 + }, + { + "epoch": 11.37, + "learning_rate": 8.27648942685923e-06, + "loss": 0.0086, + "step": 36815 + }, + { + "epoch": 11.37, + "learning_rate": 8.275996794764203e-06, + "loss": 0.011, + "step": 36816 + }, + { + "epoch": 11.37, + "learning_rate": 8.275504166981222e-06, + "loss": 0.0085, + "step": 36817 + }, + { + "epoch": 11.37, + "learning_rate": 8.275011543511524e-06, + "loss": 0.0106, + "step": 36818 + }, + { + "epoch": 11.37, + "learning_rate": 8.274518924356335e-06, + "loss": 0.0104, + "step": 36819 + }, + { + "epoch": 11.37, + "learning_rate": 8.274026309516888e-06, + "loss": 0.0104, + "step": 36820 + }, + { + "epoch": 11.37, + "learning_rate": 8.273533698994417e-06, + "loss": 0.0089, + "step": 36821 + }, + { + "epoch": 11.37, + "learning_rate": 8.273041092790151e-06, + "loss": 0.0092, + "step": 36822 + }, + { + "epoch": 11.37, + "learning_rate": 8.272548490905324e-06, + "loss": 0.012, + "step": 36823 + }, + { + "epoch": 11.37, + "learning_rate": 8.272055893341172e-06, + "loss": 0.0086, + "step": 36824 + }, + { + "epoch": 11.37, + "learning_rate": 8.271563300098919e-06, + "loss": 0.0092, + "step": 36825 + }, + { + "epoch": 11.37, + "learning_rate": 8.271070711179804e-06, + "loss": 0.0119, + "step": 36826 + }, + { + "epoch": 11.37, + "learning_rate": 8.270578126585059e-06, + "loss": 0.0094, + "step": 36827 + }, + { + "epoch": 11.37, + "learning_rate": 8.270085546315907e-06, + "loss": 0.0087, + "step": 36828 + }, + { + "epoch": 11.37, + "learning_rate": 8.26959297037359e-06, + "loss": 0.009, + "step": 36829 + }, + { + "epoch": 11.37, + "learning_rate": 8.269100398759339e-06, + "loss": 0.0099, + "step": 36830 + }, + { + "epoch": 11.37, + "learning_rate": 8.268607831474382e-06, + "loss": 0.0091, + "step": 36831 + }, + { + "epoch": 11.37, + "learning_rate": 8.26811526851995e-06, + "loss": 0.0101, + "step": 36832 + }, + { + "epoch": 11.37, + "learning_rate": 8.26762270989728e-06, + "loss": 0.0098, + "step": 36833 + }, + { + "epoch": 11.38, + "learning_rate": 8.2671301556076e-06, + "loss": 0.0094, + "step": 36834 + }, + { + "epoch": 11.38, + "learning_rate": 8.266637605652143e-06, + "loss": 0.0086, + "step": 36835 + }, + { + "epoch": 11.38, + "learning_rate": 8.266145060032144e-06, + "loss": 0.0103, + "step": 36836 + }, + { + "epoch": 11.38, + "learning_rate": 8.265652518748833e-06, + "loss": 0.0084, + "step": 36837 + }, + { + "epoch": 11.38, + "learning_rate": 8.26515998180344e-06, + "loss": 0.0111, + "step": 36838 + }, + { + "epoch": 11.38, + "learning_rate": 8.264667449197197e-06, + "loss": 0.0086, + "step": 36839 + }, + { + "epoch": 11.38, + "learning_rate": 8.26417492093134e-06, + "loss": 0.0092, + "step": 36840 + }, + { + "epoch": 11.38, + "learning_rate": 8.263682397007096e-06, + "loss": 0.0099, + "step": 36841 + }, + { + "epoch": 11.38, + "learning_rate": 8.263189877425698e-06, + "loss": 0.0092, + "step": 36842 + }, + { + "epoch": 11.38, + "learning_rate": 8.262697362188383e-06, + "loss": 0.0089, + "step": 36843 + }, + { + "epoch": 11.38, + "learning_rate": 8.262204851296375e-06, + "loss": 0.0099, + "step": 36844 + }, + { + "epoch": 11.38, + "learning_rate": 8.261712344750909e-06, + "loss": 0.0088, + "step": 36845 + }, + { + "epoch": 11.38, + "learning_rate": 8.261219842553222e-06, + "loss": 0.0091, + "step": 36846 + }, + { + "epoch": 11.38, + "learning_rate": 8.260727344704538e-06, + "loss": 0.0113, + "step": 36847 + }, + { + "epoch": 11.38, + "learning_rate": 8.260234851206091e-06, + "loss": 0.0096, + "step": 36848 + }, + { + "epoch": 11.38, + "learning_rate": 8.25974236205912e-06, + "loss": 0.0094, + "step": 36849 + }, + { + "epoch": 11.38, + "learning_rate": 8.259249877264844e-06, + "loss": 0.0096, + "step": 36850 + }, + { + "epoch": 11.38, + "learning_rate": 8.258757396824504e-06, + "loss": 0.0112, + "step": 36851 + }, + { + "epoch": 11.38, + "learning_rate": 8.258264920739332e-06, + "loss": 0.01, + "step": 36852 + }, + { + "epoch": 11.38, + "learning_rate": 8.257772449010552e-06, + "loss": 0.0085, + "step": 36853 + }, + { + "epoch": 11.38, + "learning_rate": 8.257279981639404e-06, + "loss": 0.01, + "step": 36854 + }, + { + "epoch": 11.38, + "learning_rate": 8.256787518627116e-06, + "loss": 0.0098, + "step": 36855 + }, + { + "epoch": 11.38, + "learning_rate": 8.256295059974919e-06, + "loss": 0.0091, + "step": 36856 + }, + { + "epoch": 11.38, + "learning_rate": 8.255802605684047e-06, + "loss": 0.011, + "step": 36857 + }, + { + "epoch": 11.38, + "learning_rate": 8.255310155755733e-06, + "loss": 0.0102, + "step": 36858 + }, + { + "epoch": 11.38, + "learning_rate": 8.254817710191206e-06, + "loss": 0.0086, + "step": 36859 + }, + { + "epoch": 11.38, + "learning_rate": 8.254325268991694e-06, + "loss": 0.0081, + "step": 36860 + }, + { + "epoch": 11.38, + "learning_rate": 8.253832832158437e-06, + "loss": 0.0101, + "step": 36861 + }, + { + "epoch": 11.38, + "learning_rate": 8.253340399692663e-06, + "loss": 0.0105, + "step": 36862 + }, + { + "epoch": 11.38, + "learning_rate": 8.252847971595598e-06, + "loss": 0.0104, + "step": 36863 + }, + { + "epoch": 11.38, + "learning_rate": 8.252355547868486e-06, + "loss": 0.0075, + "step": 36864 + }, + { + "epoch": 11.38, + "learning_rate": 8.251863128512547e-06, + "loss": 0.0081, + "step": 36865 + }, + { + "epoch": 11.38, + "learning_rate": 8.251370713529015e-06, + "loss": 0.0104, + "step": 36866 + }, + { + "epoch": 11.39, + "learning_rate": 8.25087830291913e-06, + "loss": 0.0095, + "step": 36867 + }, + { + "epoch": 11.39, + "learning_rate": 8.250385896684115e-06, + "loss": 0.0095, + "step": 36868 + }, + { + "epoch": 11.39, + "learning_rate": 8.249893494825199e-06, + "loss": 0.01, + "step": 36869 + }, + { + "epoch": 11.39, + "learning_rate": 8.249401097343624e-06, + "loss": 0.0092, + "step": 36870 + }, + { + "epoch": 11.39, + "learning_rate": 8.248908704240618e-06, + "loss": 0.0097, + "step": 36871 + }, + { + "epoch": 11.39, + "learning_rate": 8.248416315517407e-06, + "loss": 0.0113, + "step": 36872 + }, + { + "epoch": 11.39, + "learning_rate": 8.247923931175224e-06, + "loss": 0.0107, + "step": 36873 + }, + { + "epoch": 11.39, + "learning_rate": 8.247431551215308e-06, + "loss": 0.0102, + "step": 36874 + }, + { + "epoch": 11.39, + "learning_rate": 8.246939175638884e-06, + "loss": 0.008, + "step": 36875 + }, + { + "epoch": 11.39, + "learning_rate": 8.246446804447182e-06, + "loss": 0.0115, + "step": 36876 + }, + { + "epoch": 11.39, + "learning_rate": 8.245954437641439e-06, + "loss": 0.0096, + "step": 36877 + }, + { + "epoch": 11.39, + "learning_rate": 8.245462075222884e-06, + "loss": 0.0097, + "step": 36878 + }, + { + "epoch": 11.39, + "learning_rate": 8.244969717192746e-06, + "loss": 0.0081, + "step": 36879 + }, + { + "epoch": 11.39, + "learning_rate": 8.244477363552263e-06, + "loss": 0.0101, + "step": 36880 + }, + { + "epoch": 11.39, + "learning_rate": 8.243985014302658e-06, + "loss": 0.0088, + "step": 36881 + }, + { + "epoch": 11.39, + "learning_rate": 8.24349266944517e-06, + "loss": 0.0092, + "step": 36882 + }, + { + "epoch": 11.39, + "learning_rate": 8.243000328981026e-06, + "loss": 0.0091, + "step": 36883 + }, + { + "epoch": 11.39, + "learning_rate": 8.242507992911457e-06, + "loss": 0.0108, + "step": 36884 + }, + { + "epoch": 11.39, + "learning_rate": 8.242015661237696e-06, + "loss": 0.0081, + "step": 36885 + }, + { + "epoch": 11.39, + "learning_rate": 8.24152333396098e-06, + "loss": 0.0091, + "step": 36886 + }, + { + "epoch": 11.39, + "learning_rate": 8.241031011082528e-06, + "loss": 0.0092, + "step": 36887 + }, + { + "epoch": 11.39, + "learning_rate": 8.24053869260358e-06, + "loss": 0.0101, + "step": 36888 + }, + { + "epoch": 11.39, + "learning_rate": 8.240046378525368e-06, + "loss": 0.0082, + "step": 36889 + }, + { + "epoch": 11.39, + "learning_rate": 8.23955406884912e-06, + "loss": 0.0091, + "step": 36890 + }, + { + "epoch": 11.39, + "learning_rate": 8.239061763576065e-06, + "loss": 0.0093, + "step": 36891 + }, + { + "epoch": 11.39, + "learning_rate": 8.238569462707444e-06, + "loss": 0.0091, + "step": 36892 + }, + { + "epoch": 11.39, + "learning_rate": 8.238077166244479e-06, + "loss": 0.0099, + "step": 36893 + }, + { + "epoch": 11.39, + "learning_rate": 8.237584874188402e-06, + "loss": 0.0084, + "step": 36894 + }, + { + "epoch": 11.39, + "learning_rate": 8.23709258654045e-06, + "loss": 0.0093, + "step": 36895 + }, + { + "epoch": 11.39, + "learning_rate": 8.23660030330185e-06, + "loss": 0.0108, + "step": 36896 + }, + { + "epoch": 11.39, + "learning_rate": 8.23610802447383e-06, + "loss": 0.0096, + "step": 36897 + }, + { + "epoch": 11.39, + "learning_rate": 8.235615750057635e-06, + "loss": 0.0097, + "step": 36898 + }, + { + "epoch": 11.4, + "learning_rate": 8.23512348005448e-06, + "loss": 0.0107, + "step": 36899 + }, + { + "epoch": 11.4, + "learning_rate": 8.234631214465604e-06, + "loss": 0.012, + "step": 36900 + }, + { + "epoch": 11.4, + "learning_rate": 8.23413895329224e-06, + "loss": 0.0088, + "step": 36901 + }, + { + "epoch": 11.4, + "learning_rate": 8.23364669653561e-06, + "loss": 0.0102, + "step": 36902 + }, + { + "epoch": 11.4, + "learning_rate": 8.233154444196958e-06, + "loss": 0.0092, + "step": 36903 + }, + { + "epoch": 11.4, + "learning_rate": 8.232662196277505e-06, + "loss": 0.01, + "step": 36904 + }, + { + "epoch": 11.4, + "learning_rate": 8.232169952778491e-06, + "loss": 0.0087, + "step": 36905 + }, + { + "epoch": 11.4, + "learning_rate": 8.231677713701139e-06, + "loss": 0.0091, + "step": 36906 + }, + { + "epoch": 11.4, + "learning_rate": 8.231185479046682e-06, + "loss": 0.0099, + "step": 36907 + }, + { + "epoch": 11.4, + "learning_rate": 8.230693248816358e-06, + "loss": 0.0087, + "step": 36908 + }, + { + "epoch": 11.4, + "learning_rate": 8.230201023011389e-06, + "loss": 0.0091, + "step": 36909 + }, + { + "epoch": 11.4, + "learning_rate": 8.22970880163301e-06, + "loss": 0.008, + "step": 36910 + }, + { + "epoch": 11.4, + "learning_rate": 8.229216584682455e-06, + "loss": 0.0095, + "step": 36911 + }, + { + "epoch": 11.4, + "learning_rate": 8.228724372160948e-06, + "loss": 0.0082, + "step": 36912 + }, + { + "epoch": 11.4, + "learning_rate": 8.228232164069727e-06, + "loss": 0.0085, + "step": 36913 + }, + { + "epoch": 11.4, + "learning_rate": 8.22773996041002e-06, + "loss": 0.0102, + "step": 36914 + }, + { + "epoch": 11.4, + "learning_rate": 8.227247761183058e-06, + "loss": 0.0108, + "step": 36915 + }, + { + "epoch": 11.4, + "learning_rate": 8.226755566390074e-06, + "loss": 0.0109, + "step": 36916 + }, + { + "epoch": 11.4, + "learning_rate": 8.2262633760323e-06, + "loss": 0.0104, + "step": 36917 + }, + { + "epoch": 11.4, + "learning_rate": 8.225771190110959e-06, + "loss": 0.0092, + "step": 36918 + }, + { + "epoch": 11.4, + "learning_rate": 8.22527900862729e-06, + "loss": 0.008, + "step": 36919 + }, + { + "epoch": 11.4, + "learning_rate": 8.224786831582526e-06, + "loss": 0.0115, + "step": 36920 + }, + { + "epoch": 11.4, + "learning_rate": 8.224294658977891e-06, + "loss": 0.0087, + "step": 36921 + }, + { + "epoch": 11.4, + "learning_rate": 8.223802490814615e-06, + "loss": 0.0101, + "step": 36922 + }, + { + "epoch": 11.4, + "learning_rate": 8.223310327093938e-06, + "loss": 0.0095, + "step": 36923 + }, + { + "epoch": 11.4, + "learning_rate": 8.222818167817086e-06, + "loss": 0.0095, + "step": 36924 + }, + { + "epoch": 11.4, + "learning_rate": 8.222326012985285e-06, + "loss": 0.0089, + "step": 36925 + }, + { + "epoch": 11.4, + "learning_rate": 8.221833862599778e-06, + "loss": 0.0092, + "step": 36926 + }, + { + "epoch": 11.4, + "learning_rate": 8.221341716661784e-06, + "loss": 0.0093, + "step": 36927 + }, + { + "epoch": 11.4, + "learning_rate": 8.220849575172537e-06, + "loss": 0.0092, + "step": 36928 + }, + { + "epoch": 11.4, + "learning_rate": 8.220357438133278e-06, + "loss": 0.0097, + "step": 36929 + }, + { + "epoch": 11.4, + "learning_rate": 8.219865305545221e-06, + "loss": 0.0101, + "step": 36930 + }, + { + "epoch": 11.41, + "learning_rate": 8.219373177409608e-06, + "loss": 0.0093, + "step": 36931 + }, + { + "epoch": 11.41, + "learning_rate": 8.21888105372767e-06, + "loss": 0.0093, + "step": 36932 + }, + { + "epoch": 11.41, + "learning_rate": 8.218388934500632e-06, + "loss": 0.0103, + "step": 36933 + }, + { + "epoch": 11.41, + "learning_rate": 8.21789681972973e-06, + "loss": 0.0086, + "step": 36934 + }, + { + "epoch": 11.41, + "learning_rate": 8.21740470941619e-06, + "loss": 0.0113, + "step": 36935 + }, + { + "epoch": 11.41, + "learning_rate": 8.216912603561252e-06, + "loss": 0.0105, + "step": 36936 + }, + { + "epoch": 11.41, + "learning_rate": 8.216420502166137e-06, + "loss": 0.0109, + "step": 36937 + }, + { + "epoch": 11.41, + "learning_rate": 8.215928405232077e-06, + "loss": 0.0099, + "step": 36938 + }, + { + "epoch": 11.41, + "learning_rate": 8.215436312760313e-06, + "loss": 0.0116, + "step": 36939 + }, + { + "epoch": 11.41, + "learning_rate": 8.214944224752063e-06, + "loss": 0.0085, + "step": 36940 + }, + { + "epoch": 11.41, + "learning_rate": 8.214452141208564e-06, + "loss": 0.0085, + "step": 36941 + }, + { + "epoch": 11.41, + "learning_rate": 8.213960062131048e-06, + "loss": 0.01, + "step": 36942 + }, + { + "epoch": 11.41, + "learning_rate": 8.213467987520737e-06, + "loss": 0.0099, + "step": 36943 + }, + { + "epoch": 11.41, + "learning_rate": 8.212975917378873e-06, + "loss": 0.0105, + "step": 36944 + }, + { + "epoch": 11.41, + "learning_rate": 8.212483851706685e-06, + "loss": 0.0094, + "step": 36945 + }, + { + "epoch": 11.41, + "learning_rate": 8.211991790505396e-06, + "loss": 0.009, + "step": 36946 + }, + { + "epoch": 11.41, + "learning_rate": 8.211499733776243e-06, + "loss": 0.0104, + "step": 36947 + }, + { + "epoch": 11.41, + "learning_rate": 8.211007681520459e-06, + "loss": 0.0119, + "step": 36948 + }, + { + "epoch": 11.41, + "learning_rate": 8.210515633739268e-06, + "loss": 0.0112, + "step": 36949 + }, + { + "epoch": 11.41, + "learning_rate": 8.210023590433902e-06, + "loss": 0.009, + "step": 36950 + }, + { + "epoch": 11.41, + "learning_rate": 8.209531551605597e-06, + "loss": 0.0088, + "step": 36951 + }, + { + "epoch": 11.41, + "learning_rate": 8.209039517255578e-06, + "loss": 0.01, + "step": 36952 + }, + { + "epoch": 11.41, + "learning_rate": 8.208547487385075e-06, + "loss": 0.0096, + "step": 36953 + }, + { + "epoch": 11.41, + "learning_rate": 8.208055461995328e-06, + "loss": 0.0107, + "step": 36954 + }, + { + "epoch": 11.41, + "learning_rate": 8.207563441087558e-06, + "loss": 0.0093, + "step": 36955 + }, + { + "epoch": 11.41, + "learning_rate": 8.207071424662996e-06, + "loss": 0.0105, + "step": 36956 + }, + { + "epoch": 11.41, + "learning_rate": 8.20657941272288e-06, + "loss": 0.0084, + "step": 36957 + }, + { + "epoch": 11.41, + "learning_rate": 8.206087405268435e-06, + "loss": 0.0088, + "step": 36958 + }, + { + "epoch": 11.41, + "learning_rate": 8.20559540230089e-06, + "loss": 0.0099, + "step": 36959 + }, + { + "epoch": 11.41, + "learning_rate": 8.205103403821482e-06, + "loss": 0.0107, + "step": 36960 + }, + { + "epoch": 11.41, + "learning_rate": 8.204611409831433e-06, + "loss": 0.0103, + "step": 36961 + }, + { + "epoch": 11.41, + "learning_rate": 8.204119420331982e-06, + "loss": 0.0096, + "step": 36962 + }, + { + "epoch": 11.41, + "learning_rate": 8.203627435324356e-06, + "loss": 0.0106, + "step": 36963 + }, + { + "epoch": 11.42, + "learning_rate": 8.203135454809782e-06, + "loss": 0.011, + "step": 36964 + }, + { + "epoch": 11.42, + "learning_rate": 8.202643478789496e-06, + "loss": 0.009, + "step": 36965 + }, + { + "epoch": 11.42, + "learning_rate": 8.202151507264729e-06, + "loss": 0.0097, + "step": 36966 + }, + { + "epoch": 11.42, + "learning_rate": 8.201659540236703e-06, + "loss": 0.0097, + "step": 36967 + }, + { + "epoch": 11.42, + "learning_rate": 8.201167577706658e-06, + "loss": 0.0098, + "step": 36968 + }, + { + "epoch": 11.42, + "learning_rate": 8.200675619675822e-06, + "loss": 0.009, + "step": 36969 + }, + { + "epoch": 11.42, + "learning_rate": 8.200183666145424e-06, + "loss": 0.0089, + "step": 36970 + }, + { + "epoch": 11.42, + "learning_rate": 8.199691717116693e-06, + "loss": 0.0109, + "step": 36971 + }, + { + "epoch": 11.42, + "learning_rate": 8.199199772590864e-06, + "loss": 0.0088, + "step": 36972 + }, + { + "epoch": 11.42, + "learning_rate": 8.198707832569164e-06, + "loss": 0.011, + "step": 36973 + }, + { + "epoch": 11.42, + "learning_rate": 8.198215897052823e-06, + "loss": 0.0098, + "step": 36974 + }, + { + "epoch": 11.42, + "learning_rate": 8.197723966043073e-06, + "loss": 0.0115, + "step": 36975 + }, + { + "epoch": 11.42, + "learning_rate": 8.197232039541147e-06, + "loss": 0.0123, + "step": 36976 + }, + { + "epoch": 11.42, + "learning_rate": 8.196740117548268e-06, + "loss": 0.0095, + "step": 36977 + }, + { + "epoch": 11.42, + "learning_rate": 8.196248200065671e-06, + "loss": 0.0109, + "step": 36978 + }, + { + "epoch": 11.42, + "learning_rate": 8.195756287094592e-06, + "loss": 0.0101, + "step": 36979 + }, + { + "epoch": 11.42, + "learning_rate": 8.19526437863625e-06, + "loss": 0.0083, + "step": 36980 + }, + { + "epoch": 11.42, + "learning_rate": 8.194772474691882e-06, + "loss": 0.0079, + "step": 36981 + }, + { + "epoch": 11.42, + "learning_rate": 8.19428057526272e-06, + "loss": 0.0111, + "step": 36982 + }, + { + "epoch": 11.42, + "learning_rate": 8.193788680349989e-06, + "loss": 0.0129, + "step": 36983 + }, + { + "epoch": 11.42, + "learning_rate": 8.19329678995492e-06, + "loss": 0.0104, + "step": 36984 + }, + { + "epoch": 11.42, + "learning_rate": 8.192804904078751e-06, + "loss": 0.0093, + "step": 36985 + }, + { + "epoch": 11.42, + "learning_rate": 8.192313022722702e-06, + "loss": 0.0088, + "step": 36986 + }, + { + "epoch": 11.42, + "learning_rate": 8.191821145888007e-06, + "loss": 0.0095, + "step": 36987 + }, + { + "epoch": 11.42, + "learning_rate": 8.191329273575902e-06, + "loss": 0.01, + "step": 36988 + }, + { + "epoch": 11.42, + "learning_rate": 8.190837405787609e-06, + "loss": 0.0101, + "step": 36989 + }, + { + "epoch": 11.42, + "learning_rate": 8.190345542524362e-06, + "loss": 0.0131, + "step": 36990 + }, + { + "epoch": 11.42, + "learning_rate": 8.189853683787393e-06, + "loss": 0.0104, + "step": 36991 + }, + { + "epoch": 11.42, + "learning_rate": 8.189361829577926e-06, + "loss": 0.0091, + "step": 36992 + }, + { + "epoch": 11.42, + "learning_rate": 8.188869979897198e-06, + "loss": 0.0089, + "step": 36993 + }, + { + "epoch": 11.42, + "learning_rate": 8.188378134746438e-06, + "loss": 0.0101, + "step": 36994 + }, + { + "epoch": 11.42, + "learning_rate": 8.18788629412687e-06, + "loss": 0.0105, + "step": 36995 + }, + { + "epoch": 11.43, + "learning_rate": 8.187394458039733e-06, + "loss": 0.0093, + "step": 36996 + }, + { + "epoch": 11.43, + "learning_rate": 8.186902626486252e-06, + "loss": 0.0094, + "step": 36997 + }, + { + "epoch": 11.43, + "learning_rate": 8.186410799467659e-06, + "loss": 0.0083, + "step": 36998 + }, + { + "epoch": 11.43, + "learning_rate": 8.18591897698518e-06, + "loss": 0.0128, + "step": 36999 + }, + { + "epoch": 11.43, + "learning_rate": 8.18542715904005e-06, + "loss": 0.0114, + "step": 37000 + }, + { + "epoch": 11.43, + "learning_rate": 8.1849353456335e-06, + "loss": 0.0094, + "step": 37001 + }, + { + "epoch": 11.43, + "learning_rate": 8.184443536766756e-06, + "loss": 0.0099, + "step": 37002 + }, + { + "epoch": 11.43, + "learning_rate": 8.183951732441049e-06, + "loss": 0.0106, + "step": 37003 + }, + { + "epoch": 11.43, + "learning_rate": 8.183459932657612e-06, + "loss": 0.0091, + "step": 37004 + }, + { + "epoch": 11.43, + "learning_rate": 8.18296813741767e-06, + "loss": 0.0104, + "step": 37005 + }, + { + "epoch": 11.43, + "learning_rate": 8.182476346722459e-06, + "loss": 0.0108, + "step": 37006 + }, + { + "epoch": 11.43, + "learning_rate": 8.181984560573206e-06, + "loss": 0.0093, + "step": 37007 + }, + { + "epoch": 11.43, + "learning_rate": 8.18149277897114e-06, + "loss": 0.01, + "step": 37008 + }, + { + "epoch": 11.43, + "learning_rate": 8.18100100191749e-06, + "loss": 0.0097, + "step": 37009 + }, + { + "epoch": 11.43, + "learning_rate": 8.180509229413494e-06, + "loss": 0.0104, + "step": 37010 + }, + { + "epoch": 11.43, + "learning_rate": 8.180017461460373e-06, + "loss": 0.0096, + "step": 37011 + }, + { + "epoch": 11.43, + "learning_rate": 8.17952569805936e-06, + "loss": 0.0096, + "step": 37012 + }, + { + "epoch": 11.43, + "learning_rate": 8.179033939211687e-06, + "loss": 0.0092, + "step": 37013 + }, + { + "epoch": 11.43, + "learning_rate": 8.17854218491858e-06, + "loss": 0.0097, + "step": 37014 + }, + { + "epoch": 11.43, + "learning_rate": 8.178050435181271e-06, + "loss": 0.0086, + "step": 37015 + }, + { + "epoch": 11.43, + "learning_rate": 8.177558690000994e-06, + "loss": 0.0102, + "step": 37016 + }, + { + "epoch": 11.43, + "learning_rate": 8.177066949378971e-06, + "loss": 0.0105, + "step": 37017 + }, + { + "epoch": 11.43, + "learning_rate": 8.176575213316437e-06, + "loss": 0.0095, + "step": 37018 + }, + { + "epoch": 11.43, + "learning_rate": 8.176083481814624e-06, + "loss": 0.0101, + "step": 37019 + }, + { + "epoch": 11.43, + "learning_rate": 8.175591754874755e-06, + "loss": 0.0111, + "step": 37020 + }, + { + "epoch": 11.43, + "learning_rate": 8.175100032498063e-06, + "loss": 0.0109, + "step": 37021 + }, + { + "epoch": 11.43, + "learning_rate": 8.174608314685784e-06, + "loss": 0.0118, + "step": 37022 + }, + { + "epoch": 11.43, + "learning_rate": 8.174116601439136e-06, + "loss": 0.0107, + "step": 37023 + }, + { + "epoch": 11.43, + "learning_rate": 8.17362489275936e-06, + "loss": 0.0095, + "step": 37024 + }, + { + "epoch": 11.43, + "learning_rate": 8.173133188647681e-06, + "loss": 0.0099, + "step": 37025 + }, + { + "epoch": 11.43, + "learning_rate": 8.172641489105326e-06, + "loss": 0.01, + "step": 37026 + }, + { + "epoch": 11.43, + "learning_rate": 8.17214979413353e-06, + "loss": 0.0093, + "step": 37027 + }, + { + "epoch": 11.43, + "learning_rate": 8.171658103733523e-06, + "loss": 0.0106, + "step": 37028 + }, + { + "epoch": 11.44, + "learning_rate": 8.17116641790653e-06, + "loss": 0.0091, + "step": 37029 + }, + { + "epoch": 11.44, + "learning_rate": 8.17067473665378e-06, + "loss": 0.0094, + "step": 37030 + }, + { + "epoch": 11.44, + "learning_rate": 8.170183059976513e-06, + "loss": 0.0079, + "step": 37031 + }, + { + "epoch": 11.44, + "learning_rate": 8.169691387875949e-06, + "loss": 0.0099, + "step": 37032 + }, + { + "epoch": 11.44, + "learning_rate": 8.169199720353317e-06, + "loss": 0.0106, + "step": 37033 + }, + { + "epoch": 11.44, + "learning_rate": 8.168708057409854e-06, + "loss": 0.0111, + "step": 37034 + }, + { + "epoch": 11.44, + "learning_rate": 8.168216399046787e-06, + "loss": 0.0103, + "step": 37035 + }, + { + "epoch": 11.44, + "learning_rate": 8.167724745265342e-06, + "loss": 0.0096, + "step": 37036 + }, + { + "epoch": 11.44, + "learning_rate": 8.167233096066754e-06, + "loss": 0.0102, + "step": 37037 + }, + { + "epoch": 11.44, + "learning_rate": 8.166741451452252e-06, + "loss": 0.0099, + "step": 37038 + }, + { + "epoch": 11.44, + "learning_rate": 8.166249811423061e-06, + "loss": 0.0096, + "step": 37039 + }, + { + "epoch": 11.44, + "learning_rate": 8.165758175980411e-06, + "loss": 0.0094, + "step": 37040 + }, + { + "epoch": 11.44, + "learning_rate": 8.165266545125541e-06, + "loss": 0.0094, + "step": 37041 + }, + { + "epoch": 11.44, + "learning_rate": 8.16477491885967e-06, + "loss": 0.0095, + "step": 37042 + }, + { + "epoch": 11.44, + "learning_rate": 8.16428329718403e-06, + "loss": 0.0094, + "step": 37043 + }, + { + "epoch": 11.44, + "learning_rate": 8.163791680099857e-06, + "loss": 0.0093, + "step": 37044 + }, + { + "epoch": 11.44, + "learning_rate": 8.163300067608374e-06, + "loss": 0.0088, + "step": 37045 + }, + { + "epoch": 11.44, + "learning_rate": 8.16280845971081e-06, + "loss": 0.0093, + "step": 37046 + }, + { + "epoch": 11.44, + "learning_rate": 8.162316856408403e-06, + "loss": 0.0104, + "step": 37047 + }, + { + "epoch": 11.44, + "learning_rate": 8.16182525770237e-06, + "loss": 0.0083, + "step": 37048 + }, + { + "epoch": 11.44, + "learning_rate": 8.16133366359395e-06, + "loss": 0.011, + "step": 37049 + }, + { + "epoch": 11.44, + "learning_rate": 8.160842074084373e-06, + "loss": 0.0087, + "step": 37050 + }, + { + "epoch": 11.44, + "learning_rate": 8.16035048917486e-06, + "loss": 0.0079, + "step": 37051 + }, + { + "epoch": 11.44, + "learning_rate": 8.159858908866649e-06, + "loss": 0.0104, + "step": 37052 + }, + { + "epoch": 11.44, + "learning_rate": 8.159367333160969e-06, + "loss": 0.0093, + "step": 37053 + }, + { + "epoch": 11.44, + "learning_rate": 8.15887576205904e-06, + "loss": 0.0108, + "step": 37054 + }, + { + "epoch": 11.44, + "learning_rate": 8.158384195562102e-06, + "loss": 0.01, + "step": 37055 + }, + { + "epoch": 11.44, + "learning_rate": 8.157892633671384e-06, + "loss": 0.0096, + "step": 37056 + }, + { + "epoch": 11.44, + "learning_rate": 8.15740107638811e-06, + "loss": 0.0093, + "step": 37057 + }, + { + "epoch": 11.44, + "learning_rate": 8.15690952371351e-06, + "loss": 0.0141, + "step": 37058 + }, + { + "epoch": 11.44, + "learning_rate": 8.156417975648819e-06, + "loss": 0.0103, + "step": 37059 + }, + { + "epoch": 11.44, + "learning_rate": 8.155926432195262e-06, + "loss": 0.011, + "step": 37060 + }, + { + "epoch": 11.45, + "learning_rate": 8.155434893354067e-06, + "loss": 0.0093, + "step": 37061 + }, + { + "epoch": 11.45, + "learning_rate": 8.154943359126469e-06, + "loss": 0.011, + "step": 37062 + }, + { + "epoch": 11.45, + "learning_rate": 8.154451829513693e-06, + "loss": 0.0104, + "step": 37063 + }, + { + "epoch": 11.45, + "learning_rate": 8.153960304516966e-06, + "loss": 0.0098, + "step": 37064 + }, + { + "epoch": 11.45, + "learning_rate": 8.153468784137524e-06, + "loss": 0.0086, + "step": 37065 + }, + { + "epoch": 11.45, + "learning_rate": 8.152977268376596e-06, + "loss": 0.0087, + "step": 37066 + }, + { + "epoch": 11.45, + "learning_rate": 8.152485757235404e-06, + "loss": 0.0098, + "step": 37067 + }, + { + "epoch": 11.45, + "learning_rate": 8.151994250715182e-06, + "loss": 0.0122, + "step": 37068 + }, + { + "epoch": 11.45, + "learning_rate": 8.151502748817165e-06, + "loss": 0.0113, + "step": 37069 + }, + { + "epoch": 11.45, + "learning_rate": 8.151011251542574e-06, + "loss": 0.0102, + "step": 37070 + }, + { + "epoch": 11.45, + "learning_rate": 8.150519758892638e-06, + "loss": 0.0112, + "step": 37071 + }, + { + "epoch": 11.45, + "learning_rate": 8.150028270868593e-06, + "loss": 0.0087, + "step": 37072 + }, + { + "epoch": 11.45, + "learning_rate": 8.149536787471663e-06, + "loss": 0.0096, + "step": 37073 + }, + { + "epoch": 11.45, + "learning_rate": 8.149045308703078e-06, + "loss": 0.0104, + "step": 37074 + }, + { + "epoch": 11.45, + "learning_rate": 8.148553834564072e-06, + "loss": 0.0107, + "step": 37075 + }, + { + "epoch": 11.45, + "learning_rate": 8.14806236505587e-06, + "loss": 0.0107, + "step": 37076 + }, + { + "epoch": 11.45, + "learning_rate": 8.147570900179698e-06, + "loss": 0.0092, + "step": 37077 + }, + { + "epoch": 11.45, + "learning_rate": 8.147079439936795e-06, + "loss": 0.0098, + "step": 37078 + }, + { + "epoch": 11.45, + "learning_rate": 8.146587984328377e-06, + "loss": 0.0094, + "step": 37079 + }, + { + "epoch": 11.45, + "learning_rate": 8.146096533355685e-06, + "loss": 0.0094, + "step": 37080 + }, + { + "epoch": 11.45, + "learning_rate": 8.145605087019944e-06, + "loss": 0.0083, + "step": 37081 + }, + { + "epoch": 11.45, + "learning_rate": 8.14511364532238e-06, + "loss": 0.0105, + "step": 37082 + }, + { + "epoch": 11.45, + "learning_rate": 8.144622208264226e-06, + "loss": 0.0097, + "step": 37083 + }, + { + "epoch": 11.45, + "learning_rate": 8.144130775846714e-06, + "loss": 0.0111, + "step": 37084 + }, + { + "epoch": 11.45, + "learning_rate": 8.143639348071064e-06, + "loss": 0.0093, + "step": 37085 + }, + { + "epoch": 11.45, + "learning_rate": 8.143147924938513e-06, + "loss": 0.0085, + "step": 37086 + }, + { + "epoch": 11.45, + "learning_rate": 8.14265650645029e-06, + "loss": 0.0106, + "step": 37087 + }, + { + "epoch": 11.45, + "learning_rate": 8.142165092607619e-06, + "loss": 0.0093, + "step": 37088 + }, + { + "epoch": 11.45, + "learning_rate": 8.14167368341173e-06, + "loss": 0.0097, + "step": 37089 + }, + { + "epoch": 11.45, + "learning_rate": 8.14118227886386e-06, + "loss": 0.0114, + "step": 37090 + }, + { + "epoch": 11.45, + "learning_rate": 8.140690878965228e-06, + "loss": 0.0103, + "step": 37091 + }, + { + "epoch": 11.45, + "learning_rate": 8.140199483717066e-06, + "loss": 0.0094, + "step": 37092 + }, + { + "epoch": 11.46, + "learning_rate": 8.139708093120608e-06, + "loss": 0.0102, + "step": 37093 + }, + { + "epoch": 11.46, + "learning_rate": 8.139216707177078e-06, + "loss": 0.0084, + "step": 37094 + }, + { + "epoch": 11.46, + "learning_rate": 8.138725325887702e-06, + "loss": 0.0098, + "step": 37095 + }, + { + "epoch": 11.46, + "learning_rate": 8.138233949253723e-06, + "loss": 0.0098, + "step": 37096 + }, + { + "epoch": 11.46, + "learning_rate": 8.137742577276354e-06, + "loss": 0.0099, + "step": 37097 + }, + { + "epoch": 11.46, + "learning_rate": 8.13725120995683e-06, + "loss": 0.0087, + "step": 37098 + }, + { + "epoch": 11.46, + "learning_rate": 8.136759847296379e-06, + "loss": 0.01, + "step": 37099 + }, + { + "epoch": 11.46, + "learning_rate": 8.136268489296237e-06, + "loss": 0.0092, + "step": 37100 + }, + { + "epoch": 11.46, + "learning_rate": 8.135777135957624e-06, + "loss": 0.0103, + "step": 37101 + }, + { + "epoch": 11.46, + "learning_rate": 8.135285787281772e-06, + "loss": 0.0097, + "step": 37102 + }, + { + "epoch": 11.46, + "learning_rate": 8.134794443269913e-06, + "loss": 0.0094, + "step": 37103 + }, + { + "epoch": 11.46, + "learning_rate": 8.134303103923271e-06, + "loss": 0.0094, + "step": 37104 + }, + { + "epoch": 11.46, + "learning_rate": 8.133811769243076e-06, + "loss": 0.0099, + "step": 37105 + }, + { + "epoch": 11.46, + "learning_rate": 8.133320439230565e-06, + "loss": 0.0104, + "step": 37106 + }, + { + "epoch": 11.46, + "learning_rate": 8.132829113886953e-06, + "loss": 0.0098, + "step": 37107 + }, + { + "epoch": 11.46, + "learning_rate": 8.132337793213478e-06, + "loss": 0.0099, + "step": 37108 + }, + { + "epoch": 11.46, + "learning_rate": 8.131846477211367e-06, + "loss": 0.0098, + "step": 37109 + }, + { + "epoch": 11.46, + "learning_rate": 8.131355165881848e-06, + "loss": 0.0095, + "step": 37110 + }, + { + "epoch": 11.46, + "learning_rate": 8.13086385922615e-06, + "loss": 0.0092, + "step": 37111 + }, + { + "epoch": 11.46, + "learning_rate": 8.130372557245506e-06, + "loss": 0.0105, + "step": 37112 + }, + { + "epoch": 11.46, + "learning_rate": 8.129881259941136e-06, + "loss": 0.0096, + "step": 37113 + }, + { + "epoch": 11.46, + "learning_rate": 8.129389967314277e-06, + "loss": 0.0095, + "step": 37114 + }, + { + "epoch": 11.46, + "learning_rate": 8.128898679366157e-06, + "loss": 0.0086, + "step": 37115 + }, + { + "epoch": 11.46, + "learning_rate": 8.128407396098001e-06, + "loss": 0.0108, + "step": 37116 + }, + { + "epoch": 11.46, + "learning_rate": 8.127916117511037e-06, + "loss": 0.01, + "step": 37117 + }, + { + "epoch": 11.46, + "learning_rate": 8.1274248436065e-06, + "loss": 0.0109, + "step": 37118 + }, + { + "epoch": 11.46, + "learning_rate": 8.126933574385612e-06, + "loss": 0.0091, + "step": 37119 + }, + { + "epoch": 11.46, + "learning_rate": 8.126442309849604e-06, + "loss": 0.0096, + "step": 37120 + }, + { + "epoch": 11.46, + "learning_rate": 8.12595104999971e-06, + "loss": 0.0123, + "step": 37121 + }, + { + "epoch": 11.46, + "learning_rate": 8.125459794837152e-06, + "loss": 0.0097, + "step": 37122 + }, + { + "epoch": 11.46, + "learning_rate": 8.124968544363157e-06, + "loss": 0.01, + "step": 37123 + }, + { + "epoch": 11.46, + "learning_rate": 8.124477298578963e-06, + "loss": 0.0107, + "step": 37124 + }, + { + "epoch": 11.46, + "learning_rate": 8.123986057485792e-06, + "loss": 0.0093, + "step": 37125 + }, + { + "epoch": 11.47, + "learning_rate": 8.123494821084874e-06, + "loss": 0.0101, + "step": 37126 + }, + { + "epoch": 11.47, + "learning_rate": 8.123003589377439e-06, + "loss": 0.0103, + "step": 37127 + }, + { + "epoch": 11.47, + "learning_rate": 8.12251236236471e-06, + "loss": 0.009, + "step": 37128 + }, + { + "epoch": 11.47, + "learning_rate": 8.122021140047921e-06, + "loss": 0.0092, + "step": 37129 + }, + { + "epoch": 11.47, + "learning_rate": 8.121529922428305e-06, + "loss": 0.0122, + "step": 37130 + }, + { + "epoch": 11.47, + "learning_rate": 8.121038709507078e-06, + "loss": 0.0104, + "step": 37131 + }, + { + "epoch": 11.47, + "learning_rate": 8.12054750128548e-06, + "loss": 0.0113, + "step": 37132 + }, + { + "epoch": 11.47, + "learning_rate": 8.120056297764734e-06, + "loss": 0.0093, + "step": 37133 + }, + { + "epoch": 11.47, + "learning_rate": 8.119565098946073e-06, + "loss": 0.0087, + "step": 37134 + }, + { + "epoch": 11.47, + "learning_rate": 8.11907390483072e-06, + "loss": 0.0102, + "step": 37135 + }, + { + "epoch": 11.47, + "learning_rate": 8.118582715419905e-06, + "loss": 0.0128, + "step": 37136 + }, + { + "epoch": 11.47, + "learning_rate": 8.118091530714863e-06, + "loss": 0.0111, + "step": 37137 + }, + { + "epoch": 11.47, + "learning_rate": 8.117600350716812e-06, + "loss": 0.01, + "step": 37138 + }, + { + "epoch": 11.47, + "learning_rate": 8.117109175426988e-06, + "loss": 0.0096, + "step": 37139 + }, + { + "epoch": 11.47, + "learning_rate": 8.11661800484662e-06, + "loss": 0.01, + "step": 37140 + }, + { + "epoch": 11.47, + "learning_rate": 8.116126838976928e-06, + "loss": 0.0101, + "step": 37141 + }, + { + "epoch": 11.47, + "learning_rate": 8.115635677819149e-06, + "loss": 0.0103, + "step": 37142 + }, + { + "epoch": 11.47, + "learning_rate": 8.115144521374512e-06, + "loss": 0.0084, + "step": 37143 + }, + { + "epoch": 11.47, + "learning_rate": 8.114653369644238e-06, + "loss": 0.0093, + "step": 37144 + }, + { + "epoch": 11.47, + "learning_rate": 8.11416222262956e-06, + "loss": 0.0091, + "step": 37145 + }, + { + "epoch": 11.47, + "learning_rate": 8.113671080331711e-06, + "loss": 0.0102, + "step": 37146 + }, + { + "epoch": 11.47, + "learning_rate": 8.11317994275191e-06, + "loss": 0.0101, + "step": 37147 + }, + { + "epoch": 11.47, + "learning_rate": 8.112688809891391e-06, + "loss": 0.0091, + "step": 37148 + }, + { + "epoch": 11.47, + "learning_rate": 8.112197681751383e-06, + "loss": 0.0105, + "step": 37149 + }, + { + "epoch": 11.47, + "learning_rate": 8.111706558333113e-06, + "loss": 0.0082, + "step": 37150 + }, + { + "epoch": 11.47, + "learning_rate": 8.111215439637805e-06, + "loss": 0.0101, + "step": 37151 + }, + { + "epoch": 11.47, + "learning_rate": 8.110724325666696e-06, + "loss": 0.0104, + "step": 37152 + }, + { + "epoch": 11.47, + "learning_rate": 8.11023321642101e-06, + "loss": 0.0109, + "step": 37153 + }, + { + "epoch": 11.47, + "learning_rate": 8.109742111901971e-06, + "loss": 0.0104, + "step": 37154 + }, + { + "epoch": 11.47, + "learning_rate": 8.10925101211082e-06, + "loss": 0.0137, + "step": 37155 + }, + { + "epoch": 11.47, + "learning_rate": 8.108759917048769e-06, + "loss": 0.0107, + "step": 37156 + }, + { + "epoch": 11.47, + "learning_rate": 8.108268826717058e-06, + "loss": 0.0088, + "step": 37157 + }, + { + "epoch": 11.48, + "learning_rate": 8.107777741116913e-06, + "loss": 0.0115, + "step": 37158 + }, + { + "epoch": 11.48, + "learning_rate": 8.107286660249558e-06, + "loss": 0.0094, + "step": 37159 + }, + { + "epoch": 11.48, + "learning_rate": 8.106795584116226e-06, + "loss": 0.0098, + "step": 37160 + }, + { + "epoch": 11.48, + "learning_rate": 8.106304512718143e-06, + "loss": 0.0082, + "step": 37161 + }, + { + "epoch": 11.48, + "learning_rate": 8.105813446056535e-06, + "loss": 0.0095, + "step": 37162 + }, + { + "epoch": 11.48, + "learning_rate": 8.105322384132637e-06, + "loss": 0.0102, + "step": 37163 + }, + { + "epoch": 11.48, + "learning_rate": 8.10483132694767e-06, + "loss": 0.0099, + "step": 37164 + }, + { + "epoch": 11.48, + "learning_rate": 8.104340274502872e-06, + "loss": 0.0092, + "step": 37165 + }, + { + "epoch": 11.48, + "learning_rate": 8.10384922679946e-06, + "loss": 0.0089, + "step": 37166 + }, + { + "epoch": 11.48, + "learning_rate": 8.103358183838665e-06, + "loss": 0.0112, + "step": 37167 + }, + { + "epoch": 11.48, + "learning_rate": 8.102867145621721e-06, + "loss": 0.0106, + "step": 37168 + }, + { + "epoch": 11.48, + "learning_rate": 8.102376112149849e-06, + "loss": 0.0104, + "step": 37169 + }, + { + "epoch": 11.48, + "learning_rate": 8.101885083424282e-06, + "loss": 0.0086, + "step": 37170 + }, + { + "epoch": 11.48, + "learning_rate": 8.101394059446248e-06, + "loss": 0.01, + "step": 37171 + }, + { + "epoch": 11.48, + "learning_rate": 8.10090304021697e-06, + "loss": 0.0112, + "step": 37172 + }, + { + "epoch": 11.48, + "learning_rate": 8.100412025737683e-06, + "loss": 0.0104, + "step": 37173 + }, + { + "epoch": 11.48, + "learning_rate": 8.099921016009613e-06, + "loss": 0.0102, + "step": 37174 + }, + { + "epoch": 11.48, + "learning_rate": 8.099430011033984e-06, + "loss": 0.0092, + "step": 37175 + }, + { + "epoch": 11.48, + "learning_rate": 8.098939010812028e-06, + "loss": 0.0103, + "step": 37176 + }, + { + "epoch": 11.48, + "learning_rate": 8.098448015344976e-06, + "loss": 0.0093, + "step": 37177 + }, + { + "epoch": 11.48, + "learning_rate": 8.09795702463405e-06, + "loss": 0.0098, + "step": 37178 + }, + { + "epoch": 11.48, + "learning_rate": 8.097466038680475e-06, + "loss": 0.0098, + "step": 37179 + }, + { + "epoch": 11.48, + "learning_rate": 8.096975057485492e-06, + "loss": 0.0099, + "step": 37180 + }, + { + "epoch": 11.48, + "learning_rate": 8.096484081050317e-06, + "loss": 0.0103, + "step": 37181 + }, + { + "epoch": 11.48, + "learning_rate": 8.095993109376183e-06, + "loss": 0.0092, + "step": 37182 + }, + { + "epoch": 11.48, + "learning_rate": 8.095502142464319e-06, + "loss": 0.0112, + "step": 37183 + }, + { + "epoch": 11.48, + "learning_rate": 8.095011180315953e-06, + "loss": 0.01, + "step": 37184 + }, + { + "epoch": 11.48, + "learning_rate": 8.094520222932305e-06, + "loss": 0.0102, + "step": 37185 + }, + { + "epoch": 11.48, + "learning_rate": 8.094029270314619e-06, + "loss": 0.012, + "step": 37186 + }, + { + "epoch": 11.48, + "learning_rate": 8.093538322464107e-06, + "loss": 0.0117, + "step": 37187 + }, + { + "epoch": 11.48, + "learning_rate": 8.093047379382004e-06, + "loss": 0.0104, + "step": 37188 + }, + { + "epoch": 11.48, + "learning_rate": 8.092556441069542e-06, + "loss": 0.0103, + "step": 37189 + }, + { + "epoch": 11.48, + "learning_rate": 8.092065507527936e-06, + "loss": 0.0104, + "step": 37190 + }, + { + "epoch": 11.49, + "learning_rate": 8.091574578758427e-06, + "loss": 0.0104, + "step": 37191 + }, + { + "epoch": 11.49, + "learning_rate": 8.09108365476224e-06, + "loss": 0.0104, + "step": 37192 + }, + { + "epoch": 11.49, + "learning_rate": 8.090592735540596e-06, + "loss": 0.0101, + "step": 37193 + }, + { + "epoch": 11.49, + "learning_rate": 8.09010182109473e-06, + "loss": 0.0102, + "step": 37194 + }, + { + "epoch": 11.49, + "learning_rate": 8.08961091142587e-06, + "loss": 0.0102, + "step": 37195 + }, + { + "epoch": 11.49, + "learning_rate": 8.089120006535239e-06, + "loss": 0.0096, + "step": 37196 + }, + { + "epoch": 11.49, + "learning_rate": 8.088629106424066e-06, + "loss": 0.0104, + "step": 37197 + }, + { + "epoch": 11.49, + "learning_rate": 8.08813821109358e-06, + "loss": 0.0106, + "step": 37198 + }, + { + "epoch": 11.49, + "learning_rate": 8.087647320545015e-06, + "loss": 0.0097, + "step": 37199 + }, + { + "epoch": 11.49, + "learning_rate": 8.087156434779587e-06, + "loss": 0.0097, + "step": 37200 + }, + { + "epoch": 11.49, + "learning_rate": 8.086665553798531e-06, + "loss": 0.0102, + "step": 37201 + }, + { + "epoch": 11.49, + "learning_rate": 8.086174677603076e-06, + "loss": 0.0097, + "step": 37202 + }, + { + "epoch": 11.49, + "learning_rate": 8.085683806194443e-06, + "loss": 0.0111, + "step": 37203 + }, + { + "epoch": 11.49, + "learning_rate": 8.085192939573867e-06, + "loss": 0.0107, + "step": 37204 + }, + { + "epoch": 11.49, + "learning_rate": 8.084702077742574e-06, + "loss": 0.0106, + "step": 37205 + }, + { + "epoch": 11.49, + "learning_rate": 8.084211220701788e-06, + "loss": 0.0095, + "step": 37206 + }, + { + "epoch": 11.49, + "learning_rate": 8.083720368452737e-06, + "loss": 0.0109, + "step": 37207 + }, + { + "epoch": 11.49, + "learning_rate": 8.083229520996656e-06, + "loss": 0.012, + "step": 37208 + }, + { + "epoch": 11.49, + "learning_rate": 8.082738678334764e-06, + "loss": 0.009, + "step": 37209 + }, + { + "epoch": 11.49, + "learning_rate": 8.082247840468292e-06, + "loss": 0.0082, + "step": 37210 + }, + { + "epoch": 11.49, + "learning_rate": 8.08175700739847e-06, + "loss": 0.01, + "step": 37211 + }, + { + "epoch": 11.49, + "learning_rate": 8.081266179126522e-06, + "loss": 0.0097, + "step": 37212 + }, + { + "epoch": 11.49, + "learning_rate": 8.080775355653677e-06, + "loss": 0.0115, + "step": 37213 + }, + { + "epoch": 11.49, + "learning_rate": 8.080284536981164e-06, + "loss": 0.0102, + "step": 37214 + }, + { + "epoch": 11.49, + "learning_rate": 8.07979372311021e-06, + "loss": 0.0098, + "step": 37215 + }, + { + "epoch": 11.49, + "learning_rate": 8.079302914042042e-06, + "loss": 0.0107, + "step": 37216 + }, + { + "epoch": 11.49, + "learning_rate": 8.07881210977789e-06, + "loss": 0.0078, + "step": 37217 + }, + { + "epoch": 11.49, + "learning_rate": 8.078321310318973e-06, + "loss": 0.0115, + "step": 37218 + }, + { + "epoch": 11.49, + "learning_rate": 8.077830515666527e-06, + "loss": 0.0087, + "step": 37219 + }, + { + "epoch": 11.49, + "learning_rate": 8.077339725821782e-06, + "loss": 0.0105, + "step": 37220 + }, + { + "epoch": 11.49, + "learning_rate": 8.076848940785955e-06, + "loss": 0.0092, + "step": 37221 + }, + { + "epoch": 11.49, + "learning_rate": 8.076358160560282e-06, + "loss": 0.0088, + "step": 37222 + }, + { + "epoch": 11.5, + "learning_rate": 8.075867385145991e-06, + "loss": 0.0121, + "step": 37223 + }, + { + "epoch": 11.5, + "learning_rate": 8.075376614544302e-06, + "loss": 0.0093, + "step": 37224 + }, + { + "epoch": 11.5, + "learning_rate": 8.07488584875645e-06, + "loss": 0.0107, + "step": 37225 + }, + { + "epoch": 11.5, + "learning_rate": 8.07439508778366e-06, + "loss": 0.0087, + "step": 37226 + }, + { + "epoch": 11.5, + "learning_rate": 8.073904331627158e-06, + "loss": 0.0111, + "step": 37227 + }, + { + "epoch": 11.5, + "learning_rate": 8.07341358028817e-06, + "loss": 0.0105, + "step": 37228 + }, + { + "epoch": 11.5, + "learning_rate": 8.072922833767929e-06, + "loss": 0.0106, + "step": 37229 + }, + { + "epoch": 11.5, + "learning_rate": 8.072432092067662e-06, + "loss": 0.0107, + "step": 37230 + }, + { + "epoch": 11.5, + "learning_rate": 8.071941355188588e-06, + "loss": 0.0094, + "step": 37231 + }, + { + "epoch": 11.5, + "learning_rate": 8.071450623131943e-06, + "loss": 0.0099, + "step": 37232 + }, + { + "epoch": 11.5, + "learning_rate": 8.070959895898953e-06, + "loss": 0.0104, + "step": 37233 + }, + { + "epoch": 11.5, + "learning_rate": 8.070469173490842e-06, + "loss": 0.0095, + "step": 37234 + }, + { + "epoch": 11.5, + "learning_rate": 8.06997845590884e-06, + "loss": 0.0101, + "step": 37235 + }, + { + "epoch": 11.5, + "learning_rate": 8.069487743154176e-06, + "loss": 0.01, + "step": 37236 + }, + { + "epoch": 11.5, + "learning_rate": 8.068997035228075e-06, + "loss": 0.012, + "step": 37237 + }, + { + "epoch": 11.5, + "learning_rate": 8.06850633213176e-06, + "loss": 0.0115, + "step": 37238 + }, + { + "epoch": 11.5, + "learning_rate": 8.068015633866468e-06, + "loss": 0.0135, + "step": 37239 + }, + { + "epoch": 11.5, + "learning_rate": 8.06752494043342e-06, + "loss": 0.0109, + "step": 37240 + }, + { + "epoch": 11.5, + "learning_rate": 8.067034251833841e-06, + "loss": 0.0126, + "step": 37241 + }, + { + "epoch": 11.5, + "learning_rate": 8.066543568068967e-06, + "loss": 0.0097, + "step": 37242 + }, + { + "epoch": 11.5, + "learning_rate": 8.06605288914002e-06, + "loss": 0.0108, + "step": 37243 + }, + { + "epoch": 11.5, + "learning_rate": 8.065562215048223e-06, + "loss": 0.0099, + "step": 37244 + }, + { + "epoch": 11.5, + "learning_rate": 8.065071545794813e-06, + "loss": 0.0111, + "step": 37245 + }, + { + "epoch": 11.5, + "learning_rate": 8.064580881381008e-06, + "loss": 0.0126, + "step": 37246 + }, + { + "epoch": 11.5, + "learning_rate": 8.064090221808041e-06, + "loss": 0.0097, + "step": 37247 + }, + { + "epoch": 11.5, + "learning_rate": 8.063599567077138e-06, + "loss": 0.0109, + "step": 37248 + }, + { + "epoch": 11.5, + "learning_rate": 8.063108917189523e-06, + "loss": 0.0101, + "step": 37249 + }, + { + "epoch": 11.5, + "learning_rate": 8.062618272146428e-06, + "loss": 0.0096, + "step": 37250 + }, + { + "epoch": 11.5, + "learning_rate": 8.062127631949079e-06, + "loss": 0.0095, + "step": 37251 + }, + { + "epoch": 11.5, + "learning_rate": 8.061636996598699e-06, + "loss": 0.0102, + "step": 37252 + }, + { + "epoch": 11.5, + "learning_rate": 8.061146366096519e-06, + "loss": 0.0097, + "step": 37253 + }, + { + "epoch": 11.5, + "learning_rate": 8.06065574044377e-06, + "loss": 0.0097, + "step": 37254 + }, + { + "epoch": 11.51, + "learning_rate": 8.060165119641671e-06, + "loss": 0.0089, + "step": 37255 + }, + { + "epoch": 11.51, + "learning_rate": 8.059674503691451e-06, + "loss": 0.0093, + "step": 37256 + }, + { + "epoch": 11.51, + "learning_rate": 8.059183892594344e-06, + "loss": 0.0086, + "step": 37257 + }, + { + "epoch": 11.51, + "learning_rate": 8.058693286351569e-06, + "loss": 0.0111, + "step": 37258 + }, + { + "epoch": 11.51, + "learning_rate": 8.058202684964354e-06, + "loss": 0.0109, + "step": 37259 + }, + { + "epoch": 11.51, + "learning_rate": 8.057712088433933e-06, + "loss": 0.0114, + "step": 37260 + }, + { + "epoch": 11.51, + "learning_rate": 8.057221496761526e-06, + "loss": 0.01, + "step": 37261 + }, + { + "epoch": 11.51, + "learning_rate": 8.05673090994836e-06, + "loss": 0.0112, + "step": 37262 + }, + { + "epoch": 11.51, + "learning_rate": 8.056240327995667e-06, + "loss": 0.0098, + "step": 37263 + }, + { + "epoch": 11.51, + "learning_rate": 8.055749750904673e-06, + "loss": 0.0095, + "step": 37264 + }, + { + "epoch": 11.51, + "learning_rate": 8.055259178676603e-06, + "loss": 0.0087, + "step": 37265 + }, + { + "epoch": 11.51, + "learning_rate": 8.05476861131268e-06, + "loss": 0.011, + "step": 37266 + }, + { + "epoch": 11.51, + "learning_rate": 8.054278048814141e-06, + "loss": 0.0095, + "step": 37267 + }, + { + "epoch": 11.51, + "learning_rate": 8.053787491182206e-06, + "loss": 0.0093, + "step": 37268 + }, + { + "epoch": 11.51, + "learning_rate": 8.0532969384181e-06, + "loss": 0.0112, + "step": 37269 + }, + { + "epoch": 11.51, + "learning_rate": 8.052806390523058e-06, + "loss": 0.01, + "step": 37270 + }, + { + "epoch": 11.51, + "learning_rate": 8.0523158474983e-06, + "loss": 0.0123, + "step": 37271 + }, + { + "epoch": 11.51, + "learning_rate": 8.051825309345053e-06, + "loss": 0.0104, + "step": 37272 + }, + { + "epoch": 11.51, + "learning_rate": 8.051334776064553e-06, + "loss": 0.0091, + "step": 37273 + }, + { + "epoch": 11.51, + "learning_rate": 8.050844247658017e-06, + "loss": 0.0088, + "step": 37274 + }, + { + "epoch": 11.51, + "learning_rate": 8.050353724126672e-06, + "loss": 0.01, + "step": 37275 + }, + { + "epoch": 11.51, + "learning_rate": 8.049863205471752e-06, + "loss": 0.0131, + "step": 37276 + }, + { + "epoch": 11.51, + "learning_rate": 8.049372691694477e-06, + "loss": 0.0108, + "step": 37277 + }, + { + "epoch": 11.51, + "learning_rate": 8.048882182796077e-06, + "loss": 0.0086, + "step": 37278 + }, + { + "epoch": 11.51, + "learning_rate": 8.048391678777782e-06, + "loss": 0.0094, + "step": 37279 + }, + { + "epoch": 11.51, + "learning_rate": 8.04790117964081e-06, + "loss": 0.0113, + "step": 37280 + }, + { + "epoch": 11.51, + "learning_rate": 8.047410685386395e-06, + "loss": 0.0122, + "step": 37281 + }, + { + "epoch": 11.51, + "learning_rate": 8.046920196015766e-06, + "loss": 0.0091, + "step": 37282 + }, + { + "epoch": 11.51, + "learning_rate": 8.04642971153014e-06, + "loss": 0.0106, + "step": 37283 + }, + { + "epoch": 11.51, + "learning_rate": 8.045939231930752e-06, + "loss": 0.0097, + "step": 37284 + }, + { + "epoch": 11.51, + "learning_rate": 8.045448757218827e-06, + "loss": 0.0095, + "step": 37285 + }, + { + "epoch": 11.51, + "learning_rate": 8.044958287395592e-06, + "loss": 0.0096, + "step": 37286 + }, + { + "epoch": 11.51, + "learning_rate": 8.04446782246227e-06, + "loss": 0.0113, + "step": 37287 + }, + { + "epoch": 11.52, + "learning_rate": 8.043977362420094e-06, + "loss": 0.0096, + "step": 37288 + }, + { + "epoch": 11.52, + "learning_rate": 8.043486907270285e-06, + "loss": 0.0099, + "step": 37289 + }, + { + "epoch": 11.52, + "learning_rate": 8.04299645701407e-06, + "loss": 0.009, + "step": 37290 + }, + { + "epoch": 11.52, + "learning_rate": 8.042506011652682e-06, + "loss": 0.0107, + "step": 37291 + }, + { + "epoch": 11.52, + "learning_rate": 8.042015571187343e-06, + "loss": 0.01, + "step": 37292 + }, + { + "epoch": 11.52, + "learning_rate": 8.041525135619276e-06, + "loss": 0.0113, + "step": 37293 + }, + { + "epoch": 11.52, + "learning_rate": 8.041034704949716e-06, + "loss": 0.0107, + "step": 37294 + }, + { + "epoch": 11.52, + "learning_rate": 8.040544279179887e-06, + "loss": 0.0123, + "step": 37295 + }, + { + "epoch": 11.52, + "learning_rate": 8.04005385831101e-06, + "loss": 0.0084, + "step": 37296 + }, + { + "epoch": 11.52, + "learning_rate": 8.039563442344316e-06, + "loss": 0.0094, + "step": 37297 + }, + { + "epoch": 11.52, + "learning_rate": 8.039073031281035e-06, + "loss": 0.0105, + "step": 37298 + }, + { + "epoch": 11.52, + "learning_rate": 8.038582625122387e-06, + "loss": 0.0116, + "step": 37299 + }, + { + "epoch": 11.52, + "learning_rate": 8.0380922238696e-06, + "loss": 0.01, + "step": 37300 + }, + { + "epoch": 11.52, + "learning_rate": 8.037601827523907e-06, + "loss": 0.0104, + "step": 37301 + }, + { + "epoch": 11.52, + "learning_rate": 8.037111436086527e-06, + "loss": 0.0095, + "step": 37302 + }, + { + "epoch": 11.52, + "learning_rate": 8.036621049558688e-06, + "loss": 0.0089, + "step": 37303 + }, + { + "epoch": 11.52, + "learning_rate": 8.036130667941623e-06, + "loss": 0.0088, + "step": 37304 + }, + { + "epoch": 11.52, + "learning_rate": 8.035640291236549e-06, + "loss": 0.0096, + "step": 37305 + }, + { + "epoch": 11.52, + "learning_rate": 8.035149919444697e-06, + "loss": 0.0088, + "step": 37306 + }, + { + "epoch": 11.52, + "learning_rate": 8.034659552567295e-06, + "loss": 0.0102, + "step": 37307 + }, + { + "epoch": 11.52, + "learning_rate": 8.034169190605565e-06, + "loss": 0.0101, + "step": 37308 + }, + { + "epoch": 11.52, + "learning_rate": 8.033678833560738e-06, + "loss": 0.0122, + "step": 37309 + }, + { + "epoch": 11.52, + "learning_rate": 8.033188481434042e-06, + "loss": 0.0112, + "step": 37310 + }, + { + "epoch": 11.52, + "learning_rate": 8.032698134226695e-06, + "loss": 0.0098, + "step": 37311 + }, + { + "epoch": 11.52, + "learning_rate": 8.032207791939932e-06, + "loss": 0.0108, + "step": 37312 + }, + { + "epoch": 11.52, + "learning_rate": 8.031717454574978e-06, + "loss": 0.0106, + "step": 37313 + }, + { + "epoch": 11.52, + "learning_rate": 8.031227122133055e-06, + "loss": 0.0081, + "step": 37314 + }, + { + "epoch": 11.52, + "learning_rate": 8.03073679461539e-06, + "loss": 0.011, + "step": 37315 + }, + { + "epoch": 11.52, + "learning_rate": 8.030246472023217e-06, + "loss": 0.009, + "step": 37316 + }, + { + "epoch": 11.52, + "learning_rate": 8.029756154357753e-06, + "loss": 0.0105, + "step": 37317 + }, + { + "epoch": 11.52, + "learning_rate": 8.029265841620226e-06, + "loss": 0.0094, + "step": 37318 + }, + { + "epoch": 11.52, + "learning_rate": 8.02877553381187e-06, + "loss": 0.0105, + "step": 37319 + }, + { + "epoch": 11.53, + "learning_rate": 8.028285230933904e-06, + "loss": 0.0122, + "step": 37320 + }, + { + "epoch": 11.53, + "learning_rate": 8.027794932987553e-06, + "loss": 0.0091, + "step": 37321 + }, + { + "epoch": 11.53, + "learning_rate": 8.02730463997405e-06, + "loss": 0.0097, + "step": 37322 + }, + { + "epoch": 11.53, + "learning_rate": 8.026814351894618e-06, + "loss": 0.0091, + "step": 37323 + }, + { + "epoch": 11.53, + "learning_rate": 8.026324068750482e-06, + "loss": 0.0101, + "step": 37324 + }, + { + "epoch": 11.53, + "learning_rate": 8.025833790542872e-06, + "loss": 0.0083, + "step": 37325 + }, + { + "epoch": 11.53, + "learning_rate": 8.025343517273007e-06, + "loss": 0.0107, + "step": 37326 + }, + { + "epoch": 11.53, + "learning_rate": 8.02485324894212e-06, + "loss": 0.0116, + "step": 37327 + }, + { + "epoch": 11.53, + "learning_rate": 8.024362985551433e-06, + "loss": 0.0109, + "step": 37328 + }, + { + "epoch": 11.53, + "learning_rate": 8.02387272710218e-06, + "loss": 0.0101, + "step": 37329 + }, + { + "epoch": 11.53, + "learning_rate": 8.02338247359558e-06, + "loss": 0.0102, + "step": 37330 + }, + { + "epoch": 11.53, + "learning_rate": 8.022892225032856e-06, + "loss": 0.0102, + "step": 37331 + }, + { + "epoch": 11.53, + "learning_rate": 8.022401981415247e-06, + "loss": 0.0107, + "step": 37332 + }, + { + "epoch": 11.53, + "learning_rate": 8.021911742743966e-06, + "loss": 0.0097, + "step": 37333 + }, + { + "epoch": 11.53, + "learning_rate": 8.021421509020247e-06, + "loss": 0.0092, + "step": 37334 + }, + { + "epoch": 11.53, + "learning_rate": 8.020931280245314e-06, + "loss": 0.0086, + "step": 37335 + }, + { + "epoch": 11.53, + "learning_rate": 8.02044105642039e-06, + "loss": 0.0111, + "step": 37336 + }, + { + "epoch": 11.53, + "learning_rate": 8.019950837546704e-06, + "loss": 0.0103, + "step": 37337 + }, + { + "epoch": 11.53, + "learning_rate": 8.019460623625486e-06, + "loss": 0.0089, + "step": 37338 + }, + { + "epoch": 11.53, + "learning_rate": 8.018970414657954e-06, + "loss": 0.0107, + "step": 37339 + }, + { + "epoch": 11.53, + "learning_rate": 8.01848021064534e-06, + "loss": 0.0124, + "step": 37340 + }, + { + "epoch": 11.53, + "learning_rate": 8.01799001158887e-06, + "loss": 0.0102, + "step": 37341 + }, + { + "epoch": 11.53, + "learning_rate": 8.017499817489764e-06, + "loss": 0.0117, + "step": 37342 + }, + { + "epoch": 11.53, + "learning_rate": 8.017009628349257e-06, + "loss": 0.0089, + "step": 37343 + }, + { + "epoch": 11.53, + "learning_rate": 8.01651944416857e-06, + "loss": 0.0099, + "step": 37344 + }, + { + "epoch": 11.53, + "learning_rate": 8.01602926494893e-06, + "loss": 0.0104, + "step": 37345 + }, + { + "epoch": 11.53, + "learning_rate": 8.015539090691558e-06, + "loss": 0.0094, + "step": 37346 + }, + { + "epoch": 11.53, + "learning_rate": 8.01504892139769e-06, + "loss": 0.0108, + "step": 37347 + }, + { + "epoch": 11.53, + "learning_rate": 8.014558757068544e-06, + "loss": 0.0128, + "step": 37348 + }, + { + "epoch": 11.53, + "learning_rate": 8.014068597705348e-06, + "loss": 0.0114, + "step": 37349 + }, + { + "epoch": 11.53, + "learning_rate": 8.013578443309332e-06, + "loss": 0.0094, + "step": 37350 + }, + { + "epoch": 11.53, + "learning_rate": 8.013088293881717e-06, + "loss": 0.0107, + "step": 37351 + }, + { + "epoch": 11.54, + "learning_rate": 8.012598149423728e-06, + "loss": 0.0107, + "step": 37352 + }, + { + "epoch": 11.54, + "learning_rate": 8.0121080099366e-06, + "loss": 0.0116, + "step": 37353 + }, + { + "epoch": 11.54, + "learning_rate": 8.011617875421546e-06, + "loss": 0.0104, + "step": 37354 + }, + { + "epoch": 11.54, + "learning_rate": 8.011127745879799e-06, + "loss": 0.0097, + "step": 37355 + }, + { + "epoch": 11.54, + "learning_rate": 8.010637621312589e-06, + "loss": 0.0104, + "step": 37356 + }, + { + "epoch": 11.54, + "learning_rate": 8.010147501721132e-06, + "loss": 0.0092, + "step": 37357 + }, + { + "epoch": 11.54, + "learning_rate": 8.00965738710666e-06, + "loss": 0.0105, + "step": 37358 + }, + { + "epoch": 11.54, + "learning_rate": 8.009167277470402e-06, + "loss": 0.0101, + "step": 37359 + }, + { + "epoch": 11.54, + "learning_rate": 8.008677172813573e-06, + "loss": 0.0102, + "step": 37360 + }, + { + "epoch": 11.54, + "learning_rate": 8.00818707313741e-06, + "loss": 0.0098, + "step": 37361 + }, + { + "epoch": 11.54, + "learning_rate": 8.007696978443131e-06, + "loss": 0.0103, + "step": 37362 + }, + { + "epoch": 11.54, + "learning_rate": 8.007206888731973e-06, + "loss": 0.009, + "step": 37363 + }, + { + "epoch": 11.54, + "learning_rate": 8.006716804005145e-06, + "loss": 0.0107, + "step": 37364 + }, + { + "epoch": 11.54, + "learning_rate": 8.006226724263886e-06, + "loss": 0.0097, + "step": 37365 + }, + { + "epoch": 11.54, + "learning_rate": 8.00573664950942e-06, + "loss": 0.0095, + "step": 37366 + }, + { + "epoch": 11.54, + "learning_rate": 8.005246579742964e-06, + "loss": 0.0096, + "step": 37367 + }, + { + "epoch": 11.54, + "learning_rate": 8.004756514965755e-06, + "loss": 0.0115, + "step": 37368 + }, + { + "epoch": 11.54, + "learning_rate": 8.004266455179015e-06, + "loss": 0.0106, + "step": 37369 + }, + { + "epoch": 11.54, + "learning_rate": 8.003776400383964e-06, + "loss": 0.0099, + "step": 37370 + }, + { + "epoch": 11.54, + "learning_rate": 8.003286350581834e-06, + "loss": 0.0102, + "step": 37371 + }, + { + "epoch": 11.54, + "learning_rate": 8.00279630577385e-06, + "loss": 0.012, + "step": 37372 + }, + { + "epoch": 11.54, + "learning_rate": 8.002306265961236e-06, + "loss": 0.0101, + "step": 37373 + }, + { + "epoch": 11.54, + "learning_rate": 8.001816231145219e-06, + "loss": 0.0104, + "step": 37374 + }, + { + "epoch": 11.54, + "learning_rate": 8.001326201327025e-06, + "loss": 0.0094, + "step": 37375 + }, + { + "epoch": 11.54, + "learning_rate": 8.000836176507876e-06, + "loss": 0.0114, + "step": 37376 + }, + { + "epoch": 11.54, + "learning_rate": 8.000346156689e-06, + "loss": 0.0105, + "step": 37377 + }, + { + "epoch": 11.54, + "learning_rate": 7.999856141871628e-06, + "loss": 0.0095, + "step": 37378 + }, + { + "epoch": 11.54, + "learning_rate": 7.999366132056975e-06, + "loss": 0.0114, + "step": 37379 + }, + { + "epoch": 11.54, + "learning_rate": 7.998876127246273e-06, + "loss": 0.0112, + "step": 37380 + }, + { + "epoch": 11.54, + "learning_rate": 7.998386127440752e-06, + "loss": 0.0106, + "step": 37381 + }, + { + "epoch": 11.54, + "learning_rate": 7.997896132641628e-06, + "loss": 0.0119, + "step": 37382 + }, + { + "epoch": 11.54, + "learning_rate": 7.997406142850132e-06, + "loss": 0.0106, + "step": 37383 + }, + { + "epoch": 11.54, + "learning_rate": 7.99691615806749e-06, + "loss": 0.0096, + "step": 37384 + }, + { + "epoch": 11.55, + "learning_rate": 7.996426178294921e-06, + "loss": 0.0092, + "step": 37385 + }, + { + "epoch": 11.55, + "learning_rate": 7.995936203533658e-06, + "loss": 0.0095, + "step": 37386 + }, + { + "epoch": 11.55, + "learning_rate": 7.995446233784928e-06, + "loss": 0.0086, + "step": 37387 + }, + { + "epoch": 11.55, + "learning_rate": 7.994956269049946e-06, + "loss": 0.0112, + "step": 37388 + }, + { + "epoch": 11.55, + "learning_rate": 7.994466309329947e-06, + "loss": 0.0094, + "step": 37389 + }, + { + "epoch": 11.55, + "learning_rate": 7.993976354626157e-06, + "loss": 0.0099, + "step": 37390 + }, + { + "epoch": 11.55, + "learning_rate": 7.993486404939793e-06, + "loss": 0.0115, + "step": 37391 + }, + { + "epoch": 11.55, + "learning_rate": 7.992996460272086e-06, + "loss": 0.0106, + "step": 37392 + }, + { + "epoch": 11.55, + "learning_rate": 7.99250652062426e-06, + "loss": 0.0102, + "step": 37393 + }, + { + "epoch": 11.55, + "learning_rate": 7.99201658599755e-06, + "loss": 0.0093, + "step": 37394 + }, + { + "epoch": 11.55, + "learning_rate": 7.991526656393164e-06, + "loss": 0.0099, + "step": 37395 + }, + { + "epoch": 11.55, + "learning_rate": 7.991036731812338e-06, + "loss": 0.0109, + "step": 37396 + }, + { + "epoch": 11.55, + "learning_rate": 7.990546812256299e-06, + "loss": 0.0101, + "step": 37397 + }, + { + "epoch": 11.55, + "learning_rate": 7.990056897726263e-06, + "loss": 0.01, + "step": 37398 + }, + { + "epoch": 11.55, + "learning_rate": 7.989566988223464e-06, + "loss": 0.0093, + "step": 37399 + }, + { + "epoch": 11.55, + "learning_rate": 7.989077083749127e-06, + "loss": 0.0111, + "step": 37400 + }, + { + "epoch": 11.55, + "learning_rate": 7.98858718430447e-06, + "loss": 0.0112, + "step": 37401 + }, + { + "epoch": 11.55, + "learning_rate": 7.988097289890727e-06, + "loss": 0.0108, + "step": 37402 + }, + { + "epoch": 11.55, + "learning_rate": 7.987607400509121e-06, + "loss": 0.0097, + "step": 37403 + }, + { + "epoch": 11.55, + "learning_rate": 7.987117516160873e-06, + "loss": 0.0098, + "step": 37404 + }, + { + "epoch": 11.55, + "learning_rate": 7.986627636847211e-06, + "loss": 0.0091, + "step": 37405 + }, + { + "epoch": 11.55, + "learning_rate": 7.986137762569364e-06, + "loss": 0.0126, + "step": 37406 + }, + { + "epoch": 11.55, + "learning_rate": 7.98564789332855e-06, + "loss": 0.0101, + "step": 37407 + }, + { + "epoch": 11.55, + "learning_rate": 7.985158029125996e-06, + "loss": 0.0104, + "step": 37408 + }, + { + "epoch": 11.55, + "learning_rate": 7.984668169962935e-06, + "loss": 0.0109, + "step": 37409 + }, + { + "epoch": 11.55, + "learning_rate": 7.984178315840585e-06, + "loss": 0.0095, + "step": 37410 + }, + { + "epoch": 11.55, + "learning_rate": 7.983688466760169e-06, + "loss": 0.0103, + "step": 37411 + }, + { + "epoch": 11.55, + "learning_rate": 7.983198622722924e-06, + "loss": 0.009, + "step": 37412 + }, + { + "epoch": 11.55, + "learning_rate": 7.98270878373006e-06, + "loss": 0.0104, + "step": 37413 + }, + { + "epoch": 11.55, + "learning_rate": 7.98221894978281e-06, + "loss": 0.0123, + "step": 37414 + }, + { + "epoch": 11.55, + "learning_rate": 7.9817291208824e-06, + "loss": 0.0105, + "step": 37415 + }, + { + "epoch": 11.55, + "learning_rate": 7.981239297030052e-06, + "loss": 0.0106, + "step": 37416 + }, + { + "epoch": 11.56, + "learning_rate": 7.980749478226993e-06, + "loss": 0.0112, + "step": 37417 + }, + { + "epoch": 11.56, + "learning_rate": 7.980259664474452e-06, + "loss": 0.0104, + "step": 37418 + }, + { + "epoch": 11.56, + "learning_rate": 7.979769855773644e-06, + "loss": 0.0111, + "step": 37419 + }, + { + "epoch": 11.56, + "learning_rate": 7.979280052125801e-06, + "loss": 0.0112, + "step": 37420 + }, + { + "epoch": 11.56, + "learning_rate": 7.978790253532152e-06, + "loss": 0.0105, + "step": 37421 + }, + { + "epoch": 11.56, + "learning_rate": 7.978300459993913e-06, + "loss": 0.01, + "step": 37422 + }, + { + "epoch": 11.56, + "learning_rate": 7.977810671512312e-06, + "loss": 0.0104, + "step": 37423 + }, + { + "epoch": 11.56, + "learning_rate": 7.97732088808858e-06, + "loss": 0.0094, + "step": 37424 + }, + { + "epoch": 11.56, + "learning_rate": 7.976831109723934e-06, + "loss": 0.0107, + "step": 37425 + }, + { + "epoch": 11.56, + "learning_rate": 7.976341336419602e-06, + "loss": 0.0103, + "step": 37426 + }, + { + "epoch": 11.56, + "learning_rate": 7.975851568176811e-06, + "loss": 0.0088, + "step": 37427 + }, + { + "epoch": 11.56, + "learning_rate": 7.975361804996786e-06, + "loss": 0.0096, + "step": 37428 + }, + { + "epoch": 11.56, + "learning_rate": 7.974872046880747e-06, + "loss": 0.0112, + "step": 37429 + }, + { + "epoch": 11.56, + "learning_rate": 7.974382293829922e-06, + "loss": 0.0103, + "step": 37430 + }, + { + "epoch": 11.56, + "learning_rate": 7.973892545845541e-06, + "loss": 0.0089, + "step": 37431 + }, + { + "epoch": 11.56, + "learning_rate": 7.97340280292882e-06, + "loss": 0.011, + "step": 37432 + }, + { + "epoch": 11.56, + "learning_rate": 7.972913065080989e-06, + "loss": 0.01, + "step": 37433 + }, + { + "epoch": 11.56, + "learning_rate": 7.972423332303275e-06, + "loss": 0.0097, + "step": 37434 + }, + { + "epoch": 11.56, + "learning_rate": 7.971933604596898e-06, + "loss": 0.0114, + "step": 37435 + }, + { + "epoch": 11.56, + "learning_rate": 7.971443881963082e-06, + "loss": 0.0095, + "step": 37436 + }, + { + "epoch": 11.56, + "learning_rate": 7.97095416440306e-06, + "loss": 0.0127, + "step": 37437 + }, + { + "epoch": 11.56, + "learning_rate": 7.97046445191805e-06, + "loss": 0.0102, + "step": 37438 + }, + { + "epoch": 11.56, + "learning_rate": 7.969974744509276e-06, + "loss": 0.0103, + "step": 37439 + }, + { + "epoch": 11.56, + "learning_rate": 7.96948504217797e-06, + "loss": 0.0083, + "step": 37440 + }, + { + "epoch": 11.56, + "learning_rate": 7.968995344925349e-06, + "loss": 0.0129, + "step": 37441 + }, + { + "epoch": 11.56, + "learning_rate": 7.96850565275264e-06, + "loss": 0.0112, + "step": 37442 + }, + { + "epoch": 11.56, + "learning_rate": 7.968015965661074e-06, + "loss": 0.0121, + "step": 37443 + }, + { + "epoch": 11.56, + "learning_rate": 7.967526283651865e-06, + "loss": 0.0099, + "step": 37444 + }, + { + "epoch": 11.56, + "learning_rate": 7.967036606726246e-06, + "loss": 0.0105, + "step": 37445 + }, + { + "epoch": 11.56, + "learning_rate": 7.966546934885441e-06, + "loss": 0.0096, + "step": 37446 + }, + { + "epoch": 11.56, + "learning_rate": 7.966057268130669e-06, + "loss": 0.0097, + "step": 37447 + }, + { + "epoch": 11.56, + "learning_rate": 7.965567606463161e-06, + "loss": 0.0103, + "step": 37448 + }, + { + "epoch": 11.56, + "learning_rate": 7.96507794988414e-06, + "loss": 0.01, + "step": 37449 + }, + { + "epoch": 11.57, + "learning_rate": 7.964588298394827e-06, + "loss": 0.0094, + "step": 37450 + }, + { + "epoch": 11.57, + "learning_rate": 7.964098651996452e-06, + "loss": 0.0096, + "step": 37451 + }, + { + "epoch": 11.57, + "learning_rate": 7.963609010690241e-06, + "loss": 0.0112, + "step": 37452 + }, + { + "epoch": 11.57, + "learning_rate": 7.963119374477413e-06, + "loss": 0.0096, + "step": 37453 + }, + { + "epoch": 11.57, + "learning_rate": 7.962629743359191e-06, + "loss": 0.0104, + "step": 37454 + }, + { + "epoch": 11.57, + "learning_rate": 7.962140117336808e-06, + "loss": 0.0085, + "step": 37455 + }, + { + "epoch": 11.57, + "learning_rate": 7.961650496411484e-06, + "loss": 0.0088, + "step": 37456 + }, + { + "epoch": 11.57, + "learning_rate": 7.96116088058444e-06, + "loss": 0.0091, + "step": 37457 + }, + { + "epoch": 11.57, + "learning_rate": 7.960671269856908e-06, + "loss": 0.0087, + "step": 37458 + }, + { + "epoch": 11.57, + "learning_rate": 7.96018166423011e-06, + "loss": 0.0096, + "step": 37459 + }, + { + "epoch": 11.57, + "learning_rate": 7.959692063705266e-06, + "loss": 0.0108, + "step": 37460 + }, + { + "epoch": 11.57, + "learning_rate": 7.959202468283607e-06, + "loss": 0.011, + "step": 37461 + }, + { + "epoch": 11.57, + "learning_rate": 7.958712877966355e-06, + "loss": 0.0107, + "step": 37462 + }, + { + "epoch": 11.57, + "learning_rate": 7.958223292754735e-06, + "loss": 0.0096, + "step": 37463 + }, + { + "epoch": 11.57, + "learning_rate": 7.957733712649966e-06, + "loss": 0.0098, + "step": 37464 + }, + { + "epoch": 11.57, + "learning_rate": 7.957244137653284e-06, + "loss": 0.0093, + "step": 37465 + }, + { + "epoch": 11.57, + "learning_rate": 7.956754567765904e-06, + "loss": 0.0097, + "step": 37466 + }, + { + "epoch": 11.57, + "learning_rate": 7.956265002989052e-06, + "loss": 0.0101, + "step": 37467 + }, + { + "epoch": 11.57, + "learning_rate": 7.955775443323957e-06, + "loss": 0.0098, + "step": 37468 + }, + { + "epoch": 11.57, + "learning_rate": 7.955285888771838e-06, + "loss": 0.0101, + "step": 37469 + }, + { + "epoch": 11.57, + "learning_rate": 7.95479633933392e-06, + "loss": 0.0092, + "step": 37470 + }, + { + "epoch": 11.57, + "learning_rate": 7.954306795011435e-06, + "loss": 0.0111, + "step": 37471 + }, + { + "epoch": 11.57, + "learning_rate": 7.9538172558056e-06, + "loss": 0.0102, + "step": 37472 + }, + { + "epoch": 11.57, + "learning_rate": 7.953327721717641e-06, + "loss": 0.0109, + "step": 37473 + }, + { + "epoch": 11.57, + "learning_rate": 7.952838192748785e-06, + "loss": 0.0104, + "step": 37474 + }, + { + "epoch": 11.57, + "learning_rate": 7.952348668900248e-06, + "loss": 0.0106, + "step": 37475 + }, + { + "epoch": 11.57, + "learning_rate": 7.951859150173262e-06, + "loss": 0.0085, + "step": 37476 + }, + { + "epoch": 11.57, + "learning_rate": 7.951369636569055e-06, + "loss": 0.011, + "step": 37477 + }, + { + "epoch": 11.57, + "learning_rate": 7.95088012808884e-06, + "loss": 0.0101, + "step": 37478 + }, + { + "epoch": 11.57, + "learning_rate": 7.95039062473385e-06, + "loss": 0.0101, + "step": 37479 + }, + { + "epoch": 11.57, + "learning_rate": 7.949901126505308e-06, + "loss": 0.0094, + "step": 37480 + }, + { + "epoch": 11.57, + "learning_rate": 7.949411633404435e-06, + "loss": 0.0113, + "step": 37481 + }, + { + "epoch": 11.58, + "learning_rate": 7.948922145432458e-06, + "loss": 0.0094, + "step": 37482 + }, + { + "epoch": 11.58, + "learning_rate": 7.948432662590604e-06, + "loss": 0.0101, + "step": 37483 + }, + { + "epoch": 11.58, + "learning_rate": 7.94794318488009e-06, + "loss": 0.0116, + "step": 37484 + }, + { + "epoch": 11.58, + "learning_rate": 7.947453712302145e-06, + "loss": 0.0104, + "step": 37485 + }, + { + "epoch": 11.58, + "learning_rate": 7.946964244857996e-06, + "loss": 0.0095, + "step": 37486 + }, + { + "epoch": 11.58, + "learning_rate": 7.94647478254886e-06, + "loss": 0.0115, + "step": 37487 + }, + { + "epoch": 11.58, + "learning_rate": 7.945985325375966e-06, + "loss": 0.0141, + "step": 37488 + }, + { + "epoch": 11.58, + "learning_rate": 7.94549587334054e-06, + "loss": 0.0095, + "step": 37489 + }, + { + "epoch": 11.58, + "learning_rate": 7.945006426443802e-06, + "loss": 0.0103, + "step": 37490 + }, + { + "epoch": 11.58, + "learning_rate": 7.944516984686974e-06, + "loss": 0.0081, + "step": 37491 + }, + { + "epoch": 11.58, + "learning_rate": 7.944027548071287e-06, + "loss": 0.0099, + "step": 37492 + }, + { + "epoch": 11.58, + "learning_rate": 7.943538116597965e-06, + "loss": 0.0104, + "step": 37493 + }, + { + "epoch": 11.58, + "learning_rate": 7.943048690268224e-06, + "loss": 0.0108, + "step": 37494 + }, + { + "epoch": 11.58, + "learning_rate": 7.942559269083294e-06, + "loss": 0.0094, + "step": 37495 + }, + { + "epoch": 11.58, + "learning_rate": 7.942069853044403e-06, + "loss": 0.0105, + "step": 37496 + }, + { + "epoch": 11.58, + "learning_rate": 7.941580442152768e-06, + "loss": 0.0113, + "step": 37497 + }, + { + "epoch": 11.58, + "learning_rate": 7.941091036409614e-06, + "loss": 0.0096, + "step": 37498 + }, + { + "epoch": 11.58, + "learning_rate": 7.94060163581617e-06, + "loss": 0.0099, + "step": 37499 + }, + { + "epoch": 11.58, + "learning_rate": 7.940112240373656e-06, + "loss": 0.0093, + "step": 37500 + }, + { + "epoch": 11.58, + "learning_rate": 7.939622850083294e-06, + "loss": 0.01, + "step": 37501 + }, + { + "epoch": 11.58, + "learning_rate": 7.939133464946317e-06, + "loss": 0.0101, + "step": 37502 + }, + { + "epoch": 11.58, + "learning_rate": 7.938644084963938e-06, + "loss": 0.0092, + "step": 37503 + }, + { + "epoch": 11.58, + "learning_rate": 7.938154710137387e-06, + "loss": 0.0102, + "step": 37504 + }, + { + "epoch": 11.58, + "learning_rate": 7.937665340467891e-06, + "loss": 0.0102, + "step": 37505 + }, + { + "epoch": 11.58, + "learning_rate": 7.937175975956663e-06, + "loss": 0.0097, + "step": 37506 + }, + { + "epoch": 11.58, + "learning_rate": 7.936686616604939e-06, + "loss": 0.0102, + "step": 37507 + }, + { + "epoch": 11.58, + "learning_rate": 7.93619726241394e-06, + "loss": 0.0112, + "step": 37508 + }, + { + "epoch": 11.58, + "learning_rate": 7.935707913384882e-06, + "loss": 0.0111, + "step": 37509 + }, + { + "epoch": 11.58, + "learning_rate": 7.935218569518998e-06, + "loss": 0.0101, + "step": 37510 + }, + { + "epoch": 11.58, + "learning_rate": 7.934729230817511e-06, + "loss": 0.0101, + "step": 37511 + }, + { + "epoch": 11.58, + "learning_rate": 7.934239897281641e-06, + "loss": 0.009, + "step": 37512 + }, + { + "epoch": 11.58, + "learning_rate": 7.933750568912613e-06, + "loss": 0.0106, + "step": 37513 + }, + { + "epoch": 11.59, + "learning_rate": 7.933261245711655e-06, + "loss": 0.0106, + "step": 37514 + }, + { + "epoch": 11.59, + "learning_rate": 7.932771927679983e-06, + "loss": 0.0113, + "step": 37515 + }, + { + "epoch": 11.59, + "learning_rate": 7.932282614818825e-06, + "loss": 0.0098, + "step": 37516 + }, + { + "epoch": 11.59, + "learning_rate": 7.93179330712941e-06, + "loss": 0.0085, + "step": 37517 + }, + { + "epoch": 11.59, + "learning_rate": 7.931304004612956e-06, + "loss": 0.0109, + "step": 37518 + }, + { + "epoch": 11.59, + "learning_rate": 7.930814707270685e-06, + "loss": 0.0099, + "step": 37519 + }, + { + "epoch": 11.59, + "learning_rate": 7.930325415103828e-06, + "loss": 0.009, + "step": 37520 + }, + { + "epoch": 11.59, + "learning_rate": 7.929836128113601e-06, + "loss": 0.0091, + "step": 37521 + }, + { + "epoch": 11.59, + "learning_rate": 7.929346846301234e-06, + "loss": 0.0118, + "step": 37522 + }, + { + "epoch": 11.59, + "learning_rate": 7.928857569667945e-06, + "loss": 0.011, + "step": 37523 + }, + { + "epoch": 11.59, + "learning_rate": 7.928368298214965e-06, + "loss": 0.0111, + "step": 37524 + }, + { + "epoch": 11.59, + "learning_rate": 7.927879031943511e-06, + "loss": 0.0111, + "step": 37525 + }, + { + "epoch": 11.59, + "learning_rate": 7.927389770854808e-06, + "loss": 0.0103, + "step": 37526 + }, + { + "epoch": 11.59, + "learning_rate": 7.926900514950086e-06, + "loss": 0.0107, + "step": 37527 + }, + { + "epoch": 11.59, + "learning_rate": 7.926411264230562e-06, + "loss": 0.0107, + "step": 37528 + }, + { + "epoch": 11.59, + "learning_rate": 7.925922018697458e-06, + "loss": 0.0101, + "step": 37529 + }, + { + "epoch": 11.59, + "learning_rate": 7.925432778352007e-06, + "loss": 0.0114, + "step": 37530 + }, + { + "epoch": 11.59, + "learning_rate": 7.924943543195424e-06, + "loss": 0.01, + "step": 37531 + }, + { + "epoch": 11.59, + "learning_rate": 7.924454313228936e-06, + "loss": 0.009, + "step": 37532 + }, + { + "epoch": 11.59, + "learning_rate": 7.923965088453769e-06, + "loss": 0.0098, + "step": 37533 + }, + { + "epoch": 11.59, + "learning_rate": 7.923475868871138e-06, + "loss": 0.0099, + "step": 37534 + }, + { + "epoch": 11.59, + "learning_rate": 7.922986654482275e-06, + "loss": 0.0095, + "step": 37535 + }, + { + "epoch": 11.59, + "learning_rate": 7.922497445288404e-06, + "loss": 0.0125, + "step": 37536 + }, + { + "epoch": 11.59, + "learning_rate": 7.922008241290742e-06, + "loss": 0.0108, + "step": 37537 + }, + { + "epoch": 11.59, + "learning_rate": 7.921519042490519e-06, + "loss": 0.0088, + "step": 37538 + }, + { + "epoch": 11.59, + "learning_rate": 7.921029848888958e-06, + "loss": 0.0094, + "step": 37539 + }, + { + "epoch": 11.59, + "learning_rate": 7.920540660487276e-06, + "loss": 0.0117, + "step": 37540 + }, + { + "epoch": 11.59, + "learning_rate": 7.920051477286701e-06, + "loss": 0.011, + "step": 37541 + }, + { + "epoch": 11.59, + "learning_rate": 7.91956229928846e-06, + "loss": 0.0097, + "step": 37542 + }, + { + "epoch": 11.59, + "learning_rate": 7.919073126493772e-06, + "loss": 0.012, + "step": 37543 + }, + { + "epoch": 11.59, + "learning_rate": 7.918583958903859e-06, + "loss": 0.0099, + "step": 37544 + }, + { + "epoch": 11.59, + "learning_rate": 7.918094796519951e-06, + "loss": 0.0119, + "step": 37545 + }, + { + "epoch": 11.59, + "learning_rate": 7.917605639343266e-06, + "loss": 0.0104, + "step": 37546 + }, + { + "epoch": 11.6, + "learning_rate": 7.917116487375027e-06, + "loss": 0.0099, + "step": 37547 + }, + { + "epoch": 11.6, + "learning_rate": 7.916627340616463e-06, + "loss": 0.0108, + "step": 37548 + }, + { + "epoch": 11.6, + "learning_rate": 7.916138199068793e-06, + "loss": 0.0114, + "step": 37549 + }, + { + "epoch": 11.6, + "learning_rate": 7.915649062733239e-06, + "loss": 0.0091, + "step": 37550 + }, + { + "epoch": 11.6, + "learning_rate": 7.915159931611033e-06, + "loss": 0.0106, + "step": 37551 + }, + { + "epoch": 11.6, + "learning_rate": 7.914670805703386e-06, + "loss": 0.0105, + "step": 37552 + }, + { + "epoch": 11.6, + "learning_rate": 7.91418168501153e-06, + "loss": 0.0105, + "step": 37553 + }, + { + "epoch": 11.6, + "learning_rate": 7.913692569536688e-06, + "loss": 0.0105, + "step": 37554 + }, + { + "epoch": 11.6, + "learning_rate": 7.913203459280077e-06, + "loss": 0.0108, + "step": 37555 + }, + { + "epoch": 11.6, + "learning_rate": 7.912714354242927e-06, + "loss": 0.0096, + "step": 37556 + }, + { + "epoch": 11.6, + "learning_rate": 7.912225254426456e-06, + "loss": 0.014, + "step": 37557 + }, + { + "epoch": 11.6, + "learning_rate": 7.911736159831896e-06, + "loss": 0.01, + "step": 37558 + }, + { + "epoch": 11.6, + "learning_rate": 7.911247070460463e-06, + "loss": 0.0102, + "step": 37559 + }, + { + "epoch": 11.6, + "learning_rate": 7.910757986313378e-06, + "loss": 0.0102, + "step": 37560 + }, + { + "epoch": 11.6, + "learning_rate": 7.910268907391877e-06, + "loss": 0.0101, + "step": 37561 + }, + { + "epoch": 11.6, + "learning_rate": 7.909779833697167e-06, + "loss": 0.0104, + "step": 37562 + }, + { + "epoch": 11.6, + "learning_rate": 7.909290765230481e-06, + "loss": 0.0102, + "step": 37563 + }, + { + "epoch": 11.6, + "learning_rate": 7.908801701993043e-06, + "loss": 0.011, + "step": 37564 + }, + { + "epoch": 11.6, + "learning_rate": 7.908312643986068e-06, + "loss": 0.0113, + "step": 37565 + }, + { + "epoch": 11.6, + "learning_rate": 7.907823591210786e-06, + "loss": 0.0089, + "step": 37566 + }, + { + "epoch": 11.6, + "learning_rate": 7.907334543668423e-06, + "loss": 0.0114, + "step": 37567 + }, + { + "epoch": 11.6, + "learning_rate": 7.906845501360192e-06, + "loss": 0.0097, + "step": 37568 + }, + { + "epoch": 11.6, + "learning_rate": 7.906356464287326e-06, + "loss": 0.0111, + "step": 37569 + }, + { + "epoch": 11.6, + "learning_rate": 7.905867432451045e-06, + "loss": 0.0096, + "step": 37570 + }, + { + "epoch": 11.6, + "learning_rate": 7.905378405852571e-06, + "loss": 0.0086, + "step": 37571 + }, + { + "epoch": 11.6, + "learning_rate": 7.904889384493125e-06, + "loss": 0.0101, + "step": 37572 + }, + { + "epoch": 11.6, + "learning_rate": 7.904400368373934e-06, + "loss": 0.01, + "step": 37573 + }, + { + "epoch": 11.6, + "learning_rate": 7.903911357496221e-06, + "loss": 0.0096, + "step": 37574 + }, + { + "epoch": 11.6, + "learning_rate": 7.903422351861205e-06, + "loss": 0.0097, + "step": 37575 + }, + { + "epoch": 11.6, + "learning_rate": 7.902933351470117e-06, + "loss": 0.0106, + "step": 37576 + }, + { + "epoch": 11.6, + "learning_rate": 7.902444356324173e-06, + "loss": 0.0116, + "step": 37577 + }, + { + "epoch": 11.6, + "learning_rate": 7.901955366424595e-06, + "loss": 0.0118, + "step": 37578 + }, + { + "epoch": 11.61, + "learning_rate": 7.901466381772614e-06, + "loss": 0.0084, + "step": 37579 + }, + { + "epoch": 11.61, + "learning_rate": 7.900977402369446e-06, + "loss": 0.01, + "step": 37580 + }, + { + "epoch": 11.61, + "learning_rate": 7.900488428216318e-06, + "loss": 0.0105, + "step": 37581 + }, + { + "epoch": 11.61, + "learning_rate": 7.899999459314452e-06, + "loss": 0.0106, + "step": 37582 + }, + { + "epoch": 11.61, + "learning_rate": 7.899510495665067e-06, + "loss": 0.0093, + "step": 37583 + }, + { + "epoch": 11.61, + "learning_rate": 7.89902153726939e-06, + "loss": 0.0087, + "step": 37584 + }, + { + "epoch": 11.61, + "learning_rate": 7.898532584128645e-06, + "loss": 0.0113, + "step": 37585 + }, + { + "epoch": 11.61, + "learning_rate": 7.89804363624405e-06, + "loss": 0.0091, + "step": 37586 + }, + { + "epoch": 11.61, + "learning_rate": 7.897554693616835e-06, + "loss": 0.0098, + "step": 37587 + }, + { + "epoch": 11.61, + "learning_rate": 7.897065756248219e-06, + "loss": 0.0093, + "step": 37588 + }, + { + "epoch": 11.61, + "learning_rate": 7.896576824139421e-06, + "loss": 0.0106, + "step": 37589 + }, + { + "epoch": 11.61, + "learning_rate": 7.896087897291673e-06, + "loss": 0.0095, + "step": 37590 + }, + { + "epoch": 11.61, + "learning_rate": 7.895598975706189e-06, + "loss": 0.0082, + "step": 37591 + }, + { + "epoch": 11.61, + "learning_rate": 7.8951100593842e-06, + "loss": 0.009, + "step": 37592 + }, + { + "epoch": 11.61, + "learning_rate": 7.89462114832692e-06, + "loss": 0.0114, + "step": 37593 + }, + { + "epoch": 11.61, + "learning_rate": 7.894132242535579e-06, + "loss": 0.0117, + "step": 37594 + }, + { + "epoch": 11.61, + "learning_rate": 7.893643342011399e-06, + "loss": 0.0107, + "step": 37595 + }, + { + "epoch": 11.61, + "learning_rate": 7.893154446755597e-06, + "loss": 0.0101, + "step": 37596 + }, + { + "epoch": 11.61, + "learning_rate": 7.892665556769404e-06, + "loss": 0.0134, + "step": 37597 + }, + { + "epoch": 11.61, + "learning_rate": 7.892176672054038e-06, + "loss": 0.01, + "step": 37598 + }, + { + "epoch": 11.61, + "learning_rate": 7.89168779261072e-06, + "loss": 0.0109, + "step": 37599 + }, + { + "epoch": 11.61, + "learning_rate": 7.891198918440677e-06, + "loss": 0.0109, + "step": 37600 + }, + { + "epoch": 11.61, + "learning_rate": 7.890710049545132e-06, + "loss": 0.0111, + "step": 37601 + }, + { + "epoch": 11.61, + "learning_rate": 7.890221185925304e-06, + "loss": 0.0112, + "step": 37602 + }, + { + "epoch": 11.61, + "learning_rate": 7.889732327582416e-06, + "loss": 0.0101, + "step": 37603 + }, + { + "epoch": 11.61, + "learning_rate": 7.889243474517694e-06, + "loss": 0.0091, + "step": 37604 + }, + { + "epoch": 11.61, + "learning_rate": 7.88875462673236e-06, + "loss": 0.0107, + "step": 37605 + }, + { + "epoch": 11.61, + "learning_rate": 7.888265784227634e-06, + "loss": 0.0094, + "step": 37606 + }, + { + "epoch": 11.61, + "learning_rate": 7.887776947004741e-06, + "loss": 0.0172, + "step": 37607 + }, + { + "epoch": 11.61, + "learning_rate": 7.887288115064903e-06, + "loss": 0.0099, + "step": 37608 + }, + { + "epoch": 11.61, + "learning_rate": 7.886799288409343e-06, + "loss": 0.0118, + "step": 37609 + }, + { + "epoch": 11.61, + "learning_rate": 7.886310467039286e-06, + "loss": 0.0117, + "step": 37610 + }, + { + "epoch": 11.62, + "learning_rate": 7.885821650955949e-06, + "loss": 0.0108, + "step": 37611 + }, + { + "epoch": 11.62, + "learning_rate": 7.885332840160557e-06, + "loss": 0.0106, + "step": 37612 + }, + { + "epoch": 11.62, + "learning_rate": 7.884844034654337e-06, + "loss": 0.0097, + "step": 37613 + }, + { + "epoch": 11.62, + "learning_rate": 7.884355234438503e-06, + "loss": 0.0115, + "step": 37614 + }, + { + "epoch": 11.62, + "learning_rate": 7.883866439514284e-06, + "loss": 0.0092, + "step": 37615 + }, + { + "epoch": 11.62, + "learning_rate": 7.883377649882903e-06, + "loss": 0.0096, + "step": 37616 + }, + { + "epoch": 11.62, + "learning_rate": 7.882888865545578e-06, + "loss": 0.0109, + "step": 37617 + }, + { + "epoch": 11.62, + "learning_rate": 7.882400086503535e-06, + "loss": 0.0116, + "step": 37618 + }, + { + "epoch": 11.62, + "learning_rate": 7.881911312758e-06, + "loss": 0.0102, + "step": 37619 + }, + { + "epoch": 11.62, + "learning_rate": 7.881422544310186e-06, + "loss": 0.0101, + "step": 37620 + }, + { + "epoch": 11.62, + "learning_rate": 7.880933781161319e-06, + "loss": 0.0092, + "step": 37621 + }, + { + "epoch": 11.62, + "learning_rate": 7.880445023312627e-06, + "loss": 0.009, + "step": 37622 + }, + { + "epoch": 11.62, + "learning_rate": 7.879956270765329e-06, + "loss": 0.0108, + "step": 37623 + }, + { + "epoch": 11.62, + "learning_rate": 7.879467523520644e-06, + "loss": 0.0097, + "step": 37624 + }, + { + "epoch": 11.62, + "learning_rate": 7.878978781579798e-06, + "loss": 0.0095, + "step": 37625 + }, + { + "epoch": 11.62, + "learning_rate": 7.878490044944016e-06, + "loss": 0.0115, + "step": 37626 + }, + { + "epoch": 11.62, + "learning_rate": 7.878001313614512e-06, + "loss": 0.0104, + "step": 37627 + }, + { + "epoch": 11.62, + "learning_rate": 7.877512587592517e-06, + "loss": 0.0117, + "step": 37628 + }, + { + "epoch": 11.62, + "learning_rate": 7.877023866879252e-06, + "loss": 0.0123, + "step": 37629 + }, + { + "epoch": 11.62, + "learning_rate": 7.876535151475936e-06, + "loss": 0.0122, + "step": 37630 + }, + { + "epoch": 11.62, + "learning_rate": 7.87604644138379e-06, + "loss": 0.0094, + "step": 37631 + }, + { + "epoch": 11.62, + "learning_rate": 7.875557736604044e-06, + "loss": 0.0094, + "step": 37632 + }, + { + "epoch": 11.62, + "learning_rate": 7.875069037137913e-06, + "loss": 0.0113, + "step": 37633 + }, + { + "epoch": 11.62, + "learning_rate": 7.87458034298662e-06, + "loss": 0.0096, + "step": 37634 + }, + { + "epoch": 11.62, + "learning_rate": 7.874091654151394e-06, + "loss": 0.0108, + "step": 37635 + }, + { + "epoch": 11.62, + "learning_rate": 7.87360297063345e-06, + "loss": 0.0108, + "step": 37636 + }, + { + "epoch": 11.62, + "learning_rate": 7.87311429243401e-06, + "loss": 0.0101, + "step": 37637 + }, + { + "epoch": 11.62, + "learning_rate": 7.872625619554304e-06, + "loss": 0.0101, + "step": 37638 + }, + { + "epoch": 11.62, + "learning_rate": 7.872136951995548e-06, + "loss": 0.0117, + "step": 37639 + }, + { + "epoch": 11.62, + "learning_rate": 7.871648289758962e-06, + "loss": 0.0099, + "step": 37640 + }, + { + "epoch": 11.62, + "learning_rate": 7.871159632845777e-06, + "loss": 0.0102, + "step": 37641 + }, + { + "epoch": 11.62, + "learning_rate": 7.870670981257207e-06, + "loss": 0.0092, + "step": 37642 + }, + { + "epoch": 11.62, + "learning_rate": 7.870182334994477e-06, + "loss": 0.0112, + "step": 37643 + }, + { + "epoch": 11.63, + "learning_rate": 7.869693694058812e-06, + "loss": 0.0108, + "step": 37644 + }, + { + "epoch": 11.63, + "learning_rate": 7.869205058451427e-06, + "loss": 0.0089, + "step": 37645 + }, + { + "epoch": 11.63, + "learning_rate": 7.868716428173552e-06, + "loss": 0.0121, + "step": 37646 + }, + { + "epoch": 11.63, + "learning_rate": 7.868227803226408e-06, + "loss": 0.0112, + "step": 37647 + }, + { + "epoch": 11.63, + "learning_rate": 7.867739183611211e-06, + "loss": 0.0112, + "step": 37648 + }, + { + "epoch": 11.63, + "learning_rate": 7.867250569329187e-06, + "loss": 0.0113, + "step": 37649 + }, + { + "epoch": 11.63, + "learning_rate": 7.866761960381564e-06, + "loss": 0.0095, + "step": 37650 + }, + { + "epoch": 11.63, + "learning_rate": 7.866273356769553e-06, + "loss": 0.0096, + "step": 37651 + }, + { + "epoch": 11.63, + "learning_rate": 7.865784758494382e-06, + "loss": 0.0095, + "step": 37652 + }, + { + "epoch": 11.63, + "learning_rate": 7.865296165557275e-06, + "loss": 0.0098, + "step": 37653 + }, + { + "epoch": 11.63, + "learning_rate": 7.86480757795945e-06, + "loss": 0.0116, + "step": 37654 + }, + { + "epoch": 11.63, + "learning_rate": 7.86431899570213e-06, + "loss": 0.0094, + "step": 37655 + }, + { + "epoch": 11.63, + "learning_rate": 7.863830418786538e-06, + "loss": 0.0102, + "step": 37656 + }, + { + "epoch": 11.63, + "learning_rate": 7.863341847213897e-06, + "loss": 0.0107, + "step": 37657 + }, + { + "epoch": 11.63, + "learning_rate": 7.862853280985427e-06, + "loss": 0.012, + "step": 37658 + }, + { + "epoch": 11.63, + "learning_rate": 7.86236472010235e-06, + "loss": 0.0177, + "step": 37659 + }, + { + "epoch": 11.63, + "learning_rate": 7.861876164565892e-06, + "loss": 0.0094, + "step": 37660 + }, + { + "epoch": 11.63, + "learning_rate": 7.86138761437727e-06, + "loss": 0.0093, + "step": 37661 + }, + { + "epoch": 11.63, + "learning_rate": 7.860899069537704e-06, + "loss": 0.0093, + "step": 37662 + }, + { + "epoch": 11.63, + "learning_rate": 7.860410530048423e-06, + "loss": 0.0089, + "step": 37663 + }, + { + "epoch": 11.63, + "learning_rate": 7.859921995910646e-06, + "loss": 0.0096, + "step": 37664 + }, + { + "epoch": 11.63, + "learning_rate": 7.85943346712559e-06, + "loss": 0.0101, + "step": 37665 + }, + { + "epoch": 11.63, + "learning_rate": 7.858944943694488e-06, + "loss": 0.0097, + "step": 37666 + }, + { + "epoch": 11.63, + "learning_rate": 7.858456425618551e-06, + "loss": 0.0092, + "step": 37667 + }, + { + "epoch": 11.63, + "learning_rate": 7.857967912899005e-06, + "loss": 0.0089, + "step": 37668 + }, + { + "epoch": 11.63, + "learning_rate": 7.857479405537076e-06, + "loss": 0.009, + "step": 37669 + }, + { + "epoch": 11.63, + "learning_rate": 7.856990903533977e-06, + "loss": 0.0118, + "step": 37670 + }, + { + "epoch": 11.63, + "learning_rate": 7.856502406890935e-06, + "loss": 0.0115, + "step": 37671 + }, + { + "epoch": 11.63, + "learning_rate": 7.856013915609176e-06, + "loss": 0.0113, + "step": 37672 + }, + { + "epoch": 11.63, + "learning_rate": 7.855525429689912e-06, + "loss": 0.012, + "step": 37673 + }, + { + "epoch": 11.63, + "learning_rate": 7.855036949134372e-06, + "loss": 0.0105, + "step": 37674 + }, + { + "epoch": 11.63, + "learning_rate": 7.854548473943778e-06, + "loss": 0.0124, + "step": 37675 + }, + { + "epoch": 11.64, + "learning_rate": 7.854060004119345e-06, + "loss": 0.0089, + "step": 37676 + }, + { + "epoch": 11.64, + "learning_rate": 7.853571539662302e-06, + "loss": 0.0098, + "step": 37677 + }, + { + "epoch": 11.64, + "learning_rate": 7.85308308057387e-06, + "loss": 0.0098, + "step": 37678 + }, + { + "epoch": 11.64, + "learning_rate": 7.852594626855266e-06, + "loss": 0.0127, + "step": 37679 + }, + { + "epoch": 11.64, + "learning_rate": 7.852106178507713e-06, + "loss": 0.0101, + "step": 37680 + }, + { + "epoch": 11.64, + "learning_rate": 7.851617735532438e-06, + "loss": 0.0104, + "step": 37681 + }, + { + "epoch": 11.64, + "learning_rate": 7.851129297930657e-06, + "loss": 0.0096, + "step": 37682 + }, + { + "epoch": 11.64, + "learning_rate": 7.850640865703591e-06, + "loss": 0.0099, + "step": 37683 + }, + { + "epoch": 11.64, + "learning_rate": 7.85015243885247e-06, + "loss": 0.0097, + "step": 37684 + }, + { + "epoch": 11.64, + "learning_rate": 7.849664017378506e-06, + "loss": 0.0116, + "step": 37685 + }, + { + "epoch": 11.64, + "learning_rate": 7.849175601282923e-06, + "loss": 0.0114, + "step": 37686 + }, + { + "epoch": 11.64, + "learning_rate": 7.848687190566946e-06, + "loss": 0.0111, + "step": 37687 + }, + { + "epoch": 11.64, + "learning_rate": 7.848198785231797e-06, + "loss": 0.0103, + "step": 37688 + }, + { + "epoch": 11.64, + "learning_rate": 7.847710385278693e-06, + "loss": 0.01, + "step": 37689 + }, + { + "epoch": 11.64, + "learning_rate": 7.847221990708857e-06, + "loss": 0.0104, + "step": 37690 + }, + { + "epoch": 11.64, + "learning_rate": 7.846733601523515e-06, + "loss": 0.0106, + "step": 37691 + }, + { + "epoch": 11.64, + "learning_rate": 7.846245217723882e-06, + "loss": 0.01, + "step": 37692 + }, + { + "epoch": 11.64, + "learning_rate": 7.84575683931118e-06, + "loss": 0.0091, + "step": 37693 + }, + { + "epoch": 11.64, + "learning_rate": 7.84526846628664e-06, + "loss": 0.0108, + "step": 37694 + }, + { + "epoch": 11.64, + "learning_rate": 7.844780098651473e-06, + "loss": 0.0115, + "step": 37695 + }, + { + "epoch": 11.64, + "learning_rate": 7.844291736406901e-06, + "loss": 0.0108, + "step": 37696 + }, + { + "epoch": 11.64, + "learning_rate": 7.843803379554153e-06, + "loss": 0.0122, + "step": 37697 + }, + { + "epoch": 11.64, + "learning_rate": 7.843315028094444e-06, + "loss": 0.0116, + "step": 37698 + }, + { + "epoch": 11.64, + "learning_rate": 7.842826682028996e-06, + "loss": 0.0099, + "step": 37699 + }, + { + "epoch": 11.64, + "learning_rate": 7.84233834135904e-06, + "loss": 0.0106, + "step": 37700 + }, + { + "epoch": 11.64, + "learning_rate": 7.84185000608578e-06, + "loss": 0.0107, + "step": 37701 + }, + { + "epoch": 11.64, + "learning_rate": 7.84136167621045e-06, + "loss": 0.0133, + "step": 37702 + }, + { + "epoch": 11.64, + "learning_rate": 7.84087335173427e-06, + "loss": 0.0116, + "step": 37703 + }, + { + "epoch": 11.64, + "learning_rate": 7.840385032658456e-06, + "loss": 0.0096, + "step": 37704 + }, + { + "epoch": 11.64, + "learning_rate": 7.839896718984234e-06, + "loss": 0.0119, + "step": 37705 + }, + { + "epoch": 11.64, + "learning_rate": 7.839408410712827e-06, + "loss": 0.0108, + "step": 37706 + }, + { + "epoch": 11.64, + "learning_rate": 7.83892010784545e-06, + "loss": 0.011, + "step": 37707 + }, + { + "epoch": 11.64, + "learning_rate": 7.838431810383328e-06, + "loss": 0.0107, + "step": 37708 + }, + { + "epoch": 11.65, + "learning_rate": 7.837943518327686e-06, + "loss": 0.0101, + "step": 37709 + }, + { + "epoch": 11.65, + "learning_rate": 7.83745523167974e-06, + "loss": 0.0109, + "step": 37710 + }, + { + "epoch": 11.65, + "learning_rate": 7.83696695044071e-06, + "loss": 0.0093, + "step": 37711 + }, + { + "epoch": 11.65, + "learning_rate": 7.836478674611824e-06, + "loss": 0.0104, + "step": 37712 + }, + { + "epoch": 11.65, + "learning_rate": 7.835990404194299e-06, + "loss": 0.0116, + "step": 37713 + }, + { + "epoch": 11.65, + "learning_rate": 7.835502139189352e-06, + "loss": 0.0115, + "step": 37714 + }, + { + "epoch": 11.65, + "learning_rate": 7.835013879598214e-06, + "loss": 0.0102, + "step": 37715 + }, + { + "epoch": 11.65, + "learning_rate": 7.8345256254221e-06, + "loss": 0.0111, + "step": 37716 + }, + { + "epoch": 11.65, + "learning_rate": 7.834037376662229e-06, + "loss": 0.0102, + "step": 37717 + }, + { + "epoch": 11.65, + "learning_rate": 7.833549133319833e-06, + "loss": 0.0111, + "step": 37718 + }, + { + "epoch": 11.65, + "learning_rate": 7.83306089539612e-06, + "loss": 0.0114, + "step": 37719 + }, + { + "epoch": 11.65, + "learning_rate": 7.832572662892317e-06, + "loss": 0.0104, + "step": 37720 + }, + { + "epoch": 11.65, + "learning_rate": 7.832084435809644e-06, + "loss": 0.012, + "step": 37721 + }, + { + "epoch": 11.65, + "learning_rate": 7.831596214149328e-06, + "loss": 0.0124, + "step": 37722 + }, + { + "epoch": 11.65, + "learning_rate": 7.831107997912583e-06, + "loss": 0.0095, + "step": 37723 + }, + { + "epoch": 11.65, + "learning_rate": 7.83061978710063e-06, + "loss": 0.0102, + "step": 37724 + }, + { + "epoch": 11.65, + "learning_rate": 7.830131581714697e-06, + "loss": 0.0097, + "step": 37725 + }, + { + "epoch": 11.65, + "learning_rate": 7.829643381755997e-06, + "loss": 0.0098, + "step": 37726 + }, + { + "epoch": 11.65, + "learning_rate": 7.829155187225755e-06, + "loss": 0.0105, + "step": 37727 + }, + { + "epoch": 11.65, + "learning_rate": 7.828666998125199e-06, + "loss": 0.0103, + "step": 37728 + }, + { + "epoch": 11.65, + "learning_rate": 7.828178814455534e-06, + "loss": 0.0089, + "step": 37729 + }, + { + "epoch": 11.65, + "learning_rate": 7.827690636217992e-06, + "loss": 0.0109, + "step": 37730 + }, + { + "epoch": 11.65, + "learning_rate": 7.827202463413796e-06, + "loss": 0.0099, + "step": 37731 + }, + { + "epoch": 11.65, + "learning_rate": 7.826714296044159e-06, + "loss": 0.0112, + "step": 37732 + }, + { + "epoch": 11.65, + "learning_rate": 7.826226134110306e-06, + "loss": 0.0133, + "step": 37733 + }, + { + "epoch": 11.65, + "learning_rate": 7.82573797761346e-06, + "loss": 0.0101, + "step": 37734 + }, + { + "epoch": 11.65, + "learning_rate": 7.825249826554836e-06, + "loss": 0.0082, + "step": 37735 + }, + { + "epoch": 11.65, + "learning_rate": 7.824761680935661e-06, + "loss": 0.0096, + "step": 37736 + }, + { + "epoch": 11.65, + "learning_rate": 7.824273540757157e-06, + "loss": 0.0116, + "step": 37737 + }, + { + "epoch": 11.65, + "learning_rate": 7.823785406020537e-06, + "loss": 0.0089, + "step": 37738 + }, + { + "epoch": 11.65, + "learning_rate": 7.823297276727028e-06, + "loss": 0.0103, + "step": 37739 + }, + { + "epoch": 11.65, + "learning_rate": 7.822809152877851e-06, + "loss": 0.0089, + "step": 37740 + }, + { + "epoch": 11.66, + "learning_rate": 7.822321034474224e-06, + "loss": 0.0106, + "step": 37741 + }, + { + "epoch": 11.66, + "learning_rate": 7.821832921517368e-06, + "loss": 0.011, + "step": 37742 + }, + { + "epoch": 11.66, + "learning_rate": 7.82134481400851e-06, + "loss": 0.0115, + "step": 37743 + }, + { + "epoch": 11.66, + "learning_rate": 7.820856711948863e-06, + "loss": 0.0103, + "step": 37744 + }, + { + "epoch": 11.66, + "learning_rate": 7.820368615339647e-06, + "loss": 0.0113, + "step": 37745 + }, + { + "epoch": 11.66, + "learning_rate": 7.819880524182094e-06, + "loss": 0.0111, + "step": 37746 + }, + { + "epoch": 11.66, + "learning_rate": 7.819392438477411e-06, + "loss": 0.0099, + "step": 37747 + }, + { + "epoch": 11.66, + "learning_rate": 7.818904358226827e-06, + "loss": 0.0123, + "step": 37748 + }, + { + "epoch": 11.66, + "learning_rate": 7.818416283431566e-06, + "loss": 0.0107, + "step": 37749 + }, + { + "epoch": 11.66, + "learning_rate": 7.817928214092838e-06, + "loss": 0.0095, + "step": 37750 + }, + { + "epoch": 11.66, + "learning_rate": 7.817440150211871e-06, + "loss": 0.0103, + "step": 37751 + }, + { + "epoch": 11.66, + "learning_rate": 7.816952091789883e-06, + "loss": 0.0106, + "step": 37752 + }, + { + "epoch": 11.66, + "learning_rate": 7.816464038828097e-06, + "loss": 0.01, + "step": 37753 + }, + { + "epoch": 11.66, + "learning_rate": 7.815975991327735e-06, + "loss": 0.0103, + "step": 37754 + }, + { + "epoch": 11.66, + "learning_rate": 7.81548794929001e-06, + "loss": 0.0099, + "step": 37755 + }, + { + "epoch": 11.66, + "learning_rate": 7.814999912716154e-06, + "loss": 0.0104, + "step": 37756 + }, + { + "epoch": 11.66, + "learning_rate": 7.81451188160738e-06, + "loss": 0.0101, + "step": 37757 + }, + { + "epoch": 11.66, + "learning_rate": 7.814023855964908e-06, + "loss": 0.0099, + "step": 37758 + }, + { + "epoch": 11.66, + "learning_rate": 7.813535835789965e-06, + "loss": 0.0088, + "step": 37759 + }, + { + "epoch": 11.66, + "learning_rate": 7.813047821083764e-06, + "loss": 0.0113, + "step": 37760 + }, + { + "epoch": 11.66, + "learning_rate": 7.81255981184753e-06, + "loss": 0.01, + "step": 37761 + }, + { + "epoch": 11.66, + "learning_rate": 7.812071808082486e-06, + "loss": 0.0097, + "step": 37762 + }, + { + "epoch": 11.66, + "learning_rate": 7.811583809789844e-06, + "loss": 0.0117, + "step": 37763 + }, + { + "epoch": 11.66, + "learning_rate": 7.811095816970833e-06, + "loss": 0.0114, + "step": 37764 + }, + { + "epoch": 11.66, + "learning_rate": 7.810607829626673e-06, + "loss": 0.0102, + "step": 37765 + }, + { + "epoch": 11.66, + "learning_rate": 7.810119847758579e-06, + "loss": 0.0109, + "step": 37766 + }, + { + "epoch": 11.66, + "learning_rate": 7.809631871367774e-06, + "loss": 0.0094, + "step": 37767 + }, + { + "epoch": 11.66, + "learning_rate": 7.809143900455483e-06, + "loss": 0.0096, + "step": 37768 + }, + { + "epoch": 11.66, + "learning_rate": 7.80865593502292e-06, + "loss": 0.0115, + "step": 37769 + }, + { + "epoch": 11.66, + "learning_rate": 7.808167975071307e-06, + "loss": 0.0088, + "step": 37770 + }, + { + "epoch": 11.66, + "learning_rate": 7.80768002060187e-06, + "loss": 0.01, + "step": 37771 + }, + { + "epoch": 11.66, + "learning_rate": 7.807192071615821e-06, + "loss": 0.0116, + "step": 37772 + }, + { + "epoch": 11.67, + "learning_rate": 7.806704128114384e-06, + "loss": 0.009, + "step": 37773 + }, + { + "epoch": 11.67, + "learning_rate": 7.806216190098783e-06, + "loss": 0.0098, + "step": 37774 + }, + { + "epoch": 11.67, + "learning_rate": 7.805728257570236e-06, + "loss": 0.0122, + "step": 37775 + }, + { + "epoch": 11.67, + "learning_rate": 7.805240330529958e-06, + "loss": 0.0103, + "step": 37776 + }, + { + "epoch": 11.67, + "learning_rate": 7.80475240897918e-06, + "loss": 0.0107, + "step": 37777 + }, + { + "epoch": 11.67, + "learning_rate": 7.804264492919113e-06, + "loss": 0.0101, + "step": 37778 + }, + { + "epoch": 11.67, + "learning_rate": 7.803776582350983e-06, + "loss": 0.0093, + "step": 37779 + }, + { + "epoch": 11.67, + "learning_rate": 7.803288677276009e-06, + "loss": 0.0104, + "step": 37780 + }, + { + "epoch": 11.67, + "learning_rate": 7.802800777695405e-06, + "loss": 0.0097, + "step": 37781 + }, + { + "epoch": 11.67, + "learning_rate": 7.802312883610403e-06, + "loss": 0.012, + "step": 37782 + }, + { + "epoch": 11.67, + "learning_rate": 7.801824995022217e-06, + "loss": 0.0105, + "step": 37783 + }, + { + "epoch": 11.67, + "learning_rate": 7.801337111932064e-06, + "loss": 0.0104, + "step": 37784 + }, + { + "epoch": 11.67, + "learning_rate": 7.80084923434117e-06, + "loss": 0.0105, + "step": 37785 + }, + { + "epoch": 11.67, + "learning_rate": 7.80036136225075e-06, + "loss": 0.0103, + "step": 37786 + }, + { + "epoch": 11.67, + "learning_rate": 7.799873495662031e-06, + "loss": 0.0097, + "step": 37787 + }, + { + "epoch": 11.67, + "learning_rate": 7.79938563457623e-06, + "loss": 0.0106, + "step": 37788 + }, + { + "epoch": 11.67, + "learning_rate": 7.798897778994566e-06, + "loss": 0.0098, + "step": 37789 + }, + { + "epoch": 11.67, + "learning_rate": 7.798409928918263e-06, + "loss": 0.0098, + "step": 37790 + }, + { + "epoch": 11.67, + "learning_rate": 7.797922084348532e-06, + "loss": 0.0103, + "step": 37791 + }, + { + "epoch": 11.67, + "learning_rate": 7.797434245286602e-06, + "loss": 0.0124, + "step": 37792 + }, + { + "epoch": 11.67, + "learning_rate": 7.796946411733695e-06, + "loss": 0.0111, + "step": 37793 + }, + { + "epoch": 11.67, + "learning_rate": 7.79645858369102e-06, + "loss": 0.0103, + "step": 37794 + }, + { + "epoch": 11.67, + "learning_rate": 7.795970761159808e-06, + "loss": 0.0112, + "step": 37795 + }, + { + "epoch": 11.67, + "learning_rate": 7.795482944141278e-06, + "loss": 0.0122, + "step": 37796 + }, + { + "epoch": 11.67, + "learning_rate": 7.79499513263664e-06, + "loss": 0.0097, + "step": 37797 + }, + { + "epoch": 11.67, + "learning_rate": 7.794507326647125e-06, + "loss": 0.0101, + "step": 37798 + }, + { + "epoch": 11.67, + "learning_rate": 7.794019526173952e-06, + "loss": 0.009, + "step": 37799 + }, + { + "epoch": 11.67, + "learning_rate": 7.793531731218336e-06, + "loss": 0.0101, + "step": 37800 + }, + { + "epoch": 11.67, + "learning_rate": 7.793043941781496e-06, + "loss": 0.0104, + "step": 37801 + }, + { + "epoch": 11.67, + "learning_rate": 7.792556157864661e-06, + "loss": 0.0097, + "step": 37802 + }, + { + "epoch": 11.67, + "learning_rate": 7.792068379469045e-06, + "loss": 0.0113, + "step": 37803 + }, + { + "epoch": 11.67, + "learning_rate": 7.791580606595866e-06, + "loss": 0.0088, + "step": 37804 + }, + { + "epoch": 11.67, + "learning_rate": 7.79109283924635e-06, + "loss": 0.0081, + "step": 37805 + }, + { + "epoch": 11.68, + "learning_rate": 7.790605077421712e-06, + "loss": 0.0104, + "step": 37806 + }, + { + "epoch": 11.68, + "learning_rate": 7.79011732112317e-06, + "loss": 0.0107, + "step": 37807 + }, + { + "epoch": 11.68, + "learning_rate": 7.789629570351956e-06, + "loss": 0.0114, + "step": 37808 + }, + { + "epoch": 11.68, + "learning_rate": 7.789141825109275e-06, + "loss": 0.0102, + "step": 37809 + }, + { + "epoch": 11.68, + "learning_rate": 7.788654085396354e-06, + "loss": 0.0099, + "step": 37810 + }, + { + "epoch": 11.68, + "learning_rate": 7.788166351214417e-06, + "loss": 0.0103, + "step": 37811 + }, + { + "epoch": 11.68, + "learning_rate": 7.787678622564674e-06, + "loss": 0.0102, + "step": 37812 + }, + { + "epoch": 11.68, + "learning_rate": 7.787190899448352e-06, + "loss": 0.0092, + "step": 37813 + }, + { + "epoch": 11.68, + "learning_rate": 7.786703181866672e-06, + "loss": 0.0106, + "step": 37814 + }, + { + "epoch": 11.68, + "learning_rate": 7.786215469820845e-06, + "loss": 0.01, + "step": 37815 + }, + { + "epoch": 11.68, + "learning_rate": 7.7857277633121e-06, + "loss": 0.01, + "step": 37816 + }, + { + "epoch": 11.68, + "learning_rate": 7.785240062341658e-06, + "loss": 0.0109, + "step": 37817 + }, + { + "epoch": 11.68, + "learning_rate": 7.784752366910731e-06, + "loss": 0.0103, + "step": 37818 + }, + { + "epoch": 11.68, + "learning_rate": 7.784264677020539e-06, + "loss": 0.0088, + "step": 37819 + }, + { + "epoch": 11.68, + "learning_rate": 7.783776992672308e-06, + "loss": 0.0103, + "step": 37820 + }, + { + "epoch": 11.68, + "learning_rate": 7.783289313867258e-06, + "loss": 0.0125, + "step": 37821 + }, + { + "epoch": 11.68, + "learning_rate": 7.7828016406066e-06, + "loss": 0.0114, + "step": 37822 + }, + { + "epoch": 11.68, + "learning_rate": 7.782313972891563e-06, + "loss": 0.0087, + "step": 37823 + }, + { + "epoch": 11.68, + "learning_rate": 7.781826310723364e-06, + "loss": 0.0092, + "step": 37824 + }, + { + "epoch": 11.68, + "learning_rate": 7.781338654103218e-06, + "loss": 0.0091, + "step": 37825 + }, + { + "epoch": 11.68, + "learning_rate": 7.780851003032352e-06, + "loss": 0.0092, + "step": 37826 + }, + { + "epoch": 11.68, + "learning_rate": 7.780363357511985e-06, + "loss": 0.0108, + "step": 37827 + }, + { + "epoch": 11.68, + "learning_rate": 7.77987571754333e-06, + "loss": 0.0093, + "step": 37828 + }, + { + "epoch": 11.68, + "learning_rate": 7.77938808312761e-06, + "loss": 0.0122, + "step": 37829 + }, + { + "epoch": 11.68, + "learning_rate": 7.77890045426605e-06, + "loss": 0.0103, + "step": 37830 + }, + { + "epoch": 11.68, + "learning_rate": 7.778412830959861e-06, + "loss": 0.0091, + "step": 37831 + }, + { + "epoch": 11.68, + "learning_rate": 7.777925213210265e-06, + "loss": 0.0098, + "step": 37832 + }, + { + "epoch": 11.68, + "learning_rate": 7.777437601018488e-06, + "loss": 0.0105, + "step": 37833 + }, + { + "epoch": 11.68, + "learning_rate": 7.776949994385742e-06, + "loss": 0.0103, + "step": 37834 + }, + { + "epoch": 11.68, + "learning_rate": 7.776462393313249e-06, + "loss": 0.0105, + "step": 37835 + }, + { + "epoch": 11.68, + "learning_rate": 7.775974797802232e-06, + "loss": 0.0099, + "step": 37836 + }, + { + "epoch": 11.68, + "learning_rate": 7.775487207853906e-06, + "loss": 0.0089, + "step": 37837 + }, + { + "epoch": 11.69, + "learning_rate": 7.774999623469494e-06, + "loss": 0.0093, + "step": 37838 + }, + { + "epoch": 11.69, + "learning_rate": 7.774512044650215e-06, + "loss": 0.0086, + "step": 37839 + }, + { + "epoch": 11.69, + "learning_rate": 7.77402447139728e-06, + "loss": 0.0106, + "step": 37840 + }, + { + "epoch": 11.69, + "learning_rate": 7.773536903711923e-06, + "loss": 0.0119, + "step": 37841 + }, + { + "epoch": 11.69, + "learning_rate": 7.773049341595354e-06, + "loss": 0.0093, + "step": 37842 + }, + { + "epoch": 11.69, + "learning_rate": 7.772561785048793e-06, + "loss": 0.0098, + "step": 37843 + }, + { + "epoch": 11.69, + "learning_rate": 7.772074234073462e-06, + "loss": 0.0108, + "step": 37844 + }, + { + "epoch": 11.69, + "learning_rate": 7.771586688670582e-06, + "loss": 0.0111, + "step": 37845 + }, + { + "epoch": 11.69, + "learning_rate": 7.771099148841366e-06, + "loss": 0.0111, + "step": 37846 + }, + { + "epoch": 11.69, + "learning_rate": 7.77061161458704e-06, + "loss": 0.0079, + "step": 37847 + }, + { + "epoch": 11.69, + "learning_rate": 7.770124085908824e-06, + "loss": 0.0098, + "step": 37848 + }, + { + "epoch": 11.69, + "learning_rate": 7.769636562807933e-06, + "loss": 0.0097, + "step": 37849 + }, + { + "epoch": 11.69, + "learning_rate": 7.769149045285582e-06, + "loss": 0.0104, + "step": 37850 + }, + { + "epoch": 11.69, + "learning_rate": 7.768661533343e-06, + "loss": 0.0099, + "step": 37851 + }, + { + "epoch": 11.69, + "learning_rate": 7.768174026981406e-06, + "loss": 0.0093, + "step": 37852 + }, + { + "epoch": 11.69, + "learning_rate": 7.76768652620201e-06, + "loss": 0.0112, + "step": 37853 + }, + { + "epoch": 11.69, + "learning_rate": 7.767199031006039e-06, + "loss": 0.0127, + "step": 37854 + }, + { + "epoch": 11.69, + "learning_rate": 7.766711541394713e-06, + "loss": 0.0094, + "step": 37855 + }, + { + "epoch": 11.69, + "learning_rate": 7.766224057369244e-06, + "loss": 0.0094, + "step": 37856 + }, + { + "epoch": 11.69, + "learning_rate": 7.765736578930859e-06, + "loss": 0.0108, + "step": 37857 + }, + { + "epoch": 11.69, + "learning_rate": 7.765249106080777e-06, + "loss": 0.0112, + "step": 37858 + }, + { + "epoch": 11.69, + "learning_rate": 7.764761638820211e-06, + "loss": 0.0104, + "step": 37859 + }, + { + "epoch": 11.69, + "learning_rate": 7.764274177150383e-06, + "loss": 0.0108, + "step": 37860 + }, + { + "epoch": 11.69, + "learning_rate": 7.763786721072518e-06, + "loss": 0.0105, + "step": 37861 + }, + { + "epoch": 11.69, + "learning_rate": 7.763299270587826e-06, + "loss": 0.0096, + "step": 37862 + }, + { + "epoch": 11.69, + "learning_rate": 7.762811825697529e-06, + "loss": 0.0123, + "step": 37863 + }, + { + "epoch": 11.69, + "learning_rate": 7.762324386402852e-06, + "loss": 0.0099, + "step": 37864 + }, + { + "epoch": 11.69, + "learning_rate": 7.76183695270501e-06, + "loss": 0.0097, + "step": 37865 + }, + { + "epoch": 11.69, + "learning_rate": 7.761349524605215e-06, + "loss": 0.0115, + "step": 37866 + }, + { + "epoch": 11.69, + "learning_rate": 7.760862102104702e-06, + "loss": 0.0098, + "step": 37867 + }, + { + "epoch": 11.69, + "learning_rate": 7.760374685204677e-06, + "loss": 0.009, + "step": 37868 + }, + { + "epoch": 11.69, + "learning_rate": 7.759887273906363e-06, + "loss": 0.0115, + "step": 37869 + }, + { + "epoch": 11.69, + "learning_rate": 7.759399868210981e-06, + "loss": 0.01, + "step": 37870 + }, + { + "epoch": 11.7, + "learning_rate": 7.758912468119747e-06, + "loss": 0.0107, + "step": 37871 + }, + { + "epoch": 11.7, + "learning_rate": 7.758425073633882e-06, + "loss": 0.0125, + "step": 37872 + }, + { + "epoch": 11.7, + "learning_rate": 7.757937684754608e-06, + "loss": 0.0116, + "step": 37873 + }, + { + "epoch": 11.7, + "learning_rate": 7.757450301483136e-06, + "loss": 0.0092, + "step": 37874 + }, + { + "epoch": 11.7, + "learning_rate": 7.756962923820692e-06, + "loss": 0.0121, + "step": 37875 + }, + { + "epoch": 11.7, + "learning_rate": 7.756475551768494e-06, + "loss": 0.0091, + "step": 37876 + }, + { + "epoch": 11.7, + "learning_rate": 7.755988185327758e-06, + "loss": 0.0115, + "step": 37877 + }, + { + "epoch": 11.7, + "learning_rate": 7.755500824499703e-06, + "loss": 0.0118, + "step": 37878 + }, + { + "epoch": 11.7, + "learning_rate": 7.755013469285555e-06, + "loss": 0.0111, + "step": 37879 + }, + { + "epoch": 11.7, + "learning_rate": 7.754526119686526e-06, + "loss": 0.0107, + "step": 37880 + }, + { + "epoch": 11.7, + "learning_rate": 7.754038775703831e-06, + "loss": 0.0099, + "step": 37881 + }, + { + "epoch": 11.7, + "learning_rate": 7.753551437338702e-06, + "loss": 0.0106, + "step": 37882 + }, + { + "epoch": 11.7, + "learning_rate": 7.753064104592349e-06, + "loss": 0.0098, + "step": 37883 + }, + { + "epoch": 11.7, + "learning_rate": 7.752576777465988e-06, + "loss": 0.0104, + "step": 37884 + }, + { + "epoch": 11.7, + "learning_rate": 7.752089455960846e-06, + "loss": 0.0099, + "step": 37885 + }, + { + "epoch": 11.7, + "learning_rate": 7.75160214007814e-06, + "loss": 0.0091, + "step": 37886 + }, + { + "epoch": 11.7, + "learning_rate": 7.751114829819086e-06, + "loss": 0.0111, + "step": 37887 + }, + { + "epoch": 11.7, + "learning_rate": 7.7506275251849e-06, + "loss": 0.0093, + "step": 37888 + }, + { + "epoch": 11.7, + "learning_rate": 7.75014022617681e-06, + "loss": 0.0112, + "step": 37889 + }, + { + "epoch": 11.7, + "learning_rate": 7.749652932796028e-06, + "loss": 0.0092, + "step": 37890 + }, + { + "epoch": 11.7, + "learning_rate": 7.749165645043771e-06, + "loss": 0.0104, + "step": 37891 + }, + { + "epoch": 11.7, + "learning_rate": 7.748678362921267e-06, + "loss": 0.0112, + "step": 37892 + }, + { + "epoch": 11.7, + "learning_rate": 7.748191086429726e-06, + "loss": 0.0112, + "step": 37893 + }, + { + "epoch": 11.7, + "learning_rate": 7.747703815570368e-06, + "loss": 0.0104, + "step": 37894 + }, + { + "epoch": 11.7, + "learning_rate": 7.747216550344417e-06, + "loss": 0.0103, + "step": 37895 + }, + { + "epoch": 11.7, + "learning_rate": 7.746729290753088e-06, + "loss": 0.0084, + "step": 37896 + }, + { + "epoch": 11.7, + "learning_rate": 7.746242036797598e-06, + "loss": 0.0099, + "step": 37897 + }, + { + "epoch": 11.7, + "learning_rate": 7.745754788479171e-06, + "loss": 0.0109, + "step": 37898 + }, + { + "epoch": 11.7, + "learning_rate": 7.745267545799019e-06, + "loss": 0.0115, + "step": 37899 + }, + { + "epoch": 11.7, + "learning_rate": 7.744780308758364e-06, + "loss": 0.0095, + "step": 37900 + }, + { + "epoch": 11.7, + "learning_rate": 7.744293077358429e-06, + "loss": 0.0113, + "step": 37901 + }, + { + "epoch": 11.7, + "learning_rate": 7.743805851600422e-06, + "loss": 0.0107, + "step": 37902 + }, + { + "epoch": 11.71, + "learning_rate": 7.743318631485573e-06, + "loss": 0.0117, + "step": 37903 + }, + { + "epoch": 11.71, + "learning_rate": 7.742831417015096e-06, + "loss": 0.0113, + "step": 37904 + }, + { + "epoch": 11.71, + "learning_rate": 7.742344208190204e-06, + "loss": 0.01, + "step": 37905 + }, + { + "epoch": 11.71, + "learning_rate": 7.741857005012125e-06, + "loss": 0.0103, + "step": 37906 + }, + { + "epoch": 11.71, + "learning_rate": 7.741369807482076e-06, + "loss": 0.0102, + "step": 37907 + }, + { + "epoch": 11.71, + "learning_rate": 7.740882615601269e-06, + "loss": 0.0117, + "step": 37908 + }, + { + "epoch": 11.71, + "learning_rate": 7.740395429370926e-06, + "loss": 0.0105, + "step": 37909 + }, + { + "epoch": 11.71, + "learning_rate": 7.739908248792268e-06, + "loss": 0.0102, + "step": 37910 + }, + { + "epoch": 11.71, + "learning_rate": 7.739421073866513e-06, + "loss": 0.0098, + "step": 37911 + }, + { + "epoch": 11.71, + "learning_rate": 7.738933904594874e-06, + "loss": 0.0092, + "step": 37912 + }, + { + "epoch": 11.71, + "learning_rate": 7.738446740978577e-06, + "loss": 0.0109, + "step": 37913 + }, + { + "epoch": 11.71, + "learning_rate": 7.737959583018836e-06, + "loss": 0.0094, + "step": 37914 + }, + { + "epoch": 11.71, + "learning_rate": 7.73747243071687e-06, + "loss": 0.0125, + "step": 37915 + }, + { + "epoch": 11.71, + "learning_rate": 7.7369852840739e-06, + "loss": 0.0104, + "step": 37916 + }, + { + "epoch": 11.71, + "learning_rate": 7.736498143091143e-06, + "loss": 0.0104, + "step": 37917 + }, + { + "epoch": 11.71, + "learning_rate": 7.736011007769817e-06, + "loss": 0.0106, + "step": 37918 + }, + { + "epoch": 11.71, + "learning_rate": 7.735523878111135e-06, + "loss": 0.0109, + "step": 37919 + }, + { + "epoch": 11.71, + "learning_rate": 7.735036754116328e-06, + "loss": 0.0087, + "step": 37920 + }, + { + "epoch": 11.71, + "learning_rate": 7.734549635786604e-06, + "loss": 0.0096, + "step": 37921 + }, + { + "epoch": 11.71, + "learning_rate": 7.734062523123183e-06, + "loss": 0.0092, + "step": 37922 + }, + { + "epoch": 11.71, + "learning_rate": 7.733575416127288e-06, + "loss": 0.0111, + "step": 37923 + }, + { + "epoch": 11.71, + "learning_rate": 7.733088314800133e-06, + "loss": 0.011, + "step": 37924 + }, + { + "epoch": 11.71, + "learning_rate": 7.732601219142935e-06, + "loss": 0.0096, + "step": 37925 + }, + { + "epoch": 11.71, + "learning_rate": 7.732114129156922e-06, + "loss": 0.0093, + "step": 37926 + }, + { + "epoch": 11.71, + "learning_rate": 7.731627044843298e-06, + "loss": 0.0099, + "step": 37927 + }, + { + "epoch": 11.71, + "learning_rate": 7.731139966203291e-06, + "loss": 0.0118, + "step": 37928 + }, + { + "epoch": 11.71, + "learning_rate": 7.73065289323812e-06, + "loss": 0.0104, + "step": 37929 + }, + { + "epoch": 11.71, + "learning_rate": 7.730165825948995e-06, + "loss": 0.0089, + "step": 37930 + }, + { + "epoch": 11.71, + "learning_rate": 7.729678764337139e-06, + "loss": 0.011, + "step": 37931 + }, + { + "epoch": 11.71, + "learning_rate": 7.729191708403775e-06, + "loss": 0.01, + "step": 37932 + }, + { + "epoch": 11.71, + "learning_rate": 7.728704658150113e-06, + "loss": 0.0118, + "step": 37933 + }, + { + "epoch": 11.71, + "learning_rate": 7.728217613577375e-06, + "loss": 0.0129, + "step": 37934 + }, + { + "epoch": 11.72, + "learning_rate": 7.727730574686782e-06, + "loss": 0.0121, + "step": 37935 + }, + { + "epoch": 11.72, + "learning_rate": 7.727243541479547e-06, + "loss": 0.0105, + "step": 37936 + }, + { + "epoch": 11.72, + "learning_rate": 7.72675651395689e-06, + "loss": 0.0097, + "step": 37937 + }, + { + "epoch": 11.72, + "learning_rate": 7.726269492120033e-06, + "loss": 0.009, + "step": 37938 + }, + { + "epoch": 11.72, + "learning_rate": 7.725782475970189e-06, + "loss": 0.0108, + "step": 37939 + }, + { + "epoch": 11.72, + "learning_rate": 7.725295465508572e-06, + "loss": 0.0111, + "step": 37940 + }, + { + "epoch": 11.72, + "learning_rate": 7.724808460736415e-06, + "loss": 0.0129, + "step": 37941 + }, + { + "epoch": 11.72, + "learning_rate": 7.724321461654922e-06, + "loss": 0.0105, + "step": 37942 + }, + { + "epoch": 11.72, + "learning_rate": 7.723834468265316e-06, + "loss": 0.0122, + "step": 37943 + }, + { + "epoch": 11.72, + "learning_rate": 7.723347480568818e-06, + "loss": 0.0109, + "step": 37944 + }, + { + "epoch": 11.72, + "learning_rate": 7.722860498566641e-06, + "loss": 0.0104, + "step": 37945 + }, + { + "epoch": 11.72, + "learning_rate": 7.722373522260005e-06, + "loss": 0.0138, + "step": 37946 + }, + { + "epoch": 11.72, + "learning_rate": 7.721886551650132e-06, + "loss": 0.0117, + "step": 37947 + }, + { + "epoch": 11.72, + "learning_rate": 7.721399586738231e-06, + "loss": 0.0103, + "step": 37948 + }, + { + "epoch": 11.72, + "learning_rate": 7.720912627525528e-06, + "loss": 0.0104, + "step": 37949 + }, + { + "epoch": 11.72, + "learning_rate": 7.720425674013234e-06, + "loss": 0.01, + "step": 37950 + }, + { + "epoch": 11.72, + "learning_rate": 7.719938726202577e-06, + "loss": 0.0101, + "step": 37951 + }, + { + "epoch": 11.72, + "learning_rate": 7.719451784094768e-06, + "loss": 0.0096, + "step": 37952 + }, + { + "epoch": 11.72, + "learning_rate": 7.718964847691022e-06, + "loss": 0.0113, + "step": 37953 + }, + { + "epoch": 11.72, + "learning_rate": 7.718477916992566e-06, + "loss": 0.0106, + "step": 37954 + }, + { + "epoch": 11.72, + "learning_rate": 7.71799099200061e-06, + "loss": 0.011, + "step": 37955 + }, + { + "epoch": 11.72, + "learning_rate": 7.717504072716374e-06, + "loss": 0.0102, + "step": 37956 + }, + { + "epoch": 11.72, + "learning_rate": 7.717017159141081e-06, + "loss": 0.0094, + "step": 37957 + }, + { + "epoch": 11.72, + "learning_rate": 7.716530251275939e-06, + "loss": 0.0108, + "step": 37958 + }, + { + "epoch": 11.72, + "learning_rate": 7.716043349122174e-06, + "loss": 0.0107, + "step": 37959 + }, + { + "epoch": 11.72, + "learning_rate": 7.715556452681003e-06, + "loss": 0.0098, + "step": 37960 + }, + { + "epoch": 11.72, + "learning_rate": 7.715069561953638e-06, + "loss": 0.01, + "step": 37961 + }, + { + "epoch": 11.72, + "learning_rate": 7.714582676941303e-06, + "loss": 0.0123, + "step": 37962 + }, + { + "epoch": 11.72, + "learning_rate": 7.714095797645215e-06, + "loss": 0.0101, + "step": 37963 + }, + { + "epoch": 11.72, + "learning_rate": 7.713608924066586e-06, + "loss": 0.0083, + "step": 37964 + }, + { + "epoch": 11.72, + "learning_rate": 7.71312205620664e-06, + "loss": 0.0111, + "step": 37965 + }, + { + "epoch": 11.72, + "learning_rate": 7.712635194066595e-06, + "loss": 0.0117, + "step": 37966 + }, + { + "epoch": 11.72, + "learning_rate": 7.712148337647667e-06, + "loss": 0.0114, + "step": 37967 + }, + { + "epoch": 11.73, + "learning_rate": 7.711661486951069e-06, + "loss": 0.0113, + "step": 37968 + }, + { + "epoch": 11.73, + "learning_rate": 7.711174641978026e-06, + "loss": 0.0118, + "step": 37969 + }, + { + "epoch": 11.73, + "learning_rate": 7.710687802729753e-06, + "loss": 0.01, + "step": 37970 + }, + { + "epoch": 11.73, + "learning_rate": 7.710200969207465e-06, + "loss": 0.0137, + "step": 37971 + }, + { + "epoch": 11.73, + "learning_rate": 7.709714141412384e-06, + "loss": 0.0096, + "step": 37972 + }, + { + "epoch": 11.73, + "learning_rate": 7.709227319345725e-06, + "loss": 0.0099, + "step": 37973 + }, + { + "epoch": 11.73, + "learning_rate": 7.708740503008705e-06, + "loss": 0.0102, + "step": 37974 + }, + { + "epoch": 11.73, + "learning_rate": 7.708253692402548e-06, + "loss": 0.0099, + "step": 37975 + }, + { + "epoch": 11.73, + "learning_rate": 7.70776688752846e-06, + "loss": 0.0116, + "step": 37976 + }, + { + "epoch": 11.73, + "learning_rate": 7.707280088387668e-06, + "loss": 0.0101, + "step": 37977 + }, + { + "epoch": 11.73, + "learning_rate": 7.706793294981389e-06, + "loss": 0.011, + "step": 37978 + }, + { + "epoch": 11.73, + "learning_rate": 7.706306507310832e-06, + "loss": 0.0105, + "step": 37979 + }, + { + "epoch": 11.73, + "learning_rate": 7.705819725377226e-06, + "loss": 0.0123, + "step": 37980 + }, + { + "epoch": 11.73, + "learning_rate": 7.705332949181778e-06, + "loss": 0.0097, + "step": 37981 + }, + { + "epoch": 11.73, + "learning_rate": 7.704846178725717e-06, + "loss": 0.0112, + "step": 37982 + }, + { + "epoch": 11.73, + "learning_rate": 7.704359414010251e-06, + "loss": 0.012, + "step": 37983 + }, + { + "epoch": 11.73, + "learning_rate": 7.7038726550366e-06, + "loss": 0.0112, + "step": 37984 + }, + { + "epoch": 11.73, + "learning_rate": 7.70338590180599e-06, + "loss": 0.0101, + "step": 37985 + }, + { + "epoch": 11.73, + "learning_rate": 7.702899154319622e-06, + "loss": 0.0109, + "step": 37986 + }, + { + "epoch": 11.73, + "learning_rate": 7.702412412578724e-06, + "loss": 0.0108, + "step": 37987 + }, + { + "epoch": 11.73, + "learning_rate": 7.701925676584516e-06, + "loss": 0.0105, + "step": 37988 + }, + { + "epoch": 11.73, + "learning_rate": 7.701438946338205e-06, + "loss": 0.0097, + "step": 37989 + }, + { + "epoch": 11.73, + "learning_rate": 7.700952221841015e-06, + "loss": 0.01, + "step": 37990 + }, + { + "epoch": 11.73, + "learning_rate": 7.700465503094168e-06, + "loss": 0.0106, + "step": 37991 + }, + { + "epoch": 11.73, + "learning_rate": 7.699978790098871e-06, + "loss": 0.0115, + "step": 37992 + }, + { + "epoch": 11.73, + "learning_rate": 7.699492082856347e-06, + "loss": 0.0114, + "step": 37993 + }, + { + "epoch": 11.73, + "learning_rate": 7.699005381367818e-06, + "loss": 0.0119, + "step": 37994 + }, + { + "epoch": 11.73, + "learning_rate": 7.69851868563449e-06, + "loss": 0.0115, + "step": 37995 + }, + { + "epoch": 11.73, + "learning_rate": 7.698031995657588e-06, + "loss": 0.0085, + "step": 37996 + }, + { + "epoch": 11.73, + "learning_rate": 7.697545311438333e-06, + "loss": 0.0104, + "step": 37997 + }, + { + "epoch": 11.73, + "learning_rate": 7.697058632977931e-06, + "loss": 0.0109, + "step": 37998 + }, + { + "epoch": 11.73, + "learning_rate": 7.696571960277606e-06, + "loss": 0.01, + "step": 37999 + }, + { + "epoch": 11.74, + "learning_rate": 7.696085293338578e-06, + "loss": 0.0099, + "step": 38000 + }, + { + "epoch": 11.74, + "learning_rate": 7.695598632162058e-06, + "loss": 0.012, + "step": 38001 + }, + { + "epoch": 11.74, + "learning_rate": 7.695111976749267e-06, + "loss": 0.0116, + "step": 38002 + }, + { + "epoch": 11.74, + "learning_rate": 7.694625327101423e-06, + "loss": 0.0102, + "step": 38003 + }, + { + "epoch": 11.74, + "learning_rate": 7.69413868321974e-06, + "loss": 0.0129, + "step": 38004 + }, + { + "epoch": 11.74, + "learning_rate": 7.693652045105434e-06, + "loss": 0.0112, + "step": 38005 + }, + { + "epoch": 11.74, + "learning_rate": 7.693165412759732e-06, + "loss": 0.011, + "step": 38006 + }, + { + "epoch": 11.74, + "learning_rate": 7.692678786183838e-06, + "loss": 0.0109, + "step": 38007 + }, + { + "epoch": 11.74, + "learning_rate": 7.692192165378977e-06, + "loss": 0.0108, + "step": 38008 + }, + { + "epoch": 11.74, + "learning_rate": 7.691705550346366e-06, + "loss": 0.0125, + "step": 38009 + }, + { + "epoch": 11.74, + "learning_rate": 7.691218941087216e-06, + "loss": 0.0113, + "step": 38010 + }, + { + "epoch": 11.74, + "learning_rate": 7.69073233760275e-06, + "loss": 0.0093, + "step": 38011 + }, + { + "epoch": 11.74, + "learning_rate": 7.690245739894187e-06, + "loss": 0.011, + "step": 38012 + }, + { + "epoch": 11.74, + "learning_rate": 7.689759147962736e-06, + "loss": 0.0101, + "step": 38013 + }, + { + "epoch": 11.74, + "learning_rate": 7.689272561809621e-06, + "loss": 0.0116, + "step": 38014 + }, + { + "epoch": 11.74, + "learning_rate": 7.688785981436055e-06, + "loss": 0.0098, + "step": 38015 + }, + { + "epoch": 11.74, + "learning_rate": 7.688299406843263e-06, + "loss": 0.0106, + "step": 38016 + }, + { + "epoch": 11.74, + "learning_rate": 7.687812838032449e-06, + "loss": 0.0107, + "step": 38017 + }, + { + "epoch": 11.74, + "learning_rate": 7.68732627500484e-06, + "loss": 0.0109, + "step": 38018 + }, + { + "epoch": 11.74, + "learning_rate": 7.686839717761651e-06, + "loss": 0.0108, + "step": 38019 + }, + { + "epoch": 11.74, + "learning_rate": 7.686353166304094e-06, + "loss": 0.0108, + "step": 38020 + }, + { + "epoch": 11.74, + "learning_rate": 7.685866620633391e-06, + "loss": 0.0104, + "step": 38021 + }, + { + "epoch": 11.74, + "learning_rate": 7.68538008075076e-06, + "loss": 0.0102, + "step": 38022 + }, + { + "epoch": 11.74, + "learning_rate": 7.684893546657411e-06, + "loss": 0.0107, + "step": 38023 + }, + { + "epoch": 11.74, + "learning_rate": 7.68440701835457e-06, + "loss": 0.0117, + "step": 38024 + }, + { + "epoch": 11.74, + "learning_rate": 7.683920495843449e-06, + "loss": 0.0106, + "step": 38025 + }, + { + "epoch": 11.74, + "learning_rate": 7.683433979125264e-06, + "loss": 0.0121, + "step": 38026 + }, + { + "epoch": 11.74, + "learning_rate": 7.68294746820123e-06, + "loss": 0.0114, + "step": 38027 + }, + { + "epoch": 11.74, + "learning_rate": 7.682460963072573e-06, + "loss": 0.0114, + "step": 38028 + }, + { + "epoch": 11.74, + "learning_rate": 7.6819744637405e-06, + "loss": 0.0135, + "step": 38029 + }, + { + "epoch": 11.74, + "learning_rate": 7.68148797020623e-06, + "loss": 0.0092, + "step": 38030 + }, + { + "epoch": 11.74, + "learning_rate": 7.681001482470987e-06, + "loss": 0.0114, + "step": 38031 + }, + { + "epoch": 11.75, + "learning_rate": 7.680515000535978e-06, + "loss": 0.0108, + "step": 38032 + }, + { + "epoch": 11.75, + "learning_rate": 7.680028524402424e-06, + "loss": 0.0102, + "step": 38033 + }, + { + "epoch": 11.75, + "learning_rate": 7.679542054071546e-06, + "loss": 0.0093, + "step": 38034 + }, + { + "epoch": 11.75, + "learning_rate": 7.679055589544553e-06, + "loss": 0.0098, + "step": 38035 + }, + { + "epoch": 11.75, + "learning_rate": 7.678569130822665e-06, + "loss": 0.012, + "step": 38036 + }, + { + "epoch": 11.75, + "learning_rate": 7.678082677907103e-06, + "loss": 0.0109, + "step": 38037 + }, + { + "epoch": 11.75, + "learning_rate": 7.677596230799073e-06, + "loss": 0.01, + "step": 38038 + }, + { + "epoch": 11.75, + "learning_rate": 7.677109789499802e-06, + "loss": 0.01, + "step": 38039 + }, + { + "epoch": 11.75, + "learning_rate": 7.676623354010507e-06, + "loss": 0.0101, + "step": 38040 + }, + { + "epoch": 11.75, + "learning_rate": 7.676136924332394e-06, + "loss": 0.0098, + "step": 38041 + }, + { + "epoch": 11.75, + "learning_rate": 7.67565050046669e-06, + "loss": 0.01, + "step": 38042 + }, + { + "epoch": 11.75, + "learning_rate": 7.675164082414607e-06, + "loss": 0.0115, + "step": 38043 + }, + { + "epoch": 11.75, + "learning_rate": 7.674677670177362e-06, + "loss": 0.0108, + "step": 38044 + }, + { + "epoch": 11.75, + "learning_rate": 7.674191263756174e-06, + "loss": 0.0108, + "step": 38045 + }, + { + "epoch": 11.75, + "learning_rate": 7.673704863152259e-06, + "loss": 0.0121, + "step": 38046 + }, + { + "epoch": 11.75, + "learning_rate": 7.67321846836683e-06, + "loss": 0.0115, + "step": 38047 + }, + { + "epoch": 11.75, + "learning_rate": 7.672732079401103e-06, + "loss": 0.0133, + "step": 38048 + }, + { + "epoch": 11.75, + "learning_rate": 7.672245696256303e-06, + "loss": 0.0108, + "step": 38049 + }, + { + "epoch": 11.75, + "learning_rate": 7.67175931893364e-06, + "loss": 0.0105, + "step": 38050 + }, + { + "epoch": 11.75, + "learning_rate": 7.671272947434328e-06, + "loss": 0.0124, + "step": 38051 + }, + { + "epoch": 11.75, + "learning_rate": 7.67078658175959e-06, + "loss": 0.0096, + "step": 38052 + }, + { + "epoch": 11.75, + "learning_rate": 7.670300221910642e-06, + "loss": 0.012, + "step": 38053 + }, + { + "epoch": 11.75, + "learning_rate": 7.669813867888692e-06, + "loss": 0.0101, + "step": 38054 + }, + { + "epoch": 11.75, + "learning_rate": 7.669327519694968e-06, + "loss": 0.0118, + "step": 38055 + }, + { + "epoch": 11.75, + "learning_rate": 7.66884117733068e-06, + "loss": 0.0113, + "step": 38056 + }, + { + "epoch": 11.75, + "learning_rate": 7.668354840797043e-06, + "loss": 0.0093, + "step": 38057 + }, + { + "epoch": 11.75, + "learning_rate": 7.667868510095276e-06, + "loss": 0.0121, + "step": 38058 + }, + { + "epoch": 11.75, + "learning_rate": 7.667382185226598e-06, + "loss": 0.0089, + "step": 38059 + }, + { + "epoch": 11.75, + "learning_rate": 7.666895866192222e-06, + "loss": 0.0111, + "step": 38060 + }, + { + "epoch": 11.75, + "learning_rate": 7.66640955299336e-06, + "loss": 0.0103, + "step": 38061 + }, + { + "epoch": 11.75, + "learning_rate": 7.665923245631239e-06, + "loss": 0.0107, + "step": 38062 + }, + { + "epoch": 11.75, + "learning_rate": 7.665436944107068e-06, + "loss": 0.0121, + "step": 38063 + }, + { + "epoch": 11.75, + "learning_rate": 7.664950648422063e-06, + "loss": 0.01, + "step": 38064 + }, + { + "epoch": 11.76, + "learning_rate": 7.664464358577448e-06, + "loss": 0.0109, + "step": 38065 + }, + { + "epoch": 11.76, + "learning_rate": 7.663978074574427e-06, + "loss": 0.0109, + "step": 38066 + }, + { + "epoch": 11.76, + "learning_rate": 7.663491796414227e-06, + "loss": 0.0104, + "step": 38067 + }, + { + "epoch": 11.76, + "learning_rate": 7.66300552409806e-06, + "loss": 0.0115, + "step": 38068 + }, + { + "epoch": 11.76, + "learning_rate": 7.66251925762714e-06, + "loss": 0.011, + "step": 38069 + }, + { + "epoch": 11.76, + "learning_rate": 7.662032997002687e-06, + "loss": 0.0111, + "step": 38070 + }, + { + "epoch": 11.76, + "learning_rate": 7.661546742225917e-06, + "loss": 0.0109, + "step": 38071 + }, + { + "epoch": 11.76, + "learning_rate": 7.661060493298042e-06, + "loss": 0.01, + "step": 38072 + }, + { + "epoch": 11.76, + "learning_rate": 7.660574250220283e-06, + "loss": 0.0119, + "step": 38073 + }, + { + "epoch": 11.76, + "learning_rate": 7.660088012993857e-06, + "loss": 0.0121, + "step": 38074 + }, + { + "epoch": 11.76, + "learning_rate": 7.659601781619974e-06, + "loss": 0.0109, + "step": 38075 + }, + { + "epoch": 11.76, + "learning_rate": 7.659115556099854e-06, + "loss": 0.0103, + "step": 38076 + }, + { + "epoch": 11.76, + "learning_rate": 7.658629336434715e-06, + "loss": 0.0113, + "step": 38077 + }, + { + "epoch": 11.76, + "learning_rate": 7.658143122625771e-06, + "loss": 0.0097, + "step": 38078 + }, + { + "epoch": 11.76, + "learning_rate": 7.657656914674235e-06, + "loss": 0.0104, + "step": 38079 + }, + { + "epoch": 11.76, + "learning_rate": 7.657170712581329e-06, + "loss": 0.0093, + "step": 38080 + }, + { + "epoch": 11.76, + "learning_rate": 7.656684516348268e-06, + "loss": 0.0103, + "step": 38081 + }, + { + "epoch": 11.76, + "learning_rate": 7.656198325976262e-06, + "loss": 0.0128, + "step": 38082 + }, + { + "epoch": 11.76, + "learning_rate": 7.655712141466533e-06, + "loss": 0.0107, + "step": 38083 + }, + { + "epoch": 11.76, + "learning_rate": 7.655225962820299e-06, + "loss": 0.0099, + "step": 38084 + }, + { + "epoch": 11.76, + "learning_rate": 7.65473979003877e-06, + "loss": 0.0106, + "step": 38085 + }, + { + "epoch": 11.76, + "learning_rate": 7.654253623123163e-06, + "loss": 0.0112, + "step": 38086 + }, + { + "epoch": 11.76, + "learning_rate": 7.653767462074698e-06, + "loss": 0.0111, + "step": 38087 + }, + { + "epoch": 11.76, + "learning_rate": 7.653281306894587e-06, + "loss": 0.0098, + "step": 38088 + }, + { + "epoch": 11.76, + "learning_rate": 7.652795157584046e-06, + "loss": 0.01, + "step": 38089 + }, + { + "epoch": 11.76, + "learning_rate": 7.652309014144297e-06, + "loss": 0.0092, + "step": 38090 + }, + { + "epoch": 11.76, + "learning_rate": 7.651822876576549e-06, + "loss": 0.0126, + "step": 38091 + }, + { + "epoch": 11.76, + "learning_rate": 7.651336744882018e-06, + "loss": 0.0098, + "step": 38092 + }, + { + "epoch": 11.76, + "learning_rate": 7.650850619061925e-06, + "loss": 0.0106, + "step": 38093 + }, + { + "epoch": 11.76, + "learning_rate": 7.650364499117483e-06, + "loss": 0.0111, + "step": 38094 + }, + { + "epoch": 11.76, + "learning_rate": 7.649878385049906e-06, + "loss": 0.0111, + "step": 38095 + }, + { + "epoch": 11.76, + "learning_rate": 7.649392276860416e-06, + "loss": 0.0094, + "step": 38096 + }, + { + "epoch": 11.77, + "learning_rate": 7.64890617455022e-06, + "loss": 0.0095, + "step": 38097 + }, + { + "epoch": 11.77, + "learning_rate": 7.64842007812054e-06, + "loss": 0.0121, + "step": 38098 + }, + { + "epoch": 11.77, + "learning_rate": 7.647933987572592e-06, + "loss": 0.0095, + "step": 38099 + }, + { + "epoch": 11.77, + "learning_rate": 7.647447902907585e-06, + "loss": 0.0097, + "step": 38100 + }, + { + "epoch": 11.77, + "learning_rate": 7.646961824126743e-06, + "loss": 0.0124, + "step": 38101 + }, + { + "epoch": 11.77, + "learning_rate": 7.646475751231282e-06, + "loss": 0.0102, + "step": 38102 + }, + { + "epoch": 11.77, + "learning_rate": 7.64598968422241e-06, + "loss": 0.0123, + "step": 38103 + }, + { + "epoch": 11.77, + "learning_rate": 7.645503623101348e-06, + "loss": 0.0106, + "step": 38104 + }, + { + "epoch": 11.77, + "learning_rate": 7.645017567869313e-06, + "loss": 0.0162, + "step": 38105 + }, + { + "epoch": 11.77, + "learning_rate": 7.644531518527516e-06, + "loss": 0.0108, + "step": 38106 + }, + { + "epoch": 11.77, + "learning_rate": 7.644045475077175e-06, + "loss": 0.0093, + "step": 38107 + }, + { + "epoch": 11.77, + "learning_rate": 7.643559437519509e-06, + "loss": 0.01, + "step": 38108 + }, + { + "epoch": 11.77, + "learning_rate": 7.643073405855729e-06, + "loss": 0.0094, + "step": 38109 + }, + { + "epoch": 11.77, + "learning_rate": 7.64258738008705e-06, + "loss": 0.0141, + "step": 38110 + }, + { + "epoch": 11.77, + "learning_rate": 7.642101360214693e-06, + "loss": 0.0113, + "step": 38111 + }, + { + "epoch": 11.77, + "learning_rate": 7.64161534623987e-06, + "loss": 0.0104, + "step": 38112 + }, + { + "epoch": 11.77, + "learning_rate": 7.641129338163796e-06, + "loss": 0.0112, + "step": 38113 + }, + { + "epoch": 11.77, + "learning_rate": 7.640643335987687e-06, + "loss": 0.0112, + "step": 38114 + }, + { + "epoch": 11.77, + "learning_rate": 7.640157339712764e-06, + "loss": 0.0102, + "step": 38115 + }, + { + "epoch": 11.77, + "learning_rate": 7.639671349340235e-06, + "loss": 0.0095, + "step": 38116 + }, + { + "epoch": 11.77, + "learning_rate": 7.639185364871316e-06, + "loss": 0.0105, + "step": 38117 + }, + { + "epoch": 11.77, + "learning_rate": 7.638699386307229e-06, + "loss": 0.0098, + "step": 38118 + }, + { + "epoch": 11.77, + "learning_rate": 7.638213413649183e-06, + "loss": 0.0093, + "step": 38119 + }, + { + "epoch": 11.77, + "learning_rate": 7.637727446898395e-06, + "loss": 0.0099, + "step": 38120 + }, + { + "epoch": 11.77, + "learning_rate": 7.637241486056083e-06, + "loss": 0.0121, + "step": 38121 + }, + { + "epoch": 11.77, + "learning_rate": 7.636755531123463e-06, + "loss": 0.0101, + "step": 38122 + }, + { + "epoch": 11.77, + "learning_rate": 7.636269582101745e-06, + "loss": 0.0107, + "step": 38123 + }, + { + "epoch": 11.77, + "learning_rate": 7.635783638992153e-06, + "loss": 0.012, + "step": 38124 + }, + { + "epoch": 11.77, + "learning_rate": 7.635297701795892e-06, + "loss": 0.0113, + "step": 38125 + }, + { + "epoch": 11.77, + "learning_rate": 7.634811770514183e-06, + "loss": 0.0098, + "step": 38126 + }, + { + "epoch": 11.77, + "learning_rate": 7.634325845148246e-06, + "loss": 0.0126, + "step": 38127 + }, + { + "epoch": 11.77, + "learning_rate": 7.633839925699285e-06, + "loss": 0.0091, + "step": 38128 + }, + { + "epoch": 11.77, + "learning_rate": 7.633354012168526e-06, + "loss": 0.0083, + "step": 38129 + }, + { + "epoch": 11.78, + "learning_rate": 7.632868104557181e-06, + "loss": 0.0098, + "step": 38130 + }, + { + "epoch": 11.78, + "learning_rate": 7.632382202866462e-06, + "loss": 0.0109, + "step": 38131 + }, + { + "epoch": 11.78, + "learning_rate": 7.631896307097587e-06, + "loss": 0.0088, + "step": 38132 + }, + { + "epoch": 11.78, + "learning_rate": 7.631410417251774e-06, + "loss": 0.0087, + "step": 38133 + }, + { + "epoch": 11.78, + "learning_rate": 7.630924533330234e-06, + "loss": 0.0111, + "step": 38134 + }, + { + "epoch": 11.78, + "learning_rate": 7.630438655334182e-06, + "loss": 0.0109, + "step": 38135 + }, + { + "epoch": 11.78, + "learning_rate": 7.62995278326484e-06, + "loss": 0.0111, + "step": 38136 + }, + { + "epoch": 11.78, + "learning_rate": 7.629466917123413e-06, + "loss": 0.01, + "step": 38137 + }, + { + "epoch": 11.78, + "learning_rate": 7.628981056911122e-06, + "loss": 0.0125, + "step": 38138 + }, + { + "epoch": 11.78, + "learning_rate": 7.6284952026291855e-06, + "loss": 0.0115, + "step": 38139 + }, + { + "epoch": 11.78, + "learning_rate": 7.628009354278814e-06, + "loss": 0.0106, + "step": 38140 + }, + { + "epoch": 11.78, + "learning_rate": 7.62752351186122e-06, + "loss": 0.0111, + "step": 38141 + }, + { + "epoch": 11.78, + "learning_rate": 7.627037675377626e-06, + "loss": 0.0127, + "step": 38142 + }, + { + "epoch": 11.78, + "learning_rate": 7.626551844829244e-06, + "loss": 0.0095, + "step": 38143 + }, + { + "epoch": 11.78, + "learning_rate": 7.6260660202172865e-06, + "loss": 0.012, + "step": 38144 + }, + { + "epoch": 11.78, + "learning_rate": 7.62558020154297e-06, + "loss": 0.0095, + "step": 38145 + }, + { + "epoch": 11.78, + "learning_rate": 7.625094388807514e-06, + "loss": 0.0108, + "step": 38146 + }, + { + "epoch": 11.78, + "learning_rate": 7.624608582012129e-06, + "loss": 0.01, + "step": 38147 + }, + { + "epoch": 11.78, + "learning_rate": 7.624122781158028e-06, + "loss": 0.0133, + "step": 38148 + }, + { + "epoch": 11.78, + "learning_rate": 7.623636986246434e-06, + "loss": 0.0124, + "step": 38149 + }, + { + "epoch": 11.78, + "learning_rate": 7.623151197278555e-06, + "loss": 0.0122, + "step": 38150 + }, + { + "epoch": 11.78, + "learning_rate": 7.622665414255607e-06, + "loss": 0.0103, + "step": 38151 + }, + { + "epoch": 11.78, + "learning_rate": 7.6221796371788105e-06, + "loss": 0.0122, + "step": 38152 + }, + { + "epoch": 11.78, + "learning_rate": 7.621693866049373e-06, + "loss": 0.0116, + "step": 38153 + }, + { + "epoch": 11.78, + "learning_rate": 7.621208100868514e-06, + "loss": 0.0117, + "step": 38154 + }, + { + "epoch": 11.78, + "learning_rate": 7.62072234163745e-06, + "loss": 0.0096, + "step": 38155 + }, + { + "epoch": 11.78, + "learning_rate": 7.620236588357388e-06, + "loss": 0.0118, + "step": 38156 + }, + { + "epoch": 11.78, + "learning_rate": 7.619750841029551e-06, + "loss": 0.011, + "step": 38157 + }, + { + "epoch": 11.78, + "learning_rate": 7.6192650996551535e-06, + "loss": 0.0112, + "step": 38158 + }, + { + "epoch": 11.78, + "learning_rate": 7.618779364235402e-06, + "loss": 0.0119, + "step": 38159 + }, + { + "epoch": 11.78, + "learning_rate": 7.618293634771522e-06, + "loss": 0.01, + "step": 38160 + }, + { + "epoch": 11.78, + "learning_rate": 7.6178079112647255e-06, + "loss": 0.0135, + "step": 38161 + }, + { + "epoch": 11.79, + "learning_rate": 7.6173221937162225e-06, + "loss": 0.0098, + "step": 38162 + }, + { + "epoch": 11.79, + "learning_rate": 7.6168364821272325e-06, + "loss": 0.0097, + "step": 38163 + }, + { + "epoch": 11.79, + "learning_rate": 7.616350776498971e-06, + "loss": 0.0096, + "step": 38164 + }, + { + "epoch": 11.79, + "learning_rate": 7.615865076832649e-06, + "loss": 0.0127, + "step": 38165 + }, + { + "epoch": 11.79, + "learning_rate": 7.615379383129482e-06, + "loss": 0.0107, + "step": 38166 + }, + { + "epoch": 11.79, + "learning_rate": 7.614893695390689e-06, + "loss": 0.0104, + "step": 38167 + }, + { + "epoch": 11.79, + "learning_rate": 7.61440801361748e-06, + "loss": 0.0117, + "step": 38168 + }, + { + "epoch": 11.79, + "learning_rate": 7.6139223378110706e-06, + "loss": 0.0124, + "step": 38169 + }, + { + "epoch": 11.79, + "learning_rate": 7.61343666797268e-06, + "loss": 0.0107, + "step": 38170 + }, + { + "epoch": 11.79, + "learning_rate": 7.612951004103518e-06, + "loss": 0.0109, + "step": 38171 + }, + { + "epoch": 11.79, + "learning_rate": 7.612465346204798e-06, + "loss": 0.0092, + "step": 38172 + }, + { + "epoch": 11.79, + "learning_rate": 7.611979694277745e-06, + "loss": 0.0098, + "step": 38173 + }, + { + "epoch": 11.79, + "learning_rate": 7.61149404832356e-06, + "loss": 0.0095, + "step": 38174 + }, + { + "epoch": 11.79, + "learning_rate": 7.6110084083434656e-06, + "loss": 0.0107, + "step": 38175 + }, + { + "epoch": 11.79, + "learning_rate": 7.610522774338677e-06, + "loss": 0.0102, + "step": 38176 + }, + { + "epoch": 11.79, + "learning_rate": 7.610037146310402e-06, + "loss": 0.0108, + "step": 38177 + }, + { + "epoch": 11.79, + "learning_rate": 7.609551524259863e-06, + "loss": 0.0106, + "step": 38178 + }, + { + "epoch": 11.79, + "learning_rate": 7.609065908188269e-06, + "loss": 0.0098, + "step": 38179 + }, + { + "epoch": 11.79, + "learning_rate": 7.608580298096842e-06, + "loss": 0.0114, + "step": 38180 + }, + { + "epoch": 11.79, + "learning_rate": 7.6080946939867885e-06, + "loss": 0.0096, + "step": 38181 + }, + { + "epoch": 11.79, + "learning_rate": 7.607609095859325e-06, + "loss": 0.0131, + "step": 38182 + }, + { + "epoch": 11.79, + "learning_rate": 7.607123503715674e-06, + "loss": 0.0123, + "step": 38183 + }, + { + "epoch": 11.79, + "learning_rate": 7.606637917557038e-06, + "loss": 0.0088, + "step": 38184 + }, + { + "epoch": 11.79, + "learning_rate": 7.606152337384638e-06, + "loss": 0.0136, + "step": 38185 + }, + { + "epoch": 11.79, + "learning_rate": 7.60566676319969e-06, + "loss": 0.011, + "step": 38186 + }, + { + "epoch": 11.79, + "learning_rate": 7.605181195003403e-06, + "loss": 0.0123, + "step": 38187 + }, + { + "epoch": 11.79, + "learning_rate": 7.604695632796994e-06, + "loss": 0.0092, + "step": 38188 + }, + { + "epoch": 11.79, + "learning_rate": 7.604210076581683e-06, + "loss": 0.0099, + "step": 38189 + }, + { + "epoch": 11.79, + "learning_rate": 7.603724526358674e-06, + "loss": 0.0123, + "step": 38190 + }, + { + "epoch": 11.79, + "learning_rate": 7.60323898212919e-06, + "loss": 0.0101, + "step": 38191 + }, + { + "epoch": 11.79, + "learning_rate": 7.602753443894444e-06, + "loss": 0.0099, + "step": 38192 + }, + { + "epoch": 11.79, + "learning_rate": 7.602267911655646e-06, + "loss": 0.0123, + "step": 38193 + }, + { + "epoch": 11.8, + "learning_rate": 7.6017823854140125e-06, + "loss": 0.0102, + "step": 38194 + }, + { + "epoch": 11.8, + "learning_rate": 7.601296865170762e-06, + "loss": 0.0094, + "step": 38195 + }, + { + "epoch": 11.8, + "learning_rate": 7.600811350927104e-06, + "loss": 0.0141, + "step": 38196 + }, + { + "epoch": 11.8, + "learning_rate": 7.600325842684252e-06, + "loss": 0.0121, + "step": 38197 + }, + { + "epoch": 11.8, + "learning_rate": 7.5998403404434275e-06, + "loss": 0.0121, + "step": 38198 + }, + { + "epoch": 11.8, + "learning_rate": 7.599354844205837e-06, + "loss": 0.0117, + "step": 38199 + }, + { + "epoch": 11.8, + "learning_rate": 7.5988693539726965e-06, + "loss": 0.0112, + "step": 38200 + }, + { + "epoch": 11.8, + "learning_rate": 7.598383869745225e-06, + "loss": 0.0101, + "step": 38201 + }, + { + "epoch": 11.8, + "learning_rate": 7.597898391524632e-06, + "loss": 0.0108, + "step": 38202 + }, + { + "epoch": 11.8, + "learning_rate": 7.597412919312134e-06, + "loss": 0.0111, + "step": 38203 + }, + { + "epoch": 11.8, + "learning_rate": 7.596927453108946e-06, + "loss": 0.0112, + "step": 38204 + }, + { + "epoch": 11.8, + "learning_rate": 7.596441992916276e-06, + "loss": 0.0115, + "step": 38205 + }, + { + "epoch": 11.8, + "learning_rate": 7.595956538735345e-06, + "loss": 0.0107, + "step": 38206 + }, + { + "epoch": 11.8, + "learning_rate": 7.5954710905673676e-06, + "loss": 0.0103, + "step": 38207 + }, + { + "epoch": 11.8, + "learning_rate": 7.594985648413552e-06, + "loss": 0.0121, + "step": 38208 + }, + { + "epoch": 11.8, + "learning_rate": 7.594500212275117e-06, + "loss": 0.0115, + "step": 38209 + }, + { + "epoch": 11.8, + "learning_rate": 7.594014782153278e-06, + "loss": 0.0108, + "step": 38210 + }, + { + "epoch": 11.8, + "learning_rate": 7.593529358049243e-06, + "loss": 0.0108, + "step": 38211 + }, + { + "epoch": 11.8, + "learning_rate": 7.593043939964233e-06, + "loss": 0.01, + "step": 38212 + }, + { + "epoch": 11.8, + "learning_rate": 7.592558527899455e-06, + "loss": 0.0108, + "step": 38213 + }, + { + "epoch": 11.8, + "learning_rate": 7.592073121856135e-06, + "loss": 0.0091, + "step": 38214 + }, + { + "epoch": 11.8, + "learning_rate": 7.591587721835473e-06, + "loss": 0.0113, + "step": 38215 + }, + { + "epoch": 11.8, + "learning_rate": 7.591102327838691e-06, + "loss": 0.0103, + "step": 38216 + }, + { + "epoch": 11.8, + "learning_rate": 7.590616939867004e-06, + "loss": 0.0105, + "step": 38217 + }, + { + "epoch": 11.8, + "learning_rate": 7.590131557921618e-06, + "loss": 0.0084, + "step": 38218 + }, + { + "epoch": 11.8, + "learning_rate": 7.589646182003756e-06, + "loss": 0.0111, + "step": 38219 + }, + { + "epoch": 11.8, + "learning_rate": 7.58916081211463e-06, + "loss": 0.0122, + "step": 38220 + }, + { + "epoch": 11.8, + "learning_rate": 7.588675448255448e-06, + "loss": 0.0111, + "step": 38221 + }, + { + "epoch": 11.8, + "learning_rate": 7.5881900904274305e-06, + "loss": 0.0101, + "step": 38222 + }, + { + "epoch": 11.8, + "learning_rate": 7.587704738631793e-06, + "loss": 0.0094, + "step": 38223 + }, + { + "epoch": 11.8, + "learning_rate": 7.587219392869743e-06, + "loss": 0.0094, + "step": 38224 + }, + { + "epoch": 11.8, + "learning_rate": 7.586734053142495e-06, + "loss": 0.0084, + "step": 38225 + }, + { + "epoch": 11.8, + "learning_rate": 7.586248719451269e-06, + "loss": 0.0114, + "step": 38226 + }, + { + "epoch": 11.81, + "learning_rate": 7.585763391797274e-06, + "loss": 0.0113, + "step": 38227 + }, + { + "epoch": 11.81, + "learning_rate": 7.585278070181723e-06, + "loss": 0.0106, + "step": 38228 + }, + { + "epoch": 11.81, + "learning_rate": 7.584792754605836e-06, + "loss": 0.0109, + "step": 38229 + }, + { + "epoch": 11.81, + "learning_rate": 7.58430744507082e-06, + "loss": 0.0106, + "step": 38230 + }, + { + "epoch": 11.81, + "learning_rate": 7.58382214157789e-06, + "loss": 0.0108, + "step": 38231 + }, + { + "epoch": 11.81, + "learning_rate": 7.583336844128268e-06, + "loss": 0.0118, + "step": 38232 + }, + { + "epoch": 11.81, + "learning_rate": 7.582851552723155e-06, + "loss": 0.0121, + "step": 38233 + }, + { + "epoch": 11.81, + "learning_rate": 7.582366267363773e-06, + "loss": 0.0108, + "step": 38234 + }, + { + "epoch": 11.81, + "learning_rate": 7.581880988051336e-06, + "loss": 0.0105, + "step": 38235 + }, + { + "epoch": 11.81, + "learning_rate": 7.581395714787052e-06, + "loss": 0.0106, + "step": 38236 + }, + { + "epoch": 11.81, + "learning_rate": 7.58091044757214e-06, + "loss": 0.0105, + "step": 38237 + }, + { + "epoch": 11.81, + "learning_rate": 7.580425186407815e-06, + "loss": 0.0116, + "step": 38238 + }, + { + "epoch": 11.81, + "learning_rate": 7.5799399312952835e-06, + "loss": 0.0112, + "step": 38239 + }, + { + "epoch": 11.81, + "learning_rate": 7.5794546822357654e-06, + "loss": 0.0092, + "step": 38240 + }, + { + "epoch": 11.81, + "learning_rate": 7.578969439230475e-06, + "loss": 0.0097, + "step": 38241 + }, + { + "epoch": 11.81, + "learning_rate": 7.578484202280622e-06, + "loss": 0.0099, + "step": 38242 + }, + { + "epoch": 11.81, + "learning_rate": 7.577998971387418e-06, + "loss": 0.0104, + "step": 38243 + }, + { + "epoch": 11.81, + "learning_rate": 7.577513746552083e-06, + "loss": 0.0091, + "step": 38244 + }, + { + "epoch": 11.81, + "learning_rate": 7.577028527775831e-06, + "loss": 0.0104, + "step": 38245 + }, + { + "epoch": 11.81, + "learning_rate": 7.576543315059867e-06, + "loss": 0.012, + "step": 38246 + }, + { + "epoch": 11.81, + "learning_rate": 7.576058108405413e-06, + "loss": 0.0101, + "step": 38247 + }, + { + "epoch": 11.81, + "learning_rate": 7.575572907813682e-06, + "loss": 0.0091, + "step": 38248 + }, + { + "epoch": 11.81, + "learning_rate": 7.5750877132858816e-06, + "loss": 0.0129, + "step": 38249 + }, + { + "epoch": 11.81, + "learning_rate": 7.57460252482323e-06, + "loss": 0.0108, + "step": 38250 + }, + { + "epoch": 11.81, + "learning_rate": 7.574117342426943e-06, + "loss": 0.0101, + "step": 38251 + }, + { + "epoch": 11.81, + "learning_rate": 7.573632166098226e-06, + "loss": 0.0103, + "step": 38252 + }, + { + "epoch": 11.81, + "learning_rate": 7.573146995838301e-06, + "loss": 0.0109, + "step": 38253 + }, + { + "epoch": 11.81, + "learning_rate": 7.572661831648378e-06, + "loss": 0.0099, + "step": 38254 + }, + { + "epoch": 11.81, + "learning_rate": 7.57217667352967e-06, + "loss": 0.0119, + "step": 38255 + }, + { + "epoch": 11.81, + "learning_rate": 7.571691521483389e-06, + "loss": 0.0104, + "step": 38256 + }, + { + "epoch": 11.81, + "learning_rate": 7.571206375510754e-06, + "loss": 0.0106, + "step": 38257 + }, + { + "epoch": 11.81, + "learning_rate": 7.570721235612973e-06, + "loss": 0.0099, + "step": 38258 + }, + { + "epoch": 11.82, + "learning_rate": 7.570236101791257e-06, + "loss": 0.0099, + "step": 38259 + }, + { + "epoch": 11.82, + "learning_rate": 7.56975097404683e-06, + "loss": 0.0103, + "step": 38260 + }, + { + "epoch": 11.82, + "learning_rate": 7.569265852380896e-06, + "loss": 0.0114, + "step": 38261 + }, + { + "epoch": 11.82, + "learning_rate": 7.568780736794671e-06, + "loss": 0.0096, + "step": 38262 + }, + { + "epoch": 11.82, + "learning_rate": 7.568295627289374e-06, + "loss": 0.0093, + "step": 38263 + }, + { + "epoch": 11.82, + "learning_rate": 7.5678105238662055e-06, + "loss": 0.0135, + "step": 38264 + }, + { + "epoch": 11.82, + "learning_rate": 7.56732542652639e-06, + "loss": 0.0102, + "step": 38265 + }, + { + "epoch": 11.82, + "learning_rate": 7.566840335271141e-06, + "loss": 0.0123, + "step": 38266 + }, + { + "epoch": 11.82, + "learning_rate": 7.566355250101661e-06, + "loss": 0.0105, + "step": 38267 + }, + { + "epoch": 11.82, + "learning_rate": 7.565870171019174e-06, + "loss": 0.0099, + "step": 38268 + }, + { + "epoch": 11.82, + "learning_rate": 7.565385098024892e-06, + "loss": 0.0099, + "step": 38269 + }, + { + "epoch": 11.82, + "learning_rate": 7.564900031120021e-06, + "loss": 0.0091, + "step": 38270 + }, + { + "epoch": 11.82, + "learning_rate": 7.564414970305782e-06, + "loss": 0.0112, + "step": 38271 + }, + { + "epoch": 11.82, + "learning_rate": 7.563929915583387e-06, + "loss": 0.0115, + "step": 38272 + }, + { + "epoch": 11.82, + "learning_rate": 7.563444866954045e-06, + "loss": 0.0131, + "step": 38273 + }, + { + "epoch": 11.82, + "learning_rate": 7.562959824418971e-06, + "loss": 0.0109, + "step": 38274 + }, + { + "epoch": 11.82, + "learning_rate": 7.562474787979381e-06, + "loss": 0.0113, + "step": 38275 + }, + { + "epoch": 11.82, + "learning_rate": 7.561989757636487e-06, + "loss": 0.0123, + "step": 38276 + }, + { + "epoch": 11.82, + "learning_rate": 7.561504733391497e-06, + "loss": 0.0099, + "step": 38277 + }, + { + "epoch": 11.82, + "learning_rate": 7.561019715245631e-06, + "loss": 0.0104, + "step": 38278 + }, + { + "epoch": 11.82, + "learning_rate": 7.560534703200102e-06, + "loss": 0.0095, + "step": 38279 + }, + { + "epoch": 11.82, + "learning_rate": 7.5600496972561154e-06, + "loss": 0.0123, + "step": 38280 + }, + { + "epoch": 11.82, + "learning_rate": 7.5595646974148926e-06, + "loss": 0.0116, + "step": 38281 + }, + { + "epoch": 11.82, + "learning_rate": 7.559079703677645e-06, + "loss": 0.0099, + "step": 38282 + }, + { + "epoch": 11.82, + "learning_rate": 7.558594716045583e-06, + "loss": 0.01, + "step": 38283 + }, + { + "epoch": 11.82, + "learning_rate": 7.558109734519919e-06, + "loss": 0.0105, + "step": 38284 + }, + { + "epoch": 11.82, + "learning_rate": 7.557624759101872e-06, + "loss": 0.011, + "step": 38285 + }, + { + "epoch": 11.82, + "learning_rate": 7.557139789792647e-06, + "loss": 0.0115, + "step": 38286 + }, + { + "epoch": 11.82, + "learning_rate": 7.55665482659346e-06, + "loss": 0.0091, + "step": 38287 + }, + { + "epoch": 11.82, + "learning_rate": 7.55616986950553e-06, + "loss": 0.0097, + "step": 38288 + }, + { + "epoch": 11.82, + "learning_rate": 7.555684918530061e-06, + "loss": 0.0106, + "step": 38289 + }, + { + "epoch": 11.82, + "learning_rate": 7.55519997366827e-06, + "loss": 0.0104, + "step": 38290 + }, + { + "epoch": 11.82, + "learning_rate": 7.554715034921373e-06, + "loss": 0.01, + "step": 38291 + }, + { + "epoch": 11.83, + "learning_rate": 7.554230102290577e-06, + "loss": 0.0109, + "step": 38292 + }, + { + "epoch": 11.83, + "learning_rate": 7.553745175777099e-06, + "loss": 0.0104, + "step": 38293 + }, + { + "epoch": 11.83, + "learning_rate": 7.553260255382151e-06, + "loss": 0.0108, + "step": 38294 + }, + { + "epoch": 11.83, + "learning_rate": 7.5527753411069414e-06, + "loss": 0.0116, + "step": 38295 + }, + { + "epoch": 11.83, + "learning_rate": 7.552290432952689e-06, + "loss": 0.0086, + "step": 38296 + }, + { + "epoch": 11.83, + "learning_rate": 7.5518055309206086e-06, + "loss": 0.0101, + "step": 38297 + }, + { + "epoch": 11.83, + "learning_rate": 7.551320635011903e-06, + "loss": 0.0094, + "step": 38298 + }, + { + "epoch": 11.83, + "learning_rate": 7.5508357452277936e-06, + "loss": 0.0113, + "step": 38299 + }, + { + "epoch": 11.83, + "learning_rate": 7.550350861569493e-06, + "loss": 0.0115, + "step": 38300 + }, + { + "epoch": 11.83, + "learning_rate": 7.549865984038207e-06, + "loss": 0.0122, + "step": 38301 + }, + { + "epoch": 11.83, + "learning_rate": 7.5493811126351555e-06, + "loss": 0.0097, + "step": 38302 + }, + { + "epoch": 11.83, + "learning_rate": 7.548896247361551e-06, + "loss": 0.0112, + "step": 38303 + }, + { + "epoch": 11.83, + "learning_rate": 7.548411388218601e-06, + "loss": 0.0109, + "step": 38304 + }, + { + "epoch": 11.83, + "learning_rate": 7.547926535207522e-06, + "loss": 0.0098, + "step": 38305 + }, + { + "epoch": 11.83, + "learning_rate": 7.5474416883295275e-06, + "loss": 0.0097, + "step": 38306 + }, + { + "epoch": 11.83, + "learning_rate": 7.546956847585827e-06, + "loss": 0.0087, + "step": 38307 + }, + { + "epoch": 11.83, + "learning_rate": 7.546472012977634e-06, + "loss": 0.0109, + "step": 38308 + }, + { + "epoch": 11.83, + "learning_rate": 7.545987184506163e-06, + "loss": 0.0127, + "step": 38309 + }, + { + "epoch": 11.83, + "learning_rate": 7.545502362172628e-06, + "loss": 0.0093, + "step": 38310 + }, + { + "epoch": 11.83, + "learning_rate": 7.545017545978235e-06, + "loss": 0.0121, + "step": 38311 + }, + { + "epoch": 11.83, + "learning_rate": 7.544532735924201e-06, + "loss": 0.0109, + "step": 38312 + }, + { + "epoch": 11.83, + "learning_rate": 7.544047932011743e-06, + "loss": 0.0113, + "step": 38313 + }, + { + "epoch": 11.83, + "learning_rate": 7.543563134242067e-06, + "loss": 0.0127, + "step": 38314 + }, + { + "epoch": 11.83, + "learning_rate": 7.543078342616385e-06, + "loss": 0.0101, + "step": 38315 + }, + { + "epoch": 11.83, + "learning_rate": 7.542593557135916e-06, + "loss": 0.009, + "step": 38316 + }, + { + "epoch": 11.83, + "learning_rate": 7.542108777801868e-06, + "loss": 0.0102, + "step": 38317 + }, + { + "epoch": 11.83, + "learning_rate": 7.541624004615451e-06, + "loss": 0.0116, + "step": 38318 + }, + { + "epoch": 11.83, + "learning_rate": 7.5411392375778844e-06, + "loss": 0.0101, + "step": 38319 + }, + { + "epoch": 11.83, + "learning_rate": 7.540654476690375e-06, + "loss": 0.0108, + "step": 38320 + }, + { + "epoch": 11.83, + "learning_rate": 7.540169721954136e-06, + "loss": 0.0094, + "step": 38321 + }, + { + "epoch": 11.83, + "learning_rate": 7.5396849733703885e-06, + "loss": 0.0115, + "step": 38322 + }, + { + "epoch": 11.83, + "learning_rate": 7.539200230940329e-06, + "loss": 0.0107, + "step": 38323 + }, + { + "epoch": 11.84, + "learning_rate": 7.538715494665182e-06, + "loss": 0.01, + "step": 38324 + }, + { + "epoch": 11.84, + "learning_rate": 7.538230764546159e-06, + "loss": 0.0092, + "step": 38325 + }, + { + "epoch": 11.84, + "learning_rate": 7.537746040584464e-06, + "loss": 0.011, + "step": 38326 + }, + { + "epoch": 11.84, + "learning_rate": 7.537261322781318e-06, + "loss": 0.0106, + "step": 38327 + }, + { + "epoch": 11.84, + "learning_rate": 7.536776611137934e-06, + "loss": 0.0116, + "step": 38328 + }, + { + "epoch": 11.84, + "learning_rate": 7.536291905655515e-06, + "loss": 0.0114, + "step": 38329 + }, + { + "epoch": 11.84, + "learning_rate": 7.535807206335282e-06, + "loss": 0.0097, + "step": 38330 + }, + { + "epoch": 11.84, + "learning_rate": 7.5353225131784465e-06, + "loss": 0.01, + "step": 38331 + }, + { + "epoch": 11.84, + "learning_rate": 7.534837826186218e-06, + "loss": 0.0098, + "step": 38332 + }, + { + "epoch": 11.84, + "learning_rate": 7.534353145359806e-06, + "loss": 0.0134, + "step": 38333 + }, + { + "epoch": 11.84, + "learning_rate": 7.533868470700432e-06, + "loss": 0.0112, + "step": 38334 + }, + { + "epoch": 11.84, + "learning_rate": 7.533383802209299e-06, + "loss": 0.0091, + "step": 38335 + }, + { + "epoch": 11.84, + "learning_rate": 7.532899139887623e-06, + "loss": 0.0104, + "step": 38336 + }, + { + "epoch": 11.84, + "learning_rate": 7.53241448373662e-06, + "loss": 0.01, + "step": 38337 + }, + { + "epoch": 11.84, + "learning_rate": 7.531929833757496e-06, + "loss": 0.0111, + "step": 38338 + }, + { + "epoch": 11.84, + "learning_rate": 7.531445189951463e-06, + "loss": 0.0098, + "step": 38339 + }, + { + "epoch": 11.84, + "learning_rate": 7.530960552319739e-06, + "loss": 0.0113, + "step": 38340 + }, + { + "epoch": 11.84, + "learning_rate": 7.530475920863534e-06, + "loss": 0.0121, + "step": 38341 + }, + { + "epoch": 11.84, + "learning_rate": 7.529991295584056e-06, + "loss": 0.0095, + "step": 38342 + }, + { + "epoch": 11.84, + "learning_rate": 7.52950667648252e-06, + "loss": 0.0108, + "step": 38343 + }, + { + "epoch": 11.84, + "learning_rate": 7.5290220635601415e-06, + "loss": 0.0101, + "step": 38344 + }, + { + "epoch": 11.84, + "learning_rate": 7.528537456818128e-06, + "loss": 0.0097, + "step": 38345 + }, + { + "epoch": 11.84, + "learning_rate": 7.528052856257691e-06, + "loss": 0.01, + "step": 38346 + }, + { + "epoch": 11.84, + "learning_rate": 7.527568261880049e-06, + "loss": 0.0106, + "step": 38347 + }, + { + "epoch": 11.84, + "learning_rate": 7.527083673686408e-06, + "loss": 0.0097, + "step": 38348 + }, + { + "epoch": 11.84, + "learning_rate": 7.52659909167798e-06, + "loss": 0.0116, + "step": 38349 + }, + { + "epoch": 11.84, + "learning_rate": 7.526114515855981e-06, + "loss": 0.0108, + "step": 38350 + }, + { + "epoch": 11.84, + "learning_rate": 7.52562994622162e-06, + "loss": 0.0104, + "step": 38351 + }, + { + "epoch": 11.84, + "learning_rate": 7.525145382776109e-06, + "loss": 0.0086, + "step": 38352 + }, + { + "epoch": 11.84, + "learning_rate": 7.524660825520664e-06, + "loss": 0.0126, + "step": 38353 + }, + { + "epoch": 11.84, + "learning_rate": 7.52417627445649e-06, + "loss": 0.01, + "step": 38354 + }, + { + "epoch": 11.84, + "learning_rate": 7.523691729584803e-06, + "loss": 0.01, + "step": 38355 + }, + { + "epoch": 11.85, + "learning_rate": 7.5232071909068185e-06, + "loss": 0.01, + "step": 38356 + }, + { + "epoch": 11.85, + "learning_rate": 7.522722658423739e-06, + "loss": 0.0099, + "step": 38357 + }, + { + "epoch": 11.85, + "learning_rate": 7.522238132136784e-06, + "loss": 0.0116, + "step": 38358 + }, + { + "epoch": 11.85, + "learning_rate": 7.521753612047166e-06, + "loss": 0.0108, + "step": 38359 + }, + { + "epoch": 11.85, + "learning_rate": 7.52126909815609e-06, + "loss": 0.0114, + "step": 38360 + }, + { + "epoch": 11.85, + "learning_rate": 7.520784590464773e-06, + "loss": 0.0106, + "step": 38361 + }, + { + "epoch": 11.85, + "learning_rate": 7.52030008897443e-06, + "loss": 0.0111, + "step": 38362 + }, + { + "epoch": 11.85, + "learning_rate": 7.519815593686266e-06, + "loss": 0.0107, + "step": 38363 + }, + { + "epoch": 11.85, + "learning_rate": 7.519331104601494e-06, + "loss": 0.0123, + "step": 38364 + }, + { + "epoch": 11.85, + "learning_rate": 7.518846621721331e-06, + "loss": 0.0106, + "step": 38365 + }, + { + "epoch": 11.85, + "learning_rate": 7.5183621450469825e-06, + "loss": 0.0125, + "step": 38366 + }, + { + "epoch": 11.85, + "learning_rate": 7.517877674579661e-06, + "loss": 0.0118, + "step": 38367 + }, + { + "epoch": 11.85, + "learning_rate": 7.517393210320585e-06, + "loss": 0.0102, + "step": 38368 + }, + { + "epoch": 11.85, + "learning_rate": 7.516908752270959e-06, + "loss": 0.011, + "step": 38369 + }, + { + "epoch": 11.85, + "learning_rate": 7.516424300431994e-06, + "loss": 0.0087, + "step": 38370 + }, + { + "epoch": 11.85, + "learning_rate": 7.515939854804912e-06, + "loss": 0.0098, + "step": 38371 + }, + { + "epoch": 11.85, + "learning_rate": 7.515455415390911e-06, + "loss": 0.0104, + "step": 38372 + }, + { + "epoch": 11.85, + "learning_rate": 7.514970982191211e-06, + "loss": 0.0104, + "step": 38373 + }, + { + "epoch": 11.85, + "learning_rate": 7.51448655520702e-06, + "loss": 0.0109, + "step": 38374 + }, + { + "epoch": 11.85, + "learning_rate": 7.514002134439557e-06, + "loss": 0.0115, + "step": 38375 + }, + { + "epoch": 11.85, + "learning_rate": 7.513517719890023e-06, + "loss": 0.0105, + "step": 38376 + }, + { + "epoch": 11.85, + "learning_rate": 7.513033311559634e-06, + "loss": 0.0106, + "step": 38377 + }, + { + "epoch": 11.85, + "learning_rate": 7.5125489094496076e-06, + "loss": 0.0111, + "step": 38378 + }, + { + "epoch": 11.85, + "learning_rate": 7.512064513561147e-06, + "loss": 0.0101, + "step": 38379 + }, + { + "epoch": 11.85, + "learning_rate": 7.511580123895466e-06, + "loss": 0.0125, + "step": 38380 + }, + { + "epoch": 11.85, + "learning_rate": 7.511095740453781e-06, + "loss": 0.0117, + "step": 38381 + }, + { + "epoch": 11.85, + "learning_rate": 7.510611363237295e-06, + "loss": 0.0107, + "step": 38382 + }, + { + "epoch": 11.85, + "learning_rate": 7.510126992247225e-06, + "loss": 0.0103, + "step": 38383 + }, + { + "epoch": 11.85, + "learning_rate": 7.509642627484783e-06, + "loss": 0.0095, + "step": 38384 + }, + { + "epoch": 11.85, + "learning_rate": 7.509158268951176e-06, + "loss": 0.0096, + "step": 38385 + }, + { + "epoch": 11.85, + "learning_rate": 7.508673916647621e-06, + "loss": 0.0097, + "step": 38386 + }, + { + "epoch": 11.85, + "learning_rate": 7.508189570575328e-06, + "loss": 0.0115, + "step": 38387 + }, + { + "epoch": 11.85, + "learning_rate": 7.507705230735505e-06, + "loss": 0.0107, + "step": 38388 + }, + { + "epoch": 11.86, + "learning_rate": 7.507220897129366e-06, + "loss": 0.01, + "step": 38389 + }, + { + "epoch": 11.86, + "learning_rate": 7.506736569758124e-06, + "loss": 0.0089, + "step": 38390 + }, + { + "epoch": 11.86, + "learning_rate": 7.506252248622987e-06, + "loss": 0.0109, + "step": 38391 + }, + { + "epoch": 11.86, + "learning_rate": 7.505767933725167e-06, + "loss": 0.0099, + "step": 38392 + }, + { + "epoch": 11.86, + "learning_rate": 7.50528362506588e-06, + "loss": 0.0128, + "step": 38393 + }, + { + "epoch": 11.86, + "learning_rate": 7.50479932264633e-06, + "loss": 0.0126, + "step": 38394 + }, + { + "epoch": 11.86, + "learning_rate": 7.504315026467732e-06, + "loss": 0.0109, + "step": 38395 + }, + { + "epoch": 11.86, + "learning_rate": 7.5038307365313e-06, + "loss": 0.0117, + "step": 38396 + }, + { + "epoch": 11.86, + "learning_rate": 7.503346452838242e-06, + "loss": 0.0124, + "step": 38397 + }, + { + "epoch": 11.86, + "learning_rate": 7.502862175389767e-06, + "loss": 0.0112, + "step": 38398 + }, + { + "epoch": 11.86, + "learning_rate": 7.5023779041870925e-06, + "loss": 0.0105, + "step": 38399 + }, + { + "epoch": 11.86, + "learning_rate": 7.501893639231426e-06, + "loss": 0.0106, + "step": 38400 + }, + { + "epoch": 11.86, + "learning_rate": 7.5014093805239776e-06, + "loss": 0.0103, + "step": 38401 + }, + { + "epoch": 11.86, + "learning_rate": 7.500925128065962e-06, + "loss": 0.0112, + "step": 38402 + }, + { + "epoch": 11.86, + "learning_rate": 7.500440881858585e-06, + "loss": 0.0103, + "step": 38403 + }, + { + "epoch": 11.86, + "learning_rate": 7.499956641903063e-06, + "loss": 0.01, + "step": 38404 + }, + { + "epoch": 11.86, + "learning_rate": 7.4994724082006085e-06, + "loss": 0.0095, + "step": 38405 + }, + { + "epoch": 11.86, + "learning_rate": 7.498988180752425e-06, + "loss": 0.011, + "step": 38406 + }, + { + "epoch": 11.86, + "learning_rate": 7.4985039595597295e-06, + "loss": 0.0092, + "step": 38407 + }, + { + "epoch": 11.86, + "learning_rate": 7.49801974462373e-06, + "loss": 0.0112, + "step": 38408 + }, + { + "epoch": 11.86, + "learning_rate": 7.497535535945643e-06, + "loss": 0.0105, + "step": 38409 + }, + { + "epoch": 11.86, + "learning_rate": 7.497051333526677e-06, + "loss": 0.0101, + "step": 38410 + }, + { + "epoch": 11.86, + "learning_rate": 7.496567137368039e-06, + "loss": 0.0115, + "step": 38411 + }, + { + "epoch": 11.86, + "learning_rate": 7.496082947470946e-06, + "loss": 0.0117, + "step": 38412 + }, + { + "epoch": 11.86, + "learning_rate": 7.495598763836602e-06, + "loss": 0.0133, + "step": 38413 + }, + { + "epoch": 11.86, + "learning_rate": 7.495114586466225e-06, + "loss": 0.0107, + "step": 38414 + }, + { + "epoch": 11.86, + "learning_rate": 7.494630415361026e-06, + "loss": 0.0106, + "step": 38415 + }, + { + "epoch": 11.86, + "learning_rate": 7.4941462505222075e-06, + "loss": 0.0124, + "step": 38416 + }, + { + "epoch": 11.86, + "learning_rate": 7.493662091950988e-06, + "loss": 0.0118, + "step": 38417 + }, + { + "epoch": 11.86, + "learning_rate": 7.493177939648582e-06, + "loss": 0.0109, + "step": 38418 + }, + { + "epoch": 11.86, + "learning_rate": 7.492693793616188e-06, + "loss": 0.0115, + "step": 38419 + }, + { + "epoch": 11.86, + "learning_rate": 7.4922096538550275e-06, + "loss": 0.0116, + "step": 38420 + }, + { + "epoch": 11.87, + "learning_rate": 7.491725520366309e-06, + "loss": 0.0126, + "step": 38421 + }, + { + "epoch": 11.87, + "learning_rate": 7.49124139315124e-06, + "loss": 0.0114, + "step": 38422 + }, + { + "epoch": 11.87, + "learning_rate": 7.4907572722110335e-06, + "loss": 0.0109, + "step": 38423 + }, + { + "epoch": 11.87, + "learning_rate": 7.490273157546905e-06, + "loss": 0.0108, + "step": 38424 + }, + { + "epoch": 11.87, + "learning_rate": 7.489789049160058e-06, + "loss": 0.0094, + "step": 38425 + }, + { + "epoch": 11.87, + "learning_rate": 7.4893049470517044e-06, + "loss": 0.0102, + "step": 38426 + }, + { + "epoch": 11.87, + "learning_rate": 7.488820851223062e-06, + "loss": 0.0116, + "step": 38427 + }, + { + "epoch": 11.87, + "learning_rate": 7.488336761675333e-06, + "loss": 0.0111, + "step": 38428 + }, + { + "epoch": 11.87, + "learning_rate": 7.487852678409731e-06, + "loss": 0.0116, + "step": 38429 + }, + { + "epoch": 11.87, + "learning_rate": 7.487368601427473e-06, + "loss": 0.0119, + "step": 38430 + }, + { + "epoch": 11.87, + "learning_rate": 7.4868845307297585e-06, + "loss": 0.0118, + "step": 38431 + }, + { + "epoch": 11.87, + "learning_rate": 7.4864004663178066e-06, + "loss": 0.0125, + "step": 38432 + }, + { + "epoch": 11.87, + "learning_rate": 7.485916408192828e-06, + "loss": 0.0128, + "step": 38433 + }, + { + "epoch": 11.87, + "learning_rate": 7.485432356356026e-06, + "loss": 0.0094, + "step": 38434 + }, + { + "epoch": 11.87, + "learning_rate": 7.484948310808619e-06, + "loss": 0.0109, + "step": 38435 + }, + { + "epoch": 11.87, + "learning_rate": 7.484464271551817e-06, + "loss": 0.0098, + "step": 38436 + }, + { + "epoch": 11.87, + "learning_rate": 7.483980238586824e-06, + "loss": 0.0097, + "step": 38437 + }, + { + "epoch": 11.87, + "learning_rate": 7.483496211914858e-06, + "loss": 0.011, + "step": 38438 + }, + { + "epoch": 11.87, + "learning_rate": 7.483012191537129e-06, + "loss": 0.0117, + "step": 38439 + }, + { + "epoch": 11.87, + "learning_rate": 7.482528177454844e-06, + "loss": 0.0097, + "step": 38440 + }, + { + "epoch": 11.87, + "learning_rate": 7.482044169669211e-06, + "loss": 0.0095, + "step": 38441 + }, + { + "epoch": 11.87, + "learning_rate": 7.48156016818145e-06, + "loss": 0.0134, + "step": 38442 + }, + { + "epoch": 11.87, + "learning_rate": 7.481076172992765e-06, + "loss": 0.0111, + "step": 38443 + }, + { + "epoch": 11.87, + "learning_rate": 7.480592184104366e-06, + "loss": 0.013, + "step": 38444 + }, + { + "epoch": 11.87, + "learning_rate": 7.480108201517466e-06, + "loss": 0.0105, + "step": 38445 + }, + { + "epoch": 11.87, + "learning_rate": 7.479624225233279e-06, + "loss": 0.0116, + "step": 38446 + }, + { + "epoch": 11.87, + "learning_rate": 7.4791402552530055e-06, + "loss": 0.0104, + "step": 38447 + }, + { + "epoch": 11.87, + "learning_rate": 7.478656291577866e-06, + "loss": 0.0104, + "step": 38448 + }, + { + "epoch": 11.87, + "learning_rate": 7.4781723342090685e-06, + "loss": 0.0115, + "step": 38449 + }, + { + "epoch": 11.87, + "learning_rate": 7.4776883831478186e-06, + "loss": 0.0119, + "step": 38450 + }, + { + "epoch": 11.87, + "learning_rate": 7.477204438395329e-06, + "loss": 0.0101, + "step": 38451 + }, + { + "epoch": 11.87, + "learning_rate": 7.476720499952815e-06, + "loss": 0.0112, + "step": 38452 + }, + { + "epoch": 11.88, + "learning_rate": 7.476236567821482e-06, + "loss": 0.0099, + "step": 38453 + }, + { + "epoch": 11.88, + "learning_rate": 7.475752642002538e-06, + "loss": 0.0127, + "step": 38454 + }, + { + "epoch": 11.88, + "learning_rate": 7.475268722497202e-06, + "loss": 0.0095, + "step": 38455 + }, + { + "epoch": 11.88, + "learning_rate": 7.474784809306679e-06, + "loss": 0.0111, + "step": 38456 + }, + { + "epoch": 11.88, + "learning_rate": 7.474300902432175e-06, + "loss": 0.0109, + "step": 38457 + }, + { + "epoch": 11.88, + "learning_rate": 7.47381700187491e-06, + "loss": 0.0119, + "step": 38458 + }, + { + "epoch": 11.88, + "learning_rate": 7.473333107636088e-06, + "loss": 0.0111, + "step": 38459 + }, + { + "epoch": 11.88, + "learning_rate": 7.472849219716921e-06, + "loss": 0.0098, + "step": 38460 + }, + { + "epoch": 11.88, + "learning_rate": 7.472365338118621e-06, + "loss": 0.0119, + "step": 38461 + }, + { + "epoch": 11.88, + "learning_rate": 7.4718814628423915e-06, + "loss": 0.0123, + "step": 38462 + }, + { + "epoch": 11.88, + "learning_rate": 7.471397593889449e-06, + "loss": 0.0121, + "step": 38463 + }, + { + "epoch": 11.88, + "learning_rate": 7.4709137312610054e-06, + "loss": 0.0089, + "step": 38464 + }, + { + "epoch": 11.88, + "learning_rate": 7.470429874958264e-06, + "loss": 0.0112, + "step": 38465 + }, + { + "epoch": 11.88, + "learning_rate": 7.46994602498244e-06, + "loss": 0.0092, + "step": 38466 + }, + { + "epoch": 11.88, + "learning_rate": 7.469462181334746e-06, + "loss": 0.0128, + "step": 38467 + }, + { + "epoch": 11.88, + "learning_rate": 7.468978344016382e-06, + "loss": 0.0127, + "step": 38468 + }, + { + "epoch": 11.88, + "learning_rate": 7.468494513028569e-06, + "loss": 0.0104, + "step": 38469 + }, + { + "epoch": 11.88, + "learning_rate": 7.468010688372514e-06, + "loss": 0.012, + "step": 38470 + }, + { + "epoch": 11.88, + "learning_rate": 7.467526870049424e-06, + "loss": 0.0115, + "step": 38471 + }, + { + "epoch": 11.88, + "learning_rate": 7.46704305806051e-06, + "loss": 0.0117, + "step": 38472 + }, + { + "epoch": 11.88, + "learning_rate": 7.466559252406984e-06, + "loss": 0.0122, + "step": 38473 + }, + { + "epoch": 11.88, + "learning_rate": 7.466075453090059e-06, + "loss": 0.011, + "step": 38474 + }, + { + "epoch": 11.88, + "learning_rate": 7.465591660110937e-06, + "loss": 0.0116, + "step": 38475 + }, + { + "epoch": 11.88, + "learning_rate": 7.465107873470833e-06, + "loss": 0.0109, + "step": 38476 + }, + { + "epoch": 11.88, + "learning_rate": 7.46462409317096e-06, + "loss": 0.0103, + "step": 38477 + }, + { + "epoch": 11.88, + "learning_rate": 7.46414031921252e-06, + "loss": 0.0101, + "step": 38478 + }, + { + "epoch": 11.88, + "learning_rate": 7.463656551596731e-06, + "loss": 0.0113, + "step": 38479 + }, + { + "epoch": 11.88, + "learning_rate": 7.4631727903248e-06, + "loss": 0.0099, + "step": 38480 + }, + { + "epoch": 11.88, + "learning_rate": 7.462689035397935e-06, + "loss": 0.0111, + "step": 38481 + }, + { + "epoch": 11.88, + "learning_rate": 7.4622052868173455e-06, + "loss": 0.0107, + "step": 38482 + }, + { + "epoch": 11.88, + "learning_rate": 7.461721544584247e-06, + "loss": 0.0118, + "step": 38483 + }, + { + "epoch": 11.88, + "learning_rate": 7.461237808699844e-06, + "loss": 0.012, + "step": 38484 + }, + { + "epoch": 11.88, + "learning_rate": 7.4607540791653465e-06, + "loss": 0.0111, + "step": 38485 + }, + { + "epoch": 11.89, + "learning_rate": 7.460270355981971e-06, + "loss": 0.0127, + "step": 38486 + }, + { + "epoch": 11.89, + "learning_rate": 7.459786639150919e-06, + "loss": 0.0115, + "step": 38487 + }, + { + "epoch": 11.89, + "learning_rate": 7.459302928673403e-06, + "loss": 0.0096, + "step": 38488 + }, + { + "epoch": 11.89, + "learning_rate": 7.45881922455064e-06, + "loss": 0.0105, + "step": 38489 + }, + { + "epoch": 11.89, + "learning_rate": 7.458335526783826e-06, + "loss": 0.0117, + "step": 38490 + }, + { + "epoch": 11.89, + "learning_rate": 7.457851835374183e-06, + "loss": 0.0126, + "step": 38491 + }, + { + "epoch": 11.89, + "learning_rate": 7.457368150322917e-06, + "loss": 0.0088, + "step": 38492 + }, + { + "epoch": 11.89, + "learning_rate": 7.456884471631232e-06, + "loss": 0.0157, + "step": 38493 + }, + { + "epoch": 11.89, + "learning_rate": 7.4564007993003455e-06, + "loss": 0.0126, + "step": 38494 + }, + { + "epoch": 11.89, + "learning_rate": 7.455917133331466e-06, + "loss": 0.0119, + "step": 38495 + }, + { + "epoch": 11.89, + "learning_rate": 7.455433473725798e-06, + "loss": 0.0121, + "step": 38496 + }, + { + "epoch": 11.89, + "learning_rate": 7.454949820484558e-06, + "loss": 0.013, + "step": 38497 + }, + { + "epoch": 11.89, + "learning_rate": 7.454466173608954e-06, + "loss": 0.0128, + "step": 38498 + }, + { + "epoch": 11.89, + "learning_rate": 7.453982533100192e-06, + "loss": 0.0118, + "step": 38499 + }, + { + "epoch": 11.89, + "learning_rate": 7.4534988989594816e-06, + "loss": 0.0105, + "step": 38500 + }, + { + "epoch": 11.89, + "learning_rate": 7.45301527118804e-06, + "loss": 0.0112, + "step": 38501 + }, + { + "epoch": 11.89, + "learning_rate": 7.452531649787069e-06, + "loss": 0.0121, + "step": 38502 + }, + { + "epoch": 11.89, + "learning_rate": 7.45204803475778e-06, + "loss": 0.0143, + "step": 38503 + }, + { + "epoch": 11.89, + "learning_rate": 7.451564426101388e-06, + "loss": 0.0129, + "step": 38504 + }, + { + "epoch": 11.89, + "learning_rate": 7.4510808238190945e-06, + "loss": 0.0102, + "step": 38505 + }, + { + "epoch": 11.89, + "learning_rate": 7.450597227912111e-06, + "loss": 0.0106, + "step": 38506 + }, + { + "epoch": 11.89, + "learning_rate": 7.450113638381651e-06, + "loss": 0.0106, + "step": 38507 + }, + { + "epoch": 11.89, + "learning_rate": 7.449630055228924e-06, + "loss": 0.013, + "step": 38508 + }, + { + "epoch": 11.89, + "learning_rate": 7.4491464784551335e-06, + "loss": 0.0105, + "step": 38509 + }, + { + "epoch": 11.89, + "learning_rate": 7.448662908061495e-06, + "loss": 0.01, + "step": 38510 + }, + { + "epoch": 11.89, + "learning_rate": 7.448179344049217e-06, + "loss": 0.0091, + "step": 38511 + }, + { + "epoch": 11.89, + "learning_rate": 7.447695786419508e-06, + "loss": 0.0116, + "step": 38512 + }, + { + "epoch": 11.89, + "learning_rate": 7.447212235173573e-06, + "loss": 0.0129, + "step": 38513 + }, + { + "epoch": 11.89, + "learning_rate": 7.446728690312631e-06, + "loss": 0.0122, + "step": 38514 + }, + { + "epoch": 11.89, + "learning_rate": 7.446245151837884e-06, + "loss": 0.0129, + "step": 38515 + }, + { + "epoch": 11.89, + "learning_rate": 7.445761619750542e-06, + "loss": 0.0109, + "step": 38516 + }, + { + "epoch": 11.89, + "learning_rate": 7.44527809405182e-06, + "loss": 0.0109, + "step": 38517 + }, + { + "epoch": 11.9, + "learning_rate": 7.444794574742922e-06, + "loss": 0.0102, + "step": 38518 + }, + { + "epoch": 11.9, + "learning_rate": 7.444311061825054e-06, + "loss": 0.0097, + "step": 38519 + }, + { + "epoch": 11.9, + "learning_rate": 7.443827555299439e-06, + "loss": 0.011, + "step": 38520 + }, + { + "epoch": 11.9, + "learning_rate": 7.443344055167271e-06, + "loss": 0.0122, + "step": 38521 + }, + { + "epoch": 11.9, + "learning_rate": 7.4428605614297675e-06, + "loss": 0.0104, + "step": 38522 + }, + { + "epoch": 11.9, + "learning_rate": 7.442377074088139e-06, + "loss": 0.0104, + "step": 38523 + }, + { + "epoch": 11.9, + "learning_rate": 7.4418935931435854e-06, + "loss": 0.0094, + "step": 38524 + }, + { + "epoch": 11.9, + "learning_rate": 7.441410118597326e-06, + "loss": 0.0106, + "step": 38525 + }, + { + "epoch": 11.9, + "learning_rate": 7.440926650450569e-06, + "loss": 0.0115, + "step": 38526 + }, + { + "epoch": 11.9, + "learning_rate": 7.440443188704517e-06, + "loss": 0.01, + "step": 38527 + }, + { + "epoch": 11.9, + "learning_rate": 7.439959733360385e-06, + "loss": 0.0103, + "step": 38528 + }, + { + "epoch": 11.9, + "learning_rate": 7.439476284419383e-06, + "loss": 0.0102, + "step": 38529 + }, + { + "epoch": 11.9, + "learning_rate": 7.438992841882716e-06, + "loss": 0.0112, + "step": 38530 + }, + { + "epoch": 11.9, + "learning_rate": 7.438509405751593e-06, + "loss": 0.0106, + "step": 38531 + }, + { + "epoch": 11.9, + "learning_rate": 7.438025976027229e-06, + "loss": 0.0113, + "step": 38532 + }, + { + "epoch": 11.9, + "learning_rate": 7.437542552710827e-06, + "loss": 0.0104, + "step": 38533 + }, + { + "epoch": 11.9, + "learning_rate": 7.437059135803597e-06, + "loss": 0.0112, + "step": 38534 + }, + { + "epoch": 11.9, + "learning_rate": 7.436575725306753e-06, + "loss": 0.0117, + "step": 38535 + }, + { + "epoch": 11.9, + "learning_rate": 7.4360923212214985e-06, + "loss": 0.0111, + "step": 38536 + }, + { + "epoch": 11.9, + "learning_rate": 7.435608923549042e-06, + "loss": 0.0111, + "step": 38537 + }, + { + "epoch": 11.9, + "learning_rate": 7.435125532290599e-06, + "loss": 0.0107, + "step": 38538 + }, + { + "epoch": 11.9, + "learning_rate": 7.434642147447377e-06, + "loss": 0.0102, + "step": 38539 + }, + { + "epoch": 11.9, + "learning_rate": 7.434158769020579e-06, + "loss": 0.0103, + "step": 38540 + }, + { + "epoch": 11.9, + "learning_rate": 7.433675397011417e-06, + "loss": 0.0129, + "step": 38541 + }, + { + "epoch": 11.9, + "learning_rate": 7.433192031421106e-06, + "loss": 0.0113, + "step": 38542 + }, + { + "epoch": 11.9, + "learning_rate": 7.4327086722508455e-06, + "loss": 0.0102, + "step": 38543 + }, + { + "epoch": 11.9, + "learning_rate": 7.432225319501849e-06, + "loss": 0.0107, + "step": 38544 + }, + { + "epoch": 11.9, + "learning_rate": 7.431741973175328e-06, + "loss": 0.0112, + "step": 38545 + }, + { + "epoch": 11.9, + "learning_rate": 7.431258633272488e-06, + "loss": 0.0107, + "step": 38546 + }, + { + "epoch": 11.9, + "learning_rate": 7.430775299794535e-06, + "loss": 0.0111, + "step": 38547 + }, + { + "epoch": 11.9, + "learning_rate": 7.4302919727426894e-06, + "loss": 0.0116, + "step": 38548 + }, + { + "epoch": 11.9, + "learning_rate": 7.429808652118144e-06, + "loss": 0.0103, + "step": 38549 + }, + { + "epoch": 11.9, + "learning_rate": 7.42932533792212e-06, + "loss": 0.0119, + "step": 38550 + }, + { + "epoch": 11.91, + "learning_rate": 7.428842030155823e-06, + "loss": 0.0119, + "step": 38551 + }, + { + "epoch": 11.91, + "learning_rate": 7.428358728820457e-06, + "loss": 0.0141, + "step": 38552 + }, + { + "epoch": 11.91, + "learning_rate": 7.427875433917237e-06, + "loss": 0.0108, + "step": 38553 + }, + { + "epoch": 11.91, + "learning_rate": 7.427392145447374e-06, + "loss": 0.0108, + "step": 38554 + }, + { + "epoch": 11.91, + "learning_rate": 7.426908863412066e-06, + "loss": 0.0124, + "step": 38555 + }, + { + "epoch": 11.91, + "learning_rate": 7.42642558781253e-06, + "loss": 0.0127, + "step": 38556 + }, + { + "epoch": 11.91, + "learning_rate": 7.4259423186499766e-06, + "loss": 0.0107, + "step": 38557 + }, + { + "epoch": 11.91, + "learning_rate": 7.425459055925606e-06, + "loss": 0.0099, + "step": 38558 + }, + { + "epoch": 11.91, + "learning_rate": 7.424975799640632e-06, + "loss": 0.0111, + "step": 38559 + }, + { + "epoch": 11.91, + "learning_rate": 7.424492549796268e-06, + "loss": 0.0123, + "step": 38560 + }, + { + "epoch": 11.91, + "learning_rate": 7.424009306393715e-06, + "loss": 0.0093, + "step": 38561 + }, + { + "epoch": 11.91, + "learning_rate": 7.423526069434183e-06, + "loss": 0.0124, + "step": 38562 + }, + { + "epoch": 11.91, + "learning_rate": 7.4230428389188856e-06, + "loss": 0.0108, + "step": 38563 + }, + { + "epoch": 11.91, + "learning_rate": 7.422559614849025e-06, + "loss": 0.0121, + "step": 38564 + }, + { + "epoch": 11.91, + "learning_rate": 7.4220763972258125e-06, + "loss": 0.0112, + "step": 38565 + }, + { + "epoch": 11.91, + "learning_rate": 7.421593186050462e-06, + "loss": 0.013, + "step": 38566 + }, + { + "epoch": 11.91, + "learning_rate": 7.421109981324173e-06, + "loss": 0.0125, + "step": 38567 + }, + { + "epoch": 11.91, + "learning_rate": 7.420626783048157e-06, + "loss": 0.0109, + "step": 38568 + }, + { + "epoch": 11.91, + "learning_rate": 7.420143591223631e-06, + "loss": 0.01, + "step": 38569 + }, + { + "epoch": 11.91, + "learning_rate": 7.41966040585179e-06, + "loss": 0.0117, + "step": 38570 + }, + { + "epoch": 11.91, + "learning_rate": 7.419177226933849e-06, + "loss": 0.0116, + "step": 38571 + }, + { + "epoch": 11.91, + "learning_rate": 7.418694054471016e-06, + "loss": 0.0118, + "step": 38572 + }, + { + "epoch": 11.91, + "learning_rate": 7.4182108884645045e-06, + "loss": 0.0116, + "step": 38573 + }, + { + "epoch": 11.91, + "learning_rate": 7.4177277289155155e-06, + "loss": 0.0105, + "step": 38574 + }, + { + "epoch": 11.91, + "learning_rate": 7.417244575825259e-06, + "loss": 0.0123, + "step": 38575 + }, + { + "epoch": 11.91, + "learning_rate": 7.4167614291949485e-06, + "loss": 0.0125, + "step": 38576 + }, + { + "epoch": 11.91, + "learning_rate": 7.416278289025787e-06, + "loss": 0.0106, + "step": 38577 + }, + { + "epoch": 11.91, + "learning_rate": 7.415795155318982e-06, + "loss": 0.0111, + "step": 38578 + }, + { + "epoch": 11.91, + "learning_rate": 7.415312028075752e-06, + "loss": 0.0126, + "step": 38579 + }, + { + "epoch": 11.91, + "learning_rate": 7.414828907297291e-06, + "loss": 0.0125, + "step": 38580 + }, + { + "epoch": 11.91, + "learning_rate": 7.414345792984816e-06, + "loss": 0.0124, + "step": 38581 + }, + { + "epoch": 11.91, + "learning_rate": 7.413862685139538e-06, + "loss": 0.0122, + "step": 38582 + }, + { + "epoch": 11.92, + "learning_rate": 7.413379583762655e-06, + "loss": 0.0117, + "step": 38583 + }, + { + "epoch": 11.92, + "learning_rate": 7.4128964888553844e-06, + "loss": 0.0111, + "step": 38584 + }, + { + "epoch": 11.92, + "learning_rate": 7.412413400418933e-06, + "loss": 0.015, + "step": 38585 + }, + { + "epoch": 11.92, + "learning_rate": 7.411930318454504e-06, + "loss": 0.0126, + "step": 38586 + }, + { + "epoch": 11.92, + "learning_rate": 7.411447242963311e-06, + "loss": 0.0111, + "step": 38587 + }, + { + "epoch": 11.92, + "learning_rate": 7.410964173946563e-06, + "loss": 0.0114, + "step": 38588 + }, + { + "epoch": 11.92, + "learning_rate": 7.410481111405463e-06, + "loss": 0.0104, + "step": 38589 + }, + { + "epoch": 11.92, + "learning_rate": 7.409998055341221e-06, + "loss": 0.0113, + "step": 38590 + }, + { + "epoch": 11.92, + "learning_rate": 7.40951500575505e-06, + "loss": 0.0125, + "step": 38591 + }, + { + "epoch": 11.92, + "learning_rate": 7.409031962648152e-06, + "loss": 0.0121, + "step": 38592 + }, + { + "epoch": 11.92, + "learning_rate": 7.408548926021736e-06, + "loss": 0.0107, + "step": 38593 + }, + { + "epoch": 11.92, + "learning_rate": 7.408065895877016e-06, + "loss": 0.011, + "step": 38594 + }, + { + "epoch": 11.92, + "learning_rate": 7.4075828722151935e-06, + "loss": 0.0113, + "step": 38595 + }, + { + "epoch": 11.92, + "learning_rate": 7.407099855037476e-06, + "loss": 0.0104, + "step": 38596 + }, + { + "epoch": 11.92, + "learning_rate": 7.4066168443450804e-06, + "loss": 0.0108, + "step": 38597 + }, + { + "epoch": 11.92, + "learning_rate": 7.4061338401392065e-06, + "loss": 0.0107, + "step": 38598 + }, + { + "epoch": 11.92, + "learning_rate": 7.405650842421066e-06, + "loss": 0.0142, + "step": 38599 + }, + { + "epoch": 11.92, + "learning_rate": 7.405167851191867e-06, + "loss": 0.0101, + "step": 38600 + }, + { + "epoch": 11.92, + "learning_rate": 7.4046848664528115e-06, + "loss": 0.0118, + "step": 38601 + }, + { + "epoch": 11.92, + "learning_rate": 7.404201888205116e-06, + "loss": 0.0102, + "step": 38602 + }, + { + "epoch": 11.92, + "learning_rate": 7.403718916449982e-06, + "loss": 0.0115, + "step": 38603 + }, + { + "epoch": 11.92, + "learning_rate": 7.403235951188625e-06, + "loss": 0.0123, + "step": 38604 + }, + { + "epoch": 11.92, + "learning_rate": 7.402752992422246e-06, + "loss": 0.0112, + "step": 38605 + }, + { + "epoch": 11.92, + "learning_rate": 7.402270040152054e-06, + "loss": 0.0123, + "step": 38606 + }, + { + "epoch": 11.92, + "learning_rate": 7.401787094379262e-06, + "loss": 0.0106, + "step": 38607 + }, + { + "epoch": 11.92, + "learning_rate": 7.401304155105073e-06, + "loss": 0.012, + "step": 38608 + }, + { + "epoch": 11.92, + "learning_rate": 7.4008212223306965e-06, + "loss": 0.0103, + "step": 38609 + }, + { + "epoch": 11.92, + "learning_rate": 7.400338296057341e-06, + "loss": 0.0095, + "step": 38610 + }, + { + "epoch": 11.92, + "learning_rate": 7.399855376286212e-06, + "loss": 0.0104, + "step": 38611 + }, + { + "epoch": 11.92, + "learning_rate": 7.399372463018518e-06, + "loss": 0.0123, + "step": 38612 + }, + { + "epoch": 11.92, + "learning_rate": 7.3988895562554705e-06, + "loss": 0.0103, + "step": 38613 + }, + { + "epoch": 11.92, + "learning_rate": 7.398406655998272e-06, + "loss": 0.0122, + "step": 38614 + }, + { + "epoch": 11.93, + "learning_rate": 7.397923762248134e-06, + "loss": 0.0122, + "step": 38615 + }, + { + "epoch": 11.93, + "learning_rate": 7.397440875006265e-06, + "loss": 0.0103, + "step": 38616 + }, + { + "epoch": 11.93, + "learning_rate": 7.396957994273868e-06, + "loss": 0.0115, + "step": 38617 + }, + { + "epoch": 11.93, + "learning_rate": 7.396475120052154e-06, + "loss": 0.0115, + "step": 38618 + }, + { + "epoch": 11.93, + "learning_rate": 7.3959922523423346e-06, + "loss": 0.0123, + "step": 38619 + }, + { + "epoch": 11.93, + "learning_rate": 7.39550939114561e-06, + "loss": 0.0125, + "step": 38620 + }, + { + "epoch": 11.93, + "learning_rate": 7.39502653646319e-06, + "loss": 0.0118, + "step": 38621 + }, + { + "epoch": 11.93, + "learning_rate": 7.394543688296288e-06, + "loss": 0.0107, + "step": 38622 + }, + { + "epoch": 11.93, + "learning_rate": 7.394060846646106e-06, + "loss": 0.0105, + "step": 38623 + }, + { + "epoch": 11.93, + "learning_rate": 7.39357801151385e-06, + "loss": 0.0122, + "step": 38624 + }, + { + "epoch": 11.93, + "learning_rate": 7.393095182900736e-06, + "loss": 0.0104, + "step": 38625 + }, + { + "epoch": 11.93, + "learning_rate": 7.392612360807963e-06, + "loss": 0.0116, + "step": 38626 + }, + { + "epoch": 11.93, + "learning_rate": 7.392129545236741e-06, + "loss": 0.0108, + "step": 38627 + }, + { + "epoch": 11.93, + "learning_rate": 7.391646736188285e-06, + "loss": 0.0114, + "step": 38628 + }, + { + "epoch": 11.93, + "learning_rate": 7.391163933663788e-06, + "loss": 0.0119, + "step": 38629 + }, + { + "epoch": 11.93, + "learning_rate": 7.39068113766447e-06, + "loss": 0.013, + "step": 38630 + }, + { + "epoch": 11.93, + "learning_rate": 7.3901983481915365e-06, + "loss": 0.0106, + "step": 38631 + }, + { + "epoch": 11.93, + "learning_rate": 7.389715565246187e-06, + "loss": 0.0113, + "step": 38632 + }, + { + "epoch": 11.93, + "learning_rate": 7.3892327888296385e-06, + "loss": 0.0107, + "step": 38633 + }, + { + "epoch": 11.93, + "learning_rate": 7.3887500189430975e-06, + "loss": 0.0109, + "step": 38634 + }, + { + "epoch": 11.93, + "learning_rate": 7.388267255587764e-06, + "loss": 0.0097, + "step": 38635 + }, + { + "epoch": 11.93, + "learning_rate": 7.387784498764851e-06, + "loss": 0.0105, + "step": 38636 + }, + { + "epoch": 11.93, + "learning_rate": 7.387301748475566e-06, + "loss": 0.0095, + "step": 38637 + }, + { + "epoch": 11.93, + "learning_rate": 7.3868190047211216e-06, + "loss": 0.0091, + "step": 38638 + }, + { + "epoch": 11.93, + "learning_rate": 7.386336267502712e-06, + "loss": 0.0104, + "step": 38639 + }, + { + "epoch": 11.93, + "learning_rate": 7.385853536821554e-06, + "loss": 0.0122, + "step": 38640 + }, + { + "epoch": 11.93, + "learning_rate": 7.385370812678857e-06, + "loss": 0.0103, + "step": 38641 + }, + { + "epoch": 11.93, + "learning_rate": 7.3848880950758195e-06, + "loss": 0.0117, + "step": 38642 + }, + { + "epoch": 11.93, + "learning_rate": 7.384405384013655e-06, + "loss": 0.0096, + "step": 38643 + }, + { + "epoch": 11.93, + "learning_rate": 7.383922679493574e-06, + "loss": 0.0102, + "step": 38644 + }, + { + "epoch": 11.93, + "learning_rate": 7.3834399815167735e-06, + "loss": 0.0111, + "step": 38645 + }, + { + "epoch": 11.93, + "learning_rate": 7.382957290084468e-06, + "loss": 0.0098, + "step": 38646 + }, + { + "epoch": 11.93, + "learning_rate": 7.382474605197867e-06, + "loss": 0.0114, + "step": 38647 + }, + { + "epoch": 11.94, + "learning_rate": 7.381991926858172e-06, + "loss": 0.0097, + "step": 38648 + }, + { + "epoch": 11.94, + "learning_rate": 7.381509255066593e-06, + "loss": 0.0119, + "step": 38649 + }, + { + "epoch": 11.94, + "learning_rate": 7.381026589824338e-06, + "loss": 0.0115, + "step": 38650 + }, + { + "epoch": 11.94, + "learning_rate": 7.380543931132611e-06, + "loss": 0.0122, + "step": 38651 + }, + { + "epoch": 11.94, + "learning_rate": 7.38006127899262e-06, + "loss": 0.0096, + "step": 38652 + }, + { + "epoch": 11.94, + "learning_rate": 7.37957863340558e-06, + "loss": 0.0124, + "step": 38653 + }, + { + "epoch": 11.94, + "learning_rate": 7.379095994372687e-06, + "loss": 0.0109, + "step": 38654 + }, + { + "epoch": 11.94, + "learning_rate": 7.378613361895152e-06, + "loss": 0.0103, + "step": 38655 + }, + { + "epoch": 11.94, + "learning_rate": 7.378130735974187e-06, + "loss": 0.0128, + "step": 38656 + }, + { + "epoch": 11.94, + "learning_rate": 7.377648116610994e-06, + "loss": 0.0108, + "step": 38657 + }, + { + "epoch": 11.94, + "learning_rate": 7.377165503806779e-06, + "loss": 0.0116, + "step": 38658 + }, + { + "epoch": 11.94, + "learning_rate": 7.3766828975627544e-06, + "loss": 0.0105, + "step": 38659 + }, + { + "epoch": 11.94, + "learning_rate": 7.376200297880122e-06, + "loss": 0.0115, + "step": 38660 + }, + { + "epoch": 11.94, + "learning_rate": 7.375717704760093e-06, + "loss": 0.0104, + "step": 38661 + }, + { + "epoch": 11.94, + "learning_rate": 7.375235118203873e-06, + "loss": 0.0095, + "step": 38662 + }, + { + "epoch": 11.94, + "learning_rate": 7.374752538212665e-06, + "loss": 0.0097, + "step": 38663 + }, + { + "epoch": 11.94, + "learning_rate": 7.374269964787681e-06, + "loss": 0.0128, + "step": 38664 + }, + { + "epoch": 11.94, + "learning_rate": 7.3737873979301315e-06, + "loss": 0.0121, + "step": 38665 + }, + { + "epoch": 11.94, + "learning_rate": 7.373304837641213e-06, + "loss": 0.0109, + "step": 38666 + }, + { + "epoch": 11.94, + "learning_rate": 7.37282228392214e-06, + "loss": 0.0113, + "step": 38667 + }, + { + "epoch": 11.94, + "learning_rate": 7.372339736774119e-06, + "loss": 0.0118, + "step": 38668 + }, + { + "epoch": 11.94, + "learning_rate": 7.3718571961983555e-06, + "loss": 0.0107, + "step": 38669 + }, + { + "epoch": 11.94, + "learning_rate": 7.3713746621960534e-06, + "loss": 0.0113, + "step": 38670 + }, + { + "epoch": 11.94, + "learning_rate": 7.370892134768424e-06, + "loss": 0.0125, + "step": 38671 + }, + { + "epoch": 11.94, + "learning_rate": 7.370409613916676e-06, + "loss": 0.0112, + "step": 38672 + }, + { + "epoch": 11.94, + "learning_rate": 7.369927099642009e-06, + "loss": 0.0112, + "step": 38673 + }, + { + "epoch": 11.94, + "learning_rate": 7.369444591945636e-06, + "loss": 0.009, + "step": 38674 + }, + { + "epoch": 11.94, + "learning_rate": 7.368962090828764e-06, + "loss": 0.0105, + "step": 38675 + }, + { + "epoch": 11.94, + "learning_rate": 7.368479596292592e-06, + "loss": 0.0107, + "step": 38676 + }, + { + "epoch": 11.94, + "learning_rate": 7.367997108338336e-06, + "loss": 0.0122, + "step": 38677 + }, + { + "epoch": 11.94, + "learning_rate": 7.367514626967201e-06, + "loss": 0.0118, + "step": 38678 + }, + { + "epoch": 11.94, + "learning_rate": 7.3670321521803914e-06, + "loss": 0.0093, + "step": 38679 + }, + { + "epoch": 11.95, + "learning_rate": 7.36654968397911e-06, + "loss": 0.0116, + "step": 38680 + }, + { + "epoch": 11.95, + "learning_rate": 7.366067222364574e-06, + "loss": 0.0115, + "step": 38681 + }, + { + "epoch": 11.95, + "learning_rate": 7.365584767337982e-06, + "loss": 0.0113, + "step": 38682 + }, + { + "epoch": 11.95, + "learning_rate": 7.365102318900541e-06, + "loss": 0.0092, + "step": 38683 + }, + { + "epoch": 11.95, + "learning_rate": 7.364619877053463e-06, + "loss": 0.0105, + "step": 38684 + }, + { + "epoch": 11.95, + "learning_rate": 7.364137441797949e-06, + "loss": 0.0115, + "step": 38685 + }, + { + "epoch": 11.95, + "learning_rate": 7.363655013135208e-06, + "loss": 0.01, + "step": 38686 + }, + { + "epoch": 11.95, + "learning_rate": 7.363172591066452e-06, + "loss": 0.0108, + "step": 38687 + }, + { + "epoch": 11.95, + "learning_rate": 7.362690175592875e-06, + "loss": 0.0115, + "step": 38688 + }, + { + "epoch": 11.95, + "learning_rate": 7.3622077667156946e-06, + "loss": 0.0121, + "step": 38689 + }, + { + "epoch": 11.95, + "learning_rate": 7.361725364436114e-06, + "loss": 0.0116, + "step": 38690 + }, + { + "epoch": 11.95, + "learning_rate": 7.361242968755336e-06, + "loss": 0.0111, + "step": 38691 + }, + { + "epoch": 11.95, + "learning_rate": 7.360760579674573e-06, + "loss": 0.0122, + "step": 38692 + }, + { + "epoch": 11.95, + "learning_rate": 7.360278197195031e-06, + "loss": 0.0115, + "step": 38693 + }, + { + "epoch": 11.95, + "learning_rate": 7.35979582131791e-06, + "loss": 0.0112, + "step": 38694 + }, + { + "epoch": 11.95, + "learning_rate": 7.3593134520444244e-06, + "loss": 0.01, + "step": 38695 + }, + { + "epoch": 11.95, + "learning_rate": 7.3588310893757796e-06, + "loss": 0.0116, + "step": 38696 + }, + { + "epoch": 11.95, + "learning_rate": 7.358348733313177e-06, + "loss": 0.009, + "step": 38697 + }, + { + "epoch": 11.95, + "learning_rate": 7.357866383857823e-06, + "loss": 0.0122, + "step": 38698 + }, + { + "epoch": 11.95, + "learning_rate": 7.357384041010934e-06, + "loss": 0.0113, + "step": 38699 + }, + { + "epoch": 11.95, + "learning_rate": 7.3569017047737045e-06, + "loss": 0.0135, + "step": 38700 + }, + { + "epoch": 11.95, + "learning_rate": 7.356419375147346e-06, + "loss": 0.0116, + "step": 38701 + }, + { + "epoch": 11.95, + "learning_rate": 7.355937052133067e-06, + "loss": 0.0112, + "step": 38702 + }, + { + "epoch": 11.95, + "learning_rate": 7.355454735732073e-06, + "loss": 0.0108, + "step": 38703 + }, + { + "epoch": 11.95, + "learning_rate": 7.354972425945563e-06, + "loss": 0.0131, + "step": 38704 + }, + { + "epoch": 11.95, + "learning_rate": 7.354490122774753e-06, + "loss": 0.0099, + "step": 38705 + }, + { + "epoch": 11.95, + "learning_rate": 7.354007826220848e-06, + "loss": 0.0123, + "step": 38706 + }, + { + "epoch": 11.95, + "learning_rate": 7.3535255362850514e-06, + "loss": 0.0117, + "step": 38707 + }, + { + "epoch": 11.95, + "learning_rate": 7.353043252968566e-06, + "loss": 0.0082, + "step": 38708 + }, + { + "epoch": 11.95, + "learning_rate": 7.352560976272607e-06, + "loss": 0.0104, + "step": 38709 + }, + { + "epoch": 11.95, + "learning_rate": 7.352078706198373e-06, + "loss": 0.0112, + "step": 38710 + }, + { + "epoch": 11.95, + "learning_rate": 7.351596442747072e-06, + "loss": 0.0103, + "step": 38711 + }, + { + "epoch": 11.96, + "learning_rate": 7.351114185919915e-06, + "loss": 0.0119, + "step": 38712 + }, + { + "epoch": 11.96, + "learning_rate": 7.350631935718103e-06, + "loss": 0.0129, + "step": 38713 + }, + { + "epoch": 11.96, + "learning_rate": 7.3501496921428415e-06, + "loss": 0.0107, + "step": 38714 + }, + { + "epoch": 11.96, + "learning_rate": 7.349667455195343e-06, + "loss": 0.0111, + "step": 38715 + }, + { + "epoch": 11.96, + "learning_rate": 7.349185224876807e-06, + "loss": 0.0126, + "step": 38716 + }, + { + "epoch": 11.96, + "learning_rate": 7.348703001188443e-06, + "loss": 0.0117, + "step": 38717 + }, + { + "epoch": 11.96, + "learning_rate": 7.348220784131459e-06, + "loss": 0.0103, + "step": 38718 + }, + { + "epoch": 11.96, + "learning_rate": 7.347738573707053e-06, + "loss": 0.011, + "step": 38719 + }, + { + "epoch": 11.96, + "learning_rate": 7.347256369916439e-06, + "loss": 0.0104, + "step": 38720 + }, + { + "epoch": 11.96, + "learning_rate": 7.346774172760822e-06, + "loss": 0.0117, + "step": 38721 + }, + { + "epoch": 11.96, + "learning_rate": 7.346291982241405e-06, + "loss": 0.0116, + "step": 38722 + }, + { + "epoch": 11.96, + "learning_rate": 7.3458097983593955e-06, + "loss": 0.0111, + "step": 38723 + }, + { + "epoch": 11.96, + "learning_rate": 7.345327621116003e-06, + "loss": 0.0108, + "step": 38724 + }, + { + "epoch": 11.96, + "learning_rate": 7.344845450512426e-06, + "loss": 0.0121, + "step": 38725 + }, + { + "epoch": 11.96, + "learning_rate": 7.344363286549876e-06, + "loss": 0.0109, + "step": 38726 + }, + { + "epoch": 11.96, + "learning_rate": 7.34388112922956e-06, + "loss": 0.0111, + "step": 38727 + }, + { + "epoch": 11.96, + "learning_rate": 7.343398978552681e-06, + "loss": 0.0128, + "step": 38728 + }, + { + "epoch": 11.96, + "learning_rate": 7.342916834520442e-06, + "loss": 0.0145, + "step": 38729 + }, + { + "epoch": 11.96, + "learning_rate": 7.3424346971340575e-06, + "loss": 0.0099, + "step": 38730 + }, + { + "epoch": 11.96, + "learning_rate": 7.341952566394727e-06, + "loss": 0.0107, + "step": 38731 + }, + { + "epoch": 11.96, + "learning_rate": 7.3414704423036555e-06, + "loss": 0.0121, + "step": 38732 + }, + { + "epoch": 11.96, + "learning_rate": 7.340988324862055e-06, + "loss": 0.0115, + "step": 38733 + }, + { + "epoch": 11.96, + "learning_rate": 7.3405062140711255e-06, + "loss": 0.0119, + "step": 38734 + }, + { + "epoch": 11.96, + "learning_rate": 7.3400241099320735e-06, + "loss": 0.0101, + "step": 38735 + }, + { + "epoch": 11.96, + "learning_rate": 7.339542012446108e-06, + "loss": 0.0102, + "step": 38736 + }, + { + "epoch": 11.96, + "learning_rate": 7.3390599216144355e-06, + "loss": 0.0116, + "step": 38737 + }, + { + "epoch": 11.96, + "learning_rate": 7.338577837438257e-06, + "loss": 0.0091, + "step": 38738 + }, + { + "epoch": 11.96, + "learning_rate": 7.33809575991878e-06, + "loss": 0.0115, + "step": 38739 + }, + { + "epoch": 11.96, + "learning_rate": 7.3376136890572135e-06, + "loss": 0.0093, + "step": 38740 + }, + { + "epoch": 11.96, + "learning_rate": 7.337131624854759e-06, + "loss": 0.0104, + "step": 38741 + }, + { + "epoch": 11.96, + "learning_rate": 7.336649567312622e-06, + "loss": 0.0084, + "step": 38742 + }, + { + "epoch": 11.96, + "learning_rate": 7.336167516432015e-06, + "loss": 0.014, + "step": 38743 + }, + { + "epoch": 11.96, + "learning_rate": 7.3356854722141364e-06, + "loss": 0.0091, + "step": 38744 + }, + { + "epoch": 11.97, + "learning_rate": 7.335203434660192e-06, + "loss": 0.0125, + "step": 38745 + }, + { + "epoch": 11.97, + "learning_rate": 7.334721403771396e-06, + "loss": 0.0112, + "step": 38746 + }, + { + "epoch": 11.97, + "learning_rate": 7.334239379548943e-06, + "loss": 0.0099, + "step": 38747 + }, + { + "epoch": 11.97, + "learning_rate": 7.333757361994045e-06, + "loss": 0.0106, + "step": 38748 + }, + { + "epoch": 11.97, + "learning_rate": 7.333275351107907e-06, + "loss": 0.0119, + "step": 38749 + }, + { + "epoch": 11.97, + "learning_rate": 7.3327933468917314e-06, + "loss": 0.0121, + "step": 38750 + }, + { + "epoch": 11.97, + "learning_rate": 7.332311349346727e-06, + "loss": 0.0122, + "step": 38751 + }, + { + "epoch": 11.97, + "learning_rate": 7.331829358474101e-06, + "loss": 0.0117, + "step": 38752 + }, + { + "epoch": 11.97, + "learning_rate": 7.331347374275052e-06, + "loss": 0.0108, + "step": 38753 + }, + { + "epoch": 11.97, + "learning_rate": 7.330865396750791e-06, + "loss": 0.0118, + "step": 38754 + }, + { + "epoch": 11.97, + "learning_rate": 7.330383425902527e-06, + "loss": 0.0104, + "step": 38755 + }, + { + "epoch": 11.97, + "learning_rate": 7.329901461731457e-06, + "loss": 0.0121, + "step": 38756 + }, + { + "epoch": 11.97, + "learning_rate": 7.329419504238788e-06, + "loss": 0.0118, + "step": 38757 + }, + { + "epoch": 11.97, + "learning_rate": 7.328937553425734e-06, + "loss": 0.0116, + "step": 38758 + }, + { + "epoch": 11.97, + "learning_rate": 7.32845560929349e-06, + "loss": 0.0109, + "step": 38759 + }, + { + "epoch": 11.97, + "learning_rate": 7.327973671843265e-06, + "loss": 0.011, + "step": 38760 + }, + { + "epoch": 11.97, + "learning_rate": 7.3274917410762695e-06, + "loss": 0.0112, + "step": 38761 + }, + { + "epoch": 11.97, + "learning_rate": 7.327009816993702e-06, + "loss": 0.0106, + "step": 38762 + }, + { + "epoch": 11.97, + "learning_rate": 7.326527899596769e-06, + "loss": 0.0104, + "step": 38763 + }, + { + "epoch": 11.97, + "learning_rate": 7.326045988886681e-06, + "loss": 0.0102, + "step": 38764 + }, + { + "epoch": 11.97, + "learning_rate": 7.325564084864638e-06, + "loss": 0.013, + "step": 38765 + }, + { + "epoch": 11.97, + "learning_rate": 7.325082187531847e-06, + "loss": 0.0139, + "step": 38766 + }, + { + "epoch": 11.97, + "learning_rate": 7.32460029688951e-06, + "loss": 0.0102, + "step": 38767 + }, + { + "epoch": 11.97, + "learning_rate": 7.324118412938841e-06, + "loss": 0.0109, + "step": 38768 + }, + { + "epoch": 11.97, + "learning_rate": 7.323636535681038e-06, + "loss": 0.0116, + "step": 38769 + }, + { + "epoch": 11.97, + "learning_rate": 7.323154665117305e-06, + "loss": 0.0095, + "step": 38770 + }, + { + "epoch": 11.97, + "learning_rate": 7.322672801248856e-06, + "loss": 0.0121, + "step": 38771 + }, + { + "epoch": 11.97, + "learning_rate": 7.322190944076888e-06, + "loss": 0.0108, + "step": 38772 + }, + { + "epoch": 11.97, + "learning_rate": 7.321709093602606e-06, + "loss": 0.0104, + "step": 38773 + }, + { + "epoch": 11.97, + "learning_rate": 7.321227249827223e-06, + "loss": 0.0122, + "step": 38774 + }, + { + "epoch": 11.97, + "learning_rate": 7.3207454127519374e-06, + "loss": 0.0094, + "step": 38775 + }, + { + "epoch": 11.97, + "learning_rate": 7.320263582377953e-06, + "loss": 0.0096, + "step": 38776 + }, + { + "epoch": 11.98, + "learning_rate": 7.3197817587064855e-06, + "loss": 0.014, + "step": 38777 + }, + { + "epoch": 11.98, + "learning_rate": 7.3192999417387254e-06, + "loss": 0.0109, + "step": 38778 + }, + { + "epoch": 11.98, + "learning_rate": 7.318818131475888e-06, + "loss": 0.0116, + "step": 38779 + }, + { + "epoch": 11.98, + "learning_rate": 7.318336327919177e-06, + "loss": 0.0111, + "step": 38780 + }, + { + "epoch": 11.98, + "learning_rate": 7.317854531069792e-06, + "loss": 0.0118, + "step": 38781 + }, + { + "epoch": 11.98, + "learning_rate": 7.317372740928944e-06, + "loss": 0.0098, + "step": 38782 + }, + { + "epoch": 11.98, + "learning_rate": 7.316890957497837e-06, + "loss": 0.0099, + "step": 38783 + }, + { + "epoch": 11.98, + "learning_rate": 7.316409180777673e-06, + "loss": 0.0117, + "step": 38784 + }, + { + "epoch": 11.98, + "learning_rate": 7.3159274107696605e-06, + "loss": 0.0107, + "step": 38785 + }, + { + "epoch": 11.98, + "learning_rate": 7.3154456474750055e-06, + "loss": 0.0129, + "step": 38786 + }, + { + "epoch": 11.98, + "learning_rate": 7.3149638908949085e-06, + "loss": 0.0109, + "step": 38787 + }, + { + "epoch": 11.98, + "learning_rate": 7.314482141030573e-06, + "loss": 0.0105, + "step": 38788 + }, + { + "epoch": 11.98, + "learning_rate": 7.314000397883213e-06, + "loss": 0.0113, + "step": 38789 + }, + { + "epoch": 11.98, + "learning_rate": 7.313518661454024e-06, + "loss": 0.0114, + "step": 38790 + }, + { + "epoch": 11.98, + "learning_rate": 7.313036931744215e-06, + "loss": 0.0103, + "step": 38791 + }, + { + "epoch": 11.98, + "learning_rate": 7.312555208754995e-06, + "loss": 0.0107, + "step": 38792 + }, + { + "epoch": 11.98, + "learning_rate": 7.312073492487561e-06, + "loss": 0.0092, + "step": 38793 + }, + { + "epoch": 11.98, + "learning_rate": 7.311591782943119e-06, + "loss": 0.0127, + "step": 38794 + }, + { + "epoch": 11.98, + "learning_rate": 7.311110080122884e-06, + "loss": 0.0123, + "step": 38795 + }, + { + "epoch": 11.98, + "learning_rate": 7.3106283840280465e-06, + "loss": 0.0112, + "step": 38796 + }, + { + "epoch": 11.98, + "learning_rate": 7.310146694659819e-06, + "loss": 0.0114, + "step": 38797 + }, + { + "epoch": 11.98, + "learning_rate": 7.309665012019409e-06, + "loss": 0.0089, + "step": 38798 + }, + { + "epoch": 11.98, + "learning_rate": 7.309183336108012e-06, + "loss": 0.0113, + "step": 38799 + }, + { + "epoch": 11.98, + "learning_rate": 7.30870166692684e-06, + "loss": 0.0108, + "step": 38800 + }, + { + "epoch": 11.98, + "learning_rate": 7.3082200044770954e-06, + "loss": 0.0134, + "step": 38801 + }, + { + "epoch": 11.98, + "learning_rate": 7.307738348759988e-06, + "loss": 0.0116, + "step": 38802 + }, + { + "epoch": 11.98, + "learning_rate": 7.307256699776713e-06, + "loss": 0.011, + "step": 38803 + }, + { + "epoch": 11.98, + "learning_rate": 7.3067750575284805e-06, + "loss": 0.0113, + "step": 38804 + }, + { + "epoch": 11.98, + "learning_rate": 7.3062934220165e-06, + "loss": 0.0108, + "step": 38805 + }, + { + "epoch": 11.98, + "learning_rate": 7.305811793241966e-06, + "loss": 0.0091, + "step": 38806 + }, + { + "epoch": 11.98, + "learning_rate": 7.305330171206089e-06, + "loss": 0.0119, + "step": 38807 + }, + { + "epoch": 11.98, + "learning_rate": 7.304848555910076e-06, + "loss": 0.0111, + "step": 38808 + }, + { + "epoch": 11.98, + "learning_rate": 7.3043669473551215e-06, + "loss": 0.0094, + "step": 38809 + }, + { + "epoch": 11.99, + "learning_rate": 7.303885345542441e-06, + "loss": 0.0104, + "step": 38810 + }, + { + "epoch": 11.99, + "learning_rate": 7.303403750473237e-06, + "loss": 0.0099, + "step": 38811 + }, + { + "epoch": 11.99, + "learning_rate": 7.302922162148708e-06, + "loss": 0.0114, + "step": 38812 + }, + { + "epoch": 11.99, + "learning_rate": 7.302440580570065e-06, + "loss": 0.0101, + "step": 38813 + }, + { + "epoch": 11.99, + "learning_rate": 7.30195900573851e-06, + "loss": 0.0107, + "step": 38814 + }, + { + "epoch": 11.99, + "learning_rate": 7.3014774376552466e-06, + "loss": 0.011, + "step": 38815 + }, + { + "epoch": 11.99, + "learning_rate": 7.30099587632148e-06, + "loss": 0.0117, + "step": 38816 + }, + { + "epoch": 11.99, + "learning_rate": 7.300514321738419e-06, + "loss": 0.0108, + "step": 38817 + }, + { + "epoch": 11.99, + "learning_rate": 7.300032773907259e-06, + "loss": 0.0095, + "step": 38818 + }, + { + "epoch": 11.99, + "learning_rate": 7.299551232829211e-06, + "loss": 0.0104, + "step": 38819 + }, + { + "epoch": 11.99, + "learning_rate": 7.29906969850548e-06, + "loss": 0.0119, + "step": 38820 + }, + { + "epoch": 11.99, + "learning_rate": 7.2985881709372665e-06, + "loss": 0.0098, + "step": 38821 + }, + { + "epoch": 11.99, + "learning_rate": 7.298106650125773e-06, + "loss": 0.0112, + "step": 38822 + }, + { + "epoch": 11.99, + "learning_rate": 7.297625136072215e-06, + "loss": 0.0109, + "step": 38823 + }, + { + "epoch": 11.99, + "learning_rate": 7.297143628777785e-06, + "loss": 0.0103, + "step": 38824 + }, + { + "epoch": 11.99, + "learning_rate": 7.29666212824369e-06, + "loss": 0.0111, + "step": 38825 + }, + { + "epoch": 11.99, + "learning_rate": 7.296180634471144e-06, + "loss": 0.0108, + "step": 38826 + }, + { + "epoch": 11.99, + "learning_rate": 7.295699147461335e-06, + "loss": 0.0091, + "step": 38827 + }, + { + "epoch": 11.99, + "learning_rate": 7.295217667215479e-06, + "loss": 0.0126, + "step": 38828 + }, + { + "epoch": 11.99, + "learning_rate": 7.294736193734779e-06, + "loss": 0.0106, + "step": 38829 + }, + { + "epoch": 11.99, + "learning_rate": 7.2942547270204325e-06, + "loss": 0.0107, + "step": 38830 + }, + { + "epoch": 11.99, + "learning_rate": 7.2937732670736504e-06, + "loss": 0.0104, + "step": 38831 + }, + { + "epoch": 11.99, + "learning_rate": 7.293291813895633e-06, + "loss": 0.0118, + "step": 38832 + }, + { + "epoch": 11.99, + "learning_rate": 7.29281036748759e-06, + "loss": 0.0126, + "step": 38833 + }, + { + "epoch": 11.99, + "learning_rate": 7.292328927850722e-06, + "loss": 0.0103, + "step": 38834 + }, + { + "epoch": 11.99, + "learning_rate": 7.291847494986228e-06, + "loss": 0.0096, + "step": 38835 + }, + { + "epoch": 11.99, + "learning_rate": 7.291366068895327e-06, + "loss": 0.0103, + "step": 38836 + }, + { + "epoch": 11.99, + "learning_rate": 7.290884649579205e-06, + "loss": 0.0103, + "step": 38837 + }, + { + "epoch": 11.99, + "learning_rate": 7.290403237039077e-06, + "loss": 0.0107, + "step": 38838 + }, + { + "epoch": 11.99, + "learning_rate": 7.2899218312761475e-06, + "loss": 0.012, + "step": 38839 + }, + { + "epoch": 11.99, + "learning_rate": 7.289440432291613e-06, + "loss": 0.0099, + "step": 38840 + }, + { + "epoch": 11.99, + "learning_rate": 7.288959040086685e-06, + "loss": 0.0111, + "step": 38841 + }, + { + "epoch": 12.0, + "learning_rate": 7.288477654662567e-06, + "loss": 0.0115, + "step": 38842 + }, + { + "epoch": 12.0, + "learning_rate": 7.287996276020456e-06, + "loss": 0.0102, + "step": 38843 + }, + { + "epoch": 12.0, + "learning_rate": 7.287514904161563e-06, + "loss": 0.0121, + "step": 38844 + }, + { + "epoch": 12.0, + "learning_rate": 7.2870335390870924e-06, + "loss": 0.013, + "step": 38845 + }, + { + "epoch": 12.0, + "learning_rate": 7.286552180798244e-06, + "loss": 0.0114, + "step": 38846 + }, + { + "epoch": 12.0, + "learning_rate": 7.286070829296221e-06, + "loss": 0.0099, + "step": 38847 + }, + { + "epoch": 12.0, + "learning_rate": 7.285589484582234e-06, + "loss": 0.0107, + "step": 38848 + }, + { + "epoch": 12.0, + "learning_rate": 7.285108146657481e-06, + "loss": 0.0107, + "step": 38849 + }, + { + "epoch": 12.0, + "learning_rate": 7.284626815523166e-06, + "loss": 0.009, + "step": 38850 + }, + { + "epoch": 12.0, + "learning_rate": 7.284145491180498e-06, + "loss": 0.0122, + "step": 38851 + }, + { + "epoch": 12.0, + "learning_rate": 7.283664173630676e-06, + "loss": 0.0095, + "step": 38852 + }, + { + "epoch": 12.0, + "learning_rate": 7.283182862874903e-06, + "loss": 0.0099, + "step": 38853 + }, + { + "epoch": 12.0, + "learning_rate": 7.282701558914389e-06, + "loss": 0.0098, + "step": 38854 + }, + { + "epoch": 12.0, + "learning_rate": 7.282220261750332e-06, + "loss": 0.0098, + "step": 38855 + }, + { + "epoch": 12.0, + "learning_rate": 7.281738971383938e-06, + "loss": 0.0118, + "step": 38856 + }, + { + "epoch": 12.0, + "learning_rate": 7.281257687816412e-06, + "loss": 0.0099, + "step": 38857 + }, + { + "epoch": 12.0, + "learning_rate": 7.280776411048953e-06, + "loss": 0.0092, + "step": 38858 + }, + { + "epoch": 12.0, + "learning_rate": 7.280295141082769e-06, + "loss": 0.0059, + "step": 38859 + }, + { + "epoch": 12.0, + "learning_rate": 7.279813877919067e-06, + "loss": 0.0058, + "step": 38860 + }, + { + "epoch": 12.0, + "learning_rate": 7.279332621559041e-06, + "loss": 0.0061, + "step": 38861 + }, + { + "epoch": 12.0, + "learning_rate": 7.278851372003903e-06, + "loss": 0.0077, + "step": 38862 + }, + { + "epoch": 12.0, + "learning_rate": 7.278370129254857e-06, + "loss": 0.0061, + "step": 38863 + }, + { + "epoch": 12.0, + "learning_rate": 7.277888893313099e-06, + "loss": 0.0058, + "step": 38864 + }, + { + "epoch": 12.0, + "learning_rate": 7.2774076641798385e-06, + "loss": 0.0063, + "step": 38865 + }, + { + "epoch": 12.0, + "learning_rate": 7.276926441856278e-06, + "loss": 0.0066, + "step": 38866 + }, + { + "epoch": 12.0, + "learning_rate": 7.276445226343623e-06, + "loss": 0.0056, + "step": 38867 + }, + { + "epoch": 12.0, + "learning_rate": 7.275964017643072e-06, + "loss": 0.0055, + "step": 38868 + }, + { + "epoch": 12.0, + "learning_rate": 7.275482815755835e-06, + "loss": 0.0066, + "step": 38869 + }, + { + "epoch": 12.0, + "learning_rate": 7.275001620683113e-06, + "loss": 0.0064, + "step": 38870 + }, + { + "epoch": 12.0, + "learning_rate": 7.274520432426104e-06, + "loss": 0.0052, + "step": 38871 + }, + { + "epoch": 12.0, + "learning_rate": 7.27403925098602e-06, + "loss": 0.0055, + "step": 38872 + }, + { + "epoch": 12.0, + "learning_rate": 7.2735580763640625e-06, + "loss": 0.0073, + "step": 38873 + }, + { + "epoch": 12.01, + "learning_rate": 7.273076908561429e-06, + "loss": 0.0053, + "step": 38874 + }, + { + "epoch": 12.01, + "learning_rate": 7.272595747579331e-06, + "loss": 0.0064, + "step": 38875 + }, + { + "epoch": 12.01, + "learning_rate": 7.272114593418969e-06, + "loss": 0.0068, + "step": 38876 + }, + { + "epoch": 12.01, + "learning_rate": 7.271633446081545e-06, + "loss": 0.0049, + "step": 38877 + }, + { + "epoch": 12.01, + "learning_rate": 7.271152305568261e-06, + "loss": 0.0067, + "step": 38878 + }, + { + "epoch": 12.01, + "learning_rate": 7.270671171880326e-06, + "loss": 0.0074, + "step": 38879 + }, + { + "epoch": 12.01, + "learning_rate": 7.2701900450189385e-06, + "loss": 0.006, + "step": 38880 + }, + { + "epoch": 12.01, + "learning_rate": 7.269708924985302e-06, + "loss": 0.0061, + "step": 38881 + }, + { + "epoch": 12.01, + "learning_rate": 7.2692278117806255e-06, + "loss": 0.0066, + "step": 38882 + }, + { + "epoch": 12.01, + "learning_rate": 7.2687467054061064e-06, + "loss": 0.0082, + "step": 38883 + }, + { + "epoch": 12.01, + "learning_rate": 7.268265605862948e-06, + "loss": 0.0067, + "step": 38884 + }, + { + "epoch": 12.01, + "learning_rate": 7.267784513152362e-06, + "loss": 0.0067, + "step": 38885 + }, + { + "epoch": 12.01, + "learning_rate": 7.267303427275539e-06, + "loss": 0.005, + "step": 38886 + }, + { + "epoch": 12.01, + "learning_rate": 7.2668223482336886e-06, + "loss": 0.0056, + "step": 38887 + }, + { + "epoch": 12.01, + "learning_rate": 7.266341276028019e-06, + "loss": 0.0073, + "step": 38888 + }, + { + "epoch": 12.01, + "learning_rate": 7.265860210659722e-06, + "loss": 0.0073, + "step": 38889 + }, + { + "epoch": 12.01, + "learning_rate": 7.26537915213001e-06, + "loss": 0.0068, + "step": 38890 + }, + { + "epoch": 12.01, + "learning_rate": 7.264898100440086e-06, + "loss": 0.0055, + "step": 38891 + }, + { + "epoch": 12.01, + "learning_rate": 7.264417055591147e-06, + "loss": 0.005, + "step": 38892 + }, + { + "epoch": 12.01, + "learning_rate": 7.263936017584401e-06, + "loss": 0.0062, + "step": 38893 + }, + { + "epoch": 12.01, + "learning_rate": 7.2634549864210524e-06, + "loss": 0.0061, + "step": 38894 + }, + { + "epoch": 12.01, + "learning_rate": 7.2629739621022995e-06, + "loss": 0.0075, + "step": 38895 + }, + { + "epoch": 12.01, + "learning_rate": 7.2624929446293465e-06, + "loss": 0.0049, + "step": 38896 + }, + { + "epoch": 12.01, + "learning_rate": 7.262011934003402e-06, + "loss": 0.0044, + "step": 38897 + }, + { + "epoch": 12.01, + "learning_rate": 7.261530930225663e-06, + "loss": 0.0065, + "step": 38898 + }, + { + "epoch": 12.01, + "learning_rate": 7.2610499332973325e-06, + "loss": 0.0061, + "step": 38899 + }, + { + "epoch": 12.01, + "learning_rate": 7.260568943219618e-06, + "loss": 0.0068, + "step": 38900 + }, + { + "epoch": 12.01, + "learning_rate": 7.260087959993722e-06, + "loss": 0.0051, + "step": 38901 + }, + { + "epoch": 12.01, + "learning_rate": 7.259606983620842e-06, + "loss": 0.0056, + "step": 38902 + }, + { + "epoch": 12.01, + "learning_rate": 7.2591260141021854e-06, + "loss": 0.0067, + "step": 38903 + }, + { + "epoch": 12.01, + "learning_rate": 7.258645051438957e-06, + "loss": 0.0064, + "step": 38904 + }, + { + "epoch": 12.01, + "learning_rate": 7.258164095632356e-06, + "loss": 0.0053, + "step": 38905 + }, + { + "epoch": 12.01, + "learning_rate": 7.257683146683585e-06, + "loss": 0.0057, + "step": 38906 + }, + { + "epoch": 12.02, + "learning_rate": 7.257202204593852e-06, + "loss": 0.0053, + "step": 38907 + }, + { + "epoch": 12.02, + "learning_rate": 7.256721269364355e-06, + "loss": 0.0061, + "step": 38908 + }, + { + "epoch": 12.02, + "learning_rate": 7.2562403409962966e-06, + "loss": 0.0062, + "step": 38909 + }, + { + "epoch": 12.02, + "learning_rate": 7.255759419490884e-06, + "loss": 0.0072, + "step": 38910 + }, + { + "epoch": 12.02, + "learning_rate": 7.255278504849317e-06, + "loss": 0.005, + "step": 38911 + }, + { + "epoch": 12.02, + "learning_rate": 7.254797597072797e-06, + "loss": 0.0088, + "step": 38912 + }, + { + "epoch": 12.02, + "learning_rate": 7.2543166961625335e-06, + "loss": 0.0062, + "step": 38913 + }, + { + "epoch": 12.02, + "learning_rate": 7.2538358021197205e-06, + "loss": 0.0062, + "step": 38914 + }, + { + "epoch": 12.02, + "learning_rate": 7.253354914945567e-06, + "loss": 0.0059, + "step": 38915 + }, + { + "epoch": 12.02, + "learning_rate": 7.252874034641275e-06, + "loss": 0.0053, + "step": 38916 + }, + { + "epoch": 12.02, + "learning_rate": 7.252393161208043e-06, + "loss": 0.0059, + "step": 38917 + }, + { + "epoch": 12.02, + "learning_rate": 7.251912294647078e-06, + "loss": 0.0046, + "step": 38918 + }, + { + "epoch": 12.02, + "learning_rate": 7.251431434959584e-06, + "loss": 0.0059, + "step": 38919 + }, + { + "epoch": 12.02, + "learning_rate": 7.250950582146756e-06, + "loss": 0.0071, + "step": 38920 + }, + { + "epoch": 12.02, + "learning_rate": 7.250469736209806e-06, + "loss": 0.006, + "step": 38921 + }, + { + "epoch": 12.02, + "learning_rate": 7.249988897149933e-06, + "loss": 0.007, + "step": 38922 + }, + { + "epoch": 12.02, + "learning_rate": 7.249508064968336e-06, + "loss": 0.0055, + "step": 38923 + }, + { + "epoch": 12.02, + "learning_rate": 7.249027239666222e-06, + "loss": 0.0068, + "step": 38924 + }, + { + "epoch": 12.02, + "learning_rate": 7.248546421244797e-06, + "loss": 0.0074, + "step": 38925 + }, + { + "epoch": 12.02, + "learning_rate": 7.248065609705255e-06, + "loss": 0.0043, + "step": 38926 + }, + { + "epoch": 12.02, + "learning_rate": 7.2475848050488015e-06, + "loss": 0.0075, + "step": 38927 + }, + { + "epoch": 12.02, + "learning_rate": 7.2471040072766455e-06, + "loss": 0.0058, + "step": 38928 + }, + { + "epoch": 12.02, + "learning_rate": 7.2466232163899805e-06, + "loss": 0.0049, + "step": 38929 + }, + { + "epoch": 12.02, + "learning_rate": 7.2461424323900135e-06, + "loss": 0.0064, + "step": 38930 + }, + { + "epoch": 12.02, + "learning_rate": 7.2456616552779465e-06, + "loss": 0.0054, + "step": 38931 + }, + { + "epoch": 12.02, + "learning_rate": 7.245180885054984e-06, + "loss": 0.0063, + "step": 38932 + }, + { + "epoch": 12.02, + "learning_rate": 7.244700121722324e-06, + "loss": 0.0061, + "step": 38933 + }, + { + "epoch": 12.02, + "learning_rate": 7.2442193652811725e-06, + "loss": 0.0062, + "step": 38934 + }, + { + "epoch": 12.02, + "learning_rate": 7.243738615732734e-06, + "loss": 0.0041, + "step": 38935 + }, + { + "epoch": 12.02, + "learning_rate": 7.243257873078205e-06, + "loss": 0.0063, + "step": 38936 + }, + { + "epoch": 12.02, + "learning_rate": 7.242777137318788e-06, + "loss": 0.0045, + "step": 38937 + }, + { + "epoch": 12.02, + "learning_rate": 7.242296408455693e-06, + "loss": 0.0067, + "step": 38938 + }, + { + "epoch": 12.03, + "learning_rate": 7.241815686490117e-06, + "loss": 0.0055, + "step": 38939 + }, + { + "epoch": 12.03, + "learning_rate": 7.241334971423259e-06, + "loss": 0.0052, + "step": 38940 + }, + { + "epoch": 12.03, + "learning_rate": 7.240854263256332e-06, + "loss": 0.0057, + "step": 38941 + }, + { + "epoch": 12.03, + "learning_rate": 7.2403735619905266e-06, + "loss": 0.0063, + "step": 38942 + }, + { + "epoch": 12.03, + "learning_rate": 7.23989286762705e-06, + "loss": 0.0069, + "step": 38943 + }, + { + "epoch": 12.03, + "learning_rate": 7.239412180167111e-06, + "loss": 0.0046, + "step": 38944 + }, + { + "epoch": 12.03, + "learning_rate": 7.238931499611899e-06, + "loss": 0.0052, + "step": 38945 + }, + { + "epoch": 12.03, + "learning_rate": 7.238450825962624e-06, + "loss": 0.0051, + "step": 38946 + }, + { + "epoch": 12.03, + "learning_rate": 7.237970159220491e-06, + "loss": 0.0056, + "step": 38947 + }, + { + "epoch": 12.03, + "learning_rate": 7.237489499386694e-06, + "loss": 0.0063, + "step": 38948 + }, + { + "epoch": 12.03, + "learning_rate": 7.2370088464624415e-06, + "loss": 0.0049, + "step": 38949 + }, + { + "epoch": 12.03, + "learning_rate": 7.236528200448936e-06, + "loss": 0.006, + "step": 38950 + }, + { + "epoch": 12.03, + "learning_rate": 7.236047561347372e-06, + "loss": 0.0053, + "step": 38951 + }, + { + "epoch": 12.03, + "learning_rate": 7.235566929158959e-06, + "loss": 0.006, + "step": 38952 + }, + { + "epoch": 12.03, + "learning_rate": 7.235086303884902e-06, + "loss": 0.0056, + "step": 38953 + }, + { + "epoch": 12.03, + "learning_rate": 7.234605685526395e-06, + "loss": 0.0064, + "step": 38954 + }, + { + "epoch": 12.03, + "learning_rate": 7.2341250740846415e-06, + "loss": 0.0063, + "step": 38955 + }, + { + "epoch": 12.03, + "learning_rate": 7.23364446956085e-06, + "loss": 0.0067, + "step": 38956 + }, + { + "epoch": 12.03, + "learning_rate": 7.233163871956215e-06, + "loss": 0.0046, + "step": 38957 + }, + { + "epoch": 12.03, + "learning_rate": 7.232683281271941e-06, + "loss": 0.0078, + "step": 38958 + }, + { + "epoch": 12.03, + "learning_rate": 7.2322026975092344e-06, + "loss": 0.0052, + "step": 38959 + }, + { + "epoch": 12.03, + "learning_rate": 7.231722120669291e-06, + "loss": 0.0061, + "step": 38960 + }, + { + "epoch": 12.03, + "learning_rate": 7.231241550753314e-06, + "loss": 0.0054, + "step": 38961 + }, + { + "epoch": 12.03, + "learning_rate": 7.230760987762512e-06, + "loss": 0.0053, + "step": 38962 + }, + { + "epoch": 12.03, + "learning_rate": 7.230280431698079e-06, + "loss": 0.0047, + "step": 38963 + }, + { + "epoch": 12.03, + "learning_rate": 7.2297998825612195e-06, + "loss": 0.0069, + "step": 38964 + }, + { + "epoch": 12.03, + "learning_rate": 7.229319340353134e-06, + "loss": 0.0057, + "step": 38965 + }, + { + "epoch": 12.03, + "learning_rate": 7.228838805075031e-06, + "loss": 0.0051, + "step": 38966 + }, + { + "epoch": 12.03, + "learning_rate": 7.228358276728104e-06, + "loss": 0.0057, + "step": 38967 + }, + { + "epoch": 12.03, + "learning_rate": 7.227877755313557e-06, + "loss": 0.0054, + "step": 38968 + }, + { + "epoch": 12.03, + "learning_rate": 7.2273972408325984e-06, + "loss": 0.006, + "step": 38969 + }, + { + "epoch": 12.03, + "learning_rate": 7.226916733286422e-06, + "loss": 0.0056, + "step": 38970 + }, + { + "epoch": 12.03, + "learning_rate": 7.2264362326762306e-06, + "loss": 0.0048, + "step": 38971 + }, + { + "epoch": 12.04, + "learning_rate": 7.225955739003232e-06, + "loss": 0.0086, + "step": 38972 + }, + { + "epoch": 12.04, + "learning_rate": 7.225475252268623e-06, + "loss": 0.0065, + "step": 38973 + }, + { + "epoch": 12.04, + "learning_rate": 7.224994772473606e-06, + "loss": 0.0064, + "step": 38974 + }, + { + "epoch": 12.04, + "learning_rate": 7.224514299619385e-06, + "loss": 0.0051, + "step": 38975 + }, + { + "epoch": 12.04, + "learning_rate": 7.224033833707156e-06, + "loss": 0.0057, + "step": 38976 + }, + { + "epoch": 12.04, + "learning_rate": 7.223553374738126e-06, + "loss": 0.0067, + "step": 38977 + }, + { + "epoch": 12.04, + "learning_rate": 7.2230729227134975e-06, + "loss": 0.006, + "step": 38978 + }, + { + "epoch": 12.04, + "learning_rate": 7.222592477634467e-06, + "loss": 0.0055, + "step": 38979 + }, + { + "epoch": 12.04, + "learning_rate": 7.2221120395022406e-06, + "loss": 0.0052, + "step": 38980 + }, + { + "epoch": 12.04, + "learning_rate": 7.22163160831802e-06, + "loss": 0.0049, + "step": 38981 + }, + { + "epoch": 12.04, + "learning_rate": 7.221151184083004e-06, + "loss": 0.0074, + "step": 38982 + }, + { + "epoch": 12.04, + "learning_rate": 7.220670766798396e-06, + "loss": 0.0058, + "step": 38983 + }, + { + "epoch": 12.04, + "learning_rate": 7.2201903564654e-06, + "loss": 0.006, + "step": 38984 + }, + { + "epoch": 12.04, + "learning_rate": 7.219709953085212e-06, + "loss": 0.0055, + "step": 38985 + }, + { + "epoch": 12.04, + "learning_rate": 7.219229556659034e-06, + "loss": 0.0061, + "step": 38986 + }, + { + "epoch": 12.04, + "learning_rate": 7.2187491671880745e-06, + "loss": 0.0057, + "step": 38987 + }, + { + "epoch": 12.04, + "learning_rate": 7.21826878467353e-06, + "loss": 0.008, + "step": 38988 + }, + { + "epoch": 12.04, + "learning_rate": 7.2177884091165995e-06, + "loss": 0.0055, + "step": 38989 + }, + { + "epoch": 12.04, + "learning_rate": 7.217308040518492e-06, + "loss": 0.0061, + "step": 38990 + }, + { + "epoch": 12.04, + "learning_rate": 7.2168276788804026e-06, + "loss": 0.0059, + "step": 38991 + }, + { + "epoch": 12.04, + "learning_rate": 7.216347324203532e-06, + "loss": 0.0058, + "step": 38992 + }, + { + "epoch": 12.04, + "learning_rate": 7.215866976489092e-06, + "loss": 0.0049, + "step": 38993 + }, + { + "epoch": 12.04, + "learning_rate": 7.215386635738268e-06, + "loss": 0.0045, + "step": 38994 + }, + { + "epoch": 12.04, + "learning_rate": 7.2149063019522734e-06, + "loss": 0.0072, + "step": 38995 + }, + { + "epoch": 12.04, + "learning_rate": 7.214425975132305e-06, + "loss": 0.0062, + "step": 38996 + }, + { + "epoch": 12.04, + "learning_rate": 7.213945655279568e-06, + "loss": 0.0057, + "step": 38997 + }, + { + "epoch": 12.04, + "learning_rate": 7.213465342395261e-06, + "loss": 0.0076, + "step": 38998 + }, + { + "epoch": 12.04, + "learning_rate": 7.212985036480581e-06, + "loss": 0.005, + "step": 38999 + }, + { + "epoch": 12.04, + "learning_rate": 7.212504737536738e-06, + "loss": 0.0052, + "step": 39000 + }, + { + "epoch": 12.04, + "learning_rate": 7.212024445564928e-06, + "loss": 0.0067, + "step": 39001 + }, + { + "epoch": 12.04, + "learning_rate": 7.21154416056635e-06, + "loss": 0.0066, + "step": 39002 + }, + { + "epoch": 12.04, + "learning_rate": 7.2110638825422175e-06, + "loss": 0.0057, + "step": 39003 + }, + { + "epoch": 12.05, + "learning_rate": 7.210583611493714e-06, + "loss": 0.0064, + "step": 39004 + }, + { + "epoch": 12.05, + "learning_rate": 7.210103347422053e-06, + "loss": 0.0047, + "step": 39005 + }, + { + "epoch": 12.05, + "learning_rate": 7.2096230903284346e-06, + "loss": 0.0055, + "step": 39006 + }, + { + "epoch": 12.05, + "learning_rate": 7.209142840214054e-06, + "loss": 0.0042, + "step": 39007 + }, + { + "epoch": 12.05, + "learning_rate": 7.2086625970801165e-06, + "loss": 0.0061, + "step": 39008 + }, + { + "epoch": 12.05, + "learning_rate": 7.208182360927827e-06, + "loss": 0.0058, + "step": 39009 + }, + { + "epoch": 12.05, + "learning_rate": 7.207702131758376e-06, + "loss": 0.0048, + "step": 39010 + }, + { + "epoch": 12.05, + "learning_rate": 7.207221909572975e-06, + "loss": 0.0069, + "step": 39011 + }, + { + "epoch": 12.05, + "learning_rate": 7.206741694372824e-06, + "loss": 0.0054, + "step": 39012 + }, + { + "epoch": 12.05, + "learning_rate": 7.206261486159119e-06, + "loss": 0.0084, + "step": 39013 + }, + { + "epoch": 12.05, + "learning_rate": 7.20578128493306e-06, + "loss": 0.0079, + "step": 39014 + }, + { + "epoch": 12.05, + "learning_rate": 7.205301090695858e-06, + "loss": 0.0061, + "step": 39015 + }, + { + "epoch": 12.05, + "learning_rate": 7.204820903448704e-06, + "loss": 0.0054, + "step": 39016 + }, + { + "epoch": 12.05, + "learning_rate": 7.204340723192802e-06, + "loss": 0.0055, + "step": 39017 + }, + { + "epoch": 12.05, + "learning_rate": 7.203860549929357e-06, + "loss": 0.0049, + "step": 39018 + }, + { + "epoch": 12.05, + "learning_rate": 7.203380383659564e-06, + "loss": 0.0064, + "step": 39019 + }, + { + "epoch": 12.05, + "learning_rate": 7.202900224384626e-06, + "loss": 0.0063, + "step": 39020 + }, + { + "epoch": 12.05, + "learning_rate": 7.202420072105748e-06, + "loss": 0.0049, + "step": 39021 + }, + { + "epoch": 12.05, + "learning_rate": 7.2019399268241264e-06, + "loss": 0.0062, + "step": 39022 + }, + { + "epoch": 12.05, + "learning_rate": 7.201459788540963e-06, + "loss": 0.006, + "step": 39023 + }, + { + "epoch": 12.05, + "learning_rate": 7.200979657257461e-06, + "loss": 0.0053, + "step": 39024 + }, + { + "epoch": 12.05, + "learning_rate": 7.200499532974814e-06, + "loss": 0.0053, + "step": 39025 + }, + { + "epoch": 12.05, + "learning_rate": 7.200019415694233e-06, + "loss": 0.0057, + "step": 39026 + }, + { + "epoch": 12.05, + "learning_rate": 7.199539305416914e-06, + "loss": 0.0059, + "step": 39027 + }, + { + "epoch": 12.05, + "learning_rate": 7.199059202144054e-06, + "loss": 0.0059, + "step": 39028 + }, + { + "epoch": 12.05, + "learning_rate": 7.198579105876862e-06, + "loss": 0.0051, + "step": 39029 + }, + { + "epoch": 12.05, + "learning_rate": 7.198099016616531e-06, + "loss": 0.0064, + "step": 39030 + }, + { + "epoch": 12.05, + "learning_rate": 7.197618934364269e-06, + "loss": 0.0051, + "step": 39031 + }, + { + "epoch": 12.05, + "learning_rate": 7.197138859121271e-06, + "loss": 0.0054, + "step": 39032 + }, + { + "epoch": 12.05, + "learning_rate": 7.19665879088874e-06, + "loss": 0.0059, + "step": 39033 + }, + { + "epoch": 12.05, + "learning_rate": 7.19617872966788e-06, + "loss": 0.0059, + "step": 39034 + }, + { + "epoch": 12.05, + "learning_rate": 7.195698675459884e-06, + "loss": 0.005, + "step": 39035 + }, + { + "epoch": 12.06, + "learning_rate": 7.1952186282659586e-06, + "loss": 0.0072, + "step": 39036 + }, + { + "epoch": 12.06, + "learning_rate": 7.194738588087304e-06, + "loss": 0.0064, + "step": 39037 + }, + { + "epoch": 12.06, + "learning_rate": 7.194258554925118e-06, + "loss": 0.0065, + "step": 39038 + }, + { + "epoch": 12.06, + "learning_rate": 7.193778528780604e-06, + "loss": 0.0057, + "step": 39039 + }, + { + "epoch": 12.06, + "learning_rate": 7.193298509654965e-06, + "loss": 0.0062, + "step": 39040 + }, + { + "epoch": 12.06, + "learning_rate": 7.192818497549392e-06, + "loss": 0.0049, + "step": 39041 + }, + { + "epoch": 12.06, + "learning_rate": 7.192338492465094e-06, + "loss": 0.0054, + "step": 39042 + }, + { + "epoch": 12.06, + "learning_rate": 7.191858494403273e-06, + "loss": 0.0058, + "step": 39043 + }, + { + "epoch": 12.06, + "learning_rate": 7.191378503365124e-06, + "loss": 0.0047, + "step": 39044 + }, + { + "epoch": 12.06, + "learning_rate": 7.190898519351848e-06, + "loss": 0.0054, + "step": 39045 + }, + { + "epoch": 12.06, + "learning_rate": 7.19041854236465e-06, + "loss": 0.006, + "step": 39046 + }, + { + "epoch": 12.06, + "learning_rate": 7.189938572404725e-06, + "loss": 0.006, + "step": 39047 + }, + { + "epoch": 12.06, + "learning_rate": 7.189458609473275e-06, + "loss": 0.0061, + "step": 39048 + }, + { + "epoch": 12.06, + "learning_rate": 7.188978653571506e-06, + "loss": 0.0052, + "step": 39049 + }, + { + "epoch": 12.06, + "learning_rate": 7.1884987047006125e-06, + "loss": 0.0053, + "step": 39050 + }, + { + "epoch": 12.06, + "learning_rate": 7.188018762861794e-06, + "loss": 0.0058, + "step": 39051 + }, + { + "epoch": 12.06, + "learning_rate": 7.18753882805626e-06, + "loss": 0.0056, + "step": 39052 + }, + { + "epoch": 12.06, + "learning_rate": 7.1870589002851974e-06, + "loss": 0.0057, + "step": 39053 + }, + { + "epoch": 12.06, + "learning_rate": 7.186578979549815e-06, + "loss": 0.0056, + "step": 39054 + }, + { + "epoch": 12.06, + "learning_rate": 7.1860990658513155e-06, + "loss": 0.0049, + "step": 39055 + }, + { + "epoch": 12.06, + "learning_rate": 7.185619159190891e-06, + "loss": 0.0055, + "step": 39056 + }, + { + "epoch": 12.06, + "learning_rate": 7.185139259569747e-06, + "loss": 0.0061, + "step": 39057 + }, + { + "epoch": 12.06, + "learning_rate": 7.1846593669890865e-06, + "loss": 0.0057, + "step": 39058 + }, + { + "epoch": 12.06, + "learning_rate": 7.184179481450101e-06, + "loss": 0.0066, + "step": 39059 + }, + { + "epoch": 12.06, + "learning_rate": 7.183699602953999e-06, + "loss": 0.0055, + "step": 39060 + }, + { + "epoch": 12.06, + "learning_rate": 7.183219731501976e-06, + "loss": 0.0064, + "step": 39061 + }, + { + "epoch": 12.06, + "learning_rate": 7.182739867095241e-06, + "loss": 0.0055, + "step": 39062 + }, + { + "epoch": 12.06, + "learning_rate": 7.1822600097349806e-06, + "loss": 0.0069, + "step": 39063 + }, + { + "epoch": 12.06, + "learning_rate": 7.181780159422404e-06, + "loss": 0.0058, + "step": 39064 + }, + { + "epoch": 12.06, + "learning_rate": 7.18130031615871e-06, + "loss": 0.0058, + "step": 39065 + }, + { + "epoch": 12.06, + "learning_rate": 7.180820479945095e-06, + "loss": 0.0063, + "step": 39066 + }, + { + "epoch": 12.06, + "learning_rate": 7.180340650782765e-06, + "loss": 0.0055, + "step": 39067 + }, + { + "epoch": 12.06, + "learning_rate": 7.179860828672918e-06, + "loss": 0.0064, + "step": 39068 + }, + { + "epoch": 12.07, + "learning_rate": 7.179381013616751e-06, + "loss": 0.0051, + "step": 39069 + }, + { + "epoch": 12.07, + "learning_rate": 7.178901205615467e-06, + "loss": 0.0068, + "step": 39070 + }, + { + "epoch": 12.07, + "learning_rate": 7.178421404670268e-06, + "loss": 0.0066, + "step": 39071 + }, + { + "epoch": 12.07, + "learning_rate": 7.177941610782349e-06, + "loss": 0.0059, + "step": 39072 + }, + { + "epoch": 12.07, + "learning_rate": 7.1774618239529125e-06, + "loss": 0.0054, + "step": 39073 + }, + { + "epoch": 12.07, + "learning_rate": 7.176982044183161e-06, + "loss": 0.0061, + "step": 39074 + }, + { + "epoch": 12.07, + "learning_rate": 7.176502271474293e-06, + "loss": 0.006, + "step": 39075 + }, + { + "epoch": 12.07, + "learning_rate": 7.176022505827502e-06, + "loss": 0.0082, + "step": 39076 + }, + { + "epoch": 12.07, + "learning_rate": 7.175542747244001e-06, + "loss": 0.0048, + "step": 39077 + }, + { + "epoch": 12.07, + "learning_rate": 7.1750629957249796e-06, + "loss": 0.0056, + "step": 39078 + }, + { + "epoch": 12.07, + "learning_rate": 7.174583251271639e-06, + "loss": 0.0057, + "step": 39079 + }, + { + "epoch": 12.07, + "learning_rate": 7.174103513885184e-06, + "loss": 0.0056, + "step": 39080 + }, + { + "epoch": 12.07, + "learning_rate": 7.17362378356681e-06, + "loss": 0.0061, + "step": 39081 + }, + { + "epoch": 12.07, + "learning_rate": 7.173144060317717e-06, + "loss": 0.0058, + "step": 39082 + }, + { + "epoch": 12.07, + "learning_rate": 7.172664344139112e-06, + "loss": 0.0047, + "step": 39083 + }, + { + "epoch": 12.07, + "learning_rate": 7.172184635032183e-06, + "loss": 0.0058, + "step": 39084 + }, + { + "epoch": 12.07, + "learning_rate": 7.171704932998138e-06, + "loss": 0.0062, + "step": 39085 + }, + { + "epoch": 12.07, + "learning_rate": 7.171225238038178e-06, + "loss": 0.006, + "step": 39086 + }, + { + "epoch": 12.07, + "learning_rate": 7.170745550153494e-06, + "loss": 0.0045, + "step": 39087 + }, + { + "epoch": 12.07, + "learning_rate": 7.170265869345294e-06, + "loss": 0.0059, + "step": 39088 + }, + { + "epoch": 12.07, + "learning_rate": 7.169786195614776e-06, + "loss": 0.0052, + "step": 39089 + }, + { + "epoch": 12.07, + "learning_rate": 7.169306528963137e-06, + "loss": 0.0053, + "step": 39090 + }, + { + "epoch": 12.07, + "learning_rate": 7.16882686939158e-06, + "loss": 0.0055, + "step": 39091 + }, + { + "epoch": 12.07, + "learning_rate": 7.168347216901305e-06, + "loss": 0.0065, + "step": 39092 + }, + { + "epoch": 12.07, + "learning_rate": 7.1678675714935075e-06, + "loss": 0.0057, + "step": 39093 + }, + { + "epoch": 12.07, + "learning_rate": 7.167387933169388e-06, + "loss": 0.0054, + "step": 39094 + }, + { + "epoch": 12.07, + "learning_rate": 7.166908301930151e-06, + "loss": 0.0069, + "step": 39095 + }, + { + "epoch": 12.07, + "learning_rate": 7.1664286777769955e-06, + "loss": 0.0052, + "step": 39096 + }, + { + "epoch": 12.07, + "learning_rate": 7.165949060711113e-06, + "loss": 0.0064, + "step": 39097 + }, + { + "epoch": 12.07, + "learning_rate": 7.165469450733711e-06, + "loss": 0.0054, + "step": 39098 + }, + { + "epoch": 12.07, + "learning_rate": 7.164989847845989e-06, + "loss": 0.0044, + "step": 39099 + }, + { + "epoch": 12.07, + "learning_rate": 7.1645102520491416e-06, + "loss": 0.0053, + "step": 39100 + }, + { + "epoch": 12.08, + "learning_rate": 7.1640306633443726e-06, + "loss": 0.0065, + "step": 39101 + }, + { + "epoch": 12.08, + "learning_rate": 7.163551081732881e-06, + "loss": 0.0057, + "step": 39102 + }, + { + "epoch": 12.08, + "learning_rate": 7.163071507215864e-06, + "loss": 0.0058, + "step": 39103 + }, + { + "epoch": 12.08, + "learning_rate": 7.162591939794521e-06, + "loss": 0.006, + "step": 39104 + }, + { + "epoch": 12.08, + "learning_rate": 7.162112379470057e-06, + "loss": 0.0074, + "step": 39105 + }, + { + "epoch": 12.08, + "learning_rate": 7.161632826243666e-06, + "loss": 0.0057, + "step": 39106 + }, + { + "epoch": 12.08, + "learning_rate": 7.161153280116546e-06, + "loss": 0.0051, + "step": 39107 + }, + { + "epoch": 12.08, + "learning_rate": 7.160673741089905e-06, + "loss": 0.006, + "step": 39108 + }, + { + "epoch": 12.08, + "learning_rate": 7.1601942091649335e-06, + "loss": 0.0058, + "step": 39109 + }, + { + "epoch": 12.08, + "learning_rate": 7.159714684342832e-06, + "loss": 0.0061, + "step": 39110 + }, + { + "epoch": 12.08, + "learning_rate": 7.159235166624807e-06, + "loss": 0.0059, + "step": 39111 + }, + { + "epoch": 12.08, + "learning_rate": 7.158755656012051e-06, + "loss": 0.0062, + "step": 39112 + }, + { + "epoch": 12.08, + "learning_rate": 7.1582761525057655e-06, + "loss": 0.0057, + "step": 39113 + }, + { + "epoch": 12.08, + "learning_rate": 7.15779665610715e-06, + "loss": 0.0072, + "step": 39114 + }, + { + "epoch": 12.08, + "learning_rate": 7.157317166817401e-06, + "loss": 0.0059, + "step": 39115 + }, + { + "epoch": 12.08, + "learning_rate": 7.156837684637721e-06, + "loss": 0.0066, + "step": 39116 + }, + { + "epoch": 12.08, + "learning_rate": 7.156358209569312e-06, + "loss": 0.0048, + "step": 39117 + }, + { + "epoch": 12.08, + "learning_rate": 7.155878741613365e-06, + "loss": 0.0051, + "step": 39118 + }, + { + "epoch": 12.08, + "learning_rate": 7.155399280771086e-06, + "loss": 0.0052, + "step": 39119 + }, + { + "epoch": 12.08, + "learning_rate": 7.154919827043674e-06, + "loss": 0.0069, + "step": 39120 + }, + { + "epoch": 12.08, + "learning_rate": 7.154440380432324e-06, + "loss": 0.006, + "step": 39121 + }, + { + "epoch": 12.08, + "learning_rate": 7.153960940938237e-06, + "loss": 0.0052, + "step": 39122 + }, + { + "epoch": 12.08, + "learning_rate": 7.153481508562617e-06, + "loss": 0.006, + "step": 39123 + }, + { + "epoch": 12.08, + "learning_rate": 7.153002083306655e-06, + "loss": 0.0046, + "step": 39124 + }, + { + "epoch": 12.08, + "learning_rate": 7.152522665171553e-06, + "loss": 0.0065, + "step": 39125 + }, + { + "epoch": 12.08, + "learning_rate": 7.152043254158516e-06, + "loss": 0.0066, + "step": 39126 + }, + { + "epoch": 12.08, + "learning_rate": 7.151563850268735e-06, + "loss": 0.0068, + "step": 39127 + }, + { + "epoch": 12.08, + "learning_rate": 7.151084453503411e-06, + "loss": 0.0048, + "step": 39128 + }, + { + "epoch": 12.08, + "learning_rate": 7.150605063863746e-06, + "loss": 0.0068, + "step": 39129 + }, + { + "epoch": 12.08, + "learning_rate": 7.150125681350939e-06, + "loss": 0.0065, + "step": 39130 + }, + { + "epoch": 12.08, + "learning_rate": 7.149646305966185e-06, + "loss": 0.006, + "step": 39131 + }, + { + "epoch": 12.08, + "learning_rate": 7.149166937710685e-06, + "loss": 0.0064, + "step": 39132 + }, + { + "epoch": 12.09, + "learning_rate": 7.148687576585643e-06, + "loss": 0.0068, + "step": 39133 + }, + { + "epoch": 12.09, + "learning_rate": 7.14820822259225e-06, + "loss": 0.0067, + "step": 39134 + }, + { + "epoch": 12.09, + "learning_rate": 7.147728875731708e-06, + "loss": 0.0067, + "step": 39135 + }, + { + "epoch": 12.09, + "learning_rate": 7.147249536005219e-06, + "loss": 0.0057, + "step": 39136 + }, + { + "epoch": 12.09, + "learning_rate": 7.1467702034139775e-06, + "loss": 0.0068, + "step": 39137 + }, + { + "epoch": 12.09, + "learning_rate": 7.146290877959181e-06, + "loss": 0.0056, + "step": 39138 + }, + { + "epoch": 12.09, + "learning_rate": 7.145811559642038e-06, + "loss": 0.0053, + "step": 39139 + }, + { + "epoch": 12.09, + "learning_rate": 7.145332248463736e-06, + "loss": 0.0063, + "step": 39140 + }, + { + "epoch": 12.09, + "learning_rate": 7.144852944425478e-06, + "loss": 0.0067, + "step": 39141 + }, + { + "epoch": 12.09, + "learning_rate": 7.144373647528469e-06, + "loss": 0.0061, + "step": 39142 + }, + { + "epoch": 12.09, + "learning_rate": 7.143894357773898e-06, + "loss": 0.0044, + "step": 39143 + }, + { + "epoch": 12.09, + "learning_rate": 7.143415075162968e-06, + "loss": 0.007, + "step": 39144 + }, + { + "epoch": 12.09, + "learning_rate": 7.142935799696882e-06, + "loss": 0.0064, + "step": 39145 + }, + { + "epoch": 12.09, + "learning_rate": 7.142456531376829e-06, + "loss": 0.0078, + "step": 39146 + }, + { + "epoch": 12.09, + "learning_rate": 7.141977270204016e-06, + "loss": 0.0055, + "step": 39147 + }, + { + "epoch": 12.09, + "learning_rate": 7.141498016179641e-06, + "loss": 0.0052, + "step": 39148 + }, + { + "epoch": 12.09, + "learning_rate": 7.141018769304897e-06, + "loss": 0.008, + "step": 39149 + }, + { + "epoch": 12.09, + "learning_rate": 7.140539529580988e-06, + "loss": 0.0065, + "step": 39150 + }, + { + "epoch": 12.09, + "learning_rate": 7.140060297009114e-06, + "loss": 0.0054, + "step": 39151 + }, + { + "epoch": 12.09, + "learning_rate": 7.139581071590468e-06, + "loss": 0.0061, + "step": 39152 + }, + { + "epoch": 12.09, + "learning_rate": 7.139101853326249e-06, + "loss": 0.0046, + "step": 39153 + }, + { + "epoch": 12.09, + "learning_rate": 7.138622642217663e-06, + "loss": 0.0052, + "step": 39154 + }, + { + "epoch": 12.09, + "learning_rate": 7.138143438265902e-06, + "loss": 0.0074, + "step": 39155 + }, + { + "epoch": 12.09, + "learning_rate": 7.137664241472165e-06, + "loss": 0.0056, + "step": 39156 + }, + { + "epoch": 12.09, + "learning_rate": 7.137185051837654e-06, + "loss": 0.0059, + "step": 39157 + }, + { + "epoch": 12.09, + "learning_rate": 7.1367058693635624e-06, + "loss": 0.0063, + "step": 39158 + }, + { + "epoch": 12.09, + "learning_rate": 7.136226694051091e-06, + "loss": 0.0063, + "step": 39159 + }, + { + "epoch": 12.09, + "learning_rate": 7.135747525901442e-06, + "loss": 0.0059, + "step": 39160 + }, + { + "epoch": 12.09, + "learning_rate": 7.135268364915813e-06, + "loss": 0.0055, + "step": 39161 + }, + { + "epoch": 12.09, + "learning_rate": 7.134789211095397e-06, + "loss": 0.0048, + "step": 39162 + }, + { + "epoch": 12.09, + "learning_rate": 7.134310064441393e-06, + "loss": 0.0063, + "step": 39163 + }, + { + "epoch": 12.09, + "learning_rate": 7.133830924955008e-06, + "loss": 0.0056, + "step": 39164 + }, + { + "epoch": 12.09, + "learning_rate": 7.133351792637432e-06, + "loss": 0.008, + "step": 39165 + }, + { + "epoch": 12.1, + "learning_rate": 7.132872667489863e-06, + "loss": 0.0059, + "step": 39166 + }, + { + "epoch": 12.1, + "learning_rate": 7.132393549513508e-06, + "loss": 0.0056, + "step": 39167 + }, + { + "epoch": 12.1, + "learning_rate": 7.131914438709557e-06, + "loss": 0.0068, + "step": 39168 + }, + { + "epoch": 12.1, + "learning_rate": 7.1314353350792086e-06, + "loss": 0.006, + "step": 39169 + }, + { + "epoch": 12.1, + "learning_rate": 7.130956238623668e-06, + "loss": 0.0058, + "step": 39170 + }, + { + "epoch": 12.1, + "learning_rate": 7.130477149344128e-06, + "loss": 0.0075, + "step": 39171 + }, + { + "epoch": 12.1, + "learning_rate": 7.129998067241787e-06, + "loss": 0.0058, + "step": 39172 + }, + { + "epoch": 12.1, + "learning_rate": 7.129518992317846e-06, + "loss": 0.0062, + "step": 39173 + }, + { + "epoch": 12.1, + "learning_rate": 7.1290399245734975e-06, + "loss": 0.007, + "step": 39174 + }, + { + "epoch": 12.1, + "learning_rate": 7.128560864009948e-06, + "loss": 0.005, + "step": 39175 + }, + { + "epoch": 12.1, + "learning_rate": 7.128081810628391e-06, + "loss": 0.0062, + "step": 39176 + }, + { + "epoch": 12.1, + "learning_rate": 7.127602764430021e-06, + "loss": 0.0052, + "step": 39177 + }, + { + "epoch": 12.1, + "learning_rate": 7.127123725416045e-06, + "loss": 0.0045, + "step": 39178 + }, + { + "epoch": 12.1, + "learning_rate": 7.126644693587657e-06, + "loss": 0.0065, + "step": 39179 + }, + { + "epoch": 12.1, + "learning_rate": 7.12616566894605e-06, + "loss": 0.0049, + "step": 39180 + }, + { + "epoch": 12.1, + "learning_rate": 7.12568665149243e-06, + "loss": 0.007, + "step": 39181 + }, + { + "epoch": 12.1, + "learning_rate": 7.125207641227993e-06, + "loss": 0.0059, + "step": 39182 + }, + { + "epoch": 12.1, + "learning_rate": 7.124728638153935e-06, + "loss": 0.006, + "step": 39183 + }, + { + "epoch": 12.1, + "learning_rate": 7.124249642271453e-06, + "loss": 0.0063, + "step": 39184 + }, + { + "epoch": 12.1, + "learning_rate": 7.1237706535817495e-06, + "loss": 0.0054, + "step": 39185 + }, + { + "epoch": 12.1, + "learning_rate": 7.123291672086019e-06, + "loss": 0.0067, + "step": 39186 + }, + { + "epoch": 12.1, + "learning_rate": 7.122812697785459e-06, + "loss": 0.0045, + "step": 39187 + }, + { + "epoch": 12.1, + "learning_rate": 7.122333730681274e-06, + "loss": 0.0053, + "step": 39188 + }, + { + "epoch": 12.1, + "learning_rate": 7.121854770774654e-06, + "loss": 0.0061, + "step": 39189 + }, + { + "epoch": 12.1, + "learning_rate": 7.121375818066799e-06, + "loss": 0.0049, + "step": 39190 + }, + { + "epoch": 12.1, + "learning_rate": 7.120896872558913e-06, + "loss": 0.0078, + "step": 39191 + }, + { + "epoch": 12.1, + "learning_rate": 7.120417934252184e-06, + "loss": 0.0049, + "step": 39192 + }, + { + "epoch": 12.1, + "learning_rate": 7.119939003147818e-06, + "loss": 0.0066, + "step": 39193 + }, + { + "epoch": 12.1, + "learning_rate": 7.119460079247006e-06, + "loss": 0.005, + "step": 39194 + }, + { + "epoch": 12.1, + "learning_rate": 7.118981162550954e-06, + "loss": 0.0057, + "step": 39195 + }, + { + "epoch": 12.1, + "learning_rate": 7.1185022530608535e-06, + "loss": 0.0044, + "step": 39196 + }, + { + "epoch": 12.1, + "learning_rate": 7.118023350777903e-06, + "loss": 0.0057, + "step": 39197 + }, + { + "epoch": 12.11, + "learning_rate": 7.117544455703306e-06, + "loss": 0.0064, + "step": 39198 + }, + { + "epoch": 12.11, + "learning_rate": 7.117065567838253e-06, + "loss": 0.0067, + "step": 39199 + }, + { + "epoch": 12.11, + "learning_rate": 7.116586687183944e-06, + "loss": 0.0067, + "step": 39200 + }, + { + "epoch": 12.11, + "learning_rate": 7.116107813741583e-06, + "loss": 0.0097, + "step": 39201 + }, + { + "epoch": 12.11, + "learning_rate": 7.115628947512356e-06, + "loss": 0.0058, + "step": 39202 + }, + { + "epoch": 12.11, + "learning_rate": 7.115150088497469e-06, + "loss": 0.0076, + "step": 39203 + }, + { + "epoch": 12.11, + "learning_rate": 7.11467123669812e-06, + "loss": 0.0058, + "step": 39204 + }, + { + "epoch": 12.11, + "learning_rate": 7.114192392115502e-06, + "loss": 0.0048, + "step": 39205 + }, + { + "epoch": 12.11, + "learning_rate": 7.113713554750815e-06, + "loss": 0.0059, + "step": 39206 + }, + { + "epoch": 12.11, + "learning_rate": 7.11323472460526e-06, + "loss": 0.0061, + "step": 39207 + }, + { + "epoch": 12.11, + "learning_rate": 7.112755901680026e-06, + "loss": 0.0068, + "step": 39208 + }, + { + "epoch": 12.11, + "learning_rate": 7.11227708597632e-06, + "loss": 0.0061, + "step": 39209 + }, + { + "epoch": 12.11, + "learning_rate": 7.111798277495338e-06, + "loss": 0.0058, + "step": 39210 + }, + { + "epoch": 12.11, + "learning_rate": 7.111319476238272e-06, + "loss": 0.006, + "step": 39211 + }, + { + "epoch": 12.11, + "learning_rate": 7.11084068220632e-06, + "loss": 0.0058, + "step": 39212 + }, + { + "epoch": 12.11, + "learning_rate": 7.110361895400688e-06, + "loss": 0.0057, + "step": 39213 + }, + { + "epoch": 12.11, + "learning_rate": 7.109883115822566e-06, + "loss": 0.0068, + "step": 39214 + }, + { + "epoch": 12.11, + "learning_rate": 7.1094043434731495e-06, + "loss": 0.0056, + "step": 39215 + }, + { + "epoch": 12.11, + "learning_rate": 7.108925578353647e-06, + "loss": 0.0058, + "step": 39216 + }, + { + "epoch": 12.11, + "learning_rate": 7.108446820465244e-06, + "loss": 0.0064, + "step": 39217 + }, + { + "epoch": 12.11, + "learning_rate": 7.107968069809142e-06, + "loss": 0.0066, + "step": 39218 + }, + { + "epoch": 12.11, + "learning_rate": 7.107489326386544e-06, + "loss": 0.0063, + "step": 39219 + }, + { + "epoch": 12.11, + "learning_rate": 7.10701059019864e-06, + "loss": 0.007, + "step": 39220 + }, + { + "epoch": 12.11, + "learning_rate": 7.1065318612466305e-06, + "loss": 0.0053, + "step": 39221 + }, + { + "epoch": 12.11, + "learning_rate": 7.106053139531715e-06, + "loss": 0.006, + "step": 39222 + }, + { + "epoch": 12.11, + "learning_rate": 7.105574425055084e-06, + "loss": 0.0049, + "step": 39223 + }, + { + "epoch": 12.11, + "learning_rate": 7.10509571781794e-06, + "loss": 0.0053, + "step": 39224 + }, + { + "epoch": 12.11, + "learning_rate": 7.104617017821479e-06, + "loss": 0.006, + "step": 39225 + }, + { + "epoch": 12.11, + "learning_rate": 7.104138325066902e-06, + "loss": 0.0063, + "step": 39226 + }, + { + "epoch": 12.11, + "learning_rate": 7.103659639555402e-06, + "loss": 0.0055, + "step": 39227 + }, + { + "epoch": 12.11, + "learning_rate": 7.103180961288177e-06, + "loss": 0.0052, + "step": 39228 + }, + { + "epoch": 12.11, + "learning_rate": 7.102702290266425e-06, + "loss": 0.0056, + "step": 39229 + }, + { + "epoch": 12.11, + "learning_rate": 7.102223626491345e-06, + "loss": 0.0055, + "step": 39230 + }, + { + "epoch": 12.12, + "learning_rate": 7.10174496996413e-06, + "loss": 0.0073, + "step": 39231 + }, + { + "epoch": 12.12, + "learning_rate": 7.101266320685982e-06, + "loss": 0.0056, + "step": 39232 + }, + { + "epoch": 12.12, + "learning_rate": 7.100787678658091e-06, + "loss": 0.0067, + "step": 39233 + }, + { + "epoch": 12.12, + "learning_rate": 7.100309043881662e-06, + "loss": 0.007, + "step": 39234 + }, + { + "epoch": 12.12, + "learning_rate": 7.099830416357889e-06, + "loss": 0.0044, + "step": 39235 + }, + { + "epoch": 12.12, + "learning_rate": 7.099351796087966e-06, + "loss": 0.0062, + "step": 39236 + }, + { + "epoch": 12.12, + "learning_rate": 7.098873183073096e-06, + "loss": 0.007, + "step": 39237 + }, + { + "epoch": 12.12, + "learning_rate": 7.098394577314476e-06, + "loss": 0.0057, + "step": 39238 + }, + { + "epoch": 12.12, + "learning_rate": 7.097915978813294e-06, + "loss": 0.0053, + "step": 39239 + }, + { + "epoch": 12.12, + "learning_rate": 7.097437387570757e-06, + "loss": 0.0049, + "step": 39240 + }, + { + "epoch": 12.12, + "learning_rate": 7.09695880358806e-06, + "loss": 0.0058, + "step": 39241 + }, + { + "epoch": 12.12, + "learning_rate": 7.096480226866397e-06, + "loss": 0.0049, + "step": 39242 + }, + { + "epoch": 12.12, + "learning_rate": 7.096001657406964e-06, + "loss": 0.0054, + "step": 39243 + }, + { + "epoch": 12.12, + "learning_rate": 7.095523095210964e-06, + "loss": 0.0051, + "step": 39244 + }, + { + "epoch": 12.12, + "learning_rate": 7.0950445402795895e-06, + "loss": 0.0066, + "step": 39245 + }, + { + "epoch": 12.12, + "learning_rate": 7.0945659926140355e-06, + "loss": 0.0068, + "step": 39246 + }, + { + "epoch": 12.12, + "learning_rate": 7.094087452215508e-06, + "loss": 0.0053, + "step": 39247 + }, + { + "epoch": 12.12, + "learning_rate": 7.093608919085193e-06, + "loss": 0.0048, + "step": 39248 + }, + { + "epoch": 12.12, + "learning_rate": 7.093130393224292e-06, + "loss": 0.0048, + "step": 39249 + }, + { + "epoch": 12.12, + "learning_rate": 7.092651874634007e-06, + "loss": 0.0053, + "step": 39250 + }, + { + "epoch": 12.12, + "learning_rate": 7.0921733633155245e-06, + "loss": 0.0064, + "step": 39251 + }, + { + "epoch": 12.12, + "learning_rate": 7.091694859270049e-06, + "loss": 0.0061, + "step": 39252 + }, + { + "epoch": 12.12, + "learning_rate": 7.091216362498776e-06, + "loss": 0.0059, + "step": 39253 + }, + { + "epoch": 12.12, + "learning_rate": 7.090737873002899e-06, + "loss": 0.005, + "step": 39254 + }, + { + "epoch": 12.12, + "learning_rate": 7.090259390783618e-06, + "loss": 0.0063, + "step": 39255 + }, + { + "epoch": 12.12, + "learning_rate": 7.089780915842132e-06, + "loss": 0.0059, + "step": 39256 + }, + { + "epoch": 12.12, + "learning_rate": 7.089302448179629e-06, + "loss": 0.0077, + "step": 39257 + }, + { + "epoch": 12.12, + "learning_rate": 7.088823987797315e-06, + "loss": 0.0056, + "step": 39258 + }, + { + "epoch": 12.12, + "learning_rate": 7.088345534696381e-06, + "loss": 0.005, + "step": 39259 + }, + { + "epoch": 12.12, + "learning_rate": 7.087867088878031e-06, + "loss": 0.0063, + "step": 39260 + }, + { + "epoch": 12.12, + "learning_rate": 7.087388650343452e-06, + "loss": 0.0065, + "step": 39261 + }, + { + "epoch": 12.12, + "learning_rate": 7.086910219093845e-06, + "loss": 0.0052, + "step": 39262 + }, + { + "epoch": 12.13, + "learning_rate": 7.086431795130411e-06, + "loss": 0.0067, + "step": 39263 + }, + { + "epoch": 12.13, + "learning_rate": 7.085953378454338e-06, + "loss": 0.0053, + "step": 39264 + }, + { + "epoch": 12.13, + "learning_rate": 7.085474969066828e-06, + "loss": 0.0085, + "step": 39265 + }, + { + "epoch": 12.13, + "learning_rate": 7.08499656696908e-06, + "loss": 0.0061, + "step": 39266 + }, + { + "epoch": 12.13, + "learning_rate": 7.084518172162282e-06, + "loss": 0.0061, + "step": 39267 + }, + { + "epoch": 12.13, + "learning_rate": 7.084039784647639e-06, + "loss": 0.0059, + "step": 39268 + }, + { + "epoch": 12.13, + "learning_rate": 7.083561404426346e-06, + "loss": 0.0065, + "step": 39269 + }, + { + "epoch": 12.13, + "learning_rate": 7.083083031499596e-06, + "loss": 0.0055, + "step": 39270 + }, + { + "epoch": 12.13, + "learning_rate": 7.082604665868584e-06, + "loss": 0.0051, + "step": 39271 + }, + { + "epoch": 12.13, + "learning_rate": 7.082126307534516e-06, + "loss": 0.0061, + "step": 39272 + }, + { + "epoch": 12.13, + "learning_rate": 7.081647956498579e-06, + "loss": 0.0075, + "step": 39273 + }, + { + "epoch": 12.13, + "learning_rate": 7.081169612761971e-06, + "loss": 0.0062, + "step": 39274 + }, + { + "epoch": 12.13, + "learning_rate": 7.0806912763258925e-06, + "loss": 0.0063, + "step": 39275 + }, + { + "epoch": 12.13, + "learning_rate": 7.080212947191538e-06, + "loss": 0.0055, + "step": 39276 + }, + { + "epoch": 12.13, + "learning_rate": 7.079734625360101e-06, + "loss": 0.0061, + "step": 39277 + }, + { + "epoch": 12.13, + "learning_rate": 7.079256310832783e-06, + "loss": 0.007, + "step": 39278 + }, + { + "epoch": 12.13, + "learning_rate": 7.0787780036107775e-06, + "loss": 0.0048, + "step": 39279 + }, + { + "epoch": 12.13, + "learning_rate": 7.078299703695279e-06, + "loss": 0.006, + "step": 39280 + }, + { + "epoch": 12.13, + "learning_rate": 7.07782141108749e-06, + "loss": 0.0069, + "step": 39281 + }, + { + "epoch": 12.13, + "learning_rate": 7.0773431257885975e-06, + "loss": 0.0055, + "step": 39282 + }, + { + "epoch": 12.13, + "learning_rate": 7.076864847799805e-06, + "loss": 0.006, + "step": 39283 + }, + { + "epoch": 12.13, + "learning_rate": 7.076386577122309e-06, + "loss": 0.0071, + "step": 39284 + }, + { + "epoch": 12.13, + "learning_rate": 7.0759083137572986e-06, + "loss": 0.005, + "step": 39285 + }, + { + "epoch": 12.13, + "learning_rate": 7.075430057705977e-06, + "loss": 0.0061, + "step": 39286 + }, + { + "epoch": 12.13, + "learning_rate": 7.07495180896954e-06, + "loss": 0.0061, + "step": 39287 + }, + { + "epoch": 12.13, + "learning_rate": 7.074473567549178e-06, + "loss": 0.0084, + "step": 39288 + }, + { + "epoch": 12.13, + "learning_rate": 7.073995333446094e-06, + "loss": 0.0079, + "step": 39289 + }, + { + "epoch": 12.13, + "learning_rate": 7.0735171066614795e-06, + "loss": 0.0048, + "step": 39290 + }, + { + "epoch": 12.13, + "learning_rate": 7.073038887196537e-06, + "loss": 0.006, + "step": 39291 + }, + { + "epoch": 12.13, + "learning_rate": 7.072560675052453e-06, + "loss": 0.0059, + "step": 39292 + }, + { + "epoch": 12.13, + "learning_rate": 7.0720824702304325e-06, + "loss": 0.0054, + "step": 39293 + }, + { + "epoch": 12.13, + "learning_rate": 7.071604272731667e-06, + "loss": 0.0053, + "step": 39294 + }, + { + "epoch": 12.14, + "learning_rate": 7.071126082557351e-06, + "loss": 0.0056, + "step": 39295 + }, + { + "epoch": 12.14, + "learning_rate": 7.070647899708684e-06, + "loss": 0.0055, + "step": 39296 + }, + { + "epoch": 12.14, + "learning_rate": 7.070169724186863e-06, + "loss": 0.0068, + "step": 39297 + }, + { + "epoch": 12.14, + "learning_rate": 7.069691555993078e-06, + "loss": 0.0051, + "step": 39298 + }, + { + "epoch": 12.14, + "learning_rate": 7.069213395128532e-06, + "loss": 0.0067, + "step": 39299 + }, + { + "epoch": 12.14, + "learning_rate": 7.068735241594418e-06, + "loss": 0.0066, + "step": 39300 + }, + { + "epoch": 12.14, + "learning_rate": 7.06825709539193e-06, + "loss": 0.0055, + "step": 39301 + }, + { + "epoch": 12.14, + "learning_rate": 7.067778956522264e-06, + "loss": 0.0065, + "step": 39302 + }, + { + "epoch": 12.14, + "learning_rate": 7.067300824986623e-06, + "loss": 0.0052, + "step": 39303 + }, + { + "epoch": 12.14, + "learning_rate": 7.0668227007861935e-06, + "loss": 0.0052, + "step": 39304 + }, + { + "epoch": 12.14, + "learning_rate": 7.066344583922173e-06, + "loss": 0.0067, + "step": 39305 + }, + { + "epoch": 12.14, + "learning_rate": 7.0658664743957665e-06, + "loss": 0.0049, + "step": 39306 + }, + { + "epoch": 12.14, + "learning_rate": 7.06538837220816e-06, + "loss": 0.0069, + "step": 39307 + }, + { + "epoch": 12.14, + "learning_rate": 7.064910277360548e-06, + "loss": 0.0057, + "step": 39308 + }, + { + "epoch": 12.14, + "learning_rate": 7.06443218985414e-06, + "loss": 0.0054, + "step": 39309 + }, + { + "epoch": 12.14, + "learning_rate": 7.063954109690116e-06, + "loss": 0.005, + "step": 39310 + }, + { + "epoch": 12.14, + "learning_rate": 7.0634760368696785e-06, + "loss": 0.0064, + "step": 39311 + }, + { + "epoch": 12.14, + "learning_rate": 7.0629979713940265e-06, + "loss": 0.0067, + "step": 39312 + }, + { + "epoch": 12.14, + "learning_rate": 7.062519913264347e-06, + "loss": 0.0051, + "step": 39313 + }, + { + "epoch": 12.14, + "learning_rate": 7.062041862481844e-06, + "loss": 0.0061, + "step": 39314 + }, + { + "epoch": 12.14, + "learning_rate": 7.061563819047712e-06, + "loss": 0.0069, + "step": 39315 + }, + { + "epoch": 12.14, + "learning_rate": 7.06108578296314e-06, + "loss": 0.0057, + "step": 39316 + }, + { + "epoch": 12.14, + "learning_rate": 7.060607754229331e-06, + "loss": 0.0065, + "step": 39317 + }, + { + "epoch": 12.14, + "learning_rate": 7.060129732847481e-06, + "loss": 0.007, + "step": 39318 + }, + { + "epoch": 12.14, + "learning_rate": 7.059651718818781e-06, + "loss": 0.0061, + "step": 39319 + }, + { + "epoch": 12.14, + "learning_rate": 7.059173712144425e-06, + "loss": 0.0059, + "step": 39320 + }, + { + "epoch": 12.14, + "learning_rate": 7.058695712825616e-06, + "loss": 0.0061, + "step": 39321 + }, + { + "epoch": 12.14, + "learning_rate": 7.058217720863545e-06, + "loss": 0.0073, + "step": 39322 + }, + { + "epoch": 12.14, + "learning_rate": 7.057739736259403e-06, + "loss": 0.0064, + "step": 39323 + }, + { + "epoch": 12.14, + "learning_rate": 7.057261759014395e-06, + "loss": 0.0061, + "step": 39324 + }, + { + "epoch": 12.14, + "learning_rate": 7.056783789129714e-06, + "loss": 0.0062, + "step": 39325 + }, + { + "epoch": 12.14, + "learning_rate": 7.056305826606549e-06, + "loss": 0.0054, + "step": 39326 + }, + { + "epoch": 12.14, + "learning_rate": 7.055827871446101e-06, + "loss": 0.0062, + "step": 39327 + }, + { + "epoch": 12.15, + "learning_rate": 7.055349923649568e-06, + "loss": 0.0054, + "step": 39328 + }, + { + "epoch": 12.15, + "learning_rate": 7.054871983218138e-06, + "loss": 0.0059, + "step": 39329 + }, + { + "epoch": 12.15, + "learning_rate": 7.054394050153011e-06, + "loss": 0.0058, + "step": 39330 + }, + { + "epoch": 12.15, + "learning_rate": 7.053916124455385e-06, + "loss": 0.0075, + "step": 39331 + }, + { + "epoch": 12.15, + "learning_rate": 7.053438206126451e-06, + "loss": 0.0063, + "step": 39332 + }, + { + "epoch": 12.15, + "learning_rate": 7.052960295167401e-06, + "loss": 0.0065, + "step": 39333 + }, + { + "epoch": 12.15, + "learning_rate": 7.052482391579441e-06, + "loss": 0.0078, + "step": 39334 + }, + { + "epoch": 12.15, + "learning_rate": 7.052004495363755e-06, + "loss": 0.006, + "step": 39335 + }, + { + "epoch": 12.15, + "learning_rate": 7.051526606521544e-06, + "loss": 0.0064, + "step": 39336 + }, + { + "epoch": 12.15, + "learning_rate": 7.051048725054006e-06, + "loss": 0.005, + "step": 39337 + }, + { + "epoch": 12.15, + "learning_rate": 7.050570850962332e-06, + "loss": 0.0056, + "step": 39338 + }, + { + "epoch": 12.15, + "learning_rate": 7.050092984247715e-06, + "loss": 0.0059, + "step": 39339 + }, + { + "epoch": 12.15, + "learning_rate": 7.04961512491136e-06, + "loss": 0.0056, + "step": 39340 + }, + { + "epoch": 12.15, + "learning_rate": 7.049137272954449e-06, + "loss": 0.0072, + "step": 39341 + }, + { + "epoch": 12.15, + "learning_rate": 7.048659428378186e-06, + "loss": 0.0064, + "step": 39342 + }, + { + "epoch": 12.15, + "learning_rate": 7.048181591183767e-06, + "loss": 0.0061, + "step": 39343 + }, + { + "epoch": 12.15, + "learning_rate": 7.04770376137238e-06, + "loss": 0.0051, + "step": 39344 + }, + { + "epoch": 12.15, + "learning_rate": 7.047225938945226e-06, + "loss": 0.0058, + "step": 39345 + }, + { + "epoch": 12.15, + "learning_rate": 7.0467481239035e-06, + "loss": 0.006, + "step": 39346 + }, + { + "epoch": 12.15, + "learning_rate": 7.046270316248393e-06, + "loss": 0.0068, + "step": 39347 + }, + { + "epoch": 12.15, + "learning_rate": 7.0457925159811034e-06, + "loss": 0.0081, + "step": 39348 + }, + { + "epoch": 12.15, + "learning_rate": 7.045314723102828e-06, + "loss": 0.0061, + "step": 39349 + }, + { + "epoch": 12.15, + "learning_rate": 7.044836937614758e-06, + "loss": 0.0059, + "step": 39350 + }, + { + "epoch": 12.15, + "learning_rate": 7.044359159518086e-06, + "loss": 0.0072, + "step": 39351 + }, + { + "epoch": 12.15, + "learning_rate": 7.043881388814017e-06, + "loss": 0.0059, + "step": 39352 + }, + { + "epoch": 12.15, + "learning_rate": 7.0434036255037365e-06, + "loss": 0.0049, + "step": 39353 + }, + { + "epoch": 12.15, + "learning_rate": 7.042925869588442e-06, + "loss": 0.0062, + "step": 39354 + }, + { + "epoch": 12.15, + "learning_rate": 7.042448121069332e-06, + "loss": 0.0065, + "step": 39355 + }, + { + "epoch": 12.15, + "learning_rate": 7.041970379947596e-06, + "loss": 0.0057, + "step": 39356 + }, + { + "epoch": 12.15, + "learning_rate": 7.041492646224431e-06, + "loss": 0.0074, + "step": 39357 + }, + { + "epoch": 12.15, + "learning_rate": 7.0410149199010334e-06, + "loss": 0.0052, + "step": 39358 + }, + { + "epoch": 12.15, + "learning_rate": 7.040537200978601e-06, + "loss": 0.0072, + "step": 39359 + }, + { + "epoch": 12.16, + "learning_rate": 7.040059489458321e-06, + "loss": 0.0077, + "step": 39360 + }, + { + "epoch": 12.16, + "learning_rate": 7.0395817853413905e-06, + "loss": 0.0071, + "step": 39361 + }, + { + "epoch": 12.16, + "learning_rate": 7.03910408862901e-06, + "loss": 0.0067, + "step": 39362 + }, + { + "epoch": 12.16, + "learning_rate": 7.0386263993223684e-06, + "loss": 0.0064, + "step": 39363 + }, + { + "epoch": 12.16, + "learning_rate": 7.03814871742266e-06, + "loss": 0.006, + "step": 39364 + }, + { + "epoch": 12.16, + "learning_rate": 7.037671042931087e-06, + "loss": 0.0054, + "step": 39365 + }, + { + "epoch": 12.16, + "learning_rate": 7.037193375848835e-06, + "loss": 0.0045, + "step": 39366 + }, + { + "epoch": 12.16, + "learning_rate": 7.0367157161771025e-06, + "loss": 0.0073, + "step": 39367 + }, + { + "epoch": 12.16, + "learning_rate": 7.036238063917089e-06, + "loss": 0.0055, + "step": 39368 + }, + { + "epoch": 12.16, + "learning_rate": 7.03576041906998e-06, + "loss": 0.0059, + "step": 39369 + }, + { + "epoch": 12.16, + "learning_rate": 7.035282781636976e-06, + "loss": 0.0053, + "step": 39370 + }, + { + "epoch": 12.16, + "learning_rate": 7.034805151619273e-06, + "loss": 0.0059, + "step": 39371 + }, + { + "epoch": 12.16, + "learning_rate": 7.034327529018059e-06, + "loss": 0.0059, + "step": 39372 + }, + { + "epoch": 12.16, + "learning_rate": 7.033849913834535e-06, + "loss": 0.0056, + "step": 39373 + }, + { + "epoch": 12.16, + "learning_rate": 7.033372306069894e-06, + "loss": 0.007, + "step": 39374 + }, + { + "epoch": 12.16, + "learning_rate": 7.0328947057253285e-06, + "loss": 0.0058, + "step": 39375 + }, + { + "epoch": 12.16, + "learning_rate": 7.032417112802034e-06, + "loss": 0.006, + "step": 39376 + }, + { + "epoch": 12.16, + "learning_rate": 7.0319395273012095e-06, + "loss": 0.006, + "step": 39377 + }, + { + "epoch": 12.16, + "learning_rate": 7.03146194922404e-06, + "loss": 0.0057, + "step": 39378 + }, + { + "epoch": 12.16, + "learning_rate": 7.030984378571728e-06, + "loss": 0.0061, + "step": 39379 + }, + { + "epoch": 12.16, + "learning_rate": 7.030506815345468e-06, + "loss": 0.0068, + "step": 39380 + }, + { + "epoch": 12.16, + "learning_rate": 7.0300292595464506e-06, + "loss": 0.0052, + "step": 39381 + }, + { + "epoch": 12.16, + "learning_rate": 7.029551711175868e-06, + "loss": 0.0061, + "step": 39382 + }, + { + "epoch": 12.16, + "learning_rate": 7.029074170234924e-06, + "loss": 0.0059, + "step": 39383 + }, + { + "epoch": 12.16, + "learning_rate": 7.028596636724805e-06, + "loss": 0.0066, + "step": 39384 + }, + { + "epoch": 12.16, + "learning_rate": 7.028119110646705e-06, + "loss": 0.0076, + "step": 39385 + }, + { + "epoch": 12.16, + "learning_rate": 7.027641592001826e-06, + "loss": 0.0053, + "step": 39386 + }, + { + "epoch": 12.16, + "learning_rate": 7.0271640807913545e-06, + "loss": 0.0065, + "step": 39387 + }, + { + "epoch": 12.16, + "learning_rate": 7.026686577016486e-06, + "loss": 0.0072, + "step": 39388 + }, + { + "epoch": 12.16, + "learning_rate": 7.026209080678419e-06, + "loss": 0.006, + "step": 39389 + }, + { + "epoch": 12.16, + "learning_rate": 7.025731591778349e-06, + "loss": 0.0059, + "step": 39390 + }, + { + "epoch": 12.16, + "learning_rate": 7.025254110317463e-06, + "loss": 0.0065, + "step": 39391 + }, + { + "epoch": 12.17, + "learning_rate": 7.0247766362969575e-06, + "loss": 0.0064, + "step": 39392 + }, + { + "epoch": 12.17, + "learning_rate": 7.024299169718032e-06, + "loss": 0.0062, + "step": 39393 + }, + { + "epoch": 12.17, + "learning_rate": 7.023821710581875e-06, + "loss": 0.0088, + "step": 39394 + }, + { + "epoch": 12.17, + "learning_rate": 7.023344258889681e-06, + "loss": 0.0072, + "step": 39395 + }, + { + "epoch": 12.17, + "learning_rate": 7.022866814642649e-06, + "loss": 0.0053, + "step": 39396 + }, + { + "epoch": 12.17, + "learning_rate": 7.022389377841969e-06, + "loss": 0.0052, + "step": 39397 + }, + { + "epoch": 12.17, + "learning_rate": 7.021911948488834e-06, + "loss": 0.0055, + "step": 39398 + }, + { + "epoch": 12.17, + "learning_rate": 7.021434526584447e-06, + "loss": 0.0056, + "step": 39399 + }, + { + "epoch": 12.17, + "learning_rate": 7.020957112129989e-06, + "loss": 0.0102, + "step": 39400 + }, + { + "epoch": 12.17, + "learning_rate": 7.020479705126662e-06, + "loss": 0.0069, + "step": 39401 + }, + { + "epoch": 12.17, + "learning_rate": 7.020002305575661e-06, + "loss": 0.0056, + "step": 39402 + }, + { + "epoch": 12.17, + "learning_rate": 7.019524913478175e-06, + "loss": 0.0073, + "step": 39403 + }, + { + "epoch": 12.17, + "learning_rate": 7.019047528835402e-06, + "loss": 0.0058, + "step": 39404 + }, + { + "epoch": 12.17, + "learning_rate": 7.018570151648536e-06, + "loss": 0.0059, + "step": 39405 + }, + { + "epoch": 12.17, + "learning_rate": 7.018092781918767e-06, + "loss": 0.0058, + "step": 39406 + }, + { + "epoch": 12.17, + "learning_rate": 7.017615419647294e-06, + "loss": 0.0064, + "step": 39407 + }, + { + "epoch": 12.17, + "learning_rate": 7.017138064835309e-06, + "loss": 0.0056, + "step": 39408 + }, + { + "epoch": 12.17, + "learning_rate": 7.0166607174840054e-06, + "loss": 0.0075, + "step": 39409 + }, + { + "epoch": 12.17, + "learning_rate": 7.016183377594574e-06, + "loss": 0.0062, + "step": 39410 + }, + { + "epoch": 12.17, + "learning_rate": 7.015706045168218e-06, + "loss": 0.0056, + "step": 39411 + }, + { + "epoch": 12.17, + "learning_rate": 7.015228720206123e-06, + "loss": 0.0054, + "step": 39412 + }, + { + "epoch": 12.17, + "learning_rate": 7.014751402709483e-06, + "loss": 0.0073, + "step": 39413 + }, + { + "epoch": 12.17, + "learning_rate": 7.014274092679499e-06, + "loss": 0.0062, + "step": 39414 + }, + { + "epoch": 12.17, + "learning_rate": 7.0137967901173565e-06, + "loss": 0.0064, + "step": 39415 + }, + { + "epoch": 12.17, + "learning_rate": 7.013319495024251e-06, + "loss": 0.0059, + "step": 39416 + }, + { + "epoch": 12.17, + "learning_rate": 7.012842207401382e-06, + "loss": 0.0066, + "step": 39417 + }, + { + "epoch": 12.17, + "learning_rate": 7.0123649272499394e-06, + "loss": 0.0063, + "step": 39418 + }, + { + "epoch": 12.17, + "learning_rate": 7.011887654571117e-06, + "loss": 0.0069, + "step": 39419 + }, + { + "epoch": 12.17, + "learning_rate": 7.011410389366109e-06, + "loss": 0.0066, + "step": 39420 + }, + { + "epoch": 12.17, + "learning_rate": 7.010933131636104e-06, + "loss": 0.0071, + "step": 39421 + }, + { + "epoch": 12.17, + "learning_rate": 7.0104558813823045e-06, + "loss": 0.007, + "step": 39422 + }, + { + "epoch": 12.17, + "learning_rate": 7.009978638605897e-06, + "loss": 0.006, + "step": 39423 + }, + { + "epoch": 12.17, + "learning_rate": 7.0095014033080825e-06, + "loss": 0.0056, + "step": 39424 + }, + { + "epoch": 12.18, + "learning_rate": 7.009024175490049e-06, + "loss": 0.0057, + "step": 39425 + }, + { + "epoch": 12.18, + "learning_rate": 7.008546955152989e-06, + "loss": 0.0081, + "step": 39426 + }, + { + "epoch": 12.18, + "learning_rate": 7.008069742298102e-06, + "loss": 0.0059, + "step": 39427 + }, + { + "epoch": 12.18, + "learning_rate": 7.0075925369265775e-06, + "loss": 0.0066, + "step": 39428 + }, + { + "epoch": 12.18, + "learning_rate": 7.007115339039608e-06, + "loss": 0.0059, + "step": 39429 + }, + { + "epoch": 12.18, + "learning_rate": 7.0066381486383925e-06, + "loss": 0.0054, + "step": 39430 + }, + { + "epoch": 12.18, + "learning_rate": 7.0061609657241154e-06, + "loss": 0.0066, + "step": 39431 + }, + { + "epoch": 12.18, + "learning_rate": 7.00568379029798e-06, + "loss": 0.0075, + "step": 39432 + }, + { + "epoch": 12.18, + "learning_rate": 7.005206622361176e-06, + "loss": 0.0063, + "step": 39433 + }, + { + "epoch": 12.18, + "learning_rate": 7.004729461914894e-06, + "loss": 0.0066, + "step": 39434 + }, + { + "epoch": 12.18, + "learning_rate": 7.004252308960331e-06, + "loss": 0.0057, + "step": 39435 + }, + { + "epoch": 12.18, + "learning_rate": 7.003775163498681e-06, + "loss": 0.0047, + "step": 39436 + }, + { + "epoch": 12.18, + "learning_rate": 7.0032980255311314e-06, + "loss": 0.0047, + "step": 39437 + }, + { + "epoch": 12.18, + "learning_rate": 7.0028208950588825e-06, + "loss": 0.0068, + "step": 39438 + }, + { + "epoch": 12.18, + "learning_rate": 7.002343772083128e-06, + "loss": 0.0051, + "step": 39439 + }, + { + "epoch": 12.18, + "learning_rate": 7.001866656605056e-06, + "loss": 0.0048, + "step": 39440 + }, + { + "epoch": 12.18, + "learning_rate": 7.00138954862586e-06, + "loss": 0.007, + "step": 39441 + }, + { + "epoch": 12.18, + "learning_rate": 7.00091244814674e-06, + "loss": 0.0055, + "step": 39442 + }, + { + "epoch": 12.18, + "learning_rate": 7.000435355168882e-06, + "loss": 0.0065, + "step": 39443 + }, + { + "epoch": 12.18, + "learning_rate": 6.999958269693481e-06, + "loss": 0.0059, + "step": 39444 + }, + { + "epoch": 12.18, + "learning_rate": 6.999481191721735e-06, + "loss": 0.0054, + "step": 39445 + }, + { + "epoch": 12.18, + "learning_rate": 6.9990041212548335e-06, + "loss": 0.0069, + "step": 39446 + }, + { + "epoch": 12.18, + "learning_rate": 6.998527058293967e-06, + "loss": 0.0066, + "step": 39447 + }, + { + "epoch": 12.18, + "learning_rate": 6.998050002840338e-06, + "loss": 0.0068, + "step": 39448 + }, + { + "epoch": 12.18, + "learning_rate": 6.997572954895126e-06, + "loss": 0.0063, + "step": 39449 + }, + { + "epoch": 12.18, + "learning_rate": 6.997095914459535e-06, + "loss": 0.0068, + "step": 39450 + }, + { + "epoch": 12.18, + "learning_rate": 6.996618881534756e-06, + "loss": 0.0072, + "step": 39451 + }, + { + "epoch": 12.18, + "learning_rate": 6.996141856121979e-06, + "loss": 0.0069, + "step": 39452 + }, + { + "epoch": 12.18, + "learning_rate": 6.995664838222398e-06, + "loss": 0.0048, + "step": 39453 + }, + { + "epoch": 12.18, + "learning_rate": 6.995187827837207e-06, + "loss": 0.0054, + "step": 39454 + }, + { + "epoch": 12.18, + "learning_rate": 6.9947108249676034e-06, + "loss": 0.0056, + "step": 39455 + }, + { + "epoch": 12.18, + "learning_rate": 6.994233829614774e-06, + "loss": 0.0069, + "step": 39456 + }, + { + "epoch": 12.19, + "learning_rate": 6.993756841779912e-06, + "loss": 0.0049, + "step": 39457 + }, + { + "epoch": 12.19, + "learning_rate": 6.993279861464218e-06, + "loss": 0.0054, + "step": 39458 + }, + { + "epoch": 12.19, + "learning_rate": 6.992802888668874e-06, + "loss": 0.0058, + "step": 39459 + }, + { + "epoch": 12.19, + "learning_rate": 6.99232592339508e-06, + "loss": 0.0071, + "step": 39460 + }, + { + "epoch": 12.19, + "learning_rate": 6.991848965644031e-06, + "loss": 0.0072, + "step": 39461 + }, + { + "epoch": 12.19, + "learning_rate": 6.99137201541691e-06, + "loss": 0.0069, + "step": 39462 + }, + { + "epoch": 12.19, + "learning_rate": 6.990895072714918e-06, + "loss": 0.0058, + "step": 39463 + }, + { + "epoch": 12.19, + "learning_rate": 6.990418137539251e-06, + "loss": 0.005, + "step": 39464 + }, + { + "epoch": 12.19, + "learning_rate": 6.989941209891091e-06, + "loss": 0.0062, + "step": 39465 + }, + { + "epoch": 12.19, + "learning_rate": 6.98946428977164e-06, + "loss": 0.0054, + "step": 39466 + }, + { + "epoch": 12.19, + "learning_rate": 6.988987377182091e-06, + "loss": 0.0051, + "step": 39467 + }, + { + "epoch": 12.19, + "learning_rate": 6.9885104721236295e-06, + "loss": 0.0058, + "step": 39468 + }, + { + "epoch": 12.19, + "learning_rate": 6.988033574597451e-06, + "loss": 0.006, + "step": 39469 + }, + { + "epoch": 12.19, + "learning_rate": 6.987556684604755e-06, + "loss": 0.0057, + "step": 39470 + }, + { + "epoch": 12.19, + "learning_rate": 6.987079802146727e-06, + "loss": 0.0061, + "step": 39471 + }, + { + "epoch": 12.19, + "learning_rate": 6.98660292722456e-06, + "loss": 0.0063, + "step": 39472 + }, + { + "epoch": 12.19, + "learning_rate": 6.986126059839451e-06, + "loss": 0.0061, + "step": 39473 + }, + { + "epoch": 12.19, + "learning_rate": 6.98564919999259e-06, + "loss": 0.0057, + "step": 39474 + }, + { + "epoch": 12.19, + "learning_rate": 6.985172347685168e-06, + "loss": 0.0058, + "step": 39475 + }, + { + "epoch": 12.19, + "learning_rate": 6.984695502918384e-06, + "loss": 0.0064, + "step": 39476 + }, + { + "epoch": 12.19, + "learning_rate": 6.984218665693423e-06, + "loss": 0.0073, + "step": 39477 + }, + { + "epoch": 12.19, + "learning_rate": 6.983741836011482e-06, + "loss": 0.0061, + "step": 39478 + }, + { + "epoch": 12.19, + "learning_rate": 6.983265013873756e-06, + "loss": 0.0075, + "step": 39479 + }, + { + "epoch": 12.19, + "learning_rate": 6.98278819928143e-06, + "loss": 0.0065, + "step": 39480 + }, + { + "epoch": 12.19, + "learning_rate": 6.982311392235701e-06, + "loss": 0.0061, + "step": 39481 + }, + { + "epoch": 12.19, + "learning_rate": 6.9818345927377665e-06, + "loss": 0.0061, + "step": 39482 + }, + { + "epoch": 12.19, + "learning_rate": 6.981357800788808e-06, + "loss": 0.0053, + "step": 39483 + }, + { + "epoch": 12.19, + "learning_rate": 6.980881016390027e-06, + "loss": 0.0071, + "step": 39484 + }, + { + "epoch": 12.19, + "learning_rate": 6.980404239542615e-06, + "loss": 0.0074, + "step": 39485 + }, + { + "epoch": 12.19, + "learning_rate": 6.979927470247759e-06, + "loss": 0.0067, + "step": 39486 + }, + { + "epoch": 12.19, + "learning_rate": 6.979450708506656e-06, + "loss": 0.005, + "step": 39487 + }, + { + "epoch": 12.19, + "learning_rate": 6.9789739543205e-06, + "loss": 0.0055, + "step": 39488 + }, + { + "epoch": 12.19, + "learning_rate": 6.9784972076904825e-06, + "loss": 0.0075, + "step": 39489 + }, + { + "epoch": 12.2, + "learning_rate": 6.978020468617789e-06, + "loss": 0.0066, + "step": 39490 + }, + { + "epoch": 12.2, + "learning_rate": 6.97754373710362e-06, + "loss": 0.008, + "step": 39491 + }, + { + "epoch": 12.2, + "learning_rate": 6.977067013149168e-06, + "loss": 0.0062, + "step": 39492 + }, + { + "epoch": 12.2, + "learning_rate": 6.976590296755618e-06, + "loss": 0.0064, + "step": 39493 + }, + { + "epoch": 12.2, + "learning_rate": 6.976113587924172e-06, + "loss": 0.0071, + "step": 39494 + }, + { + "epoch": 12.2, + "learning_rate": 6.975636886656017e-06, + "loss": 0.0071, + "step": 39495 + }, + { + "epoch": 12.2, + "learning_rate": 6.975160192952341e-06, + "loss": 0.0065, + "step": 39496 + }, + { + "epoch": 12.2, + "learning_rate": 6.974683506814344e-06, + "loss": 0.0072, + "step": 39497 + }, + { + "epoch": 12.2, + "learning_rate": 6.974206828243218e-06, + "loss": 0.0055, + "step": 39498 + }, + { + "epoch": 12.2, + "learning_rate": 6.97373015724015e-06, + "loss": 0.0064, + "step": 39499 + }, + { + "epoch": 12.2, + "learning_rate": 6.973253493806331e-06, + "loss": 0.0049, + "step": 39500 + }, + { + "epoch": 12.2, + "learning_rate": 6.972776837942964e-06, + "loss": 0.006, + "step": 39501 + }, + { + "epoch": 12.2, + "learning_rate": 6.972300189651231e-06, + "loss": 0.0071, + "step": 39502 + }, + { + "epoch": 12.2, + "learning_rate": 6.971823548932326e-06, + "loss": 0.0067, + "step": 39503 + }, + { + "epoch": 12.2, + "learning_rate": 6.9713469157874456e-06, + "loss": 0.0062, + "step": 39504 + }, + { + "epoch": 12.2, + "learning_rate": 6.970870290217777e-06, + "loss": 0.006, + "step": 39505 + }, + { + "epoch": 12.2, + "learning_rate": 6.970393672224514e-06, + "loss": 0.0059, + "step": 39506 + }, + { + "epoch": 12.2, + "learning_rate": 6.969917061808853e-06, + "loss": 0.0049, + "step": 39507 + }, + { + "epoch": 12.2, + "learning_rate": 6.969440458971977e-06, + "loss": 0.0064, + "step": 39508 + }, + { + "epoch": 12.2, + "learning_rate": 6.968963863715085e-06, + "loss": 0.0056, + "step": 39509 + }, + { + "epoch": 12.2, + "learning_rate": 6.968487276039369e-06, + "loss": 0.0073, + "step": 39510 + }, + { + "epoch": 12.2, + "learning_rate": 6.968010695946015e-06, + "loss": 0.0052, + "step": 39511 + }, + { + "epoch": 12.2, + "learning_rate": 6.967534123436221e-06, + "loss": 0.0058, + "step": 39512 + }, + { + "epoch": 12.2, + "learning_rate": 6.967057558511181e-06, + "loss": 0.0063, + "step": 39513 + }, + { + "epoch": 12.2, + "learning_rate": 6.966581001172078e-06, + "loss": 0.008, + "step": 39514 + }, + { + "epoch": 12.2, + "learning_rate": 6.966104451420112e-06, + "loss": 0.0069, + "step": 39515 + }, + { + "epoch": 12.2, + "learning_rate": 6.965627909256474e-06, + "loss": 0.007, + "step": 39516 + }, + { + "epoch": 12.2, + "learning_rate": 6.965151374682351e-06, + "loss": 0.0076, + "step": 39517 + }, + { + "epoch": 12.2, + "learning_rate": 6.9646748476989355e-06, + "loss": 0.0076, + "step": 39518 + }, + { + "epoch": 12.2, + "learning_rate": 6.9641983283074256e-06, + "loss": 0.0062, + "step": 39519 + }, + { + "epoch": 12.2, + "learning_rate": 6.96372181650901e-06, + "loss": 0.0055, + "step": 39520 + }, + { + "epoch": 12.2, + "learning_rate": 6.963245312304876e-06, + "loss": 0.0075, + "step": 39521 + }, + { + "epoch": 12.21, + "learning_rate": 6.962768815696222e-06, + "loss": 0.0065, + "step": 39522 + }, + { + "epoch": 12.21, + "learning_rate": 6.962292326684239e-06, + "loss": 0.0053, + "step": 39523 + }, + { + "epoch": 12.21, + "learning_rate": 6.961815845270113e-06, + "loss": 0.0063, + "step": 39524 + }, + { + "epoch": 12.21, + "learning_rate": 6.961339371455042e-06, + "loss": 0.0062, + "step": 39525 + }, + { + "epoch": 12.21, + "learning_rate": 6.960862905240217e-06, + "loss": 0.0064, + "step": 39526 + }, + { + "epoch": 12.21, + "learning_rate": 6.960386446626825e-06, + "loss": 0.0053, + "step": 39527 + }, + { + "epoch": 12.21, + "learning_rate": 6.959909995616061e-06, + "loss": 0.0054, + "step": 39528 + }, + { + "epoch": 12.21, + "learning_rate": 6.959433552209119e-06, + "loss": 0.0067, + "step": 39529 + }, + { + "epoch": 12.21, + "learning_rate": 6.958957116407188e-06, + "loss": 0.0074, + "step": 39530 + }, + { + "epoch": 12.21, + "learning_rate": 6.958480688211456e-06, + "loss": 0.0052, + "step": 39531 + }, + { + "epoch": 12.21, + "learning_rate": 6.958004267623123e-06, + "loss": 0.0053, + "step": 39532 + }, + { + "epoch": 12.21, + "learning_rate": 6.957527854643374e-06, + "loss": 0.0054, + "step": 39533 + }, + { + "epoch": 12.21, + "learning_rate": 6.957051449273402e-06, + "loss": 0.0053, + "step": 39534 + }, + { + "epoch": 12.21, + "learning_rate": 6.956575051514403e-06, + "loss": 0.0059, + "step": 39535 + }, + { + "epoch": 12.21, + "learning_rate": 6.956098661367562e-06, + "loss": 0.0076, + "step": 39536 + }, + { + "epoch": 12.21, + "learning_rate": 6.955622278834073e-06, + "loss": 0.0062, + "step": 39537 + }, + { + "epoch": 12.21, + "learning_rate": 6.955145903915132e-06, + "loss": 0.0058, + "step": 39538 + }, + { + "epoch": 12.21, + "learning_rate": 6.95466953661192e-06, + "loss": 0.0073, + "step": 39539 + }, + { + "epoch": 12.21, + "learning_rate": 6.9541931769256385e-06, + "loss": 0.0064, + "step": 39540 + }, + { + "epoch": 12.21, + "learning_rate": 6.953716824857477e-06, + "loss": 0.0071, + "step": 39541 + }, + { + "epoch": 12.21, + "learning_rate": 6.9532404804086215e-06, + "loss": 0.0067, + "step": 39542 + }, + { + "epoch": 12.21, + "learning_rate": 6.95276414358027e-06, + "loss": 0.0056, + "step": 39543 + }, + { + "epoch": 12.21, + "learning_rate": 6.952287814373611e-06, + "loss": 0.0064, + "step": 39544 + }, + { + "epoch": 12.21, + "learning_rate": 6.9518114927898335e-06, + "loss": 0.0061, + "step": 39545 + }, + { + "epoch": 12.21, + "learning_rate": 6.951335178830134e-06, + "loss": 0.0064, + "step": 39546 + }, + { + "epoch": 12.21, + "learning_rate": 6.950858872495703e-06, + "loss": 0.0072, + "step": 39547 + }, + { + "epoch": 12.21, + "learning_rate": 6.950382573787726e-06, + "loss": 0.0066, + "step": 39548 + }, + { + "epoch": 12.21, + "learning_rate": 6.9499062827073994e-06, + "loss": 0.0059, + "step": 39549 + }, + { + "epoch": 12.21, + "learning_rate": 6.949429999255916e-06, + "loss": 0.0092, + "step": 39550 + }, + { + "epoch": 12.21, + "learning_rate": 6.948953723434462e-06, + "loss": 0.0061, + "step": 39551 + }, + { + "epoch": 12.21, + "learning_rate": 6.948477455244229e-06, + "loss": 0.007, + "step": 39552 + }, + { + "epoch": 12.21, + "learning_rate": 6.948001194686414e-06, + "loss": 0.0073, + "step": 39553 + }, + { + "epoch": 12.22, + "learning_rate": 6.947524941762207e-06, + "loss": 0.0066, + "step": 39554 + }, + { + "epoch": 12.22, + "learning_rate": 6.947048696472791e-06, + "loss": 0.0049, + "step": 39555 + }, + { + "epoch": 12.22, + "learning_rate": 6.946572458819365e-06, + "loss": 0.0062, + "step": 39556 + }, + { + "epoch": 12.22, + "learning_rate": 6.946096228803122e-06, + "loss": 0.0067, + "step": 39557 + }, + { + "epoch": 12.22, + "learning_rate": 6.945620006425247e-06, + "loss": 0.005, + "step": 39558 + }, + { + "epoch": 12.22, + "learning_rate": 6.94514379168693e-06, + "loss": 0.0063, + "step": 39559 + }, + { + "epoch": 12.22, + "learning_rate": 6.9446675845893705e-06, + "loss": 0.0065, + "step": 39560 + }, + { + "epoch": 12.22, + "learning_rate": 6.9441913851337515e-06, + "loss": 0.0073, + "step": 39561 + }, + { + "epoch": 12.22, + "learning_rate": 6.943715193321267e-06, + "loss": 0.0057, + "step": 39562 + }, + { + "epoch": 12.22, + "learning_rate": 6.943239009153111e-06, + "loss": 0.0079, + "step": 39563 + }, + { + "epoch": 12.22, + "learning_rate": 6.942762832630471e-06, + "loss": 0.0074, + "step": 39564 + }, + { + "epoch": 12.22, + "learning_rate": 6.942286663754536e-06, + "loss": 0.006, + "step": 39565 + }, + { + "epoch": 12.22, + "learning_rate": 6.941810502526505e-06, + "loss": 0.0063, + "step": 39566 + }, + { + "epoch": 12.22, + "learning_rate": 6.941334348947559e-06, + "loss": 0.0064, + "step": 39567 + }, + { + "epoch": 12.22, + "learning_rate": 6.940858203018894e-06, + "loss": 0.0074, + "step": 39568 + }, + { + "epoch": 12.22, + "learning_rate": 6.940382064741704e-06, + "loss": 0.007, + "step": 39569 + }, + { + "epoch": 12.22, + "learning_rate": 6.9399059341171726e-06, + "loss": 0.0072, + "step": 39570 + }, + { + "epoch": 12.22, + "learning_rate": 6.939429811146497e-06, + "loss": 0.0058, + "step": 39571 + }, + { + "epoch": 12.22, + "learning_rate": 6.938953695830866e-06, + "loss": 0.006, + "step": 39572 + }, + { + "epoch": 12.22, + "learning_rate": 6.938477588171466e-06, + "loss": 0.0063, + "step": 39573 + }, + { + "epoch": 12.22, + "learning_rate": 6.938001488169495e-06, + "loss": 0.0095, + "step": 39574 + }, + { + "epoch": 12.22, + "learning_rate": 6.937525395826143e-06, + "loss": 0.0067, + "step": 39575 + }, + { + "epoch": 12.22, + "learning_rate": 6.937049311142596e-06, + "loss": 0.0071, + "step": 39576 + }, + { + "epoch": 12.22, + "learning_rate": 6.936573234120046e-06, + "loss": 0.0053, + "step": 39577 + }, + { + "epoch": 12.22, + "learning_rate": 6.936097164759688e-06, + "loss": 0.0069, + "step": 39578 + }, + { + "epoch": 12.22, + "learning_rate": 6.9356211030627085e-06, + "loss": 0.0066, + "step": 39579 + }, + { + "epoch": 12.22, + "learning_rate": 6.935145049030298e-06, + "loss": 0.0073, + "step": 39580 + }, + { + "epoch": 12.22, + "learning_rate": 6.934669002663652e-06, + "loss": 0.0081, + "step": 39581 + }, + { + "epoch": 12.22, + "learning_rate": 6.934192963963955e-06, + "loss": 0.0071, + "step": 39582 + }, + { + "epoch": 12.22, + "learning_rate": 6.9337169329324e-06, + "loss": 0.0074, + "step": 39583 + }, + { + "epoch": 12.22, + "learning_rate": 6.933240909570183e-06, + "loss": 0.0067, + "step": 39584 + }, + { + "epoch": 12.22, + "learning_rate": 6.932764893878485e-06, + "loss": 0.0068, + "step": 39585 + }, + { + "epoch": 12.22, + "learning_rate": 6.932288885858503e-06, + "loss": 0.0079, + "step": 39586 + }, + { + "epoch": 12.23, + "learning_rate": 6.931812885511424e-06, + "loss": 0.0051, + "step": 39587 + }, + { + "epoch": 12.23, + "learning_rate": 6.931336892838445e-06, + "loss": 0.0053, + "step": 39588 + }, + { + "epoch": 12.23, + "learning_rate": 6.930860907840749e-06, + "loss": 0.0052, + "step": 39589 + }, + { + "epoch": 12.23, + "learning_rate": 6.930384930519529e-06, + "loss": 0.0064, + "step": 39590 + }, + { + "epoch": 12.23, + "learning_rate": 6.929908960875979e-06, + "loss": 0.0085, + "step": 39591 + }, + { + "epoch": 12.23, + "learning_rate": 6.929432998911285e-06, + "loss": 0.0072, + "step": 39592 + }, + { + "epoch": 12.23, + "learning_rate": 6.928957044626639e-06, + "loss": 0.0052, + "step": 39593 + }, + { + "epoch": 12.23, + "learning_rate": 6.928481098023232e-06, + "loss": 0.0064, + "step": 39594 + }, + { + "epoch": 12.23, + "learning_rate": 6.928005159102255e-06, + "loss": 0.0059, + "step": 39595 + }, + { + "epoch": 12.23, + "learning_rate": 6.927529227864893e-06, + "loss": 0.0076, + "step": 39596 + }, + { + "epoch": 12.23, + "learning_rate": 6.927053304312349e-06, + "loss": 0.0065, + "step": 39597 + }, + { + "epoch": 12.23, + "learning_rate": 6.926577388445797e-06, + "loss": 0.0065, + "step": 39598 + }, + { + "epoch": 12.23, + "learning_rate": 6.926101480266439e-06, + "loss": 0.0088, + "step": 39599 + }, + { + "epoch": 12.23, + "learning_rate": 6.925625579775464e-06, + "loss": 0.0064, + "step": 39600 + }, + { + "epoch": 12.23, + "learning_rate": 6.925149686974056e-06, + "loss": 0.0112, + "step": 39601 + }, + { + "epoch": 12.23, + "learning_rate": 6.9246738018634104e-06, + "loss": 0.0062, + "step": 39602 + }, + { + "epoch": 12.23, + "learning_rate": 6.92419792444472e-06, + "loss": 0.0074, + "step": 39603 + }, + { + "epoch": 12.23, + "learning_rate": 6.923722054719167e-06, + "loss": 0.0063, + "step": 39604 + }, + { + "epoch": 12.23, + "learning_rate": 6.9232461926879465e-06, + "loss": 0.0073, + "step": 39605 + }, + { + "epoch": 12.23, + "learning_rate": 6.922770338352254e-06, + "loss": 0.0056, + "step": 39606 + }, + { + "epoch": 12.23, + "learning_rate": 6.922294491713268e-06, + "loss": 0.006, + "step": 39607 + }, + { + "epoch": 12.23, + "learning_rate": 6.9218186527721856e-06, + "loss": 0.0053, + "step": 39608 + }, + { + "epoch": 12.23, + "learning_rate": 6.921342821530199e-06, + "loss": 0.0067, + "step": 39609 + }, + { + "epoch": 12.23, + "learning_rate": 6.920866997988495e-06, + "loss": 0.0063, + "step": 39610 + }, + { + "epoch": 12.23, + "learning_rate": 6.920391182148261e-06, + "loss": 0.0064, + "step": 39611 + }, + { + "epoch": 12.23, + "learning_rate": 6.919915374010695e-06, + "loss": 0.0058, + "step": 39612 + }, + { + "epoch": 12.23, + "learning_rate": 6.919439573576981e-06, + "loss": 0.007, + "step": 39613 + }, + { + "epoch": 12.23, + "learning_rate": 6.9189637808483065e-06, + "loss": 0.0055, + "step": 39614 + }, + { + "epoch": 12.23, + "learning_rate": 6.918487995825872e-06, + "loss": 0.006, + "step": 39615 + }, + { + "epoch": 12.23, + "learning_rate": 6.9180122185108555e-06, + "loss": 0.0073, + "step": 39616 + }, + { + "epoch": 12.23, + "learning_rate": 6.917536448904455e-06, + "loss": 0.0055, + "step": 39617 + }, + { + "epoch": 12.23, + "learning_rate": 6.917060687007855e-06, + "loss": 0.0063, + "step": 39618 + }, + { + "epoch": 12.24, + "learning_rate": 6.916584932822254e-06, + "loss": 0.0059, + "step": 39619 + }, + { + "epoch": 12.24, + "learning_rate": 6.916109186348834e-06, + "loss": 0.0054, + "step": 39620 + }, + { + "epoch": 12.24, + "learning_rate": 6.915633447588785e-06, + "loss": 0.0057, + "step": 39621 + }, + { + "epoch": 12.24, + "learning_rate": 6.915157716543303e-06, + "loss": 0.0067, + "step": 39622 + }, + { + "epoch": 12.24, + "learning_rate": 6.914681993213572e-06, + "loss": 0.0055, + "step": 39623 + }, + { + "epoch": 12.24, + "learning_rate": 6.914206277600783e-06, + "loss": 0.0065, + "step": 39624 + }, + { + "epoch": 12.24, + "learning_rate": 6.913730569706132e-06, + "loss": 0.0063, + "step": 39625 + }, + { + "epoch": 12.24, + "learning_rate": 6.913254869530799e-06, + "loss": 0.0085, + "step": 39626 + }, + { + "epoch": 12.24, + "learning_rate": 6.912779177075979e-06, + "loss": 0.0067, + "step": 39627 + }, + { + "epoch": 12.24, + "learning_rate": 6.912303492342865e-06, + "loss": 0.0056, + "step": 39628 + }, + { + "epoch": 12.24, + "learning_rate": 6.911827815332638e-06, + "loss": 0.0052, + "step": 39629 + }, + { + "epoch": 12.24, + "learning_rate": 6.911352146046495e-06, + "loss": 0.0068, + "step": 39630 + }, + { + "epoch": 12.24, + "learning_rate": 6.910876484485626e-06, + "loss": 0.006, + "step": 39631 + }, + { + "epoch": 12.24, + "learning_rate": 6.910400830651214e-06, + "loss": 0.0059, + "step": 39632 + }, + { + "epoch": 12.24, + "learning_rate": 6.9099251845444546e-06, + "loss": 0.0065, + "step": 39633 + }, + { + "epoch": 12.24, + "learning_rate": 6.909449546166539e-06, + "loss": 0.0064, + "step": 39634 + }, + { + "epoch": 12.24, + "learning_rate": 6.908973915518648e-06, + "loss": 0.0065, + "step": 39635 + }, + { + "epoch": 12.24, + "learning_rate": 6.908498292601981e-06, + "loss": 0.007, + "step": 39636 + }, + { + "epoch": 12.24, + "learning_rate": 6.908022677417725e-06, + "loss": 0.0063, + "step": 39637 + }, + { + "epoch": 12.24, + "learning_rate": 6.907547069967067e-06, + "loss": 0.0078, + "step": 39638 + }, + { + "epoch": 12.24, + "learning_rate": 6.907071470251194e-06, + "loss": 0.0063, + "step": 39639 + }, + { + "epoch": 12.24, + "learning_rate": 6.906595878271305e-06, + "loss": 0.0064, + "step": 39640 + }, + { + "epoch": 12.24, + "learning_rate": 6.9061202940285806e-06, + "loss": 0.0067, + "step": 39641 + }, + { + "epoch": 12.24, + "learning_rate": 6.9056447175242125e-06, + "loss": 0.0053, + "step": 39642 + }, + { + "epoch": 12.24, + "learning_rate": 6.9051691487593945e-06, + "loss": 0.006, + "step": 39643 + }, + { + "epoch": 12.24, + "learning_rate": 6.904693587735312e-06, + "loss": 0.006, + "step": 39644 + }, + { + "epoch": 12.24, + "learning_rate": 6.904218034453153e-06, + "loss": 0.0066, + "step": 39645 + }, + { + "epoch": 12.24, + "learning_rate": 6.903742488914116e-06, + "loss": 0.0054, + "step": 39646 + }, + { + "epoch": 12.24, + "learning_rate": 6.903266951119376e-06, + "loss": 0.0057, + "step": 39647 + }, + { + "epoch": 12.24, + "learning_rate": 6.902791421070133e-06, + "loss": 0.0073, + "step": 39648 + }, + { + "epoch": 12.24, + "learning_rate": 6.902315898767575e-06, + "loss": 0.0068, + "step": 39649 + }, + { + "epoch": 12.24, + "learning_rate": 6.901840384212888e-06, + "loss": 0.0073, + "step": 39650 + }, + { + "epoch": 12.24, + "learning_rate": 6.901364877407263e-06, + "loss": 0.0066, + "step": 39651 + }, + { + "epoch": 12.25, + "learning_rate": 6.9008893783518885e-06, + "loss": 0.0064, + "step": 39652 + }, + { + "epoch": 12.25, + "learning_rate": 6.900413887047958e-06, + "loss": 0.006, + "step": 39653 + }, + { + "epoch": 12.25, + "learning_rate": 6.899938403496658e-06, + "loss": 0.0067, + "step": 39654 + }, + { + "epoch": 12.25, + "learning_rate": 6.899462927699173e-06, + "loss": 0.0067, + "step": 39655 + }, + { + "epoch": 12.25, + "learning_rate": 6.8989874596567045e-06, + "loss": 0.0055, + "step": 39656 + }, + { + "epoch": 12.25, + "learning_rate": 6.898511999370427e-06, + "loss": 0.0081, + "step": 39657 + }, + { + "epoch": 12.25, + "learning_rate": 6.898036546841539e-06, + "loss": 0.0066, + "step": 39658 + }, + { + "epoch": 12.25, + "learning_rate": 6.897561102071228e-06, + "loss": 0.0062, + "step": 39659 + }, + { + "epoch": 12.25, + "learning_rate": 6.897085665060681e-06, + "loss": 0.007, + "step": 39660 + }, + { + "epoch": 12.25, + "learning_rate": 6.89661023581109e-06, + "loss": 0.0065, + "step": 39661 + }, + { + "epoch": 12.25, + "learning_rate": 6.896134814323643e-06, + "loss": 0.0061, + "step": 39662 + }, + { + "epoch": 12.25, + "learning_rate": 6.895659400599526e-06, + "loss": 0.0062, + "step": 39663 + }, + { + "epoch": 12.25, + "learning_rate": 6.895183994639933e-06, + "loss": 0.0067, + "step": 39664 + }, + { + "epoch": 12.25, + "learning_rate": 6.894708596446054e-06, + "loss": 0.0053, + "step": 39665 + }, + { + "epoch": 12.25, + "learning_rate": 6.894233206019072e-06, + "loss": 0.0061, + "step": 39666 + }, + { + "epoch": 12.25, + "learning_rate": 6.893757823360179e-06, + "loss": 0.0064, + "step": 39667 + }, + { + "epoch": 12.25, + "learning_rate": 6.893282448470566e-06, + "loss": 0.0064, + "step": 39668 + }, + { + "epoch": 12.25, + "learning_rate": 6.892807081351419e-06, + "loss": 0.0068, + "step": 39669 + }, + { + "epoch": 12.25, + "learning_rate": 6.8923317220039266e-06, + "loss": 0.0065, + "step": 39670 + }, + { + "epoch": 12.25, + "learning_rate": 6.891856370429284e-06, + "loss": 0.0058, + "step": 39671 + }, + { + "epoch": 12.25, + "learning_rate": 6.8913810266286714e-06, + "loss": 0.0057, + "step": 39672 + }, + { + "epoch": 12.25, + "learning_rate": 6.890905690603282e-06, + "loss": 0.0065, + "step": 39673 + }, + { + "epoch": 12.25, + "learning_rate": 6.890430362354308e-06, + "loss": 0.0065, + "step": 39674 + }, + { + "epoch": 12.25, + "learning_rate": 6.889955041882932e-06, + "loss": 0.0053, + "step": 39675 + }, + { + "epoch": 12.25, + "learning_rate": 6.8894797291903456e-06, + "loss": 0.0056, + "step": 39676 + }, + { + "epoch": 12.25, + "learning_rate": 6.889004424277741e-06, + "loss": 0.0056, + "step": 39677 + }, + { + "epoch": 12.25, + "learning_rate": 6.888529127146298e-06, + "loss": 0.006, + "step": 39678 + }, + { + "epoch": 12.25, + "learning_rate": 6.888053837797215e-06, + "loss": 0.0068, + "step": 39679 + }, + { + "epoch": 12.25, + "learning_rate": 6.8875785562316775e-06, + "loss": 0.006, + "step": 39680 + }, + { + "epoch": 12.25, + "learning_rate": 6.887103282450871e-06, + "loss": 0.0049, + "step": 39681 + }, + { + "epoch": 12.25, + "learning_rate": 6.886628016455988e-06, + "loss": 0.0067, + "step": 39682 + }, + { + "epoch": 12.25, + "learning_rate": 6.886152758248215e-06, + "loss": 0.0077, + "step": 39683 + }, + { + "epoch": 12.26, + "learning_rate": 6.8856775078287445e-06, + "loss": 0.0064, + "step": 39684 + }, + { + "epoch": 12.26, + "learning_rate": 6.88520226519876e-06, + "loss": 0.0072, + "step": 39685 + }, + { + "epoch": 12.26, + "learning_rate": 6.884727030359455e-06, + "loss": 0.0055, + "step": 39686 + }, + { + "epoch": 12.26, + "learning_rate": 6.8842518033120165e-06, + "loss": 0.0059, + "step": 39687 + }, + { + "epoch": 12.26, + "learning_rate": 6.8837765840576286e-06, + "loss": 0.0066, + "step": 39688 + }, + { + "epoch": 12.26, + "learning_rate": 6.883301372597487e-06, + "loss": 0.0059, + "step": 39689 + }, + { + "epoch": 12.26, + "learning_rate": 6.882826168932779e-06, + "loss": 0.0062, + "step": 39690 + }, + { + "epoch": 12.26, + "learning_rate": 6.8823509730646865e-06, + "loss": 0.0066, + "step": 39691 + }, + { + "epoch": 12.26, + "learning_rate": 6.881875784994405e-06, + "loss": 0.0063, + "step": 39692 + }, + { + "epoch": 12.26, + "learning_rate": 6.881400604723123e-06, + "loss": 0.0074, + "step": 39693 + }, + { + "epoch": 12.26, + "learning_rate": 6.8809254322520215e-06, + "loss": 0.0061, + "step": 39694 + }, + { + "epoch": 12.26, + "learning_rate": 6.8804502675822984e-06, + "loss": 0.0071, + "step": 39695 + }, + { + "epoch": 12.26, + "learning_rate": 6.879975110715139e-06, + "loss": 0.0057, + "step": 39696 + }, + { + "epoch": 12.26, + "learning_rate": 6.87949996165173e-06, + "loss": 0.0063, + "step": 39697 + }, + { + "epoch": 12.26, + "learning_rate": 6.879024820393257e-06, + "loss": 0.0057, + "step": 39698 + }, + { + "epoch": 12.26, + "learning_rate": 6.8785496869409176e-06, + "loss": 0.0075, + "step": 39699 + }, + { + "epoch": 12.26, + "learning_rate": 6.878074561295892e-06, + "loss": 0.0054, + "step": 39700 + }, + { + "epoch": 12.26, + "learning_rate": 6.8775994434593695e-06, + "loss": 0.006, + "step": 39701 + }, + { + "epoch": 12.26, + "learning_rate": 6.877124333432544e-06, + "loss": 0.0072, + "step": 39702 + }, + { + "epoch": 12.26, + "learning_rate": 6.876649231216599e-06, + "loss": 0.0067, + "step": 39703 + }, + { + "epoch": 12.26, + "learning_rate": 6.876174136812721e-06, + "loss": 0.0078, + "step": 39704 + }, + { + "epoch": 12.26, + "learning_rate": 6.875699050222109e-06, + "loss": 0.0079, + "step": 39705 + }, + { + "epoch": 12.26, + "learning_rate": 6.875223971445935e-06, + "loss": 0.0061, + "step": 39706 + }, + { + "epoch": 12.26, + "learning_rate": 6.874748900485399e-06, + "loss": 0.0065, + "step": 39707 + }, + { + "epoch": 12.26, + "learning_rate": 6.874273837341688e-06, + "loss": 0.006, + "step": 39708 + }, + { + "epoch": 12.26, + "learning_rate": 6.8737987820159845e-06, + "loss": 0.0069, + "step": 39709 + }, + { + "epoch": 12.26, + "learning_rate": 6.8733237345094825e-06, + "loss": 0.0052, + "step": 39710 + }, + { + "epoch": 12.26, + "learning_rate": 6.87284869482337e-06, + "loss": 0.0055, + "step": 39711 + }, + { + "epoch": 12.26, + "learning_rate": 6.872373662958829e-06, + "loss": 0.006, + "step": 39712 + }, + { + "epoch": 12.26, + "learning_rate": 6.8718986389170535e-06, + "loss": 0.0095, + "step": 39713 + }, + { + "epoch": 12.26, + "learning_rate": 6.871423622699233e-06, + "loss": 0.0062, + "step": 39714 + }, + { + "epoch": 12.26, + "learning_rate": 6.87094861430655e-06, + "loss": 0.0057, + "step": 39715 + }, + { + "epoch": 12.27, + "learning_rate": 6.870473613740193e-06, + "loss": 0.0082, + "step": 39716 + }, + { + "epoch": 12.27, + "learning_rate": 6.869998621001355e-06, + "loss": 0.0066, + "step": 39717 + }, + { + "epoch": 12.27, + "learning_rate": 6.869523636091222e-06, + "loss": 0.0079, + "step": 39718 + }, + { + "epoch": 12.27, + "learning_rate": 6.869048659010979e-06, + "loss": 0.0047, + "step": 39719 + }, + { + "epoch": 12.27, + "learning_rate": 6.8685736897618176e-06, + "loss": 0.0074, + "step": 39720 + }, + { + "epoch": 12.27, + "learning_rate": 6.868098728344926e-06, + "loss": 0.0079, + "step": 39721 + }, + { + "epoch": 12.27, + "learning_rate": 6.867623774761487e-06, + "loss": 0.0062, + "step": 39722 + }, + { + "epoch": 12.27, + "learning_rate": 6.867148829012695e-06, + "loss": 0.0065, + "step": 39723 + }, + { + "epoch": 12.27, + "learning_rate": 6.8666738910997365e-06, + "loss": 0.005, + "step": 39724 + }, + { + "epoch": 12.27, + "learning_rate": 6.866198961023797e-06, + "loss": 0.0061, + "step": 39725 + }, + { + "epoch": 12.27, + "learning_rate": 6.865724038786061e-06, + "loss": 0.0073, + "step": 39726 + }, + { + "epoch": 12.27, + "learning_rate": 6.8652491243877275e-06, + "loss": 0.0064, + "step": 39727 + }, + { + "epoch": 12.27, + "learning_rate": 6.864774217829974e-06, + "loss": 0.0049, + "step": 39728 + }, + { + "epoch": 12.27, + "learning_rate": 6.864299319113991e-06, + "loss": 0.0064, + "step": 39729 + }, + { + "epoch": 12.27, + "learning_rate": 6.863824428240972e-06, + "loss": 0.0067, + "step": 39730 + }, + { + "epoch": 12.27, + "learning_rate": 6.863349545212097e-06, + "loss": 0.0061, + "step": 39731 + }, + { + "epoch": 12.27, + "learning_rate": 6.862874670028554e-06, + "loss": 0.0059, + "step": 39732 + }, + { + "epoch": 12.27, + "learning_rate": 6.862399802691539e-06, + "loss": 0.0061, + "step": 39733 + }, + { + "epoch": 12.27, + "learning_rate": 6.861924943202233e-06, + "loss": 0.0063, + "step": 39734 + }, + { + "epoch": 12.27, + "learning_rate": 6.861450091561823e-06, + "loss": 0.0061, + "step": 39735 + }, + { + "epoch": 12.27, + "learning_rate": 6.860975247771503e-06, + "loss": 0.0063, + "step": 39736 + }, + { + "epoch": 12.27, + "learning_rate": 6.860500411832452e-06, + "loss": 0.0063, + "step": 39737 + }, + { + "epoch": 12.27, + "learning_rate": 6.860025583745862e-06, + "loss": 0.0063, + "step": 39738 + }, + { + "epoch": 12.27, + "learning_rate": 6.859550763512926e-06, + "loss": 0.0065, + "step": 39739 + }, + { + "epoch": 12.27, + "learning_rate": 6.8590759511348195e-06, + "loss": 0.0081, + "step": 39740 + }, + { + "epoch": 12.27, + "learning_rate": 6.85860114661274e-06, + "loss": 0.0055, + "step": 39741 + }, + { + "epoch": 12.27, + "learning_rate": 6.858126349947873e-06, + "loss": 0.0056, + "step": 39742 + }, + { + "epoch": 12.27, + "learning_rate": 6.8576515611414015e-06, + "loss": 0.007, + "step": 39743 + }, + { + "epoch": 12.27, + "learning_rate": 6.857176780194519e-06, + "loss": 0.006, + "step": 39744 + }, + { + "epoch": 12.27, + "learning_rate": 6.8567020071084136e-06, + "loss": 0.0051, + "step": 39745 + }, + { + "epoch": 12.27, + "learning_rate": 6.856227241884266e-06, + "loss": 0.0049, + "step": 39746 + }, + { + "epoch": 12.27, + "learning_rate": 6.855752484523266e-06, + "loss": 0.0086, + "step": 39747 + }, + { + "epoch": 12.27, + "learning_rate": 6.855277735026604e-06, + "loss": 0.0053, + "step": 39748 + }, + { + "epoch": 12.28, + "learning_rate": 6.85480299339547e-06, + "loss": 0.0057, + "step": 39749 + }, + { + "epoch": 12.28, + "learning_rate": 6.854328259631042e-06, + "loss": 0.0073, + "step": 39750 + }, + { + "epoch": 12.28, + "learning_rate": 6.8538535337345136e-06, + "loss": 0.0071, + "step": 39751 + }, + { + "epoch": 12.28, + "learning_rate": 6.8533788157070745e-06, + "loss": 0.0065, + "step": 39752 + }, + { + "epoch": 12.28, + "learning_rate": 6.852904105549906e-06, + "loss": 0.0075, + "step": 39753 + }, + { + "epoch": 12.28, + "learning_rate": 6.852429403264198e-06, + "loss": 0.0057, + "step": 39754 + }, + { + "epoch": 12.28, + "learning_rate": 6.851954708851143e-06, + "loss": 0.0057, + "step": 39755 + }, + { + "epoch": 12.28, + "learning_rate": 6.851480022311918e-06, + "loss": 0.0064, + "step": 39756 + }, + { + "epoch": 12.28, + "learning_rate": 6.8510053436477165e-06, + "loss": 0.0055, + "step": 39757 + }, + { + "epoch": 12.28, + "learning_rate": 6.850530672859728e-06, + "loss": 0.0063, + "step": 39758 + }, + { + "epoch": 12.28, + "learning_rate": 6.850056009949135e-06, + "loss": 0.0071, + "step": 39759 + }, + { + "epoch": 12.28, + "learning_rate": 6.849581354917123e-06, + "loss": 0.0064, + "step": 39760 + }, + { + "epoch": 12.28, + "learning_rate": 6.849106707764888e-06, + "loss": 0.0071, + "step": 39761 + }, + { + "epoch": 12.28, + "learning_rate": 6.84863206849361e-06, + "loss": 0.0061, + "step": 39762 + }, + { + "epoch": 12.28, + "learning_rate": 6.848157437104476e-06, + "loss": 0.0056, + "step": 39763 + }, + { + "epoch": 12.28, + "learning_rate": 6.847682813598679e-06, + "loss": 0.0063, + "step": 39764 + }, + { + "epoch": 12.28, + "learning_rate": 6.8472081979774e-06, + "loss": 0.006, + "step": 39765 + }, + { + "epoch": 12.28, + "learning_rate": 6.846733590241827e-06, + "loss": 0.0063, + "step": 39766 + }, + { + "epoch": 12.28, + "learning_rate": 6.846258990393152e-06, + "loss": 0.0066, + "step": 39767 + }, + { + "epoch": 12.28, + "learning_rate": 6.845784398432554e-06, + "loss": 0.0058, + "step": 39768 + }, + { + "epoch": 12.28, + "learning_rate": 6.845309814361226e-06, + "loss": 0.0051, + "step": 39769 + }, + { + "epoch": 12.28, + "learning_rate": 6.844835238180356e-06, + "loss": 0.0064, + "step": 39770 + }, + { + "epoch": 12.28, + "learning_rate": 6.844360669891126e-06, + "loss": 0.0061, + "step": 39771 + }, + { + "epoch": 12.28, + "learning_rate": 6.843886109494726e-06, + "loss": 0.006, + "step": 39772 + }, + { + "epoch": 12.28, + "learning_rate": 6.843411556992344e-06, + "loss": 0.0075, + "step": 39773 + }, + { + "epoch": 12.28, + "learning_rate": 6.842937012385165e-06, + "loss": 0.0061, + "step": 39774 + }, + { + "epoch": 12.28, + "learning_rate": 6.842462475674372e-06, + "loss": 0.0062, + "step": 39775 + }, + { + "epoch": 12.28, + "learning_rate": 6.8419879468611614e-06, + "loss": 0.0058, + "step": 39776 + }, + { + "epoch": 12.28, + "learning_rate": 6.841513425946714e-06, + "loss": 0.0085, + "step": 39777 + }, + { + "epoch": 12.28, + "learning_rate": 6.841038912932214e-06, + "loss": 0.0064, + "step": 39778 + }, + { + "epoch": 12.28, + "learning_rate": 6.840564407818857e-06, + "loss": 0.006, + "step": 39779 + }, + { + "epoch": 12.28, + "learning_rate": 6.840089910607823e-06, + "loss": 0.0071, + "step": 39780 + }, + { + "epoch": 12.29, + "learning_rate": 6.839615421300297e-06, + "loss": 0.0067, + "step": 39781 + }, + { + "epoch": 12.29, + "learning_rate": 6.839140939897473e-06, + "loss": 0.0064, + "step": 39782 + }, + { + "epoch": 12.29, + "learning_rate": 6.838666466400534e-06, + "loss": 0.0068, + "step": 39783 + }, + { + "epoch": 12.29, + "learning_rate": 6.838192000810666e-06, + "loss": 0.0073, + "step": 39784 + }, + { + "epoch": 12.29, + "learning_rate": 6.837717543129054e-06, + "loss": 0.0082, + "step": 39785 + }, + { + "epoch": 12.29, + "learning_rate": 6.837243093356892e-06, + "loss": 0.0076, + "step": 39786 + }, + { + "epoch": 12.29, + "learning_rate": 6.83676865149536e-06, + "loss": 0.0057, + "step": 39787 + }, + { + "epoch": 12.29, + "learning_rate": 6.836294217545642e-06, + "loss": 0.0061, + "step": 39788 + }, + { + "epoch": 12.29, + "learning_rate": 6.8358197915089365e-06, + "loss": 0.006, + "step": 39789 + }, + { + "epoch": 12.29, + "learning_rate": 6.8353453733864196e-06, + "loss": 0.006, + "step": 39790 + }, + { + "epoch": 12.29, + "learning_rate": 6.834870963179279e-06, + "loss": 0.0053, + "step": 39791 + }, + { + "epoch": 12.29, + "learning_rate": 6.834396560888707e-06, + "loss": 0.0066, + "step": 39792 + }, + { + "epoch": 12.29, + "learning_rate": 6.833922166515885e-06, + "loss": 0.0067, + "step": 39793 + }, + { + "epoch": 12.29, + "learning_rate": 6.833447780062002e-06, + "loss": 0.0063, + "step": 39794 + }, + { + "epoch": 12.29, + "learning_rate": 6.832973401528244e-06, + "loss": 0.0062, + "step": 39795 + }, + { + "epoch": 12.29, + "learning_rate": 6.832499030915794e-06, + "loss": 0.0063, + "step": 39796 + }, + { + "epoch": 12.29, + "learning_rate": 6.832024668225843e-06, + "loss": 0.005, + "step": 39797 + }, + { + "epoch": 12.29, + "learning_rate": 6.8315503134595785e-06, + "loss": 0.0068, + "step": 39798 + }, + { + "epoch": 12.29, + "learning_rate": 6.831075966618181e-06, + "loss": 0.0061, + "step": 39799 + }, + { + "epoch": 12.29, + "learning_rate": 6.830601627702842e-06, + "loss": 0.0055, + "step": 39800 + }, + { + "epoch": 12.29, + "learning_rate": 6.830127296714748e-06, + "loss": 0.0069, + "step": 39801 + }, + { + "epoch": 12.29, + "learning_rate": 6.82965297365508e-06, + "loss": 0.0072, + "step": 39802 + }, + { + "epoch": 12.29, + "learning_rate": 6.829178658525031e-06, + "loss": 0.006, + "step": 39803 + }, + { + "epoch": 12.29, + "learning_rate": 6.8287043513257856e-06, + "loss": 0.0093, + "step": 39804 + }, + { + "epoch": 12.29, + "learning_rate": 6.828230052058527e-06, + "loss": 0.0066, + "step": 39805 + }, + { + "epoch": 12.29, + "learning_rate": 6.8277557607244416e-06, + "loss": 0.0078, + "step": 39806 + }, + { + "epoch": 12.29, + "learning_rate": 6.827281477324722e-06, + "loss": 0.0072, + "step": 39807 + }, + { + "epoch": 12.29, + "learning_rate": 6.826807201860548e-06, + "loss": 0.0049, + "step": 39808 + }, + { + "epoch": 12.29, + "learning_rate": 6.826332934333106e-06, + "loss": 0.0052, + "step": 39809 + }, + { + "epoch": 12.29, + "learning_rate": 6.825858674743588e-06, + "loss": 0.0056, + "step": 39810 + }, + { + "epoch": 12.29, + "learning_rate": 6.825384423093174e-06, + "loss": 0.0067, + "step": 39811 + }, + { + "epoch": 12.29, + "learning_rate": 6.824910179383051e-06, + "loss": 0.0062, + "step": 39812 + }, + { + "epoch": 12.3, + "learning_rate": 6.824435943614414e-06, + "loss": 0.0065, + "step": 39813 + }, + { + "epoch": 12.3, + "learning_rate": 6.823961715788434e-06, + "loss": 0.0064, + "step": 39814 + }, + { + "epoch": 12.3, + "learning_rate": 6.823487495906307e-06, + "loss": 0.0068, + "step": 39815 + }, + { + "epoch": 12.3, + "learning_rate": 6.823013283969216e-06, + "loss": 0.0074, + "step": 39816 + }, + { + "epoch": 12.3, + "learning_rate": 6.822539079978352e-06, + "loss": 0.0057, + "step": 39817 + }, + { + "epoch": 12.3, + "learning_rate": 6.822064883934896e-06, + "loss": 0.0068, + "step": 39818 + }, + { + "epoch": 12.3, + "learning_rate": 6.821590695840032e-06, + "loss": 0.0064, + "step": 39819 + }, + { + "epoch": 12.3, + "learning_rate": 6.821116515694955e-06, + "loss": 0.0065, + "step": 39820 + }, + { + "epoch": 12.3, + "learning_rate": 6.820642343500842e-06, + "loss": 0.005, + "step": 39821 + }, + { + "epoch": 12.3, + "learning_rate": 6.8201681792588815e-06, + "loss": 0.0078, + "step": 39822 + }, + { + "epoch": 12.3, + "learning_rate": 6.819694022970264e-06, + "loss": 0.0068, + "step": 39823 + }, + { + "epoch": 12.3, + "learning_rate": 6.819219874636168e-06, + "loss": 0.0059, + "step": 39824 + }, + { + "epoch": 12.3, + "learning_rate": 6.818745734257786e-06, + "loss": 0.0061, + "step": 39825 + }, + { + "epoch": 12.3, + "learning_rate": 6.818271601836301e-06, + "loss": 0.006, + "step": 39826 + }, + { + "epoch": 12.3, + "learning_rate": 6.817797477372896e-06, + "loss": 0.0057, + "step": 39827 + }, + { + "epoch": 12.3, + "learning_rate": 6.817323360868762e-06, + "loss": 0.006, + "step": 39828 + }, + { + "epoch": 12.3, + "learning_rate": 6.816849252325084e-06, + "loss": 0.0068, + "step": 39829 + }, + { + "epoch": 12.3, + "learning_rate": 6.816375151743043e-06, + "loss": 0.0064, + "step": 39830 + }, + { + "epoch": 12.3, + "learning_rate": 6.81590105912383e-06, + "loss": 0.0077, + "step": 39831 + }, + { + "epoch": 12.3, + "learning_rate": 6.815426974468633e-06, + "loss": 0.0079, + "step": 39832 + }, + { + "epoch": 12.3, + "learning_rate": 6.8149528977786305e-06, + "loss": 0.0067, + "step": 39833 + }, + { + "epoch": 12.3, + "learning_rate": 6.814478829055009e-06, + "loss": 0.0072, + "step": 39834 + }, + { + "epoch": 12.3, + "learning_rate": 6.814004768298963e-06, + "loss": 0.0071, + "step": 39835 + }, + { + "epoch": 12.3, + "learning_rate": 6.8135307155116695e-06, + "loss": 0.0064, + "step": 39836 + }, + { + "epoch": 12.3, + "learning_rate": 6.8130566706943135e-06, + "loss": 0.0077, + "step": 39837 + }, + { + "epoch": 12.3, + "learning_rate": 6.812582633848088e-06, + "loss": 0.0056, + "step": 39838 + }, + { + "epoch": 12.3, + "learning_rate": 6.812108604974175e-06, + "loss": 0.0061, + "step": 39839 + }, + { + "epoch": 12.3, + "learning_rate": 6.8116345840737565e-06, + "loss": 0.0054, + "step": 39840 + }, + { + "epoch": 12.3, + "learning_rate": 6.8111605711480244e-06, + "loss": 0.0062, + "step": 39841 + }, + { + "epoch": 12.3, + "learning_rate": 6.8106865661981604e-06, + "loss": 0.0061, + "step": 39842 + }, + { + "epoch": 12.3, + "learning_rate": 6.81021256922535e-06, + "loss": 0.0058, + "step": 39843 + }, + { + "epoch": 12.3, + "learning_rate": 6.809738580230783e-06, + "loss": 0.0061, + "step": 39844 + }, + { + "epoch": 12.3, + "learning_rate": 6.809264599215637e-06, + "loss": 0.0067, + "step": 39845 + }, + { + "epoch": 12.31, + "learning_rate": 6.808790626181105e-06, + "loss": 0.0056, + "step": 39846 + }, + { + "epoch": 12.31, + "learning_rate": 6.808316661128367e-06, + "loss": 0.005, + "step": 39847 + }, + { + "epoch": 12.31, + "learning_rate": 6.807842704058616e-06, + "loss": 0.007, + "step": 39848 + }, + { + "epoch": 12.31, + "learning_rate": 6.807368754973029e-06, + "loss": 0.0061, + "step": 39849 + }, + { + "epoch": 12.31, + "learning_rate": 6.806894813872794e-06, + "loss": 0.0077, + "step": 39850 + }, + { + "epoch": 12.31, + "learning_rate": 6.806420880759102e-06, + "loss": 0.0074, + "step": 39851 + }, + { + "epoch": 12.31, + "learning_rate": 6.805946955633131e-06, + "loss": 0.0061, + "step": 39852 + }, + { + "epoch": 12.31, + "learning_rate": 6.8054730384960675e-06, + "loss": 0.007, + "step": 39853 + }, + { + "epoch": 12.31, + "learning_rate": 6.804999129349104e-06, + "loss": 0.0063, + "step": 39854 + }, + { + "epoch": 12.31, + "learning_rate": 6.804525228193416e-06, + "loss": 0.0062, + "step": 39855 + }, + { + "epoch": 12.31, + "learning_rate": 6.804051335030194e-06, + "loss": 0.0057, + "step": 39856 + }, + { + "epoch": 12.31, + "learning_rate": 6.8035774498606255e-06, + "loss": 0.0079, + "step": 39857 + }, + { + "epoch": 12.31, + "learning_rate": 6.8031035726858874e-06, + "loss": 0.0069, + "step": 39858 + }, + { + "epoch": 12.31, + "learning_rate": 6.8026297035071734e-06, + "loss": 0.0059, + "step": 39859 + }, + { + "epoch": 12.31, + "learning_rate": 6.802155842325666e-06, + "loss": 0.0073, + "step": 39860 + }, + { + "epoch": 12.31, + "learning_rate": 6.801681989142548e-06, + "loss": 0.0076, + "step": 39861 + }, + { + "epoch": 12.31, + "learning_rate": 6.801208143959008e-06, + "loss": 0.0059, + "step": 39862 + }, + { + "epoch": 12.31, + "learning_rate": 6.800734306776231e-06, + "loss": 0.0084, + "step": 39863 + }, + { + "epoch": 12.31, + "learning_rate": 6.8002604775954e-06, + "loss": 0.0052, + "step": 39864 + }, + { + "epoch": 12.31, + "learning_rate": 6.7997866564176995e-06, + "loss": 0.0066, + "step": 39865 + }, + { + "epoch": 12.31, + "learning_rate": 6.7993128432443186e-06, + "loss": 0.0058, + "step": 39866 + }, + { + "epoch": 12.31, + "learning_rate": 6.79883903807644e-06, + "loss": 0.006, + "step": 39867 + }, + { + "epoch": 12.31, + "learning_rate": 6.7983652409152455e-06, + "loss": 0.0059, + "step": 39868 + }, + { + "epoch": 12.31, + "learning_rate": 6.797891451761929e-06, + "loss": 0.0072, + "step": 39869 + }, + { + "epoch": 12.31, + "learning_rate": 6.797417670617668e-06, + "loss": 0.0072, + "step": 39870 + }, + { + "epoch": 12.31, + "learning_rate": 6.796943897483645e-06, + "loss": 0.0068, + "step": 39871 + }, + { + "epoch": 12.31, + "learning_rate": 6.796470132361057e-06, + "loss": 0.008, + "step": 39872 + }, + { + "epoch": 12.31, + "learning_rate": 6.795996375251076e-06, + "loss": 0.0058, + "step": 39873 + }, + { + "epoch": 12.31, + "learning_rate": 6.795522626154894e-06, + "loss": 0.006, + "step": 39874 + }, + { + "epoch": 12.31, + "learning_rate": 6.7950488850736965e-06, + "loss": 0.0065, + "step": 39875 + }, + { + "epoch": 12.31, + "learning_rate": 6.794575152008662e-06, + "loss": 0.0067, + "step": 39876 + }, + { + "epoch": 12.31, + "learning_rate": 6.7941014269609815e-06, + "loss": 0.0054, + "step": 39877 + }, + { + "epoch": 12.32, + "learning_rate": 6.7936277099318405e-06, + "loss": 0.0052, + "step": 39878 + }, + { + "epoch": 12.32, + "learning_rate": 6.793154000922418e-06, + "loss": 0.0067, + "step": 39879 + }, + { + "epoch": 12.32, + "learning_rate": 6.792680299933903e-06, + "loss": 0.0075, + "step": 39880 + }, + { + "epoch": 12.32, + "learning_rate": 6.792206606967477e-06, + "loss": 0.0042, + "step": 39881 + }, + { + "epoch": 12.32, + "learning_rate": 6.791732922024335e-06, + "loss": 0.0071, + "step": 39882 + }, + { + "epoch": 12.32, + "learning_rate": 6.791259245105648e-06, + "loss": 0.0085, + "step": 39883 + }, + { + "epoch": 12.32, + "learning_rate": 6.790785576212608e-06, + "loss": 0.0077, + "step": 39884 + }, + { + "epoch": 12.32, + "learning_rate": 6.790311915346401e-06, + "loss": 0.0075, + "step": 39885 + }, + { + "epoch": 12.32, + "learning_rate": 6.789838262508205e-06, + "loss": 0.0083, + "step": 39886 + }, + { + "epoch": 12.32, + "learning_rate": 6.789364617699211e-06, + "loss": 0.0064, + "step": 39887 + }, + { + "epoch": 12.32, + "learning_rate": 6.788890980920604e-06, + "loss": 0.007, + "step": 39888 + }, + { + "epoch": 12.32, + "learning_rate": 6.788417352173562e-06, + "loss": 0.007, + "step": 39889 + }, + { + "epoch": 12.32, + "learning_rate": 6.787943731459277e-06, + "loss": 0.0058, + "step": 39890 + }, + { + "epoch": 12.32, + "learning_rate": 6.7874701187789315e-06, + "loss": 0.0069, + "step": 39891 + }, + { + "epoch": 12.32, + "learning_rate": 6.786996514133706e-06, + "loss": 0.0058, + "step": 39892 + }, + { + "epoch": 12.32, + "learning_rate": 6.78652291752479e-06, + "loss": 0.007, + "step": 39893 + }, + { + "epoch": 12.32, + "learning_rate": 6.786049328953368e-06, + "loss": 0.0057, + "step": 39894 + }, + { + "epoch": 12.32, + "learning_rate": 6.785575748420621e-06, + "loss": 0.0066, + "step": 39895 + }, + { + "epoch": 12.32, + "learning_rate": 6.785102175927731e-06, + "loss": 0.0061, + "step": 39896 + }, + { + "epoch": 12.32, + "learning_rate": 6.784628611475894e-06, + "loss": 0.0063, + "step": 39897 + }, + { + "epoch": 12.32, + "learning_rate": 6.784155055066284e-06, + "loss": 0.0078, + "step": 39898 + }, + { + "epoch": 12.32, + "learning_rate": 6.7836815067000875e-06, + "loss": 0.006, + "step": 39899 + }, + { + "epoch": 12.32, + "learning_rate": 6.783207966378493e-06, + "loss": 0.0063, + "step": 39900 + }, + { + "epoch": 12.32, + "learning_rate": 6.782734434102681e-06, + "loss": 0.0071, + "step": 39901 + }, + { + "epoch": 12.32, + "learning_rate": 6.782260909873835e-06, + "loss": 0.0074, + "step": 39902 + }, + { + "epoch": 12.32, + "learning_rate": 6.781787393693147e-06, + "loss": 0.006, + "step": 39903 + }, + { + "epoch": 12.32, + "learning_rate": 6.781313885561789e-06, + "loss": 0.007, + "step": 39904 + }, + { + "epoch": 12.32, + "learning_rate": 6.780840385480955e-06, + "loss": 0.0065, + "step": 39905 + }, + { + "epoch": 12.32, + "learning_rate": 6.780366893451828e-06, + "loss": 0.0065, + "step": 39906 + }, + { + "epoch": 12.32, + "learning_rate": 6.779893409475586e-06, + "loss": 0.0063, + "step": 39907 + }, + { + "epoch": 12.32, + "learning_rate": 6.779419933553422e-06, + "loss": 0.0063, + "step": 39908 + }, + { + "epoch": 12.32, + "learning_rate": 6.778946465686517e-06, + "loss": 0.0044, + "step": 39909 + }, + { + "epoch": 12.32, + "learning_rate": 6.7784730058760495e-06, + "loss": 0.0063, + "step": 39910 + }, + { + "epoch": 12.33, + "learning_rate": 6.777999554123211e-06, + "loss": 0.0065, + "step": 39911 + }, + { + "epoch": 12.33, + "learning_rate": 6.777526110429182e-06, + "loss": 0.0053, + "step": 39912 + }, + { + "epoch": 12.33, + "learning_rate": 6.777052674795153e-06, + "loss": 0.0066, + "step": 39913 + }, + { + "epoch": 12.33, + "learning_rate": 6.776579247222297e-06, + "loss": 0.0079, + "step": 39914 + }, + { + "epoch": 12.33, + "learning_rate": 6.776105827711808e-06, + "loss": 0.0072, + "step": 39915 + }, + { + "epoch": 12.33, + "learning_rate": 6.775632416264865e-06, + "loss": 0.007, + "step": 39916 + }, + { + "epoch": 12.33, + "learning_rate": 6.775159012882653e-06, + "loss": 0.0066, + "step": 39917 + }, + { + "epoch": 12.33, + "learning_rate": 6.774685617566357e-06, + "loss": 0.0063, + "step": 39918 + }, + { + "epoch": 12.33, + "learning_rate": 6.774212230317163e-06, + "loss": 0.0057, + "step": 39919 + }, + { + "epoch": 12.33, + "learning_rate": 6.7737388511362466e-06, + "loss": 0.0069, + "step": 39920 + }, + { + "epoch": 12.33, + "learning_rate": 6.773265480024802e-06, + "loss": 0.0062, + "step": 39921 + }, + { + "epoch": 12.33, + "learning_rate": 6.77279211698401e-06, + "loss": 0.0068, + "step": 39922 + }, + { + "epoch": 12.33, + "learning_rate": 6.772318762015051e-06, + "loss": 0.0055, + "step": 39923 + }, + { + "epoch": 12.33, + "learning_rate": 6.771845415119112e-06, + "loss": 0.0054, + "step": 39924 + }, + { + "epoch": 12.33, + "learning_rate": 6.771372076297378e-06, + "loss": 0.0075, + "step": 39925 + }, + { + "epoch": 12.33, + "learning_rate": 6.770898745551029e-06, + "loss": 0.0059, + "step": 39926 + }, + { + "epoch": 12.33, + "learning_rate": 6.77042542288125e-06, + "loss": 0.0072, + "step": 39927 + }, + { + "epoch": 12.33, + "learning_rate": 6.76995210828923e-06, + "loss": 0.0059, + "step": 39928 + }, + { + "epoch": 12.33, + "learning_rate": 6.769478801776148e-06, + "loss": 0.0061, + "step": 39929 + }, + { + "epoch": 12.33, + "learning_rate": 6.769005503343185e-06, + "loss": 0.0079, + "step": 39930 + }, + { + "epoch": 12.33, + "learning_rate": 6.768532212991533e-06, + "loss": 0.0071, + "step": 39931 + }, + { + "epoch": 12.33, + "learning_rate": 6.7680589307223695e-06, + "loss": 0.0058, + "step": 39932 + }, + { + "epoch": 12.33, + "learning_rate": 6.7675856565368815e-06, + "loss": 0.0139, + "step": 39933 + }, + { + "epoch": 12.33, + "learning_rate": 6.767112390436251e-06, + "loss": 0.006, + "step": 39934 + }, + { + "epoch": 12.33, + "learning_rate": 6.7666391324216596e-06, + "loss": 0.0069, + "step": 39935 + }, + { + "epoch": 12.33, + "learning_rate": 6.766165882494295e-06, + "loss": 0.0067, + "step": 39936 + }, + { + "epoch": 12.33, + "learning_rate": 6.765692640655342e-06, + "loss": 0.006, + "step": 39937 + }, + { + "epoch": 12.33, + "learning_rate": 6.765219406905977e-06, + "loss": 0.0062, + "step": 39938 + }, + { + "epoch": 12.33, + "learning_rate": 6.764746181247388e-06, + "loss": 0.0055, + "step": 39939 + }, + { + "epoch": 12.33, + "learning_rate": 6.764272963680764e-06, + "loss": 0.0069, + "step": 39940 + }, + { + "epoch": 12.33, + "learning_rate": 6.763799754207278e-06, + "loss": 0.0067, + "step": 39941 + }, + { + "epoch": 12.33, + "learning_rate": 6.763326552828122e-06, + "loss": 0.0075, + "step": 39942 + }, + { + "epoch": 12.34, + "learning_rate": 6.762853359544478e-06, + "loss": 0.0057, + "step": 39943 + }, + { + "epoch": 12.34, + "learning_rate": 6.762380174357526e-06, + "loss": 0.0065, + "step": 39944 + }, + { + "epoch": 12.34, + "learning_rate": 6.7619069972684504e-06, + "loss": 0.0076, + "step": 39945 + }, + { + "epoch": 12.34, + "learning_rate": 6.761433828278436e-06, + "loss": 0.0068, + "step": 39946 + }, + { + "epoch": 12.34, + "learning_rate": 6.760960667388671e-06, + "loss": 0.0066, + "step": 39947 + }, + { + "epoch": 12.34, + "learning_rate": 6.760487514600329e-06, + "loss": 0.0063, + "step": 39948 + }, + { + "epoch": 12.34, + "learning_rate": 6.7600143699146e-06, + "loss": 0.0064, + "step": 39949 + }, + { + "epoch": 12.34, + "learning_rate": 6.759541233332669e-06, + "loss": 0.0066, + "step": 39950 + }, + { + "epoch": 12.34, + "learning_rate": 6.759068104855713e-06, + "loss": 0.008, + "step": 39951 + }, + { + "epoch": 12.34, + "learning_rate": 6.758594984484918e-06, + "loss": 0.0055, + "step": 39952 + }, + { + "epoch": 12.34, + "learning_rate": 6.758121872221472e-06, + "loss": 0.0068, + "step": 39953 + }, + { + "epoch": 12.34, + "learning_rate": 6.757648768066553e-06, + "loss": 0.0058, + "step": 39954 + }, + { + "epoch": 12.34, + "learning_rate": 6.757175672021344e-06, + "loss": 0.0068, + "step": 39955 + }, + { + "epoch": 12.34, + "learning_rate": 6.756702584087033e-06, + "loss": 0.0052, + "step": 39956 + }, + { + "epoch": 12.34, + "learning_rate": 6.756229504264797e-06, + "loss": 0.0066, + "step": 39957 + }, + { + "epoch": 12.34, + "learning_rate": 6.755756432555823e-06, + "loss": 0.0068, + "step": 39958 + }, + { + "epoch": 12.34, + "learning_rate": 6.755283368961297e-06, + "loss": 0.0054, + "step": 39959 + }, + { + "epoch": 12.34, + "learning_rate": 6.7548103134823985e-06, + "loss": 0.0066, + "step": 39960 + }, + { + "epoch": 12.34, + "learning_rate": 6.754337266120308e-06, + "loss": 0.006, + "step": 39961 + }, + { + "epoch": 12.34, + "learning_rate": 6.753864226876217e-06, + "loss": 0.007, + "step": 39962 + }, + { + "epoch": 12.34, + "learning_rate": 6.753391195751299e-06, + "loss": 0.0061, + "step": 39963 + }, + { + "epoch": 12.34, + "learning_rate": 6.752918172746743e-06, + "loss": 0.0065, + "step": 39964 + }, + { + "epoch": 12.34, + "learning_rate": 6.752445157863734e-06, + "loss": 0.0071, + "step": 39965 + }, + { + "epoch": 12.34, + "learning_rate": 6.751972151103447e-06, + "loss": 0.0065, + "step": 39966 + }, + { + "epoch": 12.34, + "learning_rate": 6.751499152467072e-06, + "loss": 0.0079, + "step": 39967 + }, + { + "epoch": 12.34, + "learning_rate": 6.7510261619557926e-06, + "loss": 0.0068, + "step": 39968 + }, + { + "epoch": 12.34, + "learning_rate": 6.750553179570785e-06, + "loss": 0.0065, + "step": 39969 + }, + { + "epoch": 12.34, + "learning_rate": 6.750080205313239e-06, + "loss": 0.0062, + "step": 39970 + }, + { + "epoch": 12.34, + "learning_rate": 6.749607239184337e-06, + "loss": 0.0073, + "step": 39971 + }, + { + "epoch": 12.34, + "learning_rate": 6.749134281185257e-06, + "loss": 0.0071, + "step": 39972 + }, + { + "epoch": 12.34, + "learning_rate": 6.748661331317184e-06, + "loss": 0.0071, + "step": 39973 + }, + { + "epoch": 12.34, + "learning_rate": 6.748188389581307e-06, + "loss": 0.0061, + "step": 39974 + }, + { + "epoch": 12.35, + "learning_rate": 6.7477154559788e-06, + "loss": 0.006, + "step": 39975 + }, + { + "epoch": 12.35, + "learning_rate": 6.747242530510849e-06, + "loss": 0.0061, + "step": 39976 + }, + { + "epoch": 12.35, + "learning_rate": 6.746769613178639e-06, + "loss": 0.0062, + "step": 39977 + }, + { + "epoch": 12.35, + "learning_rate": 6.746296703983355e-06, + "loss": 0.006, + "step": 39978 + }, + { + "epoch": 12.35, + "learning_rate": 6.745823802926172e-06, + "loss": 0.007, + "step": 39979 + }, + { + "epoch": 12.35, + "learning_rate": 6.745350910008278e-06, + "loss": 0.0065, + "step": 39980 + }, + { + "epoch": 12.35, + "learning_rate": 6.744878025230859e-06, + "loss": 0.0073, + "step": 39981 + }, + { + "epoch": 12.35, + "learning_rate": 6.74440514859509e-06, + "loss": 0.007, + "step": 39982 + }, + { + "epoch": 12.35, + "learning_rate": 6.743932280102155e-06, + "loss": 0.0058, + "step": 39983 + }, + { + "epoch": 12.35, + "learning_rate": 6.7434594197532446e-06, + "loss": 0.0048, + "step": 39984 + }, + { + "epoch": 12.35, + "learning_rate": 6.742986567549534e-06, + "loss": 0.0068, + "step": 39985 + }, + { + "epoch": 12.35, + "learning_rate": 6.742513723492206e-06, + "loss": 0.0064, + "step": 39986 + }, + { + "epoch": 12.35, + "learning_rate": 6.742040887582448e-06, + "loss": 0.0062, + "step": 39987 + }, + { + "epoch": 12.35, + "learning_rate": 6.741568059821439e-06, + "loss": 0.0067, + "step": 39988 + }, + { + "epoch": 12.35, + "learning_rate": 6.74109524021036e-06, + "loss": 0.0074, + "step": 39989 + }, + { + "epoch": 12.35, + "learning_rate": 6.740622428750402e-06, + "loss": 0.0073, + "step": 39990 + }, + { + "epoch": 12.35, + "learning_rate": 6.740149625442738e-06, + "loss": 0.0068, + "step": 39991 + }, + { + "epoch": 12.35, + "learning_rate": 6.739676830288555e-06, + "loss": 0.0081, + "step": 39992 + }, + { + "epoch": 12.35, + "learning_rate": 6.7392040432890374e-06, + "loss": 0.0057, + "step": 39993 + }, + { + "epoch": 12.35, + "learning_rate": 6.738731264445359e-06, + "loss": 0.008, + "step": 39994 + }, + { + "epoch": 12.35, + "learning_rate": 6.738258493758713e-06, + "loss": 0.0053, + "step": 39995 + }, + { + "epoch": 12.35, + "learning_rate": 6.7377857312302796e-06, + "loss": 0.0072, + "step": 39996 + }, + { + "epoch": 12.35, + "learning_rate": 6.737312976861233e-06, + "loss": 0.0073, + "step": 39997 + }, + { + "epoch": 12.35, + "learning_rate": 6.736840230652766e-06, + "loss": 0.0063, + "step": 39998 + }, + { + "epoch": 12.35, + "learning_rate": 6.736367492606057e-06, + "loss": 0.0058, + "step": 39999 + }, + { + "epoch": 12.35, + "learning_rate": 6.735894762722284e-06, + "loss": 0.006, + "step": 40000 + }, + { + "epoch": 12.35, + "learning_rate": 6.735422041002636e-06, + "loss": 0.007, + "step": 40001 + }, + { + "epoch": 12.35, + "learning_rate": 6.734949327448296e-06, + "loss": 0.0084, + "step": 40002 + }, + { + "epoch": 12.35, + "learning_rate": 6.73447662206044e-06, + "loss": 0.0094, + "step": 40003 + }, + { + "epoch": 12.35, + "learning_rate": 6.734003924840251e-06, + "loss": 0.0081, + "step": 40004 + }, + { + "epoch": 12.35, + "learning_rate": 6.73353123578892e-06, + "loss": 0.0069, + "step": 40005 + }, + { + "epoch": 12.35, + "learning_rate": 6.733058554907619e-06, + "loss": 0.0074, + "step": 40006 + }, + { + "epoch": 12.35, + "learning_rate": 6.732585882197533e-06, + "loss": 0.0099, + "step": 40007 + }, + { + "epoch": 12.36, + "learning_rate": 6.73211321765985e-06, + "loss": 0.007, + "step": 40008 + }, + { + "epoch": 12.36, + "learning_rate": 6.731640561295747e-06, + "loss": 0.0069, + "step": 40009 + }, + { + "epoch": 12.36, + "learning_rate": 6.7311679131064034e-06, + "loss": 0.0067, + "step": 40010 + }, + { + "epoch": 12.36, + "learning_rate": 6.7306952730930075e-06, + "loss": 0.0067, + "step": 40011 + }, + { + "epoch": 12.36, + "learning_rate": 6.730222641256741e-06, + "loss": 0.0057, + "step": 40012 + }, + { + "epoch": 12.36, + "learning_rate": 6.729750017598782e-06, + "loss": 0.0087, + "step": 40013 + }, + { + "epoch": 12.36, + "learning_rate": 6.7292774021203135e-06, + "loss": 0.0067, + "step": 40014 + }, + { + "epoch": 12.36, + "learning_rate": 6.728804794822521e-06, + "loss": 0.0062, + "step": 40015 + }, + { + "epoch": 12.36, + "learning_rate": 6.728332195706584e-06, + "loss": 0.0069, + "step": 40016 + }, + { + "epoch": 12.36, + "learning_rate": 6.727859604773681e-06, + "loss": 0.0088, + "step": 40017 + }, + { + "epoch": 12.36, + "learning_rate": 6.727387022025005e-06, + "loss": 0.0064, + "step": 40018 + }, + { + "epoch": 12.36, + "learning_rate": 6.726914447461726e-06, + "loss": 0.0049, + "step": 40019 + }, + { + "epoch": 12.36, + "learning_rate": 6.7264418810850305e-06, + "loss": 0.0079, + "step": 40020 + }, + { + "epoch": 12.36, + "learning_rate": 6.725969322896107e-06, + "loss": 0.0071, + "step": 40021 + }, + { + "epoch": 12.36, + "learning_rate": 6.725496772896124e-06, + "loss": 0.0074, + "step": 40022 + }, + { + "epoch": 12.36, + "learning_rate": 6.725024231086273e-06, + "loss": 0.006, + "step": 40023 + }, + { + "epoch": 12.36, + "learning_rate": 6.724551697467737e-06, + "loss": 0.0056, + "step": 40024 + }, + { + "epoch": 12.36, + "learning_rate": 6.72407917204169e-06, + "loss": 0.0082, + "step": 40025 + }, + { + "epoch": 12.36, + "learning_rate": 6.723606654809321e-06, + "loss": 0.006, + "step": 40026 + }, + { + "epoch": 12.36, + "learning_rate": 6.72313414577181e-06, + "loss": 0.007, + "step": 40027 + }, + { + "epoch": 12.36, + "learning_rate": 6.722661644930335e-06, + "loss": 0.0062, + "step": 40028 + }, + { + "epoch": 12.36, + "learning_rate": 6.722189152286083e-06, + "loss": 0.0073, + "step": 40029 + }, + { + "epoch": 12.36, + "learning_rate": 6.7217166678402355e-06, + "loss": 0.0059, + "step": 40030 + }, + { + "epoch": 12.36, + "learning_rate": 6.721244191593971e-06, + "loss": 0.0055, + "step": 40031 + }, + { + "epoch": 12.36, + "learning_rate": 6.72077172354847e-06, + "loss": 0.0068, + "step": 40032 + }, + { + "epoch": 12.36, + "learning_rate": 6.720299263704921e-06, + "loss": 0.0063, + "step": 40033 + }, + { + "epoch": 12.36, + "learning_rate": 6.719826812064501e-06, + "loss": 0.0059, + "step": 40034 + }, + { + "epoch": 12.36, + "learning_rate": 6.71935436862839e-06, + "loss": 0.007, + "step": 40035 + }, + { + "epoch": 12.36, + "learning_rate": 6.718881933397777e-06, + "loss": 0.0067, + "step": 40036 + }, + { + "epoch": 12.36, + "learning_rate": 6.718409506373834e-06, + "loss": 0.0069, + "step": 40037 + }, + { + "epoch": 12.36, + "learning_rate": 6.717937087557747e-06, + "loss": 0.0069, + "step": 40038 + }, + { + "epoch": 12.36, + "learning_rate": 6.717464676950702e-06, + "loss": 0.0079, + "step": 40039 + }, + { + "epoch": 12.37, + "learning_rate": 6.716992274553874e-06, + "loss": 0.0059, + "step": 40040 + }, + { + "epoch": 12.37, + "learning_rate": 6.7165198803684476e-06, + "loss": 0.0074, + "step": 40041 + }, + { + "epoch": 12.37, + "learning_rate": 6.716047494395605e-06, + "loss": 0.007, + "step": 40042 + }, + { + "epoch": 12.37, + "learning_rate": 6.715575116636524e-06, + "loss": 0.0065, + "step": 40043 + }, + { + "epoch": 12.37, + "learning_rate": 6.71510274709239e-06, + "loss": 0.0082, + "step": 40044 + }, + { + "epoch": 12.37, + "learning_rate": 6.71463038576438e-06, + "loss": 0.0071, + "step": 40045 + }, + { + "epoch": 12.37, + "learning_rate": 6.7141580326536835e-06, + "loss": 0.0063, + "step": 40046 + }, + { + "epoch": 12.37, + "learning_rate": 6.713685687761475e-06, + "loss": 0.0065, + "step": 40047 + }, + { + "epoch": 12.37, + "learning_rate": 6.713213351088936e-06, + "loss": 0.007, + "step": 40048 + }, + { + "epoch": 12.37, + "learning_rate": 6.712741022637254e-06, + "loss": 0.0064, + "step": 40049 + }, + { + "epoch": 12.37, + "learning_rate": 6.712268702407605e-06, + "loss": 0.0074, + "step": 40050 + }, + { + "epoch": 12.37, + "learning_rate": 6.7117963904011706e-06, + "loss": 0.0077, + "step": 40051 + }, + { + "epoch": 12.37, + "learning_rate": 6.711324086619136e-06, + "loss": 0.0057, + "step": 40052 + }, + { + "epoch": 12.37, + "learning_rate": 6.710851791062676e-06, + "loss": 0.0069, + "step": 40053 + }, + { + "epoch": 12.37, + "learning_rate": 6.710379503732977e-06, + "loss": 0.0063, + "step": 40054 + }, + { + "epoch": 12.37, + "learning_rate": 6.70990722463122e-06, + "loss": 0.0065, + "step": 40055 + }, + { + "epoch": 12.37, + "learning_rate": 6.709434953758582e-06, + "loss": 0.0066, + "step": 40056 + }, + { + "epoch": 12.37, + "learning_rate": 6.708962691116248e-06, + "loss": 0.0051, + "step": 40057 + }, + { + "epoch": 12.37, + "learning_rate": 6.708490436705403e-06, + "loss": 0.0064, + "step": 40058 + }, + { + "epoch": 12.37, + "learning_rate": 6.708018190527218e-06, + "loss": 0.0077, + "step": 40059 + }, + { + "epoch": 12.37, + "learning_rate": 6.707545952582883e-06, + "loss": 0.0072, + "step": 40060 + }, + { + "epoch": 12.37, + "learning_rate": 6.707073722873576e-06, + "loss": 0.0068, + "step": 40061 + }, + { + "epoch": 12.37, + "learning_rate": 6.706601501400479e-06, + "loss": 0.006, + "step": 40062 + }, + { + "epoch": 12.37, + "learning_rate": 6.706129288164769e-06, + "loss": 0.0057, + "step": 40063 + }, + { + "epoch": 12.37, + "learning_rate": 6.705657083167634e-06, + "loss": 0.0076, + "step": 40064 + }, + { + "epoch": 12.37, + "learning_rate": 6.70518488641025e-06, + "loss": 0.0057, + "step": 40065 + }, + { + "epoch": 12.37, + "learning_rate": 6.704712697893796e-06, + "loss": 0.0067, + "step": 40066 + }, + { + "epoch": 12.37, + "learning_rate": 6.704240517619463e-06, + "loss": 0.0056, + "step": 40067 + }, + { + "epoch": 12.37, + "learning_rate": 6.703768345588422e-06, + "loss": 0.0063, + "step": 40068 + }, + { + "epoch": 12.37, + "learning_rate": 6.703296181801856e-06, + "loss": 0.0064, + "step": 40069 + }, + { + "epoch": 12.37, + "learning_rate": 6.702824026260955e-06, + "loss": 0.0077, + "step": 40070 + }, + { + "epoch": 12.37, + "learning_rate": 6.702351878966884e-06, + "loss": 0.0061, + "step": 40071 + }, + { + "epoch": 12.37, + "learning_rate": 6.701879739920835e-06, + "loss": 0.0065, + "step": 40072 + }, + { + "epoch": 12.38, + "learning_rate": 6.7014076091239886e-06, + "loss": 0.0078, + "step": 40073 + }, + { + "epoch": 12.38, + "learning_rate": 6.70093548657752e-06, + "loss": 0.0066, + "step": 40074 + }, + { + "epoch": 12.38, + "learning_rate": 6.700463372282615e-06, + "loss": 0.0074, + "step": 40075 + }, + { + "epoch": 12.38, + "learning_rate": 6.699991266240451e-06, + "loss": 0.0062, + "step": 40076 + }, + { + "epoch": 12.38, + "learning_rate": 6.699519168452216e-06, + "loss": 0.0068, + "step": 40077 + }, + { + "epoch": 12.38, + "learning_rate": 6.699047078919081e-06, + "loss": 0.0065, + "step": 40078 + }, + { + "epoch": 12.38, + "learning_rate": 6.698574997642231e-06, + "loss": 0.0064, + "step": 40079 + }, + { + "epoch": 12.38, + "learning_rate": 6.6981029246228524e-06, + "loss": 0.0058, + "step": 40080 + }, + { + "epoch": 12.38, + "learning_rate": 6.697630859862115e-06, + "loss": 0.0067, + "step": 40081 + }, + { + "epoch": 12.38, + "learning_rate": 6.697158803361206e-06, + "loss": 0.0056, + "step": 40082 + }, + { + "epoch": 12.38, + "learning_rate": 6.696686755121309e-06, + "loss": 0.0073, + "step": 40083 + }, + { + "epoch": 12.38, + "learning_rate": 6.696214715143596e-06, + "loss": 0.0085, + "step": 40084 + }, + { + "epoch": 12.38, + "learning_rate": 6.6957426834292535e-06, + "loss": 0.0064, + "step": 40085 + }, + { + "epoch": 12.38, + "learning_rate": 6.6952706599794645e-06, + "loss": 0.0073, + "step": 40086 + }, + { + "epoch": 12.38, + "learning_rate": 6.6947986447954025e-06, + "loss": 0.0081, + "step": 40087 + }, + { + "epoch": 12.38, + "learning_rate": 6.694326637878254e-06, + "loss": 0.0066, + "step": 40088 + }, + { + "epoch": 12.38, + "learning_rate": 6.693854639229199e-06, + "loss": 0.006, + "step": 40089 + }, + { + "epoch": 12.38, + "learning_rate": 6.693382648849415e-06, + "loss": 0.0077, + "step": 40090 + }, + { + "epoch": 12.38, + "learning_rate": 6.692910666740083e-06, + "loss": 0.0081, + "step": 40091 + }, + { + "epoch": 12.38, + "learning_rate": 6.6924386929023855e-06, + "loss": 0.0061, + "step": 40092 + }, + { + "epoch": 12.38, + "learning_rate": 6.6919667273375026e-06, + "loss": 0.008, + "step": 40093 + }, + { + "epoch": 12.38, + "learning_rate": 6.691494770046612e-06, + "loss": 0.0061, + "step": 40094 + }, + { + "epoch": 12.38, + "learning_rate": 6.691022821030899e-06, + "loss": 0.0078, + "step": 40095 + }, + { + "epoch": 12.38, + "learning_rate": 6.690550880291541e-06, + "loss": 0.0067, + "step": 40096 + }, + { + "epoch": 12.38, + "learning_rate": 6.690078947829717e-06, + "loss": 0.0063, + "step": 40097 + }, + { + "epoch": 12.38, + "learning_rate": 6.6896070236466114e-06, + "loss": 0.0061, + "step": 40098 + }, + { + "epoch": 12.38, + "learning_rate": 6.689135107743402e-06, + "loss": 0.0111, + "step": 40099 + }, + { + "epoch": 12.38, + "learning_rate": 6.688663200121268e-06, + "loss": 0.0076, + "step": 40100 + }, + { + "epoch": 12.38, + "learning_rate": 6.688191300781395e-06, + "loss": 0.0076, + "step": 40101 + }, + { + "epoch": 12.38, + "learning_rate": 6.687719409724955e-06, + "loss": 0.0099, + "step": 40102 + }, + { + "epoch": 12.38, + "learning_rate": 6.687247526953136e-06, + "loss": 0.0081, + "step": 40103 + }, + { + "epoch": 12.38, + "learning_rate": 6.686775652467114e-06, + "loss": 0.0078, + "step": 40104 + }, + { + "epoch": 12.39, + "learning_rate": 6.686303786268069e-06, + "loss": 0.007, + "step": 40105 + }, + { + "epoch": 12.39, + "learning_rate": 6.685831928357185e-06, + "loss": 0.006, + "step": 40106 + }, + { + "epoch": 12.39, + "learning_rate": 6.685360078735641e-06, + "loss": 0.0066, + "step": 40107 + }, + { + "epoch": 12.39, + "learning_rate": 6.684888237404612e-06, + "loss": 0.0071, + "step": 40108 + }, + { + "epoch": 12.39, + "learning_rate": 6.6844164043652835e-06, + "loss": 0.006, + "step": 40109 + }, + { + "epoch": 12.39, + "learning_rate": 6.683944579618833e-06, + "loss": 0.0076, + "step": 40110 + }, + { + "epoch": 12.39, + "learning_rate": 6.683472763166448e-06, + "loss": 0.0069, + "step": 40111 + }, + { + "epoch": 12.39, + "learning_rate": 6.683000955009296e-06, + "loss": 0.0067, + "step": 40112 + }, + { + "epoch": 12.39, + "learning_rate": 6.682529155148565e-06, + "loss": 0.0074, + "step": 40113 + }, + { + "epoch": 12.39, + "learning_rate": 6.6820573635854365e-06, + "loss": 0.0064, + "step": 40114 + }, + { + "epoch": 12.39, + "learning_rate": 6.681585580321084e-06, + "loss": 0.0068, + "step": 40115 + }, + { + "epoch": 12.39, + "learning_rate": 6.681113805356693e-06, + "loss": 0.0065, + "step": 40116 + }, + { + "epoch": 12.39, + "learning_rate": 6.680642038693443e-06, + "loss": 0.0054, + "step": 40117 + }, + { + "epoch": 12.39, + "learning_rate": 6.680170280332509e-06, + "loss": 0.0064, + "step": 40118 + }, + { + "epoch": 12.39, + "learning_rate": 6.6796985302750775e-06, + "loss": 0.0077, + "step": 40119 + }, + { + "epoch": 12.39, + "learning_rate": 6.679226788522326e-06, + "loss": 0.006, + "step": 40120 + }, + { + "epoch": 12.39, + "learning_rate": 6.678755055075435e-06, + "loss": 0.0066, + "step": 40121 + }, + { + "epoch": 12.39, + "learning_rate": 6.678283329935578e-06, + "loss": 0.0068, + "step": 40122 + }, + { + "epoch": 12.39, + "learning_rate": 6.677811613103946e-06, + "loss": 0.0074, + "step": 40123 + }, + { + "epoch": 12.39, + "learning_rate": 6.67733990458171e-06, + "loss": 0.008, + "step": 40124 + }, + { + "epoch": 12.39, + "learning_rate": 6.676868204370052e-06, + "loss": 0.006, + "step": 40125 + }, + { + "epoch": 12.39, + "learning_rate": 6.676396512470156e-06, + "loss": 0.0073, + "step": 40126 + }, + { + "epoch": 12.39, + "learning_rate": 6.675924828883196e-06, + "loss": 0.0078, + "step": 40127 + }, + { + "epoch": 12.39, + "learning_rate": 6.675453153610354e-06, + "loss": 0.0056, + "step": 40128 + }, + { + "epoch": 12.39, + "learning_rate": 6.674981486652814e-06, + "loss": 0.0066, + "step": 40129 + }, + { + "epoch": 12.39, + "learning_rate": 6.674509828011747e-06, + "loss": 0.0044, + "step": 40130 + }, + { + "epoch": 12.39, + "learning_rate": 6.67403817768834e-06, + "loss": 0.0067, + "step": 40131 + }, + { + "epoch": 12.39, + "learning_rate": 6.673566535683771e-06, + "loss": 0.0073, + "step": 40132 + }, + { + "epoch": 12.39, + "learning_rate": 6.673094901999216e-06, + "loss": 0.0095, + "step": 40133 + }, + { + "epoch": 12.39, + "learning_rate": 6.672623276635857e-06, + "loss": 0.0074, + "step": 40134 + }, + { + "epoch": 12.39, + "learning_rate": 6.672151659594878e-06, + "loss": 0.0059, + "step": 40135 + }, + { + "epoch": 12.39, + "learning_rate": 6.67168005087745e-06, + "loss": 0.0066, + "step": 40136 + }, + { + "epoch": 12.4, + "learning_rate": 6.671208450484761e-06, + "loss": 0.0069, + "step": 40137 + }, + { + "epoch": 12.4, + "learning_rate": 6.670736858417986e-06, + "loss": 0.0063, + "step": 40138 + }, + { + "epoch": 12.4, + "learning_rate": 6.670265274678304e-06, + "loss": 0.0078, + "step": 40139 + }, + { + "epoch": 12.4, + "learning_rate": 6.669793699266895e-06, + "loss": 0.0066, + "step": 40140 + }, + { + "epoch": 12.4, + "learning_rate": 6.669322132184941e-06, + "loss": 0.0065, + "step": 40141 + }, + { + "epoch": 12.4, + "learning_rate": 6.668850573433623e-06, + "loss": 0.0053, + "step": 40142 + }, + { + "epoch": 12.4, + "learning_rate": 6.668379023014111e-06, + "loss": 0.0081, + "step": 40143 + }, + { + "epoch": 12.4, + "learning_rate": 6.6679074809275936e-06, + "loss": 0.0066, + "step": 40144 + }, + { + "epoch": 12.4, + "learning_rate": 6.667435947175249e-06, + "loss": 0.0078, + "step": 40145 + }, + { + "epoch": 12.4, + "learning_rate": 6.666964421758253e-06, + "loss": 0.0065, + "step": 40146 + }, + { + "epoch": 12.4, + "learning_rate": 6.666492904677786e-06, + "loss": 0.0063, + "step": 40147 + }, + { + "epoch": 12.4, + "learning_rate": 6.666021395935032e-06, + "loss": 0.0064, + "step": 40148 + }, + { + "epoch": 12.4, + "learning_rate": 6.665549895531163e-06, + "loss": 0.0062, + "step": 40149 + }, + { + "epoch": 12.4, + "learning_rate": 6.665078403467362e-06, + "loss": 0.0065, + "step": 40150 + }, + { + "epoch": 12.4, + "learning_rate": 6.664606919744811e-06, + "loss": 0.0075, + "step": 40151 + }, + { + "epoch": 12.4, + "learning_rate": 6.664135444364685e-06, + "loss": 0.0071, + "step": 40152 + }, + { + "epoch": 12.4, + "learning_rate": 6.663663977328162e-06, + "loss": 0.0065, + "step": 40153 + }, + { + "epoch": 12.4, + "learning_rate": 6.663192518636428e-06, + "loss": 0.0058, + "step": 40154 + }, + { + "epoch": 12.4, + "learning_rate": 6.662721068290656e-06, + "loss": 0.0074, + "step": 40155 + }, + { + "epoch": 12.4, + "learning_rate": 6.662249626292025e-06, + "loss": 0.0073, + "step": 40156 + }, + { + "epoch": 12.4, + "learning_rate": 6.6617781926417215e-06, + "loss": 0.0057, + "step": 40157 + }, + { + "epoch": 12.4, + "learning_rate": 6.661306767340917e-06, + "loss": 0.0078, + "step": 40158 + }, + { + "epoch": 12.4, + "learning_rate": 6.660835350390791e-06, + "loss": 0.0074, + "step": 40159 + }, + { + "epoch": 12.4, + "learning_rate": 6.660363941792532e-06, + "loss": 0.0071, + "step": 40160 + }, + { + "epoch": 12.4, + "learning_rate": 6.659892541547304e-06, + "loss": 0.0066, + "step": 40161 + }, + { + "epoch": 12.4, + "learning_rate": 6.659421149656298e-06, + "loss": 0.0074, + "step": 40162 + }, + { + "epoch": 12.4, + "learning_rate": 6.658949766120689e-06, + "loss": 0.0068, + "step": 40163 + }, + { + "epoch": 12.4, + "learning_rate": 6.658478390941654e-06, + "loss": 0.0057, + "step": 40164 + }, + { + "epoch": 12.4, + "learning_rate": 6.658007024120374e-06, + "loss": 0.0092, + "step": 40165 + }, + { + "epoch": 12.4, + "learning_rate": 6.6575356656580306e-06, + "loss": 0.0069, + "step": 40166 + }, + { + "epoch": 12.4, + "learning_rate": 6.657064315555797e-06, + "loss": 0.0063, + "step": 40167 + }, + { + "epoch": 12.4, + "learning_rate": 6.656592973814857e-06, + "loss": 0.0069, + "step": 40168 + }, + { + "epoch": 12.4, + "learning_rate": 6.656121640436388e-06, + "loss": 0.0069, + "step": 40169 + }, + { + "epoch": 12.41, + "learning_rate": 6.655650315421569e-06, + "loss": 0.0066, + "step": 40170 + }, + { + "epoch": 12.41, + "learning_rate": 6.6551789987715755e-06, + "loss": 0.0075, + "step": 40171 + }, + { + "epoch": 12.41, + "learning_rate": 6.654707690487594e-06, + "loss": 0.0072, + "step": 40172 + }, + { + "epoch": 12.41, + "learning_rate": 6.654236390570797e-06, + "loss": 0.0058, + "step": 40173 + }, + { + "epoch": 12.41, + "learning_rate": 6.653765099022361e-06, + "loss": 0.0085, + "step": 40174 + }, + { + "epoch": 12.41, + "learning_rate": 6.6532938158434725e-06, + "loss": 0.0075, + "step": 40175 + }, + { + "epoch": 12.41, + "learning_rate": 6.652822541035309e-06, + "loss": 0.0063, + "step": 40176 + }, + { + "epoch": 12.41, + "learning_rate": 6.6523512745990404e-06, + "loss": 0.0065, + "step": 40177 + }, + { + "epoch": 12.41, + "learning_rate": 6.651880016535855e-06, + "loss": 0.0069, + "step": 40178 + }, + { + "epoch": 12.41, + "learning_rate": 6.6514087668469315e-06, + "loss": 0.0069, + "step": 40179 + }, + { + "epoch": 12.41, + "learning_rate": 6.650937525533443e-06, + "loss": 0.0074, + "step": 40180 + }, + { + "epoch": 12.41, + "learning_rate": 6.650466292596568e-06, + "loss": 0.0069, + "step": 40181 + }, + { + "epoch": 12.41, + "learning_rate": 6.6499950680374916e-06, + "loss": 0.0078, + "step": 40182 + }, + { + "epoch": 12.41, + "learning_rate": 6.649523851857387e-06, + "loss": 0.0085, + "step": 40183 + }, + { + "epoch": 12.41, + "learning_rate": 6.649052644057432e-06, + "loss": 0.0057, + "step": 40184 + }, + { + "epoch": 12.41, + "learning_rate": 6.648581444638812e-06, + "loss": 0.0071, + "step": 40185 + }, + { + "epoch": 12.41, + "learning_rate": 6.648110253602698e-06, + "loss": 0.0074, + "step": 40186 + }, + { + "epoch": 12.41, + "learning_rate": 6.647639070950271e-06, + "loss": 0.0053, + "step": 40187 + }, + { + "epoch": 12.41, + "learning_rate": 6.647167896682714e-06, + "loss": 0.006, + "step": 40188 + }, + { + "epoch": 12.41, + "learning_rate": 6.646696730801198e-06, + "loss": 0.0069, + "step": 40189 + }, + { + "epoch": 12.41, + "learning_rate": 6.646225573306907e-06, + "loss": 0.0054, + "step": 40190 + }, + { + "epoch": 12.41, + "learning_rate": 6.6457544242010185e-06, + "loss": 0.0063, + "step": 40191 + }, + { + "epoch": 12.41, + "learning_rate": 6.645283283484707e-06, + "loss": 0.0085, + "step": 40192 + }, + { + "epoch": 12.41, + "learning_rate": 6.644812151159155e-06, + "loss": 0.0067, + "step": 40193 + }, + { + "epoch": 12.41, + "learning_rate": 6.64434102722554e-06, + "loss": 0.0076, + "step": 40194 + }, + { + "epoch": 12.41, + "learning_rate": 6.6438699116850394e-06, + "loss": 0.007, + "step": 40195 + }, + { + "epoch": 12.41, + "learning_rate": 6.643398804538832e-06, + "loss": 0.0067, + "step": 40196 + }, + { + "epoch": 12.41, + "learning_rate": 6.6429277057881e-06, + "loss": 0.0066, + "step": 40197 + }, + { + "epoch": 12.41, + "learning_rate": 6.642456615434013e-06, + "loss": 0.0078, + "step": 40198 + }, + { + "epoch": 12.41, + "learning_rate": 6.641985533477757e-06, + "loss": 0.0065, + "step": 40199 + }, + { + "epoch": 12.41, + "learning_rate": 6.641514459920509e-06, + "loss": 0.0068, + "step": 40200 + }, + { + "epoch": 12.41, + "learning_rate": 6.6410433947634445e-06, + "loss": 0.0061, + "step": 40201 + }, + { + "epoch": 12.42, + "learning_rate": 6.64057233800774e-06, + "loss": 0.0071, + "step": 40202 + }, + { + "epoch": 12.42, + "learning_rate": 6.640101289654581e-06, + "loss": 0.0065, + "step": 40203 + }, + { + "epoch": 12.42, + "learning_rate": 6.639630249705141e-06, + "loss": 0.0068, + "step": 40204 + }, + { + "epoch": 12.42, + "learning_rate": 6.639159218160596e-06, + "loss": 0.0052, + "step": 40205 + }, + { + "epoch": 12.42, + "learning_rate": 6.638688195022128e-06, + "loss": 0.0066, + "step": 40206 + }, + { + "epoch": 12.42, + "learning_rate": 6.638217180290917e-06, + "loss": 0.0073, + "step": 40207 + }, + { + "epoch": 12.42, + "learning_rate": 6.637746173968134e-06, + "loss": 0.0092, + "step": 40208 + }, + { + "epoch": 12.42, + "learning_rate": 6.637275176054961e-06, + "loss": 0.0066, + "step": 40209 + }, + { + "epoch": 12.42, + "learning_rate": 6.63680418655258e-06, + "loss": 0.0058, + "step": 40210 + }, + { + "epoch": 12.42, + "learning_rate": 6.636333205462162e-06, + "loss": 0.0071, + "step": 40211 + }, + { + "epoch": 12.42, + "learning_rate": 6.6358622327848875e-06, + "loss": 0.0069, + "step": 40212 + }, + { + "epoch": 12.42, + "learning_rate": 6.635391268521938e-06, + "loss": 0.0085, + "step": 40213 + }, + { + "epoch": 12.42, + "learning_rate": 6.634920312674488e-06, + "loss": 0.007, + "step": 40214 + }, + { + "epoch": 12.42, + "learning_rate": 6.634449365243714e-06, + "loss": 0.007, + "step": 40215 + }, + { + "epoch": 12.42, + "learning_rate": 6.6339784262307985e-06, + "loss": 0.0062, + "step": 40216 + }, + { + "epoch": 12.42, + "learning_rate": 6.633507495636915e-06, + "loss": 0.0072, + "step": 40217 + }, + { + "epoch": 12.42, + "learning_rate": 6.633036573463242e-06, + "loss": 0.007, + "step": 40218 + }, + { + "epoch": 12.42, + "learning_rate": 6.632565659710965e-06, + "loss": 0.0062, + "step": 40219 + }, + { + "epoch": 12.42, + "learning_rate": 6.6320947543812485e-06, + "loss": 0.0069, + "step": 40220 + }, + { + "epoch": 12.42, + "learning_rate": 6.631623857475279e-06, + "loss": 0.0068, + "step": 40221 + }, + { + "epoch": 12.42, + "learning_rate": 6.631152968994235e-06, + "loss": 0.0074, + "step": 40222 + }, + { + "epoch": 12.42, + "learning_rate": 6.6306820889392885e-06, + "loss": 0.0087, + "step": 40223 + }, + { + "epoch": 12.42, + "learning_rate": 6.630211217311622e-06, + "loss": 0.0077, + "step": 40224 + }, + { + "epoch": 12.42, + "learning_rate": 6.629740354112414e-06, + "loss": 0.0063, + "step": 40225 + }, + { + "epoch": 12.42, + "learning_rate": 6.629269499342836e-06, + "loss": 0.0061, + "step": 40226 + }, + { + "epoch": 12.42, + "learning_rate": 6.628798653004072e-06, + "loss": 0.0077, + "step": 40227 + }, + { + "epoch": 12.42, + "learning_rate": 6.6283278150973e-06, + "loss": 0.0079, + "step": 40228 + }, + { + "epoch": 12.42, + "learning_rate": 6.627856985623692e-06, + "loss": 0.0063, + "step": 40229 + }, + { + "epoch": 12.42, + "learning_rate": 6.627386164584426e-06, + "loss": 0.0066, + "step": 40230 + }, + { + "epoch": 12.42, + "learning_rate": 6.626915351980688e-06, + "loss": 0.0073, + "step": 40231 + }, + { + "epoch": 12.42, + "learning_rate": 6.6264445478136485e-06, + "loss": 0.0067, + "step": 40232 + }, + { + "epoch": 12.42, + "learning_rate": 6.6259737520844825e-06, + "loss": 0.006, + "step": 40233 + }, + { + "epoch": 12.43, + "learning_rate": 6.625502964794377e-06, + "loss": 0.0061, + "step": 40234 + }, + { + "epoch": 12.43, + "learning_rate": 6.625032185944501e-06, + "loss": 0.0074, + "step": 40235 + }, + { + "epoch": 12.43, + "learning_rate": 6.6245614155360325e-06, + "loss": 0.0063, + "step": 40236 + }, + { + "epoch": 12.43, + "learning_rate": 6.624090653570158e-06, + "loss": 0.0066, + "step": 40237 + }, + { + "epoch": 12.43, + "learning_rate": 6.623619900048044e-06, + "loss": 0.0065, + "step": 40238 + }, + { + "epoch": 12.43, + "learning_rate": 6.623149154970874e-06, + "loss": 0.0058, + "step": 40239 + }, + { + "epoch": 12.43, + "learning_rate": 6.622678418339821e-06, + "loss": 0.0071, + "step": 40240 + }, + { + "epoch": 12.43, + "learning_rate": 6.6222076901560705e-06, + "loss": 0.0068, + "step": 40241 + }, + { + "epoch": 12.43, + "learning_rate": 6.621736970420791e-06, + "loss": 0.0078, + "step": 40242 + }, + { + "epoch": 12.43, + "learning_rate": 6.621266259135162e-06, + "loss": 0.0074, + "step": 40243 + }, + { + "epoch": 12.43, + "learning_rate": 6.620795556300368e-06, + "loss": 0.0075, + "step": 40244 + }, + { + "epoch": 12.43, + "learning_rate": 6.620324861917577e-06, + "loss": 0.0062, + "step": 40245 + }, + { + "epoch": 12.43, + "learning_rate": 6.619854175987968e-06, + "loss": 0.0072, + "step": 40246 + }, + { + "epoch": 12.43, + "learning_rate": 6.619383498512724e-06, + "loss": 0.0078, + "step": 40247 + }, + { + "epoch": 12.43, + "learning_rate": 6.618912829493016e-06, + "loss": 0.0093, + "step": 40248 + }, + { + "epoch": 12.43, + "learning_rate": 6.618442168930026e-06, + "loss": 0.0075, + "step": 40249 + }, + { + "epoch": 12.43, + "learning_rate": 6.617971516824928e-06, + "loss": 0.0056, + "step": 40250 + }, + { + "epoch": 12.43, + "learning_rate": 6.617500873178898e-06, + "loss": 0.0058, + "step": 40251 + }, + { + "epoch": 12.43, + "learning_rate": 6.617030237993116e-06, + "loss": 0.0072, + "step": 40252 + }, + { + "epoch": 12.43, + "learning_rate": 6.616559611268762e-06, + "loss": 0.0068, + "step": 40253 + }, + { + "epoch": 12.43, + "learning_rate": 6.6160889930070035e-06, + "loss": 0.0068, + "step": 40254 + }, + { + "epoch": 12.43, + "learning_rate": 6.615618383209028e-06, + "loss": 0.0067, + "step": 40255 + }, + { + "epoch": 12.43, + "learning_rate": 6.615147781876009e-06, + "loss": 0.0068, + "step": 40256 + }, + { + "epoch": 12.43, + "learning_rate": 6.614677189009118e-06, + "loss": 0.0065, + "step": 40257 + }, + { + "epoch": 12.43, + "learning_rate": 6.61420660460954e-06, + "loss": 0.0107, + "step": 40258 + }, + { + "epoch": 12.43, + "learning_rate": 6.61373602867845e-06, + "loss": 0.0068, + "step": 40259 + }, + { + "epoch": 12.43, + "learning_rate": 6.613265461217022e-06, + "loss": 0.006, + "step": 40260 + }, + { + "epoch": 12.43, + "learning_rate": 6.612794902226434e-06, + "loss": 0.0067, + "step": 40261 + }, + { + "epoch": 12.43, + "learning_rate": 6.612324351707866e-06, + "loss": 0.0076, + "step": 40262 + }, + { + "epoch": 12.43, + "learning_rate": 6.611853809662492e-06, + "loss": 0.008, + "step": 40263 + }, + { + "epoch": 12.43, + "learning_rate": 6.611383276091485e-06, + "loss": 0.0067, + "step": 40264 + }, + { + "epoch": 12.43, + "learning_rate": 6.610912750996033e-06, + "loss": 0.0072, + "step": 40265 + }, + { + "epoch": 12.43, + "learning_rate": 6.610442234377303e-06, + "loss": 0.0064, + "step": 40266 + }, + { + "epoch": 12.44, + "learning_rate": 6.609971726236475e-06, + "loss": 0.0069, + "step": 40267 + }, + { + "epoch": 12.44, + "learning_rate": 6.6095012265747305e-06, + "loss": 0.0063, + "step": 40268 + }, + { + "epoch": 12.44, + "learning_rate": 6.609030735393236e-06, + "loss": 0.0084, + "step": 40269 + }, + { + "epoch": 12.44, + "learning_rate": 6.608560252693177e-06, + "loss": 0.0079, + "step": 40270 + }, + { + "epoch": 12.44, + "learning_rate": 6.608089778475728e-06, + "loss": 0.0076, + "step": 40271 + }, + { + "epoch": 12.44, + "learning_rate": 6.607619312742062e-06, + "loss": 0.0072, + "step": 40272 + }, + { + "epoch": 12.44, + "learning_rate": 6.607148855493362e-06, + "loss": 0.0067, + "step": 40273 + }, + { + "epoch": 12.44, + "learning_rate": 6.606678406730798e-06, + "loss": 0.0066, + "step": 40274 + }, + { + "epoch": 12.44, + "learning_rate": 6.606207966455554e-06, + "loss": 0.0078, + "step": 40275 + }, + { + "epoch": 12.44, + "learning_rate": 6.605737534668801e-06, + "loss": 0.0072, + "step": 40276 + }, + { + "epoch": 12.44, + "learning_rate": 6.605267111371716e-06, + "loss": 0.0071, + "step": 40277 + }, + { + "epoch": 12.44, + "learning_rate": 6.604796696565483e-06, + "loss": 0.0052, + "step": 40278 + }, + { + "epoch": 12.44, + "learning_rate": 6.604326290251266e-06, + "loss": 0.0073, + "step": 40279 + }, + { + "epoch": 12.44, + "learning_rate": 6.603855892430251e-06, + "loss": 0.0076, + "step": 40280 + }, + { + "epoch": 12.44, + "learning_rate": 6.603385503103614e-06, + "loss": 0.006, + "step": 40281 + }, + { + "epoch": 12.44, + "learning_rate": 6.602915122272524e-06, + "loss": 0.0062, + "step": 40282 + }, + { + "epoch": 12.44, + "learning_rate": 6.602444749938166e-06, + "loss": 0.0081, + "step": 40283 + }, + { + "epoch": 12.44, + "learning_rate": 6.601974386101715e-06, + "loss": 0.0066, + "step": 40284 + }, + { + "epoch": 12.44, + "learning_rate": 6.601504030764343e-06, + "loss": 0.007, + "step": 40285 + }, + { + "epoch": 12.44, + "learning_rate": 6.6010336839272295e-06, + "loss": 0.0054, + "step": 40286 + }, + { + "epoch": 12.44, + "learning_rate": 6.600563345591554e-06, + "loss": 0.0068, + "step": 40287 + }, + { + "epoch": 12.44, + "learning_rate": 6.600093015758486e-06, + "loss": 0.0068, + "step": 40288 + }, + { + "epoch": 12.44, + "learning_rate": 6.599622694429207e-06, + "loss": 0.0068, + "step": 40289 + }, + { + "epoch": 12.44, + "learning_rate": 6.599152381604892e-06, + "loss": 0.0075, + "step": 40290 + }, + { + "epoch": 12.44, + "learning_rate": 6.5986820772867165e-06, + "loss": 0.0063, + "step": 40291 + }, + { + "epoch": 12.44, + "learning_rate": 6.598211781475856e-06, + "loss": 0.0082, + "step": 40292 + }, + { + "epoch": 12.44, + "learning_rate": 6.597741494173492e-06, + "loss": 0.0072, + "step": 40293 + }, + { + "epoch": 12.44, + "learning_rate": 6.597271215380794e-06, + "loss": 0.007, + "step": 40294 + }, + { + "epoch": 12.44, + "learning_rate": 6.59680094509894e-06, + "loss": 0.0072, + "step": 40295 + }, + { + "epoch": 12.44, + "learning_rate": 6.596330683329113e-06, + "loss": 0.0073, + "step": 40296 + }, + { + "epoch": 12.44, + "learning_rate": 6.59586043007248e-06, + "loss": 0.006, + "step": 40297 + }, + { + "epoch": 12.44, + "learning_rate": 6.595390185330222e-06, + "loss": 0.0083, + "step": 40298 + }, + { + "epoch": 12.45, + "learning_rate": 6.5949199491035155e-06, + "loss": 0.0078, + "step": 40299 + }, + { + "epoch": 12.45, + "learning_rate": 6.594449721393531e-06, + "loss": 0.0078, + "step": 40300 + }, + { + "epoch": 12.45, + "learning_rate": 6.593979502201451e-06, + "loss": 0.0077, + "step": 40301 + }, + { + "epoch": 12.45, + "learning_rate": 6.593509291528452e-06, + "loss": 0.0061, + "step": 40302 + }, + { + "epoch": 12.45, + "learning_rate": 6.593039089375703e-06, + "loss": 0.0068, + "step": 40303 + }, + { + "epoch": 12.45, + "learning_rate": 6.592568895744387e-06, + "loss": 0.0061, + "step": 40304 + }, + { + "epoch": 12.45, + "learning_rate": 6.592098710635675e-06, + "loss": 0.0068, + "step": 40305 + }, + { + "epoch": 12.45, + "learning_rate": 6.591628534050751e-06, + "loss": 0.0073, + "step": 40306 + }, + { + "epoch": 12.45, + "learning_rate": 6.591158365990783e-06, + "loss": 0.0072, + "step": 40307 + }, + { + "epoch": 12.45, + "learning_rate": 6.59068820645695e-06, + "loss": 0.0081, + "step": 40308 + }, + { + "epoch": 12.45, + "learning_rate": 6.590218055450428e-06, + "loss": 0.007, + "step": 40309 + }, + { + "epoch": 12.45, + "learning_rate": 6.58974791297239e-06, + "loss": 0.0079, + "step": 40310 + }, + { + "epoch": 12.45, + "learning_rate": 6.589277779024017e-06, + "loss": 0.0081, + "step": 40311 + }, + { + "epoch": 12.45, + "learning_rate": 6.588807653606484e-06, + "loss": 0.0072, + "step": 40312 + }, + { + "epoch": 12.45, + "learning_rate": 6.5883375367209604e-06, + "loss": 0.0098, + "step": 40313 + }, + { + "epoch": 12.45, + "learning_rate": 6.587867428368628e-06, + "loss": 0.0067, + "step": 40314 + }, + { + "epoch": 12.45, + "learning_rate": 6.587397328550666e-06, + "loss": 0.0062, + "step": 40315 + }, + { + "epoch": 12.45, + "learning_rate": 6.586927237268239e-06, + "loss": 0.0061, + "step": 40316 + }, + { + "epoch": 12.45, + "learning_rate": 6.586457154522534e-06, + "loss": 0.0073, + "step": 40317 + }, + { + "epoch": 12.45, + "learning_rate": 6.585987080314723e-06, + "loss": 0.0073, + "step": 40318 + }, + { + "epoch": 12.45, + "learning_rate": 6.585517014645979e-06, + "loss": 0.0059, + "step": 40319 + }, + { + "epoch": 12.45, + "learning_rate": 6.585046957517478e-06, + "loss": 0.0082, + "step": 40320 + }, + { + "epoch": 12.45, + "learning_rate": 6.5845769089304014e-06, + "loss": 0.0062, + "step": 40321 + }, + { + "epoch": 12.45, + "learning_rate": 6.584106868885919e-06, + "loss": 0.0075, + "step": 40322 + }, + { + "epoch": 12.45, + "learning_rate": 6.583636837385206e-06, + "loss": 0.0063, + "step": 40323 + }, + { + "epoch": 12.45, + "learning_rate": 6.583166814429445e-06, + "loss": 0.0058, + "step": 40324 + }, + { + "epoch": 12.45, + "learning_rate": 6.5826968000198036e-06, + "loss": 0.0062, + "step": 40325 + }, + { + "epoch": 12.45, + "learning_rate": 6.58222679415746e-06, + "loss": 0.0072, + "step": 40326 + }, + { + "epoch": 12.45, + "learning_rate": 6.581756796843597e-06, + "loss": 0.0076, + "step": 40327 + }, + { + "epoch": 12.45, + "learning_rate": 6.581286808079377e-06, + "loss": 0.0064, + "step": 40328 + }, + { + "epoch": 12.45, + "learning_rate": 6.5808168278659835e-06, + "loss": 0.0064, + "step": 40329 + }, + { + "epoch": 12.45, + "learning_rate": 6.580346856204593e-06, + "loss": 0.0078, + "step": 40330 + }, + { + "epoch": 12.45, + "learning_rate": 6.579876893096376e-06, + "loss": 0.0063, + "step": 40331 + }, + { + "epoch": 12.46, + "learning_rate": 6.579406938542511e-06, + "loss": 0.0065, + "step": 40332 + }, + { + "epoch": 12.46, + "learning_rate": 6.578936992544176e-06, + "loss": 0.0073, + "step": 40333 + }, + { + "epoch": 12.46, + "learning_rate": 6.5784670551025395e-06, + "loss": 0.0065, + "step": 40334 + }, + { + "epoch": 12.46, + "learning_rate": 6.577997126218782e-06, + "loss": 0.0067, + "step": 40335 + }, + { + "epoch": 12.46, + "learning_rate": 6.577527205894081e-06, + "loss": 0.0059, + "step": 40336 + }, + { + "epoch": 12.46, + "learning_rate": 6.5770572941296075e-06, + "loss": 0.0073, + "step": 40337 + }, + { + "epoch": 12.46, + "learning_rate": 6.576587390926535e-06, + "loss": 0.0067, + "step": 40338 + }, + { + "epoch": 12.46, + "learning_rate": 6.576117496286043e-06, + "loss": 0.0065, + "step": 40339 + }, + { + "epoch": 12.46, + "learning_rate": 6.575647610209308e-06, + "loss": 0.0069, + "step": 40340 + }, + { + "epoch": 12.46, + "learning_rate": 6.5751777326975e-06, + "loss": 0.006, + "step": 40341 + }, + { + "epoch": 12.46, + "learning_rate": 6.574707863751797e-06, + "loss": 0.0067, + "step": 40342 + }, + { + "epoch": 12.46, + "learning_rate": 6.5742380033733785e-06, + "loss": 0.0062, + "step": 40343 + }, + { + "epoch": 12.46, + "learning_rate": 6.573768151563411e-06, + "loss": 0.0083, + "step": 40344 + }, + { + "epoch": 12.46, + "learning_rate": 6.573298308323075e-06, + "loss": 0.0059, + "step": 40345 + }, + { + "epoch": 12.46, + "learning_rate": 6.57282847365355e-06, + "loss": 0.0097, + "step": 40346 + }, + { + "epoch": 12.46, + "learning_rate": 6.5723586475560005e-06, + "loss": 0.0085, + "step": 40347 + }, + { + "epoch": 12.46, + "learning_rate": 6.571888830031607e-06, + "loss": 0.0057, + "step": 40348 + }, + { + "epoch": 12.46, + "learning_rate": 6.571419021081549e-06, + "loss": 0.0075, + "step": 40349 + }, + { + "epoch": 12.46, + "learning_rate": 6.570949220706995e-06, + "loss": 0.0072, + "step": 40350 + }, + { + "epoch": 12.46, + "learning_rate": 6.57047942890912e-06, + "loss": 0.0072, + "step": 40351 + }, + { + "epoch": 12.46, + "learning_rate": 6.570009645689106e-06, + "loss": 0.0083, + "step": 40352 + }, + { + "epoch": 12.46, + "learning_rate": 6.569539871048121e-06, + "loss": 0.0078, + "step": 40353 + }, + { + "epoch": 12.46, + "learning_rate": 6.569070104987341e-06, + "loss": 0.0073, + "step": 40354 + }, + { + "epoch": 12.46, + "learning_rate": 6.568600347507945e-06, + "loss": 0.0074, + "step": 40355 + }, + { + "epoch": 12.46, + "learning_rate": 6.5681305986111056e-06, + "loss": 0.0073, + "step": 40356 + }, + { + "epoch": 12.46, + "learning_rate": 6.567660858297996e-06, + "loss": 0.0083, + "step": 40357 + }, + { + "epoch": 12.46, + "learning_rate": 6.5671911265697955e-06, + "loss": 0.0061, + "step": 40358 + }, + { + "epoch": 12.46, + "learning_rate": 6.566721403427672e-06, + "loss": 0.0066, + "step": 40359 + }, + { + "epoch": 12.46, + "learning_rate": 6.566251688872804e-06, + "loss": 0.0072, + "step": 40360 + }, + { + "epoch": 12.46, + "learning_rate": 6.565781982906372e-06, + "loss": 0.0074, + "step": 40361 + }, + { + "epoch": 12.46, + "learning_rate": 6.5653122855295405e-06, + "loss": 0.0067, + "step": 40362 + }, + { + "epoch": 12.46, + "learning_rate": 6.564842596743492e-06, + "loss": 0.0062, + "step": 40363 + }, + { + "epoch": 12.47, + "learning_rate": 6.5643729165494e-06, + "loss": 0.007, + "step": 40364 + }, + { + "epoch": 12.47, + "learning_rate": 6.563903244948433e-06, + "loss": 0.0065, + "step": 40365 + }, + { + "epoch": 12.47, + "learning_rate": 6.563433581941774e-06, + "loss": 0.0071, + "step": 40366 + }, + { + "epoch": 12.47, + "learning_rate": 6.5629639275305965e-06, + "loss": 0.0068, + "step": 40367 + }, + { + "epoch": 12.47, + "learning_rate": 6.562494281716071e-06, + "loss": 0.0063, + "step": 40368 + }, + { + "epoch": 12.47, + "learning_rate": 6.562024644499372e-06, + "loss": 0.0081, + "step": 40369 + }, + { + "epoch": 12.47, + "learning_rate": 6.561555015881677e-06, + "loss": 0.0077, + "step": 40370 + }, + { + "epoch": 12.47, + "learning_rate": 6.561085395864165e-06, + "loss": 0.0076, + "step": 40371 + }, + { + "epoch": 12.47, + "learning_rate": 6.560615784448e-06, + "loss": 0.0082, + "step": 40372 + }, + { + "epoch": 12.47, + "learning_rate": 6.560146181634364e-06, + "loss": 0.0063, + "step": 40373 + }, + { + "epoch": 12.47, + "learning_rate": 6.559676587424433e-06, + "loss": 0.0064, + "step": 40374 + }, + { + "epoch": 12.47, + "learning_rate": 6.559207001819373e-06, + "loss": 0.0057, + "step": 40375 + }, + { + "epoch": 12.47, + "learning_rate": 6.5587374248203664e-06, + "loss": 0.0078, + "step": 40376 + }, + { + "epoch": 12.47, + "learning_rate": 6.558267856428586e-06, + "loss": 0.007, + "step": 40377 + }, + { + "epoch": 12.47, + "learning_rate": 6.557798296645206e-06, + "loss": 0.0066, + "step": 40378 + }, + { + "epoch": 12.47, + "learning_rate": 6.557328745471396e-06, + "loss": 0.0072, + "step": 40379 + }, + { + "epoch": 12.47, + "learning_rate": 6.55685920290834e-06, + "loss": 0.0059, + "step": 40380 + }, + { + "epoch": 12.47, + "learning_rate": 6.556389668957204e-06, + "loss": 0.008, + "step": 40381 + }, + { + "epoch": 12.47, + "learning_rate": 6.555920143619164e-06, + "loss": 0.0068, + "step": 40382 + }, + { + "epoch": 12.47, + "learning_rate": 6.555450626895401e-06, + "loss": 0.0069, + "step": 40383 + }, + { + "epoch": 12.47, + "learning_rate": 6.55498111878708e-06, + "loss": 0.0083, + "step": 40384 + }, + { + "epoch": 12.47, + "learning_rate": 6.5545116192953794e-06, + "loss": 0.007, + "step": 40385 + }, + { + "epoch": 12.47, + "learning_rate": 6.554042128421478e-06, + "loss": 0.0064, + "step": 40386 + }, + { + "epoch": 12.47, + "learning_rate": 6.553572646166541e-06, + "loss": 0.0077, + "step": 40387 + }, + { + "epoch": 12.47, + "learning_rate": 6.5531031725317496e-06, + "loss": 0.0062, + "step": 40388 + }, + { + "epoch": 12.47, + "learning_rate": 6.552633707518278e-06, + "loss": 0.007, + "step": 40389 + }, + { + "epoch": 12.47, + "learning_rate": 6.5521642511272935e-06, + "loss": 0.0063, + "step": 40390 + }, + { + "epoch": 12.47, + "learning_rate": 6.551694803359978e-06, + "loss": 0.0066, + "step": 40391 + }, + { + "epoch": 12.47, + "learning_rate": 6.551225364217504e-06, + "loss": 0.0075, + "step": 40392 + }, + { + "epoch": 12.47, + "learning_rate": 6.550755933701039e-06, + "loss": 0.0095, + "step": 40393 + }, + { + "epoch": 12.47, + "learning_rate": 6.550286511811766e-06, + "loss": 0.006, + "step": 40394 + }, + { + "epoch": 12.47, + "learning_rate": 6.549817098550858e-06, + "loss": 0.0067, + "step": 40395 + }, + { + "epoch": 12.48, + "learning_rate": 6.549347693919484e-06, + "loss": 0.0084, + "step": 40396 + }, + { + "epoch": 12.48, + "learning_rate": 6.5488782979188195e-06, + "loss": 0.0073, + "step": 40397 + }, + { + "epoch": 12.48, + "learning_rate": 6.548408910550044e-06, + "loss": 0.0068, + "step": 40398 + }, + { + "epoch": 12.48, + "learning_rate": 6.547939531814324e-06, + "loss": 0.0066, + "step": 40399 + }, + { + "epoch": 12.48, + "learning_rate": 6.547470161712834e-06, + "loss": 0.0076, + "step": 40400 + }, + { + "epoch": 12.48, + "learning_rate": 6.5470008002467565e-06, + "loss": 0.0077, + "step": 40401 + }, + { + "epoch": 12.48, + "learning_rate": 6.54653144741726e-06, + "loss": 0.0076, + "step": 40402 + }, + { + "epoch": 12.48, + "learning_rate": 6.5460621032255125e-06, + "loss": 0.0064, + "step": 40403 + }, + { + "epoch": 12.48, + "learning_rate": 6.545592767672697e-06, + "loss": 0.0076, + "step": 40404 + }, + { + "epoch": 12.48, + "learning_rate": 6.5451234407599865e-06, + "loss": 0.0072, + "step": 40405 + }, + { + "epoch": 12.48, + "learning_rate": 6.5446541224885496e-06, + "loss": 0.0102, + "step": 40406 + }, + { + "epoch": 12.48, + "learning_rate": 6.544184812859561e-06, + "loss": 0.0067, + "step": 40407 + }, + { + "epoch": 12.48, + "learning_rate": 6.5437155118742004e-06, + "loss": 0.0065, + "step": 40408 + }, + { + "epoch": 12.48, + "learning_rate": 6.543246219533636e-06, + "loss": 0.0071, + "step": 40409 + }, + { + "epoch": 12.48, + "learning_rate": 6.542776935839041e-06, + "loss": 0.0066, + "step": 40410 + }, + { + "epoch": 12.48, + "learning_rate": 6.542307660791596e-06, + "loss": 0.0073, + "step": 40411 + }, + { + "epoch": 12.48, + "learning_rate": 6.5418383943924676e-06, + "loss": 0.0077, + "step": 40412 + }, + { + "epoch": 12.48, + "learning_rate": 6.5413691366428315e-06, + "loss": 0.0056, + "step": 40413 + }, + { + "epoch": 12.48, + "learning_rate": 6.540899887543864e-06, + "loss": 0.0078, + "step": 40414 + }, + { + "epoch": 12.48, + "learning_rate": 6.540430647096736e-06, + "loss": 0.0072, + "step": 40415 + }, + { + "epoch": 12.48, + "learning_rate": 6.539961415302621e-06, + "loss": 0.0065, + "step": 40416 + }, + { + "epoch": 12.48, + "learning_rate": 6.5394921921626975e-06, + "loss": 0.0087, + "step": 40417 + }, + { + "epoch": 12.48, + "learning_rate": 6.539022977678129e-06, + "loss": 0.0059, + "step": 40418 + }, + { + "epoch": 12.48, + "learning_rate": 6.538553771850098e-06, + "loss": 0.0067, + "step": 40419 + }, + { + "epoch": 12.48, + "learning_rate": 6.538084574679778e-06, + "loss": 0.0081, + "step": 40420 + }, + { + "epoch": 12.48, + "learning_rate": 6.5376153861683355e-06, + "loss": 0.0072, + "step": 40421 + }, + { + "epoch": 12.48, + "learning_rate": 6.537146206316951e-06, + "loss": 0.0091, + "step": 40422 + }, + { + "epoch": 12.48, + "learning_rate": 6.536677035126796e-06, + "loss": 0.0084, + "step": 40423 + }, + { + "epoch": 12.48, + "learning_rate": 6.536207872599041e-06, + "loss": 0.0067, + "step": 40424 + }, + { + "epoch": 12.48, + "learning_rate": 6.535738718734863e-06, + "loss": 0.0073, + "step": 40425 + }, + { + "epoch": 12.48, + "learning_rate": 6.535269573535436e-06, + "loss": 0.0062, + "step": 40426 + }, + { + "epoch": 12.48, + "learning_rate": 6.534800437001929e-06, + "loss": 0.0068, + "step": 40427 + }, + { + "epoch": 12.48, + "learning_rate": 6.534331309135518e-06, + "loss": 0.0068, + "step": 40428 + }, + { + "epoch": 12.49, + "learning_rate": 6.53386218993738e-06, + "loss": 0.0073, + "step": 40429 + }, + { + "epoch": 12.49, + "learning_rate": 6.533393079408683e-06, + "loss": 0.0086, + "step": 40430 + }, + { + "epoch": 12.49, + "learning_rate": 6.532923977550598e-06, + "loss": 0.008, + "step": 40431 + }, + { + "epoch": 12.49, + "learning_rate": 6.53245488436431e-06, + "loss": 0.008, + "step": 40432 + }, + { + "epoch": 12.49, + "learning_rate": 6.531985799850979e-06, + "loss": 0.0065, + "step": 40433 + }, + { + "epoch": 12.49, + "learning_rate": 6.531516724011785e-06, + "loss": 0.0068, + "step": 40434 + }, + { + "epoch": 12.49, + "learning_rate": 6.531047656847902e-06, + "loss": 0.0074, + "step": 40435 + }, + { + "epoch": 12.49, + "learning_rate": 6.530578598360502e-06, + "loss": 0.0065, + "step": 40436 + }, + { + "epoch": 12.49, + "learning_rate": 6.530109548550757e-06, + "loss": 0.006, + "step": 40437 + }, + { + "epoch": 12.49, + "learning_rate": 6.5296405074198384e-06, + "loss": 0.0061, + "step": 40438 + }, + { + "epoch": 12.49, + "learning_rate": 6.529171474968925e-06, + "loss": 0.007, + "step": 40439 + }, + { + "epoch": 12.49, + "learning_rate": 6.528702451199187e-06, + "loss": 0.0067, + "step": 40440 + }, + { + "epoch": 12.49, + "learning_rate": 6.5282334361117924e-06, + "loss": 0.0066, + "step": 40441 + }, + { + "epoch": 12.49, + "learning_rate": 6.527764429707926e-06, + "loss": 0.0079, + "step": 40442 + }, + { + "epoch": 12.49, + "learning_rate": 6.52729543198875e-06, + "loss": 0.0077, + "step": 40443 + }, + { + "epoch": 12.49, + "learning_rate": 6.52682644295544e-06, + "loss": 0.0059, + "step": 40444 + }, + { + "epoch": 12.49, + "learning_rate": 6.526357462609178e-06, + "loss": 0.0067, + "step": 40445 + }, + { + "epoch": 12.49, + "learning_rate": 6.525888490951122e-06, + "loss": 0.0064, + "step": 40446 + }, + { + "epoch": 12.49, + "learning_rate": 6.525419527982455e-06, + "loss": 0.0068, + "step": 40447 + }, + { + "epoch": 12.49, + "learning_rate": 6.52495057370435e-06, + "loss": 0.0073, + "step": 40448 + }, + { + "epoch": 12.49, + "learning_rate": 6.524481628117971e-06, + "loss": 0.0056, + "step": 40449 + }, + { + "epoch": 12.49, + "learning_rate": 6.524012691224502e-06, + "loss": 0.0069, + "step": 40450 + }, + { + "epoch": 12.49, + "learning_rate": 6.523543763025113e-06, + "loss": 0.0065, + "step": 40451 + }, + { + "epoch": 12.49, + "learning_rate": 6.523074843520969e-06, + "loss": 0.0075, + "step": 40452 + }, + { + "epoch": 12.49, + "learning_rate": 6.5226059327132525e-06, + "loss": 0.0078, + "step": 40453 + }, + { + "epoch": 12.49, + "learning_rate": 6.522137030603135e-06, + "loss": 0.0077, + "step": 40454 + }, + { + "epoch": 12.49, + "learning_rate": 6.521668137191783e-06, + "loss": 0.0063, + "step": 40455 + }, + { + "epoch": 12.49, + "learning_rate": 6.521199252480376e-06, + "loss": 0.0077, + "step": 40456 + }, + { + "epoch": 12.49, + "learning_rate": 6.520730376470086e-06, + "loss": 0.007, + "step": 40457 + }, + { + "epoch": 12.49, + "learning_rate": 6.52026150916208e-06, + "loss": 0.0067, + "step": 40458 + }, + { + "epoch": 12.49, + "learning_rate": 6.519792650557535e-06, + "loss": 0.0069, + "step": 40459 + }, + { + "epoch": 12.49, + "learning_rate": 6.519323800657626e-06, + "loss": 0.0083, + "step": 40460 + }, + { + "epoch": 12.5, + "learning_rate": 6.518854959463521e-06, + "loss": 0.0072, + "step": 40461 + }, + { + "epoch": 12.5, + "learning_rate": 6.518386126976393e-06, + "loss": 0.0071, + "step": 40462 + }, + { + "epoch": 12.5, + "learning_rate": 6.517917303197421e-06, + "loss": 0.007, + "step": 40463 + }, + { + "epoch": 12.5, + "learning_rate": 6.517448488127769e-06, + "loss": 0.0082, + "step": 40464 + }, + { + "epoch": 12.5, + "learning_rate": 6.516979681768613e-06, + "loss": 0.0062, + "step": 40465 + }, + { + "epoch": 12.5, + "learning_rate": 6.516510884121132e-06, + "loss": 0.0081, + "step": 40466 + }, + { + "epoch": 12.5, + "learning_rate": 6.516042095186485e-06, + "loss": 0.0067, + "step": 40467 + }, + { + "epoch": 12.5, + "learning_rate": 6.515573314965858e-06, + "loss": 0.008, + "step": 40468 + }, + { + "epoch": 12.5, + "learning_rate": 6.515104543460411e-06, + "loss": 0.006, + "step": 40469 + }, + { + "epoch": 12.5, + "learning_rate": 6.51463578067133e-06, + "loss": 0.0064, + "step": 40470 + }, + { + "epoch": 12.5, + "learning_rate": 6.514167026599778e-06, + "loss": 0.0069, + "step": 40471 + }, + { + "epoch": 12.5, + "learning_rate": 6.513698281246927e-06, + "loss": 0.0071, + "step": 40472 + }, + { + "epoch": 12.5, + "learning_rate": 6.513229544613959e-06, + "loss": 0.0076, + "step": 40473 + }, + { + "epoch": 12.5, + "learning_rate": 6.512760816702036e-06, + "loss": 0.0055, + "step": 40474 + }, + { + "epoch": 12.5, + "learning_rate": 6.512292097512333e-06, + "loss": 0.0068, + "step": 40475 + }, + { + "epoch": 12.5, + "learning_rate": 6.511823387046029e-06, + "loss": 0.0066, + "step": 40476 + }, + { + "epoch": 12.5, + "learning_rate": 6.5113546853042854e-06, + "loss": 0.0077, + "step": 40477 + }, + { + "epoch": 12.5, + "learning_rate": 6.510885992288281e-06, + "loss": 0.0079, + "step": 40478 + }, + { + "epoch": 12.5, + "learning_rate": 6.51041730799919e-06, + "loss": 0.008, + "step": 40479 + }, + { + "epoch": 12.5, + "learning_rate": 6.5099486324381764e-06, + "loss": 0.0067, + "step": 40480 + }, + { + "epoch": 12.5, + "learning_rate": 6.509479965606422e-06, + "loss": 0.0071, + "step": 40481 + }, + { + "epoch": 12.5, + "learning_rate": 6.509011307505095e-06, + "loss": 0.0085, + "step": 40482 + }, + { + "epoch": 12.5, + "learning_rate": 6.508542658135365e-06, + "loss": 0.007, + "step": 40483 + }, + { + "epoch": 12.5, + "learning_rate": 6.5080740174984066e-06, + "loss": 0.0058, + "step": 40484 + }, + { + "epoch": 12.5, + "learning_rate": 6.507605385595397e-06, + "loss": 0.0079, + "step": 40485 + }, + { + "epoch": 12.5, + "learning_rate": 6.507136762427499e-06, + "loss": 0.0065, + "step": 40486 + }, + { + "epoch": 12.5, + "learning_rate": 6.506668147995887e-06, + "loss": 0.007, + "step": 40487 + }, + { + "epoch": 12.5, + "learning_rate": 6.50619954230174e-06, + "loss": 0.0072, + "step": 40488 + }, + { + "epoch": 12.5, + "learning_rate": 6.505730945346222e-06, + "loss": 0.0077, + "step": 40489 + }, + { + "epoch": 12.5, + "learning_rate": 6.505262357130508e-06, + "loss": 0.0091, + "step": 40490 + }, + { + "epoch": 12.5, + "learning_rate": 6.5047937776557735e-06, + "loss": 0.0072, + "step": 40491 + }, + { + "epoch": 12.5, + "learning_rate": 6.504325206923185e-06, + "loss": 0.0077, + "step": 40492 + }, + { + "epoch": 12.51, + "learning_rate": 6.503856644933914e-06, + "loss": 0.0061, + "step": 40493 + }, + { + "epoch": 12.51, + "learning_rate": 6.5033880916891405e-06, + "loss": 0.0082, + "step": 40494 + }, + { + "epoch": 12.51, + "learning_rate": 6.502919547190028e-06, + "loss": 0.0079, + "step": 40495 + }, + { + "epoch": 12.51, + "learning_rate": 6.502451011437753e-06, + "loss": 0.0078, + "step": 40496 + }, + { + "epoch": 12.51, + "learning_rate": 6.501982484433487e-06, + "loss": 0.0073, + "step": 40497 + }, + { + "epoch": 12.51, + "learning_rate": 6.5015139661783965e-06, + "loss": 0.0068, + "step": 40498 + }, + { + "epoch": 12.51, + "learning_rate": 6.50104545667366e-06, + "loss": 0.0085, + "step": 40499 + }, + { + "epoch": 12.51, + "learning_rate": 6.500576955920449e-06, + "loss": 0.0071, + "step": 40500 + }, + { + "epoch": 12.51, + "learning_rate": 6.50010846391993e-06, + "loss": 0.0124, + "step": 40501 + }, + { + "epoch": 12.51, + "learning_rate": 6.499639980673278e-06, + "loss": 0.0075, + "step": 40502 + }, + { + "epoch": 12.51, + "learning_rate": 6.499171506181665e-06, + "loss": 0.0074, + "step": 40503 + }, + { + "epoch": 12.51, + "learning_rate": 6.498703040446266e-06, + "loss": 0.0066, + "step": 40504 + }, + { + "epoch": 12.51, + "learning_rate": 6.498234583468246e-06, + "loss": 0.0074, + "step": 40505 + }, + { + "epoch": 12.51, + "learning_rate": 6.4977661352487816e-06, + "loss": 0.0077, + "step": 40506 + }, + { + "epoch": 12.51, + "learning_rate": 6.4972976957890445e-06, + "loss": 0.0059, + "step": 40507 + }, + { + "epoch": 12.51, + "learning_rate": 6.496829265090201e-06, + "loss": 0.0072, + "step": 40508 + }, + { + "epoch": 12.51, + "learning_rate": 6.496360843153428e-06, + "loss": 0.0078, + "step": 40509 + }, + { + "epoch": 12.51, + "learning_rate": 6.495892429979897e-06, + "loss": 0.0068, + "step": 40510 + }, + { + "epoch": 12.51, + "learning_rate": 6.495424025570775e-06, + "loss": 0.0072, + "step": 40511 + }, + { + "epoch": 12.51, + "learning_rate": 6.494955629927238e-06, + "loss": 0.0068, + "step": 40512 + }, + { + "epoch": 12.51, + "learning_rate": 6.4944872430504576e-06, + "loss": 0.0073, + "step": 40513 + }, + { + "epoch": 12.51, + "learning_rate": 6.494018864941602e-06, + "loss": 0.0059, + "step": 40514 + }, + { + "epoch": 12.51, + "learning_rate": 6.493550495601846e-06, + "loss": 0.0064, + "step": 40515 + }, + { + "epoch": 12.51, + "learning_rate": 6.493082135032361e-06, + "loss": 0.0072, + "step": 40516 + }, + { + "epoch": 12.51, + "learning_rate": 6.4926137832343164e-06, + "loss": 0.0072, + "step": 40517 + }, + { + "epoch": 12.51, + "learning_rate": 6.4921454402088814e-06, + "loss": 0.0062, + "step": 40518 + }, + { + "epoch": 12.51, + "learning_rate": 6.491677105957235e-06, + "loss": 0.0091, + "step": 40519 + }, + { + "epoch": 12.51, + "learning_rate": 6.49120878048054e-06, + "loss": 0.0062, + "step": 40520 + }, + { + "epoch": 12.51, + "learning_rate": 6.490740463779972e-06, + "loss": 0.0075, + "step": 40521 + }, + { + "epoch": 12.51, + "learning_rate": 6.490272155856706e-06, + "loss": 0.0077, + "step": 40522 + }, + { + "epoch": 12.51, + "learning_rate": 6.489803856711907e-06, + "loss": 0.0077, + "step": 40523 + }, + { + "epoch": 12.51, + "learning_rate": 6.489335566346747e-06, + "loss": 0.0069, + "step": 40524 + }, + { + "epoch": 12.51, + "learning_rate": 6.488867284762406e-06, + "loss": 0.0078, + "step": 40525 + }, + { + "epoch": 12.52, + "learning_rate": 6.48839901196004e-06, + "loss": 0.0082, + "step": 40526 + }, + { + "epoch": 12.52, + "learning_rate": 6.487930747940832e-06, + "loss": 0.0074, + "step": 40527 + }, + { + "epoch": 12.52, + "learning_rate": 6.487462492705951e-06, + "loss": 0.0079, + "step": 40528 + }, + { + "epoch": 12.52, + "learning_rate": 6.486994246256564e-06, + "loss": 0.0088, + "step": 40529 + }, + { + "epoch": 12.52, + "learning_rate": 6.486526008593847e-06, + "loss": 0.0074, + "step": 40530 + }, + { + "epoch": 12.52, + "learning_rate": 6.486057779718971e-06, + "loss": 0.0082, + "step": 40531 + }, + { + "epoch": 12.52, + "learning_rate": 6.4855895596331005e-06, + "loss": 0.0071, + "step": 40532 + }, + { + "epoch": 12.52, + "learning_rate": 6.4851213483374155e-06, + "loss": 0.0084, + "step": 40533 + }, + { + "epoch": 12.52, + "learning_rate": 6.4846531458330795e-06, + "loss": 0.0069, + "step": 40534 + }, + { + "epoch": 12.52, + "learning_rate": 6.484184952121274e-06, + "loss": 0.0057, + "step": 40535 + }, + { + "epoch": 12.52, + "learning_rate": 6.483716767203156e-06, + "loss": 0.0079, + "step": 40536 + }, + { + "epoch": 12.52, + "learning_rate": 6.483248591079907e-06, + "loss": 0.0066, + "step": 40537 + }, + { + "epoch": 12.52, + "learning_rate": 6.482780423752696e-06, + "loss": 0.0068, + "step": 40538 + }, + { + "epoch": 12.52, + "learning_rate": 6.482312265222689e-06, + "loss": 0.0084, + "step": 40539 + }, + { + "epoch": 12.52, + "learning_rate": 6.481844115491063e-06, + "loss": 0.008, + "step": 40540 + }, + { + "epoch": 12.52, + "learning_rate": 6.481375974558987e-06, + "loss": 0.0065, + "step": 40541 + }, + { + "epoch": 12.52, + "learning_rate": 6.480907842427628e-06, + "loss": 0.0074, + "step": 40542 + }, + { + "epoch": 12.52, + "learning_rate": 6.480439719098164e-06, + "loss": 0.0072, + "step": 40543 + }, + { + "epoch": 12.52, + "learning_rate": 6.479971604571762e-06, + "loss": 0.0076, + "step": 40544 + }, + { + "epoch": 12.52, + "learning_rate": 6.479503498849592e-06, + "loss": 0.0062, + "step": 40545 + }, + { + "epoch": 12.52, + "learning_rate": 6.479035401932824e-06, + "loss": 0.0066, + "step": 40546 + }, + { + "epoch": 12.52, + "learning_rate": 6.478567313822635e-06, + "loss": 0.008, + "step": 40547 + }, + { + "epoch": 12.52, + "learning_rate": 6.478099234520188e-06, + "loss": 0.0069, + "step": 40548 + }, + { + "epoch": 12.52, + "learning_rate": 6.4776311640266566e-06, + "loss": 0.0058, + "step": 40549 + }, + { + "epoch": 12.52, + "learning_rate": 6.477163102343216e-06, + "loss": 0.0065, + "step": 40550 + }, + { + "epoch": 12.52, + "learning_rate": 6.476695049471029e-06, + "loss": 0.0064, + "step": 40551 + }, + { + "epoch": 12.52, + "learning_rate": 6.4762270054112704e-06, + "loss": 0.0077, + "step": 40552 + }, + { + "epoch": 12.52, + "learning_rate": 6.475758970165114e-06, + "loss": 0.0066, + "step": 40553 + }, + { + "epoch": 12.52, + "learning_rate": 6.475290943733725e-06, + "loss": 0.0066, + "step": 40554 + }, + { + "epoch": 12.52, + "learning_rate": 6.474822926118277e-06, + "loss": 0.0082, + "step": 40555 + }, + { + "epoch": 12.52, + "learning_rate": 6.474354917319941e-06, + "loss": 0.0069, + "step": 40556 + }, + { + "epoch": 12.52, + "learning_rate": 6.473886917339884e-06, + "loss": 0.0063, + "step": 40557 + }, + { + "epoch": 12.53, + "learning_rate": 6.473418926179279e-06, + "loss": 0.0068, + "step": 40558 + }, + { + "epoch": 12.53, + "learning_rate": 6.4729509438393005e-06, + "loss": 0.0084, + "step": 40559 + }, + { + "epoch": 12.53, + "learning_rate": 6.472482970321108e-06, + "loss": 0.0072, + "step": 40560 + }, + { + "epoch": 12.53, + "learning_rate": 6.472015005625882e-06, + "loss": 0.0061, + "step": 40561 + }, + { + "epoch": 12.53, + "learning_rate": 6.471547049754794e-06, + "loss": 0.008, + "step": 40562 + }, + { + "epoch": 12.53, + "learning_rate": 6.471079102709005e-06, + "loss": 0.0052, + "step": 40563 + }, + { + "epoch": 12.53, + "learning_rate": 6.470611164489693e-06, + "loss": 0.0069, + "step": 40564 + }, + { + "epoch": 12.53, + "learning_rate": 6.4701432350980275e-06, + "loss": 0.0073, + "step": 40565 + }, + { + "epoch": 12.53, + "learning_rate": 6.469675314535175e-06, + "loss": 0.0086, + "step": 40566 + }, + { + "epoch": 12.53, + "learning_rate": 6.469207402802309e-06, + "loss": 0.0071, + "step": 40567 + }, + { + "epoch": 12.53, + "learning_rate": 6.468739499900599e-06, + "loss": 0.0068, + "step": 40568 + }, + { + "epoch": 12.53, + "learning_rate": 6.468271605831218e-06, + "loss": 0.0091, + "step": 40569 + }, + { + "epoch": 12.53, + "learning_rate": 6.46780372059533e-06, + "loss": 0.0076, + "step": 40570 + }, + { + "epoch": 12.53, + "learning_rate": 6.467335844194111e-06, + "loss": 0.0065, + "step": 40571 + }, + { + "epoch": 12.53, + "learning_rate": 6.466867976628732e-06, + "loss": 0.007, + "step": 40572 + }, + { + "epoch": 12.53, + "learning_rate": 6.466400117900357e-06, + "loss": 0.0074, + "step": 40573 + }, + { + "epoch": 12.53, + "learning_rate": 6.46593226801016e-06, + "loss": 0.0062, + "step": 40574 + }, + { + "epoch": 12.53, + "learning_rate": 6.4654644269593145e-06, + "loss": 0.0077, + "step": 40575 + }, + { + "epoch": 12.53, + "learning_rate": 6.464996594748985e-06, + "loss": 0.007, + "step": 40576 + }, + { + "epoch": 12.53, + "learning_rate": 6.464528771380341e-06, + "loss": 0.0068, + "step": 40577 + }, + { + "epoch": 12.53, + "learning_rate": 6.464060956854561e-06, + "loss": 0.006, + "step": 40578 + }, + { + "epoch": 12.53, + "learning_rate": 6.463593151172805e-06, + "loss": 0.0068, + "step": 40579 + }, + { + "epoch": 12.53, + "learning_rate": 6.463125354336247e-06, + "loss": 0.0085, + "step": 40580 + }, + { + "epoch": 12.53, + "learning_rate": 6.4626575663460625e-06, + "loss": 0.0076, + "step": 40581 + }, + { + "epoch": 12.53, + "learning_rate": 6.4621897872034125e-06, + "loss": 0.0071, + "step": 40582 + }, + { + "epoch": 12.53, + "learning_rate": 6.46172201690947e-06, + "loss": 0.0084, + "step": 40583 + }, + { + "epoch": 12.53, + "learning_rate": 6.4612542554654125e-06, + "loss": 0.0069, + "step": 40584 + }, + { + "epoch": 12.53, + "learning_rate": 6.460786502872396e-06, + "loss": 0.0062, + "step": 40585 + }, + { + "epoch": 12.53, + "learning_rate": 6.460318759131602e-06, + "loss": 0.0075, + "step": 40586 + }, + { + "epoch": 12.53, + "learning_rate": 6.459851024244197e-06, + "loss": 0.0061, + "step": 40587 + }, + { + "epoch": 12.53, + "learning_rate": 6.459383298211347e-06, + "loss": 0.0066, + "step": 40588 + }, + { + "epoch": 12.53, + "learning_rate": 6.458915581034227e-06, + "loss": 0.0075, + "step": 40589 + }, + { + "epoch": 12.53, + "learning_rate": 6.458447872714006e-06, + "loss": 0.0075, + "step": 40590 + }, + { + "epoch": 12.54, + "learning_rate": 6.45798017325185e-06, + "loss": 0.0067, + "step": 40591 + }, + { + "epoch": 12.54, + "learning_rate": 6.457512482648933e-06, + "loss": 0.0058, + "step": 40592 + }, + { + "epoch": 12.54, + "learning_rate": 6.457044800906427e-06, + "loss": 0.0068, + "step": 40593 + }, + { + "epoch": 12.54, + "learning_rate": 6.456577128025494e-06, + "loss": 0.0061, + "step": 40594 + }, + { + "epoch": 12.54, + "learning_rate": 6.456109464007308e-06, + "loss": 0.006, + "step": 40595 + }, + { + "epoch": 12.54, + "learning_rate": 6.4556418088530415e-06, + "loss": 0.008, + "step": 40596 + }, + { + "epoch": 12.54, + "learning_rate": 6.455174162563858e-06, + "loss": 0.007, + "step": 40597 + }, + { + "epoch": 12.54, + "learning_rate": 6.45470652514093e-06, + "loss": 0.0069, + "step": 40598 + }, + { + "epoch": 12.54, + "learning_rate": 6.45423889658543e-06, + "loss": 0.0085, + "step": 40599 + }, + { + "epoch": 12.54, + "learning_rate": 6.453771276898526e-06, + "loss": 0.0061, + "step": 40600 + }, + { + "epoch": 12.54, + "learning_rate": 6.453303666081383e-06, + "loss": 0.0065, + "step": 40601 + }, + { + "epoch": 12.54, + "learning_rate": 6.452836064135176e-06, + "loss": 0.0084, + "step": 40602 + }, + { + "epoch": 12.54, + "learning_rate": 6.452368471061076e-06, + "loss": 0.0081, + "step": 40603 + }, + { + "epoch": 12.54, + "learning_rate": 6.4519008868602476e-06, + "loss": 0.0077, + "step": 40604 + }, + { + "epoch": 12.54, + "learning_rate": 6.451433311533859e-06, + "loss": 0.0069, + "step": 40605 + }, + { + "epoch": 12.54, + "learning_rate": 6.4509657450830875e-06, + "loss": 0.0073, + "step": 40606 + }, + { + "epoch": 12.54, + "learning_rate": 6.450498187509096e-06, + "loss": 0.0091, + "step": 40607 + }, + { + "epoch": 12.54, + "learning_rate": 6.450030638813054e-06, + "loss": 0.008, + "step": 40608 + }, + { + "epoch": 12.54, + "learning_rate": 6.449563098996137e-06, + "loss": 0.0059, + "step": 40609 + }, + { + "epoch": 12.54, + "learning_rate": 6.449095568059509e-06, + "loss": 0.0074, + "step": 40610 + }, + { + "epoch": 12.54, + "learning_rate": 6.4486280460043375e-06, + "loss": 0.0069, + "step": 40611 + }, + { + "epoch": 12.54, + "learning_rate": 6.448160532831799e-06, + "loss": 0.007, + "step": 40612 + }, + { + "epoch": 12.54, + "learning_rate": 6.447693028543056e-06, + "loss": 0.0071, + "step": 40613 + }, + { + "epoch": 12.54, + "learning_rate": 6.447225533139283e-06, + "loss": 0.0084, + "step": 40614 + }, + { + "epoch": 12.54, + "learning_rate": 6.446758046621647e-06, + "loss": 0.0066, + "step": 40615 + }, + { + "epoch": 12.54, + "learning_rate": 6.446290568991313e-06, + "loss": 0.0068, + "step": 40616 + }, + { + "epoch": 12.54, + "learning_rate": 6.445823100249458e-06, + "loss": 0.0092, + "step": 40617 + }, + { + "epoch": 12.54, + "learning_rate": 6.445355640397249e-06, + "loss": 0.0053, + "step": 40618 + }, + { + "epoch": 12.54, + "learning_rate": 6.4448881894358494e-06, + "loss": 0.0072, + "step": 40619 + }, + { + "epoch": 12.54, + "learning_rate": 6.444420747366435e-06, + "loss": 0.0077, + "step": 40620 + }, + { + "epoch": 12.54, + "learning_rate": 6.443953314190177e-06, + "loss": 0.0066, + "step": 40621 + }, + { + "epoch": 12.54, + "learning_rate": 6.443485889908233e-06, + "loss": 0.0088, + "step": 40622 + }, + { + "epoch": 12.55, + "learning_rate": 6.443018474521783e-06, + "loss": 0.0074, + "step": 40623 + }, + { + "epoch": 12.55, + "learning_rate": 6.442551068031995e-06, + "loss": 0.0073, + "step": 40624 + }, + { + "epoch": 12.55, + "learning_rate": 6.442083670440033e-06, + "loss": 0.0061, + "step": 40625 + }, + { + "epoch": 12.55, + "learning_rate": 6.4416162817470665e-06, + "loss": 0.0091, + "step": 40626 + }, + { + "epoch": 12.55, + "learning_rate": 6.44114890195427e-06, + "loss": 0.0074, + "step": 40627 + }, + { + "epoch": 12.55, + "learning_rate": 6.440681531062809e-06, + "loss": 0.0077, + "step": 40628 + }, + { + "epoch": 12.55, + "learning_rate": 6.440214169073849e-06, + "loss": 0.0076, + "step": 40629 + }, + { + "epoch": 12.55, + "learning_rate": 6.4397468159885675e-06, + "loss": 0.0083, + "step": 40630 + }, + { + "epoch": 12.55, + "learning_rate": 6.439279471808126e-06, + "loss": 0.0074, + "step": 40631 + }, + { + "epoch": 12.55, + "learning_rate": 6.438812136533695e-06, + "loss": 0.0069, + "step": 40632 + }, + { + "epoch": 12.55, + "learning_rate": 6.438344810166446e-06, + "loss": 0.0073, + "step": 40633 + }, + { + "epoch": 12.55, + "learning_rate": 6.4378774927075485e-06, + "loss": 0.0075, + "step": 40634 + }, + { + "epoch": 12.55, + "learning_rate": 6.437410184158166e-06, + "loss": 0.0066, + "step": 40635 + }, + { + "epoch": 12.55, + "learning_rate": 6.4369428845194695e-06, + "loss": 0.0066, + "step": 40636 + }, + { + "epoch": 12.55, + "learning_rate": 6.436475593792631e-06, + "loss": 0.0064, + "step": 40637 + }, + { + "epoch": 12.55, + "learning_rate": 6.436008311978816e-06, + "loss": 0.0072, + "step": 40638 + }, + { + "epoch": 12.55, + "learning_rate": 6.435541039079194e-06, + "loss": 0.0076, + "step": 40639 + }, + { + "epoch": 12.55, + "learning_rate": 6.435073775094935e-06, + "loss": 0.0062, + "step": 40640 + }, + { + "epoch": 12.55, + "learning_rate": 6.434606520027207e-06, + "loss": 0.0086, + "step": 40641 + }, + { + "epoch": 12.55, + "learning_rate": 6.434139273877176e-06, + "loss": 0.0062, + "step": 40642 + }, + { + "epoch": 12.55, + "learning_rate": 6.433672036646018e-06, + "loss": 0.0078, + "step": 40643 + }, + { + "epoch": 12.55, + "learning_rate": 6.433204808334892e-06, + "loss": 0.007, + "step": 40644 + }, + { + "epoch": 12.55, + "learning_rate": 6.432737588944972e-06, + "loss": 0.0065, + "step": 40645 + }, + { + "epoch": 12.55, + "learning_rate": 6.432270378477428e-06, + "loss": 0.0089, + "step": 40646 + }, + { + "epoch": 12.55, + "learning_rate": 6.431803176933423e-06, + "loss": 0.0065, + "step": 40647 + }, + { + "epoch": 12.55, + "learning_rate": 6.431335984314131e-06, + "loss": 0.0061, + "step": 40648 + }, + { + "epoch": 12.55, + "learning_rate": 6.430868800620721e-06, + "loss": 0.0082, + "step": 40649 + }, + { + "epoch": 12.55, + "learning_rate": 6.4304016258543544e-06, + "loss": 0.0062, + "step": 40650 + }, + { + "epoch": 12.55, + "learning_rate": 6.429934460016207e-06, + "loss": 0.0072, + "step": 40651 + }, + { + "epoch": 12.55, + "learning_rate": 6.429467303107446e-06, + "loss": 0.006, + "step": 40652 + }, + { + "epoch": 12.55, + "learning_rate": 6.429000155129237e-06, + "loss": 0.0066, + "step": 40653 + }, + { + "epoch": 12.55, + "learning_rate": 6.428533016082747e-06, + "loss": 0.0078, + "step": 40654 + }, + { + "epoch": 12.56, + "learning_rate": 6.428065885969152e-06, + "loss": 0.0097, + "step": 40655 + }, + { + "epoch": 12.56, + "learning_rate": 6.4275987647896145e-06, + "loss": 0.0105, + "step": 40656 + }, + { + "epoch": 12.56, + "learning_rate": 6.427131652545301e-06, + "loss": 0.0094, + "step": 40657 + }, + { + "epoch": 12.56, + "learning_rate": 6.426664549237387e-06, + "loss": 0.0075, + "step": 40658 + }, + { + "epoch": 12.56, + "learning_rate": 6.4261974548670355e-06, + "loss": 0.0074, + "step": 40659 + }, + { + "epoch": 12.56, + "learning_rate": 6.425730369435414e-06, + "loss": 0.0084, + "step": 40660 + }, + { + "epoch": 12.56, + "learning_rate": 6.425263292943695e-06, + "loss": 0.0087, + "step": 40661 + }, + { + "epoch": 12.56, + "learning_rate": 6.424796225393044e-06, + "loss": 0.0078, + "step": 40662 + }, + { + "epoch": 12.56, + "learning_rate": 6.424329166784628e-06, + "loss": 0.0094, + "step": 40663 + }, + { + "epoch": 12.56, + "learning_rate": 6.423862117119617e-06, + "loss": 0.0059, + "step": 40664 + }, + { + "epoch": 12.56, + "learning_rate": 6.4233950763991835e-06, + "loss": 0.0086, + "step": 40665 + }, + { + "epoch": 12.56, + "learning_rate": 6.422928044624488e-06, + "loss": 0.0067, + "step": 40666 + }, + { + "epoch": 12.56, + "learning_rate": 6.4224610217967e-06, + "loss": 0.0068, + "step": 40667 + }, + { + "epoch": 12.56, + "learning_rate": 6.421994007916993e-06, + "loss": 0.0085, + "step": 40668 + }, + { + "epoch": 12.56, + "learning_rate": 6.42152700298653e-06, + "loss": 0.009, + "step": 40669 + }, + { + "epoch": 12.56, + "learning_rate": 6.421060007006479e-06, + "loss": 0.0071, + "step": 40670 + }, + { + "epoch": 12.56, + "learning_rate": 6.420593019978013e-06, + "loss": 0.0059, + "step": 40671 + }, + { + "epoch": 12.56, + "learning_rate": 6.420126041902295e-06, + "loss": 0.0065, + "step": 40672 + }, + { + "epoch": 12.56, + "learning_rate": 6.419659072780493e-06, + "loss": 0.0068, + "step": 40673 + }, + { + "epoch": 12.56, + "learning_rate": 6.419192112613783e-06, + "loss": 0.008, + "step": 40674 + }, + { + "epoch": 12.56, + "learning_rate": 6.41872516140332e-06, + "loss": 0.0077, + "step": 40675 + }, + { + "epoch": 12.56, + "learning_rate": 6.41825821915028e-06, + "loss": 0.0063, + "step": 40676 + }, + { + "epoch": 12.56, + "learning_rate": 6.417791285855832e-06, + "loss": 0.0083, + "step": 40677 + }, + { + "epoch": 12.56, + "learning_rate": 6.417324361521138e-06, + "loss": 0.0081, + "step": 40678 + }, + { + "epoch": 12.56, + "learning_rate": 6.4168574461473705e-06, + "loss": 0.0073, + "step": 40679 + }, + { + "epoch": 12.56, + "learning_rate": 6.416390539735699e-06, + "loss": 0.0061, + "step": 40680 + }, + { + "epoch": 12.56, + "learning_rate": 6.415923642287283e-06, + "loss": 0.0075, + "step": 40681 + }, + { + "epoch": 12.56, + "learning_rate": 6.415456753803297e-06, + "loss": 0.0069, + "step": 40682 + }, + { + "epoch": 12.56, + "learning_rate": 6.414989874284911e-06, + "loss": 0.0079, + "step": 40683 + }, + { + "epoch": 12.56, + "learning_rate": 6.414523003733287e-06, + "loss": 0.0075, + "step": 40684 + }, + { + "epoch": 12.56, + "learning_rate": 6.414056142149594e-06, + "loss": 0.0067, + "step": 40685 + }, + { + "epoch": 12.56, + "learning_rate": 6.413589289535002e-06, + "loss": 0.0065, + "step": 40686 + }, + { + "epoch": 12.56, + "learning_rate": 6.4131224458906785e-06, + "loss": 0.0067, + "step": 40687 + }, + { + "epoch": 12.57, + "learning_rate": 6.412655611217785e-06, + "loss": 0.0071, + "step": 40688 + }, + { + "epoch": 12.57, + "learning_rate": 6.4121887855174995e-06, + "loss": 0.0061, + "step": 40689 + }, + { + "epoch": 12.57, + "learning_rate": 6.411721968790982e-06, + "loss": 0.0064, + "step": 40690 + }, + { + "epoch": 12.57, + "learning_rate": 6.4112551610394e-06, + "loss": 0.0073, + "step": 40691 + }, + { + "epoch": 12.57, + "learning_rate": 6.41078836226393e-06, + "loss": 0.0064, + "step": 40692 + }, + { + "epoch": 12.57, + "learning_rate": 6.410321572465726e-06, + "loss": 0.0055, + "step": 40693 + }, + { + "epoch": 12.57, + "learning_rate": 6.409854791645966e-06, + "loss": 0.0064, + "step": 40694 + }, + { + "epoch": 12.57, + "learning_rate": 6.409388019805815e-06, + "loss": 0.0065, + "step": 40695 + }, + { + "epoch": 12.57, + "learning_rate": 6.408921256946435e-06, + "loss": 0.0094, + "step": 40696 + }, + { + "epoch": 12.57, + "learning_rate": 6.408454503069001e-06, + "loss": 0.0073, + "step": 40697 + }, + { + "epoch": 12.57, + "learning_rate": 6.4079877581746744e-06, + "loss": 0.0071, + "step": 40698 + }, + { + "epoch": 12.57, + "learning_rate": 6.40752102226463e-06, + "loss": 0.007, + "step": 40699 + }, + { + "epoch": 12.57, + "learning_rate": 6.4070542953400295e-06, + "loss": 0.0066, + "step": 40700 + }, + { + "epoch": 12.57, + "learning_rate": 6.406587577402038e-06, + "loss": 0.0067, + "step": 40701 + }, + { + "epoch": 12.57, + "learning_rate": 6.406120868451833e-06, + "loss": 0.0076, + "step": 40702 + }, + { + "epoch": 12.57, + "learning_rate": 6.405654168490569e-06, + "loss": 0.0058, + "step": 40703 + }, + { + "epoch": 12.57, + "learning_rate": 6.405187477519422e-06, + "loss": 0.0059, + "step": 40704 + }, + { + "epoch": 12.57, + "learning_rate": 6.404720795539558e-06, + "loss": 0.0079, + "step": 40705 + }, + { + "epoch": 12.57, + "learning_rate": 6.40425412255214e-06, + "loss": 0.0082, + "step": 40706 + }, + { + "epoch": 12.57, + "learning_rate": 6.403787458558339e-06, + "loss": 0.007, + "step": 40707 + }, + { + "epoch": 12.57, + "learning_rate": 6.403320803559325e-06, + "loss": 0.0089, + "step": 40708 + }, + { + "epoch": 12.57, + "learning_rate": 6.402854157556257e-06, + "loss": 0.0059, + "step": 40709 + }, + { + "epoch": 12.57, + "learning_rate": 6.402387520550308e-06, + "loss": 0.0076, + "step": 40710 + }, + { + "epoch": 12.57, + "learning_rate": 6.401920892542648e-06, + "loss": 0.0073, + "step": 40711 + }, + { + "epoch": 12.57, + "learning_rate": 6.4014542735344355e-06, + "loss": 0.006, + "step": 40712 + }, + { + "epoch": 12.57, + "learning_rate": 6.400987663526843e-06, + "loss": 0.0073, + "step": 40713 + }, + { + "epoch": 12.57, + "learning_rate": 6.400521062521039e-06, + "loss": 0.006, + "step": 40714 + }, + { + "epoch": 12.57, + "learning_rate": 6.400054470518187e-06, + "loss": 0.0069, + "step": 40715 + }, + { + "epoch": 12.57, + "learning_rate": 6.399587887519453e-06, + "loss": 0.0072, + "step": 40716 + }, + { + "epoch": 12.57, + "learning_rate": 6.399121313526011e-06, + "loss": 0.0077, + "step": 40717 + }, + { + "epoch": 12.57, + "learning_rate": 6.39865474853902e-06, + "loss": 0.0073, + "step": 40718 + }, + { + "epoch": 12.57, + "learning_rate": 6.398188192559649e-06, + "loss": 0.0065, + "step": 40719 + }, + { + "epoch": 12.58, + "learning_rate": 6.39772164558907e-06, + "loss": 0.0061, + "step": 40720 + }, + { + "epoch": 12.58, + "learning_rate": 6.397255107628445e-06, + "loss": 0.0068, + "step": 40721 + }, + { + "epoch": 12.58, + "learning_rate": 6.3967885786789394e-06, + "loss": 0.0069, + "step": 40722 + }, + { + "epoch": 12.58, + "learning_rate": 6.396322058741728e-06, + "loss": 0.0063, + "step": 40723 + }, + { + "epoch": 12.58, + "learning_rate": 6.3958555478179685e-06, + "loss": 0.0091, + "step": 40724 + }, + { + "epoch": 12.58, + "learning_rate": 6.395389045908833e-06, + "loss": 0.0063, + "step": 40725 + }, + { + "epoch": 12.58, + "learning_rate": 6.3949225530154875e-06, + "loss": 0.0068, + "step": 40726 + }, + { + "epoch": 12.58, + "learning_rate": 6.394456069139096e-06, + "loss": 0.0078, + "step": 40727 + }, + { + "epoch": 12.58, + "learning_rate": 6.393989594280827e-06, + "loss": 0.0075, + "step": 40728 + }, + { + "epoch": 12.58, + "learning_rate": 6.393523128441852e-06, + "loss": 0.008, + "step": 40729 + }, + { + "epoch": 12.58, + "learning_rate": 6.393056671623329e-06, + "loss": 0.0071, + "step": 40730 + }, + { + "epoch": 12.58, + "learning_rate": 6.392590223826432e-06, + "loss": 0.0091, + "step": 40731 + }, + { + "epoch": 12.58, + "learning_rate": 6.39212378505232e-06, + "loss": 0.0091, + "step": 40732 + }, + { + "epoch": 12.58, + "learning_rate": 6.391657355302172e-06, + "loss": 0.0068, + "step": 40733 + }, + { + "epoch": 12.58, + "learning_rate": 6.391190934577141e-06, + "loss": 0.0079, + "step": 40734 + }, + { + "epoch": 12.58, + "learning_rate": 6.390724522878402e-06, + "loss": 0.008, + "step": 40735 + }, + { + "epoch": 12.58, + "learning_rate": 6.390258120207123e-06, + "loss": 0.0067, + "step": 40736 + }, + { + "epoch": 12.58, + "learning_rate": 6.38979172656446e-06, + "loss": 0.0066, + "step": 40737 + }, + { + "epoch": 12.58, + "learning_rate": 6.3893253419515885e-06, + "loss": 0.0069, + "step": 40738 + }, + { + "epoch": 12.58, + "learning_rate": 6.388858966369677e-06, + "loss": 0.0066, + "step": 40739 + }, + { + "epoch": 12.58, + "learning_rate": 6.388392599819882e-06, + "loss": 0.0061, + "step": 40740 + }, + { + "epoch": 12.58, + "learning_rate": 6.387926242303378e-06, + "loss": 0.0064, + "step": 40741 + }, + { + "epoch": 12.58, + "learning_rate": 6.387459893821332e-06, + "loss": 0.0072, + "step": 40742 + }, + { + "epoch": 12.58, + "learning_rate": 6.386993554374905e-06, + "loss": 0.0096, + "step": 40743 + }, + { + "epoch": 12.58, + "learning_rate": 6.386527223965264e-06, + "loss": 0.006, + "step": 40744 + }, + { + "epoch": 12.58, + "learning_rate": 6.3860609025935825e-06, + "loss": 0.0056, + "step": 40745 + }, + { + "epoch": 12.58, + "learning_rate": 6.3855945902610195e-06, + "loss": 0.0075, + "step": 40746 + }, + { + "epoch": 12.58, + "learning_rate": 6.38512828696874e-06, + "loss": 0.0079, + "step": 40747 + }, + { + "epoch": 12.58, + "learning_rate": 6.38466199271792e-06, + "loss": 0.0062, + "step": 40748 + }, + { + "epoch": 12.58, + "learning_rate": 6.384195707509717e-06, + "loss": 0.0071, + "step": 40749 + }, + { + "epoch": 12.58, + "learning_rate": 6.383729431345298e-06, + "loss": 0.0075, + "step": 40750 + }, + { + "epoch": 12.58, + "learning_rate": 6.383263164225836e-06, + "loss": 0.0063, + "step": 40751 + }, + { + "epoch": 12.58, + "learning_rate": 6.382796906152489e-06, + "loss": 0.0068, + "step": 40752 + }, + { + "epoch": 12.59, + "learning_rate": 6.382330657126428e-06, + "loss": 0.0065, + "step": 40753 + }, + { + "epoch": 12.59, + "learning_rate": 6.38186441714882e-06, + "loss": 0.0075, + "step": 40754 + }, + { + "epoch": 12.59, + "learning_rate": 6.3813981862208244e-06, + "loss": 0.0071, + "step": 40755 + }, + { + "epoch": 12.59, + "learning_rate": 6.380931964343613e-06, + "loss": 0.0068, + "step": 40756 + }, + { + "epoch": 12.59, + "learning_rate": 6.380465751518355e-06, + "loss": 0.0065, + "step": 40757 + }, + { + "epoch": 12.59, + "learning_rate": 6.3799995477462064e-06, + "loss": 0.0077, + "step": 40758 + }, + { + "epoch": 12.59, + "learning_rate": 6.379533353028342e-06, + "loss": 0.0079, + "step": 40759 + }, + { + "epoch": 12.59, + "learning_rate": 6.379067167365926e-06, + "loss": 0.0075, + "step": 40760 + }, + { + "epoch": 12.59, + "learning_rate": 6.378600990760121e-06, + "loss": 0.0086, + "step": 40761 + }, + { + "epoch": 12.59, + "learning_rate": 6.378134823212097e-06, + "loss": 0.0064, + "step": 40762 + }, + { + "epoch": 12.59, + "learning_rate": 6.377668664723018e-06, + "loss": 0.0071, + "step": 40763 + }, + { + "epoch": 12.59, + "learning_rate": 6.377202515294052e-06, + "loss": 0.0062, + "step": 40764 + }, + { + "epoch": 12.59, + "learning_rate": 6.37673637492636e-06, + "loss": 0.0072, + "step": 40765 + }, + { + "epoch": 12.59, + "learning_rate": 6.376270243621112e-06, + "loss": 0.0069, + "step": 40766 + }, + { + "epoch": 12.59, + "learning_rate": 6.375804121379477e-06, + "loss": 0.0066, + "step": 40767 + }, + { + "epoch": 12.59, + "learning_rate": 6.3753380082026115e-06, + "loss": 0.0057, + "step": 40768 + }, + { + "epoch": 12.59, + "learning_rate": 6.374871904091688e-06, + "loss": 0.0074, + "step": 40769 + }, + { + "epoch": 12.59, + "learning_rate": 6.374405809047875e-06, + "loss": 0.007, + "step": 40770 + }, + { + "epoch": 12.59, + "learning_rate": 6.3739397230723284e-06, + "loss": 0.0075, + "step": 40771 + }, + { + "epoch": 12.59, + "learning_rate": 6.373473646166224e-06, + "loss": 0.0074, + "step": 40772 + }, + { + "epoch": 12.59, + "learning_rate": 6.373007578330724e-06, + "loss": 0.0074, + "step": 40773 + }, + { + "epoch": 12.59, + "learning_rate": 6.372541519566993e-06, + "loss": 0.0071, + "step": 40774 + }, + { + "epoch": 12.59, + "learning_rate": 6.372075469876193e-06, + "loss": 0.0067, + "step": 40775 + }, + { + "epoch": 12.59, + "learning_rate": 6.3716094292595e-06, + "loss": 0.0071, + "step": 40776 + }, + { + "epoch": 12.59, + "learning_rate": 6.37114339771807e-06, + "loss": 0.0068, + "step": 40777 + }, + { + "epoch": 12.59, + "learning_rate": 6.370677375253072e-06, + "loss": 0.0072, + "step": 40778 + }, + { + "epoch": 12.59, + "learning_rate": 6.370211361865675e-06, + "loss": 0.0073, + "step": 40779 + }, + { + "epoch": 12.59, + "learning_rate": 6.369745357557038e-06, + "loss": 0.0067, + "step": 40780 + }, + { + "epoch": 12.59, + "learning_rate": 6.369279362328329e-06, + "loss": 0.0077, + "step": 40781 + }, + { + "epoch": 12.59, + "learning_rate": 6.368813376180721e-06, + "loss": 0.0076, + "step": 40782 + }, + { + "epoch": 12.59, + "learning_rate": 6.368347399115367e-06, + "loss": 0.0067, + "step": 40783 + }, + { + "epoch": 12.59, + "learning_rate": 6.3678814311334404e-06, + "loss": 0.006, + "step": 40784 + }, + { + "epoch": 12.6, + "learning_rate": 6.367415472236107e-06, + "loss": 0.0072, + "step": 40785 + }, + { + "epoch": 12.6, + "learning_rate": 6.366949522424526e-06, + "loss": 0.0077, + "step": 40786 + }, + { + "epoch": 12.6, + "learning_rate": 6.366483581699867e-06, + "loss": 0.0064, + "step": 40787 + }, + { + "epoch": 12.6, + "learning_rate": 6.3660176500633e-06, + "loss": 0.0064, + "step": 40788 + }, + { + "epoch": 12.6, + "learning_rate": 6.36555172751598e-06, + "loss": 0.0083, + "step": 40789 + }, + { + "epoch": 12.6, + "learning_rate": 6.365085814059081e-06, + "loss": 0.0059, + "step": 40790 + }, + { + "epoch": 12.6, + "learning_rate": 6.364619909693767e-06, + "loss": 0.006, + "step": 40791 + }, + { + "epoch": 12.6, + "learning_rate": 6.3641540144212e-06, + "loss": 0.0077, + "step": 40792 + }, + { + "epoch": 12.6, + "learning_rate": 6.363688128242544e-06, + "loss": 0.0065, + "step": 40793 + }, + { + "epoch": 12.6, + "learning_rate": 6.363222251158972e-06, + "loss": 0.0071, + "step": 40794 + }, + { + "epoch": 12.6, + "learning_rate": 6.362756383171642e-06, + "loss": 0.0071, + "step": 40795 + }, + { + "epoch": 12.6, + "learning_rate": 6.36229052428172e-06, + "loss": 0.0067, + "step": 40796 + }, + { + "epoch": 12.6, + "learning_rate": 6.361824674490375e-06, + "loss": 0.0068, + "step": 40797 + }, + { + "epoch": 12.6, + "learning_rate": 6.3613588337987705e-06, + "loss": 0.0077, + "step": 40798 + }, + { + "epoch": 12.6, + "learning_rate": 6.360893002208069e-06, + "loss": 0.0071, + "step": 40799 + }, + { + "epoch": 12.6, + "learning_rate": 6.36042717971944e-06, + "loss": 0.0084, + "step": 40800 + }, + { + "epoch": 12.6, + "learning_rate": 6.359961366334047e-06, + "loss": 0.0077, + "step": 40801 + }, + { + "epoch": 12.6, + "learning_rate": 6.359495562053053e-06, + "loss": 0.0083, + "step": 40802 + }, + { + "epoch": 12.6, + "learning_rate": 6.359029766877622e-06, + "loss": 0.0071, + "step": 40803 + }, + { + "epoch": 12.6, + "learning_rate": 6.358563980808927e-06, + "loss": 0.007, + "step": 40804 + }, + { + "epoch": 12.6, + "learning_rate": 6.358098203848126e-06, + "loss": 0.0076, + "step": 40805 + }, + { + "epoch": 12.6, + "learning_rate": 6.357632435996383e-06, + "loss": 0.0077, + "step": 40806 + }, + { + "epoch": 12.6, + "learning_rate": 6.357166677254869e-06, + "loss": 0.007, + "step": 40807 + }, + { + "epoch": 12.6, + "learning_rate": 6.356700927624744e-06, + "loss": 0.0063, + "step": 40808 + }, + { + "epoch": 12.6, + "learning_rate": 6.356235187107172e-06, + "loss": 0.0083, + "step": 40809 + }, + { + "epoch": 12.6, + "learning_rate": 6.3557694557033245e-06, + "loss": 0.0083, + "step": 40810 + }, + { + "epoch": 12.6, + "learning_rate": 6.355303733414361e-06, + "loss": 0.006, + "step": 40811 + }, + { + "epoch": 12.6, + "learning_rate": 6.3548380202414476e-06, + "loss": 0.0084, + "step": 40812 + }, + { + "epoch": 12.6, + "learning_rate": 6.3543723161857506e-06, + "loss": 0.0067, + "step": 40813 + }, + { + "epoch": 12.6, + "learning_rate": 6.353906621248429e-06, + "loss": 0.0082, + "step": 40814 + }, + { + "epoch": 12.6, + "learning_rate": 6.353440935430654e-06, + "loss": 0.0074, + "step": 40815 + }, + { + "epoch": 12.6, + "learning_rate": 6.352975258733591e-06, + "loss": 0.0067, + "step": 40816 + }, + { + "epoch": 12.61, + "learning_rate": 6.352509591158398e-06, + "loss": 0.0065, + "step": 40817 + }, + { + "epoch": 12.61, + "learning_rate": 6.352043932706246e-06, + "loss": 0.006, + "step": 40818 + }, + { + "epoch": 12.61, + "learning_rate": 6.351578283378299e-06, + "loss": 0.0071, + "step": 40819 + }, + { + "epoch": 12.61, + "learning_rate": 6.351112643175716e-06, + "loss": 0.0074, + "step": 40820 + }, + { + "epoch": 12.61, + "learning_rate": 6.350647012099667e-06, + "loss": 0.0071, + "step": 40821 + }, + { + "epoch": 12.61, + "learning_rate": 6.3501813901513184e-06, + "loss": 0.0073, + "step": 40822 + }, + { + "epoch": 12.61, + "learning_rate": 6.3497157773318306e-06, + "loss": 0.0072, + "step": 40823 + }, + { + "epoch": 12.61, + "learning_rate": 6.349250173642366e-06, + "loss": 0.0072, + "step": 40824 + }, + { + "epoch": 12.61, + "learning_rate": 6.348784579084097e-06, + "loss": 0.0055, + "step": 40825 + }, + { + "epoch": 12.61, + "learning_rate": 6.348318993658182e-06, + "loss": 0.009, + "step": 40826 + }, + { + "epoch": 12.61, + "learning_rate": 6.347853417365786e-06, + "loss": 0.0054, + "step": 40827 + }, + { + "epoch": 12.61, + "learning_rate": 6.3473878502080755e-06, + "loss": 0.0077, + "step": 40828 + }, + { + "epoch": 12.61, + "learning_rate": 6.346922292186216e-06, + "loss": 0.0068, + "step": 40829 + }, + { + "epoch": 12.61, + "learning_rate": 6.346456743301367e-06, + "loss": 0.0063, + "step": 40830 + }, + { + "epoch": 12.61, + "learning_rate": 6.345991203554698e-06, + "loss": 0.0077, + "step": 40831 + }, + { + "epoch": 12.61, + "learning_rate": 6.345525672947372e-06, + "loss": 0.0062, + "step": 40832 + }, + { + "epoch": 12.61, + "learning_rate": 6.3450601514805536e-06, + "loss": 0.0073, + "step": 40833 + }, + { + "epoch": 12.61, + "learning_rate": 6.344594639155402e-06, + "loss": 0.0074, + "step": 40834 + }, + { + "epoch": 12.61, + "learning_rate": 6.3441291359730895e-06, + "loss": 0.0063, + "step": 40835 + }, + { + "epoch": 12.61, + "learning_rate": 6.343663641934777e-06, + "loss": 0.0069, + "step": 40836 + }, + { + "epoch": 12.61, + "learning_rate": 6.343198157041625e-06, + "loss": 0.0081, + "step": 40837 + }, + { + "epoch": 12.61, + "learning_rate": 6.342732681294805e-06, + "loss": 0.0058, + "step": 40838 + }, + { + "epoch": 12.61, + "learning_rate": 6.342267214695478e-06, + "loss": 0.0077, + "step": 40839 + }, + { + "epoch": 12.61, + "learning_rate": 6.341801757244803e-06, + "loss": 0.0071, + "step": 40840 + }, + { + "epoch": 12.61, + "learning_rate": 6.341336308943957e-06, + "loss": 0.0057, + "step": 40841 + }, + { + "epoch": 12.61, + "learning_rate": 6.34087086979409e-06, + "loss": 0.007, + "step": 40842 + }, + { + "epoch": 12.61, + "learning_rate": 6.340405439796373e-06, + "loss": 0.0066, + "step": 40843 + }, + { + "epoch": 12.61, + "learning_rate": 6.339940018951974e-06, + "loss": 0.0081, + "step": 40844 + }, + { + "epoch": 12.61, + "learning_rate": 6.3394746072620465e-06, + "loss": 0.0071, + "step": 40845 + }, + { + "epoch": 12.61, + "learning_rate": 6.339009204727763e-06, + "loss": 0.0065, + "step": 40846 + }, + { + "epoch": 12.61, + "learning_rate": 6.338543811350287e-06, + "loss": 0.0079, + "step": 40847 + }, + { + "epoch": 12.61, + "learning_rate": 6.338078427130777e-06, + "loss": 0.0062, + "step": 40848 + }, + { + "epoch": 12.61, + "learning_rate": 6.3376130520704024e-06, + "loss": 0.0075, + "step": 40849 + }, + { + "epoch": 12.62, + "learning_rate": 6.337147686170328e-06, + "loss": 0.0076, + "step": 40850 + }, + { + "epoch": 12.62, + "learning_rate": 6.336682329431714e-06, + "loss": 0.007, + "step": 40851 + }, + { + "epoch": 12.62, + "learning_rate": 6.336216981855723e-06, + "loss": 0.0057, + "step": 40852 + }, + { + "epoch": 12.62, + "learning_rate": 6.3357516434435255e-06, + "loss": 0.0071, + "step": 40853 + }, + { + "epoch": 12.62, + "learning_rate": 6.335286314196278e-06, + "loss": 0.0067, + "step": 40854 + }, + { + "epoch": 12.62, + "learning_rate": 6.334820994115147e-06, + "loss": 0.0089, + "step": 40855 + }, + { + "epoch": 12.62, + "learning_rate": 6.3343556832013035e-06, + "loss": 0.008, + "step": 40856 + }, + { + "epoch": 12.62, + "learning_rate": 6.3338903814559004e-06, + "loss": 0.0066, + "step": 40857 + }, + { + "epoch": 12.62, + "learning_rate": 6.333425088880104e-06, + "loss": 0.0066, + "step": 40858 + }, + { + "epoch": 12.62, + "learning_rate": 6.3329598054750855e-06, + "loss": 0.0092, + "step": 40859 + }, + { + "epoch": 12.62, + "learning_rate": 6.3324945312419995e-06, + "loss": 0.0075, + "step": 40860 + }, + { + "epoch": 12.62, + "learning_rate": 6.332029266182015e-06, + "loss": 0.0068, + "step": 40861 + }, + { + "epoch": 12.62, + "learning_rate": 6.3315640102962915e-06, + "loss": 0.0069, + "step": 40862 + }, + { + "epoch": 12.62, + "learning_rate": 6.331098763586001e-06, + "loss": 0.0072, + "step": 40863 + }, + { + "epoch": 12.62, + "learning_rate": 6.330633526052299e-06, + "loss": 0.0071, + "step": 40864 + }, + { + "epoch": 12.62, + "learning_rate": 6.330168297696349e-06, + "loss": 0.007, + "step": 40865 + }, + { + "epoch": 12.62, + "learning_rate": 6.329703078519323e-06, + "loss": 0.0088, + "step": 40866 + }, + { + "epoch": 12.62, + "learning_rate": 6.3292378685223754e-06, + "loss": 0.0072, + "step": 40867 + }, + { + "epoch": 12.62, + "learning_rate": 6.328772667706671e-06, + "loss": 0.0067, + "step": 40868 + }, + { + "epoch": 12.62, + "learning_rate": 6.328307476073381e-06, + "loss": 0.0073, + "step": 40869 + }, + { + "epoch": 12.62, + "learning_rate": 6.327842293623661e-06, + "loss": 0.0091, + "step": 40870 + }, + { + "epoch": 12.62, + "learning_rate": 6.3273771203586776e-06, + "loss": 0.0078, + "step": 40871 + }, + { + "epoch": 12.62, + "learning_rate": 6.3269119562795955e-06, + "loss": 0.0072, + "step": 40872 + }, + { + "epoch": 12.62, + "learning_rate": 6.326446801387573e-06, + "loss": 0.0078, + "step": 40873 + }, + { + "epoch": 12.62, + "learning_rate": 6.325981655683779e-06, + "loss": 0.0077, + "step": 40874 + }, + { + "epoch": 12.62, + "learning_rate": 6.325516519169377e-06, + "loss": 0.0055, + "step": 40875 + }, + { + "epoch": 12.62, + "learning_rate": 6.3250513918455246e-06, + "loss": 0.0063, + "step": 40876 + }, + { + "epoch": 12.62, + "learning_rate": 6.32458627371339e-06, + "loss": 0.007, + "step": 40877 + }, + { + "epoch": 12.62, + "learning_rate": 6.324121164774138e-06, + "loss": 0.0078, + "step": 40878 + }, + { + "epoch": 12.62, + "learning_rate": 6.323656065028926e-06, + "loss": 0.0074, + "step": 40879 + }, + { + "epoch": 12.62, + "learning_rate": 6.323190974478922e-06, + "loss": 0.0066, + "step": 40880 + }, + { + "epoch": 12.62, + "learning_rate": 6.32272589312529e-06, + "loss": 0.0062, + "step": 40881 + }, + { + "epoch": 12.63, + "learning_rate": 6.32226082096919e-06, + "loss": 0.0075, + "step": 40882 + }, + { + "epoch": 12.63, + "learning_rate": 6.321795758011784e-06, + "loss": 0.0067, + "step": 40883 + }, + { + "epoch": 12.63, + "learning_rate": 6.321330704254241e-06, + "loss": 0.0069, + "step": 40884 + }, + { + "epoch": 12.63, + "learning_rate": 6.320865659697719e-06, + "loss": 0.0064, + "step": 40885 + }, + { + "epoch": 12.63, + "learning_rate": 6.3204006243433815e-06, + "loss": 0.0082, + "step": 40886 + }, + { + "epoch": 12.63, + "learning_rate": 6.319935598192397e-06, + "loss": 0.007, + "step": 40887 + }, + { + "epoch": 12.63, + "learning_rate": 6.3194705812459234e-06, + "loss": 0.0058, + "step": 40888 + }, + { + "epoch": 12.63, + "learning_rate": 6.319005573505121e-06, + "loss": 0.0085, + "step": 40889 + }, + { + "epoch": 12.63, + "learning_rate": 6.318540574971166e-06, + "loss": 0.0083, + "step": 40890 + }, + { + "epoch": 12.63, + "learning_rate": 6.318075585645205e-06, + "loss": 0.0065, + "step": 40891 + }, + { + "epoch": 12.63, + "learning_rate": 6.31761060552841e-06, + "loss": 0.0073, + "step": 40892 + }, + { + "epoch": 12.63, + "learning_rate": 6.317145634621942e-06, + "loss": 0.0066, + "step": 40893 + }, + { + "epoch": 12.63, + "learning_rate": 6.316680672926967e-06, + "loss": 0.0078, + "step": 40894 + }, + { + "epoch": 12.63, + "learning_rate": 6.316215720444644e-06, + "loss": 0.0067, + "step": 40895 + }, + { + "epoch": 12.63, + "learning_rate": 6.315750777176135e-06, + "loss": 0.0081, + "step": 40896 + }, + { + "epoch": 12.63, + "learning_rate": 6.31528584312261e-06, + "loss": 0.0075, + "step": 40897 + }, + { + "epoch": 12.63, + "learning_rate": 6.314820918285225e-06, + "loss": 0.0068, + "step": 40898 + }, + { + "epoch": 12.63, + "learning_rate": 6.314356002665143e-06, + "loss": 0.0088, + "step": 40899 + }, + { + "epoch": 12.63, + "learning_rate": 6.3138910962635345e-06, + "loss": 0.0071, + "step": 40900 + }, + { + "epoch": 12.63, + "learning_rate": 6.313426199081552e-06, + "loss": 0.0054, + "step": 40901 + }, + { + "epoch": 12.63, + "learning_rate": 6.312961311120363e-06, + "loss": 0.0081, + "step": 40902 + }, + { + "epoch": 12.63, + "learning_rate": 6.3124964323811325e-06, + "loss": 0.0063, + "step": 40903 + }, + { + "epoch": 12.63, + "learning_rate": 6.312031562865018e-06, + "loss": 0.008, + "step": 40904 + }, + { + "epoch": 12.63, + "learning_rate": 6.311566702573187e-06, + "loss": 0.008, + "step": 40905 + }, + { + "epoch": 12.63, + "learning_rate": 6.311101851506802e-06, + "loss": 0.0062, + "step": 40906 + }, + { + "epoch": 12.63, + "learning_rate": 6.31063700966702e-06, + "loss": 0.0095, + "step": 40907 + }, + { + "epoch": 12.63, + "learning_rate": 6.310172177055009e-06, + "loss": 0.0076, + "step": 40908 + }, + { + "epoch": 12.63, + "learning_rate": 6.309707353671934e-06, + "loss": 0.0059, + "step": 40909 + }, + { + "epoch": 12.63, + "learning_rate": 6.309242539518952e-06, + "loss": 0.0064, + "step": 40910 + }, + { + "epoch": 12.63, + "learning_rate": 6.308777734597225e-06, + "loss": 0.0083, + "step": 40911 + }, + { + "epoch": 12.63, + "learning_rate": 6.3083129389079214e-06, + "loss": 0.0085, + "step": 40912 + }, + { + "epoch": 12.63, + "learning_rate": 6.307848152452198e-06, + "loss": 0.0074, + "step": 40913 + }, + { + "epoch": 12.64, + "learning_rate": 6.30738337523122e-06, + "loss": 0.0074, + "step": 40914 + }, + { + "epoch": 12.64, + "learning_rate": 6.306918607246153e-06, + "loss": 0.008, + "step": 40915 + }, + { + "epoch": 12.64, + "learning_rate": 6.306453848498153e-06, + "loss": 0.007, + "step": 40916 + }, + { + "epoch": 12.64, + "learning_rate": 6.305989098988384e-06, + "loss": 0.0068, + "step": 40917 + }, + { + "epoch": 12.64, + "learning_rate": 6.305524358718013e-06, + "loss": 0.0107, + "step": 40918 + }, + { + "epoch": 12.64, + "learning_rate": 6.305059627688199e-06, + "loss": 0.0058, + "step": 40919 + }, + { + "epoch": 12.64, + "learning_rate": 6.304594905900106e-06, + "loss": 0.0073, + "step": 40920 + }, + { + "epoch": 12.64, + "learning_rate": 6.304130193354895e-06, + "loss": 0.0077, + "step": 40921 + }, + { + "epoch": 12.64, + "learning_rate": 6.303665490053725e-06, + "loss": 0.0067, + "step": 40922 + }, + { + "epoch": 12.64, + "learning_rate": 6.303200795997764e-06, + "loss": 0.0079, + "step": 40923 + }, + { + "epoch": 12.64, + "learning_rate": 6.3027361111881735e-06, + "loss": 0.0071, + "step": 40924 + }, + { + "epoch": 12.64, + "learning_rate": 6.30227143562611e-06, + "loss": 0.0059, + "step": 40925 + }, + { + "epoch": 12.64, + "learning_rate": 6.301806769312744e-06, + "loss": 0.0074, + "step": 40926 + }, + { + "epoch": 12.64, + "learning_rate": 6.3013421122492306e-06, + "loss": 0.0087, + "step": 40927 + }, + { + "epoch": 12.64, + "learning_rate": 6.300877464436739e-06, + "loss": 0.0076, + "step": 40928 + }, + { + "epoch": 12.64, + "learning_rate": 6.300412825876425e-06, + "loss": 0.0082, + "step": 40929 + }, + { + "epoch": 12.64, + "learning_rate": 6.299948196569452e-06, + "loss": 0.0074, + "step": 40930 + }, + { + "epoch": 12.64, + "learning_rate": 6.299483576516989e-06, + "loss": 0.0069, + "step": 40931 + }, + { + "epoch": 12.64, + "learning_rate": 6.2990189657201875e-06, + "loss": 0.0068, + "step": 40932 + }, + { + "epoch": 12.64, + "learning_rate": 6.298554364180216e-06, + "loss": 0.0127, + "step": 40933 + }, + { + "epoch": 12.64, + "learning_rate": 6.298089771898237e-06, + "loss": 0.0078, + "step": 40934 + }, + { + "epoch": 12.64, + "learning_rate": 6.297625188875407e-06, + "loss": 0.008, + "step": 40935 + }, + { + "epoch": 12.64, + "learning_rate": 6.297160615112894e-06, + "loss": 0.0078, + "step": 40936 + }, + { + "epoch": 12.64, + "learning_rate": 6.296696050611858e-06, + "loss": 0.0071, + "step": 40937 + }, + { + "epoch": 12.64, + "learning_rate": 6.296231495373457e-06, + "loss": 0.007, + "step": 40938 + }, + { + "epoch": 12.64, + "learning_rate": 6.29576694939886e-06, + "loss": 0.0067, + "step": 40939 + }, + { + "epoch": 12.64, + "learning_rate": 6.295302412689227e-06, + "loss": 0.0076, + "step": 40940 + }, + { + "epoch": 12.64, + "learning_rate": 6.294837885245716e-06, + "loss": 0.0086, + "step": 40941 + }, + { + "epoch": 12.64, + "learning_rate": 6.294373367069489e-06, + "loss": 0.0083, + "step": 40942 + }, + { + "epoch": 12.64, + "learning_rate": 6.293908858161714e-06, + "loss": 0.0064, + "step": 40943 + }, + { + "epoch": 12.64, + "learning_rate": 6.2934443585235485e-06, + "loss": 0.0062, + "step": 40944 + }, + { + "epoch": 12.64, + "learning_rate": 6.2929798681561505e-06, + "loss": 0.0076, + "step": 40945 + }, + { + "epoch": 12.64, + "learning_rate": 6.292515387060691e-06, + "loss": 0.0069, + "step": 40946 + }, + { + "epoch": 12.65, + "learning_rate": 6.292050915238325e-06, + "loss": 0.0065, + "step": 40947 + }, + { + "epoch": 12.65, + "learning_rate": 6.291586452690213e-06, + "loss": 0.007, + "step": 40948 + }, + { + "epoch": 12.65, + "learning_rate": 6.291121999417527e-06, + "loss": 0.0066, + "step": 40949 + }, + { + "epoch": 12.65, + "learning_rate": 6.290657555421414e-06, + "loss": 0.0061, + "step": 40950 + }, + { + "epoch": 12.65, + "learning_rate": 6.290193120703045e-06, + "loss": 0.0074, + "step": 40951 + }, + { + "epoch": 12.65, + "learning_rate": 6.289728695263584e-06, + "loss": 0.0079, + "step": 40952 + }, + { + "epoch": 12.65, + "learning_rate": 6.2892642791041814e-06, + "loss": 0.0086, + "step": 40953 + }, + { + "epoch": 12.65, + "learning_rate": 6.288799872226009e-06, + "loss": 0.0069, + "step": 40954 + }, + { + "epoch": 12.65, + "learning_rate": 6.288335474630227e-06, + "loss": 0.0073, + "step": 40955 + }, + { + "epoch": 12.65, + "learning_rate": 6.2878710863179905e-06, + "loss": 0.0067, + "step": 40956 + }, + { + "epoch": 12.65, + "learning_rate": 6.287406707290466e-06, + "loss": 0.009, + "step": 40957 + }, + { + "epoch": 12.65, + "learning_rate": 6.286942337548819e-06, + "loss": 0.0085, + "step": 40958 + }, + { + "epoch": 12.65, + "learning_rate": 6.286477977094204e-06, + "loss": 0.007, + "step": 40959 + }, + { + "epoch": 12.65, + "learning_rate": 6.2860136259277825e-06, + "loss": 0.0064, + "step": 40960 + }, + { + "epoch": 12.65, + "learning_rate": 6.28554928405072e-06, + "loss": 0.0077, + "step": 40961 + }, + { + "epoch": 12.65, + "learning_rate": 6.285084951464178e-06, + "loss": 0.0056, + "step": 40962 + }, + { + "epoch": 12.65, + "learning_rate": 6.284620628169313e-06, + "loss": 0.0068, + "step": 40963 + }, + { + "epoch": 12.65, + "learning_rate": 6.284156314167291e-06, + "loss": 0.0077, + "step": 40964 + }, + { + "epoch": 12.65, + "learning_rate": 6.283692009459274e-06, + "loss": 0.0084, + "step": 40965 + }, + { + "epoch": 12.65, + "learning_rate": 6.283227714046416e-06, + "loss": 0.0092, + "step": 40966 + }, + { + "epoch": 12.65, + "learning_rate": 6.282763427929887e-06, + "loss": 0.0082, + "step": 40967 + }, + { + "epoch": 12.65, + "learning_rate": 6.282299151110845e-06, + "loss": 0.007, + "step": 40968 + }, + { + "epoch": 12.65, + "learning_rate": 6.281834883590447e-06, + "loss": 0.0074, + "step": 40969 + }, + { + "epoch": 12.65, + "learning_rate": 6.281370625369862e-06, + "loss": 0.0065, + "step": 40970 + }, + { + "epoch": 12.65, + "learning_rate": 6.2809063764502485e-06, + "loss": 0.0091, + "step": 40971 + }, + { + "epoch": 12.65, + "learning_rate": 6.280442136832764e-06, + "loss": 0.0066, + "step": 40972 + }, + { + "epoch": 12.65, + "learning_rate": 6.279977906518571e-06, + "loss": 0.0067, + "step": 40973 + }, + { + "epoch": 12.65, + "learning_rate": 6.279513685508833e-06, + "loss": 0.0073, + "step": 40974 + }, + { + "epoch": 12.65, + "learning_rate": 6.279049473804711e-06, + "loss": 0.0089, + "step": 40975 + }, + { + "epoch": 12.65, + "learning_rate": 6.278585271407363e-06, + "loss": 0.0073, + "step": 40976 + }, + { + "epoch": 12.65, + "learning_rate": 6.278121078317954e-06, + "loss": 0.0078, + "step": 40977 + }, + { + "epoch": 12.65, + "learning_rate": 6.277656894537641e-06, + "loss": 0.0089, + "step": 40978 + }, + { + "epoch": 12.66, + "learning_rate": 6.277192720067586e-06, + "loss": 0.0072, + "step": 40979 + }, + { + "epoch": 12.66, + "learning_rate": 6.276728554908957e-06, + "loss": 0.0083, + "step": 40980 + }, + { + "epoch": 12.66, + "learning_rate": 6.276264399062902e-06, + "loss": 0.009, + "step": 40981 + }, + { + "epoch": 12.66, + "learning_rate": 6.275800252530593e-06, + "loss": 0.0075, + "step": 40982 + }, + { + "epoch": 12.66, + "learning_rate": 6.275336115313187e-06, + "loss": 0.0075, + "step": 40983 + }, + { + "epoch": 12.66, + "learning_rate": 6.274871987411841e-06, + "loss": 0.0087, + "step": 40984 + }, + { + "epoch": 12.66, + "learning_rate": 6.274407868827721e-06, + "loss": 0.0074, + "step": 40985 + }, + { + "epoch": 12.66, + "learning_rate": 6.2739437595619905e-06, + "loss": 0.0077, + "step": 40986 + }, + { + "epoch": 12.66, + "learning_rate": 6.2734796596158e-06, + "loss": 0.0059, + "step": 40987 + }, + { + "epoch": 12.66, + "learning_rate": 6.273015568990319e-06, + "loss": 0.0072, + "step": 40988 + }, + { + "epoch": 12.66, + "learning_rate": 6.272551487686709e-06, + "loss": 0.01, + "step": 40989 + }, + { + "epoch": 12.66, + "learning_rate": 6.272087415706125e-06, + "loss": 0.0072, + "step": 40990 + }, + { + "epoch": 12.66, + "learning_rate": 6.271623353049728e-06, + "loss": 0.0061, + "step": 40991 + }, + { + "epoch": 12.66, + "learning_rate": 6.271159299718683e-06, + "loss": 0.0065, + "step": 40992 + }, + { + "epoch": 12.66, + "learning_rate": 6.270695255714152e-06, + "loss": 0.0078, + "step": 40993 + }, + { + "epoch": 12.66, + "learning_rate": 6.270231221037287e-06, + "loss": 0.0072, + "step": 40994 + }, + { + "epoch": 12.66, + "learning_rate": 6.2697671956892555e-06, + "loss": 0.0067, + "step": 40995 + }, + { + "epoch": 12.66, + "learning_rate": 6.26930317967122e-06, + "loss": 0.008, + "step": 40996 + }, + { + "epoch": 12.66, + "learning_rate": 6.268839172984334e-06, + "loss": 0.0067, + "step": 40997 + }, + { + "epoch": 12.66, + "learning_rate": 6.268375175629762e-06, + "loss": 0.0067, + "step": 40998 + }, + { + "epoch": 12.66, + "learning_rate": 6.267911187608667e-06, + "loss": 0.0068, + "step": 40999 + }, + { + "epoch": 12.66, + "learning_rate": 6.267447208922204e-06, + "loss": 0.008, + "step": 41000 + }, + { + "epoch": 12.66, + "learning_rate": 6.266983239571536e-06, + "loss": 0.0059, + "step": 41001 + }, + { + "epoch": 12.66, + "learning_rate": 6.2665192795578265e-06, + "loss": 0.0064, + "step": 41002 + }, + { + "epoch": 12.66, + "learning_rate": 6.266055328882232e-06, + "loss": 0.0095, + "step": 41003 + }, + { + "epoch": 12.66, + "learning_rate": 6.265591387545911e-06, + "loss": 0.0065, + "step": 41004 + }, + { + "epoch": 12.66, + "learning_rate": 6.265127455550033e-06, + "loss": 0.0072, + "step": 41005 + }, + { + "epoch": 12.66, + "learning_rate": 6.264663532895748e-06, + "loss": 0.0081, + "step": 41006 + }, + { + "epoch": 12.66, + "learning_rate": 6.264199619584221e-06, + "loss": 0.0065, + "step": 41007 + }, + { + "epoch": 12.66, + "learning_rate": 6.2637357156166145e-06, + "loss": 0.0068, + "step": 41008 + }, + { + "epoch": 12.66, + "learning_rate": 6.263271820994086e-06, + "loss": 0.0089, + "step": 41009 + }, + { + "epoch": 12.66, + "learning_rate": 6.262807935717795e-06, + "loss": 0.0062, + "step": 41010 + }, + { + "epoch": 12.66, + "learning_rate": 6.262344059788905e-06, + "loss": 0.0058, + "step": 41011 + }, + { + "epoch": 12.67, + "learning_rate": 6.261880193208571e-06, + "loss": 0.0067, + "step": 41012 + }, + { + "epoch": 12.67, + "learning_rate": 6.2614163359779575e-06, + "loss": 0.0065, + "step": 41013 + }, + { + "epoch": 12.67, + "learning_rate": 6.2609524880982265e-06, + "loss": 0.0074, + "step": 41014 + }, + { + "epoch": 12.67, + "learning_rate": 6.260488649570531e-06, + "loss": 0.0069, + "step": 41015 + }, + { + "epoch": 12.67, + "learning_rate": 6.260024820396037e-06, + "loss": 0.0073, + "step": 41016 + }, + { + "epoch": 12.67, + "learning_rate": 6.2595610005759055e-06, + "loss": 0.0071, + "step": 41017 + }, + { + "epoch": 12.67, + "learning_rate": 6.259097190111289e-06, + "loss": 0.0076, + "step": 41018 + }, + { + "epoch": 12.67, + "learning_rate": 6.258633389003357e-06, + "loss": 0.0064, + "step": 41019 + }, + { + "epoch": 12.67, + "learning_rate": 6.258169597253266e-06, + "loss": 0.0075, + "step": 41020 + }, + { + "epoch": 12.67, + "learning_rate": 6.257705814862173e-06, + "loss": 0.0059, + "step": 41021 + }, + { + "epoch": 12.67, + "learning_rate": 6.257242041831239e-06, + "loss": 0.0072, + "step": 41022 + }, + { + "epoch": 12.67, + "learning_rate": 6.2567782781616284e-06, + "loss": 0.0071, + "step": 41023 + }, + { + "epoch": 12.67, + "learning_rate": 6.256314523854496e-06, + "loss": 0.0058, + "step": 41024 + }, + { + "epoch": 12.67, + "learning_rate": 6.255850778911003e-06, + "loss": 0.0071, + "step": 41025 + }, + { + "epoch": 12.67, + "learning_rate": 6.2553870433323105e-06, + "loss": 0.0078, + "step": 41026 + }, + { + "epoch": 12.67, + "learning_rate": 6.254923317119581e-06, + "loss": 0.0075, + "step": 41027 + }, + { + "epoch": 12.67, + "learning_rate": 6.254459600273968e-06, + "loss": 0.008, + "step": 41028 + }, + { + "epoch": 12.67, + "learning_rate": 6.253995892796636e-06, + "loss": 0.0076, + "step": 41029 + }, + { + "epoch": 12.67, + "learning_rate": 6.253532194688745e-06, + "loss": 0.0087, + "step": 41030 + }, + { + "epoch": 12.67, + "learning_rate": 6.253068505951452e-06, + "loss": 0.0069, + "step": 41031 + }, + { + "epoch": 12.67, + "learning_rate": 6.252604826585915e-06, + "loss": 0.0073, + "step": 41032 + }, + { + "epoch": 12.67, + "learning_rate": 6.252141156593302e-06, + "loss": 0.0062, + "step": 41033 + }, + { + "epoch": 12.67, + "learning_rate": 6.251677495974766e-06, + "loss": 0.0069, + "step": 41034 + }, + { + "epoch": 12.67, + "learning_rate": 6.251213844731465e-06, + "loss": 0.0075, + "step": 41035 + }, + { + "epoch": 12.67, + "learning_rate": 6.2507502028645665e-06, + "loss": 0.0075, + "step": 41036 + }, + { + "epoch": 12.67, + "learning_rate": 6.250286570375223e-06, + "loss": 0.0066, + "step": 41037 + }, + { + "epoch": 12.67, + "learning_rate": 6.249822947264595e-06, + "loss": 0.0062, + "step": 41038 + }, + { + "epoch": 12.67, + "learning_rate": 6.24935933353385e-06, + "loss": 0.0069, + "step": 41039 + }, + { + "epoch": 12.67, + "learning_rate": 6.2488957291841345e-06, + "loss": 0.0068, + "step": 41040 + }, + { + "epoch": 12.67, + "learning_rate": 6.248432134216618e-06, + "loss": 0.0067, + "step": 41041 + }, + { + "epoch": 12.67, + "learning_rate": 6.247968548632459e-06, + "loss": 0.006, + "step": 41042 + }, + { + "epoch": 12.67, + "learning_rate": 6.247504972432811e-06, + "loss": 0.0075, + "step": 41043 + }, + { + "epoch": 12.68, + "learning_rate": 6.247041405618839e-06, + "loss": 0.0075, + "step": 41044 + }, + { + "epoch": 12.68, + "learning_rate": 6.246577848191703e-06, + "loss": 0.0068, + "step": 41045 + }, + { + "epoch": 12.68, + "learning_rate": 6.246114300152556e-06, + "loss": 0.0061, + "step": 41046 + }, + { + "epoch": 12.68, + "learning_rate": 6.245650761502564e-06, + "loss": 0.0081, + "step": 41047 + }, + { + "epoch": 12.68, + "learning_rate": 6.245187232242886e-06, + "loss": 0.009, + "step": 41048 + }, + { + "epoch": 12.68, + "learning_rate": 6.244723712374678e-06, + "loss": 0.0095, + "step": 41049 + }, + { + "epoch": 12.68, + "learning_rate": 6.2442602018991e-06, + "loss": 0.0076, + "step": 41050 + }, + { + "epoch": 12.68, + "learning_rate": 6.243796700817315e-06, + "loss": 0.0083, + "step": 41051 + }, + { + "epoch": 12.68, + "learning_rate": 6.2433332091304775e-06, + "loss": 0.0067, + "step": 41052 + }, + { + "epoch": 12.68, + "learning_rate": 6.242869726839746e-06, + "loss": 0.0061, + "step": 41053 + }, + { + "epoch": 12.68, + "learning_rate": 6.242406253946289e-06, + "loss": 0.0078, + "step": 41054 + }, + { + "epoch": 12.68, + "learning_rate": 6.241942790451255e-06, + "loss": 0.0061, + "step": 41055 + }, + { + "epoch": 12.68, + "learning_rate": 6.241479336355807e-06, + "loss": 0.0074, + "step": 41056 + }, + { + "epoch": 12.68, + "learning_rate": 6.241015891661106e-06, + "loss": 0.0059, + "step": 41057 + }, + { + "epoch": 12.68, + "learning_rate": 6.2405524563683114e-06, + "loss": 0.0063, + "step": 41058 + }, + { + "epoch": 12.68, + "learning_rate": 6.2400890304785795e-06, + "loss": 0.0076, + "step": 41059 + }, + { + "epoch": 12.68, + "learning_rate": 6.239625613993069e-06, + "loss": 0.0075, + "step": 41060 + }, + { + "epoch": 12.68, + "learning_rate": 6.239162206912943e-06, + "loss": 0.0085, + "step": 41061 + }, + { + "epoch": 12.68, + "learning_rate": 6.238698809239358e-06, + "loss": 0.0095, + "step": 41062 + }, + { + "epoch": 12.68, + "learning_rate": 6.23823542097347e-06, + "loss": 0.0075, + "step": 41063 + }, + { + "epoch": 12.68, + "learning_rate": 6.237772042116448e-06, + "loss": 0.0059, + "step": 41064 + }, + { + "epoch": 12.68, + "learning_rate": 6.2373086726694395e-06, + "loss": 0.0077, + "step": 41065 + }, + { + "epoch": 12.68, + "learning_rate": 6.236845312633607e-06, + "loss": 0.0064, + "step": 41066 + }, + { + "epoch": 12.68, + "learning_rate": 6.236381962010115e-06, + "loss": 0.0061, + "step": 41067 + }, + { + "epoch": 12.68, + "learning_rate": 6.235918620800117e-06, + "loss": 0.006, + "step": 41068 + }, + { + "epoch": 12.68, + "learning_rate": 6.23545528900477e-06, + "loss": 0.0077, + "step": 41069 + }, + { + "epoch": 12.68, + "learning_rate": 6.234991966625241e-06, + "loss": 0.007, + "step": 41070 + }, + { + "epoch": 12.68, + "learning_rate": 6.2345286536626795e-06, + "loss": 0.0064, + "step": 41071 + }, + { + "epoch": 12.68, + "learning_rate": 6.23406535011825e-06, + "loss": 0.0087, + "step": 41072 + }, + { + "epoch": 12.68, + "learning_rate": 6.233602055993111e-06, + "loss": 0.0066, + "step": 41073 + }, + { + "epoch": 12.68, + "learning_rate": 6.233138771288417e-06, + "loss": 0.0068, + "step": 41074 + }, + { + "epoch": 12.68, + "learning_rate": 6.232675496005333e-06, + "loss": 0.0059, + "step": 41075 + }, + { + "epoch": 12.69, + "learning_rate": 6.232212230145015e-06, + "loss": 0.0088, + "step": 41076 + }, + { + "epoch": 12.69, + "learning_rate": 6.231748973708618e-06, + "loss": 0.0065, + "step": 41077 + }, + { + "epoch": 12.69, + "learning_rate": 6.231285726697307e-06, + "loss": 0.005, + "step": 41078 + }, + { + "epoch": 12.69, + "learning_rate": 6.230822489112238e-06, + "loss": 0.0078, + "step": 41079 + }, + { + "epoch": 12.69, + "learning_rate": 6.2303592609545686e-06, + "loss": 0.0075, + "step": 41080 + }, + { + "epoch": 12.69, + "learning_rate": 6.2298960422254566e-06, + "loss": 0.0073, + "step": 41081 + }, + { + "epoch": 12.69, + "learning_rate": 6.229432832926066e-06, + "loss": 0.0067, + "step": 41082 + }, + { + "epoch": 12.69, + "learning_rate": 6.2289696330575485e-06, + "loss": 0.007, + "step": 41083 + }, + { + "epoch": 12.69, + "learning_rate": 6.228506442621065e-06, + "loss": 0.0085, + "step": 41084 + }, + { + "epoch": 12.69, + "learning_rate": 6.228043261617778e-06, + "loss": 0.007, + "step": 41085 + }, + { + "epoch": 12.69, + "learning_rate": 6.2275800900488415e-06, + "loss": 0.0081, + "step": 41086 + }, + { + "epoch": 12.69, + "learning_rate": 6.227116927915412e-06, + "loss": 0.0061, + "step": 41087 + }, + { + "epoch": 12.69, + "learning_rate": 6.226653775218659e-06, + "loss": 0.0068, + "step": 41088 + }, + { + "epoch": 12.69, + "learning_rate": 6.226190631959726e-06, + "loss": 0.0074, + "step": 41089 + }, + { + "epoch": 12.69, + "learning_rate": 6.22572749813978e-06, + "loss": 0.0066, + "step": 41090 + }, + { + "epoch": 12.69, + "learning_rate": 6.225264373759976e-06, + "loss": 0.0072, + "step": 41091 + }, + { + "epoch": 12.69, + "learning_rate": 6.22480125882148e-06, + "loss": 0.0105, + "step": 41092 + }, + { + "epoch": 12.69, + "learning_rate": 6.22433815332544e-06, + "loss": 0.0077, + "step": 41093 + }, + { + "epoch": 12.69, + "learning_rate": 6.2238750572730185e-06, + "loss": 0.0063, + "step": 41094 + }, + { + "epoch": 12.69, + "learning_rate": 6.223411970665379e-06, + "loss": 0.0083, + "step": 41095 + }, + { + "epoch": 12.69, + "learning_rate": 6.222948893503671e-06, + "loss": 0.0073, + "step": 41096 + }, + { + "epoch": 12.69, + "learning_rate": 6.222485825789056e-06, + "loss": 0.0068, + "step": 41097 + }, + { + "epoch": 12.69, + "learning_rate": 6.2220227675227e-06, + "loss": 0.0068, + "step": 41098 + }, + { + "epoch": 12.69, + "learning_rate": 6.221559718705745e-06, + "loss": 0.007, + "step": 41099 + }, + { + "epoch": 12.69, + "learning_rate": 6.221096679339362e-06, + "loss": 0.0065, + "step": 41100 + }, + { + "epoch": 12.69, + "learning_rate": 6.220633649424708e-06, + "loss": 0.0066, + "step": 41101 + }, + { + "epoch": 12.69, + "learning_rate": 6.220170628962934e-06, + "loss": 0.0077, + "step": 41102 + }, + { + "epoch": 12.69, + "learning_rate": 6.219707617955204e-06, + "loss": 0.0069, + "step": 41103 + }, + { + "epoch": 12.69, + "learning_rate": 6.2192446164026775e-06, + "loss": 0.007, + "step": 41104 + }, + { + "epoch": 12.69, + "learning_rate": 6.218781624306507e-06, + "loss": 0.0083, + "step": 41105 + }, + { + "epoch": 12.69, + "learning_rate": 6.218318641667853e-06, + "loss": 0.0078, + "step": 41106 + }, + { + "epoch": 12.69, + "learning_rate": 6.217855668487877e-06, + "loss": 0.0095, + "step": 41107 + }, + { + "epoch": 12.69, + "learning_rate": 6.217392704767732e-06, + "loss": 0.0079, + "step": 41108 + }, + { + "epoch": 12.7, + "learning_rate": 6.216929750508576e-06, + "loss": 0.0065, + "step": 41109 + }, + { + "epoch": 12.7, + "learning_rate": 6.2164668057115715e-06, + "loss": 0.0076, + "step": 41110 + }, + { + "epoch": 12.7, + "learning_rate": 6.216003870377872e-06, + "loss": 0.007, + "step": 41111 + }, + { + "epoch": 12.7, + "learning_rate": 6.215540944508636e-06, + "loss": 0.0077, + "step": 41112 + }, + { + "epoch": 12.7, + "learning_rate": 6.215078028105024e-06, + "loss": 0.0066, + "step": 41113 + }, + { + "epoch": 12.7, + "learning_rate": 6.214615121168193e-06, + "loss": 0.0074, + "step": 41114 + }, + { + "epoch": 12.7, + "learning_rate": 6.214152223699296e-06, + "loss": 0.006, + "step": 41115 + }, + { + "epoch": 12.7, + "learning_rate": 6.2136893356994996e-06, + "loss": 0.0072, + "step": 41116 + }, + { + "epoch": 12.7, + "learning_rate": 6.2132264571699544e-06, + "loss": 0.0074, + "step": 41117 + }, + { + "epoch": 12.7, + "learning_rate": 6.212763588111821e-06, + "loss": 0.0054, + "step": 41118 + }, + { + "epoch": 12.7, + "learning_rate": 6.212300728526257e-06, + "loss": 0.0063, + "step": 41119 + }, + { + "epoch": 12.7, + "learning_rate": 6.211837878414418e-06, + "loss": 0.0074, + "step": 41120 + }, + { + "epoch": 12.7, + "learning_rate": 6.211375037777464e-06, + "loss": 0.0071, + "step": 41121 + }, + { + "epoch": 12.7, + "learning_rate": 6.210912206616551e-06, + "loss": 0.007, + "step": 41122 + }, + { + "epoch": 12.7, + "learning_rate": 6.210449384932841e-06, + "loss": 0.0068, + "step": 41123 + }, + { + "epoch": 12.7, + "learning_rate": 6.209986572727485e-06, + "loss": 0.0101, + "step": 41124 + }, + { + "epoch": 12.7, + "learning_rate": 6.209523770001644e-06, + "loss": 0.0061, + "step": 41125 + }, + { + "epoch": 12.7, + "learning_rate": 6.209060976756478e-06, + "loss": 0.0082, + "step": 41126 + }, + { + "epoch": 12.7, + "learning_rate": 6.2085981929931406e-06, + "loss": 0.0075, + "step": 41127 + }, + { + "epoch": 12.7, + "learning_rate": 6.20813541871279e-06, + "loss": 0.0093, + "step": 41128 + }, + { + "epoch": 12.7, + "learning_rate": 6.2076726539165876e-06, + "loss": 0.0062, + "step": 41129 + }, + { + "epoch": 12.7, + "learning_rate": 6.2072098986056825e-06, + "loss": 0.0069, + "step": 41130 + }, + { + "epoch": 12.7, + "learning_rate": 6.20674715278124e-06, + "loss": 0.0063, + "step": 41131 + }, + { + "epoch": 12.7, + "learning_rate": 6.206284416444416e-06, + "loss": 0.0083, + "step": 41132 + }, + { + "epoch": 12.7, + "learning_rate": 6.205821689596363e-06, + "loss": 0.0062, + "step": 41133 + }, + { + "epoch": 12.7, + "learning_rate": 6.205358972238244e-06, + "loss": 0.006, + "step": 41134 + }, + { + "epoch": 12.7, + "learning_rate": 6.204896264371216e-06, + "loss": 0.0075, + "step": 41135 + }, + { + "epoch": 12.7, + "learning_rate": 6.204433565996431e-06, + "loss": 0.0067, + "step": 41136 + }, + { + "epoch": 12.7, + "learning_rate": 6.203970877115051e-06, + "loss": 0.0068, + "step": 41137 + }, + { + "epoch": 12.7, + "learning_rate": 6.203508197728234e-06, + "loss": 0.0074, + "step": 41138 + }, + { + "epoch": 12.7, + "learning_rate": 6.203045527837135e-06, + "loss": 0.0069, + "step": 41139 + }, + { + "epoch": 12.7, + "learning_rate": 6.202582867442909e-06, + "loss": 0.0079, + "step": 41140 + }, + { + "epoch": 12.71, + "learning_rate": 6.20212021654672e-06, + "loss": 0.0075, + "step": 41141 + }, + { + "epoch": 12.71, + "learning_rate": 6.2016575751497175e-06, + "loss": 0.0074, + "step": 41142 + }, + { + "epoch": 12.71, + "learning_rate": 6.201194943253061e-06, + "loss": 0.0066, + "step": 41143 + }, + { + "epoch": 12.71, + "learning_rate": 6.200732320857914e-06, + "loss": 0.0078, + "step": 41144 + }, + { + "epoch": 12.71, + "learning_rate": 6.200269707965426e-06, + "loss": 0.0077, + "step": 41145 + }, + { + "epoch": 12.71, + "learning_rate": 6.199807104576754e-06, + "loss": 0.0081, + "step": 41146 + }, + { + "epoch": 12.71, + "learning_rate": 6.1993445106930635e-06, + "loss": 0.0082, + "step": 41147 + }, + { + "epoch": 12.71, + "learning_rate": 6.198881926315501e-06, + "loss": 0.0065, + "step": 41148 + }, + { + "epoch": 12.71, + "learning_rate": 6.198419351445229e-06, + "loss": 0.009, + "step": 41149 + }, + { + "epoch": 12.71, + "learning_rate": 6.197956786083405e-06, + "loss": 0.0074, + "step": 41150 + }, + { + "epoch": 12.71, + "learning_rate": 6.19749423023118e-06, + "loss": 0.0078, + "step": 41151 + }, + { + "epoch": 12.71, + "learning_rate": 6.197031683889719e-06, + "loss": 0.0062, + "step": 41152 + }, + { + "epoch": 12.71, + "learning_rate": 6.196569147060177e-06, + "loss": 0.0069, + "step": 41153 + }, + { + "epoch": 12.71, + "learning_rate": 6.1961066197437045e-06, + "loss": 0.0063, + "step": 41154 + }, + { + "epoch": 12.71, + "learning_rate": 6.195644101941467e-06, + "loss": 0.0081, + "step": 41155 + }, + { + "epoch": 12.71, + "learning_rate": 6.195181593654613e-06, + "loss": 0.0066, + "step": 41156 + }, + { + "epoch": 12.71, + "learning_rate": 6.194719094884312e-06, + "loss": 0.0074, + "step": 41157 + }, + { + "epoch": 12.71, + "learning_rate": 6.1942566056317055e-06, + "loss": 0.006, + "step": 41158 + }, + { + "epoch": 12.71, + "learning_rate": 6.193794125897959e-06, + "loss": 0.0081, + "step": 41159 + }, + { + "epoch": 12.71, + "learning_rate": 6.19333165568423e-06, + "loss": 0.0071, + "step": 41160 + }, + { + "epoch": 12.71, + "learning_rate": 6.192869194991668e-06, + "loss": 0.0059, + "step": 41161 + }, + { + "epoch": 12.71, + "learning_rate": 6.192406743821437e-06, + "loss": 0.0068, + "step": 41162 + }, + { + "epoch": 12.71, + "learning_rate": 6.191944302174695e-06, + "loss": 0.0068, + "step": 41163 + }, + { + "epoch": 12.71, + "learning_rate": 6.191481870052589e-06, + "loss": 0.0093, + "step": 41164 + }, + { + "epoch": 12.71, + "learning_rate": 6.1910194474562835e-06, + "loss": 0.0063, + "step": 41165 + }, + { + "epoch": 12.71, + "learning_rate": 6.190557034386936e-06, + "loss": 0.0074, + "step": 41166 + }, + { + "epoch": 12.71, + "learning_rate": 6.190094630845698e-06, + "loss": 0.0072, + "step": 41167 + }, + { + "epoch": 12.71, + "learning_rate": 6.189632236833725e-06, + "loss": 0.0086, + "step": 41168 + }, + { + "epoch": 12.71, + "learning_rate": 6.189169852352181e-06, + "loss": 0.0084, + "step": 41169 + }, + { + "epoch": 12.71, + "learning_rate": 6.188707477402218e-06, + "loss": 0.0073, + "step": 41170 + }, + { + "epoch": 12.71, + "learning_rate": 6.188245111984989e-06, + "loss": 0.0069, + "step": 41171 + }, + { + "epoch": 12.71, + "learning_rate": 6.187782756101659e-06, + "loss": 0.0067, + "step": 41172 + }, + { + "epoch": 12.72, + "learning_rate": 6.187320409753376e-06, + "loss": 0.0063, + "step": 41173 + }, + { + "epoch": 12.72, + "learning_rate": 6.1868580729413e-06, + "loss": 0.0088, + "step": 41174 + }, + { + "epoch": 12.72, + "learning_rate": 6.186395745666591e-06, + "loss": 0.0083, + "step": 41175 + }, + { + "epoch": 12.72, + "learning_rate": 6.185933427930399e-06, + "loss": 0.0062, + "step": 41176 + }, + { + "epoch": 12.72, + "learning_rate": 6.185471119733885e-06, + "loss": 0.0083, + "step": 41177 + }, + { + "epoch": 12.72, + "learning_rate": 6.185008821078205e-06, + "loss": 0.006, + "step": 41178 + }, + { + "epoch": 12.72, + "learning_rate": 6.184546531964508e-06, + "loss": 0.0068, + "step": 41179 + }, + { + "epoch": 12.72, + "learning_rate": 6.184084252393958e-06, + "loss": 0.0069, + "step": 41180 + }, + { + "epoch": 12.72, + "learning_rate": 6.183621982367714e-06, + "loss": 0.0068, + "step": 41181 + }, + { + "epoch": 12.72, + "learning_rate": 6.183159721886921e-06, + "loss": 0.008, + "step": 41182 + }, + { + "epoch": 12.72, + "learning_rate": 6.182697470952744e-06, + "loss": 0.0073, + "step": 41183 + }, + { + "epoch": 12.72, + "learning_rate": 6.18223522956634e-06, + "loss": 0.0094, + "step": 41184 + }, + { + "epoch": 12.72, + "learning_rate": 6.181772997728857e-06, + "loss": 0.0083, + "step": 41185 + }, + { + "epoch": 12.72, + "learning_rate": 6.181310775441458e-06, + "loss": 0.0085, + "step": 41186 + }, + { + "epoch": 12.72, + "learning_rate": 6.1808485627053e-06, + "loss": 0.0064, + "step": 41187 + }, + { + "epoch": 12.72, + "learning_rate": 6.180386359521534e-06, + "loss": 0.0079, + "step": 41188 + }, + { + "epoch": 12.72, + "learning_rate": 6.179924165891315e-06, + "loss": 0.0075, + "step": 41189 + }, + { + "epoch": 12.72, + "learning_rate": 6.179461981815806e-06, + "loss": 0.0085, + "step": 41190 + }, + { + "epoch": 12.72, + "learning_rate": 6.178999807296162e-06, + "loss": 0.007, + "step": 41191 + }, + { + "epoch": 12.72, + "learning_rate": 6.178537642333532e-06, + "loss": 0.0073, + "step": 41192 + }, + { + "epoch": 12.72, + "learning_rate": 6.178075486929078e-06, + "loss": 0.0061, + "step": 41193 + }, + { + "epoch": 12.72, + "learning_rate": 6.177613341083957e-06, + "loss": 0.0079, + "step": 41194 + }, + { + "epoch": 12.72, + "learning_rate": 6.1771512047993166e-06, + "loss": 0.0095, + "step": 41195 + }, + { + "epoch": 12.72, + "learning_rate": 6.176689078076321e-06, + "loss": 0.0069, + "step": 41196 + }, + { + "epoch": 12.72, + "learning_rate": 6.176226960916125e-06, + "loss": 0.0076, + "step": 41197 + }, + { + "epoch": 12.72, + "learning_rate": 6.175764853319881e-06, + "loss": 0.0067, + "step": 41198 + }, + { + "epoch": 12.72, + "learning_rate": 6.175302755288746e-06, + "loss": 0.0066, + "step": 41199 + }, + { + "epoch": 12.72, + "learning_rate": 6.174840666823878e-06, + "loss": 0.0058, + "step": 41200 + }, + { + "epoch": 12.72, + "learning_rate": 6.1743785879264305e-06, + "loss": 0.0073, + "step": 41201 + }, + { + "epoch": 12.72, + "learning_rate": 6.173916518597558e-06, + "loss": 0.0091, + "step": 41202 + }, + { + "epoch": 12.72, + "learning_rate": 6.173454458838421e-06, + "loss": 0.008, + "step": 41203 + }, + { + "epoch": 12.72, + "learning_rate": 6.172992408650171e-06, + "loss": 0.0074, + "step": 41204 + }, + { + "epoch": 12.72, + "learning_rate": 6.172530368033964e-06, + "loss": 0.0075, + "step": 41205 + }, + { + "epoch": 12.73, + "learning_rate": 6.172068336990962e-06, + "loss": 0.0068, + "step": 41206 + }, + { + "epoch": 12.73, + "learning_rate": 6.17160631552231e-06, + "loss": 0.0067, + "step": 41207 + }, + { + "epoch": 12.73, + "learning_rate": 6.171144303629169e-06, + "loss": 0.0071, + "step": 41208 + }, + { + "epoch": 12.73, + "learning_rate": 6.170682301312697e-06, + "loss": 0.0077, + "step": 41209 + }, + { + "epoch": 12.73, + "learning_rate": 6.170220308574045e-06, + "loss": 0.0071, + "step": 41210 + }, + { + "epoch": 12.73, + "learning_rate": 6.16975832541437e-06, + "loss": 0.0085, + "step": 41211 + }, + { + "epoch": 12.73, + "learning_rate": 6.16929635183483e-06, + "loss": 0.0079, + "step": 41212 + }, + { + "epoch": 12.73, + "learning_rate": 6.168834387836575e-06, + "loss": 0.0073, + "step": 41213 + }, + { + "epoch": 12.73, + "learning_rate": 6.1683724334207665e-06, + "loss": 0.0072, + "step": 41214 + }, + { + "epoch": 12.73, + "learning_rate": 6.16791048858856e-06, + "loss": 0.0075, + "step": 41215 + }, + { + "epoch": 12.73, + "learning_rate": 6.167448553341104e-06, + "loss": 0.0071, + "step": 41216 + }, + { + "epoch": 12.73, + "learning_rate": 6.166986627679559e-06, + "loss": 0.0083, + "step": 41217 + }, + { + "epoch": 12.73, + "learning_rate": 6.166524711605082e-06, + "loss": 0.0077, + "step": 41218 + }, + { + "epoch": 12.73, + "learning_rate": 6.166062805118824e-06, + "loss": 0.0063, + "step": 41219 + }, + { + "epoch": 12.73, + "learning_rate": 6.165600908221941e-06, + "loss": 0.0064, + "step": 41220 + }, + { + "epoch": 12.73, + "learning_rate": 6.16513902091559e-06, + "loss": 0.0065, + "step": 41221 + }, + { + "epoch": 12.73, + "learning_rate": 6.164677143200929e-06, + "loss": 0.0069, + "step": 41222 + }, + { + "epoch": 12.73, + "learning_rate": 6.164215275079105e-06, + "loss": 0.0088, + "step": 41223 + }, + { + "epoch": 12.73, + "learning_rate": 6.163753416551281e-06, + "loss": 0.0073, + "step": 41224 + }, + { + "epoch": 12.73, + "learning_rate": 6.163291567618611e-06, + "loss": 0.0077, + "step": 41225 + }, + { + "epoch": 12.73, + "learning_rate": 6.162829728282245e-06, + "loss": 0.0077, + "step": 41226 + }, + { + "epoch": 12.73, + "learning_rate": 6.1623678985433436e-06, + "loss": 0.0067, + "step": 41227 + }, + { + "epoch": 12.73, + "learning_rate": 6.161906078403062e-06, + "loss": 0.0076, + "step": 41228 + }, + { + "epoch": 12.73, + "learning_rate": 6.161444267862551e-06, + "loss": 0.0067, + "step": 41229 + }, + { + "epoch": 12.73, + "learning_rate": 6.160982466922966e-06, + "loss": 0.0077, + "step": 41230 + }, + { + "epoch": 12.73, + "learning_rate": 6.160520675585469e-06, + "loss": 0.0072, + "step": 41231 + }, + { + "epoch": 12.73, + "learning_rate": 6.160058893851207e-06, + "loss": 0.0064, + "step": 41232 + }, + { + "epoch": 12.73, + "learning_rate": 6.1595971217213344e-06, + "loss": 0.0061, + "step": 41233 + }, + { + "epoch": 12.73, + "learning_rate": 6.159135359197017e-06, + "loss": 0.0069, + "step": 41234 + }, + { + "epoch": 12.73, + "learning_rate": 6.158673606279399e-06, + "loss": 0.0076, + "step": 41235 + }, + { + "epoch": 12.73, + "learning_rate": 6.158211862969637e-06, + "loss": 0.0066, + "step": 41236 + }, + { + "epoch": 12.73, + "learning_rate": 6.157750129268894e-06, + "loss": 0.0068, + "step": 41237 + }, + { + "epoch": 12.74, + "learning_rate": 6.157288405178314e-06, + "loss": 0.0079, + "step": 41238 + }, + { + "epoch": 12.74, + "learning_rate": 6.1568266906990556e-06, + "loss": 0.0076, + "step": 41239 + }, + { + "epoch": 12.74, + "learning_rate": 6.15636498583228e-06, + "loss": 0.0061, + "step": 41240 + }, + { + "epoch": 12.74, + "learning_rate": 6.1559032905791305e-06, + "loss": 0.0063, + "step": 41241 + }, + { + "epoch": 12.74, + "learning_rate": 6.155441604940771e-06, + "loss": 0.0083, + "step": 41242 + }, + { + "epoch": 12.74, + "learning_rate": 6.154979928918354e-06, + "loss": 0.0071, + "step": 41243 + }, + { + "epoch": 12.74, + "learning_rate": 6.15451826251303e-06, + "loss": 0.0066, + "step": 41244 + }, + { + "epoch": 12.74, + "learning_rate": 6.15405660572596e-06, + "loss": 0.0067, + "step": 41245 + }, + { + "epoch": 12.74, + "learning_rate": 6.153594958558298e-06, + "loss": 0.0071, + "step": 41246 + }, + { + "epoch": 12.74, + "learning_rate": 6.153133321011193e-06, + "loss": 0.0061, + "step": 41247 + }, + { + "epoch": 12.74, + "learning_rate": 6.152671693085801e-06, + "loss": 0.0059, + "step": 41248 + }, + { + "epoch": 12.74, + "learning_rate": 6.1522100747832845e-06, + "loss": 0.0084, + "step": 41249 + }, + { + "epoch": 12.74, + "learning_rate": 6.15174846610479e-06, + "loss": 0.0068, + "step": 41250 + }, + { + "epoch": 12.74, + "learning_rate": 6.151286867051471e-06, + "loss": 0.0084, + "step": 41251 + }, + { + "epoch": 12.74, + "learning_rate": 6.1508252776244926e-06, + "loss": 0.0053, + "step": 41252 + }, + { + "epoch": 12.74, + "learning_rate": 6.150363697824997e-06, + "loss": 0.0083, + "step": 41253 + }, + { + "epoch": 12.74, + "learning_rate": 6.149902127654144e-06, + "loss": 0.0075, + "step": 41254 + }, + { + "epoch": 12.74, + "learning_rate": 6.149440567113089e-06, + "loss": 0.007, + "step": 41255 + }, + { + "epoch": 12.74, + "learning_rate": 6.148979016202987e-06, + "loss": 0.0082, + "step": 41256 + }, + { + "epoch": 12.74, + "learning_rate": 6.148517474924991e-06, + "loss": 0.0083, + "step": 41257 + }, + { + "epoch": 12.74, + "learning_rate": 6.1480559432802514e-06, + "loss": 0.0077, + "step": 41258 + }, + { + "epoch": 12.74, + "learning_rate": 6.147594421269931e-06, + "loss": 0.0071, + "step": 41259 + }, + { + "epoch": 12.74, + "learning_rate": 6.147132908895177e-06, + "loss": 0.0069, + "step": 41260 + }, + { + "epoch": 12.74, + "learning_rate": 6.1466714061571456e-06, + "loss": 0.0089, + "step": 41261 + }, + { + "epoch": 12.74, + "learning_rate": 6.146209913056994e-06, + "loss": 0.0074, + "step": 41262 + }, + { + "epoch": 12.74, + "learning_rate": 6.145748429595872e-06, + "loss": 0.0065, + "step": 41263 + }, + { + "epoch": 12.74, + "learning_rate": 6.1452869557749365e-06, + "loss": 0.007, + "step": 41264 + }, + { + "epoch": 12.74, + "learning_rate": 6.144825491595347e-06, + "loss": 0.0094, + "step": 41265 + }, + { + "epoch": 12.74, + "learning_rate": 6.144364037058244e-06, + "loss": 0.007, + "step": 41266 + }, + { + "epoch": 12.74, + "learning_rate": 6.143902592164794e-06, + "loss": 0.0081, + "step": 41267 + }, + { + "epoch": 12.74, + "learning_rate": 6.143441156916148e-06, + "loss": 0.0071, + "step": 41268 + }, + { + "epoch": 12.74, + "learning_rate": 6.1429797313134544e-06, + "loss": 0.0088, + "step": 41269 + }, + { + "epoch": 12.74, + "learning_rate": 6.1425183153578745e-06, + "loss": 0.0067, + "step": 41270 + }, + { + "epoch": 12.75, + "learning_rate": 6.142056909050562e-06, + "loss": 0.0071, + "step": 41271 + }, + { + "epoch": 12.75, + "learning_rate": 6.141595512392666e-06, + "loss": 0.0075, + "step": 41272 + }, + { + "epoch": 12.75, + "learning_rate": 6.141134125385344e-06, + "loss": 0.0088, + "step": 41273 + }, + { + "epoch": 12.75, + "learning_rate": 6.140672748029752e-06, + "loss": 0.007, + "step": 41274 + }, + { + "epoch": 12.75, + "learning_rate": 6.140211380327037e-06, + "loss": 0.0089, + "step": 41275 + }, + { + "epoch": 12.75, + "learning_rate": 6.139750022278359e-06, + "loss": 0.0061, + "step": 41276 + }, + { + "epoch": 12.75, + "learning_rate": 6.139288673884872e-06, + "loss": 0.0067, + "step": 41277 + }, + { + "epoch": 12.75, + "learning_rate": 6.138827335147727e-06, + "loss": 0.0082, + "step": 41278 + }, + { + "epoch": 12.75, + "learning_rate": 6.138366006068077e-06, + "loss": 0.007, + "step": 41279 + }, + { + "epoch": 12.75, + "learning_rate": 6.137904686647082e-06, + "loss": 0.0068, + "step": 41280 + }, + { + "epoch": 12.75, + "learning_rate": 6.1374433768858886e-06, + "loss": 0.0057, + "step": 41281 + }, + { + "epoch": 12.75, + "learning_rate": 6.136982076785653e-06, + "loss": 0.0078, + "step": 41282 + }, + { + "epoch": 12.75, + "learning_rate": 6.136520786347533e-06, + "loss": 0.01, + "step": 41283 + }, + { + "epoch": 12.75, + "learning_rate": 6.136059505572678e-06, + "loss": 0.0082, + "step": 41284 + }, + { + "epoch": 12.75, + "learning_rate": 6.1355982344622415e-06, + "loss": 0.0073, + "step": 41285 + }, + { + "epoch": 12.75, + "learning_rate": 6.1351369730173795e-06, + "loss": 0.0105, + "step": 41286 + }, + { + "epoch": 12.75, + "learning_rate": 6.134675721239246e-06, + "loss": 0.0079, + "step": 41287 + }, + { + "epoch": 12.75, + "learning_rate": 6.134214479128992e-06, + "loss": 0.0087, + "step": 41288 + }, + { + "epoch": 12.75, + "learning_rate": 6.133753246687773e-06, + "loss": 0.0069, + "step": 41289 + }, + { + "epoch": 12.75, + "learning_rate": 6.1332920239167435e-06, + "loss": 0.0105, + "step": 41290 + }, + { + "epoch": 12.75, + "learning_rate": 6.1328308108170545e-06, + "loss": 0.0075, + "step": 41291 + }, + { + "epoch": 12.75, + "learning_rate": 6.13236960738986e-06, + "loss": 0.0083, + "step": 41292 + }, + { + "epoch": 12.75, + "learning_rate": 6.131908413636318e-06, + "loss": 0.0078, + "step": 41293 + }, + { + "epoch": 12.75, + "learning_rate": 6.131447229557577e-06, + "loss": 0.008, + "step": 41294 + }, + { + "epoch": 12.75, + "learning_rate": 6.130986055154789e-06, + "loss": 0.0067, + "step": 41295 + }, + { + "epoch": 12.75, + "learning_rate": 6.130524890429117e-06, + "loss": 0.0056, + "step": 41296 + }, + { + "epoch": 12.75, + "learning_rate": 6.130063735381701e-06, + "loss": 0.0088, + "step": 41297 + }, + { + "epoch": 12.75, + "learning_rate": 6.129602590013706e-06, + "loss": 0.0073, + "step": 41298 + }, + { + "epoch": 12.75, + "learning_rate": 6.12914145432628e-06, + "loss": 0.006, + "step": 41299 + }, + { + "epoch": 12.75, + "learning_rate": 6.128680328320575e-06, + "loss": 0.0073, + "step": 41300 + }, + { + "epoch": 12.75, + "learning_rate": 6.128219211997748e-06, + "loss": 0.0071, + "step": 41301 + }, + { + "epoch": 12.75, + "learning_rate": 6.127758105358953e-06, + "loss": 0.0069, + "step": 41302 + }, + { + "epoch": 12.76, + "learning_rate": 6.127297008405337e-06, + "loss": 0.0062, + "step": 41303 + }, + { + "epoch": 12.76, + "learning_rate": 6.12683592113806e-06, + "loss": 0.0075, + "step": 41304 + }, + { + "epoch": 12.76, + "learning_rate": 6.126374843558273e-06, + "loss": 0.006, + "step": 41305 + }, + { + "epoch": 12.76, + "learning_rate": 6.12591377566713e-06, + "loss": 0.0077, + "step": 41306 + }, + { + "epoch": 12.76, + "learning_rate": 6.1254527174657796e-06, + "loss": 0.0077, + "step": 41307 + }, + { + "epoch": 12.76, + "learning_rate": 6.1249916689553825e-06, + "loss": 0.0091, + "step": 41308 + }, + { + "epoch": 12.76, + "learning_rate": 6.124530630137086e-06, + "loss": 0.0081, + "step": 41309 + }, + { + "epoch": 12.76, + "learning_rate": 6.124069601012044e-06, + "loss": 0.0075, + "step": 41310 + }, + { + "epoch": 12.76, + "learning_rate": 6.123608581581415e-06, + "loss": 0.0075, + "step": 41311 + }, + { + "epoch": 12.76, + "learning_rate": 6.123147571846345e-06, + "loss": 0.0078, + "step": 41312 + }, + { + "epoch": 12.76, + "learning_rate": 6.1226865718079885e-06, + "loss": 0.0072, + "step": 41313 + }, + { + "epoch": 12.76, + "learning_rate": 6.1222255814675045e-06, + "loss": 0.008, + "step": 41314 + }, + { + "epoch": 12.76, + "learning_rate": 6.121764600826039e-06, + "loss": 0.0064, + "step": 41315 + }, + { + "epoch": 12.76, + "learning_rate": 6.121303629884748e-06, + "loss": 0.0058, + "step": 41316 + }, + { + "epoch": 12.76, + "learning_rate": 6.1208426686447845e-06, + "loss": 0.0102, + "step": 41317 + }, + { + "epoch": 12.76, + "learning_rate": 6.120381717107299e-06, + "loss": 0.0065, + "step": 41318 + }, + { + "epoch": 12.76, + "learning_rate": 6.119920775273447e-06, + "loss": 0.0068, + "step": 41319 + }, + { + "epoch": 12.76, + "learning_rate": 6.11945984314438e-06, + "loss": 0.008, + "step": 41320 + }, + { + "epoch": 12.76, + "learning_rate": 6.118998920721255e-06, + "loss": 0.0075, + "step": 41321 + }, + { + "epoch": 12.76, + "learning_rate": 6.118538008005219e-06, + "loss": 0.0092, + "step": 41322 + }, + { + "epoch": 12.76, + "learning_rate": 6.118077104997426e-06, + "loss": 0.0072, + "step": 41323 + }, + { + "epoch": 12.76, + "learning_rate": 6.117616211699034e-06, + "loss": 0.0065, + "step": 41324 + }, + { + "epoch": 12.76, + "learning_rate": 6.11715532811119e-06, + "loss": 0.0069, + "step": 41325 + }, + { + "epoch": 12.76, + "learning_rate": 6.116694454235051e-06, + "loss": 0.007, + "step": 41326 + }, + { + "epoch": 12.76, + "learning_rate": 6.116233590071766e-06, + "loss": 0.0079, + "step": 41327 + }, + { + "epoch": 12.76, + "learning_rate": 6.115772735622486e-06, + "loss": 0.0069, + "step": 41328 + }, + { + "epoch": 12.76, + "learning_rate": 6.115311890888369e-06, + "loss": 0.0067, + "step": 41329 + }, + { + "epoch": 12.76, + "learning_rate": 6.114851055870568e-06, + "loss": 0.0079, + "step": 41330 + }, + { + "epoch": 12.76, + "learning_rate": 6.114390230570228e-06, + "loss": 0.0068, + "step": 41331 + }, + { + "epoch": 12.76, + "learning_rate": 6.1139294149885105e-06, + "loss": 0.0099, + "step": 41332 + }, + { + "epoch": 12.76, + "learning_rate": 6.113468609126566e-06, + "loss": 0.0068, + "step": 41333 + }, + { + "epoch": 12.76, + "learning_rate": 6.113007812985541e-06, + "loss": 0.0061, + "step": 41334 + }, + { + "epoch": 12.77, + "learning_rate": 6.1125470265665935e-06, + "loss": 0.0084, + "step": 41335 + }, + { + "epoch": 12.77, + "learning_rate": 6.112086249870878e-06, + "loss": 0.0065, + "step": 41336 + }, + { + "epoch": 12.77, + "learning_rate": 6.111625482899541e-06, + "loss": 0.0074, + "step": 41337 + }, + { + "epoch": 12.77, + "learning_rate": 6.111164725653737e-06, + "loss": 0.0072, + "step": 41338 + }, + { + "epoch": 12.77, + "learning_rate": 6.110703978134622e-06, + "loss": 0.0076, + "step": 41339 + }, + { + "epoch": 12.77, + "learning_rate": 6.110243240343345e-06, + "loss": 0.0071, + "step": 41340 + }, + { + "epoch": 12.77, + "learning_rate": 6.109782512281056e-06, + "loss": 0.0058, + "step": 41341 + }, + { + "epoch": 12.77, + "learning_rate": 6.109321793948915e-06, + "loss": 0.0073, + "step": 41342 + }, + { + "epoch": 12.77, + "learning_rate": 6.108861085348068e-06, + "loss": 0.0075, + "step": 41343 + }, + { + "epoch": 12.77, + "learning_rate": 6.108400386479667e-06, + "loss": 0.0073, + "step": 41344 + }, + { + "epoch": 12.77, + "learning_rate": 6.107939697344873e-06, + "loss": 0.0093, + "step": 41345 + }, + { + "epoch": 12.77, + "learning_rate": 6.107479017944824e-06, + "loss": 0.0081, + "step": 41346 + }, + { + "epoch": 12.77, + "learning_rate": 6.107018348280683e-06, + "loss": 0.0064, + "step": 41347 + }, + { + "epoch": 12.77, + "learning_rate": 6.1065576883536015e-06, + "loss": 0.0069, + "step": 41348 + }, + { + "epoch": 12.77, + "learning_rate": 6.1060970381647245e-06, + "loss": 0.0068, + "step": 41349 + }, + { + "epoch": 12.77, + "learning_rate": 6.105636397715211e-06, + "loss": 0.0071, + "step": 41350 + }, + { + "epoch": 12.77, + "learning_rate": 6.105175767006211e-06, + "loss": 0.0086, + "step": 41351 + }, + { + "epoch": 12.77, + "learning_rate": 6.104715146038879e-06, + "loss": 0.0078, + "step": 41352 + }, + { + "epoch": 12.77, + "learning_rate": 6.104254534814363e-06, + "loss": 0.0075, + "step": 41353 + }, + { + "epoch": 12.77, + "learning_rate": 6.103793933333815e-06, + "loss": 0.0082, + "step": 41354 + }, + { + "epoch": 12.77, + "learning_rate": 6.103333341598395e-06, + "loss": 0.0084, + "step": 41355 + }, + { + "epoch": 12.77, + "learning_rate": 6.102872759609244e-06, + "loss": 0.0072, + "step": 41356 + }, + { + "epoch": 12.77, + "learning_rate": 6.102412187367519e-06, + "loss": 0.0078, + "step": 41357 + }, + { + "epoch": 12.77, + "learning_rate": 6.101951624874376e-06, + "loss": 0.0077, + "step": 41358 + }, + { + "epoch": 12.77, + "learning_rate": 6.101491072130959e-06, + "loss": 0.0091, + "step": 41359 + }, + { + "epoch": 12.77, + "learning_rate": 6.1010305291384245e-06, + "loss": 0.0066, + "step": 41360 + }, + { + "epoch": 12.77, + "learning_rate": 6.100569995897926e-06, + "loss": 0.0065, + "step": 41361 + }, + { + "epoch": 12.77, + "learning_rate": 6.100109472410609e-06, + "loss": 0.0079, + "step": 41362 + }, + { + "epoch": 12.77, + "learning_rate": 6.099648958677632e-06, + "loss": 0.0064, + "step": 41363 + }, + { + "epoch": 12.77, + "learning_rate": 6.099188454700147e-06, + "loss": 0.0067, + "step": 41364 + }, + { + "epoch": 12.77, + "learning_rate": 6.098727960479301e-06, + "loss": 0.0092, + "step": 41365 + }, + { + "epoch": 12.77, + "learning_rate": 6.098267476016244e-06, + "loss": 0.0075, + "step": 41366 + }, + { + "epoch": 12.77, + "learning_rate": 6.097807001312137e-06, + "loss": 0.0071, + "step": 41367 + }, + { + "epoch": 12.78, + "learning_rate": 6.097346536368125e-06, + "loss": 0.0076, + "step": 41368 + }, + { + "epoch": 12.78, + "learning_rate": 6.096886081185358e-06, + "loss": 0.0073, + "step": 41369 + }, + { + "epoch": 12.78, + "learning_rate": 6.096425635764995e-06, + "loss": 0.0078, + "step": 41370 + }, + { + "epoch": 12.78, + "learning_rate": 6.095965200108183e-06, + "loss": 0.0074, + "step": 41371 + }, + { + "epoch": 12.78, + "learning_rate": 6.09550477421607e-06, + "loss": 0.0072, + "step": 41372 + }, + { + "epoch": 12.78, + "learning_rate": 6.095044358089816e-06, + "loss": 0.0076, + "step": 41373 + }, + { + "epoch": 12.78, + "learning_rate": 6.0945839517305684e-06, + "loss": 0.0071, + "step": 41374 + }, + { + "epoch": 12.78, + "learning_rate": 6.0941235551394765e-06, + "loss": 0.0085, + "step": 41375 + }, + { + "epoch": 12.78, + "learning_rate": 6.093663168317696e-06, + "loss": 0.007, + "step": 41376 + }, + { + "epoch": 12.78, + "learning_rate": 6.093202791266372e-06, + "loss": 0.0075, + "step": 41377 + }, + { + "epoch": 12.78, + "learning_rate": 6.092742423986664e-06, + "loss": 0.0058, + "step": 41378 + }, + { + "epoch": 12.78, + "learning_rate": 6.092282066479722e-06, + "loss": 0.0072, + "step": 41379 + }, + { + "epoch": 12.78, + "learning_rate": 6.091821718746691e-06, + "loss": 0.0059, + "step": 41380 + }, + { + "epoch": 12.78, + "learning_rate": 6.091361380788727e-06, + "loss": 0.007, + "step": 41381 + }, + { + "epoch": 12.78, + "learning_rate": 6.090901052606984e-06, + "loss": 0.0097, + "step": 41382 + }, + { + "epoch": 12.78, + "learning_rate": 6.090440734202608e-06, + "loss": 0.0069, + "step": 41383 + }, + { + "epoch": 12.78, + "learning_rate": 6.089980425576752e-06, + "loss": 0.0075, + "step": 41384 + }, + { + "epoch": 12.78, + "learning_rate": 6.08952012673057e-06, + "loss": 0.0059, + "step": 41385 + }, + { + "epoch": 12.78, + "learning_rate": 6.089059837665213e-06, + "loss": 0.0092, + "step": 41386 + }, + { + "epoch": 12.78, + "learning_rate": 6.088599558381827e-06, + "loss": 0.0086, + "step": 41387 + }, + { + "epoch": 12.78, + "learning_rate": 6.088139288881569e-06, + "loss": 0.0071, + "step": 41388 + }, + { + "epoch": 12.78, + "learning_rate": 6.087679029165589e-06, + "loss": 0.0075, + "step": 41389 + }, + { + "epoch": 12.78, + "learning_rate": 6.087218779235033e-06, + "loss": 0.0062, + "step": 41390 + }, + { + "epoch": 12.78, + "learning_rate": 6.08675853909106e-06, + "loss": 0.0085, + "step": 41391 + }, + { + "epoch": 12.78, + "learning_rate": 6.08629830873482e-06, + "loss": 0.0088, + "step": 41392 + }, + { + "epoch": 12.78, + "learning_rate": 6.085838088167456e-06, + "loss": 0.0075, + "step": 41393 + }, + { + "epoch": 12.78, + "learning_rate": 6.085377877390128e-06, + "loss": 0.0065, + "step": 41394 + }, + { + "epoch": 12.78, + "learning_rate": 6.084917676403985e-06, + "loss": 0.0075, + "step": 41395 + }, + { + "epoch": 12.78, + "learning_rate": 6.084457485210176e-06, + "loss": 0.006, + "step": 41396 + }, + { + "epoch": 12.78, + "learning_rate": 6.08399730380985e-06, + "loss": 0.0072, + "step": 41397 + }, + { + "epoch": 12.78, + "learning_rate": 6.0835371322041645e-06, + "loss": 0.0062, + "step": 41398 + }, + { + "epoch": 12.78, + "learning_rate": 6.083076970394266e-06, + "loss": 0.0064, + "step": 41399 + }, + { + "epoch": 12.79, + "learning_rate": 6.082616818381305e-06, + "loss": 0.0083, + "step": 41400 + }, + { + "epoch": 12.79, + "learning_rate": 6.082156676166438e-06, + "loss": 0.0086, + "step": 41401 + }, + { + "epoch": 12.79, + "learning_rate": 6.081696543750808e-06, + "loss": 0.0078, + "step": 41402 + }, + { + "epoch": 12.79, + "learning_rate": 6.081236421135568e-06, + "loss": 0.007, + "step": 41403 + }, + { + "epoch": 12.79, + "learning_rate": 6.080776308321877e-06, + "loss": 0.0073, + "step": 41404 + }, + { + "epoch": 12.79, + "learning_rate": 6.080316205310873e-06, + "loss": 0.0076, + "step": 41405 + }, + { + "epoch": 12.79, + "learning_rate": 6.079856112103715e-06, + "loss": 0.0064, + "step": 41406 + }, + { + "epoch": 12.79, + "learning_rate": 6.079396028701554e-06, + "loss": 0.0075, + "step": 41407 + }, + { + "epoch": 12.79, + "learning_rate": 6.078935955105536e-06, + "loss": 0.006, + "step": 41408 + }, + { + "epoch": 12.79, + "learning_rate": 6.078475891316814e-06, + "loss": 0.0072, + "step": 41409 + }, + { + "epoch": 12.79, + "learning_rate": 6.078015837336541e-06, + "loss": 0.007, + "step": 41410 + }, + { + "epoch": 12.79, + "learning_rate": 6.0775557931658635e-06, + "loss": 0.0075, + "step": 41411 + }, + { + "epoch": 12.79, + "learning_rate": 6.077095758805936e-06, + "loss": 0.0063, + "step": 41412 + }, + { + "epoch": 12.79, + "learning_rate": 6.0766357342579095e-06, + "loss": 0.0073, + "step": 41413 + }, + { + "epoch": 12.79, + "learning_rate": 6.07617571952293e-06, + "loss": 0.0071, + "step": 41414 + }, + { + "epoch": 12.79, + "learning_rate": 6.075715714602148e-06, + "loss": 0.0078, + "step": 41415 + }, + { + "epoch": 12.79, + "learning_rate": 6.075255719496722e-06, + "loss": 0.0056, + "step": 41416 + }, + { + "epoch": 12.79, + "learning_rate": 6.074795734207796e-06, + "loss": 0.0085, + "step": 41417 + }, + { + "epoch": 12.79, + "learning_rate": 6.074335758736518e-06, + "loss": 0.008, + "step": 41418 + }, + { + "epoch": 12.79, + "learning_rate": 6.073875793084045e-06, + "loss": 0.0065, + "step": 41419 + }, + { + "epoch": 12.79, + "learning_rate": 6.073415837251527e-06, + "loss": 0.0075, + "step": 41420 + }, + { + "epoch": 12.79, + "learning_rate": 6.072955891240108e-06, + "loss": 0.0072, + "step": 41421 + }, + { + "epoch": 12.79, + "learning_rate": 6.0724959550509445e-06, + "loss": 0.0079, + "step": 41422 + }, + { + "epoch": 12.79, + "learning_rate": 6.0720360286851864e-06, + "loss": 0.0087, + "step": 41423 + }, + { + "epoch": 12.79, + "learning_rate": 6.071576112143982e-06, + "loss": 0.0079, + "step": 41424 + }, + { + "epoch": 12.79, + "learning_rate": 6.071116205428479e-06, + "loss": 0.0076, + "step": 41425 + }, + { + "epoch": 12.79, + "learning_rate": 6.070656308539835e-06, + "loss": 0.0077, + "step": 41426 + }, + { + "epoch": 12.79, + "learning_rate": 6.070196421479196e-06, + "loss": 0.0074, + "step": 41427 + }, + { + "epoch": 12.79, + "learning_rate": 6.069736544247707e-06, + "loss": 0.0087, + "step": 41428 + }, + { + "epoch": 12.79, + "learning_rate": 6.069276676846531e-06, + "loss": 0.0076, + "step": 41429 + }, + { + "epoch": 12.79, + "learning_rate": 6.068816819276807e-06, + "loss": 0.0065, + "step": 41430 + }, + { + "epoch": 12.79, + "learning_rate": 6.068356971539688e-06, + "loss": 0.0075, + "step": 41431 + }, + { + "epoch": 12.79, + "learning_rate": 6.067897133636329e-06, + "loss": 0.007, + "step": 41432 + }, + { + "epoch": 12.8, + "learning_rate": 6.0674373055678744e-06, + "loss": 0.0069, + "step": 41433 + }, + { + "epoch": 12.8, + "learning_rate": 6.0669774873354766e-06, + "loss": 0.0067, + "step": 41434 + }, + { + "epoch": 12.8, + "learning_rate": 6.066517678940287e-06, + "loss": 0.0065, + "step": 41435 + }, + { + "epoch": 12.8, + "learning_rate": 6.066057880383452e-06, + "loss": 0.006, + "step": 41436 + }, + { + "epoch": 12.8, + "learning_rate": 6.065598091666123e-06, + "loss": 0.0069, + "step": 41437 + }, + { + "epoch": 12.8, + "learning_rate": 6.065138312789454e-06, + "loss": 0.0075, + "step": 41438 + }, + { + "epoch": 12.8, + "learning_rate": 6.064678543754587e-06, + "loss": 0.007, + "step": 41439 + }, + { + "epoch": 12.8, + "learning_rate": 6.064218784562681e-06, + "loss": 0.0064, + "step": 41440 + }, + { + "epoch": 12.8, + "learning_rate": 6.063759035214882e-06, + "loss": 0.0072, + "step": 41441 + }, + { + "epoch": 12.8, + "learning_rate": 6.063299295712335e-06, + "loss": 0.0074, + "step": 41442 + }, + { + "epoch": 12.8, + "learning_rate": 6.062839566056198e-06, + "loss": 0.0075, + "step": 41443 + }, + { + "epoch": 12.8, + "learning_rate": 6.062379846247618e-06, + "loss": 0.0086, + "step": 41444 + }, + { + "epoch": 12.8, + "learning_rate": 6.061920136287742e-06, + "loss": 0.0073, + "step": 41445 + }, + { + "epoch": 12.8, + "learning_rate": 6.0614604361777214e-06, + "loss": 0.0082, + "step": 41446 + }, + { + "epoch": 12.8, + "learning_rate": 6.06100074591871e-06, + "loss": 0.0081, + "step": 41447 + }, + { + "epoch": 12.8, + "learning_rate": 6.060541065511851e-06, + "loss": 0.0078, + "step": 41448 + }, + { + "epoch": 12.8, + "learning_rate": 6.060081394958297e-06, + "loss": 0.0072, + "step": 41449 + }, + { + "epoch": 12.8, + "learning_rate": 6.0596217342592e-06, + "loss": 0.0089, + "step": 41450 + }, + { + "epoch": 12.8, + "learning_rate": 6.059162083415709e-06, + "loss": 0.0073, + "step": 41451 + }, + { + "epoch": 12.8, + "learning_rate": 6.058702442428968e-06, + "loss": 0.0075, + "step": 41452 + }, + { + "epoch": 12.8, + "learning_rate": 6.0582428113001345e-06, + "loss": 0.0057, + "step": 41453 + }, + { + "epoch": 12.8, + "learning_rate": 6.057783190030355e-06, + "loss": 0.0067, + "step": 41454 + }, + { + "epoch": 12.8, + "learning_rate": 6.057323578620777e-06, + "loss": 0.0085, + "step": 41455 + }, + { + "epoch": 12.8, + "learning_rate": 6.056863977072551e-06, + "loss": 0.0064, + "step": 41456 + }, + { + "epoch": 12.8, + "learning_rate": 6.056404385386832e-06, + "loss": 0.008, + "step": 41457 + }, + { + "epoch": 12.8, + "learning_rate": 6.055944803564761e-06, + "loss": 0.0069, + "step": 41458 + }, + { + "epoch": 12.8, + "learning_rate": 6.05548523160749e-06, + "loss": 0.0071, + "step": 41459 + }, + { + "epoch": 12.8, + "learning_rate": 6.055025669516172e-06, + "loss": 0.0079, + "step": 41460 + }, + { + "epoch": 12.8, + "learning_rate": 6.0545661172919556e-06, + "loss": 0.0067, + "step": 41461 + }, + { + "epoch": 12.8, + "learning_rate": 6.0541065749359855e-06, + "loss": 0.0093, + "step": 41462 + }, + { + "epoch": 12.8, + "learning_rate": 6.05364704244942e-06, + "loss": 0.0078, + "step": 41463 + }, + { + "epoch": 12.8, + "learning_rate": 6.0531875198333975e-06, + "loss": 0.0075, + "step": 41464 + }, + { + "epoch": 12.81, + "learning_rate": 6.052728007089075e-06, + "loss": 0.0076, + "step": 41465 + }, + { + "epoch": 12.81, + "learning_rate": 6.0522685042176025e-06, + "loss": 0.008, + "step": 41466 + }, + { + "epoch": 12.81, + "learning_rate": 6.051809011220121e-06, + "loss": 0.0071, + "step": 41467 + }, + { + "epoch": 12.81, + "learning_rate": 6.0513495280977875e-06, + "loss": 0.0074, + "step": 41468 + }, + { + "epoch": 12.81, + "learning_rate": 6.050890054851752e-06, + "loss": 0.0077, + "step": 41469 + }, + { + "epoch": 12.81, + "learning_rate": 6.050430591483156e-06, + "loss": 0.0079, + "step": 41470 + }, + { + "epoch": 12.81, + "learning_rate": 6.049971137993156e-06, + "loss": 0.0067, + "step": 41471 + }, + { + "epoch": 12.81, + "learning_rate": 6.049511694382899e-06, + "loss": 0.0072, + "step": 41472 + }, + { + "epoch": 12.81, + "learning_rate": 6.049052260653534e-06, + "loss": 0.008, + "step": 41473 + }, + { + "epoch": 12.81, + "learning_rate": 6.048592836806207e-06, + "loss": 0.0063, + "step": 41474 + }, + { + "epoch": 12.81, + "learning_rate": 6.048133422842073e-06, + "loss": 0.0105, + "step": 41475 + }, + { + "epoch": 12.81, + "learning_rate": 6.047674018762277e-06, + "loss": 0.0086, + "step": 41476 + }, + { + "epoch": 12.81, + "learning_rate": 6.047214624567968e-06, + "loss": 0.0072, + "step": 41477 + }, + { + "epoch": 12.81, + "learning_rate": 6.046755240260299e-06, + "loss": 0.0072, + "step": 41478 + }, + { + "epoch": 12.81, + "learning_rate": 6.046295865840415e-06, + "loss": 0.0098, + "step": 41479 + }, + { + "epoch": 12.81, + "learning_rate": 6.0458365013094634e-06, + "loss": 0.0089, + "step": 41480 + }, + { + "epoch": 12.81, + "learning_rate": 6.045377146668601e-06, + "loss": 0.0068, + "step": 41481 + }, + { + "epoch": 12.81, + "learning_rate": 6.044917801918968e-06, + "loss": 0.0073, + "step": 41482 + }, + { + "epoch": 12.81, + "learning_rate": 6.044458467061718e-06, + "loss": 0.0085, + "step": 41483 + }, + { + "epoch": 12.81, + "learning_rate": 6.043999142097996e-06, + "loss": 0.0058, + "step": 41484 + }, + { + "epoch": 12.81, + "learning_rate": 6.043539827028958e-06, + "loss": 0.0071, + "step": 41485 + }, + { + "epoch": 12.81, + "learning_rate": 6.043080521855746e-06, + "loss": 0.0079, + "step": 41486 + }, + { + "epoch": 12.81, + "learning_rate": 6.04262122657951e-06, + "loss": 0.0079, + "step": 41487 + }, + { + "epoch": 12.81, + "learning_rate": 6.042161941201405e-06, + "loss": 0.0078, + "step": 41488 + }, + { + "epoch": 12.81, + "learning_rate": 6.0417026657225715e-06, + "loss": 0.0077, + "step": 41489 + }, + { + "epoch": 12.81, + "learning_rate": 6.04124340014416e-06, + "loss": 0.007, + "step": 41490 + }, + { + "epoch": 12.81, + "learning_rate": 6.040784144467324e-06, + "loss": 0.0071, + "step": 41491 + }, + { + "epoch": 12.81, + "learning_rate": 6.040324898693208e-06, + "loss": 0.0084, + "step": 41492 + }, + { + "epoch": 12.81, + "learning_rate": 6.03986566282296e-06, + "loss": 0.0066, + "step": 41493 + }, + { + "epoch": 12.81, + "learning_rate": 6.039406436857735e-06, + "loss": 0.0072, + "step": 41494 + }, + { + "epoch": 12.81, + "learning_rate": 6.038947220798672e-06, + "loss": 0.0071, + "step": 41495 + }, + { + "epoch": 12.81, + "learning_rate": 6.038488014646926e-06, + "loss": 0.0069, + "step": 41496 + }, + { + "epoch": 12.82, + "learning_rate": 6.038028818403647e-06, + "loss": 0.0071, + "step": 41497 + }, + { + "epoch": 12.82, + "learning_rate": 6.037569632069975e-06, + "loss": 0.0071, + "step": 41498 + }, + { + "epoch": 12.82, + "learning_rate": 6.037110455647066e-06, + "loss": 0.0071, + "step": 41499 + }, + { + "epoch": 12.82, + "learning_rate": 6.036651289136071e-06, + "loss": 0.0068, + "step": 41500 + }, + { + "epoch": 12.82, + "learning_rate": 6.036192132538128e-06, + "loss": 0.0068, + "step": 41501 + }, + { + "epoch": 12.82, + "learning_rate": 6.035732985854392e-06, + "loss": 0.0071, + "step": 41502 + }, + { + "epoch": 12.82, + "learning_rate": 6.035273849086015e-06, + "loss": 0.0068, + "step": 41503 + }, + { + "epoch": 12.82, + "learning_rate": 6.0348147222341394e-06, + "loss": 0.0082, + "step": 41504 + }, + { + "epoch": 12.82, + "learning_rate": 6.034355605299912e-06, + "loss": 0.0075, + "step": 41505 + }, + { + "epoch": 12.82, + "learning_rate": 6.0338964982844885e-06, + "loss": 0.0077, + "step": 41506 + }, + { + "epoch": 12.82, + "learning_rate": 6.033437401189013e-06, + "loss": 0.0081, + "step": 41507 + }, + { + "epoch": 12.82, + "learning_rate": 6.03297831401463e-06, + "loss": 0.0072, + "step": 41508 + }, + { + "epoch": 12.82, + "learning_rate": 6.0325192367624975e-06, + "loss": 0.0089, + "step": 41509 + }, + { + "epoch": 12.82, + "learning_rate": 6.0320601694337555e-06, + "loss": 0.0093, + "step": 41510 + }, + { + "epoch": 12.82, + "learning_rate": 6.031601112029551e-06, + "loss": 0.0077, + "step": 41511 + }, + { + "epoch": 12.82, + "learning_rate": 6.031142064551043e-06, + "loss": 0.0078, + "step": 41512 + }, + { + "epoch": 12.82, + "learning_rate": 6.030683026999367e-06, + "loss": 0.0082, + "step": 41513 + }, + { + "epoch": 12.82, + "learning_rate": 6.030223999375679e-06, + "loss": 0.0061, + "step": 41514 + }, + { + "epoch": 12.82, + "learning_rate": 6.029764981681123e-06, + "loss": 0.0075, + "step": 41515 + }, + { + "epoch": 12.82, + "learning_rate": 6.029305973916853e-06, + "loss": 0.0065, + "step": 41516 + }, + { + "epoch": 12.82, + "learning_rate": 6.0288469760840095e-06, + "loss": 0.008, + "step": 41517 + }, + { + "epoch": 12.82, + "learning_rate": 6.028387988183742e-06, + "loss": 0.0092, + "step": 41518 + }, + { + "epoch": 12.82, + "learning_rate": 6.027929010217206e-06, + "loss": 0.008, + "step": 41519 + }, + { + "epoch": 12.82, + "learning_rate": 6.0274700421855416e-06, + "loss": 0.0076, + "step": 41520 + }, + { + "epoch": 12.82, + "learning_rate": 6.0270110840898965e-06, + "loss": 0.0079, + "step": 41521 + }, + { + "epoch": 12.82, + "learning_rate": 6.026552135931427e-06, + "loss": 0.0067, + "step": 41522 + }, + { + "epoch": 12.82, + "learning_rate": 6.026093197711271e-06, + "loss": 0.0074, + "step": 41523 + }, + { + "epoch": 12.82, + "learning_rate": 6.025634269430582e-06, + "loss": 0.0087, + "step": 41524 + }, + { + "epoch": 12.82, + "learning_rate": 6.0251753510905076e-06, + "loss": 0.0066, + "step": 41525 + }, + { + "epoch": 12.82, + "learning_rate": 6.024716442692191e-06, + "loss": 0.0077, + "step": 41526 + }, + { + "epoch": 12.82, + "learning_rate": 6.024257544236787e-06, + "loss": 0.0086, + "step": 41527 + }, + { + "epoch": 12.82, + "learning_rate": 6.02379865572544e-06, + "loss": 0.0071, + "step": 41528 + }, + { + "epoch": 12.82, + "learning_rate": 6.023339777159295e-06, + "loss": 0.0073, + "step": 41529 + }, + { + "epoch": 12.83, + "learning_rate": 6.022880908539503e-06, + "loss": 0.0083, + "step": 41530 + }, + { + "epoch": 12.83, + "learning_rate": 6.022422049867216e-06, + "loss": 0.0075, + "step": 41531 + }, + { + "epoch": 12.83, + "learning_rate": 6.02196320114357e-06, + "loss": 0.0064, + "step": 41532 + }, + { + "epoch": 12.83, + "learning_rate": 6.021504362369723e-06, + "loss": 0.0079, + "step": 41533 + }, + { + "epoch": 12.83, + "learning_rate": 6.021045533546822e-06, + "loss": 0.0063, + "step": 41534 + }, + { + "epoch": 12.83, + "learning_rate": 6.020586714676009e-06, + "loss": 0.007, + "step": 41535 + }, + { + "epoch": 12.83, + "learning_rate": 6.0201279057584325e-06, + "loss": 0.0065, + "step": 41536 + }, + { + "epoch": 12.83, + "learning_rate": 6.019669106795246e-06, + "loss": 0.0067, + "step": 41537 + }, + { + "epoch": 12.83, + "learning_rate": 6.0192103177875915e-06, + "loss": 0.0066, + "step": 41538 + }, + { + "epoch": 12.83, + "learning_rate": 6.0187515387366155e-06, + "loss": 0.0061, + "step": 41539 + }, + { + "epoch": 12.83, + "learning_rate": 6.018292769643472e-06, + "loss": 0.0073, + "step": 41540 + }, + { + "epoch": 12.83, + "learning_rate": 6.017834010509303e-06, + "loss": 0.0079, + "step": 41541 + }, + { + "epoch": 12.83, + "learning_rate": 6.017375261335254e-06, + "loss": 0.0074, + "step": 41542 + }, + { + "epoch": 12.83, + "learning_rate": 6.016916522122482e-06, + "loss": 0.0064, + "step": 41543 + }, + { + "epoch": 12.83, + "learning_rate": 6.016457792872124e-06, + "loss": 0.0067, + "step": 41544 + }, + { + "epoch": 12.83, + "learning_rate": 6.015999073585333e-06, + "loss": 0.0068, + "step": 41545 + }, + { + "epoch": 12.83, + "learning_rate": 6.015540364263257e-06, + "loss": 0.0062, + "step": 41546 + }, + { + "epoch": 12.83, + "learning_rate": 6.0150816649070365e-06, + "loss": 0.0076, + "step": 41547 + }, + { + "epoch": 12.83, + "learning_rate": 6.014622975517825e-06, + "loss": 0.0084, + "step": 41548 + }, + { + "epoch": 12.83, + "learning_rate": 6.014164296096768e-06, + "loss": 0.0077, + "step": 41549 + }, + { + "epoch": 12.83, + "learning_rate": 6.013705626645017e-06, + "loss": 0.0072, + "step": 41550 + }, + { + "epoch": 12.83, + "learning_rate": 6.013246967163713e-06, + "loss": 0.0075, + "step": 41551 + }, + { + "epoch": 12.83, + "learning_rate": 6.012788317654001e-06, + "loss": 0.0061, + "step": 41552 + }, + { + "epoch": 12.83, + "learning_rate": 6.012329678117042e-06, + "loss": 0.0067, + "step": 41553 + }, + { + "epoch": 12.83, + "learning_rate": 6.011871048553966e-06, + "loss": 0.0064, + "step": 41554 + }, + { + "epoch": 12.83, + "learning_rate": 6.0114124289659305e-06, + "loss": 0.0066, + "step": 41555 + }, + { + "epoch": 12.83, + "learning_rate": 6.010953819354082e-06, + "loss": 0.0074, + "step": 41556 + }, + { + "epoch": 12.83, + "learning_rate": 6.010495219719562e-06, + "loss": 0.0073, + "step": 41557 + }, + { + "epoch": 12.83, + "learning_rate": 6.0100366300635225e-06, + "loss": 0.0064, + "step": 41558 + }, + { + "epoch": 12.83, + "learning_rate": 6.009578050387112e-06, + "loss": 0.0082, + "step": 41559 + }, + { + "epoch": 12.83, + "learning_rate": 6.009119480691469e-06, + "loss": 0.0066, + "step": 41560 + }, + { + "epoch": 12.83, + "learning_rate": 6.008660920977749e-06, + "loss": 0.0074, + "step": 41561 + }, + { + "epoch": 12.84, + "learning_rate": 6.008202371247098e-06, + "loss": 0.009, + "step": 41562 + }, + { + "epoch": 12.84, + "learning_rate": 6.007743831500659e-06, + "loss": 0.0061, + "step": 41563 + }, + { + "epoch": 12.84, + "learning_rate": 6.007285301739578e-06, + "loss": 0.0069, + "step": 41564 + }, + { + "epoch": 12.84, + "learning_rate": 6.00682678196501e-06, + "loss": 0.0096, + "step": 41565 + }, + { + "epoch": 12.84, + "learning_rate": 6.006368272178094e-06, + "loss": 0.0063, + "step": 41566 + }, + { + "epoch": 12.84, + "learning_rate": 6.005909772379976e-06, + "loss": 0.0066, + "step": 41567 + }, + { + "epoch": 12.84, + "learning_rate": 6.005451282571813e-06, + "loss": 0.0089, + "step": 41568 + }, + { + "epoch": 12.84, + "learning_rate": 6.00499280275474e-06, + "loss": 0.0113, + "step": 41569 + }, + { + "epoch": 12.84, + "learning_rate": 6.004534332929908e-06, + "loss": 0.0073, + "step": 41570 + }, + { + "epoch": 12.84, + "learning_rate": 6.004075873098468e-06, + "loss": 0.0057, + "step": 41571 + }, + { + "epoch": 12.84, + "learning_rate": 6.003617423261562e-06, + "loss": 0.0068, + "step": 41572 + }, + { + "epoch": 12.84, + "learning_rate": 6.003158983420336e-06, + "loss": 0.0081, + "step": 41573 + }, + { + "epoch": 12.84, + "learning_rate": 6.002700553575942e-06, + "loss": 0.0063, + "step": 41574 + }, + { + "epoch": 12.84, + "learning_rate": 6.002242133729519e-06, + "loss": 0.0065, + "step": 41575 + }, + { + "epoch": 12.84, + "learning_rate": 6.001783723882217e-06, + "loss": 0.0075, + "step": 41576 + }, + { + "epoch": 12.84, + "learning_rate": 6.001325324035188e-06, + "loss": 0.0078, + "step": 41577 + }, + { + "epoch": 12.84, + "learning_rate": 6.000866934189569e-06, + "loss": 0.0072, + "step": 41578 + }, + { + "epoch": 12.84, + "learning_rate": 6.000408554346513e-06, + "loss": 0.007, + "step": 41579 + }, + { + "epoch": 12.84, + "learning_rate": 5.999950184507162e-06, + "loss": 0.008, + "step": 41580 + }, + { + "epoch": 12.84, + "learning_rate": 5.999491824672669e-06, + "loss": 0.0078, + "step": 41581 + }, + { + "epoch": 12.84, + "learning_rate": 5.999033474844176e-06, + "loss": 0.0082, + "step": 41582 + }, + { + "epoch": 12.84, + "learning_rate": 5.998575135022831e-06, + "loss": 0.0069, + "step": 41583 + }, + { + "epoch": 12.84, + "learning_rate": 5.99811680520978e-06, + "loss": 0.0104, + "step": 41584 + }, + { + "epoch": 12.84, + "learning_rate": 5.9976584854061636e-06, + "loss": 0.009, + "step": 41585 + }, + { + "epoch": 12.84, + "learning_rate": 5.997200175613136e-06, + "loss": 0.0067, + "step": 41586 + }, + { + "epoch": 12.84, + "learning_rate": 5.996741875831843e-06, + "loss": 0.0078, + "step": 41587 + }, + { + "epoch": 12.84, + "learning_rate": 5.996283586063425e-06, + "loss": 0.0083, + "step": 41588 + }, + { + "epoch": 12.84, + "learning_rate": 5.9958253063090336e-06, + "loss": 0.0087, + "step": 41589 + }, + { + "epoch": 12.84, + "learning_rate": 5.995367036569816e-06, + "loss": 0.0069, + "step": 41590 + }, + { + "epoch": 12.84, + "learning_rate": 5.994908776846911e-06, + "loss": 0.0083, + "step": 41591 + }, + { + "epoch": 12.84, + "learning_rate": 5.994450527141472e-06, + "loss": 0.0078, + "step": 41592 + }, + { + "epoch": 12.84, + "learning_rate": 5.993992287454644e-06, + "loss": 0.0061, + "step": 41593 + }, + { + "epoch": 12.85, + "learning_rate": 5.993534057787571e-06, + "loss": 0.0077, + "step": 41594 + }, + { + "epoch": 12.85, + "learning_rate": 5.993075838141398e-06, + "loss": 0.009, + "step": 41595 + }, + { + "epoch": 12.85, + "learning_rate": 5.992617628517278e-06, + "loss": 0.007, + "step": 41596 + }, + { + "epoch": 12.85, + "learning_rate": 5.992159428916349e-06, + "loss": 0.0063, + "step": 41597 + }, + { + "epoch": 12.85, + "learning_rate": 5.991701239339758e-06, + "loss": 0.0075, + "step": 41598 + }, + { + "epoch": 12.85, + "learning_rate": 5.991243059788659e-06, + "loss": 0.007, + "step": 41599 + }, + { + "epoch": 12.85, + "learning_rate": 5.990784890264187e-06, + "loss": 0.0075, + "step": 41600 + }, + { + "epoch": 12.85, + "learning_rate": 5.990326730767494e-06, + "loss": 0.0075, + "step": 41601 + }, + { + "epoch": 12.85, + "learning_rate": 5.9898685812997305e-06, + "loss": 0.0072, + "step": 41602 + }, + { + "epoch": 12.85, + "learning_rate": 5.989410441862031e-06, + "loss": 0.0068, + "step": 41603 + }, + { + "epoch": 12.85, + "learning_rate": 5.988952312455549e-06, + "loss": 0.008, + "step": 41604 + }, + { + "epoch": 12.85, + "learning_rate": 5.988494193081431e-06, + "loss": 0.0069, + "step": 41605 + }, + { + "epoch": 12.85, + "learning_rate": 5.988036083740818e-06, + "loss": 0.0071, + "step": 41606 + }, + { + "epoch": 12.85, + "learning_rate": 5.987577984434859e-06, + "loss": 0.0077, + "step": 41607 + }, + { + "epoch": 12.85, + "learning_rate": 5.987119895164701e-06, + "loss": 0.0063, + "step": 41608 + }, + { + "epoch": 12.85, + "learning_rate": 5.9866618159314845e-06, + "loss": 0.0102, + "step": 41609 + }, + { + "epoch": 12.85, + "learning_rate": 5.986203746736362e-06, + "loss": 0.0069, + "step": 41610 + }, + { + "epoch": 12.85, + "learning_rate": 5.985745687580478e-06, + "loss": 0.0071, + "step": 41611 + }, + { + "epoch": 12.85, + "learning_rate": 5.985287638464972e-06, + "loss": 0.0081, + "step": 41612 + }, + { + "epoch": 12.85, + "learning_rate": 5.984829599390993e-06, + "loss": 0.0086, + "step": 41613 + }, + { + "epoch": 12.85, + "learning_rate": 5.984371570359691e-06, + "loss": 0.0072, + "step": 41614 + }, + { + "epoch": 12.85, + "learning_rate": 5.983913551372208e-06, + "loss": 0.0074, + "step": 41615 + }, + { + "epoch": 12.85, + "learning_rate": 5.983455542429686e-06, + "loss": 0.0072, + "step": 41616 + }, + { + "epoch": 12.85, + "learning_rate": 5.982997543533278e-06, + "loss": 0.0072, + "step": 41617 + }, + { + "epoch": 12.85, + "learning_rate": 5.982539554684126e-06, + "loss": 0.0077, + "step": 41618 + }, + { + "epoch": 12.85, + "learning_rate": 5.982081575883372e-06, + "loss": 0.0074, + "step": 41619 + }, + { + "epoch": 12.85, + "learning_rate": 5.981623607132165e-06, + "loss": 0.0071, + "step": 41620 + }, + { + "epoch": 12.85, + "learning_rate": 5.981165648431655e-06, + "loss": 0.008, + "step": 41621 + }, + { + "epoch": 12.85, + "learning_rate": 5.98070769978298e-06, + "loss": 0.0067, + "step": 41622 + }, + { + "epoch": 12.85, + "learning_rate": 5.980249761187284e-06, + "loss": 0.0074, + "step": 41623 + }, + { + "epoch": 12.85, + "learning_rate": 5.979791832645723e-06, + "loss": 0.0064, + "step": 41624 + }, + { + "epoch": 12.85, + "learning_rate": 5.979333914159433e-06, + "loss": 0.0078, + "step": 41625 + }, + { + "epoch": 12.85, + "learning_rate": 5.97887600572956e-06, + "loss": 0.0077, + "step": 41626 + }, + { + "epoch": 12.86, + "learning_rate": 5.9784181073572556e-06, + "loss": 0.0074, + "step": 41627 + }, + { + "epoch": 12.86, + "learning_rate": 5.9779602190436595e-06, + "loss": 0.0068, + "step": 41628 + }, + { + "epoch": 12.86, + "learning_rate": 5.977502340789915e-06, + "loss": 0.0062, + "step": 41629 + }, + { + "epoch": 12.86, + "learning_rate": 5.977044472597178e-06, + "loss": 0.0072, + "step": 41630 + }, + { + "epoch": 12.86, + "learning_rate": 5.976586614466582e-06, + "loss": 0.0062, + "step": 41631 + }, + { + "epoch": 12.86, + "learning_rate": 5.976128766399276e-06, + "loss": 0.0068, + "step": 41632 + }, + { + "epoch": 12.86, + "learning_rate": 5.9756709283964095e-06, + "loss": 0.0083, + "step": 41633 + }, + { + "epoch": 12.86, + "learning_rate": 5.9752131004591195e-06, + "loss": 0.007, + "step": 41634 + }, + { + "epoch": 12.86, + "learning_rate": 5.974755282588558e-06, + "loss": 0.0068, + "step": 41635 + }, + { + "epoch": 12.86, + "learning_rate": 5.974297474785868e-06, + "loss": 0.0068, + "step": 41636 + }, + { + "epoch": 12.86, + "learning_rate": 5.973839677052193e-06, + "loss": 0.0066, + "step": 41637 + }, + { + "epoch": 12.86, + "learning_rate": 5.973381889388679e-06, + "loss": 0.0095, + "step": 41638 + }, + { + "epoch": 12.86, + "learning_rate": 5.972924111796474e-06, + "loss": 0.0074, + "step": 41639 + }, + { + "epoch": 12.86, + "learning_rate": 5.972466344276717e-06, + "loss": 0.0086, + "step": 41640 + }, + { + "epoch": 12.86, + "learning_rate": 5.9720085868305575e-06, + "loss": 0.0072, + "step": 41641 + }, + { + "epoch": 12.86, + "learning_rate": 5.971550839459142e-06, + "loss": 0.0084, + "step": 41642 + }, + { + "epoch": 12.86, + "learning_rate": 5.9710931021636096e-06, + "loss": 0.0067, + "step": 41643 + }, + { + "epoch": 12.86, + "learning_rate": 5.9706353749451065e-06, + "loss": 0.0068, + "step": 41644 + }, + { + "epoch": 12.86, + "learning_rate": 5.9701776578047836e-06, + "loss": 0.0069, + "step": 41645 + }, + { + "epoch": 12.86, + "learning_rate": 5.969719950743778e-06, + "loss": 0.0073, + "step": 41646 + }, + { + "epoch": 12.86, + "learning_rate": 5.969262253763238e-06, + "loss": 0.0068, + "step": 41647 + }, + { + "epoch": 12.86, + "learning_rate": 5.968804566864309e-06, + "loss": 0.0078, + "step": 41648 + }, + { + "epoch": 12.86, + "learning_rate": 5.9683468900481375e-06, + "loss": 0.0061, + "step": 41649 + }, + { + "epoch": 12.86, + "learning_rate": 5.967889223315862e-06, + "loss": 0.0076, + "step": 41650 + }, + { + "epoch": 12.86, + "learning_rate": 5.967431566668631e-06, + "loss": 0.0097, + "step": 41651 + }, + { + "epoch": 12.86, + "learning_rate": 5.966973920107593e-06, + "loss": 0.0083, + "step": 41652 + }, + { + "epoch": 12.86, + "learning_rate": 5.9665162836338875e-06, + "loss": 0.0066, + "step": 41653 + }, + { + "epoch": 12.86, + "learning_rate": 5.9660586572486565e-06, + "loss": 0.0082, + "step": 41654 + }, + { + "epoch": 12.86, + "learning_rate": 5.965601040953053e-06, + "loss": 0.0064, + "step": 41655 + }, + { + "epoch": 12.86, + "learning_rate": 5.965143434748215e-06, + "loss": 0.0072, + "step": 41656 + }, + { + "epoch": 12.86, + "learning_rate": 5.9646858386352894e-06, + "loss": 0.0074, + "step": 41657 + }, + { + "epoch": 12.86, + "learning_rate": 5.964228252615423e-06, + "loss": 0.0095, + "step": 41658 + }, + { + "epoch": 12.87, + "learning_rate": 5.963770676689755e-06, + "loss": 0.0062, + "step": 41659 + }, + { + "epoch": 12.87, + "learning_rate": 5.9633131108594315e-06, + "loss": 0.0068, + "step": 41660 + }, + { + "epoch": 12.87, + "learning_rate": 5.962855555125604e-06, + "loss": 0.009, + "step": 41661 + }, + { + "epoch": 12.87, + "learning_rate": 5.962398009489405e-06, + "loss": 0.0068, + "step": 41662 + }, + { + "epoch": 12.87, + "learning_rate": 5.961940473951986e-06, + "loss": 0.0073, + "step": 41663 + }, + { + "epoch": 12.87, + "learning_rate": 5.961482948514495e-06, + "loss": 0.0064, + "step": 41664 + }, + { + "epoch": 12.87, + "learning_rate": 5.9610254331780645e-06, + "loss": 0.0068, + "step": 41665 + }, + { + "epoch": 12.87, + "learning_rate": 5.96056792794385e-06, + "loss": 0.0073, + "step": 41666 + }, + { + "epoch": 12.87, + "learning_rate": 5.960110432812993e-06, + "loss": 0.0063, + "step": 41667 + }, + { + "epoch": 12.87, + "learning_rate": 5.959652947786634e-06, + "loss": 0.0077, + "step": 41668 + }, + { + "epoch": 12.87, + "learning_rate": 5.959195472865922e-06, + "loss": 0.0065, + "step": 41669 + }, + { + "epoch": 12.87, + "learning_rate": 5.958738008051999e-06, + "loss": 0.0062, + "step": 41670 + }, + { + "epoch": 12.87, + "learning_rate": 5.95828055334601e-06, + "loss": 0.0062, + "step": 41671 + }, + { + "epoch": 12.87, + "learning_rate": 5.957823108749094e-06, + "loss": 0.0071, + "step": 41672 + }, + { + "epoch": 12.87, + "learning_rate": 5.9573656742624054e-06, + "loss": 0.007, + "step": 41673 + }, + { + "epoch": 12.87, + "learning_rate": 5.956908249887079e-06, + "loss": 0.0086, + "step": 41674 + }, + { + "epoch": 12.87, + "learning_rate": 5.956450835624261e-06, + "loss": 0.0075, + "step": 41675 + }, + { + "epoch": 12.87, + "learning_rate": 5.955993431475102e-06, + "loss": 0.0077, + "step": 41676 + }, + { + "epoch": 12.87, + "learning_rate": 5.955536037440738e-06, + "loss": 0.0069, + "step": 41677 + }, + { + "epoch": 12.87, + "learning_rate": 5.955078653522315e-06, + "loss": 0.008, + "step": 41678 + }, + { + "epoch": 12.87, + "learning_rate": 5.954621279720979e-06, + "loss": 0.0067, + "step": 41679 + }, + { + "epoch": 12.87, + "learning_rate": 5.954163916037875e-06, + "loss": 0.0061, + "step": 41680 + }, + { + "epoch": 12.87, + "learning_rate": 5.953706562474144e-06, + "loss": 0.0069, + "step": 41681 + }, + { + "epoch": 12.87, + "learning_rate": 5.953249219030928e-06, + "loss": 0.008, + "step": 41682 + }, + { + "epoch": 12.87, + "learning_rate": 5.952791885709378e-06, + "loss": 0.008, + "step": 41683 + }, + { + "epoch": 12.87, + "learning_rate": 5.952334562510631e-06, + "loss": 0.0075, + "step": 41684 + }, + { + "epoch": 12.87, + "learning_rate": 5.951877249435834e-06, + "loss": 0.0061, + "step": 41685 + }, + { + "epoch": 12.87, + "learning_rate": 5.951419946486131e-06, + "loss": 0.0061, + "step": 41686 + }, + { + "epoch": 12.87, + "learning_rate": 5.950962653662664e-06, + "loss": 0.007, + "step": 41687 + }, + { + "epoch": 12.87, + "learning_rate": 5.950505370966577e-06, + "loss": 0.0065, + "step": 41688 + }, + { + "epoch": 12.87, + "learning_rate": 5.950048098399018e-06, + "loss": 0.0066, + "step": 41689 + }, + { + "epoch": 12.87, + "learning_rate": 5.949590835961125e-06, + "loss": 0.0056, + "step": 41690 + }, + { + "epoch": 12.87, + "learning_rate": 5.949133583654046e-06, + "loss": 0.0066, + "step": 41691 + }, + { + "epoch": 12.88, + "learning_rate": 5.9486763414789225e-06, + "loss": 0.0099, + "step": 41692 + }, + { + "epoch": 12.88, + "learning_rate": 5.948219109436896e-06, + "loss": 0.0069, + "step": 41693 + }, + { + "epoch": 12.88, + "learning_rate": 5.947761887529113e-06, + "loss": 0.0087, + "step": 41694 + }, + { + "epoch": 12.88, + "learning_rate": 5.94730467575672e-06, + "loss": 0.0074, + "step": 41695 + }, + { + "epoch": 12.88, + "learning_rate": 5.9468474741208526e-06, + "loss": 0.0083, + "step": 41696 + }, + { + "epoch": 12.88, + "learning_rate": 5.94639028262266e-06, + "loss": 0.007, + "step": 41697 + }, + { + "epoch": 12.88, + "learning_rate": 5.945933101263288e-06, + "loss": 0.0055, + "step": 41698 + }, + { + "epoch": 12.88, + "learning_rate": 5.945475930043873e-06, + "loss": 0.0072, + "step": 41699 + }, + { + "epoch": 12.88, + "learning_rate": 5.945018768965563e-06, + "loss": 0.0071, + "step": 41700 + }, + { + "epoch": 12.88, + "learning_rate": 5.944561618029503e-06, + "loss": 0.0079, + "step": 41701 + }, + { + "epoch": 12.88, + "learning_rate": 5.944104477236832e-06, + "loss": 0.007, + "step": 41702 + }, + { + "epoch": 12.88, + "learning_rate": 5.9436473465886936e-06, + "loss": 0.0083, + "step": 41703 + }, + { + "epoch": 12.88, + "learning_rate": 5.943190226086237e-06, + "loss": 0.0088, + "step": 41704 + }, + { + "epoch": 12.88, + "learning_rate": 5.942733115730599e-06, + "loss": 0.0076, + "step": 41705 + }, + { + "epoch": 12.88, + "learning_rate": 5.942276015522926e-06, + "loss": 0.0072, + "step": 41706 + }, + { + "epoch": 12.88, + "learning_rate": 5.9418189254643625e-06, + "loss": 0.008, + "step": 41707 + }, + { + "epoch": 12.88, + "learning_rate": 5.9413618455560474e-06, + "loss": 0.0068, + "step": 41708 + }, + { + "epoch": 12.88, + "learning_rate": 5.940904775799126e-06, + "loss": 0.0079, + "step": 41709 + }, + { + "epoch": 12.88, + "learning_rate": 5.940447716194747e-06, + "loss": 0.0063, + "step": 41710 + }, + { + "epoch": 12.88, + "learning_rate": 5.939990666744044e-06, + "loss": 0.0078, + "step": 41711 + }, + { + "epoch": 12.88, + "learning_rate": 5.939533627448165e-06, + "loss": 0.0066, + "step": 41712 + }, + { + "epoch": 12.88, + "learning_rate": 5.9390765983082535e-06, + "loss": 0.0071, + "step": 41713 + }, + { + "epoch": 12.88, + "learning_rate": 5.938619579325453e-06, + "loss": 0.0074, + "step": 41714 + }, + { + "epoch": 12.88, + "learning_rate": 5.938162570500906e-06, + "loss": 0.0079, + "step": 41715 + }, + { + "epoch": 12.88, + "learning_rate": 5.937705571835752e-06, + "loss": 0.0087, + "step": 41716 + }, + { + "epoch": 12.88, + "learning_rate": 5.9372485833311435e-06, + "loss": 0.0057, + "step": 41717 + }, + { + "epoch": 12.88, + "learning_rate": 5.936791604988212e-06, + "loss": 0.0067, + "step": 41718 + }, + { + "epoch": 12.88, + "learning_rate": 5.936334636808105e-06, + "loss": 0.0098, + "step": 41719 + }, + { + "epoch": 12.88, + "learning_rate": 5.935877678791975e-06, + "loss": 0.008, + "step": 41720 + }, + { + "epoch": 12.88, + "learning_rate": 5.9354207309409464e-06, + "loss": 0.0068, + "step": 41721 + }, + { + "epoch": 12.88, + "learning_rate": 5.934963793256177e-06, + "loss": 0.0061, + "step": 41722 + }, + { + "epoch": 12.88, + "learning_rate": 5.934506865738804e-06, + "loss": 0.0071, + "step": 41723 + }, + { + "epoch": 12.89, + "learning_rate": 5.934049948389967e-06, + "loss": 0.0085, + "step": 41724 + }, + { + "epoch": 12.89, + "learning_rate": 5.933593041210817e-06, + "loss": 0.0076, + "step": 41725 + }, + { + "epoch": 12.89, + "learning_rate": 5.9331361442024915e-06, + "loss": 0.0089, + "step": 41726 + }, + { + "epoch": 12.89, + "learning_rate": 5.932679257366132e-06, + "loss": 0.0064, + "step": 41727 + }, + { + "epoch": 12.89, + "learning_rate": 5.932222380702886e-06, + "loss": 0.0069, + "step": 41728 + }, + { + "epoch": 12.89, + "learning_rate": 5.931765514213894e-06, + "loss": 0.0069, + "step": 41729 + }, + { + "epoch": 12.89, + "learning_rate": 5.931308657900297e-06, + "loss": 0.0077, + "step": 41730 + }, + { + "epoch": 12.89, + "learning_rate": 5.9308518117632386e-06, + "loss": 0.007, + "step": 41731 + }, + { + "epoch": 12.89, + "learning_rate": 5.930394975803864e-06, + "loss": 0.0078, + "step": 41732 + }, + { + "epoch": 12.89, + "learning_rate": 5.929938150023313e-06, + "loss": 0.0065, + "step": 41733 + }, + { + "epoch": 12.89, + "learning_rate": 5.929481334422726e-06, + "loss": 0.0081, + "step": 41734 + }, + { + "epoch": 12.89, + "learning_rate": 5.929024529003253e-06, + "loss": 0.007, + "step": 41735 + }, + { + "epoch": 12.89, + "learning_rate": 5.92856773376603e-06, + "loss": 0.0058, + "step": 41736 + }, + { + "epoch": 12.89, + "learning_rate": 5.928110948712201e-06, + "loss": 0.0064, + "step": 41737 + }, + { + "epoch": 12.89, + "learning_rate": 5.927654173842913e-06, + "loss": 0.01, + "step": 41738 + }, + { + "epoch": 12.89, + "learning_rate": 5.927197409159302e-06, + "loss": 0.0061, + "step": 41739 + }, + { + "epoch": 12.89, + "learning_rate": 5.9267406546625126e-06, + "loss": 0.0073, + "step": 41740 + }, + { + "epoch": 12.89, + "learning_rate": 5.926283910353689e-06, + "loss": 0.0065, + "step": 41741 + }, + { + "epoch": 12.89, + "learning_rate": 5.925827176233971e-06, + "loss": 0.0061, + "step": 41742 + }, + { + "epoch": 12.89, + "learning_rate": 5.925370452304503e-06, + "loss": 0.0062, + "step": 41743 + }, + { + "epoch": 12.89, + "learning_rate": 5.924913738566425e-06, + "loss": 0.0077, + "step": 41744 + }, + { + "epoch": 12.89, + "learning_rate": 5.924457035020884e-06, + "loss": 0.009, + "step": 41745 + }, + { + "epoch": 12.89, + "learning_rate": 5.924000341669019e-06, + "loss": 0.0074, + "step": 41746 + }, + { + "epoch": 12.89, + "learning_rate": 5.923543658511968e-06, + "loss": 0.0072, + "step": 41747 + }, + { + "epoch": 12.89, + "learning_rate": 5.923086985550883e-06, + "loss": 0.0067, + "step": 41748 + }, + { + "epoch": 12.89, + "learning_rate": 5.9226303227869e-06, + "loss": 0.0086, + "step": 41749 + }, + { + "epoch": 12.89, + "learning_rate": 5.922173670221159e-06, + "loss": 0.007, + "step": 41750 + }, + { + "epoch": 12.89, + "learning_rate": 5.921717027854812e-06, + "loss": 0.0075, + "step": 41751 + }, + { + "epoch": 12.89, + "learning_rate": 5.9212603956889884e-06, + "loss": 0.0061, + "step": 41752 + }, + { + "epoch": 12.89, + "learning_rate": 5.9208037737248384e-06, + "loss": 0.0075, + "step": 41753 + }, + { + "epoch": 12.89, + "learning_rate": 5.920347161963504e-06, + "loss": 0.0063, + "step": 41754 + }, + { + "epoch": 12.89, + "learning_rate": 5.919890560406122e-06, + "loss": 0.0075, + "step": 41755 + }, + { + "epoch": 12.9, + "learning_rate": 5.9194339690538394e-06, + "loss": 0.0077, + "step": 41756 + }, + { + "epoch": 12.9, + "learning_rate": 5.918977387907798e-06, + "loss": 0.0075, + "step": 41757 + }, + { + "epoch": 12.9, + "learning_rate": 5.918520816969136e-06, + "loss": 0.0095, + "step": 41758 + }, + { + "epoch": 12.9, + "learning_rate": 5.918064256238999e-06, + "loss": 0.0068, + "step": 41759 + }, + { + "epoch": 12.9, + "learning_rate": 5.91760770571853e-06, + "loss": 0.0069, + "step": 41760 + }, + { + "epoch": 12.9, + "learning_rate": 5.9171511654088675e-06, + "loss": 0.0064, + "step": 41761 + }, + { + "epoch": 12.9, + "learning_rate": 5.916694635311151e-06, + "loss": 0.006, + "step": 41762 + }, + { + "epoch": 12.9, + "learning_rate": 5.9162381154265316e-06, + "loss": 0.0089, + "step": 41763 + }, + { + "epoch": 12.9, + "learning_rate": 5.9157816057561415e-06, + "loss": 0.008, + "step": 41764 + }, + { + "epoch": 12.9, + "learning_rate": 5.915325106301126e-06, + "loss": 0.007, + "step": 41765 + }, + { + "epoch": 12.9, + "learning_rate": 5.914868617062631e-06, + "loss": 0.0084, + "step": 41766 + }, + { + "epoch": 12.9, + "learning_rate": 5.914412138041793e-06, + "loss": 0.0081, + "step": 41767 + }, + { + "epoch": 12.9, + "learning_rate": 5.913955669239752e-06, + "loss": 0.0068, + "step": 41768 + }, + { + "epoch": 12.9, + "learning_rate": 5.913499210657661e-06, + "loss": 0.0098, + "step": 41769 + }, + { + "epoch": 12.9, + "learning_rate": 5.913042762296648e-06, + "loss": 0.0072, + "step": 41770 + }, + { + "epoch": 12.9, + "learning_rate": 5.9125863241578606e-06, + "loss": 0.0076, + "step": 41771 + }, + { + "epoch": 12.9, + "learning_rate": 5.912129896242443e-06, + "loss": 0.0083, + "step": 41772 + }, + { + "epoch": 12.9, + "learning_rate": 5.9116734785515305e-06, + "loss": 0.0079, + "step": 41773 + }, + { + "epoch": 12.9, + "learning_rate": 5.91121707108627e-06, + "loss": 0.008, + "step": 41774 + }, + { + "epoch": 12.9, + "learning_rate": 5.910760673847804e-06, + "loss": 0.0063, + "step": 41775 + }, + { + "epoch": 12.9, + "learning_rate": 5.910304286837267e-06, + "loss": 0.0076, + "step": 41776 + }, + { + "epoch": 12.9, + "learning_rate": 5.909847910055806e-06, + "loss": 0.0081, + "step": 41777 + }, + { + "epoch": 12.9, + "learning_rate": 5.9093915435045615e-06, + "loss": 0.0061, + "step": 41778 + }, + { + "epoch": 12.9, + "learning_rate": 5.908935187184679e-06, + "loss": 0.0104, + "step": 41779 + }, + { + "epoch": 12.9, + "learning_rate": 5.908478841097289e-06, + "loss": 0.0068, + "step": 41780 + }, + { + "epoch": 12.9, + "learning_rate": 5.908022505243544e-06, + "loss": 0.0077, + "step": 41781 + }, + { + "epoch": 12.9, + "learning_rate": 5.907566179624582e-06, + "loss": 0.0069, + "step": 41782 + }, + { + "epoch": 12.9, + "learning_rate": 5.907109864241539e-06, + "loss": 0.0067, + "step": 41783 + }, + { + "epoch": 12.9, + "learning_rate": 5.9066535590955634e-06, + "loss": 0.0078, + "step": 41784 + }, + { + "epoch": 12.9, + "learning_rate": 5.906197264187795e-06, + "loss": 0.0078, + "step": 41785 + }, + { + "epoch": 12.9, + "learning_rate": 5.90574097951937e-06, + "loss": 0.006, + "step": 41786 + }, + { + "epoch": 12.9, + "learning_rate": 5.905284705091436e-06, + "loss": 0.0071, + "step": 41787 + }, + { + "epoch": 12.9, + "learning_rate": 5.904828440905135e-06, + "loss": 0.0077, + "step": 41788 + }, + { + "epoch": 12.91, + "learning_rate": 5.904372186961599e-06, + "loss": 0.009, + "step": 41789 + }, + { + "epoch": 12.91, + "learning_rate": 5.903915943261977e-06, + "loss": 0.0076, + "step": 41790 + }, + { + "epoch": 12.91, + "learning_rate": 5.903459709807412e-06, + "loss": 0.0073, + "step": 41791 + }, + { + "epoch": 12.91, + "learning_rate": 5.90300348659904e-06, + "loss": 0.0078, + "step": 41792 + }, + { + "epoch": 12.91, + "learning_rate": 5.9025472736379984e-06, + "loss": 0.0058, + "step": 41793 + }, + { + "epoch": 12.91, + "learning_rate": 5.90209107092544e-06, + "loss": 0.0081, + "step": 41794 + }, + { + "epoch": 12.91, + "learning_rate": 5.901634878462497e-06, + "loss": 0.0081, + "step": 41795 + }, + { + "epoch": 12.91, + "learning_rate": 5.901178696250309e-06, + "loss": 0.0067, + "step": 41796 + }, + { + "epoch": 12.91, + "learning_rate": 5.900722524290026e-06, + "loss": 0.0083, + "step": 41797 + }, + { + "epoch": 12.91, + "learning_rate": 5.9002663625827805e-06, + "loss": 0.0083, + "step": 41798 + }, + { + "epoch": 12.91, + "learning_rate": 5.899810211129715e-06, + "loss": 0.0076, + "step": 41799 + }, + { + "epoch": 12.91, + "learning_rate": 5.899354069931979e-06, + "loss": 0.0063, + "step": 41800 + }, + { + "epoch": 12.91, + "learning_rate": 5.898897938990699e-06, + "loss": 0.0078, + "step": 41801 + }, + { + "epoch": 12.91, + "learning_rate": 5.898441818307027e-06, + "loss": 0.0071, + "step": 41802 + }, + { + "epoch": 12.91, + "learning_rate": 5.897985707882101e-06, + "loss": 0.0089, + "step": 41803 + }, + { + "epoch": 12.91, + "learning_rate": 5.897529607717058e-06, + "loss": 0.0088, + "step": 41804 + }, + { + "epoch": 12.91, + "learning_rate": 5.897073517813041e-06, + "loss": 0.0087, + "step": 41805 + }, + { + "epoch": 12.91, + "learning_rate": 5.896617438171196e-06, + "loss": 0.0073, + "step": 41806 + }, + { + "epoch": 12.91, + "learning_rate": 5.896161368792654e-06, + "loss": 0.0076, + "step": 41807 + }, + { + "epoch": 12.91, + "learning_rate": 5.895705309678563e-06, + "loss": 0.0074, + "step": 41808 + }, + { + "epoch": 12.91, + "learning_rate": 5.89524926083006e-06, + "loss": 0.0072, + "step": 41809 + }, + { + "epoch": 12.91, + "learning_rate": 5.894793222248294e-06, + "loss": 0.0067, + "step": 41810 + }, + { + "epoch": 12.91, + "learning_rate": 5.894337193934392e-06, + "loss": 0.0085, + "step": 41811 + }, + { + "epoch": 12.91, + "learning_rate": 5.893881175889503e-06, + "loss": 0.0067, + "step": 41812 + }, + { + "epoch": 12.91, + "learning_rate": 5.89342516811477e-06, + "loss": 0.0054, + "step": 41813 + }, + { + "epoch": 12.91, + "learning_rate": 5.892969170611322e-06, + "loss": 0.0065, + "step": 41814 + }, + { + "epoch": 12.91, + "learning_rate": 5.892513183380313e-06, + "loss": 0.0093, + "step": 41815 + }, + { + "epoch": 12.91, + "learning_rate": 5.892057206422878e-06, + "loss": 0.0073, + "step": 41816 + }, + { + "epoch": 12.91, + "learning_rate": 5.891601239740152e-06, + "loss": 0.007, + "step": 41817 + }, + { + "epoch": 12.91, + "learning_rate": 5.891145283333285e-06, + "loss": 0.0058, + "step": 41818 + }, + { + "epoch": 12.91, + "learning_rate": 5.890689337203415e-06, + "loss": 0.0079, + "step": 41819 + }, + { + "epoch": 12.91, + "learning_rate": 5.890233401351677e-06, + "loss": 0.0072, + "step": 41820 + }, + { + "epoch": 12.92, + "learning_rate": 5.889777475779212e-06, + "loss": 0.0065, + "step": 41821 + }, + { + "epoch": 12.92, + "learning_rate": 5.889321560487169e-06, + "loss": 0.007, + "step": 41822 + }, + { + "epoch": 12.92, + "learning_rate": 5.88886565547668e-06, + "loss": 0.0075, + "step": 41823 + }, + { + "epoch": 12.92, + "learning_rate": 5.888409760748886e-06, + "loss": 0.0082, + "step": 41824 + }, + { + "epoch": 12.92, + "learning_rate": 5.887953876304933e-06, + "loss": 0.0073, + "step": 41825 + }, + { + "epoch": 12.92, + "learning_rate": 5.887498002145955e-06, + "loss": 0.0089, + "step": 41826 + }, + { + "epoch": 12.92, + "learning_rate": 5.8870421382730935e-06, + "loss": 0.0094, + "step": 41827 + }, + { + "epoch": 12.92, + "learning_rate": 5.886586284687492e-06, + "loss": 0.0076, + "step": 41828 + }, + { + "epoch": 12.92, + "learning_rate": 5.8861304413902874e-06, + "loss": 0.0062, + "step": 41829 + }, + { + "epoch": 12.92, + "learning_rate": 5.885674608382621e-06, + "loss": 0.0077, + "step": 41830 + }, + { + "epoch": 12.92, + "learning_rate": 5.8852187856656365e-06, + "loss": 0.0077, + "step": 41831 + }, + { + "epoch": 12.92, + "learning_rate": 5.8847629732404636e-06, + "loss": 0.0072, + "step": 41832 + }, + { + "epoch": 12.92, + "learning_rate": 5.884307171108252e-06, + "loss": 0.008, + "step": 41833 + }, + { + "epoch": 12.92, + "learning_rate": 5.883851379270141e-06, + "loss": 0.0062, + "step": 41834 + }, + { + "epoch": 12.92, + "learning_rate": 5.883395597727264e-06, + "loss": 0.0071, + "step": 41835 + }, + { + "epoch": 12.92, + "learning_rate": 5.882939826480768e-06, + "loss": 0.0071, + "step": 41836 + }, + { + "epoch": 12.92, + "learning_rate": 5.882484065531793e-06, + "loss": 0.0078, + "step": 41837 + }, + { + "epoch": 12.92, + "learning_rate": 5.882028314881471e-06, + "loss": 0.0078, + "step": 41838 + }, + { + "epoch": 12.92, + "learning_rate": 5.8815725745309495e-06, + "loss": 0.0073, + "step": 41839 + }, + { + "epoch": 12.92, + "learning_rate": 5.88111684448137e-06, + "loss": 0.0075, + "step": 41840 + }, + { + "epoch": 12.92, + "learning_rate": 5.880661124733864e-06, + "loss": 0.0088, + "step": 41841 + }, + { + "epoch": 12.92, + "learning_rate": 5.880205415289575e-06, + "loss": 0.0067, + "step": 41842 + }, + { + "epoch": 12.92, + "learning_rate": 5.8797497161496455e-06, + "loss": 0.0075, + "step": 41843 + }, + { + "epoch": 12.92, + "learning_rate": 5.879294027315214e-06, + "loss": 0.0086, + "step": 41844 + }, + { + "epoch": 12.92, + "learning_rate": 5.878838348787418e-06, + "loss": 0.0067, + "step": 41845 + }, + { + "epoch": 12.92, + "learning_rate": 5.8783826805674005e-06, + "loss": 0.0073, + "step": 41846 + }, + { + "epoch": 12.92, + "learning_rate": 5.8779270226563e-06, + "loss": 0.0087, + "step": 41847 + }, + { + "epoch": 12.92, + "learning_rate": 5.877471375055254e-06, + "loss": 0.0073, + "step": 41848 + }, + { + "epoch": 12.92, + "learning_rate": 5.877015737765405e-06, + "loss": 0.0065, + "step": 41849 + }, + { + "epoch": 12.92, + "learning_rate": 5.876560110787893e-06, + "loss": 0.0079, + "step": 41850 + }, + { + "epoch": 12.92, + "learning_rate": 5.876104494123856e-06, + "loss": 0.0089, + "step": 41851 + }, + { + "epoch": 12.92, + "learning_rate": 5.87564888777443e-06, + "loss": 0.0081, + "step": 41852 + }, + { + "epoch": 12.92, + "learning_rate": 5.875193291740764e-06, + "loss": 0.0081, + "step": 41853 + }, + { + "epoch": 12.93, + "learning_rate": 5.874737706023987e-06, + "loss": 0.0066, + "step": 41854 + }, + { + "epoch": 12.93, + "learning_rate": 5.874282130625244e-06, + "loss": 0.0077, + "step": 41855 + }, + { + "epoch": 12.93, + "learning_rate": 5.873826565545677e-06, + "loss": 0.0074, + "step": 41856 + }, + { + "epoch": 12.93, + "learning_rate": 5.873371010786422e-06, + "loss": 0.0077, + "step": 41857 + }, + { + "epoch": 12.93, + "learning_rate": 5.872915466348614e-06, + "loss": 0.0076, + "step": 41858 + }, + { + "epoch": 12.93, + "learning_rate": 5.872459932233405e-06, + "loss": 0.007, + "step": 41859 + }, + { + "epoch": 12.93, + "learning_rate": 5.8720044084419206e-06, + "loss": 0.0068, + "step": 41860 + }, + { + "epoch": 12.93, + "learning_rate": 5.871548894975308e-06, + "loss": 0.0084, + "step": 41861 + }, + { + "epoch": 12.93, + "learning_rate": 5.871093391834706e-06, + "loss": 0.0076, + "step": 41862 + }, + { + "epoch": 12.93, + "learning_rate": 5.8706378990212475e-06, + "loss": 0.0077, + "step": 41863 + }, + { + "epoch": 12.93, + "learning_rate": 5.87018241653608e-06, + "loss": 0.0094, + "step": 41864 + }, + { + "epoch": 12.93, + "learning_rate": 5.869726944380341e-06, + "loss": 0.0074, + "step": 41865 + }, + { + "epoch": 12.93, + "learning_rate": 5.869271482555165e-06, + "loss": 0.0055, + "step": 41866 + }, + { + "epoch": 12.93, + "learning_rate": 5.868816031061696e-06, + "loss": 0.0077, + "step": 41867 + }, + { + "epoch": 12.93, + "learning_rate": 5.868360589901074e-06, + "loss": 0.0074, + "step": 41868 + }, + { + "epoch": 12.93, + "learning_rate": 5.867905159074433e-06, + "loss": 0.0098, + "step": 41869 + }, + { + "epoch": 12.93, + "learning_rate": 5.867449738582913e-06, + "loss": 0.0073, + "step": 41870 + }, + { + "epoch": 12.93, + "learning_rate": 5.866994328427659e-06, + "loss": 0.0073, + "step": 41871 + }, + { + "epoch": 12.93, + "learning_rate": 5.866538928609804e-06, + "loss": 0.0078, + "step": 41872 + }, + { + "epoch": 12.93, + "learning_rate": 5.866083539130487e-06, + "loss": 0.0077, + "step": 41873 + }, + { + "epoch": 12.93, + "learning_rate": 5.865628159990853e-06, + "loss": 0.0076, + "step": 41874 + }, + { + "epoch": 12.93, + "learning_rate": 5.865172791192035e-06, + "loss": 0.0072, + "step": 41875 + }, + { + "epoch": 12.93, + "learning_rate": 5.864717432735172e-06, + "loss": 0.0069, + "step": 41876 + }, + { + "epoch": 12.93, + "learning_rate": 5.864262084621408e-06, + "loss": 0.0064, + "step": 41877 + }, + { + "epoch": 12.93, + "learning_rate": 5.86380674685188e-06, + "loss": 0.007, + "step": 41878 + }, + { + "epoch": 12.93, + "learning_rate": 5.863351419427723e-06, + "loss": 0.0062, + "step": 41879 + }, + { + "epoch": 12.93, + "learning_rate": 5.862896102350078e-06, + "loss": 0.0071, + "step": 41880 + }, + { + "epoch": 12.93, + "learning_rate": 5.862440795620088e-06, + "loss": 0.0074, + "step": 41881 + }, + { + "epoch": 12.93, + "learning_rate": 5.8619854992388844e-06, + "loss": 0.0065, + "step": 41882 + }, + { + "epoch": 12.93, + "learning_rate": 5.86153021320761e-06, + "loss": 0.0073, + "step": 41883 + }, + { + "epoch": 12.93, + "learning_rate": 5.8610749375274065e-06, + "loss": 0.006, + "step": 41884 + }, + { + "epoch": 12.93, + "learning_rate": 5.860619672199408e-06, + "loss": 0.007, + "step": 41885 + }, + { + "epoch": 12.94, + "learning_rate": 5.860164417224752e-06, + "loss": 0.0076, + "step": 41886 + }, + { + "epoch": 12.94, + "learning_rate": 5.859709172604584e-06, + "loss": 0.0079, + "step": 41887 + }, + { + "epoch": 12.94, + "learning_rate": 5.859253938340037e-06, + "loss": 0.0073, + "step": 41888 + }, + { + "epoch": 12.94, + "learning_rate": 5.85879871443225e-06, + "loss": 0.0081, + "step": 41889 + }, + { + "epoch": 12.94, + "learning_rate": 5.858343500882366e-06, + "loss": 0.0059, + "step": 41890 + }, + { + "epoch": 12.94, + "learning_rate": 5.8578882976915165e-06, + "loss": 0.0075, + "step": 41891 + }, + { + "epoch": 12.94, + "learning_rate": 5.8574331048608445e-06, + "loss": 0.0066, + "step": 41892 + }, + { + "epoch": 12.94, + "learning_rate": 5.85697792239149e-06, + "loss": 0.0068, + "step": 41893 + }, + { + "epoch": 12.94, + "learning_rate": 5.856522750284586e-06, + "loss": 0.0076, + "step": 41894 + }, + { + "epoch": 12.94, + "learning_rate": 5.856067588541276e-06, + "loss": 0.0065, + "step": 41895 + }, + { + "epoch": 12.94, + "learning_rate": 5.8556124371626985e-06, + "loss": 0.0073, + "step": 41896 + }, + { + "epoch": 12.94, + "learning_rate": 5.855157296149987e-06, + "loss": 0.0069, + "step": 41897 + }, + { + "epoch": 12.94, + "learning_rate": 5.854702165504285e-06, + "loss": 0.008, + "step": 41898 + }, + { + "epoch": 12.94, + "learning_rate": 5.8542470452267305e-06, + "loss": 0.0066, + "step": 41899 + }, + { + "epoch": 12.94, + "learning_rate": 5.853791935318458e-06, + "loss": 0.0068, + "step": 41900 + }, + { + "epoch": 12.94, + "learning_rate": 5.853336835780607e-06, + "loss": 0.0086, + "step": 41901 + }, + { + "epoch": 12.94, + "learning_rate": 5.852881746614321e-06, + "loss": 0.0074, + "step": 41902 + }, + { + "epoch": 12.94, + "learning_rate": 5.852426667820731e-06, + "loss": 0.0075, + "step": 41903 + }, + { + "epoch": 12.94, + "learning_rate": 5.851971599400976e-06, + "loss": 0.0059, + "step": 41904 + }, + { + "epoch": 12.94, + "learning_rate": 5.8515165413562015e-06, + "loss": 0.0081, + "step": 41905 + }, + { + "epoch": 12.94, + "learning_rate": 5.85106149368754e-06, + "loss": 0.0074, + "step": 41906 + }, + { + "epoch": 12.94, + "learning_rate": 5.850606456396126e-06, + "loss": 0.0069, + "step": 41907 + }, + { + "epoch": 12.94, + "learning_rate": 5.850151429483106e-06, + "loss": 0.0076, + "step": 41908 + }, + { + "epoch": 12.94, + "learning_rate": 5.849696412949615e-06, + "loss": 0.0084, + "step": 41909 + }, + { + "epoch": 12.94, + "learning_rate": 5.849241406796788e-06, + "loss": 0.008, + "step": 41910 + }, + { + "epoch": 12.94, + "learning_rate": 5.848786411025764e-06, + "loss": 0.0085, + "step": 41911 + }, + { + "epoch": 12.94, + "learning_rate": 5.848331425637687e-06, + "loss": 0.0067, + "step": 41912 + }, + { + "epoch": 12.94, + "learning_rate": 5.847876450633687e-06, + "loss": 0.0083, + "step": 41913 + }, + { + "epoch": 12.94, + "learning_rate": 5.847421486014904e-06, + "loss": 0.0089, + "step": 41914 + }, + { + "epoch": 12.94, + "learning_rate": 5.8469665317824805e-06, + "loss": 0.0066, + "step": 41915 + }, + { + "epoch": 12.94, + "learning_rate": 5.846511587937551e-06, + "loss": 0.007, + "step": 41916 + }, + { + "epoch": 12.94, + "learning_rate": 5.846056654481249e-06, + "loss": 0.0066, + "step": 41917 + }, + { + "epoch": 12.95, + "learning_rate": 5.845601731414725e-06, + "loss": 0.0083, + "step": 41918 + }, + { + "epoch": 12.95, + "learning_rate": 5.845146818739103e-06, + "loss": 0.0084, + "step": 41919 + }, + { + "epoch": 12.95, + "learning_rate": 5.844691916455527e-06, + "loss": 0.0091, + "step": 41920 + }, + { + "epoch": 12.95, + "learning_rate": 5.844237024565136e-06, + "loss": 0.0094, + "step": 41921 + }, + { + "epoch": 12.95, + "learning_rate": 5.843782143069064e-06, + "loss": 0.009, + "step": 41922 + }, + { + "epoch": 12.95, + "learning_rate": 5.843327271968452e-06, + "loss": 0.0065, + "step": 41923 + }, + { + "epoch": 12.95, + "learning_rate": 5.842872411264439e-06, + "loss": 0.0082, + "step": 41924 + }, + { + "epoch": 12.95, + "learning_rate": 5.8424175609581555e-06, + "loss": 0.0076, + "step": 41925 + }, + { + "epoch": 12.95, + "learning_rate": 5.8419627210507465e-06, + "loss": 0.0076, + "step": 41926 + }, + { + "epoch": 12.95, + "learning_rate": 5.8415078915433494e-06, + "loss": 0.007, + "step": 41927 + }, + { + "epoch": 12.95, + "learning_rate": 5.841053072437098e-06, + "loss": 0.0074, + "step": 41928 + }, + { + "epoch": 12.95, + "learning_rate": 5.840598263733128e-06, + "loss": 0.0075, + "step": 41929 + }, + { + "epoch": 12.95, + "learning_rate": 5.8401434654325855e-06, + "loss": 0.0062, + "step": 41930 + }, + { + "epoch": 12.95, + "learning_rate": 5.8396886775366e-06, + "loss": 0.007, + "step": 41931 + }, + { + "epoch": 12.95, + "learning_rate": 5.83923390004631e-06, + "loss": 0.0074, + "step": 41932 + }, + { + "epoch": 12.95, + "learning_rate": 5.83877913296286e-06, + "loss": 0.0081, + "step": 41933 + }, + { + "epoch": 12.95, + "learning_rate": 5.838324376287379e-06, + "loss": 0.006, + "step": 41934 + }, + { + "epoch": 12.95, + "learning_rate": 5.837869630021007e-06, + "loss": 0.0061, + "step": 41935 + }, + { + "epoch": 12.95, + "learning_rate": 5.837414894164885e-06, + "loss": 0.0081, + "step": 41936 + }, + { + "epoch": 12.95, + "learning_rate": 5.8369601687201446e-06, + "loss": 0.0068, + "step": 41937 + }, + { + "epoch": 12.95, + "learning_rate": 5.836505453687928e-06, + "loss": 0.0095, + "step": 41938 + }, + { + "epoch": 12.95, + "learning_rate": 5.836050749069373e-06, + "loss": 0.0086, + "step": 41939 + }, + { + "epoch": 12.95, + "learning_rate": 5.835596054865611e-06, + "loss": 0.0068, + "step": 41940 + }, + { + "epoch": 12.95, + "learning_rate": 5.835141371077782e-06, + "loss": 0.0066, + "step": 41941 + }, + { + "epoch": 12.95, + "learning_rate": 5.834686697707026e-06, + "loss": 0.0082, + "step": 41942 + }, + { + "epoch": 12.95, + "learning_rate": 5.834232034754481e-06, + "loss": 0.0078, + "step": 41943 + }, + { + "epoch": 12.95, + "learning_rate": 5.833777382221275e-06, + "loss": 0.0084, + "step": 41944 + }, + { + "epoch": 12.95, + "learning_rate": 5.833322740108554e-06, + "loss": 0.0075, + "step": 41945 + }, + { + "epoch": 12.95, + "learning_rate": 5.8328681084174556e-06, + "loss": 0.0063, + "step": 41946 + }, + { + "epoch": 12.95, + "learning_rate": 5.83241348714911e-06, + "loss": 0.0069, + "step": 41947 + }, + { + "epoch": 12.95, + "learning_rate": 5.831958876304663e-06, + "loss": 0.0065, + "step": 41948 + }, + { + "epoch": 12.95, + "learning_rate": 5.831504275885247e-06, + "loss": 0.0061, + "step": 41949 + }, + { + "epoch": 12.95, + "learning_rate": 5.831049685891994e-06, + "loss": 0.0073, + "step": 41950 + }, + { + "epoch": 12.96, + "learning_rate": 5.830595106326047e-06, + "loss": 0.0079, + "step": 41951 + }, + { + "epoch": 12.96, + "learning_rate": 5.8301405371885464e-06, + "loss": 0.0075, + "step": 41952 + }, + { + "epoch": 12.96, + "learning_rate": 5.829685978480625e-06, + "loss": 0.0085, + "step": 41953 + }, + { + "epoch": 12.96, + "learning_rate": 5.829231430203415e-06, + "loss": 0.0059, + "step": 41954 + }, + { + "epoch": 12.96, + "learning_rate": 5.828776892358062e-06, + "loss": 0.0061, + "step": 41955 + }, + { + "epoch": 12.96, + "learning_rate": 5.8283223649456945e-06, + "loss": 0.0064, + "step": 41956 + }, + { + "epoch": 12.96, + "learning_rate": 5.8278678479674544e-06, + "loss": 0.0071, + "step": 41957 + }, + { + "epoch": 12.96, + "learning_rate": 5.827413341424485e-06, + "loss": 0.0085, + "step": 41958 + }, + { + "epoch": 12.96, + "learning_rate": 5.8269588453179075e-06, + "loss": 0.007, + "step": 41959 + }, + { + "epoch": 12.96, + "learning_rate": 5.826504359648868e-06, + "loss": 0.0078, + "step": 41960 + }, + { + "epoch": 12.96, + "learning_rate": 5.826049884418505e-06, + "loss": 0.0079, + "step": 41961 + }, + { + "epoch": 12.96, + "learning_rate": 5.82559541962795e-06, + "loss": 0.0075, + "step": 41962 + }, + { + "epoch": 12.96, + "learning_rate": 5.825140965278347e-06, + "loss": 0.0069, + "step": 41963 + }, + { + "epoch": 12.96, + "learning_rate": 5.824686521370826e-06, + "loss": 0.0076, + "step": 41964 + }, + { + "epoch": 12.96, + "learning_rate": 5.824232087906522e-06, + "loss": 0.0079, + "step": 41965 + }, + { + "epoch": 12.96, + "learning_rate": 5.823777664886575e-06, + "loss": 0.0079, + "step": 41966 + }, + { + "epoch": 12.96, + "learning_rate": 5.8233232523121256e-06, + "loss": 0.0083, + "step": 41967 + }, + { + "epoch": 12.96, + "learning_rate": 5.822868850184307e-06, + "loss": 0.0068, + "step": 41968 + }, + { + "epoch": 12.96, + "learning_rate": 5.8224144585042515e-06, + "loss": 0.0083, + "step": 41969 + }, + { + "epoch": 12.96, + "learning_rate": 5.821960077273103e-06, + "loss": 0.0076, + "step": 41970 + }, + { + "epoch": 12.96, + "learning_rate": 5.82150570649199e-06, + "loss": 0.0075, + "step": 41971 + }, + { + "epoch": 12.96, + "learning_rate": 5.821051346162055e-06, + "loss": 0.0077, + "step": 41972 + }, + { + "epoch": 12.96, + "learning_rate": 5.820596996284436e-06, + "loss": 0.0072, + "step": 41973 + }, + { + "epoch": 12.96, + "learning_rate": 5.820142656860265e-06, + "loss": 0.008, + "step": 41974 + }, + { + "epoch": 12.96, + "learning_rate": 5.8196883278906755e-06, + "loss": 0.008, + "step": 41975 + }, + { + "epoch": 12.96, + "learning_rate": 5.8192340093768095e-06, + "loss": 0.0067, + "step": 41976 + }, + { + "epoch": 12.96, + "learning_rate": 5.818779701319806e-06, + "loss": 0.0064, + "step": 41977 + }, + { + "epoch": 12.96, + "learning_rate": 5.818325403720795e-06, + "loss": 0.0087, + "step": 41978 + }, + { + "epoch": 12.96, + "learning_rate": 5.817871116580912e-06, + "loss": 0.0073, + "step": 41979 + }, + { + "epoch": 12.96, + "learning_rate": 5.8174168399013e-06, + "loss": 0.0082, + "step": 41980 + }, + { + "epoch": 12.96, + "learning_rate": 5.816962573683087e-06, + "loss": 0.007, + "step": 41981 + }, + { + "epoch": 12.96, + "learning_rate": 5.816508317927414e-06, + "loss": 0.006, + "step": 41982 + }, + { + "epoch": 12.97, + "learning_rate": 5.816054072635422e-06, + "loss": 0.0067, + "step": 41983 + }, + { + "epoch": 12.97, + "learning_rate": 5.8155998378082405e-06, + "loss": 0.0079, + "step": 41984 + }, + { + "epoch": 12.97, + "learning_rate": 5.815145613447002e-06, + "loss": 0.0086, + "step": 41985 + }, + { + "epoch": 12.97, + "learning_rate": 5.814691399552853e-06, + "loss": 0.0082, + "step": 41986 + }, + { + "epoch": 12.97, + "learning_rate": 5.814237196126919e-06, + "loss": 0.0072, + "step": 41987 + }, + { + "epoch": 12.97, + "learning_rate": 5.813783003170347e-06, + "loss": 0.0078, + "step": 41988 + }, + { + "epoch": 12.97, + "learning_rate": 5.813328820684266e-06, + "loss": 0.0082, + "step": 41989 + }, + { + "epoch": 12.97, + "learning_rate": 5.812874648669809e-06, + "loss": 0.0064, + "step": 41990 + }, + { + "epoch": 12.97, + "learning_rate": 5.812420487128118e-06, + "loss": 0.0064, + "step": 41991 + }, + { + "epoch": 12.97, + "learning_rate": 5.8119663360603285e-06, + "loss": 0.0069, + "step": 41992 + }, + { + "epoch": 12.97, + "learning_rate": 5.811512195467572e-06, + "loss": 0.0078, + "step": 41993 + }, + { + "epoch": 12.97, + "learning_rate": 5.811058065350993e-06, + "loss": 0.0074, + "step": 41994 + }, + { + "epoch": 12.97, + "learning_rate": 5.81060394571172e-06, + "loss": 0.0063, + "step": 41995 + }, + { + "epoch": 12.97, + "learning_rate": 5.810149836550887e-06, + "loss": 0.0069, + "step": 41996 + }, + { + "epoch": 12.97, + "learning_rate": 5.809695737869634e-06, + "loss": 0.0072, + "step": 41997 + }, + { + "epoch": 12.97, + "learning_rate": 5.809241649669099e-06, + "loss": 0.0085, + "step": 41998 + }, + { + "epoch": 12.97, + "learning_rate": 5.808787571950416e-06, + "loss": 0.0067, + "step": 41999 + }, + { + "epoch": 12.97, + "learning_rate": 5.808333504714716e-06, + "loss": 0.0082, + "step": 42000 + }, + { + "epoch": 12.97, + "learning_rate": 5.807879447963143e-06, + "loss": 0.0081, + "step": 42001 + }, + { + "epoch": 12.97, + "learning_rate": 5.8074254016968225e-06, + "loss": 0.0073, + "step": 42002 + }, + { + "epoch": 12.97, + "learning_rate": 5.806971365916896e-06, + "loss": 0.0067, + "step": 42003 + }, + { + "epoch": 12.97, + "learning_rate": 5.806517340624504e-06, + "loss": 0.0073, + "step": 42004 + }, + { + "epoch": 12.97, + "learning_rate": 5.806063325820776e-06, + "loss": 0.0087, + "step": 42005 + }, + { + "epoch": 12.97, + "learning_rate": 5.805609321506844e-06, + "loss": 0.006, + "step": 42006 + }, + { + "epoch": 12.97, + "learning_rate": 5.805155327683849e-06, + "loss": 0.0071, + "step": 42007 + }, + { + "epoch": 12.97, + "learning_rate": 5.80470134435293e-06, + "loss": 0.0059, + "step": 42008 + }, + { + "epoch": 12.97, + "learning_rate": 5.804247371515217e-06, + "loss": 0.0088, + "step": 42009 + }, + { + "epoch": 12.97, + "learning_rate": 5.803793409171843e-06, + "loss": 0.0066, + "step": 42010 + }, + { + "epoch": 12.97, + "learning_rate": 5.8033394573239506e-06, + "loss": 0.0075, + "step": 42011 + }, + { + "epoch": 12.97, + "learning_rate": 5.802885515972669e-06, + "loss": 0.0073, + "step": 42012 + }, + { + "epoch": 12.97, + "learning_rate": 5.802431585119135e-06, + "loss": 0.0076, + "step": 42013 + }, + { + "epoch": 12.97, + "learning_rate": 5.8019776647644896e-06, + "loss": 0.0077, + "step": 42014 + }, + { + "epoch": 12.98, + "learning_rate": 5.801523754909863e-06, + "loss": 0.0079, + "step": 42015 + }, + { + "epoch": 12.98, + "learning_rate": 5.8010698555563895e-06, + "loss": 0.0061, + "step": 42016 + }, + { + "epoch": 12.98, + "learning_rate": 5.800615966705208e-06, + "loss": 0.0076, + "step": 42017 + }, + { + "epoch": 12.98, + "learning_rate": 5.800162088357448e-06, + "loss": 0.0061, + "step": 42018 + }, + { + "epoch": 12.98, + "learning_rate": 5.799708220514253e-06, + "loss": 0.0063, + "step": 42019 + }, + { + "epoch": 12.98, + "learning_rate": 5.799254363176754e-06, + "loss": 0.0065, + "step": 42020 + }, + { + "epoch": 12.98, + "learning_rate": 5.798800516346082e-06, + "loss": 0.0076, + "step": 42021 + }, + { + "epoch": 12.98, + "learning_rate": 5.798346680023376e-06, + "loss": 0.0075, + "step": 42022 + }, + { + "epoch": 12.98, + "learning_rate": 5.797892854209776e-06, + "loss": 0.0079, + "step": 42023 + }, + { + "epoch": 12.98, + "learning_rate": 5.7974390389064075e-06, + "loss": 0.0068, + "step": 42024 + }, + { + "epoch": 12.98, + "learning_rate": 5.796985234114414e-06, + "loss": 0.0061, + "step": 42025 + }, + { + "epoch": 12.98, + "learning_rate": 5.796531439834929e-06, + "loss": 0.0084, + "step": 42026 + }, + { + "epoch": 12.98, + "learning_rate": 5.796077656069079e-06, + "loss": 0.0062, + "step": 42027 + }, + { + "epoch": 12.98, + "learning_rate": 5.795623882818007e-06, + "loss": 0.0071, + "step": 42028 + }, + { + "epoch": 12.98, + "learning_rate": 5.795170120082852e-06, + "loss": 0.0072, + "step": 42029 + }, + { + "epoch": 12.98, + "learning_rate": 5.794716367864741e-06, + "loss": 0.0063, + "step": 42030 + }, + { + "epoch": 12.98, + "learning_rate": 5.794262626164808e-06, + "loss": 0.0067, + "step": 42031 + }, + { + "epoch": 12.98, + "learning_rate": 5.793808894984195e-06, + "loss": 0.0073, + "step": 42032 + }, + { + "epoch": 12.98, + "learning_rate": 5.793355174324029e-06, + "loss": 0.0073, + "step": 42033 + }, + { + "epoch": 12.98, + "learning_rate": 5.79290146418545e-06, + "loss": 0.0088, + "step": 42034 + }, + { + "epoch": 12.98, + "learning_rate": 5.792447764569596e-06, + "loss": 0.0066, + "step": 42035 + }, + { + "epoch": 12.98, + "learning_rate": 5.791994075477596e-06, + "loss": 0.0077, + "step": 42036 + }, + { + "epoch": 12.98, + "learning_rate": 5.791540396910582e-06, + "loss": 0.0075, + "step": 42037 + }, + { + "epoch": 12.98, + "learning_rate": 5.791086728869695e-06, + "loss": 0.0071, + "step": 42038 + }, + { + "epoch": 12.98, + "learning_rate": 5.790633071356071e-06, + "loss": 0.0072, + "step": 42039 + }, + { + "epoch": 12.98, + "learning_rate": 5.790179424370841e-06, + "loss": 0.0081, + "step": 42040 + }, + { + "epoch": 12.98, + "learning_rate": 5.789725787915137e-06, + "loss": 0.0069, + "step": 42041 + }, + { + "epoch": 12.98, + "learning_rate": 5.789272161990099e-06, + "loss": 0.0091, + "step": 42042 + }, + { + "epoch": 12.98, + "learning_rate": 5.788818546596857e-06, + "loss": 0.0062, + "step": 42043 + }, + { + "epoch": 12.98, + "learning_rate": 5.788364941736547e-06, + "loss": 0.0071, + "step": 42044 + }, + { + "epoch": 12.98, + "learning_rate": 5.7879113474103086e-06, + "loss": 0.007, + "step": 42045 + }, + { + "epoch": 12.98, + "learning_rate": 5.787457763619273e-06, + "loss": 0.0064, + "step": 42046 + }, + { + "epoch": 12.98, + "learning_rate": 5.787004190364569e-06, + "loss": 0.0067, + "step": 42047 + }, + { + "epoch": 12.99, + "learning_rate": 5.78655062764734e-06, + "loss": 0.0077, + "step": 42048 + }, + { + "epoch": 12.99, + "learning_rate": 5.7860970754687125e-06, + "loss": 0.0074, + "step": 42049 + }, + { + "epoch": 12.99, + "learning_rate": 5.7856435338298276e-06, + "loss": 0.0091, + "step": 42050 + }, + { + "epoch": 12.99, + "learning_rate": 5.785190002731819e-06, + "loss": 0.0074, + "step": 42051 + }, + { + "epoch": 12.99, + "learning_rate": 5.784736482175813e-06, + "loss": 0.0078, + "step": 42052 + }, + { + "epoch": 12.99, + "learning_rate": 5.784282972162951e-06, + "loss": 0.0082, + "step": 42053 + }, + { + "epoch": 12.99, + "learning_rate": 5.78382947269437e-06, + "loss": 0.0073, + "step": 42054 + }, + { + "epoch": 12.99, + "learning_rate": 5.783375983771197e-06, + "loss": 0.0083, + "step": 42055 + }, + { + "epoch": 12.99, + "learning_rate": 5.7829225053945724e-06, + "loss": 0.0065, + "step": 42056 + }, + { + "epoch": 12.99, + "learning_rate": 5.782469037565629e-06, + "loss": 0.0082, + "step": 42057 + }, + { + "epoch": 12.99, + "learning_rate": 5.782015580285496e-06, + "loss": 0.0076, + "step": 42058 + }, + { + "epoch": 12.99, + "learning_rate": 5.781562133555309e-06, + "loss": 0.0062, + "step": 42059 + }, + { + "epoch": 12.99, + "learning_rate": 5.781108697376211e-06, + "loss": 0.0074, + "step": 42060 + }, + { + "epoch": 12.99, + "learning_rate": 5.780655271749329e-06, + "loss": 0.0065, + "step": 42061 + }, + { + "epoch": 12.99, + "learning_rate": 5.7802018566757935e-06, + "loss": 0.0068, + "step": 42062 + }, + { + "epoch": 12.99, + "learning_rate": 5.779748452156746e-06, + "loss": 0.0079, + "step": 42063 + }, + { + "epoch": 12.99, + "learning_rate": 5.779295058193315e-06, + "loss": 0.0064, + "step": 42064 + }, + { + "epoch": 12.99, + "learning_rate": 5.778841674786635e-06, + "loss": 0.0062, + "step": 42065 + }, + { + "epoch": 12.99, + "learning_rate": 5.778388301937852e-06, + "loss": 0.007, + "step": 42066 + }, + { + "epoch": 12.99, + "learning_rate": 5.77793493964808e-06, + "loss": 0.0078, + "step": 42067 + }, + { + "epoch": 12.99, + "learning_rate": 5.777481587918463e-06, + "loss": 0.007, + "step": 42068 + }, + { + "epoch": 12.99, + "learning_rate": 5.77702824675014e-06, + "loss": 0.0062, + "step": 42069 + }, + { + "epoch": 12.99, + "learning_rate": 5.776574916144234e-06, + "loss": 0.0081, + "step": 42070 + }, + { + "epoch": 12.99, + "learning_rate": 5.776121596101889e-06, + "loss": 0.0066, + "step": 42071 + }, + { + "epoch": 12.99, + "learning_rate": 5.775668286624231e-06, + "loss": 0.0078, + "step": 42072 + }, + { + "epoch": 12.99, + "learning_rate": 5.775214987712401e-06, + "loss": 0.0068, + "step": 42073 + }, + { + "epoch": 12.99, + "learning_rate": 5.774761699367524e-06, + "loss": 0.0072, + "step": 42074 + }, + { + "epoch": 12.99, + "learning_rate": 5.774308421590739e-06, + "loss": 0.0071, + "step": 42075 + }, + { + "epoch": 12.99, + "learning_rate": 5.773855154383188e-06, + "loss": 0.0062, + "step": 42076 + }, + { + "epoch": 12.99, + "learning_rate": 5.773401897745987e-06, + "loss": 0.0067, + "step": 42077 + }, + { + "epoch": 12.99, + "learning_rate": 5.772948651680279e-06, + "loss": 0.0068, + "step": 42078 + }, + { + "epoch": 12.99, + "learning_rate": 5.772495416187202e-06, + "loss": 0.0073, + "step": 42079 + }, + { + "epoch": 13.0, + "learning_rate": 5.7720421912678795e-06, + "loss": 0.0083, + "step": 42080 + }, + { + "epoch": 13.0, + "learning_rate": 5.771588976923457e-06, + "loss": 0.0084, + "step": 42081 + }, + { + "epoch": 13.0, + "learning_rate": 5.7711357731550584e-06, + "loss": 0.0071, + "step": 42082 + }, + { + "epoch": 13.0, + "learning_rate": 5.77068257996382e-06, + "loss": 0.0093, + "step": 42083 + }, + { + "epoch": 13.0, + "learning_rate": 5.770229397350874e-06, + "loss": 0.0078, + "step": 42084 + }, + { + "epoch": 13.0, + "learning_rate": 5.76977622531736e-06, + "loss": 0.0061, + "step": 42085 + }, + { + "epoch": 13.0, + "learning_rate": 5.769323063864407e-06, + "loss": 0.0066, + "step": 42086 + }, + { + "epoch": 13.0, + "learning_rate": 5.7688699129931445e-06, + "loss": 0.0081, + "step": 42087 + }, + { + "epoch": 13.0, + "learning_rate": 5.7684167727047144e-06, + "loss": 0.0066, + "step": 42088 + }, + { + "epoch": 13.0, + "learning_rate": 5.767963643000243e-06, + "loss": 0.0075, + "step": 42089 + }, + { + "epoch": 13.0, + "learning_rate": 5.767510523880865e-06, + "loss": 0.0081, + "step": 42090 + }, + { + "epoch": 13.0, + "learning_rate": 5.7670574153477185e-06, + "loss": 0.0081, + "step": 42091 + }, + { + "epoch": 13.0, + "learning_rate": 5.766604317401935e-06, + "loss": 0.01, + "step": 42092 + }, + { + "epoch": 13.0, + "learning_rate": 5.766151230044641e-06, + "loss": 0.0083, + "step": 42093 + }, + { + "epoch": 13.0, + "learning_rate": 5.76569815327698e-06, + "loss": 0.0069, + "step": 42094 + }, + { + "epoch": 13.0, + "learning_rate": 5.765245087100075e-06, + "loss": 0.0069, + "step": 42095 + }, + { + "epoch": 13.0, + "learning_rate": 5.7647920315150696e-06, + "loss": 0.0078, + "step": 42096 + }, + { + "epoch": 13.0, + "learning_rate": 5.764338986523092e-06, + "loss": 0.0038, + "step": 42097 + }, + { + "epoch": 13.0, + "learning_rate": 5.76388595212527e-06, + "loss": 0.0043, + "step": 42098 + }, + { + "epoch": 13.0, + "learning_rate": 5.763432928322743e-06, + "loss": 0.0037, + "step": 42099 + }, + { + "epoch": 13.0, + "learning_rate": 5.7629799151166456e-06, + "loss": 0.004, + "step": 42100 + }, + { + "epoch": 13.0, + "learning_rate": 5.762526912508105e-06, + "loss": 0.0037, + "step": 42101 + }, + { + "epoch": 13.0, + "learning_rate": 5.762073920498261e-06, + "loss": 0.0042, + "step": 42102 + }, + { + "epoch": 13.0, + "learning_rate": 5.761620939088244e-06, + "loss": 0.0043, + "step": 42103 + }, + { + "epoch": 13.0, + "learning_rate": 5.761167968279181e-06, + "loss": 0.0031, + "step": 42104 + }, + { + "epoch": 13.0, + "learning_rate": 5.76071500807221e-06, + "loss": 0.0052, + "step": 42105 + }, + { + "epoch": 13.0, + "learning_rate": 5.7602620584684685e-06, + "loss": 0.0037, + "step": 42106 + }, + { + "epoch": 13.0, + "learning_rate": 5.759809119469085e-06, + "loss": 0.0038, + "step": 42107 + }, + { + "epoch": 13.0, + "learning_rate": 5.759356191075188e-06, + "loss": 0.0049, + "step": 42108 + }, + { + "epoch": 13.0, + "learning_rate": 5.7589032732879145e-06, + "loss": 0.0043, + "step": 42109 + }, + { + "epoch": 13.0, + "learning_rate": 5.758450366108402e-06, + "loss": 0.0044, + "step": 42110 + }, + { + "epoch": 13.0, + "learning_rate": 5.757997469537775e-06, + "loss": 0.0044, + "step": 42111 + }, + { + "epoch": 13.0, + "learning_rate": 5.7575445835771725e-06, + "loss": 0.0043, + "step": 42112 + }, + { + "epoch": 13.01, + "learning_rate": 5.757091708227727e-06, + "loss": 0.005, + "step": 42113 + }, + { + "epoch": 13.01, + "learning_rate": 5.756638843490563e-06, + "loss": 0.004, + "step": 42114 + }, + { + "epoch": 13.01, + "learning_rate": 5.75618598936682e-06, + "loss": 0.0043, + "step": 42115 + }, + { + "epoch": 13.01, + "learning_rate": 5.755733145857634e-06, + "loss": 0.0053, + "step": 42116 + }, + { + "epoch": 13.01, + "learning_rate": 5.755280312964133e-06, + "loss": 0.0035, + "step": 42117 + }, + { + "epoch": 13.01, + "learning_rate": 5.754827490687446e-06, + "loss": 0.0041, + "step": 42118 + }, + { + "epoch": 13.01, + "learning_rate": 5.754374679028713e-06, + "loss": 0.0049, + "step": 42119 + }, + { + "epoch": 13.01, + "learning_rate": 5.7539218779890615e-06, + "loss": 0.0042, + "step": 42120 + }, + { + "epoch": 13.01, + "learning_rate": 5.753469087569626e-06, + "loss": 0.0041, + "step": 42121 + }, + { + "epoch": 13.01, + "learning_rate": 5.753016307771539e-06, + "loss": 0.0041, + "step": 42122 + }, + { + "epoch": 13.01, + "learning_rate": 5.752563538595936e-06, + "loss": 0.0036, + "step": 42123 + }, + { + "epoch": 13.01, + "learning_rate": 5.7521107800439425e-06, + "loss": 0.0037, + "step": 42124 + }, + { + "epoch": 13.01, + "learning_rate": 5.751658032116697e-06, + "loss": 0.0046, + "step": 42125 + }, + { + "epoch": 13.01, + "learning_rate": 5.751205294815328e-06, + "loss": 0.0042, + "step": 42126 + }, + { + "epoch": 13.01, + "learning_rate": 5.750752568140971e-06, + "loss": 0.0047, + "step": 42127 + }, + { + "epoch": 13.01, + "learning_rate": 5.750299852094757e-06, + "loss": 0.0037, + "step": 42128 + }, + { + "epoch": 13.01, + "learning_rate": 5.749847146677816e-06, + "loss": 0.0033, + "step": 42129 + }, + { + "epoch": 13.01, + "learning_rate": 5.749394451891282e-06, + "loss": 0.0031, + "step": 42130 + }, + { + "epoch": 13.01, + "learning_rate": 5.748941767736289e-06, + "loss": 0.0059, + "step": 42131 + }, + { + "epoch": 13.01, + "learning_rate": 5.748489094213967e-06, + "loss": 0.0036, + "step": 42132 + }, + { + "epoch": 13.01, + "learning_rate": 5.7480364313254525e-06, + "loss": 0.0036, + "step": 42133 + }, + { + "epoch": 13.01, + "learning_rate": 5.747583779071874e-06, + "loss": 0.0047, + "step": 42134 + }, + { + "epoch": 13.01, + "learning_rate": 5.7471311374543605e-06, + "loss": 0.0035, + "step": 42135 + }, + { + "epoch": 13.01, + "learning_rate": 5.746678506474047e-06, + "loss": 0.0036, + "step": 42136 + }, + { + "epoch": 13.01, + "learning_rate": 5.7462258861320705e-06, + "loss": 0.0041, + "step": 42137 + }, + { + "epoch": 13.01, + "learning_rate": 5.745773276429559e-06, + "loss": 0.0042, + "step": 42138 + }, + { + "epoch": 13.01, + "learning_rate": 5.7453206773676405e-06, + "loss": 0.0046, + "step": 42139 + }, + { + "epoch": 13.01, + "learning_rate": 5.744868088947451e-06, + "loss": 0.0033, + "step": 42140 + }, + { + "epoch": 13.01, + "learning_rate": 5.744415511170127e-06, + "loss": 0.0038, + "step": 42141 + }, + { + "epoch": 13.01, + "learning_rate": 5.7439629440367915e-06, + "loss": 0.0045, + "step": 42142 + }, + { + "epoch": 13.01, + "learning_rate": 5.743510387548585e-06, + "loss": 0.0055, + "step": 42143 + }, + { + "epoch": 13.01, + "learning_rate": 5.743057841706636e-06, + "loss": 0.0054, + "step": 42144 + }, + { + "epoch": 13.02, + "learning_rate": 5.74260530651207e-06, + "loss": 0.0042, + "step": 42145 + }, + { + "epoch": 13.02, + "learning_rate": 5.742152781966026e-06, + "loss": 0.0049, + "step": 42146 + }, + { + "epoch": 13.02, + "learning_rate": 5.741700268069639e-06, + "loss": 0.0049, + "step": 42147 + }, + { + "epoch": 13.02, + "learning_rate": 5.741247764824036e-06, + "loss": 0.0037, + "step": 42148 + }, + { + "epoch": 13.02, + "learning_rate": 5.740795272230344e-06, + "loss": 0.0043, + "step": 42149 + }, + { + "epoch": 13.02, + "learning_rate": 5.740342790289704e-06, + "loss": 0.0049, + "step": 42150 + }, + { + "epoch": 13.02, + "learning_rate": 5.739890319003241e-06, + "loss": 0.0035, + "step": 42151 + }, + { + "epoch": 13.02, + "learning_rate": 5.7394378583720876e-06, + "loss": 0.0041, + "step": 42152 + }, + { + "epoch": 13.02, + "learning_rate": 5.738985408397381e-06, + "loss": 0.004, + "step": 42153 + }, + { + "epoch": 13.02, + "learning_rate": 5.738532969080252e-06, + "loss": 0.0054, + "step": 42154 + }, + { + "epoch": 13.02, + "learning_rate": 5.738080540421822e-06, + "loss": 0.004, + "step": 42155 + }, + { + "epoch": 13.02, + "learning_rate": 5.737628122423235e-06, + "loss": 0.0036, + "step": 42156 + }, + { + "epoch": 13.02, + "learning_rate": 5.737175715085615e-06, + "loss": 0.0044, + "step": 42157 + }, + { + "epoch": 13.02, + "learning_rate": 5.7367233184100975e-06, + "loss": 0.0036, + "step": 42158 + }, + { + "epoch": 13.02, + "learning_rate": 5.736270932397814e-06, + "loss": 0.0048, + "step": 42159 + }, + { + "epoch": 13.02, + "learning_rate": 5.735818557049891e-06, + "loss": 0.0042, + "step": 42160 + }, + { + "epoch": 13.02, + "learning_rate": 5.735366192367462e-06, + "loss": 0.0039, + "step": 42161 + }, + { + "epoch": 13.02, + "learning_rate": 5.7349138383516656e-06, + "loss": 0.0045, + "step": 42162 + }, + { + "epoch": 13.02, + "learning_rate": 5.7344614950036224e-06, + "loss": 0.0037, + "step": 42163 + }, + { + "epoch": 13.02, + "learning_rate": 5.734009162324474e-06, + "loss": 0.0042, + "step": 42164 + }, + { + "epoch": 13.02, + "learning_rate": 5.733556840315347e-06, + "loss": 0.0038, + "step": 42165 + }, + { + "epoch": 13.02, + "learning_rate": 5.7331045289773665e-06, + "loss": 0.0034, + "step": 42166 + }, + { + "epoch": 13.02, + "learning_rate": 5.73265222831167e-06, + "loss": 0.0042, + "step": 42167 + }, + { + "epoch": 13.02, + "learning_rate": 5.732199938319394e-06, + "loss": 0.004, + "step": 42168 + }, + { + "epoch": 13.02, + "learning_rate": 5.731747659001664e-06, + "loss": 0.0037, + "step": 42169 + }, + { + "epoch": 13.02, + "learning_rate": 5.731295390359608e-06, + "loss": 0.0052, + "step": 42170 + }, + { + "epoch": 13.02, + "learning_rate": 5.7308431323943595e-06, + "loss": 0.0047, + "step": 42171 + }, + { + "epoch": 13.02, + "learning_rate": 5.730390885107056e-06, + "loss": 0.0036, + "step": 42172 + }, + { + "epoch": 13.02, + "learning_rate": 5.72993864849882e-06, + "loss": 0.0059, + "step": 42173 + }, + { + "epoch": 13.02, + "learning_rate": 5.729486422570789e-06, + "loss": 0.0037, + "step": 42174 + }, + { + "epoch": 13.02, + "learning_rate": 5.729034207324092e-06, + "loss": 0.0047, + "step": 42175 + }, + { + "epoch": 13.02, + "learning_rate": 5.728582002759855e-06, + "loss": 0.0051, + "step": 42176 + }, + { + "epoch": 13.03, + "learning_rate": 5.728129808879215e-06, + "loss": 0.0041, + "step": 42177 + }, + { + "epoch": 13.03, + "learning_rate": 5.727677625683303e-06, + "loss": 0.0056, + "step": 42178 + }, + { + "epoch": 13.03, + "learning_rate": 5.727225453173251e-06, + "loss": 0.0043, + "step": 42179 + }, + { + "epoch": 13.03, + "learning_rate": 5.726773291350182e-06, + "loss": 0.005, + "step": 42180 + }, + { + "epoch": 13.03, + "learning_rate": 5.726321140215237e-06, + "loss": 0.0033, + "step": 42181 + }, + { + "epoch": 13.03, + "learning_rate": 5.7258689997695375e-06, + "loss": 0.0037, + "step": 42182 + }, + { + "epoch": 13.03, + "learning_rate": 5.72541687001422e-06, + "loss": 0.0041, + "step": 42183 + }, + { + "epoch": 13.03, + "learning_rate": 5.7249647509504214e-06, + "loss": 0.0047, + "step": 42184 + }, + { + "epoch": 13.03, + "learning_rate": 5.724512642579259e-06, + "loss": 0.0035, + "step": 42185 + }, + { + "epoch": 13.03, + "learning_rate": 5.724060544901869e-06, + "loss": 0.0043, + "step": 42186 + }, + { + "epoch": 13.03, + "learning_rate": 5.723608457919389e-06, + "loss": 0.0054, + "step": 42187 + }, + { + "epoch": 13.03, + "learning_rate": 5.723156381632939e-06, + "loss": 0.0044, + "step": 42188 + }, + { + "epoch": 13.03, + "learning_rate": 5.722704316043659e-06, + "loss": 0.0036, + "step": 42189 + }, + { + "epoch": 13.03, + "learning_rate": 5.722252261152677e-06, + "loss": 0.0045, + "step": 42190 + }, + { + "epoch": 13.03, + "learning_rate": 5.721800216961117e-06, + "loss": 0.0045, + "step": 42191 + }, + { + "epoch": 13.03, + "learning_rate": 5.721348183470115e-06, + "loss": 0.0048, + "step": 42192 + }, + { + "epoch": 13.03, + "learning_rate": 5.720896160680806e-06, + "loss": 0.0054, + "step": 42193 + }, + { + "epoch": 13.03, + "learning_rate": 5.7204441485943155e-06, + "loss": 0.0049, + "step": 42194 + }, + { + "epoch": 13.03, + "learning_rate": 5.719992147211772e-06, + "loss": 0.0042, + "step": 42195 + }, + { + "epoch": 13.03, + "learning_rate": 5.719540156534311e-06, + "loss": 0.0044, + "step": 42196 + }, + { + "epoch": 13.03, + "learning_rate": 5.719088176563059e-06, + "loss": 0.0047, + "step": 42197 + }, + { + "epoch": 13.03, + "learning_rate": 5.718636207299146e-06, + "loss": 0.004, + "step": 42198 + }, + { + "epoch": 13.03, + "learning_rate": 5.71818424874371e-06, + "loss": 0.004, + "step": 42199 + }, + { + "epoch": 13.03, + "learning_rate": 5.7177323008978754e-06, + "loss": 0.0044, + "step": 42200 + }, + { + "epoch": 13.03, + "learning_rate": 5.7172803637627704e-06, + "loss": 0.0046, + "step": 42201 + }, + { + "epoch": 13.03, + "learning_rate": 5.716828437339528e-06, + "loss": 0.0036, + "step": 42202 + }, + { + "epoch": 13.03, + "learning_rate": 5.716376521629282e-06, + "loss": 0.0031, + "step": 42203 + }, + { + "epoch": 13.03, + "learning_rate": 5.715924616633157e-06, + "loss": 0.0033, + "step": 42204 + }, + { + "epoch": 13.03, + "learning_rate": 5.715472722352289e-06, + "loss": 0.0051, + "step": 42205 + }, + { + "epoch": 13.03, + "learning_rate": 5.715020838787805e-06, + "loss": 0.0033, + "step": 42206 + }, + { + "epoch": 13.03, + "learning_rate": 5.714568965940832e-06, + "loss": 0.0042, + "step": 42207 + }, + { + "epoch": 13.03, + "learning_rate": 5.714117103812503e-06, + "loss": 0.0051, + "step": 42208 + }, + { + "epoch": 13.03, + "learning_rate": 5.713665252403952e-06, + "loss": 0.0049, + "step": 42209 + }, + { + "epoch": 13.04, + "learning_rate": 5.713213411716309e-06, + "loss": 0.0048, + "step": 42210 + }, + { + "epoch": 13.04, + "learning_rate": 5.712761581750694e-06, + "loss": 0.0043, + "step": 42211 + }, + { + "epoch": 13.04, + "learning_rate": 5.71230976250825e-06, + "loss": 0.0039, + "step": 42212 + }, + { + "epoch": 13.04, + "learning_rate": 5.7118579539900965e-06, + "loss": 0.0047, + "step": 42213 + }, + { + "epoch": 13.04, + "learning_rate": 5.71140615619737e-06, + "loss": 0.0053, + "step": 42214 + }, + { + "epoch": 13.04, + "learning_rate": 5.710954369131205e-06, + "loss": 0.005, + "step": 42215 + }, + { + "epoch": 13.04, + "learning_rate": 5.710502592792717e-06, + "loss": 0.0045, + "step": 42216 + }, + { + "epoch": 13.04, + "learning_rate": 5.7100508271830466e-06, + "loss": 0.0035, + "step": 42217 + }, + { + "epoch": 13.04, + "learning_rate": 5.7095990723033246e-06, + "loss": 0.0044, + "step": 42218 + }, + { + "epoch": 13.04, + "learning_rate": 5.709147328154673e-06, + "loss": 0.0037, + "step": 42219 + }, + { + "epoch": 13.04, + "learning_rate": 5.708695594738231e-06, + "loss": 0.0048, + "step": 42220 + }, + { + "epoch": 13.04, + "learning_rate": 5.708243872055124e-06, + "loss": 0.0053, + "step": 42221 + }, + { + "epoch": 13.04, + "learning_rate": 5.707792160106478e-06, + "loss": 0.004, + "step": 42222 + }, + { + "epoch": 13.04, + "learning_rate": 5.707340458893427e-06, + "loss": 0.0041, + "step": 42223 + }, + { + "epoch": 13.04, + "learning_rate": 5.706888768417103e-06, + "loss": 0.004, + "step": 42224 + }, + { + "epoch": 13.04, + "learning_rate": 5.7064370886786335e-06, + "loss": 0.0031, + "step": 42225 + }, + { + "epoch": 13.04, + "learning_rate": 5.705985419679145e-06, + "loss": 0.0044, + "step": 42226 + }, + { + "epoch": 13.04, + "learning_rate": 5.705533761419775e-06, + "loss": 0.0051, + "step": 42227 + }, + { + "epoch": 13.04, + "learning_rate": 5.7050821139016425e-06, + "loss": 0.0033, + "step": 42228 + }, + { + "epoch": 13.04, + "learning_rate": 5.704630477125883e-06, + "loss": 0.004, + "step": 42229 + }, + { + "epoch": 13.04, + "learning_rate": 5.704178851093631e-06, + "loss": 0.0035, + "step": 42230 + }, + { + "epoch": 13.04, + "learning_rate": 5.703727235806011e-06, + "loss": 0.0051, + "step": 42231 + }, + { + "epoch": 13.04, + "learning_rate": 5.703275631264149e-06, + "loss": 0.0042, + "step": 42232 + }, + { + "epoch": 13.04, + "learning_rate": 5.702824037469181e-06, + "loss": 0.0042, + "step": 42233 + }, + { + "epoch": 13.04, + "learning_rate": 5.702372454422232e-06, + "loss": 0.0044, + "step": 42234 + }, + { + "epoch": 13.04, + "learning_rate": 5.701920882124436e-06, + "loss": 0.0068, + "step": 42235 + }, + { + "epoch": 13.04, + "learning_rate": 5.701469320576916e-06, + "loss": 0.0047, + "step": 42236 + }, + { + "epoch": 13.04, + "learning_rate": 5.701017769780807e-06, + "loss": 0.0054, + "step": 42237 + }, + { + "epoch": 13.04, + "learning_rate": 5.700566229737237e-06, + "loss": 0.0035, + "step": 42238 + }, + { + "epoch": 13.04, + "learning_rate": 5.700114700447332e-06, + "loss": 0.0055, + "step": 42239 + }, + { + "epoch": 13.04, + "learning_rate": 5.699663181912229e-06, + "loss": 0.0038, + "step": 42240 + }, + { + "epoch": 13.04, + "learning_rate": 5.699211674133054e-06, + "loss": 0.0044, + "step": 42241 + }, + { + "epoch": 13.05, + "learning_rate": 5.698760177110929e-06, + "loss": 0.0038, + "step": 42242 + }, + { + "epoch": 13.05, + "learning_rate": 5.698308690846994e-06, + "loss": 0.0047, + "step": 42243 + }, + { + "epoch": 13.05, + "learning_rate": 5.69785721534237e-06, + "loss": 0.004, + "step": 42244 + }, + { + "epoch": 13.05, + "learning_rate": 5.697405750598194e-06, + "loss": 0.0043, + "step": 42245 + }, + { + "epoch": 13.05, + "learning_rate": 5.696954296615591e-06, + "loss": 0.0042, + "step": 42246 + }, + { + "epoch": 13.05, + "learning_rate": 5.696502853395684e-06, + "loss": 0.0047, + "step": 42247 + }, + { + "epoch": 13.05, + "learning_rate": 5.696051420939611e-06, + "loss": 0.0037, + "step": 42248 + }, + { + "epoch": 13.05, + "learning_rate": 5.6955999992485015e-06, + "loss": 0.0033, + "step": 42249 + }, + { + "epoch": 13.05, + "learning_rate": 5.695148588323477e-06, + "loss": 0.0044, + "step": 42250 + }, + { + "epoch": 13.05, + "learning_rate": 5.694697188165676e-06, + "loss": 0.0053, + "step": 42251 + }, + { + "epoch": 13.05, + "learning_rate": 5.694245798776221e-06, + "loss": 0.004, + "step": 42252 + }, + { + "epoch": 13.05, + "learning_rate": 5.69379442015624e-06, + "loss": 0.005, + "step": 42253 + }, + { + "epoch": 13.05, + "learning_rate": 5.693343052306863e-06, + "loss": 0.0049, + "step": 42254 + }, + { + "epoch": 13.05, + "learning_rate": 5.692891695229226e-06, + "loss": 0.0039, + "step": 42255 + }, + { + "epoch": 13.05, + "learning_rate": 5.692440348924453e-06, + "loss": 0.0039, + "step": 42256 + }, + { + "epoch": 13.05, + "learning_rate": 5.691989013393666e-06, + "loss": 0.0044, + "step": 42257 + }, + { + "epoch": 13.05, + "learning_rate": 5.691537688638007e-06, + "loss": 0.0042, + "step": 42258 + }, + { + "epoch": 13.05, + "learning_rate": 5.691086374658592e-06, + "loss": 0.0041, + "step": 42259 + }, + { + "epoch": 13.05, + "learning_rate": 5.690635071456556e-06, + "loss": 0.0046, + "step": 42260 + }, + { + "epoch": 13.05, + "learning_rate": 5.690183779033032e-06, + "loss": 0.0048, + "step": 42261 + }, + { + "epoch": 13.05, + "learning_rate": 5.689732497389144e-06, + "loss": 0.0037, + "step": 42262 + }, + { + "epoch": 13.05, + "learning_rate": 5.689281226526018e-06, + "loss": 0.0039, + "step": 42263 + }, + { + "epoch": 13.05, + "learning_rate": 5.68882996644479e-06, + "loss": 0.005, + "step": 42264 + }, + { + "epoch": 13.05, + "learning_rate": 5.688378717146581e-06, + "loss": 0.0045, + "step": 42265 + }, + { + "epoch": 13.05, + "learning_rate": 5.687927478632525e-06, + "loss": 0.0044, + "step": 42266 + }, + { + "epoch": 13.05, + "learning_rate": 5.687476250903747e-06, + "loss": 0.0045, + "step": 42267 + }, + { + "epoch": 13.05, + "learning_rate": 5.687025033961381e-06, + "loss": 0.0038, + "step": 42268 + }, + { + "epoch": 13.05, + "learning_rate": 5.686573827806547e-06, + "loss": 0.0042, + "step": 42269 + }, + { + "epoch": 13.05, + "learning_rate": 5.68612263244038e-06, + "loss": 0.0042, + "step": 42270 + }, + { + "epoch": 13.05, + "learning_rate": 5.68567144786401e-06, + "loss": 0.0048, + "step": 42271 + }, + { + "epoch": 13.05, + "learning_rate": 5.685220274078562e-06, + "loss": 0.0034, + "step": 42272 + }, + { + "epoch": 13.05, + "learning_rate": 5.684769111085162e-06, + "loss": 0.0043, + "step": 42273 + }, + { + "epoch": 13.06, + "learning_rate": 5.684317958884946e-06, + "loss": 0.0043, + "step": 42274 + }, + { + "epoch": 13.06, + "learning_rate": 5.683866817479034e-06, + "loss": 0.0039, + "step": 42275 + }, + { + "epoch": 13.06, + "learning_rate": 5.683415686868562e-06, + "loss": 0.0037, + "step": 42276 + }, + { + "epoch": 13.06, + "learning_rate": 5.682964567054654e-06, + "loss": 0.0045, + "step": 42277 + }, + { + "epoch": 13.06, + "learning_rate": 5.6825134580384355e-06, + "loss": 0.0049, + "step": 42278 + }, + { + "epoch": 13.06, + "learning_rate": 5.682062359821039e-06, + "loss": 0.0042, + "step": 42279 + }, + { + "epoch": 13.06, + "learning_rate": 5.6816112724035944e-06, + "loss": 0.0032, + "step": 42280 + }, + { + "epoch": 13.06, + "learning_rate": 5.681160195787225e-06, + "loss": 0.0051, + "step": 42281 + }, + { + "epoch": 13.06, + "learning_rate": 5.680709129973066e-06, + "loss": 0.0041, + "step": 42282 + }, + { + "epoch": 13.06, + "learning_rate": 5.680258074962239e-06, + "loss": 0.0036, + "step": 42283 + }, + { + "epoch": 13.06, + "learning_rate": 5.679807030755872e-06, + "loss": 0.0041, + "step": 42284 + }, + { + "epoch": 13.06, + "learning_rate": 5.679355997355096e-06, + "loss": 0.0035, + "step": 42285 + }, + { + "epoch": 13.06, + "learning_rate": 5.678904974761042e-06, + "loss": 0.0044, + "step": 42286 + }, + { + "epoch": 13.06, + "learning_rate": 5.6784539629748346e-06, + "loss": 0.0028, + "step": 42287 + }, + { + "epoch": 13.06, + "learning_rate": 5.678002961997599e-06, + "loss": 0.0038, + "step": 42288 + }, + { + "epoch": 13.06, + "learning_rate": 5.677551971830468e-06, + "loss": 0.005, + "step": 42289 + }, + { + "epoch": 13.06, + "learning_rate": 5.677100992474567e-06, + "loss": 0.0041, + "step": 42290 + }, + { + "epoch": 13.06, + "learning_rate": 5.676650023931023e-06, + "loss": 0.0039, + "step": 42291 + }, + { + "epoch": 13.06, + "learning_rate": 5.67619906620097e-06, + "loss": 0.0034, + "step": 42292 + }, + { + "epoch": 13.06, + "learning_rate": 5.675748119285531e-06, + "loss": 0.0039, + "step": 42293 + }, + { + "epoch": 13.06, + "learning_rate": 5.675297183185832e-06, + "loss": 0.0037, + "step": 42294 + }, + { + "epoch": 13.06, + "learning_rate": 5.674846257903008e-06, + "loss": 0.0034, + "step": 42295 + }, + { + "epoch": 13.06, + "learning_rate": 5.674395343438177e-06, + "loss": 0.0044, + "step": 42296 + }, + { + "epoch": 13.06, + "learning_rate": 5.673944439792477e-06, + "loss": 0.0039, + "step": 42297 + }, + { + "epoch": 13.06, + "learning_rate": 5.6734935469670305e-06, + "loss": 0.0041, + "step": 42298 + }, + { + "epoch": 13.06, + "learning_rate": 5.6730426649629624e-06, + "loss": 0.0043, + "step": 42299 + }, + { + "epoch": 13.06, + "learning_rate": 5.672591793781404e-06, + "loss": 0.0046, + "step": 42300 + }, + { + "epoch": 13.06, + "learning_rate": 5.67214093342348e-06, + "loss": 0.0056, + "step": 42301 + }, + { + "epoch": 13.06, + "learning_rate": 5.671690083890327e-06, + "loss": 0.0039, + "step": 42302 + }, + { + "epoch": 13.06, + "learning_rate": 5.671239245183067e-06, + "loss": 0.0048, + "step": 42303 + }, + { + "epoch": 13.06, + "learning_rate": 5.6707884173028225e-06, + "loss": 0.0038, + "step": 42304 + }, + { + "epoch": 13.06, + "learning_rate": 5.670337600250731e-06, + "loss": 0.0051, + "step": 42305 + }, + { + "epoch": 13.06, + "learning_rate": 5.669886794027909e-06, + "loss": 0.0041, + "step": 42306 + }, + { + "epoch": 13.07, + "learning_rate": 5.669435998635496e-06, + "loss": 0.0048, + "step": 42307 + }, + { + "epoch": 13.07, + "learning_rate": 5.66898521407461e-06, + "loss": 0.0045, + "step": 42308 + }, + { + "epoch": 13.07, + "learning_rate": 5.66853444034638e-06, + "loss": 0.0043, + "step": 42309 + }, + { + "epoch": 13.07, + "learning_rate": 5.668083677451937e-06, + "loss": 0.0054, + "step": 42310 + }, + { + "epoch": 13.07, + "learning_rate": 5.667632925392408e-06, + "loss": 0.0039, + "step": 42311 + }, + { + "epoch": 13.07, + "learning_rate": 5.667182184168916e-06, + "loss": 0.0059, + "step": 42312 + }, + { + "epoch": 13.07, + "learning_rate": 5.6667314537825966e-06, + "loss": 0.0044, + "step": 42313 + }, + { + "epoch": 13.07, + "learning_rate": 5.6662807342345714e-06, + "loss": 0.0041, + "step": 42314 + }, + { + "epoch": 13.07, + "learning_rate": 5.665830025525964e-06, + "loss": 0.0038, + "step": 42315 + }, + { + "epoch": 13.07, + "learning_rate": 5.6653793276579075e-06, + "loss": 0.0039, + "step": 42316 + }, + { + "epoch": 13.07, + "learning_rate": 5.66492864063153e-06, + "loss": 0.0054, + "step": 42317 + }, + { + "epoch": 13.07, + "learning_rate": 5.664477964447958e-06, + "loss": 0.0051, + "step": 42318 + }, + { + "epoch": 13.07, + "learning_rate": 5.664027299108315e-06, + "loss": 0.0042, + "step": 42319 + }, + { + "epoch": 13.07, + "learning_rate": 5.663576644613733e-06, + "loss": 0.0039, + "step": 42320 + }, + { + "epoch": 13.07, + "learning_rate": 5.663126000965331e-06, + "loss": 0.0038, + "step": 42321 + }, + { + "epoch": 13.07, + "learning_rate": 5.662675368164244e-06, + "loss": 0.005, + "step": 42322 + }, + { + "epoch": 13.07, + "learning_rate": 5.6622247462116045e-06, + "loss": 0.004, + "step": 42323 + }, + { + "epoch": 13.07, + "learning_rate": 5.661774135108524e-06, + "loss": 0.0049, + "step": 42324 + }, + { + "epoch": 13.07, + "learning_rate": 5.661323534856138e-06, + "loss": 0.0039, + "step": 42325 + }, + { + "epoch": 13.07, + "learning_rate": 5.6608729454555766e-06, + "loss": 0.0048, + "step": 42326 + }, + { + "epoch": 13.07, + "learning_rate": 5.660422366907959e-06, + "loss": 0.0043, + "step": 42327 + }, + { + "epoch": 13.07, + "learning_rate": 5.659971799214421e-06, + "loss": 0.0036, + "step": 42328 + }, + { + "epoch": 13.07, + "learning_rate": 5.6595212423760856e-06, + "loss": 0.0032, + "step": 42329 + }, + { + "epoch": 13.07, + "learning_rate": 5.6590706963940755e-06, + "loss": 0.0037, + "step": 42330 + }, + { + "epoch": 13.07, + "learning_rate": 5.65862016126952e-06, + "loss": 0.004, + "step": 42331 + }, + { + "epoch": 13.07, + "learning_rate": 5.658169637003552e-06, + "loss": 0.0046, + "step": 42332 + }, + { + "epoch": 13.07, + "learning_rate": 5.657719123597294e-06, + "loss": 0.0041, + "step": 42333 + }, + { + "epoch": 13.07, + "learning_rate": 5.657268621051868e-06, + "loss": 0.0056, + "step": 42334 + }, + { + "epoch": 13.07, + "learning_rate": 5.656818129368404e-06, + "loss": 0.0042, + "step": 42335 + }, + { + "epoch": 13.07, + "learning_rate": 5.6563676485480355e-06, + "loss": 0.0039, + "step": 42336 + }, + { + "epoch": 13.07, + "learning_rate": 5.655917178591881e-06, + "loss": 0.004, + "step": 42337 + }, + { + "epoch": 13.07, + "learning_rate": 5.655466719501071e-06, + "loss": 0.003, + "step": 42338 + }, + { + "epoch": 13.08, + "learning_rate": 5.655016271276733e-06, + "loss": 0.0037, + "step": 42339 + }, + { + "epoch": 13.08, + "learning_rate": 5.654565833919987e-06, + "loss": 0.0037, + "step": 42340 + }, + { + "epoch": 13.08, + "learning_rate": 5.654115407431966e-06, + "loss": 0.0056, + "step": 42341 + }, + { + "epoch": 13.08, + "learning_rate": 5.6536649918137966e-06, + "loss": 0.0036, + "step": 42342 + }, + { + "epoch": 13.08, + "learning_rate": 5.653214587066606e-06, + "loss": 0.0041, + "step": 42343 + }, + { + "epoch": 13.08, + "learning_rate": 5.652764193191514e-06, + "loss": 0.0035, + "step": 42344 + }, + { + "epoch": 13.08, + "learning_rate": 5.652313810189653e-06, + "loss": 0.0045, + "step": 42345 + }, + { + "epoch": 13.08, + "learning_rate": 5.651863438062147e-06, + "loss": 0.004, + "step": 42346 + }, + { + "epoch": 13.08, + "learning_rate": 5.651413076810124e-06, + "loss": 0.0042, + "step": 42347 + }, + { + "epoch": 13.08, + "learning_rate": 5.650962726434712e-06, + "loss": 0.0041, + "step": 42348 + }, + { + "epoch": 13.08, + "learning_rate": 5.650512386937037e-06, + "loss": 0.0041, + "step": 42349 + }, + { + "epoch": 13.08, + "learning_rate": 5.650062058318219e-06, + "loss": 0.0047, + "step": 42350 + }, + { + "epoch": 13.08, + "learning_rate": 5.6496117405793925e-06, + "loss": 0.0049, + "step": 42351 + }, + { + "epoch": 13.08, + "learning_rate": 5.649161433721677e-06, + "loss": 0.0054, + "step": 42352 + }, + { + "epoch": 13.08, + "learning_rate": 5.648711137746208e-06, + "loss": 0.0043, + "step": 42353 + }, + { + "epoch": 13.08, + "learning_rate": 5.648260852654104e-06, + "loss": 0.005, + "step": 42354 + }, + { + "epoch": 13.08, + "learning_rate": 5.64781057844649e-06, + "loss": 0.0041, + "step": 42355 + }, + { + "epoch": 13.08, + "learning_rate": 5.647360315124495e-06, + "loss": 0.0032, + "step": 42356 + }, + { + "epoch": 13.08, + "learning_rate": 5.6469100626892506e-06, + "loss": 0.0046, + "step": 42357 + }, + { + "epoch": 13.08, + "learning_rate": 5.6464598211418745e-06, + "loss": 0.0046, + "step": 42358 + }, + { + "epoch": 13.08, + "learning_rate": 5.646009590483499e-06, + "loss": 0.0037, + "step": 42359 + }, + { + "epoch": 13.08, + "learning_rate": 5.645559370715248e-06, + "loss": 0.0053, + "step": 42360 + }, + { + "epoch": 13.08, + "learning_rate": 5.645109161838243e-06, + "loss": 0.005, + "step": 42361 + }, + { + "epoch": 13.08, + "learning_rate": 5.644658963853615e-06, + "loss": 0.0037, + "step": 42362 + }, + { + "epoch": 13.08, + "learning_rate": 5.644208776762493e-06, + "loss": 0.0037, + "step": 42363 + }, + { + "epoch": 13.08, + "learning_rate": 5.643758600566001e-06, + "loss": 0.004, + "step": 42364 + }, + { + "epoch": 13.08, + "learning_rate": 5.643308435265256e-06, + "loss": 0.0034, + "step": 42365 + }, + { + "epoch": 13.08, + "learning_rate": 5.642858280861393e-06, + "loss": 0.0045, + "step": 42366 + }, + { + "epoch": 13.08, + "learning_rate": 5.642408137355539e-06, + "loss": 0.0044, + "step": 42367 + }, + { + "epoch": 13.08, + "learning_rate": 5.641958004748815e-06, + "loss": 0.0038, + "step": 42368 + }, + { + "epoch": 13.08, + "learning_rate": 5.641507883042352e-06, + "loss": 0.0044, + "step": 42369 + }, + { + "epoch": 13.08, + "learning_rate": 5.641057772237273e-06, + "loss": 0.0033, + "step": 42370 + }, + { + "epoch": 13.08, + "learning_rate": 5.640607672334699e-06, + "loss": 0.0033, + "step": 42371 + }, + { + "epoch": 13.09, + "learning_rate": 5.64015758333576e-06, + "loss": 0.0033, + "step": 42372 + }, + { + "epoch": 13.09, + "learning_rate": 5.639707505241587e-06, + "loss": 0.0042, + "step": 42373 + }, + { + "epoch": 13.09, + "learning_rate": 5.639257438053301e-06, + "loss": 0.0044, + "step": 42374 + }, + { + "epoch": 13.09, + "learning_rate": 5.638807381772023e-06, + "loss": 0.0035, + "step": 42375 + }, + { + "epoch": 13.09, + "learning_rate": 5.638357336398885e-06, + "loss": 0.0037, + "step": 42376 + }, + { + "epoch": 13.09, + "learning_rate": 5.637907301935009e-06, + "loss": 0.0042, + "step": 42377 + }, + { + "epoch": 13.09, + "learning_rate": 5.637457278381523e-06, + "loss": 0.0046, + "step": 42378 + }, + { + "epoch": 13.09, + "learning_rate": 5.6370072657395555e-06, + "loss": 0.0039, + "step": 42379 + }, + { + "epoch": 13.09, + "learning_rate": 5.6365572640102274e-06, + "loss": 0.0044, + "step": 42380 + }, + { + "epoch": 13.09, + "learning_rate": 5.636107273194663e-06, + "loss": 0.0038, + "step": 42381 + }, + { + "epoch": 13.09, + "learning_rate": 5.635657293293993e-06, + "loss": 0.0046, + "step": 42382 + }, + { + "epoch": 13.09, + "learning_rate": 5.635207324309338e-06, + "loss": 0.0045, + "step": 42383 + }, + { + "epoch": 13.09, + "learning_rate": 5.6347573662418274e-06, + "loss": 0.0049, + "step": 42384 + }, + { + "epoch": 13.09, + "learning_rate": 5.634307419092586e-06, + "loss": 0.0037, + "step": 42385 + }, + { + "epoch": 13.09, + "learning_rate": 5.633857482862734e-06, + "loss": 0.0042, + "step": 42386 + }, + { + "epoch": 13.09, + "learning_rate": 5.633407557553401e-06, + "loss": 0.0045, + "step": 42387 + }, + { + "epoch": 13.09, + "learning_rate": 5.632957643165715e-06, + "loss": 0.005, + "step": 42388 + }, + { + "epoch": 13.09, + "learning_rate": 5.6325077397007945e-06, + "loss": 0.0037, + "step": 42389 + }, + { + "epoch": 13.09, + "learning_rate": 5.632057847159773e-06, + "loss": 0.0042, + "step": 42390 + }, + { + "epoch": 13.09, + "learning_rate": 5.631607965543773e-06, + "loss": 0.0044, + "step": 42391 + }, + { + "epoch": 13.09, + "learning_rate": 5.631158094853913e-06, + "loss": 0.0033, + "step": 42392 + }, + { + "epoch": 13.09, + "learning_rate": 5.6307082350913225e-06, + "loss": 0.0049, + "step": 42393 + }, + { + "epoch": 13.09, + "learning_rate": 5.630258386257133e-06, + "loss": 0.0058, + "step": 42394 + }, + { + "epoch": 13.09, + "learning_rate": 5.629808548352463e-06, + "loss": 0.0032, + "step": 42395 + }, + { + "epoch": 13.09, + "learning_rate": 5.629358721378435e-06, + "loss": 0.0047, + "step": 42396 + }, + { + "epoch": 13.09, + "learning_rate": 5.628908905336183e-06, + "loss": 0.0046, + "step": 42397 + }, + { + "epoch": 13.09, + "learning_rate": 5.6284591002268226e-06, + "loss": 0.0043, + "step": 42398 + }, + { + "epoch": 13.09, + "learning_rate": 5.628009306051484e-06, + "loss": 0.0056, + "step": 42399 + }, + { + "epoch": 13.09, + "learning_rate": 5.6275595228112946e-06, + "loss": 0.0036, + "step": 42400 + }, + { + "epoch": 13.09, + "learning_rate": 5.627109750507377e-06, + "loss": 0.0045, + "step": 42401 + }, + { + "epoch": 13.09, + "learning_rate": 5.626659989140852e-06, + "loss": 0.0046, + "step": 42402 + }, + { + "epoch": 13.09, + "learning_rate": 5.626210238712846e-06, + "loss": 0.0045, + "step": 42403 + }, + { + "epoch": 13.1, + "learning_rate": 5.62576049922449e-06, + "loss": 0.0036, + "step": 42404 + }, + { + "epoch": 13.1, + "learning_rate": 5.625310770676907e-06, + "loss": 0.0046, + "step": 42405 + }, + { + "epoch": 13.1, + "learning_rate": 5.624861053071215e-06, + "loss": 0.0039, + "step": 42406 + }, + { + "epoch": 13.1, + "learning_rate": 5.624411346408547e-06, + "loss": 0.0049, + "step": 42407 + }, + { + "epoch": 13.1, + "learning_rate": 5.62396165069002e-06, + "loss": 0.0045, + "step": 42408 + }, + { + "epoch": 13.1, + "learning_rate": 5.623511965916764e-06, + "loss": 0.0044, + "step": 42409 + }, + { + "epoch": 13.1, + "learning_rate": 5.623062292089906e-06, + "loss": 0.0042, + "step": 42410 + }, + { + "epoch": 13.1, + "learning_rate": 5.622612629210567e-06, + "loss": 0.0051, + "step": 42411 + }, + { + "epoch": 13.1, + "learning_rate": 5.622162977279869e-06, + "loss": 0.0036, + "step": 42412 + }, + { + "epoch": 13.1, + "learning_rate": 5.621713336298944e-06, + "loss": 0.0036, + "step": 42413 + }, + { + "epoch": 13.1, + "learning_rate": 5.621263706268908e-06, + "loss": 0.0047, + "step": 42414 + }, + { + "epoch": 13.1, + "learning_rate": 5.6208140871908945e-06, + "loss": 0.005, + "step": 42415 + }, + { + "epoch": 13.1, + "learning_rate": 5.620364479066023e-06, + "loss": 0.0038, + "step": 42416 + }, + { + "epoch": 13.1, + "learning_rate": 5.619914881895417e-06, + "loss": 0.0034, + "step": 42417 + }, + { + "epoch": 13.1, + "learning_rate": 5.6194652956802e-06, + "loss": 0.0039, + "step": 42418 + }, + { + "epoch": 13.1, + "learning_rate": 5.619015720421503e-06, + "loss": 0.0039, + "step": 42419 + }, + { + "epoch": 13.1, + "learning_rate": 5.618566156120444e-06, + "loss": 0.0048, + "step": 42420 + }, + { + "epoch": 13.1, + "learning_rate": 5.618116602778154e-06, + "loss": 0.0036, + "step": 42421 + }, + { + "epoch": 13.1, + "learning_rate": 5.617667060395755e-06, + "loss": 0.0063, + "step": 42422 + }, + { + "epoch": 13.1, + "learning_rate": 5.617217528974363e-06, + "loss": 0.0032, + "step": 42423 + }, + { + "epoch": 13.1, + "learning_rate": 5.616768008515112e-06, + "loss": 0.0047, + "step": 42424 + }, + { + "epoch": 13.1, + "learning_rate": 5.616318499019126e-06, + "loss": 0.004, + "step": 42425 + }, + { + "epoch": 13.1, + "learning_rate": 5.6158690004875285e-06, + "loss": 0.0045, + "step": 42426 + }, + { + "epoch": 13.1, + "learning_rate": 5.615419512921437e-06, + "loss": 0.005, + "step": 42427 + }, + { + "epoch": 13.1, + "learning_rate": 5.614970036321986e-06, + "loss": 0.0062, + "step": 42428 + }, + { + "epoch": 13.1, + "learning_rate": 5.6145205706902896e-06, + "loss": 0.0059, + "step": 42429 + }, + { + "epoch": 13.1, + "learning_rate": 5.614071116027478e-06, + "loss": 0.0035, + "step": 42430 + }, + { + "epoch": 13.1, + "learning_rate": 5.613621672334678e-06, + "loss": 0.0049, + "step": 42431 + }, + { + "epoch": 13.1, + "learning_rate": 5.613172239613011e-06, + "loss": 0.0038, + "step": 42432 + }, + { + "epoch": 13.1, + "learning_rate": 5.612722817863595e-06, + "loss": 0.0037, + "step": 42433 + }, + { + "epoch": 13.1, + "learning_rate": 5.6122734070875606e-06, + "loss": 0.007, + "step": 42434 + }, + { + "epoch": 13.1, + "learning_rate": 5.6118240072860334e-06, + "loss": 0.0041, + "step": 42435 + }, + { + "epoch": 13.11, + "learning_rate": 5.611374618460136e-06, + "loss": 0.0042, + "step": 42436 + }, + { + "epoch": 13.11, + "learning_rate": 5.610925240610987e-06, + "loss": 0.0038, + "step": 42437 + }, + { + "epoch": 13.11, + "learning_rate": 5.610475873739718e-06, + "loss": 0.0045, + "step": 42438 + }, + { + "epoch": 13.11, + "learning_rate": 5.610026517847445e-06, + "loss": 0.0048, + "step": 42439 + }, + { + "epoch": 13.11, + "learning_rate": 5.6095771729352966e-06, + "loss": 0.0039, + "step": 42440 + }, + { + "epoch": 13.11, + "learning_rate": 5.609127839004405e-06, + "loss": 0.0047, + "step": 42441 + }, + { + "epoch": 13.11, + "learning_rate": 5.608678516055877e-06, + "loss": 0.0041, + "step": 42442 + }, + { + "epoch": 13.11, + "learning_rate": 5.608229204090845e-06, + "loss": 0.0048, + "step": 42443 + }, + { + "epoch": 13.11, + "learning_rate": 5.607779903110437e-06, + "loss": 0.0045, + "step": 42444 + }, + { + "epoch": 13.11, + "learning_rate": 5.607330613115769e-06, + "loss": 0.0048, + "step": 42445 + }, + { + "epoch": 13.11, + "learning_rate": 5.606881334107972e-06, + "loss": 0.004, + "step": 42446 + }, + { + "epoch": 13.11, + "learning_rate": 5.606432066088165e-06, + "loss": 0.007, + "step": 42447 + }, + { + "epoch": 13.11, + "learning_rate": 5.605982809057471e-06, + "loss": 0.004, + "step": 42448 + }, + { + "epoch": 13.11, + "learning_rate": 5.605533563017014e-06, + "loss": 0.0038, + "step": 42449 + }, + { + "epoch": 13.11, + "learning_rate": 5.605084327967923e-06, + "loss": 0.0045, + "step": 42450 + }, + { + "epoch": 13.11, + "learning_rate": 5.604635103911318e-06, + "loss": 0.0049, + "step": 42451 + }, + { + "epoch": 13.11, + "learning_rate": 5.604185890848317e-06, + "loss": 0.005, + "step": 42452 + }, + { + "epoch": 13.11, + "learning_rate": 5.603736688780055e-06, + "loss": 0.0052, + "step": 42453 + }, + { + "epoch": 13.11, + "learning_rate": 5.6032874977076436e-06, + "loss": 0.0034, + "step": 42454 + }, + { + "epoch": 13.11, + "learning_rate": 5.6028383176322135e-06, + "loss": 0.0038, + "step": 42455 + }, + { + "epoch": 13.11, + "learning_rate": 5.6023891485548895e-06, + "loss": 0.0048, + "step": 42456 + }, + { + "epoch": 13.11, + "learning_rate": 5.601939990476792e-06, + "loss": 0.0036, + "step": 42457 + }, + { + "epoch": 13.11, + "learning_rate": 5.601490843399042e-06, + "loss": 0.0042, + "step": 42458 + }, + { + "epoch": 13.11, + "learning_rate": 5.6010417073227696e-06, + "loss": 0.006, + "step": 42459 + }, + { + "epoch": 13.11, + "learning_rate": 5.600592582249089e-06, + "loss": 0.004, + "step": 42460 + }, + { + "epoch": 13.11, + "learning_rate": 5.60014346817913e-06, + "loss": 0.0036, + "step": 42461 + }, + { + "epoch": 13.11, + "learning_rate": 5.599694365114022e-06, + "loss": 0.0044, + "step": 42462 + }, + { + "epoch": 13.11, + "learning_rate": 5.599245273054873e-06, + "loss": 0.0033, + "step": 42463 + }, + { + "epoch": 13.11, + "learning_rate": 5.598796192002814e-06, + "loss": 0.0057, + "step": 42464 + }, + { + "epoch": 13.11, + "learning_rate": 5.598347121958969e-06, + "loss": 0.0038, + "step": 42465 + }, + { + "epoch": 13.11, + "learning_rate": 5.597898062924465e-06, + "loss": 0.0052, + "step": 42466 + }, + { + "epoch": 13.11, + "learning_rate": 5.59744901490042e-06, + "loss": 0.0048, + "step": 42467 + }, + { + "epoch": 13.11, + "learning_rate": 5.596999977887955e-06, + "loss": 0.0051, + "step": 42468 + }, + { + "epoch": 13.12, + "learning_rate": 5.596550951888199e-06, + "loss": 0.0037, + "step": 42469 + }, + { + "epoch": 13.12, + "learning_rate": 5.5961019369022696e-06, + "loss": 0.0046, + "step": 42470 + }, + { + "epoch": 13.12, + "learning_rate": 5.59565293293129e-06, + "loss": 0.0052, + "step": 42471 + }, + { + "epoch": 13.12, + "learning_rate": 5.5952039399763954e-06, + "loss": 0.0057, + "step": 42472 + }, + { + "epoch": 13.12, + "learning_rate": 5.594754958038692e-06, + "loss": 0.0034, + "step": 42473 + }, + { + "epoch": 13.12, + "learning_rate": 5.594305987119309e-06, + "loss": 0.0038, + "step": 42474 + }, + { + "epoch": 13.12, + "learning_rate": 5.593857027219374e-06, + "loss": 0.0039, + "step": 42475 + }, + { + "epoch": 13.12, + "learning_rate": 5.593408078340001e-06, + "loss": 0.004, + "step": 42476 + }, + { + "epoch": 13.12, + "learning_rate": 5.5929591404823235e-06, + "loss": 0.0034, + "step": 42477 + }, + { + "epoch": 13.12, + "learning_rate": 5.592510213647459e-06, + "loss": 0.0042, + "step": 42478 + }, + { + "epoch": 13.12, + "learning_rate": 5.592061297836527e-06, + "loss": 0.0034, + "step": 42479 + }, + { + "epoch": 13.12, + "learning_rate": 5.591612393050654e-06, + "loss": 0.0061, + "step": 42480 + }, + { + "epoch": 13.12, + "learning_rate": 5.591163499290965e-06, + "loss": 0.0038, + "step": 42481 + }, + { + "epoch": 13.12, + "learning_rate": 5.59071461655858e-06, + "loss": 0.0046, + "step": 42482 + }, + { + "epoch": 13.12, + "learning_rate": 5.59026574485462e-06, + "loss": 0.0048, + "step": 42483 + }, + { + "epoch": 13.12, + "learning_rate": 5.589816884180211e-06, + "loss": 0.0042, + "step": 42484 + }, + { + "epoch": 13.12, + "learning_rate": 5.589368034536471e-06, + "loss": 0.0044, + "step": 42485 + }, + { + "epoch": 13.12, + "learning_rate": 5.588919195924527e-06, + "loss": 0.0042, + "step": 42486 + }, + { + "epoch": 13.12, + "learning_rate": 5.588470368345505e-06, + "loss": 0.0043, + "step": 42487 + }, + { + "epoch": 13.12, + "learning_rate": 5.588021551800522e-06, + "loss": 0.0045, + "step": 42488 + }, + { + "epoch": 13.12, + "learning_rate": 5.587572746290697e-06, + "loss": 0.0037, + "step": 42489 + }, + { + "epoch": 13.12, + "learning_rate": 5.587123951817164e-06, + "loss": 0.0055, + "step": 42490 + }, + { + "epoch": 13.12, + "learning_rate": 5.586675168381033e-06, + "loss": 0.0047, + "step": 42491 + }, + { + "epoch": 13.12, + "learning_rate": 5.586226395983436e-06, + "loss": 0.0054, + "step": 42492 + }, + { + "epoch": 13.12, + "learning_rate": 5.585777634625493e-06, + "loss": 0.0041, + "step": 42493 + }, + { + "epoch": 13.12, + "learning_rate": 5.585328884308321e-06, + "loss": 0.0045, + "step": 42494 + }, + { + "epoch": 13.12, + "learning_rate": 5.584880145033046e-06, + "loss": 0.0047, + "step": 42495 + }, + { + "epoch": 13.12, + "learning_rate": 5.584431416800791e-06, + "loss": 0.0047, + "step": 42496 + }, + { + "epoch": 13.12, + "learning_rate": 5.583982699612684e-06, + "loss": 0.0047, + "step": 42497 + }, + { + "epoch": 13.12, + "learning_rate": 5.58353399346984e-06, + "loss": 0.0049, + "step": 42498 + }, + { + "epoch": 13.12, + "learning_rate": 5.583085298373379e-06, + "loss": 0.0043, + "step": 42499 + }, + { + "epoch": 13.12, + "learning_rate": 5.582636614324433e-06, + "loss": 0.0046, + "step": 42500 + }, + { + "epoch": 13.13, + "learning_rate": 5.582187941324112e-06, + "loss": 0.005, + "step": 42501 + }, + { + "epoch": 13.13, + "learning_rate": 5.58173927937355e-06, + "loss": 0.0036, + "step": 42502 + }, + { + "epoch": 13.13, + "learning_rate": 5.581290628473863e-06, + "loss": 0.0043, + "step": 42503 + }, + { + "epoch": 13.13, + "learning_rate": 5.580841988626172e-06, + "loss": 0.0049, + "step": 42504 + }, + { + "epoch": 13.13, + "learning_rate": 5.580393359831599e-06, + "loss": 0.0041, + "step": 42505 + }, + { + "epoch": 13.13, + "learning_rate": 5.579944742091274e-06, + "loss": 0.0042, + "step": 42506 + }, + { + "epoch": 13.13, + "learning_rate": 5.57949613540631e-06, + "loss": 0.0038, + "step": 42507 + }, + { + "epoch": 13.13, + "learning_rate": 5.5790475397778355e-06, + "loss": 0.0048, + "step": 42508 + }, + { + "epoch": 13.13, + "learning_rate": 5.578598955206968e-06, + "loss": 0.0041, + "step": 42509 + }, + { + "epoch": 13.13, + "learning_rate": 5.578150381694829e-06, + "loss": 0.0039, + "step": 42510 + }, + { + "epoch": 13.13, + "learning_rate": 5.57770181924254e-06, + "loss": 0.006, + "step": 42511 + }, + { + "epoch": 13.13, + "learning_rate": 5.577253267851232e-06, + "loss": 0.0043, + "step": 42512 + }, + { + "epoch": 13.13, + "learning_rate": 5.576804727522018e-06, + "loss": 0.0037, + "step": 42513 + }, + { + "epoch": 13.13, + "learning_rate": 5.57635619825602e-06, + "loss": 0.0046, + "step": 42514 + }, + { + "epoch": 13.13, + "learning_rate": 5.5759076800543644e-06, + "loss": 0.0047, + "step": 42515 + }, + { + "epoch": 13.13, + "learning_rate": 5.5754591729181676e-06, + "loss": 0.0031, + "step": 42516 + }, + { + "epoch": 13.13, + "learning_rate": 5.575010676848554e-06, + "loss": 0.0055, + "step": 42517 + }, + { + "epoch": 13.13, + "learning_rate": 5.574562191846651e-06, + "loss": 0.004, + "step": 42518 + }, + { + "epoch": 13.13, + "learning_rate": 5.574113717913574e-06, + "loss": 0.0049, + "step": 42519 + }, + { + "epoch": 13.13, + "learning_rate": 5.573665255050441e-06, + "loss": 0.0045, + "step": 42520 + }, + { + "epoch": 13.13, + "learning_rate": 5.5732168032583835e-06, + "loss": 0.0045, + "step": 42521 + }, + { + "epoch": 13.13, + "learning_rate": 5.572768362538514e-06, + "loss": 0.0041, + "step": 42522 + }, + { + "epoch": 13.13, + "learning_rate": 5.572319932891962e-06, + "loss": 0.0051, + "step": 42523 + }, + { + "epoch": 13.13, + "learning_rate": 5.571871514319846e-06, + "loss": 0.0037, + "step": 42524 + }, + { + "epoch": 13.13, + "learning_rate": 5.5714231068232825e-06, + "loss": 0.0038, + "step": 42525 + }, + { + "epoch": 13.13, + "learning_rate": 5.570974710403398e-06, + "loss": 0.0036, + "step": 42526 + }, + { + "epoch": 13.13, + "learning_rate": 5.570526325061316e-06, + "loss": 0.0031, + "step": 42527 + }, + { + "epoch": 13.13, + "learning_rate": 5.570077950798154e-06, + "loss": 0.0039, + "step": 42528 + }, + { + "epoch": 13.13, + "learning_rate": 5.569629587615037e-06, + "loss": 0.0043, + "step": 42529 + }, + { + "epoch": 13.13, + "learning_rate": 5.5691812355130815e-06, + "loss": 0.005, + "step": 42530 + }, + { + "epoch": 13.13, + "learning_rate": 5.568732894493416e-06, + "loss": 0.0042, + "step": 42531 + }, + { + "epoch": 13.13, + "learning_rate": 5.568284564557154e-06, + "loss": 0.0056, + "step": 42532 + }, + { + "epoch": 13.13, + "learning_rate": 5.567836245705424e-06, + "loss": 0.0041, + "step": 42533 + }, + { + "epoch": 13.14, + "learning_rate": 5.5673879379393435e-06, + "loss": 0.0051, + "step": 42534 + }, + { + "epoch": 13.14, + "learning_rate": 5.56693964126003e-06, + "loss": 0.0037, + "step": 42535 + }, + { + "epoch": 13.14, + "learning_rate": 5.566491355668611e-06, + "loss": 0.0033, + "step": 42536 + }, + { + "epoch": 13.14, + "learning_rate": 5.566043081166208e-06, + "loss": 0.005, + "step": 42537 + }, + { + "epoch": 13.14, + "learning_rate": 5.565594817753936e-06, + "loss": 0.0049, + "step": 42538 + }, + { + "epoch": 13.14, + "learning_rate": 5.565146565432924e-06, + "loss": 0.0051, + "step": 42539 + }, + { + "epoch": 13.14, + "learning_rate": 5.56469832420429e-06, + "loss": 0.004, + "step": 42540 + }, + { + "epoch": 13.14, + "learning_rate": 5.56425009406915e-06, + "loss": 0.0047, + "step": 42541 + }, + { + "epoch": 13.14, + "learning_rate": 5.563801875028629e-06, + "loss": 0.0035, + "step": 42542 + }, + { + "epoch": 13.14, + "learning_rate": 5.563353667083855e-06, + "loss": 0.0048, + "step": 42543 + }, + { + "epoch": 13.14, + "learning_rate": 5.56290547023594e-06, + "loss": 0.0041, + "step": 42544 + }, + { + "epoch": 13.14, + "learning_rate": 5.562457284486005e-06, + "loss": 0.0055, + "step": 42545 + }, + { + "epoch": 13.14, + "learning_rate": 5.562009109835178e-06, + "loss": 0.0035, + "step": 42546 + }, + { + "epoch": 13.14, + "learning_rate": 5.56156094628457e-06, + "loss": 0.0042, + "step": 42547 + }, + { + "epoch": 13.14, + "learning_rate": 5.561112793835309e-06, + "loss": 0.0042, + "step": 42548 + }, + { + "epoch": 13.14, + "learning_rate": 5.560664652488519e-06, + "loss": 0.0039, + "step": 42549 + }, + { + "epoch": 13.14, + "learning_rate": 5.560216522245315e-06, + "loss": 0.0037, + "step": 42550 + }, + { + "epoch": 13.14, + "learning_rate": 5.5597684031068155e-06, + "loss": 0.0037, + "step": 42551 + }, + { + "epoch": 13.14, + "learning_rate": 5.55932029507415e-06, + "loss": 0.005, + "step": 42552 + }, + { + "epoch": 13.14, + "learning_rate": 5.558872198148429e-06, + "loss": 0.0041, + "step": 42553 + }, + { + "epoch": 13.14, + "learning_rate": 5.558424112330784e-06, + "loss": 0.0047, + "step": 42554 + }, + { + "epoch": 13.14, + "learning_rate": 5.5579760376223305e-06, + "loss": 0.0045, + "step": 42555 + }, + { + "epoch": 13.14, + "learning_rate": 5.557527974024184e-06, + "loss": 0.0043, + "step": 42556 + }, + { + "epoch": 13.14, + "learning_rate": 5.55707992153747e-06, + "loss": 0.0047, + "step": 42557 + }, + { + "epoch": 13.14, + "learning_rate": 5.556631880163315e-06, + "loss": 0.0042, + "step": 42558 + }, + { + "epoch": 13.14, + "learning_rate": 5.556183849902828e-06, + "loss": 0.0038, + "step": 42559 + }, + { + "epoch": 13.14, + "learning_rate": 5.555735830757142e-06, + "loss": 0.0036, + "step": 42560 + }, + { + "epoch": 13.14, + "learning_rate": 5.55528782272737e-06, + "loss": 0.0049, + "step": 42561 + }, + { + "epoch": 13.14, + "learning_rate": 5.554839825814629e-06, + "loss": 0.004, + "step": 42562 + }, + { + "epoch": 13.14, + "learning_rate": 5.554391840020046e-06, + "loss": 0.0042, + "step": 42563 + }, + { + "epoch": 13.14, + "learning_rate": 5.553943865344744e-06, + "loss": 0.0037, + "step": 42564 + }, + { + "epoch": 13.14, + "learning_rate": 5.5534959017898384e-06, + "loss": 0.0041, + "step": 42565 + }, + { + "epoch": 13.15, + "learning_rate": 5.553047949356446e-06, + "loss": 0.004, + "step": 42566 + }, + { + "epoch": 13.15, + "learning_rate": 5.552600008045692e-06, + "loss": 0.0041, + "step": 42567 + }, + { + "epoch": 13.15, + "learning_rate": 5.552152077858701e-06, + "loss": 0.0049, + "step": 42568 + }, + { + "epoch": 13.15, + "learning_rate": 5.551704158796585e-06, + "loss": 0.0034, + "step": 42569 + }, + { + "epoch": 13.15, + "learning_rate": 5.551256250860473e-06, + "loss": 0.0047, + "step": 42570 + }, + { + "epoch": 13.15, + "learning_rate": 5.550808354051479e-06, + "loss": 0.0041, + "step": 42571 + }, + { + "epoch": 13.15, + "learning_rate": 5.550360468370721e-06, + "loss": 0.0054, + "step": 42572 + }, + { + "epoch": 13.15, + "learning_rate": 5.549912593819324e-06, + "loss": 0.0046, + "step": 42573 + }, + { + "epoch": 13.15, + "learning_rate": 5.549464730398411e-06, + "loss": 0.0046, + "step": 42574 + }, + { + "epoch": 13.15, + "learning_rate": 5.549016878109097e-06, + "loss": 0.0037, + "step": 42575 + }, + { + "epoch": 13.15, + "learning_rate": 5.5485690369525e-06, + "loss": 0.0041, + "step": 42576 + }, + { + "epoch": 13.15, + "learning_rate": 5.5481212069297495e-06, + "loss": 0.0035, + "step": 42577 + }, + { + "epoch": 13.15, + "learning_rate": 5.547673388041954e-06, + "loss": 0.006, + "step": 42578 + }, + { + "epoch": 13.15, + "learning_rate": 5.547225580290241e-06, + "loss": 0.0042, + "step": 42579 + }, + { + "epoch": 13.15, + "learning_rate": 5.546777783675736e-06, + "loss": 0.0044, + "step": 42580 + }, + { + "epoch": 13.15, + "learning_rate": 5.546329998199544e-06, + "loss": 0.0043, + "step": 42581 + }, + { + "epoch": 13.15, + "learning_rate": 5.545882223862793e-06, + "loss": 0.0041, + "step": 42582 + }, + { + "epoch": 13.15, + "learning_rate": 5.545434460666608e-06, + "loss": 0.004, + "step": 42583 + }, + { + "epoch": 13.15, + "learning_rate": 5.544986708612098e-06, + "loss": 0.0033, + "step": 42584 + }, + { + "epoch": 13.15, + "learning_rate": 5.544538967700393e-06, + "loss": 0.0048, + "step": 42585 + }, + { + "epoch": 13.15, + "learning_rate": 5.54409123793261e-06, + "loss": 0.0037, + "step": 42586 + }, + { + "epoch": 13.15, + "learning_rate": 5.543643519309862e-06, + "loss": 0.0043, + "step": 42587 + }, + { + "epoch": 13.15, + "learning_rate": 5.543195811833275e-06, + "loss": 0.0049, + "step": 42588 + }, + { + "epoch": 13.15, + "learning_rate": 5.542748115503973e-06, + "loss": 0.0035, + "step": 42589 + }, + { + "epoch": 13.15, + "learning_rate": 5.542300430323071e-06, + "loss": 0.0046, + "step": 42590 + }, + { + "epoch": 13.15, + "learning_rate": 5.541852756291684e-06, + "loss": 0.0046, + "step": 42591 + }, + { + "epoch": 13.15, + "learning_rate": 5.5414050934109395e-06, + "loss": 0.0053, + "step": 42592 + }, + { + "epoch": 13.15, + "learning_rate": 5.540957441681951e-06, + "loss": 0.0037, + "step": 42593 + }, + { + "epoch": 13.15, + "learning_rate": 5.540509801105841e-06, + "loss": 0.0044, + "step": 42594 + }, + { + "epoch": 13.15, + "learning_rate": 5.540062171683733e-06, + "loss": 0.0041, + "step": 42595 + }, + { + "epoch": 13.15, + "learning_rate": 5.539614553416744e-06, + "loss": 0.0035, + "step": 42596 + }, + { + "epoch": 13.15, + "learning_rate": 5.539166946305987e-06, + "loss": 0.005, + "step": 42597 + }, + { + "epoch": 13.16, + "learning_rate": 5.538719350352589e-06, + "loss": 0.0045, + "step": 42598 + }, + { + "epoch": 13.16, + "learning_rate": 5.53827176555767e-06, + "loss": 0.0036, + "step": 42599 + }, + { + "epoch": 13.16, + "learning_rate": 5.537824191922348e-06, + "loss": 0.0035, + "step": 42600 + }, + { + "epoch": 13.16, + "learning_rate": 5.537376629447737e-06, + "loss": 0.0039, + "step": 42601 + }, + { + "epoch": 13.16, + "learning_rate": 5.536929078134965e-06, + "loss": 0.0036, + "step": 42602 + }, + { + "epoch": 13.16, + "learning_rate": 5.536481537985143e-06, + "loss": 0.0042, + "step": 42603 + }, + { + "epoch": 13.16, + "learning_rate": 5.536034008999396e-06, + "loss": 0.0042, + "step": 42604 + }, + { + "epoch": 13.16, + "learning_rate": 5.535586491178846e-06, + "loss": 0.0041, + "step": 42605 + }, + { + "epoch": 13.16, + "learning_rate": 5.535138984524606e-06, + "loss": 0.0038, + "step": 42606 + }, + { + "epoch": 13.16, + "learning_rate": 5.534691489037797e-06, + "loss": 0.0056, + "step": 42607 + }, + { + "epoch": 13.16, + "learning_rate": 5.534244004719541e-06, + "loss": 0.0053, + "step": 42608 + }, + { + "epoch": 13.16, + "learning_rate": 5.5337965315709515e-06, + "loss": 0.0042, + "step": 42609 + }, + { + "epoch": 13.16, + "learning_rate": 5.533349069593157e-06, + "loss": 0.0041, + "step": 42610 + }, + { + "epoch": 13.16, + "learning_rate": 5.532901618787269e-06, + "loss": 0.004, + "step": 42611 + }, + { + "epoch": 13.16, + "learning_rate": 5.532454179154406e-06, + "loss": 0.0045, + "step": 42612 + }, + { + "epoch": 13.16, + "learning_rate": 5.53200675069569e-06, + "loss": 0.0044, + "step": 42613 + }, + { + "epoch": 13.16, + "learning_rate": 5.5315593334122445e-06, + "loss": 0.0042, + "step": 42614 + }, + { + "epoch": 13.16, + "learning_rate": 5.531111927305178e-06, + "loss": 0.0042, + "step": 42615 + }, + { + "epoch": 13.16, + "learning_rate": 5.530664532375622e-06, + "loss": 0.0054, + "step": 42616 + }, + { + "epoch": 13.16, + "learning_rate": 5.5302171486246884e-06, + "loss": 0.0049, + "step": 42617 + }, + { + "epoch": 13.16, + "learning_rate": 5.5297697760534914e-06, + "loss": 0.0057, + "step": 42618 + }, + { + "epoch": 13.16, + "learning_rate": 5.5293224146631564e-06, + "loss": 0.0051, + "step": 42619 + }, + { + "epoch": 13.16, + "learning_rate": 5.528875064454806e-06, + "loss": 0.0046, + "step": 42620 + }, + { + "epoch": 13.16, + "learning_rate": 5.528427725429555e-06, + "loss": 0.0036, + "step": 42621 + }, + { + "epoch": 13.16, + "learning_rate": 5.527980397588517e-06, + "loss": 0.005, + "step": 42622 + }, + { + "epoch": 13.16, + "learning_rate": 5.52753308093282e-06, + "loss": 0.0035, + "step": 42623 + }, + { + "epoch": 13.16, + "learning_rate": 5.527085775463574e-06, + "loss": 0.0035, + "step": 42624 + }, + { + "epoch": 13.16, + "learning_rate": 5.526638481181903e-06, + "loss": 0.0046, + "step": 42625 + }, + { + "epoch": 13.16, + "learning_rate": 5.5261911980889285e-06, + "loss": 0.0042, + "step": 42626 + }, + { + "epoch": 13.16, + "learning_rate": 5.525743926185766e-06, + "loss": 0.0055, + "step": 42627 + }, + { + "epoch": 13.16, + "learning_rate": 5.52529666547353e-06, + "loss": 0.0036, + "step": 42628 + }, + { + "epoch": 13.16, + "learning_rate": 5.524849415953344e-06, + "loss": 0.0039, + "step": 42629 + }, + { + "epoch": 13.16, + "learning_rate": 5.524402177626328e-06, + "loss": 0.0042, + "step": 42630 + }, + { + "epoch": 13.17, + "learning_rate": 5.523954950493599e-06, + "loss": 0.0039, + "step": 42631 + }, + { + "epoch": 13.17, + "learning_rate": 5.523507734556273e-06, + "loss": 0.0073, + "step": 42632 + }, + { + "epoch": 13.17, + "learning_rate": 5.523060529815472e-06, + "loss": 0.0044, + "step": 42633 + }, + { + "epoch": 13.17, + "learning_rate": 5.522613336272311e-06, + "loss": 0.0045, + "step": 42634 + }, + { + "epoch": 13.17, + "learning_rate": 5.522166153927909e-06, + "loss": 0.0042, + "step": 42635 + }, + { + "epoch": 13.17, + "learning_rate": 5.521718982783391e-06, + "loss": 0.0043, + "step": 42636 + }, + { + "epoch": 13.17, + "learning_rate": 5.521271822839871e-06, + "loss": 0.0035, + "step": 42637 + }, + { + "epoch": 13.17, + "learning_rate": 5.520824674098463e-06, + "loss": 0.0039, + "step": 42638 + }, + { + "epoch": 13.17, + "learning_rate": 5.520377536560293e-06, + "loss": 0.0044, + "step": 42639 + }, + { + "epoch": 13.17, + "learning_rate": 5.5199304102264715e-06, + "loss": 0.0052, + "step": 42640 + }, + { + "epoch": 13.17, + "learning_rate": 5.519483295098126e-06, + "loss": 0.0035, + "step": 42641 + }, + { + "epoch": 13.17, + "learning_rate": 5.51903619117637e-06, + "loss": 0.0049, + "step": 42642 + }, + { + "epoch": 13.17, + "learning_rate": 5.5185890984623165e-06, + "loss": 0.0038, + "step": 42643 + }, + { + "epoch": 13.17, + "learning_rate": 5.518142016957091e-06, + "loss": 0.0076, + "step": 42644 + }, + { + "epoch": 13.17, + "learning_rate": 5.517694946661811e-06, + "loss": 0.0053, + "step": 42645 + }, + { + "epoch": 13.17, + "learning_rate": 5.517247887577593e-06, + "loss": 0.0046, + "step": 42646 + }, + { + "epoch": 13.17, + "learning_rate": 5.516800839705556e-06, + "loss": 0.0045, + "step": 42647 + }, + { + "epoch": 13.17, + "learning_rate": 5.51635380304682e-06, + "loss": 0.0041, + "step": 42648 + }, + { + "epoch": 13.17, + "learning_rate": 5.5159067776024966e-06, + "loss": 0.0043, + "step": 42649 + }, + { + "epoch": 13.17, + "learning_rate": 5.515459763373708e-06, + "loss": 0.0043, + "step": 42650 + }, + { + "epoch": 13.17, + "learning_rate": 5.515012760361577e-06, + "loss": 0.0044, + "step": 42651 + }, + { + "epoch": 13.17, + "learning_rate": 5.514565768567216e-06, + "loss": 0.0053, + "step": 42652 + }, + { + "epoch": 13.17, + "learning_rate": 5.51411878799174e-06, + "loss": 0.004, + "step": 42653 + }, + { + "epoch": 13.17, + "learning_rate": 5.513671818636277e-06, + "loss": 0.0046, + "step": 42654 + }, + { + "epoch": 13.17, + "learning_rate": 5.513224860501933e-06, + "loss": 0.0043, + "step": 42655 + }, + { + "epoch": 13.17, + "learning_rate": 5.512777913589833e-06, + "loss": 0.0043, + "step": 42656 + }, + { + "epoch": 13.17, + "learning_rate": 5.512330977901098e-06, + "loss": 0.0056, + "step": 42657 + }, + { + "epoch": 13.17, + "learning_rate": 5.511884053436841e-06, + "loss": 0.0037, + "step": 42658 + }, + { + "epoch": 13.17, + "learning_rate": 5.511437140198177e-06, + "loss": 0.0057, + "step": 42659 + }, + { + "epoch": 13.17, + "learning_rate": 5.510990238186227e-06, + "loss": 0.0041, + "step": 42660 + }, + { + "epoch": 13.17, + "learning_rate": 5.510543347402114e-06, + "loss": 0.0045, + "step": 42661 + }, + { + "epoch": 13.17, + "learning_rate": 5.510096467846951e-06, + "loss": 0.005, + "step": 42662 + }, + { + "epoch": 13.18, + "learning_rate": 5.50964959952185e-06, + "loss": 0.0047, + "step": 42663 + }, + { + "epoch": 13.18, + "learning_rate": 5.509202742427939e-06, + "loss": 0.0044, + "step": 42664 + }, + { + "epoch": 13.18, + "learning_rate": 5.508755896566328e-06, + "loss": 0.0038, + "step": 42665 + }, + { + "epoch": 13.18, + "learning_rate": 5.508309061938137e-06, + "loss": 0.004, + "step": 42666 + }, + { + "epoch": 13.18, + "learning_rate": 5.507862238544488e-06, + "loss": 0.0059, + "step": 42667 + }, + { + "epoch": 13.18, + "learning_rate": 5.507415426386495e-06, + "loss": 0.004, + "step": 42668 + }, + { + "epoch": 13.18, + "learning_rate": 5.506968625465272e-06, + "loss": 0.0047, + "step": 42669 + }, + { + "epoch": 13.18, + "learning_rate": 5.506521835781944e-06, + "loss": 0.0044, + "step": 42670 + }, + { + "epoch": 13.18, + "learning_rate": 5.506075057337619e-06, + "loss": 0.005, + "step": 42671 + }, + { + "epoch": 13.18, + "learning_rate": 5.505628290133425e-06, + "loss": 0.0061, + "step": 42672 + }, + { + "epoch": 13.18, + "learning_rate": 5.505181534170474e-06, + "loss": 0.0037, + "step": 42673 + }, + { + "epoch": 13.18, + "learning_rate": 5.50473478944988e-06, + "loss": 0.0037, + "step": 42674 + }, + { + "epoch": 13.18, + "learning_rate": 5.504288055972764e-06, + "loss": 0.0053, + "step": 42675 + }, + { + "epoch": 13.18, + "learning_rate": 5.503841333740249e-06, + "loss": 0.0041, + "step": 42676 + }, + { + "epoch": 13.18, + "learning_rate": 5.503394622753442e-06, + "loss": 0.0052, + "step": 42677 + }, + { + "epoch": 13.18, + "learning_rate": 5.502947923013468e-06, + "loss": 0.0038, + "step": 42678 + }, + { + "epoch": 13.18, + "learning_rate": 5.502501234521442e-06, + "loss": 0.0047, + "step": 42679 + }, + { + "epoch": 13.18, + "learning_rate": 5.502054557278478e-06, + "loss": 0.0041, + "step": 42680 + }, + { + "epoch": 13.18, + "learning_rate": 5.501607891285694e-06, + "loss": 0.0037, + "step": 42681 + }, + { + "epoch": 13.18, + "learning_rate": 5.501161236544215e-06, + "loss": 0.0048, + "step": 42682 + }, + { + "epoch": 13.18, + "learning_rate": 5.50071459305515e-06, + "loss": 0.0046, + "step": 42683 + }, + { + "epoch": 13.18, + "learning_rate": 5.5002679608196165e-06, + "loss": 0.0038, + "step": 42684 + }, + { + "epoch": 13.18, + "learning_rate": 5.499821339838735e-06, + "loss": 0.0036, + "step": 42685 + }, + { + "epoch": 13.18, + "learning_rate": 5.49937473011362e-06, + "loss": 0.0049, + "step": 42686 + }, + { + "epoch": 13.18, + "learning_rate": 5.498928131645389e-06, + "loss": 0.0036, + "step": 42687 + }, + { + "epoch": 13.18, + "learning_rate": 5.4984815444351665e-06, + "loss": 0.0045, + "step": 42688 + }, + { + "epoch": 13.18, + "learning_rate": 5.498034968484056e-06, + "loss": 0.0047, + "step": 42689 + }, + { + "epoch": 13.18, + "learning_rate": 5.4975884037931795e-06, + "loss": 0.0053, + "step": 42690 + }, + { + "epoch": 13.18, + "learning_rate": 5.497141850363661e-06, + "loss": 0.0038, + "step": 42691 + }, + { + "epoch": 13.18, + "learning_rate": 5.496695308196608e-06, + "loss": 0.0049, + "step": 42692 + }, + { + "epoch": 13.18, + "learning_rate": 5.496248777293145e-06, + "loss": 0.0049, + "step": 42693 + }, + { + "epoch": 13.18, + "learning_rate": 5.495802257654381e-06, + "loss": 0.0043, + "step": 42694 + }, + { + "epoch": 13.19, + "learning_rate": 5.495355749281441e-06, + "loss": 0.0062, + "step": 42695 + }, + { + "epoch": 13.19, + "learning_rate": 5.494909252175435e-06, + "loss": 0.0038, + "step": 42696 + }, + { + "epoch": 13.19, + "learning_rate": 5.494462766337482e-06, + "loss": 0.0044, + "step": 42697 + }, + { + "epoch": 13.19, + "learning_rate": 5.494016291768707e-06, + "loss": 0.0041, + "step": 42698 + }, + { + "epoch": 13.19, + "learning_rate": 5.493569828470211e-06, + "loss": 0.0035, + "step": 42699 + }, + { + "epoch": 13.19, + "learning_rate": 5.4931233764431194e-06, + "loss": 0.0043, + "step": 42700 + }, + { + "epoch": 13.19, + "learning_rate": 5.492676935688551e-06, + "loss": 0.005, + "step": 42701 + }, + { + "epoch": 13.19, + "learning_rate": 5.492230506207616e-06, + "loss": 0.0045, + "step": 42702 + }, + { + "epoch": 13.19, + "learning_rate": 5.4917840880014395e-06, + "loss": 0.0037, + "step": 42703 + }, + { + "epoch": 13.19, + "learning_rate": 5.491337681071134e-06, + "loss": 0.0034, + "step": 42704 + }, + { + "epoch": 13.19, + "learning_rate": 5.49089128541781e-06, + "loss": 0.0031, + "step": 42705 + }, + { + "epoch": 13.19, + "learning_rate": 5.49044490104259e-06, + "loss": 0.0051, + "step": 42706 + }, + { + "epoch": 13.19, + "learning_rate": 5.4899985279465926e-06, + "loss": 0.0047, + "step": 42707 + }, + { + "epoch": 13.19, + "learning_rate": 5.489552166130933e-06, + "loss": 0.0041, + "step": 42708 + }, + { + "epoch": 13.19, + "learning_rate": 5.4891058155967204e-06, + "loss": 0.0056, + "step": 42709 + }, + { + "epoch": 13.19, + "learning_rate": 5.488659476345082e-06, + "loss": 0.0052, + "step": 42710 + }, + { + "epoch": 13.19, + "learning_rate": 5.488213148377125e-06, + "loss": 0.0044, + "step": 42711 + }, + { + "epoch": 13.19, + "learning_rate": 5.4877668316939706e-06, + "loss": 0.0043, + "step": 42712 + }, + { + "epoch": 13.19, + "learning_rate": 5.487320526296737e-06, + "loss": 0.0044, + "step": 42713 + }, + { + "epoch": 13.19, + "learning_rate": 5.486874232186538e-06, + "loss": 0.004, + "step": 42714 + }, + { + "epoch": 13.19, + "learning_rate": 5.486427949364485e-06, + "loss": 0.0037, + "step": 42715 + }, + { + "epoch": 13.19, + "learning_rate": 5.485981677831704e-06, + "loss": 0.0037, + "step": 42716 + }, + { + "epoch": 13.19, + "learning_rate": 5.485535417589303e-06, + "loss": 0.0037, + "step": 42717 + }, + { + "epoch": 13.19, + "learning_rate": 5.4850891686384e-06, + "loss": 0.0057, + "step": 42718 + }, + { + "epoch": 13.19, + "learning_rate": 5.484642930980121e-06, + "loss": 0.0045, + "step": 42719 + }, + { + "epoch": 13.19, + "learning_rate": 5.484196704615565e-06, + "loss": 0.0057, + "step": 42720 + }, + { + "epoch": 13.19, + "learning_rate": 5.483750489545857e-06, + "loss": 0.0046, + "step": 42721 + }, + { + "epoch": 13.19, + "learning_rate": 5.483304285772118e-06, + "loss": 0.004, + "step": 42722 + }, + { + "epoch": 13.19, + "learning_rate": 5.4828580932954535e-06, + "loss": 0.0041, + "step": 42723 + }, + { + "epoch": 13.19, + "learning_rate": 5.482411912116987e-06, + "loss": 0.004, + "step": 42724 + }, + { + "epoch": 13.19, + "learning_rate": 5.481965742237831e-06, + "loss": 0.0053, + "step": 42725 + }, + { + "epoch": 13.19, + "learning_rate": 5.4815195836591055e-06, + "loss": 0.0034, + "step": 42726 + }, + { + "epoch": 13.19, + "learning_rate": 5.481073436381921e-06, + "loss": 0.005, + "step": 42727 + }, + { + "epoch": 13.2, + "learning_rate": 5.480627300407394e-06, + "loss": 0.0038, + "step": 42728 + }, + { + "epoch": 13.2, + "learning_rate": 5.4801811757366515e-06, + "loss": 0.0047, + "step": 42729 + }, + { + "epoch": 13.2, + "learning_rate": 5.479735062370793e-06, + "loss": 0.0046, + "step": 42730 + }, + { + "epoch": 13.2, + "learning_rate": 5.47928896031094e-06, + "loss": 0.0039, + "step": 42731 + }, + { + "epoch": 13.2, + "learning_rate": 5.478842869558214e-06, + "loss": 0.0037, + "step": 42732 + }, + { + "epoch": 13.2, + "learning_rate": 5.478396790113724e-06, + "loss": 0.0049, + "step": 42733 + }, + { + "epoch": 13.2, + "learning_rate": 5.477950721978591e-06, + "loss": 0.0053, + "step": 42734 + }, + { + "epoch": 13.2, + "learning_rate": 5.477504665153928e-06, + "loss": 0.0047, + "step": 42735 + }, + { + "epoch": 13.2, + "learning_rate": 5.477058619640847e-06, + "loss": 0.005, + "step": 42736 + }, + { + "epoch": 13.2, + "learning_rate": 5.476612585440469e-06, + "loss": 0.0043, + "step": 42737 + }, + { + "epoch": 13.2, + "learning_rate": 5.4761665625539085e-06, + "loss": 0.004, + "step": 42738 + }, + { + "epoch": 13.2, + "learning_rate": 5.475720550982283e-06, + "loss": 0.0047, + "step": 42739 + }, + { + "epoch": 13.2, + "learning_rate": 5.475274550726701e-06, + "loss": 0.0051, + "step": 42740 + }, + { + "epoch": 13.2, + "learning_rate": 5.474828561788287e-06, + "loss": 0.0052, + "step": 42741 + }, + { + "epoch": 13.2, + "learning_rate": 5.474382584168148e-06, + "loss": 0.0046, + "step": 42742 + }, + { + "epoch": 13.2, + "learning_rate": 5.473936617867403e-06, + "loss": 0.0042, + "step": 42743 + }, + { + "epoch": 13.2, + "learning_rate": 5.473490662887172e-06, + "loss": 0.005, + "step": 42744 + }, + { + "epoch": 13.2, + "learning_rate": 5.473044719228566e-06, + "loss": 0.0052, + "step": 42745 + }, + { + "epoch": 13.2, + "learning_rate": 5.472598786892698e-06, + "loss": 0.0042, + "step": 42746 + }, + { + "epoch": 13.2, + "learning_rate": 5.47215286588069e-06, + "loss": 0.0053, + "step": 42747 + }, + { + "epoch": 13.2, + "learning_rate": 5.471706956193649e-06, + "loss": 0.0036, + "step": 42748 + }, + { + "epoch": 13.2, + "learning_rate": 5.4712610578326996e-06, + "loss": 0.0051, + "step": 42749 + }, + { + "epoch": 13.2, + "learning_rate": 5.470815170798951e-06, + "loss": 0.0041, + "step": 42750 + }, + { + "epoch": 13.2, + "learning_rate": 5.470369295093516e-06, + "loss": 0.0042, + "step": 42751 + }, + { + "epoch": 13.2, + "learning_rate": 5.469923430717514e-06, + "loss": 0.0054, + "step": 42752 + }, + { + "epoch": 13.2, + "learning_rate": 5.469477577672064e-06, + "loss": 0.0037, + "step": 42753 + }, + { + "epoch": 13.2, + "learning_rate": 5.469031735958273e-06, + "loss": 0.0041, + "step": 42754 + }, + { + "epoch": 13.2, + "learning_rate": 5.468585905577264e-06, + "loss": 0.0038, + "step": 42755 + }, + { + "epoch": 13.2, + "learning_rate": 5.468140086530147e-06, + "loss": 0.0047, + "step": 42756 + }, + { + "epoch": 13.2, + "learning_rate": 5.467694278818036e-06, + "loss": 0.0042, + "step": 42757 + }, + { + "epoch": 13.2, + "learning_rate": 5.467248482442047e-06, + "loss": 0.0038, + "step": 42758 + }, + { + "epoch": 13.2, + "learning_rate": 5.466802697403301e-06, + "loss": 0.0053, + "step": 42759 + }, + { + "epoch": 13.21, + "learning_rate": 5.4663569237029065e-06, + "loss": 0.0055, + "step": 42760 + }, + { + "epoch": 13.21, + "learning_rate": 5.465911161341978e-06, + "loss": 0.0039, + "step": 42761 + }, + { + "epoch": 13.21, + "learning_rate": 5.465465410321632e-06, + "loss": 0.003, + "step": 42762 + }, + { + "epoch": 13.21, + "learning_rate": 5.465019670642988e-06, + "loss": 0.0039, + "step": 42763 + }, + { + "epoch": 13.21, + "learning_rate": 5.464573942307154e-06, + "loss": 0.0043, + "step": 42764 + }, + { + "epoch": 13.21, + "learning_rate": 5.4641282253152505e-06, + "loss": 0.0045, + "step": 42765 + }, + { + "epoch": 13.21, + "learning_rate": 5.46368251966839e-06, + "loss": 0.005, + "step": 42766 + }, + { + "epoch": 13.21, + "learning_rate": 5.463236825367684e-06, + "loss": 0.0044, + "step": 42767 + }, + { + "epoch": 13.21, + "learning_rate": 5.462791142414247e-06, + "loss": 0.0052, + "step": 42768 + }, + { + "epoch": 13.21, + "learning_rate": 5.462345470809204e-06, + "loss": 0.0056, + "step": 42769 + }, + { + "epoch": 13.21, + "learning_rate": 5.4618998105536615e-06, + "loss": 0.0047, + "step": 42770 + }, + { + "epoch": 13.21, + "learning_rate": 5.461454161648732e-06, + "loss": 0.0045, + "step": 42771 + }, + { + "epoch": 13.21, + "learning_rate": 5.461008524095536e-06, + "loss": 0.004, + "step": 42772 + }, + { + "epoch": 13.21, + "learning_rate": 5.460562897895183e-06, + "loss": 0.0048, + "step": 42773 + }, + { + "epoch": 13.21, + "learning_rate": 5.460117283048789e-06, + "loss": 0.0033, + "step": 42774 + }, + { + "epoch": 13.21, + "learning_rate": 5.459671679557475e-06, + "loss": 0.0046, + "step": 42775 + }, + { + "epoch": 13.21, + "learning_rate": 5.459226087422348e-06, + "loss": 0.0053, + "step": 42776 + }, + { + "epoch": 13.21, + "learning_rate": 5.458780506644522e-06, + "loss": 0.0044, + "step": 42777 + }, + { + "epoch": 13.21, + "learning_rate": 5.458334937225118e-06, + "loss": 0.0054, + "step": 42778 + }, + { + "epoch": 13.21, + "learning_rate": 5.457889379165243e-06, + "loss": 0.0045, + "step": 42779 + }, + { + "epoch": 13.21, + "learning_rate": 5.457443832466019e-06, + "loss": 0.0039, + "step": 42780 + }, + { + "epoch": 13.21, + "learning_rate": 5.456998297128557e-06, + "loss": 0.0052, + "step": 42781 + }, + { + "epoch": 13.21, + "learning_rate": 5.456552773153967e-06, + "loss": 0.0042, + "step": 42782 + }, + { + "epoch": 13.21, + "learning_rate": 5.456107260543366e-06, + "loss": 0.0048, + "step": 42783 + }, + { + "epoch": 13.21, + "learning_rate": 5.455661759297874e-06, + "loss": 0.0039, + "step": 42784 + }, + { + "epoch": 13.21, + "learning_rate": 5.455216269418597e-06, + "loss": 0.0048, + "step": 42785 + }, + { + "epoch": 13.21, + "learning_rate": 5.4547707909066564e-06, + "loss": 0.0067, + "step": 42786 + }, + { + "epoch": 13.21, + "learning_rate": 5.454325323763163e-06, + "loss": 0.0039, + "step": 42787 + }, + { + "epoch": 13.21, + "learning_rate": 5.453879867989229e-06, + "loss": 0.0037, + "step": 42788 + }, + { + "epoch": 13.21, + "learning_rate": 5.453434423585968e-06, + "loss": 0.004, + "step": 42789 + }, + { + "epoch": 13.21, + "learning_rate": 5.452988990554502e-06, + "loss": 0.0045, + "step": 42790 + }, + { + "epoch": 13.21, + "learning_rate": 5.45254356889594e-06, + "loss": 0.0065, + "step": 42791 + }, + { + "epoch": 13.21, + "learning_rate": 5.452098158611392e-06, + "loss": 0.0039, + "step": 42792 + }, + { + "epoch": 13.22, + "learning_rate": 5.451652759701975e-06, + "loss": 0.0042, + "step": 42793 + }, + { + "epoch": 13.22, + "learning_rate": 5.45120737216881e-06, + "loss": 0.0053, + "step": 42794 + }, + { + "epoch": 13.22, + "learning_rate": 5.450761996012999e-06, + "loss": 0.0043, + "step": 42795 + }, + { + "epoch": 13.22, + "learning_rate": 5.450316631235667e-06, + "loss": 0.0043, + "step": 42796 + }, + { + "epoch": 13.22, + "learning_rate": 5.449871277837922e-06, + "loss": 0.0045, + "step": 42797 + }, + { + "epoch": 13.22, + "learning_rate": 5.449425935820875e-06, + "loss": 0.004, + "step": 42798 + }, + { + "epoch": 13.22, + "learning_rate": 5.448980605185646e-06, + "loss": 0.0052, + "step": 42799 + }, + { + "epoch": 13.22, + "learning_rate": 5.4485352859333486e-06, + "loss": 0.0038, + "step": 42800 + }, + { + "epoch": 13.22, + "learning_rate": 5.448089978065094e-06, + "loss": 0.0037, + "step": 42801 + }, + { + "epoch": 13.22, + "learning_rate": 5.447644681581994e-06, + "loss": 0.0039, + "step": 42802 + }, + { + "epoch": 13.22, + "learning_rate": 5.447199396485168e-06, + "loss": 0.0053, + "step": 42803 + }, + { + "epoch": 13.22, + "learning_rate": 5.446754122775722e-06, + "loss": 0.0045, + "step": 42804 + }, + { + "epoch": 13.22, + "learning_rate": 5.4463088604547764e-06, + "loss": 0.0057, + "step": 42805 + }, + { + "epoch": 13.22, + "learning_rate": 5.4458636095234454e-06, + "loss": 0.0046, + "step": 42806 + }, + { + "epoch": 13.22, + "learning_rate": 5.44541836998284e-06, + "loss": 0.0041, + "step": 42807 + }, + { + "epoch": 13.22, + "learning_rate": 5.444973141834071e-06, + "loss": 0.0057, + "step": 42808 + }, + { + "epoch": 13.22, + "learning_rate": 5.444527925078258e-06, + "loss": 0.0058, + "step": 42809 + }, + { + "epoch": 13.22, + "learning_rate": 5.444082719716508e-06, + "loss": 0.0044, + "step": 42810 + }, + { + "epoch": 13.22, + "learning_rate": 5.443637525749943e-06, + "loss": 0.0044, + "step": 42811 + }, + { + "epoch": 13.22, + "learning_rate": 5.443192343179671e-06, + "loss": 0.0048, + "step": 42812 + }, + { + "epoch": 13.22, + "learning_rate": 5.442747172006802e-06, + "loss": 0.0044, + "step": 42813 + }, + { + "epoch": 13.22, + "learning_rate": 5.442302012232452e-06, + "loss": 0.0046, + "step": 42814 + }, + { + "epoch": 13.22, + "learning_rate": 5.441856863857741e-06, + "loss": 0.0041, + "step": 42815 + }, + { + "epoch": 13.22, + "learning_rate": 5.441411726883774e-06, + "loss": 0.0044, + "step": 42816 + }, + { + "epoch": 13.22, + "learning_rate": 5.440966601311671e-06, + "loss": 0.0047, + "step": 42817 + }, + { + "epoch": 13.22, + "learning_rate": 5.4405214871425425e-06, + "loss": 0.0034, + "step": 42818 + }, + { + "epoch": 13.22, + "learning_rate": 5.440076384377498e-06, + "loss": 0.0066, + "step": 42819 + }, + { + "epoch": 13.22, + "learning_rate": 5.439631293017652e-06, + "loss": 0.0043, + "step": 42820 + }, + { + "epoch": 13.22, + "learning_rate": 5.439186213064125e-06, + "loss": 0.0034, + "step": 42821 + }, + { + "epoch": 13.22, + "learning_rate": 5.438741144518025e-06, + "loss": 0.0039, + "step": 42822 + }, + { + "epoch": 13.22, + "learning_rate": 5.438296087380463e-06, + "loss": 0.0048, + "step": 42823 + }, + { + "epoch": 13.22, + "learning_rate": 5.437851041652552e-06, + "loss": 0.0037, + "step": 42824 + }, + { + "epoch": 13.23, + "learning_rate": 5.437406007335413e-06, + "loss": 0.0033, + "step": 42825 + }, + { + "epoch": 13.23, + "learning_rate": 5.436960984430149e-06, + "loss": 0.0049, + "step": 42826 + }, + { + "epoch": 13.23, + "learning_rate": 5.436515972937883e-06, + "loss": 0.0035, + "step": 42827 + }, + { + "epoch": 13.23, + "learning_rate": 5.436070972859722e-06, + "loss": 0.0038, + "step": 42828 + }, + { + "epoch": 13.23, + "learning_rate": 5.435625984196775e-06, + "loss": 0.0049, + "step": 42829 + }, + { + "epoch": 13.23, + "learning_rate": 5.435181006950162e-06, + "loss": 0.0044, + "step": 42830 + }, + { + "epoch": 13.23, + "learning_rate": 5.434736041120996e-06, + "loss": 0.004, + "step": 42831 + }, + { + "epoch": 13.23, + "learning_rate": 5.4342910867103894e-06, + "loss": 0.0045, + "step": 42832 + }, + { + "epoch": 13.23, + "learning_rate": 5.4338461437194475e-06, + "loss": 0.0046, + "step": 42833 + }, + { + "epoch": 13.23, + "learning_rate": 5.4334012121492964e-06, + "loss": 0.0042, + "step": 42834 + }, + { + "epoch": 13.23, + "learning_rate": 5.432956292001035e-06, + "loss": 0.0039, + "step": 42835 + }, + { + "epoch": 13.23, + "learning_rate": 5.432511383275783e-06, + "loss": 0.0069, + "step": 42836 + }, + { + "epoch": 13.23, + "learning_rate": 5.432066485974663e-06, + "loss": 0.0046, + "step": 42837 + }, + { + "epoch": 13.23, + "learning_rate": 5.4316216000987685e-06, + "loss": 0.004, + "step": 42838 + }, + { + "epoch": 13.23, + "learning_rate": 5.431176725649221e-06, + "loss": 0.0045, + "step": 42839 + }, + { + "epoch": 13.23, + "learning_rate": 5.430731862627139e-06, + "loss": 0.0057, + "step": 42840 + }, + { + "epoch": 13.23, + "learning_rate": 5.430287011033626e-06, + "loss": 0.0043, + "step": 42841 + }, + { + "epoch": 13.23, + "learning_rate": 5.4298421708698016e-06, + "loss": 0.0042, + "step": 42842 + }, + { + "epoch": 13.23, + "learning_rate": 5.429397342136776e-06, + "loss": 0.0042, + "step": 42843 + }, + { + "epoch": 13.23, + "learning_rate": 5.4289525248356575e-06, + "loss": 0.004, + "step": 42844 + }, + { + "epoch": 13.23, + "learning_rate": 5.428507718967562e-06, + "loss": 0.0044, + "step": 42845 + }, + { + "epoch": 13.23, + "learning_rate": 5.428062924533608e-06, + "loss": 0.0048, + "step": 42846 + }, + { + "epoch": 13.23, + "learning_rate": 5.4276181415349004e-06, + "loss": 0.0038, + "step": 42847 + }, + { + "epoch": 13.23, + "learning_rate": 5.427173369972551e-06, + "loss": 0.005, + "step": 42848 + }, + { + "epoch": 13.23, + "learning_rate": 5.4267286098476775e-06, + "loss": 0.0045, + "step": 42849 + }, + { + "epoch": 13.23, + "learning_rate": 5.4262838611613876e-06, + "loss": 0.0042, + "step": 42850 + }, + { + "epoch": 13.23, + "learning_rate": 5.425839123914796e-06, + "loss": 0.0038, + "step": 42851 + }, + { + "epoch": 13.23, + "learning_rate": 5.425394398109018e-06, + "loss": 0.0039, + "step": 42852 + }, + { + "epoch": 13.23, + "learning_rate": 5.424949683745164e-06, + "loss": 0.0055, + "step": 42853 + }, + { + "epoch": 13.23, + "learning_rate": 5.424504980824341e-06, + "loss": 0.0044, + "step": 42854 + }, + { + "epoch": 13.23, + "learning_rate": 5.424060289347669e-06, + "loss": 0.0039, + "step": 42855 + }, + { + "epoch": 13.23, + "learning_rate": 5.423615609316253e-06, + "loss": 0.0059, + "step": 42856 + }, + { + "epoch": 13.24, + "learning_rate": 5.423170940731213e-06, + "loss": 0.0055, + "step": 42857 + }, + { + "epoch": 13.24, + "learning_rate": 5.4227262835936536e-06, + "loss": 0.0037, + "step": 42858 + }, + { + "epoch": 13.24, + "learning_rate": 5.422281637904694e-06, + "loss": 0.0042, + "step": 42859 + }, + { + "epoch": 13.24, + "learning_rate": 5.42183700366544e-06, + "loss": 0.0045, + "step": 42860 + }, + { + "epoch": 13.24, + "learning_rate": 5.421392380877005e-06, + "loss": 0.0039, + "step": 42861 + }, + { + "epoch": 13.24, + "learning_rate": 5.420947769540508e-06, + "loss": 0.0042, + "step": 42862 + }, + { + "epoch": 13.24, + "learning_rate": 5.420503169657055e-06, + "loss": 0.0053, + "step": 42863 + }, + { + "epoch": 13.24, + "learning_rate": 5.4200585812277566e-06, + "loss": 0.005, + "step": 42864 + }, + { + "epoch": 13.24, + "learning_rate": 5.41961400425373e-06, + "loss": 0.0048, + "step": 42865 + }, + { + "epoch": 13.24, + "learning_rate": 5.4191694387360784e-06, + "loss": 0.0046, + "step": 42866 + }, + { + "epoch": 13.24, + "learning_rate": 5.418724884675926e-06, + "loss": 0.005, + "step": 42867 + }, + { + "epoch": 13.24, + "learning_rate": 5.418280342074377e-06, + "loss": 0.0046, + "step": 42868 + }, + { + "epoch": 13.24, + "learning_rate": 5.417835810932541e-06, + "loss": 0.0043, + "step": 42869 + }, + { + "epoch": 13.24, + "learning_rate": 5.417391291251532e-06, + "loss": 0.0048, + "step": 42870 + }, + { + "epoch": 13.24, + "learning_rate": 5.416946783032468e-06, + "loss": 0.0038, + "step": 42871 + }, + { + "epoch": 13.24, + "learning_rate": 5.4165022862764535e-06, + "loss": 0.0039, + "step": 42872 + }, + { + "epoch": 13.24, + "learning_rate": 5.416057800984606e-06, + "loss": 0.0053, + "step": 42873 + }, + { + "epoch": 13.24, + "learning_rate": 5.4156133271580335e-06, + "loss": 0.0047, + "step": 42874 + }, + { + "epoch": 13.24, + "learning_rate": 5.415168864797844e-06, + "loss": 0.0036, + "step": 42875 + }, + { + "epoch": 13.24, + "learning_rate": 5.414724413905155e-06, + "loss": 0.0046, + "step": 42876 + }, + { + "epoch": 13.24, + "learning_rate": 5.414279974481078e-06, + "loss": 0.0041, + "step": 42877 + }, + { + "epoch": 13.24, + "learning_rate": 5.413835546526725e-06, + "loss": 0.004, + "step": 42878 + }, + { + "epoch": 13.24, + "learning_rate": 5.413391130043201e-06, + "loss": 0.004, + "step": 42879 + }, + { + "epoch": 13.24, + "learning_rate": 5.412946725031627e-06, + "loss": 0.0048, + "step": 42880 + }, + { + "epoch": 13.24, + "learning_rate": 5.412502331493105e-06, + "loss": 0.0035, + "step": 42881 + }, + { + "epoch": 13.24, + "learning_rate": 5.412057949428752e-06, + "loss": 0.0043, + "step": 42882 + }, + { + "epoch": 13.24, + "learning_rate": 5.411613578839683e-06, + "loss": 0.0042, + "step": 42883 + }, + { + "epoch": 13.24, + "learning_rate": 5.4111692197270035e-06, + "loss": 0.0047, + "step": 42884 + }, + { + "epoch": 13.24, + "learning_rate": 5.4107248720918245e-06, + "loss": 0.0036, + "step": 42885 + }, + { + "epoch": 13.24, + "learning_rate": 5.410280535935264e-06, + "loss": 0.0036, + "step": 42886 + }, + { + "epoch": 13.24, + "learning_rate": 5.4098362112584234e-06, + "loss": 0.0055, + "step": 42887 + }, + { + "epoch": 13.24, + "learning_rate": 5.409391898062425e-06, + "loss": 0.0043, + "step": 42888 + }, + { + "epoch": 13.24, + "learning_rate": 5.4089475963483705e-06, + "loss": 0.0033, + "step": 42889 + }, + { + "epoch": 13.25, + "learning_rate": 5.408503306117378e-06, + "loss": 0.0053, + "step": 42890 + }, + { + "epoch": 13.25, + "learning_rate": 5.408059027370554e-06, + "loss": 0.0037, + "step": 42891 + }, + { + "epoch": 13.25, + "learning_rate": 5.407614760109011e-06, + "loss": 0.0052, + "step": 42892 + }, + { + "epoch": 13.25, + "learning_rate": 5.407170504333865e-06, + "loss": 0.0038, + "step": 42893 + }, + { + "epoch": 13.25, + "learning_rate": 5.4067262600462245e-06, + "loss": 0.0038, + "step": 42894 + }, + { + "epoch": 13.25, + "learning_rate": 5.406282027247194e-06, + "loss": 0.0062, + "step": 42895 + }, + { + "epoch": 13.25, + "learning_rate": 5.405837805937895e-06, + "loss": 0.0059, + "step": 42896 + }, + { + "epoch": 13.25, + "learning_rate": 5.405393596119428e-06, + "loss": 0.005, + "step": 42897 + }, + { + "epoch": 13.25, + "learning_rate": 5.404949397792916e-06, + "loss": 0.0038, + "step": 42898 + }, + { + "epoch": 13.25, + "learning_rate": 5.404505210959461e-06, + "loss": 0.004, + "step": 42899 + }, + { + "epoch": 13.25, + "learning_rate": 5.404061035620174e-06, + "loss": 0.0039, + "step": 42900 + }, + { + "epoch": 13.25, + "learning_rate": 5.4036168717761695e-06, + "loss": 0.0044, + "step": 42901 + }, + { + "epoch": 13.25, + "learning_rate": 5.40317271942856e-06, + "loss": 0.0042, + "step": 42902 + }, + { + "epoch": 13.25, + "learning_rate": 5.402728578578451e-06, + "loss": 0.0046, + "step": 42903 + }, + { + "epoch": 13.25, + "learning_rate": 5.402284449226959e-06, + "loss": 0.0041, + "step": 42904 + }, + { + "epoch": 13.25, + "learning_rate": 5.401840331375194e-06, + "loss": 0.0032, + "step": 42905 + }, + { + "epoch": 13.25, + "learning_rate": 5.401396225024259e-06, + "loss": 0.005, + "step": 42906 + }, + { + "epoch": 13.25, + "learning_rate": 5.400952130175272e-06, + "loss": 0.0042, + "step": 42907 + }, + { + "epoch": 13.25, + "learning_rate": 5.400508046829346e-06, + "loss": 0.004, + "step": 42908 + }, + { + "epoch": 13.25, + "learning_rate": 5.400063974987588e-06, + "loss": 0.007, + "step": 42909 + }, + { + "epoch": 13.25, + "learning_rate": 5.3996199146511066e-06, + "loss": 0.0044, + "step": 42910 + }, + { + "epoch": 13.25, + "learning_rate": 5.399175865821017e-06, + "loss": 0.0038, + "step": 42911 + }, + { + "epoch": 13.25, + "learning_rate": 5.398731828498425e-06, + "loss": 0.0053, + "step": 42912 + }, + { + "epoch": 13.25, + "learning_rate": 5.398287802684443e-06, + "loss": 0.0045, + "step": 42913 + }, + { + "epoch": 13.25, + "learning_rate": 5.397843788380186e-06, + "loss": 0.0052, + "step": 42914 + }, + { + "epoch": 13.25, + "learning_rate": 5.397399785586763e-06, + "loss": 0.0054, + "step": 42915 + }, + { + "epoch": 13.25, + "learning_rate": 5.396955794305276e-06, + "loss": 0.0038, + "step": 42916 + }, + { + "epoch": 13.25, + "learning_rate": 5.396511814536849e-06, + "loss": 0.0049, + "step": 42917 + }, + { + "epoch": 13.25, + "learning_rate": 5.39606784628258e-06, + "loss": 0.0036, + "step": 42918 + }, + { + "epoch": 13.25, + "learning_rate": 5.395623889543589e-06, + "loss": 0.0034, + "step": 42919 + }, + { + "epoch": 13.25, + "learning_rate": 5.395179944320983e-06, + "loss": 0.0055, + "step": 42920 + }, + { + "epoch": 13.25, + "learning_rate": 5.394736010615866e-06, + "loss": 0.004, + "step": 42921 + }, + { + "epoch": 13.26, + "learning_rate": 5.394292088429357e-06, + "loss": 0.0046, + "step": 42922 + }, + { + "epoch": 13.26, + "learning_rate": 5.393848177762561e-06, + "loss": 0.004, + "step": 42923 + }, + { + "epoch": 13.26, + "learning_rate": 5.393404278616596e-06, + "loss": 0.0044, + "step": 42924 + }, + { + "epoch": 13.26, + "learning_rate": 5.392960390992568e-06, + "loss": 0.0049, + "step": 42925 + }, + { + "epoch": 13.26, + "learning_rate": 5.392516514891582e-06, + "loss": 0.0034, + "step": 42926 + }, + { + "epoch": 13.26, + "learning_rate": 5.392072650314755e-06, + "loss": 0.0046, + "step": 42927 + }, + { + "epoch": 13.26, + "learning_rate": 5.391628797263192e-06, + "loss": 0.0051, + "step": 42928 + }, + { + "epoch": 13.26, + "learning_rate": 5.3911849557380095e-06, + "loss": 0.0044, + "step": 42929 + }, + { + "epoch": 13.26, + "learning_rate": 5.390741125740314e-06, + "loss": 0.0041, + "step": 42930 + }, + { + "epoch": 13.26, + "learning_rate": 5.390297307271213e-06, + "loss": 0.0046, + "step": 42931 + }, + { + "epoch": 13.26, + "learning_rate": 5.389853500331817e-06, + "loss": 0.0048, + "step": 42932 + }, + { + "epoch": 13.26, + "learning_rate": 5.389409704923243e-06, + "loss": 0.0041, + "step": 42933 + }, + { + "epoch": 13.26, + "learning_rate": 5.388965921046593e-06, + "loss": 0.005, + "step": 42934 + }, + { + "epoch": 13.26, + "learning_rate": 5.388522148702984e-06, + "loss": 0.0042, + "step": 42935 + }, + { + "epoch": 13.26, + "learning_rate": 5.38807838789352e-06, + "loss": 0.0042, + "step": 42936 + }, + { + "epoch": 13.26, + "learning_rate": 5.387634638619313e-06, + "loss": 0.0049, + "step": 42937 + }, + { + "epoch": 13.26, + "learning_rate": 5.387190900881469e-06, + "loss": 0.0042, + "step": 42938 + }, + { + "epoch": 13.26, + "learning_rate": 5.386747174681108e-06, + "loss": 0.0031, + "step": 42939 + }, + { + "epoch": 13.26, + "learning_rate": 5.386303460019334e-06, + "loss": 0.0047, + "step": 42940 + }, + { + "epoch": 13.26, + "learning_rate": 5.385859756897252e-06, + "loss": 0.0052, + "step": 42941 + }, + { + "epoch": 13.26, + "learning_rate": 5.38541606531598e-06, + "loss": 0.006, + "step": 42942 + }, + { + "epoch": 13.26, + "learning_rate": 5.384972385276621e-06, + "loss": 0.0041, + "step": 42943 + }, + { + "epoch": 13.26, + "learning_rate": 5.384528716780289e-06, + "loss": 0.0043, + "step": 42944 + }, + { + "epoch": 13.26, + "learning_rate": 5.384085059828097e-06, + "loss": 0.0039, + "step": 42945 + }, + { + "epoch": 13.26, + "learning_rate": 5.383641414421143e-06, + "loss": 0.0041, + "step": 42946 + }, + { + "epoch": 13.26, + "learning_rate": 5.3831977805605465e-06, + "loss": 0.0046, + "step": 42947 + }, + { + "epoch": 13.26, + "learning_rate": 5.382754158247416e-06, + "loss": 0.0056, + "step": 42948 + }, + { + "epoch": 13.26, + "learning_rate": 5.382310547482857e-06, + "loss": 0.0051, + "step": 42949 + }, + { + "epoch": 13.26, + "learning_rate": 5.381866948267984e-06, + "loss": 0.0048, + "step": 42950 + }, + { + "epoch": 13.26, + "learning_rate": 5.381423360603905e-06, + "loss": 0.0046, + "step": 42951 + }, + { + "epoch": 13.26, + "learning_rate": 5.380979784491725e-06, + "loss": 0.0047, + "step": 42952 + }, + { + "epoch": 13.26, + "learning_rate": 5.380536219932555e-06, + "loss": 0.0044, + "step": 42953 + }, + { + "epoch": 13.27, + "learning_rate": 5.380092666927508e-06, + "loss": 0.0046, + "step": 42954 + }, + { + "epoch": 13.27, + "learning_rate": 5.3796491254777e-06, + "loss": 0.0053, + "step": 42955 + }, + { + "epoch": 13.27, + "learning_rate": 5.3792055955842225e-06, + "loss": 0.0051, + "step": 42956 + }, + { + "epoch": 13.27, + "learning_rate": 5.378762077248196e-06, + "loss": 0.0052, + "step": 42957 + }, + { + "epoch": 13.27, + "learning_rate": 5.378318570470733e-06, + "loss": 0.0049, + "step": 42958 + }, + { + "epoch": 13.27, + "learning_rate": 5.377875075252933e-06, + "loss": 0.006, + "step": 42959 + }, + { + "epoch": 13.27, + "learning_rate": 5.377431591595915e-06, + "loss": 0.0039, + "step": 42960 + }, + { + "epoch": 13.27, + "learning_rate": 5.376988119500783e-06, + "loss": 0.0046, + "step": 42961 + }, + { + "epoch": 13.27, + "learning_rate": 5.376544658968644e-06, + "loss": 0.0036, + "step": 42962 + }, + { + "epoch": 13.27, + "learning_rate": 5.376101210000611e-06, + "loss": 0.0048, + "step": 42963 + }, + { + "epoch": 13.27, + "learning_rate": 5.375657772597793e-06, + "loss": 0.0043, + "step": 42964 + }, + { + "epoch": 13.27, + "learning_rate": 5.375214346761301e-06, + "loss": 0.0052, + "step": 42965 + }, + { + "epoch": 13.27, + "learning_rate": 5.374770932492237e-06, + "loss": 0.0063, + "step": 42966 + }, + { + "epoch": 13.27, + "learning_rate": 5.374327529791717e-06, + "loss": 0.0045, + "step": 42967 + }, + { + "epoch": 13.27, + "learning_rate": 5.373884138660845e-06, + "loss": 0.005, + "step": 42968 + }, + { + "epoch": 13.27, + "learning_rate": 5.373440759100732e-06, + "loss": 0.0071, + "step": 42969 + }, + { + "epoch": 13.27, + "learning_rate": 5.3729973911124915e-06, + "loss": 0.0103, + "step": 42970 + }, + { + "epoch": 13.27, + "learning_rate": 5.372554034697228e-06, + "loss": 0.0045, + "step": 42971 + }, + { + "epoch": 13.27, + "learning_rate": 5.372110689856048e-06, + "loss": 0.0042, + "step": 42972 + }, + { + "epoch": 13.27, + "learning_rate": 5.371667356590066e-06, + "loss": 0.006, + "step": 42973 + }, + { + "epoch": 13.27, + "learning_rate": 5.371224034900386e-06, + "loss": 0.0038, + "step": 42974 + }, + { + "epoch": 13.27, + "learning_rate": 5.370780724788117e-06, + "loss": 0.0056, + "step": 42975 + }, + { + "epoch": 13.27, + "learning_rate": 5.370337426254379e-06, + "loss": 0.0051, + "step": 42976 + }, + { + "epoch": 13.27, + "learning_rate": 5.369894139300262e-06, + "loss": 0.0047, + "step": 42977 + }, + { + "epoch": 13.27, + "learning_rate": 5.369450863926886e-06, + "loss": 0.004, + "step": 42978 + }, + { + "epoch": 13.27, + "learning_rate": 5.369007600135361e-06, + "loss": 0.0052, + "step": 42979 + }, + { + "epoch": 13.27, + "learning_rate": 5.368564347926788e-06, + "loss": 0.0046, + "step": 42980 + }, + { + "epoch": 13.27, + "learning_rate": 5.368121107302286e-06, + "loss": 0.004, + "step": 42981 + }, + { + "epoch": 13.27, + "learning_rate": 5.367677878262955e-06, + "loss": 0.0066, + "step": 42982 + }, + { + "epoch": 13.27, + "learning_rate": 5.367234660809906e-06, + "loss": 0.0039, + "step": 42983 + }, + { + "epoch": 13.27, + "learning_rate": 5.366791454944247e-06, + "loss": 0.0039, + "step": 42984 + }, + { + "epoch": 13.27, + "learning_rate": 5.36634826066709e-06, + "loss": 0.0046, + "step": 42985 + }, + { + "epoch": 13.27, + "learning_rate": 5.365905077979543e-06, + "loss": 0.005, + "step": 42986 + }, + { + "epoch": 13.28, + "learning_rate": 5.365461906882708e-06, + "loss": 0.0048, + "step": 42987 + }, + { + "epoch": 13.28, + "learning_rate": 5.365018747377697e-06, + "loss": 0.0044, + "step": 42988 + }, + { + "epoch": 13.28, + "learning_rate": 5.3645755994656246e-06, + "loss": 0.0034, + "step": 42989 + }, + { + "epoch": 13.28, + "learning_rate": 5.36413246314759e-06, + "loss": 0.005, + "step": 42990 + }, + { + "epoch": 13.28, + "learning_rate": 5.363689338424709e-06, + "loss": 0.0054, + "step": 42991 + }, + { + "epoch": 13.28, + "learning_rate": 5.363246225298088e-06, + "loss": 0.0039, + "step": 42992 + }, + { + "epoch": 13.28, + "learning_rate": 5.362803123768828e-06, + "loss": 0.0048, + "step": 42993 + }, + { + "epoch": 13.28, + "learning_rate": 5.362360033838044e-06, + "loss": 0.0043, + "step": 42994 + }, + { + "epoch": 13.28, + "learning_rate": 5.361916955506848e-06, + "loss": 0.0039, + "step": 42995 + }, + { + "epoch": 13.28, + "learning_rate": 5.3614738887763425e-06, + "loss": 0.0044, + "step": 42996 + }, + { + "epoch": 13.28, + "learning_rate": 5.361030833647633e-06, + "loss": 0.0044, + "step": 42997 + }, + { + "epoch": 13.28, + "learning_rate": 5.360587790121837e-06, + "loss": 0.0041, + "step": 42998 + }, + { + "epoch": 13.28, + "learning_rate": 5.360144758200052e-06, + "loss": 0.005, + "step": 42999 + }, + { + "epoch": 13.28, + "learning_rate": 5.359701737883391e-06, + "loss": 0.005, + "step": 43000 + }, + { + "epoch": 13.28, + "learning_rate": 5.359258729172967e-06, + "loss": 0.0045, + "step": 43001 + }, + { + "epoch": 13.28, + "learning_rate": 5.358815732069883e-06, + "loss": 0.0044, + "step": 43002 + }, + { + "epoch": 13.28, + "learning_rate": 5.358372746575243e-06, + "loss": 0.004, + "step": 43003 + }, + { + "epoch": 13.28, + "learning_rate": 5.357929772690163e-06, + "loss": 0.0055, + "step": 43004 + }, + { + "epoch": 13.28, + "learning_rate": 5.357486810415744e-06, + "loss": 0.0051, + "step": 43005 + }, + { + "epoch": 13.28, + "learning_rate": 5.357043859753102e-06, + "loss": 0.0041, + "step": 43006 + }, + { + "epoch": 13.28, + "learning_rate": 5.3566009207033385e-06, + "loss": 0.0049, + "step": 43007 + }, + { + "epoch": 13.28, + "learning_rate": 5.35615799326756e-06, + "loss": 0.0045, + "step": 43008 + }, + { + "epoch": 13.28, + "learning_rate": 5.3557150774468766e-06, + "loss": 0.0062, + "step": 43009 + }, + { + "epoch": 13.28, + "learning_rate": 5.355272173242402e-06, + "loss": 0.0033, + "step": 43010 + }, + { + "epoch": 13.28, + "learning_rate": 5.354829280655234e-06, + "loss": 0.0052, + "step": 43011 + }, + { + "epoch": 13.28, + "learning_rate": 5.35438639968649e-06, + "loss": 0.0042, + "step": 43012 + }, + { + "epoch": 13.28, + "learning_rate": 5.353943530337271e-06, + "loss": 0.005, + "step": 43013 + }, + { + "epoch": 13.28, + "learning_rate": 5.353500672608685e-06, + "loss": 0.0044, + "step": 43014 + }, + { + "epoch": 13.28, + "learning_rate": 5.35305782650184e-06, + "loss": 0.0046, + "step": 43015 + }, + { + "epoch": 13.28, + "learning_rate": 5.352614992017848e-06, + "loss": 0.0051, + "step": 43016 + }, + { + "epoch": 13.28, + "learning_rate": 5.352172169157815e-06, + "loss": 0.0051, + "step": 43017 + }, + { + "epoch": 13.28, + "learning_rate": 5.351729357922844e-06, + "loss": 0.0054, + "step": 43018 + }, + { + "epoch": 13.29, + "learning_rate": 5.351286558314048e-06, + "loss": 0.005, + "step": 43019 + }, + { + "epoch": 13.29, + "learning_rate": 5.350843770332528e-06, + "loss": 0.0041, + "step": 43020 + }, + { + "epoch": 13.29, + "learning_rate": 5.350400993979396e-06, + "loss": 0.0041, + "step": 43021 + }, + { + "epoch": 13.29, + "learning_rate": 5.349958229255765e-06, + "loss": 0.0043, + "step": 43022 + }, + { + "epoch": 13.29, + "learning_rate": 5.3495154761627345e-06, + "loss": 0.005, + "step": 43023 + }, + { + "epoch": 13.29, + "learning_rate": 5.349072734701411e-06, + "loss": 0.0037, + "step": 43024 + }, + { + "epoch": 13.29, + "learning_rate": 5.348630004872904e-06, + "loss": 0.0039, + "step": 43025 + }, + { + "epoch": 13.29, + "learning_rate": 5.348187286678326e-06, + "loss": 0.0048, + "step": 43026 + }, + { + "epoch": 13.29, + "learning_rate": 5.34774458011878e-06, + "loss": 0.0057, + "step": 43027 + }, + { + "epoch": 13.29, + "learning_rate": 5.347301885195369e-06, + "loss": 0.0048, + "step": 43028 + }, + { + "epoch": 13.29, + "learning_rate": 5.3468592019092095e-06, + "loss": 0.0051, + "step": 43029 + }, + { + "epoch": 13.29, + "learning_rate": 5.3464165302614e-06, + "loss": 0.0053, + "step": 43030 + }, + { + "epoch": 13.29, + "learning_rate": 5.345973870253051e-06, + "loss": 0.0042, + "step": 43031 + }, + { + "epoch": 13.29, + "learning_rate": 5.345531221885274e-06, + "loss": 0.0045, + "step": 43032 + }, + { + "epoch": 13.29, + "learning_rate": 5.345088585159173e-06, + "loss": 0.0043, + "step": 43033 + }, + { + "epoch": 13.29, + "learning_rate": 5.34464596007585e-06, + "loss": 0.0065, + "step": 43034 + }, + { + "epoch": 13.29, + "learning_rate": 5.344203346636419e-06, + "loss": 0.0048, + "step": 43035 + }, + { + "epoch": 13.29, + "learning_rate": 5.343760744841982e-06, + "loss": 0.0044, + "step": 43036 + }, + { + "epoch": 13.29, + "learning_rate": 5.343318154693653e-06, + "loss": 0.004, + "step": 43037 + }, + { + "epoch": 13.29, + "learning_rate": 5.3428755761925344e-06, + "loss": 0.0047, + "step": 43038 + }, + { + "epoch": 13.29, + "learning_rate": 5.342433009339729e-06, + "loss": 0.005, + "step": 43039 + }, + { + "epoch": 13.29, + "learning_rate": 5.341990454136348e-06, + "loss": 0.0051, + "step": 43040 + }, + { + "epoch": 13.29, + "learning_rate": 5.341547910583503e-06, + "loss": 0.0037, + "step": 43041 + }, + { + "epoch": 13.29, + "learning_rate": 5.341105378682292e-06, + "loss": 0.004, + "step": 43042 + }, + { + "epoch": 13.29, + "learning_rate": 5.34066285843383e-06, + "loss": 0.0042, + "step": 43043 + }, + { + "epoch": 13.29, + "learning_rate": 5.34022034983922e-06, + "loss": 0.0056, + "step": 43044 + }, + { + "epoch": 13.29, + "learning_rate": 5.339777852899566e-06, + "loss": 0.0038, + "step": 43045 + }, + { + "epoch": 13.29, + "learning_rate": 5.339335367615977e-06, + "loss": 0.0042, + "step": 43046 + }, + { + "epoch": 13.29, + "learning_rate": 5.338892893989564e-06, + "loss": 0.0052, + "step": 43047 + }, + { + "epoch": 13.29, + "learning_rate": 5.3384504320214295e-06, + "loss": 0.0039, + "step": 43048 + }, + { + "epoch": 13.29, + "learning_rate": 5.338007981712677e-06, + "loss": 0.0049, + "step": 43049 + }, + { + "epoch": 13.29, + "learning_rate": 5.3375655430644215e-06, + "loss": 0.0052, + "step": 43050 + }, + { + "epoch": 13.29, + "learning_rate": 5.337123116077761e-06, + "loss": 0.005, + "step": 43051 + }, + { + "epoch": 13.3, + "learning_rate": 5.336680700753804e-06, + "loss": 0.0042, + "step": 43052 + }, + { + "epoch": 13.3, + "learning_rate": 5.336238297093665e-06, + "loss": 0.0047, + "step": 43053 + }, + { + "epoch": 13.3, + "learning_rate": 5.335795905098444e-06, + "loss": 0.0049, + "step": 43054 + }, + { + "epoch": 13.3, + "learning_rate": 5.335353524769244e-06, + "loss": 0.0053, + "step": 43055 + }, + { + "epoch": 13.3, + "learning_rate": 5.3349111561071765e-06, + "loss": 0.0058, + "step": 43056 + }, + { + "epoch": 13.3, + "learning_rate": 5.33446879911335e-06, + "loss": 0.0047, + "step": 43057 + }, + { + "epoch": 13.3, + "learning_rate": 5.33402645378887e-06, + "loss": 0.0058, + "step": 43058 + }, + { + "epoch": 13.3, + "learning_rate": 5.333584120134835e-06, + "loss": 0.004, + "step": 43059 + }, + { + "epoch": 13.3, + "learning_rate": 5.333141798152362e-06, + "loss": 0.0041, + "step": 43060 + }, + { + "epoch": 13.3, + "learning_rate": 5.332699487842547e-06, + "loss": 0.0041, + "step": 43061 + }, + { + "epoch": 13.3, + "learning_rate": 5.332257189206504e-06, + "loss": 0.0049, + "step": 43062 + }, + { + "epoch": 13.3, + "learning_rate": 5.33181490224534e-06, + "loss": 0.0042, + "step": 43063 + }, + { + "epoch": 13.3, + "learning_rate": 5.331372626960158e-06, + "loss": 0.0036, + "step": 43064 + }, + { + "epoch": 13.3, + "learning_rate": 5.330930363352062e-06, + "loss": 0.004, + "step": 43065 + }, + { + "epoch": 13.3, + "learning_rate": 5.330488111422163e-06, + "loss": 0.0054, + "step": 43066 + }, + { + "epoch": 13.3, + "learning_rate": 5.330045871171562e-06, + "loss": 0.0053, + "step": 43067 + }, + { + "epoch": 13.3, + "learning_rate": 5.329603642601371e-06, + "loss": 0.0036, + "step": 43068 + }, + { + "epoch": 13.3, + "learning_rate": 5.329161425712694e-06, + "loss": 0.0047, + "step": 43069 + }, + { + "epoch": 13.3, + "learning_rate": 5.328719220506633e-06, + "loss": 0.0038, + "step": 43070 + }, + { + "epoch": 13.3, + "learning_rate": 5.328277026984295e-06, + "loss": 0.0032, + "step": 43071 + }, + { + "epoch": 13.3, + "learning_rate": 5.3278348451467935e-06, + "loss": 0.0042, + "step": 43072 + }, + { + "epoch": 13.3, + "learning_rate": 5.327392674995225e-06, + "loss": 0.0042, + "step": 43073 + }, + { + "epoch": 13.3, + "learning_rate": 5.326950516530705e-06, + "loss": 0.0044, + "step": 43074 + }, + { + "epoch": 13.3, + "learning_rate": 5.326508369754332e-06, + "loss": 0.0048, + "step": 43075 + }, + { + "epoch": 13.3, + "learning_rate": 5.326066234667211e-06, + "loss": 0.0044, + "step": 43076 + }, + { + "epoch": 13.3, + "learning_rate": 5.325624111270451e-06, + "loss": 0.0051, + "step": 43077 + }, + { + "epoch": 13.3, + "learning_rate": 5.3251819995651614e-06, + "loss": 0.0049, + "step": 43078 + }, + { + "epoch": 13.3, + "learning_rate": 5.324739899552443e-06, + "loss": 0.0032, + "step": 43079 + }, + { + "epoch": 13.3, + "learning_rate": 5.3242978112334006e-06, + "loss": 0.0047, + "step": 43080 + }, + { + "epoch": 13.3, + "learning_rate": 5.323855734609144e-06, + "loss": 0.0045, + "step": 43081 + }, + { + "epoch": 13.3, + "learning_rate": 5.323413669680776e-06, + "loss": 0.0038, + "step": 43082 + }, + { + "epoch": 13.3, + "learning_rate": 5.322971616449402e-06, + "loss": 0.0053, + "step": 43083 + }, + { + "epoch": 13.31, + "learning_rate": 5.322529574916137e-06, + "loss": 0.0048, + "step": 43084 + }, + { + "epoch": 13.31, + "learning_rate": 5.322087545082071e-06, + "loss": 0.0042, + "step": 43085 + }, + { + "epoch": 13.31, + "learning_rate": 5.321645526948315e-06, + "loss": 0.0037, + "step": 43086 + }, + { + "epoch": 13.31, + "learning_rate": 5.32120352051598e-06, + "loss": 0.0056, + "step": 43087 + }, + { + "epoch": 13.31, + "learning_rate": 5.320761525786171e-06, + "loss": 0.004, + "step": 43088 + }, + { + "epoch": 13.31, + "learning_rate": 5.320319542759991e-06, + "loss": 0.0041, + "step": 43089 + }, + { + "epoch": 13.31, + "learning_rate": 5.319877571438541e-06, + "loss": 0.0054, + "step": 43090 + }, + { + "epoch": 13.31, + "learning_rate": 5.319435611822935e-06, + "loss": 0.0046, + "step": 43091 + }, + { + "epoch": 13.31, + "learning_rate": 5.318993663914271e-06, + "loss": 0.0037, + "step": 43092 + }, + { + "epoch": 13.31, + "learning_rate": 5.318551727713657e-06, + "loss": 0.0048, + "step": 43093 + }, + { + "epoch": 13.31, + "learning_rate": 5.3181098032222064e-06, + "loss": 0.0053, + "step": 43094 + }, + { + "epoch": 13.31, + "learning_rate": 5.3176678904410095e-06, + "loss": 0.0049, + "step": 43095 + }, + { + "epoch": 13.31, + "learning_rate": 5.31722598937118e-06, + "loss": 0.0054, + "step": 43096 + }, + { + "epoch": 13.31, + "learning_rate": 5.316784100013825e-06, + "loss": 0.004, + "step": 43097 + }, + { + "epoch": 13.31, + "learning_rate": 5.316342222370044e-06, + "loss": 0.0046, + "step": 43098 + }, + { + "epoch": 13.31, + "learning_rate": 5.315900356440949e-06, + "loss": 0.0038, + "step": 43099 + }, + { + "epoch": 13.31, + "learning_rate": 5.315458502227642e-06, + "loss": 0.0055, + "step": 43100 + }, + { + "epoch": 13.31, + "learning_rate": 5.315016659731223e-06, + "loss": 0.0043, + "step": 43101 + }, + { + "epoch": 13.31, + "learning_rate": 5.3145748289528024e-06, + "loss": 0.0049, + "step": 43102 + }, + { + "epoch": 13.31, + "learning_rate": 5.314133009893489e-06, + "loss": 0.0051, + "step": 43103 + }, + { + "epoch": 13.31, + "learning_rate": 5.313691202554383e-06, + "loss": 0.0045, + "step": 43104 + }, + { + "epoch": 13.31, + "learning_rate": 5.313249406936585e-06, + "loss": 0.0048, + "step": 43105 + }, + { + "epoch": 13.31, + "learning_rate": 5.31280762304121e-06, + "loss": 0.0046, + "step": 43106 + }, + { + "epoch": 13.31, + "learning_rate": 5.3123658508693545e-06, + "loss": 0.0043, + "step": 43107 + }, + { + "epoch": 13.31, + "learning_rate": 5.311924090422127e-06, + "loss": 0.0038, + "step": 43108 + }, + { + "epoch": 13.31, + "learning_rate": 5.311482341700635e-06, + "loss": 0.0044, + "step": 43109 + }, + { + "epoch": 13.31, + "learning_rate": 5.311040604705983e-06, + "loss": 0.0061, + "step": 43110 + }, + { + "epoch": 13.31, + "learning_rate": 5.310598879439268e-06, + "loss": 0.0041, + "step": 43111 + }, + { + "epoch": 13.31, + "learning_rate": 5.310157165901606e-06, + "loss": 0.0049, + "step": 43112 + }, + { + "epoch": 13.31, + "learning_rate": 5.309715464094092e-06, + "loss": 0.0051, + "step": 43113 + }, + { + "epoch": 13.31, + "learning_rate": 5.309273774017838e-06, + "loss": 0.0059, + "step": 43114 + }, + { + "epoch": 13.31, + "learning_rate": 5.308832095673946e-06, + "loss": 0.0048, + "step": 43115 + }, + { + "epoch": 13.32, + "learning_rate": 5.308390429063517e-06, + "loss": 0.0055, + "step": 43116 + }, + { + "epoch": 13.32, + "learning_rate": 5.307948774187659e-06, + "loss": 0.0036, + "step": 43117 + }, + { + "epoch": 13.32, + "learning_rate": 5.3075071310474755e-06, + "loss": 0.0043, + "step": 43118 + }, + { + "epoch": 13.32, + "learning_rate": 5.3070654996440795e-06, + "loss": 0.0039, + "step": 43119 + }, + { + "epoch": 13.32, + "learning_rate": 5.306623879978566e-06, + "loss": 0.0049, + "step": 43120 + }, + { + "epoch": 13.32, + "learning_rate": 5.306182272052039e-06, + "loss": 0.0038, + "step": 43121 + }, + { + "epoch": 13.32, + "learning_rate": 5.305740675865612e-06, + "loss": 0.0044, + "step": 43122 + }, + { + "epoch": 13.32, + "learning_rate": 5.305299091420377e-06, + "loss": 0.0055, + "step": 43123 + }, + { + "epoch": 13.32, + "learning_rate": 5.30485751871745e-06, + "loss": 0.0037, + "step": 43124 + }, + { + "epoch": 13.32, + "learning_rate": 5.304415957757932e-06, + "loss": 0.0043, + "step": 43125 + }, + { + "epoch": 13.32, + "learning_rate": 5.303974408542921e-06, + "loss": 0.0054, + "step": 43126 + }, + { + "epoch": 13.32, + "learning_rate": 5.303532871073527e-06, + "loss": 0.0072, + "step": 43127 + }, + { + "epoch": 13.32, + "learning_rate": 5.303091345350857e-06, + "loss": 0.0046, + "step": 43128 + }, + { + "epoch": 13.32, + "learning_rate": 5.30264983137601e-06, + "loss": 0.0046, + "step": 43129 + }, + { + "epoch": 13.32, + "learning_rate": 5.302208329150095e-06, + "loss": 0.0055, + "step": 43130 + }, + { + "epoch": 13.32, + "learning_rate": 5.301766838674214e-06, + "loss": 0.0038, + "step": 43131 + }, + { + "epoch": 13.32, + "learning_rate": 5.301325359949468e-06, + "loss": 0.0047, + "step": 43132 + }, + { + "epoch": 13.32, + "learning_rate": 5.300883892976963e-06, + "loss": 0.0046, + "step": 43133 + }, + { + "epoch": 13.32, + "learning_rate": 5.300442437757809e-06, + "loss": 0.0038, + "step": 43134 + }, + { + "epoch": 13.32, + "learning_rate": 5.300000994293105e-06, + "loss": 0.0042, + "step": 43135 + }, + { + "epoch": 13.32, + "learning_rate": 5.299559562583953e-06, + "loss": 0.0063, + "step": 43136 + }, + { + "epoch": 13.32, + "learning_rate": 5.299118142631463e-06, + "loss": 0.0039, + "step": 43137 + }, + { + "epoch": 13.32, + "learning_rate": 5.298676734436732e-06, + "loss": 0.0039, + "step": 43138 + }, + { + "epoch": 13.32, + "learning_rate": 5.298235338000868e-06, + "loss": 0.005, + "step": 43139 + }, + { + "epoch": 13.32, + "learning_rate": 5.297793953324979e-06, + "loss": 0.0048, + "step": 43140 + }, + { + "epoch": 13.32, + "learning_rate": 5.2973525804101645e-06, + "loss": 0.0048, + "step": 43141 + }, + { + "epoch": 13.32, + "learning_rate": 5.296911219257525e-06, + "loss": 0.006, + "step": 43142 + }, + { + "epoch": 13.32, + "learning_rate": 5.296469869868173e-06, + "loss": 0.0053, + "step": 43143 + }, + { + "epoch": 13.32, + "learning_rate": 5.296028532243202e-06, + "loss": 0.0041, + "step": 43144 + }, + { + "epoch": 13.32, + "learning_rate": 5.295587206383728e-06, + "loss": 0.0052, + "step": 43145 + }, + { + "epoch": 13.32, + "learning_rate": 5.295145892290847e-06, + "loss": 0.0056, + "step": 43146 + }, + { + "epoch": 13.32, + "learning_rate": 5.29470458996566e-06, + "loss": 0.005, + "step": 43147 + }, + { + "epoch": 13.32, + "learning_rate": 5.294263299409277e-06, + "loss": 0.0051, + "step": 43148 + }, + { + "epoch": 13.33, + "learning_rate": 5.293822020622802e-06, + "loss": 0.0047, + "step": 43149 + }, + { + "epoch": 13.33, + "learning_rate": 5.293380753607334e-06, + "loss": 0.0045, + "step": 43150 + }, + { + "epoch": 13.33, + "learning_rate": 5.292939498363981e-06, + "loss": 0.0048, + "step": 43151 + }, + { + "epoch": 13.33, + "learning_rate": 5.292498254893842e-06, + "loss": 0.0035, + "step": 43152 + }, + { + "epoch": 13.33, + "learning_rate": 5.292057023198027e-06, + "loss": 0.0048, + "step": 43153 + }, + { + "epoch": 13.33, + "learning_rate": 5.291615803277632e-06, + "loss": 0.0038, + "step": 43154 + }, + { + "epoch": 13.33, + "learning_rate": 5.29117459513377e-06, + "loss": 0.0045, + "step": 43155 + }, + { + "epoch": 13.33, + "learning_rate": 5.290733398767538e-06, + "loss": 0.0058, + "step": 43156 + }, + { + "epoch": 13.33, + "learning_rate": 5.290292214180038e-06, + "loss": 0.0043, + "step": 43157 + }, + { + "epoch": 13.33, + "learning_rate": 5.289851041372373e-06, + "loss": 0.0052, + "step": 43158 + }, + { + "epoch": 13.33, + "learning_rate": 5.289409880345656e-06, + "loss": 0.004, + "step": 43159 + }, + { + "epoch": 13.33, + "learning_rate": 5.28896873110098e-06, + "loss": 0.0049, + "step": 43160 + }, + { + "epoch": 13.33, + "learning_rate": 5.288527593639456e-06, + "loss": 0.0045, + "step": 43161 + }, + { + "epoch": 13.33, + "learning_rate": 5.288086467962183e-06, + "loss": 0.005, + "step": 43162 + }, + { + "epoch": 13.33, + "learning_rate": 5.287645354070263e-06, + "loss": 0.0054, + "step": 43163 + }, + { + "epoch": 13.33, + "learning_rate": 5.287204251964801e-06, + "loss": 0.0039, + "step": 43164 + }, + { + "epoch": 13.33, + "learning_rate": 5.286763161646904e-06, + "loss": 0.0043, + "step": 43165 + }, + { + "epoch": 13.33, + "learning_rate": 5.286322083117672e-06, + "loss": 0.0048, + "step": 43166 + }, + { + "epoch": 13.33, + "learning_rate": 5.285881016378205e-06, + "loss": 0.0058, + "step": 43167 + }, + { + "epoch": 13.33, + "learning_rate": 5.285439961429612e-06, + "loss": 0.0043, + "step": 43168 + }, + { + "epoch": 13.33, + "learning_rate": 5.284998918272991e-06, + "loss": 0.0039, + "step": 43169 + }, + { + "epoch": 13.33, + "learning_rate": 5.2845578869094475e-06, + "loss": 0.0039, + "step": 43170 + }, + { + "epoch": 13.33, + "learning_rate": 5.284116867340087e-06, + "loss": 0.0052, + "step": 43171 + }, + { + "epoch": 13.33, + "learning_rate": 5.283675859566012e-06, + "loss": 0.0043, + "step": 43172 + }, + { + "epoch": 13.33, + "learning_rate": 5.28323486358832e-06, + "loss": 0.0045, + "step": 43173 + }, + { + "epoch": 13.33, + "learning_rate": 5.282793879408122e-06, + "loss": 0.0051, + "step": 43174 + }, + { + "epoch": 13.33, + "learning_rate": 5.282352907026511e-06, + "loss": 0.0035, + "step": 43175 + }, + { + "epoch": 13.33, + "learning_rate": 5.281911946444603e-06, + "loss": 0.0057, + "step": 43176 + }, + { + "epoch": 13.33, + "learning_rate": 5.28147099766349e-06, + "loss": 0.004, + "step": 43177 + }, + { + "epoch": 13.33, + "learning_rate": 5.2810300606842765e-06, + "loss": 0.0044, + "step": 43178 + }, + { + "epoch": 13.33, + "learning_rate": 5.280589135508067e-06, + "loss": 0.0056, + "step": 43179 + }, + { + "epoch": 13.33, + "learning_rate": 5.28014822213597e-06, + "loss": 0.005, + "step": 43180 + }, + { + "epoch": 13.34, + "learning_rate": 5.279707320569078e-06, + "loss": 0.0039, + "step": 43181 + }, + { + "epoch": 13.34, + "learning_rate": 5.279266430808504e-06, + "loss": 0.0042, + "step": 43182 + }, + { + "epoch": 13.34, + "learning_rate": 5.278825552855345e-06, + "loss": 0.0048, + "step": 43183 + }, + { + "epoch": 13.34, + "learning_rate": 5.2783846867107e-06, + "loss": 0.0042, + "step": 43184 + }, + { + "epoch": 13.34, + "learning_rate": 5.277943832375677e-06, + "loss": 0.0045, + "step": 43185 + }, + { + "epoch": 13.34, + "learning_rate": 5.277502989851382e-06, + "loss": 0.0048, + "step": 43186 + }, + { + "epoch": 13.34, + "learning_rate": 5.277062159138913e-06, + "loss": 0.0042, + "step": 43187 + }, + { + "epoch": 13.34, + "learning_rate": 5.276621340239368e-06, + "loss": 0.0034, + "step": 43188 + }, + { + "epoch": 13.34, + "learning_rate": 5.276180533153854e-06, + "loss": 0.0047, + "step": 43189 + }, + { + "epoch": 13.34, + "learning_rate": 5.27573973788348e-06, + "loss": 0.0052, + "step": 43190 + }, + { + "epoch": 13.34, + "learning_rate": 5.275298954429338e-06, + "loss": 0.0058, + "step": 43191 + }, + { + "epoch": 13.34, + "learning_rate": 5.274858182792537e-06, + "loss": 0.0047, + "step": 43192 + }, + { + "epoch": 13.34, + "learning_rate": 5.274417422974181e-06, + "loss": 0.0048, + "step": 43193 + }, + { + "epoch": 13.34, + "learning_rate": 5.273976674975363e-06, + "loss": 0.0055, + "step": 43194 + }, + { + "epoch": 13.34, + "learning_rate": 5.273535938797191e-06, + "loss": 0.0051, + "step": 43195 + }, + { + "epoch": 13.34, + "learning_rate": 5.273095214440772e-06, + "loss": 0.0039, + "step": 43196 + }, + { + "epoch": 13.34, + "learning_rate": 5.272654501907204e-06, + "loss": 0.0038, + "step": 43197 + }, + { + "epoch": 13.34, + "learning_rate": 5.272213801197585e-06, + "loss": 0.0044, + "step": 43198 + }, + { + "epoch": 13.34, + "learning_rate": 5.271773112313025e-06, + "loss": 0.0049, + "step": 43199 + }, + { + "epoch": 13.34, + "learning_rate": 5.271332435254621e-06, + "loss": 0.0044, + "step": 43200 + }, + { + "epoch": 13.34, + "learning_rate": 5.270891770023477e-06, + "loss": 0.0038, + "step": 43201 + }, + { + "epoch": 13.34, + "learning_rate": 5.2704511166207006e-06, + "loss": 0.0045, + "step": 43202 + }, + { + "epoch": 13.34, + "learning_rate": 5.2700104750473825e-06, + "loss": 0.0051, + "step": 43203 + }, + { + "epoch": 13.34, + "learning_rate": 5.2695698453046304e-06, + "loss": 0.0042, + "step": 43204 + }, + { + "epoch": 13.34, + "learning_rate": 5.269129227393551e-06, + "loss": 0.0052, + "step": 43205 + }, + { + "epoch": 13.34, + "learning_rate": 5.268688621315239e-06, + "loss": 0.0057, + "step": 43206 + }, + { + "epoch": 13.34, + "learning_rate": 5.2682480270708014e-06, + "loss": 0.0044, + "step": 43207 + }, + { + "epoch": 13.34, + "learning_rate": 5.267807444661341e-06, + "loss": 0.0038, + "step": 43208 + }, + { + "epoch": 13.34, + "learning_rate": 5.267366874087951e-06, + "loss": 0.0062, + "step": 43209 + }, + { + "epoch": 13.34, + "learning_rate": 5.266926315351742e-06, + "loss": 0.0048, + "step": 43210 + }, + { + "epoch": 13.34, + "learning_rate": 5.266485768453816e-06, + "loss": 0.0049, + "step": 43211 + }, + { + "epoch": 13.34, + "learning_rate": 5.266045233395274e-06, + "loss": 0.0039, + "step": 43212 + }, + { + "epoch": 13.34, + "learning_rate": 5.26560471017721e-06, + "loss": 0.0051, + "step": 43213 + }, + { + "epoch": 13.35, + "learning_rate": 5.265164198800738e-06, + "loss": 0.0051, + "step": 43214 + }, + { + "epoch": 13.35, + "learning_rate": 5.2647236992669495e-06, + "loss": 0.004, + "step": 43215 + }, + { + "epoch": 13.35, + "learning_rate": 5.2642832115769505e-06, + "loss": 0.005, + "step": 43216 + }, + { + "epoch": 13.35, + "learning_rate": 5.263842735731846e-06, + "loss": 0.0039, + "step": 43217 + }, + { + "epoch": 13.35, + "learning_rate": 5.263402271732736e-06, + "loss": 0.0041, + "step": 43218 + }, + { + "epoch": 13.35, + "learning_rate": 5.262961819580716e-06, + "loss": 0.0043, + "step": 43219 + }, + { + "epoch": 13.35, + "learning_rate": 5.262521379276892e-06, + "loss": 0.0043, + "step": 43220 + }, + { + "epoch": 13.35, + "learning_rate": 5.262080950822371e-06, + "loss": 0.0049, + "step": 43221 + }, + { + "epoch": 13.35, + "learning_rate": 5.261640534218251e-06, + "loss": 0.0034, + "step": 43222 + }, + { + "epoch": 13.35, + "learning_rate": 5.2612001294656255e-06, + "loss": 0.0056, + "step": 43223 + }, + { + "epoch": 13.35, + "learning_rate": 5.260759736565608e-06, + "loss": 0.0038, + "step": 43224 + }, + { + "epoch": 13.35, + "learning_rate": 5.260319355519291e-06, + "loss": 0.0034, + "step": 43225 + }, + { + "epoch": 13.35, + "learning_rate": 5.25987898632778e-06, + "loss": 0.0033, + "step": 43226 + }, + { + "epoch": 13.35, + "learning_rate": 5.25943862899218e-06, + "loss": 0.0056, + "step": 43227 + }, + { + "epoch": 13.35, + "learning_rate": 5.258998283513588e-06, + "loss": 0.0046, + "step": 43228 + }, + { + "epoch": 13.35, + "learning_rate": 5.258557949893103e-06, + "loss": 0.0069, + "step": 43229 + }, + { + "epoch": 13.35, + "learning_rate": 5.258117628131833e-06, + "loss": 0.0046, + "step": 43230 + }, + { + "epoch": 13.35, + "learning_rate": 5.2576773182308704e-06, + "loss": 0.0046, + "step": 43231 + }, + { + "epoch": 13.35, + "learning_rate": 5.257237020191327e-06, + "loss": 0.004, + "step": 43232 + }, + { + "epoch": 13.35, + "learning_rate": 5.256796734014299e-06, + "loss": 0.0044, + "step": 43233 + }, + { + "epoch": 13.35, + "learning_rate": 5.256356459700882e-06, + "loss": 0.0047, + "step": 43234 + }, + { + "epoch": 13.35, + "learning_rate": 5.255916197252185e-06, + "loss": 0.0048, + "step": 43235 + }, + { + "epoch": 13.35, + "learning_rate": 5.25547594666931e-06, + "loss": 0.0046, + "step": 43236 + }, + { + "epoch": 13.35, + "learning_rate": 5.25503570795335e-06, + "loss": 0.004, + "step": 43237 + }, + { + "epoch": 13.35, + "learning_rate": 5.2545954811054154e-06, + "loss": 0.0051, + "step": 43238 + }, + { + "epoch": 13.35, + "learning_rate": 5.254155266126604e-06, + "loss": 0.0057, + "step": 43239 + }, + { + "epoch": 13.35, + "learning_rate": 5.253715063018011e-06, + "loss": 0.0041, + "step": 43240 + }, + { + "epoch": 13.35, + "learning_rate": 5.253274871780743e-06, + "loss": 0.0041, + "step": 43241 + }, + { + "epoch": 13.35, + "learning_rate": 5.252834692415903e-06, + "loss": 0.0045, + "step": 43242 + }, + { + "epoch": 13.35, + "learning_rate": 5.2523945249245914e-06, + "loss": 0.0042, + "step": 43243 + }, + { + "epoch": 13.35, + "learning_rate": 5.251954369307901e-06, + "loss": 0.0053, + "step": 43244 + }, + { + "epoch": 13.35, + "learning_rate": 5.251514225566943e-06, + "loss": 0.0042, + "step": 43245 + }, + { + "epoch": 13.36, + "learning_rate": 5.251074093702811e-06, + "loss": 0.0057, + "step": 43246 + }, + { + "epoch": 13.36, + "learning_rate": 5.250633973716608e-06, + "loss": 0.004, + "step": 43247 + }, + { + "epoch": 13.36, + "learning_rate": 5.25019386560944e-06, + "loss": 0.0038, + "step": 43248 + }, + { + "epoch": 13.36, + "learning_rate": 5.2497537693824045e-06, + "loss": 0.0036, + "step": 43249 + }, + { + "epoch": 13.36, + "learning_rate": 5.249313685036595e-06, + "loss": 0.0035, + "step": 43250 + }, + { + "epoch": 13.36, + "learning_rate": 5.24887361257312e-06, + "loss": 0.0062, + "step": 43251 + }, + { + "epoch": 13.36, + "learning_rate": 5.248433551993082e-06, + "loss": 0.004, + "step": 43252 + }, + { + "epoch": 13.36, + "learning_rate": 5.247993503297578e-06, + "loss": 0.004, + "step": 43253 + }, + { + "epoch": 13.36, + "learning_rate": 5.247553466487706e-06, + "loss": 0.0045, + "step": 43254 + }, + { + "epoch": 13.36, + "learning_rate": 5.247113441564573e-06, + "loss": 0.005, + "step": 43255 + }, + { + "epoch": 13.36, + "learning_rate": 5.246673428529272e-06, + "loss": 0.0046, + "step": 43256 + }, + { + "epoch": 13.36, + "learning_rate": 5.246233427382907e-06, + "loss": 0.0047, + "step": 43257 + }, + { + "epoch": 13.36, + "learning_rate": 5.245793438126585e-06, + "loss": 0.0039, + "step": 43258 + }, + { + "epoch": 13.36, + "learning_rate": 5.2453534607613996e-06, + "loss": 0.0047, + "step": 43259 + }, + { + "epoch": 13.36, + "learning_rate": 5.2449134952884485e-06, + "loss": 0.0045, + "step": 43260 + }, + { + "epoch": 13.36, + "learning_rate": 5.244473541708841e-06, + "loss": 0.0042, + "step": 43261 + }, + { + "epoch": 13.36, + "learning_rate": 5.244033600023668e-06, + "loss": 0.005, + "step": 43262 + }, + { + "epoch": 13.36, + "learning_rate": 5.243593670234037e-06, + "loss": 0.0049, + "step": 43263 + }, + { + "epoch": 13.36, + "learning_rate": 5.243153752341047e-06, + "loss": 0.0042, + "step": 43264 + }, + { + "epoch": 13.36, + "learning_rate": 5.242713846345793e-06, + "loss": 0.0038, + "step": 43265 + }, + { + "epoch": 13.36, + "learning_rate": 5.242273952249379e-06, + "loss": 0.0036, + "step": 43266 + }, + { + "epoch": 13.36, + "learning_rate": 5.24183407005291e-06, + "loss": 0.0039, + "step": 43267 + }, + { + "epoch": 13.36, + "learning_rate": 5.241394199757478e-06, + "loss": 0.0049, + "step": 43268 + }, + { + "epoch": 13.36, + "learning_rate": 5.240954341364191e-06, + "loss": 0.0037, + "step": 43269 + }, + { + "epoch": 13.36, + "learning_rate": 5.240514494874145e-06, + "loss": 0.0047, + "step": 43270 + }, + { + "epoch": 13.36, + "learning_rate": 5.240074660288436e-06, + "loss": 0.0048, + "step": 43271 + }, + { + "epoch": 13.36, + "learning_rate": 5.239634837608169e-06, + "loss": 0.0053, + "step": 43272 + }, + { + "epoch": 13.36, + "learning_rate": 5.239195026834447e-06, + "loss": 0.0055, + "step": 43273 + }, + { + "epoch": 13.36, + "learning_rate": 5.238755227968366e-06, + "loss": 0.0058, + "step": 43274 + }, + { + "epoch": 13.36, + "learning_rate": 5.238315441011024e-06, + "loss": 0.004, + "step": 43275 + }, + { + "epoch": 13.36, + "learning_rate": 5.237875665963526e-06, + "loss": 0.0045, + "step": 43276 + }, + { + "epoch": 13.36, + "learning_rate": 5.237435902826966e-06, + "loss": 0.0043, + "step": 43277 + }, + { + "epoch": 13.37, + "learning_rate": 5.236996151602448e-06, + "loss": 0.0043, + "step": 43278 + }, + { + "epoch": 13.37, + "learning_rate": 5.236556412291076e-06, + "loss": 0.0045, + "step": 43279 + }, + { + "epoch": 13.37, + "learning_rate": 5.236116684893944e-06, + "loss": 0.0043, + "step": 43280 + }, + { + "epoch": 13.37, + "learning_rate": 5.235676969412149e-06, + "loss": 0.0037, + "step": 43281 + }, + { + "epoch": 13.37, + "learning_rate": 5.235237265846795e-06, + "loss": 0.0042, + "step": 43282 + }, + { + "epoch": 13.37, + "learning_rate": 5.234797574198987e-06, + "loss": 0.0046, + "step": 43283 + }, + { + "epoch": 13.37, + "learning_rate": 5.234357894469817e-06, + "loss": 0.0047, + "step": 43284 + }, + { + "epoch": 13.37, + "learning_rate": 5.233918226660385e-06, + "loss": 0.0048, + "step": 43285 + }, + { + "epoch": 13.37, + "learning_rate": 5.233478570771796e-06, + "loss": 0.004, + "step": 43286 + }, + { + "epoch": 13.37, + "learning_rate": 5.233038926805143e-06, + "loss": 0.0043, + "step": 43287 + }, + { + "epoch": 13.37, + "learning_rate": 5.232599294761529e-06, + "loss": 0.0042, + "step": 43288 + }, + { + "epoch": 13.37, + "learning_rate": 5.232159674642057e-06, + "loss": 0.0041, + "step": 43289 + }, + { + "epoch": 13.37, + "learning_rate": 5.231720066447823e-06, + "loss": 0.0037, + "step": 43290 + }, + { + "epoch": 13.37, + "learning_rate": 5.231280470179925e-06, + "loss": 0.0051, + "step": 43291 + }, + { + "epoch": 13.37, + "learning_rate": 5.2308408858394655e-06, + "loss": 0.0039, + "step": 43292 + }, + { + "epoch": 13.37, + "learning_rate": 5.23040131342754e-06, + "loss": 0.005, + "step": 43293 + }, + { + "epoch": 13.37, + "learning_rate": 5.229961752945255e-06, + "loss": 0.0046, + "step": 43294 + }, + { + "epoch": 13.37, + "learning_rate": 5.229522204393705e-06, + "loss": 0.0035, + "step": 43295 + }, + { + "epoch": 13.37, + "learning_rate": 5.229082667773987e-06, + "loss": 0.0048, + "step": 43296 + }, + { + "epoch": 13.37, + "learning_rate": 5.228643143087202e-06, + "loss": 0.0047, + "step": 43297 + }, + { + "epoch": 13.37, + "learning_rate": 5.228203630334456e-06, + "loss": 0.0053, + "step": 43298 + }, + { + "epoch": 13.37, + "learning_rate": 5.227764129516839e-06, + "loss": 0.0042, + "step": 43299 + }, + { + "epoch": 13.37, + "learning_rate": 5.227324640635458e-06, + "loss": 0.0054, + "step": 43300 + }, + { + "epoch": 13.37, + "learning_rate": 5.226885163691409e-06, + "loss": 0.0042, + "step": 43301 + }, + { + "epoch": 13.37, + "learning_rate": 5.226445698685786e-06, + "loss": 0.005, + "step": 43302 + }, + { + "epoch": 13.37, + "learning_rate": 5.226006245619693e-06, + "loss": 0.0049, + "step": 43303 + }, + { + "epoch": 13.37, + "learning_rate": 5.225566804494233e-06, + "loss": 0.0034, + "step": 43304 + }, + { + "epoch": 13.37, + "learning_rate": 5.225127375310501e-06, + "loss": 0.0046, + "step": 43305 + }, + { + "epoch": 13.37, + "learning_rate": 5.224687958069594e-06, + "loss": 0.0051, + "step": 43306 + }, + { + "epoch": 13.37, + "learning_rate": 5.224248552772616e-06, + "loss": 0.0058, + "step": 43307 + }, + { + "epoch": 13.37, + "learning_rate": 5.22380915942066e-06, + "loss": 0.0052, + "step": 43308 + }, + { + "epoch": 13.37, + "learning_rate": 5.223369778014828e-06, + "loss": 0.0046, + "step": 43309 + }, + { + "epoch": 13.37, + "learning_rate": 5.222930408556227e-06, + "loss": 0.0041, + "step": 43310 + }, + { + "epoch": 13.38, + "learning_rate": 5.222491051045942e-06, + "loss": 0.0053, + "step": 43311 + }, + { + "epoch": 13.38, + "learning_rate": 5.222051705485076e-06, + "loss": 0.0051, + "step": 43312 + }, + { + "epoch": 13.38, + "learning_rate": 5.221612371874736e-06, + "loss": 0.0046, + "step": 43313 + }, + { + "epoch": 13.38, + "learning_rate": 5.22117305021601e-06, + "loss": 0.0045, + "step": 43314 + }, + { + "epoch": 13.38, + "learning_rate": 5.220733740510006e-06, + "loss": 0.0038, + "step": 43315 + }, + { + "epoch": 13.38, + "learning_rate": 5.220294442757814e-06, + "loss": 0.005, + "step": 43316 + }, + { + "epoch": 13.38, + "learning_rate": 5.219855156960542e-06, + "loss": 0.0038, + "step": 43317 + }, + { + "epoch": 13.38, + "learning_rate": 5.2194158831192805e-06, + "loss": 0.0047, + "step": 43318 + }, + { + "epoch": 13.38, + "learning_rate": 5.218976621235131e-06, + "loss": 0.0044, + "step": 43319 + }, + { + "epoch": 13.38, + "learning_rate": 5.218537371309198e-06, + "loss": 0.005, + "step": 43320 + }, + { + "epoch": 13.38, + "learning_rate": 5.218098133342573e-06, + "loss": 0.0052, + "step": 43321 + }, + { + "epoch": 13.38, + "learning_rate": 5.217658907336355e-06, + "loss": 0.0054, + "step": 43322 + }, + { + "epoch": 13.38, + "learning_rate": 5.217219693291648e-06, + "loss": 0.0058, + "step": 43323 + }, + { + "epoch": 13.38, + "learning_rate": 5.216780491209541e-06, + "loss": 0.0045, + "step": 43324 + }, + { + "epoch": 13.38, + "learning_rate": 5.216341301091144e-06, + "loss": 0.0058, + "step": 43325 + }, + { + "epoch": 13.38, + "learning_rate": 5.2159021229375505e-06, + "loss": 0.0052, + "step": 43326 + }, + { + "epoch": 13.38, + "learning_rate": 5.215462956749853e-06, + "loss": 0.0038, + "step": 43327 + }, + { + "epoch": 13.38, + "learning_rate": 5.215023802529156e-06, + "loss": 0.0047, + "step": 43328 + }, + { + "epoch": 13.38, + "learning_rate": 5.21458466027656e-06, + "loss": 0.0048, + "step": 43329 + }, + { + "epoch": 13.38, + "learning_rate": 5.214145529993157e-06, + "loss": 0.0047, + "step": 43330 + }, + { + "epoch": 13.38, + "learning_rate": 5.213706411680055e-06, + "loss": 0.004, + "step": 43331 + }, + { + "epoch": 13.38, + "learning_rate": 5.213267305338344e-06, + "loss": 0.0048, + "step": 43332 + }, + { + "epoch": 13.38, + "learning_rate": 5.212828210969122e-06, + "loss": 0.0058, + "step": 43333 + }, + { + "epoch": 13.38, + "learning_rate": 5.212389128573489e-06, + "loss": 0.0051, + "step": 43334 + }, + { + "epoch": 13.38, + "learning_rate": 5.211950058152548e-06, + "loss": 0.0046, + "step": 43335 + }, + { + "epoch": 13.38, + "learning_rate": 5.211510999707392e-06, + "loss": 0.0048, + "step": 43336 + }, + { + "epoch": 13.38, + "learning_rate": 5.2110719532391184e-06, + "loss": 0.0048, + "step": 43337 + }, + { + "epoch": 13.38, + "learning_rate": 5.21063291874883e-06, + "loss": 0.0042, + "step": 43338 + }, + { + "epoch": 13.38, + "learning_rate": 5.2101938962376186e-06, + "loss": 0.0073, + "step": 43339 + }, + { + "epoch": 13.38, + "learning_rate": 5.209754885706586e-06, + "loss": 0.0044, + "step": 43340 + }, + { + "epoch": 13.38, + "learning_rate": 5.209315887156838e-06, + "loss": 0.006, + "step": 43341 + }, + { + "epoch": 13.38, + "learning_rate": 5.208876900589457e-06, + "loss": 0.005, + "step": 43342 + }, + { + "epoch": 13.39, + "learning_rate": 5.208437926005549e-06, + "loss": 0.0038, + "step": 43343 + }, + { + "epoch": 13.39, + "learning_rate": 5.207998963406215e-06, + "loss": 0.0051, + "step": 43344 + }, + { + "epoch": 13.39, + "learning_rate": 5.207560012792545e-06, + "loss": 0.0059, + "step": 43345 + }, + { + "epoch": 13.39, + "learning_rate": 5.207121074165646e-06, + "loss": 0.0045, + "step": 43346 + }, + { + "epoch": 13.39, + "learning_rate": 5.206682147526608e-06, + "loss": 0.005, + "step": 43347 + }, + { + "epoch": 13.39, + "learning_rate": 5.2062432328765355e-06, + "loss": 0.0055, + "step": 43348 + }, + { + "epoch": 13.39, + "learning_rate": 5.20580433021652e-06, + "loss": 0.0054, + "step": 43349 + }, + { + "epoch": 13.39, + "learning_rate": 5.205365439547661e-06, + "loss": 0.005, + "step": 43350 + }, + { + "epoch": 13.39, + "learning_rate": 5.204926560871066e-06, + "loss": 0.0045, + "step": 43351 + }, + { + "epoch": 13.39, + "learning_rate": 5.204487694187816e-06, + "loss": 0.0046, + "step": 43352 + }, + { + "epoch": 13.39, + "learning_rate": 5.204048839499019e-06, + "loss": 0.0052, + "step": 43353 + }, + { + "epoch": 13.39, + "learning_rate": 5.203609996805772e-06, + "loss": 0.0043, + "step": 43354 + }, + { + "epoch": 13.39, + "learning_rate": 5.2031711661091675e-06, + "loss": 0.0039, + "step": 43355 + }, + { + "epoch": 13.39, + "learning_rate": 5.202732347410311e-06, + "loss": 0.0062, + "step": 43356 + }, + { + "epoch": 13.39, + "learning_rate": 5.202293540710297e-06, + "loss": 0.0045, + "step": 43357 + }, + { + "epoch": 13.39, + "learning_rate": 5.201854746010216e-06, + "loss": 0.0044, + "step": 43358 + }, + { + "epoch": 13.39, + "learning_rate": 5.201415963311174e-06, + "loss": 0.0051, + "step": 43359 + }, + { + "epoch": 13.39, + "learning_rate": 5.2009771926142676e-06, + "loss": 0.0044, + "step": 43360 + }, + { + "epoch": 13.39, + "learning_rate": 5.200538433920593e-06, + "loss": 0.0046, + "step": 43361 + }, + { + "epoch": 13.39, + "learning_rate": 5.200099687231244e-06, + "loss": 0.0046, + "step": 43362 + }, + { + "epoch": 13.39, + "learning_rate": 5.199660952547324e-06, + "loss": 0.0041, + "step": 43363 + }, + { + "epoch": 13.39, + "learning_rate": 5.199222229869925e-06, + "loss": 0.0055, + "step": 43364 + }, + { + "epoch": 13.39, + "learning_rate": 5.1987835192001456e-06, + "loss": 0.0047, + "step": 43365 + }, + { + "epoch": 13.39, + "learning_rate": 5.1983448205390876e-06, + "loss": 0.0052, + "step": 43366 + }, + { + "epoch": 13.39, + "learning_rate": 5.197906133887846e-06, + "loss": 0.0038, + "step": 43367 + }, + { + "epoch": 13.39, + "learning_rate": 5.197467459247514e-06, + "loss": 0.005, + "step": 43368 + }, + { + "epoch": 13.39, + "learning_rate": 5.197028796619195e-06, + "loss": 0.0044, + "step": 43369 + }, + { + "epoch": 13.39, + "learning_rate": 5.196590146003978e-06, + "loss": 0.0043, + "step": 43370 + }, + { + "epoch": 13.39, + "learning_rate": 5.19615150740297e-06, + "loss": 0.0047, + "step": 43371 + }, + { + "epoch": 13.39, + "learning_rate": 5.195712880817263e-06, + "loss": 0.0052, + "step": 43372 + }, + { + "epoch": 13.39, + "learning_rate": 5.195274266247951e-06, + "loss": 0.0047, + "step": 43373 + }, + { + "epoch": 13.39, + "learning_rate": 5.194835663696134e-06, + "loss": 0.0045, + "step": 43374 + }, + { + "epoch": 13.4, + "learning_rate": 5.194397073162912e-06, + "loss": 0.0049, + "step": 43375 + }, + { + "epoch": 13.4, + "learning_rate": 5.193958494649377e-06, + "loss": 0.0047, + "step": 43376 + }, + { + "epoch": 13.4, + "learning_rate": 5.193519928156631e-06, + "loss": 0.0045, + "step": 43377 + }, + { + "epoch": 13.4, + "learning_rate": 5.193081373685771e-06, + "loss": 0.0052, + "step": 43378 + }, + { + "epoch": 13.4, + "learning_rate": 5.192642831237885e-06, + "loss": 0.0037, + "step": 43379 + }, + { + "epoch": 13.4, + "learning_rate": 5.1922043008140765e-06, + "loss": 0.0034, + "step": 43380 + }, + { + "epoch": 13.4, + "learning_rate": 5.1917657824154465e-06, + "loss": 0.006, + "step": 43381 + }, + { + "epoch": 13.4, + "learning_rate": 5.191327276043087e-06, + "loss": 0.0058, + "step": 43382 + }, + { + "epoch": 13.4, + "learning_rate": 5.190888781698091e-06, + "loss": 0.0048, + "step": 43383 + }, + { + "epoch": 13.4, + "learning_rate": 5.190450299381559e-06, + "loss": 0.006, + "step": 43384 + }, + { + "epoch": 13.4, + "learning_rate": 5.190011829094592e-06, + "loss": 0.005, + "step": 43385 + }, + { + "epoch": 13.4, + "learning_rate": 5.189573370838279e-06, + "loss": 0.0039, + "step": 43386 + }, + { + "epoch": 13.4, + "learning_rate": 5.189134924613724e-06, + "loss": 0.0055, + "step": 43387 + }, + { + "epoch": 13.4, + "learning_rate": 5.18869649042202e-06, + "loss": 0.0054, + "step": 43388 + }, + { + "epoch": 13.4, + "learning_rate": 5.188258068264261e-06, + "loss": 0.0039, + "step": 43389 + }, + { + "epoch": 13.4, + "learning_rate": 5.187819658141544e-06, + "loss": 0.0034, + "step": 43390 + }, + { + "epoch": 13.4, + "learning_rate": 5.187381260054973e-06, + "loss": 0.005, + "step": 43391 + }, + { + "epoch": 13.4, + "learning_rate": 5.186942874005638e-06, + "loss": 0.0051, + "step": 43392 + }, + { + "epoch": 13.4, + "learning_rate": 5.186504499994633e-06, + "loss": 0.0037, + "step": 43393 + }, + { + "epoch": 13.4, + "learning_rate": 5.186066138023065e-06, + "loss": 0.0056, + "step": 43394 + }, + { + "epoch": 13.4, + "learning_rate": 5.185627788092016e-06, + "loss": 0.0044, + "step": 43395 + }, + { + "epoch": 13.4, + "learning_rate": 5.185189450202592e-06, + "loss": 0.0041, + "step": 43396 + }, + { + "epoch": 13.4, + "learning_rate": 5.184751124355891e-06, + "loss": 0.0045, + "step": 43397 + }, + { + "epoch": 13.4, + "learning_rate": 5.184312810553005e-06, + "loss": 0.0049, + "step": 43398 + }, + { + "epoch": 13.4, + "learning_rate": 5.183874508795028e-06, + "loss": 0.0051, + "step": 43399 + }, + { + "epoch": 13.4, + "learning_rate": 5.183436219083062e-06, + "loss": 0.0051, + "step": 43400 + }, + { + "epoch": 13.4, + "learning_rate": 5.182997941418197e-06, + "loss": 0.0047, + "step": 43401 + }, + { + "epoch": 13.4, + "learning_rate": 5.182559675801538e-06, + "loss": 0.0059, + "step": 43402 + }, + { + "epoch": 13.4, + "learning_rate": 5.182121422234174e-06, + "loss": 0.0035, + "step": 43403 + }, + { + "epoch": 13.4, + "learning_rate": 5.181683180717201e-06, + "loss": 0.0042, + "step": 43404 + }, + { + "epoch": 13.4, + "learning_rate": 5.181244951251716e-06, + "loss": 0.0043, + "step": 43405 + }, + { + "epoch": 13.4, + "learning_rate": 5.1808067338388195e-06, + "loss": 0.0043, + "step": 43406 + }, + { + "epoch": 13.4, + "learning_rate": 5.180368528479602e-06, + "loss": 0.0052, + "step": 43407 + }, + { + "epoch": 13.41, + "learning_rate": 5.179930335175165e-06, + "loss": 0.0049, + "step": 43408 + }, + { + "epoch": 13.41, + "learning_rate": 5.179492153926601e-06, + "loss": 0.005, + "step": 43409 + }, + { + "epoch": 13.41, + "learning_rate": 5.179053984735003e-06, + "loss": 0.005, + "step": 43410 + }, + { + "epoch": 13.41, + "learning_rate": 5.178615827601469e-06, + "loss": 0.0042, + "step": 43411 + }, + { + "epoch": 13.41, + "learning_rate": 5.178177682527101e-06, + "loss": 0.0045, + "step": 43412 + }, + { + "epoch": 13.41, + "learning_rate": 5.17773954951299e-06, + "loss": 0.0043, + "step": 43413 + }, + { + "epoch": 13.41, + "learning_rate": 5.1773014285602285e-06, + "loss": 0.0061, + "step": 43414 + }, + { + "epoch": 13.41, + "learning_rate": 5.176863319669916e-06, + "loss": 0.0049, + "step": 43415 + }, + { + "epoch": 13.41, + "learning_rate": 5.176425222843151e-06, + "loss": 0.0042, + "step": 43416 + }, + { + "epoch": 13.41, + "learning_rate": 5.175987138081022e-06, + "loss": 0.004, + "step": 43417 + }, + { + "epoch": 13.41, + "learning_rate": 5.175549065384634e-06, + "loss": 0.0051, + "step": 43418 + }, + { + "epoch": 13.41, + "learning_rate": 5.175111004755078e-06, + "loss": 0.0047, + "step": 43419 + }, + { + "epoch": 13.41, + "learning_rate": 5.174672956193445e-06, + "loss": 0.0039, + "step": 43420 + }, + { + "epoch": 13.41, + "learning_rate": 5.174234919700834e-06, + "loss": 0.0054, + "step": 43421 + }, + { + "epoch": 13.41, + "learning_rate": 5.173796895278347e-06, + "loss": 0.0046, + "step": 43422 + }, + { + "epoch": 13.41, + "learning_rate": 5.173358882927073e-06, + "loss": 0.0046, + "step": 43423 + }, + { + "epoch": 13.41, + "learning_rate": 5.172920882648105e-06, + "loss": 0.0054, + "step": 43424 + }, + { + "epoch": 13.41, + "learning_rate": 5.172482894442548e-06, + "loss": 0.0046, + "step": 43425 + }, + { + "epoch": 13.41, + "learning_rate": 5.172044918311485e-06, + "loss": 0.0039, + "step": 43426 + }, + { + "epoch": 13.41, + "learning_rate": 5.171606954256021e-06, + "loss": 0.0046, + "step": 43427 + }, + { + "epoch": 13.41, + "learning_rate": 5.17116900227725e-06, + "loss": 0.0045, + "step": 43428 + }, + { + "epoch": 13.41, + "learning_rate": 5.170731062376269e-06, + "loss": 0.0043, + "step": 43429 + }, + { + "epoch": 13.41, + "learning_rate": 5.170293134554163e-06, + "loss": 0.0049, + "step": 43430 + }, + { + "epoch": 13.41, + "learning_rate": 5.169855218812041e-06, + "loss": 0.005, + "step": 43431 + }, + { + "epoch": 13.41, + "learning_rate": 5.169417315150987e-06, + "loss": 0.0045, + "step": 43432 + }, + { + "epoch": 13.41, + "learning_rate": 5.168979423572107e-06, + "loss": 0.0049, + "step": 43433 + }, + { + "epoch": 13.41, + "learning_rate": 5.1685415440764884e-06, + "loss": 0.0066, + "step": 43434 + }, + { + "epoch": 13.41, + "learning_rate": 5.168103676665226e-06, + "loss": 0.0049, + "step": 43435 + }, + { + "epoch": 13.41, + "learning_rate": 5.167665821339418e-06, + "loss": 0.0043, + "step": 43436 + }, + { + "epoch": 13.41, + "learning_rate": 5.167227978100162e-06, + "loss": 0.0043, + "step": 43437 + }, + { + "epoch": 13.41, + "learning_rate": 5.166790146948546e-06, + "loss": 0.0052, + "step": 43438 + }, + { + "epoch": 13.41, + "learning_rate": 5.166352327885675e-06, + "loss": 0.0069, + "step": 43439 + }, + { + "epoch": 13.42, + "learning_rate": 5.1659145209126375e-06, + "loss": 0.0055, + "step": 43440 + }, + { + "epoch": 13.42, + "learning_rate": 5.165476726030525e-06, + "loss": 0.0052, + "step": 43441 + }, + { + "epoch": 13.42, + "learning_rate": 5.165038943240437e-06, + "loss": 0.0044, + "step": 43442 + }, + { + "epoch": 13.42, + "learning_rate": 5.164601172543473e-06, + "loss": 0.0056, + "step": 43443 + }, + { + "epoch": 13.42, + "learning_rate": 5.164163413940724e-06, + "loss": 0.0035, + "step": 43444 + }, + { + "epoch": 13.42, + "learning_rate": 5.163725667433279e-06, + "loss": 0.0032, + "step": 43445 + }, + { + "epoch": 13.42, + "learning_rate": 5.163287933022238e-06, + "loss": 0.0043, + "step": 43446 + }, + { + "epoch": 13.42, + "learning_rate": 5.162850210708702e-06, + "loss": 0.0053, + "step": 43447 + }, + { + "epoch": 13.42, + "learning_rate": 5.162412500493754e-06, + "loss": 0.0044, + "step": 43448 + }, + { + "epoch": 13.42, + "learning_rate": 5.1619748023785e-06, + "loss": 0.0052, + "step": 43449 + }, + { + "epoch": 13.42, + "learning_rate": 5.1615371163640285e-06, + "loss": 0.0046, + "step": 43450 + }, + { + "epoch": 13.42, + "learning_rate": 5.161099442451431e-06, + "loss": 0.0055, + "step": 43451 + }, + { + "epoch": 13.42, + "learning_rate": 5.160661780641807e-06, + "loss": 0.006, + "step": 43452 + }, + { + "epoch": 13.42, + "learning_rate": 5.1602241309362546e-06, + "loss": 0.0054, + "step": 43453 + }, + { + "epoch": 13.42, + "learning_rate": 5.159786493335863e-06, + "loss": 0.0042, + "step": 43454 + }, + { + "epoch": 13.42, + "learning_rate": 5.159348867841726e-06, + "loss": 0.0051, + "step": 43455 + }, + { + "epoch": 13.42, + "learning_rate": 5.158911254454943e-06, + "loss": 0.0046, + "step": 43456 + }, + { + "epoch": 13.42, + "learning_rate": 5.158473653176604e-06, + "loss": 0.0047, + "step": 43457 + }, + { + "epoch": 13.42, + "learning_rate": 5.158036064007803e-06, + "loss": 0.0044, + "step": 43458 + }, + { + "epoch": 13.42, + "learning_rate": 5.157598486949646e-06, + "loss": 0.0047, + "step": 43459 + }, + { + "epoch": 13.42, + "learning_rate": 5.15716092200321e-06, + "loss": 0.0051, + "step": 43460 + }, + { + "epoch": 13.42, + "learning_rate": 5.1567233691695985e-06, + "loss": 0.0049, + "step": 43461 + }, + { + "epoch": 13.42, + "learning_rate": 5.156285828449908e-06, + "loss": 0.0036, + "step": 43462 + }, + { + "epoch": 13.42, + "learning_rate": 5.155848299845228e-06, + "loss": 0.0057, + "step": 43463 + }, + { + "epoch": 13.42, + "learning_rate": 5.155410783356657e-06, + "loss": 0.0067, + "step": 43464 + }, + { + "epoch": 13.42, + "learning_rate": 5.154973278985288e-06, + "loss": 0.0048, + "step": 43465 + }, + { + "epoch": 13.42, + "learning_rate": 5.154535786732211e-06, + "loss": 0.0037, + "step": 43466 + }, + { + "epoch": 13.42, + "learning_rate": 5.154098306598523e-06, + "loss": 0.0042, + "step": 43467 + }, + { + "epoch": 13.42, + "learning_rate": 5.153660838585323e-06, + "loss": 0.0039, + "step": 43468 + }, + { + "epoch": 13.42, + "learning_rate": 5.153223382693702e-06, + "loss": 0.0045, + "step": 43469 + }, + { + "epoch": 13.42, + "learning_rate": 5.152785938924748e-06, + "loss": 0.0042, + "step": 43470 + }, + { + "epoch": 13.42, + "learning_rate": 5.1523485072795654e-06, + "loss": 0.0061, + "step": 43471 + }, + { + "epoch": 13.42, + "learning_rate": 5.151911087759238e-06, + "loss": 0.0047, + "step": 43472 + }, + { + "epoch": 13.43, + "learning_rate": 5.151473680364867e-06, + "loss": 0.0056, + "step": 43473 + }, + { + "epoch": 13.43, + "learning_rate": 5.151036285097548e-06, + "loss": 0.0049, + "step": 43474 + }, + { + "epoch": 13.43, + "learning_rate": 5.150598901958372e-06, + "loss": 0.0057, + "step": 43475 + }, + { + "epoch": 13.43, + "learning_rate": 5.150161530948427e-06, + "loss": 0.005, + "step": 43476 + }, + { + "epoch": 13.43, + "learning_rate": 5.149724172068818e-06, + "loss": 0.0053, + "step": 43477 + }, + { + "epoch": 13.43, + "learning_rate": 5.14928682532063e-06, + "loss": 0.0043, + "step": 43478 + }, + { + "epoch": 13.43, + "learning_rate": 5.148849490704964e-06, + "loss": 0.0045, + "step": 43479 + }, + { + "epoch": 13.43, + "learning_rate": 5.148412168222905e-06, + "loss": 0.0059, + "step": 43480 + }, + { + "epoch": 13.43, + "learning_rate": 5.147974857875557e-06, + "loss": 0.0054, + "step": 43481 + }, + { + "epoch": 13.43, + "learning_rate": 5.147537559664004e-06, + "loss": 0.0045, + "step": 43482 + }, + { + "epoch": 13.43, + "learning_rate": 5.147100273589346e-06, + "loss": 0.0046, + "step": 43483 + }, + { + "epoch": 13.43, + "learning_rate": 5.146662999652678e-06, + "loss": 0.0057, + "step": 43484 + }, + { + "epoch": 13.43, + "learning_rate": 5.146225737855093e-06, + "loss": 0.0054, + "step": 43485 + }, + { + "epoch": 13.43, + "learning_rate": 5.145788488197676e-06, + "loss": 0.0042, + "step": 43486 + }, + { + "epoch": 13.43, + "learning_rate": 5.145351250681534e-06, + "loss": 0.0041, + "step": 43487 + }, + { + "epoch": 13.43, + "learning_rate": 5.144914025307748e-06, + "loss": 0.0062, + "step": 43488 + }, + { + "epoch": 13.43, + "learning_rate": 5.144476812077423e-06, + "loss": 0.0051, + "step": 43489 + }, + { + "epoch": 13.43, + "learning_rate": 5.144039610991646e-06, + "loss": 0.0045, + "step": 43490 + }, + { + "epoch": 13.43, + "learning_rate": 5.143602422051508e-06, + "loss": 0.0049, + "step": 43491 + }, + { + "epoch": 13.43, + "learning_rate": 5.143165245258106e-06, + "loss": 0.0044, + "step": 43492 + }, + { + "epoch": 13.43, + "learning_rate": 5.142728080612537e-06, + "loss": 0.0055, + "step": 43493 + }, + { + "epoch": 13.43, + "learning_rate": 5.142290928115888e-06, + "loss": 0.0053, + "step": 43494 + }, + { + "epoch": 13.43, + "learning_rate": 5.1418537877692576e-06, + "loss": 0.0056, + "step": 43495 + }, + { + "epoch": 13.43, + "learning_rate": 5.1414166595737395e-06, + "loss": 0.0052, + "step": 43496 + }, + { + "epoch": 13.43, + "learning_rate": 5.140979543530419e-06, + "loss": 0.0053, + "step": 43497 + }, + { + "epoch": 13.43, + "learning_rate": 5.140542439640395e-06, + "loss": 0.0072, + "step": 43498 + }, + { + "epoch": 13.43, + "learning_rate": 5.140105347904764e-06, + "loss": 0.0047, + "step": 43499 + }, + { + "epoch": 13.43, + "learning_rate": 5.139668268324618e-06, + "loss": 0.004, + "step": 43500 + }, + { + "epoch": 13.43, + "learning_rate": 5.139231200901043e-06, + "loss": 0.0058, + "step": 43501 + }, + { + "epoch": 13.43, + "learning_rate": 5.13879414563514e-06, + "loss": 0.0054, + "step": 43502 + }, + { + "epoch": 13.43, + "learning_rate": 5.138357102527997e-06, + "loss": 0.0052, + "step": 43503 + }, + { + "epoch": 13.43, + "learning_rate": 5.137920071580709e-06, + "loss": 0.0051, + "step": 43504 + }, + { + "epoch": 13.44, + "learning_rate": 5.137483052794374e-06, + "loss": 0.0044, + "step": 43505 + }, + { + "epoch": 13.44, + "learning_rate": 5.13704604617008e-06, + "loss": 0.004, + "step": 43506 + }, + { + "epoch": 13.44, + "learning_rate": 5.136609051708918e-06, + "loss": 0.0037, + "step": 43507 + }, + { + "epoch": 13.44, + "learning_rate": 5.136172069411987e-06, + "loss": 0.0045, + "step": 43508 + }, + { + "epoch": 13.44, + "learning_rate": 5.135735099280373e-06, + "loss": 0.0047, + "step": 43509 + }, + { + "epoch": 13.44, + "learning_rate": 5.135298141315177e-06, + "loss": 0.0045, + "step": 43510 + }, + { + "epoch": 13.44, + "learning_rate": 5.1348611955174835e-06, + "loss": 0.0045, + "step": 43511 + }, + { + "epoch": 13.44, + "learning_rate": 5.134424261888393e-06, + "loss": 0.0055, + "step": 43512 + }, + { + "epoch": 13.44, + "learning_rate": 5.133987340428992e-06, + "loss": 0.0042, + "step": 43513 + }, + { + "epoch": 13.44, + "learning_rate": 5.133550431140375e-06, + "loss": 0.0037, + "step": 43514 + }, + { + "epoch": 13.44, + "learning_rate": 5.133113534023639e-06, + "loss": 0.0058, + "step": 43515 + }, + { + "epoch": 13.44, + "learning_rate": 5.1326766490798755e-06, + "loss": 0.0039, + "step": 43516 + }, + { + "epoch": 13.44, + "learning_rate": 5.132239776310171e-06, + "loss": 0.006, + "step": 43517 + }, + { + "epoch": 13.44, + "learning_rate": 5.131802915715627e-06, + "loss": 0.0053, + "step": 43518 + }, + { + "epoch": 13.44, + "learning_rate": 5.1313660672973276e-06, + "loss": 0.0046, + "step": 43519 + }, + { + "epoch": 13.44, + "learning_rate": 5.130929231056373e-06, + "loss": 0.0056, + "step": 43520 + }, + { + "epoch": 13.44, + "learning_rate": 5.130492406993853e-06, + "loss": 0.0046, + "step": 43521 + }, + { + "epoch": 13.44, + "learning_rate": 5.130055595110856e-06, + "loss": 0.0046, + "step": 43522 + }, + { + "epoch": 13.44, + "learning_rate": 5.129618795408478e-06, + "loss": 0.0041, + "step": 43523 + }, + { + "epoch": 13.44, + "learning_rate": 5.129182007887814e-06, + "loss": 0.0041, + "step": 43524 + }, + { + "epoch": 13.44, + "learning_rate": 5.128745232549952e-06, + "loss": 0.0045, + "step": 43525 + }, + { + "epoch": 13.44, + "learning_rate": 5.12830846939599e-06, + "loss": 0.0038, + "step": 43526 + }, + { + "epoch": 13.44, + "learning_rate": 5.127871718427018e-06, + "loss": 0.005, + "step": 43527 + }, + { + "epoch": 13.44, + "learning_rate": 5.127434979644122e-06, + "loss": 0.0049, + "step": 43528 + }, + { + "epoch": 13.44, + "learning_rate": 5.126998253048401e-06, + "loss": 0.0036, + "step": 43529 + }, + { + "epoch": 13.44, + "learning_rate": 5.126561538640949e-06, + "loss": 0.0056, + "step": 43530 + }, + { + "epoch": 13.44, + "learning_rate": 5.1261248364228564e-06, + "loss": 0.004, + "step": 43531 + }, + { + "epoch": 13.44, + "learning_rate": 5.125688146395211e-06, + "loss": 0.0051, + "step": 43532 + }, + { + "epoch": 13.44, + "learning_rate": 5.125251468559112e-06, + "loss": 0.0047, + "step": 43533 + }, + { + "epoch": 13.44, + "learning_rate": 5.124814802915643e-06, + "loss": 0.0053, + "step": 43534 + }, + { + "epoch": 13.44, + "learning_rate": 5.124378149465903e-06, + "loss": 0.005, + "step": 43535 + }, + { + "epoch": 13.44, + "learning_rate": 5.123941508210985e-06, + "loss": 0.0042, + "step": 43536 + }, + { + "epoch": 13.45, + "learning_rate": 5.12350487915198e-06, + "loss": 0.0058, + "step": 43537 + }, + { + "epoch": 13.45, + "learning_rate": 5.1230682622899745e-06, + "loss": 0.0051, + "step": 43538 + }, + { + "epoch": 13.45, + "learning_rate": 5.122631657626068e-06, + "loss": 0.0044, + "step": 43539 + }, + { + "epoch": 13.45, + "learning_rate": 5.122195065161346e-06, + "loss": 0.0046, + "step": 43540 + }, + { + "epoch": 13.45, + "learning_rate": 5.121758484896908e-06, + "loss": 0.0044, + "step": 43541 + }, + { + "epoch": 13.45, + "learning_rate": 5.121321916833841e-06, + "loss": 0.0045, + "step": 43542 + }, + { + "epoch": 13.45, + "learning_rate": 5.120885360973233e-06, + "loss": 0.0049, + "step": 43543 + }, + { + "epoch": 13.45, + "learning_rate": 5.120448817316183e-06, + "loss": 0.0076, + "step": 43544 + }, + { + "epoch": 13.45, + "learning_rate": 5.120012285863779e-06, + "loss": 0.0036, + "step": 43545 + }, + { + "epoch": 13.45, + "learning_rate": 5.119575766617119e-06, + "loss": 0.0052, + "step": 43546 + }, + { + "epoch": 13.45, + "learning_rate": 5.1191392595772886e-06, + "loss": 0.0062, + "step": 43547 + }, + { + "epoch": 13.45, + "learning_rate": 5.118702764745378e-06, + "loss": 0.0045, + "step": 43548 + }, + { + "epoch": 13.45, + "learning_rate": 5.118266282122486e-06, + "loss": 0.0047, + "step": 43549 + }, + { + "epoch": 13.45, + "learning_rate": 5.117829811709698e-06, + "loss": 0.0055, + "step": 43550 + }, + { + "epoch": 13.45, + "learning_rate": 5.11739335350811e-06, + "loss": 0.0055, + "step": 43551 + }, + { + "epoch": 13.45, + "learning_rate": 5.116956907518813e-06, + "loss": 0.0043, + "step": 43552 + }, + { + "epoch": 13.45, + "learning_rate": 5.116520473742892e-06, + "loss": 0.0043, + "step": 43553 + }, + { + "epoch": 13.45, + "learning_rate": 5.116084052181445e-06, + "loss": 0.0062, + "step": 43554 + }, + { + "epoch": 13.45, + "learning_rate": 5.115647642835566e-06, + "loss": 0.0047, + "step": 43555 + }, + { + "epoch": 13.45, + "learning_rate": 5.11521124570634e-06, + "loss": 0.0048, + "step": 43556 + }, + { + "epoch": 13.45, + "learning_rate": 5.114774860794865e-06, + "loss": 0.0044, + "step": 43557 + }, + { + "epoch": 13.45, + "learning_rate": 5.114338488102229e-06, + "loss": 0.0051, + "step": 43558 + }, + { + "epoch": 13.45, + "learning_rate": 5.11390212762952e-06, + "loss": 0.0064, + "step": 43559 + }, + { + "epoch": 13.45, + "learning_rate": 5.113465779377833e-06, + "loss": 0.0052, + "step": 43560 + }, + { + "epoch": 13.45, + "learning_rate": 5.113029443348263e-06, + "loss": 0.004, + "step": 43561 + }, + { + "epoch": 13.45, + "learning_rate": 5.112593119541898e-06, + "loss": 0.0048, + "step": 43562 + }, + { + "epoch": 13.45, + "learning_rate": 5.1121568079598235e-06, + "loss": 0.0048, + "step": 43563 + }, + { + "epoch": 13.45, + "learning_rate": 5.111720508603142e-06, + "loss": 0.0039, + "step": 43564 + }, + { + "epoch": 13.45, + "learning_rate": 5.111284221472934e-06, + "loss": 0.0046, + "step": 43565 + }, + { + "epoch": 13.45, + "learning_rate": 5.110847946570297e-06, + "loss": 0.0042, + "step": 43566 + }, + { + "epoch": 13.45, + "learning_rate": 5.110411683896328e-06, + "loss": 0.0042, + "step": 43567 + }, + { + "epoch": 13.45, + "learning_rate": 5.109975433452103e-06, + "loss": 0.0043, + "step": 43568 + }, + { + "epoch": 13.45, + "learning_rate": 5.109539195238723e-06, + "loss": 0.0043, + "step": 43569 + }, + { + "epoch": 13.46, + "learning_rate": 5.10910296925728e-06, + "loss": 0.0045, + "step": 43570 + }, + { + "epoch": 13.46, + "learning_rate": 5.10866675550886e-06, + "loss": 0.0044, + "step": 43571 + }, + { + "epoch": 13.46, + "learning_rate": 5.108230553994559e-06, + "loss": 0.0037, + "step": 43572 + }, + { + "epoch": 13.46, + "learning_rate": 5.107794364715466e-06, + "loss": 0.0046, + "step": 43573 + }, + { + "epoch": 13.46, + "learning_rate": 5.107358187672667e-06, + "loss": 0.0043, + "step": 43574 + }, + { + "epoch": 13.46, + "learning_rate": 5.106922022867258e-06, + "loss": 0.0059, + "step": 43575 + }, + { + "epoch": 13.46, + "learning_rate": 5.106485870300331e-06, + "loss": 0.0038, + "step": 43576 + }, + { + "epoch": 13.46, + "learning_rate": 5.106049729972978e-06, + "loss": 0.0039, + "step": 43577 + }, + { + "epoch": 13.46, + "learning_rate": 5.105613601886286e-06, + "loss": 0.0057, + "step": 43578 + }, + { + "epoch": 13.46, + "learning_rate": 5.105177486041344e-06, + "loss": 0.0044, + "step": 43579 + }, + { + "epoch": 13.46, + "learning_rate": 5.104741382439251e-06, + "loss": 0.0037, + "step": 43580 + }, + { + "epoch": 13.46, + "learning_rate": 5.104305291081087e-06, + "loss": 0.0057, + "step": 43581 + }, + { + "epoch": 13.46, + "learning_rate": 5.1038692119679534e-06, + "loss": 0.0048, + "step": 43582 + }, + { + "epoch": 13.46, + "learning_rate": 5.103433145100935e-06, + "loss": 0.0047, + "step": 43583 + }, + { + "epoch": 13.46, + "learning_rate": 5.102997090481121e-06, + "loss": 0.0056, + "step": 43584 + }, + { + "epoch": 13.46, + "learning_rate": 5.102561048109602e-06, + "loss": 0.0056, + "step": 43585 + }, + { + "epoch": 13.46, + "learning_rate": 5.102125017987478e-06, + "loss": 0.0058, + "step": 43586 + }, + { + "epoch": 13.46, + "learning_rate": 5.1016890001158255e-06, + "loss": 0.0051, + "step": 43587 + }, + { + "epoch": 13.46, + "learning_rate": 5.101252994495749e-06, + "loss": 0.0044, + "step": 43588 + }, + { + "epoch": 13.46, + "learning_rate": 5.100817001128331e-06, + "loss": 0.0057, + "step": 43589 + }, + { + "epoch": 13.46, + "learning_rate": 5.10038102001466e-06, + "loss": 0.0051, + "step": 43590 + }, + { + "epoch": 13.46, + "learning_rate": 5.099945051155828e-06, + "loss": 0.0043, + "step": 43591 + }, + { + "epoch": 13.46, + "learning_rate": 5.099509094552932e-06, + "loss": 0.0042, + "step": 43592 + }, + { + "epoch": 13.46, + "learning_rate": 5.099073150207059e-06, + "loss": 0.0065, + "step": 43593 + }, + { + "epoch": 13.46, + "learning_rate": 5.098637218119291e-06, + "loss": 0.0052, + "step": 43594 + }, + { + "epoch": 13.46, + "learning_rate": 5.098201298290732e-06, + "loss": 0.0041, + "step": 43595 + }, + { + "epoch": 13.46, + "learning_rate": 5.09776539072246e-06, + "loss": 0.0048, + "step": 43596 + }, + { + "epoch": 13.46, + "learning_rate": 5.0973294954155716e-06, + "loss": 0.004, + "step": 43597 + }, + { + "epoch": 13.46, + "learning_rate": 5.096893612371164e-06, + "loss": 0.005, + "step": 43598 + }, + { + "epoch": 13.46, + "learning_rate": 5.096457741590313e-06, + "loss": 0.0057, + "step": 43599 + }, + { + "epoch": 13.46, + "learning_rate": 5.0960218830741136e-06, + "loss": 0.0036, + "step": 43600 + }, + { + "epoch": 13.46, + "learning_rate": 5.095586036823663e-06, + "loss": 0.0053, + "step": 43601 + }, + { + "epoch": 13.47, + "learning_rate": 5.095150202840041e-06, + "loss": 0.0045, + "step": 43602 + }, + { + "epoch": 13.47, + "learning_rate": 5.094714381124348e-06, + "loss": 0.005, + "step": 43603 + }, + { + "epoch": 13.47, + "learning_rate": 5.094278571677669e-06, + "loss": 0.0039, + "step": 43604 + }, + { + "epoch": 13.47, + "learning_rate": 5.09384277450109e-06, + "loss": 0.0048, + "step": 43605 + }, + { + "epoch": 13.47, + "learning_rate": 5.093406989595705e-06, + "loss": 0.0058, + "step": 43606 + }, + { + "epoch": 13.47, + "learning_rate": 5.092971216962608e-06, + "loss": 0.0046, + "step": 43607 + }, + { + "epoch": 13.47, + "learning_rate": 5.092535456602885e-06, + "loss": 0.0039, + "step": 43608 + }, + { + "epoch": 13.47, + "learning_rate": 5.092099708517622e-06, + "loss": 0.0046, + "step": 43609 + }, + { + "epoch": 13.47, + "learning_rate": 5.091663972707912e-06, + "loss": 0.0037, + "step": 43610 + }, + { + "epoch": 13.47, + "learning_rate": 5.091228249174851e-06, + "loss": 0.0045, + "step": 43611 + }, + { + "epoch": 13.47, + "learning_rate": 5.090792537919518e-06, + "loss": 0.0038, + "step": 43612 + }, + { + "epoch": 13.47, + "learning_rate": 5.0903568389430136e-06, + "loss": 0.0064, + "step": 43613 + }, + { + "epoch": 13.47, + "learning_rate": 5.089921152246421e-06, + "loss": 0.0052, + "step": 43614 + }, + { + "epoch": 13.47, + "learning_rate": 5.089485477830827e-06, + "loss": 0.0056, + "step": 43615 + }, + { + "epoch": 13.47, + "learning_rate": 5.0890498156973265e-06, + "loss": 0.0045, + "step": 43616 + }, + { + "epoch": 13.47, + "learning_rate": 5.088614165847012e-06, + "loss": 0.0048, + "step": 43617 + }, + { + "epoch": 13.47, + "learning_rate": 5.088178528280969e-06, + "loss": 0.0053, + "step": 43618 + }, + { + "epoch": 13.47, + "learning_rate": 5.087742903000284e-06, + "loss": 0.0062, + "step": 43619 + }, + { + "epoch": 13.47, + "learning_rate": 5.0873072900060524e-06, + "loss": 0.004, + "step": 43620 + }, + { + "epoch": 13.47, + "learning_rate": 5.086871689299357e-06, + "loss": 0.0049, + "step": 43621 + }, + { + "epoch": 13.47, + "learning_rate": 5.086436100881293e-06, + "loss": 0.0046, + "step": 43622 + }, + { + "epoch": 13.47, + "learning_rate": 5.086000524752953e-06, + "loss": 0.0039, + "step": 43623 + }, + { + "epoch": 13.47, + "learning_rate": 5.0855649609154216e-06, + "loss": 0.005, + "step": 43624 + }, + { + "epoch": 13.47, + "learning_rate": 5.085129409369784e-06, + "loss": 0.0049, + "step": 43625 + }, + { + "epoch": 13.47, + "learning_rate": 5.0846938701171385e-06, + "loss": 0.0037, + "step": 43626 + }, + { + "epoch": 13.47, + "learning_rate": 5.084258343158565e-06, + "loss": 0.0047, + "step": 43627 + }, + { + "epoch": 13.47, + "learning_rate": 5.083822828495164e-06, + "loss": 0.005, + "step": 43628 + }, + { + "epoch": 13.47, + "learning_rate": 5.0833873261280175e-06, + "loss": 0.0054, + "step": 43629 + }, + { + "epoch": 13.47, + "learning_rate": 5.082951836058212e-06, + "loss": 0.0042, + "step": 43630 + }, + { + "epoch": 13.47, + "learning_rate": 5.082516358286842e-06, + "loss": 0.0052, + "step": 43631 + }, + { + "epoch": 13.47, + "learning_rate": 5.082080892814998e-06, + "loss": 0.0051, + "step": 43632 + }, + { + "epoch": 13.47, + "learning_rate": 5.081645439643763e-06, + "loss": 0.0042, + "step": 43633 + }, + { + "epoch": 13.47, + "learning_rate": 5.081209998774234e-06, + "loss": 0.0039, + "step": 43634 + }, + { + "epoch": 13.48, + "learning_rate": 5.080774570207496e-06, + "loss": 0.005, + "step": 43635 + }, + { + "epoch": 13.48, + "learning_rate": 5.0803391539446335e-06, + "loss": 0.0046, + "step": 43636 + }, + { + "epoch": 13.48, + "learning_rate": 5.079903749986741e-06, + "loss": 0.005, + "step": 43637 + }, + { + "epoch": 13.48, + "learning_rate": 5.079468358334909e-06, + "loss": 0.0047, + "step": 43638 + }, + { + "epoch": 13.48, + "learning_rate": 5.0790329789902255e-06, + "loss": 0.0055, + "step": 43639 + }, + { + "epoch": 13.48, + "learning_rate": 5.078597611953774e-06, + "loss": 0.0053, + "step": 43640 + }, + { + "epoch": 13.48, + "learning_rate": 5.078162257226651e-06, + "loss": 0.0052, + "step": 43641 + }, + { + "epoch": 13.48, + "learning_rate": 5.077726914809938e-06, + "loss": 0.0045, + "step": 43642 + }, + { + "epoch": 13.48, + "learning_rate": 5.077291584704728e-06, + "loss": 0.0041, + "step": 43643 + }, + { + "epoch": 13.48, + "learning_rate": 5.076856266912114e-06, + "loss": 0.0056, + "step": 43644 + }, + { + "epoch": 13.48, + "learning_rate": 5.07642096143318e-06, + "loss": 0.0056, + "step": 43645 + }, + { + "epoch": 13.48, + "learning_rate": 5.07598566826901e-06, + "loss": 0.006, + "step": 43646 + }, + { + "epoch": 13.48, + "learning_rate": 5.075550387420698e-06, + "loss": 0.0039, + "step": 43647 + }, + { + "epoch": 13.48, + "learning_rate": 5.075115118889338e-06, + "loss": 0.0048, + "step": 43648 + }, + { + "epoch": 13.48, + "learning_rate": 5.074679862676013e-06, + "loss": 0.0051, + "step": 43649 + }, + { + "epoch": 13.48, + "learning_rate": 5.0742446187818075e-06, + "loss": 0.0041, + "step": 43650 + }, + { + "epoch": 13.48, + "learning_rate": 5.073809387207819e-06, + "loss": 0.0044, + "step": 43651 + }, + { + "epoch": 13.48, + "learning_rate": 5.0733741679551275e-06, + "loss": 0.0053, + "step": 43652 + }, + { + "epoch": 13.48, + "learning_rate": 5.072938961024827e-06, + "loss": 0.0055, + "step": 43653 + }, + { + "epoch": 13.48, + "learning_rate": 5.072503766418007e-06, + "loss": 0.0058, + "step": 43654 + }, + { + "epoch": 13.48, + "learning_rate": 5.0720685841357545e-06, + "loss": 0.0043, + "step": 43655 + }, + { + "epoch": 13.48, + "learning_rate": 5.0716334141791536e-06, + "loss": 0.0047, + "step": 43656 + }, + { + "epoch": 13.48, + "learning_rate": 5.0711982565493e-06, + "loss": 0.0042, + "step": 43657 + }, + { + "epoch": 13.48, + "learning_rate": 5.070763111247275e-06, + "loss": 0.0048, + "step": 43658 + }, + { + "epoch": 13.48, + "learning_rate": 5.0703279782741744e-06, + "loss": 0.0038, + "step": 43659 + }, + { + "epoch": 13.48, + "learning_rate": 5.069892857631081e-06, + "loss": 0.005, + "step": 43660 + }, + { + "epoch": 13.48, + "learning_rate": 5.069457749319082e-06, + "loss": 0.0041, + "step": 43661 + }, + { + "epoch": 13.48, + "learning_rate": 5.06902265333927e-06, + "loss": 0.0043, + "step": 43662 + }, + { + "epoch": 13.48, + "learning_rate": 5.068587569692733e-06, + "loss": 0.0058, + "step": 43663 + }, + { + "epoch": 13.48, + "learning_rate": 5.068152498380556e-06, + "loss": 0.004, + "step": 43664 + }, + { + "epoch": 13.48, + "learning_rate": 5.067717439403832e-06, + "loss": 0.0053, + "step": 43665 + }, + { + "epoch": 13.48, + "learning_rate": 5.067282392763646e-06, + "loss": 0.0037, + "step": 43666 + }, + { + "epoch": 13.49, + "learning_rate": 5.066847358461084e-06, + "loss": 0.0092, + "step": 43667 + }, + { + "epoch": 13.49, + "learning_rate": 5.066412336497235e-06, + "loss": 0.0053, + "step": 43668 + }, + { + "epoch": 13.49, + "learning_rate": 5.065977326873192e-06, + "loss": 0.005, + "step": 43669 + }, + { + "epoch": 13.49, + "learning_rate": 5.06554232959004e-06, + "loss": 0.0052, + "step": 43670 + }, + { + "epoch": 13.49, + "learning_rate": 5.065107344648865e-06, + "loss": 0.006, + "step": 43671 + }, + { + "epoch": 13.49, + "learning_rate": 5.064672372050759e-06, + "loss": 0.005, + "step": 43672 + }, + { + "epoch": 13.49, + "learning_rate": 5.064237411796804e-06, + "loss": 0.0048, + "step": 43673 + }, + { + "epoch": 13.49, + "learning_rate": 5.06380246388809e-06, + "loss": 0.0056, + "step": 43674 + }, + { + "epoch": 13.49, + "learning_rate": 5.063367528325711e-06, + "loss": 0.0034, + "step": 43675 + }, + { + "epoch": 13.49, + "learning_rate": 5.062932605110751e-06, + "loss": 0.0042, + "step": 43676 + }, + { + "epoch": 13.49, + "learning_rate": 5.0624976942442925e-06, + "loss": 0.0039, + "step": 43677 + }, + { + "epoch": 13.49, + "learning_rate": 5.062062795727427e-06, + "loss": 0.0057, + "step": 43678 + }, + { + "epoch": 13.49, + "learning_rate": 5.0616279095612486e-06, + "loss": 0.0064, + "step": 43679 + }, + { + "epoch": 13.49, + "learning_rate": 5.0611930357468384e-06, + "loss": 0.0043, + "step": 43680 + }, + { + "epoch": 13.49, + "learning_rate": 5.0607581742852815e-06, + "loss": 0.0045, + "step": 43681 + }, + { + "epoch": 13.49, + "learning_rate": 5.060323325177674e-06, + "loss": 0.0048, + "step": 43682 + }, + { + "epoch": 13.49, + "learning_rate": 5.059888488425093e-06, + "loss": 0.0045, + "step": 43683 + }, + { + "epoch": 13.49, + "learning_rate": 5.059453664028634e-06, + "loss": 0.006, + "step": 43684 + }, + { + "epoch": 13.49, + "learning_rate": 5.059018851989385e-06, + "loss": 0.0053, + "step": 43685 + }, + { + "epoch": 13.49, + "learning_rate": 5.058584052308432e-06, + "loss": 0.0053, + "step": 43686 + }, + { + "epoch": 13.49, + "learning_rate": 5.058149264986857e-06, + "loss": 0.0041, + "step": 43687 + }, + { + "epoch": 13.49, + "learning_rate": 5.0577144900257554e-06, + "loss": 0.0051, + "step": 43688 + }, + { + "epoch": 13.49, + "learning_rate": 5.057279727426209e-06, + "loss": 0.0043, + "step": 43689 + }, + { + "epoch": 13.49, + "learning_rate": 5.056844977189311e-06, + "loss": 0.0052, + "step": 43690 + }, + { + "epoch": 13.49, + "learning_rate": 5.056410239316143e-06, + "loss": 0.0051, + "step": 43691 + }, + { + "epoch": 13.49, + "learning_rate": 5.055975513807794e-06, + "loss": 0.0049, + "step": 43692 + }, + { + "epoch": 13.49, + "learning_rate": 5.055540800665349e-06, + "loss": 0.0043, + "step": 43693 + }, + { + "epoch": 13.49, + "learning_rate": 5.055106099889904e-06, + "loss": 0.0051, + "step": 43694 + }, + { + "epoch": 13.49, + "learning_rate": 5.054671411482537e-06, + "loss": 0.0053, + "step": 43695 + }, + { + "epoch": 13.49, + "learning_rate": 5.054236735444341e-06, + "loss": 0.0053, + "step": 43696 + }, + { + "epoch": 13.49, + "learning_rate": 5.0538020717764025e-06, + "loss": 0.0049, + "step": 43697 + }, + { + "epoch": 13.49, + "learning_rate": 5.053367420479802e-06, + "loss": 0.0049, + "step": 43698 + }, + { + "epoch": 13.5, + "learning_rate": 5.052932781555633e-06, + "loss": 0.0046, + "step": 43699 + }, + { + "epoch": 13.5, + "learning_rate": 5.0524981550049845e-06, + "loss": 0.008, + "step": 43700 + }, + { + "epoch": 13.5, + "learning_rate": 5.052063540828941e-06, + "loss": 0.0053, + "step": 43701 + }, + { + "epoch": 13.5, + "learning_rate": 5.051628939028584e-06, + "loss": 0.0041, + "step": 43702 + }, + { + "epoch": 13.5, + "learning_rate": 5.051194349605011e-06, + "loss": 0.0044, + "step": 43703 + }, + { + "epoch": 13.5, + "learning_rate": 5.050759772559299e-06, + "loss": 0.0048, + "step": 43704 + }, + { + "epoch": 13.5, + "learning_rate": 5.050325207892539e-06, + "loss": 0.0053, + "step": 43705 + }, + { + "epoch": 13.5, + "learning_rate": 5.049890655605827e-06, + "loss": 0.0043, + "step": 43706 + }, + { + "epoch": 13.5, + "learning_rate": 5.0494561157002335e-06, + "loss": 0.0059, + "step": 43707 + }, + { + "epoch": 13.5, + "learning_rate": 5.049021588176852e-06, + "loss": 0.0046, + "step": 43708 + }, + { + "epoch": 13.5, + "learning_rate": 5.0485870730367725e-06, + "loss": 0.0053, + "step": 43709 + }, + { + "epoch": 13.5, + "learning_rate": 5.048152570281082e-06, + "loss": 0.0056, + "step": 43710 + }, + { + "epoch": 13.5, + "learning_rate": 5.047718079910866e-06, + "loss": 0.0053, + "step": 43711 + }, + { + "epoch": 13.5, + "learning_rate": 5.047283601927206e-06, + "loss": 0.0044, + "step": 43712 + }, + { + "epoch": 13.5, + "learning_rate": 5.046849136331197e-06, + "loss": 0.0046, + "step": 43713 + }, + { + "epoch": 13.5, + "learning_rate": 5.046414683123917e-06, + "loss": 0.005, + "step": 43714 + }, + { + "epoch": 13.5, + "learning_rate": 5.045980242306459e-06, + "loss": 0.0051, + "step": 43715 + }, + { + "epoch": 13.5, + "learning_rate": 5.045545813879915e-06, + "loss": 0.0037, + "step": 43716 + }, + { + "epoch": 13.5, + "learning_rate": 5.045111397845357e-06, + "loss": 0.0044, + "step": 43717 + }, + { + "epoch": 13.5, + "learning_rate": 5.044676994203879e-06, + "loss": 0.0043, + "step": 43718 + }, + { + "epoch": 13.5, + "learning_rate": 5.0442426029565705e-06, + "loss": 0.0049, + "step": 43719 + }, + { + "epoch": 13.5, + "learning_rate": 5.043808224104511e-06, + "loss": 0.0043, + "step": 43720 + }, + { + "epoch": 13.5, + "learning_rate": 5.043373857648797e-06, + "loss": 0.0056, + "step": 43721 + }, + { + "epoch": 13.5, + "learning_rate": 5.0429395035905085e-06, + "loss": 0.0045, + "step": 43722 + }, + { + "epoch": 13.5, + "learning_rate": 5.042505161930727e-06, + "loss": 0.0048, + "step": 43723 + }, + { + "epoch": 13.5, + "learning_rate": 5.042070832670546e-06, + "loss": 0.0059, + "step": 43724 + }, + { + "epoch": 13.5, + "learning_rate": 5.041636515811053e-06, + "loss": 0.0066, + "step": 43725 + }, + { + "epoch": 13.5, + "learning_rate": 5.041202211353332e-06, + "loss": 0.0055, + "step": 43726 + }, + { + "epoch": 13.5, + "learning_rate": 5.040767919298465e-06, + "loss": 0.0053, + "step": 43727 + }, + { + "epoch": 13.5, + "learning_rate": 5.040333639647545e-06, + "loss": 0.0079, + "step": 43728 + }, + { + "epoch": 13.5, + "learning_rate": 5.039899372401652e-06, + "loss": 0.0053, + "step": 43729 + }, + { + "epoch": 13.5, + "learning_rate": 5.039465117561874e-06, + "loss": 0.0048, + "step": 43730 + }, + { + "epoch": 13.5, + "learning_rate": 5.0390308751293045e-06, + "loss": 0.0049, + "step": 43731 + }, + { + "epoch": 13.51, + "learning_rate": 5.038596645105023e-06, + "loss": 0.0058, + "step": 43732 + }, + { + "epoch": 13.51, + "learning_rate": 5.038162427490111e-06, + "loss": 0.0054, + "step": 43733 + }, + { + "epoch": 13.51, + "learning_rate": 5.0377282222856646e-06, + "loss": 0.0037, + "step": 43734 + }, + { + "epoch": 13.51, + "learning_rate": 5.037294029492761e-06, + "loss": 0.0042, + "step": 43735 + }, + { + "epoch": 13.51, + "learning_rate": 5.036859849112494e-06, + "loss": 0.0047, + "step": 43736 + }, + { + "epoch": 13.51, + "learning_rate": 5.0364256811459455e-06, + "loss": 0.0051, + "step": 43737 + }, + { + "epoch": 13.51, + "learning_rate": 5.035991525594198e-06, + "loss": 0.0046, + "step": 43738 + }, + { + "epoch": 13.51, + "learning_rate": 5.035557382458342e-06, + "loss": 0.0046, + "step": 43739 + }, + { + "epoch": 13.51, + "learning_rate": 5.035123251739461e-06, + "loss": 0.0049, + "step": 43740 + }, + { + "epoch": 13.51, + "learning_rate": 5.034689133438646e-06, + "loss": 0.0051, + "step": 43741 + }, + { + "epoch": 13.51, + "learning_rate": 5.03425502755698e-06, + "loss": 0.0054, + "step": 43742 + }, + { + "epoch": 13.51, + "learning_rate": 5.0338209340955435e-06, + "loss": 0.005, + "step": 43743 + }, + { + "epoch": 13.51, + "learning_rate": 5.033386853055431e-06, + "loss": 0.006, + "step": 43744 + }, + { + "epoch": 13.51, + "learning_rate": 5.03295278443772e-06, + "loss": 0.0041, + "step": 43745 + }, + { + "epoch": 13.51, + "learning_rate": 5.032518728243504e-06, + "loss": 0.0046, + "step": 43746 + }, + { + "epoch": 13.51, + "learning_rate": 5.032084684473864e-06, + "loss": 0.0046, + "step": 43747 + }, + { + "epoch": 13.51, + "learning_rate": 5.031650653129882e-06, + "loss": 0.0051, + "step": 43748 + }, + { + "epoch": 13.51, + "learning_rate": 5.03121663421265e-06, + "loss": 0.0055, + "step": 43749 + }, + { + "epoch": 13.51, + "learning_rate": 5.030782627723254e-06, + "loss": 0.0056, + "step": 43750 + }, + { + "epoch": 13.51, + "learning_rate": 5.0303486336627724e-06, + "loss": 0.0053, + "step": 43751 + }, + { + "epoch": 13.51, + "learning_rate": 5.029914652032299e-06, + "loss": 0.0047, + "step": 43752 + }, + { + "epoch": 13.51, + "learning_rate": 5.029480682832917e-06, + "loss": 0.0055, + "step": 43753 + }, + { + "epoch": 13.51, + "learning_rate": 5.029046726065706e-06, + "loss": 0.0041, + "step": 43754 + }, + { + "epoch": 13.51, + "learning_rate": 5.028612781731756e-06, + "loss": 0.0057, + "step": 43755 + }, + { + "epoch": 13.51, + "learning_rate": 5.028178849832155e-06, + "loss": 0.0047, + "step": 43756 + }, + { + "epoch": 13.51, + "learning_rate": 5.027744930367986e-06, + "loss": 0.0055, + "step": 43757 + }, + { + "epoch": 13.51, + "learning_rate": 5.027311023340331e-06, + "loss": 0.0056, + "step": 43758 + }, + { + "epoch": 13.51, + "learning_rate": 5.026877128750281e-06, + "loss": 0.0055, + "step": 43759 + }, + { + "epoch": 13.51, + "learning_rate": 5.026443246598914e-06, + "loss": 0.0041, + "step": 43760 + }, + { + "epoch": 13.51, + "learning_rate": 5.0260093768873195e-06, + "loss": 0.0053, + "step": 43761 + }, + { + "epoch": 13.51, + "learning_rate": 5.025575519616588e-06, + "loss": 0.0044, + "step": 43762 + }, + { + "epoch": 13.51, + "learning_rate": 5.025141674787799e-06, + "loss": 0.0065, + "step": 43763 + }, + { + "epoch": 13.52, + "learning_rate": 5.024707842402034e-06, + "loss": 0.005, + "step": 43764 + }, + { + "epoch": 13.52, + "learning_rate": 5.024274022460385e-06, + "loss": 0.0054, + "step": 43765 + }, + { + "epoch": 13.52, + "learning_rate": 5.023840214963931e-06, + "loss": 0.0049, + "step": 43766 + }, + { + "epoch": 13.52, + "learning_rate": 5.0234064199137645e-06, + "loss": 0.0051, + "step": 43767 + }, + { + "epoch": 13.52, + "learning_rate": 5.022972637310966e-06, + "loss": 0.0048, + "step": 43768 + }, + { + "epoch": 13.52, + "learning_rate": 5.022538867156617e-06, + "loss": 0.0047, + "step": 43769 + }, + { + "epoch": 13.52, + "learning_rate": 5.022105109451804e-06, + "loss": 0.0035, + "step": 43770 + }, + { + "epoch": 13.52, + "learning_rate": 5.021671364197621e-06, + "loss": 0.0059, + "step": 43771 + }, + { + "epoch": 13.52, + "learning_rate": 5.021237631395142e-06, + "loss": 0.0045, + "step": 43772 + }, + { + "epoch": 13.52, + "learning_rate": 5.0208039110454575e-06, + "loss": 0.0053, + "step": 43773 + }, + { + "epoch": 13.52, + "learning_rate": 5.020370203149647e-06, + "loss": 0.0061, + "step": 43774 + }, + { + "epoch": 13.52, + "learning_rate": 5.0199365077088035e-06, + "loss": 0.0062, + "step": 43775 + }, + { + "epoch": 13.52, + "learning_rate": 5.019502824724003e-06, + "loss": 0.006, + "step": 43776 + }, + { + "epoch": 13.52, + "learning_rate": 5.0190691541963385e-06, + "loss": 0.0044, + "step": 43777 + }, + { + "epoch": 13.52, + "learning_rate": 5.01863549612689e-06, + "loss": 0.0047, + "step": 43778 + }, + { + "epoch": 13.52, + "learning_rate": 5.0182018505167395e-06, + "loss": 0.0066, + "step": 43779 + }, + { + "epoch": 13.52, + "learning_rate": 5.017768217366974e-06, + "loss": 0.0056, + "step": 43780 + }, + { + "epoch": 13.52, + "learning_rate": 5.0173345966786825e-06, + "loss": 0.0043, + "step": 43781 + }, + { + "epoch": 13.52, + "learning_rate": 5.016900988452944e-06, + "loss": 0.0054, + "step": 43782 + }, + { + "epoch": 13.52, + "learning_rate": 5.016467392690847e-06, + "loss": 0.0062, + "step": 43783 + }, + { + "epoch": 13.52, + "learning_rate": 5.016033809393475e-06, + "loss": 0.0045, + "step": 43784 + }, + { + "epoch": 13.52, + "learning_rate": 5.0156002385619065e-06, + "loss": 0.0051, + "step": 43785 + }, + { + "epoch": 13.52, + "learning_rate": 5.015166680197232e-06, + "loss": 0.0051, + "step": 43786 + }, + { + "epoch": 13.52, + "learning_rate": 5.014733134300538e-06, + "loss": 0.0035, + "step": 43787 + }, + { + "epoch": 13.52, + "learning_rate": 5.014299600872905e-06, + "loss": 0.0055, + "step": 43788 + }, + { + "epoch": 13.52, + "learning_rate": 5.013866079915416e-06, + "loss": 0.0053, + "step": 43789 + }, + { + "epoch": 13.52, + "learning_rate": 5.01343257142916e-06, + "loss": 0.0047, + "step": 43790 + }, + { + "epoch": 13.52, + "learning_rate": 5.012999075415215e-06, + "loss": 0.0043, + "step": 43791 + }, + { + "epoch": 13.52, + "learning_rate": 5.012565591874669e-06, + "loss": 0.0062, + "step": 43792 + }, + { + "epoch": 13.52, + "learning_rate": 5.01213212080861e-06, + "loss": 0.0044, + "step": 43793 + }, + { + "epoch": 13.52, + "learning_rate": 5.011698662218119e-06, + "loss": 0.004, + "step": 43794 + }, + { + "epoch": 13.52, + "learning_rate": 5.011265216104274e-06, + "loss": 0.0046, + "step": 43795 + }, + { + "epoch": 13.53, + "learning_rate": 5.0108317824681685e-06, + "loss": 0.0058, + "step": 43796 + }, + { + "epoch": 13.53, + "learning_rate": 5.0103983613108795e-06, + "loss": 0.0041, + "step": 43797 + }, + { + "epoch": 13.53, + "learning_rate": 5.0099649526334996e-06, + "loss": 0.0051, + "step": 43798 + }, + { + "epoch": 13.53, + "learning_rate": 5.009531556437105e-06, + "loss": 0.0041, + "step": 43799 + }, + { + "epoch": 13.53, + "learning_rate": 5.00909817272278e-06, + "loss": 0.0045, + "step": 43800 + }, + { + "epoch": 13.53, + "learning_rate": 5.008664801491609e-06, + "loss": 0.0045, + "step": 43801 + }, + { + "epoch": 13.53, + "learning_rate": 5.0082314427446835e-06, + "loss": 0.0043, + "step": 43802 + }, + { + "epoch": 13.53, + "learning_rate": 5.007798096483076e-06, + "loss": 0.0049, + "step": 43803 + }, + { + "epoch": 13.53, + "learning_rate": 5.007364762707881e-06, + "loss": 0.0043, + "step": 43804 + }, + { + "epoch": 13.53, + "learning_rate": 5.006931441420173e-06, + "loss": 0.0041, + "step": 43805 + }, + { + "epoch": 13.53, + "learning_rate": 5.006498132621045e-06, + "loss": 0.0048, + "step": 43806 + }, + { + "epoch": 13.53, + "learning_rate": 5.00606483631157e-06, + "loss": 0.0056, + "step": 43807 + }, + { + "epoch": 13.53, + "learning_rate": 5.0056315524928445e-06, + "loss": 0.0045, + "step": 43808 + }, + { + "epoch": 13.53, + "learning_rate": 5.005198281165944e-06, + "loss": 0.0042, + "step": 43809 + }, + { + "epoch": 13.53, + "learning_rate": 5.004765022331949e-06, + "loss": 0.0059, + "step": 43810 + }, + { + "epoch": 13.53, + "learning_rate": 5.004331775991949e-06, + "loss": 0.0049, + "step": 43811 + }, + { + "epoch": 13.53, + "learning_rate": 5.003898542147028e-06, + "loss": 0.0056, + "step": 43812 + }, + { + "epoch": 13.53, + "learning_rate": 5.003465320798267e-06, + "loss": 0.006, + "step": 43813 + }, + { + "epoch": 13.53, + "learning_rate": 5.003032111946752e-06, + "loss": 0.0049, + "step": 43814 + }, + { + "epoch": 13.53, + "learning_rate": 5.0025989155935665e-06, + "loss": 0.0055, + "step": 43815 + }, + { + "epoch": 13.53, + "learning_rate": 5.002165731739787e-06, + "loss": 0.0042, + "step": 43816 + }, + { + "epoch": 13.53, + "learning_rate": 5.001732560386506e-06, + "loss": 0.0056, + "step": 43817 + }, + { + "epoch": 13.53, + "learning_rate": 5.001299401534804e-06, + "loss": 0.0047, + "step": 43818 + }, + { + "epoch": 13.53, + "learning_rate": 5.000866255185765e-06, + "loss": 0.0051, + "step": 43819 + }, + { + "epoch": 13.53, + "learning_rate": 5.000433121340466e-06, + "loss": 0.0053, + "step": 43820 + }, + { + "epoch": 13.53, + "learning_rate": 5.000000000000003e-06, + "loss": 0.0048, + "step": 43821 + }, + { + "epoch": 13.53, + "learning_rate": 4.999566891165446e-06, + "loss": 0.0042, + "step": 43822 + }, + { + "epoch": 13.53, + "learning_rate": 4.999133794837884e-06, + "loss": 0.005, + "step": 43823 + }, + { + "epoch": 13.53, + "learning_rate": 4.998700711018408e-06, + "loss": 0.0061, + "step": 43824 + }, + { + "epoch": 13.53, + "learning_rate": 4.998267639708087e-06, + "loss": 0.0044, + "step": 43825 + }, + { + "epoch": 13.53, + "learning_rate": 4.9978345809080095e-06, + "loss": 0.0045, + "step": 43826 + }, + { + "epoch": 13.53, + "learning_rate": 4.9974015346192654e-06, + "loss": 0.0052, + "step": 43827 + }, + { + "epoch": 13.53, + "learning_rate": 4.996968500842928e-06, + "loss": 0.0049, + "step": 43828 + }, + { + "epoch": 13.54, + "learning_rate": 4.996535479580089e-06, + "loss": 0.0049, + "step": 43829 + }, + { + "epoch": 13.54, + "learning_rate": 4.996102470831827e-06, + "loss": 0.0048, + "step": 43830 + }, + { + "epoch": 13.54, + "learning_rate": 4.995669474599222e-06, + "loss": 0.0045, + "step": 43831 + }, + { + "epoch": 13.54, + "learning_rate": 4.99523649088336e-06, + "loss": 0.0034, + "step": 43832 + }, + { + "epoch": 13.54, + "learning_rate": 4.994803519685327e-06, + "loss": 0.005, + "step": 43833 + }, + { + "epoch": 13.54, + "learning_rate": 4.994370561006206e-06, + "loss": 0.0052, + "step": 43834 + }, + { + "epoch": 13.54, + "learning_rate": 4.993937614847071e-06, + "loss": 0.0048, + "step": 43835 + }, + { + "epoch": 13.54, + "learning_rate": 4.993504681209016e-06, + "loss": 0.0071, + "step": 43836 + }, + { + "epoch": 13.54, + "learning_rate": 4.993071760093114e-06, + "loss": 0.005, + "step": 43837 + }, + { + "epoch": 13.54, + "learning_rate": 4.992638851500454e-06, + "loss": 0.0044, + "step": 43838 + }, + { + "epoch": 13.54, + "learning_rate": 4.992205955432121e-06, + "loss": 0.0063, + "step": 43839 + }, + { + "epoch": 13.54, + "learning_rate": 4.9917730718891945e-06, + "loss": 0.0112, + "step": 43840 + }, + { + "epoch": 13.54, + "learning_rate": 4.991340200872753e-06, + "loss": 0.0049, + "step": 43841 + }, + { + "epoch": 13.54, + "learning_rate": 4.990907342383883e-06, + "loss": 0.0048, + "step": 43842 + }, + { + "epoch": 13.54, + "learning_rate": 4.99047449642367e-06, + "loss": 0.0035, + "step": 43843 + }, + { + "epoch": 13.54, + "learning_rate": 4.990041662993192e-06, + "loss": 0.0047, + "step": 43844 + }, + { + "epoch": 13.54, + "learning_rate": 4.989608842093536e-06, + "loss": 0.0047, + "step": 43845 + }, + { + "epoch": 13.54, + "learning_rate": 4.989176033725783e-06, + "loss": 0.0047, + "step": 43846 + }, + { + "epoch": 13.54, + "learning_rate": 4.988743237891012e-06, + "loss": 0.0052, + "step": 43847 + }, + { + "epoch": 13.54, + "learning_rate": 4.988310454590306e-06, + "loss": 0.0049, + "step": 43848 + }, + { + "epoch": 13.54, + "learning_rate": 4.987877683824754e-06, + "loss": 0.0047, + "step": 43849 + }, + { + "epoch": 13.54, + "learning_rate": 4.987444925595435e-06, + "loss": 0.0045, + "step": 43850 + }, + { + "epoch": 13.54, + "learning_rate": 4.987012179903425e-06, + "loss": 0.0043, + "step": 43851 + }, + { + "epoch": 13.54, + "learning_rate": 4.986579446749817e-06, + "loss": 0.0041, + "step": 43852 + }, + { + "epoch": 13.54, + "learning_rate": 4.986146726135684e-06, + "loss": 0.0062, + "step": 43853 + }, + { + "epoch": 13.54, + "learning_rate": 4.985714018062113e-06, + "loss": 0.0048, + "step": 43854 + }, + { + "epoch": 13.54, + "learning_rate": 4.985281322530194e-06, + "loss": 0.0041, + "step": 43855 + }, + { + "epoch": 13.54, + "learning_rate": 4.9848486395409915e-06, + "loss": 0.0055, + "step": 43856 + }, + { + "epoch": 13.54, + "learning_rate": 4.9844159690955986e-06, + "loss": 0.0061, + "step": 43857 + }, + { + "epoch": 13.54, + "learning_rate": 4.983983311195099e-06, + "loss": 0.0072, + "step": 43858 + }, + { + "epoch": 13.54, + "learning_rate": 4.9835506658405685e-06, + "loss": 0.004, + "step": 43859 + }, + { + "epoch": 13.54, + "learning_rate": 4.983118033033096e-06, + "loss": 0.0048, + "step": 43860 + }, + { + "epoch": 13.55, + "learning_rate": 4.982685412773763e-06, + "loss": 0.0039, + "step": 43861 + }, + { + "epoch": 13.55, + "learning_rate": 4.982252805063642e-06, + "loss": 0.0051, + "step": 43862 + }, + { + "epoch": 13.55, + "learning_rate": 4.9818202099038225e-06, + "loss": 0.0065, + "step": 43863 + }, + { + "epoch": 13.55, + "learning_rate": 4.981387627295391e-06, + "loss": 0.0041, + "step": 43864 + }, + { + "epoch": 13.55, + "learning_rate": 4.980955057239424e-06, + "loss": 0.0058, + "step": 43865 + }, + { + "epoch": 13.55, + "learning_rate": 4.9805224997369995e-06, + "loss": 0.0046, + "step": 43866 + }, + { + "epoch": 13.55, + "learning_rate": 4.980089954789207e-06, + "loss": 0.0041, + "step": 43867 + }, + { + "epoch": 13.55, + "learning_rate": 4.979657422397122e-06, + "loss": 0.0046, + "step": 43868 + }, + { + "epoch": 13.55, + "learning_rate": 4.97922490256183e-06, + "loss": 0.0041, + "step": 43869 + }, + { + "epoch": 13.55, + "learning_rate": 4.978792395284415e-06, + "loss": 0.004, + "step": 43870 + }, + { + "epoch": 13.55, + "learning_rate": 4.978359900565956e-06, + "loss": 0.0054, + "step": 43871 + }, + { + "epoch": 13.55, + "learning_rate": 4.9779274184075325e-06, + "loss": 0.0044, + "step": 43872 + }, + { + "epoch": 13.55, + "learning_rate": 4.977494948810228e-06, + "loss": 0.0046, + "step": 43873 + }, + { + "epoch": 13.55, + "learning_rate": 4.977062491775126e-06, + "loss": 0.0052, + "step": 43874 + }, + { + "epoch": 13.55, + "learning_rate": 4.97663004730331e-06, + "loss": 0.0052, + "step": 43875 + }, + { + "epoch": 13.55, + "learning_rate": 4.9761976153958535e-06, + "loss": 0.0054, + "step": 43876 + }, + { + "epoch": 13.55, + "learning_rate": 4.975765196053847e-06, + "loss": 0.0059, + "step": 43877 + }, + { + "epoch": 13.55, + "learning_rate": 4.975332789278363e-06, + "loss": 0.0051, + "step": 43878 + }, + { + "epoch": 13.55, + "learning_rate": 4.97490039507049e-06, + "loss": 0.0036, + "step": 43879 + }, + { + "epoch": 13.55, + "learning_rate": 4.97446801343131e-06, + "loss": 0.0062, + "step": 43880 + }, + { + "epoch": 13.55, + "learning_rate": 4.974035644361903e-06, + "loss": 0.0051, + "step": 43881 + }, + { + "epoch": 13.55, + "learning_rate": 4.973603287863346e-06, + "loss": 0.0057, + "step": 43882 + }, + { + "epoch": 13.55, + "learning_rate": 4.973170943936727e-06, + "loss": 0.0049, + "step": 43883 + }, + { + "epoch": 13.55, + "learning_rate": 4.972738612583121e-06, + "loss": 0.0043, + "step": 43884 + }, + { + "epoch": 13.55, + "learning_rate": 4.972306293803616e-06, + "loss": 0.005, + "step": 43885 + }, + { + "epoch": 13.55, + "learning_rate": 4.971873987599291e-06, + "loss": 0.005, + "step": 43886 + }, + { + "epoch": 13.55, + "learning_rate": 4.971441693971221e-06, + "loss": 0.0042, + "step": 43887 + }, + { + "epoch": 13.55, + "learning_rate": 4.971009412920493e-06, + "loss": 0.0042, + "step": 43888 + }, + { + "epoch": 13.55, + "learning_rate": 4.970577144448191e-06, + "loss": 0.0044, + "step": 43889 + }, + { + "epoch": 13.55, + "learning_rate": 4.9701448885553905e-06, + "loss": 0.0054, + "step": 43890 + }, + { + "epoch": 13.55, + "learning_rate": 4.969712645243177e-06, + "loss": 0.0066, + "step": 43891 + }, + { + "epoch": 13.55, + "learning_rate": 4.969280414512631e-06, + "loss": 0.0063, + "step": 43892 + }, + { + "epoch": 13.55, + "learning_rate": 4.968848196364829e-06, + "loss": 0.0068, + "step": 43893 + }, + { + "epoch": 13.56, + "learning_rate": 4.968415990800853e-06, + "loss": 0.0063, + "step": 43894 + }, + { + "epoch": 13.56, + "learning_rate": 4.9679837978217915e-06, + "loss": 0.0042, + "step": 43895 + }, + { + "epoch": 13.56, + "learning_rate": 4.9675516174287205e-06, + "loss": 0.0044, + "step": 43896 + }, + { + "epoch": 13.56, + "learning_rate": 4.967119449622716e-06, + "loss": 0.0046, + "step": 43897 + }, + { + "epoch": 13.56, + "learning_rate": 4.966687294404868e-06, + "loss": 0.0048, + "step": 43898 + }, + { + "epoch": 13.56, + "learning_rate": 4.9662551517762505e-06, + "loss": 0.0063, + "step": 43899 + }, + { + "epoch": 13.56, + "learning_rate": 4.965823021737946e-06, + "loss": 0.0035, + "step": 43900 + }, + { + "epoch": 13.56, + "learning_rate": 4.96539090429104e-06, + "loss": 0.0058, + "step": 43901 + }, + { + "epoch": 13.56, + "learning_rate": 4.964958799436609e-06, + "loss": 0.0047, + "step": 43902 + }, + { + "epoch": 13.56, + "learning_rate": 4.964526707175732e-06, + "loss": 0.005, + "step": 43903 + }, + { + "epoch": 13.56, + "learning_rate": 4.96409462750949e-06, + "loss": 0.0047, + "step": 43904 + }, + { + "epoch": 13.56, + "learning_rate": 4.9636625604389724e-06, + "loss": 0.0055, + "step": 43905 + }, + { + "epoch": 13.56, + "learning_rate": 4.963230505965251e-06, + "loss": 0.0075, + "step": 43906 + }, + { + "epoch": 13.56, + "learning_rate": 4.962798464089406e-06, + "loss": 0.0041, + "step": 43907 + }, + { + "epoch": 13.56, + "learning_rate": 4.962366434812524e-06, + "loss": 0.0034, + "step": 43908 + }, + { + "epoch": 13.56, + "learning_rate": 4.961934418135679e-06, + "loss": 0.0054, + "step": 43909 + }, + { + "epoch": 13.56, + "learning_rate": 4.961502414059956e-06, + "loss": 0.0046, + "step": 43910 + }, + { + "epoch": 13.56, + "learning_rate": 4.961070422586436e-06, + "loss": 0.005, + "step": 43911 + }, + { + "epoch": 13.56, + "learning_rate": 4.9606384437162e-06, + "loss": 0.0051, + "step": 43912 + }, + { + "epoch": 13.56, + "learning_rate": 4.960206477450321e-06, + "loss": 0.0042, + "step": 43913 + }, + { + "epoch": 13.56, + "learning_rate": 4.959774523789889e-06, + "loss": 0.0048, + "step": 43914 + }, + { + "epoch": 13.56, + "learning_rate": 4.9593425827359765e-06, + "loss": 0.004, + "step": 43915 + }, + { + "epoch": 13.56, + "learning_rate": 4.958910654289672e-06, + "loss": 0.0047, + "step": 43916 + }, + { + "epoch": 13.56, + "learning_rate": 4.95847873845205e-06, + "loss": 0.0048, + "step": 43917 + }, + { + "epoch": 13.56, + "learning_rate": 4.95804683522419e-06, + "loss": 0.0045, + "step": 43918 + }, + { + "epoch": 13.56, + "learning_rate": 4.957614944607173e-06, + "loss": 0.0046, + "step": 43919 + }, + { + "epoch": 13.56, + "learning_rate": 4.9571830666020845e-06, + "loss": 0.0051, + "step": 43920 + }, + { + "epoch": 13.56, + "learning_rate": 4.956751201209998e-06, + "loss": 0.006, + "step": 43921 + }, + { + "epoch": 13.56, + "learning_rate": 4.956319348432e-06, + "loss": 0.0043, + "step": 43922 + }, + { + "epoch": 13.56, + "learning_rate": 4.955887508269168e-06, + "loss": 0.0055, + "step": 43923 + }, + { + "epoch": 13.56, + "learning_rate": 4.955455680722577e-06, + "loss": 0.0043, + "step": 43924 + }, + { + "epoch": 13.56, + "learning_rate": 4.955023865793311e-06, + "loss": 0.0047, + "step": 43925 + }, + { + "epoch": 13.57, + "learning_rate": 4.954592063482455e-06, + "loss": 0.0042, + "step": 43926 + }, + { + "epoch": 13.57, + "learning_rate": 4.954160273791083e-06, + "loss": 0.0043, + "step": 43927 + }, + { + "epoch": 13.57, + "learning_rate": 4.953728496720275e-06, + "loss": 0.0047, + "step": 43928 + }, + { + "epoch": 13.57, + "learning_rate": 4.953296732271114e-06, + "loss": 0.0046, + "step": 43929 + }, + { + "epoch": 13.57, + "learning_rate": 4.952864980444676e-06, + "loss": 0.0046, + "step": 43930 + }, + { + "epoch": 13.57, + "learning_rate": 4.952433241242043e-06, + "loss": 0.0046, + "step": 43931 + }, + { + "epoch": 13.57, + "learning_rate": 4.952001514664298e-06, + "loss": 0.0061, + "step": 43932 + }, + { + "epoch": 13.57, + "learning_rate": 4.951569800712518e-06, + "loss": 0.0061, + "step": 43933 + }, + { + "epoch": 13.57, + "learning_rate": 4.95113809938778e-06, + "loss": 0.0049, + "step": 43934 + }, + { + "epoch": 13.57, + "learning_rate": 4.95070641069117e-06, + "loss": 0.005, + "step": 43935 + }, + { + "epoch": 13.57, + "learning_rate": 4.950274734623759e-06, + "loss": 0.0051, + "step": 43936 + }, + { + "epoch": 13.57, + "learning_rate": 4.9498430711866375e-06, + "loss": 0.005, + "step": 43937 + }, + { + "epoch": 13.57, + "learning_rate": 4.949411420380874e-06, + "loss": 0.0048, + "step": 43938 + }, + { + "epoch": 13.57, + "learning_rate": 4.948979782207559e-06, + "loss": 0.005, + "step": 43939 + }, + { + "epoch": 13.57, + "learning_rate": 4.9485481566677626e-06, + "loss": 0.0051, + "step": 43940 + }, + { + "epoch": 13.57, + "learning_rate": 4.948116543762569e-06, + "loss": 0.0043, + "step": 43941 + }, + { + "epoch": 13.57, + "learning_rate": 4.94768494349306e-06, + "loss": 0.0047, + "step": 43942 + }, + { + "epoch": 13.57, + "learning_rate": 4.947253355860313e-06, + "loss": 0.0039, + "step": 43943 + }, + { + "epoch": 13.57, + "learning_rate": 4.946821780865403e-06, + "loss": 0.0051, + "step": 43944 + }, + { + "epoch": 13.57, + "learning_rate": 4.946390218509418e-06, + "loss": 0.0051, + "step": 43945 + }, + { + "epoch": 13.57, + "learning_rate": 4.945958668793428e-06, + "loss": 0.0046, + "step": 43946 + }, + { + "epoch": 13.57, + "learning_rate": 4.945527131718522e-06, + "loss": 0.0057, + "step": 43947 + }, + { + "epoch": 13.57, + "learning_rate": 4.945095607285774e-06, + "loss": 0.0036, + "step": 43948 + }, + { + "epoch": 13.57, + "learning_rate": 4.944664095496259e-06, + "loss": 0.0045, + "step": 43949 + }, + { + "epoch": 13.57, + "learning_rate": 4.944232596351061e-06, + "loss": 0.005, + "step": 43950 + }, + { + "epoch": 13.57, + "learning_rate": 4.943801109851265e-06, + "loss": 0.0054, + "step": 43951 + }, + { + "epoch": 13.57, + "learning_rate": 4.9433696359979395e-06, + "loss": 0.0056, + "step": 43952 + }, + { + "epoch": 13.57, + "learning_rate": 4.9429381747921735e-06, + "loss": 0.0037, + "step": 43953 + }, + { + "epoch": 13.57, + "learning_rate": 4.942506726235041e-06, + "loss": 0.0061, + "step": 43954 + }, + { + "epoch": 13.57, + "learning_rate": 4.942075290327618e-06, + "loss": 0.0055, + "step": 43955 + }, + { + "epoch": 13.57, + "learning_rate": 4.9416438670709875e-06, + "loss": 0.0043, + "step": 43956 + }, + { + "epoch": 13.57, + "learning_rate": 4.941212456466232e-06, + "loss": 0.0047, + "step": 43957 + }, + { + "epoch": 13.58, + "learning_rate": 4.940781058514427e-06, + "loss": 0.0044, + "step": 43958 + }, + { + "epoch": 13.58, + "learning_rate": 4.9403496732166465e-06, + "loss": 0.0054, + "step": 43959 + }, + { + "epoch": 13.58, + "learning_rate": 4.939918300573978e-06, + "loss": 0.004, + "step": 43960 + }, + { + "epoch": 13.58, + "learning_rate": 4.939486940587493e-06, + "loss": 0.0052, + "step": 43961 + }, + { + "epoch": 13.58, + "learning_rate": 4.939055593258275e-06, + "loss": 0.0048, + "step": 43962 + }, + { + "epoch": 13.58, + "learning_rate": 4.93862425858741e-06, + "loss": 0.0045, + "step": 43963 + }, + { + "epoch": 13.58, + "learning_rate": 4.938192936575961e-06, + "loss": 0.0057, + "step": 43964 + }, + { + "epoch": 13.58, + "learning_rate": 4.937761627225014e-06, + "loss": 0.0058, + "step": 43965 + }, + { + "epoch": 13.58, + "learning_rate": 4.9373303305356525e-06, + "loss": 0.0052, + "step": 43966 + }, + { + "epoch": 13.58, + "learning_rate": 4.936899046508948e-06, + "loss": 0.0047, + "step": 43967 + }, + { + "epoch": 13.58, + "learning_rate": 4.936467775145984e-06, + "loss": 0.0047, + "step": 43968 + }, + { + "epoch": 13.58, + "learning_rate": 4.936036516447836e-06, + "loss": 0.0066, + "step": 43969 + }, + { + "epoch": 13.58, + "learning_rate": 4.935605270415588e-06, + "loss": 0.0037, + "step": 43970 + }, + { + "epoch": 13.58, + "learning_rate": 4.935174037050311e-06, + "loss": 0.0045, + "step": 43971 + }, + { + "epoch": 13.58, + "learning_rate": 4.934742816353086e-06, + "loss": 0.0036, + "step": 43972 + }, + { + "epoch": 13.58, + "learning_rate": 4.934311608325003e-06, + "loss": 0.0036, + "step": 43973 + }, + { + "epoch": 13.58, + "learning_rate": 4.933880412967121e-06, + "loss": 0.0043, + "step": 43974 + }, + { + "epoch": 13.58, + "learning_rate": 4.933449230280529e-06, + "loss": 0.0043, + "step": 43975 + }, + { + "epoch": 13.58, + "learning_rate": 4.933018060266309e-06, + "loss": 0.0049, + "step": 43976 + }, + { + "epoch": 13.58, + "learning_rate": 4.93258690292553e-06, + "loss": 0.0051, + "step": 43977 + }, + { + "epoch": 13.58, + "learning_rate": 4.932155758259281e-06, + "loss": 0.0041, + "step": 43978 + }, + { + "epoch": 13.58, + "learning_rate": 4.931724626268632e-06, + "loss": 0.0049, + "step": 43979 + }, + { + "epoch": 13.58, + "learning_rate": 4.931293506954662e-06, + "loss": 0.0042, + "step": 43980 + }, + { + "epoch": 13.58, + "learning_rate": 4.930862400318451e-06, + "loss": 0.0051, + "step": 43981 + }, + { + "epoch": 13.58, + "learning_rate": 4.930431306361082e-06, + "loss": 0.0039, + "step": 43982 + }, + { + "epoch": 13.58, + "learning_rate": 4.930000225083629e-06, + "loss": 0.0053, + "step": 43983 + }, + { + "epoch": 13.58, + "learning_rate": 4.929569156487165e-06, + "loss": 0.0048, + "step": 43984 + }, + { + "epoch": 13.58, + "learning_rate": 4.929138100572779e-06, + "loss": 0.0065, + "step": 43985 + }, + { + "epoch": 13.58, + "learning_rate": 4.9287070573415385e-06, + "loss": 0.0042, + "step": 43986 + }, + { + "epoch": 13.58, + "learning_rate": 4.928276026794526e-06, + "loss": 0.0043, + "step": 43987 + }, + { + "epoch": 13.58, + "learning_rate": 4.927845008932826e-06, + "loss": 0.005, + "step": 43988 + }, + { + "epoch": 13.58, + "learning_rate": 4.927414003757509e-06, + "loss": 0.0048, + "step": 43989 + }, + { + "epoch": 13.58, + "learning_rate": 4.926983011269651e-06, + "loss": 0.0038, + "step": 43990 + }, + { + "epoch": 13.59, + "learning_rate": 4.9265520314703385e-06, + "loss": 0.0056, + "step": 43991 + }, + { + "epoch": 13.59, + "learning_rate": 4.926121064360641e-06, + "loss": 0.0042, + "step": 43992 + }, + { + "epoch": 13.59, + "learning_rate": 4.925690109941643e-06, + "loss": 0.0047, + "step": 43993 + }, + { + "epoch": 13.59, + "learning_rate": 4.92525916821442e-06, + "loss": 0.0049, + "step": 43994 + }, + { + "epoch": 13.59, + "learning_rate": 4.924828239180045e-06, + "loss": 0.0053, + "step": 43995 + }, + { + "epoch": 13.59, + "learning_rate": 4.924397322839601e-06, + "loss": 0.0055, + "step": 43996 + }, + { + "epoch": 13.59, + "learning_rate": 4.923966419194168e-06, + "loss": 0.0045, + "step": 43997 + }, + { + "epoch": 13.59, + "learning_rate": 4.9235355282448184e-06, + "loss": 0.0046, + "step": 43998 + }, + { + "epoch": 13.59, + "learning_rate": 4.923104649992635e-06, + "loss": 0.0072, + "step": 43999 + }, + { + "epoch": 13.59, + "learning_rate": 4.922673784438693e-06, + "loss": 0.0045, + "step": 44000 + }, + { + "epoch": 13.59, + "learning_rate": 4.922242931584067e-06, + "loss": 0.0044, + "step": 44001 + }, + { + "epoch": 13.59, + "learning_rate": 4.921812091429836e-06, + "loss": 0.0035, + "step": 44002 + }, + { + "epoch": 13.59, + "learning_rate": 4.921381263977084e-06, + "loss": 0.0051, + "step": 44003 + }, + { + "epoch": 13.59, + "learning_rate": 4.920950449226883e-06, + "loss": 0.0043, + "step": 44004 + }, + { + "epoch": 13.59, + "learning_rate": 4.920519647180308e-06, + "loss": 0.0043, + "step": 44005 + }, + { + "epoch": 13.59, + "learning_rate": 4.920088857838441e-06, + "loss": 0.0057, + "step": 44006 + }, + { + "epoch": 13.59, + "learning_rate": 4.919658081202361e-06, + "loss": 0.0057, + "step": 44007 + }, + { + "epoch": 13.59, + "learning_rate": 4.919227317273139e-06, + "loss": 0.0033, + "step": 44008 + }, + { + "epoch": 13.59, + "learning_rate": 4.918796566051859e-06, + "loss": 0.0046, + "step": 44009 + }, + { + "epoch": 13.59, + "learning_rate": 4.9183658275395964e-06, + "loss": 0.0058, + "step": 44010 + }, + { + "epoch": 13.59, + "learning_rate": 4.917935101737424e-06, + "loss": 0.0057, + "step": 44011 + }, + { + "epoch": 13.59, + "learning_rate": 4.917504388646423e-06, + "loss": 0.0048, + "step": 44012 + }, + { + "epoch": 13.59, + "learning_rate": 4.917073688267674e-06, + "loss": 0.0041, + "step": 44013 + }, + { + "epoch": 13.59, + "learning_rate": 4.91664300060225e-06, + "loss": 0.0059, + "step": 44014 + }, + { + "epoch": 13.59, + "learning_rate": 4.916212325651226e-06, + "loss": 0.0049, + "step": 44015 + }, + { + "epoch": 13.59, + "learning_rate": 4.915781663415686e-06, + "loss": 0.0045, + "step": 44016 + }, + { + "epoch": 13.59, + "learning_rate": 4.9153510138967e-06, + "loss": 0.0038, + "step": 44017 + }, + { + "epoch": 13.59, + "learning_rate": 4.914920377095348e-06, + "loss": 0.0052, + "step": 44018 + }, + { + "epoch": 13.59, + "learning_rate": 4.914489753012711e-06, + "loss": 0.005, + "step": 44019 + }, + { + "epoch": 13.59, + "learning_rate": 4.914059141649863e-06, + "loss": 0.0044, + "step": 44020 + }, + { + "epoch": 13.59, + "learning_rate": 4.913628543007877e-06, + "loss": 0.0045, + "step": 44021 + }, + { + "epoch": 13.59, + "learning_rate": 4.913197957087837e-06, + "loss": 0.004, + "step": 44022 + }, + { + "epoch": 13.6, + "learning_rate": 4.912767383890814e-06, + "loss": 0.0039, + "step": 44023 + }, + { + "epoch": 13.6, + "learning_rate": 4.91233682341789e-06, + "loss": 0.0043, + "step": 44024 + }, + { + "epoch": 13.6, + "learning_rate": 4.911906275670141e-06, + "loss": 0.0048, + "step": 44025 + }, + { + "epoch": 13.6, + "learning_rate": 4.911475740648638e-06, + "loss": 0.0054, + "step": 44026 + }, + { + "epoch": 13.6, + "learning_rate": 4.9110452183544625e-06, + "loss": 0.0049, + "step": 44027 + }, + { + "epoch": 13.6, + "learning_rate": 4.910614708788693e-06, + "loss": 0.0044, + "step": 44028 + }, + { + "epoch": 13.6, + "learning_rate": 4.9101842119524034e-06, + "loss": 0.0051, + "step": 44029 + }, + { + "epoch": 13.6, + "learning_rate": 4.909753727846673e-06, + "loss": 0.0046, + "step": 44030 + }, + { + "epoch": 13.6, + "learning_rate": 4.909323256472579e-06, + "loss": 0.0055, + "step": 44031 + }, + { + "epoch": 13.6, + "learning_rate": 4.908892797831191e-06, + "loss": 0.0045, + "step": 44032 + }, + { + "epoch": 13.6, + "learning_rate": 4.908462351923591e-06, + "loss": 0.0047, + "step": 44033 + }, + { + "epoch": 13.6, + "learning_rate": 4.9080319187508585e-06, + "loss": 0.0053, + "step": 44034 + }, + { + "epoch": 13.6, + "learning_rate": 4.9076014983140675e-06, + "loss": 0.0045, + "step": 44035 + }, + { + "epoch": 13.6, + "learning_rate": 4.907171090614289e-06, + "loss": 0.0052, + "step": 44036 + }, + { + "epoch": 13.6, + "learning_rate": 4.906740695652606e-06, + "loss": 0.0047, + "step": 44037 + }, + { + "epoch": 13.6, + "learning_rate": 4.906310313430096e-06, + "loss": 0.006, + "step": 44038 + }, + { + "epoch": 13.6, + "learning_rate": 4.9058799439478295e-06, + "loss": 0.0057, + "step": 44039 + }, + { + "epoch": 13.6, + "learning_rate": 4.90544958720689e-06, + "loss": 0.0052, + "step": 44040 + }, + { + "epoch": 13.6, + "learning_rate": 4.905019243208352e-06, + "loss": 0.0047, + "step": 44041 + }, + { + "epoch": 13.6, + "learning_rate": 4.904588911953285e-06, + "loss": 0.0043, + "step": 44042 + }, + { + "epoch": 13.6, + "learning_rate": 4.904158593442771e-06, + "loss": 0.0045, + "step": 44043 + }, + { + "epoch": 13.6, + "learning_rate": 4.903728287677889e-06, + "loss": 0.0046, + "step": 44044 + }, + { + "epoch": 13.6, + "learning_rate": 4.903297994659712e-06, + "loss": 0.0075, + "step": 44045 + }, + { + "epoch": 13.6, + "learning_rate": 4.902867714389312e-06, + "loss": 0.0042, + "step": 44046 + }, + { + "epoch": 13.6, + "learning_rate": 4.902437446867775e-06, + "loss": 0.0036, + "step": 44047 + }, + { + "epoch": 13.6, + "learning_rate": 4.902007192096167e-06, + "loss": 0.0048, + "step": 44048 + }, + { + "epoch": 13.6, + "learning_rate": 4.901576950075568e-06, + "loss": 0.0043, + "step": 44049 + }, + { + "epoch": 13.6, + "learning_rate": 4.901146720807059e-06, + "loss": 0.0063, + "step": 44050 + }, + { + "epoch": 13.6, + "learning_rate": 4.900716504291712e-06, + "loss": 0.0062, + "step": 44051 + }, + { + "epoch": 13.6, + "learning_rate": 4.9002863005306e-06, + "loss": 0.006, + "step": 44052 + }, + { + "epoch": 13.6, + "learning_rate": 4.899856109524807e-06, + "loss": 0.0059, + "step": 44053 + }, + { + "epoch": 13.6, + "learning_rate": 4.899425931275398e-06, + "loss": 0.0058, + "step": 44054 + }, + { + "epoch": 13.61, + "learning_rate": 4.8989957657834595e-06, + "loss": 0.0047, + "step": 44055 + }, + { + "epoch": 13.61, + "learning_rate": 4.8985656130500635e-06, + "loss": 0.0045, + "step": 44056 + }, + { + "epoch": 13.61, + "learning_rate": 4.898135473076281e-06, + "loss": 0.0057, + "step": 44057 + }, + { + "epoch": 13.61, + "learning_rate": 4.897705345863193e-06, + "loss": 0.0046, + "step": 44058 + }, + { + "epoch": 13.61, + "learning_rate": 4.8972752314118775e-06, + "loss": 0.0052, + "step": 44059 + }, + { + "epoch": 13.61, + "learning_rate": 4.896845129723403e-06, + "loss": 0.005, + "step": 44060 + }, + { + "epoch": 13.61, + "learning_rate": 4.896415040798855e-06, + "loss": 0.0051, + "step": 44061 + }, + { + "epoch": 13.61, + "learning_rate": 4.8959849646393035e-06, + "loss": 0.0045, + "step": 44062 + }, + { + "epoch": 13.61, + "learning_rate": 4.895554901245819e-06, + "loss": 0.005, + "step": 44063 + }, + { + "epoch": 13.61, + "learning_rate": 4.895124850619485e-06, + "loss": 0.0048, + "step": 44064 + }, + { + "epoch": 13.61, + "learning_rate": 4.894694812761377e-06, + "loss": 0.0049, + "step": 44065 + }, + { + "epoch": 13.61, + "learning_rate": 4.894264787672569e-06, + "loss": 0.0046, + "step": 44066 + }, + { + "epoch": 13.61, + "learning_rate": 4.893834775354132e-06, + "loss": 0.0056, + "step": 44067 + }, + { + "epoch": 13.61, + "learning_rate": 4.893404775807146e-06, + "loss": 0.0056, + "step": 44068 + }, + { + "epoch": 13.61, + "learning_rate": 4.89297478903269e-06, + "loss": 0.0057, + "step": 44069 + }, + { + "epoch": 13.61, + "learning_rate": 4.89254481503183e-06, + "loss": 0.0042, + "step": 44070 + }, + { + "epoch": 13.61, + "learning_rate": 4.8921148538056525e-06, + "loss": 0.0056, + "step": 44071 + }, + { + "epoch": 13.61, + "learning_rate": 4.891684905355228e-06, + "loss": 0.0045, + "step": 44072 + }, + { + "epoch": 13.61, + "learning_rate": 4.891254969681625e-06, + "loss": 0.0049, + "step": 44073 + }, + { + "epoch": 13.61, + "learning_rate": 4.8908250467859266e-06, + "loss": 0.0055, + "step": 44074 + }, + { + "epoch": 13.61, + "learning_rate": 4.89039513666921e-06, + "loss": 0.0049, + "step": 44075 + }, + { + "epoch": 13.61, + "learning_rate": 4.889965239332547e-06, + "loss": 0.0051, + "step": 44076 + }, + { + "epoch": 13.61, + "learning_rate": 4.88953535477701e-06, + "loss": 0.0057, + "step": 44077 + }, + { + "epoch": 13.61, + "learning_rate": 4.8891054830036795e-06, + "loss": 0.005, + "step": 44078 + }, + { + "epoch": 13.61, + "learning_rate": 4.888675624013627e-06, + "loss": 0.0041, + "step": 44079 + }, + { + "epoch": 13.61, + "learning_rate": 4.8882457778079275e-06, + "loss": 0.0049, + "step": 44080 + }, + { + "epoch": 13.61, + "learning_rate": 4.887815944387665e-06, + "loss": 0.0039, + "step": 44081 + }, + { + "epoch": 13.61, + "learning_rate": 4.887386123753899e-06, + "loss": 0.0053, + "step": 44082 + }, + { + "epoch": 13.61, + "learning_rate": 4.8869563159077135e-06, + "loss": 0.0051, + "step": 44083 + }, + { + "epoch": 13.61, + "learning_rate": 4.8865265208501875e-06, + "loss": 0.0071, + "step": 44084 + }, + { + "epoch": 13.61, + "learning_rate": 4.886096738582386e-06, + "loss": 0.0056, + "step": 44085 + }, + { + "epoch": 13.61, + "learning_rate": 4.885666969105395e-06, + "loss": 0.0037, + "step": 44086 + }, + { + "epoch": 13.61, + "learning_rate": 4.885237212420282e-06, + "loss": 0.0054, + "step": 44087 + }, + { + "epoch": 13.62, + "learning_rate": 4.88480746852812e-06, + "loss": 0.0047, + "step": 44088 + }, + { + "epoch": 13.62, + "learning_rate": 4.884377737429988e-06, + "loss": 0.0053, + "step": 44089 + }, + { + "epoch": 13.62, + "learning_rate": 4.883948019126964e-06, + "loss": 0.0062, + "step": 44090 + }, + { + "epoch": 13.62, + "learning_rate": 4.883518313620119e-06, + "loss": 0.0051, + "step": 44091 + }, + { + "epoch": 13.62, + "learning_rate": 4.8830886209105245e-06, + "loss": 0.0051, + "step": 44092 + }, + { + "epoch": 13.62, + "learning_rate": 4.882658940999262e-06, + "loss": 0.0057, + "step": 44093 + }, + { + "epoch": 13.62, + "learning_rate": 4.8822292738873985e-06, + "loss": 0.0047, + "step": 44094 + }, + { + "epoch": 13.62, + "learning_rate": 4.881799619576015e-06, + "loss": 0.0041, + "step": 44095 + }, + { + "epoch": 13.62, + "learning_rate": 4.881369978066186e-06, + "loss": 0.0044, + "step": 44096 + }, + { + "epoch": 13.62, + "learning_rate": 4.880940349358984e-06, + "loss": 0.0051, + "step": 44097 + }, + { + "epoch": 13.62, + "learning_rate": 4.880510733455481e-06, + "loss": 0.0043, + "step": 44098 + }, + { + "epoch": 13.62, + "learning_rate": 4.8800811303567584e-06, + "loss": 0.0038, + "step": 44099 + }, + { + "epoch": 13.62, + "learning_rate": 4.879651540063882e-06, + "loss": 0.005, + "step": 44100 + }, + { + "epoch": 13.62, + "learning_rate": 4.879221962577933e-06, + "loss": 0.0043, + "step": 44101 + }, + { + "epoch": 13.62, + "learning_rate": 4.878792397899985e-06, + "loss": 0.0062, + "step": 44102 + }, + { + "epoch": 13.62, + "learning_rate": 4.878362846031113e-06, + "loss": 0.0061, + "step": 44103 + }, + { + "epoch": 13.62, + "learning_rate": 4.877933306972385e-06, + "loss": 0.006, + "step": 44104 + }, + { + "epoch": 13.62, + "learning_rate": 4.877503780724881e-06, + "loss": 0.0047, + "step": 44105 + }, + { + "epoch": 13.62, + "learning_rate": 4.877074267289676e-06, + "loss": 0.0045, + "step": 44106 + }, + { + "epoch": 13.62, + "learning_rate": 4.876644766667845e-06, + "loss": 0.0038, + "step": 44107 + }, + { + "epoch": 13.62, + "learning_rate": 4.876215278860456e-06, + "loss": 0.0066, + "step": 44108 + }, + { + "epoch": 13.62, + "learning_rate": 4.875785803868589e-06, + "loss": 0.0051, + "step": 44109 + }, + { + "epoch": 13.62, + "learning_rate": 4.875356341693313e-06, + "loss": 0.0049, + "step": 44110 + }, + { + "epoch": 13.62, + "learning_rate": 4.874926892335707e-06, + "loss": 0.0067, + "step": 44111 + }, + { + "epoch": 13.62, + "learning_rate": 4.874497455796851e-06, + "loss": 0.0051, + "step": 44112 + }, + { + "epoch": 13.62, + "learning_rate": 4.874068032077802e-06, + "loss": 0.0048, + "step": 44113 + }, + { + "epoch": 13.62, + "learning_rate": 4.873638621179646e-06, + "loss": 0.0041, + "step": 44114 + }, + { + "epoch": 13.62, + "learning_rate": 4.873209223103457e-06, + "loss": 0.0044, + "step": 44115 + }, + { + "epoch": 13.62, + "learning_rate": 4.872779837850305e-06, + "loss": 0.005, + "step": 44116 + }, + { + "epoch": 13.62, + "learning_rate": 4.872350465421267e-06, + "loss": 0.0049, + "step": 44117 + }, + { + "epoch": 13.62, + "learning_rate": 4.871921105817418e-06, + "loss": 0.0035, + "step": 44118 + }, + { + "epoch": 13.62, + "learning_rate": 4.871491759039823e-06, + "loss": 0.0052, + "step": 44119 + }, + { + "epoch": 13.63, + "learning_rate": 4.8710624250895655e-06, + "loss": 0.0052, + "step": 44120 + }, + { + "epoch": 13.63, + "learning_rate": 4.870633103967719e-06, + "loss": 0.0056, + "step": 44121 + }, + { + "epoch": 13.63, + "learning_rate": 4.8702037956753545e-06, + "loss": 0.0063, + "step": 44122 + }, + { + "epoch": 13.63, + "learning_rate": 4.869774500213542e-06, + "loss": 0.0058, + "step": 44123 + }, + { + "epoch": 13.63, + "learning_rate": 4.869345217583364e-06, + "loss": 0.0044, + "step": 44124 + }, + { + "epoch": 13.63, + "learning_rate": 4.8689159477858835e-06, + "loss": 0.0053, + "step": 44125 + }, + { + "epoch": 13.63, + "learning_rate": 4.868486690822182e-06, + "loss": 0.0052, + "step": 44126 + }, + { + "epoch": 13.63, + "learning_rate": 4.868057446693334e-06, + "loss": 0.0056, + "step": 44127 + }, + { + "epoch": 13.63, + "learning_rate": 4.8676282154004104e-06, + "loss": 0.0057, + "step": 44128 + }, + { + "epoch": 13.63, + "learning_rate": 4.8671989969444815e-06, + "loss": 0.0044, + "step": 44129 + }, + { + "epoch": 13.63, + "learning_rate": 4.866769791326628e-06, + "loss": 0.0053, + "step": 44130 + }, + { + "epoch": 13.63, + "learning_rate": 4.866340598547915e-06, + "loss": 0.0046, + "step": 44131 + }, + { + "epoch": 13.63, + "learning_rate": 4.865911418609423e-06, + "loss": 0.0052, + "step": 44132 + }, + { + "epoch": 13.63, + "learning_rate": 4.8654822515122215e-06, + "loss": 0.0057, + "step": 44133 + }, + { + "epoch": 13.63, + "learning_rate": 4.8650530972573886e-06, + "loss": 0.0051, + "step": 44134 + }, + { + "epoch": 13.63, + "learning_rate": 4.864623955845991e-06, + "loss": 0.0063, + "step": 44135 + }, + { + "epoch": 13.63, + "learning_rate": 4.864194827279104e-06, + "loss": 0.005, + "step": 44136 + }, + { + "epoch": 13.63, + "learning_rate": 4.863765711557807e-06, + "loss": 0.0052, + "step": 44137 + }, + { + "epoch": 13.63, + "learning_rate": 4.863336608683169e-06, + "loss": 0.0047, + "step": 44138 + }, + { + "epoch": 13.63, + "learning_rate": 4.862907518656259e-06, + "loss": 0.0053, + "step": 44139 + }, + { + "epoch": 13.63, + "learning_rate": 4.862478441478159e-06, + "loss": 0.0058, + "step": 44140 + }, + { + "epoch": 13.63, + "learning_rate": 4.8620493771499325e-06, + "loss": 0.0042, + "step": 44141 + }, + { + "epoch": 13.63, + "learning_rate": 4.861620325672661e-06, + "loss": 0.0043, + "step": 44142 + }, + { + "epoch": 13.63, + "learning_rate": 4.861191287047416e-06, + "loss": 0.0057, + "step": 44143 + }, + { + "epoch": 13.63, + "learning_rate": 4.860762261275264e-06, + "loss": 0.004, + "step": 44144 + }, + { + "epoch": 13.63, + "learning_rate": 4.860333248357283e-06, + "loss": 0.0052, + "step": 44145 + }, + { + "epoch": 13.63, + "learning_rate": 4.859904248294549e-06, + "loss": 0.0048, + "step": 44146 + }, + { + "epoch": 13.63, + "learning_rate": 4.859475261088129e-06, + "loss": 0.0047, + "step": 44147 + }, + { + "epoch": 13.63, + "learning_rate": 4.859046286739103e-06, + "loss": 0.005, + "step": 44148 + }, + { + "epoch": 13.63, + "learning_rate": 4.858617325248539e-06, + "loss": 0.0064, + "step": 44149 + }, + { + "epoch": 13.63, + "learning_rate": 4.858188376617508e-06, + "loss": 0.0054, + "step": 44150 + }, + { + "epoch": 13.63, + "learning_rate": 4.857759440847085e-06, + "loss": 0.0042, + "step": 44151 + }, + { + "epoch": 13.63, + "learning_rate": 4.857330517938348e-06, + "loss": 0.0043, + "step": 44152 + }, + { + "epoch": 13.64, + "learning_rate": 4.856901607892365e-06, + "loss": 0.006, + "step": 44153 + }, + { + "epoch": 13.64, + "learning_rate": 4.856472710710205e-06, + "loss": 0.0051, + "step": 44154 + }, + { + "epoch": 13.64, + "learning_rate": 4.856043826392949e-06, + "loss": 0.0052, + "step": 44155 + }, + { + "epoch": 13.64, + "learning_rate": 4.855614954941661e-06, + "loss": 0.0047, + "step": 44156 + }, + { + "epoch": 13.64, + "learning_rate": 4.855186096357419e-06, + "loss": 0.0042, + "step": 44157 + }, + { + "epoch": 13.64, + "learning_rate": 4.854757250641299e-06, + "loss": 0.0063, + "step": 44158 + }, + { + "epoch": 13.64, + "learning_rate": 4.854328417794368e-06, + "loss": 0.0053, + "step": 44159 + }, + { + "epoch": 13.64, + "learning_rate": 4.853899597817698e-06, + "loss": 0.0047, + "step": 44160 + }, + { + "epoch": 13.64, + "learning_rate": 4.853470790712368e-06, + "loss": 0.0044, + "step": 44161 + }, + { + "epoch": 13.64, + "learning_rate": 4.85304199647944e-06, + "loss": 0.0055, + "step": 44162 + }, + { + "epoch": 13.64, + "learning_rate": 4.852613215119999e-06, + "loss": 0.0065, + "step": 44163 + }, + { + "epoch": 13.64, + "learning_rate": 4.85218444663511e-06, + "loss": 0.0048, + "step": 44164 + }, + { + "epoch": 13.64, + "learning_rate": 4.851755691025843e-06, + "loss": 0.0052, + "step": 44165 + }, + { + "epoch": 13.64, + "learning_rate": 4.851326948293274e-06, + "loss": 0.0056, + "step": 44166 + }, + { + "epoch": 13.64, + "learning_rate": 4.850898218438476e-06, + "loss": 0.0051, + "step": 44167 + }, + { + "epoch": 13.64, + "learning_rate": 4.850469501462522e-06, + "loss": 0.0059, + "step": 44168 + }, + { + "epoch": 13.64, + "learning_rate": 4.8500407973664856e-06, + "loss": 0.0054, + "step": 44169 + }, + { + "epoch": 13.64, + "learning_rate": 4.849612106151432e-06, + "loss": 0.0054, + "step": 44170 + }, + { + "epoch": 13.64, + "learning_rate": 4.8491834278184416e-06, + "loss": 0.0048, + "step": 44171 + }, + { + "epoch": 13.64, + "learning_rate": 4.84875476236858e-06, + "loss": 0.0047, + "step": 44172 + }, + { + "epoch": 13.64, + "learning_rate": 4.848326109802924e-06, + "loss": 0.0064, + "step": 44173 + }, + { + "epoch": 13.64, + "learning_rate": 4.847897470122545e-06, + "loss": 0.0042, + "step": 44174 + }, + { + "epoch": 13.64, + "learning_rate": 4.84746884332851e-06, + "loss": 0.0054, + "step": 44175 + }, + { + "epoch": 13.64, + "learning_rate": 4.847040229421897e-06, + "loss": 0.0048, + "step": 44176 + }, + { + "epoch": 13.64, + "learning_rate": 4.846611628403778e-06, + "loss": 0.0051, + "step": 44177 + }, + { + "epoch": 13.64, + "learning_rate": 4.846183040275219e-06, + "loss": 0.0053, + "step": 44178 + }, + { + "epoch": 13.64, + "learning_rate": 4.845754465037302e-06, + "loss": 0.0056, + "step": 44179 + }, + { + "epoch": 13.64, + "learning_rate": 4.845325902691093e-06, + "loss": 0.0058, + "step": 44180 + }, + { + "epoch": 13.64, + "learning_rate": 4.844897353237659e-06, + "loss": 0.0039, + "step": 44181 + }, + { + "epoch": 13.64, + "learning_rate": 4.844468816678077e-06, + "loss": 0.0049, + "step": 44182 + }, + { + "epoch": 13.64, + "learning_rate": 4.844040293013423e-06, + "loss": 0.0051, + "step": 44183 + }, + { + "epoch": 13.64, + "learning_rate": 4.843611782244765e-06, + "loss": 0.0059, + "step": 44184 + }, + { + "epoch": 13.65, + "learning_rate": 4.843183284373169e-06, + "loss": 0.0051, + "step": 44185 + }, + { + "epoch": 13.65, + "learning_rate": 4.842754799399718e-06, + "loss": 0.0052, + "step": 44186 + }, + { + "epoch": 13.65, + "learning_rate": 4.842326327325474e-06, + "loss": 0.0043, + "step": 44187 + }, + { + "epoch": 13.65, + "learning_rate": 4.841897868151512e-06, + "loss": 0.0053, + "step": 44188 + }, + { + "epoch": 13.65, + "learning_rate": 4.841469421878907e-06, + "loss": 0.0066, + "step": 44189 + }, + { + "epoch": 13.65, + "learning_rate": 4.84104098850873e-06, + "loss": 0.0057, + "step": 44190 + }, + { + "epoch": 13.65, + "learning_rate": 4.840612568042045e-06, + "loss": 0.0046, + "step": 44191 + }, + { + "epoch": 13.65, + "learning_rate": 4.840184160479933e-06, + "loss": 0.0048, + "step": 44192 + }, + { + "epoch": 13.65, + "learning_rate": 4.839755765823458e-06, + "loss": 0.004, + "step": 44193 + }, + { + "epoch": 13.65, + "learning_rate": 4.839327384073698e-06, + "loss": 0.005, + "step": 44194 + }, + { + "epoch": 13.65, + "learning_rate": 4.838899015231722e-06, + "loss": 0.0049, + "step": 44195 + }, + { + "epoch": 13.65, + "learning_rate": 4.838470659298598e-06, + "loss": 0.0055, + "step": 44196 + }, + { + "epoch": 13.65, + "learning_rate": 4.838042316275399e-06, + "loss": 0.004, + "step": 44197 + }, + { + "epoch": 13.65, + "learning_rate": 4.837613986163198e-06, + "loss": 0.0052, + "step": 44198 + }, + { + "epoch": 13.65, + "learning_rate": 4.837185668963069e-06, + "loss": 0.0049, + "step": 44199 + }, + { + "epoch": 13.65, + "learning_rate": 4.836757364676081e-06, + "loss": 0.0039, + "step": 44200 + }, + { + "epoch": 13.65, + "learning_rate": 4.836329073303302e-06, + "loss": 0.0056, + "step": 44201 + }, + { + "epoch": 13.65, + "learning_rate": 4.835900794845808e-06, + "loss": 0.0065, + "step": 44202 + }, + { + "epoch": 13.65, + "learning_rate": 4.8354725293046645e-06, + "loss": 0.0049, + "step": 44203 + }, + { + "epoch": 13.65, + "learning_rate": 4.8350442766809505e-06, + "loss": 0.0047, + "step": 44204 + }, + { + "epoch": 13.65, + "learning_rate": 4.834616036975732e-06, + "loss": 0.0052, + "step": 44205 + }, + { + "epoch": 13.65, + "learning_rate": 4.8341878101900774e-06, + "loss": 0.0056, + "step": 44206 + }, + { + "epoch": 13.65, + "learning_rate": 4.833759596325061e-06, + "loss": 0.0047, + "step": 44207 + }, + { + "epoch": 13.65, + "learning_rate": 4.833331395381758e-06, + "loss": 0.0045, + "step": 44208 + }, + { + "epoch": 13.65, + "learning_rate": 4.832903207361233e-06, + "loss": 0.0042, + "step": 44209 + }, + { + "epoch": 13.65, + "learning_rate": 4.832475032264562e-06, + "loss": 0.0049, + "step": 44210 + }, + { + "epoch": 13.65, + "learning_rate": 4.832046870092813e-06, + "loss": 0.0045, + "step": 44211 + }, + { + "epoch": 13.65, + "learning_rate": 4.831618720847056e-06, + "loss": 0.0047, + "step": 44212 + }, + { + "epoch": 13.65, + "learning_rate": 4.8311905845283615e-06, + "loss": 0.007, + "step": 44213 + }, + { + "epoch": 13.65, + "learning_rate": 4.830762461137806e-06, + "loss": 0.0056, + "step": 44214 + }, + { + "epoch": 13.65, + "learning_rate": 4.830334350676455e-06, + "loss": 0.0056, + "step": 44215 + }, + { + "epoch": 13.65, + "learning_rate": 4.829906253145379e-06, + "loss": 0.0053, + "step": 44216 + }, + { + "epoch": 13.66, + "learning_rate": 4.829478168545654e-06, + "loss": 0.005, + "step": 44217 + }, + { + "epoch": 13.66, + "learning_rate": 4.829050096878341e-06, + "loss": 0.0046, + "step": 44218 + }, + { + "epoch": 13.66, + "learning_rate": 4.828622038144519e-06, + "loss": 0.0054, + "step": 44219 + }, + { + "epoch": 13.66, + "learning_rate": 4.828193992345265e-06, + "loss": 0.0051, + "step": 44220 + }, + { + "epoch": 13.66, + "learning_rate": 4.827765959481632e-06, + "loss": 0.0054, + "step": 44221 + }, + { + "epoch": 13.66, + "learning_rate": 4.827337939554699e-06, + "loss": 0.004, + "step": 44222 + }, + { + "epoch": 13.66, + "learning_rate": 4.826909932565542e-06, + "loss": 0.0043, + "step": 44223 + }, + { + "epoch": 13.66, + "learning_rate": 4.826481938515223e-06, + "loss": 0.0054, + "step": 44224 + }, + { + "epoch": 13.66, + "learning_rate": 4.826053957404821e-06, + "loss": 0.005, + "step": 44225 + }, + { + "epoch": 13.66, + "learning_rate": 4.8256259892354e-06, + "loss": 0.0041, + "step": 44226 + }, + { + "epoch": 13.66, + "learning_rate": 4.8251980340080284e-06, + "loss": 0.0044, + "step": 44227 + }, + { + "epoch": 13.66, + "learning_rate": 4.824770091723782e-06, + "loss": 0.0056, + "step": 44228 + }, + { + "epoch": 13.66, + "learning_rate": 4.824342162383731e-06, + "loss": 0.0052, + "step": 44229 + }, + { + "epoch": 13.66, + "learning_rate": 4.823914245988946e-06, + "loss": 0.0046, + "step": 44230 + }, + { + "epoch": 13.66, + "learning_rate": 4.823486342540491e-06, + "loss": 0.0069, + "step": 44231 + }, + { + "epoch": 13.66, + "learning_rate": 4.823058452039442e-06, + "loss": 0.0052, + "step": 44232 + }, + { + "epoch": 13.66, + "learning_rate": 4.822630574486871e-06, + "loss": 0.0052, + "step": 44233 + }, + { + "epoch": 13.66, + "learning_rate": 4.8222027098838405e-06, + "loss": 0.0039, + "step": 44234 + }, + { + "epoch": 13.66, + "learning_rate": 4.821774858231431e-06, + "loss": 0.0043, + "step": 44235 + }, + { + "epoch": 13.66, + "learning_rate": 4.821347019530705e-06, + "loss": 0.0047, + "step": 44236 + }, + { + "epoch": 13.66, + "learning_rate": 4.820919193782732e-06, + "loss": 0.0072, + "step": 44237 + }, + { + "epoch": 13.66, + "learning_rate": 4.820491380988584e-06, + "loss": 0.0065, + "step": 44238 + }, + { + "epoch": 13.66, + "learning_rate": 4.820063581149337e-06, + "loss": 0.0044, + "step": 44239 + }, + { + "epoch": 13.66, + "learning_rate": 4.819635794266054e-06, + "loss": 0.0043, + "step": 44240 + }, + { + "epoch": 13.66, + "learning_rate": 4.819208020339804e-06, + "loss": 0.0058, + "step": 44241 + }, + { + "epoch": 13.66, + "learning_rate": 4.818780259371664e-06, + "loss": 0.005, + "step": 44242 + }, + { + "epoch": 13.66, + "learning_rate": 4.818352511362694e-06, + "loss": 0.0051, + "step": 44243 + }, + { + "epoch": 13.66, + "learning_rate": 4.8179247763139716e-06, + "loss": 0.0041, + "step": 44244 + }, + { + "epoch": 13.66, + "learning_rate": 4.817497054226567e-06, + "loss": 0.0046, + "step": 44245 + }, + { + "epoch": 13.66, + "learning_rate": 4.8170693451015475e-06, + "loss": 0.0059, + "step": 44246 + }, + { + "epoch": 13.66, + "learning_rate": 4.816641648939978e-06, + "loss": 0.0045, + "step": 44247 + }, + { + "epoch": 13.66, + "learning_rate": 4.816213965742939e-06, + "loss": 0.0044, + "step": 44248 + }, + { + "epoch": 13.66, + "learning_rate": 4.81578629551149e-06, + "loss": 0.0065, + "step": 44249 + }, + { + "epoch": 13.67, + "learning_rate": 4.8153586382467074e-06, + "loss": 0.0044, + "step": 44250 + }, + { + "epoch": 13.67, + "learning_rate": 4.81493099394966e-06, + "loss": 0.004, + "step": 44251 + }, + { + "epoch": 13.67, + "learning_rate": 4.814503362621411e-06, + "loss": 0.0052, + "step": 44252 + }, + { + "epoch": 13.67, + "learning_rate": 4.814075744263036e-06, + "loss": 0.0045, + "step": 44253 + }, + { + "epoch": 13.67, + "learning_rate": 4.813648138875607e-06, + "loss": 0.0056, + "step": 44254 + }, + { + "epoch": 13.67, + "learning_rate": 4.813220546460186e-06, + "loss": 0.0045, + "step": 44255 + }, + { + "epoch": 13.67, + "learning_rate": 4.81279296701785e-06, + "loss": 0.0059, + "step": 44256 + }, + { + "epoch": 13.67, + "learning_rate": 4.812365400549665e-06, + "loss": 0.0054, + "step": 44257 + }, + { + "epoch": 13.67, + "learning_rate": 4.8119378470566955e-06, + "loss": 0.0055, + "step": 44258 + }, + { + "epoch": 13.67, + "learning_rate": 4.811510306540017e-06, + "loss": 0.0052, + "step": 44259 + }, + { + "epoch": 13.67, + "learning_rate": 4.811082779000701e-06, + "loss": 0.0045, + "step": 44260 + }, + { + "epoch": 13.67, + "learning_rate": 4.810655264439813e-06, + "loss": 0.0052, + "step": 44261 + }, + { + "epoch": 13.67, + "learning_rate": 4.8102277628584194e-06, + "loss": 0.0045, + "step": 44262 + }, + { + "epoch": 13.67, + "learning_rate": 4.809800274257592e-06, + "loss": 0.0052, + "step": 44263 + }, + { + "epoch": 13.67, + "learning_rate": 4.809372798638405e-06, + "loss": 0.0043, + "step": 44264 + }, + { + "epoch": 13.67, + "learning_rate": 4.80894533600192e-06, + "loss": 0.0041, + "step": 44265 + }, + { + "epoch": 13.67, + "learning_rate": 4.8085178863492136e-06, + "loss": 0.0048, + "step": 44266 + }, + { + "epoch": 13.67, + "learning_rate": 4.808090449681349e-06, + "loss": 0.008, + "step": 44267 + }, + { + "epoch": 13.67, + "learning_rate": 4.807663025999395e-06, + "loss": 0.0048, + "step": 44268 + }, + { + "epoch": 13.67, + "learning_rate": 4.8072356153044216e-06, + "loss": 0.0052, + "step": 44269 + }, + { + "epoch": 13.67, + "learning_rate": 4.806808217597504e-06, + "loss": 0.0051, + "step": 44270 + }, + { + "epoch": 13.67, + "learning_rate": 4.806380832879706e-06, + "loss": 0.0049, + "step": 44271 + }, + { + "epoch": 13.67, + "learning_rate": 4.805953461152092e-06, + "loss": 0.0053, + "step": 44272 + }, + { + "epoch": 13.67, + "learning_rate": 4.805526102415741e-06, + "loss": 0.0058, + "step": 44273 + }, + { + "epoch": 13.67, + "learning_rate": 4.8050987566717125e-06, + "loss": 0.0053, + "step": 44274 + }, + { + "epoch": 13.67, + "learning_rate": 4.804671423921078e-06, + "loss": 0.0043, + "step": 44275 + }, + { + "epoch": 13.67, + "learning_rate": 4.8042441041649135e-06, + "loss": 0.0042, + "step": 44276 + }, + { + "epoch": 13.67, + "learning_rate": 4.803816797404281e-06, + "loss": 0.0043, + "step": 44277 + }, + { + "epoch": 13.67, + "learning_rate": 4.803389503640247e-06, + "loss": 0.0045, + "step": 44278 + }, + { + "epoch": 13.67, + "learning_rate": 4.802962222873887e-06, + "loss": 0.0068, + "step": 44279 + }, + { + "epoch": 13.67, + "learning_rate": 4.802534955106263e-06, + "loss": 0.005, + "step": 44280 + }, + { + "epoch": 13.67, + "learning_rate": 4.802107700338451e-06, + "loss": 0.0067, + "step": 44281 + }, + { + "epoch": 13.68, + "learning_rate": 4.8016804585715145e-06, + "loss": 0.0052, + "step": 44282 + }, + { + "epoch": 13.68, + "learning_rate": 4.801253229806522e-06, + "loss": 0.0058, + "step": 44283 + }, + { + "epoch": 13.68, + "learning_rate": 4.800826014044542e-06, + "loss": 0.0055, + "step": 44284 + }, + { + "epoch": 13.68, + "learning_rate": 4.800398811286648e-06, + "loss": 0.005, + "step": 44285 + }, + { + "epoch": 13.68, + "learning_rate": 4.799971621533901e-06, + "loss": 0.0051, + "step": 44286 + }, + { + "epoch": 13.68, + "learning_rate": 4.799544444787377e-06, + "loss": 0.0042, + "step": 44287 + }, + { + "epoch": 13.68, + "learning_rate": 4.799117281048141e-06, + "loss": 0.0046, + "step": 44288 + }, + { + "epoch": 13.68, + "learning_rate": 4.798690130317257e-06, + "loss": 0.0047, + "step": 44289 + }, + { + "epoch": 13.68, + "learning_rate": 4.7982629925957995e-06, + "loss": 0.0057, + "step": 44290 + }, + { + "epoch": 13.68, + "learning_rate": 4.797835867884837e-06, + "loss": 0.0059, + "step": 44291 + }, + { + "epoch": 13.68, + "learning_rate": 4.797408756185437e-06, + "loss": 0.0065, + "step": 44292 + }, + { + "epoch": 13.68, + "learning_rate": 4.796981657498662e-06, + "loss": 0.0063, + "step": 44293 + }, + { + "epoch": 13.68, + "learning_rate": 4.796554571825589e-06, + "loss": 0.0045, + "step": 44294 + }, + { + "epoch": 13.68, + "learning_rate": 4.796127499167278e-06, + "loss": 0.0056, + "step": 44295 + }, + { + "epoch": 13.68, + "learning_rate": 4.7957004395248005e-06, + "loss": 0.0046, + "step": 44296 + }, + { + "epoch": 13.68, + "learning_rate": 4.79527339289923e-06, + "loss": 0.005, + "step": 44297 + }, + { + "epoch": 13.68, + "learning_rate": 4.7948463592916304e-06, + "loss": 0.005, + "step": 44298 + }, + { + "epoch": 13.68, + "learning_rate": 4.794419338703066e-06, + "loss": 0.0057, + "step": 44299 + }, + { + "epoch": 13.68, + "learning_rate": 4.793992331134607e-06, + "loss": 0.0049, + "step": 44300 + }, + { + "epoch": 13.68, + "learning_rate": 4.793565336587327e-06, + "loss": 0.0043, + "step": 44301 + }, + { + "epoch": 13.68, + "learning_rate": 4.79313835506229e-06, + "loss": 0.0041, + "step": 44302 + }, + { + "epoch": 13.68, + "learning_rate": 4.79271138656056e-06, + "loss": 0.0047, + "step": 44303 + }, + { + "epoch": 13.68, + "learning_rate": 4.7922844310832115e-06, + "loss": 0.0057, + "step": 44304 + }, + { + "epoch": 13.68, + "learning_rate": 4.791857488631306e-06, + "loss": 0.0043, + "step": 44305 + }, + { + "epoch": 13.68, + "learning_rate": 4.791430559205915e-06, + "loss": 0.0051, + "step": 44306 + }, + { + "epoch": 13.68, + "learning_rate": 4.791003642808111e-06, + "loss": 0.0049, + "step": 44307 + }, + { + "epoch": 13.68, + "learning_rate": 4.790576739438956e-06, + "loss": 0.005, + "step": 44308 + }, + { + "epoch": 13.68, + "learning_rate": 4.7901498490995145e-06, + "loss": 0.0047, + "step": 44309 + }, + { + "epoch": 13.68, + "learning_rate": 4.7897229717908624e-06, + "loss": 0.0051, + "step": 44310 + }, + { + "epoch": 13.68, + "learning_rate": 4.78929610751406e-06, + "loss": 0.0048, + "step": 44311 + }, + { + "epoch": 13.68, + "learning_rate": 4.788869256270181e-06, + "loss": 0.0056, + "step": 44312 + }, + { + "epoch": 13.68, + "learning_rate": 4.788442418060292e-06, + "loss": 0.005, + "step": 44313 + }, + { + "epoch": 13.68, + "learning_rate": 4.788015592885455e-06, + "loss": 0.0068, + "step": 44314 + }, + { + "epoch": 13.69, + "learning_rate": 4.787588780746742e-06, + "loss": 0.0053, + "step": 44315 + }, + { + "epoch": 13.69, + "learning_rate": 4.787161981645222e-06, + "loss": 0.0041, + "step": 44316 + }, + { + "epoch": 13.69, + "learning_rate": 4.786735195581958e-06, + "loss": 0.0051, + "step": 44317 + }, + { + "epoch": 13.69, + "learning_rate": 4.786308422558025e-06, + "loss": 0.0059, + "step": 44318 + }, + { + "epoch": 13.69, + "learning_rate": 4.785881662574484e-06, + "loss": 0.0039, + "step": 44319 + }, + { + "epoch": 13.69, + "learning_rate": 4.7854549156324e-06, + "loss": 0.006, + "step": 44320 + }, + { + "epoch": 13.69, + "learning_rate": 4.785028181732846e-06, + "loss": 0.0054, + "step": 44321 + }, + { + "epoch": 13.69, + "learning_rate": 4.78460146087689e-06, + "loss": 0.0048, + "step": 44322 + }, + { + "epoch": 13.69, + "learning_rate": 4.784174753065598e-06, + "loss": 0.004, + "step": 44323 + }, + { + "epoch": 13.69, + "learning_rate": 4.783748058300032e-06, + "loss": 0.006, + "step": 44324 + }, + { + "epoch": 13.69, + "learning_rate": 4.783321376581267e-06, + "loss": 0.0073, + "step": 44325 + }, + { + "epoch": 13.69, + "learning_rate": 4.782894707910363e-06, + "loss": 0.0056, + "step": 44326 + }, + { + "epoch": 13.69, + "learning_rate": 4.782468052288391e-06, + "loss": 0.0041, + "step": 44327 + }, + { + "epoch": 13.69, + "learning_rate": 4.7820414097164254e-06, + "loss": 0.0064, + "step": 44328 + }, + { + "epoch": 13.69, + "learning_rate": 4.78161478019552e-06, + "loss": 0.0065, + "step": 44329 + }, + { + "epoch": 13.69, + "learning_rate": 4.781188163726745e-06, + "loss": 0.0053, + "step": 44330 + }, + { + "epoch": 13.69, + "learning_rate": 4.780761560311172e-06, + "loss": 0.0055, + "step": 44331 + }, + { + "epoch": 13.69, + "learning_rate": 4.780334969949869e-06, + "loss": 0.0059, + "step": 44332 + }, + { + "epoch": 13.69, + "learning_rate": 4.7799083926439014e-06, + "loss": 0.0037, + "step": 44333 + }, + { + "epoch": 13.69, + "learning_rate": 4.779481828394331e-06, + "loss": 0.0058, + "step": 44334 + }, + { + "epoch": 13.69, + "learning_rate": 4.7790552772022325e-06, + "loss": 0.0048, + "step": 44335 + }, + { + "epoch": 13.69, + "learning_rate": 4.778628739068664e-06, + "loss": 0.0049, + "step": 44336 + }, + { + "epoch": 13.69, + "learning_rate": 4.7782022139946985e-06, + "loss": 0.0063, + "step": 44337 + }, + { + "epoch": 13.69, + "learning_rate": 4.77777570198141e-06, + "loss": 0.0045, + "step": 44338 + }, + { + "epoch": 13.69, + "learning_rate": 4.777349203029848e-06, + "loss": 0.0063, + "step": 44339 + }, + { + "epoch": 13.69, + "learning_rate": 4.776922717141088e-06, + "loss": 0.005, + "step": 44340 + }, + { + "epoch": 13.69, + "learning_rate": 4.776496244316201e-06, + "loss": 0.0053, + "step": 44341 + }, + { + "epoch": 13.69, + "learning_rate": 4.776069784556246e-06, + "loss": 0.0058, + "step": 44342 + }, + { + "epoch": 13.69, + "learning_rate": 4.775643337862298e-06, + "loss": 0.0048, + "step": 44343 + }, + { + "epoch": 13.69, + "learning_rate": 4.775216904235418e-06, + "loss": 0.0047, + "step": 44344 + }, + { + "epoch": 13.69, + "learning_rate": 4.774790483676669e-06, + "loss": 0.0053, + "step": 44345 + }, + { + "epoch": 13.69, + "learning_rate": 4.774364076187123e-06, + "loss": 0.0044, + "step": 44346 + }, + { + "epoch": 13.7, + "learning_rate": 4.77393768176785e-06, + "loss": 0.0057, + "step": 44347 + }, + { + "epoch": 13.7, + "learning_rate": 4.773511300419911e-06, + "loss": 0.0046, + "step": 44348 + }, + { + "epoch": 13.7, + "learning_rate": 4.773084932144369e-06, + "loss": 0.0058, + "step": 44349 + }, + { + "epoch": 13.7, + "learning_rate": 4.772658576942299e-06, + "loss": 0.0066, + "step": 44350 + }, + { + "epoch": 13.7, + "learning_rate": 4.772232234814761e-06, + "loss": 0.0042, + "step": 44351 + }, + { + "epoch": 13.7, + "learning_rate": 4.771805905762822e-06, + "loss": 0.0072, + "step": 44352 + }, + { + "epoch": 13.7, + "learning_rate": 4.7713795897875544e-06, + "loss": 0.0046, + "step": 44353 + }, + { + "epoch": 13.7, + "learning_rate": 4.77095328689002e-06, + "loss": 0.0042, + "step": 44354 + }, + { + "epoch": 13.7, + "learning_rate": 4.770526997071282e-06, + "loss": 0.0047, + "step": 44355 + }, + { + "epoch": 13.7, + "learning_rate": 4.7701007203324125e-06, + "loss": 0.0047, + "step": 44356 + }, + { + "epoch": 13.7, + "learning_rate": 4.769674456674473e-06, + "loss": 0.0045, + "step": 44357 + }, + { + "epoch": 13.7, + "learning_rate": 4.769248206098529e-06, + "loss": 0.0049, + "step": 44358 + }, + { + "epoch": 13.7, + "learning_rate": 4.768821968605659e-06, + "loss": 0.0059, + "step": 44359 + }, + { + "epoch": 13.7, + "learning_rate": 4.768395744196911e-06, + "loss": 0.0051, + "step": 44360 + }, + { + "epoch": 13.7, + "learning_rate": 4.767969532873359e-06, + "loss": 0.0057, + "step": 44361 + }, + { + "epoch": 13.7, + "learning_rate": 4.76754333463607e-06, + "loss": 0.0058, + "step": 44362 + }, + { + "epoch": 13.7, + "learning_rate": 4.767117149486114e-06, + "loss": 0.0059, + "step": 44363 + }, + { + "epoch": 13.7, + "learning_rate": 4.766690977424551e-06, + "loss": 0.0053, + "step": 44364 + }, + { + "epoch": 13.7, + "learning_rate": 4.766264818452445e-06, + "loss": 0.0053, + "step": 44365 + }, + { + "epoch": 13.7, + "learning_rate": 4.7658386725708696e-06, + "loss": 0.0048, + "step": 44366 + }, + { + "epoch": 13.7, + "learning_rate": 4.765412539780881e-06, + "loss": 0.0055, + "step": 44367 + }, + { + "epoch": 13.7, + "learning_rate": 4.764986420083552e-06, + "loss": 0.0056, + "step": 44368 + }, + { + "epoch": 13.7, + "learning_rate": 4.764560313479955e-06, + "loss": 0.0049, + "step": 44369 + }, + { + "epoch": 13.7, + "learning_rate": 4.764134219971138e-06, + "loss": 0.0051, + "step": 44370 + }, + { + "epoch": 13.7, + "learning_rate": 4.763708139558177e-06, + "loss": 0.0052, + "step": 44371 + }, + { + "epoch": 13.7, + "learning_rate": 4.7632820722421404e-06, + "loss": 0.0052, + "step": 44372 + }, + { + "epoch": 13.7, + "learning_rate": 4.762856018024088e-06, + "loss": 0.0052, + "step": 44373 + }, + { + "epoch": 13.7, + "learning_rate": 4.762429976905091e-06, + "loss": 0.0053, + "step": 44374 + }, + { + "epoch": 13.7, + "learning_rate": 4.762003948886211e-06, + "loss": 0.0061, + "step": 44375 + }, + { + "epoch": 13.7, + "learning_rate": 4.761577933968512e-06, + "loss": 0.0048, + "step": 44376 + }, + { + "epoch": 13.7, + "learning_rate": 4.7611519321530605e-06, + "loss": 0.0048, + "step": 44377 + }, + { + "epoch": 13.7, + "learning_rate": 4.760725943440928e-06, + "loss": 0.0064, + "step": 44378 + }, + { + "epoch": 13.71, + "learning_rate": 4.760299967833176e-06, + "loss": 0.0062, + "step": 44379 + }, + { + "epoch": 13.71, + "learning_rate": 4.759874005330866e-06, + "loss": 0.0051, + "step": 44380 + }, + { + "epoch": 13.71, + "learning_rate": 4.759448055935069e-06, + "loss": 0.0065, + "step": 44381 + }, + { + "epoch": 13.71, + "learning_rate": 4.759022119646847e-06, + "loss": 0.0049, + "step": 44382 + }, + { + "epoch": 13.71, + "learning_rate": 4.758596196467265e-06, + "loss": 0.005, + "step": 44383 + }, + { + "epoch": 13.71, + "learning_rate": 4.758170286397394e-06, + "loss": 0.007, + "step": 44384 + }, + { + "epoch": 13.71, + "learning_rate": 4.757744389438293e-06, + "loss": 0.0044, + "step": 44385 + }, + { + "epoch": 13.71, + "learning_rate": 4.757318505591029e-06, + "loss": 0.0049, + "step": 44386 + }, + { + "epoch": 13.71, + "learning_rate": 4.756892634856669e-06, + "loss": 0.0059, + "step": 44387 + }, + { + "epoch": 13.71, + "learning_rate": 4.756466777236274e-06, + "loss": 0.0054, + "step": 44388 + }, + { + "epoch": 13.71, + "learning_rate": 4.7560409327309154e-06, + "loss": 0.0053, + "step": 44389 + }, + { + "epoch": 13.71, + "learning_rate": 4.755615101341655e-06, + "loss": 0.0047, + "step": 44390 + }, + { + "epoch": 13.71, + "learning_rate": 4.755189283069554e-06, + "loss": 0.0053, + "step": 44391 + }, + { + "epoch": 13.71, + "learning_rate": 4.754763477915682e-06, + "loss": 0.0064, + "step": 44392 + }, + { + "epoch": 13.71, + "learning_rate": 4.754337685881106e-06, + "loss": 0.0056, + "step": 44393 + }, + { + "epoch": 13.71, + "learning_rate": 4.753911906966885e-06, + "loss": 0.006, + "step": 44394 + }, + { + "epoch": 13.71, + "learning_rate": 4.753486141174091e-06, + "loss": 0.0055, + "step": 44395 + }, + { + "epoch": 13.71, + "learning_rate": 4.753060388503781e-06, + "loss": 0.0051, + "step": 44396 + }, + { + "epoch": 13.71, + "learning_rate": 4.752634648957027e-06, + "loss": 0.0059, + "step": 44397 + }, + { + "epoch": 13.71, + "learning_rate": 4.752208922534888e-06, + "loss": 0.0051, + "step": 44398 + }, + { + "epoch": 13.71, + "learning_rate": 4.751783209238435e-06, + "loss": 0.0045, + "step": 44399 + }, + { + "epoch": 13.71, + "learning_rate": 4.751357509068729e-06, + "loss": 0.0053, + "step": 44400 + }, + { + "epoch": 13.71, + "learning_rate": 4.750931822026832e-06, + "loss": 0.0062, + "step": 44401 + }, + { + "epoch": 13.71, + "learning_rate": 4.750506148113811e-06, + "loss": 0.0058, + "step": 44402 + }, + { + "epoch": 13.71, + "learning_rate": 4.750080487330737e-06, + "loss": 0.0052, + "step": 44403 + }, + { + "epoch": 13.71, + "learning_rate": 4.749654839678665e-06, + "loss": 0.0074, + "step": 44404 + }, + { + "epoch": 13.71, + "learning_rate": 4.749229205158666e-06, + "loss": 0.0043, + "step": 44405 + }, + { + "epoch": 13.71, + "learning_rate": 4.748803583771804e-06, + "loss": 0.0048, + "step": 44406 + }, + { + "epoch": 13.71, + "learning_rate": 4.748377975519138e-06, + "loss": 0.0043, + "step": 44407 + }, + { + "epoch": 13.71, + "learning_rate": 4.747952380401737e-06, + "loss": 0.0064, + "step": 44408 + }, + { + "epoch": 13.71, + "learning_rate": 4.747526798420668e-06, + "loss": 0.0047, + "step": 44409 + }, + { + "epoch": 13.71, + "learning_rate": 4.747101229576993e-06, + "loss": 0.0047, + "step": 44410 + }, + { + "epoch": 13.71, + "learning_rate": 4.746675673871771e-06, + "loss": 0.0051, + "step": 44411 + }, + { + "epoch": 13.72, + "learning_rate": 4.7462501313060764e-06, + "loss": 0.0057, + "step": 44412 + }, + { + "epoch": 13.72, + "learning_rate": 4.745824601880963e-06, + "loss": 0.0052, + "step": 44413 + }, + { + "epoch": 13.72, + "learning_rate": 4.745399085597502e-06, + "loss": 0.0049, + "step": 44414 + }, + { + "epoch": 13.72, + "learning_rate": 4.74497358245676e-06, + "loss": 0.0042, + "step": 44415 + }, + { + "epoch": 13.72, + "learning_rate": 4.744548092459796e-06, + "loss": 0.005, + "step": 44416 + }, + { + "epoch": 13.72, + "learning_rate": 4.744122615607674e-06, + "loss": 0.0041, + "step": 44417 + }, + { + "epoch": 13.72, + "learning_rate": 4.743697151901463e-06, + "loss": 0.0058, + "step": 44418 + }, + { + "epoch": 13.72, + "learning_rate": 4.7432717013422205e-06, + "loss": 0.0039, + "step": 44419 + }, + { + "epoch": 13.72, + "learning_rate": 4.742846263931017e-06, + "loss": 0.0049, + "step": 44420 + }, + { + "epoch": 13.72, + "learning_rate": 4.742420839668915e-06, + "loss": 0.0043, + "step": 44421 + }, + { + "epoch": 13.72, + "learning_rate": 4.741995428556974e-06, + "loss": 0.0057, + "step": 44422 + }, + { + "epoch": 13.72, + "learning_rate": 4.74157003059626e-06, + "loss": 0.0062, + "step": 44423 + }, + { + "epoch": 13.72, + "learning_rate": 4.7411446457878426e-06, + "loss": 0.0047, + "step": 44424 + }, + { + "epoch": 13.72, + "learning_rate": 4.740719274132778e-06, + "loss": 0.0056, + "step": 44425 + }, + { + "epoch": 13.72, + "learning_rate": 4.740293915632138e-06, + "loss": 0.0052, + "step": 44426 + }, + { + "epoch": 13.72, + "learning_rate": 4.7398685702869776e-06, + "loss": 0.004, + "step": 44427 + }, + { + "epoch": 13.72, + "learning_rate": 4.73944323809837e-06, + "loss": 0.0049, + "step": 44428 + }, + { + "epoch": 13.72, + "learning_rate": 4.73901791906737e-06, + "loss": 0.0039, + "step": 44429 + }, + { + "epoch": 13.72, + "learning_rate": 4.738592613195049e-06, + "loss": 0.0049, + "step": 44430 + }, + { + "epoch": 13.72, + "learning_rate": 4.738167320482468e-06, + "loss": 0.0056, + "step": 44431 + }, + { + "epoch": 13.72, + "learning_rate": 4.737742040930687e-06, + "loss": 0.0062, + "step": 44432 + }, + { + "epoch": 13.72, + "learning_rate": 4.7373167745407725e-06, + "loss": 0.0047, + "step": 44433 + }, + { + "epoch": 13.72, + "learning_rate": 4.736891521313792e-06, + "loss": 0.0047, + "step": 44434 + }, + { + "epoch": 13.72, + "learning_rate": 4.7364662812508025e-06, + "loss": 0.0047, + "step": 44435 + }, + { + "epoch": 13.72, + "learning_rate": 4.736041054352875e-06, + "loss": 0.0054, + "step": 44436 + }, + { + "epoch": 13.72, + "learning_rate": 4.735615840621067e-06, + "loss": 0.0038, + "step": 44437 + }, + { + "epoch": 13.72, + "learning_rate": 4.735190640056442e-06, + "loss": 0.0054, + "step": 44438 + }, + { + "epoch": 13.72, + "learning_rate": 4.734765452660065e-06, + "loss": 0.0049, + "step": 44439 + }, + { + "epoch": 13.72, + "learning_rate": 4.734340278433004e-06, + "loss": 0.0055, + "step": 44440 + }, + { + "epoch": 13.72, + "learning_rate": 4.7339151173763175e-06, + "loss": 0.0071, + "step": 44441 + }, + { + "epoch": 13.72, + "learning_rate": 4.7334899694910665e-06, + "loss": 0.0053, + "step": 44442 + }, + { + "epoch": 13.72, + "learning_rate": 4.733064834778321e-06, + "loss": 0.006, + "step": 44443 + }, + { + "epoch": 13.73, + "learning_rate": 4.7326397132391375e-06, + "loss": 0.0056, + "step": 44444 + }, + { + "epoch": 13.73, + "learning_rate": 4.732214604874583e-06, + "loss": 0.0053, + "step": 44445 + }, + { + "epoch": 13.73, + "learning_rate": 4.731789509685725e-06, + "loss": 0.0039, + "step": 44446 + }, + { + "epoch": 13.73, + "learning_rate": 4.7313644276736215e-06, + "loss": 0.0039, + "step": 44447 + }, + { + "epoch": 13.73, + "learning_rate": 4.730939358839332e-06, + "loss": 0.0052, + "step": 44448 + }, + { + "epoch": 13.73, + "learning_rate": 4.7305143031839296e-06, + "loss": 0.006, + "step": 44449 + }, + { + "epoch": 13.73, + "learning_rate": 4.730089260708467e-06, + "loss": 0.0047, + "step": 44450 + }, + { + "epoch": 13.73, + "learning_rate": 4.729664231414016e-06, + "loss": 0.0059, + "step": 44451 + }, + { + "epoch": 13.73, + "learning_rate": 4.729239215301636e-06, + "loss": 0.0049, + "step": 44452 + }, + { + "epoch": 13.73, + "learning_rate": 4.728814212372388e-06, + "loss": 0.0043, + "step": 44453 + }, + { + "epoch": 13.73, + "learning_rate": 4.728389222627335e-06, + "loss": 0.0046, + "step": 44454 + }, + { + "epoch": 13.73, + "learning_rate": 4.727964246067547e-06, + "loss": 0.0058, + "step": 44455 + }, + { + "epoch": 13.73, + "learning_rate": 4.727539282694078e-06, + "loss": 0.0045, + "step": 44456 + }, + { + "epoch": 13.73, + "learning_rate": 4.727114332507999e-06, + "loss": 0.0047, + "step": 44457 + }, + { + "epoch": 13.73, + "learning_rate": 4.726689395510368e-06, + "loss": 0.0041, + "step": 44458 + }, + { + "epoch": 13.73, + "learning_rate": 4.726264471702244e-06, + "loss": 0.0043, + "step": 44459 + }, + { + "epoch": 13.73, + "learning_rate": 4.725839561084696e-06, + "loss": 0.0048, + "step": 44460 + }, + { + "epoch": 13.73, + "learning_rate": 4.725414663658788e-06, + "loss": 0.0053, + "step": 44461 + }, + { + "epoch": 13.73, + "learning_rate": 4.724989779425581e-06, + "loss": 0.0052, + "step": 44462 + }, + { + "epoch": 13.73, + "learning_rate": 4.7245649083861325e-06, + "loss": 0.0055, + "step": 44463 + }, + { + "epoch": 13.73, + "learning_rate": 4.7241400505415095e-06, + "loss": 0.0054, + "step": 44464 + }, + { + "epoch": 13.73, + "learning_rate": 4.723715205892777e-06, + "loss": 0.0043, + "step": 44465 + }, + { + "epoch": 13.73, + "learning_rate": 4.723290374440992e-06, + "loss": 0.0055, + "step": 44466 + }, + { + "epoch": 13.73, + "learning_rate": 4.722865556187225e-06, + "loss": 0.0049, + "step": 44467 + }, + { + "epoch": 13.73, + "learning_rate": 4.722440751132532e-06, + "loss": 0.0047, + "step": 44468 + }, + { + "epoch": 13.73, + "learning_rate": 4.722015959277975e-06, + "loss": 0.0045, + "step": 44469 + }, + { + "epoch": 13.73, + "learning_rate": 4.721591180624619e-06, + "loss": 0.0058, + "step": 44470 + }, + { + "epoch": 13.73, + "learning_rate": 4.721166415173528e-06, + "loss": 0.005, + "step": 44471 + }, + { + "epoch": 13.73, + "learning_rate": 4.720741662925764e-06, + "loss": 0.0042, + "step": 44472 + }, + { + "epoch": 13.73, + "learning_rate": 4.720316923882384e-06, + "loss": 0.0044, + "step": 44473 + }, + { + "epoch": 13.73, + "learning_rate": 4.7198921980444576e-06, + "loss": 0.0083, + "step": 44474 + }, + { + "epoch": 13.73, + "learning_rate": 4.71946748541304e-06, + "loss": 0.0051, + "step": 44475 + }, + { + "epoch": 13.74, + "learning_rate": 4.719042785989199e-06, + "loss": 0.0052, + "step": 44476 + }, + { + "epoch": 13.74, + "learning_rate": 4.718618099774001e-06, + "loss": 0.0044, + "step": 44477 + }, + { + "epoch": 13.74, + "learning_rate": 4.718193426768496e-06, + "loss": 0.0048, + "step": 44478 + }, + { + "epoch": 13.74, + "learning_rate": 4.717768766973751e-06, + "loss": 0.0054, + "step": 44479 + }, + { + "epoch": 13.74, + "learning_rate": 4.717344120390834e-06, + "loss": 0.0045, + "step": 44480 + }, + { + "epoch": 13.74, + "learning_rate": 4.7169194870208e-06, + "loss": 0.0046, + "step": 44481 + }, + { + "epoch": 13.74, + "learning_rate": 4.716494866864717e-06, + "loss": 0.0047, + "step": 44482 + }, + { + "epoch": 13.74, + "learning_rate": 4.716070259923645e-06, + "loss": 0.0052, + "step": 44483 + }, + { + "epoch": 13.74, + "learning_rate": 4.715645666198641e-06, + "loss": 0.0059, + "step": 44484 + }, + { + "epoch": 13.74, + "learning_rate": 4.71522108569077e-06, + "loss": 0.0047, + "step": 44485 + }, + { + "epoch": 13.74, + "learning_rate": 4.714796518401099e-06, + "loss": 0.0046, + "step": 44486 + }, + { + "epoch": 13.74, + "learning_rate": 4.714371964330686e-06, + "loss": 0.0051, + "step": 44487 + }, + { + "epoch": 13.74, + "learning_rate": 4.713947423480589e-06, + "loss": 0.0055, + "step": 44488 + }, + { + "epoch": 13.74, + "learning_rate": 4.7135228958518775e-06, + "loss": 0.005, + "step": 44489 + }, + { + "epoch": 13.74, + "learning_rate": 4.713098381445605e-06, + "loss": 0.0047, + "step": 44490 + }, + { + "epoch": 13.74, + "learning_rate": 4.712673880262839e-06, + "loss": 0.0038, + "step": 44491 + }, + { + "epoch": 13.74, + "learning_rate": 4.712249392304643e-06, + "loss": 0.0045, + "step": 44492 + }, + { + "epoch": 13.74, + "learning_rate": 4.711824917572075e-06, + "loss": 0.0055, + "step": 44493 + }, + { + "epoch": 13.74, + "learning_rate": 4.711400456066195e-06, + "loss": 0.0056, + "step": 44494 + }, + { + "epoch": 13.74, + "learning_rate": 4.710976007788066e-06, + "loss": 0.0047, + "step": 44495 + }, + { + "epoch": 13.74, + "learning_rate": 4.710551572738755e-06, + "loss": 0.0052, + "step": 44496 + }, + { + "epoch": 13.74, + "learning_rate": 4.710127150919319e-06, + "loss": 0.0046, + "step": 44497 + }, + { + "epoch": 13.74, + "learning_rate": 4.709702742330816e-06, + "loss": 0.0051, + "step": 44498 + }, + { + "epoch": 13.74, + "learning_rate": 4.709278346974316e-06, + "loss": 0.005, + "step": 44499 + }, + { + "epoch": 13.74, + "learning_rate": 4.708853964850871e-06, + "loss": 0.0045, + "step": 44500 + }, + { + "epoch": 13.74, + "learning_rate": 4.708429595961548e-06, + "loss": 0.005, + "step": 44501 + }, + { + "epoch": 13.74, + "learning_rate": 4.70800524030741e-06, + "loss": 0.0051, + "step": 44502 + }, + { + "epoch": 13.74, + "learning_rate": 4.707580897889518e-06, + "loss": 0.0053, + "step": 44503 + }, + { + "epoch": 13.74, + "learning_rate": 4.707156568708926e-06, + "loss": 0.0064, + "step": 44504 + }, + { + "epoch": 13.74, + "learning_rate": 4.706732252766706e-06, + "loss": 0.0045, + "step": 44505 + }, + { + "epoch": 13.74, + "learning_rate": 4.70630795006391e-06, + "loss": 0.0063, + "step": 44506 + }, + { + "epoch": 13.74, + "learning_rate": 4.705883660601606e-06, + "loss": 0.0062, + "step": 44507 + }, + { + "epoch": 13.74, + "learning_rate": 4.705459384380854e-06, + "loss": 0.0048, + "step": 44508 + }, + { + "epoch": 13.75, + "learning_rate": 4.705035121402709e-06, + "loss": 0.0059, + "step": 44509 + }, + { + "epoch": 13.75, + "learning_rate": 4.704610871668237e-06, + "loss": 0.0056, + "step": 44510 + }, + { + "epoch": 13.75, + "learning_rate": 4.7041866351785026e-06, + "loss": 0.007, + "step": 44511 + }, + { + "epoch": 13.75, + "learning_rate": 4.70376241193456e-06, + "loss": 0.0058, + "step": 44512 + }, + { + "epoch": 13.75, + "learning_rate": 4.703338201937478e-06, + "loss": 0.0044, + "step": 44513 + }, + { + "epoch": 13.75, + "learning_rate": 4.702914005188312e-06, + "loss": 0.0043, + "step": 44514 + }, + { + "epoch": 13.75, + "learning_rate": 4.702489821688121e-06, + "loss": 0.0061, + "step": 44515 + }, + { + "epoch": 13.75, + "learning_rate": 4.702065651437969e-06, + "loss": 0.0042, + "step": 44516 + }, + { + "epoch": 13.75, + "learning_rate": 4.7016414944389214e-06, + "loss": 0.0054, + "step": 44517 + }, + { + "epoch": 13.75, + "learning_rate": 4.701217350692033e-06, + "loss": 0.004, + "step": 44518 + }, + { + "epoch": 13.75, + "learning_rate": 4.7007932201983645e-06, + "loss": 0.0067, + "step": 44519 + }, + { + "epoch": 13.75, + "learning_rate": 4.700369102958983e-06, + "loss": 0.0063, + "step": 44520 + }, + { + "epoch": 13.75, + "learning_rate": 4.699944998974939e-06, + "loss": 0.0048, + "step": 44521 + }, + { + "epoch": 13.75, + "learning_rate": 4.6995209082473e-06, + "loss": 0.006, + "step": 44522 + }, + { + "epoch": 13.75, + "learning_rate": 4.69909683077713e-06, + "loss": 0.0046, + "step": 44523 + }, + { + "epoch": 13.75, + "learning_rate": 4.698672766565486e-06, + "loss": 0.005, + "step": 44524 + }, + { + "epoch": 13.75, + "learning_rate": 4.698248715613425e-06, + "loss": 0.005, + "step": 44525 + }, + { + "epoch": 13.75, + "learning_rate": 4.6978246779220095e-06, + "loss": 0.0052, + "step": 44526 + }, + { + "epoch": 13.75, + "learning_rate": 4.697400653492306e-06, + "loss": 0.0059, + "step": 44527 + }, + { + "epoch": 13.75, + "learning_rate": 4.696976642325371e-06, + "loss": 0.0054, + "step": 44528 + }, + { + "epoch": 13.75, + "learning_rate": 4.696552644422261e-06, + "loss": 0.0068, + "step": 44529 + }, + { + "epoch": 13.75, + "learning_rate": 4.696128659784043e-06, + "loss": 0.0086, + "step": 44530 + }, + { + "epoch": 13.75, + "learning_rate": 4.6957046884117705e-06, + "loss": 0.0046, + "step": 44531 + }, + { + "epoch": 13.75, + "learning_rate": 4.69528073030651e-06, + "loss": 0.0057, + "step": 44532 + }, + { + "epoch": 13.75, + "learning_rate": 4.6948567854693215e-06, + "loss": 0.0046, + "step": 44533 + }, + { + "epoch": 13.75, + "learning_rate": 4.694432853901265e-06, + "loss": 0.0046, + "step": 44534 + }, + { + "epoch": 13.75, + "learning_rate": 4.694008935603396e-06, + "loss": 0.0056, + "step": 44535 + }, + { + "epoch": 13.75, + "learning_rate": 4.693585030576781e-06, + "loss": 0.004, + "step": 44536 + }, + { + "epoch": 13.75, + "learning_rate": 4.693161138822474e-06, + "loss": 0.0049, + "step": 44537 + }, + { + "epoch": 13.75, + "learning_rate": 4.692737260341543e-06, + "loss": 0.0052, + "step": 44538 + }, + { + "epoch": 13.75, + "learning_rate": 4.692313395135045e-06, + "loss": 0.0047, + "step": 44539 + }, + { + "epoch": 13.75, + "learning_rate": 4.691889543204035e-06, + "loss": 0.0046, + "step": 44540 + }, + { + "epoch": 13.76, + "learning_rate": 4.691465704549577e-06, + "loss": 0.0058, + "step": 44541 + }, + { + "epoch": 13.76, + "learning_rate": 4.691041879172735e-06, + "loss": 0.0065, + "step": 44542 + }, + { + "epoch": 13.76, + "learning_rate": 4.690618067074563e-06, + "loss": 0.0044, + "step": 44543 + }, + { + "epoch": 13.76, + "learning_rate": 4.690194268256126e-06, + "loss": 0.0061, + "step": 44544 + }, + { + "epoch": 13.76, + "learning_rate": 4.689770482718483e-06, + "loss": 0.0042, + "step": 44545 + }, + { + "epoch": 13.76, + "learning_rate": 4.689346710462688e-06, + "loss": 0.0053, + "step": 44546 + }, + { + "epoch": 13.76, + "learning_rate": 4.688922951489805e-06, + "loss": 0.005, + "step": 44547 + }, + { + "epoch": 13.76, + "learning_rate": 4.688499205800898e-06, + "loss": 0.0071, + "step": 44548 + }, + { + "epoch": 13.76, + "learning_rate": 4.688075473397025e-06, + "loss": 0.005, + "step": 44549 + }, + { + "epoch": 13.76, + "learning_rate": 4.687651754279239e-06, + "loss": 0.0047, + "step": 44550 + }, + { + "epoch": 13.76, + "learning_rate": 4.687228048448609e-06, + "loss": 0.004, + "step": 44551 + }, + { + "epoch": 13.76, + "learning_rate": 4.686804355906186e-06, + "loss": 0.0054, + "step": 44552 + }, + { + "epoch": 13.76, + "learning_rate": 4.686380676653035e-06, + "loss": 0.005, + "step": 44553 + }, + { + "epoch": 13.76, + "learning_rate": 4.6859570106902194e-06, + "loss": 0.0048, + "step": 44554 + }, + { + "epoch": 13.76, + "learning_rate": 4.6855333580187935e-06, + "loss": 0.0062, + "step": 44555 + }, + { + "epoch": 13.76, + "learning_rate": 4.685109718639815e-06, + "loss": 0.0055, + "step": 44556 + }, + { + "epoch": 13.76, + "learning_rate": 4.68468609255435e-06, + "loss": 0.0055, + "step": 44557 + }, + { + "epoch": 13.76, + "learning_rate": 4.68426247976345e-06, + "loss": 0.0053, + "step": 44558 + }, + { + "epoch": 13.76, + "learning_rate": 4.6838388802681846e-06, + "loss": 0.0051, + "step": 44559 + }, + { + "epoch": 13.76, + "learning_rate": 4.683415294069603e-06, + "loss": 0.0041, + "step": 44560 + }, + { + "epoch": 13.76, + "learning_rate": 4.682991721168773e-06, + "loss": 0.0059, + "step": 44561 + }, + { + "epoch": 13.76, + "learning_rate": 4.682568161566746e-06, + "loss": 0.0053, + "step": 44562 + }, + { + "epoch": 13.76, + "learning_rate": 4.682144615264588e-06, + "loss": 0.0045, + "step": 44563 + }, + { + "epoch": 13.76, + "learning_rate": 4.681721082263358e-06, + "loss": 0.0052, + "step": 44564 + }, + { + "epoch": 13.76, + "learning_rate": 4.6812975625641144e-06, + "loss": 0.0057, + "step": 44565 + }, + { + "epoch": 13.76, + "learning_rate": 4.680874056167912e-06, + "loss": 0.0042, + "step": 44566 + }, + { + "epoch": 13.76, + "learning_rate": 4.680450563075817e-06, + "loss": 0.0066, + "step": 44567 + }, + { + "epoch": 13.76, + "learning_rate": 4.680027083288882e-06, + "loss": 0.0046, + "step": 44568 + }, + { + "epoch": 13.76, + "learning_rate": 4.679603616808174e-06, + "loss": 0.0044, + "step": 44569 + }, + { + "epoch": 13.76, + "learning_rate": 4.679180163634746e-06, + "loss": 0.0041, + "step": 44570 + }, + { + "epoch": 13.76, + "learning_rate": 4.678756723769656e-06, + "loss": 0.0045, + "step": 44571 + }, + { + "epoch": 13.76, + "learning_rate": 4.678333297213966e-06, + "loss": 0.0073, + "step": 44572 + }, + { + "epoch": 13.76, + "learning_rate": 4.677909883968739e-06, + "loss": 0.0053, + "step": 44573 + }, + { + "epoch": 13.77, + "learning_rate": 4.677486484035027e-06, + "loss": 0.0051, + "step": 44574 + }, + { + "epoch": 13.77, + "learning_rate": 4.677063097413894e-06, + "loss": 0.0053, + "step": 44575 + }, + { + "epoch": 13.77, + "learning_rate": 4.676639724106399e-06, + "loss": 0.0043, + "step": 44576 + }, + { + "epoch": 13.77, + "learning_rate": 4.676216364113594e-06, + "loss": 0.0054, + "step": 44577 + }, + { + "epoch": 13.77, + "learning_rate": 4.675793017436543e-06, + "loss": 0.0062, + "step": 44578 + }, + { + "epoch": 13.77, + "learning_rate": 4.675369684076308e-06, + "loss": 0.0066, + "step": 44579 + }, + { + "epoch": 13.77, + "learning_rate": 4.674946364033946e-06, + "loss": 0.0044, + "step": 44580 + }, + { + "epoch": 13.77, + "learning_rate": 4.6745230573105096e-06, + "loss": 0.0047, + "step": 44581 + }, + { + "epoch": 13.77, + "learning_rate": 4.674099763907066e-06, + "loss": 0.0055, + "step": 44582 + }, + { + "epoch": 13.77, + "learning_rate": 4.673676483824666e-06, + "loss": 0.0047, + "step": 44583 + }, + { + "epoch": 13.77, + "learning_rate": 4.673253217064374e-06, + "loss": 0.0061, + "step": 44584 + }, + { + "epoch": 13.77, + "learning_rate": 4.672829963627254e-06, + "loss": 0.0064, + "step": 44585 + }, + { + "epoch": 13.77, + "learning_rate": 4.672406723514351e-06, + "loss": 0.0051, + "step": 44586 + }, + { + "epoch": 13.77, + "learning_rate": 4.6719834967267295e-06, + "loss": 0.0052, + "step": 44587 + }, + { + "epoch": 13.77, + "learning_rate": 4.671560283265454e-06, + "loss": 0.0049, + "step": 44588 + }, + { + "epoch": 13.77, + "learning_rate": 4.671137083131573e-06, + "loss": 0.0045, + "step": 44589 + }, + { + "epoch": 13.77, + "learning_rate": 4.670713896326155e-06, + "loss": 0.0059, + "step": 44590 + }, + { + "epoch": 13.77, + "learning_rate": 4.670290722850248e-06, + "loss": 0.0054, + "step": 44591 + }, + { + "epoch": 13.77, + "learning_rate": 4.669867562704922e-06, + "loss": 0.0062, + "step": 44592 + }, + { + "epoch": 13.77, + "learning_rate": 4.669444415891225e-06, + "loss": 0.0053, + "step": 44593 + }, + { + "epoch": 13.77, + "learning_rate": 4.6690212824102185e-06, + "loss": 0.0049, + "step": 44594 + }, + { + "epoch": 13.77, + "learning_rate": 4.66859816226297e-06, + "loss": 0.0049, + "step": 44595 + }, + { + "epoch": 13.77, + "learning_rate": 4.6681750554505236e-06, + "loss": 0.0059, + "step": 44596 + }, + { + "epoch": 13.77, + "learning_rate": 4.667751961973943e-06, + "loss": 0.0044, + "step": 44597 + }, + { + "epoch": 13.77, + "learning_rate": 4.667328881834291e-06, + "loss": 0.0054, + "step": 44598 + }, + { + "epoch": 13.77, + "learning_rate": 4.666905815032618e-06, + "loss": 0.005, + "step": 44599 + }, + { + "epoch": 13.77, + "learning_rate": 4.66648276156999e-06, + "loss": 0.0058, + "step": 44600 + }, + { + "epoch": 13.77, + "learning_rate": 4.666059721447462e-06, + "loss": 0.0051, + "step": 44601 + }, + { + "epoch": 13.77, + "learning_rate": 4.665636694666088e-06, + "loss": 0.0044, + "step": 44602 + }, + { + "epoch": 13.77, + "learning_rate": 4.665213681226929e-06, + "loss": 0.005, + "step": 44603 + }, + { + "epoch": 13.77, + "learning_rate": 4.664790681131047e-06, + "loss": 0.0042, + "step": 44604 + }, + { + "epoch": 13.77, + "learning_rate": 4.664367694379497e-06, + "loss": 0.0066, + "step": 44605 + }, + { + "epoch": 13.78, + "learning_rate": 4.663944720973333e-06, + "loss": 0.0059, + "step": 44606 + }, + { + "epoch": 13.78, + "learning_rate": 4.66352176091362e-06, + "loss": 0.0055, + "step": 44607 + }, + { + "epoch": 13.78, + "learning_rate": 4.663098814201409e-06, + "loss": 0.0051, + "step": 44608 + }, + { + "epoch": 13.78, + "learning_rate": 4.6626758808377605e-06, + "loss": 0.0043, + "step": 44609 + }, + { + "epoch": 13.78, + "learning_rate": 4.662252960823738e-06, + "loss": 0.0049, + "step": 44610 + }, + { + "epoch": 13.78, + "learning_rate": 4.661830054160393e-06, + "loss": 0.0068, + "step": 44611 + }, + { + "epoch": 13.78, + "learning_rate": 4.661407160848782e-06, + "loss": 0.0057, + "step": 44612 + }, + { + "epoch": 13.78, + "learning_rate": 4.660984280889969e-06, + "loss": 0.005, + "step": 44613 + }, + { + "epoch": 13.78, + "learning_rate": 4.6605614142850045e-06, + "loss": 0.0059, + "step": 44614 + }, + { + "epoch": 13.78, + "learning_rate": 4.660138561034948e-06, + "loss": 0.0058, + "step": 44615 + }, + { + "epoch": 13.78, + "learning_rate": 4.6597157211408686e-06, + "loss": 0.0054, + "step": 44616 + }, + { + "epoch": 13.78, + "learning_rate": 4.659292894603805e-06, + "loss": 0.0059, + "step": 44617 + }, + { + "epoch": 13.78, + "learning_rate": 4.658870081424826e-06, + "loss": 0.0048, + "step": 44618 + }, + { + "epoch": 13.78, + "learning_rate": 4.658447281604988e-06, + "loss": 0.0057, + "step": 44619 + }, + { + "epoch": 13.78, + "learning_rate": 4.6580244951453455e-06, + "loss": 0.0051, + "step": 44620 + }, + { + "epoch": 13.78, + "learning_rate": 4.657601722046963e-06, + "loss": 0.0054, + "step": 44621 + }, + { + "epoch": 13.78, + "learning_rate": 4.657178962310891e-06, + "loss": 0.0053, + "step": 44622 + }, + { + "epoch": 13.78, + "learning_rate": 4.6567562159381865e-06, + "loss": 0.0059, + "step": 44623 + }, + { + "epoch": 13.78, + "learning_rate": 4.656333482929908e-06, + "loss": 0.0079, + "step": 44624 + }, + { + "epoch": 13.78, + "learning_rate": 4.6559107632871145e-06, + "loss": 0.0049, + "step": 44625 + }, + { + "epoch": 13.78, + "learning_rate": 4.655488057010871e-06, + "loss": 0.0046, + "step": 44626 + }, + { + "epoch": 13.78, + "learning_rate": 4.655065364102218e-06, + "loss": 0.0068, + "step": 44627 + }, + { + "epoch": 13.78, + "learning_rate": 4.654642684562223e-06, + "loss": 0.0052, + "step": 44628 + }, + { + "epoch": 13.78, + "learning_rate": 4.654220018391944e-06, + "loss": 0.0058, + "step": 44629 + }, + { + "epoch": 13.78, + "learning_rate": 4.6537973655924325e-06, + "loss": 0.005, + "step": 44630 + }, + { + "epoch": 13.78, + "learning_rate": 4.653374726164752e-06, + "loss": 0.007, + "step": 44631 + }, + { + "epoch": 13.78, + "learning_rate": 4.652952100109957e-06, + "loss": 0.0065, + "step": 44632 + }, + { + "epoch": 13.78, + "learning_rate": 4.652529487429101e-06, + "loss": 0.0057, + "step": 44633 + }, + { + "epoch": 13.78, + "learning_rate": 4.652106888123244e-06, + "loss": 0.0061, + "step": 44634 + }, + { + "epoch": 13.78, + "learning_rate": 4.651684302193445e-06, + "loss": 0.0046, + "step": 44635 + }, + { + "epoch": 13.78, + "learning_rate": 4.65126172964076e-06, + "loss": 0.0048, + "step": 44636 + }, + { + "epoch": 13.78, + "learning_rate": 4.6508391704662425e-06, + "loss": 0.0058, + "step": 44637 + }, + { + "epoch": 13.79, + "learning_rate": 4.650416624670954e-06, + "loss": 0.0055, + "step": 44638 + }, + { + "epoch": 13.79, + "learning_rate": 4.649994092255946e-06, + "loss": 0.0056, + "step": 44639 + }, + { + "epoch": 13.79, + "learning_rate": 4.649571573222279e-06, + "loss": 0.005, + "step": 44640 + }, + { + "epoch": 13.79, + "learning_rate": 4.649149067571012e-06, + "loss": 0.0043, + "step": 44641 + }, + { + "epoch": 13.79, + "learning_rate": 4.648726575303201e-06, + "loss": 0.0065, + "step": 44642 + }, + { + "epoch": 13.79, + "learning_rate": 4.648304096419896e-06, + "loss": 0.0052, + "step": 44643 + }, + { + "epoch": 13.79, + "learning_rate": 4.647881630922161e-06, + "loss": 0.0054, + "step": 44644 + }, + { + "epoch": 13.79, + "learning_rate": 4.6474591788110475e-06, + "loss": 0.0053, + "step": 44645 + }, + { + "epoch": 13.79, + "learning_rate": 4.647036740087619e-06, + "loss": 0.0058, + "step": 44646 + }, + { + "epoch": 13.79, + "learning_rate": 4.646614314752927e-06, + "loss": 0.0041, + "step": 44647 + }, + { + "epoch": 13.79, + "learning_rate": 4.646191902808027e-06, + "loss": 0.0047, + "step": 44648 + }, + { + "epoch": 13.79, + "learning_rate": 4.645769504253976e-06, + "loss": 0.0058, + "step": 44649 + }, + { + "epoch": 13.79, + "learning_rate": 4.645347119091837e-06, + "loss": 0.0057, + "step": 44650 + }, + { + "epoch": 13.79, + "learning_rate": 4.644924747322656e-06, + "loss": 0.0053, + "step": 44651 + }, + { + "epoch": 13.79, + "learning_rate": 4.6445023889475e-06, + "loss": 0.0041, + "step": 44652 + }, + { + "epoch": 13.79, + "learning_rate": 4.644080043967419e-06, + "loss": 0.0046, + "step": 44653 + }, + { + "epoch": 13.79, + "learning_rate": 4.643657712383469e-06, + "loss": 0.005, + "step": 44654 + }, + { + "epoch": 13.79, + "learning_rate": 4.643235394196707e-06, + "loss": 0.0045, + "step": 44655 + }, + { + "epoch": 13.79, + "learning_rate": 4.642813089408194e-06, + "loss": 0.0043, + "step": 44656 + }, + { + "epoch": 13.79, + "learning_rate": 4.642390798018982e-06, + "loss": 0.0053, + "step": 44657 + }, + { + "epoch": 13.79, + "learning_rate": 4.641968520030125e-06, + "loss": 0.0047, + "step": 44658 + }, + { + "epoch": 13.79, + "learning_rate": 4.641546255442681e-06, + "loss": 0.0053, + "step": 44659 + }, + { + "epoch": 13.79, + "learning_rate": 4.641124004257711e-06, + "loss": 0.0051, + "step": 44660 + }, + { + "epoch": 13.79, + "learning_rate": 4.640701766476265e-06, + "loss": 0.0044, + "step": 44661 + }, + { + "epoch": 13.79, + "learning_rate": 4.640279542099403e-06, + "loss": 0.0058, + "step": 44662 + }, + { + "epoch": 13.79, + "learning_rate": 4.63985733112818e-06, + "loss": 0.006, + "step": 44663 + }, + { + "epoch": 13.79, + "learning_rate": 4.639435133563648e-06, + "loss": 0.0053, + "step": 44664 + }, + { + "epoch": 13.79, + "learning_rate": 4.639012949406867e-06, + "loss": 0.0055, + "step": 44665 + }, + { + "epoch": 13.79, + "learning_rate": 4.638590778658896e-06, + "loss": 0.0052, + "step": 44666 + }, + { + "epoch": 13.79, + "learning_rate": 4.638168621320787e-06, + "loss": 0.0051, + "step": 44667 + }, + { + "epoch": 13.79, + "learning_rate": 4.637746477393592e-06, + "loss": 0.0064, + "step": 44668 + }, + { + "epoch": 13.79, + "learning_rate": 4.6373243468783745e-06, + "loss": 0.0049, + "step": 44669 + }, + { + "epoch": 13.79, + "learning_rate": 4.6369022297761845e-06, + "loss": 0.0058, + "step": 44670 + }, + { + "epoch": 13.8, + "learning_rate": 4.63648012608808e-06, + "loss": 0.0044, + "step": 44671 + }, + { + "epoch": 13.8, + "learning_rate": 4.63605803581512e-06, + "loss": 0.0061, + "step": 44672 + }, + { + "epoch": 13.8, + "learning_rate": 4.635635958958356e-06, + "loss": 0.0056, + "step": 44673 + }, + { + "epoch": 13.8, + "learning_rate": 4.635213895518844e-06, + "loss": 0.0052, + "step": 44674 + }, + { + "epoch": 13.8, + "learning_rate": 4.634791845497643e-06, + "loss": 0.0065, + "step": 44675 + }, + { + "epoch": 13.8, + "learning_rate": 4.634369808895802e-06, + "loss": 0.0047, + "step": 44676 + }, + { + "epoch": 13.8, + "learning_rate": 4.633947785714384e-06, + "loss": 0.0045, + "step": 44677 + }, + { + "epoch": 13.8, + "learning_rate": 4.6335257759544424e-06, + "loss": 0.0045, + "step": 44678 + }, + { + "epoch": 13.8, + "learning_rate": 4.633103779617028e-06, + "loss": 0.0043, + "step": 44679 + }, + { + "epoch": 13.8, + "learning_rate": 4.632681796703199e-06, + "loss": 0.0057, + "step": 44680 + }, + { + "epoch": 13.8, + "learning_rate": 4.632259827214016e-06, + "loss": 0.0051, + "step": 44681 + }, + { + "epoch": 13.8, + "learning_rate": 4.631837871150526e-06, + "loss": 0.0043, + "step": 44682 + }, + { + "epoch": 13.8, + "learning_rate": 4.631415928513793e-06, + "loss": 0.0059, + "step": 44683 + }, + { + "epoch": 13.8, + "learning_rate": 4.630993999304867e-06, + "loss": 0.0049, + "step": 44684 + }, + { + "epoch": 13.8, + "learning_rate": 4.630572083524801e-06, + "loss": 0.0051, + "step": 44685 + }, + { + "epoch": 13.8, + "learning_rate": 4.630150181174654e-06, + "loss": 0.0045, + "step": 44686 + }, + { + "epoch": 13.8, + "learning_rate": 4.629728292255484e-06, + "loss": 0.0038, + "step": 44687 + }, + { + "epoch": 13.8, + "learning_rate": 4.629306416768343e-06, + "loss": 0.0056, + "step": 44688 + }, + { + "epoch": 13.8, + "learning_rate": 4.628884554714284e-06, + "loss": 0.0044, + "step": 44689 + }, + { + "epoch": 13.8, + "learning_rate": 4.628462706094362e-06, + "loss": 0.0048, + "step": 44690 + }, + { + "epoch": 13.8, + "learning_rate": 4.6280408709096395e-06, + "loss": 0.005, + "step": 44691 + }, + { + "epoch": 13.8, + "learning_rate": 4.627619049161163e-06, + "loss": 0.006, + "step": 44692 + }, + { + "epoch": 13.8, + "learning_rate": 4.627197240849995e-06, + "loss": 0.0051, + "step": 44693 + }, + { + "epoch": 13.8, + "learning_rate": 4.6267754459771856e-06, + "loss": 0.0055, + "step": 44694 + }, + { + "epoch": 13.8, + "learning_rate": 4.626353664543787e-06, + "loss": 0.0055, + "step": 44695 + }, + { + "epoch": 13.8, + "learning_rate": 4.625931896550858e-06, + "loss": 0.0051, + "step": 44696 + }, + { + "epoch": 13.8, + "learning_rate": 4.6255101419994585e-06, + "loss": 0.0052, + "step": 44697 + }, + { + "epoch": 13.8, + "learning_rate": 4.625088400890637e-06, + "loss": 0.0049, + "step": 44698 + }, + { + "epoch": 13.8, + "learning_rate": 4.624666673225448e-06, + "loss": 0.0052, + "step": 44699 + }, + { + "epoch": 13.8, + "learning_rate": 4.62424495900495e-06, + "loss": 0.0047, + "step": 44700 + }, + { + "epoch": 13.8, + "learning_rate": 4.623823258230192e-06, + "loss": 0.0038, + "step": 44701 + }, + { + "epoch": 13.8, + "learning_rate": 4.6234015709022324e-06, + "loss": 0.0051, + "step": 44702 + }, + { + "epoch": 13.81, + "learning_rate": 4.622979897022132e-06, + "loss": 0.0048, + "step": 44703 + }, + { + "epoch": 13.81, + "learning_rate": 4.622558236590937e-06, + "loss": 0.0057, + "step": 44704 + }, + { + "epoch": 13.81, + "learning_rate": 4.622136589609703e-06, + "loss": 0.0054, + "step": 44705 + }, + { + "epoch": 13.81, + "learning_rate": 4.621714956079488e-06, + "loss": 0.0053, + "step": 44706 + }, + { + "epoch": 13.81, + "learning_rate": 4.621293336001342e-06, + "loss": 0.0048, + "step": 44707 + }, + { + "epoch": 13.81, + "learning_rate": 4.620871729376327e-06, + "loss": 0.0049, + "step": 44708 + }, + { + "epoch": 13.81, + "learning_rate": 4.620450136205492e-06, + "loss": 0.0045, + "step": 44709 + }, + { + "epoch": 13.81, + "learning_rate": 4.62002855648989e-06, + "loss": 0.0054, + "step": 44710 + }, + { + "epoch": 13.81, + "learning_rate": 4.619606990230575e-06, + "loss": 0.0044, + "step": 44711 + }, + { + "epoch": 13.81, + "learning_rate": 4.619185437428611e-06, + "loss": 0.0053, + "step": 44712 + }, + { + "epoch": 13.81, + "learning_rate": 4.61876389808504e-06, + "loss": 0.0055, + "step": 44713 + }, + { + "epoch": 13.81, + "learning_rate": 4.618342372200926e-06, + "loss": 0.0049, + "step": 44714 + }, + { + "epoch": 13.81, + "learning_rate": 4.617920859777319e-06, + "loss": 0.0044, + "step": 44715 + }, + { + "epoch": 13.81, + "learning_rate": 4.6174993608152705e-06, + "loss": 0.0054, + "step": 44716 + }, + { + "epoch": 13.81, + "learning_rate": 4.617077875315837e-06, + "loss": 0.0057, + "step": 44717 + }, + { + "epoch": 13.81, + "learning_rate": 4.616656403280079e-06, + "loss": 0.0056, + "step": 44718 + }, + { + "epoch": 13.81, + "learning_rate": 4.616234944709044e-06, + "loss": 0.0056, + "step": 44719 + }, + { + "epoch": 13.81, + "learning_rate": 4.615813499603783e-06, + "loss": 0.0065, + "step": 44720 + }, + { + "epoch": 13.81, + "learning_rate": 4.615392067965355e-06, + "loss": 0.0068, + "step": 44721 + }, + { + "epoch": 13.81, + "learning_rate": 4.614970649794818e-06, + "loss": 0.0059, + "step": 44722 + }, + { + "epoch": 13.81, + "learning_rate": 4.614549245093217e-06, + "loss": 0.0047, + "step": 44723 + }, + { + "epoch": 13.81, + "learning_rate": 4.614127853861614e-06, + "loss": 0.0054, + "step": 44724 + }, + { + "epoch": 13.81, + "learning_rate": 4.613706476101061e-06, + "loss": 0.0047, + "step": 44725 + }, + { + "epoch": 13.81, + "learning_rate": 4.6132851118126055e-06, + "loss": 0.0056, + "step": 44726 + }, + { + "epoch": 13.81, + "learning_rate": 4.612863760997306e-06, + "loss": 0.0064, + "step": 44727 + }, + { + "epoch": 13.81, + "learning_rate": 4.612442423656221e-06, + "loss": 0.0045, + "step": 44728 + }, + { + "epoch": 13.81, + "learning_rate": 4.612021099790402e-06, + "loss": 0.0055, + "step": 44729 + }, + { + "epoch": 13.81, + "learning_rate": 4.611599789400895e-06, + "loss": 0.005, + "step": 44730 + }, + { + "epoch": 13.81, + "learning_rate": 4.611178492488764e-06, + "loss": 0.0043, + "step": 44731 + }, + { + "epoch": 13.81, + "learning_rate": 4.610757209055055e-06, + "loss": 0.0035, + "step": 44732 + }, + { + "epoch": 13.81, + "learning_rate": 4.610335939100824e-06, + "loss": 0.0046, + "step": 44733 + }, + { + "epoch": 13.81, + "learning_rate": 4.609914682627135e-06, + "loss": 0.0062, + "step": 44734 + }, + { + "epoch": 13.82, + "learning_rate": 4.609493439635023e-06, + "loss": 0.0055, + "step": 44735 + }, + { + "epoch": 13.82, + "learning_rate": 4.6090722101255526e-06, + "loss": 0.0042, + "step": 44736 + }, + { + "epoch": 13.82, + "learning_rate": 4.608650994099779e-06, + "loss": 0.0052, + "step": 44737 + }, + { + "epoch": 13.82, + "learning_rate": 4.608229791558749e-06, + "loss": 0.0053, + "step": 44738 + }, + { + "epoch": 13.82, + "learning_rate": 4.607808602503524e-06, + "loss": 0.0044, + "step": 44739 + }, + { + "epoch": 13.82, + "learning_rate": 4.607387426935152e-06, + "loss": 0.005, + "step": 44740 + }, + { + "epoch": 13.82, + "learning_rate": 4.606966264854686e-06, + "loss": 0.0055, + "step": 44741 + }, + { + "epoch": 13.82, + "learning_rate": 4.6065451162631795e-06, + "loss": 0.0054, + "step": 44742 + }, + { + "epoch": 13.82, + "learning_rate": 4.606123981161691e-06, + "loss": 0.006, + "step": 44743 + }, + { + "epoch": 13.82, + "learning_rate": 4.6057028595512695e-06, + "loss": 0.0058, + "step": 44744 + }, + { + "epoch": 13.82, + "learning_rate": 4.605281751432967e-06, + "loss": 0.0047, + "step": 44745 + }, + { + "epoch": 13.82, + "learning_rate": 4.604860656807842e-06, + "loss": 0.0044, + "step": 44746 + }, + { + "epoch": 13.82, + "learning_rate": 4.60443957567694e-06, + "loss": 0.0042, + "step": 44747 + }, + { + "epoch": 13.82, + "learning_rate": 4.604018508041319e-06, + "loss": 0.0041, + "step": 44748 + }, + { + "epoch": 13.82, + "learning_rate": 4.603597453902035e-06, + "loss": 0.007, + "step": 44749 + }, + { + "epoch": 13.82, + "learning_rate": 4.60317641326014e-06, + "loss": 0.0054, + "step": 44750 + }, + { + "epoch": 13.82, + "learning_rate": 4.60275538611668e-06, + "loss": 0.0051, + "step": 44751 + }, + { + "epoch": 13.82, + "learning_rate": 4.602334372472717e-06, + "loss": 0.0048, + "step": 44752 + }, + { + "epoch": 13.82, + "learning_rate": 4.6019133723292965e-06, + "loss": 0.0042, + "step": 44753 + }, + { + "epoch": 13.82, + "learning_rate": 4.601492385687478e-06, + "loss": 0.0056, + "step": 44754 + }, + { + "epoch": 13.82, + "learning_rate": 4.601071412548309e-06, + "loss": 0.0053, + "step": 44755 + }, + { + "epoch": 13.82, + "learning_rate": 4.600650452912849e-06, + "loss": 0.0047, + "step": 44756 + }, + { + "epoch": 13.82, + "learning_rate": 4.600229506782143e-06, + "loss": 0.0064, + "step": 44757 + }, + { + "epoch": 13.82, + "learning_rate": 4.599808574157249e-06, + "loss": 0.004, + "step": 44758 + }, + { + "epoch": 13.82, + "learning_rate": 4.59938765503922e-06, + "loss": 0.0052, + "step": 44759 + }, + { + "epoch": 13.82, + "learning_rate": 4.598966749429109e-06, + "loss": 0.0043, + "step": 44760 + }, + { + "epoch": 13.82, + "learning_rate": 4.598545857327963e-06, + "loss": 0.0049, + "step": 44761 + }, + { + "epoch": 13.82, + "learning_rate": 4.598124978736843e-06, + "loss": 0.0063, + "step": 44762 + }, + { + "epoch": 13.82, + "learning_rate": 4.5977041136567945e-06, + "loss": 0.0054, + "step": 44763 + }, + { + "epoch": 13.82, + "learning_rate": 4.597283262088876e-06, + "loss": 0.0052, + "step": 44764 + }, + { + "epoch": 13.82, + "learning_rate": 4.596862424034139e-06, + "loss": 0.0049, + "step": 44765 + }, + { + "epoch": 13.82, + "learning_rate": 4.596441599493628e-06, + "loss": 0.0048, + "step": 44766 + }, + { + "epoch": 13.82, + "learning_rate": 4.596020788468405e-06, + "loss": 0.0054, + "step": 44767 + }, + { + "epoch": 13.83, + "learning_rate": 4.595599990959521e-06, + "loss": 0.0039, + "step": 44768 + }, + { + "epoch": 13.83, + "learning_rate": 4.5951792069680255e-06, + "loss": 0.0043, + "step": 44769 + }, + { + "epoch": 13.83, + "learning_rate": 4.594758436494976e-06, + "loss": 0.0045, + "step": 44770 + }, + { + "epoch": 13.83, + "learning_rate": 4.594337679541421e-06, + "loss": 0.0052, + "step": 44771 + }, + { + "epoch": 13.83, + "learning_rate": 4.593916936108409e-06, + "loss": 0.0054, + "step": 44772 + }, + { + "epoch": 13.83, + "learning_rate": 4.593496206196997e-06, + "loss": 0.0043, + "step": 44773 + }, + { + "epoch": 13.83, + "learning_rate": 4.593075489808242e-06, + "loss": 0.006, + "step": 44774 + }, + { + "epoch": 13.83, + "learning_rate": 4.59265478694319e-06, + "loss": 0.0049, + "step": 44775 + }, + { + "epoch": 13.83, + "learning_rate": 4.592234097602891e-06, + "loss": 0.005, + "step": 44776 + }, + { + "epoch": 13.83, + "learning_rate": 4.591813421788406e-06, + "loss": 0.0058, + "step": 44777 + }, + { + "epoch": 13.83, + "learning_rate": 4.591392759500777e-06, + "loss": 0.0051, + "step": 44778 + }, + { + "epoch": 13.83, + "learning_rate": 4.590972110741061e-06, + "loss": 0.0052, + "step": 44779 + }, + { + "epoch": 13.83, + "learning_rate": 4.5905514755103145e-06, + "loss": 0.006, + "step": 44780 + }, + { + "epoch": 13.83, + "learning_rate": 4.590130853809586e-06, + "loss": 0.0063, + "step": 44781 + }, + { + "epoch": 13.83, + "learning_rate": 4.5897102456399225e-06, + "loss": 0.0059, + "step": 44782 + }, + { + "epoch": 13.83, + "learning_rate": 4.589289651002383e-06, + "loss": 0.0049, + "step": 44783 + }, + { + "epoch": 13.83, + "learning_rate": 4.588869069898016e-06, + "loss": 0.0077, + "step": 44784 + }, + { + "epoch": 13.83, + "learning_rate": 4.588448502327875e-06, + "loss": 0.0044, + "step": 44785 + }, + { + "epoch": 13.83, + "learning_rate": 4.588027948293013e-06, + "loss": 0.0038, + "step": 44786 + }, + { + "epoch": 13.83, + "learning_rate": 4.5876074077944765e-06, + "loss": 0.0046, + "step": 44787 + }, + { + "epoch": 13.83, + "learning_rate": 4.587186880833321e-06, + "loss": 0.0054, + "step": 44788 + }, + { + "epoch": 13.83, + "learning_rate": 4.586766367410598e-06, + "loss": 0.0072, + "step": 44789 + }, + { + "epoch": 13.83, + "learning_rate": 4.586345867527363e-06, + "loss": 0.0045, + "step": 44790 + }, + { + "epoch": 13.83, + "learning_rate": 4.585925381184666e-06, + "loss": 0.0066, + "step": 44791 + }, + { + "epoch": 13.83, + "learning_rate": 4.585504908383553e-06, + "loss": 0.005, + "step": 44792 + }, + { + "epoch": 13.83, + "learning_rate": 4.5850844491250815e-06, + "loss": 0.0061, + "step": 44793 + }, + { + "epoch": 13.83, + "learning_rate": 4.584664003410299e-06, + "loss": 0.0058, + "step": 44794 + }, + { + "epoch": 13.83, + "learning_rate": 4.584243571240263e-06, + "loss": 0.0049, + "step": 44795 + }, + { + "epoch": 13.83, + "learning_rate": 4.583823152616022e-06, + "loss": 0.0056, + "step": 44796 + }, + { + "epoch": 13.83, + "learning_rate": 4.583402747538623e-06, + "loss": 0.0049, + "step": 44797 + }, + { + "epoch": 13.83, + "learning_rate": 4.5829823560091225e-06, + "loss": 0.0044, + "step": 44798 + }, + { + "epoch": 13.83, + "learning_rate": 4.582561978028574e-06, + "loss": 0.0064, + "step": 44799 + }, + { + "epoch": 13.84, + "learning_rate": 4.582141613598022e-06, + "loss": 0.0056, + "step": 44800 + }, + { + "epoch": 13.84, + "learning_rate": 4.581721262718527e-06, + "loss": 0.0044, + "step": 44801 + }, + { + "epoch": 13.84, + "learning_rate": 4.581300925391135e-06, + "loss": 0.0053, + "step": 44802 + }, + { + "epoch": 13.84, + "learning_rate": 4.580880601616893e-06, + "loss": 0.0059, + "step": 44803 + }, + { + "epoch": 13.84, + "learning_rate": 4.5804602913968575e-06, + "loss": 0.0047, + "step": 44804 + }, + { + "epoch": 13.84, + "learning_rate": 4.580039994732083e-06, + "loss": 0.0062, + "step": 44805 + }, + { + "epoch": 13.84, + "learning_rate": 4.579619711623617e-06, + "loss": 0.0041, + "step": 44806 + }, + { + "epoch": 13.84, + "learning_rate": 4.579199442072507e-06, + "loss": 0.0061, + "step": 44807 + }, + { + "epoch": 13.84, + "learning_rate": 4.5787791860798115e-06, + "loss": 0.0049, + "step": 44808 + }, + { + "epoch": 13.84, + "learning_rate": 4.578358943646575e-06, + "loss": 0.0048, + "step": 44809 + }, + { + "epoch": 13.84, + "learning_rate": 4.5779387147738504e-06, + "loss": 0.0061, + "step": 44810 + }, + { + "epoch": 13.84, + "learning_rate": 4.577518499462695e-06, + "loss": 0.0059, + "step": 44811 + }, + { + "epoch": 13.84, + "learning_rate": 4.5770982977141545e-06, + "loss": 0.006, + "step": 44812 + }, + { + "epoch": 13.84, + "learning_rate": 4.576678109529277e-06, + "loss": 0.0052, + "step": 44813 + }, + { + "epoch": 13.84, + "learning_rate": 4.5762579349091186e-06, + "loss": 0.0059, + "step": 44814 + }, + { + "epoch": 13.84, + "learning_rate": 4.5758377738547265e-06, + "loss": 0.0054, + "step": 44815 + }, + { + "epoch": 13.84, + "learning_rate": 4.575417626367155e-06, + "loss": 0.005, + "step": 44816 + }, + { + "epoch": 13.84, + "learning_rate": 4.574997492447456e-06, + "loss": 0.0046, + "step": 44817 + }, + { + "epoch": 13.84, + "learning_rate": 4.574577372096673e-06, + "loss": 0.0041, + "step": 44818 + }, + { + "epoch": 13.84, + "learning_rate": 4.574157265315861e-06, + "loss": 0.0053, + "step": 44819 + }, + { + "epoch": 13.84, + "learning_rate": 4.573737172106072e-06, + "loss": 0.0058, + "step": 44820 + }, + { + "epoch": 13.84, + "learning_rate": 4.573317092468359e-06, + "loss": 0.0058, + "step": 44821 + }, + { + "epoch": 13.84, + "learning_rate": 4.5728970264037695e-06, + "loss": 0.0057, + "step": 44822 + }, + { + "epoch": 13.84, + "learning_rate": 4.5724769739133515e-06, + "loss": 0.0055, + "step": 44823 + }, + { + "epoch": 13.84, + "learning_rate": 4.572056934998163e-06, + "loss": 0.0057, + "step": 44824 + }, + { + "epoch": 13.84, + "learning_rate": 4.571636909659245e-06, + "loss": 0.0053, + "step": 44825 + }, + { + "epoch": 13.84, + "learning_rate": 4.571216897897657e-06, + "loss": 0.0047, + "step": 44826 + }, + { + "epoch": 13.84, + "learning_rate": 4.570796899714446e-06, + "loss": 0.005, + "step": 44827 + }, + { + "epoch": 13.84, + "learning_rate": 4.570376915110658e-06, + "loss": 0.0045, + "step": 44828 + }, + { + "epoch": 13.84, + "learning_rate": 4.5699569440873485e-06, + "loss": 0.0048, + "step": 44829 + }, + { + "epoch": 13.84, + "learning_rate": 4.56953698664557e-06, + "loss": 0.0051, + "step": 44830 + }, + { + "epoch": 13.84, + "learning_rate": 4.5691170427863665e-06, + "loss": 0.0058, + "step": 44831 + }, + { + "epoch": 13.84, + "learning_rate": 4.568697112510794e-06, + "loss": 0.0068, + "step": 44832 + }, + { + "epoch": 13.85, + "learning_rate": 4.568277195819904e-06, + "loss": 0.0057, + "step": 44833 + }, + { + "epoch": 13.85, + "learning_rate": 4.567857292714737e-06, + "loss": 0.0042, + "step": 44834 + }, + { + "epoch": 13.85, + "learning_rate": 4.567437403196351e-06, + "loss": 0.0047, + "step": 44835 + }, + { + "epoch": 13.85, + "learning_rate": 4.567017527265798e-06, + "loss": 0.0048, + "step": 44836 + }, + { + "epoch": 13.85, + "learning_rate": 4.566597664924125e-06, + "loss": 0.006, + "step": 44837 + }, + { + "epoch": 13.85, + "learning_rate": 4.566177816172379e-06, + "loss": 0.0041, + "step": 44838 + }, + { + "epoch": 13.85, + "learning_rate": 4.565757981011617e-06, + "loss": 0.005, + "step": 44839 + }, + { + "epoch": 13.85, + "learning_rate": 4.5653381594428815e-06, + "loss": 0.0058, + "step": 44840 + }, + { + "epoch": 13.85, + "learning_rate": 4.564918351467227e-06, + "loss": 0.0049, + "step": 44841 + }, + { + "epoch": 13.85, + "learning_rate": 4.564498557085709e-06, + "loss": 0.0055, + "step": 44842 + }, + { + "epoch": 13.85, + "learning_rate": 4.564078776299365e-06, + "loss": 0.006, + "step": 44843 + }, + { + "epoch": 13.85, + "learning_rate": 4.563659009109251e-06, + "loss": 0.0046, + "step": 44844 + }, + { + "epoch": 13.85, + "learning_rate": 4.563239255516422e-06, + "loss": 0.0052, + "step": 44845 + }, + { + "epoch": 13.85, + "learning_rate": 4.562819515521919e-06, + "loss": 0.0053, + "step": 44846 + }, + { + "epoch": 13.85, + "learning_rate": 4.5623997891268005e-06, + "loss": 0.0051, + "step": 44847 + }, + { + "epoch": 13.85, + "learning_rate": 4.561980076332111e-06, + "loss": 0.0053, + "step": 44848 + }, + { + "epoch": 13.85, + "learning_rate": 4.5615603771388976e-06, + "loss": 0.0044, + "step": 44849 + }, + { + "epoch": 13.85, + "learning_rate": 4.561140691548214e-06, + "loss": 0.0051, + "step": 44850 + }, + { + "epoch": 13.85, + "learning_rate": 4.560721019561111e-06, + "loss": 0.0043, + "step": 44851 + }, + { + "epoch": 13.85, + "learning_rate": 4.56030136117864e-06, + "loss": 0.0048, + "step": 44852 + }, + { + "epoch": 13.85, + "learning_rate": 4.559881716401843e-06, + "loss": 0.0047, + "step": 44853 + }, + { + "epoch": 13.85, + "learning_rate": 4.5594620852317725e-06, + "loss": 0.0051, + "step": 44854 + }, + { + "epoch": 13.85, + "learning_rate": 4.5590424676694846e-06, + "loss": 0.0044, + "step": 44855 + }, + { + "epoch": 13.85, + "learning_rate": 4.55862286371602e-06, + "loss": 0.0038, + "step": 44856 + }, + { + "epoch": 13.85, + "learning_rate": 4.558203273372435e-06, + "loss": 0.0053, + "step": 44857 + }, + { + "epoch": 13.85, + "learning_rate": 4.557783696639777e-06, + "loss": 0.0055, + "step": 44858 + }, + { + "epoch": 13.85, + "learning_rate": 4.55736413351909e-06, + "loss": 0.0047, + "step": 44859 + }, + { + "epoch": 13.85, + "learning_rate": 4.556944584011429e-06, + "loss": 0.005, + "step": 44860 + }, + { + "epoch": 13.85, + "learning_rate": 4.556525048117846e-06, + "loss": 0.0053, + "step": 44861 + }, + { + "epoch": 13.85, + "learning_rate": 4.556105525839386e-06, + "loss": 0.0055, + "step": 44862 + }, + { + "epoch": 13.85, + "learning_rate": 4.555686017177096e-06, + "loss": 0.0042, + "step": 44863 + }, + { + "epoch": 13.85, + "learning_rate": 4.555266522132031e-06, + "loss": 0.0049, + "step": 44864 + }, + { + "epoch": 13.86, + "learning_rate": 4.554847040705233e-06, + "loss": 0.0047, + "step": 44865 + }, + { + "epoch": 13.86, + "learning_rate": 4.554427572897758e-06, + "loss": 0.0052, + "step": 44866 + }, + { + "epoch": 13.86, + "learning_rate": 4.5540081187106555e-06, + "loss": 0.0043, + "step": 44867 + }, + { + "epoch": 13.86, + "learning_rate": 4.553588678144972e-06, + "loss": 0.0049, + "step": 44868 + }, + { + "epoch": 13.86, + "learning_rate": 4.553169251201753e-06, + "loss": 0.005, + "step": 44869 + }, + { + "epoch": 13.86, + "learning_rate": 4.552749837882054e-06, + "loss": 0.0043, + "step": 44870 + }, + { + "epoch": 13.86, + "learning_rate": 4.552330438186919e-06, + "loss": 0.005, + "step": 44871 + }, + { + "epoch": 13.86, + "learning_rate": 4.5519110521174024e-06, + "loss": 0.0046, + "step": 44872 + }, + { + "epoch": 13.86, + "learning_rate": 4.551491679674549e-06, + "loss": 0.0059, + "step": 44873 + }, + { + "epoch": 13.86, + "learning_rate": 4.5510723208594055e-06, + "loss": 0.0054, + "step": 44874 + }, + { + "epoch": 13.86, + "learning_rate": 4.550652975673024e-06, + "loss": 0.005, + "step": 44875 + }, + { + "epoch": 13.86, + "learning_rate": 4.5502336441164574e-06, + "loss": 0.0055, + "step": 44876 + }, + { + "epoch": 13.86, + "learning_rate": 4.549814326190746e-06, + "loss": 0.0066, + "step": 44877 + }, + { + "epoch": 13.86, + "learning_rate": 4.549395021896947e-06, + "loss": 0.0064, + "step": 44878 + }, + { + "epoch": 13.86, + "learning_rate": 4.548975731236106e-06, + "loss": 0.0054, + "step": 44879 + }, + { + "epoch": 13.86, + "learning_rate": 4.548556454209266e-06, + "loss": 0.0059, + "step": 44880 + }, + { + "epoch": 13.86, + "learning_rate": 4.548137190817481e-06, + "loss": 0.0056, + "step": 44881 + }, + { + "epoch": 13.86, + "learning_rate": 4.547717941061803e-06, + "loss": 0.0059, + "step": 44882 + }, + { + "epoch": 13.86, + "learning_rate": 4.547298704943277e-06, + "loss": 0.0048, + "step": 44883 + }, + { + "epoch": 13.86, + "learning_rate": 4.546879482462947e-06, + "loss": 0.005, + "step": 44884 + }, + { + "epoch": 13.86, + "learning_rate": 4.546460273621867e-06, + "loss": 0.0054, + "step": 44885 + }, + { + "epoch": 13.86, + "learning_rate": 4.5460410784210875e-06, + "loss": 0.0059, + "step": 44886 + }, + { + "epoch": 13.86, + "learning_rate": 4.54562189686165e-06, + "loss": 0.0061, + "step": 44887 + }, + { + "epoch": 13.86, + "learning_rate": 4.545202728944612e-06, + "loss": 0.005, + "step": 44888 + }, + { + "epoch": 13.86, + "learning_rate": 4.544783574671017e-06, + "loss": 0.0047, + "step": 44889 + }, + { + "epoch": 13.86, + "learning_rate": 4.544364434041908e-06, + "loss": 0.0043, + "step": 44890 + }, + { + "epoch": 13.86, + "learning_rate": 4.543945307058339e-06, + "loss": 0.0054, + "step": 44891 + }, + { + "epoch": 13.86, + "learning_rate": 4.543526193721362e-06, + "loss": 0.004, + "step": 44892 + }, + { + "epoch": 13.86, + "learning_rate": 4.543107094032021e-06, + "loss": 0.0052, + "step": 44893 + }, + { + "epoch": 13.86, + "learning_rate": 4.5426880079913605e-06, + "loss": 0.006, + "step": 44894 + }, + { + "epoch": 13.86, + "learning_rate": 4.5422689356004364e-06, + "loss": 0.0047, + "step": 44895 + }, + { + "epoch": 13.86, + "learning_rate": 4.54184987686029e-06, + "loss": 0.0067, + "step": 44896 + }, + { + "epoch": 13.87, + "learning_rate": 4.541430831771972e-06, + "loss": 0.0051, + "step": 44897 + }, + { + "epoch": 13.87, + "learning_rate": 4.541011800336535e-06, + "loss": 0.0051, + "step": 44898 + }, + { + "epoch": 13.87, + "learning_rate": 4.540592782555023e-06, + "loss": 0.0055, + "step": 44899 + }, + { + "epoch": 13.87, + "learning_rate": 4.5401737784284815e-06, + "loss": 0.0042, + "step": 44900 + }, + { + "epoch": 13.87, + "learning_rate": 4.539754787957964e-06, + "loss": 0.0063, + "step": 44901 + }, + { + "epoch": 13.87, + "learning_rate": 4.539335811144512e-06, + "loss": 0.0045, + "step": 44902 + }, + { + "epoch": 13.87, + "learning_rate": 4.538916847989181e-06, + "loss": 0.0057, + "step": 44903 + }, + { + "epoch": 13.87, + "learning_rate": 4.538497898493015e-06, + "loss": 0.0067, + "step": 44904 + }, + { + "epoch": 13.87, + "learning_rate": 4.538078962657057e-06, + "loss": 0.0066, + "step": 44905 + }, + { + "epoch": 13.87, + "learning_rate": 4.537660040482361e-06, + "loss": 0.0057, + "step": 44906 + }, + { + "epoch": 13.87, + "learning_rate": 4.537241131969977e-06, + "loss": 0.006, + "step": 44907 + }, + { + "epoch": 13.87, + "learning_rate": 4.536822237120946e-06, + "loss": 0.0058, + "step": 44908 + }, + { + "epoch": 13.87, + "learning_rate": 4.536403355936322e-06, + "loss": 0.0043, + "step": 44909 + }, + { + "epoch": 13.87, + "learning_rate": 4.53598448841715e-06, + "loss": 0.0045, + "step": 44910 + }, + { + "epoch": 13.87, + "learning_rate": 4.535565634564473e-06, + "loss": 0.0061, + "step": 44911 + }, + { + "epoch": 13.87, + "learning_rate": 4.535146794379344e-06, + "loss": 0.0051, + "step": 44912 + }, + { + "epoch": 13.87, + "learning_rate": 4.534727967862812e-06, + "loss": 0.0049, + "step": 44913 + }, + { + "epoch": 13.87, + "learning_rate": 4.534309155015924e-06, + "loss": 0.0066, + "step": 44914 + }, + { + "epoch": 13.87, + "learning_rate": 4.533890355839721e-06, + "loss": 0.0048, + "step": 44915 + }, + { + "epoch": 13.87, + "learning_rate": 4.533471570335258e-06, + "loss": 0.0039, + "step": 44916 + }, + { + "epoch": 13.87, + "learning_rate": 4.533052798503576e-06, + "loss": 0.005, + "step": 44917 + }, + { + "epoch": 13.87, + "learning_rate": 4.532634040345728e-06, + "loss": 0.0062, + "step": 44918 + }, + { + "epoch": 13.87, + "learning_rate": 4.532215295862762e-06, + "loss": 0.004, + "step": 44919 + }, + { + "epoch": 13.87, + "learning_rate": 4.531796565055723e-06, + "loss": 0.0056, + "step": 44920 + }, + { + "epoch": 13.87, + "learning_rate": 4.531377847925653e-06, + "loss": 0.0052, + "step": 44921 + }, + { + "epoch": 13.87, + "learning_rate": 4.530959144473607e-06, + "loss": 0.0047, + "step": 44922 + }, + { + "epoch": 13.87, + "learning_rate": 4.530540454700631e-06, + "loss": 0.0059, + "step": 44923 + }, + { + "epoch": 13.87, + "learning_rate": 4.5301217786077725e-06, + "loss": 0.0066, + "step": 44924 + }, + { + "epoch": 13.87, + "learning_rate": 4.529703116196073e-06, + "loss": 0.005, + "step": 44925 + }, + { + "epoch": 13.87, + "learning_rate": 4.529284467466587e-06, + "loss": 0.005, + "step": 44926 + }, + { + "epoch": 13.87, + "learning_rate": 4.528865832420355e-06, + "loss": 0.0061, + "step": 44927 + }, + { + "epoch": 13.87, + "learning_rate": 4.528447211058427e-06, + "loss": 0.006, + "step": 44928 + }, + { + "epoch": 13.87, + "learning_rate": 4.5280286033818545e-06, + "loss": 0.0054, + "step": 44929 + }, + { + "epoch": 13.88, + "learning_rate": 4.52761000939168e-06, + "loss": 0.0049, + "step": 44930 + }, + { + "epoch": 13.88, + "learning_rate": 4.5271914290889475e-06, + "loss": 0.0057, + "step": 44931 + }, + { + "epoch": 13.88, + "learning_rate": 4.5267728624747125e-06, + "loss": 0.0047, + "step": 44932 + }, + { + "epoch": 13.88, + "learning_rate": 4.52635430955001e-06, + "loss": 0.0058, + "step": 44933 + }, + { + "epoch": 13.88, + "learning_rate": 4.5259357703159e-06, + "loss": 0.0082, + "step": 44934 + }, + { + "epoch": 13.88, + "learning_rate": 4.525517244773423e-06, + "loss": 0.0044, + "step": 44935 + }, + { + "epoch": 13.88, + "learning_rate": 4.525098732923622e-06, + "loss": 0.0049, + "step": 44936 + }, + { + "epoch": 13.88, + "learning_rate": 4.524680234767547e-06, + "loss": 0.004, + "step": 44937 + }, + { + "epoch": 13.88, + "learning_rate": 4.524261750306249e-06, + "loss": 0.005, + "step": 44938 + }, + { + "epoch": 13.88, + "learning_rate": 4.523843279540767e-06, + "loss": 0.004, + "step": 44939 + }, + { + "epoch": 13.88, + "learning_rate": 4.523424822472157e-06, + "loss": 0.004, + "step": 44940 + }, + { + "epoch": 13.88, + "learning_rate": 4.5230063791014586e-06, + "loss": 0.0049, + "step": 44941 + }, + { + "epoch": 13.88, + "learning_rate": 4.5225879494297175e-06, + "loss": 0.0042, + "step": 44942 + }, + { + "epoch": 13.88, + "learning_rate": 4.522169533457983e-06, + "loss": 0.0064, + "step": 44943 + }, + { + "epoch": 13.88, + "learning_rate": 4.521751131187306e-06, + "loss": 0.0049, + "step": 44944 + }, + { + "epoch": 13.88, + "learning_rate": 4.521332742618727e-06, + "loss": 0.0056, + "step": 44945 + }, + { + "epoch": 13.88, + "learning_rate": 4.5209143677532904e-06, + "loss": 0.0049, + "step": 44946 + }, + { + "epoch": 13.88, + "learning_rate": 4.520496006592051e-06, + "loss": 0.0045, + "step": 44947 + }, + { + "epoch": 13.88, + "learning_rate": 4.520077659136046e-06, + "loss": 0.0052, + "step": 44948 + }, + { + "epoch": 13.88, + "learning_rate": 4.5196593253863265e-06, + "loss": 0.0047, + "step": 44949 + }, + { + "epoch": 13.88, + "learning_rate": 4.519241005343943e-06, + "loss": 0.0046, + "step": 44950 + }, + { + "epoch": 13.88, + "learning_rate": 4.5188226990099375e-06, + "loss": 0.0038, + "step": 44951 + }, + { + "epoch": 13.88, + "learning_rate": 4.518404406385351e-06, + "loss": 0.0054, + "step": 44952 + }, + { + "epoch": 13.88, + "learning_rate": 4.517986127471236e-06, + "loss": 0.0055, + "step": 44953 + }, + { + "epoch": 13.88, + "learning_rate": 4.51756786226864e-06, + "loss": 0.0045, + "step": 44954 + }, + { + "epoch": 13.88, + "learning_rate": 4.517149610778608e-06, + "loss": 0.0049, + "step": 44955 + }, + { + "epoch": 13.88, + "learning_rate": 4.51673137300218e-06, + "loss": 0.0053, + "step": 44956 + }, + { + "epoch": 13.88, + "learning_rate": 4.5163131489404125e-06, + "loss": 0.0056, + "step": 44957 + }, + { + "epoch": 13.88, + "learning_rate": 4.5158949385943405e-06, + "loss": 0.0045, + "step": 44958 + }, + { + "epoch": 13.88, + "learning_rate": 4.515476741965016e-06, + "loss": 0.0059, + "step": 44959 + }, + { + "epoch": 13.88, + "learning_rate": 4.515058559053488e-06, + "loss": 0.0051, + "step": 44960 + }, + { + "epoch": 13.88, + "learning_rate": 4.5146403898608e-06, + "loss": 0.0069, + "step": 44961 + }, + { + "epoch": 13.89, + "learning_rate": 4.514222234387992e-06, + "loss": 0.0064, + "step": 44962 + }, + { + "epoch": 13.89, + "learning_rate": 4.513804092636118e-06, + "loss": 0.0057, + "step": 44963 + }, + { + "epoch": 13.89, + "learning_rate": 4.513385964606218e-06, + "loss": 0.0057, + "step": 44964 + }, + { + "epoch": 13.89, + "learning_rate": 4.512967850299344e-06, + "loss": 0.0046, + "step": 44965 + }, + { + "epoch": 13.89, + "learning_rate": 4.5125497497165386e-06, + "loss": 0.0051, + "step": 44966 + }, + { + "epoch": 13.89, + "learning_rate": 4.512131662858842e-06, + "loss": 0.0047, + "step": 44967 + }, + { + "epoch": 13.89, + "learning_rate": 4.511713589727305e-06, + "loss": 0.0059, + "step": 44968 + }, + { + "epoch": 13.89, + "learning_rate": 4.511295530322979e-06, + "loss": 0.0061, + "step": 44969 + }, + { + "epoch": 13.89, + "learning_rate": 4.510877484646898e-06, + "loss": 0.0043, + "step": 44970 + }, + { + "epoch": 13.89, + "learning_rate": 4.510459452700119e-06, + "loss": 0.0052, + "step": 44971 + }, + { + "epoch": 13.89, + "learning_rate": 4.510041434483681e-06, + "loss": 0.0061, + "step": 44972 + }, + { + "epoch": 13.89, + "learning_rate": 4.509623429998628e-06, + "loss": 0.0056, + "step": 44973 + }, + { + "epoch": 13.89, + "learning_rate": 4.509205439246008e-06, + "loss": 0.0051, + "step": 44974 + }, + { + "epoch": 13.89, + "learning_rate": 4.5087874622268705e-06, + "loss": 0.0059, + "step": 44975 + }, + { + "epoch": 13.89, + "learning_rate": 4.5083694989422555e-06, + "loss": 0.005, + "step": 44976 + }, + { + "epoch": 13.89, + "learning_rate": 4.507951549393208e-06, + "loss": 0.0051, + "step": 44977 + }, + { + "epoch": 13.89, + "learning_rate": 4.507533613580778e-06, + "loss": 0.0048, + "step": 44978 + }, + { + "epoch": 13.89, + "learning_rate": 4.5071156915060055e-06, + "loss": 0.0048, + "step": 44979 + }, + { + "epoch": 13.89, + "learning_rate": 4.506697783169937e-06, + "loss": 0.0053, + "step": 44980 + }, + { + "epoch": 13.89, + "learning_rate": 4.506279888573628e-06, + "loss": 0.0064, + "step": 44981 + }, + { + "epoch": 13.89, + "learning_rate": 4.505862007718107e-06, + "loss": 0.0056, + "step": 44982 + }, + { + "epoch": 13.89, + "learning_rate": 4.505444140604428e-06, + "loss": 0.0051, + "step": 44983 + }, + { + "epoch": 13.89, + "learning_rate": 4.505026287233635e-06, + "loss": 0.0048, + "step": 44984 + }, + { + "epoch": 13.89, + "learning_rate": 4.504608447606776e-06, + "loss": 0.0043, + "step": 44985 + }, + { + "epoch": 13.89, + "learning_rate": 4.504190621724896e-06, + "loss": 0.0053, + "step": 44986 + }, + { + "epoch": 13.89, + "learning_rate": 4.503772809589031e-06, + "loss": 0.0051, + "step": 44987 + }, + { + "epoch": 13.89, + "learning_rate": 4.503355011200238e-06, + "loss": 0.0043, + "step": 44988 + }, + { + "epoch": 13.89, + "learning_rate": 4.502937226559553e-06, + "loss": 0.0047, + "step": 44989 + }, + { + "epoch": 13.89, + "learning_rate": 4.502519455668024e-06, + "loss": 0.0062, + "step": 44990 + }, + { + "epoch": 13.89, + "learning_rate": 4.502101698526704e-06, + "loss": 0.0056, + "step": 44991 + }, + { + "epoch": 13.89, + "learning_rate": 4.501683955136623e-06, + "loss": 0.0052, + "step": 44992 + }, + { + "epoch": 13.89, + "learning_rate": 4.501266225498834e-06, + "loss": 0.0047, + "step": 44993 + }, + { + "epoch": 13.89, + "learning_rate": 4.500848509614384e-06, + "loss": 0.0051, + "step": 44994 + }, + { + "epoch": 13.9, + "learning_rate": 4.500430807484312e-06, + "loss": 0.0061, + "step": 44995 + }, + { + "epoch": 13.9, + "learning_rate": 4.500013119109669e-06, + "loss": 0.0055, + "step": 44996 + }, + { + "epoch": 13.9, + "learning_rate": 4.499595444491496e-06, + "loss": 0.005, + "step": 44997 + }, + { + "epoch": 13.9, + "learning_rate": 4.499177783630833e-06, + "loss": 0.0041, + "step": 44998 + }, + { + "epoch": 13.9, + "learning_rate": 4.498760136528732e-06, + "loss": 0.005, + "step": 44999 + }, + { + "epoch": 13.9, + "learning_rate": 4.4983425031862375e-06, + "loss": 0.0066, + "step": 45000 + }, + { + "epoch": 13.9, + "learning_rate": 4.497924883604392e-06, + "loss": 0.0055, + "step": 45001 + }, + { + "epoch": 13.9, + "learning_rate": 4.497507277784236e-06, + "loss": 0.006, + "step": 45002 + }, + { + "epoch": 13.9, + "learning_rate": 4.497089685726823e-06, + "loss": 0.0057, + "step": 45003 + }, + { + "epoch": 13.9, + "learning_rate": 4.496672107433187e-06, + "loss": 0.0056, + "step": 45004 + }, + { + "epoch": 13.9, + "learning_rate": 4.496254542904379e-06, + "loss": 0.0055, + "step": 45005 + }, + { + "epoch": 13.9, + "learning_rate": 4.495836992141446e-06, + "loss": 0.0053, + "step": 45006 + }, + { + "epoch": 13.9, + "learning_rate": 4.495419455145428e-06, + "loss": 0.0097, + "step": 45007 + }, + { + "epoch": 13.9, + "learning_rate": 4.495001931917367e-06, + "loss": 0.0051, + "step": 45008 + }, + { + "epoch": 13.9, + "learning_rate": 4.494584422458312e-06, + "loss": 0.0057, + "step": 45009 + }, + { + "epoch": 13.9, + "learning_rate": 4.494166926769303e-06, + "loss": 0.0047, + "step": 45010 + }, + { + "epoch": 13.9, + "learning_rate": 4.493749444851391e-06, + "loss": 0.007, + "step": 45011 + }, + { + "epoch": 13.9, + "learning_rate": 4.493331976705615e-06, + "loss": 0.0054, + "step": 45012 + }, + { + "epoch": 13.9, + "learning_rate": 4.492914522333016e-06, + "loss": 0.0063, + "step": 45013 + }, + { + "epoch": 13.9, + "learning_rate": 4.492497081734643e-06, + "loss": 0.0044, + "step": 45014 + }, + { + "epoch": 13.9, + "learning_rate": 4.492079654911543e-06, + "loss": 0.0053, + "step": 45015 + }, + { + "epoch": 13.9, + "learning_rate": 4.491662241864752e-06, + "loss": 0.0066, + "step": 45016 + }, + { + "epoch": 13.9, + "learning_rate": 4.491244842595324e-06, + "loss": 0.004, + "step": 45017 + }, + { + "epoch": 13.9, + "learning_rate": 4.490827457104292e-06, + "loss": 0.0049, + "step": 45018 + }, + { + "epoch": 13.9, + "learning_rate": 4.490410085392709e-06, + "loss": 0.005, + "step": 45019 + }, + { + "epoch": 13.9, + "learning_rate": 4.4899927274616115e-06, + "loss": 0.0056, + "step": 45020 + }, + { + "epoch": 13.9, + "learning_rate": 4.4895753833120515e-06, + "loss": 0.0081, + "step": 45021 + }, + { + "epoch": 13.9, + "learning_rate": 4.4891580529450686e-06, + "loss": 0.0072, + "step": 45022 + }, + { + "epoch": 13.9, + "learning_rate": 4.488740736361702e-06, + "loss": 0.007, + "step": 45023 + }, + { + "epoch": 13.9, + "learning_rate": 4.488323433563001e-06, + "loss": 0.0047, + "step": 45024 + }, + { + "epoch": 13.9, + "learning_rate": 4.487906144550012e-06, + "loss": 0.0057, + "step": 45025 + }, + { + "epoch": 13.9, + "learning_rate": 4.487488869323771e-06, + "loss": 0.0058, + "step": 45026 + }, + { + "epoch": 13.91, + "learning_rate": 4.48707160788533e-06, + "loss": 0.0044, + "step": 45027 + }, + { + "epoch": 13.91, + "learning_rate": 4.486654360235727e-06, + "loss": 0.0043, + "step": 45028 + }, + { + "epoch": 13.91, + "learning_rate": 4.486237126376004e-06, + "loss": 0.0052, + "step": 45029 + }, + { + "epoch": 13.91, + "learning_rate": 4.485819906307207e-06, + "loss": 0.0051, + "step": 45030 + }, + { + "epoch": 13.91, + "learning_rate": 4.485402700030384e-06, + "loss": 0.0053, + "step": 45031 + }, + { + "epoch": 13.91, + "learning_rate": 4.484985507546576e-06, + "loss": 0.0045, + "step": 45032 + }, + { + "epoch": 13.91, + "learning_rate": 4.484568328856821e-06, + "loss": 0.0058, + "step": 45033 + }, + { + "epoch": 13.91, + "learning_rate": 4.4841511639621695e-06, + "loss": 0.0054, + "step": 45034 + }, + { + "epoch": 13.91, + "learning_rate": 4.483734012863659e-06, + "loss": 0.0049, + "step": 45035 + }, + { + "epoch": 13.91, + "learning_rate": 4.483316875562336e-06, + "loss": 0.0065, + "step": 45036 + }, + { + "epoch": 13.91, + "learning_rate": 4.482899752059246e-06, + "loss": 0.0055, + "step": 45037 + }, + { + "epoch": 13.91, + "learning_rate": 4.482482642355431e-06, + "loss": 0.0055, + "step": 45038 + }, + { + "epoch": 13.91, + "learning_rate": 4.482065546451929e-06, + "loss": 0.005, + "step": 45039 + }, + { + "epoch": 13.91, + "learning_rate": 4.481648464349792e-06, + "loss": 0.0053, + "step": 45040 + }, + { + "epoch": 13.91, + "learning_rate": 4.481231396050054e-06, + "loss": 0.0069, + "step": 45041 + }, + { + "epoch": 13.91, + "learning_rate": 4.480814341553768e-06, + "loss": 0.0082, + "step": 45042 + }, + { + "epoch": 13.91, + "learning_rate": 4.480397300861971e-06, + "loss": 0.0055, + "step": 45043 + }, + { + "epoch": 13.91, + "learning_rate": 4.4799802739757025e-06, + "loss": 0.0055, + "step": 45044 + }, + { + "epoch": 13.91, + "learning_rate": 4.479563260896011e-06, + "loss": 0.0056, + "step": 45045 + }, + { + "epoch": 13.91, + "learning_rate": 4.479146261623943e-06, + "loss": 0.0052, + "step": 45046 + }, + { + "epoch": 13.91, + "learning_rate": 4.478729276160533e-06, + "loss": 0.0048, + "step": 45047 + }, + { + "epoch": 13.91, + "learning_rate": 4.478312304506831e-06, + "loss": 0.005, + "step": 45048 + }, + { + "epoch": 13.91, + "learning_rate": 4.4778953466638746e-06, + "loss": 0.0049, + "step": 45049 + }, + { + "epoch": 13.91, + "learning_rate": 4.4774784026327126e-06, + "loss": 0.0047, + "step": 45050 + }, + { + "epoch": 13.91, + "learning_rate": 4.477061472414379e-06, + "loss": 0.005, + "step": 45051 + }, + { + "epoch": 13.91, + "learning_rate": 4.476644556009927e-06, + "loss": 0.0054, + "step": 45052 + }, + { + "epoch": 13.91, + "learning_rate": 4.476227653420395e-06, + "loss": 0.005, + "step": 45053 + }, + { + "epoch": 13.91, + "learning_rate": 4.475810764646821e-06, + "loss": 0.0056, + "step": 45054 + }, + { + "epoch": 13.91, + "learning_rate": 4.47539388969025e-06, + "loss": 0.0057, + "step": 45055 + }, + { + "epoch": 13.91, + "learning_rate": 4.474977028551732e-06, + "loss": 0.0048, + "step": 45056 + }, + { + "epoch": 13.91, + "learning_rate": 4.4745601812323e-06, + "loss": 0.0045, + "step": 45057 + }, + { + "epoch": 13.91, + "learning_rate": 4.474143347733005e-06, + "loss": 0.0073, + "step": 45058 + }, + { + "epoch": 13.92, + "learning_rate": 4.473726528054885e-06, + "loss": 0.0062, + "step": 45059 + }, + { + "epoch": 13.92, + "learning_rate": 4.473309722198979e-06, + "loss": 0.0044, + "step": 45060 + }, + { + "epoch": 13.92, + "learning_rate": 4.472892930166334e-06, + "loss": 0.0047, + "step": 45061 + }, + { + "epoch": 13.92, + "learning_rate": 4.4724761519579955e-06, + "loss": 0.0049, + "step": 45062 + }, + { + "epoch": 13.92, + "learning_rate": 4.472059387575002e-06, + "loss": 0.0053, + "step": 45063 + }, + { + "epoch": 13.92, + "learning_rate": 4.471642637018392e-06, + "loss": 0.0062, + "step": 45064 + }, + { + "epoch": 13.92, + "learning_rate": 4.471225900289215e-06, + "loss": 0.0047, + "step": 45065 + }, + { + "epoch": 13.92, + "learning_rate": 4.470809177388509e-06, + "loss": 0.0057, + "step": 45066 + }, + { + "epoch": 13.92, + "learning_rate": 4.470392468317316e-06, + "loss": 0.0063, + "step": 45067 + }, + { + "epoch": 13.92, + "learning_rate": 4.469975773076685e-06, + "loss": 0.0057, + "step": 45068 + }, + { + "epoch": 13.92, + "learning_rate": 4.469559091667652e-06, + "loss": 0.0056, + "step": 45069 + }, + { + "epoch": 13.92, + "learning_rate": 4.4691424240912575e-06, + "loss": 0.0048, + "step": 45070 + }, + { + "epoch": 13.92, + "learning_rate": 4.46872577034855e-06, + "loss": 0.0059, + "step": 45071 + }, + { + "epoch": 13.92, + "learning_rate": 4.468309130440565e-06, + "loss": 0.0056, + "step": 45072 + }, + { + "epoch": 13.92, + "learning_rate": 4.46789250436835e-06, + "loss": 0.0069, + "step": 45073 + }, + { + "epoch": 13.92, + "learning_rate": 4.4674758921329454e-06, + "loss": 0.0056, + "step": 45074 + }, + { + "epoch": 13.92, + "learning_rate": 4.467059293735389e-06, + "loss": 0.0053, + "step": 45075 + }, + { + "epoch": 13.92, + "learning_rate": 4.466642709176727e-06, + "loss": 0.0057, + "step": 45076 + }, + { + "epoch": 13.92, + "learning_rate": 4.4662261384580045e-06, + "loss": 0.0048, + "step": 45077 + }, + { + "epoch": 13.92, + "learning_rate": 4.465809581580256e-06, + "loss": 0.0046, + "step": 45078 + }, + { + "epoch": 13.92, + "learning_rate": 4.465393038544531e-06, + "loss": 0.0058, + "step": 45079 + }, + { + "epoch": 13.92, + "learning_rate": 4.4649765093518675e-06, + "loss": 0.0055, + "step": 45080 + }, + { + "epoch": 13.92, + "learning_rate": 4.4645599940033025e-06, + "loss": 0.0049, + "step": 45081 + }, + { + "epoch": 13.92, + "learning_rate": 4.464143492499882e-06, + "loss": 0.0044, + "step": 45082 + }, + { + "epoch": 13.92, + "learning_rate": 4.463727004842654e-06, + "loss": 0.0056, + "step": 45083 + }, + { + "epoch": 13.92, + "learning_rate": 4.463310531032654e-06, + "loss": 0.0045, + "step": 45084 + }, + { + "epoch": 13.92, + "learning_rate": 4.46289407107092e-06, + "loss": 0.0053, + "step": 45085 + }, + { + "epoch": 13.92, + "learning_rate": 4.462477624958498e-06, + "loss": 0.0042, + "step": 45086 + }, + { + "epoch": 13.92, + "learning_rate": 4.462061192696433e-06, + "loss": 0.0062, + "step": 45087 + }, + { + "epoch": 13.92, + "learning_rate": 4.461644774285759e-06, + "loss": 0.0054, + "step": 45088 + }, + { + "epoch": 13.92, + "learning_rate": 4.461228369727526e-06, + "loss": 0.0051, + "step": 45089 + }, + { + "epoch": 13.92, + "learning_rate": 4.460811979022771e-06, + "loss": 0.0058, + "step": 45090 + }, + { + "epoch": 13.92, + "learning_rate": 4.460395602172532e-06, + "loss": 0.0062, + "step": 45091 + }, + { + "epoch": 13.93, + "learning_rate": 4.459979239177853e-06, + "loss": 0.0056, + "step": 45092 + }, + { + "epoch": 13.93, + "learning_rate": 4.459562890039781e-06, + "loss": 0.0039, + "step": 45093 + }, + { + "epoch": 13.93, + "learning_rate": 4.459146554759353e-06, + "loss": 0.0051, + "step": 45094 + }, + { + "epoch": 13.93, + "learning_rate": 4.4587302333376045e-06, + "loss": 0.0048, + "step": 45095 + }, + { + "epoch": 13.93, + "learning_rate": 4.458313925775588e-06, + "loss": 0.0054, + "step": 45096 + }, + { + "epoch": 13.93, + "learning_rate": 4.457897632074335e-06, + "loss": 0.0045, + "step": 45097 + }, + { + "epoch": 13.93, + "learning_rate": 4.45748135223489e-06, + "loss": 0.0053, + "step": 45098 + }, + { + "epoch": 13.93, + "learning_rate": 4.457065086258303e-06, + "loss": 0.0047, + "step": 45099 + }, + { + "epoch": 13.93, + "learning_rate": 4.4566488341456e-06, + "loss": 0.0059, + "step": 45100 + }, + { + "epoch": 13.93, + "learning_rate": 4.456232595897829e-06, + "loss": 0.0064, + "step": 45101 + }, + { + "epoch": 13.93, + "learning_rate": 4.455816371516035e-06, + "loss": 0.0051, + "step": 45102 + }, + { + "epoch": 13.93, + "learning_rate": 4.455400161001252e-06, + "loss": 0.0064, + "step": 45103 + }, + { + "epoch": 13.93, + "learning_rate": 4.454983964354528e-06, + "loss": 0.0064, + "step": 45104 + }, + { + "epoch": 13.93, + "learning_rate": 4.454567781576901e-06, + "loss": 0.0041, + "step": 45105 + }, + { + "epoch": 13.93, + "learning_rate": 4.454151612669407e-06, + "loss": 0.0052, + "step": 45106 + }, + { + "epoch": 13.93, + "learning_rate": 4.4537354576330915e-06, + "loss": 0.0055, + "step": 45107 + }, + { + "epoch": 13.93, + "learning_rate": 4.453319316468999e-06, + "loss": 0.0047, + "step": 45108 + }, + { + "epoch": 13.93, + "learning_rate": 4.452903189178166e-06, + "loss": 0.0044, + "step": 45109 + }, + { + "epoch": 13.93, + "learning_rate": 4.452487075761631e-06, + "loss": 0.0049, + "step": 45110 + }, + { + "epoch": 13.93, + "learning_rate": 4.45207097622044e-06, + "loss": 0.0053, + "step": 45111 + }, + { + "epoch": 13.93, + "learning_rate": 4.451654890555629e-06, + "loss": 0.0048, + "step": 45112 + }, + { + "epoch": 13.93, + "learning_rate": 4.451238818768241e-06, + "loss": 0.0049, + "step": 45113 + }, + { + "epoch": 13.93, + "learning_rate": 4.45082276085932e-06, + "loss": 0.0057, + "step": 45114 + }, + { + "epoch": 13.93, + "learning_rate": 4.450406716829903e-06, + "loss": 0.0055, + "step": 45115 + }, + { + "epoch": 13.93, + "learning_rate": 4.449990686681028e-06, + "loss": 0.0059, + "step": 45116 + }, + { + "epoch": 13.93, + "learning_rate": 4.449574670413739e-06, + "loss": 0.006, + "step": 45117 + }, + { + "epoch": 13.93, + "learning_rate": 4.449158668029079e-06, + "loss": 0.0057, + "step": 45118 + }, + { + "epoch": 13.93, + "learning_rate": 4.448742679528085e-06, + "loss": 0.0062, + "step": 45119 + }, + { + "epoch": 13.93, + "learning_rate": 4.448326704911796e-06, + "loss": 0.0041, + "step": 45120 + }, + { + "epoch": 13.93, + "learning_rate": 4.447910744181258e-06, + "loss": 0.0049, + "step": 45121 + }, + { + "epoch": 13.93, + "learning_rate": 4.447494797337503e-06, + "loss": 0.0065, + "step": 45122 + }, + { + "epoch": 13.93, + "learning_rate": 4.447078864381576e-06, + "loss": 0.0038, + "step": 45123 + }, + { + "epoch": 13.94, + "learning_rate": 4.446662945314522e-06, + "loss": 0.0044, + "step": 45124 + }, + { + "epoch": 13.94, + "learning_rate": 4.446247040137377e-06, + "loss": 0.0042, + "step": 45125 + }, + { + "epoch": 13.94, + "learning_rate": 4.445831148851176e-06, + "loss": 0.0048, + "step": 45126 + }, + { + "epoch": 13.94, + "learning_rate": 4.44541527145697e-06, + "loss": 0.0048, + "step": 45127 + }, + { + "epoch": 13.94, + "learning_rate": 4.444999407955789e-06, + "loss": 0.0067, + "step": 45128 + }, + { + "epoch": 13.94, + "learning_rate": 4.444583558348681e-06, + "loss": 0.0049, + "step": 45129 + }, + { + "epoch": 13.94, + "learning_rate": 4.444167722636683e-06, + "loss": 0.0057, + "step": 45130 + }, + { + "epoch": 13.94, + "learning_rate": 4.443751900820832e-06, + "loss": 0.0047, + "step": 45131 + }, + { + "epoch": 13.94, + "learning_rate": 4.443336092902169e-06, + "loss": 0.0051, + "step": 45132 + }, + { + "epoch": 13.94, + "learning_rate": 4.442920298881741e-06, + "loss": 0.0048, + "step": 45133 + }, + { + "epoch": 13.94, + "learning_rate": 4.442504518760579e-06, + "loss": 0.005, + "step": 45134 + }, + { + "epoch": 13.94, + "learning_rate": 4.44208875253973e-06, + "loss": 0.0043, + "step": 45135 + }, + { + "epoch": 13.94, + "learning_rate": 4.441673000220232e-06, + "loss": 0.0045, + "step": 45136 + }, + { + "epoch": 13.94, + "learning_rate": 4.441257261803118e-06, + "loss": 0.0081, + "step": 45137 + }, + { + "epoch": 13.94, + "learning_rate": 4.4408415372894355e-06, + "loss": 0.0062, + "step": 45138 + }, + { + "epoch": 13.94, + "learning_rate": 4.440425826680224e-06, + "loss": 0.0043, + "step": 45139 + }, + { + "epoch": 13.94, + "learning_rate": 4.440010129976523e-06, + "loss": 0.0059, + "step": 45140 + }, + { + "epoch": 13.94, + "learning_rate": 4.4395944471793665e-06, + "loss": 0.0046, + "step": 45141 + }, + { + "epoch": 13.94, + "learning_rate": 4.439178778289802e-06, + "loss": 0.0053, + "step": 45142 + }, + { + "epoch": 13.94, + "learning_rate": 4.438763123308861e-06, + "loss": 0.0054, + "step": 45143 + }, + { + "epoch": 13.94, + "learning_rate": 4.43834748223759e-06, + "loss": 0.0048, + "step": 45144 + }, + { + "epoch": 13.94, + "learning_rate": 4.437931855077028e-06, + "loss": 0.0056, + "step": 45145 + }, + { + "epoch": 13.94, + "learning_rate": 4.437516241828214e-06, + "loss": 0.0061, + "step": 45146 + }, + { + "epoch": 13.94, + "learning_rate": 4.437100642492183e-06, + "loss": 0.0063, + "step": 45147 + }, + { + "epoch": 13.94, + "learning_rate": 4.436685057069977e-06, + "loss": 0.0062, + "step": 45148 + }, + { + "epoch": 13.94, + "learning_rate": 4.4362694855626395e-06, + "loss": 0.0048, + "step": 45149 + }, + { + "epoch": 13.94, + "learning_rate": 4.4358539279712076e-06, + "loss": 0.0057, + "step": 45150 + }, + { + "epoch": 13.94, + "learning_rate": 4.435438384296717e-06, + "loss": 0.0057, + "step": 45151 + }, + { + "epoch": 13.94, + "learning_rate": 4.435022854540212e-06, + "loss": 0.0057, + "step": 45152 + }, + { + "epoch": 13.94, + "learning_rate": 4.434607338702727e-06, + "loss": 0.0053, + "step": 45153 + }, + { + "epoch": 13.94, + "learning_rate": 4.434191836785304e-06, + "loss": 0.0051, + "step": 45154 + }, + { + "epoch": 13.94, + "learning_rate": 4.433776348788987e-06, + "loss": 0.0052, + "step": 45155 + }, + { + "epoch": 13.95, + "learning_rate": 4.433360874714809e-06, + "loss": 0.0047, + "step": 45156 + }, + { + "epoch": 13.95, + "learning_rate": 4.432945414563807e-06, + "loss": 0.0061, + "step": 45157 + }, + { + "epoch": 13.95, + "learning_rate": 4.432529968337029e-06, + "loss": 0.005, + "step": 45158 + }, + { + "epoch": 13.95, + "learning_rate": 4.432114536035505e-06, + "loss": 0.0051, + "step": 45159 + }, + { + "epoch": 13.95, + "learning_rate": 4.431699117660281e-06, + "loss": 0.0049, + "step": 45160 + }, + { + "epoch": 13.95, + "learning_rate": 4.4312837132123934e-06, + "loss": 0.0043, + "step": 45161 + }, + { + "epoch": 13.95, + "learning_rate": 4.4308683226928775e-06, + "loss": 0.0054, + "step": 45162 + }, + { + "epoch": 13.95, + "learning_rate": 4.430452946102776e-06, + "loss": 0.0052, + "step": 45163 + }, + { + "epoch": 13.95, + "learning_rate": 4.43003758344313e-06, + "loss": 0.0051, + "step": 45164 + }, + { + "epoch": 13.95, + "learning_rate": 4.429622234714973e-06, + "loss": 0.0055, + "step": 45165 + }, + { + "epoch": 13.95, + "learning_rate": 4.42920689991935e-06, + "loss": 0.0047, + "step": 45166 + }, + { + "epoch": 13.95, + "learning_rate": 4.428791579057297e-06, + "loss": 0.0049, + "step": 45167 + }, + { + "epoch": 13.95, + "learning_rate": 4.428376272129849e-06, + "loss": 0.0051, + "step": 45168 + }, + { + "epoch": 13.95, + "learning_rate": 4.4279609791380475e-06, + "loss": 0.0041, + "step": 45169 + }, + { + "epoch": 13.95, + "learning_rate": 4.427545700082934e-06, + "loss": 0.0062, + "step": 45170 + }, + { + "epoch": 13.95, + "learning_rate": 4.4271304349655485e-06, + "loss": 0.0045, + "step": 45171 + }, + { + "epoch": 13.95, + "learning_rate": 4.426715183786921e-06, + "loss": 0.0047, + "step": 45172 + }, + { + "epoch": 13.95, + "learning_rate": 4.426299946548098e-06, + "loss": 0.0053, + "step": 45173 + }, + { + "epoch": 13.95, + "learning_rate": 4.425884723250112e-06, + "loss": 0.0044, + "step": 45174 + }, + { + "epoch": 13.95, + "learning_rate": 4.425469513894006e-06, + "loss": 0.005, + "step": 45175 + }, + { + "epoch": 13.95, + "learning_rate": 4.4250543184808215e-06, + "loss": 0.006, + "step": 45176 + }, + { + "epoch": 13.95, + "learning_rate": 4.424639137011592e-06, + "loss": 0.0055, + "step": 45177 + }, + { + "epoch": 13.95, + "learning_rate": 4.424223969487353e-06, + "loss": 0.0062, + "step": 45178 + }, + { + "epoch": 13.95, + "learning_rate": 4.423808815909148e-06, + "loss": 0.0042, + "step": 45179 + }, + { + "epoch": 13.95, + "learning_rate": 4.423393676278016e-06, + "loss": 0.0048, + "step": 45180 + }, + { + "epoch": 13.95, + "learning_rate": 4.422978550594995e-06, + "loss": 0.0052, + "step": 45181 + }, + { + "epoch": 13.95, + "learning_rate": 4.422563438861119e-06, + "loss": 0.0056, + "step": 45182 + }, + { + "epoch": 13.95, + "learning_rate": 4.42214834107743e-06, + "loss": 0.0053, + "step": 45183 + }, + { + "epoch": 13.95, + "learning_rate": 4.421733257244963e-06, + "loss": 0.005, + "step": 45184 + }, + { + "epoch": 13.95, + "learning_rate": 4.421318187364759e-06, + "loss": 0.0051, + "step": 45185 + }, + { + "epoch": 13.95, + "learning_rate": 4.420903131437859e-06, + "loss": 0.0053, + "step": 45186 + }, + { + "epoch": 13.95, + "learning_rate": 4.420488089465298e-06, + "loss": 0.0052, + "step": 45187 + }, + { + "epoch": 13.95, + "learning_rate": 4.42007306144811e-06, + "loss": 0.0056, + "step": 45188 + }, + { + "epoch": 13.96, + "learning_rate": 4.419658047387341e-06, + "loss": 0.0043, + "step": 45189 + }, + { + "epoch": 13.96, + "learning_rate": 4.419243047284021e-06, + "loss": 0.0058, + "step": 45190 + }, + { + "epoch": 13.96, + "learning_rate": 4.418828061139196e-06, + "loss": 0.0051, + "step": 45191 + }, + { + "epoch": 13.96, + "learning_rate": 4.4184130889539005e-06, + "loss": 0.0051, + "step": 45192 + }, + { + "epoch": 13.96, + "learning_rate": 4.417998130729167e-06, + "loss": 0.0069, + "step": 45193 + }, + { + "epoch": 13.96, + "learning_rate": 4.417583186466039e-06, + "loss": 0.0055, + "step": 45194 + }, + { + "epoch": 13.96, + "learning_rate": 4.417168256165557e-06, + "loss": 0.0056, + "step": 45195 + }, + { + "epoch": 13.96, + "learning_rate": 4.416753339828752e-06, + "loss": 0.0065, + "step": 45196 + }, + { + "epoch": 13.96, + "learning_rate": 4.4163384374566685e-06, + "loss": 0.0054, + "step": 45197 + }, + { + "epoch": 13.96, + "learning_rate": 4.415923549050342e-06, + "loss": 0.0042, + "step": 45198 + }, + { + "epoch": 13.96, + "learning_rate": 4.415508674610804e-06, + "loss": 0.0046, + "step": 45199 + }, + { + "epoch": 13.96, + "learning_rate": 4.415093814139097e-06, + "loss": 0.0054, + "step": 45200 + }, + { + "epoch": 13.96, + "learning_rate": 4.414678967636265e-06, + "loss": 0.0053, + "step": 45201 + }, + { + "epoch": 13.96, + "learning_rate": 4.4142641351033374e-06, + "loss": 0.0061, + "step": 45202 + }, + { + "epoch": 13.96, + "learning_rate": 4.413849316541352e-06, + "loss": 0.0045, + "step": 45203 + }, + { + "epoch": 13.96, + "learning_rate": 4.413434511951351e-06, + "loss": 0.0057, + "step": 45204 + }, + { + "epoch": 13.96, + "learning_rate": 4.413019721334366e-06, + "loss": 0.005, + "step": 45205 + }, + { + "epoch": 13.96, + "learning_rate": 4.412604944691437e-06, + "loss": 0.0045, + "step": 45206 + }, + { + "epoch": 13.96, + "learning_rate": 4.41219018202361e-06, + "loss": 0.0057, + "step": 45207 + }, + { + "epoch": 13.96, + "learning_rate": 4.411775433331907e-06, + "loss": 0.0054, + "step": 45208 + }, + { + "epoch": 13.96, + "learning_rate": 4.411360698617373e-06, + "loss": 0.0044, + "step": 45209 + }, + { + "epoch": 13.96, + "learning_rate": 4.41094597788105e-06, + "loss": 0.0058, + "step": 45210 + }, + { + "epoch": 13.96, + "learning_rate": 4.410531271123964e-06, + "loss": 0.0049, + "step": 45211 + }, + { + "epoch": 13.96, + "learning_rate": 4.410116578347164e-06, + "loss": 0.0057, + "step": 45212 + }, + { + "epoch": 13.96, + "learning_rate": 4.409701899551679e-06, + "loss": 0.0058, + "step": 45213 + }, + { + "epoch": 13.96, + "learning_rate": 4.409287234738552e-06, + "loss": 0.0042, + "step": 45214 + }, + { + "epoch": 13.96, + "learning_rate": 4.408872583908814e-06, + "loss": 0.0062, + "step": 45215 + }, + { + "epoch": 13.96, + "learning_rate": 4.408457947063505e-06, + "loss": 0.005, + "step": 45216 + }, + { + "epoch": 13.96, + "learning_rate": 4.4080433242036665e-06, + "loss": 0.0061, + "step": 45217 + }, + { + "epoch": 13.96, + "learning_rate": 4.407628715330331e-06, + "loss": 0.0045, + "step": 45218 + }, + { + "epoch": 13.96, + "learning_rate": 4.4072141204445325e-06, + "loss": 0.0042, + "step": 45219 + }, + { + "epoch": 13.96, + "learning_rate": 4.406799539547316e-06, + "loss": 0.0046, + "step": 45220 + }, + { + "epoch": 13.97, + "learning_rate": 4.40638497263971e-06, + "loss": 0.0044, + "step": 45221 + }, + { + "epoch": 13.97, + "learning_rate": 4.405970419722759e-06, + "loss": 0.0043, + "step": 45222 + }, + { + "epoch": 13.97, + "learning_rate": 4.405555880797497e-06, + "loss": 0.0047, + "step": 45223 + }, + { + "epoch": 13.97, + "learning_rate": 4.405141355864955e-06, + "loss": 0.0053, + "step": 45224 + }, + { + "epoch": 13.97, + "learning_rate": 4.404726844926176e-06, + "loss": 0.0054, + "step": 45225 + }, + { + "epoch": 13.97, + "learning_rate": 4.404312347982198e-06, + "loss": 0.0048, + "step": 45226 + }, + { + "epoch": 13.97, + "learning_rate": 4.403897865034052e-06, + "loss": 0.005, + "step": 45227 + }, + { + "epoch": 13.97, + "learning_rate": 4.403483396082784e-06, + "loss": 0.0044, + "step": 45228 + }, + { + "epoch": 13.97, + "learning_rate": 4.4030689411294225e-06, + "loss": 0.0055, + "step": 45229 + }, + { + "epoch": 13.97, + "learning_rate": 4.402654500175003e-06, + "loss": 0.0048, + "step": 45230 + }, + { + "epoch": 13.97, + "learning_rate": 4.4022400732205665e-06, + "loss": 0.0053, + "step": 45231 + }, + { + "epoch": 13.97, + "learning_rate": 4.401825660267152e-06, + "loss": 0.0051, + "step": 45232 + }, + { + "epoch": 13.97, + "learning_rate": 4.401411261315791e-06, + "loss": 0.0042, + "step": 45233 + }, + { + "epoch": 13.97, + "learning_rate": 4.400996876367519e-06, + "loss": 0.0065, + "step": 45234 + }, + { + "epoch": 13.97, + "learning_rate": 4.4005825054233795e-06, + "loss": 0.0046, + "step": 45235 + }, + { + "epoch": 13.97, + "learning_rate": 4.400168148484399e-06, + "loss": 0.0053, + "step": 45236 + }, + { + "epoch": 13.97, + "learning_rate": 4.399753805551621e-06, + "loss": 0.0045, + "step": 45237 + }, + { + "epoch": 13.97, + "learning_rate": 4.399339476626087e-06, + "loss": 0.0055, + "step": 45238 + }, + { + "epoch": 13.97, + "learning_rate": 4.398925161708819e-06, + "loss": 0.0037, + "step": 45239 + }, + { + "epoch": 13.97, + "learning_rate": 4.398510860800861e-06, + "loss": 0.0044, + "step": 45240 + }, + { + "epoch": 13.97, + "learning_rate": 4.398096573903252e-06, + "loss": 0.0054, + "step": 45241 + }, + { + "epoch": 13.97, + "learning_rate": 4.397682301017022e-06, + "loss": 0.0056, + "step": 45242 + }, + { + "epoch": 13.97, + "learning_rate": 4.397268042143213e-06, + "loss": 0.0045, + "step": 45243 + }, + { + "epoch": 13.97, + "learning_rate": 4.396853797282859e-06, + "loss": 0.0051, + "step": 45244 + }, + { + "epoch": 13.97, + "learning_rate": 4.396439566436993e-06, + "loss": 0.0058, + "step": 45245 + }, + { + "epoch": 13.97, + "learning_rate": 4.396025349606653e-06, + "loss": 0.0056, + "step": 45246 + }, + { + "epoch": 13.97, + "learning_rate": 4.3956111467928765e-06, + "loss": 0.0042, + "step": 45247 + }, + { + "epoch": 13.97, + "learning_rate": 4.395196957996704e-06, + "loss": 0.0037, + "step": 45248 + }, + { + "epoch": 13.97, + "learning_rate": 4.39478278321916e-06, + "loss": 0.005, + "step": 45249 + }, + { + "epoch": 13.97, + "learning_rate": 4.394368622461287e-06, + "loss": 0.0046, + "step": 45250 + }, + { + "epoch": 13.97, + "learning_rate": 4.393954475724123e-06, + "loss": 0.0057, + "step": 45251 + }, + { + "epoch": 13.97, + "learning_rate": 4.3935403430087e-06, + "loss": 0.0058, + "step": 45252 + }, + { + "epoch": 13.97, + "learning_rate": 4.3931262243160565e-06, + "loss": 0.0052, + "step": 45253 + }, + { + "epoch": 13.98, + "learning_rate": 4.392712119647228e-06, + "loss": 0.0056, + "step": 45254 + }, + { + "epoch": 13.98, + "learning_rate": 4.392298029003245e-06, + "loss": 0.0054, + "step": 45255 + }, + { + "epoch": 13.98, + "learning_rate": 4.391883952385147e-06, + "loss": 0.0057, + "step": 45256 + }, + { + "epoch": 13.98, + "learning_rate": 4.391469889793975e-06, + "loss": 0.0061, + "step": 45257 + }, + { + "epoch": 13.98, + "learning_rate": 4.391055841230759e-06, + "loss": 0.005, + "step": 45258 + }, + { + "epoch": 13.98, + "learning_rate": 4.3906418066965315e-06, + "loss": 0.006, + "step": 45259 + }, + { + "epoch": 13.98, + "learning_rate": 4.390227786192336e-06, + "loss": 0.0048, + "step": 45260 + }, + { + "epoch": 13.98, + "learning_rate": 4.389813779719201e-06, + "loss": 0.0055, + "step": 45261 + }, + { + "epoch": 13.98, + "learning_rate": 4.389399787278163e-06, + "loss": 0.005, + "step": 45262 + }, + { + "epoch": 13.98, + "learning_rate": 4.388985808870265e-06, + "loss": 0.0044, + "step": 45263 + }, + { + "epoch": 13.98, + "learning_rate": 4.388571844496536e-06, + "loss": 0.0056, + "step": 45264 + }, + { + "epoch": 13.98, + "learning_rate": 4.3881578941580095e-06, + "loss": 0.0046, + "step": 45265 + }, + { + "epoch": 13.98, + "learning_rate": 4.387743957855726e-06, + "loss": 0.0057, + "step": 45266 + }, + { + "epoch": 13.98, + "learning_rate": 4.387330035590716e-06, + "loss": 0.0049, + "step": 45267 + }, + { + "epoch": 13.98, + "learning_rate": 4.38691612736402e-06, + "loss": 0.0047, + "step": 45268 + }, + { + "epoch": 13.98, + "learning_rate": 4.38650223317667e-06, + "loss": 0.0047, + "step": 45269 + }, + { + "epoch": 13.98, + "learning_rate": 4.386088353029699e-06, + "loss": 0.0051, + "step": 45270 + }, + { + "epoch": 13.98, + "learning_rate": 4.385674486924145e-06, + "loss": 0.0048, + "step": 45271 + }, + { + "epoch": 13.98, + "learning_rate": 4.385260634861047e-06, + "loss": 0.0046, + "step": 45272 + }, + { + "epoch": 13.98, + "learning_rate": 4.384846796841432e-06, + "loss": 0.005, + "step": 45273 + }, + { + "epoch": 13.98, + "learning_rate": 4.384432972866344e-06, + "loss": 0.0039, + "step": 45274 + }, + { + "epoch": 13.98, + "learning_rate": 4.384019162936812e-06, + "loss": 0.0045, + "step": 45275 + }, + { + "epoch": 13.98, + "learning_rate": 4.383605367053869e-06, + "loss": 0.0047, + "step": 45276 + }, + { + "epoch": 13.98, + "learning_rate": 4.383191585218553e-06, + "loss": 0.0042, + "step": 45277 + }, + { + "epoch": 13.98, + "learning_rate": 4.382777817431905e-06, + "loss": 0.0056, + "step": 45278 + }, + { + "epoch": 13.98, + "learning_rate": 4.382364063694952e-06, + "loss": 0.0074, + "step": 45279 + }, + { + "epoch": 13.98, + "learning_rate": 4.381950324008728e-06, + "loss": 0.0104, + "step": 45280 + }, + { + "epoch": 13.98, + "learning_rate": 4.381536598374271e-06, + "loss": 0.0062, + "step": 45281 + }, + { + "epoch": 13.98, + "learning_rate": 4.381122886792619e-06, + "loss": 0.007, + "step": 45282 + }, + { + "epoch": 13.98, + "learning_rate": 4.3807091892648e-06, + "loss": 0.005, + "step": 45283 + }, + { + "epoch": 13.98, + "learning_rate": 4.3802955057918576e-06, + "loss": 0.0045, + "step": 45284 + }, + { + "epoch": 13.98, + "learning_rate": 4.379881836374819e-06, + "loss": 0.0048, + "step": 45285 + }, + { + "epoch": 13.99, + "learning_rate": 4.379468181014718e-06, + "loss": 0.0044, + "step": 45286 + }, + { + "epoch": 13.99, + "learning_rate": 4.3790545397125915e-06, + "loss": 0.0057, + "step": 45287 + }, + { + "epoch": 13.99, + "learning_rate": 4.37864091246948e-06, + "loss": 0.0061, + "step": 45288 + }, + { + "epoch": 13.99, + "learning_rate": 4.378227299286411e-06, + "loss": 0.0037, + "step": 45289 + }, + { + "epoch": 13.99, + "learning_rate": 4.377813700164418e-06, + "loss": 0.0051, + "step": 45290 + }, + { + "epoch": 13.99, + "learning_rate": 4.377400115104542e-06, + "loss": 0.0051, + "step": 45291 + }, + { + "epoch": 13.99, + "learning_rate": 4.3769865441078104e-06, + "loss": 0.005, + "step": 45292 + }, + { + "epoch": 13.99, + "learning_rate": 4.376572987175261e-06, + "loss": 0.0051, + "step": 45293 + }, + { + "epoch": 13.99, + "learning_rate": 4.3761594443079324e-06, + "loss": 0.0032, + "step": 45294 + }, + { + "epoch": 13.99, + "learning_rate": 4.375745915506854e-06, + "loss": 0.0051, + "step": 45295 + }, + { + "epoch": 13.99, + "learning_rate": 4.3753324007730565e-06, + "loss": 0.0069, + "step": 45296 + }, + { + "epoch": 13.99, + "learning_rate": 4.374918900107584e-06, + "loss": 0.007, + "step": 45297 + }, + { + "epoch": 13.99, + "learning_rate": 4.374505413511461e-06, + "loss": 0.0049, + "step": 45298 + }, + { + "epoch": 13.99, + "learning_rate": 4.374091940985729e-06, + "loss": 0.0041, + "step": 45299 + }, + { + "epoch": 13.99, + "learning_rate": 4.373678482531419e-06, + "loss": 0.0044, + "step": 45300 + }, + { + "epoch": 13.99, + "learning_rate": 4.373265038149562e-06, + "loss": 0.0055, + "step": 45301 + }, + { + "epoch": 13.99, + "learning_rate": 4.372851607841196e-06, + "loss": 0.0048, + "step": 45302 + }, + { + "epoch": 13.99, + "learning_rate": 4.372438191607357e-06, + "loss": 0.0055, + "step": 45303 + }, + { + "epoch": 13.99, + "learning_rate": 4.372024789449074e-06, + "loss": 0.0042, + "step": 45304 + }, + { + "epoch": 13.99, + "learning_rate": 4.371611401367386e-06, + "loss": 0.0069, + "step": 45305 + }, + { + "epoch": 13.99, + "learning_rate": 4.371198027363326e-06, + "loss": 0.0051, + "step": 45306 + }, + { + "epoch": 13.99, + "learning_rate": 4.37078466743792e-06, + "loss": 0.0046, + "step": 45307 + }, + { + "epoch": 13.99, + "learning_rate": 4.370371321592211e-06, + "loss": 0.006, + "step": 45308 + }, + { + "epoch": 13.99, + "learning_rate": 4.369957989827232e-06, + "loss": 0.0047, + "step": 45309 + }, + { + "epoch": 13.99, + "learning_rate": 4.369544672144016e-06, + "loss": 0.0064, + "step": 45310 + }, + { + "epoch": 13.99, + "learning_rate": 4.369131368543592e-06, + "loss": 0.0065, + "step": 45311 + }, + { + "epoch": 13.99, + "learning_rate": 4.368718079026998e-06, + "loss": 0.0049, + "step": 45312 + }, + { + "epoch": 13.99, + "learning_rate": 4.368304803595269e-06, + "loss": 0.0049, + "step": 45313 + }, + { + "epoch": 13.99, + "learning_rate": 4.367891542249435e-06, + "loss": 0.0048, + "step": 45314 + }, + { + "epoch": 13.99, + "learning_rate": 4.367478294990533e-06, + "loss": 0.0058, + "step": 45315 + }, + { + "epoch": 13.99, + "learning_rate": 4.367065061819598e-06, + "loss": 0.0054, + "step": 45316 + }, + { + "epoch": 13.99, + "learning_rate": 4.366651842737654e-06, + "loss": 0.0049, + "step": 45317 + }, + { + "epoch": 14.0, + "learning_rate": 4.366238637745743e-06, + "loss": 0.0056, + "step": 45318 + }, + { + "epoch": 14.0, + "learning_rate": 4.3658254468449e-06, + "loss": 0.0064, + "step": 45319 + }, + { + "epoch": 14.0, + "learning_rate": 4.365412270036156e-06, + "loss": 0.0039, + "step": 45320 + }, + { + "epoch": 14.0, + "learning_rate": 4.364999107320539e-06, + "loss": 0.0047, + "step": 45321 + }, + { + "epoch": 14.0, + "learning_rate": 4.36458595869909e-06, + "loss": 0.0058, + "step": 45322 + }, + { + "epoch": 14.0, + "learning_rate": 4.364172824172836e-06, + "loss": 0.0049, + "step": 45323 + }, + { + "epoch": 14.0, + "learning_rate": 4.3637597037428145e-06, + "loss": 0.0051, + "step": 45324 + }, + { + "epoch": 14.0, + "learning_rate": 4.363346597410061e-06, + "loss": 0.0056, + "step": 45325 + }, + { + "epoch": 14.0, + "learning_rate": 4.362933505175606e-06, + "loss": 0.0048, + "step": 45326 + }, + { + "epoch": 14.0, + "learning_rate": 4.362520427040479e-06, + "loss": 0.0053, + "step": 45327 + }, + { + "epoch": 14.0, + "learning_rate": 4.36210736300572e-06, + "loss": 0.0063, + "step": 45328 + }, + { + "epoch": 14.0, + "learning_rate": 4.361694313072355e-06, + "loss": 0.0052, + "step": 45329 + }, + { + "epoch": 14.0, + "learning_rate": 4.3612812772414245e-06, + "loss": 0.0049, + "step": 45330 + }, + { + "epoch": 14.0, + "learning_rate": 4.360868255513958e-06, + "loss": 0.0048, + "step": 45331 + }, + { + "epoch": 14.0, + "learning_rate": 4.3604552478909855e-06, + "loss": 0.0059, + "step": 45332 + }, + { + "epoch": 14.0, + "learning_rate": 4.360042254373542e-06, + "loss": 0.0061, + "step": 45333 + }, + { + "epoch": 14.0, + "learning_rate": 4.3596292749626655e-06, + "loss": 0.0048, + "step": 45334 + }, + { + "epoch": 14.0, + "learning_rate": 4.3592163096593824e-06, + "loss": 0.0038, + "step": 45335 + }, + { + "epoch": 14.0, + "learning_rate": 4.358803358464731e-06, + "loss": 0.0033, + "step": 45336 + }, + { + "epoch": 14.0, + "learning_rate": 4.3583904213797405e-06, + "loss": 0.0033, + "step": 45337 + }, + { + "epoch": 14.0, + "learning_rate": 4.3579774984054416e-06, + "loss": 0.0028, + "step": 45338 + }, + { + "epoch": 14.0, + "learning_rate": 4.35756458954287e-06, + "loss": 0.0037, + "step": 45339 + }, + { + "epoch": 14.0, + "learning_rate": 4.3571516947930616e-06, + "loss": 0.0035, + "step": 45340 + }, + { + "epoch": 14.0, + "learning_rate": 4.356738814157046e-06, + "loss": 0.0039, + "step": 45341 + }, + { + "epoch": 14.0, + "learning_rate": 4.3563259476358536e-06, + "loss": 0.0032, + "step": 45342 + }, + { + "epoch": 14.0, + "learning_rate": 4.355913095230517e-06, + "loss": 0.0024, + "step": 45343 + }, + { + "epoch": 14.0, + "learning_rate": 4.355500256942077e-06, + "loss": 0.0029, + "step": 45344 + }, + { + "epoch": 14.0, + "learning_rate": 4.3550874327715566e-06, + "loss": 0.0032, + "step": 45345 + }, + { + "epoch": 14.0, + "learning_rate": 4.3546746227199946e-06, + "loss": 0.0032, + "step": 45346 + }, + { + "epoch": 14.0, + "learning_rate": 4.354261826788421e-06, + "loss": 0.0032, + "step": 45347 + }, + { + "epoch": 14.0, + "learning_rate": 4.353849044977865e-06, + "loss": 0.0029, + "step": 45348 + }, + { + "epoch": 14.0, + "learning_rate": 4.3534362772893624e-06, + "loss": 0.0041, + "step": 45349 + }, + { + "epoch": 14.0, + "learning_rate": 4.353023523723949e-06, + "loss": 0.0037, + "step": 45350 + }, + { + "epoch": 14.01, + "learning_rate": 4.352610784282655e-06, + "loss": 0.0022, + "step": 45351 + }, + { + "epoch": 14.01, + "learning_rate": 4.352198058966506e-06, + "loss": 0.0036, + "step": 45352 + }, + { + "epoch": 14.01, + "learning_rate": 4.3517853477765444e-06, + "loss": 0.0021, + "step": 45353 + }, + { + "epoch": 14.01, + "learning_rate": 4.351372650713795e-06, + "loss": 0.0027, + "step": 45354 + }, + { + "epoch": 14.01, + "learning_rate": 4.35095996777929e-06, + "loss": 0.0033, + "step": 45355 + }, + { + "epoch": 14.01, + "learning_rate": 4.350547298974074e-06, + "loss": 0.0032, + "step": 45356 + }, + { + "epoch": 14.01, + "learning_rate": 4.350134644299162e-06, + "loss": 0.0038, + "step": 45357 + }, + { + "epoch": 14.01, + "learning_rate": 4.3497220037555935e-06, + "loss": 0.0026, + "step": 45358 + }, + { + "epoch": 14.01, + "learning_rate": 4.349309377344404e-06, + "loss": 0.003, + "step": 45359 + }, + { + "epoch": 14.01, + "learning_rate": 4.348896765066619e-06, + "loss": 0.0046, + "step": 45360 + }, + { + "epoch": 14.01, + "learning_rate": 4.348484166923278e-06, + "loss": 0.0028, + "step": 45361 + }, + { + "epoch": 14.01, + "learning_rate": 4.348071582915408e-06, + "loss": 0.0032, + "step": 45362 + }, + { + "epoch": 14.01, + "learning_rate": 4.34765901304404e-06, + "loss": 0.0026, + "step": 45363 + }, + { + "epoch": 14.01, + "learning_rate": 4.347246457310205e-06, + "loss": 0.0042, + "step": 45364 + }, + { + "epoch": 14.01, + "learning_rate": 4.346833915714944e-06, + "loss": 0.0026, + "step": 45365 + }, + { + "epoch": 14.01, + "learning_rate": 4.346421388259281e-06, + "loss": 0.0038, + "step": 45366 + }, + { + "epoch": 14.01, + "learning_rate": 4.346008874944245e-06, + "loss": 0.004, + "step": 45367 + }, + { + "epoch": 14.01, + "learning_rate": 4.3455963757708775e-06, + "loss": 0.0037, + "step": 45368 + }, + { + "epoch": 14.01, + "learning_rate": 4.3451838907402e-06, + "loss": 0.0035, + "step": 45369 + }, + { + "epoch": 14.01, + "learning_rate": 4.3447714198532486e-06, + "loss": 0.0037, + "step": 45370 + }, + { + "epoch": 14.01, + "learning_rate": 4.344358963111059e-06, + "loss": 0.0031, + "step": 45371 + }, + { + "epoch": 14.01, + "learning_rate": 4.34394652051466e-06, + "loss": 0.0036, + "step": 45372 + }, + { + "epoch": 14.01, + "learning_rate": 4.34353409206508e-06, + "loss": 0.003, + "step": 45373 + }, + { + "epoch": 14.01, + "learning_rate": 4.3431216777633534e-06, + "loss": 0.0025, + "step": 45374 + }, + { + "epoch": 14.01, + "learning_rate": 4.34270927761051e-06, + "loss": 0.0035, + "step": 45375 + }, + { + "epoch": 14.01, + "learning_rate": 4.342296891607585e-06, + "loss": 0.003, + "step": 45376 + }, + { + "epoch": 14.01, + "learning_rate": 4.3418845197556035e-06, + "loss": 0.0025, + "step": 45377 + }, + { + "epoch": 14.01, + "learning_rate": 4.341472162055605e-06, + "loss": 0.0038, + "step": 45378 + }, + { + "epoch": 14.01, + "learning_rate": 4.341059818508613e-06, + "loss": 0.0029, + "step": 45379 + }, + { + "epoch": 14.01, + "learning_rate": 4.3406474891156626e-06, + "loss": 0.0026, + "step": 45380 + }, + { + "epoch": 14.01, + "learning_rate": 4.340235173877788e-06, + "loss": 0.0025, + "step": 45381 + }, + { + "epoch": 14.01, + "learning_rate": 4.339822872796018e-06, + "loss": 0.0027, + "step": 45382 + }, + { + "epoch": 14.02, + "learning_rate": 4.33941058587138e-06, + "loss": 0.0037, + "step": 45383 + }, + { + "epoch": 14.02, + "learning_rate": 4.338998313104912e-06, + "loss": 0.0032, + "step": 45384 + }, + { + "epoch": 14.02, + "learning_rate": 4.338586054497638e-06, + "loss": 0.004, + "step": 45385 + }, + { + "epoch": 14.02, + "learning_rate": 4.3381738100505966e-06, + "loss": 0.0039, + "step": 45386 + }, + { + "epoch": 14.02, + "learning_rate": 4.337761579764814e-06, + "loss": 0.0039, + "step": 45387 + }, + { + "epoch": 14.02, + "learning_rate": 4.33734936364132e-06, + "loss": 0.0032, + "step": 45388 + }, + { + "epoch": 14.02, + "learning_rate": 4.336937161681149e-06, + "loss": 0.0032, + "step": 45389 + }, + { + "epoch": 14.02, + "learning_rate": 4.336524973885333e-06, + "loss": 0.0025, + "step": 45390 + }, + { + "epoch": 14.02, + "learning_rate": 4.336112800254898e-06, + "loss": 0.0031, + "step": 45391 + }, + { + "epoch": 14.02, + "learning_rate": 4.335700640790881e-06, + "loss": 0.0037, + "step": 45392 + }, + { + "epoch": 14.02, + "learning_rate": 4.335288495494311e-06, + "loss": 0.003, + "step": 45393 + }, + { + "epoch": 14.02, + "learning_rate": 4.334876364366213e-06, + "loss": 0.0032, + "step": 45394 + }, + { + "epoch": 14.02, + "learning_rate": 4.334464247407623e-06, + "loss": 0.0032, + "step": 45395 + }, + { + "epoch": 14.02, + "learning_rate": 4.334052144619574e-06, + "loss": 0.0025, + "step": 45396 + }, + { + "epoch": 14.02, + "learning_rate": 4.333640056003094e-06, + "loss": 0.0026, + "step": 45397 + }, + { + "epoch": 14.02, + "learning_rate": 4.333227981559211e-06, + "loss": 0.0024, + "step": 45398 + }, + { + "epoch": 14.02, + "learning_rate": 4.332815921288962e-06, + "loss": 0.003, + "step": 45399 + }, + { + "epoch": 14.02, + "learning_rate": 4.332403875193371e-06, + "loss": 0.0041, + "step": 45400 + }, + { + "epoch": 14.02, + "learning_rate": 4.33199184327347e-06, + "loss": 0.0027, + "step": 45401 + }, + { + "epoch": 14.02, + "learning_rate": 4.331579825530295e-06, + "loss": 0.0026, + "step": 45402 + }, + { + "epoch": 14.02, + "learning_rate": 4.331167821964873e-06, + "loss": 0.0027, + "step": 45403 + }, + { + "epoch": 14.02, + "learning_rate": 4.33075583257823e-06, + "loss": 0.0028, + "step": 45404 + }, + { + "epoch": 14.02, + "learning_rate": 4.330343857371406e-06, + "loss": 0.0061, + "step": 45405 + }, + { + "epoch": 14.02, + "learning_rate": 4.329931896345422e-06, + "loss": 0.0032, + "step": 45406 + }, + { + "epoch": 14.02, + "learning_rate": 4.329519949501315e-06, + "loss": 0.0032, + "step": 45407 + }, + { + "epoch": 14.02, + "learning_rate": 4.32910801684011e-06, + "loss": 0.0025, + "step": 45408 + }, + { + "epoch": 14.02, + "learning_rate": 4.328696098362843e-06, + "loss": 0.0028, + "step": 45409 + }, + { + "epoch": 14.02, + "learning_rate": 4.328284194070539e-06, + "loss": 0.0034, + "step": 45410 + }, + { + "epoch": 14.02, + "learning_rate": 4.32787230396423e-06, + "loss": 0.0036, + "step": 45411 + }, + { + "epoch": 14.02, + "learning_rate": 4.327460428044951e-06, + "loss": 0.0035, + "step": 45412 + }, + { + "epoch": 14.02, + "learning_rate": 4.327048566313727e-06, + "loss": 0.0033, + "step": 45413 + }, + { + "epoch": 14.02, + "learning_rate": 4.3266367187715875e-06, + "loss": 0.0035, + "step": 45414 + }, + { + "epoch": 14.02, + "learning_rate": 4.3262248854195665e-06, + "loss": 0.003, + "step": 45415 + }, + { + "epoch": 14.03, + "learning_rate": 4.325813066258688e-06, + "loss": 0.0034, + "step": 45416 + }, + { + "epoch": 14.03, + "learning_rate": 4.3254012612899906e-06, + "loss": 0.0032, + "step": 45417 + }, + { + "epoch": 14.03, + "learning_rate": 4.324989470514499e-06, + "loss": 0.0042, + "step": 45418 + }, + { + "epoch": 14.03, + "learning_rate": 4.324577693933241e-06, + "loss": 0.0034, + "step": 45419 + }, + { + "epoch": 14.03, + "learning_rate": 4.324165931547249e-06, + "loss": 0.0034, + "step": 45420 + }, + { + "epoch": 14.03, + "learning_rate": 4.323754183357556e-06, + "loss": 0.0025, + "step": 45421 + }, + { + "epoch": 14.03, + "learning_rate": 4.3233424493651854e-06, + "loss": 0.0027, + "step": 45422 + }, + { + "epoch": 14.03, + "learning_rate": 4.322930729571175e-06, + "loss": 0.0026, + "step": 45423 + }, + { + "epoch": 14.03, + "learning_rate": 4.32251902397655e-06, + "loss": 0.0032, + "step": 45424 + }, + { + "epoch": 14.03, + "learning_rate": 4.322107332582337e-06, + "loss": 0.0036, + "step": 45425 + }, + { + "epoch": 14.03, + "learning_rate": 4.321695655389569e-06, + "loss": 0.0039, + "step": 45426 + }, + { + "epoch": 14.03, + "learning_rate": 4.321283992399279e-06, + "loss": 0.0027, + "step": 45427 + }, + { + "epoch": 14.03, + "learning_rate": 4.320872343612494e-06, + "loss": 0.0041, + "step": 45428 + }, + { + "epoch": 14.03, + "learning_rate": 4.32046070903024e-06, + "loss": 0.0025, + "step": 45429 + }, + { + "epoch": 14.03, + "learning_rate": 4.320049088653553e-06, + "loss": 0.0032, + "step": 45430 + }, + { + "epoch": 14.03, + "learning_rate": 4.3196374824834546e-06, + "loss": 0.0038, + "step": 45431 + }, + { + "epoch": 14.03, + "learning_rate": 4.319225890520979e-06, + "loss": 0.0033, + "step": 45432 + }, + { + "epoch": 14.03, + "learning_rate": 4.31881431276716e-06, + "loss": 0.0035, + "step": 45433 + }, + { + "epoch": 14.03, + "learning_rate": 4.318402749223023e-06, + "loss": 0.0025, + "step": 45434 + }, + { + "epoch": 14.03, + "learning_rate": 4.317991199889592e-06, + "loss": 0.0033, + "step": 45435 + }, + { + "epoch": 14.03, + "learning_rate": 4.3175796647679056e-06, + "loss": 0.0028, + "step": 45436 + }, + { + "epoch": 14.03, + "learning_rate": 4.3171681438589855e-06, + "loss": 0.0034, + "step": 45437 + }, + { + "epoch": 14.03, + "learning_rate": 4.316756637163868e-06, + "loss": 0.0028, + "step": 45438 + }, + { + "epoch": 14.03, + "learning_rate": 4.316345144683578e-06, + "loss": 0.0033, + "step": 45439 + }, + { + "epoch": 14.03, + "learning_rate": 4.315933666419142e-06, + "loss": 0.0028, + "step": 45440 + }, + { + "epoch": 14.03, + "learning_rate": 4.315522202371594e-06, + "loss": 0.0032, + "step": 45441 + }, + { + "epoch": 14.03, + "learning_rate": 4.31511075254196e-06, + "loss": 0.0024, + "step": 45442 + }, + { + "epoch": 14.03, + "learning_rate": 4.3146993169312755e-06, + "loss": 0.0032, + "step": 45443 + }, + { + "epoch": 14.03, + "learning_rate": 4.314287895540564e-06, + "loss": 0.0029, + "step": 45444 + }, + { + "epoch": 14.03, + "learning_rate": 4.313876488370853e-06, + "loss": 0.0043, + "step": 45445 + }, + { + "epoch": 14.03, + "learning_rate": 4.313465095423177e-06, + "loss": 0.0026, + "step": 45446 + }, + { + "epoch": 14.03, + "learning_rate": 4.313053716698558e-06, + "loss": 0.0025, + "step": 45447 + }, + { + "epoch": 14.04, + "learning_rate": 4.312642352198033e-06, + "loss": 0.0039, + "step": 45448 + }, + { + "epoch": 14.04, + "learning_rate": 4.3122310019226265e-06, + "loss": 0.0024, + "step": 45449 + }, + { + "epoch": 14.04, + "learning_rate": 4.311819665873364e-06, + "loss": 0.0035, + "step": 45450 + }, + { + "epoch": 14.04, + "learning_rate": 4.311408344051279e-06, + "loss": 0.0035, + "step": 45451 + }, + { + "epoch": 14.04, + "learning_rate": 4.310997036457402e-06, + "loss": 0.0033, + "step": 45452 + }, + { + "epoch": 14.04, + "learning_rate": 4.310585743092755e-06, + "loss": 0.0027, + "step": 45453 + }, + { + "epoch": 14.04, + "learning_rate": 4.310174463958375e-06, + "loss": 0.0024, + "step": 45454 + }, + { + "epoch": 14.04, + "learning_rate": 4.309763199055286e-06, + "loss": 0.0023, + "step": 45455 + }, + { + "epoch": 14.04, + "learning_rate": 4.3093519483845135e-06, + "loss": 0.0031, + "step": 45456 + }, + { + "epoch": 14.04, + "learning_rate": 4.308940711947091e-06, + "loss": 0.0024, + "step": 45457 + }, + { + "epoch": 14.04, + "learning_rate": 4.308529489744047e-06, + "loss": 0.0036, + "step": 45458 + }, + { + "epoch": 14.04, + "learning_rate": 4.30811828177641e-06, + "loss": 0.003, + "step": 45459 + }, + { + "epoch": 14.04, + "learning_rate": 4.307707088045204e-06, + "loss": 0.0029, + "step": 45460 + }, + { + "epoch": 14.04, + "learning_rate": 4.307295908551464e-06, + "loss": 0.0022, + "step": 45461 + }, + { + "epoch": 14.04, + "learning_rate": 4.306884743296212e-06, + "loss": 0.0021, + "step": 45462 + }, + { + "epoch": 14.04, + "learning_rate": 4.306473592280479e-06, + "loss": 0.0031, + "step": 45463 + }, + { + "epoch": 14.04, + "learning_rate": 4.306062455505302e-06, + "loss": 0.0028, + "step": 45464 + }, + { + "epoch": 14.04, + "learning_rate": 4.305651332971694e-06, + "loss": 0.0033, + "step": 45465 + }, + { + "epoch": 14.04, + "learning_rate": 4.30524022468069e-06, + "loss": 0.0026, + "step": 45466 + }, + { + "epoch": 14.04, + "learning_rate": 4.3048291306333226e-06, + "loss": 0.0032, + "step": 45467 + }, + { + "epoch": 14.04, + "learning_rate": 4.304418050830613e-06, + "loss": 0.0039, + "step": 45468 + }, + { + "epoch": 14.04, + "learning_rate": 4.304006985273597e-06, + "loss": 0.0037, + "step": 45469 + }, + { + "epoch": 14.04, + "learning_rate": 4.303595933963297e-06, + "loss": 0.004, + "step": 45470 + }, + { + "epoch": 14.04, + "learning_rate": 4.303184896900739e-06, + "loss": 0.0031, + "step": 45471 + }, + { + "epoch": 14.04, + "learning_rate": 4.302773874086955e-06, + "loss": 0.004, + "step": 45472 + }, + { + "epoch": 14.04, + "learning_rate": 4.302362865522977e-06, + "loss": 0.0031, + "step": 45473 + }, + { + "epoch": 14.04, + "learning_rate": 4.301951871209824e-06, + "loss": 0.0038, + "step": 45474 + }, + { + "epoch": 14.04, + "learning_rate": 4.301540891148533e-06, + "loss": 0.0029, + "step": 45475 + }, + { + "epoch": 14.04, + "learning_rate": 4.301129925340123e-06, + "loss": 0.0034, + "step": 45476 + }, + { + "epoch": 14.04, + "learning_rate": 4.30071897378563e-06, + "loss": 0.0019, + "step": 45477 + }, + { + "epoch": 14.04, + "learning_rate": 4.300308036486076e-06, + "loss": 0.0026, + "step": 45478 + }, + { + "epoch": 14.04, + "learning_rate": 4.2998971134424935e-06, + "loss": 0.0029, + "step": 45479 + }, + { + "epoch": 14.05, + "learning_rate": 4.299486204655908e-06, + "loss": 0.0033, + "step": 45480 + }, + { + "epoch": 14.05, + "learning_rate": 4.299075310127345e-06, + "loss": 0.0036, + "step": 45481 + }, + { + "epoch": 14.05, + "learning_rate": 4.298664429857834e-06, + "loss": 0.0033, + "step": 45482 + }, + { + "epoch": 14.05, + "learning_rate": 4.298253563848405e-06, + "loss": 0.0046, + "step": 45483 + }, + { + "epoch": 14.05, + "learning_rate": 4.297842712100082e-06, + "loss": 0.0031, + "step": 45484 + }, + { + "epoch": 14.05, + "learning_rate": 4.297431874613898e-06, + "loss": 0.0025, + "step": 45485 + }, + { + "epoch": 14.05, + "learning_rate": 4.297021051390876e-06, + "loss": 0.003, + "step": 45486 + }, + { + "epoch": 14.05, + "learning_rate": 4.296610242432041e-06, + "loss": 0.0028, + "step": 45487 + }, + { + "epoch": 14.05, + "learning_rate": 4.296199447738425e-06, + "loss": 0.0025, + "step": 45488 + }, + { + "epoch": 14.05, + "learning_rate": 4.295788667311057e-06, + "loss": 0.0035, + "step": 45489 + }, + { + "epoch": 14.05, + "learning_rate": 4.295377901150962e-06, + "loss": 0.0025, + "step": 45490 + }, + { + "epoch": 14.05, + "learning_rate": 4.294967149259165e-06, + "loss": 0.0036, + "step": 45491 + }, + { + "epoch": 14.05, + "learning_rate": 4.294556411636698e-06, + "loss": 0.0031, + "step": 45492 + }, + { + "epoch": 14.05, + "learning_rate": 4.294145688284583e-06, + "loss": 0.0037, + "step": 45493 + }, + { + "epoch": 14.05, + "learning_rate": 4.2937349792038495e-06, + "loss": 0.0032, + "step": 45494 + }, + { + "epoch": 14.05, + "learning_rate": 4.2933242843955335e-06, + "loss": 0.0042, + "step": 45495 + }, + { + "epoch": 14.05, + "learning_rate": 4.292913603860648e-06, + "loss": 0.0037, + "step": 45496 + }, + { + "epoch": 14.05, + "learning_rate": 4.2925029376002244e-06, + "loss": 0.0039, + "step": 45497 + }, + { + "epoch": 14.05, + "learning_rate": 4.292092285615297e-06, + "loss": 0.0035, + "step": 45498 + }, + { + "epoch": 14.05, + "learning_rate": 4.291681647906884e-06, + "loss": 0.0033, + "step": 45499 + }, + { + "epoch": 14.05, + "learning_rate": 4.2912710244760205e-06, + "loss": 0.0028, + "step": 45500 + }, + { + "epoch": 14.05, + "learning_rate": 4.2908604153237275e-06, + "loss": 0.0026, + "step": 45501 + }, + { + "epoch": 14.05, + "learning_rate": 4.290449820451033e-06, + "loss": 0.0031, + "step": 45502 + }, + { + "epoch": 14.05, + "learning_rate": 4.290039239858962e-06, + "loss": 0.0034, + "step": 45503 + }, + { + "epoch": 14.05, + "learning_rate": 4.289628673548549e-06, + "loss": 0.0032, + "step": 45504 + }, + { + "epoch": 14.05, + "learning_rate": 4.289218121520817e-06, + "loss": 0.0025, + "step": 45505 + }, + { + "epoch": 14.05, + "learning_rate": 4.288807583776787e-06, + "loss": 0.0031, + "step": 45506 + }, + { + "epoch": 14.05, + "learning_rate": 4.288397060317493e-06, + "loss": 0.0035, + "step": 45507 + }, + { + "epoch": 14.05, + "learning_rate": 4.287986551143961e-06, + "loss": 0.0036, + "step": 45508 + }, + { + "epoch": 14.05, + "learning_rate": 4.287576056257214e-06, + "loss": 0.0027, + "step": 45509 + }, + { + "epoch": 14.05, + "learning_rate": 4.287165575658286e-06, + "loss": 0.0041, + "step": 45510 + }, + { + "epoch": 14.05, + "learning_rate": 4.2867551093481965e-06, + "loss": 0.0026, + "step": 45511 + }, + { + "epoch": 14.05, + "learning_rate": 4.2863446573279725e-06, + "loss": 0.004, + "step": 45512 + }, + { + "epoch": 14.06, + "learning_rate": 4.285934219598642e-06, + "loss": 0.0052, + "step": 45513 + }, + { + "epoch": 14.06, + "learning_rate": 4.285523796161235e-06, + "loss": 0.0028, + "step": 45514 + }, + { + "epoch": 14.06, + "learning_rate": 4.285113387016776e-06, + "loss": 0.0037, + "step": 45515 + }, + { + "epoch": 14.06, + "learning_rate": 4.2847029921662875e-06, + "loss": 0.0039, + "step": 45516 + }, + { + "epoch": 14.06, + "learning_rate": 4.284292611610803e-06, + "loss": 0.0029, + "step": 45517 + }, + { + "epoch": 14.06, + "learning_rate": 4.28388224535134e-06, + "loss": 0.0036, + "step": 45518 + }, + { + "epoch": 14.06, + "learning_rate": 4.283471893388932e-06, + "loss": 0.0033, + "step": 45519 + }, + { + "epoch": 14.06, + "learning_rate": 4.2830615557246055e-06, + "loss": 0.0026, + "step": 45520 + }, + { + "epoch": 14.06, + "learning_rate": 4.282651232359386e-06, + "loss": 0.0034, + "step": 45521 + }, + { + "epoch": 14.06, + "learning_rate": 4.282240923294294e-06, + "loss": 0.0027, + "step": 45522 + }, + { + "epoch": 14.06, + "learning_rate": 4.2818306285303646e-06, + "loss": 0.0028, + "step": 45523 + }, + { + "epoch": 14.06, + "learning_rate": 4.2814203480686155e-06, + "loss": 0.0031, + "step": 45524 + }, + { + "epoch": 14.06, + "learning_rate": 4.281010081910081e-06, + "loss": 0.0036, + "step": 45525 + }, + { + "epoch": 14.06, + "learning_rate": 4.280599830055784e-06, + "loss": 0.0032, + "step": 45526 + }, + { + "epoch": 14.06, + "learning_rate": 4.280189592506745e-06, + "loss": 0.003, + "step": 45527 + }, + { + "epoch": 14.06, + "learning_rate": 4.2797793692639966e-06, + "loss": 0.0034, + "step": 45528 + }, + { + "epoch": 14.06, + "learning_rate": 4.279369160328566e-06, + "loss": 0.0033, + "step": 45529 + }, + { + "epoch": 14.06, + "learning_rate": 4.278958965701473e-06, + "loss": 0.0032, + "step": 45530 + }, + { + "epoch": 14.06, + "learning_rate": 4.27854878538375e-06, + "loss": 0.0026, + "step": 45531 + }, + { + "epoch": 14.06, + "learning_rate": 4.278138619376421e-06, + "loss": 0.003, + "step": 45532 + }, + { + "epoch": 14.06, + "learning_rate": 4.277728467680508e-06, + "loss": 0.0038, + "step": 45533 + }, + { + "epoch": 14.06, + "learning_rate": 4.277318330297037e-06, + "loss": 0.0029, + "step": 45534 + }, + { + "epoch": 14.06, + "learning_rate": 4.276908207227043e-06, + "loss": 0.0023, + "step": 45535 + }, + { + "epoch": 14.06, + "learning_rate": 4.276498098471544e-06, + "loss": 0.0028, + "step": 45536 + }, + { + "epoch": 14.06, + "learning_rate": 4.276088004031564e-06, + "loss": 0.0032, + "step": 45537 + }, + { + "epoch": 14.06, + "learning_rate": 4.275677923908136e-06, + "loss": 0.0025, + "step": 45538 + }, + { + "epoch": 14.06, + "learning_rate": 4.275267858102278e-06, + "loss": 0.0028, + "step": 45539 + }, + { + "epoch": 14.06, + "learning_rate": 4.274857806615018e-06, + "loss": 0.0034, + "step": 45540 + }, + { + "epoch": 14.06, + "learning_rate": 4.274447769447388e-06, + "loss": 0.0035, + "step": 45541 + }, + { + "epoch": 14.06, + "learning_rate": 4.274037746600407e-06, + "loss": 0.003, + "step": 45542 + }, + { + "epoch": 14.06, + "learning_rate": 4.273627738075098e-06, + "loss": 0.0023, + "step": 45543 + }, + { + "epoch": 14.06, + "learning_rate": 4.273217743872491e-06, + "loss": 0.0033, + "step": 45544 + }, + { + "epoch": 14.07, + "learning_rate": 4.272807763993615e-06, + "loss": 0.003, + "step": 45545 + }, + { + "epoch": 14.07, + "learning_rate": 4.272397798439491e-06, + "loss": 0.0026, + "step": 45546 + }, + { + "epoch": 14.07, + "learning_rate": 4.271987847211142e-06, + "loss": 0.0041, + "step": 45547 + }, + { + "epoch": 14.07, + "learning_rate": 4.271577910309599e-06, + "loss": 0.0031, + "step": 45548 + }, + { + "epoch": 14.07, + "learning_rate": 4.27116798773588e-06, + "loss": 0.0044, + "step": 45549 + }, + { + "epoch": 14.07, + "learning_rate": 4.2707580794910164e-06, + "loss": 0.0027, + "step": 45550 + }, + { + "epoch": 14.07, + "learning_rate": 4.270348185576034e-06, + "loss": 0.0039, + "step": 45551 + }, + { + "epoch": 14.07, + "learning_rate": 4.269938305991956e-06, + "loss": 0.0027, + "step": 45552 + }, + { + "epoch": 14.07, + "learning_rate": 4.2695284407398056e-06, + "loss": 0.003, + "step": 45553 + }, + { + "epoch": 14.07, + "learning_rate": 4.269118589820611e-06, + "loss": 0.0035, + "step": 45554 + }, + { + "epoch": 14.07, + "learning_rate": 4.268708753235393e-06, + "loss": 0.0025, + "step": 45555 + }, + { + "epoch": 14.07, + "learning_rate": 4.2682989309851844e-06, + "loss": 0.0034, + "step": 45556 + }, + { + "epoch": 14.07, + "learning_rate": 4.267889123071005e-06, + "loss": 0.0039, + "step": 45557 + }, + { + "epoch": 14.07, + "learning_rate": 4.267479329493876e-06, + "loss": 0.0034, + "step": 45558 + }, + { + "epoch": 14.07, + "learning_rate": 4.267069550254827e-06, + "loss": 0.0024, + "step": 45559 + }, + { + "epoch": 14.07, + "learning_rate": 4.266659785354888e-06, + "loss": 0.003, + "step": 45560 + }, + { + "epoch": 14.07, + "learning_rate": 4.266250034795073e-06, + "loss": 0.0035, + "step": 45561 + }, + { + "epoch": 14.07, + "learning_rate": 4.265840298576417e-06, + "loss": 0.0024, + "step": 45562 + }, + { + "epoch": 14.07, + "learning_rate": 4.2654305766999396e-06, + "loss": 0.003, + "step": 45563 + }, + { + "epoch": 14.07, + "learning_rate": 4.265020869166663e-06, + "loss": 0.0034, + "step": 45564 + }, + { + "epoch": 14.07, + "learning_rate": 4.264611175977615e-06, + "loss": 0.004, + "step": 45565 + }, + { + "epoch": 14.07, + "learning_rate": 4.264201497133825e-06, + "loss": 0.0031, + "step": 45566 + }, + { + "epoch": 14.07, + "learning_rate": 4.263791832636313e-06, + "loss": 0.0031, + "step": 45567 + }, + { + "epoch": 14.07, + "learning_rate": 4.263382182486099e-06, + "loss": 0.0036, + "step": 45568 + }, + { + "epoch": 14.07, + "learning_rate": 4.262972546684216e-06, + "loss": 0.004, + "step": 45569 + }, + { + "epoch": 14.07, + "learning_rate": 4.2625629252316836e-06, + "loss": 0.0028, + "step": 45570 + }, + { + "epoch": 14.07, + "learning_rate": 4.262153318129526e-06, + "loss": 0.0029, + "step": 45571 + }, + { + "epoch": 14.07, + "learning_rate": 4.261743725378773e-06, + "loss": 0.0028, + "step": 45572 + }, + { + "epoch": 14.07, + "learning_rate": 4.261334146980446e-06, + "loss": 0.0025, + "step": 45573 + }, + { + "epoch": 14.07, + "learning_rate": 4.260924582935566e-06, + "loss": 0.0033, + "step": 45574 + }, + { + "epoch": 14.07, + "learning_rate": 4.260515033245159e-06, + "loss": 0.0034, + "step": 45575 + }, + { + "epoch": 14.07, + "learning_rate": 4.2601054979102555e-06, + "loss": 0.0028, + "step": 45576 + }, + { + "epoch": 14.08, + "learning_rate": 4.259695976931875e-06, + "loss": 0.0036, + "step": 45577 + }, + { + "epoch": 14.08, + "learning_rate": 4.259286470311037e-06, + "loss": 0.0035, + "step": 45578 + }, + { + "epoch": 14.08, + "learning_rate": 4.258876978048776e-06, + "loss": 0.0029, + "step": 45579 + }, + { + "epoch": 14.08, + "learning_rate": 4.258467500146106e-06, + "loss": 0.004, + "step": 45580 + }, + { + "epoch": 14.08, + "learning_rate": 4.258058036604056e-06, + "loss": 0.0036, + "step": 45581 + }, + { + "epoch": 14.08, + "learning_rate": 4.2576485874236536e-06, + "loss": 0.0035, + "step": 45582 + }, + { + "epoch": 14.08, + "learning_rate": 4.25723915260592e-06, + "loss": 0.003, + "step": 45583 + }, + { + "epoch": 14.08, + "learning_rate": 4.256829732151875e-06, + "loss": 0.0026, + "step": 45584 + }, + { + "epoch": 14.08, + "learning_rate": 4.256420326062549e-06, + "loss": 0.0046, + "step": 45585 + }, + { + "epoch": 14.08, + "learning_rate": 4.256010934338961e-06, + "loss": 0.0024, + "step": 45586 + }, + { + "epoch": 14.08, + "learning_rate": 4.25560155698214e-06, + "loss": 0.0029, + "step": 45587 + }, + { + "epoch": 14.08, + "learning_rate": 4.255192193993108e-06, + "loss": 0.0035, + "step": 45588 + }, + { + "epoch": 14.08, + "learning_rate": 4.254782845372885e-06, + "loss": 0.0037, + "step": 45589 + }, + { + "epoch": 14.08, + "learning_rate": 4.254373511122496e-06, + "loss": 0.0044, + "step": 45590 + }, + { + "epoch": 14.08, + "learning_rate": 4.253964191242972e-06, + "loss": 0.0045, + "step": 45591 + }, + { + "epoch": 14.08, + "learning_rate": 4.253554885735327e-06, + "loss": 0.0042, + "step": 45592 + }, + { + "epoch": 14.08, + "learning_rate": 4.253145594600593e-06, + "loss": 0.0039, + "step": 45593 + }, + { + "epoch": 14.08, + "learning_rate": 4.25273631783979e-06, + "loss": 0.0025, + "step": 45594 + }, + { + "epoch": 14.08, + "learning_rate": 4.252327055453939e-06, + "loss": 0.003, + "step": 45595 + }, + { + "epoch": 14.08, + "learning_rate": 4.251917807444066e-06, + "loss": 0.0028, + "step": 45596 + }, + { + "epoch": 14.08, + "learning_rate": 4.251508573811198e-06, + "loss": 0.0031, + "step": 45597 + }, + { + "epoch": 14.08, + "learning_rate": 4.2510993545563565e-06, + "loss": 0.0041, + "step": 45598 + }, + { + "epoch": 14.08, + "learning_rate": 4.25069014968056e-06, + "loss": 0.004, + "step": 45599 + }, + { + "epoch": 14.08, + "learning_rate": 4.250280959184839e-06, + "loss": 0.0026, + "step": 45600 + }, + { + "epoch": 14.08, + "learning_rate": 4.249871783070211e-06, + "loss": 0.0036, + "step": 45601 + }, + { + "epoch": 14.08, + "learning_rate": 4.249462621337702e-06, + "loss": 0.0029, + "step": 45602 + }, + { + "epoch": 14.08, + "learning_rate": 4.249053473988344e-06, + "loss": 0.003, + "step": 45603 + }, + { + "epoch": 14.08, + "learning_rate": 4.2486443410231436e-06, + "loss": 0.0026, + "step": 45604 + }, + { + "epoch": 14.08, + "learning_rate": 4.248235222443133e-06, + "loss": 0.0029, + "step": 45605 + }, + { + "epoch": 14.08, + "learning_rate": 4.247826118249336e-06, + "loss": 0.0025, + "step": 45606 + }, + { + "epoch": 14.08, + "learning_rate": 4.2474170284427786e-06, + "loss": 0.0028, + "step": 45607 + }, + { + "epoch": 14.08, + "learning_rate": 4.247007953024479e-06, + "loss": 0.003, + "step": 45608 + }, + { + "epoch": 14.08, + "learning_rate": 4.246598891995459e-06, + "loss": 0.0035, + "step": 45609 + }, + { + "epoch": 14.09, + "learning_rate": 4.246189845356749e-06, + "loss": 0.0026, + "step": 45610 + }, + { + "epoch": 14.09, + "learning_rate": 4.245780813109363e-06, + "loss": 0.0025, + "step": 45611 + }, + { + "epoch": 14.09, + "learning_rate": 4.24537179525433e-06, + "loss": 0.0036, + "step": 45612 + }, + { + "epoch": 14.09, + "learning_rate": 4.244962791792677e-06, + "loss": 0.0028, + "step": 45613 + }, + { + "epoch": 14.09, + "learning_rate": 4.244553802725415e-06, + "loss": 0.0023, + "step": 45614 + }, + { + "epoch": 14.09, + "learning_rate": 4.244144828053575e-06, + "loss": 0.0046, + "step": 45615 + }, + { + "epoch": 14.09, + "learning_rate": 4.2437358677781805e-06, + "loss": 0.0033, + "step": 45616 + }, + { + "epoch": 14.09, + "learning_rate": 4.2433269219002506e-06, + "loss": 0.0033, + "step": 45617 + }, + { + "epoch": 14.09, + "learning_rate": 4.242917990420812e-06, + "loss": 0.0027, + "step": 45618 + }, + { + "epoch": 14.09, + "learning_rate": 4.242509073340886e-06, + "loss": 0.0028, + "step": 45619 + }, + { + "epoch": 14.09, + "learning_rate": 4.242100170661492e-06, + "loss": 0.003, + "step": 45620 + }, + { + "epoch": 14.09, + "learning_rate": 4.241691282383655e-06, + "loss": 0.0042, + "step": 45621 + }, + { + "epoch": 14.09, + "learning_rate": 4.241282408508401e-06, + "loss": 0.0029, + "step": 45622 + }, + { + "epoch": 14.09, + "learning_rate": 4.240873549036753e-06, + "loss": 0.0028, + "step": 45623 + }, + { + "epoch": 14.09, + "learning_rate": 4.240464703969725e-06, + "loss": 0.0031, + "step": 45624 + }, + { + "epoch": 14.09, + "learning_rate": 4.2400558733083486e-06, + "loss": 0.0038, + "step": 45625 + }, + { + "epoch": 14.09, + "learning_rate": 4.23964705705364e-06, + "loss": 0.0029, + "step": 45626 + }, + { + "epoch": 14.09, + "learning_rate": 4.239238255206624e-06, + "loss": 0.0036, + "step": 45627 + }, + { + "epoch": 14.09, + "learning_rate": 4.238829467768329e-06, + "loss": 0.0029, + "step": 45628 + }, + { + "epoch": 14.09, + "learning_rate": 4.23842069473977e-06, + "loss": 0.0029, + "step": 45629 + }, + { + "epoch": 14.09, + "learning_rate": 4.238011936121969e-06, + "loss": 0.0034, + "step": 45630 + }, + { + "epoch": 14.09, + "learning_rate": 4.237603191915955e-06, + "loss": 0.0041, + "step": 45631 + }, + { + "epoch": 14.09, + "learning_rate": 4.237194462122744e-06, + "loss": 0.0028, + "step": 45632 + }, + { + "epoch": 14.09, + "learning_rate": 4.2367857467433625e-06, + "loss": 0.0049, + "step": 45633 + }, + { + "epoch": 14.09, + "learning_rate": 4.236377045778832e-06, + "loss": 0.0029, + "step": 45634 + }, + { + "epoch": 14.09, + "learning_rate": 4.235968359230169e-06, + "loss": 0.0032, + "step": 45635 + }, + { + "epoch": 14.09, + "learning_rate": 4.235559687098402e-06, + "loss": 0.004, + "step": 45636 + }, + { + "epoch": 14.09, + "learning_rate": 4.235151029384551e-06, + "loss": 0.0035, + "step": 45637 + }, + { + "epoch": 14.09, + "learning_rate": 4.234742386089642e-06, + "loss": 0.003, + "step": 45638 + }, + { + "epoch": 14.09, + "learning_rate": 4.234333757214694e-06, + "loss": 0.0036, + "step": 45639 + }, + { + "epoch": 14.09, + "learning_rate": 4.2339251427607255e-06, + "loss": 0.0029, + "step": 45640 + }, + { + "epoch": 14.09, + "learning_rate": 4.233516542728765e-06, + "loss": 0.0022, + "step": 45641 + }, + { + "epoch": 14.1, + "learning_rate": 4.233107957119827e-06, + "loss": 0.0026, + "step": 45642 + }, + { + "epoch": 14.1, + "learning_rate": 4.232699385934943e-06, + "loss": 0.0027, + "step": 45643 + }, + { + "epoch": 14.1, + "learning_rate": 4.232290829175129e-06, + "loss": 0.003, + "step": 45644 + }, + { + "epoch": 14.1, + "learning_rate": 4.231882286841405e-06, + "loss": 0.0031, + "step": 45645 + }, + { + "epoch": 14.1, + "learning_rate": 4.231473758934793e-06, + "loss": 0.0038, + "step": 45646 + }, + { + "epoch": 14.1, + "learning_rate": 4.231065245456323e-06, + "loss": 0.0039, + "step": 45647 + }, + { + "epoch": 14.1, + "learning_rate": 4.230656746407007e-06, + "loss": 0.0026, + "step": 45648 + }, + { + "epoch": 14.1, + "learning_rate": 4.230248261787874e-06, + "loss": 0.003, + "step": 45649 + }, + { + "epoch": 14.1, + "learning_rate": 4.229839791599942e-06, + "loss": 0.0028, + "step": 45650 + }, + { + "epoch": 14.1, + "learning_rate": 4.2294313358442305e-06, + "loss": 0.0034, + "step": 45651 + }, + { + "epoch": 14.1, + "learning_rate": 4.229022894521763e-06, + "loss": 0.0033, + "step": 45652 + }, + { + "epoch": 14.1, + "learning_rate": 4.228614467633566e-06, + "loss": 0.0046, + "step": 45653 + }, + { + "epoch": 14.1, + "learning_rate": 4.228206055180656e-06, + "loss": 0.0025, + "step": 45654 + }, + { + "epoch": 14.1, + "learning_rate": 4.227797657164052e-06, + "loss": 0.0035, + "step": 45655 + }, + { + "epoch": 14.1, + "learning_rate": 4.227389273584783e-06, + "loss": 0.0039, + "step": 45656 + }, + { + "epoch": 14.1, + "learning_rate": 4.226980904443863e-06, + "loss": 0.003, + "step": 45657 + }, + { + "epoch": 14.1, + "learning_rate": 4.226572549742316e-06, + "loss": 0.0038, + "step": 45658 + }, + { + "epoch": 14.1, + "learning_rate": 4.226164209481168e-06, + "loss": 0.0027, + "step": 45659 + }, + { + "epoch": 14.1, + "learning_rate": 4.225755883661436e-06, + "loss": 0.0029, + "step": 45660 + }, + { + "epoch": 14.1, + "learning_rate": 4.225347572284137e-06, + "loss": 0.0035, + "step": 45661 + }, + { + "epoch": 14.1, + "learning_rate": 4.224939275350303e-06, + "loss": 0.0026, + "step": 45662 + }, + { + "epoch": 14.1, + "learning_rate": 4.224530992860944e-06, + "loss": 0.0036, + "step": 45663 + }, + { + "epoch": 14.1, + "learning_rate": 4.22412272481709e-06, + "loss": 0.003, + "step": 45664 + }, + { + "epoch": 14.1, + "learning_rate": 4.22371447121976e-06, + "loss": 0.0035, + "step": 45665 + }, + { + "epoch": 14.1, + "learning_rate": 4.223306232069968e-06, + "loss": 0.0029, + "step": 45666 + }, + { + "epoch": 14.1, + "learning_rate": 4.222898007368742e-06, + "loss": 0.0036, + "step": 45667 + }, + { + "epoch": 14.1, + "learning_rate": 4.222489797117106e-06, + "loss": 0.0027, + "step": 45668 + }, + { + "epoch": 14.1, + "learning_rate": 4.222081601316071e-06, + "loss": 0.0033, + "step": 45669 + }, + { + "epoch": 14.1, + "learning_rate": 4.221673419966669e-06, + "loss": 0.0029, + "step": 45670 + }, + { + "epoch": 14.1, + "learning_rate": 4.2212652530699105e-06, + "loss": 0.0033, + "step": 45671 + }, + { + "epoch": 14.1, + "learning_rate": 4.220857100626826e-06, + "loss": 0.004, + "step": 45672 + }, + { + "epoch": 14.1, + "learning_rate": 4.22044896263843e-06, + "loss": 0.0035, + "step": 45673 + }, + { + "epoch": 14.1, + "learning_rate": 4.220040839105747e-06, + "loss": 0.0032, + "step": 45674 + }, + { + "epoch": 14.11, + "learning_rate": 4.219632730029795e-06, + "loss": 0.0031, + "step": 45675 + }, + { + "epoch": 14.11, + "learning_rate": 4.219224635411595e-06, + "loss": 0.0025, + "step": 45676 + }, + { + "epoch": 14.11, + "learning_rate": 4.218816555252168e-06, + "loss": 0.0032, + "step": 45677 + }, + { + "epoch": 14.11, + "learning_rate": 4.2184084895525364e-06, + "loss": 0.0029, + "step": 45678 + }, + { + "epoch": 14.11, + "learning_rate": 4.218000438313718e-06, + "loss": 0.0028, + "step": 45679 + }, + { + "epoch": 14.11, + "learning_rate": 4.2175924015367385e-06, + "loss": 0.0025, + "step": 45680 + }, + { + "epoch": 14.11, + "learning_rate": 4.217184379222615e-06, + "loss": 0.0028, + "step": 45681 + }, + { + "epoch": 14.11, + "learning_rate": 4.216776371372365e-06, + "loss": 0.0037, + "step": 45682 + }, + { + "epoch": 14.11, + "learning_rate": 4.216368377987011e-06, + "loss": 0.0034, + "step": 45683 + }, + { + "epoch": 14.11, + "learning_rate": 4.215960399067579e-06, + "loss": 0.0028, + "step": 45684 + }, + { + "epoch": 14.11, + "learning_rate": 4.215552434615085e-06, + "loss": 0.0041, + "step": 45685 + }, + { + "epoch": 14.11, + "learning_rate": 4.215144484630545e-06, + "loss": 0.0034, + "step": 45686 + }, + { + "epoch": 14.11, + "learning_rate": 4.214736549114988e-06, + "loss": 0.003, + "step": 45687 + }, + { + "epoch": 14.11, + "learning_rate": 4.214328628069426e-06, + "loss": 0.0033, + "step": 45688 + }, + { + "epoch": 14.11, + "learning_rate": 4.213920721494884e-06, + "loss": 0.0034, + "step": 45689 + }, + { + "epoch": 14.11, + "learning_rate": 4.213512829392384e-06, + "loss": 0.0029, + "step": 45690 + }, + { + "epoch": 14.11, + "learning_rate": 4.213104951762945e-06, + "loss": 0.0037, + "step": 45691 + }, + { + "epoch": 14.11, + "learning_rate": 4.212697088607583e-06, + "loss": 0.0037, + "step": 45692 + }, + { + "epoch": 14.11, + "learning_rate": 4.212289239927323e-06, + "loss": 0.0034, + "step": 45693 + }, + { + "epoch": 14.11, + "learning_rate": 4.21188140572318e-06, + "loss": 0.0027, + "step": 45694 + }, + { + "epoch": 14.11, + "learning_rate": 4.211473585996182e-06, + "loss": 0.0035, + "step": 45695 + }, + { + "epoch": 14.11, + "learning_rate": 4.211065780747343e-06, + "loss": 0.0046, + "step": 45696 + }, + { + "epoch": 14.11, + "learning_rate": 4.210657989977681e-06, + "loss": 0.0039, + "step": 45697 + }, + { + "epoch": 14.11, + "learning_rate": 4.210250213688219e-06, + "loss": 0.0033, + "step": 45698 + }, + { + "epoch": 14.11, + "learning_rate": 4.2098424518799815e-06, + "loss": 0.004, + "step": 45699 + }, + { + "epoch": 14.11, + "learning_rate": 4.209434704553981e-06, + "loss": 0.0044, + "step": 45700 + }, + { + "epoch": 14.11, + "learning_rate": 4.209026971711243e-06, + "loss": 0.0037, + "step": 45701 + }, + { + "epoch": 14.11, + "learning_rate": 4.208619253352785e-06, + "loss": 0.0028, + "step": 45702 + }, + { + "epoch": 14.11, + "learning_rate": 4.208211549479624e-06, + "loss": 0.0039, + "step": 45703 + }, + { + "epoch": 14.11, + "learning_rate": 4.20780386009278e-06, + "loss": 0.0034, + "step": 45704 + }, + { + "epoch": 14.11, + "learning_rate": 4.207396185193281e-06, + "loss": 0.0037, + "step": 45705 + }, + { + "epoch": 14.11, + "learning_rate": 4.206988524782138e-06, + "loss": 0.0034, + "step": 45706 + }, + { + "epoch": 14.12, + "learning_rate": 4.206580878860372e-06, + "loss": 0.0037, + "step": 45707 + }, + { + "epoch": 14.12, + "learning_rate": 4.206173247429003e-06, + "loss": 0.0048, + "step": 45708 + }, + { + "epoch": 14.12, + "learning_rate": 4.2057656304890545e-06, + "loss": 0.003, + "step": 45709 + }, + { + "epoch": 14.12, + "learning_rate": 4.20535802804154e-06, + "loss": 0.003, + "step": 45710 + }, + { + "epoch": 14.12, + "learning_rate": 4.204950440087486e-06, + "loss": 0.0032, + "step": 45711 + }, + { + "epoch": 14.12, + "learning_rate": 4.204542866627908e-06, + "loss": 0.0036, + "step": 45712 + }, + { + "epoch": 14.12, + "learning_rate": 4.204135307663821e-06, + "loss": 0.0026, + "step": 45713 + }, + { + "epoch": 14.12, + "learning_rate": 4.203727763196249e-06, + "loss": 0.0029, + "step": 45714 + }, + { + "epoch": 14.12, + "learning_rate": 4.203320233226215e-06, + "loss": 0.0033, + "step": 45715 + }, + { + "epoch": 14.12, + "learning_rate": 4.202912717754734e-06, + "loss": 0.0027, + "step": 45716 + }, + { + "epoch": 14.12, + "learning_rate": 4.2025052167828205e-06, + "loss": 0.0029, + "step": 45717 + }, + { + "epoch": 14.12, + "learning_rate": 4.202097730311504e-06, + "loss": 0.0031, + "step": 45718 + }, + { + "epoch": 14.12, + "learning_rate": 4.201690258341795e-06, + "loss": 0.0041, + "step": 45719 + }, + { + "epoch": 14.12, + "learning_rate": 4.201282800874715e-06, + "loss": 0.0027, + "step": 45720 + }, + { + "epoch": 14.12, + "learning_rate": 4.200875357911294e-06, + "loss": 0.0031, + "step": 45721 + }, + { + "epoch": 14.12, + "learning_rate": 4.200467929452532e-06, + "loss": 0.0039, + "step": 45722 + }, + { + "epoch": 14.12, + "learning_rate": 4.200060515499458e-06, + "loss": 0.0032, + "step": 45723 + }, + { + "epoch": 14.12, + "learning_rate": 4.199653116053094e-06, + "loss": 0.0037, + "step": 45724 + }, + { + "epoch": 14.12, + "learning_rate": 4.199245731114453e-06, + "loss": 0.003, + "step": 45725 + }, + { + "epoch": 14.12, + "learning_rate": 4.198838360684558e-06, + "loss": 0.003, + "step": 45726 + }, + { + "epoch": 14.12, + "learning_rate": 4.198431004764428e-06, + "loss": 0.0033, + "step": 45727 + }, + { + "epoch": 14.12, + "learning_rate": 4.1980236633550765e-06, + "loss": 0.0035, + "step": 45728 + }, + { + "epoch": 14.12, + "learning_rate": 4.197616336457525e-06, + "loss": 0.0028, + "step": 45729 + }, + { + "epoch": 14.12, + "learning_rate": 4.197209024072798e-06, + "loss": 0.003, + "step": 45730 + }, + { + "epoch": 14.12, + "learning_rate": 4.196801726201909e-06, + "loss": 0.0035, + "step": 45731 + }, + { + "epoch": 14.12, + "learning_rate": 4.1963944428458735e-06, + "loss": 0.0023, + "step": 45732 + }, + { + "epoch": 14.12, + "learning_rate": 4.195987174005718e-06, + "loss": 0.003, + "step": 45733 + }, + { + "epoch": 14.12, + "learning_rate": 4.195579919682454e-06, + "loss": 0.0031, + "step": 45734 + }, + { + "epoch": 14.12, + "learning_rate": 4.195172679877103e-06, + "loss": 0.0033, + "step": 45735 + }, + { + "epoch": 14.12, + "learning_rate": 4.194765454590687e-06, + "loss": 0.0033, + "step": 45736 + }, + { + "epoch": 14.12, + "learning_rate": 4.194358243824222e-06, + "loss": 0.003, + "step": 45737 + }, + { + "epoch": 14.12, + "learning_rate": 4.193951047578722e-06, + "loss": 0.0023, + "step": 45738 + }, + { + "epoch": 14.13, + "learning_rate": 4.1935438658552084e-06, + "loss": 0.0027, + "step": 45739 + }, + { + "epoch": 14.13, + "learning_rate": 4.193136698654706e-06, + "loss": 0.0031, + "step": 45740 + }, + { + "epoch": 14.13, + "learning_rate": 4.1927295459782236e-06, + "loss": 0.0031, + "step": 45741 + }, + { + "epoch": 14.13, + "learning_rate": 4.1923224078267865e-06, + "loss": 0.0036, + "step": 45742 + }, + { + "epoch": 14.13, + "learning_rate": 4.191915284201411e-06, + "loss": 0.0031, + "step": 45743 + }, + { + "epoch": 14.13, + "learning_rate": 4.191508175103112e-06, + "loss": 0.0026, + "step": 45744 + }, + { + "epoch": 14.13, + "learning_rate": 4.191101080532909e-06, + "loss": 0.0032, + "step": 45745 + }, + { + "epoch": 14.13, + "learning_rate": 4.190694000491826e-06, + "loss": 0.0041, + "step": 45746 + }, + { + "epoch": 14.13, + "learning_rate": 4.1902869349808775e-06, + "loss": 0.0033, + "step": 45747 + }, + { + "epoch": 14.13, + "learning_rate": 4.1898798840010755e-06, + "loss": 0.0025, + "step": 45748 + }, + { + "epoch": 14.13, + "learning_rate": 4.1894728475534485e-06, + "loss": 0.003, + "step": 45749 + }, + { + "epoch": 14.13, + "learning_rate": 4.189065825639006e-06, + "loss": 0.0035, + "step": 45750 + }, + { + "epoch": 14.13, + "learning_rate": 4.188658818258769e-06, + "loss": 0.0026, + "step": 45751 + }, + { + "epoch": 14.13, + "learning_rate": 4.188251825413765e-06, + "loss": 0.0031, + "step": 45752 + }, + { + "epoch": 14.13, + "learning_rate": 4.1878448471049945e-06, + "loss": 0.0033, + "step": 45753 + }, + { + "epoch": 14.13, + "learning_rate": 4.187437883333485e-06, + "loss": 0.0029, + "step": 45754 + }, + { + "epoch": 14.13, + "learning_rate": 4.187030934100257e-06, + "loss": 0.0026, + "step": 45755 + }, + { + "epoch": 14.13, + "learning_rate": 4.186623999406321e-06, + "loss": 0.0031, + "step": 45756 + }, + { + "epoch": 14.13, + "learning_rate": 4.186217079252703e-06, + "loss": 0.0031, + "step": 45757 + }, + { + "epoch": 14.13, + "learning_rate": 4.185810173640415e-06, + "loss": 0.0027, + "step": 45758 + }, + { + "epoch": 14.13, + "learning_rate": 4.185403282570473e-06, + "loss": 0.003, + "step": 45759 + }, + { + "epoch": 14.13, + "learning_rate": 4.184996406043899e-06, + "loss": 0.0024, + "step": 45760 + }, + { + "epoch": 14.13, + "learning_rate": 4.184589544061711e-06, + "loss": 0.003, + "step": 45761 + }, + { + "epoch": 14.13, + "learning_rate": 4.184182696624928e-06, + "loss": 0.0037, + "step": 45762 + }, + { + "epoch": 14.13, + "learning_rate": 4.1837758637345595e-06, + "loss": 0.0032, + "step": 45763 + }, + { + "epoch": 14.13, + "learning_rate": 4.183369045391632e-06, + "loss": 0.0029, + "step": 45764 + }, + { + "epoch": 14.13, + "learning_rate": 4.182962241597156e-06, + "loss": 0.0032, + "step": 45765 + }, + { + "epoch": 14.13, + "learning_rate": 4.1825554523521524e-06, + "loss": 0.0028, + "step": 45766 + }, + { + "epoch": 14.13, + "learning_rate": 4.182148677657643e-06, + "loss": 0.0038, + "step": 45767 + }, + { + "epoch": 14.13, + "learning_rate": 4.18174191751464e-06, + "loss": 0.0043, + "step": 45768 + }, + { + "epoch": 14.13, + "learning_rate": 4.181335171924158e-06, + "loss": 0.0026, + "step": 45769 + }, + { + "epoch": 14.13, + "learning_rate": 4.180928440887219e-06, + "loss": 0.0036, + "step": 45770 + }, + { + "epoch": 14.13, + "learning_rate": 4.180521724404842e-06, + "loss": 0.0029, + "step": 45771 + }, + { + "epoch": 14.14, + "learning_rate": 4.1801150224780405e-06, + "loss": 0.0035, + "step": 45772 + }, + { + "epoch": 14.14, + "learning_rate": 4.17970833510783e-06, + "loss": 0.0033, + "step": 45773 + }, + { + "epoch": 14.14, + "learning_rate": 4.179301662295235e-06, + "loss": 0.0035, + "step": 45774 + }, + { + "epoch": 14.14, + "learning_rate": 4.178895004041265e-06, + "loss": 0.0033, + "step": 45775 + }, + { + "epoch": 14.14, + "learning_rate": 4.17848836034694e-06, + "loss": 0.0031, + "step": 45776 + }, + { + "epoch": 14.14, + "learning_rate": 4.178081731213279e-06, + "loss": 0.0032, + "step": 45777 + }, + { + "epoch": 14.14, + "learning_rate": 4.1776751166413e-06, + "loss": 0.0032, + "step": 45778 + }, + { + "epoch": 14.14, + "learning_rate": 4.177268516632012e-06, + "loss": 0.0036, + "step": 45779 + }, + { + "epoch": 14.14, + "learning_rate": 4.176861931186442e-06, + "loss": 0.0032, + "step": 45780 + }, + { + "epoch": 14.14, + "learning_rate": 4.176455360305598e-06, + "loss": 0.0032, + "step": 45781 + }, + { + "epoch": 14.14, + "learning_rate": 4.1760488039905055e-06, + "loss": 0.0032, + "step": 45782 + }, + { + "epoch": 14.14, + "learning_rate": 4.175642262242177e-06, + "loss": 0.0026, + "step": 45783 + }, + { + "epoch": 14.14, + "learning_rate": 4.175235735061627e-06, + "loss": 0.0027, + "step": 45784 + }, + { + "epoch": 14.14, + "learning_rate": 4.174829222449873e-06, + "loss": 0.0029, + "step": 45785 + }, + { + "epoch": 14.14, + "learning_rate": 4.174422724407938e-06, + "loss": 0.0032, + "step": 45786 + }, + { + "epoch": 14.14, + "learning_rate": 4.174016240936831e-06, + "loss": 0.0034, + "step": 45787 + }, + { + "epoch": 14.14, + "learning_rate": 4.173609772037575e-06, + "loss": 0.0025, + "step": 45788 + }, + { + "epoch": 14.14, + "learning_rate": 4.173203317711184e-06, + "loss": 0.0033, + "step": 45789 + }, + { + "epoch": 14.14, + "learning_rate": 4.17279687795867e-06, + "loss": 0.0028, + "step": 45790 + }, + { + "epoch": 14.14, + "learning_rate": 4.172390452781055e-06, + "loss": 0.0026, + "step": 45791 + }, + { + "epoch": 14.14, + "learning_rate": 4.171984042179357e-06, + "loss": 0.0038, + "step": 45792 + }, + { + "epoch": 14.14, + "learning_rate": 4.17157764615459e-06, + "loss": 0.0044, + "step": 45793 + }, + { + "epoch": 14.14, + "learning_rate": 4.171171264707767e-06, + "loss": 0.0037, + "step": 45794 + }, + { + "epoch": 14.14, + "learning_rate": 4.170764897839912e-06, + "loss": 0.003, + "step": 45795 + }, + { + "epoch": 14.14, + "learning_rate": 4.170358545552032e-06, + "loss": 0.0035, + "step": 45796 + }, + { + "epoch": 14.14, + "learning_rate": 4.169952207845149e-06, + "loss": 0.0031, + "step": 45797 + }, + { + "epoch": 14.14, + "learning_rate": 4.1695458847202826e-06, + "loss": 0.0031, + "step": 45798 + }, + { + "epoch": 14.14, + "learning_rate": 4.169139576178446e-06, + "loss": 0.0033, + "step": 45799 + }, + { + "epoch": 14.14, + "learning_rate": 4.168733282220652e-06, + "loss": 0.0022, + "step": 45800 + }, + { + "epoch": 14.14, + "learning_rate": 4.168327002847917e-06, + "loss": 0.0031, + "step": 45801 + }, + { + "epoch": 14.14, + "learning_rate": 4.167920738061265e-06, + "loss": 0.0031, + "step": 45802 + }, + { + "epoch": 14.14, + "learning_rate": 4.167514487861707e-06, + "loss": 0.0034, + "step": 45803 + }, + { + "epoch": 14.15, + "learning_rate": 4.167108252250255e-06, + "loss": 0.0038, + "step": 45804 + }, + { + "epoch": 14.15, + "learning_rate": 4.166702031227934e-06, + "loss": 0.0032, + "step": 45805 + }, + { + "epoch": 14.15, + "learning_rate": 4.16629582479575e-06, + "loss": 0.0034, + "step": 45806 + }, + { + "epoch": 14.15, + "learning_rate": 4.165889632954724e-06, + "loss": 0.0024, + "step": 45807 + }, + { + "epoch": 14.15, + "learning_rate": 4.165483455705877e-06, + "loss": 0.0032, + "step": 45808 + }, + { + "epoch": 14.15, + "learning_rate": 4.1650772930502196e-06, + "loss": 0.0035, + "step": 45809 + }, + { + "epoch": 14.15, + "learning_rate": 4.164671144988763e-06, + "loss": 0.0027, + "step": 45810 + }, + { + "epoch": 14.15, + "learning_rate": 4.164265011522533e-06, + "loss": 0.003, + "step": 45811 + }, + { + "epoch": 14.15, + "learning_rate": 4.163858892652538e-06, + "loss": 0.0033, + "step": 45812 + }, + { + "epoch": 14.15, + "learning_rate": 4.163452788379798e-06, + "loss": 0.0036, + "step": 45813 + }, + { + "epoch": 14.15, + "learning_rate": 4.163046698705329e-06, + "loss": 0.0029, + "step": 45814 + }, + { + "epoch": 14.15, + "learning_rate": 4.162640623630139e-06, + "loss": 0.0044, + "step": 45815 + }, + { + "epoch": 14.15, + "learning_rate": 4.162234563155252e-06, + "loss": 0.0039, + "step": 45816 + }, + { + "epoch": 14.15, + "learning_rate": 4.161828517281683e-06, + "loss": 0.0026, + "step": 45817 + }, + { + "epoch": 14.15, + "learning_rate": 4.161422486010442e-06, + "loss": 0.0034, + "step": 45818 + }, + { + "epoch": 14.15, + "learning_rate": 4.161016469342553e-06, + "loss": 0.004, + "step": 45819 + }, + { + "epoch": 14.15, + "learning_rate": 4.160610467279026e-06, + "loss": 0.0037, + "step": 45820 + }, + { + "epoch": 14.15, + "learning_rate": 4.160204479820874e-06, + "loss": 0.0031, + "step": 45821 + }, + { + "epoch": 14.15, + "learning_rate": 4.159798506969115e-06, + "loss": 0.0027, + "step": 45822 + }, + { + "epoch": 14.15, + "learning_rate": 4.15939254872477e-06, + "loss": 0.0039, + "step": 45823 + }, + { + "epoch": 14.15, + "learning_rate": 4.158986605088849e-06, + "loss": 0.0022, + "step": 45824 + }, + { + "epoch": 14.15, + "learning_rate": 4.158580676062364e-06, + "loss": 0.0034, + "step": 45825 + }, + { + "epoch": 14.15, + "learning_rate": 4.158174761646337e-06, + "loss": 0.0035, + "step": 45826 + }, + { + "epoch": 14.15, + "learning_rate": 4.157768861841778e-06, + "loss": 0.004, + "step": 45827 + }, + { + "epoch": 14.15, + "learning_rate": 4.157362976649704e-06, + "loss": 0.0035, + "step": 45828 + }, + { + "epoch": 14.15, + "learning_rate": 4.156957106071134e-06, + "loss": 0.0027, + "step": 45829 + }, + { + "epoch": 14.15, + "learning_rate": 4.15655125010708e-06, + "loss": 0.0034, + "step": 45830 + }, + { + "epoch": 14.15, + "learning_rate": 4.156145408758555e-06, + "loss": 0.0031, + "step": 45831 + }, + { + "epoch": 14.15, + "learning_rate": 4.155739582026579e-06, + "loss": 0.0027, + "step": 45832 + }, + { + "epoch": 14.15, + "learning_rate": 4.1553337699121595e-06, + "loss": 0.0035, + "step": 45833 + }, + { + "epoch": 14.15, + "learning_rate": 4.154927972416322e-06, + "loss": 0.0052, + "step": 45834 + }, + { + "epoch": 14.15, + "learning_rate": 4.1545221895400704e-06, + "loss": 0.0047, + "step": 45835 + }, + { + "epoch": 14.16, + "learning_rate": 4.1541164212844285e-06, + "loss": 0.003, + "step": 45836 + }, + { + "epoch": 14.16, + "learning_rate": 4.153710667650405e-06, + "loss": 0.0047, + "step": 45837 + }, + { + "epoch": 14.16, + "learning_rate": 4.153304928639017e-06, + "loss": 0.0028, + "step": 45838 + }, + { + "epoch": 14.16, + "learning_rate": 4.152899204251283e-06, + "loss": 0.0032, + "step": 45839 + }, + { + "epoch": 14.16, + "learning_rate": 4.152493494488215e-06, + "loss": 0.0023, + "step": 45840 + }, + { + "epoch": 14.16, + "learning_rate": 4.152087799350823e-06, + "loss": 0.003, + "step": 45841 + }, + { + "epoch": 14.16, + "learning_rate": 4.1516821188401315e-06, + "loss": 0.0034, + "step": 45842 + }, + { + "epoch": 14.16, + "learning_rate": 4.151276452957145e-06, + "loss": 0.0034, + "step": 45843 + }, + { + "epoch": 14.16, + "learning_rate": 4.1508708017028855e-06, + "loss": 0.0034, + "step": 45844 + }, + { + "epoch": 14.16, + "learning_rate": 4.150465165078366e-06, + "loss": 0.0033, + "step": 45845 + }, + { + "epoch": 14.16, + "learning_rate": 4.1500595430845955e-06, + "loss": 0.0033, + "step": 45846 + }, + { + "epoch": 14.16, + "learning_rate": 4.149653935722594e-06, + "loss": 0.0033, + "step": 45847 + }, + { + "epoch": 14.16, + "learning_rate": 4.1492483429933785e-06, + "loss": 0.0036, + "step": 45848 + }, + { + "epoch": 14.16, + "learning_rate": 4.148842764897955e-06, + "loss": 0.0032, + "step": 45849 + }, + { + "epoch": 14.16, + "learning_rate": 4.148437201437348e-06, + "loss": 0.0034, + "step": 45850 + }, + { + "epoch": 14.16, + "learning_rate": 4.148031652612567e-06, + "loss": 0.0043, + "step": 45851 + }, + { + "epoch": 14.16, + "learning_rate": 4.147626118424623e-06, + "loss": 0.0036, + "step": 45852 + }, + { + "epoch": 14.16, + "learning_rate": 4.147220598874532e-06, + "loss": 0.0031, + "step": 45853 + }, + { + "epoch": 14.16, + "learning_rate": 4.146815093963313e-06, + "loss": 0.003, + "step": 45854 + }, + { + "epoch": 14.16, + "learning_rate": 4.1464096036919785e-06, + "loss": 0.0026, + "step": 45855 + }, + { + "epoch": 14.16, + "learning_rate": 4.146004128061537e-06, + "loss": 0.0042, + "step": 45856 + }, + { + "epoch": 14.16, + "learning_rate": 4.145598667073011e-06, + "loss": 0.0026, + "step": 45857 + }, + { + "epoch": 14.16, + "learning_rate": 4.145193220727406e-06, + "loss": 0.0037, + "step": 45858 + }, + { + "epoch": 14.16, + "learning_rate": 4.1447877890257415e-06, + "loss": 0.0031, + "step": 45859 + }, + { + "epoch": 14.16, + "learning_rate": 4.144382371969037e-06, + "loss": 0.0025, + "step": 45860 + }, + { + "epoch": 14.16, + "learning_rate": 4.143976969558293e-06, + "loss": 0.0022, + "step": 45861 + }, + { + "epoch": 14.16, + "learning_rate": 4.143571581794531e-06, + "loss": 0.0031, + "step": 45862 + }, + { + "epoch": 14.16, + "learning_rate": 4.143166208678768e-06, + "loss": 0.0039, + "step": 45863 + }, + { + "epoch": 14.16, + "learning_rate": 4.142760850212012e-06, + "loss": 0.0026, + "step": 45864 + }, + { + "epoch": 14.16, + "learning_rate": 4.142355506395283e-06, + "loss": 0.0031, + "step": 45865 + }, + { + "epoch": 14.16, + "learning_rate": 4.141950177229585e-06, + "loss": 0.004, + "step": 45866 + }, + { + "epoch": 14.16, + "learning_rate": 4.141544862715945e-06, + "loss": 0.0038, + "step": 45867 + }, + { + "epoch": 14.16, + "learning_rate": 4.141139562855364e-06, + "loss": 0.0041, + "step": 45868 + }, + { + "epoch": 14.17, + "learning_rate": 4.1407342776488625e-06, + "loss": 0.0026, + "step": 45869 + }, + { + "epoch": 14.17, + "learning_rate": 4.14032900709746e-06, + "loss": 0.0027, + "step": 45870 + }, + { + "epoch": 14.17, + "learning_rate": 4.139923751202157e-06, + "loss": 0.0041, + "step": 45871 + }, + { + "epoch": 14.17, + "learning_rate": 4.139518509963973e-06, + "loss": 0.0037, + "step": 45872 + }, + { + "epoch": 14.17, + "learning_rate": 4.139113283383925e-06, + "loss": 0.0045, + "step": 45873 + }, + { + "epoch": 14.17, + "learning_rate": 4.138708071463021e-06, + "loss": 0.0028, + "step": 45874 + }, + { + "epoch": 14.17, + "learning_rate": 4.13830287420228e-06, + "loss": 0.0033, + "step": 45875 + }, + { + "epoch": 14.17, + "learning_rate": 4.137897691602714e-06, + "loss": 0.0026, + "step": 45876 + }, + { + "epoch": 14.17, + "learning_rate": 4.13749252366533e-06, + "loss": 0.0033, + "step": 45877 + }, + { + "epoch": 14.17, + "learning_rate": 4.1370873703911466e-06, + "loss": 0.0029, + "step": 45878 + }, + { + "epoch": 14.17, + "learning_rate": 4.1366822317811805e-06, + "loss": 0.0031, + "step": 45879 + }, + { + "epoch": 14.17, + "learning_rate": 4.136277107836443e-06, + "loss": 0.0032, + "step": 45880 + }, + { + "epoch": 14.17, + "learning_rate": 4.135871998557941e-06, + "loss": 0.004, + "step": 45881 + }, + { + "epoch": 14.17, + "learning_rate": 4.135466903946697e-06, + "loss": 0.0036, + "step": 45882 + }, + { + "epoch": 14.17, + "learning_rate": 4.135061824003715e-06, + "loss": 0.0031, + "step": 45883 + }, + { + "epoch": 14.17, + "learning_rate": 4.134656758730015e-06, + "loss": 0.0034, + "step": 45884 + }, + { + "epoch": 14.17, + "learning_rate": 4.1342517081266095e-06, + "loss": 0.0039, + "step": 45885 + }, + { + "epoch": 14.17, + "learning_rate": 4.133846672194513e-06, + "loss": 0.0031, + "step": 45886 + }, + { + "epoch": 14.17, + "learning_rate": 4.13344165093473e-06, + "loss": 0.0036, + "step": 45887 + }, + { + "epoch": 14.17, + "learning_rate": 4.133036644348284e-06, + "loss": 0.0036, + "step": 45888 + }, + { + "epoch": 14.17, + "learning_rate": 4.13263165243618e-06, + "loss": 0.003, + "step": 45889 + }, + { + "epoch": 14.17, + "learning_rate": 4.132226675199438e-06, + "loss": 0.004, + "step": 45890 + }, + { + "epoch": 14.17, + "learning_rate": 4.131821712639066e-06, + "loss": 0.0041, + "step": 45891 + }, + { + "epoch": 14.17, + "learning_rate": 4.131416764756075e-06, + "loss": 0.0031, + "step": 45892 + }, + { + "epoch": 14.17, + "learning_rate": 4.131011831551482e-06, + "loss": 0.0038, + "step": 45893 + }, + { + "epoch": 14.17, + "learning_rate": 4.130606913026303e-06, + "loss": 0.0034, + "step": 45894 + }, + { + "epoch": 14.17, + "learning_rate": 4.130202009181542e-06, + "loss": 0.0037, + "step": 45895 + }, + { + "epoch": 14.17, + "learning_rate": 4.129797120018219e-06, + "loss": 0.0027, + "step": 45896 + }, + { + "epoch": 14.17, + "learning_rate": 4.129392245537346e-06, + "loss": 0.0034, + "step": 45897 + }, + { + "epoch": 14.17, + "learning_rate": 4.128987385739929e-06, + "loss": 0.0033, + "step": 45898 + }, + { + "epoch": 14.17, + "learning_rate": 4.128582540626985e-06, + "loss": 0.0046, + "step": 45899 + }, + { + "epoch": 14.17, + "learning_rate": 4.128177710199532e-06, + "loss": 0.0032, + "step": 45900 + }, + { + "epoch": 14.18, + "learning_rate": 4.127772894458576e-06, + "loss": 0.0038, + "step": 45901 + }, + { + "epoch": 14.18, + "learning_rate": 4.127368093405129e-06, + "loss": 0.0039, + "step": 45902 + }, + { + "epoch": 14.18, + "learning_rate": 4.126963307040204e-06, + "loss": 0.0038, + "step": 45903 + }, + { + "epoch": 14.18, + "learning_rate": 4.126558535364819e-06, + "loss": 0.0035, + "step": 45904 + }, + { + "epoch": 14.18, + "learning_rate": 4.126153778379978e-06, + "loss": 0.0039, + "step": 45905 + }, + { + "epoch": 14.18, + "learning_rate": 4.125749036086704e-06, + "loss": 0.0037, + "step": 45906 + }, + { + "epoch": 14.18, + "learning_rate": 4.125344308486e-06, + "loss": 0.0035, + "step": 45907 + }, + { + "epoch": 14.18, + "learning_rate": 4.12493959557888e-06, + "loss": 0.004, + "step": 45908 + }, + { + "epoch": 14.18, + "learning_rate": 4.124534897366356e-06, + "loss": 0.0045, + "step": 45909 + }, + { + "epoch": 14.18, + "learning_rate": 4.124130213849446e-06, + "loss": 0.0035, + "step": 45910 + }, + { + "epoch": 14.18, + "learning_rate": 4.123725545029158e-06, + "loss": 0.0028, + "step": 45911 + }, + { + "epoch": 14.18, + "learning_rate": 4.123320890906501e-06, + "loss": 0.0035, + "step": 45912 + }, + { + "epoch": 14.18, + "learning_rate": 4.122916251482494e-06, + "loss": 0.0043, + "step": 45913 + }, + { + "epoch": 14.18, + "learning_rate": 4.1225116267581414e-06, + "loss": 0.0031, + "step": 45914 + }, + { + "epoch": 14.18, + "learning_rate": 4.122107016734458e-06, + "loss": 0.0038, + "step": 45915 + }, + { + "epoch": 14.18, + "learning_rate": 4.121702421412463e-06, + "loss": 0.0036, + "step": 45916 + }, + { + "epoch": 14.18, + "learning_rate": 4.12129784079316e-06, + "loss": 0.0024, + "step": 45917 + }, + { + "epoch": 14.18, + "learning_rate": 4.120893274877561e-06, + "loss": 0.0031, + "step": 45918 + }, + { + "epoch": 14.18, + "learning_rate": 4.120488723666683e-06, + "loss": 0.003, + "step": 45919 + }, + { + "epoch": 14.18, + "learning_rate": 4.120084187161533e-06, + "loss": 0.0034, + "step": 45920 + }, + { + "epoch": 14.18, + "learning_rate": 4.119679665363128e-06, + "loss": 0.0036, + "step": 45921 + }, + { + "epoch": 14.18, + "learning_rate": 4.119275158272476e-06, + "loss": 0.004, + "step": 45922 + }, + { + "epoch": 14.18, + "learning_rate": 4.118870665890585e-06, + "loss": 0.0032, + "step": 45923 + }, + { + "epoch": 14.18, + "learning_rate": 4.118466188218473e-06, + "loss": 0.0038, + "step": 45924 + }, + { + "epoch": 14.18, + "learning_rate": 4.118061725257152e-06, + "loss": 0.0023, + "step": 45925 + }, + { + "epoch": 14.18, + "learning_rate": 4.117657277007629e-06, + "loss": 0.0048, + "step": 45926 + }, + { + "epoch": 14.18, + "learning_rate": 4.11725284347092e-06, + "loss": 0.0036, + "step": 45927 + }, + { + "epoch": 14.18, + "learning_rate": 4.116848424648036e-06, + "loss": 0.0029, + "step": 45928 + }, + { + "epoch": 14.18, + "learning_rate": 4.116444020539984e-06, + "loss": 0.0033, + "step": 45929 + }, + { + "epoch": 14.18, + "learning_rate": 4.116039631147777e-06, + "loss": 0.0026, + "step": 45930 + }, + { + "epoch": 14.18, + "learning_rate": 4.115635256472433e-06, + "loss": 0.003, + "step": 45931 + }, + { + "epoch": 14.18, + "learning_rate": 4.1152308965149565e-06, + "loss": 0.0031, + "step": 45932 + }, + { + "epoch": 14.18, + "learning_rate": 4.114826551276358e-06, + "loss": 0.003, + "step": 45933 + }, + { + "epoch": 14.19, + "learning_rate": 4.114422220757654e-06, + "loss": 0.0035, + "step": 45934 + }, + { + "epoch": 14.19, + "learning_rate": 4.114017904959854e-06, + "loss": 0.0035, + "step": 45935 + }, + { + "epoch": 14.19, + "learning_rate": 4.113613603883967e-06, + "loss": 0.0035, + "step": 45936 + }, + { + "epoch": 14.19, + "learning_rate": 4.113209317531008e-06, + "loss": 0.0028, + "step": 45937 + }, + { + "epoch": 14.19, + "learning_rate": 4.112805045901989e-06, + "loss": 0.0033, + "step": 45938 + }, + { + "epoch": 14.19, + "learning_rate": 4.112400788997912e-06, + "loss": 0.0043, + "step": 45939 + }, + { + "epoch": 14.19, + "learning_rate": 4.1119965468197955e-06, + "loss": 0.0034, + "step": 45940 + }, + { + "epoch": 14.19, + "learning_rate": 4.111592319368654e-06, + "loss": 0.0034, + "step": 45941 + }, + { + "epoch": 14.19, + "learning_rate": 4.111188106645492e-06, + "loss": 0.0032, + "step": 45942 + }, + { + "epoch": 14.19, + "learning_rate": 4.11078390865132e-06, + "loss": 0.0033, + "step": 45943 + }, + { + "epoch": 14.19, + "learning_rate": 4.1103797253871556e-06, + "loss": 0.0029, + "step": 45944 + }, + { + "epoch": 14.19, + "learning_rate": 4.109975556854003e-06, + "loss": 0.0032, + "step": 45945 + }, + { + "epoch": 14.19, + "learning_rate": 4.109571403052874e-06, + "loss": 0.0034, + "step": 45946 + }, + { + "epoch": 14.19, + "learning_rate": 4.109167263984785e-06, + "loss": 0.0029, + "step": 45947 + }, + { + "epoch": 14.19, + "learning_rate": 4.108763139650743e-06, + "loss": 0.0029, + "step": 45948 + }, + { + "epoch": 14.19, + "learning_rate": 4.108359030051756e-06, + "loss": 0.0026, + "step": 45949 + }, + { + "epoch": 14.19, + "learning_rate": 4.107954935188842e-06, + "loss": 0.0038, + "step": 45950 + }, + { + "epoch": 14.19, + "learning_rate": 4.107550855063003e-06, + "loss": 0.0072, + "step": 45951 + }, + { + "epoch": 14.19, + "learning_rate": 4.1071467896752575e-06, + "loss": 0.0049, + "step": 45952 + }, + { + "epoch": 14.19, + "learning_rate": 4.106742739026612e-06, + "loss": 0.0039, + "step": 45953 + }, + { + "epoch": 14.19, + "learning_rate": 4.106338703118075e-06, + "loss": 0.0035, + "step": 45954 + }, + { + "epoch": 14.19, + "learning_rate": 4.10593468195066e-06, + "loss": 0.0033, + "step": 45955 + }, + { + "epoch": 14.19, + "learning_rate": 4.10553067552538e-06, + "loss": 0.0039, + "step": 45956 + }, + { + "epoch": 14.19, + "learning_rate": 4.10512668384324e-06, + "loss": 0.0033, + "step": 45957 + }, + { + "epoch": 14.19, + "learning_rate": 4.104722706905256e-06, + "loss": 0.0036, + "step": 45958 + }, + { + "epoch": 14.19, + "learning_rate": 4.104318744712438e-06, + "loss": 0.0033, + "step": 45959 + }, + { + "epoch": 14.19, + "learning_rate": 4.103914797265789e-06, + "loss": 0.0046, + "step": 45960 + }, + { + "epoch": 14.19, + "learning_rate": 4.103510864566324e-06, + "loss": 0.0029, + "step": 45961 + }, + { + "epoch": 14.19, + "learning_rate": 4.103106946615058e-06, + "loss": 0.0027, + "step": 45962 + }, + { + "epoch": 14.19, + "learning_rate": 4.102703043412997e-06, + "loss": 0.0026, + "step": 45963 + }, + { + "epoch": 14.19, + "learning_rate": 4.1022991549611475e-06, + "loss": 0.0045, + "step": 45964 + }, + { + "epoch": 14.19, + "learning_rate": 4.101895281260524e-06, + "loss": 0.0035, + "step": 45965 + }, + { + "epoch": 14.2, + "learning_rate": 4.101491422312139e-06, + "loss": 0.0031, + "step": 45966 + }, + { + "epoch": 14.2, + "learning_rate": 4.1010875781169965e-06, + "loss": 0.0042, + "step": 45967 + }, + { + "epoch": 14.2, + "learning_rate": 4.100683748676114e-06, + "loss": 0.0021, + "step": 45968 + }, + { + "epoch": 14.2, + "learning_rate": 4.100279933990496e-06, + "loss": 0.0031, + "step": 45969 + }, + { + "epoch": 14.2, + "learning_rate": 4.099876134061153e-06, + "loss": 0.0032, + "step": 45970 + }, + { + "epoch": 14.2, + "learning_rate": 4.099472348889093e-06, + "loss": 0.0047, + "step": 45971 + }, + { + "epoch": 14.2, + "learning_rate": 4.099068578475333e-06, + "loss": 0.0036, + "step": 45972 + }, + { + "epoch": 14.2, + "learning_rate": 4.098664822820881e-06, + "loss": 0.004, + "step": 45973 + }, + { + "epoch": 14.2, + "learning_rate": 4.098261081926739e-06, + "loss": 0.0035, + "step": 45974 + }, + { + "epoch": 14.2, + "learning_rate": 4.097857355793926e-06, + "loss": 0.0027, + "step": 45975 + }, + { + "epoch": 14.2, + "learning_rate": 4.097453644423445e-06, + "loss": 0.0021, + "step": 45976 + }, + { + "epoch": 14.2, + "learning_rate": 4.097049947816309e-06, + "loss": 0.0037, + "step": 45977 + }, + { + "epoch": 14.2, + "learning_rate": 4.096646265973535e-06, + "loss": 0.0032, + "step": 45978 + }, + { + "epoch": 14.2, + "learning_rate": 4.096242598896119e-06, + "loss": 0.0027, + "step": 45979 + }, + { + "epoch": 14.2, + "learning_rate": 4.095838946585076e-06, + "loss": 0.0025, + "step": 45980 + }, + { + "epoch": 14.2, + "learning_rate": 4.09543530904142e-06, + "loss": 0.0031, + "step": 45981 + }, + { + "epoch": 14.2, + "learning_rate": 4.095031686266154e-06, + "loss": 0.0029, + "step": 45982 + }, + { + "epoch": 14.2, + "learning_rate": 4.094628078260294e-06, + "loss": 0.004, + "step": 45983 + }, + { + "epoch": 14.2, + "learning_rate": 4.094224485024847e-06, + "loss": 0.0037, + "step": 45984 + }, + { + "epoch": 14.2, + "learning_rate": 4.093820906560818e-06, + "loss": 0.0027, + "step": 45985 + }, + { + "epoch": 14.2, + "learning_rate": 4.09341734286922e-06, + "loss": 0.0042, + "step": 45986 + }, + { + "epoch": 14.2, + "learning_rate": 4.093013793951066e-06, + "loss": 0.0032, + "step": 45987 + }, + { + "epoch": 14.2, + "learning_rate": 4.092610259807362e-06, + "loss": 0.0034, + "step": 45988 + }, + { + "epoch": 14.2, + "learning_rate": 4.092206740439113e-06, + "loss": 0.0032, + "step": 45989 + }, + { + "epoch": 14.2, + "learning_rate": 4.091803235847337e-06, + "loss": 0.0031, + "step": 45990 + }, + { + "epoch": 14.2, + "learning_rate": 4.091399746033034e-06, + "loss": 0.0029, + "step": 45991 + }, + { + "epoch": 14.2, + "learning_rate": 4.090996270997219e-06, + "loss": 0.0036, + "step": 45992 + }, + { + "epoch": 14.2, + "learning_rate": 4.090592810740903e-06, + "loss": 0.0026, + "step": 45993 + }, + { + "epoch": 14.2, + "learning_rate": 4.090189365265092e-06, + "loss": 0.0027, + "step": 45994 + }, + { + "epoch": 14.2, + "learning_rate": 4.089785934570792e-06, + "loss": 0.0035, + "step": 45995 + }, + { + "epoch": 14.2, + "learning_rate": 4.08938251865902e-06, + "loss": 0.0038, + "step": 45996 + }, + { + "epoch": 14.2, + "learning_rate": 4.088979117530776e-06, + "loss": 0.004, + "step": 45997 + }, + { + "epoch": 14.21, + "learning_rate": 4.088575731187073e-06, + "loss": 0.0034, + "step": 45998 + }, + { + "epoch": 14.21, + "learning_rate": 4.088172359628924e-06, + "loss": 0.0037, + "step": 45999 + }, + { + "epoch": 14.21, + "learning_rate": 4.087769002857334e-06, + "loss": 0.0036, + "step": 46000 + }, + { + "epoch": 14.21, + "learning_rate": 4.087365660873308e-06, + "loss": 0.0033, + "step": 46001 + }, + { + "epoch": 14.21, + "learning_rate": 4.08696233367786e-06, + "loss": 0.0034, + "step": 46002 + }, + { + "epoch": 14.21, + "learning_rate": 4.086559021272e-06, + "loss": 0.0048, + "step": 46003 + }, + { + "epoch": 14.21, + "learning_rate": 4.086155723656735e-06, + "loss": 0.0035, + "step": 46004 + }, + { + "epoch": 14.21, + "learning_rate": 4.085752440833071e-06, + "loss": 0.0021, + "step": 46005 + }, + { + "epoch": 14.21, + "learning_rate": 4.08534917280202e-06, + "loss": 0.0037, + "step": 46006 + }, + { + "epoch": 14.21, + "learning_rate": 4.084945919564588e-06, + "loss": 0.0028, + "step": 46007 + }, + { + "epoch": 14.21, + "learning_rate": 4.084542681121784e-06, + "loss": 0.0038, + "step": 46008 + }, + { + "epoch": 14.21, + "learning_rate": 4.0841394574746255e-06, + "loss": 0.0025, + "step": 46009 + }, + { + "epoch": 14.21, + "learning_rate": 4.083736248624105e-06, + "loss": 0.0036, + "step": 46010 + }, + { + "epoch": 14.21, + "learning_rate": 4.083333054571239e-06, + "loss": 0.0025, + "step": 46011 + }, + { + "epoch": 14.21, + "learning_rate": 4.082929875317041e-06, + "loss": 0.0032, + "step": 46012 + }, + { + "epoch": 14.21, + "learning_rate": 4.08252671086251e-06, + "loss": 0.0034, + "step": 46013 + }, + { + "epoch": 14.21, + "learning_rate": 4.082123561208663e-06, + "loss": 0.0028, + "step": 46014 + }, + { + "epoch": 14.21, + "learning_rate": 4.081720426356505e-06, + "loss": 0.0044, + "step": 46015 + }, + { + "epoch": 14.21, + "learning_rate": 4.0813173063070385e-06, + "loss": 0.0029, + "step": 46016 + }, + { + "epoch": 14.21, + "learning_rate": 4.080914201061278e-06, + "loss": 0.0045, + "step": 46017 + }, + { + "epoch": 14.21, + "learning_rate": 4.080511110620235e-06, + "loss": 0.0029, + "step": 46018 + }, + { + "epoch": 14.21, + "learning_rate": 4.080108034984912e-06, + "loss": 0.0034, + "step": 46019 + }, + { + "epoch": 14.21, + "learning_rate": 4.079704974156315e-06, + "loss": 0.0031, + "step": 46020 + }, + { + "epoch": 14.21, + "learning_rate": 4.0793019281354595e-06, + "loss": 0.0036, + "step": 46021 + }, + { + "epoch": 14.21, + "learning_rate": 4.078898896923347e-06, + "loss": 0.0031, + "step": 46022 + }, + { + "epoch": 14.21, + "learning_rate": 4.078495880520987e-06, + "loss": 0.0036, + "step": 46023 + }, + { + "epoch": 14.21, + "learning_rate": 4.078092878929393e-06, + "loss": 0.0039, + "step": 46024 + }, + { + "epoch": 14.21, + "learning_rate": 4.077689892149569e-06, + "loss": 0.0038, + "step": 46025 + }, + { + "epoch": 14.21, + "learning_rate": 4.077286920182519e-06, + "loss": 0.0034, + "step": 46026 + }, + { + "epoch": 14.21, + "learning_rate": 4.076883963029258e-06, + "loss": 0.0031, + "step": 46027 + }, + { + "epoch": 14.21, + "learning_rate": 4.076481020690787e-06, + "loss": 0.0035, + "step": 46028 + }, + { + "epoch": 14.21, + "learning_rate": 4.076078093168121e-06, + "loss": 0.0038, + "step": 46029 + }, + { + "epoch": 14.21, + "learning_rate": 4.0756751804622606e-06, + "loss": 0.0025, + "step": 46030 + }, + { + "epoch": 14.22, + "learning_rate": 4.075272282574221e-06, + "loss": 0.0029, + "step": 46031 + }, + { + "epoch": 14.22, + "learning_rate": 4.074869399505001e-06, + "loss": 0.0032, + "step": 46032 + }, + { + "epoch": 14.22, + "learning_rate": 4.0744665312556154e-06, + "loss": 0.003, + "step": 46033 + }, + { + "epoch": 14.22, + "learning_rate": 4.0740636778270726e-06, + "loss": 0.0036, + "step": 46034 + }, + { + "epoch": 14.22, + "learning_rate": 4.073660839220377e-06, + "loss": 0.0036, + "step": 46035 + }, + { + "epoch": 14.22, + "learning_rate": 4.073258015436533e-06, + "loss": 0.0032, + "step": 46036 + }, + { + "epoch": 14.22, + "learning_rate": 4.072855206476555e-06, + "loss": 0.0027, + "step": 46037 + }, + { + "epoch": 14.22, + "learning_rate": 4.072452412341444e-06, + "loss": 0.0045, + "step": 46038 + }, + { + "epoch": 14.22, + "learning_rate": 4.0720496330322144e-06, + "loss": 0.0039, + "step": 46039 + }, + { + "epoch": 14.22, + "learning_rate": 4.07164686854987e-06, + "loss": 0.0031, + "step": 46040 + }, + { + "epoch": 14.22, + "learning_rate": 4.071244118895413e-06, + "loss": 0.0026, + "step": 46041 + }, + { + "epoch": 14.22, + "learning_rate": 4.070841384069857e-06, + "loss": 0.0044, + "step": 46042 + }, + { + "epoch": 14.22, + "learning_rate": 4.0704386640742125e-06, + "loss": 0.0051, + "step": 46043 + }, + { + "epoch": 14.22, + "learning_rate": 4.070035958909477e-06, + "loss": 0.0031, + "step": 46044 + }, + { + "epoch": 14.22, + "learning_rate": 4.0696332685766684e-06, + "loss": 0.003, + "step": 46045 + }, + { + "epoch": 14.22, + "learning_rate": 4.069230593076787e-06, + "loss": 0.0033, + "step": 46046 + }, + { + "epoch": 14.22, + "learning_rate": 4.068827932410839e-06, + "loss": 0.003, + "step": 46047 + }, + { + "epoch": 14.22, + "learning_rate": 4.068425286579833e-06, + "loss": 0.0029, + "step": 46048 + }, + { + "epoch": 14.22, + "learning_rate": 4.068022655584783e-06, + "loss": 0.004, + "step": 46049 + }, + { + "epoch": 14.22, + "learning_rate": 4.067620039426689e-06, + "loss": 0.0032, + "step": 46050 + }, + { + "epoch": 14.22, + "learning_rate": 4.067217438106556e-06, + "loss": 0.0024, + "step": 46051 + }, + { + "epoch": 14.22, + "learning_rate": 4.066814851625397e-06, + "loss": 0.0035, + "step": 46052 + }, + { + "epoch": 14.22, + "learning_rate": 4.066412279984213e-06, + "loss": 0.0034, + "step": 46053 + }, + { + "epoch": 14.22, + "learning_rate": 4.066009723184015e-06, + "loss": 0.003, + "step": 46054 + }, + { + "epoch": 14.22, + "learning_rate": 4.0656071812258116e-06, + "loss": 0.0031, + "step": 46055 + }, + { + "epoch": 14.22, + "learning_rate": 4.065204654110606e-06, + "loss": 0.004, + "step": 46056 + }, + { + "epoch": 14.22, + "learning_rate": 4.064802141839404e-06, + "loss": 0.0031, + "step": 46057 + }, + { + "epoch": 14.22, + "learning_rate": 4.064399644413217e-06, + "loss": 0.0043, + "step": 46058 + }, + { + "epoch": 14.22, + "learning_rate": 4.0639971618330465e-06, + "loss": 0.003, + "step": 46059 + }, + { + "epoch": 14.22, + "learning_rate": 4.063594694099905e-06, + "loss": 0.0035, + "step": 46060 + }, + { + "epoch": 14.22, + "learning_rate": 4.063192241214796e-06, + "loss": 0.0034, + "step": 46061 + }, + { + "epoch": 14.22, + "learning_rate": 4.062789803178723e-06, + "loss": 0.003, + "step": 46062 + }, + { + "epoch": 14.23, + "learning_rate": 4.062387379992694e-06, + "loss": 0.0025, + "step": 46063 + }, + { + "epoch": 14.23, + "learning_rate": 4.061984971657718e-06, + "loss": 0.0042, + "step": 46064 + }, + { + "epoch": 14.23, + "learning_rate": 4.061582578174804e-06, + "loss": 0.0029, + "step": 46065 + }, + { + "epoch": 14.23, + "learning_rate": 4.061180199544955e-06, + "loss": 0.0053, + "step": 46066 + }, + { + "epoch": 14.23, + "learning_rate": 4.060777835769174e-06, + "loss": 0.003, + "step": 46067 + }, + { + "epoch": 14.23, + "learning_rate": 4.060375486848475e-06, + "loss": 0.0038, + "step": 46068 + }, + { + "epoch": 14.23, + "learning_rate": 4.059973152783856e-06, + "loss": 0.0038, + "step": 46069 + }, + { + "epoch": 14.23, + "learning_rate": 4.059570833576332e-06, + "loss": 0.0029, + "step": 46070 + }, + { + "epoch": 14.23, + "learning_rate": 4.059168529226904e-06, + "loss": 0.0042, + "step": 46071 + }, + { + "epoch": 14.23, + "learning_rate": 4.058766239736576e-06, + "loss": 0.0034, + "step": 46072 + }, + { + "epoch": 14.23, + "learning_rate": 4.058363965106356e-06, + "loss": 0.0038, + "step": 46073 + }, + { + "epoch": 14.23, + "learning_rate": 4.057961705337256e-06, + "loss": 0.0031, + "step": 46074 + }, + { + "epoch": 14.23, + "learning_rate": 4.057559460430274e-06, + "loss": 0.0032, + "step": 46075 + }, + { + "epoch": 14.23, + "learning_rate": 4.057157230386422e-06, + "loss": 0.0031, + "step": 46076 + }, + { + "epoch": 14.23, + "learning_rate": 4.056755015206705e-06, + "loss": 0.003, + "step": 46077 + }, + { + "epoch": 14.23, + "learning_rate": 4.056352814892124e-06, + "loss": 0.0037, + "step": 46078 + }, + { + "epoch": 14.23, + "learning_rate": 4.055950629443689e-06, + "loss": 0.0033, + "step": 46079 + }, + { + "epoch": 14.23, + "learning_rate": 4.055548458862408e-06, + "loss": 0.0035, + "step": 46080 + }, + { + "epoch": 14.23, + "learning_rate": 4.055146303149286e-06, + "loss": 0.003, + "step": 46081 + }, + { + "epoch": 14.23, + "learning_rate": 4.054744162305322e-06, + "loss": 0.0023, + "step": 46082 + }, + { + "epoch": 14.23, + "learning_rate": 4.054342036331532e-06, + "loss": 0.003, + "step": 46083 + }, + { + "epoch": 14.23, + "learning_rate": 4.053939925228913e-06, + "loss": 0.0027, + "step": 46084 + }, + { + "epoch": 14.23, + "learning_rate": 4.053537828998475e-06, + "loss": 0.0049, + "step": 46085 + }, + { + "epoch": 14.23, + "learning_rate": 4.053135747641227e-06, + "loss": 0.0027, + "step": 46086 + }, + { + "epoch": 14.23, + "learning_rate": 4.0527336811581706e-06, + "loss": 0.003, + "step": 46087 + }, + { + "epoch": 14.23, + "learning_rate": 4.052331629550309e-06, + "loss": 0.0023, + "step": 46088 + }, + { + "epoch": 14.23, + "learning_rate": 4.051929592818654e-06, + "loss": 0.0028, + "step": 46089 + }, + { + "epoch": 14.23, + "learning_rate": 4.051527570964205e-06, + "loss": 0.0031, + "step": 46090 + }, + { + "epoch": 14.23, + "learning_rate": 4.051125563987973e-06, + "loss": 0.0024, + "step": 46091 + }, + { + "epoch": 14.23, + "learning_rate": 4.050723571890962e-06, + "loss": 0.0029, + "step": 46092 + }, + { + "epoch": 14.23, + "learning_rate": 4.050321594674172e-06, + "loss": 0.0033, + "step": 46093 + }, + { + "epoch": 14.23, + "learning_rate": 4.049919632338613e-06, + "loss": 0.0034, + "step": 46094 + }, + { + "epoch": 14.23, + "learning_rate": 4.049517684885291e-06, + "loss": 0.0027, + "step": 46095 + }, + { + "epoch": 14.24, + "learning_rate": 4.0491157523152134e-06, + "loss": 0.003, + "step": 46096 + }, + { + "epoch": 14.24, + "learning_rate": 4.0487138346293835e-06, + "loss": 0.0029, + "step": 46097 + }, + { + "epoch": 14.24, + "learning_rate": 4.0483119318288014e-06, + "loss": 0.0027, + "step": 46098 + }, + { + "epoch": 14.24, + "learning_rate": 4.04791004391448e-06, + "loss": 0.0028, + "step": 46099 + }, + { + "epoch": 14.24, + "learning_rate": 4.047508170887419e-06, + "loss": 0.0035, + "step": 46100 + }, + { + "epoch": 14.24, + "learning_rate": 4.047106312748628e-06, + "loss": 0.0026, + "step": 46101 + }, + { + "epoch": 14.24, + "learning_rate": 4.04670446949911e-06, + "loss": 0.0034, + "step": 46102 + }, + { + "epoch": 14.24, + "learning_rate": 4.046302641139867e-06, + "loss": 0.003, + "step": 46103 + }, + { + "epoch": 14.24, + "learning_rate": 4.045900827671906e-06, + "loss": 0.0028, + "step": 46104 + }, + { + "epoch": 14.24, + "learning_rate": 4.045499029096237e-06, + "loss": 0.0044, + "step": 46105 + }, + { + "epoch": 14.24, + "learning_rate": 4.045097245413858e-06, + "loss": 0.0037, + "step": 46106 + }, + { + "epoch": 14.24, + "learning_rate": 4.044695476625779e-06, + "loss": 0.0033, + "step": 46107 + }, + { + "epoch": 14.24, + "learning_rate": 4.044293722733005e-06, + "loss": 0.003, + "step": 46108 + }, + { + "epoch": 14.24, + "learning_rate": 4.043891983736533e-06, + "loss": 0.0035, + "step": 46109 + }, + { + "epoch": 14.24, + "learning_rate": 4.043490259637375e-06, + "loss": 0.0027, + "step": 46110 + }, + { + "epoch": 14.24, + "learning_rate": 4.043088550436537e-06, + "loss": 0.0044, + "step": 46111 + }, + { + "epoch": 14.24, + "learning_rate": 4.0426868561350205e-06, + "loss": 0.0038, + "step": 46112 + }, + { + "epoch": 14.24, + "learning_rate": 4.042285176733828e-06, + "loss": 0.0035, + "step": 46113 + }, + { + "epoch": 14.24, + "learning_rate": 4.0418835122339705e-06, + "loss": 0.0044, + "step": 46114 + }, + { + "epoch": 14.24, + "learning_rate": 4.041481862636445e-06, + "loss": 0.003, + "step": 46115 + }, + { + "epoch": 14.24, + "learning_rate": 4.04108022794226e-06, + "loss": 0.0031, + "step": 46116 + }, + { + "epoch": 14.24, + "learning_rate": 4.040678608152428e-06, + "loss": 0.0046, + "step": 46117 + }, + { + "epoch": 14.24, + "learning_rate": 4.040277003267938e-06, + "loss": 0.0026, + "step": 46118 + }, + { + "epoch": 14.24, + "learning_rate": 4.0398754132898036e-06, + "loss": 0.0033, + "step": 46119 + }, + { + "epoch": 14.24, + "learning_rate": 4.039473838219029e-06, + "loss": 0.0033, + "step": 46120 + }, + { + "epoch": 14.24, + "learning_rate": 4.039072278056616e-06, + "loss": 0.0035, + "step": 46121 + }, + { + "epoch": 14.24, + "learning_rate": 4.038670732803573e-06, + "loss": 0.0031, + "step": 46122 + }, + { + "epoch": 14.24, + "learning_rate": 4.038269202460902e-06, + "loss": 0.0037, + "step": 46123 + }, + { + "epoch": 14.24, + "learning_rate": 4.037867687029603e-06, + "loss": 0.0028, + "step": 46124 + }, + { + "epoch": 14.24, + "learning_rate": 4.0374661865106845e-06, + "loss": 0.003, + "step": 46125 + }, + { + "epoch": 14.24, + "learning_rate": 4.037064700905155e-06, + "loss": 0.0032, + "step": 46126 + }, + { + "epoch": 14.24, + "learning_rate": 4.036663230214014e-06, + "loss": 0.0034, + "step": 46127 + }, + { + "epoch": 14.25, + "learning_rate": 4.036261774438262e-06, + "loss": 0.0029, + "step": 46128 + }, + { + "epoch": 14.25, + "learning_rate": 4.035860333578907e-06, + "loss": 0.0039, + "step": 46129 + }, + { + "epoch": 14.25, + "learning_rate": 4.035458907636957e-06, + "loss": 0.0036, + "step": 46130 + }, + { + "epoch": 14.25, + "learning_rate": 4.035057496613408e-06, + "loss": 0.0036, + "step": 46131 + }, + { + "epoch": 14.25, + "learning_rate": 4.034656100509272e-06, + "loss": 0.0027, + "step": 46132 + }, + { + "epoch": 14.25, + "learning_rate": 4.034254719325549e-06, + "loss": 0.0037, + "step": 46133 + }, + { + "epoch": 14.25, + "learning_rate": 4.03385335306324e-06, + "loss": 0.0027, + "step": 46134 + }, + { + "epoch": 14.25, + "learning_rate": 4.03345200172335e-06, + "loss": 0.0047, + "step": 46135 + }, + { + "epoch": 14.25, + "learning_rate": 4.03305066530689e-06, + "loss": 0.0029, + "step": 46136 + }, + { + "epoch": 14.25, + "learning_rate": 4.032649343814859e-06, + "loss": 0.004, + "step": 46137 + }, + { + "epoch": 14.25, + "learning_rate": 4.032248037248257e-06, + "loss": 0.0027, + "step": 46138 + }, + { + "epoch": 14.25, + "learning_rate": 4.031846745608093e-06, + "loss": 0.0025, + "step": 46139 + }, + { + "epoch": 14.25, + "learning_rate": 4.031445468895367e-06, + "loss": 0.0035, + "step": 46140 + }, + { + "epoch": 14.25, + "learning_rate": 4.031044207111083e-06, + "loss": 0.0036, + "step": 46141 + }, + { + "epoch": 14.25, + "learning_rate": 4.03064296025625e-06, + "loss": 0.0036, + "step": 46142 + }, + { + "epoch": 14.25, + "learning_rate": 4.030241728331868e-06, + "loss": 0.003, + "step": 46143 + }, + { + "epoch": 14.25, + "learning_rate": 4.029840511338937e-06, + "loss": 0.0038, + "step": 46144 + }, + { + "epoch": 14.25, + "learning_rate": 4.029439309278466e-06, + "loss": 0.0037, + "step": 46145 + }, + { + "epoch": 14.25, + "learning_rate": 4.0290381221514545e-06, + "loss": 0.003, + "step": 46146 + }, + { + "epoch": 14.25, + "learning_rate": 4.028636949958911e-06, + "loss": 0.0027, + "step": 46147 + }, + { + "epoch": 14.25, + "learning_rate": 4.028235792701835e-06, + "loss": 0.0031, + "step": 46148 + }, + { + "epoch": 14.25, + "learning_rate": 4.027834650381226e-06, + "loss": 0.0042, + "step": 46149 + }, + { + "epoch": 14.25, + "learning_rate": 4.027433522998093e-06, + "loss": 0.0033, + "step": 46150 + }, + { + "epoch": 14.25, + "learning_rate": 4.027032410553442e-06, + "loss": 0.003, + "step": 46151 + }, + { + "epoch": 14.25, + "learning_rate": 4.026631313048268e-06, + "loss": 0.0027, + "step": 46152 + }, + { + "epoch": 14.25, + "learning_rate": 4.026230230483582e-06, + "loss": 0.0029, + "step": 46153 + }, + { + "epoch": 14.25, + "learning_rate": 4.025829162860384e-06, + "loss": 0.0041, + "step": 46154 + }, + { + "epoch": 14.25, + "learning_rate": 4.025428110179674e-06, + "loss": 0.0032, + "step": 46155 + }, + { + "epoch": 14.25, + "learning_rate": 4.0250270724424565e-06, + "loss": 0.0032, + "step": 46156 + }, + { + "epoch": 14.25, + "learning_rate": 4.02462604964974e-06, + "loss": 0.0023, + "step": 46157 + }, + { + "epoch": 14.25, + "learning_rate": 4.024225041802524e-06, + "loss": 0.0034, + "step": 46158 + }, + { + "epoch": 14.25, + "learning_rate": 4.023824048901809e-06, + "loss": 0.0036, + "step": 46159 + }, + { + "epoch": 14.26, + "learning_rate": 4.023423070948601e-06, + "loss": 0.0029, + "step": 46160 + }, + { + "epoch": 14.26, + "learning_rate": 4.023022107943901e-06, + "loss": 0.0046, + "step": 46161 + }, + { + "epoch": 14.26, + "learning_rate": 4.02262115988871e-06, + "loss": 0.0042, + "step": 46162 + }, + { + "epoch": 14.26, + "learning_rate": 4.02222022678404e-06, + "loss": 0.0035, + "step": 46163 + }, + { + "epoch": 14.26, + "learning_rate": 4.021819308630886e-06, + "loss": 0.0027, + "step": 46164 + }, + { + "epoch": 14.26, + "learning_rate": 4.021418405430249e-06, + "loss": 0.0032, + "step": 46165 + }, + { + "epoch": 14.26, + "learning_rate": 4.021017517183134e-06, + "loss": 0.0031, + "step": 46166 + }, + { + "epoch": 14.26, + "learning_rate": 4.020616643890549e-06, + "loss": 0.0029, + "step": 46167 + }, + { + "epoch": 14.26, + "learning_rate": 4.020215785553493e-06, + "loss": 0.0024, + "step": 46168 + }, + { + "epoch": 14.26, + "learning_rate": 4.0198149421729635e-06, + "loss": 0.0034, + "step": 46169 + }, + { + "epoch": 14.26, + "learning_rate": 4.019414113749971e-06, + "loss": 0.0028, + "step": 46170 + }, + { + "epoch": 14.26, + "learning_rate": 4.0190133002855115e-06, + "loss": 0.003, + "step": 46171 + }, + { + "epoch": 14.26, + "learning_rate": 4.018612501780591e-06, + "loss": 0.0036, + "step": 46172 + }, + { + "epoch": 14.26, + "learning_rate": 4.018211718236215e-06, + "loss": 0.0035, + "step": 46173 + }, + { + "epoch": 14.26, + "learning_rate": 4.017810949653381e-06, + "loss": 0.0032, + "step": 46174 + }, + { + "epoch": 14.26, + "learning_rate": 4.017410196033091e-06, + "loss": 0.003, + "step": 46175 + }, + { + "epoch": 14.26, + "learning_rate": 4.0170094573763526e-06, + "loss": 0.0034, + "step": 46176 + }, + { + "epoch": 14.26, + "learning_rate": 4.01660873368416e-06, + "loss": 0.0041, + "step": 46177 + }, + { + "epoch": 14.26, + "learning_rate": 4.016208024957527e-06, + "loss": 0.0037, + "step": 46178 + }, + { + "epoch": 14.26, + "learning_rate": 4.015807331197445e-06, + "loss": 0.0029, + "step": 46179 + }, + { + "epoch": 14.26, + "learning_rate": 4.0154066524049196e-06, + "loss": 0.0034, + "step": 46180 + }, + { + "epoch": 14.26, + "learning_rate": 4.015005988580953e-06, + "loss": 0.0038, + "step": 46181 + }, + { + "epoch": 14.26, + "learning_rate": 4.014605339726551e-06, + "loss": 0.0029, + "step": 46182 + }, + { + "epoch": 14.26, + "learning_rate": 4.014204705842709e-06, + "loss": 0.0036, + "step": 46183 + }, + { + "epoch": 14.26, + "learning_rate": 4.013804086930437e-06, + "loss": 0.0031, + "step": 46184 + }, + { + "epoch": 14.26, + "learning_rate": 4.013403482990733e-06, + "loss": 0.0027, + "step": 46185 + }, + { + "epoch": 14.26, + "learning_rate": 4.0130028940245945e-06, + "loss": 0.0028, + "step": 46186 + }, + { + "epoch": 14.26, + "learning_rate": 4.012602320033028e-06, + "loss": 0.0038, + "step": 46187 + }, + { + "epoch": 14.26, + "learning_rate": 4.012201761017039e-06, + "loss": 0.0022, + "step": 46188 + }, + { + "epoch": 14.26, + "learning_rate": 4.0118012169776256e-06, + "loss": 0.0031, + "step": 46189 + }, + { + "epoch": 14.26, + "learning_rate": 4.011400687915785e-06, + "loss": 0.0028, + "step": 46190 + }, + { + "epoch": 14.26, + "learning_rate": 4.011000173832527e-06, + "loss": 0.003, + "step": 46191 + }, + { + "epoch": 14.26, + "learning_rate": 4.010599674728848e-06, + "loss": 0.0029, + "step": 46192 + }, + { + "epoch": 14.27, + "learning_rate": 4.0101991906057505e-06, + "loss": 0.0034, + "step": 46193 + }, + { + "epoch": 14.27, + "learning_rate": 4.009798721464241e-06, + "loss": 0.0035, + "step": 46194 + }, + { + "epoch": 14.27, + "learning_rate": 4.009398267305318e-06, + "loss": 0.0031, + "step": 46195 + }, + { + "epoch": 14.27, + "learning_rate": 4.008997828129978e-06, + "loss": 0.0027, + "step": 46196 + }, + { + "epoch": 14.27, + "learning_rate": 4.0085974039392274e-06, + "loss": 0.0029, + "step": 46197 + }, + { + "epoch": 14.27, + "learning_rate": 4.008196994734072e-06, + "loss": 0.003, + "step": 46198 + }, + { + "epoch": 14.27, + "learning_rate": 4.007796600515506e-06, + "loss": 0.0035, + "step": 46199 + }, + { + "epoch": 14.27, + "learning_rate": 4.007396221284533e-06, + "loss": 0.0036, + "step": 46200 + }, + { + "epoch": 14.27, + "learning_rate": 4.006995857042157e-06, + "loss": 0.0047, + "step": 46201 + }, + { + "epoch": 14.27, + "learning_rate": 4.006595507789374e-06, + "loss": 0.0036, + "step": 46202 + }, + { + "epoch": 14.27, + "learning_rate": 4.006195173527191e-06, + "loss": 0.0041, + "step": 46203 + }, + { + "epoch": 14.27, + "learning_rate": 4.005794854256609e-06, + "loss": 0.0026, + "step": 46204 + }, + { + "epoch": 14.27, + "learning_rate": 4.0053945499786265e-06, + "loss": 0.0033, + "step": 46205 + }, + { + "epoch": 14.27, + "learning_rate": 4.004994260694242e-06, + "loss": 0.0035, + "step": 46206 + }, + { + "epoch": 14.27, + "learning_rate": 4.004593986404465e-06, + "loss": 0.0033, + "step": 46207 + }, + { + "epoch": 14.27, + "learning_rate": 4.004193727110288e-06, + "loss": 0.0035, + "step": 46208 + }, + { + "epoch": 14.27, + "learning_rate": 4.003793482812719e-06, + "loss": 0.0032, + "step": 46209 + }, + { + "epoch": 14.27, + "learning_rate": 4.003393253512757e-06, + "loss": 0.003, + "step": 46210 + }, + { + "epoch": 14.27, + "learning_rate": 4.002993039211398e-06, + "loss": 0.0036, + "step": 46211 + }, + { + "epoch": 14.27, + "learning_rate": 4.002592839909648e-06, + "loss": 0.0039, + "step": 46212 + }, + { + "epoch": 14.27, + "learning_rate": 4.00219265560851e-06, + "loss": 0.0031, + "step": 46213 + }, + { + "epoch": 14.27, + "learning_rate": 4.0017924863089786e-06, + "loss": 0.0047, + "step": 46214 + }, + { + "epoch": 14.27, + "learning_rate": 4.001392332012062e-06, + "loss": 0.0029, + "step": 46215 + }, + { + "epoch": 14.27, + "learning_rate": 4.0009921927187565e-06, + "loss": 0.0039, + "step": 46216 + }, + { + "epoch": 14.27, + "learning_rate": 4.000592068430061e-06, + "loss": 0.0042, + "step": 46217 + }, + { + "epoch": 14.27, + "learning_rate": 4.000191959146979e-06, + "loss": 0.0025, + "step": 46218 + }, + { + "epoch": 14.27, + "learning_rate": 3.999791864870515e-06, + "loss": 0.0028, + "step": 46219 + }, + { + "epoch": 14.27, + "learning_rate": 3.999391785601665e-06, + "loss": 0.0034, + "step": 46220 + }, + { + "epoch": 14.27, + "learning_rate": 3.998991721341427e-06, + "loss": 0.0041, + "step": 46221 + }, + { + "epoch": 14.27, + "learning_rate": 3.99859167209081e-06, + "loss": 0.0039, + "step": 46222 + }, + { + "epoch": 14.27, + "learning_rate": 3.998191637850806e-06, + "loss": 0.0046, + "step": 46223 + }, + { + "epoch": 14.27, + "learning_rate": 3.997791618622418e-06, + "loss": 0.0035, + "step": 46224 + }, + { + "epoch": 14.28, + "learning_rate": 3.997391614406656e-06, + "loss": 0.0029, + "step": 46225 + }, + { + "epoch": 14.28, + "learning_rate": 3.996991625204505e-06, + "loss": 0.0033, + "step": 46226 + }, + { + "epoch": 14.28, + "learning_rate": 3.996591651016973e-06, + "loss": 0.003, + "step": 46227 + }, + { + "epoch": 14.28, + "learning_rate": 3.996191691845061e-06, + "loss": 0.0031, + "step": 46228 + }, + { + "epoch": 14.28, + "learning_rate": 3.99579174768977e-06, + "loss": 0.0032, + "step": 46229 + }, + { + "epoch": 14.28, + "learning_rate": 3.995391818552101e-06, + "loss": 0.003, + "step": 46230 + }, + { + "epoch": 14.28, + "learning_rate": 3.9949919044330474e-06, + "loss": 0.0031, + "step": 46231 + }, + { + "epoch": 14.28, + "learning_rate": 3.994592005333619e-06, + "loss": 0.0036, + "step": 46232 + }, + { + "epoch": 14.28, + "learning_rate": 3.994192121254807e-06, + "loss": 0.0038, + "step": 46233 + }, + { + "epoch": 14.28, + "learning_rate": 3.993792252197615e-06, + "loss": 0.0037, + "step": 46234 + }, + { + "epoch": 14.28, + "learning_rate": 3.993392398163053e-06, + "loss": 0.0034, + "step": 46235 + }, + { + "epoch": 14.28, + "learning_rate": 3.992992559152105e-06, + "loss": 0.0038, + "step": 46236 + }, + { + "epoch": 14.28, + "learning_rate": 3.992592735165776e-06, + "loss": 0.0029, + "step": 46237 + }, + { + "epoch": 14.28, + "learning_rate": 3.992192926205074e-06, + "loss": 0.0029, + "step": 46238 + }, + { + "epoch": 14.28, + "learning_rate": 3.991793132270989e-06, + "loss": 0.0045, + "step": 46239 + }, + { + "epoch": 14.28, + "learning_rate": 3.991393353364529e-06, + "loss": 0.0031, + "step": 46240 + }, + { + "epoch": 14.28, + "learning_rate": 3.990993589486691e-06, + "loss": 0.003, + "step": 46241 + }, + { + "epoch": 14.28, + "learning_rate": 3.990593840638468e-06, + "loss": 0.0032, + "step": 46242 + }, + { + "epoch": 14.28, + "learning_rate": 3.990194106820867e-06, + "loss": 0.0033, + "step": 46243 + }, + { + "epoch": 14.28, + "learning_rate": 3.989794388034891e-06, + "loss": 0.0034, + "step": 46244 + }, + { + "epoch": 14.28, + "learning_rate": 3.989394684281534e-06, + "loss": 0.0039, + "step": 46245 + }, + { + "epoch": 14.28, + "learning_rate": 3.988994995561795e-06, + "loss": 0.0025, + "step": 46246 + }, + { + "epoch": 14.28, + "learning_rate": 3.98859532187668e-06, + "loss": 0.0041, + "step": 46247 + }, + { + "epoch": 14.28, + "learning_rate": 3.988195663227179e-06, + "loss": 0.0044, + "step": 46248 + }, + { + "epoch": 14.28, + "learning_rate": 3.987796019614297e-06, + "loss": 0.0026, + "step": 46249 + }, + { + "epoch": 14.28, + "learning_rate": 3.987396391039039e-06, + "loss": 0.0037, + "step": 46250 + }, + { + "epoch": 14.28, + "learning_rate": 3.986996777502398e-06, + "loss": 0.0031, + "step": 46251 + }, + { + "epoch": 14.28, + "learning_rate": 3.986597179005371e-06, + "loss": 0.0028, + "step": 46252 + }, + { + "epoch": 14.28, + "learning_rate": 3.986197595548966e-06, + "loss": 0.0032, + "step": 46253 + }, + { + "epoch": 14.28, + "learning_rate": 3.985798027134173e-06, + "loss": 0.0035, + "step": 46254 + }, + { + "epoch": 14.28, + "learning_rate": 3.9853984737619975e-06, + "loss": 0.0038, + "step": 46255 + }, + { + "epoch": 14.28, + "learning_rate": 3.984998935433444e-06, + "loss": 0.0029, + "step": 46256 + }, + { + "epoch": 14.29, + "learning_rate": 3.984599412149497e-06, + "loss": 0.0026, + "step": 46257 + }, + { + "epoch": 14.29, + "learning_rate": 3.9841999039111644e-06, + "loss": 0.0031, + "step": 46258 + }, + { + "epoch": 14.29, + "learning_rate": 3.983800410719446e-06, + "loss": 0.0029, + "step": 46259 + }, + { + "epoch": 14.29, + "learning_rate": 3.983400932575343e-06, + "loss": 0.0032, + "step": 46260 + }, + { + "epoch": 14.29, + "learning_rate": 3.983001469479852e-06, + "loss": 0.0024, + "step": 46261 + }, + { + "epoch": 14.29, + "learning_rate": 3.982602021433967e-06, + "loss": 0.003, + "step": 46262 + }, + { + "epoch": 14.29, + "learning_rate": 3.982202588438697e-06, + "loss": 0.0026, + "step": 46263 + }, + { + "epoch": 14.29, + "learning_rate": 3.9818031704950315e-06, + "loss": 0.0027, + "step": 46264 + }, + { + "epoch": 14.29, + "learning_rate": 3.981403767603974e-06, + "loss": 0.0034, + "step": 46265 + }, + { + "epoch": 14.29, + "learning_rate": 3.98100437976653e-06, + "loss": 0.0038, + "step": 46266 + }, + { + "epoch": 14.29, + "learning_rate": 3.980605006983686e-06, + "loss": 0.0035, + "step": 46267 + }, + { + "epoch": 14.29, + "learning_rate": 3.980205649256445e-06, + "loss": 0.0032, + "step": 46268 + }, + { + "epoch": 14.29, + "learning_rate": 3.9798063065858124e-06, + "loss": 0.0034, + "step": 46269 + }, + { + "epoch": 14.29, + "learning_rate": 3.9794069789727785e-06, + "loss": 0.0036, + "step": 46270 + }, + { + "epoch": 14.29, + "learning_rate": 3.9790076664183496e-06, + "loss": 0.0031, + "step": 46271 + }, + { + "epoch": 14.29, + "learning_rate": 3.97860836892352e-06, + "loss": 0.0026, + "step": 46272 + }, + { + "epoch": 14.29, + "learning_rate": 3.9782090864892865e-06, + "loss": 0.0043, + "step": 46273 + }, + { + "epoch": 14.29, + "learning_rate": 3.97780981911665e-06, + "loss": 0.0033, + "step": 46274 + }, + { + "epoch": 14.29, + "learning_rate": 3.977410566806613e-06, + "loss": 0.0031, + "step": 46275 + }, + { + "epoch": 14.29, + "learning_rate": 3.977011329560171e-06, + "loss": 0.003, + "step": 46276 + }, + { + "epoch": 14.29, + "learning_rate": 3.976612107378317e-06, + "loss": 0.0049, + "step": 46277 + }, + { + "epoch": 14.29, + "learning_rate": 3.97621290026206e-06, + "loss": 0.0027, + "step": 46278 + }, + { + "epoch": 14.29, + "learning_rate": 3.9758137082123896e-06, + "loss": 0.0039, + "step": 46279 + }, + { + "epoch": 14.29, + "learning_rate": 3.975414531230307e-06, + "loss": 0.0035, + "step": 46280 + }, + { + "epoch": 14.29, + "learning_rate": 3.975015369316816e-06, + "loss": 0.0031, + "step": 46281 + }, + { + "epoch": 14.29, + "learning_rate": 3.974616222472909e-06, + "loss": 0.0055, + "step": 46282 + }, + { + "epoch": 14.29, + "learning_rate": 3.974217090699584e-06, + "loss": 0.0035, + "step": 46283 + }, + { + "epoch": 14.29, + "learning_rate": 3.973817973997844e-06, + "loss": 0.003, + "step": 46284 + }, + { + "epoch": 14.29, + "learning_rate": 3.973418872368679e-06, + "loss": 0.0034, + "step": 46285 + }, + { + "epoch": 14.29, + "learning_rate": 3.973019785813098e-06, + "loss": 0.0026, + "step": 46286 + }, + { + "epoch": 14.29, + "learning_rate": 3.972620714332094e-06, + "loss": 0.0036, + "step": 46287 + }, + { + "epoch": 14.29, + "learning_rate": 3.972221657926661e-06, + "loss": 0.0039, + "step": 46288 + }, + { + "epoch": 14.29, + "learning_rate": 3.9718226165978e-06, + "loss": 0.0038, + "step": 46289 + }, + { + "epoch": 14.3, + "learning_rate": 3.9714235903465144e-06, + "loss": 0.0024, + "step": 46290 + }, + { + "epoch": 14.3, + "learning_rate": 3.971024579173794e-06, + "loss": 0.0035, + "step": 46291 + }, + { + "epoch": 14.3, + "learning_rate": 3.970625583080646e-06, + "loss": 0.0031, + "step": 46292 + }, + { + "epoch": 14.3, + "learning_rate": 3.970226602068058e-06, + "loss": 0.0041, + "step": 46293 + }, + { + "epoch": 14.3, + "learning_rate": 3.969827636137037e-06, + "loss": 0.0031, + "step": 46294 + }, + { + "epoch": 14.3, + "learning_rate": 3.969428685288573e-06, + "loss": 0.0032, + "step": 46295 + }, + { + "epoch": 14.3, + "learning_rate": 3.969029749523672e-06, + "loss": 0.0029, + "step": 46296 + }, + { + "epoch": 14.3, + "learning_rate": 3.968630828843327e-06, + "loss": 0.004, + "step": 46297 + }, + { + "epoch": 14.3, + "learning_rate": 3.968231923248533e-06, + "loss": 0.0037, + "step": 46298 + }, + { + "epoch": 14.3, + "learning_rate": 3.9678330327402915e-06, + "loss": 0.003, + "step": 46299 + }, + { + "epoch": 14.3, + "learning_rate": 3.967434157319603e-06, + "loss": 0.0039, + "step": 46300 + }, + { + "epoch": 14.3, + "learning_rate": 3.967035296987458e-06, + "loss": 0.0033, + "step": 46301 + }, + { + "epoch": 14.3, + "learning_rate": 3.966636451744862e-06, + "loss": 0.0028, + "step": 46302 + }, + { + "epoch": 14.3, + "learning_rate": 3.966237621592809e-06, + "loss": 0.0027, + "step": 46303 + }, + { + "epoch": 14.3, + "learning_rate": 3.965838806532291e-06, + "loss": 0.0036, + "step": 46304 + }, + { + "epoch": 14.3, + "learning_rate": 3.965440006564313e-06, + "loss": 0.0035, + "step": 46305 + }, + { + "epoch": 14.3, + "learning_rate": 3.965041221689872e-06, + "loss": 0.003, + "step": 46306 + }, + { + "epoch": 14.3, + "learning_rate": 3.964642451909965e-06, + "loss": 0.0033, + "step": 46307 + }, + { + "epoch": 14.3, + "learning_rate": 3.964243697225582e-06, + "loss": 0.0044, + "step": 46308 + }, + { + "epoch": 14.3, + "learning_rate": 3.963844957637732e-06, + "loss": 0.0035, + "step": 46309 + }, + { + "epoch": 14.3, + "learning_rate": 3.9634462331474036e-06, + "loss": 0.0036, + "step": 46310 + }, + { + "epoch": 14.3, + "learning_rate": 3.963047523755596e-06, + "loss": 0.0023, + "step": 46311 + }, + { + "epoch": 14.3, + "learning_rate": 3.962648829463312e-06, + "loss": 0.0035, + "step": 46312 + }, + { + "epoch": 14.3, + "learning_rate": 3.9622501502715435e-06, + "loss": 0.0034, + "step": 46313 + }, + { + "epoch": 14.3, + "learning_rate": 3.961851486181286e-06, + "loss": 0.0038, + "step": 46314 + }, + { + "epoch": 14.3, + "learning_rate": 3.961452837193542e-06, + "loss": 0.004, + "step": 46315 + }, + { + "epoch": 14.3, + "learning_rate": 3.961054203309303e-06, + "loss": 0.0036, + "step": 46316 + }, + { + "epoch": 14.3, + "learning_rate": 3.960655584529572e-06, + "loss": 0.0034, + "step": 46317 + }, + { + "epoch": 14.3, + "learning_rate": 3.9602569808553426e-06, + "loss": 0.0028, + "step": 46318 + }, + { + "epoch": 14.3, + "learning_rate": 3.959858392287609e-06, + "loss": 0.0034, + "step": 46319 + }, + { + "epoch": 14.3, + "learning_rate": 3.9594598188273704e-06, + "loss": 0.0034, + "step": 46320 + }, + { + "epoch": 14.3, + "learning_rate": 3.959061260475628e-06, + "loss": 0.0028, + "step": 46321 + }, + { + "epoch": 14.31, + "learning_rate": 3.958662717233373e-06, + "loss": 0.0034, + "step": 46322 + }, + { + "epoch": 14.31, + "learning_rate": 3.958264189101607e-06, + "loss": 0.0032, + "step": 46323 + }, + { + "epoch": 14.31, + "learning_rate": 3.9578656760813205e-06, + "loss": 0.0027, + "step": 46324 + }, + { + "epoch": 14.31, + "learning_rate": 3.957467178173519e-06, + "loss": 0.0042, + "step": 46325 + }, + { + "epoch": 14.31, + "learning_rate": 3.957068695379189e-06, + "loss": 0.0035, + "step": 46326 + }, + { + "epoch": 14.31, + "learning_rate": 3.956670227699336e-06, + "loss": 0.0035, + "step": 46327 + }, + { + "epoch": 14.31, + "learning_rate": 3.956271775134953e-06, + "loss": 0.004, + "step": 46328 + }, + { + "epoch": 14.31, + "learning_rate": 3.955873337687034e-06, + "loss": 0.0025, + "step": 46329 + }, + { + "epoch": 14.31, + "learning_rate": 3.955474915356577e-06, + "loss": 0.0034, + "step": 46330 + }, + { + "epoch": 14.31, + "learning_rate": 3.955076508144584e-06, + "loss": 0.0033, + "step": 46331 + }, + { + "epoch": 14.31, + "learning_rate": 3.9546781160520445e-06, + "loss": 0.0031, + "step": 46332 + }, + { + "epoch": 14.31, + "learning_rate": 3.954279739079961e-06, + "loss": 0.0036, + "step": 46333 + }, + { + "epoch": 14.31, + "learning_rate": 3.953881377229325e-06, + "loss": 0.0037, + "step": 46334 + }, + { + "epoch": 14.31, + "learning_rate": 3.953483030501131e-06, + "loss": 0.0024, + "step": 46335 + }, + { + "epoch": 14.31, + "learning_rate": 3.95308469889638e-06, + "loss": 0.0033, + "step": 46336 + }, + { + "epoch": 14.31, + "learning_rate": 3.95268638241607e-06, + "loss": 0.0031, + "step": 46337 + }, + { + "epoch": 14.31, + "learning_rate": 3.9522880810611944e-06, + "loss": 0.0032, + "step": 46338 + }, + { + "epoch": 14.31, + "learning_rate": 3.9518897948327455e-06, + "loss": 0.0031, + "step": 46339 + }, + { + "epoch": 14.31, + "learning_rate": 3.951491523731726e-06, + "loss": 0.0032, + "step": 46340 + }, + { + "epoch": 14.31, + "learning_rate": 3.9510932677591274e-06, + "loss": 0.003, + "step": 46341 + }, + { + "epoch": 14.31, + "learning_rate": 3.950695026915947e-06, + "loss": 0.0027, + "step": 46342 + }, + { + "epoch": 14.31, + "learning_rate": 3.950296801203186e-06, + "loss": 0.003, + "step": 46343 + }, + { + "epoch": 14.31, + "learning_rate": 3.949898590621836e-06, + "loss": 0.0029, + "step": 46344 + }, + { + "epoch": 14.31, + "learning_rate": 3.949500395172889e-06, + "loss": 0.0034, + "step": 46345 + }, + { + "epoch": 14.31, + "learning_rate": 3.949102214857348e-06, + "loss": 0.0035, + "step": 46346 + }, + { + "epoch": 14.31, + "learning_rate": 3.948704049676203e-06, + "loss": 0.004, + "step": 46347 + }, + { + "epoch": 14.31, + "learning_rate": 3.948305899630457e-06, + "loss": 0.0042, + "step": 46348 + }, + { + "epoch": 14.31, + "learning_rate": 3.947907764721101e-06, + "loss": 0.0038, + "step": 46349 + }, + { + "epoch": 14.31, + "learning_rate": 3.947509644949128e-06, + "loss": 0.0048, + "step": 46350 + }, + { + "epoch": 14.31, + "learning_rate": 3.947111540315538e-06, + "loss": 0.0037, + "step": 46351 + }, + { + "epoch": 14.31, + "learning_rate": 3.946713450821329e-06, + "loss": 0.004, + "step": 46352 + }, + { + "epoch": 14.31, + "learning_rate": 3.94631537646749e-06, + "loss": 0.0034, + "step": 46353 + }, + { + "epoch": 14.31, + "learning_rate": 3.9459173172550245e-06, + "loss": 0.0055, + "step": 46354 + }, + { + "epoch": 14.32, + "learning_rate": 3.945519273184923e-06, + "loss": 0.0029, + "step": 46355 + }, + { + "epoch": 14.32, + "learning_rate": 3.94512124425818e-06, + "loss": 0.0026, + "step": 46356 + }, + { + "epoch": 14.32, + "learning_rate": 3.944723230475792e-06, + "loss": 0.0033, + "step": 46357 + }, + { + "epoch": 14.32, + "learning_rate": 3.944325231838759e-06, + "loss": 0.0028, + "step": 46358 + }, + { + "epoch": 14.32, + "learning_rate": 3.943927248348074e-06, + "loss": 0.0031, + "step": 46359 + }, + { + "epoch": 14.32, + "learning_rate": 3.943529280004727e-06, + "loss": 0.0033, + "step": 46360 + }, + { + "epoch": 14.32, + "learning_rate": 3.9431313268097185e-06, + "loss": 0.0031, + "step": 46361 + }, + { + "epoch": 14.32, + "learning_rate": 3.942733388764047e-06, + "loss": 0.0028, + "step": 46362 + }, + { + "epoch": 14.32, + "learning_rate": 3.9423354658687e-06, + "loss": 0.004, + "step": 46363 + }, + { + "epoch": 14.32, + "learning_rate": 3.941937558124681e-06, + "loss": 0.0034, + "step": 46364 + }, + { + "epoch": 14.32, + "learning_rate": 3.941539665532981e-06, + "loss": 0.0029, + "step": 46365 + }, + { + "epoch": 14.32, + "learning_rate": 3.941141788094591e-06, + "loss": 0.0027, + "step": 46366 + }, + { + "epoch": 14.32, + "learning_rate": 3.940743925810511e-06, + "loss": 0.003, + "step": 46367 + }, + { + "epoch": 14.32, + "learning_rate": 3.9403460786817386e-06, + "loss": 0.0037, + "step": 46368 + }, + { + "epoch": 14.32, + "learning_rate": 3.9399482467092665e-06, + "loss": 0.003, + "step": 46369 + }, + { + "epoch": 14.32, + "learning_rate": 3.939550429894086e-06, + "loss": 0.0039, + "step": 46370 + }, + { + "epoch": 14.32, + "learning_rate": 3.939152628237197e-06, + "loss": 0.0026, + "step": 46371 + }, + { + "epoch": 14.32, + "learning_rate": 3.9387548417395905e-06, + "loss": 0.0036, + "step": 46372 + }, + { + "epoch": 14.32, + "learning_rate": 3.938357070402263e-06, + "loss": 0.0033, + "step": 46373 + }, + { + "epoch": 14.32, + "learning_rate": 3.937959314226219e-06, + "loss": 0.004, + "step": 46374 + }, + { + "epoch": 14.32, + "learning_rate": 3.937561573212435e-06, + "loss": 0.0036, + "step": 46375 + }, + { + "epoch": 14.32, + "learning_rate": 3.937163847361916e-06, + "loss": 0.003, + "step": 46376 + }, + { + "epoch": 14.32, + "learning_rate": 3.93676613667566e-06, + "loss": 0.0037, + "step": 46377 + }, + { + "epoch": 14.32, + "learning_rate": 3.936368441154653e-06, + "loss": 0.0042, + "step": 46378 + }, + { + "epoch": 14.32, + "learning_rate": 3.9359707607999e-06, + "loss": 0.0031, + "step": 46379 + }, + { + "epoch": 14.32, + "learning_rate": 3.935573095612388e-06, + "loss": 0.0041, + "step": 46380 + }, + { + "epoch": 14.32, + "learning_rate": 3.935175445593111e-06, + "loss": 0.0028, + "step": 46381 + }, + { + "epoch": 14.32, + "learning_rate": 3.934777810743068e-06, + "loss": 0.0032, + "step": 46382 + }, + { + "epoch": 14.32, + "learning_rate": 3.934380191063253e-06, + "loss": 0.0025, + "step": 46383 + }, + { + "epoch": 14.32, + "learning_rate": 3.933982586554661e-06, + "loss": 0.004, + "step": 46384 + }, + { + "epoch": 14.32, + "learning_rate": 3.933584997218281e-06, + "loss": 0.0031, + "step": 46385 + }, + { + "epoch": 14.32, + "learning_rate": 3.933187423055114e-06, + "loss": 0.0024, + "step": 46386 + }, + { + "epoch": 14.33, + "learning_rate": 3.93278986406615e-06, + "loss": 0.0026, + "step": 46387 + }, + { + "epoch": 14.33, + "learning_rate": 3.9323923202523835e-06, + "loss": 0.0031, + "step": 46388 + }, + { + "epoch": 14.33, + "learning_rate": 3.931994791614815e-06, + "loss": 0.0027, + "step": 46389 + }, + { + "epoch": 14.33, + "learning_rate": 3.931597278154434e-06, + "loss": 0.0043, + "step": 46390 + }, + { + "epoch": 14.33, + "learning_rate": 3.931199779872231e-06, + "loss": 0.0044, + "step": 46391 + }, + { + "epoch": 14.33, + "learning_rate": 3.930802296769205e-06, + "loss": 0.0033, + "step": 46392 + }, + { + "epoch": 14.33, + "learning_rate": 3.930404828846353e-06, + "loss": 0.0045, + "step": 46393 + }, + { + "epoch": 14.33, + "learning_rate": 3.9300073761046655e-06, + "loss": 0.0035, + "step": 46394 + }, + { + "epoch": 14.33, + "learning_rate": 3.9296099385451325e-06, + "loss": 0.0034, + "step": 46395 + }, + { + "epoch": 14.33, + "learning_rate": 3.929212516168756e-06, + "loss": 0.0033, + "step": 46396 + }, + { + "epoch": 14.33, + "learning_rate": 3.928815108976523e-06, + "loss": 0.0039, + "step": 46397 + }, + { + "epoch": 14.33, + "learning_rate": 3.928417716969429e-06, + "loss": 0.0031, + "step": 46398 + }, + { + "epoch": 14.33, + "learning_rate": 3.928020340148475e-06, + "loss": 0.0032, + "step": 46399 + }, + { + "epoch": 14.33, + "learning_rate": 3.927622978514649e-06, + "loss": 0.0027, + "step": 46400 + }, + { + "epoch": 14.33, + "learning_rate": 3.927225632068943e-06, + "loss": 0.0045, + "step": 46401 + }, + { + "epoch": 14.33, + "learning_rate": 3.926828300812355e-06, + "loss": 0.0037, + "step": 46402 + }, + { + "epoch": 14.33, + "learning_rate": 3.926430984745876e-06, + "loss": 0.0043, + "step": 46403 + }, + { + "epoch": 14.33, + "learning_rate": 3.926033683870503e-06, + "loss": 0.0027, + "step": 46404 + }, + { + "epoch": 14.33, + "learning_rate": 3.925636398187227e-06, + "loss": 0.0037, + "step": 46405 + }, + { + "epoch": 14.33, + "learning_rate": 3.925239127697039e-06, + "loss": 0.0031, + "step": 46406 + }, + { + "epoch": 14.33, + "learning_rate": 3.924841872400937e-06, + "loss": 0.0041, + "step": 46407 + }, + { + "epoch": 14.33, + "learning_rate": 3.924444632299915e-06, + "loss": 0.0027, + "step": 46408 + }, + { + "epoch": 14.33, + "learning_rate": 3.924047407394963e-06, + "loss": 0.0039, + "step": 46409 + }, + { + "epoch": 14.33, + "learning_rate": 3.92365019768708e-06, + "loss": 0.0035, + "step": 46410 + }, + { + "epoch": 14.33, + "learning_rate": 3.923253003177256e-06, + "loss": 0.0038, + "step": 46411 + }, + { + "epoch": 14.33, + "learning_rate": 3.922855823866481e-06, + "loss": 0.0027, + "step": 46412 + }, + { + "epoch": 14.33, + "learning_rate": 3.922458659755753e-06, + "loss": 0.0032, + "step": 46413 + }, + { + "epoch": 14.33, + "learning_rate": 3.922061510846067e-06, + "loss": 0.0029, + "step": 46414 + }, + { + "epoch": 14.33, + "learning_rate": 3.9216643771384136e-06, + "loss": 0.003, + "step": 46415 + }, + { + "epoch": 14.33, + "learning_rate": 3.921267258633782e-06, + "loss": 0.003, + "step": 46416 + }, + { + "epoch": 14.33, + "learning_rate": 3.920870155333174e-06, + "loss": 0.0032, + "step": 46417 + }, + { + "epoch": 14.33, + "learning_rate": 3.920473067237576e-06, + "loss": 0.0045, + "step": 46418 + }, + { + "epoch": 14.34, + "learning_rate": 3.920075994347981e-06, + "loss": 0.0024, + "step": 46419 + }, + { + "epoch": 14.34, + "learning_rate": 3.919678936665391e-06, + "loss": 0.0035, + "step": 46420 + }, + { + "epoch": 14.34, + "learning_rate": 3.919281894190792e-06, + "loss": 0.0029, + "step": 46421 + }, + { + "epoch": 14.34, + "learning_rate": 3.918884866925174e-06, + "loss": 0.0032, + "step": 46422 + }, + { + "epoch": 14.34, + "learning_rate": 3.918487854869535e-06, + "loss": 0.0029, + "step": 46423 + }, + { + "epoch": 14.34, + "learning_rate": 3.91809085802487e-06, + "loss": 0.0039, + "step": 46424 + }, + { + "epoch": 14.34, + "learning_rate": 3.917693876392169e-06, + "loss": 0.0035, + "step": 46425 + }, + { + "epoch": 14.34, + "learning_rate": 3.917296909972422e-06, + "loss": 0.0056, + "step": 46426 + }, + { + "epoch": 14.34, + "learning_rate": 3.916899958766628e-06, + "loss": 0.0042, + "step": 46427 + }, + { + "epoch": 14.34, + "learning_rate": 3.916503022775773e-06, + "loss": 0.0027, + "step": 46428 + }, + { + "epoch": 14.34, + "learning_rate": 3.916106102000854e-06, + "loss": 0.0031, + "step": 46429 + }, + { + "epoch": 14.34, + "learning_rate": 3.9157091964428665e-06, + "loss": 0.0031, + "step": 46430 + }, + { + "epoch": 14.34, + "learning_rate": 3.9153123061028e-06, + "loss": 0.0035, + "step": 46431 + }, + { + "epoch": 14.34, + "learning_rate": 3.914915430981642e-06, + "loss": 0.0037, + "step": 46432 + }, + { + "epoch": 14.34, + "learning_rate": 3.914518571080397e-06, + "loss": 0.003, + "step": 46433 + }, + { + "epoch": 14.34, + "learning_rate": 3.914121726400045e-06, + "loss": 0.0038, + "step": 46434 + }, + { + "epoch": 14.34, + "learning_rate": 3.91372489694159e-06, + "loss": 0.0033, + "step": 46435 + }, + { + "epoch": 14.34, + "learning_rate": 3.913328082706018e-06, + "loss": 0.0032, + "step": 46436 + }, + { + "epoch": 14.34, + "learning_rate": 3.912931283694319e-06, + "loss": 0.0035, + "step": 46437 + }, + { + "epoch": 14.34, + "learning_rate": 3.91253449990749e-06, + "loss": 0.0028, + "step": 46438 + }, + { + "epoch": 14.34, + "learning_rate": 3.9121377313465245e-06, + "loss": 0.004, + "step": 46439 + }, + { + "epoch": 14.34, + "learning_rate": 3.91174097801241e-06, + "loss": 0.0033, + "step": 46440 + }, + { + "epoch": 14.34, + "learning_rate": 3.911344239906146e-06, + "loss": 0.0034, + "step": 46441 + }, + { + "epoch": 14.34, + "learning_rate": 3.91094751702872e-06, + "loss": 0.0037, + "step": 46442 + }, + { + "epoch": 14.34, + "learning_rate": 3.910550809381122e-06, + "loss": 0.0029, + "step": 46443 + }, + { + "epoch": 14.34, + "learning_rate": 3.910154116964346e-06, + "loss": 0.0029, + "step": 46444 + }, + { + "epoch": 14.34, + "learning_rate": 3.9097574397793894e-06, + "loss": 0.0032, + "step": 46445 + }, + { + "epoch": 14.34, + "learning_rate": 3.90936077782724e-06, + "loss": 0.0027, + "step": 46446 + }, + { + "epoch": 14.34, + "learning_rate": 3.908964131108887e-06, + "loss": 0.0032, + "step": 46447 + }, + { + "epoch": 14.34, + "learning_rate": 3.908567499625329e-06, + "loss": 0.0037, + "step": 46448 + }, + { + "epoch": 14.34, + "learning_rate": 3.90817088337755e-06, + "loss": 0.0031, + "step": 46449 + }, + { + "epoch": 14.34, + "learning_rate": 3.907774282366547e-06, + "loss": 0.0043, + "step": 46450 + }, + { + "epoch": 14.34, + "learning_rate": 3.9073776965933166e-06, + "loss": 0.0041, + "step": 46451 + }, + { + "epoch": 14.35, + "learning_rate": 3.9069811260588455e-06, + "loss": 0.0033, + "step": 46452 + }, + { + "epoch": 14.35, + "learning_rate": 3.906584570764122e-06, + "loss": 0.003, + "step": 46453 + }, + { + "epoch": 14.35, + "learning_rate": 3.906188030710146e-06, + "loss": 0.0025, + "step": 46454 + }, + { + "epoch": 14.35, + "learning_rate": 3.9057915058979e-06, + "loss": 0.0032, + "step": 46455 + }, + { + "epoch": 14.35, + "learning_rate": 3.905394996328385e-06, + "loss": 0.0041, + "step": 46456 + }, + { + "epoch": 14.35, + "learning_rate": 3.904998502002586e-06, + "loss": 0.0032, + "step": 46457 + }, + { + "epoch": 14.35, + "learning_rate": 3.904602022921501e-06, + "loss": 0.0038, + "step": 46458 + }, + { + "epoch": 14.35, + "learning_rate": 3.904205559086114e-06, + "loss": 0.0037, + "step": 46459 + }, + { + "epoch": 14.35, + "learning_rate": 3.903809110497421e-06, + "loss": 0.0033, + "step": 46460 + }, + { + "epoch": 14.35, + "learning_rate": 3.903412677156416e-06, + "loss": 0.0042, + "step": 46461 + }, + { + "epoch": 14.35, + "learning_rate": 3.9030162590640894e-06, + "loss": 0.0035, + "step": 46462 + }, + { + "epoch": 14.35, + "learning_rate": 3.902619856221427e-06, + "loss": 0.0039, + "step": 46463 + }, + { + "epoch": 14.35, + "learning_rate": 3.902223468629427e-06, + "loss": 0.004, + "step": 46464 + }, + { + "epoch": 14.35, + "learning_rate": 3.901827096289076e-06, + "loss": 0.0034, + "step": 46465 + }, + { + "epoch": 14.35, + "learning_rate": 3.9014307392013705e-06, + "loss": 0.0033, + "step": 46466 + }, + { + "epoch": 14.35, + "learning_rate": 3.9010343973672995e-06, + "loss": 0.0029, + "step": 46467 + }, + { + "epoch": 14.35, + "learning_rate": 3.90063807078785e-06, + "loss": 0.0032, + "step": 46468 + }, + { + "epoch": 14.35, + "learning_rate": 3.900241759464016e-06, + "loss": 0.0044, + "step": 46469 + }, + { + "epoch": 14.35, + "learning_rate": 3.899845463396795e-06, + "loss": 0.0035, + "step": 46470 + }, + { + "epoch": 14.35, + "learning_rate": 3.899449182587169e-06, + "loss": 0.0033, + "step": 46471 + }, + { + "epoch": 14.35, + "learning_rate": 3.899052917036137e-06, + "loss": 0.0066, + "step": 46472 + }, + { + "epoch": 14.35, + "learning_rate": 3.8986566667446866e-06, + "loss": 0.0032, + "step": 46473 + }, + { + "epoch": 14.35, + "learning_rate": 3.898260431713805e-06, + "loss": 0.0037, + "step": 46474 + }, + { + "epoch": 14.35, + "learning_rate": 3.897864211944487e-06, + "loss": 0.0037, + "step": 46475 + }, + { + "epoch": 14.35, + "learning_rate": 3.897468007437727e-06, + "loss": 0.0038, + "step": 46476 + }, + { + "epoch": 14.35, + "learning_rate": 3.897071818194512e-06, + "loss": 0.0023, + "step": 46477 + }, + { + "epoch": 14.35, + "learning_rate": 3.89667564421583e-06, + "loss": 0.003, + "step": 46478 + }, + { + "epoch": 14.35, + "learning_rate": 3.89627948550268e-06, + "loss": 0.0028, + "step": 46479 + }, + { + "epoch": 14.35, + "learning_rate": 3.895883342056044e-06, + "loss": 0.0033, + "step": 46480 + }, + { + "epoch": 14.35, + "learning_rate": 3.8954872138769174e-06, + "loss": 0.003, + "step": 46481 + }, + { + "epoch": 14.35, + "learning_rate": 3.895091100966297e-06, + "loss": 0.0039, + "step": 46482 + }, + { + "epoch": 14.35, + "learning_rate": 3.894695003325161e-06, + "loss": 0.0036, + "step": 46483 + }, + { + "epoch": 14.36, + "learning_rate": 3.894298920954506e-06, + "loss": 0.0044, + "step": 46484 + }, + { + "epoch": 14.36, + "learning_rate": 3.893902853855326e-06, + "loss": 0.0033, + "step": 46485 + }, + { + "epoch": 14.36, + "learning_rate": 3.893506802028606e-06, + "loss": 0.0042, + "step": 46486 + }, + { + "epoch": 14.36, + "learning_rate": 3.893110765475342e-06, + "loss": 0.0032, + "step": 46487 + }, + { + "epoch": 14.36, + "learning_rate": 3.8927147441965186e-06, + "loss": 0.0031, + "step": 46488 + }, + { + "epoch": 14.36, + "learning_rate": 3.892318738193134e-06, + "loss": 0.0038, + "step": 46489 + }, + { + "epoch": 14.36, + "learning_rate": 3.891922747466169e-06, + "loss": 0.0028, + "step": 46490 + }, + { + "epoch": 14.36, + "learning_rate": 3.8915267720166205e-06, + "loss": 0.004, + "step": 46491 + }, + { + "epoch": 14.36, + "learning_rate": 3.891130811845484e-06, + "loss": 0.0038, + "step": 46492 + }, + { + "epoch": 14.36, + "learning_rate": 3.890734866953737e-06, + "loss": 0.0032, + "step": 46493 + }, + { + "epoch": 14.36, + "learning_rate": 3.890338937342376e-06, + "loss": 0.0033, + "step": 46494 + }, + { + "epoch": 14.36, + "learning_rate": 3.889943023012396e-06, + "loss": 0.0028, + "step": 46495 + }, + { + "epoch": 14.36, + "learning_rate": 3.889547123964778e-06, + "loss": 0.0033, + "step": 46496 + }, + { + "epoch": 14.36, + "learning_rate": 3.889151240200522e-06, + "loss": 0.0027, + "step": 46497 + }, + { + "epoch": 14.36, + "learning_rate": 3.8887553717206115e-06, + "loss": 0.0031, + "step": 46498 + }, + { + "epoch": 14.36, + "learning_rate": 3.888359518526037e-06, + "loss": 0.004, + "step": 46499 + }, + { + "epoch": 14.36, + "learning_rate": 3.887963680617789e-06, + "loss": 0.0025, + "step": 46500 + }, + { + "epoch": 14.36, + "learning_rate": 3.887567857996861e-06, + "loss": 0.0038, + "step": 46501 + }, + { + "epoch": 14.36, + "learning_rate": 3.887172050664243e-06, + "loss": 0.0042, + "step": 46502 + }, + { + "epoch": 14.36, + "learning_rate": 3.886776258620918e-06, + "loss": 0.0029, + "step": 46503 + }, + { + "epoch": 14.36, + "learning_rate": 3.886380481867883e-06, + "loss": 0.0035, + "step": 46504 + }, + { + "epoch": 14.36, + "learning_rate": 3.885984720406123e-06, + "loss": 0.0031, + "step": 46505 + }, + { + "epoch": 14.36, + "learning_rate": 3.88558897423663e-06, + "loss": 0.0043, + "step": 46506 + }, + { + "epoch": 14.36, + "learning_rate": 3.885193243360399e-06, + "loss": 0.0035, + "step": 46507 + }, + { + "epoch": 14.36, + "learning_rate": 3.884797527778414e-06, + "loss": 0.0022, + "step": 46508 + }, + { + "epoch": 14.36, + "learning_rate": 3.8844018274916615e-06, + "loss": 0.0032, + "step": 46509 + }, + { + "epoch": 14.36, + "learning_rate": 3.88400614250114e-06, + "loss": 0.0024, + "step": 46510 + }, + { + "epoch": 14.36, + "learning_rate": 3.883610472807831e-06, + "loss": 0.0032, + "step": 46511 + }, + { + "epoch": 14.36, + "learning_rate": 3.8832148184127275e-06, + "loss": 0.0035, + "step": 46512 + }, + { + "epoch": 14.36, + "learning_rate": 3.882819179316826e-06, + "loss": 0.0032, + "step": 46513 + }, + { + "epoch": 14.36, + "learning_rate": 3.8824235555211034e-06, + "loss": 0.0027, + "step": 46514 + }, + { + "epoch": 14.36, + "learning_rate": 3.882027947026555e-06, + "loss": 0.0039, + "step": 46515 + }, + { + "epoch": 14.36, + "learning_rate": 3.881632353834173e-06, + "loss": 0.0043, + "step": 46516 + }, + { + "epoch": 14.37, + "learning_rate": 3.881236775944941e-06, + "loss": 0.0035, + "step": 46517 + }, + { + "epoch": 14.37, + "learning_rate": 3.880841213359856e-06, + "loss": 0.0038, + "step": 46518 + }, + { + "epoch": 14.37, + "learning_rate": 3.880445666079903e-06, + "loss": 0.003, + "step": 46519 + }, + { + "epoch": 14.37, + "learning_rate": 3.880050134106068e-06, + "loss": 0.0037, + "step": 46520 + }, + { + "epoch": 14.37, + "learning_rate": 3.8796546174393445e-06, + "loss": 0.0038, + "step": 46521 + }, + { + "epoch": 14.37, + "learning_rate": 3.87925911608072e-06, + "loss": 0.0048, + "step": 46522 + }, + { + "epoch": 14.37, + "learning_rate": 3.8788636300311935e-06, + "loss": 0.0044, + "step": 46523 + }, + { + "epoch": 14.37, + "learning_rate": 3.878468159291737e-06, + "loss": 0.0024, + "step": 46524 + }, + { + "epoch": 14.37, + "learning_rate": 3.8780727038633485e-06, + "loss": 0.0035, + "step": 46525 + }, + { + "epoch": 14.37, + "learning_rate": 3.877677263747019e-06, + "loss": 0.0033, + "step": 46526 + }, + { + "epoch": 14.37, + "learning_rate": 3.877281838943734e-06, + "loss": 0.0029, + "step": 46527 + }, + { + "epoch": 14.37, + "learning_rate": 3.8768864294544864e-06, + "loss": 0.0031, + "step": 46528 + }, + { + "epoch": 14.37, + "learning_rate": 3.876491035280262e-06, + "loss": 0.0035, + "step": 46529 + }, + { + "epoch": 14.37, + "learning_rate": 3.876095656422047e-06, + "loss": 0.0037, + "step": 46530 + }, + { + "epoch": 14.37, + "learning_rate": 3.875700292880835e-06, + "loss": 0.0046, + "step": 46531 + }, + { + "epoch": 14.37, + "learning_rate": 3.875304944657616e-06, + "loss": 0.0023, + "step": 46532 + }, + { + "epoch": 14.37, + "learning_rate": 3.874909611753377e-06, + "loss": 0.0033, + "step": 46533 + }, + { + "epoch": 14.37, + "learning_rate": 3.874514294169103e-06, + "loss": 0.0026, + "step": 46534 + }, + { + "epoch": 14.37, + "learning_rate": 3.874118991905789e-06, + "loss": 0.0036, + "step": 46535 + }, + { + "epoch": 14.37, + "learning_rate": 3.873723704964416e-06, + "loss": 0.0026, + "step": 46536 + }, + { + "epoch": 14.37, + "learning_rate": 3.873328433345979e-06, + "loss": 0.0033, + "step": 46537 + }, + { + "epoch": 14.37, + "learning_rate": 3.872933177051468e-06, + "loss": 0.003, + "step": 46538 + }, + { + "epoch": 14.37, + "learning_rate": 3.8725379360818684e-06, + "loss": 0.0037, + "step": 46539 + }, + { + "epoch": 14.37, + "learning_rate": 3.872142710438165e-06, + "loss": 0.0035, + "step": 46540 + }, + { + "epoch": 14.37, + "learning_rate": 3.871747500121354e-06, + "loss": 0.0037, + "step": 46541 + }, + { + "epoch": 14.37, + "learning_rate": 3.8713523051324175e-06, + "loss": 0.0034, + "step": 46542 + }, + { + "epoch": 14.37, + "learning_rate": 3.87095712547235e-06, + "loss": 0.003, + "step": 46543 + }, + { + "epoch": 14.37, + "learning_rate": 3.870561961142137e-06, + "loss": 0.0036, + "step": 46544 + }, + { + "epoch": 14.37, + "learning_rate": 3.8701668121427624e-06, + "loss": 0.0032, + "step": 46545 + }, + { + "epoch": 14.37, + "learning_rate": 3.869771678475218e-06, + "loss": 0.003, + "step": 46546 + }, + { + "epoch": 14.37, + "learning_rate": 3.869376560140498e-06, + "loss": 0.0032, + "step": 46547 + }, + { + "epoch": 14.37, + "learning_rate": 3.86898145713958e-06, + "loss": 0.0032, + "step": 46548 + }, + { + "epoch": 14.38, + "learning_rate": 3.8685863694734615e-06, + "loss": 0.0045, + "step": 46549 + }, + { + "epoch": 14.38, + "learning_rate": 3.868191297143128e-06, + "loss": 0.0035, + "step": 46550 + }, + { + "epoch": 14.38, + "learning_rate": 3.867796240149562e-06, + "loss": 0.0038, + "step": 46551 + }, + { + "epoch": 14.38, + "learning_rate": 3.867401198493756e-06, + "loss": 0.0038, + "step": 46552 + }, + { + "epoch": 14.38, + "learning_rate": 3.867006172176702e-06, + "loss": 0.0027, + "step": 46553 + }, + { + "epoch": 14.38, + "learning_rate": 3.866611161199384e-06, + "loss": 0.003, + "step": 46554 + }, + { + "epoch": 14.38, + "learning_rate": 3.866216165562786e-06, + "loss": 0.0041, + "step": 46555 + }, + { + "epoch": 14.38, + "learning_rate": 3.865821185267901e-06, + "loss": 0.0037, + "step": 46556 + }, + { + "epoch": 14.38, + "learning_rate": 3.865426220315719e-06, + "loss": 0.0025, + "step": 46557 + }, + { + "epoch": 14.38, + "learning_rate": 3.865031270707221e-06, + "loss": 0.0035, + "step": 46558 + }, + { + "epoch": 14.38, + "learning_rate": 3.864636336443404e-06, + "loss": 0.0031, + "step": 46559 + }, + { + "epoch": 14.38, + "learning_rate": 3.8642414175252485e-06, + "loss": 0.0026, + "step": 46560 + }, + { + "epoch": 14.38, + "learning_rate": 3.863846513953742e-06, + "loss": 0.003, + "step": 46561 + }, + { + "epoch": 14.38, + "learning_rate": 3.863451625729874e-06, + "loss": 0.003, + "step": 46562 + }, + { + "epoch": 14.38, + "learning_rate": 3.863056752854637e-06, + "loss": 0.0032, + "step": 46563 + }, + { + "epoch": 14.38, + "learning_rate": 3.862661895329013e-06, + "loss": 0.0043, + "step": 46564 + }, + { + "epoch": 14.38, + "learning_rate": 3.862267053153988e-06, + "loss": 0.0041, + "step": 46565 + }, + { + "epoch": 14.38, + "learning_rate": 3.861872226330556e-06, + "loss": 0.0029, + "step": 46566 + }, + { + "epoch": 14.38, + "learning_rate": 3.861477414859699e-06, + "loss": 0.0036, + "step": 46567 + }, + { + "epoch": 14.38, + "learning_rate": 3.861082618742405e-06, + "loss": 0.0033, + "step": 46568 + }, + { + "epoch": 14.38, + "learning_rate": 3.860687837979667e-06, + "loss": 0.0039, + "step": 46569 + }, + { + "epoch": 14.38, + "learning_rate": 3.8602930725724685e-06, + "loss": 0.0028, + "step": 46570 + }, + { + "epoch": 14.38, + "learning_rate": 3.859898322521793e-06, + "loss": 0.004, + "step": 46571 + }, + { + "epoch": 14.38, + "learning_rate": 3.859503587828636e-06, + "loss": 0.0033, + "step": 46572 + }, + { + "epoch": 14.38, + "learning_rate": 3.859108868493977e-06, + "loss": 0.0033, + "step": 46573 + }, + { + "epoch": 14.38, + "learning_rate": 3.8587141645188095e-06, + "loss": 0.0027, + "step": 46574 + }, + { + "epoch": 14.38, + "learning_rate": 3.8583194759041175e-06, + "loss": 0.0025, + "step": 46575 + }, + { + "epoch": 14.38, + "learning_rate": 3.857924802650886e-06, + "loss": 0.0038, + "step": 46576 + }, + { + "epoch": 14.38, + "learning_rate": 3.857530144760105e-06, + "loss": 0.0038, + "step": 46577 + }, + { + "epoch": 14.38, + "learning_rate": 3.857135502232765e-06, + "loss": 0.003, + "step": 46578 + }, + { + "epoch": 14.38, + "learning_rate": 3.8567408750698455e-06, + "loss": 0.005, + "step": 46579 + }, + { + "epoch": 14.38, + "learning_rate": 3.856346263272341e-06, + "loss": 0.0036, + "step": 46580 + }, + { + "epoch": 14.39, + "learning_rate": 3.855951666841236e-06, + "loss": 0.0026, + "step": 46581 + }, + { + "epoch": 14.39, + "learning_rate": 3.855557085777512e-06, + "loss": 0.0037, + "step": 46582 + }, + { + "epoch": 14.39, + "learning_rate": 3.85516252008216e-06, + "loss": 0.0029, + "step": 46583 + }, + { + "epoch": 14.39, + "learning_rate": 3.854767969756171e-06, + "loss": 0.0041, + "step": 46584 + }, + { + "epoch": 14.39, + "learning_rate": 3.854373434800529e-06, + "loss": 0.0027, + "step": 46585 + }, + { + "epoch": 14.39, + "learning_rate": 3.853978915216216e-06, + "loss": 0.0037, + "step": 46586 + }, + { + "epoch": 14.39, + "learning_rate": 3.853584411004222e-06, + "loss": 0.0034, + "step": 46587 + }, + { + "epoch": 14.39, + "learning_rate": 3.8531899221655385e-06, + "loss": 0.003, + "step": 46588 + }, + { + "epoch": 14.39, + "learning_rate": 3.852795448701145e-06, + "loss": 0.0035, + "step": 46589 + }, + { + "epoch": 14.39, + "learning_rate": 3.852400990612034e-06, + "loss": 0.0036, + "step": 46590 + }, + { + "epoch": 14.39, + "learning_rate": 3.85200654789919e-06, + "loss": 0.003, + "step": 46591 + }, + { + "epoch": 14.39, + "learning_rate": 3.851612120563596e-06, + "loss": 0.0032, + "step": 46592 + }, + { + "epoch": 14.39, + "learning_rate": 3.85121770860624e-06, + "loss": 0.0026, + "step": 46593 + }, + { + "epoch": 14.39, + "learning_rate": 3.850823312028115e-06, + "loss": 0.004, + "step": 46594 + }, + { + "epoch": 14.39, + "learning_rate": 3.850428930830201e-06, + "loss": 0.0031, + "step": 46595 + }, + { + "epoch": 14.39, + "learning_rate": 3.8500345650134825e-06, + "loss": 0.0044, + "step": 46596 + }, + { + "epoch": 14.39, + "learning_rate": 3.849640214578954e-06, + "loss": 0.0034, + "step": 46597 + }, + { + "epoch": 14.39, + "learning_rate": 3.849245879527592e-06, + "loss": 0.0025, + "step": 46598 + }, + { + "epoch": 14.39, + "learning_rate": 3.84885155986039e-06, + "loss": 0.0038, + "step": 46599 + }, + { + "epoch": 14.39, + "learning_rate": 3.848457255578334e-06, + "loss": 0.0063, + "step": 46600 + }, + { + "epoch": 14.39, + "learning_rate": 3.848062966682408e-06, + "loss": 0.0029, + "step": 46601 + }, + { + "epoch": 14.39, + "learning_rate": 3.847668693173596e-06, + "loss": 0.0034, + "step": 46602 + }, + { + "epoch": 14.39, + "learning_rate": 3.84727443505289e-06, + "loss": 0.0118, + "step": 46603 + }, + { + "epoch": 14.39, + "learning_rate": 3.846880192321269e-06, + "loss": 0.005, + "step": 46604 + }, + { + "epoch": 14.39, + "learning_rate": 3.846485964979727e-06, + "loss": 0.0037, + "step": 46605 + }, + { + "epoch": 14.39, + "learning_rate": 3.846091753029245e-06, + "loss": 0.0041, + "step": 46606 + }, + { + "epoch": 14.39, + "learning_rate": 3.8456975564708075e-06, + "loss": 0.0034, + "step": 46607 + }, + { + "epoch": 14.39, + "learning_rate": 3.845303375305402e-06, + "loss": 0.0033, + "step": 46608 + }, + { + "epoch": 14.39, + "learning_rate": 3.8449092095340205e-06, + "loss": 0.0034, + "step": 46609 + }, + { + "epoch": 14.39, + "learning_rate": 3.844515059157639e-06, + "loss": 0.0042, + "step": 46610 + }, + { + "epoch": 14.39, + "learning_rate": 3.84412092417725e-06, + "loss": 0.0033, + "step": 46611 + }, + { + "epoch": 14.39, + "learning_rate": 3.843726804593839e-06, + "loss": 0.0031, + "step": 46612 + }, + { + "epoch": 14.39, + "learning_rate": 3.8433327004083865e-06, + "loss": 0.0029, + "step": 46613 + }, + { + "epoch": 14.4, + "learning_rate": 3.842938611621883e-06, + "loss": 0.0037, + "step": 46614 + }, + { + "epoch": 14.4, + "learning_rate": 3.842544538235315e-06, + "loss": 0.0041, + "step": 46615 + }, + { + "epoch": 14.4, + "learning_rate": 3.842150480249666e-06, + "loss": 0.0036, + "step": 46616 + }, + { + "epoch": 14.4, + "learning_rate": 3.841756437665919e-06, + "loss": 0.004, + "step": 46617 + }, + { + "epoch": 14.4, + "learning_rate": 3.841362410485065e-06, + "loss": 0.0034, + "step": 46618 + }, + { + "epoch": 14.4, + "learning_rate": 3.840968398708084e-06, + "loss": 0.0058, + "step": 46619 + }, + { + "epoch": 14.4, + "learning_rate": 3.840574402335964e-06, + "loss": 0.0049, + "step": 46620 + }, + { + "epoch": 14.4, + "learning_rate": 3.8401804213696944e-06, + "loss": 0.0047, + "step": 46621 + }, + { + "epoch": 14.4, + "learning_rate": 3.839786455810257e-06, + "loss": 0.004, + "step": 46622 + }, + { + "epoch": 14.4, + "learning_rate": 3.8393925056586345e-06, + "loss": 0.0031, + "step": 46623 + }, + { + "epoch": 14.4, + "learning_rate": 3.838998570915814e-06, + "loss": 0.0045, + "step": 46624 + }, + { + "epoch": 14.4, + "learning_rate": 3.838604651582786e-06, + "loss": 0.0032, + "step": 46625 + }, + { + "epoch": 14.4, + "learning_rate": 3.838210747660532e-06, + "loss": 0.0029, + "step": 46626 + }, + { + "epoch": 14.4, + "learning_rate": 3.837816859150032e-06, + "loss": 0.004, + "step": 46627 + }, + { + "epoch": 14.4, + "learning_rate": 3.83742298605228e-06, + "loss": 0.0043, + "step": 46628 + }, + { + "epoch": 14.4, + "learning_rate": 3.837029128368254e-06, + "loss": 0.0034, + "step": 46629 + }, + { + "epoch": 14.4, + "learning_rate": 3.836635286098941e-06, + "loss": 0.003, + "step": 46630 + }, + { + "epoch": 14.4, + "learning_rate": 3.836241459245334e-06, + "loss": 0.0039, + "step": 46631 + }, + { + "epoch": 14.4, + "learning_rate": 3.835847647808406e-06, + "loss": 0.0043, + "step": 46632 + }, + { + "epoch": 14.4, + "learning_rate": 3.835453851789147e-06, + "loss": 0.0023, + "step": 46633 + }, + { + "epoch": 14.4, + "learning_rate": 3.835060071188546e-06, + "loss": 0.003, + "step": 46634 + }, + { + "epoch": 14.4, + "learning_rate": 3.8346663060075795e-06, + "loss": 0.0027, + "step": 46635 + }, + { + "epoch": 14.4, + "learning_rate": 3.834272556247242e-06, + "loss": 0.0039, + "step": 46636 + }, + { + "epoch": 14.4, + "learning_rate": 3.833878821908512e-06, + "loss": 0.0036, + "step": 46637 + }, + { + "epoch": 14.4, + "learning_rate": 3.833485102992372e-06, + "loss": 0.0044, + "step": 46638 + }, + { + "epoch": 14.4, + "learning_rate": 3.833091399499812e-06, + "loss": 0.0035, + "step": 46639 + }, + { + "epoch": 14.4, + "learning_rate": 3.832697711431818e-06, + "loss": 0.0035, + "step": 46640 + }, + { + "epoch": 14.4, + "learning_rate": 3.8323040387893705e-06, + "loss": 0.0042, + "step": 46641 + }, + { + "epoch": 14.4, + "learning_rate": 3.831910381573454e-06, + "loss": 0.0052, + "step": 46642 + }, + { + "epoch": 14.4, + "learning_rate": 3.831516739785058e-06, + "loss": 0.0041, + "step": 46643 + }, + { + "epoch": 14.4, + "learning_rate": 3.831123113425159e-06, + "loss": 0.0036, + "step": 46644 + }, + { + "epoch": 14.4, + "learning_rate": 3.830729502494747e-06, + "loss": 0.0032, + "step": 46645 + }, + { + "epoch": 14.41, + "learning_rate": 3.830335906994809e-06, + "loss": 0.0032, + "step": 46646 + }, + { + "epoch": 14.41, + "learning_rate": 3.829942326926326e-06, + "loss": 0.0031, + "step": 46647 + }, + { + "epoch": 14.41, + "learning_rate": 3.829548762290279e-06, + "loss": 0.0025, + "step": 46648 + }, + { + "epoch": 14.41, + "learning_rate": 3.82915521308766e-06, + "loss": 0.0035, + "step": 46649 + }, + { + "epoch": 14.41, + "learning_rate": 3.828761679319445e-06, + "loss": 0.0032, + "step": 46650 + }, + { + "epoch": 14.41, + "learning_rate": 3.8283681609866275e-06, + "loss": 0.0028, + "step": 46651 + }, + { + "epoch": 14.41, + "learning_rate": 3.8279746580901825e-06, + "loss": 0.0041, + "step": 46652 + }, + { + "epoch": 14.41, + "learning_rate": 3.827581170631102e-06, + "loss": 0.0033, + "step": 46653 + }, + { + "epoch": 14.41, + "learning_rate": 3.827187698610363e-06, + "loss": 0.0034, + "step": 46654 + }, + { + "epoch": 14.41, + "learning_rate": 3.826794242028954e-06, + "loss": 0.0027, + "step": 46655 + }, + { + "epoch": 14.41, + "learning_rate": 3.8264008008878615e-06, + "loss": 0.003, + "step": 46656 + }, + { + "epoch": 14.41, + "learning_rate": 3.826007375188066e-06, + "loss": 0.004, + "step": 46657 + }, + { + "epoch": 14.41, + "learning_rate": 3.82561396493055e-06, + "loss": 0.0035, + "step": 46658 + }, + { + "epoch": 14.41, + "learning_rate": 3.825220570116304e-06, + "loss": 0.0045, + "step": 46659 + }, + { + "epoch": 14.41, + "learning_rate": 3.824827190746302e-06, + "loss": 0.0029, + "step": 46660 + }, + { + "epoch": 14.41, + "learning_rate": 3.824433826821537e-06, + "loss": 0.0031, + "step": 46661 + }, + { + "epoch": 14.41, + "learning_rate": 3.8240404783429906e-06, + "loss": 0.0036, + "step": 46662 + }, + { + "epoch": 14.41, + "learning_rate": 3.823647145311641e-06, + "loss": 0.0033, + "step": 46663 + }, + { + "epoch": 14.41, + "learning_rate": 3.823253827728477e-06, + "loss": 0.0044, + "step": 46664 + }, + { + "epoch": 14.41, + "learning_rate": 3.822860525594485e-06, + "loss": 0.0049, + "step": 46665 + }, + { + "epoch": 14.41, + "learning_rate": 3.822467238910642e-06, + "loss": 0.0037, + "step": 46666 + }, + { + "epoch": 14.41, + "learning_rate": 3.822073967677938e-06, + "loss": 0.0033, + "step": 46667 + }, + { + "epoch": 14.41, + "learning_rate": 3.8216807118973545e-06, + "loss": 0.0037, + "step": 46668 + }, + { + "epoch": 14.41, + "learning_rate": 3.821287471569871e-06, + "loss": 0.0038, + "step": 46669 + }, + { + "epoch": 14.41, + "learning_rate": 3.8208942466964735e-06, + "loss": 0.0038, + "step": 46670 + }, + { + "epoch": 14.41, + "learning_rate": 3.820501037278152e-06, + "loss": 0.0023, + "step": 46671 + }, + { + "epoch": 14.41, + "learning_rate": 3.820107843315882e-06, + "loss": 0.0034, + "step": 46672 + }, + { + "epoch": 14.41, + "learning_rate": 3.819714664810648e-06, + "loss": 0.0024, + "step": 46673 + }, + { + "epoch": 14.41, + "learning_rate": 3.819321501763437e-06, + "loss": 0.0026, + "step": 46674 + }, + { + "epoch": 14.41, + "learning_rate": 3.8189283541752275e-06, + "loss": 0.0025, + "step": 46675 + }, + { + "epoch": 14.41, + "learning_rate": 3.818535222047005e-06, + "loss": 0.0033, + "step": 46676 + }, + { + "epoch": 14.41, + "learning_rate": 3.8181421053797576e-06, + "loss": 0.0034, + "step": 46677 + }, + { + "epoch": 14.42, + "learning_rate": 3.817749004174463e-06, + "loss": 0.0032, + "step": 46678 + }, + { + "epoch": 14.42, + "learning_rate": 3.817355918432103e-06, + "loss": 0.0029, + "step": 46679 + }, + { + "epoch": 14.42, + "learning_rate": 3.816962848153667e-06, + "loss": 0.0033, + "step": 46680 + }, + { + "epoch": 14.42, + "learning_rate": 3.816569793340131e-06, + "loss": 0.0034, + "step": 46681 + }, + { + "epoch": 14.42, + "learning_rate": 3.816176753992485e-06, + "loss": 0.0031, + "step": 46682 + }, + { + "epoch": 14.42, + "learning_rate": 3.815783730111709e-06, + "loss": 0.0032, + "step": 46683 + }, + { + "epoch": 14.42, + "learning_rate": 3.815390721698783e-06, + "loss": 0.0038, + "step": 46684 + }, + { + "epoch": 14.42, + "learning_rate": 3.814997728754692e-06, + "loss": 0.0033, + "step": 46685 + }, + { + "epoch": 14.42, + "learning_rate": 3.8146047512804194e-06, + "loss": 0.0029, + "step": 46686 + }, + { + "epoch": 14.42, + "learning_rate": 3.8142117892769524e-06, + "loss": 0.0037, + "step": 46687 + }, + { + "epoch": 14.42, + "learning_rate": 3.8138188427452706e-06, + "loss": 0.0035, + "step": 46688 + }, + { + "epoch": 14.42, + "learning_rate": 3.8134259116863528e-06, + "loss": 0.0034, + "step": 46689 + }, + { + "epoch": 14.42, + "learning_rate": 3.813032996101187e-06, + "loss": 0.0026, + "step": 46690 + }, + { + "epoch": 14.42, + "learning_rate": 3.8126400959907516e-06, + "loss": 0.0031, + "step": 46691 + }, + { + "epoch": 14.42, + "learning_rate": 3.812247211356036e-06, + "loss": 0.0029, + "step": 46692 + }, + { + "epoch": 14.42, + "learning_rate": 3.811854342198018e-06, + "loss": 0.0037, + "step": 46693 + }, + { + "epoch": 14.42, + "learning_rate": 3.8114614885176772e-06, + "loss": 0.0033, + "step": 46694 + }, + { + "epoch": 14.42, + "learning_rate": 3.811068650316e-06, + "loss": 0.0034, + "step": 46695 + }, + { + "epoch": 14.42, + "learning_rate": 3.8106758275939724e-06, + "loss": 0.003, + "step": 46696 + }, + { + "epoch": 14.42, + "learning_rate": 3.810283020352571e-06, + "loss": 0.0028, + "step": 46697 + }, + { + "epoch": 14.42, + "learning_rate": 3.809890228592783e-06, + "loss": 0.0045, + "step": 46698 + }, + { + "epoch": 14.42, + "learning_rate": 3.809497452315588e-06, + "loss": 0.0038, + "step": 46699 + }, + { + "epoch": 14.42, + "learning_rate": 3.8091046915219665e-06, + "loss": 0.0027, + "step": 46700 + }, + { + "epoch": 14.42, + "learning_rate": 3.808711946212903e-06, + "loss": 0.0045, + "step": 46701 + }, + { + "epoch": 14.42, + "learning_rate": 3.8083192163893847e-06, + "loss": 0.003, + "step": 46702 + }, + { + "epoch": 14.42, + "learning_rate": 3.807926502052388e-06, + "loss": 0.004, + "step": 46703 + }, + { + "epoch": 14.42, + "learning_rate": 3.807533803202893e-06, + "loss": 0.0031, + "step": 46704 + }, + { + "epoch": 14.42, + "learning_rate": 3.8071411198418895e-06, + "loss": 0.0036, + "step": 46705 + }, + { + "epoch": 14.42, + "learning_rate": 3.8067484519703525e-06, + "loss": 0.003, + "step": 46706 + }, + { + "epoch": 14.42, + "learning_rate": 3.8063557995892664e-06, + "loss": 0.0035, + "step": 46707 + }, + { + "epoch": 14.42, + "learning_rate": 3.8059631626996175e-06, + "loss": 0.0032, + "step": 46708 + }, + { + "epoch": 14.42, + "learning_rate": 3.8055705413023846e-06, + "loss": 0.004, + "step": 46709 + }, + { + "epoch": 14.42, + "learning_rate": 3.8051779353985465e-06, + "loss": 0.0025, + "step": 46710 + }, + { + "epoch": 14.43, + "learning_rate": 3.8047853449890903e-06, + "loss": 0.0036, + "step": 46711 + }, + { + "epoch": 14.43, + "learning_rate": 3.804392770074994e-06, + "loss": 0.003, + "step": 46712 + }, + { + "epoch": 14.43, + "learning_rate": 3.804000210657245e-06, + "loss": 0.0026, + "step": 46713 + }, + { + "epoch": 14.43, + "learning_rate": 3.8036076667368204e-06, + "loss": 0.0028, + "step": 46714 + }, + { + "epoch": 14.43, + "learning_rate": 3.8032151383146998e-06, + "loss": 0.0036, + "step": 46715 + }, + { + "epoch": 14.43, + "learning_rate": 3.802822625391869e-06, + "loss": 0.0035, + "step": 46716 + }, + { + "epoch": 14.43, + "learning_rate": 3.802430127969309e-06, + "loss": 0.0028, + "step": 46717 + }, + { + "epoch": 14.43, + "learning_rate": 3.8020376460480045e-06, + "loss": 0.004, + "step": 46718 + }, + { + "epoch": 14.43, + "learning_rate": 3.8016451796289353e-06, + "loss": 0.0031, + "step": 46719 + }, + { + "epoch": 14.43, + "learning_rate": 3.8012527287130785e-06, + "loss": 0.0034, + "step": 46720 + }, + { + "epoch": 14.43, + "learning_rate": 3.8008602933014215e-06, + "loss": 0.0035, + "step": 46721 + }, + { + "epoch": 14.43, + "learning_rate": 3.8004678733949407e-06, + "loss": 0.0029, + "step": 46722 + }, + { + "epoch": 14.43, + "learning_rate": 3.800075468994624e-06, + "loss": 0.0035, + "step": 46723 + }, + { + "epoch": 14.43, + "learning_rate": 3.7996830801014494e-06, + "loss": 0.0038, + "step": 46724 + }, + { + "epoch": 14.43, + "learning_rate": 3.799290706716395e-06, + "loss": 0.0027, + "step": 46725 + }, + { + "epoch": 14.43, + "learning_rate": 3.7988983488404453e-06, + "loss": 0.0044, + "step": 46726 + }, + { + "epoch": 14.43, + "learning_rate": 3.798506006474585e-06, + "loss": 0.0031, + "step": 46727 + }, + { + "epoch": 14.43, + "learning_rate": 3.798113679619789e-06, + "loss": 0.0028, + "step": 46728 + }, + { + "epoch": 14.43, + "learning_rate": 3.7977213682770455e-06, + "loss": 0.0039, + "step": 46729 + }, + { + "epoch": 14.43, + "learning_rate": 3.797329072447332e-06, + "loss": 0.0034, + "step": 46730 + }, + { + "epoch": 14.43, + "learning_rate": 3.7969367921316256e-06, + "loss": 0.0045, + "step": 46731 + }, + { + "epoch": 14.43, + "learning_rate": 3.796544527330913e-06, + "loss": 0.0031, + "step": 46732 + }, + { + "epoch": 14.43, + "learning_rate": 3.796152278046177e-06, + "loss": 0.004, + "step": 46733 + }, + { + "epoch": 14.43, + "learning_rate": 3.795760044278395e-06, + "loss": 0.0029, + "step": 46734 + }, + { + "epoch": 14.43, + "learning_rate": 3.7953678260285464e-06, + "loss": 0.0032, + "step": 46735 + }, + { + "epoch": 14.43, + "learning_rate": 3.7949756232976163e-06, + "loss": 0.0032, + "step": 46736 + }, + { + "epoch": 14.43, + "learning_rate": 3.7945834360865817e-06, + "loss": 0.0022, + "step": 46737 + }, + { + "epoch": 14.43, + "learning_rate": 3.794191264396425e-06, + "loss": 0.0049, + "step": 46738 + }, + { + "epoch": 14.43, + "learning_rate": 3.7937991082281358e-06, + "loss": 0.0034, + "step": 46739 + }, + { + "epoch": 14.43, + "learning_rate": 3.793406967582679e-06, + "loss": 0.0026, + "step": 46740 + }, + { + "epoch": 14.43, + "learning_rate": 3.7930148424610445e-06, + "loss": 0.0042, + "step": 46741 + }, + { + "epoch": 14.43, + "learning_rate": 3.792622732864214e-06, + "loss": 0.0037, + "step": 46742 + }, + { + "epoch": 14.44, + "learning_rate": 3.792230638793164e-06, + "loss": 0.0033, + "step": 46743 + }, + { + "epoch": 14.44, + "learning_rate": 3.7918385602488807e-06, + "loss": 0.0037, + "step": 46744 + }, + { + "epoch": 14.44, + "learning_rate": 3.7914464972323405e-06, + "loss": 0.0026, + "step": 46745 + }, + { + "epoch": 14.44, + "learning_rate": 3.7910544497445223e-06, + "loss": 0.0031, + "step": 46746 + }, + { + "epoch": 14.44, + "learning_rate": 3.7906624177864094e-06, + "loss": 0.0036, + "step": 46747 + }, + { + "epoch": 14.44, + "learning_rate": 3.7902704013589853e-06, + "loss": 0.0033, + "step": 46748 + }, + { + "epoch": 14.44, + "learning_rate": 3.789878400463227e-06, + "loss": 0.0042, + "step": 46749 + }, + { + "epoch": 14.44, + "learning_rate": 3.789486415100113e-06, + "loss": 0.0025, + "step": 46750 + }, + { + "epoch": 14.44, + "learning_rate": 3.7890944452706257e-06, + "loss": 0.0031, + "step": 46751 + }, + { + "epoch": 14.44, + "learning_rate": 3.7887024909757495e-06, + "loss": 0.004, + "step": 46752 + }, + { + "epoch": 14.44, + "learning_rate": 3.788310552216459e-06, + "loss": 0.0034, + "step": 46753 + }, + { + "epoch": 14.44, + "learning_rate": 3.7879186289937386e-06, + "loss": 0.0029, + "step": 46754 + }, + { + "epoch": 14.44, + "learning_rate": 3.7875267213085677e-06, + "loss": 0.004, + "step": 46755 + }, + { + "epoch": 14.44, + "learning_rate": 3.7871348291619215e-06, + "loss": 0.0034, + "step": 46756 + }, + { + "epoch": 14.44, + "learning_rate": 3.786742952554785e-06, + "loss": 0.0034, + "step": 46757 + }, + { + "epoch": 14.44, + "learning_rate": 3.7863510914881396e-06, + "loss": 0.0031, + "step": 46758 + }, + { + "epoch": 14.44, + "learning_rate": 3.7859592459629648e-06, + "loss": 0.003, + "step": 46759 + }, + { + "epoch": 14.44, + "learning_rate": 3.785567415980236e-06, + "loss": 0.0035, + "step": 46760 + }, + { + "epoch": 14.44, + "learning_rate": 3.785175601540939e-06, + "loss": 0.0041, + "step": 46761 + }, + { + "epoch": 14.44, + "learning_rate": 3.784783802646048e-06, + "loss": 0.0034, + "step": 46762 + }, + { + "epoch": 14.44, + "learning_rate": 3.7843920192965468e-06, + "loss": 0.0032, + "step": 46763 + }, + { + "epoch": 14.44, + "learning_rate": 3.7840002514934173e-06, + "loss": 0.0038, + "step": 46764 + }, + { + "epoch": 14.44, + "learning_rate": 3.7836084992376377e-06, + "loss": 0.0031, + "step": 46765 + }, + { + "epoch": 14.44, + "learning_rate": 3.7832167625301843e-06, + "loss": 0.0022, + "step": 46766 + }, + { + "epoch": 14.44, + "learning_rate": 3.782825041372041e-06, + "loss": 0.0042, + "step": 46767 + }, + { + "epoch": 14.44, + "learning_rate": 3.782433335764185e-06, + "loss": 0.0038, + "step": 46768 + }, + { + "epoch": 14.44, + "learning_rate": 3.782041645707599e-06, + "loss": 0.0033, + "step": 46769 + }, + { + "epoch": 14.44, + "learning_rate": 3.7816499712032617e-06, + "loss": 0.0024, + "step": 46770 + }, + { + "epoch": 14.44, + "learning_rate": 3.7812583122521482e-06, + "loss": 0.0029, + "step": 46771 + }, + { + "epoch": 14.44, + "learning_rate": 3.780866668855243e-06, + "loss": 0.004, + "step": 46772 + }, + { + "epoch": 14.44, + "learning_rate": 3.780475041013527e-06, + "loss": 0.0027, + "step": 46773 + }, + { + "epoch": 14.44, + "learning_rate": 3.780083428727974e-06, + "loss": 0.0034, + "step": 46774 + }, + { + "epoch": 14.44, + "learning_rate": 3.77969183199957e-06, + "loss": 0.0042, + "step": 46775 + }, + { + "epoch": 14.45, + "learning_rate": 3.779300250829292e-06, + "loss": 0.0033, + "step": 46776 + }, + { + "epoch": 14.45, + "learning_rate": 3.7789086852181144e-06, + "loss": 0.0041, + "step": 46777 + }, + { + "epoch": 14.45, + "learning_rate": 3.7785171351670213e-06, + "loss": 0.007, + "step": 46778 + }, + { + "epoch": 14.45, + "learning_rate": 3.778125600676995e-06, + "loss": 0.0031, + "step": 46779 + }, + { + "epoch": 14.45, + "learning_rate": 3.7777340817490115e-06, + "loss": 0.0034, + "step": 46780 + }, + { + "epoch": 14.45, + "learning_rate": 3.7773425783840455e-06, + "loss": 0.0038, + "step": 46781 + }, + { + "epoch": 14.45, + "learning_rate": 3.776951090583082e-06, + "loss": 0.0036, + "step": 46782 + }, + { + "epoch": 14.45, + "learning_rate": 3.776559618347102e-06, + "loss": 0.0028, + "step": 46783 + }, + { + "epoch": 14.45, + "learning_rate": 3.7761681616770774e-06, + "loss": 0.0036, + "step": 46784 + }, + { + "epoch": 14.45, + "learning_rate": 3.775776720573995e-06, + "loss": 0.0037, + "step": 46785 + }, + { + "epoch": 14.45, + "learning_rate": 3.7753852950388305e-06, + "loss": 0.0029, + "step": 46786 + }, + { + "epoch": 14.45, + "learning_rate": 3.7749938850725586e-06, + "loss": 0.003, + "step": 46787 + }, + { + "epoch": 14.45, + "learning_rate": 3.7746024906761637e-06, + "loss": 0.0045, + "step": 46788 + }, + { + "epoch": 14.45, + "learning_rate": 3.774211111850625e-06, + "loss": 0.0031, + "step": 46789 + }, + { + "epoch": 14.45, + "learning_rate": 3.7738197485969217e-06, + "loss": 0.0031, + "step": 46790 + }, + { + "epoch": 14.45, + "learning_rate": 3.773428400916026e-06, + "loss": 0.0048, + "step": 46791 + }, + { + "epoch": 14.45, + "learning_rate": 3.7730370688089257e-06, + "loss": 0.0029, + "step": 46792 + }, + { + "epoch": 14.45, + "learning_rate": 3.7726457522765923e-06, + "loss": 0.0029, + "step": 46793 + }, + { + "epoch": 14.45, + "learning_rate": 3.7722544513200064e-06, + "loss": 0.0023, + "step": 46794 + }, + { + "epoch": 14.45, + "learning_rate": 3.7718631659401527e-06, + "loss": 0.0032, + "step": 46795 + }, + { + "epoch": 14.45, + "learning_rate": 3.771471896138005e-06, + "loss": 0.0037, + "step": 46796 + }, + { + "epoch": 14.45, + "learning_rate": 3.7710806419145374e-06, + "loss": 0.0035, + "step": 46797 + }, + { + "epoch": 14.45, + "learning_rate": 3.7706894032707375e-06, + "loss": 0.0038, + "step": 46798 + }, + { + "epoch": 14.45, + "learning_rate": 3.7702981802075767e-06, + "loss": 0.0037, + "step": 46799 + }, + { + "epoch": 14.45, + "learning_rate": 3.7699069727260394e-06, + "loss": 0.0034, + "step": 46800 + }, + { + "epoch": 14.45, + "learning_rate": 3.769515780827101e-06, + "loss": 0.003, + "step": 46801 + }, + { + "epoch": 14.45, + "learning_rate": 3.7691246045117357e-06, + "loss": 0.0027, + "step": 46802 + }, + { + "epoch": 14.45, + "learning_rate": 3.7687334437809274e-06, + "loss": 0.0034, + "step": 46803 + }, + { + "epoch": 14.45, + "learning_rate": 3.7683422986356566e-06, + "loss": 0.0042, + "step": 46804 + }, + { + "epoch": 14.45, + "learning_rate": 3.7679511690768945e-06, + "loss": 0.0032, + "step": 46805 + }, + { + "epoch": 14.45, + "learning_rate": 3.767560055105627e-06, + "loss": 0.0033, + "step": 46806 + }, + { + "epoch": 14.45, + "learning_rate": 3.7671689567228276e-06, + "loss": 0.0037, + "step": 46807 + }, + { + "epoch": 14.46, + "learning_rate": 3.7667778739294723e-06, + "loss": 0.0031, + "step": 46808 + }, + { + "epoch": 14.46, + "learning_rate": 3.766386806726543e-06, + "loss": 0.0037, + "step": 46809 + }, + { + "epoch": 14.46, + "learning_rate": 3.7659957551150207e-06, + "loss": 0.0032, + "step": 46810 + }, + { + "epoch": 14.46, + "learning_rate": 3.765604719095879e-06, + "loss": 0.0038, + "step": 46811 + }, + { + "epoch": 14.46, + "learning_rate": 3.765213698670095e-06, + "loss": 0.003, + "step": 46812 + }, + { + "epoch": 14.46, + "learning_rate": 3.764822693838651e-06, + "loss": 0.0029, + "step": 46813 + }, + { + "epoch": 14.46, + "learning_rate": 3.7644317046025192e-06, + "loss": 0.0041, + "step": 46814 + }, + { + "epoch": 14.46, + "learning_rate": 3.7640407309626813e-06, + "loss": 0.004, + "step": 46815 + }, + { + "epoch": 14.46, + "learning_rate": 3.763649772920119e-06, + "loss": 0.0039, + "step": 46816 + }, + { + "epoch": 14.46, + "learning_rate": 3.7632588304758055e-06, + "loss": 0.004, + "step": 46817 + }, + { + "epoch": 14.46, + "learning_rate": 3.7628679036307157e-06, + "loss": 0.003, + "step": 46818 + }, + { + "epoch": 14.46, + "learning_rate": 3.7624769923858307e-06, + "loss": 0.0041, + "step": 46819 + }, + { + "epoch": 14.46, + "learning_rate": 3.7620860967421325e-06, + "loss": 0.0036, + "step": 46820 + }, + { + "epoch": 14.46, + "learning_rate": 3.7616952167005936e-06, + "loss": 0.004, + "step": 46821 + }, + { + "epoch": 14.46, + "learning_rate": 3.7613043522621906e-06, + "loss": 0.004, + "step": 46822 + }, + { + "epoch": 14.46, + "learning_rate": 3.760913503427905e-06, + "loss": 0.0029, + "step": 46823 + }, + { + "epoch": 14.46, + "learning_rate": 3.7605226701987107e-06, + "loss": 0.0035, + "step": 46824 + }, + { + "epoch": 14.46, + "learning_rate": 3.760131852575587e-06, + "loss": 0.0036, + "step": 46825 + }, + { + "epoch": 14.46, + "learning_rate": 3.7597410505595155e-06, + "loss": 0.0032, + "step": 46826 + }, + { + "epoch": 14.46, + "learning_rate": 3.759350264151469e-06, + "loss": 0.0025, + "step": 46827 + }, + { + "epoch": 14.46, + "learning_rate": 3.758959493352422e-06, + "loss": 0.003, + "step": 46828 + }, + { + "epoch": 14.46, + "learning_rate": 3.7585687381633594e-06, + "loss": 0.0037, + "step": 46829 + }, + { + "epoch": 14.46, + "learning_rate": 3.758177998585252e-06, + "loss": 0.0032, + "step": 46830 + }, + { + "epoch": 14.46, + "learning_rate": 3.7577872746190825e-06, + "loss": 0.0028, + "step": 46831 + }, + { + "epoch": 14.46, + "learning_rate": 3.757396566265825e-06, + "loss": 0.0029, + "step": 46832 + }, + { + "epoch": 14.46, + "learning_rate": 3.757005873526455e-06, + "loss": 0.0042, + "step": 46833 + }, + { + "epoch": 14.46, + "learning_rate": 3.7566151964019517e-06, + "loss": 0.0042, + "step": 46834 + }, + { + "epoch": 14.46, + "learning_rate": 3.7562245348932958e-06, + "loss": 0.0031, + "step": 46835 + }, + { + "epoch": 14.46, + "learning_rate": 3.755833889001458e-06, + "loss": 0.0044, + "step": 46836 + }, + { + "epoch": 14.46, + "learning_rate": 3.7554432587274214e-06, + "loss": 0.0031, + "step": 46837 + }, + { + "epoch": 14.46, + "learning_rate": 3.75505264407216e-06, + "loss": 0.0033, + "step": 46838 + }, + { + "epoch": 14.46, + "learning_rate": 3.754662045036648e-06, + "loss": 0.0029, + "step": 46839 + }, + { + "epoch": 14.47, + "learning_rate": 3.7542714616218644e-06, + "loss": 0.0031, + "step": 46840 + }, + { + "epoch": 14.47, + "learning_rate": 3.753880893828792e-06, + "loss": 0.0026, + "step": 46841 + }, + { + "epoch": 14.47, + "learning_rate": 3.7534903416584023e-06, + "loss": 0.0032, + "step": 46842 + }, + { + "epoch": 14.47, + "learning_rate": 3.7530998051116683e-06, + "loss": 0.003, + "step": 46843 + }, + { + "epoch": 14.47, + "learning_rate": 3.752709284189575e-06, + "loss": 0.0029, + "step": 46844 + }, + { + "epoch": 14.47, + "learning_rate": 3.7523187788930914e-06, + "loss": 0.0036, + "step": 46845 + }, + { + "epoch": 14.47, + "learning_rate": 3.751928289223199e-06, + "loss": 0.0036, + "step": 46846 + }, + { + "epoch": 14.47, + "learning_rate": 3.751537815180879e-06, + "loss": 0.0031, + "step": 46847 + }, + { + "epoch": 14.47, + "learning_rate": 3.7511473567670966e-06, + "loss": 0.003, + "step": 46848 + }, + { + "epoch": 14.47, + "learning_rate": 3.7507569139828335e-06, + "loss": 0.004, + "step": 46849 + }, + { + "epoch": 14.47, + "learning_rate": 3.750366486829069e-06, + "loss": 0.0033, + "step": 46850 + }, + { + "epoch": 14.47, + "learning_rate": 3.7499760753067795e-06, + "loss": 0.0038, + "step": 46851 + }, + { + "epoch": 14.47, + "learning_rate": 3.7495856794169404e-06, + "loss": 0.0042, + "step": 46852 + }, + { + "epoch": 14.47, + "learning_rate": 3.749195299160524e-06, + "loss": 0.0027, + "step": 46853 + }, + { + "epoch": 14.47, + "learning_rate": 3.7488049345385134e-06, + "loss": 0.0039, + "step": 46854 + }, + { + "epoch": 14.47, + "learning_rate": 3.7484145855518795e-06, + "loss": 0.0044, + "step": 46855 + }, + { + "epoch": 14.47, + "learning_rate": 3.7480242522015996e-06, + "loss": 0.0026, + "step": 46856 + }, + { + "epoch": 14.47, + "learning_rate": 3.747633934488656e-06, + "loss": 0.0028, + "step": 46857 + }, + { + "epoch": 14.47, + "learning_rate": 3.7472436324140193e-06, + "loss": 0.0039, + "step": 46858 + }, + { + "epoch": 14.47, + "learning_rate": 3.7468533459786637e-06, + "loss": 0.0039, + "step": 46859 + }, + { + "epoch": 14.47, + "learning_rate": 3.746463075183572e-06, + "loss": 0.0038, + "step": 46860 + }, + { + "epoch": 14.47, + "learning_rate": 3.7460728200297123e-06, + "loss": 0.0048, + "step": 46861 + }, + { + "epoch": 14.47, + "learning_rate": 3.74568258051807e-06, + "loss": 0.0043, + "step": 46862 + }, + { + "epoch": 14.47, + "learning_rate": 3.7452923566496147e-06, + "loss": 0.0032, + "step": 46863 + }, + { + "epoch": 14.47, + "learning_rate": 3.744902148425321e-06, + "loss": 0.0038, + "step": 46864 + }, + { + "epoch": 14.47, + "learning_rate": 3.7445119558461683e-06, + "loss": 0.0051, + "step": 46865 + }, + { + "epoch": 14.47, + "learning_rate": 3.7441217789131357e-06, + "loss": 0.0041, + "step": 46866 + }, + { + "epoch": 14.47, + "learning_rate": 3.743731617627192e-06, + "loss": 0.0032, + "step": 46867 + }, + { + "epoch": 14.47, + "learning_rate": 3.74334147198932e-06, + "loss": 0.0048, + "step": 46868 + }, + { + "epoch": 14.47, + "learning_rate": 3.7429513420004916e-06, + "loss": 0.0034, + "step": 46869 + }, + { + "epoch": 14.47, + "learning_rate": 3.7425612276616806e-06, + "loss": 0.0057, + "step": 46870 + }, + { + "epoch": 14.47, + "learning_rate": 3.742171128973865e-06, + "loss": 0.0034, + "step": 46871 + }, + { + "epoch": 14.47, + "learning_rate": 3.7417810459380234e-06, + "loss": 0.003, + "step": 46872 + }, + { + "epoch": 14.48, + "learning_rate": 3.7413909785551293e-06, + "loss": 0.0033, + "step": 46873 + }, + { + "epoch": 14.48, + "learning_rate": 3.741000926826155e-06, + "loss": 0.0033, + "step": 46874 + }, + { + "epoch": 14.48, + "learning_rate": 3.740610890752082e-06, + "loss": 0.003, + "step": 46875 + }, + { + "epoch": 14.48, + "learning_rate": 3.7402208703338795e-06, + "loss": 0.0036, + "step": 46876 + }, + { + "epoch": 14.48, + "learning_rate": 3.739830865572526e-06, + "loss": 0.0037, + "step": 46877 + }, + { + "epoch": 14.48, + "learning_rate": 3.7394408764690036e-06, + "loss": 0.0031, + "step": 46878 + }, + { + "epoch": 14.48, + "learning_rate": 3.739050903024276e-06, + "loss": 0.0029, + "step": 46879 + }, + { + "epoch": 14.48, + "learning_rate": 3.7386609452393228e-06, + "loss": 0.0032, + "step": 46880 + }, + { + "epoch": 14.48, + "learning_rate": 3.7382710031151213e-06, + "loss": 0.0032, + "step": 46881 + }, + { + "epoch": 14.48, + "learning_rate": 3.7378810766526484e-06, + "loss": 0.0037, + "step": 46882 + }, + { + "epoch": 14.48, + "learning_rate": 3.737491165852879e-06, + "loss": 0.0025, + "step": 46883 + }, + { + "epoch": 14.48, + "learning_rate": 3.737101270716782e-06, + "loss": 0.0028, + "step": 46884 + }, + { + "epoch": 14.48, + "learning_rate": 3.73671139124534e-06, + "loss": 0.0034, + "step": 46885 + }, + { + "epoch": 14.48, + "learning_rate": 3.7363215274395216e-06, + "loss": 0.0036, + "step": 46886 + }, + { + "epoch": 14.48, + "learning_rate": 3.7359316793003066e-06, + "loss": 0.0042, + "step": 46887 + }, + { + "epoch": 14.48, + "learning_rate": 3.7355418468286752e-06, + "loss": 0.0033, + "step": 46888 + }, + { + "epoch": 14.48, + "learning_rate": 3.7351520300255885e-06, + "loss": 0.0042, + "step": 46889 + }, + { + "epoch": 14.48, + "learning_rate": 3.7347622288920303e-06, + "loss": 0.0024, + "step": 46890 + }, + { + "epoch": 14.48, + "learning_rate": 3.7343724434289776e-06, + "loss": 0.0033, + "step": 46891 + }, + { + "epoch": 14.48, + "learning_rate": 3.7339826736373985e-06, + "loss": 0.0042, + "step": 46892 + }, + { + "epoch": 14.48, + "learning_rate": 3.7335929195182753e-06, + "loss": 0.0031, + "step": 46893 + }, + { + "epoch": 14.48, + "learning_rate": 3.73320318107258e-06, + "loss": 0.0034, + "step": 46894 + }, + { + "epoch": 14.48, + "learning_rate": 3.732813458301282e-06, + "loss": 0.0044, + "step": 46895 + }, + { + "epoch": 14.48, + "learning_rate": 3.7324237512053605e-06, + "loss": 0.0032, + "step": 46896 + }, + { + "epoch": 14.48, + "learning_rate": 3.732034059785794e-06, + "loss": 0.0034, + "step": 46897 + }, + { + "epoch": 14.48, + "learning_rate": 3.7316443840435536e-06, + "loss": 0.0038, + "step": 46898 + }, + { + "epoch": 14.48, + "learning_rate": 3.7312547239796105e-06, + "loss": 0.0051, + "step": 46899 + }, + { + "epoch": 14.48, + "learning_rate": 3.7308650795949464e-06, + "loss": 0.0051, + "step": 46900 + }, + { + "epoch": 14.48, + "learning_rate": 3.7304754508905283e-06, + "loss": 0.0036, + "step": 46901 + }, + { + "epoch": 14.48, + "learning_rate": 3.7300858378673345e-06, + "loss": 0.0029, + "step": 46902 + }, + { + "epoch": 14.48, + "learning_rate": 3.7296962405263437e-06, + "loss": 0.0036, + "step": 46903 + }, + { + "epoch": 14.48, + "learning_rate": 3.729306658868526e-06, + "loss": 0.0035, + "step": 46904 + }, + { + "epoch": 14.49, + "learning_rate": 3.7289170928948515e-06, + "loss": 0.0035, + "step": 46905 + }, + { + "epoch": 14.49, + "learning_rate": 3.7285275426063038e-06, + "loss": 0.0024, + "step": 46906 + }, + { + "epoch": 14.49, + "learning_rate": 3.7281380080038487e-06, + "loss": 0.0042, + "step": 46907 + }, + { + "epoch": 14.49, + "learning_rate": 3.7277484890884674e-06, + "loss": 0.0038, + "step": 46908 + }, + { + "epoch": 14.49, + "learning_rate": 3.7273589858611312e-06, + "loss": 0.0039, + "step": 46909 + }, + { + "epoch": 14.49, + "learning_rate": 3.726969498322812e-06, + "loss": 0.0038, + "step": 46910 + }, + { + "epoch": 14.49, + "learning_rate": 3.7265800264744856e-06, + "loss": 0.0031, + "step": 46911 + }, + { + "epoch": 14.49, + "learning_rate": 3.72619057031713e-06, + "loss": 0.0035, + "step": 46912 + }, + { + "epoch": 14.49, + "learning_rate": 3.7258011298517117e-06, + "loss": 0.0031, + "step": 46913 + }, + { + "epoch": 14.49, + "learning_rate": 3.7254117050792136e-06, + "loss": 0.0048, + "step": 46914 + }, + { + "epoch": 14.49, + "learning_rate": 3.725022296000602e-06, + "loss": 0.0033, + "step": 46915 + }, + { + "epoch": 14.49, + "learning_rate": 3.7246329026168573e-06, + "loss": 0.0038, + "step": 46916 + }, + { + "epoch": 14.49, + "learning_rate": 3.7242435249289467e-06, + "loss": 0.003, + "step": 46917 + }, + { + "epoch": 14.49, + "learning_rate": 3.723854162937851e-06, + "loss": 0.0039, + "step": 46918 + }, + { + "epoch": 14.49, + "learning_rate": 3.7234648166445407e-06, + "loss": 0.0038, + "step": 46919 + }, + { + "epoch": 14.49, + "learning_rate": 3.723075486049986e-06, + "loss": 0.0033, + "step": 46920 + }, + { + "epoch": 14.49, + "learning_rate": 3.7226861711551653e-06, + "loss": 0.0032, + "step": 46921 + }, + { + "epoch": 14.49, + "learning_rate": 3.7222968719610543e-06, + "loss": 0.0034, + "step": 46922 + }, + { + "epoch": 14.49, + "learning_rate": 3.721907588468621e-06, + "loss": 0.0032, + "step": 46923 + }, + { + "epoch": 14.49, + "learning_rate": 3.7215183206788442e-06, + "loss": 0.0029, + "step": 46924 + }, + { + "epoch": 14.49, + "learning_rate": 3.721129068592695e-06, + "loss": 0.0045, + "step": 46925 + }, + { + "epoch": 14.49, + "learning_rate": 3.7207398322111444e-06, + "loss": 0.0031, + "step": 46926 + }, + { + "epoch": 14.49, + "learning_rate": 3.7203506115351695e-06, + "loss": 0.0042, + "step": 46927 + }, + { + "epoch": 14.49, + "learning_rate": 3.719961406565745e-06, + "loss": 0.0039, + "step": 46928 + }, + { + "epoch": 14.49, + "learning_rate": 3.719572217303844e-06, + "loss": 0.0041, + "step": 46929 + }, + { + "epoch": 14.49, + "learning_rate": 3.719183043750434e-06, + "loss": 0.0037, + "step": 46930 + }, + { + "epoch": 14.49, + "learning_rate": 3.7187938859064955e-06, + "loss": 0.0046, + "step": 46931 + }, + { + "epoch": 14.49, + "learning_rate": 3.7184047437729965e-06, + "loss": 0.0027, + "step": 46932 + }, + { + "epoch": 14.49, + "learning_rate": 3.718015617350913e-06, + "loss": 0.0039, + "step": 46933 + }, + { + "epoch": 14.49, + "learning_rate": 3.717626506641222e-06, + "loss": 0.004, + "step": 46934 + }, + { + "epoch": 14.49, + "learning_rate": 3.717237411644893e-06, + "loss": 0.0031, + "step": 46935 + }, + { + "epoch": 14.49, + "learning_rate": 3.7168483323628945e-06, + "loss": 0.0038, + "step": 46936 + }, + { + "epoch": 14.5, + "learning_rate": 3.716459268796209e-06, + "loss": 0.0039, + "step": 46937 + }, + { + "epoch": 14.5, + "learning_rate": 3.7160702209458e-06, + "loss": 0.0032, + "step": 46938 + }, + { + "epoch": 14.5, + "learning_rate": 3.71568118881265e-06, + "loss": 0.0033, + "step": 46939 + }, + { + "epoch": 14.5, + "learning_rate": 3.7152921723977275e-06, + "loss": 0.0033, + "step": 46940 + }, + { + "epoch": 14.5, + "learning_rate": 3.7149031717020022e-06, + "loss": 0.0034, + "step": 46941 + }, + { + "epoch": 14.5, + "learning_rate": 3.71451418672645e-06, + "loss": 0.004, + "step": 46942 + }, + { + "epoch": 14.5, + "learning_rate": 3.7141252174720477e-06, + "loss": 0.0042, + "step": 46943 + }, + { + "epoch": 14.5, + "learning_rate": 3.713736263939761e-06, + "loss": 0.0032, + "step": 46944 + }, + { + "epoch": 14.5, + "learning_rate": 3.713347326130571e-06, + "loss": 0.0037, + "step": 46945 + }, + { + "epoch": 14.5, + "learning_rate": 3.7129584040454414e-06, + "loss": 0.0032, + "step": 46946 + }, + { + "epoch": 14.5, + "learning_rate": 3.7125694976853534e-06, + "loss": 0.0034, + "step": 46947 + }, + { + "epoch": 14.5, + "learning_rate": 3.7121806070512725e-06, + "loss": 0.0031, + "step": 46948 + }, + { + "epoch": 14.5, + "learning_rate": 3.7117917321441776e-06, + "loss": 0.0039, + "step": 46949 + }, + { + "epoch": 14.5, + "learning_rate": 3.7114028729650386e-06, + "loss": 0.0029, + "step": 46950 + }, + { + "epoch": 14.5, + "learning_rate": 3.7110140295148254e-06, + "loss": 0.004, + "step": 46951 + }, + { + "epoch": 14.5, + "learning_rate": 3.710625201794512e-06, + "loss": 0.003, + "step": 46952 + }, + { + "epoch": 14.5, + "learning_rate": 3.7102363898050763e-06, + "loss": 0.0043, + "step": 46953 + }, + { + "epoch": 14.5, + "learning_rate": 3.7098475935474833e-06, + "loss": 0.005, + "step": 46954 + }, + { + "epoch": 14.5, + "learning_rate": 3.7094588130227117e-06, + "loss": 0.0043, + "step": 46955 + }, + { + "epoch": 14.5, + "learning_rate": 3.709070048231731e-06, + "loss": 0.0023, + "step": 46956 + }, + { + "epoch": 14.5, + "learning_rate": 3.7086812991755105e-06, + "loss": 0.0035, + "step": 46957 + }, + { + "epoch": 14.5, + "learning_rate": 3.708292565855025e-06, + "loss": 0.0036, + "step": 46958 + }, + { + "epoch": 14.5, + "learning_rate": 3.7079038482712505e-06, + "loss": 0.0044, + "step": 46959 + }, + { + "epoch": 14.5, + "learning_rate": 3.707515146425157e-06, + "loss": 0.0037, + "step": 46960 + }, + { + "epoch": 14.5, + "learning_rate": 3.7071264603177114e-06, + "loss": 0.0038, + "step": 46961 + }, + { + "epoch": 14.5, + "learning_rate": 3.7067377899498947e-06, + "loss": 0.0031, + "step": 46962 + }, + { + "epoch": 14.5, + "learning_rate": 3.70634913532267e-06, + "loss": 0.0038, + "step": 46963 + }, + { + "epoch": 14.5, + "learning_rate": 3.7059604964370144e-06, + "loss": 0.003, + "step": 46964 + }, + { + "epoch": 14.5, + "learning_rate": 3.705571873293904e-06, + "loss": 0.0032, + "step": 46965 + }, + { + "epoch": 14.5, + "learning_rate": 3.7051832658943053e-06, + "loss": 0.0027, + "step": 46966 + }, + { + "epoch": 14.5, + "learning_rate": 3.704794674239188e-06, + "loss": 0.0034, + "step": 46967 + }, + { + "epoch": 14.5, + "learning_rate": 3.7044060983295305e-06, + "loss": 0.0032, + "step": 46968 + }, + { + "epoch": 14.5, + "learning_rate": 3.704017538166299e-06, + "loss": 0.0043, + "step": 46969 + }, + { + "epoch": 14.51, + "learning_rate": 3.7036289937504712e-06, + "loss": 0.0032, + "step": 46970 + }, + { + "epoch": 14.51, + "learning_rate": 3.7032404650830157e-06, + "loss": 0.0028, + "step": 46971 + }, + { + "epoch": 14.51, + "learning_rate": 3.7028519521649007e-06, + "loss": 0.0041, + "step": 46972 + }, + { + "epoch": 14.51, + "learning_rate": 3.7024634549971017e-06, + "loss": 0.0031, + "step": 46973 + }, + { + "epoch": 14.51, + "learning_rate": 3.7020749735805926e-06, + "loss": 0.0029, + "step": 46974 + }, + { + "epoch": 14.51, + "learning_rate": 3.70168650791634e-06, + "loss": 0.0037, + "step": 46975 + }, + { + "epoch": 14.51, + "learning_rate": 3.7012980580053215e-06, + "loss": 0.0031, + "step": 46976 + }, + { + "epoch": 14.51, + "learning_rate": 3.7009096238485067e-06, + "loss": 0.0037, + "step": 46977 + }, + { + "epoch": 14.51, + "learning_rate": 3.700521205446861e-06, + "loss": 0.0032, + "step": 46978 + }, + { + "epoch": 14.51, + "learning_rate": 3.7001328028013606e-06, + "loss": 0.0045, + "step": 46979 + }, + { + "epoch": 14.51, + "learning_rate": 3.69974441591298e-06, + "loss": 0.004, + "step": 46980 + }, + { + "epoch": 14.51, + "learning_rate": 3.6993560447826893e-06, + "loss": 0.004, + "step": 46981 + }, + { + "epoch": 14.51, + "learning_rate": 3.6989676894114535e-06, + "loss": 0.0032, + "step": 46982 + }, + { + "epoch": 14.51, + "learning_rate": 3.6985793498002496e-06, + "loss": 0.003, + "step": 46983 + }, + { + "epoch": 14.51, + "learning_rate": 3.698191025950052e-06, + "loss": 0.003, + "step": 46984 + }, + { + "epoch": 14.51, + "learning_rate": 3.697802717861824e-06, + "loss": 0.0036, + "step": 46985 + }, + { + "epoch": 14.51, + "learning_rate": 3.697414425536543e-06, + "loss": 0.0031, + "step": 46986 + }, + { + "epoch": 14.51, + "learning_rate": 3.697026148975179e-06, + "loss": 0.0038, + "step": 46987 + }, + { + "epoch": 14.51, + "learning_rate": 3.696637888178699e-06, + "loss": 0.0039, + "step": 46988 + }, + { + "epoch": 14.51, + "learning_rate": 3.6962496431480775e-06, + "loss": 0.0039, + "step": 46989 + }, + { + "epoch": 14.51, + "learning_rate": 3.6958614138842886e-06, + "loss": 0.0042, + "step": 46990 + }, + { + "epoch": 14.51, + "learning_rate": 3.6954732003883e-06, + "loss": 0.0026, + "step": 46991 + }, + { + "epoch": 14.51, + "learning_rate": 3.6950850026610796e-06, + "loss": 0.004, + "step": 46992 + }, + { + "epoch": 14.51, + "learning_rate": 3.6946968207036047e-06, + "loss": 0.0032, + "step": 46993 + }, + { + "epoch": 14.51, + "learning_rate": 3.6943086545168394e-06, + "loss": 0.004, + "step": 46994 + }, + { + "epoch": 14.51, + "learning_rate": 3.693920504101759e-06, + "loss": 0.0027, + "step": 46995 + }, + { + "epoch": 14.51, + "learning_rate": 3.6935323694593395e-06, + "loss": 0.0033, + "step": 46996 + }, + { + "epoch": 14.51, + "learning_rate": 3.69314425059054e-06, + "loss": 0.0032, + "step": 46997 + }, + { + "epoch": 14.51, + "learning_rate": 3.6927561474963358e-06, + "loss": 0.0031, + "step": 46998 + }, + { + "epoch": 14.51, + "learning_rate": 3.6923680601777035e-06, + "loss": 0.0036, + "step": 46999 + }, + { + "epoch": 14.51, + "learning_rate": 3.6919799886356044e-06, + "loss": 0.0041, + "step": 47000 + }, + { + "epoch": 14.51, + "learning_rate": 3.6915919328710183e-06, + "loss": 0.0031, + "step": 47001 + }, + { + "epoch": 14.52, + "learning_rate": 3.6912038928849115e-06, + "loss": 0.0035, + "step": 47002 + }, + { + "epoch": 14.52, + "learning_rate": 3.6908158686782505e-06, + "loss": 0.0033, + "step": 47003 + }, + { + "epoch": 14.52, + "learning_rate": 3.6904278602520094e-06, + "loss": 0.0031, + "step": 47004 + }, + { + "epoch": 14.52, + "learning_rate": 3.6900398676071627e-06, + "loss": 0.0028, + "step": 47005 + }, + { + "epoch": 14.52, + "learning_rate": 3.6896518907446777e-06, + "loss": 0.0045, + "step": 47006 + }, + { + "epoch": 14.52, + "learning_rate": 3.6892639296655196e-06, + "loss": 0.003, + "step": 47007 + }, + { + "epoch": 14.52, + "learning_rate": 3.688875984370668e-06, + "loss": 0.0032, + "step": 47008 + }, + { + "epoch": 14.52, + "learning_rate": 3.688488054861085e-06, + "loss": 0.0042, + "step": 47009 + }, + { + "epoch": 14.52, + "learning_rate": 3.688100141137745e-06, + "loss": 0.0034, + "step": 47010 + }, + { + "epoch": 14.52, + "learning_rate": 3.68771224320162e-06, + "loss": 0.0027, + "step": 47011 + }, + { + "epoch": 14.52, + "learning_rate": 3.687324361053679e-06, + "loss": 0.0038, + "step": 47012 + }, + { + "epoch": 14.52, + "learning_rate": 3.686936494694887e-06, + "loss": 0.0035, + "step": 47013 + }, + { + "epoch": 14.52, + "learning_rate": 3.686548644126219e-06, + "loss": 0.0024, + "step": 47014 + }, + { + "epoch": 14.52, + "learning_rate": 3.686160809348647e-06, + "loss": 0.0045, + "step": 47015 + }, + { + "epoch": 14.52, + "learning_rate": 3.685772990363138e-06, + "loss": 0.0033, + "step": 47016 + }, + { + "epoch": 14.52, + "learning_rate": 3.6853851871706603e-06, + "loss": 0.0033, + "step": 47017 + }, + { + "epoch": 14.52, + "learning_rate": 3.6849973997721877e-06, + "loss": 0.0037, + "step": 47018 + }, + { + "epoch": 14.52, + "learning_rate": 3.6846096281686862e-06, + "loss": 0.0045, + "step": 47019 + }, + { + "epoch": 14.52, + "learning_rate": 3.684221872361128e-06, + "loss": 0.0037, + "step": 47020 + }, + { + "epoch": 14.52, + "learning_rate": 3.6838341323504856e-06, + "loss": 0.003, + "step": 47021 + }, + { + "epoch": 14.52, + "learning_rate": 3.6834464081377262e-06, + "loss": 0.0029, + "step": 47022 + }, + { + "epoch": 14.52, + "learning_rate": 3.683058699723816e-06, + "loss": 0.0034, + "step": 47023 + }, + { + "epoch": 14.52, + "learning_rate": 3.6826710071097326e-06, + "loss": 0.0037, + "step": 47024 + }, + { + "epoch": 14.52, + "learning_rate": 3.6822833302964367e-06, + "loss": 0.0031, + "step": 47025 + }, + { + "epoch": 14.52, + "learning_rate": 3.681895669284906e-06, + "loss": 0.0046, + "step": 47026 + }, + { + "epoch": 14.52, + "learning_rate": 3.681508024076107e-06, + "loss": 0.0039, + "step": 47027 + }, + { + "epoch": 14.52, + "learning_rate": 3.681120394671005e-06, + "loss": 0.0037, + "step": 47028 + }, + { + "epoch": 14.52, + "learning_rate": 3.6807327810705726e-06, + "loss": 0.0038, + "step": 47029 + }, + { + "epoch": 14.52, + "learning_rate": 3.6803451832757853e-06, + "loss": 0.004, + "step": 47030 + }, + { + "epoch": 14.52, + "learning_rate": 3.6799576012876026e-06, + "loss": 0.0028, + "step": 47031 + }, + { + "epoch": 14.52, + "learning_rate": 3.679570035107002e-06, + "loss": 0.0025, + "step": 47032 + }, + { + "epoch": 14.52, + "learning_rate": 3.67918248473495e-06, + "loss": 0.004, + "step": 47033 + }, + { + "epoch": 14.52, + "learning_rate": 3.678794950172412e-06, + "loss": 0.0036, + "step": 47034 + }, + { + "epoch": 14.53, + "learning_rate": 3.678407431420361e-06, + "loss": 0.003, + "step": 47035 + }, + { + "epoch": 14.53, + "learning_rate": 3.6780199284797693e-06, + "loss": 0.0031, + "step": 47036 + }, + { + "epoch": 14.53, + "learning_rate": 3.6776324413516017e-06, + "loss": 0.0036, + "step": 47037 + }, + { + "epoch": 14.53, + "learning_rate": 3.677244970036826e-06, + "loss": 0.0031, + "step": 47038 + }, + { + "epoch": 14.53, + "learning_rate": 3.676857514536418e-06, + "loss": 0.0031, + "step": 47039 + }, + { + "epoch": 14.53, + "learning_rate": 3.6764700748513384e-06, + "loss": 0.0034, + "step": 47040 + }, + { + "epoch": 14.53, + "learning_rate": 3.676082650982561e-06, + "loss": 0.0028, + "step": 47041 + }, + { + "epoch": 14.53, + "learning_rate": 3.6756952429310566e-06, + "loss": 0.0041, + "step": 47042 + }, + { + "epoch": 14.53, + "learning_rate": 3.675307850697792e-06, + "loss": 0.0032, + "step": 47043 + }, + { + "epoch": 14.53, + "learning_rate": 3.674920474283734e-06, + "loss": 0.004, + "step": 47044 + }, + { + "epoch": 14.53, + "learning_rate": 3.6745331136898523e-06, + "loss": 0.0028, + "step": 47045 + }, + { + "epoch": 14.53, + "learning_rate": 3.6741457689171212e-06, + "loss": 0.0035, + "step": 47046 + }, + { + "epoch": 14.53, + "learning_rate": 3.673758439966505e-06, + "loss": 0.005, + "step": 47047 + }, + { + "epoch": 14.53, + "learning_rate": 3.6733711268389695e-06, + "loss": 0.0034, + "step": 47048 + }, + { + "epoch": 14.53, + "learning_rate": 3.672983829535489e-06, + "loss": 0.0041, + "step": 47049 + }, + { + "epoch": 14.53, + "learning_rate": 3.672596548057028e-06, + "loss": 0.003, + "step": 47050 + }, + { + "epoch": 14.53, + "learning_rate": 3.6722092824045562e-06, + "loss": 0.0031, + "step": 47051 + }, + { + "epoch": 14.53, + "learning_rate": 3.6718220325790466e-06, + "loss": 0.0032, + "step": 47052 + }, + { + "epoch": 14.53, + "learning_rate": 3.6714347985814648e-06, + "loss": 0.004, + "step": 47053 + }, + { + "epoch": 14.53, + "learning_rate": 3.6710475804127743e-06, + "loss": 0.0036, + "step": 47054 + }, + { + "epoch": 14.53, + "learning_rate": 3.6706603780739527e-06, + "loss": 0.0034, + "step": 47055 + }, + { + "epoch": 14.53, + "learning_rate": 3.670273191565961e-06, + "loss": 0.0042, + "step": 47056 + }, + { + "epoch": 14.53, + "learning_rate": 3.6698860208897724e-06, + "loss": 0.0035, + "step": 47057 + }, + { + "epoch": 14.53, + "learning_rate": 3.6694988660463536e-06, + "loss": 0.0026, + "step": 47058 + }, + { + "epoch": 14.53, + "learning_rate": 3.6691117270366694e-06, + "loss": 0.0034, + "step": 47059 + }, + { + "epoch": 14.53, + "learning_rate": 3.668724603861692e-06, + "loss": 0.0036, + "step": 47060 + }, + { + "epoch": 14.53, + "learning_rate": 3.668337496522393e-06, + "loss": 0.0029, + "step": 47061 + }, + { + "epoch": 14.53, + "learning_rate": 3.6679504050197323e-06, + "loss": 0.0034, + "step": 47062 + }, + { + "epoch": 14.53, + "learning_rate": 3.6675633293546863e-06, + "loss": 0.004, + "step": 47063 + }, + { + "epoch": 14.53, + "learning_rate": 3.66717626952822e-06, + "loss": 0.0031, + "step": 47064 + }, + { + "epoch": 14.53, + "learning_rate": 3.6667892255412964e-06, + "loss": 0.0053, + "step": 47065 + }, + { + "epoch": 14.53, + "learning_rate": 3.6664021973948884e-06, + "loss": 0.0024, + "step": 47066 + }, + { + "epoch": 14.54, + "learning_rate": 3.6660151850899672e-06, + "loss": 0.004, + "step": 47067 + }, + { + "epoch": 14.54, + "learning_rate": 3.665628188627497e-06, + "loss": 0.0038, + "step": 47068 + }, + { + "epoch": 14.54, + "learning_rate": 3.6652412080084433e-06, + "loss": 0.0024, + "step": 47069 + }, + { + "epoch": 14.54, + "learning_rate": 3.66485424323378e-06, + "loss": 0.0035, + "step": 47070 + }, + { + "epoch": 14.54, + "learning_rate": 3.664467294304468e-06, + "loss": 0.0046, + "step": 47071 + }, + { + "epoch": 14.54, + "learning_rate": 3.664080361221478e-06, + "loss": 0.0028, + "step": 47072 + }, + { + "epoch": 14.54, + "learning_rate": 3.663693443985783e-06, + "loss": 0.0035, + "step": 47073 + }, + { + "epoch": 14.54, + "learning_rate": 3.663306542598346e-06, + "loss": 0.0034, + "step": 47074 + }, + { + "epoch": 14.54, + "learning_rate": 3.6629196570601323e-06, + "loss": 0.0024, + "step": 47075 + }, + { + "epoch": 14.54, + "learning_rate": 3.6625327873721152e-06, + "loss": 0.0033, + "step": 47076 + }, + { + "epoch": 14.54, + "learning_rate": 3.662145933535256e-06, + "loss": 0.0046, + "step": 47077 + }, + { + "epoch": 14.54, + "learning_rate": 3.66175909555053e-06, + "loss": 0.0044, + "step": 47078 + }, + { + "epoch": 14.54, + "learning_rate": 3.6613722734188962e-06, + "loss": 0.0033, + "step": 47079 + }, + { + "epoch": 14.54, + "learning_rate": 3.6609854671413305e-06, + "loss": 0.0033, + "step": 47080 + }, + { + "epoch": 14.54, + "learning_rate": 3.6605986767187917e-06, + "loss": 0.0031, + "step": 47081 + }, + { + "epoch": 14.54, + "learning_rate": 3.6602119021522532e-06, + "loss": 0.0034, + "step": 47082 + }, + { + "epoch": 14.54, + "learning_rate": 3.6598251434426848e-06, + "loss": 0.0036, + "step": 47083 + }, + { + "epoch": 14.54, + "learning_rate": 3.659438400591049e-06, + "loss": 0.0047, + "step": 47084 + }, + { + "epoch": 14.54, + "learning_rate": 3.659051673598311e-06, + "loss": 0.0034, + "step": 47085 + }, + { + "epoch": 14.54, + "learning_rate": 3.6586649624654446e-06, + "loss": 0.0031, + "step": 47086 + }, + { + "epoch": 14.54, + "learning_rate": 3.6582782671934105e-06, + "loss": 0.0035, + "step": 47087 + }, + { + "epoch": 14.54, + "learning_rate": 3.657891587783182e-06, + "loss": 0.0034, + "step": 47088 + }, + { + "epoch": 14.54, + "learning_rate": 3.657504924235724e-06, + "loss": 0.0038, + "step": 47089 + }, + { + "epoch": 14.54, + "learning_rate": 3.657118276552e-06, + "loss": 0.0041, + "step": 47090 + }, + { + "epoch": 14.54, + "learning_rate": 3.656731644732979e-06, + "loss": 0.0028, + "step": 47091 + }, + { + "epoch": 14.54, + "learning_rate": 3.656345028779633e-06, + "loss": 0.0049, + "step": 47092 + }, + { + "epoch": 14.54, + "learning_rate": 3.655958428692922e-06, + "loss": 0.0037, + "step": 47093 + }, + { + "epoch": 14.54, + "learning_rate": 3.6555718444738185e-06, + "loss": 0.0039, + "step": 47094 + }, + { + "epoch": 14.54, + "learning_rate": 3.6551852761232875e-06, + "loss": 0.0048, + "step": 47095 + }, + { + "epoch": 14.54, + "learning_rate": 3.6547987236422922e-06, + "loss": 0.0033, + "step": 47096 + }, + { + "epoch": 14.54, + "learning_rate": 3.6544121870318027e-06, + "loss": 0.0031, + "step": 47097 + }, + { + "epoch": 14.54, + "learning_rate": 3.6540256662927886e-06, + "loss": 0.003, + "step": 47098 + }, + { + "epoch": 14.55, + "learning_rate": 3.6536391614262136e-06, + "loss": 0.0053, + "step": 47099 + }, + { + "epoch": 14.55, + "learning_rate": 3.653252672433042e-06, + "loss": 0.0033, + "step": 47100 + }, + { + "epoch": 14.55, + "learning_rate": 3.6528661993142455e-06, + "loss": 0.0033, + "step": 47101 + }, + { + "epoch": 14.55, + "learning_rate": 3.652479742070786e-06, + "loss": 0.0056, + "step": 47102 + }, + { + "epoch": 14.55, + "learning_rate": 3.6520933007036307e-06, + "loss": 0.0035, + "step": 47103 + }, + { + "epoch": 14.55, + "learning_rate": 3.651706875213756e-06, + "loss": 0.0033, + "step": 47104 + }, + { + "epoch": 14.55, + "learning_rate": 3.6513204656021126e-06, + "loss": 0.0036, + "step": 47105 + }, + { + "epoch": 14.55, + "learning_rate": 3.6509340718696763e-06, + "loss": 0.0033, + "step": 47106 + }, + { + "epoch": 14.55, + "learning_rate": 3.6505476940174133e-06, + "loss": 0.005, + "step": 47107 + }, + { + "epoch": 14.55, + "learning_rate": 3.650161332046286e-06, + "loss": 0.0037, + "step": 47108 + }, + { + "epoch": 14.55, + "learning_rate": 3.6497749859572675e-06, + "loss": 0.004, + "step": 47109 + }, + { + "epoch": 14.55, + "learning_rate": 3.6493886557513146e-06, + "loss": 0.0034, + "step": 47110 + }, + { + "epoch": 14.55, + "learning_rate": 3.649002341429404e-06, + "loss": 0.0035, + "step": 47111 + }, + { + "epoch": 14.55, + "learning_rate": 3.648616042992493e-06, + "loss": 0.0041, + "step": 47112 + }, + { + "epoch": 14.55, + "learning_rate": 3.648229760441552e-06, + "loss": 0.0032, + "step": 47113 + }, + { + "epoch": 14.55, + "learning_rate": 3.6478434937775497e-06, + "loss": 0.0041, + "step": 47114 + }, + { + "epoch": 14.55, + "learning_rate": 3.64745724300145e-06, + "loss": 0.0037, + "step": 47115 + }, + { + "epoch": 14.55, + "learning_rate": 3.647071008114215e-06, + "loss": 0.0031, + "step": 47116 + }, + { + "epoch": 14.55, + "learning_rate": 3.646684789116817e-06, + "loss": 0.0046, + "step": 47117 + }, + { + "epoch": 14.55, + "learning_rate": 3.6462985860102164e-06, + "loss": 0.0025, + "step": 47118 + }, + { + "epoch": 14.55, + "learning_rate": 3.6459123987953847e-06, + "loss": 0.0032, + "step": 47119 + }, + { + "epoch": 14.55, + "learning_rate": 3.645526227473285e-06, + "loss": 0.0034, + "step": 47120 + }, + { + "epoch": 14.55, + "learning_rate": 3.6451400720448793e-06, + "loss": 0.0038, + "step": 47121 + }, + { + "epoch": 14.55, + "learning_rate": 3.6447539325111382e-06, + "loss": 0.0035, + "step": 47122 + }, + { + "epoch": 14.55, + "learning_rate": 3.6443678088730296e-06, + "loss": 0.0044, + "step": 47123 + }, + { + "epoch": 14.55, + "learning_rate": 3.6439817011315126e-06, + "loss": 0.0034, + "step": 47124 + }, + { + "epoch": 14.55, + "learning_rate": 3.643595609287561e-06, + "loss": 0.0038, + "step": 47125 + }, + { + "epoch": 14.55, + "learning_rate": 3.643209533342136e-06, + "loss": 0.0031, + "step": 47126 + }, + { + "epoch": 14.55, + "learning_rate": 3.6428234732961985e-06, + "loss": 0.0027, + "step": 47127 + }, + { + "epoch": 14.55, + "learning_rate": 3.6424374291507204e-06, + "loss": 0.0037, + "step": 47128 + }, + { + "epoch": 14.55, + "learning_rate": 3.642051400906669e-06, + "loss": 0.0037, + "step": 47129 + }, + { + "epoch": 14.55, + "learning_rate": 3.6416653885650066e-06, + "loss": 0.0038, + "step": 47130 + }, + { + "epoch": 14.55, + "learning_rate": 3.6412793921266953e-06, + "loss": 0.0039, + "step": 47131 + }, + { + "epoch": 14.56, + "learning_rate": 3.6408934115927076e-06, + "loss": 0.003, + "step": 47132 + }, + { + "epoch": 14.56, + "learning_rate": 3.6405074469640012e-06, + "loss": 0.0034, + "step": 47133 + }, + { + "epoch": 14.56, + "learning_rate": 3.6401214982415466e-06, + "loss": 0.0032, + "step": 47134 + }, + { + "epoch": 14.56, + "learning_rate": 3.6397355654263144e-06, + "loss": 0.0045, + "step": 47135 + }, + { + "epoch": 14.56, + "learning_rate": 3.639349648519257e-06, + "loss": 0.0024, + "step": 47136 + }, + { + "epoch": 14.56, + "learning_rate": 3.638963747521346e-06, + "loss": 0.0034, + "step": 47137 + }, + { + "epoch": 14.56, + "learning_rate": 3.6385778624335497e-06, + "loss": 0.005, + "step": 47138 + }, + { + "epoch": 14.56, + "learning_rate": 3.638191993256828e-06, + "loss": 0.0033, + "step": 47139 + }, + { + "epoch": 14.56, + "learning_rate": 3.6378061399921518e-06, + "loss": 0.0033, + "step": 47140 + }, + { + "epoch": 14.56, + "learning_rate": 3.637420302640482e-06, + "loss": 0.0035, + "step": 47141 + }, + { + "epoch": 14.56, + "learning_rate": 3.6370344812027815e-06, + "loss": 0.0032, + "step": 47142 + }, + { + "epoch": 14.56, + "learning_rate": 3.636648675680018e-06, + "loss": 0.003, + "step": 47143 + }, + { + "epoch": 14.56, + "learning_rate": 3.6362628860731575e-06, + "loss": 0.0043, + "step": 47144 + }, + { + "epoch": 14.56, + "learning_rate": 3.6358771123831704e-06, + "loss": 0.0037, + "step": 47145 + }, + { + "epoch": 14.56, + "learning_rate": 3.6354913546110084e-06, + "loss": 0.0038, + "step": 47146 + }, + { + "epoch": 14.56, + "learning_rate": 3.6351056127576445e-06, + "loss": 0.004, + "step": 47147 + }, + { + "epoch": 14.56, + "learning_rate": 3.634719886824044e-06, + "loss": 0.0037, + "step": 47148 + }, + { + "epoch": 14.56, + "learning_rate": 3.6343341768111683e-06, + "loss": 0.0038, + "step": 47149 + }, + { + "epoch": 14.56, + "learning_rate": 3.633948482719987e-06, + "loss": 0.0043, + "step": 47150 + }, + { + "epoch": 14.56, + "learning_rate": 3.6335628045514604e-06, + "loss": 0.0041, + "step": 47151 + }, + { + "epoch": 14.56, + "learning_rate": 3.633177142306552e-06, + "loss": 0.0032, + "step": 47152 + }, + { + "epoch": 14.56, + "learning_rate": 3.6327914959862288e-06, + "loss": 0.003, + "step": 47153 + }, + { + "epoch": 14.56, + "learning_rate": 3.6324058655914583e-06, + "loss": 0.0034, + "step": 47154 + }, + { + "epoch": 14.56, + "learning_rate": 3.6320202511232018e-06, + "loss": 0.0035, + "step": 47155 + }, + { + "epoch": 14.56, + "learning_rate": 3.631634652582422e-06, + "loss": 0.0037, + "step": 47156 + }, + { + "epoch": 14.56, + "learning_rate": 3.6312490699700874e-06, + "loss": 0.0027, + "step": 47157 + }, + { + "epoch": 14.56, + "learning_rate": 3.6308635032871574e-06, + "loss": 0.0045, + "step": 47158 + }, + { + "epoch": 14.56, + "learning_rate": 3.6304779525346e-06, + "loss": 0.0042, + "step": 47159 + }, + { + "epoch": 14.56, + "learning_rate": 3.6300924177133823e-06, + "loss": 0.005, + "step": 47160 + }, + { + "epoch": 14.56, + "learning_rate": 3.6297068988244654e-06, + "loss": 0.0034, + "step": 47161 + }, + { + "epoch": 14.56, + "learning_rate": 3.62932139586881e-06, + "loss": 0.0035, + "step": 47162 + }, + { + "epoch": 14.56, + "learning_rate": 3.6289359088473865e-06, + "loss": 0.0031, + "step": 47163 + }, + { + "epoch": 14.57, + "learning_rate": 3.6285504377611535e-06, + "loss": 0.0029, + "step": 47164 + }, + { + "epoch": 14.57, + "learning_rate": 3.628164982611081e-06, + "loss": 0.0033, + "step": 47165 + }, + { + "epoch": 14.57, + "learning_rate": 3.62777954339813e-06, + "loss": 0.0037, + "step": 47166 + }, + { + "epoch": 14.57, + "learning_rate": 3.627394120123261e-06, + "loss": 0.003, + "step": 47167 + }, + { + "epoch": 14.57, + "learning_rate": 3.627008712787442e-06, + "loss": 0.0028, + "step": 47168 + }, + { + "epoch": 14.57, + "learning_rate": 3.62662332139164e-06, + "loss": 0.0027, + "step": 47169 + }, + { + "epoch": 14.57, + "learning_rate": 3.6262379459368125e-06, + "loss": 0.0028, + "step": 47170 + }, + { + "epoch": 14.57, + "learning_rate": 3.625852586423929e-06, + "loss": 0.0035, + "step": 47171 + }, + { + "epoch": 14.57, + "learning_rate": 3.6254672428539505e-06, + "loss": 0.0034, + "step": 47172 + }, + { + "epoch": 14.57, + "learning_rate": 3.6250819152278383e-06, + "loss": 0.0031, + "step": 47173 + }, + { + "epoch": 14.57, + "learning_rate": 3.6246966035465593e-06, + "loss": 0.0029, + "step": 47174 + }, + { + "epoch": 14.57, + "learning_rate": 3.624311307811079e-06, + "loss": 0.0032, + "step": 47175 + }, + { + "epoch": 14.57, + "learning_rate": 3.623926028022361e-06, + "loss": 0.0042, + "step": 47176 + }, + { + "epoch": 14.57, + "learning_rate": 3.6235407641813614e-06, + "loss": 0.0035, + "step": 47177 + }, + { + "epoch": 14.57, + "learning_rate": 3.6231555162890507e-06, + "loss": 0.0038, + "step": 47178 + }, + { + "epoch": 14.57, + "learning_rate": 3.622770284346394e-06, + "loss": 0.0036, + "step": 47179 + }, + { + "epoch": 14.57, + "learning_rate": 3.622385068354348e-06, + "loss": 0.0041, + "step": 47180 + }, + { + "epoch": 14.57, + "learning_rate": 3.6219998683138847e-06, + "loss": 0.0032, + "step": 47181 + }, + { + "epoch": 14.57, + "learning_rate": 3.6216146842259626e-06, + "loss": 0.0042, + "step": 47182 + }, + { + "epoch": 14.57, + "learning_rate": 3.6212295160915423e-06, + "loss": 0.0046, + "step": 47183 + }, + { + "epoch": 14.57, + "learning_rate": 3.62084436391159e-06, + "loss": 0.0039, + "step": 47184 + }, + { + "epoch": 14.57, + "learning_rate": 3.6204592276870732e-06, + "loss": 0.0043, + "step": 47185 + }, + { + "epoch": 14.57, + "learning_rate": 3.6200741074189506e-06, + "loss": 0.0054, + "step": 47186 + }, + { + "epoch": 14.57, + "learning_rate": 3.6196890031081833e-06, + "loss": 0.0032, + "step": 47187 + }, + { + "epoch": 14.57, + "learning_rate": 3.6193039147557417e-06, + "loss": 0.0037, + "step": 47188 + }, + { + "epoch": 14.57, + "learning_rate": 3.61891884236258e-06, + "loss": 0.0039, + "step": 47189 + }, + { + "epoch": 14.57, + "learning_rate": 3.6185337859296676e-06, + "loss": 0.0042, + "step": 47190 + }, + { + "epoch": 14.57, + "learning_rate": 3.6181487454579677e-06, + "loss": 0.0035, + "step": 47191 + }, + { + "epoch": 14.57, + "learning_rate": 3.6177637209484427e-06, + "loss": 0.0032, + "step": 47192 + }, + { + "epoch": 14.57, + "learning_rate": 3.617378712402052e-06, + "loss": 0.0031, + "step": 47193 + }, + { + "epoch": 14.57, + "learning_rate": 3.6169937198197636e-06, + "loss": 0.003, + "step": 47194 + }, + { + "epoch": 14.57, + "learning_rate": 3.6166087432025356e-06, + "loss": 0.0046, + "step": 47195 + }, + { + "epoch": 14.57, + "learning_rate": 3.616223782551337e-06, + "loss": 0.0029, + "step": 47196 + }, + { + "epoch": 14.58, + "learning_rate": 3.615838837867126e-06, + "loss": 0.0034, + "step": 47197 + }, + { + "epoch": 14.58, + "learning_rate": 3.6154539091508633e-06, + "loss": 0.0042, + "step": 47198 + }, + { + "epoch": 14.58, + "learning_rate": 3.6150689964035147e-06, + "loss": 0.0035, + "step": 47199 + }, + { + "epoch": 14.58, + "learning_rate": 3.6146840996260466e-06, + "loss": 0.0063, + "step": 47200 + }, + { + "epoch": 14.58, + "learning_rate": 3.6142992188194148e-06, + "loss": 0.0026, + "step": 47201 + }, + { + "epoch": 14.58, + "learning_rate": 3.613914353984589e-06, + "loss": 0.0035, + "step": 47202 + }, + { + "epoch": 14.58, + "learning_rate": 3.6135295051225284e-06, + "loss": 0.0025, + "step": 47203 + }, + { + "epoch": 14.58, + "learning_rate": 3.613144672234191e-06, + "loss": 0.0033, + "step": 47204 + }, + { + "epoch": 14.58, + "learning_rate": 3.6127598553205445e-06, + "loss": 0.0034, + "step": 47205 + }, + { + "epoch": 14.58, + "learning_rate": 3.6123750543825542e-06, + "loss": 0.0035, + "step": 47206 + }, + { + "epoch": 14.58, + "learning_rate": 3.6119902694211783e-06, + "loss": 0.004, + "step": 47207 + }, + { + "epoch": 14.58, + "learning_rate": 3.6116055004373764e-06, + "loss": 0.0034, + "step": 47208 + }, + { + "epoch": 14.58, + "learning_rate": 3.611220747432115e-06, + "loss": 0.0035, + "step": 47209 + }, + { + "epoch": 14.58, + "learning_rate": 3.610836010406358e-06, + "loss": 0.0038, + "step": 47210 + }, + { + "epoch": 14.58, + "learning_rate": 3.610451289361062e-06, + "loss": 0.0035, + "step": 47211 + }, + { + "epoch": 14.58, + "learning_rate": 3.610066584297197e-06, + "loss": 0.0037, + "step": 47212 + }, + { + "epoch": 14.58, + "learning_rate": 3.609681895215721e-06, + "loss": 0.0032, + "step": 47213 + }, + { + "epoch": 14.58, + "learning_rate": 3.6092972221175925e-06, + "loss": 0.0032, + "step": 47214 + }, + { + "epoch": 14.58, + "learning_rate": 3.608912565003777e-06, + "loss": 0.0034, + "step": 47215 + }, + { + "epoch": 14.58, + "learning_rate": 3.60852792387524e-06, + "loss": 0.0044, + "step": 47216 + }, + { + "epoch": 14.58, + "learning_rate": 3.6081432987329414e-06, + "loss": 0.0031, + "step": 47217 + }, + { + "epoch": 14.58, + "learning_rate": 3.6077586895778382e-06, + "loss": 0.0041, + "step": 47218 + }, + { + "epoch": 14.58, + "learning_rate": 3.6073740964108995e-06, + "loss": 0.003, + "step": 47219 + }, + { + "epoch": 14.58, + "learning_rate": 3.6069895192330807e-06, + "loss": 0.0041, + "step": 47220 + }, + { + "epoch": 14.58, + "learning_rate": 3.606604958045348e-06, + "loss": 0.0033, + "step": 47221 + }, + { + "epoch": 14.58, + "learning_rate": 3.6062204128486646e-06, + "loss": 0.0033, + "step": 47222 + }, + { + "epoch": 14.58, + "learning_rate": 3.605835883643991e-06, + "loss": 0.0027, + "step": 47223 + }, + { + "epoch": 14.58, + "learning_rate": 3.6054513704322846e-06, + "loss": 0.0029, + "step": 47224 + }, + { + "epoch": 14.58, + "learning_rate": 3.6050668732145132e-06, + "loss": 0.0029, + "step": 47225 + }, + { + "epoch": 14.58, + "learning_rate": 3.604682391991633e-06, + "loss": 0.0033, + "step": 47226 + }, + { + "epoch": 14.58, + "learning_rate": 3.6042979267646127e-06, + "loss": 0.0036, + "step": 47227 + }, + { + "epoch": 14.58, + "learning_rate": 3.6039134775344088e-06, + "loss": 0.0036, + "step": 47228 + }, + { + "epoch": 14.59, + "learning_rate": 3.603529044301981e-06, + "loss": 0.0032, + "step": 47229 + }, + { + "epoch": 14.59, + "learning_rate": 3.6031446270682934e-06, + "loss": 0.0044, + "step": 47230 + }, + { + "epoch": 14.59, + "learning_rate": 3.602760225834311e-06, + "loss": 0.0037, + "step": 47231 + }, + { + "epoch": 14.59, + "learning_rate": 3.602375840600989e-06, + "loss": 0.0035, + "step": 47232 + }, + { + "epoch": 14.59, + "learning_rate": 3.601991471369295e-06, + "loss": 0.0033, + "step": 47233 + }, + { + "epoch": 14.59, + "learning_rate": 3.601607118140188e-06, + "loss": 0.0031, + "step": 47234 + }, + { + "epoch": 14.59, + "learning_rate": 3.601222780914625e-06, + "loss": 0.004, + "step": 47235 + }, + { + "epoch": 14.59, + "learning_rate": 3.60083845969357e-06, + "loss": 0.0039, + "step": 47236 + }, + { + "epoch": 14.59, + "learning_rate": 3.600454154477989e-06, + "loss": 0.003, + "step": 47237 + }, + { + "epoch": 14.59, + "learning_rate": 3.6000698652688393e-06, + "loss": 0.003, + "step": 47238 + }, + { + "epoch": 14.59, + "learning_rate": 3.5996855920670794e-06, + "loss": 0.003, + "step": 47239 + }, + { + "epoch": 14.59, + "learning_rate": 3.5993013348736725e-06, + "loss": 0.003, + "step": 47240 + }, + { + "epoch": 14.59, + "learning_rate": 3.5989170936895844e-06, + "loss": 0.0039, + "step": 47241 + }, + { + "epoch": 14.59, + "learning_rate": 3.5985328685157683e-06, + "loss": 0.0025, + "step": 47242 + }, + { + "epoch": 14.59, + "learning_rate": 3.5981486593531923e-06, + "loss": 0.0039, + "step": 47243 + }, + { + "epoch": 14.59, + "learning_rate": 3.5977644662028146e-06, + "loss": 0.0036, + "step": 47244 + }, + { + "epoch": 14.59, + "learning_rate": 3.5973802890655917e-06, + "loss": 0.0043, + "step": 47245 + }, + { + "epoch": 14.59, + "learning_rate": 3.5969961279424894e-06, + "loss": 0.0039, + "step": 47246 + }, + { + "epoch": 14.59, + "learning_rate": 3.5966119828344694e-06, + "loss": 0.0035, + "step": 47247 + }, + { + "epoch": 14.59, + "learning_rate": 3.5962278537424922e-06, + "loss": 0.0042, + "step": 47248 + }, + { + "epoch": 14.59, + "learning_rate": 3.595843740667513e-06, + "loss": 0.0038, + "step": 47249 + }, + { + "epoch": 14.59, + "learning_rate": 3.5954596436105006e-06, + "loss": 0.0035, + "step": 47250 + }, + { + "epoch": 14.59, + "learning_rate": 3.5950755625724077e-06, + "loss": 0.0024, + "step": 47251 + }, + { + "epoch": 14.59, + "learning_rate": 3.5946914975541993e-06, + "loss": 0.0043, + "step": 47252 + }, + { + "epoch": 14.59, + "learning_rate": 3.594307448556843e-06, + "loss": 0.0033, + "step": 47253 + }, + { + "epoch": 14.59, + "learning_rate": 3.593923415581284e-06, + "loss": 0.004, + "step": 47254 + }, + { + "epoch": 14.59, + "learning_rate": 3.5935393986284916e-06, + "loss": 0.004, + "step": 47255 + }, + { + "epoch": 14.59, + "learning_rate": 3.5931553976994295e-06, + "loss": 0.0043, + "step": 47256 + }, + { + "epoch": 14.59, + "learning_rate": 3.5927714127950507e-06, + "loss": 0.0049, + "step": 47257 + }, + { + "epoch": 14.59, + "learning_rate": 3.592387443916322e-06, + "loss": 0.0041, + "step": 47258 + }, + { + "epoch": 14.59, + "learning_rate": 3.5920034910642023e-06, + "loss": 0.0052, + "step": 47259 + }, + { + "epoch": 14.59, + "learning_rate": 3.591619554239646e-06, + "loss": 0.0029, + "step": 47260 + }, + { + "epoch": 14.6, + "learning_rate": 3.5912356334436183e-06, + "loss": 0.0034, + "step": 47261 + }, + { + "epoch": 14.6, + "learning_rate": 3.5908517286770826e-06, + "loss": 0.0031, + "step": 47262 + }, + { + "epoch": 14.6, + "learning_rate": 3.5904678399409953e-06, + "loss": 0.0037, + "step": 47263 + }, + { + "epoch": 14.6, + "learning_rate": 3.5900839672363143e-06, + "loss": 0.004, + "step": 47264 + }, + { + "epoch": 14.6, + "learning_rate": 3.589700110564006e-06, + "loss": 0.0043, + "step": 47265 + }, + { + "epoch": 14.6, + "learning_rate": 3.589316269925023e-06, + "loss": 0.0037, + "step": 47266 + }, + { + "epoch": 14.6, + "learning_rate": 3.5889324453203287e-06, + "loss": 0.0028, + "step": 47267 + }, + { + "epoch": 14.6, + "learning_rate": 3.588548636750888e-06, + "loss": 0.0044, + "step": 47268 + }, + { + "epoch": 14.6, + "learning_rate": 3.5881648442176555e-06, + "loss": 0.004, + "step": 47269 + }, + { + "epoch": 14.6, + "learning_rate": 3.5877810677215897e-06, + "loss": 0.0039, + "step": 47270 + }, + { + "epoch": 14.6, + "learning_rate": 3.5873973072636558e-06, + "loss": 0.0043, + "step": 47271 + }, + { + "epoch": 14.6, + "learning_rate": 3.5870135628448078e-06, + "loss": 0.006, + "step": 47272 + }, + { + "epoch": 14.6, + "learning_rate": 3.5866298344660122e-06, + "loss": 0.0031, + "step": 47273 + }, + { + "epoch": 14.6, + "learning_rate": 3.5862461221282208e-06, + "loss": 0.0051, + "step": 47274 + }, + { + "epoch": 14.6, + "learning_rate": 3.5858624258324015e-06, + "loss": 0.0039, + "step": 47275 + }, + { + "epoch": 14.6, + "learning_rate": 3.585478745579507e-06, + "loss": 0.0046, + "step": 47276 + }, + { + "epoch": 14.6, + "learning_rate": 3.5850950813705e-06, + "loss": 0.0038, + "step": 47277 + }, + { + "epoch": 14.6, + "learning_rate": 3.5847114332063436e-06, + "loss": 0.0031, + "step": 47278 + }, + { + "epoch": 14.6, + "learning_rate": 3.5843278010879933e-06, + "loss": 0.0038, + "step": 47279 + }, + { + "epoch": 14.6, + "learning_rate": 3.583944185016407e-06, + "loss": 0.0035, + "step": 47280 + }, + { + "epoch": 14.6, + "learning_rate": 3.583560584992549e-06, + "loss": 0.0039, + "step": 47281 + }, + { + "epoch": 14.6, + "learning_rate": 3.5831770010173737e-06, + "loss": 0.0042, + "step": 47282 + }, + { + "epoch": 14.6, + "learning_rate": 3.5827934330918455e-06, + "loss": 0.0035, + "step": 47283 + }, + { + "epoch": 14.6, + "learning_rate": 3.5824098812169217e-06, + "loss": 0.003, + "step": 47284 + }, + { + "epoch": 14.6, + "learning_rate": 3.582026345393559e-06, + "loss": 0.0042, + "step": 47285 + }, + { + "epoch": 14.6, + "learning_rate": 3.5816428256227174e-06, + "loss": 0.0033, + "step": 47286 + }, + { + "epoch": 14.6, + "learning_rate": 3.5812593219053614e-06, + "loss": 0.004, + "step": 47287 + }, + { + "epoch": 14.6, + "learning_rate": 3.5808758342424442e-06, + "loss": 0.0038, + "step": 47288 + }, + { + "epoch": 14.6, + "learning_rate": 3.58049236263493e-06, + "loss": 0.0026, + "step": 47289 + }, + { + "epoch": 14.6, + "learning_rate": 3.5801089070837746e-06, + "loss": 0.004, + "step": 47290 + }, + { + "epoch": 14.6, + "learning_rate": 3.579725467589935e-06, + "loss": 0.0038, + "step": 47291 + }, + { + "epoch": 14.6, + "learning_rate": 3.5793420441543737e-06, + "loss": 0.0031, + "step": 47292 + }, + { + "epoch": 14.6, + "learning_rate": 3.5789586367780517e-06, + "loss": 0.0042, + "step": 47293 + }, + { + "epoch": 14.61, + "learning_rate": 3.578575245461925e-06, + "loss": 0.0028, + "step": 47294 + }, + { + "epoch": 14.61, + "learning_rate": 3.5781918702069495e-06, + "loss": 0.0032, + "step": 47295 + }, + { + "epoch": 14.61, + "learning_rate": 3.5778085110140916e-06, + "loss": 0.0048, + "step": 47296 + }, + { + "epoch": 14.61, + "learning_rate": 3.577425167884302e-06, + "loss": 0.0033, + "step": 47297 + }, + { + "epoch": 14.61, + "learning_rate": 3.5770418408185425e-06, + "loss": 0.0027, + "step": 47298 + }, + { + "epoch": 14.61, + "learning_rate": 3.576658529817778e-06, + "loss": 0.0035, + "step": 47299 + }, + { + "epoch": 14.61, + "learning_rate": 3.576275234882961e-06, + "loss": 0.0034, + "step": 47300 + }, + { + "epoch": 14.61, + "learning_rate": 3.5758919560150475e-06, + "loss": 0.0045, + "step": 47301 + }, + { + "epoch": 14.61, + "learning_rate": 3.575508693215004e-06, + "loss": 0.0039, + "step": 47302 + }, + { + "epoch": 14.61, + "learning_rate": 3.5751254464837817e-06, + "loss": 0.0032, + "step": 47303 + }, + { + "epoch": 14.61, + "learning_rate": 3.5747422158223455e-06, + "loss": 0.0048, + "step": 47304 + }, + { + "epoch": 14.61, + "learning_rate": 3.574359001231651e-06, + "loss": 0.004, + "step": 47305 + }, + { + "epoch": 14.61, + "learning_rate": 3.573975802712654e-06, + "loss": 0.003, + "step": 47306 + }, + { + "epoch": 14.61, + "learning_rate": 3.5735926202663142e-06, + "loss": 0.003, + "step": 47307 + }, + { + "epoch": 14.61, + "learning_rate": 3.573209453893591e-06, + "loss": 0.0032, + "step": 47308 + }, + { + "epoch": 14.61, + "learning_rate": 3.572826303595448e-06, + "loss": 0.0045, + "step": 47309 + }, + { + "epoch": 14.61, + "learning_rate": 3.572443169372839e-06, + "loss": 0.0044, + "step": 47310 + }, + { + "epoch": 14.61, + "learning_rate": 3.5720600512267165e-06, + "loss": 0.0037, + "step": 47311 + }, + { + "epoch": 14.61, + "learning_rate": 3.5716769491580493e-06, + "loss": 0.0029, + "step": 47312 + }, + { + "epoch": 14.61, + "learning_rate": 3.571293863167786e-06, + "loss": 0.0044, + "step": 47313 + }, + { + "epoch": 14.61, + "learning_rate": 3.570910793256894e-06, + "loss": 0.0027, + "step": 47314 + }, + { + "epoch": 14.61, + "learning_rate": 3.570527739426326e-06, + "loss": 0.0032, + "step": 47315 + }, + { + "epoch": 14.61, + "learning_rate": 3.5701447016770374e-06, + "loss": 0.0032, + "step": 47316 + }, + { + "epoch": 14.61, + "learning_rate": 3.56976168000999e-06, + "loss": 0.0038, + "step": 47317 + }, + { + "epoch": 14.61, + "learning_rate": 3.569378674426144e-06, + "loss": 0.0028, + "step": 47318 + }, + { + "epoch": 14.61, + "learning_rate": 3.5689956849264517e-06, + "loss": 0.0039, + "step": 47319 + }, + { + "epoch": 14.61, + "learning_rate": 3.5686127115118773e-06, + "loss": 0.0036, + "step": 47320 + }, + { + "epoch": 14.61, + "learning_rate": 3.5682297541833764e-06, + "loss": 0.0044, + "step": 47321 + }, + { + "epoch": 14.61, + "learning_rate": 3.567846812941902e-06, + "loss": 0.0037, + "step": 47322 + }, + { + "epoch": 14.61, + "learning_rate": 3.567463887788416e-06, + "loss": 0.0034, + "step": 47323 + }, + { + "epoch": 14.61, + "learning_rate": 3.567080978723879e-06, + "loss": 0.0036, + "step": 47324 + }, + { + "epoch": 14.61, + "learning_rate": 3.566698085749246e-06, + "loss": 0.0041, + "step": 47325 + }, + { + "epoch": 14.62, + "learning_rate": 3.5663152088654718e-06, + "loss": 0.003, + "step": 47326 + }, + { + "epoch": 14.62, + "learning_rate": 3.5659323480735187e-06, + "loss": 0.0045, + "step": 47327 + }, + { + "epoch": 14.62, + "learning_rate": 3.5655495033743404e-06, + "loss": 0.003, + "step": 47328 + }, + { + "epoch": 14.62, + "learning_rate": 3.5651666747688952e-06, + "loss": 0.0033, + "step": 47329 + }, + { + "epoch": 14.62, + "learning_rate": 3.5647838622581454e-06, + "loss": 0.0044, + "step": 47330 + }, + { + "epoch": 14.62, + "learning_rate": 3.564401065843045e-06, + "loss": 0.0029, + "step": 47331 + }, + { + "epoch": 14.62, + "learning_rate": 3.5640182855245487e-06, + "loss": 0.0038, + "step": 47332 + }, + { + "epoch": 14.62, + "learning_rate": 3.563635521303619e-06, + "loss": 0.0034, + "step": 47333 + }, + { + "epoch": 14.62, + "learning_rate": 3.5632527731812074e-06, + "loss": 0.0032, + "step": 47334 + }, + { + "epoch": 14.62, + "learning_rate": 3.5628700411582786e-06, + "loss": 0.0033, + "step": 47335 + }, + { + "epoch": 14.62, + "learning_rate": 3.562487325235785e-06, + "loss": 0.0033, + "step": 47336 + }, + { + "epoch": 14.62, + "learning_rate": 3.562104625414682e-06, + "loss": 0.0034, + "step": 47337 + }, + { + "epoch": 14.62, + "learning_rate": 3.561721941695929e-06, + "loss": 0.0032, + "step": 47338 + }, + { + "epoch": 14.62, + "learning_rate": 3.5613392740804843e-06, + "loss": 0.0026, + "step": 47339 + }, + { + "epoch": 14.62, + "learning_rate": 3.5609566225693072e-06, + "loss": 0.0032, + "step": 47340 + }, + { + "epoch": 14.62, + "learning_rate": 3.560573987163353e-06, + "loss": 0.0035, + "step": 47341 + }, + { + "epoch": 14.62, + "learning_rate": 3.5601913678635737e-06, + "loss": 0.0031, + "step": 47342 + }, + { + "epoch": 14.62, + "learning_rate": 3.5598087646709333e-06, + "loss": 0.0034, + "step": 47343 + }, + { + "epoch": 14.62, + "learning_rate": 3.5594261775863824e-06, + "loss": 0.004, + "step": 47344 + }, + { + "epoch": 14.62, + "learning_rate": 3.559043606610886e-06, + "loss": 0.003, + "step": 47345 + }, + { + "epoch": 14.62, + "learning_rate": 3.5586610517453947e-06, + "loss": 0.0041, + "step": 47346 + }, + { + "epoch": 14.62, + "learning_rate": 3.558278512990865e-06, + "loss": 0.0038, + "step": 47347 + }, + { + "epoch": 14.62, + "learning_rate": 3.5578959903482545e-06, + "loss": 0.0034, + "step": 47348 + }, + { + "epoch": 14.62, + "learning_rate": 3.5575134838185245e-06, + "loss": 0.0037, + "step": 47349 + }, + { + "epoch": 14.62, + "learning_rate": 3.5571309934026256e-06, + "loss": 0.004, + "step": 47350 + }, + { + "epoch": 14.62, + "learning_rate": 3.5567485191015204e-06, + "loss": 0.003, + "step": 47351 + }, + { + "epoch": 14.62, + "learning_rate": 3.556366060916162e-06, + "loss": 0.0029, + "step": 47352 + }, + { + "epoch": 14.62, + "learning_rate": 3.555983618847504e-06, + "loss": 0.0041, + "step": 47353 + }, + { + "epoch": 14.62, + "learning_rate": 3.555601192896506e-06, + "loss": 0.0033, + "step": 47354 + }, + { + "epoch": 14.62, + "learning_rate": 3.555218783064129e-06, + "loss": 0.0039, + "step": 47355 + }, + { + "epoch": 14.62, + "learning_rate": 3.5548363893513247e-06, + "loss": 0.0037, + "step": 47356 + }, + { + "epoch": 14.62, + "learning_rate": 3.5544540117590476e-06, + "loss": 0.0029, + "step": 47357 + }, + { + "epoch": 14.63, + "learning_rate": 3.5540716502882587e-06, + "loss": 0.0044, + "step": 47358 + }, + { + "epoch": 14.63, + "learning_rate": 3.5536893049399102e-06, + "loss": 0.0039, + "step": 47359 + }, + { + "epoch": 14.63, + "learning_rate": 3.5533069757149597e-06, + "loss": 0.0033, + "step": 47360 + }, + { + "epoch": 14.63, + "learning_rate": 3.552924662614371e-06, + "loss": 0.0037, + "step": 47361 + }, + { + "epoch": 14.63, + "learning_rate": 3.552542365639087e-06, + "loss": 0.0034, + "step": 47362 + }, + { + "epoch": 14.63, + "learning_rate": 3.5521600847900705e-06, + "loss": 0.0048, + "step": 47363 + }, + { + "epoch": 14.63, + "learning_rate": 3.5517778200682806e-06, + "loss": 0.0045, + "step": 47364 + }, + { + "epoch": 14.63, + "learning_rate": 3.5513955714746672e-06, + "loss": 0.0039, + "step": 47365 + }, + { + "epoch": 14.63, + "learning_rate": 3.5510133390101942e-06, + "loss": 0.0027, + "step": 47366 + }, + { + "epoch": 14.63, + "learning_rate": 3.5506311226758116e-06, + "loss": 0.0029, + "step": 47367 + }, + { + "epoch": 14.63, + "learning_rate": 3.5502489224724747e-06, + "loss": 0.0043, + "step": 47368 + }, + { + "epoch": 14.63, + "learning_rate": 3.54986673840114e-06, + "loss": 0.004, + "step": 47369 + }, + { + "epoch": 14.63, + "learning_rate": 3.54948457046277e-06, + "loss": 0.0033, + "step": 47370 + }, + { + "epoch": 14.63, + "learning_rate": 3.5491024186583146e-06, + "loss": 0.0036, + "step": 47371 + }, + { + "epoch": 14.63, + "learning_rate": 3.548720282988727e-06, + "loss": 0.0043, + "step": 47372 + }, + { + "epoch": 14.63, + "learning_rate": 3.5483381634549673e-06, + "loss": 0.0032, + "step": 47373 + }, + { + "epoch": 14.63, + "learning_rate": 3.5479560600579942e-06, + "loss": 0.0036, + "step": 47374 + }, + { + "epoch": 14.63, + "learning_rate": 3.5475739727987556e-06, + "loss": 0.0035, + "step": 47375 + }, + { + "epoch": 14.63, + "learning_rate": 3.5471919016782153e-06, + "loss": 0.0038, + "step": 47376 + }, + { + "epoch": 14.63, + "learning_rate": 3.5468098466973245e-06, + "loss": 0.0037, + "step": 47377 + }, + { + "epoch": 14.63, + "learning_rate": 3.5464278078570358e-06, + "loss": 0.0031, + "step": 47378 + }, + { + "epoch": 14.63, + "learning_rate": 3.5460457851583087e-06, + "loss": 0.0033, + "step": 47379 + }, + { + "epoch": 14.63, + "learning_rate": 3.545663778602102e-06, + "loss": 0.0032, + "step": 47380 + }, + { + "epoch": 14.63, + "learning_rate": 3.5452817881893633e-06, + "loss": 0.0044, + "step": 47381 + }, + { + "epoch": 14.63, + "learning_rate": 3.5448998139210554e-06, + "loss": 0.0051, + "step": 47382 + }, + { + "epoch": 14.63, + "learning_rate": 3.544517855798131e-06, + "loss": 0.0034, + "step": 47383 + }, + { + "epoch": 14.63, + "learning_rate": 3.5441359138215413e-06, + "loss": 0.0028, + "step": 47384 + }, + { + "epoch": 14.63, + "learning_rate": 3.5437539879922444e-06, + "loss": 0.003, + "step": 47385 + }, + { + "epoch": 14.63, + "learning_rate": 3.5433720783112003e-06, + "loss": 0.005, + "step": 47386 + }, + { + "epoch": 14.63, + "learning_rate": 3.5429901847793603e-06, + "loss": 0.0043, + "step": 47387 + }, + { + "epoch": 14.63, + "learning_rate": 3.542608307397676e-06, + "loss": 0.0036, + "step": 47388 + }, + { + "epoch": 14.63, + "learning_rate": 3.5422264461671096e-06, + "loss": 0.0034, + "step": 47389 + }, + { + "epoch": 14.63, + "learning_rate": 3.54184460108861e-06, + "loss": 0.0038, + "step": 47390 + }, + { + "epoch": 14.64, + "learning_rate": 3.5414627721631334e-06, + "loss": 0.0042, + "step": 47391 + }, + { + "epoch": 14.64, + "learning_rate": 3.541080959391644e-06, + "loss": 0.0052, + "step": 47392 + }, + { + "epoch": 14.64, + "learning_rate": 3.540699162775082e-06, + "loss": 0.0051, + "step": 47393 + }, + { + "epoch": 14.64, + "learning_rate": 3.54031738231441e-06, + "loss": 0.0049, + "step": 47394 + }, + { + "epoch": 14.64, + "learning_rate": 3.539935618010586e-06, + "loss": 0.0044, + "step": 47395 + }, + { + "epoch": 14.64, + "learning_rate": 3.539553869864557e-06, + "loss": 0.0029, + "step": 47396 + }, + { + "epoch": 14.64, + "learning_rate": 3.539172137877286e-06, + "loss": 0.0034, + "step": 47397 + }, + { + "epoch": 14.64, + "learning_rate": 3.538790422049724e-06, + "loss": 0.0034, + "step": 47398 + }, + { + "epoch": 14.64, + "learning_rate": 3.5384087223828224e-06, + "loss": 0.0036, + "step": 47399 + }, + { + "epoch": 14.64, + "learning_rate": 3.5380270388775383e-06, + "loss": 0.0035, + "step": 47400 + }, + { + "epoch": 14.64, + "learning_rate": 3.537645371534831e-06, + "loss": 0.0039, + "step": 47401 + }, + { + "epoch": 14.64, + "learning_rate": 3.5372637203556515e-06, + "loss": 0.0036, + "step": 47402 + }, + { + "epoch": 14.64, + "learning_rate": 3.5368820853409503e-06, + "loss": 0.0034, + "step": 47403 + }, + { + "epoch": 14.64, + "learning_rate": 3.536500466491686e-06, + "loss": 0.0035, + "step": 47404 + }, + { + "epoch": 14.64, + "learning_rate": 3.5361188638088163e-06, + "loss": 0.0037, + "step": 47405 + }, + { + "epoch": 14.64, + "learning_rate": 3.5357372772932884e-06, + "loss": 0.0037, + "step": 47406 + }, + { + "epoch": 14.64, + "learning_rate": 3.535355706946065e-06, + "loss": 0.0033, + "step": 47407 + }, + { + "epoch": 14.64, + "learning_rate": 3.5349741527680957e-06, + "loss": 0.0038, + "step": 47408 + }, + { + "epoch": 14.64, + "learning_rate": 3.5345926147603316e-06, + "loss": 0.0046, + "step": 47409 + }, + { + "epoch": 14.64, + "learning_rate": 3.5342110929237305e-06, + "loss": 0.0029, + "step": 47410 + }, + { + "epoch": 14.64, + "learning_rate": 3.53382958725925e-06, + "loss": 0.0031, + "step": 47411 + }, + { + "epoch": 14.64, + "learning_rate": 3.533448097767842e-06, + "loss": 0.0034, + "step": 47412 + }, + { + "epoch": 14.64, + "learning_rate": 3.5330666244504552e-06, + "loss": 0.0036, + "step": 47413 + }, + { + "epoch": 14.64, + "learning_rate": 3.532685167308052e-06, + "loss": 0.0041, + "step": 47414 + }, + { + "epoch": 14.64, + "learning_rate": 3.5323037263415794e-06, + "loss": 0.0044, + "step": 47415 + }, + { + "epoch": 14.64, + "learning_rate": 3.5319223015519956e-06, + "loss": 0.0046, + "step": 47416 + }, + { + "epoch": 14.64, + "learning_rate": 3.5315408929402562e-06, + "loss": 0.0037, + "step": 47417 + }, + { + "epoch": 14.64, + "learning_rate": 3.531159500507313e-06, + "loss": 0.0034, + "step": 47418 + }, + { + "epoch": 14.64, + "learning_rate": 3.5307781242541162e-06, + "loss": 0.0032, + "step": 47419 + }, + { + "epoch": 14.64, + "learning_rate": 3.5303967641816274e-06, + "loss": 0.0038, + "step": 47420 + }, + { + "epoch": 14.64, + "learning_rate": 3.530015420290792e-06, + "loss": 0.0033, + "step": 47421 + }, + { + "epoch": 14.64, + "learning_rate": 3.5296340925825724e-06, + "loss": 0.0041, + "step": 47422 + }, + { + "epoch": 14.65, + "learning_rate": 3.529252781057917e-06, + "loss": 0.0037, + "step": 47423 + }, + { + "epoch": 14.65, + "learning_rate": 3.5288714857177774e-06, + "loss": 0.0034, + "step": 47424 + }, + { + "epoch": 14.65, + "learning_rate": 3.528490206563111e-06, + "loss": 0.0038, + "step": 47425 + }, + { + "epoch": 14.65, + "learning_rate": 3.5281089435948747e-06, + "loss": 0.0032, + "step": 47426 + }, + { + "epoch": 14.65, + "learning_rate": 3.527727696814014e-06, + "loss": 0.0037, + "step": 47427 + }, + { + "epoch": 14.65, + "learning_rate": 3.5273464662214897e-06, + "loss": 0.0034, + "step": 47428 + }, + { + "epoch": 14.65, + "learning_rate": 3.526965251818254e-06, + "loss": 0.0032, + "step": 47429 + }, + { + "epoch": 14.65, + "learning_rate": 3.526584053605254e-06, + "loss": 0.0036, + "step": 47430 + }, + { + "epoch": 14.65, + "learning_rate": 3.5262028715834483e-06, + "loss": 0.0039, + "step": 47431 + }, + { + "epoch": 14.65, + "learning_rate": 3.5258217057537946e-06, + "loss": 0.004, + "step": 47432 + }, + { + "epoch": 14.65, + "learning_rate": 3.52544055611724e-06, + "loss": 0.0029, + "step": 47433 + }, + { + "epoch": 14.65, + "learning_rate": 3.525059422674737e-06, + "loss": 0.0032, + "step": 47434 + }, + { + "epoch": 14.65, + "learning_rate": 3.524678305427245e-06, + "loss": 0.0048, + "step": 47435 + }, + { + "epoch": 14.65, + "learning_rate": 3.5242972043757094e-06, + "loss": 0.004, + "step": 47436 + }, + { + "epoch": 14.65, + "learning_rate": 3.523916119521088e-06, + "loss": 0.0049, + "step": 47437 + }, + { + "epoch": 14.65, + "learning_rate": 3.5235350508643362e-06, + "loss": 0.0037, + "step": 47438 + }, + { + "epoch": 14.65, + "learning_rate": 3.5231539984064058e-06, + "loss": 0.0033, + "step": 47439 + }, + { + "epoch": 14.65, + "learning_rate": 3.5227729621482442e-06, + "loss": 0.0042, + "step": 47440 + }, + { + "epoch": 14.65, + "learning_rate": 3.5223919420908093e-06, + "loss": 0.004, + "step": 47441 + }, + { + "epoch": 14.65, + "learning_rate": 3.5220109382350563e-06, + "loss": 0.0028, + "step": 47442 + }, + { + "epoch": 14.65, + "learning_rate": 3.521629950581936e-06, + "loss": 0.0034, + "step": 47443 + }, + { + "epoch": 14.65, + "learning_rate": 3.521248979132397e-06, + "loss": 0.0032, + "step": 47444 + }, + { + "epoch": 14.65, + "learning_rate": 3.5208680238873993e-06, + "loss": 0.0035, + "step": 47445 + }, + { + "epoch": 14.65, + "learning_rate": 3.52048708484789e-06, + "loss": 0.0035, + "step": 47446 + }, + { + "epoch": 14.65, + "learning_rate": 3.5201061620148236e-06, + "loss": 0.0032, + "step": 47447 + }, + { + "epoch": 14.65, + "learning_rate": 3.519725255389157e-06, + "loss": 0.0037, + "step": 47448 + }, + { + "epoch": 14.65, + "learning_rate": 3.5193443649718393e-06, + "loss": 0.0039, + "step": 47449 + }, + { + "epoch": 14.65, + "learning_rate": 3.518963490763819e-06, + "loss": 0.0034, + "step": 47450 + }, + { + "epoch": 14.65, + "learning_rate": 3.518582632766059e-06, + "loss": 0.0041, + "step": 47451 + }, + { + "epoch": 14.65, + "learning_rate": 3.518201790979501e-06, + "loss": 0.003, + "step": 47452 + }, + { + "epoch": 14.65, + "learning_rate": 3.5178209654051055e-06, + "loss": 0.0035, + "step": 47453 + }, + { + "epoch": 14.65, + "learning_rate": 3.517440156043822e-06, + "loss": 0.0033, + "step": 47454 + }, + { + "epoch": 14.65, + "learning_rate": 3.517059362896601e-06, + "loss": 0.0031, + "step": 47455 + }, + { + "epoch": 14.66, + "learning_rate": 3.516678585964396e-06, + "loss": 0.0042, + "step": 47456 + }, + { + "epoch": 14.66, + "learning_rate": 3.516297825248164e-06, + "loss": 0.0051, + "step": 47457 + }, + { + "epoch": 14.66, + "learning_rate": 3.5159170807488498e-06, + "loss": 0.0027, + "step": 47458 + }, + { + "epoch": 14.66, + "learning_rate": 3.5155363524674137e-06, + "loss": 0.0046, + "step": 47459 + }, + { + "epoch": 14.66, + "learning_rate": 3.515155640404803e-06, + "loss": 0.0037, + "step": 47460 + }, + { + "epoch": 14.66, + "learning_rate": 3.514774944561968e-06, + "loss": 0.0041, + "step": 47461 + }, + { + "epoch": 14.66, + "learning_rate": 3.5143942649398632e-06, + "loss": 0.0046, + "step": 47462 + }, + { + "epoch": 14.66, + "learning_rate": 3.5140136015394455e-06, + "loss": 0.0038, + "step": 47463 + }, + { + "epoch": 14.66, + "learning_rate": 3.513632954361662e-06, + "loss": 0.0031, + "step": 47464 + }, + { + "epoch": 14.66, + "learning_rate": 3.5132523234074633e-06, + "loss": 0.0031, + "step": 47465 + }, + { + "epoch": 14.66, + "learning_rate": 3.5128717086778052e-06, + "loss": 0.0037, + "step": 47466 + }, + { + "epoch": 14.66, + "learning_rate": 3.512491110173636e-06, + "loss": 0.0042, + "step": 47467 + }, + { + "epoch": 14.66, + "learning_rate": 3.51211052789591e-06, + "loss": 0.0038, + "step": 47468 + }, + { + "epoch": 14.66, + "learning_rate": 3.5117299618455815e-06, + "loss": 0.0033, + "step": 47469 + }, + { + "epoch": 14.66, + "learning_rate": 3.5113494120236003e-06, + "loss": 0.0028, + "step": 47470 + }, + { + "epoch": 14.66, + "learning_rate": 3.5109688784309135e-06, + "loss": 0.0028, + "step": 47471 + }, + { + "epoch": 14.66, + "learning_rate": 3.510588361068478e-06, + "loss": 0.0042, + "step": 47472 + }, + { + "epoch": 14.66, + "learning_rate": 3.510207859937248e-06, + "loss": 0.0036, + "step": 47473 + }, + { + "epoch": 14.66, + "learning_rate": 3.5098273750381704e-06, + "loss": 0.0032, + "step": 47474 + }, + { + "epoch": 14.66, + "learning_rate": 3.5094469063721968e-06, + "loss": 0.0032, + "step": 47475 + }, + { + "epoch": 14.66, + "learning_rate": 3.5090664539402817e-06, + "loss": 0.0032, + "step": 47476 + }, + { + "epoch": 14.66, + "learning_rate": 3.5086860177433734e-06, + "loss": 0.0046, + "step": 47477 + }, + { + "epoch": 14.66, + "learning_rate": 3.5083055977824253e-06, + "loss": 0.0048, + "step": 47478 + }, + { + "epoch": 14.66, + "learning_rate": 3.5079251940583915e-06, + "loss": 0.0041, + "step": 47479 + }, + { + "epoch": 14.66, + "learning_rate": 3.5075448065722216e-06, + "loss": 0.0043, + "step": 47480 + }, + { + "epoch": 14.66, + "learning_rate": 3.5071644353248625e-06, + "loss": 0.0052, + "step": 47481 + }, + { + "epoch": 14.66, + "learning_rate": 3.5067840803172726e-06, + "loss": 0.0039, + "step": 47482 + }, + { + "epoch": 14.66, + "learning_rate": 3.5064037415503973e-06, + "loss": 0.0028, + "step": 47483 + }, + { + "epoch": 14.66, + "learning_rate": 3.5060234190251928e-06, + "loss": 0.0042, + "step": 47484 + }, + { + "epoch": 14.66, + "learning_rate": 3.5056431127426095e-06, + "loss": 0.0031, + "step": 47485 + }, + { + "epoch": 14.66, + "learning_rate": 3.5052628227035923e-06, + "loss": 0.0052, + "step": 47486 + }, + { + "epoch": 14.66, + "learning_rate": 3.5048825489090988e-06, + "loss": 0.0054, + "step": 47487 + }, + { + "epoch": 14.67, + "learning_rate": 3.5045022913600813e-06, + "loss": 0.0043, + "step": 47488 + }, + { + "epoch": 14.67, + "learning_rate": 3.5041220500574858e-06, + "loss": 0.0041, + "step": 47489 + }, + { + "epoch": 14.67, + "learning_rate": 3.503741825002268e-06, + "loss": 0.0035, + "step": 47490 + }, + { + "epoch": 14.67, + "learning_rate": 3.5033616161953778e-06, + "loss": 0.0039, + "step": 47491 + }, + { + "epoch": 14.67, + "learning_rate": 3.50298142363776e-06, + "loss": 0.0039, + "step": 47492 + }, + { + "epoch": 14.67, + "learning_rate": 3.5026012473303726e-06, + "loss": 0.0046, + "step": 47493 + }, + { + "epoch": 14.67, + "learning_rate": 3.502221087274167e-06, + "loss": 0.0036, + "step": 47494 + }, + { + "epoch": 14.67, + "learning_rate": 3.501840943470092e-06, + "loss": 0.0031, + "step": 47495 + }, + { + "epoch": 14.67, + "learning_rate": 3.5014608159190944e-06, + "loss": 0.0027, + "step": 47496 + }, + { + "epoch": 14.67, + "learning_rate": 3.501080704622132e-06, + "loss": 0.0041, + "step": 47497 + }, + { + "epoch": 14.67, + "learning_rate": 3.500700609580148e-06, + "loss": 0.0037, + "step": 47498 + }, + { + "epoch": 14.67, + "learning_rate": 3.500320530794098e-06, + "loss": 0.0036, + "step": 47499 + }, + { + "epoch": 14.67, + "learning_rate": 3.4999404682649383e-06, + "loss": 0.0037, + "step": 47500 + }, + { + "epoch": 14.67, + "learning_rate": 3.4995604219936063e-06, + "loss": 0.0037, + "step": 47501 + }, + { + "epoch": 14.67, + "learning_rate": 3.49918039198106e-06, + "loss": 0.0037, + "step": 47502 + }, + { + "epoch": 14.67, + "learning_rate": 3.4988003782282476e-06, + "loss": 0.003, + "step": 47503 + }, + { + "epoch": 14.67, + "learning_rate": 3.498420380736126e-06, + "loss": 0.0042, + "step": 47504 + }, + { + "epoch": 14.67, + "learning_rate": 3.49804039950564e-06, + "loss": 0.0035, + "step": 47505 + }, + { + "epoch": 14.67, + "learning_rate": 3.4976604345377374e-06, + "loss": 0.0041, + "step": 47506 + }, + { + "epoch": 14.67, + "learning_rate": 3.4972804858333764e-06, + "loss": 0.0035, + "step": 47507 + }, + { + "epoch": 14.67, + "learning_rate": 3.4969005533934986e-06, + "loss": 0.0046, + "step": 47508 + }, + { + "epoch": 14.67, + "learning_rate": 3.4965206372190598e-06, + "loss": 0.0041, + "step": 47509 + }, + { + "epoch": 14.67, + "learning_rate": 3.4961407373110146e-06, + "loss": 0.004, + "step": 47510 + }, + { + "epoch": 14.67, + "learning_rate": 3.4957608536703015e-06, + "loss": 0.0028, + "step": 47511 + }, + { + "epoch": 14.67, + "learning_rate": 3.495380986297876e-06, + "loss": 0.004, + "step": 47512 + }, + { + "epoch": 14.67, + "learning_rate": 3.4950011351946935e-06, + "loss": 0.0041, + "step": 47513 + }, + { + "epoch": 14.67, + "learning_rate": 3.4946213003616947e-06, + "loss": 0.0041, + "step": 47514 + }, + { + "epoch": 14.67, + "learning_rate": 3.494241481799839e-06, + "loss": 0.0048, + "step": 47515 + }, + { + "epoch": 14.67, + "learning_rate": 3.4938616795100724e-06, + "loss": 0.0037, + "step": 47516 + }, + { + "epoch": 14.67, + "learning_rate": 3.4934818934933403e-06, + "loss": 0.0031, + "step": 47517 + }, + { + "epoch": 14.67, + "learning_rate": 3.493102123750597e-06, + "loss": 0.0036, + "step": 47518 + }, + { + "epoch": 14.67, + "learning_rate": 3.492722370282795e-06, + "loss": 0.0034, + "step": 47519 + }, + { + "epoch": 14.68, + "learning_rate": 3.4923426330908815e-06, + "loss": 0.0037, + "step": 47520 + }, + { + "epoch": 14.68, + "learning_rate": 3.4919629121758024e-06, + "loss": 0.0038, + "step": 47521 + }, + { + "epoch": 14.68, + "learning_rate": 3.4915832075385147e-06, + "loss": 0.0032, + "step": 47522 + }, + { + "epoch": 14.68, + "learning_rate": 3.491203519179961e-06, + "loss": 0.0029, + "step": 47523 + }, + { + "epoch": 14.68, + "learning_rate": 3.4908238471010945e-06, + "loss": 0.0047, + "step": 47524 + }, + { + "epoch": 14.68, + "learning_rate": 3.4904441913028676e-06, + "loss": 0.0036, + "step": 47525 + }, + { + "epoch": 14.68, + "learning_rate": 3.4900645517862275e-06, + "loss": 0.0041, + "step": 47526 + }, + { + "epoch": 14.68, + "learning_rate": 3.4896849285521204e-06, + "loss": 0.0037, + "step": 47527 + }, + { + "epoch": 14.68, + "learning_rate": 3.4893053216015017e-06, + "loss": 0.0039, + "step": 47528 + }, + { + "epoch": 14.68, + "learning_rate": 3.4889257309353142e-06, + "loss": 0.0027, + "step": 47529 + }, + { + "epoch": 14.68, + "learning_rate": 3.4885461565545142e-06, + "loss": 0.0042, + "step": 47530 + }, + { + "epoch": 14.68, + "learning_rate": 3.4881665984600487e-06, + "loss": 0.0036, + "step": 47531 + }, + { + "epoch": 14.68, + "learning_rate": 3.487787056652863e-06, + "loss": 0.0032, + "step": 47532 + }, + { + "epoch": 14.68, + "learning_rate": 3.4874075311339085e-06, + "loss": 0.0033, + "step": 47533 + }, + { + "epoch": 14.68, + "learning_rate": 3.4870280219041396e-06, + "loss": 0.004, + "step": 47534 + }, + { + "epoch": 14.68, + "learning_rate": 3.486648528964498e-06, + "loss": 0.003, + "step": 47535 + }, + { + "epoch": 14.68, + "learning_rate": 3.4862690523159394e-06, + "loss": 0.0038, + "step": 47536 + }, + { + "epoch": 14.68, + "learning_rate": 3.485889591959407e-06, + "loss": 0.0047, + "step": 47537 + }, + { + "epoch": 14.68, + "learning_rate": 3.4855101478958563e-06, + "loss": 0.0035, + "step": 47538 + }, + { + "epoch": 14.68, + "learning_rate": 3.48513072012623e-06, + "loss": 0.0036, + "step": 47539 + }, + { + "epoch": 14.68, + "learning_rate": 3.484751308651482e-06, + "loss": 0.0039, + "step": 47540 + }, + { + "epoch": 14.68, + "learning_rate": 3.4843719134725594e-06, + "loss": 0.0032, + "step": 47541 + }, + { + "epoch": 14.68, + "learning_rate": 3.483992534590409e-06, + "loss": 0.0035, + "step": 47542 + }, + { + "epoch": 14.68, + "learning_rate": 3.483613172005981e-06, + "loss": 0.004, + "step": 47543 + }, + { + "epoch": 14.68, + "learning_rate": 3.483233825720228e-06, + "loss": 0.0027, + "step": 47544 + }, + { + "epoch": 14.68, + "learning_rate": 3.4828544957340925e-06, + "loss": 0.0028, + "step": 47545 + }, + { + "epoch": 14.68, + "learning_rate": 3.4824751820485304e-06, + "loss": 0.0036, + "step": 47546 + }, + { + "epoch": 14.68, + "learning_rate": 3.482095884664486e-06, + "loss": 0.0024, + "step": 47547 + }, + { + "epoch": 14.68, + "learning_rate": 3.4817166035829063e-06, + "loss": 0.0033, + "step": 47548 + }, + { + "epoch": 14.68, + "learning_rate": 3.481337338804741e-06, + "loss": 0.0036, + "step": 47549 + }, + { + "epoch": 14.68, + "learning_rate": 3.480958090330944e-06, + "loss": 0.0033, + "step": 47550 + }, + { + "epoch": 14.68, + "learning_rate": 3.48057885816246e-06, + "loss": 0.0039, + "step": 47551 + }, + { + "epoch": 14.68, + "learning_rate": 3.4801996423002337e-06, + "loss": 0.005, + "step": 47552 + }, + { + "epoch": 14.69, + "learning_rate": 3.47982044274522e-06, + "loss": 0.0042, + "step": 47553 + }, + { + "epoch": 14.69, + "learning_rate": 3.479441259498362e-06, + "loss": 0.0032, + "step": 47554 + }, + { + "epoch": 14.69, + "learning_rate": 3.47906209256061e-06, + "loss": 0.0034, + "step": 47555 + }, + { + "epoch": 14.69, + "learning_rate": 3.478682941932917e-06, + "loss": 0.0035, + "step": 47556 + }, + { + "epoch": 14.69, + "learning_rate": 3.478303807616227e-06, + "loss": 0.0049, + "step": 47557 + }, + { + "epoch": 14.69, + "learning_rate": 3.477924689611486e-06, + "loss": 0.0037, + "step": 47558 + }, + { + "epoch": 14.69, + "learning_rate": 3.4775455879196474e-06, + "loss": 0.0036, + "step": 47559 + }, + { + "epoch": 14.69, + "learning_rate": 3.4771665025416545e-06, + "loss": 0.0034, + "step": 47560 + }, + { + "epoch": 14.69, + "learning_rate": 3.47678743347846e-06, + "loss": 0.0031, + "step": 47561 + }, + { + "epoch": 14.69, + "learning_rate": 3.4764083807310112e-06, + "loss": 0.0038, + "step": 47562 + }, + { + "epoch": 14.69, + "learning_rate": 3.4760293443002503e-06, + "loss": 0.0053, + "step": 47563 + }, + { + "epoch": 14.69, + "learning_rate": 3.475650324187131e-06, + "loss": 0.0038, + "step": 47564 + }, + { + "epoch": 14.69, + "learning_rate": 3.4752713203926025e-06, + "loss": 0.0034, + "step": 47565 + }, + { + "epoch": 14.69, + "learning_rate": 3.474892332917608e-06, + "loss": 0.0033, + "step": 47566 + }, + { + "epoch": 14.69, + "learning_rate": 3.4745133617631e-06, + "loss": 0.0041, + "step": 47567 + }, + { + "epoch": 14.69, + "learning_rate": 3.474134406930022e-06, + "loss": 0.0032, + "step": 47568 + }, + { + "epoch": 14.69, + "learning_rate": 3.4737554684193274e-06, + "loss": 0.0046, + "step": 47569 + }, + { + "epoch": 14.69, + "learning_rate": 3.473376546231957e-06, + "loss": 0.004, + "step": 47570 + }, + { + "epoch": 14.69, + "learning_rate": 3.472997640368866e-06, + "loss": 0.0033, + "step": 47571 + }, + { + "epoch": 14.69, + "learning_rate": 3.4726187508309982e-06, + "loss": 0.0031, + "step": 47572 + }, + { + "epoch": 14.69, + "learning_rate": 3.4722398776192977e-06, + "loss": 0.004, + "step": 47573 + }, + { + "epoch": 14.69, + "learning_rate": 3.4718610207347158e-06, + "loss": 0.0032, + "step": 47574 + }, + { + "epoch": 14.69, + "learning_rate": 3.4714821801782037e-06, + "loss": 0.0042, + "step": 47575 + }, + { + "epoch": 14.69, + "learning_rate": 3.4711033559507023e-06, + "loss": 0.003, + "step": 47576 + }, + { + "epoch": 14.69, + "learning_rate": 3.470724548053166e-06, + "loss": 0.0029, + "step": 47577 + }, + { + "epoch": 14.69, + "learning_rate": 3.4703457564865374e-06, + "loss": 0.0035, + "step": 47578 + }, + { + "epoch": 14.69, + "learning_rate": 3.469966981251762e-06, + "loss": 0.0046, + "step": 47579 + }, + { + "epoch": 14.69, + "learning_rate": 3.46958822234979e-06, + "loss": 0.0028, + "step": 47580 + }, + { + "epoch": 14.69, + "learning_rate": 3.4692094797815733e-06, + "loss": 0.0035, + "step": 47581 + }, + { + "epoch": 14.69, + "learning_rate": 3.468830753548054e-06, + "loss": 0.0037, + "step": 47582 + }, + { + "epoch": 14.69, + "learning_rate": 3.4684520436501767e-06, + "loss": 0.0033, + "step": 47583 + }, + { + "epoch": 14.69, + "learning_rate": 3.4680733500888965e-06, + "loss": 0.004, + "step": 47584 + }, + { + "epoch": 14.7, + "learning_rate": 3.467694672865152e-06, + "loss": 0.0034, + "step": 47585 + }, + { + "epoch": 14.7, + "learning_rate": 3.4673160119798943e-06, + "loss": 0.0042, + "step": 47586 + }, + { + "epoch": 14.7, + "learning_rate": 3.4669373674340747e-06, + "loss": 0.0026, + "step": 47587 + }, + { + "epoch": 14.7, + "learning_rate": 3.466558739228636e-06, + "loss": 0.0041, + "step": 47588 + }, + { + "epoch": 14.7, + "learning_rate": 3.4661801273645214e-06, + "loss": 0.0041, + "step": 47589 + }, + { + "epoch": 14.7, + "learning_rate": 3.4658015318426865e-06, + "loss": 0.0039, + "step": 47590 + }, + { + "epoch": 14.7, + "learning_rate": 3.46542295266407e-06, + "loss": 0.0033, + "step": 47591 + }, + { + "epoch": 14.7, + "learning_rate": 3.465044389829626e-06, + "loss": 0.003, + "step": 47592 + }, + { + "epoch": 14.7, + "learning_rate": 3.464665843340298e-06, + "loss": 0.0034, + "step": 47593 + }, + { + "epoch": 14.7, + "learning_rate": 3.464287313197029e-06, + "loss": 0.0026, + "step": 47594 + }, + { + "epoch": 14.7, + "learning_rate": 3.4639087994007692e-06, + "loss": 0.0035, + "step": 47595 + }, + { + "epoch": 14.7, + "learning_rate": 3.463530301952469e-06, + "loss": 0.004, + "step": 47596 + }, + { + "epoch": 14.7, + "learning_rate": 3.463151820853069e-06, + "loss": 0.0054, + "step": 47597 + }, + { + "epoch": 14.7, + "learning_rate": 3.4627733561035214e-06, + "loss": 0.004, + "step": 47598 + }, + { + "epoch": 14.7, + "learning_rate": 3.4623949077047703e-06, + "loss": 0.004, + "step": 47599 + }, + { + "epoch": 14.7, + "learning_rate": 3.462016475657759e-06, + "loss": 0.0034, + "step": 47600 + }, + { + "epoch": 14.7, + "learning_rate": 3.4616380599634357e-06, + "loss": 0.0037, + "step": 47601 + }, + { + "epoch": 14.7, + "learning_rate": 3.461259660622752e-06, + "loss": 0.0034, + "step": 47602 + }, + { + "epoch": 14.7, + "learning_rate": 3.4608812776366506e-06, + "loss": 0.0033, + "step": 47603 + }, + { + "epoch": 14.7, + "learning_rate": 3.460502911006075e-06, + "loss": 0.0041, + "step": 47604 + }, + { + "epoch": 14.7, + "learning_rate": 3.4601245607319735e-06, + "loss": 0.0036, + "step": 47605 + }, + { + "epoch": 14.7, + "learning_rate": 3.459746226815297e-06, + "loss": 0.0036, + "step": 47606 + }, + { + "epoch": 14.7, + "learning_rate": 3.459367909256984e-06, + "loss": 0.0038, + "step": 47607 + }, + { + "epoch": 14.7, + "learning_rate": 3.45898960805799e-06, + "loss": 0.0043, + "step": 47608 + }, + { + "epoch": 14.7, + "learning_rate": 3.4586113232192544e-06, + "loss": 0.0036, + "step": 47609 + }, + { + "epoch": 14.7, + "learning_rate": 3.458233054741722e-06, + "loss": 0.0037, + "step": 47610 + }, + { + "epoch": 14.7, + "learning_rate": 3.4578548026263416e-06, + "loss": 0.0035, + "step": 47611 + }, + { + "epoch": 14.7, + "learning_rate": 3.457476566874063e-06, + "loss": 0.0044, + "step": 47612 + }, + { + "epoch": 14.7, + "learning_rate": 3.457098347485829e-06, + "loss": 0.004, + "step": 47613 + }, + { + "epoch": 14.7, + "learning_rate": 3.456720144462582e-06, + "loss": 0.0036, + "step": 47614 + }, + { + "epoch": 14.7, + "learning_rate": 3.456341957805275e-06, + "loss": 0.0026, + "step": 47615 + }, + { + "epoch": 14.7, + "learning_rate": 3.4559637875148466e-06, + "loss": 0.0037, + "step": 47616 + }, + { + "epoch": 14.71, + "learning_rate": 3.4555856335922457e-06, + "loss": 0.0031, + "step": 47617 + }, + { + "epoch": 14.71, + "learning_rate": 3.455207496038426e-06, + "loss": 0.0036, + "step": 47618 + }, + { + "epoch": 14.71, + "learning_rate": 3.4548293748543195e-06, + "loss": 0.0043, + "step": 47619 + }, + { + "epoch": 14.71, + "learning_rate": 3.4544512700408784e-06, + "loss": 0.0034, + "step": 47620 + }, + { + "epoch": 14.71, + "learning_rate": 3.4540731815990523e-06, + "loss": 0.0032, + "step": 47621 + }, + { + "epoch": 14.71, + "learning_rate": 3.453695109529779e-06, + "loss": 0.0029, + "step": 47622 + }, + { + "epoch": 14.71, + "learning_rate": 3.4533170538340123e-06, + "loss": 0.0032, + "step": 47623 + }, + { + "epoch": 14.71, + "learning_rate": 3.452939014512693e-06, + "loss": 0.0041, + "step": 47624 + }, + { + "epoch": 14.71, + "learning_rate": 3.4525609915667636e-06, + "loss": 0.0042, + "step": 47625 + }, + { + "epoch": 14.71, + "learning_rate": 3.4521829849971745e-06, + "loss": 0.0041, + "step": 47626 + }, + { + "epoch": 14.71, + "learning_rate": 3.4518049948048726e-06, + "loss": 0.003, + "step": 47627 + }, + { + "epoch": 14.71, + "learning_rate": 3.4514270209908006e-06, + "loss": 0.0037, + "step": 47628 + }, + { + "epoch": 14.71, + "learning_rate": 3.4510490635559012e-06, + "loss": 0.0029, + "step": 47629 + }, + { + "epoch": 14.71, + "learning_rate": 3.4506711225011258e-06, + "loss": 0.0031, + "step": 47630 + }, + { + "epoch": 14.71, + "learning_rate": 3.4502931978274123e-06, + "loss": 0.0044, + "step": 47631 + }, + { + "epoch": 14.71, + "learning_rate": 3.449915289535711e-06, + "loss": 0.0037, + "step": 47632 + }, + { + "epoch": 14.71, + "learning_rate": 3.4495373976269698e-06, + "loss": 0.0039, + "step": 47633 + }, + { + "epoch": 14.71, + "learning_rate": 3.44915952210213e-06, + "loss": 0.004, + "step": 47634 + }, + { + "epoch": 14.71, + "learning_rate": 3.448781662962133e-06, + "loss": 0.0034, + "step": 47635 + }, + { + "epoch": 14.71, + "learning_rate": 3.4484038202079286e-06, + "loss": 0.0043, + "step": 47636 + }, + { + "epoch": 14.71, + "learning_rate": 3.4480259938404646e-06, + "loss": 0.0037, + "step": 47637 + }, + { + "epoch": 14.71, + "learning_rate": 3.447648183860679e-06, + "loss": 0.0047, + "step": 47638 + }, + { + "epoch": 14.71, + "learning_rate": 3.4472703902695237e-06, + "loss": 0.0032, + "step": 47639 + }, + { + "epoch": 14.71, + "learning_rate": 3.4468926130679403e-06, + "loss": 0.0037, + "step": 47640 + }, + { + "epoch": 14.71, + "learning_rate": 3.4465148522568704e-06, + "loss": 0.0034, + "step": 47641 + }, + { + "epoch": 14.71, + "learning_rate": 3.446137107837262e-06, + "loss": 0.0027, + "step": 47642 + }, + { + "epoch": 14.71, + "learning_rate": 3.445759379810063e-06, + "loss": 0.0034, + "step": 47643 + }, + { + "epoch": 14.71, + "learning_rate": 3.4453816681762164e-06, + "loss": 0.0035, + "step": 47644 + }, + { + "epoch": 14.71, + "learning_rate": 3.4450039729366614e-06, + "loss": 0.0039, + "step": 47645 + }, + { + "epoch": 14.71, + "learning_rate": 3.44462629409235e-06, + "loss": 0.0036, + "step": 47646 + }, + { + "epoch": 14.71, + "learning_rate": 3.4442486316442214e-06, + "loss": 0.0039, + "step": 47647 + }, + { + "epoch": 14.71, + "learning_rate": 3.4438709855932228e-06, + "loss": 0.0033, + "step": 47648 + }, + { + "epoch": 14.71, + "learning_rate": 3.443493355940305e-06, + "loss": 0.004, + "step": 47649 + }, + { + "epoch": 14.72, + "learning_rate": 3.4431157426863993e-06, + "loss": 0.0029, + "step": 47650 + }, + { + "epoch": 14.72, + "learning_rate": 3.442738145832457e-06, + "loss": 0.0038, + "step": 47651 + }, + { + "epoch": 14.72, + "learning_rate": 3.4423605653794266e-06, + "loss": 0.0044, + "step": 47652 + }, + { + "epoch": 14.72, + "learning_rate": 3.4419830013282442e-06, + "loss": 0.0035, + "step": 47653 + }, + { + "epoch": 14.72, + "learning_rate": 3.4416054536798625e-06, + "loss": 0.0045, + "step": 47654 + }, + { + "epoch": 14.72, + "learning_rate": 3.4412279224352217e-06, + "loss": 0.0029, + "step": 47655 + }, + { + "epoch": 14.72, + "learning_rate": 3.440850407595262e-06, + "loss": 0.0036, + "step": 47656 + }, + { + "epoch": 14.72, + "learning_rate": 3.4404729091609323e-06, + "loss": 0.0027, + "step": 47657 + }, + { + "epoch": 14.72, + "learning_rate": 3.4400954271331798e-06, + "loss": 0.0047, + "step": 47658 + }, + { + "epoch": 14.72, + "learning_rate": 3.439717961512945e-06, + "loss": 0.0035, + "step": 47659 + }, + { + "epoch": 14.72, + "learning_rate": 3.439340512301168e-06, + "loss": 0.0041, + "step": 47660 + }, + { + "epoch": 14.72, + "learning_rate": 3.4389630794988004e-06, + "loss": 0.0038, + "step": 47661 + }, + { + "epoch": 14.72, + "learning_rate": 3.4385856631067805e-06, + "loss": 0.0039, + "step": 47662 + }, + { + "epoch": 14.72, + "learning_rate": 3.4382082631260537e-06, + "loss": 0.0037, + "step": 47663 + }, + { + "epoch": 14.72, + "learning_rate": 3.4378308795575686e-06, + "loss": 0.0041, + "step": 47664 + }, + { + "epoch": 14.72, + "learning_rate": 3.4374535124022657e-06, + "loss": 0.0033, + "step": 47665 + }, + { + "epoch": 14.72, + "learning_rate": 3.4370761616610837e-06, + "loss": 0.0048, + "step": 47666 + }, + { + "epoch": 14.72, + "learning_rate": 3.436698827334972e-06, + "loss": 0.0037, + "step": 47667 + }, + { + "epoch": 14.72, + "learning_rate": 3.436321509424878e-06, + "loss": 0.005, + "step": 47668 + }, + { + "epoch": 14.72, + "learning_rate": 3.4359442079317396e-06, + "loss": 0.0033, + "step": 47669 + }, + { + "epoch": 14.72, + "learning_rate": 3.4355669228564992e-06, + "loss": 0.0027, + "step": 47670 + }, + { + "epoch": 14.72, + "learning_rate": 3.435189654200106e-06, + "loss": 0.0038, + "step": 47671 + }, + { + "epoch": 14.72, + "learning_rate": 3.434812401963499e-06, + "loss": 0.0034, + "step": 47672 + }, + { + "epoch": 14.72, + "learning_rate": 3.4344351661476226e-06, + "loss": 0.0036, + "step": 47673 + }, + { + "epoch": 14.72, + "learning_rate": 3.434057946753424e-06, + "loss": 0.0034, + "step": 47674 + }, + { + "epoch": 14.72, + "learning_rate": 3.4336807437818453e-06, + "loss": 0.0037, + "step": 47675 + }, + { + "epoch": 14.72, + "learning_rate": 3.4333035572338246e-06, + "loss": 0.0035, + "step": 47676 + }, + { + "epoch": 14.72, + "learning_rate": 3.4329263871103124e-06, + "loss": 0.0048, + "step": 47677 + }, + { + "epoch": 14.72, + "learning_rate": 3.4325492334122466e-06, + "loss": 0.0041, + "step": 47678 + }, + { + "epoch": 14.72, + "learning_rate": 3.4321720961405756e-06, + "loss": 0.0036, + "step": 47679 + }, + { + "epoch": 14.72, + "learning_rate": 3.431794975296241e-06, + "loss": 0.0053, + "step": 47680 + }, + { + "epoch": 14.72, + "learning_rate": 3.4314178708801804e-06, + "loss": 0.0041, + "step": 47681 + }, + { + "epoch": 14.73, + "learning_rate": 3.4310407828933434e-06, + "loss": 0.0044, + "step": 47682 + }, + { + "epoch": 14.73, + "learning_rate": 3.430663711336674e-06, + "loss": 0.0041, + "step": 47683 + }, + { + "epoch": 14.73, + "learning_rate": 3.4302866562111093e-06, + "loss": 0.004, + "step": 47684 + }, + { + "epoch": 14.73, + "learning_rate": 3.4299096175175994e-06, + "loss": 0.0031, + "step": 47685 + }, + { + "epoch": 14.73, + "learning_rate": 3.4295325952570835e-06, + "loss": 0.0033, + "step": 47686 + }, + { + "epoch": 14.73, + "learning_rate": 3.429155589430502e-06, + "loss": 0.0039, + "step": 47687 + }, + { + "epoch": 14.73, + "learning_rate": 3.4287786000388013e-06, + "loss": 0.003, + "step": 47688 + }, + { + "epoch": 14.73, + "learning_rate": 3.428401627082927e-06, + "loss": 0.0025, + "step": 47689 + }, + { + "epoch": 14.73, + "learning_rate": 3.4280246705638177e-06, + "loss": 0.0038, + "step": 47690 + }, + { + "epoch": 14.73, + "learning_rate": 3.427647730482415e-06, + "loss": 0.0034, + "step": 47691 + }, + { + "epoch": 14.73, + "learning_rate": 3.4272708068396675e-06, + "loss": 0.0037, + "step": 47692 + }, + { + "epoch": 14.73, + "learning_rate": 3.4268938996365107e-06, + "loss": 0.0036, + "step": 47693 + }, + { + "epoch": 14.73, + "learning_rate": 3.4265170088738907e-06, + "loss": 0.003, + "step": 47694 + }, + { + "epoch": 14.73, + "learning_rate": 3.4261401345527544e-06, + "loss": 0.0033, + "step": 47695 + }, + { + "epoch": 14.73, + "learning_rate": 3.4257632766740414e-06, + "loss": 0.0039, + "step": 47696 + }, + { + "epoch": 14.73, + "learning_rate": 3.425386435238689e-06, + "loss": 0.0038, + "step": 47697 + }, + { + "epoch": 14.73, + "learning_rate": 3.425009610247645e-06, + "loss": 0.0048, + "step": 47698 + }, + { + "epoch": 14.73, + "learning_rate": 3.424632801701855e-06, + "loss": 0.0031, + "step": 47699 + }, + { + "epoch": 14.73, + "learning_rate": 3.424256009602257e-06, + "loss": 0.004, + "step": 47700 + }, + { + "epoch": 14.73, + "learning_rate": 3.4238792339497906e-06, + "loss": 0.0036, + "step": 47701 + }, + { + "epoch": 14.73, + "learning_rate": 3.423502474745405e-06, + "loss": 0.0029, + "step": 47702 + }, + { + "epoch": 14.73, + "learning_rate": 3.4231257319900356e-06, + "loss": 0.0029, + "step": 47703 + }, + { + "epoch": 14.73, + "learning_rate": 3.422749005684628e-06, + "loss": 0.0035, + "step": 47704 + }, + { + "epoch": 14.73, + "learning_rate": 3.4223722958301287e-06, + "loss": 0.0028, + "step": 47705 + }, + { + "epoch": 14.73, + "learning_rate": 3.421995602427476e-06, + "loss": 0.0035, + "step": 47706 + }, + { + "epoch": 14.73, + "learning_rate": 3.4216189254776088e-06, + "loss": 0.0033, + "step": 47707 + }, + { + "epoch": 14.73, + "learning_rate": 3.4212422649814757e-06, + "loss": 0.0034, + "step": 47708 + }, + { + "epoch": 14.73, + "learning_rate": 3.4208656209400125e-06, + "loss": 0.004, + "step": 47709 + }, + { + "epoch": 14.73, + "learning_rate": 3.4204889933541672e-06, + "loss": 0.0037, + "step": 47710 + }, + { + "epoch": 14.73, + "learning_rate": 3.4201123822248795e-06, + "loss": 0.0036, + "step": 47711 + }, + { + "epoch": 14.73, + "learning_rate": 3.4197357875530866e-06, + "loss": 0.0042, + "step": 47712 + }, + { + "epoch": 14.73, + "learning_rate": 3.4193592093397356e-06, + "loss": 0.0034, + "step": 47713 + }, + { + "epoch": 14.73, + "learning_rate": 3.4189826475857703e-06, + "loss": 0.0037, + "step": 47714 + }, + { + "epoch": 14.74, + "learning_rate": 3.418606102292127e-06, + "loss": 0.0033, + "step": 47715 + }, + { + "epoch": 14.74, + "learning_rate": 3.4182295734597527e-06, + "loss": 0.0035, + "step": 47716 + }, + { + "epoch": 14.74, + "learning_rate": 3.4178530610895867e-06, + "loss": 0.0042, + "step": 47717 + }, + { + "epoch": 14.74, + "learning_rate": 3.417476565182568e-06, + "loss": 0.003, + "step": 47718 + }, + { + "epoch": 14.74, + "learning_rate": 3.4171000857396407e-06, + "loss": 0.0035, + "step": 47719 + }, + { + "epoch": 14.74, + "learning_rate": 3.4167236227617496e-06, + "loss": 0.0035, + "step": 47720 + }, + { + "epoch": 14.74, + "learning_rate": 3.4163471762498335e-06, + "loss": 0.0053, + "step": 47721 + }, + { + "epoch": 14.74, + "learning_rate": 3.4159707462048307e-06, + "loss": 0.0032, + "step": 47722 + }, + { + "epoch": 14.74, + "learning_rate": 3.4155943326276897e-06, + "loss": 0.0032, + "step": 47723 + }, + { + "epoch": 14.74, + "learning_rate": 3.415217935519345e-06, + "loss": 0.0038, + "step": 47724 + }, + { + "epoch": 14.74, + "learning_rate": 3.414841554880741e-06, + "loss": 0.0027, + "step": 47725 + }, + { + "epoch": 14.74, + "learning_rate": 3.4144651907128225e-06, + "loss": 0.0024, + "step": 47726 + }, + { + "epoch": 14.74, + "learning_rate": 3.4140888430165277e-06, + "loss": 0.0035, + "step": 47727 + }, + { + "epoch": 14.74, + "learning_rate": 3.413712511792794e-06, + "loss": 0.0045, + "step": 47728 + }, + { + "epoch": 14.74, + "learning_rate": 3.4133361970425705e-06, + "loss": 0.0035, + "step": 47729 + }, + { + "epoch": 14.74, + "learning_rate": 3.412959898766791e-06, + "loss": 0.0035, + "step": 47730 + }, + { + "epoch": 14.74, + "learning_rate": 3.412583616966404e-06, + "loss": 0.0034, + "step": 47731 + }, + { + "epoch": 14.74, + "learning_rate": 3.412207351642344e-06, + "loss": 0.0051, + "step": 47732 + }, + { + "epoch": 14.74, + "learning_rate": 3.4118311027955563e-06, + "loss": 0.0041, + "step": 47733 + }, + { + "epoch": 14.74, + "learning_rate": 3.411454870426979e-06, + "loss": 0.0033, + "step": 47734 + }, + { + "epoch": 14.74, + "learning_rate": 3.411078654537554e-06, + "loss": 0.0043, + "step": 47735 + }, + { + "epoch": 14.74, + "learning_rate": 3.4107024551282263e-06, + "loss": 0.0033, + "step": 47736 + }, + { + "epoch": 14.74, + "learning_rate": 3.4103262721999343e-06, + "loss": 0.0036, + "step": 47737 + }, + { + "epoch": 14.74, + "learning_rate": 3.4099501057536142e-06, + "loss": 0.0034, + "step": 47738 + }, + { + "epoch": 14.74, + "learning_rate": 3.409573955790214e-06, + "loss": 0.0041, + "step": 47739 + }, + { + "epoch": 14.74, + "learning_rate": 3.4091978223106682e-06, + "loss": 0.0036, + "step": 47740 + }, + { + "epoch": 14.74, + "learning_rate": 3.4088217053159244e-06, + "loss": 0.0043, + "step": 47741 + }, + { + "epoch": 14.74, + "learning_rate": 3.4084456048069193e-06, + "loss": 0.0042, + "step": 47742 + }, + { + "epoch": 14.74, + "learning_rate": 3.4080695207845914e-06, + "loss": 0.004, + "step": 47743 + }, + { + "epoch": 14.74, + "learning_rate": 3.407693453249883e-06, + "loss": 0.0037, + "step": 47744 + }, + { + "epoch": 14.74, + "learning_rate": 3.407317402203739e-06, + "loss": 0.0039, + "step": 47745 + }, + { + "epoch": 14.74, + "learning_rate": 3.406941367647094e-06, + "loss": 0.004, + "step": 47746 + }, + { + "epoch": 14.75, + "learning_rate": 3.4065653495808936e-06, + "loss": 0.0043, + "step": 47747 + }, + { + "epoch": 14.75, + "learning_rate": 3.406189348006077e-06, + "loss": 0.0046, + "step": 47748 + }, + { + "epoch": 14.75, + "learning_rate": 3.405813362923579e-06, + "loss": 0.004, + "step": 47749 + }, + { + "epoch": 14.75, + "learning_rate": 3.4054373943343455e-06, + "loss": 0.0032, + "step": 47750 + }, + { + "epoch": 14.75, + "learning_rate": 3.405061442239318e-06, + "loss": 0.0032, + "step": 47751 + }, + { + "epoch": 14.75, + "learning_rate": 3.4046855066394357e-06, + "loss": 0.0036, + "step": 47752 + }, + { + "epoch": 14.75, + "learning_rate": 3.4043095875356335e-06, + "loss": 0.0031, + "step": 47753 + }, + { + "epoch": 14.75, + "learning_rate": 3.4039336849288605e-06, + "loss": 0.0045, + "step": 47754 + }, + { + "epoch": 14.75, + "learning_rate": 3.4035577988200485e-06, + "loss": 0.0036, + "step": 47755 + }, + { + "epoch": 14.75, + "learning_rate": 3.403181929210142e-06, + "loss": 0.0041, + "step": 47756 + }, + { + "epoch": 14.75, + "learning_rate": 3.4028060761000857e-06, + "loss": 0.0035, + "step": 47757 + }, + { + "epoch": 14.75, + "learning_rate": 3.4024302394908106e-06, + "loss": 0.0037, + "step": 47758 + }, + { + "epoch": 14.75, + "learning_rate": 3.402054419383258e-06, + "loss": 0.0038, + "step": 47759 + }, + { + "epoch": 14.75, + "learning_rate": 3.4016786157783767e-06, + "loss": 0.0026, + "step": 47760 + }, + { + "epoch": 14.75, + "learning_rate": 3.4013028286770953e-06, + "loss": 0.0032, + "step": 47761 + }, + { + "epoch": 14.75, + "learning_rate": 3.400927058080363e-06, + "loss": 0.0039, + "step": 47762 + }, + { + "epoch": 14.75, + "learning_rate": 3.4005513039891157e-06, + "loss": 0.0034, + "step": 47763 + }, + { + "epoch": 14.75, + "learning_rate": 3.4001755664042903e-06, + "loss": 0.0037, + "step": 47764 + }, + { + "epoch": 14.75, + "learning_rate": 3.3997998453268287e-06, + "loss": 0.0037, + "step": 47765 + }, + { + "epoch": 14.75, + "learning_rate": 3.399424140757672e-06, + "loss": 0.0039, + "step": 47766 + }, + { + "epoch": 14.75, + "learning_rate": 3.3990484526977675e-06, + "loss": 0.0039, + "step": 47767 + }, + { + "epoch": 14.75, + "learning_rate": 3.398672781148038e-06, + "loss": 0.0038, + "step": 47768 + }, + { + "epoch": 14.75, + "learning_rate": 3.398297126109432e-06, + "loss": 0.0039, + "step": 47769 + }, + { + "epoch": 14.75, + "learning_rate": 3.3979214875828936e-06, + "loss": 0.0034, + "step": 47770 + }, + { + "epoch": 14.75, + "learning_rate": 3.397545865569354e-06, + "loss": 0.0028, + "step": 47771 + }, + { + "epoch": 14.75, + "learning_rate": 3.3971702600697586e-06, + "loss": 0.0044, + "step": 47772 + }, + { + "epoch": 14.75, + "learning_rate": 3.3967946710850464e-06, + "loss": 0.0042, + "step": 47773 + }, + { + "epoch": 14.75, + "learning_rate": 3.3964190986161506e-06, + "loss": 0.004, + "step": 47774 + }, + { + "epoch": 14.75, + "learning_rate": 3.396043542664015e-06, + "loss": 0.0041, + "step": 47775 + }, + { + "epoch": 14.75, + "learning_rate": 3.395668003229583e-06, + "loss": 0.0031, + "step": 47776 + }, + { + "epoch": 14.75, + "learning_rate": 3.3952924803137886e-06, + "loss": 0.004, + "step": 47777 + }, + { + "epoch": 14.75, + "learning_rate": 3.3949169739175704e-06, + "loss": 0.0041, + "step": 47778 + }, + { + "epoch": 14.76, + "learning_rate": 3.3945414840418722e-06, + "loss": 0.0044, + "step": 47779 + }, + { + "epoch": 14.76, + "learning_rate": 3.3941660106876275e-06, + "loss": 0.004, + "step": 47780 + }, + { + "epoch": 14.76, + "learning_rate": 3.393790553855778e-06, + "loss": 0.0029, + "step": 47781 + }, + { + "epoch": 14.76, + "learning_rate": 3.393415113547267e-06, + "loss": 0.0043, + "step": 47782 + }, + { + "epoch": 14.76, + "learning_rate": 3.393039689763029e-06, + "loss": 0.0035, + "step": 47783 + }, + { + "epoch": 14.76, + "learning_rate": 3.392664282504001e-06, + "loss": 0.0034, + "step": 47784 + }, + { + "epoch": 14.76, + "learning_rate": 3.3922888917711284e-06, + "loss": 0.0043, + "step": 47785 + }, + { + "epoch": 14.76, + "learning_rate": 3.3919135175653427e-06, + "loss": 0.0041, + "step": 47786 + }, + { + "epoch": 14.76, + "learning_rate": 3.3915381598875907e-06, + "loss": 0.0041, + "step": 47787 + }, + { + "epoch": 14.76, + "learning_rate": 3.3911628187388057e-06, + "loss": 0.002, + "step": 47788 + }, + { + "epoch": 14.76, + "learning_rate": 3.390787494119926e-06, + "loss": 0.0031, + "step": 47789 + }, + { + "epoch": 14.76, + "learning_rate": 3.3904121860318905e-06, + "loss": 0.004, + "step": 47790 + }, + { + "epoch": 14.76, + "learning_rate": 3.3900368944756445e-06, + "loss": 0.0041, + "step": 47791 + }, + { + "epoch": 14.76, + "learning_rate": 3.389661619452117e-06, + "loss": 0.0039, + "step": 47792 + }, + { + "epoch": 14.76, + "learning_rate": 3.389286360962256e-06, + "loss": 0.0051, + "step": 47793 + }, + { + "epoch": 14.76, + "learning_rate": 3.3889111190069957e-06, + "loss": 0.0042, + "step": 47794 + }, + { + "epoch": 14.76, + "learning_rate": 3.3885358935872703e-06, + "loss": 0.004, + "step": 47795 + }, + { + "epoch": 14.76, + "learning_rate": 3.3881606847040226e-06, + "loss": 0.0036, + "step": 47796 + }, + { + "epoch": 14.76, + "learning_rate": 3.3877854923581944e-06, + "loss": 0.0027, + "step": 47797 + }, + { + "epoch": 14.76, + "learning_rate": 3.387410316550721e-06, + "loss": 0.0043, + "step": 47798 + }, + { + "epoch": 14.76, + "learning_rate": 3.3870351572825366e-06, + "loss": 0.004, + "step": 47799 + }, + { + "epoch": 14.76, + "learning_rate": 3.3866600145545835e-06, + "loss": 0.0041, + "step": 47800 + }, + { + "epoch": 14.76, + "learning_rate": 3.3862848883678036e-06, + "loss": 0.003, + "step": 47801 + }, + { + "epoch": 14.76, + "learning_rate": 3.385909778723128e-06, + "loss": 0.0042, + "step": 47802 + }, + { + "epoch": 14.76, + "learning_rate": 3.385534685621502e-06, + "loss": 0.0037, + "step": 47803 + }, + { + "epoch": 14.76, + "learning_rate": 3.3851596090638596e-06, + "loss": 0.0029, + "step": 47804 + }, + { + "epoch": 14.76, + "learning_rate": 3.3847845490511366e-06, + "loss": 0.0037, + "step": 47805 + }, + { + "epoch": 14.76, + "learning_rate": 3.384409505584273e-06, + "loss": 0.0047, + "step": 47806 + }, + { + "epoch": 14.76, + "learning_rate": 3.384034478664212e-06, + "loss": 0.0047, + "step": 47807 + }, + { + "epoch": 14.76, + "learning_rate": 3.383659468291888e-06, + "loss": 0.0034, + "step": 47808 + }, + { + "epoch": 14.76, + "learning_rate": 3.3832844744682335e-06, + "loss": 0.0036, + "step": 47809 + }, + { + "epoch": 14.76, + "learning_rate": 3.3829094971941957e-06, + "loss": 0.0037, + "step": 47810 + }, + { + "epoch": 14.76, + "learning_rate": 3.3825345364707052e-06, + "loss": 0.0042, + "step": 47811 + }, + { + "epoch": 14.77, + "learning_rate": 3.3821595922987015e-06, + "loss": 0.0036, + "step": 47812 + }, + { + "epoch": 14.77, + "learning_rate": 3.3817846646791284e-06, + "loss": 0.0038, + "step": 47813 + }, + { + "epoch": 14.77, + "learning_rate": 3.3814097536129186e-06, + "loss": 0.0043, + "step": 47814 + }, + { + "epoch": 14.77, + "learning_rate": 3.381034859101007e-06, + "loss": 0.0035, + "step": 47815 + }, + { + "epoch": 14.77, + "learning_rate": 3.380659981144336e-06, + "loss": 0.0038, + "step": 47816 + }, + { + "epoch": 14.77, + "learning_rate": 3.38028511974384e-06, + "loss": 0.0041, + "step": 47817 + }, + { + "epoch": 14.77, + "learning_rate": 3.379910274900462e-06, + "loss": 0.0038, + "step": 47818 + }, + { + "epoch": 14.77, + "learning_rate": 3.3795354466151344e-06, + "loss": 0.0038, + "step": 47819 + }, + { + "epoch": 14.77, + "learning_rate": 3.379160634888794e-06, + "loss": 0.0046, + "step": 47820 + }, + { + "epoch": 14.77, + "learning_rate": 3.3787858397223795e-06, + "loss": 0.0043, + "step": 47821 + }, + { + "epoch": 14.77, + "learning_rate": 3.378411061116833e-06, + "loss": 0.0035, + "step": 47822 + }, + { + "epoch": 14.77, + "learning_rate": 3.378036299073085e-06, + "loss": 0.0045, + "step": 47823 + }, + { + "epoch": 14.77, + "learning_rate": 3.3776615535920786e-06, + "loss": 0.0041, + "step": 47824 + }, + { + "epoch": 14.77, + "learning_rate": 3.3772868246747493e-06, + "loss": 0.0046, + "step": 47825 + }, + { + "epoch": 14.77, + "learning_rate": 3.3769121123220306e-06, + "loss": 0.0039, + "step": 47826 + }, + { + "epoch": 14.77, + "learning_rate": 3.376537416534862e-06, + "loss": 0.0035, + "step": 47827 + }, + { + "epoch": 14.77, + "learning_rate": 3.3761627373141846e-06, + "loss": 0.0043, + "step": 47828 + }, + { + "epoch": 14.77, + "learning_rate": 3.3757880746609327e-06, + "loss": 0.0036, + "step": 47829 + }, + { + "epoch": 14.77, + "learning_rate": 3.3754134285760386e-06, + "loss": 0.0037, + "step": 47830 + }, + { + "epoch": 14.77, + "learning_rate": 3.375038799060445e-06, + "loss": 0.0043, + "step": 47831 + }, + { + "epoch": 14.77, + "learning_rate": 3.374664186115091e-06, + "loss": 0.0036, + "step": 47832 + }, + { + "epoch": 14.77, + "learning_rate": 3.3742895897409068e-06, + "loss": 0.0032, + "step": 47833 + }, + { + "epoch": 14.77, + "learning_rate": 3.373915009938835e-06, + "loss": 0.003, + "step": 47834 + }, + { + "epoch": 14.77, + "learning_rate": 3.373540446709811e-06, + "loss": 0.0036, + "step": 47835 + }, + { + "epoch": 14.77, + "learning_rate": 3.373165900054768e-06, + "loss": 0.0036, + "step": 47836 + }, + { + "epoch": 14.77, + "learning_rate": 3.372791369974646e-06, + "loss": 0.0047, + "step": 47837 + }, + { + "epoch": 14.77, + "learning_rate": 3.372416856470384e-06, + "loss": 0.0042, + "step": 47838 + }, + { + "epoch": 14.77, + "learning_rate": 3.3720423595429165e-06, + "loss": 0.004, + "step": 47839 + }, + { + "epoch": 14.77, + "learning_rate": 3.3716678791931768e-06, + "loss": 0.0036, + "step": 47840 + }, + { + "epoch": 14.77, + "learning_rate": 3.3712934154221076e-06, + "loss": 0.0042, + "step": 47841 + }, + { + "epoch": 14.77, + "learning_rate": 3.37091896823064e-06, + "loss": 0.0032, + "step": 47842 + }, + { + "epoch": 14.77, + "learning_rate": 3.370544537619712e-06, + "loss": 0.0037, + "step": 47843 + }, + { + "epoch": 14.78, + "learning_rate": 3.370170123590265e-06, + "loss": 0.004, + "step": 47844 + }, + { + "epoch": 14.78, + "learning_rate": 3.3697957261432323e-06, + "loss": 0.0036, + "step": 47845 + }, + { + "epoch": 14.78, + "learning_rate": 3.3694213452795464e-06, + "loss": 0.0028, + "step": 47846 + }, + { + "epoch": 14.78, + "learning_rate": 3.3690469810001503e-06, + "loss": 0.0035, + "step": 47847 + }, + { + "epoch": 14.78, + "learning_rate": 3.3686726333059726e-06, + "loss": 0.0026, + "step": 47848 + }, + { + "epoch": 14.78, + "learning_rate": 3.3682983021979588e-06, + "loss": 0.0043, + "step": 47849 + }, + { + "epoch": 14.78, + "learning_rate": 3.3679239876770396e-06, + "loss": 0.0039, + "step": 47850 + }, + { + "epoch": 14.78, + "learning_rate": 3.3675496897441495e-06, + "loss": 0.0039, + "step": 47851 + }, + { + "epoch": 14.78, + "learning_rate": 3.367175408400227e-06, + "loss": 0.0048, + "step": 47852 + }, + { + "epoch": 14.78, + "learning_rate": 3.366801143646212e-06, + "loss": 0.0037, + "step": 47853 + }, + { + "epoch": 14.78, + "learning_rate": 3.3664268954830336e-06, + "loss": 0.0051, + "step": 47854 + }, + { + "epoch": 14.78, + "learning_rate": 3.3660526639116355e-06, + "loss": 0.0062, + "step": 47855 + }, + { + "epoch": 14.78, + "learning_rate": 3.3656784489329488e-06, + "loss": 0.0027, + "step": 47856 + }, + { + "epoch": 14.78, + "learning_rate": 3.3653042505479072e-06, + "loss": 0.0045, + "step": 47857 + }, + { + "epoch": 14.78, + "learning_rate": 3.3649300687574503e-06, + "loss": 0.004, + "step": 47858 + }, + { + "epoch": 14.78, + "learning_rate": 3.3645559035625164e-06, + "loss": 0.0045, + "step": 47859 + }, + { + "epoch": 14.78, + "learning_rate": 3.364181754964038e-06, + "loss": 0.0055, + "step": 47860 + }, + { + "epoch": 14.78, + "learning_rate": 3.363807622962949e-06, + "loss": 0.003, + "step": 47861 + }, + { + "epoch": 14.78, + "learning_rate": 3.3634335075601865e-06, + "loss": 0.0029, + "step": 47862 + }, + { + "epoch": 14.78, + "learning_rate": 3.3630594087566903e-06, + "loss": 0.0037, + "step": 47863 + }, + { + "epoch": 14.78, + "learning_rate": 3.362685326553391e-06, + "loss": 0.0041, + "step": 47864 + }, + { + "epoch": 14.78, + "learning_rate": 3.3623112609512288e-06, + "loss": 0.004, + "step": 47865 + }, + { + "epoch": 14.78, + "learning_rate": 3.361937211951136e-06, + "loss": 0.0041, + "step": 47866 + }, + { + "epoch": 14.78, + "learning_rate": 3.3615631795540473e-06, + "loss": 0.003, + "step": 47867 + }, + { + "epoch": 14.78, + "learning_rate": 3.3611891637608985e-06, + "loss": 0.0041, + "step": 47868 + }, + { + "epoch": 14.78, + "learning_rate": 3.3608151645726307e-06, + "loss": 0.0033, + "step": 47869 + }, + { + "epoch": 14.78, + "learning_rate": 3.360441181990175e-06, + "loss": 0.0032, + "step": 47870 + }, + { + "epoch": 14.78, + "learning_rate": 3.360067216014463e-06, + "loss": 0.0041, + "step": 47871 + }, + { + "epoch": 14.78, + "learning_rate": 3.359693266646438e-06, + "loss": 0.0059, + "step": 47872 + }, + { + "epoch": 14.78, + "learning_rate": 3.3593193338870268e-06, + "loss": 0.0025, + "step": 47873 + }, + { + "epoch": 14.78, + "learning_rate": 3.3589454177371707e-06, + "loss": 0.0045, + "step": 47874 + }, + { + "epoch": 14.78, + "learning_rate": 3.3585715181978086e-06, + "loss": 0.0036, + "step": 47875 + }, + { + "epoch": 14.78, + "learning_rate": 3.358197635269864e-06, + "loss": 0.0042, + "step": 47876 + }, + { + "epoch": 14.79, + "learning_rate": 3.3578237689542793e-06, + "loss": 0.0037, + "step": 47877 + }, + { + "epoch": 14.79, + "learning_rate": 3.3574499192519916e-06, + "loss": 0.0032, + "step": 47878 + }, + { + "epoch": 14.79, + "learning_rate": 3.3570760861639295e-06, + "loss": 0.0037, + "step": 47879 + }, + { + "epoch": 14.79, + "learning_rate": 3.356702269691036e-06, + "loss": 0.0035, + "step": 47880 + }, + { + "epoch": 14.79, + "learning_rate": 3.3563284698342404e-06, + "loss": 0.0041, + "step": 47881 + }, + { + "epoch": 14.79, + "learning_rate": 3.355954686594477e-06, + "loss": 0.0031, + "step": 47882 + }, + { + "epoch": 14.79, + "learning_rate": 3.355580919972682e-06, + "loss": 0.0032, + "step": 47883 + }, + { + "epoch": 14.79, + "learning_rate": 3.355207169969794e-06, + "loss": 0.0043, + "step": 47884 + }, + { + "epoch": 14.79, + "learning_rate": 3.3548334365867463e-06, + "loss": 0.0037, + "step": 47885 + }, + { + "epoch": 14.79, + "learning_rate": 3.354459719824468e-06, + "loss": 0.0041, + "step": 47886 + }, + { + "epoch": 14.79, + "learning_rate": 3.3540860196839008e-06, + "loss": 0.0036, + "step": 47887 + }, + { + "epoch": 14.79, + "learning_rate": 3.353712336165974e-06, + "loss": 0.0045, + "step": 47888 + }, + { + "epoch": 14.79, + "learning_rate": 3.353338669271624e-06, + "loss": 0.0042, + "step": 47889 + }, + { + "epoch": 14.79, + "learning_rate": 3.3529650190017904e-06, + "loss": 0.0034, + "step": 47890 + }, + { + "epoch": 14.79, + "learning_rate": 3.3525913853574033e-06, + "loss": 0.0047, + "step": 47891 + }, + { + "epoch": 14.79, + "learning_rate": 3.352217768339394e-06, + "loss": 0.0036, + "step": 47892 + }, + { + "epoch": 14.79, + "learning_rate": 3.3518441679487045e-06, + "loss": 0.0042, + "step": 47893 + }, + { + "epoch": 14.79, + "learning_rate": 3.3514705841862617e-06, + "loss": 0.0035, + "step": 47894 + }, + { + "epoch": 14.79, + "learning_rate": 3.351097017053003e-06, + "loss": 0.0039, + "step": 47895 + }, + { + "epoch": 14.79, + "learning_rate": 3.3507234665498677e-06, + "loss": 0.0033, + "step": 47896 + }, + { + "epoch": 14.79, + "learning_rate": 3.3503499326777854e-06, + "loss": 0.004, + "step": 47897 + }, + { + "epoch": 14.79, + "learning_rate": 3.349976415437688e-06, + "loss": 0.0035, + "step": 47898 + }, + { + "epoch": 14.79, + "learning_rate": 3.349602914830511e-06, + "loss": 0.0032, + "step": 47899 + }, + { + "epoch": 14.79, + "learning_rate": 3.3492294308571947e-06, + "loss": 0.0033, + "step": 47900 + }, + { + "epoch": 14.79, + "learning_rate": 3.3488559635186678e-06, + "loss": 0.0036, + "step": 47901 + }, + { + "epoch": 14.79, + "learning_rate": 3.3484825128158616e-06, + "loss": 0.0029, + "step": 47902 + }, + { + "epoch": 14.79, + "learning_rate": 3.3481090787497185e-06, + "loss": 0.0052, + "step": 47903 + }, + { + "epoch": 14.79, + "learning_rate": 3.347735661321163e-06, + "loss": 0.0041, + "step": 47904 + }, + { + "epoch": 14.79, + "learning_rate": 3.347362260531135e-06, + "loss": 0.0041, + "step": 47905 + }, + { + "epoch": 14.79, + "learning_rate": 3.3469888763805734e-06, + "loss": 0.0044, + "step": 47906 + }, + { + "epoch": 14.79, + "learning_rate": 3.3466155088704e-06, + "loss": 0.0045, + "step": 47907 + }, + { + "epoch": 14.79, + "learning_rate": 3.3462421580015535e-06, + "loss": 0.0044, + "step": 47908 + }, + { + "epoch": 14.8, + "learning_rate": 3.345868823774974e-06, + "loss": 0.0046, + "step": 47909 + }, + { + "epoch": 14.8, + "learning_rate": 3.345495506191586e-06, + "loss": 0.005, + "step": 47910 + }, + { + "epoch": 14.8, + "learning_rate": 3.34512220525233e-06, + "loss": 0.0039, + "step": 47911 + }, + { + "epoch": 14.8, + "learning_rate": 3.3447489209581386e-06, + "loss": 0.0056, + "step": 47912 + }, + { + "epoch": 14.8, + "learning_rate": 3.3443756533099393e-06, + "loss": 0.0032, + "step": 47913 + }, + { + "epoch": 14.8, + "learning_rate": 3.3440024023086716e-06, + "loss": 0.0034, + "step": 47914 + }, + { + "epoch": 14.8, + "learning_rate": 3.3436291679552703e-06, + "loss": 0.0036, + "step": 47915 + }, + { + "epoch": 14.8, + "learning_rate": 3.3432559502506666e-06, + "loss": 0.0039, + "step": 47916 + }, + { + "epoch": 14.8, + "learning_rate": 3.3428827491957915e-06, + "loss": 0.0036, + "step": 47917 + }, + { + "epoch": 14.8, + "learning_rate": 3.342509564791583e-06, + "loss": 0.0033, + "step": 47918 + }, + { + "epoch": 14.8, + "learning_rate": 3.34213639703897e-06, + "loss": 0.0035, + "step": 47919 + }, + { + "epoch": 14.8, + "learning_rate": 3.341763245938887e-06, + "loss": 0.0036, + "step": 47920 + }, + { + "epoch": 14.8, + "learning_rate": 3.3413901114922732e-06, + "loss": 0.0038, + "step": 47921 + }, + { + "epoch": 14.8, + "learning_rate": 3.3410169937000558e-06, + "loss": 0.0029, + "step": 47922 + }, + { + "epoch": 14.8, + "learning_rate": 3.3406438925631666e-06, + "loss": 0.0042, + "step": 47923 + }, + { + "epoch": 14.8, + "learning_rate": 3.340270808082545e-06, + "loss": 0.0042, + "step": 47924 + }, + { + "epoch": 14.8, + "learning_rate": 3.3398977402591182e-06, + "loss": 0.0034, + "step": 47925 + }, + { + "epoch": 14.8, + "learning_rate": 3.3395246890938238e-06, + "loss": 0.0034, + "step": 47926 + }, + { + "epoch": 14.8, + "learning_rate": 3.3391516545875934e-06, + "loss": 0.0032, + "step": 47927 + }, + { + "epoch": 14.8, + "learning_rate": 3.3387786367413577e-06, + "loss": 0.0026, + "step": 47928 + }, + { + "epoch": 14.8, + "learning_rate": 3.3384056355560503e-06, + "loss": 0.0044, + "step": 47929 + }, + { + "epoch": 14.8, + "learning_rate": 3.3380326510326057e-06, + "loss": 0.0035, + "step": 47930 + }, + { + "epoch": 14.8, + "learning_rate": 3.337659683171959e-06, + "loss": 0.0043, + "step": 47931 + }, + { + "epoch": 14.8, + "learning_rate": 3.3372867319750413e-06, + "loss": 0.0041, + "step": 47932 + }, + { + "epoch": 14.8, + "learning_rate": 3.336913797442781e-06, + "loss": 0.0039, + "step": 47933 + }, + { + "epoch": 14.8, + "learning_rate": 3.336540879576118e-06, + "loss": 0.0053, + "step": 47934 + }, + { + "epoch": 14.8, + "learning_rate": 3.3361679783759793e-06, + "loss": 0.0024, + "step": 47935 + }, + { + "epoch": 14.8, + "learning_rate": 3.3357950938433015e-06, + "loss": 0.0038, + "step": 47936 + }, + { + "epoch": 14.8, + "learning_rate": 3.335422225979017e-06, + "loss": 0.0035, + "step": 47937 + }, + { + "epoch": 14.8, + "learning_rate": 3.335049374784053e-06, + "loss": 0.0033, + "step": 47938 + }, + { + "epoch": 14.8, + "learning_rate": 3.3346765402593463e-06, + "loss": 0.0039, + "step": 47939 + }, + { + "epoch": 14.8, + "learning_rate": 3.3343037224058327e-06, + "loss": 0.003, + "step": 47940 + }, + { + "epoch": 14.81, + "learning_rate": 3.3339309212244377e-06, + "loss": 0.0031, + "step": 47941 + }, + { + "epoch": 14.81, + "learning_rate": 3.3335581367161006e-06, + "loss": 0.0039, + "step": 47942 + }, + { + "epoch": 14.81, + "learning_rate": 3.3331853688817507e-06, + "loss": 0.0052, + "step": 47943 + }, + { + "epoch": 14.81, + "learning_rate": 3.3328126177223175e-06, + "loss": 0.0035, + "step": 47944 + }, + { + "epoch": 14.81, + "learning_rate": 3.332439883238735e-06, + "loss": 0.0031, + "step": 47945 + }, + { + "epoch": 14.81, + "learning_rate": 3.332067165431939e-06, + "loss": 0.0037, + "step": 47946 + }, + { + "epoch": 14.81, + "learning_rate": 3.3316944643028605e-06, + "loss": 0.004, + "step": 47947 + }, + { + "epoch": 14.81, + "learning_rate": 3.3313217798524265e-06, + "loss": 0.0031, + "step": 47948 + }, + { + "epoch": 14.81, + "learning_rate": 3.3309491120815773e-06, + "loss": 0.0034, + "step": 47949 + }, + { + "epoch": 14.81, + "learning_rate": 3.330576460991236e-06, + "loss": 0.0041, + "step": 47950 + }, + { + "epoch": 14.81, + "learning_rate": 3.33020382658234e-06, + "loss": 0.0042, + "step": 47951 + }, + { + "epoch": 14.81, + "learning_rate": 3.3298312088558247e-06, + "loss": 0.0041, + "step": 47952 + }, + { + "epoch": 14.81, + "learning_rate": 3.3294586078126167e-06, + "loss": 0.0037, + "step": 47953 + }, + { + "epoch": 14.81, + "learning_rate": 3.329086023453647e-06, + "loss": 0.0038, + "step": 47954 + }, + { + "epoch": 14.81, + "learning_rate": 3.328713455779853e-06, + "loss": 0.0032, + "step": 47955 + }, + { + "epoch": 14.81, + "learning_rate": 3.32834090479216e-06, + "loss": 0.0041, + "step": 47956 + }, + { + "epoch": 14.81, + "learning_rate": 3.3279683704915065e-06, + "loss": 0.0037, + "step": 47957 + }, + { + "epoch": 14.81, + "learning_rate": 3.327595852878822e-06, + "loss": 0.0027, + "step": 47958 + }, + { + "epoch": 14.81, + "learning_rate": 3.3272233519550324e-06, + "loss": 0.0036, + "step": 47959 + }, + { + "epoch": 14.81, + "learning_rate": 3.3268508677210754e-06, + "loss": 0.0038, + "step": 47960 + }, + { + "epoch": 14.81, + "learning_rate": 3.3264784001778806e-06, + "loss": 0.0027, + "step": 47961 + }, + { + "epoch": 14.81, + "learning_rate": 3.3261059493263848e-06, + "loss": 0.0032, + "step": 47962 + }, + { + "epoch": 14.81, + "learning_rate": 3.3257335151675142e-06, + "loss": 0.0032, + "step": 47963 + }, + { + "epoch": 14.81, + "learning_rate": 3.325361097702199e-06, + "loss": 0.004, + "step": 47964 + }, + { + "epoch": 14.81, + "learning_rate": 3.3249886969313763e-06, + "loss": 0.0045, + "step": 47965 + }, + { + "epoch": 14.81, + "learning_rate": 3.3246163128559693e-06, + "loss": 0.003, + "step": 47966 + }, + { + "epoch": 14.81, + "learning_rate": 3.3242439454769193e-06, + "loss": 0.0028, + "step": 47967 + }, + { + "epoch": 14.81, + "learning_rate": 3.3238715947951527e-06, + "loss": 0.0035, + "step": 47968 + }, + { + "epoch": 14.81, + "learning_rate": 3.323499260811598e-06, + "loss": 0.0042, + "step": 47969 + }, + { + "epoch": 14.81, + "learning_rate": 3.3231269435271887e-06, + "loss": 0.0039, + "step": 47970 + }, + { + "epoch": 14.81, + "learning_rate": 3.3227546429428605e-06, + "loss": 0.0036, + "step": 47971 + }, + { + "epoch": 14.81, + "learning_rate": 3.322382359059536e-06, + "loss": 0.004, + "step": 47972 + }, + { + "epoch": 14.81, + "learning_rate": 3.3220100918781563e-06, + "loss": 0.0053, + "step": 47973 + }, + { + "epoch": 14.82, + "learning_rate": 3.3216378413996463e-06, + "loss": 0.003, + "step": 47974 + }, + { + "epoch": 14.82, + "learning_rate": 3.321265607624935e-06, + "loss": 0.0044, + "step": 47975 + }, + { + "epoch": 14.82, + "learning_rate": 3.3208933905549567e-06, + "loss": 0.0033, + "step": 47976 + }, + { + "epoch": 14.82, + "learning_rate": 3.3205211901906453e-06, + "loss": 0.0029, + "step": 47977 + }, + { + "epoch": 14.82, + "learning_rate": 3.320149006532929e-06, + "loss": 0.0037, + "step": 47978 + }, + { + "epoch": 14.82, + "learning_rate": 3.3197768395827344e-06, + "loss": 0.0066, + "step": 47979 + }, + { + "epoch": 14.82, + "learning_rate": 3.3194046893410005e-06, + "loss": 0.0051, + "step": 47980 + }, + { + "epoch": 14.82, + "learning_rate": 3.31903255580865e-06, + "loss": 0.0036, + "step": 47981 + }, + { + "epoch": 14.82, + "learning_rate": 3.3186604389866184e-06, + "loss": 0.0039, + "step": 47982 + }, + { + "epoch": 14.82, + "learning_rate": 3.318288338875838e-06, + "loss": 0.0035, + "step": 47983 + }, + { + "epoch": 14.82, + "learning_rate": 3.3179162554772372e-06, + "loss": 0.005, + "step": 47984 + }, + { + "epoch": 14.82, + "learning_rate": 3.3175441887917435e-06, + "loss": 0.004, + "step": 47985 + }, + { + "epoch": 14.82, + "learning_rate": 3.3171721388202948e-06, + "loss": 0.0037, + "step": 47986 + }, + { + "epoch": 14.82, + "learning_rate": 3.316800105563813e-06, + "loss": 0.0044, + "step": 47987 + }, + { + "epoch": 14.82, + "learning_rate": 3.316428089023237e-06, + "loss": 0.0042, + "step": 47988 + }, + { + "epoch": 14.82, + "learning_rate": 3.316056089199493e-06, + "loss": 0.0031, + "step": 47989 + }, + { + "epoch": 14.82, + "learning_rate": 3.3156841060935086e-06, + "loss": 0.0028, + "step": 47990 + }, + { + "epoch": 14.82, + "learning_rate": 3.315312139706217e-06, + "loss": 0.0035, + "step": 47991 + }, + { + "epoch": 14.82, + "learning_rate": 3.3149401900385524e-06, + "loss": 0.0035, + "step": 47992 + }, + { + "epoch": 14.82, + "learning_rate": 3.3145682570914384e-06, + "loss": 0.0043, + "step": 47993 + }, + { + "epoch": 14.82, + "learning_rate": 3.3141963408658128e-06, + "loss": 0.0038, + "step": 47994 + }, + { + "epoch": 14.82, + "learning_rate": 3.3138244413625974e-06, + "loss": 0.004, + "step": 47995 + }, + { + "epoch": 14.82, + "learning_rate": 3.313452558582729e-06, + "loss": 0.0056, + "step": 47996 + }, + { + "epoch": 14.82, + "learning_rate": 3.313080692527134e-06, + "loss": 0.0036, + "step": 47997 + }, + { + "epoch": 14.82, + "learning_rate": 3.312708843196746e-06, + "loss": 0.0036, + "step": 47998 + }, + { + "epoch": 14.82, + "learning_rate": 3.312337010592492e-06, + "loss": 0.0046, + "step": 47999 + }, + { + "epoch": 14.82, + "learning_rate": 3.311965194715301e-06, + "loss": 0.0032, + "step": 48000 + }, + { + "epoch": 14.82, + "learning_rate": 3.311593395566104e-06, + "loss": 0.0034, + "step": 48001 + }, + { + "epoch": 14.82, + "learning_rate": 3.3112216131458363e-06, + "loss": 0.0036, + "step": 48002 + }, + { + "epoch": 14.82, + "learning_rate": 3.3108498474554185e-06, + "loss": 0.0035, + "step": 48003 + }, + { + "epoch": 14.82, + "learning_rate": 3.3104780984957894e-06, + "loss": 0.0039, + "step": 48004 + }, + { + "epoch": 14.82, + "learning_rate": 3.3101063662678745e-06, + "loss": 0.0041, + "step": 48005 + }, + { + "epoch": 14.83, + "learning_rate": 3.3097346507726003e-06, + "loss": 0.0053, + "step": 48006 + }, + { + "epoch": 14.83, + "learning_rate": 3.3093629520109004e-06, + "loss": 0.0035, + "step": 48007 + }, + { + "epoch": 14.83, + "learning_rate": 3.3089912699837068e-06, + "loss": 0.0036, + "step": 48008 + }, + { + "epoch": 14.83, + "learning_rate": 3.308619604691947e-06, + "loss": 0.0043, + "step": 48009 + }, + { + "epoch": 14.83, + "learning_rate": 3.3082479561365466e-06, + "loss": 0.0036, + "step": 48010 + }, + { + "epoch": 14.83, + "learning_rate": 3.307876324318441e-06, + "loss": 0.0035, + "step": 48011 + }, + { + "epoch": 14.83, + "learning_rate": 3.3075047092385547e-06, + "loss": 0.0028, + "step": 48012 + }, + { + "epoch": 14.83, + "learning_rate": 3.30713311089782e-06, + "loss": 0.0043, + "step": 48013 + }, + { + "epoch": 14.83, + "learning_rate": 3.306761529297172e-06, + "loss": 0.0037, + "step": 48014 + }, + { + "epoch": 14.83, + "learning_rate": 3.3063899644375288e-06, + "loss": 0.0031, + "step": 48015 + }, + { + "epoch": 14.83, + "learning_rate": 3.306018416319824e-06, + "loss": 0.0033, + "step": 48016 + }, + { + "epoch": 14.83, + "learning_rate": 3.3056468849449906e-06, + "loss": 0.0031, + "step": 48017 + }, + { + "epoch": 14.83, + "learning_rate": 3.3052753703139538e-06, + "loss": 0.0034, + "step": 48018 + }, + { + "epoch": 14.83, + "learning_rate": 3.304903872427647e-06, + "loss": 0.0049, + "step": 48019 + }, + { + "epoch": 14.83, + "learning_rate": 3.3045323912869965e-06, + "loss": 0.003, + "step": 48020 + }, + { + "epoch": 14.83, + "learning_rate": 3.3041609268929286e-06, + "loss": 0.0036, + "step": 48021 + }, + { + "epoch": 14.83, + "learning_rate": 3.3037894792463753e-06, + "loss": 0.0029, + "step": 48022 + }, + { + "epoch": 14.83, + "learning_rate": 3.3034180483482693e-06, + "loss": 0.0032, + "step": 48023 + }, + { + "epoch": 14.83, + "learning_rate": 3.303046634199536e-06, + "loss": 0.0043, + "step": 48024 + }, + { + "epoch": 14.83, + "learning_rate": 3.3026752368011006e-06, + "loss": 0.004, + "step": 48025 + }, + { + "epoch": 14.83, + "learning_rate": 3.3023038561538967e-06, + "loss": 0.004, + "step": 48026 + }, + { + "epoch": 14.83, + "learning_rate": 3.3019324922588556e-06, + "loss": 0.0041, + "step": 48027 + }, + { + "epoch": 14.83, + "learning_rate": 3.3015611451168993e-06, + "loss": 0.004, + "step": 48028 + }, + { + "epoch": 14.83, + "learning_rate": 3.3011898147289645e-06, + "loss": 0.0037, + "step": 48029 + }, + { + "epoch": 14.83, + "learning_rate": 3.3008185010959747e-06, + "loss": 0.0032, + "step": 48030 + }, + { + "epoch": 14.83, + "learning_rate": 3.300447204218857e-06, + "loss": 0.0047, + "step": 48031 + }, + { + "epoch": 14.83, + "learning_rate": 3.3000759240985437e-06, + "loss": 0.004, + "step": 48032 + }, + { + "epoch": 14.83, + "learning_rate": 3.299704660735964e-06, + "loss": 0.0028, + "step": 48033 + }, + { + "epoch": 14.83, + "learning_rate": 3.2993334141320467e-06, + "loss": 0.0034, + "step": 48034 + }, + { + "epoch": 14.83, + "learning_rate": 3.298962184287714e-06, + "loss": 0.0039, + "step": 48035 + }, + { + "epoch": 14.83, + "learning_rate": 3.298590971203902e-06, + "loss": 0.0038, + "step": 48036 + }, + { + "epoch": 14.83, + "learning_rate": 3.2982197748815347e-06, + "loss": 0.0046, + "step": 48037 + }, + { + "epoch": 14.84, + "learning_rate": 3.297848595321541e-06, + "loss": 0.0038, + "step": 48038 + }, + { + "epoch": 14.84, + "learning_rate": 3.297477432524854e-06, + "loss": 0.0034, + "step": 48039 + }, + { + "epoch": 14.84, + "learning_rate": 3.2971062864923975e-06, + "loss": 0.0037, + "step": 48040 + }, + { + "epoch": 14.84, + "learning_rate": 3.2967351572250982e-06, + "loss": 0.0033, + "step": 48041 + }, + { + "epoch": 14.84, + "learning_rate": 3.29636404472389e-06, + "loss": 0.0037, + "step": 48042 + }, + { + "epoch": 14.84, + "learning_rate": 3.2959929489896946e-06, + "loss": 0.0033, + "step": 48043 + }, + { + "epoch": 14.84, + "learning_rate": 3.2956218700234478e-06, + "loss": 0.0025, + "step": 48044 + }, + { + "epoch": 14.84, + "learning_rate": 3.2952508078260727e-06, + "loss": 0.0038, + "step": 48045 + }, + { + "epoch": 14.84, + "learning_rate": 3.294879762398495e-06, + "loss": 0.0036, + "step": 48046 + }, + { + "epoch": 14.84, + "learning_rate": 3.2945087337416457e-06, + "loss": 0.0053, + "step": 48047 + }, + { + "epoch": 14.84, + "learning_rate": 3.2941377218564565e-06, + "loss": 0.0048, + "step": 48048 + }, + { + "epoch": 14.84, + "learning_rate": 3.293766726743849e-06, + "loss": 0.0032, + "step": 48049 + }, + { + "epoch": 14.84, + "learning_rate": 3.2933957484047563e-06, + "loss": 0.0029, + "step": 48050 + }, + { + "epoch": 14.84, + "learning_rate": 3.2930247868401055e-06, + "loss": 0.0033, + "step": 48051 + }, + { + "epoch": 14.84, + "learning_rate": 3.2926538420508193e-06, + "loss": 0.0041, + "step": 48052 + }, + { + "epoch": 14.84, + "learning_rate": 3.2922829140378288e-06, + "loss": 0.0038, + "step": 48053 + }, + { + "epoch": 14.84, + "learning_rate": 3.2919120028020647e-06, + "loss": 0.0035, + "step": 48054 + }, + { + "epoch": 14.84, + "learning_rate": 3.2915411083444538e-06, + "loss": 0.0045, + "step": 48055 + }, + { + "epoch": 14.84, + "learning_rate": 3.2911702306659175e-06, + "loss": 0.0039, + "step": 48056 + }, + { + "epoch": 14.84, + "learning_rate": 3.2907993697673924e-06, + "loss": 0.0043, + "step": 48057 + }, + { + "epoch": 14.84, + "learning_rate": 3.290428525649797e-06, + "loss": 0.0044, + "step": 48058 + }, + { + "epoch": 14.84, + "learning_rate": 3.290057698314065e-06, + "loss": 0.0041, + "step": 48059 + }, + { + "epoch": 14.84, + "learning_rate": 3.2896868877611256e-06, + "loss": 0.0045, + "step": 48060 + }, + { + "epoch": 14.84, + "learning_rate": 3.289316093991902e-06, + "loss": 0.0041, + "step": 48061 + }, + { + "epoch": 14.84, + "learning_rate": 3.2889453170073217e-06, + "loss": 0.0027, + "step": 48062 + }, + { + "epoch": 14.84, + "learning_rate": 3.2885745568083114e-06, + "loss": 0.0037, + "step": 48063 + }, + { + "epoch": 14.84, + "learning_rate": 3.288203813395804e-06, + "loss": 0.0044, + "step": 48064 + }, + { + "epoch": 14.84, + "learning_rate": 3.287833086770723e-06, + "loss": 0.0037, + "step": 48065 + }, + { + "epoch": 14.84, + "learning_rate": 3.287462376933992e-06, + "loss": 0.003, + "step": 48066 + }, + { + "epoch": 14.84, + "learning_rate": 3.2870916838865465e-06, + "loss": 0.0037, + "step": 48067 + }, + { + "epoch": 14.84, + "learning_rate": 3.2867210076293043e-06, + "loss": 0.0043, + "step": 48068 + }, + { + "epoch": 14.84, + "learning_rate": 3.2863503481631977e-06, + "loss": 0.0042, + "step": 48069 + }, + { + "epoch": 14.84, + "learning_rate": 3.2859797054891572e-06, + "loss": 0.0038, + "step": 48070 + }, + { + "epoch": 14.85, + "learning_rate": 3.2856090796081052e-06, + "loss": 0.0038, + "step": 48071 + }, + { + "epoch": 14.85, + "learning_rate": 3.285238470520967e-06, + "loss": 0.0034, + "step": 48072 + }, + { + "epoch": 14.85, + "learning_rate": 3.2848678782286746e-06, + "loss": 0.0032, + "step": 48073 + }, + { + "epoch": 14.85, + "learning_rate": 3.28449730273215e-06, + "loss": 0.0039, + "step": 48074 + }, + { + "epoch": 14.85, + "learning_rate": 3.2841267440323254e-06, + "loss": 0.0044, + "step": 48075 + }, + { + "epoch": 14.85, + "learning_rate": 3.283756202130124e-06, + "loss": 0.0029, + "step": 48076 + }, + { + "epoch": 14.85, + "learning_rate": 3.2833856770264717e-06, + "loss": 0.0042, + "step": 48077 + }, + { + "epoch": 14.85, + "learning_rate": 3.2830151687222956e-06, + "loss": 0.0035, + "step": 48078 + }, + { + "epoch": 14.85, + "learning_rate": 3.282644677218527e-06, + "loss": 0.0058, + "step": 48079 + }, + { + "epoch": 14.85, + "learning_rate": 3.282274202516086e-06, + "loss": 0.0042, + "step": 48080 + }, + { + "epoch": 14.85, + "learning_rate": 3.281903744615905e-06, + "loss": 0.0042, + "step": 48081 + }, + { + "epoch": 14.85, + "learning_rate": 3.281533303518909e-06, + "loss": 0.0053, + "step": 48082 + }, + { + "epoch": 14.85, + "learning_rate": 3.2811628792260207e-06, + "loss": 0.0038, + "step": 48083 + }, + { + "epoch": 14.85, + "learning_rate": 3.2807924717381688e-06, + "loss": 0.0038, + "step": 48084 + }, + { + "epoch": 14.85, + "learning_rate": 3.2804220810562836e-06, + "loss": 0.0036, + "step": 48085 + }, + { + "epoch": 14.85, + "learning_rate": 3.2800517071812888e-06, + "loss": 0.0044, + "step": 48086 + }, + { + "epoch": 14.85, + "learning_rate": 3.279681350114107e-06, + "loss": 0.0036, + "step": 48087 + }, + { + "epoch": 14.85, + "learning_rate": 3.279311009855671e-06, + "loss": 0.0038, + "step": 48088 + }, + { + "epoch": 14.85, + "learning_rate": 3.2789406864069007e-06, + "loss": 0.0033, + "step": 48089 + }, + { + "epoch": 14.85, + "learning_rate": 3.2785703797687252e-06, + "loss": 0.0028, + "step": 48090 + }, + { + "epoch": 14.85, + "learning_rate": 3.278200089942075e-06, + "loss": 0.0037, + "step": 48091 + }, + { + "epoch": 14.85, + "learning_rate": 3.277829816927872e-06, + "loss": 0.0041, + "step": 48092 + }, + { + "epoch": 14.85, + "learning_rate": 3.27745956072704e-06, + "loss": 0.0042, + "step": 48093 + }, + { + "epoch": 14.85, + "learning_rate": 3.2770893213405064e-06, + "loss": 0.0034, + "step": 48094 + }, + { + "epoch": 14.85, + "learning_rate": 3.2767190987692033e-06, + "loss": 0.0048, + "step": 48095 + }, + { + "epoch": 14.85, + "learning_rate": 3.2763488930140507e-06, + "loss": 0.003, + "step": 48096 + }, + { + "epoch": 14.85, + "learning_rate": 3.2759787040759737e-06, + "loss": 0.0033, + "step": 48097 + }, + { + "epoch": 14.85, + "learning_rate": 3.2756085319559027e-06, + "loss": 0.0036, + "step": 48098 + }, + { + "epoch": 14.85, + "learning_rate": 3.275238376654759e-06, + "loss": 0.0037, + "step": 48099 + }, + { + "epoch": 14.85, + "learning_rate": 3.2748682381734698e-06, + "loss": 0.0041, + "step": 48100 + }, + { + "epoch": 14.85, + "learning_rate": 3.2744981165129654e-06, + "loss": 0.0038, + "step": 48101 + }, + { + "epoch": 14.85, + "learning_rate": 3.274128011674168e-06, + "loss": 0.004, + "step": 48102 + }, + { + "epoch": 14.86, + "learning_rate": 3.2737579236579996e-06, + "loss": 0.0043, + "step": 48103 + }, + { + "epoch": 14.86, + "learning_rate": 3.2733878524653915e-06, + "loss": 0.0037, + "step": 48104 + }, + { + "epoch": 14.86, + "learning_rate": 3.2730177980972655e-06, + "loss": 0.0039, + "step": 48105 + }, + { + "epoch": 14.86, + "learning_rate": 3.2726477605545527e-06, + "loss": 0.0039, + "step": 48106 + }, + { + "epoch": 14.86, + "learning_rate": 3.2722777398381732e-06, + "loss": 0.0037, + "step": 48107 + }, + { + "epoch": 14.86, + "learning_rate": 3.2719077359490515e-06, + "loss": 0.0049, + "step": 48108 + }, + { + "epoch": 14.86, + "learning_rate": 3.2715377488881162e-06, + "loss": 0.004, + "step": 48109 + }, + { + "epoch": 14.86, + "learning_rate": 3.2711677786562954e-06, + "loss": 0.0045, + "step": 48110 + }, + { + "epoch": 14.86, + "learning_rate": 3.270797825254507e-06, + "loss": 0.0031, + "step": 48111 + }, + { + "epoch": 14.86, + "learning_rate": 3.2704278886836848e-06, + "loss": 0.0027, + "step": 48112 + }, + { + "epoch": 14.86, + "learning_rate": 3.27005796894475e-06, + "loss": 0.0038, + "step": 48113 + }, + { + "epoch": 14.86, + "learning_rate": 3.2696880660386233e-06, + "loss": 0.0032, + "step": 48114 + }, + { + "epoch": 14.86, + "learning_rate": 3.2693181799662356e-06, + "loss": 0.0036, + "step": 48115 + }, + { + "epoch": 14.86, + "learning_rate": 3.2689483107285126e-06, + "loss": 0.003, + "step": 48116 + }, + { + "epoch": 14.86, + "learning_rate": 3.268578458326379e-06, + "loss": 0.0037, + "step": 48117 + }, + { + "epoch": 14.86, + "learning_rate": 3.2682086227607534e-06, + "loss": 0.0038, + "step": 48118 + }, + { + "epoch": 14.86, + "learning_rate": 3.2678388040325706e-06, + "loss": 0.0034, + "step": 48119 + }, + { + "epoch": 14.86, + "learning_rate": 3.2674690021427467e-06, + "loss": 0.0034, + "step": 48120 + }, + { + "epoch": 14.86, + "learning_rate": 3.267099217092211e-06, + "loss": 0.0043, + "step": 48121 + }, + { + "epoch": 14.86, + "learning_rate": 3.2667294488818956e-06, + "loss": 0.0037, + "step": 48122 + }, + { + "epoch": 14.86, + "learning_rate": 3.266359697512711e-06, + "loss": 0.0039, + "step": 48123 + }, + { + "epoch": 14.86, + "learning_rate": 3.2659899629855884e-06, + "loss": 0.0041, + "step": 48124 + }, + { + "epoch": 14.86, + "learning_rate": 3.265620245301453e-06, + "loss": 0.0038, + "step": 48125 + }, + { + "epoch": 14.86, + "learning_rate": 3.2652505444612324e-06, + "loss": 0.0037, + "step": 48126 + }, + { + "epoch": 14.86, + "learning_rate": 3.26488086046585e-06, + "loss": 0.0034, + "step": 48127 + }, + { + "epoch": 14.86, + "learning_rate": 3.2645111933162254e-06, + "loss": 0.0026, + "step": 48128 + }, + { + "epoch": 14.86, + "learning_rate": 3.2641415430132894e-06, + "loss": 0.0049, + "step": 48129 + }, + { + "epoch": 14.86, + "learning_rate": 3.263771909557961e-06, + "loss": 0.0038, + "step": 48130 + }, + { + "epoch": 14.86, + "learning_rate": 3.263402292951168e-06, + "loss": 0.0034, + "step": 48131 + }, + { + "epoch": 14.86, + "learning_rate": 3.2630326931938404e-06, + "loss": 0.0039, + "step": 48132 + }, + { + "epoch": 14.86, + "learning_rate": 3.26266311028689e-06, + "loss": 0.0032, + "step": 48133 + }, + { + "epoch": 14.86, + "learning_rate": 3.262293544231249e-06, + "loss": 0.0038, + "step": 48134 + }, + { + "epoch": 14.86, + "learning_rate": 3.2619239950278436e-06, + "loss": 0.0057, + "step": 48135 + }, + { + "epoch": 14.87, + "learning_rate": 3.261554462677592e-06, + "loss": 0.005, + "step": 48136 + }, + { + "epoch": 14.87, + "learning_rate": 3.261184947181424e-06, + "loss": 0.0043, + "step": 48137 + }, + { + "epoch": 14.87, + "learning_rate": 3.2608154485402633e-06, + "loss": 0.0024, + "step": 48138 + }, + { + "epoch": 14.87, + "learning_rate": 3.260445966755027e-06, + "loss": 0.0038, + "step": 48139 + }, + { + "epoch": 14.87, + "learning_rate": 3.2600765018266467e-06, + "loss": 0.0052, + "step": 48140 + }, + { + "epoch": 14.87, + "learning_rate": 3.259707053756046e-06, + "loss": 0.0039, + "step": 48141 + }, + { + "epoch": 14.87, + "learning_rate": 3.2593376225441477e-06, + "loss": 0.0046, + "step": 48142 + }, + { + "epoch": 14.87, + "learning_rate": 3.258968208191873e-06, + "loss": 0.0025, + "step": 48143 + }, + { + "epoch": 14.87, + "learning_rate": 3.258598810700151e-06, + "loss": 0.003, + "step": 48144 + }, + { + "epoch": 14.87, + "learning_rate": 3.258229430069899e-06, + "loss": 0.0039, + "step": 48145 + }, + { + "epoch": 14.87, + "learning_rate": 3.2578600663020455e-06, + "loss": 0.0038, + "step": 48146 + }, + { + "epoch": 14.87, + "learning_rate": 3.257490719397517e-06, + "loss": 0.0039, + "step": 48147 + }, + { + "epoch": 14.87, + "learning_rate": 3.257121389357234e-06, + "loss": 0.0039, + "step": 48148 + }, + { + "epoch": 14.87, + "learning_rate": 3.256752076182117e-06, + "loss": 0.0034, + "step": 48149 + }, + { + "epoch": 14.87, + "learning_rate": 3.256382779873095e-06, + "loss": 0.0031, + "step": 48150 + }, + { + "epoch": 14.87, + "learning_rate": 3.2560135004310878e-06, + "loss": 0.0033, + "step": 48151 + }, + { + "epoch": 14.87, + "learning_rate": 3.255644237857021e-06, + "loss": 0.0049, + "step": 48152 + }, + { + "epoch": 14.87, + "learning_rate": 3.2552749921518234e-06, + "loss": 0.0029, + "step": 48153 + }, + { + "epoch": 14.87, + "learning_rate": 3.2549057633164073e-06, + "loss": 0.0038, + "step": 48154 + }, + { + "epoch": 14.87, + "learning_rate": 3.2545365513517025e-06, + "loss": 0.0034, + "step": 48155 + }, + { + "epoch": 14.87, + "learning_rate": 3.254167356258634e-06, + "loss": 0.004, + "step": 48156 + }, + { + "epoch": 14.87, + "learning_rate": 3.253798178038121e-06, + "loss": 0.0044, + "step": 48157 + }, + { + "epoch": 14.87, + "learning_rate": 3.253429016691093e-06, + "loss": 0.004, + "step": 48158 + }, + { + "epoch": 14.87, + "learning_rate": 3.253059872218466e-06, + "loss": 0.0038, + "step": 48159 + }, + { + "epoch": 14.87, + "learning_rate": 3.2526907446211696e-06, + "loss": 0.0036, + "step": 48160 + }, + { + "epoch": 14.87, + "learning_rate": 3.2523216339001205e-06, + "loss": 0.0034, + "step": 48161 + }, + { + "epoch": 14.87, + "learning_rate": 3.251952540056247e-06, + "loss": 0.0039, + "step": 48162 + }, + { + "epoch": 14.87, + "learning_rate": 3.2515834630904764e-06, + "loss": 0.0042, + "step": 48163 + }, + { + "epoch": 14.87, + "learning_rate": 3.2512144030037207e-06, + "loss": 0.0032, + "step": 48164 + }, + { + "epoch": 14.87, + "learning_rate": 3.2508453597969083e-06, + "loss": 0.0033, + "step": 48165 + }, + { + "epoch": 14.87, + "learning_rate": 3.2504763334709656e-06, + "loss": 0.0039, + "step": 48166 + }, + { + "epoch": 14.87, + "learning_rate": 3.2501073240268098e-06, + "loss": 0.0034, + "step": 48167 + }, + { + "epoch": 14.88, + "learning_rate": 3.2497383314653694e-06, + "loss": 0.0027, + "step": 48168 + }, + { + "epoch": 14.88, + "learning_rate": 3.2493693557875662e-06, + "loss": 0.0032, + "step": 48169 + }, + { + "epoch": 14.88, + "learning_rate": 3.249000396994316e-06, + "loss": 0.0033, + "step": 48170 + }, + { + "epoch": 14.88, + "learning_rate": 3.248631455086548e-06, + "loss": 0.0042, + "step": 48171 + }, + { + "epoch": 14.88, + "learning_rate": 3.248262530065188e-06, + "loss": 0.0045, + "step": 48172 + }, + { + "epoch": 14.88, + "learning_rate": 3.2478936219311542e-06, + "loss": 0.0032, + "step": 48173 + }, + { + "epoch": 14.88, + "learning_rate": 3.2475247306853674e-06, + "loss": 0.0037, + "step": 48174 + }, + { + "epoch": 14.88, + "learning_rate": 3.2471558563287555e-06, + "loss": 0.0032, + "step": 48175 + }, + { + "epoch": 14.88, + "learning_rate": 3.2467869988622347e-06, + "loss": 0.0032, + "step": 48176 + }, + { + "epoch": 14.88, + "learning_rate": 3.2464181582867325e-06, + "loss": 0.0039, + "step": 48177 + }, + { + "epoch": 14.88, + "learning_rate": 3.246049334603173e-06, + "loss": 0.0036, + "step": 48178 + }, + { + "epoch": 14.88, + "learning_rate": 3.245680527812476e-06, + "loss": 0.0027, + "step": 48179 + }, + { + "epoch": 14.88, + "learning_rate": 3.24531173791556e-06, + "loss": 0.004, + "step": 48180 + }, + { + "epoch": 14.88, + "learning_rate": 3.2449429649133544e-06, + "loss": 0.0043, + "step": 48181 + }, + { + "epoch": 14.88, + "learning_rate": 3.2445742088067767e-06, + "loss": 0.0037, + "step": 48182 + }, + { + "epoch": 14.88, + "learning_rate": 3.244205469596753e-06, + "loss": 0.0037, + "step": 48183 + }, + { + "epoch": 14.88, + "learning_rate": 3.2438367472842047e-06, + "loss": 0.0034, + "step": 48184 + }, + { + "epoch": 14.88, + "learning_rate": 3.2434680418700493e-06, + "loss": 0.0036, + "step": 48185 + }, + { + "epoch": 14.88, + "learning_rate": 3.2430993533552113e-06, + "loss": 0.0042, + "step": 48186 + }, + { + "epoch": 14.88, + "learning_rate": 3.242730681740619e-06, + "loss": 0.0033, + "step": 48187 + }, + { + "epoch": 14.88, + "learning_rate": 3.242362027027186e-06, + "loss": 0.0042, + "step": 48188 + }, + { + "epoch": 14.88, + "learning_rate": 3.241993389215842e-06, + "loss": 0.0039, + "step": 48189 + }, + { + "epoch": 14.88, + "learning_rate": 3.241624768307501e-06, + "loss": 0.003, + "step": 48190 + }, + { + "epoch": 14.88, + "learning_rate": 3.2412561643030925e-06, + "loss": 0.0046, + "step": 48191 + }, + { + "epoch": 14.88, + "learning_rate": 3.240887577203532e-06, + "loss": 0.0056, + "step": 48192 + }, + { + "epoch": 14.88, + "learning_rate": 3.240519007009747e-06, + "loss": 0.0035, + "step": 48193 + }, + { + "epoch": 14.88, + "learning_rate": 3.240150453722658e-06, + "loss": 0.0037, + "step": 48194 + }, + { + "epoch": 14.88, + "learning_rate": 3.239781917343181e-06, + "loss": 0.0037, + "step": 48195 + }, + { + "epoch": 14.88, + "learning_rate": 3.239413397872244e-06, + "loss": 0.0027, + "step": 48196 + }, + { + "epoch": 14.88, + "learning_rate": 3.239044895310769e-06, + "loss": 0.0041, + "step": 48197 + }, + { + "epoch": 14.88, + "learning_rate": 3.2386764096596734e-06, + "loss": 0.0028, + "step": 48198 + }, + { + "epoch": 14.88, + "learning_rate": 3.238307940919885e-06, + "loss": 0.0028, + "step": 48199 + }, + { + "epoch": 14.89, + "learning_rate": 3.2379394890923198e-06, + "loss": 0.0028, + "step": 48200 + }, + { + "epoch": 14.89, + "learning_rate": 3.2375710541779006e-06, + "loss": 0.0039, + "step": 48201 + }, + { + "epoch": 14.89, + "learning_rate": 3.2372026361775478e-06, + "loss": 0.0034, + "step": 48202 + }, + { + "epoch": 14.89, + "learning_rate": 3.236834235092188e-06, + "loss": 0.0057, + "step": 48203 + }, + { + "epoch": 14.89, + "learning_rate": 3.2364658509227397e-06, + "loss": 0.0033, + "step": 48204 + }, + { + "epoch": 14.89, + "learning_rate": 3.236097483670121e-06, + "loss": 0.004, + "step": 48205 + }, + { + "epoch": 14.89, + "learning_rate": 3.235729133335258e-06, + "loss": 0.0034, + "step": 48206 + }, + { + "epoch": 14.89, + "learning_rate": 3.235360799919068e-06, + "loss": 0.0038, + "step": 48207 + }, + { + "epoch": 14.89, + "learning_rate": 3.2349924834224745e-06, + "loss": 0.0032, + "step": 48208 + }, + { + "epoch": 14.89, + "learning_rate": 3.234624183846402e-06, + "loss": 0.0048, + "step": 48209 + }, + { + "epoch": 14.89, + "learning_rate": 3.2342559011917684e-06, + "loss": 0.004, + "step": 48210 + }, + { + "epoch": 14.89, + "learning_rate": 3.2338876354594906e-06, + "loss": 0.0046, + "step": 48211 + }, + { + "epoch": 14.89, + "learning_rate": 3.233519386650498e-06, + "loss": 0.0036, + "step": 48212 + }, + { + "epoch": 14.89, + "learning_rate": 3.2331511547657045e-06, + "loss": 0.0033, + "step": 48213 + }, + { + "epoch": 14.89, + "learning_rate": 3.2327829398060364e-06, + "loss": 0.0039, + "step": 48214 + }, + { + "epoch": 14.89, + "learning_rate": 3.232414741772413e-06, + "loss": 0.0042, + "step": 48215 + }, + { + "epoch": 14.89, + "learning_rate": 3.2320465606657514e-06, + "loss": 0.0037, + "step": 48216 + }, + { + "epoch": 14.89, + "learning_rate": 3.2316783964869756e-06, + "loss": 0.0025, + "step": 48217 + }, + { + "epoch": 14.89, + "learning_rate": 3.231310249237011e-06, + "loss": 0.0041, + "step": 48218 + }, + { + "epoch": 14.89, + "learning_rate": 3.2309421189167687e-06, + "loss": 0.0038, + "step": 48219 + }, + { + "epoch": 14.89, + "learning_rate": 3.2305740055271794e-06, + "loss": 0.0053, + "step": 48220 + }, + { + "epoch": 14.89, + "learning_rate": 3.2302059090691583e-06, + "loss": 0.0045, + "step": 48221 + }, + { + "epoch": 14.89, + "learning_rate": 3.229837829543625e-06, + "loss": 0.0028, + "step": 48222 + }, + { + "epoch": 14.89, + "learning_rate": 3.229469766951501e-06, + "loss": 0.0029, + "step": 48223 + }, + { + "epoch": 14.89, + "learning_rate": 3.2291017212937116e-06, + "loss": 0.0037, + "step": 48224 + }, + { + "epoch": 14.89, + "learning_rate": 3.2287336925711733e-06, + "loss": 0.0035, + "step": 48225 + }, + { + "epoch": 14.89, + "learning_rate": 3.228365680784804e-06, + "loss": 0.0051, + "step": 48226 + }, + { + "epoch": 14.89, + "learning_rate": 3.227997685935528e-06, + "loss": 0.0034, + "step": 48227 + }, + { + "epoch": 14.89, + "learning_rate": 3.227629708024268e-06, + "loss": 0.0036, + "step": 48228 + }, + { + "epoch": 14.89, + "learning_rate": 3.2272617470519374e-06, + "loss": 0.0041, + "step": 48229 + }, + { + "epoch": 14.89, + "learning_rate": 3.226893803019464e-06, + "loss": 0.004, + "step": 48230 + }, + { + "epoch": 14.89, + "learning_rate": 3.226525875927764e-06, + "loss": 0.0044, + "step": 48231 + }, + { + "epoch": 14.89, + "learning_rate": 3.2261579657777554e-06, + "loss": 0.0033, + "step": 48232 + }, + { + "epoch": 14.9, + "learning_rate": 3.2257900725703616e-06, + "loss": 0.0031, + "step": 48233 + }, + { + "epoch": 14.9, + "learning_rate": 3.2254221963065045e-06, + "loss": 0.0038, + "step": 48234 + }, + { + "epoch": 14.9, + "learning_rate": 3.2250543369871036e-06, + "loss": 0.0035, + "step": 48235 + }, + { + "epoch": 14.9, + "learning_rate": 3.224686494613073e-06, + "loss": 0.0033, + "step": 48236 + }, + { + "epoch": 14.9, + "learning_rate": 3.224318669185341e-06, + "loss": 0.0031, + "step": 48237 + }, + { + "epoch": 14.9, + "learning_rate": 3.22395086070482e-06, + "loss": 0.0036, + "step": 48238 + }, + { + "epoch": 14.9, + "learning_rate": 3.2235830691724346e-06, + "loss": 0.0033, + "step": 48239 + }, + { + "epoch": 14.9, + "learning_rate": 3.223215294589106e-06, + "loss": 0.0034, + "step": 48240 + }, + { + "epoch": 14.9, + "learning_rate": 3.2228475369557534e-06, + "loss": 0.0044, + "step": 48241 + }, + { + "epoch": 14.9, + "learning_rate": 3.2224797962732914e-06, + "loss": 0.0045, + "step": 48242 + }, + { + "epoch": 14.9, + "learning_rate": 3.222112072542646e-06, + "loss": 0.0029, + "step": 48243 + }, + { + "epoch": 14.9, + "learning_rate": 3.2217443657647317e-06, + "loss": 0.0033, + "step": 48244 + }, + { + "epoch": 14.9, + "learning_rate": 3.221376675940475e-06, + "loss": 0.0033, + "step": 48245 + }, + { + "epoch": 14.9, + "learning_rate": 3.2210090030707907e-06, + "loss": 0.0033, + "step": 48246 + }, + { + "epoch": 14.9, + "learning_rate": 3.2206413471565968e-06, + "loss": 0.0034, + "step": 48247 + }, + { + "epoch": 14.9, + "learning_rate": 3.2202737081988145e-06, + "loss": 0.0031, + "step": 48248 + }, + { + "epoch": 14.9, + "learning_rate": 3.219906086198369e-06, + "loss": 0.004, + "step": 48249 + }, + { + "epoch": 14.9, + "learning_rate": 3.2195384811561704e-06, + "loss": 0.0035, + "step": 48250 + }, + { + "epoch": 14.9, + "learning_rate": 3.2191708930731457e-06, + "loss": 0.0033, + "step": 48251 + }, + { + "epoch": 14.9, + "learning_rate": 3.2188033219502122e-06, + "loss": 0.0039, + "step": 48252 + }, + { + "epoch": 14.9, + "learning_rate": 3.218435767788285e-06, + "loss": 0.0047, + "step": 48253 + }, + { + "epoch": 14.9, + "learning_rate": 3.218068230588286e-06, + "loss": 0.0038, + "step": 48254 + }, + { + "epoch": 14.9, + "learning_rate": 3.217700710351139e-06, + "loss": 0.0039, + "step": 48255 + }, + { + "epoch": 14.9, + "learning_rate": 3.2173332070777605e-06, + "loss": 0.0041, + "step": 48256 + }, + { + "epoch": 14.9, + "learning_rate": 3.2169657207690653e-06, + "loss": 0.0033, + "step": 48257 + }, + { + "epoch": 14.9, + "learning_rate": 3.2165982514259754e-06, + "loss": 0.0038, + "step": 48258 + }, + { + "epoch": 14.9, + "learning_rate": 3.2162307990494136e-06, + "loss": 0.0036, + "step": 48259 + }, + { + "epoch": 14.9, + "learning_rate": 3.2158633636402923e-06, + "loss": 0.0036, + "step": 48260 + }, + { + "epoch": 14.9, + "learning_rate": 3.215495945199538e-06, + "loss": 0.0033, + "step": 48261 + }, + { + "epoch": 14.9, + "learning_rate": 3.2151285437280653e-06, + "loss": 0.0045, + "step": 48262 + }, + { + "epoch": 14.9, + "learning_rate": 3.21476115922679e-06, + "loss": 0.0028, + "step": 48263 + }, + { + "epoch": 14.9, + "learning_rate": 3.214393791696636e-06, + "loss": 0.0038, + "step": 48264 + }, + { + "epoch": 14.91, + "learning_rate": 3.2140264411385235e-06, + "loss": 0.0036, + "step": 48265 + }, + { + "epoch": 14.91, + "learning_rate": 3.2136591075533673e-06, + "loss": 0.0034, + "step": 48266 + }, + { + "epoch": 14.91, + "learning_rate": 3.2132917909420856e-06, + "loss": 0.0042, + "step": 48267 + }, + { + "epoch": 14.91, + "learning_rate": 3.2129244913056025e-06, + "loss": 0.0037, + "step": 48268 + }, + { + "epoch": 14.91, + "learning_rate": 3.2125572086448286e-06, + "loss": 0.0035, + "step": 48269 + }, + { + "epoch": 14.91, + "learning_rate": 3.2121899429606875e-06, + "loss": 0.0037, + "step": 48270 + }, + { + "epoch": 14.91, + "learning_rate": 3.2118226942541042e-06, + "loss": 0.0037, + "step": 48271 + }, + { + "epoch": 14.91, + "learning_rate": 3.211455462525983e-06, + "loss": 0.0034, + "step": 48272 + }, + { + "epoch": 14.91, + "learning_rate": 3.211088247777251e-06, + "loss": 0.0038, + "step": 48273 + }, + { + "epoch": 14.91, + "learning_rate": 3.210721050008828e-06, + "loss": 0.004, + "step": 48274 + }, + { + "epoch": 14.91, + "learning_rate": 3.2103538692216275e-06, + "loss": 0.0031, + "step": 48275 + }, + { + "epoch": 14.91, + "learning_rate": 3.209986705416572e-06, + "loss": 0.0034, + "step": 48276 + }, + { + "epoch": 14.91, + "learning_rate": 3.20961955859458e-06, + "loss": 0.0039, + "step": 48277 + }, + { + "epoch": 14.91, + "learning_rate": 3.209252428756564e-06, + "loss": 0.0033, + "step": 48278 + }, + { + "epoch": 14.91, + "learning_rate": 3.2088853159034463e-06, + "loss": 0.004, + "step": 48279 + }, + { + "epoch": 14.91, + "learning_rate": 3.2085182200361474e-06, + "loss": 0.0028, + "step": 48280 + }, + { + "epoch": 14.91, + "learning_rate": 3.2081511411555844e-06, + "loss": 0.0041, + "step": 48281 + }, + { + "epoch": 14.91, + "learning_rate": 3.2077840792626704e-06, + "loss": 0.0042, + "step": 48282 + }, + { + "epoch": 14.91, + "learning_rate": 3.20741703435833e-06, + "loss": 0.0045, + "step": 48283 + }, + { + "epoch": 14.91, + "learning_rate": 3.2070500064434763e-06, + "loss": 0.0033, + "step": 48284 + }, + { + "epoch": 14.91, + "learning_rate": 3.2066829955190283e-06, + "loss": 0.0041, + "step": 48285 + }, + { + "epoch": 14.91, + "learning_rate": 3.2063160015859097e-06, + "loss": 0.0043, + "step": 48286 + }, + { + "epoch": 14.91, + "learning_rate": 3.205949024645033e-06, + "loss": 0.0039, + "step": 48287 + }, + { + "epoch": 14.91, + "learning_rate": 3.2055820646973135e-06, + "loss": 0.0033, + "step": 48288 + }, + { + "epoch": 14.91, + "learning_rate": 3.2052151217436733e-06, + "loss": 0.0037, + "step": 48289 + }, + { + "epoch": 14.91, + "learning_rate": 3.204848195785032e-06, + "loss": 0.0036, + "step": 48290 + }, + { + "epoch": 14.91, + "learning_rate": 3.204481286822305e-06, + "loss": 0.0033, + "step": 48291 + }, + { + "epoch": 14.91, + "learning_rate": 3.2041143948564057e-06, + "loss": 0.0051, + "step": 48292 + }, + { + "epoch": 14.91, + "learning_rate": 3.2037475198882606e-06, + "loss": 0.0037, + "step": 48293 + }, + { + "epoch": 14.91, + "learning_rate": 3.203380661918778e-06, + "loss": 0.0038, + "step": 48294 + }, + { + "epoch": 14.91, + "learning_rate": 3.2030138209488804e-06, + "loss": 0.0048, + "step": 48295 + }, + { + "epoch": 14.91, + "learning_rate": 3.2026469969794884e-06, + "loss": 0.0031, + "step": 48296 + }, + { + "epoch": 14.91, + "learning_rate": 3.202280190011515e-06, + "loss": 0.0035, + "step": 48297 + }, + { + "epoch": 14.92, + "learning_rate": 3.2019134000458763e-06, + "loss": 0.0036, + "step": 48298 + }, + { + "epoch": 14.92, + "learning_rate": 3.201546627083496e-06, + "loss": 0.0046, + "step": 48299 + }, + { + "epoch": 14.92, + "learning_rate": 3.201179871125283e-06, + "loss": 0.0032, + "step": 48300 + }, + { + "epoch": 14.92, + "learning_rate": 3.200813132172164e-06, + "loss": 0.0034, + "step": 48301 + }, + { + "epoch": 14.92, + "learning_rate": 3.2004464102250498e-06, + "loss": 0.0037, + "step": 48302 + }, + { + "epoch": 14.92, + "learning_rate": 3.2000797052848564e-06, + "loss": 0.0038, + "step": 48303 + }, + { + "epoch": 14.92, + "learning_rate": 3.199713017352504e-06, + "loss": 0.0038, + "step": 48304 + }, + { + "epoch": 14.92, + "learning_rate": 3.199346346428913e-06, + "loss": 0.0036, + "step": 48305 + }, + { + "epoch": 14.92, + "learning_rate": 3.198979692514994e-06, + "loss": 0.0032, + "step": 48306 + }, + { + "epoch": 14.92, + "learning_rate": 3.1986130556116702e-06, + "loss": 0.0034, + "step": 48307 + }, + { + "epoch": 14.92, + "learning_rate": 3.198246435719856e-06, + "loss": 0.0034, + "step": 48308 + }, + { + "epoch": 14.92, + "learning_rate": 3.1978798328404646e-06, + "loss": 0.005, + "step": 48309 + }, + { + "epoch": 14.92, + "learning_rate": 3.1975132469744164e-06, + "loss": 0.0034, + "step": 48310 + }, + { + "epoch": 14.92, + "learning_rate": 3.1971466781226313e-06, + "loss": 0.0041, + "step": 48311 + }, + { + "epoch": 14.92, + "learning_rate": 3.1967801262860233e-06, + "loss": 0.004, + "step": 48312 + }, + { + "epoch": 14.92, + "learning_rate": 3.196413591465506e-06, + "loss": 0.0036, + "step": 48313 + }, + { + "epoch": 14.92, + "learning_rate": 3.196047073662002e-06, + "loss": 0.0046, + "step": 48314 + }, + { + "epoch": 14.92, + "learning_rate": 3.1956805728764216e-06, + "loss": 0.0037, + "step": 48315 + }, + { + "epoch": 14.92, + "learning_rate": 3.195314089109687e-06, + "loss": 0.0034, + "step": 48316 + }, + { + "epoch": 14.92, + "learning_rate": 3.194947622362714e-06, + "loss": 0.0058, + "step": 48317 + }, + { + "epoch": 14.92, + "learning_rate": 3.1945811726364197e-06, + "loss": 0.0064, + "step": 48318 + }, + { + "epoch": 14.92, + "learning_rate": 3.1942147399317147e-06, + "loss": 0.0035, + "step": 48319 + }, + { + "epoch": 14.92, + "learning_rate": 3.1938483242495213e-06, + "loss": 0.0033, + "step": 48320 + }, + { + "epoch": 14.92, + "learning_rate": 3.1934819255907568e-06, + "loss": 0.0037, + "step": 48321 + }, + { + "epoch": 14.92, + "learning_rate": 3.1931155439563355e-06, + "loss": 0.0047, + "step": 48322 + }, + { + "epoch": 14.92, + "learning_rate": 3.192749179347171e-06, + "loss": 0.0031, + "step": 48323 + }, + { + "epoch": 14.92, + "learning_rate": 3.192382831764185e-06, + "loss": 0.004, + "step": 48324 + }, + { + "epoch": 14.92, + "learning_rate": 3.192016501208288e-06, + "loss": 0.0046, + "step": 48325 + }, + { + "epoch": 14.92, + "learning_rate": 3.1916501876803997e-06, + "loss": 0.0036, + "step": 48326 + }, + { + "epoch": 14.92, + "learning_rate": 3.191283891181439e-06, + "loss": 0.0033, + "step": 48327 + }, + { + "epoch": 14.92, + "learning_rate": 3.19091761171232e-06, + "loss": 0.0035, + "step": 48328 + }, + { + "epoch": 14.92, + "learning_rate": 3.1905513492739538e-06, + "loss": 0.0031, + "step": 48329 + }, + { + "epoch": 14.93, + "learning_rate": 3.1901851038672637e-06, + "loss": 0.0036, + "step": 48330 + }, + { + "epoch": 14.93, + "learning_rate": 3.1898188754931603e-06, + "loss": 0.0049, + "step": 48331 + }, + { + "epoch": 14.93, + "learning_rate": 3.1894526641525645e-06, + "loss": 0.0038, + "step": 48332 + }, + { + "epoch": 14.93, + "learning_rate": 3.189086469846391e-06, + "loss": 0.0032, + "step": 48333 + }, + { + "epoch": 14.93, + "learning_rate": 3.18872029257555e-06, + "loss": 0.0041, + "step": 48334 + }, + { + "epoch": 14.93, + "learning_rate": 3.1883541323409616e-06, + "loss": 0.0041, + "step": 48335 + }, + { + "epoch": 14.93, + "learning_rate": 3.187987989143546e-06, + "loss": 0.0041, + "step": 48336 + }, + { + "epoch": 14.93, + "learning_rate": 3.1876218629842113e-06, + "loss": 0.0037, + "step": 48337 + }, + { + "epoch": 14.93, + "learning_rate": 3.1872557538638803e-06, + "loss": 0.0035, + "step": 48338 + }, + { + "epoch": 14.93, + "learning_rate": 3.1868896617834644e-06, + "loss": 0.0031, + "step": 48339 + }, + { + "epoch": 14.93, + "learning_rate": 3.186523586743878e-06, + "loss": 0.0039, + "step": 48340 + }, + { + "epoch": 14.93, + "learning_rate": 3.1861575287460376e-06, + "loss": 0.0045, + "step": 48341 + }, + { + "epoch": 14.93, + "learning_rate": 3.1857914877908647e-06, + "loss": 0.0051, + "step": 48342 + }, + { + "epoch": 14.93, + "learning_rate": 3.185425463879269e-06, + "loss": 0.0039, + "step": 48343 + }, + { + "epoch": 14.93, + "learning_rate": 3.185059457012164e-06, + "loss": 0.003, + "step": 48344 + }, + { + "epoch": 14.93, + "learning_rate": 3.1846934671904718e-06, + "loss": 0.0038, + "step": 48345 + }, + { + "epoch": 14.93, + "learning_rate": 3.1843274944151005e-06, + "loss": 0.0031, + "step": 48346 + }, + { + "epoch": 14.93, + "learning_rate": 3.1839615386869704e-06, + "loss": 0.0039, + "step": 48347 + }, + { + "epoch": 14.93, + "learning_rate": 3.183595600006998e-06, + "loss": 0.0035, + "step": 48348 + }, + { + "epoch": 14.93, + "learning_rate": 3.1832296783760963e-06, + "loss": 0.0033, + "step": 48349 + }, + { + "epoch": 14.93, + "learning_rate": 3.1828637737951774e-06, + "loss": 0.005, + "step": 48350 + }, + { + "epoch": 14.93, + "learning_rate": 3.182497886265162e-06, + "loss": 0.0051, + "step": 48351 + }, + { + "epoch": 14.93, + "learning_rate": 3.1821320157869607e-06, + "loss": 0.004, + "step": 48352 + }, + { + "epoch": 14.93, + "learning_rate": 3.181766162361494e-06, + "loss": 0.0037, + "step": 48353 + }, + { + "epoch": 14.93, + "learning_rate": 3.18140032598967e-06, + "loss": 0.0032, + "step": 48354 + }, + { + "epoch": 14.93, + "learning_rate": 3.18103450667241e-06, + "loss": 0.0031, + "step": 48355 + }, + { + "epoch": 14.93, + "learning_rate": 3.1806687044106245e-06, + "loss": 0.0029, + "step": 48356 + }, + { + "epoch": 14.93, + "learning_rate": 3.1803029192052293e-06, + "loss": 0.0024, + "step": 48357 + }, + { + "epoch": 14.93, + "learning_rate": 3.1799371510571443e-06, + "loss": 0.0035, + "step": 48358 + }, + { + "epoch": 14.93, + "learning_rate": 3.1795713999672796e-06, + "loss": 0.0035, + "step": 48359 + }, + { + "epoch": 14.93, + "learning_rate": 3.1792056659365488e-06, + "loss": 0.0029, + "step": 48360 + }, + { + "epoch": 14.93, + "learning_rate": 3.1788399489658704e-06, + "loss": 0.004, + "step": 48361 + }, + { + "epoch": 14.94, + "learning_rate": 3.1784742490561547e-06, + "loss": 0.0054, + "step": 48362 + }, + { + "epoch": 14.94, + "learning_rate": 3.178108566208323e-06, + "loss": 0.0035, + "step": 48363 + }, + { + "epoch": 14.94, + "learning_rate": 3.177742900423285e-06, + "loss": 0.0048, + "step": 48364 + }, + { + "epoch": 14.94, + "learning_rate": 3.177377251701954e-06, + "loss": 0.0042, + "step": 48365 + }, + { + "epoch": 14.94, + "learning_rate": 3.177011620045246e-06, + "loss": 0.0051, + "step": 48366 + }, + { + "epoch": 14.94, + "learning_rate": 3.1766460054540805e-06, + "loss": 0.0029, + "step": 48367 + }, + { + "epoch": 14.94, + "learning_rate": 3.1762804079293643e-06, + "loss": 0.0041, + "step": 48368 + }, + { + "epoch": 14.94, + "learning_rate": 3.1759148274720185e-06, + "loss": 0.0053, + "step": 48369 + }, + { + "epoch": 14.94, + "learning_rate": 3.1755492640829545e-06, + "loss": 0.0038, + "step": 48370 + }, + { + "epoch": 14.94, + "learning_rate": 3.175183717763083e-06, + "loss": 0.0043, + "step": 48371 + }, + { + "epoch": 14.94, + "learning_rate": 3.174818188513321e-06, + "loss": 0.0036, + "step": 48372 + }, + { + "epoch": 14.94, + "learning_rate": 3.1744526763345883e-06, + "loss": 0.0043, + "step": 48373 + }, + { + "epoch": 14.94, + "learning_rate": 3.174087181227794e-06, + "loss": 0.0037, + "step": 48374 + }, + { + "epoch": 14.94, + "learning_rate": 3.1737217031938484e-06, + "loss": 0.005, + "step": 48375 + }, + { + "epoch": 14.94, + "learning_rate": 3.173356242233674e-06, + "loss": 0.0028, + "step": 48376 + }, + { + "epoch": 14.94, + "learning_rate": 3.1729907983481778e-06, + "loss": 0.004, + "step": 48377 + }, + { + "epoch": 14.94, + "learning_rate": 3.172625371538276e-06, + "loss": 0.0044, + "step": 48378 + }, + { + "epoch": 14.94, + "learning_rate": 3.17225996180489e-06, + "loss": 0.0038, + "step": 48379 + }, + { + "epoch": 14.94, + "learning_rate": 3.1718945691489213e-06, + "loss": 0.0037, + "step": 48380 + }, + { + "epoch": 14.94, + "learning_rate": 3.171529193571289e-06, + "loss": 0.0035, + "step": 48381 + }, + { + "epoch": 14.94, + "learning_rate": 3.17116383507291e-06, + "loss": 0.003, + "step": 48382 + }, + { + "epoch": 14.94, + "learning_rate": 3.1707984936546943e-06, + "loss": 0.0033, + "step": 48383 + }, + { + "epoch": 14.94, + "learning_rate": 3.1704331693175595e-06, + "loss": 0.0037, + "step": 48384 + }, + { + "epoch": 14.94, + "learning_rate": 3.170067862062417e-06, + "loss": 0.0033, + "step": 48385 + }, + { + "epoch": 14.94, + "learning_rate": 3.1697025718901774e-06, + "loss": 0.0035, + "step": 48386 + }, + { + "epoch": 14.94, + "learning_rate": 3.1693372988017568e-06, + "loss": 0.0043, + "step": 48387 + }, + { + "epoch": 14.94, + "learning_rate": 3.1689720427980707e-06, + "loss": 0.004, + "step": 48388 + }, + { + "epoch": 14.94, + "learning_rate": 3.1686068038800366e-06, + "loss": 0.0033, + "step": 48389 + }, + { + "epoch": 14.94, + "learning_rate": 3.168241582048557e-06, + "loss": 0.0041, + "step": 48390 + }, + { + "epoch": 14.94, + "learning_rate": 3.167876377304552e-06, + "loss": 0.0035, + "step": 48391 + }, + { + "epoch": 14.94, + "learning_rate": 3.1675111896489365e-06, + "loss": 0.0041, + "step": 48392 + }, + { + "epoch": 14.94, + "learning_rate": 3.1671460190826186e-06, + "loss": 0.0033, + "step": 48393 + }, + { + "epoch": 14.94, + "learning_rate": 3.1667808656065178e-06, + "loss": 0.0031, + "step": 48394 + }, + { + "epoch": 14.95, + "learning_rate": 3.166415729221545e-06, + "loss": 0.0037, + "step": 48395 + }, + { + "epoch": 14.95, + "learning_rate": 3.1660506099286094e-06, + "loss": 0.0036, + "step": 48396 + }, + { + "epoch": 14.95, + "learning_rate": 3.1656855077286263e-06, + "loss": 0.0034, + "step": 48397 + }, + { + "epoch": 14.95, + "learning_rate": 3.165320422622515e-06, + "loss": 0.0037, + "step": 48398 + }, + { + "epoch": 14.95, + "learning_rate": 3.164955354611183e-06, + "loss": 0.0057, + "step": 48399 + }, + { + "epoch": 14.95, + "learning_rate": 3.1645903036955426e-06, + "loss": 0.0039, + "step": 48400 + }, + { + "epoch": 14.95, + "learning_rate": 3.1642252698765107e-06, + "loss": 0.0036, + "step": 48401 + }, + { + "epoch": 14.95, + "learning_rate": 3.1638602531549944e-06, + "loss": 0.0041, + "step": 48402 + }, + { + "epoch": 14.95, + "learning_rate": 3.163495253531912e-06, + "loss": 0.004, + "step": 48403 + }, + { + "epoch": 14.95, + "learning_rate": 3.163130271008177e-06, + "loss": 0.0029, + "step": 48404 + }, + { + "epoch": 14.95, + "learning_rate": 3.1627653055846995e-06, + "loss": 0.003, + "step": 48405 + }, + { + "epoch": 14.95, + "learning_rate": 3.162400357262391e-06, + "loss": 0.0035, + "step": 48406 + }, + { + "epoch": 14.95, + "learning_rate": 3.1620354260421695e-06, + "loss": 0.0046, + "step": 48407 + }, + { + "epoch": 14.95, + "learning_rate": 3.16167051192494e-06, + "loss": 0.0038, + "step": 48408 + }, + { + "epoch": 14.95, + "learning_rate": 3.161305614911625e-06, + "loss": 0.0045, + "step": 48409 + }, + { + "epoch": 14.95, + "learning_rate": 3.160940735003131e-06, + "loss": 0.0036, + "step": 48410 + }, + { + "epoch": 14.95, + "learning_rate": 3.1605758722003678e-06, + "loss": 0.004, + "step": 48411 + }, + { + "epoch": 14.95, + "learning_rate": 3.1602110265042516e-06, + "loss": 0.0037, + "step": 48412 + }, + { + "epoch": 14.95, + "learning_rate": 3.1598461979157e-06, + "loss": 0.004, + "step": 48413 + }, + { + "epoch": 14.95, + "learning_rate": 3.1594813864356168e-06, + "loss": 0.0033, + "step": 48414 + }, + { + "epoch": 14.95, + "learning_rate": 3.1591165920649204e-06, + "loss": 0.0035, + "step": 48415 + }, + { + "epoch": 14.95, + "learning_rate": 3.1587518148045217e-06, + "loss": 0.0029, + "step": 48416 + }, + { + "epoch": 14.95, + "learning_rate": 3.15838705465533e-06, + "loss": 0.0048, + "step": 48417 + }, + { + "epoch": 14.95, + "learning_rate": 3.1580223116182597e-06, + "loss": 0.004, + "step": 48418 + }, + { + "epoch": 14.95, + "learning_rate": 3.1576575856942227e-06, + "loss": 0.0036, + "step": 48419 + }, + { + "epoch": 14.95, + "learning_rate": 3.157292876884139e-06, + "loss": 0.0046, + "step": 48420 + }, + { + "epoch": 14.95, + "learning_rate": 3.1569281851889077e-06, + "loss": 0.0033, + "step": 48421 + }, + { + "epoch": 14.95, + "learning_rate": 3.1565635106094474e-06, + "loss": 0.003, + "step": 48422 + }, + { + "epoch": 14.95, + "learning_rate": 3.1561988531466713e-06, + "loss": 0.003, + "step": 48423 + }, + { + "epoch": 14.95, + "learning_rate": 3.1558342128014883e-06, + "loss": 0.0041, + "step": 48424 + }, + { + "epoch": 14.95, + "learning_rate": 3.1554695895748154e-06, + "loss": 0.0034, + "step": 48425 + }, + { + "epoch": 14.95, + "learning_rate": 3.155104983467562e-06, + "loss": 0.0035, + "step": 48426 + }, + { + "epoch": 14.96, + "learning_rate": 3.1547403944806355e-06, + "loss": 0.0045, + "step": 48427 + }, + { + "epoch": 14.96, + "learning_rate": 3.1543758226149523e-06, + "loss": 0.0048, + "step": 48428 + }, + { + "epoch": 14.96, + "learning_rate": 3.1540112678714263e-06, + "loss": 0.0036, + "step": 48429 + }, + { + "epoch": 14.96, + "learning_rate": 3.1536467302509666e-06, + "loss": 0.0033, + "step": 48430 + }, + { + "epoch": 14.96, + "learning_rate": 3.1532822097544824e-06, + "loss": 0.0035, + "step": 48431 + }, + { + "epoch": 14.96, + "learning_rate": 3.152917706382892e-06, + "loss": 0.0027, + "step": 48432 + }, + { + "epoch": 14.96, + "learning_rate": 3.152553220137099e-06, + "loss": 0.0036, + "step": 48433 + }, + { + "epoch": 14.96, + "learning_rate": 3.1521887510180194e-06, + "loss": 0.005, + "step": 48434 + }, + { + "epoch": 14.96, + "learning_rate": 3.151824299026568e-06, + "loss": 0.0039, + "step": 48435 + }, + { + "epoch": 14.96, + "learning_rate": 3.151459864163653e-06, + "loss": 0.0037, + "step": 48436 + }, + { + "epoch": 14.96, + "learning_rate": 3.1510954464301835e-06, + "loss": 0.0037, + "step": 48437 + }, + { + "epoch": 14.96, + "learning_rate": 3.1507310458270756e-06, + "loss": 0.0045, + "step": 48438 + }, + { + "epoch": 14.96, + "learning_rate": 3.1503666623552366e-06, + "loss": 0.0038, + "step": 48439 + }, + { + "epoch": 14.96, + "learning_rate": 3.1500022960155818e-06, + "loss": 0.0028, + "step": 48440 + }, + { + "epoch": 14.96, + "learning_rate": 3.149637946809021e-06, + "loss": 0.0031, + "step": 48441 + }, + { + "epoch": 14.96, + "learning_rate": 3.1492736147364624e-06, + "loss": 0.0043, + "step": 48442 + }, + { + "epoch": 14.96, + "learning_rate": 3.148909299798819e-06, + "loss": 0.0044, + "step": 48443 + }, + { + "epoch": 14.96, + "learning_rate": 3.148545001997008e-06, + "loss": 0.0034, + "step": 48444 + }, + { + "epoch": 14.96, + "learning_rate": 3.1481807213319302e-06, + "loss": 0.0029, + "step": 48445 + }, + { + "epoch": 14.96, + "learning_rate": 3.147816457804507e-06, + "loss": 0.0031, + "step": 48446 + }, + { + "epoch": 14.96, + "learning_rate": 3.1474522114156436e-06, + "loss": 0.0041, + "step": 48447 + }, + { + "epoch": 14.96, + "learning_rate": 3.1470879821662494e-06, + "loss": 0.0041, + "step": 48448 + }, + { + "epoch": 14.96, + "learning_rate": 3.1467237700572386e-06, + "loss": 0.0033, + "step": 48449 + }, + { + "epoch": 14.96, + "learning_rate": 3.146359575089524e-06, + "loss": 0.0038, + "step": 48450 + }, + { + "epoch": 14.96, + "learning_rate": 3.1459953972640136e-06, + "loss": 0.0042, + "step": 48451 + }, + { + "epoch": 14.96, + "learning_rate": 3.1456312365816167e-06, + "loss": 0.0032, + "step": 48452 + }, + { + "epoch": 14.96, + "learning_rate": 3.145267093043245e-06, + "loss": 0.0046, + "step": 48453 + }, + { + "epoch": 14.96, + "learning_rate": 3.144902966649814e-06, + "loss": 0.0051, + "step": 48454 + }, + { + "epoch": 14.96, + "learning_rate": 3.1445388574022284e-06, + "loss": 0.0041, + "step": 48455 + }, + { + "epoch": 14.96, + "learning_rate": 3.1441747653014054e-06, + "loss": 0.0033, + "step": 48456 + }, + { + "epoch": 14.96, + "learning_rate": 3.1438106903482503e-06, + "loss": 0.0035, + "step": 48457 + }, + { + "epoch": 14.96, + "learning_rate": 3.143446632543673e-06, + "loss": 0.0049, + "step": 48458 + }, + { + "epoch": 14.97, + "learning_rate": 3.1430825918885855e-06, + "loss": 0.0041, + "step": 48459 + }, + { + "epoch": 14.97, + "learning_rate": 3.1427185683839025e-06, + "loss": 0.0039, + "step": 48460 + }, + { + "epoch": 14.97, + "learning_rate": 3.1423545620305308e-06, + "loss": 0.0026, + "step": 48461 + }, + { + "epoch": 14.97, + "learning_rate": 3.1419905728293785e-06, + "loss": 0.0042, + "step": 48462 + }, + { + "epoch": 14.97, + "learning_rate": 3.1416266007813613e-06, + "loss": 0.0034, + "step": 48463 + }, + { + "epoch": 14.97, + "learning_rate": 3.141262645887384e-06, + "loss": 0.0041, + "step": 48464 + }, + { + "epoch": 14.97, + "learning_rate": 3.140898708148359e-06, + "loss": 0.004, + "step": 48465 + }, + { + "epoch": 14.97, + "learning_rate": 3.1405347875652013e-06, + "loss": 0.0034, + "step": 48466 + }, + { + "epoch": 14.97, + "learning_rate": 3.1401708841388167e-06, + "loss": 0.0038, + "step": 48467 + }, + { + "epoch": 14.97, + "learning_rate": 3.139806997870114e-06, + "loss": 0.004, + "step": 48468 + }, + { + "epoch": 14.97, + "learning_rate": 3.139443128760007e-06, + "loss": 0.0027, + "step": 48469 + }, + { + "epoch": 14.97, + "learning_rate": 3.1390792768094013e-06, + "loss": 0.0036, + "step": 48470 + }, + { + "epoch": 14.97, + "learning_rate": 3.1387154420192124e-06, + "loss": 0.0038, + "step": 48471 + }, + { + "epoch": 14.97, + "learning_rate": 3.1383516243903477e-06, + "loss": 0.0036, + "step": 48472 + }, + { + "epoch": 14.97, + "learning_rate": 3.137987823923715e-06, + "loss": 0.0041, + "step": 48473 + }, + { + "epoch": 14.97, + "learning_rate": 3.1376240406202253e-06, + "loss": 0.0038, + "step": 48474 + }, + { + "epoch": 14.97, + "learning_rate": 3.1372602744807934e-06, + "loss": 0.003, + "step": 48475 + }, + { + "epoch": 14.97, + "learning_rate": 3.136896525506321e-06, + "loss": 0.0033, + "step": 48476 + }, + { + "epoch": 14.97, + "learning_rate": 3.1365327936977262e-06, + "loss": 0.0037, + "step": 48477 + }, + { + "epoch": 14.97, + "learning_rate": 3.1361690790559142e-06, + "loss": 0.005, + "step": 48478 + }, + { + "epoch": 14.97, + "learning_rate": 3.1358053815817922e-06, + "loss": 0.0042, + "step": 48479 + }, + { + "epoch": 14.97, + "learning_rate": 3.135441701276273e-06, + "loss": 0.0037, + "step": 48480 + }, + { + "epoch": 14.97, + "learning_rate": 3.135078038140269e-06, + "loss": 0.0039, + "step": 48481 + }, + { + "epoch": 14.97, + "learning_rate": 3.134714392174687e-06, + "loss": 0.0038, + "step": 48482 + }, + { + "epoch": 14.97, + "learning_rate": 3.1343507633804336e-06, + "loss": 0.0034, + "step": 48483 + }, + { + "epoch": 14.97, + "learning_rate": 3.1339871517584207e-06, + "loss": 0.0046, + "step": 48484 + }, + { + "epoch": 14.97, + "learning_rate": 3.133623557309562e-06, + "loss": 0.0051, + "step": 48485 + }, + { + "epoch": 14.97, + "learning_rate": 3.1332599800347595e-06, + "loss": 0.0039, + "step": 48486 + }, + { + "epoch": 14.97, + "learning_rate": 3.1328964199349286e-06, + "loss": 0.0041, + "step": 48487 + }, + { + "epoch": 14.97, + "learning_rate": 3.1325328770109773e-06, + "loss": 0.0054, + "step": 48488 + }, + { + "epoch": 14.97, + "learning_rate": 3.1321693512638107e-06, + "loss": 0.0032, + "step": 48489 + }, + { + "epoch": 14.97, + "learning_rate": 3.131805842694341e-06, + "loss": 0.0043, + "step": 48490 + }, + { + "epoch": 14.97, + "learning_rate": 3.1314423513034807e-06, + "loss": 0.0042, + "step": 48491 + }, + { + "epoch": 14.98, + "learning_rate": 3.1310788770921363e-06, + "loss": 0.0041, + "step": 48492 + }, + { + "epoch": 14.98, + "learning_rate": 3.130715420061212e-06, + "loss": 0.0033, + "step": 48493 + }, + { + "epoch": 14.98, + "learning_rate": 3.1303519802116257e-06, + "loss": 0.0036, + "step": 48494 + }, + { + "epoch": 14.98, + "learning_rate": 3.129988557544278e-06, + "loss": 0.0049, + "step": 48495 + }, + { + "epoch": 14.98, + "learning_rate": 3.129625152060083e-06, + "loss": 0.0052, + "step": 48496 + }, + { + "epoch": 14.98, + "learning_rate": 3.129261763759951e-06, + "loss": 0.004, + "step": 48497 + }, + { + "epoch": 14.98, + "learning_rate": 3.128898392644788e-06, + "loss": 0.0033, + "step": 48498 + }, + { + "epoch": 14.98, + "learning_rate": 3.128535038715501e-06, + "loss": 0.0042, + "step": 48499 + }, + { + "epoch": 14.98, + "learning_rate": 3.128171701973004e-06, + "loss": 0.0031, + "step": 48500 + }, + { + "epoch": 14.98, + "learning_rate": 3.1278083824181993e-06, + "loss": 0.0045, + "step": 48501 + }, + { + "epoch": 14.98, + "learning_rate": 3.127445080052004e-06, + "loss": 0.0029, + "step": 48502 + }, + { + "epoch": 14.98, + "learning_rate": 3.127081794875321e-06, + "loss": 0.0035, + "step": 48503 + }, + { + "epoch": 14.98, + "learning_rate": 3.1267185268890565e-06, + "loss": 0.0033, + "step": 48504 + }, + { + "epoch": 14.98, + "learning_rate": 3.126355276094123e-06, + "loss": 0.003, + "step": 48505 + }, + { + "epoch": 14.98, + "learning_rate": 3.1259920424914315e-06, + "loss": 0.0044, + "step": 48506 + }, + { + "epoch": 14.98, + "learning_rate": 3.1256288260818847e-06, + "loss": 0.0038, + "step": 48507 + }, + { + "epoch": 14.98, + "learning_rate": 3.125265626866396e-06, + "loss": 0.0038, + "step": 48508 + }, + { + "epoch": 14.98, + "learning_rate": 3.1249024448458733e-06, + "loss": 0.0049, + "step": 48509 + }, + { + "epoch": 14.98, + "learning_rate": 3.1245392800212204e-06, + "loss": 0.0044, + "step": 48510 + }, + { + "epoch": 14.98, + "learning_rate": 3.1241761323933485e-06, + "loss": 0.0031, + "step": 48511 + }, + { + "epoch": 14.98, + "learning_rate": 3.1238130019631685e-06, + "loss": 0.004, + "step": 48512 + }, + { + "epoch": 14.98, + "learning_rate": 3.1234498887315867e-06, + "loss": 0.0036, + "step": 48513 + }, + { + "epoch": 14.98, + "learning_rate": 3.123086792699508e-06, + "loss": 0.0038, + "step": 48514 + }, + { + "epoch": 14.98, + "learning_rate": 3.122723713867847e-06, + "loss": 0.0038, + "step": 48515 + }, + { + "epoch": 14.98, + "learning_rate": 3.122360652237505e-06, + "loss": 0.0039, + "step": 48516 + }, + { + "epoch": 14.98, + "learning_rate": 3.1219976078093927e-06, + "loss": 0.0043, + "step": 48517 + }, + { + "epoch": 14.98, + "learning_rate": 3.1216345805844226e-06, + "loss": 0.0033, + "step": 48518 + }, + { + "epoch": 14.98, + "learning_rate": 3.1212715705634998e-06, + "loss": 0.0033, + "step": 48519 + }, + { + "epoch": 14.98, + "learning_rate": 3.1209085777475266e-06, + "loss": 0.0031, + "step": 48520 + }, + { + "epoch": 14.98, + "learning_rate": 3.120545602137417e-06, + "loss": 0.0033, + "step": 48521 + }, + { + "epoch": 14.98, + "learning_rate": 3.12018264373408e-06, + "loss": 0.004, + "step": 48522 + }, + { + "epoch": 14.98, + "learning_rate": 3.1198197025384214e-06, + "loss": 0.0032, + "step": 48523 + }, + { + "epoch": 14.99, + "learning_rate": 3.1194567785513453e-06, + "loss": 0.0034, + "step": 48524 + }, + { + "epoch": 14.99, + "learning_rate": 3.119093871773766e-06, + "loss": 0.0025, + "step": 48525 + }, + { + "epoch": 14.99, + "learning_rate": 3.118730982206585e-06, + "loss": 0.0062, + "step": 48526 + }, + { + "epoch": 14.99, + "learning_rate": 3.1183681098507124e-06, + "loss": 0.0043, + "step": 48527 + }, + { + "epoch": 14.99, + "learning_rate": 3.1180052547070627e-06, + "loss": 0.0026, + "step": 48528 + }, + { + "epoch": 14.99, + "learning_rate": 3.1176424167765307e-06, + "loss": 0.0043, + "step": 48529 + }, + { + "epoch": 14.99, + "learning_rate": 3.11727959606003e-06, + "loss": 0.0039, + "step": 48530 + }, + { + "epoch": 14.99, + "learning_rate": 3.1169167925584722e-06, + "loss": 0.0034, + "step": 48531 + }, + { + "epoch": 14.99, + "learning_rate": 3.1165540062727575e-06, + "loss": 0.0036, + "step": 48532 + }, + { + "epoch": 14.99, + "learning_rate": 3.1161912372037993e-06, + "loss": 0.0038, + "step": 48533 + }, + { + "epoch": 14.99, + "learning_rate": 3.1158284853525035e-06, + "loss": 0.0036, + "step": 48534 + }, + { + "epoch": 14.99, + "learning_rate": 3.1154657507197715e-06, + "loss": 0.0035, + "step": 48535 + }, + { + "epoch": 14.99, + "learning_rate": 3.115103033306517e-06, + "loss": 0.0053, + "step": 48536 + }, + { + "epoch": 14.99, + "learning_rate": 3.1147403331136474e-06, + "loss": 0.0029, + "step": 48537 + }, + { + "epoch": 14.99, + "learning_rate": 3.1143776501420684e-06, + "loss": 0.004, + "step": 48538 + }, + { + "epoch": 14.99, + "learning_rate": 3.1140149843926835e-06, + "loss": 0.0055, + "step": 48539 + }, + { + "epoch": 14.99, + "learning_rate": 3.113652335866407e-06, + "loss": 0.004, + "step": 48540 + }, + { + "epoch": 14.99, + "learning_rate": 3.1132897045641386e-06, + "loss": 0.0033, + "step": 48541 + }, + { + "epoch": 14.99, + "learning_rate": 3.1129270904867882e-06, + "loss": 0.004, + "step": 48542 + }, + { + "epoch": 14.99, + "learning_rate": 3.112564493635266e-06, + "loss": 0.0045, + "step": 48543 + }, + { + "epoch": 14.99, + "learning_rate": 3.1122019140104774e-06, + "loss": 0.0041, + "step": 48544 + }, + { + "epoch": 14.99, + "learning_rate": 3.111839351613324e-06, + "loss": 0.0027, + "step": 48545 + }, + { + "epoch": 14.99, + "learning_rate": 3.11147680644472e-06, + "loss": 0.0027, + "step": 48546 + }, + { + "epoch": 14.99, + "learning_rate": 3.111114278505566e-06, + "loss": 0.0036, + "step": 48547 + }, + { + "epoch": 14.99, + "learning_rate": 3.1107517677967747e-06, + "loss": 0.0033, + "step": 48548 + }, + { + "epoch": 14.99, + "learning_rate": 3.1103892743192465e-06, + "loss": 0.0036, + "step": 48549 + }, + { + "epoch": 14.99, + "learning_rate": 3.110026798073895e-06, + "loss": 0.0033, + "step": 48550 + }, + { + "epoch": 14.99, + "learning_rate": 3.10966433906162e-06, + "loss": 0.0052, + "step": 48551 + }, + { + "epoch": 14.99, + "learning_rate": 3.10930189728333e-06, + "loss": 0.004, + "step": 48552 + }, + { + "epoch": 14.99, + "learning_rate": 3.108939472739937e-06, + "loss": 0.0035, + "step": 48553 + }, + { + "epoch": 14.99, + "learning_rate": 3.1085770654323433e-06, + "loss": 0.0037, + "step": 48554 + }, + { + "epoch": 14.99, + "learning_rate": 3.1082146753614515e-06, + "loss": 0.0035, + "step": 48555 + }, + { + "epoch": 14.99, + "learning_rate": 3.107852302528175e-06, + "loss": 0.0037, + "step": 48556 + }, + { + "epoch": 15.0, + "learning_rate": 3.1074899469334143e-06, + "loss": 0.0035, + "step": 48557 + }, + { + "epoch": 15.0, + "learning_rate": 3.107127608578081e-06, + "loss": 0.0033, + "step": 48558 + }, + { + "epoch": 15.0, + "learning_rate": 3.1067652874630784e-06, + "loss": 0.004, + "step": 48559 + }, + { + "epoch": 15.0, + "learning_rate": 3.1064029835893104e-06, + "loss": 0.0042, + "step": 48560 + }, + { + "epoch": 15.0, + "learning_rate": 3.106040696957686e-06, + "loss": 0.0049, + "step": 48561 + }, + { + "epoch": 15.0, + "learning_rate": 3.105678427569114e-06, + "loss": 0.0048, + "step": 48562 + }, + { + "epoch": 15.0, + "learning_rate": 3.1053161754244953e-06, + "loss": 0.0038, + "step": 48563 + }, + { + "epoch": 15.0, + "learning_rate": 3.104953940524741e-06, + "loss": 0.0031, + "step": 48564 + }, + { + "epoch": 15.0, + "learning_rate": 3.1045917228707534e-06, + "loss": 0.0035, + "step": 48565 + }, + { + "epoch": 15.0, + "learning_rate": 3.104229522463438e-06, + "loss": 0.0047, + "step": 48566 + }, + { + "epoch": 15.0, + "learning_rate": 3.103867339303701e-06, + "loss": 0.0036, + "step": 48567 + }, + { + "epoch": 15.0, + "learning_rate": 3.1035051733924537e-06, + "loss": 0.0035, + "step": 48568 + }, + { + "epoch": 15.0, + "learning_rate": 3.1031430247305983e-06, + "loss": 0.0038, + "step": 48569 + }, + { + "epoch": 15.0, + "learning_rate": 3.102780893319035e-06, + "loss": 0.0037, + "step": 48570 + }, + { + "epoch": 15.0, + "learning_rate": 3.1024187791586804e-06, + "loss": 0.0035, + "step": 48571 + }, + { + "epoch": 15.0, + "learning_rate": 3.1020566822504296e-06, + "loss": 0.0042, + "step": 48572 + }, + { + "epoch": 15.0, + "learning_rate": 3.101694602595193e-06, + "loss": 0.003, + "step": 48573 + }, + { + "epoch": 15.0, + "learning_rate": 3.10133254019388e-06, + "loss": 0.0024, + "step": 48574 + }, + { + "epoch": 15.0, + "learning_rate": 3.100970495047393e-06, + "loss": 0.0027, + "step": 48575 + }, + { + "epoch": 15.0, + "learning_rate": 3.100608467156633e-06, + "loss": 0.0024, + "step": 48576 + }, + { + "epoch": 15.0, + "learning_rate": 3.1002464565225134e-06, + "loss": 0.0023, + "step": 48577 + }, + { + "epoch": 15.0, + "learning_rate": 3.0998844631459326e-06, + "loss": 0.0026, + "step": 48578 + }, + { + "epoch": 15.0, + "learning_rate": 3.099522487027802e-06, + "loss": 0.0024, + "step": 48579 + }, + { + "epoch": 15.0, + "learning_rate": 3.099160528169024e-06, + "loss": 0.0024, + "step": 48580 + }, + { + "epoch": 15.0, + "learning_rate": 3.0987985865705017e-06, + "loss": 0.0026, + "step": 48581 + }, + { + "epoch": 15.0, + "learning_rate": 3.098436662233143e-06, + "loss": 0.0031, + "step": 48582 + }, + { + "epoch": 15.0, + "learning_rate": 3.0980747551578527e-06, + "loss": 0.0026, + "step": 48583 + }, + { + "epoch": 15.0, + "learning_rate": 3.097712865345539e-06, + "loss": 0.0023, + "step": 48584 + }, + { + "epoch": 15.0, + "learning_rate": 3.0973509927971045e-06, + "loss": 0.0017, + "step": 48585 + }, + { + "epoch": 15.0, + "learning_rate": 3.096989137513452e-06, + "loss": 0.0024, + "step": 48586 + }, + { + "epoch": 15.0, + "learning_rate": 3.0966272994954903e-06, + "loss": 0.0024, + "step": 48587 + }, + { + "epoch": 15.0, + "learning_rate": 3.0962654787441204e-06, + "loss": 0.0037, + "step": 48588 + }, + { + "epoch": 15.01, + "learning_rate": 3.095903675260253e-06, + "loss": 0.0022, + "step": 48589 + }, + { + "epoch": 15.01, + "learning_rate": 3.09554188904479e-06, + "loss": 0.0022, + "step": 48590 + }, + { + "epoch": 15.01, + "learning_rate": 3.095180120098632e-06, + "loss": 0.0026, + "step": 48591 + }, + { + "epoch": 15.01, + "learning_rate": 3.0948183684226886e-06, + "loss": 0.002, + "step": 48592 + }, + { + "epoch": 15.01, + "learning_rate": 3.0944566340178663e-06, + "loss": 0.0034, + "step": 48593 + }, + { + "epoch": 15.01, + "learning_rate": 3.0940949168850655e-06, + "loss": 0.0021, + "step": 48594 + }, + { + "epoch": 15.01, + "learning_rate": 3.0937332170251944e-06, + "loss": 0.0023, + "step": 48595 + }, + { + "epoch": 15.01, + "learning_rate": 3.093371534439158e-06, + "loss": 0.0021, + "step": 48596 + }, + { + "epoch": 15.01, + "learning_rate": 3.093009869127854e-06, + "loss": 0.0032, + "step": 48597 + }, + { + "epoch": 15.01, + "learning_rate": 3.0926482210921938e-06, + "loss": 0.0019, + "step": 48598 + }, + { + "epoch": 15.01, + "learning_rate": 3.0922865903330824e-06, + "loss": 0.0029, + "step": 48599 + }, + { + "epoch": 15.01, + "learning_rate": 3.0919249768514227e-06, + "loss": 0.002, + "step": 48600 + }, + { + "epoch": 15.01, + "learning_rate": 3.0915633806481148e-06, + "loss": 0.0023, + "step": 48601 + }, + { + "epoch": 15.01, + "learning_rate": 3.09120180172407e-06, + "loss": 0.0022, + "step": 48602 + }, + { + "epoch": 15.01, + "learning_rate": 3.0908402400801873e-06, + "loss": 0.0032, + "step": 48603 + }, + { + "epoch": 15.01, + "learning_rate": 3.0904786957173727e-06, + "loss": 0.0019, + "step": 48604 + }, + { + "epoch": 15.01, + "learning_rate": 3.0901171686365337e-06, + "loss": 0.0017, + "step": 48605 + }, + { + "epoch": 15.01, + "learning_rate": 3.0897556588385723e-06, + "loss": 0.0039, + "step": 48606 + }, + { + "epoch": 15.01, + "learning_rate": 3.0893941663243897e-06, + "loss": 0.0016, + "step": 48607 + }, + { + "epoch": 15.01, + "learning_rate": 3.0890326910948966e-06, + "loss": 0.0029, + "step": 48608 + }, + { + "epoch": 15.01, + "learning_rate": 3.088671233150988e-06, + "loss": 0.002, + "step": 48609 + }, + { + "epoch": 15.01, + "learning_rate": 3.088309792493578e-06, + "loss": 0.0016, + "step": 48610 + }, + { + "epoch": 15.01, + "learning_rate": 3.0879483691235657e-06, + "loss": 0.0032, + "step": 48611 + }, + { + "epoch": 15.01, + "learning_rate": 3.0875869630418508e-06, + "loss": 0.0026, + "step": 48612 + }, + { + "epoch": 15.01, + "learning_rate": 3.087225574249343e-06, + "loss": 0.0053, + "step": 48613 + }, + { + "epoch": 15.01, + "learning_rate": 3.0868642027469475e-06, + "loss": 0.0022, + "step": 48614 + }, + { + "epoch": 15.01, + "learning_rate": 3.0865028485355617e-06, + "loss": 0.0024, + "step": 48615 + }, + { + "epoch": 15.01, + "learning_rate": 3.0861415116160974e-06, + "loss": 0.0022, + "step": 48616 + }, + { + "epoch": 15.01, + "learning_rate": 3.0857801919894505e-06, + "loss": 0.0029, + "step": 48617 + }, + { + "epoch": 15.01, + "learning_rate": 3.085418889656532e-06, + "loss": 0.0026, + "step": 48618 + }, + { + "epoch": 15.01, + "learning_rate": 3.085057604618239e-06, + "loss": 0.0019, + "step": 48619 + }, + { + "epoch": 15.01, + "learning_rate": 3.0846963368754803e-06, + "loss": 0.002, + "step": 48620 + }, + { + "epoch": 15.02, + "learning_rate": 3.0843350864291576e-06, + "loss": 0.0025, + "step": 48621 + }, + { + "epoch": 15.02, + "learning_rate": 3.083973853280171e-06, + "loss": 0.0022, + "step": 48622 + }, + { + "epoch": 15.02, + "learning_rate": 3.0836126374294283e-06, + "loss": 0.0023, + "step": 48623 + }, + { + "epoch": 15.02, + "learning_rate": 3.0832514388778345e-06, + "loss": 0.0028, + "step": 48624 + }, + { + "epoch": 15.02, + "learning_rate": 3.0828902576262863e-06, + "loss": 0.0035, + "step": 48625 + }, + { + "epoch": 15.02, + "learning_rate": 3.082529093675695e-06, + "loss": 0.0021, + "step": 48626 + }, + { + "epoch": 15.02, + "learning_rate": 3.0821679470269604e-06, + "loss": 0.0022, + "step": 48627 + }, + { + "epoch": 15.02, + "learning_rate": 3.0818068176809822e-06, + "loss": 0.0024, + "step": 48628 + }, + { + "epoch": 15.02, + "learning_rate": 3.081445705638666e-06, + "loss": 0.0021, + "step": 48629 + }, + { + "epoch": 15.02, + "learning_rate": 3.0810846109009207e-06, + "loss": 0.0023, + "step": 48630 + }, + { + "epoch": 15.02, + "learning_rate": 3.0807235334686436e-06, + "loss": 0.0021, + "step": 48631 + }, + { + "epoch": 15.02, + "learning_rate": 3.080362473342736e-06, + "loss": 0.0021, + "step": 48632 + }, + { + "epoch": 15.02, + "learning_rate": 3.0800014305241076e-06, + "loss": 0.0032, + "step": 48633 + }, + { + "epoch": 15.02, + "learning_rate": 3.0796404050136542e-06, + "loss": 0.0023, + "step": 48634 + }, + { + "epoch": 15.02, + "learning_rate": 3.0792793968122814e-06, + "loss": 0.0021, + "step": 48635 + }, + { + "epoch": 15.02, + "learning_rate": 3.078918405920901e-06, + "loss": 0.0021, + "step": 48636 + }, + { + "epoch": 15.02, + "learning_rate": 3.078557432340401e-06, + "loss": 0.0027, + "step": 48637 + }, + { + "epoch": 15.02, + "learning_rate": 3.078196476071691e-06, + "loss": 0.0022, + "step": 48638 + }, + { + "epoch": 15.02, + "learning_rate": 3.0778355371156776e-06, + "loss": 0.0029, + "step": 48639 + }, + { + "epoch": 15.02, + "learning_rate": 3.077474615473257e-06, + "loss": 0.0022, + "step": 48640 + }, + { + "epoch": 15.02, + "learning_rate": 3.0771137111453373e-06, + "loss": 0.0021, + "step": 48641 + }, + { + "epoch": 15.02, + "learning_rate": 3.0767528241328193e-06, + "loss": 0.0025, + "step": 48642 + }, + { + "epoch": 15.02, + "learning_rate": 3.076391954436603e-06, + "loss": 0.0022, + "step": 48643 + }, + { + "epoch": 15.02, + "learning_rate": 3.0760311020575917e-06, + "loss": 0.0019, + "step": 48644 + }, + { + "epoch": 15.02, + "learning_rate": 3.0756702669966943e-06, + "loss": 0.002, + "step": 48645 + }, + { + "epoch": 15.02, + "learning_rate": 3.0753094492548073e-06, + "loss": 0.0022, + "step": 48646 + }, + { + "epoch": 15.02, + "learning_rate": 3.0749486488328306e-06, + "loss": 0.0034, + "step": 48647 + }, + { + "epoch": 15.02, + "learning_rate": 3.074587865731672e-06, + "loss": 0.0022, + "step": 48648 + }, + { + "epoch": 15.02, + "learning_rate": 3.074227099952234e-06, + "loss": 0.003, + "step": 48649 + }, + { + "epoch": 15.02, + "learning_rate": 3.0738663514954147e-06, + "loss": 0.0027, + "step": 48650 + }, + { + "epoch": 15.02, + "learning_rate": 3.0735056203621226e-06, + "loss": 0.0022, + "step": 48651 + }, + { + "epoch": 15.02, + "learning_rate": 3.0731449065532547e-06, + "loss": 0.0015, + "step": 48652 + }, + { + "epoch": 15.02, + "learning_rate": 3.0727842100697135e-06, + "loss": 0.0022, + "step": 48653 + }, + { + "epoch": 15.03, + "learning_rate": 3.072423530912402e-06, + "loss": 0.0024, + "step": 48654 + }, + { + "epoch": 15.03, + "learning_rate": 3.0720628690822254e-06, + "loss": 0.0014, + "step": 48655 + }, + { + "epoch": 15.03, + "learning_rate": 3.0717022245800822e-06, + "loss": 0.0022, + "step": 48656 + }, + { + "epoch": 15.03, + "learning_rate": 3.0713415974068737e-06, + "loss": 0.0027, + "step": 48657 + }, + { + "epoch": 15.03, + "learning_rate": 3.0709809875635065e-06, + "loss": 0.0032, + "step": 48658 + }, + { + "epoch": 15.03, + "learning_rate": 3.070620395050876e-06, + "loss": 0.0023, + "step": 48659 + }, + { + "epoch": 15.03, + "learning_rate": 3.0702598198698873e-06, + "loss": 0.0019, + "step": 48660 + }, + { + "epoch": 15.03, + "learning_rate": 3.0698992620214474e-06, + "loss": 0.0024, + "step": 48661 + }, + { + "epoch": 15.03, + "learning_rate": 3.069538721506452e-06, + "loss": 0.0027, + "step": 48662 + }, + { + "epoch": 15.03, + "learning_rate": 3.0691781983258016e-06, + "loss": 0.002, + "step": 48663 + }, + { + "epoch": 15.03, + "learning_rate": 3.0688176924804036e-06, + "loss": 0.0017, + "step": 48664 + }, + { + "epoch": 15.03, + "learning_rate": 3.0684572039711536e-06, + "loss": 0.0022, + "step": 48665 + }, + { + "epoch": 15.03, + "learning_rate": 3.0680967327989595e-06, + "loss": 0.0021, + "step": 48666 + }, + { + "epoch": 15.03, + "learning_rate": 3.06773627896472e-06, + "loss": 0.0022, + "step": 48667 + }, + { + "epoch": 15.03, + "learning_rate": 3.0673758424693345e-06, + "loss": 0.0018, + "step": 48668 + }, + { + "epoch": 15.03, + "learning_rate": 3.067015423313705e-06, + "loss": 0.0029, + "step": 48669 + }, + { + "epoch": 15.03, + "learning_rate": 3.0666550214987377e-06, + "loss": 0.0026, + "step": 48670 + }, + { + "epoch": 15.03, + "learning_rate": 3.0662946370253277e-06, + "loss": 0.0021, + "step": 48671 + }, + { + "epoch": 15.03, + "learning_rate": 3.0659342698943828e-06, + "loss": 0.0024, + "step": 48672 + }, + { + "epoch": 15.03, + "learning_rate": 3.0655739201068e-06, + "loss": 0.0023, + "step": 48673 + }, + { + "epoch": 15.03, + "learning_rate": 3.0652135876634794e-06, + "loss": 0.0023, + "step": 48674 + }, + { + "epoch": 15.03, + "learning_rate": 3.0648532725653246e-06, + "loss": 0.0028, + "step": 48675 + }, + { + "epoch": 15.03, + "learning_rate": 3.064492974813239e-06, + "loss": 0.0028, + "step": 48676 + }, + { + "epoch": 15.03, + "learning_rate": 3.064132694408122e-06, + "loss": 0.0023, + "step": 48677 + }, + { + "epoch": 15.03, + "learning_rate": 3.063772431350871e-06, + "loss": 0.0025, + "step": 48678 + }, + { + "epoch": 15.03, + "learning_rate": 3.063412185642394e-06, + "loss": 0.0031, + "step": 48679 + }, + { + "epoch": 15.03, + "learning_rate": 3.0630519572835837e-06, + "loss": 0.0018, + "step": 48680 + }, + { + "epoch": 15.03, + "learning_rate": 3.062691746275347e-06, + "loss": 0.0026, + "step": 48681 + }, + { + "epoch": 15.03, + "learning_rate": 3.062331552618586e-06, + "loss": 0.0028, + "step": 48682 + }, + { + "epoch": 15.03, + "learning_rate": 3.061971376314199e-06, + "loss": 0.0027, + "step": 48683 + }, + { + "epoch": 15.03, + "learning_rate": 3.061611217363084e-06, + "loss": 0.0026, + "step": 48684 + }, + { + "epoch": 15.03, + "learning_rate": 3.061251075766145e-06, + "loss": 0.0027, + "step": 48685 + }, + { + "epoch": 15.04, + "learning_rate": 3.0608909515242855e-06, + "loss": 0.0026, + "step": 48686 + }, + { + "epoch": 15.04, + "learning_rate": 3.060530844638403e-06, + "loss": 0.0028, + "step": 48687 + }, + { + "epoch": 15.04, + "learning_rate": 3.0601707551093963e-06, + "loss": 0.0023, + "step": 48688 + }, + { + "epoch": 15.04, + "learning_rate": 3.0598106829381715e-06, + "loss": 0.0028, + "step": 48689 + }, + { + "epoch": 15.04, + "learning_rate": 3.059450628125622e-06, + "loss": 0.0022, + "step": 48690 + }, + { + "epoch": 15.04, + "learning_rate": 3.059090590672652e-06, + "loss": 0.0018, + "step": 48691 + }, + { + "epoch": 15.04, + "learning_rate": 3.0587305705801674e-06, + "loss": 0.003, + "step": 48692 + }, + { + "epoch": 15.04, + "learning_rate": 3.0583705678490615e-06, + "loss": 0.0017, + "step": 48693 + }, + { + "epoch": 15.04, + "learning_rate": 3.0580105824802353e-06, + "loss": 0.0022, + "step": 48694 + }, + { + "epoch": 15.04, + "learning_rate": 3.057650614474593e-06, + "loss": 0.0016, + "step": 48695 + }, + { + "epoch": 15.04, + "learning_rate": 3.0572906638330303e-06, + "loss": 0.0018, + "step": 48696 + }, + { + "epoch": 15.04, + "learning_rate": 3.056930730556452e-06, + "loss": 0.0027, + "step": 48697 + }, + { + "epoch": 15.04, + "learning_rate": 3.0565708146457575e-06, + "loss": 0.0015, + "step": 48698 + }, + { + "epoch": 15.04, + "learning_rate": 3.0562109161018416e-06, + "loss": 0.0018, + "step": 48699 + }, + { + "epoch": 15.04, + "learning_rate": 3.05585103492561e-06, + "loss": 0.0027, + "step": 48700 + }, + { + "epoch": 15.04, + "learning_rate": 3.0554911711179634e-06, + "loss": 0.0028, + "step": 48701 + }, + { + "epoch": 15.04, + "learning_rate": 3.0551313246797976e-06, + "loss": 0.0018, + "step": 48702 + }, + { + "epoch": 15.04, + "learning_rate": 3.0547714956120177e-06, + "loss": 0.0039, + "step": 48703 + }, + { + "epoch": 15.04, + "learning_rate": 3.0544116839155216e-06, + "loss": 0.0026, + "step": 48704 + }, + { + "epoch": 15.04, + "learning_rate": 3.054051889591204e-06, + "loss": 0.0019, + "step": 48705 + }, + { + "epoch": 15.04, + "learning_rate": 3.053692112639971e-06, + "loss": 0.0027, + "step": 48706 + }, + { + "epoch": 15.04, + "learning_rate": 3.0533323530627236e-06, + "loss": 0.0022, + "step": 48707 + }, + { + "epoch": 15.04, + "learning_rate": 3.0529726108603595e-06, + "loss": 0.0028, + "step": 48708 + }, + { + "epoch": 15.04, + "learning_rate": 3.0526128860337743e-06, + "loss": 0.0023, + "step": 48709 + }, + { + "epoch": 15.04, + "learning_rate": 3.052253178583874e-06, + "loss": 0.0033, + "step": 48710 + }, + { + "epoch": 15.04, + "learning_rate": 3.0518934885115537e-06, + "loss": 0.0022, + "step": 48711 + }, + { + "epoch": 15.04, + "learning_rate": 3.0515338158177145e-06, + "loss": 0.0024, + "step": 48712 + }, + { + "epoch": 15.04, + "learning_rate": 3.0511741605032595e-06, + "loss": 0.0027, + "step": 48713 + }, + { + "epoch": 15.04, + "learning_rate": 3.0508145225690855e-06, + "loss": 0.0022, + "step": 48714 + }, + { + "epoch": 15.04, + "learning_rate": 3.050454902016089e-06, + "loss": 0.0026, + "step": 48715 + }, + { + "epoch": 15.04, + "learning_rate": 3.0500952988451715e-06, + "loss": 0.0023, + "step": 48716 + }, + { + "epoch": 15.04, + "learning_rate": 3.049735713057237e-06, + "loss": 0.0029, + "step": 48717 + }, + { + "epoch": 15.05, + "learning_rate": 3.0493761446531812e-06, + "loss": 0.0028, + "step": 48718 + }, + { + "epoch": 15.05, + "learning_rate": 3.0490165936339e-06, + "loss": 0.0035, + "step": 48719 + }, + { + "epoch": 15.05, + "learning_rate": 3.0486570600002997e-06, + "loss": 0.0029, + "step": 48720 + }, + { + "epoch": 15.05, + "learning_rate": 3.0482975437532713e-06, + "loss": 0.003, + "step": 48721 + }, + { + "epoch": 15.05, + "learning_rate": 3.04793804489372e-06, + "loss": 0.0023, + "step": 48722 + }, + { + "epoch": 15.05, + "learning_rate": 3.0475785634225463e-06, + "loss": 0.0019, + "step": 48723 + }, + { + "epoch": 15.05, + "learning_rate": 3.047219099340647e-06, + "loss": 0.0024, + "step": 48724 + }, + { + "epoch": 15.05, + "learning_rate": 3.046859652648918e-06, + "loss": 0.0017, + "step": 48725 + }, + { + "epoch": 15.05, + "learning_rate": 3.046500223348263e-06, + "loss": 0.0026, + "step": 48726 + }, + { + "epoch": 15.05, + "learning_rate": 3.0461408114395773e-06, + "loss": 0.0024, + "step": 48727 + }, + { + "epoch": 15.05, + "learning_rate": 3.0457814169237644e-06, + "loss": 0.0026, + "step": 48728 + }, + { + "epoch": 15.05, + "learning_rate": 3.045422039801721e-06, + "loss": 0.0024, + "step": 48729 + }, + { + "epoch": 15.05, + "learning_rate": 3.045062680074342e-06, + "loss": 0.0025, + "step": 48730 + }, + { + "epoch": 15.05, + "learning_rate": 3.0447033377425294e-06, + "loss": 0.0025, + "step": 48731 + }, + { + "epoch": 15.05, + "learning_rate": 3.0443440128071853e-06, + "loss": 0.0016, + "step": 48732 + }, + { + "epoch": 15.05, + "learning_rate": 3.043984705269203e-06, + "loss": 0.0018, + "step": 48733 + }, + { + "epoch": 15.05, + "learning_rate": 3.0436254151294876e-06, + "loss": 0.0024, + "step": 48734 + }, + { + "epoch": 15.05, + "learning_rate": 3.043266142388932e-06, + "loss": 0.0023, + "step": 48735 + }, + { + "epoch": 15.05, + "learning_rate": 3.0429068870484344e-06, + "loss": 0.0022, + "step": 48736 + }, + { + "epoch": 15.05, + "learning_rate": 3.042547649108896e-06, + "loss": 0.0016, + "step": 48737 + }, + { + "epoch": 15.05, + "learning_rate": 3.042188428571217e-06, + "loss": 0.0029, + "step": 48738 + }, + { + "epoch": 15.05, + "learning_rate": 3.0418292254362947e-06, + "loss": 0.003, + "step": 48739 + }, + { + "epoch": 15.05, + "learning_rate": 3.0414700397050222e-06, + "loss": 0.0028, + "step": 48740 + }, + { + "epoch": 15.05, + "learning_rate": 3.0411108713783067e-06, + "loss": 0.0021, + "step": 48741 + }, + { + "epoch": 15.05, + "learning_rate": 3.040751720457038e-06, + "loss": 0.0019, + "step": 48742 + }, + { + "epoch": 15.05, + "learning_rate": 3.0403925869421193e-06, + "loss": 0.0021, + "step": 48743 + }, + { + "epoch": 15.05, + "learning_rate": 3.040033470834454e-06, + "loss": 0.0024, + "step": 48744 + }, + { + "epoch": 15.05, + "learning_rate": 3.0396743721349286e-06, + "loss": 0.0022, + "step": 48745 + }, + { + "epoch": 15.05, + "learning_rate": 3.0393152908444466e-06, + "loss": 0.0025, + "step": 48746 + }, + { + "epoch": 15.05, + "learning_rate": 3.038956226963906e-06, + "loss": 0.0022, + "step": 48747 + }, + { + "epoch": 15.05, + "learning_rate": 3.0385971804942106e-06, + "loss": 0.003, + "step": 48748 + }, + { + "epoch": 15.05, + "learning_rate": 3.038238151436251e-06, + "loss": 0.0026, + "step": 48749 + }, + { + "epoch": 15.05, + "learning_rate": 3.037879139790926e-06, + "loss": 0.0021, + "step": 48750 + }, + { + "epoch": 15.06, + "learning_rate": 3.0375201455591373e-06, + "loss": 0.0026, + "step": 48751 + }, + { + "epoch": 15.06, + "learning_rate": 3.0371611687417777e-06, + "loss": 0.0028, + "step": 48752 + }, + { + "epoch": 15.06, + "learning_rate": 3.0368022093397485e-06, + "loss": 0.0023, + "step": 48753 + }, + { + "epoch": 15.06, + "learning_rate": 3.0364432673539503e-06, + "loss": 0.002, + "step": 48754 + }, + { + "epoch": 15.06, + "learning_rate": 3.0360843427852772e-06, + "loss": 0.0027, + "step": 48755 + }, + { + "epoch": 15.06, + "learning_rate": 3.0357254356346234e-06, + "loss": 0.0025, + "step": 48756 + }, + { + "epoch": 15.06, + "learning_rate": 3.0353665459028946e-06, + "loss": 0.0023, + "step": 48757 + }, + { + "epoch": 15.06, + "learning_rate": 3.0350076735909808e-06, + "loss": 0.0021, + "step": 48758 + }, + { + "epoch": 15.06, + "learning_rate": 3.034648818699786e-06, + "loss": 0.0021, + "step": 48759 + }, + { + "epoch": 15.06, + "learning_rate": 3.0342899812302052e-06, + "loss": 0.002, + "step": 48760 + }, + { + "epoch": 15.06, + "learning_rate": 3.0339311611831325e-06, + "loss": 0.0018, + "step": 48761 + }, + { + "epoch": 15.06, + "learning_rate": 3.0335723585594678e-06, + "loss": 0.002, + "step": 48762 + }, + { + "epoch": 15.06, + "learning_rate": 3.033213573360113e-06, + "loss": 0.0024, + "step": 48763 + }, + { + "epoch": 15.06, + "learning_rate": 3.0328548055859584e-06, + "loss": 0.0025, + "step": 48764 + }, + { + "epoch": 15.06, + "learning_rate": 3.032496055237909e-06, + "loss": 0.0027, + "step": 48765 + }, + { + "epoch": 15.06, + "learning_rate": 3.0321373223168558e-06, + "loss": 0.003, + "step": 48766 + }, + { + "epoch": 15.06, + "learning_rate": 3.0317786068236964e-06, + "loss": 0.0025, + "step": 48767 + }, + { + "epoch": 15.06, + "learning_rate": 3.0314199087593287e-06, + "loss": 0.0028, + "step": 48768 + }, + { + "epoch": 15.06, + "learning_rate": 3.0310612281246545e-06, + "loss": 0.0022, + "step": 48769 + }, + { + "epoch": 15.06, + "learning_rate": 3.030702564920567e-06, + "loss": 0.0027, + "step": 48770 + }, + { + "epoch": 15.06, + "learning_rate": 3.030343919147961e-06, + "loss": 0.0036, + "step": 48771 + }, + { + "epoch": 15.06, + "learning_rate": 3.0299852908077387e-06, + "loss": 0.0017, + "step": 48772 + }, + { + "epoch": 15.06, + "learning_rate": 3.0296266799007912e-06, + "loss": 0.0021, + "step": 48773 + }, + { + "epoch": 15.06, + "learning_rate": 3.0292680864280176e-06, + "loss": 0.0027, + "step": 48774 + }, + { + "epoch": 15.06, + "learning_rate": 3.028909510390324e-06, + "loss": 0.0031, + "step": 48775 + }, + { + "epoch": 15.06, + "learning_rate": 3.0285509517885925e-06, + "loss": 0.0026, + "step": 48776 + }, + { + "epoch": 15.06, + "learning_rate": 3.028192410623726e-06, + "loss": 0.0024, + "step": 48777 + }, + { + "epoch": 15.06, + "learning_rate": 3.0278338868966216e-06, + "loss": 0.0029, + "step": 48778 + }, + { + "epoch": 15.06, + "learning_rate": 3.02747538060818e-06, + "loss": 0.0023, + "step": 48779 + }, + { + "epoch": 15.06, + "learning_rate": 3.027116891759294e-06, + "loss": 0.0021, + "step": 48780 + }, + { + "epoch": 15.06, + "learning_rate": 3.026758420350857e-06, + "loss": 0.0029, + "step": 48781 + }, + { + "epoch": 15.06, + "learning_rate": 3.026399966383773e-06, + "loss": 0.0017, + "step": 48782 + }, + { + "epoch": 15.07, + "learning_rate": 3.026041529858931e-06, + "loss": 0.0025, + "step": 48783 + }, + { + "epoch": 15.07, + "learning_rate": 3.025683110777231e-06, + "loss": 0.003, + "step": 48784 + }, + { + "epoch": 15.07, + "learning_rate": 3.0253247091395764e-06, + "loss": 0.0014, + "step": 48785 + }, + { + "epoch": 15.07, + "learning_rate": 3.02496632494685e-06, + "loss": 0.0018, + "step": 48786 + }, + { + "epoch": 15.07, + "learning_rate": 3.0246079581999545e-06, + "loss": 0.0023, + "step": 48787 + }, + { + "epoch": 15.07, + "learning_rate": 3.024249608899791e-06, + "loss": 0.0016, + "step": 48788 + }, + { + "epoch": 15.07, + "learning_rate": 3.0238912770472475e-06, + "loss": 0.0026, + "step": 48789 + }, + { + "epoch": 15.07, + "learning_rate": 3.0235329626432274e-06, + "loss": 0.0023, + "step": 48790 + }, + { + "epoch": 15.07, + "learning_rate": 3.0231746656886243e-06, + "loss": 0.0017, + "step": 48791 + }, + { + "epoch": 15.07, + "learning_rate": 3.022816386184331e-06, + "loss": 0.0026, + "step": 48792 + }, + { + "epoch": 15.07, + "learning_rate": 3.0224581241312456e-06, + "loss": 0.0028, + "step": 48793 + }, + { + "epoch": 15.07, + "learning_rate": 3.0220998795302692e-06, + "loss": 0.0027, + "step": 48794 + }, + { + "epoch": 15.07, + "learning_rate": 3.0217416523822928e-06, + "loss": 0.0026, + "step": 48795 + }, + { + "epoch": 15.07, + "learning_rate": 3.0213834426882103e-06, + "loss": 0.0021, + "step": 48796 + }, + { + "epoch": 15.07, + "learning_rate": 3.0210252504489235e-06, + "loss": 0.0022, + "step": 48797 + }, + { + "epoch": 15.07, + "learning_rate": 3.0206670756653235e-06, + "loss": 0.0034, + "step": 48798 + }, + { + "epoch": 15.07, + "learning_rate": 3.020308918338307e-06, + "loss": 0.002, + "step": 48799 + }, + { + "epoch": 15.07, + "learning_rate": 3.019950778468774e-06, + "loss": 0.0019, + "step": 48800 + }, + { + "epoch": 15.07, + "learning_rate": 3.0195926560576185e-06, + "loss": 0.0023, + "step": 48801 + }, + { + "epoch": 15.07, + "learning_rate": 3.0192345511057295e-06, + "loss": 0.0028, + "step": 48802 + }, + { + "epoch": 15.07, + "learning_rate": 3.018876463614013e-06, + "loss": 0.0024, + "step": 48803 + }, + { + "epoch": 15.07, + "learning_rate": 3.0185183935833564e-06, + "loss": 0.0037, + "step": 48804 + }, + { + "epoch": 15.07, + "learning_rate": 3.018160341014662e-06, + "loss": 0.0029, + "step": 48805 + }, + { + "epoch": 15.07, + "learning_rate": 3.0178023059088214e-06, + "loss": 0.0018, + "step": 48806 + }, + { + "epoch": 15.07, + "learning_rate": 3.0174442882667275e-06, + "loss": 0.002, + "step": 48807 + }, + { + "epoch": 15.07, + "learning_rate": 3.017086288089279e-06, + "loss": 0.0025, + "step": 48808 + }, + { + "epoch": 15.07, + "learning_rate": 3.0167283053773743e-06, + "loss": 0.0025, + "step": 48809 + }, + { + "epoch": 15.07, + "learning_rate": 3.0163703401319034e-06, + "loss": 0.0024, + "step": 48810 + }, + { + "epoch": 15.07, + "learning_rate": 3.0160123923537663e-06, + "loss": 0.0022, + "step": 48811 + }, + { + "epoch": 15.07, + "learning_rate": 3.0156544620438534e-06, + "loss": 0.0031, + "step": 48812 + }, + { + "epoch": 15.07, + "learning_rate": 3.0152965492030662e-06, + "loss": 0.0024, + "step": 48813 + }, + { + "epoch": 15.07, + "learning_rate": 3.014938653832292e-06, + "loss": 0.0025, + "step": 48814 + }, + { + "epoch": 15.07, + "learning_rate": 3.0145807759324343e-06, + "loss": 0.0022, + "step": 48815 + }, + { + "epoch": 15.08, + "learning_rate": 3.0142229155043832e-06, + "loss": 0.0017, + "step": 48816 + }, + { + "epoch": 15.08, + "learning_rate": 3.0138650725490328e-06, + "loss": 0.0021, + "step": 48817 + }, + { + "epoch": 15.08, + "learning_rate": 3.0135072470672787e-06, + "loss": 0.0034, + "step": 48818 + }, + { + "epoch": 15.08, + "learning_rate": 3.0131494390600215e-06, + "loss": 0.0019, + "step": 48819 + }, + { + "epoch": 15.08, + "learning_rate": 3.012791648528147e-06, + "loss": 0.0014, + "step": 48820 + }, + { + "epoch": 15.08, + "learning_rate": 3.01243387547256e-06, + "loss": 0.0025, + "step": 48821 + }, + { + "epoch": 15.08, + "learning_rate": 3.0120761198941494e-06, + "loss": 0.0028, + "step": 48822 + }, + { + "epoch": 15.08, + "learning_rate": 3.011718381793808e-06, + "loss": 0.0026, + "step": 48823 + }, + { + "epoch": 15.08, + "learning_rate": 3.0113606611724343e-06, + "loss": 0.002, + "step": 48824 + }, + { + "epoch": 15.08, + "learning_rate": 3.0110029580309243e-06, + "loss": 0.0019, + "step": 48825 + }, + { + "epoch": 15.08, + "learning_rate": 3.0106452723701707e-06, + "loss": 0.002, + "step": 48826 + }, + { + "epoch": 15.08, + "learning_rate": 3.0102876041910658e-06, + "loss": 0.0027, + "step": 48827 + }, + { + "epoch": 15.08, + "learning_rate": 3.0099299534945083e-06, + "loss": 0.0028, + "step": 48828 + }, + { + "epoch": 15.08, + "learning_rate": 3.0095723202813885e-06, + "loss": 0.0026, + "step": 48829 + }, + { + "epoch": 15.08, + "learning_rate": 3.0092147045526033e-06, + "loss": 0.0025, + "step": 48830 + }, + { + "epoch": 15.08, + "learning_rate": 3.00885710630905e-06, + "loss": 0.0024, + "step": 48831 + }, + { + "epoch": 15.08, + "learning_rate": 3.0084995255516204e-06, + "loss": 0.0025, + "step": 48832 + }, + { + "epoch": 15.08, + "learning_rate": 3.0081419622812056e-06, + "loss": 0.0015, + "step": 48833 + }, + { + "epoch": 15.08, + "learning_rate": 3.0077844164987068e-06, + "loss": 0.0013, + "step": 48834 + }, + { + "epoch": 15.08, + "learning_rate": 3.0074268882050107e-06, + "loss": 0.0025, + "step": 48835 + }, + { + "epoch": 15.08, + "learning_rate": 3.0070693774010173e-06, + "loss": 0.0026, + "step": 48836 + }, + { + "epoch": 15.08, + "learning_rate": 3.0067118840876208e-06, + "loss": 0.0023, + "step": 48837 + }, + { + "epoch": 15.08, + "learning_rate": 3.006354408265709e-06, + "loss": 0.0017, + "step": 48838 + }, + { + "epoch": 15.08, + "learning_rate": 3.0059969499361806e-06, + "loss": 0.0027, + "step": 48839 + }, + { + "epoch": 15.08, + "learning_rate": 3.0056395090999322e-06, + "loss": 0.0028, + "step": 48840 + }, + { + "epoch": 15.08, + "learning_rate": 3.005282085757852e-06, + "loss": 0.0026, + "step": 48841 + }, + { + "epoch": 15.08, + "learning_rate": 3.0049246799108413e-06, + "loss": 0.0026, + "step": 48842 + }, + { + "epoch": 15.08, + "learning_rate": 3.004567291559789e-06, + "loss": 0.0037, + "step": 48843 + }, + { + "epoch": 15.08, + "learning_rate": 3.0042099207055873e-06, + "loss": 0.0026, + "step": 48844 + }, + { + "epoch": 15.08, + "learning_rate": 3.0038525673491315e-06, + "loss": 0.0026, + "step": 48845 + }, + { + "epoch": 15.08, + "learning_rate": 3.00349523149132e-06, + "loss": 0.0022, + "step": 48846 + }, + { + "epoch": 15.08, + "learning_rate": 3.003137913133043e-06, + "loss": 0.0026, + "step": 48847 + }, + { + "epoch": 15.09, + "learning_rate": 3.002780612275191e-06, + "loss": 0.0022, + "step": 48848 + }, + { + "epoch": 15.09, + "learning_rate": 3.002423328918662e-06, + "loss": 0.0039, + "step": 48849 + }, + { + "epoch": 15.09, + "learning_rate": 3.0020660630643506e-06, + "loss": 0.0023, + "step": 48850 + }, + { + "epoch": 15.09, + "learning_rate": 3.001708814713146e-06, + "loss": 0.0049, + "step": 48851 + }, + { + "epoch": 15.09, + "learning_rate": 3.001351583865946e-06, + "loss": 0.0027, + "step": 48852 + }, + { + "epoch": 15.09, + "learning_rate": 3.000994370523642e-06, + "loss": 0.0031, + "step": 48853 + }, + { + "epoch": 15.09, + "learning_rate": 3.0006371746871255e-06, + "loss": 0.0023, + "step": 48854 + }, + { + "epoch": 15.09, + "learning_rate": 3.0002799963572914e-06, + "loss": 0.0026, + "step": 48855 + }, + { + "epoch": 15.09, + "learning_rate": 2.9999228355350375e-06, + "loss": 0.0023, + "step": 48856 + }, + { + "epoch": 15.09, + "learning_rate": 2.9995656922212536e-06, + "loss": 0.0027, + "step": 48857 + }, + { + "epoch": 15.09, + "learning_rate": 2.999208566416828e-06, + "loss": 0.0023, + "step": 48858 + }, + { + "epoch": 15.09, + "learning_rate": 2.9988514581226636e-06, + "loss": 0.0021, + "step": 48859 + }, + { + "epoch": 15.09, + "learning_rate": 2.998494367339644e-06, + "loss": 0.0031, + "step": 48860 + }, + { + "epoch": 15.09, + "learning_rate": 2.9981372940686682e-06, + "loss": 0.0027, + "step": 48861 + }, + { + "epoch": 15.09, + "learning_rate": 2.9977802383106303e-06, + "loss": 0.0026, + "step": 48862 + }, + { + "epoch": 15.09, + "learning_rate": 2.9974232000664215e-06, + "loss": 0.0027, + "step": 48863 + }, + { + "epoch": 15.09, + "learning_rate": 2.9970661793369314e-06, + "loss": 0.0028, + "step": 48864 + }, + { + "epoch": 15.09, + "learning_rate": 2.9967091761230594e-06, + "loss": 0.0029, + "step": 48865 + }, + { + "epoch": 15.09, + "learning_rate": 2.996352190425691e-06, + "loss": 0.0025, + "step": 48866 + }, + { + "epoch": 15.09, + "learning_rate": 2.995995222245727e-06, + "loss": 0.0033, + "step": 48867 + }, + { + "epoch": 15.09, + "learning_rate": 2.995638271584056e-06, + "loss": 0.0023, + "step": 48868 + }, + { + "epoch": 15.09, + "learning_rate": 2.995281338441569e-06, + "loss": 0.0022, + "step": 48869 + }, + { + "epoch": 15.09, + "learning_rate": 2.99492442281916e-06, + "loss": 0.0016, + "step": 48870 + }, + { + "epoch": 15.09, + "learning_rate": 2.994567524717726e-06, + "loss": 0.0028, + "step": 48871 + }, + { + "epoch": 15.09, + "learning_rate": 2.9942106441381537e-06, + "loss": 0.0018, + "step": 48872 + }, + { + "epoch": 15.09, + "learning_rate": 2.9938537810813408e-06, + "loss": 0.0021, + "step": 48873 + }, + { + "epoch": 15.09, + "learning_rate": 2.993496935548178e-06, + "loss": 0.0024, + "step": 48874 + }, + { + "epoch": 15.09, + "learning_rate": 2.9931401075395537e-06, + "loss": 0.0022, + "step": 48875 + }, + { + "epoch": 15.09, + "learning_rate": 2.9927832970563644e-06, + "loss": 0.003, + "step": 48876 + }, + { + "epoch": 15.09, + "learning_rate": 2.9924265040995047e-06, + "loss": 0.0057, + "step": 48877 + }, + { + "epoch": 15.09, + "learning_rate": 2.9920697286698654e-06, + "loss": 0.0031, + "step": 48878 + }, + { + "epoch": 15.09, + "learning_rate": 2.9917129707683333e-06, + "loss": 0.0021, + "step": 48879 + }, + { + "epoch": 15.1, + "learning_rate": 2.9913562303958067e-06, + "loss": 0.0027, + "step": 48880 + }, + { + "epoch": 15.1, + "learning_rate": 2.9909995075531784e-06, + "loss": 0.0025, + "step": 48881 + }, + { + "epoch": 15.1, + "learning_rate": 2.990642802241336e-06, + "loss": 0.0024, + "step": 48882 + }, + { + "epoch": 15.1, + "learning_rate": 2.990286114461177e-06, + "loss": 0.0022, + "step": 48883 + }, + { + "epoch": 15.1, + "learning_rate": 2.9899294442135917e-06, + "loss": 0.0017, + "step": 48884 + }, + { + "epoch": 15.1, + "learning_rate": 2.989572791499469e-06, + "loss": 0.0029, + "step": 48885 + }, + { + "epoch": 15.1, + "learning_rate": 2.989216156319702e-06, + "loss": 0.0027, + "step": 48886 + }, + { + "epoch": 15.1, + "learning_rate": 2.988859538675187e-06, + "loss": 0.002, + "step": 48887 + }, + { + "epoch": 15.1, + "learning_rate": 2.9885029385668142e-06, + "loss": 0.0025, + "step": 48888 + }, + { + "epoch": 15.1, + "learning_rate": 2.9881463559954716e-06, + "loss": 0.0031, + "step": 48889 + }, + { + "epoch": 15.1, + "learning_rate": 2.987789790962056e-06, + "loss": 0.0023, + "step": 48890 + }, + { + "epoch": 15.1, + "learning_rate": 2.9874332434674537e-06, + "loss": 0.0028, + "step": 48891 + }, + { + "epoch": 15.1, + "learning_rate": 2.98707671351256e-06, + "loss": 0.0025, + "step": 48892 + }, + { + "epoch": 15.1, + "learning_rate": 2.9867202010982732e-06, + "loss": 0.0025, + "step": 48893 + }, + { + "epoch": 15.1, + "learning_rate": 2.9863637062254723e-06, + "loss": 0.0023, + "step": 48894 + }, + { + "epoch": 15.1, + "learning_rate": 2.986007228895055e-06, + "loss": 0.0028, + "step": 48895 + }, + { + "epoch": 15.1, + "learning_rate": 2.985650769107915e-06, + "loss": 0.0022, + "step": 48896 + }, + { + "epoch": 15.1, + "learning_rate": 2.9852943268649392e-06, + "loss": 0.0018, + "step": 48897 + }, + { + "epoch": 15.1, + "learning_rate": 2.9849379021670244e-06, + "loss": 0.0028, + "step": 48898 + }, + { + "epoch": 15.1, + "learning_rate": 2.9845814950150608e-06, + "loss": 0.0027, + "step": 48899 + }, + { + "epoch": 15.1, + "learning_rate": 2.9842251054099335e-06, + "loss": 0.0028, + "step": 48900 + }, + { + "epoch": 15.1, + "learning_rate": 2.9838687333525397e-06, + "loss": 0.0027, + "step": 48901 + }, + { + "epoch": 15.1, + "learning_rate": 2.9835123788437737e-06, + "loss": 0.0021, + "step": 48902 + }, + { + "epoch": 15.1, + "learning_rate": 2.983156041884522e-06, + "loss": 0.0031, + "step": 48903 + }, + { + "epoch": 15.1, + "learning_rate": 2.9827997224756735e-06, + "loss": 0.003, + "step": 48904 + }, + { + "epoch": 15.1, + "learning_rate": 2.9824434206181265e-06, + "loss": 0.002, + "step": 48905 + }, + { + "epoch": 15.1, + "learning_rate": 2.9820871363127645e-06, + "loss": 0.0016, + "step": 48906 + }, + { + "epoch": 15.1, + "learning_rate": 2.981730869560484e-06, + "loss": 0.0026, + "step": 48907 + }, + { + "epoch": 15.1, + "learning_rate": 2.9813746203621763e-06, + "loss": 0.0017, + "step": 48908 + }, + { + "epoch": 15.1, + "learning_rate": 2.9810183887187317e-06, + "loss": 0.0021, + "step": 48909 + }, + { + "epoch": 15.1, + "learning_rate": 2.9806621746310373e-06, + "loss": 0.002, + "step": 48910 + }, + { + "epoch": 15.1, + "learning_rate": 2.9803059780999867e-06, + "loss": 0.0028, + "step": 48911 + }, + { + "epoch": 15.1, + "learning_rate": 2.979949799126474e-06, + "loss": 0.0015, + "step": 48912 + }, + { + "epoch": 15.11, + "learning_rate": 2.9795936377113865e-06, + "loss": 0.0026, + "step": 48913 + }, + { + "epoch": 15.11, + "learning_rate": 2.9792374938556144e-06, + "loss": 0.0022, + "step": 48914 + }, + { + "epoch": 15.11, + "learning_rate": 2.9788813675600512e-06, + "loss": 0.0028, + "step": 48915 + }, + { + "epoch": 15.11, + "learning_rate": 2.9785252588255843e-06, + "loss": 0.0018, + "step": 48916 + }, + { + "epoch": 15.11, + "learning_rate": 2.9781691676531066e-06, + "loss": 0.0027, + "step": 48917 + }, + { + "epoch": 15.11, + "learning_rate": 2.977813094043511e-06, + "loss": 0.003, + "step": 48918 + }, + { + "epoch": 15.11, + "learning_rate": 2.9774570379976864e-06, + "loss": 0.0019, + "step": 48919 + }, + { + "epoch": 15.11, + "learning_rate": 2.977100999516518e-06, + "loss": 0.0021, + "step": 48920 + }, + { + "epoch": 15.11, + "learning_rate": 2.976744978600905e-06, + "loss": 0.002, + "step": 48921 + }, + { + "epoch": 15.11, + "learning_rate": 2.9763889752517305e-06, + "loss": 0.0027, + "step": 48922 + }, + { + "epoch": 15.11, + "learning_rate": 2.976032989469891e-06, + "loss": 0.0027, + "step": 48923 + }, + { + "epoch": 15.11, + "learning_rate": 2.9756770212562746e-06, + "loss": 0.0031, + "step": 48924 + }, + { + "epoch": 15.11, + "learning_rate": 2.9753210706117684e-06, + "loss": 0.002, + "step": 48925 + }, + { + "epoch": 15.11, + "learning_rate": 2.9749651375372645e-06, + "loss": 0.003, + "step": 48926 + }, + { + "epoch": 15.11, + "learning_rate": 2.9746092220336573e-06, + "loss": 0.0038, + "step": 48927 + }, + { + "epoch": 15.11, + "learning_rate": 2.9742533241018313e-06, + "loss": 0.0027, + "step": 48928 + }, + { + "epoch": 15.11, + "learning_rate": 2.9738974437426816e-06, + "loss": 0.0018, + "step": 48929 + }, + { + "epoch": 15.11, + "learning_rate": 2.9735415809570965e-06, + "loss": 0.0029, + "step": 48930 + }, + { + "epoch": 15.11, + "learning_rate": 2.9731857357459626e-06, + "loss": 0.0035, + "step": 48931 + }, + { + "epoch": 15.11, + "learning_rate": 2.972829908110172e-06, + "loss": 0.0028, + "step": 48932 + }, + { + "epoch": 15.11, + "learning_rate": 2.9724740980506185e-06, + "loss": 0.0025, + "step": 48933 + }, + { + "epoch": 15.11, + "learning_rate": 2.972118305568189e-06, + "loss": 0.0022, + "step": 48934 + }, + { + "epoch": 15.11, + "learning_rate": 2.971762530663771e-06, + "loss": 0.0023, + "step": 48935 + }, + { + "epoch": 15.11, + "learning_rate": 2.971406773338259e-06, + "loss": 0.0036, + "step": 48936 + }, + { + "epoch": 15.11, + "learning_rate": 2.971051033592538e-06, + "loss": 0.0027, + "step": 48937 + }, + { + "epoch": 15.11, + "learning_rate": 2.9706953114275007e-06, + "loss": 0.0023, + "step": 48938 + }, + { + "epoch": 15.11, + "learning_rate": 2.970339606844039e-06, + "loss": 0.0024, + "step": 48939 + }, + { + "epoch": 15.11, + "learning_rate": 2.96998391984304e-06, + "loss": 0.0014, + "step": 48940 + }, + { + "epoch": 15.11, + "learning_rate": 2.9696282504253915e-06, + "loss": 0.0023, + "step": 48941 + }, + { + "epoch": 15.11, + "learning_rate": 2.9692725985919833e-06, + "loss": 0.0025, + "step": 48942 + }, + { + "epoch": 15.11, + "learning_rate": 2.968916964343711e-06, + "loss": 0.0023, + "step": 48943 + }, + { + "epoch": 15.11, + "learning_rate": 2.968561347681459e-06, + "loss": 0.0023, + "step": 48944 + }, + { + "epoch": 15.12, + "learning_rate": 2.9682057486061155e-06, + "loss": 0.0023, + "step": 48945 + }, + { + "epoch": 15.12, + "learning_rate": 2.9678501671185746e-06, + "loss": 0.0031, + "step": 48946 + }, + { + "epoch": 15.12, + "learning_rate": 2.9674946032197195e-06, + "loss": 0.0022, + "step": 48947 + }, + { + "epoch": 15.12, + "learning_rate": 2.967139056910443e-06, + "loss": 0.0028, + "step": 48948 + }, + { + "epoch": 15.12, + "learning_rate": 2.966783528191638e-06, + "loss": 0.0023, + "step": 48949 + }, + { + "epoch": 15.12, + "learning_rate": 2.966428017064189e-06, + "loss": 0.0026, + "step": 48950 + }, + { + "epoch": 15.12, + "learning_rate": 2.9660725235289846e-06, + "loss": 0.0022, + "step": 48951 + }, + { + "epoch": 15.12, + "learning_rate": 2.965717047586918e-06, + "loss": 0.0024, + "step": 48952 + }, + { + "epoch": 15.12, + "learning_rate": 2.9653615892388734e-06, + "loss": 0.0025, + "step": 48953 + }, + { + "epoch": 15.12, + "learning_rate": 2.965006148485746e-06, + "loss": 0.0024, + "step": 48954 + }, + { + "epoch": 15.12, + "learning_rate": 2.9646507253284206e-06, + "loss": 0.0026, + "step": 48955 + }, + { + "epoch": 15.12, + "learning_rate": 2.964295319767784e-06, + "loss": 0.0036, + "step": 48956 + }, + { + "epoch": 15.12, + "learning_rate": 2.963939931804728e-06, + "loss": 0.0019, + "step": 48957 + }, + { + "epoch": 15.12, + "learning_rate": 2.9635845614401447e-06, + "loss": 0.0024, + "step": 48958 + }, + { + "epoch": 15.12, + "learning_rate": 2.963229208674917e-06, + "loss": 0.0019, + "step": 48959 + }, + { + "epoch": 15.12, + "learning_rate": 2.9628738735099393e-06, + "loss": 0.0038, + "step": 48960 + }, + { + "epoch": 15.12, + "learning_rate": 2.9625185559460978e-06, + "loss": 0.0019, + "step": 48961 + }, + { + "epoch": 15.12, + "learning_rate": 2.9621632559842773e-06, + "loss": 0.0028, + "step": 48962 + }, + { + "epoch": 15.12, + "learning_rate": 2.96180797362537e-06, + "loss": 0.0026, + "step": 48963 + }, + { + "epoch": 15.12, + "learning_rate": 2.9614527088702682e-06, + "loss": 0.003, + "step": 48964 + }, + { + "epoch": 15.12, + "learning_rate": 2.961097461719857e-06, + "loss": 0.0022, + "step": 48965 + }, + { + "epoch": 15.12, + "learning_rate": 2.9607422321750213e-06, + "loss": 0.0034, + "step": 48966 + }, + { + "epoch": 15.12, + "learning_rate": 2.9603870202366568e-06, + "loss": 0.0026, + "step": 48967 + }, + { + "epoch": 15.12, + "learning_rate": 2.960031825905645e-06, + "loss": 0.0024, + "step": 48968 + }, + { + "epoch": 15.12, + "learning_rate": 2.9596766491828775e-06, + "loss": 0.0033, + "step": 48969 + }, + { + "epoch": 15.12, + "learning_rate": 2.959321490069246e-06, + "loss": 0.0025, + "step": 48970 + }, + { + "epoch": 15.12, + "learning_rate": 2.958966348565636e-06, + "loss": 0.0024, + "step": 48971 + }, + { + "epoch": 15.12, + "learning_rate": 2.9586112246729317e-06, + "loss": 0.0021, + "step": 48972 + }, + { + "epoch": 15.12, + "learning_rate": 2.9582561183920276e-06, + "loss": 0.0019, + "step": 48973 + }, + { + "epoch": 15.12, + "learning_rate": 2.9579010297238073e-06, + "loss": 0.0021, + "step": 48974 + }, + { + "epoch": 15.12, + "learning_rate": 2.9575459586691633e-06, + "loss": 0.0021, + "step": 48975 + }, + { + "epoch": 15.12, + "learning_rate": 2.957190905228978e-06, + "loss": 0.0026, + "step": 48976 + }, + { + "epoch": 15.12, + "learning_rate": 2.9568358694041467e-06, + "loss": 0.0021, + "step": 48977 + }, + { + "epoch": 15.13, + "learning_rate": 2.95648085119555e-06, + "loss": 0.0023, + "step": 48978 + }, + { + "epoch": 15.13, + "learning_rate": 2.9561258506040793e-06, + "loss": 0.0025, + "step": 48979 + }, + { + "epoch": 15.13, + "learning_rate": 2.9557708676306262e-06, + "loss": 0.002, + "step": 48980 + }, + { + "epoch": 15.13, + "learning_rate": 2.9554159022760743e-06, + "loss": 0.0027, + "step": 48981 + }, + { + "epoch": 15.13, + "learning_rate": 2.955060954541309e-06, + "loss": 0.0031, + "step": 48982 + }, + { + "epoch": 15.13, + "learning_rate": 2.954706024427224e-06, + "loss": 0.0029, + "step": 48983 + }, + { + "epoch": 15.13, + "learning_rate": 2.9543511119347024e-06, + "loss": 0.0026, + "step": 48984 + }, + { + "epoch": 15.13, + "learning_rate": 2.953996217064635e-06, + "loss": 0.0024, + "step": 48985 + }, + { + "epoch": 15.13, + "learning_rate": 2.95364133981791e-06, + "loss": 0.0026, + "step": 48986 + }, + { + "epoch": 15.13, + "learning_rate": 2.9532864801954086e-06, + "loss": 0.0025, + "step": 48987 + }, + { + "epoch": 15.13, + "learning_rate": 2.9529316381980235e-06, + "loss": 0.0022, + "step": 48988 + }, + { + "epoch": 15.13, + "learning_rate": 2.9525768138266453e-06, + "loss": 0.0021, + "step": 48989 + }, + { + "epoch": 15.13, + "learning_rate": 2.952222007082154e-06, + "loss": 0.0026, + "step": 48990 + }, + { + "epoch": 15.13, + "learning_rate": 2.951867217965444e-06, + "loss": 0.0045, + "step": 48991 + }, + { + "epoch": 15.13, + "learning_rate": 2.9515124464774e-06, + "loss": 0.0021, + "step": 48992 + }, + { + "epoch": 15.13, + "learning_rate": 2.9511576926189054e-06, + "loss": 0.0021, + "step": 48993 + }, + { + "epoch": 15.13, + "learning_rate": 2.9508029563908527e-06, + "loss": 0.0029, + "step": 48994 + }, + { + "epoch": 15.13, + "learning_rate": 2.950448237794129e-06, + "loss": 0.0029, + "step": 48995 + }, + { + "epoch": 15.13, + "learning_rate": 2.9500935368296203e-06, + "loss": 0.0017, + "step": 48996 + }, + { + "epoch": 15.13, + "learning_rate": 2.9497388534982097e-06, + "loss": 0.0018, + "step": 48997 + }, + { + "epoch": 15.13, + "learning_rate": 2.949384187800792e-06, + "loss": 0.0028, + "step": 48998 + }, + { + "epoch": 15.13, + "learning_rate": 2.9490295397382474e-06, + "loss": 0.002, + "step": 48999 + }, + { + "epoch": 15.13, + "learning_rate": 2.948674909311465e-06, + "loss": 0.003, + "step": 49000 + }, + { + "epoch": 15.13, + "learning_rate": 2.9483202965213396e-06, + "loss": 0.0025, + "step": 49001 + }, + { + "epoch": 15.13, + "learning_rate": 2.9479657013687456e-06, + "loss": 0.0031, + "step": 49002 + }, + { + "epoch": 15.13, + "learning_rate": 2.9476111238545755e-06, + "loss": 0.0019, + "step": 49003 + }, + { + "epoch": 15.13, + "learning_rate": 2.947256563979719e-06, + "loss": 0.0022, + "step": 49004 + }, + { + "epoch": 15.13, + "learning_rate": 2.946902021745057e-06, + "loss": 0.0021, + "step": 49005 + }, + { + "epoch": 15.13, + "learning_rate": 2.946547497151483e-06, + "loss": 0.0022, + "step": 49006 + }, + { + "epoch": 15.13, + "learning_rate": 2.9461929901998765e-06, + "loss": 0.0051, + "step": 49007 + }, + { + "epoch": 15.13, + "learning_rate": 2.9458385008911305e-06, + "loss": 0.002, + "step": 49008 + }, + { + "epoch": 15.13, + "learning_rate": 2.9454840292261264e-06, + "loss": 0.0023, + "step": 49009 + }, + { + "epoch": 15.14, + "learning_rate": 2.945129575205754e-06, + "loss": 0.0034, + "step": 49010 + }, + { + "epoch": 15.14, + "learning_rate": 2.9447751388309054e-06, + "loss": 0.0024, + "step": 49011 + }, + { + "epoch": 15.14, + "learning_rate": 2.9444207201024545e-06, + "loss": 0.0018, + "step": 49012 + }, + { + "epoch": 15.14, + "learning_rate": 2.9440663190212938e-06, + "loss": 0.0023, + "step": 49013 + }, + { + "epoch": 15.14, + "learning_rate": 2.9437119355883136e-06, + "loss": 0.0027, + "step": 49014 + }, + { + "epoch": 15.14, + "learning_rate": 2.9433575698043935e-06, + "loss": 0.0026, + "step": 49015 + }, + { + "epoch": 15.14, + "learning_rate": 2.9430032216704263e-06, + "loss": 0.0024, + "step": 49016 + }, + { + "epoch": 15.14, + "learning_rate": 2.942648891187295e-06, + "loss": 0.0024, + "step": 49017 + }, + { + "epoch": 15.14, + "learning_rate": 2.9422945783558832e-06, + "loss": 0.0021, + "step": 49018 + }, + { + "epoch": 15.14, + "learning_rate": 2.9419402831770806e-06, + "loss": 0.0023, + "step": 49019 + }, + { + "epoch": 15.14, + "learning_rate": 2.941586005651775e-06, + "loss": 0.0022, + "step": 49020 + }, + { + "epoch": 15.14, + "learning_rate": 2.9412317457808472e-06, + "loss": 0.002, + "step": 49021 + }, + { + "epoch": 15.14, + "learning_rate": 2.9408775035651894e-06, + "loss": 0.0018, + "step": 49022 + }, + { + "epoch": 15.14, + "learning_rate": 2.9405232790056835e-06, + "loss": 0.0022, + "step": 49023 + }, + { + "epoch": 15.14, + "learning_rate": 2.940169072103215e-06, + "loss": 0.0031, + "step": 49024 + }, + { + "epoch": 15.14, + "learning_rate": 2.9398148828586705e-06, + "loss": 0.0021, + "step": 49025 + }, + { + "epoch": 15.14, + "learning_rate": 2.93946071127294e-06, + "loss": 0.0031, + "step": 49026 + }, + { + "epoch": 15.14, + "learning_rate": 2.9391065573469056e-06, + "loss": 0.0022, + "step": 49027 + }, + { + "epoch": 15.14, + "learning_rate": 2.938752421081451e-06, + "loss": 0.0028, + "step": 49028 + }, + { + "epoch": 15.14, + "learning_rate": 2.9383983024774666e-06, + "loss": 0.0026, + "step": 49029 + }, + { + "epoch": 15.14, + "learning_rate": 2.9380442015358333e-06, + "loss": 0.0024, + "step": 49030 + }, + { + "epoch": 15.14, + "learning_rate": 2.93769011825744e-06, + "loss": 0.0026, + "step": 49031 + }, + { + "epoch": 15.14, + "learning_rate": 2.937336052643178e-06, + "loss": 0.0022, + "step": 49032 + }, + { + "epoch": 15.14, + "learning_rate": 2.9369820046939202e-06, + "loss": 0.0018, + "step": 49033 + }, + { + "epoch": 15.14, + "learning_rate": 2.9366279744105586e-06, + "loss": 0.0027, + "step": 49034 + }, + { + "epoch": 15.14, + "learning_rate": 2.9362739617939816e-06, + "loss": 0.0023, + "step": 49035 + }, + { + "epoch": 15.14, + "learning_rate": 2.935919966845069e-06, + "loss": 0.0025, + "step": 49036 + }, + { + "epoch": 15.14, + "learning_rate": 2.9355659895647127e-06, + "loss": 0.0027, + "step": 49037 + }, + { + "epoch": 15.14, + "learning_rate": 2.9352120299537936e-06, + "loss": 0.0031, + "step": 49038 + }, + { + "epoch": 15.14, + "learning_rate": 2.934858088013194e-06, + "loss": 0.0019, + "step": 49039 + }, + { + "epoch": 15.14, + "learning_rate": 2.9345041637438033e-06, + "loss": 0.0025, + "step": 49040 + }, + { + "epoch": 15.14, + "learning_rate": 2.9341502571465063e-06, + "loss": 0.0021, + "step": 49041 + }, + { + "epoch": 15.15, + "learning_rate": 2.9337963682221947e-06, + "loss": 0.0023, + "step": 49042 + }, + { + "epoch": 15.15, + "learning_rate": 2.9334424969717413e-06, + "loss": 0.0032, + "step": 49043 + }, + { + "epoch": 15.15, + "learning_rate": 2.933088643396037e-06, + "loss": 0.002, + "step": 49044 + }, + { + "epoch": 15.15, + "learning_rate": 2.9327348074959705e-06, + "loss": 0.0023, + "step": 49045 + }, + { + "epoch": 15.15, + "learning_rate": 2.9323809892724185e-06, + "loss": 0.0022, + "step": 49046 + }, + { + "epoch": 15.15, + "learning_rate": 2.9320271887262753e-06, + "loss": 0.0025, + "step": 49047 + }, + { + "epoch": 15.15, + "learning_rate": 2.9316734058584207e-06, + "loss": 0.0023, + "step": 49048 + }, + { + "epoch": 15.15, + "learning_rate": 2.9313196406697374e-06, + "loss": 0.003, + "step": 49049 + }, + { + "epoch": 15.15, + "learning_rate": 2.930965893161112e-06, + "loss": 0.0022, + "step": 49050 + }, + { + "epoch": 15.15, + "learning_rate": 2.930612163333434e-06, + "loss": 0.0025, + "step": 49051 + }, + { + "epoch": 15.15, + "learning_rate": 2.930258451187584e-06, + "loss": 0.0027, + "step": 49052 + }, + { + "epoch": 15.15, + "learning_rate": 2.9299047567244444e-06, + "loss": 0.0027, + "step": 49053 + }, + { + "epoch": 15.15, + "learning_rate": 2.9295510799449055e-06, + "loss": 0.0025, + "step": 49054 + }, + { + "epoch": 15.15, + "learning_rate": 2.9291974208498453e-06, + "loss": 0.0018, + "step": 49055 + }, + { + "epoch": 15.15, + "learning_rate": 2.9288437794401525e-06, + "loss": 0.0019, + "step": 49056 + }, + { + "epoch": 15.15, + "learning_rate": 2.9284901557167144e-06, + "loss": 0.0025, + "step": 49057 + }, + { + "epoch": 15.15, + "learning_rate": 2.9281365496804117e-06, + "loss": 0.0024, + "step": 49058 + }, + { + "epoch": 15.15, + "learning_rate": 2.9277829613321264e-06, + "loss": 0.0025, + "step": 49059 + }, + { + "epoch": 15.15, + "learning_rate": 2.927429390672748e-06, + "loss": 0.0025, + "step": 49060 + }, + { + "epoch": 15.15, + "learning_rate": 2.927075837703157e-06, + "loss": 0.0026, + "step": 49061 + }, + { + "epoch": 15.15, + "learning_rate": 2.926722302424242e-06, + "loss": 0.0022, + "step": 49062 + }, + { + "epoch": 15.15, + "learning_rate": 2.9263687848368837e-06, + "loss": 0.0019, + "step": 49063 + }, + { + "epoch": 15.15, + "learning_rate": 2.9260152849419654e-06, + "loss": 0.0024, + "step": 49064 + }, + { + "epoch": 15.15, + "learning_rate": 2.925661802740373e-06, + "loss": 0.0018, + "step": 49065 + }, + { + "epoch": 15.15, + "learning_rate": 2.9253083382329927e-06, + "loss": 0.0023, + "step": 49066 + }, + { + "epoch": 15.15, + "learning_rate": 2.924954891420705e-06, + "loss": 0.002, + "step": 49067 + }, + { + "epoch": 15.15, + "learning_rate": 2.9246014623043973e-06, + "loss": 0.0024, + "step": 49068 + }, + { + "epoch": 15.15, + "learning_rate": 2.9242480508849524e-06, + "loss": 0.0024, + "step": 49069 + }, + { + "epoch": 15.15, + "learning_rate": 2.92389465716325e-06, + "loss": 0.0025, + "step": 49070 + }, + { + "epoch": 15.15, + "learning_rate": 2.9235412811401786e-06, + "loss": 0.0029, + "step": 49071 + }, + { + "epoch": 15.15, + "learning_rate": 2.923187922816624e-06, + "loss": 0.0025, + "step": 49072 + }, + { + "epoch": 15.15, + "learning_rate": 2.9228345821934666e-06, + "loss": 0.0026, + "step": 49073 + }, + { + "epoch": 15.15, + "learning_rate": 2.922481259271588e-06, + "loss": 0.0025, + "step": 49074 + }, + { + "epoch": 15.16, + "learning_rate": 2.9221279540518743e-06, + "loss": 0.0029, + "step": 49075 + }, + { + "epoch": 15.16, + "learning_rate": 2.921774666535213e-06, + "loss": 0.0026, + "step": 49076 + }, + { + "epoch": 15.16, + "learning_rate": 2.9214213967224804e-06, + "loss": 0.0031, + "step": 49077 + }, + { + "epoch": 15.16, + "learning_rate": 2.9210681446145685e-06, + "loss": 0.0029, + "step": 49078 + }, + { + "epoch": 15.16, + "learning_rate": 2.9207149102123545e-06, + "loss": 0.0022, + "step": 49079 + }, + { + "epoch": 15.16, + "learning_rate": 2.920361693516722e-06, + "loss": 0.0027, + "step": 49080 + }, + { + "epoch": 15.16, + "learning_rate": 2.9200084945285554e-06, + "loss": 0.0019, + "step": 49081 + }, + { + "epoch": 15.16, + "learning_rate": 2.9196553132487424e-06, + "loss": 0.0031, + "step": 49082 + }, + { + "epoch": 15.16, + "learning_rate": 2.9193021496781628e-06, + "loss": 0.0021, + "step": 49083 + }, + { + "epoch": 15.16, + "learning_rate": 2.918949003817697e-06, + "loss": 0.0027, + "step": 49084 + }, + { + "epoch": 15.16, + "learning_rate": 2.9185958756682343e-06, + "loss": 0.0034, + "step": 49085 + }, + { + "epoch": 15.16, + "learning_rate": 2.918242765230651e-06, + "loss": 0.0025, + "step": 49086 + }, + { + "epoch": 15.16, + "learning_rate": 2.917889672505835e-06, + "loss": 0.0023, + "step": 49087 + }, + { + "epoch": 15.16, + "learning_rate": 2.917536597494671e-06, + "loss": 0.0025, + "step": 49088 + }, + { + "epoch": 15.16, + "learning_rate": 2.91718354019804e-06, + "loss": 0.0028, + "step": 49089 + }, + { + "epoch": 15.16, + "learning_rate": 2.916830500616822e-06, + "loss": 0.0024, + "step": 49090 + }, + { + "epoch": 15.16, + "learning_rate": 2.916477478751906e-06, + "loss": 0.0026, + "step": 49091 + }, + { + "epoch": 15.16, + "learning_rate": 2.9161244746041682e-06, + "loss": 0.0022, + "step": 49092 + }, + { + "epoch": 15.16, + "learning_rate": 2.915771488174498e-06, + "loss": 0.0024, + "step": 49093 + }, + { + "epoch": 15.16, + "learning_rate": 2.9154185194637764e-06, + "loss": 0.0027, + "step": 49094 + }, + { + "epoch": 15.16, + "learning_rate": 2.9150655684728814e-06, + "loss": 0.0032, + "step": 49095 + }, + { + "epoch": 15.16, + "learning_rate": 2.9147126352027e-06, + "loss": 0.0027, + "step": 49096 + }, + { + "epoch": 15.16, + "learning_rate": 2.9143597196541175e-06, + "loss": 0.0019, + "step": 49097 + }, + { + "epoch": 15.16, + "learning_rate": 2.9140068218280103e-06, + "loss": 0.0019, + "step": 49098 + }, + { + "epoch": 15.16, + "learning_rate": 2.9136539417252684e-06, + "loss": 0.0019, + "step": 49099 + }, + { + "epoch": 15.16, + "learning_rate": 2.9133010793467697e-06, + "loss": 0.0028, + "step": 49100 + }, + { + "epoch": 15.16, + "learning_rate": 2.9129482346933947e-06, + "loss": 0.0022, + "step": 49101 + }, + { + "epoch": 15.16, + "learning_rate": 2.912595407766028e-06, + "loss": 0.0018, + "step": 49102 + }, + { + "epoch": 15.16, + "learning_rate": 2.9122425985655567e-06, + "loss": 0.0028, + "step": 49103 + }, + { + "epoch": 15.16, + "learning_rate": 2.9118898070928594e-06, + "loss": 0.0025, + "step": 49104 + }, + { + "epoch": 15.16, + "learning_rate": 2.9115370333488158e-06, + "loss": 0.0034, + "step": 49105 + }, + { + "epoch": 15.16, + "learning_rate": 2.91118427733431e-06, + "loss": 0.0024, + "step": 49106 + }, + { + "epoch": 15.17, + "learning_rate": 2.9108315390502285e-06, + "loss": 0.0019, + "step": 49107 + }, + { + "epoch": 15.17, + "learning_rate": 2.9104788184974476e-06, + "loss": 0.0022, + "step": 49108 + }, + { + "epoch": 15.17, + "learning_rate": 2.910126115676856e-06, + "loss": 0.0031, + "step": 49109 + }, + { + "epoch": 15.17, + "learning_rate": 2.909773430589331e-06, + "loss": 0.002, + "step": 49110 + }, + { + "epoch": 15.17, + "learning_rate": 2.909420763235753e-06, + "loss": 0.0016, + "step": 49111 + }, + { + "epoch": 15.17, + "learning_rate": 2.9090681136170064e-06, + "loss": 0.003, + "step": 49112 + }, + { + "epoch": 15.17, + "learning_rate": 2.908715481733978e-06, + "loss": 0.0022, + "step": 49113 + }, + { + "epoch": 15.17, + "learning_rate": 2.908362867587544e-06, + "loss": 0.0025, + "step": 49114 + }, + { + "epoch": 15.17, + "learning_rate": 2.9080102711785863e-06, + "loss": 0.0028, + "step": 49115 + }, + { + "epoch": 15.17, + "learning_rate": 2.9076576925079915e-06, + "loss": 0.0025, + "step": 49116 + }, + { + "epoch": 15.17, + "learning_rate": 2.9073051315766344e-06, + "loss": 0.0032, + "step": 49117 + }, + { + "epoch": 15.17, + "learning_rate": 2.906952588385401e-06, + "loss": 0.0025, + "step": 49118 + }, + { + "epoch": 15.17, + "learning_rate": 2.9066000629351755e-06, + "loss": 0.0022, + "step": 49119 + }, + { + "epoch": 15.17, + "learning_rate": 2.9062475552268376e-06, + "loss": 0.0018, + "step": 49120 + }, + { + "epoch": 15.17, + "learning_rate": 2.905895065261265e-06, + "loss": 0.003, + "step": 49121 + }, + { + "epoch": 15.17, + "learning_rate": 2.9055425930393466e-06, + "loss": 0.0022, + "step": 49122 + }, + { + "epoch": 15.17, + "learning_rate": 2.905190138561956e-06, + "loss": 0.0025, + "step": 49123 + }, + { + "epoch": 15.17, + "learning_rate": 2.9048377018299834e-06, + "loss": 0.0018, + "step": 49124 + }, + { + "epoch": 15.17, + "learning_rate": 2.9044852828443047e-06, + "loss": 0.0022, + "step": 49125 + }, + { + "epoch": 15.17, + "learning_rate": 2.904132881605799e-06, + "loss": 0.0031, + "step": 49126 + }, + { + "epoch": 15.17, + "learning_rate": 2.9037804981153517e-06, + "loss": 0.0018, + "step": 49127 + }, + { + "epoch": 15.17, + "learning_rate": 2.903428132373847e-06, + "loss": 0.0024, + "step": 49128 + }, + { + "epoch": 15.17, + "learning_rate": 2.903075784382159e-06, + "loss": 0.0027, + "step": 49129 + }, + { + "epoch": 15.17, + "learning_rate": 2.9027234541411766e-06, + "loss": 0.0022, + "step": 49130 + }, + { + "epoch": 15.17, + "learning_rate": 2.9023711416517776e-06, + "loss": 0.0022, + "step": 49131 + }, + { + "epoch": 15.17, + "learning_rate": 2.902018846914839e-06, + "loss": 0.0029, + "step": 49132 + }, + { + "epoch": 15.17, + "learning_rate": 2.901666569931246e-06, + "loss": 0.003, + "step": 49133 + }, + { + "epoch": 15.17, + "learning_rate": 2.901314310701884e-06, + "loss": 0.0022, + "step": 49134 + }, + { + "epoch": 15.17, + "learning_rate": 2.9009620692276276e-06, + "loss": 0.0021, + "step": 49135 + }, + { + "epoch": 15.17, + "learning_rate": 2.900609845509358e-06, + "loss": 0.0017, + "step": 49136 + }, + { + "epoch": 15.17, + "learning_rate": 2.900257639547961e-06, + "loss": 0.0027, + "step": 49137 + }, + { + "epoch": 15.17, + "learning_rate": 2.8999054513443104e-06, + "loss": 0.0017, + "step": 49138 + }, + { + "epoch": 15.18, + "learning_rate": 2.899553280899292e-06, + "loss": 0.0028, + "step": 49139 + }, + { + "epoch": 15.18, + "learning_rate": 2.89920112821379e-06, + "loss": 0.0025, + "step": 49140 + }, + { + "epoch": 15.18, + "learning_rate": 2.8988489932886797e-06, + "loss": 0.0026, + "step": 49141 + }, + { + "epoch": 15.18, + "learning_rate": 2.898496876124841e-06, + "loss": 0.0025, + "step": 49142 + }, + { + "epoch": 15.18, + "learning_rate": 2.898144776723156e-06, + "loss": 0.0036, + "step": 49143 + }, + { + "epoch": 15.18, + "learning_rate": 2.8977926950845105e-06, + "loss": 0.0021, + "step": 49144 + }, + { + "epoch": 15.18, + "learning_rate": 2.8974406312097792e-06, + "loss": 0.0022, + "step": 49145 + }, + { + "epoch": 15.18, + "learning_rate": 2.897088585099842e-06, + "loss": 0.0022, + "step": 49146 + }, + { + "epoch": 15.18, + "learning_rate": 2.896736556755585e-06, + "loss": 0.0026, + "step": 49147 + }, + { + "epoch": 15.18, + "learning_rate": 2.896384546177883e-06, + "loss": 0.0024, + "step": 49148 + }, + { + "epoch": 15.18, + "learning_rate": 2.896032553367617e-06, + "loss": 0.0023, + "step": 49149 + }, + { + "epoch": 15.18, + "learning_rate": 2.895680578325677e-06, + "loss": 0.0028, + "step": 49150 + }, + { + "epoch": 15.18, + "learning_rate": 2.89532862105293e-06, + "loss": 0.0026, + "step": 49151 + }, + { + "epoch": 15.18, + "learning_rate": 2.89497668155026e-06, + "loss": 0.0035, + "step": 49152 + }, + { + "epoch": 15.18, + "learning_rate": 2.8946247598185526e-06, + "loss": 0.0032, + "step": 49153 + }, + { + "epoch": 15.18, + "learning_rate": 2.894272855858683e-06, + "loss": 0.0036, + "step": 49154 + }, + { + "epoch": 15.18, + "learning_rate": 2.8939209696715354e-06, + "loss": 0.0022, + "step": 49155 + }, + { + "epoch": 15.18, + "learning_rate": 2.893569101257987e-06, + "loss": 0.0029, + "step": 49156 + }, + { + "epoch": 15.18, + "learning_rate": 2.893217250618916e-06, + "loss": 0.003, + "step": 49157 + }, + { + "epoch": 15.18, + "learning_rate": 2.892865417755204e-06, + "loss": 0.0025, + "step": 49158 + }, + { + "epoch": 15.18, + "learning_rate": 2.892513602667736e-06, + "loss": 0.0024, + "step": 49159 + }, + { + "epoch": 15.18, + "learning_rate": 2.8921618053573876e-06, + "loss": 0.0023, + "step": 49160 + }, + { + "epoch": 15.18, + "learning_rate": 2.891810025825035e-06, + "loss": 0.0035, + "step": 49161 + }, + { + "epoch": 15.18, + "learning_rate": 2.891458264071565e-06, + "loss": 0.0025, + "step": 49162 + }, + { + "epoch": 15.18, + "learning_rate": 2.8911065200978527e-06, + "loss": 0.0025, + "step": 49163 + }, + { + "epoch": 15.18, + "learning_rate": 2.8907547939047787e-06, + "loss": 0.002, + "step": 49164 + }, + { + "epoch": 15.18, + "learning_rate": 2.8904030854932264e-06, + "loss": 0.003, + "step": 49165 + }, + { + "epoch": 15.18, + "learning_rate": 2.890051394864073e-06, + "loss": 0.0029, + "step": 49166 + }, + { + "epoch": 15.18, + "learning_rate": 2.8896997220181944e-06, + "loss": 0.0024, + "step": 49167 + }, + { + "epoch": 15.18, + "learning_rate": 2.8893480669564778e-06, + "loss": 0.0029, + "step": 49168 + }, + { + "epoch": 15.18, + "learning_rate": 2.8889964296797946e-06, + "loss": 0.0022, + "step": 49169 + }, + { + "epoch": 15.18, + "learning_rate": 2.888644810189032e-06, + "loss": 0.0023, + "step": 49170 + }, + { + "epoch": 15.18, + "learning_rate": 2.8882932084850613e-06, + "loss": 0.0025, + "step": 49171 + }, + { + "epoch": 15.19, + "learning_rate": 2.887941624568771e-06, + "loss": 0.0017, + "step": 49172 + }, + { + "epoch": 15.19, + "learning_rate": 2.887590058441032e-06, + "loss": 0.0022, + "step": 49173 + }, + { + "epoch": 15.19, + "learning_rate": 2.887238510102728e-06, + "loss": 0.0029, + "step": 49174 + }, + { + "epoch": 15.19, + "learning_rate": 2.8868869795547407e-06, + "loss": 0.0033, + "step": 49175 + }, + { + "epoch": 15.19, + "learning_rate": 2.886535466797946e-06, + "loss": 0.0025, + "step": 49176 + }, + { + "epoch": 15.19, + "learning_rate": 2.8861839718332208e-06, + "loss": 0.0024, + "step": 49177 + }, + { + "epoch": 15.19, + "learning_rate": 2.885832494661449e-06, + "loss": 0.0028, + "step": 49178 + }, + { + "epoch": 15.19, + "learning_rate": 2.8854810352835062e-06, + "loss": 0.0028, + "step": 49179 + }, + { + "epoch": 15.19, + "learning_rate": 2.8851295937002754e-06, + "loss": 0.0031, + "step": 49180 + }, + { + "epoch": 15.19, + "learning_rate": 2.8847781699126333e-06, + "loss": 0.0022, + "step": 49181 + }, + { + "epoch": 15.19, + "learning_rate": 2.884426763921455e-06, + "loss": 0.002, + "step": 49182 + }, + { + "epoch": 15.19, + "learning_rate": 2.884075375727624e-06, + "loss": 0.0029, + "step": 49183 + }, + { + "epoch": 15.19, + "learning_rate": 2.88372400533202e-06, + "loss": 0.0023, + "step": 49184 + }, + { + "epoch": 15.19, + "learning_rate": 2.8833726527355186e-06, + "loss": 0.0023, + "step": 49185 + }, + { + "epoch": 15.19, + "learning_rate": 2.8830213179390033e-06, + "loss": 0.0031, + "step": 49186 + }, + { + "epoch": 15.19, + "learning_rate": 2.8826700009433495e-06, + "loss": 0.0027, + "step": 49187 + }, + { + "epoch": 15.19, + "learning_rate": 2.8823187017494326e-06, + "loss": 0.0023, + "step": 49188 + }, + { + "epoch": 15.19, + "learning_rate": 2.881967420358135e-06, + "loss": 0.0028, + "step": 49189 + }, + { + "epoch": 15.19, + "learning_rate": 2.881616156770338e-06, + "loss": 0.0023, + "step": 49190 + }, + { + "epoch": 15.19, + "learning_rate": 2.8812649109869173e-06, + "loss": 0.0023, + "step": 49191 + }, + { + "epoch": 15.19, + "learning_rate": 2.880913683008749e-06, + "loss": 0.0023, + "step": 49192 + }, + { + "epoch": 15.19, + "learning_rate": 2.8805624728367163e-06, + "loss": 0.0028, + "step": 49193 + }, + { + "epoch": 15.19, + "learning_rate": 2.880211280471693e-06, + "loss": 0.0018, + "step": 49194 + }, + { + "epoch": 15.19, + "learning_rate": 2.879860105914559e-06, + "loss": 0.0023, + "step": 49195 + }, + { + "epoch": 15.19, + "learning_rate": 2.8795089491661975e-06, + "loss": 0.0023, + "step": 49196 + }, + { + "epoch": 15.19, + "learning_rate": 2.879157810227483e-06, + "loss": 0.003, + "step": 49197 + }, + { + "epoch": 15.19, + "learning_rate": 2.8788066890992895e-06, + "loss": 0.0028, + "step": 49198 + }, + { + "epoch": 15.19, + "learning_rate": 2.8784555857825024e-06, + "loss": 0.0027, + "step": 49199 + }, + { + "epoch": 15.19, + "learning_rate": 2.878104500277995e-06, + "loss": 0.0022, + "step": 49200 + }, + { + "epoch": 15.19, + "learning_rate": 2.8777534325866485e-06, + "loss": 0.0033, + "step": 49201 + }, + { + "epoch": 15.19, + "learning_rate": 2.877402382709341e-06, + "loss": 0.0018, + "step": 49202 + }, + { + "epoch": 15.19, + "learning_rate": 2.8770513506469454e-06, + "loss": 0.0025, + "step": 49203 + }, + { + "epoch": 15.2, + "learning_rate": 2.8767003364003445e-06, + "loss": 0.0024, + "step": 49204 + }, + { + "epoch": 15.2, + "learning_rate": 2.8763493399704146e-06, + "loss": 0.0028, + "step": 49205 + }, + { + "epoch": 15.2, + "learning_rate": 2.8759983613580365e-06, + "loss": 0.0021, + "step": 49206 + }, + { + "epoch": 15.2, + "learning_rate": 2.8756474005640876e-06, + "loss": 0.003, + "step": 49207 + }, + { + "epoch": 15.2, + "learning_rate": 2.875296457589439e-06, + "loss": 0.0031, + "step": 49208 + }, + { + "epoch": 15.2, + "learning_rate": 2.8749455324349783e-06, + "loss": 0.0024, + "step": 49209 + }, + { + "epoch": 15.2, + "learning_rate": 2.8745946251015743e-06, + "loss": 0.0026, + "step": 49210 + }, + { + "epoch": 15.2, + "learning_rate": 2.874243735590112e-06, + "loss": 0.0022, + "step": 49211 + }, + { + "epoch": 15.2, + "learning_rate": 2.873892863901465e-06, + "loss": 0.0027, + "step": 49212 + }, + { + "epoch": 15.2, + "learning_rate": 2.8735420100365095e-06, + "loss": 0.0016, + "step": 49213 + }, + { + "epoch": 15.2, + "learning_rate": 2.873191173996125e-06, + "loss": 0.0027, + "step": 49214 + }, + { + "epoch": 15.2, + "learning_rate": 2.8728403557811924e-06, + "loss": 0.0024, + "step": 49215 + }, + { + "epoch": 15.2, + "learning_rate": 2.8724895553925836e-06, + "loss": 0.0024, + "step": 49216 + }, + { + "epoch": 15.2, + "learning_rate": 2.87213877283118e-06, + "loss": 0.002, + "step": 49217 + }, + { + "epoch": 15.2, + "learning_rate": 2.8717880080978576e-06, + "loss": 0.003, + "step": 49218 + }, + { + "epoch": 15.2, + "learning_rate": 2.8714372611934917e-06, + "loss": 0.0028, + "step": 49219 + }, + { + "epoch": 15.2, + "learning_rate": 2.871086532118961e-06, + "loss": 0.002, + "step": 49220 + }, + { + "epoch": 15.2, + "learning_rate": 2.8707358208751458e-06, + "loss": 0.003, + "step": 49221 + }, + { + "epoch": 15.2, + "learning_rate": 2.87038512746292e-06, + "loss": 0.0024, + "step": 49222 + }, + { + "epoch": 15.2, + "learning_rate": 2.870034451883159e-06, + "loss": 0.0022, + "step": 49223 + }, + { + "epoch": 15.2, + "learning_rate": 2.869683794136745e-06, + "loss": 0.002, + "step": 49224 + }, + { + "epoch": 15.2, + "learning_rate": 2.8693331542245497e-06, + "loss": 0.0018, + "step": 49225 + }, + { + "epoch": 15.2, + "learning_rate": 2.8689825321474516e-06, + "loss": 0.0027, + "step": 49226 + }, + { + "epoch": 15.2, + "learning_rate": 2.8686319279063335e-06, + "loss": 0.0022, + "step": 49227 + }, + { + "epoch": 15.2, + "learning_rate": 2.868281341502067e-06, + "loss": 0.0026, + "step": 49228 + }, + { + "epoch": 15.2, + "learning_rate": 2.8679307729355266e-06, + "loss": 0.0017, + "step": 49229 + }, + { + "epoch": 15.2, + "learning_rate": 2.8675802222075946e-06, + "loss": 0.0019, + "step": 49230 + }, + { + "epoch": 15.2, + "learning_rate": 2.8672296893191432e-06, + "loss": 0.0028, + "step": 49231 + }, + { + "epoch": 15.2, + "learning_rate": 2.866879174271053e-06, + "loss": 0.0021, + "step": 49232 + }, + { + "epoch": 15.2, + "learning_rate": 2.8665286770641997e-06, + "loss": 0.0023, + "step": 49233 + }, + { + "epoch": 15.2, + "learning_rate": 2.8661781976994563e-06, + "loss": 0.0028, + "step": 49234 + }, + { + "epoch": 15.2, + "learning_rate": 2.8658277361777033e-06, + "loss": 0.0026, + "step": 49235 + }, + { + "epoch": 15.2, + "learning_rate": 2.8654772924998152e-06, + "loss": 0.0023, + "step": 49236 + }, + { + "epoch": 15.21, + "learning_rate": 2.865126866666673e-06, + "loss": 0.003, + "step": 49237 + }, + { + "epoch": 15.21, + "learning_rate": 2.8647764586791493e-06, + "loss": 0.0026, + "step": 49238 + }, + { + "epoch": 15.21, + "learning_rate": 2.8644260685381185e-06, + "loss": 0.0032, + "step": 49239 + }, + { + "epoch": 15.21, + "learning_rate": 2.8640756962444628e-06, + "loss": 0.0024, + "step": 49240 + }, + { + "epoch": 15.21, + "learning_rate": 2.8637253417990516e-06, + "loss": 0.0025, + "step": 49241 + }, + { + "epoch": 15.21, + "learning_rate": 2.8633750052027685e-06, + "loss": 0.0027, + "step": 49242 + }, + { + "epoch": 15.21, + "learning_rate": 2.863024686456486e-06, + "loss": 0.0018, + "step": 49243 + }, + { + "epoch": 15.21, + "learning_rate": 2.8626743855610775e-06, + "loss": 0.0018, + "step": 49244 + }, + { + "epoch": 15.21, + "learning_rate": 2.862324102517422e-06, + "loss": 0.0027, + "step": 49245 + }, + { + "epoch": 15.21, + "learning_rate": 2.8619738373263984e-06, + "loss": 0.0022, + "step": 49246 + }, + { + "epoch": 15.21, + "learning_rate": 2.8616235899888777e-06, + "loss": 0.0026, + "step": 49247 + }, + { + "epoch": 15.21, + "learning_rate": 2.861273360505741e-06, + "loss": 0.0021, + "step": 49248 + }, + { + "epoch": 15.21, + "learning_rate": 2.860923148877862e-06, + "loss": 0.002, + "step": 49249 + }, + { + "epoch": 15.21, + "learning_rate": 2.8605729551061133e-06, + "loss": 0.0027, + "step": 49250 + }, + { + "epoch": 15.21, + "learning_rate": 2.860222779191374e-06, + "loss": 0.0031, + "step": 49251 + }, + { + "epoch": 15.21, + "learning_rate": 2.859872621134522e-06, + "loss": 0.0028, + "step": 49252 + }, + { + "epoch": 15.21, + "learning_rate": 2.8595224809364306e-06, + "loss": 0.0033, + "step": 49253 + }, + { + "epoch": 15.21, + "learning_rate": 2.8591723585979735e-06, + "loss": 0.0026, + "step": 49254 + }, + { + "epoch": 15.21, + "learning_rate": 2.858822254120032e-06, + "loss": 0.0021, + "step": 49255 + }, + { + "epoch": 15.21, + "learning_rate": 2.8584721675034753e-06, + "loss": 0.0028, + "step": 49256 + }, + { + "epoch": 15.21, + "learning_rate": 2.858122098749182e-06, + "loss": 0.0025, + "step": 49257 + }, + { + "epoch": 15.21, + "learning_rate": 2.857772047858034e-06, + "loss": 0.0027, + "step": 49258 + }, + { + "epoch": 15.21, + "learning_rate": 2.8574220148308952e-06, + "loss": 0.0029, + "step": 49259 + }, + { + "epoch": 15.21, + "learning_rate": 2.8570719996686456e-06, + "loss": 0.0022, + "step": 49260 + }, + { + "epoch": 15.21, + "learning_rate": 2.856722002372165e-06, + "loss": 0.0035, + "step": 49261 + }, + { + "epoch": 15.21, + "learning_rate": 2.856372022942323e-06, + "loss": 0.0026, + "step": 49262 + }, + { + "epoch": 15.21, + "learning_rate": 2.8560220613800003e-06, + "loss": 0.0023, + "step": 49263 + }, + { + "epoch": 15.21, + "learning_rate": 2.8556721176860704e-06, + "loss": 0.0031, + "step": 49264 + }, + { + "epoch": 15.21, + "learning_rate": 2.855322191861404e-06, + "loss": 0.0018, + "step": 49265 + }, + { + "epoch": 15.21, + "learning_rate": 2.8549722839068793e-06, + "loss": 0.0026, + "step": 49266 + }, + { + "epoch": 15.21, + "learning_rate": 2.8546223938233753e-06, + "loss": 0.0037, + "step": 49267 + }, + { + "epoch": 15.21, + "learning_rate": 2.854272521611764e-06, + "loss": 0.0028, + "step": 49268 + }, + { + "epoch": 15.22, + "learning_rate": 2.853922667272917e-06, + "loss": 0.0029, + "step": 49269 + }, + { + "epoch": 15.22, + "learning_rate": 2.8535728308077137e-06, + "loss": 0.0016, + "step": 49270 + }, + { + "epoch": 15.22, + "learning_rate": 2.8532230122170303e-06, + "loss": 0.002, + "step": 49271 + }, + { + "epoch": 15.22, + "learning_rate": 2.8528732115017376e-06, + "loss": 0.0027, + "step": 49272 + }, + { + "epoch": 15.22, + "learning_rate": 2.8525234286627144e-06, + "loss": 0.0023, + "step": 49273 + }, + { + "epoch": 15.22, + "learning_rate": 2.8521736637008345e-06, + "loss": 0.0026, + "step": 49274 + }, + { + "epoch": 15.22, + "learning_rate": 2.8518239166169694e-06, + "loss": 0.0028, + "step": 49275 + }, + { + "epoch": 15.22, + "learning_rate": 2.8514741874119958e-06, + "loss": 0.0018, + "step": 49276 + }, + { + "epoch": 15.22, + "learning_rate": 2.8511244760867916e-06, + "loss": 0.0026, + "step": 49277 + }, + { + "epoch": 15.22, + "learning_rate": 2.850774782642226e-06, + "loss": 0.0029, + "step": 49278 + }, + { + "epoch": 15.22, + "learning_rate": 2.8504251070791798e-06, + "loss": 0.0026, + "step": 49279 + }, + { + "epoch": 15.22, + "learning_rate": 2.850075449398525e-06, + "loss": 0.003, + "step": 49280 + }, + { + "epoch": 15.22, + "learning_rate": 2.849725809601133e-06, + "loss": 0.0018, + "step": 49281 + }, + { + "epoch": 15.22, + "learning_rate": 2.8493761876878787e-06, + "loss": 0.0019, + "step": 49282 + }, + { + "epoch": 15.22, + "learning_rate": 2.849026583659643e-06, + "loss": 0.0032, + "step": 49283 + }, + { + "epoch": 15.22, + "learning_rate": 2.848676997517297e-06, + "loss": 0.0031, + "step": 49284 + }, + { + "epoch": 15.22, + "learning_rate": 2.84832742926171e-06, + "loss": 0.0033, + "step": 49285 + }, + { + "epoch": 15.22, + "learning_rate": 2.847977878893764e-06, + "loss": 0.0025, + "step": 49286 + }, + { + "epoch": 15.22, + "learning_rate": 2.8476283464143263e-06, + "loss": 0.0024, + "step": 49287 + }, + { + "epoch": 15.22, + "learning_rate": 2.847278831824275e-06, + "loss": 0.0035, + "step": 49288 + }, + { + "epoch": 15.22, + "learning_rate": 2.8469293351244897e-06, + "loss": 0.0019, + "step": 49289 + }, + { + "epoch": 15.22, + "learning_rate": 2.846579856315833e-06, + "loss": 0.0026, + "step": 49290 + }, + { + "epoch": 15.22, + "learning_rate": 2.8462303953991844e-06, + "loss": 0.0028, + "step": 49291 + }, + { + "epoch": 15.22, + "learning_rate": 2.8458809523754216e-06, + "loss": 0.0035, + "step": 49292 + }, + { + "epoch": 15.22, + "learning_rate": 2.845531527245413e-06, + "loss": 0.0024, + "step": 49293 + }, + { + "epoch": 15.22, + "learning_rate": 2.845182120010037e-06, + "loss": 0.003, + "step": 49294 + }, + { + "epoch": 15.22, + "learning_rate": 2.8448327306701663e-06, + "loss": 0.0021, + "step": 49295 + }, + { + "epoch": 15.22, + "learning_rate": 2.8444833592266697e-06, + "loss": 0.0022, + "step": 49296 + }, + { + "epoch": 15.22, + "learning_rate": 2.8441340056804267e-06, + "loss": 0.0021, + "step": 49297 + }, + { + "epoch": 15.22, + "learning_rate": 2.8437846700323125e-06, + "loss": 0.0027, + "step": 49298 + }, + { + "epoch": 15.22, + "learning_rate": 2.843435352283197e-06, + "loss": 0.0029, + "step": 49299 + }, + { + "epoch": 15.22, + "learning_rate": 2.843086052433952e-06, + "loss": 0.0024, + "step": 49300 + }, + { + "epoch": 15.23, + "learning_rate": 2.842736770485458e-06, + "loss": 0.0022, + "step": 49301 + }, + { + "epoch": 15.23, + "learning_rate": 2.842387506438582e-06, + "loss": 0.0025, + "step": 49302 + }, + { + "epoch": 15.23, + "learning_rate": 2.8420382602942e-06, + "loss": 0.0024, + "step": 49303 + }, + { + "epoch": 15.23, + "learning_rate": 2.8416890320531876e-06, + "loss": 0.0028, + "step": 49304 + }, + { + "epoch": 15.23, + "learning_rate": 2.841339821716418e-06, + "loss": 0.0032, + "step": 49305 + }, + { + "epoch": 15.23, + "learning_rate": 2.84099062928476e-06, + "loss": 0.0023, + "step": 49306 + }, + { + "epoch": 15.23, + "learning_rate": 2.84064145475909e-06, + "loss": 0.0027, + "step": 49307 + }, + { + "epoch": 15.23, + "learning_rate": 2.8402922981402834e-06, + "loss": 0.0018, + "step": 49308 + }, + { + "epoch": 15.23, + "learning_rate": 2.8399431594292124e-06, + "loss": 0.0028, + "step": 49309 + }, + { + "epoch": 15.23, + "learning_rate": 2.8395940386267473e-06, + "loss": 0.0022, + "step": 49310 + }, + { + "epoch": 15.23, + "learning_rate": 2.839244935733766e-06, + "loss": 0.0033, + "step": 49311 + }, + { + "epoch": 15.23, + "learning_rate": 2.8388958507511353e-06, + "loss": 0.0025, + "step": 49312 + }, + { + "epoch": 15.23, + "learning_rate": 2.838546783679733e-06, + "loss": 0.0024, + "step": 49313 + }, + { + "epoch": 15.23, + "learning_rate": 2.8381977345204346e-06, + "loss": 0.0021, + "step": 49314 + }, + { + "epoch": 15.23, + "learning_rate": 2.83784870327411e-06, + "loss": 0.0033, + "step": 49315 + }, + { + "epoch": 15.23, + "learning_rate": 2.8374996899416283e-06, + "loss": 0.0024, + "step": 49316 + }, + { + "epoch": 15.23, + "learning_rate": 2.8371506945238693e-06, + "loss": 0.0029, + "step": 49317 + }, + { + "epoch": 15.23, + "learning_rate": 2.8368017170217e-06, + "loss": 0.0036, + "step": 49318 + }, + { + "epoch": 15.23, + "learning_rate": 2.836452757435999e-06, + "loss": 0.0028, + "step": 49319 + }, + { + "epoch": 15.23, + "learning_rate": 2.836103815767637e-06, + "loss": 0.0023, + "step": 49320 + }, + { + "epoch": 15.23, + "learning_rate": 2.8357548920174814e-06, + "loss": 0.0026, + "step": 49321 + }, + { + "epoch": 15.23, + "learning_rate": 2.8354059861864115e-06, + "loss": 0.0025, + "step": 49322 + }, + { + "epoch": 15.23, + "learning_rate": 2.835057098275299e-06, + "loss": 0.0027, + "step": 49323 + }, + { + "epoch": 15.23, + "learning_rate": 2.8347082282850134e-06, + "loss": 0.0035, + "step": 49324 + }, + { + "epoch": 15.23, + "learning_rate": 2.8343593762164334e-06, + "loss": 0.0024, + "step": 49325 + }, + { + "epoch": 15.23, + "learning_rate": 2.8340105420704255e-06, + "loss": 0.0026, + "step": 49326 + }, + { + "epoch": 15.23, + "learning_rate": 2.8336617258478627e-06, + "loss": 0.0026, + "step": 49327 + }, + { + "epoch": 15.23, + "learning_rate": 2.8333129275496185e-06, + "loss": 0.0031, + "step": 49328 + }, + { + "epoch": 15.23, + "learning_rate": 2.832964147176569e-06, + "loss": 0.002, + "step": 49329 + }, + { + "epoch": 15.23, + "learning_rate": 2.8326153847295835e-06, + "loss": 0.0023, + "step": 49330 + }, + { + "epoch": 15.23, + "learning_rate": 2.83226664020953e-06, + "loss": 0.0024, + "step": 49331 + }, + { + "epoch": 15.23, + "learning_rate": 2.8319179136172893e-06, + "loss": 0.0026, + "step": 49332 + }, + { + "epoch": 15.23, + "learning_rate": 2.831569204953726e-06, + "loss": 0.0014, + "step": 49333 + }, + { + "epoch": 15.24, + "learning_rate": 2.8312205142197146e-06, + "loss": 0.002, + "step": 49334 + }, + { + "epoch": 15.24, + "learning_rate": 2.830871841416133e-06, + "loss": 0.0026, + "step": 49335 + }, + { + "epoch": 15.24, + "learning_rate": 2.8305231865438467e-06, + "loss": 0.0021, + "step": 49336 + }, + { + "epoch": 15.24, + "learning_rate": 2.830174549603727e-06, + "loss": 0.0029, + "step": 49337 + }, + { + "epoch": 15.24, + "learning_rate": 2.829825930596649e-06, + "loss": 0.0024, + "step": 49338 + }, + { + "epoch": 15.24, + "learning_rate": 2.8294773295234867e-06, + "loss": 0.0021, + "step": 49339 + }, + { + "epoch": 15.24, + "learning_rate": 2.8291287463851103e-06, + "loss": 0.0024, + "step": 49340 + }, + { + "epoch": 15.24, + "learning_rate": 2.828780181182387e-06, + "loss": 0.0023, + "step": 49341 + }, + { + "epoch": 15.24, + "learning_rate": 2.8284316339161955e-06, + "loss": 0.0025, + "step": 49342 + }, + { + "epoch": 15.24, + "learning_rate": 2.8280831045874015e-06, + "loss": 0.002, + "step": 49343 + }, + { + "epoch": 15.24, + "learning_rate": 2.8277345931968793e-06, + "loss": 0.0024, + "step": 49344 + }, + { + "epoch": 15.24, + "learning_rate": 2.8273860997455037e-06, + "loss": 0.0019, + "step": 49345 + }, + { + "epoch": 15.24, + "learning_rate": 2.8270376242341448e-06, + "loss": 0.0035, + "step": 49346 + }, + { + "epoch": 15.24, + "learning_rate": 2.8266891666636696e-06, + "loss": 0.0026, + "step": 49347 + }, + { + "epoch": 15.24, + "learning_rate": 2.826340727034956e-06, + "loss": 0.0028, + "step": 49348 + }, + { + "epoch": 15.24, + "learning_rate": 2.82599230534887e-06, + "loss": 0.0022, + "step": 49349 + }, + { + "epoch": 15.24, + "learning_rate": 2.825643901606289e-06, + "loss": 0.0025, + "step": 49350 + }, + { + "epoch": 15.24, + "learning_rate": 2.82529551580808e-06, + "loss": 0.0024, + "step": 49351 + }, + { + "epoch": 15.24, + "learning_rate": 2.8249471479551125e-06, + "loss": 0.0027, + "step": 49352 + }, + { + "epoch": 15.24, + "learning_rate": 2.8245987980482624e-06, + "loss": 0.002, + "step": 49353 + }, + { + "epoch": 15.24, + "learning_rate": 2.824250466088401e-06, + "loss": 0.002, + "step": 49354 + }, + { + "epoch": 15.24, + "learning_rate": 2.8239021520763955e-06, + "loss": 0.0031, + "step": 49355 + }, + { + "epoch": 15.24, + "learning_rate": 2.8235538560131225e-06, + "loss": 0.0025, + "step": 49356 + }, + { + "epoch": 15.24, + "learning_rate": 2.8232055778994505e-06, + "loss": 0.0029, + "step": 49357 + }, + { + "epoch": 15.24, + "learning_rate": 2.822857317736247e-06, + "loss": 0.002, + "step": 49358 + }, + { + "epoch": 15.24, + "learning_rate": 2.8225090755243855e-06, + "loss": 0.0022, + "step": 49359 + }, + { + "epoch": 15.24, + "learning_rate": 2.8221608512647425e-06, + "loss": 0.0023, + "step": 49360 + }, + { + "epoch": 15.24, + "learning_rate": 2.821812644958184e-06, + "loss": 0.0031, + "step": 49361 + }, + { + "epoch": 15.24, + "learning_rate": 2.821464456605577e-06, + "loss": 0.0028, + "step": 49362 + }, + { + "epoch": 15.24, + "learning_rate": 2.8211162862078013e-06, + "loss": 0.0035, + "step": 49363 + }, + { + "epoch": 15.24, + "learning_rate": 2.8207681337657187e-06, + "loss": 0.003, + "step": 49364 + }, + { + "epoch": 15.24, + "learning_rate": 2.8204199992802052e-06, + "loss": 0.0033, + "step": 49365 + }, + { + "epoch": 15.25, + "learning_rate": 2.8200718827521345e-06, + "loss": 0.0032, + "step": 49366 + }, + { + "epoch": 15.25, + "learning_rate": 2.8197237841823723e-06, + "loss": 0.0029, + "step": 49367 + }, + { + "epoch": 15.25, + "learning_rate": 2.8193757035717884e-06, + "loss": 0.0029, + "step": 49368 + }, + { + "epoch": 15.25, + "learning_rate": 2.8190276409212546e-06, + "loss": 0.0014, + "step": 49369 + }, + { + "epoch": 15.25, + "learning_rate": 2.818679596231646e-06, + "loss": 0.0022, + "step": 49370 + }, + { + "epoch": 15.25, + "learning_rate": 2.8183315695038294e-06, + "loss": 0.0021, + "step": 49371 + }, + { + "epoch": 15.25, + "learning_rate": 2.817983560738673e-06, + "loss": 0.002, + "step": 49372 + }, + { + "epoch": 15.25, + "learning_rate": 2.8176355699370515e-06, + "loss": 0.0026, + "step": 49373 + }, + { + "epoch": 15.25, + "learning_rate": 2.8172875970998316e-06, + "loss": 0.0026, + "step": 49374 + }, + { + "epoch": 15.25, + "learning_rate": 2.8169396422278837e-06, + "loss": 0.0023, + "step": 49375 + }, + { + "epoch": 15.25, + "learning_rate": 2.816591705322085e-06, + "loss": 0.0026, + "step": 49376 + }, + { + "epoch": 15.25, + "learning_rate": 2.8162437863832994e-06, + "loss": 0.0019, + "step": 49377 + }, + { + "epoch": 15.25, + "learning_rate": 2.815895885412395e-06, + "loss": 0.0023, + "step": 49378 + }, + { + "epoch": 15.25, + "learning_rate": 2.815548002410249e-06, + "loss": 0.002, + "step": 49379 + }, + { + "epoch": 15.25, + "learning_rate": 2.8152001373777247e-06, + "loss": 0.0023, + "step": 49380 + }, + { + "epoch": 15.25, + "learning_rate": 2.8148522903156984e-06, + "loss": 0.0034, + "step": 49381 + }, + { + "epoch": 15.25, + "learning_rate": 2.814504461225037e-06, + "loss": 0.003, + "step": 49382 + }, + { + "epoch": 15.25, + "learning_rate": 2.8141566501066065e-06, + "loss": 0.0028, + "step": 49383 + }, + { + "epoch": 15.25, + "learning_rate": 2.813808856961282e-06, + "loss": 0.0022, + "step": 49384 + }, + { + "epoch": 15.25, + "learning_rate": 2.8134610817899353e-06, + "loss": 0.0025, + "step": 49385 + }, + { + "epoch": 15.25, + "learning_rate": 2.8131133245934294e-06, + "loss": 0.0025, + "step": 49386 + }, + { + "epoch": 15.25, + "learning_rate": 2.812765585372641e-06, + "loss": 0.0021, + "step": 49387 + }, + { + "epoch": 15.25, + "learning_rate": 2.8124178641284373e-06, + "loss": 0.0038, + "step": 49388 + }, + { + "epoch": 15.25, + "learning_rate": 2.812070160861684e-06, + "loss": 0.0026, + "step": 49389 + }, + { + "epoch": 15.25, + "learning_rate": 2.811722475573254e-06, + "loss": 0.0019, + "step": 49390 + }, + { + "epoch": 15.25, + "learning_rate": 2.8113748082640214e-06, + "loss": 0.0032, + "step": 49391 + }, + { + "epoch": 15.25, + "learning_rate": 2.8110271589348503e-06, + "loss": 0.003, + "step": 49392 + }, + { + "epoch": 15.25, + "learning_rate": 2.8106795275866084e-06, + "loss": 0.0034, + "step": 49393 + }, + { + "epoch": 15.25, + "learning_rate": 2.810331914220172e-06, + "loss": 0.0032, + "step": 49394 + }, + { + "epoch": 15.25, + "learning_rate": 2.809984318836404e-06, + "loss": 0.0023, + "step": 49395 + }, + { + "epoch": 15.25, + "learning_rate": 2.8096367414361757e-06, + "loss": 0.003, + "step": 49396 + }, + { + "epoch": 15.25, + "learning_rate": 2.809289182020364e-06, + "loss": 0.0048, + "step": 49397 + }, + { + "epoch": 15.26, + "learning_rate": 2.8089416405898252e-06, + "loss": 0.0022, + "step": 49398 + }, + { + "epoch": 15.26, + "learning_rate": 2.8085941171454345e-06, + "loss": 0.0027, + "step": 49399 + }, + { + "epoch": 15.26, + "learning_rate": 2.8082466116880625e-06, + "loss": 0.0016, + "step": 49400 + }, + { + "epoch": 15.26, + "learning_rate": 2.8078991242185794e-06, + "loss": 0.0032, + "step": 49401 + }, + { + "epoch": 15.26, + "learning_rate": 2.8075516547378536e-06, + "loss": 0.0034, + "step": 49402 + }, + { + "epoch": 15.26, + "learning_rate": 2.8072042032467484e-06, + "loss": 0.0026, + "step": 49403 + }, + { + "epoch": 15.26, + "learning_rate": 2.806856769746141e-06, + "loss": 0.0026, + "step": 49404 + }, + { + "epoch": 15.26, + "learning_rate": 2.8065093542368948e-06, + "loss": 0.0021, + "step": 49405 + }, + { + "epoch": 15.26, + "learning_rate": 2.8061619567198793e-06, + "loss": 0.0024, + "step": 49406 + }, + { + "epoch": 15.26, + "learning_rate": 2.8058145771959722e-06, + "loss": 0.0023, + "step": 49407 + }, + { + "epoch": 15.26, + "learning_rate": 2.8054672156660278e-06, + "loss": 0.0025, + "step": 49408 + }, + { + "epoch": 15.26, + "learning_rate": 2.8051198721309226e-06, + "loss": 0.0025, + "step": 49409 + }, + { + "epoch": 15.26, + "learning_rate": 2.8047725465915275e-06, + "loss": 0.0032, + "step": 49410 + }, + { + "epoch": 15.26, + "learning_rate": 2.804425239048706e-06, + "loss": 0.0023, + "step": 49411 + }, + { + "epoch": 15.26, + "learning_rate": 2.8040779495033323e-06, + "loss": 0.0024, + "step": 49412 + }, + { + "epoch": 15.26, + "learning_rate": 2.803730677956271e-06, + "loss": 0.0022, + "step": 49413 + }, + { + "epoch": 15.26, + "learning_rate": 2.8033834244083903e-06, + "loss": 0.0038, + "step": 49414 + }, + { + "epoch": 15.26, + "learning_rate": 2.8030361888605593e-06, + "loss": 0.0025, + "step": 49415 + }, + { + "epoch": 15.26, + "learning_rate": 2.802688971313652e-06, + "loss": 0.0034, + "step": 49416 + }, + { + "epoch": 15.26, + "learning_rate": 2.802341771768531e-06, + "loss": 0.0028, + "step": 49417 + }, + { + "epoch": 15.26, + "learning_rate": 2.8019945902260626e-06, + "loss": 0.0033, + "step": 49418 + }, + { + "epoch": 15.26, + "learning_rate": 2.801647426687122e-06, + "loss": 0.0029, + "step": 49419 + }, + { + "epoch": 15.26, + "learning_rate": 2.801300281152571e-06, + "loss": 0.0027, + "step": 49420 + }, + { + "epoch": 15.26, + "learning_rate": 2.8009531536232813e-06, + "loss": 0.0025, + "step": 49421 + }, + { + "epoch": 15.26, + "learning_rate": 2.8006060441001238e-06, + "loss": 0.0022, + "step": 49422 + }, + { + "epoch": 15.26, + "learning_rate": 2.8002589525839643e-06, + "loss": 0.0023, + "step": 49423 + }, + { + "epoch": 15.26, + "learning_rate": 2.7999118790756664e-06, + "loss": 0.0032, + "step": 49424 + }, + { + "epoch": 15.26, + "learning_rate": 2.799564823576104e-06, + "loss": 0.0025, + "step": 49425 + }, + { + "epoch": 15.26, + "learning_rate": 2.7992177860861426e-06, + "loss": 0.0022, + "step": 49426 + }, + { + "epoch": 15.26, + "learning_rate": 2.7988707666066527e-06, + "loss": 0.0026, + "step": 49427 + }, + { + "epoch": 15.26, + "learning_rate": 2.7985237651385e-06, + "loss": 0.0023, + "step": 49428 + }, + { + "epoch": 15.26, + "learning_rate": 2.79817678168255e-06, + "loss": 0.0027, + "step": 49429 + }, + { + "epoch": 15.26, + "learning_rate": 2.7978298162396746e-06, + "loss": 0.0028, + "step": 49430 + }, + { + "epoch": 15.27, + "learning_rate": 2.7974828688107414e-06, + "loss": 0.003, + "step": 49431 + }, + { + "epoch": 15.27, + "learning_rate": 2.797135939396616e-06, + "loss": 0.0019, + "step": 49432 + }, + { + "epoch": 15.27, + "learning_rate": 2.796789027998169e-06, + "loss": 0.0036, + "step": 49433 + }, + { + "epoch": 15.27, + "learning_rate": 2.796442134616264e-06, + "loss": 0.0022, + "step": 49434 + }, + { + "epoch": 15.27, + "learning_rate": 2.7960952592517743e-06, + "loss": 0.0028, + "step": 49435 + }, + { + "epoch": 15.27, + "learning_rate": 2.7957484019055615e-06, + "loss": 0.0027, + "step": 49436 + }, + { + "epoch": 15.27, + "learning_rate": 2.795401562578498e-06, + "loss": 0.0021, + "step": 49437 + }, + { + "epoch": 15.27, + "learning_rate": 2.79505474127145e-06, + "loss": 0.0016, + "step": 49438 + }, + { + "epoch": 15.27, + "learning_rate": 2.7947079379852814e-06, + "loss": 0.0029, + "step": 49439 + }, + { + "epoch": 15.27, + "learning_rate": 2.7943611527208614e-06, + "loss": 0.0022, + "step": 49440 + }, + { + "epoch": 15.27, + "learning_rate": 2.7940143854790626e-06, + "loss": 0.0023, + "step": 49441 + }, + { + "epoch": 15.27, + "learning_rate": 2.793667636260744e-06, + "loss": 0.0028, + "step": 49442 + }, + { + "epoch": 15.27, + "learning_rate": 2.793320905066781e-06, + "loss": 0.002, + "step": 49443 + }, + { + "epoch": 15.27, + "learning_rate": 2.7929741918980356e-06, + "loss": 0.0023, + "step": 49444 + }, + { + "epoch": 15.27, + "learning_rate": 2.7926274967553746e-06, + "loss": 0.0027, + "step": 49445 + }, + { + "epoch": 15.27, + "learning_rate": 2.7922808196396656e-06, + "loss": 0.0025, + "step": 49446 + }, + { + "epoch": 15.27, + "learning_rate": 2.7919341605517803e-06, + "loss": 0.0023, + "step": 49447 + }, + { + "epoch": 15.27, + "learning_rate": 2.7915875194925825e-06, + "loss": 0.0025, + "step": 49448 + }, + { + "epoch": 15.27, + "learning_rate": 2.7912408964629354e-06, + "loss": 0.0027, + "step": 49449 + }, + { + "epoch": 15.27, + "learning_rate": 2.7908942914637137e-06, + "loss": 0.0025, + "step": 49450 + }, + { + "epoch": 15.27, + "learning_rate": 2.7905477044957765e-06, + "loss": 0.0025, + "step": 49451 + }, + { + "epoch": 15.27, + "learning_rate": 2.7902011355599946e-06, + "loss": 0.0021, + "step": 49452 + }, + { + "epoch": 15.27, + "learning_rate": 2.7898545846572376e-06, + "loss": 0.0027, + "step": 49453 + }, + { + "epoch": 15.27, + "learning_rate": 2.78950805178837e-06, + "loss": 0.0026, + "step": 49454 + }, + { + "epoch": 15.27, + "learning_rate": 2.7891615369542535e-06, + "loss": 0.0032, + "step": 49455 + }, + { + "epoch": 15.27, + "learning_rate": 2.7888150401557632e-06, + "loss": 0.0035, + "step": 49456 + }, + { + "epoch": 15.27, + "learning_rate": 2.7884685613937588e-06, + "loss": 0.0034, + "step": 49457 + }, + { + "epoch": 15.27, + "learning_rate": 2.788122100669113e-06, + "loss": 0.0039, + "step": 49458 + }, + { + "epoch": 15.27, + "learning_rate": 2.7877756579826877e-06, + "loss": 0.0025, + "step": 49459 + }, + { + "epoch": 15.27, + "learning_rate": 2.787429233335349e-06, + "loss": 0.0019, + "step": 49460 + }, + { + "epoch": 15.27, + "learning_rate": 2.787082826727965e-06, + "loss": 0.0021, + "step": 49461 + }, + { + "epoch": 15.27, + "learning_rate": 2.786736438161406e-06, + "loss": 0.0021, + "step": 49462 + }, + { + "epoch": 15.28, + "learning_rate": 2.7863900676365306e-06, + "loss": 0.0036, + "step": 49463 + }, + { + "epoch": 15.28, + "learning_rate": 2.786043715154214e-06, + "loss": 0.0028, + "step": 49464 + }, + { + "epoch": 15.28, + "learning_rate": 2.785697380715313e-06, + "loss": 0.0024, + "step": 49465 + }, + { + "epoch": 15.28, + "learning_rate": 2.7853510643207028e-06, + "loss": 0.0021, + "step": 49466 + }, + { + "epoch": 15.28, + "learning_rate": 2.785004765971242e-06, + "loss": 0.0024, + "step": 49467 + }, + { + "epoch": 15.28, + "learning_rate": 2.784658485667804e-06, + "loss": 0.0019, + "step": 49468 + }, + { + "epoch": 15.28, + "learning_rate": 2.7843122234112507e-06, + "loss": 0.0026, + "step": 49469 + }, + { + "epoch": 15.28, + "learning_rate": 2.7839659792024454e-06, + "loss": 0.0029, + "step": 49470 + }, + { + "epoch": 15.28, + "learning_rate": 2.783619753042257e-06, + "loss": 0.0024, + "step": 49471 + }, + { + "epoch": 15.28, + "learning_rate": 2.7832735449315552e-06, + "loss": 0.0026, + "step": 49472 + }, + { + "epoch": 15.28, + "learning_rate": 2.7829273548711988e-06, + "loss": 0.0022, + "step": 49473 + }, + { + "epoch": 15.28, + "learning_rate": 2.782581182862062e-06, + "loss": 0.0026, + "step": 49474 + }, + { + "epoch": 15.28, + "learning_rate": 2.782235028905005e-06, + "loss": 0.003, + "step": 49475 + }, + { + "epoch": 15.28, + "learning_rate": 2.7818888930008913e-06, + "loss": 0.0029, + "step": 49476 + }, + { + "epoch": 15.28, + "learning_rate": 2.781542775150591e-06, + "loss": 0.0027, + "step": 49477 + }, + { + "epoch": 15.28, + "learning_rate": 2.78119667535497e-06, + "loss": 0.0028, + "step": 49478 + }, + { + "epoch": 15.28, + "learning_rate": 2.7808505936148944e-06, + "loss": 0.0027, + "step": 49479 + }, + { + "epoch": 15.28, + "learning_rate": 2.780504529931225e-06, + "loss": 0.0027, + "step": 49480 + }, + { + "epoch": 15.28, + "learning_rate": 2.780158484304832e-06, + "loss": 0.0023, + "step": 49481 + }, + { + "epoch": 15.28, + "learning_rate": 2.779812456736578e-06, + "loss": 0.0035, + "step": 49482 + }, + { + "epoch": 15.28, + "learning_rate": 2.7794664472273303e-06, + "loss": 0.0024, + "step": 49483 + }, + { + "epoch": 15.28, + "learning_rate": 2.779120455777956e-06, + "loss": 0.0025, + "step": 49484 + }, + { + "epoch": 15.28, + "learning_rate": 2.7787744823893183e-06, + "loss": 0.0027, + "step": 49485 + }, + { + "epoch": 15.28, + "learning_rate": 2.77842852706228e-06, + "loss": 0.0025, + "step": 49486 + }, + { + "epoch": 15.28, + "learning_rate": 2.7780825897977127e-06, + "loss": 0.0023, + "step": 49487 + }, + { + "epoch": 15.28, + "learning_rate": 2.7777366705964738e-06, + "loss": 0.0028, + "step": 49488 + }, + { + "epoch": 15.28, + "learning_rate": 2.777390769459437e-06, + "loss": 0.0031, + "step": 49489 + }, + { + "epoch": 15.28, + "learning_rate": 2.7770448863874623e-06, + "loss": 0.0033, + "step": 49490 + }, + { + "epoch": 15.28, + "learning_rate": 2.7766990213814128e-06, + "loss": 0.0033, + "step": 49491 + }, + { + "epoch": 15.28, + "learning_rate": 2.7763531744421567e-06, + "loss": 0.0027, + "step": 49492 + }, + { + "epoch": 15.28, + "learning_rate": 2.7760073455705627e-06, + "loss": 0.0025, + "step": 49493 + }, + { + "epoch": 15.28, + "learning_rate": 2.7756615347674876e-06, + "loss": 0.0028, + "step": 49494 + }, + { + "epoch": 15.28, + "learning_rate": 2.775315742033804e-06, + "loss": 0.0031, + "step": 49495 + }, + { + "epoch": 15.29, + "learning_rate": 2.7749699673703733e-06, + "loss": 0.003, + "step": 49496 + }, + { + "epoch": 15.29, + "learning_rate": 2.7746242107780587e-06, + "loss": 0.0022, + "step": 49497 + }, + { + "epoch": 15.29, + "learning_rate": 2.7742784722577256e-06, + "loss": 0.0023, + "step": 49498 + }, + { + "epoch": 15.29, + "learning_rate": 2.7739327518102422e-06, + "loss": 0.0024, + "step": 49499 + }, + { + "epoch": 15.29, + "learning_rate": 2.7735870494364726e-06, + "loss": 0.0028, + "step": 49500 + }, + { + "epoch": 15.29, + "learning_rate": 2.7732413651372757e-06, + "loss": 0.0023, + "step": 49501 + }, + { + "epoch": 15.29, + "learning_rate": 2.7728956989135204e-06, + "loss": 0.0028, + "step": 49502 + }, + { + "epoch": 15.29, + "learning_rate": 2.772550050766074e-06, + "loss": 0.0031, + "step": 49503 + }, + { + "epoch": 15.29, + "learning_rate": 2.7722044206957955e-06, + "loss": 0.0024, + "step": 49504 + }, + { + "epoch": 15.29, + "learning_rate": 2.771858808703556e-06, + "loss": 0.0029, + "step": 49505 + }, + { + "epoch": 15.29, + "learning_rate": 2.7715132147902148e-06, + "loss": 0.0024, + "step": 49506 + }, + { + "epoch": 15.29, + "learning_rate": 2.7711676389566343e-06, + "loss": 0.002, + "step": 49507 + }, + { + "epoch": 15.29, + "learning_rate": 2.7708220812036824e-06, + "loss": 0.0025, + "step": 49508 + }, + { + "epoch": 15.29, + "learning_rate": 2.7704765415322254e-06, + "loss": 0.0023, + "step": 49509 + }, + { + "epoch": 15.29, + "learning_rate": 2.7701310199431254e-06, + "loss": 0.0022, + "step": 49510 + }, + { + "epoch": 15.29, + "learning_rate": 2.769785516437243e-06, + "loss": 0.0023, + "step": 49511 + }, + { + "epoch": 15.29, + "learning_rate": 2.76944003101545e-06, + "loss": 0.0026, + "step": 49512 + }, + { + "epoch": 15.29, + "learning_rate": 2.7690945636786027e-06, + "loss": 0.0031, + "step": 49513 + }, + { + "epoch": 15.29, + "learning_rate": 2.768749114427568e-06, + "loss": 0.0028, + "step": 49514 + }, + { + "epoch": 15.29, + "learning_rate": 2.7684036832632176e-06, + "loss": 0.0018, + "step": 49515 + }, + { + "epoch": 15.29, + "learning_rate": 2.768058270186402e-06, + "loss": 0.0026, + "step": 49516 + }, + { + "epoch": 15.29, + "learning_rate": 2.767712875197992e-06, + "loss": 0.0014, + "step": 49517 + }, + { + "epoch": 15.29, + "learning_rate": 2.767367498298854e-06, + "loss": 0.0019, + "step": 49518 + }, + { + "epoch": 15.29, + "learning_rate": 2.7670221394898454e-06, + "loss": 0.0032, + "step": 49519 + }, + { + "epoch": 15.29, + "learning_rate": 2.766676798771838e-06, + "loss": 0.0021, + "step": 49520 + }, + { + "epoch": 15.29, + "learning_rate": 2.7663314761456904e-06, + "loss": 0.0032, + "step": 49521 + }, + { + "epoch": 15.29, + "learning_rate": 2.765986171612264e-06, + "loss": 0.002, + "step": 49522 + }, + { + "epoch": 15.29, + "learning_rate": 2.765640885172426e-06, + "loss": 0.0024, + "step": 49523 + }, + { + "epoch": 15.29, + "learning_rate": 2.765295616827042e-06, + "loss": 0.0022, + "step": 49524 + }, + { + "epoch": 15.29, + "learning_rate": 2.764950366576974e-06, + "loss": 0.0032, + "step": 49525 + }, + { + "epoch": 15.29, + "learning_rate": 2.7646051344230806e-06, + "loss": 0.004, + "step": 49526 + }, + { + "epoch": 15.29, + "learning_rate": 2.7642599203662336e-06, + "loss": 0.0026, + "step": 49527 + }, + { + "epoch": 15.3, + "learning_rate": 2.7639147244072886e-06, + "loss": 0.0049, + "step": 49528 + }, + { + "epoch": 15.3, + "learning_rate": 2.7635695465471134e-06, + "loss": 0.0026, + "step": 49529 + }, + { + "epoch": 15.3, + "learning_rate": 2.763224386786573e-06, + "loss": 0.003, + "step": 49530 + }, + { + "epoch": 15.3, + "learning_rate": 2.7628792451265283e-06, + "loss": 0.0028, + "step": 49531 + }, + { + "epoch": 15.3, + "learning_rate": 2.7625341215678393e-06, + "loss": 0.0024, + "step": 49532 + }, + { + "epoch": 15.3, + "learning_rate": 2.762189016111373e-06, + "loss": 0.002, + "step": 49533 + }, + { + "epoch": 15.3, + "learning_rate": 2.7618439287579946e-06, + "loss": 0.002, + "step": 49534 + }, + { + "epoch": 15.3, + "learning_rate": 2.7614988595085623e-06, + "loss": 0.0025, + "step": 49535 + }, + { + "epoch": 15.3, + "learning_rate": 2.7611538083639443e-06, + "loss": 0.0029, + "step": 49536 + }, + { + "epoch": 15.3, + "learning_rate": 2.760808775325001e-06, + "loss": 0.0032, + "step": 49537 + }, + { + "epoch": 15.3, + "learning_rate": 2.760463760392592e-06, + "loss": 0.0029, + "step": 49538 + }, + { + "epoch": 15.3, + "learning_rate": 2.760118763567584e-06, + "loss": 0.0021, + "step": 49539 + }, + { + "epoch": 15.3, + "learning_rate": 2.759773784850842e-06, + "loss": 0.0033, + "step": 49540 + }, + { + "epoch": 15.3, + "learning_rate": 2.7594288242432265e-06, + "loss": 0.003, + "step": 49541 + }, + { + "epoch": 15.3, + "learning_rate": 2.7590838817455968e-06, + "loss": 0.003, + "step": 49542 + }, + { + "epoch": 15.3, + "learning_rate": 2.758738957358823e-06, + "loss": 0.0033, + "step": 49543 + }, + { + "epoch": 15.3, + "learning_rate": 2.758394051083759e-06, + "loss": 0.0019, + "step": 49544 + }, + { + "epoch": 15.3, + "learning_rate": 2.7580491629212736e-06, + "loss": 0.0029, + "step": 49545 + }, + { + "epoch": 15.3, + "learning_rate": 2.757704292872234e-06, + "loss": 0.0027, + "step": 49546 + }, + { + "epoch": 15.3, + "learning_rate": 2.7573594409374905e-06, + "loss": 0.0027, + "step": 49547 + }, + { + "epoch": 15.3, + "learning_rate": 2.7570146071179127e-06, + "loss": 0.0026, + "step": 49548 + }, + { + "epoch": 15.3, + "learning_rate": 2.7566697914143647e-06, + "loss": 0.0032, + "step": 49549 + }, + { + "epoch": 15.3, + "learning_rate": 2.7563249938277038e-06, + "loss": 0.0032, + "step": 49550 + }, + { + "epoch": 15.3, + "learning_rate": 2.7559802143587976e-06, + "loss": 0.0023, + "step": 49551 + }, + { + "epoch": 15.3, + "learning_rate": 2.7556354530085073e-06, + "loss": 0.0019, + "step": 49552 + }, + { + "epoch": 15.3, + "learning_rate": 2.7552907097776904e-06, + "loss": 0.0025, + "step": 49553 + }, + { + "epoch": 15.3, + "learning_rate": 2.7549459846672134e-06, + "loss": 0.0026, + "step": 49554 + }, + { + "epoch": 15.3, + "learning_rate": 2.7546012776779407e-06, + "loss": 0.0021, + "step": 49555 + }, + { + "epoch": 15.3, + "learning_rate": 2.754256588810731e-06, + "loss": 0.0016, + "step": 49556 + }, + { + "epoch": 15.3, + "learning_rate": 2.753911918066444e-06, + "loss": 0.0027, + "step": 49557 + }, + { + "epoch": 15.3, + "learning_rate": 2.753567265445949e-06, + "loss": 0.0021, + "step": 49558 + }, + { + "epoch": 15.3, + "learning_rate": 2.7532226309501e-06, + "loss": 0.0025, + "step": 49559 + }, + { + "epoch": 15.31, + "learning_rate": 2.752878014579764e-06, + "loss": 0.0028, + "step": 49560 + }, + { + "epoch": 15.31, + "learning_rate": 2.752533416335804e-06, + "loss": 0.0023, + "step": 49561 + }, + { + "epoch": 15.31, + "learning_rate": 2.75218883621908e-06, + "loss": 0.0026, + "step": 49562 + }, + { + "epoch": 15.31, + "learning_rate": 2.751844274230451e-06, + "loss": 0.003, + "step": 49563 + }, + { + "epoch": 15.31, + "learning_rate": 2.75149973037078e-06, + "loss": 0.0026, + "step": 49564 + }, + { + "epoch": 15.31, + "learning_rate": 2.751155204640934e-06, + "loss": 0.0019, + "step": 49565 + }, + { + "epoch": 15.31, + "learning_rate": 2.7508106970417716e-06, + "loss": 0.0024, + "step": 49566 + }, + { + "epoch": 15.31, + "learning_rate": 2.750466207574151e-06, + "loss": 0.0025, + "step": 49567 + }, + { + "epoch": 15.31, + "learning_rate": 2.750121736238939e-06, + "loss": 0.0023, + "step": 49568 + }, + { + "epoch": 15.31, + "learning_rate": 2.749777283036992e-06, + "loss": 0.0028, + "step": 49569 + }, + { + "epoch": 15.31, + "learning_rate": 2.7494328479691735e-06, + "loss": 0.002, + "step": 49570 + }, + { + "epoch": 15.31, + "learning_rate": 2.7490884310363497e-06, + "loss": 0.0031, + "step": 49571 + }, + { + "epoch": 15.31, + "learning_rate": 2.748744032239379e-06, + "loss": 0.0034, + "step": 49572 + }, + { + "epoch": 15.31, + "learning_rate": 2.7483996515791176e-06, + "loss": 0.0021, + "step": 49573 + }, + { + "epoch": 15.31, + "learning_rate": 2.7480552890564348e-06, + "loss": 0.0026, + "step": 49574 + }, + { + "epoch": 15.31, + "learning_rate": 2.747710944672185e-06, + "loss": 0.0028, + "step": 49575 + }, + { + "epoch": 15.31, + "learning_rate": 2.747366618427236e-06, + "loss": 0.0033, + "step": 49576 + }, + { + "epoch": 15.31, + "learning_rate": 2.7470223103224468e-06, + "loss": 0.0028, + "step": 49577 + }, + { + "epoch": 15.31, + "learning_rate": 2.746678020358674e-06, + "loss": 0.003, + "step": 49578 + }, + { + "epoch": 15.31, + "learning_rate": 2.7463337485367825e-06, + "loss": 0.0026, + "step": 49579 + }, + { + "epoch": 15.31, + "learning_rate": 2.745989494857636e-06, + "loss": 0.0025, + "step": 49580 + }, + { + "epoch": 15.31, + "learning_rate": 2.7456452593220906e-06, + "loss": 0.003, + "step": 49581 + }, + { + "epoch": 15.31, + "learning_rate": 2.745301041931012e-06, + "loss": 0.0025, + "step": 49582 + }, + { + "epoch": 15.31, + "learning_rate": 2.744956842685258e-06, + "loss": 0.0027, + "step": 49583 + }, + { + "epoch": 15.31, + "learning_rate": 2.744612661585688e-06, + "loss": 0.0032, + "step": 49584 + }, + { + "epoch": 15.31, + "learning_rate": 2.7442684986331648e-06, + "loss": 0.0032, + "step": 49585 + }, + { + "epoch": 15.31, + "learning_rate": 2.743924353828553e-06, + "loss": 0.0023, + "step": 49586 + }, + { + "epoch": 15.31, + "learning_rate": 2.74358022717271e-06, + "loss": 0.0027, + "step": 49587 + }, + { + "epoch": 15.31, + "learning_rate": 2.7432361186664915e-06, + "loss": 0.0029, + "step": 49588 + }, + { + "epoch": 15.31, + "learning_rate": 2.7428920283107674e-06, + "loss": 0.0023, + "step": 49589 + }, + { + "epoch": 15.31, + "learning_rate": 2.7425479561063906e-06, + "loss": 0.0026, + "step": 49590 + }, + { + "epoch": 15.31, + "learning_rate": 2.7422039020542255e-06, + "loss": 0.0025, + "step": 49591 + }, + { + "epoch": 15.31, + "learning_rate": 2.7418598661551344e-06, + "loss": 0.0035, + "step": 49592 + }, + { + "epoch": 15.32, + "learning_rate": 2.7415158484099756e-06, + "loss": 0.0023, + "step": 49593 + }, + { + "epoch": 15.32, + "learning_rate": 2.741171848819607e-06, + "loss": 0.0021, + "step": 49594 + }, + { + "epoch": 15.32, + "learning_rate": 2.7408278673848952e-06, + "loss": 0.0022, + "step": 49595 + }, + { + "epoch": 15.32, + "learning_rate": 2.7404839041066934e-06, + "loss": 0.0029, + "step": 49596 + }, + { + "epoch": 15.32, + "learning_rate": 2.740139958985868e-06, + "loss": 0.002, + "step": 49597 + }, + { + "epoch": 15.32, + "learning_rate": 2.7397960320232744e-06, + "loss": 0.002, + "step": 49598 + }, + { + "epoch": 15.32, + "learning_rate": 2.739452123219777e-06, + "loss": 0.0033, + "step": 49599 + }, + { + "epoch": 15.32, + "learning_rate": 2.739108232576232e-06, + "loss": 0.0025, + "step": 49600 + }, + { + "epoch": 15.32, + "learning_rate": 2.738764360093501e-06, + "loss": 0.0044, + "step": 49601 + }, + { + "epoch": 15.32, + "learning_rate": 2.738420505772448e-06, + "loss": 0.0029, + "step": 49602 + }, + { + "epoch": 15.32, + "learning_rate": 2.7380766696139295e-06, + "loss": 0.0025, + "step": 49603 + }, + { + "epoch": 15.32, + "learning_rate": 2.737732851618803e-06, + "loss": 0.0027, + "step": 49604 + }, + { + "epoch": 15.32, + "learning_rate": 2.7373890517879342e-06, + "loss": 0.0022, + "step": 49605 + }, + { + "epoch": 15.32, + "learning_rate": 2.737045270122177e-06, + "loss": 0.0039, + "step": 49606 + }, + { + "epoch": 15.32, + "learning_rate": 2.7367015066223966e-06, + "loss": 0.0023, + "step": 49607 + }, + { + "epoch": 15.32, + "learning_rate": 2.736357761289452e-06, + "loss": 0.0026, + "step": 49608 + }, + { + "epoch": 15.32, + "learning_rate": 2.736014034124197e-06, + "loss": 0.0028, + "step": 49609 + }, + { + "epoch": 15.32, + "learning_rate": 2.7356703251274964e-06, + "loss": 0.0024, + "step": 49610 + }, + { + "epoch": 15.32, + "learning_rate": 2.7353266343002115e-06, + "loss": 0.0026, + "step": 49611 + }, + { + "epoch": 15.32, + "learning_rate": 2.734982961643198e-06, + "loss": 0.0023, + "step": 49612 + }, + { + "epoch": 15.32, + "learning_rate": 2.7346393071573194e-06, + "loss": 0.0027, + "step": 49613 + }, + { + "epoch": 15.32, + "learning_rate": 2.734295670843433e-06, + "loss": 0.0024, + "step": 49614 + }, + { + "epoch": 15.32, + "learning_rate": 2.7339520527023954e-06, + "loss": 0.0021, + "step": 49615 + }, + { + "epoch": 15.32, + "learning_rate": 2.7336084527350693e-06, + "loss": 0.0025, + "step": 49616 + }, + { + "epoch": 15.32, + "learning_rate": 2.733264870942316e-06, + "loss": 0.002, + "step": 49617 + }, + { + "epoch": 15.32, + "learning_rate": 2.7329213073249926e-06, + "loss": 0.0029, + "step": 49618 + }, + { + "epoch": 15.32, + "learning_rate": 2.732577761883957e-06, + "loss": 0.0027, + "step": 49619 + }, + { + "epoch": 15.32, + "learning_rate": 2.7322342346200715e-06, + "loss": 0.0029, + "step": 49620 + }, + { + "epoch": 15.32, + "learning_rate": 2.731890725534191e-06, + "loss": 0.0028, + "step": 49621 + }, + { + "epoch": 15.32, + "learning_rate": 2.7315472346271775e-06, + "loss": 0.0027, + "step": 49622 + }, + { + "epoch": 15.32, + "learning_rate": 2.731203761899893e-06, + "loss": 0.0022, + "step": 49623 + }, + { + "epoch": 15.32, + "learning_rate": 2.7308603073531938e-06, + "loss": 0.0023, + "step": 49624 + }, + { + "epoch": 15.33, + "learning_rate": 2.730516870987936e-06, + "loss": 0.0027, + "step": 49625 + }, + { + "epoch": 15.33, + "learning_rate": 2.730173452804984e-06, + "loss": 0.0022, + "step": 49626 + }, + { + "epoch": 15.33, + "learning_rate": 2.7298300528051902e-06, + "loss": 0.0029, + "step": 49627 + }, + { + "epoch": 15.33, + "learning_rate": 2.7294866709894217e-06, + "loss": 0.0028, + "step": 49628 + }, + { + "epoch": 15.33, + "learning_rate": 2.7291433073585295e-06, + "loss": 0.0021, + "step": 49629 + }, + { + "epoch": 15.33, + "learning_rate": 2.72879996191338e-06, + "loss": 0.003, + "step": 49630 + }, + { + "epoch": 15.33, + "learning_rate": 2.7284566346548236e-06, + "loss": 0.0029, + "step": 49631 + }, + { + "epoch": 15.33, + "learning_rate": 2.7281133255837244e-06, + "loss": 0.0028, + "step": 49632 + }, + { + "epoch": 15.33, + "learning_rate": 2.727770034700943e-06, + "loss": 0.0028, + "step": 49633 + }, + { + "epoch": 15.33, + "learning_rate": 2.7274267620073347e-06, + "loss": 0.0031, + "step": 49634 + }, + { + "epoch": 15.33, + "learning_rate": 2.727083507503756e-06, + "loss": 0.0024, + "step": 49635 + }, + { + "epoch": 15.33, + "learning_rate": 2.7267402711910705e-06, + "loss": 0.0037, + "step": 49636 + }, + { + "epoch": 15.33, + "learning_rate": 2.726397053070131e-06, + "loss": 0.0027, + "step": 49637 + }, + { + "epoch": 15.33, + "learning_rate": 2.7260538531418025e-06, + "loss": 0.0021, + "step": 49638 + }, + { + "epoch": 15.33, + "learning_rate": 2.725710671406939e-06, + "loss": 0.0029, + "step": 49639 + }, + { + "epoch": 15.33, + "learning_rate": 2.725367507866399e-06, + "loss": 0.002, + "step": 49640 + }, + { + "epoch": 15.33, + "learning_rate": 2.7250243625210394e-06, + "loss": 0.0042, + "step": 49641 + }, + { + "epoch": 15.33, + "learning_rate": 2.7246812353717244e-06, + "loss": 0.004, + "step": 49642 + }, + { + "epoch": 15.33, + "learning_rate": 2.724338126419307e-06, + "loss": 0.002, + "step": 49643 + }, + { + "epoch": 15.33, + "learning_rate": 2.723995035664648e-06, + "loss": 0.0022, + "step": 49644 + }, + { + "epoch": 15.33, + "learning_rate": 2.7236519631086055e-06, + "loss": 0.0028, + "step": 49645 + }, + { + "epoch": 15.33, + "learning_rate": 2.7233089087520335e-06, + "loss": 0.0019, + "step": 49646 + }, + { + "epoch": 15.33, + "learning_rate": 2.722965872595793e-06, + "loss": 0.0028, + "step": 49647 + }, + { + "epoch": 15.33, + "learning_rate": 2.7226228546407454e-06, + "loss": 0.0021, + "step": 49648 + }, + { + "epoch": 15.33, + "learning_rate": 2.722279854887745e-06, + "loss": 0.0026, + "step": 49649 + }, + { + "epoch": 15.33, + "learning_rate": 2.721936873337647e-06, + "loss": 0.0021, + "step": 49650 + }, + { + "epoch": 15.33, + "learning_rate": 2.7215939099913146e-06, + "loss": 0.0027, + "step": 49651 + }, + { + "epoch": 15.33, + "learning_rate": 2.721250964849602e-06, + "loss": 0.0031, + "step": 49652 + }, + { + "epoch": 15.33, + "learning_rate": 2.720908037913367e-06, + "loss": 0.0025, + "step": 49653 + }, + { + "epoch": 15.33, + "learning_rate": 2.7205651291834757e-06, + "loss": 0.0032, + "step": 49654 + }, + { + "epoch": 15.33, + "learning_rate": 2.7202222386607715e-06, + "loss": 0.0031, + "step": 49655 + }, + { + "epoch": 15.33, + "learning_rate": 2.71987936634612e-06, + "loss": 0.0026, + "step": 49656 + }, + { + "epoch": 15.33, + "learning_rate": 2.7195365122403806e-06, + "loss": 0.0027, + "step": 49657 + }, + { + "epoch": 15.34, + "learning_rate": 2.719193676344405e-06, + "loss": 0.0023, + "step": 49658 + }, + { + "epoch": 15.34, + "learning_rate": 2.718850858659058e-06, + "loss": 0.0029, + "step": 49659 + }, + { + "epoch": 15.34, + "learning_rate": 2.718508059185192e-06, + "loss": 0.0027, + "step": 49660 + }, + { + "epoch": 15.34, + "learning_rate": 2.7181652779236634e-06, + "loss": 0.003, + "step": 49661 + }, + { + "epoch": 15.34, + "learning_rate": 2.71782251487533e-06, + "loss": 0.0027, + "step": 49662 + }, + { + "epoch": 15.34, + "learning_rate": 2.7174797700410526e-06, + "loss": 0.0021, + "step": 49663 + }, + { + "epoch": 15.34, + "learning_rate": 2.7171370434216916e-06, + "loss": 0.0029, + "step": 49664 + }, + { + "epoch": 15.34, + "learning_rate": 2.7167943350180925e-06, + "loss": 0.0036, + "step": 49665 + }, + { + "epoch": 15.34, + "learning_rate": 2.7164516448311194e-06, + "loss": 0.003, + "step": 49666 + }, + { + "epoch": 15.34, + "learning_rate": 2.716108972861633e-06, + "loss": 0.0026, + "step": 49667 + }, + { + "epoch": 15.34, + "learning_rate": 2.7157663191104834e-06, + "loss": 0.0022, + "step": 49668 + }, + { + "epoch": 15.34, + "learning_rate": 2.715423683578533e-06, + "loss": 0.0024, + "step": 49669 + }, + { + "epoch": 15.34, + "learning_rate": 2.7150810662666373e-06, + "loss": 0.0017, + "step": 49670 + }, + { + "epoch": 15.34, + "learning_rate": 2.7147384671756496e-06, + "loss": 0.0027, + "step": 49671 + }, + { + "epoch": 15.34, + "learning_rate": 2.714395886306429e-06, + "loss": 0.0024, + "step": 49672 + }, + { + "epoch": 15.34, + "learning_rate": 2.7140533236598367e-06, + "loss": 0.0022, + "step": 49673 + }, + { + "epoch": 15.34, + "learning_rate": 2.7137107792367256e-06, + "loss": 0.0026, + "step": 49674 + }, + { + "epoch": 15.34, + "learning_rate": 2.71336825303795e-06, + "loss": 0.0025, + "step": 49675 + }, + { + "epoch": 15.34, + "learning_rate": 2.7130257450643726e-06, + "loss": 0.0022, + "step": 49676 + }, + { + "epoch": 15.34, + "learning_rate": 2.7126832553168435e-06, + "loss": 0.0019, + "step": 49677 + }, + { + "epoch": 15.34, + "learning_rate": 2.7123407837962233e-06, + "loss": 0.0023, + "step": 49678 + }, + { + "epoch": 15.34, + "learning_rate": 2.71199833050337e-06, + "loss": 0.0019, + "step": 49679 + }, + { + "epoch": 15.34, + "learning_rate": 2.711655895439139e-06, + "loss": 0.0024, + "step": 49680 + }, + { + "epoch": 15.34, + "learning_rate": 2.7113134786043827e-06, + "loss": 0.0022, + "step": 49681 + }, + { + "epoch": 15.34, + "learning_rate": 2.7109710799999632e-06, + "loss": 0.0029, + "step": 49682 + }, + { + "epoch": 15.34, + "learning_rate": 2.7106286996267328e-06, + "loss": 0.0032, + "step": 49683 + }, + { + "epoch": 15.34, + "learning_rate": 2.7102863374855515e-06, + "loss": 0.0025, + "step": 49684 + }, + { + "epoch": 15.34, + "learning_rate": 2.709943993577273e-06, + "loss": 0.0025, + "step": 49685 + }, + { + "epoch": 15.34, + "learning_rate": 2.7096016679027526e-06, + "loss": 0.0033, + "step": 49686 + }, + { + "epoch": 15.34, + "learning_rate": 2.709259360462847e-06, + "loss": 0.0012, + "step": 49687 + }, + { + "epoch": 15.34, + "learning_rate": 2.7089170712584177e-06, + "loss": 0.0034, + "step": 49688 + }, + { + "epoch": 15.34, + "learning_rate": 2.7085748002903123e-06, + "loss": 0.0024, + "step": 49689 + }, + { + "epoch": 15.35, + "learning_rate": 2.708232547559395e-06, + "loss": 0.0028, + "step": 49690 + }, + { + "epoch": 15.35, + "learning_rate": 2.7078903130665178e-06, + "loss": 0.003, + "step": 49691 + }, + { + "epoch": 15.35, + "learning_rate": 2.7075480968125345e-06, + "loss": 0.0025, + "step": 49692 + }, + { + "epoch": 15.35, + "learning_rate": 2.707205898798302e-06, + "loss": 0.0028, + "step": 49693 + }, + { + "epoch": 15.35, + "learning_rate": 2.7068637190246818e-06, + "loss": 0.0022, + "step": 49694 + }, + { + "epoch": 15.35, + "learning_rate": 2.706521557492525e-06, + "loss": 0.0032, + "step": 49695 + }, + { + "epoch": 15.35, + "learning_rate": 2.7061794142026866e-06, + "loss": 0.0023, + "step": 49696 + }, + { + "epoch": 15.35, + "learning_rate": 2.7058372891560227e-06, + "loss": 0.0029, + "step": 49697 + }, + { + "epoch": 15.35, + "learning_rate": 2.7054951823533926e-06, + "loss": 0.0022, + "step": 49698 + }, + { + "epoch": 15.35, + "learning_rate": 2.7051530937956472e-06, + "loss": 0.0025, + "step": 49699 + }, + { + "epoch": 15.35, + "learning_rate": 2.7048110234836467e-06, + "loss": 0.0027, + "step": 49700 + }, + { + "epoch": 15.35, + "learning_rate": 2.704468971418245e-06, + "loss": 0.002, + "step": 49701 + }, + { + "epoch": 15.35, + "learning_rate": 2.7041269376002934e-06, + "loss": 0.0024, + "step": 49702 + }, + { + "epoch": 15.35, + "learning_rate": 2.703784922030651e-06, + "loss": 0.0023, + "step": 49703 + }, + { + "epoch": 15.35, + "learning_rate": 2.703442924710178e-06, + "loss": 0.0022, + "step": 49704 + }, + { + "epoch": 15.35, + "learning_rate": 2.703100945639723e-06, + "loss": 0.0025, + "step": 49705 + }, + { + "epoch": 15.35, + "learning_rate": 2.7027589848201406e-06, + "loss": 0.003, + "step": 49706 + }, + { + "epoch": 15.35, + "learning_rate": 2.7024170422522934e-06, + "loss": 0.0035, + "step": 49707 + }, + { + "epoch": 15.35, + "learning_rate": 2.7020751179370274e-06, + "loss": 0.0031, + "step": 49708 + }, + { + "epoch": 15.35, + "learning_rate": 2.7017332118752038e-06, + "loss": 0.0025, + "step": 49709 + }, + { + "epoch": 15.35, + "learning_rate": 2.701391324067679e-06, + "loss": 0.0023, + "step": 49710 + }, + { + "epoch": 15.35, + "learning_rate": 2.7010494545153066e-06, + "loss": 0.0024, + "step": 49711 + }, + { + "epoch": 15.35, + "learning_rate": 2.7007076032189372e-06, + "loss": 0.0035, + "step": 49712 + }, + { + "epoch": 15.35, + "learning_rate": 2.700365770179432e-06, + "loss": 0.0027, + "step": 49713 + }, + { + "epoch": 15.35, + "learning_rate": 2.70002395539764e-06, + "loss": 0.0032, + "step": 49714 + }, + { + "epoch": 15.35, + "learning_rate": 2.699682158874424e-06, + "loss": 0.0021, + "step": 49715 + }, + { + "epoch": 15.35, + "learning_rate": 2.6993403806106333e-06, + "loss": 0.0034, + "step": 49716 + }, + { + "epoch": 15.35, + "learning_rate": 2.6989986206071206e-06, + "loss": 0.0016, + "step": 49717 + }, + { + "epoch": 15.35, + "learning_rate": 2.698656878864745e-06, + "loss": 0.0024, + "step": 49718 + }, + { + "epoch": 15.35, + "learning_rate": 2.6983151553843625e-06, + "loss": 0.0028, + "step": 49719 + }, + { + "epoch": 15.35, + "learning_rate": 2.697973450166823e-06, + "loss": 0.0034, + "step": 49720 + }, + { + "epoch": 15.35, + "learning_rate": 2.697631763212987e-06, + "loss": 0.0025, + "step": 49721 + }, + { + "epoch": 15.36, + "learning_rate": 2.6972900945237046e-06, + "loss": 0.0029, + "step": 49722 + }, + { + "epoch": 15.36, + "learning_rate": 2.6969484440998295e-06, + "loss": 0.0022, + "step": 49723 + }, + { + "epoch": 15.36, + "learning_rate": 2.6966068119422183e-06, + "loss": 0.0014, + "step": 49724 + }, + { + "epoch": 15.36, + "learning_rate": 2.6962651980517284e-06, + "loss": 0.003, + "step": 49725 + }, + { + "epoch": 15.36, + "learning_rate": 2.6959236024292112e-06, + "loss": 0.0024, + "step": 49726 + }, + { + "epoch": 15.36, + "learning_rate": 2.695582025075518e-06, + "loss": 0.0021, + "step": 49727 + }, + { + "epoch": 15.36, + "learning_rate": 2.6952404659915065e-06, + "loss": 0.0025, + "step": 49728 + }, + { + "epoch": 15.36, + "learning_rate": 2.6948989251780345e-06, + "loss": 0.0023, + "step": 49729 + }, + { + "epoch": 15.36, + "learning_rate": 2.694557402635949e-06, + "loss": 0.0023, + "step": 49730 + }, + { + "epoch": 15.36, + "learning_rate": 2.6942158983661116e-06, + "loss": 0.0021, + "step": 49731 + }, + { + "epoch": 15.36, + "learning_rate": 2.693874412369373e-06, + "loss": 0.0027, + "step": 49732 + }, + { + "epoch": 15.36, + "learning_rate": 2.693532944646583e-06, + "loss": 0.0027, + "step": 49733 + }, + { + "epoch": 15.36, + "learning_rate": 2.6931914951985992e-06, + "loss": 0.003, + "step": 49734 + }, + { + "epoch": 15.36, + "learning_rate": 2.69285006402628e-06, + "loss": 0.0024, + "step": 49735 + }, + { + "epoch": 15.36, + "learning_rate": 2.6925086511304767e-06, + "loss": 0.002, + "step": 49736 + }, + { + "epoch": 15.36, + "learning_rate": 2.692167256512037e-06, + "loss": 0.0023, + "step": 49737 + }, + { + "epoch": 15.36, + "learning_rate": 2.6918258801718245e-06, + "loss": 0.0022, + "step": 49738 + }, + { + "epoch": 15.36, + "learning_rate": 2.6914845221106843e-06, + "loss": 0.003, + "step": 49739 + }, + { + "epoch": 15.36, + "learning_rate": 2.6911431823294743e-06, + "loss": 0.0029, + "step": 49740 + }, + { + "epoch": 15.36, + "learning_rate": 2.6908018608290522e-06, + "loss": 0.0027, + "step": 49741 + }, + { + "epoch": 15.36, + "learning_rate": 2.690460557610267e-06, + "loss": 0.0031, + "step": 49742 + }, + { + "epoch": 15.36, + "learning_rate": 2.69011927267397e-06, + "loss": 0.0035, + "step": 49743 + }, + { + "epoch": 15.36, + "learning_rate": 2.689778006021022e-06, + "loss": 0.0027, + "step": 49744 + }, + { + "epoch": 15.36, + "learning_rate": 2.6894367576522686e-06, + "loss": 0.0024, + "step": 49745 + }, + { + "epoch": 15.36, + "learning_rate": 2.6890955275685702e-06, + "loss": 0.0023, + "step": 49746 + }, + { + "epoch": 15.36, + "learning_rate": 2.6887543157707775e-06, + "loss": 0.0023, + "step": 49747 + }, + { + "epoch": 15.36, + "learning_rate": 2.688413122259741e-06, + "loss": 0.0034, + "step": 49748 + }, + { + "epoch": 15.36, + "learning_rate": 2.688071947036316e-06, + "loss": 0.0033, + "step": 49749 + }, + { + "epoch": 15.36, + "learning_rate": 2.6877307901013604e-06, + "loss": 0.0022, + "step": 49750 + }, + { + "epoch": 15.36, + "learning_rate": 2.687389651455721e-06, + "loss": 0.0026, + "step": 49751 + }, + { + "epoch": 15.36, + "learning_rate": 2.687048531100256e-06, + "loss": 0.0021, + "step": 49752 + }, + { + "epoch": 15.36, + "learning_rate": 2.6867074290358174e-06, + "loss": 0.0046, + "step": 49753 + }, + { + "epoch": 15.36, + "learning_rate": 2.6863663452632536e-06, + "loss": 0.0034, + "step": 49754 + }, + { + "epoch": 15.37, + "learning_rate": 2.6860252797834217e-06, + "loss": 0.0025, + "step": 49755 + }, + { + "epoch": 15.37, + "learning_rate": 2.6856842325971777e-06, + "loss": 0.0028, + "step": 49756 + }, + { + "epoch": 15.37, + "learning_rate": 2.685343203705372e-06, + "loss": 0.0034, + "step": 49757 + }, + { + "epoch": 15.37, + "learning_rate": 2.6850021931088534e-06, + "loss": 0.0021, + "step": 49758 + }, + { + "epoch": 15.37, + "learning_rate": 2.6846612008084804e-06, + "loss": 0.0022, + "step": 49759 + }, + { + "epoch": 15.37, + "learning_rate": 2.684320226805103e-06, + "loss": 0.0025, + "step": 49760 + }, + { + "epoch": 15.37, + "learning_rate": 2.6839792710995737e-06, + "loss": 0.0028, + "step": 49761 + }, + { + "epoch": 15.37, + "learning_rate": 2.6836383336927498e-06, + "loss": 0.0031, + "step": 49762 + }, + { + "epoch": 15.37, + "learning_rate": 2.683297414585482e-06, + "loss": 0.0027, + "step": 49763 + }, + { + "epoch": 15.37, + "learning_rate": 2.6829565137786173e-06, + "loss": 0.0032, + "step": 49764 + }, + { + "epoch": 15.37, + "learning_rate": 2.6826156312730135e-06, + "loss": 0.0027, + "step": 49765 + }, + { + "epoch": 15.37, + "learning_rate": 2.682274767069526e-06, + "loss": 0.0021, + "step": 49766 + }, + { + "epoch": 15.37, + "learning_rate": 2.681933921169003e-06, + "loss": 0.0025, + "step": 49767 + }, + { + "epoch": 15.37, + "learning_rate": 2.6815930935722954e-06, + "loss": 0.0025, + "step": 49768 + }, + { + "epoch": 15.37, + "learning_rate": 2.6812522842802622e-06, + "loss": 0.0032, + "step": 49769 + }, + { + "epoch": 15.37, + "learning_rate": 2.6809114932937473e-06, + "loss": 0.0038, + "step": 49770 + }, + { + "epoch": 15.37, + "learning_rate": 2.6805707206136088e-06, + "loss": 0.0027, + "step": 49771 + }, + { + "epoch": 15.37, + "learning_rate": 2.6802299662407037e-06, + "loss": 0.0028, + "step": 49772 + }, + { + "epoch": 15.37, + "learning_rate": 2.679889230175873e-06, + "loss": 0.003, + "step": 49773 + }, + { + "epoch": 15.37, + "learning_rate": 2.679548512419974e-06, + "loss": 0.0022, + "step": 49774 + }, + { + "epoch": 15.37, + "learning_rate": 2.679207812973862e-06, + "loss": 0.003, + "step": 49775 + }, + { + "epoch": 15.37, + "learning_rate": 2.678867131838384e-06, + "loss": 0.0023, + "step": 49776 + }, + { + "epoch": 15.37, + "learning_rate": 2.6785264690143962e-06, + "loss": 0.0026, + "step": 49777 + }, + { + "epoch": 15.37, + "learning_rate": 2.6781858245027503e-06, + "loss": 0.0027, + "step": 49778 + }, + { + "epoch": 15.37, + "learning_rate": 2.6778451983042943e-06, + "loss": 0.0031, + "step": 49779 + }, + { + "epoch": 15.37, + "learning_rate": 2.677504590419883e-06, + "loss": 0.0026, + "step": 49780 + }, + { + "epoch": 15.37, + "learning_rate": 2.677164000850371e-06, + "loss": 0.0024, + "step": 49781 + }, + { + "epoch": 15.37, + "learning_rate": 2.6768234295966065e-06, + "loss": 0.0023, + "step": 49782 + }, + { + "epoch": 15.37, + "learning_rate": 2.676482876659441e-06, + "loss": 0.0035, + "step": 49783 + }, + { + "epoch": 15.37, + "learning_rate": 2.6761423420397294e-06, + "loss": 0.003, + "step": 49784 + }, + { + "epoch": 15.37, + "learning_rate": 2.675801825738318e-06, + "loss": 0.0027, + "step": 49785 + }, + { + "epoch": 15.37, + "learning_rate": 2.6754613277560638e-06, + "loss": 0.0026, + "step": 49786 + }, + { + "epoch": 15.38, + "learning_rate": 2.6751208480938185e-06, + "loss": 0.003, + "step": 49787 + }, + { + "epoch": 15.38, + "learning_rate": 2.6747803867524325e-06, + "loss": 0.0019, + "step": 49788 + }, + { + "epoch": 15.38, + "learning_rate": 2.674439943732753e-06, + "loss": 0.0021, + "step": 49789 + }, + { + "epoch": 15.38, + "learning_rate": 2.674099519035639e-06, + "loss": 0.0021, + "step": 49790 + }, + { + "epoch": 15.38, + "learning_rate": 2.6737591126619343e-06, + "loss": 0.0025, + "step": 49791 + }, + { + "epoch": 15.38, + "learning_rate": 2.6734187246124953e-06, + "loss": 0.0025, + "step": 49792 + }, + { + "epoch": 15.38, + "learning_rate": 2.6730783548881754e-06, + "loss": 0.0027, + "step": 49793 + }, + { + "epoch": 15.38, + "learning_rate": 2.6727380034898232e-06, + "loss": 0.0023, + "step": 49794 + }, + { + "epoch": 15.38, + "learning_rate": 2.672397670418285e-06, + "loss": 0.0021, + "step": 49795 + }, + { + "epoch": 15.38, + "learning_rate": 2.672057355674418e-06, + "loss": 0.002, + "step": 49796 + }, + { + "epoch": 15.38, + "learning_rate": 2.6717170592590747e-06, + "loss": 0.0025, + "step": 49797 + }, + { + "epoch": 15.38, + "learning_rate": 2.6713767811731038e-06, + "loss": 0.0023, + "step": 49798 + }, + { + "epoch": 15.38, + "learning_rate": 2.671036521417354e-06, + "loss": 0.0023, + "step": 49799 + }, + { + "epoch": 15.38, + "learning_rate": 2.6706962799926805e-06, + "loss": 0.0023, + "step": 49800 + }, + { + "epoch": 15.38, + "learning_rate": 2.67035605689993e-06, + "loss": 0.0018, + "step": 49801 + }, + { + "epoch": 15.38, + "learning_rate": 2.6700158521399554e-06, + "loss": 0.003, + "step": 49802 + }, + { + "epoch": 15.38, + "learning_rate": 2.6696756657136136e-06, + "loss": 0.0025, + "step": 49803 + }, + { + "epoch": 15.38, + "learning_rate": 2.6693354976217445e-06, + "loss": 0.0022, + "step": 49804 + }, + { + "epoch": 15.38, + "learning_rate": 2.6689953478652043e-06, + "loss": 0.0026, + "step": 49805 + }, + { + "epoch": 15.38, + "learning_rate": 2.6686552164448474e-06, + "loss": 0.003, + "step": 49806 + }, + { + "epoch": 15.38, + "learning_rate": 2.6683151033615172e-06, + "loss": 0.0027, + "step": 49807 + }, + { + "epoch": 15.38, + "learning_rate": 2.6679750086160717e-06, + "loss": 0.0025, + "step": 49808 + }, + { + "epoch": 15.38, + "learning_rate": 2.6676349322093575e-06, + "loss": 0.0025, + "step": 49809 + }, + { + "epoch": 15.38, + "learning_rate": 2.667294874142222e-06, + "loss": 0.0028, + "step": 49810 + }, + { + "epoch": 15.38, + "learning_rate": 2.6669548344155204e-06, + "loss": 0.0027, + "step": 49811 + }, + { + "epoch": 15.38, + "learning_rate": 2.666614813030105e-06, + "loss": 0.0024, + "step": 49812 + }, + { + "epoch": 15.38, + "learning_rate": 2.666274809986824e-06, + "loss": 0.0026, + "step": 49813 + }, + { + "epoch": 15.38, + "learning_rate": 2.6659348252865235e-06, + "loss": 0.0031, + "step": 49814 + }, + { + "epoch": 15.38, + "learning_rate": 2.665594858930062e-06, + "loss": 0.0025, + "step": 49815 + }, + { + "epoch": 15.38, + "learning_rate": 2.6652549109182814e-06, + "loss": 0.0023, + "step": 49816 + }, + { + "epoch": 15.38, + "learning_rate": 2.664914981252036e-06, + "loss": 0.0036, + "step": 49817 + }, + { + "epoch": 15.38, + "learning_rate": 2.664575069932179e-06, + "loss": 0.0017, + "step": 49818 + }, + { + "epoch": 15.39, + "learning_rate": 2.6642351769595574e-06, + "loss": 0.002, + "step": 49819 + }, + { + "epoch": 15.39, + "learning_rate": 2.663895302335019e-06, + "loss": 0.0037, + "step": 49820 + }, + { + "epoch": 15.39, + "learning_rate": 2.663555446059419e-06, + "loss": 0.0025, + "step": 49821 + }, + { + "epoch": 15.39, + "learning_rate": 2.6632156081336034e-06, + "loss": 0.0028, + "step": 49822 + }, + { + "epoch": 15.39, + "learning_rate": 2.6628757885584257e-06, + "loss": 0.0024, + "step": 49823 + }, + { + "epoch": 15.39, + "learning_rate": 2.6625359873347336e-06, + "loss": 0.0031, + "step": 49824 + }, + { + "epoch": 15.39, + "learning_rate": 2.6621962044633743e-06, + "loss": 0.0029, + "step": 49825 + }, + { + "epoch": 15.39, + "learning_rate": 2.6618564399452006e-06, + "loss": 0.0029, + "step": 49826 + }, + { + "epoch": 15.39, + "learning_rate": 2.661516693781063e-06, + "loss": 0.0023, + "step": 49827 + }, + { + "epoch": 15.39, + "learning_rate": 2.6611769659718134e-06, + "loss": 0.0023, + "step": 49828 + }, + { + "epoch": 15.39, + "learning_rate": 2.6608372565182982e-06, + "loss": 0.002, + "step": 49829 + }, + { + "epoch": 15.39, + "learning_rate": 2.660497565421365e-06, + "loss": 0.0025, + "step": 49830 + }, + { + "epoch": 15.39, + "learning_rate": 2.6601578926818692e-06, + "loss": 0.0032, + "step": 49831 + }, + { + "epoch": 15.39, + "learning_rate": 2.6598182383006533e-06, + "loss": 0.0021, + "step": 49832 + }, + { + "epoch": 15.39, + "learning_rate": 2.6594786022785745e-06, + "loss": 0.0027, + "step": 49833 + }, + { + "epoch": 15.39, + "learning_rate": 2.6591389846164782e-06, + "loss": 0.003, + "step": 49834 + }, + { + "epoch": 15.39, + "learning_rate": 2.6587993853152115e-06, + "loss": 0.0024, + "step": 49835 + }, + { + "epoch": 15.39, + "learning_rate": 2.6584598043756273e-06, + "loss": 0.0024, + "step": 49836 + }, + { + "epoch": 15.39, + "learning_rate": 2.6581202417985764e-06, + "loss": 0.0021, + "step": 49837 + }, + { + "epoch": 15.39, + "learning_rate": 2.657780697584902e-06, + "loss": 0.0026, + "step": 49838 + }, + { + "epoch": 15.39, + "learning_rate": 2.657441171735461e-06, + "loss": 0.0026, + "step": 49839 + }, + { + "epoch": 15.39, + "learning_rate": 2.6571016642510996e-06, + "loss": 0.0028, + "step": 49840 + }, + { + "epoch": 15.39, + "learning_rate": 2.656762175132662e-06, + "loss": 0.0039, + "step": 49841 + }, + { + "epoch": 15.39, + "learning_rate": 2.656422704381002e-06, + "loss": 0.002, + "step": 49842 + }, + { + "epoch": 15.39, + "learning_rate": 2.6560832519969703e-06, + "loss": 0.0032, + "step": 49843 + }, + { + "epoch": 15.39, + "learning_rate": 2.6557438179814154e-06, + "loss": 0.0021, + "step": 49844 + }, + { + "epoch": 15.39, + "learning_rate": 2.655404402335181e-06, + "loss": 0.0027, + "step": 49845 + }, + { + "epoch": 15.39, + "learning_rate": 2.655065005059122e-06, + "loss": 0.0037, + "step": 49846 + }, + { + "epoch": 15.39, + "learning_rate": 2.654725626154083e-06, + "loss": 0.0019, + "step": 49847 + }, + { + "epoch": 15.39, + "learning_rate": 2.6543862656209154e-06, + "loss": 0.0025, + "step": 49848 + }, + { + "epoch": 15.39, + "learning_rate": 2.6540469234604695e-06, + "loss": 0.0036, + "step": 49849 + }, + { + "epoch": 15.39, + "learning_rate": 2.6537075996735918e-06, + "loss": 0.0027, + "step": 49850 + }, + { + "epoch": 15.39, + "learning_rate": 2.6533682942611295e-06, + "loss": 0.003, + "step": 49851 + }, + { + "epoch": 15.4, + "learning_rate": 2.653029007223935e-06, + "loss": 0.0031, + "step": 49852 + }, + { + "epoch": 15.4, + "learning_rate": 2.6526897385628524e-06, + "loss": 0.0024, + "step": 49853 + }, + { + "epoch": 15.4, + "learning_rate": 2.6523504882787354e-06, + "loss": 0.0028, + "step": 49854 + }, + { + "epoch": 15.4, + "learning_rate": 2.652011256372431e-06, + "loss": 0.0021, + "step": 49855 + }, + { + "epoch": 15.4, + "learning_rate": 2.6516720428447828e-06, + "loss": 0.0022, + "step": 49856 + }, + { + "epoch": 15.4, + "learning_rate": 2.651332847696643e-06, + "loss": 0.0029, + "step": 49857 + }, + { + "epoch": 15.4, + "learning_rate": 2.6509936709288595e-06, + "loss": 0.0028, + "step": 49858 + }, + { + "epoch": 15.4, + "learning_rate": 2.6506545125422854e-06, + "loss": 0.0023, + "step": 49859 + }, + { + "epoch": 15.4, + "learning_rate": 2.650315372537764e-06, + "loss": 0.0031, + "step": 49860 + }, + { + "epoch": 15.4, + "learning_rate": 2.649976250916142e-06, + "loss": 0.0034, + "step": 49861 + }, + { + "epoch": 15.4, + "learning_rate": 2.6496371476782733e-06, + "loss": 0.0025, + "step": 49862 + }, + { + "epoch": 15.4, + "learning_rate": 2.649298062824999e-06, + "loss": 0.003, + "step": 49863 + }, + { + "epoch": 15.4, + "learning_rate": 2.6489589963571738e-06, + "loss": 0.0025, + "step": 49864 + }, + { + "epoch": 15.4, + "learning_rate": 2.6486199482756426e-06, + "loss": 0.0028, + "step": 49865 + }, + { + "epoch": 15.4, + "learning_rate": 2.648280918581252e-06, + "loss": 0.0028, + "step": 49866 + }, + { + "epoch": 15.4, + "learning_rate": 2.64794190727485e-06, + "loss": 0.0025, + "step": 49867 + }, + { + "epoch": 15.4, + "learning_rate": 2.6476029143572913e-06, + "loss": 0.0022, + "step": 49868 + }, + { + "epoch": 15.4, + "learning_rate": 2.647263939829414e-06, + "loss": 0.0025, + "step": 49869 + }, + { + "epoch": 15.4, + "learning_rate": 2.646924983692074e-06, + "loss": 0.0022, + "step": 49870 + }, + { + "epoch": 15.4, + "learning_rate": 2.6465860459461158e-06, + "loss": 0.0032, + "step": 49871 + }, + { + "epoch": 15.4, + "learning_rate": 2.646247126592385e-06, + "loss": 0.0021, + "step": 49872 + }, + { + "epoch": 15.4, + "learning_rate": 2.6459082256317303e-06, + "loss": 0.0026, + "step": 49873 + }, + { + "epoch": 15.4, + "learning_rate": 2.645569343065003e-06, + "loss": 0.0034, + "step": 49874 + }, + { + "epoch": 15.4, + "learning_rate": 2.645230478893049e-06, + "loss": 0.0024, + "step": 49875 + }, + { + "epoch": 15.4, + "learning_rate": 2.6448916331167117e-06, + "loss": 0.0026, + "step": 49876 + }, + { + "epoch": 15.4, + "learning_rate": 2.6445528057368452e-06, + "loss": 0.0017, + "step": 49877 + }, + { + "epoch": 15.4, + "learning_rate": 2.6442139967542913e-06, + "loss": 0.0023, + "step": 49878 + }, + { + "epoch": 15.4, + "learning_rate": 2.643875206169899e-06, + "loss": 0.0021, + "step": 49879 + }, + { + "epoch": 15.4, + "learning_rate": 2.643536433984519e-06, + "loss": 0.0022, + "step": 49880 + }, + { + "epoch": 15.4, + "learning_rate": 2.643197680198997e-06, + "loss": 0.0033, + "step": 49881 + }, + { + "epoch": 15.4, + "learning_rate": 2.642858944814176e-06, + "loss": 0.0036, + "step": 49882 + }, + { + "epoch": 15.4, + "learning_rate": 2.642520227830909e-06, + "loss": 0.0025, + "step": 49883 + }, + { + "epoch": 15.41, + "learning_rate": 2.6421815292500396e-06, + "loss": 0.0023, + "step": 49884 + }, + { + "epoch": 15.41, + "learning_rate": 2.641842849072418e-06, + "loss": 0.0024, + "step": 49885 + }, + { + "epoch": 15.41, + "learning_rate": 2.6415041872988888e-06, + "loss": 0.0027, + "step": 49886 + }, + { + "epoch": 15.41, + "learning_rate": 2.6411655439302974e-06, + "loss": 0.0028, + "step": 49887 + }, + { + "epoch": 15.41, + "learning_rate": 2.640826918967494e-06, + "loss": 0.0028, + "step": 49888 + }, + { + "epoch": 15.41, + "learning_rate": 2.6404883124113267e-06, + "loss": 0.003, + "step": 49889 + }, + { + "epoch": 15.41, + "learning_rate": 2.6401497242626373e-06, + "loss": 0.002, + "step": 49890 + }, + { + "epoch": 15.41, + "learning_rate": 2.6398111545222794e-06, + "loss": 0.0023, + "step": 49891 + }, + { + "epoch": 15.41, + "learning_rate": 2.6394726031910933e-06, + "loss": 0.0023, + "step": 49892 + }, + { + "epoch": 15.41, + "learning_rate": 2.6391340702699308e-06, + "loss": 0.0028, + "step": 49893 + }, + { + "epoch": 15.41, + "learning_rate": 2.6387955557596345e-06, + "loss": 0.0022, + "step": 49894 + }, + { + "epoch": 15.41, + "learning_rate": 2.638457059661056e-06, + "loss": 0.0021, + "step": 49895 + }, + { + "epoch": 15.41, + "learning_rate": 2.638118581975039e-06, + "loss": 0.0025, + "step": 49896 + }, + { + "epoch": 15.41, + "learning_rate": 2.6377801227024267e-06, + "loss": 0.0024, + "step": 49897 + }, + { + "epoch": 15.41, + "learning_rate": 2.6374416818440694e-06, + "loss": 0.0024, + "step": 49898 + }, + { + "epoch": 15.41, + "learning_rate": 2.637103259400816e-06, + "loss": 0.0023, + "step": 49899 + }, + { + "epoch": 15.41, + "learning_rate": 2.6367648553735072e-06, + "loss": 0.0032, + "step": 49900 + }, + { + "epoch": 15.41, + "learning_rate": 2.636426469762996e-06, + "loss": 0.003, + "step": 49901 + }, + { + "epoch": 15.41, + "learning_rate": 2.6360881025701246e-06, + "loss": 0.0025, + "step": 49902 + }, + { + "epoch": 15.41, + "learning_rate": 2.635749753795738e-06, + "loss": 0.0024, + "step": 49903 + }, + { + "epoch": 15.41, + "learning_rate": 2.6354114234406835e-06, + "loss": 0.0021, + "step": 49904 + }, + { + "epoch": 15.41, + "learning_rate": 2.6350731115058116e-06, + "loss": 0.0032, + "step": 49905 + }, + { + "epoch": 15.41, + "learning_rate": 2.6347348179919653e-06, + "loss": 0.0028, + "step": 49906 + }, + { + "epoch": 15.41, + "learning_rate": 2.6343965428999874e-06, + "loss": 0.0028, + "step": 49907 + }, + { + "epoch": 15.41, + "learning_rate": 2.6340582862307297e-06, + "loss": 0.0028, + "step": 49908 + }, + { + "epoch": 15.41, + "learning_rate": 2.6337200479850335e-06, + "loss": 0.0024, + "step": 49909 + }, + { + "epoch": 15.41, + "learning_rate": 2.6333818281637457e-06, + "loss": 0.0022, + "step": 49910 + }, + { + "epoch": 15.41, + "learning_rate": 2.6330436267677207e-06, + "loss": 0.002, + "step": 49911 + }, + { + "epoch": 15.41, + "learning_rate": 2.6327054437977904e-06, + "loss": 0.0034, + "step": 49912 + }, + { + "epoch": 15.41, + "learning_rate": 2.6323672792548082e-06, + "loss": 0.0025, + "step": 49913 + }, + { + "epoch": 15.41, + "learning_rate": 2.632029133139622e-06, + "loss": 0.0028, + "step": 49914 + }, + { + "epoch": 15.41, + "learning_rate": 2.631691005453072e-06, + "loss": 0.0036, + "step": 49915 + }, + { + "epoch": 15.41, + "learning_rate": 2.631352896196009e-06, + "loss": 0.0025, + "step": 49916 + }, + { + "epoch": 15.42, + "learning_rate": 2.6310148053692773e-06, + "loss": 0.0027, + "step": 49917 + }, + { + "epoch": 15.42, + "learning_rate": 2.630676732973718e-06, + "loss": 0.0021, + "step": 49918 + }, + { + "epoch": 15.42, + "learning_rate": 2.6303386790101803e-06, + "loss": 0.0025, + "step": 49919 + }, + { + "epoch": 15.42, + "learning_rate": 2.6300006434795135e-06, + "loss": 0.0022, + "step": 49920 + }, + { + "epoch": 15.42, + "learning_rate": 2.6296626263825575e-06, + "loss": 0.0028, + "step": 49921 + }, + { + "epoch": 15.42, + "learning_rate": 2.629324627720158e-06, + "loss": 0.0026, + "step": 49922 + }, + { + "epoch": 15.42, + "learning_rate": 2.6289866474931613e-06, + "loss": 0.0024, + "step": 49923 + }, + { + "epoch": 15.42, + "learning_rate": 2.6286486857024173e-06, + "loss": 0.0021, + "step": 49924 + }, + { + "epoch": 15.42, + "learning_rate": 2.628310742348763e-06, + "loss": 0.003, + "step": 49925 + }, + { + "epoch": 15.42, + "learning_rate": 2.627972817433052e-06, + "loss": 0.0028, + "step": 49926 + }, + { + "epoch": 15.42, + "learning_rate": 2.627634910956125e-06, + "loss": 0.0028, + "step": 49927 + }, + { + "epoch": 15.42, + "learning_rate": 2.6272970229188256e-06, + "loss": 0.0022, + "step": 49928 + }, + { + "epoch": 15.42, + "learning_rate": 2.626959153322001e-06, + "loss": 0.0022, + "step": 49929 + }, + { + "epoch": 15.42, + "learning_rate": 2.626621302166498e-06, + "loss": 0.0023, + "step": 49930 + }, + { + "epoch": 15.42, + "learning_rate": 2.626283469453161e-06, + "loss": 0.0028, + "step": 49931 + }, + { + "epoch": 15.42, + "learning_rate": 2.625945655182831e-06, + "loss": 0.0024, + "step": 49932 + }, + { + "epoch": 15.42, + "learning_rate": 2.6256078593563583e-06, + "loss": 0.0021, + "step": 49933 + }, + { + "epoch": 15.42, + "learning_rate": 2.6252700819745824e-06, + "loss": 0.0024, + "step": 49934 + }, + { + "epoch": 15.42, + "learning_rate": 2.6249323230383516e-06, + "loss": 0.0032, + "step": 49935 + }, + { + "epoch": 15.42, + "learning_rate": 2.624594582548513e-06, + "loss": 0.0033, + "step": 49936 + }, + { + "epoch": 15.42, + "learning_rate": 2.624256860505908e-06, + "loss": 0.0025, + "step": 49937 + }, + { + "epoch": 15.42, + "learning_rate": 2.62391915691138e-06, + "loss": 0.0018, + "step": 49938 + }, + { + "epoch": 15.42, + "learning_rate": 2.623581471765777e-06, + "loss": 0.0028, + "step": 49939 + }, + { + "epoch": 15.42, + "learning_rate": 2.6232438050699405e-06, + "loss": 0.0023, + "step": 49940 + }, + { + "epoch": 15.42, + "learning_rate": 2.622906156824718e-06, + "loss": 0.0032, + "step": 49941 + }, + { + "epoch": 15.42, + "learning_rate": 2.6225685270309544e-06, + "loss": 0.0018, + "step": 49942 + }, + { + "epoch": 15.42, + "learning_rate": 2.6222309156894887e-06, + "loss": 0.0029, + "step": 49943 + }, + { + "epoch": 15.42, + "learning_rate": 2.621893322801169e-06, + "loss": 0.0017, + "step": 49944 + }, + { + "epoch": 15.42, + "learning_rate": 2.621555748366843e-06, + "loss": 0.0024, + "step": 49945 + }, + { + "epoch": 15.42, + "learning_rate": 2.6212181923873494e-06, + "loss": 0.0024, + "step": 49946 + }, + { + "epoch": 15.42, + "learning_rate": 2.6208806548635366e-06, + "loss": 0.0022, + "step": 49947 + }, + { + "epoch": 15.42, + "learning_rate": 2.6205431357962487e-06, + "loss": 0.0026, + "step": 49948 + }, + { + "epoch": 15.43, + "learning_rate": 2.6202056351863237e-06, + "loss": 0.0026, + "step": 49949 + }, + { + "epoch": 15.43, + "learning_rate": 2.6198681530346116e-06, + "loss": 0.0026, + "step": 49950 + }, + { + "epoch": 15.43, + "learning_rate": 2.619530689341958e-06, + "loss": 0.0028, + "step": 49951 + }, + { + "epoch": 15.43, + "learning_rate": 2.619193244109204e-06, + "loss": 0.0024, + "step": 49952 + }, + { + "epoch": 15.43, + "learning_rate": 2.6188558173371913e-06, + "loss": 0.0026, + "step": 49953 + }, + { + "epoch": 15.43, + "learning_rate": 2.618518409026769e-06, + "loss": 0.0024, + "step": 49954 + }, + { + "epoch": 15.43, + "learning_rate": 2.618181019178776e-06, + "loss": 0.0023, + "step": 49955 + }, + { + "epoch": 15.43, + "learning_rate": 2.6178436477940584e-06, + "loss": 0.0029, + "step": 49956 + }, + { + "epoch": 15.43, + "learning_rate": 2.617506294873463e-06, + "loss": 0.0024, + "step": 49957 + }, + { + "epoch": 15.43, + "learning_rate": 2.617168960417831e-06, + "loss": 0.0025, + "step": 49958 + }, + { + "epoch": 15.43, + "learning_rate": 2.616831644428003e-06, + "loss": 0.0024, + "step": 49959 + }, + { + "epoch": 15.43, + "learning_rate": 2.6164943469048255e-06, + "loss": 0.0018, + "step": 49960 + }, + { + "epoch": 15.43, + "learning_rate": 2.6161570678491453e-06, + "loss": 0.0023, + "step": 49961 + }, + { + "epoch": 15.43, + "learning_rate": 2.6158198072618026e-06, + "loss": 0.0033, + "step": 49962 + }, + { + "epoch": 15.43, + "learning_rate": 2.615482565143639e-06, + "loss": 0.0025, + "step": 49963 + }, + { + "epoch": 15.43, + "learning_rate": 2.615145341495503e-06, + "loss": 0.0028, + "step": 49964 + }, + { + "epoch": 15.43, + "learning_rate": 2.614808136318233e-06, + "loss": 0.0025, + "step": 49965 + }, + { + "epoch": 15.43, + "learning_rate": 2.6144709496126743e-06, + "loss": 0.002, + "step": 49966 + }, + { + "epoch": 15.43, + "learning_rate": 2.614133781379674e-06, + "loss": 0.0025, + "step": 49967 + }, + { + "epoch": 15.43, + "learning_rate": 2.6137966316200726e-06, + "loss": 0.0029, + "step": 49968 + }, + { + "epoch": 15.43, + "learning_rate": 2.61345950033471e-06, + "loss": 0.0023, + "step": 49969 + }, + { + "epoch": 15.43, + "learning_rate": 2.6131223875244337e-06, + "loss": 0.0024, + "step": 49970 + }, + { + "epoch": 15.43, + "learning_rate": 2.6127852931900845e-06, + "loss": 0.0045, + "step": 49971 + }, + { + "epoch": 15.43, + "learning_rate": 2.6124482173325096e-06, + "loss": 0.0023, + "step": 49972 + }, + { + "epoch": 15.43, + "learning_rate": 2.6121111599525486e-06, + "loss": 0.0025, + "step": 49973 + }, + { + "epoch": 15.43, + "learning_rate": 2.6117741210510415e-06, + "loss": 0.0038, + "step": 49974 + }, + { + "epoch": 15.43, + "learning_rate": 2.611437100628835e-06, + "loss": 0.0031, + "step": 49975 + }, + { + "epoch": 15.43, + "learning_rate": 2.611100098686775e-06, + "loss": 0.0026, + "step": 49976 + }, + { + "epoch": 15.43, + "learning_rate": 2.6107631152256985e-06, + "loss": 0.0026, + "step": 49977 + }, + { + "epoch": 15.43, + "learning_rate": 2.6104261502464546e-06, + "loss": 0.0016, + "step": 49978 + }, + { + "epoch": 15.43, + "learning_rate": 2.6100892037498826e-06, + "loss": 0.003, + "step": 49979 + }, + { + "epoch": 15.43, + "learning_rate": 2.609752275736821e-06, + "loss": 0.0023, + "step": 49980 + }, + { + "epoch": 15.44, + "learning_rate": 2.6094153662081177e-06, + "loss": 0.0024, + "step": 49981 + }, + { + "epoch": 15.44, + "learning_rate": 2.609078475164618e-06, + "loss": 0.0026, + "step": 49982 + }, + { + "epoch": 15.44, + "learning_rate": 2.608741602607161e-06, + "loss": 0.0025, + "step": 49983 + }, + { + "epoch": 15.44, + "learning_rate": 2.608404748536586e-06, + "loss": 0.0022, + "step": 49984 + }, + { + "epoch": 15.44, + "learning_rate": 2.6080679129537423e-06, + "loss": 0.0032, + "step": 49985 + }, + { + "epoch": 15.44, + "learning_rate": 2.6077310958594647e-06, + "loss": 0.0025, + "step": 49986 + }, + { + "epoch": 15.44, + "learning_rate": 2.6073942972546018e-06, + "loss": 0.0023, + "step": 49987 + }, + { + "epoch": 15.44, + "learning_rate": 2.607057517139996e-06, + "loss": 0.0022, + "step": 49988 + }, + { + "epoch": 15.44, + "learning_rate": 2.6067207555164876e-06, + "loss": 0.0023, + "step": 49989 + }, + { + "epoch": 15.44, + "learning_rate": 2.606384012384916e-06, + "loss": 0.0037, + "step": 49990 + }, + { + "epoch": 15.44, + "learning_rate": 2.606047287746126e-06, + "loss": 0.0019, + "step": 49991 + }, + { + "epoch": 15.44, + "learning_rate": 2.6057105816009653e-06, + "loss": 0.0023, + "step": 49992 + }, + { + "epoch": 15.44, + "learning_rate": 2.6053738939502695e-06, + "loss": 0.0037, + "step": 49993 + }, + { + "epoch": 15.44, + "learning_rate": 2.60503722479488e-06, + "loss": 0.0031, + "step": 49994 + }, + { + "epoch": 15.44, + "learning_rate": 2.6047005741356434e-06, + "loss": 0.0028, + "step": 49995 + }, + { + "epoch": 15.44, + "learning_rate": 2.6043639419733967e-06, + "loss": 0.0028, + "step": 49996 + }, + { + "epoch": 15.44, + "learning_rate": 2.6040273283089845e-06, + "loss": 0.0022, + "step": 49997 + }, + { + "epoch": 15.44, + "learning_rate": 2.6036907331432526e-06, + "loss": 0.0024, + "step": 49998 + }, + { + "epoch": 15.44, + "learning_rate": 2.603354156477038e-06, + "loss": 0.0022, + "step": 49999 + }, + { + "epoch": 15.44, + "learning_rate": 2.6030175983111817e-06, + "loss": 0.0035, + "step": 50000 + }, + { + "epoch": 15.44, + "learning_rate": 2.602681058646531e-06, + "loss": 0.0018, + "step": 50001 + }, + { + "epoch": 15.44, + "learning_rate": 2.6023445374839194e-06, + "loss": 0.0025, + "step": 50002 + }, + { + "epoch": 15.44, + "learning_rate": 2.602008034824198e-06, + "loss": 0.0028, + "step": 50003 + }, + { + "epoch": 15.44, + "learning_rate": 2.6016715506682035e-06, + "loss": 0.0029, + "step": 50004 + }, + { + "epoch": 15.44, + "learning_rate": 2.601335085016774e-06, + "loss": 0.0022, + "step": 50005 + }, + { + "epoch": 15.44, + "learning_rate": 2.6009986378707564e-06, + "loss": 0.002, + "step": 50006 + }, + { + "epoch": 15.44, + "learning_rate": 2.6006622092309918e-06, + "loss": 0.0025, + "step": 50007 + }, + { + "epoch": 15.44, + "learning_rate": 2.600325799098319e-06, + "loss": 0.0033, + "step": 50008 + }, + { + "epoch": 15.44, + "learning_rate": 2.599989407473583e-06, + "loss": 0.0022, + "step": 50009 + }, + { + "epoch": 15.44, + "learning_rate": 2.5996530343576245e-06, + "loss": 0.0026, + "step": 50010 + }, + { + "epoch": 15.44, + "learning_rate": 2.599316679751279e-06, + "loss": 0.0031, + "step": 50011 + }, + { + "epoch": 15.44, + "learning_rate": 2.598980343655393e-06, + "loss": 0.0023, + "step": 50012 + }, + { + "epoch": 15.44, + "learning_rate": 2.59864402607081e-06, + "loss": 0.003, + "step": 50013 + }, + { + "epoch": 15.45, + "learning_rate": 2.598307726998368e-06, + "loss": 0.0033, + "step": 50014 + }, + { + "epoch": 15.45, + "learning_rate": 2.597971446438906e-06, + "loss": 0.002, + "step": 50015 + }, + { + "epoch": 15.45, + "learning_rate": 2.5976351843932703e-06, + "loss": 0.0017, + "step": 50016 + }, + { + "epoch": 15.45, + "learning_rate": 2.597298940862295e-06, + "loss": 0.0021, + "step": 50017 + }, + { + "epoch": 15.45, + "learning_rate": 2.596962715846827e-06, + "loss": 0.0042, + "step": 50018 + }, + { + "epoch": 15.45, + "learning_rate": 2.5966265093477106e-06, + "loss": 0.0021, + "step": 50019 + }, + { + "epoch": 15.45, + "learning_rate": 2.5962903213657755e-06, + "loss": 0.0031, + "step": 50020 + }, + { + "epoch": 15.45, + "learning_rate": 2.595954151901868e-06, + "loss": 0.0025, + "step": 50021 + }, + { + "epoch": 15.45, + "learning_rate": 2.59561800095683e-06, + "loss": 0.0022, + "step": 50022 + }, + { + "epoch": 15.45, + "learning_rate": 2.595281868531505e-06, + "loss": 0.0025, + "step": 50023 + }, + { + "epoch": 15.45, + "learning_rate": 2.5949457546267308e-06, + "loss": 0.003, + "step": 50024 + }, + { + "epoch": 15.45, + "learning_rate": 2.5946096592433455e-06, + "loss": 0.0029, + "step": 50025 + }, + { + "epoch": 15.45, + "learning_rate": 2.594273582382194e-06, + "loss": 0.0036, + "step": 50026 + }, + { + "epoch": 15.45, + "learning_rate": 2.5939375240441122e-06, + "loss": 0.0023, + "step": 50027 + }, + { + "epoch": 15.45, + "learning_rate": 2.593601484229944e-06, + "loss": 0.0028, + "step": 50028 + }, + { + "epoch": 15.45, + "learning_rate": 2.5932654629405353e-06, + "loss": 0.0026, + "step": 50029 + }, + { + "epoch": 15.45, + "learning_rate": 2.5929294601767143e-06, + "loss": 0.0029, + "step": 50030 + }, + { + "epoch": 15.45, + "learning_rate": 2.5925934759393266e-06, + "loss": 0.0022, + "step": 50031 + }, + { + "epoch": 15.45, + "learning_rate": 2.592257510229218e-06, + "loss": 0.0018, + "step": 50032 + }, + { + "epoch": 15.45, + "learning_rate": 2.5919215630472205e-06, + "loss": 0.0019, + "step": 50033 + }, + { + "epoch": 15.45, + "learning_rate": 2.5915856343941825e-06, + "loss": 0.0023, + "step": 50034 + }, + { + "epoch": 15.45, + "learning_rate": 2.591249724270939e-06, + "loss": 0.0029, + "step": 50035 + }, + { + "epoch": 15.45, + "learning_rate": 2.590913832678329e-06, + "loss": 0.0026, + "step": 50036 + }, + { + "epoch": 15.45, + "learning_rate": 2.5905779596171944e-06, + "loss": 0.0021, + "step": 50037 + }, + { + "epoch": 15.45, + "learning_rate": 2.5902421050883785e-06, + "loss": 0.0024, + "step": 50038 + }, + { + "epoch": 15.45, + "learning_rate": 2.589906269092719e-06, + "loss": 0.0024, + "step": 50039 + }, + { + "epoch": 15.45, + "learning_rate": 2.589570451631053e-06, + "loss": 0.0033, + "step": 50040 + }, + { + "epoch": 15.45, + "learning_rate": 2.5892346527042245e-06, + "loss": 0.0022, + "step": 50041 + }, + { + "epoch": 15.45, + "learning_rate": 2.5888988723130693e-06, + "loss": 0.0021, + "step": 50042 + }, + { + "epoch": 15.45, + "learning_rate": 2.5885631104584298e-06, + "loss": 0.0021, + "step": 50043 + }, + { + "epoch": 15.45, + "learning_rate": 2.5882273671411495e-06, + "loss": 0.0016, + "step": 50044 + }, + { + "epoch": 15.45, + "learning_rate": 2.5878916423620636e-06, + "loss": 0.0032, + "step": 50045 + }, + { + "epoch": 15.46, + "learning_rate": 2.5875559361220094e-06, + "loss": 0.0025, + "step": 50046 + }, + { + "epoch": 15.46, + "learning_rate": 2.5872202484218336e-06, + "loss": 0.003, + "step": 50047 + }, + { + "epoch": 15.46, + "learning_rate": 2.5868845792623674e-06, + "loss": 0.0031, + "step": 50048 + }, + { + "epoch": 15.46, + "learning_rate": 2.586548928644459e-06, + "loss": 0.0034, + "step": 50049 + }, + { + "epoch": 15.46, + "learning_rate": 2.5862132965689434e-06, + "loss": 0.0019, + "step": 50050 + }, + { + "epoch": 15.46, + "learning_rate": 2.5858776830366585e-06, + "loss": 0.0023, + "step": 50051 + }, + { + "epoch": 15.46, + "learning_rate": 2.585542088048445e-06, + "loss": 0.0038, + "step": 50052 + }, + { + "epoch": 15.46, + "learning_rate": 2.585206511605146e-06, + "loss": 0.0022, + "step": 50053 + }, + { + "epoch": 15.46, + "learning_rate": 2.5848709537075957e-06, + "loss": 0.0024, + "step": 50054 + }, + { + "epoch": 15.46, + "learning_rate": 2.584535414356638e-06, + "loss": 0.0032, + "step": 50055 + }, + { + "epoch": 15.46, + "learning_rate": 2.5841998935531067e-06, + "loss": 0.0023, + "step": 50056 + }, + { + "epoch": 15.46, + "learning_rate": 2.583864391297847e-06, + "loss": 0.0021, + "step": 50057 + }, + { + "epoch": 15.46, + "learning_rate": 2.5835289075916913e-06, + "loss": 0.0022, + "step": 50058 + }, + { + "epoch": 15.46, + "learning_rate": 2.5831934424354844e-06, + "loss": 0.0031, + "step": 50059 + }, + { + "epoch": 15.46, + "learning_rate": 2.5828579958300682e-06, + "loss": 0.0029, + "step": 50060 + }, + { + "epoch": 15.46, + "learning_rate": 2.582522567776271e-06, + "loss": 0.0021, + "step": 50061 + }, + { + "epoch": 15.46, + "learning_rate": 2.582187158274937e-06, + "loss": 0.0034, + "step": 50062 + }, + { + "epoch": 15.46, + "learning_rate": 2.5818517673269092e-06, + "loss": 0.0024, + "step": 50063 + }, + { + "epoch": 15.46, + "learning_rate": 2.5815163949330213e-06, + "loss": 0.003, + "step": 50064 + }, + { + "epoch": 15.46, + "learning_rate": 2.5811810410941165e-06, + "loss": 0.003, + "step": 50065 + }, + { + "epoch": 15.46, + "learning_rate": 2.5808457058110303e-06, + "loss": 0.0041, + "step": 50066 + }, + { + "epoch": 15.46, + "learning_rate": 2.5805103890845995e-06, + "loss": 0.0024, + "step": 50067 + }, + { + "epoch": 15.46, + "learning_rate": 2.5801750909156654e-06, + "loss": 0.0032, + "step": 50068 + }, + { + "epoch": 15.46, + "learning_rate": 2.5798398113050703e-06, + "loss": 0.0025, + "step": 50069 + }, + { + "epoch": 15.46, + "learning_rate": 2.5795045502536485e-06, + "loss": 0.0026, + "step": 50070 + }, + { + "epoch": 15.46, + "learning_rate": 2.579169307762237e-06, + "loss": 0.0021, + "step": 50071 + }, + { + "epoch": 15.46, + "learning_rate": 2.578834083831678e-06, + "loss": 0.003, + "step": 50072 + }, + { + "epoch": 15.46, + "learning_rate": 2.5784988784628073e-06, + "loss": 0.0022, + "step": 50073 + }, + { + "epoch": 15.46, + "learning_rate": 2.5781636916564635e-06, + "loss": 0.0028, + "step": 50074 + }, + { + "epoch": 15.46, + "learning_rate": 2.5778285234134892e-06, + "loss": 0.0034, + "step": 50075 + }, + { + "epoch": 15.46, + "learning_rate": 2.5774933737347196e-06, + "loss": 0.0023, + "step": 50076 + }, + { + "epoch": 15.46, + "learning_rate": 2.5771582426209895e-06, + "loss": 0.0022, + "step": 50077 + }, + { + "epoch": 15.46, + "learning_rate": 2.5768231300731437e-06, + "loss": 0.0026, + "step": 50078 + }, + { + "epoch": 15.47, + "learning_rate": 2.576488036092014e-06, + "loss": 0.0026, + "step": 50079 + }, + { + "epoch": 15.47, + "learning_rate": 2.576152960678445e-06, + "loss": 0.0031, + "step": 50080 + }, + { + "epoch": 15.47, + "learning_rate": 2.575817903833271e-06, + "loss": 0.0021, + "step": 50081 + }, + { + "epoch": 15.47, + "learning_rate": 2.575482865557327e-06, + "loss": 0.0025, + "step": 50082 + }, + { + "epoch": 15.47, + "learning_rate": 2.5751478458514557e-06, + "loss": 0.0026, + "step": 50083 + }, + { + "epoch": 15.47, + "learning_rate": 2.5748128447164966e-06, + "loss": 0.0023, + "step": 50084 + }, + { + "epoch": 15.47, + "learning_rate": 2.5744778621532817e-06, + "loss": 0.0023, + "step": 50085 + }, + { + "epoch": 15.47, + "learning_rate": 2.574142898162655e-06, + "loss": 0.0032, + "step": 50086 + }, + { + "epoch": 15.47, + "learning_rate": 2.5738079527454486e-06, + "loss": 0.003, + "step": 50087 + }, + { + "epoch": 15.47, + "learning_rate": 2.5734730259025054e-06, + "loss": 0.0035, + "step": 50088 + }, + { + "epoch": 15.47, + "learning_rate": 2.573138117634658e-06, + "loss": 0.0025, + "step": 50089 + }, + { + "epoch": 15.47, + "learning_rate": 2.5728032279427495e-06, + "loss": 0.0024, + "step": 50090 + }, + { + "epoch": 15.47, + "learning_rate": 2.5724683568276155e-06, + "loss": 0.0021, + "step": 50091 + }, + { + "epoch": 15.47, + "learning_rate": 2.5721335042900888e-06, + "loss": 0.0025, + "step": 50092 + }, + { + "epoch": 15.47, + "learning_rate": 2.5717986703310117e-06, + "loss": 0.0032, + "step": 50093 + }, + { + "epoch": 15.47, + "learning_rate": 2.571463854951223e-06, + "loss": 0.0028, + "step": 50094 + }, + { + "epoch": 15.47, + "learning_rate": 2.5711290581515558e-06, + "loss": 0.0025, + "step": 50095 + }, + { + "epoch": 15.47, + "learning_rate": 2.570794279932853e-06, + "loss": 0.0027, + "step": 50096 + }, + { + "epoch": 15.47, + "learning_rate": 2.570459520295948e-06, + "loss": 0.003, + "step": 50097 + }, + { + "epoch": 15.47, + "learning_rate": 2.5701247792416762e-06, + "loss": 0.0024, + "step": 50098 + }, + { + "epoch": 15.47, + "learning_rate": 2.5697900567708778e-06, + "loss": 0.0031, + "step": 50099 + }, + { + "epoch": 15.47, + "learning_rate": 2.5694553528843926e-06, + "loss": 0.002, + "step": 50100 + }, + { + "epoch": 15.47, + "learning_rate": 2.5691206675830537e-06, + "loss": 0.0034, + "step": 50101 + }, + { + "epoch": 15.47, + "learning_rate": 2.568786000867698e-06, + "loss": 0.0029, + "step": 50102 + }, + { + "epoch": 15.47, + "learning_rate": 2.568451352739165e-06, + "loss": 0.0031, + "step": 50103 + }, + { + "epoch": 15.47, + "learning_rate": 2.5681167231982894e-06, + "loss": 0.0018, + "step": 50104 + }, + { + "epoch": 15.47, + "learning_rate": 2.567782112245909e-06, + "loss": 0.002, + "step": 50105 + }, + { + "epoch": 15.47, + "learning_rate": 2.567447519882863e-06, + "loss": 0.0041, + "step": 50106 + }, + { + "epoch": 15.47, + "learning_rate": 2.5671129461099873e-06, + "loss": 0.0031, + "step": 50107 + }, + { + "epoch": 15.47, + "learning_rate": 2.5667783909281142e-06, + "loss": 0.0024, + "step": 50108 + }, + { + "epoch": 15.47, + "learning_rate": 2.5664438543380874e-06, + "loss": 0.0024, + "step": 50109 + }, + { + "epoch": 15.47, + "learning_rate": 2.5661093363407375e-06, + "loss": 0.002, + "step": 50110 + }, + { + "epoch": 15.48, + "learning_rate": 2.5657748369369072e-06, + "loss": 0.002, + "step": 50111 + }, + { + "epoch": 15.48, + "learning_rate": 2.565440356127429e-06, + "loss": 0.0035, + "step": 50112 + }, + { + "epoch": 15.48, + "learning_rate": 2.565105893913138e-06, + "loss": 0.0034, + "step": 50113 + }, + { + "epoch": 15.48, + "learning_rate": 2.5647714502948737e-06, + "loss": 0.0031, + "step": 50114 + }, + { + "epoch": 15.48, + "learning_rate": 2.5644370252734742e-06, + "loss": 0.0024, + "step": 50115 + }, + { + "epoch": 15.48, + "learning_rate": 2.564102618849772e-06, + "loss": 0.0022, + "step": 50116 + }, + { + "epoch": 15.48, + "learning_rate": 2.563768231024607e-06, + "loss": 0.002, + "step": 50117 + }, + { + "epoch": 15.48, + "learning_rate": 2.5634338617988154e-06, + "loss": 0.0026, + "step": 50118 + }, + { + "epoch": 15.48, + "learning_rate": 2.563099511173228e-06, + "loss": 0.0037, + "step": 50119 + }, + { + "epoch": 15.48, + "learning_rate": 2.562765179148685e-06, + "loss": 0.0021, + "step": 50120 + }, + { + "epoch": 15.48, + "learning_rate": 2.5624308657260265e-06, + "loss": 0.0024, + "step": 50121 + }, + { + "epoch": 15.48, + "learning_rate": 2.562096570906084e-06, + "loss": 0.0028, + "step": 50122 + }, + { + "epoch": 15.48, + "learning_rate": 2.5617622946896923e-06, + "loss": 0.004, + "step": 50123 + }, + { + "epoch": 15.48, + "learning_rate": 2.56142803707769e-06, + "loss": 0.0028, + "step": 50124 + }, + { + "epoch": 15.48, + "learning_rate": 2.561093798070915e-06, + "loss": 0.0026, + "step": 50125 + }, + { + "epoch": 15.48, + "learning_rate": 2.5607595776701986e-06, + "loss": 0.0025, + "step": 50126 + }, + { + "epoch": 15.48, + "learning_rate": 2.560425375876383e-06, + "loss": 0.0022, + "step": 50127 + }, + { + "epoch": 15.48, + "learning_rate": 2.5600911926902993e-06, + "loss": 0.0024, + "step": 50128 + }, + { + "epoch": 15.48, + "learning_rate": 2.5597570281127824e-06, + "loss": 0.0025, + "step": 50129 + }, + { + "epoch": 15.48, + "learning_rate": 2.5594228821446696e-06, + "loss": 0.0025, + "step": 50130 + }, + { + "epoch": 15.48, + "learning_rate": 2.5590887547868003e-06, + "loss": 0.003, + "step": 50131 + }, + { + "epoch": 15.48, + "learning_rate": 2.5587546460400083e-06, + "loss": 0.0031, + "step": 50132 + }, + { + "epoch": 15.48, + "learning_rate": 2.5584205559051234e-06, + "loss": 0.003, + "step": 50133 + }, + { + "epoch": 15.48, + "learning_rate": 2.55808648438299e-06, + "loss": 0.0033, + "step": 50134 + }, + { + "epoch": 15.48, + "learning_rate": 2.557752431474436e-06, + "loss": 0.0027, + "step": 50135 + }, + { + "epoch": 15.48, + "learning_rate": 2.557418397180301e-06, + "loss": 0.003, + "step": 50136 + }, + { + "epoch": 15.48, + "learning_rate": 2.5570843815014236e-06, + "loss": 0.0022, + "step": 50137 + }, + { + "epoch": 15.48, + "learning_rate": 2.556750384438634e-06, + "loss": 0.0026, + "step": 50138 + }, + { + "epoch": 15.48, + "learning_rate": 2.556416405992768e-06, + "loss": 0.0028, + "step": 50139 + }, + { + "epoch": 15.48, + "learning_rate": 2.5560824461646637e-06, + "loss": 0.0022, + "step": 50140 + }, + { + "epoch": 15.48, + "learning_rate": 2.5557485049551534e-06, + "loss": 0.0025, + "step": 50141 + }, + { + "epoch": 15.48, + "learning_rate": 2.5554145823650757e-06, + "loss": 0.0025, + "step": 50142 + }, + { + "epoch": 15.49, + "learning_rate": 2.555080678395264e-06, + "loss": 0.0025, + "step": 50143 + }, + { + "epoch": 15.49, + "learning_rate": 2.554746793046551e-06, + "loss": 0.0022, + "step": 50144 + }, + { + "epoch": 15.49, + "learning_rate": 2.5544129263197737e-06, + "loss": 0.0034, + "step": 50145 + }, + { + "epoch": 15.49, + "learning_rate": 2.554079078215771e-06, + "loss": 0.0031, + "step": 50146 + }, + { + "epoch": 15.49, + "learning_rate": 2.5537452487353707e-06, + "loss": 0.0023, + "step": 50147 + }, + { + "epoch": 15.49, + "learning_rate": 2.553411437879416e-06, + "loss": 0.0022, + "step": 50148 + }, + { + "epoch": 15.49, + "learning_rate": 2.5530776456487373e-06, + "loss": 0.0021, + "step": 50149 + }, + { + "epoch": 15.49, + "learning_rate": 2.5527438720441656e-06, + "loss": 0.0023, + "step": 50150 + }, + { + "epoch": 15.49, + "learning_rate": 2.5524101170665404e-06, + "loss": 0.0028, + "step": 50151 + }, + { + "epoch": 15.49, + "learning_rate": 2.5520763807166983e-06, + "loss": 0.0032, + "step": 50152 + }, + { + "epoch": 15.49, + "learning_rate": 2.551742662995472e-06, + "loss": 0.0021, + "step": 50153 + }, + { + "epoch": 15.49, + "learning_rate": 2.5514089639036934e-06, + "loss": 0.0024, + "step": 50154 + }, + { + "epoch": 15.49, + "learning_rate": 2.5510752834421993e-06, + "loss": 0.0025, + "step": 50155 + }, + { + "epoch": 15.49, + "learning_rate": 2.5507416216118264e-06, + "loss": 0.0031, + "step": 50156 + }, + { + "epoch": 15.49, + "learning_rate": 2.550407978413405e-06, + "loss": 0.0026, + "step": 50157 + }, + { + "epoch": 15.49, + "learning_rate": 2.5500743538477758e-06, + "loss": 0.0031, + "step": 50158 + }, + { + "epoch": 15.49, + "learning_rate": 2.549740747915769e-06, + "loss": 0.0029, + "step": 50159 + }, + { + "epoch": 15.49, + "learning_rate": 2.5494071606182157e-06, + "loss": 0.0029, + "step": 50160 + }, + { + "epoch": 15.49, + "learning_rate": 2.549073591955955e-06, + "loss": 0.0032, + "step": 50161 + }, + { + "epoch": 15.49, + "learning_rate": 2.5487400419298225e-06, + "loss": 0.0021, + "step": 50162 + }, + { + "epoch": 15.49, + "learning_rate": 2.54840651054065e-06, + "loss": 0.0023, + "step": 50163 + }, + { + "epoch": 15.49, + "learning_rate": 2.548072997789269e-06, + "loss": 0.0032, + "step": 50164 + }, + { + "epoch": 15.49, + "learning_rate": 2.5477395036765206e-06, + "loss": 0.0033, + "step": 50165 + }, + { + "epoch": 15.49, + "learning_rate": 2.547406028203231e-06, + "loss": 0.0024, + "step": 50166 + }, + { + "epoch": 15.49, + "learning_rate": 2.5470725713702384e-06, + "loss": 0.0028, + "step": 50167 + }, + { + "epoch": 15.49, + "learning_rate": 2.546739133178382e-06, + "loss": 0.0027, + "step": 50168 + }, + { + "epoch": 15.49, + "learning_rate": 2.5464057136284846e-06, + "loss": 0.0028, + "step": 50169 + }, + { + "epoch": 15.49, + "learning_rate": 2.546072312721387e-06, + "loss": 0.0034, + "step": 50170 + }, + { + "epoch": 15.49, + "learning_rate": 2.545738930457924e-06, + "loss": 0.0028, + "step": 50171 + }, + { + "epoch": 15.49, + "learning_rate": 2.5454055668389254e-06, + "loss": 0.0026, + "step": 50172 + }, + { + "epoch": 15.49, + "learning_rate": 2.5450722218652292e-06, + "loss": 0.0029, + "step": 50173 + }, + { + "epoch": 15.49, + "learning_rate": 2.5447388955376674e-06, + "loss": 0.0025, + "step": 50174 + }, + { + "epoch": 15.49, + "learning_rate": 2.5444055878570705e-06, + "loss": 0.0028, + "step": 50175 + }, + { + "epoch": 15.5, + "learning_rate": 2.544072298824275e-06, + "loss": 0.0025, + "step": 50176 + }, + { + "epoch": 15.5, + "learning_rate": 2.5437390284401175e-06, + "loss": 0.0029, + "step": 50177 + }, + { + "epoch": 15.5, + "learning_rate": 2.543405776705429e-06, + "loss": 0.0025, + "step": 50178 + }, + { + "epoch": 15.5, + "learning_rate": 2.543072543621039e-06, + "loss": 0.0031, + "step": 50179 + }, + { + "epoch": 15.5, + "learning_rate": 2.542739329187789e-06, + "loss": 0.0023, + "step": 50180 + }, + { + "epoch": 15.5, + "learning_rate": 2.542406133406503e-06, + "loss": 0.0028, + "step": 50181 + }, + { + "epoch": 15.5, + "learning_rate": 2.542072956278021e-06, + "loss": 0.0032, + "step": 50182 + }, + { + "epoch": 15.5, + "learning_rate": 2.5417397978031765e-06, + "loss": 0.0027, + "step": 50183 + }, + { + "epoch": 15.5, + "learning_rate": 2.5414066579828024e-06, + "loss": 0.0028, + "step": 50184 + }, + { + "epoch": 15.5, + "learning_rate": 2.5410735368177276e-06, + "loss": 0.0024, + "step": 50185 + }, + { + "epoch": 15.5, + "learning_rate": 2.540740434308787e-06, + "loss": 0.0024, + "step": 50186 + }, + { + "epoch": 15.5, + "learning_rate": 2.5404073504568193e-06, + "loss": 0.0031, + "step": 50187 + }, + { + "epoch": 15.5, + "learning_rate": 2.5400742852626525e-06, + "loss": 0.0027, + "step": 50188 + }, + { + "epoch": 15.5, + "learning_rate": 2.539741238727118e-06, + "loss": 0.0046, + "step": 50189 + }, + { + "epoch": 15.5, + "learning_rate": 2.5394082108510544e-06, + "loss": 0.0028, + "step": 50190 + }, + { + "epoch": 15.5, + "learning_rate": 2.5390752016352884e-06, + "loss": 0.0025, + "step": 50191 + }, + { + "epoch": 15.5, + "learning_rate": 2.538742211080656e-06, + "loss": 0.0036, + "step": 50192 + }, + { + "epoch": 15.5, + "learning_rate": 2.5384092391879933e-06, + "loss": 0.0029, + "step": 50193 + }, + { + "epoch": 15.5, + "learning_rate": 2.53807628595813e-06, + "loss": 0.0025, + "step": 50194 + }, + { + "epoch": 15.5, + "learning_rate": 2.537743351391896e-06, + "loss": 0.0025, + "step": 50195 + }, + { + "epoch": 15.5, + "learning_rate": 2.5374104354901296e-06, + "loss": 0.0026, + "step": 50196 + }, + { + "epoch": 15.5, + "learning_rate": 2.537077538253657e-06, + "loss": 0.0024, + "step": 50197 + }, + { + "epoch": 15.5, + "learning_rate": 2.536744659683319e-06, + "loss": 0.0026, + "step": 50198 + }, + { + "epoch": 15.5, + "learning_rate": 2.536411799779943e-06, + "loss": 0.0033, + "step": 50199 + }, + { + "epoch": 15.5, + "learning_rate": 2.53607895854436e-06, + "loss": 0.0029, + "step": 50200 + }, + { + "epoch": 15.5, + "learning_rate": 2.5357461359774048e-06, + "loss": 0.0024, + "step": 50201 + }, + { + "epoch": 15.5, + "learning_rate": 2.5354133320799133e-06, + "loss": 0.003, + "step": 50202 + }, + { + "epoch": 15.5, + "learning_rate": 2.5350805468527106e-06, + "loss": 0.002, + "step": 50203 + }, + { + "epoch": 15.5, + "learning_rate": 2.5347477802966358e-06, + "loss": 0.0027, + "step": 50204 + }, + { + "epoch": 15.5, + "learning_rate": 2.5344150324125196e-06, + "loss": 0.003, + "step": 50205 + }, + { + "epoch": 15.5, + "learning_rate": 2.5340823032011897e-06, + "loss": 0.0024, + "step": 50206 + }, + { + "epoch": 15.5, + "learning_rate": 2.5337495926634804e-06, + "loss": 0.0024, + "step": 50207 + }, + { + "epoch": 15.51, + "learning_rate": 2.5334169008002298e-06, + "loss": 0.0031, + "step": 50208 + }, + { + "epoch": 15.51, + "learning_rate": 2.5330842276122634e-06, + "loss": 0.0038, + "step": 50209 + }, + { + "epoch": 15.51, + "learning_rate": 2.5327515731004138e-06, + "loss": 0.0025, + "step": 50210 + }, + { + "epoch": 15.51, + "learning_rate": 2.5324189372655174e-06, + "loss": 0.0026, + "step": 50211 + }, + { + "epoch": 15.51, + "learning_rate": 2.5320863201084e-06, + "loss": 0.0028, + "step": 50212 + }, + { + "epoch": 15.51, + "learning_rate": 2.531753721629897e-06, + "loss": 0.0034, + "step": 50213 + }, + { + "epoch": 15.51, + "learning_rate": 2.5314211418308423e-06, + "loss": 0.0029, + "step": 50214 + }, + { + "epoch": 15.51, + "learning_rate": 2.5310885807120657e-06, + "loss": 0.0026, + "step": 50215 + }, + { + "epoch": 15.51, + "learning_rate": 2.5307560382743967e-06, + "loss": 0.003, + "step": 50216 + }, + { + "epoch": 15.51, + "learning_rate": 2.530423514518671e-06, + "loss": 0.0027, + "step": 50217 + }, + { + "epoch": 15.51, + "learning_rate": 2.5300910094457164e-06, + "loss": 0.003, + "step": 50218 + }, + { + "epoch": 15.51, + "learning_rate": 2.529758523056369e-06, + "loss": 0.0035, + "step": 50219 + }, + { + "epoch": 15.51, + "learning_rate": 2.5294260553514548e-06, + "loss": 0.0025, + "step": 50220 + }, + { + "epoch": 15.51, + "learning_rate": 2.5290936063318116e-06, + "loss": 0.003, + "step": 50221 + }, + { + "epoch": 15.51, + "learning_rate": 2.5287611759982657e-06, + "loss": 0.003, + "step": 50222 + }, + { + "epoch": 15.51, + "learning_rate": 2.5284287643516503e-06, + "loss": 0.0028, + "step": 50223 + }, + { + "epoch": 15.51, + "learning_rate": 2.528096371392801e-06, + "loss": 0.0027, + "step": 50224 + }, + { + "epoch": 15.51, + "learning_rate": 2.5277639971225444e-06, + "loss": 0.0023, + "step": 50225 + }, + { + "epoch": 15.51, + "learning_rate": 2.52743164154171e-06, + "loss": 0.0028, + "step": 50226 + }, + { + "epoch": 15.51, + "learning_rate": 2.527099304651135e-06, + "loss": 0.0029, + "step": 50227 + }, + { + "epoch": 15.51, + "learning_rate": 2.526766986451645e-06, + "loss": 0.0029, + "step": 50228 + }, + { + "epoch": 15.51, + "learning_rate": 2.526434686944077e-06, + "loss": 0.0024, + "step": 50229 + }, + { + "epoch": 15.51, + "learning_rate": 2.5261024061292584e-06, + "loss": 0.0034, + "step": 50230 + }, + { + "epoch": 15.51, + "learning_rate": 2.5257701440080186e-06, + "loss": 0.0028, + "step": 50231 + }, + { + "epoch": 15.51, + "learning_rate": 2.5254379005811902e-06, + "loss": 0.0029, + "step": 50232 + }, + { + "epoch": 15.51, + "learning_rate": 2.525105675849607e-06, + "loss": 0.003, + "step": 50233 + }, + { + "epoch": 15.51, + "learning_rate": 2.524773469814097e-06, + "loss": 0.0028, + "step": 50234 + }, + { + "epoch": 15.51, + "learning_rate": 2.5244412824754938e-06, + "loss": 0.002, + "step": 50235 + }, + { + "epoch": 15.51, + "learning_rate": 2.5241091138346265e-06, + "loss": 0.0024, + "step": 50236 + }, + { + "epoch": 15.51, + "learning_rate": 2.523776963892323e-06, + "loss": 0.0019, + "step": 50237 + }, + { + "epoch": 15.51, + "learning_rate": 2.5234448326494166e-06, + "loss": 0.0027, + "step": 50238 + }, + { + "epoch": 15.51, + "learning_rate": 2.5231127201067406e-06, + "loss": 0.0028, + "step": 50239 + }, + { + "epoch": 15.52, + "learning_rate": 2.5227806262651243e-06, + "loss": 0.002, + "step": 50240 + }, + { + "epoch": 15.52, + "learning_rate": 2.5224485511253937e-06, + "loss": 0.0023, + "step": 50241 + }, + { + "epoch": 15.52, + "learning_rate": 2.522116494688387e-06, + "loss": 0.0022, + "step": 50242 + }, + { + "epoch": 15.52, + "learning_rate": 2.5217844569549277e-06, + "loss": 0.0021, + "step": 50243 + }, + { + "epoch": 15.52, + "learning_rate": 2.5214524379258486e-06, + "loss": 0.0027, + "step": 50244 + }, + { + "epoch": 15.52, + "learning_rate": 2.521120437601985e-06, + "loss": 0.0028, + "step": 50245 + }, + { + "epoch": 15.52, + "learning_rate": 2.520788455984163e-06, + "loss": 0.0025, + "step": 50246 + }, + { + "epoch": 15.52, + "learning_rate": 2.52045649307321e-06, + "loss": 0.0031, + "step": 50247 + }, + { + "epoch": 15.52, + "learning_rate": 2.520124548869962e-06, + "loss": 0.0028, + "step": 50248 + }, + { + "epoch": 15.52, + "learning_rate": 2.5197926233752445e-06, + "loss": 0.0032, + "step": 50249 + }, + { + "epoch": 15.52, + "learning_rate": 2.5194607165898932e-06, + "loss": 0.0031, + "step": 50250 + }, + { + "epoch": 15.52, + "learning_rate": 2.519128828514731e-06, + "loss": 0.0023, + "step": 50251 + }, + { + "epoch": 15.52, + "learning_rate": 2.5187969591505957e-06, + "loss": 0.0021, + "step": 50252 + }, + { + "epoch": 15.52, + "learning_rate": 2.51846510849831e-06, + "loss": 0.0031, + "step": 50253 + }, + { + "epoch": 15.52, + "learning_rate": 2.5181332765587085e-06, + "loss": 0.003, + "step": 50254 + }, + { + "epoch": 15.52, + "learning_rate": 2.5178014633326232e-06, + "loss": 0.0023, + "step": 50255 + }, + { + "epoch": 15.52, + "learning_rate": 2.51746966882088e-06, + "loss": 0.0027, + "step": 50256 + }, + { + "epoch": 15.52, + "learning_rate": 2.5171378930243083e-06, + "loss": 0.0028, + "step": 50257 + }, + { + "epoch": 15.52, + "learning_rate": 2.516806135943742e-06, + "loss": 0.0029, + "step": 50258 + }, + { + "epoch": 15.52, + "learning_rate": 2.5164743975800055e-06, + "loss": 0.0034, + "step": 50259 + }, + { + "epoch": 15.52, + "learning_rate": 2.516142677933934e-06, + "loss": 0.0028, + "step": 50260 + }, + { + "epoch": 15.52, + "learning_rate": 2.5158109770063545e-06, + "loss": 0.0027, + "step": 50261 + }, + { + "epoch": 15.52, + "learning_rate": 2.5154792947980943e-06, + "loss": 0.0027, + "step": 50262 + }, + { + "epoch": 15.52, + "learning_rate": 2.515147631309985e-06, + "loss": 0.0024, + "step": 50263 + }, + { + "epoch": 15.52, + "learning_rate": 2.5148159865428603e-06, + "loss": 0.0031, + "step": 50264 + }, + { + "epoch": 15.52, + "learning_rate": 2.514484360497543e-06, + "loss": 0.0021, + "step": 50265 + }, + { + "epoch": 15.52, + "learning_rate": 2.514152753174868e-06, + "loss": 0.0028, + "step": 50266 + }, + { + "epoch": 15.52, + "learning_rate": 2.5138211645756627e-06, + "loss": 0.0027, + "step": 50267 + }, + { + "epoch": 15.52, + "learning_rate": 2.5134895947007532e-06, + "loss": 0.0026, + "step": 50268 + }, + { + "epoch": 15.52, + "learning_rate": 2.5131580435509715e-06, + "loss": 0.0032, + "step": 50269 + }, + { + "epoch": 15.52, + "learning_rate": 2.51282651112715e-06, + "loss": 0.003, + "step": 50270 + }, + { + "epoch": 15.52, + "learning_rate": 2.512494997430115e-06, + "loss": 0.0025, + "step": 50271 + }, + { + "epoch": 15.52, + "learning_rate": 2.5121635024606926e-06, + "loss": 0.0025, + "step": 50272 + }, + { + "epoch": 15.53, + "learning_rate": 2.511832026219717e-06, + "loss": 0.0027, + "step": 50273 + }, + { + "epoch": 15.53, + "learning_rate": 2.511500568708014e-06, + "loss": 0.0027, + "step": 50274 + }, + { + "epoch": 15.53, + "learning_rate": 2.511169129926413e-06, + "loss": 0.0028, + "step": 50275 + }, + { + "epoch": 15.53, + "learning_rate": 2.5108377098757495e-06, + "loss": 0.0029, + "step": 50276 + }, + { + "epoch": 15.53, + "learning_rate": 2.5105063085568415e-06, + "loss": 0.0022, + "step": 50277 + }, + { + "epoch": 15.53, + "learning_rate": 2.5101749259705233e-06, + "loss": 0.0026, + "step": 50278 + }, + { + "epoch": 15.53, + "learning_rate": 2.5098435621176265e-06, + "loss": 0.0038, + "step": 50279 + }, + { + "epoch": 15.53, + "learning_rate": 2.509512216998974e-06, + "loss": 0.0028, + "step": 50280 + }, + { + "epoch": 15.53, + "learning_rate": 2.5091808906154003e-06, + "loss": 0.003, + "step": 50281 + }, + { + "epoch": 15.53, + "learning_rate": 2.508849582967732e-06, + "loss": 0.0035, + "step": 50282 + }, + { + "epoch": 15.53, + "learning_rate": 2.5085182940567943e-06, + "loss": 0.0026, + "step": 50283 + }, + { + "epoch": 15.53, + "learning_rate": 2.508187023883418e-06, + "loss": 0.0025, + "step": 50284 + }, + { + "epoch": 15.53, + "learning_rate": 2.507855772448433e-06, + "loss": 0.0021, + "step": 50285 + }, + { + "epoch": 15.53, + "learning_rate": 2.5075245397526725e-06, + "loss": 0.0036, + "step": 50286 + }, + { + "epoch": 15.53, + "learning_rate": 2.507193325796954e-06, + "loss": 0.0033, + "step": 50287 + }, + { + "epoch": 15.53, + "learning_rate": 2.5068621305821117e-06, + "loss": 0.0029, + "step": 50288 + }, + { + "epoch": 15.53, + "learning_rate": 2.5065309541089766e-06, + "loss": 0.0024, + "step": 50289 + }, + { + "epoch": 15.53, + "learning_rate": 2.5061997963783725e-06, + "loss": 0.0025, + "step": 50290 + }, + { + "epoch": 15.53, + "learning_rate": 2.5058686573911307e-06, + "loss": 0.003, + "step": 50291 + }, + { + "epoch": 15.53, + "learning_rate": 2.5055375371480797e-06, + "loss": 0.0029, + "step": 50292 + }, + { + "epoch": 15.53, + "learning_rate": 2.5052064356500426e-06, + "loss": 0.0026, + "step": 50293 + }, + { + "epoch": 15.53, + "learning_rate": 2.504875352897851e-06, + "loss": 0.0027, + "step": 50294 + }, + { + "epoch": 15.53, + "learning_rate": 2.5045442888923366e-06, + "loss": 0.0021, + "step": 50295 + }, + { + "epoch": 15.53, + "learning_rate": 2.5042132436343235e-06, + "loss": 0.0027, + "step": 50296 + }, + { + "epoch": 15.53, + "learning_rate": 2.503882217124638e-06, + "loss": 0.0033, + "step": 50297 + }, + { + "epoch": 15.53, + "learning_rate": 2.5035512093641123e-06, + "loss": 0.0025, + "step": 50298 + }, + { + "epoch": 15.53, + "learning_rate": 2.5032202203535694e-06, + "loss": 0.0029, + "step": 50299 + }, + { + "epoch": 15.53, + "learning_rate": 2.5028892500938406e-06, + "loss": 0.0015, + "step": 50300 + }, + { + "epoch": 15.53, + "learning_rate": 2.5025582985857564e-06, + "loss": 0.003, + "step": 50301 + }, + { + "epoch": 15.53, + "learning_rate": 2.502227365830141e-06, + "loss": 0.0028, + "step": 50302 + }, + { + "epoch": 15.53, + "learning_rate": 2.501896451827819e-06, + "loss": 0.0026, + "step": 50303 + }, + { + "epoch": 15.53, + "learning_rate": 2.501565556579625e-06, + "loss": 0.0026, + "step": 50304 + }, + { + "epoch": 15.54, + "learning_rate": 2.5012346800863807e-06, + "loss": 0.0025, + "step": 50305 + }, + { + "epoch": 15.54, + "learning_rate": 2.500903822348918e-06, + "loss": 0.0037, + "step": 50306 + }, + { + "epoch": 15.54, + "learning_rate": 2.5005729833680635e-06, + "loss": 0.0026, + "step": 50307 + }, + { + "epoch": 15.54, + "learning_rate": 2.5002421631446406e-06, + "loss": 0.0028, + "step": 50308 + }, + { + "epoch": 15.54, + "learning_rate": 2.499911361679479e-06, + "loss": 0.0022, + "step": 50309 + }, + { + "epoch": 15.54, + "learning_rate": 2.4995805789734105e-06, + "loss": 0.0026, + "step": 50310 + }, + { + "epoch": 15.54, + "learning_rate": 2.499249815027257e-06, + "loss": 0.0025, + "step": 50311 + }, + { + "epoch": 15.54, + "learning_rate": 2.49891906984185e-06, + "loss": 0.0018, + "step": 50312 + }, + { + "epoch": 15.54, + "learning_rate": 2.498588343418015e-06, + "loss": 0.0029, + "step": 50313 + }, + { + "epoch": 15.54, + "learning_rate": 2.4982576357565745e-06, + "loss": 0.003, + "step": 50314 + }, + { + "epoch": 15.54, + "learning_rate": 2.497926946858361e-06, + "loss": 0.0033, + "step": 50315 + }, + { + "epoch": 15.54, + "learning_rate": 2.4975962767242e-06, + "loss": 0.0027, + "step": 50316 + }, + { + "epoch": 15.54, + "learning_rate": 2.4972656253549254e-06, + "loss": 0.0036, + "step": 50317 + }, + { + "epoch": 15.54, + "learning_rate": 2.496934992751352e-06, + "loss": 0.0025, + "step": 50318 + }, + { + "epoch": 15.54, + "learning_rate": 2.4966043789143123e-06, + "loss": 0.0023, + "step": 50319 + }, + { + "epoch": 15.54, + "learning_rate": 2.496273783844636e-06, + "loss": 0.0027, + "step": 50320 + }, + { + "epoch": 15.54, + "learning_rate": 2.4959432075431457e-06, + "loss": 0.0025, + "step": 50321 + }, + { + "epoch": 15.54, + "learning_rate": 2.4956126500106724e-06, + "loss": 0.0028, + "step": 50322 + }, + { + "epoch": 15.54, + "learning_rate": 2.495282111248041e-06, + "loss": 0.0027, + "step": 50323 + }, + { + "epoch": 15.54, + "learning_rate": 2.494951591256074e-06, + "loss": 0.0031, + "step": 50324 + }, + { + "epoch": 15.54, + "learning_rate": 2.4946210900356028e-06, + "loss": 0.0027, + "step": 50325 + }, + { + "epoch": 15.54, + "learning_rate": 2.4942906075874562e-06, + "loss": 0.0025, + "step": 50326 + }, + { + "epoch": 15.54, + "learning_rate": 2.493960143912457e-06, + "loss": 0.0027, + "step": 50327 + }, + { + "epoch": 15.54, + "learning_rate": 2.4936296990114294e-06, + "loss": 0.0032, + "step": 50328 + }, + { + "epoch": 15.54, + "learning_rate": 2.493299272885207e-06, + "loss": 0.0028, + "step": 50329 + }, + { + "epoch": 15.54, + "learning_rate": 2.4929688655346084e-06, + "loss": 0.0028, + "step": 50330 + }, + { + "epoch": 15.54, + "learning_rate": 2.492638476960464e-06, + "loss": 0.0028, + "step": 50331 + }, + { + "epoch": 15.54, + "learning_rate": 2.4923081071636037e-06, + "loss": 0.0026, + "step": 50332 + }, + { + "epoch": 15.54, + "learning_rate": 2.49197775614485e-06, + "loss": 0.0029, + "step": 50333 + }, + { + "epoch": 15.54, + "learning_rate": 2.491647423905026e-06, + "loss": 0.0032, + "step": 50334 + }, + { + "epoch": 15.54, + "learning_rate": 2.491317110444964e-06, + "loss": 0.0034, + "step": 50335 + }, + { + "epoch": 15.54, + "learning_rate": 2.4909868157654837e-06, + "loss": 0.0028, + "step": 50336 + }, + { + "epoch": 15.54, + "learning_rate": 2.49065653986742e-06, + "loss": 0.0026, + "step": 50337 + }, + { + "epoch": 15.55, + "learning_rate": 2.4903262827515918e-06, + "loss": 0.0023, + "step": 50338 + }, + { + "epoch": 15.55, + "learning_rate": 2.4899960444188255e-06, + "loss": 0.0036, + "step": 50339 + }, + { + "epoch": 15.55, + "learning_rate": 2.489665824869949e-06, + "loss": 0.0032, + "step": 50340 + }, + { + "epoch": 15.55, + "learning_rate": 2.48933562410579e-06, + "loss": 0.0031, + "step": 50341 + }, + { + "epoch": 15.55, + "learning_rate": 2.4890054421271704e-06, + "loss": 0.0025, + "step": 50342 + }, + { + "epoch": 15.55, + "learning_rate": 2.488675278934921e-06, + "loss": 0.0031, + "step": 50343 + }, + { + "epoch": 15.55, + "learning_rate": 2.4883451345298636e-06, + "loss": 0.0028, + "step": 50344 + }, + { + "epoch": 15.55, + "learning_rate": 2.488015008912823e-06, + "loss": 0.0022, + "step": 50345 + }, + { + "epoch": 15.55, + "learning_rate": 2.487684902084627e-06, + "loss": 0.0025, + "step": 50346 + }, + { + "epoch": 15.55, + "learning_rate": 2.4873548140461047e-06, + "loss": 0.003, + "step": 50347 + }, + { + "epoch": 15.55, + "learning_rate": 2.487024744798078e-06, + "loss": 0.0026, + "step": 50348 + }, + { + "epoch": 15.55, + "learning_rate": 2.4866946943413685e-06, + "loss": 0.0024, + "step": 50349 + }, + { + "epoch": 15.55, + "learning_rate": 2.486364662676807e-06, + "loss": 0.0038, + "step": 50350 + }, + { + "epoch": 15.55, + "learning_rate": 2.4860346498052202e-06, + "loss": 0.0029, + "step": 50351 + }, + { + "epoch": 15.55, + "learning_rate": 2.4857046557274287e-06, + "loss": 0.0019, + "step": 50352 + }, + { + "epoch": 15.55, + "learning_rate": 2.4853746804442637e-06, + "loss": 0.0034, + "step": 50353 + }, + { + "epoch": 15.55, + "learning_rate": 2.4850447239565467e-06, + "loss": 0.0027, + "step": 50354 + }, + { + "epoch": 15.55, + "learning_rate": 2.484714786265101e-06, + "loss": 0.0025, + "step": 50355 + }, + { + "epoch": 15.55, + "learning_rate": 2.4843848673707537e-06, + "loss": 0.0033, + "step": 50356 + }, + { + "epoch": 15.55, + "learning_rate": 2.4840549672743344e-06, + "loss": 0.0023, + "step": 50357 + }, + { + "epoch": 15.55, + "learning_rate": 2.4837250859766636e-06, + "loss": 0.0025, + "step": 50358 + }, + { + "epoch": 15.55, + "learning_rate": 2.4833952234785642e-06, + "loss": 0.0027, + "step": 50359 + }, + { + "epoch": 15.55, + "learning_rate": 2.483065379780868e-06, + "loss": 0.0027, + "step": 50360 + }, + { + "epoch": 15.55, + "learning_rate": 2.482735554884392e-06, + "loss": 0.003, + "step": 50361 + }, + { + "epoch": 15.55, + "learning_rate": 2.4824057487899665e-06, + "loss": 0.0026, + "step": 50362 + }, + { + "epoch": 15.55, + "learning_rate": 2.482075961498419e-06, + "loss": 0.0026, + "step": 50363 + }, + { + "epoch": 15.55, + "learning_rate": 2.481746193010569e-06, + "loss": 0.0032, + "step": 50364 + }, + { + "epoch": 15.55, + "learning_rate": 2.4814164433272416e-06, + "loss": 0.0023, + "step": 50365 + }, + { + "epoch": 15.55, + "learning_rate": 2.4810867124492654e-06, + "loss": 0.0024, + "step": 50366 + }, + { + "epoch": 15.55, + "learning_rate": 2.4807570003774594e-06, + "loss": 0.0033, + "step": 50367 + }, + { + "epoch": 15.55, + "learning_rate": 2.480427307112655e-06, + "loss": 0.0029, + "step": 50368 + }, + { + "epoch": 15.55, + "learning_rate": 2.4800976326556726e-06, + "loss": 0.0023, + "step": 50369 + }, + { + "epoch": 15.56, + "learning_rate": 2.479767977007336e-06, + "loss": 0.0024, + "step": 50370 + }, + { + "epoch": 15.56, + "learning_rate": 2.4794383401684694e-06, + "loss": 0.0033, + "step": 50371 + }, + { + "epoch": 15.56, + "learning_rate": 2.4791087221399034e-06, + "loss": 0.0026, + "step": 50372 + }, + { + "epoch": 15.56, + "learning_rate": 2.4787791229224555e-06, + "loss": 0.0025, + "step": 50373 + }, + { + "epoch": 15.56, + "learning_rate": 2.4784495425169554e-06, + "loss": 0.0023, + "step": 50374 + }, + { + "epoch": 15.56, + "learning_rate": 2.478119980924224e-06, + "loss": 0.0025, + "step": 50375 + }, + { + "epoch": 15.56, + "learning_rate": 2.4777904381450845e-06, + "loss": 0.0024, + "step": 50376 + }, + { + "epoch": 15.56, + "learning_rate": 2.477460914180363e-06, + "loss": 0.003, + "step": 50377 + }, + { + "epoch": 15.56, + "learning_rate": 2.477131409030886e-06, + "loss": 0.0038, + "step": 50378 + }, + { + "epoch": 15.56, + "learning_rate": 2.476801922697476e-06, + "loss": 0.0024, + "step": 50379 + }, + { + "epoch": 15.56, + "learning_rate": 2.476472455180954e-06, + "loss": 0.0025, + "step": 50380 + }, + { + "epoch": 15.56, + "learning_rate": 2.476143006482146e-06, + "loss": 0.0049, + "step": 50381 + }, + { + "epoch": 15.56, + "learning_rate": 2.47581357660188e-06, + "loss": 0.0022, + "step": 50382 + }, + { + "epoch": 15.56, + "learning_rate": 2.4754841655409736e-06, + "loss": 0.0025, + "step": 50383 + }, + { + "epoch": 15.56, + "learning_rate": 2.4751547733002556e-06, + "loss": 0.0025, + "step": 50384 + }, + { + "epoch": 15.56, + "learning_rate": 2.4748253998805483e-06, + "loss": 0.003, + "step": 50385 + }, + { + "epoch": 15.56, + "learning_rate": 2.474496045282673e-06, + "loss": 0.0025, + "step": 50386 + }, + { + "epoch": 15.56, + "learning_rate": 2.474166709507455e-06, + "loss": 0.0028, + "step": 50387 + }, + { + "epoch": 15.56, + "learning_rate": 2.4738373925557223e-06, + "loss": 0.0022, + "step": 50388 + }, + { + "epoch": 15.56, + "learning_rate": 2.473508094428294e-06, + "loss": 0.0028, + "step": 50389 + }, + { + "epoch": 15.56, + "learning_rate": 2.473178815125993e-06, + "loss": 0.0027, + "step": 50390 + }, + { + "epoch": 15.56, + "learning_rate": 2.4728495546496466e-06, + "loss": 0.0029, + "step": 50391 + }, + { + "epoch": 15.56, + "learning_rate": 2.472520313000074e-06, + "loss": 0.0029, + "step": 50392 + }, + { + "epoch": 15.56, + "learning_rate": 2.472191090178101e-06, + "loss": 0.0017, + "step": 50393 + }, + { + "epoch": 15.56, + "learning_rate": 2.4718618861845533e-06, + "loss": 0.0035, + "step": 50394 + }, + { + "epoch": 15.56, + "learning_rate": 2.471532701020253e-06, + "loss": 0.0028, + "step": 50395 + }, + { + "epoch": 15.56, + "learning_rate": 2.4712035346860184e-06, + "loss": 0.0025, + "step": 50396 + }, + { + "epoch": 15.56, + "learning_rate": 2.4708743871826803e-06, + "loss": 0.0026, + "step": 50397 + }, + { + "epoch": 15.56, + "learning_rate": 2.4705452585110556e-06, + "loss": 0.0024, + "step": 50398 + }, + { + "epoch": 15.56, + "learning_rate": 2.4702161486719743e-06, + "loss": 0.003, + "step": 50399 + }, + { + "epoch": 15.56, + "learning_rate": 2.4698870576662547e-06, + "loss": 0.0041, + "step": 50400 + }, + { + "epoch": 15.56, + "learning_rate": 2.469557985494718e-06, + "loss": 0.0026, + "step": 50401 + }, + { + "epoch": 15.57, + "learning_rate": 2.469228932158192e-06, + "loss": 0.0032, + "step": 50402 + }, + { + "epoch": 15.57, + "learning_rate": 2.4688998976574997e-06, + "loss": 0.0018, + "step": 50403 + }, + { + "epoch": 15.57, + "learning_rate": 2.4685708819934584e-06, + "loss": 0.0033, + "step": 50404 + }, + { + "epoch": 15.57, + "learning_rate": 2.4682418851668987e-06, + "loss": 0.0025, + "step": 50405 + }, + { + "epoch": 15.57, + "learning_rate": 2.46791290717864e-06, + "loss": 0.0024, + "step": 50406 + }, + { + "epoch": 15.57, + "learning_rate": 2.4675839480295027e-06, + "loss": 0.0032, + "step": 50407 + }, + { + "epoch": 15.57, + "learning_rate": 2.4672550077203105e-06, + "loss": 0.0027, + "step": 50408 + }, + { + "epoch": 15.57, + "learning_rate": 2.4669260862518907e-06, + "loss": 0.0034, + "step": 50409 + }, + { + "epoch": 15.57, + "learning_rate": 2.4665971836250623e-06, + "loss": 0.0025, + "step": 50410 + }, + { + "epoch": 15.57, + "learning_rate": 2.466268299840646e-06, + "loss": 0.003, + "step": 50411 + }, + { + "epoch": 15.57, + "learning_rate": 2.4659394348994703e-06, + "loss": 0.0036, + "step": 50412 + }, + { + "epoch": 15.57, + "learning_rate": 2.4656105888023507e-06, + "loss": 0.0031, + "step": 50413 + }, + { + "epoch": 15.57, + "learning_rate": 2.4652817615501125e-06, + "loss": 0.0025, + "step": 50414 + }, + { + "epoch": 15.57, + "learning_rate": 2.4649529531435823e-06, + "loss": 0.0036, + "step": 50415 + }, + { + "epoch": 15.57, + "learning_rate": 2.46462416358358e-06, + "loss": 0.0026, + "step": 50416 + }, + { + "epoch": 15.57, + "learning_rate": 2.4642953928709223e-06, + "loss": 0.0024, + "step": 50417 + }, + { + "epoch": 15.57, + "learning_rate": 2.463966641006438e-06, + "loss": 0.0026, + "step": 50418 + }, + { + "epoch": 15.57, + "learning_rate": 2.463637907990949e-06, + "loss": 0.002, + "step": 50419 + }, + { + "epoch": 15.57, + "learning_rate": 2.4633091938252773e-06, + "loss": 0.0025, + "step": 50420 + }, + { + "epoch": 15.57, + "learning_rate": 2.46298049851024e-06, + "loss": 0.0034, + "step": 50421 + }, + { + "epoch": 15.57, + "learning_rate": 2.4626518220466665e-06, + "loss": 0.0027, + "step": 50422 + }, + { + "epoch": 15.57, + "learning_rate": 2.4623231644353727e-06, + "loss": 0.0026, + "step": 50423 + }, + { + "epoch": 15.57, + "learning_rate": 2.4619945256771836e-06, + "loss": 0.0033, + "step": 50424 + }, + { + "epoch": 15.57, + "learning_rate": 2.4616659057729277e-06, + "loss": 0.0034, + "step": 50425 + }, + { + "epoch": 15.57, + "learning_rate": 2.4613373047234126e-06, + "loss": 0.0025, + "step": 50426 + }, + { + "epoch": 15.57, + "learning_rate": 2.4610087225294688e-06, + "loss": 0.003, + "step": 50427 + }, + { + "epoch": 15.57, + "learning_rate": 2.4606801591919204e-06, + "loss": 0.003, + "step": 50428 + }, + { + "epoch": 15.57, + "learning_rate": 2.4603516147115824e-06, + "loss": 0.0033, + "step": 50429 + }, + { + "epoch": 15.57, + "learning_rate": 2.460023089089284e-06, + "loss": 0.0022, + "step": 50430 + }, + { + "epoch": 15.57, + "learning_rate": 2.459694582325842e-06, + "loss": 0.0025, + "step": 50431 + }, + { + "epoch": 15.57, + "learning_rate": 2.4593660944220767e-06, + "loss": 0.0028, + "step": 50432 + }, + { + "epoch": 15.57, + "learning_rate": 2.459037625378812e-06, + "loss": 0.0027, + "step": 50433 + }, + { + "epoch": 15.57, + "learning_rate": 2.4587091751968727e-06, + "loss": 0.0025, + "step": 50434 + }, + { + "epoch": 15.58, + "learning_rate": 2.458380743877077e-06, + "loss": 0.0027, + "step": 50435 + }, + { + "epoch": 15.58, + "learning_rate": 2.458052331420244e-06, + "loss": 0.0048, + "step": 50436 + }, + { + "epoch": 15.58, + "learning_rate": 2.4577239378271998e-06, + "loss": 0.0041, + "step": 50437 + }, + { + "epoch": 15.58, + "learning_rate": 2.4573955630987624e-06, + "loss": 0.0028, + "step": 50438 + }, + { + "epoch": 15.58, + "learning_rate": 2.4570672072357525e-06, + "loss": 0.0026, + "step": 50439 + }, + { + "epoch": 15.58, + "learning_rate": 2.456738870238997e-06, + "loss": 0.0028, + "step": 50440 + }, + { + "epoch": 15.58, + "learning_rate": 2.456410552109314e-06, + "loss": 0.0026, + "step": 50441 + }, + { + "epoch": 15.58, + "learning_rate": 2.4560822528475205e-06, + "loss": 0.0027, + "step": 50442 + }, + { + "epoch": 15.58, + "learning_rate": 2.455753972454443e-06, + "loss": 0.0022, + "step": 50443 + }, + { + "epoch": 15.58, + "learning_rate": 2.4554257109309e-06, + "loss": 0.003, + "step": 50444 + }, + { + "epoch": 15.58, + "learning_rate": 2.455097468277715e-06, + "loss": 0.0032, + "step": 50445 + }, + { + "epoch": 15.58, + "learning_rate": 2.454769244495707e-06, + "loss": 0.0018, + "step": 50446 + }, + { + "epoch": 15.58, + "learning_rate": 2.4544410395856954e-06, + "loss": 0.0022, + "step": 50447 + }, + { + "epoch": 15.58, + "learning_rate": 2.4541128535485024e-06, + "loss": 0.0024, + "step": 50448 + }, + { + "epoch": 15.58, + "learning_rate": 2.45378468638495e-06, + "loss": 0.0024, + "step": 50449 + }, + { + "epoch": 15.58, + "learning_rate": 2.453456538095861e-06, + "loss": 0.0032, + "step": 50450 + }, + { + "epoch": 15.58, + "learning_rate": 2.453128408682054e-06, + "loss": 0.0016, + "step": 50451 + }, + { + "epoch": 15.58, + "learning_rate": 2.4528002981443455e-06, + "loss": 0.003, + "step": 50452 + }, + { + "epoch": 15.58, + "learning_rate": 2.452472206483564e-06, + "loss": 0.003, + "step": 50453 + }, + { + "epoch": 15.58, + "learning_rate": 2.4521441337005213e-06, + "loss": 0.0042, + "step": 50454 + }, + { + "epoch": 15.58, + "learning_rate": 2.451816079796048e-06, + "loss": 0.0029, + "step": 50455 + }, + { + "epoch": 15.58, + "learning_rate": 2.4514880447709575e-06, + "loss": 0.0025, + "step": 50456 + }, + { + "epoch": 15.58, + "learning_rate": 2.4511600286260706e-06, + "loss": 0.0026, + "step": 50457 + }, + { + "epoch": 15.58, + "learning_rate": 2.450832031362208e-06, + "loss": 0.0021, + "step": 50458 + }, + { + "epoch": 15.58, + "learning_rate": 2.450504052980196e-06, + "loss": 0.0027, + "step": 50459 + }, + { + "epoch": 15.58, + "learning_rate": 2.450176093480846e-06, + "loss": 0.0025, + "step": 50460 + }, + { + "epoch": 15.58, + "learning_rate": 2.4498481528649854e-06, + "loss": 0.0031, + "step": 50461 + }, + { + "epoch": 15.58, + "learning_rate": 2.4495202311334333e-06, + "loss": 0.0032, + "step": 50462 + }, + { + "epoch": 15.58, + "learning_rate": 2.4491923282870035e-06, + "loss": 0.0019, + "step": 50463 + }, + { + "epoch": 15.58, + "learning_rate": 2.448864444326522e-06, + "loss": 0.0032, + "step": 50464 + }, + { + "epoch": 15.58, + "learning_rate": 2.4485365792528094e-06, + "loss": 0.0041, + "step": 50465 + }, + { + "epoch": 15.58, + "learning_rate": 2.4482087330666847e-06, + "loss": 0.0022, + "step": 50466 + }, + { + "epoch": 15.59, + "learning_rate": 2.4478809057689657e-06, + "loss": 0.0024, + "step": 50467 + }, + { + "epoch": 15.59, + "learning_rate": 2.4475530973604757e-06, + "loss": 0.0022, + "step": 50468 + }, + { + "epoch": 15.59, + "learning_rate": 2.4472253078420296e-06, + "loss": 0.0031, + "step": 50469 + }, + { + "epoch": 15.59, + "learning_rate": 2.446897537214451e-06, + "loss": 0.0025, + "step": 50470 + }, + { + "epoch": 15.59, + "learning_rate": 2.4465697854785617e-06, + "loss": 0.0021, + "step": 50471 + }, + { + "epoch": 15.59, + "learning_rate": 2.4462420526351803e-06, + "loss": 0.0025, + "step": 50472 + }, + { + "epoch": 15.59, + "learning_rate": 2.445914338685121e-06, + "loss": 0.003, + "step": 50473 + }, + { + "epoch": 15.59, + "learning_rate": 2.445586643629212e-06, + "loss": 0.0025, + "step": 50474 + }, + { + "epoch": 15.59, + "learning_rate": 2.445258967468265e-06, + "loss": 0.002, + "step": 50475 + }, + { + "epoch": 15.59, + "learning_rate": 2.4449313102031057e-06, + "loss": 0.0029, + "step": 50476 + }, + { + "epoch": 15.59, + "learning_rate": 2.4446036718345512e-06, + "loss": 0.0026, + "step": 50477 + }, + { + "epoch": 15.59, + "learning_rate": 2.444276052363419e-06, + "loss": 0.0035, + "step": 50478 + }, + { + "epoch": 15.59, + "learning_rate": 2.44394845179053e-06, + "loss": 0.0038, + "step": 50479 + }, + { + "epoch": 15.59, + "learning_rate": 2.443620870116703e-06, + "loss": 0.0029, + "step": 50480 + }, + { + "epoch": 15.59, + "learning_rate": 2.4432933073427624e-06, + "loss": 0.0025, + "step": 50481 + }, + { + "epoch": 15.59, + "learning_rate": 2.4429657634695237e-06, + "loss": 0.0032, + "step": 50482 + }, + { + "epoch": 15.59, + "learning_rate": 2.442638238497802e-06, + "loss": 0.0027, + "step": 50483 + }, + { + "epoch": 15.59, + "learning_rate": 2.4423107324284245e-06, + "loss": 0.002, + "step": 50484 + }, + { + "epoch": 15.59, + "learning_rate": 2.4419832452622026e-06, + "loss": 0.002, + "step": 50485 + }, + { + "epoch": 15.59, + "learning_rate": 2.4416557769999626e-06, + "loss": 0.0025, + "step": 50486 + }, + { + "epoch": 15.59, + "learning_rate": 2.441328327642519e-06, + "loss": 0.0026, + "step": 50487 + }, + { + "epoch": 15.59, + "learning_rate": 2.4410008971906906e-06, + "loss": 0.0031, + "step": 50488 + }, + { + "epoch": 15.59, + "learning_rate": 2.4406734856452964e-06, + "loss": 0.0028, + "step": 50489 + }, + { + "epoch": 15.59, + "learning_rate": 2.44034609300716e-06, + "loss": 0.0037, + "step": 50490 + }, + { + "epoch": 15.59, + "learning_rate": 2.440018719277093e-06, + "loss": 0.0033, + "step": 50491 + }, + { + "epoch": 15.59, + "learning_rate": 2.4396913644559215e-06, + "loss": 0.0035, + "step": 50492 + }, + { + "epoch": 15.59, + "learning_rate": 2.439364028544462e-06, + "loss": 0.0026, + "step": 50493 + }, + { + "epoch": 15.59, + "learning_rate": 2.4390367115435276e-06, + "loss": 0.0024, + "step": 50494 + }, + { + "epoch": 15.59, + "learning_rate": 2.4387094134539413e-06, + "loss": 0.003, + "step": 50495 + }, + { + "epoch": 15.59, + "learning_rate": 2.4383821342765258e-06, + "loss": 0.0028, + "step": 50496 + }, + { + "epoch": 15.59, + "learning_rate": 2.4380548740120956e-06, + "loss": 0.0028, + "step": 50497 + }, + { + "epoch": 15.59, + "learning_rate": 2.437727632661466e-06, + "loss": 0.0033, + "step": 50498 + }, + { + "epoch": 15.6, + "learning_rate": 2.437400410225462e-06, + "loss": 0.0034, + "step": 50499 + }, + { + "epoch": 15.6, + "learning_rate": 2.4370732067048952e-06, + "loss": 0.0031, + "step": 50500 + }, + { + "epoch": 15.6, + "learning_rate": 2.436746022100589e-06, + "loss": 0.0021, + "step": 50501 + }, + { + "epoch": 15.6, + "learning_rate": 2.436418856413363e-06, + "loss": 0.0029, + "step": 50502 + }, + { + "epoch": 15.6, + "learning_rate": 2.4360917096440328e-06, + "loss": 0.0024, + "step": 50503 + }, + { + "epoch": 15.6, + "learning_rate": 2.435764581793414e-06, + "loss": 0.0027, + "step": 50504 + }, + { + "epoch": 15.6, + "learning_rate": 2.43543747286233e-06, + "loss": 0.0027, + "step": 50505 + }, + { + "epoch": 15.6, + "learning_rate": 2.4351103828515933e-06, + "loss": 0.003, + "step": 50506 + }, + { + "epoch": 15.6, + "learning_rate": 2.434783311762029e-06, + "loss": 0.0035, + "step": 50507 + }, + { + "epoch": 15.6, + "learning_rate": 2.434456259594452e-06, + "loss": 0.0021, + "step": 50508 + }, + { + "epoch": 15.6, + "learning_rate": 2.4341292263496764e-06, + "loss": 0.0025, + "step": 50509 + }, + { + "epoch": 15.6, + "learning_rate": 2.4338022120285233e-06, + "loss": 0.0028, + "step": 50510 + }, + { + "epoch": 15.6, + "learning_rate": 2.4334752166318133e-06, + "loss": 0.0026, + "step": 50511 + }, + { + "epoch": 15.6, + "learning_rate": 2.433148240160359e-06, + "loss": 0.0033, + "step": 50512 + }, + { + "epoch": 15.6, + "learning_rate": 2.4328212826149846e-06, + "loss": 0.0028, + "step": 50513 + }, + { + "epoch": 15.6, + "learning_rate": 2.432494343996501e-06, + "loss": 0.0034, + "step": 50514 + }, + { + "epoch": 15.6, + "learning_rate": 2.4321674243057325e-06, + "loss": 0.0024, + "step": 50515 + }, + { + "epoch": 15.6, + "learning_rate": 2.4318405235434905e-06, + "loss": 0.0022, + "step": 50516 + }, + { + "epoch": 15.6, + "learning_rate": 2.431513641710599e-06, + "loss": 0.0022, + "step": 50517 + }, + { + "epoch": 15.6, + "learning_rate": 2.4311867788078715e-06, + "loss": 0.0023, + "step": 50518 + }, + { + "epoch": 15.6, + "learning_rate": 2.430859934836124e-06, + "loss": 0.0043, + "step": 50519 + }, + { + "epoch": 15.6, + "learning_rate": 2.430533109796176e-06, + "loss": 0.0019, + "step": 50520 + }, + { + "epoch": 15.6, + "learning_rate": 2.430206303688849e-06, + "loss": 0.0026, + "step": 50521 + }, + { + "epoch": 15.6, + "learning_rate": 2.4298795165149525e-06, + "loss": 0.0022, + "step": 50522 + }, + { + "epoch": 15.6, + "learning_rate": 2.429552748275312e-06, + "loss": 0.0036, + "step": 50523 + }, + { + "epoch": 15.6, + "learning_rate": 2.42922599897074e-06, + "loss": 0.0027, + "step": 50524 + }, + { + "epoch": 15.6, + "learning_rate": 2.428899268602053e-06, + "loss": 0.0024, + "step": 50525 + }, + { + "epoch": 15.6, + "learning_rate": 2.428572557170068e-06, + "loss": 0.0024, + "step": 50526 + }, + { + "epoch": 15.6, + "learning_rate": 2.428245864675608e-06, + "loss": 0.0025, + "step": 50527 + }, + { + "epoch": 15.6, + "learning_rate": 2.4279191911194866e-06, + "loss": 0.0028, + "step": 50528 + }, + { + "epoch": 15.6, + "learning_rate": 2.4275925365025166e-06, + "loss": 0.0029, + "step": 50529 + }, + { + "epoch": 15.6, + "learning_rate": 2.4272659008255217e-06, + "loss": 0.0029, + "step": 50530 + }, + { + "epoch": 15.6, + "learning_rate": 2.4269392840893135e-06, + "loss": 0.002, + "step": 50531 + }, + { + "epoch": 15.61, + "learning_rate": 2.4266126862947106e-06, + "loss": 0.0025, + "step": 50532 + }, + { + "epoch": 15.61, + "learning_rate": 2.426286107442537e-06, + "loss": 0.0023, + "step": 50533 + }, + { + "epoch": 15.61, + "learning_rate": 2.4259595475335973e-06, + "loss": 0.0035, + "step": 50534 + }, + { + "epoch": 15.61, + "learning_rate": 2.425633006568715e-06, + "loss": 0.0038, + "step": 50535 + }, + { + "epoch": 15.61, + "learning_rate": 2.425306484548707e-06, + "loss": 0.0035, + "step": 50536 + }, + { + "epoch": 15.61, + "learning_rate": 2.4249799814743878e-06, + "loss": 0.0027, + "step": 50537 + }, + { + "epoch": 15.61, + "learning_rate": 2.4246534973465775e-06, + "loss": 0.0027, + "step": 50538 + }, + { + "epoch": 15.61, + "learning_rate": 2.4243270321660905e-06, + "loss": 0.0038, + "step": 50539 + }, + { + "epoch": 15.61, + "learning_rate": 2.424000585933741e-06, + "loss": 0.0032, + "step": 50540 + }, + { + "epoch": 15.61, + "learning_rate": 2.4236741586503475e-06, + "loss": 0.0026, + "step": 50541 + }, + { + "epoch": 15.61, + "learning_rate": 2.4233477503167293e-06, + "loss": 0.0023, + "step": 50542 + }, + { + "epoch": 15.61, + "learning_rate": 2.4230213609337004e-06, + "loss": 0.0032, + "step": 50543 + }, + { + "epoch": 15.61, + "learning_rate": 2.4226949905020745e-06, + "loss": 0.0024, + "step": 50544 + }, + { + "epoch": 15.61, + "learning_rate": 2.4223686390226697e-06, + "loss": 0.0029, + "step": 50545 + }, + { + "epoch": 15.61, + "learning_rate": 2.4220423064963073e-06, + "loss": 0.0024, + "step": 50546 + }, + { + "epoch": 15.61, + "learning_rate": 2.4217159929237953e-06, + "loss": 0.003, + "step": 50547 + }, + { + "epoch": 15.61, + "learning_rate": 2.421389698305957e-06, + "loss": 0.0024, + "step": 50548 + }, + { + "epoch": 15.61, + "learning_rate": 2.4210634226436045e-06, + "loss": 0.0024, + "step": 50549 + }, + { + "epoch": 15.61, + "learning_rate": 2.4207371659375524e-06, + "loss": 0.0025, + "step": 50550 + }, + { + "epoch": 15.61, + "learning_rate": 2.420410928188619e-06, + "loss": 0.0041, + "step": 50551 + }, + { + "epoch": 15.61, + "learning_rate": 2.4200847093976233e-06, + "loss": 0.0041, + "step": 50552 + }, + { + "epoch": 15.61, + "learning_rate": 2.4197585095653787e-06, + "loss": 0.0029, + "step": 50553 + }, + { + "epoch": 15.61, + "learning_rate": 2.419432328692697e-06, + "loss": 0.0019, + "step": 50554 + }, + { + "epoch": 15.61, + "learning_rate": 2.4191061667804007e-06, + "loss": 0.0028, + "step": 50555 + }, + { + "epoch": 15.61, + "learning_rate": 2.418780023829299e-06, + "loss": 0.0026, + "step": 50556 + }, + { + "epoch": 15.61, + "learning_rate": 2.418453899840213e-06, + "loss": 0.003, + "step": 50557 + }, + { + "epoch": 15.61, + "learning_rate": 2.418127794813958e-06, + "loss": 0.0021, + "step": 50558 + }, + { + "epoch": 15.61, + "learning_rate": 2.4178017087513485e-06, + "loss": 0.0024, + "step": 50559 + }, + { + "epoch": 15.61, + "learning_rate": 2.4174756416531964e-06, + "loss": 0.0028, + "step": 50560 + }, + { + "epoch": 15.61, + "learning_rate": 2.417149593520325e-06, + "loss": 0.0029, + "step": 50561 + }, + { + "epoch": 15.61, + "learning_rate": 2.416823564353542e-06, + "loss": 0.003, + "step": 50562 + }, + { + "epoch": 15.61, + "learning_rate": 2.416497554153668e-06, + "loss": 0.0022, + "step": 50563 + }, + { + "epoch": 15.62, + "learning_rate": 2.4161715629215187e-06, + "loss": 0.0028, + "step": 50564 + }, + { + "epoch": 15.62, + "learning_rate": 2.415845590657904e-06, + "loss": 0.003, + "step": 50565 + }, + { + "epoch": 15.62, + "learning_rate": 2.4155196373636414e-06, + "loss": 0.0025, + "step": 50566 + }, + { + "epoch": 15.62, + "learning_rate": 2.415193703039552e-06, + "loss": 0.0037, + "step": 50567 + }, + { + "epoch": 15.62, + "learning_rate": 2.4148677876864436e-06, + "loss": 0.0024, + "step": 50568 + }, + { + "epoch": 15.62, + "learning_rate": 2.4145418913051368e-06, + "loss": 0.0034, + "step": 50569 + }, + { + "epoch": 15.62, + "learning_rate": 2.4142160138964434e-06, + "loss": 0.0028, + "step": 50570 + }, + { + "epoch": 15.62, + "learning_rate": 2.413890155461177e-06, + "loss": 0.0036, + "step": 50571 + }, + { + "epoch": 15.62, + "learning_rate": 2.4135643160001552e-06, + "loss": 0.0025, + "step": 50572 + }, + { + "epoch": 15.62, + "learning_rate": 2.4132384955141965e-06, + "loss": 0.0027, + "step": 50573 + }, + { + "epoch": 15.62, + "learning_rate": 2.41291269400411e-06, + "loss": 0.0023, + "step": 50574 + }, + { + "epoch": 15.62, + "learning_rate": 2.412586911470711e-06, + "loss": 0.0028, + "step": 50575 + }, + { + "epoch": 15.62, + "learning_rate": 2.4122611479148197e-06, + "loss": 0.0026, + "step": 50576 + }, + { + "epoch": 15.62, + "learning_rate": 2.4119354033372423e-06, + "loss": 0.0029, + "step": 50577 + }, + { + "epoch": 15.62, + "learning_rate": 2.4116096777387997e-06, + "loss": 0.0028, + "step": 50578 + }, + { + "epoch": 15.62, + "learning_rate": 2.4112839711203084e-06, + "loss": 0.0029, + "step": 50579 + }, + { + "epoch": 15.62, + "learning_rate": 2.4109582834825795e-06, + "loss": 0.0023, + "step": 50580 + }, + { + "epoch": 15.62, + "learning_rate": 2.410632614826425e-06, + "loss": 0.0027, + "step": 50581 + }, + { + "epoch": 15.62, + "learning_rate": 2.4103069651526622e-06, + "loss": 0.0028, + "step": 50582 + }, + { + "epoch": 15.62, + "learning_rate": 2.4099813344621103e-06, + "loss": 0.0029, + "step": 50583 + }, + { + "epoch": 15.62, + "learning_rate": 2.4096557227555785e-06, + "loss": 0.0028, + "step": 50584 + }, + { + "epoch": 15.62, + "learning_rate": 2.409330130033879e-06, + "loss": 0.0024, + "step": 50585 + }, + { + "epoch": 15.62, + "learning_rate": 2.4090045562978326e-06, + "loss": 0.0028, + "step": 50586 + }, + { + "epoch": 15.62, + "learning_rate": 2.4086790015482474e-06, + "loss": 0.0029, + "step": 50587 + }, + { + "epoch": 15.62, + "learning_rate": 2.408353465785941e-06, + "loss": 0.0024, + "step": 50588 + }, + { + "epoch": 15.62, + "learning_rate": 2.4080279490117286e-06, + "loss": 0.0024, + "step": 50589 + }, + { + "epoch": 15.62, + "learning_rate": 2.4077024512264245e-06, + "loss": 0.0023, + "step": 50590 + }, + { + "epoch": 15.62, + "learning_rate": 2.407376972430838e-06, + "loss": 0.0038, + "step": 50591 + }, + { + "epoch": 15.62, + "learning_rate": 2.407051512625789e-06, + "loss": 0.0024, + "step": 50592 + }, + { + "epoch": 15.62, + "learning_rate": 2.4067260718120865e-06, + "loss": 0.0031, + "step": 50593 + }, + { + "epoch": 15.62, + "learning_rate": 2.40640064999055e-06, + "loss": 0.0027, + "step": 50594 + }, + { + "epoch": 15.62, + "learning_rate": 2.4060752471619906e-06, + "loss": 0.0025, + "step": 50595 + }, + { + "epoch": 15.62, + "learning_rate": 2.4057498633272192e-06, + "loss": 0.0029, + "step": 50596 + }, + { + "epoch": 15.63, + "learning_rate": 2.405424498487051e-06, + "loss": 0.0025, + "step": 50597 + }, + { + "epoch": 15.63, + "learning_rate": 2.4050991526423063e-06, + "loss": 0.0029, + "step": 50598 + }, + { + "epoch": 15.63, + "learning_rate": 2.4047738257937902e-06, + "loss": 0.0027, + "step": 50599 + }, + { + "epoch": 15.63, + "learning_rate": 2.404448517942323e-06, + "loss": 0.0029, + "step": 50600 + }, + { + "epoch": 15.63, + "learning_rate": 2.404123229088714e-06, + "loss": 0.0026, + "step": 50601 + }, + { + "epoch": 15.63, + "learning_rate": 2.403797959233777e-06, + "loss": 0.0028, + "step": 50602 + }, + { + "epoch": 15.63, + "learning_rate": 2.403472708378326e-06, + "loss": 0.0024, + "step": 50603 + }, + { + "epoch": 15.63, + "learning_rate": 2.403147476523179e-06, + "loss": 0.0027, + "step": 50604 + }, + { + "epoch": 15.63, + "learning_rate": 2.4028222636691447e-06, + "loss": 0.0026, + "step": 50605 + }, + { + "epoch": 15.63, + "learning_rate": 2.4024970698170346e-06, + "loss": 0.0033, + "step": 50606 + }, + { + "epoch": 15.63, + "learning_rate": 2.4021718949676686e-06, + "loss": 0.0023, + "step": 50607 + }, + { + "epoch": 15.63, + "learning_rate": 2.4018467391218536e-06, + "loss": 0.0027, + "step": 50608 + }, + { + "epoch": 15.63, + "learning_rate": 2.4015216022804056e-06, + "loss": 0.0027, + "step": 50609 + }, + { + "epoch": 15.63, + "learning_rate": 2.4011964844441404e-06, + "loss": 0.0022, + "step": 50610 + }, + { + "epoch": 15.63, + "learning_rate": 2.40087138561387e-06, + "loss": 0.0029, + "step": 50611 + }, + { + "epoch": 15.63, + "learning_rate": 2.4005463057904023e-06, + "loss": 0.0025, + "step": 50612 + }, + { + "epoch": 15.63, + "learning_rate": 2.4002212449745545e-06, + "loss": 0.0022, + "step": 50613 + }, + { + "epoch": 15.63, + "learning_rate": 2.3998962031671425e-06, + "loss": 0.003, + "step": 50614 + }, + { + "epoch": 15.63, + "learning_rate": 2.399571180368976e-06, + "loss": 0.0024, + "step": 50615 + }, + { + "epoch": 15.63, + "learning_rate": 2.399246176580865e-06, + "loss": 0.003, + "step": 50616 + }, + { + "epoch": 15.63, + "learning_rate": 2.398921191803629e-06, + "loss": 0.0036, + "step": 50617 + }, + { + "epoch": 15.63, + "learning_rate": 2.398596226038075e-06, + "loss": 0.0021, + "step": 50618 + }, + { + "epoch": 15.63, + "learning_rate": 2.398271279285017e-06, + "loss": 0.0026, + "step": 50619 + }, + { + "epoch": 15.63, + "learning_rate": 2.397946351545273e-06, + "loss": 0.0024, + "step": 50620 + }, + { + "epoch": 15.63, + "learning_rate": 2.397621442819651e-06, + "loss": 0.0018, + "step": 50621 + }, + { + "epoch": 15.63, + "learning_rate": 2.397296553108962e-06, + "loss": 0.0027, + "step": 50622 + }, + { + "epoch": 15.63, + "learning_rate": 2.3969716824140243e-06, + "loss": 0.0024, + "step": 50623 + }, + { + "epoch": 15.63, + "learning_rate": 2.396646830735643e-06, + "loss": 0.0024, + "step": 50624 + }, + { + "epoch": 15.63, + "learning_rate": 2.3963219980746386e-06, + "loss": 0.0028, + "step": 50625 + }, + { + "epoch": 15.63, + "learning_rate": 2.3959971844318186e-06, + "loss": 0.0029, + "step": 50626 + }, + { + "epoch": 15.63, + "learning_rate": 2.3956723898079948e-06, + "loss": 0.003, + "step": 50627 + }, + { + "epoch": 15.63, + "learning_rate": 2.395347614203981e-06, + "loss": 0.0023, + "step": 50628 + }, + { + "epoch": 15.64, + "learning_rate": 2.3950228576205924e-06, + "loss": 0.0022, + "step": 50629 + }, + { + "epoch": 15.64, + "learning_rate": 2.394698120058636e-06, + "loss": 0.0024, + "step": 50630 + }, + { + "epoch": 15.64, + "learning_rate": 2.3943734015189304e-06, + "loss": 0.0022, + "step": 50631 + }, + { + "epoch": 15.64, + "learning_rate": 2.394048702002283e-06, + "loss": 0.0027, + "step": 50632 + }, + { + "epoch": 15.64, + "learning_rate": 2.3937240215095037e-06, + "loss": 0.0033, + "step": 50633 + }, + { + "epoch": 15.64, + "learning_rate": 2.3933993600414098e-06, + "loss": 0.0023, + "step": 50634 + }, + { + "epoch": 15.64, + "learning_rate": 2.393074717598812e-06, + "loss": 0.0027, + "step": 50635 + }, + { + "epoch": 15.64, + "learning_rate": 2.392750094182523e-06, + "loss": 0.0027, + "step": 50636 + }, + { + "epoch": 15.64, + "learning_rate": 2.3924254897933507e-06, + "loss": 0.0023, + "step": 50637 + }, + { + "epoch": 15.64, + "learning_rate": 2.3921009044321133e-06, + "loss": 0.0026, + "step": 50638 + }, + { + "epoch": 15.64, + "learning_rate": 2.391776338099615e-06, + "loss": 0.0034, + "step": 50639 + }, + { + "epoch": 15.64, + "learning_rate": 2.3914517907966727e-06, + "loss": 0.0025, + "step": 50640 + }, + { + "epoch": 15.64, + "learning_rate": 2.3911272625241023e-06, + "loss": 0.0035, + "step": 50641 + }, + { + "epoch": 15.64, + "learning_rate": 2.390802753282705e-06, + "loss": 0.0035, + "step": 50642 + }, + { + "epoch": 15.64, + "learning_rate": 2.390478263073297e-06, + "loss": 0.0033, + "step": 50643 + }, + { + "epoch": 15.64, + "learning_rate": 2.390153791896692e-06, + "loss": 0.0024, + "step": 50644 + }, + { + "epoch": 15.64, + "learning_rate": 2.389829339753702e-06, + "loss": 0.0024, + "step": 50645 + }, + { + "epoch": 15.64, + "learning_rate": 2.389504906645138e-06, + "loss": 0.003, + "step": 50646 + }, + { + "epoch": 15.64, + "learning_rate": 2.3891804925718064e-06, + "loss": 0.0023, + "step": 50647 + }, + { + "epoch": 15.64, + "learning_rate": 2.3888560975345252e-06, + "loss": 0.0029, + "step": 50648 + }, + { + "epoch": 15.64, + "learning_rate": 2.388531721534102e-06, + "loss": 0.0027, + "step": 50649 + }, + { + "epoch": 15.64, + "learning_rate": 2.3882073645713477e-06, + "loss": 0.004, + "step": 50650 + }, + { + "epoch": 15.64, + "learning_rate": 2.3878830266470786e-06, + "loss": 0.0028, + "step": 50651 + }, + { + "epoch": 15.64, + "learning_rate": 2.3875587077621023e-06, + "loss": 0.0022, + "step": 50652 + }, + { + "epoch": 15.64, + "learning_rate": 2.387234407917226e-06, + "loss": 0.003, + "step": 50653 + }, + { + "epoch": 15.64, + "learning_rate": 2.386910127113269e-06, + "loss": 0.0024, + "step": 50654 + }, + { + "epoch": 15.64, + "learning_rate": 2.3865858653510355e-06, + "loss": 0.003, + "step": 50655 + }, + { + "epoch": 15.64, + "learning_rate": 2.3862616226313418e-06, + "loss": 0.004, + "step": 50656 + }, + { + "epoch": 15.64, + "learning_rate": 2.3859373989549973e-06, + "loss": 0.0028, + "step": 50657 + }, + { + "epoch": 15.64, + "learning_rate": 2.385613194322808e-06, + "loss": 0.0024, + "step": 50658 + }, + { + "epoch": 15.64, + "learning_rate": 2.3852890087355895e-06, + "loss": 0.0023, + "step": 50659 + }, + { + "epoch": 15.64, + "learning_rate": 2.384964842194155e-06, + "loss": 0.0024, + "step": 50660 + }, + { + "epoch": 15.65, + "learning_rate": 2.3846406946993096e-06, + "loss": 0.0023, + "step": 50661 + }, + { + "epoch": 15.65, + "learning_rate": 2.3843165662518686e-06, + "loss": 0.003, + "step": 50662 + }, + { + "epoch": 15.65, + "learning_rate": 2.3839924568526417e-06, + "loss": 0.0023, + "step": 50663 + }, + { + "epoch": 15.65, + "learning_rate": 2.383668366502436e-06, + "loss": 0.0028, + "step": 50664 + }, + { + "epoch": 15.65, + "learning_rate": 2.3833442952020648e-06, + "loss": 0.0038, + "step": 50665 + }, + { + "epoch": 15.65, + "learning_rate": 2.383020242952342e-06, + "loss": 0.0033, + "step": 50666 + }, + { + "epoch": 15.65, + "learning_rate": 2.382696209754074e-06, + "loss": 0.0022, + "step": 50667 + }, + { + "epoch": 15.65, + "learning_rate": 2.382372195608069e-06, + "loss": 0.0021, + "step": 50668 + }, + { + "epoch": 15.65, + "learning_rate": 2.3820482005151436e-06, + "loss": 0.0024, + "step": 50669 + }, + { + "epoch": 15.65, + "learning_rate": 2.381724224476103e-06, + "loss": 0.003, + "step": 50670 + }, + { + "epoch": 15.65, + "learning_rate": 2.381400267491759e-06, + "loss": 0.0037, + "step": 50671 + }, + { + "epoch": 15.65, + "learning_rate": 2.381076329562928e-06, + "loss": 0.0032, + "step": 50672 + }, + { + "epoch": 15.65, + "learning_rate": 2.380752410690409e-06, + "loss": 0.0024, + "step": 50673 + }, + { + "epoch": 15.65, + "learning_rate": 2.380428510875018e-06, + "loss": 0.0023, + "step": 50674 + }, + { + "epoch": 15.65, + "learning_rate": 2.380104630117569e-06, + "loss": 0.0036, + "step": 50675 + }, + { + "epoch": 15.65, + "learning_rate": 2.3797807684188635e-06, + "loss": 0.0032, + "step": 50676 + }, + { + "epoch": 15.65, + "learning_rate": 2.3794569257797194e-06, + "loss": 0.0024, + "step": 50677 + }, + { + "epoch": 15.65, + "learning_rate": 2.379133102200941e-06, + "loss": 0.0027, + "step": 50678 + }, + { + "epoch": 15.65, + "learning_rate": 2.3788092976833444e-06, + "loss": 0.0027, + "step": 50679 + }, + { + "epoch": 15.65, + "learning_rate": 2.3784855122277317e-06, + "loss": 0.0022, + "step": 50680 + }, + { + "epoch": 15.65, + "learning_rate": 2.378161745834917e-06, + "loss": 0.0026, + "step": 50681 + }, + { + "epoch": 15.65, + "learning_rate": 2.3778379985057154e-06, + "loss": 0.0026, + "step": 50682 + }, + { + "epoch": 15.65, + "learning_rate": 2.377514270240926e-06, + "loss": 0.0041, + "step": 50683 + }, + { + "epoch": 15.65, + "learning_rate": 2.377190561041364e-06, + "loss": 0.0022, + "step": 50684 + }, + { + "epoch": 15.65, + "learning_rate": 2.37686687090784e-06, + "loss": 0.0028, + "step": 50685 + }, + { + "epoch": 15.65, + "learning_rate": 2.37654319984116e-06, + "loss": 0.0031, + "step": 50686 + }, + { + "epoch": 15.65, + "learning_rate": 2.37621954784214e-06, + "loss": 0.0029, + "step": 50687 + }, + { + "epoch": 15.65, + "learning_rate": 2.3758959149115847e-06, + "loss": 0.0028, + "step": 50688 + }, + { + "epoch": 15.65, + "learning_rate": 2.3755723010503006e-06, + "loss": 0.0025, + "step": 50689 + }, + { + "epoch": 15.65, + "learning_rate": 2.3752487062591023e-06, + "loss": 0.0034, + "step": 50690 + }, + { + "epoch": 15.65, + "learning_rate": 2.3749251305387987e-06, + "loss": 0.0033, + "step": 50691 + }, + { + "epoch": 15.65, + "learning_rate": 2.3746015738901996e-06, + "loss": 0.0019, + "step": 50692 + }, + { + "epoch": 15.65, + "learning_rate": 2.3742780363141093e-06, + "loss": 0.004, + "step": 50693 + }, + { + "epoch": 15.66, + "learning_rate": 2.3739545178113433e-06, + "loss": 0.0026, + "step": 50694 + }, + { + "epoch": 15.66, + "learning_rate": 2.373631018382705e-06, + "loss": 0.0023, + "step": 50695 + }, + { + "epoch": 15.66, + "learning_rate": 2.3733075380290073e-06, + "loss": 0.0037, + "step": 50696 + }, + { + "epoch": 15.66, + "learning_rate": 2.3729840767510605e-06, + "loss": 0.0027, + "step": 50697 + }, + { + "epoch": 15.66, + "learning_rate": 2.3726606345496717e-06, + "loss": 0.0026, + "step": 50698 + }, + { + "epoch": 15.66, + "learning_rate": 2.3723372114256473e-06, + "loss": 0.0033, + "step": 50699 + }, + { + "epoch": 15.66, + "learning_rate": 2.3720138073798016e-06, + "loss": 0.0024, + "step": 50700 + }, + { + "epoch": 15.66, + "learning_rate": 2.3716904224129365e-06, + "loss": 0.0023, + "step": 50701 + }, + { + "epoch": 15.66, + "learning_rate": 2.3713670565258696e-06, + "loss": 0.0034, + "step": 50702 + }, + { + "epoch": 15.66, + "learning_rate": 2.371043709719404e-06, + "loss": 0.0028, + "step": 50703 + }, + { + "epoch": 15.66, + "learning_rate": 2.370720381994347e-06, + "loss": 0.0047, + "step": 50704 + }, + { + "epoch": 15.66, + "learning_rate": 2.3703970733515103e-06, + "loss": 0.0026, + "step": 50705 + }, + { + "epoch": 15.66, + "learning_rate": 2.370073783791704e-06, + "loss": 0.0025, + "step": 50706 + }, + { + "epoch": 15.66, + "learning_rate": 2.369750513315733e-06, + "loss": 0.0027, + "step": 50707 + }, + { + "epoch": 15.66, + "learning_rate": 2.3694272619244096e-06, + "loss": 0.0025, + "step": 50708 + }, + { + "epoch": 15.66, + "learning_rate": 2.3691040296185373e-06, + "loss": 0.0024, + "step": 50709 + }, + { + "epoch": 15.66, + "learning_rate": 2.3687808163989313e-06, + "loss": 0.0038, + "step": 50710 + }, + { + "epoch": 15.66, + "learning_rate": 2.3684576222663924e-06, + "loss": 0.0027, + "step": 50711 + }, + { + "epoch": 15.66, + "learning_rate": 2.368134447221736e-06, + "loss": 0.0027, + "step": 50712 + }, + { + "epoch": 15.66, + "learning_rate": 2.367811291265768e-06, + "loss": 0.0034, + "step": 50713 + }, + { + "epoch": 15.66, + "learning_rate": 2.3674881543992932e-06, + "loss": 0.003, + "step": 50714 + }, + { + "epoch": 15.66, + "learning_rate": 2.3671650366231225e-06, + "loss": 0.0026, + "step": 50715 + }, + { + "epoch": 15.66, + "learning_rate": 2.366841937938067e-06, + "loss": 0.0031, + "step": 50716 + }, + { + "epoch": 15.66, + "learning_rate": 2.3665188583449285e-06, + "loss": 0.0023, + "step": 50717 + }, + { + "epoch": 15.66, + "learning_rate": 2.3661957978445217e-06, + "loss": 0.0027, + "step": 50718 + }, + { + "epoch": 15.66, + "learning_rate": 2.3658727564376517e-06, + "loss": 0.0028, + "step": 50719 + }, + { + "epoch": 15.66, + "learning_rate": 2.365549734125123e-06, + "loss": 0.003, + "step": 50720 + }, + { + "epoch": 15.66, + "learning_rate": 2.3652267309077483e-06, + "loss": 0.0024, + "step": 50721 + }, + { + "epoch": 15.66, + "learning_rate": 2.3649037467863357e-06, + "loss": 0.0031, + "step": 50722 + }, + { + "epoch": 15.66, + "learning_rate": 2.3645807817616917e-06, + "loss": 0.003, + "step": 50723 + }, + { + "epoch": 15.66, + "learning_rate": 2.36425783583462e-06, + "loss": 0.0033, + "step": 50724 + }, + { + "epoch": 15.66, + "learning_rate": 2.363934909005936e-06, + "loss": 0.0027, + "step": 50725 + }, + { + "epoch": 15.67, + "learning_rate": 2.3636120012764406e-06, + "loss": 0.0023, + "step": 50726 + }, + { + "epoch": 15.67, + "learning_rate": 2.363289112646945e-06, + "loss": 0.0033, + "step": 50727 + }, + { + "epoch": 15.67, + "learning_rate": 2.3629662431182578e-06, + "loss": 0.0033, + "step": 50728 + }, + { + "epoch": 15.67, + "learning_rate": 2.362643392691185e-06, + "loss": 0.0025, + "step": 50729 + }, + { + "epoch": 15.67, + "learning_rate": 2.3623205613665325e-06, + "loss": 0.003, + "step": 50730 + }, + { + "epoch": 15.67, + "learning_rate": 2.3619977491451105e-06, + "loss": 0.0028, + "step": 50731 + }, + { + "epoch": 15.67, + "learning_rate": 2.361674956027724e-06, + "loss": 0.0026, + "step": 50732 + }, + { + "epoch": 15.67, + "learning_rate": 2.361352182015183e-06, + "loss": 0.0034, + "step": 50733 + }, + { + "epoch": 15.67, + "learning_rate": 2.3610294271082945e-06, + "loss": 0.0025, + "step": 50734 + }, + { + "epoch": 15.67, + "learning_rate": 2.3607066913078613e-06, + "loss": 0.0029, + "step": 50735 + }, + { + "epoch": 15.67, + "learning_rate": 2.360383974614694e-06, + "loss": 0.0031, + "step": 50736 + }, + { + "epoch": 15.67, + "learning_rate": 2.3600612770296018e-06, + "loss": 0.0022, + "step": 50737 + }, + { + "epoch": 15.67, + "learning_rate": 2.3597385985533883e-06, + "loss": 0.0026, + "step": 50738 + }, + { + "epoch": 15.67, + "learning_rate": 2.3594159391868645e-06, + "loss": 0.0027, + "step": 50739 + }, + { + "epoch": 15.67, + "learning_rate": 2.3590932989308346e-06, + "loss": 0.0037, + "step": 50740 + }, + { + "epoch": 15.67, + "learning_rate": 2.358770677786103e-06, + "loss": 0.0038, + "step": 50741 + }, + { + "epoch": 15.67, + "learning_rate": 2.35844807575348e-06, + "loss": 0.0028, + "step": 50742 + }, + { + "epoch": 15.67, + "learning_rate": 2.358125492833775e-06, + "loss": 0.0032, + "step": 50743 + }, + { + "epoch": 15.67, + "learning_rate": 2.3578029290277916e-06, + "loss": 0.0024, + "step": 50744 + }, + { + "epoch": 15.67, + "learning_rate": 2.3574803843363346e-06, + "loss": 0.0026, + "step": 50745 + }, + { + "epoch": 15.67, + "learning_rate": 2.357157858760213e-06, + "loss": 0.0034, + "step": 50746 + }, + { + "epoch": 15.67, + "learning_rate": 2.3568353523002363e-06, + "loss": 0.0029, + "step": 50747 + }, + { + "epoch": 15.67, + "learning_rate": 2.3565128649572043e-06, + "loss": 0.0031, + "step": 50748 + }, + { + "epoch": 15.67, + "learning_rate": 2.356190396731932e-06, + "loss": 0.0029, + "step": 50749 + }, + { + "epoch": 15.67, + "learning_rate": 2.355867947625222e-06, + "loss": 0.0029, + "step": 50750 + }, + { + "epoch": 15.67, + "learning_rate": 2.355545517637877e-06, + "loss": 0.0021, + "step": 50751 + }, + { + "epoch": 15.67, + "learning_rate": 2.3552231067707065e-06, + "loss": 0.0025, + "step": 50752 + }, + { + "epoch": 15.67, + "learning_rate": 2.3549007150245206e-06, + "loss": 0.0029, + "step": 50753 + }, + { + "epoch": 15.67, + "learning_rate": 2.354578342400122e-06, + "loss": 0.0031, + "step": 50754 + }, + { + "epoch": 15.67, + "learning_rate": 2.3542559888983154e-06, + "loss": 0.0029, + "step": 50755 + }, + { + "epoch": 15.67, + "learning_rate": 2.353933654519911e-06, + "loss": 0.003, + "step": 50756 + }, + { + "epoch": 15.67, + "learning_rate": 2.3536113392657112e-06, + "loss": 0.0029, + "step": 50757 + }, + { + "epoch": 15.67, + "learning_rate": 2.353289043136523e-06, + "loss": 0.0024, + "step": 50758 + }, + { + "epoch": 15.68, + "learning_rate": 2.352966766133158e-06, + "loss": 0.0022, + "step": 50759 + }, + { + "epoch": 15.68, + "learning_rate": 2.3526445082564166e-06, + "loss": 0.0024, + "step": 50760 + }, + { + "epoch": 15.68, + "learning_rate": 2.3523222695071035e-06, + "loss": 0.0028, + "step": 50761 + }, + { + "epoch": 15.68, + "learning_rate": 2.3520000498860297e-06, + "loss": 0.0026, + "step": 50762 + }, + { + "epoch": 15.68, + "learning_rate": 2.3516778493939964e-06, + "loss": 0.0034, + "step": 50763 + }, + { + "epoch": 15.68, + "learning_rate": 2.351355668031814e-06, + "loss": 0.0027, + "step": 50764 + }, + { + "epoch": 15.68, + "learning_rate": 2.3510335058002864e-06, + "loss": 0.0026, + "step": 50765 + }, + { + "epoch": 15.68, + "learning_rate": 2.3507113627002164e-06, + "loss": 0.0026, + "step": 50766 + }, + { + "epoch": 15.68, + "learning_rate": 2.350389238732412e-06, + "loss": 0.0028, + "step": 50767 + }, + { + "epoch": 15.68, + "learning_rate": 2.3500671338976832e-06, + "loss": 0.0036, + "step": 50768 + }, + { + "epoch": 15.68, + "learning_rate": 2.3497450481968277e-06, + "loss": 0.0031, + "step": 50769 + }, + { + "epoch": 15.68, + "learning_rate": 2.349422981630659e-06, + "loss": 0.0025, + "step": 50770 + }, + { + "epoch": 15.68, + "learning_rate": 2.349100934199978e-06, + "loss": 0.0033, + "step": 50771 + }, + { + "epoch": 15.68, + "learning_rate": 2.3487789059055886e-06, + "loss": 0.0027, + "step": 50772 + }, + { + "epoch": 15.68, + "learning_rate": 2.348456896748298e-06, + "loss": 0.0027, + "step": 50773 + }, + { + "epoch": 15.68, + "learning_rate": 2.348134906728916e-06, + "loss": 0.003, + "step": 50774 + }, + { + "epoch": 15.68, + "learning_rate": 2.3478129358482436e-06, + "loss": 0.0018, + "step": 50775 + }, + { + "epoch": 15.68, + "learning_rate": 2.3474909841070847e-06, + "loss": 0.003, + "step": 50776 + }, + { + "epoch": 15.68, + "learning_rate": 2.347169051506246e-06, + "loss": 0.0021, + "step": 50777 + }, + { + "epoch": 15.68, + "learning_rate": 2.3468471380465362e-06, + "loss": 0.0045, + "step": 50778 + }, + { + "epoch": 15.68, + "learning_rate": 2.3465252437287546e-06, + "loss": 0.0023, + "step": 50779 + }, + { + "epoch": 15.68, + "learning_rate": 2.3462033685537122e-06, + "loss": 0.0022, + "step": 50780 + }, + { + "epoch": 15.68, + "learning_rate": 2.345881512522211e-06, + "loss": 0.004, + "step": 50781 + }, + { + "epoch": 15.68, + "learning_rate": 2.3455596756350528e-06, + "loss": 0.0026, + "step": 50782 + }, + { + "epoch": 15.68, + "learning_rate": 2.3452378578930468e-06, + "loss": 0.0024, + "step": 50783 + }, + { + "epoch": 15.68, + "learning_rate": 2.344916059297e-06, + "loss": 0.0027, + "step": 50784 + }, + { + "epoch": 15.68, + "learning_rate": 2.344594279847714e-06, + "loss": 0.0034, + "step": 50785 + }, + { + "epoch": 15.68, + "learning_rate": 2.3442725195459903e-06, + "loss": 0.0029, + "step": 50786 + }, + { + "epoch": 15.68, + "learning_rate": 2.343950778392642e-06, + "loss": 0.0022, + "step": 50787 + }, + { + "epoch": 15.68, + "learning_rate": 2.3436290563884644e-06, + "loss": 0.0035, + "step": 50788 + }, + { + "epoch": 15.68, + "learning_rate": 2.3433073535342685e-06, + "loss": 0.003, + "step": 50789 + }, + { + "epoch": 15.68, + "learning_rate": 2.342985669830863e-06, + "loss": 0.0031, + "step": 50790 + }, + { + "epoch": 15.69, + "learning_rate": 2.3426640052790404e-06, + "loss": 0.0031, + "step": 50791 + }, + { + "epoch": 15.69, + "learning_rate": 2.342342359879611e-06, + "loss": 0.0027, + "step": 50792 + }, + { + "epoch": 15.69, + "learning_rate": 2.3420207336333845e-06, + "loss": 0.0022, + "step": 50793 + }, + { + "epoch": 15.69, + "learning_rate": 2.341699126541157e-06, + "loss": 0.0019, + "step": 50794 + }, + { + "epoch": 15.69, + "learning_rate": 2.3413775386037407e-06, + "loss": 0.0026, + "step": 50795 + }, + { + "epoch": 15.69, + "learning_rate": 2.3410559698219347e-06, + "loss": 0.0035, + "step": 50796 + }, + { + "epoch": 15.69, + "learning_rate": 2.340734420196543e-06, + "loss": 0.0022, + "step": 50797 + }, + { + "epoch": 15.69, + "learning_rate": 2.3404128897283705e-06, + "loss": 0.003, + "step": 50798 + }, + { + "epoch": 15.69, + "learning_rate": 2.3400913784182256e-06, + "loss": 0.002, + "step": 50799 + }, + { + "epoch": 15.69, + "learning_rate": 2.3397698862669092e-06, + "loss": 0.0027, + "step": 50800 + }, + { + "epoch": 15.69, + "learning_rate": 2.3394484132752236e-06, + "loss": 0.0022, + "step": 50801 + }, + { + "epoch": 15.69, + "learning_rate": 2.339126959443976e-06, + "loss": 0.0022, + "step": 50802 + }, + { + "epoch": 15.69, + "learning_rate": 2.338805524773967e-06, + "loss": 0.0022, + "step": 50803 + }, + { + "epoch": 15.69, + "learning_rate": 2.3384841092660026e-06, + "loss": 0.0027, + "step": 50804 + }, + { + "epoch": 15.69, + "learning_rate": 2.3381627129208906e-06, + "loss": 0.003, + "step": 50805 + }, + { + "epoch": 15.69, + "learning_rate": 2.3378413357394293e-06, + "loss": 0.0034, + "step": 50806 + }, + { + "epoch": 15.69, + "learning_rate": 2.337519977722422e-06, + "loss": 0.0019, + "step": 50807 + }, + { + "epoch": 15.69, + "learning_rate": 2.337198638870676e-06, + "loss": 0.0024, + "step": 50808 + }, + { + "epoch": 15.69, + "learning_rate": 2.336877319184996e-06, + "loss": 0.0033, + "step": 50809 + }, + { + "epoch": 15.69, + "learning_rate": 2.336556018666183e-06, + "loss": 0.0028, + "step": 50810 + }, + { + "epoch": 15.69, + "learning_rate": 2.3362347373150385e-06, + "loss": 0.0028, + "step": 50811 + }, + { + "epoch": 15.69, + "learning_rate": 2.335913475132372e-06, + "loss": 0.0025, + "step": 50812 + }, + { + "epoch": 15.69, + "learning_rate": 2.3355922321189805e-06, + "loss": 0.0022, + "step": 50813 + }, + { + "epoch": 15.69, + "learning_rate": 2.33527100827567e-06, + "loss": 0.0023, + "step": 50814 + }, + { + "epoch": 15.69, + "learning_rate": 2.334949803603249e-06, + "loss": 0.0026, + "step": 50815 + }, + { + "epoch": 15.69, + "learning_rate": 2.334628618102516e-06, + "loss": 0.0023, + "step": 50816 + }, + { + "epoch": 15.69, + "learning_rate": 2.3343074517742714e-06, + "loss": 0.0029, + "step": 50817 + }, + { + "epoch": 15.69, + "learning_rate": 2.333986304619326e-06, + "loss": 0.0027, + "step": 50818 + }, + { + "epoch": 15.69, + "learning_rate": 2.3336651766384745e-06, + "loss": 0.0028, + "step": 50819 + }, + { + "epoch": 15.69, + "learning_rate": 2.3333440678325292e-06, + "loss": 0.0033, + "step": 50820 + }, + { + "epoch": 15.69, + "learning_rate": 2.333022978202287e-06, + "loss": 0.0028, + "step": 50821 + }, + { + "epoch": 15.69, + "learning_rate": 2.3327019077485513e-06, + "loss": 0.0026, + "step": 50822 + }, + { + "epoch": 15.7, + "learning_rate": 2.3323808564721263e-06, + "loss": 0.0028, + "step": 50823 + }, + { + "epoch": 15.7, + "learning_rate": 2.332059824373818e-06, + "loss": 0.0024, + "step": 50824 + }, + { + "epoch": 15.7, + "learning_rate": 2.3317388114544238e-06, + "loss": 0.003, + "step": 50825 + }, + { + "epoch": 15.7, + "learning_rate": 2.3314178177147518e-06, + "loss": 0.003, + "step": 50826 + }, + { + "epoch": 15.7, + "learning_rate": 2.3310968431556034e-06, + "loss": 0.0031, + "step": 50827 + }, + { + "epoch": 15.7, + "learning_rate": 2.3307758877777762e-06, + "loss": 0.002, + "step": 50828 + }, + { + "epoch": 15.7, + "learning_rate": 2.3304549515820786e-06, + "loss": 0.0033, + "step": 50829 + }, + { + "epoch": 15.7, + "learning_rate": 2.3301340345693145e-06, + "loss": 0.0026, + "step": 50830 + }, + { + "epoch": 15.7, + "learning_rate": 2.3298131367402843e-06, + "loss": 0.0028, + "step": 50831 + }, + { + "epoch": 15.7, + "learning_rate": 2.329492258095788e-06, + "loss": 0.0038, + "step": 50832 + }, + { + "epoch": 15.7, + "learning_rate": 2.329171398636633e-06, + "loss": 0.0026, + "step": 50833 + }, + { + "epoch": 15.7, + "learning_rate": 2.3288505583636154e-06, + "loss": 0.0031, + "step": 50834 + }, + { + "epoch": 15.7, + "learning_rate": 2.3285297372775426e-06, + "loss": 0.0031, + "step": 50835 + }, + { + "epoch": 15.7, + "learning_rate": 2.328208935379219e-06, + "loss": 0.0022, + "step": 50836 + }, + { + "epoch": 15.7, + "learning_rate": 2.327888152669444e-06, + "loss": 0.005, + "step": 50837 + }, + { + "epoch": 15.7, + "learning_rate": 2.327567389149017e-06, + "loss": 0.0033, + "step": 50838 + }, + { + "epoch": 15.7, + "learning_rate": 2.3272466448187435e-06, + "loss": 0.0026, + "step": 50839 + }, + { + "epoch": 15.7, + "learning_rate": 2.326925919679429e-06, + "loss": 0.0029, + "step": 50840 + }, + { + "epoch": 15.7, + "learning_rate": 2.3266052137318717e-06, + "loss": 0.0032, + "step": 50841 + }, + { + "epoch": 15.7, + "learning_rate": 2.3262845269768717e-06, + "loss": 0.003, + "step": 50842 + }, + { + "epoch": 15.7, + "learning_rate": 2.3259638594152356e-06, + "loss": 0.0027, + "step": 50843 + }, + { + "epoch": 15.7, + "learning_rate": 2.3256432110477625e-06, + "loss": 0.0035, + "step": 50844 + }, + { + "epoch": 15.7, + "learning_rate": 2.325322581875253e-06, + "loss": 0.0034, + "step": 50845 + }, + { + "epoch": 15.7, + "learning_rate": 2.3250019718985163e-06, + "loss": 0.0029, + "step": 50846 + }, + { + "epoch": 15.7, + "learning_rate": 2.3246813811183488e-06, + "loss": 0.0027, + "step": 50847 + }, + { + "epoch": 15.7, + "learning_rate": 2.3243608095355507e-06, + "loss": 0.0032, + "step": 50848 + }, + { + "epoch": 15.7, + "learning_rate": 2.324040257150929e-06, + "loss": 0.0031, + "step": 50849 + }, + { + "epoch": 15.7, + "learning_rate": 2.3237197239652787e-06, + "loss": 0.0027, + "step": 50850 + }, + { + "epoch": 15.7, + "learning_rate": 2.323399209979409e-06, + "loss": 0.0025, + "step": 50851 + }, + { + "epoch": 15.7, + "learning_rate": 2.323078715194118e-06, + "loss": 0.0025, + "step": 50852 + }, + { + "epoch": 15.7, + "learning_rate": 2.3227582396102045e-06, + "loss": 0.0031, + "step": 50853 + }, + { + "epoch": 15.7, + "learning_rate": 2.3224377832284727e-06, + "loss": 0.0027, + "step": 50854 + }, + { + "epoch": 15.7, + "learning_rate": 2.3221173460497282e-06, + "loss": 0.0028, + "step": 50855 + }, + { + "epoch": 15.71, + "learning_rate": 2.3217969280747644e-06, + "loss": 0.0038, + "step": 50856 + }, + { + "epoch": 15.71, + "learning_rate": 2.3214765293043906e-06, + "loss": 0.0019, + "step": 50857 + }, + { + "epoch": 15.71, + "learning_rate": 2.321156149739403e-06, + "loss": 0.0028, + "step": 50858 + }, + { + "epoch": 15.71, + "learning_rate": 2.3208357893806032e-06, + "loss": 0.0033, + "step": 50859 + }, + { + "epoch": 15.71, + "learning_rate": 2.3205154482287927e-06, + "loss": 0.0032, + "step": 50860 + }, + { + "epoch": 15.71, + "learning_rate": 2.3201951262847777e-06, + "loss": 0.0029, + "step": 50861 + }, + { + "epoch": 15.71, + "learning_rate": 2.319874823549354e-06, + "loss": 0.0037, + "step": 50862 + }, + { + "epoch": 15.71, + "learning_rate": 2.3195545400233223e-06, + "loss": 0.0022, + "step": 50863 + }, + { + "epoch": 15.71, + "learning_rate": 2.319234275707488e-06, + "loss": 0.0021, + "step": 50864 + }, + { + "epoch": 15.71, + "learning_rate": 2.318914030602647e-06, + "loss": 0.003, + "step": 50865 + }, + { + "epoch": 15.71, + "learning_rate": 2.3185938047096024e-06, + "loss": 0.0026, + "step": 50866 + }, + { + "epoch": 15.71, + "learning_rate": 2.318273598029159e-06, + "loss": 0.0024, + "step": 50867 + }, + { + "epoch": 15.71, + "learning_rate": 2.317953410562115e-06, + "loss": 0.0024, + "step": 50868 + }, + { + "epoch": 15.71, + "learning_rate": 2.3176332423092663e-06, + "loss": 0.003, + "step": 50869 + }, + { + "epoch": 15.71, + "learning_rate": 2.3173130932714217e-06, + "loss": 0.0021, + "step": 50870 + }, + { + "epoch": 15.71, + "learning_rate": 2.316992963449376e-06, + "loss": 0.0034, + "step": 50871 + }, + { + "epoch": 15.71, + "learning_rate": 2.316672852843934e-06, + "loss": 0.0042, + "step": 50872 + }, + { + "epoch": 15.71, + "learning_rate": 2.3163527614558922e-06, + "loss": 0.0031, + "step": 50873 + }, + { + "epoch": 15.71, + "learning_rate": 2.3160326892860564e-06, + "loss": 0.0027, + "step": 50874 + }, + { + "epoch": 15.71, + "learning_rate": 2.315712636335221e-06, + "loss": 0.0028, + "step": 50875 + }, + { + "epoch": 15.71, + "learning_rate": 2.3153926026041907e-06, + "loss": 0.0035, + "step": 50876 + }, + { + "epoch": 15.71, + "learning_rate": 2.3150725880937676e-06, + "loss": 0.0032, + "step": 50877 + }, + { + "epoch": 15.71, + "learning_rate": 2.3147525928047497e-06, + "loss": 0.0028, + "step": 50878 + }, + { + "epoch": 15.71, + "learning_rate": 2.314432616737934e-06, + "loss": 0.0037, + "step": 50879 + }, + { + "epoch": 15.71, + "learning_rate": 2.3141126598941266e-06, + "loss": 0.0037, + "step": 50880 + }, + { + "epoch": 15.71, + "learning_rate": 2.313792722274123e-06, + "loss": 0.0023, + "step": 50881 + }, + { + "epoch": 15.71, + "learning_rate": 2.313472803878729e-06, + "loss": 0.0028, + "step": 50882 + }, + { + "epoch": 15.71, + "learning_rate": 2.313152904708741e-06, + "loss": 0.0032, + "step": 50883 + }, + { + "epoch": 15.71, + "learning_rate": 2.3128330247649568e-06, + "loss": 0.0026, + "step": 50884 + }, + { + "epoch": 15.71, + "learning_rate": 2.312513164048179e-06, + "loss": 0.002, + "step": 50885 + }, + { + "epoch": 15.71, + "learning_rate": 2.312193322559211e-06, + "loss": 0.0028, + "step": 50886 + }, + { + "epoch": 15.71, + "learning_rate": 2.3118735002988458e-06, + "loss": 0.0025, + "step": 50887 + }, + { + "epoch": 15.72, + "learning_rate": 2.3115536972678908e-06, + "loss": 0.004, + "step": 50888 + }, + { + "epoch": 15.72, + "learning_rate": 2.3112339134671426e-06, + "loss": 0.0038, + "step": 50889 + }, + { + "epoch": 15.72, + "learning_rate": 2.3109141488973986e-06, + "loss": 0.0027, + "step": 50890 + }, + { + "epoch": 15.72, + "learning_rate": 2.31059440355946e-06, + "loss": 0.0033, + "step": 50891 + }, + { + "epoch": 15.72, + "learning_rate": 2.3102746774541296e-06, + "loss": 0.0024, + "step": 50892 + }, + { + "epoch": 15.72, + "learning_rate": 2.3099549705822045e-06, + "loss": 0.003, + "step": 50893 + }, + { + "epoch": 15.72, + "learning_rate": 2.3096352829444826e-06, + "loss": 0.0024, + "step": 50894 + }, + { + "epoch": 15.72, + "learning_rate": 2.3093156145417684e-06, + "loss": 0.003, + "step": 50895 + }, + { + "epoch": 15.72, + "learning_rate": 2.308995965374855e-06, + "loss": 0.0023, + "step": 50896 + }, + { + "epoch": 15.72, + "learning_rate": 2.308676335444545e-06, + "loss": 0.0035, + "step": 50897 + }, + { + "epoch": 15.72, + "learning_rate": 2.3083567247516447e-06, + "loss": 0.0027, + "step": 50898 + }, + { + "epoch": 15.72, + "learning_rate": 2.308037133296942e-06, + "loss": 0.0023, + "step": 50899 + }, + { + "epoch": 15.72, + "learning_rate": 2.3077175610812406e-06, + "loss": 0.0028, + "step": 50900 + }, + { + "epoch": 15.72, + "learning_rate": 2.307398008105344e-06, + "loss": 0.003, + "step": 50901 + }, + { + "epoch": 15.72, + "learning_rate": 2.307078474370045e-06, + "loss": 0.0022, + "step": 50902 + }, + { + "epoch": 15.72, + "learning_rate": 2.3067589598761484e-06, + "loss": 0.0027, + "step": 50903 + }, + { + "epoch": 15.72, + "learning_rate": 2.3064394646244505e-06, + "loss": 0.0027, + "step": 50904 + }, + { + "epoch": 15.72, + "learning_rate": 2.306119988615748e-06, + "loss": 0.0031, + "step": 50905 + }, + { + "epoch": 15.72, + "learning_rate": 2.3058005318508437e-06, + "loss": 0.003, + "step": 50906 + }, + { + "epoch": 15.72, + "learning_rate": 2.305481094330535e-06, + "loss": 0.0027, + "step": 50907 + }, + { + "epoch": 15.72, + "learning_rate": 2.305161676055626e-06, + "loss": 0.0025, + "step": 50908 + }, + { + "epoch": 15.72, + "learning_rate": 2.3048422770269076e-06, + "loss": 0.0029, + "step": 50909 + }, + { + "epoch": 15.72, + "learning_rate": 2.3045228972451805e-06, + "loss": 0.0037, + "step": 50910 + }, + { + "epoch": 15.72, + "learning_rate": 2.304203536711248e-06, + "loss": 0.0035, + "step": 50911 + }, + { + "epoch": 15.72, + "learning_rate": 2.303884195425904e-06, + "loss": 0.0033, + "step": 50912 + }, + { + "epoch": 15.72, + "learning_rate": 2.3035648733899517e-06, + "loss": 0.0027, + "step": 50913 + }, + { + "epoch": 15.72, + "learning_rate": 2.303245570604188e-06, + "loss": 0.0029, + "step": 50914 + }, + { + "epoch": 15.72, + "learning_rate": 2.302926287069408e-06, + "loss": 0.0021, + "step": 50915 + }, + { + "epoch": 15.72, + "learning_rate": 2.302607022786413e-06, + "loss": 0.0021, + "step": 50916 + }, + { + "epoch": 15.72, + "learning_rate": 2.302287777756005e-06, + "loss": 0.0027, + "step": 50917 + }, + { + "epoch": 15.72, + "learning_rate": 2.301968551978976e-06, + "loss": 0.0048, + "step": 50918 + }, + { + "epoch": 15.72, + "learning_rate": 2.3016493454561297e-06, + "loss": 0.0034, + "step": 50919 + }, + { + "epoch": 15.73, + "learning_rate": 2.301330158188263e-06, + "loss": 0.0029, + "step": 50920 + }, + { + "epoch": 15.73, + "learning_rate": 2.3010109901761713e-06, + "loss": 0.0031, + "step": 50921 + }, + { + "epoch": 15.73, + "learning_rate": 2.300691841420656e-06, + "loss": 0.0023, + "step": 50922 + }, + { + "epoch": 15.73, + "learning_rate": 2.300372711922516e-06, + "loss": 0.0035, + "step": 50923 + }, + { + "epoch": 15.73, + "learning_rate": 2.3000536016825493e-06, + "loss": 0.0028, + "step": 50924 + }, + { + "epoch": 15.73, + "learning_rate": 2.299734510701549e-06, + "loss": 0.0026, + "step": 50925 + }, + { + "epoch": 15.73, + "learning_rate": 2.2994154389803215e-06, + "loss": 0.0032, + "step": 50926 + }, + { + "epoch": 15.73, + "learning_rate": 2.299096386519656e-06, + "loss": 0.0025, + "step": 50927 + }, + { + "epoch": 15.73, + "learning_rate": 2.298777353320356e-06, + "loss": 0.0032, + "step": 50928 + }, + { + "epoch": 15.73, + "learning_rate": 2.298458339383224e-06, + "loss": 0.0025, + "step": 50929 + }, + { + "epoch": 15.73, + "learning_rate": 2.2981393447090463e-06, + "loss": 0.0041, + "step": 50930 + }, + { + "epoch": 15.73, + "learning_rate": 2.297820369298627e-06, + "loss": 0.0027, + "step": 50931 + }, + { + "epoch": 15.73, + "learning_rate": 2.297501413152766e-06, + "loss": 0.0043, + "step": 50932 + }, + { + "epoch": 15.73, + "learning_rate": 2.2971824762722573e-06, + "loss": 0.0022, + "step": 50933 + }, + { + "epoch": 15.73, + "learning_rate": 2.2968635586579025e-06, + "loss": 0.0024, + "step": 50934 + }, + { + "epoch": 15.73, + "learning_rate": 2.296544660310497e-06, + "loss": 0.0031, + "step": 50935 + }, + { + "epoch": 15.73, + "learning_rate": 2.2962257812308355e-06, + "loss": 0.0026, + "step": 50936 + }, + { + "epoch": 15.73, + "learning_rate": 2.295906921419717e-06, + "loss": 0.0034, + "step": 50937 + }, + { + "epoch": 15.73, + "learning_rate": 2.2955880808779417e-06, + "loss": 0.002, + "step": 50938 + }, + { + "epoch": 15.73, + "learning_rate": 2.295269259606312e-06, + "loss": 0.0028, + "step": 50939 + }, + { + "epoch": 15.73, + "learning_rate": 2.2949504576056127e-06, + "loss": 0.0028, + "step": 50940 + }, + { + "epoch": 15.73, + "learning_rate": 2.2946316748766473e-06, + "loss": 0.0043, + "step": 50941 + }, + { + "epoch": 15.73, + "learning_rate": 2.2943129114202166e-06, + "loss": 0.0021, + "step": 50942 + }, + { + "epoch": 15.73, + "learning_rate": 2.2939941672371126e-06, + "loss": 0.0036, + "step": 50943 + }, + { + "epoch": 15.73, + "learning_rate": 2.293675442328136e-06, + "loss": 0.0032, + "step": 50944 + }, + { + "epoch": 15.73, + "learning_rate": 2.2933567366940835e-06, + "loss": 0.0029, + "step": 50945 + }, + { + "epoch": 15.73, + "learning_rate": 2.2930380503357495e-06, + "loss": 0.0029, + "step": 50946 + }, + { + "epoch": 15.73, + "learning_rate": 2.2927193832539318e-06, + "loss": 0.0025, + "step": 50947 + }, + { + "epoch": 15.73, + "learning_rate": 2.2924007354494315e-06, + "loss": 0.0031, + "step": 50948 + }, + { + "epoch": 15.73, + "learning_rate": 2.2920821069230437e-06, + "loss": 0.002, + "step": 50949 + }, + { + "epoch": 15.73, + "learning_rate": 2.291763497675561e-06, + "loss": 0.0025, + "step": 50950 + }, + { + "epoch": 15.73, + "learning_rate": 2.291444907707786e-06, + "loss": 0.0026, + "step": 50951 + }, + { + "epoch": 15.73, + "learning_rate": 2.2911263370205106e-06, + "loss": 0.0025, + "step": 50952 + }, + { + "epoch": 15.74, + "learning_rate": 2.290807785614535e-06, + "loss": 0.0026, + "step": 50953 + }, + { + "epoch": 15.74, + "learning_rate": 2.2904892534906576e-06, + "loss": 0.0032, + "step": 50954 + }, + { + "epoch": 15.74, + "learning_rate": 2.290170740649672e-06, + "loss": 0.0027, + "step": 50955 + }, + { + "epoch": 15.74, + "learning_rate": 2.2898522470923736e-06, + "loss": 0.0023, + "step": 50956 + }, + { + "epoch": 15.74, + "learning_rate": 2.289533772819563e-06, + "loss": 0.0024, + "step": 50957 + }, + { + "epoch": 15.74, + "learning_rate": 2.2892153178320333e-06, + "loss": 0.0022, + "step": 50958 + }, + { + "epoch": 15.74, + "learning_rate": 2.2888968821305847e-06, + "loss": 0.0021, + "step": 50959 + }, + { + "epoch": 15.74, + "learning_rate": 2.28857846571601e-06, + "loss": 0.0032, + "step": 50960 + }, + { + "epoch": 15.74, + "learning_rate": 2.2882600685891052e-06, + "loss": 0.0029, + "step": 50961 + }, + { + "epoch": 15.74, + "learning_rate": 2.287941690750669e-06, + "loss": 0.002, + "step": 50962 + }, + { + "epoch": 15.74, + "learning_rate": 2.2876233322014997e-06, + "loss": 0.0028, + "step": 50963 + }, + { + "epoch": 15.74, + "learning_rate": 2.2873049929423885e-06, + "loss": 0.0032, + "step": 50964 + }, + { + "epoch": 15.74, + "learning_rate": 2.2869866729741364e-06, + "loss": 0.0027, + "step": 50965 + }, + { + "epoch": 15.74, + "learning_rate": 2.2866683722975382e-06, + "loss": 0.0029, + "step": 50966 + }, + { + "epoch": 15.74, + "learning_rate": 2.2863500909133864e-06, + "loss": 0.0023, + "step": 50967 + }, + { + "epoch": 15.74, + "learning_rate": 2.2860318288224792e-06, + "loss": 0.0019, + "step": 50968 + }, + { + "epoch": 15.74, + "learning_rate": 2.2857135860256163e-06, + "loss": 0.0028, + "step": 50969 + }, + { + "epoch": 15.74, + "learning_rate": 2.2853953625235914e-06, + "loss": 0.0027, + "step": 50970 + }, + { + "epoch": 15.74, + "learning_rate": 2.285077158317196e-06, + "loss": 0.0021, + "step": 50971 + }, + { + "epoch": 15.74, + "learning_rate": 2.2847589734072304e-06, + "loss": 0.0028, + "step": 50972 + }, + { + "epoch": 15.74, + "learning_rate": 2.2844408077944923e-06, + "loss": 0.0031, + "step": 50973 + }, + { + "epoch": 15.74, + "learning_rate": 2.284122661479772e-06, + "loss": 0.0039, + "step": 50974 + }, + { + "epoch": 15.74, + "learning_rate": 2.2838045344638714e-06, + "loss": 0.0027, + "step": 50975 + }, + { + "epoch": 15.74, + "learning_rate": 2.283486426747583e-06, + "loss": 0.0019, + "step": 50976 + }, + { + "epoch": 15.74, + "learning_rate": 2.2831683383316995e-06, + "loss": 0.0032, + "step": 50977 + }, + { + "epoch": 15.74, + "learning_rate": 2.2828502692170197e-06, + "loss": 0.0029, + "step": 50978 + }, + { + "epoch": 15.74, + "learning_rate": 2.2825322194043408e-06, + "loss": 0.0027, + "step": 50979 + }, + { + "epoch": 15.74, + "learning_rate": 2.282214188894457e-06, + "loss": 0.0023, + "step": 50980 + }, + { + "epoch": 15.74, + "learning_rate": 2.281896177688161e-06, + "loss": 0.0033, + "step": 50981 + }, + { + "epoch": 15.74, + "learning_rate": 2.281578185786252e-06, + "loss": 0.0027, + "step": 50982 + }, + { + "epoch": 15.74, + "learning_rate": 2.281260213189521e-06, + "loss": 0.003, + "step": 50983 + }, + { + "epoch": 15.74, + "learning_rate": 2.2809422598987673e-06, + "loss": 0.0028, + "step": 50984 + }, + { + "epoch": 15.75, + "learning_rate": 2.2806243259147865e-06, + "loss": 0.0036, + "step": 50985 + }, + { + "epoch": 15.75, + "learning_rate": 2.2803064112383734e-06, + "loss": 0.0031, + "step": 50986 + }, + { + "epoch": 15.75, + "learning_rate": 2.279988515870317e-06, + "loss": 0.0024, + "step": 50987 + }, + { + "epoch": 15.75, + "learning_rate": 2.2796706398114223e-06, + "loss": 0.0026, + "step": 50988 + }, + { + "epoch": 15.75, + "learning_rate": 2.279352783062475e-06, + "loss": 0.0028, + "step": 50989 + }, + { + "epoch": 15.75, + "learning_rate": 2.2790349456242787e-06, + "loss": 0.0029, + "step": 50990 + }, + { + "epoch": 15.75, + "learning_rate": 2.2787171274976237e-06, + "loss": 0.0023, + "step": 50991 + }, + { + "epoch": 15.75, + "learning_rate": 2.278399328683303e-06, + "loss": 0.0034, + "step": 50992 + }, + { + "epoch": 15.75, + "learning_rate": 2.278081549182113e-06, + "loss": 0.0029, + "step": 50993 + }, + { + "epoch": 15.75, + "learning_rate": 2.2777637889948524e-06, + "loss": 0.0022, + "step": 50994 + }, + { + "epoch": 15.75, + "learning_rate": 2.2774460481223105e-06, + "loss": 0.0027, + "step": 50995 + }, + { + "epoch": 15.75, + "learning_rate": 2.2771283265652876e-06, + "loss": 0.003, + "step": 50996 + }, + { + "epoch": 15.75, + "learning_rate": 2.2768106243245758e-06, + "loss": 0.0022, + "step": 50997 + }, + { + "epoch": 15.75, + "learning_rate": 2.276492941400965e-06, + "loss": 0.0023, + "step": 50998 + }, + { + "epoch": 15.75, + "learning_rate": 2.276175277795255e-06, + "loss": 0.0033, + "step": 50999 + }, + { + "epoch": 15.75, + "learning_rate": 2.275857633508242e-06, + "loss": 0.0042, + "step": 51000 + }, + { + "epoch": 15.75, + "learning_rate": 2.2755400085407174e-06, + "loss": 0.0038, + "step": 51001 + }, + { + "epoch": 15.75, + "learning_rate": 2.2752224028934745e-06, + "loss": 0.0035, + "step": 51002 + }, + { + "epoch": 15.75, + "learning_rate": 2.274904816567308e-06, + "loss": 0.0029, + "step": 51003 + }, + { + "epoch": 15.75, + "learning_rate": 2.2745872495630173e-06, + "loss": 0.0025, + "step": 51004 + }, + { + "epoch": 15.75, + "learning_rate": 2.2742697018813895e-06, + "loss": 0.0025, + "step": 51005 + }, + { + "epoch": 15.75, + "learning_rate": 2.273952173523225e-06, + "loss": 0.0039, + "step": 51006 + }, + { + "epoch": 15.75, + "learning_rate": 2.273634664489315e-06, + "loss": 0.0025, + "step": 51007 + }, + { + "epoch": 15.75, + "learning_rate": 2.2733171747804517e-06, + "loss": 0.0025, + "step": 51008 + }, + { + "epoch": 15.75, + "learning_rate": 2.2729997043974315e-06, + "loss": 0.0036, + "step": 51009 + }, + { + "epoch": 15.75, + "learning_rate": 2.2726822533410508e-06, + "loss": 0.0023, + "step": 51010 + }, + { + "epoch": 15.75, + "learning_rate": 2.272364821612101e-06, + "loss": 0.0026, + "step": 51011 + }, + { + "epoch": 15.75, + "learning_rate": 2.272047409211374e-06, + "loss": 0.0032, + "step": 51012 + }, + { + "epoch": 15.75, + "learning_rate": 2.2717300161396684e-06, + "loss": 0.0026, + "step": 51013 + }, + { + "epoch": 15.75, + "learning_rate": 2.271412642397772e-06, + "loss": 0.0039, + "step": 51014 + }, + { + "epoch": 15.75, + "learning_rate": 2.2710952879864835e-06, + "loss": 0.0026, + "step": 51015 + }, + { + "epoch": 15.75, + "learning_rate": 2.2707779529065976e-06, + "loss": 0.0029, + "step": 51016 + }, + { + "epoch": 15.75, + "learning_rate": 2.2704606371589054e-06, + "loss": 0.0025, + "step": 51017 + }, + { + "epoch": 15.76, + "learning_rate": 2.2701433407441987e-06, + "loss": 0.0029, + "step": 51018 + }, + { + "epoch": 15.76, + "learning_rate": 2.2698260636632764e-06, + "loss": 0.0032, + "step": 51019 + }, + { + "epoch": 15.76, + "learning_rate": 2.2695088059169256e-06, + "loss": 0.0022, + "step": 51020 + }, + { + "epoch": 15.76, + "learning_rate": 2.269191567505946e-06, + "loss": 0.0023, + "step": 51021 + }, + { + "epoch": 15.76, + "learning_rate": 2.2688743484311293e-06, + "loss": 0.0032, + "step": 51022 + }, + { + "epoch": 15.76, + "learning_rate": 2.268557148693263e-06, + "loss": 0.002, + "step": 51023 + }, + { + "epoch": 15.76, + "learning_rate": 2.268239968293148e-06, + "loss": 0.0022, + "step": 51024 + }, + { + "epoch": 15.76, + "learning_rate": 2.267922807231576e-06, + "loss": 0.0039, + "step": 51025 + }, + { + "epoch": 15.76, + "learning_rate": 2.2676056655093372e-06, + "loss": 0.0028, + "step": 51026 + }, + { + "epoch": 15.76, + "learning_rate": 2.2672885431272298e-06, + "loss": 0.0023, + "step": 51027 + }, + { + "epoch": 15.76, + "learning_rate": 2.266971440086043e-06, + "loss": 0.0031, + "step": 51028 + }, + { + "epoch": 15.76, + "learning_rate": 2.2666543563865696e-06, + "loss": 0.0025, + "step": 51029 + }, + { + "epoch": 15.76, + "learning_rate": 2.2663372920296034e-06, + "loss": 0.0025, + "step": 51030 + }, + { + "epoch": 15.76, + "learning_rate": 2.266020247015942e-06, + "loss": 0.0024, + "step": 51031 + }, + { + "epoch": 15.76, + "learning_rate": 2.2657032213463737e-06, + "loss": 0.0027, + "step": 51032 + }, + { + "epoch": 15.76, + "learning_rate": 2.2653862150216887e-06, + "loss": 0.0025, + "step": 51033 + }, + { + "epoch": 15.76, + "learning_rate": 2.265069228042688e-06, + "loss": 0.0036, + "step": 51034 + }, + { + "epoch": 15.76, + "learning_rate": 2.2647522604101557e-06, + "loss": 0.0037, + "step": 51035 + }, + { + "epoch": 15.76, + "learning_rate": 2.2644353121248896e-06, + "loss": 0.0025, + "step": 51036 + }, + { + "epoch": 15.76, + "learning_rate": 2.2641183831876846e-06, + "loss": 0.0025, + "step": 51037 + }, + { + "epoch": 15.76, + "learning_rate": 2.2638014735993296e-06, + "loss": 0.0045, + "step": 51038 + }, + { + "epoch": 15.76, + "learning_rate": 2.2634845833606155e-06, + "loss": 0.0028, + "step": 51039 + }, + { + "epoch": 15.76, + "learning_rate": 2.263167712472338e-06, + "loss": 0.0025, + "step": 51040 + }, + { + "epoch": 15.76, + "learning_rate": 2.2628508609352917e-06, + "loss": 0.0041, + "step": 51041 + }, + { + "epoch": 15.76, + "learning_rate": 2.262534028750267e-06, + "loss": 0.004, + "step": 51042 + }, + { + "epoch": 15.76, + "learning_rate": 2.2622172159180533e-06, + "loss": 0.0024, + "step": 51043 + }, + { + "epoch": 15.76, + "learning_rate": 2.261900422439447e-06, + "loss": 0.0034, + "step": 51044 + }, + { + "epoch": 15.76, + "learning_rate": 2.2615836483152378e-06, + "loss": 0.0027, + "step": 51045 + }, + { + "epoch": 15.76, + "learning_rate": 2.261266893546219e-06, + "loss": 0.003, + "step": 51046 + }, + { + "epoch": 15.76, + "learning_rate": 2.260950158133188e-06, + "loss": 0.0028, + "step": 51047 + }, + { + "epoch": 15.76, + "learning_rate": 2.260633442076927e-06, + "loss": 0.0028, + "step": 51048 + }, + { + "epoch": 15.76, + "learning_rate": 2.260316745378234e-06, + "loss": 0.0024, + "step": 51049 + }, + { + "epoch": 15.77, + "learning_rate": 2.260000068037902e-06, + "loss": 0.0035, + "step": 51050 + }, + { + "epoch": 15.77, + "learning_rate": 2.259683410056719e-06, + "loss": 0.0024, + "step": 51051 + }, + { + "epoch": 15.77, + "learning_rate": 2.2593667714354827e-06, + "loss": 0.0026, + "step": 51052 + }, + { + "epoch": 15.77, + "learning_rate": 2.259050152174982e-06, + "loss": 0.0031, + "step": 51053 + }, + { + "epoch": 15.77, + "learning_rate": 2.2587335522760055e-06, + "loss": 0.0029, + "step": 51054 + }, + { + "epoch": 15.77, + "learning_rate": 2.258416971739349e-06, + "loss": 0.0024, + "step": 51055 + }, + { + "epoch": 15.77, + "learning_rate": 2.2581004105658053e-06, + "loss": 0.0028, + "step": 51056 + }, + { + "epoch": 15.77, + "learning_rate": 2.257783868756166e-06, + "loss": 0.0025, + "step": 51057 + }, + { + "epoch": 15.77, + "learning_rate": 2.257467346311217e-06, + "loss": 0.0026, + "step": 51058 + }, + { + "epoch": 15.77, + "learning_rate": 2.257150843231758e-06, + "loss": 0.0024, + "step": 51059 + }, + { + "epoch": 15.77, + "learning_rate": 2.2568343595185747e-06, + "loss": 0.002, + "step": 51060 + }, + { + "epoch": 15.77, + "learning_rate": 2.25651789517246e-06, + "loss": 0.0017, + "step": 51061 + }, + { + "epoch": 15.77, + "learning_rate": 2.25620145019421e-06, + "loss": 0.0023, + "step": 51062 + }, + { + "epoch": 15.77, + "learning_rate": 2.255885024584611e-06, + "loss": 0.0031, + "step": 51063 + }, + { + "epoch": 15.77, + "learning_rate": 2.2555686183444548e-06, + "loss": 0.0021, + "step": 51064 + }, + { + "epoch": 15.77, + "learning_rate": 2.255252231474536e-06, + "loss": 0.0031, + "step": 51065 + }, + { + "epoch": 15.77, + "learning_rate": 2.2549358639756413e-06, + "loss": 0.0028, + "step": 51066 + }, + { + "epoch": 15.77, + "learning_rate": 2.2546195158485675e-06, + "loss": 0.0039, + "step": 51067 + }, + { + "epoch": 15.77, + "learning_rate": 2.2543031870941003e-06, + "loss": 0.0033, + "step": 51068 + }, + { + "epoch": 15.77, + "learning_rate": 2.253986877713036e-06, + "loss": 0.0029, + "step": 51069 + }, + { + "epoch": 15.77, + "learning_rate": 2.2536705877061606e-06, + "loss": 0.0028, + "step": 51070 + }, + { + "epoch": 15.77, + "learning_rate": 2.253354317074268e-06, + "loss": 0.0025, + "step": 51071 + }, + { + "epoch": 15.77, + "learning_rate": 2.253038065818152e-06, + "loss": 0.0031, + "step": 51072 + }, + { + "epoch": 15.77, + "learning_rate": 2.2527218339386005e-06, + "loss": 0.0024, + "step": 51073 + }, + { + "epoch": 15.77, + "learning_rate": 2.252405621436402e-06, + "loss": 0.0035, + "step": 51074 + }, + { + "epoch": 15.77, + "learning_rate": 2.252089428312353e-06, + "loss": 0.0032, + "step": 51075 + }, + { + "epoch": 15.77, + "learning_rate": 2.2517732545672376e-06, + "loss": 0.0031, + "step": 51076 + }, + { + "epoch": 15.77, + "learning_rate": 2.251457100201855e-06, + "loss": 0.0025, + "step": 51077 + }, + { + "epoch": 15.77, + "learning_rate": 2.25114096521699e-06, + "loss": 0.0027, + "step": 51078 + }, + { + "epoch": 15.77, + "learning_rate": 2.2508248496134335e-06, + "loss": 0.0048, + "step": 51079 + }, + { + "epoch": 15.77, + "learning_rate": 2.2505087533919765e-06, + "loss": 0.0027, + "step": 51080 + }, + { + "epoch": 15.77, + "learning_rate": 2.2501926765534134e-06, + "loss": 0.0024, + "step": 51081 + }, + { + "epoch": 15.78, + "learning_rate": 2.249876619098529e-06, + "loss": 0.003, + "step": 51082 + }, + { + "epoch": 15.78, + "learning_rate": 2.2495605810281195e-06, + "loss": 0.0027, + "step": 51083 + }, + { + "epoch": 15.78, + "learning_rate": 2.2492445623429726e-06, + "loss": 0.0031, + "step": 51084 + }, + { + "epoch": 15.78, + "learning_rate": 2.248928563043876e-06, + "loss": 0.0036, + "step": 51085 + }, + { + "epoch": 15.78, + "learning_rate": 2.248612583131623e-06, + "loss": 0.0037, + "step": 51086 + }, + { + "epoch": 15.78, + "learning_rate": 2.248296622607006e-06, + "loss": 0.0026, + "step": 51087 + }, + { + "epoch": 15.78, + "learning_rate": 2.247980681470814e-06, + "loss": 0.0035, + "step": 51088 + }, + { + "epoch": 15.78, + "learning_rate": 2.2476647597238323e-06, + "loss": 0.0027, + "step": 51089 + }, + { + "epoch": 15.78, + "learning_rate": 2.2473488573668578e-06, + "loss": 0.0034, + "step": 51090 + }, + { + "epoch": 15.78, + "learning_rate": 2.2470329744006756e-06, + "loss": 0.003, + "step": 51091 + }, + { + "epoch": 15.78, + "learning_rate": 2.246717110826078e-06, + "loss": 0.0025, + "step": 51092 + }, + { + "epoch": 15.78, + "learning_rate": 2.246401266643857e-06, + "loss": 0.0034, + "step": 51093 + }, + { + "epoch": 15.78, + "learning_rate": 2.2460854418548015e-06, + "loss": 0.0031, + "step": 51094 + }, + { + "epoch": 15.78, + "learning_rate": 2.245769636459697e-06, + "loss": 0.0024, + "step": 51095 + }, + { + "epoch": 15.78, + "learning_rate": 2.2454538504593405e-06, + "loss": 0.0025, + "step": 51096 + }, + { + "epoch": 15.78, + "learning_rate": 2.2451380838545145e-06, + "loss": 0.0025, + "step": 51097 + }, + { + "epoch": 15.78, + "learning_rate": 2.2448223366460166e-06, + "loss": 0.0026, + "step": 51098 + }, + { + "epoch": 15.78, + "learning_rate": 2.2445066088346312e-06, + "loss": 0.0038, + "step": 51099 + }, + { + "epoch": 15.78, + "learning_rate": 2.244190900421147e-06, + "loss": 0.0032, + "step": 51100 + }, + { + "epoch": 15.78, + "learning_rate": 2.2438752114063554e-06, + "loss": 0.0027, + "step": 51101 + }, + { + "epoch": 15.78, + "learning_rate": 2.243559541791047e-06, + "loss": 0.0024, + "step": 51102 + }, + { + "epoch": 15.78, + "learning_rate": 2.2432438915760146e-06, + "loss": 0.0023, + "step": 51103 + }, + { + "epoch": 15.78, + "learning_rate": 2.2429282607620427e-06, + "loss": 0.004, + "step": 51104 + }, + { + "epoch": 15.78, + "learning_rate": 2.24261264934992e-06, + "loss": 0.0025, + "step": 51105 + }, + { + "epoch": 15.78, + "learning_rate": 2.2422970573404402e-06, + "loss": 0.0023, + "step": 51106 + }, + { + "epoch": 15.78, + "learning_rate": 2.2419814847343878e-06, + "loss": 0.0033, + "step": 51107 + }, + { + "epoch": 15.78, + "learning_rate": 2.2416659315325574e-06, + "loss": 0.0028, + "step": 51108 + }, + { + "epoch": 15.78, + "learning_rate": 2.2413503977357356e-06, + "loss": 0.0028, + "step": 51109 + }, + { + "epoch": 15.78, + "learning_rate": 2.241034883344709e-06, + "loss": 0.0024, + "step": 51110 + }, + { + "epoch": 15.78, + "learning_rate": 2.2407193883602694e-06, + "loss": 0.0021, + "step": 51111 + }, + { + "epoch": 15.78, + "learning_rate": 2.2404039127832077e-06, + "loss": 0.0038, + "step": 51112 + }, + { + "epoch": 15.78, + "learning_rate": 2.240088456614309e-06, + "loss": 0.0029, + "step": 51113 + }, + { + "epoch": 15.78, + "learning_rate": 2.2397730198543668e-06, + "loss": 0.0027, + "step": 51114 + }, + { + "epoch": 15.79, + "learning_rate": 2.239457602504168e-06, + "loss": 0.0033, + "step": 51115 + }, + { + "epoch": 15.79, + "learning_rate": 2.2391422045644984e-06, + "loss": 0.0029, + "step": 51116 + }, + { + "epoch": 15.79, + "learning_rate": 2.238826826036149e-06, + "loss": 0.0022, + "step": 51117 + }, + { + "epoch": 15.79, + "learning_rate": 2.2385114669199126e-06, + "loss": 0.0055, + "step": 51118 + }, + { + "epoch": 15.79, + "learning_rate": 2.2381961272165754e-06, + "loss": 0.0024, + "step": 51119 + }, + { + "epoch": 15.79, + "learning_rate": 2.2378808069269207e-06, + "loss": 0.0029, + "step": 51120 + }, + { + "epoch": 15.79, + "learning_rate": 2.2375655060517465e-06, + "loss": 0.0022, + "step": 51121 + }, + { + "epoch": 15.79, + "learning_rate": 2.2372502245918325e-06, + "loss": 0.0028, + "step": 51122 + }, + { + "epoch": 15.79, + "learning_rate": 2.2369349625479733e-06, + "loss": 0.0035, + "step": 51123 + }, + { + "epoch": 15.79, + "learning_rate": 2.236619719920956e-06, + "loss": 0.0025, + "step": 51124 + }, + { + "epoch": 15.79, + "learning_rate": 2.236304496711571e-06, + "loss": 0.0032, + "step": 51125 + }, + { + "epoch": 15.79, + "learning_rate": 2.2359892929206007e-06, + "loss": 0.0033, + "step": 51126 + }, + { + "epoch": 15.79, + "learning_rate": 2.23567410854884e-06, + "loss": 0.0027, + "step": 51127 + }, + { + "epoch": 15.79, + "learning_rate": 2.2353589435970715e-06, + "loss": 0.003, + "step": 51128 + }, + { + "epoch": 15.79, + "learning_rate": 2.235043798066089e-06, + "loss": 0.0034, + "step": 51129 + }, + { + "epoch": 15.79, + "learning_rate": 2.2347286719566787e-06, + "loss": 0.0019, + "step": 51130 + }, + { + "epoch": 15.79, + "learning_rate": 2.234413565269625e-06, + "loss": 0.0026, + "step": 51131 + }, + { + "epoch": 15.79, + "learning_rate": 2.2340984780057206e-06, + "loss": 0.0028, + "step": 51132 + }, + { + "epoch": 15.79, + "learning_rate": 2.233783410165754e-06, + "loss": 0.0023, + "step": 51133 + }, + { + "epoch": 15.79, + "learning_rate": 2.2334683617505095e-06, + "loss": 0.0031, + "step": 51134 + }, + { + "epoch": 15.79, + "learning_rate": 2.233153332760779e-06, + "loss": 0.0024, + "step": 51135 + }, + { + "epoch": 15.79, + "learning_rate": 2.2328383231973462e-06, + "loss": 0.0024, + "step": 51136 + }, + { + "epoch": 15.79, + "learning_rate": 2.2325233330610042e-06, + "loss": 0.0028, + "step": 51137 + }, + { + "epoch": 15.79, + "learning_rate": 2.232208362352536e-06, + "loss": 0.003, + "step": 51138 + }, + { + "epoch": 15.79, + "learning_rate": 2.231893411072733e-06, + "loss": 0.0031, + "step": 51139 + }, + { + "epoch": 15.79, + "learning_rate": 2.2315784792223825e-06, + "loss": 0.0036, + "step": 51140 + }, + { + "epoch": 15.79, + "learning_rate": 2.2312635668022676e-06, + "loss": 0.0029, + "step": 51141 + }, + { + "epoch": 15.79, + "learning_rate": 2.230948673813179e-06, + "loss": 0.003, + "step": 51142 + }, + { + "epoch": 15.79, + "learning_rate": 2.230633800255909e-06, + "loss": 0.0023, + "step": 51143 + }, + { + "epoch": 15.79, + "learning_rate": 2.2303189461312367e-06, + "loss": 0.0027, + "step": 51144 + }, + { + "epoch": 15.79, + "learning_rate": 2.2300041114399574e-06, + "loss": 0.0027, + "step": 51145 + }, + { + "epoch": 15.79, + "learning_rate": 2.2296892961828555e-06, + "loss": 0.0032, + "step": 51146 + }, + { + "epoch": 15.8, + "learning_rate": 2.2293745003607137e-06, + "loss": 0.0026, + "step": 51147 + }, + { + "epoch": 15.8, + "learning_rate": 2.229059723974324e-06, + "loss": 0.0022, + "step": 51148 + }, + { + "epoch": 15.8, + "learning_rate": 2.2287449670244764e-06, + "loss": 0.0029, + "step": 51149 + }, + { + "epoch": 15.8, + "learning_rate": 2.228430229511955e-06, + "loss": 0.0018, + "step": 51150 + }, + { + "epoch": 15.8, + "learning_rate": 2.228115511437544e-06, + "loss": 0.0033, + "step": 51151 + }, + { + "epoch": 15.8, + "learning_rate": 2.227800812802037e-06, + "loss": 0.0027, + "step": 51152 + }, + { + "epoch": 15.8, + "learning_rate": 2.227486133606215e-06, + "loss": 0.0032, + "step": 51153 + }, + { + "epoch": 15.8, + "learning_rate": 2.2271714738508664e-06, + "loss": 0.0029, + "step": 51154 + }, + { + "epoch": 15.8, + "learning_rate": 2.226856833536787e-06, + "loss": 0.0034, + "step": 51155 + }, + { + "epoch": 15.8, + "learning_rate": 2.2265422126647498e-06, + "loss": 0.0022, + "step": 51156 + }, + { + "epoch": 15.8, + "learning_rate": 2.2262276112355474e-06, + "loss": 0.0041, + "step": 51157 + }, + { + "epoch": 15.8, + "learning_rate": 2.225913029249972e-06, + "loss": 0.0032, + "step": 51158 + }, + { + "epoch": 15.8, + "learning_rate": 2.2255984667088027e-06, + "loss": 0.0037, + "step": 51159 + }, + { + "epoch": 15.8, + "learning_rate": 2.225283923612832e-06, + "loss": 0.0033, + "step": 51160 + }, + { + "epoch": 15.8, + "learning_rate": 2.224969399962845e-06, + "loss": 0.0023, + "step": 51161 + }, + { + "epoch": 15.8, + "learning_rate": 2.224654895759624e-06, + "loss": 0.0028, + "step": 51162 + }, + { + "epoch": 15.8, + "learning_rate": 2.22434041100396e-06, + "loss": 0.0028, + "step": 51163 + }, + { + "epoch": 15.8, + "learning_rate": 2.2240259456966408e-06, + "loss": 0.0023, + "step": 51164 + }, + { + "epoch": 15.8, + "learning_rate": 2.223711499838451e-06, + "loss": 0.0027, + "step": 51165 + }, + { + "epoch": 15.8, + "learning_rate": 2.2233970734301746e-06, + "loss": 0.0038, + "step": 51166 + }, + { + "epoch": 15.8, + "learning_rate": 2.223082666472601e-06, + "loss": 0.0028, + "step": 51167 + }, + { + "epoch": 15.8, + "learning_rate": 2.2227682789665184e-06, + "loss": 0.0025, + "step": 51168 + }, + { + "epoch": 15.8, + "learning_rate": 2.2224539109127074e-06, + "loss": 0.0034, + "step": 51169 + }, + { + "epoch": 15.8, + "learning_rate": 2.2221395623119614e-06, + "loss": 0.0024, + "step": 51170 + }, + { + "epoch": 15.8, + "learning_rate": 2.2218252331650626e-06, + "loss": 0.0024, + "step": 51171 + }, + { + "epoch": 15.8, + "learning_rate": 2.221510923472795e-06, + "loss": 0.0027, + "step": 51172 + }, + { + "epoch": 15.8, + "learning_rate": 2.221196633235947e-06, + "loss": 0.0034, + "step": 51173 + }, + { + "epoch": 15.8, + "learning_rate": 2.2208823624553077e-06, + "loss": 0.0026, + "step": 51174 + }, + { + "epoch": 15.8, + "learning_rate": 2.2205681111316577e-06, + "loss": 0.0035, + "step": 51175 + }, + { + "epoch": 15.8, + "learning_rate": 2.220253879265789e-06, + "loss": 0.0028, + "step": 51176 + }, + { + "epoch": 15.8, + "learning_rate": 2.219939666858484e-06, + "loss": 0.0033, + "step": 51177 + }, + { + "epoch": 15.8, + "learning_rate": 2.219625473910526e-06, + "loss": 0.0022, + "step": 51178 + }, + { + "epoch": 15.81, + "learning_rate": 2.219311300422704e-06, + "loss": 0.0031, + "step": 51179 + }, + { + "epoch": 15.81, + "learning_rate": 2.218997146395806e-06, + "loss": 0.0034, + "step": 51180 + }, + { + "epoch": 15.81, + "learning_rate": 2.2186830118306157e-06, + "loss": 0.0023, + "step": 51181 + }, + { + "epoch": 15.81, + "learning_rate": 2.2183688967279148e-06, + "loss": 0.0027, + "step": 51182 + }, + { + "epoch": 15.81, + "learning_rate": 2.218054801088496e-06, + "loss": 0.0025, + "step": 51183 + }, + { + "epoch": 15.81, + "learning_rate": 2.2177407249131387e-06, + "loss": 0.0019, + "step": 51184 + }, + { + "epoch": 15.81, + "learning_rate": 2.2174266682026314e-06, + "loss": 0.0026, + "step": 51185 + }, + { + "epoch": 15.81, + "learning_rate": 2.217112630957764e-06, + "loss": 0.0027, + "step": 51186 + }, + { + "epoch": 15.81, + "learning_rate": 2.2167986131793127e-06, + "loss": 0.0028, + "step": 51187 + }, + { + "epoch": 15.81, + "learning_rate": 2.2164846148680675e-06, + "loss": 0.0021, + "step": 51188 + }, + { + "epoch": 15.81, + "learning_rate": 2.216170636024817e-06, + "loss": 0.0031, + "step": 51189 + }, + { + "epoch": 15.81, + "learning_rate": 2.21585667665034e-06, + "loss": 0.0028, + "step": 51190 + }, + { + "epoch": 15.81, + "learning_rate": 2.2155427367454286e-06, + "loss": 0.0022, + "step": 51191 + }, + { + "epoch": 15.81, + "learning_rate": 2.2152288163108635e-06, + "loss": 0.003, + "step": 51192 + }, + { + "epoch": 15.81, + "learning_rate": 2.2149149153474302e-06, + "loss": 0.0028, + "step": 51193 + }, + { + "epoch": 15.81, + "learning_rate": 2.214601033855913e-06, + "loss": 0.0023, + "step": 51194 + }, + { + "epoch": 15.81, + "learning_rate": 2.2142871718371018e-06, + "loss": 0.0024, + "step": 51195 + }, + { + "epoch": 15.81, + "learning_rate": 2.2139733292917787e-06, + "loss": 0.0031, + "step": 51196 + }, + { + "epoch": 15.81, + "learning_rate": 2.2136595062207257e-06, + "loss": 0.003, + "step": 51197 + }, + { + "epoch": 15.81, + "learning_rate": 2.2133457026247317e-06, + "loss": 0.0029, + "step": 51198 + }, + { + "epoch": 15.81, + "learning_rate": 2.213031918504579e-06, + "loss": 0.0028, + "step": 51199 + }, + { + "epoch": 15.81, + "learning_rate": 2.212718153861053e-06, + "loss": 0.0026, + "step": 51200 + }, + { + "epoch": 15.81, + "learning_rate": 2.2124044086949423e-06, + "loss": 0.0029, + "step": 51201 + }, + { + "epoch": 15.81, + "learning_rate": 2.212090683007029e-06, + "loss": 0.0035, + "step": 51202 + }, + { + "epoch": 15.81, + "learning_rate": 2.2117769767980944e-06, + "loss": 0.0035, + "step": 51203 + }, + { + "epoch": 15.81, + "learning_rate": 2.211463290068926e-06, + "loss": 0.0032, + "step": 51204 + }, + { + "epoch": 15.81, + "learning_rate": 2.2111496228203113e-06, + "loss": 0.0024, + "step": 51205 + }, + { + "epoch": 15.81, + "learning_rate": 2.2108359750530304e-06, + "loss": 0.003, + "step": 51206 + }, + { + "epoch": 15.81, + "learning_rate": 2.210522346767868e-06, + "loss": 0.0038, + "step": 51207 + }, + { + "epoch": 15.81, + "learning_rate": 2.2102087379656136e-06, + "loss": 0.0036, + "step": 51208 + }, + { + "epoch": 15.81, + "learning_rate": 2.2098951486470434e-06, + "loss": 0.0027, + "step": 51209 + }, + { + "epoch": 15.81, + "learning_rate": 2.209581578812947e-06, + "loss": 0.0027, + "step": 51210 + }, + { + "epoch": 15.81, + "learning_rate": 2.209268028464111e-06, + "loss": 0.0029, + "step": 51211 + }, + { + "epoch": 15.82, + "learning_rate": 2.2089544976013167e-06, + "loss": 0.0033, + "step": 51212 + }, + { + "epoch": 15.82, + "learning_rate": 2.2086409862253444e-06, + "loss": 0.0022, + "step": 51213 + }, + { + "epoch": 15.82, + "learning_rate": 2.208327494336986e-06, + "loss": 0.0024, + "step": 51214 + }, + { + "epoch": 15.82, + "learning_rate": 2.208014021937018e-06, + "loss": 0.0033, + "step": 51215 + }, + { + "epoch": 15.82, + "learning_rate": 2.207700569026232e-06, + "loss": 0.0022, + "step": 51216 + }, + { + "epoch": 15.82, + "learning_rate": 2.2073871356054065e-06, + "loss": 0.0022, + "step": 51217 + }, + { + "epoch": 15.82, + "learning_rate": 2.2070737216753257e-06, + "loss": 0.0026, + "step": 51218 + }, + { + "epoch": 15.82, + "learning_rate": 2.2067603272367745e-06, + "loss": 0.0025, + "step": 51219 + }, + { + "epoch": 15.82, + "learning_rate": 2.2064469522905397e-06, + "loss": 0.0029, + "step": 51220 + }, + { + "epoch": 15.82, + "learning_rate": 2.2061335968374e-06, + "loss": 0.0028, + "step": 51221 + }, + { + "epoch": 15.82, + "learning_rate": 2.205820260878143e-06, + "loss": 0.0034, + "step": 51222 + }, + { + "epoch": 15.82, + "learning_rate": 2.2055069444135533e-06, + "loss": 0.0023, + "step": 51223 + }, + { + "epoch": 15.82, + "learning_rate": 2.205193647444408e-06, + "loss": 0.0034, + "step": 51224 + }, + { + "epoch": 15.82, + "learning_rate": 2.204880369971496e-06, + "loss": 0.0041, + "step": 51225 + }, + { + "epoch": 15.82, + "learning_rate": 2.2045671119956024e-06, + "loss": 0.0036, + "step": 51226 + }, + { + "epoch": 15.82, + "learning_rate": 2.204253873517508e-06, + "loss": 0.0034, + "step": 51227 + }, + { + "epoch": 15.82, + "learning_rate": 2.203940654537994e-06, + "loss": 0.0024, + "step": 51228 + }, + { + "epoch": 15.82, + "learning_rate": 2.2036274550578495e-06, + "loss": 0.0025, + "step": 51229 + }, + { + "epoch": 15.82, + "learning_rate": 2.203314275077851e-06, + "loss": 0.0028, + "step": 51230 + }, + { + "epoch": 15.82, + "learning_rate": 2.203001114598786e-06, + "loss": 0.0029, + "step": 51231 + }, + { + "epoch": 15.82, + "learning_rate": 2.20268797362144e-06, + "loss": 0.0029, + "step": 51232 + }, + { + "epoch": 15.82, + "learning_rate": 2.2023748521465936e-06, + "loss": 0.003, + "step": 51233 + }, + { + "epoch": 15.82, + "learning_rate": 2.2020617501750275e-06, + "loss": 0.0025, + "step": 51234 + }, + { + "epoch": 15.82, + "learning_rate": 2.201748667707527e-06, + "loss": 0.0029, + "step": 51235 + }, + { + "epoch": 15.82, + "learning_rate": 2.201435604744878e-06, + "loss": 0.0029, + "step": 51236 + }, + { + "epoch": 15.82, + "learning_rate": 2.2011225612878607e-06, + "loss": 0.0022, + "step": 51237 + }, + { + "epoch": 15.82, + "learning_rate": 2.2008095373372563e-06, + "loss": 0.002, + "step": 51238 + }, + { + "epoch": 15.82, + "learning_rate": 2.2004965328938523e-06, + "loss": 0.0031, + "step": 51239 + }, + { + "epoch": 15.82, + "learning_rate": 2.2001835479584257e-06, + "loss": 0.0022, + "step": 51240 + }, + { + "epoch": 15.82, + "learning_rate": 2.1998705825317623e-06, + "loss": 0.0023, + "step": 51241 + }, + { + "epoch": 15.82, + "learning_rate": 2.1995576366146488e-06, + "loss": 0.0032, + "step": 51242 + }, + { + "epoch": 15.82, + "learning_rate": 2.199244710207864e-06, + "loss": 0.0025, + "step": 51243 + }, + { + "epoch": 15.83, + "learning_rate": 2.1989318033121885e-06, + "loss": 0.0033, + "step": 51244 + }, + { + "epoch": 15.83, + "learning_rate": 2.19861891592841e-06, + "loss": 0.0029, + "step": 51245 + }, + { + "epoch": 15.83, + "learning_rate": 2.198306048057306e-06, + "loss": 0.0041, + "step": 51246 + }, + { + "epoch": 15.83, + "learning_rate": 2.197993199699664e-06, + "loss": 0.0038, + "step": 51247 + }, + { + "epoch": 15.83, + "learning_rate": 2.1976803708562634e-06, + "loss": 0.0037, + "step": 51248 + }, + { + "epoch": 15.83, + "learning_rate": 2.1973675615278856e-06, + "loss": 0.0028, + "step": 51249 + }, + { + "epoch": 15.83, + "learning_rate": 2.1970547717153134e-06, + "loss": 0.0025, + "step": 51250 + }, + { + "epoch": 15.83, + "learning_rate": 2.196742001419334e-06, + "loss": 0.0031, + "step": 51251 + }, + { + "epoch": 15.83, + "learning_rate": 2.1964292506407227e-06, + "loss": 0.0029, + "step": 51252 + }, + { + "epoch": 15.83, + "learning_rate": 2.196116519380269e-06, + "loss": 0.0029, + "step": 51253 + }, + { + "epoch": 15.83, + "learning_rate": 2.19580380763875e-06, + "loss": 0.0029, + "step": 51254 + }, + { + "epoch": 15.83, + "learning_rate": 2.1954911154169465e-06, + "loss": 0.003, + "step": 51255 + }, + { + "epoch": 15.83, + "learning_rate": 2.1951784427156443e-06, + "loss": 0.0037, + "step": 51256 + }, + { + "epoch": 15.83, + "learning_rate": 2.194865789535626e-06, + "loss": 0.0019, + "step": 51257 + }, + { + "epoch": 15.83, + "learning_rate": 2.1945531558776724e-06, + "loss": 0.0031, + "step": 51258 + }, + { + "epoch": 15.83, + "learning_rate": 2.1942405417425617e-06, + "loss": 0.002, + "step": 51259 + }, + { + "epoch": 15.83, + "learning_rate": 2.1939279471310827e-06, + "loss": 0.0025, + "step": 51260 + }, + { + "epoch": 15.83, + "learning_rate": 2.19361537204401e-06, + "loss": 0.0024, + "step": 51261 + }, + { + "epoch": 15.83, + "learning_rate": 2.19330281648213e-06, + "loss": 0.0024, + "step": 51262 + }, + { + "epoch": 15.83, + "learning_rate": 2.1929902804462253e-06, + "loss": 0.003, + "step": 51263 + }, + { + "epoch": 15.83, + "learning_rate": 2.1926777639370765e-06, + "loss": 0.0022, + "step": 51264 + }, + { + "epoch": 15.83, + "learning_rate": 2.192365266955462e-06, + "loss": 0.0024, + "step": 51265 + }, + { + "epoch": 15.83, + "learning_rate": 2.1920527895021646e-06, + "loss": 0.0028, + "step": 51266 + }, + { + "epoch": 15.83, + "learning_rate": 2.1917403315779717e-06, + "loss": 0.0026, + "step": 51267 + }, + { + "epoch": 15.83, + "learning_rate": 2.1914278931836598e-06, + "loss": 0.0032, + "step": 51268 + }, + { + "epoch": 15.83, + "learning_rate": 2.191115474320008e-06, + "loss": 0.0035, + "step": 51269 + }, + { + "epoch": 15.83, + "learning_rate": 2.190803074987803e-06, + "loss": 0.0028, + "step": 51270 + }, + { + "epoch": 15.83, + "learning_rate": 2.1904906951878214e-06, + "loss": 0.0035, + "step": 51271 + }, + { + "epoch": 15.83, + "learning_rate": 2.1901783349208474e-06, + "loss": 0.0027, + "step": 51272 + }, + { + "epoch": 15.83, + "learning_rate": 2.1898659941876645e-06, + "loss": 0.0024, + "step": 51273 + }, + { + "epoch": 15.83, + "learning_rate": 2.1895536729890497e-06, + "loss": 0.0024, + "step": 51274 + }, + { + "epoch": 15.83, + "learning_rate": 2.189241371325784e-06, + "loss": 0.0032, + "step": 51275 + }, + { + "epoch": 15.83, + "learning_rate": 2.1889290891986537e-06, + "loss": 0.0027, + "step": 51276 + }, + { + "epoch": 15.84, + "learning_rate": 2.188616826608433e-06, + "loss": 0.0022, + "step": 51277 + }, + { + "epoch": 15.84, + "learning_rate": 2.188304583555909e-06, + "loss": 0.0032, + "step": 51278 + }, + { + "epoch": 15.84, + "learning_rate": 2.1879923600418607e-06, + "loss": 0.0035, + "step": 51279 + }, + { + "epoch": 15.84, + "learning_rate": 2.1876801560670645e-06, + "loss": 0.0025, + "step": 51280 + }, + { + "epoch": 15.84, + "learning_rate": 2.187367971632306e-06, + "loss": 0.0028, + "step": 51281 + }, + { + "epoch": 15.84, + "learning_rate": 2.1870558067383673e-06, + "loss": 0.0027, + "step": 51282 + }, + { + "epoch": 15.84, + "learning_rate": 2.1867436613860247e-06, + "loss": 0.0024, + "step": 51283 + }, + { + "epoch": 15.84, + "learning_rate": 2.1864315355760634e-06, + "loss": 0.0025, + "step": 51284 + }, + { + "epoch": 15.84, + "learning_rate": 2.1861194293092625e-06, + "loss": 0.0032, + "step": 51285 + }, + { + "epoch": 15.84, + "learning_rate": 2.185807342586399e-06, + "loss": 0.0022, + "step": 51286 + }, + { + "epoch": 15.84, + "learning_rate": 2.185495275408257e-06, + "loss": 0.0028, + "step": 51287 + }, + { + "epoch": 15.84, + "learning_rate": 2.1851832277756193e-06, + "loss": 0.0029, + "step": 51288 + }, + { + "epoch": 15.84, + "learning_rate": 2.1848711996892636e-06, + "loss": 0.0024, + "step": 51289 + }, + { + "epoch": 15.84, + "learning_rate": 2.1845591911499677e-06, + "loss": 0.0033, + "step": 51290 + }, + { + "epoch": 15.84, + "learning_rate": 2.1842472021585172e-06, + "loss": 0.0029, + "step": 51291 + }, + { + "epoch": 15.84, + "learning_rate": 2.1839352327156872e-06, + "loss": 0.0024, + "step": 51292 + }, + { + "epoch": 15.84, + "learning_rate": 2.1836232828222603e-06, + "loss": 0.0035, + "step": 51293 + }, + { + "epoch": 15.84, + "learning_rate": 2.183311352479024e-06, + "loss": 0.0031, + "step": 51294 + }, + { + "epoch": 15.84, + "learning_rate": 2.182999441686745e-06, + "loss": 0.0025, + "step": 51295 + }, + { + "epoch": 15.84, + "learning_rate": 2.182687550446211e-06, + "loss": 0.0032, + "step": 51296 + }, + { + "epoch": 15.84, + "learning_rate": 2.1823756787582005e-06, + "loss": 0.0039, + "step": 51297 + }, + { + "epoch": 15.84, + "learning_rate": 2.1820638266234972e-06, + "loss": 0.0027, + "step": 51298 + }, + { + "epoch": 15.84, + "learning_rate": 2.181751994042878e-06, + "loss": 0.0032, + "step": 51299 + }, + { + "epoch": 15.84, + "learning_rate": 2.1814401810171206e-06, + "loss": 0.0025, + "step": 51300 + }, + { + "epoch": 15.84, + "learning_rate": 2.18112838754701e-06, + "loss": 0.0024, + "step": 51301 + }, + { + "epoch": 15.84, + "learning_rate": 2.180816613633321e-06, + "loss": 0.0024, + "step": 51302 + }, + { + "epoch": 15.84, + "learning_rate": 2.180504859276835e-06, + "loss": 0.0023, + "step": 51303 + }, + { + "epoch": 15.84, + "learning_rate": 2.180193124478338e-06, + "loss": 0.003, + "step": 51304 + }, + { + "epoch": 15.84, + "learning_rate": 2.179881409238599e-06, + "loss": 0.0029, + "step": 51305 + }, + { + "epoch": 15.84, + "learning_rate": 2.179569713558404e-06, + "loss": 0.0027, + "step": 51306 + }, + { + "epoch": 15.84, + "learning_rate": 2.179258037438533e-06, + "loss": 0.0032, + "step": 51307 + }, + { + "epoch": 15.84, + "learning_rate": 2.1789463808797616e-06, + "loss": 0.002, + "step": 51308 + }, + { + "epoch": 15.85, + "learning_rate": 2.178634743882875e-06, + "loss": 0.0031, + "step": 51309 + }, + { + "epoch": 15.85, + "learning_rate": 2.178323126448648e-06, + "loss": 0.0027, + "step": 51310 + }, + { + "epoch": 15.85, + "learning_rate": 2.1780115285778603e-06, + "loss": 0.0031, + "step": 51311 + }, + { + "epoch": 15.85, + "learning_rate": 2.1776999502712915e-06, + "loss": 0.0033, + "step": 51312 + }, + { + "epoch": 15.85, + "learning_rate": 2.1773883915297243e-06, + "loss": 0.0029, + "step": 51313 + }, + { + "epoch": 15.85, + "learning_rate": 2.1770768523539367e-06, + "loss": 0.0027, + "step": 51314 + }, + { + "epoch": 15.85, + "learning_rate": 2.1767653327447034e-06, + "loss": 0.0023, + "step": 51315 + }, + { + "epoch": 15.85, + "learning_rate": 2.1764538327028096e-06, + "loss": 0.0029, + "step": 51316 + }, + { + "epoch": 15.85, + "learning_rate": 2.176142352229028e-06, + "loss": 0.0035, + "step": 51317 + }, + { + "epoch": 15.85, + "learning_rate": 2.1758308913241433e-06, + "loss": 0.0026, + "step": 51318 + }, + { + "epoch": 15.85, + "learning_rate": 2.175519449988934e-06, + "loss": 0.0037, + "step": 51319 + }, + { + "epoch": 15.85, + "learning_rate": 2.1752080282241773e-06, + "loss": 0.0023, + "step": 51320 + }, + { + "epoch": 15.85, + "learning_rate": 2.1748966260306503e-06, + "loss": 0.003, + "step": 51321 + }, + { + "epoch": 15.85, + "learning_rate": 2.1745852434091375e-06, + "loss": 0.0033, + "step": 51322 + }, + { + "epoch": 15.85, + "learning_rate": 2.17427388036041e-06, + "loss": 0.0028, + "step": 51323 + }, + { + "epoch": 15.85, + "learning_rate": 2.1739625368852548e-06, + "loss": 0.0019, + "step": 51324 + }, + { + "epoch": 15.85, + "learning_rate": 2.1736512129844468e-06, + "loss": 0.0025, + "step": 51325 + }, + { + "epoch": 15.85, + "learning_rate": 2.1733399086587616e-06, + "loss": 0.0033, + "step": 51326 + }, + { + "epoch": 15.85, + "learning_rate": 2.1730286239089802e-06, + "loss": 0.0034, + "step": 51327 + }, + { + "epoch": 15.85, + "learning_rate": 2.172717358735884e-06, + "loss": 0.0021, + "step": 51328 + }, + { + "epoch": 15.85, + "learning_rate": 2.1724061131402473e-06, + "loss": 0.0029, + "step": 51329 + }, + { + "epoch": 15.85, + "learning_rate": 2.172094887122854e-06, + "loss": 0.0026, + "step": 51330 + }, + { + "epoch": 15.85, + "learning_rate": 2.171783680684476e-06, + "loss": 0.0028, + "step": 51331 + }, + { + "epoch": 15.85, + "learning_rate": 2.171472493825897e-06, + "loss": 0.0032, + "step": 51332 + }, + { + "epoch": 15.85, + "learning_rate": 2.1711613265478903e-06, + "loss": 0.0024, + "step": 51333 + }, + { + "epoch": 15.85, + "learning_rate": 2.1708501788512403e-06, + "loss": 0.0029, + "step": 51334 + }, + { + "epoch": 15.85, + "learning_rate": 2.170539050736722e-06, + "loss": 0.0037, + "step": 51335 + }, + { + "epoch": 15.85, + "learning_rate": 2.170227942205111e-06, + "loss": 0.0025, + "step": 51336 + }, + { + "epoch": 15.85, + "learning_rate": 2.169916853257187e-06, + "loss": 0.0035, + "step": 51337 + }, + { + "epoch": 15.85, + "learning_rate": 2.1696057838937323e-06, + "loss": 0.0025, + "step": 51338 + }, + { + "epoch": 15.85, + "learning_rate": 2.169294734115519e-06, + "loss": 0.0029, + "step": 51339 + }, + { + "epoch": 15.85, + "learning_rate": 2.168983703923331e-06, + "loss": 0.0046, + "step": 51340 + }, + { + "epoch": 15.86, + "learning_rate": 2.1686726933179423e-06, + "loss": 0.0028, + "step": 51341 + }, + { + "epoch": 15.86, + "learning_rate": 2.1683617023001292e-06, + "loss": 0.0028, + "step": 51342 + }, + { + "epoch": 15.86, + "learning_rate": 2.168050730870672e-06, + "loss": 0.0029, + "step": 51343 + }, + { + "epoch": 15.86, + "learning_rate": 2.1677397790303513e-06, + "loss": 0.0027, + "step": 51344 + }, + { + "epoch": 15.86, + "learning_rate": 2.1674288467799408e-06, + "loss": 0.0029, + "step": 51345 + }, + { + "epoch": 15.86, + "learning_rate": 2.1671179341202177e-06, + "loss": 0.0028, + "step": 51346 + }, + { + "epoch": 15.86, + "learning_rate": 2.1668070410519635e-06, + "loss": 0.0032, + "step": 51347 + }, + { + "epoch": 15.86, + "learning_rate": 2.166496167575951e-06, + "loss": 0.003, + "step": 51348 + }, + { + "epoch": 15.86, + "learning_rate": 2.16618531369296e-06, + "loss": 0.0022, + "step": 51349 + }, + { + "epoch": 15.86, + "learning_rate": 2.165874479403771e-06, + "loss": 0.0033, + "step": 51350 + }, + { + "epoch": 15.86, + "learning_rate": 2.1655636647091593e-06, + "loss": 0.0032, + "step": 51351 + }, + { + "epoch": 15.86, + "learning_rate": 2.1652528696098996e-06, + "loss": 0.0022, + "step": 51352 + }, + { + "epoch": 15.86, + "learning_rate": 2.1649420941067734e-06, + "loss": 0.0025, + "step": 51353 + }, + { + "epoch": 15.86, + "learning_rate": 2.1646313382005536e-06, + "loss": 0.0029, + "step": 51354 + }, + { + "epoch": 15.86, + "learning_rate": 2.1643206018920225e-06, + "loss": 0.003, + "step": 51355 + }, + { + "epoch": 15.86, + "learning_rate": 2.1640098851819547e-06, + "loss": 0.0025, + "step": 51356 + }, + { + "epoch": 15.86, + "learning_rate": 2.1636991880711242e-06, + "loss": 0.0029, + "step": 51357 + }, + { + "epoch": 15.86, + "learning_rate": 2.1633885105603114e-06, + "loss": 0.0028, + "step": 51358 + }, + { + "epoch": 15.86, + "learning_rate": 2.1630778526502962e-06, + "loss": 0.0038, + "step": 51359 + }, + { + "epoch": 15.86, + "learning_rate": 2.16276721434185e-06, + "loss": 0.0035, + "step": 51360 + }, + { + "epoch": 15.86, + "learning_rate": 2.1624565956357557e-06, + "loss": 0.0031, + "step": 51361 + }, + { + "epoch": 15.86, + "learning_rate": 2.1621459965327863e-06, + "loss": 0.0041, + "step": 51362 + }, + { + "epoch": 15.86, + "learning_rate": 2.1618354170337164e-06, + "loss": 0.0027, + "step": 51363 + }, + { + "epoch": 15.86, + "learning_rate": 2.1615248571393253e-06, + "loss": 0.0032, + "step": 51364 + }, + { + "epoch": 15.86, + "learning_rate": 2.161214316850394e-06, + "loss": 0.003, + "step": 51365 + }, + { + "epoch": 15.86, + "learning_rate": 2.160903796167695e-06, + "loss": 0.0027, + "step": 51366 + }, + { + "epoch": 15.86, + "learning_rate": 2.1605932950920026e-06, + "loss": 0.0025, + "step": 51367 + }, + { + "epoch": 15.86, + "learning_rate": 2.160282813624096e-06, + "loss": 0.0081, + "step": 51368 + }, + { + "epoch": 15.86, + "learning_rate": 2.1599723517647554e-06, + "loss": 0.0024, + "step": 51369 + }, + { + "epoch": 15.86, + "learning_rate": 2.159661909514751e-06, + "loss": 0.0026, + "step": 51370 + }, + { + "epoch": 15.86, + "learning_rate": 2.1593514868748643e-06, + "loss": 0.0033, + "step": 51371 + }, + { + "epoch": 15.86, + "learning_rate": 2.1590410838458696e-06, + "loss": 0.0026, + "step": 51372 + }, + { + "epoch": 15.86, + "learning_rate": 2.158730700428541e-06, + "loss": 0.0021, + "step": 51373 + }, + { + "epoch": 15.87, + "learning_rate": 2.158420336623657e-06, + "loss": 0.003, + "step": 51374 + }, + { + "epoch": 15.87, + "learning_rate": 2.158109992431996e-06, + "loss": 0.0034, + "step": 51375 + }, + { + "epoch": 15.87, + "learning_rate": 2.1577996678543323e-06, + "loss": 0.0033, + "step": 51376 + }, + { + "epoch": 15.87, + "learning_rate": 2.1574893628914393e-06, + "loss": 0.0023, + "step": 51377 + }, + { + "epoch": 15.87, + "learning_rate": 2.1571790775440993e-06, + "loss": 0.0025, + "step": 51378 + }, + { + "epoch": 15.87, + "learning_rate": 2.156868811813081e-06, + "loss": 0.0027, + "step": 51379 + }, + { + "epoch": 15.87, + "learning_rate": 2.156558565699165e-06, + "loss": 0.003, + "step": 51380 + }, + { + "epoch": 15.87, + "learning_rate": 2.15624833920313e-06, + "loss": 0.0027, + "step": 51381 + }, + { + "epoch": 15.87, + "learning_rate": 2.155938132325748e-06, + "loss": 0.0038, + "step": 51382 + }, + { + "epoch": 15.87, + "learning_rate": 2.155627945067792e-06, + "loss": 0.0026, + "step": 51383 + }, + { + "epoch": 15.87, + "learning_rate": 2.1553177774300436e-06, + "loss": 0.0028, + "step": 51384 + }, + { + "epoch": 15.87, + "learning_rate": 2.1550076294132747e-06, + "loss": 0.002, + "step": 51385 + }, + { + "epoch": 15.87, + "learning_rate": 2.1546975010182646e-06, + "loss": 0.0028, + "step": 51386 + }, + { + "epoch": 15.87, + "learning_rate": 2.1543873922457883e-06, + "loss": 0.0028, + "step": 51387 + }, + { + "epoch": 15.87, + "learning_rate": 2.1540773030966157e-06, + "loss": 0.0022, + "step": 51388 + }, + { + "epoch": 15.87, + "learning_rate": 2.1537672335715275e-06, + "loss": 0.0026, + "step": 51389 + }, + { + "epoch": 15.87, + "learning_rate": 2.1534571836713003e-06, + "loss": 0.0024, + "step": 51390 + }, + { + "epoch": 15.87, + "learning_rate": 2.1531471533967062e-06, + "loss": 0.0021, + "step": 51391 + }, + { + "epoch": 15.87, + "learning_rate": 2.152837142748525e-06, + "loss": 0.0029, + "step": 51392 + }, + { + "epoch": 15.87, + "learning_rate": 2.152527151727528e-06, + "loss": 0.0032, + "step": 51393 + }, + { + "epoch": 15.87, + "learning_rate": 2.1522171803344903e-06, + "loss": 0.0028, + "step": 51394 + }, + { + "epoch": 15.87, + "learning_rate": 2.151907228570189e-06, + "loss": 0.0035, + "step": 51395 + }, + { + "epoch": 15.87, + "learning_rate": 2.1515972964354014e-06, + "loss": 0.0021, + "step": 51396 + }, + { + "epoch": 15.87, + "learning_rate": 2.1512873839309e-06, + "loss": 0.0038, + "step": 51397 + }, + { + "epoch": 15.87, + "learning_rate": 2.150977491057459e-06, + "loss": 0.0035, + "step": 51398 + }, + { + "epoch": 15.87, + "learning_rate": 2.150667617815854e-06, + "loss": 0.0026, + "step": 51399 + }, + { + "epoch": 15.87, + "learning_rate": 2.150357764206863e-06, + "loss": 0.0033, + "step": 51400 + }, + { + "epoch": 15.87, + "learning_rate": 2.150047930231257e-06, + "loss": 0.0025, + "step": 51401 + }, + { + "epoch": 15.87, + "learning_rate": 2.1497381158898155e-06, + "loss": 0.0018, + "step": 51402 + }, + { + "epoch": 15.87, + "learning_rate": 2.1494283211833113e-06, + "loss": 0.0022, + "step": 51403 + }, + { + "epoch": 15.87, + "learning_rate": 2.149118546112514e-06, + "loss": 0.0032, + "step": 51404 + }, + { + "epoch": 15.87, + "learning_rate": 2.1488087906782053e-06, + "loss": 0.002, + "step": 51405 + }, + { + "epoch": 15.88, + "learning_rate": 2.148499054881159e-06, + "loss": 0.0023, + "step": 51406 + }, + { + "epoch": 15.88, + "learning_rate": 2.14818933872215e-06, + "loss": 0.0037, + "step": 51407 + }, + { + "epoch": 15.88, + "learning_rate": 2.1478796422019478e-06, + "loss": 0.0032, + "step": 51408 + }, + { + "epoch": 15.88, + "learning_rate": 2.1475699653213344e-06, + "loss": 0.0036, + "step": 51409 + }, + { + "epoch": 15.88, + "learning_rate": 2.1472603080810773e-06, + "loss": 0.0021, + "step": 51410 + }, + { + "epoch": 15.88, + "learning_rate": 2.146950670481954e-06, + "loss": 0.0028, + "step": 51411 + }, + { + "epoch": 15.88, + "learning_rate": 2.146641052524745e-06, + "loss": 0.0024, + "step": 51412 + }, + { + "epoch": 15.88, + "learning_rate": 2.146331454210214e-06, + "loss": 0.0026, + "step": 51413 + }, + { + "epoch": 15.88, + "learning_rate": 2.1460218755391404e-06, + "loss": 0.003, + "step": 51414 + }, + { + "epoch": 15.88, + "learning_rate": 2.145712316512302e-06, + "loss": 0.0029, + "step": 51415 + }, + { + "epoch": 15.88, + "learning_rate": 2.1454027771304664e-06, + "loss": 0.0024, + "step": 51416 + }, + { + "epoch": 15.88, + "learning_rate": 2.145093257394413e-06, + "loss": 0.003, + "step": 51417 + }, + { + "epoch": 15.88, + "learning_rate": 2.1447837573049145e-06, + "loss": 0.0024, + "step": 51418 + }, + { + "epoch": 15.88, + "learning_rate": 2.1444742768627423e-06, + "loss": 0.0039, + "step": 51419 + }, + { + "epoch": 15.88, + "learning_rate": 2.1441648160686724e-06, + "loss": 0.0024, + "step": 51420 + }, + { + "epoch": 15.88, + "learning_rate": 2.1438553749234815e-06, + "loss": 0.0033, + "step": 51421 + }, + { + "epoch": 15.88, + "learning_rate": 2.1435459534279414e-06, + "loss": 0.0025, + "step": 51422 + }, + { + "epoch": 15.88, + "learning_rate": 2.1432365515828224e-06, + "loss": 0.0024, + "step": 51423 + }, + { + "epoch": 15.88, + "learning_rate": 2.1429271693889055e-06, + "loss": 0.0041, + "step": 51424 + }, + { + "epoch": 15.88, + "learning_rate": 2.1426178068469584e-06, + "loss": 0.0029, + "step": 51425 + }, + { + "epoch": 15.88, + "learning_rate": 2.1423084639577564e-06, + "loss": 0.0029, + "step": 51426 + }, + { + "epoch": 15.88, + "learning_rate": 2.1419991407220764e-06, + "loss": 0.0021, + "step": 51427 + }, + { + "epoch": 15.88, + "learning_rate": 2.14168983714069e-06, + "loss": 0.0029, + "step": 51428 + }, + { + "epoch": 15.88, + "learning_rate": 2.1413805532143692e-06, + "loss": 0.0022, + "step": 51429 + }, + { + "epoch": 15.88, + "learning_rate": 2.141071288943888e-06, + "loss": 0.0028, + "step": 51430 + }, + { + "epoch": 15.88, + "learning_rate": 2.140762044330024e-06, + "loss": 0.0026, + "step": 51431 + }, + { + "epoch": 15.88, + "learning_rate": 2.1404528193735442e-06, + "loss": 0.0029, + "step": 51432 + }, + { + "epoch": 15.88, + "learning_rate": 2.1401436140752276e-06, + "loss": 0.0029, + "step": 51433 + }, + { + "epoch": 15.88, + "learning_rate": 2.1398344284358465e-06, + "loss": 0.0048, + "step": 51434 + }, + { + "epoch": 15.88, + "learning_rate": 2.1395252624561704e-06, + "loss": 0.0022, + "step": 51435 + }, + { + "epoch": 15.88, + "learning_rate": 2.139216116136974e-06, + "loss": 0.0021, + "step": 51436 + }, + { + "epoch": 15.88, + "learning_rate": 2.138906989479036e-06, + "loss": 0.0028, + "step": 51437 + }, + { + "epoch": 15.88, + "learning_rate": 2.138597882483124e-06, + "loss": 0.0021, + "step": 51438 + }, + { + "epoch": 15.89, + "learning_rate": 2.138288795150011e-06, + "loss": 0.0024, + "step": 51439 + }, + { + "epoch": 15.89, + "learning_rate": 2.1379797274804735e-06, + "loss": 0.0033, + "step": 51440 + }, + { + "epoch": 15.89, + "learning_rate": 2.137670679475281e-06, + "loss": 0.0026, + "step": 51441 + }, + { + "epoch": 15.89, + "learning_rate": 2.1373616511352068e-06, + "loss": 0.0029, + "step": 51442 + }, + { + "epoch": 15.89, + "learning_rate": 2.1370526424610318e-06, + "loss": 0.0026, + "step": 51443 + }, + { + "epoch": 15.89, + "learning_rate": 2.1367436534535168e-06, + "loss": 0.0028, + "step": 51444 + }, + { + "epoch": 15.89, + "learning_rate": 2.1364346841134385e-06, + "loss": 0.0033, + "step": 51445 + }, + { + "epoch": 15.89, + "learning_rate": 2.1361257344415754e-06, + "loss": 0.0032, + "step": 51446 + }, + { + "epoch": 15.89, + "learning_rate": 2.1358168044386927e-06, + "loss": 0.0024, + "step": 51447 + }, + { + "epoch": 15.89, + "learning_rate": 2.1355078941055706e-06, + "loss": 0.0031, + "step": 51448 + }, + { + "epoch": 15.89, + "learning_rate": 2.135199003442976e-06, + "loss": 0.0023, + "step": 51449 + }, + { + "epoch": 15.89, + "learning_rate": 2.1348901324516815e-06, + "loss": 0.003, + "step": 51450 + }, + { + "epoch": 15.89, + "learning_rate": 2.1345812811324607e-06, + "loss": 0.0027, + "step": 51451 + }, + { + "epoch": 15.89, + "learning_rate": 2.13427244948609e-06, + "loss": 0.0023, + "step": 51452 + }, + { + "epoch": 15.89, + "learning_rate": 2.1339636375133375e-06, + "loss": 0.0026, + "step": 51453 + }, + { + "epoch": 15.89, + "learning_rate": 2.1336548452149753e-06, + "loss": 0.0025, + "step": 51454 + }, + { + "epoch": 15.89, + "learning_rate": 2.1333460725917785e-06, + "loss": 0.0025, + "step": 51455 + }, + { + "epoch": 15.89, + "learning_rate": 2.1330373196445155e-06, + "loss": 0.0029, + "step": 51456 + }, + { + "epoch": 15.89, + "learning_rate": 2.132728586373961e-06, + "loss": 0.0032, + "step": 51457 + }, + { + "epoch": 15.89, + "learning_rate": 2.132419872780891e-06, + "loss": 0.0023, + "step": 51458 + }, + { + "epoch": 15.89, + "learning_rate": 2.132111178866073e-06, + "loss": 0.0032, + "step": 51459 + }, + { + "epoch": 15.89, + "learning_rate": 2.131802504630277e-06, + "loss": 0.0027, + "step": 51460 + }, + { + "epoch": 15.89, + "learning_rate": 2.1314938500742778e-06, + "loss": 0.0036, + "step": 51461 + }, + { + "epoch": 15.89, + "learning_rate": 2.131185215198851e-06, + "loss": 0.0025, + "step": 51462 + }, + { + "epoch": 15.89, + "learning_rate": 2.1308766000047654e-06, + "loss": 0.0023, + "step": 51463 + }, + { + "epoch": 15.89, + "learning_rate": 2.130568004492789e-06, + "loss": 0.0033, + "step": 51464 + }, + { + "epoch": 15.89, + "learning_rate": 2.1302594286637002e-06, + "loss": 0.0026, + "step": 51465 + }, + { + "epoch": 15.89, + "learning_rate": 2.129950872518266e-06, + "loss": 0.0026, + "step": 51466 + }, + { + "epoch": 15.89, + "learning_rate": 2.129642336057259e-06, + "loss": 0.003, + "step": 51467 + }, + { + "epoch": 15.89, + "learning_rate": 2.129333819281456e-06, + "loss": 0.0027, + "step": 51468 + }, + { + "epoch": 15.89, + "learning_rate": 2.1290253221916234e-06, + "loss": 0.0025, + "step": 51469 + }, + { + "epoch": 15.89, + "learning_rate": 2.128716844788532e-06, + "loss": 0.0027, + "step": 51470 + }, + { + "epoch": 15.9, + "learning_rate": 2.128408387072959e-06, + "loss": 0.0024, + "step": 51471 + }, + { + "epoch": 15.9, + "learning_rate": 2.128099949045668e-06, + "loss": 0.0033, + "step": 51472 + }, + { + "epoch": 15.9, + "learning_rate": 2.1277915307074383e-06, + "loss": 0.003, + "step": 51473 + }, + { + "epoch": 15.9, + "learning_rate": 2.127483132059037e-06, + "loss": 0.0041, + "step": 51474 + }, + { + "epoch": 15.9, + "learning_rate": 2.1271747531012344e-06, + "loss": 0.0033, + "step": 51475 + }, + { + "epoch": 15.9, + "learning_rate": 2.1268663938348034e-06, + "loss": 0.0026, + "step": 51476 + }, + { + "epoch": 15.9, + "learning_rate": 2.126558054260518e-06, + "loss": 0.0036, + "step": 51477 + }, + { + "epoch": 15.9, + "learning_rate": 2.1262497343791445e-06, + "loss": 0.003, + "step": 51478 + }, + { + "epoch": 15.9, + "learning_rate": 2.1259414341914587e-06, + "loss": 0.0029, + "step": 51479 + }, + { + "epoch": 15.9, + "learning_rate": 2.12563315369823e-06, + "loss": 0.0021, + "step": 51480 + }, + { + "epoch": 15.9, + "learning_rate": 2.125324892900227e-06, + "loss": 0.0033, + "step": 51481 + }, + { + "epoch": 15.9, + "learning_rate": 2.125016651798221e-06, + "loss": 0.0023, + "step": 51482 + }, + { + "epoch": 15.9, + "learning_rate": 2.1247084303929886e-06, + "loss": 0.0025, + "step": 51483 + }, + { + "epoch": 15.9, + "learning_rate": 2.124400228685296e-06, + "loss": 0.0024, + "step": 51484 + }, + { + "epoch": 15.9, + "learning_rate": 2.124092046675913e-06, + "loss": 0.0018, + "step": 51485 + }, + { + "epoch": 15.9, + "learning_rate": 2.1237838843656144e-06, + "loss": 0.0026, + "step": 51486 + }, + { + "epoch": 15.9, + "learning_rate": 2.1234757417551668e-06, + "loss": 0.0029, + "step": 51487 + }, + { + "epoch": 15.9, + "learning_rate": 2.123167618845342e-06, + "loss": 0.003, + "step": 51488 + }, + { + "epoch": 15.9, + "learning_rate": 2.122859515636915e-06, + "loss": 0.003, + "step": 51489 + }, + { + "epoch": 15.9, + "learning_rate": 2.122551432130653e-06, + "loss": 0.0025, + "step": 51490 + }, + { + "epoch": 15.9, + "learning_rate": 2.1222433683273236e-06, + "loss": 0.0026, + "step": 51491 + }, + { + "epoch": 15.9, + "learning_rate": 2.121935324227703e-06, + "loss": 0.0025, + "step": 51492 + }, + { + "epoch": 15.9, + "learning_rate": 2.121627299832556e-06, + "loss": 0.0017, + "step": 51493 + }, + { + "epoch": 15.9, + "learning_rate": 2.12131929514266e-06, + "loss": 0.0029, + "step": 51494 + }, + { + "epoch": 15.9, + "learning_rate": 2.121011310158777e-06, + "loss": 0.0027, + "step": 51495 + }, + { + "epoch": 15.9, + "learning_rate": 2.120703344881686e-06, + "loss": 0.0029, + "step": 51496 + }, + { + "epoch": 15.9, + "learning_rate": 2.1203953993121494e-06, + "loss": 0.0031, + "step": 51497 + }, + { + "epoch": 15.9, + "learning_rate": 2.1200874734509413e-06, + "loss": 0.0028, + "step": 51498 + }, + { + "epoch": 15.9, + "learning_rate": 2.1197795672988355e-06, + "loss": 0.0027, + "step": 51499 + }, + { + "epoch": 15.9, + "learning_rate": 2.1194716808565963e-06, + "loss": 0.0026, + "step": 51500 + }, + { + "epoch": 15.9, + "learning_rate": 2.119163814124994e-06, + "loss": 0.0029, + "step": 51501 + }, + { + "epoch": 15.9, + "learning_rate": 2.1188559671048036e-06, + "loss": 0.0027, + "step": 51502 + }, + { + "epoch": 15.91, + "learning_rate": 2.1185481397967877e-06, + "loss": 0.0028, + "step": 51503 + }, + { + "epoch": 15.91, + "learning_rate": 2.1182403322017244e-06, + "loss": 0.0032, + "step": 51504 + }, + { + "epoch": 15.91, + "learning_rate": 2.117932544320379e-06, + "loss": 0.0036, + "step": 51505 + }, + { + "epoch": 15.91, + "learning_rate": 2.1176247761535196e-06, + "loss": 0.0026, + "step": 51506 + }, + { + "epoch": 15.91, + "learning_rate": 2.1173170277019185e-06, + "loss": 0.005, + "step": 51507 + }, + { + "epoch": 15.91, + "learning_rate": 2.117009298966347e-06, + "loss": 0.0023, + "step": 51508 + }, + { + "epoch": 15.91, + "learning_rate": 2.116701589947571e-06, + "loss": 0.0023, + "step": 51509 + }, + { + "epoch": 15.91, + "learning_rate": 2.116393900646364e-06, + "loss": 0.0033, + "step": 51510 + }, + { + "epoch": 15.91, + "learning_rate": 2.1160862310634945e-06, + "loss": 0.0025, + "step": 51511 + }, + { + "epoch": 15.91, + "learning_rate": 2.115778581199729e-06, + "loss": 0.0029, + "step": 51512 + }, + { + "epoch": 15.91, + "learning_rate": 2.115470951055838e-06, + "loss": 0.0026, + "step": 51513 + }, + { + "epoch": 15.91, + "learning_rate": 2.1151633406325956e-06, + "loss": 0.0032, + "step": 51514 + }, + { + "epoch": 15.91, + "learning_rate": 2.1148557499307687e-06, + "loss": 0.0041, + "step": 51515 + }, + { + "epoch": 15.91, + "learning_rate": 2.1145481789511213e-06, + "loss": 0.003, + "step": 51516 + }, + { + "epoch": 15.91, + "learning_rate": 2.1142406276944303e-06, + "loss": 0.004, + "step": 51517 + }, + { + "epoch": 15.91, + "learning_rate": 2.11393309616146e-06, + "loss": 0.0026, + "step": 51518 + }, + { + "epoch": 15.91, + "learning_rate": 2.1136255843529807e-06, + "loss": 0.0029, + "step": 51519 + }, + { + "epoch": 15.91, + "learning_rate": 2.113318092269765e-06, + "loss": 0.0033, + "step": 51520 + }, + { + "epoch": 15.91, + "learning_rate": 2.113010619912579e-06, + "loss": 0.0033, + "step": 51521 + }, + { + "epoch": 15.91, + "learning_rate": 2.1127031672821897e-06, + "loss": 0.003, + "step": 51522 + }, + { + "epoch": 15.91, + "learning_rate": 2.112395734379371e-06, + "loss": 0.0032, + "step": 51523 + }, + { + "epoch": 15.91, + "learning_rate": 2.1120883212048858e-06, + "loss": 0.0036, + "step": 51524 + }, + { + "epoch": 15.91, + "learning_rate": 2.1117809277595092e-06, + "loss": 0.0032, + "step": 51525 + }, + { + "epoch": 15.91, + "learning_rate": 2.1114735540440055e-06, + "loss": 0.0023, + "step": 51526 + }, + { + "epoch": 15.91, + "learning_rate": 2.111166200059147e-06, + "loss": 0.0031, + "step": 51527 + }, + { + "epoch": 15.91, + "learning_rate": 2.1108588658056983e-06, + "loss": 0.0032, + "step": 51528 + }, + { + "epoch": 15.91, + "learning_rate": 2.1105515512844297e-06, + "loss": 0.0025, + "step": 51529 + }, + { + "epoch": 15.91, + "learning_rate": 2.1102442564961146e-06, + "loss": 0.0029, + "step": 51530 + }, + { + "epoch": 15.91, + "learning_rate": 2.1099369814415173e-06, + "loss": 0.0025, + "step": 51531 + }, + { + "epoch": 15.91, + "learning_rate": 2.109629726121403e-06, + "loss": 0.0027, + "step": 51532 + }, + { + "epoch": 15.91, + "learning_rate": 2.1093224905365474e-06, + "loss": 0.0025, + "step": 51533 + }, + { + "epoch": 15.91, + "learning_rate": 2.1090152746877126e-06, + "loss": 0.0028, + "step": 51534 + }, + { + "epoch": 15.91, + "learning_rate": 2.108708078575672e-06, + "loss": 0.0024, + "step": 51535 + }, + { + "epoch": 15.92, + "learning_rate": 2.1084009022011933e-06, + "loss": 0.0023, + "step": 51536 + }, + { + "epoch": 15.92, + "learning_rate": 2.1080937455650386e-06, + "loss": 0.0032, + "step": 51537 + }, + { + "epoch": 15.92, + "learning_rate": 2.107786608667982e-06, + "loss": 0.0026, + "step": 51538 + }, + { + "epoch": 15.92, + "learning_rate": 2.107479491510793e-06, + "loss": 0.0026, + "step": 51539 + }, + { + "epoch": 15.92, + "learning_rate": 2.1071723940942345e-06, + "loss": 0.0027, + "step": 51540 + }, + { + "epoch": 15.92, + "learning_rate": 2.10686531641908e-06, + "loss": 0.0031, + "step": 51541 + }, + { + "epoch": 15.92, + "learning_rate": 2.1065582584860956e-06, + "loss": 0.0031, + "step": 51542 + }, + { + "epoch": 15.92, + "learning_rate": 2.106251220296045e-06, + "loss": 0.0039, + "step": 51543 + }, + { + "epoch": 15.92, + "learning_rate": 2.1059442018497013e-06, + "loss": 0.0024, + "step": 51544 + }, + { + "epoch": 15.92, + "learning_rate": 2.1056372031478324e-06, + "loss": 0.0041, + "step": 51545 + }, + { + "epoch": 15.92, + "learning_rate": 2.1053302241912045e-06, + "loss": 0.0022, + "step": 51546 + }, + { + "epoch": 15.92, + "learning_rate": 2.1050232649805836e-06, + "loss": 0.0036, + "step": 51547 + }, + { + "epoch": 15.92, + "learning_rate": 2.1047163255167424e-06, + "loss": 0.0032, + "step": 51548 + }, + { + "epoch": 15.92, + "learning_rate": 2.1044094058004417e-06, + "loss": 0.003, + "step": 51549 + }, + { + "epoch": 15.92, + "learning_rate": 2.104102505832454e-06, + "loss": 0.0032, + "step": 51550 + }, + { + "epoch": 15.92, + "learning_rate": 2.1037956256135515e-06, + "loss": 0.0031, + "step": 51551 + }, + { + "epoch": 15.92, + "learning_rate": 2.103488765144491e-06, + "loss": 0.0031, + "step": 51552 + }, + { + "epoch": 15.92, + "learning_rate": 2.1031819244260454e-06, + "loss": 0.0029, + "step": 51553 + }, + { + "epoch": 15.92, + "learning_rate": 2.1028751034589845e-06, + "loss": 0.0028, + "step": 51554 + }, + { + "epoch": 15.92, + "learning_rate": 2.1025683022440713e-06, + "loss": 0.0031, + "step": 51555 + }, + { + "epoch": 15.92, + "learning_rate": 2.102261520782076e-06, + "loss": 0.004, + "step": 51556 + }, + { + "epoch": 15.92, + "learning_rate": 2.1019547590737667e-06, + "loss": 0.0027, + "step": 51557 + }, + { + "epoch": 15.92, + "learning_rate": 2.101648017119906e-06, + "loss": 0.0032, + "step": 51558 + }, + { + "epoch": 15.92, + "learning_rate": 2.101341294921264e-06, + "loss": 0.0033, + "step": 51559 + }, + { + "epoch": 15.92, + "learning_rate": 2.101034592478609e-06, + "loss": 0.0041, + "step": 51560 + }, + { + "epoch": 15.92, + "learning_rate": 2.1007279097927114e-06, + "loss": 0.003, + "step": 51561 + }, + { + "epoch": 15.92, + "learning_rate": 2.1004212468643294e-06, + "loss": 0.0025, + "step": 51562 + }, + { + "epoch": 15.92, + "learning_rate": 2.1001146036942343e-06, + "loss": 0.0031, + "step": 51563 + }, + { + "epoch": 15.92, + "learning_rate": 2.099807980283196e-06, + "loss": 0.0032, + "step": 51564 + }, + { + "epoch": 15.92, + "learning_rate": 2.0995013766319762e-06, + "loss": 0.0024, + "step": 51565 + }, + { + "epoch": 15.92, + "learning_rate": 2.099194792741347e-06, + "loss": 0.0025, + "step": 51566 + }, + { + "epoch": 15.92, + "learning_rate": 2.0988882286120736e-06, + "loss": 0.0037, + "step": 51567 + }, + { + "epoch": 15.93, + "learning_rate": 2.098581684244918e-06, + "loss": 0.0031, + "step": 51568 + }, + { + "epoch": 15.93, + "learning_rate": 2.0982751596406513e-06, + "loss": 0.0024, + "step": 51569 + }, + { + "epoch": 15.93, + "learning_rate": 2.097968654800042e-06, + "loss": 0.003, + "step": 51570 + }, + { + "epoch": 15.93, + "learning_rate": 2.097662169723854e-06, + "loss": 0.0028, + "step": 51571 + }, + { + "epoch": 15.93, + "learning_rate": 2.097355704412852e-06, + "loss": 0.0028, + "step": 51572 + }, + { + "epoch": 15.93, + "learning_rate": 2.0970492588678083e-06, + "loss": 0.0028, + "step": 51573 + }, + { + "epoch": 15.93, + "learning_rate": 2.0967428330894814e-06, + "loss": 0.0038, + "step": 51574 + }, + { + "epoch": 15.93, + "learning_rate": 2.096436427078643e-06, + "loss": 0.0033, + "step": 51575 + }, + { + "epoch": 15.93, + "learning_rate": 2.096130040836062e-06, + "loss": 0.0023, + "step": 51576 + }, + { + "epoch": 15.93, + "learning_rate": 2.0958236743625005e-06, + "loss": 0.0027, + "step": 51577 + }, + { + "epoch": 15.93, + "learning_rate": 2.0955173276587227e-06, + "loss": 0.0028, + "step": 51578 + }, + { + "epoch": 15.93, + "learning_rate": 2.095211000725501e-06, + "loss": 0.0027, + "step": 51579 + }, + { + "epoch": 15.93, + "learning_rate": 2.0949046935635954e-06, + "loss": 0.0059, + "step": 51580 + }, + { + "epoch": 15.93, + "learning_rate": 2.0945984061737766e-06, + "loss": 0.0021, + "step": 51581 + }, + { + "epoch": 15.93, + "learning_rate": 2.0942921385568103e-06, + "loss": 0.0027, + "step": 51582 + }, + { + "epoch": 15.93, + "learning_rate": 2.0939858907134593e-06, + "loss": 0.003, + "step": 51583 + }, + { + "epoch": 15.93, + "learning_rate": 2.09367966264449e-06, + "loss": 0.0024, + "step": 51584 + }, + { + "epoch": 15.93, + "learning_rate": 2.0933734543506735e-06, + "loss": 0.0038, + "step": 51585 + }, + { + "epoch": 15.93, + "learning_rate": 2.093067265832769e-06, + "loss": 0.003, + "step": 51586 + }, + { + "epoch": 15.93, + "learning_rate": 2.092761097091548e-06, + "loss": 0.0023, + "step": 51587 + }, + { + "epoch": 15.93, + "learning_rate": 2.0924549481277744e-06, + "loss": 0.0018, + "step": 51588 + }, + { + "epoch": 15.93, + "learning_rate": 2.09214881894221e-06, + "loss": 0.0028, + "step": 51589 + }, + { + "epoch": 15.93, + "learning_rate": 2.0918427095356232e-06, + "loss": 0.0029, + "step": 51590 + }, + { + "epoch": 15.93, + "learning_rate": 2.091536619908784e-06, + "loss": 0.0027, + "step": 51591 + }, + { + "epoch": 15.93, + "learning_rate": 2.091230550062453e-06, + "loss": 0.003, + "step": 51592 + }, + { + "epoch": 15.93, + "learning_rate": 2.0909244999973942e-06, + "loss": 0.0027, + "step": 51593 + }, + { + "epoch": 15.93, + "learning_rate": 2.090618469714376e-06, + "loss": 0.0024, + "step": 51594 + }, + { + "epoch": 15.93, + "learning_rate": 2.0903124592141665e-06, + "loss": 0.003, + "step": 51595 + }, + { + "epoch": 15.93, + "learning_rate": 2.0900064684975265e-06, + "loss": 0.0025, + "step": 51596 + }, + { + "epoch": 15.93, + "learning_rate": 2.0897004975652247e-06, + "loss": 0.0029, + "step": 51597 + }, + { + "epoch": 15.93, + "learning_rate": 2.0893945464180245e-06, + "loss": 0.0032, + "step": 51598 + }, + { + "epoch": 15.93, + "learning_rate": 2.089088615056688e-06, + "loss": 0.0018, + "step": 51599 + }, + { + "epoch": 15.94, + "learning_rate": 2.0887827034819853e-06, + "loss": 0.0024, + "step": 51600 + }, + { + "epoch": 15.94, + "learning_rate": 2.088476811694682e-06, + "loss": 0.0035, + "step": 51601 + }, + { + "epoch": 15.94, + "learning_rate": 2.0881709396955406e-06, + "loss": 0.0026, + "step": 51602 + }, + { + "epoch": 15.94, + "learning_rate": 2.0878650874853245e-06, + "loss": 0.0036, + "step": 51603 + }, + { + "epoch": 15.94, + "learning_rate": 2.0875592550648038e-06, + "loss": 0.0026, + "step": 51604 + }, + { + "epoch": 15.94, + "learning_rate": 2.0872534424347378e-06, + "loss": 0.0028, + "step": 51605 + }, + { + "epoch": 15.94, + "learning_rate": 2.086947649595894e-06, + "loss": 0.0028, + "step": 51606 + }, + { + "epoch": 15.94, + "learning_rate": 2.086641876549039e-06, + "loss": 0.0029, + "step": 51607 + }, + { + "epoch": 15.94, + "learning_rate": 2.0863361232949374e-06, + "loss": 0.0033, + "step": 51608 + }, + { + "epoch": 15.94, + "learning_rate": 2.0860303898343504e-06, + "loss": 0.0033, + "step": 51609 + }, + { + "epoch": 15.94, + "learning_rate": 2.085724676168046e-06, + "loss": 0.0032, + "step": 51610 + }, + { + "epoch": 15.94, + "learning_rate": 2.085418982296785e-06, + "loss": 0.0023, + "step": 51611 + }, + { + "epoch": 15.94, + "learning_rate": 2.0851133082213383e-06, + "loss": 0.0034, + "step": 51612 + }, + { + "epoch": 15.94, + "learning_rate": 2.0848076539424665e-06, + "loss": 0.0026, + "step": 51613 + }, + { + "epoch": 15.94, + "learning_rate": 2.084502019460931e-06, + "loss": 0.0022, + "step": 51614 + }, + { + "epoch": 15.94, + "learning_rate": 2.084196404777501e-06, + "loss": 0.0023, + "step": 51615 + }, + { + "epoch": 15.94, + "learning_rate": 2.083890809892941e-06, + "loss": 0.0024, + "step": 51616 + }, + { + "epoch": 15.94, + "learning_rate": 2.083585234808012e-06, + "loss": 0.0026, + "step": 51617 + }, + { + "epoch": 15.94, + "learning_rate": 2.083279679523482e-06, + "loss": 0.0029, + "step": 51618 + }, + { + "epoch": 15.94, + "learning_rate": 2.0829741440401142e-06, + "loss": 0.0033, + "step": 51619 + }, + { + "epoch": 15.94, + "learning_rate": 2.0826686283586694e-06, + "loss": 0.0031, + "step": 51620 + }, + { + "epoch": 15.94, + "learning_rate": 2.0823631324799143e-06, + "loss": 0.0025, + "step": 51621 + }, + { + "epoch": 15.94, + "learning_rate": 2.082057656404616e-06, + "loss": 0.0029, + "step": 51622 + }, + { + "epoch": 15.94, + "learning_rate": 2.0817522001335343e-06, + "loss": 0.0031, + "step": 51623 + }, + { + "epoch": 15.94, + "learning_rate": 2.0814467636674327e-06, + "loss": 0.003, + "step": 51624 + }, + { + "epoch": 15.94, + "learning_rate": 2.0811413470070774e-06, + "loss": 0.0038, + "step": 51625 + }, + { + "epoch": 15.94, + "learning_rate": 2.080835950153235e-06, + "loss": 0.0032, + "step": 51626 + }, + { + "epoch": 15.94, + "learning_rate": 2.0805305731066627e-06, + "loss": 0.0025, + "step": 51627 + }, + { + "epoch": 15.94, + "learning_rate": 2.08022521586813e-06, + "loss": 0.0029, + "step": 51628 + }, + { + "epoch": 15.94, + "learning_rate": 2.0799198784384e-06, + "loss": 0.004, + "step": 51629 + }, + { + "epoch": 15.94, + "learning_rate": 2.0796145608182307e-06, + "loss": 0.0032, + "step": 51630 + }, + { + "epoch": 15.94, + "learning_rate": 2.079309263008391e-06, + "loss": 0.0026, + "step": 51631 + }, + { + "epoch": 15.94, + "learning_rate": 2.0790039850096455e-06, + "loss": 0.0023, + "step": 51632 + }, + { + "epoch": 15.95, + "learning_rate": 2.0786987268227565e-06, + "loss": 0.0039, + "step": 51633 + }, + { + "epoch": 15.95, + "learning_rate": 2.0783934884484836e-06, + "loss": 0.0025, + "step": 51634 + }, + { + "epoch": 15.95, + "learning_rate": 2.078088269887596e-06, + "loss": 0.0025, + "step": 51635 + }, + { + "epoch": 15.95, + "learning_rate": 2.077783071140852e-06, + "loss": 0.0026, + "step": 51636 + }, + { + "epoch": 15.95, + "learning_rate": 2.077477892209018e-06, + "loss": 0.0027, + "step": 51637 + }, + { + "epoch": 15.95, + "learning_rate": 2.077172733092858e-06, + "loss": 0.0026, + "step": 51638 + }, + { + "epoch": 15.95, + "learning_rate": 2.076867593793136e-06, + "loss": 0.0026, + "step": 51639 + }, + { + "epoch": 15.95, + "learning_rate": 2.0765624743106093e-06, + "loss": 0.0033, + "step": 51640 + }, + { + "epoch": 15.95, + "learning_rate": 2.076257374646048e-06, + "loss": 0.0032, + "step": 51641 + }, + { + "epoch": 15.95, + "learning_rate": 2.0759522948002086e-06, + "loss": 0.0032, + "step": 51642 + }, + { + "epoch": 15.95, + "learning_rate": 2.075647234773861e-06, + "loss": 0.0031, + "step": 51643 + }, + { + "epoch": 15.95, + "learning_rate": 2.0753421945677656e-06, + "loss": 0.0034, + "step": 51644 + }, + { + "epoch": 15.95, + "learning_rate": 2.0750371741826813e-06, + "loss": 0.0028, + "step": 51645 + }, + { + "epoch": 15.95, + "learning_rate": 2.074732173619375e-06, + "loss": 0.0029, + "step": 51646 + }, + { + "epoch": 15.95, + "learning_rate": 2.074427192878612e-06, + "loss": 0.0034, + "step": 51647 + }, + { + "epoch": 15.95, + "learning_rate": 2.0741222319611487e-06, + "loss": 0.0027, + "step": 51648 + }, + { + "epoch": 15.95, + "learning_rate": 2.0738172908677545e-06, + "loss": 0.0021, + "step": 51649 + }, + { + "epoch": 15.95, + "learning_rate": 2.0735123695991886e-06, + "loss": 0.0025, + "step": 51650 + }, + { + "epoch": 15.95, + "learning_rate": 2.073207468156211e-06, + "loss": 0.003, + "step": 51651 + }, + { + "epoch": 15.95, + "learning_rate": 2.072902586539588e-06, + "loss": 0.0025, + "step": 51652 + }, + { + "epoch": 15.95, + "learning_rate": 2.072597724750083e-06, + "loss": 0.0032, + "step": 51653 + }, + { + "epoch": 15.95, + "learning_rate": 2.072292882788458e-06, + "loss": 0.0038, + "step": 51654 + }, + { + "epoch": 15.95, + "learning_rate": 2.071988060655471e-06, + "loss": 0.0033, + "step": 51655 + }, + { + "epoch": 15.95, + "learning_rate": 2.071683258351891e-06, + "loss": 0.0034, + "step": 51656 + }, + { + "epoch": 15.95, + "learning_rate": 2.071378475878475e-06, + "loss": 0.003, + "step": 51657 + }, + { + "epoch": 15.95, + "learning_rate": 2.071073713235987e-06, + "loss": 0.0035, + "step": 51658 + }, + { + "epoch": 15.95, + "learning_rate": 2.070768970425192e-06, + "loss": 0.0027, + "step": 51659 + }, + { + "epoch": 15.95, + "learning_rate": 2.0704642474468505e-06, + "loss": 0.0033, + "step": 51660 + }, + { + "epoch": 15.95, + "learning_rate": 2.070159544301722e-06, + "loss": 0.0028, + "step": 51661 + }, + { + "epoch": 15.95, + "learning_rate": 2.06985486099057e-06, + "loss": 0.0028, + "step": 51662 + }, + { + "epoch": 15.95, + "learning_rate": 2.0695501975141597e-06, + "loss": 0.0036, + "step": 51663 + }, + { + "epoch": 15.95, + "learning_rate": 2.0692455538732516e-06, + "loss": 0.0027, + "step": 51664 + }, + { + "epoch": 15.96, + "learning_rate": 2.0689409300686036e-06, + "loss": 0.0035, + "step": 51665 + }, + { + "epoch": 15.96, + "learning_rate": 2.0686363261009844e-06, + "loss": 0.0023, + "step": 51666 + }, + { + "epoch": 15.96, + "learning_rate": 2.068331741971149e-06, + "loss": 0.0037, + "step": 51667 + }, + { + "epoch": 15.96, + "learning_rate": 2.0680271776798623e-06, + "loss": 0.002, + "step": 51668 + }, + { + "epoch": 15.96, + "learning_rate": 2.067722633227892e-06, + "loss": 0.0029, + "step": 51669 + }, + { + "epoch": 15.96, + "learning_rate": 2.0674181086159894e-06, + "loss": 0.0024, + "step": 51670 + }, + { + "epoch": 15.96, + "learning_rate": 2.06711360384492e-06, + "loss": 0.0023, + "step": 51671 + }, + { + "epoch": 15.96, + "learning_rate": 2.066809118915449e-06, + "loss": 0.0028, + "step": 51672 + }, + { + "epoch": 15.96, + "learning_rate": 2.066504653828334e-06, + "loss": 0.0032, + "step": 51673 + }, + { + "epoch": 15.96, + "learning_rate": 2.066200208584339e-06, + "loss": 0.0026, + "step": 51674 + }, + { + "epoch": 15.96, + "learning_rate": 2.065895783184225e-06, + "loss": 0.0036, + "step": 51675 + }, + { + "epoch": 15.96, + "learning_rate": 2.0655913776287506e-06, + "loss": 0.0028, + "step": 51676 + }, + { + "epoch": 15.96, + "learning_rate": 2.065286991918678e-06, + "loss": 0.0032, + "step": 51677 + }, + { + "epoch": 15.96, + "learning_rate": 2.0649826260547734e-06, + "loss": 0.0035, + "step": 51678 + }, + { + "epoch": 15.96, + "learning_rate": 2.064678280037794e-06, + "loss": 0.0029, + "step": 51679 + }, + { + "epoch": 15.96, + "learning_rate": 2.0643739538684992e-06, + "loss": 0.0035, + "step": 51680 + }, + { + "epoch": 15.96, + "learning_rate": 2.064069647547655e-06, + "loss": 0.0029, + "step": 51681 + }, + { + "epoch": 15.96, + "learning_rate": 2.063765361076018e-06, + "loss": 0.0027, + "step": 51682 + }, + { + "epoch": 15.96, + "learning_rate": 2.063461094454351e-06, + "loss": 0.0029, + "step": 51683 + }, + { + "epoch": 15.96, + "learning_rate": 2.0631568476834174e-06, + "loss": 0.0026, + "step": 51684 + }, + { + "epoch": 15.96, + "learning_rate": 2.0628526207639765e-06, + "loss": 0.0044, + "step": 51685 + }, + { + "epoch": 15.96, + "learning_rate": 2.0625484136967866e-06, + "loss": 0.0031, + "step": 51686 + }, + { + "epoch": 15.96, + "learning_rate": 2.0622442264826127e-06, + "loss": 0.0039, + "step": 51687 + }, + { + "epoch": 15.96, + "learning_rate": 2.0619400591222115e-06, + "loss": 0.0027, + "step": 51688 + }, + { + "epoch": 15.96, + "learning_rate": 2.0616359116163463e-06, + "loss": 0.0033, + "step": 51689 + }, + { + "epoch": 15.96, + "learning_rate": 2.0613317839657796e-06, + "loss": 0.0027, + "step": 51690 + }, + { + "epoch": 15.96, + "learning_rate": 2.06102767617127e-06, + "loss": 0.0022, + "step": 51691 + }, + { + "epoch": 15.96, + "learning_rate": 2.060723588233576e-06, + "loss": 0.0021, + "step": 51692 + }, + { + "epoch": 15.96, + "learning_rate": 2.0604195201534606e-06, + "loss": 0.0018, + "step": 51693 + }, + { + "epoch": 15.96, + "learning_rate": 2.060115471931686e-06, + "loss": 0.0028, + "step": 51694 + }, + { + "epoch": 15.96, + "learning_rate": 2.0598114435690108e-06, + "loss": 0.0024, + "step": 51695 + }, + { + "epoch": 15.96, + "learning_rate": 2.059507435066194e-06, + "loss": 0.0029, + "step": 51696 + }, + { + "epoch": 15.96, + "learning_rate": 2.0592034464239986e-06, + "loss": 0.0027, + "step": 51697 + }, + { + "epoch": 15.97, + "learning_rate": 2.0588994776431813e-06, + "loss": 0.0026, + "step": 51698 + }, + { + "epoch": 15.97, + "learning_rate": 2.058595528724504e-06, + "loss": 0.0031, + "step": 51699 + }, + { + "epoch": 15.97, + "learning_rate": 2.0582915996687346e-06, + "loss": 0.0035, + "step": 51700 + }, + { + "epoch": 15.97, + "learning_rate": 2.0579876904766204e-06, + "loss": 0.0029, + "step": 51701 + }, + { + "epoch": 15.97, + "learning_rate": 2.0576838011489277e-06, + "loss": 0.0031, + "step": 51702 + }, + { + "epoch": 15.97, + "learning_rate": 2.0573799316864183e-06, + "loss": 0.0026, + "step": 51703 + }, + { + "epoch": 15.97, + "learning_rate": 2.057076082089848e-06, + "loss": 0.0028, + "step": 51704 + }, + { + "epoch": 15.97, + "learning_rate": 2.056772252359982e-06, + "loss": 0.0028, + "step": 51705 + }, + { + "epoch": 15.97, + "learning_rate": 2.056468442497578e-06, + "loss": 0.0029, + "step": 51706 + }, + { + "epoch": 15.97, + "learning_rate": 2.0561646525033917e-06, + "loss": 0.0028, + "step": 51707 + }, + { + "epoch": 15.97, + "learning_rate": 2.0558608823781865e-06, + "loss": 0.0023, + "step": 51708 + }, + { + "epoch": 15.97, + "learning_rate": 2.055557132122725e-06, + "loss": 0.0031, + "step": 51709 + }, + { + "epoch": 15.97, + "learning_rate": 2.0552534017377647e-06, + "loss": 0.002, + "step": 51710 + }, + { + "epoch": 15.97, + "learning_rate": 2.054949691224061e-06, + "loss": 0.0024, + "step": 51711 + }, + { + "epoch": 15.97, + "learning_rate": 2.054646000582381e-06, + "loss": 0.0035, + "step": 51712 + }, + { + "epoch": 15.97, + "learning_rate": 2.054342329813477e-06, + "loss": 0.0026, + "step": 51713 + }, + { + "epoch": 15.97, + "learning_rate": 2.054038678918112e-06, + "loss": 0.004, + "step": 51714 + }, + { + "epoch": 15.97, + "learning_rate": 2.0537350478970474e-06, + "loss": 0.0031, + "step": 51715 + }, + { + "epoch": 15.97, + "learning_rate": 2.0534314367510423e-06, + "loss": 0.0031, + "step": 51716 + }, + { + "epoch": 15.97, + "learning_rate": 2.0531278454808513e-06, + "loss": 0.0042, + "step": 51717 + }, + { + "epoch": 15.97, + "learning_rate": 2.0528242740872396e-06, + "loss": 0.0035, + "step": 51718 + }, + { + "epoch": 15.97, + "learning_rate": 2.052520722570961e-06, + "loss": 0.0029, + "step": 51719 + }, + { + "epoch": 15.97, + "learning_rate": 2.0522171909327805e-06, + "loss": 0.0026, + "step": 51720 + }, + { + "epoch": 15.97, + "learning_rate": 2.051913679173455e-06, + "loss": 0.0021, + "step": 51721 + }, + { + "epoch": 15.97, + "learning_rate": 2.051610187293739e-06, + "loss": 0.0024, + "step": 51722 + }, + { + "epoch": 15.97, + "learning_rate": 2.0513067152943965e-06, + "loss": 0.0045, + "step": 51723 + }, + { + "epoch": 15.97, + "learning_rate": 2.0510032631761854e-06, + "loss": 0.002, + "step": 51724 + }, + { + "epoch": 15.97, + "learning_rate": 2.0506998309398675e-06, + "loss": 0.0041, + "step": 51725 + }, + { + "epoch": 15.97, + "learning_rate": 2.0503964185862004e-06, + "loss": 0.0039, + "step": 51726 + }, + { + "epoch": 15.97, + "learning_rate": 2.050093026115938e-06, + "loss": 0.0031, + "step": 51727 + }, + { + "epoch": 15.97, + "learning_rate": 2.0497896535298457e-06, + "loss": 0.0032, + "step": 51728 + }, + { + "epoch": 15.97, + "learning_rate": 2.049486300828676e-06, + "loss": 0.0028, + "step": 51729 + }, + { + "epoch": 15.98, + "learning_rate": 2.049182968013195e-06, + "loss": 0.0023, + "step": 51730 + }, + { + "epoch": 15.98, + "learning_rate": 2.0488796550841574e-06, + "loss": 0.0027, + "step": 51731 + }, + { + "epoch": 15.98, + "learning_rate": 2.0485763620423192e-06, + "loss": 0.0025, + "step": 51732 + }, + { + "epoch": 15.98, + "learning_rate": 2.0482730888884416e-06, + "loss": 0.0031, + "step": 51733 + }, + { + "epoch": 15.98, + "learning_rate": 2.047969835623286e-06, + "loss": 0.0026, + "step": 51734 + }, + { + "epoch": 15.98, + "learning_rate": 2.0476666022476056e-06, + "loss": 0.004, + "step": 51735 + }, + { + "epoch": 15.98, + "learning_rate": 2.0473633887621635e-06, + "loss": 0.0029, + "step": 51736 + }, + { + "epoch": 15.98, + "learning_rate": 2.047060195167717e-06, + "loss": 0.0023, + "step": 51737 + }, + { + "epoch": 15.98, + "learning_rate": 2.04675702146502e-06, + "loss": 0.0034, + "step": 51738 + }, + { + "epoch": 15.98, + "learning_rate": 2.046453867654835e-06, + "loss": 0.0035, + "step": 51739 + }, + { + "epoch": 15.98, + "learning_rate": 2.0461507337379214e-06, + "loss": 0.0028, + "step": 51740 + }, + { + "epoch": 15.98, + "learning_rate": 2.045847619715037e-06, + "loss": 0.0023, + "step": 51741 + }, + { + "epoch": 15.98, + "learning_rate": 2.0455445255869343e-06, + "loss": 0.0028, + "step": 51742 + }, + { + "epoch": 15.98, + "learning_rate": 2.0452414513543783e-06, + "loss": 0.0034, + "step": 51743 + }, + { + "epoch": 15.98, + "learning_rate": 2.0449383970181226e-06, + "loss": 0.0033, + "step": 51744 + }, + { + "epoch": 15.98, + "learning_rate": 2.0446353625789263e-06, + "loss": 0.0028, + "step": 51745 + }, + { + "epoch": 15.98, + "learning_rate": 2.04433234803755e-06, + "loss": 0.0022, + "step": 51746 + }, + { + "epoch": 15.98, + "learning_rate": 2.04402935339475e-06, + "loss": 0.0026, + "step": 51747 + }, + { + "epoch": 15.98, + "learning_rate": 2.0437263786512817e-06, + "loss": 0.0029, + "step": 51748 + }, + { + "epoch": 15.98, + "learning_rate": 2.0434234238079065e-06, + "loss": 0.0031, + "step": 51749 + }, + { + "epoch": 15.98, + "learning_rate": 2.0431204888653777e-06, + "loss": 0.0034, + "step": 51750 + }, + { + "epoch": 15.98, + "learning_rate": 2.0428175738244594e-06, + "loss": 0.0045, + "step": 51751 + }, + { + "epoch": 15.98, + "learning_rate": 2.0425146786859053e-06, + "loss": 0.0032, + "step": 51752 + }, + { + "epoch": 15.98, + "learning_rate": 2.042211803450471e-06, + "loss": 0.0025, + "step": 51753 + }, + { + "epoch": 15.98, + "learning_rate": 2.041908948118916e-06, + "loss": 0.0023, + "step": 51754 + }, + { + "epoch": 15.98, + "learning_rate": 2.041606112691998e-06, + "loss": 0.0028, + "step": 51755 + }, + { + "epoch": 15.98, + "learning_rate": 2.041303297170477e-06, + "loss": 0.0038, + "step": 51756 + }, + { + "epoch": 15.98, + "learning_rate": 2.0410005015551094e-06, + "loss": 0.0031, + "step": 51757 + }, + { + "epoch": 15.98, + "learning_rate": 2.0406977258466475e-06, + "loss": 0.0025, + "step": 51758 + }, + { + "epoch": 15.98, + "learning_rate": 2.0403949700458547e-06, + "loss": 0.0032, + "step": 51759 + }, + { + "epoch": 15.98, + "learning_rate": 2.0400922341534834e-06, + "loss": 0.0036, + "step": 51760 + }, + { + "epoch": 15.98, + "learning_rate": 2.0397895181702966e-06, + "loss": 0.0026, + "step": 51761 + }, + { + "epoch": 15.99, + "learning_rate": 2.0394868220970475e-06, + "loss": 0.003, + "step": 51762 + }, + { + "epoch": 15.99, + "learning_rate": 2.0391841459344907e-06, + "loss": 0.003, + "step": 51763 + }, + { + "epoch": 15.99, + "learning_rate": 2.0388814896833863e-06, + "loss": 0.0026, + "step": 51764 + }, + { + "epoch": 15.99, + "learning_rate": 2.038578853344495e-06, + "loss": 0.0026, + "step": 51765 + }, + { + "epoch": 15.99, + "learning_rate": 2.0382762369185672e-06, + "loss": 0.0028, + "step": 51766 + }, + { + "epoch": 15.99, + "learning_rate": 2.0379736404063644e-06, + "loss": 0.0023, + "step": 51767 + }, + { + "epoch": 15.99, + "learning_rate": 2.0376710638086426e-06, + "loss": 0.003, + "step": 51768 + }, + { + "epoch": 15.99, + "learning_rate": 2.037368507126154e-06, + "loss": 0.0029, + "step": 51769 + }, + { + "epoch": 15.99, + "learning_rate": 2.0370659703596595e-06, + "loss": 0.0021, + "step": 51770 + }, + { + "epoch": 15.99, + "learning_rate": 2.036763453509919e-06, + "loss": 0.0031, + "step": 51771 + }, + { + "epoch": 15.99, + "learning_rate": 2.036460956577685e-06, + "loss": 0.0029, + "step": 51772 + }, + { + "epoch": 15.99, + "learning_rate": 2.0361584795637114e-06, + "loss": 0.0034, + "step": 51773 + }, + { + "epoch": 15.99, + "learning_rate": 2.0358560224687605e-06, + "loss": 0.0031, + "step": 51774 + }, + { + "epoch": 15.99, + "learning_rate": 2.0355535852935847e-06, + "loss": 0.0027, + "step": 51775 + }, + { + "epoch": 15.99, + "learning_rate": 2.0352511680389408e-06, + "loss": 0.0022, + "step": 51776 + }, + { + "epoch": 15.99, + "learning_rate": 2.0349487707055893e-06, + "loss": 0.0028, + "step": 51777 + }, + { + "epoch": 15.99, + "learning_rate": 2.034646393294284e-06, + "loss": 0.0026, + "step": 51778 + }, + { + "epoch": 15.99, + "learning_rate": 2.0343440358057785e-06, + "loss": 0.0031, + "step": 51779 + }, + { + "epoch": 15.99, + "learning_rate": 2.034041698240834e-06, + "loss": 0.0033, + "step": 51780 + }, + { + "epoch": 15.99, + "learning_rate": 2.0337393806002006e-06, + "loss": 0.0031, + "step": 51781 + }, + { + "epoch": 15.99, + "learning_rate": 2.0334370828846416e-06, + "loss": 0.0039, + "step": 51782 + }, + { + "epoch": 15.99, + "learning_rate": 2.0331348050949084e-06, + "loss": 0.0022, + "step": 51783 + }, + { + "epoch": 15.99, + "learning_rate": 2.0328325472317565e-06, + "loss": 0.0021, + "step": 51784 + }, + { + "epoch": 15.99, + "learning_rate": 2.0325303092959437e-06, + "loss": 0.0029, + "step": 51785 + }, + { + "epoch": 15.99, + "learning_rate": 2.0322280912882277e-06, + "loss": 0.0018, + "step": 51786 + }, + { + "epoch": 15.99, + "learning_rate": 2.03192589320936e-06, + "loss": 0.0021, + "step": 51787 + }, + { + "epoch": 15.99, + "learning_rate": 2.0316237150601015e-06, + "loss": 0.0025, + "step": 51788 + }, + { + "epoch": 15.99, + "learning_rate": 2.0313215568412026e-06, + "loss": 0.0028, + "step": 51789 + }, + { + "epoch": 15.99, + "learning_rate": 2.0310194185534247e-06, + "loss": 0.0033, + "step": 51790 + }, + { + "epoch": 15.99, + "learning_rate": 2.030717300197518e-06, + "loss": 0.003, + "step": 51791 + }, + { + "epoch": 15.99, + "learning_rate": 2.030415201774244e-06, + "loss": 0.0029, + "step": 51792 + }, + { + "epoch": 15.99, + "learning_rate": 2.030113123284354e-06, + "loss": 0.0028, + "step": 51793 + }, + { + "epoch": 15.99, + "learning_rate": 2.029811064728603e-06, + "loss": 0.0034, + "step": 51794 + }, + { + "epoch": 16.0, + "learning_rate": 2.0295090261077487e-06, + "loss": 0.0025, + "step": 51795 + }, + { + "epoch": 16.0, + "learning_rate": 2.029207007422548e-06, + "loss": 0.0022, + "step": 51796 + }, + { + "epoch": 16.0, + "learning_rate": 2.0289050086737517e-06, + "loss": 0.0035, + "step": 51797 + }, + { + "epoch": 16.0, + "learning_rate": 2.0286030298621197e-06, + "loss": 0.0029, + "step": 51798 + }, + { + "epoch": 16.0, + "learning_rate": 2.0283010709884065e-06, + "loss": 0.0027, + "step": 51799 + }, + { + "epoch": 16.0, + "learning_rate": 2.027999132053363e-06, + "loss": 0.0028, + "step": 51800 + }, + { + "epoch": 16.0, + "learning_rate": 2.0276972130577486e-06, + "loss": 0.0024, + "step": 51801 + }, + { + "epoch": 16.0, + "learning_rate": 2.0273953140023196e-06, + "loss": 0.0028, + "step": 51802 + }, + { + "epoch": 16.0, + "learning_rate": 2.027093434887829e-06, + "loss": 0.0029, + "step": 51803 + }, + { + "epoch": 16.0, + "learning_rate": 2.026791575715029e-06, + "loss": 0.0029, + "step": 51804 + }, + { + "epoch": 16.0, + "learning_rate": 2.0264897364846803e-06, + "loss": 0.0029, + "step": 51805 + }, + { + "epoch": 16.0, + "learning_rate": 2.0261879171975318e-06, + "loss": 0.0027, + "step": 51806 + }, + { + "epoch": 16.0, + "learning_rate": 2.025886117854343e-06, + "loss": 0.0021, + "step": 51807 + }, + { + "epoch": 16.0, + "learning_rate": 2.0255843384558717e-06, + "loss": 0.003, + "step": 51808 + }, + { + "epoch": 16.0, + "learning_rate": 2.025282579002864e-06, + "loss": 0.0027, + "step": 51809 + }, + { + "epoch": 16.0, + "learning_rate": 2.024980839496078e-06, + "loss": 0.0033, + "step": 51810 + }, + { + "epoch": 16.0, + "learning_rate": 2.0246791199362726e-06, + "loss": 0.0019, + "step": 51811 + }, + { + "epoch": 16.0, + "learning_rate": 2.024377420324197e-06, + "loss": 0.0023, + "step": 51812 + }, + { + "epoch": 16.0, + "learning_rate": 2.0240757406606102e-06, + "loss": 0.0017, + "step": 51813 + }, + { + "epoch": 16.0, + "learning_rate": 2.0237740809462646e-06, + "loss": 0.0022, + "step": 51814 + }, + { + "epoch": 16.0, + "learning_rate": 2.0234724411819127e-06, + "loss": 0.0017, + "step": 51815 + }, + { + "epoch": 16.0, + "learning_rate": 2.023170821368311e-06, + "loss": 0.002, + "step": 51816 + }, + { + "epoch": 16.0, + "learning_rate": 2.0228692215062163e-06, + "loss": 0.002, + "step": 51817 + }, + { + "epoch": 16.0, + "learning_rate": 2.0225676415963812e-06, + "loss": 0.0024, + "step": 51818 + }, + { + "epoch": 16.0, + "learning_rate": 2.022266081639556e-06, + "loss": 0.0023, + "step": 51819 + }, + { + "epoch": 16.0, + "learning_rate": 2.021964541636502e-06, + "loss": 0.0018, + "step": 51820 + }, + { + "epoch": 16.0, + "learning_rate": 2.0216630215879663e-06, + "loss": 0.004, + "step": 51821 + }, + { + "epoch": 16.0, + "learning_rate": 2.021361521494707e-06, + "loss": 0.0021, + "step": 51822 + }, + { + "epoch": 16.0, + "learning_rate": 2.02106004135748e-06, + "loss": 0.0018, + "step": 51823 + }, + { + "epoch": 16.0, + "learning_rate": 2.020758581177037e-06, + "loss": 0.002, + "step": 51824 + }, + { + "epoch": 16.0, + "learning_rate": 2.0204571409541296e-06, + "loss": 0.0023, + "step": 51825 + }, + { + "epoch": 16.0, + "learning_rate": 2.020155720689514e-06, + "loss": 0.002, + "step": 51826 + }, + { + "epoch": 16.01, + "learning_rate": 2.0198543203839484e-06, + "loss": 0.0017, + "step": 51827 + }, + { + "epoch": 16.01, + "learning_rate": 2.019552940038181e-06, + "loss": 0.0017, + "step": 51828 + }, + { + "epoch": 16.01, + "learning_rate": 2.0192515796529655e-06, + "loss": 0.0015, + "step": 51829 + }, + { + "epoch": 16.01, + "learning_rate": 2.0189502392290594e-06, + "loss": 0.0017, + "step": 51830 + }, + { + "epoch": 16.01, + "learning_rate": 2.018648918767212e-06, + "loss": 0.0022, + "step": 51831 + }, + { + "epoch": 16.01, + "learning_rate": 2.0183476182681795e-06, + "loss": 0.0021, + "step": 51832 + }, + { + "epoch": 16.01, + "learning_rate": 2.0180463377327185e-06, + "loss": 0.0017, + "step": 51833 + }, + { + "epoch": 16.01, + "learning_rate": 2.0177450771615793e-06, + "loss": 0.0021, + "step": 51834 + }, + { + "epoch": 16.01, + "learning_rate": 2.0174438365555115e-06, + "loss": 0.0016, + "step": 51835 + }, + { + "epoch": 16.01, + "learning_rate": 2.0171426159152774e-06, + "loss": 0.0026, + "step": 51836 + }, + { + "epoch": 16.01, + "learning_rate": 2.0168414152416215e-06, + "loss": 0.0019, + "step": 51837 + }, + { + "epoch": 16.01, + "learning_rate": 2.0165402345353034e-06, + "loss": 0.002, + "step": 51838 + }, + { + "epoch": 16.01, + "learning_rate": 2.0162390737970762e-06, + "loss": 0.0018, + "step": 51839 + }, + { + "epoch": 16.01, + "learning_rate": 2.0159379330276873e-06, + "loss": 0.0024, + "step": 51840 + }, + { + "epoch": 16.01, + "learning_rate": 2.0156368122278937e-06, + "loss": 0.0016, + "step": 51841 + }, + { + "epoch": 16.01, + "learning_rate": 2.0153357113984515e-06, + "loss": 0.002, + "step": 51842 + }, + { + "epoch": 16.01, + "learning_rate": 2.015034630540109e-06, + "loss": 0.0024, + "step": 51843 + }, + { + "epoch": 16.01, + "learning_rate": 2.0147335696536228e-06, + "loss": 0.0019, + "step": 51844 + }, + { + "epoch": 16.01, + "learning_rate": 2.0144325287397448e-06, + "loss": 0.0018, + "step": 51845 + }, + { + "epoch": 16.01, + "learning_rate": 2.014131507799225e-06, + "loss": 0.0016, + "step": 51846 + }, + { + "epoch": 16.01, + "learning_rate": 2.013830506832819e-06, + "loss": 0.0021, + "step": 51847 + }, + { + "epoch": 16.01, + "learning_rate": 2.013529525841282e-06, + "loss": 0.0021, + "step": 51848 + }, + { + "epoch": 16.01, + "learning_rate": 2.0132285648253645e-06, + "loss": 0.0025, + "step": 51849 + }, + { + "epoch": 16.01, + "learning_rate": 2.0129276237858164e-06, + "loss": 0.002, + "step": 51850 + }, + { + "epoch": 16.01, + "learning_rate": 2.012626702723396e-06, + "loss": 0.0014, + "step": 51851 + }, + { + "epoch": 16.01, + "learning_rate": 2.0123258016388493e-06, + "loss": 0.002, + "step": 51852 + }, + { + "epoch": 16.01, + "learning_rate": 2.0120249205329334e-06, + "loss": 0.0014, + "step": 51853 + }, + { + "epoch": 16.01, + "learning_rate": 2.0117240594064025e-06, + "loss": 0.0017, + "step": 51854 + }, + { + "epoch": 16.01, + "learning_rate": 2.011423218260007e-06, + "loss": 0.0015, + "step": 51855 + }, + { + "epoch": 16.01, + "learning_rate": 2.0111223970944958e-06, + "loss": 0.0021, + "step": 51856 + }, + { + "epoch": 16.01, + "learning_rate": 2.0108215959106248e-06, + "loss": 0.0021, + "step": 51857 + }, + { + "epoch": 16.01, + "learning_rate": 2.010520814709149e-06, + "loss": 0.0029, + "step": 51858 + }, + { + "epoch": 16.01, + "learning_rate": 2.010220053490818e-06, + "loss": 0.0016, + "step": 51859 + }, + { + "epoch": 16.02, + "learning_rate": 2.009919312256381e-06, + "loss": 0.0012, + "step": 51860 + }, + { + "epoch": 16.02, + "learning_rate": 2.009618591006596e-06, + "loss": 0.0018, + "step": 51861 + }, + { + "epoch": 16.02, + "learning_rate": 2.0093178897422083e-06, + "loss": 0.002, + "step": 51862 + }, + { + "epoch": 16.02, + "learning_rate": 2.0090172084639758e-06, + "loss": 0.0019, + "step": 51863 + }, + { + "epoch": 16.02, + "learning_rate": 2.00871654717265e-06, + "loss": 0.0021, + "step": 51864 + }, + { + "epoch": 16.02, + "learning_rate": 2.0084159058689822e-06, + "loss": 0.0016, + "step": 51865 + }, + { + "epoch": 16.02, + "learning_rate": 2.008115284553721e-06, + "loss": 0.002, + "step": 51866 + }, + { + "epoch": 16.02, + "learning_rate": 2.0078146832276245e-06, + "loss": 0.0022, + "step": 51867 + }, + { + "epoch": 16.02, + "learning_rate": 2.007514101891438e-06, + "loss": 0.0015, + "step": 51868 + }, + { + "epoch": 16.02, + "learning_rate": 2.007213540545919e-06, + "loss": 0.0022, + "step": 51869 + }, + { + "epoch": 16.02, + "learning_rate": 2.006912999191817e-06, + "loss": 0.0015, + "step": 51870 + }, + { + "epoch": 16.02, + "learning_rate": 2.00661247782988e-06, + "loss": 0.002, + "step": 51871 + }, + { + "epoch": 16.02, + "learning_rate": 2.0063119764608643e-06, + "loss": 0.0022, + "step": 51872 + }, + { + "epoch": 16.02, + "learning_rate": 2.0060114950855213e-06, + "loss": 0.0024, + "step": 51873 + }, + { + "epoch": 16.02, + "learning_rate": 2.0057110337046004e-06, + "loss": 0.0017, + "step": 51874 + }, + { + "epoch": 16.02, + "learning_rate": 2.005410592318856e-06, + "loss": 0.0017, + "step": 51875 + }, + { + "epoch": 16.02, + "learning_rate": 2.0051101709290388e-06, + "loss": 0.0024, + "step": 51876 + }, + { + "epoch": 16.02, + "learning_rate": 2.0048097695358957e-06, + "loss": 0.0018, + "step": 51877 + }, + { + "epoch": 16.02, + "learning_rate": 2.004509388140182e-06, + "loss": 0.0024, + "step": 51878 + }, + { + "epoch": 16.02, + "learning_rate": 2.0042090267426515e-06, + "loss": 0.002, + "step": 51879 + }, + { + "epoch": 16.02, + "learning_rate": 2.0039086853440526e-06, + "loss": 0.002, + "step": 51880 + }, + { + "epoch": 16.02, + "learning_rate": 2.003608363945133e-06, + "loss": 0.0026, + "step": 51881 + }, + { + "epoch": 16.02, + "learning_rate": 2.0033080625466507e-06, + "loss": 0.0026, + "step": 51882 + }, + { + "epoch": 16.02, + "learning_rate": 2.003007781149351e-06, + "loss": 0.0021, + "step": 51883 + }, + { + "epoch": 16.02, + "learning_rate": 2.002707519753987e-06, + "loss": 0.0014, + "step": 51884 + }, + { + "epoch": 16.02, + "learning_rate": 2.0024072783613125e-06, + "loss": 0.0017, + "step": 51885 + }, + { + "epoch": 16.02, + "learning_rate": 2.002107056972076e-06, + "loss": 0.0015, + "step": 51886 + }, + { + "epoch": 16.02, + "learning_rate": 2.001806855587026e-06, + "loss": 0.0021, + "step": 51887 + }, + { + "epoch": 16.02, + "learning_rate": 2.0015066742069167e-06, + "loss": 0.002, + "step": 51888 + }, + { + "epoch": 16.02, + "learning_rate": 2.0012065128325e-06, + "loss": 0.0017, + "step": 51889 + }, + { + "epoch": 16.02, + "learning_rate": 2.000906371464524e-06, + "loss": 0.0024, + "step": 51890 + }, + { + "epoch": 16.02, + "learning_rate": 2.000606250103738e-06, + "loss": 0.0013, + "step": 51891 + }, + { + "epoch": 16.03, + "learning_rate": 2.000306148750898e-06, + "loss": 0.0025, + "step": 51892 + }, + { + "epoch": 16.03, + "learning_rate": 2.0000060674067478e-06, + "loss": 0.0028, + "step": 51893 + }, + { + "epoch": 16.03, + "learning_rate": 1.999706006072042e-06, + "loss": 0.0018, + "step": 51894 + }, + { + "epoch": 16.03, + "learning_rate": 1.999405964747534e-06, + "loss": 0.0025, + "step": 51895 + }, + { + "epoch": 16.03, + "learning_rate": 1.99910594343397e-06, + "loss": 0.0021, + "step": 51896 + }, + { + "epoch": 16.03, + "learning_rate": 1.998805942132098e-06, + "loss": 0.0018, + "step": 51897 + }, + { + "epoch": 16.03, + "learning_rate": 1.998505960842676e-06, + "loss": 0.0016, + "step": 51898 + }, + { + "epoch": 16.03, + "learning_rate": 1.998205999566446e-06, + "loss": 0.0023, + "step": 51899 + }, + { + "epoch": 16.03, + "learning_rate": 1.9979060583041654e-06, + "loss": 0.0021, + "step": 51900 + }, + { + "epoch": 16.03, + "learning_rate": 1.9976061370565812e-06, + "loss": 0.0018, + "step": 51901 + }, + { + "epoch": 16.03, + "learning_rate": 1.997306235824441e-06, + "loss": 0.0023, + "step": 51902 + }, + { + "epoch": 16.03, + "learning_rate": 1.997006354608497e-06, + "loss": 0.0015, + "step": 51903 + }, + { + "epoch": 16.03, + "learning_rate": 1.9967064934095036e-06, + "loss": 0.0014, + "step": 51904 + }, + { + "epoch": 16.03, + "learning_rate": 1.9964066522282034e-06, + "loss": 0.0027, + "step": 51905 + }, + { + "epoch": 16.03, + "learning_rate": 1.996106831065353e-06, + "loss": 0.002, + "step": 51906 + }, + { + "epoch": 16.03, + "learning_rate": 1.9958070299216993e-06, + "loss": 0.0016, + "step": 51907 + }, + { + "epoch": 16.03, + "learning_rate": 1.9955072487979887e-06, + "loss": 0.0022, + "step": 51908 + }, + { + "epoch": 16.03, + "learning_rate": 1.9952074876949746e-06, + "loss": 0.0018, + "step": 51909 + }, + { + "epoch": 16.03, + "learning_rate": 1.994907746613409e-06, + "loss": 0.0022, + "step": 51910 + }, + { + "epoch": 16.03, + "learning_rate": 1.99460802555404e-06, + "loss": 0.0026, + "step": 51911 + }, + { + "epoch": 16.03, + "learning_rate": 1.994308324517613e-06, + "loss": 0.002, + "step": 51912 + }, + { + "epoch": 16.03, + "learning_rate": 1.9940086435048846e-06, + "loss": 0.0017, + "step": 51913 + }, + { + "epoch": 16.03, + "learning_rate": 1.993708982516598e-06, + "loss": 0.0019, + "step": 51914 + }, + { + "epoch": 16.03, + "learning_rate": 1.993409341553505e-06, + "loss": 0.0022, + "step": 51915 + }, + { + "epoch": 16.03, + "learning_rate": 1.9931097206163606e-06, + "loss": 0.0019, + "step": 51916 + }, + { + "epoch": 16.03, + "learning_rate": 1.9928101197059047e-06, + "loss": 0.0017, + "step": 51917 + }, + { + "epoch": 16.03, + "learning_rate": 1.9925105388228903e-06, + "loss": 0.0025, + "step": 51918 + }, + { + "epoch": 16.03, + "learning_rate": 1.9922109779680677e-06, + "loss": 0.0017, + "step": 51919 + }, + { + "epoch": 16.03, + "learning_rate": 1.9919114371421887e-06, + "loss": 0.0017, + "step": 51920 + }, + { + "epoch": 16.03, + "learning_rate": 1.991611916346e-06, + "loss": 0.0019, + "step": 51921 + }, + { + "epoch": 16.03, + "learning_rate": 1.9913124155802478e-06, + "loss": 0.0021, + "step": 51922 + }, + { + "epoch": 16.03, + "learning_rate": 1.9910129348456864e-06, + "loss": 0.0014, + "step": 51923 + }, + { + "epoch": 16.04, + "learning_rate": 1.99071347414306e-06, + "loss": 0.0018, + "step": 51924 + }, + { + "epoch": 16.04, + "learning_rate": 1.990414033473119e-06, + "loss": 0.0021, + "step": 51925 + }, + { + "epoch": 16.04, + "learning_rate": 1.99011461283662e-06, + "loss": 0.0019, + "step": 51926 + }, + { + "epoch": 16.04, + "learning_rate": 1.9898152122342996e-06, + "loss": 0.0019, + "step": 51927 + }, + { + "epoch": 16.04, + "learning_rate": 1.9895158316669115e-06, + "loss": 0.0016, + "step": 51928 + }, + { + "epoch": 16.04, + "learning_rate": 1.989216471135209e-06, + "loss": 0.002, + "step": 51929 + }, + { + "epoch": 16.04, + "learning_rate": 1.9889171306399345e-06, + "loss": 0.0022, + "step": 51930 + }, + { + "epoch": 16.04, + "learning_rate": 1.9886178101818422e-06, + "loss": 0.0016, + "step": 51931 + }, + { + "epoch": 16.04, + "learning_rate": 1.9883185097616776e-06, + "loss": 0.0024, + "step": 51932 + }, + { + "epoch": 16.04, + "learning_rate": 1.9880192293801857e-06, + "loss": 0.0019, + "step": 51933 + }, + { + "epoch": 16.04, + "learning_rate": 1.987719969038121e-06, + "loss": 0.0024, + "step": 51934 + }, + { + "epoch": 16.04, + "learning_rate": 1.9874207287362313e-06, + "loss": 0.0022, + "step": 51935 + }, + { + "epoch": 16.04, + "learning_rate": 1.9871215084752648e-06, + "loss": 0.0021, + "step": 51936 + }, + { + "epoch": 16.04, + "learning_rate": 1.9868223082559655e-06, + "loss": 0.0014, + "step": 51937 + }, + { + "epoch": 16.04, + "learning_rate": 1.9865231280790875e-06, + "loss": 0.0017, + "step": 51938 + }, + { + "epoch": 16.04, + "learning_rate": 1.9862239679453755e-06, + "loss": 0.0015, + "step": 51939 + }, + { + "epoch": 16.04, + "learning_rate": 1.9859248278555777e-06, + "loss": 0.0018, + "step": 51940 + }, + { + "epoch": 16.04, + "learning_rate": 1.985625707810447e-06, + "loss": 0.0015, + "step": 51941 + }, + { + "epoch": 16.04, + "learning_rate": 1.985326607810727e-06, + "loss": 0.0018, + "step": 51942 + }, + { + "epoch": 16.04, + "learning_rate": 1.9850275278571652e-06, + "loss": 0.002, + "step": 51943 + }, + { + "epoch": 16.04, + "learning_rate": 1.984728467950514e-06, + "loss": 0.0019, + "step": 51944 + }, + { + "epoch": 16.04, + "learning_rate": 1.9844294280915156e-06, + "loss": 0.0015, + "step": 51945 + }, + { + "epoch": 16.04, + "learning_rate": 1.9841304082809244e-06, + "loss": 0.0018, + "step": 51946 + }, + { + "epoch": 16.04, + "learning_rate": 1.9838314085194844e-06, + "loss": 0.0019, + "step": 51947 + }, + { + "epoch": 16.04, + "learning_rate": 1.9835324288079416e-06, + "loss": 0.002, + "step": 51948 + }, + { + "epoch": 16.04, + "learning_rate": 1.9832334691470467e-06, + "loss": 0.0023, + "step": 51949 + }, + { + "epoch": 16.04, + "learning_rate": 1.9829345295375503e-06, + "loss": 0.0023, + "step": 51950 + }, + { + "epoch": 16.04, + "learning_rate": 1.9826356099801935e-06, + "loss": 0.0018, + "step": 51951 + }, + { + "epoch": 16.04, + "learning_rate": 1.9823367104757297e-06, + "loss": 0.0023, + "step": 51952 + }, + { + "epoch": 16.04, + "learning_rate": 1.9820378310249023e-06, + "loss": 0.0021, + "step": 51953 + }, + { + "epoch": 16.04, + "learning_rate": 1.981738971628462e-06, + "loss": 0.002, + "step": 51954 + }, + { + "epoch": 16.04, + "learning_rate": 1.9814401322871536e-06, + "loss": 0.0028, + "step": 51955 + }, + { + "epoch": 16.04, + "learning_rate": 1.981141313001725e-06, + "loss": 0.0019, + "step": 51956 + }, + { + "epoch": 16.05, + "learning_rate": 1.9808425137729304e-06, + "loss": 0.0018, + "step": 51957 + }, + { + "epoch": 16.05, + "learning_rate": 1.9805437346015056e-06, + "loss": 0.0013, + "step": 51958 + }, + { + "epoch": 16.05, + "learning_rate": 1.9802449754882034e-06, + "loss": 0.0023, + "step": 51959 + }, + { + "epoch": 16.05, + "learning_rate": 1.979946236433775e-06, + "loss": 0.0025, + "step": 51960 + }, + { + "epoch": 16.05, + "learning_rate": 1.979647517438961e-06, + "loss": 0.0015, + "step": 51961 + }, + { + "epoch": 16.05, + "learning_rate": 1.979348818504513e-06, + "loss": 0.0015, + "step": 51962 + }, + { + "epoch": 16.05, + "learning_rate": 1.9790501396311767e-06, + "loss": 0.0016, + "step": 51963 + }, + { + "epoch": 16.05, + "learning_rate": 1.978751480819696e-06, + "loss": 0.0031, + "step": 51964 + }, + { + "epoch": 16.05, + "learning_rate": 1.9784528420708217e-06, + "loss": 0.0016, + "step": 51965 + }, + { + "epoch": 16.05, + "learning_rate": 1.978154223385302e-06, + "loss": 0.0022, + "step": 51966 + }, + { + "epoch": 16.05, + "learning_rate": 1.9778556247638824e-06, + "loss": 0.0019, + "step": 51967 + }, + { + "epoch": 16.05, + "learning_rate": 1.9775570462073056e-06, + "loss": 0.0018, + "step": 51968 + }, + { + "epoch": 16.05, + "learning_rate": 1.9772584877163247e-06, + "loss": 0.0024, + "step": 51969 + }, + { + "epoch": 16.05, + "learning_rate": 1.9769599492916815e-06, + "loss": 0.0026, + "step": 51970 + }, + { + "epoch": 16.05, + "learning_rate": 1.9766614309341237e-06, + "loss": 0.0015, + "step": 51971 + }, + { + "epoch": 16.05, + "learning_rate": 1.9763629326444024e-06, + "loss": 0.0024, + "step": 51972 + }, + { + "epoch": 16.05, + "learning_rate": 1.976064454423261e-06, + "loss": 0.0021, + "step": 51973 + }, + { + "epoch": 16.05, + "learning_rate": 1.9757659962714424e-06, + "loss": 0.0019, + "step": 51974 + }, + { + "epoch": 16.05, + "learning_rate": 1.9754675581896996e-06, + "loss": 0.0024, + "step": 51975 + }, + { + "epoch": 16.05, + "learning_rate": 1.9751691401787744e-06, + "loss": 0.0021, + "step": 51976 + }, + { + "epoch": 16.05, + "learning_rate": 1.9748707422394154e-06, + "loss": 0.0017, + "step": 51977 + }, + { + "epoch": 16.05, + "learning_rate": 1.9745723643723703e-06, + "loss": 0.0013, + "step": 51978 + }, + { + "epoch": 16.05, + "learning_rate": 1.9742740065783793e-06, + "loss": 0.0014, + "step": 51979 + }, + { + "epoch": 16.05, + "learning_rate": 1.9739756688581934e-06, + "loss": 0.0024, + "step": 51980 + }, + { + "epoch": 16.05, + "learning_rate": 1.9736773512125616e-06, + "loss": 0.0016, + "step": 51981 + }, + { + "epoch": 16.05, + "learning_rate": 1.9733790536422235e-06, + "loss": 0.0017, + "step": 51982 + }, + { + "epoch": 16.05, + "learning_rate": 1.973080776147931e-06, + "loss": 0.0019, + "step": 51983 + }, + { + "epoch": 16.05, + "learning_rate": 1.972782518730424e-06, + "loss": 0.0016, + "step": 51984 + }, + { + "epoch": 16.05, + "learning_rate": 1.9724842813904553e-06, + "loss": 0.0027, + "step": 51985 + }, + { + "epoch": 16.05, + "learning_rate": 1.972186064128765e-06, + "loss": 0.0016, + "step": 51986 + }, + { + "epoch": 16.05, + "learning_rate": 1.971887866946105e-06, + "loss": 0.0014, + "step": 51987 + }, + { + "epoch": 16.05, + "learning_rate": 1.9715896898432163e-06, + "loss": 0.001, + "step": 51988 + }, + { + "epoch": 16.06, + "learning_rate": 1.971291532820844e-06, + "loss": 0.0017, + "step": 51989 + }, + { + "epoch": 16.06, + "learning_rate": 1.9709933958797358e-06, + "loss": 0.0019, + "step": 51990 + }, + { + "epoch": 16.06, + "learning_rate": 1.97069527902064e-06, + "loss": 0.0022, + "step": 51991 + }, + { + "epoch": 16.06, + "learning_rate": 1.970397182244298e-06, + "loss": 0.0018, + "step": 51992 + }, + { + "epoch": 16.06, + "learning_rate": 1.9700991055514583e-06, + "loss": 0.002, + "step": 51993 + }, + { + "epoch": 16.06, + "learning_rate": 1.9698010489428664e-06, + "loss": 0.0019, + "step": 51994 + }, + { + "epoch": 16.06, + "learning_rate": 1.969503012419264e-06, + "loss": 0.0015, + "step": 51995 + }, + { + "epoch": 16.06, + "learning_rate": 1.9692049959813996e-06, + "loss": 0.0019, + "step": 51996 + }, + { + "epoch": 16.06, + "learning_rate": 1.96890699963002e-06, + "loss": 0.0023, + "step": 51997 + }, + { + "epoch": 16.06, + "learning_rate": 1.9686090233658694e-06, + "loss": 0.0018, + "step": 51998 + }, + { + "epoch": 16.06, + "learning_rate": 1.9683110671896887e-06, + "loss": 0.0019, + "step": 51999 + }, + { + "epoch": 16.06, + "learning_rate": 1.968013131102231e-06, + "loss": 0.0026, + "step": 52000 + }, + { + "epoch": 16.06, + "learning_rate": 1.9677152151042347e-06, + "loss": 0.002, + "step": 52001 + }, + { + "epoch": 16.06, + "learning_rate": 1.9674173191964463e-06, + "loss": 0.0019, + "step": 52002 + }, + { + "epoch": 16.06, + "learning_rate": 1.9671194433796157e-06, + "loss": 0.0017, + "step": 52003 + }, + { + "epoch": 16.06, + "learning_rate": 1.966821587654485e-06, + "loss": 0.002, + "step": 52004 + }, + { + "epoch": 16.06, + "learning_rate": 1.966523752021795e-06, + "loss": 0.0018, + "step": 52005 + }, + { + "epoch": 16.06, + "learning_rate": 1.9662259364822976e-06, + "loss": 0.0017, + "step": 52006 + }, + { + "epoch": 16.06, + "learning_rate": 1.9659281410367316e-06, + "loss": 0.0019, + "step": 52007 + }, + { + "epoch": 16.06, + "learning_rate": 1.9656303656858466e-06, + "loss": 0.0019, + "step": 52008 + }, + { + "epoch": 16.06, + "learning_rate": 1.965332610430386e-06, + "loss": 0.0017, + "step": 52009 + }, + { + "epoch": 16.06, + "learning_rate": 1.9650348752710923e-06, + "loss": 0.0029, + "step": 52010 + }, + { + "epoch": 16.06, + "learning_rate": 1.9647371602087107e-06, + "loss": 0.0015, + "step": 52011 + }, + { + "epoch": 16.06, + "learning_rate": 1.96443946524399e-06, + "loss": 0.0019, + "step": 52012 + }, + { + "epoch": 16.06, + "learning_rate": 1.9641417903776693e-06, + "loss": 0.0021, + "step": 52013 + }, + { + "epoch": 16.06, + "learning_rate": 1.9638441356104976e-06, + "loss": 0.002, + "step": 52014 + }, + { + "epoch": 16.06, + "learning_rate": 1.9635465009432174e-06, + "loss": 0.0021, + "step": 52015 + }, + { + "epoch": 16.06, + "learning_rate": 1.963248886376572e-06, + "loss": 0.0019, + "step": 52016 + }, + { + "epoch": 16.06, + "learning_rate": 1.962951291911306e-06, + "loss": 0.0022, + "step": 52017 + }, + { + "epoch": 16.06, + "learning_rate": 1.9626537175481663e-06, + "loss": 0.0022, + "step": 52018 + }, + { + "epoch": 16.06, + "learning_rate": 1.9623561632878976e-06, + "loss": 0.0022, + "step": 52019 + }, + { + "epoch": 16.06, + "learning_rate": 1.9620586291312384e-06, + "loss": 0.0022, + "step": 52020 + }, + { + "epoch": 16.07, + "learning_rate": 1.9617611150789364e-06, + "loss": 0.0018, + "step": 52021 + }, + { + "epoch": 16.07, + "learning_rate": 1.9614636211317384e-06, + "loss": 0.0019, + "step": 52022 + }, + { + "epoch": 16.07, + "learning_rate": 1.961166147290384e-06, + "loss": 0.0015, + "step": 52023 + }, + { + "epoch": 16.07, + "learning_rate": 1.960868693555621e-06, + "loss": 0.0017, + "step": 52024 + }, + { + "epoch": 16.07, + "learning_rate": 1.960571259928192e-06, + "loss": 0.003, + "step": 52025 + }, + { + "epoch": 16.07, + "learning_rate": 1.960273846408839e-06, + "loss": 0.0029, + "step": 52026 + }, + { + "epoch": 16.07, + "learning_rate": 1.9599764529983067e-06, + "loss": 0.0023, + "step": 52027 + }, + { + "epoch": 16.07, + "learning_rate": 1.959679079697342e-06, + "loss": 0.002, + "step": 52028 + }, + { + "epoch": 16.07, + "learning_rate": 1.9593817265066873e-06, + "loss": 0.002, + "step": 52029 + }, + { + "epoch": 16.07, + "learning_rate": 1.959084393427082e-06, + "loss": 0.0023, + "step": 52030 + }, + { + "epoch": 16.07, + "learning_rate": 1.9587870804592756e-06, + "loss": 0.003, + "step": 52031 + }, + { + "epoch": 16.07, + "learning_rate": 1.9584897876040076e-06, + "loss": 0.0022, + "step": 52032 + }, + { + "epoch": 16.07, + "learning_rate": 1.9581925148620228e-06, + "loss": 0.0015, + "step": 52033 + }, + { + "epoch": 16.07, + "learning_rate": 1.9578952622340685e-06, + "loss": 0.0015, + "step": 52034 + }, + { + "epoch": 16.07, + "learning_rate": 1.957598029720884e-06, + "loss": 0.0015, + "step": 52035 + }, + { + "epoch": 16.07, + "learning_rate": 1.957300817323211e-06, + "loss": 0.0016, + "step": 52036 + }, + { + "epoch": 16.07, + "learning_rate": 1.957003625041799e-06, + "loss": 0.002, + "step": 52037 + }, + { + "epoch": 16.07, + "learning_rate": 1.956706452877385e-06, + "loss": 0.0022, + "step": 52038 + }, + { + "epoch": 16.07, + "learning_rate": 1.9564093008307173e-06, + "loss": 0.0018, + "step": 52039 + }, + { + "epoch": 16.07, + "learning_rate": 1.9561121689025376e-06, + "loss": 0.002, + "step": 52040 + }, + { + "epoch": 16.07, + "learning_rate": 1.955815057093585e-06, + "loss": 0.0023, + "step": 52041 + }, + { + "epoch": 16.07, + "learning_rate": 1.9555179654046073e-06, + "loss": 0.0019, + "step": 52042 + }, + { + "epoch": 16.07, + "learning_rate": 1.9552208938363483e-06, + "loss": 0.0019, + "step": 52043 + }, + { + "epoch": 16.07, + "learning_rate": 1.9549238423895466e-06, + "loss": 0.0027, + "step": 52044 + }, + { + "epoch": 16.07, + "learning_rate": 1.9546268110649503e-06, + "loss": 0.0019, + "step": 52045 + }, + { + "epoch": 16.07, + "learning_rate": 1.9543297998633005e-06, + "loss": 0.0015, + "step": 52046 + }, + { + "epoch": 16.07, + "learning_rate": 1.9540328087853353e-06, + "loss": 0.0014, + "step": 52047 + }, + { + "epoch": 16.07, + "learning_rate": 1.9537358378318028e-06, + "loss": 0.0018, + "step": 52048 + }, + { + "epoch": 16.07, + "learning_rate": 1.953438887003446e-06, + "loss": 0.0021, + "step": 52049 + }, + { + "epoch": 16.07, + "learning_rate": 1.953141956301007e-06, + "loss": 0.0021, + "step": 52050 + }, + { + "epoch": 16.07, + "learning_rate": 1.9528450457252245e-06, + "loss": 0.0021, + "step": 52051 + }, + { + "epoch": 16.07, + "learning_rate": 1.9525481552768445e-06, + "loss": 0.0015, + "step": 52052 + }, + { + "epoch": 16.07, + "learning_rate": 1.952251284956612e-06, + "loss": 0.0014, + "step": 52053 + }, + { + "epoch": 16.08, + "learning_rate": 1.951954434765264e-06, + "loss": 0.0016, + "step": 52054 + }, + { + "epoch": 16.08, + "learning_rate": 1.9516576047035484e-06, + "loss": 0.0021, + "step": 52055 + }, + { + "epoch": 16.08, + "learning_rate": 1.9513607947722056e-06, + "loss": 0.0019, + "step": 52056 + }, + { + "epoch": 16.08, + "learning_rate": 1.9510640049719742e-06, + "loss": 0.0016, + "step": 52057 + }, + { + "epoch": 16.08, + "learning_rate": 1.9507672353036e-06, + "loss": 0.0014, + "step": 52058 + }, + { + "epoch": 16.08, + "learning_rate": 1.950470485767828e-06, + "loss": 0.0019, + "step": 52059 + }, + { + "epoch": 16.08, + "learning_rate": 1.950173756365398e-06, + "loss": 0.002, + "step": 52060 + }, + { + "epoch": 16.08, + "learning_rate": 1.9498770470970476e-06, + "loss": 0.0022, + "step": 52061 + }, + { + "epoch": 16.08, + "learning_rate": 1.9495803579635264e-06, + "loss": 0.002, + "step": 52062 + }, + { + "epoch": 16.08, + "learning_rate": 1.94928368896557e-06, + "loss": 0.0021, + "step": 52063 + }, + { + "epoch": 16.08, + "learning_rate": 1.9489870401039236e-06, + "loss": 0.0015, + "step": 52064 + }, + { + "epoch": 16.08, + "learning_rate": 1.9486904113793337e-06, + "loss": 0.0019, + "step": 52065 + }, + { + "epoch": 16.08, + "learning_rate": 1.948393802792533e-06, + "loss": 0.0021, + "step": 52066 + }, + { + "epoch": 16.08, + "learning_rate": 1.948097214344268e-06, + "loss": 0.0017, + "step": 52067 + }, + { + "epoch": 16.08, + "learning_rate": 1.9478006460352825e-06, + "loss": 0.0031, + "step": 52068 + }, + { + "epoch": 16.08, + "learning_rate": 1.947504097866314e-06, + "loss": 0.0022, + "step": 52069 + }, + { + "epoch": 16.08, + "learning_rate": 1.9472075698381086e-06, + "loss": 0.0019, + "step": 52070 + }, + { + "epoch": 16.08, + "learning_rate": 1.9469110619514066e-06, + "loss": 0.0025, + "step": 52071 + }, + { + "epoch": 16.08, + "learning_rate": 1.9466145742069452e-06, + "loss": 0.0023, + "step": 52072 + }, + { + "epoch": 16.08, + "learning_rate": 1.9463181066054703e-06, + "loss": 0.0016, + "step": 52073 + }, + { + "epoch": 16.08, + "learning_rate": 1.9460216591477255e-06, + "loss": 0.0021, + "step": 52074 + }, + { + "epoch": 16.08, + "learning_rate": 1.94572523183445e-06, + "loss": 0.0032, + "step": 52075 + }, + { + "epoch": 16.08, + "learning_rate": 1.945428824666381e-06, + "loss": 0.0018, + "step": 52076 + }, + { + "epoch": 16.08, + "learning_rate": 1.945132437644266e-06, + "loss": 0.0022, + "step": 52077 + }, + { + "epoch": 16.08, + "learning_rate": 1.944836070768842e-06, + "loss": 0.0014, + "step": 52078 + }, + { + "epoch": 16.08, + "learning_rate": 1.9445397240408514e-06, + "loss": 0.002, + "step": 52079 + }, + { + "epoch": 16.08, + "learning_rate": 1.9442433974610398e-06, + "loss": 0.0021, + "step": 52080 + }, + { + "epoch": 16.08, + "learning_rate": 1.9439470910301438e-06, + "loss": 0.0023, + "step": 52081 + }, + { + "epoch": 16.08, + "learning_rate": 1.9436508047489033e-06, + "loss": 0.002, + "step": 52082 + }, + { + "epoch": 16.08, + "learning_rate": 1.943354538618062e-06, + "loss": 0.0016, + "step": 52083 + }, + { + "epoch": 16.08, + "learning_rate": 1.943058292638362e-06, + "loss": 0.002, + "step": 52084 + }, + { + "epoch": 16.08, + "learning_rate": 1.942762066810544e-06, + "loss": 0.0014, + "step": 52085 + }, + { + "epoch": 16.09, + "learning_rate": 1.942465861135344e-06, + "loss": 0.0025, + "step": 52086 + }, + { + "epoch": 16.09, + "learning_rate": 1.94216967561351e-06, + "loss": 0.0032, + "step": 52087 + }, + { + "epoch": 16.09, + "learning_rate": 1.9418735102457753e-06, + "loss": 0.0015, + "step": 52088 + }, + { + "epoch": 16.09, + "learning_rate": 1.941577365032886e-06, + "loss": 0.0024, + "step": 52089 + }, + { + "epoch": 16.09, + "learning_rate": 1.941281239975583e-06, + "loss": 0.0021, + "step": 52090 + }, + { + "epoch": 16.09, + "learning_rate": 1.9409851350746068e-06, + "loss": 0.0023, + "step": 52091 + }, + { + "epoch": 16.09, + "learning_rate": 1.940689050330693e-06, + "loss": 0.0015, + "step": 52092 + }, + { + "epoch": 16.09, + "learning_rate": 1.940392985744588e-06, + "loss": 0.0024, + "step": 52093 + }, + { + "epoch": 16.09, + "learning_rate": 1.940096941317028e-06, + "loss": 0.0022, + "step": 52094 + }, + { + "epoch": 16.09, + "learning_rate": 1.9398009170487585e-06, + "loss": 0.0022, + "step": 52095 + }, + { + "epoch": 16.09, + "learning_rate": 1.9395049129405173e-06, + "loss": 0.002, + "step": 52096 + }, + { + "epoch": 16.09, + "learning_rate": 1.9392089289930417e-06, + "loss": 0.0017, + "step": 52097 + }, + { + "epoch": 16.09, + "learning_rate": 1.938912965207074e-06, + "loss": 0.002, + "step": 52098 + }, + { + "epoch": 16.09, + "learning_rate": 1.9386170215833577e-06, + "loss": 0.0032, + "step": 52099 + }, + { + "epoch": 16.09, + "learning_rate": 1.9383210981226286e-06, + "loss": 0.0016, + "step": 52100 + }, + { + "epoch": 16.09, + "learning_rate": 1.9380251948256314e-06, + "loss": 0.002, + "step": 52101 + }, + { + "epoch": 16.09, + "learning_rate": 1.937729311693104e-06, + "loss": 0.0015, + "step": 52102 + }, + { + "epoch": 16.09, + "learning_rate": 1.937433448725783e-06, + "loss": 0.0021, + "step": 52103 + }, + { + "epoch": 16.09, + "learning_rate": 1.9371376059244107e-06, + "loss": 0.0035, + "step": 52104 + }, + { + "epoch": 16.09, + "learning_rate": 1.9368417832897313e-06, + "loss": 0.0024, + "step": 52105 + }, + { + "epoch": 16.09, + "learning_rate": 1.9365459808224808e-06, + "loss": 0.0023, + "step": 52106 + }, + { + "epoch": 16.09, + "learning_rate": 1.9362501985233973e-06, + "loss": 0.0024, + "step": 52107 + }, + { + "epoch": 16.09, + "learning_rate": 1.935954436393226e-06, + "loss": 0.0015, + "step": 52108 + }, + { + "epoch": 16.09, + "learning_rate": 1.9356586944326994e-06, + "loss": 0.0017, + "step": 52109 + }, + { + "epoch": 16.09, + "learning_rate": 1.9353629726425614e-06, + "loss": 0.0017, + "step": 52110 + }, + { + "epoch": 16.09, + "learning_rate": 1.935067271023555e-06, + "loss": 0.0021, + "step": 52111 + }, + { + "epoch": 16.09, + "learning_rate": 1.9347715895764163e-06, + "loss": 0.0014, + "step": 52112 + }, + { + "epoch": 16.09, + "learning_rate": 1.9344759283018823e-06, + "loss": 0.0024, + "step": 52113 + }, + { + "epoch": 16.09, + "learning_rate": 1.9341802872006966e-06, + "loss": 0.0032, + "step": 52114 + }, + { + "epoch": 16.09, + "learning_rate": 1.9338846662735953e-06, + "loss": 0.002, + "step": 52115 + }, + { + "epoch": 16.09, + "learning_rate": 1.9335890655213217e-06, + "loss": 0.0024, + "step": 52116 + }, + { + "epoch": 16.09, + "learning_rate": 1.933293484944612e-06, + "loss": 0.0019, + "step": 52117 + }, + { + "epoch": 16.09, + "learning_rate": 1.9329979245442077e-06, + "loss": 0.0017, + "step": 52118 + }, + { + "epoch": 16.1, + "learning_rate": 1.9327023843208437e-06, + "loss": 0.0018, + "step": 52119 + }, + { + "epoch": 16.1, + "learning_rate": 1.9324068642752635e-06, + "loss": 0.0017, + "step": 52120 + }, + { + "epoch": 16.1, + "learning_rate": 1.932111364408208e-06, + "loss": 0.002, + "step": 52121 + }, + { + "epoch": 16.1, + "learning_rate": 1.931815884720413e-06, + "loss": 0.0022, + "step": 52122 + }, + { + "epoch": 16.1, + "learning_rate": 1.9315204252126154e-06, + "loss": 0.0021, + "step": 52123 + }, + { + "epoch": 16.1, + "learning_rate": 1.931224985885559e-06, + "loss": 0.0021, + "step": 52124 + }, + { + "epoch": 16.1, + "learning_rate": 1.9309295667399797e-06, + "loss": 0.0017, + "step": 52125 + }, + { + "epoch": 16.1, + "learning_rate": 1.9306341677766184e-06, + "loss": 0.0019, + "step": 52126 + }, + { + "epoch": 16.1, + "learning_rate": 1.9303387889962133e-06, + "loss": 0.0017, + "step": 52127 + }, + { + "epoch": 16.1, + "learning_rate": 1.9300434303994996e-06, + "loss": 0.0037, + "step": 52128 + }, + { + "epoch": 16.1, + "learning_rate": 1.929748091987219e-06, + "loss": 0.0021, + "step": 52129 + }, + { + "epoch": 16.1, + "learning_rate": 1.9294527737601134e-06, + "loss": 0.0017, + "step": 52130 + }, + { + "epoch": 16.1, + "learning_rate": 1.929157475718916e-06, + "loss": 0.0018, + "step": 52131 + }, + { + "epoch": 16.1, + "learning_rate": 1.9288621978643694e-06, + "loss": 0.0017, + "step": 52132 + }, + { + "epoch": 16.1, + "learning_rate": 1.9285669401972117e-06, + "loss": 0.0021, + "step": 52133 + }, + { + "epoch": 16.1, + "learning_rate": 1.9282717027181775e-06, + "loss": 0.0015, + "step": 52134 + }, + { + "epoch": 16.1, + "learning_rate": 1.927976485428008e-06, + "loss": 0.0021, + "step": 52135 + }, + { + "epoch": 16.1, + "learning_rate": 1.927681288327443e-06, + "loss": 0.0015, + "step": 52136 + }, + { + "epoch": 16.1, + "learning_rate": 1.927386111417221e-06, + "loss": 0.0021, + "step": 52137 + }, + { + "epoch": 16.1, + "learning_rate": 1.9270909546980756e-06, + "loss": 0.002, + "step": 52138 + }, + { + "epoch": 16.1, + "learning_rate": 1.92679581817075e-06, + "loss": 0.0016, + "step": 52139 + }, + { + "epoch": 16.1, + "learning_rate": 1.9265007018359783e-06, + "loss": 0.0021, + "step": 52140 + }, + { + "epoch": 16.1, + "learning_rate": 1.926205605694501e-06, + "loss": 0.002, + "step": 52141 + }, + { + "epoch": 16.1, + "learning_rate": 1.925910529747058e-06, + "loss": 0.0027, + "step": 52142 + }, + { + "epoch": 16.1, + "learning_rate": 1.9256154739943866e-06, + "loss": 0.0016, + "step": 52143 + }, + { + "epoch": 16.1, + "learning_rate": 1.925320438437219e-06, + "loss": 0.0018, + "step": 52144 + }, + { + "epoch": 16.1, + "learning_rate": 1.925025423076302e-06, + "loss": 0.0018, + "step": 52145 + }, + { + "epoch": 16.1, + "learning_rate": 1.924730427912367e-06, + "loss": 0.003, + "step": 52146 + }, + { + "epoch": 16.1, + "learning_rate": 1.924435452946155e-06, + "loss": 0.002, + "step": 52147 + }, + { + "epoch": 16.1, + "learning_rate": 1.9241404981784017e-06, + "loss": 0.0024, + "step": 52148 + }, + { + "epoch": 16.1, + "learning_rate": 1.9238455636098475e-06, + "loss": 0.0019, + "step": 52149 + }, + { + "epoch": 16.1, + "learning_rate": 1.923550649241227e-06, + "loss": 0.0025, + "step": 52150 + }, + { + "epoch": 16.11, + "learning_rate": 1.923255755073279e-06, + "loss": 0.0026, + "step": 52151 + }, + { + "epoch": 16.11, + "learning_rate": 1.9229608811067434e-06, + "loss": 0.0022, + "step": 52152 + }, + { + "epoch": 16.11, + "learning_rate": 1.922666027342356e-06, + "loss": 0.0024, + "step": 52153 + }, + { + "epoch": 16.11, + "learning_rate": 1.922371193780852e-06, + "loss": 0.0015, + "step": 52154 + }, + { + "epoch": 16.11, + "learning_rate": 1.9220763804229723e-06, + "loss": 0.0018, + "step": 52155 + }, + { + "epoch": 16.11, + "learning_rate": 1.9217815872694524e-06, + "loss": 0.0018, + "step": 52156 + }, + { + "epoch": 16.11, + "learning_rate": 1.921486814321031e-06, + "loss": 0.0017, + "step": 52157 + }, + { + "epoch": 16.11, + "learning_rate": 1.9211920615784454e-06, + "loss": 0.0021, + "step": 52158 + }, + { + "epoch": 16.11, + "learning_rate": 1.9208973290424284e-06, + "loss": 0.0016, + "step": 52159 + }, + { + "epoch": 16.11, + "learning_rate": 1.9206026167137214e-06, + "loss": 0.003, + "step": 52160 + }, + { + "epoch": 16.11, + "learning_rate": 1.9203079245930633e-06, + "loss": 0.002, + "step": 52161 + }, + { + "epoch": 16.11, + "learning_rate": 1.9200132526811865e-06, + "loss": 0.002, + "step": 52162 + }, + { + "epoch": 16.11, + "learning_rate": 1.9197186009788327e-06, + "loss": 0.0025, + "step": 52163 + }, + { + "epoch": 16.11, + "learning_rate": 1.9194239694867354e-06, + "loss": 0.0021, + "step": 52164 + }, + { + "epoch": 16.11, + "learning_rate": 1.9191293582056316e-06, + "loss": 0.0018, + "step": 52165 + }, + { + "epoch": 16.11, + "learning_rate": 1.9188347671362586e-06, + "loss": 0.0025, + "step": 52166 + }, + { + "epoch": 16.11, + "learning_rate": 1.9185401962793557e-06, + "loss": 0.0017, + "step": 52167 + }, + { + "epoch": 16.11, + "learning_rate": 1.918245645635658e-06, + "loss": 0.0028, + "step": 52168 + }, + { + "epoch": 16.11, + "learning_rate": 1.9179511152058992e-06, + "loss": 0.0017, + "step": 52169 + }, + { + "epoch": 16.11, + "learning_rate": 1.917656604990822e-06, + "loss": 0.0026, + "step": 52170 + }, + { + "epoch": 16.11, + "learning_rate": 1.917362114991157e-06, + "loss": 0.0027, + "step": 52171 + }, + { + "epoch": 16.11, + "learning_rate": 1.917067645207643e-06, + "loss": 0.0015, + "step": 52172 + }, + { + "epoch": 16.11, + "learning_rate": 1.916773195641023e-06, + "loss": 0.0015, + "step": 52173 + }, + { + "epoch": 16.11, + "learning_rate": 1.9164787662920214e-06, + "loss": 0.0018, + "step": 52174 + }, + { + "epoch": 16.11, + "learning_rate": 1.9161843571613812e-06, + "loss": 0.0021, + "step": 52175 + }, + { + "epoch": 16.11, + "learning_rate": 1.915889968249841e-06, + "loss": 0.002, + "step": 52176 + }, + { + "epoch": 16.11, + "learning_rate": 1.915595599558132e-06, + "loss": 0.0021, + "step": 52177 + }, + { + "epoch": 16.11, + "learning_rate": 1.915301251086995e-06, + "loss": 0.0017, + "step": 52178 + }, + { + "epoch": 16.11, + "learning_rate": 1.915006922837165e-06, + "loss": 0.0015, + "step": 52179 + }, + { + "epoch": 16.11, + "learning_rate": 1.914712614809374e-06, + "loss": 0.0022, + "step": 52180 + }, + { + "epoch": 16.11, + "learning_rate": 1.9144183270043613e-06, + "loss": 0.0038, + "step": 52181 + }, + { + "epoch": 16.11, + "learning_rate": 1.914124059422864e-06, + "loss": 0.002, + "step": 52182 + }, + { + "epoch": 16.12, + "learning_rate": 1.913829812065621e-06, + "loss": 0.002, + "step": 52183 + }, + { + "epoch": 16.12, + "learning_rate": 1.9135355849333603e-06, + "loss": 0.0019, + "step": 52184 + }, + { + "epoch": 16.12, + "learning_rate": 1.913241378026821e-06, + "loss": 0.0021, + "step": 52185 + }, + { + "epoch": 16.12, + "learning_rate": 1.9129471913467436e-06, + "loss": 0.0017, + "step": 52186 + }, + { + "epoch": 16.12, + "learning_rate": 1.9126530248938567e-06, + "loss": 0.0024, + "step": 52187 + }, + { + "epoch": 16.12, + "learning_rate": 1.912358878668904e-06, + "loss": 0.0024, + "step": 52188 + }, + { + "epoch": 16.12, + "learning_rate": 1.9120647526726156e-06, + "loss": 0.0024, + "step": 52189 + }, + { + "epoch": 16.12, + "learning_rate": 1.9117706469057252e-06, + "loss": 0.0024, + "step": 52190 + }, + { + "epoch": 16.12, + "learning_rate": 1.9114765613689725e-06, + "loss": 0.0024, + "step": 52191 + }, + { + "epoch": 16.12, + "learning_rate": 1.9111824960630943e-06, + "loss": 0.0017, + "step": 52192 + }, + { + "epoch": 16.12, + "learning_rate": 1.910888450988825e-06, + "loss": 0.0021, + "step": 52193 + }, + { + "epoch": 16.12, + "learning_rate": 1.9105944261468957e-06, + "loss": 0.0018, + "step": 52194 + }, + { + "epoch": 16.12, + "learning_rate": 1.910300421538047e-06, + "loss": 0.0015, + "step": 52195 + }, + { + "epoch": 16.12, + "learning_rate": 1.910006437163011e-06, + "loss": 0.0017, + "step": 52196 + }, + { + "epoch": 16.12, + "learning_rate": 1.909712473022524e-06, + "loss": 0.0018, + "step": 52197 + }, + { + "epoch": 16.12, + "learning_rate": 1.909418529117324e-06, + "loss": 0.0019, + "step": 52198 + }, + { + "epoch": 16.12, + "learning_rate": 1.909124605448144e-06, + "loss": 0.0026, + "step": 52199 + }, + { + "epoch": 16.12, + "learning_rate": 1.908830702015717e-06, + "loss": 0.0019, + "step": 52200 + }, + { + "epoch": 16.12, + "learning_rate": 1.908536818820782e-06, + "loss": 0.0019, + "step": 52201 + }, + { + "epoch": 16.12, + "learning_rate": 1.9082429558640705e-06, + "loss": 0.0015, + "step": 52202 + }, + { + "epoch": 16.12, + "learning_rate": 1.90794911314632e-06, + "loss": 0.0018, + "step": 52203 + }, + { + "epoch": 16.12, + "learning_rate": 1.9076552906682664e-06, + "loss": 0.0023, + "step": 52204 + }, + { + "epoch": 16.12, + "learning_rate": 1.9073614884306402e-06, + "loss": 0.002, + "step": 52205 + }, + { + "epoch": 16.12, + "learning_rate": 1.907067706434178e-06, + "loss": 0.0015, + "step": 52206 + }, + { + "epoch": 16.12, + "learning_rate": 1.9067739446796186e-06, + "loss": 0.0023, + "step": 52207 + }, + { + "epoch": 16.12, + "learning_rate": 1.906480203167691e-06, + "loss": 0.0019, + "step": 52208 + }, + { + "epoch": 16.12, + "learning_rate": 1.906186481899136e-06, + "loss": 0.0024, + "step": 52209 + }, + { + "epoch": 16.12, + "learning_rate": 1.905892780874684e-06, + "loss": 0.0019, + "step": 52210 + }, + { + "epoch": 16.12, + "learning_rate": 1.905599100095068e-06, + "loss": 0.0022, + "step": 52211 + }, + { + "epoch": 16.12, + "learning_rate": 1.9053054395610248e-06, + "loss": 0.0026, + "step": 52212 + }, + { + "epoch": 16.12, + "learning_rate": 1.9050117992732885e-06, + "loss": 0.0023, + "step": 52213 + }, + { + "epoch": 16.12, + "learning_rate": 1.904718179232601e-06, + "loss": 0.0018, + "step": 52214 + }, + { + "epoch": 16.12, + "learning_rate": 1.9044245794396832e-06, + "loss": 0.0022, + "step": 52215 + }, + { + "epoch": 16.13, + "learning_rate": 1.9041309998952761e-06, + "loss": 0.002, + "step": 52216 + }, + { + "epoch": 16.13, + "learning_rate": 1.903837440600117e-06, + "loss": 0.0024, + "step": 52217 + }, + { + "epoch": 16.13, + "learning_rate": 1.903543901554935e-06, + "loss": 0.0025, + "step": 52218 + }, + { + "epoch": 16.13, + "learning_rate": 1.9032503827604688e-06, + "loss": 0.002, + "step": 52219 + }, + { + "epoch": 16.13, + "learning_rate": 1.9029568842174496e-06, + "loss": 0.002, + "step": 52220 + }, + { + "epoch": 16.13, + "learning_rate": 1.902663405926609e-06, + "loss": 0.0023, + "step": 52221 + }, + { + "epoch": 16.13, + "learning_rate": 1.9023699478886849e-06, + "loss": 0.0019, + "step": 52222 + }, + { + "epoch": 16.13, + "learning_rate": 1.9020765101044136e-06, + "loss": 0.0022, + "step": 52223 + }, + { + "epoch": 16.13, + "learning_rate": 1.901783092574525e-06, + "loss": 0.0025, + "step": 52224 + }, + { + "epoch": 16.13, + "learning_rate": 1.901489695299752e-06, + "loss": 0.0018, + "step": 52225 + }, + { + "epoch": 16.13, + "learning_rate": 1.9011963182808324e-06, + "loss": 0.0021, + "step": 52226 + }, + { + "epoch": 16.13, + "learning_rate": 1.9009029615184948e-06, + "loss": 0.0019, + "step": 52227 + }, + { + "epoch": 16.13, + "learning_rate": 1.9006096250134764e-06, + "loss": 0.0021, + "step": 52228 + }, + { + "epoch": 16.13, + "learning_rate": 1.9003163087665143e-06, + "loss": 0.0021, + "step": 52229 + }, + { + "epoch": 16.13, + "learning_rate": 1.900023012778337e-06, + "loss": 0.0023, + "step": 52230 + }, + { + "epoch": 16.13, + "learning_rate": 1.899729737049678e-06, + "loss": 0.0023, + "step": 52231 + }, + { + "epoch": 16.13, + "learning_rate": 1.8994364815812739e-06, + "loss": 0.0034, + "step": 52232 + }, + { + "epoch": 16.13, + "learning_rate": 1.8991432463738546e-06, + "loss": 0.0016, + "step": 52233 + }, + { + "epoch": 16.13, + "learning_rate": 1.898850031428159e-06, + "loss": 0.0021, + "step": 52234 + }, + { + "epoch": 16.13, + "learning_rate": 1.898556836744916e-06, + "loss": 0.0017, + "step": 52235 + }, + { + "epoch": 16.13, + "learning_rate": 1.8982636623248562e-06, + "loss": 0.0017, + "step": 52236 + }, + { + "epoch": 16.13, + "learning_rate": 1.8979705081687182e-06, + "loss": 0.0023, + "step": 52237 + }, + { + "epoch": 16.13, + "learning_rate": 1.897677374277236e-06, + "loss": 0.0025, + "step": 52238 + }, + { + "epoch": 16.13, + "learning_rate": 1.8973842606511383e-06, + "loss": 0.0035, + "step": 52239 + }, + { + "epoch": 16.13, + "learning_rate": 1.897091167291162e-06, + "loss": 0.002, + "step": 52240 + }, + { + "epoch": 16.13, + "learning_rate": 1.8967980941980391e-06, + "loss": 0.0016, + "step": 52241 + }, + { + "epoch": 16.13, + "learning_rate": 1.8965050413724994e-06, + "loss": 0.0019, + "step": 52242 + }, + { + "epoch": 16.13, + "learning_rate": 1.896212008815279e-06, + "loss": 0.0016, + "step": 52243 + }, + { + "epoch": 16.13, + "learning_rate": 1.895918996527113e-06, + "loss": 0.0018, + "step": 52244 + }, + { + "epoch": 16.13, + "learning_rate": 1.8956260045087316e-06, + "loss": 0.002, + "step": 52245 + }, + { + "epoch": 16.13, + "learning_rate": 1.8953330327608643e-06, + "loss": 0.0017, + "step": 52246 + }, + { + "epoch": 16.13, + "learning_rate": 1.8950400812842474e-06, + "loss": 0.0015, + "step": 52247 + }, + { + "epoch": 16.14, + "learning_rate": 1.8947471500796166e-06, + "loss": 0.0019, + "step": 52248 + }, + { + "epoch": 16.14, + "learning_rate": 1.8944542391476994e-06, + "loss": 0.0019, + "step": 52249 + }, + { + "epoch": 16.14, + "learning_rate": 1.8941613484892329e-06, + "loss": 0.0025, + "step": 52250 + }, + { + "epoch": 16.14, + "learning_rate": 1.8938684781049465e-06, + "loss": 0.002, + "step": 52251 + }, + { + "epoch": 16.14, + "learning_rate": 1.8935756279955707e-06, + "loss": 0.0015, + "step": 52252 + }, + { + "epoch": 16.14, + "learning_rate": 1.8932827981618417e-06, + "loss": 0.0019, + "step": 52253 + }, + { + "epoch": 16.14, + "learning_rate": 1.8929899886044933e-06, + "loss": 0.0014, + "step": 52254 + }, + { + "epoch": 16.14, + "learning_rate": 1.892697199324256e-06, + "loss": 0.002, + "step": 52255 + }, + { + "epoch": 16.14, + "learning_rate": 1.892404430321858e-06, + "loss": 0.0022, + "step": 52256 + }, + { + "epoch": 16.14, + "learning_rate": 1.892111681598039e-06, + "loss": 0.0017, + "step": 52257 + }, + { + "epoch": 16.14, + "learning_rate": 1.8918189531535248e-06, + "loss": 0.0019, + "step": 52258 + }, + { + "epoch": 16.14, + "learning_rate": 1.8915262449890492e-06, + "loss": 0.0021, + "step": 52259 + }, + { + "epoch": 16.14, + "learning_rate": 1.8912335571053485e-06, + "loss": 0.0028, + "step": 52260 + }, + { + "epoch": 16.14, + "learning_rate": 1.8909408895031521e-06, + "loss": 0.0015, + "step": 52261 + }, + { + "epoch": 16.14, + "learning_rate": 1.8906482421831885e-06, + "loss": 0.0025, + "step": 52262 + }, + { + "epoch": 16.14, + "learning_rate": 1.8903556151461955e-06, + "loss": 0.0015, + "step": 52263 + }, + { + "epoch": 16.14, + "learning_rate": 1.8900630083928994e-06, + "loss": 0.0019, + "step": 52264 + }, + { + "epoch": 16.14, + "learning_rate": 1.8897704219240376e-06, + "loss": 0.0026, + "step": 52265 + }, + { + "epoch": 16.14, + "learning_rate": 1.8894778557403382e-06, + "loss": 0.0027, + "step": 52266 + }, + { + "epoch": 16.14, + "learning_rate": 1.889185309842533e-06, + "loss": 0.0012, + "step": 52267 + }, + { + "epoch": 16.14, + "learning_rate": 1.8888927842313532e-06, + "loss": 0.0024, + "step": 52268 + }, + { + "epoch": 16.14, + "learning_rate": 1.8886002789075352e-06, + "loss": 0.0025, + "step": 52269 + }, + { + "epoch": 16.14, + "learning_rate": 1.8883077938718053e-06, + "loss": 0.002, + "step": 52270 + }, + { + "epoch": 16.14, + "learning_rate": 1.8880153291248992e-06, + "loss": 0.0013, + "step": 52271 + }, + { + "epoch": 16.14, + "learning_rate": 1.8877228846675456e-06, + "loss": 0.0028, + "step": 52272 + }, + { + "epoch": 16.14, + "learning_rate": 1.8874304605004756e-06, + "loss": 0.0021, + "step": 52273 + }, + { + "epoch": 16.14, + "learning_rate": 1.88713805662442e-06, + "loss": 0.0021, + "step": 52274 + }, + { + "epoch": 16.14, + "learning_rate": 1.8868456730401153e-06, + "loss": 0.0016, + "step": 52275 + }, + { + "epoch": 16.14, + "learning_rate": 1.886553309748289e-06, + "loss": 0.0018, + "step": 52276 + }, + { + "epoch": 16.14, + "learning_rate": 1.88626096674967e-06, + "loss": 0.0019, + "step": 52277 + }, + { + "epoch": 16.14, + "learning_rate": 1.8859686440449954e-06, + "loss": 0.0036, + "step": 52278 + }, + { + "epoch": 16.14, + "learning_rate": 1.88567634163499e-06, + "loss": 0.0026, + "step": 52279 + }, + { + "epoch": 16.15, + "learning_rate": 1.8853840595203887e-06, + "loss": 0.0014, + "step": 52280 + }, + { + "epoch": 16.15, + "learning_rate": 1.8850917977019235e-06, + "loss": 0.0017, + "step": 52281 + }, + { + "epoch": 16.15, + "learning_rate": 1.8847995561803244e-06, + "loss": 0.0022, + "step": 52282 + }, + { + "epoch": 16.15, + "learning_rate": 1.8845073349563193e-06, + "loss": 0.0014, + "step": 52283 + }, + { + "epoch": 16.15, + "learning_rate": 1.8842151340306414e-06, + "loss": 0.0016, + "step": 52284 + }, + { + "epoch": 16.15, + "learning_rate": 1.8839229534040237e-06, + "loss": 0.0019, + "step": 52285 + }, + { + "epoch": 16.15, + "learning_rate": 1.8836307930771957e-06, + "loss": 0.0027, + "step": 52286 + }, + { + "epoch": 16.15, + "learning_rate": 1.8833386530508846e-06, + "loss": 0.0025, + "step": 52287 + }, + { + "epoch": 16.15, + "learning_rate": 1.8830465333258264e-06, + "loss": 0.0023, + "step": 52288 + }, + { + "epoch": 16.15, + "learning_rate": 1.8827544339027459e-06, + "loss": 0.0029, + "step": 52289 + }, + { + "epoch": 16.15, + "learning_rate": 1.8824623547823783e-06, + "loss": 0.0019, + "step": 52290 + }, + { + "epoch": 16.15, + "learning_rate": 1.8821702959654552e-06, + "loss": 0.0027, + "step": 52291 + }, + { + "epoch": 16.15, + "learning_rate": 1.881878257452704e-06, + "loss": 0.0033, + "step": 52292 + }, + { + "epoch": 16.15, + "learning_rate": 1.8815862392448536e-06, + "loss": 0.0023, + "step": 52293 + }, + { + "epoch": 16.15, + "learning_rate": 1.8812942413426406e-06, + "loss": 0.002, + "step": 52294 + }, + { + "epoch": 16.15, + "learning_rate": 1.8810022637467874e-06, + "loss": 0.002, + "step": 52295 + }, + { + "epoch": 16.15, + "learning_rate": 1.8807103064580311e-06, + "loss": 0.0022, + "step": 52296 + }, + { + "epoch": 16.15, + "learning_rate": 1.8804183694771005e-06, + "loss": 0.0021, + "step": 52297 + }, + { + "epoch": 16.15, + "learning_rate": 1.8801264528047203e-06, + "loss": 0.002, + "step": 52298 + }, + { + "epoch": 16.15, + "learning_rate": 1.8798345564416254e-06, + "loss": 0.0021, + "step": 52299 + }, + { + "epoch": 16.15, + "learning_rate": 1.8795426803885486e-06, + "loss": 0.0021, + "step": 52300 + }, + { + "epoch": 16.15, + "learning_rate": 1.8792508246462127e-06, + "loss": 0.0021, + "step": 52301 + }, + { + "epoch": 16.15, + "learning_rate": 1.8789589892153549e-06, + "loss": 0.0026, + "step": 52302 + }, + { + "epoch": 16.15, + "learning_rate": 1.8786671740967022e-06, + "loss": 0.0019, + "step": 52303 + }, + { + "epoch": 16.15, + "learning_rate": 1.8783753792909808e-06, + "loss": 0.0017, + "step": 52304 + }, + { + "epoch": 16.15, + "learning_rate": 1.8780836047989247e-06, + "loss": 0.0015, + "step": 52305 + }, + { + "epoch": 16.15, + "learning_rate": 1.8777918506212645e-06, + "loss": 0.0023, + "step": 52306 + }, + { + "epoch": 16.15, + "learning_rate": 1.8775001167587291e-06, + "loss": 0.0021, + "step": 52307 + }, + { + "epoch": 16.15, + "learning_rate": 1.8772084032120442e-06, + "loss": 0.0018, + "step": 52308 + }, + { + "epoch": 16.15, + "learning_rate": 1.876916709981945e-06, + "loss": 0.0018, + "step": 52309 + }, + { + "epoch": 16.15, + "learning_rate": 1.8766250370691575e-06, + "loss": 0.0017, + "step": 52310 + }, + { + "epoch": 16.15, + "learning_rate": 1.8763333844744114e-06, + "loss": 0.002, + "step": 52311 + }, + { + "epoch": 16.15, + "learning_rate": 1.8760417521984397e-06, + "loss": 0.0023, + "step": 52312 + }, + { + "epoch": 16.16, + "learning_rate": 1.8757501402419686e-06, + "loss": 0.0017, + "step": 52313 + }, + { + "epoch": 16.16, + "learning_rate": 1.8754585486057265e-06, + "loss": 0.0014, + "step": 52314 + }, + { + "epoch": 16.16, + "learning_rate": 1.8751669772904447e-06, + "loss": 0.002, + "step": 52315 + }, + { + "epoch": 16.16, + "learning_rate": 1.8748754262968538e-06, + "loss": 0.0025, + "step": 52316 + }, + { + "epoch": 16.16, + "learning_rate": 1.8745838956256824e-06, + "loss": 0.0016, + "step": 52317 + }, + { + "epoch": 16.16, + "learning_rate": 1.874292385277655e-06, + "loss": 0.0021, + "step": 52318 + }, + { + "epoch": 16.16, + "learning_rate": 1.8740008952535082e-06, + "loss": 0.0016, + "step": 52319 + }, + { + "epoch": 16.16, + "learning_rate": 1.8737094255539633e-06, + "loss": 0.0016, + "step": 52320 + }, + { + "epoch": 16.16, + "learning_rate": 1.8734179761797545e-06, + "loss": 0.0018, + "step": 52321 + }, + { + "epoch": 16.16, + "learning_rate": 1.873126547131614e-06, + "loss": 0.0017, + "step": 52322 + }, + { + "epoch": 16.16, + "learning_rate": 1.8728351384102618e-06, + "loss": 0.0023, + "step": 52323 + }, + { + "epoch": 16.16, + "learning_rate": 1.87254375001643e-06, + "loss": 0.0024, + "step": 52324 + }, + { + "epoch": 16.16, + "learning_rate": 1.872252381950852e-06, + "loss": 0.0021, + "step": 52325 + }, + { + "epoch": 16.16, + "learning_rate": 1.8719610342142501e-06, + "loss": 0.0022, + "step": 52326 + }, + { + "epoch": 16.16, + "learning_rate": 1.8716697068073596e-06, + "loss": 0.0015, + "step": 52327 + }, + { + "epoch": 16.16, + "learning_rate": 1.8713783997309055e-06, + "loss": 0.0024, + "step": 52328 + }, + { + "epoch": 16.16, + "learning_rate": 1.8710871129856135e-06, + "loss": 0.0019, + "step": 52329 + }, + { + "epoch": 16.16, + "learning_rate": 1.8707958465722153e-06, + "loss": 0.0021, + "step": 52330 + }, + { + "epoch": 16.16, + "learning_rate": 1.8705046004914418e-06, + "loss": 0.0019, + "step": 52331 + }, + { + "epoch": 16.16, + "learning_rate": 1.87021337474402e-06, + "loss": 0.0022, + "step": 52332 + }, + { + "epoch": 16.16, + "learning_rate": 1.8699221693306735e-06, + "loss": 0.0023, + "step": 52333 + }, + { + "epoch": 16.16, + "learning_rate": 1.8696309842521376e-06, + "loss": 0.002, + "step": 52334 + }, + { + "epoch": 16.16, + "learning_rate": 1.869339819509135e-06, + "loss": 0.0026, + "step": 52335 + }, + { + "epoch": 16.16, + "learning_rate": 1.8690486751023962e-06, + "loss": 0.0019, + "step": 52336 + }, + { + "epoch": 16.16, + "learning_rate": 1.8687575510326528e-06, + "loss": 0.0016, + "step": 52337 + }, + { + "epoch": 16.16, + "learning_rate": 1.8684664473006286e-06, + "loss": 0.0019, + "step": 52338 + }, + { + "epoch": 16.16, + "learning_rate": 1.868175363907052e-06, + "loss": 0.0027, + "step": 52339 + }, + { + "epoch": 16.16, + "learning_rate": 1.8678843008526538e-06, + "loss": 0.0033, + "step": 52340 + }, + { + "epoch": 16.16, + "learning_rate": 1.8675932581381572e-06, + "loss": 0.0016, + "step": 52341 + }, + { + "epoch": 16.16, + "learning_rate": 1.8673022357642957e-06, + "loss": 0.0027, + "step": 52342 + }, + { + "epoch": 16.16, + "learning_rate": 1.8670112337317948e-06, + "loss": 0.002, + "step": 52343 + }, + { + "epoch": 16.16, + "learning_rate": 1.8667202520413797e-06, + "loss": 0.002, + "step": 52344 + }, + { + "epoch": 16.17, + "learning_rate": 1.866429290693781e-06, + "loss": 0.0027, + "step": 52345 + }, + { + "epoch": 16.17, + "learning_rate": 1.8661383496897257e-06, + "loss": 0.0021, + "step": 52346 + }, + { + "epoch": 16.17, + "learning_rate": 1.8658474290299445e-06, + "loss": 0.002, + "step": 52347 + }, + { + "epoch": 16.17, + "learning_rate": 1.8655565287151633e-06, + "loss": 0.0016, + "step": 52348 + }, + { + "epoch": 16.17, + "learning_rate": 1.8652656487461052e-06, + "loss": 0.0024, + "step": 52349 + }, + { + "epoch": 16.17, + "learning_rate": 1.8649747891235038e-06, + "loss": 0.0022, + "step": 52350 + }, + { + "epoch": 16.17, + "learning_rate": 1.8646839498480829e-06, + "loss": 0.0024, + "step": 52351 + }, + { + "epoch": 16.17, + "learning_rate": 1.864393130920572e-06, + "loss": 0.0017, + "step": 52352 + }, + { + "epoch": 16.17, + "learning_rate": 1.8641023323416995e-06, + "loss": 0.0022, + "step": 52353 + }, + { + "epoch": 16.17, + "learning_rate": 1.863811554112187e-06, + "loss": 0.0022, + "step": 52354 + }, + { + "epoch": 16.17, + "learning_rate": 1.8635207962327673e-06, + "loss": 0.0026, + "step": 52355 + }, + { + "epoch": 16.17, + "learning_rate": 1.8632300587041675e-06, + "loss": 0.0021, + "step": 52356 + }, + { + "epoch": 16.17, + "learning_rate": 1.8629393415271102e-06, + "loss": 0.0019, + "step": 52357 + }, + { + "epoch": 16.17, + "learning_rate": 1.8626486447023295e-06, + "loss": 0.0023, + "step": 52358 + }, + { + "epoch": 16.17, + "learning_rate": 1.8623579682305481e-06, + "loss": 0.0016, + "step": 52359 + }, + { + "epoch": 16.17, + "learning_rate": 1.862067312112492e-06, + "loss": 0.0016, + "step": 52360 + }, + { + "epoch": 16.17, + "learning_rate": 1.8617766763488886e-06, + "loss": 0.0017, + "step": 52361 + }, + { + "epoch": 16.17, + "learning_rate": 1.8614860609404695e-06, + "loss": 0.0021, + "step": 52362 + }, + { + "epoch": 16.17, + "learning_rate": 1.8611954658879572e-06, + "loss": 0.0016, + "step": 52363 + }, + { + "epoch": 16.17, + "learning_rate": 1.860904891192078e-06, + "loss": 0.0022, + "step": 52364 + }, + { + "epoch": 16.17, + "learning_rate": 1.8606143368535622e-06, + "loss": 0.0016, + "step": 52365 + }, + { + "epoch": 16.17, + "learning_rate": 1.8603238028731319e-06, + "loss": 0.0018, + "step": 52366 + }, + { + "epoch": 16.17, + "learning_rate": 1.860033289251516e-06, + "loss": 0.0018, + "step": 52367 + }, + { + "epoch": 16.17, + "learning_rate": 1.8597427959894443e-06, + "loss": 0.0023, + "step": 52368 + }, + { + "epoch": 16.17, + "learning_rate": 1.8594523230876405e-06, + "loss": 0.0021, + "step": 52369 + }, + { + "epoch": 16.17, + "learning_rate": 1.8591618705468295e-06, + "loss": 0.002, + "step": 52370 + }, + { + "epoch": 16.17, + "learning_rate": 1.8588714383677409e-06, + "loss": 0.0021, + "step": 52371 + }, + { + "epoch": 16.17, + "learning_rate": 1.8585810265510973e-06, + "loss": 0.0016, + "step": 52372 + }, + { + "epoch": 16.17, + "learning_rate": 1.8582906350976304e-06, + "loss": 0.0018, + "step": 52373 + }, + { + "epoch": 16.17, + "learning_rate": 1.858000264008063e-06, + "loss": 0.0019, + "step": 52374 + }, + { + "epoch": 16.17, + "learning_rate": 1.85770991328312e-06, + "loss": 0.0019, + "step": 52375 + }, + { + "epoch": 16.17, + "learning_rate": 1.8574195829235299e-06, + "loss": 0.0014, + "step": 52376 + }, + { + "epoch": 16.17, + "learning_rate": 1.8571292729300173e-06, + "loss": 0.0018, + "step": 52377 + }, + { + "epoch": 16.18, + "learning_rate": 1.856838983303313e-06, + "loss": 0.0017, + "step": 52378 + }, + { + "epoch": 16.18, + "learning_rate": 1.8565487140441396e-06, + "loss": 0.0025, + "step": 52379 + }, + { + "epoch": 16.18, + "learning_rate": 1.8562584651532201e-06, + "loss": 0.0021, + "step": 52380 + }, + { + "epoch": 16.18, + "learning_rate": 1.855968236631287e-06, + "loss": 0.0023, + "step": 52381 + }, + { + "epoch": 16.18, + "learning_rate": 1.8556780284790588e-06, + "loss": 0.0024, + "step": 52382 + }, + { + "epoch": 16.18, + "learning_rate": 1.8553878406972693e-06, + "loss": 0.0016, + "step": 52383 + }, + { + "epoch": 16.18, + "learning_rate": 1.8550976732866389e-06, + "loss": 0.0018, + "step": 52384 + }, + { + "epoch": 16.18, + "learning_rate": 1.8548075262478927e-06, + "loss": 0.003, + "step": 52385 + }, + { + "epoch": 16.18, + "learning_rate": 1.8545173995817589e-06, + "loss": 0.0017, + "step": 52386 + }, + { + "epoch": 16.18, + "learning_rate": 1.8542272932889648e-06, + "loss": 0.002, + "step": 52387 + }, + { + "epoch": 16.18, + "learning_rate": 1.8539372073702323e-06, + "loss": 0.0024, + "step": 52388 + }, + { + "epoch": 16.18, + "learning_rate": 1.8536471418262903e-06, + "loss": 0.0016, + "step": 52389 + }, + { + "epoch": 16.18, + "learning_rate": 1.8533570966578629e-06, + "loss": 0.0018, + "step": 52390 + }, + { + "epoch": 16.18, + "learning_rate": 1.8530670718656719e-06, + "loss": 0.0019, + "step": 52391 + }, + { + "epoch": 16.18, + "learning_rate": 1.8527770674504464e-06, + "loss": 0.0017, + "step": 52392 + }, + { + "epoch": 16.18, + "learning_rate": 1.852487083412915e-06, + "loss": 0.0021, + "step": 52393 + }, + { + "epoch": 16.18, + "learning_rate": 1.852197119753798e-06, + "loss": 0.0017, + "step": 52394 + }, + { + "epoch": 16.18, + "learning_rate": 1.8519071764738205e-06, + "loss": 0.0019, + "step": 52395 + }, + { + "epoch": 16.18, + "learning_rate": 1.851617253573712e-06, + "loss": 0.0021, + "step": 52396 + }, + { + "epoch": 16.18, + "learning_rate": 1.8513273510541919e-06, + "loss": 0.0023, + "step": 52397 + }, + { + "epoch": 16.18, + "learning_rate": 1.8510374689159883e-06, + "loss": 0.0015, + "step": 52398 + }, + { + "epoch": 16.18, + "learning_rate": 1.8507476071598285e-06, + "loss": 0.0016, + "step": 52399 + }, + { + "epoch": 16.18, + "learning_rate": 1.8504577657864353e-06, + "loss": 0.0025, + "step": 52400 + }, + { + "epoch": 16.18, + "learning_rate": 1.8501679447965314e-06, + "loss": 0.0021, + "step": 52401 + }, + { + "epoch": 16.18, + "learning_rate": 1.8498781441908465e-06, + "loss": 0.0024, + "step": 52402 + }, + { + "epoch": 16.18, + "learning_rate": 1.8495883639701006e-06, + "loss": 0.0018, + "step": 52403 + }, + { + "epoch": 16.18, + "learning_rate": 1.8492986041350224e-06, + "loss": 0.0025, + "step": 52404 + }, + { + "epoch": 16.18, + "learning_rate": 1.8490088646863357e-06, + "loss": 0.0033, + "step": 52405 + }, + { + "epoch": 16.18, + "learning_rate": 1.8487191456247623e-06, + "loss": 0.0018, + "step": 52406 + }, + { + "epoch": 16.18, + "learning_rate": 1.8484294469510277e-06, + "loss": 0.0019, + "step": 52407 + }, + { + "epoch": 16.18, + "learning_rate": 1.848139768665862e-06, + "loss": 0.0025, + "step": 52408 + }, + { + "epoch": 16.18, + "learning_rate": 1.847850110769982e-06, + "loss": 0.0021, + "step": 52409 + }, + { + "epoch": 16.19, + "learning_rate": 1.8475604732641184e-06, + "loss": 0.0016, + "step": 52410 + }, + { + "epoch": 16.19, + "learning_rate": 1.8472708561489893e-06, + "loss": 0.0021, + "step": 52411 + }, + { + "epoch": 16.19, + "learning_rate": 1.8469812594253267e-06, + "loss": 0.0022, + "step": 52412 + }, + { + "epoch": 16.19, + "learning_rate": 1.8466916830938485e-06, + "loss": 0.0016, + "step": 52413 + }, + { + "epoch": 16.19, + "learning_rate": 1.8464021271552834e-06, + "loss": 0.0023, + "step": 52414 + }, + { + "epoch": 16.19, + "learning_rate": 1.846112591610354e-06, + "loss": 0.0019, + "step": 52415 + }, + { + "epoch": 16.19, + "learning_rate": 1.8458230764597818e-06, + "loss": 0.0021, + "step": 52416 + }, + { + "epoch": 16.19, + "learning_rate": 1.845533581704293e-06, + "loss": 0.0016, + "step": 52417 + }, + { + "epoch": 16.19, + "learning_rate": 1.8452441073446149e-06, + "loss": 0.002, + "step": 52418 + }, + { + "epoch": 16.19, + "learning_rate": 1.8449546533814656e-06, + "loss": 0.002, + "step": 52419 + }, + { + "epoch": 16.19, + "learning_rate": 1.8446652198155746e-06, + "loss": 0.0026, + "step": 52420 + }, + { + "epoch": 16.19, + "learning_rate": 1.8443758066476636e-06, + "loss": 0.0016, + "step": 52421 + }, + { + "epoch": 16.19, + "learning_rate": 1.8440864138784543e-06, + "loss": 0.0026, + "step": 52422 + }, + { + "epoch": 16.19, + "learning_rate": 1.8437970415086714e-06, + "loss": 0.0018, + "step": 52423 + }, + { + "epoch": 16.19, + "learning_rate": 1.8435076895390425e-06, + "loss": 0.0019, + "step": 52424 + }, + { + "epoch": 16.19, + "learning_rate": 1.843218357970289e-06, + "loss": 0.0021, + "step": 52425 + }, + { + "epoch": 16.19, + "learning_rate": 1.8429290468031313e-06, + "loss": 0.0014, + "step": 52426 + }, + { + "epoch": 16.19, + "learning_rate": 1.8426397560382981e-06, + "loss": 0.0019, + "step": 52427 + }, + { + "epoch": 16.19, + "learning_rate": 1.8423504856765085e-06, + "loss": 0.0017, + "step": 52428 + }, + { + "epoch": 16.19, + "learning_rate": 1.8420612357184874e-06, + "loss": 0.002, + "step": 52429 + }, + { + "epoch": 16.19, + "learning_rate": 1.8417720061649647e-06, + "loss": 0.0017, + "step": 52430 + }, + { + "epoch": 16.19, + "learning_rate": 1.8414827970166538e-06, + "loss": 0.0018, + "step": 52431 + }, + { + "epoch": 16.19, + "learning_rate": 1.8411936082742809e-06, + "loss": 0.0022, + "step": 52432 + }, + { + "epoch": 16.19, + "learning_rate": 1.8409044399385745e-06, + "loss": 0.0014, + "step": 52433 + }, + { + "epoch": 16.19, + "learning_rate": 1.8406152920102516e-06, + "loss": 0.002, + "step": 52434 + }, + { + "epoch": 16.19, + "learning_rate": 1.8403261644900406e-06, + "loss": 0.0025, + "step": 52435 + }, + { + "epoch": 16.19, + "learning_rate": 1.8400370573786619e-06, + "loss": 0.0016, + "step": 52436 + }, + { + "epoch": 16.19, + "learning_rate": 1.8397479706768362e-06, + "loss": 0.0015, + "step": 52437 + }, + { + "epoch": 16.19, + "learning_rate": 1.8394589043852896e-06, + "loss": 0.002, + "step": 52438 + }, + { + "epoch": 16.19, + "learning_rate": 1.8391698585047468e-06, + "loss": 0.0023, + "step": 52439 + }, + { + "epoch": 16.19, + "learning_rate": 1.8388808330359287e-06, + "loss": 0.0019, + "step": 52440 + }, + { + "epoch": 16.19, + "learning_rate": 1.8385918279795557e-06, + "loss": 0.0024, + "step": 52441 + }, + { + "epoch": 16.2, + "learning_rate": 1.8383028433363526e-06, + "loss": 0.0017, + "step": 52442 + }, + { + "epoch": 16.2, + "learning_rate": 1.8380138791070456e-06, + "loss": 0.0015, + "step": 52443 + }, + { + "epoch": 16.2, + "learning_rate": 1.837724935292352e-06, + "loss": 0.0015, + "step": 52444 + }, + { + "epoch": 16.2, + "learning_rate": 1.8374360118930002e-06, + "loss": 0.0031, + "step": 52445 + }, + { + "epoch": 16.2, + "learning_rate": 1.8371471089097083e-06, + "loss": 0.0016, + "step": 52446 + }, + { + "epoch": 16.2, + "learning_rate": 1.836858226343199e-06, + "loss": 0.0022, + "step": 52447 + }, + { + "epoch": 16.2, + "learning_rate": 1.836569364194195e-06, + "loss": 0.0031, + "step": 52448 + }, + { + "epoch": 16.2, + "learning_rate": 1.836280522463424e-06, + "loss": 0.0019, + "step": 52449 + }, + { + "epoch": 16.2, + "learning_rate": 1.8359917011516025e-06, + "loss": 0.002, + "step": 52450 + }, + { + "epoch": 16.2, + "learning_rate": 1.835702900259454e-06, + "loss": 0.0021, + "step": 52451 + }, + { + "epoch": 16.2, + "learning_rate": 1.8354141197877029e-06, + "loss": 0.0022, + "step": 52452 + }, + { + "epoch": 16.2, + "learning_rate": 1.8351253597370688e-06, + "loss": 0.0032, + "step": 52453 + }, + { + "epoch": 16.2, + "learning_rate": 1.8348366201082746e-06, + "loss": 0.002, + "step": 52454 + }, + { + "epoch": 16.2, + "learning_rate": 1.8345479009020461e-06, + "loss": 0.0022, + "step": 52455 + }, + { + "epoch": 16.2, + "learning_rate": 1.834259202119102e-06, + "loss": 0.0022, + "step": 52456 + }, + { + "epoch": 16.2, + "learning_rate": 1.8339705237601634e-06, + "loss": 0.0023, + "step": 52457 + }, + { + "epoch": 16.2, + "learning_rate": 1.8336818658259559e-06, + "loss": 0.0017, + "step": 52458 + }, + { + "epoch": 16.2, + "learning_rate": 1.8333932283171961e-06, + "loss": 0.0022, + "step": 52459 + }, + { + "epoch": 16.2, + "learning_rate": 1.8331046112346128e-06, + "loss": 0.0018, + "step": 52460 + }, + { + "epoch": 16.2, + "learning_rate": 1.8328160145789253e-06, + "loss": 0.004, + "step": 52461 + }, + { + "epoch": 16.2, + "learning_rate": 1.8325274383508506e-06, + "loss": 0.0015, + "step": 52462 + }, + { + "epoch": 16.2, + "learning_rate": 1.832238882551115e-06, + "loss": 0.0023, + "step": 52463 + }, + { + "epoch": 16.2, + "learning_rate": 1.8319503471804423e-06, + "loss": 0.0018, + "step": 52464 + }, + { + "epoch": 16.2, + "learning_rate": 1.8316618322395485e-06, + "loss": 0.002, + "step": 52465 + }, + { + "epoch": 16.2, + "learning_rate": 1.831373337729161e-06, + "loss": 0.0016, + "step": 52466 + }, + { + "epoch": 16.2, + "learning_rate": 1.8310848636499989e-06, + "loss": 0.0031, + "step": 52467 + }, + { + "epoch": 16.2, + "learning_rate": 1.8307964100027808e-06, + "loss": 0.0015, + "step": 52468 + }, + { + "epoch": 16.2, + "learning_rate": 1.8305079767882305e-06, + "loss": 0.0021, + "step": 52469 + }, + { + "epoch": 16.2, + "learning_rate": 1.830219564007073e-06, + "loss": 0.0024, + "step": 52470 + }, + { + "epoch": 16.2, + "learning_rate": 1.8299311716600266e-06, + "loss": 0.002, + "step": 52471 + }, + { + "epoch": 16.2, + "learning_rate": 1.8296427997478083e-06, + "loss": 0.0028, + "step": 52472 + }, + { + "epoch": 16.2, + "learning_rate": 1.8293544482711479e-06, + "loss": 0.0015, + "step": 52473 + }, + { + "epoch": 16.2, + "learning_rate": 1.8290661172307589e-06, + "loss": 0.0019, + "step": 52474 + }, + { + "epoch": 16.21, + "learning_rate": 1.8287778066273655e-06, + "loss": 0.0017, + "step": 52475 + }, + { + "epoch": 16.21, + "learning_rate": 1.8284895164616923e-06, + "loss": 0.0018, + "step": 52476 + }, + { + "epoch": 16.21, + "learning_rate": 1.8282012467344568e-06, + "loss": 0.0028, + "step": 52477 + }, + { + "epoch": 16.21, + "learning_rate": 1.8279129974463782e-06, + "loss": 0.0025, + "step": 52478 + }, + { + "epoch": 16.21, + "learning_rate": 1.8276247685981797e-06, + "loss": 0.002, + "step": 52479 + }, + { + "epoch": 16.21, + "learning_rate": 1.8273365601905847e-06, + "loss": 0.002, + "step": 52480 + }, + { + "epoch": 16.21, + "learning_rate": 1.8270483722243114e-06, + "loss": 0.0028, + "step": 52481 + }, + { + "epoch": 16.21, + "learning_rate": 1.8267602047000787e-06, + "loss": 0.0016, + "step": 52482 + }, + { + "epoch": 16.21, + "learning_rate": 1.8264720576186112e-06, + "loss": 0.0024, + "step": 52483 + }, + { + "epoch": 16.21, + "learning_rate": 1.8261839309806263e-06, + "loss": 0.0021, + "step": 52484 + }, + { + "epoch": 16.21, + "learning_rate": 1.8258958247868452e-06, + "loss": 0.0025, + "step": 52485 + }, + { + "epoch": 16.21, + "learning_rate": 1.8256077390379923e-06, + "loss": 0.002, + "step": 52486 + }, + { + "epoch": 16.21, + "learning_rate": 1.8253196737347856e-06, + "loss": 0.0022, + "step": 52487 + }, + { + "epoch": 16.21, + "learning_rate": 1.8250316288779436e-06, + "loss": 0.003, + "step": 52488 + }, + { + "epoch": 16.21, + "learning_rate": 1.82474360446819e-06, + "loss": 0.0022, + "step": 52489 + }, + { + "epoch": 16.21, + "learning_rate": 1.8244556005062408e-06, + "loss": 0.0029, + "step": 52490 + }, + { + "epoch": 16.21, + "learning_rate": 1.8241676169928224e-06, + "loss": 0.0025, + "step": 52491 + }, + { + "epoch": 16.21, + "learning_rate": 1.8238796539286518e-06, + "loss": 0.0024, + "step": 52492 + }, + { + "epoch": 16.21, + "learning_rate": 1.8235917113144475e-06, + "loss": 0.0021, + "step": 52493 + }, + { + "epoch": 16.21, + "learning_rate": 1.823303789150931e-06, + "loss": 0.0015, + "step": 52494 + }, + { + "epoch": 16.21, + "learning_rate": 1.823015887438826e-06, + "loss": 0.0015, + "step": 52495 + }, + { + "epoch": 16.21, + "learning_rate": 1.8227280061788466e-06, + "loss": 0.003, + "step": 52496 + }, + { + "epoch": 16.21, + "learning_rate": 1.8224401453717189e-06, + "loss": 0.0025, + "step": 52497 + }, + { + "epoch": 16.21, + "learning_rate": 1.82215230501816e-06, + "loss": 0.0017, + "step": 52498 + }, + { + "epoch": 16.21, + "learning_rate": 1.8218644851188871e-06, + "loss": 0.0027, + "step": 52499 + }, + { + "epoch": 16.21, + "learning_rate": 1.821576685674622e-06, + "loss": 0.002, + "step": 52500 + }, + { + "epoch": 16.21, + "learning_rate": 1.8212889066860885e-06, + "loss": 0.0017, + "step": 52501 + }, + { + "epoch": 16.21, + "learning_rate": 1.8210011481540024e-06, + "loss": 0.0021, + "step": 52502 + }, + { + "epoch": 16.21, + "learning_rate": 1.8207134100790825e-06, + "loss": 0.0014, + "step": 52503 + }, + { + "epoch": 16.21, + "learning_rate": 1.8204256924620522e-06, + "loss": 0.0018, + "step": 52504 + }, + { + "epoch": 16.21, + "learning_rate": 1.8201379953036268e-06, + "loss": 0.002, + "step": 52505 + }, + { + "epoch": 16.21, + "learning_rate": 1.819850318604529e-06, + "loss": 0.0018, + "step": 52506 + }, + { + "epoch": 16.22, + "learning_rate": 1.8195626623654795e-06, + "loss": 0.0018, + "step": 52507 + }, + { + "epoch": 16.22, + "learning_rate": 1.819275026587195e-06, + "loss": 0.002, + "step": 52508 + }, + { + "epoch": 16.22, + "learning_rate": 1.818987411270393e-06, + "loss": 0.0015, + "step": 52509 + }, + { + "epoch": 16.22, + "learning_rate": 1.8186998164157964e-06, + "loss": 0.0015, + "step": 52510 + }, + { + "epoch": 16.22, + "learning_rate": 1.8184122420241269e-06, + "loss": 0.0015, + "step": 52511 + }, + { + "epoch": 16.22, + "learning_rate": 1.8181246880961001e-06, + "loss": 0.0022, + "step": 52512 + }, + { + "epoch": 16.22, + "learning_rate": 1.8178371546324326e-06, + "loss": 0.003, + "step": 52513 + }, + { + "epoch": 16.22, + "learning_rate": 1.8175496416338501e-06, + "loss": 0.0022, + "step": 52514 + }, + { + "epoch": 16.22, + "learning_rate": 1.8172621491010656e-06, + "loss": 0.0017, + "step": 52515 + }, + { + "epoch": 16.22, + "learning_rate": 1.8169746770347996e-06, + "loss": 0.0018, + "step": 52516 + }, + { + "epoch": 16.22, + "learning_rate": 1.8166872254357771e-06, + "loss": 0.0028, + "step": 52517 + }, + { + "epoch": 16.22, + "learning_rate": 1.8163997943047108e-06, + "loss": 0.0025, + "step": 52518 + }, + { + "epoch": 16.22, + "learning_rate": 1.8161123836423188e-06, + "loss": 0.0023, + "step": 52519 + }, + { + "epoch": 16.22, + "learning_rate": 1.8158249934493255e-06, + "loss": 0.0036, + "step": 52520 + }, + { + "epoch": 16.22, + "learning_rate": 1.8155376237264443e-06, + "loss": 0.0017, + "step": 52521 + }, + { + "epoch": 16.22, + "learning_rate": 1.8152502744743982e-06, + "loss": 0.0018, + "step": 52522 + }, + { + "epoch": 16.22, + "learning_rate": 1.8149629456939044e-06, + "loss": 0.0022, + "step": 52523 + }, + { + "epoch": 16.22, + "learning_rate": 1.8146756373856778e-06, + "loss": 0.0021, + "step": 52524 + }, + { + "epoch": 16.22, + "learning_rate": 1.8143883495504411e-06, + "loss": 0.0015, + "step": 52525 + }, + { + "epoch": 16.22, + "learning_rate": 1.8141010821889138e-06, + "loss": 0.002, + "step": 52526 + }, + { + "epoch": 16.22, + "learning_rate": 1.813813835301811e-06, + "loss": 0.0026, + "step": 52527 + }, + { + "epoch": 16.22, + "learning_rate": 1.8135266088898552e-06, + "loss": 0.002, + "step": 52528 + }, + { + "epoch": 16.22, + "learning_rate": 1.8132394029537625e-06, + "loss": 0.002, + "step": 52529 + }, + { + "epoch": 16.22, + "learning_rate": 1.8129522174942482e-06, + "loss": 0.0019, + "step": 52530 + }, + { + "epoch": 16.22, + "learning_rate": 1.812665052512035e-06, + "loss": 0.0018, + "step": 52531 + }, + { + "epoch": 16.22, + "learning_rate": 1.8123779080078407e-06, + "loss": 0.0022, + "step": 52532 + }, + { + "epoch": 16.22, + "learning_rate": 1.8120907839823832e-06, + "loss": 0.0021, + "step": 52533 + }, + { + "epoch": 16.22, + "learning_rate": 1.8118036804363782e-06, + "loss": 0.0018, + "step": 52534 + }, + { + "epoch": 16.22, + "learning_rate": 1.8115165973705474e-06, + "loss": 0.0029, + "step": 52535 + }, + { + "epoch": 16.22, + "learning_rate": 1.8112295347856045e-06, + "loss": 0.0028, + "step": 52536 + }, + { + "epoch": 16.22, + "learning_rate": 1.8109424926822705e-06, + "loss": 0.0015, + "step": 52537 + }, + { + "epoch": 16.22, + "learning_rate": 1.8106554710612678e-06, + "loss": 0.002, + "step": 52538 + }, + { + "epoch": 16.22, + "learning_rate": 1.8103684699233037e-06, + "loss": 0.0019, + "step": 52539 + }, + { + "epoch": 16.23, + "learning_rate": 1.810081489269102e-06, + "loss": 0.0022, + "step": 52540 + }, + { + "epoch": 16.23, + "learning_rate": 1.8097945290993813e-06, + "loss": 0.0019, + "step": 52541 + }, + { + "epoch": 16.23, + "learning_rate": 1.8095075894148595e-06, + "loss": 0.0019, + "step": 52542 + }, + { + "epoch": 16.23, + "learning_rate": 1.809220670216254e-06, + "loss": 0.0021, + "step": 52543 + }, + { + "epoch": 16.23, + "learning_rate": 1.8089337715042787e-06, + "loss": 0.0018, + "step": 52544 + }, + { + "epoch": 16.23, + "learning_rate": 1.8086468932796563e-06, + "loss": 0.0021, + "step": 52545 + }, + { + "epoch": 16.23, + "learning_rate": 1.8083600355430996e-06, + "loss": 0.0017, + "step": 52546 + }, + { + "epoch": 16.23, + "learning_rate": 1.808073198295328e-06, + "loss": 0.0019, + "step": 52547 + }, + { + "epoch": 16.23, + "learning_rate": 1.8077863815370656e-06, + "loss": 0.0031, + "step": 52548 + }, + { + "epoch": 16.23, + "learning_rate": 1.807499585269018e-06, + "loss": 0.0022, + "step": 52549 + }, + { + "epoch": 16.23, + "learning_rate": 1.8072128094919083e-06, + "loss": 0.0025, + "step": 52550 + }, + { + "epoch": 16.23, + "learning_rate": 1.8069260542064559e-06, + "loss": 0.0019, + "step": 52551 + }, + { + "epoch": 16.23, + "learning_rate": 1.8066393194133735e-06, + "loss": 0.0026, + "step": 52552 + }, + { + "epoch": 16.23, + "learning_rate": 1.8063526051133829e-06, + "loss": 0.0019, + "step": 52553 + }, + { + "epoch": 16.23, + "learning_rate": 1.8060659113071988e-06, + "loss": 0.0022, + "step": 52554 + }, + { + "epoch": 16.23, + "learning_rate": 1.8057792379955364e-06, + "loss": 0.0023, + "step": 52555 + }, + { + "epoch": 16.23, + "learning_rate": 1.8054925851791138e-06, + "loss": 0.0027, + "step": 52556 + }, + { + "epoch": 16.23, + "learning_rate": 1.8052059528586518e-06, + "loss": 0.0019, + "step": 52557 + }, + { + "epoch": 16.23, + "learning_rate": 1.804919341034862e-06, + "loss": 0.0015, + "step": 52558 + }, + { + "epoch": 16.23, + "learning_rate": 1.804632749708466e-06, + "loss": 0.0022, + "step": 52559 + }, + { + "epoch": 16.23, + "learning_rate": 1.8043461788801774e-06, + "loss": 0.0024, + "step": 52560 + }, + { + "epoch": 16.23, + "learning_rate": 1.8040596285507117e-06, + "loss": 0.0027, + "step": 52561 + }, + { + "epoch": 16.23, + "learning_rate": 1.803773098720788e-06, + "loss": 0.0025, + "step": 52562 + }, + { + "epoch": 16.23, + "learning_rate": 1.8034865893911259e-06, + "loss": 0.0017, + "step": 52563 + }, + { + "epoch": 16.23, + "learning_rate": 1.8032001005624378e-06, + "loss": 0.0018, + "step": 52564 + }, + { + "epoch": 16.23, + "learning_rate": 1.802913632235439e-06, + "loss": 0.0023, + "step": 52565 + }, + { + "epoch": 16.23, + "learning_rate": 1.8026271844108513e-06, + "loss": 0.0017, + "step": 52566 + }, + { + "epoch": 16.23, + "learning_rate": 1.8023407570893847e-06, + "loss": 0.0018, + "step": 52567 + }, + { + "epoch": 16.23, + "learning_rate": 1.8020543502717592e-06, + "loss": 0.0019, + "step": 52568 + }, + { + "epoch": 16.23, + "learning_rate": 1.801767963958696e-06, + "loss": 0.0028, + "step": 52569 + }, + { + "epoch": 16.23, + "learning_rate": 1.8014815981509027e-06, + "loss": 0.002, + "step": 52570 + }, + { + "epoch": 16.23, + "learning_rate": 1.8011952528490973e-06, + "loss": 0.0021, + "step": 52571 + }, + { + "epoch": 16.24, + "learning_rate": 1.8009089280540015e-06, + "loss": 0.002, + "step": 52572 + }, + { + "epoch": 16.24, + "learning_rate": 1.8006226237663249e-06, + "loss": 0.0026, + "step": 52573 + }, + { + "epoch": 16.24, + "learning_rate": 1.8003363399867901e-06, + "loss": 0.002, + "step": 52574 + }, + { + "epoch": 16.24, + "learning_rate": 1.8000500767161067e-06, + "loss": 0.0019, + "step": 52575 + }, + { + "epoch": 16.24, + "learning_rate": 1.799763833954995e-06, + "loss": 0.0025, + "step": 52576 + }, + { + "epoch": 16.24, + "learning_rate": 1.799477611704168e-06, + "loss": 0.0016, + "step": 52577 + }, + { + "epoch": 16.24, + "learning_rate": 1.7991914099643438e-06, + "loss": 0.002, + "step": 52578 + }, + { + "epoch": 16.24, + "learning_rate": 1.7989052287362418e-06, + "loss": 0.0029, + "step": 52579 + }, + { + "epoch": 16.24, + "learning_rate": 1.7986190680205685e-06, + "loss": 0.0018, + "step": 52580 + }, + { + "epoch": 16.24, + "learning_rate": 1.798332927818045e-06, + "loss": 0.0022, + "step": 52581 + }, + { + "epoch": 16.24, + "learning_rate": 1.7980468081293889e-06, + "loss": 0.0019, + "step": 52582 + }, + { + "epoch": 16.24, + "learning_rate": 1.7977607089553117e-06, + "loss": 0.0023, + "step": 52583 + }, + { + "epoch": 16.24, + "learning_rate": 1.797474630296533e-06, + "loss": 0.002, + "step": 52584 + }, + { + "epoch": 16.24, + "learning_rate": 1.7971885721537674e-06, + "loss": 0.0018, + "step": 52585 + }, + { + "epoch": 16.24, + "learning_rate": 1.7969025345277259e-06, + "loss": 0.0035, + "step": 52586 + }, + { + "epoch": 16.24, + "learning_rate": 1.7966165174191275e-06, + "loss": 0.0026, + "step": 52587 + }, + { + "epoch": 16.24, + "learning_rate": 1.7963305208286896e-06, + "loss": 0.0027, + "step": 52588 + }, + { + "epoch": 16.24, + "learning_rate": 1.7960445447571251e-06, + "loss": 0.0019, + "step": 52589 + }, + { + "epoch": 16.24, + "learning_rate": 1.7957585892051476e-06, + "loss": 0.0018, + "step": 52590 + }, + { + "epoch": 16.24, + "learning_rate": 1.795472654173477e-06, + "loss": 0.0029, + "step": 52591 + }, + { + "epoch": 16.24, + "learning_rate": 1.795186739662822e-06, + "loss": 0.0014, + "step": 52592 + }, + { + "epoch": 16.24, + "learning_rate": 1.7949008456739025e-06, + "loss": 0.0016, + "step": 52593 + }, + { + "epoch": 16.24, + "learning_rate": 1.7946149722074346e-06, + "loss": 0.0023, + "step": 52594 + }, + { + "epoch": 16.24, + "learning_rate": 1.794329119264131e-06, + "loss": 0.0021, + "step": 52595 + }, + { + "epoch": 16.24, + "learning_rate": 1.7940432868447045e-06, + "loss": 0.0029, + "step": 52596 + }, + { + "epoch": 16.24, + "learning_rate": 1.7937574749498754e-06, + "loss": 0.0018, + "step": 52597 + }, + { + "epoch": 16.24, + "learning_rate": 1.7934716835803522e-06, + "loss": 0.0023, + "step": 52598 + }, + { + "epoch": 16.24, + "learning_rate": 1.7931859127368568e-06, + "loss": 0.002, + "step": 52599 + }, + { + "epoch": 16.24, + "learning_rate": 1.7929001624200993e-06, + "loss": 0.0018, + "step": 52600 + }, + { + "epoch": 16.24, + "learning_rate": 1.7926144326307937e-06, + "loss": 0.0017, + "step": 52601 + }, + { + "epoch": 16.24, + "learning_rate": 1.7923287233696552e-06, + "loss": 0.003, + "step": 52602 + }, + { + "epoch": 16.24, + "learning_rate": 1.7920430346374029e-06, + "loss": 0.0025, + "step": 52603 + }, + { + "epoch": 16.25, + "learning_rate": 1.7917573664347455e-06, + "loss": 0.0025, + "step": 52604 + }, + { + "epoch": 16.25, + "learning_rate": 1.791471718762402e-06, + "loss": 0.0024, + "step": 52605 + }, + { + "epoch": 16.25, + "learning_rate": 1.7911860916210822e-06, + "loss": 0.0018, + "step": 52606 + }, + { + "epoch": 16.25, + "learning_rate": 1.7909004850115063e-06, + "loss": 0.0015, + "step": 52607 + }, + { + "epoch": 16.25, + "learning_rate": 1.7906148989343831e-06, + "loss": 0.0014, + "step": 52608 + }, + { + "epoch": 16.25, + "learning_rate": 1.7903293333904314e-06, + "loss": 0.0026, + "step": 52609 + }, + { + "epoch": 16.25, + "learning_rate": 1.7900437883803644e-06, + "loss": 0.0018, + "step": 52610 + }, + { + "epoch": 16.25, + "learning_rate": 1.7897582639048916e-06, + "loss": 0.0022, + "step": 52611 + }, + { + "epoch": 16.25, + "learning_rate": 1.789472759964731e-06, + "loss": 0.0027, + "step": 52612 + }, + { + "epoch": 16.25, + "learning_rate": 1.7891872765606e-06, + "loss": 0.0026, + "step": 52613 + }, + { + "epoch": 16.25, + "learning_rate": 1.7889018136932057e-06, + "loss": 0.0025, + "step": 52614 + }, + { + "epoch": 16.25, + "learning_rate": 1.7886163713632676e-06, + "loss": 0.0018, + "step": 52615 + }, + { + "epoch": 16.25, + "learning_rate": 1.7883309495714985e-06, + "loss": 0.0022, + "step": 52616 + }, + { + "epoch": 16.25, + "learning_rate": 1.7880455483186088e-06, + "loss": 0.0027, + "step": 52617 + }, + { + "epoch": 16.25, + "learning_rate": 1.7877601676053146e-06, + "loss": 0.0023, + "step": 52618 + }, + { + "epoch": 16.25, + "learning_rate": 1.7874748074323333e-06, + "loss": 0.0024, + "step": 52619 + }, + { + "epoch": 16.25, + "learning_rate": 1.7871894678003754e-06, + "loss": 0.0023, + "step": 52620 + }, + { + "epoch": 16.25, + "learning_rate": 1.7869041487101514e-06, + "loss": 0.002, + "step": 52621 + }, + { + "epoch": 16.25, + "learning_rate": 1.7866188501623804e-06, + "loss": 0.0019, + "step": 52622 + }, + { + "epoch": 16.25, + "learning_rate": 1.7863335721577713e-06, + "loss": 0.0026, + "step": 52623 + }, + { + "epoch": 16.25, + "learning_rate": 1.7860483146970408e-06, + "loss": 0.0026, + "step": 52624 + }, + { + "epoch": 16.25, + "learning_rate": 1.785763077780903e-06, + "loss": 0.0015, + "step": 52625 + }, + { + "epoch": 16.25, + "learning_rate": 1.785477861410071e-06, + "loss": 0.0019, + "step": 52626 + }, + { + "epoch": 16.25, + "learning_rate": 1.7851926655852536e-06, + "loss": 0.0025, + "step": 52627 + }, + { + "epoch": 16.25, + "learning_rate": 1.7849074903071717e-06, + "loss": 0.0018, + "step": 52628 + }, + { + "epoch": 16.25, + "learning_rate": 1.7846223355765303e-06, + "loss": 0.0026, + "step": 52629 + }, + { + "epoch": 16.25, + "learning_rate": 1.7843372013940496e-06, + "loss": 0.0021, + "step": 52630 + }, + { + "epoch": 16.25, + "learning_rate": 1.7840520877604405e-06, + "loss": 0.0017, + "step": 52631 + }, + { + "epoch": 16.25, + "learning_rate": 1.7837669946764135e-06, + "loss": 0.0022, + "step": 52632 + }, + { + "epoch": 16.25, + "learning_rate": 1.7834819221426836e-06, + "loss": 0.002, + "step": 52633 + }, + { + "epoch": 16.25, + "learning_rate": 1.7831968701599656e-06, + "loss": 0.0024, + "step": 52634 + }, + { + "epoch": 16.25, + "learning_rate": 1.782911838728969e-06, + "loss": 0.0019, + "step": 52635 + }, + { + "epoch": 16.25, + "learning_rate": 1.782626827850411e-06, + "loss": 0.002, + "step": 52636 + }, + { + "epoch": 16.26, + "learning_rate": 1.7823418375250024e-06, + "loss": 0.0018, + "step": 52637 + }, + { + "epoch": 16.26, + "learning_rate": 1.7820568677534534e-06, + "loss": 0.0021, + "step": 52638 + }, + { + "epoch": 16.26, + "learning_rate": 1.7817719185364779e-06, + "loss": 0.0025, + "step": 52639 + }, + { + "epoch": 16.26, + "learning_rate": 1.7814869898747933e-06, + "loss": 0.0018, + "step": 52640 + }, + { + "epoch": 16.26, + "learning_rate": 1.7812020817691078e-06, + "loss": 0.0023, + "step": 52641 + }, + { + "epoch": 16.26, + "learning_rate": 1.7809171942201331e-06, + "loss": 0.0016, + "step": 52642 + }, + { + "epoch": 16.26, + "learning_rate": 1.780632327228583e-06, + "loss": 0.0019, + "step": 52643 + }, + { + "epoch": 16.26, + "learning_rate": 1.7803474807951738e-06, + "loss": 0.0026, + "step": 52644 + }, + { + "epoch": 16.26, + "learning_rate": 1.7800626549206123e-06, + "loss": 0.002, + "step": 52645 + }, + { + "epoch": 16.26, + "learning_rate": 1.7797778496056151e-06, + "loss": 0.0016, + "step": 52646 + }, + { + "epoch": 16.26, + "learning_rate": 1.7794930648508934e-06, + "loss": 0.0023, + "step": 52647 + }, + { + "epoch": 16.26, + "learning_rate": 1.779208300657156e-06, + "loss": 0.0013, + "step": 52648 + }, + { + "epoch": 16.26, + "learning_rate": 1.7789235570251173e-06, + "loss": 0.0016, + "step": 52649 + }, + { + "epoch": 16.26, + "learning_rate": 1.7786388339554938e-06, + "loss": 0.0019, + "step": 52650 + }, + { + "epoch": 16.26, + "learning_rate": 1.7783541314489939e-06, + "loss": 0.0016, + "step": 52651 + }, + { + "epoch": 16.26, + "learning_rate": 1.7780694495063266e-06, + "loss": 0.0024, + "step": 52652 + }, + { + "epoch": 16.26, + "learning_rate": 1.7777847881282108e-06, + "loss": 0.0019, + "step": 52653 + }, + { + "epoch": 16.26, + "learning_rate": 1.777500147315352e-06, + "loss": 0.0022, + "step": 52654 + }, + { + "epoch": 16.26, + "learning_rate": 1.7772155270684644e-06, + "loss": 0.0021, + "step": 52655 + }, + { + "epoch": 16.26, + "learning_rate": 1.776930927388264e-06, + "loss": 0.0021, + "step": 52656 + }, + { + "epoch": 16.26, + "learning_rate": 1.7766463482754581e-06, + "loss": 0.0022, + "step": 52657 + }, + { + "epoch": 16.26, + "learning_rate": 1.7763617897307572e-06, + "loss": 0.0024, + "step": 52658 + }, + { + "epoch": 16.26, + "learning_rate": 1.7760772517548785e-06, + "loss": 0.0032, + "step": 52659 + }, + { + "epoch": 16.26, + "learning_rate": 1.7757927343485281e-06, + "loss": 0.0025, + "step": 52660 + }, + { + "epoch": 16.26, + "learning_rate": 1.7755082375124222e-06, + "loss": 0.0019, + "step": 52661 + }, + { + "epoch": 16.26, + "learning_rate": 1.77522376124727e-06, + "loss": 0.0017, + "step": 52662 + }, + { + "epoch": 16.26, + "learning_rate": 1.7749393055537811e-06, + "loss": 0.0016, + "step": 52663 + }, + { + "epoch": 16.26, + "learning_rate": 1.7746548704326694e-06, + "loss": 0.002, + "step": 52664 + }, + { + "epoch": 16.26, + "learning_rate": 1.7743704558846486e-06, + "loss": 0.0016, + "step": 52665 + }, + { + "epoch": 16.26, + "learning_rate": 1.7740860619104239e-06, + "loss": 0.0014, + "step": 52666 + }, + { + "epoch": 16.26, + "learning_rate": 1.7738016885107135e-06, + "loss": 0.0022, + "step": 52667 + }, + { + "epoch": 16.26, + "learning_rate": 1.7735173356862256e-06, + "loss": 0.002, + "step": 52668 + }, + { + "epoch": 16.27, + "learning_rate": 1.773233003437669e-06, + "loss": 0.0025, + "step": 52669 + }, + { + "epoch": 16.27, + "learning_rate": 1.7729486917657569e-06, + "loss": 0.0023, + "step": 52670 + }, + { + "epoch": 16.27, + "learning_rate": 1.7726644006712035e-06, + "loss": 0.0022, + "step": 52671 + }, + { + "epoch": 16.27, + "learning_rate": 1.7723801301547162e-06, + "loss": 0.002, + "step": 52672 + }, + { + "epoch": 16.27, + "learning_rate": 1.7720958802170052e-06, + "loss": 0.0023, + "step": 52673 + }, + { + "epoch": 16.27, + "learning_rate": 1.7718116508587824e-06, + "loss": 0.0023, + "step": 52674 + }, + { + "epoch": 16.27, + "learning_rate": 1.7715274420807615e-06, + "loss": 0.002, + "step": 52675 + }, + { + "epoch": 16.27, + "learning_rate": 1.77124325388365e-06, + "loss": 0.0019, + "step": 52676 + }, + { + "epoch": 16.27, + "learning_rate": 1.7709590862681614e-06, + "loss": 0.0014, + "step": 52677 + }, + { + "epoch": 16.27, + "learning_rate": 1.7706749392350054e-06, + "loss": 0.0016, + "step": 52678 + }, + { + "epoch": 16.27, + "learning_rate": 1.77039081278489e-06, + "loss": 0.0018, + "step": 52679 + }, + { + "epoch": 16.27, + "learning_rate": 1.7701067069185274e-06, + "loss": 0.0029, + "step": 52680 + }, + { + "epoch": 16.27, + "learning_rate": 1.769822621636632e-06, + "loss": 0.0019, + "step": 52681 + }, + { + "epoch": 16.27, + "learning_rate": 1.7695385569399114e-06, + "loss": 0.0015, + "step": 52682 + }, + { + "epoch": 16.27, + "learning_rate": 1.7692545128290738e-06, + "loss": 0.0022, + "step": 52683 + }, + { + "epoch": 16.27, + "learning_rate": 1.7689704893048344e-06, + "loss": 0.0028, + "step": 52684 + }, + { + "epoch": 16.27, + "learning_rate": 1.7686864863678975e-06, + "loss": 0.0027, + "step": 52685 + }, + { + "epoch": 16.27, + "learning_rate": 1.7684025040189778e-06, + "loss": 0.0018, + "step": 52686 + }, + { + "epoch": 16.27, + "learning_rate": 1.76811854225879e-06, + "loss": 0.002, + "step": 52687 + }, + { + "epoch": 16.27, + "learning_rate": 1.767834601088033e-06, + "loss": 0.0019, + "step": 52688 + }, + { + "epoch": 16.27, + "learning_rate": 1.7675506805074249e-06, + "loss": 0.0024, + "step": 52689 + }, + { + "epoch": 16.27, + "learning_rate": 1.7672667805176758e-06, + "loss": 0.0019, + "step": 52690 + }, + { + "epoch": 16.27, + "learning_rate": 1.7669829011194906e-06, + "loss": 0.0021, + "step": 52691 + }, + { + "epoch": 16.27, + "learning_rate": 1.7666990423135865e-06, + "loss": 0.0029, + "step": 52692 + }, + { + "epoch": 16.27, + "learning_rate": 1.7664152041006688e-06, + "loss": 0.002, + "step": 52693 + }, + { + "epoch": 16.27, + "learning_rate": 1.7661313864814466e-06, + "loss": 0.0018, + "step": 52694 + }, + { + "epoch": 16.27, + "learning_rate": 1.7658475894566306e-06, + "loss": 0.0022, + "step": 52695 + }, + { + "epoch": 16.27, + "learning_rate": 1.7655638130269348e-06, + "loss": 0.0027, + "step": 52696 + }, + { + "epoch": 16.27, + "learning_rate": 1.7652800571930662e-06, + "loss": 0.0026, + "step": 52697 + }, + { + "epoch": 16.27, + "learning_rate": 1.764996321955731e-06, + "loss": 0.0028, + "step": 52698 + }, + { + "epoch": 16.27, + "learning_rate": 1.764712607315645e-06, + "loss": 0.0031, + "step": 52699 + }, + { + "epoch": 16.27, + "learning_rate": 1.7644289132735115e-06, + "loss": 0.0023, + "step": 52700 + }, + { + "epoch": 16.28, + "learning_rate": 1.764145239830044e-06, + "loss": 0.0016, + "step": 52701 + }, + { + "epoch": 16.28, + "learning_rate": 1.7638615869859533e-06, + "loss": 0.0019, + "step": 52702 + }, + { + "epoch": 16.28, + "learning_rate": 1.7635779547419473e-06, + "loss": 0.0015, + "step": 52703 + }, + { + "epoch": 16.28, + "learning_rate": 1.7632943430987325e-06, + "loss": 0.0018, + "step": 52704 + }, + { + "epoch": 16.28, + "learning_rate": 1.7630107520570205e-06, + "loss": 0.0029, + "step": 52705 + }, + { + "epoch": 16.28, + "learning_rate": 1.762727181617524e-06, + "loss": 0.0025, + "step": 52706 + }, + { + "epoch": 16.28, + "learning_rate": 1.762443631780949e-06, + "loss": 0.002, + "step": 52707 + }, + { + "epoch": 16.28, + "learning_rate": 1.762160102548003e-06, + "loss": 0.0018, + "step": 52708 + }, + { + "epoch": 16.28, + "learning_rate": 1.7618765939193983e-06, + "loss": 0.0016, + "step": 52709 + }, + { + "epoch": 16.28, + "learning_rate": 1.7615931058958414e-06, + "loss": 0.0018, + "step": 52710 + }, + { + "epoch": 16.28, + "learning_rate": 1.7613096384780425e-06, + "loss": 0.0018, + "step": 52711 + }, + { + "epoch": 16.28, + "learning_rate": 1.7610261916667125e-06, + "loss": 0.0029, + "step": 52712 + }, + { + "epoch": 16.28, + "learning_rate": 1.7607427654625598e-06, + "loss": 0.0017, + "step": 52713 + }, + { + "epoch": 16.28, + "learning_rate": 1.760459359866289e-06, + "loss": 0.0024, + "step": 52714 + }, + { + "epoch": 16.28, + "learning_rate": 1.7601759748786152e-06, + "loss": 0.0027, + "step": 52715 + }, + { + "epoch": 16.28, + "learning_rate": 1.759892610500241e-06, + "loss": 0.0017, + "step": 52716 + }, + { + "epoch": 16.28, + "learning_rate": 1.759609266731881e-06, + "loss": 0.0014, + "step": 52717 + }, + { + "epoch": 16.28, + "learning_rate": 1.7593259435742416e-06, + "loss": 0.0019, + "step": 52718 + }, + { + "epoch": 16.28, + "learning_rate": 1.7590426410280281e-06, + "loss": 0.0022, + "step": 52719 + }, + { + "epoch": 16.28, + "learning_rate": 1.7587593590939523e-06, + "loss": 0.0025, + "step": 52720 + }, + { + "epoch": 16.28, + "learning_rate": 1.7584760977727244e-06, + "loss": 0.0015, + "step": 52721 + }, + { + "epoch": 16.28, + "learning_rate": 1.7581928570650485e-06, + "loss": 0.0019, + "step": 52722 + }, + { + "epoch": 16.28, + "learning_rate": 1.7579096369716386e-06, + "loss": 0.0017, + "step": 52723 + }, + { + "epoch": 16.28, + "learning_rate": 1.7576264374931995e-06, + "loss": 0.0019, + "step": 52724 + }, + { + "epoch": 16.28, + "learning_rate": 1.7573432586304385e-06, + "loss": 0.0013, + "step": 52725 + }, + { + "epoch": 16.28, + "learning_rate": 1.7570601003840638e-06, + "loss": 0.0019, + "step": 52726 + }, + { + "epoch": 16.28, + "learning_rate": 1.7567769627547893e-06, + "loss": 0.0021, + "step": 52727 + }, + { + "epoch": 16.28, + "learning_rate": 1.7564938457433178e-06, + "loss": 0.0021, + "step": 52728 + }, + { + "epoch": 16.28, + "learning_rate": 1.7562107493503567e-06, + "loss": 0.0017, + "step": 52729 + }, + { + "epoch": 16.28, + "learning_rate": 1.7559276735766184e-06, + "loss": 0.0019, + "step": 52730 + }, + { + "epoch": 16.28, + "learning_rate": 1.755644618422806e-06, + "loss": 0.0022, + "step": 52731 + }, + { + "epoch": 16.28, + "learning_rate": 1.7553615838896299e-06, + "loss": 0.0019, + "step": 52732 + }, + { + "epoch": 16.28, + "learning_rate": 1.7550785699778017e-06, + "loss": 0.002, + "step": 52733 + }, + { + "epoch": 16.29, + "learning_rate": 1.7547955766880253e-06, + "loss": 0.002, + "step": 52734 + }, + { + "epoch": 16.29, + "learning_rate": 1.7545126040210059e-06, + "loss": 0.0018, + "step": 52735 + }, + { + "epoch": 16.29, + "learning_rate": 1.7542296519774571e-06, + "loss": 0.0019, + "step": 52736 + }, + { + "epoch": 16.29, + "learning_rate": 1.7539467205580818e-06, + "loss": 0.0016, + "step": 52737 + }, + { + "epoch": 16.29, + "learning_rate": 1.7536638097635927e-06, + "loss": 0.0022, + "step": 52738 + }, + { + "epoch": 16.29, + "learning_rate": 1.7533809195946905e-06, + "loss": 0.0024, + "step": 52739 + }, + { + "epoch": 16.29, + "learning_rate": 1.75309805005209e-06, + "loss": 0.0023, + "step": 52740 + }, + { + "epoch": 16.29, + "learning_rate": 1.752815201136493e-06, + "loss": 0.0018, + "step": 52741 + }, + { + "epoch": 16.29, + "learning_rate": 1.75253237284861e-06, + "loss": 0.0018, + "step": 52742 + }, + { + "epoch": 16.29, + "learning_rate": 1.752249565189149e-06, + "loss": 0.0027, + "step": 52743 + }, + { + "epoch": 16.29, + "learning_rate": 1.7519667781588169e-06, + "loss": 0.0018, + "step": 52744 + }, + { + "epoch": 16.29, + "learning_rate": 1.751684011758318e-06, + "loss": 0.0014, + "step": 52745 + }, + { + "epoch": 16.29, + "learning_rate": 1.751401265988364e-06, + "loss": 0.0027, + "step": 52746 + }, + { + "epoch": 16.29, + "learning_rate": 1.7511185408496568e-06, + "loss": 0.002, + "step": 52747 + }, + { + "epoch": 16.29, + "learning_rate": 1.750835836342909e-06, + "loss": 0.002, + "step": 52748 + }, + { + "epoch": 16.29, + "learning_rate": 1.750553152468827e-06, + "loss": 0.003, + "step": 52749 + }, + { + "epoch": 16.29, + "learning_rate": 1.7502704892281119e-06, + "loss": 0.0018, + "step": 52750 + }, + { + "epoch": 16.29, + "learning_rate": 1.7499878466214758e-06, + "loss": 0.0028, + "step": 52751 + }, + { + "epoch": 16.29, + "learning_rate": 1.749705224649627e-06, + "loss": 0.0022, + "step": 52752 + }, + { + "epoch": 16.29, + "learning_rate": 1.7494226233132683e-06, + "loss": 0.0018, + "step": 52753 + }, + { + "epoch": 16.29, + "learning_rate": 1.74914004261311e-06, + "loss": 0.0023, + "step": 52754 + }, + { + "epoch": 16.29, + "learning_rate": 1.7488574825498572e-06, + "loss": 0.0022, + "step": 52755 + }, + { + "epoch": 16.29, + "learning_rate": 1.748574943124215e-06, + "loss": 0.0021, + "step": 52756 + }, + { + "epoch": 16.29, + "learning_rate": 1.7482924243368916e-06, + "loss": 0.0025, + "step": 52757 + }, + { + "epoch": 16.29, + "learning_rate": 1.7480099261885964e-06, + "loss": 0.0022, + "step": 52758 + }, + { + "epoch": 16.29, + "learning_rate": 1.7477274486800343e-06, + "loss": 0.0026, + "step": 52759 + }, + { + "epoch": 16.29, + "learning_rate": 1.7474449918119074e-06, + "loss": 0.002, + "step": 52760 + }, + { + "epoch": 16.29, + "learning_rate": 1.7471625555849281e-06, + "loss": 0.002, + "step": 52761 + }, + { + "epoch": 16.29, + "learning_rate": 1.746880139999798e-06, + "loss": 0.0012, + "step": 52762 + }, + { + "epoch": 16.29, + "learning_rate": 1.746597745057227e-06, + "loss": 0.0026, + "step": 52763 + }, + { + "epoch": 16.29, + "learning_rate": 1.7463153707579217e-06, + "loss": 0.0024, + "step": 52764 + }, + { + "epoch": 16.29, + "learning_rate": 1.7460330171025875e-06, + "loss": 0.0015, + "step": 52765 + }, + { + "epoch": 16.3, + "learning_rate": 1.745750684091928e-06, + "loss": 0.0024, + "step": 52766 + }, + { + "epoch": 16.3, + "learning_rate": 1.745468371726654e-06, + "loss": 0.0015, + "step": 52767 + }, + { + "epoch": 16.3, + "learning_rate": 1.7451860800074661e-06, + "loss": 0.0026, + "step": 52768 + }, + { + "epoch": 16.3, + "learning_rate": 1.7449038089350755e-06, + "loss": 0.003, + "step": 52769 + }, + { + "epoch": 16.3, + "learning_rate": 1.7446215585101845e-06, + "loss": 0.0018, + "step": 52770 + }, + { + "epoch": 16.3, + "learning_rate": 1.7443393287335031e-06, + "loss": 0.0019, + "step": 52771 + }, + { + "epoch": 16.3, + "learning_rate": 1.744057119605732e-06, + "loss": 0.0016, + "step": 52772 + }, + { + "epoch": 16.3, + "learning_rate": 1.7437749311275798e-06, + "loss": 0.0022, + "step": 52773 + }, + { + "epoch": 16.3, + "learning_rate": 1.7434927632997544e-06, + "loss": 0.0019, + "step": 52774 + }, + { + "epoch": 16.3, + "learning_rate": 1.74321061612296e-06, + "loss": 0.0015, + "step": 52775 + }, + { + "epoch": 16.3, + "learning_rate": 1.7429284895979004e-06, + "loss": 0.0021, + "step": 52776 + }, + { + "epoch": 16.3, + "learning_rate": 1.7426463837252839e-06, + "loss": 0.0023, + "step": 52777 + }, + { + "epoch": 16.3, + "learning_rate": 1.742364298505812e-06, + "loss": 0.0031, + "step": 52778 + }, + { + "epoch": 16.3, + "learning_rate": 1.7420822339401967e-06, + "loss": 0.0022, + "step": 52779 + }, + { + "epoch": 16.3, + "learning_rate": 1.7418001900291393e-06, + "loss": 0.0022, + "step": 52780 + }, + { + "epoch": 16.3, + "learning_rate": 1.7415181667733428e-06, + "loss": 0.0015, + "step": 52781 + }, + { + "epoch": 16.3, + "learning_rate": 1.7412361641735164e-06, + "loss": 0.0021, + "step": 52782 + }, + { + "epoch": 16.3, + "learning_rate": 1.7409541822303667e-06, + "loss": 0.0032, + "step": 52783 + }, + { + "epoch": 16.3, + "learning_rate": 1.7406722209445948e-06, + "loss": 0.0026, + "step": 52784 + }, + { + "epoch": 16.3, + "learning_rate": 1.7403902803169104e-06, + "loss": 0.0029, + "step": 52785 + }, + { + "epoch": 16.3, + "learning_rate": 1.7401083603480163e-06, + "loss": 0.0023, + "step": 52786 + }, + { + "epoch": 16.3, + "learning_rate": 1.7398264610386152e-06, + "loss": 0.0023, + "step": 52787 + }, + { + "epoch": 16.3, + "learning_rate": 1.739544582389414e-06, + "loss": 0.0016, + "step": 52788 + }, + { + "epoch": 16.3, + "learning_rate": 1.739262724401123e-06, + "loss": 0.0021, + "step": 52789 + }, + { + "epoch": 16.3, + "learning_rate": 1.7389808870744407e-06, + "loss": 0.0019, + "step": 52790 + }, + { + "epoch": 16.3, + "learning_rate": 1.7386990704100715e-06, + "loss": 0.0024, + "step": 52791 + }, + { + "epoch": 16.3, + "learning_rate": 1.7384172744087257e-06, + "loss": 0.0026, + "step": 52792 + }, + { + "epoch": 16.3, + "learning_rate": 1.738135499071103e-06, + "loss": 0.002, + "step": 52793 + }, + { + "epoch": 16.3, + "learning_rate": 1.7378537443979092e-06, + "loss": 0.0021, + "step": 52794 + }, + { + "epoch": 16.3, + "learning_rate": 1.7375720103898564e-06, + "loss": 0.0034, + "step": 52795 + }, + { + "epoch": 16.3, + "learning_rate": 1.7372902970476368e-06, + "loss": 0.0018, + "step": 52796 + }, + { + "epoch": 16.3, + "learning_rate": 1.7370086043719626e-06, + "loss": 0.0021, + "step": 52797 + }, + { + "epoch": 16.3, + "learning_rate": 1.7367269323635384e-06, + "loss": 0.0017, + "step": 52798 + }, + { + "epoch": 16.31, + "learning_rate": 1.7364452810230648e-06, + "loss": 0.0025, + "step": 52799 + }, + { + "epoch": 16.31, + "learning_rate": 1.7361636503512513e-06, + "loss": 0.0025, + "step": 52800 + }, + { + "epoch": 16.31, + "learning_rate": 1.7358820403487997e-06, + "loss": 0.0022, + "step": 52801 + }, + { + "epoch": 16.31, + "learning_rate": 1.7356004510164125e-06, + "loss": 0.0024, + "step": 52802 + }, + { + "epoch": 16.31, + "learning_rate": 1.735318882354795e-06, + "loss": 0.0015, + "step": 52803 + }, + { + "epoch": 16.31, + "learning_rate": 1.7350373343646532e-06, + "loss": 0.002, + "step": 52804 + }, + { + "epoch": 16.31, + "learning_rate": 1.7347558070466952e-06, + "loss": 0.0024, + "step": 52805 + }, + { + "epoch": 16.31, + "learning_rate": 1.7344743004016152e-06, + "loss": 0.0028, + "step": 52806 + }, + { + "epoch": 16.31, + "learning_rate": 1.7341928144301223e-06, + "loss": 0.0018, + "step": 52807 + }, + { + "epoch": 16.31, + "learning_rate": 1.733911349132924e-06, + "loss": 0.0018, + "step": 52808 + }, + { + "epoch": 16.31, + "learning_rate": 1.7336299045107175e-06, + "loss": 0.0022, + "step": 52809 + }, + { + "epoch": 16.31, + "learning_rate": 1.7333484805642132e-06, + "loss": 0.0022, + "step": 52810 + }, + { + "epoch": 16.31, + "learning_rate": 1.7330670772941128e-06, + "loss": 0.0016, + "step": 52811 + }, + { + "epoch": 16.31, + "learning_rate": 1.7327856947011168e-06, + "loss": 0.0021, + "step": 52812 + }, + { + "epoch": 16.31, + "learning_rate": 1.7325043327859303e-06, + "loss": 0.0017, + "step": 52813 + }, + { + "epoch": 16.31, + "learning_rate": 1.7322229915492627e-06, + "loss": 0.0019, + "step": 52814 + }, + { + "epoch": 16.31, + "learning_rate": 1.7319416709918091e-06, + "loss": 0.0018, + "step": 52815 + }, + { + "epoch": 16.31, + "learning_rate": 1.731660371114281e-06, + "loss": 0.002, + "step": 52816 + }, + { + "epoch": 16.31, + "learning_rate": 1.7313790919173779e-06, + "loss": 0.002, + "step": 52817 + }, + { + "epoch": 16.31, + "learning_rate": 1.7310978334018025e-06, + "loss": 0.0024, + "step": 52818 + }, + { + "epoch": 16.31, + "learning_rate": 1.7308165955682576e-06, + "loss": 0.0017, + "step": 52819 + }, + { + "epoch": 16.31, + "learning_rate": 1.7305353784174528e-06, + "loss": 0.0024, + "step": 52820 + }, + { + "epoch": 16.31, + "learning_rate": 1.7302541819500863e-06, + "loss": 0.0024, + "step": 52821 + }, + { + "epoch": 16.31, + "learning_rate": 1.7299730061668596e-06, + "loss": 0.0011, + "step": 52822 + }, + { + "epoch": 16.31, + "learning_rate": 1.7296918510684823e-06, + "loss": 0.0022, + "step": 52823 + }, + { + "epoch": 16.31, + "learning_rate": 1.7294107166556505e-06, + "loss": 0.0019, + "step": 52824 + }, + { + "epoch": 16.31, + "learning_rate": 1.7291296029290727e-06, + "loss": 0.0017, + "step": 52825 + }, + { + "epoch": 16.31, + "learning_rate": 1.7288485098894536e-06, + "loss": 0.0023, + "step": 52826 + }, + { + "epoch": 16.31, + "learning_rate": 1.7285674375374883e-06, + "loss": 0.0016, + "step": 52827 + }, + { + "epoch": 16.31, + "learning_rate": 1.7282863858738853e-06, + "loss": 0.0023, + "step": 52828 + }, + { + "epoch": 16.31, + "learning_rate": 1.728005354899348e-06, + "loss": 0.0028, + "step": 52829 + }, + { + "epoch": 16.31, + "learning_rate": 1.7277243446145764e-06, + "loss": 0.0024, + "step": 52830 + }, + { + "epoch": 16.32, + "learning_rate": 1.7274433550202773e-06, + "loss": 0.0025, + "step": 52831 + }, + { + "epoch": 16.32, + "learning_rate": 1.7271623861171505e-06, + "loss": 0.0017, + "step": 52832 + }, + { + "epoch": 16.32, + "learning_rate": 1.7268814379058973e-06, + "loss": 0.0023, + "step": 52833 + }, + { + "epoch": 16.32, + "learning_rate": 1.726600510387223e-06, + "loss": 0.0021, + "step": 52834 + }, + { + "epoch": 16.32, + "learning_rate": 1.7263196035618301e-06, + "loss": 0.0016, + "step": 52835 + }, + { + "epoch": 16.32, + "learning_rate": 1.726038717430425e-06, + "loss": 0.0017, + "step": 52836 + }, + { + "epoch": 16.32, + "learning_rate": 1.7257578519937013e-06, + "loss": 0.0024, + "step": 52837 + }, + { + "epoch": 16.32, + "learning_rate": 1.7254770072523664e-06, + "loss": 0.0023, + "step": 52838 + }, + { + "epoch": 16.32, + "learning_rate": 1.7251961832071252e-06, + "loss": 0.0018, + "step": 52839 + }, + { + "epoch": 16.32, + "learning_rate": 1.724915379858676e-06, + "loss": 0.002, + "step": 52840 + }, + { + "epoch": 16.32, + "learning_rate": 1.7246345972077238e-06, + "loss": 0.0024, + "step": 52841 + }, + { + "epoch": 16.32, + "learning_rate": 1.7243538352549706e-06, + "loss": 0.0035, + "step": 52842 + }, + { + "epoch": 16.32, + "learning_rate": 1.7240730940011153e-06, + "loss": 0.0018, + "step": 52843 + }, + { + "epoch": 16.32, + "learning_rate": 1.723792373446862e-06, + "loss": 0.0019, + "step": 52844 + }, + { + "epoch": 16.32, + "learning_rate": 1.723511673592917e-06, + "loss": 0.0019, + "step": 52845 + }, + { + "epoch": 16.32, + "learning_rate": 1.7232309944399784e-06, + "loss": 0.0018, + "step": 52846 + }, + { + "epoch": 16.32, + "learning_rate": 1.7229503359887456e-06, + "loss": 0.002, + "step": 52847 + }, + { + "epoch": 16.32, + "learning_rate": 1.7226696982399261e-06, + "loss": 0.0024, + "step": 52848 + }, + { + "epoch": 16.32, + "learning_rate": 1.7223890811942178e-06, + "loss": 0.002, + "step": 52849 + }, + { + "epoch": 16.32, + "learning_rate": 1.722108484852324e-06, + "loss": 0.002, + "step": 52850 + }, + { + "epoch": 16.32, + "learning_rate": 1.721827909214948e-06, + "loss": 0.0017, + "step": 52851 + }, + { + "epoch": 16.32, + "learning_rate": 1.721547354282792e-06, + "loss": 0.0016, + "step": 52852 + }, + { + "epoch": 16.32, + "learning_rate": 1.7212668200565518e-06, + "loss": 0.0025, + "step": 52853 + }, + { + "epoch": 16.32, + "learning_rate": 1.720986306536937e-06, + "loss": 0.0015, + "step": 52854 + }, + { + "epoch": 16.32, + "learning_rate": 1.7207058137246423e-06, + "loss": 0.0017, + "step": 52855 + }, + { + "epoch": 16.32, + "learning_rate": 1.7204253416203754e-06, + "loss": 0.0023, + "step": 52856 + }, + { + "epoch": 16.32, + "learning_rate": 1.7201448902248341e-06, + "loss": 0.002, + "step": 52857 + }, + { + "epoch": 16.32, + "learning_rate": 1.7198644595387193e-06, + "loss": 0.0022, + "step": 52858 + }, + { + "epoch": 16.32, + "learning_rate": 1.7195840495627326e-06, + "loss": 0.0022, + "step": 52859 + }, + { + "epoch": 16.32, + "learning_rate": 1.7193036602975787e-06, + "loss": 0.0016, + "step": 52860 + }, + { + "epoch": 16.32, + "learning_rate": 1.7190232917439553e-06, + "loss": 0.0023, + "step": 52861 + }, + { + "epoch": 16.32, + "learning_rate": 1.718742943902566e-06, + "loss": 0.002, + "step": 52862 + }, + { + "epoch": 16.33, + "learning_rate": 1.7184626167741126e-06, + "loss": 0.0025, + "step": 52863 + }, + { + "epoch": 16.33, + "learning_rate": 1.718182310359291e-06, + "loss": 0.002, + "step": 52864 + }, + { + "epoch": 16.33, + "learning_rate": 1.7179020246588064e-06, + "loss": 0.0025, + "step": 52865 + }, + { + "epoch": 16.33, + "learning_rate": 1.7176217596733625e-06, + "loss": 0.0018, + "step": 52866 + }, + { + "epoch": 16.33, + "learning_rate": 1.7173415154036565e-06, + "loss": 0.0022, + "step": 52867 + }, + { + "epoch": 16.33, + "learning_rate": 1.7170612918503871e-06, + "loss": 0.0015, + "step": 52868 + }, + { + "epoch": 16.33, + "learning_rate": 1.7167810890142589e-06, + "loss": 0.0017, + "step": 52869 + }, + { + "epoch": 16.33, + "learning_rate": 1.7165009068959738e-06, + "loss": 0.0026, + "step": 52870 + }, + { + "epoch": 16.33, + "learning_rate": 1.7162207454962287e-06, + "loss": 0.0023, + "step": 52871 + }, + { + "epoch": 16.33, + "learning_rate": 1.715940604815729e-06, + "loss": 0.002, + "step": 52872 + }, + { + "epoch": 16.33, + "learning_rate": 1.7156604848551727e-06, + "loss": 0.0014, + "step": 52873 + }, + { + "epoch": 16.33, + "learning_rate": 1.7153803856152572e-06, + "loss": 0.0017, + "step": 52874 + }, + { + "epoch": 16.33, + "learning_rate": 1.7151003070966876e-06, + "loss": 0.0018, + "step": 52875 + }, + { + "epoch": 16.33, + "learning_rate": 1.7148202493001653e-06, + "loss": 0.0028, + "step": 52876 + }, + { + "epoch": 16.33, + "learning_rate": 1.7145402122263889e-06, + "loss": 0.0029, + "step": 52877 + }, + { + "epoch": 16.33, + "learning_rate": 1.7142601958760552e-06, + "loss": 0.0016, + "step": 52878 + }, + { + "epoch": 16.33, + "learning_rate": 1.7139802002498707e-06, + "loss": 0.002, + "step": 52879 + }, + { + "epoch": 16.33, + "learning_rate": 1.7137002253485313e-06, + "loss": 0.0021, + "step": 52880 + }, + { + "epoch": 16.33, + "learning_rate": 1.7134202711727387e-06, + "loss": 0.0017, + "step": 52881 + }, + { + "epoch": 16.33, + "learning_rate": 1.7131403377231947e-06, + "loss": 0.0023, + "step": 52882 + }, + { + "epoch": 16.33, + "learning_rate": 1.7128604250005998e-06, + "loss": 0.0026, + "step": 52883 + }, + { + "epoch": 16.33, + "learning_rate": 1.7125805330056488e-06, + "loss": 0.0021, + "step": 52884 + }, + { + "epoch": 16.33, + "learning_rate": 1.7123006617390492e-06, + "loss": 0.0024, + "step": 52885 + }, + { + "epoch": 16.33, + "learning_rate": 1.7120208112014936e-06, + "loss": 0.0026, + "step": 52886 + }, + { + "epoch": 16.33, + "learning_rate": 1.711740981393688e-06, + "loss": 0.0023, + "step": 52887 + }, + { + "epoch": 16.33, + "learning_rate": 1.71146117231633e-06, + "loss": 0.0019, + "step": 52888 + }, + { + "epoch": 16.33, + "learning_rate": 1.7111813839701174e-06, + "loss": 0.0025, + "step": 52889 + }, + { + "epoch": 16.33, + "learning_rate": 1.7109016163557523e-06, + "loss": 0.0026, + "step": 52890 + }, + { + "epoch": 16.33, + "learning_rate": 1.710621869473935e-06, + "loss": 0.0022, + "step": 52891 + }, + { + "epoch": 16.33, + "learning_rate": 1.710342143325363e-06, + "loss": 0.0034, + "step": 52892 + }, + { + "epoch": 16.33, + "learning_rate": 1.71006243791074e-06, + "loss": 0.0025, + "step": 52893 + }, + { + "epoch": 16.33, + "learning_rate": 1.709782753230762e-06, + "loss": 0.0015, + "step": 52894 + }, + { + "epoch": 16.33, + "learning_rate": 1.7095030892861275e-06, + "loss": 0.0024, + "step": 52895 + }, + { + "epoch": 16.34, + "learning_rate": 1.709223446077537e-06, + "loss": 0.0033, + "step": 52896 + }, + { + "epoch": 16.34, + "learning_rate": 1.7089438236056943e-06, + "loss": 0.0016, + "step": 52897 + }, + { + "epoch": 16.34, + "learning_rate": 1.7086642218712945e-06, + "loss": 0.0024, + "step": 52898 + }, + { + "epoch": 16.34, + "learning_rate": 1.708384640875036e-06, + "loss": 0.0021, + "step": 52899 + }, + { + "epoch": 16.34, + "learning_rate": 1.7081050806176213e-06, + "loss": 0.0019, + "step": 52900 + }, + { + "epoch": 16.34, + "learning_rate": 1.7078255410997468e-06, + "loss": 0.0022, + "step": 52901 + }, + { + "epoch": 16.34, + "learning_rate": 1.7075460223221118e-06, + "loss": 0.0021, + "step": 52902 + }, + { + "epoch": 16.34, + "learning_rate": 1.7072665242854203e-06, + "loss": 0.0018, + "step": 52903 + }, + { + "epoch": 16.34, + "learning_rate": 1.7069870469903672e-06, + "loss": 0.0019, + "step": 52904 + }, + { + "epoch": 16.34, + "learning_rate": 1.7067075904376495e-06, + "loss": 0.0037, + "step": 52905 + }, + { + "epoch": 16.34, + "learning_rate": 1.7064281546279692e-06, + "loss": 0.0018, + "step": 52906 + }, + { + "epoch": 16.34, + "learning_rate": 1.7061487395620268e-06, + "loss": 0.002, + "step": 52907 + }, + { + "epoch": 16.34, + "learning_rate": 1.7058693452405183e-06, + "loss": 0.0016, + "step": 52908 + }, + { + "epoch": 16.34, + "learning_rate": 1.7055899716641422e-06, + "loss": 0.0021, + "step": 52909 + }, + { + "epoch": 16.34, + "learning_rate": 1.7053106188336e-06, + "loss": 0.0015, + "step": 52910 + }, + { + "epoch": 16.34, + "learning_rate": 1.7050312867495866e-06, + "loss": 0.0031, + "step": 52911 + }, + { + "epoch": 16.34, + "learning_rate": 1.7047519754128027e-06, + "loss": 0.0017, + "step": 52912 + }, + { + "epoch": 16.34, + "learning_rate": 1.7044726848239502e-06, + "loss": 0.0014, + "step": 52913 + }, + { + "epoch": 16.34, + "learning_rate": 1.7041934149837248e-06, + "loss": 0.0013, + "step": 52914 + }, + { + "epoch": 16.34, + "learning_rate": 1.7039141658928205e-06, + "loss": 0.0019, + "step": 52915 + }, + { + "epoch": 16.34, + "learning_rate": 1.7036349375519435e-06, + "loss": 0.002, + "step": 52916 + }, + { + "epoch": 16.34, + "learning_rate": 1.7033557299617865e-06, + "loss": 0.0022, + "step": 52917 + }, + { + "epoch": 16.34, + "learning_rate": 1.7030765431230523e-06, + "loss": 0.0021, + "step": 52918 + }, + { + "epoch": 16.34, + "learning_rate": 1.702797377036437e-06, + "loss": 0.0023, + "step": 52919 + }, + { + "epoch": 16.34, + "learning_rate": 1.7025182317026356e-06, + "loss": 0.0023, + "step": 52920 + }, + { + "epoch": 16.34, + "learning_rate": 1.702239107122351e-06, + "loss": 0.0039, + "step": 52921 + }, + { + "epoch": 16.34, + "learning_rate": 1.7019600032962814e-06, + "loss": 0.0024, + "step": 52922 + }, + { + "epoch": 16.34, + "learning_rate": 1.7016809202251206e-06, + "loss": 0.0027, + "step": 52923 + }, + { + "epoch": 16.34, + "learning_rate": 1.7014018579095715e-06, + "loss": 0.0019, + "step": 52924 + }, + { + "epoch": 16.34, + "learning_rate": 1.7011228163503302e-06, + "loss": 0.0026, + "step": 52925 + }, + { + "epoch": 16.34, + "learning_rate": 1.7008437955480915e-06, + "loss": 0.0033, + "step": 52926 + }, + { + "epoch": 16.34, + "learning_rate": 1.7005647955035577e-06, + "loss": 0.0017, + "step": 52927 + }, + { + "epoch": 16.35, + "learning_rate": 1.7002858162174262e-06, + "loss": 0.0016, + "step": 52928 + }, + { + "epoch": 16.35, + "learning_rate": 1.700006857690394e-06, + "loss": 0.0023, + "step": 52929 + }, + { + "epoch": 16.35, + "learning_rate": 1.6997279199231553e-06, + "loss": 0.0017, + "step": 52930 + }, + { + "epoch": 16.35, + "learning_rate": 1.6994490029164145e-06, + "loss": 0.0019, + "step": 52931 + }, + { + "epoch": 16.35, + "learning_rate": 1.6991701066708632e-06, + "loss": 0.002, + "step": 52932 + }, + { + "epoch": 16.35, + "learning_rate": 1.6988912311872009e-06, + "loss": 0.002, + "step": 52933 + }, + { + "epoch": 16.35, + "learning_rate": 1.6986123764661277e-06, + "loss": 0.0023, + "step": 52934 + }, + { + "epoch": 16.35, + "learning_rate": 1.6983335425083403e-06, + "loss": 0.0014, + "step": 52935 + }, + { + "epoch": 16.35, + "learning_rate": 1.6980547293145312e-06, + "loss": 0.0024, + "step": 52936 + }, + { + "epoch": 16.35, + "learning_rate": 1.6977759368854019e-06, + "loss": 0.0024, + "step": 52937 + }, + { + "epoch": 16.35, + "learning_rate": 1.697497165221652e-06, + "loss": 0.0029, + "step": 52938 + }, + { + "epoch": 16.35, + "learning_rate": 1.6972184143239756e-06, + "loss": 0.0012, + "step": 52939 + }, + { + "epoch": 16.35, + "learning_rate": 1.6969396841930674e-06, + "loss": 0.002, + "step": 52940 + }, + { + "epoch": 16.35, + "learning_rate": 1.6966609748296303e-06, + "loss": 0.0017, + "step": 52941 + }, + { + "epoch": 16.35, + "learning_rate": 1.6963822862343559e-06, + "loss": 0.0016, + "step": 52942 + }, + { + "epoch": 16.35, + "learning_rate": 1.696103618407945e-06, + "loss": 0.0024, + "step": 52943 + }, + { + "epoch": 16.35, + "learning_rate": 1.6958249713510966e-06, + "loss": 0.002, + "step": 52944 + }, + { + "epoch": 16.35, + "learning_rate": 1.6955463450645005e-06, + "loss": 0.0022, + "step": 52945 + }, + { + "epoch": 16.35, + "learning_rate": 1.6952677395488581e-06, + "loss": 0.0022, + "step": 52946 + }, + { + "epoch": 16.35, + "learning_rate": 1.694989154804868e-06, + "loss": 0.0017, + "step": 52947 + }, + { + "epoch": 16.35, + "learning_rate": 1.6947105908332218e-06, + "loss": 0.002, + "step": 52948 + }, + { + "epoch": 16.35, + "learning_rate": 1.6944320476346222e-06, + "loss": 0.003, + "step": 52949 + }, + { + "epoch": 16.35, + "learning_rate": 1.6941535252097619e-06, + "loss": 0.0021, + "step": 52950 + }, + { + "epoch": 16.35, + "learning_rate": 1.693875023559337e-06, + "loss": 0.0019, + "step": 52951 + }, + { + "epoch": 16.35, + "learning_rate": 1.693596542684045e-06, + "loss": 0.0016, + "step": 52952 + }, + { + "epoch": 16.35, + "learning_rate": 1.6933180825845862e-06, + "loss": 0.0026, + "step": 52953 + }, + { + "epoch": 16.35, + "learning_rate": 1.6930396432616536e-06, + "loss": 0.0024, + "step": 52954 + }, + { + "epoch": 16.35, + "learning_rate": 1.692761224715942e-06, + "loss": 0.0022, + "step": 52955 + }, + { + "epoch": 16.35, + "learning_rate": 1.692482826948152e-06, + "loss": 0.0039, + "step": 52956 + }, + { + "epoch": 16.35, + "learning_rate": 1.692204449958974e-06, + "loss": 0.0024, + "step": 52957 + }, + { + "epoch": 16.35, + "learning_rate": 1.691926093749109e-06, + "loss": 0.003, + "step": 52958 + }, + { + "epoch": 16.35, + "learning_rate": 1.6916477583192548e-06, + "loss": 0.0016, + "step": 52959 + }, + { + "epoch": 16.36, + "learning_rate": 1.6913694436701045e-06, + "loss": 0.0026, + "step": 52960 + }, + { + "epoch": 16.36, + "learning_rate": 1.691091149802352e-06, + "loss": 0.0026, + "step": 52961 + }, + { + "epoch": 16.36, + "learning_rate": 1.6908128767166986e-06, + "loss": 0.0021, + "step": 52962 + }, + { + "epoch": 16.36, + "learning_rate": 1.6905346244138355e-06, + "loss": 0.0026, + "step": 52963 + }, + { + "epoch": 16.36, + "learning_rate": 1.6902563928944627e-06, + "loss": 0.0018, + "step": 52964 + }, + { + "epoch": 16.36, + "learning_rate": 1.6899781821592741e-06, + "loss": 0.0014, + "step": 52965 + }, + { + "epoch": 16.36, + "learning_rate": 1.6896999922089642e-06, + "loss": 0.0022, + "step": 52966 + }, + { + "epoch": 16.36, + "learning_rate": 1.6894218230442295e-06, + "loss": 0.0026, + "step": 52967 + }, + { + "epoch": 16.36, + "learning_rate": 1.6891436746657674e-06, + "loss": 0.0022, + "step": 52968 + }, + { + "epoch": 16.36, + "learning_rate": 1.6888655470742743e-06, + "loss": 0.0023, + "step": 52969 + }, + { + "epoch": 16.36, + "learning_rate": 1.688587440270445e-06, + "loss": 0.0024, + "step": 52970 + }, + { + "epoch": 16.36, + "learning_rate": 1.6883093542549722e-06, + "loss": 0.0022, + "step": 52971 + }, + { + "epoch": 16.36, + "learning_rate": 1.6880312890285555e-06, + "loss": 0.0015, + "step": 52972 + }, + { + "epoch": 16.36, + "learning_rate": 1.6877532445918865e-06, + "loss": 0.002, + "step": 52973 + }, + { + "epoch": 16.36, + "learning_rate": 1.6874752209456647e-06, + "loss": 0.003, + "step": 52974 + }, + { + "epoch": 16.36, + "learning_rate": 1.6871972180905838e-06, + "loss": 0.0019, + "step": 52975 + }, + { + "epoch": 16.36, + "learning_rate": 1.6869192360273367e-06, + "loss": 0.0018, + "step": 52976 + }, + { + "epoch": 16.36, + "learning_rate": 1.6866412747566197e-06, + "loss": 0.0019, + "step": 52977 + }, + { + "epoch": 16.36, + "learning_rate": 1.686363334279133e-06, + "loss": 0.003, + "step": 52978 + }, + { + "epoch": 16.36, + "learning_rate": 1.686085414595564e-06, + "loss": 0.0016, + "step": 52979 + }, + { + "epoch": 16.36, + "learning_rate": 1.6858075157066157e-06, + "loss": 0.0016, + "step": 52980 + }, + { + "epoch": 16.36, + "learning_rate": 1.685529637612978e-06, + "loss": 0.0022, + "step": 52981 + }, + { + "epoch": 16.36, + "learning_rate": 1.6852517803153457e-06, + "loss": 0.0025, + "step": 52982 + }, + { + "epoch": 16.36, + "learning_rate": 1.6849739438144141e-06, + "loss": 0.0023, + "step": 52983 + }, + { + "epoch": 16.36, + "learning_rate": 1.684696128110882e-06, + "loss": 0.0026, + "step": 52984 + }, + { + "epoch": 16.36, + "learning_rate": 1.684418333205442e-06, + "loss": 0.0018, + "step": 52985 + }, + { + "epoch": 16.36, + "learning_rate": 1.6841405590987858e-06, + "loss": 0.0023, + "step": 52986 + }, + { + "epoch": 16.36, + "learning_rate": 1.6838628057916128e-06, + "loss": 0.0023, + "step": 52987 + }, + { + "epoch": 16.36, + "learning_rate": 1.6835850732846137e-06, + "loss": 0.0021, + "step": 52988 + }, + { + "epoch": 16.36, + "learning_rate": 1.6833073615784856e-06, + "loss": 0.0024, + "step": 52989 + }, + { + "epoch": 16.36, + "learning_rate": 1.6830296706739247e-06, + "loss": 0.0021, + "step": 52990 + }, + { + "epoch": 16.36, + "learning_rate": 1.6827520005716225e-06, + "loss": 0.0023, + "step": 52991 + }, + { + "epoch": 16.36, + "learning_rate": 1.682474351272273e-06, + "loss": 0.0017, + "step": 52992 + }, + { + "epoch": 16.37, + "learning_rate": 1.6821967227765746e-06, + "loss": 0.0021, + "step": 52993 + }, + { + "epoch": 16.37, + "learning_rate": 1.6819191150852176e-06, + "loss": 0.0014, + "step": 52994 + }, + { + "epoch": 16.37, + "learning_rate": 1.6816415281988996e-06, + "loss": 0.0017, + "step": 52995 + }, + { + "epoch": 16.37, + "learning_rate": 1.6813639621183132e-06, + "loss": 0.003, + "step": 52996 + }, + { + "epoch": 16.37, + "learning_rate": 1.6810864168441498e-06, + "loss": 0.0018, + "step": 52997 + }, + { + "epoch": 16.37, + "learning_rate": 1.680808892377107e-06, + "loss": 0.0021, + "step": 52998 + }, + { + "epoch": 16.37, + "learning_rate": 1.6805313887178799e-06, + "loss": 0.0026, + "step": 52999 + }, + { + "epoch": 16.37, + "learning_rate": 1.6802539058671618e-06, + "loss": 0.0025, + "step": 53000 + }, + { + "epoch": 16.37, + "learning_rate": 1.6799764438256473e-06, + "loss": 0.0031, + "step": 53001 + }, + { + "epoch": 16.37, + "learning_rate": 1.6796990025940252e-06, + "loss": 0.0024, + "step": 53002 + }, + { + "epoch": 16.37, + "learning_rate": 1.6794215821729975e-06, + "loss": 0.002, + "step": 53003 + }, + { + "epoch": 16.37, + "learning_rate": 1.6791441825632504e-06, + "loss": 0.0018, + "step": 53004 + }, + { + "epoch": 16.37, + "learning_rate": 1.6788668037654843e-06, + "loss": 0.0025, + "step": 53005 + }, + { + "epoch": 16.37, + "learning_rate": 1.6785894457803897e-06, + "loss": 0.0015, + "step": 53006 + }, + { + "epoch": 16.37, + "learning_rate": 1.6783121086086584e-06, + "loss": 0.0028, + "step": 53007 + }, + { + "epoch": 16.37, + "learning_rate": 1.6780347922509865e-06, + "loss": 0.0017, + "step": 53008 + }, + { + "epoch": 16.37, + "learning_rate": 1.67775749670807e-06, + "loss": 0.0021, + "step": 53009 + }, + { + "epoch": 16.37, + "learning_rate": 1.6774802219805975e-06, + "loss": 0.0024, + "step": 53010 + }, + { + "epoch": 16.37, + "learning_rate": 1.677202968069267e-06, + "loss": 0.0021, + "step": 53011 + }, + { + "epoch": 16.37, + "learning_rate": 1.6769257349747693e-06, + "loss": 0.0023, + "step": 53012 + }, + { + "epoch": 16.37, + "learning_rate": 1.676648522697797e-06, + "loss": 0.0014, + "step": 53013 + }, + { + "epoch": 16.37, + "learning_rate": 1.676371331239044e-06, + "loss": 0.0028, + "step": 53014 + }, + { + "epoch": 16.37, + "learning_rate": 1.6760941605992075e-06, + "loss": 0.0024, + "step": 53015 + }, + { + "epoch": 16.37, + "learning_rate": 1.6758170107789772e-06, + "loss": 0.0014, + "step": 53016 + }, + { + "epoch": 16.37, + "learning_rate": 1.6755398817790446e-06, + "loss": 0.0028, + "step": 53017 + }, + { + "epoch": 16.37, + "learning_rate": 1.675262773600107e-06, + "loss": 0.0026, + "step": 53018 + }, + { + "epoch": 16.37, + "learning_rate": 1.6749856862428537e-06, + "loss": 0.0021, + "step": 53019 + }, + { + "epoch": 16.37, + "learning_rate": 1.6747086197079798e-06, + "loss": 0.0019, + "step": 53020 + }, + { + "epoch": 16.37, + "learning_rate": 1.6744315739961792e-06, + "loss": 0.0022, + "step": 53021 + }, + { + "epoch": 16.37, + "learning_rate": 1.6741545491081445e-06, + "loss": 0.0019, + "step": 53022 + }, + { + "epoch": 16.37, + "learning_rate": 1.6738775450445666e-06, + "loss": 0.0022, + "step": 53023 + }, + { + "epoch": 16.37, + "learning_rate": 1.67360056180614e-06, + "loss": 0.0027, + "step": 53024 + }, + { + "epoch": 16.38, + "learning_rate": 1.673323599393556e-06, + "loss": 0.0022, + "step": 53025 + }, + { + "epoch": 16.38, + "learning_rate": 1.67304665780751e-06, + "loss": 0.0025, + "step": 53026 + }, + { + "epoch": 16.38, + "learning_rate": 1.672769737048694e-06, + "loss": 0.0024, + "step": 53027 + }, + { + "epoch": 16.38, + "learning_rate": 1.6724928371177963e-06, + "loss": 0.0017, + "step": 53028 + }, + { + "epoch": 16.38, + "learning_rate": 1.672215958015513e-06, + "loss": 0.0027, + "step": 53029 + }, + { + "epoch": 16.38, + "learning_rate": 1.6719390997425388e-06, + "loss": 0.0027, + "step": 53030 + }, + { + "epoch": 16.38, + "learning_rate": 1.6716622622995616e-06, + "loss": 0.002, + "step": 53031 + }, + { + "epoch": 16.38, + "learning_rate": 1.6713854456872792e-06, + "loss": 0.0018, + "step": 53032 + }, + { + "epoch": 16.38, + "learning_rate": 1.6711086499063777e-06, + "loss": 0.0024, + "step": 53033 + }, + { + "epoch": 16.38, + "learning_rate": 1.6708318749575548e-06, + "loss": 0.002, + "step": 53034 + }, + { + "epoch": 16.38, + "learning_rate": 1.6705551208414982e-06, + "loss": 0.0016, + "step": 53035 + }, + { + "epoch": 16.38, + "learning_rate": 1.6702783875589058e-06, + "loss": 0.0023, + "step": 53036 + }, + { + "epoch": 16.38, + "learning_rate": 1.6700016751104653e-06, + "loss": 0.0029, + "step": 53037 + }, + { + "epoch": 16.38, + "learning_rate": 1.6697249834968676e-06, + "loss": 0.0018, + "step": 53038 + }, + { + "epoch": 16.38, + "learning_rate": 1.6694483127188076e-06, + "loss": 0.0022, + "step": 53039 + }, + { + "epoch": 16.38, + "learning_rate": 1.6691716627769795e-06, + "loss": 0.0017, + "step": 53040 + }, + { + "epoch": 16.38, + "learning_rate": 1.6688950336720689e-06, + "loss": 0.0021, + "step": 53041 + }, + { + "epoch": 16.38, + "learning_rate": 1.6686184254047744e-06, + "loss": 0.0021, + "step": 53042 + }, + { + "epoch": 16.38, + "learning_rate": 1.6683418379757843e-06, + "loss": 0.0021, + "step": 53043 + }, + { + "epoch": 16.38, + "learning_rate": 1.6680652713857893e-06, + "loss": 0.002, + "step": 53044 + }, + { + "epoch": 16.38, + "learning_rate": 1.6677887256354818e-06, + "loss": 0.0019, + "step": 53045 + }, + { + "epoch": 16.38, + "learning_rate": 1.6675122007255573e-06, + "loss": 0.0014, + "step": 53046 + }, + { + "epoch": 16.38, + "learning_rate": 1.6672356966567049e-06, + "loss": 0.0032, + "step": 53047 + }, + { + "epoch": 16.38, + "learning_rate": 1.666959213429613e-06, + "loss": 0.0015, + "step": 53048 + }, + { + "epoch": 16.38, + "learning_rate": 1.666682751044978e-06, + "loss": 0.0019, + "step": 53049 + }, + { + "epoch": 16.38, + "learning_rate": 1.6664063095034878e-06, + "loss": 0.0025, + "step": 53050 + }, + { + "epoch": 16.38, + "learning_rate": 1.6661298888058352e-06, + "loss": 0.0023, + "step": 53051 + }, + { + "epoch": 16.38, + "learning_rate": 1.6658534889527156e-06, + "loss": 0.0018, + "step": 53052 + }, + { + "epoch": 16.38, + "learning_rate": 1.6655771099448126e-06, + "loss": 0.0024, + "step": 53053 + }, + { + "epoch": 16.38, + "learning_rate": 1.6653007517828213e-06, + "loss": 0.0022, + "step": 53054 + }, + { + "epoch": 16.38, + "learning_rate": 1.6650244144674355e-06, + "loss": 0.0019, + "step": 53055 + }, + { + "epoch": 16.38, + "learning_rate": 1.6647480979993403e-06, + "loss": 0.0015, + "step": 53056 + }, + { + "epoch": 16.38, + "learning_rate": 1.664471802379234e-06, + "loss": 0.0021, + "step": 53057 + }, + { + "epoch": 16.39, + "learning_rate": 1.6641955276078036e-06, + "loss": 0.0022, + "step": 53058 + }, + { + "epoch": 16.39, + "learning_rate": 1.663919273685738e-06, + "loss": 0.0016, + "step": 53059 + }, + { + "epoch": 16.39, + "learning_rate": 1.6636430406137305e-06, + "loss": 0.0021, + "step": 53060 + }, + { + "epoch": 16.39, + "learning_rate": 1.6633668283924752e-06, + "loss": 0.003, + "step": 53061 + }, + { + "epoch": 16.39, + "learning_rate": 1.6630906370226596e-06, + "loss": 0.0029, + "step": 53062 + }, + { + "epoch": 16.39, + "learning_rate": 1.6628144665049728e-06, + "loss": 0.002, + "step": 53063 + }, + { + "epoch": 16.39, + "learning_rate": 1.6625383168401076e-06, + "loss": 0.0021, + "step": 53064 + }, + { + "epoch": 16.39, + "learning_rate": 1.662262188028757e-06, + "loss": 0.0015, + "step": 53065 + }, + { + "epoch": 16.39, + "learning_rate": 1.661986080071607e-06, + "loss": 0.0027, + "step": 53066 + }, + { + "epoch": 16.39, + "learning_rate": 1.6617099929693525e-06, + "loss": 0.0022, + "step": 53067 + }, + { + "epoch": 16.39, + "learning_rate": 1.661433926722682e-06, + "loss": 0.0027, + "step": 53068 + }, + { + "epoch": 16.39, + "learning_rate": 1.6611578813322847e-06, + "loss": 0.0026, + "step": 53069 + }, + { + "epoch": 16.39, + "learning_rate": 1.6608818567988517e-06, + "loss": 0.0019, + "step": 53070 + }, + { + "epoch": 16.39, + "learning_rate": 1.6606058531230773e-06, + "loss": 0.0023, + "step": 53071 + }, + { + "epoch": 16.39, + "learning_rate": 1.6603298703056459e-06, + "loss": 0.0021, + "step": 53072 + }, + { + "epoch": 16.39, + "learning_rate": 1.6600539083472523e-06, + "loss": 0.0021, + "step": 53073 + }, + { + "epoch": 16.39, + "learning_rate": 1.659777967248586e-06, + "loss": 0.0021, + "step": 53074 + }, + { + "epoch": 16.39, + "learning_rate": 1.6595020470103328e-06, + "loss": 0.002, + "step": 53075 + }, + { + "epoch": 16.39, + "learning_rate": 1.6592261476331872e-06, + "loss": 0.003, + "step": 53076 + }, + { + "epoch": 16.39, + "learning_rate": 1.6589502691178395e-06, + "loss": 0.0018, + "step": 53077 + }, + { + "epoch": 16.39, + "learning_rate": 1.65867441146498e-06, + "loss": 0.0022, + "step": 53078 + }, + { + "epoch": 16.39, + "learning_rate": 1.6583985746752928e-06, + "loss": 0.0029, + "step": 53079 + }, + { + "epoch": 16.39, + "learning_rate": 1.6581227587494764e-06, + "loss": 0.0019, + "step": 53080 + }, + { + "epoch": 16.39, + "learning_rate": 1.6578469636882132e-06, + "loss": 0.0023, + "step": 53081 + }, + { + "epoch": 16.39, + "learning_rate": 1.6575711894921965e-06, + "loss": 0.0025, + "step": 53082 + }, + { + "epoch": 16.39, + "learning_rate": 1.6572954361621208e-06, + "loss": 0.0018, + "step": 53083 + }, + { + "epoch": 16.39, + "learning_rate": 1.6570197036986658e-06, + "loss": 0.0018, + "step": 53084 + }, + { + "epoch": 16.39, + "learning_rate": 1.6567439921025252e-06, + "loss": 0.0023, + "step": 53085 + }, + { + "epoch": 16.39, + "learning_rate": 1.6564683013743933e-06, + "loss": 0.0018, + "step": 53086 + }, + { + "epoch": 16.39, + "learning_rate": 1.6561926315149534e-06, + "loss": 0.0022, + "step": 53087 + }, + { + "epoch": 16.39, + "learning_rate": 1.6559169825248988e-06, + "loss": 0.0033, + "step": 53088 + }, + { + "epoch": 16.39, + "learning_rate": 1.6556413544049188e-06, + "loss": 0.0024, + "step": 53089 + }, + { + "epoch": 16.4, + "learning_rate": 1.6553657471556995e-06, + "loss": 0.0023, + "step": 53090 + }, + { + "epoch": 16.4, + "learning_rate": 1.6550901607779323e-06, + "loss": 0.0015, + "step": 53091 + }, + { + "epoch": 16.4, + "learning_rate": 1.6548145952723083e-06, + "loss": 0.0026, + "step": 53092 + }, + { + "epoch": 16.4, + "learning_rate": 1.6545390506395154e-06, + "loss": 0.002, + "step": 53093 + }, + { + "epoch": 16.4, + "learning_rate": 1.6542635268802398e-06, + "loss": 0.0017, + "step": 53094 + }, + { + "epoch": 16.4, + "learning_rate": 1.6539880239951767e-06, + "loss": 0.0018, + "step": 53095 + }, + { + "epoch": 16.4, + "learning_rate": 1.6537125419850087e-06, + "loss": 0.0017, + "step": 53096 + }, + { + "epoch": 16.4, + "learning_rate": 1.6534370808504274e-06, + "loss": 0.0017, + "step": 53097 + }, + { + "epoch": 16.4, + "learning_rate": 1.6531616405921259e-06, + "loss": 0.0023, + "step": 53098 + }, + { + "epoch": 16.4, + "learning_rate": 1.6528862212107888e-06, + "loss": 0.0023, + "step": 53099 + }, + { + "epoch": 16.4, + "learning_rate": 1.6526108227071024e-06, + "loss": 0.0023, + "step": 53100 + }, + { + "epoch": 16.4, + "learning_rate": 1.6523354450817596e-06, + "loss": 0.0023, + "step": 53101 + }, + { + "epoch": 16.4, + "learning_rate": 1.652060088335451e-06, + "loss": 0.0024, + "step": 53102 + }, + { + "epoch": 16.4, + "learning_rate": 1.6517847524688623e-06, + "loss": 0.0019, + "step": 53103 + }, + { + "epoch": 16.4, + "learning_rate": 1.6515094374826813e-06, + "loss": 0.002, + "step": 53104 + }, + { + "epoch": 16.4, + "learning_rate": 1.651234143377599e-06, + "loss": 0.0016, + "step": 53105 + }, + { + "epoch": 16.4, + "learning_rate": 1.650958870154301e-06, + "loss": 0.002, + "step": 53106 + }, + { + "epoch": 16.4, + "learning_rate": 1.6506836178134766e-06, + "loss": 0.0023, + "step": 53107 + }, + { + "epoch": 16.4, + "learning_rate": 1.6504083863558185e-06, + "loss": 0.0021, + "step": 53108 + }, + { + "epoch": 16.4, + "learning_rate": 1.6501331757820126e-06, + "loss": 0.0025, + "step": 53109 + }, + { + "epoch": 16.4, + "learning_rate": 1.6498579860927433e-06, + "loss": 0.0021, + "step": 53110 + }, + { + "epoch": 16.4, + "learning_rate": 1.649582817288704e-06, + "loss": 0.0016, + "step": 53111 + }, + { + "epoch": 16.4, + "learning_rate": 1.64930766937058e-06, + "loss": 0.0014, + "step": 53112 + }, + { + "epoch": 16.4, + "learning_rate": 1.6490325423390619e-06, + "loss": 0.0022, + "step": 53113 + }, + { + "epoch": 16.4, + "learning_rate": 1.6487574361948377e-06, + "loss": 0.002, + "step": 53114 + }, + { + "epoch": 16.4, + "learning_rate": 1.6484823509385905e-06, + "loss": 0.0021, + "step": 53115 + }, + { + "epoch": 16.4, + "learning_rate": 1.648207286571013e-06, + "loss": 0.0019, + "step": 53116 + }, + { + "epoch": 16.4, + "learning_rate": 1.6479322430927947e-06, + "loss": 0.0025, + "step": 53117 + }, + { + "epoch": 16.4, + "learning_rate": 1.6476572205046192e-06, + "loss": 0.0016, + "step": 53118 + }, + { + "epoch": 16.4, + "learning_rate": 1.6473822188071785e-06, + "loss": 0.0026, + "step": 53119 + }, + { + "epoch": 16.4, + "learning_rate": 1.6471072380011578e-06, + "loss": 0.0022, + "step": 53120 + }, + { + "epoch": 16.4, + "learning_rate": 1.6468322780872425e-06, + "loss": 0.003, + "step": 53121 + }, + { + "epoch": 16.41, + "learning_rate": 1.6465573390661249e-06, + "loss": 0.0014, + "step": 53122 + }, + { + "epoch": 16.41, + "learning_rate": 1.646282420938492e-06, + "loss": 0.0027, + "step": 53123 + }, + { + "epoch": 16.41, + "learning_rate": 1.6460075237050311e-06, + "loss": 0.0019, + "step": 53124 + }, + { + "epoch": 16.41, + "learning_rate": 1.645732647366426e-06, + "loss": 0.0025, + "step": 53125 + }, + { + "epoch": 16.41, + "learning_rate": 1.6454577919233706e-06, + "loss": 0.0025, + "step": 53126 + }, + { + "epoch": 16.41, + "learning_rate": 1.6451829573765454e-06, + "loss": 0.002, + "step": 53127 + }, + { + "epoch": 16.41, + "learning_rate": 1.6449081437266424e-06, + "loss": 0.0029, + "step": 53128 + }, + { + "epoch": 16.41, + "learning_rate": 1.6446333509743496e-06, + "loss": 0.0022, + "step": 53129 + }, + { + "epoch": 16.41, + "learning_rate": 1.6443585791203541e-06, + "loss": 0.002, + "step": 53130 + }, + { + "epoch": 16.41, + "learning_rate": 1.6440838281653381e-06, + "loss": 0.002, + "step": 53131 + }, + { + "epoch": 16.41, + "learning_rate": 1.643809098109993e-06, + "loss": 0.0021, + "step": 53132 + }, + { + "epoch": 16.41, + "learning_rate": 1.643534388955007e-06, + "loss": 0.0025, + "step": 53133 + }, + { + "epoch": 16.41, + "learning_rate": 1.6432597007010664e-06, + "loss": 0.0018, + "step": 53134 + }, + { + "epoch": 16.41, + "learning_rate": 1.642985033348855e-06, + "loss": 0.0018, + "step": 53135 + }, + { + "epoch": 16.41, + "learning_rate": 1.6427103868990646e-06, + "loss": 0.0031, + "step": 53136 + }, + { + "epoch": 16.41, + "learning_rate": 1.6424357613523777e-06, + "loss": 0.002, + "step": 53137 + }, + { + "epoch": 16.41, + "learning_rate": 1.642161156709483e-06, + "loss": 0.0026, + "step": 53138 + }, + { + "epoch": 16.41, + "learning_rate": 1.6418865729710698e-06, + "loss": 0.0035, + "step": 53139 + }, + { + "epoch": 16.41, + "learning_rate": 1.641612010137823e-06, + "loss": 0.0018, + "step": 53140 + }, + { + "epoch": 16.41, + "learning_rate": 1.6413374682104265e-06, + "loss": 0.0022, + "step": 53141 + }, + { + "epoch": 16.41, + "learning_rate": 1.6410629471895723e-06, + "loss": 0.0022, + "step": 53142 + }, + { + "epoch": 16.41, + "learning_rate": 1.6407884470759417e-06, + "loss": 0.0021, + "step": 53143 + }, + { + "epoch": 16.41, + "learning_rate": 1.6405139678702264e-06, + "loss": 0.0023, + "step": 53144 + }, + { + "epoch": 16.41, + "learning_rate": 1.6402395095731093e-06, + "loss": 0.002, + "step": 53145 + }, + { + "epoch": 16.41, + "learning_rate": 1.6399650721852767e-06, + "loss": 0.0026, + "step": 53146 + }, + { + "epoch": 16.41, + "learning_rate": 1.6396906557074155e-06, + "loss": 0.0019, + "step": 53147 + }, + { + "epoch": 16.41, + "learning_rate": 1.6394162601402153e-06, + "loss": 0.0016, + "step": 53148 + }, + { + "epoch": 16.41, + "learning_rate": 1.6391418854843577e-06, + "loss": 0.0025, + "step": 53149 + }, + { + "epoch": 16.41, + "learning_rate": 1.6388675317405333e-06, + "loss": 0.0015, + "step": 53150 + }, + { + "epoch": 16.41, + "learning_rate": 1.6385931989094273e-06, + "loss": 0.0027, + "step": 53151 + }, + { + "epoch": 16.41, + "learning_rate": 1.638318886991721e-06, + "loss": 0.0015, + "step": 53152 + }, + { + "epoch": 16.41, + "learning_rate": 1.638044595988104e-06, + "loss": 0.0022, + "step": 53153 + }, + { + "epoch": 16.41, + "learning_rate": 1.6377703258992661e-06, + "loss": 0.0021, + "step": 53154 + }, + { + "epoch": 16.42, + "learning_rate": 1.6374960767258896e-06, + "loss": 0.0021, + "step": 53155 + }, + { + "epoch": 16.42, + "learning_rate": 1.6372218484686574e-06, + "loss": 0.0021, + "step": 53156 + }, + { + "epoch": 16.42, + "learning_rate": 1.6369476411282614e-06, + "loss": 0.0023, + "step": 53157 + }, + { + "epoch": 16.42, + "learning_rate": 1.636673454705383e-06, + "loss": 0.0019, + "step": 53158 + }, + { + "epoch": 16.42, + "learning_rate": 1.6363992892007097e-06, + "loss": 0.0021, + "step": 53159 + }, + { + "epoch": 16.42, + "learning_rate": 1.6361251446149284e-06, + "loss": 0.0022, + "step": 53160 + }, + { + "epoch": 16.42, + "learning_rate": 1.6358510209487244e-06, + "loss": 0.0022, + "step": 53161 + }, + { + "epoch": 16.42, + "learning_rate": 1.6355769182027803e-06, + "loss": 0.0026, + "step": 53162 + }, + { + "epoch": 16.42, + "learning_rate": 1.6353028363777834e-06, + "loss": 0.0022, + "step": 53163 + }, + { + "epoch": 16.42, + "learning_rate": 1.635028775474422e-06, + "loss": 0.0025, + "step": 53164 + }, + { + "epoch": 16.42, + "learning_rate": 1.6347547354933802e-06, + "loss": 0.0029, + "step": 53165 + }, + { + "epoch": 16.42, + "learning_rate": 1.6344807164353393e-06, + "loss": 0.0024, + "step": 53166 + }, + { + "epoch": 16.42, + "learning_rate": 1.6342067183009902e-06, + "loss": 0.0025, + "step": 53167 + }, + { + "epoch": 16.42, + "learning_rate": 1.6339327410910143e-06, + "loss": 0.0022, + "step": 53168 + }, + { + "epoch": 16.42, + "learning_rate": 1.633658784806098e-06, + "loss": 0.0027, + "step": 53169 + }, + { + "epoch": 16.42, + "learning_rate": 1.6333848494469296e-06, + "loss": 0.0021, + "step": 53170 + }, + { + "epoch": 16.42, + "learning_rate": 1.6331109350141917e-06, + "loss": 0.0021, + "step": 53171 + }, + { + "epoch": 16.42, + "learning_rate": 1.6328370415085658e-06, + "loss": 0.0017, + "step": 53172 + }, + { + "epoch": 16.42, + "learning_rate": 1.6325631689307442e-06, + "loss": 0.0019, + "step": 53173 + }, + { + "epoch": 16.42, + "learning_rate": 1.6322893172814059e-06, + "loss": 0.0018, + "step": 53174 + }, + { + "epoch": 16.42, + "learning_rate": 1.6320154865612403e-06, + "loss": 0.0025, + "step": 53175 + }, + { + "epoch": 16.42, + "learning_rate": 1.6317416767709304e-06, + "loss": 0.002, + "step": 53176 + }, + { + "epoch": 16.42, + "learning_rate": 1.6314678879111578e-06, + "loss": 0.0032, + "step": 53177 + }, + { + "epoch": 16.42, + "learning_rate": 1.6311941199826108e-06, + "loss": 0.003, + "step": 53178 + }, + { + "epoch": 16.42, + "learning_rate": 1.6309203729859757e-06, + "loss": 0.002, + "step": 53179 + }, + { + "epoch": 16.42, + "learning_rate": 1.630646646921934e-06, + "loss": 0.0019, + "step": 53180 + }, + { + "epoch": 16.42, + "learning_rate": 1.630372941791173e-06, + "loss": 0.0023, + "step": 53181 + }, + { + "epoch": 16.42, + "learning_rate": 1.6300992575943753e-06, + "loss": 0.0025, + "step": 53182 + }, + { + "epoch": 16.42, + "learning_rate": 1.6298255943322238e-06, + "loss": 0.0024, + "step": 53183 + }, + { + "epoch": 16.42, + "learning_rate": 1.629551952005406e-06, + "loss": 0.0027, + "step": 53184 + }, + { + "epoch": 16.42, + "learning_rate": 1.6292783306146064e-06, + "loss": 0.0022, + "step": 53185 + }, + { + "epoch": 16.42, + "learning_rate": 1.6290047301605093e-06, + "loss": 0.0019, + "step": 53186 + }, + { + "epoch": 16.43, + "learning_rate": 1.6287311506437964e-06, + "loss": 0.0021, + "step": 53187 + }, + { + "epoch": 16.43, + "learning_rate": 1.6284575920651547e-06, + "loss": 0.0022, + "step": 53188 + }, + { + "epoch": 16.43, + "learning_rate": 1.628184054425266e-06, + "loss": 0.0023, + "step": 53189 + }, + { + "epoch": 16.43, + "learning_rate": 1.6279105377248162e-06, + "loss": 0.002, + "step": 53190 + }, + { + "epoch": 16.43, + "learning_rate": 1.6276370419644926e-06, + "loss": 0.0021, + "step": 53191 + }, + { + "epoch": 16.43, + "learning_rate": 1.6273635671449718e-06, + "loss": 0.0022, + "step": 53192 + }, + { + "epoch": 16.43, + "learning_rate": 1.6270901132669415e-06, + "loss": 0.0024, + "step": 53193 + }, + { + "epoch": 16.43, + "learning_rate": 1.6268166803310893e-06, + "loss": 0.0026, + "step": 53194 + }, + { + "epoch": 16.43, + "learning_rate": 1.6265432683380922e-06, + "loss": 0.0026, + "step": 53195 + }, + { + "epoch": 16.43, + "learning_rate": 1.626269877288641e-06, + "loss": 0.002, + "step": 53196 + }, + { + "epoch": 16.43, + "learning_rate": 1.6259965071834128e-06, + "loss": 0.002, + "step": 53197 + }, + { + "epoch": 16.43, + "learning_rate": 1.625723158023097e-06, + "loss": 0.0017, + "step": 53198 + }, + { + "epoch": 16.43, + "learning_rate": 1.6254498298083733e-06, + "loss": 0.0019, + "step": 53199 + }, + { + "epoch": 16.43, + "learning_rate": 1.6251765225399262e-06, + "loss": 0.0022, + "step": 53200 + }, + { + "epoch": 16.43, + "learning_rate": 1.6249032362184458e-06, + "loss": 0.0014, + "step": 53201 + }, + { + "epoch": 16.43, + "learning_rate": 1.6246299708446045e-06, + "loss": 0.0024, + "step": 53202 + }, + { + "epoch": 16.43, + "learning_rate": 1.6243567264190918e-06, + "loss": 0.0028, + "step": 53203 + }, + { + "epoch": 16.43, + "learning_rate": 1.6240835029425917e-06, + "loss": 0.0024, + "step": 53204 + }, + { + "epoch": 16.43, + "learning_rate": 1.6238103004157857e-06, + "loss": 0.0021, + "step": 53205 + }, + { + "epoch": 16.43, + "learning_rate": 1.623537118839359e-06, + "loss": 0.0023, + "step": 53206 + }, + { + "epoch": 16.43, + "learning_rate": 1.623263958213994e-06, + "loss": 0.0026, + "step": 53207 + }, + { + "epoch": 16.43, + "learning_rate": 1.622990818540372e-06, + "loss": 0.0026, + "step": 53208 + }, + { + "epoch": 16.43, + "learning_rate": 1.6227176998191762e-06, + "loss": 0.0021, + "step": 53209 + }, + { + "epoch": 16.43, + "learning_rate": 1.6224446020510953e-06, + "loss": 0.0022, + "step": 53210 + }, + { + "epoch": 16.43, + "learning_rate": 1.6221715252368076e-06, + "loss": 0.0023, + "step": 53211 + }, + { + "epoch": 16.43, + "learning_rate": 1.6218984693769957e-06, + "loss": 0.0018, + "step": 53212 + }, + { + "epoch": 16.43, + "learning_rate": 1.6216254344723447e-06, + "loss": 0.0017, + "step": 53213 + }, + { + "epoch": 16.43, + "learning_rate": 1.6213524205235354e-06, + "loss": 0.0016, + "step": 53214 + }, + { + "epoch": 16.43, + "learning_rate": 1.6210794275312513e-06, + "loss": 0.0023, + "step": 53215 + }, + { + "epoch": 16.43, + "learning_rate": 1.6208064554961777e-06, + "loss": 0.0029, + "step": 53216 + }, + { + "epoch": 16.43, + "learning_rate": 1.6205335044189963e-06, + "loss": 0.0017, + "step": 53217 + }, + { + "epoch": 16.43, + "learning_rate": 1.6202605743003864e-06, + "loss": 0.0019, + "step": 53218 + }, + { + "epoch": 16.43, + "learning_rate": 1.6199876651410352e-06, + "loss": 0.0016, + "step": 53219 + }, + { + "epoch": 16.44, + "learning_rate": 1.619714776941621e-06, + "loss": 0.0021, + "step": 53220 + }, + { + "epoch": 16.44, + "learning_rate": 1.6194419097028313e-06, + "loss": 0.0028, + "step": 53221 + }, + { + "epoch": 16.44, + "learning_rate": 1.6191690634253454e-06, + "loss": 0.0023, + "step": 53222 + }, + { + "epoch": 16.44, + "learning_rate": 1.6188962381098439e-06, + "loss": 0.002, + "step": 53223 + }, + { + "epoch": 16.44, + "learning_rate": 1.6186234337570116e-06, + "loss": 0.0024, + "step": 53224 + }, + { + "epoch": 16.44, + "learning_rate": 1.6183506503675328e-06, + "loss": 0.0021, + "step": 53225 + }, + { + "epoch": 16.44, + "learning_rate": 1.6180778879420867e-06, + "loss": 0.0024, + "step": 53226 + }, + { + "epoch": 16.44, + "learning_rate": 1.6178051464813572e-06, + "loss": 0.0021, + "step": 53227 + }, + { + "epoch": 16.44, + "learning_rate": 1.6175324259860249e-06, + "loss": 0.0021, + "step": 53228 + }, + { + "epoch": 16.44, + "learning_rate": 1.6172597264567746e-06, + "loss": 0.002, + "step": 53229 + }, + { + "epoch": 16.44, + "learning_rate": 1.616987047894284e-06, + "loss": 0.0014, + "step": 53230 + }, + { + "epoch": 16.44, + "learning_rate": 1.616714390299241e-06, + "loss": 0.0015, + "step": 53231 + }, + { + "epoch": 16.44, + "learning_rate": 1.6164417536723231e-06, + "loss": 0.0027, + "step": 53232 + }, + { + "epoch": 16.44, + "learning_rate": 1.6161691380142119e-06, + "loss": 0.0016, + "step": 53233 + }, + { + "epoch": 16.44, + "learning_rate": 1.6158965433255903e-06, + "loss": 0.0028, + "step": 53234 + }, + { + "epoch": 16.44, + "learning_rate": 1.6156239696071442e-06, + "loss": 0.0024, + "step": 53235 + }, + { + "epoch": 16.44, + "learning_rate": 1.6153514168595485e-06, + "loss": 0.0018, + "step": 53236 + }, + { + "epoch": 16.44, + "learning_rate": 1.6150788850834897e-06, + "loss": 0.0019, + "step": 53237 + }, + { + "epoch": 16.44, + "learning_rate": 1.6148063742796494e-06, + "loss": 0.0029, + "step": 53238 + }, + { + "epoch": 16.44, + "learning_rate": 1.6145338844487045e-06, + "loss": 0.0028, + "step": 53239 + }, + { + "epoch": 16.44, + "learning_rate": 1.6142614155913404e-06, + "loss": 0.0027, + "step": 53240 + }, + { + "epoch": 16.44, + "learning_rate": 1.6139889677082398e-06, + "loss": 0.0019, + "step": 53241 + }, + { + "epoch": 16.44, + "learning_rate": 1.613716540800082e-06, + "loss": 0.0018, + "step": 53242 + }, + { + "epoch": 16.44, + "learning_rate": 1.6134441348675467e-06, + "loss": 0.0026, + "step": 53243 + }, + { + "epoch": 16.44, + "learning_rate": 1.6131717499113198e-06, + "loss": 0.0023, + "step": 53244 + }, + { + "epoch": 16.44, + "learning_rate": 1.6128993859320774e-06, + "loss": 0.0021, + "step": 53245 + }, + { + "epoch": 16.44, + "learning_rate": 1.6126270429305035e-06, + "loss": 0.0023, + "step": 53246 + }, + { + "epoch": 16.44, + "learning_rate": 1.612354720907282e-06, + "loss": 0.0018, + "step": 53247 + }, + { + "epoch": 16.44, + "learning_rate": 1.6120824198630902e-06, + "loss": 0.0019, + "step": 53248 + }, + { + "epoch": 16.44, + "learning_rate": 1.6118101397986085e-06, + "loss": 0.0021, + "step": 53249 + }, + { + "epoch": 16.44, + "learning_rate": 1.611537880714521e-06, + "loss": 0.0024, + "step": 53250 + }, + { + "epoch": 16.44, + "learning_rate": 1.611265642611506e-06, + "loss": 0.0023, + "step": 53251 + }, + { + "epoch": 16.45, + "learning_rate": 1.610993425490247e-06, + "loss": 0.002, + "step": 53252 + }, + { + "epoch": 16.45, + "learning_rate": 1.6107212293514241e-06, + "loss": 0.0016, + "step": 53253 + }, + { + "epoch": 16.45, + "learning_rate": 1.6104490541957151e-06, + "loss": 0.0019, + "step": 53254 + }, + { + "epoch": 16.45, + "learning_rate": 1.6101769000238032e-06, + "loss": 0.0024, + "step": 53255 + }, + { + "epoch": 16.45, + "learning_rate": 1.6099047668363709e-06, + "loss": 0.0026, + "step": 53256 + }, + { + "epoch": 16.45, + "learning_rate": 1.6096326546340957e-06, + "loss": 0.0025, + "step": 53257 + }, + { + "epoch": 16.45, + "learning_rate": 1.6093605634176611e-06, + "loss": 0.0024, + "step": 53258 + }, + { + "epoch": 16.45, + "learning_rate": 1.609088493187746e-06, + "loss": 0.0026, + "step": 53259 + }, + { + "epoch": 16.45, + "learning_rate": 1.6088164439450294e-06, + "loss": 0.002, + "step": 53260 + }, + { + "epoch": 16.45, + "learning_rate": 1.608544415690193e-06, + "loss": 0.0017, + "step": 53261 + }, + { + "epoch": 16.45, + "learning_rate": 1.6082724084239199e-06, + "loss": 0.0022, + "step": 53262 + }, + { + "epoch": 16.45, + "learning_rate": 1.608000422146887e-06, + "loss": 0.0027, + "step": 53263 + }, + { + "epoch": 16.45, + "learning_rate": 1.607728456859775e-06, + "loss": 0.0022, + "step": 53264 + }, + { + "epoch": 16.45, + "learning_rate": 1.6074565125632634e-06, + "loss": 0.002, + "step": 53265 + }, + { + "epoch": 16.45, + "learning_rate": 1.6071845892580373e-06, + "loss": 0.002, + "step": 53266 + }, + { + "epoch": 16.45, + "learning_rate": 1.6069126869447694e-06, + "loss": 0.0025, + "step": 53267 + }, + { + "epoch": 16.45, + "learning_rate": 1.6066408056241478e-06, + "loss": 0.0026, + "step": 53268 + }, + { + "epoch": 16.45, + "learning_rate": 1.6063689452968468e-06, + "loss": 0.0021, + "step": 53269 + }, + { + "epoch": 16.45, + "learning_rate": 1.6060971059635467e-06, + "loss": 0.0021, + "step": 53270 + }, + { + "epoch": 16.45, + "learning_rate": 1.605825287624928e-06, + "loss": 0.0016, + "step": 53271 + }, + { + "epoch": 16.45, + "learning_rate": 1.6055534902816738e-06, + "loss": 0.0014, + "step": 53272 + }, + { + "epoch": 16.45, + "learning_rate": 1.6052817139344624e-06, + "loss": 0.002, + "step": 53273 + }, + { + "epoch": 16.45, + "learning_rate": 1.6050099585839695e-06, + "loss": 0.003, + "step": 53274 + }, + { + "epoch": 16.45, + "learning_rate": 1.6047382242308796e-06, + "loss": 0.0022, + "step": 53275 + }, + { + "epoch": 16.45, + "learning_rate": 1.6044665108758684e-06, + "loss": 0.0042, + "step": 53276 + }, + { + "epoch": 16.45, + "learning_rate": 1.6041948185196177e-06, + "loss": 0.0023, + "step": 53277 + }, + { + "epoch": 16.45, + "learning_rate": 1.6039231471628103e-06, + "loss": 0.0022, + "step": 53278 + }, + { + "epoch": 16.45, + "learning_rate": 1.6036514968061223e-06, + "loss": 0.0021, + "step": 53279 + }, + { + "epoch": 16.45, + "learning_rate": 1.6033798674502299e-06, + "loss": 0.0029, + "step": 53280 + }, + { + "epoch": 16.45, + "learning_rate": 1.603108259095819e-06, + "loss": 0.0025, + "step": 53281 + }, + { + "epoch": 16.45, + "learning_rate": 1.6028366717435629e-06, + "loss": 0.0018, + "step": 53282 + }, + { + "epoch": 16.45, + "learning_rate": 1.6025651053941472e-06, + "loss": 0.0031, + "step": 53283 + }, + { + "epoch": 16.46, + "learning_rate": 1.602293560048247e-06, + "loss": 0.0023, + "step": 53284 + }, + { + "epoch": 16.46, + "learning_rate": 1.6020220357065397e-06, + "loss": 0.0027, + "step": 53285 + }, + { + "epoch": 16.46, + "learning_rate": 1.601750532369708e-06, + "loss": 0.0028, + "step": 53286 + }, + { + "epoch": 16.46, + "learning_rate": 1.6014790500384314e-06, + "loss": 0.0024, + "step": 53287 + }, + { + "epoch": 16.46, + "learning_rate": 1.601207588713385e-06, + "loss": 0.0024, + "step": 53288 + }, + { + "epoch": 16.46, + "learning_rate": 1.6009361483952536e-06, + "loss": 0.0038, + "step": 53289 + }, + { + "epoch": 16.46, + "learning_rate": 1.6006647290847122e-06, + "loss": 0.0024, + "step": 53290 + }, + { + "epoch": 16.46, + "learning_rate": 1.6003933307824381e-06, + "loss": 0.0023, + "step": 53291 + }, + { + "epoch": 16.46, + "learning_rate": 1.6001219534891122e-06, + "loss": 0.002, + "step": 53292 + }, + { + "epoch": 16.46, + "learning_rate": 1.5998505972054156e-06, + "loss": 0.0021, + "step": 53293 + }, + { + "epoch": 16.46, + "learning_rate": 1.599579261932025e-06, + "loss": 0.0012, + "step": 53294 + }, + { + "epoch": 16.46, + "learning_rate": 1.599307947669616e-06, + "loss": 0.0028, + "step": 53295 + }, + { + "epoch": 16.46, + "learning_rate": 1.5990366544188695e-06, + "loss": 0.0023, + "step": 53296 + }, + { + "epoch": 16.46, + "learning_rate": 1.5987653821804682e-06, + "loss": 0.0031, + "step": 53297 + }, + { + "epoch": 16.46, + "learning_rate": 1.598494130955084e-06, + "loss": 0.0037, + "step": 53298 + }, + { + "epoch": 16.46, + "learning_rate": 1.5982229007434002e-06, + "loss": 0.0022, + "step": 53299 + }, + { + "epoch": 16.46, + "learning_rate": 1.5979516915460946e-06, + "loss": 0.0026, + "step": 53300 + }, + { + "epoch": 16.46, + "learning_rate": 1.597680503363841e-06, + "loss": 0.0024, + "step": 53301 + }, + { + "epoch": 16.46, + "learning_rate": 1.597409336197321e-06, + "loss": 0.0023, + "step": 53302 + }, + { + "epoch": 16.46, + "learning_rate": 1.5971381900472149e-06, + "loss": 0.0026, + "step": 53303 + }, + { + "epoch": 16.46, + "learning_rate": 1.5968670649141993e-06, + "loss": 0.0018, + "step": 53304 + }, + { + "epoch": 16.46, + "learning_rate": 1.596595960798949e-06, + "loss": 0.0022, + "step": 53305 + }, + { + "epoch": 16.46, + "learning_rate": 1.5963248777021477e-06, + "loss": 0.0025, + "step": 53306 + }, + { + "epoch": 16.46, + "learning_rate": 1.5960538156244675e-06, + "loss": 0.0029, + "step": 53307 + }, + { + "epoch": 16.46, + "learning_rate": 1.595782774566591e-06, + "loss": 0.0023, + "step": 53308 + }, + { + "epoch": 16.46, + "learning_rate": 1.5955117545291977e-06, + "loss": 0.0015, + "step": 53309 + }, + { + "epoch": 16.46, + "learning_rate": 1.595240755512959e-06, + "loss": 0.0018, + "step": 53310 + }, + { + "epoch": 16.46, + "learning_rate": 1.5949697775185546e-06, + "loss": 0.0019, + "step": 53311 + }, + { + "epoch": 16.46, + "learning_rate": 1.5946988205466673e-06, + "loss": 0.0026, + "step": 53312 + }, + { + "epoch": 16.46, + "learning_rate": 1.594427884597969e-06, + "loss": 0.0016, + "step": 53313 + }, + { + "epoch": 16.46, + "learning_rate": 1.5941569696731407e-06, + "loss": 0.0018, + "step": 53314 + }, + { + "epoch": 16.46, + "learning_rate": 1.5938860757728603e-06, + "loss": 0.0025, + "step": 53315 + }, + { + "epoch": 16.46, + "learning_rate": 1.5936152028978013e-06, + "loss": 0.0017, + "step": 53316 + }, + { + "epoch": 16.47, + "learning_rate": 1.5933443510486435e-06, + "loss": 0.0022, + "step": 53317 + }, + { + "epoch": 16.47, + "learning_rate": 1.5930735202260673e-06, + "loss": 0.0023, + "step": 53318 + }, + { + "epoch": 16.47, + "learning_rate": 1.5928027104307486e-06, + "loss": 0.0022, + "step": 53319 + }, + { + "epoch": 16.47, + "learning_rate": 1.5925319216633594e-06, + "loss": 0.0026, + "step": 53320 + }, + { + "epoch": 16.47, + "learning_rate": 1.5922611539245847e-06, + "loss": 0.002, + "step": 53321 + }, + { + "epoch": 16.47, + "learning_rate": 1.591990407215096e-06, + "loss": 0.0023, + "step": 53322 + }, + { + "epoch": 16.47, + "learning_rate": 1.5917196815355729e-06, + "loss": 0.0016, + "step": 53323 + }, + { + "epoch": 16.47, + "learning_rate": 1.5914489768866948e-06, + "loss": 0.0024, + "step": 53324 + }, + { + "epoch": 16.47, + "learning_rate": 1.5911782932691367e-06, + "loss": 0.002, + "step": 53325 + }, + { + "epoch": 16.47, + "learning_rate": 1.5909076306835726e-06, + "loss": 0.0021, + "step": 53326 + }, + { + "epoch": 16.47, + "learning_rate": 1.5906369891306816e-06, + "loss": 0.0026, + "step": 53327 + }, + { + "epoch": 16.47, + "learning_rate": 1.5903663686111449e-06, + "loss": 0.0019, + "step": 53328 + }, + { + "epoch": 16.47, + "learning_rate": 1.5900957691256324e-06, + "loss": 0.0028, + "step": 53329 + }, + { + "epoch": 16.47, + "learning_rate": 1.5898251906748264e-06, + "loss": 0.0021, + "step": 53330 + }, + { + "epoch": 16.47, + "learning_rate": 1.5895546332594024e-06, + "loss": 0.0018, + "step": 53331 + }, + { + "epoch": 16.47, + "learning_rate": 1.5892840968800339e-06, + "loss": 0.0027, + "step": 53332 + }, + { + "epoch": 16.47, + "learning_rate": 1.5890135815373996e-06, + "loss": 0.0021, + "step": 53333 + }, + { + "epoch": 16.47, + "learning_rate": 1.5887430872321786e-06, + "loss": 0.002, + "step": 53334 + }, + { + "epoch": 16.47, + "learning_rate": 1.5884726139650452e-06, + "loss": 0.0025, + "step": 53335 + }, + { + "epoch": 16.47, + "learning_rate": 1.5882021617366739e-06, + "loss": 0.0024, + "step": 53336 + }, + { + "epoch": 16.47, + "learning_rate": 1.5879317305477448e-06, + "loss": 0.0022, + "step": 53337 + }, + { + "epoch": 16.47, + "learning_rate": 1.587661320398931e-06, + "loss": 0.0024, + "step": 53338 + }, + { + "epoch": 16.47, + "learning_rate": 1.5873909312909108e-06, + "loss": 0.0018, + "step": 53339 + }, + { + "epoch": 16.47, + "learning_rate": 1.5871205632243646e-06, + "loss": 0.0022, + "step": 53340 + }, + { + "epoch": 16.47, + "learning_rate": 1.58685021619996e-06, + "loss": 0.0022, + "step": 53341 + }, + { + "epoch": 16.47, + "learning_rate": 1.586579890218377e-06, + "loss": 0.0025, + "step": 53342 + }, + { + "epoch": 16.47, + "learning_rate": 1.5863095852802945e-06, + "loss": 0.0019, + "step": 53343 + }, + { + "epoch": 16.47, + "learning_rate": 1.586039301386384e-06, + "loss": 0.0019, + "step": 53344 + }, + { + "epoch": 16.47, + "learning_rate": 1.585769038537326e-06, + "loss": 0.0022, + "step": 53345 + }, + { + "epoch": 16.47, + "learning_rate": 1.5854987967337954e-06, + "loss": 0.0019, + "step": 53346 + }, + { + "epoch": 16.47, + "learning_rate": 1.585228575976463e-06, + "loss": 0.0021, + "step": 53347 + }, + { + "epoch": 16.47, + "learning_rate": 1.5849583762660103e-06, + "loss": 0.002, + "step": 53348 + }, + { + "epoch": 16.48, + "learning_rate": 1.5846881976031126e-06, + "loss": 0.0016, + "step": 53349 + }, + { + "epoch": 16.48, + "learning_rate": 1.5844180399884457e-06, + "loss": 0.002, + "step": 53350 + }, + { + "epoch": 16.48, + "learning_rate": 1.5841479034226803e-06, + "loss": 0.0018, + "step": 53351 + }, + { + "epoch": 16.48, + "learning_rate": 1.5838777879064993e-06, + "loss": 0.0025, + "step": 53352 + }, + { + "epoch": 16.48, + "learning_rate": 1.583607693440573e-06, + "loss": 0.0023, + "step": 53353 + }, + { + "epoch": 16.48, + "learning_rate": 1.5833376200255779e-06, + "loss": 0.0022, + "step": 53354 + }, + { + "epoch": 16.48, + "learning_rate": 1.5830675676621931e-06, + "loss": 0.002, + "step": 53355 + }, + { + "epoch": 16.48, + "learning_rate": 1.5827975363510927e-06, + "loss": 0.002, + "step": 53356 + }, + { + "epoch": 16.48, + "learning_rate": 1.5825275260929473e-06, + "loss": 0.0024, + "step": 53357 + }, + { + "epoch": 16.48, + "learning_rate": 1.5822575368884384e-06, + "loss": 0.0011, + "step": 53358 + }, + { + "epoch": 16.48, + "learning_rate": 1.5819875687382359e-06, + "loss": 0.0019, + "step": 53359 + }, + { + "epoch": 16.48, + "learning_rate": 1.5817176216430207e-06, + "loss": 0.002, + "step": 53360 + }, + { + "epoch": 16.48, + "learning_rate": 1.581447695603463e-06, + "loss": 0.0023, + "step": 53361 + }, + { + "epoch": 16.48, + "learning_rate": 1.5811777906202419e-06, + "loss": 0.0024, + "step": 53362 + }, + { + "epoch": 16.48, + "learning_rate": 1.5809079066940292e-06, + "loss": 0.0021, + "step": 53363 + }, + { + "epoch": 16.48, + "learning_rate": 1.5806380438254999e-06, + "loss": 0.0014, + "step": 53364 + }, + { + "epoch": 16.48, + "learning_rate": 1.5803682020153343e-06, + "loss": 0.0019, + "step": 53365 + }, + { + "epoch": 16.48, + "learning_rate": 1.5800983812642024e-06, + "loss": 0.002, + "step": 53366 + }, + { + "epoch": 16.48, + "learning_rate": 1.5798285815727788e-06, + "loss": 0.0019, + "step": 53367 + }, + { + "epoch": 16.48, + "learning_rate": 1.5795588029417407e-06, + "loss": 0.0016, + "step": 53368 + }, + { + "epoch": 16.48, + "learning_rate": 1.5792890453717603e-06, + "loss": 0.0022, + "step": 53369 + }, + { + "epoch": 16.48, + "learning_rate": 1.5790193088635164e-06, + "loss": 0.0019, + "step": 53370 + }, + { + "epoch": 16.48, + "learning_rate": 1.578749593417681e-06, + "loss": 0.0019, + "step": 53371 + }, + { + "epoch": 16.48, + "learning_rate": 1.578479899034926e-06, + "loss": 0.0023, + "step": 53372 + }, + { + "epoch": 16.48, + "learning_rate": 1.5782102257159283e-06, + "loss": 0.0026, + "step": 53373 + }, + { + "epoch": 16.48, + "learning_rate": 1.5779405734613662e-06, + "loss": 0.0022, + "step": 53374 + }, + { + "epoch": 16.48, + "learning_rate": 1.5776709422719084e-06, + "loss": 0.0018, + "step": 53375 + }, + { + "epoch": 16.48, + "learning_rate": 1.577401332148234e-06, + "loss": 0.0026, + "step": 53376 + }, + { + "epoch": 16.48, + "learning_rate": 1.577131743091015e-06, + "loss": 0.0022, + "step": 53377 + }, + { + "epoch": 16.48, + "learning_rate": 1.5768621751009227e-06, + "loss": 0.0015, + "step": 53378 + }, + { + "epoch": 16.48, + "learning_rate": 1.5765926281786348e-06, + "loss": 0.0023, + "step": 53379 + }, + { + "epoch": 16.48, + "learning_rate": 1.5763231023248282e-06, + "loss": 0.0023, + "step": 53380 + }, + { + "epoch": 16.49, + "learning_rate": 1.5760535975401726e-06, + "loss": 0.0022, + "step": 53381 + }, + { + "epoch": 16.49, + "learning_rate": 1.5757841138253416e-06, + "loss": 0.0019, + "step": 53382 + }, + { + "epoch": 16.49, + "learning_rate": 1.5755146511810138e-06, + "loss": 0.002, + "step": 53383 + }, + { + "epoch": 16.49, + "learning_rate": 1.5752452096078575e-06, + "loss": 0.0027, + "step": 53384 + }, + { + "epoch": 16.49, + "learning_rate": 1.5749757891065499e-06, + "loss": 0.0015, + "step": 53385 + }, + { + "epoch": 16.49, + "learning_rate": 1.574706389677767e-06, + "loss": 0.0025, + "step": 53386 + }, + { + "epoch": 16.49, + "learning_rate": 1.5744370113221796e-06, + "loss": 0.0025, + "step": 53387 + }, + { + "epoch": 16.49, + "learning_rate": 1.5741676540404593e-06, + "loss": 0.0022, + "step": 53388 + }, + { + "epoch": 16.49, + "learning_rate": 1.5738983178332856e-06, + "loss": 0.0024, + "step": 53389 + }, + { + "epoch": 16.49, + "learning_rate": 1.5736290027013268e-06, + "loss": 0.0018, + "step": 53390 + }, + { + "epoch": 16.49, + "learning_rate": 1.5733597086452602e-06, + "loss": 0.0026, + "step": 53391 + }, + { + "epoch": 16.49, + "learning_rate": 1.5730904356657562e-06, + "loss": 0.0047, + "step": 53392 + }, + { + "epoch": 16.49, + "learning_rate": 1.572821183763492e-06, + "loss": 0.0016, + "step": 53393 + }, + { + "epoch": 16.49, + "learning_rate": 1.5725519529391365e-06, + "loss": 0.0021, + "step": 53394 + }, + { + "epoch": 16.49, + "learning_rate": 1.5722827431933663e-06, + "loss": 0.0015, + "step": 53395 + }, + { + "epoch": 16.49, + "learning_rate": 1.5720135545268555e-06, + "loss": 0.0021, + "step": 53396 + }, + { + "epoch": 16.49, + "learning_rate": 1.571744386940277e-06, + "loss": 0.002, + "step": 53397 + }, + { + "epoch": 16.49, + "learning_rate": 1.5714752404343003e-06, + "loss": 0.0018, + "step": 53398 + }, + { + "epoch": 16.49, + "learning_rate": 1.5712061150096036e-06, + "loss": 0.0014, + "step": 53399 + }, + { + "epoch": 16.49, + "learning_rate": 1.5709370106668553e-06, + "loss": 0.0022, + "step": 53400 + }, + { + "epoch": 16.49, + "learning_rate": 1.5706679274067339e-06, + "loss": 0.0023, + "step": 53401 + }, + { + "epoch": 16.49, + "learning_rate": 1.5703988652299085e-06, + "loss": 0.0024, + "step": 53402 + }, + { + "epoch": 16.49, + "learning_rate": 1.570129824137051e-06, + "loss": 0.0018, + "step": 53403 + }, + { + "epoch": 16.49, + "learning_rate": 1.5698608041288355e-06, + "loss": 0.0038, + "step": 53404 + }, + { + "epoch": 16.49, + "learning_rate": 1.569591805205939e-06, + "loss": 0.0024, + "step": 53405 + }, + { + "epoch": 16.49, + "learning_rate": 1.5693228273690286e-06, + "loss": 0.0025, + "step": 53406 + }, + { + "epoch": 16.49, + "learning_rate": 1.5690538706187818e-06, + "loss": 0.0019, + "step": 53407 + }, + { + "epoch": 16.49, + "learning_rate": 1.5687849349558692e-06, + "loss": 0.0033, + "step": 53408 + }, + { + "epoch": 16.49, + "learning_rate": 1.5685160203809602e-06, + "loss": 0.0026, + "step": 53409 + }, + { + "epoch": 16.49, + "learning_rate": 1.5682471268947308e-06, + "loss": 0.0023, + "step": 53410 + }, + { + "epoch": 16.49, + "learning_rate": 1.567978254497856e-06, + "loss": 0.0023, + "step": 53411 + }, + { + "epoch": 16.49, + "learning_rate": 1.5677094031910046e-06, + "loss": 0.0025, + "step": 53412 + }, + { + "epoch": 16.49, + "learning_rate": 1.5674405729748477e-06, + "loss": 0.0017, + "step": 53413 + }, + { + "epoch": 16.5, + "learning_rate": 1.5671717638500627e-06, + "loss": 0.0023, + "step": 53414 + }, + { + "epoch": 16.5, + "learning_rate": 1.566902975817317e-06, + "loss": 0.0026, + "step": 53415 + }, + { + "epoch": 16.5, + "learning_rate": 1.5666342088772845e-06, + "loss": 0.002, + "step": 53416 + }, + { + "epoch": 16.5, + "learning_rate": 1.5663654630306413e-06, + "loss": 0.0017, + "step": 53417 + }, + { + "epoch": 16.5, + "learning_rate": 1.5660967382780557e-06, + "loss": 0.0022, + "step": 53418 + }, + { + "epoch": 16.5, + "learning_rate": 1.565828034620197e-06, + "loss": 0.0018, + "step": 53419 + }, + { + "epoch": 16.5, + "learning_rate": 1.565559352057745e-06, + "loss": 0.0018, + "step": 53420 + }, + { + "epoch": 16.5, + "learning_rate": 1.5652906905913634e-06, + "loss": 0.0017, + "step": 53421 + }, + { + "epoch": 16.5, + "learning_rate": 1.5650220502217316e-06, + "loss": 0.0025, + "step": 53422 + }, + { + "epoch": 16.5, + "learning_rate": 1.5647534309495172e-06, + "loss": 0.0022, + "step": 53423 + }, + { + "epoch": 16.5, + "learning_rate": 1.5644848327753914e-06, + "loss": 0.0032, + "step": 53424 + }, + { + "epoch": 16.5, + "learning_rate": 1.5642162557000274e-06, + "loss": 0.0025, + "step": 53425 + }, + { + "epoch": 16.5, + "learning_rate": 1.5639476997240966e-06, + "loss": 0.0012, + "step": 53426 + }, + { + "epoch": 16.5, + "learning_rate": 1.563679164848274e-06, + "loss": 0.0024, + "step": 53427 + }, + { + "epoch": 16.5, + "learning_rate": 1.5634106510732282e-06, + "loss": 0.0021, + "step": 53428 + }, + { + "epoch": 16.5, + "learning_rate": 1.5631421583996299e-06, + "loss": 0.0017, + "step": 53429 + }, + { + "epoch": 16.5, + "learning_rate": 1.5628736868281525e-06, + "loss": 0.0022, + "step": 53430 + }, + { + "epoch": 16.5, + "learning_rate": 1.5626052363594658e-06, + "loss": 0.0017, + "step": 53431 + }, + { + "epoch": 16.5, + "learning_rate": 1.5623368069942434e-06, + "loss": 0.0023, + "step": 53432 + }, + { + "epoch": 16.5, + "learning_rate": 1.5620683987331576e-06, + "loss": 0.0015, + "step": 53433 + }, + { + "epoch": 16.5, + "learning_rate": 1.5618000115768739e-06, + "loss": 0.0024, + "step": 53434 + }, + { + "epoch": 16.5, + "learning_rate": 1.5615316455260677e-06, + "loss": 0.0019, + "step": 53435 + }, + { + "epoch": 16.5, + "learning_rate": 1.5612633005814115e-06, + "loss": 0.0017, + "step": 53436 + }, + { + "epoch": 16.5, + "learning_rate": 1.560994976743574e-06, + "loss": 0.0023, + "step": 53437 + }, + { + "epoch": 16.5, + "learning_rate": 1.5607266740132287e-06, + "loss": 0.0018, + "step": 53438 + }, + { + "epoch": 16.5, + "learning_rate": 1.5604583923910454e-06, + "loss": 0.0026, + "step": 53439 + }, + { + "epoch": 16.5, + "learning_rate": 1.5601901318776924e-06, + "loss": 0.0017, + "step": 53440 + }, + { + "epoch": 16.5, + "learning_rate": 1.5599218924738435e-06, + "loss": 0.0016, + "step": 53441 + }, + { + "epoch": 16.5, + "learning_rate": 1.5596536741801715e-06, + "loss": 0.002, + "step": 53442 + }, + { + "epoch": 16.5, + "learning_rate": 1.559385476997345e-06, + "loss": 0.0021, + "step": 53443 + }, + { + "epoch": 16.5, + "learning_rate": 1.5591173009260318e-06, + "loss": 0.002, + "step": 53444 + }, + { + "epoch": 16.5, + "learning_rate": 1.5588491459669098e-06, + "loss": 0.0023, + "step": 53445 + }, + { + "epoch": 16.51, + "learning_rate": 1.5585810121206424e-06, + "loss": 0.0019, + "step": 53446 + }, + { + "epoch": 16.51, + "learning_rate": 1.5583128993879037e-06, + "loss": 0.0022, + "step": 53447 + }, + { + "epoch": 16.51, + "learning_rate": 1.5580448077693689e-06, + "loss": 0.002, + "step": 53448 + }, + { + "epoch": 16.51, + "learning_rate": 1.5577767372656983e-06, + "loss": 0.0014, + "step": 53449 + }, + { + "epoch": 16.51, + "learning_rate": 1.557508687877568e-06, + "loss": 0.0025, + "step": 53450 + }, + { + "epoch": 16.51, + "learning_rate": 1.557240659605651e-06, + "loss": 0.0037, + "step": 53451 + }, + { + "epoch": 16.51, + "learning_rate": 1.5569726524506135e-06, + "loss": 0.0025, + "step": 53452 + }, + { + "epoch": 16.51, + "learning_rate": 1.556704666413128e-06, + "loss": 0.0018, + "step": 53453 + }, + { + "epoch": 16.51, + "learning_rate": 1.5564367014938652e-06, + "loss": 0.0016, + "step": 53454 + }, + { + "epoch": 16.51, + "learning_rate": 1.5561687576934914e-06, + "loss": 0.0022, + "step": 53455 + }, + { + "epoch": 16.51, + "learning_rate": 1.5559008350126803e-06, + "loss": 0.0019, + "step": 53456 + }, + { + "epoch": 16.51, + "learning_rate": 1.5556329334521004e-06, + "loss": 0.0019, + "step": 53457 + }, + { + "epoch": 16.51, + "learning_rate": 1.5553650530124276e-06, + "loss": 0.0022, + "step": 53458 + }, + { + "epoch": 16.51, + "learning_rate": 1.5550971936943227e-06, + "loss": 0.002, + "step": 53459 + }, + { + "epoch": 16.51, + "learning_rate": 1.5548293554984594e-06, + "loss": 0.0023, + "step": 53460 + }, + { + "epoch": 16.51, + "learning_rate": 1.5545615384255107e-06, + "loss": 0.0017, + "step": 53461 + }, + { + "epoch": 16.51, + "learning_rate": 1.5542937424761429e-06, + "loss": 0.0022, + "step": 53462 + }, + { + "epoch": 16.51, + "learning_rate": 1.5540259676510271e-06, + "loss": 0.0024, + "step": 53463 + }, + { + "epoch": 16.51, + "learning_rate": 1.5537582139508345e-06, + "loss": 0.0019, + "step": 53464 + }, + { + "epoch": 16.51, + "learning_rate": 1.5534904813762297e-06, + "loss": 0.0028, + "step": 53465 + }, + { + "epoch": 16.51, + "learning_rate": 1.5532227699278858e-06, + "loss": 0.0026, + "step": 53466 + }, + { + "epoch": 16.51, + "learning_rate": 1.5529550796064752e-06, + "loss": 0.0027, + "step": 53467 + }, + { + "epoch": 16.51, + "learning_rate": 1.5526874104126643e-06, + "loss": 0.0019, + "step": 53468 + }, + { + "epoch": 16.51, + "learning_rate": 1.5524197623471205e-06, + "loss": 0.0023, + "step": 53469 + }, + { + "epoch": 16.51, + "learning_rate": 1.5521521354105184e-06, + "loss": 0.0021, + "step": 53470 + }, + { + "epoch": 16.51, + "learning_rate": 1.5518845296035222e-06, + "loss": 0.0029, + "step": 53471 + }, + { + "epoch": 16.51, + "learning_rate": 1.5516169449268026e-06, + "loss": 0.0025, + "step": 53472 + }, + { + "epoch": 16.51, + "learning_rate": 1.5513493813810333e-06, + "loss": 0.0024, + "step": 53473 + }, + { + "epoch": 16.51, + "learning_rate": 1.5510818389668803e-06, + "loss": 0.0021, + "step": 53474 + }, + { + "epoch": 16.51, + "learning_rate": 1.55081431768501e-06, + "loss": 0.0016, + "step": 53475 + }, + { + "epoch": 16.51, + "learning_rate": 1.550546817536096e-06, + "loss": 0.0021, + "step": 53476 + }, + { + "epoch": 16.51, + "learning_rate": 1.5502793385208037e-06, + "loss": 0.0022, + "step": 53477 + }, + { + "epoch": 16.51, + "learning_rate": 1.5500118806398056e-06, + "loss": 0.0022, + "step": 53478 + }, + { + "epoch": 16.52, + "learning_rate": 1.5497444438937692e-06, + "loss": 0.0032, + "step": 53479 + }, + { + "epoch": 16.52, + "learning_rate": 1.5494770282833616e-06, + "loss": 0.0023, + "step": 53480 + }, + { + "epoch": 16.52, + "learning_rate": 1.5492096338092521e-06, + "loss": 0.0018, + "step": 53481 + }, + { + "epoch": 16.52, + "learning_rate": 1.5489422604721138e-06, + "loss": 0.0024, + "step": 53482 + }, + { + "epoch": 16.52, + "learning_rate": 1.5486749082726094e-06, + "loss": 0.003, + "step": 53483 + }, + { + "epoch": 16.52, + "learning_rate": 1.5484075772114126e-06, + "loss": 0.0017, + "step": 53484 + }, + { + "epoch": 16.52, + "learning_rate": 1.548140267289191e-06, + "loss": 0.0017, + "step": 53485 + }, + { + "epoch": 16.52, + "learning_rate": 1.5478729785066094e-06, + "loss": 0.0022, + "step": 53486 + }, + { + "epoch": 16.52, + "learning_rate": 1.5476057108643382e-06, + "loss": 0.0018, + "step": 53487 + }, + { + "epoch": 16.52, + "learning_rate": 1.5473384643630495e-06, + "loss": 0.002, + "step": 53488 + }, + { + "epoch": 16.52, + "learning_rate": 1.5470712390034092e-06, + "loss": 0.0026, + "step": 53489 + }, + { + "epoch": 16.52, + "learning_rate": 1.5468040347860836e-06, + "loss": 0.002, + "step": 53490 + }, + { + "epoch": 16.52, + "learning_rate": 1.5465368517117418e-06, + "loss": 0.0027, + "step": 53491 + }, + { + "epoch": 16.52, + "learning_rate": 1.5462696897810558e-06, + "loss": 0.002, + "step": 53492 + }, + { + "epoch": 16.52, + "learning_rate": 1.5460025489946895e-06, + "loss": 0.0038, + "step": 53493 + }, + { + "epoch": 16.52, + "learning_rate": 1.5457354293533143e-06, + "loss": 0.0019, + "step": 53494 + }, + { + "epoch": 16.52, + "learning_rate": 1.545468330857598e-06, + "loss": 0.0022, + "step": 53495 + }, + { + "epoch": 16.52, + "learning_rate": 1.545201253508204e-06, + "loss": 0.0017, + "step": 53496 + }, + { + "epoch": 16.52, + "learning_rate": 1.544934197305803e-06, + "loss": 0.0026, + "step": 53497 + }, + { + "epoch": 16.52, + "learning_rate": 1.5446671622510679e-06, + "loss": 0.003, + "step": 53498 + }, + { + "epoch": 16.52, + "learning_rate": 1.5444001483446614e-06, + "loss": 0.0028, + "step": 53499 + }, + { + "epoch": 16.52, + "learning_rate": 1.5441331555872497e-06, + "loss": 0.0017, + "step": 53500 + }, + { + "epoch": 16.52, + "learning_rate": 1.5438661839795055e-06, + "loss": 0.0019, + "step": 53501 + }, + { + "epoch": 16.52, + "learning_rate": 1.543599233522093e-06, + "loss": 0.0015, + "step": 53502 + }, + { + "epoch": 16.52, + "learning_rate": 1.54333230421568e-06, + "loss": 0.0024, + "step": 53503 + }, + { + "epoch": 16.52, + "learning_rate": 1.5430653960609376e-06, + "loss": 0.0019, + "step": 53504 + }, + { + "epoch": 16.52, + "learning_rate": 1.5427985090585317e-06, + "loss": 0.0019, + "step": 53505 + }, + { + "epoch": 16.52, + "learning_rate": 1.5425316432091275e-06, + "loss": 0.0019, + "step": 53506 + }, + { + "epoch": 16.52, + "learning_rate": 1.5422647985133954e-06, + "loss": 0.0021, + "step": 53507 + }, + { + "epoch": 16.52, + "learning_rate": 1.5419979749719994e-06, + "loss": 0.0023, + "step": 53508 + }, + { + "epoch": 16.52, + "learning_rate": 1.541731172585612e-06, + "loss": 0.0024, + "step": 53509 + }, + { + "epoch": 16.52, + "learning_rate": 1.5414643913548976e-06, + "loss": 0.0025, + "step": 53510 + }, + { + "epoch": 16.53, + "learning_rate": 1.541197631280521e-06, + "loss": 0.0023, + "step": 53511 + }, + { + "epoch": 16.53, + "learning_rate": 1.5409308923631516e-06, + "loss": 0.002, + "step": 53512 + }, + { + "epoch": 16.53, + "learning_rate": 1.5406641746034601e-06, + "loss": 0.0019, + "step": 53513 + }, + { + "epoch": 16.53, + "learning_rate": 1.5403974780021068e-06, + "loss": 0.0019, + "step": 53514 + }, + { + "epoch": 16.53, + "learning_rate": 1.540130802559765e-06, + "loss": 0.0019, + "step": 53515 + }, + { + "epoch": 16.53, + "learning_rate": 1.5398641482771003e-06, + "loss": 0.0018, + "step": 53516 + }, + { + "epoch": 16.53, + "learning_rate": 1.5395975151547748e-06, + "loss": 0.0019, + "step": 53517 + }, + { + "epoch": 16.53, + "learning_rate": 1.539330903193459e-06, + "loss": 0.0028, + "step": 53518 + }, + { + "epoch": 16.53, + "learning_rate": 1.5390643123938232e-06, + "loss": 0.002, + "step": 53519 + }, + { + "epoch": 16.53, + "learning_rate": 1.5387977427565292e-06, + "loss": 0.0019, + "step": 53520 + }, + { + "epoch": 16.53, + "learning_rate": 1.5385311942822435e-06, + "loss": 0.0016, + "step": 53521 + }, + { + "epoch": 16.53, + "learning_rate": 1.538264666971635e-06, + "loss": 0.0023, + "step": 53522 + }, + { + "epoch": 16.53, + "learning_rate": 1.5379981608253724e-06, + "loss": 0.0024, + "step": 53523 + }, + { + "epoch": 16.53, + "learning_rate": 1.5377316758441163e-06, + "loss": 0.0027, + "step": 53524 + }, + { + "epoch": 16.53, + "learning_rate": 1.5374652120285405e-06, + "loss": 0.0022, + "step": 53525 + }, + { + "epoch": 16.53, + "learning_rate": 1.5371987693793066e-06, + "loss": 0.002, + "step": 53526 + }, + { + "epoch": 16.53, + "learning_rate": 1.5369323478970799e-06, + "loss": 0.0019, + "step": 53527 + }, + { + "epoch": 16.53, + "learning_rate": 1.5366659475825296e-06, + "loss": 0.0023, + "step": 53528 + }, + { + "epoch": 16.53, + "learning_rate": 1.5363995684363231e-06, + "loss": 0.0022, + "step": 53529 + }, + { + "epoch": 16.53, + "learning_rate": 1.5361332104591253e-06, + "loss": 0.0022, + "step": 53530 + }, + { + "epoch": 16.53, + "learning_rate": 1.5358668736515991e-06, + "loss": 0.0023, + "step": 53531 + }, + { + "epoch": 16.53, + "learning_rate": 1.5356005580144162e-06, + "loss": 0.0029, + "step": 53532 + }, + { + "epoch": 16.53, + "learning_rate": 1.5353342635482383e-06, + "loss": 0.0027, + "step": 53533 + }, + { + "epoch": 16.53, + "learning_rate": 1.5350679902537324e-06, + "loss": 0.0019, + "step": 53534 + }, + { + "epoch": 16.53, + "learning_rate": 1.5348017381315682e-06, + "loss": 0.0023, + "step": 53535 + }, + { + "epoch": 16.53, + "learning_rate": 1.5345355071824086e-06, + "loss": 0.0034, + "step": 53536 + }, + { + "epoch": 16.53, + "learning_rate": 1.5342692974069184e-06, + "loss": 0.0019, + "step": 53537 + }, + { + "epoch": 16.53, + "learning_rate": 1.534003108805766e-06, + "loss": 0.0032, + "step": 53538 + }, + { + "epoch": 16.53, + "learning_rate": 1.5337369413796134e-06, + "loss": 0.0019, + "step": 53539 + }, + { + "epoch": 16.53, + "learning_rate": 1.5334707951291317e-06, + "loss": 0.0023, + "step": 53540 + }, + { + "epoch": 16.53, + "learning_rate": 1.533204670054984e-06, + "loss": 0.0024, + "step": 53541 + }, + { + "epoch": 16.53, + "learning_rate": 1.5329385661578333e-06, + "loss": 0.0021, + "step": 53542 + }, + { + "epoch": 16.54, + "learning_rate": 1.5326724834383467e-06, + "loss": 0.0022, + "step": 53543 + }, + { + "epoch": 16.54, + "learning_rate": 1.5324064218971934e-06, + "loss": 0.0023, + "step": 53544 + }, + { + "epoch": 16.54, + "learning_rate": 1.5321403815350345e-06, + "loss": 0.0024, + "step": 53545 + }, + { + "epoch": 16.54, + "learning_rate": 1.531874362352538e-06, + "loss": 0.0016, + "step": 53546 + }, + { + "epoch": 16.54, + "learning_rate": 1.5316083643503688e-06, + "loss": 0.0017, + "step": 53547 + }, + { + "epoch": 16.54, + "learning_rate": 1.5313423875291889e-06, + "loss": 0.0026, + "step": 53548 + }, + { + "epoch": 16.54, + "learning_rate": 1.5310764318896664e-06, + "loss": 0.0017, + "step": 53549 + }, + { + "epoch": 16.54, + "learning_rate": 1.5308104974324689e-06, + "loss": 0.0016, + "step": 53550 + }, + { + "epoch": 16.54, + "learning_rate": 1.53054458415826e-06, + "loss": 0.0022, + "step": 53551 + }, + { + "epoch": 16.54, + "learning_rate": 1.5302786920677004e-06, + "loss": 0.0026, + "step": 53552 + }, + { + "epoch": 16.54, + "learning_rate": 1.5300128211614606e-06, + "loss": 0.0022, + "step": 53553 + }, + { + "epoch": 16.54, + "learning_rate": 1.5297469714402013e-06, + "loss": 0.0022, + "step": 53554 + }, + { + "epoch": 16.54, + "learning_rate": 1.5294811429045909e-06, + "loss": 0.0023, + "step": 53555 + }, + { + "epoch": 16.54, + "learning_rate": 1.5292153355552942e-06, + "loss": 0.0021, + "step": 53556 + }, + { + "epoch": 16.54, + "learning_rate": 1.5289495493929752e-06, + "loss": 0.0024, + "step": 53557 + }, + { + "epoch": 16.54, + "learning_rate": 1.5286837844182968e-06, + "loss": 0.0019, + "step": 53558 + }, + { + "epoch": 16.54, + "learning_rate": 1.5284180406319237e-06, + "loss": 0.0015, + "step": 53559 + }, + { + "epoch": 16.54, + "learning_rate": 1.528152318034526e-06, + "loss": 0.0023, + "step": 53560 + }, + { + "epoch": 16.54, + "learning_rate": 1.5278866166267637e-06, + "loss": 0.0022, + "step": 53561 + }, + { + "epoch": 16.54, + "learning_rate": 1.5276209364093008e-06, + "loss": 0.0026, + "step": 53562 + }, + { + "epoch": 16.54, + "learning_rate": 1.527355277382805e-06, + "loss": 0.0022, + "step": 53563 + }, + { + "epoch": 16.54, + "learning_rate": 1.5270896395479363e-06, + "loss": 0.0023, + "step": 53564 + }, + { + "epoch": 16.54, + "learning_rate": 1.5268240229053622e-06, + "loss": 0.0021, + "step": 53565 + }, + { + "epoch": 16.54, + "learning_rate": 1.526558427455751e-06, + "loss": 0.002, + "step": 53566 + }, + { + "epoch": 16.54, + "learning_rate": 1.5262928531997578e-06, + "loss": 0.0021, + "step": 53567 + }, + { + "epoch": 16.54, + "learning_rate": 1.5260273001380522e-06, + "loss": 0.0018, + "step": 53568 + }, + { + "epoch": 16.54, + "learning_rate": 1.5257617682712999e-06, + "loss": 0.002, + "step": 53569 + }, + { + "epoch": 16.54, + "learning_rate": 1.5254962576001609e-06, + "loss": 0.0021, + "step": 53570 + }, + { + "epoch": 16.54, + "learning_rate": 1.5252307681253042e-06, + "loss": 0.002, + "step": 53571 + }, + { + "epoch": 16.54, + "learning_rate": 1.5249652998473906e-06, + "loss": 0.002, + "step": 53572 + }, + { + "epoch": 16.54, + "learning_rate": 1.524699852767082e-06, + "loss": 0.0023, + "step": 53573 + }, + { + "epoch": 16.54, + "learning_rate": 1.524434426885044e-06, + "loss": 0.0026, + "step": 53574 + }, + { + "epoch": 16.54, + "learning_rate": 1.5241690222019456e-06, + "loss": 0.0025, + "step": 53575 + }, + { + "epoch": 16.55, + "learning_rate": 1.5239036387184447e-06, + "loss": 0.0021, + "step": 53576 + }, + { + "epoch": 16.55, + "learning_rate": 1.5236382764352054e-06, + "loss": 0.0021, + "step": 53577 + }, + { + "epoch": 16.55, + "learning_rate": 1.5233729353528948e-06, + "loss": 0.0024, + "step": 53578 + }, + { + "epoch": 16.55, + "learning_rate": 1.5231076154721724e-06, + "loss": 0.0022, + "step": 53579 + }, + { + "epoch": 16.55, + "learning_rate": 1.5228423167937034e-06, + "loss": 0.0031, + "step": 53580 + }, + { + "epoch": 16.55, + "learning_rate": 1.522577039318155e-06, + "loss": 0.0018, + "step": 53581 + }, + { + "epoch": 16.55, + "learning_rate": 1.5223117830461875e-06, + "loss": 0.0025, + "step": 53582 + }, + { + "epoch": 16.55, + "learning_rate": 1.522046547978462e-06, + "loss": 0.0018, + "step": 53583 + }, + { + "epoch": 16.55, + "learning_rate": 1.5217813341156463e-06, + "loss": 0.0018, + "step": 53584 + }, + { + "epoch": 16.55, + "learning_rate": 1.521516141458399e-06, + "loss": 0.002, + "step": 53585 + }, + { + "epoch": 16.55, + "learning_rate": 1.5212509700073897e-06, + "loss": 0.002, + "step": 53586 + }, + { + "epoch": 16.55, + "learning_rate": 1.5209858197632777e-06, + "loss": 0.0018, + "step": 53587 + }, + { + "epoch": 16.55, + "learning_rate": 1.5207206907267246e-06, + "loss": 0.0023, + "step": 53588 + }, + { + "epoch": 16.55, + "learning_rate": 1.5204555828983946e-06, + "loss": 0.0019, + "step": 53589 + }, + { + "epoch": 16.55, + "learning_rate": 1.5201904962789526e-06, + "loss": 0.0026, + "step": 53590 + }, + { + "epoch": 16.55, + "learning_rate": 1.5199254308690636e-06, + "loss": 0.0028, + "step": 53591 + }, + { + "epoch": 16.55, + "learning_rate": 1.5196603866693872e-06, + "loss": 0.0023, + "step": 53592 + }, + { + "epoch": 16.55, + "learning_rate": 1.5193953636805846e-06, + "loss": 0.002, + "step": 53593 + }, + { + "epoch": 16.55, + "learning_rate": 1.5191303619033226e-06, + "loss": 0.0022, + "step": 53594 + }, + { + "epoch": 16.55, + "learning_rate": 1.5188653813382604e-06, + "loss": 0.0028, + "step": 53595 + }, + { + "epoch": 16.55, + "learning_rate": 1.518600421986063e-06, + "loss": 0.003, + "step": 53596 + }, + { + "epoch": 16.55, + "learning_rate": 1.5183354838473974e-06, + "loss": 0.003, + "step": 53597 + }, + { + "epoch": 16.55, + "learning_rate": 1.5180705669229179e-06, + "loss": 0.0015, + "step": 53598 + }, + { + "epoch": 16.55, + "learning_rate": 1.5178056712132905e-06, + "loss": 0.002, + "step": 53599 + }, + { + "epoch": 16.55, + "learning_rate": 1.517540796719179e-06, + "loss": 0.0018, + "step": 53600 + }, + { + "epoch": 16.55, + "learning_rate": 1.5172759434412444e-06, + "loss": 0.0027, + "step": 53601 + }, + { + "epoch": 16.55, + "learning_rate": 1.5170111113801522e-06, + "loss": 0.0021, + "step": 53602 + }, + { + "epoch": 16.55, + "learning_rate": 1.5167463005365613e-06, + "loss": 0.0017, + "step": 53603 + }, + { + "epoch": 16.55, + "learning_rate": 1.516481510911133e-06, + "loss": 0.0019, + "step": 53604 + }, + { + "epoch": 16.55, + "learning_rate": 1.5162167425045326e-06, + "loss": 0.0017, + "step": 53605 + }, + { + "epoch": 16.55, + "learning_rate": 1.515951995317424e-06, + "loss": 0.002, + "step": 53606 + }, + { + "epoch": 16.55, + "learning_rate": 1.5156872693504654e-06, + "loss": 0.0025, + "step": 53607 + }, + { + "epoch": 16.56, + "learning_rate": 1.5154225646043187e-06, + "loss": 0.0024, + "step": 53608 + }, + { + "epoch": 16.56, + "learning_rate": 1.5151578810796509e-06, + "loss": 0.002, + "step": 53609 + }, + { + "epoch": 16.56, + "learning_rate": 1.514893218777117e-06, + "loss": 0.0023, + "step": 53610 + }, + { + "epoch": 16.56, + "learning_rate": 1.5146285776973835e-06, + "loss": 0.0024, + "step": 53611 + }, + { + "epoch": 16.56, + "learning_rate": 1.514363957841114e-06, + "loss": 0.0018, + "step": 53612 + }, + { + "epoch": 16.56, + "learning_rate": 1.514099359208968e-06, + "loss": 0.0021, + "step": 53613 + }, + { + "epoch": 16.56, + "learning_rate": 1.5138347818016041e-06, + "loss": 0.0019, + "step": 53614 + }, + { + "epoch": 16.56, + "learning_rate": 1.5135702256196905e-06, + "loss": 0.003, + "step": 53615 + }, + { + "epoch": 16.56, + "learning_rate": 1.5133056906638831e-06, + "loss": 0.0021, + "step": 53616 + }, + { + "epoch": 16.56, + "learning_rate": 1.5130411769348474e-06, + "loss": 0.002, + "step": 53617 + }, + { + "epoch": 16.56, + "learning_rate": 1.5127766844332447e-06, + "loss": 0.0025, + "step": 53618 + }, + { + "epoch": 16.56, + "learning_rate": 1.5125122131597325e-06, + "loss": 0.0029, + "step": 53619 + }, + { + "epoch": 16.56, + "learning_rate": 1.5122477631149757e-06, + "loss": 0.0021, + "step": 53620 + }, + { + "epoch": 16.56, + "learning_rate": 1.511983334299636e-06, + "loss": 0.0028, + "step": 53621 + }, + { + "epoch": 16.56, + "learning_rate": 1.511718926714375e-06, + "loss": 0.0022, + "step": 53622 + }, + { + "epoch": 16.56, + "learning_rate": 1.5114545403598536e-06, + "loss": 0.0019, + "step": 53623 + }, + { + "epoch": 16.56, + "learning_rate": 1.5111901752367307e-06, + "loss": 0.0025, + "step": 53624 + }, + { + "epoch": 16.56, + "learning_rate": 1.510925831345671e-06, + "loss": 0.0022, + "step": 53625 + }, + { + "epoch": 16.56, + "learning_rate": 1.5106615086873322e-06, + "loss": 0.0031, + "step": 53626 + }, + { + "epoch": 16.56, + "learning_rate": 1.5103972072623806e-06, + "loss": 0.0026, + "step": 53627 + }, + { + "epoch": 16.56, + "learning_rate": 1.5101329270714727e-06, + "loss": 0.0018, + "step": 53628 + }, + { + "epoch": 16.56, + "learning_rate": 1.5098686681152685e-06, + "loss": 0.002, + "step": 53629 + }, + { + "epoch": 16.56, + "learning_rate": 1.5096044303944324e-06, + "loss": 0.0014, + "step": 53630 + }, + { + "epoch": 16.56, + "learning_rate": 1.509340213909626e-06, + "loss": 0.0022, + "step": 53631 + }, + { + "epoch": 16.56, + "learning_rate": 1.509076018661505e-06, + "loss": 0.0024, + "step": 53632 + }, + { + "epoch": 16.56, + "learning_rate": 1.5088118446507371e-06, + "loss": 0.0021, + "step": 53633 + }, + { + "epoch": 16.56, + "learning_rate": 1.5085476918779784e-06, + "loss": 0.0017, + "step": 53634 + }, + { + "epoch": 16.56, + "learning_rate": 1.5082835603438896e-06, + "loss": 0.0032, + "step": 53635 + }, + { + "epoch": 16.56, + "learning_rate": 1.5080194500491318e-06, + "loss": 0.0024, + "step": 53636 + }, + { + "epoch": 16.56, + "learning_rate": 1.5077553609943685e-06, + "loss": 0.0017, + "step": 53637 + }, + { + "epoch": 16.56, + "learning_rate": 1.5074912931802578e-06, + "loss": 0.0019, + "step": 53638 + }, + { + "epoch": 16.56, + "learning_rate": 1.5072272466074578e-06, + "loss": 0.0026, + "step": 53639 + }, + { + "epoch": 16.56, + "learning_rate": 1.5069632212766338e-06, + "loss": 0.0024, + "step": 53640 + }, + { + "epoch": 16.57, + "learning_rate": 1.506699217188442e-06, + "loss": 0.0025, + "step": 53641 + }, + { + "epoch": 16.57, + "learning_rate": 1.506435234343544e-06, + "loss": 0.0017, + "step": 53642 + }, + { + "epoch": 16.57, + "learning_rate": 1.5061712727426036e-06, + "loss": 0.002, + "step": 53643 + }, + { + "epoch": 16.57, + "learning_rate": 1.5059073323862773e-06, + "loss": 0.0014, + "step": 53644 + }, + { + "epoch": 16.57, + "learning_rate": 1.505643413275224e-06, + "loss": 0.0022, + "step": 53645 + }, + { + "epoch": 16.57, + "learning_rate": 1.505379515410108e-06, + "loss": 0.0023, + "step": 53646 + }, + { + "epoch": 16.57, + "learning_rate": 1.5051156387915855e-06, + "loss": 0.0017, + "step": 53647 + }, + { + "epoch": 16.57, + "learning_rate": 1.504851783420319e-06, + "loss": 0.0033, + "step": 53648 + }, + { + "epoch": 16.57, + "learning_rate": 1.5045879492969695e-06, + "loss": 0.0019, + "step": 53649 + }, + { + "epoch": 16.57, + "learning_rate": 1.5043241364221917e-06, + "loss": 0.0021, + "step": 53650 + }, + { + "epoch": 16.57, + "learning_rate": 1.5040603447966483e-06, + "loss": 0.0017, + "step": 53651 + }, + { + "epoch": 16.57, + "learning_rate": 1.5037965744210027e-06, + "loss": 0.0025, + "step": 53652 + }, + { + "epoch": 16.57, + "learning_rate": 1.503532825295908e-06, + "loss": 0.0026, + "step": 53653 + }, + { + "epoch": 16.57, + "learning_rate": 1.5032690974220309e-06, + "loss": 0.0026, + "step": 53654 + }, + { + "epoch": 16.57, + "learning_rate": 1.5030053908000253e-06, + "loss": 0.0016, + "step": 53655 + }, + { + "epoch": 16.57, + "learning_rate": 1.5027417054305538e-06, + "loss": 0.0023, + "step": 53656 + }, + { + "epoch": 16.57, + "learning_rate": 1.5024780413142737e-06, + "loss": 0.0018, + "step": 53657 + }, + { + "epoch": 16.57, + "learning_rate": 1.502214398451849e-06, + "loss": 0.0022, + "step": 53658 + }, + { + "epoch": 16.57, + "learning_rate": 1.5019507768439344e-06, + "loss": 0.0028, + "step": 53659 + }, + { + "epoch": 16.57, + "learning_rate": 1.50168717649119e-06, + "loss": 0.0015, + "step": 53660 + }, + { + "epoch": 16.57, + "learning_rate": 1.5014235973942749e-06, + "loss": 0.002, + "step": 53661 + }, + { + "epoch": 16.57, + "learning_rate": 1.5011600395538527e-06, + "loss": 0.002, + "step": 53662 + }, + { + "epoch": 16.57, + "learning_rate": 1.5008965029705758e-06, + "loss": 0.0023, + "step": 53663 + }, + { + "epoch": 16.57, + "learning_rate": 1.5006329876451098e-06, + "loss": 0.0032, + "step": 53664 + }, + { + "epoch": 16.57, + "learning_rate": 1.500369493578111e-06, + "loss": 0.0028, + "step": 53665 + }, + { + "epoch": 16.57, + "learning_rate": 1.5001060207702368e-06, + "loss": 0.0023, + "step": 53666 + }, + { + "epoch": 16.57, + "learning_rate": 1.4998425692221464e-06, + "loss": 0.0028, + "step": 53667 + }, + { + "epoch": 16.57, + "learning_rate": 1.4995791389345028e-06, + "loss": 0.002, + "step": 53668 + }, + { + "epoch": 16.57, + "learning_rate": 1.499315729907962e-06, + "loss": 0.0025, + "step": 53669 + }, + { + "epoch": 16.57, + "learning_rate": 1.4990523421431813e-06, + "loss": 0.0016, + "step": 53670 + }, + { + "epoch": 16.57, + "learning_rate": 1.4987889756408224e-06, + "loss": 0.0024, + "step": 53671 + }, + { + "epoch": 16.57, + "learning_rate": 1.4985256304015416e-06, + "loss": 0.0025, + "step": 53672 + }, + { + "epoch": 16.58, + "learning_rate": 1.4982623064259983e-06, + "loss": 0.0019, + "step": 53673 + }, + { + "epoch": 16.58, + "learning_rate": 1.4979990037148539e-06, + "loss": 0.0023, + "step": 53674 + }, + { + "epoch": 16.58, + "learning_rate": 1.4977357222687649e-06, + "loss": 0.0026, + "step": 53675 + }, + { + "epoch": 16.58, + "learning_rate": 1.4974724620883874e-06, + "loss": 0.002, + "step": 53676 + }, + { + "epoch": 16.58, + "learning_rate": 1.497209223174384e-06, + "loss": 0.0022, + "step": 53677 + }, + { + "epoch": 16.58, + "learning_rate": 1.4969460055274088e-06, + "loss": 0.002, + "step": 53678 + }, + { + "epoch": 16.58, + "learning_rate": 1.4966828091481245e-06, + "loss": 0.0023, + "step": 53679 + }, + { + "epoch": 16.58, + "learning_rate": 1.4964196340371873e-06, + "loss": 0.0025, + "step": 53680 + }, + { + "epoch": 16.58, + "learning_rate": 1.4961564801952543e-06, + "loss": 0.0032, + "step": 53681 + }, + { + "epoch": 16.58, + "learning_rate": 1.4958933476229843e-06, + "loss": 0.0022, + "step": 53682 + }, + { + "epoch": 16.58, + "learning_rate": 1.4956302363210385e-06, + "loss": 0.0018, + "step": 53683 + }, + { + "epoch": 16.58, + "learning_rate": 1.4953671462900698e-06, + "loss": 0.0019, + "step": 53684 + }, + { + "epoch": 16.58, + "learning_rate": 1.4951040775307423e-06, + "loss": 0.0017, + "step": 53685 + }, + { + "epoch": 16.58, + "learning_rate": 1.4948410300437078e-06, + "loss": 0.0023, + "step": 53686 + }, + { + "epoch": 16.58, + "learning_rate": 1.4945780038296287e-06, + "loss": 0.0024, + "step": 53687 + }, + { + "epoch": 16.58, + "learning_rate": 1.4943149988891604e-06, + "loss": 0.003, + "step": 53688 + }, + { + "epoch": 16.58, + "learning_rate": 1.4940520152229631e-06, + "loss": 0.0022, + "step": 53689 + }, + { + "epoch": 16.58, + "learning_rate": 1.4937890528316935e-06, + "loss": 0.0021, + "step": 53690 + }, + { + "epoch": 16.58, + "learning_rate": 1.493526111716006e-06, + "loss": 0.0022, + "step": 53691 + }, + { + "epoch": 16.58, + "learning_rate": 1.4932631918765617e-06, + "loss": 0.0026, + "step": 53692 + }, + { + "epoch": 16.58, + "learning_rate": 1.4930002933140197e-06, + "loss": 0.0017, + "step": 53693 + }, + { + "epoch": 16.58, + "learning_rate": 1.492737416029033e-06, + "loss": 0.0019, + "step": 53694 + }, + { + "epoch": 16.58, + "learning_rate": 1.4924745600222646e-06, + "loss": 0.002, + "step": 53695 + }, + { + "epoch": 16.58, + "learning_rate": 1.492211725294369e-06, + "loss": 0.0024, + "step": 53696 + }, + { + "epoch": 16.58, + "learning_rate": 1.4919489118460006e-06, + "loss": 0.0022, + "step": 53697 + }, + { + "epoch": 16.58, + "learning_rate": 1.491686119677821e-06, + "loss": 0.003, + "step": 53698 + }, + { + "epoch": 16.58, + "learning_rate": 1.4914233487904872e-06, + "loss": 0.002, + "step": 53699 + }, + { + "epoch": 16.58, + "learning_rate": 1.4911605991846567e-06, + "loss": 0.0021, + "step": 53700 + }, + { + "epoch": 16.58, + "learning_rate": 1.4908978708609822e-06, + "loss": 0.0018, + "step": 53701 + }, + { + "epoch": 16.58, + "learning_rate": 1.4906351638201267e-06, + "loss": 0.0029, + "step": 53702 + }, + { + "epoch": 16.58, + "learning_rate": 1.4903724780627428e-06, + "loss": 0.0021, + "step": 53703 + }, + { + "epoch": 16.58, + "learning_rate": 1.4901098135894886e-06, + "loss": 0.0022, + "step": 53704 + }, + { + "epoch": 16.59, + "learning_rate": 1.4898471704010264e-06, + "loss": 0.0023, + "step": 53705 + }, + { + "epoch": 16.59, + "learning_rate": 1.4895845484980043e-06, + "loss": 0.0024, + "step": 53706 + }, + { + "epoch": 16.59, + "learning_rate": 1.4893219478810839e-06, + "loss": 0.003, + "step": 53707 + }, + { + "epoch": 16.59, + "learning_rate": 1.4890593685509236e-06, + "loss": 0.0028, + "step": 53708 + }, + { + "epoch": 16.59, + "learning_rate": 1.4887968105081752e-06, + "loss": 0.0018, + "step": 53709 + }, + { + "epoch": 16.59, + "learning_rate": 1.4885342737535014e-06, + "loss": 0.0025, + "step": 53710 + }, + { + "epoch": 16.59, + "learning_rate": 1.488271758287555e-06, + "loss": 0.0018, + "step": 53711 + }, + { + "epoch": 16.59, + "learning_rate": 1.4880092641109922e-06, + "loss": 0.0025, + "step": 53712 + }, + { + "epoch": 16.59, + "learning_rate": 1.4877467912244703e-06, + "loss": 0.002, + "step": 53713 + }, + { + "epoch": 16.59, + "learning_rate": 1.4874843396286475e-06, + "loss": 0.0015, + "step": 53714 + }, + { + "epoch": 16.59, + "learning_rate": 1.4872219093241801e-06, + "loss": 0.0016, + "step": 53715 + }, + { + "epoch": 16.59, + "learning_rate": 1.486959500311721e-06, + "loss": 0.0028, + "step": 53716 + }, + { + "epoch": 16.59, + "learning_rate": 1.4866971125919305e-06, + "loss": 0.003, + "step": 53717 + }, + { + "epoch": 16.59, + "learning_rate": 1.4864347461654617e-06, + "loss": 0.0034, + "step": 53718 + }, + { + "epoch": 16.59, + "learning_rate": 1.4861724010329714e-06, + "loss": 0.0016, + "step": 53719 + }, + { + "epoch": 16.59, + "learning_rate": 1.4859100771951196e-06, + "loss": 0.0022, + "step": 53720 + }, + { + "epoch": 16.59, + "learning_rate": 1.48564777465256e-06, + "loss": 0.0025, + "step": 53721 + }, + { + "epoch": 16.59, + "learning_rate": 1.4853854934059452e-06, + "loss": 0.0028, + "step": 53722 + }, + { + "epoch": 16.59, + "learning_rate": 1.485123233455935e-06, + "loss": 0.0026, + "step": 53723 + }, + { + "epoch": 16.59, + "learning_rate": 1.4848609948031866e-06, + "loss": 0.0032, + "step": 53724 + }, + { + "epoch": 16.59, + "learning_rate": 1.4845987774483539e-06, + "loss": 0.0026, + "step": 53725 + }, + { + "epoch": 16.59, + "learning_rate": 1.4843365813920896e-06, + "loss": 0.0018, + "step": 53726 + }, + { + "epoch": 16.59, + "learning_rate": 1.4840744066350566e-06, + "loss": 0.0023, + "step": 53727 + }, + { + "epoch": 16.59, + "learning_rate": 1.4838122531779031e-06, + "loss": 0.0017, + "step": 53728 + }, + { + "epoch": 16.59, + "learning_rate": 1.4835501210212888e-06, + "loss": 0.0024, + "step": 53729 + }, + { + "epoch": 16.59, + "learning_rate": 1.4832880101658719e-06, + "loss": 0.0017, + "step": 53730 + }, + { + "epoch": 16.59, + "learning_rate": 1.4830259206123043e-06, + "loss": 0.0034, + "step": 53731 + }, + { + "epoch": 16.59, + "learning_rate": 1.4827638523612398e-06, + "loss": 0.0018, + "step": 53732 + }, + { + "epoch": 16.59, + "learning_rate": 1.4825018054133388e-06, + "loss": 0.0019, + "step": 53733 + }, + { + "epoch": 16.59, + "learning_rate": 1.4822397797692522e-06, + "loss": 0.002, + "step": 53734 + }, + { + "epoch": 16.59, + "learning_rate": 1.4819777754296404e-06, + "loss": 0.0025, + "step": 53735 + }, + { + "epoch": 16.59, + "learning_rate": 1.4817157923951553e-06, + "loss": 0.0019, + "step": 53736 + }, + { + "epoch": 16.59, + "learning_rate": 1.4814538306664495e-06, + "loss": 0.002, + "step": 53737 + }, + { + "epoch": 16.6, + "learning_rate": 1.4811918902441824e-06, + "loss": 0.0024, + "step": 53738 + }, + { + "epoch": 16.6, + "learning_rate": 1.4809299711290093e-06, + "loss": 0.0015, + "step": 53739 + }, + { + "epoch": 16.6, + "learning_rate": 1.4806680733215828e-06, + "loss": 0.0031, + "step": 53740 + }, + { + "epoch": 16.6, + "learning_rate": 1.4804061968225614e-06, + "loss": 0.0029, + "step": 53741 + }, + { + "epoch": 16.6, + "learning_rate": 1.4801443416325977e-06, + "loss": 0.0019, + "step": 53742 + }, + { + "epoch": 16.6, + "learning_rate": 1.4798825077523448e-06, + "loss": 0.0023, + "step": 53743 + }, + { + "epoch": 16.6, + "learning_rate": 1.4796206951824598e-06, + "loss": 0.0022, + "step": 53744 + }, + { + "epoch": 16.6, + "learning_rate": 1.4793589039236001e-06, + "loss": 0.0023, + "step": 53745 + }, + { + "epoch": 16.6, + "learning_rate": 1.479097133976417e-06, + "loss": 0.0023, + "step": 53746 + }, + { + "epoch": 16.6, + "learning_rate": 1.4788353853415648e-06, + "loss": 0.0022, + "step": 53747 + }, + { + "epoch": 16.6, + "learning_rate": 1.4785736580197008e-06, + "loss": 0.0019, + "step": 53748 + }, + { + "epoch": 16.6, + "learning_rate": 1.4783119520114763e-06, + "loss": 0.0018, + "step": 53749 + }, + { + "epoch": 16.6, + "learning_rate": 1.4780502673175478e-06, + "loss": 0.002, + "step": 53750 + }, + { + "epoch": 16.6, + "learning_rate": 1.4777886039385726e-06, + "loss": 0.0025, + "step": 53751 + }, + { + "epoch": 16.6, + "learning_rate": 1.477526961875203e-06, + "loss": 0.002, + "step": 53752 + }, + { + "epoch": 16.6, + "learning_rate": 1.4772653411280891e-06, + "loss": 0.0024, + "step": 53753 + }, + { + "epoch": 16.6, + "learning_rate": 1.47700374169789e-06, + "loss": 0.0024, + "step": 53754 + }, + { + "epoch": 16.6, + "learning_rate": 1.4767421635852607e-06, + "loss": 0.002, + "step": 53755 + }, + { + "epoch": 16.6, + "learning_rate": 1.4764806067908545e-06, + "loss": 0.0021, + "step": 53756 + }, + { + "epoch": 16.6, + "learning_rate": 1.4762190713153224e-06, + "loss": 0.0021, + "step": 53757 + }, + { + "epoch": 16.6, + "learning_rate": 1.4759575571593231e-06, + "loss": 0.0025, + "step": 53758 + }, + { + "epoch": 16.6, + "learning_rate": 1.4756960643235063e-06, + "loss": 0.0024, + "step": 53759 + }, + { + "epoch": 16.6, + "learning_rate": 1.475434592808529e-06, + "loss": 0.002, + "step": 53760 + }, + { + "epoch": 16.6, + "learning_rate": 1.4751731426150461e-06, + "loss": 0.0023, + "step": 53761 + }, + { + "epoch": 16.6, + "learning_rate": 1.4749117137437096e-06, + "loss": 0.0026, + "step": 53762 + }, + { + "epoch": 16.6, + "learning_rate": 1.4746503061951723e-06, + "loss": 0.0022, + "step": 53763 + }, + { + "epoch": 16.6, + "learning_rate": 1.4743889199700922e-06, + "loss": 0.002, + "step": 53764 + }, + { + "epoch": 16.6, + "learning_rate": 1.474127555069117e-06, + "loss": 0.0024, + "step": 53765 + }, + { + "epoch": 16.6, + "learning_rate": 1.473866211492907e-06, + "loss": 0.0015, + "step": 53766 + }, + { + "epoch": 16.6, + "learning_rate": 1.473604889242113e-06, + "loss": 0.0022, + "step": 53767 + }, + { + "epoch": 16.6, + "learning_rate": 1.4733435883173842e-06, + "loss": 0.0017, + "step": 53768 + }, + { + "epoch": 16.6, + "learning_rate": 1.4730823087193801e-06, + "loss": 0.002, + "step": 53769 + }, + { + "epoch": 16.61, + "learning_rate": 1.4728210504487538e-06, + "loss": 0.0028, + "step": 53770 + }, + { + "epoch": 16.61, + "learning_rate": 1.4725598135061548e-06, + "loss": 0.0023, + "step": 53771 + }, + { + "epoch": 16.61, + "learning_rate": 1.4722985978922422e-06, + "loss": 0.0016, + "step": 53772 + }, + { + "epoch": 16.61, + "learning_rate": 1.4720374036076658e-06, + "loss": 0.0025, + "step": 53773 + }, + { + "epoch": 16.61, + "learning_rate": 1.4717762306530757e-06, + "loss": 0.002, + "step": 53774 + }, + { + "epoch": 16.61, + "learning_rate": 1.4715150790291299e-06, + "loss": 0.002, + "step": 53775 + }, + { + "epoch": 16.61, + "learning_rate": 1.4712539487364829e-06, + "loss": 0.0017, + "step": 53776 + }, + { + "epoch": 16.61, + "learning_rate": 1.4709928397757856e-06, + "loss": 0.0018, + "step": 53777 + }, + { + "epoch": 16.61, + "learning_rate": 1.4707317521476871e-06, + "loss": 0.0019, + "step": 53778 + }, + { + "epoch": 16.61, + "learning_rate": 1.4704706858528472e-06, + "loss": 0.002, + "step": 53779 + }, + { + "epoch": 16.61, + "learning_rate": 1.4702096408919142e-06, + "loss": 0.0023, + "step": 53780 + }, + { + "epoch": 16.61, + "learning_rate": 1.469948617265542e-06, + "loss": 0.002, + "step": 53781 + }, + { + "epoch": 16.61, + "learning_rate": 1.4696876149743855e-06, + "loss": 0.003, + "step": 53782 + }, + { + "epoch": 16.61, + "learning_rate": 1.4694266340190977e-06, + "loss": 0.0023, + "step": 53783 + }, + { + "epoch": 16.61, + "learning_rate": 1.4691656744003269e-06, + "loss": 0.0028, + "step": 53784 + }, + { + "epoch": 16.61, + "learning_rate": 1.468904736118728e-06, + "loss": 0.0025, + "step": 53785 + }, + { + "epoch": 16.61, + "learning_rate": 1.4686438191749574e-06, + "loss": 0.0024, + "step": 53786 + }, + { + "epoch": 16.61, + "learning_rate": 1.4683829235696646e-06, + "loss": 0.0017, + "step": 53787 + }, + { + "epoch": 16.61, + "learning_rate": 1.4681220493034987e-06, + "loss": 0.002, + "step": 53788 + }, + { + "epoch": 16.61, + "learning_rate": 1.4678611963771194e-06, + "loss": 0.0027, + "step": 53789 + }, + { + "epoch": 16.61, + "learning_rate": 1.467600364791173e-06, + "loss": 0.0025, + "step": 53790 + }, + { + "epoch": 16.61, + "learning_rate": 1.4673395545463132e-06, + "loss": 0.0023, + "step": 53791 + }, + { + "epoch": 16.61, + "learning_rate": 1.4670787656431962e-06, + "loss": 0.0026, + "step": 53792 + }, + { + "epoch": 16.61, + "learning_rate": 1.4668179980824726e-06, + "loss": 0.0028, + "step": 53793 + }, + { + "epoch": 16.61, + "learning_rate": 1.4665572518647896e-06, + "loss": 0.0018, + "step": 53794 + }, + { + "epoch": 16.61, + "learning_rate": 1.466296526990807e-06, + "loss": 0.002, + "step": 53795 + }, + { + "epoch": 16.61, + "learning_rate": 1.4660358234611705e-06, + "loss": 0.0024, + "step": 53796 + }, + { + "epoch": 16.61, + "learning_rate": 1.4657751412765365e-06, + "loss": 0.0019, + "step": 53797 + }, + { + "epoch": 16.61, + "learning_rate": 1.4655144804375565e-06, + "loss": 0.0023, + "step": 53798 + }, + { + "epoch": 16.61, + "learning_rate": 1.465253840944878e-06, + "loss": 0.0015, + "step": 53799 + }, + { + "epoch": 16.61, + "learning_rate": 1.464993222799157e-06, + "loss": 0.0024, + "step": 53800 + }, + { + "epoch": 16.61, + "learning_rate": 1.4647326260010464e-06, + "loss": 0.0021, + "step": 53801 + }, + { + "epoch": 16.62, + "learning_rate": 1.4644720505511944e-06, + "loss": 0.002, + "step": 53802 + }, + { + "epoch": 16.62, + "learning_rate": 1.4642114964502574e-06, + "loss": 0.0022, + "step": 53803 + }, + { + "epoch": 16.62, + "learning_rate": 1.4639509636988835e-06, + "loss": 0.0023, + "step": 53804 + }, + { + "epoch": 16.62, + "learning_rate": 1.4636904522977225e-06, + "loss": 0.0024, + "step": 53805 + }, + { + "epoch": 16.62, + "learning_rate": 1.463429962247429e-06, + "loss": 0.002, + "step": 53806 + }, + { + "epoch": 16.62, + "learning_rate": 1.4631694935486573e-06, + "loss": 0.0015, + "step": 53807 + }, + { + "epoch": 16.62, + "learning_rate": 1.4629090462020546e-06, + "loss": 0.0016, + "step": 53808 + }, + { + "epoch": 16.62, + "learning_rate": 1.4626486202082712e-06, + "loss": 0.0028, + "step": 53809 + }, + { + "epoch": 16.62, + "learning_rate": 1.4623882155679636e-06, + "loss": 0.0029, + "step": 53810 + }, + { + "epoch": 16.62, + "learning_rate": 1.4621278322817777e-06, + "loss": 0.002, + "step": 53811 + }, + { + "epoch": 16.62, + "learning_rate": 1.4618674703503676e-06, + "loss": 0.0015, + "step": 53812 + }, + { + "epoch": 16.62, + "learning_rate": 1.4616071297743883e-06, + "loss": 0.0025, + "step": 53813 + }, + { + "epoch": 16.62, + "learning_rate": 1.4613468105544827e-06, + "loss": 0.0027, + "step": 53814 + }, + { + "epoch": 16.62, + "learning_rate": 1.4610865126913054e-06, + "loss": 0.0019, + "step": 53815 + }, + { + "epoch": 16.62, + "learning_rate": 1.4608262361855107e-06, + "loss": 0.0016, + "step": 53816 + }, + { + "epoch": 16.62, + "learning_rate": 1.4605659810377448e-06, + "loss": 0.0023, + "step": 53817 + }, + { + "epoch": 16.62, + "learning_rate": 1.4603057472486637e-06, + "loss": 0.0025, + "step": 53818 + }, + { + "epoch": 16.62, + "learning_rate": 1.4600455348189125e-06, + "loss": 0.0019, + "step": 53819 + }, + { + "epoch": 16.62, + "learning_rate": 1.4597853437491471e-06, + "loss": 0.0019, + "step": 53820 + }, + { + "epoch": 16.62, + "learning_rate": 1.4595251740400151e-06, + "loss": 0.0026, + "step": 53821 + }, + { + "epoch": 16.62, + "learning_rate": 1.459265025692167e-06, + "loss": 0.0015, + "step": 53822 + }, + { + "epoch": 16.62, + "learning_rate": 1.45900489870626e-06, + "loss": 0.0017, + "step": 53823 + }, + { + "epoch": 16.62, + "learning_rate": 1.4587447930829356e-06, + "loss": 0.0023, + "step": 53824 + }, + { + "epoch": 16.62, + "learning_rate": 1.458484708822847e-06, + "loss": 0.0021, + "step": 53825 + }, + { + "epoch": 16.62, + "learning_rate": 1.4582246459266492e-06, + "loss": 0.0024, + "step": 53826 + }, + { + "epoch": 16.62, + "learning_rate": 1.457964604394987e-06, + "loss": 0.0018, + "step": 53827 + }, + { + "epoch": 16.62, + "learning_rate": 1.4577045842285154e-06, + "loss": 0.0016, + "step": 53828 + }, + { + "epoch": 16.62, + "learning_rate": 1.457444585427883e-06, + "loss": 0.0023, + "step": 53829 + }, + { + "epoch": 16.62, + "learning_rate": 1.457184607993737e-06, + "loss": 0.0024, + "step": 53830 + }, + { + "epoch": 16.62, + "learning_rate": 1.45692465192673e-06, + "loss": 0.0024, + "step": 53831 + }, + { + "epoch": 16.62, + "learning_rate": 1.4566647172275162e-06, + "loss": 0.0025, + "step": 53832 + }, + { + "epoch": 16.62, + "learning_rate": 1.4564048038967416e-06, + "loss": 0.0025, + "step": 53833 + }, + { + "epoch": 16.62, + "learning_rate": 1.4561449119350546e-06, + "loss": 0.003, + "step": 53834 + }, + { + "epoch": 16.63, + "learning_rate": 1.455885041343109e-06, + "loss": 0.002, + "step": 53835 + }, + { + "epoch": 16.63, + "learning_rate": 1.4556251921215513e-06, + "loss": 0.0018, + "step": 53836 + }, + { + "epoch": 16.63, + "learning_rate": 1.4553653642710342e-06, + "loss": 0.0023, + "step": 53837 + }, + { + "epoch": 16.63, + "learning_rate": 1.4551055577922079e-06, + "loss": 0.0027, + "step": 53838 + }, + { + "epoch": 16.63, + "learning_rate": 1.4548457726857223e-06, + "loss": 0.0027, + "step": 53839 + }, + { + "epoch": 16.63, + "learning_rate": 1.4545860089522225e-06, + "loss": 0.0025, + "step": 53840 + }, + { + "epoch": 16.63, + "learning_rate": 1.4543262665923653e-06, + "loss": 0.0021, + "step": 53841 + }, + { + "epoch": 16.63, + "learning_rate": 1.4540665456067927e-06, + "loss": 0.0023, + "step": 53842 + }, + { + "epoch": 16.63, + "learning_rate": 1.453806845996162e-06, + "loss": 0.002, + "step": 53843 + }, + { + "epoch": 16.63, + "learning_rate": 1.453547167761119e-06, + "loss": 0.0023, + "step": 53844 + }, + { + "epoch": 16.63, + "learning_rate": 1.4532875109023105e-06, + "loss": 0.0021, + "step": 53845 + }, + { + "epoch": 16.63, + "learning_rate": 1.4530278754203885e-06, + "loss": 0.0026, + "step": 53846 + }, + { + "epoch": 16.63, + "learning_rate": 1.4527682613160054e-06, + "loss": 0.0024, + "step": 53847 + }, + { + "epoch": 16.63, + "learning_rate": 1.452508668589806e-06, + "loss": 0.002, + "step": 53848 + }, + { + "epoch": 16.63, + "learning_rate": 1.452249097242443e-06, + "loss": 0.003, + "step": 53849 + }, + { + "epoch": 16.63, + "learning_rate": 1.4519895472745627e-06, + "loss": 0.0046, + "step": 53850 + }, + { + "epoch": 16.63, + "learning_rate": 1.4517300186868167e-06, + "loss": 0.0036, + "step": 53851 + }, + { + "epoch": 16.63, + "learning_rate": 1.451470511479851e-06, + "loss": 0.0028, + "step": 53852 + }, + { + "epoch": 16.63, + "learning_rate": 1.4512110256543167e-06, + "loss": 0.0015, + "step": 53853 + }, + { + "epoch": 16.63, + "learning_rate": 1.4509515612108681e-06, + "loss": 0.0024, + "step": 53854 + }, + { + "epoch": 16.63, + "learning_rate": 1.4506921181501433e-06, + "loss": 0.0023, + "step": 53855 + }, + { + "epoch": 16.63, + "learning_rate": 1.4504326964727976e-06, + "loss": 0.003, + "step": 53856 + }, + { + "epoch": 16.63, + "learning_rate": 1.4501732961794812e-06, + "loss": 0.0024, + "step": 53857 + }, + { + "epoch": 16.63, + "learning_rate": 1.4499139172708389e-06, + "loss": 0.0025, + "step": 53858 + }, + { + "epoch": 16.63, + "learning_rate": 1.4496545597475232e-06, + "loss": 0.0025, + "step": 53859 + }, + { + "epoch": 16.63, + "learning_rate": 1.4493952236101805e-06, + "loss": 0.002, + "step": 53860 + }, + { + "epoch": 16.63, + "learning_rate": 1.4491359088594581e-06, + "loss": 0.0025, + "step": 53861 + }, + { + "epoch": 16.63, + "learning_rate": 1.4488766154960055e-06, + "loss": 0.0019, + "step": 53862 + }, + { + "epoch": 16.63, + "learning_rate": 1.4486173435204754e-06, + "loss": 0.0022, + "step": 53863 + }, + { + "epoch": 16.63, + "learning_rate": 1.4483580929335129e-06, + "loss": 0.002, + "step": 53864 + }, + { + "epoch": 16.63, + "learning_rate": 1.4480988637357641e-06, + "loss": 0.0016, + "step": 53865 + }, + { + "epoch": 16.63, + "learning_rate": 1.4478396559278817e-06, + "loss": 0.0019, + "step": 53866 + }, + { + "epoch": 16.64, + "learning_rate": 1.44758046951051e-06, + "loss": 0.003, + "step": 53867 + }, + { + "epoch": 16.64, + "learning_rate": 1.4473213044842992e-06, + "loss": 0.0021, + "step": 53868 + }, + { + "epoch": 16.64, + "learning_rate": 1.4470621608499015e-06, + "loss": 0.0018, + "step": 53869 + }, + { + "epoch": 16.64, + "learning_rate": 1.44680303860796e-06, + "loss": 0.0024, + "step": 53870 + }, + { + "epoch": 16.64, + "learning_rate": 1.4465439377591218e-06, + "loss": 0.0019, + "step": 53871 + }, + { + "epoch": 16.64, + "learning_rate": 1.44628485830404e-06, + "loss": 0.0026, + "step": 53872 + }, + { + "epoch": 16.64, + "learning_rate": 1.446025800243357e-06, + "loss": 0.0021, + "step": 53873 + }, + { + "epoch": 16.64, + "learning_rate": 1.4457667635777263e-06, + "loss": 0.0022, + "step": 53874 + }, + { + "epoch": 16.64, + "learning_rate": 1.4455077483077928e-06, + "loss": 0.0031, + "step": 53875 + }, + { + "epoch": 16.64, + "learning_rate": 1.445248754434203e-06, + "loss": 0.0022, + "step": 53876 + }, + { + "epoch": 16.64, + "learning_rate": 1.4449897819576063e-06, + "loss": 0.002, + "step": 53877 + }, + { + "epoch": 16.64, + "learning_rate": 1.4447308308786522e-06, + "loss": 0.0029, + "step": 53878 + }, + { + "epoch": 16.64, + "learning_rate": 1.4444719011979846e-06, + "loss": 0.0027, + "step": 53879 + }, + { + "epoch": 16.64, + "learning_rate": 1.4442129929162552e-06, + "loss": 0.0028, + "step": 53880 + }, + { + "epoch": 16.64, + "learning_rate": 1.44395410603411e-06, + "loss": 0.0023, + "step": 53881 + }, + { + "epoch": 16.64, + "learning_rate": 1.4436952405521943e-06, + "loss": 0.002, + "step": 53882 + }, + { + "epoch": 16.64, + "learning_rate": 1.4434363964711563e-06, + "loss": 0.0026, + "step": 53883 + }, + { + "epoch": 16.64, + "learning_rate": 1.4431775737916477e-06, + "loss": 0.0029, + "step": 53884 + }, + { + "epoch": 16.64, + "learning_rate": 1.4429187725143124e-06, + "loss": 0.0019, + "step": 53885 + }, + { + "epoch": 16.64, + "learning_rate": 1.4426599926397954e-06, + "loss": 0.0017, + "step": 53886 + }, + { + "epoch": 16.64, + "learning_rate": 1.4424012341687465e-06, + "loss": 0.0019, + "step": 53887 + }, + { + "epoch": 16.64, + "learning_rate": 1.442142497101815e-06, + "loss": 0.0024, + "step": 53888 + }, + { + "epoch": 16.64, + "learning_rate": 1.4418837814396447e-06, + "loss": 0.0021, + "step": 53889 + }, + { + "epoch": 16.64, + "learning_rate": 1.4416250871828852e-06, + "loss": 0.0022, + "step": 53890 + }, + { + "epoch": 16.64, + "learning_rate": 1.4413664143321826e-06, + "loss": 0.0017, + "step": 53891 + }, + { + "epoch": 16.64, + "learning_rate": 1.441107762888182e-06, + "loss": 0.0025, + "step": 53892 + }, + { + "epoch": 16.64, + "learning_rate": 1.4408491328515317e-06, + "loss": 0.002, + "step": 53893 + }, + { + "epoch": 16.64, + "learning_rate": 1.4405905242228802e-06, + "loss": 0.0021, + "step": 53894 + }, + { + "epoch": 16.64, + "learning_rate": 1.4403319370028735e-06, + "loss": 0.0019, + "step": 53895 + }, + { + "epoch": 16.64, + "learning_rate": 1.4400733711921554e-06, + "loss": 0.0025, + "step": 53896 + }, + { + "epoch": 16.64, + "learning_rate": 1.439814826791378e-06, + "loss": 0.0021, + "step": 53897 + }, + { + "epoch": 16.64, + "learning_rate": 1.4395563038011817e-06, + "loss": 0.0022, + "step": 53898 + }, + { + "epoch": 16.64, + "learning_rate": 1.439297802222217e-06, + "loss": 0.002, + "step": 53899 + }, + { + "epoch": 16.65, + "learning_rate": 1.4390393220551323e-06, + "loss": 0.0028, + "step": 53900 + }, + { + "epoch": 16.65, + "learning_rate": 1.4387808633005707e-06, + "loss": 0.0019, + "step": 53901 + }, + { + "epoch": 16.65, + "learning_rate": 1.438522425959179e-06, + "loss": 0.002, + "step": 53902 + }, + { + "epoch": 16.65, + "learning_rate": 1.4382640100316049e-06, + "loss": 0.0025, + "step": 53903 + }, + { + "epoch": 16.65, + "learning_rate": 1.438005615518493e-06, + "loss": 0.0029, + "step": 53904 + }, + { + "epoch": 16.65, + "learning_rate": 1.437747242420492e-06, + "loss": 0.0021, + "step": 53905 + }, + { + "epoch": 16.65, + "learning_rate": 1.4374888907382478e-06, + "loss": 0.0023, + "step": 53906 + }, + { + "epoch": 16.65, + "learning_rate": 1.4372305604724024e-06, + "loss": 0.0031, + "step": 53907 + }, + { + "epoch": 16.65, + "learning_rate": 1.4369722516236051e-06, + "loss": 0.0033, + "step": 53908 + }, + { + "epoch": 16.65, + "learning_rate": 1.4367139641925043e-06, + "loss": 0.0026, + "step": 53909 + }, + { + "epoch": 16.65, + "learning_rate": 1.4364556981797418e-06, + "loss": 0.003, + "step": 53910 + }, + { + "epoch": 16.65, + "learning_rate": 1.436197453585968e-06, + "loss": 0.0023, + "step": 53911 + }, + { + "epoch": 16.65, + "learning_rate": 1.4359392304118258e-06, + "loss": 0.0021, + "step": 53912 + }, + { + "epoch": 16.65, + "learning_rate": 1.4356810286579602e-06, + "loss": 0.002, + "step": 53913 + }, + { + "epoch": 16.65, + "learning_rate": 1.4354228483250177e-06, + "loss": 0.0019, + "step": 53914 + }, + { + "epoch": 16.65, + "learning_rate": 1.4351646894136472e-06, + "loss": 0.0031, + "step": 53915 + }, + { + "epoch": 16.65, + "learning_rate": 1.4349065519244909e-06, + "loss": 0.0021, + "step": 53916 + }, + { + "epoch": 16.65, + "learning_rate": 1.4346484358581948e-06, + "loss": 0.0025, + "step": 53917 + }, + { + "epoch": 16.65, + "learning_rate": 1.4343903412154036e-06, + "loss": 0.0023, + "step": 53918 + }, + { + "epoch": 16.65, + "learning_rate": 1.4341322679967685e-06, + "loss": 0.0023, + "step": 53919 + }, + { + "epoch": 16.65, + "learning_rate": 1.4338742162029273e-06, + "loss": 0.0023, + "step": 53920 + }, + { + "epoch": 16.65, + "learning_rate": 1.433616185834532e-06, + "loss": 0.0028, + "step": 53921 + }, + { + "epoch": 16.65, + "learning_rate": 1.4333581768922245e-06, + "loss": 0.0019, + "step": 53922 + }, + { + "epoch": 16.65, + "learning_rate": 1.4331001893766483e-06, + "loss": 0.0018, + "step": 53923 + }, + { + "epoch": 16.65, + "learning_rate": 1.432842223288452e-06, + "loss": 0.0017, + "step": 53924 + }, + { + "epoch": 16.65, + "learning_rate": 1.4325842786282818e-06, + "loss": 0.0021, + "step": 53925 + }, + { + "epoch": 16.65, + "learning_rate": 1.4323263553967803e-06, + "loss": 0.0019, + "step": 53926 + }, + { + "epoch": 16.65, + "learning_rate": 1.4320684535945905e-06, + "loss": 0.0023, + "step": 53927 + }, + { + "epoch": 16.65, + "learning_rate": 1.431810573222364e-06, + "loss": 0.0016, + "step": 53928 + }, + { + "epoch": 16.65, + "learning_rate": 1.4315527142807385e-06, + "loss": 0.0025, + "step": 53929 + }, + { + "epoch": 16.65, + "learning_rate": 1.4312948767703627e-06, + "loss": 0.0021, + "step": 53930 + }, + { + "epoch": 16.65, + "learning_rate": 1.4310370606918844e-06, + "loss": 0.0024, + "step": 53931 + }, + { + "epoch": 16.66, + "learning_rate": 1.430779266045944e-06, + "loss": 0.0017, + "step": 53932 + }, + { + "epoch": 16.66, + "learning_rate": 1.4305214928331869e-06, + "loss": 0.0026, + "step": 53933 + }, + { + "epoch": 16.66, + "learning_rate": 1.4302637410542596e-06, + "loss": 0.0027, + "step": 53934 + }, + { + "epoch": 16.66, + "learning_rate": 1.4300060107098035e-06, + "loss": 0.0018, + "step": 53935 + }, + { + "epoch": 16.66, + "learning_rate": 1.4297483018004676e-06, + "loss": 0.0022, + "step": 53936 + }, + { + "epoch": 16.66, + "learning_rate": 1.4294906143268949e-06, + "loss": 0.0019, + "step": 53937 + }, + { + "epoch": 16.66, + "learning_rate": 1.429232948289726e-06, + "loss": 0.0017, + "step": 53938 + }, + { + "epoch": 16.66, + "learning_rate": 1.4289753036896103e-06, + "loss": 0.0022, + "step": 53939 + }, + { + "epoch": 16.66, + "learning_rate": 1.4287176805271918e-06, + "loss": 0.0019, + "step": 53940 + }, + { + "epoch": 16.66, + "learning_rate": 1.428460078803111e-06, + "loss": 0.0029, + "step": 53941 + }, + { + "epoch": 16.66, + "learning_rate": 1.4282024985180188e-06, + "loss": 0.0019, + "step": 53942 + }, + { + "epoch": 16.66, + "learning_rate": 1.4279449396725543e-06, + "loss": 0.0019, + "step": 53943 + }, + { + "epoch": 16.66, + "learning_rate": 1.4276874022673614e-06, + "loss": 0.0024, + "step": 53944 + }, + { + "epoch": 16.66, + "learning_rate": 1.4274298863030844e-06, + "loss": 0.0026, + "step": 53945 + }, + { + "epoch": 16.66, + "learning_rate": 1.4271723917803725e-06, + "loss": 0.0023, + "step": 53946 + }, + { + "epoch": 16.66, + "learning_rate": 1.4269149186998654e-06, + "loss": 0.002, + "step": 53947 + }, + { + "epoch": 16.66, + "learning_rate": 1.4266574670622057e-06, + "loss": 0.0026, + "step": 53948 + }, + { + "epoch": 16.66, + "learning_rate": 1.4264000368680397e-06, + "loss": 0.0016, + "step": 53949 + }, + { + "epoch": 16.66, + "learning_rate": 1.4261426281180125e-06, + "loss": 0.0024, + "step": 53950 + }, + { + "epoch": 16.66, + "learning_rate": 1.4258852408127643e-06, + "loss": 0.002, + "step": 53951 + }, + { + "epoch": 16.66, + "learning_rate": 1.4256278749529428e-06, + "loss": 0.0024, + "step": 53952 + }, + { + "epoch": 16.66, + "learning_rate": 1.4253705305391907e-06, + "loss": 0.0015, + "step": 53953 + }, + { + "epoch": 16.66, + "learning_rate": 1.4251132075721486e-06, + "loss": 0.0027, + "step": 53954 + }, + { + "epoch": 16.66, + "learning_rate": 1.4248559060524614e-06, + "loss": 0.0022, + "step": 53955 + }, + { + "epoch": 16.66, + "learning_rate": 1.4245986259807766e-06, + "loss": 0.0023, + "step": 53956 + }, + { + "epoch": 16.66, + "learning_rate": 1.4243413673577345e-06, + "loss": 0.0024, + "step": 53957 + }, + { + "epoch": 16.66, + "learning_rate": 1.4240841301839759e-06, + "loss": 0.0021, + "step": 53958 + }, + { + "epoch": 16.66, + "learning_rate": 1.4238269144601503e-06, + "loss": 0.0017, + "step": 53959 + }, + { + "epoch": 16.66, + "learning_rate": 1.4235697201868947e-06, + "loss": 0.0016, + "step": 53960 + }, + { + "epoch": 16.66, + "learning_rate": 1.4233125473648557e-06, + "loss": 0.0022, + "step": 53961 + }, + { + "epoch": 16.66, + "learning_rate": 1.4230553959946814e-06, + "loss": 0.0023, + "step": 53962 + }, + { + "epoch": 16.66, + "learning_rate": 1.4227982660770046e-06, + "loss": 0.002, + "step": 53963 + }, + { + "epoch": 16.67, + "learning_rate": 1.4225411576124747e-06, + "loss": 0.0029, + "step": 53964 + }, + { + "epoch": 16.67, + "learning_rate": 1.422284070601735e-06, + "loss": 0.002, + "step": 53965 + }, + { + "epoch": 16.67, + "learning_rate": 1.4220270050454254e-06, + "loss": 0.0021, + "step": 53966 + }, + { + "epoch": 16.67, + "learning_rate": 1.4217699609441927e-06, + "loss": 0.0019, + "step": 53967 + }, + { + "epoch": 16.67, + "learning_rate": 1.4215129382986793e-06, + "loss": 0.0029, + "step": 53968 + }, + { + "epoch": 16.67, + "learning_rate": 1.4212559371095224e-06, + "loss": 0.0016, + "step": 53969 + }, + { + "epoch": 16.67, + "learning_rate": 1.4209989573773707e-06, + "loss": 0.0022, + "step": 53970 + }, + { + "epoch": 16.67, + "learning_rate": 1.420741999102867e-06, + "loss": 0.0026, + "step": 53971 + }, + { + "epoch": 16.67, + "learning_rate": 1.4204850622866516e-06, + "loss": 0.0025, + "step": 53972 + }, + { + "epoch": 16.67, + "learning_rate": 1.4202281469293667e-06, + "loss": 0.0021, + "step": 53973 + }, + { + "epoch": 16.67, + "learning_rate": 1.4199712530316578e-06, + "loss": 0.0023, + "step": 53974 + }, + { + "epoch": 16.67, + "learning_rate": 1.4197143805941638e-06, + "loss": 0.0026, + "step": 53975 + }, + { + "epoch": 16.67, + "learning_rate": 1.4194575296175284e-06, + "loss": 0.0021, + "step": 53976 + }, + { + "epoch": 16.67, + "learning_rate": 1.4192007001023977e-06, + "loss": 0.0019, + "step": 53977 + }, + { + "epoch": 16.67, + "learning_rate": 1.4189438920494102e-06, + "loss": 0.0019, + "step": 53978 + }, + { + "epoch": 16.67, + "learning_rate": 1.4186871054592077e-06, + "loss": 0.0024, + "step": 53979 + }, + { + "epoch": 16.67, + "learning_rate": 1.418430340332434e-06, + "loss": 0.0021, + "step": 53980 + }, + { + "epoch": 16.67, + "learning_rate": 1.418173596669733e-06, + "loss": 0.003, + "step": 53981 + }, + { + "epoch": 16.67, + "learning_rate": 1.4179168744717453e-06, + "loss": 0.0031, + "step": 53982 + }, + { + "epoch": 16.67, + "learning_rate": 1.4176601737391104e-06, + "loss": 0.0018, + "step": 53983 + }, + { + "epoch": 16.67, + "learning_rate": 1.4174034944724747e-06, + "loss": 0.0022, + "step": 53984 + }, + { + "epoch": 16.67, + "learning_rate": 1.4171468366724762e-06, + "loss": 0.0025, + "step": 53985 + }, + { + "epoch": 16.67, + "learning_rate": 1.4168902003397589e-06, + "loss": 0.0025, + "step": 53986 + }, + { + "epoch": 16.67, + "learning_rate": 1.4166335854749668e-06, + "loss": 0.0022, + "step": 53987 + }, + { + "epoch": 16.67, + "learning_rate": 1.4163769920787396e-06, + "loss": 0.0016, + "step": 53988 + }, + { + "epoch": 16.67, + "learning_rate": 1.4161204201517166e-06, + "loss": 0.0024, + "step": 53989 + }, + { + "epoch": 16.67, + "learning_rate": 1.4158638696945448e-06, + "loss": 0.0023, + "step": 53990 + }, + { + "epoch": 16.67, + "learning_rate": 1.4156073407078608e-06, + "loss": 0.0021, + "step": 53991 + }, + { + "epoch": 16.67, + "learning_rate": 1.4153508331923104e-06, + "loss": 0.0018, + "step": 53992 + }, + { + "epoch": 16.67, + "learning_rate": 1.4150943471485335e-06, + "loss": 0.0024, + "step": 53993 + }, + { + "epoch": 16.67, + "learning_rate": 1.4148378825771703e-06, + "loss": 0.0029, + "step": 53994 + }, + { + "epoch": 16.67, + "learning_rate": 1.4145814394788615e-06, + "loss": 0.0026, + "step": 53995 + }, + { + "epoch": 16.67, + "learning_rate": 1.4143250178542534e-06, + "loss": 0.0025, + "step": 53996 + }, + { + "epoch": 16.68, + "learning_rate": 1.414068617703983e-06, + "loss": 0.0021, + "step": 53997 + }, + { + "epoch": 16.68, + "learning_rate": 1.4138122390286947e-06, + "loss": 0.0021, + "step": 53998 + }, + { + "epoch": 16.68, + "learning_rate": 1.4135558818290274e-06, + "loss": 0.002, + "step": 53999 + }, + { + "epoch": 16.68, + "learning_rate": 1.413299546105621e-06, + "loss": 0.0025, + "step": 54000 + }, + { + "epoch": 16.68, + "learning_rate": 1.413043231859118e-06, + "loss": 0.0019, + "step": 54001 + }, + { + "epoch": 16.68, + "learning_rate": 1.4127869390901626e-06, + "loss": 0.0015, + "step": 54002 + }, + { + "epoch": 16.68, + "learning_rate": 1.4125306677993943e-06, + "loss": 0.0023, + "step": 54003 + }, + { + "epoch": 16.68, + "learning_rate": 1.4122744179874493e-06, + "loss": 0.0017, + "step": 54004 + }, + { + "epoch": 16.68, + "learning_rate": 1.4120181896549756e-06, + "loss": 0.0026, + "step": 54005 + }, + { + "epoch": 16.68, + "learning_rate": 1.4117619828026085e-06, + "loss": 0.004, + "step": 54006 + }, + { + "epoch": 16.68, + "learning_rate": 1.4115057974309908e-06, + "loss": 0.002, + "step": 54007 + }, + { + "epoch": 16.68, + "learning_rate": 1.4112496335407654e-06, + "loss": 0.0035, + "step": 54008 + }, + { + "epoch": 16.68, + "learning_rate": 1.4109934911325718e-06, + "loss": 0.0014, + "step": 54009 + }, + { + "epoch": 16.68, + "learning_rate": 1.410737370207047e-06, + "loss": 0.0027, + "step": 54010 + }, + { + "epoch": 16.68, + "learning_rate": 1.4104812707648374e-06, + "loss": 0.0029, + "step": 54011 + }, + { + "epoch": 16.68, + "learning_rate": 1.410225192806579e-06, + "loss": 0.0025, + "step": 54012 + }, + { + "epoch": 16.68, + "learning_rate": 1.409969136332916e-06, + "loss": 0.0016, + "step": 54013 + }, + { + "epoch": 16.68, + "learning_rate": 1.4097131013444843e-06, + "loss": 0.0031, + "step": 54014 + }, + { + "epoch": 16.68, + "learning_rate": 1.4094570878419288e-06, + "loss": 0.0031, + "step": 54015 + }, + { + "epoch": 16.68, + "learning_rate": 1.4092010958258862e-06, + "loss": 0.0022, + "step": 54016 + }, + { + "epoch": 16.68, + "learning_rate": 1.4089451252969988e-06, + "loss": 0.0023, + "step": 54017 + }, + { + "epoch": 16.68, + "learning_rate": 1.4086891762559084e-06, + "loss": 0.0031, + "step": 54018 + }, + { + "epoch": 16.68, + "learning_rate": 1.4084332487032538e-06, + "loss": 0.0026, + "step": 54019 + }, + { + "epoch": 16.68, + "learning_rate": 1.4081773426396715e-06, + "loss": 0.0025, + "step": 54020 + }, + { + "epoch": 16.68, + "learning_rate": 1.4079214580658073e-06, + "loss": 0.002, + "step": 54021 + }, + { + "epoch": 16.68, + "learning_rate": 1.4076655949822971e-06, + "loss": 0.0021, + "step": 54022 + }, + { + "epoch": 16.68, + "learning_rate": 1.4074097533897836e-06, + "loss": 0.0033, + "step": 54023 + }, + { + "epoch": 16.68, + "learning_rate": 1.4071539332889061e-06, + "loss": 0.0022, + "step": 54024 + }, + { + "epoch": 16.68, + "learning_rate": 1.4068981346803013e-06, + "loss": 0.0018, + "step": 54025 + }, + { + "epoch": 16.68, + "learning_rate": 1.4066423575646127e-06, + "loss": 0.0024, + "step": 54026 + }, + { + "epoch": 16.68, + "learning_rate": 1.40638660194248e-06, + "loss": 0.002, + "step": 54027 + }, + { + "epoch": 16.68, + "learning_rate": 1.406130867814539e-06, + "loss": 0.0021, + "step": 54028 + }, + { + "epoch": 16.69, + "learning_rate": 1.4058751551814355e-06, + "loss": 0.0027, + "step": 54029 + }, + { + "epoch": 16.69, + "learning_rate": 1.4056194640438058e-06, + "loss": 0.0022, + "step": 54030 + }, + { + "epoch": 16.69, + "learning_rate": 1.4053637944022857e-06, + "loss": 0.0031, + "step": 54031 + }, + { + "epoch": 16.69, + "learning_rate": 1.40510814625752e-06, + "loss": 0.0021, + "step": 54032 + }, + { + "epoch": 16.69, + "learning_rate": 1.404852519610148e-06, + "loss": 0.0028, + "step": 54033 + }, + { + "epoch": 16.69, + "learning_rate": 1.4045969144608074e-06, + "loss": 0.002, + "step": 54034 + }, + { + "epoch": 16.69, + "learning_rate": 1.404341330810135e-06, + "loss": 0.0031, + "step": 54035 + }, + { + "epoch": 16.69, + "learning_rate": 1.404085768658775e-06, + "loss": 0.0019, + "step": 54036 + }, + { + "epoch": 16.69, + "learning_rate": 1.4038302280073624e-06, + "loss": 0.0023, + "step": 54037 + }, + { + "epoch": 16.69, + "learning_rate": 1.4035747088565387e-06, + "loss": 0.0019, + "step": 54038 + }, + { + "epoch": 16.69, + "learning_rate": 1.4033192112069438e-06, + "loss": 0.0024, + "step": 54039 + }, + { + "epoch": 16.69, + "learning_rate": 1.403063735059217e-06, + "loss": 0.0019, + "step": 54040 + }, + { + "epoch": 16.69, + "learning_rate": 1.402808280413992e-06, + "loss": 0.0023, + "step": 54041 + }, + { + "epoch": 16.69, + "learning_rate": 1.4025528472719142e-06, + "loss": 0.0017, + "step": 54042 + }, + { + "epoch": 16.69, + "learning_rate": 1.4022974356336184e-06, + "loss": 0.0023, + "step": 54043 + }, + { + "epoch": 16.69, + "learning_rate": 1.4020420454997452e-06, + "loss": 0.0019, + "step": 54044 + }, + { + "epoch": 16.69, + "learning_rate": 1.4017866768709343e-06, + "loss": 0.0026, + "step": 54045 + }, + { + "epoch": 16.69, + "learning_rate": 1.4015313297478218e-06, + "loss": 0.0024, + "step": 54046 + }, + { + "epoch": 16.69, + "learning_rate": 1.4012760041310458e-06, + "loss": 0.0024, + "step": 54047 + }, + { + "epoch": 16.69, + "learning_rate": 1.4010207000212484e-06, + "loss": 0.0027, + "step": 54048 + }, + { + "epoch": 16.69, + "learning_rate": 1.4007654174190677e-06, + "loss": 0.0017, + "step": 54049 + }, + { + "epoch": 16.69, + "learning_rate": 1.4005101563251412e-06, + "loss": 0.0023, + "step": 54050 + }, + { + "epoch": 16.69, + "learning_rate": 1.4002549167401057e-06, + "loss": 0.0023, + "step": 54051 + }, + { + "epoch": 16.69, + "learning_rate": 1.3999996986646025e-06, + "loss": 0.0017, + "step": 54052 + }, + { + "epoch": 16.69, + "learning_rate": 1.3997445020992672e-06, + "loss": 0.0028, + "step": 54053 + }, + { + "epoch": 16.69, + "learning_rate": 1.3994893270447418e-06, + "loss": 0.0022, + "step": 54054 + }, + { + "epoch": 16.69, + "learning_rate": 1.3992341735016613e-06, + "loss": 0.0019, + "step": 54055 + }, + { + "epoch": 16.69, + "learning_rate": 1.3989790414706627e-06, + "loss": 0.0019, + "step": 54056 + }, + { + "epoch": 16.69, + "learning_rate": 1.398723930952387e-06, + "loss": 0.0016, + "step": 54057 + }, + { + "epoch": 16.69, + "learning_rate": 1.3984688419474735e-06, + "loss": 0.0025, + "step": 54058 + }, + { + "epoch": 16.69, + "learning_rate": 1.398213774456556e-06, + "loss": 0.0029, + "step": 54059 + }, + { + "epoch": 16.69, + "learning_rate": 1.3979587284802766e-06, + "loss": 0.0022, + "step": 54060 + }, + { + "epoch": 16.7, + "learning_rate": 1.397703704019272e-06, + "loss": 0.0031, + "step": 54061 + }, + { + "epoch": 16.7, + "learning_rate": 1.3974487010741767e-06, + "loss": 0.0019, + "step": 54062 + }, + { + "epoch": 16.7, + "learning_rate": 1.3971937196456309e-06, + "loss": 0.003, + "step": 54063 + }, + { + "epoch": 16.7, + "learning_rate": 1.3969387597342753e-06, + "loss": 0.0021, + "step": 54064 + }, + { + "epoch": 16.7, + "learning_rate": 1.3966838213407452e-06, + "loss": 0.0024, + "step": 54065 + }, + { + "epoch": 16.7, + "learning_rate": 1.3964289044656753e-06, + "loss": 0.002, + "step": 54066 + }, + { + "epoch": 16.7, + "learning_rate": 1.3961740091097087e-06, + "loss": 0.0017, + "step": 54067 + }, + { + "epoch": 16.7, + "learning_rate": 1.395919135273477e-06, + "loss": 0.0017, + "step": 54068 + }, + { + "epoch": 16.7, + "learning_rate": 1.3956642829576216e-06, + "loss": 0.0028, + "step": 54069 + }, + { + "epoch": 16.7, + "learning_rate": 1.3954094521627836e-06, + "loss": 0.0021, + "step": 54070 + }, + { + "epoch": 16.7, + "learning_rate": 1.3951546428895913e-06, + "loss": 0.003, + "step": 54071 + }, + { + "epoch": 16.7, + "learning_rate": 1.3948998551386862e-06, + "loss": 0.002, + "step": 54072 + }, + { + "epoch": 16.7, + "learning_rate": 1.394645088910709e-06, + "loss": 0.0023, + "step": 54073 + }, + { + "epoch": 16.7, + "learning_rate": 1.3943903442062911e-06, + "loss": 0.0022, + "step": 54074 + }, + { + "epoch": 16.7, + "learning_rate": 1.3941356210260747e-06, + "loss": 0.0023, + "step": 54075 + }, + { + "epoch": 16.7, + "learning_rate": 1.393880919370696e-06, + "loss": 0.0023, + "step": 54076 + }, + { + "epoch": 16.7, + "learning_rate": 1.3936262392407874e-06, + "loss": 0.002, + "step": 54077 + }, + { + "epoch": 16.7, + "learning_rate": 1.3933715806369896e-06, + "loss": 0.003, + "step": 54078 + }, + { + "epoch": 16.7, + "learning_rate": 1.393116943559939e-06, + "loss": 0.0023, + "step": 54079 + }, + { + "epoch": 16.7, + "learning_rate": 1.392862328010277e-06, + "loss": 0.0021, + "step": 54080 + }, + { + "epoch": 16.7, + "learning_rate": 1.3926077339886323e-06, + "loss": 0.0023, + "step": 54081 + }, + { + "epoch": 16.7, + "learning_rate": 1.3923531614956454e-06, + "loss": 0.0027, + "step": 54082 + }, + { + "epoch": 16.7, + "learning_rate": 1.3920986105319556e-06, + "loss": 0.0027, + "step": 54083 + }, + { + "epoch": 16.7, + "learning_rate": 1.3918440810981937e-06, + "loss": 0.0023, + "step": 54084 + }, + { + "epoch": 16.7, + "learning_rate": 1.3915895731950036e-06, + "loss": 0.0028, + "step": 54085 + }, + { + "epoch": 16.7, + "learning_rate": 1.391335086823017e-06, + "loss": 0.0029, + "step": 54086 + }, + { + "epoch": 16.7, + "learning_rate": 1.39108062198287e-06, + "loss": 0.0017, + "step": 54087 + }, + { + "epoch": 16.7, + "learning_rate": 1.3908261786751998e-06, + "loss": 0.0015, + "step": 54088 + }, + { + "epoch": 16.7, + "learning_rate": 1.390571756900646e-06, + "loss": 0.0032, + "step": 54089 + }, + { + "epoch": 16.7, + "learning_rate": 1.3903173566598426e-06, + "loss": 0.0029, + "step": 54090 + }, + { + "epoch": 16.7, + "learning_rate": 1.3900629779534236e-06, + "loss": 0.0027, + "step": 54091 + }, + { + "epoch": 16.7, + "learning_rate": 1.3898086207820305e-06, + "loss": 0.0022, + "step": 54092 + }, + { + "epoch": 16.7, + "learning_rate": 1.3895542851462928e-06, + "loss": 0.0023, + "step": 54093 + }, + { + "epoch": 16.71, + "learning_rate": 1.3892999710468513e-06, + "loss": 0.0023, + "step": 54094 + }, + { + "epoch": 16.71, + "learning_rate": 1.389045678484342e-06, + "loss": 0.0013, + "step": 54095 + }, + { + "epoch": 16.71, + "learning_rate": 1.388791407459401e-06, + "loss": 0.0021, + "step": 54096 + }, + { + "epoch": 16.71, + "learning_rate": 1.3885371579726614e-06, + "loss": 0.0031, + "step": 54097 + }, + { + "epoch": 16.71, + "learning_rate": 1.3882829300247624e-06, + "loss": 0.0024, + "step": 54098 + }, + { + "epoch": 16.71, + "learning_rate": 1.388028723616337e-06, + "loss": 0.0023, + "step": 54099 + }, + { + "epoch": 16.71, + "learning_rate": 1.3877745387480246e-06, + "loss": 0.0031, + "step": 54100 + }, + { + "epoch": 16.71, + "learning_rate": 1.387520375420458e-06, + "loss": 0.0016, + "step": 54101 + }, + { + "epoch": 16.71, + "learning_rate": 1.3872662336342723e-06, + "loss": 0.0025, + "step": 54102 + }, + { + "epoch": 16.71, + "learning_rate": 1.3870121133901038e-06, + "loss": 0.0023, + "step": 54103 + }, + { + "epoch": 16.71, + "learning_rate": 1.3867580146885918e-06, + "loss": 0.0019, + "step": 54104 + }, + { + "epoch": 16.71, + "learning_rate": 1.386503937530367e-06, + "loss": 0.0023, + "step": 54105 + }, + { + "epoch": 16.71, + "learning_rate": 1.3862498819160686e-06, + "loss": 0.0021, + "step": 54106 + }, + { + "epoch": 16.71, + "learning_rate": 1.385995847846331e-06, + "loss": 0.002, + "step": 54107 + }, + { + "epoch": 16.71, + "learning_rate": 1.3857418353217854e-06, + "loss": 0.0022, + "step": 54108 + }, + { + "epoch": 16.71, + "learning_rate": 1.385487844343072e-06, + "loss": 0.0018, + "step": 54109 + }, + { + "epoch": 16.71, + "learning_rate": 1.3852338749108263e-06, + "loss": 0.0032, + "step": 54110 + }, + { + "epoch": 16.71, + "learning_rate": 1.3849799270256814e-06, + "loss": 0.0018, + "step": 54111 + }, + { + "epoch": 16.71, + "learning_rate": 1.3847260006882712e-06, + "loss": 0.003, + "step": 54112 + }, + { + "epoch": 16.71, + "learning_rate": 1.384472095899233e-06, + "loss": 0.002, + "step": 54113 + }, + { + "epoch": 16.71, + "learning_rate": 1.384218212659203e-06, + "loss": 0.0022, + "step": 54114 + }, + { + "epoch": 16.71, + "learning_rate": 1.3839643509688128e-06, + "loss": 0.0027, + "step": 54115 + }, + { + "epoch": 16.71, + "learning_rate": 1.3837105108287008e-06, + "loss": 0.0018, + "step": 54116 + }, + { + "epoch": 16.71, + "learning_rate": 1.3834566922395009e-06, + "loss": 0.0027, + "step": 54117 + }, + { + "epoch": 16.71, + "learning_rate": 1.3832028952018462e-06, + "loss": 0.0025, + "step": 54118 + }, + { + "epoch": 16.71, + "learning_rate": 1.3829491197163715e-06, + "loss": 0.0019, + "step": 54119 + }, + { + "epoch": 16.71, + "learning_rate": 1.382695365783715e-06, + "loss": 0.002, + "step": 54120 + }, + { + "epoch": 16.71, + "learning_rate": 1.3824416334045087e-06, + "loss": 0.0021, + "step": 54121 + }, + { + "epoch": 16.71, + "learning_rate": 1.3821879225793855e-06, + "loss": 0.0028, + "step": 54122 + }, + { + "epoch": 16.71, + "learning_rate": 1.3819342333089847e-06, + "loss": 0.003, + "step": 54123 + }, + { + "epoch": 16.71, + "learning_rate": 1.3816805655939359e-06, + "loss": 0.0019, + "step": 54124 + }, + { + "epoch": 16.71, + "learning_rate": 1.3814269194348762e-06, + "loss": 0.0018, + "step": 54125 + }, + { + "epoch": 16.72, + "learning_rate": 1.3811732948324419e-06, + "loss": 0.0023, + "step": 54126 + }, + { + "epoch": 16.72, + "learning_rate": 1.3809196917872648e-06, + "loss": 0.002, + "step": 54127 + }, + { + "epoch": 16.72, + "learning_rate": 1.3806661102999774e-06, + "loss": 0.0024, + "step": 54128 + }, + { + "epoch": 16.72, + "learning_rate": 1.3804125503712185e-06, + "loss": 0.0023, + "step": 54129 + }, + { + "epoch": 16.72, + "learning_rate": 1.3801590120016173e-06, + "loss": 0.0023, + "step": 54130 + }, + { + "epoch": 16.72, + "learning_rate": 1.3799054951918134e-06, + "loss": 0.0024, + "step": 54131 + }, + { + "epoch": 16.72, + "learning_rate": 1.3796519999424384e-06, + "loss": 0.0028, + "step": 54132 + }, + { + "epoch": 16.72, + "learning_rate": 1.3793985262541233e-06, + "loss": 0.0022, + "step": 54133 + }, + { + "epoch": 16.72, + "learning_rate": 1.3791450741275037e-06, + "loss": 0.002, + "step": 54134 + }, + { + "epoch": 16.72, + "learning_rate": 1.3788916435632182e-06, + "loss": 0.0017, + "step": 54135 + }, + { + "epoch": 16.72, + "learning_rate": 1.3786382345618944e-06, + "loss": 0.002, + "step": 54136 + }, + { + "epoch": 16.72, + "learning_rate": 1.3783848471241712e-06, + "loss": 0.0034, + "step": 54137 + }, + { + "epoch": 16.72, + "learning_rate": 1.3781314812506796e-06, + "loss": 0.003, + "step": 54138 + }, + { + "epoch": 16.72, + "learning_rate": 1.3778781369420523e-06, + "loss": 0.0019, + "step": 54139 + }, + { + "epoch": 16.72, + "learning_rate": 1.3776248141989235e-06, + "loss": 0.0017, + "step": 54140 + }, + { + "epoch": 16.72, + "learning_rate": 1.3773715130219301e-06, + "loss": 0.002, + "step": 54141 + }, + { + "epoch": 16.72, + "learning_rate": 1.3771182334117038e-06, + "loss": 0.0021, + "step": 54142 + }, + { + "epoch": 16.72, + "learning_rate": 1.3768649753688746e-06, + "loss": 0.0031, + "step": 54143 + }, + { + "epoch": 16.72, + "learning_rate": 1.3766117388940792e-06, + "loss": 0.0019, + "step": 54144 + }, + { + "epoch": 16.72, + "learning_rate": 1.3763585239879528e-06, + "loss": 0.0018, + "step": 54145 + }, + { + "epoch": 16.72, + "learning_rate": 1.376105330651124e-06, + "loss": 0.0022, + "step": 54146 + }, + { + "epoch": 16.72, + "learning_rate": 1.3758521588842312e-06, + "loss": 0.002, + "step": 54147 + }, + { + "epoch": 16.72, + "learning_rate": 1.3755990086879045e-06, + "loss": 0.0018, + "step": 54148 + }, + { + "epoch": 16.72, + "learning_rate": 1.3753458800627761e-06, + "loss": 0.0026, + "step": 54149 + }, + { + "epoch": 16.72, + "learning_rate": 1.375092773009481e-06, + "loss": 0.0029, + "step": 54150 + }, + { + "epoch": 16.72, + "learning_rate": 1.374839687528654e-06, + "loss": 0.0018, + "step": 54151 + }, + { + "epoch": 16.72, + "learning_rate": 1.374586623620926e-06, + "loss": 0.0023, + "step": 54152 + }, + { + "epoch": 16.72, + "learning_rate": 1.3743335812869274e-06, + "loss": 0.0018, + "step": 54153 + }, + { + "epoch": 16.72, + "learning_rate": 1.3740805605272967e-06, + "loss": 0.0021, + "step": 54154 + }, + { + "epoch": 16.72, + "learning_rate": 1.373827561342661e-06, + "loss": 0.0023, + "step": 54155 + }, + { + "epoch": 16.72, + "learning_rate": 1.3735745837336556e-06, + "loss": 0.0031, + "step": 54156 + }, + { + "epoch": 16.72, + "learning_rate": 1.3733216277009164e-06, + "loss": 0.0025, + "step": 54157 + }, + { + "epoch": 16.72, + "learning_rate": 1.3730686932450732e-06, + "loss": 0.0024, + "step": 54158 + }, + { + "epoch": 16.73, + "learning_rate": 1.3728157803667562e-06, + "loss": 0.0021, + "step": 54159 + }, + { + "epoch": 16.73, + "learning_rate": 1.3725628890666021e-06, + "loss": 0.003, + "step": 54160 + }, + { + "epoch": 16.73, + "learning_rate": 1.3723100193452398e-06, + "loss": 0.002, + "step": 54161 + }, + { + "epoch": 16.73, + "learning_rate": 1.372057171203307e-06, + "loss": 0.0025, + "step": 54162 + }, + { + "epoch": 16.73, + "learning_rate": 1.371804344641432e-06, + "loss": 0.0022, + "step": 54163 + }, + { + "epoch": 16.73, + "learning_rate": 1.3715515396602452e-06, + "loss": 0.0023, + "step": 54164 + }, + { + "epoch": 16.73, + "learning_rate": 1.371298756260383e-06, + "loss": 0.0022, + "step": 54165 + }, + { + "epoch": 16.73, + "learning_rate": 1.371045994442478e-06, + "loss": 0.0022, + "step": 54166 + }, + { + "epoch": 16.73, + "learning_rate": 1.370793254207159e-06, + "loss": 0.0018, + "step": 54167 + }, + { + "epoch": 16.73, + "learning_rate": 1.3705405355550616e-06, + "loss": 0.0029, + "step": 54168 + }, + { + "epoch": 16.73, + "learning_rate": 1.3702878384868167e-06, + "loss": 0.0029, + "step": 54169 + }, + { + "epoch": 16.73, + "learning_rate": 1.370035163003053e-06, + "loss": 0.0023, + "step": 54170 + }, + { + "epoch": 16.73, + "learning_rate": 1.3697825091044059e-06, + "loss": 0.0019, + "step": 54171 + }, + { + "epoch": 16.73, + "learning_rate": 1.3695298767915088e-06, + "loss": 0.0023, + "step": 54172 + }, + { + "epoch": 16.73, + "learning_rate": 1.3692772660649912e-06, + "loss": 0.0027, + "step": 54173 + }, + { + "epoch": 16.73, + "learning_rate": 1.3690246769254833e-06, + "loss": 0.0017, + "step": 54174 + }, + { + "epoch": 16.73, + "learning_rate": 1.3687721093736216e-06, + "loss": 0.0018, + "step": 54175 + }, + { + "epoch": 16.73, + "learning_rate": 1.3685195634100324e-06, + "loss": 0.0026, + "step": 54176 + }, + { + "epoch": 16.73, + "learning_rate": 1.3682670390353504e-06, + "loss": 0.0022, + "step": 54177 + }, + { + "epoch": 16.73, + "learning_rate": 1.3680145362502096e-06, + "loss": 0.0022, + "step": 54178 + }, + { + "epoch": 16.73, + "learning_rate": 1.3677620550552373e-06, + "loss": 0.0024, + "step": 54179 + }, + { + "epoch": 16.73, + "learning_rate": 1.3675095954510654e-06, + "loss": 0.0028, + "step": 54180 + }, + { + "epoch": 16.73, + "learning_rate": 1.3672571574383264e-06, + "loss": 0.0017, + "step": 54181 + }, + { + "epoch": 16.73, + "learning_rate": 1.3670047410176534e-06, + "loss": 0.0018, + "step": 54182 + }, + { + "epoch": 16.73, + "learning_rate": 1.366752346189677e-06, + "loss": 0.0024, + "step": 54183 + }, + { + "epoch": 16.73, + "learning_rate": 1.3664999729550244e-06, + "loss": 0.0019, + "step": 54184 + }, + { + "epoch": 16.73, + "learning_rate": 1.3662476213143327e-06, + "loss": 0.0026, + "step": 54185 + }, + { + "epoch": 16.73, + "learning_rate": 1.3659952912682283e-06, + "loss": 0.0027, + "step": 54186 + }, + { + "epoch": 16.73, + "learning_rate": 1.365742982817344e-06, + "loss": 0.0023, + "step": 54187 + }, + { + "epoch": 16.73, + "learning_rate": 1.3654906959623138e-06, + "loss": 0.0037, + "step": 54188 + }, + { + "epoch": 16.73, + "learning_rate": 1.365238430703767e-06, + "loss": 0.0022, + "step": 54189 + }, + { + "epoch": 16.73, + "learning_rate": 1.364986187042331e-06, + "loss": 0.0022, + "step": 54190 + }, + { + "epoch": 16.74, + "learning_rate": 1.3647339649786407e-06, + "loss": 0.0028, + "step": 54191 + }, + { + "epoch": 16.74, + "learning_rate": 1.3644817645133246e-06, + "loss": 0.0014, + "step": 54192 + }, + { + "epoch": 16.74, + "learning_rate": 1.3642295856470168e-06, + "loss": 0.0027, + "step": 54193 + }, + { + "epoch": 16.74, + "learning_rate": 1.3639774283803454e-06, + "loss": 0.0028, + "step": 54194 + }, + { + "epoch": 16.74, + "learning_rate": 1.3637252927139389e-06, + "loss": 0.0018, + "step": 54195 + }, + { + "epoch": 16.74, + "learning_rate": 1.3634731786484313e-06, + "loss": 0.0039, + "step": 54196 + }, + { + "epoch": 16.74, + "learning_rate": 1.3632210861844552e-06, + "loss": 0.0027, + "step": 54197 + }, + { + "epoch": 16.74, + "learning_rate": 1.362969015322635e-06, + "loss": 0.0027, + "step": 54198 + }, + { + "epoch": 16.74, + "learning_rate": 1.3627169660636075e-06, + "loss": 0.0021, + "step": 54199 + }, + { + "epoch": 16.74, + "learning_rate": 1.3624649384080003e-06, + "loss": 0.0029, + "step": 54200 + }, + { + "epoch": 16.74, + "learning_rate": 1.3622129323564414e-06, + "loss": 0.0019, + "step": 54201 + }, + { + "epoch": 16.74, + "learning_rate": 1.361960947909563e-06, + "loss": 0.0024, + "step": 54202 + }, + { + "epoch": 16.74, + "learning_rate": 1.3617089850679989e-06, + "loss": 0.0017, + "step": 54203 + }, + { + "epoch": 16.74, + "learning_rate": 1.361457043832375e-06, + "loss": 0.0021, + "step": 54204 + }, + { + "epoch": 16.74, + "learning_rate": 1.3612051242033209e-06, + "loss": 0.0023, + "step": 54205 + }, + { + "epoch": 16.74, + "learning_rate": 1.3609532261814706e-06, + "loss": 0.002, + "step": 54206 + }, + { + "epoch": 16.74, + "learning_rate": 1.3607013497674505e-06, + "loss": 0.0027, + "step": 54207 + }, + { + "epoch": 16.74, + "learning_rate": 1.3604494949618907e-06, + "loss": 0.0024, + "step": 54208 + }, + { + "epoch": 16.74, + "learning_rate": 1.3601976617654256e-06, + "loss": 0.0022, + "step": 54209 + }, + { + "epoch": 16.74, + "learning_rate": 1.3599458501786812e-06, + "loss": 0.0022, + "step": 54210 + }, + { + "epoch": 16.74, + "learning_rate": 1.3596940602022869e-06, + "loss": 0.0017, + "step": 54211 + }, + { + "epoch": 16.74, + "learning_rate": 1.3594422918368722e-06, + "loss": 0.0024, + "step": 54212 + }, + { + "epoch": 16.74, + "learning_rate": 1.3591905450830723e-06, + "loss": 0.0022, + "step": 54213 + }, + { + "epoch": 16.74, + "learning_rate": 1.358938819941511e-06, + "loss": 0.0025, + "step": 54214 + }, + { + "epoch": 16.74, + "learning_rate": 1.358687116412819e-06, + "loss": 0.0017, + "step": 54215 + }, + { + "epoch": 16.74, + "learning_rate": 1.358435434497628e-06, + "loss": 0.0019, + "step": 54216 + }, + { + "epoch": 16.74, + "learning_rate": 1.3581837741965641e-06, + "loss": 0.003, + "step": 54217 + }, + { + "epoch": 16.74, + "learning_rate": 1.357932135510258e-06, + "loss": 0.0028, + "step": 54218 + }, + { + "epoch": 16.74, + "learning_rate": 1.357680518439346e-06, + "loss": 0.002, + "step": 54219 + }, + { + "epoch": 16.74, + "learning_rate": 1.357428922984445e-06, + "loss": 0.0021, + "step": 54220 + }, + { + "epoch": 16.74, + "learning_rate": 1.3571773491461915e-06, + "loss": 0.0017, + "step": 54221 + }, + { + "epoch": 16.74, + "learning_rate": 1.3569257969252158e-06, + "loss": 0.0023, + "step": 54222 + }, + { + "epoch": 16.75, + "learning_rate": 1.3566742663221433e-06, + "loss": 0.0027, + "step": 54223 + }, + { + "epoch": 16.75, + "learning_rate": 1.3564227573376065e-06, + "loss": 0.002, + "step": 54224 + }, + { + "epoch": 16.75, + "learning_rate": 1.356171269972234e-06, + "loss": 0.0024, + "step": 54225 + }, + { + "epoch": 16.75, + "learning_rate": 1.3559198042266508e-06, + "loss": 0.002, + "step": 54226 + }, + { + "epoch": 16.75, + "learning_rate": 1.3556683601014885e-06, + "loss": 0.0029, + "step": 54227 + }, + { + "epoch": 16.75, + "learning_rate": 1.355416937597378e-06, + "loss": 0.0022, + "step": 54228 + }, + { + "epoch": 16.75, + "learning_rate": 1.3551655367149474e-06, + "loss": 0.0029, + "step": 54229 + }, + { + "epoch": 16.75, + "learning_rate": 1.354914157454822e-06, + "loss": 0.002, + "step": 54230 + }, + { + "epoch": 16.75, + "learning_rate": 1.3546627998176354e-06, + "loss": 0.0026, + "step": 54231 + }, + { + "epoch": 16.75, + "learning_rate": 1.3544114638040107e-06, + "loss": 0.0024, + "step": 54232 + }, + { + "epoch": 16.75, + "learning_rate": 1.3541601494145805e-06, + "loss": 0.0016, + "step": 54233 + }, + { + "epoch": 16.75, + "learning_rate": 1.3539088566499758e-06, + "loss": 0.0023, + "step": 54234 + }, + { + "epoch": 16.75, + "learning_rate": 1.3536575855108215e-06, + "loss": 0.0026, + "step": 54235 + }, + { + "epoch": 16.75, + "learning_rate": 1.3534063359977434e-06, + "loss": 0.0021, + "step": 54236 + }, + { + "epoch": 16.75, + "learning_rate": 1.3531551081113757e-06, + "loss": 0.0019, + "step": 54237 + }, + { + "epoch": 16.75, + "learning_rate": 1.3529039018523426e-06, + "loss": 0.002, + "step": 54238 + }, + { + "epoch": 16.75, + "learning_rate": 1.3526527172212756e-06, + "loss": 0.0014, + "step": 54239 + }, + { + "epoch": 16.75, + "learning_rate": 1.3524015542188018e-06, + "loss": 0.0022, + "step": 54240 + }, + { + "epoch": 16.75, + "learning_rate": 1.3521504128455465e-06, + "loss": 0.0027, + "step": 54241 + }, + { + "epoch": 16.75, + "learning_rate": 1.3518992931021401e-06, + "loss": 0.0023, + "step": 54242 + }, + { + "epoch": 16.75, + "learning_rate": 1.3516481949892113e-06, + "loss": 0.002, + "step": 54243 + }, + { + "epoch": 16.75, + "learning_rate": 1.3513971185073893e-06, + "loss": 0.0018, + "step": 54244 + }, + { + "epoch": 16.75, + "learning_rate": 1.3511460636573003e-06, + "loss": 0.0023, + "step": 54245 + }, + { + "epoch": 16.75, + "learning_rate": 1.3508950304395718e-06, + "loss": 0.002, + "step": 54246 + }, + { + "epoch": 16.75, + "learning_rate": 1.3506440188548331e-06, + "loss": 0.0022, + "step": 54247 + }, + { + "epoch": 16.75, + "learning_rate": 1.3503930289037093e-06, + "loss": 0.0023, + "step": 54248 + }, + { + "epoch": 16.75, + "learning_rate": 1.3501420605868332e-06, + "loss": 0.0022, + "step": 54249 + }, + { + "epoch": 16.75, + "learning_rate": 1.3498911139048288e-06, + "loss": 0.0023, + "step": 54250 + }, + { + "epoch": 16.75, + "learning_rate": 1.3496401888583223e-06, + "loss": 0.002, + "step": 54251 + }, + { + "epoch": 16.75, + "learning_rate": 1.349389285447943e-06, + "loss": 0.0021, + "step": 54252 + }, + { + "epoch": 16.75, + "learning_rate": 1.3491384036743204e-06, + "loss": 0.0025, + "step": 54253 + }, + { + "epoch": 16.75, + "learning_rate": 1.34888754353808e-06, + "loss": 0.0017, + "step": 54254 + }, + { + "epoch": 16.75, + "learning_rate": 1.3486367050398507e-06, + "loss": 0.0022, + "step": 54255 + }, + { + "epoch": 16.76, + "learning_rate": 1.3483858881802591e-06, + "loss": 0.0022, + "step": 54256 + }, + { + "epoch": 16.76, + "learning_rate": 1.3481350929599313e-06, + "loss": 0.0028, + "step": 54257 + }, + { + "epoch": 16.76, + "learning_rate": 1.3478843193794943e-06, + "loss": 0.0028, + "step": 54258 + }, + { + "epoch": 16.76, + "learning_rate": 1.347633567439579e-06, + "loss": 0.0029, + "step": 54259 + }, + { + "epoch": 16.76, + "learning_rate": 1.3473828371408104e-06, + "loss": 0.0016, + "step": 54260 + }, + { + "epoch": 16.76, + "learning_rate": 1.3471321284838134e-06, + "loss": 0.002, + "step": 54261 + }, + { + "epoch": 16.76, + "learning_rate": 1.34688144146922e-06, + "loss": 0.0018, + "step": 54262 + }, + { + "epoch": 16.76, + "learning_rate": 1.3466307760976517e-06, + "loss": 0.0022, + "step": 54263 + }, + { + "epoch": 16.76, + "learning_rate": 1.3463801323697378e-06, + "loss": 0.0019, + "step": 54264 + }, + { + "epoch": 16.76, + "learning_rate": 1.3461295102861072e-06, + "loss": 0.0021, + "step": 54265 + }, + { + "epoch": 16.76, + "learning_rate": 1.3458789098473857e-06, + "loss": 0.0028, + "step": 54266 + }, + { + "epoch": 16.76, + "learning_rate": 1.3456283310541972e-06, + "loss": 0.003, + "step": 54267 + }, + { + "epoch": 16.76, + "learning_rate": 1.3453777739071727e-06, + "loss": 0.0029, + "step": 54268 + }, + { + "epoch": 16.76, + "learning_rate": 1.3451272384069347e-06, + "loss": 0.0025, + "step": 54269 + }, + { + "epoch": 16.76, + "learning_rate": 1.344876724554115e-06, + "loss": 0.0022, + "step": 54270 + }, + { + "epoch": 16.76, + "learning_rate": 1.3446262323493364e-06, + "loss": 0.0023, + "step": 54271 + }, + { + "epoch": 16.76, + "learning_rate": 1.344375761793224e-06, + "loss": 0.0028, + "step": 54272 + }, + { + "epoch": 16.76, + "learning_rate": 1.3441253128864074e-06, + "loss": 0.0017, + "step": 54273 + }, + { + "epoch": 16.76, + "learning_rate": 1.3438748856295136e-06, + "loss": 0.0024, + "step": 54274 + }, + { + "epoch": 16.76, + "learning_rate": 1.3436244800231657e-06, + "loss": 0.0023, + "step": 54275 + }, + { + "epoch": 16.76, + "learning_rate": 1.343374096067993e-06, + "loss": 0.003, + "step": 54276 + }, + { + "epoch": 16.76, + "learning_rate": 1.3431237337646197e-06, + "loss": 0.0017, + "step": 54277 + }, + { + "epoch": 16.76, + "learning_rate": 1.342873393113674e-06, + "loss": 0.002, + "step": 54278 + }, + { + "epoch": 16.76, + "learning_rate": 1.3426230741157798e-06, + "loss": 0.0025, + "step": 54279 + }, + { + "epoch": 16.76, + "learning_rate": 1.3423727767715655e-06, + "loss": 0.002, + "step": 54280 + }, + { + "epoch": 16.76, + "learning_rate": 1.3421225010816563e-06, + "loss": 0.0017, + "step": 54281 + }, + { + "epoch": 16.76, + "learning_rate": 1.341872247046675e-06, + "loss": 0.0024, + "step": 54282 + }, + { + "epoch": 16.76, + "learning_rate": 1.3416220146672509e-06, + "loss": 0.0016, + "step": 54283 + }, + { + "epoch": 16.76, + "learning_rate": 1.3413718039440115e-06, + "loss": 0.0026, + "step": 54284 + }, + { + "epoch": 16.76, + "learning_rate": 1.3411216148775785e-06, + "loss": 0.0029, + "step": 54285 + }, + { + "epoch": 16.76, + "learning_rate": 1.3408714474685814e-06, + "loss": 0.0032, + "step": 54286 + }, + { + "epoch": 16.76, + "learning_rate": 1.340621301717645e-06, + "loss": 0.0022, + "step": 54287 + }, + { + "epoch": 16.77, + "learning_rate": 1.3403711776253914e-06, + "loss": 0.0025, + "step": 54288 + }, + { + "epoch": 16.77, + "learning_rate": 1.3401210751924486e-06, + "loss": 0.0031, + "step": 54289 + }, + { + "epoch": 16.77, + "learning_rate": 1.3398709944194443e-06, + "loss": 0.0025, + "step": 54290 + }, + { + "epoch": 16.77, + "learning_rate": 1.3396209353070034e-06, + "loss": 0.0019, + "step": 54291 + }, + { + "epoch": 16.77, + "learning_rate": 1.3393708978557475e-06, + "loss": 0.0018, + "step": 54292 + }, + { + "epoch": 16.77, + "learning_rate": 1.339120882066306e-06, + "loss": 0.0014, + "step": 54293 + }, + { + "epoch": 16.77, + "learning_rate": 1.3388708879393008e-06, + "loss": 0.002, + "step": 54294 + }, + { + "epoch": 16.77, + "learning_rate": 1.3386209154753593e-06, + "loss": 0.0021, + "step": 54295 + }, + { + "epoch": 16.77, + "learning_rate": 1.3383709646751097e-06, + "loss": 0.0021, + "step": 54296 + }, + { + "epoch": 16.77, + "learning_rate": 1.3381210355391728e-06, + "loss": 0.0019, + "step": 54297 + }, + { + "epoch": 16.77, + "learning_rate": 1.3378711280681733e-06, + "loss": 0.0022, + "step": 54298 + }, + { + "epoch": 16.77, + "learning_rate": 1.337621242262741e-06, + "loss": 0.0026, + "step": 54299 + }, + { + "epoch": 16.77, + "learning_rate": 1.3373713781234943e-06, + "loss": 0.0029, + "step": 54300 + }, + { + "epoch": 16.77, + "learning_rate": 1.3371215356510646e-06, + "loss": 0.0028, + "step": 54301 + }, + { + "epoch": 16.77, + "learning_rate": 1.336871714846074e-06, + "loss": 0.0023, + "step": 54302 + }, + { + "epoch": 16.77, + "learning_rate": 1.3366219157091453e-06, + "loss": 0.0016, + "step": 54303 + }, + { + "epoch": 16.77, + "learning_rate": 1.3363721382409057e-06, + "loss": 0.0023, + "step": 54304 + }, + { + "epoch": 16.77, + "learning_rate": 1.336122382441981e-06, + "loss": 0.0025, + "step": 54305 + }, + { + "epoch": 16.77, + "learning_rate": 1.3358726483129925e-06, + "loss": 0.0049, + "step": 54306 + }, + { + "epoch": 16.77, + "learning_rate": 1.335622935854568e-06, + "loss": 0.002, + "step": 54307 + }, + { + "epoch": 16.77, + "learning_rate": 1.3353732450673296e-06, + "loss": 0.002, + "step": 54308 + }, + { + "epoch": 16.77, + "learning_rate": 1.3351235759519054e-06, + "loss": 0.0021, + "step": 54309 + }, + { + "epoch": 16.77, + "learning_rate": 1.3348739285089152e-06, + "loss": 0.0021, + "step": 54310 + }, + { + "epoch": 16.77, + "learning_rate": 1.334624302738987e-06, + "loss": 0.0023, + "step": 54311 + }, + { + "epoch": 16.77, + "learning_rate": 1.334374698642744e-06, + "loss": 0.002, + "step": 54312 + }, + { + "epoch": 16.77, + "learning_rate": 1.3341251162208091e-06, + "loss": 0.0023, + "step": 54313 + }, + { + "epoch": 16.77, + "learning_rate": 1.333875555473808e-06, + "loss": 0.0018, + "step": 54314 + }, + { + "epoch": 16.77, + "learning_rate": 1.3336260164023662e-06, + "loss": 0.003, + "step": 54315 + }, + { + "epoch": 16.77, + "learning_rate": 1.333376499007104e-06, + "loss": 0.0024, + "step": 54316 + }, + { + "epoch": 16.77, + "learning_rate": 1.3331270032886513e-06, + "loss": 0.0031, + "step": 54317 + }, + { + "epoch": 16.77, + "learning_rate": 1.332877529247627e-06, + "loss": 0.0027, + "step": 54318 + }, + { + "epoch": 16.77, + "learning_rate": 1.3326280768846556e-06, + "loss": 0.0022, + "step": 54319 + }, + { + "epoch": 16.77, + "learning_rate": 1.3323786462003629e-06, + "loss": 0.0026, + "step": 54320 + }, + { + "epoch": 16.78, + "learning_rate": 1.3321292371953732e-06, + "loss": 0.0022, + "step": 54321 + }, + { + "epoch": 16.78, + "learning_rate": 1.331879849870309e-06, + "loss": 0.002, + "step": 54322 + }, + { + "epoch": 16.78, + "learning_rate": 1.3316304842257933e-06, + "loss": 0.0022, + "step": 54323 + }, + { + "epoch": 16.78, + "learning_rate": 1.3313811402624522e-06, + "loss": 0.0018, + "step": 54324 + }, + { + "epoch": 16.78, + "learning_rate": 1.3311318179809052e-06, + "loss": 0.0023, + "step": 54325 + }, + { + "epoch": 16.78, + "learning_rate": 1.3308825173817796e-06, + "loss": 0.0033, + "step": 54326 + }, + { + "epoch": 16.78, + "learning_rate": 1.3306332384657018e-06, + "loss": 0.0023, + "step": 54327 + }, + { + "epoch": 16.78, + "learning_rate": 1.3303839812332864e-06, + "loss": 0.0015, + "step": 54328 + }, + { + "epoch": 16.78, + "learning_rate": 1.3301347456851632e-06, + "loss": 0.0019, + "step": 54329 + }, + { + "epoch": 16.78, + "learning_rate": 1.3298855318219562e-06, + "loss": 0.002, + "step": 54330 + }, + { + "epoch": 16.78, + "learning_rate": 1.3296363396442845e-06, + "loss": 0.0036, + "step": 54331 + }, + { + "epoch": 16.78, + "learning_rate": 1.329387169152775e-06, + "loss": 0.0018, + "step": 54332 + }, + { + "epoch": 16.78, + "learning_rate": 1.3291380203480509e-06, + "loss": 0.002, + "step": 54333 + }, + { + "epoch": 16.78, + "learning_rate": 1.3288888932307309e-06, + "loss": 0.0022, + "step": 54334 + }, + { + "epoch": 16.78, + "learning_rate": 1.3286397878014423e-06, + "loss": 0.0021, + "step": 54335 + }, + { + "epoch": 16.78, + "learning_rate": 1.3283907040608091e-06, + "loss": 0.0027, + "step": 54336 + }, + { + "epoch": 16.78, + "learning_rate": 1.3281416420094517e-06, + "loss": 0.0022, + "step": 54337 + }, + { + "epoch": 16.78, + "learning_rate": 1.327892601647992e-06, + "loss": 0.0026, + "step": 54338 + }, + { + "epoch": 16.78, + "learning_rate": 1.3276435829770562e-06, + "loss": 0.0019, + "step": 54339 + }, + { + "epoch": 16.78, + "learning_rate": 1.3273945859972637e-06, + "loss": 0.0022, + "step": 54340 + }, + { + "epoch": 16.78, + "learning_rate": 1.3271456107092396e-06, + "loss": 0.002, + "step": 54341 + }, + { + "epoch": 16.78, + "learning_rate": 1.3268966571136077e-06, + "loss": 0.0028, + "step": 54342 + }, + { + "epoch": 16.78, + "learning_rate": 1.32664772521099e-06, + "loss": 0.0017, + "step": 54343 + }, + { + "epoch": 16.78, + "learning_rate": 1.3263988150020047e-06, + "loss": 0.0027, + "step": 54344 + }, + { + "epoch": 16.78, + "learning_rate": 1.326149926487279e-06, + "loss": 0.003, + "step": 54345 + }, + { + "epoch": 16.78, + "learning_rate": 1.325901059667436e-06, + "loss": 0.0024, + "step": 54346 + }, + { + "epoch": 16.78, + "learning_rate": 1.3256522145430971e-06, + "loss": 0.0037, + "step": 54347 + }, + { + "epoch": 16.78, + "learning_rate": 1.3254033911148811e-06, + "loss": 0.0019, + "step": 54348 + }, + { + "epoch": 16.78, + "learning_rate": 1.3251545893834162e-06, + "loss": 0.0028, + "step": 54349 + }, + { + "epoch": 16.78, + "learning_rate": 1.3249058093493194e-06, + "loss": 0.0028, + "step": 54350 + }, + { + "epoch": 16.78, + "learning_rate": 1.3246570510132162e-06, + "loss": 0.0018, + "step": 54351 + }, + { + "epoch": 16.78, + "learning_rate": 1.324408314375729e-06, + "loss": 0.0027, + "step": 54352 + }, + { + "epoch": 16.79, + "learning_rate": 1.32415959943748e-06, + "loss": 0.0022, + "step": 54353 + }, + { + "epoch": 16.79, + "learning_rate": 1.3239109061990874e-06, + "loss": 0.0022, + "step": 54354 + }, + { + "epoch": 16.79, + "learning_rate": 1.3236622346611782e-06, + "loss": 0.0015, + "step": 54355 + }, + { + "epoch": 16.79, + "learning_rate": 1.3234135848243702e-06, + "loss": 0.003, + "step": 54356 + }, + { + "epoch": 16.79, + "learning_rate": 1.323164956689289e-06, + "loss": 0.0024, + "step": 54357 + }, + { + "epoch": 16.79, + "learning_rate": 1.3229163502565556e-06, + "loss": 0.0024, + "step": 54358 + }, + { + "epoch": 16.79, + "learning_rate": 1.3226677655267883e-06, + "loss": 0.0022, + "step": 54359 + }, + { + "epoch": 16.79, + "learning_rate": 1.322419202500611e-06, + "loss": 0.0016, + "step": 54360 + }, + { + "epoch": 16.79, + "learning_rate": 1.32217066117865e-06, + "loss": 0.0025, + "step": 54361 + }, + { + "epoch": 16.79, + "learning_rate": 1.321922141561519e-06, + "loss": 0.0026, + "step": 54362 + }, + { + "epoch": 16.79, + "learning_rate": 1.3216736436498468e-06, + "loss": 0.0019, + "step": 54363 + }, + { + "epoch": 16.79, + "learning_rate": 1.3214251674442513e-06, + "loss": 0.0022, + "step": 54364 + }, + { + "epoch": 16.79, + "learning_rate": 1.3211767129453512e-06, + "loss": 0.0025, + "step": 54365 + }, + { + "epoch": 16.79, + "learning_rate": 1.3209282801537727e-06, + "loss": 0.0023, + "step": 54366 + }, + { + "epoch": 16.79, + "learning_rate": 1.320679869070136e-06, + "loss": 0.0024, + "step": 54367 + }, + { + "epoch": 16.79, + "learning_rate": 1.3204314796950634e-06, + "loss": 0.0023, + "step": 54368 + }, + { + "epoch": 16.79, + "learning_rate": 1.3201831120291718e-06, + "loss": 0.0027, + "step": 54369 + }, + { + "epoch": 16.79, + "learning_rate": 1.3199347660730877e-06, + "loss": 0.0022, + "step": 54370 + }, + { + "epoch": 16.79, + "learning_rate": 1.319686441827428e-06, + "loss": 0.0022, + "step": 54371 + }, + { + "epoch": 16.79, + "learning_rate": 1.3194381392928146e-06, + "loss": 0.0028, + "step": 54372 + }, + { + "epoch": 16.79, + "learning_rate": 1.3191898584698725e-06, + "loss": 0.0019, + "step": 54373 + }, + { + "epoch": 16.79, + "learning_rate": 1.3189415993592203e-06, + "loss": 0.0019, + "step": 54374 + }, + { + "epoch": 16.79, + "learning_rate": 1.3186933619614761e-06, + "loss": 0.0023, + "step": 54375 + }, + { + "epoch": 16.79, + "learning_rate": 1.318445146277263e-06, + "loss": 0.0023, + "step": 54376 + }, + { + "epoch": 16.79, + "learning_rate": 1.3181969523072048e-06, + "loss": 0.0022, + "step": 54377 + }, + { + "epoch": 16.79, + "learning_rate": 1.3179487800519187e-06, + "loss": 0.0025, + "step": 54378 + }, + { + "epoch": 16.79, + "learning_rate": 1.3177006295120242e-06, + "loss": 0.0034, + "step": 54379 + }, + { + "epoch": 16.79, + "learning_rate": 1.3174525006881456e-06, + "loss": 0.0014, + "step": 54380 + }, + { + "epoch": 16.79, + "learning_rate": 1.317204393580901e-06, + "loss": 0.0033, + "step": 54381 + }, + { + "epoch": 16.79, + "learning_rate": 1.316956308190911e-06, + "loss": 0.0026, + "step": 54382 + }, + { + "epoch": 16.79, + "learning_rate": 1.3167082445187995e-06, + "loss": 0.002, + "step": 54383 + }, + { + "epoch": 16.79, + "learning_rate": 1.316460202565184e-06, + "loss": 0.0021, + "step": 54384 + }, + { + "epoch": 16.8, + "learning_rate": 1.316212182330684e-06, + "loss": 0.0018, + "step": 54385 + }, + { + "epoch": 16.8, + "learning_rate": 1.315964183815922e-06, + "loss": 0.0027, + "step": 54386 + }, + { + "epoch": 16.8, + "learning_rate": 1.3157162070215157e-06, + "loss": 0.0024, + "step": 54387 + }, + { + "epoch": 16.8, + "learning_rate": 1.31546825194809e-06, + "loss": 0.0019, + "step": 54388 + }, + { + "epoch": 16.8, + "learning_rate": 1.315220318596262e-06, + "loss": 0.0024, + "step": 54389 + }, + { + "epoch": 16.8, + "learning_rate": 1.3149724069666492e-06, + "loss": 0.0019, + "step": 54390 + }, + { + "epoch": 16.8, + "learning_rate": 1.3147245170598744e-06, + "loss": 0.0024, + "step": 54391 + }, + { + "epoch": 16.8, + "learning_rate": 1.3144766488765604e-06, + "loss": 0.0028, + "step": 54392 + }, + { + "epoch": 16.8, + "learning_rate": 1.3142288024173223e-06, + "loss": 0.0016, + "step": 54393 + }, + { + "epoch": 16.8, + "learning_rate": 1.313980977682784e-06, + "loss": 0.0031, + "step": 54394 + }, + { + "epoch": 16.8, + "learning_rate": 1.3137331746735639e-06, + "loss": 0.0016, + "step": 54395 + }, + { + "epoch": 16.8, + "learning_rate": 1.3134853933902792e-06, + "loss": 0.0023, + "step": 54396 + }, + { + "epoch": 16.8, + "learning_rate": 1.3132376338335505e-06, + "loss": 0.0018, + "step": 54397 + }, + { + "epoch": 16.8, + "learning_rate": 1.3129898960040022e-06, + "loss": 0.003, + "step": 54398 + }, + { + "epoch": 16.8, + "learning_rate": 1.312742179902251e-06, + "loss": 0.0031, + "step": 54399 + }, + { + "epoch": 16.8, + "learning_rate": 1.3124944855289134e-06, + "loss": 0.0018, + "step": 54400 + }, + { + "epoch": 16.8, + "learning_rate": 1.3122468128846134e-06, + "loss": 0.0026, + "step": 54401 + }, + { + "epoch": 16.8, + "learning_rate": 1.3119991619699668e-06, + "loss": 0.0017, + "step": 54402 + }, + { + "epoch": 16.8, + "learning_rate": 1.3117515327855956e-06, + "loss": 0.0022, + "step": 54403 + }, + { + "epoch": 16.8, + "learning_rate": 1.3115039253321193e-06, + "loss": 0.0027, + "step": 54404 + }, + { + "epoch": 16.8, + "learning_rate": 1.3112563396101574e-06, + "loss": 0.0022, + "step": 54405 + }, + { + "epoch": 16.8, + "learning_rate": 1.311008775620326e-06, + "loss": 0.0016, + "step": 54406 + }, + { + "epoch": 16.8, + "learning_rate": 1.3107612333632457e-06, + "loss": 0.003, + "step": 54407 + }, + { + "epoch": 16.8, + "learning_rate": 1.3105137128395384e-06, + "loss": 0.0022, + "step": 54408 + }, + { + "epoch": 16.8, + "learning_rate": 1.3102662140498223e-06, + "loss": 0.0026, + "step": 54409 + }, + { + "epoch": 16.8, + "learning_rate": 1.3100187369947127e-06, + "loss": 0.0021, + "step": 54410 + }, + { + "epoch": 16.8, + "learning_rate": 1.309771281674833e-06, + "loss": 0.0025, + "step": 54411 + }, + { + "epoch": 16.8, + "learning_rate": 1.309523848090798e-06, + "loss": 0.0025, + "step": 54412 + }, + { + "epoch": 16.8, + "learning_rate": 1.3092764362432287e-06, + "loss": 0.002, + "step": 54413 + }, + { + "epoch": 16.8, + "learning_rate": 1.309029046132747e-06, + "loss": 0.0017, + "step": 54414 + }, + { + "epoch": 16.8, + "learning_rate": 1.3087816777599683e-06, + "loss": 0.002, + "step": 54415 + }, + { + "epoch": 16.8, + "learning_rate": 1.3085343311255106e-06, + "loss": 0.0027, + "step": 54416 + }, + { + "epoch": 16.8, + "learning_rate": 1.3082870062299946e-06, + "loss": 0.0026, + "step": 54417 + }, + { + "epoch": 16.81, + "learning_rate": 1.3080397030740365e-06, + "loss": 0.0019, + "step": 54418 + }, + { + "epoch": 16.81, + "learning_rate": 1.3077924216582593e-06, + "loss": 0.0024, + "step": 54419 + }, + { + "epoch": 16.81, + "learning_rate": 1.307545161983278e-06, + "loss": 0.0018, + "step": 54420 + }, + { + "epoch": 16.81, + "learning_rate": 1.3072979240497086e-06, + "loss": 0.002, + "step": 54421 + }, + { + "epoch": 16.81, + "learning_rate": 1.307050707858174e-06, + "loss": 0.0016, + "step": 54422 + }, + { + "epoch": 16.81, + "learning_rate": 1.3068035134092927e-06, + "loss": 0.0044, + "step": 54423 + }, + { + "epoch": 16.81, + "learning_rate": 1.3065563407036785e-06, + "loss": 0.0024, + "step": 54424 + }, + { + "epoch": 16.81, + "learning_rate": 1.3063091897419556e-06, + "loss": 0.0019, + "step": 54425 + }, + { + "epoch": 16.81, + "learning_rate": 1.3060620605247387e-06, + "loss": 0.0022, + "step": 54426 + }, + { + "epoch": 16.81, + "learning_rate": 1.3058149530526444e-06, + "loss": 0.0024, + "step": 54427 + }, + { + "epoch": 16.81, + "learning_rate": 1.3055678673262918e-06, + "loss": 0.0018, + "step": 54428 + }, + { + "epoch": 16.81, + "learning_rate": 1.3053208033463026e-06, + "loss": 0.002, + "step": 54429 + }, + { + "epoch": 16.81, + "learning_rate": 1.3050737611132913e-06, + "loss": 0.0021, + "step": 54430 + }, + { + "epoch": 16.81, + "learning_rate": 1.3048267406278748e-06, + "loss": 0.002, + "step": 54431 + }, + { + "epoch": 16.81, + "learning_rate": 1.3045797418906747e-06, + "loss": 0.0022, + "step": 54432 + }, + { + "epoch": 16.81, + "learning_rate": 1.3043327649023042e-06, + "loss": 0.0018, + "step": 54433 + }, + { + "epoch": 16.81, + "learning_rate": 1.3040858096633835e-06, + "loss": 0.0024, + "step": 54434 + }, + { + "epoch": 16.81, + "learning_rate": 1.3038388761745346e-06, + "loss": 0.0028, + "step": 54435 + }, + { + "epoch": 16.81, + "learning_rate": 1.303591964436366e-06, + "loss": 0.0025, + "step": 54436 + }, + { + "epoch": 16.81, + "learning_rate": 1.3033450744495002e-06, + "loss": 0.0026, + "step": 54437 + }, + { + "epoch": 16.81, + "learning_rate": 1.3030982062145548e-06, + "loss": 0.0023, + "step": 54438 + }, + { + "epoch": 16.81, + "learning_rate": 1.3028513597321491e-06, + "loss": 0.0024, + "step": 54439 + }, + { + "epoch": 16.81, + "learning_rate": 1.3026045350028982e-06, + "loss": 0.0023, + "step": 54440 + }, + { + "epoch": 16.81, + "learning_rate": 1.3023577320274182e-06, + "loss": 0.0029, + "step": 54441 + }, + { + "epoch": 16.81, + "learning_rate": 1.302110950806329e-06, + "loss": 0.0015, + "step": 54442 + }, + { + "epoch": 16.81, + "learning_rate": 1.3018641913402453e-06, + "loss": 0.0021, + "step": 54443 + }, + { + "epoch": 16.81, + "learning_rate": 1.3016174536297854e-06, + "loss": 0.002, + "step": 54444 + }, + { + "epoch": 16.81, + "learning_rate": 1.3013707376755712e-06, + "loss": 0.0017, + "step": 54445 + }, + { + "epoch": 16.81, + "learning_rate": 1.3011240434782102e-06, + "loss": 0.0022, + "step": 54446 + }, + { + "epoch": 16.81, + "learning_rate": 1.300877371038326e-06, + "loss": 0.0022, + "step": 54447 + }, + { + "epoch": 16.81, + "learning_rate": 1.300630720356535e-06, + "loss": 0.0021, + "step": 54448 + }, + { + "epoch": 16.81, + "learning_rate": 1.300384091433452e-06, + "loss": 0.0022, + "step": 54449 + }, + { + "epoch": 16.82, + "learning_rate": 1.3001374842696969e-06, + "loss": 0.0017, + "step": 54450 + }, + { + "epoch": 16.82, + "learning_rate": 1.2998908988658844e-06, + "loss": 0.0021, + "step": 54451 + }, + { + "epoch": 16.82, + "learning_rate": 1.2996443352226295e-06, + "loss": 0.0029, + "step": 54452 + }, + { + "epoch": 16.82, + "learning_rate": 1.299397793340551e-06, + "loss": 0.0016, + "step": 54453 + }, + { + "epoch": 16.82, + "learning_rate": 1.2991512732202683e-06, + "loss": 0.0023, + "step": 54454 + }, + { + "epoch": 16.82, + "learning_rate": 1.298904774862393e-06, + "loss": 0.0014, + "step": 54455 + }, + { + "epoch": 16.82, + "learning_rate": 1.2986582982675443e-06, + "loss": 0.0023, + "step": 54456 + }, + { + "epoch": 16.82, + "learning_rate": 1.2984118434363401e-06, + "loss": 0.0025, + "step": 54457 + }, + { + "epoch": 16.82, + "learning_rate": 1.298165410369392e-06, + "loss": 0.0027, + "step": 54458 + }, + { + "epoch": 16.82, + "learning_rate": 1.297918999067319e-06, + "loss": 0.0021, + "step": 54459 + }, + { + "epoch": 16.82, + "learning_rate": 1.2976726095307412e-06, + "loss": 0.0024, + "step": 54460 + }, + { + "epoch": 16.82, + "learning_rate": 1.2974262417602702e-06, + "loss": 0.0022, + "step": 54461 + }, + { + "epoch": 16.82, + "learning_rate": 1.2971798957565218e-06, + "loss": 0.0021, + "step": 54462 + }, + { + "epoch": 16.82, + "learning_rate": 1.2969335715201159e-06, + "loss": 0.0021, + "step": 54463 + }, + { + "epoch": 16.82, + "learning_rate": 1.296687269051664e-06, + "loss": 0.0022, + "step": 54464 + }, + { + "epoch": 16.82, + "learning_rate": 1.2964409883517849e-06, + "loss": 0.0027, + "step": 54465 + }, + { + "epoch": 16.82, + "learning_rate": 1.2961947294210986e-06, + "loss": 0.0029, + "step": 54466 + }, + { + "epoch": 16.82, + "learning_rate": 1.2959484922602129e-06, + "loss": 0.0016, + "step": 54467 + }, + { + "epoch": 16.82, + "learning_rate": 1.295702276869747e-06, + "loss": 0.002, + "step": 54468 + }, + { + "epoch": 16.82, + "learning_rate": 1.2954560832503194e-06, + "loss": 0.0017, + "step": 54469 + }, + { + "epoch": 16.82, + "learning_rate": 1.2952099114025407e-06, + "loss": 0.0023, + "step": 54470 + }, + { + "epoch": 16.82, + "learning_rate": 1.2949637613270337e-06, + "loss": 0.0024, + "step": 54471 + }, + { + "epoch": 16.82, + "learning_rate": 1.294717633024407e-06, + "loss": 0.002, + "step": 54472 + }, + { + "epoch": 16.82, + "learning_rate": 1.2944715264952812e-06, + "loss": 0.0019, + "step": 54473 + }, + { + "epoch": 16.82, + "learning_rate": 1.2942254417402677e-06, + "loss": 0.0025, + "step": 54474 + }, + { + "epoch": 16.82, + "learning_rate": 1.2939793787599842e-06, + "loss": 0.0018, + "step": 54475 + }, + { + "epoch": 16.82, + "learning_rate": 1.2937333375550509e-06, + "loss": 0.003, + "step": 54476 + }, + { + "epoch": 16.82, + "learning_rate": 1.2934873181260742e-06, + "loss": 0.0022, + "step": 54477 + }, + { + "epoch": 16.82, + "learning_rate": 1.2932413204736726e-06, + "loss": 0.002, + "step": 54478 + }, + { + "epoch": 16.82, + "learning_rate": 1.2929953445984656e-06, + "loss": 0.0031, + "step": 54479 + }, + { + "epoch": 16.82, + "learning_rate": 1.2927493905010635e-06, + "loss": 0.0019, + "step": 54480 + }, + { + "epoch": 16.82, + "learning_rate": 1.292503458182085e-06, + "loss": 0.0018, + "step": 54481 + }, + { + "epoch": 16.83, + "learning_rate": 1.2922575476421428e-06, + "loss": 0.0025, + "step": 54482 + }, + { + "epoch": 16.83, + "learning_rate": 1.2920116588818509e-06, + "loss": 0.002, + "step": 54483 + }, + { + "epoch": 16.83, + "learning_rate": 1.2917657919018266e-06, + "loss": 0.0021, + "step": 54484 + }, + { + "epoch": 16.83, + "learning_rate": 1.2915199467026862e-06, + "loss": 0.0024, + "step": 54485 + }, + { + "epoch": 16.83, + "learning_rate": 1.2912741232850423e-06, + "loss": 0.0026, + "step": 54486 + }, + { + "epoch": 16.83, + "learning_rate": 1.291028321649509e-06, + "loss": 0.002, + "step": 54487 + }, + { + "epoch": 16.83, + "learning_rate": 1.2907825417967034e-06, + "loss": 0.0022, + "step": 54488 + }, + { + "epoch": 16.83, + "learning_rate": 1.2905367837272376e-06, + "loss": 0.0014, + "step": 54489 + }, + { + "epoch": 16.83, + "learning_rate": 1.2902910474417285e-06, + "loss": 0.0024, + "step": 54490 + }, + { + "epoch": 16.83, + "learning_rate": 1.2900453329407913e-06, + "loss": 0.0026, + "step": 54491 + }, + { + "epoch": 16.83, + "learning_rate": 1.289799640225039e-06, + "loss": 0.0026, + "step": 54492 + }, + { + "epoch": 16.83, + "learning_rate": 1.2895539692950842e-06, + "loss": 0.0016, + "step": 54493 + }, + { + "epoch": 16.83, + "learning_rate": 1.2893083201515467e-06, + "loss": 0.0031, + "step": 54494 + }, + { + "epoch": 16.83, + "learning_rate": 1.2890626927950356e-06, + "loss": 0.0019, + "step": 54495 + }, + { + "epoch": 16.83, + "learning_rate": 1.2888170872261685e-06, + "loss": 0.0021, + "step": 54496 + }, + { + "epoch": 16.83, + "learning_rate": 1.2885715034455604e-06, + "loss": 0.0015, + "step": 54497 + }, + { + "epoch": 16.83, + "learning_rate": 1.2883259414538197e-06, + "loss": 0.0019, + "step": 54498 + }, + { + "epoch": 16.83, + "learning_rate": 1.2880804012515658e-06, + "loss": 0.0021, + "step": 54499 + }, + { + "epoch": 16.83, + "learning_rate": 1.2878348828394138e-06, + "loss": 0.002, + "step": 54500 + }, + { + "epoch": 16.83, + "learning_rate": 1.2875893862179744e-06, + "loss": 0.0023, + "step": 54501 + }, + { + "epoch": 16.83, + "learning_rate": 1.2873439113878639e-06, + "loss": 0.0024, + "step": 54502 + }, + { + "epoch": 16.83, + "learning_rate": 1.287098458349696e-06, + "loss": 0.0021, + "step": 54503 + }, + { + "epoch": 16.83, + "learning_rate": 1.2868530271040814e-06, + "loss": 0.0016, + "step": 54504 + }, + { + "epoch": 16.83, + "learning_rate": 1.2866076176516374e-06, + "loss": 0.0022, + "step": 54505 + }, + { + "epoch": 16.83, + "learning_rate": 1.286362229992979e-06, + "loss": 0.002, + "step": 54506 + }, + { + "epoch": 16.83, + "learning_rate": 1.2861168641287169e-06, + "loss": 0.0027, + "step": 54507 + }, + { + "epoch": 16.83, + "learning_rate": 1.2858715200594641e-06, + "loss": 0.0022, + "step": 54508 + }, + { + "epoch": 16.83, + "learning_rate": 1.2856261977858364e-06, + "loss": 0.0028, + "step": 54509 + }, + { + "epoch": 16.83, + "learning_rate": 1.2853808973084492e-06, + "loss": 0.0019, + "step": 54510 + }, + { + "epoch": 16.83, + "learning_rate": 1.285135618627912e-06, + "loss": 0.0028, + "step": 54511 + }, + { + "epoch": 16.83, + "learning_rate": 1.2848903617448406e-06, + "loss": 0.0033, + "step": 54512 + }, + { + "epoch": 16.83, + "learning_rate": 1.2846451266598492e-06, + "loss": 0.0018, + "step": 54513 + }, + { + "epoch": 16.83, + "learning_rate": 1.2843999133735474e-06, + "loss": 0.0023, + "step": 54514 + }, + { + "epoch": 16.84, + "learning_rate": 1.2841547218865514e-06, + "loss": 0.002, + "step": 54515 + }, + { + "epoch": 16.84, + "learning_rate": 1.283909552199476e-06, + "loss": 0.0027, + "step": 54516 + }, + { + "epoch": 16.84, + "learning_rate": 1.283664404312933e-06, + "loss": 0.0022, + "step": 54517 + }, + { + "epoch": 16.84, + "learning_rate": 1.2834192782275322e-06, + "loss": 0.0027, + "step": 54518 + }, + { + "epoch": 16.84, + "learning_rate": 1.2831741739438919e-06, + "loss": 0.0019, + "step": 54519 + }, + { + "epoch": 16.84, + "learning_rate": 1.2829290914626214e-06, + "loss": 0.0022, + "step": 54520 + }, + { + "epoch": 16.84, + "learning_rate": 1.2826840307843346e-06, + "loss": 0.0027, + "step": 54521 + }, + { + "epoch": 16.84, + "learning_rate": 1.282438991909647e-06, + "loss": 0.002, + "step": 54522 + }, + { + "epoch": 16.84, + "learning_rate": 1.2821939748391699e-06, + "loss": 0.0027, + "step": 54523 + }, + { + "epoch": 16.84, + "learning_rate": 1.281948979573513e-06, + "loss": 0.0024, + "step": 54524 + }, + { + "epoch": 16.84, + "learning_rate": 1.2817040061132945e-06, + "loss": 0.0021, + "step": 54525 + }, + { + "epoch": 16.84, + "learning_rate": 1.2814590544591222e-06, + "loss": 0.0019, + "step": 54526 + }, + { + "epoch": 16.84, + "learning_rate": 1.2812141246116127e-06, + "loss": 0.0026, + "step": 54527 + }, + { + "epoch": 16.84, + "learning_rate": 1.2809692165713771e-06, + "loss": 0.0032, + "step": 54528 + }, + { + "epoch": 16.84, + "learning_rate": 1.280724330339025e-06, + "loss": 0.0029, + "step": 54529 + }, + { + "epoch": 16.84, + "learning_rate": 1.280479465915172e-06, + "loss": 0.0021, + "step": 54530 + }, + { + "epoch": 16.84, + "learning_rate": 1.2802346233004326e-06, + "loss": 0.0023, + "step": 54531 + }, + { + "epoch": 16.84, + "learning_rate": 1.2799898024954148e-06, + "loss": 0.0025, + "step": 54532 + }, + { + "epoch": 16.84, + "learning_rate": 1.2797450035007353e-06, + "loss": 0.0043, + "step": 54533 + }, + { + "epoch": 16.84, + "learning_rate": 1.279500226317003e-06, + "loss": 0.0022, + "step": 54534 + }, + { + "epoch": 16.84, + "learning_rate": 1.2792554709448301e-06, + "loss": 0.0028, + "step": 54535 + }, + { + "epoch": 16.84, + "learning_rate": 1.2790107373848293e-06, + "loss": 0.0016, + "step": 54536 + }, + { + "epoch": 16.84, + "learning_rate": 1.2787660256376155e-06, + "loss": 0.0022, + "step": 54537 + }, + { + "epoch": 16.84, + "learning_rate": 1.2785213357037985e-06, + "loss": 0.0023, + "step": 54538 + }, + { + "epoch": 16.84, + "learning_rate": 1.2782766675839876e-06, + "loss": 0.0021, + "step": 54539 + }, + { + "epoch": 16.84, + "learning_rate": 1.2780320212787978e-06, + "loss": 0.002, + "step": 54540 + }, + { + "epoch": 16.84, + "learning_rate": 1.2777873967888431e-06, + "loss": 0.0022, + "step": 54541 + }, + { + "epoch": 16.84, + "learning_rate": 1.277542794114731e-06, + "loss": 0.0022, + "step": 54542 + }, + { + "epoch": 16.84, + "learning_rate": 1.2772982132570766e-06, + "loss": 0.0027, + "step": 54543 + }, + { + "epoch": 16.84, + "learning_rate": 1.2770536542164913e-06, + "loss": 0.0012, + "step": 54544 + }, + { + "epoch": 16.84, + "learning_rate": 1.2768091169935837e-06, + "loss": 0.0022, + "step": 54545 + }, + { + "epoch": 16.84, + "learning_rate": 1.2765646015889666e-06, + "loss": 0.0027, + "step": 54546 + }, + { + "epoch": 16.85, + "learning_rate": 1.276320108003255e-06, + "loss": 0.0024, + "step": 54547 + }, + { + "epoch": 16.85, + "learning_rate": 1.2760756362370575e-06, + "loss": 0.0017, + "step": 54548 + }, + { + "epoch": 16.85, + "learning_rate": 1.2758311862909844e-06, + "loss": 0.0025, + "step": 54549 + }, + { + "epoch": 16.85, + "learning_rate": 1.2755867581656512e-06, + "loss": 0.0027, + "step": 54550 + }, + { + "epoch": 16.85, + "learning_rate": 1.2753423518616636e-06, + "loss": 0.0019, + "step": 54551 + }, + { + "epoch": 16.85, + "learning_rate": 1.275097967379637e-06, + "loss": 0.002, + "step": 54552 + }, + { + "epoch": 16.85, + "learning_rate": 1.274853604720183e-06, + "loss": 0.0022, + "step": 54553 + }, + { + "epoch": 16.85, + "learning_rate": 1.2746092638839124e-06, + "loss": 0.0018, + "step": 54554 + }, + { + "epoch": 16.85, + "learning_rate": 1.2743649448714323e-06, + "loss": 0.0025, + "step": 54555 + }, + { + "epoch": 16.85, + "learning_rate": 1.2741206476833602e-06, + "loss": 0.0016, + "step": 54556 + }, + { + "epoch": 16.85, + "learning_rate": 1.2738763723203007e-06, + "loss": 0.0027, + "step": 54557 + }, + { + "epoch": 16.85, + "learning_rate": 1.2736321187828704e-06, + "loss": 0.0021, + "step": 54558 + }, + { + "epoch": 16.85, + "learning_rate": 1.2733878870716786e-06, + "loss": 0.0024, + "step": 54559 + }, + { + "epoch": 16.85, + "learning_rate": 1.2731436771873318e-06, + "loss": 0.0034, + "step": 54560 + }, + { + "epoch": 16.85, + "learning_rate": 1.2728994891304446e-06, + "loss": 0.0033, + "step": 54561 + }, + { + "epoch": 16.85, + "learning_rate": 1.2726553229016304e-06, + "loss": 0.0026, + "step": 54562 + }, + { + "epoch": 16.85, + "learning_rate": 1.2724111785014947e-06, + "loss": 0.0021, + "step": 54563 + }, + { + "epoch": 16.85, + "learning_rate": 1.272167055930652e-06, + "loss": 0.0017, + "step": 54564 + }, + { + "epoch": 16.85, + "learning_rate": 1.2719229551897117e-06, + "loss": 0.0022, + "step": 54565 + }, + { + "epoch": 16.85, + "learning_rate": 1.271678876279282e-06, + "loss": 0.0022, + "step": 54566 + }, + { + "epoch": 16.85, + "learning_rate": 1.271434819199976e-06, + "loss": 0.0024, + "step": 54567 + }, + { + "epoch": 16.85, + "learning_rate": 1.271190783952404e-06, + "loss": 0.0022, + "step": 54568 + }, + { + "epoch": 16.85, + "learning_rate": 1.2709467705371769e-06, + "loss": 0.003, + "step": 54569 + }, + { + "epoch": 16.85, + "learning_rate": 1.270702778954902e-06, + "loss": 0.0021, + "step": 54570 + }, + { + "epoch": 16.85, + "learning_rate": 1.270458809206192e-06, + "loss": 0.0024, + "step": 54571 + }, + { + "epoch": 16.85, + "learning_rate": 1.2702148612916575e-06, + "loss": 0.0018, + "step": 54572 + }, + { + "epoch": 16.85, + "learning_rate": 1.2699709352119071e-06, + "loss": 0.0026, + "step": 54573 + }, + { + "epoch": 16.85, + "learning_rate": 1.2697270309675525e-06, + "loss": 0.002, + "step": 54574 + }, + { + "epoch": 16.85, + "learning_rate": 1.269483148559204e-06, + "loss": 0.0015, + "step": 54575 + }, + { + "epoch": 16.85, + "learning_rate": 1.2692392879874672e-06, + "loss": 0.0023, + "step": 54576 + }, + { + "epoch": 16.85, + "learning_rate": 1.2689954492529566e-06, + "loss": 0.0022, + "step": 54577 + }, + { + "epoch": 16.85, + "learning_rate": 1.268751632356282e-06, + "loss": 0.002, + "step": 54578 + }, + { + "epoch": 16.85, + "learning_rate": 1.268507837298052e-06, + "loss": 0.0025, + "step": 54579 + }, + { + "epoch": 16.86, + "learning_rate": 1.2682640640788745e-06, + "loss": 0.0017, + "step": 54580 + }, + { + "epoch": 16.86, + "learning_rate": 1.268020312699364e-06, + "loss": 0.0024, + "step": 54581 + }, + { + "epoch": 16.86, + "learning_rate": 1.267776583160124e-06, + "loss": 0.0031, + "step": 54582 + }, + { + "epoch": 16.86, + "learning_rate": 1.2675328754617688e-06, + "loss": 0.0034, + "step": 54583 + }, + { + "epoch": 16.86, + "learning_rate": 1.26728918960491e-06, + "loss": 0.0021, + "step": 54584 + }, + { + "epoch": 16.86, + "learning_rate": 1.2670455255901492e-06, + "loss": 0.0022, + "step": 54585 + }, + { + "epoch": 16.86, + "learning_rate": 1.2668018834181006e-06, + "loss": 0.002, + "step": 54586 + }, + { + "epoch": 16.86, + "learning_rate": 1.2665582630893757e-06, + "loss": 0.0014, + "step": 54587 + }, + { + "epoch": 16.86, + "learning_rate": 1.2663146646045788e-06, + "loss": 0.0025, + "step": 54588 + }, + { + "epoch": 16.86, + "learning_rate": 1.2660710879643244e-06, + "loss": 0.0018, + "step": 54589 + }, + { + "epoch": 16.86, + "learning_rate": 1.2658275331692194e-06, + "loss": 0.0027, + "step": 54590 + }, + { + "epoch": 16.86, + "learning_rate": 1.2655840002198705e-06, + "loss": 0.0024, + "step": 54591 + }, + { + "epoch": 16.86, + "learning_rate": 1.2653404891168886e-06, + "loss": 0.002, + "step": 54592 + }, + { + "epoch": 16.86, + "learning_rate": 1.2650969998608853e-06, + "loss": 0.0028, + "step": 54593 + }, + { + "epoch": 16.86, + "learning_rate": 1.264853532452468e-06, + "loss": 0.0019, + "step": 54594 + }, + { + "epoch": 16.86, + "learning_rate": 1.2646100868922428e-06, + "loss": 0.0022, + "step": 54595 + }, + { + "epoch": 16.86, + "learning_rate": 1.2643666631808238e-06, + "loss": 0.0025, + "step": 54596 + }, + { + "epoch": 16.86, + "learning_rate": 1.2641232613188138e-06, + "loss": 0.002, + "step": 54597 + }, + { + "epoch": 16.86, + "learning_rate": 1.2638798813068255e-06, + "loss": 0.0023, + "step": 54598 + }, + { + "epoch": 16.86, + "learning_rate": 1.2636365231454695e-06, + "loss": 0.0023, + "step": 54599 + }, + { + "epoch": 16.86, + "learning_rate": 1.263393186835351e-06, + "loss": 0.002, + "step": 54600 + }, + { + "epoch": 16.86, + "learning_rate": 1.2631498723770786e-06, + "loss": 0.0024, + "step": 54601 + }, + { + "epoch": 16.86, + "learning_rate": 1.2629065797712615e-06, + "loss": 0.0031, + "step": 54602 + }, + { + "epoch": 16.86, + "learning_rate": 1.2626633090185102e-06, + "loss": 0.0017, + "step": 54603 + }, + { + "epoch": 16.86, + "learning_rate": 1.2624200601194313e-06, + "loss": 0.0022, + "step": 54604 + }, + { + "epoch": 16.86, + "learning_rate": 1.262176833074632e-06, + "loss": 0.003, + "step": 54605 + }, + { + "epoch": 16.86, + "learning_rate": 1.261933627884725e-06, + "loss": 0.0018, + "step": 54606 + }, + { + "epoch": 16.86, + "learning_rate": 1.261690444550312e-06, + "loss": 0.0021, + "step": 54607 + }, + { + "epoch": 16.86, + "learning_rate": 1.2614472830720058e-06, + "loss": 0.0029, + "step": 54608 + }, + { + "epoch": 16.86, + "learning_rate": 1.2612041434504163e-06, + "loss": 0.0026, + "step": 54609 + }, + { + "epoch": 16.86, + "learning_rate": 1.2609610256861482e-06, + "loss": 0.0014, + "step": 54610 + }, + { + "epoch": 16.86, + "learning_rate": 1.2607179297798088e-06, + "loss": 0.0019, + "step": 54611 + }, + { + "epoch": 16.87, + "learning_rate": 1.26047485573201e-06, + "loss": 0.0026, + "step": 54612 + }, + { + "epoch": 16.87, + "learning_rate": 1.2602318035433548e-06, + "loss": 0.0022, + "step": 54613 + }, + { + "epoch": 16.87, + "learning_rate": 1.2599887732144567e-06, + "loss": 0.0029, + "step": 54614 + }, + { + "epoch": 16.87, + "learning_rate": 1.2597457647459211e-06, + "loss": 0.0025, + "step": 54615 + }, + { + "epoch": 16.87, + "learning_rate": 1.2595027781383528e-06, + "loss": 0.0021, + "step": 54616 + }, + { + "epoch": 16.87, + "learning_rate": 1.2592598133923617e-06, + "loss": 0.0017, + "step": 54617 + }, + { + "epoch": 16.87, + "learning_rate": 1.2590168705085594e-06, + "loss": 0.0023, + "step": 54618 + }, + { + "epoch": 16.87, + "learning_rate": 1.2587739494875473e-06, + "loss": 0.0025, + "step": 54619 + }, + { + "epoch": 16.87, + "learning_rate": 1.2585310503299374e-06, + "loss": 0.0025, + "step": 54620 + }, + { + "epoch": 16.87, + "learning_rate": 1.2582881730363371e-06, + "loss": 0.0015, + "step": 54621 + }, + { + "epoch": 16.87, + "learning_rate": 1.2580453176073493e-06, + "loss": 0.0032, + "step": 54622 + }, + { + "epoch": 16.87, + "learning_rate": 1.2578024840435843e-06, + "loss": 0.0022, + "step": 54623 + }, + { + "epoch": 16.87, + "learning_rate": 1.2575596723456528e-06, + "loss": 0.0023, + "step": 54624 + }, + { + "epoch": 16.87, + "learning_rate": 1.257316882514159e-06, + "loss": 0.0033, + "step": 54625 + }, + { + "epoch": 16.87, + "learning_rate": 1.2570741145497078e-06, + "loss": 0.0024, + "step": 54626 + }, + { + "epoch": 16.87, + "learning_rate": 1.256831368452911e-06, + "loss": 0.0023, + "step": 54627 + }, + { + "epoch": 16.87, + "learning_rate": 1.2565886442243713e-06, + "loss": 0.002, + "step": 54628 + }, + { + "epoch": 16.87, + "learning_rate": 1.2563459418646983e-06, + "loss": 0.0016, + "step": 54629 + }, + { + "epoch": 16.87, + "learning_rate": 1.2561032613745006e-06, + "loss": 0.002, + "step": 54630 + }, + { + "epoch": 16.87, + "learning_rate": 1.255860602754384e-06, + "loss": 0.0019, + "step": 54631 + }, + { + "epoch": 16.87, + "learning_rate": 1.2556179660049529e-06, + "loss": 0.0032, + "step": 54632 + }, + { + "epoch": 16.87, + "learning_rate": 1.2553753511268175e-06, + "loss": 0.0019, + "step": 54633 + }, + { + "epoch": 16.87, + "learning_rate": 1.2551327581205818e-06, + "loss": 0.0024, + "step": 54634 + }, + { + "epoch": 16.87, + "learning_rate": 1.2548901869868557e-06, + "loss": 0.0023, + "step": 54635 + }, + { + "epoch": 16.87, + "learning_rate": 1.2546476377262417e-06, + "loss": 0.0025, + "step": 54636 + }, + { + "epoch": 16.87, + "learning_rate": 1.2544051103393529e-06, + "loss": 0.002, + "step": 54637 + }, + { + "epoch": 16.87, + "learning_rate": 1.2541626048267885e-06, + "loss": 0.0021, + "step": 54638 + }, + { + "epoch": 16.87, + "learning_rate": 1.2539201211891583e-06, + "loss": 0.003, + "step": 54639 + }, + { + "epoch": 16.87, + "learning_rate": 1.2536776594270716e-06, + "loss": 0.0028, + "step": 54640 + }, + { + "epoch": 16.87, + "learning_rate": 1.2534352195411326e-06, + "loss": 0.0033, + "step": 54641 + }, + { + "epoch": 16.87, + "learning_rate": 1.253192801531945e-06, + "loss": 0.0018, + "step": 54642 + }, + { + "epoch": 16.87, + "learning_rate": 1.2529504054001196e-06, + "loss": 0.0024, + "step": 54643 + }, + { + "epoch": 16.88, + "learning_rate": 1.2527080311462592e-06, + "loss": 0.0024, + "step": 54644 + }, + { + "epoch": 16.88, + "learning_rate": 1.2524656787709722e-06, + "loss": 0.0025, + "step": 54645 + }, + { + "epoch": 16.88, + "learning_rate": 1.2522233482748648e-06, + "loss": 0.0019, + "step": 54646 + }, + { + "epoch": 16.88, + "learning_rate": 1.2519810396585408e-06, + "loss": 0.0026, + "step": 54647 + }, + { + "epoch": 16.88, + "learning_rate": 1.2517387529226067e-06, + "loss": 0.0026, + "step": 54648 + }, + { + "epoch": 16.88, + "learning_rate": 1.2514964880676718e-06, + "loss": 0.0019, + "step": 54649 + }, + { + "epoch": 16.88, + "learning_rate": 1.2512542450943376e-06, + "loss": 0.0027, + "step": 54650 + }, + { + "epoch": 16.88, + "learning_rate": 1.2510120240032153e-06, + "loss": 0.0024, + "step": 54651 + }, + { + "epoch": 16.88, + "learning_rate": 1.2507698247949074e-06, + "loss": 0.0025, + "step": 54652 + }, + { + "epoch": 16.88, + "learning_rate": 1.2505276474700168e-06, + "loss": 0.002, + "step": 54653 + }, + { + "epoch": 16.88, + "learning_rate": 1.250285492029153e-06, + "loss": 0.0024, + "step": 54654 + }, + { + "epoch": 16.88, + "learning_rate": 1.2500433584729233e-06, + "loss": 0.0019, + "step": 54655 + }, + { + "epoch": 16.88, + "learning_rate": 1.2498012468019305e-06, + "loss": 0.0028, + "step": 54656 + }, + { + "epoch": 16.88, + "learning_rate": 1.2495591570167798e-06, + "loss": 0.0019, + "step": 54657 + }, + { + "epoch": 16.88, + "learning_rate": 1.2493170891180784e-06, + "loss": 0.0028, + "step": 54658 + }, + { + "epoch": 16.88, + "learning_rate": 1.249075043106429e-06, + "loss": 0.0031, + "step": 54659 + }, + { + "epoch": 16.88, + "learning_rate": 1.2488330189824394e-06, + "loss": 0.0018, + "step": 54660 + }, + { + "epoch": 16.88, + "learning_rate": 1.2485910167467174e-06, + "loss": 0.0026, + "step": 54661 + }, + { + "epoch": 16.88, + "learning_rate": 1.2483490363998641e-06, + "loss": 0.0018, + "step": 54662 + }, + { + "epoch": 16.88, + "learning_rate": 1.2481070779424841e-06, + "loss": 0.0037, + "step": 54663 + }, + { + "epoch": 16.88, + "learning_rate": 1.2478651413751873e-06, + "loss": 0.0022, + "step": 54664 + }, + { + "epoch": 16.88, + "learning_rate": 1.2476232266985744e-06, + "loss": 0.0021, + "step": 54665 + }, + { + "epoch": 16.88, + "learning_rate": 1.2473813339132534e-06, + "loss": 0.0022, + "step": 54666 + }, + { + "epoch": 16.88, + "learning_rate": 1.2471394630198263e-06, + "loss": 0.003, + "step": 54667 + }, + { + "epoch": 16.88, + "learning_rate": 1.2468976140189014e-06, + "loss": 0.002, + "step": 54668 + }, + { + "epoch": 16.88, + "learning_rate": 1.2466557869110796e-06, + "loss": 0.0021, + "step": 54669 + }, + { + "epoch": 16.88, + "learning_rate": 1.2464139816969688e-06, + "loss": 0.0021, + "step": 54670 + }, + { + "epoch": 16.88, + "learning_rate": 1.2461721983771757e-06, + "loss": 0.0021, + "step": 54671 + }, + { + "epoch": 16.88, + "learning_rate": 1.245930436952303e-06, + "loss": 0.0024, + "step": 54672 + }, + { + "epoch": 16.88, + "learning_rate": 1.245688697422951e-06, + "loss": 0.0022, + "step": 54673 + }, + { + "epoch": 16.88, + "learning_rate": 1.2454469797897318e-06, + "loss": 0.0018, + "step": 54674 + }, + { + "epoch": 16.88, + "learning_rate": 1.2452052840532435e-06, + "loss": 0.002, + "step": 54675 + }, + { + "epoch": 16.88, + "learning_rate": 1.2449636102140961e-06, + "loss": 0.0019, + "step": 54676 + }, + { + "epoch": 16.89, + "learning_rate": 1.244721958272892e-06, + "loss": 0.0023, + "step": 54677 + }, + { + "epoch": 16.89, + "learning_rate": 1.244480328230232e-06, + "loss": 0.0022, + "step": 54678 + }, + { + "epoch": 16.89, + "learning_rate": 1.2442387200867245e-06, + "loss": 0.0022, + "step": 54679 + }, + { + "epoch": 16.89, + "learning_rate": 1.2439971338429745e-06, + "loss": 0.0025, + "step": 54680 + }, + { + "epoch": 16.89, + "learning_rate": 1.243755569499583e-06, + "loss": 0.0022, + "step": 54681 + }, + { + "epoch": 16.89, + "learning_rate": 1.2435140270571578e-06, + "loss": 0.0022, + "step": 54682 + }, + { + "epoch": 16.89, + "learning_rate": 1.243272506516301e-06, + "loss": 0.0022, + "step": 54683 + }, + { + "epoch": 16.89, + "learning_rate": 1.2430310078776142e-06, + "loss": 0.0018, + "step": 54684 + }, + { + "epoch": 16.89, + "learning_rate": 1.2427895311417048e-06, + "loss": 0.0025, + "step": 54685 + }, + { + "epoch": 16.89, + "learning_rate": 1.242548076309178e-06, + "loss": 0.0021, + "step": 54686 + }, + { + "epoch": 16.89, + "learning_rate": 1.2423066433806352e-06, + "loss": 0.0023, + "step": 54687 + }, + { + "epoch": 16.89, + "learning_rate": 1.2420652323566784e-06, + "loss": 0.0022, + "step": 54688 + }, + { + "epoch": 16.89, + "learning_rate": 1.241823843237917e-06, + "loss": 0.0018, + "step": 54689 + }, + { + "epoch": 16.89, + "learning_rate": 1.2415824760249484e-06, + "loss": 0.0019, + "step": 54690 + }, + { + "epoch": 16.89, + "learning_rate": 1.241341130718381e-06, + "loss": 0.0018, + "step": 54691 + }, + { + "epoch": 16.89, + "learning_rate": 1.2410998073188197e-06, + "loss": 0.0026, + "step": 54692 + }, + { + "epoch": 16.89, + "learning_rate": 1.240858505826862e-06, + "loss": 0.0023, + "step": 54693 + }, + { + "epoch": 16.89, + "learning_rate": 1.2406172262431138e-06, + "loss": 0.002, + "step": 54694 + }, + { + "epoch": 16.89, + "learning_rate": 1.2403759685681826e-06, + "loss": 0.002, + "step": 54695 + }, + { + "epoch": 16.89, + "learning_rate": 1.2401347328026658e-06, + "loss": 0.0022, + "step": 54696 + }, + { + "epoch": 16.89, + "learning_rate": 1.2398935189471717e-06, + "loss": 0.0016, + "step": 54697 + }, + { + "epoch": 16.89, + "learning_rate": 1.239652327002303e-06, + "loss": 0.0024, + "step": 54698 + }, + { + "epoch": 16.89, + "learning_rate": 1.2394111569686584e-06, + "loss": 0.0023, + "step": 54699 + }, + { + "epoch": 16.89, + "learning_rate": 1.2391700088468438e-06, + "loss": 0.0018, + "step": 54700 + }, + { + "epoch": 16.89, + "learning_rate": 1.2389288826374646e-06, + "loss": 0.0024, + "step": 54701 + }, + { + "epoch": 16.89, + "learning_rate": 1.2386877783411256e-06, + "loss": 0.0018, + "step": 54702 + }, + { + "epoch": 16.89, + "learning_rate": 1.2384466959584218e-06, + "loss": 0.0023, + "step": 54703 + }, + { + "epoch": 16.89, + "learning_rate": 1.2382056354899608e-06, + "loss": 0.0017, + "step": 54704 + }, + { + "epoch": 16.89, + "learning_rate": 1.2379645969363485e-06, + "loss": 0.0023, + "step": 54705 + }, + { + "epoch": 16.89, + "learning_rate": 1.2377235802981812e-06, + "loss": 0.0022, + "step": 54706 + }, + { + "epoch": 16.89, + "learning_rate": 1.2374825855760686e-06, + "loss": 0.0022, + "step": 54707 + }, + { + "epoch": 16.89, + "learning_rate": 1.237241612770611e-06, + "loss": 0.0024, + "step": 54708 + }, + { + "epoch": 16.9, + "learning_rate": 1.237000661882407e-06, + "loss": 0.0023, + "step": 54709 + }, + { + "epoch": 16.9, + "learning_rate": 1.2367597329120628e-06, + "loss": 0.002, + "step": 54710 + }, + { + "epoch": 16.9, + "learning_rate": 1.2365188258601835e-06, + "loss": 0.0019, + "step": 54711 + }, + { + "epoch": 16.9, + "learning_rate": 1.2362779407273662e-06, + "loss": 0.0015, + "step": 54712 + }, + { + "epoch": 16.9, + "learning_rate": 1.2360370775142183e-06, + "loss": 0.0024, + "step": 54713 + }, + { + "epoch": 16.9, + "learning_rate": 1.2357962362213405e-06, + "loss": 0.0028, + "step": 54714 + }, + { + "epoch": 16.9, + "learning_rate": 1.2355554168493321e-06, + "loss": 0.0028, + "step": 54715 + }, + { + "epoch": 16.9, + "learning_rate": 1.2353146193987997e-06, + "loss": 0.002, + "step": 54716 + }, + { + "epoch": 16.9, + "learning_rate": 1.2350738438703447e-06, + "loss": 0.0029, + "step": 54717 + }, + { + "epoch": 16.9, + "learning_rate": 1.2348330902645688e-06, + "loss": 0.0019, + "step": 54718 + }, + { + "epoch": 16.9, + "learning_rate": 1.2345923585820717e-06, + "loss": 0.0022, + "step": 54719 + }, + { + "epoch": 16.9, + "learning_rate": 1.2343516488234608e-06, + "loss": 0.0025, + "step": 54720 + }, + { + "epoch": 16.9, + "learning_rate": 1.234110960989332e-06, + "loss": 0.0023, + "step": 54721 + }, + { + "epoch": 16.9, + "learning_rate": 1.2338702950802916e-06, + "loss": 0.0022, + "step": 54722 + }, + { + "epoch": 16.9, + "learning_rate": 1.2336296510969436e-06, + "loss": 0.0017, + "step": 54723 + }, + { + "epoch": 16.9, + "learning_rate": 1.2333890290398832e-06, + "loss": 0.0022, + "step": 54724 + }, + { + "epoch": 16.9, + "learning_rate": 1.2331484289097162e-06, + "loss": 0.0025, + "step": 54725 + }, + { + "epoch": 16.9, + "learning_rate": 1.2329078507070446e-06, + "loss": 0.0024, + "step": 54726 + }, + { + "epoch": 16.9, + "learning_rate": 1.2326672944324692e-06, + "loss": 0.0016, + "step": 54727 + }, + { + "epoch": 16.9, + "learning_rate": 1.2324267600865925e-06, + "loss": 0.0022, + "step": 54728 + }, + { + "epoch": 16.9, + "learning_rate": 1.2321862476700164e-06, + "loss": 0.0027, + "step": 54729 + }, + { + "epoch": 16.9, + "learning_rate": 1.2319457571833393e-06, + "loss": 0.0018, + "step": 54730 + }, + { + "epoch": 16.9, + "learning_rate": 1.2317052886271651e-06, + "loss": 0.0018, + "step": 54731 + }, + { + "epoch": 16.9, + "learning_rate": 1.231464842002097e-06, + "loss": 0.0027, + "step": 54732 + }, + { + "epoch": 16.9, + "learning_rate": 1.2312244173087352e-06, + "loss": 0.0017, + "step": 54733 + }, + { + "epoch": 16.9, + "learning_rate": 1.2309840145476781e-06, + "loss": 0.0025, + "step": 54734 + }, + { + "epoch": 16.9, + "learning_rate": 1.2307436337195288e-06, + "loss": 0.002, + "step": 54735 + }, + { + "epoch": 16.9, + "learning_rate": 1.2305032748248925e-06, + "loss": 0.0035, + "step": 54736 + }, + { + "epoch": 16.9, + "learning_rate": 1.230262937864364e-06, + "loss": 0.0019, + "step": 54737 + }, + { + "epoch": 16.9, + "learning_rate": 1.2300226228385493e-06, + "loss": 0.0029, + "step": 54738 + }, + { + "epoch": 16.9, + "learning_rate": 1.2297823297480472e-06, + "loss": 0.0025, + "step": 54739 + }, + { + "epoch": 16.9, + "learning_rate": 1.2295420585934581e-06, + "loss": 0.0032, + "step": 54740 + }, + { + "epoch": 16.91, + "learning_rate": 1.2293018093753827e-06, + "loss": 0.0018, + "step": 54741 + }, + { + "epoch": 16.91, + "learning_rate": 1.2290615820944264e-06, + "loss": 0.0022, + "step": 54742 + }, + { + "epoch": 16.91, + "learning_rate": 1.228821376751187e-06, + "loss": 0.0021, + "step": 54743 + }, + { + "epoch": 16.91, + "learning_rate": 1.228581193346262e-06, + "loss": 0.0022, + "step": 54744 + }, + { + "epoch": 16.91, + "learning_rate": 1.228341031880258e-06, + "loss": 0.0031, + "step": 54745 + }, + { + "epoch": 16.91, + "learning_rate": 1.2281008923537707e-06, + "loss": 0.0024, + "step": 54746 + }, + { + "epoch": 16.91, + "learning_rate": 1.227860774767402e-06, + "loss": 0.0032, + "step": 54747 + }, + { + "epoch": 16.91, + "learning_rate": 1.227620679121757e-06, + "loss": 0.0028, + "step": 54748 + }, + { + "epoch": 16.91, + "learning_rate": 1.227380605417432e-06, + "loss": 0.0037, + "step": 54749 + }, + { + "epoch": 16.91, + "learning_rate": 1.2271405536550264e-06, + "loss": 0.0024, + "step": 54750 + }, + { + "epoch": 16.91, + "learning_rate": 1.226900523835144e-06, + "loss": 0.0023, + "step": 54751 + }, + { + "epoch": 16.91, + "learning_rate": 1.226660515958381e-06, + "loss": 0.0025, + "step": 54752 + }, + { + "epoch": 16.91, + "learning_rate": 1.226420530025343e-06, + "loss": 0.0027, + "step": 54753 + }, + { + "epoch": 16.91, + "learning_rate": 1.2261805660366266e-06, + "loss": 0.0031, + "step": 54754 + }, + { + "epoch": 16.91, + "learning_rate": 1.2259406239928317e-06, + "loss": 0.0027, + "step": 54755 + }, + { + "epoch": 16.91, + "learning_rate": 1.225700703894559e-06, + "loss": 0.0024, + "step": 54756 + }, + { + "epoch": 16.91, + "learning_rate": 1.2254608057424123e-06, + "loss": 0.0027, + "step": 54757 + }, + { + "epoch": 16.91, + "learning_rate": 1.2252209295369854e-06, + "loss": 0.0021, + "step": 54758 + }, + { + "epoch": 16.91, + "learning_rate": 1.2249810752788837e-06, + "loss": 0.0015, + "step": 54759 + }, + { + "epoch": 16.91, + "learning_rate": 1.2247412429687044e-06, + "loss": 0.0021, + "step": 54760 + }, + { + "epoch": 16.91, + "learning_rate": 1.2245014326070471e-06, + "loss": 0.0021, + "step": 54761 + }, + { + "epoch": 16.91, + "learning_rate": 1.224261644194511e-06, + "loss": 0.0023, + "step": 54762 + }, + { + "epoch": 16.91, + "learning_rate": 1.2240218777316991e-06, + "loss": 0.0023, + "step": 54763 + }, + { + "epoch": 16.91, + "learning_rate": 1.2237821332192101e-06, + "loss": 0.002, + "step": 54764 + }, + { + "epoch": 16.91, + "learning_rate": 1.2235424106576399e-06, + "loss": 0.0021, + "step": 54765 + }, + { + "epoch": 16.91, + "learning_rate": 1.2233027100475902e-06, + "loss": 0.0029, + "step": 54766 + }, + { + "epoch": 16.91, + "learning_rate": 1.223063031389664e-06, + "loss": 0.0037, + "step": 54767 + }, + { + "epoch": 16.91, + "learning_rate": 1.2228233746844565e-06, + "loss": 0.0026, + "step": 54768 + }, + { + "epoch": 16.91, + "learning_rate": 1.22258373993257e-06, + "loss": 0.0025, + "step": 54769 + }, + { + "epoch": 16.91, + "learning_rate": 1.2223441271346027e-06, + "loss": 0.0021, + "step": 54770 + }, + { + "epoch": 16.91, + "learning_rate": 1.222104536291151e-06, + "loss": 0.0016, + "step": 54771 + }, + { + "epoch": 16.91, + "learning_rate": 1.221864967402817e-06, + "loss": 0.002, + "step": 54772 + }, + { + "epoch": 16.91, + "learning_rate": 1.2216254204702028e-06, + "loss": 0.0017, + "step": 54773 + }, + { + "epoch": 16.92, + "learning_rate": 1.221385895493904e-06, + "loss": 0.0023, + "step": 54774 + }, + { + "epoch": 16.92, + "learning_rate": 1.221146392474517e-06, + "loss": 0.0017, + "step": 54775 + }, + { + "epoch": 16.92, + "learning_rate": 1.2209069114126482e-06, + "loss": 0.002, + "step": 54776 + }, + { + "epoch": 16.92, + "learning_rate": 1.220667452308889e-06, + "loss": 0.0022, + "step": 54777 + }, + { + "epoch": 16.92, + "learning_rate": 1.2204280151638415e-06, + "loss": 0.0019, + "step": 54778 + }, + { + "epoch": 16.92, + "learning_rate": 1.220188599978107e-06, + "loss": 0.0024, + "step": 54779 + }, + { + "epoch": 16.92, + "learning_rate": 1.2199492067522834e-06, + "loss": 0.0017, + "step": 54780 + }, + { + "epoch": 16.92, + "learning_rate": 1.2197098354869651e-06, + "loss": 0.0018, + "step": 54781 + }, + { + "epoch": 16.92, + "learning_rate": 1.2194704861827556e-06, + "loss": 0.0023, + "step": 54782 + }, + { + "epoch": 16.92, + "learning_rate": 1.2192311588402506e-06, + "loss": 0.0023, + "step": 54783 + }, + { + "epoch": 16.92, + "learning_rate": 1.218991853460052e-06, + "loss": 0.0023, + "step": 54784 + }, + { + "epoch": 16.92, + "learning_rate": 1.218752570042756e-06, + "loss": 0.0023, + "step": 54785 + }, + { + "epoch": 16.92, + "learning_rate": 1.21851330858896e-06, + "loss": 0.0019, + "step": 54786 + }, + { + "epoch": 16.92, + "learning_rate": 1.2182740690992635e-06, + "loss": 0.002, + "step": 54787 + }, + { + "epoch": 16.92, + "learning_rate": 1.2180348515742669e-06, + "loss": 0.002, + "step": 54788 + }, + { + "epoch": 16.92, + "learning_rate": 1.2177956560145642e-06, + "loss": 0.0018, + "step": 54789 + }, + { + "epoch": 16.92, + "learning_rate": 1.2175564824207597e-06, + "loss": 0.0014, + "step": 54790 + }, + { + "epoch": 16.92, + "learning_rate": 1.2173173307934483e-06, + "loss": 0.0027, + "step": 54791 + }, + { + "epoch": 16.92, + "learning_rate": 1.217078201133225e-06, + "loss": 0.0028, + "step": 54792 + }, + { + "epoch": 16.92, + "learning_rate": 1.2168390934406915e-06, + "loss": 0.0027, + "step": 54793 + }, + { + "epoch": 16.92, + "learning_rate": 1.2166000077164474e-06, + "loss": 0.0018, + "step": 54794 + }, + { + "epoch": 16.92, + "learning_rate": 1.2163609439610891e-06, + "loss": 0.0027, + "step": 54795 + }, + { + "epoch": 16.92, + "learning_rate": 1.2161219021752125e-06, + "loss": 0.0026, + "step": 54796 + }, + { + "epoch": 16.92, + "learning_rate": 1.2158828823594181e-06, + "loss": 0.0042, + "step": 54797 + }, + { + "epoch": 16.92, + "learning_rate": 1.2156438845143004e-06, + "loss": 0.0023, + "step": 54798 + }, + { + "epoch": 16.92, + "learning_rate": 1.2154049086404607e-06, + "loss": 0.002, + "step": 54799 + }, + { + "epoch": 16.92, + "learning_rate": 1.2151659547384965e-06, + "loss": 0.0022, + "step": 54800 + }, + { + "epoch": 16.92, + "learning_rate": 1.214927022809005e-06, + "loss": 0.0026, + "step": 54801 + }, + { + "epoch": 16.92, + "learning_rate": 1.214688112852581e-06, + "loss": 0.0027, + "step": 54802 + }, + { + "epoch": 16.92, + "learning_rate": 1.2144492248698247e-06, + "loss": 0.0018, + "step": 54803 + }, + { + "epoch": 16.92, + "learning_rate": 1.2142103588613351e-06, + "loss": 0.0022, + "step": 54804 + }, + { + "epoch": 16.92, + "learning_rate": 1.2139715148277087e-06, + "loss": 0.0031, + "step": 54805 + }, + { + "epoch": 16.93, + "learning_rate": 1.213732692769539e-06, + "loss": 0.0022, + "step": 54806 + }, + { + "epoch": 16.93, + "learning_rate": 1.2134938926874284e-06, + "loss": 0.0025, + "step": 54807 + }, + { + "epoch": 16.93, + "learning_rate": 1.2132551145819704e-06, + "loss": 0.002, + "step": 54808 + }, + { + "epoch": 16.93, + "learning_rate": 1.2130163584537646e-06, + "loss": 0.0034, + "step": 54809 + }, + { + "epoch": 16.93, + "learning_rate": 1.2127776243034085e-06, + "loss": 0.0023, + "step": 54810 + }, + { + "epoch": 16.93, + "learning_rate": 1.212538912131499e-06, + "loss": 0.002, + "step": 54811 + }, + { + "epoch": 16.93, + "learning_rate": 1.2123002219386293e-06, + "loss": 0.0019, + "step": 54812 + }, + { + "epoch": 16.93, + "learning_rate": 1.2120615537254022e-06, + "loss": 0.0028, + "step": 54813 + }, + { + "epoch": 16.93, + "learning_rate": 1.2118229074924103e-06, + "loss": 0.0026, + "step": 54814 + }, + { + "epoch": 16.93, + "learning_rate": 1.2115842832402535e-06, + "loss": 0.0019, + "step": 54815 + }, + { + "epoch": 16.93, + "learning_rate": 1.211345680969528e-06, + "loss": 0.0025, + "step": 54816 + }, + { + "epoch": 16.93, + "learning_rate": 1.2111071006808274e-06, + "loss": 0.0021, + "step": 54817 + }, + { + "epoch": 16.93, + "learning_rate": 1.2108685423747512e-06, + "loss": 0.0027, + "step": 54818 + }, + { + "epoch": 16.93, + "learning_rate": 1.2106300060518982e-06, + "loss": 0.0026, + "step": 54819 + }, + { + "epoch": 16.93, + "learning_rate": 1.21039149171286e-06, + "loss": 0.0025, + "step": 54820 + }, + { + "epoch": 16.93, + "learning_rate": 1.2101529993582383e-06, + "loss": 0.0032, + "step": 54821 + }, + { + "epoch": 16.93, + "learning_rate": 1.209914528988626e-06, + "loss": 0.0023, + "step": 54822 + }, + { + "epoch": 16.93, + "learning_rate": 1.2096760806046205e-06, + "loss": 0.0019, + "step": 54823 + }, + { + "epoch": 16.93, + "learning_rate": 1.2094376542068165e-06, + "loss": 0.0022, + "step": 54824 + }, + { + "epoch": 16.93, + "learning_rate": 1.209199249795815e-06, + "loss": 0.0026, + "step": 54825 + }, + { + "epoch": 16.93, + "learning_rate": 1.2089608673722098e-06, + "loss": 0.0025, + "step": 54826 + }, + { + "epoch": 16.93, + "learning_rate": 1.208722506936595e-06, + "loss": 0.0025, + "step": 54827 + }, + { + "epoch": 16.93, + "learning_rate": 1.20848416848957e-06, + "loss": 0.003, + "step": 54828 + }, + { + "epoch": 16.93, + "learning_rate": 1.2082458520317275e-06, + "loss": 0.0027, + "step": 54829 + }, + { + "epoch": 16.93, + "learning_rate": 1.2080075575636662e-06, + "loss": 0.002, + "step": 54830 + }, + { + "epoch": 16.93, + "learning_rate": 1.2077692850859836e-06, + "loss": 0.0025, + "step": 54831 + }, + { + "epoch": 16.93, + "learning_rate": 1.207531034599273e-06, + "loss": 0.0026, + "step": 54832 + }, + { + "epoch": 16.93, + "learning_rate": 1.20729280610413e-06, + "loss": 0.0035, + "step": 54833 + }, + { + "epoch": 16.93, + "learning_rate": 1.2070545996011507e-06, + "loss": 0.0022, + "step": 54834 + }, + { + "epoch": 16.93, + "learning_rate": 1.2068164150909334e-06, + "loss": 0.003, + "step": 54835 + }, + { + "epoch": 16.93, + "learning_rate": 1.206578252574072e-06, + "loss": 0.0023, + "step": 54836 + }, + { + "epoch": 16.93, + "learning_rate": 1.2063401120511608e-06, + "loss": 0.003, + "step": 54837 + }, + { + "epoch": 16.93, + "learning_rate": 1.206101993522798e-06, + "loss": 0.0024, + "step": 54838 + }, + { + "epoch": 16.94, + "learning_rate": 1.2058638969895764e-06, + "loss": 0.0021, + "step": 54839 + }, + { + "epoch": 16.94, + "learning_rate": 1.2056258224520933e-06, + "loss": 0.0025, + "step": 54840 + }, + { + "epoch": 16.94, + "learning_rate": 1.2053877699109485e-06, + "loss": 0.0022, + "step": 54841 + }, + { + "epoch": 16.94, + "learning_rate": 1.2051497393667278e-06, + "loss": 0.0026, + "step": 54842 + }, + { + "epoch": 16.94, + "learning_rate": 1.204911730820032e-06, + "loss": 0.0025, + "step": 54843 + }, + { + "epoch": 16.94, + "learning_rate": 1.2046737442714585e-06, + "loss": 0.0023, + "step": 54844 + }, + { + "epoch": 16.94, + "learning_rate": 1.2044357797215977e-06, + "loss": 0.0021, + "step": 54845 + }, + { + "epoch": 16.94, + "learning_rate": 1.2041978371710493e-06, + "loss": 0.0029, + "step": 54846 + }, + { + "epoch": 16.94, + "learning_rate": 1.2039599166204075e-06, + "loss": 0.0023, + "step": 54847 + }, + { + "epoch": 16.94, + "learning_rate": 1.2037220180702625e-06, + "loss": 0.002, + "step": 54848 + }, + { + "epoch": 16.94, + "learning_rate": 1.2034841415212138e-06, + "loss": 0.0022, + "step": 54849 + }, + { + "epoch": 16.94, + "learning_rate": 1.203246286973858e-06, + "loss": 0.0031, + "step": 54850 + }, + { + "epoch": 16.94, + "learning_rate": 1.203008454428788e-06, + "loss": 0.0018, + "step": 54851 + }, + { + "epoch": 16.94, + "learning_rate": 1.202770643886595e-06, + "loss": 0.0017, + "step": 54852 + }, + { + "epoch": 16.94, + "learning_rate": 1.2025328553478798e-06, + "loss": 0.0023, + "step": 54853 + }, + { + "epoch": 16.94, + "learning_rate": 1.2022950888132324e-06, + "loss": 0.0025, + "step": 54854 + }, + { + "epoch": 16.94, + "learning_rate": 1.2020573442832495e-06, + "loss": 0.0029, + "step": 54855 + }, + { + "epoch": 16.94, + "learning_rate": 1.2018196217585288e-06, + "loss": 0.0022, + "step": 54856 + }, + { + "epoch": 16.94, + "learning_rate": 1.2015819212396606e-06, + "loss": 0.0022, + "step": 54857 + }, + { + "epoch": 16.94, + "learning_rate": 1.2013442427272392e-06, + "loss": 0.0019, + "step": 54858 + }, + { + "epoch": 16.94, + "learning_rate": 1.201106586221863e-06, + "loss": 0.0026, + "step": 54859 + }, + { + "epoch": 16.94, + "learning_rate": 1.2008689517241223e-06, + "loss": 0.0022, + "step": 54860 + }, + { + "epoch": 16.94, + "learning_rate": 1.2006313392346146e-06, + "loss": 0.0032, + "step": 54861 + }, + { + "epoch": 16.94, + "learning_rate": 1.200393748753933e-06, + "loss": 0.0027, + "step": 54862 + }, + { + "epoch": 16.94, + "learning_rate": 1.200156180282669e-06, + "loss": 0.0027, + "step": 54863 + }, + { + "epoch": 16.94, + "learning_rate": 1.1999186338214198e-06, + "loss": 0.0019, + "step": 54864 + }, + { + "epoch": 16.94, + "learning_rate": 1.1996811093707795e-06, + "loss": 0.0019, + "step": 54865 + }, + { + "epoch": 16.94, + "learning_rate": 1.1994436069313431e-06, + "loss": 0.0022, + "step": 54866 + }, + { + "epoch": 16.94, + "learning_rate": 1.1992061265037037e-06, + "loss": 0.0028, + "step": 54867 + }, + { + "epoch": 16.94, + "learning_rate": 1.1989686680884539e-06, + "loss": 0.0023, + "step": 54868 + }, + { + "epoch": 16.94, + "learning_rate": 1.1987312316861888e-06, + "loss": 0.0022, + "step": 54869 + }, + { + "epoch": 16.94, + "learning_rate": 1.1984938172975014e-06, + "loss": 0.002, + "step": 54870 + }, + { + "epoch": 16.95, + "learning_rate": 1.1982564249229878e-06, + "loss": 0.0019, + "step": 54871 + }, + { + "epoch": 16.95, + "learning_rate": 1.1980190545632408e-06, + "loss": 0.0018, + "step": 54872 + }, + { + "epoch": 16.95, + "learning_rate": 1.1977817062188512e-06, + "loss": 0.0028, + "step": 54873 + }, + { + "epoch": 16.95, + "learning_rate": 1.1975443798904151e-06, + "loss": 0.0025, + "step": 54874 + }, + { + "epoch": 16.95, + "learning_rate": 1.1973070755785276e-06, + "loss": 0.002, + "step": 54875 + }, + { + "epoch": 16.95, + "learning_rate": 1.1970697932837782e-06, + "loss": 0.0024, + "step": 54876 + }, + { + "epoch": 16.95, + "learning_rate": 1.1968325330067653e-06, + "loss": 0.003, + "step": 54877 + }, + { + "epoch": 16.95, + "learning_rate": 1.1965952947480808e-06, + "loss": 0.0017, + "step": 54878 + }, + { + "epoch": 16.95, + "learning_rate": 1.196358078508314e-06, + "loss": 0.0023, + "step": 54879 + }, + { + "epoch": 16.95, + "learning_rate": 1.196120884288061e-06, + "loss": 0.0025, + "step": 54880 + }, + { + "epoch": 16.95, + "learning_rate": 1.1958837120879185e-06, + "loss": 0.0018, + "step": 54881 + }, + { + "epoch": 16.95, + "learning_rate": 1.1956465619084755e-06, + "loss": 0.0026, + "step": 54882 + }, + { + "epoch": 16.95, + "learning_rate": 1.1954094337503253e-06, + "loss": 0.0021, + "step": 54883 + }, + { + "epoch": 16.95, + "learning_rate": 1.1951723276140636e-06, + "loss": 0.0024, + "step": 54884 + }, + { + "epoch": 16.95, + "learning_rate": 1.1949352435002793e-06, + "loss": 0.0023, + "step": 54885 + }, + { + "epoch": 16.95, + "learning_rate": 1.1946981814095682e-06, + "loss": 0.0023, + "step": 54886 + }, + { + "epoch": 16.95, + "learning_rate": 1.1944611413425256e-06, + "loss": 0.0022, + "step": 54887 + }, + { + "epoch": 16.95, + "learning_rate": 1.194224123299741e-06, + "loss": 0.0021, + "step": 54888 + }, + { + "epoch": 16.95, + "learning_rate": 1.193987127281806e-06, + "loss": 0.0019, + "step": 54889 + }, + { + "epoch": 16.95, + "learning_rate": 1.1937501532893181e-06, + "loss": 0.0029, + "step": 54890 + }, + { + "epoch": 16.95, + "learning_rate": 1.1935132013228646e-06, + "loss": 0.0026, + "step": 54891 + }, + { + "epoch": 16.95, + "learning_rate": 1.1932762713830426e-06, + "loss": 0.0018, + "step": 54892 + }, + { + "epoch": 16.95, + "learning_rate": 1.193039363470443e-06, + "loss": 0.0024, + "step": 54893 + }, + { + "epoch": 16.95, + "learning_rate": 1.1928024775856562e-06, + "loss": 0.0019, + "step": 54894 + }, + { + "epoch": 16.95, + "learning_rate": 1.1925656137292762e-06, + "loss": 0.0019, + "step": 54895 + }, + { + "epoch": 16.95, + "learning_rate": 1.1923287719018973e-06, + "loss": 0.003, + "step": 54896 + }, + { + "epoch": 16.95, + "learning_rate": 1.1920919521041107e-06, + "loss": 0.003, + "step": 54897 + }, + { + "epoch": 16.95, + "learning_rate": 1.1918551543365109e-06, + "loss": 0.0029, + "step": 54898 + }, + { + "epoch": 16.95, + "learning_rate": 1.1916183785996838e-06, + "loss": 0.002, + "step": 54899 + }, + { + "epoch": 16.95, + "learning_rate": 1.191381624894229e-06, + "loss": 0.0023, + "step": 54900 + }, + { + "epoch": 16.95, + "learning_rate": 1.1911448932207326e-06, + "loss": 0.002, + "step": 54901 + }, + { + "epoch": 16.95, + "learning_rate": 1.190908183579792e-06, + "loss": 0.0018, + "step": 54902 + }, + { + "epoch": 16.96, + "learning_rate": 1.1906714959719967e-06, + "loss": 0.0019, + "step": 54903 + }, + { + "epoch": 16.96, + "learning_rate": 1.1904348303979363e-06, + "loss": 0.0029, + "step": 54904 + }, + { + "epoch": 16.96, + "learning_rate": 1.1901981868582058e-06, + "loss": 0.0022, + "step": 54905 + }, + { + "epoch": 16.96, + "learning_rate": 1.189961565353398e-06, + "loss": 0.0024, + "step": 54906 + }, + { + "epoch": 16.96, + "learning_rate": 1.1897249658841004e-06, + "loss": 0.0025, + "step": 54907 + }, + { + "epoch": 16.96, + "learning_rate": 1.1894883884509102e-06, + "loss": 0.0022, + "step": 54908 + }, + { + "epoch": 16.96, + "learning_rate": 1.1892518330544166e-06, + "loss": 0.0027, + "step": 54909 + }, + { + "epoch": 16.96, + "learning_rate": 1.1890152996952098e-06, + "loss": 0.0019, + "step": 54910 + }, + { + "epoch": 16.96, + "learning_rate": 1.1887787883738821e-06, + "loss": 0.0021, + "step": 54911 + }, + { + "epoch": 16.96, + "learning_rate": 1.1885422990910278e-06, + "loss": 0.0021, + "step": 54912 + }, + { + "epoch": 16.96, + "learning_rate": 1.1883058318472362e-06, + "loss": 0.0034, + "step": 54913 + }, + { + "epoch": 16.96, + "learning_rate": 1.188069386643097e-06, + "loss": 0.0025, + "step": 54914 + }, + { + "epoch": 16.96, + "learning_rate": 1.1878329634792052e-06, + "loss": 0.0023, + "step": 54915 + }, + { + "epoch": 16.96, + "learning_rate": 1.187596562356148e-06, + "loss": 0.0026, + "step": 54916 + }, + { + "epoch": 16.96, + "learning_rate": 1.1873601832745197e-06, + "loss": 0.0035, + "step": 54917 + }, + { + "epoch": 16.96, + "learning_rate": 1.1871238262349128e-06, + "loss": 0.0026, + "step": 54918 + }, + { + "epoch": 16.96, + "learning_rate": 1.186887491237917e-06, + "loss": 0.003, + "step": 54919 + }, + { + "epoch": 16.96, + "learning_rate": 1.1866511782841206e-06, + "loss": 0.0024, + "step": 54920 + }, + { + "epoch": 16.96, + "learning_rate": 1.1864148873741189e-06, + "loss": 0.0019, + "step": 54921 + }, + { + "epoch": 16.96, + "learning_rate": 1.186178618508499e-06, + "loss": 0.0027, + "step": 54922 + }, + { + "epoch": 16.96, + "learning_rate": 1.185942371687857e-06, + "loss": 0.0023, + "step": 54923 + }, + { + "epoch": 16.96, + "learning_rate": 1.1857061469127794e-06, + "loss": 0.002, + "step": 54924 + }, + { + "epoch": 16.96, + "learning_rate": 1.185469944183857e-06, + "loss": 0.0029, + "step": 54925 + }, + { + "epoch": 16.96, + "learning_rate": 1.185233763501682e-06, + "loss": 0.0021, + "step": 54926 + }, + { + "epoch": 16.96, + "learning_rate": 1.1849976048668466e-06, + "loss": 0.0028, + "step": 54927 + }, + { + "epoch": 16.96, + "learning_rate": 1.1847614682799379e-06, + "loss": 0.0022, + "step": 54928 + }, + { + "epoch": 16.96, + "learning_rate": 1.1845253537415513e-06, + "loss": 0.0036, + "step": 54929 + }, + { + "epoch": 16.96, + "learning_rate": 1.1842892612522715e-06, + "loss": 0.002, + "step": 54930 + }, + { + "epoch": 16.96, + "learning_rate": 1.1840531908126951e-06, + "loss": 0.0026, + "step": 54931 + }, + { + "epoch": 16.96, + "learning_rate": 1.183817142423408e-06, + "loss": 0.0022, + "step": 54932 + }, + { + "epoch": 16.96, + "learning_rate": 1.183581116085003e-06, + "loss": 0.002, + "step": 54933 + }, + { + "epoch": 16.96, + "learning_rate": 1.1833451117980698e-06, + "loss": 0.0024, + "step": 54934 + }, + { + "epoch": 16.96, + "learning_rate": 1.183109129563197e-06, + "loss": 0.0025, + "step": 54935 + }, + { + "epoch": 16.97, + "learning_rate": 1.182873169380977e-06, + "loss": 0.0025, + "step": 54936 + }, + { + "epoch": 16.97, + "learning_rate": 1.1826372312519997e-06, + "loss": 0.0022, + "step": 54937 + }, + { + "epoch": 16.97, + "learning_rate": 1.1824013151768542e-06, + "loss": 0.0023, + "step": 54938 + }, + { + "epoch": 16.97, + "learning_rate": 1.1821654211561329e-06, + "loss": 0.0021, + "step": 54939 + }, + { + "epoch": 16.97, + "learning_rate": 1.1819295491904236e-06, + "loss": 0.0019, + "step": 54940 + }, + { + "epoch": 16.97, + "learning_rate": 1.1816936992803151e-06, + "loss": 0.0024, + "step": 54941 + }, + { + "epoch": 16.97, + "learning_rate": 1.1814578714264002e-06, + "loss": 0.0024, + "step": 54942 + }, + { + "epoch": 16.97, + "learning_rate": 1.1812220656292683e-06, + "loss": 0.0022, + "step": 54943 + }, + { + "epoch": 16.97, + "learning_rate": 1.180986281889509e-06, + "loss": 0.0024, + "step": 54944 + }, + { + "epoch": 16.97, + "learning_rate": 1.1807505202077084e-06, + "loss": 0.0019, + "step": 54945 + }, + { + "epoch": 16.97, + "learning_rate": 1.180514780584463e-06, + "loss": 0.0021, + "step": 54946 + }, + { + "epoch": 16.97, + "learning_rate": 1.1802790630203554e-06, + "loss": 0.0028, + "step": 54947 + }, + { + "epoch": 16.97, + "learning_rate": 1.1800433675159784e-06, + "loss": 0.0024, + "step": 54948 + }, + { + "epoch": 16.97, + "learning_rate": 1.1798076940719272e-06, + "loss": 0.0025, + "step": 54949 + }, + { + "epoch": 16.97, + "learning_rate": 1.1795720426887802e-06, + "loss": 0.0024, + "step": 54950 + }, + { + "epoch": 16.97, + "learning_rate": 1.1793364133671326e-06, + "loss": 0.0022, + "step": 54951 + }, + { + "epoch": 16.97, + "learning_rate": 1.179100806107575e-06, + "loss": 0.0024, + "step": 54952 + }, + { + "epoch": 16.97, + "learning_rate": 1.1788652209106933e-06, + "loss": 0.0027, + "step": 54953 + }, + { + "epoch": 16.97, + "learning_rate": 1.1786296577770817e-06, + "loss": 0.002, + "step": 54954 + }, + { + "epoch": 16.97, + "learning_rate": 1.1783941167073253e-06, + "loss": 0.0013, + "step": 54955 + }, + { + "epoch": 16.97, + "learning_rate": 1.1781585977020116e-06, + "loss": 0.002, + "step": 54956 + }, + { + "epoch": 16.97, + "learning_rate": 1.177923100761733e-06, + "loss": 0.0019, + "step": 54957 + }, + { + "epoch": 16.97, + "learning_rate": 1.1776876258870795e-06, + "loss": 0.0014, + "step": 54958 + }, + { + "epoch": 16.97, + "learning_rate": 1.1774521730786392e-06, + "loss": 0.0019, + "step": 54959 + }, + { + "epoch": 16.97, + "learning_rate": 1.1772167423369974e-06, + "loss": 0.0023, + "step": 54960 + }, + { + "epoch": 16.97, + "learning_rate": 1.1769813336627479e-06, + "loss": 0.0019, + "step": 54961 + }, + { + "epoch": 16.97, + "learning_rate": 1.1767459470564747e-06, + "loss": 0.0017, + "step": 54962 + }, + { + "epoch": 16.97, + "learning_rate": 1.1765105825187695e-06, + "loss": 0.002, + "step": 54963 + }, + { + "epoch": 16.97, + "learning_rate": 1.1762752400502232e-06, + "loss": 0.0018, + "step": 54964 + }, + { + "epoch": 16.97, + "learning_rate": 1.1760399196514205e-06, + "loss": 0.0015, + "step": 54965 + }, + { + "epoch": 16.97, + "learning_rate": 1.1758046213229512e-06, + "loss": 0.0019, + "step": 54966 + }, + { + "epoch": 16.97, + "learning_rate": 1.1755693450654027e-06, + "loss": 0.0037, + "step": 54967 + }, + { + "epoch": 16.98, + "learning_rate": 1.1753340908793665e-06, + "loss": 0.0022, + "step": 54968 + }, + { + "epoch": 16.98, + "learning_rate": 1.1750988587654277e-06, + "loss": 0.0018, + "step": 54969 + }, + { + "epoch": 16.98, + "learning_rate": 1.1748636487241793e-06, + "loss": 0.0025, + "step": 54970 + }, + { + "epoch": 16.98, + "learning_rate": 1.1746284607562052e-06, + "loss": 0.0025, + "step": 54971 + }, + { + "epoch": 16.98, + "learning_rate": 1.174393294862093e-06, + "loss": 0.0023, + "step": 54972 + }, + { + "epoch": 16.98, + "learning_rate": 1.1741581510424339e-06, + "loss": 0.0024, + "step": 54973 + }, + { + "epoch": 16.98, + "learning_rate": 1.1739230292978154e-06, + "loss": 0.0021, + "step": 54974 + }, + { + "epoch": 16.98, + "learning_rate": 1.173687929628826e-06, + "loss": 0.0021, + "step": 54975 + }, + { + "epoch": 16.98, + "learning_rate": 1.1734528520360511e-06, + "loss": 0.0025, + "step": 54976 + }, + { + "epoch": 16.98, + "learning_rate": 1.1732177965200831e-06, + "loss": 0.0019, + "step": 54977 + }, + { + "epoch": 16.98, + "learning_rate": 1.172982763081504e-06, + "loss": 0.0019, + "step": 54978 + }, + { + "epoch": 16.98, + "learning_rate": 1.1727477517209052e-06, + "loss": 0.0021, + "step": 54979 + }, + { + "epoch": 16.98, + "learning_rate": 1.1725127624388788e-06, + "loss": 0.0022, + "step": 54980 + }, + { + "epoch": 16.98, + "learning_rate": 1.1722777952360044e-06, + "loss": 0.0023, + "step": 54981 + }, + { + "epoch": 16.98, + "learning_rate": 1.1720428501128722e-06, + "loss": 0.002, + "step": 54982 + }, + { + "epoch": 16.98, + "learning_rate": 1.1718079270700733e-06, + "loss": 0.0028, + "step": 54983 + }, + { + "epoch": 16.98, + "learning_rate": 1.1715730261081914e-06, + "loss": 0.0024, + "step": 54984 + }, + { + "epoch": 16.98, + "learning_rate": 1.1713381472278175e-06, + "loss": 0.0021, + "step": 54985 + }, + { + "epoch": 16.98, + "learning_rate": 1.1711032904295372e-06, + "loss": 0.0034, + "step": 54986 + }, + { + "epoch": 16.98, + "learning_rate": 1.170868455713935e-06, + "loss": 0.0021, + "step": 54987 + }, + { + "epoch": 16.98, + "learning_rate": 1.1706336430816013e-06, + "loss": 0.0024, + "step": 54988 + }, + { + "epoch": 16.98, + "learning_rate": 1.1703988525331256e-06, + "loss": 0.0019, + "step": 54989 + }, + { + "epoch": 16.98, + "learning_rate": 1.170164084069093e-06, + "loss": 0.0024, + "step": 54990 + }, + { + "epoch": 16.98, + "learning_rate": 1.1699293376900888e-06, + "loss": 0.0021, + "step": 54991 + }, + { + "epoch": 16.98, + "learning_rate": 1.1696946133967035e-06, + "loss": 0.0018, + "step": 54992 + }, + { + "epoch": 16.98, + "learning_rate": 1.16945991118952e-06, + "loss": 0.0027, + "step": 54993 + }, + { + "epoch": 16.98, + "learning_rate": 1.1692252310691277e-06, + "loss": 0.002, + "step": 54994 + }, + { + "epoch": 16.98, + "learning_rate": 1.1689905730361162e-06, + "loss": 0.0022, + "step": 54995 + }, + { + "epoch": 16.98, + "learning_rate": 1.1687559370910705e-06, + "loss": 0.0021, + "step": 54996 + }, + { + "epoch": 16.98, + "learning_rate": 1.1685213232345738e-06, + "loss": 0.002, + "step": 54997 + }, + { + "epoch": 16.98, + "learning_rate": 1.1682867314672176e-06, + "loss": 0.0031, + "step": 54998 + }, + { + "epoch": 16.98, + "learning_rate": 1.168052161789588e-06, + "loss": 0.0018, + "step": 54999 + }, + { + "epoch": 16.98, + "learning_rate": 1.1678176142022702e-06, + "loss": 0.0017, + "step": 55000 + }, + { + "epoch": 16.99, + "learning_rate": 1.1675830887058505e-06, + "loss": 0.0036, + "step": 55001 + }, + { + "epoch": 16.99, + "learning_rate": 1.1673485853009182e-06, + "loss": 0.0021, + "step": 55002 + }, + { + "epoch": 16.99, + "learning_rate": 1.167114103988055e-06, + "loss": 0.0028, + "step": 55003 + }, + { + "epoch": 16.99, + "learning_rate": 1.1668796447678522e-06, + "loss": 0.0024, + "step": 55004 + }, + { + "epoch": 16.99, + "learning_rate": 1.1666452076408952e-06, + "loss": 0.0022, + "step": 55005 + }, + { + "epoch": 16.99, + "learning_rate": 1.1664107926077706e-06, + "loss": 0.0024, + "step": 55006 + }, + { + "epoch": 16.99, + "learning_rate": 1.1661763996690612e-06, + "loss": 0.0029, + "step": 55007 + }, + { + "epoch": 16.99, + "learning_rate": 1.1659420288253575e-06, + "loss": 0.0021, + "step": 55008 + }, + { + "epoch": 16.99, + "learning_rate": 1.1657076800772427e-06, + "loss": 0.0022, + "step": 55009 + }, + { + "epoch": 16.99, + "learning_rate": 1.165473353425306e-06, + "loss": 0.0028, + "step": 55010 + }, + { + "epoch": 16.99, + "learning_rate": 1.1652390488701316e-06, + "loss": 0.0018, + "step": 55011 + }, + { + "epoch": 16.99, + "learning_rate": 1.1650047664123032e-06, + "loss": 0.0021, + "step": 55012 + }, + { + "epoch": 16.99, + "learning_rate": 1.1647705060524106e-06, + "loss": 0.0022, + "step": 55013 + }, + { + "epoch": 16.99, + "learning_rate": 1.1645362677910398e-06, + "loss": 0.0018, + "step": 55014 + }, + { + "epoch": 16.99, + "learning_rate": 1.1643020516287728e-06, + "loss": 0.0029, + "step": 55015 + }, + { + "epoch": 16.99, + "learning_rate": 1.1640678575662002e-06, + "loss": 0.0015, + "step": 55016 + }, + { + "epoch": 16.99, + "learning_rate": 1.1638336856039056e-06, + "loss": 0.0019, + "step": 55017 + }, + { + "epoch": 16.99, + "learning_rate": 1.1635995357424723e-06, + "loss": 0.0024, + "step": 55018 + }, + { + "epoch": 16.99, + "learning_rate": 1.1633654079824885e-06, + "loss": 0.0024, + "step": 55019 + }, + { + "epoch": 16.99, + "learning_rate": 1.1631313023245417e-06, + "loss": 0.0028, + "step": 55020 + }, + { + "epoch": 16.99, + "learning_rate": 1.1628972187692145e-06, + "loss": 0.0018, + "step": 55021 + }, + { + "epoch": 16.99, + "learning_rate": 1.162663157317092e-06, + "loss": 0.0028, + "step": 55022 + }, + { + "epoch": 16.99, + "learning_rate": 1.1624291179687619e-06, + "loss": 0.0029, + "step": 55023 + }, + { + "epoch": 16.99, + "learning_rate": 1.1621951007248079e-06, + "loss": 0.0023, + "step": 55024 + }, + { + "epoch": 16.99, + "learning_rate": 1.1619611055858138e-06, + "loss": 0.0026, + "step": 55025 + }, + { + "epoch": 16.99, + "learning_rate": 1.1617271325523705e-06, + "loss": 0.0029, + "step": 55026 + }, + { + "epoch": 16.99, + "learning_rate": 1.1614931816250597e-06, + "loss": 0.0021, + "step": 55027 + }, + { + "epoch": 16.99, + "learning_rate": 1.161259252804463e-06, + "loss": 0.0029, + "step": 55028 + }, + { + "epoch": 16.99, + "learning_rate": 1.1610253460911702e-06, + "loss": 0.0024, + "step": 55029 + }, + { + "epoch": 16.99, + "learning_rate": 1.1607914614857675e-06, + "loss": 0.0027, + "step": 55030 + }, + { + "epoch": 16.99, + "learning_rate": 1.1605575989888363e-06, + "loss": 0.0025, + "step": 55031 + }, + { + "epoch": 16.99, + "learning_rate": 1.160323758600962e-06, + "loss": 0.002, + "step": 55032 + }, + { + "epoch": 17.0, + "learning_rate": 1.1600899403227317e-06, + "loss": 0.0021, + "step": 55033 + }, + { + "epoch": 17.0, + "learning_rate": 1.1598561441547263e-06, + "loss": 0.0024, + "step": 55034 + }, + { + "epoch": 17.0, + "learning_rate": 1.159622370097534e-06, + "loss": 0.0024, + "step": 55035 + }, + { + "epoch": 17.0, + "learning_rate": 1.1593886181517399e-06, + "loss": 0.0023, + "step": 55036 + }, + { + "epoch": 17.0, + "learning_rate": 1.1591548883179271e-06, + "loss": 0.0027, + "step": 55037 + }, + { + "epoch": 17.0, + "learning_rate": 1.1589211805966782e-06, + "loss": 0.0029, + "step": 55038 + }, + { + "epoch": 17.0, + "learning_rate": 1.158687494988583e-06, + "loss": 0.0022, + "step": 55039 + }, + { + "epoch": 17.0, + "learning_rate": 1.1584538314942206e-06, + "loss": 0.0026, + "step": 55040 + }, + { + "epoch": 17.0, + "learning_rate": 1.1582201901141787e-06, + "loss": 0.0021, + "step": 55041 + }, + { + "epoch": 17.0, + "learning_rate": 1.1579865708490423e-06, + "loss": 0.0028, + "step": 55042 + }, + { + "epoch": 17.0, + "learning_rate": 1.1577529736993908e-06, + "loss": 0.0021, + "step": 55043 + }, + { + "epoch": 17.0, + "learning_rate": 1.1575193986658128e-06, + "loss": 0.0025, + "step": 55044 + }, + { + "epoch": 17.0, + "learning_rate": 1.1572858457488933e-06, + "loss": 0.0023, + "step": 55045 + }, + { + "epoch": 17.0, + "learning_rate": 1.157052314949212e-06, + "loss": 0.0016, + "step": 55046 + }, + { + "epoch": 17.0, + "learning_rate": 1.156818806267359e-06, + "loss": 0.0038, + "step": 55047 + }, + { + "epoch": 17.0, + "learning_rate": 1.1565853197039145e-06, + "loss": 0.0023, + "step": 55048 + }, + { + "epoch": 17.0, + "learning_rate": 1.15635185525946e-06, + "loss": 0.0025, + "step": 55049 + }, + { + "epoch": 17.0, + "learning_rate": 1.1561184129345837e-06, + "loss": 0.0019, + "step": 55050 + }, + { + "epoch": 17.0, + "learning_rate": 1.1558849927298699e-06, + "loss": 0.0013, + "step": 55051 + }, + { + "epoch": 17.0, + "learning_rate": 1.1556515946459013e-06, + "loss": 0.0016, + "step": 55052 + }, + { + "epoch": 17.0, + "learning_rate": 1.1554182186832585e-06, + "loss": 0.0018, + "step": 55053 + }, + { + "epoch": 17.0, + "learning_rate": 1.15518486484253e-06, + "loss": 0.0015, + "step": 55054 + }, + { + "epoch": 17.0, + "learning_rate": 1.1549515331242955e-06, + "loss": 0.002, + "step": 55055 + }, + { + "epoch": 17.0, + "learning_rate": 1.154718223529141e-06, + "loss": 0.0015, + "step": 55056 + }, + { + "epoch": 17.0, + "learning_rate": 1.1544849360576504e-06, + "loss": 0.0016, + "step": 55057 + }, + { + "epoch": 17.0, + "learning_rate": 1.1542516707104069e-06, + "loss": 0.0017, + "step": 55058 + }, + { + "epoch": 17.0, + "learning_rate": 1.1540184274879917e-06, + "loss": 0.0011, + "step": 55059 + }, + { + "epoch": 17.0, + "learning_rate": 1.1537852063909893e-06, + "loss": 0.0019, + "step": 55060 + }, + { + "epoch": 17.0, + "learning_rate": 1.1535520074199858e-06, + "loss": 0.0015, + "step": 55061 + }, + { + "epoch": 17.0, + "learning_rate": 1.1533188305755616e-06, + "loss": 0.0013, + "step": 55062 + }, + { + "epoch": 17.0, + "learning_rate": 1.1530856758582987e-06, + "loss": 0.0015, + "step": 55063 + }, + { + "epoch": 17.0, + "learning_rate": 1.1528525432687853e-06, + "loss": 0.0016, + "step": 55064 + }, + { + "epoch": 17.01, + "learning_rate": 1.152619432807598e-06, + "loss": 0.0015, + "step": 55065 + }, + { + "epoch": 17.01, + "learning_rate": 1.1523863444753235e-06, + "loss": 0.0018, + "step": 55066 + }, + { + "epoch": 17.01, + "learning_rate": 1.1521532782725465e-06, + "loss": 0.0014, + "step": 55067 + }, + { + "epoch": 17.01, + "learning_rate": 1.1519202341998482e-06, + "loss": 0.0019, + "step": 55068 + }, + { + "epoch": 17.01, + "learning_rate": 1.1516872122578081e-06, + "loss": 0.0015, + "step": 55069 + }, + { + "epoch": 17.01, + "learning_rate": 1.1514542124470151e-06, + "loss": 0.0021, + "step": 55070 + }, + { + "epoch": 17.01, + "learning_rate": 1.1512212347680474e-06, + "loss": 0.0021, + "step": 55071 + }, + { + "epoch": 17.01, + "learning_rate": 1.150988279221491e-06, + "loss": 0.0018, + "step": 55072 + }, + { + "epoch": 17.01, + "learning_rate": 1.1507553458079256e-06, + "loss": 0.0017, + "step": 55073 + }, + { + "epoch": 17.01, + "learning_rate": 1.1505224345279341e-06, + "loss": 0.0016, + "step": 55074 + }, + { + "epoch": 17.01, + "learning_rate": 1.1502895453821005e-06, + "loss": 0.0017, + "step": 55075 + }, + { + "epoch": 17.01, + "learning_rate": 1.1500566783710087e-06, + "loss": 0.0017, + "step": 55076 + }, + { + "epoch": 17.01, + "learning_rate": 1.1498238334952362e-06, + "loss": 0.0013, + "step": 55077 + }, + { + "epoch": 17.01, + "learning_rate": 1.149591010755372e-06, + "loss": 0.0019, + "step": 55078 + }, + { + "epoch": 17.01, + "learning_rate": 1.149358210151994e-06, + "loss": 0.0013, + "step": 55079 + }, + { + "epoch": 17.01, + "learning_rate": 1.1491254316856837e-06, + "loss": 0.0016, + "step": 55080 + }, + { + "epoch": 17.01, + "learning_rate": 1.1488926753570239e-06, + "loss": 0.0017, + "step": 55081 + }, + { + "epoch": 17.01, + "learning_rate": 1.148659941166601e-06, + "loss": 0.0021, + "step": 55082 + }, + { + "epoch": 17.01, + "learning_rate": 1.1484272291149935e-06, + "loss": 0.002, + "step": 55083 + }, + { + "epoch": 17.01, + "learning_rate": 1.1481945392027827e-06, + "loss": 0.0022, + "step": 55084 + }, + { + "epoch": 17.01, + "learning_rate": 1.147961871430553e-06, + "loss": 0.0023, + "step": 55085 + }, + { + "epoch": 17.01, + "learning_rate": 1.1477292257988836e-06, + "loss": 0.0018, + "step": 55086 + }, + { + "epoch": 17.01, + "learning_rate": 1.1474966023083579e-06, + "loss": 0.0019, + "step": 55087 + }, + { + "epoch": 17.01, + "learning_rate": 1.1472640009595616e-06, + "loss": 0.0014, + "step": 55088 + }, + { + "epoch": 17.01, + "learning_rate": 1.1470314217530688e-06, + "loss": 0.0017, + "step": 55089 + }, + { + "epoch": 17.01, + "learning_rate": 1.1467988646894646e-06, + "loss": 0.0015, + "step": 55090 + }, + { + "epoch": 17.01, + "learning_rate": 1.146566329769333e-06, + "loss": 0.0017, + "step": 55091 + }, + { + "epoch": 17.01, + "learning_rate": 1.1463338169932524e-06, + "loss": 0.0016, + "step": 55092 + }, + { + "epoch": 17.01, + "learning_rate": 1.146101326361808e-06, + "loss": 0.0016, + "step": 55093 + }, + { + "epoch": 17.01, + "learning_rate": 1.1458688578755772e-06, + "loss": 0.0014, + "step": 55094 + }, + { + "epoch": 17.01, + "learning_rate": 1.1456364115351448e-06, + "loss": 0.0016, + "step": 55095 + }, + { + "epoch": 17.01, + "learning_rate": 1.1454039873410883e-06, + "loss": 0.0013, + "step": 55096 + }, + { + "epoch": 17.01, + "learning_rate": 1.1451715852939916e-06, + "loss": 0.0012, + "step": 55097 + }, + { + "epoch": 17.02, + "learning_rate": 1.1449392053944398e-06, + "loss": 0.0019, + "step": 55098 + }, + { + "epoch": 17.02, + "learning_rate": 1.1447068476430068e-06, + "loss": 0.0017, + "step": 55099 + }, + { + "epoch": 17.02, + "learning_rate": 1.1444745120402767e-06, + "loss": 0.0018, + "step": 55100 + }, + { + "epoch": 17.02, + "learning_rate": 1.1442421985868324e-06, + "loss": 0.0016, + "step": 55101 + }, + { + "epoch": 17.02, + "learning_rate": 1.1440099072832523e-06, + "loss": 0.0015, + "step": 55102 + }, + { + "epoch": 17.02, + "learning_rate": 1.1437776381301203e-06, + "loss": 0.0017, + "step": 55103 + }, + { + "epoch": 17.02, + "learning_rate": 1.1435453911280159e-06, + "loss": 0.0021, + "step": 55104 + }, + { + "epoch": 17.02, + "learning_rate": 1.1433131662775177e-06, + "loss": 0.0016, + "step": 55105 + }, + { + "epoch": 17.02, + "learning_rate": 1.1430809635792083e-06, + "loss": 0.0015, + "step": 55106 + }, + { + "epoch": 17.02, + "learning_rate": 1.142848783033671e-06, + "loss": 0.0015, + "step": 55107 + }, + { + "epoch": 17.02, + "learning_rate": 1.142616624641485e-06, + "loss": 0.002, + "step": 55108 + }, + { + "epoch": 17.02, + "learning_rate": 1.1423844884032276e-06, + "loss": 0.0017, + "step": 55109 + }, + { + "epoch": 17.02, + "learning_rate": 1.142152374319484e-06, + "loss": 0.0023, + "step": 55110 + }, + { + "epoch": 17.02, + "learning_rate": 1.1419202823908315e-06, + "loss": 0.0015, + "step": 55111 + }, + { + "epoch": 17.02, + "learning_rate": 1.1416882126178508e-06, + "loss": 0.0018, + "step": 55112 + }, + { + "epoch": 17.02, + "learning_rate": 1.1414561650011269e-06, + "loss": 0.0017, + "step": 55113 + }, + { + "epoch": 17.02, + "learning_rate": 1.141224139541236e-06, + "loss": 0.0019, + "step": 55114 + }, + { + "epoch": 17.02, + "learning_rate": 1.1409921362387576e-06, + "loss": 0.0019, + "step": 55115 + }, + { + "epoch": 17.02, + "learning_rate": 1.140760155094276e-06, + "loss": 0.0017, + "step": 55116 + }, + { + "epoch": 17.02, + "learning_rate": 1.140528196108366e-06, + "loss": 0.0019, + "step": 55117 + }, + { + "epoch": 17.02, + "learning_rate": 1.1402962592816137e-06, + "loss": 0.002, + "step": 55118 + }, + { + "epoch": 17.02, + "learning_rate": 1.1400643446145965e-06, + "loss": 0.0016, + "step": 55119 + }, + { + "epoch": 17.02, + "learning_rate": 1.139832452107892e-06, + "loss": 0.0014, + "step": 55120 + }, + { + "epoch": 17.02, + "learning_rate": 1.1396005817620825e-06, + "loss": 0.0016, + "step": 55121 + }, + { + "epoch": 17.02, + "learning_rate": 1.1393687335777504e-06, + "loss": 0.0017, + "step": 55122 + }, + { + "epoch": 17.02, + "learning_rate": 1.1391369075554704e-06, + "loss": 0.0027, + "step": 55123 + }, + { + "epoch": 17.02, + "learning_rate": 1.1389051036958276e-06, + "loss": 0.0015, + "step": 55124 + }, + { + "epoch": 17.02, + "learning_rate": 1.1386733219993973e-06, + "loss": 0.0015, + "step": 55125 + }, + { + "epoch": 17.02, + "learning_rate": 1.1384415624667632e-06, + "loss": 0.0021, + "step": 55126 + }, + { + "epoch": 17.02, + "learning_rate": 1.1382098250985007e-06, + "loss": 0.0013, + "step": 55127 + }, + { + "epoch": 17.02, + "learning_rate": 1.1379781098951936e-06, + "loss": 0.002, + "step": 55128 + }, + { + "epoch": 17.02, + "learning_rate": 1.1377464168574203e-06, + "loss": 0.0017, + "step": 55129 + }, + { + "epoch": 17.03, + "learning_rate": 1.1375147459857572e-06, + "loss": 0.002, + "step": 55130 + }, + { + "epoch": 17.03, + "learning_rate": 1.1372830972807858e-06, + "loss": 0.0017, + "step": 55131 + }, + { + "epoch": 17.03, + "learning_rate": 1.1370514707430891e-06, + "loss": 0.0014, + "step": 55132 + }, + { + "epoch": 17.03, + "learning_rate": 1.13681986637324e-06, + "loss": 0.0015, + "step": 55133 + }, + { + "epoch": 17.03, + "learning_rate": 1.1365882841718235e-06, + "loss": 0.0016, + "step": 55134 + }, + { + "epoch": 17.03, + "learning_rate": 1.1363567241394159e-06, + "loss": 0.002, + "step": 55135 + }, + { + "epoch": 17.03, + "learning_rate": 1.1361251862765943e-06, + "loss": 0.0021, + "step": 55136 + }, + { + "epoch": 17.03, + "learning_rate": 1.1358936705839408e-06, + "loss": 0.0015, + "step": 55137 + }, + { + "epoch": 17.03, + "learning_rate": 1.1356621770620368e-06, + "loss": 0.0024, + "step": 55138 + }, + { + "epoch": 17.03, + "learning_rate": 1.1354307057114578e-06, + "loss": 0.0013, + "step": 55139 + }, + { + "epoch": 17.03, + "learning_rate": 1.1351992565327808e-06, + "loss": 0.0009, + "step": 55140 + }, + { + "epoch": 17.03, + "learning_rate": 1.1349678295265898e-06, + "loss": 0.0013, + "step": 55141 + }, + { + "epoch": 17.03, + "learning_rate": 1.134736424693459e-06, + "loss": 0.0014, + "step": 55142 + }, + { + "epoch": 17.03, + "learning_rate": 1.1345050420339687e-06, + "loss": 0.0017, + "step": 55143 + }, + { + "epoch": 17.03, + "learning_rate": 1.134273681548701e-06, + "loss": 0.0017, + "step": 55144 + }, + { + "epoch": 17.03, + "learning_rate": 1.1340423432382319e-06, + "loss": 0.0022, + "step": 55145 + }, + { + "epoch": 17.03, + "learning_rate": 1.1338110271031378e-06, + "loss": 0.0013, + "step": 55146 + }, + { + "epoch": 17.03, + "learning_rate": 1.1335797331440025e-06, + "loss": 0.0015, + "step": 55147 + }, + { + "epoch": 17.03, + "learning_rate": 1.1333484613613976e-06, + "loss": 0.0019, + "step": 55148 + }, + { + "epoch": 17.03, + "learning_rate": 1.1331172117559086e-06, + "loss": 0.0013, + "step": 55149 + }, + { + "epoch": 17.03, + "learning_rate": 1.1328859843281105e-06, + "loss": 0.0014, + "step": 55150 + }, + { + "epoch": 17.03, + "learning_rate": 1.1326547790785792e-06, + "loss": 0.002, + "step": 55151 + }, + { + "epoch": 17.03, + "learning_rate": 1.1324235960078956e-06, + "loss": 0.0012, + "step": 55152 + }, + { + "epoch": 17.03, + "learning_rate": 1.1321924351166402e-06, + "loss": 0.0019, + "step": 55153 + }, + { + "epoch": 17.03, + "learning_rate": 1.1319612964053871e-06, + "loss": 0.0018, + "step": 55154 + }, + { + "epoch": 17.03, + "learning_rate": 1.1317301798747182e-06, + "loss": 0.0013, + "step": 55155 + }, + { + "epoch": 17.03, + "learning_rate": 1.1314990855252094e-06, + "loss": 0.0017, + "step": 55156 + }, + { + "epoch": 17.03, + "learning_rate": 1.131268013357437e-06, + "loss": 0.0013, + "step": 55157 + }, + { + "epoch": 17.03, + "learning_rate": 1.1310369633719809e-06, + "loss": 0.0019, + "step": 55158 + }, + { + "epoch": 17.03, + "learning_rate": 1.1308059355694212e-06, + "loss": 0.0022, + "step": 55159 + }, + { + "epoch": 17.03, + "learning_rate": 1.1305749299503333e-06, + "loss": 0.0017, + "step": 55160 + }, + { + "epoch": 17.03, + "learning_rate": 1.1303439465152933e-06, + "loss": 0.0017, + "step": 55161 + }, + { + "epoch": 17.04, + "learning_rate": 1.1301129852648795e-06, + "loss": 0.0021, + "step": 55162 + }, + { + "epoch": 17.04, + "learning_rate": 1.1298820461996752e-06, + "loss": 0.0018, + "step": 55163 + }, + { + "epoch": 17.04, + "learning_rate": 1.1296511293202494e-06, + "loss": 0.0016, + "step": 55164 + }, + { + "epoch": 17.04, + "learning_rate": 1.1294202346271877e-06, + "loss": 0.0025, + "step": 55165 + }, + { + "epoch": 17.04, + "learning_rate": 1.1291893621210637e-06, + "loss": 0.0013, + "step": 55166 + }, + { + "epoch": 17.04, + "learning_rate": 1.1289585118024516e-06, + "loss": 0.0018, + "step": 55167 + }, + { + "epoch": 17.04, + "learning_rate": 1.1287276836719341e-06, + "loss": 0.0017, + "step": 55168 + }, + { + "epoch": 17.04, + "learning_rate": 1.1284968777300876e-06, + "loss": 0.0018, + "step": 55169 + }, + { + "epoch": 17.04, + "learning_rate": 1.128266093977488e-06, + "loss": 0.0015, + "step": 55170 + }, + { + "epoch": 17.04, + "learning_rate": 1.1280353324147119e-06, + "loss": 0.0019, + "step": 55171 + }, + { + "epoch": 17.04, + "learning_rate": 1.1278045930423399e-06, + "loss": 0.0016, + "step": 55172 + }, + { + "epoch": 17.04, + "learning_rate": 1.1275738758609444e-06, + "loss": 0.0015, + "step": 55173 + }, + { + "epoch": 17.04, + "learning_rate": 1.1273431808711045e-06, + "loss": 0.0021, + "step": 55174 + }, + { + "epoch": 17.04, + "learning_rate": 1.1271125080734003e-06, + "loss": 0.0016, + "step": 55175 + }, + { + "epoch": 17.04, + "learning_rate": 1.1268818574684049e-06, + "loss": 0.0012, + "step": 55176 + }, + { + "epoch": 17.04, + "learning_rate": 1.1266512290566955e-06, + "loss": 0.0015, + "step": 55177 + }, + { + "epoch": 17.04, + "learning_rate": 1.1264206228388508e-06, + "loss": 0.0014, + "step": 55178 + }, + { + "epoch": 17.04, + "learning_rate": 1.1261900388154445e-06, + "loss": 0.002, + "step": 55179 + }, + { + "epoch": 17.04, + "learning_rate": 1.1259594769870586e-06, + "loss": 0.0018, + "step": 55180 + }, + { + "epoch": 17.04, + "learning_rate": 1.1257289373542657e-06, + "loss": 0.002, + "step": 55181 + }, + { + "epoch": 17.04, + "learning_rate": 1.1254984199176411e-06, + "loss": 0.0019, + "step": 55182 + }, + { + "epoch": 17.04, + "learning_rate": 1.1252679246777642e-06, + "loss": 0.0012, + "step": 55183 + }, + { + "epoch": 17.04, + "learning_rate": 1.1250374516352125e-06, + "loss": 0.0017, + "step": 55184 + }, + { + "epoch": 17.04, + "learning_rate": 1.1248070007905587e-06, + "loss": 0.001, + "step": 55185 + }, + { + "epoch": 17.04, + "learning_rate": 1.1245765721443835e-06, + "loss": 0.0017, + "step": 55186 + }, + { + "epoch": 17.04, + "learning_rate": 1.1243461656972621e-06, + "loss": 0.0024, + "step": 55187 + }, + { + "epoch": 17.04, + "learning_rate": 1.1241157814497662e-06, + "loss": 0.0016, + "step": 55188 + }, + { + "epoch": 17.04, + "learning_rate": 1.1238854194024763e-06, + "loss": 0.0025, + "step": 55189 + }, + { + "epoch": 17.04, + "learning_rate": 1.1236550795559697e-06, + "loss": 0.0013, + "step": 55190 + }, + { + "epoch": 17.04, + "learning_rate": 1.1234247619108207e-06, + "loss": 0.0022, + "step": 55191 + }, + { + "epoch": 17.04, + "learning_rate": 1.1231944664676032e-06, + "loss": 0.0016, + "step": 55192 + }, + { + "epoch": 17.04, + "learning_rate": 1.1229641932268953e-06, + "loss": 0.0018, + "step": 55193 + }, + { + "epoch": 17.04, + "learning_rate": 1.1227339421892758e-06, + "loss": 0.0013, + "step": 55194 + }, + { + "epoch": 17.05, + "learning_rate": 1.1225037133553151e-06, + "loss": 0.0012, + "step": 55195 + }, + { + "epoch": 17.05, + "learning_rate": 1.1222735067255941e-06, + "loss": 0.0021, + "step": 55196 + }, + { + "epoch": 17.05, + "learning_rate": 1.1220433223006866e-06, + "loss": 0.0016, + "step": 55197 + }, + { + "epoch": 17.05, + "learning_rate": 1.1218131600811655e-06, + "loss": 0.0021, + "step": 55198 + }, + { + "epoch": 17.05, + "learning_rate": 1.1215830200676091e-06, + "loss": 0.0015, + "step": 55199 + }, + { + "epoch": 17.05, + "learning_rate": 1.121352902260594e-06, + "loss": 0.0019, + "step": 55200 + }, + { + "epoch": 17.05, + "learning_rate": 1.1211228066606962e-06, + "loss": 0.0012, + "step": 55201 + }, + { + "epoch": 17.05, + "learning_rate": 1.120892733268486e-06, + "loss": 0.0016, + "step": 55202 + }, + { + "epoch": 17.05, + "learning_rate": 1.1206626820845456e-06, + "loss": 0.0017, + "step": 55203 + }, + { + "epoch": 17.05, + "learning_rate": 1.1204326531094456e-06, + "loss": 0.0011, + "step": 55204 + }, + { + "epoch": 17.05, + "learning_rate": 1.1202026463437621e-06, + "loss": 0.0015, + "step": 55205 + }, + { + "epoch": 17.05, + "learning_rate": 1.1199726617880758e-06, + "loss": 0.0016, + "step": 55206 + }, + { + "epoch": 17.05, + "learning_rate": 1.1197426994429538e-06, + "loss": 0.0019, + "step": 55207 + }, + { + "epoch": 17.05, + "learning_rate": 1.119512759308975e-06, + "loss": 0.0016, + "step": 55208 + }, + { + "epoch": 17.05, + "learning_rate": 1.1192828413867162e-06, + "loss": 0.0014, + "step": 55209 + }, + { + "epoch": 17.05, + "learning_rate": 1.1190529456767485e-06, + "loss": 0.0014, + "step": 55210 + }, + { + "epoch": 17.05, + "learning_rate": 1.118823072179651e-06, + "loss": 0.0021, + "step": 55211 + }, + { + "epoch": 17.05, + "learning_rate": 1.1185932208959982e-06, + "loss": 0.0019, + "step": 55212 + }, + { + "epoch": 17.05, + "learning_rate": 1.1183633918263603e-06, + "loss": 0.0019, + "step": 55213 + }, + { + "epoch": 17.05, + "learning_rate": 1.118133584971316e-06, + "loss": 0.0017, + "step": 55214 + }, + { + "epoch": 17.05, + "learning_rate": 1.1179038003314414e-06, + "loss": 0.0015, + "step": 55215 + }, + { + "epoch": 17.05, + "learning_rate": 1.1176740379073091e-06, + "loss": 0.002, + "step": 55216 + }, + { + "epoch": 17.05, + "learning_rate": 1.1174442976994927e-06, + "loss": 0.0018, + "step": 55217 + }, + { + "epoch": 17.05, + "learning_rate": 1.1172145797085699e-06, + "loss": 0.0015, + "step": 55218 + }, + { + "epoch": 17.05, + "learning_rate": 1.1169848839351116e-06, + "loss": 0.0021, + "step": 55219 + }, + { + "epoch": 17.05, + "learning_rate": 1.1167552103796942e-06, + "loss": 0.0014, + "step": 55220 + }, + { + "epoch": 17.05, + "learning_rate": 1.1165255590428936e-06, + "loss": 0.0019, + "step": 55221 + }, + { + "epoch": 17.05, + "learning_rate": 1.116295929925284e-06, + "loss": 0.0016, + "step": 55222 + }, + { + "epoch": 17.05, + "learning_rate": 1.116066323027436e-06, + "loss": 0.0017, + "step": 55223 + }, + { + "epoch": 17.05, + "learning_rate": 1.1158367383499259e-06, + "loss": 0.0022, + "step": 55224 + }, + { + "epoch": 17.05, + "learning_rate": 1.1156071758933308e-06, + "loss": 0.0014, + "step": 55225 + }, + { + "epoch": 17.05, + "learning_rate": 1.1153776356582236e-06, + "loss": 0.0017, + "step": 55226 + }, + { + "epoch": 17.06, + "learning_rate": 1.1151481176451739e-06, + "loss": 0.0013, + "step": 55227 + }, + { + "epoch": 17.06, + "learning_rate": 1.1149186218547626e-06, + "loss": 0.0015, + "step": 55228 + }, + { + "epoch": 17.06, + "learning_rate": 1.1146891482875576e-06, + "loss": 0.0013, + "step": 55229 + }, + { + "epoch": 17.06, + "learning_rate": 1.1144596969441357e-06, + "loss": 0.0012, + "step": 55230 + }, + { + "epoch": 17.06, + "learning_rate": 1.1142302678250726e-06, + "loss": 0.0027, + "step": 55231 + }, + { + "epoch": 17.06, + "learning_rate": 1.1140008609309404e-06, + "loss": 0.0011, + "step": 55232 + }, + { + "epoch": 17.06, + "learning_rate": 1.1137714762623108e-06, + "loss": 0.0016, + "step": 55233 + }, + { + "epoch": 17.06, + "learning_rate": 1.113542113819761e-06, + "loss": 0.0019, + "step": 55234 + }, + { + "epoch": 17.06, + "learning_rate": 1.1133127736038617e-06, + "loss": 0.0016, + "step": 55235 + }, + { + "epoch": 17.06, + "learning_rate": 1.1130834556151882e-06, + "loss": 0.0016, + "step": 55236 + }, + { + "epoch": 17.06, + "learning_rate": 1.1128541598543174e-06, + "loss": 0.0013, + "step": 55237 + }, + { + "epoch": 17.06, + "learning_rate": 1.1126248863218147e-06, + "loss": 0.0014, + "step": 55238 + }, + { + "epoch": 17.06, + "learning_rate": 1.1123956350182596e-06, + "loss": 0.0015, + "step": 55239 + }, + { + "epoch": 17.06, + "learning_rate": 1.112166405944225e-06, + "loss": 0.0013, + "step": 55240 + }, + { + "epoch": 17.06, + "learning_rate": 1.1119371991002813e-06, + "loss": 0.0016, + "step": 55241 + }, + { + "epoch": 17.06, + "learning_rate": 1.1117080144870062e-06, + "loss": 0.0015, + "step": 55242 + }, + { + "epoch": 17.06, + "learning_rate": 1.1114788521049703e-06, + "loss": 0.0019, + "step": 55243 + }, + { + "epoch": 17.06, + "learning_rate": 1.111249711954745e-06, + "loss": 0.002, + "step": 55244 + }, + { + "epoch": 17.06, + "learning_rate": 1.1110205940369046e-06, + "loss": 0.002, + "step": 55245 + }, + { + "epoch": 17.06, + "learning_rate": 1.110791498352025e-06, + "loss": 0.0018, + "step": 55246 + }, + { + "epoch": 17.06, + "learning_rate": 1.1105624249006786e-06, + "loss": 0.0014, + "step": 55247 + }, + { + "epoch": 17.06, + "learning_rate": 1.1103333736834343e-06, + "loss": 0.0016, + "step": 55248 + }, + { + "epoch": 17.06, + "learning_rate": 1.1101043447008686e-06, + "loss": 0.0018, + "step": 55249 + }, + { + "epoch": 17.06, + "learning_rate": 1.1098753379535522e-06, + "loss": 0.0017, + "step": 55250 + }, + { + "epoch": 17.06, + "learning_rate": 1.1096463534420587e-06, + "loss": 0.0014, + "step": 55251 + }, + { + "epoch": 17.06, + "learning_rate": 1.1094173911669637e-06, + "loss": 0.0027, + "step": 55252 + }, + { + "epoch": 17.06, + "learning_rate": 1.1091884511288376e-06, + "loss": 0.0019, + "step": 55253 + }, + { + "epoch": 17.06, + "learning_rate": 1.10895953332825e-06, + "loss": 0.0015, + "step": 55254 + }, + { + "epoch": 17.06, + "learning_rate": 1.108730637765778e-06, + "loss": 0.0016, + "step": 55255 + }, + { + "epoch": 17.06, + "learning_rate": 1.1085017644419904e-06, + "loss": 0.0021, + "step": 55256 + }, + { + "epoch": 17.06, + "learning_rate": 1.1082729133574644e-06, + "loss": 0.0016, + "step": 55257 + }, + { + "epoch": 17.06, + "learning_rate": 1.1080440845127671e-06, + "loss": 0.002, + "step": 55258 + }, + { + "epoch": 17.06, + "learning_rate": 1.1078152779084761e-06, + "loss": 0.0015, + "step": 55259 + }, + { + "epoch": 17.07, + "learning_rate": 1.1075864935451574e-06, + "loss": 0.0017, + "step": 55260 + }, + { + "epoch": 17.07, + "learning_rate": 1.1073577314233874e-06, + "loss": 0.0019, + "step": 55261 + }, + { + "epoch": 17.07, + "learning_rate": 1.10712899154374e-06, + "loss": 0.0024, + "step": 55262 + }, + { + "epoch": 17.07, + "learning_rate": 1.1069002739067847e-06, + "loss": 0.0026, + "step": 55263 + }, + { + "epoch": 17.07, + "learning_rate": 1.106671578513092e-06, + "loss": 0.002, + "step": 55264 + }, + { + "epoch": 17.07, + "learning_rate": 1.1064429053632376e-06, + "loss": 0.0029, + "step": 55265 + }, + { + "epoch": 17.07, + "learning_rate": 1.1062142544577903e-06, + "loss": 0.0017, + "step": 55266 + }, + { + "epoch": 17.07, + "learning_rate": 1.1059856257973245e-06, + "loss": 0.0017, + "step": 55267 + }, + { + "epoch": 17.07, + "learning_rate": 1.1057570193824107e-06, + "loss": 0.0024, + "step": 55268 + }, + { + "epoch": 17.07, + "learning_rate": 1.1055284352136187e-06, + "loss": 0.0018, + "step": 55269 + }, + { + "epoch": 17.07, + "learning_rate": 1.1052998732915222e-06, + "loss": 0.0016, + "step": 55270 + }, + { + "epoch": 17.07, + "learning_rate": 1.1050713336166962e-06, + "loss": 0.0017, + "step": 55271 + }, + { + "epoch": 17.07, + "learning_rate": 1.1048428161897062e-06, + "loss": 0.0015, + "step": 55272 + }, + { + "epoch": 17.07, + "learning_rate": 1.1046143210111283e-06, + "loss": 0.0015, + "step": 55273 + }, + { + "epoch": 17.07, + "learning_rate": 1.1043858480815327e-06, + "loss": 0.0014, + "step": 55274 + }, + { + "epoch": 17.07, + "learning_rate": 1.1041573974014897e-06, + "loss": 0.0023, + "step": 55275 + }, + { + "epoch": 17.07, + "learning_rate": 1.1039289689715705e-06, + "loss": 0.0018, + "step": 55276 + }, + { + "epoch": 17.07, + "learning_rate": 1.1037005627923492e-06, + "loss": 0.0014, + "step": 55277 + }, + { + "epoch": 17.07, + "learning_rate": 1.1034721788643965e-06, + "loss": 0.0014, + "step": 55278 + }, + { + "epoch": 17.07, + "learning_rate": 1.1032438171882799e-06, + "loss": 0.0021, + "step": 55279 + }, + { + "epoch": 17.07, + "learning_rate": 1.103015477764574e-06, + "loss": 0.0018, + "step": 55280 + }, + { + "epoch": 17.07, + "learning_rate": 1.102787160593849e-06, + "loss": 0.0013, + "step": 55281 + }, + { + "epoch": 17.07, + "learning_rate": 1.102558865676675e-06, + "loss": 0.0013, + "step": 55282 + }, + { + "epoch": 17.07, + "learning_rate": 1.1023305930136264e-06, + "loss": 0.0019, + "step": 55283 + }, + { + "epoch": 17.07, + "learning_rate": 1.1021023426052713e-06, + "loss": 0.0012, + "step": 55284 + }, + { + "epoch": 17.07, + "learning_rate": 1.1018741144521793e-06, + "loss": 0.0017, + "step": 55285 + }, + { + "epoch": 17.07, + "learning_rate": 1.1016459085549259e-06, + "loss": 0.0016, + "step": 55286 + }, + { + "epoch": 17.07, + "learning_rate": 1.1014177249140767e-06, + "loss": 0.0015, + "step": 55287 + }, + { + "epoch": 17.07, + "learning_rate": 1.101189563530206e-06, + "loss": 0.0018, + "step": 55288 + }, + { + "epoch": 17.07, + "learning_rate": 1.1009614244038824e-06, + "loss": 0.0024, + "step": 55289 + }, + { + "epoch": 17.07, + "learning_rate": 1.1007333075356786e-06, + "loss": 0.0017, + "step": 55290 + }, + { + "epoch": 17.07, + "learning_rate": 1.1005052129261616e-06, + "loss": 0.0018, + "step": 55291 + }, + { + "epoch": 17.08, + "learning_rate": 1.1002771405759049e-06, + "loss": 0.0014, + "step": 55292 + }, + { + "epoch": 17.08, + "learning_rate": 1.10004909048548e-06, + "loss": 0.0014, + "step": 55293 + }, + { + "epoch": 17.08, + "learning_rate": 1.0998210626554561e-06, + "loss": 0.0017, + "step": 55294 + }, + { + "epoch": 17.08, + "learning_rate": 1.0995930570864e-06, + "loss": 0.0016, + "step": 55295 + }, + { + "epoch": 17.08, + "learning_rate": 1.0993650737788875e-06, + "loss": 0.0019, + "step": 55296 + }, + { + "epoch": 17.08, + "learning_rate": 1.099137112733485e-06, + "loss": 0.0021, + "step": 55297 + }, + { + "epoch": 17.08, + "learning_rate": 1.0989091739507652e-06, + "loss": 0.0022, + "step": 55298 + }, + { + "epoch": 17.08, + "learning_rate": 1.0986812574312965e-06, + "loss": 0.0016, + "step": 55299 + }, + { + "epoch": 17.08, + "learning_rate": 1.0984533631756489e-06, + "loss": 0.0017, + "step": 55300 + }, + { + "epoch": 17.08, + "learning_rate": 1.0982254911843927e-06, + "loss": 0.0015, + "step": 55301 + }, + { + "epoch": 17.08, + "learning_rate": 1.0979976414580995e-06, + "loss": 0.0019, + "step": 55302 + }, + { + "epoch": 17.08, + "learning_rate": 1.0977698139973357e-06, + "loss": 0.0017, + "step": 55303 + }, + { + "epoch": 17.08, + "learning_rate": 1.0975420088026755e-06, + "loss": 0.0014, + "step": 55304 + }, + { + "epoch": 17.08, + "learning_rate": 1.0973142258746861e-06, + "loss": 0.0018, + "step": 55305 + }, + { + "epoch": 17.08, + "learning_rate": 1.0970864652139368e-06, + "loss": 0.0015, + "step": 55306 + }, + { + "epoch": 17.08, + "learning_rate": 1.0968587268209962e-06, + "loss": 0.0016, + "step": 55307 + }, + { + "epoch": 17.08, + "learning_rate": 1.0966310106964394e-06, + "loss": 0.0019, + "step": 55308 + }, + { + "epoch": 17.08, + "learning_rate": 1.0964033168408318e-06, + "loss": 0.0016, + "step": 55309 + }, + { + "epoch": 17.08, + "learning_rate": 1.0961756452547412e-06, + "loss": 0.0016, + "step": 55310 + }, + { + "epoch": 17.08, + "learning_rate": 1.0959479959387409e-06, + "loss": 0.0011, + "step": 55311 + }, + { + "epoch": 17.08, + "learning_rate": 1.0957203688933971e-06, + "loss": 0.0015, + "step": 55312 + }, + { + "epoch": 17.08, + "learning_rate": 1.0954927641192814e-06, + "loss": 0.0013, + "step": 55313 + }, + { + "epoch": 17.08, + "learning_rate": 1.0952651816169635e-06, + "loss": 0.002, + "step": 55314 + }, + { + "epoch": 17.08, + "learning_rate": 1.0950376213870118e-06, + "loss": 0.0019, + "step": 55315 + }, + { + "epoch": 17.08, + "learning_rate": 1.0948100834299924e-06, + "loss": 0.0018, + "step": 55316 + }, + { + "epoch": 17.08, + "learning_rate": 1.0945825677464804e-06, + "loss": 0.0017, + "step": 55317 + }, + { + "epoch": 17.08, + "learning_rate": 1.094355074337039e-06, + "loss": 0.0015, + "step": 55318 + }, + { + "epoch": 17.08, + "learning_rate": 1.094127603202242e-06, + "loss": 0.0015, + "step": 55319 + }, + { + "epoch": 17.08, + "learning_rate": 1.0939001543426563e-06, + "loss": 0.0017, + "step": 55320 + }, + { + "epoch": 17.08, + "learning_rate": 1.0936727277588488e-06, + "loss": 0.0014, + "step": 55321 + }, + { + "epoch": 17.08, + "learning_rate": 1.0934453234513897e-06, + "loss": 0.0012, + "step": 55322 + }, + { + "epoch": 17.08, + "learning_rate": 1.0932179414208489e-06, + "loss": 0.001, + "step": 55323 + }, + { + "epoch": 17.09, + "learning_rate": 1.0929905816677955e-06, + "loss": 0.0023, + "step": 55324 + }, + { + "epoch": 17.09, + "learning_rate": 1.0927632441927983e-06, + "loss": 0.0022, + "step": 55325 + }, + { + "epoch": 17.09, + "learning_rate": 1.092535928996422e-06, + "loss": 0.0014, + "step": 55326 + }, + { + "epoch": 17.09, + "learning_rate": 1.09230863607924e-06, + "loss": 0.0017, + "step": 55327 + }, + { + "epoch": 17.09, + "learning_rate": 1.0920813654418172e-06, + "loss": 0.0026, + "step": 55328 + }, + { + "epoch": 17.09, + "learning_rate": 1.0918541170847264e-06, + "loss": 0.0013, + "step": 55329 + }, + { + "epoch": 17.09, + "learning_rate": 1.0916268910085314e-06, + "loss": 0.0021, + "step": 55330 + }, + { + "epoch": 17.09, + "learning_rate": 1.0913996872138011e-06, + "loss": 0.0013, + "step": 55331 + }, + { + "epoch": 17.09, + "learning_rate": 1.0911725057011058e-06, + "loss": 0.002, + "step": 55332 + }, + { + "epoch": 17.09, + "learning_rate": 1.090945346471014e-06, + "loss": 0.002, + "step": 55333 + }, + { + "epoch": 17.09, + "learning_rate": 1.090718209524091e-06, + "loss": 0.0019, + "step": 55334 + }, + { + "epoch": 17.09, + "learning_rate": 1.0904910948609093e-06, + "loss": 0.0018, + "step": 55335 + }, + { + "epoch": 17.09, + "learning_rate": 1.0902640024820331e-06, + "loss": 0.0019, + "step": 55336 + }, + { + "epoch": 17.09, + "learning_rate": 1.0900369323880312e-06, + "loss": 0.0015, + "step": 55337 + }, + { + "epoch": 17.09, + "learning_rate": 1.0898098845794713e-06, + "loss": 0.0017, + "step": 55338 + }, + { + "epoch": 17.09, + "learning_rate": 1.0895828590569235e-06, + "loss": 0.0026, + "step": 55339 + }, + { + "epoch": 17.09, + "learning_rate": 1.0893558558209549e-06, + "loss": 0.0014, + "step": 55340 + }, + { + "epoch": 17.09, + "learning_rate": 1.0891288748721297e-06, + "loss": 0.0019, + "step": 55341 + }, + { + "epoch": 17.09, + "learning_rate": 1.0889019162110216e-06, + "loss": 0.0012, + "step": 55342 + }, + { + "epoch": 17.09, + "learning_rate": 1.0886749798381912e-06, + "loss": 0.0022, + "step": 55343 + }, + { + "epoch": 17.09, + "learning_rate": 1.088448065754212e-06, + "loss": 0.0018, + "step": 55344 + }, + { + "epoch": 17.09, + "learning_rate": 1.0882211739596526e-06, + "loss": 0.0019, + "step": 55345 + }, + { + "epoch": 17.09, + "learning_rate": 1.0879943044550734e-06, + "loss": 0.0016, + "step": 55346 + }, + { + "epoch": 17.09, + "learning_rate": 1.0877674572410457e-06, + "loss": 0.0016, + "step": 55347 + }, + { + "epoch": 17.09, + "learning_rate": 1.0875406323181403e-06, + "loss": 0.0017, + "step": 55348 + }, + { + "epoch": 17.09, + "learning_rate": 1.087313829686918e-06, + "loss": 0.0017, + "step": 55349 + }, + { + "epoch": 17.09, + "learning_rate": 1.0870870493479513e-06, + "loss": 0.0018, + "step": 55350 + }, + { + "epoch": 17.09, + "learning_rate": 1.0868602913018067e-06, + "loss": 0.0014, + "step": 55351 + }, + { + "epoch": 17.09, + "learning_rate": 1.0866335555490471e-06, + "loss": 0.0026, + "step": 55352 + }, + { + "epoch": 17.09, + "learning_rate": 1.086406842090243e-06, + "loss": 0.0019, + "step": 55353 + }, + { + "epoch": 17.09, + "learning_rate": 1.0861801509259617e-06, + "loss": 0.0021, + "step": 55354 + }, + { + "epoch": 17.09, + "learning_rate": 1.085953482056773e-06, + "loss": 0.0014, + "step": 55355 + }, + { + "epoch": 17.09, + "learning_rate": 1.0857268354832362e-06, + "loss": 0.0018, + "step": 55356 + }, + { + "epoch": 17.1, + "learning_rate": 1.0855002112059233e-06, + "loss": 0.0016, + "step": 55357 + }, + { + "epoch": 17.1, + "learning_rate": 1.0852736092254013e-06, + "loss": 0.0013, + "step": 55358 + }, + { + "epoch": 17.1, + "learning_rate": 1.0850470295422343e-06, + "loss": 0.0012, + "step": 55359 + }, + { + "epoch": 17.1, + "learning_rate": 1.0848204721569932e-06, + "loss": 0.0014, + "step": 55360 + }, + { + "epoch": 17.1, + "learning_rate": 1.0845939370702418e-06, + "loss": 0.0018, + "step": 55361 + }, + { + "epoch": 17.1, + "learning_rate": 1.0843674242825454e-06, + "loss": 0.0022, + "step": 55362 + }, + { + "epoch": 17.1, + "learning_rate": 1.0841409337944719e-06, + "loss": 0.0016, + "step": 55363 + }, + { + "epoch": 17.1, + "learning_rate": 1.0839144656065893e-06, + "loss": 0.0015, + "step": 55364 + }, + { + "epoch": 17.1, + "learning_rate": 1.0836880197194632e-06, + "loss": 0.0019, + "step": 55365 + }, + { + "epoch": 17.1, + "learning_rate": 1.083461596133658e-06, + "loss": 0.0013, + "step": 55366 + }, + { + "epoch": 17.1, + "learning_rate": 1.0832351948497443e-06, + "loss": 0.0019, + "step": 55367 + }, + { + "epoch": 17.1, + "learning_rate": 1.0830088158682828e-06, + "loss": 0.0016, + "step": 55368 + }, + { + "epoch": 17.1, + "learning_rate": 1.0827824591898428e-06, + "loss": 0.0014, + "step": 55369 + }, + { + "epoch": 17.1, + "learning_rate": 1.082556124814992e-06, + "loss": 0.0018, + "step": 55370 + }, + { + "epoch": 17.1, + "learning_rate": 1.082329812744295e-06, + "loss": 0.0016, + "step": 55371 + }, + { + "epoch": 17.1, + "learning_rate": 1.082103522978315e-06, + "loss": 0.0022, + "step": 55372 + }, + { + "epoch": 17.1, + "learning_rate": 1.0818772555176239e-06, + "loss": 0.0014, + "step": 55373 + }, + { + "epoch": 17.1, + "learning_rate": 1.081651010362781e-06, + "loss": 0.0014, + "step": 55374 + }, + { + "epoch": 17.1, + "learning_rate": 1.081424787514358e-06, + "loss": 0.0015, + "step": 55375 + }, + { + "epoch": 17.1, + "learning_rate": 1.081198586972919e-06, + "loss": 0.0016, + "step": 55376 + }, + { + "epoch": 17.1, + "learning_rate": 1.080972408739026e-06, + "loss": 0.0018, + "step": 55377 + }, + { + "epoch": 17.1, + "learning_rate": 1.0807462528132483e-06, + "loss": 0.0023, + "step": 55378 + }, + { + "epoch": 17.1, + "learning_rate": 1.0805201191961524e-06, + "loss": 0.0015, + "step": 55379 + }, + { + "epoch": 17.1, + "learning_rate": 1.0802940078883017e-06, + "loss": 0.0013, + "step": 55380 + }, + { + "epoch": 17.1, + "learning_rate": 1.0800679188902629e-06, + "loss": 0.0012, + "step": 55381 + }, + { + "epoch": 17.1, + "learning_rate": 1.0798418522026022e-06, + "loss": 0.0016, + "step": 55382 + }, + { + "epoch": 17.1, + "learning_rate": 1.0796158078258822e-06, + "loss": 0.0012, + "step": 55383 + }, + { + "epoch": 17.1, + "learning_rate": 1.0793897857606694e-06, + "loss": 0.0016, + "step": 55384 + }, + { + "epoch": 17.1, + "learning_rate": 1.0791637860075321e-06, + "loss": 0.0011, + "step": 55385 + }, + { + "epoch": 17.1, + "learning_rate": 1.0789378085670332e-06, + "loss": 0.0022, + "step": 55386 + }, + { + "epoch": 17.1, + "learning_rate": 1.0787118534397355e-06, + "loss": 0.0019, + "step": 55387 + }, + { + "epoch": 17.1, + "learning_rate": 1.0784859206262067e-06, + "loss": 0.0011, + "step": 55388 + }, + { + "epoch": 17.11, + "learning_rate": 1.0782600101270146e-06, + "loss": 0.0015, + "step": 55389 + }, + { + "epoch": 17.11, + "learning_rate": 1.0780341219427181e-06, + "loss": 0.0018, + "step": 55390 + }, + { + "epoch": 17.11, + "learning_rate": 1.077808256073889e-06, + "loss": 0.002, + "step": 55391 + }, + { + "epoch": 17.11, + "learning_rate": 1.0775824125210877e-06, + "loss": 0.0018, + "step": 55392 + }, + { + "epoch": 17.11, + "learning_rate": 1.0773565912848782e-06, + "loss": 0.0019, + "step": 55393 + }, + { + "epoch": 17.11, + "learning_rate": 1.0771307923658282e-06, + "loss": 0.0018, + "step": 55394 + }, + { + "epoch": 17.11, + "learning_rate": 1.0769050157645022e-06, + "loss": 0.002, + "step": 55395 + }, + { + "epoch": 17.11, + "learning_rate": 1.0766792614814648e-06, + "loss": 0.0039, + "step": 55396 + }, + { + "epoch": 17.11, + "learning_rate": 1.0764535295172784e-06, + "loss": 0.0012, + "step": 55397 + }, + { + "epoch": 17.11, + "learning_rate": 1.0762278198725119e-06, + "loss": 0.0016, + "step": 55398 + }, + { + "epoch": 17.11, + "learning_rate": 1.0760021325477233e-06, + "loss": 0.0014, + "step": 55399 + }, + { + "epoch": 17.11, + "learning_rate": 1.0757764675434824e-06, + "loss": 0.0015, + "step": 55400 + }, + { + "epoch": 17.11, + "learning_rate": 1.075550824860354e-06, + "loss": 0.0015, + "step": 55401 + }, + { + "epoch": 17.11, + "learning_rate": 1.0753252044989003e-06, + "loss": 0.0024, + "step": 55402 + }, + { + "epoch": 17.11, + "learning_rate": 1.075099606459684e-06, + "loss": 0.0023, + "step": 55403 + }, + { + "epoch": 17.11, + "learning_rate": 1.0748740307432747e-06, + "loss": 0.0021, + "step": 55404 + }, + { + "epoch": 17.11, + "learning_rate": 1.0746484773502297e-06, + "loss": 0.0014, + "step": 55405 + }, + { + "epoch": 17.11, + "learning_rate": 1.0744229462811195e-06, + "loss": 0.0018, + "step": 55406 + }, + { + "epoch": 17.11, + "learning_rate": 1.0741974375365049e-06, + "loss": 0.002, + "step": 55407 + }, + { + "epoch": 17.11, + "learning_rate": 1.0739719511169488e-06, + "loss": 0.0014, + "step": 55408 + }, + { + "epoch": 17.11, + "learning_rate": 1.0737464870230174e-06, + "loss": 0.0016, + "step": 55409 + }, + { + "epoch": 17.11, + "learning_rate": 1.0735210452552758e-06, + "loss": 0.0025, + "step": 55410 + }, + { + "epoch": 17.11, + "learning_rate": 1.0732956258142836e-06, + "loss": 0.0015, + "step": 55411 + }, + { + "epoch": 17.11, + "learning_rate": 1.0730702287006101e-06, + "loss": 0.0019, + "step": 55412 + }, + { + "epoch": 17.11, + "learning_rate": 1.0728448539148152e-06, + "loss": 0.0016, + "step": 55413 + }, + { + "epoch": 17.11, + "learning_rate": 1.0726195014574613e-06, + "loss": 0.0018, + "step": 55414 + }, + { + "epoch": 17.11, + "learning_rate": 1.0723941713291153e-06, + "loss": 0.0022, + "step": 55415 + }, + { + "epoch": 17.11, + "learning_rate": 1.0721688635303406e-06, + "loss": 0.0024, + "step": 55416 + }, + { + "epoch": 17.11, + "learning_rate": 1.0719435780617016e-06, + "loss": 0.0016, + "step": 55417 + }, + { + "epoch": 17.11, + "learning_rate": 1.0717183149237565e-06, + "loss": 0.0017, + "step": 55418 + }, + { + "epoch": 17.11, + "learning_rate": 1.0714930741170749e-06, + "loss": 0.0017, + "step": 55419 + }, + { + "epoch": 17.11, + "learning_rate": 1.0712678556422163e-06, + "loss": 0.0019, + "step": 55420 + }, + { + "epoch": 17.11, + "learning_rate": 1.0710426594997436e-06, + "loss": 0.0016, + "step": 55421 + }, + { + "epoch": 17.12, + "learning_rate": 1.0708174856902253e-06, + "loss": 0.0022, + "step": 55422 + }, + { + "epoch": 17.12, + "learning_rate": 1.07059233421422e-06, + "loss": 0.0015, + "step": 55423 + }, + { + "epoch": 17.12, + "learning_rate": 1.0703672050722914e-06, + "loss": 0.0019, + "step": 55424 + }, + { + "epoch": 17.12, + "learning_rate": 1.0701420982650012e-06, + "loss": 0.002, + "step": 55425 + }, + { + "epoch": 17.12, + "learning_rate": 1.0699170137929172e-06, + "loss": 0.002, + "step": 55426 + }, + { + "epoch": 17.12, + "learning_rate": 1.0696919516565996e-06, + "loss": 0.0016, + "step": 55427 + }, + { + "epoch": 17.12, + "learning_rate": 1.0694669118566093e-06, + "loss": 0.0017, + "step": 55428 + }, + { + "epoch": 17.12, + "learning_rate": 1.0692418943935122e-06, + "loss": 0.0016, + "step": 55429 + }, + { + "epoch": 17.12, + "learning_rate": 1.0690168992678696e-06, + "loss": 0.0021, + "step": 55430 + }, + { + "epoch": 17.12, + "learning_rate": 1.0687919264802437e-06, + "loss": 0.0016, + "step": 55431 + }, + { + "epoch": 17.12, + "learning_rate": 1.0685669760312001e-06, + "loss": 0.002, + "step": 55432 + }, + { + "epoch": 17.12, + "learning_rate": 1.068342047921299e-06, + "loss": 0.0015, + "step": 55433 + }, + { + "epoch": 17.12, + "learning_rate": 1.0681171421511028e-06, + "loss": 0.0017, + "step": 55434 + }, + { + "epoch": 17.12, + "learning_rate": 1.067892258721176e-06, + "loss": 0.0015, + "step": 55435 + }, + { + "epoch": 17.12, + "learning_rate": 1.0676673976320773e-06, + "loss": 0.0015, + "step": 55436 + }, + { + "epoch": 17.12, + "learning_rate": 1.067442558884374e-06, + "loss": 0.0022, + "step": 55437 + }, + { + "epoch": 17.12, + "learning_rate": 1.0672177424786256e-06, + "loss": 0.0019, + "step": 55438 + }, + { + "epoch": 17.12, + "learning_rate": 1.066992948415394e-06, + "loss": 0.0017, + "step": 55439 + }, + { + "epoch": 17.12, + "learning_rate": 1.066768176695241e-06, + "loss": 0.0018, + "step": 55440 + }, + { + "epoch": 17.12, + "learning_rate": 1.0665434273187325e-06, + "loss": 0.0017, + "step": 55441 + }, + { + "epoch": 17.12, + "learning_rate": 1.0663187002864273e-06, + "loss": 0.0018, + "step": 55442 + }, + { + "epoch": 17.12, + "learning_rate": 1.0660939955988891e-06, + "loss": 0.0013, + "step": 55443 + }, + { + "epoch": 17.12, + "learning_rate": 1.06586931325668e-06, + "loss": 0.0019, + "step": 55444 + }, + { + "epoch": 17.12, + "learning_rate": 1.0656446532603592e-06, + "loss": 0.0017, + "step": 55445 + }, + { + "epoch": 17.12, + "learning_rate": 1.06542001561049e-06, + "loss": 0.0023, + "step": 55446 + }, + { + "epoch": 17.12, + "learning_rate": 1.065195400307637e-06, + "loss": 0.0016, + "step": 55447 + }, + { + "epoch": 17.12, + "learning_rate": 1.0649708073523613e-06, + "loss": 0.0011, + "step": 55448 + }, + { + "epoch": 17.12, + "learning_rate": 1.06474623674522e-06, + "loss": 0.0015, + "step": 55449 + }, + { + "epoch": 17.12, + "learning_rate": 1.0645216884867803e-06, + "loss": 0.0015, + "step": 55450 + }, + { + "epoch": 17.12, + "learning_rate": 1.0642971625775988e-06, + "loss": 0.0019, + "step": 55451 + }, + { + "epoch": 17.12, + "learning_rate": 1.0640726590182416e-06, + "loss": 0.0015, + "step": 55452 + }, + { + "epoch": 17.12, + "learning_rate": 1.063848177809269e-06, + "loss": 0.0019, + "step": 55453 + }, + { + "epoch": 17.13, + "learning_rate": 1.063623718951242e-06, + "loss": 0.0019, + "step": 55454 + }, + { + "epoch": 17.13, + "learning_rate": 1.0633992824447202e-06, + "loss": 0.0014, + "step": 55455 + }, + { + "epoch": 17.13, + "learning_rate": 1.0631748682902675e-06, + "loss": 0.0015, + "step": 55456 + }, + { + "epoch": 17.13, + "learning_rate": 1.0629504764884457e-06, + "loss": 0.0017, + "step": 55457 + }, + { + "epoch": 17.13, + "learning_rate": 1.0627261070398154e-06, + "loss": 0.0016, + "step": 55458 + }, + { + "epoch": 17.13, + "learning_rate": 1.062501759944935e-06, + "loss": 0.0017, + "step": 55459 + }, + { + "epoch": 17.13, + "learning_rate": 1.0622774352043697e-06, + "loss": 0.0015, + "step": 55460 + }, + { + "epoch": 17.13, + "learning_rate": 1.0620531328186755e-06, + "loss": 0.0018, + "step": 55461 + }, + { + "epoch": 17.13, + "learning_rate": 1.061828852788418e-06, + "loss": 0.0018, + "step": 55462 + }, + { + "epoch": 17.13, + "learning_rate": 1.0616045951141607e-06, + "loss": 0.0016, + "step": 55463 + }, + { + "epoch": 17.13, + "learning_rate": 1.0613803597964557e-06, + "loss": 0.0016, + "step": 55464 + }, + { + "epoch": 17.13, + "learning_rate": 1.06115614683587e-06, + "loss": 0.0026, + "step": 55465 + }, + { + "epoch": 17.13, + "learning_rate": 1.0609319562329645e-06, + "loss": 0.0021, + "step": 55466 + }, + { + "epoch": 17.13, + "learning_rate": 1.0607077879882954e-06, + "loss": 0.0012, + "step": 55467 + }, + { + "epoch": 17.13, + "learning_rate": 1.06048364210243e-06, + "loss": 0.0015, + "step": 55468 + }, + { + "epoch": 17.13, + "learning_rate": 1.0602595185759256e-06, + "loss": 0.0015, + "step": 55469 + }, + { + "epoch": 17.13, + "learning_rate": 1.0600354174093397e-06, + "loss": 0.0021, + "step": 55470 + }, + { + "epoch": 17.13, + "learning_rate": 1.059811338603236e-06, + "loss": 0.0019, + "step": 55471 + }, + { + "epoch": 17.13, + "learning_rate": 1.0595872821581777e-06, + "loss": 0.0015, + "step": 55472 + }, + { + "epoch": 17.13, + "learning_rate": 1.0593632480747206e-06, + "loss": 0.0015, + "step": 55473 + }, + { + "epoch": 17.13, + "learning_rate": 1.059139236353426e-06, + "loss": 0.0021, + "step": 55474 + }, + { + "epoch": 17.13, + "learning_rate": 1.058915246994856e-06, + "loss": 0.0018, + "step": 55475 + }, + { + "epoch": 17.13, + "learning_rate": 1.0586912799995685e-06, + "loss": 0.0022, + "step": 55476 + }, + { + "epoch": 17.13, + "learning_rate": 1.058467335368124e-06, + "loss": 0.002, + "step": 55477 + }, + { + "epoch": 17.13, + "learning_rate": 1.0582434131010865e-06, + "loss": 0.0018, + "step": 55478 + }, + { + "epoch": 17.13, + "learning_rate": 1.0580195131990123e-06, + "loss": 0.0021, + "step": 55479 + }, + { + "epoch": 17.13, + "learning_rate": 1.0577956356624609e-06, + "loss": 0.0017, + "step": 55480 + }, + { + "epoch": 17.13, + "learning_rate": 1.057571780491995e-06, + "loss": 0.0019, + "step": 55481 + }, + { + "epoch": 17.13, + "learning_rate": 1.0573479476881721e-06, + "loss": 0.0017, + "step": 55482 + }, + { + "epoch": 17.13, + "learning_rate": 1.057124137251554e-06, + "loss": 0.002, + "step": 55483 + }, + { + "epoch": 17.13, + "learning_rate": 1.0569003491827e-06, + "loss": 0.0013, + "step": 55484 + }, + { + "epoch": 17.13, + "learning_rate": 1.0566765834821668e-06, + "loss": 0.0022, + "step": 55485 + }, + { + "epoch": 17.14, + "learning_rate": 1.056452840150517e-06, + "loss": 0.0022, + "step": 55486 + }, + { + "epoch": 17.14, + "learning_rate": 1.05622911918831e-06, + "loss": 0.0017, + "step": 55487 + }, + { + "epoch": 17.14, + "learning_rate": 1.0560054205961067e-06, + "loss": 0.0019, + "step": 55488 + }, + { + "epoch": 17.14, + "learning_rate": 1.0557817443744656e-06, + "loss": 0.0016, + "step": 55489 + }, + { + "epoch": 17.14, + "learning_rate": 1.0555580905239438e-06, + "loss": 0.0015, + "step": 55490 + }, + { + "epoch": 17.14, + "learning_rate": 1.0553344590451043e-06, + "loss": 0.0017, + "step": 55491 + }, + { + "epoch": 17.14, + "learning_rate": 1.055110849938502e-06, + "loss": 0.0015, + "step": 55492 + }, + { + "epoch": 17.14, + "learning_rate": 1.0548872632047002e-06, + "loss": 0.0017, + "step": 55493 + }, + { + "epoch": 17.14, + "learning_rate": 1.0546636988442594e-06, + "loss": 0.0018, + "step": 55494 + }, + { + "epoch": 17.14, + "learning_rate": 1.0544401568577333e-06, + "loss": 0.0021, + "step": 55495 + }, + { + "epoch": 17.14, + "learning_rate": 1.0542166372456841e-06, + "loss": 0.0015, + "step": 55496 + }, + { + "epoch": 17.14, + "learning_rate": 1.0539931400086722e-06, + "loss": 0.0014, + "step": 55497 + }, + { + "epoch": 17.14, + "learning_rate": 1.0537696651472528e-06, + "loss": 0.0016, + "step": 55498 + }, + { + "epoch": 17.14, + "learning_rate": 1.05354621266199e-06, + "loss": 0.0012, + "step": 55499 + }, + { + "epoch": 17.14, + "learning_rate": 1.0533227825534399e-06, + "loss": 0.0013, + "step": 55500 + }, + { + "epoch": 17.14, + "learning_rate": 1.0530993748221585e-06, + "loss": 0.0017, + "step": 55501 + }, + { + "epoch": 17.14, + "learning_rate": 1.052875989468708e-06, + "loss": 0.0014, + "step": 55502 + }, + { + "epoch": 17.14, + "learning_rate": 1.0526526264936476e-06, + "loss": 0.0012, + "step": 55503 + }, + { + "epoch": 17.14, + "learning_rate": 1.052429285897536e-06, + "loss": 0.0023, + "step": 55504 + }, + { + "epoch": 17.14, + "learning_rate": 1.052205967680928e-06, + "loss": 0.0015, + "step": 55505 + }, + { + "epoch": 17.14, + "learning_rate": 1.051982671844387e-06, + "loss": 0.0021, + "step": 55506 + }, + { + "epoch": 17.14, + "learning_rate": 1.0517593983884677e-06, + "loss": 0.0015, + "step": 55507 + }, + { + "epoch": 17.14, + "learning_rate": 1.0515361473137297e-06, + "loss": 0.0014, + "step": 55508 + }, + { + "epoch": 17.14, + "learning_rate": 1.0513129186207338e-06, + "loss": 0.0014, + "step": 55509 + }, + { + "epoch": 17.14, + "learning_rate": 1.051089712310036e-06, + "loss": 0.0017, + "step": 55510 + }, + { + "epoch": 17.14, + "learning_rate": 1.0508665283821939e-06, + "loss": 0.0013, + "step": 55511 + }, + { + "epoch": 17.14, + "learning_rate": 1.050643366837769e-06, + "loss": 0.0025, + "step": 55512 + }, + { + "epoch": 17.14, + "learning_rate": 1.0504202276773146e-06, + "loss": 0.0018, + "step": 55513 + }, + { + "epoch": 17.14, + "learning_rate": 1.0501971109013943e-06, + "loss": 0.0024, + "step": 55514 + }, + { + "epoch": 17.14, + "learning_rate": 1.0499740165105632e-06, + "loss": 0.0022, + "step": 55515 + }, + { + "epoch": 17.14, + "learning_rate": 1.0497509445053767e-06, + "loss": 0.0022, + "step": 55516 + }, + { + "epoch": 17.14, + "learning_rate": 1.0495278948863963e-06, + "loss": 0.0018, + "step": 55517 + }, + { + "epoch": 17.14, + "learning_rate": 1.0493048676541784e-06, + "loss": 0.0017, + "step": 55518 + }, + { + "epoch": 17.15, + "learning_rate": 1.0490818628092846e-06, + "loss": 0.002, + "step": 55519 + }, + { + "epoch": 17.15, + "learning_rate": 1.048858880352268e-06, + "loss": 0.0021, + "step": 55520 + }, + { + "epoch": 17.15, + "learning_rate": 1.048635920283687e-06, + "loss": 0.002, + "step": 55521 + }, + { + "epoch": 17.15, + "learning_rate": 1.0484129826041023e-06, + "loss": 0.0014, + "step": 55522 + }, + { + "epoch": 17.15, + "learning_rate": 1.0481900673140678e-06, + "loss": 0.0021, + "step": 55523 + }, + { + "epoch": 17.15, + "learning_rate": 1.047967174414144e-06, + "loss": 0.0018, + "step": 55524 + }, + { + "epoch": 17.15, + "learning_rate": 1.0477443039048862e-06, + "loss": 0.0016, + "step": 55525 + }, + { + "epoch": 17.15, + "learning_rate": 1.0475214557868518e-06, + "loss": 0.0018, + "step": 55526 + }, + { + "epoch": 17.15, + "learning_rate": 1.047298630060599e-06, + "loss": 0.0017, + "step": 55527 + }, + { + "epoch": 17.15, + "learning_rate": 1.0470758267266868e-06, + "loss": 0.0016, + "step": 55528 + }, + { + "epoch": 17.15, + "learning_rate": 1.0468530457856696e-06, + "loss": 0.002, + "step": 55529 + }, + { + "epoch": 17.15, + "learning_rate": 1.0466302872381072e-06, + "loss": 0.0021, + "step": 55530 + }, + { + "epoch": 17.15, + "learning_rate": 1.046407551084555e-06, + "loss": 0.0017, + "step": 55531 + }, + { + "epoch": 17.15, + "learning_rate": 1.04618483732557e-06, + "loss": 0.0022, + "step": 55532 + }, + { + "epoch": 17.15, + "learning_rate": 1.0459621459617087e-06, + "loss": 0.0014, + "step": 55533 + }, + { + "epoch": 17.15, + "learning_rate": 1.0457394769935314e-06, + "loss": 0.0015, + "step": 55534 + }, + { + "epoch": 17.15, + "learning_rate": 1.0455168304215923e-06, + "loss": 0.0014, + "step": 55535 + }, + { + "epoch": 17.15, + "learning_rate": 1.0452942062464478e-06, + "loss": 0.0015, + "step": 55536 + }, + { + "epoch": 17.15, + "learning_rate": 1.045071604468657e-06, + "loss": 0.0017, + "step": 55537 + }, + { + "epoch": 17.15, + "learning_rate": 1.0448490250887743e-06, + "loss": 0.0016, + "step": 55538 + }, + { + "epoch": 17.15, + "learning_rate": 1.044626468107357e-06, + "loss": 0.0026, + "step": 55539 + }, + { + "epoch": 17.15, + "learning_rate": 1.0444039335249634e-06, + "loss": 0.0028, + "step": 55540 + }, + { + "epoch": 17.15, + "learning_rate": 1.0441814213421498e-06, + "loss": 0.0024, + "step": 55541 + }, + { + "epoch": 17.15, + "learning_rate": 1.04395893155947e-06, + "loss": 0.0017, + "step": 55542 + }, + { + "epoch": 17.15, + "learning_rate": 1.0437364641774839e-06, + "loss": 0.0019, + "step": 55543 + }, + { + "epoch": 17.15, + "learning_rate": 1.0435140191967452e-06, + "loss": 0.0015, + "step": 55544 + }, + { + "epoch": 17.15, + "learning_rate": 1.0432915966178125e-06, + "loss": 0.0012, + "step": 55545 + }, + { + "epoch": 17.15, + "learning_rate": 1.043069196441242e-06, + "loss": 0.0018, + "step": 55546 + }, + { + "epoch": 17.15, + "learning_rate": 1.0428468186675867e-06, + "loss": 0.0015, + "step": 55547 + }, + { + "epoch": 17.15, + "learning_rate": 1.0426244632974048e-06, + "loss": 0.0018, + "step": 55548 + }, + { + "epoch": 17.15, + "learning_rate": 1.042402130331256e-06, + "loss": 0.0019, + "step": 55549 + }, + { + "epoch": 17.15, + "learning_rate": 1.0421798197696896e-06, + "loss": 0.0017, + "step": 55550 + }, + { + "epoch": 17.16, + "learning_rate": 1.0419575316132691e-06, + "loss": 0.0018, + "step": 55551 + }, + { + "epoch": 17.16, + "learning_rate": 1.0417352658625434e-06, + "loss": 0.0012, + "step": 55552 + }, + { + "epoch": 17.16, + "learning_rate": 1.0415130225180736e-06, + "loss": 0.0017, + "step": 55553 + }, + { + "epoch": 17.16, + "learning_rate": 1.0412908015804125e-06, + "loss": 0.0017, + "step": 55554 + }, + { + "epoch": 17.16, + "learning_rate": 1.0410686030501183e-06, + "loss": 0.001, + "step": 55555 + }, + { + "epoch": 17.16, + "learning_rate": 1.0408464269277462e-06, + "loss": 0.0015, + "step": 55556 + }, + { + "epoch": 17.16, + "learning_rate": 1.0406242732138495e-06, + "loss": 0.002, + "step": 55557 + }, + { + "epoch": 17.16, + "learning_rate": 1.040402141908985e-06, + "loss": 0.0014, + "step": 55558 + }, + { + "epoch": 17.16, + "learning_rate": 1.0401800330137102e-06, + "loss": 0.0022, + "step": 55559 + }, + { + "epoch": 17.16, + "learning_rate": 1.0399579465285781e-06, + "loss": 0.0012, + "step": 55560 + }, + { + "epoch": 17.16, + "learning_rate": 1.039735882454147e-06, + "loss": 0.0015, + "step": 55561 + }, + { + "epoch": 17.16, + "learning_rate": 1.039513840790971e-06, + "loss": 0.0015, + "step": 55562 + }, + { + "epoch": 17.16, + "learning_rate": 1.039291821539603e-06, + "loss": 0.0013, + "step": 55563 + }, + { + "epoch": 17.16, + "learning_rate": 1.0390698247006004e-06, + "loss": 0.0016, + "step": 55564 + }, + { + "epoch": 17.16, + "learning_rate": 1.0388478502745213e-06, + "loss": 0.0017, + "step": 55565 + }, + { + "epoch": 17.16, + "learning_rate": 1.0386258982619179e-06, + "loss": 0.0018, + "step": 55566 + }, + { + "epoch": 17.16, + "learning_rate": 1.038403968663343e-06, + "loss": 0.0015, + "step": 55567 + }, + { + "epoch": 17.16, + "learning_rate": 1.038182061479357e-06, + "loss": 0.0018, + "step": 55568 + }, + { + "epoch": 17.16, + "learning_rate": 1.0379601767105097e-06, + "loss": 0.0018, + "step": 55569 + }, + { + "epoch": 17.16, + "learning_rate": 1.0377383143573582e-06, + "loss": 0.0015, + "step": 55570 + }, + { + "epoch": 17.16, + "learning_rate": 1.0375164744204602e-06, + "loss": 0.0023, + "step": 55571 + }, + { + "epoch": 17.16, + "learning_rate": 1.0372946569003684e-06, + "loss": 0.002, + "step": 55572 + }, + { + "epoch": 17.16, + "learning_rate": 1.0370728617976345e-06, + "loss": 0.0023, + "step": 55573 + }, + { + "epoch": 17.16, + "learning_rate": 1.0368510891128192e-06, + "loss": 0.0023, + "step": 55574 + }, + { + "epoch": 17.16, + "learning_rate": 1.036629338846471e-06, + "loss": 0.0018, + "step": 55575 + }, + { + "epoch": 17.16, + "learning_rate": 1.0364076109991505e-06, + "loss": 0.0019, + "step": 55576 + }, + { + "epoch": 17.16, + "learning_rate": 1.0361859055714096e-06, + "loss": 0.0017, + "step": 55577 + }, + { + "epoch": 17.16, + "learning_rate": 1.0359642225638e-06, + "loss": 0.0021, + "step": 55578 + }, + { + "epoch": 17.16, + "learning_rate": 1.035742561976879e-06, + "loss": 0.0012, + "step": 55579 + }, + { + "epoch": 17.16, + "learning_rate": 1.0355209238112029e-06, + "loss": 0.002, + "step": 55580 + }, + { + "epoch": 17.16, + "learning_rate": 1.0352993080673223e-06, + "loss": 0.0021, + "step": 55581 + }, + { + "epoch": 17.16, + "learning_rate": 1.0350777147457946e-06, + "loss": 0.0012, + "step": 55582 + }, + { + "epoch": 17.17, + "learning_rate": 1.0348561438471705e-06, + "loss": 0.0023, + "step": 55583 + }, + { + "epoch": 17.17, + "learning_rate": 1.0346345953720093e-06, + "loss": 0.002, + "step": 55584 + }, + { + "epoch": 17.17, + "learning_rate": 1.0344130693208598e-06, + "loss": 0.0023, + "step": 55585 + }, + { + "epoch": 17.17, + "learning_rate": 1.0341915656942803e-06, + "loss": 0.0016, + "step": 55586 + }, + { + "epoch": 17.17, + "learning_rate": 1.0339700844928225e-06, + "loss": 0.0021, + "step": 55587 + }, + { + "epoch": 17.17, + "learning_rate": 1.0337486257170393e-06, + "loss": 0.0016, + "step": 55588 + }, + { + "epoch": 17.17, + "learning_rate": 1.0335271893674859e-06, + "loss": 0.0015, + "step": 55589 + }, + { + "epoch": 17.17, + "learning_rate": 1.0333057754447183e-06, + "loss": 0.0019, + "step": 55590 + }, + { + "epoch": 17.17, + "learning_rate": 1.0330843839492867e-06, + "loss": 0.0021, + "step": 55591 + }, + { + "epoch": 17.17, + "learning_rate": 1.0328630148817486e-06, + "loss": 0.0018, + "step": 55592 + }, + { + "epoch": 17.17, + "learning_rate": 1.0326416682426555e-06, + "loss": 0.0016, + "step": 55593 + }, + { + "epoch": 17.17, + "learning_rate": 1.0324203440325586e-06, + "loss": 0.003, + "step": 55594 + }, + { + "epoch": 17.17, + "learning_rate": 1.0321990422520145e-06, + "loss": 0.0016, + "step": 55595 + }, + { + "epoch": 17.17, + "learning_rate": 1.031977762901578e-06, + "loss": 0.0017, + "step": 55596 + }, + { + "epoch": 17.17, + "learning_rate": 1.0317565059818013e-06, + "loss": 0.0023, + "step": 55597 + }, + { + "epoch": 17.17, + "learning_rate": 1.0315352714932348e-06, + "loss": 0.0011, + "step": 55598 + }, + { + "epoch": 17.17, + "learning_rate": 1.0313140594364367e-06, + "loss": 0.002, + "step": 55599 + }, + { + "epoch": 17.17, + "learning_rate": 1.031092869811956e-06, + "loss": 0.0023, + "step": 55600 + }, + { + "epoch": 17.17, + "learning_rate": 1.0308717026203474e-06, + "loss": 0.0019, + "step": 55601 + }, + { + "epoch": 17.17, + "learning_rate": 1.0306505578621684e-06, + "loss": 0.0012, + "step": 55602 + }, + { + "epoch": 17.17, + "learning_rate": 1.030429435537964e-06, + "loss": 0.0017, + "step": 55603 + }, + { + "epoch": 17.17, + "learning_rate": 1.0302083356482927e-06, + "loss": 0.0011, + "step": 55604 + }, + { + "epoch": 17.17, + "learning_rate": 1.0299872581937076e-06, + "loss": 0.0015, + "step": 55605 + }, + { + "epoch": 17.17, + "learning_rate": 1.029766203174759e-06, + "loss": 0.0017, + "step": 55606 + }, + { + "epoch": 17.17, + "learning_rate": 1.0295451705920023e-06, + "loss": 0.0013, + "step": 55607 + }, + { + "epoch": 17.17, + "learning_rate": 1.0293241604459891e-06, + "loss": 0.0017, + "step": 55608 + }, + { + "epoch": 17.17, + "learning_rate": 1.0291031727372713e-06, + "loss": 0.0016, + "step": 55609 + }, + { + "epoch": 17.17, + "learning_rate": 1.028882207466403e-06, + "loss": 0.0014, + "step": 55610 + }, + { + "epoch": 17.17, + "learning_rate": 1.0286612646339367e-06, + "loss": 0.0021, + "step": 55611 + }, + { + "epoch": 17.17, + "learning_rate": 1.0284403442404267e-06, + "loss": 0.0022, + "step": 55612 + }, + { + "epoch": 17.17, + "learning_rate": 1.0282194462864204e-06, + "loss": 0.002, + "step": 55613 + }, + { + "epoch": 17.17, + "learning_rate": 1.027998570772476e-06, + "loss": 0.0015, + "step": 55614 + }, + { + "epoch": 17.17, + "learning_rate": 1.0277777176991421e-06, + "loss": 0.0021, + "step": 55615 + }, + { + "epoch": 17.18, + "learning_rate": 1.0275568870669716e-06, + "loss": 0.0016, + "step": 55616 + }, + { + "epoch": 17.18, + "learning_rate": 1.0273360788765208e-06, + "loss": 0.0021, + "step": 55617 + }, + { + "epoch": 17.18, + "learning_rate": 1.027115293128338e-06, + "loss": 0.002, + "step": 55618 + }, + { + "epoch": 17.18, + "learning_rate": 1.026894529822975e-06, + "loss": 0.0018, + "step": 55619 + }, + { + "epoch": 17.18, + "learning_rate": 1.0266737889609856e-06, + "loss": 0.0019, + "step": 55620 + }, + { + "epoch": 17.18, + "learning_rate": 1.0264530705429232e-06, + "loss": 0.0024, + "step": 55621 + }, + { + "epoch": 17.18, + "learning_rate": 1.0262323745693393e-06, + "loss": 0.0016, + "step": 55622 + }, + { + "epoch": 17.18, + "learning_rate": 1.026011701040782e-06, + "loss": 0.0017, + "step": 55623 + }, + { + "epoch": 17.18, + "learning_rate": 1.0257910499578084e-06, + "loss": 0.0019, + "step": 55624 + }, + { + "epoch": 17.18, + "learning_rate": 1.0255704213209661e-06, + "loss": 0.0026, + "step": 55625 + }, + { + "epoch": 17.18, + "learning_rate": 1.0253498151308083e-06, + "loss": 0.0021, + "step": 55626 + }, + { + "epoch": 17.18, + "learning_rate": 1.0251292313878903e-06, + "loss": 0.0017, + "step": 55627 + }, + { + "epoch": 17.18, + "learning_rate": 1.0249086700927614e-06, + "loss": 0.0019, + "step": 55628 + }, + { + "epoch": 17.18, + "learning_rate": 1.02468813124597e-06, + "loss": 0.0018, + "step": 55629 + }, + { + "epoch": 17.18, + "learning_rate": 1.0244676148480737e-06, + "loss": 0.0017, + "step": 55630 + }, + { + "epoch": 17.18, + "learning_rate": 1.0242471208996175e-06, + "loss": 0.0019, + "step": 55631 + }, + { + "epoch": 17.18, + "learning_rate": 1.0240266494011597e-06, + "loss": 0.0022, + "step": 55632 + }, + { + "epoch": 17.18, + "learning_rate": 1.0238062003532478e-06, + "loss": 0.0029, + "step": 55633 + }, + { + "epoch": 17.18, + "learning_rate": 1.0235857737564313e-06, + "loss": 0.002, + "step": 55634 + }, + { + "epoch": 17.18, + "learning_rate": 1.0233653696112644e-06, + "loss": 0.0015, + "step": 55635 + }, + { + "epoch": 17.18, + "learning_rate": 1.0231449879182998e-06, + "loss": 0.0018, + "step": 55636 + }, + { + "epoch": 17.18, + "learning_rate": 1.0229246286780848e-06, + "loss": 0.0015, + "step": 55637 + }, + { + "epoch": 17.18, + "learning_rate": 1.0227042918911746e-06, + "loss": 0.0018, + "step": 55638 + }, + { + "epoch": 17.18, + "learning_rate": 1.0224839775581186e-06, + "loss": 0.0016, + "step": 55639 + }, + { + "epoch": 17.18, + "learning_rate": 1.0222636856794655e-06, + "loss": 0.001, + "step": 55640 + }, + { + "epoch": 17.18, + "learning_rate": 1.022043416255768e-06, + "loss": 0.0017, + "step": 55641 + }, + { + "epoch": 17.18, + "learning_rate": 1.0218231692875802e-06, + "loss": 0.0016, + "step": 55642 + }, + { + "epoch": 17.18, + "learning_rate": 1.0216029447754493e-06, + "loss": 0.0021, + "step": 55643 + }, + { + "epoch": 17.18, + "learning_rate": 1.0213827427199252e-06, + "loss": 0.0019, + "step": 55644 + }, + { + "epoch": 17.18, + "learning_rate": 1.0211625631215627e-06, + "loss": 0.0014, + "step": 55645 + }, + { + "epoch": 17.18, + "learning_rate": 1.020942405980908e-06, + "loss": 0.0014, + "step": 55646 + }, + { + "epoch": 17.18, + "learning_rate": 1.0207222712985154e-06, + "loss": 0.0019, + "step": 55647 + }, + { + "epoch": 17.19, + "learning_rate": 1.0205021590749342e-06, + "loss": 0.0014, + "step": 55648 + }, + { + "epoch": 17.19, + "learning_rate": 1.0202820693107163e-06, + "loss": 0.0016, + "step": 55649 + }, + { + "epoch": 17.19, + "learning_rate": 1.0200620020064078e-06, + "loss": 0.0018, + "step": 55650 + }, + { + "epoch": 17.19, + "learning_rate": 1.0198419571625617e-06, + "loss": 0.0014, + "step": 55651 + }, + { + "epoch": 17.19, + "learning_rate": 1.019621934779732e-06, + "loss": 0.0018, + "step": 55652 + }, + { + "epoch": 17.19, + "learning_rate": 1.0194019348584649e-06, + "loss": 0.0014, + "step": 55653 + }, + { + "epoch": 17.19, + "learning_rate": 1.01918195739931e-06, + "loss": 0.0018, + "step": 55654 + }, + { + "epoch": 17.19, + "learning_rate": 1.0189620024028202e-06, + "loss": 0.0019, + "step": 55655 + }, + { + "epoch": 17.19, + "learning_rate": 1.0187420698695428e-06, + "loss": 0.0017, + "step": 55656 + }, + { + "epoch": 17.19, + "learning_rate": 1.0185221598000305e-06, + "loss": 0.0017, + "step": 55657 + }, + { + "epoch": 17.19, + "learning_rate": 1.0183022721948333e-06, + "loss": 0.0014, + "step": 55658 + }, + { + "epoch": 17.19, + "learning_rate": 1.0180824070545003e-06, + "loss": 0.0019, + "step": 55659 + }, + { + "epoch": 17.19, + "learning_rate": 1.0178625643795802e-06, + "loss": 0.0017, + "step": 55660 + }, + { + "epoch": 17.19, + "learning_rate": 1.017642744170626e-06, + "loss": 0.0018, + "step": 55661 + }, + { + "epoch": 17.19, + "learning_rate": 1.0174229464281826e-06, + "loss": 0.0014, + "step": 55662 + }, + { + "epoch": 17.19, + "learning_rate": 1.017203171152805e-06, + "loss": 0.0016, + "step": 55663 + }, + { + "epoch": 17.19, + "learning_rate": 1.0169834183450412e-06, + "loss": 0.0013, + "step": 55664 + }, + { + "epoch": 17.19, + "learning_rate": 1.0167636880054387e-06, + "loss": 0.0024, + "step": 55665 + }, + { + "epoch": 17.19, + "learning_rate": 1.0165439801345478e-06, + "loss": 0.0022, + "step": 55666 + }, + { + "epoch": 17.19, + "learning_rate": 1.016324294732921e-06, + "loss": 0.0019, + "step": 55667 + }, + { + "epoch": 17.19, + "learning_rate": 1.0161046318011037e-06, + "loss": 0.0019, + "step": 55668 + }, + { + "epoch": 17.19, + "learning_rate": 1.0158849913396496e-06, + "loss": 0.0019, + "step": 55669 + }, + { + "epoch": 17.19, + "learning_rate": 1.015665373349105e-06, + "loss": 0.002, + "step": 55670 + }, + { + "epoch": 17.19, + "learning_rate": 1.0154457778300186e-06, + "loss": 0.0023, + "step": 55671 + }, + { + "epoch": 17.19, + "learning_rate": 1.015226204782941e-06, + "loss": 0.0025, + "step": 55672 + }, + { + "epoch": 17.19, + "learning_rate": 1.0150066542084224e-06, + "loss": 0.0015, + "step": 55673 + }, + { + "epoch": 17.19, + "learning_rate": 1.014787126107012e-06, + "loss": 0.0016, + "step": 55674 + }, + { + "epoch": 17.19, + "learning_rate": 1.0145676204792553e-06, + "loss": 0.0013, + "step": 55675 + }, + { + "epoch": 17.19, + "learning_rate": 1.0143481373257068e-06, + "loss": 0.0019, + "step": 55676 + }, + { + "epoch": 17.19, + "learning_rate": 1.0141286766469093e-06, + "loss": 0.002, + "step": 55677 + }, + { + "epoch": 17.19, + "learning_rate": 1.0139092384434158e-06, + "loss": 0.0011, + "step": 55678 + }, + { + "epoch": 17.19, + "learning_rate": 1.0136898227157755e-06, + "loss": 0.0017, + "step": 55679 + }, + { + "epoch": 17.19, + "learning_rate": 1.0134704294645358e-06, + "loss": 0.0018, + "step": 55680 + }, + { + "epoch": 17.2, + "learning_rate": 1.0132510586902444e-06, + "loss": 0.0017, + "step": 55681 + }, + { + "epoch": 17.2, + "learning_rate": 1.0130317103934505e-06, + "loss": 0.0014, + "step": 55682 + }, + { + "epoch": 17.2, + "learning_rate": 1.0128123845747062e-06, + "loss": 0.0016, + "step": 55683 + }, + { + "epoch": 17.2, + "learning_rate": 1.0125930812345564e-06, + "loss": 0.0016, + "step": 55684 + }, + { + "epoch": 17.2, + "learning_rate": 1.0123738003735484e-06, + "loss": 0.0018, + "step": 55685 + }, + { + "epoch": 17.2, + "learning_rate": 1.0121545419922362e-06, + "loss": 0.0016, + "step": 55686 + }, + { + "epoch": 17.2, + "learning_rate": 1.0119353060911619e-06, + "loss": 0.0021, + "step": 55687 + }, + { + "epoch": 17.2, + "learning_rate": 1.0117160926708758e-06, + "loss": 0.0019, + "step": 55688 + }, + { + "epoch": 17.2, + "learning_rate": 1.01149690173193e-06, + "loss": 0.0018, + "step": 55689 + }, + { + "epoch": 17.2, + "learning_rate": 1.0112777332748702e-06, + "loss": 0.0019, + "step": 55690 + }, + { + "epoch": 17.2, + "learning_rate": 1.011058587300242e-06, + "loss": 0.0022, + "step": 55691 + }, + { + "epoch": 17.2, + "learning_rate": 1.0108394638085972e-06, + "loss": 0.0016, + "step": 55692 + }, + { + "epoch": 17.2, + "learning_rate": 1.0106203628004807e-06, + "loss": 0.0014, + "step": 55693 + }, + { + "epoch": 17.2, + "learning_rate": 1.0104012842764443e-06, + "loss": 0.0025, + "step": 55694 + }, + { + "epoch": 17.2, + "learning_rate": 1.0101822282370343e-06, + "loss": 0.0019, + "step": 55695 + }, + { + "epoch": 17.2, + "learning_rate": 1.009963194682796e-06, + "loss": 0.002, + "step": 55696 + }, + { + "epoch": 17.2, + "learning_rate": 1.0097441836142796e-06, + "loss": 0.002, + "step": 55697 + }, + { + "epoch": 17.2, + "learning_rate": 1.009525195032034e-06, + "loss": 0.0016, + "step": 55698 + }, + { + "epoch": 17.2, + "learning_rate": 1.009306228936604e-06, + "loss": 0.0012, + "step": 55699 + }, + { + "epoch": 17.2, + "learning_rate": 1.0090872853285405e-06, + "loss": 0.0017, + "step": 55700 + }, + { + "epoch": 17.2, + "learning_rate": 1.0088683642083906e-06, + "loss": 0.0019, + "step": 55701 + }, + { + "epoch": 17.2, + "learning_rate": 1.0086494655766977e-06, + "loss": 0.002, + "step": 55702 + }, + { + "epoch": 17.2, + "learning_rate": 1.008430589434013e-06, + "loss": 0.0027, + "step": 55703 + }, + { + "epoch": 17.2, + "learning_rate": 1.0082117357808852e-06, + "loss": 0.0022, + "step": 55704 + }, + { + "epoch": 17.2, + "learning_rate": 1.0079929046178606e-06, + "loss": 0.0017, + "step": 55705 + }, + { + "epoch": 17.2, + "learning_rate": 1.007774095945483e-06, + "loss": 0.0018, + "step": 55706 + }, + { + "epoch": 17.2, + "learning_rate": 1.0075553097643042e-06, + "loss": 0.0034, + "step": 55707 + }, + { + "epoch": 17.2, + "learning_rate": 1.0073365460748674e-06, + "loss": 0.0021, + "step": 55708 + }, + { + "epoch": 17.2, + "learning_rate": 1.0071178048777231e-06, + "loss": 0.0017, + "step": 55709 + }, + { + "epoch": 17.2, + "learning_rate": 1.0068990861734206e-06, + "loss": 0.0025, + "step": 55710 + }, + { + "epoch": 17.2, + "learning_rate": 1.0066803899625e-06, + "loss": 0.0014, + "step": 55711 + }, + { + "epoch": 17.2, + "learning_rate": 1.0064617162455126e-06, + "loss": 0.002, + "step": 55712 + }, + { + "epoch": 17.21, + "learning_rate": 1.0062430650230059e-06, + "loss": 0.0021, + "step": 55713 + }, + { + "epoch": 17.21, + "learning_rate": 1.006024436295524e-06, + "loss": 0.0013, + "step": 55714 + }, + { + "epoch": 17.21, + "learning_rate": 1.0058058300636176e-06, + "loss": 0.0017, + "step": 55715 + }, + { + "epoch": 17.21, + "learning_rate": 1.0055872463278293e-06, + "loss": 0.0021, + "step": 55716 + }, + { + "epoch": 17.21, + "learning_rate": 1.005368685088709e-06, + "loss": 0.0023, + "step": 55717 + }, + { + "epoch": 17.21, + "learning_rate": 1.0051501463468017e-06, + "loss": 0.0012, + "step": 55718 + }, + { + "epoch": 17.21, + "learning_rate": 1.0049316301026535e-06, + "loss": 0.0017, + "step": 55719 + }, + { + "epoch": 17.21, + "learning_rate": 1.0047131363568153e-06, + "loss": 0.0013, + "step": 55720 + }, + { + "epoch": 17.21, + "learning_rate": 1.0044946651098264e-06, + "loss": 0.0015, + "step": 55721 + }, + { + "epoch": 17.21, + "learning_rate": 1.0042762163622376e-06, + "loss": 0.0022, + "step": 55722 + }, + { + "epoch": 17.21, + "learning_rate": 1.0040577901145964e-06, + "loss": 0.0019, + "step": 55723 + }, + { + "epoch": 17.21, + "learning_rate": 1.0038393863674456e-06, + "loss": 0.0016, + "step": 55724 + }, + { + "epoch": 17.21, + "learning_rate": 1.0036210051213346e-06, + "loss": 0.0013, + "step": 55725 + }, + { + "epoch": 17.21, + "learning_rate": 1.0034026463768088e-06, + "loss": 0.0018, + "step": 55726 + }, + { + "epoch": 17.21, + "learning_rate": 1.0031843101344119e-06, + "loss": 0.0016, + "step": 55727 + }, + { + "epoch": 17.21, + "learning_rate": 1.0029659963946924e-06, + "loss": 0.002, + "step": 55728 + }, + { + "epoch": 17.21, + "learning_rate": 1.002747705158198e-06, + "loss": 0.0012, + "step": 55729 + }, + { + "epoch": 17.21, + "learning_rate": 1.0025294364254712e-06, + "loss": 0.002, + "step": 55730 + }, + { + "epoch": 17.21, + "learning_rate": 1.0023111901970583e-06, + "loss": 0.0014, + "step": 55731 + }, + { + "epoch": 17.21, + "learning_rate": 1.002092966473508e-06, + "loss": 0.0014, + "step": 55732 + }, + { + "epoch": 17.21, + "learning_rate": 1.0018747652553628e-06, + "loss": 0.0019, + "step": 55733 + }, + { + "epoch": 17.21, + "learning_rate": 1.0016565865431693e-06, + "loss": 0.0018, + "step": 55734 + }, + { + "epoch": 17.21, + "learning_rate": 1.0014384303374758e-06, + "loss": 0.0016, + "step": 55735 + }, + { + "epoch": 17.21, + "learning_rate": 1.0012202966388263e-06, + "loss": 0.0019, + "step": 55736 + }, + { + "epoch": 17.21, + "learning_rate": 1.0010021854477647e-06, + "loss": 0.0019, + "step": 55737 + }, + { + "epoch": 17.21, + "learning_rate": 1.0007840967648398e-06, + "loss": 0.0016, + "step": 55738 + }, + { + "epoch": 17.21, + "learning_rate": 1.0005660305905918e-06, + "loss": 0.0017, + "step": 55739 + }, + { + "epoch": 17.21, + "learning_rate": 1.0003479869255728e-06, + "loss": 0.0021, + "step": 55740 + }, + { + "epoch": 17.21, + "learning_rate": 1.0001299657703245e-06, + "loss": 0.0015, + "step": 55741 + }, + { + "epoch": 17.21, + "learning_rate": 9.99911967125391e-07, + "loss": 0.0014, + "step": 55742 + }, + { + "epoch": 17.21, + "learning_rate": 9.996939909913194e-07, + "loss": 0.0017, + "step": 55743 + }, + { + "epoch": 17.21, + "learning_rate": 9.994760373686562e-07, + "loss": 0.0027, + "step": 55744 + }, + { + "epoch": 17.22, + "learning_rate": 9.992581062579431e-07, + "loss": 0.0014, + "step": 55745 + }, + { + "epoch": 17.22, + "learning_rate": 9.990401976597287e-07, + "loss": 0.0014, + "step": 55746 + }, + { + "epoch": 17.22, + "learning_rate": 9.988223115745554e-07, + "loss": 0.0013, + "step": 55747 + }, + { + "epoch": 17.22, + "learning_rate": 9.9860444800297e-07, + "loss": 0.0022, + "step": 55748 + }, + { + "epoch": 17.22, + "learning_rate": 9.983866069455161e-07, + "loss": 0.0025, + "step": 55749 + }, + { + "epoch": 17.22, + "learning_rate": 9.98168788402738e-07, + "loss": 0.0022, + "step": 55750 + }, + { + "epoch": 17.22, + "learning_rate": 9.97950992375185e-07, + "loss": 0.002, + "step": 55751 + }, + { + "epoch": 17.22, + "learning_rate": 9.97733218863396e-07, + "loss": 0.0018, + "step": 55752 + }, + { + "epoch": 17.22, + "learning_rate": 9.975154678679177e-07, + "loss": 0.0011, + "step": 55753 + }, + { + "epoch": 17.22, + "learning_rate": 9.972977393892969e-07, + "loss": 0.0016, + "step": 55754 + }, + { + "epoch": 17.22, + "learning_rate": 9.97080033428074e-07, + "loss": 0.0025, + "step": 55755 + }, + { + "epoch": 17.22, + "learning_rate": 9.968623499847985e-07, + "loss": 0.002, + "step": 55756 + }, + { + "epoch": 17.22, + "learning_rate": 9.966446890600124e-07, + "loss": 0.002, + "step": 55757 + }, + { + "epoch": 17.22, + "learning_rate": 9.964270506542573e-07, + "loss": 0.0014, + "step": 55758 + }, + { + "epoch": 17.22, + "learning_rate": 9.962094347680817e-07, + "loss": 0.0017, + "step": 55759 + }, + { + "epoch": 17.22, + "learning_rate": 9.959918414020298e-07, + "loss": 0.0019, + "step": 55760 + }, + { + "epoch": 17.22, + "learning_rate": 9.957742705566441e-07, + "loss": 0.0015, + "step": 55761 + }, + { + "epoch": 17.22, + "learning_rate": 9.955567222324669e-07, + "loss": 0.0016, + "step": 55762 + }, + { + "epoch": 17.22, + "learning_rate": 9.953391964300474e-07, + "loss": 0.0016, + "step": 55763 + }, + { + "epoch": 17.22, + "learning_rate": 9.951216931499253e-07, + "loss": 0.0017, + "step": 55764 + }, + { + "epoch": 17.22, + "learning_rate": 9.949042123926455e-07, + "loss": 0.0023, + "step": 55765 + }, + { + "epoch": 17.22, + "learning_rate": 9.946867541587545e-07, + "loss": 0.0015, + "step": 55766 + }, + { + "epoch": 17.22, + "learning_rate": 9.944693184487952e-07, + "loss": 0.0016, + "step": 55767 + }, + { + "epoch": 17.22, + "learning_rate": 9.942519052633081e-07, + "loss": 0.0016, + "step": 55768 + }, + { + "epoch": 17.22, + "learning_rate": 9.940345146028418e-07, + "loss": 0.0019, + "step": 55769 + }, + { + "epoch": 17.22, + "learning_rate": 9.938171464679358e-07, + "loss": 0.002, + "step": 55770 + }, + { + "epoch": 17.22, + "learning_rate": 9.935998008591375e-07, + "loss": 0.0018, + "step": 55771 + }, + { + "epoch": 17.22, + "learning_rate": 9.933824777769886e-07, + "loss": 0.0017, + "step": 55772 + }, + { + "epoch": 17.22, + "learning_rate": 9.93165177222032e-07, + "loss": 0.0017, + "step": 55773 + }, + { + "epoch": 17.22, + "learning_rate": 9.929478991948104e-07, + "loss": 0.0016, + "step": 55774 + }, + { + "epoch": 17.22, + "learning_rate": 9.927306436958718e-07, + "loss": 0.0022, + "step": 55775 + }, + { + "epoch": 17.22, + "learning_rate": 9.925134107257539e-07, + "loss": 0.0013, + "step": 55776 + }, + { + "epoch": 17.22, + "learning_rate": 9.922962002850056e-07, + "loss": 0.0014, + "step": 55777 + }, + { + "epoch": 17.23, + "learning_rate": 9.920790123741676e-07, + "loss": 0.0013, + "step": 55778 + }, + { + "epoch": 17.23, + "learning_rate": 9.918618469937802e-07, + "loss": 0.0016, + "step": 55779 + }, + { + "epoch": 17.23, + "learning_rate": 9.9164470414439e-07, + "loss": 0.0018, + "step": 55780 + }, + { + "epoch": 17.23, + "learning_rate": 9.914275838265408e-07, + "loss": 0.001, + "step": 55781 + }, + { + "epoch": 17.23, + "learning_rate": 9.912104860407745e-07, + "loss": 0.0022, + "step": 55782 + }, + { + "epoch": 17.23, + "learning_rate": 9.909934107876317e-07, + "loss": 0.0018, + "step": 55783 + }, + { + "epoch": 17.23, + "learning_rate": 9.907763580676577e-07, + "loss": 0.0019, + "step": 55784 + }, + { + "epoch": 17.23, + "learning_rate": 9.905593278813973e-07, + "loss": 0.0018, + "step": 55785 + }, + { + "epoch": 17.23, + "learning_rate": 9.903423202293893e-07, + "loss": 0.0019, + "step": 55786 + }, + { + "epoch": 17.23, + "learning_rate": 9.90125335112181e-07, + "loss": 0.0017, + "step": 55787 + }, + { + "epoch": 17.23, + "learning_rate": 9.899083725303116e-07, + "loss": 0.0018, + "step": 55788 + }, + { + "epoch": 17.23, + "learning_rate": 9.896914324843231e-07, + "loss": 0.0025, + "step": 55789 + }, + { + "epoch": 17.23, + "learning_rate": 9.894745149747586e-07, + "loss": 0.002, + "step": 55790 + }, + { + "epoch": 17.23, + "learning_rate": 9.892576200021652e-07, + "loss": 0.0023, + "step": 55791 + }, + { + "epoch": 17.23, + "learning_rate": 9.890407475670817e-07, + "loss": 0.0016, + "step": 55792 + }, + { + "epoch": 17.23, + "learning_rate": 9.88823897670048e-07, + "loss": 0.0014, + "step": 55793 + }, + { + "epoch": 17.23, + "learning_rate": 9.886070703116124e-07, + "loss": 0.0015, + "step": 55794 + }, + { + "epoch": 17.23, + "learning_rate": 9.883902654923117e-07, + "loss": 0.0018, + "step": 55795 + }, + { + "epoch": 17.23, + "learning_rate": 9.8817348321269e-07, + "loss": 0.0015, + "step": 55796 + }, + { + "epoch": 17.23, + "learning_rate": 9.879567234732923e-07, + "loss": 0.0016, + "step": 55797 + }, + { + "epoch": 17.23, + "learning_rate": 9.877399862746584e-07, + "loss": 0.0016, + "step": 55798 + }, + { + "epoch": 17.23, + "learning_rate": 9.87523271617329e-07, + "loss": 0.0015, + "step": 55799 + }, + { + "epoch": 17.23, + "learning_rate": 9.8730657950185e-07, + "loss": 0.0018, + "step": 55800 + }, + { + "epoch": 17.23, + "learning_rate": 9.870899099287578e-07, + "loss": 0.0016, + "step": 55801 + }, + { + "epoch": 17.23, + "learning_rate": 9.868732628986e-07, + "loss": 0.0012, + "step": 55802 + }, + { + "epoch": 17.23, + "learning_rate": 9.86656638411917e-07, + "loss": 0.0016, + "step": 55803 + }, + { + "epoch": 17.23, + "learning_rate": 9.864400364692473e-07, + "loss": 0.0021, + "step": 55804 + }, + { + "epoch": 17.23, + "learning_rate": 9.86223457071135e-07, + "loss": 0.0016, + "step": 55805 + }, + { + "epoch": 17.23, + "learning_rate": 9.860069002181226e-07, + "loss": 0.0018, + "step": 55806 + }, + { + "epoch": 17.23, + "learning_rate": 9.857903659107504e-07, + "loss": 0.0017, + "step": 55807 + }, + { + "epoch": 17.23, + "learning_rate": 9.855738541495618e-07, + "loss": 0.0016, + "step": 55808 + }, + { + "epoch": 17.23, + "learning_rate": 9.853573649350977e-07, + "loss": 0.0015, + "step": 55809 + }, + { + "epoch": 17.24, + "learning_rate": 9.851408982678966e-07, + "loss": 0.0014, + "step": 55810 + }, + { + "epoch": 17.24, + "learning_rate": 9.849244541485025e-07, + "loss": 0.0015, + "step": 55811 + }, + { + "epoch": 17.24, + "learning_rate": 9.847080325774594e-07, + "loss": 0.0015, + "step": 55812 + }, + { + "epoch": 17.24, + "learning_rate": 9.844916335553045e-07, + "loss": 0.0015, + "step": 55813 + }, + { + "epoch": 17.24, + "learning_rate": 9.842752570825787e-07, + "loss": 0.0019, + "step": 55814 + }, + { + "epoch": 17.24, + "learning_rate": 9.840589031598257e-07, + "loss": 0.002, + "step": 55815 + }, + { + "epoch": 17.24, + "learning_rate": 9.838425717875866e-07, + "loss": 0.0016, + "step": 55816 + }, + { + "epoch": 17.24, + "learning_rate": 9.836262629664006e-07, + "loss": 0.0016, + "step": 55817 + }, + { + "epoch": 17.24, + "learning_rate": 9.834099766968108e-07, + "loss": 0.0022, + "step": 55818 + }, + { + "epoch": 17.24, + "learning_rate": 9.83193712979358e-07, + "loss": 0.0027, + "step": 55819 + }, + { + "epoch": 17.24, + "learning_rate": 9.829774718145802e-07, + "loss": 0.0011, + "step": 55820 + }, + { + "epoch": 17.24, + "learning_rate": 9.827612532030205e-07, + "loss": 0.0015, + "step": 55821 + }, + { + "epoch": 17.24, + "learning_rate": 9.82545057145221e-07, + "loss": 0.0017, + "step": 55822 + }, + { + "epoch": 17.24, + "learning_rate": 9.82328883641721e-07, + "loss": 0.0014, + "step": 55823 + }, + { + "epoch": 17.24, + "learning_rate": 9.82112732693059e-07, + "loss": 0.0017, + "step": 55824 + }, + { + "epoch": 17.24, + "learning_rate": 9.818966042997802e-07, + "loss": 0.0018, + "step": 55825 + }, + { + "epoch": 17.24, + "learning_rate": 9.816804984624218e-07, + "loss": 0.0017, + "step": 55826 + }, + { + "epoch": 17.24, + "learning_rate": 9.814644151815245e-07, + "loss": 0.0017, + "step": 55827 + }, + { + "epoch": 17.24, + "learning_rate": 9.812483544576312e-07, + "loss": 0.0016, + "step": 55828 + }, + { + "epoch": 17.24, + "learning_rate": 9.810323162912806e-07, + "loss": 0.0017, + "step": 55829 + }, + { + "epoch": 17.24, + "learning_rate": 9.808163006830118e-07, + "loss": 0.002, + "step": 55830 + }, + { + "epoch": 17.24, + "learning_rate": 9.80600307633367e-07, + "loss": 0.0017, + "step": 55831 + }, + { + "epoch": 17.24, + "learning_rate": 9.803843371428856e-07, + "loss": 0.0012, + "step": 55832 + }, + { + "epoch": 17.24, + "learning_rate": 9.801683892121095e-07, + "loss": 0.0023, + "step": 55833 + }, + { + "epoch": 17.24, + "learning_rate": 9.79952463841577e-07, + "loss": 0.0021, + "step": 55834 + }, + { + "epoch": 17.24, + "learning_rate": 9.797365610318265e-07, + "loss": 0.0024, + "step": 55835 + }, + { + "epoch": 17.24, + "learning_rate": 9.795206807834002e-07, + "loss": 0.0021, + "step": 55836 + }, + { + "epoch": 17.24, + "learning_rate": 9.793048230968405e-07, + "loss": 0.0023, + "step": 55837 + }, + { + "epoch": 17.24, + "learning_rate": 9.790889879726816e-07, + "loss": 0.0021, + "step": 55838 + }, + { + "epoch": 17.24, + "learning_rate": 9.7887317541147e-07, + "loss": 0.0017, + "step": 55839 + }, + { + "epoch": 17.24, + "learning_rate": 9.786573854137404e-07, + "loss": 0.0024, + "step": 55840 + }, + { + "epoch": 17.24, + "learning_rate": 9.784416179800327e-07, + "loss": 0.0018, + "step": 55841 + }, + { + "epoch": 17.25, + "learning_rate": 9.782258731108884e-07, + "loss": 0.0018, + "step": 55842 + }, + { + "epoch": 17.25, + "learning_rate": 9.780101508068484e-07, + "loss": 0.0015, + "step": 55843 + }, + { + "epoch": 17.25, + "learning_rate": 9.7779445106845e-07, + "loss": 0.0023, + "step": 55844 + }, + { + "epoch": 17.25, + "learning_rate": 9.775787738962317e-07, + "loss": 0.0022, + "step": 55845 + }, + { + "epoch": 17.25, + "learning_rate": 9.77363119290734e-07, + "loss": 0.0018, + "step": 55846 + }, + { + "epoch": 17.25, + "learning_rate": 9.77147487252499e-07, + "loss": 0.0019, + "step": 55847 + }, + { + "epoch": 17.25, + "learning_rate": 9.769318777820624e-07, + "loss": 0.0015, + "step": 55848 + }, + { + "epoch": 17.25, + "learning_rate": 9.767162908799666e-07, + "loss": 0.0019, + "step": 55849 + }, + { + "epoch": 17.25, + "learning_rate": 9.765007265467485e-07, + "loss": 0.0021, + "step": 55850 + }, + { + "epoch": 17.25, + "learning_rate": 9.762851847829457e-07, + "loss": 0.0016, + "step": 55851 + }, + { + "epoch": 17.25, + "learning_rate": 9.76069665589101e-07, + "loss": 0.0016, + "step": 55852 + }, + { + "epoch": 17.25, + "learning_rate": 9.758541689657531e-07, + "loss": 0.0018, + "step": 55853 + }, + { + "epoch": 17.25, + "learning_rate": 9.756386949134388e-07, + "loss": 0.0016, + "step": 55854 + }, + { + "epoch": 17.25, + "learning_rate": 9.754232434326972e-07, + "loss": 0.0015, + "step": 55855 + }, + { + "epoch": 17.25, + "learning_rate": 9.752078145240696e-07, + "loss": 0.0018, + "step": 55856 + }, + { + "epoch": 17.25, + "learning_rate": 9.749924081880913e-07, + "loss": 0.0017, + "step": 55857 + }, + { + "epoch": 17.25, + "learning_rate": 9.747770244253042e-07, + "loss": 0.0014, + "step": 55858 + }, + { + "epoch": 17.25, + "learning_rate": 9.745616632362486e-07, + "loss": 0.0018, + "step": 55859 + }, + { + "epoch": 17.25, + "learning_rate": 9.74346324621457e-07, + "loss": 0.0021, + "step": 55860 + }, + { + "epoch": 17.25, + "learning_rate": 9.741310085814703e-07, + "loss": 0.0013, + "step": 55861 + }, + { + "epoch": 17.25, + "learning_rate": 9.73915715116831e-07, + "loss": 0.0016, + "step": 55862 + }, + { + "epoch": 17.25, + "learning_rate": 9.73700444228073e-07, + "loss": 0.002, + "step": 55863 + }, + { + "epoch": 17.25, + "learning_rate": 9.734851959157375e-07, + "loss": 0.0025, + "step": 55864 + }, + { + "epoch": 17.25, + "learning_rate": 9.732699701803627e-07, + "loss": 0.0012, + "step": 55865 + }, + { + "epoch": 17.25, + "learning_rate": 9.730547670224843e-07, + "loss": 0.002, + "step": 55866 + }, + { + "epoch": 17.25, + "learning_rate": 9.728395864426421e-07, + "loss": 0.0012, + "step": 55867 + }, + { + "epoch": 17.25, + "learning_rate": 9.726244284413767e-07, + "loss": 0.0017, + "step": 55868 + }, + { + "epoch": 17.25, + "learning_rate": 9.724092930192231e-07, + "loss": 0.0015, + "step": 55869 + }, + { + "epoch": 17.25, + "learning_rate": 9.7219418017672e-07, + "loss": 0.0012, + "step": 55870 + }, + { + "epoch": 17.25, + "learning_rate": 9.719790899144066e-07, + "loss": 0.002, + "step": 55871 + }, + { + "epoch": 17.25, + "learning_rate": 9.717640222328183e-07, + "loss": 0.0025, + "step": 55872 + }, + { + "epoch": 17.25, + "learning_rate": 9.715489771324948e-07, + "loss": 0.0016, + "step": 55873 + }, + { + "epoch": 17.25, + "learning_rate": 9.713339546139765e-07, + "loss": 0.0014, + "step": 55874 + }, + { + "epoch": 17.26, + "learning_rate": 9.711189546777977e-07, + "loss": 0.0021, + "step": 55875 + }, + { + "epoch": 17.26, + "learning_rate": 9.709039773244966e-07, + "loss": 0.0011, + "step": 55876 + }, + { + "epoch": 17.26, + "learning_rate": 9.706890225546129e-07, + "loss": 0.0017, + "step": 55877 + }, + { + "epoch": 17.26, + "learning_rate": 9.704740903686805e-07, + "loss": 0.0022, + "step": 55878 + }, + { + "epoch": 17.26, + "learning_rate": 9.702591807672412e-07, + "loss": 0.0018, + "step": 55879 + }, + { + "epoch": 17.26, + "learning_rate": 9.70044293750828e-07, + "loss": 0.0021, + "step": 55880 + }, + { + "epoch": 17.26, + "learning_rate": 9.69829429319984e-07, + "loss": 0.0016, + "step": 55881 + }, + { + "epoch": 17.26, + "learning_rate": 9.696145874752417e-07, + "loss": 0.0013, + "step": 55882 + }, + { + "epoch": 17.26, + "learning_rate": 9.693997682171396e-07, + "loss": 0.0014, + "step": 55883 + }, + { + "epoch": 17.26, + "learning_rate": 9.691849715462187e-07, + "loss": 0.0014, + "step": 55884 + }, + { + "epoch": 17.26, + "learning_rate": 9.689701974630127e-07, + "loss": 0.0024, + "step": 55885 + }, + { + "epoch": 17.26, + "learning_rate": 9.68755445968057e-07, + "loss": 0.0015, + "step": 55886 + }, + { + "epoch": 17.26, + "learning_rate": 9.685407170618943e-07, + "loss": 0.0013, + "step": 55887 + }, + { + "epoch": 17.26, + "learning_rate": 9.683260107450553e-07, + "loss": 0.0013, + "step": 55888 + }, + { + "epoch": 17.26, + "learning_rate": 9.68111327018083e-07, + "loss": 0.0017, + "step": 55889 + }, + { + "epoch": 17.26, + "learning_rate": 9.678966658815114e-07, + "loss": 0.0023, + "step": 55890 + }, + { + "epoch": 17.26, + "learning_rate": 9.676820273358757e-07, + "loss": 0.0013, + "step": 55891 + }, + { + "epoch": 17.26, + "learning_rate": 9.67467411381714e-07, + "loss": 0.0018, + "step": 55892 + }, + { + "epoch": 17.26, + "learning_rate": 9.672528180195662e-07, + "loss": 0.0021, + "step": 55893 + }, + { + "epoch": 17.26, + "learning_rate": 9.67038247249965e-07, + "loss": 0.0021, + "step": 55894 + }, + { + "epoch": 17.26, + "learning_rate": 9.668236990734504e-07, + "loss": 0.0019, + "step": 55895 + }, + { + "epoch": 17.26, + "learning_rate": 9.66609173490557e-07, + "loss": 0.0014, + "step": 55896 + }, + { + "epoch": 17.26, + "learning_rate": 9.66394670501819e-07, + "loss": 0.0015, + "step": 55897 + }, + { + "epoch": 17.26, + "learning_rate": 9.661801901077761e-07, + "loss": 0.0018, + "step": 55898 + }, + { + "epoch": 17.26, + "learning_rate": 9.659657323089666e-07, + "loss": 0.0026, + "step": 55899 + }, + { + "epoch": 17.26, + "learning_rate": 9.657512971059246e-07, + "loss": 0.0019, + "step": 55900 + }, + { + "epoch": 17.26, + "learning_rate": 9.655368844991841e-07, + "loss": 0.0019, + "step": 55901 + }, + { + "epoch": 17.26, + "learning_rate": 9.653224944892858e-07, + "loss": 0.0023, + "step": 55902 + }, + { + "epoch": 17.26, + "learning_rate": 9.651081270767615e-07, + "loss": 0.0018, + "step": 55903 + }, + { + "epoch": 17.26, + "learning_rate": 9.648937822621497e-07, + "loss": 0.0026, + "step": 55904 + }, + { + "epoch": 17.26, + "learning_rate": 9.646794600459885e-07, + "loss": 0.0013, + "step": 55905 + }, + { + "epoch": 17.26, + "learning_rate": 9.644651604288114e-07, + "loss": 0.0022, + "step": 55906 + }, + { + "epoch": 17.27, + "learning_rate": 9.64250883411153e-07, + "loss": 0.0017, + "step": 55907 + }, + { + "epoch": 17.27, + "learning_rate": 9.640366289935543e-07, + "loss": 0.0019, + "step": 55908 + }, + { + "epoch": 17.27, + "learning_rate": 9.638223971765448e-07, + "loss": 0.0021, + "step": 55909 + }, + { + "epoch": 17.27, + "learning_rate": 9.636081879606661e-07, + "loss": 0.0025, + "step": 55910 + }, + { + "epoch": 17.27, + "learning_rate": 9.633940013464493e-07, + "loss": 0.0016, + "step": 55911 + }, + { + "epoch": 17.27, + "learning_rate": 9.631798373344348e-07, + "loss": 0.0016, + "step": 55912 + }, + { + "epoch": 17.27, + "learning_rate": 9.629656959251532e-07, + "loss": 0.0015, + "step": 55913 + }, + { + "epoch": 17.27, + "learning_rate": 9.627515771191431e-07, + "loss": 0.0016, + "step": 55914 + }, + { + "epoch": 17.27, + "learning_rate": 9.625374809169408e-07, + "loss": 0.0015, + "step": 55915 + }, + { + "epoch": 17.27, + "learning_rate": 9.623234073190813e-07, + "loss": 0.0014, + "step": 55916 + }, + { + "epoch": 17.27, + "learning_rate": 9.621093563260964e-07, + "loss": 0.0018, + "step": 55917 + }, + { + "epoch": 17.27, + "learning_rate": 9.61895327938528e-07, + "loss": 0.0014, + "step": 55918 + }, + { + "epoch": 17.27, + "learning_rate": 9.616813221569044e-07, + "loss": 0.0016, + "step": 55919 + }, + { + "epoch": 17.27, + "learning_rate": 9.614673389817664e-07, + "loss": 0.0018, + "step": 55920 + }, + { + "epoch": 17.27, + "learning_rate": 9.61253378413648e-07, + "loss": 0.0018, + "step": 55921 + }, + { + "epoch": 17.27, + "learning_rate": 9.61039440453081e-07, + "loss": 0.0019, + "step": 55922 + }, + { + "epoch": 17.27, + "learning_rate": 9.608255251006027e-07, + "loss": 0.0019, + "step": 55923 + }, + { + "epoch": 17.27, + "learning_rate": 9.606116323567504e-07, + "loss": 0.002, + "step": 55924 + }, + { + "epoch": 17.27, + "learning_rate": 9.603977622220561e-07, + "loss": 0.0014, + "step": 55925 + }, + { + "epoch": 17.27, + "learning_rate": 9.60183914697057e-07, + "loss": 0.0019, + "step": 55926 + }, + { + "epoch": 17.27, + "learning_rate": 9.599700897822861e-07, + "loss": 0.0021, + "step": 55927 + }, + { + "epoch": 17.27, + "learning_rate": 9.597562874782774e-07, + "loss": 0.0018, + "step": 55928 + }, + { + "epoch": 17.27, + "learning_rate": 9.59542507785567e-07, + "loss": 0.0023, + "step": 55929 + }, + { + "epoch": 17.27, + "learning_rate": 9.593287507046922e-07, + "loss": 0.0019, + "step": 55930 + }, + { + "epoch": 17.27, + "learning_rate": 9.59115016236184e-07, + "loss": 0.0017, + "step": 55931 + }, + { + "epoch": 17.27, + "learning_rate": 9.589013043805773e-07, + "loss": 0.0019, + "step": 55932 + }, + { + "epoch": 17.27, + "learning_rate": 9.586876151384085e-07, + "loss": 0.0016, + "step": 55933 + }, + { + "epoch": 17.27, + "learning_rate": 9.58473948510209e-07, + "loss": 0.0022, + "step": 55934 + }, + { + "epoch": 17.27, + "learning_rate": 9.582603044965155e-07, + "loss": 0.0015, + "step": 55935 + }, + { + "epoch": 17.27, + "learning_rate": 9.58046683097864e-07, + "loss": 0.0017, + "step": 55936 + }, + { + "epoch": 17.27, + "learning_rate": 9.578330843147876e-07, + "loss": 0.0021, + "step": 55937 + }, + { + "epoch": 17.27, + "learning_rate": 9.576195081478168e-07, + "loss": 0.0015, + "step": 55938 + }, + { + "epoch": 17.27, + "learning_rate": 9.574059545974923e-07, + "loss": 0.0014, + "step": 55939 + }, + { + "epoch": 17.28, + "learning_rate": 9.571924236643416e-07, + "loss": 0.003, + "step": 55940 + }, + { + "epoch": 17.28, + "learning_rate": 9.56978915348904e-07, + "loss": 0.0016, + "step": 55941 + }, + { + "epoch": 17.28, + "learning_rate": 9.567654296517115e-07, + "loss": 0.0022, + "step": 55942 + }, + { + "epoch": 17.28, + "learning_rate": 9.56551966573296e-07, + "loss": 0.0017, + "step": 55943 + }, + { + "epoch": 17.28, + "learning_rate": 9.563385261141932e-07, + "loss": 0.0025, + "step": 55944 + }, + { + "epoch": 17.28, + "learning_rate": 9.561251082749379e-07, + "loss": 0.0019, + "step": 55945 + }, + { + "epoch": 17.28, + "learning_rate": 9.559117130560658e-07, + "loss": 0.0015, + "step": 55946 + }, + { + "epoch": 17.28, + "learning_rate": 9.556983404581067e-07, + "loss": 0.0014, + "step": 55947 + }, + { + "epoch": 17.28, + "learning_rate": 9.554849904815943e-07, + "loss": 0.0026, + "step": 55948 + }, + { + "epoch": 17.28, + "learning_rate": 9.552716631270653e-07, + "loss": 0.0015, + "step": 55949 + }, + { + "epoch": 17.28, + "learning_rate": 9.55058358395049e-07, + "loss": 0.0019, + "step": 55950 + }, + { + "epoch": 17.28, + "learning_rate": 9.54845076286085e-07, + "loss": 0.0017, + "step": 55951 + }, + { + "epoch": 17.28, + "learning_rate": 9.546318168007019e-07, + "loss": 0.0014, + "step": 55952 + }, + { + "epoch": 17.28, + "learning_rate": 9.544185799394323e-07, + "loss": 0.0017, + "step": 55953 + }, + { + "epoch": 17.28, + "learning_rate": 9.542053657028127e-07, + "loss": 0.0014, + "step": 55954 + }, + { + "epoch": 17.28, + "learning_rate": 9.53992174091376e-07, + "loss": 0.0022, + "step": 55955 + }, + { + "epoch": 17.28, + "learning_rate": 9.537790051056539e-07, + "loss": 0.0025, + "step": 55956 + }, + { + "epoch": 17.28, + "learning_rate": 9.535658587461816e-07, + "loss": 0.0019, + "step": 55957 + }, + { + "epoch": 17.28, + "learning_rate": 9.533527350134919e-07, + "loss": 0.0017, + "step": 55958 + }, + { + "epoch": 17.28, + "learning_rate": 9.531396339081145e-07, + "loss": 0.0018, + "step": 55959 + }, + { + "epoch": 17.28, + "learning_rate": 9.529265554305844e-07, + "loss": 0.0019, + "step": 55960 + }, + { + "epoch": 17.28, + "learning_rate": 9.52713499581438e-07, + "loss": 0.0024, + "step": 55961 + }, + { + "epoch": 17.28, + "learning_rate": 9.525004663612048e-07, + "loss": 0.0018, + "step": 55962 + }, + { + "epoch": 17.28, + "learning_rate": 9.522874557704165e-07, + "loss": 0.0029, + "step": 55963 + }, + { + "epoch": 17.28, + "learning_rate": 9.520744678096094e-07, + "loss": 0.0016, + "step": 55964 + }, + { + "epoch": 17.28, + "learning_rate": 9.518615024793121e-07, + "loss": 0.0017, + "step": 55965 + }, + { + "epoch": 17.28, + "learning_rate": 9.516485597800595e-07, + "loss": 0.0017, + "step": 55966 + }, + { + "epoch": 17.28, + "learning_rate": 9.514356397123881e-07, + "loss": 0.002, + "step": 55967 + }, + { + "epoch": 17.28, + "learning_rate": 9.512227422768228e-07, + "loss": 0.0018, + "step": 55968 + }, + { + "epoch": 17.28, + "learning_rate": 9.510098674738988e-07, + "loss": 0.0016, + "step": 55969 + }, + { + "epoch": 17.28, + "learning_rate": 9.507970153041523e-07, + "loss": 0.0021, + "step": 55970 + }, + { + "epoch": 17.28, + "learning_rate": 9.505841857681108e-07, + "loss": 0.0018, + "step": 55971 + }, + { + "epoch": 17.29, + "learning_rate": 9.503713788663116e-07, + "loss": 0.0021, + "step": 55972 + }, + { + "epoch": 17.29, + "learning_rate": 9.501585945992831e-07, + "loss": 0.0025, + "step": 55973 + }, + { + "epoch": 17.29, + "learning_rate": 9.499458329675571e-07, + "loss": 0.0018, + "step": 55974 + }, + { + "epoch": 17.29, + "learning_rate": 9.497330939716665e-07, + "loss": 0.001, + "step": 55975 + }, + { + "epoch": 17.29, + "learning_rate": 9.495203776121453e-07, + "loss": 0.0016, + "step": 55976 + }, + { + "epoch": 17.29, + "learning_rate": 9.493076838895266e-07, + "loss": 0.0022, + "step": 55977 + }, + { + "epoch": 17.29, + "learning_rate": 9.490950128043375e-07, + "loss": 0.0021, + "step": 55978 + }, + { + "epoch": 17.29, + "learning_rate": 9.488823643571122e-07, + "loss": 0.0017, + "step": 55979 + }, + { + "epoch": 17.29, + "learning_rate": 9.486697385483845e-07, + "loss": 0.0017, + "step": 55980 + }, + { + "epoch": 17.29, + "learning_rate": 9.484571353786831e-07, + "loss": 0.0025, + "step": 55981 + }, + { + "epoch": 17.29, + "learning_rate": 9.482445548485442e-07, + "loss": 0.0012, + "step": 55982 + }, + { + "epoch": 17.29, + "learning_rate": 9.480319969584951e-07, + "loss": 0.0019, + "step": 55983 + }, + { + "epoch": 17.29, + "learning_rate": 9.478194617090675e-07, + "loss": 0.0016, + "step": 55984 + }, + { + "epoch": 17.29, + "learning_rate": 9.476069491007944e-07, + "loss": 0.0014, + "step": 55985 + }, + { + "epoch": 17.29, + "learning_rate": 9.473944591342099e-07, + "loss": 0.003, + "step": 55986 + }, + { + "epoch": 17.29, + "learning_rate": 9.471819918098424e-07, + "loss": 0.0022, + "step": 55987 + }, + { + "epoch": 17.29, + "learning_rate": 9.469695471282214e-07, + "loss": 0.0013, + "step": 55988 + }, + { + "epoch": 17.29, + "learning_rate": 9.467571250898833e-07, + "loss": 0.002, + "step": 55989 + }, + { + "epoch": 17.29, + "learning_rate": 9.465447256953553e-07, + "loss": 0.0022, + "step": 55990 + }, + { + "epoch": 17.29, + "learning_rate": 9.463323489451692e-07, + "loss": 0.0031, + "step": 55991 + }, + { + "epoch": 17.29, + "learning_rate": 9.461199948398603e-07, + "loss": 0.0024, + "step": 55992 + }, + { + "epoch": 17.29, + "learning_rate": 9.459076633799558e-07, + "loss": 0.0023, + "step": 55993 + }, + { + "epoch": 17.29, + "learning_rate": 9.456953545659863e-07, + "loss": 0.0019, + "step": 55994 + }, + { + "epoch": 17.29, + "learning_rate": 9.45483068398485e-07, + "loss": 0.0017, + "step": 55995 + }, + { + "epoch": 17.29, + "learning_rate": 9.452708048779813e-07, + "loss": 0.0025, + "step": 55996 + }, + { + "epoch": 17.29, + "learning_rate": 9.450585640050081e-07, + "loss": 0.0018, + "step": 55997 + }, + { + "epoch": 17.29, + "learning_rate": 9.448463457800939e-07, + "loss": 0.0019, + "step": 55998 + }, + { + "epoch": 17.29, + "learning_rate": 9.446341502037703e-07, + "loss": 0.0016, + "step": 55999 + }, + { + "epoch": 17.29, + "learning_rate": 9.444219772765673e-07, + "loss": 0.0016, + "step": 56000 + }, + { + "epoch": 17.29, + "learning_rate": 9.442098269990186e-07, + "loss": 0.0017, + "step": 56001 + }, + { + "epoch": 17.29, + "learning_rate": 9.439976993716515e-07, + "loss": 0.0019, + "step": 56002 + }, + { + "epoch": 17.29, + "learning_rate": 9.437855943949992e-07, + "loss": 0.0021, + "step": 56003 + }, + { + "epoch": 17.3, + "learning_rate": 9.435735120695911e-07, + "loss": 0.0024, + "step": 56004 + }, + { + "epoch": 17.3, + "learning_rate": 9.433614523959556e-07, + "loss": 0.0016, + "step": 56005 + }, + { + "epoch": 17.3, + "learning_rate": 9.431494153746246e-07, + "loss": 0.0021, + "step": 56006 + }, + { + "epoch": 17.3, + "learning_rate": 9.42937401006131e-07, + "loss": 0.0015, + "step": 56007 + }, + { + "epoch": 17.3, + "learning_rate": 9.427254092910032e-07, + "loss": 0.0018, + "step": 56008 + }, + { + "epoch": 17.3, + "learning_rate": 9.425134402297686e-07, + "loss": 0.0018, + "step": 56009 + }, + { + "epoch": 17.3, + "learning_rate": 9.423014938229602e-07, + "loss": 0.0021, + "step": 56010 + }, + { + "epoch": 17.3, + "learning_rate": 9.420895700711097e-07, + "loss": 0.0019, + "step": 56011 + }, + { + "epoch": 17.3, + "learning_rate": 9.418776689747433e-07, + "loss": 0.0019, + "step": 56012 + }, + { + "epoch": 17.3, + "learning_rate": 9.41665790534394e-07, + "loss": 0.0017, + "step": 56013 + }, + { + "epoch": 17.3, + "learning_rate": 9.414539347505913e-07, + "loss": 0.002, + "step": 56014 + }, + { + "epoch": 17.3, + "learning_rate": 9.412421016238627e-07, + "loss": 0.0015, + "step": 56015 + }, + { + "epoch": 17.3, + "learning_rate": 9.410302911547397e-07, + "loss": 0.0028, + "step": 56016 + }, + { + "epoch": 17.3, + "learning_rate": 9.408185033437545e-07, + "loss": 0.0016, + "step": 56017 + }, + { + "epoch": 17.3, + "learning_rate": 9.406067381914341e-07, + "loss": 0.002, + "step": 56018 + }, + { + "epoch": 17.3, + "learning_rate": 9.403949956983072e-07, + "loss": 0.0014, + "step": 56019 + }, + { + "epoch": 17.3, + "learning_rate": 9.401832758649065e-07, + "loss": 0.0019, + "step": 56020 + }, + { + "epoch": 17.3, + "learning_rate": 9.399715786917573e-07, + "loss": 0.0017, + "step": 56021 + }, + { + "epoch": 17.3, + "learning_rate": 9.397599041793926e-07, + "loss": 0.002, + "step": 56022 + }, + { + "epoch": 17.3, + "learning_rate": 9.395482523283417e-07, + "loss": 0.0021, + "step": 56023 + }, + { + "epoch": 17.3, + "learning_rate": 9.393366231391332e-07, + "loss": 0.0018, + "step": 56024 + }, + { + "epoch": 17.3, + "learning_rate": 9.391250166122956e-07, + "loss": 0.0019, + "step": 56025 + }, + { + "epoch": 17.3, + "learning_rate": 9.389134327483596e-07, + "loss": 0.0017, + "step": 56026 + }, + { + "epoch": 17.3, + "learning_rate": 9.387018715478525e-07, + "loss": 0.0019, + "step": 56027 + }, + { + "epoch": 17.3, + "learning_rate": 9.384903330113071e-07, + "loss": 0.0014, + "step": 56028 + }, + { + "epoch": 17.3, + "learning_rate": 9.382788171392487e-07, + "loss": 0.0016, + "step": 56029 + }, + { + "epoch": 17.3, + "learning_rate": 9.380673239322069e-07, + "loss": 0.0013, + "step": 56030 + }, + { + "epoch": 17.3, + "learning_rate": 9.378558533907112e-07, + "loss": 0.0024, + "step": 56031 + }, + { + "epoch": 17.3, + "learning_rate": 9.376444055152933e-07, + "loss": 0.0018, + "step": 56032 + }, + { + "epoch": 17.3, + "learning_rate": 9.374329803064763e-07, + "loss": 0.0013, + "step": 56033 + }, + { + "epoch": 17.3, + "learning_rate": 9.372215777647953e-07, + "loss": 0.0015, + "step": 56034 + }, + { + "epoch": 17.3, + "learning_rate": 9.370101978907764e-07, + "loss": 0.0013, + "step": 56035 + }, + { + "epoch": 17.3, + "learning_rate": 9.36798840684946e-07, + "loss": 0.0015, + "step": 56036 + }, + { + "epoch": 17.31, + "learning_rate": 9.365875061478336e-07, + "loss": 0.0016, + "step": 56037 + }, + { + "epoch": 17.31, + "learning_rate": 9.363761942799721e-07, + "loss": 0.0022, + "step": 56038 + }, + { + "epoch": 17.31, + "learning_rate": 9.361649050818855e-07, + "loss": 0.002, + "step": 56039 + }, + { + "epoch": 17.31, + "learning_rate": 9.359536385541024e-07, + "loss": 0.0018, + "step": 56040 + }, + { + "epoch": 17.31, + "learning_rate": 9.357423946971534e-07, + "loss": 0.0014, + "step": 56041 + }, + { + "epoch": 17.31, + "learning_rate": 9.355311735115669e-07, + "loss": 0.0017, + "step": 56042 + }, + { + "epoch": 17.31, + "learning_rate": 9.353199749978681e-07, + "loss": 0.0011, + "step": 56043 + }, + { + "epoch": 17.31, + "learning_rate": 9.351087991565889e-07, + "loss": 0.0021, + "step": 56044 + }, + { + "epoch": 17.31, + "learning_rate": 9.348976459882564e-07, + "loss": 0.0026, + "step": 56045 + }, + { + "epoch": 17.31, + "learning_rate": 9.34686515493397e-07, + "loss": 0.0021, + "step": 56046 + }, + { + "epoch": 17.31, + "learning_rate": 9.344754076725393e-07, + "loss": 0.0015, + "step": 56047 + }, + { + "epoch": 17.31, + "learning_rate": 9.342643225262138e-07, + "loss": 0.002, + "step": 56048 + }, + { + "epoch": 17.31, + "learning_rate": 9.340532600549468e-07, + "loss": 0.0016, + "step": 56049 + }, + { + "epoch": 17.31, + "learning_rate": 9.338422202592645e-07, + "loss": 0.0027, + "step": 56050 + }, + { + "epoch": 17.31, + "learning_rate": 9.336312031396988e-07, + "loss": 0.0012, + "step": 56051 + }, + { + "epoch": 17.31, + "learning_rate": 9.334202086967725e-07, + "loss": 0.002, + "step": 56052 + }, + { + "epoch": 17.31, + "learning_rate": 9.332092369310153e-07, + "loss": 0.0015, + "step": 56053 + }, + { + "epoch": 17.31, + "learning_rate": 9.329982878429589e-07, + "loss": 0.0019, + "step": 56054 + }, + { + "epoch": 17.31, + "learning_rate": 9.327873614331262e-07, + "loss": 0.0011, + "step": 56055 + }, + { + "epoch": 17.31, + "learning_rate": 9.325764577020446e-07, + "loss": 0.0016, + "step": 56056 + }, + { + "epoch": 17.31, + "learning_rate": 9.323655766502449e-07, + "loss": 0.0022, + "step": 56057 + }, + { + "epoch": 17.31, + "learning_rate": 9.321547182782509e-07, + "loss": 0.002, + "step": 56058 + }, + { + "epoch": 17.31, + "learning_rate": 9.319438825865934e-07, + "loss": 0.0018, + "step": 56059 + }, + { + "epoch": 17.31, + "learning_rate": 9.317330695757987e-07, + "loss": 0.0016, + "step": 56060 + }, + { + "epoch": 17.31, + "learning_rate": 9.315222792463919e-07, + "loss": 0.0015, + "step": 56061 + }, + { + "epoch": 17.31, + "learning_rate": 9.313115115989013e-07, + "loss": 0.0015, + "step": 56062 + }, + { + "epoch": 17.31, + "learning_rate": 9.311007666338568e-07, + "loss": 0.002, + "step": 56063 + }, + { + "epoch": 17.31, + "learning_rate": 9.30890044351781e-07, + "loss": 0.0019, + "step": 56064 + }, + { + "epoch": 17.31, + "learning_rate": 9.306793447532059e-07, + "loss": 0.0013, + "step": 56065 + }, + { + "epoch": 17.31, + "learning_rate": 9.304686678386554e-07, + "loss": 0.0019, + "step": 56066 + }, + { + "epoch": 17.31, + "learning_rate": 9.302580136086548e-07, + "loss": 0.0016, + "step": 56067 + }, + { + "epoch": 17.31, + "learning_rate": 9.300473820637334e-07, + "loss": 0.0021, + "step": 56068 + }, + { + "epoch": 17.32, + "learning_rate": 9.2983677320442e-07, + "loss": 0.0016, + "step": 56069 + }, + { + "epoch": 17.32, + "learning_rate": 9.296261870312384e-07, + "loss": 0.002, + "step": 56070 + }, + { + "epoch": 17.32, + "learning_rate": 9.294156235447149e-07, + "loss": 0.0015, + "step": 56071 + }, + { + "epoch": 17.32, + "learning_rate": 9.292050827453791e-07, + "loss": 0.0015, + "step": 56072 + }, + { + "epoch": 17.32, + "learning_rate": 9.289945646337528e-07, + "loss": 0.0016, + "step": 56073 + }, + { + "epoch": 17.32, + "learning_rate": 9.287840692103667e-07, + "loss": 0.0017, + "step": 56074 + }, + { + "epoch": 17.32, + "learning_rate": 9.28573596475748e-07, + "loss": 0.0016, + "step": 56075 + }, + { + "epoch": 17.32, + "learning_rate": 9.283631464304211e-07, + "loss": 0.0017, + "step": 56076 + }, + { + "epoch": 17.32, + "learning_rate": 9.281527190749107e-07, + "loss": 0.0029, + "step": 56077 + }, + { + "epoch": 17.32, + "learning_rate": 9.279423144097444e-07, + "loss": 0.0021, + "step": 56078 + }, + { + "epoch": 17.32, + "learning_rate": 9.277319324354517e-07, + "loss": 0.0014, + "step": 56079 + }, + { + "epoch": 17.32, + "learning_rate": 9.275215731525555e-07, + "loss": 0.0023, + "step": 56080 + }, + { + "epoch": 17.32, + "learning_rate": 9.27311236561581e-07, + "loss": 0.0018, + "step": 56081 + }, + { + "epoch": 17.32, + "learning_rate": 9.271009226630567e-07, + "loss": 0.002, + "step": 56082 + }, + { + "epoch": 17.32, + "learning_rate": 9.268906314575077e-07, + "loss": 0.0017, + "step": 56083 + }, + { + "epoch": 17.32, + "learning_rate": 9.26680362945459e-07, + "loss": 0.0016, + "step": 56084 + }, + { + "epoch": 17.32, + "learning_rate": 9.264701171274415e-07, + "loss": 0.0016, + "step": 56085 + }, + { + "epoch": 17.32, + "learning_rate": 9.262598940039736e-07, + "loss": 0.0016, + "step": 56086 + }, + { + "epoch": 17.32, + "learning_rate": 9.260496935755836e-07, + "loss": 0.0013, + "step": 56087 + }, + { + "epoch": 17.32, + "learning_rate": 9.258395158428012e-07, + "loss": 0.0025, + "step": 56088 + }, + { + "epoch": 17.32, + "learning_rate": 9.256293608061473e-07, + "loss": 0.0013, + "step": 56089 + }, + { + "epoch": 17.32, + "learning_rate": 9.254192284661512e-07, + "loss": 0.0021, + "step": 56090 + }, + { + "epoch": 17.32, + "learning_rate": 9.25209118823337e-07, + "loss": 0.0017, + "step": 56091 + }, + { + "epoch": 17.32, + "learning_rate": 9.249990318782276e-07, + "loss": 0.0018, + "step": 56092 + }, + { + "epoch": 17.32, + "learning_rate": 9.247889676313504e-07, + "loss": 0.0019, + "step": 56093 + }, + { + "epoch": 17.32, + "learning_rate": 9.245789260832338e-07, + "loss": 0.0021, + "step": 56094 + }, + { + "epoch": 17.32, + "learning_rate": 9.243689072343987e-07, + "loss": 0.002, + "step": 56095 + }, + { + "epoch": 17.32, + "learning_rate": 9.241589110853744e-07, + "loss": 0.0017, + "step": 56096 + }, + { + "epoch": 17.32, + "learning_rate": 9.239489376366828e-07, + "loss": 0.0025, + "step": 56097 + }, + { + "epoch": 17.32, + "learning_rate": 9.237389868888491e-07, + "loss": 0.0018, + "step": 56098 + }, + { + "epoch": 17.32, + "learning_rate": 9.235290588423996e-07, + "loss": 0.0028, + "step": 56099 + }, + { + "epoch": 17.32, + "learning_rate": 9.233191534978614e-07, + "loss": 0.0018, + "step": 56100 + }, + { + "epoch": 17.32, + "learning_rate": 9.231092708557577e-07, + "loss": 0.002, + "step": 56101 + }, + { + "epoch": 17.33, + "learning_rate": 9.228994109166112e-07, + "loss": 0.002, + "step": 56102 + }, + { + "epoch": 17.33, + "learning_rate": 9.226895736809505e-07, + "loss": 0.0018, + "step": 56103 + }, + { + "epoch": 17.33, + "learning_rate": 9.224797591492962e-07, + "loss": 0.0019, + "step": 56104 + }, + { + "epoch": 17.33, + "learning_rate": 9.222699673221769e-07, + "loss": 0.0012, + "step": 56105 + }, + { + "epoch": 17.33, + "learning_rate": 9.220601982001187e-07, + "loss": 0.0018, + "step": 56106 + }, + { + "epoch": 17.33, + "learning_rate": 9.218504517836413e-07, + "loss": 0.0015, + "step": 56107 + }, + { + "epoch": 17.33, + "learning_rate": 9.216407280732709e-07, + "loss": 0.0017, + "step": 56108 + }, + { + "epoch": 17.33, + "learning_rate": 9.214310270695326e-07, + "loss": 0.002, + "step": 56109 + }, + { + "epoch": 17.33, + "learning_rate": 9.212213487729526e-07, + "loss": 0.0017, + "step": 56110 + }, + { + "epoch": 17.33, + "learning_rate": 9.210116931840552e-07, + "loss": 0.0024, + "step": 56111 + }, + { + "epoch": 17.33, + "learning_rate": 9.208020603033607e-07, + "loss": 0.0014, + "step": 56112 + }, + { + "epoch": 17.33, + "learning_rate": 9.205924501313978e-07, + "loss": 0.002, + "step": 56113 + }, + { + "epoch": 17.33, + "learning_rate": 9.203828626686884e-07, + "loss": 0.0015, + "step": 56114 + }, + { + "epoch": 17.33, + "learning_rate": 9.201732979157562e-07, + "loss": 0.0015, + "step": 56115 + }, + { + "epoch": 17.33, + "learning_rate": 9.199637558731311e-07, + "loss": 0.0014, + "step": 56116 + }, + { + "epoch": 17.33, + "learning_rate": 9.197542365413292e-07, + "loss": 0.0017, + "step": 56117 + }, + { + "epoch": 17.33, + "learning_rate": 9.195447399208779e-07, + "loss": 0.0032, + "step": 56118 + }, + { + "epoch": 17.33, + "learning_rate": 9.193352660123034e-07, + "loss": 0.0021, + "step": 56119 + }, + { + "epoch": 17.33, + "learning_rate": 9.191258148161253e-07, + "loss": 0.0024, + "step": 56120 + }, + { + "epoch": 17.33, + "learning_rate": 9.18916386332872e-07, + "loss": 0.0016, + "step": 56121 + }, + { + "epoch": 17.33, + "learning_rate": 9.187069805630644e-07, + "loss": 0.0019, + "step": 56122 + }, + { + "epoch": 17.33, + "learning_rate": 9.184975975072252e-07, + "loss": 0.0016, + "step": 56123 + }, + { + "epoch": 17.33, + "learning_rate": 9.182882371658808e-07, + "loss": 0.0021, + "step": 56124 + }, + { + "epoch": 17.33, + "learning_rate": 9.180788995395551e-07, + "loss": 0.0016, + "step": 56125 + }, + { + "epoch": 17.33, + "learning_rate": 9.178695846287711e-07, + "loss": 0.0022, + "step": 56126 + }, + { + "epoch": 17.33, + "learning_rate": 9.176602924340494e-07, + "loss": 0.002, + "step": 56127 + }, + { + "epoch": 17.33, + "learning_rate": 9.174510229559174e-07, + "loss": 0.0016, + "step": 56128 + }, + { + "epoch": 17.33, + "learning_rate": 9.172417761948959e-07, + "loss": 0.0012, + "step": 56129 + }, + { + "epoch": 17.33, + "learning_rate": 9.170325521515089e-07, + "loss": 0.0024, + "step": 56130 + }, + { + "epoch": 17.33, + "learning_rate": 9.168233508262813e-07, + "loss": 0.0019, + "step": 56131 + }, + { + "epoch": 17.33, + "learning_rate": 9.166141722197363e-07, + "loss": 0.0022, + "step": 56132 + }, + { + "epoch": 17.33, + "learning_rate": 9.164050163323934e-07, + "loss": 0.0014, + "step": 56133 + }, + { + "epoch": 17.34, + "learning_rate": 9.161958831647799e-07, + "loss": 0.0015, + "step": 56134 + }, + { + "epoch": 17.34, + "learning_rate": 9.159867727174166e-07, + "loss": 0.0022, + "step": 56135 + }, + { + "epoch": 17.34, + "learning_rate": 9.157776849908285e-07, + "loss": 0.0024, + "step": 56136 + }, + { + "epoch": 17.34, + "learning_rate": 9.155686199855362e-07, + "loss": 0.0018, + "step": 56137 + }, + { + "epoch": 17.34, + "learning_rate": 9.15359577702063e-07, + "loss": 0.0012, + "step": 56138 + }, + { + "epoch": 17.34, + "learning_rate": 9.151505581409326e-07, + "loss": 0.0017, + "step": 56139 + }, + { + "epoch": 17.34, + "learning_rate": 9.149415613026669e-07, + "loss": 0.0019, + "step": 56140 + }, + { + "epoch": 17.34, + "learning_rate": 9.147325871877921e-07, + "loss": 0.0018, + "step": 56141 + }, + { + "epoch": 17.34, + "learning_rate": 9.145236357968268e-07, + "loss": 0.0022, + "step": 56142 + }, + { + "epoch": 17.34, + "learning_rate": 9.143147071302939e-07, + "loss": 0.0015, + "step": 56143 + }, + { + "epoch": 17.34, + "learning_rate": 9.141058011887194e-07, + "loss": 0.0027, + "step": 56144 + }, + { + "epoch": 17.34, + "learning_rate": 9.138969179726209e-07, + "loss": 0.0019, + "step": 56145 + }, + { + "epoch": 17.34, + "learning_rate": 9.136880574825258e-07, + "loss": 0.0016, + "step": 56146 + }, + { + "epoch": 17.34, + "learning_rate": 9.134792197189534e-07, + "loss": 0.0026, + "step": 56147 + }, + { + "epoch": 17.34, + "learning_rate": 9.132704046824248e-07, + "loss": 0.0014, + "step": 56148 + }, + { + "epoch": 17.34, + "learning_rate": 9.130616123734648e-07, + "loss": 0.0013, + "step": 56149 + }, + { + "epoch": 17.34, + "learning_rate": 9.128528427925965e-07, + "loss": 0.0014, + "step": 56150 + }, + { + "epoch": 17.34, + "learning_rate": 9.126440959403393e-07, + "loss": 0.002, + "step": 56151 + }, + { + "epoch": 17.34, + "learning_rate": 9.124353718172186e-07, + "loss": 0.0015, + "step": 56152 + }, + { + "epoch": 17.34, + "learning_rate": 9.122266704237536e-07, + "loss": 0.0019, + "step": 56153 + }, + { + "epoch": 17.34, + "learning_rate": 9.120179917604666e-07, + "loss": 0.0031, + "step": 56154 + }, + { + "epoch": 17.34, + "learning_rate": 9.11809335827879e-07, + "loss": 0.0019, + "step": 56155 + }, + { + "epoch": 17.34, + "learning_rate": 9.116007026265162e-07, + "loss": 0.0023, + "step": 56156 + }, + { + "epoch": 17.34, + "learning_rate": 9.113920921568975e-07, + "loss": 0.0019, + "step": 56157 + }, + { + "epoch": 17.34, + "learning_rate": 9.111835044195438e-07, + "loss": 0.0018, + "step": 56158 + }, + { + "epoch": 17.34, + "learning_rate": 9.109749394149792e-07, + "loss": 0.0019, + "step": 56159 + }, + { + "epoch": 17.34, + "learning_rate": 9.107663971437219e-07, + "loss": 0.0018, + "step": 56160 + }, + { + "epoch": 17.34, + "learning_rate": 9.105578776062951e-07, + "loss": 0.0015, + "step": 56161 + }, + { + "epoch": 17.34, + "learning_rate": 9.103493808032237e-07, + "loss": 0.0022, + "step": 56162 + }, + { + "epoch": 17.34, + "learning_rate": 9.101409067350254e-07, + "loss": 0.0017, + "step": 56163 + }, + { + "epoch": 17.34, + "learning_rate": 9.099324554022215e-07, + "loss": 0.002, + "step": 56164 + }, + { + "epoch": 17.34, + "learning_rate": 9.097240268053364e-07, + "loss": 0.0021, + "step": 56165 + }, + { + "epoch": 17.35, + "learning_rate": 9.095156209448874e-07, + "loss": 0.0021, + "step": 56166 + }, + { + "epoch": 17.35, + "learning_rate": 9.093072378213996e-07, + "loss": 0.0015, + "step": 56167 + }, + { + "epoch": 17.35, + "learning_rate": 9.090988774353926e-07, + "loss": 0.0016, + "step": 56168 + }, + { + "epoch": 17.35, + "learning_rate": 9.088905397873849e-07, + "loss": 0.0019, + "step": 56169 + }, + { + "epoch": 17.35, + "learning_rate": 9.086822248779004e-07, + "loss": 0.0026, + "step": 56170 + }, + { + "epoch": 17.35, + "learning_rate": 9.084739327074621e-07, + "loss": 0.002, + "step": 56171 + }, + { + "epoch": 17.35, + "learning_rate": 9.082656632765862e-07, + "loss": 0.0029, + "step": 56172 + }, + { + "epoch": 17.35, + "learning_rate": 9.080574165857981e-07, + "loss": 0.0014, + "step": 56173 + }, + { + "epoch": 17.35, + "learning_rate": 9.078491926356147e-07, + "loss": 0.0017, + "step": 56174 + }, + { + "epoch": 17.35, + "learning_rate": 9.076409914265616e-07, + "loss": 0.0019, + "step": 56175 + }, + { + "epoch": 17.35, + "learning_rate": 9.074328129591536e-07, + "loss": 0.0018, + "step": 56176 + }, + { + "epoch": 17.35, + "learning_rate": 9.072246572339172e-07, + "loss": 0.0023, + "step": 56177 + }, + { + "epoch": 17.35, + "learning_rate": 9.070165242513707e-07, + "loss": 0.002, + "step": 56178 + }, + { + "epoch": 17.35, + "learning_rate": 9.068084140120314e-07, + "loss": 0.0015, + "step": 56179 + }, + { + "epoch": 17.35, + "learning_rate": 9.066003265164236e-07, + "loss": 0.0014, + "step": 56180 + }, + { + "epoch": 17.35, + "learning_rate": 9.063922617650678e-07, + "loss": 0.0015, + "step": 56181 + }, + { + "epoch": 17.35, + "learning_rate": 9.061842197584825e-07, + "loss": 0.0024, + "step": 56182 + }, + { + "epoch": 17.35, + "learning_rate": 9.059762004971906e-07, + "loss": 0.0024, + "step": 56183 + }, + { + "epoch": 17.35, + "learning_rate": 9.057682039817106e-07, + "loss": 0.0024, + "step": 56184 + }, + { + "epoch": 17.35, + "learning_rate": 9.055602302125621e-07, + "loss": 0.0019, + "step": 56185 + }, + { + "epoch": 17.35, + "learning_rate": 9.053522791902658e-07, + "loss": 0.0024, + "step": 56186 + }, + { + "epoch": 17.35, + "learning_rate": 9.051443509153435e-07, + "loss": 0.0019, + "step": 56187 + }, + { + "epoch": 17.35, + "learning_rate": 9.049364453883147e-07, + "loss": 0.0018, + "step": 56188 + }, + { + "epoch": 17.35, + "learning_rate": 9.047285626096957e-07, + "loss": 0.0017, + "step": 56189 + }, + { + "epoch": 17.35, + "learning_rate": 9.045207025800129e-07, + "loss": 0.0016, + "step": 56190 + }, + { + "epoch": 17.35, + "learning_rate": 9.043128652997801e-07, + "loss": 0.0024, + "step": 56191 + }, + { + "epoch": 17.35, + "learning_rate": 9.041050507695192e-07, + "loss": 0.0018, + "step": 56192 + }, + { + "epoch": 17.35, + "learning_rate": 9.038972589897532e-07, + "loss": 0.0017, + "step": 56193 + }, + { + "epoch": 17.35, + "learning_rate": 9.036894899609993e-07, + "loss": 0.0022, + "step": 56194 + }, + { + "epoch": 17.35, + "learning_rate": 9.03481743683774e-07, + "loss": 0.0015, + "step": 56195 + }, + { + "epoch": 17.35, + "learning_rate": 9.032740201586032e-07, + "loss": 0.0025, + "step": 56196 + }, + { + "epoch": 17.35, + "learning_rate": 9.030663193860012e-07, + "loss": 0.0023, + "step": 56197 + }, + { + "epoch": 17.35, + "learning_rate": 9.028586413664908e-07, + "loss": 0.0017, + "step": 56198 + }, + { + "epoch": 17.36, + "learning_rate": 9.026509861005894e-07, + "loss": 0.0014, + "step": 56199 + }, + { + "epoch": 17.36, + "learning_rate": 9.024433535888166e-07, + "loss": 0.0019, + "step": 56200 + }, + { + "epoch": 17.36, + "learning_rate": 9.02235743831692e-07, + "loss": 0.0017, + "step": 56201 + }, + { + "epoch": 17.36, + "learning_rate": 9.020281568297373e-07, + "loss": 0.0026, + "step": 56202 + }, + { + "epoch": 17.36, + "learning_rate": 9.018205925834666e-07, + "loss": 0.0021, + "step": 56203 + }, + { + "epoch": 17.36, + "learning_rate": 9.016130510934052e-07, + "loss": 0.0022, + "step": 56204 + }, + { + "epoch": 17.36, + "learning_rate": 9.014055323600657e-07, + "loss": 0.0023, + "step": 56205 + }, + { + "epoch": 17.36, + "learning_rate": 9.011980363839734e-07, + "loss": 0.0012, + "step": 56206 + }, + { + "epoch": 17.36, + "learning_rate": 9.009905631656424e-07, + "loss": 0.0013, + "step": 56207 + }, + { + "epoch": 17.36, + "learning_rate": 9.007831127055944e-07, + "loss": 0.0016, + "step": 56208 + }, + { + "epoch": 17.36, + "learning_rate": 9.00575685004349e-07, + "loss": 0.0017, + "step": 56209 + }, + { + "epoch": 17.36, + "learning_rate": 9.003682800624203e-07, + "loss": 0.0015, + "step": 56210 + }, + { + "epoch": 17.36, + "learning_rate": 9.001608978803311e-07, + "loss": 0.0017, + "step": 56211 + }, + { + "epoch": 17.36, + "learning_rate": 8.999535384586e-07, + "loss": 0.0015, + "step": 56212 + }, + { + "epoch": 17.36, + "learning_rate": 8.997462017977432e-07, + "loss": 0.0024, + "step": 56213 + }, + { + "epoch": 17.36, + "learning_rate": 8.995388878982836e-07, + "loss": 0.0013, + "step": 56214 + }, + { + "epoch": 17.36, + "learning_rate": 8.993315967607363e-07, + "loss": 0.0018, + "step": 56215 + }, + { + "epoch": 17.36, + "learning_rate": 8.9912432838562e-07, + "loss": 0.0018, + "step": 56216 + }, + { + "epoch": 17.36, + "learning_rate": 8.989170827734517e-07, + "loss": 0.0018, + "step": 56217 + }, + { + "epoch": 17.36, + "learning_rate": 8.987098599247545e-07, + "loss": 0.0033, + "step": 56218 + }, + { + "epoch": 17.36, + "learning_rate": 8.985026598400448e-07, + "loss": 0.0015, + "step": 56219 + }, + { + "epoch": 17.36, + "learning_rate": 8.982954825198365e-07, + "loss": 0.0022, + "step": 56220 + }, + { + "epoch": 17.36, + "learning_rate": 8.980883279646546e-07, + "loss": 0.0013, + "step": 56221 + }, + { + "epoch": 17.36, + "learning_rate": 8.978811961750111e-07, + "loss": 0.0016, + "step": 56222 + }, + { + "epoch": 17.36, + "learning_rate": 8.976740871514266e-07, + "loss": 0.0015, + "step": 56223 + }, + { + "epoch": 17.36, + "learning_rate": 8.974670008944241e-07, + "loss": 0.0019, + "step": 56224 + }, + { + "epoch": 17.36, + "learning_rate": 8.972599374045121e-07, + "loss": 0.002, + "step": 56225 + }, + { + "epoch": 17.36, + "learning_rate": 8.970528966822134e-07, + "loss": 0.0015, + "step": 56226 + }, + { + "epoch": 17.36, + "learning_rate": 8.968458787280476e-07, + "loss": 0.0021, + "step": 56227 + }, + { + "epoch": 17.36, + "learning_rate": 8.966388835425299e-07, + "loss": 0.002, + "step": 56228 + }, + { + "epoch": 17.36, + "learning_rate": 8.964319111261788e-07, + "loss": 0.002, + "step": 56229 + }, + { + "epoch": 17.36, + "learning_rate": 8.962249614795127e-07, + "loss": 0.0015, + "step": 56230 + }, + { + "epoch": 17.37, + "learning_rate": 8.960180346030467e-07, + "loss": 0.0016, + "step": 56231 + }, + { + "epoch": 17.37, + "learning_rate": 8.958111304972994e-07, + "loss": 0.0016, + "step": 56232 + }, + { + "epoch": 17.37, + "learning_rate": 8.956042491627915e-07, + "loss": 0.0014, + "step": 56233 + }, + { + "epoch": 17.37, + "learning_rate": 8.953973906000379e-07, + "loss": 0.0015, + "step": 56234 + }, + { + "epoch": 17.37, + "learning_rate": 8.951905548095541e-07, + "loss": 0.0016, + "step": 56235 + }, + { + "epoch": 17.37, + "learning_rate": 8.949837417918605e-07, + "loss": 0.0022, + "step": 56236 + }, + { + "epoch": 17.37, + "learning_rate": 8.947769515474725e-07, + "loss": 0.002, + "step": 56237 + }, + { + "epoch": 17.37, + "learning_rate": 8.945701840769072e-07, + "loss": 0.002, + "step": 56238 + }, + { + "epoch": 17.37, + "learning_rate": 8.943634393806844e-07, + "loss": 0.002, + "step": 56239 + }, + { + "epoch": 17.37, + "learning_rate": 8.941567174593202e-07, + "loss": 0.0016, + "step": 56240 + }, + { + "epoch": 17.37, + "learning_rate": 8.939500183133276e-07, + "loss": 0.0016, + "step": 56241 + }, + { + "epoch": 17.37, + "learning_rate": 8.937433419432285e-07, + "loss": 0.0016, + "step": 56242 + }, + { + "epoch": 17.37, + "learning_rate": 8.935366883495388e-07, + "loss": 0.0016, + "step": 56243 + }, + { + "epoch": 17.37, + "learning_rate": 8.933300575327752e-07, + "loss": 0.0015, + "step": 56244 + }, + { + "epoch": 17.37, + "learning_rate": 8.931234494934526e-07, + "loss": 0.0014, + "step": 56245 + }, + { + "epoch": 17.37, + "learning_rate": 8.929168642320907e-07, + "loss": 0.0014, + "step": 56246 + }, + { + "epoch": 17.37, + "learning_rate": 8.927103017492023e-07, + "loss": 0.0016, + "step": 56247 + }, + { + "epoch": 17.37, + "learning_rate": 8.92503762045307e-07, + "loss": 0.0015, + "step": 56248 + }, + { + "epoch": 17.37, + "learning_rate": 8.922972451209234e-07, + "loss": 0.0018, + "step": 56249 + }, + { + "epoch": 17.37, + "learning_rate": 8.920907509765653e-07, + "loss": 0.0018, + "step": 56250 + }, + { + "epoch": 17.37, + "learning_rate": 8.918842796127469e-07, + "loss": 0.0023, + "step": 56251 + }, + { + "epoch": 17.37, + "learning_rate": 8.916778310299889e-07, + "loss": 0.0024, + "step": 56252 + }, + { + "epoch": 17.37, + "learning_rate": 8.914714052288042e-07, + "loss": 0.0027, + "step": 56253 + }, + { + "epoch": 17.37, + "learning_rate": 8.912650022097135e-07, + "loss": 0.0022, + "step": 56254 + }, + { + "epoch": 17.37, + "learning_rate": 8.910586219732298e-07, + "loss": 0.0013, + "step": 56255 + }, + { + "epoch": 17.37, + "learning_rate": 8.90852264519868e-07, + "loss": 0.0016, + "step": 56256 + }, + { + "epoch": 17.37, + "learning_rate": 8.906459298501457e-07, + "loss": 0.0015, + "step": 56257 + }, + { + "epoch": 17.37, + "learning_rate": 8.904396179645825e-07, + "loss": 0.0014, + "step": 56258 + }, + { + "epoch": 17.37, + "learning_rate": 8.902333288636878e-07, + "loss": 0.0021, + "step": 56259 + }, + { + "epoch": 17.37, + "learning_rate": 8.900270625479835e-07, + "loss": 0.0016, + "step": 56260 + }, + { + "epoch": 17.37, + "learning_rate": 8.898208190179835e-07, + "loss": 0.0022, + "step": 56261 + }, + { + "epoch": 17.37, + "learning_rate": 8.89614598274201e-07, + "loss": 0.0024, + "step": 56262 + }, + { + "epoch": 17.38, + "learning_rate": 8.894084003171543e-07, + "loss": 0.0021, + "step": 56263 + }, + { + "epoch": 17.38, + "learning_rate": 8.892022251473609e-07, + "loss": 0.0018, + "step": 56264 + }, + { + "epoch": 17.38, + "learning_rate": 8.889960727653335e-07, + "loss": 0.0018, + "step": 56265 + }, + { + "epoch": 17.38, + "learning_rate": 8.887899431715874e-07, + "loss": 0.0019, + "step": 56266 + }, + { + "epoch": 17.38, + "learning_rate": 8.885838363666421e-07, + "loss": 0.0018, + "step": 56267 + }, + { + "epoch": 17.38, + "learning_rate": 8.883777523510073e-07, + "loss": 0.0018, + "step": 56268 + }, + { + "epoch": 17.38, + "learning_rate": 8.881716911252025e-07, + "loss": 0.0016, + "step": 56269 + }, + { + "epoch": 17.38, + "learning_rate": 8.879656526897429e-07, + "loss": 0.0017, + "step": 56270 + }, + { + "epoch": 17.38, + "learning_rate": 8.877596370451446e-07, + "loss": 0.002, + "step": 56271 + }, + { + "epoch": 17.38, + "learning_rate": 8.875536441919186e-07, + "loss": 0.0017, + "step": 56272 + }, + { + "epoch": 17.38, + "learning_rate": 8.87347674130583e-07, + "loss": 0.0015, + "step": 56273 + }, + { + "epoch": 17.38, + "learning_rate": 8.871417268616544e-07, + "loss": 0.0021, + "step": 56274 + }, + { + "epoch": 17.38, + "learning_rate": 8.869358023856478e-07, + "loss": 0.0016, + "step": 56275 + }, + { + "epoch": 17.38, + "learning_rate": 8.867299007030738e-07, + "loss": 0.002, + "step": 56276 + }, + { + "epoch": 17.38, + "learning_rate": 8.865240218144521e-07, + "loss": 0.0015, + "step": 56277 + }, + { + "epoch": 17.38, + "learning_rate": 8.863181657202957e-07, + "loss": 0.0015, + "step": 56278 + }, + { + "epoch": 17.38, + "learning_rate": 8.861123324211184e-07, + "loss": 0.0019, + "step": 56279 + }, + { + "epoch": 17.38, + "learning_rate": 8.85906521917439e-07, + "loss": 0.002, + "step": 56280 + }, + { + "epoch": 17.38, + "learning_rate": 8.857007342097689e-07, + "loss": 0.0019, + "step": 56281 + }, + { + "epoch": 17.38, + "learning_rate": 8.854949692986225e-07, + "loss": 0.0021, + "step": 56282 + }, + { + "epoch": 17.38, + "learning_rate": 8.85289227184517e-07, + "loss": 0.0021, + "step": 56283 + }, + { + "epoch": 17.38, + "learning_rate": 8.850835078679643e-07, + "loss": 0.0014, + "step": 56284 + }, + { + "epoch": 17.38, + "learning_rate": 8.848778113494816e-07, + "loss": 0.002, + "step": 56285 + }, + { + "epoch": 17.38, + "learning_rate": 8.846721376295819e-07, + "loss": 0.0017, + "step": 56286 + }, + { + "epoch": 17.38, + "learning_rate": 8.844664867087783e-07, + "loss": 0.0017, + "step": 56287 + }, + { + "epoch": 17.38, + "learning_rate": 8.842608585875867e-07, + "loss": 0.002, + "step": 56288 + }, + { + "epoch": 17.38, + "learning_rate": 8.840552532665225e-07, + "loss": 0.0024, + "step": 56289 + }, + { + "epoch": 17.38, + "learning_rate": 8.838496707460975e-07, + "loss": 0.0014, + "step": 56290 + }, + { + "epoch": 17.38, + "learning_rate": 8.836441110268279e-07, + "loss": 0.0019, + "step": 56291 + }, + { + "epoch": 17.38, + "learning_rate": 8.834385741092277e-07, + "loss": 0.0013, + "step": 56292 + }, + { + "epoch": 17.38, + "learning_rate": 8.832330599938089e-07, + "loss": 0.0017, + "step": 56293 + }, + { + "epoch": 17.38, + "learning_rate": 8.830275686810874e-07, + "loss": 0.0022, + "step": 56294 + }, + { + "epoch": 17.38, + "learning_rate": 8.828221001715776e-07, + "loss": 0.0014, + "step": 56295 + }, + { + "epoch": 17.39, + "learning_rate": 8.826166544657932e-07, + "loss": 0.0026, + "step": 56296 + }, + { + "epoch": 17.39, + "learning_rate": 8.824112315642453e-07, + "loss": 0.0013, + "step": 56297 + }, + { + "epoch": 17.39, + "learning_rate": 8.822058314674519e-07, + "loss": 0.0014, + "step": 56298 + }, + { + "epoch": 17.39, + "learning_rate": 8.820004541759231e-07, + "loss": 0.0018, + "step": 56299 + }, + { + "epoch": 17.39, + "learning_rate": 8.817950996901736e-07, + "loss": 0.0017, + "step": 56300 + }, + { + "epoch": 17.39, + "learning_rate": 8.815897680107199e-07, + "loss": 0.0018, + "step": 56301 + }, + { + "epoch": 17.39, + "learning_rate": 8.813844591380727e-07, + "loss": 0.0018, + "step": 56302 + }, + { + "epoch": 17.39, + "learning_rate": 8.811791730727449e-07, + "loss": 0.0022, + "step": 56303 + }, + { + "epoch": 17.39, + "learning_rate": 8.809739098152514e-07, + "loss": 0.0023, + "step": 56304 + }, + { + "epoch": 17.39, + "learning_rate": 8.807686693661067e-07, + "loss": 0.0017, + "step": 56305 + }, + { + "epoch": 17.39, + "learning_rate": 8.805634517258222e-07, + "loss": 0.0015, + "step": 56306 + }, + { + "epoch": 17.39, + "learning_rate": 8.803582568949109e-07, + "loss": 0.002, + "step": 56307 + }, + { + "epoch": 17.39, + "learning_rate": 8.801530848738881e-07, + "loss": 0.0018, + "step": 56308 + }, + { + "epoch": 17.39, + "learning_rate": 8.799479356632646e-07, + "loss": 0.0018, + "step": 56309 + }, + { + "epoch": 17.39, + "learning_rate": 8.797428092635551e-07, + "loss": 0.0016, + "step": 56310 + }, + { + "epoch": 17.39, + "learning_rate": 8.79537705675273e-07, + "loss": 0.0021, + "step": 56311 + }, + { + "epoch": 17.39, + "learning_rate": 8.793326248989309e-07, + "loss": 0.002, + "step": 56312 + }, + { + "epoch": 17.39, + "learning_rate": 8.791275669350397e-07, + "loss": 0.0021, + "step": 56313 + }, + { + "epoch": 17.39, + "learning_rate": 8.789225317841155e-07, + "loss": 0.0028, + "step": 56314 + }, + { + "epoch": 17.39, + "learning_rate": 8.78717519446668e-07, + "loss": 0.0018, + "step": 56315 + }, + { + "epoch": 17.39, + "learning_rate": 8.785125299232144e-07, + "loss": 0.0017, + "step": 56316 + }, + { + "epoch": 17.39, + "learning_rate": 8.783075632142635e-07, + "loss": 0.0015, + "step": 56317 + }, + { + "epoch": 17.39, + "learning_rate": 8.781026193203268e-07, + "loss": 0.0012, + "step": 56318 + }, + { + "epoch": 17.39, + "learning_rate": 8.778976982419208e-07, + "loss": 0.002, + "step": 56319 + }, + { + "epoch": 17.39, + "learning_rate": 8.776927999795571e-07, + "loss": 0.0012, + "step": 56320 + }, + { + "epoch": 17.39, + "learning_rate": 8.774879245337453e-07, + "loss": 0.0016, + "step": 56321 + }, + { + "epoch": 17.39, + "learning_rate": 8.77283071905003e-07, + "loss": 0.002, + "step": 56322 + }, + { + "epoch": 17.39, + "learning_rate": 8.770782420938384e-07, + "loss": 0.0021, + "step": 56323 + }, + { + "epoch": 17.39, + "learning_rate": 8.768734351007646e-07, + "loss": 0.0017, + "step": 56324 + }, + { + "epoch": 17.39, + "learning_rate": 8.766686509262934e-07, + "loss": 0.0022, + "step": 56325 + }, + { + "epoch": 17.39, + "learning_rate": 8.764638895709399e-07, + "loss": 0.0031, + "step": 56326 + }, + { + "epoch": 17.39, + "learning_rate": 8.762591510352148e-07, + "loss": 0.0011, + "step": 56327 + }, + { + "epoch": 17.4, + "learning_rate": 8.760544353196266e-07, + "loss": 0.0026, + "step": 56328 + }, + { + "epoch": 17.4, + "learning_rate": 8.758497424246925e-07, + "loss": 0.0019, + "step": 56329 + }, + { + "epoch": 17.4, + "learning_rate": 8.756450723509214e-07, + "loss": 0.0015, + "step": 56330 + }, + { + "epoch": 17.4, + "learning_rate": 8.754404250988258e-07, + "loss": 0.0014, + "step": 56331 + }, + { + "epoch": 17.4, + "learning_rate": 8.75235800668921e-07, + "loss": 0.0019, + "step": 56332 + }, + { + "epoch": 17.4, + "learning_rate": 8.750311990617121e-07, + "loss": 0.0021, + "step": 56333 + }, + { + "epoch": 17.4, + "learning_rate": 8.748266202777156e-07, + "loss": 0.0021, + "step": 56334 + }, + { + "epoch": 17.4, + "learning_rate": 8.74622064317443e-07, + "loss": 0.0018, + "step": 56335 + }, + { + "epoch": 17.4, + "learning_rate": 8.744175311814029e-07, + "loss": 0.0015, + "step": 56336 + }, + { + "epoch": 17.4, + "learning_rate": 8.742130208701116e-07, + "loss": 0.0013, + "step": 56337 + }, + { + "epoch": 17.4, + "learning_rate": 8.740085333840753e-07, + "loss": 0.0021, + "step": 56338 + }, + { + "epoch": 17.4, + "learning_rate": 8.738040687238103e-07, + "loss": 0.002, + "step": 56339 + }, + { + "epoch": 17.4, + "learning_rate": 8.735996268898239e-07, + "loss": 0.0021, + "step": 56340 + }, + { + "epoch": 17.4, + "learning_rate": 8.733952078826291e-07, + "loss": 0.0023, + "step": 56341 + }, + { + "epoch": 17.4, + "learning_rate": 8.731908117027421e-07, + "loss": 0.0016, + "step": 56342 + }, + { + "epoch": 17.4, + "learning_rate": 8.729864383506647e-07, + "loss": 0.0021, + "step": 56343 + }, + { + "epoch": 17.4, + "learning_rate": 8.727820878269144e-07, + "loss": 0.0017, + "step": 56344 + }, + { + "epoch": 17.4, + "learning_rate": 8.725777601320017e-07, + "loss": 0.0024, + "step": 56345 + }, + { + "epoch": 17.4, + "learning_rate": 8.723734552664343e-07, + "loss": 0.0019, + "step": 56346 + }, + { + "epoch": 17.4, + "learning_rate": 8.72169173230728e-07, + "loss": 0.0019, + "step": 56347 + }, + { + "epoch": 17.4, + "learning_rate": 8.719649140253916e-07, + "loss": 0.0027, + "step": 56348 + }, + { + "epoch": 17.4, + "learning_rate": 8.717606776509346e-07, + "loss": 0.0014, + "step": 56349 + }, + { + "epoch": 17.4, + "learning_rate": 8.715564641078677e-07, + "loss": 0.0019, + "step": 56350 + }, + { + "epoch": 17.4, + "learning_rate": 8.713522733967061e-07, + "loss": 0.0021, + "step": 56351 + }, + { + "epoch": 17.4, + "learning_rate": 8.71148105517955e-07, + "loss": 0.0017, + "step": 56352 + }, + { + "epoch": 17.4, + "learning_rate": 8.709439604721293e-07, + "loss": 0.0018, + "step": 56353 + }, + { + "epoch": 17.4, + "learning_rate": 8.707398382597376e-07, + "loss": 0.001, + "step": 56354 + }, + { + "epoch": 17.4, + "learning_rate": 8.705357388812886e-07, + "loss": 0.0019, + "step": 56355 + }, + { + "epoch": 17.4, + "learning_rate": 8.70331662337296e-07, + "loss": 0.0015, + "step": 56356 + }, + { + "epoch": 17.4, + "learning_rate": 8.701276086282695e-07, + "loss": 0.002, + "step": 56357 + }, + { + "epoch": 17.4, + "learning_rate": 8.699235777547199e-07, + "loss": 0.0013, + "step": 56358 + }, + { + "epoch": 17.4, + "learning_rate": 8.697195697171546e-07, + "loss": 0.0019, + "step": 56359 + }, + { + "epoch": 17.4, + "learning_rate": 8.695155845160874e-07, + "loss": 0.0017, + "step": 56360 + }, + { + "epoch": 17.41, + "learning_rate": 8.693116221520259e-07, + "loss": 0.0024, + "step": 56361 + }, + { + "epoch": 17.41, + "learning_rate": 8.691076826254808e-07, + "loss": 0.0022, + "step": 56362 + }, + { + "epoch": 17.41, + "learning_rate": 8.68903765936967e-07, + "loss": 0.0022, + "step": 56363 + }, + { + "epoch": 17.41, + "learning_rate": 8.686998720869855e-07, + "loss": 0.0014, + "step": 56364 + }, + { + "epoch": 17.41, + "learning_rate": 8.684960010760524e-07, + "loss": 0.0017, + "step": 56365 + }, + { + "epoch": 17.41, + "learning_rate": 8.682921529046773e-07, + "loss": 0.0011, + "step": 56366 + }, + { + "epoch": 17.41, + "learning_rate": 8.680883275733676e-07, + "loss": 0.0028, + "step": 56367 + }, + { + "epoch": 17.41, + "learning_rate": 8.678845250826362e-07, + "loss": 0.0025, + "step": 56368 + }, + { + "epoch": 17.41, + "learning_rate": 8.676807454329894e-07, + "loss": 0.0018, + "step": 56369 + }, + { + "epoch": 17.41, + "learning_rate": 8.674769886249401e-07, + "loss": 0.0019, + "step": 56370 + }, + { + "epoch": 17.41, + "learning_rate": 8.672732546589946e-07, + "loss": 0.0016, + "step": 56371 + }, + { + "epoch": 17.41, + "learning_rate": 8.670695435356657e-07, + "loss": 0.0013, + "step": 56372 + }, + { + "epoch": 17.41, + "learning_rate": 8.668658552554643e-07, + "loss": 0.0026, + "step": 56373 + }, + { + "epoch": 17.41, + "learning_rate": 8.666621898188932e-07, + "loss": 0.0017, + "step": 56374 + }, + { + "epoch": 17.41, + "learning_rate": 8.664585472264664e-07, + "loss": 0.0011, + "step": 56375 + }, + { + "epoch": 17.41, + "learning_rate": 8.662549274786947e-07, + "loss": 0.0019, + "step": 56376 + }, + { + "epoch": 17.41, + "learning_rate": 8.660513305760831e-07, + "loss": 0.0022, + "step": 56377 + }, + { + "epoch": 17.41, + "learning_rate": 8.658477565191447e-07, + "loss": 0.002, + "step": 56378 + }, + { + "epoch": 17.41, + "learning_rate": 8.656442053083869e-07, + "loss": 0.0018, + "step": 56379 + }, + { + "epoch": 17.41, + "learning_rate": 8.654406769443169e-07, + "loss": 0.0017, + "step": 56380 + }, + { + "epoch": 17.41, + "learning_rate": 8.652371714274465e-07, + "loss": 0.0017, + "step": 56381 + }, + { + "epoch": 17.41, + "learning_rate": 8.650336887582855e-07, + "loss": 0.0017, + "step": 56382 + }, + { + "epoch": 17.41, + "learning_rate": 8.648302289373423e-07, + "loss": 0.0019, + "step": 56383 + }, + { + "epoch": 17.41, + "learning_rate": 8.646267919651219e-07, + "loss": 0.0018, + "step": 56384 + }, + { + "epoch": 17.41, + "learning_rate": 8.644233778421385e-07, + "loss": 0.0021, + "step": 56385 + }, + { + "epoch": 17.41, + "learning_rate": 8.64219986568896e-07, + "loss": 0.0021, + "step": 56386 + }, + { + "epoch": 17.41, + "learning_rate": 8.640166181459064e-07, + "loss": 0.0033, + "step": 56387 + }, + { + "epoch": 17.41, + "learning_rate": 8.638132725736781e-07, + "loss": 0.0017, + "step": 56388 + }, + { + "epoch": 17.41, + "learning_rate": 8.636099498527206e-07, + "loss": 0.0018, + "step": 56389 + }, + { + "epoch": 17.41, + "learning_rate": 8.634066499835381e-07, + "loss": 0.0023, + "step": 56390 + }, + { + "epoch": 17.41, + "learning_rate": 8.632033729666445e-07, + "loss": 0.0021, + "step": 56391 + }, + { + "epoch": 17.41, + "learning_rate": 8.630001188025439e-07, + "loss": 0.0018, + "step": 56392 + }, + { + "epoch": 17.42, + "learning_rate": 8.627968874917481e-07, + "loss": 0.0016, + "step": 56393 + }, + { + "epoch": 17.42, + "learning_rate": 8.625936790347633e-07, + "loss": 0.0016, + "step": 56394 + }, + { + "epoch": 17.42, + "learning_rate": 8.62390493432097e-07, + "loss": 0.0017, + "step": 56395 + }, + { + "epoch": 17.42, + "learning_rate": 8.621873306842587e-07, + "loss": 0.0017, + "step": 56396 + }, + { + "epoch": 17.42, + "learning_rate": 8.619841907917581e-07, + "loss": 0.0016, + "step": 56397 + }, + { + "epoch": 17.42, + "learning_rate": 8.617810737551002e-07, + "loss": 0.0011, + "step": 56398 + }, + { + "epoch": 17.42, + "learning_rate": 8.615779795747958e-07, + "loss": 0.0022, + "step": 56399 + }, + { + "epoch": 17.42, + "learning_rate": 8.613749082513523e-07, + "loss": 0.0015, + "step": 56400 + }, + { + "epoch": 17.42, + "learning_rate": 8.611718597852747e-07, + "loss": 0.0035, + "step": 56401 + }, + { + "epoch": 17.42, + "learning_rate": 8.609688341770728e-07, + "loss": 0.0016, + "step": 56402 + }, + { + "epoch": 17.42, + "learning_rate": 8.607658314272571e-07, + "loss": 0.0026, + "step": 56403 + }, + { + "epoch": 17.42, + "learning_rate": 8.605628515363329e-07, + "loss": 0.0014, + "step": 56404 + }, + { + "epoch": 17.42, + "learning_rate": 8.603598945048053e-07, + "loss": 0.0024, + "step": 56405 + }, + { + "epoch": 17.42, + "learning_rate": 8.601569603331849e-07, + "loss": 0.0014, + "step": 56406 + }, + { + "epoch": 17.42, + "learning_rate": 8.599540490219816e-07, + "loss": 0.0019, + "step": 56407 + }, + { + "epoch": 17.42, + "learning_rate": 8.59751160571698e-07, + "loss": 0.0027, + "step": 56408 + }, + { + "epoch": 17.42, + "learning_rate": 8.595482949828449e-07, + "loss": 0.0018, + "step": 56409 + }, + { + "epoch": 17.42, + "learning_rate": 8.593454522559297e-07, + "loss": 0.0019, + "step": 56410 + }, + { + "epoch": 17.42, + "learning_rate": 8.591426323914564e-07, + "loss": 0.0014, + "step": 56411 + }, + { + "epoch": 17.42, + "learning_rate": 8.589398353899347e-07, + "loss": 0.0017, + "step": 56412 + }, + { + "epoch": 17.42, + "learning_rate": 8.587370612518731e-07, + "loss": 0.0015, + "step": 56413 + }, + { + "epoch": 17.42, + "learning_rate": 8.585343099777776e-07, + "loss": 0.0022, + "step": 56414 + }, + { + "epoch": 17.42, + "learning_rate": 8.583315815681537e-07, + "loss": 0.0019, + "step": 56415 + }, + { + "epoch": 17.42, + "learning_rate": 8.581288760235119e-07, + "loss": 0.002, + "step": 56416 + }, + { + "epoch": 17.42, + "learning_rate": 8.579261933443538e-07, + "loss": 0.0022, + "step": 56417 + }, + { + "epoch": 17.42, + "learning_rate": 8.577235335311917e-07, + "loss": 0.0025, + "step": 56418 + }, + { + "epoch": 17.42, + "learning_rate": 8.575208965845305e-07, + "loss": 0.0025, + "step": 56419 + }, + { + "epoch": 17.42, + "learning_rate": 8.573182825048787e-07, + "loss": 0.0018, + "step": 56420 + }, + { + "epoch": 17.42, + "learning_rate": 8.571156912927381e-07, + "loss": 0.002, + "step": 56421 + }, + { + "epoch": 17.42, + "learning_rate": 8.569131229486216e-07, + "loss": 0.0018, + "step": 56422 + }, + { + "epoch": 17.42, + "learning_rate": 8.5671057747303e-07, + "loss": 0.0013, + "step": 56423 + }, + { + "epoch": 17.42, + "learning_rate": 8.565080548664761e-07, + "loss": 0.0019, + "step": 56424 + }, + { + "epoch": 17.43, + "learning_rate": 8.563055551294619e-07, + "loss": 0.0014, + "step": 56425 + }, + { + "epoch": 17.43, + "learning_rate": 8.561030782624947e-07, + "loss": 0.0015, + "step": 56426 + }, + { + "epoch": 17.43, + "learning_rate": 8.559006242660805e-07, + "loss": 0.0024, + "step": 56427 + }, + { + "epoch": 17.43, + "learning_rate": 8.556981931407282e-07, + "loss": 0.0018, + "step": 56428 + }, + { + "epoch": 17.43, + "learning_rate": 8.554957848869416e-07, + "loss": 0.0018, + "step": 56429 + }, + { + "epoch": 17.43, + "learning_rate": 8.552933995052293e-07, + "loss": 0.0018, + "step": 56430 + }, + { + "epoch": 17.43, + "learning_rate": 8.550910369960963e-07, + "loss": 0.0011, + "step": 56431 + }, + { + "epoch": 17.43, + "learning_rate": 8.548886973600457e-07, + "loss": 0.0027, + "step": 56432 + }, + { + "epoch": 17.43, + "learning_rate": 8.54686380597588e-07, + "loss": 0.0022, + "step": 56433 + }, + { + "epoch": 17.43, + "learning_rate": 8.544840867092285e-07, + "loss": 0.0014, + "step": 56434 + }, + { + "epoch": 17.43, + "learning_rate": 8.542818156954724e-07, + "loss": 0.0014, + "step": 56435 + }, + { + "epoch": 17.43, + "learning_rate": 8.540795675568237e-07, + "loss": 0.0017, + "step": 56436 + }, + { + "epoch": 17.43, + "learning_rate": 8.538773422937907e-07, + "loss": 0.0021, + "step": 56437 + }, + { + "epoch": 17.43, + "learning_rate": 8.536751399068798e-07, + "loss": 0.0016, + "step": 56438 + }, + { + "epoch": 17.43, + "learning_rate": 8.534729603965941e-07, + "loss": 0.0021, + "step": 56439 + }, + { + "epoch": 17.43, + "learning_rate": 8.53270803763443e-07, + "loss": 0.0017, + "step": 56440 + }, + { + "epoch": 17.43, + "learning_rate": 8.530686700079294e-07, + "loss": 0.0017, + "step": 56441 + }, + { + "epoch": 17.43, + "learning_rate": 8.528665591305574e-07, + "loss": 0.0019, + "step": 56442 + }, + { + "epoch": 17.43, + "learning_rate": 8.526644711318344e-07, + "loss": 0.0017, + "step": 56443 + }, + { + "epoch": 17.43, + "learning_rate": 8.524624060122677e-07, + "loss": 0.0016, + "step": 56444 + }, + { + "epoch": 17.43, + "learning_rate": 8.522603637723615e-07, + "loss": 0.0012, + "step": 56445 + }, + { + "epoch": 17.43, + "learning_rate": 8.520583444126185e-07, + "loss": 0.0018, + "step": 56446 + }, + { + "epoch": 17.43, + "learning_rate": 8.518563479335473e-07, + "loss": 0.0016, + "step": 56447 + }, + { + "epoch": 17.43, + "learning_rate": 8.516543743356509e-07, + "loss": 0.0013, + "step": 56448 + }, + { + "epoch": 17.43, + "learning_rate": 8.514524236194344e-07, + "loss": 0.003, + "step": 56449 + }, + { + "epoch": 17.43, + "learning_rate": 8.512504957854073e-07, + "loss": 0.002, + "step": 56450 + }, + { + "epoch": 17.43, + "learning_rate": 8.510485908340704e-07, + "loss": 0.0013, + "step": 56451 + }, + { + "epoch": 17.43, + "learning_rate": 8.508467087659277e-07, + "loss": 0.0024, + "step": 56452 + }, + { + "epoch": 17.43, + "learning_rate": 8.506448495814878e-07, + "loss": 0.0017, + "step": 56453 + }, + { + "epoch": 17.43, + "learning_rate": 8.504430132812524e-07, + "loss": 0.0019, + "step": 56454 + }, + { + "epoch": 17.43, + "learning_rate": 8.5024119986573e-07, + "loss": 0.0026, + "step": 56455 + }, + { + "epoch": 17.43, + "learning_rate": 8.500394093354225e-07, + "loss": 0.0016, + "step": 56456 + }, + { + "epoch": 17.43, + "learning_rate": 8.498376416908338e-07, + "loss": 0.0019, + "step": 56457 + }, + { + "epoch": 17.44, + "learning_rate": 8.496358969324703e-07, + "loss": 0.0034, + "step": 56458 + }, + { + "epoch": 17.44, + "learning_rate": 8.494341750608381e-07, + "loss": 0.0013, + "step": 56459 + }, + { + "epoch": 17.44, + "learning_rate": 8.492324760764381e-07, + "loss": 0.0017, + "step": 56460 + }, + { + "epoch": 17.44, + "learning_rate": 8.490307999797776e-07, + "loss": 0.0019, + "step": 56461 + }, + { + "epoch": 17.44, + "learning_rate": 8.488291467713605e-07, + "loss": 0.0019, + "step": 56462 + }, + { + "epoch": 17.44, + "learning_rate": 8.486275164516899e-07, + "loss": 0.0021, + "step": 56463 + }, + { + "epoch": 17.44, + "learning_rate": 8.484259090212699e-07, + "loss": 0.0018, + "step": 56464 + }, + { + "epoch": 17.44, + "learning_rate": 8.482243244806087e-07, + "loss": 0.0025, + "step": 56465 + }, + { + "epoch": 17.44, + "learning_rate": 8.480227628302073e-07, + "loss": 0.002, + "step": 56466 + }, + { + "epoch": 17.44, + "learning_rate": 8.478212240705675e-07, + "loss": 0.0013, + "step": 56467 + }, + { + "epoch": 17.44, + "learning_rate": 8.476197082021975e-07, + "loss": 0.0015, + "step": 56468 + }, + { + "epoch": 17.44, + "learning_rate": 8.474182152256005e-07, + "loss": 0.0021, + "step": 56469 + }, + { + "epoch": 17.44, + "learning_rate": 8.472167451412783e-07, + "loss": 0.002, + "step": 56470 + }, + { + "epoch": 17.44, + "learning_rate": 8.470152979497381e-07, + "loss": 0.0015, + "step": 56471 + }, + { + "epoch": 17.44, + "learning_rate": 8.46813873651483e-07, + "loss": 0.0017, + "step": 56472 + }, + { + "epoch": 17.44, + "learning_rate": 8.466124722470137e-07, + "loss": 0.0024, + "step": 56473 + }, + { + "epoch": 17.44, + "learning_rate": 8.464110937368353e-07, + "loss": 0.0023, + "step": 56474 + }, + { + "epoch": 17.44, + "learning_rate": 8.46209738121454e-07, + "loss": 0.0018, + "step": 56475 + }, + { + "epoch": 17.44, + "learning_rate": 8.460084054013728e-07, + "loss": 0.0016, + "step": 56476 + }, + { + "epoch": 17.44, + "learning_rate": 8.458070955770914e-07, + "loss": 0.002, + "step": 56477 + }, + { + "epoch": 17.44, + "learning_rate": 8.456058086491181e-07, + "loss": 0.0014, + "step": 56478 + }, + { + "epoch": 17.44, + "learning_rate": 8.454045446179526e-07, + "loss": 0.0021, + "step": 56479 + }, + { + "epoch": 17.44, + "learning_rate": 8.452033034841001e-07, + "loss": 0.0026, + "step": 56480 + }, + { + "epoch": 17.44, + "learning_rate": 8.450020852480678e-07, + "loss": 0.0016, + "step": 56481 + }, + { + "epoch": 17.44, + "learning_rate": 8.44800889910351e-07, + "loss": 0.0024, + "step": 56482 + }, + { + "epoch": 17.44, + "learning_rate": 8.445997174714571e-07, + "loss": 0.0024, + "step": 56483 + }, + { + "epoch": 17.44, + "learning_rate": 8.443985679318912e-07, + "loss": 0.0014, + "step": 56484 + }, + { + "epoch": 17.44, + "learning_rate": 8.441974412921527e-07, + "loss": 0.0017, + "step": 56485 + }, + { + "epoch": 17.44, + "learning_rate": 8.439963375527472e-07, + "loss": 0.0013, + "step": 56486 + }, + { + "epoch": 17.44, + "learning_rate": 8.437952567141771e-07, + "loss": 0.0019, + "step": 56487 + }, + { + "epoch": 17.44, + "learning_rate": 8.435941987769436e-07, + "loss": 0.0014, + "step": 56488 + }, + { + "epoch": 17.44, + "learning_rate": 8.433931637415515e-07, + "loss": 0.0019, + "step": 56489 + }, + { + "epoch": 17.45, + "learning_rate": 8.43192151608504e-07, + "loss": 0.0018, + "step": 56490 + }, + { + "epoch": 17.45, + "learning_rate": 8.429911623783038e-07, + "loss": 0.0015, + "step": 56491 + }, + { + "epoch": 17.45, + "learning_rate": 8.427901960514506e-07, + "loss": 0.0015, + "step": 56492 + }, + { + "epoch": 17.45, + "learning_rate": 8.425892526284507e-07, + "loss": 0.0023, + "step": 56493 + }, + { + "epoch": 17.45, + "learning_rate": 8.423883321098036e-07, + "loss": 0.0021, + "step": 56494 + }, + { + "epoch": 17.45, + "learning_rate": 8.421874344960146e-07, + "loss": 0.0014, + "step": 56495 + }, + { + "epoch": 17.45, + "learning_rate": 8.419865597875854e-07, + "loss": 0.002, + "step": 56496 + }, + { + "epoch": 17.45, + "learning_rate": 8.417857079850189e-07, + "loss": 0.002, + "step": 56497 + }, + { + "epoch": 17.45, + "learning_rate": 8.415848790888148e-07, + "loss": 0.0016, + "step": 56498 + }, + { + "epoch": 17.45, + "learning_rate": 8.413840730994782e-07, + "loss": 0.0018, + "step": 56499 + }, + { + "epoch": 17.45, + "learning_rate": 8.41183290017511e-07, + "loss": 0.0022, + "step": 56500 + }, + { + "epoch": 17.45, + "learning_rate": 8.409825298434149e-07, + "loss": 0.0026, + "step": 56501 + }, + { + "epoch": 17.45, + "learning_rate": 8.407817925776906e-07, + "loss": 0.0015, + "step": 56502 + }, + { + "epoch": 17.45, + "learning_rate": 8.405810782208434e-07, + "loss": 0.0014, + "step": 56503 + }, + { + "epoch": 17.45, + "learning_rate": 8.403803867733717e-07, + "loss": 0.0016, + "step": 56504 + }, + { + "epoch": 17.45, + "learning_rate": 8.401797182357796e-07, + "loss": 0.0016, + "step": 56505 + }, + { + "epoch": 17.45, + "learning_rate": 8.399790726085699e-07, + "loss": 0.0024, + "step": 56506 + }, + { + "epoch": 17.45, + "learning_rate": 8.397784498922434e-07, + "loss": 0.0022, + "step": 56507 + }, + { + "epoch": 17.45, + "learning_rate": 8.395778500872998e-07, + "loss": 0.0014, + "step": 56508 + }, + { + "epoch": 17.45, + "learning_rate": 8.393772731942451e-07, + "loss": 0.0023, + "step": 56509 + }, + { + "epoch": 17.45, + "learning_rate": 8.391767192135769e-07, + "loss": 0.0015, + "step": 56510 + }, + { + "epoch": 17.45, + "learning_rate": 8.389761881457992e-07, + "loss": 0.0015, + "step": 56511 + }, + { + "epoch": 17.45, + "learning_rate": 8.387756799914137e-07, + "loss": 0.0021, + "step": 56512 + }, + { + "epoch": 17.45, + "learning_rate": 8.385751947509191e-07, + "loss": 0.0016, + "step": 56513 + }, + { + "epoch": 17.45, + "learning_rate": 8.383747324248192e-07, + "loss": 0.0021, + "step": 56514 + }, + { + "epoch": 17.45, + "learning_rate": 8.381742930136172e-07, + "loss": 0.0014, + "step": 56515 + }, + { + "epoch": 17.45, + "learning_rate": 8.379738765178092e-07, + "loss": 0.002, + "step": 56516 + }, + { + "epoch": 17.45, + "learning_rate": 8.377734829379025e-07, + "loss": 0.0012, + "step": 56517 + }, + { + "epoch": 17.45, + "learning_rate": 8.375731122743946e-07, + "loss": 0.0022, + "step": 56518 + }, + { + "epoch": 17.45, + "learning_rate": 8.373727645277862e-07, + "loss": 0.002, + "step": 56519 + }, + { + "epoch": 17.45, + "learning_rate": 8.371724396985803e-07, + "loss": 0.0014, + "step": 56520 + }, + { + "epoch": 17.45, + "learning_rate": 8.369721377872786e-07, + "loss": 0.0018, + "step": 56521 + }, + { + "epoch": 17.45, + "learning_rate": 8.367718587943796e-07, + "loss": 0.0017, + "step": 56522 + }, + { + "epoch": 17.46, + "learning_rate": 8.365716027203852e-07, + "loss": 0.002, + "step": 56523 + }, + { + "epoch": 17.46, + "learning_rate": 8.363713695657983e-07, + "loss": 0.0026, + "step": 56524 + }, + { + "epoch": 17.46, + "learning_rate": 8.36171159331115e-07, + "loss": 0.0018, + "step": 56525 + }, + { + "epoch": 17.46, + "learning_rate": 8.359709720168396e-07, + "loss": 0.0017, + "step": 56526 + }, + { + "epoch": 17.46, + "learning_rate": 8.35770807623475e-07, + "loss": 0.0021, + "step": 56527 + }, + { + "epoch": 17.46, + "learning_rate": 8.355706661515172e-07, + "loss": 0.0019, + "step": 56528 + }, + { + "epoch": 17.46, + "learning_rate": 8.353705476014684e-07, + "loss": 0.0019, + "step": 56529 + }, + { + "epoch": 17.46, + "learning_rate": 8.351704519738302e-07, + "loss": 0.002, + "step": 56530 + }, + { + "epoch": 17.46, + "learning_rate": 8.349703792691011e-07, + "loss": 0.0018, + "step": 56531 + }, + { + "epoch": 17.46, + "learning_rate": 8.34770329487784e-07, + "loss": 0.0022, + "step": 56532 + }, + { + "epoch": 17.46, + "learning_rate": 8.345703026303764e-07, + "loss": 0.0018, + "step": 56533 + }, + { + "epoch": 17.46, + "learning_rate": 8.343702986973823e-07, + "loss": 0.0021, + "step": 56534 + }, + { + "epoch": 17.46, + "learning_rate": 8.341703176892979e-07, + "loss": 0.0016, + "step": 56535 + }, + { + "epoch": 17.46, + "learning_rate": 8.339703596066251e-07, + "loss": 0.0016, + "step": 56536 + }, + { + "epoch": 17.46, + "learning_rate": 8.337704244498657e-07, + "loss": 0.0025, + "step": 56537 + }, + { + "epoch": 17.46, + "learning_rate": 8.335705122195181e-07, + "loss": 0.0017, + "step": 56538 + }, + { + "epoch": 17.46, + "learning_rate": 8.333706229160809e-07, + "loss": 0.0022, + "step": 56539 + }, + { + "epoch": 17.46, + "learning_rate": 8.331707565400582e-07, + "loss": 0.0018, + "step": 56540 + }, + { + "epoch": 17.46, + "learning_rate": 8.32970913091945e-07, + "loss": 0.0021, + "step": 56541 + }, + { + "epoch": 17.46, + "learning_rate": 8.327710925722455e-07, + "loss": 0.0013, + "step": 56542 + }, + { + "epoch": 17.46, + "learning_rate": 8.325712949814568e-07, + "loss": 0.0019, + "step": 56543 + }, + { + "epoch": 17.46, + "learning_rate": 8.323715203200778e-07, + "loss": 0.0015, + "step": 56544 + }, + { + "epoch": 17.46, + "learning_rate": 8.321717685886099e-07, + "loss": 0.0017, + "step": 56545 + }, + { + "epoch": 17.46, + "learning_rate": 8.319720397875541e-07, + "loss": 0.0022, + "step": 56546 + }, + { + "epoch": 17.46, + "learning_rate": 8.317723339174078e-07, + "loss": 0.0022, + "step": 56547 + }, + { + "epoch": 17.46, + "learning_rate": 8.315726509786715e-07, + "loss": 0.0015, + "step": 56548 + }, + { + "epoch": 17.46, + "learning_rate": 8.313729909718449e-07, + "loss": 0.0022, + "step": 56549 + }, + { + "epoch": 17.46, + "learning_rate": 8.311733538974243e-07, + "loss": 0.0025, + "step": 56550 + }, + { + "epoch": 17.46, + "learning_rate": 8.309737397559115e-07, + "loss": 0.0019, + "step": 56551 + }, + { + "epoch": 17.46, + "learning_rate": 8.307741485478083e-07, + "loss": 0.0016, + "step": 56552 + }, + { + "epoch": 17.46, + "learning_rate": 8.30574580273611e-07, + "loss": 0.0018, + "step": 56553 + }, + { + "epoch": 17.46, + "learning_rate": 8.303750349338169e-07, + "loss": 0.0019, + "step": 56554 + }, + { + "epoch": 17.47, + "learning_rate": 8.30175512528929e-07, + "loss": 0.002, + "step": 56555 + }, + { + "epoch": 17.47, + "learning_rate": 8.299760130594426e-07, + "loss": 0.0021, + "step": 56556 + }, + { + "epoch": 17.47, + "learning_rate": 8.297765365258592e-07, + "loss": 0.0017, + "step": 56557 + }, + { + "epoch": 17.47, + "learning_rate": 8.295770829286787e-07, + "loss": 0.0023, + "step": 56558 + }, + { + "epoch": 17.47, + "learning_rate": 8.293776522683994e-07, + "loss": 0.002, + "step": 56559 + }, + { + "epoch": 17.47, + "learning_rate": 8.291782445455165e-07, + "loss": 0.0018, + "step": 56560 + }, + { + "epoch": 17.47, + "learning_rate": 8.289788597605331e-07, + "loss": 0.0014, + "step": 56561 + }, + { + "epoch": 17.47, + "learning_rate": 8.287794979139452e-07, + "loss": 0.0021, + "step": 56562 + }, + { + "epoch": 17.47, + "learning_rate": 8.285801590062537e-07, + "loss": 0.0018, + "step": 56563 + }, + { + "epoch": 17.47, + "learning_rate": 8.28380843037957e-07, + "loss": 0.0018, + "step": 56564 + }, + { + "epoch": 17.47, + "learning_rate": 8.281815500095502e-07, + "loss": 0.0016, + "step": 56565 + }, + { + "epoch": 17.47, + "learning_rate": 8.279822799215331e-07, + "loss": 0.0012, + "step": 56566 + }, + { + "epoch": 17.47, + "learning_rate": 8.277830327744063e-07, + "loss": 0.0019, + "step": 56567 + }, + { + "epoch": 17.47, + "learning_rate": 8.275838085686694e-07, + "loss": 0.0015, + "step": 56568 + }, + { + "epoch": 17.47, + "learning_rate": 8.273846073048175e-07, + "loss": 0.002, + "step": 56569 + }, + { + "epoch": 17.47, + "learning_rate": 8.27185428983348e-07, + "loss": 0.0018, + "step": 56570 + }, + { + "epoch": 17.47, + "learning_rate": 8.269862736047629e-07, + "loss": 0.0019, + "step": 56571 + }, + { + "epoch": 17.47, + "learning_rate": 8.267871411695561e-07, + "loss": 0.002, + "step": 56572 + }, + { + "epoch": 17.47, + "learning_rate": 8.265880316782293e-07, + "loss": 0.0018, + "step": 56573 + }, + { + "epoch": 17.47, + "learning_rate": 8.26388945131279e-07, + "loss": 0.0021, + "step": 56574 + }, + { + "epoch": 17.47, + "learning_rate": 8.261898815292014e-07, + "loss": 0.0021, + "step": 56575 + }, + { + "epoch": 17.47, + "learning_rate": 8.25990840872496e-07, + "loss": 0.0025, + "step": 56576 + }, + { + "epoch": 17.47, + "learning_rate": 8.257918231616624e-07, + "loss": 0.0018, + "step": 56577 + }, + { + "epoch": 17.47, + "learning_rate": 8.255928283971959e-07, + "loss": 0.0028, + "step": 56578 + }, + { + "epoch": 17.47, + "learning_rate": 8.253938565795961e-07, + "loss": 0.002, + "step": 56579 + }, + { + "epoch": 17.47, + "learning_rate": 8.251949077093591e-07, + "loss": 0.0022, + "step": 56580 + }, + { + "epoch": 17.47, + "learning_rate": 8.249959817869824e-07, + "loss": 0.0023, + "step": 56581 + }, + { + "epoch": 17.47, + "learning_rate": 8.247970788129633e-07, + "loss": 0.0022, + "step": 56582 + }, + { + "epoch": 17.47, + "learning_rate": 8.245981987878026e-07, + "loss": 0.0021, + "step": 56583 + }, + { + "epoch": 17.47, + "learning_rate": 8.243993417119944e-07, + "loss": 0.0016, + "step": 56584 + }, + { + "epoch": 17.47, + "learning_rate": 8.24200507586036e-07, + "loss": 0.0019, + "step": 56585 + }, + { + "epoch": 17.47, + "learning_rate": 8.240016964104269e-07, + "loss": 0.0022, + "step": 56586 + }, + { + "epoch": 17.48, + "learning_rate": 8.238029081856624e-07, + "loss": 0.0015, + "step": 56587 + }, + { + "epoch": 17.48, + "learning_rate": 8.236041429122387e-07, + "loss": 0.0019, + "step": 56588 + }, + { + "epoch": 17.48, + "learning_rate": 8.2340540059066e-07, + "loss": 0.0015, + "step": 56589 + }, + { + "epoch": 17.48, + "learning_rate": 8.232066812214135e-07, + "loss": 0.0016, + "step": 56590 + }, + { + "epoch": 17.48, + "learning_rate": 8.23007984805001e-07, + "loss": 0.0022, + "step": 56591 + }, + { + "epoch": 17.48, + "learning_rate": 8.228093113419211e-07, + "loss": 0.0021, + "step": 56592 + }, + { + "epoch": 17.48, + "learning_rate": 8.226106608326678e-07, + "loss": 0.0015, + "step": 56593 + }, + { + "epoch": 17.48, + "learning_rate": 8.224120332777408e-07, + "loss": 0.0018, + "step": 56594 + }, + { + "epoch": 17.48, + "learning_rate": 8.22213428677634e-07, + "loss": 0.0016, + "step": 56595 + }, + { + "epoch": 17.48, + "learning_rate": 8.220148470328449e-07, + "loss": 0.0019, + "step": 56596 + }, + { + "epoch": 17.48, + "learning_rate": 8.218162883438697e-07, + "loss": 0.002, + "step": 56597 + }, + { + "epoch": 17.48, + "learning_rate": 8.216177526112068e-07, + "loss": 0.0015, + "step": 56598 + }, + { + "epoch": 17.48, + "learning_rate": 8.214192398353549e-07, + "loss": 0.0011, + "step": 56599 + }, + { + "epoch": 17.48, + "learning_rate": 8.212207500168035e-07, + "loss": 0.0017, + "step": 56600 + }, + { + "epoch": 17.48, + "learning_rate": 8.210222831560544e-07, + "loss": 0.0016, + "step": 56601 + }, + { + "epoch": 17.48, + "learning_rate": 8.208238392536039e-07, + "loss": 0.0018, + "step": 56602 + }, + { + "epoch": 17.48, + "learning_rate": 8.206254183099449e-07, + "loss": 0.0016, + "step": 56603 + }, + { + "epoch": 17.48, + "learning_rate": 8.204270203255782e-07, + "loss": 0.0024, + "step": 56604 + }, + { + "epoch": 17.48, + "learning_rate": 8.202286453009978e-07, + "loss": 0.0024, + "step": 56605 + }, + { + "epoch": 17.48, + "learning_rate": 8.200302932366977e-07, + "loss": 0.0025, + "step": 56606 + }, + { + "epoch": 17.48, + "learning_rate": 8.198319641331764e-07, + "loss": 0.0014, + "step": 56607 + }, + { + "epoch": 17.48, + "learning_rate": 8.196336579909314e-07, + "loss": 0.0023, + "step": 56608 + }, + { + "epoch": 17.48, + "learning_rate": 8.194353748104556e-07, + "loss": 0.0022, + "step": 56609 + }, + { + "epoch": 17.48, + "learning_rate": 8.192371145922473e-07, + "loss": 0.0023, + "step": 56610 + }, + { + "epoch": 17.48, + "learning_rate": 8.190388773368019e-07, + "loss": 0.0018, + "step": 56611 + }, + { + "epoch": 17.48, + "learning_rate": 8.188406630446132e-07, + "loss": 0.0024, + "step": 56612 + }, + { + "epoch": 17.48, + "learning_rate": 8.18642471716179e-07, + "loss": 0.0015, + "step": 56613 + }, + { + "epoch": 17.48, + "learning_rate": 8.184443033519951e-07, + "loss": 0.0019, + "step": 56614 + }, + { + "epoch": 17.48, + "learning_rate": 8.182461579525569e-07, + "loss": 0.0012, + "step": 56615 + }, + { + "epoch": 17.48, + "learning_rate": 8.180480355183585e-07, + "loss": 0.0015, + "step": 56616 + }, + { + "epoch": 17.48, + "learning_rate": 8.178499360498982e-07, + "loss": 0.0018, + "step": 56617 + }, + { + "epoch": 17.48, + "learning_rate": 8.17651859547669e-07, + "loss": 0.0022, + "step": 56618 + }, + { + "epoch": 17.48, + "learning_rate": 8.174538060121662e-07, + "loss": 0.002, + "step": 56619 + }, + { + "epoch": 17.49, + "learning_rate": 8.172557754438893e-07, + "loss": 0.0019, + "step": 56620 + }, + { + "epoch": 17.49, + "learning_rate": 8.170577678433278e-07, + "loss": 0.002, + "step": 56621 + }, + { + "epoch": 17.49, + "learning_rate": 8.168597832109803e-07, + "loss": 0.0016, + "step": 56622 + }, + { + "epoch": 17.49, + "learning_rate": 8.16661821547342e-07, + "loss": 0.0015, + "step": 56623 + }, + { + "epoch": 17.49, + "learning_rate": 8.16463882852906e-07, + "loss": 0.0017, + "step": 56624 + }, + { + "epoch": 17.49, + "learning_rate": 8.162659671281703e-07, + "loss": 0.0015, + "step": 56625 + }, + { + "epoch": 17.49, + "learning_rate": 8.160680743736293e-07, + "loss": 0.0014, + "step": 56626 + }, + { + "epoch": 17.49, + "learning_rate": 8.158702045897749e-07, + "loss": 0.0018, + "step": 56627 + }, + { + "epoch": 17.49, + "learning_rate": 8.156723577771042e-07, + "loss": 0.003, + "step": 56628 + }, + { + "epoch": 17.49, + "learning_rate": 8.154745339361136e-07, + "loss": 0.002, + "step": 56629 + }, + { + "epoch": 17.49, + "learning_rate": 8.152767330672962e-07, + "loss": 0.002, + "step": 56630 + }, + { + "epoch": 17.49, + "learning_rate": 8.150789551711458e-07, + "loss": 0.0014, + "step": 56631 + }, + { + "epoch": 17.49, + "learning_rate": 8.148812002481577e-07, + "loss": 0.0016, + "step": 56632 + }, + { + "epoch": 17.49, + "learning_rate": 8.14683468298828e-07, + "loss": 0.0022, + "step": 56633 + }, + { + "epoch": 17.49, + "learning_rate": 8.144857593236499e-07, + "loss": 0.0016, + "step": 56634 + }, + { + "epoch": 17.49, + "learning_rate": 8.142880733231196e-07, + "loss": 0.002, + "step": 56635 + }, + { + "epoch": 17.49, + "learning_rate": 8.140904102977299e-07, + "loss": 0.0022, + "step": 56636 + }, + { + "epoch": 17.49, + "learning_rate": 8.138927702479737e-07, + "loss": 0.0019, + "step": 56637 + }, + { + "epoch": 17.49, + "learning_rate": 8.136951531743464e-07, + "loss": 0.0014, + "step": 56638 + }, + { + "epoch": 17.49, + "learning_rate": 8.134975590773463e-07, + "loss": 0.0015, + "step": 56639 + }, + { + "epoch": 17.49, + "learning_rate": 8.132999879574632e-07, + "loss": 0.0019, + "step": 56640 + }, + { + "epoch": 17.49, + "learning_rate": 8.13102439815191e-07, + "loss": 0.0023, + "step": 56641 + }, + { + "epoch": 17.49, + "learning_rate": 8.129049146510271e-07, + "loss": 0.0019, + "step": 56642 + }, + { + "epoch": 17.49, + "learning_rate": 8.127074124654621e-07, + "loss": 0.0027, + "step": 56643 + }, + { + "epoch": 17.49, + "learning_rate": 8.125099332589903e-07, + "loss": 0.0026, + "step": 56644 + }, + { + "epoch": 17.49, + "learning_rate": 8.1231247703211e-07, + "loss": 0.0021, + "step": 56645 + }, + { + "epoch": 17.49, + "learning_rate": 8.121150437853109e-07, + "loss": 0.0019, + "step": 56646 + }, + { + "epoch": 17.49, + "learning_rate": 8.11917633519087e-07, + "loss": 0.0025, + "step": 56647 + }, + { + "epoch": 17.49, + "learning_rate": 8.117202462339347e-07, + "loss": 0.0019, + "step": 56648 + }, + { + "epoch": 17.49, + "learning_rate": 8.115228819303434e-07, + "loss": 0.003, + "step": 56649 + }, + { + "epoch": 17.49, + "learning_rate": 8.113255406088105e-07, + "loss": 0.0023, + "step": 56650 + }, + { + "epoch": 17.49, + "learning_rate": 8.111282222698292e-07, + "loss": 0.0019, + "step": 56651 + }, + { + "epoch": 17.5, + "learning_rate": 8.109309269138909e-07, + "loss": 0.0015, + "step": 56652 + }, + { + "epoch": 17.5, + "learning_rate": 8.10733654541489e-07, + "loss": 0.0014, + "step": 56653 + }, + { + "epoch": 17.5, + "learning_rate": 8.105364051531217e-07, + "loss": 0.0022, + "step": 56654 + }, + { + "epoch": 17.5, + "learning_rate": 8.103391787492754e-07, + "loss": 0.0021, + "step": 56655 + }, + { + "epoch": 17.5, + "learning_rate": 8.101419753304496e-07, + "loss": 0.0019, + "step": 56656 + }, + { + "epoch": 17.5, + "learning_rate": 8.099447948971351e-07, + "loss": 0.0019, + "step": 56657 + }, + { + "epoch": 17.5, + "learning_rate": 8.097476374498225e-07, + "loss": 0.0017, + "step": 56658 + }, + { + "epoch": 17.5, + "learning_rate": 8.095505029890072e-07, + "loss": 0.0012, + "step": 56659 + }, + { + "epoch": 17.5, + "learning_rate": 8.093533915151841e-07, + "loss": 0.002, + "step": 56660 + }, + { + "epoch": 17.5, + "learning_rate": 8.091563030288452e-07, + "loss": 0.0019, + "step": 56661 + }, + { + "epoch": 17.5, + "learning_rate": 8.0895923753048e-07, + "loss": 0.0016, + "step": 56662 + }, + { + "epoch": 17.5, + "learning_rate": 8.087621950205849e-07, + "loss": 0.0018, + "step": 56663 + }, + { + "epoch": 17.5, + "learning_rate": 8.085651754996526e-07, + "loss": 0.0019, + "step": 56664 + }, + { + "epoch": 17.5, + "learning_rate": 8.08368178968174e-07, + "loss": 0.0014, + "step": 56665 + }, + { + "epoch": 17.5, + "learning_rate": 8.081712054266455e-07, + "loss": 0.0019, + "step": 56666 + }, + { + "epoch": 17.5, + "learning_rate": 8.079742548755565e-07, + "loss": 0.0015, + "step": 56667 + }, + { + "epoch": 17.5, + "learning_rate": 8.077773273153988e-07, + "loss": 0.0023, + "step": 56668 + }, + { + "epoch": 17.5, + "learning_rate": 8.075804227466666e-07, + "loss": 0.0022, + "step": 56669 + }, + { + "epoch": 17.5, + "learning_rate": 8.073835411698538e-07, + "loss": 0.0017, + "step": 56670 + }, + { + "epoch": 17.5, + "learning_rate": 8.071866825854524e-07, + "loss": 0.0018, + "step": 56671 + }, + { + "epoch": 17.5, + "learning_rate": 8.069898469939508e-07, + "loss": 0.0018, + "step": 56672 + }, + { + "epoch": 17.5, + "learning_rate": 8.067930343958463e-07, + "loss": 0.0022, + "step": 56673 + }, + { + "epoch": 17.5, + "learning_rate": 8.065962447916287e-07, + "loss": 0.0018, + "step": 56674 + }, + { + "epoch": 17.5, + "learning_rate": 8.063994781817896e-07, + "loss": 0.002, + "step": 56675 + }, + { + "epoch": 17.5, + "learning_rate": 8.062027345668233e-07, + "loss": 0.0017, + "step": 56676 + }, + { + "epoch": 17.5, + "learning_rate": 8.060060139472215e-07, + "loss": 0.0026, + "step": 56677 + }, + { + "epoch": 17.5, + "learning_rate": 8.058093163234737e-07, + "loss": 0.0016, + "step": 56678 + }, + { + "epoch": 17.5, + "learning_rate": 8.056126416960763e-07, + "loss": 0.0015, + "step": 56679 + }, + { + "epoch": 17.5, + "learning_rate": 8.054159900655156e-07, + "loss": 0.0016, + "step": 56680 + }, + { + "epoch": 17.5, + "learning_rate": 8.05219361432289e-07, + "loss": 0.0023, + "step": 56681 + }, + { + "epoch": 17.5, + "learning_rate": 8.050227557968859e-07, + "loss": 0.0014, + "step": 56682 + }, + { + "epoch": 17.5, + "learning_rate": 8.048261731597951e-07, + "loss": 0.0024, + "step": 56683 + }, + { + "epoch": 17.51, + "learning_rate": 8.046296135215126e-07, + "loss": 0.002, + "step": 56684 + }, + { + "epoch": 17.51, + "learning_rate": 8.044330768825292e-07, + "loss": 0.0019, + "step": 56685 + }, + { + "epoch": 17.51, + "learning_rate": 8.042365632433347e-07, + "loss": 0.0017, + "step": 56686 + }, + { + "epoch": 17.51, + "learning_rate": 8.040400726044228e-07, + "loss": 0.0016, + "step": 56687 + }, + { + "epoch": 17.51, + "learning_rate": 8.038436049662845e-07, + "loss": 0.0016, + "step": 56688 + }, + { + "epoch": 17.51, + "learning_rate": 8.036471603294094e-07, + "loss": 0.0022, + "step": 56689 + }, + { + "epoch": 17.51, + "learning_rate": 8.034507386942891e-07, + "loss": 0.0025, + "step": 56690 + }, + { + "epoch": 17.51, + "learning_rate": 8.032543400614179e-07, + "loss": 0.0019, + "step": 56691 + }, + { + "epoch": 17.51, + "learning_rate": 8.030579644312852e-07, + "loss": 0.0017, + "step": 56692 + }, + { + "epoch": 17.51, + "learning_rate": 8.028616118043809e-07, + "loss": 0.0019, + "step": 56693 + }, + { + "epoch": 17.51, + "learning_rate": 8.026652821811975e-07, + "loss": 0.0016, + "step": 56694 + }, + { + "epoch": 17.51, + "learning_rate": 8.024689755622251e-07, + "loss": 0.002, + "step": 56695 + }, + { + "epoch": 17.51, + "learning_rate": 8.02272691947954e-07, + "loss": 0.002, + "step": 56696 + }, + { + "epoch": 17.51, + "learning_rate": 8.020764313388795e-07, + "loss": 0.0013, + "step": 56697 + }, + { + "epoch": 17.51, + "learning_rate": 8.018801937354892e-07, + "loss": 0.0027, + "step": 56698 + }, + { + "epoch": 17.51, + "learning_rate": 8.016839791382713e-07, + "loss": 0.0016, + "step": 56699 + }, + { + "epoch": 17.51, + "learning_rate": 8.0148778754772e-07, + "loss": 0.0014, + "step": 56700 + }, + { + "epoch": 17.51, + "learning_rate": 8.012916189643283e-07, + "loss": 0.0011, + "step": 56701 + }, + { + "epoch": 17.51, + "learning_rate": 8.010954733885834e-07, + "loss": 0.0019, + "step": 56702 + }, + { + "epoch": 17.51, + "learning_rate": 8.008993508209739e-07, + "loss": 0.0013, + "step": 56703 + }, + { + "epoch": 17.51, + "learning_rate": 8.00703251261995e-07, + "loss": 0.0024, + "step": 56704 + }, + { + "epoch": 17.51, + "learning_rate": 8.00507174712134e-07, + "loss": 0.0021, + "step": 56705 + }, + { + "epoch": 17.51, + "learning_rate": 8.003111211718817e-07, + "loss": 0.0016, + "step": 56706 + }, + { + "epoch": 17.51, + "learning_rate": 8.001150906417321e-07, + "loss": 0.0028, + "step": 56707 + }, + { + "epoch": 17.51, + "learning_rate": 7.999190831221715e-07, + "loss": 0.0016, + "step": 56708 + }, + { + "epoch": 17.51, + "learning_rate": 7.997230986136894e-07, + "loss": 0.0014, + "step": 56709 + }, + { + "epoch": 17.51, + "learning_rate": 7.995271371167812e-07, + "loss": 0.002, + "step": 56710 + }, + { + "epoch": 17.51, + "learning_rate": 7.993311986319307e-07, + "loss": 0.002, + "step": 56711 + }, + { + "epoch": 17.51, + "learning_rate": 7.991352831596321e-07, + "loss": 0.0018, + "step": 56712 + }, + { + "epoch": 17.51, + "learning_rate": 7.989393907003751e-07, + "loss": 0.003, + "step": 56713 + }, + { + "epoch": 17.51, + "learning_rate": 7.987435212546468e-07, + "loss": 0.0022, + "step": 56714 + }, + { + "epoch": 17.51, + "learning_rate": 7.985476748229404e-07, + "loss": 0.0021, + "step": 56715 + }, + { + "epoch": 17.51, + "learning_rate": 7.983518514057453e-07, + "loss": 0.0024, + "step": 56716 + }, + { + "epoch": 17.52, + "learning_rate": 7.98156051003548e-07, + "loss": 0.002, + "step": 56717 + }, + { + "epoch": 17.52, + "learning_rate": 7.979602736168435e-07, + "loss": 0.0021, + "step": 56718 + }, + { + "epoch": 17.52, + "learning_rate": 7.977645192461181e-07, + "loss": 0.0018, + "step": 56719 + }, + { + "epoch": 17.52, + "learning_rate": 7.975687878918603e-07, + "loss": 0.0022, + "step": 56720 + }, + { + "epoch": 17.52, + "learning_rate": 7.97373079554562e-07, + "loss": 0.0028, + "step": 56721 + }, + { + "epoch": 17.52, + "learning_rate": 7.971773942347138e-07, + "loss": 0.0019, + "step": 56722 + }, + { + "epoch": 17.52, + "learning_rate": 7.969817319328033e-07, + "loss": 0.0017, + "step": 56723 + }, + { + "epoch": 17.52, + "learning_rate": 7.967860926493177e-07, + "loss": 0.0016, + "step": 56724 + }, + { + "epoch": 17.52, + "learning_rate": 7.965904763847509e-07, + "loss": 0.0019, + "step": 56725 + }, + { + "epoch": 17.52, + "learning_rate": 7.963948831395873e-07, + "loss": 0.0022, + "step": 56726 + }, + { + "epoch": 17.52, + "learning_rate": 7.961993129143197e-07, + "loss": 0.0024, + "step": 56727 + }, + { + "epoch": 17.52, + "learning_rate": 7.960037657094377e-07, + "loss": 0.0018, + "step": 56728 + }, + { + "epoch": 17.52, + "learning_rate": 7.958082415254298e-07, + "loss": 0.0015, + "step": 56729 + }, + { + "epoch": 17.52, + "learning_rate": 7.956127403627811e-07, + "loss": 0.0015, + "step": 56730 + }, + { + "epoch": 17.52, + "learning_rate": 7.954172622219847e-07, + "loss": 0.0018, + "step": 56731 + }, + { + "epoch": 17.52, + "learning_rate": 7.9522180710353e-07, + "loss": 0.0015, + "step": 56732 + }, + { + "epoch": 17.52, + "learning_rate": 7.950263750079046e-07, + "loss": 0.0023, + "step": 56733 + }, + { + "epoch": 17.52, + "learning_rate": 7.948309659355946e-07, + "loss": 0.0014, + "step": 56734 + }, + { + "epoch": 17.52, + "learning_rate": 7.946355798870942e-07, + "loss": 0.002, + "step": 56735 + }, + { + "epoch": 17.52, + "learning_rate": 7.944402168628862e-07, + "loss": 0.002, + "step": 56736 + }, + { + "epoch": 17.52, + "learning_rate": 7.942448768634625e-07, + "loss": 0.0026, + "step": 56737 + }, + { + "epoch": 17.52, + "learning_rate": 7.94049559889315e-07, + "loss": 0.0015, + "step": 56738 + }, + { + "epoch": 17.52, + "learning_rate": 7.938542659409254e-07, + "loss": 0.0018, + "step": 56739 + }, + { + "epoch": 17.52, + "learning_rate": 7.936589950187856e-07, + "loss": 0.0016, + "step": 56740 + }, + { + "epoch": 17.52, + "learning_rate": 7.934637471233853e-07, + "loss": 0.0028, + "step": 56741 + }, + { + "epoch": 17.52, + "learning_rate": 7.932685222552095e-07, + "loss": 0.0022, + "step": 56742 + }, + { + "epoch": 17.52, + "learning_rate": 7.930733204147501e-07, + "loss": 0.0016, + "step": 56743 + }, + { + "epoch": 17.52, + "learning_rate": 7.928781416024933e-07, + "loss": 0.0023, + "step": 56744 + }, + { + "epoch": 17.52, + "learning_rate": 7.926829858189256e-07, + "loss": 0.0019, + "step": 56745 + }, + { + "epoch": 17.52, + "learning_rate": 7.924878530645375e-07, + "loss": 0.0021, + "step": 56746 + }, + { + "epoch": 17.52, + "learning_rate": 7.922927433398187e-07, + "loss": 0.0022, + "step": 56747 + }, + { + "epoch": 17.52, + "learning_rate": 7.920976566452543e-07, + "loss": 0.0019, + "step": 56748 + }, + { + "epoch": 17.53, + "learning_rate": 7.919025929813328e-07, + "loss": 0.0018, + "step": 56749 + }, + { + "epoch": 17.53, + "learning_rate": 7.917075523485429e-07, + "loss": 0.0023, + "step": 56750 + }, + { + "epoch": 17.53, + "learning_rate": 7.915125347473706e-07, + "loss": 0.0018, + "step": 56751 + }, + { + "epoch": 17.53, + "learning_rate": 7.913175401783046e-07, + "loss": 0.0022, + "step": 56752 + }, + { + "epoch": 17.53, + "learning_rate": 7.911225686418344e-07, + "loss": 0.0018, + "step": 56753 + }, + { + "epoch": 17.53, + "learning_rate": 7.909276201384464e-07, + "loss": 0.002, + "step": 56754 + }, + { + "epoch": 17.53, + "learning_rate": 7.907326946686267e-07, + "loss": 0.0017, + "step": 56755 + }, + { + "epoch": 17.53, + "learning_rate": 7.905377922328661e-07, + "loss": 0.0014, + "step": 56756 + }, + { + "epoch": 17.53, + "learning_rate": 7.903429128316487e-07, + "loss": 0.0018, + "step": 56757 + }, + { + "epoch": 17.53, + "learning_rate": 7.90148056465464e-07, + "loss": 0.0016, + "step": 56758 + }, + { + "epoch": 17.53, + "learning_rate": 7.899532231347995e-07, + "loss": 0.0018, + "step": 56759 + }, + { + "epoch": 17.53, + "learning_rate": 7.897584128401403e-07, + "loss": 0.0023, + "step": 56760 + }, + { + "epoch": 17.53, + "learning_rate": 7.89563625581975e-07, + "loss": 0.0024, + "step": 56761 + }, + { + "epoch": 17.53, + "learning_rate": 7.893688613607909e-07, + "loss": 0.0018, + "step": 56762 + }, + { + "epoch": 17.53, + "learning_rate": 7.891741201770764e-07, + "loss": 0.0017, + "step": 56763 + }, + { + "epoch": 17.53, + "learning_rate": 7.88979402031318e-07, + "loss": 0.0017, + "step": 56764 + }, + { + "epoch": 17.53, + "learning_rate": 7.887847069240007e-07, + "loss": 0.0017, + "step": 56765 + }, + { + "epoch": 17.53, + "learning_rate": 7.885900348556141e-07, + "loss": 0.0015, + "step": 56766 + }, + { + "epoch": 17.53, + "learning_rate": 7.883953858266413e-07, + "loss": 0.0013, + "step": 56767 + }, + { + "epoch": 17.53, + "learning_rate": 7.882007598375751e-07, + "loss": 0.0023, + "step": 56768 + }, + { + "epoch": 17.53, + "learning_rate": 7.880061568888975e-07, + "loss": 0.002, + "step": 56769 + }, + { + "epoch": 17.53, + "learning_rate": 7.878115769810957e-07, + "loss": 0.0017, + "step": 56770 + }, + { + "epoch": 17.53, + "learning_rate": 7.876170201146571e-07, + "loss": 0.0012, + "step": 56771 + }, + { + "epoch": 17.53, + "learning_rate": 7.874224862900704e-07, + "loss": 0.0019, + "step": 56772 + }, + { + "epoch": 17.53, + "learning_rate": 7.872279755078183e-07, + "loss": 0.0018, + "step": 56773 + }, + { + "epoch": 17.53, + "learning_rate": 7.870334877683916e-07, + "loss": 0.0017, + "step": 56774 + }, + { + "epoch": 17.53, + "learning_rate": 7.868390230722745e-07, + "loss": 0.0019, + "step": 56775 + }, + { + "epoch": 17.53, + "learning_rate": 7.866445814199519e-07, + "loss": 0.0016, + "step": 56776 + }, + { + "epoch": 17.53, + "learning_rate": 7.864501628119104e-07, + "loss": 0.0019, + "step": 56777 + }, + { + "epoch": 17.53, + "learning_rate": 7.862557672486404e-07, + "loss": 0.0017, + "step": 56778 + }, + { + "epoch": 17.53, + "learning_rate": 7.86061394730625e-07, + "loss": 0.0016, + "step": 56779 + }, + { + "epoch": 17.53, + "learning_rate": 7.858670452583483e-07, + "loss": 0.0016, + "step": 56780 + }, + { + "epoch": 17.53, + "learning_rate": 7.85672718832301e-07, + "loss": 0.0018, + "step": 56781 + }, + { + "epoch": 17.54, + "learning_rate": 7.854784154529638e-07, + "loss": 0.0017, + "step": 56782 + }, + { + "epoch": 17.54, + "learning_rate": 7.852841351208273e-07, + "loss": 0.0018, + "step": 56783 + }, + { + "epoch": 17.54, + "learning_rate": 7.850898778363769e-07, + "loss": 0.0023, + "step": 56784 + }, + { + "epoch": 17.54, + "learning_rate": 7.848956436000976e-07, + "loss": 0.0014, + "step": 56785 + }, + { + "epoch": 17.54, + "learning_rate": 7.847014324124724e-07, + "loss": 0.002, + "step": 56786 + }, + { + "epoch": 17.54, + "learning_rate": 7.845072442739931e-07, + "loss": 0.0018, + "step": 56787 + }, + { + "epoch": 17.54, + "learning_rate": 7.843130791851394e-07, + "loss": 0.0023, + "step": 56788 + }, + { + "epoch": 17.54, + "learning_rate": 7.841189371464009e-07, + "loss": 0.0021, + "step": 56789 + }, + { + "epoch": 17.54, + "learning_rate": 7.839248181582615e-07, + "loss": 0.0019, + "step": 56790 + }, + { + "epoch": 17.54, + "learning_rate": 7.837307222212065e-07, + "loss": 0.0018, + "step": 56791 + }, + { + "epoch": 17.54, + "learning_rate": 7.83536649335721e-07, + "loss": 0.0014, + "step": 56792 + }, + { + "epoch": 17.54, + "learning_rate": 7.833425995022936e-07, + "loss": 0.0011, + "step": 56793 + }, + { + "epoch": 17.54, + "learning_rate": 7.83148572721405e-07, + "loss": 0.0015, + "step": 56794 + }, + { + "epoch": 17.54, + "learning_rate": 7.829545689935458e-07, + "loss": 0.0022, + "step": 56795 + }, + { + "epoch": 17.54, + "learning_rate": 7.827605883191958e-07, + "loss": 0.0019, + "step": 56796 + }, + { + "epoch": 17.54, + "learning_rate": 7.825666306988433e-07, + "loss": 0.0019, + "step": 56797 + }, + { + "epoch": 17.54, + "learning_rate": 7.823726961329725e-07, + "loss": 0.0019, + "step": 56798 + }, + { + "epoch": 17.54, + "learning_rate": 7.821787846220708e-07, + "loss": 0.0018, + "step": 56799 + }, + { + "epoch": 17.54, + "learning_rate": 7.819848961666199e-07, + "loss": 0.0016, + "step": 56800 + }, + { + "epoch": 17.54, + "learning_rate": 7.817910307671051e-07, + "loss": 0.0016, + "step": 56801 + }, + { + "epoch": 17.54, + "learning_rate": 7.815971884240125e-07, + "loss": 0.0017, + "step": 56802 + }, + { + "epoch": 17.54, + "learning_rate": 7.814033691378276e-07, + "loss": 0.002, + "step": 56803 + }, + { + "epoch": 17.54, + "learning_rate": 7.81209572909033e-07, + "loss": 0.0015, + "step": 56804 + }, + { + "epoch": 17.54, + "learning_rate": 7.810157997381162e-07, + "loss": 0.0021, + "step": 56805 + }, + { + "epoch": 17.54, + "learning_rate": 7.808220496255603e-07, + "loss": 0.0013, + "step": 56806 + }, + { + "epoch": 17.54, + "learning_rate": 7.806283225718481e-07, + "loss": 0.0017, + "step": 56807 + }, + { + "epoch": 17.54, + "learning_rate": 7.804346185774669e-07, + "loss": 0.0015, + "step": 56808 + }, + { + "epoch": 17.54, + "learning_rate": 7.80240937642901e-07, + "loss": 0.0016, + "step": 56809 + }, + { + "epoch": 17.54, + "learning_rate": 7.800472797686343e-07, + "loss": 0.002, + "step": 56810 + }, + { + "epoch": 17.54, + "learning_rate": 7.798536449551497e-07, + "loss": 0.0021, + "step": 56811 + }, + { + "epoch": 17.54, + "learning_rate": 7.796600332029336e-07, + "loss": 0.0016, + "step": 56812 + }, + { + "epoch": 17.54, + "learning_rate": 7.794664445124689e-07, + "loss": 0.0018, + "step": 56813 + }, + { + "epoch": 17.55, + "learning_rate": 7.792728788842396e-07, + "loss": 0.0015, + "step": 56814 + }, + { + "epoch": 17.55, + "learning_rate": 7.790793363187321e-07, + "loss": 0.0019, + "step": 56815 + }, + { + "epoch": 17.55, + "learning_rate": 7.788858168164293e-07, + "loss": 0.0032, + "step": 56816 + }, + { + "epoch": 17.55, + "learning_rate": 7.78692320377813e-07, + "loss": 0.0019, + "step": 56817 + }, + { + "epoch": 17.55, + "learning_rate": 7.784988470033705e-07, + "loss": 0.0017, + "step": 56818 + }, + { + "epoch": 17.55, + "learning_rate": 7.783053966935838e-07, + "loss": 0.0029, + "step": 56819 + }, + { + "epoch": 17.55, + "learning_rate": 7.781119694489381e-07, + "loss": 0.0019, + "step": 56820 + }, + { + "epoch": 17.55, + "learning_rate": 7.779185652699162e-07, + "loss": 0.0024, + "step": 56821 + }, + { + "epoch": 17.55, + "learning_rate": 7.77725184157e-07, + "loss": 0.0027, + "step": 56822 + }, + { + "epoch": 17.55, + "learning_rate": 7.775318261106757e-07, + "loss": 0.0023, + "step": 56823 + }, + { + "epoch": 17.55, + "learning_rate": 7.773384911314285e-07, + "loss": 0.0017, + "step": 56824 + }, + { + "epoch": 17.55, + "learning_rate": 7.771451792197371e-07, + "loss": 0.0019, + "step": 56825 + }, + { + "epoch": 17.55, + "learning_rate": 7.769518903760897e-07, + "loss": 0.0017, + "step": 56826 + }, + { + "epoch": 17.55, + "learning_rate": 7.767586246009661e-07, + "loss": 0.0014, + "step": 56827 + }, + { + "epoch": 17.55, + "learning_rate": 7.765653818948538e-07, + "loss": 0.0019, + "step": 56828 + }, + { + "epoch": 17.55, + "learning_rate": 7.763721622582321e-07, + "loss": 0.0018, + "step": 56829 + }, + { + "epoch": 17.55, + "learning_rate": 7.761789656915863e-07, + "loss": 0.002, + "step": 56830 + }, + { + "epoch": 17.55, + "learning_rate": 7.759857921954006e-07, + "loss": 0.0016, + "step": 56831 + }, + { + "epoch": 17.55, + "learning_rate": 7.757926417701545e-07, + "loss": 0.0017, + "step": 56832 + }, + { + "epoch": 17.55, + "learning_rate": 7.755995144163331e-07, + "loss": 0.0018, + "step": 56833 + }, + { + "epoch": 17.55, + "learning_rate": 7.754064101344217e-07, + "loss": 0.002, + "step": 56834 + }, + { + "epoch": 17.55, + "learning_rate": 7.752133289248998e-07, + "loss": 0.0018, + "step": 56835 + }, + { + "epoch": 17.55, + "learning_rate": 7.750202707882537e-07, + "loss": 0.0017, + "step": 56836 + }, + { + "epoch": 17.55, + "learning_rate": 7.748272357249643e-07, + "loss": 0.002, + "step": 56837 + }, + { + "epoch": 17.55, + "learning_rate": 7.74634223735512e-07, + "loss": 0.0014, + "step": 56838 + }, + { + "epoch": 17.55, + "learning_rate": 7.744412348203834e-07, + "loss": 0.0021, + "step": 56839 + }, + { + "epoch": 17.55, + "learning_rate": 7.742482689800613e-07, + "loss": 0.0017, + "step": 56840 + }, + { + "epoch": 17.55, + "learning_rate": 7.740553262150264e-07, + "loss": 0.0032, + "step": 56841 + }, + { + "epoch": 17.55, + "learning_rate": 7.738624065257605e-07, + "loss": 0.0016, + "step": 56842 + }, + { + "epoch": 17.55, + "learning_rate": 7.736695099127489e-07, + "loss": 0.0015, + "step": 56843 + }, + { + "epoch": 17.55, + "learning_rate": 7.734766363764711e-07, + "loss": 0.0013, + "step": 56844 + }, + { + "epoch": 17.55, + "learning_rate": 7.732837859174113e-07, + "loss": 0.0021, + "step": 56845 + }, + { + "epoch": 17.56, + "learning_rate": 7.730909585360546e-07, + "loss": 0.002, + "step": 56846 + }, + { + "epoch": 17.56, + "learning_rate": 7.728981542328773e-07, + "loss": 0.0023, + "step": 56847 + }, + { + "epoch": 17.56, + "learning_rate": 7.727053730083645e-07, + "loss": 0.002, + "step": 56848 + }, + { + "epoch": 17.56, + "learning_rate": 7.725126148629991e-07, + "loss": 0.0011, + "step": 56849 + }, + { + "epoch": 17.56, + "learning_rate": 7.723198797972619e-07, + "loss": 0.0018, + "step": 56850 + }, + { + "epoch": 17.56, + "learning_rate": 7.721271678116383e-07, + "loss": 0.0017, + "step": 56851 + }, + { + "epoch": 17.56, + "learning_rate": 7.719344789066064e-07, + "loss": 0.0019, + "step": 56852 + }, + { + "epoch": 17.56, + "learning_rate": 7.717418130826482e-07, + "loss": 0.002, + "step": 56853 + }, + { + "epoch": 17.56, + "learning_rate": 7.715491703402467e-07, + "loss": 0.0019, + "step": 56854 + }, + { + "epoch": 17.56, + "learning_rate": 7.713565506798859e-07, + "loss": 0.0022, + "step": 56855 + }, + { + "epoch": 17.56, + "learning_rate": 7.711639541020455e-07, + "loss": 0.0024, + "step": 56856 + }, + { + "epoch": 17.56, + "learning_rate": 7.709713806072061e-07, + "loss": 0.0019, + "step": 56857 + }, + { + "epoch": 17.56, + "learning_rate": 7.707788301958507e-07, + "loss": 0.0022, + "step": 56858 + }, + { + "epoch": 17.56, + "learning_rate": 7.705863028684602e-07, + "loss": 0.0018, + "step": 56859 + }, + { + "epoch": 17.56, + "learning_rate": 7.703937986255172e-07, + "loss": 0.002, + "step": 56860 + }, + { + "epoch": 17.56, + "learning_rate": 7.702013174675038e-07, + "loss": 0.0019, + "step": 56861 + }, + { + "epoch": 17.56, + "learning_rate": 7.700088593948996e-07, + "loss": 0.0016, + "step": 56862 + }, + { + "epoch": 17.56, + "learning_rate": 7.698164244081862e-07, + "loss": 0.0027, + "step": 56863 + }, + { + "epoch": 17.56, + "learning_rate": 7.696240125078447e-07, + "loss": 0.002, + "step": 56864 + }, + { + "epoch": 17.56, + "learning_rate": 7.694316236943589e-07, + "loss": 0.0021, + "step": 56865 + }, + { + "epoch": 17.56, + "learning_rate": 7.692392579682062e-07, + "loss": 0.0013, + "step": 56866 + }, + { + "epoch": 17.56, + "learning_rate": 7.690469153298719e-07, + "loss": 0.0016, + "step": 56867 + }, + { + "epoch": 17.56, + "learning_rate": 7.688545957798343e-07, + "loss": 0.0017, + "step": 56868 + }, + { + "epoch": 17.56, + "learning_rate": 7.686622993185733e-07, + "loss": 0.0013, + "step": 56869 + }, + { + "epoch": 17.56, + "learning_rate": 7.684700259465727e-07, + "loss": 0.0018, + "step": 56870 + }, + { + "epoch": 17.56, + "learning_rate": 7.682777756643122e-07, + "loss": 0.0016, + "step": 56871 + }, + { + "epoch": 17.56, + "learning_rate": 7.680855484722738e-07, + "loss": 0.0026, + "step": 56872 + }, + { + "epoch": 17.56, + "learning_rate": 7.678933443709357e-07, + "loss": 0.0024, + "step": 56873 + }, + { + "epoch": 17.56, + "learning_rate": 7.677011633607823e-07, + "loss": 0.0016, + "step": 56874 + }, + { + "epoch": 17.56, + "learning_rate": 7.675090054422896e-07, + "loss": 0.002, + "step": 56875 + }, + { + "epoch": 17.56, + "learning_rate": 7.673168706159406e-07, + "loss": 0.0022, + "step": 56876 + }, + { + "epoch": 17.56, + "learning_rate": 7.671247588822195e-07, + "loss": 0.0017, + "step": 56877 + }, + { + "epoch": 17.56, + "learning_rate": 7.669326702416002e-07, + "loss": 0.0019, + "step": 56878 + }, + { + "epoch": 17.57, + "learning_rate": 7.667406046945669e-07, + "loss": 0.0022, + "step": 56879 + }, + { + "epoch": 17.57, + "learning_rate": 7.665485622416002e-07, + "loss": 0.0014, + "step": 56880 + }, + { + "epoch": 17.57, + "learning_rate": 7.663565428831787e-07, + "loss": 0.0021, + "step": 56881 + }, + { + "epoch": 17.57, + "learning_rate": 7.661645466197853e-07, + "loss": 0.0025, + "step": 56882 + }, + { + "epoch": 17.57, + "learning_rate": 7.659725734518975e-07, + "loss": 0.0018, + "step": 56883 + }, + { + "epoch": 17.57, + "learning_rate": 7.657806233799958e-07, + "loss": 0.0019, + "step": 56884 + }, + { + "epoch": 17.57, + "learning_rate": 7.6558869640456e-07, + "loss": 0.002, + "step": 56885 + }, + { + "epoch": 17.57, + "learning_rate": 7.653967925260741e-07, + "loss": 0.0014, + "step": 56886 + }, + { + "epoch": 17.57, + "learning_rate": 7.652049117450144e-07, + "loss": 0.0016, + "step": 56887 + }, + { + "epoch": 17.57, + "learning_rate": 7.650130540618595e-07, + "loss": 0.0017, + "step": 56888 + }, + { + "epoch": 17.57, + "learning_rate": 7.648212194770932e-07, + "loss": 0.0017, + "step": 56889 + }, + { + "epoch": 17.57, + "learning_rate": 7.64629407991192e-07, + "loss": 0.0016, + "step": 56890 + }, + { + "epoch": 17.57, + "learning_rate": 7.644376196046366e-07, + "loss": 0.0026, + "step": 56891 + }, + { + "epoch": 17.57, + "learning_rate": 7.642458543179099e-07, + "loss": 0.0013, + "step": 56892 + }, + { + "epoch": 17.57, + "learning_rate": 7.640541121314882e-07, + "loss": 0.0014, + "step": 56893 + }, + { + "epoch": 17.57, + "learning_rate": 7.6386239304585e-07, + "loss": 0.0013, + "step": 56894 + }, + { + "epoch": 17.57, + "learning_rate": 7.636706970614761e-07, + "loss": 0.0019, + "step": 56895 + }, + { + "epoch": 17.57, + "learning_rate": 7.634790241788482e-07, + "loss": 0.0016, + "step": 56896 + }, + { + "epoch": 17.57, + "learning_rate": 7.632873743984437e-07, + "loss": 0.0016, + "step": 56897 + }, + { + "epoch": 17.57, + "learning_rate": 7.630957477207413e-07, + "loss": 0.0023, + "step": 56898 + }, + { + "epoch": 17.57, + "learning_rate": 7.629041441462226e-07, + "loss": 0.0017, + "step": 56899 + }, + { + "epoch": 17.57, + "learning_rate": 7.627125636753629e-07, + "loss": 0.0022, + "step": 56900 + }, + { + "epoch": 17.57, + "learning_rate": 7.625210063086452e-07, + "loss": 0.0019, + "step": 56901 + }, + { + "epoch": 17.57, + "learning_rate": 7.623294720465479e-07, + "loss": 0.0015, + "step": 56902 + }, + { + "epoch": 17.57, + "learning_rate": 7.621379608895496e-07, + "loss": 0.0025, + "step": 56903 + }, + { + "epoch": 17.57, + "learning_rate": 7.619464728381276e-07, + "loss": 0.0016, + "step": 56904 + }, + { + "epoch": 17.57, + "learning_rate": 7.617550078927638e-07, + "loss": 0.0018, + "step": 56905 + }, + { + "epoch": 17.57, + "learning_rate": 7.615635660539344e-07, + "loss": 0.0018, + "step": 56906 + }, + { + "epoch": 17.57, + "learning_rate": 7.613721473221214e-07, + "loss": 0.003, + "step": 56907 + }, + { + "epoch": 17.57, + "learning_rate": 7.61180751697801e-07, + "loss": 0.0018, + "step": 56908 + }, + { + "epoch": 17.57, + "learning_rate": 7.609893791814515e-07, + "loss": 0.0023, + "step": 56909 + }, + { + "epoch": 17.57, + "learning_rate": 7.607980297735529e-07, + "loss": 0.002, + "step": 56910 + }, + { + "epoch": 17.58, + "learning_rate": 7.606067034745846e-07, + "loss": 0.0015, + "step": 56911 + }, + { + "epoch": 17.58, + "learning_rate": 7.604154002850228e-07, + "loss": 0.0015, + "step": 56912 + }, + { + "epoch": 17.58, + "learning_rate": 7.602241202053484e-07, + "loss": 0.0016, + "step": 56913 + }, + { + "epoch": 17.58, + "learning_rate": 7.600328632360388e-07, + "loss": 0.0014, + "step": 56914 + }, + { + "epoch": 17.58, + "learning_rate": 7.598416293775712e-07, + "loss": 0.0015, + "step": 56915 + }, + { + "epoch": 17.58, + "learning_rate": 7.596504186304243e-07, + "loss": 0.0016, + "step": 56916 + }, + { + "epoch": 17.58, + "learning_rate": 7.594592309950788e-07, + "loss": 0.0012, + "step": 56917 + }, + { + "epoch": 17.58, + "learning_rate": 7.59268066472012e-07, + "loss": 0.0016, + "step": 56918 + }, + { + "epoch": 17.58, + "learning_rate": 7.590769250616981e-07, + "loss": 0.0014, + "step": 56919 + }, + { + "epoch": 17.58, + "learning_rate": 7.58885806764621e-07, + "loss": 0.0017, + "step": 56920 + }, + { + "epoch": 17.58, + "learning_rate": 7.586947115812537e-07, + "loss": 0.002, + "step": 56921 + }, + { + "epoch": 17.58, + "learning_rate": 7.58503639512077e-07, + "loss": 0.0019, + "step": 56922 + }, + { + "epoch": 17.58, + "learning_rate": 7.583125905575694e-07, + "loss": 0.0022, + "step": 56923 + }, + { + "epoch": 17.58, + "learning_rate": 7.581215647182083e-07, + "loss": 0.0019, + "step": 56924 + }, + { + "epoch": 17.58, + "learning_rate": 7.579305619944688e-07, + "loss": 0.0021, + "step": 56925 + }, + { + "epoch": 17.58, + "learning_rate": 7.577395823868294e-07, + "loss": 0.0023, + "step": 56926 + }, + { + "epoch": 17.58, + "learning_rate": 7.57548625895772e-07, + "loss": 0.0026, + "step": 56927 + }, + { + "epoch": 17.58, + "learning_rate": 7.573576925217707e-07, + "loss": 0.0019, + "step": 56928 + }, + { + "epoch": 17.58, + "learning_rate": 7.571667822653028e-07, + "loss": 0.0022, + "step": 56929 + }, + { + "epoch": 17.58, + "learning_rate": 7.569758951268469e-07, + "loss": 0.0023, + "step": 56930 + }, + { + "epoch": 17.58, + "learning_rate": 7.567850311068792e-07, + "loss": 0.002, + "step": 56931 + }, + { + "epoch": 17.58, + "learning_rate": 7.565941902058782e-07, + "loss": 0.0019, + "step": 56932 + }, + { + "epoch": 17.58, + "learning_rate": 7.564033724243225e-07, + "loss": 0.0023, + "step": 56933 + }, + { + "epoch": 17.58, + "learning_rate": 7.562125777626872e-07, + "loss": 0.0023, + "step": 56934 + }, + { + "epoch": 17.58, + "learning_rate": 7.560218062214497e-07, + "loss": 0.0017, + "step": 56935 + }, + { + "epoch": 17.58, + "learning_rate": 7.558310578010885e-07, + "loss": 0.0022, + "step": 56936 + }, + { + "epoch": 17.58, + "learning_rate": 7.556403325020778e-07, + "loss": 0.0021, + "step": 56937 + }, + { + "epoch": 17.58, + "learning_rate": 7.554496303248992e-07, + "loss": 0.0017, + "step": 56938 + }, + { + "epoch": 17.58, + "learning_rate": 7.552589512700271e-07, + "loss": 0.0023, + "step": 56939 + }, + { + "epoch": 17.58, + "learning_rate": 7.550682953379362e-07, + "loss": 0.0025, + "step": 56940 + }, + { + "epoch": 17.58, + "learning_rate": 7.548776625291066e-07, + "loss": 0.0017, + "step": 56941 + }, + { + "epoch": 17.58, + "learning_rate": 7.546870528440154e-07, + "loss": 0.0021, + "step": 56942 + }, + { + "epoch": 17.59, + "learning_rate": 7.544964662831367e-07, + "loss": 0.002, + "step": 56943 + }, + { + "epoch": 17.59, + "learning_rate": 7.54305902846949e-07, + "loss": 0.002, + "step": 56944 + }, + { + "epoch": 17.59, + "learning_rate": 7.541153625359299e-07, + "loss": 0.0021, + "step": 56945 + }, + { + "epoch": 17.59, + "learning_rate": 7.539248453505532e-07, + "loss": 0.0019, + "step": 56946 + }, + { + "epoch": 17.59, + "learning_rate": 7.537343512912953e-07, + "loss": 0.0017, + "step": 56947 + }, + { + "epoch": 17.59, + "learning_rate": 7.53543880358637e-07, + "loss": 0.0018, + "step": 56948 + }, + { + "epoch": 17.59, + "learning_rate": 7.533534325530523e-07, + "loss": 0.002, + "step": 56949 + }, + { + "epoch": 17.59, + "learning_rate": 7.53163007875014e-07, + "loss": 0.0019, + "step": 56950 + }, + { + "epoch": 17.59, + "learning_rate": 7.529726063250042e-07, + "loss": 0.0018, + "step": 56951 + }, + { + "epoch": 17.59, + "learning_rate": 7.527822279034946e-07, + "loss": 0.0015, + "step": 56952 + }, + { + "epoch": 17.59, + "learning_rate": 7.525918726109638e-07, + "loss": 0.0017, + "step": 56953 + }, + { + "epoch": 17.59, + "learning_rate": 7.524015404478891e-07, + "loss": 0.0014, + "step": 56954 + }, + { + "epoch": 17.59, + "learning_rate": 7.522112314147434e-07, + "loss": 0.0022, + "step": 56955 + }, + { + "epoch": 17.59, + "learning_rate": 7.520209455120031e-07, + "loss": 0.0025, + "step": 56956 + }, + { + "epoch": 17.59, + "learning_rate": 7.518306827401456e-07, + "loss": 0.0019, + "step": 56957 + }, + { + "epoch": 17.59, + "learning_rate": 7.516404430996482e-07, + "loss": 0.0015, + "step": 56958 + }, + { + "epoch": 17.59, + "learning_rate": 7.51450226590984e-07, + "loss": 0.002, + "step": 56959 + }, + { + "epoch": 17.59, + "learning_rate": 7.512600332146281e-07, + "loss": 0.0015, + "step": 56960 + }, + { + "epoch": 17.59, + "learning_rate": 7.5106986297106e-07, + "loss": 0.0029, + "step": 56961 + }, + { + "epoch": 17.59, + "learning_rate": 7.508797158607506e-07, + "loss": 0.0013, + "step": 56962 + }, + { + "epoch": 17.59, + "learning_rate": 7.506895918841783e-07, + "loss": 0.0026, + "step": 56963 + }, + { + "epoch": 17.59, + "learning_rate": 7.504994910418207e-07, + "loss": 0.0023, + "step": 56964 + }, + { + "epoch": 17.59, + "learning_rate": 7.503094133341505e-07, + "loss": 0.002, + "step": 56965 + }, + { + "epoch": 17.59, + "learning_rate": 7.501193587616406e-07, + "loss": 0.0017, + "step": 56966 + }, + { + "epoch": 17.59, + "learning_rate": 7.499293273247721e-07, + "loss": 0.0018, + "step": 56967 + }, + { + "epoch": 17.59, + "learning_rate": 7.497393190240154e-07, + "loss": 0.0018, + "step": 56968 + }, + { + "epoch": 17.59, + "learning_rate": 7.495493338598503e-07, + "loss": 0.002, + "step": 56969 + }, + { + "epoch": 17.59, + "learning_rate": 7.493593718327486e-07, + "loss": 0.002, + "step": 56970 + }, + { + "epoch": 17.59, + "learning_rate": 7.491694329431842e-07, + "loss": 0.0017, + "step": 56971 + }, + { + "epoch": 17.59, + "learning_rate": 7.489795171916359e-07, + "loss": 0.0021, + "step": 56972 + }, + { + "epoch": 17.59, + "learning_rate": 7.487896245785775e-07, + "loss": 0.0022, + "step": 56973 + }, + { + "epoch": 17.59, + "learning_rate": 7.485997551044821e-07, + "loss": 0.0022, + "step": 56974 + }, + { + "epoch": 17.59, + "learning_rate": 7.484099087698282e-07, + "loss": 0.0017, + "step": 56975 + }, + { + "epoch": 17.6, + "learning_rate": 7.482200855750876e-07, + "loss": 0.0017, + "step": 56976 + }, + { + "epoch": 17.6, + "learning_rate": 7.480302855207356e-07, + "loss": 0.0021, + "step": 56977 + }, + { + "epoch": 17.6, + "learning_rate": 7.47840508607246e-07, + "loss": 0.0014, + "step": 56978 + }, + { + "epoch": 17.6, + "learning_rate": 7.476507548350975e-07, + "loss": 0.0026, + "step": 56979 + }, + { + "epoch": 17.6, + "learning_rate": 7.474610242047609e-07, + "loss": 0.0022, + "step": 56980 + }, + { + "epoch": 17.6, + "learning_rate": 7.472713167167112e-07, + "loss": 0.0024, + "step": 56981 + }, + { + "epoch": 17.6, + "learning_rate": 7.470816323714248e-07, + "loss": 0.0016, + "step": 56982 + }, + { + "epoch": 17.6, + "learning_rate": 7.468919711693734e-07, + "loss": 0.0022, + "step": 56983 + }, + { + "epoch": 17.6, + "learning_rate": 7.467023331110323e-07, + "loss": 0.0021, + "step": 56984 + }, + { + "epoch": 17.6, + "learning_rate": 7.4651271819688e-07, + "loss": 0.002, + "step": 56985 + }, + { + "epoch": 17.6, + "learning_rate": 7.46323126427384e-07, + "loss": 0.0022, + "step": 56986 + }, + { + "epoch": 17.6, + "learning_rate": 7.461335578030215e-07, + "loss": 0.0018, + "step": 56987 + }, + { + "epoch": 17.6, + "learning_rate": 7.459440123242678e-07, + "loss": 0.0014, + "step": 56988 + }, + { + "epoch": 17.6, + "learning_rate": 7.457544899915947e-07, + "loss": 0.0017, + "step": 56989 + }, + { + "epoch": 17.6, + "learning_rate": 7.455649908054796e-07, + "loss": 0.0015, + "step": 56990 + }, + { + "epoch": 17.6, + "learning_rate": 7.453755147663921e-07, + "loss": 0.0017, + "step": 56991 + }, + { + "epoch": 17.6, + "learning_rate": 7.451860618748108e-07, + "loss": 0.0016, + "step": 56992 + }, + { + "epoch": 17.6, + "learning_rate": 7.449966321312052e-07, + "loss": 0.0023, + "step": 56993 + }, + { + "epoch": 17.6, + "learning_rate": 7.448072255360505e-07, + "loss": 0.0019, + "step": 56994 + }, + { + "epoch": 17.6, + "learning_rate": 7.446178420898254e-07, + "loss": 0.0019, + "step": 56995 + }, + { + "epoch": 17.6, + "learning_rate": 7.444284817929948e-07, + "loss": 0.0025, + "step": 56996 + }, + { + "epoch": 17.6, + "learning_rate": 7.442391446460373e-07, + "loss": 0.0024, + "step": 56997 + }, + { + "epoch": 17.6, + "learning_rate": 7.440498306494271e-07, + "loss": 0.0021, + "step": 56998 + }, + { + "epoch": 17.6, + "learning_rate": 7.438605398036347e-07, + "loss": 0.0017, + "step": 56999 + }, + { + "epoch": 17.6, + "learning_rate": 7.436712721091365e-07, + "loss": 0.0019, + "step": 57000 + }, + { + "epoch": 17.6, + "learning_rate": 7.434820275664056e-07, + "loss": 0.0017, + "step": 57001 + }, + { + "epoch": 17.6, + "learning_rate": 7.432928061759126e-07, + "loss": 0.0018, + "step": 57002 + }, + { + "epoch": 17.6, + "learning_rate": 7.431036079381326e-07, + "loss": 0.0019, + "step": 57003 + }, + { + "epoch": 17.6, + "learning_rate": 7.42914432853541e-07, + "loss": 0.002, + "step": 57004 + }, + { + "epoch": 17.6, + "learning_rate": 7.427252809226071e-07, + "loss": 0.0015, + "step": 57005 + }, + { + "epoch": 17.6, + "learning_rate": 7.425361521458052e-07, + "loss": 0.0018, + "step": 57006 + }, + { + "epoch": 17.6, + "learning_rate": 7.423470465236104e-07, + "loss": 0.002, + "step": 57007 + }, + { + "epoch": 17.61, + "learning_rate": 7.421579640564924e-07, + "loss": 0.0022, + "step": 57008 + }, + { + "epoch": 17.61, + "learning_rate": 7.419689047449263e-07, + "loss": 0.0016, + "step": 57009 + }, + { + "epoch": 17.61, + "learning_rate": 7.417798685893862e-07, + "loss": 0.0023, + "step": 57010 + }, + { + "epoch": 17.61, + "learning_rate": 7.415908555903428e-07, + "loss": 0.0014, + "step": 57011 + }, + { + "epoch": 17.61, + "learning_rate": 7.41401865748268e-07, + "loss": 0.0018, + "step": 57012 + }, + { + "epoch": 17.61, + "learning_rate": 7.412128990636369e-07, + "loss": 0.0027, + "step": 57013 + }, + { + "epoch": 17.61, + "learning_rate": 7.410239555369192e-07, + "loss": 0.0016, + "step": 57014 + }, + { + "epoch": 17.61, + "learning_rate": 7.408350351685923e-07, + "loss": 0.0024, + "step": 57015 + }, + { + "epoch": 17.61, + "learning_rate": 7.406461379591245e-07, + "loss": 0.0019, + "step": 57016 + }, + { + "epoch": 17.61, + "learning_rate": 7.404572639089879e-07, + "loss": 0.0018, + "step": 57017 + }, + { + "epoch": 17.61, + "learning_rate": 7.402684130186565e-07, + "loss": 0.0017, + "step": 57018 + }, + { + "epoch": 17.61, + "learning_rate": 7.400795852886056e-07, + "loss": 0.0026, + "step": 57019 + }, + { + "epoch": 17.61, + "learning_rate": 7.398907807193012e-07, + "loss": 0.0024, + "step": 57020 + }, + { + "epoch": 17.61, + "learning_rate": 7.39701999311222e-07, + "loss": 0.0022, + "step": 57021 + }, + { + "epoch": 17.61, + "learning_rate": 7.395132410648365e-07, + "loss": 0.0022, + "step": 57022 + }, + { + "epoch": 17.61, + "learning_rate": 7.393245059806154e-07, + "loss": 0.0016, + "step": 57023 + }, + { + "epoch": 17.61, + "learning_rate": 7.391357940590327e-07, + "loss": 0.0015, + "step": 57024 + }, + { + "epoch": 17.61, + "learning_rate": 7.389471053005626e-07, + "loss": 0.0022, + "step": 57025 + }, + { + "epoch": 17.61, + "learning_rate": 7.387584397056746e-07, + "loss": 0.0021, + "step": 57026 + }, + { + "epoch": 17.61, + "learning_rate": 7.385697972748396e-07, + "loss": 0.0025, + "step": 57027 + }, + { + "epoch": 17.61, + "learning_rate": 7.383811780085304e-07, + "loss": 0.0018, + "step": 57028 + }, + { + "epoch": 17.61, + "learning_rate": 7.381925819072211e-07, + "loss": 0.0021, + "step": 57029 + }, + { + "epoch": 17.61, + "learning_rate": 7.380040089713792e-07, + "loss": 0.0023, + "step": 57030 + }, + { + "epoch": 17.61, + "learning_rate": 7.378154592014797e-07, + "loss": 0.0022, + "step": 57031 + }, + { + "epoch": 17.61, + "learning_rate": 7.376269325979946e-07, + "loss": 0.0017, + "step": 57032 + }, + { + "epoch": 17.61, + "learning_rate": 7.374384291613912e-07, + "loss": 0.0026, + "step": 57033 + }, + { + "epoch": 17.61, + "learning_rate": 7.372499488921436e-07, + "loss": 0.0019, + "step": 57034 + }, + { + "epoch": 17.61, + "learning_rate": 7.37061491790726e-07, + "loss": 0.0019, + "step": 57035 + }, + { + "epoch": 17.61, + "learning_rate": 7.368730578576056e-07, + "loss": 0.0016, + "step": 57036 + }, + { + "epoch": 17.61, + "learning_rate": 7.366846470932543e-07, + "loss": 0.0025, + "step": 57037 + }, + { + "epoch": 17.61, + "learning_rate": 7.364962594981462e-07, + "loss": 0.0025, + "step": 57038 + }, + { + "epoch": 17.61, + "learning_rate": 7.363078950727487e-07, + "loss": 0.0021, + "step": 57039 + }, + { + "epoch": 17.61, + "learning_rate": 7.361195538175337e-07, + "loss": 0.0018, + "step": 57040 + }, + { + "epoch": 17.62, + "learning_rate": 7.359312357329762e-07, + "loss": 0.0014, + "step": 57041 + }, + { + "epoch": 17.62, + "learning_rate": 7.357429408195438e-07, + "loss": 0.0021, + "step": 57042 + }, + { + "epoch": 17.62, + "learning_rate": 7.355546690777071e-07, + "loss": 0.0021, + "step": 57043 + }, + { + "epoch": 17.62, + "learning_rate": 7.353664205079381e-07, + "loss": 0.0019, + "step": 57044 + }, + { + "epoch": 17.62, + "learning_rate": 7.351781951107073e-07, + "loss": 0.0018, + "step": 57045 + }, + { + "epoch": 17.62, + "learning_rate": 7.349899928864868e-07, + "loss": 0.0019, + "step": 57046 + }, + { + "epoch": 17.62, + "learning_rate": 7.34801813835746e-07, + "loss": 0.0019, + "step": 57047 + }, + { + "epoch": 17.62, + "learning_rate": 7.346136579589535e-07, + "loss": 0.0018, + "step": 57048 + }, + { + "epoch": 17.62, + "learning_rate": 7.344255252565824e-07, + "loss": 0.0013, + "step": 57049 + }, + { + "epoch": 17.62, + "learning_rate": 7.342374157291054e-07, + "loss": 0.001, + "step": 57050 + }, + { + "epoch": 17.62, + "learning_rate": 7.34049329376989e-07, + "loss": 0.0017, + "step": 57051 + }, + { + "epoch": 17.62, + "learning_rate": 7.338612662007061e-07, + "loss": 0.0017, + "step": 57052 + }, + { + "epoch": 17.62, + "learning_rate": 7.336732262007262e-07, + "loss": 0.0014, + "step": 57053 + }, + { + "epoch": 17.62, + "learning_rate": 7.33485209377518e-07, + "loss": 0.0021, + "step": 57054 + }, + { + "epoch": 17.62, + "learning_rate": 7.332972157315543e-07, + "loss": 0.0013, + "step": 57055 + }, + { + "epoch": 17.62, + "learning_rate": 7.331092452633048e-07, + "loss": 0.0017, + "step": 57056 + }, + { + "epoch": 17.62, + "learning_rate": 7.329212979732403e-07, + "loss": 0.0022, + "step": 57057 + }, + { + "epoch": 17.62, + "learning_rate": 7.327333738618281e-07, + "loss": 0.0019, + "step": 57058 + }, + { + "epoch": 17.62, + "learning_rate": 7.325454729295389e-07, + "loss": 0.0019, + "step": 57059 + }, + { + "epoch": 17.62, + "learning_rate": 7.323575951768469e-07, + "loss": 0.0021, + "step": 57060 + }, + { + "epoch": 17.62, + "learning_rate": 7.321697406042161e-07, + "loss": 0.0011, + "step": 57061 + }, + { + "epoch": 17.62, + "learning_rate": 7.319819092121217e-07, + "loss": 0.002, + "step": 57062 + }, + { + "epoch": 17.62, + "learning_rate": 7.317941010010299e-07, + "loss": 0.0018, + "step": 57063 + }, + { + "epoch": 17.62, + "learning_rate": 7.316063159714104e-07, + "loss": 0.0019, + "step": 57064 + }, + { + "epoch": 17.62, + "learning_rate": 7.31418554123734e-07, + "loss": 0.0017, + "step": 57065 + }, + { + "epoch": 17.62, + "learning_rate": 7.312308154584713e-07, + "loss": 0.0032, + "step": 57066 + }, + { + "epoch": 17.62, + "learning_rate": 7.310430999760909e-07, + "loss": 0.0012, + "step": 57067 + }, + { + "epoch": 17.62, + "learning_rate": 7.308554076770613e-07, + "loss": 0.0014, + "step": 57068 + }, + { + "epoch": 17.62, + "learning_rate": 7.306677385618543e-07, + "loss": 0.0015, + "step": 57069 + }, + { + "epoch": 17.62, + "learning_rate": 7.304800926309363e-07, + "loss": 0.0023, + "step": 57070 + }, + { + "epoch": 17.62, + "learning_rate": 7.30292469884778e-07, + "loss": 0.0017, + "step": 57071 + }, + { + "epoch": 17.62, + "learning_rate": 7.301048703238512e-07, + "loss": 0.0022, + "step": 57072 + }, + { + "epoch": 17.63, + "learning_rate": 7.299172939486221e-07, + "loss": 0.0019, + "step": 57073 + }, + { + "epoch": 17.63, + "learning_rate": 7.297297407595594e-07, + "loss": 0.0015, + "step": 57074 + }, + { + "epoch": 17.63, + "learning_rate": 7.295422107571348e-07, + "loss": 0.0019, + "step": 57075 + }, + { + "epoch": 17.63, + "learning_rate": 7.293547039418147e-07, + "loss": 0.0018, + "step": 57076 + }, + { + "epoch": 17.63, + "learning_rate": 7.29167220314071e-07, + "loss": 0.0027, + "step": 57077 + }, + { + "epoch": 17.63, + "learning_rate": 7.289797598743709e-07, + "loss": 0.0016, + "step": 57078 + }, + { + "epoch": 17.63, + "learning_rate": 7.287923226231808e-07, + "loss": 0.002, + "step": 57079 + }, + { + "epoch": 17.63, + "learning_rate": 7.286049085609726e-07, + "loss": 0.002, + "step": 57080 + }, + { + "epoch": 17.63, + "learning_rate": 7.284175176882169e-07, + "loss": 0.0018, + "step": 57081 + }, + { + "epoch": 17.63, + "learning_rate": 7.282301500053779e-07, + "loss": 0.0018, + "step": 57082 + }, + { + "epoch": 17.63, + "learning_rate": 7.280428055129274e-07, + "loss": 0.0015, + "step": 57083 + }, + { + "epoch": 17.63, + "learning_rate": 7.278554842113339e-07, + "loss": 0.0018, + "step": 57084 + }, + { + "epoch": 17.63, + "learning_rate": 7.276681861010626e-07, + "loss": 0.0028, + "step": 57085 + }, + { + "epoch": 17.63, + "learning_rate": 7.274809111825842e-07, + "loss": 0.0018, + "step": 57086 + }, + { + "epoch": 17.63, + "learning_rate": 7.272936594563696e-07, + "loss": 0.0019, + "step": 57087 + }, + { + "epoch": 17.63, + "learning_rate": 7.271064309228848e-07, + "loss": 0.0021, + "step": 57088 + }, + { + "epoch": 17.63, + "learning_rate": 7.269192255825963e-07, + "loss": 0.002, + "step": 57089 + }, + { + "epoch": 17.63, + "learning_rate": 7.267320434359737e-07, + "loss": 0.0027, + "step": 57090 + }, + { + "epoch": 17.63, + "learning_rate": 7.265448844834877e-07, + "loss": 0.0015, + "step": 57091 + }, + { + "epoch": 17.63, + "learning_rate": 7.263577487256024e-07, + "loss": 0.0022, + "step": 57092 + }, + { + "epoch": 17.63, + "learning_rate": 7.261706361627896e-07, + "loss": 0.0021, + "step": 57093 + }, + { + "epoch": 17.63, + "learning_rate": 7.259835467955145e-07, + "loss": 0.0012, + "step": 57094 + }, + { + "epoch": 17.63, + "learning_rate": 7.257964806242456e-07, + "loss": 0.0025, + "step": 57095 + }, + { + "epoch": 17.63, + "learning_rate": 7.256094376494505e-07, + "loss": 0.0019, + "step": 57096 + }, + { + "epoch": 17.63, + "learning_rate": 7.254224178716007e-07, + "loss": 0.002, + "step": 57097 + }, + { + "epoch": 17.63, + "learning_rate": 7.252354212911594e-07, + "loss": 0.0021, + "step": 57098 + }, + { + "epoch": 17.63, + "learning_rate": 7.250484479085951e-07, + "loss": 0.0027, + "step": 57099 + }, + { + "epoch": 17.63, + "learning_rate": 7.248614977243773e-07, + "loss": 0.0016, + "step": 57100 + }, + { + "epoch": 17.63, + "learning_rate": 7.246745707389724e-07, + "loss": 0.0022, + "step": 57101 + }, + { + "epoch": 17.63, + "learning_rate": 7.244876669528467e-07, + "loss": 0.0014, + "step": 57102 + }, + { + "epoch": 17.63, + "learning_rate": 7.24300786366473e-07, + "loss": 0.0018, + "step": 57103 + }, + { + "epoch": 17.63, + "learning_rate": 7.241139289803111e-07, + "loss": 0.0021, + "step": 57104 + }, + { + "epoch": 17.64, + "learning_rate": 7.239270947948318e-07, + "loss": 0.0019, + "step": 57105 + }, + { + "epoch": 17.64, + "learning_rate": 7.237402838105057e-07, + "loss": 0.0014, + "step": 57106 + }, + { + "epoch": 17.64, + "learning_rate": 7.235534960277946e-07, + "loss": 0.0016, + "step": 57107 + }, + { + "epoch": 17.64, + "learning_rate": 7.233667314471693e-07, + "loss": 0.0016, + "step": 57108 + }, + { + "epoch": 17.64, + "learning_rate": 7.231799900690961e-07, + "loss": 0.0044, + "step": 57109 + }, + { + "epoch": 17.64, + "learning_rate": 7.229932718940403e-07, + "loss": 0.0018, + "step": 57110 + }, + { + "epoch": 17.64, + "learning_rate": 7.228065769224701e-07, + "loss": 0.002, + "step": 57111 + }, + { + "epoch": 17.64, + "learning_rate": 7.226199051548543e-07, + "loss": 0.0021, + "step": 57112 + }, + { + "epoch": 17.64, + "learning_rate": 7.224332565916581e-07, + "loss": 0.0027, + "step": 57113 + }, + { + "epoch": 17.64, + "learning_rate": 7.222466312333476e-07, + "loss": 0.0016, + "step": 57114 + }, + { + "epoch": 17.64, + "learning_rate": 7.220600290803914e-07, + "loss": 0.0019, + "step": 57115 + }, + { + "epoch": 17.64, + "learning_rate": 7.218734501332536e-07, + "loss": 0.0019, + "step": 57116 + }, + { + "epoch": 17.64, + "learning_rate": 7.216868943924027e-07, + "loss": 0.0017, + "step": 57117 + }, + { + "epoch": 17.64, + "learning_rate": 7.21500361858306e-07, + "loss": 0.0018, + "step": 57118 + }, + { + "epoch": 17.64, + "learning_rate": 7.2131385253143e-07, + "loss": 0.0019, + "step": 57119 + }, + { + "epoch": 17.64, + "learning_rate": 7.211273664122387e-07, + "loss": 0.0021, + "step": 57120 + }, + { + "epoch": 17.64, + "learning_rate": 7.209409035012005e-07, + "loss": 0.0027, + "step": 57121 + }, + { + "epoch": 17.64, + "learning_rate": 7.207544637987829e-07, + "loss": 0.002, + "step": 57122 + }, + { + "epoch": 17.64, + "learning_rate": 7.20568047305451e-07, + "loss": 0.0016, + "step": 57123 + }, + { + "epoch": 17.64, + "learning_rate": 7.203816540216691e-07, + "loss": 0.0024, + "step": 57124 + }, + { + "epoch": 17.64, + "learning_rate": 7.201952839479065e-07, + "loss": 0.0015, + "step": 57125 + }, + { + "epoch": 17.64, + "learning_rate": 7.200089370846263e-07, + "loss": 0.0013, + "step": 57126 + }, + { + "epoch": 17.64, + "learning_rate": 7.198226134322961e-07, + "loss": 0.0024, + "step": 57127 + }, + { + "epoch": 17.64, + "learning_rate": 7.196363129913842e-07, + "loss": 0.0023, + "step": 57128 + }, + { + "epoch": 17.64, + "learning_rate": 7.194500357623546e-07, + "loss": 0.0022, + "step": 57129 + }, + { + "epoch": 17.64, + "learning_rate": 7.192637817456715e-07, + "loss": 0.0017, + "step": 57130 + }, + { + "epoch": 17.64, + "learning_rate": 7.190775509418046e-07, + "loss": 0.0019, + "step": 57131 + }, + { + "epoch": 17.64, + "learning_rate": 7.188913433512145e-07, + "loss": 0.002, + "step": 57132 + }, + { + "epoch": 17.64, + "learning_rate": 7.18705158974371e-07, + "loss": 0.0023, + "step": 57133 + }, + { + "epoch": 17.64, + "learning_rate": 7.185189978117413e-07, + "loss": 0.0023, + "step": 57134 + }, + { + "epoch": 17.64, + "learning_rate": 7.183328598637862e-07, + "loss": 0.002, + "step": 57135 + }, + { + "epoch": 17.64, + "learning_rate": 7.18146745130972e-07, + "loss": 0.0016, + "step": 57136 + }, + { + "epoch": 17.64, + "learning_rate": 7.179606536137685e-07, + "loss": 0.0016, + "step": 57137 + }, + { + "epoch": 17.65, + "learning_rate": 7.177745853126361e-07, + "loss": 0.0017, + "step": 57138 + }, + { + "epoch": 17.65, + "learning_rate": 7.175885402280447e-07, + "loss": 0.0018, + "step": 57139 + }, + { + "epoch": 17.65, + "learning_rate": 7.174025183604571e-07, + "loss": 0.0013, + "step": 57140 + }, + { + "epoch": 17.65, + "learning_rate": 7.172165197103364e-07, + "loss": 0.0018, + "step": 57141 + }, + { + "epoch": 17.65, + "learning_rate": 7.170305442781511e-07, + "loss": 0.0019, + "step": 57142 + }, + { + "epoch": 17.65, + "learning_rate": 7.168445920643674e-07, + "loss": 0.0019, + "step": 57143 + }, + { + "epoch": 17.65, + "learning_rate": 7.166586630694472e-07, + "loss": 0.0019, + "step": 57144 + }, + { + "epoch": 17.65, + "learning_rate": 7.164727572938568e-07, + "loss": 0.0016, + "step": 57145 + }, + { + "epoch": 17.65, + "learning_rate": 7.162868747380614e-07, + "loss": 0.0022, + "step": 57146 + }, + { + "epoch": 17.65, + "learning_rate": 7.16101015402525e-07, + "loss": 0.0017, + "step": 57147 + }, + { + "epoch": 17.65, + "learning_rate": 7.159151792877139e-07, + "loss": 0.0015, + "step": 57148 + }, + { + "epoch": 17.65, + "learning_rate": 7.157293663940923e-07, + "loss": 0.0013, + "step": 57149 + }, + { + "epoch": 17.65, + "learning_rate": 7.155435767221264e-07, + "loss": 0.0018, + "step": 57150 + }, + { + "epoch": 17.65, + "learning_rate": 7.15357810272277e-07, + "loss": 0.0018, + "step": 57151 + }, + { + "epoch": 17.65, + "learning_rate": 7.151720670450124e-07, + "loss": 0.0017, + "step": 57152 + }, + { + "epoch": 17.65, + "learning_rate": 7.149863470407948e-07, + "loss": 0.0016, + "step": 57153 + }, + { + "epoch": 17.65, + "learning_rate": 7.148006502600913e-07, + "loss": 0.0025, + "step": 57154 + }, + { + "epoch": 17.65, + "learning_rate": 7.146149767033639e-07, + "loss": 0.0016, + "step": 57155 + }, + { + "epoch": 17.65, + "learning_rate": 7.144293263710789e-07, + "loss": 0.0025, + "step": 57156 + }, + { + "epoch": 17.65, + "learning_rate": 7.142436992636981e-07, + "loss": 0.0018, + "step": 57157 + }, + { + "epoch": 17.65, + "learning_rate": 7.140580953816878e-07, + "loss": 0.0025, + "step": 57158 + }, + { + "epoch": 17.65, + "learning_rate": 7.138725147255132e-07, + "loss": 0.0022, + "step": 57159 + }, + { + "epoch": 17.65, + "learning_rate": 7.136869572956373e-07, + "loss": 0.0019, + "step": 57160 + }, + { + "epoch": 17.65, + "learning_rate": 7.135014230925219e-07, + "loss": 0.0019, + "step": 57161 + }, + { + "epoch": 17.65, + "learning_rate": 7.133159121166355e-07, + "loss": 0.0015, + "step": 57162 + }, + { + "epoch": 17.65, + "learning_rate": 7.131304243684379e-07, + "loss": 0.0018, + "step": 57163 + }, + { + "epoch": 17.65, + "learning_rate": 7.129449598483962e-07, + "loss": 0.0019, + "step": 57164 + }, + { + "epoch": 17.65, + "learning_rate": 7.127595185569736e-07, + "loss": 0.0019, + "step": 57165 + }, + { + "epoch": 17.65, + "learning_rate": 7.125741004946318e-07, + "loss": 0.0015, + "step": 57166 + }, + { + "epoch": 17.65, + "learning_rate": 7.123887056618351e-07, + "loss": 0.0017, + "step": 57167 + }, + { + "epoch": 17.65, + "learning_rate": 7.122033340590506e-07, + "loss": 0.0019, + "step": 57168 + }, + { + "epoch": 17.65, + "learning_rate": 7.120179856867381e-07, + "loss": 0.0018, + "step": 57169 + }, + { + "epoch": 17.66, + "learning_rate": 7.118326605453641e-07, + "loss": 0.0016, + "step": 57170 + }, + { + "epoch": 17.66, + "learning_rate": 7.116473586353901e-07, + "loss": 0.0018, + "step": 57171 + }, + { + "epoch": 17.66, + "learning_rate": 7.114620799572791e-07, + "loss": 0.0017, + "step": 57172 + }, + { + "epoch": 17.66, + "learning_rate": 7.112768245114954e-07, + "loss": 0.0018, + "step": 57173 + }, + { + "epoch": 17.66, + "learning_rate": 7.11091592298504e-07, + "loss": 0.0016, + "step": 57174 + }, + { + "epoch": 17.66, + "learning_rate": 7.109063833187668e-07, + "loss": 0.0017, + "step": 57175 + }, + { + "epoch": 17.66, + "learning_rate": 7.107211975727457e-07, + "loss": 0.0022, + "step": 57176 + }, + { + "epoch": 17.66, + "learning_rate": 7.105360350609069e-07, + "loss": 0.0018, + "step": 57177 + }, + { + "epoch": 17.66, + "learning_rate": 7.10350895783709e-07, + "loss": 0.0019, + "step": 57178 + }, + { + "epoch": 17.66, + "learning_rate": 7.101657797416195e-07, + "loss": 0.0017, + "step": 57179 + }, + { + "epoch": 17.66, + "learning_rate": 7.099806869351e-07, + "loss": 0.0013, + "step": 57180 + }, + { + "epoch": 17.66, + "learning_rate": 7.097956173646136e-07, + "loss": 0.002, + "step": 57181 + }, + { + "epoch": 17.66, + "learning_rate": 7.096105710306212e-07, + "loss": 0.0016, + "step": 57182 + }, + { + "epoch": 17.66, + "learning_rate": 7.094255479335888e-07, + "loss": 0.0023, + "step": 57183 + }, + { + "epoch": 17.66, + "learning_rate": 7.092405480739761e-07, + "loss": 0.0025, + "step": 57184 + }, + { + "epoch": 17.66, + "learning_rate": 7.090555714522485e-07, + "loss": 0.0017, + "step": 57185 + }, + { + "epoch": 17.66, + "learning_rate": 7.088706180688665e-07, + "loss": 0.0018, + "step": 57186 + }, + { + "epoch": 17.66, + "learning_rate": 7.086856879242953e-07, + "loss": 0.0018, + "step": 57187 + }, + { + "epoch": 17.66, + "learning_rate": 7.085007810189937e-07, + "loss": 0.0016, + "step": 57188 + }, + { + "epoch": 17.66, + "learning_rate": 7.083158973534265e-07, + "loss": 0.002, + "step": 57189 + }, + { + "epoch": 17.66, + "learning_rate": 7.081310369280581e-07, + "loss": 0.0019, + "step": 57190 + }, + { + "epoch": 17.66, + "learning_rate": 7.079461997433479e-07, + "loss": 0.0016, + "step": 57191 + }, + { + "epoch": 17.66, + "learning_rate": 7.077613857997578e-07, + "loss": 0.0015, + "step": 57192 + }, + { + "epoch": 17.66, + "learning_rate": 7.07576595097752e-07, + "loss": 0.0018, + "step": 57193 + }, + { + "epoch": 17.66, + "learning_rate": 7.073918276377911e-07, + "loss": 0.0015, + "step": 57194 + }, + { + "epoch": 17.66, + "learning_rate": 7.072070834203404e-07, + "loss": 0.0015, + "step": 57195 + }, + { + "epoch": 17.66, + "learning_rate": 7.070223624458594e-07, + "loss": 0.0025, + "step": 57196 + }, + { + "epoch": 17.66, + "learning_rate": 7.068376647148078e-07, + "loss": 0.0018, + "step": 57197 + }, + { + "epoch": 17.66, + "learning_rate": 7.066529902276509e-07, + "loss": 0.0015, + "step": 57198 + }, + { + "epoch": 17.66, + "learning_rate": 7.064683389848514e-07, + "loss": 0.0015, + "step": 57199 + }, + { + "epoch": 17.66, + "learning_rate": 7.062837109868681e-07, + "loss": 0.0018, + "step": 57200 + }, + { + "epoch": 17.66, + "learning_rate": 7.06099106234166e-07, + "loss": 0.0018, + "step": 57201 + }, + { + "epoch": 17.66, + "learning_rate": 7.059145247272048e-07, + "loss": 0.0011, + "step": 57202 + }, + { + "epoch": 17.67, + "learning_rate": 7.057299664664452e-07, + "loss": 0.0023, + "step": 57203 + }, + { + "epoch": 17.67, + "learning_rate": 7.055454314523502e-07, + "loss": 0.0021, + "step": 57204 + }, + { + "epoch": 17.67, + "learning_rate": 7.053609196853828e-07, + "loss": 0.0021, + "step": 57205 + }, + { + "epoch": 17.67, + "learning_rate": 7.051764311660026e-07, + "loss": 0.0019, + "step": 57206 + }, + { + "epoch": 17.67, + "learning_rate": 7.049919658946702e-07, + "loss": 0.0019, + "step": 57207 + }, + { + "epoch": 17.67, + "learning_rate": 7.048075238718488e-07, + "loss": 0.0013, + "step": 57208 + }, + { + "epoch": 17.67, + "learning_rate": 7.04623105097999e-07, + "loss": 0.0014, + "step": 57209 + }, + { + "epoch": 17.67, + "learning_rate": 7.044387095735816e-07, + "loss": 0.0019, + "step": 57210 + }, + { + "epoch": 17.67, + "learning_rate": 7.042543372990595e-07, + "loss": 0.0016, + "step": 57211 + }, + { + "epoch": 17.67, + "learning_rate": 7.040699882748936e-07, + "loss": 0.0017, + "step": 57212 + }, + { + "epoch": 17.67, + "learning_rate": 7.038856625015422e-07, + "loss": 0.0022, + "step": 57213 + }, + { + "epoch": 17.67, + "learning_rate": 7.037013599794695e-07, + "loss": 0.0025, + "step": 57214 + }, + { + "epoch": 17.67, + "learning_rate": 7.03517080709134e-07, + "loss": 0.0021, + "step": 57215 + }, + { + "epoch": 17.67, + "learning_rate": 7.033328246909998e-07, + "loss": 0.0022, + "step": 57216 + }, + { + "epoch": 17.67, + "learning_rate": 7.031485919255254e-07, + "loss": 0.0022, + "step": 57217 + }, + { + "epoch": 17.67, + "learning_rate": 7.029643824131704e-07, + "loss": 0.0021, + "step": 57218 + }, + { + "epoch": 17.67, + "learning_rate": 7.027801961543968e-07, + "loss": 0.002, + "step": 57219 + }, + { + "epoch": 17.67, + "learning_rate": 7.025960331496661e-07, + "loss": 0.0029, + "step": 57220 + }, + { + "epoch": 17.67, + "learning_rate": 7.024118933994394e-07, + "loss": 0.0016, + "step": 57221 + }, + { + "epoch": 17.67, + "learning_rate": 7.022277769041774e-07, + "loss": 0.0023, + "step": 57222 + }, + { + "epoch": 17.67, + "learning_rate": 7.020436836643374e-07, + "loss": 0.0018, + "step": 57223 + }, + { + "epoch": 17.67, + "learning_rate": 7.018596136803835e-07, + "loss": 0.0018, + "step": 57224 + }, + { + "epoch": 17.67, + "learning_rate": 7.01675566952773e-07, + "loss": 0.0015, + "step": 57225 + }, + { + "epoch": 17.67, + "learning_rate": 7.014915434819692e-07, + "loss": 0.0018, + "step": 57226 + }, + { + "epoch": 17.67, + "learning_rate": 7.013075432684313e-07, + "loss": 0.0018, + "step": 57227 + }, + { + "epoch": 17.67, + "learning_rate": 7.011235663126181e-07, + "loss": 0.0024, + "step": 57228 + }, + { + "epoch": 17.67, + "learning_rate": 7.009396126149903e-07, + "loss": 0.002, + "step": 57229 + }, + { + "epoch": 17.67, + "learning_rate": 7.007556821760097e-07, + "loss": 0.0024, + "step": 57230 + }, + { + "epoch": 17.67, + "learning_rate": 7.005717749961349e-07, + "loss": 0.0016, + "step": 57231 + }, + { + "epoch": 17.67, + "learning_rate": 7.003878910758266e-07, + "loss": 0.0013, + "step": 57232 + }, + { + "epoch": 17.67, + "learning_rate": 7.002040304155444e-07, + "loss": 0.0015, + "step": 57233 + }, + { + "epoch": 17.67, + "learning_rate": 7.00020193015748e-07, + "loss": 0.0024, + "step": 57234 + }, + { + "epoch": 17.68, + "learning_rate": 6.998363788768958e-07, + "loss": 0.002, + "step": 57235 + }, + { + "epoch": 17.68, + "learning_rate": 6.996525879994509e-07, + "loss": 0.0018, + "step": 57236 + }, + { + "epoch": 17.68, + "learning_rate": 6.994688203838717e-07, + "loss": 0.0026, + "step": 57237 + }, + { + "epoch": 17.68, + "learning_rate": 6.992850760306147e-07, + "loss": 0.0016, + "step": 57238 + }, + { + "epoch": 17.68, + "learning_rate": 6.991013549401449e-07, + "loss": 0.0023, + "step": 57239 + }, + { + "epoch": 17.68, + "learning_rate": 6.989176571129164e-07, + "loss": 0.0019, + "step": 57240 + }, + { + "epoch": 17.68, + "learning_rate": 6.987339825493911e-07, + "loss": 0.002, + "step": 57241 + }, + { + "epoch": 17.68, + "learning_rate": 6.98550331250033e-07, + "loss": 0.0019, + "step": 57242 + }, + { + "epoch": 17.68, + "learning_rate": 6.98366703215293e-07, + "loss": 0.0022, + "step": 57243 + }, + { + "epoch": 17.68, + "learning_rate": 6.981830984456339e-07, + "loss": 0.0022, + "step": 57244 + }, + { + "epoch": 17.68, + "learning_rate": 6.979995169415176e-07, + "loss": 0.0022, + "step": 57245 + }, + { + "epoch": 17.68, + "learning_rate": 6.978159587033994e-07, + "loss": 0.0018, + "step": 57246 + }, + { + "epoch": 17.68, + "learning_rate": 6.976324237317422e-07, + "loss": 0.0037, + "step": 57247 + }, + { + "epoch": 17.68, + "learning_rate": 6.974489120270023e-07, + "loss": 0.0022, + "step": 57248 + }, + { + "epoch": 17.68, + "learning_rate": 6.972654235896381e-07, + "loss": 0.0017, + "step": 57249 + }, + { + "epoch": 17.68, + "learning_rate": 6.970819584201094e-07, + "loss": 0.0017, + "step": 57250 + }, + { + "epoch": 17.68, + "learning_rate": 6.96898516518878e-07, + "loss": 0.0019, + "step": 57251 + }, + { + "epoch": 17.68, + "learning_rate": 6.96715097886399e-07, + "loss": 0.0019, + "step": 57252 + }, + { + "epoch": 17.68, + "learning_rate": 6.965317025231311e-07, + "loss": 0.0016, + "step": 57253 + }, + { + "epoch": 17.68, + "learning_rate": 6.963483304295348e-07, + "loss": 0.0026, + "step": 57254 + }, + { + "epoch": 17.68, + "learning_rate": 6.961649816060689e-07, + "loss": 0.0013, + "step": 57255 + }, + { + "epoch": 17.68, + "learning_rate": 6.959816560531906e-07, + "loss": 0.0016, + "step": 57256 + }, + { + "epoch": 17.68, + "learning_rate": 6.957983537713609e-07, + "loss": 0.0018, + "step": 57257 + }, + { + "epoch": 17.68, + "learning_rate": 6.956150747610357e-07, + "loss": 0.0014, + "step": 57258 + }, + { + "epoch": 17.68, + "learning_rate": 6.954318190226728e-07, + "loss": 0.0016, + "step": 57259 + }, + { + "epoch": 17.68, + "learning_rate": 6.952485865567316e-07, + "loss": 0.0022, + "step": 57260 + }, + { + "epoch": 17.68, + "learning_rate": 6.950653773636729e-07, + "loss": 0.0019, + "step": 57261 + }, + { + "epoch": 17.68, + "learning_rate": 6.948821914439529e-07, + "loss": 0.0021, + "step": 57262 + }, + { + "epoch": 17.68, + "learning_rate": 6.946990287980282e-07, + "loss": 0.0023, + "step": 57263 + }, + { + "epoch": 17.68, + "learning_rate": 6.945158894263592e-07, + "loss": 0.0031, + "step": 57264 + }, + { + "epoch": 17.68, + "learning_rate": 6.943327733294025e-07, + "loss": 0.0015, + "step": 57265 + }, + { + "epoch": 17.68, + "learning_rate": 6.941496805076164e-07, + "loss": 0.0014, + "step": 57266 + }, + { + "epoch": 17.69, + "learning_rate": 6.939666109614607e-07, + "loss": 0.0017, + "step": 57267 + }, + { + "epoch": 17.69, + "learning_rate": 6.937835646913915e-07, + "loss": 0.0014, + "step": 57268 + }, + { + "epoch": 17.69, + "learning_rate": 6.936005416978653e-07, + "loss": 0.0021, + "step": 57269 + }, + { + "epoch": 17.69, + "learning_rate": 6.934175419813438e-07, + "loss": 0.0024, + "step": 57270 + }, + { + "epoch": 17.69, + "learning_rate": 6.932345655422812e-07, + "loss": 0.0029, + "step": 57271 + }, + { + "epoch": 17.69, + "learning_rate": 6.930516123811371e-07, + "loss": 0.0017, + "step": 57272 + }, + { + "epoch": 17.69, + "learning_rate": 6.928686824983688e-07, + "loss": 0.0017, + "step": 57273 + }, + { + "epoch": 17.69, + "learning_rate": 6.926857758944317e-07, + "loss": 0.0013, + "step": 57274 + }, + { + "epoch": 17.69, + "learning_rate": 6.925028925697852e-07, + "loss": 0.0019, + "step": 57275 + }, + { + "epoch": 17.69, + "learning_rate": 6.92320032524888e-07, + "loss": 0.0019, + "step": 57276 + }, + { + "epoch": 17.69, + "learning_rate": 6.921371957601941e-07, + "loss": 0.0021, + "step": 57277 + }, + { + "epoch": 17.69, + "learning_rate": 6.919543822761654e-07, + "loss": 0.002, + "step": 57278 + }, + { + "epoch": 17.69, + "learning_rate": 6.917715920732549e-07, + "loss": 0.0022, + "step": 57279 + }, + { + "epoch": 17.69, + "learning_rate": 6.91588825151921e-07, + "loss": 0.0019, + "step": 57280 + }, + { + "epoch": 17.69, + "learning_rate": 6.914060815126212e-07, + "loss": 0.0021, + "step": 57281 + }, + { + "epoch": 17.69, + "learning_rate": 6.912233611558139e-07, + "loss": 0.0023, + "step": 57282 + }, + { + "epoch": 17.69, + "learning_rate": 6.910406640819545e-07, + "loss": 0.0021, + "step": 57283 + }, + { + "epoch": 17.69, + "learning_rate": 6.90857990291498e-07, + "loss": 0.0017, + "step": 57284 + }, + { + "epoch": 17.69, + "learning_rate": 6.906753397849053e-07, + "loss": 0.0019, + "step": 57285 + }, + { + "epoch": 17.69, + "learning_rate": 6.904927125626315e-07, + "loss": 0.0016, + "step": 57286 + }, + { + "epoch": 17.69, + "learning_rate": 6.903101086251329e-07, + "loss": 0.0018, + "step": 57287 + }, + { + "epoch": 17.69, + "learning_rate": 6.90127527972867e-07, + "loss": 0.0015, + "step": 57288 + }, + { + "epoch": 17.69, + "learning_rate": 6.899449706062911e-07, + "loss": 0.0013, + "step": 57289 + }, + { + "epoch": 17.69, + "learning_rate": 6.897624365258593e-07, + "loss": 0.002, + "step": 57290 + }, + { + "epoch": 17.69, + "learning_rate": 6.895799257320302e-07, + "loss": 0.0026, + "step": 57291 + }, + { + "epoch": 17.69, + "learning_rate": 6.8939743822526e-07, + "loss": 0.0016, + "step": 57292 + }, + { + "epoch": 17.69, + "learning_rate": 6.892149740060061e-07, + "loss": 0.0014, + "step": 57293 + }, + { + "epoch": 17.69, + "learning_rate": 6.890325330747216e-07, + "loss": 0.0016, + "step": 57294 + }, + { + "epoch": 17.69, + "learning_rate": 6.888501154318672e-07, + "loss": 0.0015, + "step": 57295 + }, + { + "epoch": 17.69, + "learning_rate": 6.886677210778947e-07, + "loss": 0.0016, + "step": 57296 + }, + { + "epoch": 17.69, + "learning_rate": 6.884853500132627e-07, + "loss": 0.0027, + "step": 57297 + }, + { + "epoch": 17.69, + "learning_rate": 6.883030022384285e-07, + "loss": 0.0021, + "step": 57298 + }, + { + "epoch": 17.69, + "learning_rate": 6.881206777538474e-07, + "loss": 0.0015, + "step": 57299 + }, + { + "epoch": 17.7, + "learning_rate": 6.879383765599723e-07, + "loss": 0.0013, + "step": 57300 + }, + { + "epoch": 17.7, + "learning_rate": 6.87756098657264e-07, + "loss": 0.0023, + "step": 57301 + }, + { + "epoch": 17.7, + "learning_rate": 6.875738440461754e-07, + "loss": 0.0018, + "step": 57302 + }, + { + "epoch": 17.7, + "learning_rate": 6.873916127271629e-07, + "loss": 0.0026, + "step": 57303 + }, + { + "epoch": 17.7, + "learning_rate": 6.872094047006838e-07, + "loss": 0.002, + "step": 57304 + }, + { + "epoch": 17.7, + "learning_rate": 6.870272199671901e-07, + "loss": 0.0018, + "step": 57305 + }, + { + "epoch": 17.7, + "learning_rate": 6.868450585271403e-07, + "loss": 0.0017, + "step": 57306 + }, + { + "epoch": 17.7, + "learning_rate": 6.866629203809916e-07, + "loss": 0.0021, + "step": 57307 + }, + { + "epoch": 17.7, + "learning_rate": 6.864808055291961e-07, + "loss": 0.0021, + "step": 57308 + }, + { + "epoch": 17.7, + "learning_rate": 6.862987139722111e-07, + "loss": 0.0016, + "step": 57309 + }, + { + "epoch": 17.7, + "learning_rate": 6.861166457104928e-07, + "loss": 0.0021, + "step": 57310 + }, + { + "epoch": 17.7, + "learning_rate": 6.859346007444934e-07, + "loss": 0.0023, + "step": 57311 + }, + { + "epoch": 17.7, + "learning_rate": 6.85752579074671e-07, + "loss": 0.0021, + "step": 57312 + }, + { + "epoch": 17.7, + "learning_rate": 6.855705807014812e-07, + "loss": 0.0024, + "step": 57313 + }, + { + "epoch": 17.7, + "learning_rate": 6.853886056253789e-07, + "loss": 0.0022, + "step": 57314 + }, + { + "epoch": 17.7, + "learning_rate": 6.85206653846816e-07, + "loss": 0.0018, + "step": 57315 + }, + { + "epoch": 17.7, + "learning_rate": 6.850247253662523e-07, + "loss": 0.0017, + "step": 57316 + }, + { + "epoch": 17.7, + "learning_rate": 6.848428201841395e-07, + "loss": 0.0024, + "step": 57317 + }, + { + "epoch": 17.7, + "learning_rate": 6.846609383009329e-07, + "loss": 0.0015, + "step": 57318 + }, + { + "epoch": 17.7, + "learning_rate": 6.844790797170908e-07, + "loss": 0.0019, + "step": 57319 + }, + { + "epoch": 17.7, + "learning_rate": 6.842972444330653e-07, + "loss": 0.0022, + "step": 57320 + }, + { + "epoch": 17.7, + "learning_rate": 6.841154324493094e-07, + "loss": 0.0016, + "step": 57321 + }, + { + "epoch": 17.7, + "learning_rate": 6.839336437662802e-07, + "loss": 0.0022, + "step": 57322 + }, + { + "epoch": 17.7, + "learning_rate": 6.837518783844343e-07, + "loss": 0.0017, + "step": 57323 + }, + { + "epoch": 17.7, + "learning_rate": 6.835701363042235e-07, + "loss": 0.0019, + "step": 57324 + }, + { + "epoch": 17.7, + "learning_rate": 6.833884175261007e-07, + "loss": 0.0029, + "step": 57325 + }, + { + "epoch": 17.7, + "learning_rate": 6.832067220505256e-07, + "loss": 0.0021, + "step": 57326 + }, + { + "epoch": 17.7, + "learning_rate": 6.830250498779478e-07, + "loss": 0.002, + "step": 57327 + }, + { + "epoch": 17.7, + "learning_rate": 6.828434010088236e-07, + "loss": 0.0022, + "step": 57328 + }, + { + "epoch": 17.7, + "learning_rate": 6.826617754436082e-07, + "loss": 0.0014, + "step": 57329 + }, + { + "epoch": 17.7, + "learning_rate": 6.824801731827557e-07, + "loss": 0.0014, + "step": 57330 + }, + { + "epoch": 17.7, + "learning_rate": 6.822985942267191e-07, + "loss": 0.0026, + "step": 57331 + }, + { + "epoch": 17.71, + "learning_rate": 6.821170385759535e-07, + "loss": 0.0027, + "step": 57332 + }, + { + "epoch": 17.71, + "learning_rate": 6.819355062309107e-07, + "loss": 0.0015, + "step": 57333 + }, + { + "epoch": 17.71, + "learning_rate": 6.817539971920494e-07, + "loss": 0.0023, + "step": 57334 + }, + { + "epoch": 17.71, + "learning_rate": 6.815725114598204e-07, + "loss": 0.0015, + "step": 57335 + }, + { + "epoch": 17.71, + "learning_rate": 6.813910490346765e-07, + "loss": 0.002, + "step": 57336 + }, + { + "epoch": 17.71, + "learning_rate": 6.81209609917074e-07, + "loss": 0.0019, + "step": 57337 + }, + { + "epoch": 17.71, + "learning_rate": 6.810281941074659e-07, + "loss": 0.0023, + "step": 57338 + }, + { + "epoch": 17.71, + "learning_rate": 6.808468016063052e-07, + "loss": 0.0022, + "step": 57339 + }, + { + "epoch": 17.71, + "learning_rate": 6.806654324140483e-07, + "loss": 0.0013, + "step": 57340 + }, + { + "epoch": 17.71, + "learning_rate": 6.804840865311468e-07, + "loss": 0.0024, + "step": 57341 + }, + { + "epoch": 17.71, + "learning_rate": 6.803027639580529e-07, + "loss": 0.0018, + "step": 57342 + }, + { + "epoch": 17.71, + "learning_rate": 6.801214646952215e-07, + "loss": 0.0025, + "step": 57343 + }, + { + "epoch": 17.71, + "learning_rate": 6.799401887431067e-07, + "loss": 0.0014, + "step": 57344 + }, + { + "epoch": 17.71, + "learning_rate": 6.797589361021628e-07, + "loss": 0.0025, + "step": 57345 + }, + { + "epoch": 17.71, + "learning_rate": 6.795777067728393e-07, + "loss": 0.0021, + "step": 57346 + }, + { + "epoch": 17.71, + "learning_rate": 6.793965007555936e-07, + "loss": 0.0024, + "step": 57347 + }, + { + "epoch": 17.71, + "learning_rate": 6.792153180508765e-07, + "loss": 0.0015, + "step": 57348 + }, + { + "epoch": 17.71, + "learning_rate": 6.790341586591409e-07, + "loss": 0.0017, + "step": 57349 + }, + { + "epoch": 17.71, + "learning_rate": 6.788530225808421e-07, + "loss": 0.0021, + "step": 57350 + }, + { + "epoch": 17.71, + "learning_rate": 6.786719098164329e-07, + "loss": 0.0017, + "step": 57351 + }, + { + "epoch": 17.71, + "learning_rate": 6.784908203663631e-07, + "loss": 0.0024, + "step": 57352 + }, + { + "epoch": 17.71, + "learning_rate": 6.783097542310891e-07, + "loss": 0.002, + "step": 57353 + }, + { + "epoch": 17.71, + "learning_rate": 6.781287114110624e-07, + "loss": 0.0023, + "step": 57354 + }, + { + "epoch": 17.71, + "learning_rate": 6.779476919067373e-07, + "loss": 0.0012, + "step": 57355 + }, + { + "epoch": 17.71, + "learning_rate": 6.777666957185636e-07, + "loss": 0.0023, + "step": 57356 + }, + { + "epoch": 17.71, + "learning_rate": 6.775857228469973e-07, + "loss": 0.0024, + "step": 57357 + }, + { + "epoch": 17.71, + "learning_rate": 6.774047732924871e-07, + "loss": 0.0016, + "step": 57358 + }, + { + "epoch": 17.71, + "learning_rate": 6.772238470554881e-07, + "loss": 0.0017, + "step": 57359 + }, + { + "epoch": 17.71, + "learning_rate": 6.770429441364557e-07, + "loss": 0.0018, + "step": 57360 + }, + { + "epoch": 17.71, + "learning_rate": 6.76862064535837e-07, + "loss": 0.0023, + "step": 57361 + }, + { + "epoch": 17.71, + "learning_rate": 6.766812082540863e-07, + "loss": 0.0016, + "step": 57362 + }, + { + "epoch": 17.71, + "learning_rate": 6.765003752916577e-07, + "loss": 0.0016, + "step": 57363 + }, + { + "epoch": 17.72, + "learning_rate": 6.763195656490007e-07, + "loss": 0.0017, + "step": 57364 + }, + { + "epoch": 17.72, + "learning_rate": 6.761387793265695e-07, + "loss": 0.0023, + "step": 57365 + }, + { + "epoch": 17.72, + "learning_rate": 6.759580163248169e-07, + "loss": 0.0018, + "step": 57366 + }, + { + "epoch": 17.72, + "learning_rate": 6.757772766441928e-07, + "loss": 0.0018, + "step": 57367 + }, + { + "epoch": 17.72, + "learning_rate": 6.7559656028515e-07, + "loss": 0.0027, + "step": 57368 + }, + { + "epoch": 17.72, + "learning_rate": 6.754158672481415e-07, + "loss": 0.0018, + "step": 57369 + }, + { + "epoch": 17.72, + "learning_rate": 6.752351975336191e-07, + "loss": 0.0026, + "step": 57370 + }, + { + "epoch": 17.72, + "learning_rate": 6.750545511420337e-07, + "loss": 0.0017, + "step": 57371 + }, + { + "epoch": 17.72, + "learning_rate": 6.748739280738382e-07, + "loss": 0.0018, + "step": 57372 + }, + { + "epoch": 17.72, + "learning_rate": 6.746933283294821e-07, + "loss": 0.0012, + "step": 57373 + }, + { + "epoch": 17.72, + "learning_rate": 6.745127519094196e-07, + "loss": 0.0016, + "step": 57374 + }, + { + "epoch": 17.72, + "learning_rate": 6.743321988141027e-07, + "loss": 0.0016, + "step": 57375 + }, + { + "epoch": 17.72, + "learning_rate": 6.74151669043982e-07, + "loss": 0.0027, + "step": 57376 + }, + { + "epoch": 17.72, + "learning_rate": 6.739711625995071e-07, + "loss": 0.002, + "step": 57377 + }, + { + "epoch": 17.72, + "learning_rate": 6.737906794811322e-07, + "loss": 0.0019, + "step": 57378 + }, + { + "epoch": 17.72, + "learning_rate": 6.736102196893068e-07, + "loss": 0.0019, + "step": 57379 + }, + { + "epoch": 17.72, + "learning_rate": 6.734297832244851e-07, + "loss": 0.0017, + "step": 57380 + }, + { + "epoch": 17.72, + "learning_rate": 6.732493700871168e-07, + "loss": 0.0017, + "step": 57381 + }, + { + "epoch": 17.72, + "learning_rate": 6.730689802776513e-07, + "loss": 0.0013, + "step": 57382 + }, + { + "epoch": 17.72, + "learning_rate": 6.728886137965407e-07, + "loss": 0.0018, + "step": 57383 + }, + { + "epoch": 17.72, + "learning_rate": 6.727082706442367e-07, + "loss": 0.0022, + "step": 57384 + }, + { + "epoch": 17.72, + "learning_rate": 6.725279508211934e-07, + "loss": 0.0026, + "step": 57385 + }, + { + "epoch": 17.72, + "learning_rate": 6.723476543278585e-07, + "loss": 0.0021, + "step": 57386 + }, + { + "epoch": 17.72, + "learning_rate": 6.721673811646811e-07, + "loss": 0.0022, + "step": 57387 + }, + { + "epoch": 17.72, + "learning_rate": 6.719871313321158e-07, + "loss": 0.0018, + "step": 57388 + }, + { + "epoch": 17.72, + "learning_rate": 6.718069048306108e-07, + "loss": 0.0016, + "step": 57389 + }, + { + "epoch": 17.72, + "learning_rate": 6.716267016606182e-07, + "loss": 0.0026, + "step": 57390 + }, + { + "epoch": 17.72, + "learning_rate": 6.714465218225918e-07, + "loss": 0.0022, + "step": 57391 + }, + { + "epoch": 17.72, + "learning_rate": 6.712663653169759e-07, + "loss": 0.0015, + "step": 57392 + }, + { + "epoch": 17.72, + "learning_rate": 6.710862321442247e-07, + "loss": 0.0022, + "step": 57393 + }, + { + "epoch": 17.72, + "learning_rate": 6.709061223047896e-07, + "loss": 0.0028, + "step": 57394 + }, + { + "epoch": 17.72, + "learning_rate": 6.707260357991174e-07, + "loss": 0.002, + "step": 57395 + }, + { + "epoch": 17.72, + "learning_rate": 6.705459726276642e-07, + "loss": 0.0023, + "step": 57396 + }, + { + "epoch": 17.73, + "learning_rate": 6.703659327908751e-07, + "loss": 0.0019, + "step": 57397 + }, + { + "epoch": 17.73, + "learning_rate": 6.701859162892021e-07, + "loss": 0.0023, + "step": 57398 + }, + { + "epoch": 17.73, + "learning_rate": 6.700059231230959e-07, + "loss": 0.0019, + "step": 57399 + }, + { + "epoch": 17.73, + "learning_rate": 6.698259532930074e-07, + "loss": 0.0017, + "step": 57400 + }, + { + "epoch": 17.73, + "learning_rate": 6.696460067993871e-07, + "loss": 0.0019, + "step": 57401 + }, + { + "epoch": 17.73, + "learning_rate": 6.694660836426814e-07, + "loss": 0.0015, + "step": 57402 + }, + { + "epoch": 17.73, + "learning_rate": 6.692861838233445e-07, + "loss": 0.0013, + "step": 57403 + }, + { + "epoch": 17.73, + "learning_rate": 6.691063073418225e-07, + "loss": 0.0025, + "step": 57404 + }, + { + "epoch": 17.73, + "learning_rate": 6.689264541985684e-07, + "loss": 0.002, + "step": 57405 + }, + { + "epoch": 17.73, + "learning_rate": 6.687466243940322e-07, + "loss": 0.0016, + "step": 57406 + }, + { + "epoch": 17.73, + "learning_rate": 6.68566817928663e-07, + "loss": 0.0019, + "step": 57407 + }, + { + "epoch": 17.73, + "learning_rate": 6.683870348029075e-07, + "loss": 0.0021, + "step": 57408 + }, + { + "epoch": 17.73, + "learning_rate": 6.682072750172209e-07, + "loss": 0.0013, + "step": 57409 + }, + { + "epoch": 17.73, + "learning_rate": 6.680275385720481e-07, + "loss": 0.0023, + "step": 57410 + }, + { + "epoch": 17.73, + "learning_rate": 6.678478254678411e-07, + "loss": 0.0016, + "step": 57411 + }, + { + "epoch": 17.73, + "learning_rate": 6.676681357050496e-07, + "loss": 0.0023, + "step": 57412 + }, + { + "epoch": 17.73, + "learning_rate": 6.674884692841211e-07, + "loss": 0.0018, + "step": 57413 + }, + { + "epoch": 17.73, + "learning_rate": 6.67308826205505e-07, + "loss": 0.0015, + "step": 57414 + }, + { + "epoch": 17.73, + "learning_rate": 6.671292064696521e-07, + "loss": 0.0024, + "step": 57415 + }, + { + "epoch": 17.73, + "learning_rate": 6.669496100770134e-07, + "loss": 0.0018, + "step": 57416 + }, + { + "epoch": 17.73, + "learning_rate": 6.66770037028035e-07, + "loss": 0.0023, + "step": 57417 + }, + { + "epoch": 17.73, + "learning_rate": 6.665904873231666e-07, + "loss": 0.0017, + "step": 57418 + }, + { + "epoch": 17.73, + "learning_rate": 6.664109609628578e-07, + "loss": 0.002, + "step": 57419 + }, + { + "epoch": 17.73, + "learning_rate": 6.662314579475571e-07, + "loss": 0.0019, + "step": 57420 + }, + { + "epoch": 17.73, + "learning_rate": 6.660519782777153e-07, + "loss": 0.002, + "step": 57421 + }, + { + "epoch": 17.73, + "learning_rate": 6.658725219537799e-07, + "loss": 0.0024, + "step": 57422 + }, + { + "epoch": 17.73, + "learning_rate": 6.65693088976197e-07, + "loss": 0.0021, + "step": 57423 + }, + { + "epoch": 17.73, + "learning_rate": 6.655136793454198e-07, + "loss": 0.0016, + "step": 57424 + }, + { + "epoch": 17.73, + "learning_rate": 6.653342930618967e-07, + "loss": 0.0017, + "step": 57425 + }, + { + "epoch": 17.73, + "learning_rate": 6.651549301260729e-07, + "loss": 0.0017, + "step": 57426 + }, + { + "epoch": 17.73, + "learning_rate": 6.649755905384004e-07, + "loss": 0.002, + "step": 57427 + }, + { + "epoch": 17.73, + "learning_rate": 6.647962742993275e-07, + "loss": 0.0016, + "step": 57428 + }, + { + "epoch": 17.74, + "learning_rate": 6.646169814092995e-07, + "loss": 0.0018, + "step": 57429 + }, + { + "epoch": 17.74, + "learning_rate": 6.644377118687672e-07, + "loss": 0.0027, + "step": 57430 + }, + { + "epoch": 17.74, + "learning_rate": 6.642584656781814e-07, + "loss": 0.0021, + "step": 57431 + }, + { + "epoch": 17.74, + "learning_rate": 6.640792428379872e-07, + "loss": 0.002, + "step": 57432 + }, + { + "epoch": 17.74, + "learning_rate": 6.63900043348632e-07, + "loss": 0.0024, + "step": 57433 + }, + { + "epoch": 17.74, + "learning_rate": 6.637208672105667e-07, + "loss": 0.0016, + "step": 57434 + }, + { + "epoch": 17.74, + "learning_rate": 6.635417144242373e-07, + "loss": 0.0017, + "step": 57435 + }, + { + "epoch": 17.74, + "learning_rate": 6.633625849900927e-07, + "loss": 0.0019, + "step": 57436 + }, + { + "epoch": 17.74, + "learning_rate": 6.631834789085834e-07, + "loss": 0.0024, + "step": 57437 + }, + { + "epoch": 17.74, + "learning_rate": 6.630043961801547e-07, + "loss": 0.0022, + "step": 57438 + }, + { + "epoch": 17.74, + "learning_rate": 6.628253368052529e-07, + "loss": 0.0018, + "step": 57439 + }, + { + "epoch": 17.74, + "learning_rate": 6.626463007843298e-07, + "loss": 0.0017, + "step": 57440 + }, + { + "epoch": 17.74, + "learning_rate": 6.624672881178307e-07, + "loss": 0.0023, + "step": 57441 + }, + { + "epoch": 17.74, + "learning_rate": 6.622882988062041e-07, + "loss": 0.0016, + "step": 57442 + }, + { + "epoch": 17.74, + "learning_rate": 6.621093328498984e-07, + "loss": 0.0014, + "step": 57443 + }, + { + "epoch": 17.74, + "learning_rate": 6.61930390249359e-07, + "loss": 0.0019, + "step": 57444 + }, + { + "epoch": 17.74, + "learning_rate": 6.617514710050343e-07, + "loss": 0.0025, + "step": 57445 + }, + { + "epoch": 17.74, + "learning_rate": 6.615725751173741e-07, + "loss": 0.0021, + "step": 57446 + }, + { + "epoch": 17.74, + "learning_rate": 6.613937025868223e-07, + "loss": 0.0015, + "step": 57447 + }, + { + "epoch": 17.74, + "learning_rate": 6.612148534138296e-07, + "loss": 0.0019, + "step": 57448 + }, + { + "epoch": 17.74, + "learning_rate": 6.610360275988404e-07, + "loss": 0.0017, + "step": 57449 + }, + { + "epoch": 17.74, + "learning_rate": 6.608572251423051e-07, + "loss": 0.0019, + "step": 57450 + }, + { + "epoch": 17.74, + "learning_rate": 6.60678446044668e-07, + "loss": 0.0021, + "step": 57451 + }, + { + "epoch": 17.74, + "learning_rate": 6.604996903063787e-07, + "loss": 0.0021, + "step": 57452 + }, + { + "epoch": 17.74, + "learning_rate": 6.603209579278836e-07, + "loss": 0.0017, + "step": 57453 + }, + { + "epoch": 17.74, + "learning_rate": 6.601422489096276e-07, + "loss": 0.0018, + "step": 57454 + }, + { + "epoch": 17.74, + "learning_rate": 6.599635632520585e-07, + "loss": 0.0014, + "step": 57455 + }, + { + "epoch": 17.74, + "learning_rate": 6.597849009556256e-07, + "loss": 0.0024, + "step": 57456 + }, + { + "epoch": 17.74, + "learning_rate": 6.596062620207732e-07, + "loss": 0.0018, + "step": 57457 + }, + { + "epoch": 17.74, + "learning_rate": 6.594276464479509e-07, + "loss": 0.0023, + "step": 57458 + }, + { + "epoch": 17.74, + "learning_rate": 6.59249054237604e-07, + "loss": 0.0017, + "step": 57459 + }, + { + "epoch": 17.74, + "learning_rate": 6.590704853901764e-07, + "loss": 0.0021, + "step": 57460 + }, + { + "epoch": 17.74, + "learning_rate": 6.588919399061178e-07, + "loss": 0.0018, + "step": 57461 + }, + { + "epoch": 17.75, + "learning_rate": 6.587134177858745e-07, + "loss": 0.0019, + "step": 57462 + }, + { + "epoch": 17.75, + "learning_rate": 6.58534919029894e-07, + "loss": 0.0022, + "step": 57463 + }, + { + "epoch": 17.75, + "learning_rate": 6.583564436386192e-07, + "loss": 0.0018, + "step": 57464 + }, + { + "epoch": 17.75, + "learning_rate": 6.581779916125009e-07, + "loss": 0.0022, + "step": 57465 + }, + { + "epoch": 17.75, + "learning_rate": 6.57999562951982e-07, + "loss": 0.0021, + "step": 57466 + }, + { + "epoch": 17.75, + "learning_rate": 6.578211576575089e-07, + "loss": 0.0022, + "step": 57467 + }, + { + "epoch": 17.75, + "learning_rate": 6.576427757295312e-07, + "loss": 0.0016, + "step": 57468 + }, + { + "epoch": 17.75, + "learning_rate": 6.57464417168493e-07, + "loss": 0.0017, + "step": 57469 + }, + { + "epoch": 17.75, + "learning_rate": 6.572860819748383e-07, + "loss": 0.002, + "step": 57470 + }, + { + "epoch": 17.75, + "learning_rate": 6.57107770149017e-07, + "loss": 0.002, + "step": 57471 + }, + { + "epoch": 17.75, + "learning_rate": 6.569294816914718e-07, + "loss": 0.0019, + "step": 57472 + }, + { + "epoch": 17.75, + "learning_rate": 6.567512166026513e-07, + "loss": 0.0023, + "step": 57473 + }, + { + "epoch": 17.75, + "learning_rate": 6.565729748829997e-07, + "loss": 0.0019, + "step": 57474 + }, + { + "epoch": 17.75, + "learning_rate": 6.56394756532962e-07, + "loss": 0.0019, + "step": 57475 + }, + { + "epoch": 17.75, + "learning_rate": 6.562165615529847e-07, + "loss": 0.002, + "step": 57476 + }, + { + "epoch": 17.75, + "learning_rate": 6.560383899435163e-07, + "loss": 0.002, + "step": 57477 + }, + { + "epoch": 17.75, + "learning_rate": 6.558602417049987e-07, + "loss": 0.0015, + "step": 57478 + }, + { + "epoch": 17.75, + "learning_rate": 6.556821168378802e-07, + "loss": 0.0023, + "step": 57479 + }, + { + "epoch": 17.75, + "learning_rate": 6.555040153426051e-07, + "loss": 0.0012, + "step": 57480 + }, + { + "epoch": 17.75, + "learning_rate": 6.553259372196163e-07, + "loss": 0.002, + "step": 57481 + }, + { + "epoch": 17.75, + "learning_rate": 6.551478824693635e-07, + "loss": 0.0021, + "step": 57482 + }, + { + "epoch": 17.75, + "learning_rate": 6.549698510922908e-07, + "loss": 0.0019, + "step": 57483 + }, + { + "epoch": 17.75, + "learning_rate": 6.547918430888422e-07, + "loss": 0.0021, + "step": 57484 + }, + { + "epoch": 17.75, + "learning_rate": 6.54613858459463e-07, + "loss": 0.0015, + "step": 57485 + }, + { + "epoch": 17.75, + "learning_rate": 6.544358972045983e-07, + "loss": 0.0019, + "step": 57486 + }, + { + "epoch": 17.75, + "learning_rate": 6.542579593246967e-07, + "loss": 0.002, + "step": 57487 + }, + { + "epoch": 17.75, + "learning_rate": 6.540800448201978e-07, + "loss": 0.0019, + "step": 57488 + }, + { + "epoch": 17.75, + "learning_rate": 6.539021536915513e-07, + "loss": 0.0012, + "step": 57489 + }, + { + "epoch": 17.75, + "learning_rate": 6.537242859392001e-07, + "loss": 0.0021, + "step": 57490 + }, + { + "epoch": 17.75, + "learning_rate": 6.535464415635884e-07, + "loss": 0.0017, + "step": 57491 + }, + { + "epoch": 17.75, + "learning_rate": 6.533686205651601e-07, + "loss": 0.0015, + "step": 57492 + }, + { + "epoch": 17.75, + "learning_rate": 6.531908229443651e-07, + "loss": 0.0012, + "step": 57493 + }, + { + "epoch": 17.76, + "learning_rate": 6.530130487016429e-07, + "loss": 0.0017, + "step": 57494 + }, + { + "epoch": 17.76, + "learning_rate": 6.528352978374386e-07, + "loss": 0.0029, + "step": 57495 + }, + { + "epoch": 17.76, + "learning_rate": 6.526575703521997e-07, + "loss": 0.003, + "step": 57496 + }, + { + "epoch": 17.76, + "learning_rate": 6.524798662463682e-07, + "loss": 0.0022, + "step": 57497 + }, + { + "epoch": 17.76, + "learning_rate": 6.523021855203893e-07, + "loss": 0.0015, + "step": 57498 + }, + { + "epoch": 17.76, + "learning_rate": 6.521245281747102e-07, + "loss": 0.0018, + "step": 57499 + }, + { + "epoch": 17.76, + "learning_rate": 6.519468942097695e-07, + "loss": 0.0016, + "step": 57500 + }, + { + "epoch": 17.76, + "learning_rate": 6.517692836260147e-07, + "loss": 0.0019, + "step": 57501 + }, + { + "epoch": 17.76, + "learning_rate": 6.515916964238911e-07, + "loss": 0.0023, + "step": 57502 + }, + { + "epoch": 17.76, + "learning_rate": 6.514141326038415e-07, + "loss": 0.0025, + "step": 57503 + }, + { + "epoch": 17.76, + "learning_rate": 6.512365921663099e-07, + "loss": 0.0019, + "step": 57504 + }, + { + "epoch": 17.76, + "learning_rate": 6.510590751117418e-07, + "loss": 0.0015, + "step": 57505 + }, + { + "epoch": 17.76, + "learning_rate": 6.508815814405789e-07, + "loss": 0.0025, + "step": 57506 + }, + { + "epoch": 17.76, + "learning_rate": 6.507041111532653e-07, + "loss": 0.0019, + "step": 57507 + }, + { + "epoch": 17.76, + "learning_rate": 6.505266642502484e-07, + "loss": 0.0014, + "step": 57508 + }, + { + "epoch": 17.76, + "learning_rate": 6.50349240731969e-07, + "loss": 0.002, + "step": 57509 + }, + { + "epoch": 17.76, + "learning_rate": 6.501718405988699e-07, + "loss": 0.0019, + "step": 57510 + }, + { + "epoch": 17.76, + "learning_rate": 6.499944638513978e-07, + "loss": 0.0017, + "step": 57511 + }, + { + "epoch": 17.76, + "learning_rate": 6.49817110489993e-07, + "loss": 0.0014, + "step": 57512 + }, + { + "epoch": 17.76, + "learning_rate": 6.496397805151022e-07, + "loss": 0.0025, + "step": 57513 + }, + { + "epoch": 17.76, + "learning_rate": 6.494624739271682e-07, + "loss": 0.0024, + "step": 57514 + }, + { + "epoch": 17.76, + "learning_rate": 6.49285190726634e-07, + "loss": 0.0014, + "step": 57515 + }, + { + "epoch": 17.76, + "learning_rate": 6.491079309139425e-07, + "loss": 0.0021, + "step": 57516 + }, + { + "epoch": 17.76, + "learning_rate": 6.489306944895369e-07, + "loss": 0.0016, + "step": 57517 + }, + { + "epoch": 17.76, + "learning_rate": 6.487534814538621e-07, + "loss": 0.0023, + "step": 57518 + }, + { + "epoch": 17.76, + "learning_rate": 6.485762918073613e-07, + "loss": 0.0019, + "step": 57519 + }, + { + "epoch": 17.76, + "learning_rate": 6.483991255504751e-07, + "loss": 0.0029, + "step": 57520 + }, + { + "epoch": 17.76, + "learning_rate": 6.482219826836489e-07, + "loss": 0.0017, + "step": 57521 + }, + { + "epoch": 17.76, + "learning_rate": 6.480448632073244e-07, + "loss": 0.0021, + "step": 57522 + }, + { + "epoch": 17.76, + "learning_rate": 6.478677671219458e-07, + "loss": 0.0031, + "step": 57523 + }, + { + "epoch": 17.76, + "learning_rate": 6.47690694427957e-07, + "loss": 0.0017, + "step": 57524 + }, + { + "epoch": 17.76, + "learning_rate": 6.475136451257991e-07, + "loss": 0.002, + "step": 57525 + }, + { + "epoch": 17.77, + "learning_rate": 6.473366192159137e-07, + "loss": 0.0015, + "step": 57526 + }, + { + "epoch": 17.77, + "learning_rate": 6.471596166987471e-07, + "loss": 0.002, + "step": 57527 + }, + { + "epoch": 17.77, + "learning_rate": 6.46982637574739e-07, + "loss": 0.0022, + "step": 57528 + }, + { + "epoch": 17.77, + "learning_rate": 6.468056818443335e-07, + "loss": 0.0021, + "step": 57529 + }, + { + "epoch": 17.77, + "learning_rate": 6.466287495079737e-07, + "loss": 0.0012, + "step": 57530 + }, + { + "epoch": 17.77, + "learning_rate": 6.464518405661003e-07, + "loss": 0.002, + "step": 57531 + }, + { + "epoch": 17.77, + "learning_rate": 6.46274955019156e-07, + "loss": 0.0022, + "step": 57532 + }, + { + "epoch": 17.77, + "learning_rate": 6.460980928675864e-07, + "loss": 0.0019, + "step": 57533 + }, + { + "epoch": 17.77, + "learning_rate": 6.459212541118298e-07, + "loss": 0.0018, + "step": 57534 + }, + { + "epoch": 17.77, + "learning_rate": 6.457444387523316e-07, + "loss": 0.0014, + "step": 57535 + }, + { + "epoch": 17.77, + "learning_rate": 6.455676467895322e-07, + "loss": 0.002, + "step": 57536 + }, + { + "epoch": 17.77, + "learning_rate": 6.453908782238727e-07, + "loss": 0.002, + "step": 57537 + }, + { + "epoch": 17.77, + "learning_rate": 6.45214133055797e-07, + "loss": 0.0018, + "step": 57538 + }, + { + "epoch": 17.77, + "learning_rate": 6.450374112857494e-07, + "loss": 0.0019, + "step": 57539 + }, + { + "epoch": 17.77, + "learning_rate": 6.448607129141682e-07, + "loss": 0.0017, + "step": 57540 + }, + { + "epoch": 17.77, + "learning_rate": 6.446840379414954e-07, + "loss": 0.0018, + "step": 57541 + }, + { + "epoch": 17.77, + "learning_rate": 6.445073863681761e-07, + "loss": 0.0026, + "step": 57542 + }, + { + "epoch": 17.77, + "learning_rate": 6.44330758194649e-07, + "loss": 0.0025, + "step": 57543 + }, + { + "epoch": 17.77, + "learning_rate": 6.441541534213558e-07, + "loss": 0.0017, + "step": 57544 + }, + { + "epoch": 17.77, + "learning_rate": 6.439775720487418e-07, + "loss": 0.0025, + "step": 57545 + }, + { + "epoch": 17.77, + "learning_rate": 6.438010140772466e-07, + "loss": 0.0021, + "step": 57546 + }, + { + "epoch": 17.77, + "learning_rate": 6.436244795073088e-07, + "loss": 0.0012, + "step": 57547 + }, + { + "epoch": 17.77, + "learning_rate": 6.434479683393735e-07, + "loss": 0.0013, + "step": 57548 + }, + { + "epoch": 17.77, + "learning_rate": 6.432714805738838e-07, + "loss": 0.0017, + "step": 57549 + }, + { + "epoch": 17.77, + "learning_rate": 6.43095016211277e-07, + "loss": 0.0017, + "step": 57550 + }, + { + "epoch": 17.77, + "learning_rate": 6.429185752519951e-07, + "loss": 0.0019, + "step": 57551 + }, + { + "epoch": 17.77, + "learning_rate": 6.427421576964832e-07, + "loss": 0.0023, + "step": 57552 + }, + { + "epoch": 17.77, + "learning_rate": 6.425657635451766e-07, + "loss": 0.0016, + "step": 57553 + }, + { + "epoch": 17.77, + "learning_rate": 6.423893927985203e-07, + "loss": 0.002, + "step": 57554 + }, + { + "epoch": 17.77, + "learning_rate": 6.422130454569564e-07, + "loss": 0.0015, + "step": 57555 + }, + { + "epoch": 17.77, + "learning_rate": 6.420367215209255e-07, + "loss": 0.0022, + "step": 57556 + }, + { + "epoch": 17.77, + "learning_rate": 6.418604209908652e-07, + "loss": 0.0014, + "step": 57557 + }, + { + "epoch": 17.77, + "learning_rate": 6.416841438672194e-07, + "loss": 0.0024, + "step": 57558 + }, + { + "epoch": 17.78, + "learning_rate": 6.415078901504279e-07, + "loss": 0.0016, + "step": 57559 + }, + { + "epoch": 17.78, + "learning_rate": 6.413316598409336e-07, + "loss": 0.0018, + "step": 57560 + }, + { + "epoch": 17.78, + "learning_rate": 6.411554529391751e-07, + "loss": 0.0015, + "step": 57561 + }, + { + "epoch": 17.78, + "learning_rate": 6.40979269445593e-07, + "loss": 0.0019, + "step": 57562 + }, + { + "epoch": 17.78, + "learning_rate": 6.408031093606282e-07, + "loss": 0.0019, + "step": 57563 + }, + { + "epoch": 17.78, + "learning_rate": 6.406269726847236e-07, + "loss": 0.0014, + "step": 57564 + }, + { + "epoch": 17.78, + "learning_rate": 6.404508594183167e-07, + "loss": 0.0017, + "step": 57565 + }, + { + "epoch": 17.78, + "learning_rate": 6.402747695618505e-07, + "loss": 0.0014, + "step": 57566 + }, + { + "epoch": 17.78, + "learning_rate": 6.400987031157635e-07, + "loss": 0.0016, + "step": 57567 + }, + { + "epoch": 17.78, + "learning_rate": 6.399226600804964e-07, + "loss": 0.0021, + "step": 57568 + }, + { + "epoch": 17.78, + "learning_rate": 6.397466404564889e-07, + "loss": 0.0023, + "step": 57569 + }, + { + "epoch": 17.78, + "learning_rate": 6.395706442441851e-07, + "loss": 0.0024, + "step": 57570 + }, + { + "epoch": 17.78, + "learning_rate": 6.393946714440214e-07, + "loss": 0.002, + "step": 57571 + }, + { + "epoch": 17.78, + "learning_rate": 6.392187220564372e-07, + "loss": 0.0015, + "step": 57572 + }, + { + "epoch": 17.78, + "learning_rate": 6.390427960818768e-07, + "loss": 0.002, + "step": 57573 + }, + { + "epoch": 17.78, + "learning_rate": 6.388668935207753e-07, + "loss": 0.0019, + "step": 57574 + }, + { + "epoch": 17.78, + "learning_rate": 6.386910143735747e-07, + "loss": 0.0018, + "step": 57575 + }, + { + "epoch": 17.78, + "learning_rate": 6.385151586407179e-07, + "loss": 0.0014, + "step": 57576 + }, + { + "epoch": 17.78, + "learning_rate": 6.383393263226411e-07, + "loss": 0.0016, + "step": 57577 + }, + { + "epoch": 17.78, + "learning_rate": 6.381635174197842e-07, + "loss": 0.0019, + "step": 57578 + }, + { + "epoch": 17.78, + "learning_rate": 6.379877319325878e-07, + "loss": 0.0018, + "step": 57579 + }, + { + "epoch": 17.78, + "learning_rate": 6.378119698614926e-07, + "loss": 0.0025, + "step": 57580 + }, + { + "epoch": 17.78, + "learning_rate": 6.376362312069384e-07, + "loss": 0.0019, + "step": 57581 + }, + { + "epoch": 17.78, + "learning_rate": 6.374605159693614e-07, + "loss": 0.0018, + "step": 57582 + }, + { + "epoch": 17.78, + "learning_rate": 6.372848241492047e-07, + "loss": 0.0019, + "step": 57583 + }, + { + "epoch": 17.78, + "learning_rate": 6.371091557469044e-07, + "loss": 0.0017, + "step": 57584 + }, + { + "epoch": 17.78, + "learning_rate": 6.369335107629027e-07, + "loss": 0.0022, + "step": 57585 + }, + { + "epoch": 17.78, + "learning_rate": 6.36757889197639e-07, + "loss": 0.0018, + "step": 57586 + }, + { + "epoch": 17.78, + "learning_rate": 6.365822910515506e-07, + "loss": 0.0021, + "step": 57587 + }, + { + "epoch": 17.78, + "learning_rate": 6.364067163250776e-07, + "loss": 0.0016, + "step": 57588 + }, + { + "epoch": 17.78, + "learning_rate": 6.362311650186604e-07, + "loss": 0.0024, + "step": 57589 + }, + { + "epoch": 17.78, + "learning_rate": 6.360556371327353e-07, + "loss": 0.0019, + "step": 57590 + }, + { + "epoch": 17.79, + "learning_rate": 6.358801326677444e-07, + "loss": 0.0017, + "step": 57591 + }, + { + "epoch": 17.79, + "learning_rate": 6.357046516241249e-07, + "loss": 0.002, + "step": 57592 + }, + { + "epoch": 17.79, + "learning_rate": 6.355291940023145e-07, + "loss": 0.0019, + "step": 57593 + }, + { + "epoch": 17.79, + "learning_rate": 6.353537598027548e-07, + "loss": 0.0025, + "step": 57594 + }, + { + "epoch": 17.79, + "learning_rate": 6.351783490258834e-07, + "loss": 0.0019, + "step": 57595 + }, + { + "epoch": 17.79, + "learning_rate": 6.350029616721376e-07, + "loss": 0.0019, + "step": 57596 + }, + { + "epoch": 17.79, + "learning_rate": 6.348275977419593e-07, + "loss": 0.0019, + "step": 57597 + }, + { + "epoch": 17.79, + "learning_rate": 6.346522572357861e-07, + "loss": 0.0016, + "step": 57598 + }, + { + "epoch": 17.79, + "learning_rate": 6.34476940154053e-07, + "loss": 0.0013, + "step": 57599 + }, + { + "epoch": 17.79, + "learning_rate": 6.343016464972018e-07, + "loss": 0.0023, + "step": 57600 + }, + { + "epoch": 17.79, + "learning_rate": 6.341263762656713e-07, + "loss": 0.0017, + "step": 57601 + }, + { + "epoch": 17.79, + "learning_rate": 6.339511294598999e-07, + "loss": 0.0016, + "step": 57602 + }, + { + "epoch": 17.79, + "learning_rate": 6.337759060803228e-07, + "loss": 0.0015, + "step": 57603 + }, + { + "epoch": 17.79, + "learning_rate": 6.33600706127383e-07, + "loss": 0.0021, + "step": 57604 + }, + { + "epoch": 17.79, + "learning_rate": 6.334255296015135e-07, + "loss": 0.0032, + "step": 57605 + }, + { + "epoch": 17.79, + "learning_rate": 6.332503765031551e-07, + "loss": 0.0016, + "step": 57606 + }, + { + "epoch": 17.79, + "learning_rate": 6.330752468327494e-07, + "loss": 0.002, + "step": 57607 + }, + { + "epoch": 17.79, + "learning_rate": 6.329001405907275e-07, + "loss": 0.0011, + "step": 57608 + }, + { + "epoch": 17.79, + "learning_rate": 6.327250577775312e-07, + "loss": 0.0019, + "step": 57609 + }, + { + "epoch": 17.79, + "learning_rate": 6.325499983936001e-07, + "loss": 0.0022, + "step": 57610 + }, + { + "epoch": 17.79, + "learning_rate": 6.323749624393671e-07, + "loss": 0.0017, + "step": 57611 + }, + { + "epoch": 17.79, + "learning_rate": 6.321999499152753e-07, + "loss": 0.0014, + "step": 57612 + }, + { + "epoch": 17.79, + "learning_rate": 6.320249608217577e-07, + "loss": 0.0012, + "step": 57613 + }, + { + "epoch": 17.79, + "learning_rate": 6.318499951592571e-07, + "loss": 0.0018, + "step": 57614 + }, + { + "epoch": 17.79, + "learning_rate": 6.316750529282056e-07, + "loss": 0.0015, + "step": 57615 + }, + { + "epoch": 17.79, + "learning_rate": 6.315001341290438e-07, + "loss": 0.002, + "step": 57616 + }, + { + "epoch": 17.79, + "learning_rate": 6.313252387622116e-07, + "loss": 0.0017, + "step": 57617 + }, + { + "epoch": 17.79, + "learning_rate": 6.311503668281416e-07, + "loss": 0.0016, + "step": 57618 + }, + { + "epoch": 17.79, + "learning_rate": 6.309755183272726e-07, + "loss": 0.0016, + "step": 57619 + }, + { + "epoch": 17.79, + "learning_rate": 6.308006932600441e-07, + "loss": 0.0017, + "step": 57620 + }, + { + "epoch": 17.79, + "learning_rate": 6.306258916268904e-07, + "loss": 0.0015, + "step": 57621 + }, + { + "epoch": 17.79, + "learning_rate": 6.304511134282521e-07, + "loss": 0.0018, + "step": 57622 + }, + { + "epoch": 17.8, + "learning_rate": 6.302763586645644e-07, + "loss": 0.0013, + "step": 57623 + }, + { + "epoch": 17.8, + "learning_rate": 6.301016273362625e-07, + "loss": 0.0017, + "step": 57624 + }, + { + "epoch": 17.8, + "learning_rate": 6.299269194437862e-07, + "loss": 0.0016, + "step": 57625 + }, + { + "epoch": 17.8, + "learning_rate": 6.297522349875729e-07, + "loss": 0.0022, + "step": 57626 + }, + { + "epoch": 17.8, + "learning_rate": 6.295775739680576e-07, + "loss": 0.0021, + "step": 57627 + }, + { + "epoch": 17.8, + "learning_rate": 6.294029363856769e-07, + "loss": 0.0022, + "step": 57628 + }, + { + "epoch": 17.8, + "learning_rate": 6.292283222408702e-07, + "loss": 0.0018, + "step": 57629 + }, + { + "epoch": 17.8, + "learning_rate": 6.290537315340706e-07, + "loss": 0.002, + "step": 57630 + }, + { + "epoch": 17.8, + "learning_rate": 6.288791642657177e-07, + "loss": 0.0021, + "step": 57631 + }, + { + "epoch": 17.8, + "learning_rate": 6.28704620436248e-07, + "loss": 0.0014, + "step": 57632 + }, + { + "epoch": 17.8, + "learning_rate": 6.285301000460975e-07, + "loss": 0.0022, + "step": 57633 + }, + { + "epoch": 17.8, + "learning_rate": 6.283556030957005e-07, + "loss": 0.002, + "step": 57634 + }, + { + "epoch": 17.8, + "learning_rate": 6.281811295854967e-07, + "loss": 0.0019, + "step": 57635 + }, + { + "epoch": 17.8, + "learning_rate": 6.280066795159213e-07, + "loss": 0.0017, + "step": 57636 + }, + { + "epoch": 17.8, + "learning_rate": 6.278322528874103e-07, + "loss": 0.0026, + "step": 57637 + }, + { + "epoch": 17.8, + "learning_rate": 6.276578497004005e-07, + "loss": 0.002, + "step": 57638 + }, + { + "epoch": 17.8, + "learning_rate": 6.274834699553267e-07, + "loss": 0.0013, + "step": 57639 + }, + { + "epoch": 17.8, + "learning_rate": 6.273091136526266e-07, + "loss": 0.0024, + "step": 57640 + }, + { + "epoch": 17.8, + "learning_rate": 6.271347807927364e-07, + "loss": 0.0022, + "step": 57641 + }, + { + "epoch": 17.8, + "learning_rate": 6.269604713760913e-07, + "loss": 0.0021, + "step": 57642 + }, + { + "epoch": 17.8, + "learning_rate": 6.267861854031288e-07, + "loss": 0.0018, + "step": 57643 + }, + { + "epoch": 17.8, + "learning_rate": 6.266119228742829e-07, + "loss": 0.0013, + "step": 57644 + }, + { + "epoch": 17.8, + "learning_rate": 6.264376837899888e-07, + "loss": 0.0018, + "step": 57645 + }, + { + "epoch": 17.8, + "learning_rate": 6.262634681506841e-07, + "loss": 0.0022, + "step": 57646 + }, + { + "epoch": 17.8, + "learning_rate": 6.260892759568038e-07, + "loss": 0.0022, + "step": 57647 + }, + { + "epoch": 17.8, + "learning_rate": 6.259151072087877e-07, + "loss": 0.002, + "step": 57648 + }, + { + "epoch": 17.8, + "learning_rate": 6.257409619070632e-07, + "loss": 0.0021, + "step": 57649 + }, + { + "epoch": 17.8, + "learning_rate": 6.255668400520709e-07, + "loss": 0.002, + "step": 57650 + }, + { + "epoch": 17.8, + "learning_rate": 6.253927416442485e-07, + "loss": 0.0016, + "step": 57651 + }, + { + "epoch": 17.8, + "learning_rate": 6.252186666840254e-07, + "loss": 0.0018, + "step": 57652 + }, + { + "epoch": 17.8, + "learning_rate": 6.250446151718426e-07, + "loss": 0.0022, + "step": 57653 + }, + { + "epoch": 17.8, + "learning_rate": 6.248705871081328e-07, + "loss": 0.0017, + "step": 57654 + }, + { + "epoch": 17.8, + "learning_rate": 6.246965824933304e-07, + "loss": 0.0023, + "step": 57655 + }, + { + "epoch": 17.81, + "learning_rate": 6.245226013278716e-07, + "loss": 0.0022, + "step": 57656 + }, + { + "epoch": 17.81, + "learning_rate": 6.243486436121938e-07, + "loss": 0.002, + "step": 57657 + }, + { + "epoch": 17.81, + "learning_rate": 6.241747093467298e-07, + "loss": 0.0021, + "step": 57658 + }, + { + "epoch": 17.81, + "learning_rate": 6.24000798531913e-07, + "loss": 0.0025, + "step": 57659 + }, + { + "epoch": 17.81, + "learning_rate": 6.238269111681816e-07, + "loss": 0.0023, + "step": 57660 + }, + { + "epoch": 17.81, + "learning_rate": 6.236530472559688e-07, + "loss": 0.0016, + "step": 57661 + }, + { + "epoch": 17.81, + "learning_rate": 6.234792067957085e-07, + "loss": 0.0017, + "step": 57662 + }, + { + "epoch": 17.81, + "learning_rate": 6.233053897878394e-07, + "loss": 0.0017, + "step": 57663 + }, + { + "epoch": 17.81, + "learning_rate": 6.231315962327933e-07, + "loss": 0.0022, + "step": 57664 + }, + { + "epoch": 17.81, + "learning_rate": 6.229578261310032e-07, + "loss": 0.0026, + "step": 57665 + }, + { + "epoch": 17.81, + "learning_rate": 6.227840794829088e-07, + "loss": 0.0017, + "step": 57666 + }, + { + "epoch": 17.81, + "learning_rate": 6.226103562889385e-07, + "loss": 0.002, + "step": 57667 + }, + { + "epoch": 17.81, + "learning_rate": 6.224366565495332e-07, + "loss": 0.0015, + "step": 57668 + }, + { + "epoch": 17.81, + "learning_rate": 6.222629802651237e-07, + "loss": 0.0016, + "step": 57669 + }, + { + "epoch": 17.81, + "learning_rate": 6.220893274361429e-07, + "loss": 0.0018, + "step": 57670 + }, + { + "epoch": 17.81, + "learning_rate": 6.21915698063027e-07, + "loss": 0.002, + "step": 57671 + }, + { + "epoch": 17.81, + "learning_rate": 6.217420921462125e-07, + "loss": 0.0022, + "step": 57672 + }, + { + "epoch": 17.81, + "learning_rate": 6.21568509686129e-07, + "loss": 0.0025, + "step": 57673 + }, + { + "epoch": 17.81, + "learning_rate": 6.213949506832162e-07, + "loss": 0.0016, + "step": 57674 + }, + { + "epoch": 17.81, + "learning_rate": 6.212214151379037e-07, + "loss": 0.0018, + "step": 57675 + }, + { + "epoch": 17.81, + "learning_rate": 6.210479030506267e-07, + "loss": 0.0016, + "step": 57676 + }, + { + "epoch": 17.81, + "learning_rate": 6.208744144218193e-07, + "loss": 0.0016, + "step": 57677 + }, + { + "epoch": 17.81, + "learning_rate": 6.207009492519167e-07, + "loss": 0.0021, + "step": 57678 + }, + { + "epoch": 17.81, + "learning_rate": 6.20527507541352e-07, + "loss": 0.0016, + "step": 57679 + }, + { + "epoch": 17.81, + "learning_rate": 6.203540892905569e-07, + "loss": 0.0015, + "step": 57680 + }, + { + "epoch": 17.81, + "learning_rate": 6.201806944999667e-07, + "loss": 0.0018, + "step": 57681 + }, + { + "epoch": 17.81, + "learning_rate": 6.200073231700177e-07, + "loss": 0.0023, + "step": 57682 + }, + { + "epoch": 17.81, + "learning_rate": 6.198339753011384e-07, + "loss": 0.0019, + "step": 57683 + }, + { + "epoch": 17.81, + "learning_rate": 6.196606508937686e-07, + "loss": 0.0019, + "step": 57684 + }, + { + "epoch": 17.81, + "learning_rate": 6.194873499483367e-07, + "loss": 0.0018, + "step": 57685 + }, + { + "epoch": 17.81, + "learning_rate": 6.193140724652768e-07, + "loss": 0.0021, + "step": 57686 + }, + { + "epoch": 17.81, + "learning_rate": 6.191408184450231e-07, + "loss": 0.0028, + "step": 57687 + }, + { + "epoch": 17.82, + "learning_rate": 6.18967587888012e-07, + "loss": 0.0017, + "step": 57688 + }, + { + "epoch": 17.82, + "learning_rate": 6.187943807946728e-07, + "loss": 0.0022, + "step": 57689 + }, + { + "epoch": 17.82, + "learning_rate": 6.186211971654388e-07, + "loss": 0.002, + "step": 57690 + }, + { + "epoch": 17.82, + "learning_rate": 6.18448037000745e-07, + "loss": 0.002, + "step": 57691 + }, + { + "epoch": 17.82, + "learning_rate": 6.182749003010225e-07, + "loss": 0.0021, + "step": 57692 + }, + { + "epoch": 17.82, + "learning_rate": 6.18101787066706e-07, + "loss": 0.0021, + "step": 57693 + }, + { + "epoch": 17.82, + "learning_rate": 6.179286972982301e-07, + "loss": 0.0018, + "step": 57694 + }, + { + "epoch": 17.82, + "learning_rate": 6.177556309960253e-07, + "loss": 0.0022, + "step": 57695 + }, + { + "epoch": 17.82, + "learning_rate": 6.175825881605225e-07, + "loss": 0.0019, + "step": 57696 + }, + { + "epoch": 17.82, + "learning_rate": 6.174095687921589e-07, + "loss": 0.0022, + "step": 57697 + }, + { + "epoch": 17.82, + "learning_rate": 6.172365728913643e-07, + "loss": 0.002, + "step": 57698 + }, + { + "epoch": 17.82, + "learning_rate": 6.170636004585728e-07, + "loss": 0.0018, + "step": 57699 + }, + { + "epoch": 17.82, + "learning_rate": 6.168906514942174e-07, + "loss": 0.0014, + "step": 57700 + }, + { + "epoch": 17.82, + "learning_rate": 6.167177259987289e-07, + "loss": 0.0018, + "step": 57701 + }, + { + "epoch": 17.82, + "learning_rate": 6.165448239725391e-07, + "loss": 0.0017, + "step": 57702 + }, + { + "epoch": 17.82, + "learning_rate": 6.163719454160855e-07, + "loss": 0.0021, + "step": 57703 + }, + { + "epoch": 17.82, + "learning_rate": 6.161990903297943e-07, + "loss": 0.0019, + "step": 57704 + }, + { + "epoch": 17.82, + "learning_rate": 6.160262587141031e-07, + "loss": 0.0013, + "step": 57705 + }, + { + "epoch": 17.82, + "learning_rate": 6.158534505694403e-07, + "loss": 0.0023, + "step": 57706 + }, + { + "epoch": 17.82, + "learning_rate": 6.156806658962388e-07, + "loss": 0.0019, + "step": 57707 + }, + { + "epoch": 17.82, + "learning_rate": 6.155079046949319e-07, + "loss": 0.0021, + "step": 57708 + }, + { + "epoch": 17.82, + "learning_rate": 6.153351669659536e-07, + "loss": 0.0019, + "step": 57709 + }, + { + "epoch": 17.82, + "learning_rate": 6.151624527097322e-07, + "loss": 0.0016, + "step": 57710 + }, + { + "epoch": 17.82, + "learning_rate": 6.149897619267009e-07, + "loss": 0.0015, + "step": 57711 + }, + { + "epoch": 17.82, + "learning_rate": 6.148170946172905e-07, + "loss": 0.0023, + "step": 57712 + }, + { + "epoch": 17.82, + "learning_rate": 6.146444507819371e-07, + "loss": 0.0021, + "step": 57713 + }, + { + "epoch": 17.82, + "learning_rate": 6.144718304210673e-07, + "loss": 0.0025, + "step": 57714 + }, + { + "epoch": 17.82, + "learning_rate": 6.142992335351173e-07, + "loss": 0.0017, + "step": 57715 + }, + { + "epoch": 17.82, + "learning_rate": 6.141266601245166e-07, + "loss": 0.002, + "step": 57716 + }, + { + "epoch": 17.82, + "learning_rate": 6.139541101896961e-07, + "loss": 0.0015, + "step": 57717 + }, + { + "epoch": 17.82, + "learning_rate": 6.137815837310879e-07, + "loss": 0.0017, + "step": 57718 + }, + { + "epoch": 17.82, + "learning_rate": 6.136090807491247e-07, + "loss": 0.0015, + "step": 57719 + }, + { + "epoch": 17.82, + "learning_rate": 6.134366012442383e-07, + "loss": 0.0021, + "step": 57720 + }, + { + "epoch": 17.83, + "learning_rate": 6.132641452168564e-07, + "loss": 0.0014, + "step": 57721 + }, + { + "epoch": 17.83, + "learning_rate": 6.130917126674152e-07, + "loss": 0.0029, + "step": 57722 + }, + { + "epoch": 17.83, + "learning_rate": 6.129193035963421e-07, + "loss": 0.0017, + "step": 57723 + }, + { + "epoch": 17.83, + "learning_rate": 6.127469180040691e-07, + "loss": 0.002, + "step": 57724 + }, + { + "epoch": 17.83, + "learning_rate": 6.125745558910323e-07, + "loss": 0.0017, + "step": 57725 + }, + { + "epoch": 17.83, + "learning_rate": 6.124022172576549e-07, + "loss": 0.0018, + "step": 57726 + }, + { + "epoch": 17.83, + "learning_rate": 6.12229902104372e-07, + "loss": 0.0018, + "step": 57727 + }, + { + "epoch": 17.83, + "learning_rate": 6.120576104316156e-07, + "loss": 0.0016, + "step": 57728 + }, + { + "epoch": 17.83, + "learning_rate": 6.118853422398141e-07, + "loss": 0.0022, + "step": 57729 + }, + { + "epoch": 17.83, + "learning_rate": 6.117130975294017e-07, + "loss": 0.0016, + "step": 57730 + }, + { + "epoch": 17.83, + "learning_rate": 6.115408763008057e-07, + "loss": 0.0017, + "step": 57731 + }, + { + "epoch": 17.83, + "learning_rate": 6.113686785544581e-07, + "loss": 0.002, + "step": 57732 + }, + { + "epoch": 17.83, + "learning_rate": 6.111965042907897e-07, + "loss": 0.0021, + "step": 57733 + }, + { + "epoch": 17.83, + "learning_rate": 6.110243535102323e-07, + "loss": 0.0016, + "step": 57734 + }, + { + "epoch": 17.83, + "learning_rate": 6.108522262132144e-07, + "loss": 0.0014, + "step": 57735 + }, + { + "epoch": 17.83, + "learning_rate": 6.106801224001691e-07, + "loss": 0.0019, + "step": 57736 + }, + { + "epoch": 17.83, + "learning_rate": 6.105080420715248e-07, + "loss": 0.002, + "step": 57737 + }, + { + "epoch": 17.83, + "learning_rate": 6.103359852277114e-07, + "loss": 0.0017, + "step": 57738 + }, + { + "epoch": 17.83, + "learning_rate": 6.101639518691593e-07, + "loss": 0.0029, + "step": 57739 + }, + { + "epoch": 17.83, + "learning_rate": 6.099919419963018e-07, + "loss": 0.0024, + "step": 57740 + }, + { + "epoch": 17.83, + "learning_rate": 6.098199556095674e-07, + "loss": 0.0015, + "step": 57741 + }, + { + "epoch": 17.83, + "learning_rate": 6.096479927093846e-07, + "loss": 0.0016, + "step": 57742 + }, + { + "epoch": 17.83, + "learning_rate": 6.094760532961841e-07, + "loss": 0.002, + "step": 57743 + }, + { + "epoch": 17.83, + "learning_rate": 6.093041373703989e-07, + "loss": 0.0024, + "step": 57744 + }, + { + "epoch": 17.83, + "learning_rate": 6.091322449324555e-07, + "loss": 0.002, + "step": 57745 + }, + { + "epoch": 17.83, + "learning_rate": 6.089603759827856e-07, + "loss": 0.0022, + "step": 57746 + }, + { + "epoch": 17.83, + "learning_rate": 6.087885305218199e-07, + "loss": 0.0031, + "step": 57747 + }, + { + "epoch": 17.83, + "learning_rate": 6.086167085499839e-07, + "loss": 0.0037, + "step": 57748 + }, + { + "epoch": 17.83, + "learning_rate": 6.084449100677114e-07, + "loss": 0.002, + "step": 57749 + }, + { + "epoch": 17.83, + "learning_rate": 6.082731350754334e-07, + "loss": 0.0021, + "step": 57750 + }, + { + "epoch": 17.83, + "learning_rate": 6.081013835735761e-07, + "loss": 0.0019, + "step": 57751 + }, + { + "epoch": 17.83, + "learning_rate": 6.079296555625691e-07, + "loss": 0.0022, + "step": 57752 + }, + { + "epoch": 17.84, + "learning_rate": 6.077579510428444e-07, + "loss": 0.0015, + "step": 57753 + }, + { + "epoch": 17.84, + "learning_rate": 6.075862700148282e-07, + "loss": 0.0017, + "step": 57754 + }, + { + "epoch": 17.84, + "learning_rate": 6.074146124789515e-07, + "loss": 0.0018, + "step": 57755 + }, + { + "epoch": 17.84, + "learning_rate": 6.072429784356481e-07, + "loss": 0.0021, + "step": 57756 + }, + { + "epoch": 17.84, + "learning_rate": 6.070713678853402e-07, + "loss": 0.0017, + "step": 57757 + }, + { + "epoch": 17.84, + "learning_rate": 6.068997808284593e-07, + "loss": 0.0019, + "step": 57758 + }, + { + "epoch": 17.84, + "learning_rate": 6.067282172654365e-07, + "loss": 0.0028, + "step": 57759 + }, + { + "epoch": 17.84, + "learning_rate": 6.06556677196698e-07, + "loss": 0.0019, + "step": 57760 + }, + { + "epoch": 17.84, + "learning_rate": 6.063851606226767e-07, + "loss": 0.0028, + "step": 57761 + }, + { + "epoch": 17.84, + "learning_rate": 6.062136675438002e-07, + "loss": 0.002, + "step": 57762 + }, + { + "epoch": 17.84, + "learning_rate": 6.060421979604936e-07, + "loss": 0.0018, + "step": 57763 + }, + { + "epoch": 17.84, + "learning_rate": 6.058707518731898e-07, + "loss": 0.0018, + "step": 57764 + }, + { + "epoch": 17.84, + "learning_rate": 6.056993292823176e-07, + "loss": 0.0017, + "step": 57765 + }, + { + "epoch": 17.84, + "learning_rate": 6.055279301883044e-07, + "loss": 0.0016, + "step": 57766 + }, + { + "epoch": 17.84, + "learning_rate": 6.053565545915785e-07, + "loss": 0.0021, + "step": 57767 + }, + { + "epoch": 17.84, + "learning_rate": 6.051852024925709e-07, + "loss": 0.001, + "step": 57768 + }, + { + "epoch": 17.84, + "learning_rate": 6.050138738917066e-07, + "loss": 0.003, + "step": 57769 + }, + { + "epoch": 17.84, + "learning_rate": 6.048425687894166e-07, + "loss": 0.0021, + "step": 57770 + }, + { + "epoch": 17.84, + "learning_rate": 6.046712871861304e-07, + "loss": 0.0017, + "step": 57771 + }, + { + "epoch": 17.84, + "learning_rate": 6.045000290822744e-07, + "loss": 0.0024, + "step": 57772 + }, + { + "epoch": 17.84, + "learning_rate": 6.043287944782761e-07, + "loss": 0.0021, + "step": 57773 + }, + { + "epoch": 17.84, + "learning_rate": 6.041575833745672e-07, + "loss": 0.0024, + "step": 57774 + }, + { + "epoch": 17.84, + "learning_rate": 6.039863957715719e-07, + "loss": 0.0016, + "step": 57775 + }, + { + "epoch": 17.84, + "learning_rate": 6.038152316697221e-07, + "loss": 0.0019, + "step": 57776 + }, + { + "epoch": 17.84, + "learning_rate": 6.036440910694419e-07, + "loss": 0.0012, + "step": 57777 + }, + { + "epoch": 17.84, + "learning_rate": 6.034729739711642e-07, + "loss": 0.0018, + "step": 57778 + }, + { + "epoch": 17.84, + "learning_rate": 6.033018803753121e-07, + "loss": 0.002, + "step": 57779 + }, + { + "epoch": 17.84, + "learning_rate": 6.031308102823163e-07, + "loss": 0.0023, + "step": 57780 + }, + { + "epoch": 17.84, + "learning_rate": 6.029597636926054e-07, + "loss": 0.0021, + "step": 57781 + }, + { + "epoch": 17.84, + "learning_rate": 6.027887406066069e-07, + "loss": 0.0016, + "step": 57782 + }, + { + "epoch": 17.84, + "learning_rate": 6.026177410247458e-07, + "loss": 0.0019, + "step": 57783 + }, + { + "epoch": 17.84, + "learning_rate": 6.024467649474519e-07, + "loss": 0.0018, + "step": 57784 + }, + { + "epoch": 17.85, + "learning_rate": 6.022758123751527e-07, + "loss": 0.0017, + "step": 57785 + }, + { + "epoch": 17.85, + "learning_rate": 6.021048833082765e-07, + "loss": 0.002, + "step": 57786 + }, + { + "epoch": 17.85, + "learning_rate": 6.01933977747251e-07, + "loss": 0.0019, + "step": 57787 + }, + { + "epoch": 17.85, + "learning_rate": 6.017630956925002e-07, + "loss": 0.0018, + "step": 57788 + }, + { + "epoch": 17.85, + "learning_rate": 6.015922371444538e-07, + "loss": 0.0029, + "step": 57789 + }, + { + "epoch": 17.85, + "learning_rate": 6.014214021035414e-07, + "loss": 0.0021, + "step": 57790 + }, + { + "epoch": 17.85, + "learning_rate": 6.012505905701871e-07, + "loss": 0.0028, + "step": 57791 + }, + { + "epoch": 17.85, + "learning_rate": 6.010798025448205e-07, + "loss": 0.0016, + "step": 57792 + }, + { + "epoch": 17.85, + "learning_rate": 6.009090380278681e-07, + "loss": 0.0017, + "step": 57793 + }, + { + "epoch": 17.85, + "learning_rate": 6.007382970197539e-07, + "loss": 0.0017, + "step": 57794 + }, + { + "epoch": 17.85, + "learning_rate": 6.005675795209087e-07, + "loss": 0.0015, + "step": 57795 + }, + { + "epoch": 17.85, + "learning_rate": 6.003968855317587e-07, + "loss": 0.0018, + "step": 57796 + }, + { + "epoch": 17.85, + "learning_rate": 6.002262150527316e-07, + "loss": 0.0013, + "step": 57797 + }, + { + "epoch": 17.85, + "learning_rate": 6.000555680842502e-07, + "loss": 0.0023, + "step": 57798 + }, + { + "epoch": 17.85, + "learning_rate": 5.998849446267474e-07, + "loss": 0.0022, + "step": 57799 + }, + { + "epoch": 17.85, + "learning_rate": 5.997143446806441e-07, + "loss": 0.0018, + "step": 57800 + }, + { + "epoch": 17.85, + "learning_rate": 5.995437682463701e-07, + "loss": 0.0019, + "step": 57801 + }, + { + "epoch": 17.85, + "learning_rate": 5.993732153243537e-07, + "loss": 0.0018, + "step": 57802 + }, + { + "epoch": 17.85, + "learning_rate": 5.992026859150191e-07, + "loss": 0.0016, + "step": 57803 + }, + { + "epoch": 17.85, + "learning_rate": 5.990321800187915e-07, + "loss": 0.0021, + "step": 57804 + }, + { + "epoch": 17.85, + "learning_rate": 5.988616976361005e-07, + "loss": 0.0015, + "step": 57805 + }, + { + "epoch": 17.85, + "learning_rate": 5.986912387673694e-07, + "loss": 0.0029, + "step": 57806 + }, + { + "epoch": 17.85, + "learning_rate": 5.985208034130286e-07, + "loss": 0.0019, + "step": 57807 + }, + { + "epoch": 17.85, + "learning_rate": 5.983503915734989e-07, + "loss": 0.0018, + "step": 57808 + }, + { + "epoch": 17.85, + "learning_rate": 5.981800032492125e-07, + "loss": 0.0016, + "step": 57809 + }, + { + "epoch": 17.85, + "learning_rate": 5.980096384405909e-07, + "loss": 0.002, + "step": 57810 + }, + { + "epoch": 17.85, + "learning_rate": 5.978392971480617e-07, + "loss": 0.0019, + "step": 57811 + }, + { + "epoch": 17.85, + "learning_rate": 5.976689793720536e-07, + "loss": 0.0016, + "step": 57812 + }, + { + "epoch": 17.85, + "learning_rate": 5.974986851129893e-07, + "loss": 0.0019, + "step": 57813 + }, + { + "epoch": 17.85, + "learning_rate": 5.973284143712943e-07, + "loss": 0.0022, + "step": 57814 + }, + { + "epoch": 17.85, + "learning_rate": 5.971581671473981e-07, + "loss": 0.0016, + "step": 57815 + }, + { + "epoch": 17.85, + "learning_rate": 5.969879434417214e-07, + "loss": 0.0034, + "step": 57816 + }, + { + "epoch": 17.85, + "learning_rate": 5.968177432546962e-07, + "loss": 0.0018, + "step": 57817 + }, + { + "epoch": 17.86, + "learning_rate": 5.966475665867433e-07, + "loss": 0.0017, + "step": 57818 + }, + { + "epoch": 17.86, + "learning_rate": 5.964774134382889e-07, + "loss": 0.0023, + "step": 57819 + }, + { + "epoch": 17.86, + "learning_rate": 5.963072838097594e-07, + "loss": 0.0017, + "step": 57820 + }, + { + "epoch": 17.86, + "learning_rate": 5.961371777015823e-07, + "loss": 0.0021, + "step": 57821 + }, + { + "epoch": 17.86, + "learning_rate": 5.959670951141805e-07, + "loss": 0.0012, + "step": 57822 + }, + { + "epoch": 17.86, + "learning_rate": 5.957970360479803e-07, + "loss": 0.0022, + "step": 57823 + }, + { + "epoch": 17.86, + "learning_rate": 5.956270005034082e-07, + "loss": 0.0021, + "step": 57824 + }, + { + "epoch": 17.86, + "learning_rate": 5.954569884808858e-07, + "loss": 0.0012, + "step": 57825 + }, + { + "epoch": 17.86, + "learning_rate": 5.952869999808409e-07, + "loss": 0.002, + "step": 57826 + }, + { + "epoch": 17.86, + "learning_rate": 5.951170350037006e-07, + "loss": 0.0012, + "step": 57827 + }, + { + "epoch": 17.86, + "learning_rate": 5.94947093549888e-07, + "loss": 0.0018, + "step": 57828 + }, + { + "epoch": 17.86, + "learning_rate": 5.947771756198262e-07, + "loss": 0.0014, + "step": 57829 + }, + { + "epoch": 17.86, + "learning_rate": 5.946072812139426e-07, + "loss": 0.0022, + "step": 57830 + }, + { + "epoch": 17.86, + "learning_rate": 5.944374103326611e-07, + "loss": 0.0025, + "step": 57831 + }, + { + "epoch": 17.86, + "learning_rate": 5.942675629764072e-07, + "loss": 0.002, + "step": 57832 + }, + { + "epoch": 17.86, + "learning_rate": 5.940977391456071e-07, + "loss": 0.003, + "step": 57833 + }, + { + "epoch": 17.86, + "learning_rate": 5.939279388406838e-07, + "loss": 0.0018, + "step": 57834 + }, + { + "epoch": 17.86, + "learning_rate": 5.937581620620614e-07, + "loss": 0.0023, + "step": 57835 + }, + { + "epoch": 17.86, + "learning_rate": 5.935884088101663e-07, + "loss": 0.0021, + "step": 57836 + }, + { + "epoch": 17.86, + "learning_rate": 5.934186790854213e-07, + "loss": 0.0022, + "step": 57837 + }, + { + "epoch": 17.86, + "learning_rate": 5.932489728882529e-07, + "loss": 0.0019, + "step": 57838 + }, + { + "epoch": 17.86, + "learning_rate": 5.93079290219084e-07, + "loss": 0.002, + "step": 57839 + }, + { + "epoch": 17.86, + "learning_rate": 5.929096310783389e-07, + "loss": 0.002, + "step": 57840 + }, + { + "epoch": 17.86, + "learning_rate": 5.927399954664414e-07, + "loss": 0.0023, + "step": 57841 + }, + { + "epoch": 17.86, + "learning_rate": 5.925703833838181e-07, + "loss": 0.0014, + "step": 57842 + }, + { + "epoch": 17.86, + "learning_rate": 5.92400794830893e-07, + "loss": 0.0023, + "step": 57843 + }, + { + "epoch": 17.86, + "learning_rate": 5.922312298080901e-07, + "loss": 0.0019, + "step": 57844 + }, + { + "epoch": 17.86, + "learning_rate": 5.920616883158304e-07, + "loss": 0.0023, + "step": 57845 + }, + { + "epoch": 17.86, + "learning_rate": 5.918921703545421e-07, + "loss": 0.0022, + "step": 57846 + }, + { + "epoch": 17.86, + "learning_rate": 5.917226759246463e-07, + "loss": 0.0026, + "step": 57847 + }, + { + "epoch": 17.86, + "learning_rate": 5.915532050265694e-07, + "loss": 0.0028, + "step": 57848 + }, + { + "epoch": 17.86, + "learning_rate": 5.91383757660734e-07, + "loss": 0.0014, + "step": 57849 + }, + { + "epoch": 17.87, + "learning_rate": 5.912143338275611e-07, + "loss": 0.002, + "step": 57850 + }, + { + "epoch": 17.87, + "learning_rate": 5.910449335274793e-07, + "loss": 0.0024, + "step": 57851 + }, + { + "epoch": 17.87, + "learning_rate": 5.908755567609103e-07, + "loss": 0.003, + "step": 57852 + }, + { + "epoch": 17.87, + "learning_rate": 5.907062035282762e-07, + "loss": 0.0026, + "step": 57853 + }, + { + "epoch": 17.87, + "learning_rate": 5.905368738300043e-07, + "loss": 0.0018, + "step": 57854 + }, + { + "epoch": 17.87, + "learning_rate": 5.903675676665144e-07, + "loss": 0.0018, + "step": 57855 + }, + { + "epoch": 17.87, + "learning_rate": 5.901982850382315e-07, + "loss": 0.0015, + "step": 57856 + }, + { + "epoch": 17.87, + "learning_rate": 5.900290259455776e-07, + "loss": 0.0017, + "step": 57857 + }, + { + "epoch": 17.87, + "learning_rate": 5.898597903889802e-07, + "loss": 0.0022, + "step": 57858 + }, + { + "epoch": 17.87, + "learning_rate": 5.896905783688589e-07, + "loss": 0.0018, + "step": 57859 + }, + { + "epoch": 17.87, + "learning_rate": 5.895213898856367e-07, + "loss": 0.0018, + "step": 57860 + }, + { + "epoch": 17.87, + "learning_rate": 5.893522249397387e-07, + "loss": 0.0017, + "step": 57861 + }, + { + "epoch": 17.87, + "learning_rate": 5.89183083531587e-07, + "loss": 0.0015, + "step": 57862 + }, + { + "epoch": 17.87, + "learning_rate": 5.890139656616034e-07, + "loss": 0.0016, + "step": 57863 + }, + { + "epoch": 17.87, + "learning_rate": 5.888448713302164e-07, + "loss": 0.0017, + "step": 57864 + }, + { + "epoch": 17.87, + "learning_rate": 5.886758005378412e-07, + "loss": 0.0031, + "step": 57865 + }, + { + "epoch": 17.87, + "learning_rate": 5.885067532849043e-07, + "loss": 0.0021, + "step": 57866 + }, + { + "epoch": 17.87, + "learning_rate": 5.883377295718307e-07, + "loss": 0.0018, + "step": 57867 + }, + { + "epoch": 17.87, + "learning_rate": 5.88168729399039e-07, + "loss": 0.002, + "step": 57868 + }, + { + "epoch": 17.87, + "learning_rate": 5.879997527669557e-07, + "loss": 0.0022, + "step": 57869 + }, + { + "epoch": 17.87, + "learning_rate": 5.878307996760014e-07, + "loss": 0.0019, + "step": 57870 + }, + { + "epoch": 17.87, + "learning_rate": 5.876618701265979e-07, + "loss": 0.0023, + "step": 57871 + }, + { + "epoch": 17.87, + "learning_rate": 5.874929641191684e-07, + "loss": 0.0026, + "step": 57872 + }, + { + "epoch": 17.87, + "learning_rate": 5.87324081654137e-07, + "loss": 0.0017, + "step": 57873 + }, + { + "epoch": 17.87, + "learning_rate": 5.871552227319255e-07, + "loss": 0.0015, + "step": 57874 + }, + { + "epoch": 17.87, + "learning_rate": 5.869863873529536e-07, + "loss": 0.002, + "step": 57875 + }, + { + "epoch": 17.87, + "learning_rate": 5.868175755176453e-07, + "loss": 0.0015, + "step": 57876 + }, + { + "epoch": 17.87, + "learning_rate": 5.866487872264248e-07, + "loss": 0.0013, + "step": 57877 + }, + { + "epoch": 17.87, + "learning_rate": 5.864800224797118e-07, + "loss": 0.002, + "step": 57878 + }, + { + "epoch": 17.87, + "learning_rate": 5.863112812779303e-07, + "loss": 0.002, + "step": 57879 + }, + { + "epoch": 17.87, + "learning_rate": 5.861425636215002e-07, + "loss": 0.0024, + "step": 57880 + }, + { + "epoch": 17.87, + "learning_rate": 5.859738695108441e-07, + "loss": 0.0023, + "step": 57881 + }, + { + "epoch": 17.87, + "learning_rate": 5.858051989463842e-07, + "loss": 0.0022, + "step": 57882 + }, + { + "epoch": 17.88, + "learning_rate": 5.856365519285445e-07, + "loss": 0.0016, + "step": 57883 + }, + { + "epoch": 17.88, + "learning_rate": 5.854679284577436e-07, + "loss": 0.0019, + "step": 57884 + }, + { + "epoch": 17.88, + "learning_rate": 5.852993285344044e-07, + "loss": 0.0016, + "step": 57885 + }, + { + "epoch": 17.88, + "learning_rate": 5.851307521589489e-07, + "loss": 0.0018, + "step": 57886 + }, + { + "epoch": 17.88, + "learning_rate": 5.849621993317977e-07, + "loss": 0.002, + "step": 57887 + }, + { + "epoch": 17.88, + "learning_rate": 5.847936700533741e-07, + "loss": 0.002, + "step": 57888 + }, + { + "epoch": 17.88, + "learning_rate": 5.846251643240985e-07, + "loss": 0.0015, + "step": 57889 + }, + { + "epoch": 17.88, + "learning_rate": 5.844566821443942e-07, + "loss": 0.0016, + "step": 57890 + }, + { + "epoch": 17.88, + "learning_rate": 5.842882235146785e-07, + "loss": 0.0018, + "step": 57891 + }, + { + "epoch": 17.88, + "learning_rate": 5.841197884353777e-07, + "loss": 0.0022, + "step": 57892 + }, + { + "epoch": 17.88, + "learning_rate": 5.839513769069083e-07, + "loss": 0.0014, + "step": 57893 + }, + { + "epoch": 17.88, + "learning_rate": 5.837829889296954e-07, + "loss": 0.0018, + "step": 57894 + }, + { + "epoch": 17.88, + "learning_rate": 5.836146245041585e-07, + "loss": 0.0026, + "step": 57895 + }, + { + "epoch": 17.88, + "learning_rate": 5.834462836307187e-07, + "loss": 0.0017, + "step": 57896 + }, + { + "epoch": 17.88, + "learning_rate": 5.832779663097965e-07, + "loss": 0.0015, + "step": 57897 + }, + { + "epoch": 17.88, + "learning_rate": 5.83109672541814e-07, + "loss": 0.0015, + "step": 57898 + }, + { + "epoch": 17.88, + "learning_rate": 5.829414023271918e-07, + "loss": 0.0024, + "step": 57899 + }, + { + "epoch": 17.88, + "learning_rate": 5.827731556663518e-07, + "loss": 0.0021, + "step": 57900 + }, + { + "epoch": 17.88, + "learning_rate": 5.826049325597127e-07, + "loss": 0.0026, + "step": 57901 + }, + { + "epoch": 17.88, + "learning_rate": 5.824367330076963e-07, + "loss": 0.0023, + "step": 57902 + }, + { + "epoch": 17.88, + "learning_rate": 5.822685570107223e-07, + "loss": 0.0028, + "step": 57903 + }, + { + "epoch": 17.88, + "learning_rate": 5.821004045692135e-07, + "loss": 0.0021, + "step": 57904 + }, + { + "epoch": 17.88, + "learning_rate": 5.81932275683591e-07, + "loss": 0.0022, + "step": 57905 + }, + { + "epoch": 17.88, + "learning_rate": 5.817641703542709e-07, + "loss": 0.0018, + "step": 57906 + }, + { + "epoch": 17.88, + "learning_rate": 5.815960885816762e-07, + "loss": 0.0014, + "step": 57907 + }, + { + "epoch": 17.88, + "learning_rate": 5.81428030366229e-07, + "loss": 0.0024, + "step": 57908 + }, + { + "epoch": 17.88, + "learning_rate": 5.812599957083476e-07, + "loss": 0.0015, + "step": 57909 + }, + { + "epoch": 17.88, + "learning_rate": 5.810919846084529e-07, + "loss": 0.0025, + "step": 57910 + }, + { + "epoch": 17.88, + "learning_rate": 5.809239970669667e-07, + "loss": 0.0021, + "step": 57911 + }, + { + "epoch": 17.88, + "learning_rate": 5.807560330843043e-07, + "loss": 0.0016, + "step": 57912 + }, + { + "epoch": 17.88, + "learning_rate": 5.805880926608897e-07, + "loss": 0.0022, + "step": 57913 + }, + { + "epoch": 17.88, + "learning_rate": 5.80420175797145e-07, + "loss": 0.0021, + "step": 57914 + }, + { + "epoch": 17.89, + "learning_rate": 5.802522824934865e-07, + "loss": 0.0021, + "step": 57915 + }, + { + "epoch": 17.89, + "learning_rate": 5.800844127503324e-07, + "loss": 0.0019, + "step": 57916 + }, + { + "epoch": 17.89, + "learning_rate": 5.799165665681084e-07, + "loss": 0.0017, + "step": 57917 + }, + { + "epoch": 17.89, + "learning_rate": 5.797487439472294e-07, + "loss": 0.0021, + "step": 57918 + }, + { + "epoch": 17.89, + "learning_rate": 5.795809448881162e-07, + "loss": 0.0012, + "step": 57919 + }, + { + "epoch": 17.89, + "learning_rate": 5.794131693911919e-07, + "loss": 0.0011, + "step": 57920 + }, + { + "epoch": 17.89, + "learning_rate": 5.79245417456873e-07, + "loss": 0.0026, + "step": 57921 + }, + { + "epoch": 17.89, + "learning_rate": 5.790776890855776e-07, + "loss": 0.0019, + "step": 57922 + }, + { + "epoch": 17.89, + "learning_rate": 5.789099842777291e-07, + "loss": 0.0016, + "step": 57923 + }, + { + "epoch": 17.89, + "learning_rate": 5.787423030337425e-07, + "loss": 0.002, + "step": 57924 + }, + { + "epoch": 17.89, + "learning_rate": 5.78574645354042e-07, + "loss": 0.0017, + "step": 57925 + }, + { + "epoch": 17.89, + "learning_rate": 5.784070112390449e-07, + "loss": 0.0017, + "step": 57926 + }, + { + "epoch": 17.89, + "learning_rate": 5.78239400689169e-07, + "loss": 0.0016, + "step": 57927 + }, + { + "epoch": 17.89, + "learning_rate": 5.780718137048347e-07, + "loss": 0.0023, + "step": 57928 + }, + { + "epoch": 17.89, + "learning_rate": 5.779042502864618e-07, + "loss": 0.0017, + "step": 57929 + }, + { + "epoch": 17.89, + "learning_rate": 5.777367104344677e-07, + "loss": 0.0028, + "step": 57930 + }, + { + "epoch": 17.89, + "learning_rate": 5.775691941492745e-07, + "loss": 0.0022, + "step": 57931 + }, + { + "epoch": 17.89, + "learning_rate": 5.774017014312993e-07, + "loss": 0.0017, + "step": 57932 + }, + { + "epoch": 17.89, + "learning_rate": 5.772342322809599e-07, + "loss": 0.0017, + "step": 57933 + }, + { + "epoch": 17.89, + "learning_rate": 5.770667866986757e-07, + "loss": 0.0011, + "step": 57934 + }, + { + "epoch": 17.89, + "learning_rate": 5.768993646848675e-07, + "loss": 0.002, + "step": 57935 + }, + { + "epoch": 17.89, + "learning_rate": 5.767319662399528e-07, + "loss": 0.0022, + "step": 57936 + }, + { + "epoch": 17.89, + "learning_rate": 5.765645913643492e-07, + "loss": 0.0022, + "step": 57937 + }, + { + "epoch": 17.89, + "learning_rate": 5.763972400584772e-07, + "loss": 0.0023, + "step": 57938 + }, + { + "epoch": 17.89, + "learning_rate": 5.762299123227533e-07, + "loss": 0.0014, + "step": 57939 + }, + { + "epoch": 17.89, + "learning_rate": 5.76062608157596e-07, + "loss": 0.0018, + "step": 57940 + }, + { + "epoch": 17.89, + "learning_rate": 5.758953275634283e-07, + "loss": 0.0017, + "step": 57941 + }, + { + "epoch": 17.89, + "learning_rate": 5.757280705406642e-07, + "loss": 0.0025, + "step": 57942 + }, + { + "epoch": 17.89, + "learning_rate": 5.755608370897214e-07, + "loss": 0.0024, + "step": 57943 + }, + { + "epoch": 17.89, + "learning_rate": 5.753936272110206e-07, + "loss": 0.0013, + "step": 57944 + }, + { + "epoch": 17.89, + "learning_rate": 5.752264409049802e-07, + "loss": 0.0023, + "step": 57945 + }, + { + "epoch": 17.89, + "learning_rate": 5.750592781720166e-07, + "loss": 0.0018, + "step": 57946 + }, + { + "epoch": 17.9, + "learning_rate": 5.748921390125483e-07, + "loss": 0.002, + "step": 57947 + }, + { + "epoch": 17.9, + "learning_rate": 5.747250234269952e-07, + "loss": 0.002, + "step": 57948 + }, + { + "epoch": 17.9, + "learning_rate": 5.745579314157723e-07, + "loss": 0.0022, + "step": 57949 + }, + { + "epoch": 17.9, + "learning_rate": 5.743908629792993e-07, + "loss": 0.0018, + "step": 57950 + }, + { + "epoch": 17.9, + "learning_rate": 5.74223818117996e-07, + "loss": 0.0019, + "step": 57951 + }, + { + "epoch": 17.9, + "learning_rate": 5.740567968322764e-07, + "loss": 0.0019, + "step": 57952 + }, + { + "epoch": 17.9, + "learning_rate": 5.7388979912256e-07, + "loss": 0.0019, + "step": 57953 + }, + { + "epoch": 17.9, + "learning_rate": 5.737228249892657e-07, + "loss": 0.0018, + "step": 57954 + }, + { + "epoch": 17.9, + "learning_rate": 5.735558744328074e-07, + "loss": 0.0016, + "step": 57955 + }, + { + "epoch": 17.9, + "learning_rate": 5.733889474536069e-07, + "loss": 0.0023, + "step": 57956 + }, + { + "epoch": 17.9, + "learning_rate": 5.732220440520808e-07, + "loss": 0.0019, + "step": 57957 + }, + { + "epoch": 17.9, + "learning_rate": 5.73055164228643e-07, + "loss": 0.0017, + "step": 57958 + }, + { + "epoch": 17.9, + "learning_rate": 5.728883079837144e-07, + "loss": 0.0019, + "step": 57959 + }, + { + "epoch": 17.9, + "learning_rate": 5.727214753177135e-07, + "loss": 0.002, + "step": 57960 + }, + { + "epoch": 17.9, + "learning_rate": 5.725546662310532e-07, + "loss": 0.002, + "step": 57961 + }, + { + "epoch": 17.9, + "learning_rate": 5.723878807241545e-07, + "loss": 0.0019, + "step": 57962 + }, + { + "epoch": 17.9, + "learning_rate": 5.722211187974336e-07, + "loss": 0.0024, + "step": 57963 + }, + { + "epoch": 17.9, + "learning_rate": 5.720543804513057e-07, + "loss": 0.0023, + "step": 57964 + }, + { + "epoch": 17.9, + "learning_rate": 5.718876656861894e-07, + "loss": 0.0023, + "step": 57965 + }, + { + "epoch": 17.9, + "learning_rate": 5.717209745025032e-07, + "loss": 0.0017, + "step": 57966 + }, + { + "epoch": 17.9, + "learning_rate": 5.715543069006624e-07, + "loss": 0.0014, + "step": 57967 + }, + { + "epoch": 17.9, + "learning_rate": 5.713876628810832e-07, + "loss": 0.002, + "step": 57968 + }, + { + "epoch": 17.9, + "learning_rate": 5.712210424441833e-07, + "loss": 0.0021, + "step": 57969 + }, + { + "epoch": 17.9, + "learning_rate": 5.710544455903788e-07, + "loss": 0.0021, + "step": 57970 + }, + { + "epoch": 17.9, + "learning_rate": 5.708878723200861e-07, + "loss": 0.002, + "step": 57971 + }, + { + "epoch": 17.9, + "learning_rate": 5.707213226337238e-07, + "loss": 0.0019, + "step": 57972 + }, + { + "epoch": 17.9, + "learning_rate": 5.705547965317082e-07, + "loss": 0.0022, + "step": 57973 + }, + { + "epoch": 17.9, + "learning_rate": 5.703882940144534e-07, + "loss": 0.0019, + "step": 57974 + }, + { + "epoch": 17.9, + "learning_rate": 5.702218150823768e-07, + "loss": 0.0025, + "step": 57975 + }, + { + "epoch": 17.9, + "learning_rate": 5.70055359735897e-07, + "loss": 0.0018, + "step": 57976 + }, + { + "epoch": 17.9, + "learning_rate": 5.698889279754283e-07, + "loss": 0.0019, + "step": 57977 + }, + { + "epoch": 17.9, + "learning_rate": 5.697225198013856e-07, + "loss": 0.0014, + "step": 57978 + }, + { + "epoch": 17.9, + "learning_rate": 5.695561352141899e-07, + "loss": 0.0023, + "step": 57979 + }, + { + "epoch": 17.91, + "learning_rate": 5.693897742142518e-07, + "loss": 0.0023, + "step": 57980 + }, + { + "epoch": 17.91, + "learning_rate": 5.692234368019899e-07, + "loss": 0.002, + "step": 57981 + }, + { + "epoch": 17.91, + "learning_rate": 5.69057122977823e-07, + "loss": 0.0021, + "step": 57982 + }, + { + "epoch": 17.91, + "learning_rate": 5.688908327421616e-07, + "loss": 0.0018, + "step": 57983 + }, + { + "epoch": 17.91, + "learning_rate": 5.687245660954243e-07, + "loss": 0.0017, + "step": 57984 + }, + { + "epoch": 17.91, + "learning_rate": 5.685583230380287e-07, + "loss": 0.0019, + "step": 57985 + }, + { + "epoch": 17.91, + "learning_rate": 5.683921035703876e-07, + "loss": 0.0024, + "step": 57986 + }, + { + "epoch": 17.91, + "learning_rate": 5.682259076929187e-07, + "loss": 0.002, + "step": 57987 + }, + { + "epoch": 17.91, + "learning_rate": 5.68059735406038e-07, + "loss": 0.0023, + "step": 57988 + }, + { + "epoch": 17.91, + "learning_rate": 5.678935867101576e-07, + "loss": 0.0018, + "step": 57989 + }, + { + "epoch": 17.91, + "learning_rate": 5.677274616056971e-07, + "loss": 0.0019, + "step": 57990 + }, + { + "epoch": 17.91, + "learning_rate": 5.675613600930707e-07, + "loss": 0.0023, + "step": 57991 + }, + { + "epoch": 17.91, + "learning_rate": 5.673952821726936e-07, + "loss": 0.0022, + "step": 57992 + }, + { + "epoch": 17.91, + "learning_rate": 5.67229227844982e-07, + "loss": 0.002, + "step": 57993 + }, + { + "epoch": 17.91, + "learning_rate": 5.670631971103502e-07, + "loss": 0.002, + "step": 57994 + }, + { + "epoch": 17.91, + "learning_rate": 5.668971899692122e-07, + "loss": 0.0021, + "step": 57995 + }, + { + "epoch": 17.91, + "learning_rate": 5.667312064219854e-07, + "loss": 0.0018, + "step": 57996 + }, + { + "epoch": 17.91, + "learning_rate": 5.665652464690862e-07, + "loss": 0.0021, + "step": 57997 + }, + { + "epoch": 17.91, + "learning_rate": 5.663993101109266e-07, + "loss": 0.0016, + "step": 57998 + }, + { + "epoch": 17.91, + "learning_rate": 5.662333973479228e-07, + "loss": 0.0016, + "step": 57999 + }, + { + "epoch": 17.91, + "learning_rate": 5.660675081804911e-07, + "loss": 0.002, + "step": 58000 + }, + { + "epoch": 17.91, + "learning_rate": 5.659016426090436e-07, + "loss": 0.0016, + "step": 58001 + }, + { + "epoch": 17.91, + "learning_rate": 5.657358006339963e-07, + "loss": 0.0021, + "step": 58002 + }, + { + "epoch": 17.91, + "learning_rate": 5.65569982255767e-07, + "loss": 0.0016, + "step": 58003 + }, + { + "epoch": 17.91, + "learning_rate": 5.654041874747663e-07, + "loss": 0.0022, + "step": 58004 + }, + { + "epoch": 17.91, + "learning_rate": 5.652384162914093e-07, + "loss": 0.0015, + "step": 58005 + }, + { + "epoch": 17.91, + "learning_rate": 5.650726687061126e-07, + "loss": 0.0018, + "step": 58006 + }, + { + "epoch": 17.91, + "learning_rate": 5.649069447192912e-07, + "loss": 0.0019, + "step": 58007 + }, + { + "epoch": 17.91, + "learning_rate": 5.647412443313582e-07, + "loss": 0.003, + "step": 58008 + }, + { + "epoch": 17.91, + "learning_rate": 5.645755675427278e-07, + "loss": 0.0015, + "step": 58009 + }, + { + "epoch": 17.91, + "learning_rate": 5.644099143538151e-07, + "loss": 0.0017, + "step": 58010 + }, + { + "epoch": 17.91, + "learning_rate": 5.642442847650331e-07, + "loss": 0.0022, + "step": 58011 + }, + { + "epoch": 17.92, + "learning_rate": 5.640786787767972e-07, + "loss": 0.0021, + "step": 58012 + }, + { + "epoch": 17.92, + "learning_rate": 5.639130963895234e-07, + "loss": 0.002, + "step": 58013 + }, + { + "epoch": 17.92, + "learning_rate": 5.637475376036227e-07, + "loss": 0.0019, + "step": 58014 + }, + { + "epoch": 17.92, + "learning_rate": 5.635820024195093e-07, + "loss": 0.0019, + "step": 58015 + }, + { + "epoch": 17.92, + "learning_rate": 5.634164908376006e-07, + "loss": 0.0018, + "step": 58016 + }, + { + "epoch": 17.92, + "learning_rate": 5.63251002858306e-07, + "loss": 0.0018, + "step": 58017 + }, + { + "epoch": 17.92, + "learning_rate": 5.630855384820443e-07, + "loss": 0.0019, + "step": 58018 + }, + { + "epoch": 17.92, + "learning_rate": 5.629200977092264e-07, + "loss": 0.0019, + "step": 58019 + }, + { + "epoch": 17.92, + "learning_rate": 5.627546805402651e-07, + "loss": 0.0019, + "step": 58020 + }, + { + "epoch": 17.92, + "learning_rate": 5.625892869755756e-07, + "loss": 0.002, + "step": 58021 + }, + { + "epoch": 17.92, + "learning_rate": 5.624239170155732e-07, + "loss": 0.0023, + "step": 58022 + }, + { + "epoch": 17.92, + "learning_rate": 5.622585706606698e-07, + "loss": 0.0018, + "step": 58023 + }, + { + "epoch": 17.92, + "learning_rate": 5.620932479112773e-07, + "loss": 0.0014, + "step": 58024 + }, + { + "epoch": 17.92, + "learning_rate": 5.61927948767813e-07, + "loss": 0.0021, + "step": 58025 + }, + { + "epoch": 17.92, + "learning_rate": 5.617626732306858e-07, + "loss": 0.0015, + "step": 58026 + }, + { + "epoch": 17.92, + "learning_rate": 5.615974213003128e-07, + "loss": 0.0018, + "step": 58027 + }, + { + "epoch": 17.92, + "learning_rate": 5.614321929771072e-07, + "loss": 0.0021, + "step": 58028 + }, + { + "epoch": 17.92, + "learning_rate": 5.612669882614807e-07, + "loss": 0.0022, + "step": 58029 + }, + { + "epoch": 17.92, + "learning_rate": 5.611018071538454e-07, + "loss": 0.0013, + "step": 58030 + }, + { + "epoch": 17.92, + "learning_rate": 5.609366496546187e-07, + "loss": 0.0023, + "step": 58031 + }, + { + "epoch": 17.92, + "learning_rate": 5.60771515764208e-07, + "loss": 0.002, + "step": 58032 + }, + { + "epoch": 17.92, + "learning_rate": 5.606064054830318e-07, + "loss": 0.0019, + "step": 58033 + }, + { + "epoch": 17.92, + "learning_rate": 5.60441318811501e-07, + "loss": 0.0025, + "step": 58034 + }, + { + "epoch": 17.92, + "learning_rate": 5.602762557500252e-07, + "loss": 0.002, + "step": 58035 + }, + { + "epoch": 17.92, + "learning_rate": 5.601112162990219e-07, + "loss": 0.0021, + "step": 58036 + }, + { + "epoch": 17.92, + "learning_rate": 5.599462004589007e-07, + "loss": 0.0017, + "step": 58037 + }, + { + "epoch": 17.92, + "learning_rate": 5.59781208230078e-07, + "loss": 0.0016, + "step": 58038 + }, + { + "epoch": 17.92, + "learning_rate": 5.596162396129645e-07, + "loss": 0.0023, + "step": 58039 + }, + { + "epoch": 17.92, + "learning_rate": 5.594512946079711e-07, + "loss": 0.0022, + "step": 58040 + }, + { + "epoch": 17.92, + "learning_rate": 5.592863732155129e-07, + "loss": 0.0015, + "step": 58041 + }, + { + "epoch": 17.92, + "learning_rate": 5.591214754359997e-07, + "loss": 0.0015, + "step": 58042 + }, + { + "epoch": 17.92, + "learning_rate": 5.589566012698477e-07, + "loss": 0.0021, + "step": 58043 + }, + { + "epoch": 17.93, + "learning_rate": 5.587917507174667e-07, + "loss": 0.0018, + "step": 58044 + }, + { + "epoch": 17.93, + "learning_rate": 5.586269237792685e-07, + "loss": 0.0017, + "step": 58045 + }, + { + "epoch": 17.93, + "learning_rate": 5.584621204556662e-07, + "loss": 0.002, + "step": 58046 + }, + { + "epoch": 17.93, + "learning_rate": 5.582973407470727e-07, + "loss": 0.0022, + "step": 58047 + }, + { + "epoch": 17.93, + "learning_rate": 5.581325846538988e-07, + "loss": 0.0024, + "step": 58048 + }, + { + "epoch": 17.93, + "learning_rate": 5.579678521765597e-07, + "loss": 0.0018, + "step": 58049 + }, + { + "epoch": 17.93, + "learning_rate": 5.57803143315464e-07, + "loss": 0.0025, + "step": 58050 + }, + { + "epoch": 17.93, + "learning_rate": 5.576384580710236e-07, + "loss": 0.0011, + "step": 58051 + }, + { + "epoch": 17.93, + "learning_rate": 5.574737964436516e-07, + "loss": 0.0019, + "step": 58052 + }, + { + "epoch": 17.93, + "learning_rate": 5.57309158433762e-07, + "loss": 0.0022, + "step": 58053 + }, + { + "epoch": 17.93, + "learning_rate": 5.571445440417633e-07, + "loss": 0.0022, + "step": 58054 + }, + { + "epoch": 17.93, + "learning_rate": 5.569799532680675e-07, + "loss": 0.0022, + "step": 58055 + }, + { + "epoch": 17.93, + "learning_rate": 5.568153861130888e-07, + "loss": 0.0017, + "step": 58056 + }, + { + "epoch": 17.93, + "learning_rate": 5.566508425772355e-07, + "loss": 0.0017, + "step": 58057 + }, + { + "epoch": 17.93, + "learning_rate": 5.564863226609208e-07, + "loss": 0.0018, + "step": 58058 + }, + { + "epoch": 17.93, + "learning_rate": 5.563218263645575e-07, + "loss": 0.0022, + "step": 58059 + }, + { + "epoch": 17.93, + "learning_rate": 5.561573536885567e-07, + "loss": 0.0027, + "step": 58060 + }, + { + "epoch": 17.93, + "learning_rate": 5.559929046333256e-07, + "loss": 0.0019, + "step": 58061 + }, + { + "epoch": 17.93, + "learning_rate": 5.558284791992819e-07, + "loss": 0.0017, + "step": 58062 + }, + { + "epoch": 17.93, + "learning_rate": 5.556640773868316e-07, + "loss": 0.0021, + "step": 58063 + }, + { + "epoch": 17.93, + "learning_rate": 5.55499699196389e-07, + "loss": 0.0015, + "step": 58064 + }, + { + "epoch": 17.93, + "learning_rate": 5.553353446283649e-07, + "loss": 0.0022, + "step": 58065 + }, + { + "epoch": 17.93, + "learning_rate": 5.551710136831678e-07, + "loss": 0.0014, + "step": 58066 + }, + { + "epoch": 17.93, + "learning_rate": 5.550067063612096e-07, + "loss": 0.002, + "step": 58067 + }, + { + "epoch": 17.93, + "learning_rate": 5.548424226629057e-07, + "loss": 0.0022, + "step": 58068 + }, + { + "epoch": 17.93, + "learning_rate": 5.54678162588661e-07, + "loss": 0.0016, + "step": 58069 + }, + { + "epoch": 17.93, + "learning_rate": 5.54513926138891e-07, + "loss": 0.0019, + "step": 58070 + }, + { + "epoch": 17.93, + "learning_rate": 5.543497133140018e-07, + "loss": 0.0023, + "step": 58071 + }, + { + "epoch": 17.93, + "learning_rate": 5.54185524114409e-07, + "loss": 0.0022, + "step": 58072 + }, + { + "epoch": 17.93, + "learning_rate": 5.540213585405197e-07, + "loss": 0.0027, + "step": 58073 + }, + { + "epoch": 17.93, + "learning_rate": 5.538572165927469e-07, + "loss": 0.0022, + "step": 58074 + }, + { + "epoch": 17.93, + "learning_rate": 5.536930982715006e-07, + "loss": 0.0021, + "step": 58075 + }, + { + "epoch": 17.93, + "learning_rate": 5.535290035771889e-07, + "loss": 0.0022, + "step": 58076 + }, + { + "epoch": 17.94, + "learning_rate": 5.533649325102242e-07, + "loss": 0.0021, + "step": 58077 + }, + { + "epoch": 17.94, + "learning_rate": 5.53200885071018e-07, + "loss": 0.0021, + "step": 58078 + }, + { + "epoch": 17.94, + "learning_rate": 5.53036861259979e-07, + "loss": 0.0022, + "step": 58079 + }, + { + "epoch": 17.94, + "learning_rate": 5.528728610775181e-07, + "loss": 0.0011, + "step": 58080 + }, + { + "epoch": 17.94, + "learning_rate": 5.527088845240458e-07, + "loss": 0.0021, + "step": 58081 + }, + { + "epoch": 17.94, + "learning_rate": 5.525449315999698e-07, + "loss": 0.0024, + "step": 58082 + }, + { + "epoch": 17.94, + "learning_rate": 5.523810023057019e-07, + "loss": 0.0015, + "step": 58083 + }, + { + "epoch": 17.94, + "learning_rate": 5.52217096641654e-07, + "loss": 0.0022, + "step": 58084 + }, + { + "epoch": 17.94, + "learning_rate": 5.520532146082346e-07, + "loss": 0.0021, + "step": 58085 + }, + { + "epoch": 17.94, + "learning_rate": 5.518893562058513e-07, + "loss": 0.0022, + "step": 58086 + }, + { + "epoch": 17.94, + "learning_rate": 5.517255214349182e-07, + "loss": 0.0023, + "step": 58087 + }, + { + "epoch": 17.94, + "learning_rate": 5.515617102958404e-07, + "loss": 0.0015, + "step": 58088 + }, + { + "epoch": 17.94, + "learning_rate": 5.513979227890298e-07, + "loss": 0.0025, + "step": 58089 + }, + { + "epoch": 17.94, + "learning_rate": 5.512341589148995e-07, + "loss": 0.0019, + "step": 58090 + }, + { + "epoch": 17.94, + "learning_rate": 5.510704186738547e-07, + "loss": 0.0019, + "step": 58091 + }, + { + "epoch": 17.94, + "learning_rate": 5.50906702066305e-07, + "loss": 0.0024, + "step": 58092 + }, + { + "epoch": 17.94, + "learning_rate": 5.507430090926625e-07, + "loss": 0.0016, + "step": 58093 + }, + { + "epoch": 17.94, + "learning_rate": 5.505793397533332e-07, + "loss": 0.0017, + "step": 58094 + }, + { + "epoch": 17.94, + "learning_rate": 5.504156940487304e-07, + "loss": 0.0018, + "step": 58095 + }, + { + "epoch": 17.94, + "learning_rate": 5.502520719792614e-07, + "loss": 0.0027, + "step": 58096 + }, + { + "epoch": 17.94, + "learning_rate": 5.500884735453338e-07, + "loss": 0.0023, + "step": 58097 + }, + { + "epoch": 17.94, + "learning_rate": 5.499248987473583e-07, + "loss": 0.0017, + "step": 58098 + }, + { + "epoch": 17.94, + "learning_rate": 5.497613475857467e-07, + "loss": 0.0024, + "step": 58099 + }, + { + "epoch": 17.94, + "learning_rate": 5.495978200609031e-07, + "loss": 0.0015, + "step": 58100 + }, + { + "epoch": 17.94, + "learning_rate": 5.494343161732407e-07, + "loss": 0.002, + "step": 58101 + }, + { + "epoch": 17.94, + "learning_rate": 5.492708359231669e-07, + "loss": 0.0027, + "step": 58102 + }, + { + "epoch": 17.94, + "learning_rate": 5.49107379311089e-07, + "loss": 0.0019, + "step": 58103 + }, + { + "epoch": 17.94, + "learning_rate": 5.489439463374169e-07, + "loss": 0.002, + "step": 58104 + }, + { + "epoch": 17.94, + "learning_rate": 5.487805370025612e-07, + "loss": 0.002, + "step": 58105 + }, + { + "epoch": 17.94, + "learning_rate": 5.486171513069294e-07, + "loss": 0.0019, + "step": 58106 + }, + { + "epoch": 17.94, + "learning_rate": 5.48453789250929e-07, + "loss": 0.003, + "step": 58107 + }, + { + "epoch": 17.94, + "learning_rate": 5.482904508349696e-07, + "loss": 0.0019, + "step": 58108 + }, + { + "epoch": 17.95, + "learning_rate": 5.481271360594598e-07, + "loss": 0.0024, + "step": 58109 + }, + { + "epoch": 17.95, + "learning_rate": 5.479638449248082e-07, + "loss": 0.0016, + "step": 58110 + }, + { + "epoch": 17.95, + "learning_rate": 5.478005774314233e-07, + "loss": 0.002, + "step": 58111 + }, + { + "epoch": 17.95, + "learning_rate": 5.476373335797136e-07, + "loss": 0.0022, + "step": 58112 + }, + { + "epoch": 17.95, + "learning_rate": 5.474741133700845e-07, + "loss": 0.0012, + "step": 58113 + }, + { + "epoch": 17.95, + "learning_rate": 5.473109168029478e-07, + "loss": 0.0019, + "step": 58114 + }, + { + "epoch": 17.95, + "learning_rate": 5.471477438787109e-07, + "loss": 0.0024, + "step": 58115 + }, + { + "epoch": 17.95, + "learning_rate": 5.469845945977825e-07, + "loss": 0.0018, + "step": 58116 + }, + { + "epoch": 17.95, + "learning_rate": 5.468214689605689e-07, + "loss": 0.0017, + "step": 58117 + }, + { + "epoch": 17.95, + "learning_rate": 5.466583669674796e-07, + "loss": 0.0021, + "step": 58118 + }, + { + "epoch": 17.95, + "learning_rate": 5.464952886189201e-07, + "loss": 0.0016, + "step": 58119 + }, + { + "epoch": 17.95, + "learning_rate": 5.463322339153009e-07, + "loss": 0.0024, + "step": 58120 + }, + { + "epoch": 17.95, + "learning_rate": 5.461692028570309e-07, + "loss": 0.0019, + "step": 58121 + }, + { + "epoch": 17.95, + "learning_rate": 5.46006195444514e-07, + "loss": 0.0013, + "step": 58122 + }, + { + "epoch": 17.95, + "learning_rate": 5.458432116781597e-07, + "loss": 0.0014, + "step": 58123 + }, + { + "epoch": 17.95, + "learning_rate": 5.45680251558377e-07, + "loss": 0.0017, + "step": 58124 + }, + { + "epoch": 17.95, + "learning_rate": 5.455173150855708e-07, + "loss": 0.0015, + "step": 58125 + }, + { + "epoch": 17.95, + "learning_rate": 5.453544022601521e-07, + "loss": 0.0022, + "step": 58126 + }, + { + "epoch": 17.95, + "learning_rate": 5.45191513082527e-07, + "loss": 0.0019, + "step": 58127 + }, + { + "epoch": 17.95, + "learning_rate": 5.450286475530997e-07, + "loss": 0.0015, + "step": 58128 + }, + { + "epoch": 17.95, + "learning_rate": 5.448658056722811e-07, + "loss": 0.0018, + "step": 58129 + }, + { + "epoch": 17.95, + "learning_rate": 5.447029874404786e-07, + "loss": 0.001, + "step": 58130 + }, + { + "epoch": 17.95, + "learning_rate": 5.445401928580984e-07, + "loss": 0.0015, + "step": 58131 + }, + { + "epoch": 17.95, + "learning_rate": 5.44377421925546e-07, + "loss": 0.0016, + "step": 58132 + }, + { + "epoch": 17.95, + "learning_rate": 5.442146746432331e-07, + "loss": 0.0023, + "step": 58133 + }, + { + "epoch": 17.95, + "learning_rate": 5.440519510115616e-07, + "loss": 0.0019, + "step": 58134 + }, + { + "epoch": 17.95, + "learning_rate": 5.438892510309402e-07, + "loss": 0.0022, + "step": 58135 + }, + { + "epoch": 17.95, + "learning_rate": 5.437265747017784e-07, + "loss": 0.0017, + "step": 58136 + }, + { + "epoch": 17.95, + "learning_rate": 5.435639220244815e-07, + "loss": 0.0022, + "step": 58137 + }, + { + "epoch": 17.95, + "learning_rate": 5.434012929994548e-07, + "loss": 0.0019, + "step": 58138 + }, + { + "epoch": 17.95, + "learning_rate": 5.432386876271056e-07, + "loss": 0.0018, + "step": 58139 + }, + { + "epoch": 17.95, + "learning_rate": 5.430761059078427e-07, + "loss": 0.0025, + "step": 58140 + }, + { + "epoch": 17.95, + "learning_rate": 5.429135478420711e-07, + "loss": 0.0014, + "step": 58141 + }, + { + "epoch": 17.96, + "learning_rate": 5.427510134301972e-07, + "loss": 0.0016, + "step": 58142 + }, + { + "epoch": 17.96, + "learning_rate": 5.425885026726286e-07, + "loss": 0.0018, + "step": 58143 + }, + { + "epoch": 17.96, + "learning_rate": 5.424260155697691e-07, + "loss": 0.0021, + "step": 58144 + }, + { + "epoch": 17.96, + "learning_rate": 5.422635521220276e-07, + "loss": 0.002, + "step": 58145 + }, + { + "epoch": 17.96, + "learning_rate": 5.421011123298114e-07, + "loss": 0.0014, + "step": 58146 + }, + { + "epoch": 17.96, + "learning_rate": 5.419386961935258e-07, + "loss": 0.002, + "step": 58147 + }, + { + "epoch": 17.96, + "learning_rate": 5.417763037135748e-07, + "loss": 0.0024, + "step": 58148 + }, + { + "epoch": 17.96, + "learning_rate": 5.416139348903682e-07, + "loss": 0.0021, + "step": 58149 + }, + { + "epoch": 17.96, + "learning_rate": 5.414515897243078e-07, + "loss": 0.0022, + "step": 58150 + }, + { + "epoch": 17.96, + "learning_rate": 5.412892682158045e-07, + "loss": 0.0018, + "step": 58151 + }, + { + "epoch": 17.96, + "learning_rate": 5.41126970365261e-07, + "loss": 0.0021, + "step": 58152 + }, + { + "epoch": 17.96, + "learning_rate": 5.40964696173083e-07, + "loss": 0.0026, + "step": 58153 + }, + { + "epoch": 17.96, + "learning_rate": 5.408024456396776e-07, + "loss": 0.0024, + "step": 58154 + }, + { + "epoch": 17.96, + "learning_rate": 5.406402187654525e-07, + "loss": 0.0018, + "step": 58155 + }, + { + "epoch": 17.96, + "learning_rate": 5.404780155508094e-07, + "loss": 0.0018, + "step": 58156 + }, + { + "epoch": 17.96, + "learning_rate": 5.40315835996158e-07, + "loss": 0.0022, + "step": 58157 + }, + { + "epoch": 17.96, + "learning_rate": 5.401536801019014e-07, + "loss": 0.0014, + "step": 58158 + }, + { + "epoch": 17.96, + "learning_rate": 5.399915478684447e-07, + "loss": 0.0024, + "step": 58159 + }, + { + "epoch": 17.96, + "learning_rate": 5.398294392961945e-07, + "loss": 0.0019, + "step": 58160 + }, + { + "epoch": 17.96, + "learning_rate": 5.396673543855579e-07, + "loss": 0.0016, + "step": 58161 + }, + { + "epoch": 17.96, + "learning_rate": 5.395052931369382e-07, + "loss": 0.002, + "step": 58162 + }, + { + "epoch": 17.96, + "learning_rate": 5.393432555507406e-07, + "loss": 0.002, + "step": 58163 + }, + { + "epoch": 17.96, + "learning_rate": 5.391812416273723e-07, + "loss": 0.0019, + "step": 58164 + }, + { + "epoch": 17.96, + "learning_rate": 5.390192513672355e-07, + "loss": 0.0023, + "step": 58165 + }, + { + "epoch": 17.96, + "learning_rate": 5.388572847707374e-07, + "loss": 0.0022, + "step": 58166 + }, + { + "epoch": 17.96, + "learning_rate": 5.386953418382834e-07, + "loss": 0.0022, + "step": 58167 + }, + { + "epoch": 17.96, + "learning_rate": 5.385334225702787e-07, + "loss": 0.0014, + "step": 58168 + }, + { + "epoch": 17.96, + "learning_rate": 5.383715269671264e-07, + "loss": 0.0018, + "step": 58169 + }, + { + "epoch": 17.96, + "learning_rate": 5.382096550292327e-07, + "loss": 0.0012, + "step": 58170 + }, + { + "epoch": 17.96, + "learning_rate": 5.380478067570027e-07, + "loss": 0.0019, + "step": 58171 + }, + { + "epoch": 17.96, + "learning_rate": 5.37885982150842e-07, + "loss": 0.0018, + "step": 58172 + }, + { + "epoch": 17.96, + "learning_rate": 5.377241812111522e-07, + "loss": 0.0016, + "step": 58173 + }, + { + "epoch": 17.97, + "learning_rate": 5.37562403938342e-07, + "loss": 0.0019, + "step": 58174 + }, + { + "epoch": 17.97, + "learning_rate": 5.374006503328122e-07, + "loss": 0.0021, + "step": 58175 + }, + { + "epoch": 17.97, + "learning_rate": 5.372389203949702e-07, + "loss": 0.0012, + "step": 58176 + }, + { + "epoch": 17.97, + "learning_rate": 5.370772141252201e-07, + "loss": 0.0019, + "step": 58177 + }, + { + "epoch": 17.97, + "learning_rate": 5.36915531523966e-07, + "loss": 0.002, + "step": 58178 + }, + { + "epoch": 17.97, + "learning_rate": 5.367538725916099e-07, + "loss": 0.0021, + "step": 58179 + }, + { + "epoch": 17.97, + "learning_rate": 5.365922373285604e-07, + "loss": 0.0018, + "step": 58180 + }, + { + "epoch": 17.97, + "learning_rate": 5.364306257352181e-07, + "loss": 0.0017, + "step": 58181 + }, + { + "epoch": 17.97, + "learning_rate": 5.362690378119905e-07, + "loss": 0.0025, + "step": 58182 + }, + { + "epoch": 17.97, + "learning_rate": 5.361074735592809e-07, + "loss": 0.0017, + "step": 58183 + }, + { + "epoch": 17.97, + "learning_rate": 5.359459329774907e-07, + "loss": 0.002, + "step": 58184 + }, + { + "epoch": 17.97, + "learning_rate": 5.357844160670255e-07, + "loss": 0.0014, + "step": 58185 + }, + { + "epoch": 17.97, + "learning_rate": 5.356229228282906e-07, + "loss": 0.0019, + "step": 58186 + }, + { + "epoch": 17.97, + "learning_rate": 5.354614532616886e-07, + "loss": 0.002, + "step": 58187 + }, + { + "epoch": 17.97, + "learning_rate": 5.35300007367624e-07, + "loss": 0.0022, + "step": 58188 + }, + { + "epoch": 17.97, + "learning_rate": 5.351385851465018e-07, + "loss": 0.0016, + "step": 58189 + }, + { + "epoch": 17.97, + "learning_rate": 5.349771865987219e-07, + "loss": 0.0019, + "step": 58190 + }, + { + "epoch": 17.97, + "learning_rate": 5.348158117246904e-07, + "loss": 0.002, + "step": 58191 + }, + { + "epoch": 17.97, + "learning_rate": 5.346544605248127e-07, + "loss": 0.0017, + "step": 58192 + }, + { + "epoch": 17.97, + "learning_rate": 5.344931329994896e-07, + "loss": 0.0018, + "step": 58193 + }, + { + "epoch": 17.97, + "learning_rate": 5.343318291491251e-07, + "loss": 0.0019, + "step": 58194 + }, + { + "epoch": 17.97, + "learning_rate": 5.341705489741244e-07, + "loss": 0.002, + "step": 58195 + }, + { + "epoch": 17.97, + "learning_rate": 5.340092924748885e-07, + "loss": 0.0017, + "step": 58196 + }, + { + "epoch": 17.97, + "learning_rate": 5.338480596518214e-07, + "loss": 0.0013, + "step": 58197 + }, + { + "epoch": 17.97, + "learning_rate": 5.336868505053283e-07, + "loss": 0.0025, + "step": 58198 + }, + { + "epoch": 17.97, + "learning_rate": 5.335256650358112e-07, + "loss": 0.002, + "step": 58199 + }, + { + "epoch": 17.97, + "learning_rate": 5.333645032436708e-07, + "loss": 0.0021, + "step": 58200 + }, + { + "epoch": 17.97, + "learning_rate": 5.332033651293134e-07, + "loss": 0.0015, + "step": 58201 + }, + { + "epoch": 17.97, + "learning_rate": 5.33042250693141e-07, + "loss": 0.0029, + "step": 58202 + }, + { + "epoch": 17.97, + "learning_rate": 5.328811599355577e-07, + "loss": 0.0013, + "step": 58203 + }, + { + "epoch": 17.97, + "learning_rate": 5.327200928569642e-07, + "loss": 0.0026, + "step": 58204 + }, + { + "epoch": 17.97, + "learning_rate": 5.325590494577649e-07, + "loss": 0.0022, + "step": 58205 + }, + { + "epoch": 17.98, + "learning_rate": 5.323980297383613e-07, + "loss": 0.0024, + "step": 58206 + }, + { + "epoch": 17.98, + "learning_rate": 5.322370336991567e-07, + "loss": 0.002, + "step": 58207 + }, + { + "epoch": 17.98, + "learning_rate": 5.320760613405562e-07, + "loss": 0.002, + "step": 58208 + }, + { + "epoch": 17.98, + "learning_rate": 5.319151126629596e-07, + "loss": 0.002, + "step": 58209 + }, + { + "epoch": 17.98, + "learning_rate": 5.317541876667698e-07, + "loss": 0.0027, + "step": 58210 + }, + { + "epoch": 17.98, + "learning_rate": 5.315932863523899e-07, + "loss": 0.0019, + "step": 58211 + }, + { + "epoch": 17.98, + "learning_rate": 5.314324087202216e-07, + "loss": 0.002, + "step": 58212 + }, + { + "epoch": 17.98, + "learning_rate": 5.312715547706682e-07, + "loss": 0.0023, + "step": 58213 + }, + { + "epoch": 17.98, + "learning_rate": 5.311107245041324e-07, + "loss": 0.0014, + "step": 58214 + }, + { + "epoch": 17.98, + "learning_rate": 5.309499179210143e-07, + "loss": 0.0018, + "step": 58215 + }, + { + "epoch": 17.98, + "learning_rate": 5.307891350217175e-07, + "loss": 0.0019, + "step": 58216 + }, + { + "epoch": 17.98, + "learning_rate": 5.306283758066444e-07, + "loss": 0.0019, + "step": 58217 + }, + { + "epoch": 17.98, + "learning_rate": 5.304676402761966e-07, + "loss": 0.0022, + "step": 58218 + }, + { + "epoch": 17.98, + "learning_rate": 5.303069284307783e-07, + "loss": 0.0019, + "step": 58219 + }, + { + "epoch": 17.98, + "learning_rate": 5.30146240270788e-07, + "loss": 0.0017, + "step": 58220 + }, + { + "epoch": 17.98, + "learning_rate": 5.299855757966288e-07, + "loss": 0.0025, + "step": 58221 + }, + { + "epoch": 17.98, + "learning_rate": 5.298249350087025e-07, + "loss": 0.0015, + "step": 58222 + }, + { + "epoch": 17.98, + "learning_rate": 5.296643179074134e-07, + "loss": 0.0013, + "step": 58223 + }, + { + "epoch": 17.98, + "learning_rate": 5.2950372449316e-07, + "loss": 0.0016, + "step": 58224 + }, + { + "epoch": 17.98, + "learning_rate": 5.293431547663442e-07, + "loss": 0.0019, + "step": 58225 + }, + { + "epoch": 17.98, + "learning_rate": 5.291826087273699e-07, + "loss": 0.0021, + "step": 58226 + }, + { + "epoch": 17.98, + "learning_rate": 5.29022086376636e-07, + "loss": 0.002, + "step": 58227 + }, + { + "epoch": 17.98, + "learning_rate": 5.288615877145454e-07, + "loss": 0.0016, + "step": 58228 + }, + { + "epoch": 17.98, + "learning_rate": 5.287011127415021e-07, + "loss": 0.0029, + "step": 58229 + }, + { + "epoch": 17.98, + "learning_rate": 5.285406614579014e-07, + "loss": 0.0017, + "step": 58230 + }, + { + "epoch": 17.98, + "learning_rate": 5.283802338641486e-07, + "loss": 0.0026, + "step": 58231 + }, + { + "epoch": 17.98, + "learning_rate": 5.282198299606456e-07, + "loss": 0.0016, + "step": 58232 + }, + { + "epoch": 17.98, + "learning_rate": 5.280594497477909e-07, + "loss": 0.0021, + "step": 58233 + }, + { + "epoch": 17.98, + "learning_rate": 5.278990932259887e-07, + "loss": 0.0019, + "step": 58234 + }, + { + "epoch": 17.98, + "learning_rate": 5.277387603956363e-07, + "loss": 0.0027, + "step": 58235 + }, + { + "epoch": 17.98, + "learning_rate": 5.275784512571391e-07, + "loss": 0.0018, + "step": 58236 + }, + { + "epoch": 17.98, + "learning_rate": 5.274181658108946e-07, + "loss": 0.0028, + "step": 58237 + }, + { + "epoch": 17.98, + "learning_rate": 5.272579040573045e-07, + "loss": 0.0013, + "step": 58238 + }, + { + "epoch": 17.99, + "learning_rate": 5.27097665996773e-07, + "loss": 0.002, + "step": 58239 + }, + { + "epoch": 17.99, + "learning_rate": 5.269374516296954e-07, + "loss": 0.0016, + "step": 58240 + }, + { + "epoch": 17.99, + "learning_rate": 5.267772609564748e-07, + "loss": 0.0017, + "step": 58241 + }, + { + "epoch": 17.99, + "learning_rate": 5.266170939775128e-07, + "loss": 0.0018, + "step": 58242 + }, + { + "epoch": 17.99, + "learning_rate": 5.264569506932093e-07, + "loss": 0.0015, + "step": 58243 + }, + { + "epoch": 17.99, + "learning_rate": 5.262968311039651e-07, + "loss": 0.0025, + "step": 58244 + }, + { + "epoch": 17.99, + "learning_rate": 5.261367352101809e-07, + "loss": 0.0015, + "step": 58245 + }, + { + "epoch": 17.99, + "learning_rate": 5.259766630122554e-07, + "loss": 0.002, + "step": 58246 + }, + { + "epoch": 17.99, + "learning_rate": 5.258166145105903e-07, + "loss": 0.0016, + "step": 58247 + }, + { + "epoch": 17.99, + "learning_rate": 5.256565897055866e-07, + "loss": 0.0048, + "step": 58248 + }, + { + "epoch": 17.99, + "learning_rate": 5.254965885976426e-07, + "loss": 0.0015, + "step": 58249 + }, + { + "epoch": 17.99, + "learning_rate": 5.253366111871616e-07, + "loss": 0.002, + "step": 58250 + }, + { + "epoch": 17.99, + "learning_rate": 5.25176657474541e-07, + "loss": 0.0019, + "step": 58251 + }, + { + "epoch": 17.99, + "learning_rate": 5.250167274601803e-07, + "loss": 0.0018, + "step": 58252 + }, + { + "epoch": 17.99, + "learning_rate": 5.248568211444816e-07, + "loss": 0.0017, + "step": 58253 + }, + { + "epoch": 17.99, + "learning_rate": 5.246969385278456e-07, + "loss": 0.0026, + "step": 58254 + }, + { + "epoch": 17.99, + "learning_rate": 5.245370796106697e-07, + "loss": 0.002, + "step": 58255 + }, + { + "epoch": 17.99, + "learning_rate": 5.243772443933537e-07, + "loss": 0.0015, + "step": 58256 + }, + { + "epoch": 17.99, + "learning_rate": 5.242174328763006e-07, + "loss": 0.0021, + "step": 58257 + }, + { + "epoch": 17.99, + "learning_rate": 5.240576450599066e-07, + "loss": 0.0028, + "step": 58258 + }, + { + "epoch": 17.99, + "learning_rate": 5.238978809445717e-07, + "loss": 0.0017, + "step": 58259 + }, + { + "epoch": 17.99, + "learning_rate": 5.237381405307007e-07, + "loss": 0.0016, + "step": 58260 + }, + { + "epoch": 17.99, + "learning_rate": 5.235784238186847e-07, + "loss": 0.0017, + "step": 58261 + }, + { + "epoch": 17.99, + "learning_rate": 5.234187308089289e-07, + "loss": 0.0016, + "step": 58262 + }, + { + "epoch": 17.99, + "learning_rate": 5.232590615018318e-07, + "loss": 0.0017, + "step": 58263 + }, + { + "epoch": 17.99, + "learning_rate": 5.230994158977909e-07, + "loss": 0.002, + "step": 58264 + }, + { + "epoch": 17.99, + "learning_rate": 5.229397939972081e-07, + "loss": 0.0021, + "step": 58265 + }, + { + "epoch": 17.99, + "learning_rate": 5.227801958004796e-07, + "loss": 0.0017, + "step": 58266 + }, + { + "epoch": 17.99, + "learning_rate": 5.226206213080087e-07, + "loss": 0.0015, + "step": 58267 + }, + { + "epoch": 17.99, + "learning_rate": 5.224610705201905e-07, + "loss": 0.0018, + "step": 58268 + }, + { + "epoch": 17.99, + "learning_rate": 5.223015434374257e-07, + "loss": 0.0024, + "step": 58269 + }, + { + "epoch": 17.99, + "learning_rate": 5.221420400601162e-07, + "loss": 0.0023, + "step": 58270 + }, + { + "epoch": 18.0, + "learning_rate": 5.219825603886552e-07, + "loss": 0.0019, + "step": 58271 + }, + { + "epoch": 18.0, + "learning_rate": 5.218231044234446e-07, + "loss": 0.0019, + "step": 58272 + }, + { + "epoch": 18.0, + "learning_rate": 5.216636721648849e-07, + "loss": 0.0025, + "step": 58273 + }, + { + "epoch": 18.0, + "learning_rate": 5.215042636133716e-07, + "loss": 0.002, + "step": 58274 + }, + { + "epoch": 18.0, + "learning_rate": 5.213448787693054e-07, + "loss": 0.0018, + "step": 58275 + }, + { + "epoch": 18.0, + "learning_rate": 5.211855176330849e-07, + "loss": 0.0024, + "step": 58276 + }, + { + "epoch": 18.0, + "learning_rate": 5.210261802051075e-07, + "loss": 0.0024, + "step": 58277 + }, + { + "epoch": 18.0, + "learning_rate": 5.208668664857719e-07, + "loss": 0.0018, + "step": 58278 + }, + { + "epoch": 18.0, + "learning_rate": 5.207075764754788e-07, + "loss": 0.0018, + "step": 58279 + }, + { + "epoch": 18.0, + "learning_rate": 5.205483101746245e-07, + "loss": 0.0022, + "step": 58280 + }, + { + "epoch": 18.0, + "learning_rate": 5.203890675836065e-07, + "loss": 0.0023, + "step": 58281 + }, + { + "epoch": 18.0, + "learning_rate": 5.202298487028268e-07, + "loss": 0.0019, + "step": 58282 + }, + { + "epoch": 18.0, + "learning_rate": 5.200706535326782e-07, + "loss": 0.0017, + "step": 58283 + }, + { + "epoch": 18.0, + "learning_rate": 5.199114820735629e-07, + "loss": 0.0022, + "step": 58284 + }, + { + "epoch": 18.0, + "learning_rate": 5.197523343258793e-07, + "loss": 0.0022, + "step": 58285 + }, + { + "epoch": 18.0, + "learning_rate": 5.195932102900247e-07, + "loss": 0.0019, + "step": 58286 + }, + { + "epoch": 18.0, + "learning_rate": 5.194341099663946e-07, + "loss": 0.0015, + "step": 58287 + }, + { + "epoch": 18.0, + "learning_rate": 5.192750333553909e-07, + "loss": 0.0015, + "step": 58288 + }, + { + "epoch": 18.0, + "learning_rate": 5.191159804574075e-07, + "loss": 0.0015, + "step": 58289 + }, + { + "epoch": 18.0, + "learning_rate": 5.189569512728454e-07, + "loss": 0.0024, + "step": 58290 + }, + { + "epoch": 18.0, + "learning_rate": 5.18797945802102e-07, + "loss": 0.0014, + "step": 58291 + }, + { + "epoch": 18.0, + "learning_rate": 5.186389640455725e-07, + "loss": 0.0016, + "step": 58292 + }, + { + "epoch": 18.0, + "learning_rate": 5.184800060036565e-07, + "loss": 0.0017, + "step": 58293 + }, + { + "epoch": 18.0, + "learning_rate": 5.183210716767528e-07, + "loss": 0.002, + "step": 58294 + }, + { + "epoch": 18.0, + "learning_rate": 5.181621610652555e-07, + "loss": 0.0019, + "step": 58295 + }, + { + "epoch": 18.0, + "learning_rate": 5.180032741695651e-07, + "loss": 0.0015, + "step": 58296 + }, + { + "epoch": 18.0, + "learning_rate": 5.178444109900782e-07, + "loss": 0.002, + "step": 58297 + }, + { + "epoch": 18.0, + "learning_rate": 5.176855715271911e-07, + "loss": 0.0016, + "step": 58298 + }, + { + "epoch": 18.0, + "learning_rate": 5.175267557813013e-07, + "loss": 0.0013, + "step": 58299 + }, + { + "epoch": 18.0, + "learning_rate": 5.173679637528084e-07, + "loss": 0.0012, + "step": 58300 + }, + { + "epoch": 18.0, + "learning_rate": 5.172091954421077e-07, + "loss": 0.0011, + "step": 58301 + }, + { + "epoch": 18.0, + "learning_rate": 5.170504508495944e-07, + "loss": 0.0014, + "step": 58302 + }, + { + "epoch": 18.0, + "learning_rate": 5.168917299756682e-07, + "loss": 0.0018, + "step": 58303 + }, + { + "epoch": 18.01, + "learning_rate": 5.167330328207265e-07, + "loss": 0.0013, + "step": 58304 + }, + { + "epoch": 18.01, + "learning_rate": 5.165743593851636e-07, + "loss": 0.0022, + "step": 58305 + }, + { + "epoch": 18.01, + "learning_rate": 5.16415709669379e-07, + "loss": 0.0012, + "step": 58306 + }, + { + "epoch": 18.01, + "learning_rate": 5.162570836737691e-07, + "loss": 0.0014, + "step": 58307 + }, + { + "epoch": 18.01, + "learning_rate": 5.16098481398728e-07, + "loss": 0.0018, + "step": 58308 + }, + { + "epoch": 18.01, + "learning_rate": 5.159399028446544e-07, + "loss": 0.0016, + "step": 58309 + }, + { + "epoch": 18.01, + "learning_rate": 5.157813480119467e-07, + "loss": 0.0025, + "step": 58310 + }, + { + "epoch": 18.01, + "learning_rate": 5.156228169009992e-07, + "loss": 0.0019, + "step": 58311 + }, + { + "epoch": 18.01, + "learning_rate": 5.15464309512208e-07, + "loss": 0.0016, + "step": 58312 + }, + { + "epoch": 18.01, + "learning_rate": 5.153058258459709e-07, + "loss": 0.001, + "step": 58313 + }, + { + "epoch": 18.01, + "learning_rate": 5.151473659026829e-07, + "loss": 0.0014, + "step": 58314 + }, + { + "epoch": 18.01, + "learning_rate": 5.149889296827415e-07, + "loss": 0.0015, + "step": 58315 + }, + { + "epoch": 18.01, + "learning_rate": 5.148305171865442e-07, + "loss": 0.0015, + "step": 58316 + }, + { + "epoch": 18.01, + "learning_rate": 5.146721284144862e-07, + "loss": 0.002, + "step": 58317 + }, + { + "epoch": 18.01, + "learning_rate": 5.145137633669606e-07, + "loss": 0.0015, + "step": 58318 + }, + { + "epoch": 18.01, + "learning_rate": 5.143554220443681e-07, + "loss": 0.0013, + "step": 58319 + }, + { + "epoch": 18.01, + "learning_rate": 5.141971044471016e-07, + "loss": 0.0014, + "step": 58320 + }, + { + "epoch": 18.01, + "learning_rate": 5.140388105755601e-07, + "loss": 0.0017, + "step": 58321 + }, + { + "epoch": 18.01, + "learning_rate": 5.138805404301361e-07, + "loss": 0.0013, + "step": 58322 + }, + { + "epoch": 18.01, + "learning_rate": 5.137222940112275e-07, + "loss": 0.0013, + "step": 58323 + }, + { + "epoch": 18.01, + "learning_rate": 5.13564071319228e-07, + "loss": 0.0013, + "step": 58324 + }, + { + "epoch": 18.01, + "learning_rate": 5.134058723545377e-07, + "loss": 0.0016, + "step": 58325 + }, + { + "epoch": 18.01, + "learning_rate": 5.13247697117547e-07, + "loss": 0.0015, + "step": 58326 + }, + { + "epoch": 18.01, + "learning_rate": 5.130895456086559e-07, + "loss": 0.0015, + "step": 58327 + }, + { + "epoch": 18.01, + "learning_rate": 5.129314178282585e-07, + "loss": 0.0026, + "step": 58328 + }, + { + "epoch": 18.01, + "learning_rate": 5.127733137767488e-07, + "loss": 0.0016, + "step": 58329 + }, + { + "epoch": 18.01, + "learning_rate": 5.126152334545231e-07, + "loss": 0.0014, + "step": 58330 + }, + { + "epoch": 18.01, + "learning_rate": 5.124571768619779e-07, + "loss": 0.0015, + "step": 58331 + }, + { + "epoch": 18.01, + "learning_rate": 5.122991439995084e-07, + "loss": 0.0017, + "step": 58332 + }, + { + "epoch": 18.01, + "learning_rate": 5.121411348675076e-07, + "loss": 0.0015, + "step": 58333 + }, + { + "epoch": 18.01, + "learning_rate": 5.119831494663719e-07, + "loss": 0.0014, + "step": 58334 + }, + { + "epoch": 18.01, + "learning_rate": 5.118251877964985e-07, + "loss": 0.0011, + "step": 58335 + }, + { + "epoch": 18.02, + "learning_rate": 5.116672498582797e-07, + "loss": 0.0014, + "step": 58336 + }, + { + "epoch": 18.02, + "learning_rate": 5.115093356521129e-07, + "loss": 0.0011, + "step": 58337 + }, + { + "epoch": 18.02, + "learning_rate": 5.113514451783918e-07, + "loss": 0.0014, + "step": 58338 + }, + { + "epoch": 18.02, + "learning_rate": 5.1119357843751e-07, + "loss": 0.0014, + "step": 58339 + }, + { + "epoch": 18.02, + "learning_rate": 5.110357354298634e-07, + "loss": 0.0019, + "step": 58340 + }, + { + "epoch": 18.02, + "learning_rate": 5.108779161558497e-07, + "loss": 0.0014, + "step": 58341 + }, + { + "epoch": 18.02, + "learning_rate": 5.107201206158596e-07, + "loss": 0.0017, + "step": 58342 + }, + { + "epoch": 18.02, + "learning_rate": 5.105623488102885e-07, + "loss": 0.0014, + "step": 58343 + }, + { + "epoch": 18.02, + "learning_rate": 5.104046007395325e-07, + "loss": 0.0021, + "step": 58344 + }, + { + "epoch": 18.02, + "learning_rate": 5.102468764039847e-07, + "loss": 0.0018, + "step": 58345 + }, + { + "epoch": 18.02, + "learning_rate": 5.100891758040405e-07, + "loss": 0.0014, + "step": 58346 + }, + { + "epoch": 18.02, + "learning_rate": 5.09931498940095e-07, + "loss": 0.0016, + "step": 58347 + }, + { + "epoch": 18.02, + "learning_rate": 5.097738458125423e-07, + "loss": 0.0016, + "step": 58348 + }, + { + "epoch": 18.02, + "learning_rate": 5.096162164217733e-07, + "loss": 0.0011, + "step": 58349 + }, + { + "epoch": 18.02, + "learning_rate": 5.094586107681876e-07, + "loss": 0.0018, + "step": 58350 + }, + { + "epoch": 18.02, + "learning_rate": 5.09301028852176e-07, + "loss": 0.0018, + "step": 58351 + }, + { + "epoch": 18.02, + "learning_rate": 5.091434706741338e-07, + "loss": 0.0016, + "step": 58352 + }, + { + "epoch": 18.02, + "learning_rate": 5.089859362344552e-07, + "loss": 0.0013, + "step": 58353 + }, + { + "epoch": 18.02, + "learning_rate": 5.088284255335319e-07, + "loss": 0.0013, + "step": 58354 + }, + { + "epoch": 18.02, + "learning_rate": 5.086709385717603e-07, + "loss": 0.0012, + "step": 58355 + }, + { + "epoch": 18.02, + "learning_rate": 5.085134753495358e-07, + "loss": 0.0016, + "step": 58356 + }, + { + "epoch": 18.02, + "learning_rate": 5.083560358672479e-07, + "loss": 0.0017, + "step": 58357 + }, + { + "epoch": 18.02, + "learning_rate": 5.081986201252953e-07, + "loss": 0.0013, + "step": 58358 + }, + { + "epoch": 18.02, + "learning_rate": 5.080412281240677e-07, + "loss": 0.0012, + "step": 58359 + }, + { + "epoch": 18.02, + "learning_rate": 5.07883859863959e-07, + "loss": 0.0011, + "step": 58360 + }, + { + "epoch": 18.02, + "learning_rate": 5.077265153453647e-07, + "loss": 0.0015, + "step": 58361 + }, + { + "epoch": 18.02, + "learning_rate": 5.075691945686789e-07, + "loss": 0.001, + "step": 58362 + }, + { + "epoch": 18.02, + "learning_rate": 5.074118975342946e-07, + "loss": 0.0017, + "step": 58363 + }, + { + "epoch": 18.02, + "learning_rate": 5.072546242426013e-07, + "loss": 0.0011, + "step": 58364 + }, + { + "epoch": 18.02, + "learning_rate": 5.070973746939966e-07, + "loss": 0.0018, + "step": 58365 + }, + { + "epoch": 18.02, + "learning_rate": 5.069401488888748e-07, + "loss": 0.0016, + "step": 58366 + }, + { + "epoch": 18.02, + "learning_rate": 5.067829468276242e-07, + "loss": 0.0017, + "step": 58367 + }, + { + "epoch": 18.03, + "learning_rate": 5.066257685106435e-07, + "loss": 0.0014, + "step": 58368 + }, + { + "epoch": 18.03, + "learning_rate": 5.064686139383235e-07, + "loss": 0.0016, + "step": 58369 + }, + { + "epoch": 18.03, + "learning_rate": 5.06311483111055e-07, + "loss": 0.0018, + "step": 58370 + }, + { + "epoch": 18.03, + "learning_rate": 5.06154376029232e-07, + "loss": 0.0017, + "step": 58371 + }, + { + "epoch": 18.03, + "learning_rate": 5.059972926932511e-07, + "loss": 0.0017, + "step": 58372 + }, + { + "epoch": 18.03, + "learning_rate": 5.058402331035028e-07, + "loss": 0.0015, + "step": 58373 + }, + { + "epoch": 18.03, + "learning_rate": 5.056831972603771e-07, + "loss": 0.0016, + "step": 58374 + }, + { + "epoch": 18.03, + "learning_rate": 5.055261851642723e-07, + "loss": 0.0013, + "step": 58375 + }, + { + "epoch": 18.03, + "learning_rate": 5.053691968155761e-07, + "loss": 0.0013, + "step": 58376 + }, + { + "epoch": 18.03, + "learning_rate": 5.052122322146824e-07, + "loss": 0.0018, + "step": 58377 + }, + { + "epoch": 18.03, + "learning_rate": 5.050552913619888e-07, + "loss": 0.0017, + "step": 58378 + }, + { + "epoch": 18.03, + "learning_rate": 5.048983742578795e-07, + "loss": 0.0019, + "step": 58379 + }, + { + "epoch": 18.03, + "learning_rate": 5.047414809027529e-07, + "loss": 0.0014, + "step": 58380 + }, + { + "epoch": 18.03, + "learning_rate": 5.045846112969999e-07, + "loss": 0.0015, + "step": 58381 + }, + { + "epoch": 18.03, + "learning_rate": 5.044277654410112e-07, + "loss": 0.0014, + "step": 58382 + }, + { + "epoch": 18.03, + "learning_rate": 5.042709433351822e-07, + "loss": 0.001, + "step": 58383 + }, + { + "epoch": 18.03, + "learning_rate": 5.041141449799036e-07, + "loss": 0.0019, + "step": 58384 + }, + { + "epoch": 18.03, + "learning_rate": 5.039573703755663e-07, + "loss": 0.0012, + "step": 58385 + }, + { + "epoch": 18.03, + "learning_rate": 5.038006195225631e-07, + "loss": 0.0014, + "step": 58386 + }, + { + "epoch": 18.03, + "learning_rate": 5.036438924212883e-07, + "loss": 0.0022, + "step": 58387 + }, + { + "epoch": 18.03, + "learning_rate": 5.034871890721316e-07, + "loss": 0.0014, + "step": 58388 + }, + { + "epoch": 18.03, + "learning_rate": 5.033305094754847e-07, + "loss": 0.0015, + "step": 58389 + }, + { + "epoch": 18.03, + "learning_rate": 5.03173853631741e-07, + "loss": 0.0013, + "step": 58390 + }, + { + "epoch": 18.03, + "learning_rate": 5.03017221541291e-07, + "loss": 0.0018, + "step": 58391 + }, + { + "epoch": 18.03, + "learning_rate": 5.028606132045266e-07, + "loss": 0.0013, + "step": 58392 + }, + { + "epoch": 18.03, + "learning_rate": 5.02704028621841e-07, + "loss": 0.0014, + "step": 58393 + }, + { + "epoch": 18.03, + "learning_rate": 5.025474677936259e-07, + "loss": 0.0019, + "step": 58394 + }, + { + "epoch": 18.03, + "learning_rate": 5.023909307202701e-07, + "loss": 0.0016, + "step": 58395 + }, + { + "epoch": 18.03, + "learning_rate": 5.022344174021676e-07, + "loss": 0.0021, + "step": 58396 + }, + { + "epoch": 18.03, + "learning_rate": 5.020779278397081e-07, + "loss": 0.0015, + "step": 58397 + }, + { + "epoch": 18.03, + "learning_rate": 5.019214620332857e-07, + "loss": 0.0013, + "step": 58398 + }, + { + "epoch": 18.03, + "learning_rate": 5.01765019983288e-07, + "loss": 0.0013, + "step": 58399 + }, + { + "epoch": 18.03, + "learning_rate": 5.016086016901101e-07, + "loss": 0.0015, + "step": 58400 + }, + { + "epoch": 18.04, + "learning_rate": 5.014522071541394e-07, + "loss": 0.0018, + "step": 58401 + }, + { + "epoch": 18.04, + "learning_rate": 5.012958363757703e-07, + "loss": 0.0014, + "step": 58402 + }, + { + "epoch": 18.04, + "learning_rate": 5.011394893553934e-07, + "loss": 0.0016, + "step": 58403 + }, + { + "epoch": 18.04, + "learning_rate": 5.009831660933994e-07, + "loss": 0.0016, + "step": 58404 + }, + { + "epoch": 18.04, + "learning_rate": 5.008268665901783e-07, + "loss": 0.0015, + "step": 58405 + }, + { + "epoch": 18.04, + "learning_rate": 5.006705908461218e-07, + "loss": 0.0019, + "step": 58406 + }, + { + "epoch": 18.04, + "learning_rate": 5.005143388616207e-07, + "loss": 0.0018, + "step": 58407 + }, + { + "epoch": 18.04, + "learning_rate": 5.003581106370659e-07, + "loss": 0.0015, + "step": 58408 + }, + { + "epoch": 18.04, + "learning_rate": 5.002019061728492e-07, + "loss": 0.0021, + "step": 58409 + }, + { + "epoch": 18.04, + "learning_rate": 5.00045725469358e-07, + "loss": 0.0015, + "step": 58410 + }, + { + "epoch": 18.04, + "learning_rate": 4.998895685269856e-07, + "loss": 0.0015, + "step": 58411 + }, + { + "epoch": 18.04, + "learning_rate": 4.997334353461236e-07, + "loss": 0.002, + "step": 58412 + }, + { + "epoch": 18.04, + "learning_rate": 4.995773259271597e-07, + "loss": 0.0018, + "step": 58413 + }, + { + "epoch": 18.04, + "learning_rate": 4.994212402704867e-07, + "loss": 0.002, + "step": 58414 + }, + { + "epoch": 18.04, + "learning_rate": 4.992651783764935e-07, + "loss": 0.0017, + "step": 58415 + }, + { + "epoch": 18.04, + "learning_rate": 4.991091402455706e-07, + "loss": 0.0012, + "step": 58416 + }, + { + "epoch": 18.04, + "learning_rate": 4.989531258781077e-07, + "loss": 0.0018, + "step": 58417 + }, + { + "epoch": 18.04, + "learning_rate": 4.98797135274498e-07, + "loss": 0.0015, + "step": 58418 + }, + { + "epoch": 18.04, + "learning_rate": 4.986411684351289e-07, + "loss": 0.0011, + "step": 58419 + }, + { + "epoch": 18.04, + "learning_rate": 4.9848522536039e-07, + "loss": 0.0014, + "step": 58420 + }, + { + "epoch": 18.04, + "learning_rate": 4.983293060506744e-07, + "loss": 0.0017, + "step": 58421 + }, + { + "epoch": 18.04, + "learning_rate": 4.981734105063684e-07, + "loss": 0.0012, + "step": 58422 + }, + { + "epoch": 18.04, + "learning_rate": 4.980175387278641e-07, + "loss": 0.002, + "step": 58423 + }, + { + "epoch": 18.04, + "learning_rate": 4.978616907155509e-07, + "loss": 0.0023, + "step": 58424 + }, + { + "epoch": 18.04, + "learning_rate": 4.977058664698209e-07, + "loss": 0.0016, + "step": 58425 + }, + { + "epoch": 18.04, + "learning_rate": 4.975500659910581e-07, + "loss": 0.0012, + "step": 58426 + }, + { + "epoch": 18.04, + "learning_rate": 4.973942892796591e-07, + "loss": 0.0012, + "step": 58427 + }, + { + "epoch": 18.04, + "learning_rate": 4.972385363360077e-07, + "loss": 0.0014, + "step": 58428 + }, + { + "epoch": 18.04, + "learning_rate": 4.970828071604971e-07, + "loss": 0.0013, + "step": 58429 + }, + { + "epoch": 18.04, + "learning_rate": 4.969271017535149e-07, + "loss": 0.0018, + "step": 58430 + }, + { + "epoch": 18.04, + "learning_rate": 4.967714201154527e-07, + "loss": 0.0019, + "step": 58431 + }, + { + "epoch": 18.04, + "learning_rate": 4.966157622466961e-07, + "loss": 0.0019, + "step": 58432 + }, + { + "epoch": 18.05, + "learning_rate": 4.964601281476378e-07, + "loss": 0.0014, + "step": 58433 + }, + { + "epoch": 18.05, + "learning_rate": 4.963045178186665e-07, + "loss": 0.0012, + "step": 58434 + }, + { + "epoch": 18.05, + "learning_rate": 4.961489312601719e-07, + "loss": 0.0017, + "step": 58435 + }, + { + "epoch": 18.05, + "learning_rate": 4.959933684725404e-07, + "loss": 0.0019, + "step": 58436 + }, + { + "epoch": 18.05, + "learning_rate": 4.958378294561639e-07, + "loss": 0.0013, + "step": 58437 + }, + { + "epoch": 18.05, + "learning_rate": 4.956823142114298e-07, + "loss": 0.001, + "step": 58438 + }, + { + "epoch": 18.05, + "learning_rate": 4.955268227387288e-07, + "loss": 0.0038, + "step": 58439 + }, + { + "epoch": 18.05, + "learning_rate": 4.953713550384486e-07, + "loss": 0.0015, + "step": 58440 + }, + { + "epoch": 18.05, + "learning_rate": 4.952159111109766e-07, + "loss": 0.0017, + "step": 58441 + }, + { + "epoch": 18.05, + "learning_rate": 4.950604909567036e-07, + "loss": 0.0012, + "step": 58442 + }, + { + "epoch": 18.05, + "learning_rate": 4.949050945760192e-07, + "loss": 0.0011, + "step": 58443 + }, + { + "epoch": 18.05, + "learning_rate": 4.947497219693098e-07, + "loss": 0.0015, + "step": 58444 + }, + { + "epoch": 18.05, + "learning_rate": 4.945943731369662e-07, + "loss": 0.0014, + "step": 58445 + }, + { + "epoch": 18.05, + "learning_rate": 4.944390480793748e-07, + "loss": 0.0015, + "step": 58446 + }, + { + "epoch": 18.05, + "learning_rate": 4.942837467969252e-07, + "loss": 0.0014, + "step": 58447 + }, + { + "epoch": 18.05, + "learning_rate": 4.94128469290005e-07, + "loss": 0.0015, + "step": 58448 + }, + { + "epoch": 18.05, + "learning_rate": 4.939732155590038e-07, + "loss": 0.0016, + "step": 58449 + }, + { + "epoch": 18.05, + "learning_rate": 4.938179856043101e-07, + "loss": 0.0012, + "step": 58450 + }, + { + "epoch": 18.05, + "learning_rate": 4.936627794263104e-07, + "loss": 0.0014, + "step": 58451 + }, + { + "epoch": 18.05, + "learning_rate": 4.935075970253944e-07, + "loss": 0.0011, + "step": 58452 + }, + { + "epoch": 18.05, + "learning_rate": 4.933524384019495e-07, + "loss": 0.0018, + "step": 58453 + }, + { + "epoch": 18.05, + "learning_rate": 4.931973035563631e-07, + "loss": 0.0015, + "step": 58454 + }, + { + "epoch": 18.05, + "learning_rate": 4.93042192489026e-07, + "loss": 0.0016, + "step": 58455 + }, + { + "epoch": 18.05, + "learning_rate": 4.928871052003248e-07, + "loss": 0.0018, + "step": 58456 + }, + { + "epoch": 18.05, + "learning_rate": 4.927320416906444e-07, + "loss": 0.002, + "step": 58457 + }, + { + "epoch": 18.05, + "learning_rate": 4.92577001960377e-07, + "loss": 0.0017, + "step": 58458 + }, + { + "epoch": 18.05, + "learning_rate": 4.924219860099077e-07, + "loss": 0.0019, + "step": 58459 + }, + { + "epoch": 18.05, + "learning_rate": 4.922669938396263e-07, + "loss": 0.0018, + "step": 58460 + }, + { + "epoch": 18.05, + "learning_rate": 4.921120254499189e-07, + "loss": 0.0016, + "step": 58461 + }, + { + "epoch": 18.05, + "learning_rate": 4.919570808411722e-07, + "loss": 0.0014, + "step": 58462 + }, + { + "epoch": 18.05, + "learning_rate": 4.918021600137757e-07, + "loss": 0.0019, + "step": 58463 + }, + { + "epoch": 18.05, + "learning_rate": 4.916472629681157e-07, + "loss": 0.0017, + "step": 58464 + }, + { + "epoch": 18.06, + "learning_rate": 4.91492389704581e-07, + "loss": 0.0017, + "step": 58465 + }, + { + "epoch": 18.06, + "learning_rate": 4.913375402235588e-07, + "loss": 0.0015, + "step": 58466 + }, + { + "epoch": 18.06, + "learning_rate": 4.911827145254333e-07, + "loss": 0.0015, + "step": 58467 + }, + { + "epoch": 18.06, + "learning_rate": 4.910279126105966e-07, + "loss": 0.0021, + "step": 58468 + }, + { + "epoch": 18.06, + "learning_rate": 4.908731344794315e-07, + "loss": 0.0015, + "step": 58469 + }, + { + "epoch": 18.06, + "learning_rate": 4.90718380132329e-07, + "loss": 0.0013, + "step": 58470 + }, + { + "epoch": 18.06, + "learning_rate": 4.90563649569673e-07, + "loss": 0.0017, + "step": 58471 + }, + { + "epoch": 18.06, + "learning_rate": 4.904089427918512e-07, + "loss": 0.0017, + "step": 58472 + }, + { + "epoch": 18.06, + "learning_rate": 4.902542597992511e-07, + "loss": 0.0014, + "step": 58473 + }, + { + "epoch": 18.06, + "learning_rate": 4.900996005922609e-07, + "loss": 0.0013, + "step": 58474 + }, + { + "epoch": 18.06, + "learning_rate": 4.89944965171264e-07, + "loss": 0.0015, + "step": 58475 + }, + { + "epoch": 18.06, + "learning_rate": 4.897903535366521e-07, + "loss": 0.0021, + "step": 58476 + }, + { + "epoch": 18.06, + "learning_rate": 4.896357656888074e-07, + "loss": 0.0013, + "step": 58477 + }, + { + "epoch": 18.06, + "learning_rate": 4.89481201628118e-07, + "loss": 0.0015, + "step": 58478 + }, + { + "epoch": 18.06, + "learning_rate": 4.893266613549707e-07, + "loss": 0.0015, + "step": 58479 + }, + { + "epoch": 18.06, + "learning_rate": 4.891721448697529e-07, + "loss": 0.0016, + "step": 58480 + }, + { + "epoch": 18.06, + "learning_rate": 4.890176521728507e-07, + "loss": 0.0016, + "step": 58481 + }, + { + "epoch": 18.06, + "learning_rate": 4.888631832646484e-07, + "loss": 0.0016, + "step": 58482 + }, + { + "epoch": 18.06, + "learning_rate": 4.887087381455357e-07, + "loss": 0.0008, + "step": 58483 + }, + { + "epoch": 18.06, + "learning_rate": 4.885543168158958e-07, + "loss": 0.0017, + "step": 58484 + }, + { + "epoch": 18.06, + "learning_rate": 4.883999192761158e-07, + "loss": 0.0017, + "step": 58485 + }, + { + "epoch": 18.06, + "learning_rate": 4.882455455265855e-07, + "loss": 0.0015, + "step": 58486 + }, + { + "epoch": 18.06, + "learning_rate": 4.880911955676848e-07, + "loss": 0.0016, + "step": 58487 + }, + { + "epoch": 18.06, + "learning_rate": 4.879368693998032e-07, + "loss": 0.0019, + "step": 58488 + }, + { + "epoch": 18.06, + "learning_rate": 4.877825670233282e-07, + "loss": 0.0013, + "step": 58489 + }, + { + "epoch": 18.06, + "learning_rate": 4.876282884386419e-07, + "loss": 0.0015, + "step": 58490 + }, + { + "epoch": 18.06, + "learning_rate": 4.874740336461337e-07, + "loss": 0.0014, + "step": 58491 + }, + { + "epoch": 18.06, + "learning_rate": 4.873198026461878e-07, + "loss": 0.0019, + "step": 58492 + }, + { + "epoch": 18.06, + "learning_rate": 4.871655954391896e-07, + "loss": 0.0015, + "step": 58493 + }, + { + "epoch": 18.06, + "learning_rate": 4.870114120255242e-07, + "loss": 0.0015, + "step": 58494 + }, + { + "epoch": 18.06, + "learning_rate": 4.868572524055781e-07, + "loss": 0.0015, + "step": 58495 + }, + { + "epoch": 18.06, + "learning_rate": 4.867031165797409e-07, + "loss": 0.0013, + "step": 58496 + }, + { + "epoch": 18.06, + "learning_rate": 4.865490045483912e-07, + "loss": 0.0015, + "step": 58497 + }, + { + "epoch": 18.07, + "learning_rate": 4.863949163119174e-07, + "loss": 0.0015, + "step": 58498 + }, + { + "epoch": 18.07, + "learning_rate": 4.862408518707062e-07, + "loss": 0.0025, + "step": 58499 + }, + { + "epoch": 18.07, + "learning_rate": 4.860868112251416e-07, + "loss": 0.0016, + "step": 58500 + }, + { + "epoch": 18.07, + "learning_rate": 4.859327943756098e-07, + "loss": 0.0014, + "step": 58501 + }, + { + "epoch": 18.07, + "learning_rate": 4.857788013224951e-07, + "loss": 0.0019, + "step": 58502 + }, + { + "epoch": 18.07, + "learning_rate": 4.856248320661816e-07, + "loss": 0.0018, + "step": 58503 + }, + { + "epoch": 18.07, + "learning_rate": 4.854708866070557e-07, + "loss": 0.0017, + "step": 58504 + }, + { + "epoch": 18.07, + "learning_rate": 4.853169649455037e-07, + "loss": 0.0016, + "step": 58505 + }, + { + "epoch": 18.07, + "learning_rate": 4.851630670819085e-07, + "loss": 0.0016, + "step": 58506 + }, + { + "epoch": 18.07, + "learning_rate": 4.850091930166567e-07, + "loss": 0.0017, + "step": 58507 + }, + { + "epoch": 18.07, + "learning_rate": 4.848553427501324e-07, + "loss": 0.0015, + "step": 58508 + }, + { + "epoch": 18.07, + "learning_rate": 4.847015162827196e-07, + "loss": 0.0015, + "step": 58509 + }, + { + "epoch": 18.07, + "learning_rate": 4.845477136148036e-07, + "loss": 0.0015, + "step": 58510 + }, + { + "epoch": 18.07, + "learning_rate": 4.843939347467696e-07, + "loss": 0.0017, + "step": 58511 + }, + { + "epoch": 18.07, + "learning_rate": 4.84240179679003e-07, + "loss": 0.0012, + "step": 58512 + }, + { + "epoch": 18.07, + "learning_rate": 4.840864484118857e-07, + "loss": 0.0018, + "step": 58513 + }, + { + "epoch": 18.07, + "learning_rate": 4.83932740945805e-07, + "loss": 0.0014, + "step": 58514 + }, + { + "epoch": 18.07, + "learning_rate": 4.837790572811429e-07, + "loss": 0.0022, + "step": 58515 + }, + { + "epoch": 18.07, + "learning_rate": 4.836253974182847e-07, + "loss": 0.0015, + "step": 58516 + }, + { + "epoch": 18.07, + "learning_rate": 4.83471761357619e-07, + "loss": 0.0014, + "step": 58517 + }, + { + "epoch": 18.07, + "learning_rate": 4.83318149099522e-07, + "loss": 0.0013, + "step": 58518 + }, + { + "epoch": 18.07, + "learning_rate": 4.831645606443824e-07, + "loss": 0.0018, + "step": 58519 + }, + { + "epoch": 18.07, + "learning_rate": 4.830109959925855e-07, + "loss": 0.0014, + "step": 58520 + }, + { + "epoch": 18.07, + "learning_rate": 4.82857455144512e-07, + "loss": 0.0022, + "step": 58521 + }, + { + "epoch": 18.07, + "learning_rate": 4.827039381005505e-07, + "loss": 0.0016, + "step": 58522 + }, + { + "epoch": 18.07, + "learning_rate": 4.825504448610807e-07, + "loss": 0.0015, + "step": 58523 + }, + { + "epoch": 18.07, + "learning_rate": 4.823969754264879e-07, + "loss": 0.0014, + "step": 58524 + }, + { + "epoch": 18.07, + "learning_rate": 4.822435297971562e-07, + "loss": 0.001, + "step": 58525 + }, + { + "epoch": 18.07, + "learning_rate": 4.820901079734697e-07, + "loss": 0.0016, + "step": 58526 + }, + { + "epoch": 18.07, + "learning_rate": 4.819367099558126e-07, + "loss": 0.0016, + "step": 58527 + }, + { + "epoch": 18.07, + "learning_rate": 4.817833357445656e-07, + "loss": 0.0015, + "step": 58528 + }, + { + "epoch": 18.07, + "learning_rate": 4.816299853401152e-07, + "loss": 0.0017, + "step": 58529 + }, + { + "epoch": 18.08, + "learning_rate": 4.814766587428455e-07, + "loss": 0.0013, + "step": 58530 + }, + { + "epoch": 18.08, + "learning_rate": 4.813233559531383e-07, + "loss": 0.0019, + "step": 58531 + }, + { + "epoch": 18.08, + "learning_rate": 4.811700769713778e-07, + "loss": 0.0022, + "step": 58532 + }, + { + "epoch": 18.08, + "learning_rate": 4.810168217979471e-07, + "loss": 0.0017, + "step": 58533 + }, + { + "epoch": 18.08, + "learning_rate": 4.808635904332282e-07, + "loss": 0.0013, + "step": 58534 + }, + { + "epoch": 18.08, + "learning_rate": 4.80710382877606e-07, + "loss": 0.0016, + "step": 58535 + }, + { + "epoch": 18.08, + "learning_rate": 4.805571991314639e-07, + "loss": 0.0013, + "step": 58536 + }, + { + "epoch": 18.08, + "learning_rate": 4.804040391951848e-07, + "loss": 0.0013, + "step": 58537 + }, + { + "epoch": 18.08, + "learning_rate": 4.802509030691505e-07, + "loss": 0.0012, + "step": 58538 + }, + { + "epoch": 18.08, + "learning_rate": 4.800977907537463e-07, + "loss": 0.0013, + "step": 58539 + }, + { + "epoch": 18.08, + "learning_rate": 4.79944702249352e-07, + "loss": 0.0011, + "step": 58540 + }, + { + "epoch": 18.08, + "learning_rate": 4.797916375563527e-07, + "loss": 0.0014, + "step": 58541 + }, + { + "epoch": 18.08, + "learning_rate": 4.796385966751327e-07, + "loss": 0.0014, + "step": 58542 + }, + { + "epoch": 18.08, + "learning_rate": 4.794855796060716e-07, + "loss": 0.0017, + "step": 58543 + }, + { + "epoch": 18.08, + "learning_rate": 4.793325863495535e-07, + "loss": 0.0014, + "step": 58544 + }, + { + "epoch": 18.08, + "learning_rate": 4.791796169059615e-07, + "loss": 0.0015, + "step": 58545 + }, + { + "epoch": 18.08, + "learning_rate": 4.790266712756775e-07, + "loss": 0.0028, + "step": 58546 + }, + { + "epoch": 18.08, + "learning_rate": 4.788737494590845e-07, + "loss": 0.0016, + "step": 58547 + }, + { + "epoch": 18.08, + "learning_rate": 4.787208514565656e-07, + "loss": 0.0016, + "step": 58548 + }, + { + "epoch": 18.08, + "learning_rate": 4.785679772685004e-07, + "loss": 0.0014, + "step": 58549 + }, + { + "epoch": 18.08, + "learning_rate": 4.784151268952741e-07, + "loss": 0.0017, + "step": 58550 + }, + { + "epoch": 18.08, + "learning_rate": 4.782623003372688e-07, + "loss": 0.0021, + "step": 58551 + }, + { + "epoch": 18.08, + "learning_rate": 4.781094975948653e-07, + "loss": 0.0017, + "step": 58552 + }, + { + "epoch": 18.08, + "learning_rate": 4.779567186684475e-07, + "loss": 0.0013, + "step": 58553 + }, + { + "epoch": 18.08, + "learning_rate": 4.778039635583976e-07, + "loss": 0.0015, + "step": 58554 + }, + { + "epoch": 18.08, + "learning_rate": 4.776512322650939e-07, + "loss": 0.0013, + "step": 58555 + }, + { + "epoch": 18.08, + "learning_rate": 4.77498524788923e-07, + "loss": 0.0015, + "step": 58556 + }, + { + "epoch": 18.08, + "learning_rate": 4.773458411302645e-07, + "loss": 0.0014, + "step": 58557 + }, + { + "epoch": 18.08, + "learning_rate": 4.771931812895025e-07, + "loss": 0.0012, + "step": 58558 + }, + { + "epoch": 18.08, + "learning_rate": 4.770405452670146e-07, + "loss": 0.0011, + "step": 58559 + }, + { + "epoch": 18.08, + "learning_rate": 4.768879330631881e-07, + "loss": 0.002, + "step": 58560 + }, + { + "epoch": 18.08, + "learning_rate": 4.7673534467839956e-07, + "loss": 0.0017, + "step": 58561 + }, + { + "epoch": 18.08, + "learning_rate": 4.765827801130318e-07, + "loss": 0.0016, + "step": 58562 + }, + { + "epoch": 18.09, + "learning_rate": 4.764302393674702e-07, + "loss": 0.0015, + "step": 58563 + }, + { + "epoch": 18.09, + "learning_rate": 4.7627772244209336e-07, + "loss": 0.0014, + "step": 58564 + }, + { + "epoch": 18.09, + "learning_rate": 4.761252293372809e-07, + "loss": 0.0014, + "step": 58565 + }, + { + "epoch": 18.09, + "learning_rate": 4.7597276005341697e-07, + "loss": 0.001, + "step": 58566 + }, + { + "epoch": 18.09, + "learning_rate": 4.758203145908835e-07, + "loss": 0.0013, + "step": 58567 + }, + { + "epoch": 18.09, + "learning_rate": 4.756678929500602e-07, + "loss": 0.0014, + "step": 58568 + }, + { + "epoch": 18.09, + "learning_rate": 4.755154951313279e-07, + "loss": 0.002, + "step": 58569 + }, + { + "epoch": 18.09, + "learning_rate": 4.7536312113506955e-07, + "loss": 0.0011, + "step": 58570 + }, + { + "epoch": 18.09, + "learning_rate": 4.752107709616638e-07, + "loss": 0.0023, + "step": 58571 + }, + { + "epoch": 18.09, + "learning_rate": 4.7505844461149367e-07, + "loss": 0.0012, + "step": 58572 + }, + { + "epoch": 18.09, + "learning_rate": 4.749061420849399e-07, + "loss": 0.0016, + "step": 58573 + }, + { + "epoch": 18.09, + "learning_rate": 4.7475386338238336e-07, + "loss": 0.0019, + "step": 58574 + }, + { + "epoch": 18.09, + "learning_rate": 4.7460160850420376e-07, + "loss": 0.0011, + "step": 58575 + }, + { + "epoch": 18.09, + "learning_rate": 4.7444937745078414e-07, + "loss": 0.0016, + "step": 58576 + }, + { + "epoch": 18.09, + "learning_rate": 4.7429717022250297e-07, + "loss": 0.0015, + "step": 58577 + }, + { + "epoch": 18.09, + "learning_rate": 4.741449868197423e-07, + "loss": 0.0014, + "step": 58578 + }, + { + "epoch": 18.09, + "learning_rate": 4.7399282724288395e-07, + "loss": 0.0014, + "step": 58579 + }, + { + "epoch": 18.09, + "learning_rate": 4.7384069149230437e-07, + "loss": 0.0012, + "step": 58580 + }, + { + "epoch": 18.09, + "learning_rate": 4.7368857956838657e-07, + "loss": 0.0014, + "step": 58581 + }, + { + "epoch": 18.09, + "learning_rate": 4.7353649147151346e-07, + "loss": 0.0019, + "step": 58582 + }, + { + "epoch": 18.09, + "learning_rate": 4.7338442720206155e-07, + "loss": 0.0013, + "step": 58583 + }, + { + "epoch": 18.09, + "learning_rate": 4.732323867604138e-07, + "loss": 0.0013, + "step": 58584 + }, + { + "epoch": 18.09, + "learning_rate": 4.7308037014694885e-07, + "loss": 0.0017, + "step": 58585 + }, + { + "epoch": 18.09, + "learning_rate": 4.729283773620463e-07, + "loss": 0.0019, + "step": 58586 + }, + { + "epoch": 18.09, + "learning_rate": 4.7277640840608816e-07, + "loss": 0.0011, + "step": 58587 + }, + { + "epoch": 18.09, + "learning_rate": 4.726244632794552e-07, + "loss": 0.0015, + "step": 58588 + }, + { + "epoch": 18.09, + "learning_rate": 4.7247254198252603e-07, + "loss": 0.0016, + "step": 58589 + }, + { + "epoch": 18.09, + "learning_rate": 4.7232064451567915e-07, + "loss": 0.0012, + "step": 58590 + }, + { + "epoch": 18.09, + "learning_rate": 4.721687708792977e-07, + "loss": 0.0016, + "step": 58591 + }, + { + "epoch": 18.09, + "learning_rate": 4.7201692107375795e-07, + "loss": 0.0017, + "step": 58592 + }, + { + "epoch": 18.09, + "learning_rate": 4.71865095099443e-07, + "loss": 0.0014, + "step": 58593 + }, + { + "epoch": 18.09, + "learning_rate": 4.717132929567314e-07, + "loss": 0.0015, + "step": 58594 + }, + { + "epoch": 18.1, + "learning_rate": 4.7156151464600287e-07, + "loss": 0.0016, + "step": 58595 + }, + { + "epoch": 18.1, + "learning_rate": 4.7140976016763596e-07, + "loss": 0.0016, + "step": 58596 + }, + { + "epoch": 18.1, + "learning_rate": 4.7125802952201036e-07, + "loss": 0.0012, + "step": 58597 + }, + { + "epoch": 18.1, + "learning_rate": 4.711063227095092e-07, + "loss": 0.0015, + "step": 58598 + }, + { + "epoch": 18.1, + "learning_rate": 4.709546397305076e-07, + "loss": 0.0012, + "step": 58599 + }, + { + "epoch": 18.1, + "learning_rate": 4.7080298058538533e-07, + "loss": 0.0016, + "step": 58600 + }, + { + "epoch": 18.1, + "learning_rate": 4.706513452745254e-07, + "loss": 0.0017, + "step": 58601 + }, + { + "epoch": 18.1, + "learning_rate": 4.7049973379830195e-07, + "loss": 0.0013, + "step": 58602 + }, + { + "epoch": 18.1, + "learning_rate": 4.703481461570969e-07, + "loss": 0.0014, + "step": 58603 + }, + { + "epoch": 18.1, + "learning_rate": 4.701965823512911e-07, + "loss": 0.0022, + "step": 58604 + }, + { + "epoch": 18.1, + "learning_rate": 4.700450423812608e-07, + "loss": 0.0016, + "step": 58605 + }, + { + "epoch": 18.1, + "learning_rate": 4.6989352624738583e-07, + "loss": 0.0013, + "step": 58606 + }, + { + "epoch": 18.1, + "learning_rate": 4.697420339500458e-07, + "loss": 0.0019, + "step": 58607 + }, + { + "epoch": 18.1, + "learning_rate": 4.6959056548961823e-07, + "loss": 0.0017, + "step": 58608 + }, + { + "epoch": 18.1, + "learning_rate": 4.6943912086648393e-07, + "loss": 0.0013, + "step": 58609 + }, + { + "epoch": 18.1, + "learning_rate": 4.692877000810203e-07, + "loss": 0.0015, + "step": 58610 + }, + { + "epoch": 18.1, + "learning_rate": 4.69136303133606e-07, + "loss": 0.0012, + "step": 58611 + }, + { + "epoch": 18.1, + "learning_rate": 4.6898493002461965e-07, + "loss": 0.0018, + "step": 58612 + }, + { + "epoch": 18.1, + "learning_rate": 4.68833580754442e-07, + "loss": 0.0011, + "step": 58613 + }, + { + "epoch": 18.1, + "learning_rate": 4.686822553234482e-07, + "loss": 0.0019, + "step": 58614 + }, + { + "epoch": 18.1, + "learning_rate": 4.685309537320204e-07, + "loss": 0.0016, + "step": 58615 + }, + { + "epoch": 18.1, + "learning_rate": 4.683796759805348e-07, + "loss": 0.0018, + "step": 58616 + }, + { + "epoch": 18.1, + "learning_rate": 4.682284220693689e-07, + "loss": 0.0014, + "step": 58617 + }, + { + "epoch": 18.1, + "learning_rate": 4.680771919989013e-07, + "loss": 0.0014, + "step": 58618 + }, + { + "epoch": 18.1, + "learning_rate": 4.679259857695129e-07, + "loss": 0.0008, + "step": 58619 + }, + { + "epoch": 18.1, + "learning_rate": 4.67774803381581e-07, + "loss": 0.0011, + "step": 58620 + }, + { + "epoch": 18.1, + "learning_rate": 4.6762364483548094e-07, + "loss": 0.0022, + "step": 58621 + }, + { + "epoch": 18.1, + "learning_rate": 4.6747251013159355e-07, + "loss": 0.0015, + "step": 58622 + }, + { + "epoch": 18.1, + "learning_rate": 4.6732139927029517e-07, + "loss": 0.0013, + "step": 58623 + }, + { + "epoch": 18.1, + "learning_rate": 4.671703122519655e-07, + "loss": 0.0016, + "step": 58624 + }, + { + "epoch": 18.1, + "learning_rate": 4.6701924907698316e-07, + "loss": 0.0013, + "step": 58625 + }, + { + "epoch": 18.1, + "learning_rate": 4.668682097457222e-07, + "loss": 0.0014, + "step": 58626 + }, + { + "epoch": 18.11, + "learning_rate": 4.6671719425856244e-07, + "loss": 0.0014, + "step": 58627 + }, + { + "epoch": 18.11, + "learning_rate": 4.6656620261588127e-07, + "loss": 0.0019, + "step": 58628 + }, + { + "epoch": 18.11, + "learning_rate": 4.6641523481805837e-07, + "loss": 0.0017, + "step": 58629 + }, + { + "epoch": 18.11, + "learning_rate": 4.662642908654702e-07, + "loss": 0.0014, + "step": 58630 + }, + { + "epoch": 18.11, + "learning_rate": 4.6611337075849194e-07, + "loss": 0.0014, + "step": 58631 + }, + { + "epoch": 18.11, + "learning_rate": 4.6596247449750554e-07, + "loss": 0.002, + "step": 58632 + }, + { + "epoch": 18.11, + "learning_rate": 4.6581160208288403e-07, + "loss": 0.0018, + "step": 58633 + }, + { + "epoch": 18.11, + "learning_rate": 4.6566075351500597e-07, + "loss": 0.0017, + "step": 58634 + }, + { + "epoch": 18.11, + "learning_rate": 4.6550992879425215e-07, + "loss": 0.0014, + "step": 58635 + }, + { + "epoch": 18.11, + "learning_rate": 4.653591279209946e-07, + "loss": 0.0021, + "step": 58636 + }, + { + "epoch": 18.11, + "learning_rate": 4.652083508956129e-07, + "loss": 0.0015, + "step": 58637 + }, + { + "epoch": 18.11, + "learning_rate": 4.6505759771848567e-07, + "loss": 0.0013, + "step": 58638 + }, + { + "epoch": 18.11, + "learning_rate": 4.64906868389986e-07, + "loss": 0.0013, + "step": 58639 + }, + { + "epoch": 18.11, + "learning_rate": 4.6475616291049577e-07, + "loss": 0.0014, + "step": 58640 + }, + { + "epoch": 18.11, + "learning_rate": 4.646054812803891e-07, + "loss": 0.0019, + "step": 58641 + }, + { + "epoch": 18.11, + "learning_rate": 4.6445482350004233e-07, + "loss": 0.0019, + "step": 58642 + }, + { + "epoch": 18.11, + "learning_rate": 4.6430418956983305e-07, + "loss": 0.0015, + "step": 58643 + }, + { + "epoch": 18.11, + "learning_rate": 4.6415357949013974e-07, + "loss": 0.0015, + "step": 58644 + }, + { + "epoch": 18.11, + "learning_rate": 4.640029932613366e-07, + "loss": 0.0012, + "step": 58645 + }, + { + "epoch": 18.11, + "learning_rate": 4.6385243088380105e-07, + "loss": 0.0014, + "step": 58646 + }, + { + "epoch": 18.11, + "learning_rate": 4.6370189235791063e-07, + "loss": 0.0014, + "step": 58647 + }, + { + "epoch": 18.11, + "learning_rate": 4.6355137768403947e-07, + "loss": 0.0016, + "step": 58648 + }, + { + "epoch": 18.11, + "learning_rate": 4.634008868625661e-07, + "loss": 0.0016, + "step": 58649 + }, + { + "epoch": 18.11, + "learning_rate": 4.632504198938681e-07, + "loss": 0.0018, + "step": 58650 + }, + { + "epoch": 18.11, + "learning_rate": 4.6309997677831955e-07, + "loss": 0.0017, + "step": 58651 + }, + { + "epoch": 18.11, + "learning_rate": 4.629495575162968e-07, + "loss": 0.0014, + "step": 58652 + }, + { + "epoch": 18.11, + "learning_rate": 4.6279916210817735e-07, + "loss": 0.0014, + "step": 58653 + }, + { + "epoch": 18.11, + "learning_rate": 4.626487905543353e-07, + "loss": 0.0014, + "step": 58654 + }, + { + "epoch": 18.11, + "learning_rate": 4.6249844285514935e-07, + "loss": 0.0012, + "step": 58655 + }, + { + "epoch": 18.11, + "learning_rate": 4.6234811901099466e-07, + "loss": 0.002, + "step": 58656 + }, + { + "epoch": 18.11, + "learning_rate": 4.621978190222454e-07, + "loss": 0.0014, + "step": 58657 + }, + { + "epoch": 18.11, + "learning_rate": 4.620475428892801e-07, + "loss": 0.0013, + "step": 58658 + }, + { + "epoch": 18.11, + "learning_rate": 4.618972906124719e-07, + "loss": 0.0013, + "step": 58659 + }, + { + "epoch": 18.12, + "learning_rate": 4.6174706219220046e-07, + "loss": 0.0015, + "step": 58660 + }, + { + "epoch": 18.12, + "learning_rate": 4.615968576288388e-07, + "loss": 0.0012, + "step": 58661 + }, + { + "epoch": 18.12, + "learning_rate": 4.6144667692276214e-07, + "loss": 0.0018, + "step": 58662 + }, + { + "epoch": 18.12, + "learning_rate": 4.61296520074348e-07, + "loss": 0.0022, + "step": 58663 + }, + { + "epoch": 18.12, + "learning_rate": 4.6114638708396944e-07, + "loss": 0.0012, + "step": 58664 + }, + { + "epoch": 18.12, + "learning_rate": 4.6099627795200606e-07, + "loss": 0.0018, + "step": 58665 + }, + { + "epoch": 18.12, + "learning_rate": 4.608461926788299e-07, + "loss": 0.0013, + "step": 58666 + }, + { + "epoch": 18.12, + "learning_rate": 4.6069613126481615e-07, + "loss": 0.0015, + "step": 58667 + }, + { + "epoch": 18.12, + "learning_rate": 4.605460937103412e-07, + "loss": 0.0019, + "step": 58668 + }, + { + "epoch": 18.12, + "learning_rate": 4.603960800157814e-07, + "loss": 0.0012, + "step": 58669 + }, + { + "epoch": 18.12, + "learning_rate": 4.602460901815098e-07, + "loss": 0.0013, + "step": 58670 + }, + { + "epoch": 18.12, + "learning_rate": 4.6009612420790383e-07, + "loss": 0.0022, + "step": 58671 + }, + { + "epoch": 18.12, + "learning_rate": 4.599461820953377e-07, + "loss": 0.0013, + "step": 58672 + }, + { + "epoch": 18.12, + "learning_rate": 4.597962638441855e-07, + "loss": 0.0009, + "step": 58673 + }, + { + "epoch": 18.12, + "learning_rate": 4.5964636945482146e-07, + "loss": 0.0016, + "step": 58674 + }, + { + "epoch": 18.12, + "learning_rate": 4.5949649892762406e-07, + "loss": 0.0024, + "step": 58675 + }, + { + "epoch": 18.12, + "learning_rate": 4.593466522629664e-07, + "loss": 0.0011, + "step": 58676 + }, + { + "epoch": 18.12, + "learning_rate": 4.5919682946122037e-07, + "loss": 0.0018, + "step": 58677 + }, + { + "epoch": 18.12, + "learning_rate": 4.5904703052276565e-07, + "loss": 0.001, + "step": 58678 + }, + { + "epoch": 18.12, + "learning_rate": 4.58897255447972e-07, + "loss": 0.002, + "step": 58679 + }, + { + "epoch": 18.12, + "learning_rate": 4.5874750423721804e-07, + "loss": 0.002, + "step": 58680 + }, + { + "epoch": 18.12, + "learning_rate": 4.585977768908767e-07, + "loss": 0.0016, + "step": 58681 + }, + { + "epoch": 18.12, + "learning_rate": 4.584480734093233e-07, + "loss": 0.0014, + "step": 58682 + }, + { + "epoch": 18.12, + "learning_rate": 4.5829839379292974e-07, + "loss": 0.0015, + "step": 58683 + }, + { + "epoch": 18.12, + "learning_rate": 4.581487380420735e-07, + "loss": 0.0017, + "step": 58684 + }, + { + "epoch": 18.12, + "learning_rate": 4.579991061571265e-07, + "loss": 0.0016, + "step": 58685 + }, + { + "epoch": 18.12, + "learning_rate": 4.5784949813846624e-07, + "loss": 0.002, + "step": 58686 + }, + { + "epoch": 18.12, + "learning_rate": 4.576999139864635e-07, + "loss": 0.002, + "step": 58687 + }, + { + "epoch": 18.12, + "learning_rate": 4.575503537014925e-07, + "loss": 0.0014, + "step": 58688 + }, + { + "epoch": 18.12, + "learning_rate": 4.5740081728392947e-07, + "loss": 0.0015, + "step": 58689 + }, + { + "epoch": 18.12, + "learning_rate": 4.572513047341476e-07, + "loss": 0.0012, + "step": 58690 + }, + { + "epoch": 18.12, + "learning_rate": 4.571018160525198e-07, + "loss": 0.0017, + "step": 58691 + }, + { + "epoch": 18.13, + "learning_rate": 4.569523512394225e-07, + "loss": 0.0014, + "step": 58692 + }, + { + "epoch": 18.13, + "learning_rate": 4.568029102952265e-07, + "loss": 0.0019, + "step": 58693 + }, + { + "epoch": 18.13, + "learning_rate": 4.5665349322030816e-07, + "loss": 0.0011, + "step": 58694 + }, + { + "epoch": 18.13, + "learning_rate": 4.5650410001503943e-07, + "loss": 0.0017, + "step": 58695 + }, + { + "epoch": 18.13, + "learning_rate": 4.5635473067979443e-07, + "loss": 0.0017, + "step": 58696 + }, + { + "epoch": 18.13, + "learning_rate": 4.562053852149484e-07, + "loss": 0.0019, + "step": 58697 + }, + { + "epoch": 18.13, + "learning_rate": 4.5605606362087106e-07, + "loss": 0.0011, + "step": 58698 + }, + { + "epoch": 18.13, + "learning_rate": 4.559067658979388e-07, + "loss": 0.0021, + "step": 58699 + }, + { + "epoch": 18.13, + "learning_rate": 4.5575749204652573e-07, + "loss": 0.0016, + "step": 58700 + }, + { + "epoch": 18.13, + "learning_rate": 4.556082420670016e-07, + "loss": 0.0014, + "step": 58701 + }, + { + "epoch": 18.13, + "learning_rate": 4.55459015959745e-07, + "loss": 0.0013, + "step": 58702 + }, + { + "epoch": 18.13, + "learning_rate": 4.553098137251255e-07, + "loss": 0.0015, + "step": 58703 + }, + { + "epoch": 18.13, + "learning_rate": 4.551606353635152e-07, + "loss": 0.0014, + "step": 58704 + }, + { + "epoch": 18.13, + "learning_rate": 4.5501148087528924e-07, + "loss": 0.0013, + "step": 58705 + }, + { + "epoch": 18.13, + "learning_rate": 4.548623502608218e-07, + "loss": 0.0014, + "step": 58706 + }, + { + "epoch": 18.13, + "learning_rate": 4.5471324352048484e-07, + "loss": 0.0014, + "step": 58707 + }, + { + "epoch": 18.13, + "learning_rate": 4.545641606546491e-07, + "loss": 0.0015, + "step": 58708 + }, + { + "epoch": 18.13, + "learning_rate": 4.5441510166369106e-07, + "loss": 0.0014, + "step": 58709 + }, + { + "epoch": 18.13, + "learning_rate": 4.542660665479803e-07, + "loss": 0.0018, + "step": 58710 + }, + { + "epoch": 18.13, + "learning_rate": 4.541170553078922e-07, + "loss": 0.0016, + "step": 58711 + }, + { + "epoch": 18.13, + "learning_rate": 4.5396806794379853e-07, + "loss": 0.0015, + "step": 58712 + }, + { + "epoch": 18.13, + "learning_rate": 4.5381910445607245e-07, + "loss": 0.0011, + "step": 58713 + }, + { + "epoch": 18.13, + "learning_rate": 4.5367016484508474e-07, + "loss": 0.0015, + "step": 58714 + }, + { + "epoch": 18.13, + "learning_rate": 4.5352124911120953e-07, + "loss": 0.0017, + "step": 58715 + }, + { + "epoch": 18.13, + "learning_rate": 4.5337235725481765e-07, + "loss": 0.0018, + "step": 58716 + }, + { + "epoch": 18.13, + "learning_rate": 4.5322348927628434e-07, + "loss": 0.0021, + "step": 58717 + }, + { + "epoch": 18.13, + "learning_rate": 4.5307464517598045e-07, + "loss": 0.0016, + "step": 58718 + }, + { + "epoch": 18.13, + "learning_rate": 4.529258249542767e-07, + "loss": 0.0014, + "step": 58719 + }, + { + "epoch": 18.13, + "learning_rate": 4.527770286115474e-07, + "loss": 0.0015, + "step": 58720 + }, + { + "epoch": 18.13, + "learning_rate": 4.526282561481643e-07, + "loss": 0.0017, + "step": 58721 + }, + { + "epoch": 18.13, + "learning_rate": 4.5247950756449833e-07, + "loss": 0.0012, + "step": 58722 + }, + { + "epoch": 18.13, + "learning_rate": 4.5233078286092355e-07, + "loss": 0.0017, + "step": 58723 + }, + { + "epoch": 18.14, + "learning_rate": 4.521820820378109e-07, + "loss": 0.0017, + "step": 58724 + }, + { + "epoch": 18.14, + "learning_rate": 4.5203340509553216e-07, + "loss": 0.0019, + "step": 58725 + }, + { + "epoch": 18.14, + "learning_rate": 4.5188475203445823e-07, + "loss": 0.0018, + "step": 58726 + }, + { + "epoch": 18.14, + "learning_rate": 4.5173612285496325e-07, + "loss": 0.002, + "step": 58727 + }, + { + "epoch": 18.14, + "learning_rate": 4.51587517557418e-07, + "loss": 0.0018, + "step": 58728 + }, + { + "epoch": 18.14, + "learning_rate": 4.5143893614219224e-07, + "loss": 0.0019, + "step": 58729 + }, + { + "epoch": 18.14, + "learning_rate": 4.5129037860966007e-07, + "loss": 0.0019, + "step": 58730 + }, + { + "epoch": 18.14, + "learning_rate": 4.5114184496019233e-07, + "loss": 0.0015, + "step": 58731 + }, + { + "epoch": 18.14, + "learning_rate": 4.5099333519415977e-07, + "loss": 0.0019, + "step": 58732 + }, + { + "epoch": 18.14, + "learning_rate": 4.508448493119366e-07, + "loss": 0.0015, + "step": 58733 + }, + { + "epoch": 18.14, + "learning_rate": 4.506963873138914e-07, + "loss": 0.0015, + "step": 58734 + }, + { + "epoch": 18.14, + "learning_rate": 4.50547949200395e-07, + "loss": 0.0016, + "step": 58735 + }, + { + "epoch": 18.14, + "learning_rate": 4.5039953497181934e-07, + "loss": 0.0013, + "step": 58736 + }, + { + "epoch": 18.14, + "learning_rate": 4.502511446285385e-07, + "loss": 0.0017, + "step": 58737 + }, + { + "epoch": 18.14, + "learning_rate": 4.5010277817092e-07, + "loss": 0.0017, + "step": 58738 + }, + { + "epoch": 18.14, + "learning_rate": 4.499544355993357e-07, + "loss": 0.0013, + "step": 58739 + }, + { + "epoch": 18.14, + "learning_rate": 4.4980611691415874e-07, + "loss": 0.0011, + "step": 58740 + }, + { + "epoch": 18.14, + "learning_rate": 4.496578221157566e-07, + "loss": 0.0012, + "step": 58741 + }, + { + "epoch": 18.14, + "learning_rate": 4.4950955120450225e-07, + "loss": 0.0014, + "step": 58742 + }, + { + "epoch": 18.14, + "learning_rate": 4.4936130418076987e-07, + "loss": 0.0014, + "step": 58743 + }, + { + "epoch": 18.14, + "learning_rate": 4.4921308104492355e-07, + "loss": 0.0015, + "step": 58744 + }, + { + "epoch": 18.14, + "learning_rate": 4.490648817973364e-07, + "loss": 0.0015, + "step": 58745 + }, + { + "epoch": 18.14, + "learning_rate": 4.489167064383826e-07, + "loss": 0.0009, + "step": 58746 + }, + { + "epoch": 18.14, + "learning_rate": 4.487685549684284e-07, + "loss": 0.0013, + "step": 58747 + }, + { + "epoch": 18.14, + "learning_rate": 4.4862042738784693e-07, + "loss": 0.0021, + "step": 58748 + }, + { + "epoch": 18.14, + "learning_rate": 4.48472323697009e-07, + "loss": 0.0015, + "step": 58749 + }, + { + "epoch": 18.14, + "learning_rate": 4.4832424389628094e-07, + "loss": 0.0019, + "step": 58750 + }, + { + "epoch": 18.14, + "learning_rate": 4.481761879860369e-07, + "loss": 0.0014, + "step": 58751 + }, + { + "epoch": 18.14, + "learning_rate": 4.480281559666477e-07, + "loss": 0.0012, + "step": 58752 + }, + { + "epoch": 18.14, + "learning_rate": 4.478801478384831e-07, + "loss": 0.0011, + "step": 58753 + }, + { + "epoch": 18.14, + "learning_rate": 4.477321636019094e-07, + "loss": 0.0016, + "step": 58754 + }, + { + "epoch": 18.14, + "learning_rate": 4.4758420325730303e-07, + "loss": 0.0017, + "step": 58755 + }, + { + "epoch": 18.14, + "learning_rate": 4.4743626680502805e-07, + "loss": 0.0016, + "step": 58756 + }, + { + "epoch": 18.15, + "learning_rate": 4.472883542454576e-07, + "loss": 0.0011, + "step": 58757 + }, + { + "epoch": 18.15, + "learning_rate": 4.471404655789624e-07, + "loss": 0.0019, + "step": 58758 + }, + { + "epoch": 18.15, + "learning_rate": 4.469926008059111e-07, + "loss": 0.0019, + "step": 58759 + }, + { + "epoch": 18.15, + "learning_rate": 4.468447599266734e-07, + "loss": 0.0016, + "step": 58760 + }, + { + "epoch": 18.15, + "learning_rate": 4.46696942941619e-07, + "loss": 0.0024, + "step": 58761 + }, + { + "epoch": 18.15, + "learning_rate": 4.4654914985111874e-07, + "loss": 0.0016, + "step": 58762 + }, + { + "epoch": 18.15, + "learning_rate": 4.464013806555412e-07, + "loss": 0.0013, + "step": 58763 + }, + { + "epoch": 18.15, + "learning_rate": 4.46253635355256e-07, + "loss": 0.0014, + "step": 58764 + }, + { + "epoch": 18.15, + "learning_rate": 4.46105913950633e-07, + "loss": 0.002, + "step": 58765 + }, + { + "epoch": 18.15, + "learning_rate": 4.459582164420417e-07, + "loss": 0.0011, + "step": 58766 + }, + { + "epoch": 18.15, + "learning_rate": 4.4581054282985094e-07, + "loss": 0.0013, + "step": 58767 + }, + { + "epoch": 18.15, + "learning_rate": 4.4566289311443134e-07, + "loss": 0.0013, + "step": 58768 + }, + { + "epoch": 18.15, + "learning_rate": 4.455152672961516e-07, + "loss": 0.0016, + "step": 58769 + }, + { + "epoch": 18.15, + "learning_rate": 4.4536766537538025e-07, + "loss": 0.0013, + "step": 58770 + }, + { + "epoch": 18.15, + "learning_rate": 4.452200873524881e-07, + "loss": 0.0011, + "step": 58771 + }, + { + "epoch": 18.15, + "learning_rate": 4.450725332278416e-07, + "loss": 0.0021, + "step": 58772 + }, + { + "epoch": 18.15, + "learning_rate": 4.449250030018115e-07, + "loss": 0.0018, + "step": 58773 + }, + { + "epoch": 18.15, + "learning_rate": 4.4477749667476864e-07, + "loss": 0.0014, + "step": 58774 + }, + { + "epoch": 18.15, + "learning_rate": 4.446300142470783e-07, + "loss": 0.0017, + "step": 58775 + }, + { + "epoch": 18.15, + "learning_rate": 4.4448255571911014e-07, + "loss": 0.0012, + "step": 58776 + }, + { + "epoch": 18.15, + "learning_rate": 4.443351210912361e-07, + "loss": 0.0013, + "step": 58777 + }, + { + "epoch": 18.15, + "learning_rate": 4.4418771036382147e-07, + "loss": 0.0021, + "step": 58778 + }, + { + "epoch": 18.15, + "learning_rate": 4.44040323537237e-07, + "loss": 0.0018, + "step": 58779 + }, + { + "epoch": 18.15, + "learning_rate": 4.4389296061185137e-07, + "loss": 0.0011, + "step": 58780 + }, + { + "epoch": 18.15, + "learning_rate": 4.437456215880309e-07, + "loss": 0.0014, + "step": 58781 + }, + { + "epoch": 18.15, + "learning_rate": 4.4359830646614534e-07, + "loss": 0.0016, + "step": 58782 + }, + { + "epoch": 18.15, + "learning_rate": 4.434510152465643e-07, + "loss": 0.0013, + "step": 58783 + }, + { + "epoch": 18.15, + "learning_rate": 4.4330374792965534e-07, + "loss": 0.0014, + "step": 58784 + }, + { + "epoch": 18.15, + "learning_rate": 4.4315650451578597e-07, + "loss": 0.0017, + "step": 58785 + }, + { + "epoch": 18.15, + "learning_rate": 4.4300928500532693e-07, + "loss": 0.003, + "step": 58786 + }, + { + "epoch": 18.15, + "learning_rate": 4.428620893986424e-07, + "loss": 0.0015, + "step": 58787 + }, + { + "epoch": 18.15, + "learning_rate": 4.427149176961032e-07, + "loss": 0.0014, + "step": 58788 + }, + { + "epoch": 18.16, + "learning_rate": 4.4256776989807905e-07, + "loss": 0.0022, + "step": 58789 + }, + { + "epoch": 18.16, + "learning_rate": 4.4242064600493516e-07, + "loss": 0.0015, + "step": 58790 + }, + { + "epoch": 18.16, + "learning_rate": 4.422735460170391e-07, + "loss": 0.0024, + "step": 58791 + }, + { + "epoch": 18.16, + "learning_rate": 4.4212646993476047e-07, + "loss": 0.0017, + "step": 58792 + }, + { + "epoch": 18.16, + "learning_rate": 4.419794177584691e-07, + "loss": 0.0017, + "step": 58793 + }, + { + "epoch": 18.16, + "learning_rate": 4.41832389488529e-07, + "loss": 0.0014, + "step": 58794 + }, + { + "epoch": 18.16, + "learning_rate": 4.416853851253089e-07, + "loss": 0.0017, + "step": 58795 + }, + { + "epoch": 18.16, + "learning_rate": 4.415384046691784e-07, + "loss": 0.0018, + "step": 58796 + }, + { + "epoch": 18.16, + "learning_rate": 4.4139144812050173e-07, + "loss": 0.002, + "step": 58797 + }, + { + "epoch": 18.16, + "learning_rate": 4.412445154796485e-07, + "loss": 0.0011, + "step": 58798 + }, + { + "epoch": 18.16, + "learning_rate": 4.4109760674698745e-07, + "loss": 0.0021, + "step": 58799 + }, + { + "epoch": 18.16, + "learning_rate": 4.409507219228859e-07, + "loss": 0.0015, + "step": 58800 + }, + { + "epoch": 18.16, + "learning_rate": 4.40803861007707e-07, + "loss": 0.0015, + "step": 58801 + }, + { + "epoch": 18.16, + "learning_rate": 4.4065702400182375e-07, + "loss": 0.0015, + "step": 58802 + }, + { + "epoch": 18.16, + "learning_rate": 4.4051021090559923e-07, + "loss": 0.0017, + "step": 58803 + }, + { + "epoch": 18.16, + "learning_rate": 4.4036342171940306e-07, + "loss": 0.0011, + "step": 58804 + }, + { + "epoch": 18.16, + "learning_rate": 4.402166564436017e-07, + "loss": 0.0024, + "step": 58805 + }, + { + "epoch": 18.16, + "learning_rate": 4.4006991507856035e-07, + "loss": 0.0023, + "step": 58806 + }, + { + "epoch": 18.16, + "learning_rate": 4.399231976246487e-07, + "loss": 0.0014, + "step": 58807 + }, + { + "epoch": 18.16, + "learning_rate": 4.3977650408223325e-07, + "loss": 0.0012, + "step": 58808 + }, + { + "epoch": 18.16, + "learning_rate": 4.3962983445168027e-07, + "loss": 0.0016, + "step": 58809 + }, + { + "epoch": 18.16, + "learning_rate": 4.3948318873335725e-07, + "loss": 0.0015, + "step": 58810 + }, + { + "epoch": 18.16, + "learning_rate": 4.393365669276306e-07, + "loss": 0.0013, + "step": 58811 + }, + { + "epoch": 18.16, + "learning_rate": 4.3918996903486557e-07, + "loss": 0.0017, + "step": 58812 + }, + { + "epoch": 18.16, + "learning_rate": 4.390433950554296e-07, + "loss": 0.0012, + "step": 58813 + }, + { + "epoch": 18.16, + "learning_rate": 4.3889684498969244e-07, + "loss": 0.0014, + "step": 58814 + }, + { + "epoch": 18.16, + "learning_rate": 4.387503188380171e-07, + "loss": 0.0021, + "step": 58815 + }, + { + "epoch": 18.16, + "learning_rate": 4.3860381660077e-07, + "loss": 0.002, + "step": 58816 + }, + { + "epoch": 18.16, + "learning_rate": 4.3845733827832084e-07, + "loss": 0.0014, + "step": 58817 + }, + { + "epoch": 18.16, + "learning_rate": 4.383108838710315e-07, + "loss": 0.0018, + "step": 58818 + }, + { + "epoch": 18.16, + "learning_rate": 4.381644533792706e-07, + "loss": 0.0015, + "step": 58819 + }, + { + "epoch": 18.16, + "learning_rate": 4.380180468034068e-07, + "loss": 0.0019, + "step": 58820 + }, + { + "epoch": 18.16, + "learning_rate": 4.37871664143803e-07, + "loss": 0.0015, + "step": 58821 + }, + { + "epoch": 18.17, + "learning_rate": 4.3772530540082457e-07, + "loss": 0.0017, + "step": 58822 + }, + { + "epoch": 18.17, + "learning_rate": 4.3757897057484013e-07, + "loss": 0.0018, + "step": 58823 + }, + { + "epoch": 18.17, + "learning_rate": 4.3743265966621484e-07, + "loss": 0.0014, + "step": 58824 + }, + { + "epoch": 18.17, + "learning_rate": 4.3728637267531516e-07, + "loss": 0.0013, + "step": 58825 + }, + { + "epoch": 18.17, + "learning_rate": 4.371401096025052e-07, + "loss": 0.0017, + "step": 58826 + }, + { + "epoch": 18.17, + "learning_rate": 4.3699387044815355e-07, + "loss": 0.0019, + "step": 58827 + }, + { + "epoch": 18.17, + "learning_rate": 4.368476552126233e-07, + "loss": 0.0011, + "step": 58828 + }, + { + "epoch": 18.17, + "learning_rate": 4.3670146389628077e-07, + "loss": 0.001, + "step": 58829 + }, + { + "epoch": 18.17, + "learning_rate": 4.3655529649949345e-07, + "loss": 0.0014, + "step": 58830 + }, + { + "epoch": 18.17, + "learning_rate": 4.3640915302262555e-07, + "loss": 0.0012, + "step": 58831 + }, + { + "epoch": 18.17, + "learning_rate": 4.3626303346604113e-07, + "loss": 0.0011, + "step": 58832 + }, + { + "epoch": 18.17, + "learning_rate": 4.361169378301089e-07, + "loss": 0.0015, + "step": 58833 + }, + { + "epoch": 18.17, + "learning_rate": 4.359708661151907e-07, + "loss": 0.0012, + "step": 58834 + }, + { + "epoch": 18.17, + "learning_rate": 4.3582481832165515e-07, + "loss": 0.0022, + "step": 58835 + }, + { + "epoch": 18.17, + "learning_rate": 4.3567879444986636e-07, + "loss": 0.0014, + "step": 58836 + }, + { + "epoch": 18.17, + "learning_rate": 4.355327945001886e-07, + "loss": 0.0016, + "step": 58837 + }, + { + "epoch": 18.17, + "learning_rate": 4.3538681847298704e-07, + "loss": 0.0014, + "step": 58838 + }, + { + "epoch": 18.17, + "learning_rate": 4.3524086636862915e-07, + "loss": 0.0016, + "step": 58839 + }, + { + "epoch": 18.17, + "learning_rate": 4.3509493818747696e-07, + "loss": 0.0016, + "step": 58840 + }, + { + "epoch": 18.17, + "learning_rate": 4.3494903392989786e-07, + "loss": 0.0017, + "step": 58841 + }, + { + "epoch": 18.17, + "learning_rate": 4.3480315359625604e-07, + "loss": 0.0017, + "step": 58842 + }, + { + "epoch": 18.17, + "learning_rate": 4.3465729718691454e-07, + "loss": 0.002, + "step": 58843 + }, + { + "epoch": 18.17, + "learning_rate": 4.345114647022408e-07, + "loss": 0.0016, + "step": 58844 + }, + { + "epoch": 18.17, + "learning_rate": 4.3436565614259906e-07, + "loss": 0.0011, + "step": 58845 + }, + { + "epoch": 18.17, + "learning_rate": 4.3421987150835343e-07, + "loss": 0.0018, + "step": 58846 + }, + { + "epoch": 18.17, + "learning_rate": 4.340741107998669e-07, + "loss": 0.0019, + "step": 58847 + }, + { + "epoch": 18.17, + "learning_rate": 4.339283740175071e-07, + "loss": 0.0017, + "step": 58848 + }, + { + "epoch": 18.17, + "learning_rate": 4.3378266116163694e-07, + "loss": 0.0014, + "step": 58849 + }, + { + "epoch": 18.17, + "learning_rate": 4.336369722326206e-07, + "loss": 0.0007, + "step": 58850 + }, + { + "epoch": 18.17, + "learning_rate": 4.3349130723082334e-07, + "loss": 0.0018, + "step": 58851 + }, + { + "epoch": 18.17, + "learning_rate": 4.3334566615661046e-07, + "loss": 0.0017, + "step": 58852 + }, + { + "epoch": 18.17, + "learning_rate": 4.3320004901034276e-07, + "loss": 0.0017, + "step": 58853 + }, + { + "epoch": 18.18, + "learning_rate": 4.3305445579238883e-07, + "loss": 0.0015, + "step": 58854 + }, + { + "epoch": 18.18, + "learning_rate": 4.3290888650310836e-07, + "loss": 0.002, + "step": 58855 + }, + { + "epoch": 18.18, + "learning_rate": 4.327633411428689e-07, + "loss": 0.0015, + "step": 58856 + }, + { + "epoch": 18.18, + "learning_rate": 4.326178197120323e-07, + "loss": 0.0016, + "step": 58857 + }, + { + "epoch": 18.18, + "learning_rate": 4.32472322210965e-07, + "loss": 0.0019, + "step": 58858 + }, + { + "epoch": 18.18, + "learning_rate": 4.3232684864002784e-07, + "loss": 0.0019, + "step": 58859 + }, + { + "epoch": 18.18, + "learning_rate": 4.321813989995871e-07, + "loss": 0.0018, + "step": 58860 + }, + { + "epoch": 18.18, + "learning_rate": 4.320359732900059e-07, + "loss": 0.0019, + "step": 58861 + }, + { + "epoch": 18.18, + "learning_rate": 4.318905715116484e-07, + "loss": 0.0013, + "step": 58862 + }, + { + "epoch": 18.18, + "learning_rate": 4.3174519366487646e-07, + "loss": 0.0011, + "step": 58863 + }, + { + "epoch": 18.18, + "learning_rate": 4.315998397500565e-07, + "loss": 0.0019, + "step": 58864 + }, + { + "epoch": 18.18, + "learning_rate": 4.3145450976754824e-07, + "loss": 0.0013, + "step": 58865 + }, + { + "epoch": 18.18, + "learning_rate": 4.313092037177202e-07, + "loss": 0.0018, + "step": 58866 + }, + { + "epoch": 18.18, + "learning_rate": 4.311639216009322e-07, + "loss": 0.0014, + "step": 58867 + }, + { + "epoch": 18.18, + "learning_rate": 4.310186634175462e-07, + "loss": 0.0017, + "step": 58868 + }, + { + "epoch": 18.18, + "learning_rate": 4.308734291679295e-07, + "loss": 0.0016, + "step": 58869 + }, + { + "epoch": 18.18, + "learning_rate": 4.307282188524442e-07, + "loss": 0.0016, + "step": 58870 + }, + { + "epoch": 18.18, + "learning_rate": 4.3058303247145104e-07, + "loss": 0.0015, + "step": 58871 + }, + { + "epoch": 18.18, + "learning_rate": 4.304378700253176e-07, + "loss": 0.0016, + "step": 58872 + }, + { + "epoch": 18.18, + "learning_rate": 4.302927315144034e-07, + "loss": 0.0019, + "step": 58873 + }, + { + "epoch": 18.18, + "learning_rate": 4.301476169390717e-07, + "loss": 0.0015, + "step": 58874 + }, + { + "epoch": 18.18, + "learning_rate": 4.300025262996865e-07, + "loss": 0.0018, + "step": 58875 + }, + { + "epoch": 18.18, + "learning_rate": 4.2985745959661095e-07, + "loss": 0.002, + "step": 58876 + }, + { + "epoch": 18.18, + "learning_rate": 4.2971241683020804e-07, + "loss": 0.0013, + "step": 58877 + }, + { + "epoch": 18.18, + "learning_rate": 4.295673980008386e-07, + "loss": 0.0014, + "step": 58878 + }, + { + "epoch": 18.18, + "learning_rate": 4.2942240310886785e-07, + "loss": 0.0015, + "step": 58879 + }, + { + "epoch": 18.18, + "learning_rate": 4.2927743215465556e-07, + "loss": 0.0013, + "step": 58880 + }, + { + "epoch": 18.18, + "learning_rate": 4.2913248513856585e-07, + "loss": 0.0016, + "step": 58881 + }, + { + "epoch": 18.18, + "learning_rate": 4.2898756206096406e-07, + "loss": 0.0014, + "step": 58882 + }, + { + "epoch": 18.18, + "learning_rate": 4.2884266292220865e-07, + "loss": 0.0014, + "step": 58883 + }, + { + "epoch": 18.18, + "learning_rate": 4.286977877226617e-07, + "loss": 0.0015, + "step": 58884 + }, + { + "epoch": 18.18, + "learning_rate": 4.285529364626895e-07, + "loss": 0.0019, + "step": 58885 + }, + { + "epoch": 18.19, + "learning_rate": 4.2840810914265065e-07, + "loss": 0.0015, + "step": 58886 + }, + { + "epoch": 18.19, + "learning_rate": 4.282633057629104e-07, + "loss": 0.0009, + "step": 58887 + }, + { + "epoch": 18.19, + "learning_rate": 4.2811852632382853e-07, + "loss": 0.0017, + "step": 58888 + }, + { + "epoch": 18.19, + "learning_rate": 4.279737708257681e-07, + "loss": 0.0011, + "step": 58889 + }, + { + "epoch": 18.19, + "learning_rate": 4.2782903926909093e-07, + "loss": 0.0022, + "step": 58890 + }, + { + "epoch": 18.19, + "learning_rate": 4.276843316541579e-07, + "loss": 0.0015, + "step": 58891 + }, + { + "epoch": 18.19, + "learning_rate": 4.275396479813365e-07, + "loss": 0.0019, + "step": 58892 + }, + { + "epoch": 18.19, + "learning_rate": 4.273949882509809e-07, + "loss": 0.001, + "step": 58893 + }, + { + "epoch": 18.19, + "learning_rate": 4.272503524634564e-07, + "loss": 0.001, + "step": 58894 + }, + { + "epoch": 18.19, + "learning_rate": 4.271057406191259e-07, + "loss": 0.0013, + "step": 58895 + }, + { + "epoch": 18.19, + "learning_rate": 4.2696115271834816e-07, + "loss": 0.0015, + "step": 58896 + }, + { + "epoch": 18.19, + "learning_rate": 4.2681658876148835e-07, + "loss": 0.0018, + "step": 58897 + }, + { + "epoch": 18.19, + "learning_rate": 4.266720487489062e-07, + "loss": 0.0013, + "step": 58898 + }, + { + "epoch": 18.19, + "learning_rate": 4.265275326809626e-07, + "loss": 0.0014, + "step": 58899 + }, + { + "epoch": 18.19, + "learning_rate": 4.263830405580194e-07, + "loss": 0.0014, + "step": 58900 + }, + { + "epoch": 18.19, + "learning_rate": 4.2623857238043965e-07, + "loss": 0.0014, + "step": 58901 + }, + { + "epoch": 18.19, + "learning_rate": 4.260941281485831e-07, + "loss": 0.0014, + "step": 58902 + }, + { + "epoch": 18.19, + "learning_rate": 4.2594970786281055e-07, + "loss": 0.0022, + "step": 58903 + }, + { + "epoch": 18.19, + "learning_rate": 4.25805311523485e-07, + "loss": 0.0014, + "step": 58904 + }, + { + "epoch": 18.19, + "learning_rate": 4.256609391309652e-07, + "loss": 0.0014, + "step": 58905 + }, + { + "epoch": 18.19, + "learning_rate": 4.255165906856129e-07, + "loss": 0.0018, + "step": 58906 + }, + { + "epoch": 18.19, + "learning_rate": 4.2537226618779236e-07, + "loss": 0.0013, + "step": 58907 + }, + { + "epoch": 18.19, + "learning_rate": 4.2522796563786216e-07, + "loss": 0.0013, + "step": 58908 + }, + { + "epoch": 18.19, + "learning_rate": 4.2508368903618094e-07, + "loss": 0.0016, + "step": 58909 + }, + { + "epoch": 18.19, + "learning_rate": 4.2493943638311386e-07, + "loss": 0.0016, + "step": 58910 + }, + { + "epoch": 18.19, + "learning_rate": 4.2479520767901737e-07, + "loss": 0.0016, + "step": 58911 + }, + { + "epoch": 18.19, + "learning_rate": 4.2465100292425675e-07, + "loss": 0.0021, + "step": 58912 + }, + { + "epoch": 18.19, + "learning_rate": 4.245068221191895e-07, + "loss": 0.0021, + "step": 58913 + }, + { + "epoch": 18.19, + "learning_rate": 4.2436266526417634e-07, + "loss": 0.002, + "step": 58914 + }, + { + "epoch": 18.19, + "learning_rate": 4.2421853235957935e-07, + "loss": 0.0016, + "step": 58915 + }, + { + "epoch": 18.19, + "learning_rate": 4.240744234057581e-07, + "loss": 0.0017, + "step": 58916 + }, + { + "epoch": 18.19, + "learning_rate": 4.239303384030735e-07, + "loss": 0.0012, + "step": 58917 + }, + { + "epoch": 18.19, + "learning_rate": 4.237862773518864e-07, + "loss": 0.0011, + "step": 58918 + }, + { + "epoch": 18.2, + "learning_rate": 4.236422402525564e-07, + "loss": 0.002, + "step": 58919 + }, + { + "epoch": 18.2, + "learning_rate": 4.234982271054422e-07, + "loss": 0.0017, + "step": 58920 + }, + { + "epoch": 18.2, + "learning_rate": 4.233542379109057e-07, + "loss": 0.0016, + "step": 58921 + }, + { + "epoch": 18.2, + "learning_rate": 4.232102726693077e-07, + "loss": 0.0016, + "step": 58922 + }, + { + "epoch": 18.2, + "learning_rate": 4.2306633138100793e-07, + "loss": 0.0015, + "step": 58923 + }, + { + "epoch": 18.2, + "learning_rate": 4.2292241404636505e-07, + "loss": 0.0016, + "step": 58924 + }, + { + "epoch": 18.2, + "learning_rate": 4.2277852066573974e-07, + "loss": 0.0016, + "step": 58925 + }, + { + "epoch": 18.2, + "learning_rate": 4.226346512394941e-07, + "loss": 0.0012, + "step": 58926 + }, + { + "epoch": 18.2, + "learning_rate": 4.224908057679833e-07, + "loss": 0.0016, + "step": 58927 + }, + { + "epoch": 18.2, + "learning_rate": 4.2234698425157263e-07, + "loss": 0.0015, + "step": 58928 + }, + { + "epoch": 18.2, + "learning_rate": 4.2220318669061733e-07, + "loss": 0.0013, + "step": 58929 + }, + { + "epoch": 18.2, + "learning_rate": 4.220594130854783e-07, + "loss": 0.0009, + "step": 58930 + }, + { + "epoch": 18.2, + "learning_rate": 4.2191566343651626e-07, + "loss": 0.0013, + "step": 58931 + }, + { + "epoch": 18.2, + "learning_rate": 4.2177193774409095e-07, + "loss": 0.0016, + "step": 58932 + }, + { + "epoch": 18.2, + "learning_rate": 4.2162823600855996e-07, + "loss": 0.0015, + "step": 58933 + }, + { + "epoch": 18.2, + "learning_rate": 4.21484558230284e-07, + "loss": 0.0016, + "step": 58934 + }, + { + "epoch": 18.2, + "learning_rate": 4.2134090440962284e-07, + "loss": 0.0013, + "step": 58935 + }, + { + "epoch": 18.2, + "learning_rate": 4.2119727454693394e-07, + "loss": 0.0013, + "step": 58936 + }, + { + "epoch": 18.2, + "learning_rate": 4.2105366864257703e-07, + "loss": 0.0009, + "step": 58937 + }, + { + "epoch": 18.2, + "learning_rate": 4.20910086696914e-07, + "loss": 0.0014, + "step": 58938 + }, + { + "epoch": 18.2, + "learning_rate": 4.207665287103013e-07, + "loss": 0.0013, + "step": 58939 + }, + { + "epoch": 18.2, + "learning_rate": 4.2062299468309753e-07, + "loss": 0.0014, + "step": 58940 + }, + { + "epoch": 18.2, + "learning_rate": 4.2047948461566457e-07, + "loss": 0.0016, + "step": 58941 + }, + { + "epoch": 18.2, + "learning_rate": 4.2033599850835773e-07, + "loss": 0.0016, + "step": 58942 + }, + { + "epoch": 18.2, + "learning_rate": 4.2019253636154e-07, + "loss": 0.0015, + "step": 58943 + }, + { + "epoch": 18.2, + "learning_rate": 4.200490981755678e-07, + "loss": 0.0017, + "step": 58944 + }, + { + "epoch": 18.2, + "learning_rate": 4.1990568395079757e-07, + "loss": 0.0014, + "step": 58945 + }, + { + "epoch": 18.2, + "learning_rate": 4.1976229368759223e-07, + "loss": 0.0012, + "step": 58946 + }, + { + "epoch": 18.2, + "learning_rate": 4.196189273863083e-07, + "loss": 0.0014, + "step": 58947 + }, + { + "epoch": 18.2, + "learning_rate": 4.194755850473042e-07, + "loss": 0.0011, + "step": 58948 + }, + { + "epoch": 18.2, + "learning_rate": 4.1933226667094094e-07, + "loss": 0.0017, + "step": 58949 + }, + { + "epoch": 18.2, + "learning_rate": 4.1918897225757484e-07, + "loss": 0.0014, + "step": 58950 + }, + { + "epoch": 18.21, + "learning_rate": 4.1904570180756334e-07, + "loss": 0.0012, + "step": 58951 + }, + { + "epoch": 18.21, + "learning_rate": 4.189024553212651e-07, + "loss": 0.0015, + "step": 58952 + }, + { + "epoch": 18.21, + "learning_rate": 4.1875923279904085e-07, + "loss": 0.0014, + "step": 58953 + }, + { + "epoch": 18.21, + "learning_rate": 4.186160342412482e-07, + "loss": 0.0014, + "step": 58954 + }, + { + "epoch": 18.21, + "learning_rate": 4.1847285964824237e-07, + "loss": 0.0012, + "step": 58955 + }, + { + "epoch": 18.21, + "learning_rate": 4.183297090203842e-07, + "loss": 0.0017, + "step": 58956 + }, + { + "epoch": 18.21, + "learning_rate": 4.181865823580311e-07, + "loss": 0.0015, + "step": 58957 + }, + { + "epoch": 18.21, + "learning_rate": 4.180434796615407e-07, + "loss": 0.0018, + "step": 58958 + }, + { + "epoch": 18.21, + "learning_rate": 4.179004009312715e-07, + "loss": 0.0008, + "step": 58959 + }, + { + "epoch": 18.21, + "learning_rate": 4.1775734616758214e-07, + "loss": 0.002, + "step": 58960 + }, + { + "epoch": 18.21, + "learning_rate": 4.176143153708279e-07, + "loss": 0.0021, + "step": 58961 + }, + { + "epoch": 18.21, + "learning_rate": 4.174713085413673e-07, + "loss": 0.0022, + "step": 58962 + }, + { + "epoch": 18.21, + "learning_rate": 4.1732832567956014e-07, + "loss": 0.0016, + "step": 58963 + }, + { + "epoch": 18.21, + "learning_rate": 4.1718536678576284e-07, + "loss": 0.0015, + "step": 58964 + }, + { + "epoch": 18.21, + "learning_rate": 4.1704243186033164e-07, + "loss": 0.0017, + "step": 58965 + }, + { + "epoch": 18.21, + "learning_rate": 4.168995209036264e-07, + "loss": 0.0013, + "step": 58966 + }, + { + "epoch": 18.21, + "learning_rate": 4.1675663391600117e-07, + "loss": 0.0017, + "step": 58967 + }, + { + "epoch": 18.21, + "learning_rate": 4.1661377089781685e-07, + "loss": 0.0018, + "step": 58968 + }, + { + "epoch": 18.21, + "learning_rate": 4.164709318494298e-07, + "loss": 0.0017, + "step": 58969 + }, + { + "epoch": 18.21, + "learning_rate": 4.1632811677119636e-07, + "loss": 0.0011, + "step": 58970 + }, + { + "epoch": 18.21, + "learning_rate": 4.1618532566347403e-07, + "loss": 0.0017, + "step": 58971 + }, + { + "epoch": 18.21, + "learning_rate": 4.160425585266215e-07, + "loss": 0.0019, + "step": 58972 + }, + { + "epoch": 18.21, + "learning_rate": 4.1589981536099277e-07, + "loss": 0.002, + "step": 58973 + }, + { + "epoch": 18.21, + "learning_rate": 4.157570961669477e-07, + "loss": 0.0021, + "step": 58974 + }, + { + "epoch": 18.21, + "learning_rate": 4.156144009448426e-07, + "loss": 0.0011, + "step": 58975 + }, + { + "epoch": 18.21, + "learning_rate": 4.154717296950317e-07, + "loss": 0.0015, + "step": 58976 + }, + { + "epoch": 18.21, + "learning_rate": 4.153290824178757e-07, + "loss": 0.0018, + "step": 58977 + }, + { + "epoch": 18.21, + "learning_rate": 4.1518645911373e-07, + "loss": 0.0023, + "step": 58978 + }, + { + "epoch": 18.21, + "learning_rate": 4.1504385978294983e-07, + "loss": 0.001, + "step": 58979 + }, + { + "epoch": 18.21, + "learning_rate": 4.149012844258948e-07, + "loss": 0.0014, + "step": 58980 + }, + { + "epoch": 18.21, + "learning_rate": 4.147587330429204e-07, + "loss": 0.0014, + "step": 58981 + }, + { + "epoch": 18.21, + "learning_rate": 4.1461620563438055e-07, + "loss": 0.0019, + "step": 58982 + }, + { + "epoch": 18.21, + "learning_rate": 4.14473702200634e-07, + "loss": 0.0016, + "step": 58983 + }, + { + "epoch": 18.22, + "learning_rate": 4.143312227420382e-07, + "loss": 0.0017, + "step": 58984 + }, + { + "epoch": 18.22, + "learning_rate": 4.141887672589495e-07, + "loss": 0.0014, + "step": 58985 + }, + { + "epoch": 18.22, + "learning_rate": 4.1404633575171995e-07, + "loss": 0.0014, + "step": 58986 + }, + { + "epoch": 18.22, + "learning_rate": 4.1390392822071024e-07, + "loss": 0.0014, + "step": 58987 + }, + { + "epoch": 18.22, + "learning_rate": 4.137615446662757e-07, + "loss": 0.0013, + "step": 58988 + }, + { + "epoch": 18.22, + "learning_rate": 4.136191850887705e-07, + "loss": 0.0015, + "step": 58989 + }, + { + "epoch": 18.22, + "learning_rate": 4.134768494885544e-07, + "loss": 0.002, + "step": 58990 + }, + { + "epoch": 18.22, + "learning_rate": 4.1333453786598034e-07, + "loss": 0.0019, + "step": 58991 + }, + { + "epoch": 18.22, + "learning_rate": 4.1319225022140474e-07, + "loss": 0.0017, + "step": 58992 + }, + { + "epoch": 18.22, + "learning_rate": 4.1304998655518294e-07, + "loss": 0.0014, + "step": 58993 + }, + { + "epoch": 18.22, + "learning_rate": 4.1290774686767343e-07, + "loss": 0.0019, + "step": 58994 + }, + { + "epoch": 18.22, + "learning_rate": 4.1276553115922933e-07, + "loss": 0.0019, + "step": 58995 + }, + { + "epoch": 18.22, + "learning_rate": 4.1262333943020707e-07, + "loss": 0.0019, + "step": 58996 + }, + { + "epoch": 18.22, + "learning_rate": 4.12481171680964e-07, + "loss": 0.0011, + "step": 58997 + }, + { + "epoch": 18.22, + "learning_rate": 4.123390279118522e-07, + "loss": 0.002, + "step": 58998 + }, + { + "epoch": 18.22, + "learning_rate": 4.121969081232291e-07, + "loss": 0.0018, + "step": 58999 + }, + { + "epoch": 18.22, + "learning_rate": 4.120548123154522e-07, + "loss": 0.0017, + "step": 59000 + }, + { + "epoch": 18.22, + "learning_rate": 4.119127404888734e-07, + "loss": 0.0015, + "step": 59001 + }, + { + "epoch": 18.22, + "learning_rate": 4.117706926438492e-07, + "loss": 0.0015, + "step": 59002 + }, + { + "epoch": 18.22, + "learning_rate": 4.116286687807369e-07, + "loss": 0.0014, + "step": 59003 + }, + { + "epoch": 18.22, + "learning_rate": 4.114866688998886e-07, + "loss": 0.0017, + "step": 59004 + }, + { + "epoch": 18.22, + "learning_rate": 4.113446930016618e-07, + "loss": 0.0019, + "step": 59005 + }, + { + "epoch": 18.22, + "learning_rate": 4.112027410864117e-07, + "loss": 0.0015, + "step": 59006 + }, + { + "epoch": 18.22, + "learning_rate": 4.110608131544902e-07, + "loss": 0.0018, + "step": 59007 + }, + { + "epoch": 18.22, + "learning_rate": 4.109189092062549e-07, + "loss": 0.0013, + "step": 59008 + }, + { + "epoch": 18.22, + "learning_rate": 4.107770292420621e-07, + "loss": 0.0021, + "step": 59009 + }, + { + "epoch": 18.22, + "learning_rate": 4.106351732622649e-07, + "loss": 0.001, + "step": 59010 + }, + { + "epoch": 18.22, + "learning_rate": 4.104933412672163e-07, + "loss": 0.0016, + "step": 59011 + }, + { + "epoch": 18.22, + "learning_rate": 4.1035153325727384e-07, + "loss": 0.0022, + "step": 59012 + }, + { + "epoch": 18.22, + "learning_rate": 4.1020974923279055e-07, + "loss": 0.0018, + "step": 59013 + }, + { + "epoch": 18.22, + "learning_rate": 4.100679891941217e-07, + "loss": 0.0013, + "step": 59014 + }, + { + "epoch": 18.22, + "learning_rate": 4.0992625314162373e-07, + "loss": 0.0019, + "step": 59015 + }, + { + "epoch": 18.23, + "learning_rate": 4.097845410756485e-07, + "loss": 0.0014, + "step": 59016 + }, + { + "epoch": 18.23, + "learning_rate": 4.096428529965502e-07, + "loss": 0.0015, + "step": 59017 + }, + { + "epoch": 18.23, + "learning_rate": 4.0950118890468516e-07, + "loss": 0.0016, + "step": 59018 + }, + { + "epoch": 18.23, + "learning_rate": 4.093595488004065e-07, + "loss": 0.0022, + "step": 59019 + }, + { + "epoch": 18.23, + "learning_rate": 4.092179326840695e-07, + "loss": 0.0014, + "step": 59020 + }, + { + "epoch": 18.23, + "learning_rate": 4.0907634055602606e-07, + "loss": 0.0013, + "step": 59021 + }, + { + "epoch": 18.23, + "learning_rate": 4.089347724166337e-07, + "loss": 0.0013, + "step": 59022 + }, + { + "epoch": 18.23, + "learning_rate": 4.087932282662443e-07, + "loss": 0.0013, + "step": 59023 + }, + { + "epoch": 18.23, + "learning_rate": 4.08651708105211e-07, + "loss": 0.0014, + "step": 59024 + }, + { + "epoch": 18.23, + "learning_rate": 4.0851021193389127e-07, + "loss": 0.0021, + "step": 59025 + }, + { + "epoch": 18.23, + "learning_rate": 4.0836873975263703e-07, + "loss": 0.0017, + "step": 59026 + }, + { + "epoch": 18.23, + "learning_rate": 4.082272915618002e-07, + "loss": 0.0021, + "step": 59027 + }, + { + "epoch": 18.23, + "learning_rate": 4.0808586736173716e-07, + "loss": 0.0014, + "step": 59028 + }, + { + "epoch": 18.23, + "learning_rate": 4.079444671527999e-07, + "loss": 0.0015, + "step": 59029 + }, + { + "epoch": 18.23, + "learning_rate": 4.078030909353437e-07, + "loss": 0.0014, + "step": 59030 + }, + { + "epoch": 18.23, + "learning_rate": 4.076617387097237e-07, + "loss": 0.0018, + "step": 59031 + }, + { + "epoch": 18.23, + "learning_rate": 4.075204104762875e-07, + "loss": 0.0013, + "step": 59032 + }, + { + "epoch": 18.23, + "learning_rate": 4.0737910623539376e-07, + "loss": 0.0014, + "step": 59033 + }, + { + "epoch": 18.23, + "learning_rate": 4.0723782598739545e-07, + "loss": 0.0013, + "step": 59034 + }, + { + "epoch": 18.23, + "learning_rate": 4.0709656973264346e-07, + "loss": 0.0014, + "step": 59035 + }, + { + "epoch": 18.23, + "learning_rate": 4.0695533747149407e-07, + "loss": 0.0012, + "step": 59036 + }, + { + "epoch": 18.23, + "learning_rate": 4.068141292042982e-07, + "loss": 0.0015, + "step": 59037 + }, + { + "epoch": 18.23, + "learning_rate": 4.0667294493141e-07, + "loss": 0.002, + "step": 59038 + }, + { + "epoch": 18.23, + "learning_rate": 4.0653178465318135e-07, + "loss": 0.0019, + "step": 59039 + }, + { + "epoch": 18.23, + "learning_rate": 4.063906483699687e-07, + "loss": 0.0012, + "step": 59040 + }, + { + "epoch": 18.23, + "learning_rate": 4.062495360821217e-07, + "loss": 0.0012, + "step": 59041 + }, + { + "epoch": 18.23, + "learning_rate": 4.061084477899935e-07, + "loss": 0.0012, + "step": 59042 + }, + { + "epoch": 18.23, + "learning_rate": 4.059673834939393e-07, + "loss": 0.0018, + "step": 59043 + }, + { + "epoch": 18.23, + "learning_rate": 4.0582634319430994e-07, + "loss": 0.0015, + "step": 59044 + }, + { + "epoch": 18.23, + "learning_rate": 4.0568532689145735e-07, + "loss": 0.0017, + "step": 59045 + }, + { + "epoch": 18.23, + "learning_rate": 4.0554433458573796e-07, + "loss": 0.0014, + "step": 59046 + }, + { + "epoch": 18.23, + "learning_rate": 4.0540336627750144e-07, + "loss": 0.0017, + "step": 59047 + }, + { + "epoch": 18.24, + "learning_rate": 4.052624219671009e-07, + "loss": 0.0017, + "step": 59048 + }, + { + "epoch": 18.24, + "learning_rate": 4.051215016548893e-07, + "loss": 0.0017, + "step": 59049 + }, + { + "epoch": 18.24, + "learning_rate": 4.049806053412175e-07, + "loss": 0.0017, + "step": 59050 + }, + { + "epoch": 18.24, + "learning_rate": 4.048397330264409e-07, + "loss": 0.0015, + "step": 59051 + }, + { + "epoch": 18.24, + "learning_rate": 4.0469888471090903e-07, + "loss": 0.0018, + "step": 59052 + }, + { + "epoch": 18.24, + "learning_rate": 4.0455806039497614e-07, + "loss": 0.0016, + "step": 59053 + }, + { + "epoch": 18.24, + "learning_rate": 4.0441726007899305e-07, + "loss": 0.0012, + "step": 59054 + }, + { + "epoch": 18.24, + "learning_rate": 4.0427648376331175e-07, + "loss": 0.0016, + "step": 59055 + }, + { + "epoch": 18.24, + "learning_rate": 4.0413573144828635e-07, + "loss": 0.0016, + "step": 59056 + }, + { + "epoch": 18.24, + "learning_rate": 4.0399500313426764e-07, + "loss": 0.0018, + "step": 59057 + }, + { + "epoch": 18.24, + "learning_rate": 4.0385429882160765e-07, + "loss": 0.0015, + "step": 59058 + }, + { + "epoch": 18.24, + "learning_rate": 4.0371361851065827e-07, + "loss": 0.0014, + "step": 59059 + }, + { + "epoch": 18.24, + "learning_rate": 4.0357296220177035e-07, + "loss": 0.0012, + "step": 59060 + }, + { + "epoch": 18.24, + "learning_rate": 4.0343232989529803e-07, + "loss": 0.0022, + "step": 59061 + }, + { + "epoch": 18.24, + "learning_rate": 4.032917215915921e-07, + "loss": 0.0014, + "step": 59062 + }, + { + "epoch": 18.24, + "learning_rate": 4.031511372910024e-07, + "loss": 0.0017, + "step": 59063 + }, + { + "epoch": 18.24, + "learning_rate": 4.030105769938819e-07, + "loss": 0.0016, + "step": 59064 + }, + { + "epoch": 18.24, + "learning_rate": 4.0287004070058364e-07, + "loss": 0.002, + "step": 59065 + }, + { + "epoch": 18.24, + "learning_rate": 4.027295284114563e-07, + "loss": 0.0016, + "step": 59066 + }, + { + "epoch": 18.24, + "learning_rate": 4.0258904012685506e-07, + "loss": 0.0017, + "step": 59067 + }, + { + "epoch": 18.24, + "learning_rate": 4.024485758471286e-07, + "loss": 0.0015, + "step": 59068 + }, + { + "epoch": 18.24, + "learning_rate": 4.023081355726266e-07, + "loss": 0.0019, + "step": 59069 + }, + { + "epoch": 18.24, + "learning_rate": 4.0216771930370323e-07, + "loss": 0.0017, + "step": 59070 + }, + { + "epoch": 18.24, + "learning_rate": 4.0202732704071047e-07, + "loss": 0.0017, + "step": 59071 + }, + { + "epoch": 18.24, + "learning_rate": 4.0188695878399796e-07, + "loss": 0.002, + "step": 59072 + }, + { + "epoch": 18.24, + "learning_rate": 4.017466145339155e-07, + "loss": 0.0011, + "step": 59073 + }, + { + "epoch": 18.24, + "learning_rate": 4.016062942908161e-07, + "loss": 0.0022, + "step": 59074 + }, + { + "epoch": 18.24, + "learning_rate": 4.014659980550484e-07, + "loss": 0.0013, + "step": 59075 + }, + { + "epoch": 18.24, + "learning_rate": 4.0132572582696537e-07, + "loss": 0.0016, + "step": 59076 + }, + { + "epoch": 18.24, + "learning_rate": 4.011854776069191e-07, + "loss": 0.0015, + "step": 59077 + }, + { + "epoch": 18.24, + "learning_rate": 4.01045253395258e-07, + "loss": 0.0018, + "step": 59078 + }, + { + "epoch": 18.24, + "learning_rate": 4.009050531923331e-07, + "loss": 0.0021, + "step": 59079 + }, + { + "epoch": 18.24, + "learning_rate": 4.007648769984951e-07, + "loss": 0.0017, + "step": 59080 + }, + { + "epoch": 18.25, + "learning_rate": 4.006247248140949e-07, + "loss": 0.0016, + "step": 59081 + }, + { + "epoch": 18.25, + "learning_rate": 4.0048459663948435e-07, + "loss": 0.0016, + "step": 59082 + }, + { + "epoch": 18.25, + "learning_rate": 4.0034449247501215e-07, + "loss": 0.0021, + "step": 59083 + }, + { + "epoch": 18.25, + "learning_rate": 4.0020441232102804e-07, + "loss": 0.0016, + "step": 59084 + }, + { + "epoch": 18.25, + "learning_rate": 4.000643561778839e-07, + "loss": 0.0015, + "step": 59085 + }, + { + "epoch": 18.25, + "learning_rate": 3.999243240459294e-07, + "loss": 0.0015, + "step": 59086 + }, + { + "epoch": 18.25, + "learning_rate": 3.9978431592551656e-07, + "loss": 0.0017, + "step": 59087 + }, + { + "epoch": 18.25, + "learning_rate": 3.99644331816994e-07, + "loss": 0.0015, + "step": 59088 + }, + { + "epoch": 18.25, + "learning_rate": 3.9950437172071145e-07, + "loss": 0.0026, + "step": 59089 + }, + { + "epoch": 18.25, + "learning_rate": 3.9936443563701964e-07, + "loss": 0.0021, + "step": 59090 + }, + { + "epoch": 18.25, + "learning_rate": 3.992245235662684e-07, + "loss": 0.0019, + "step": 59091 + }, + { + "epoch": 18.25, + "learning_rate": 3.990846355088074e-07, + "loss": 0.0013, + "step": 59092 + }, + { + "epoch": 18.25, + "learning_rate": 3.989447714649886e-07, + "loss": 0.0014, + "step": 59093 + }, + { + "epoch": 18.25, + "learning_rate": 3.988049314351572e-07, + "loss": 0.0016, + "step": 59094 + }, + { + "epoch": 18.25, + "learning_rate": 3.9866511541966636e-07, + "loss": 0.0015, + "step": 59095 + }, + { + "epoch": 18.25, + "learning_rate": 3.9852532341886683e-07, + "loss": 0.0018, + "step": 59096 + }, + { + "epoch": 18.25, + "learning_rate": 3.983855554331051e-07, + "loss": 0.0012, + "step": 59097 + }, + { + "epoch": 18.25, + "learning_rate": 3.982458114627341e-07, + "loss": 0.0015, + "step": 59098 + }, + { + "epoch": 18.25, + "learning_rate": 3.981060915081003e-07, + "loss": 0.0018, + "step": 59099 + }, + { + "epoch": 18.25, + "learning_rate": 3.9796639556955454e-07, + "loss": 0.0013, + "step": 59100 + }, + { + "epoch": 18.25, + "learning_rate": 3.9782672364744534e-07, + "loss": 0.0011, + "step": 59101 + }, + { + "epoch": 18.25, + "learning_rate": 3.9768707574212473e-07, + "loss": 0.0016, + "step": 59102 + }, + { + "epoch": 18.25, + "learning_rate": 3.9754745185393905e-07, + "loss": 0.0018, + "step": 59103 + }, + { + "epoch": 18.25, + "learning_rate": 3.9740785198323806e-07, + "loss": 0.001, + "step": 59104 + }, + { + "epoch": 18.25, + "learning_rate": 3.9726827613037256e-07, + "loss": 0.0017, + "step": 59105 + }, + { + "epoch": 18.25, + "learning_rate": 3.9712872429569003e-07, + "loss": 0.0013, + "step": 59106 + }, + { + "epoch": 18.25, + "learning_rate": 3.9698919647953913e-07, + "loss": 0.0016, + "step": 59107 + }, + { + "epoch": 18.25, + "learning_rate": 3.968496926822707e-07, + "loss": 0.0015, + "step": 59108 + }, + { + "epoch": 18.25, + "learning_rate": 3.967102129042333e-07, + "loss": 0.0021, + "step": 59109 + }, + { + "epoch": 18.25, + "learning_rate": 3.965707571457733e-07, + "loss": 0.0014, + "step": 59110 + }, + { + "epoch": 18.25, + "learning_rate": 3.964313254072438e-07, + "loss": 0.0014, + "step": 59111 + }, + { + "epoch": 18.25, + "learning_rate": 3.96291917688989e-07, + "loss": 0.0011, + "step": 59112 + }, + { + "epoch": 18.26, + "learning_rate": 3.961525339913608e-07, + "loss": 0.0017, + "step": 59113 + }, + { + "epoch": 18.26, + "learning_rate": 3.9601317431470777e-07, + "loss": 0.0013, + "step": 59114 + }, + { + "epoch": 18.26, + "learning_rate": 3.9587383865937524e-07, + "loss": 0.0017, + "step": 59115 + }, + { + "epoch": 18.26, + "learning_rate": 3.9573452702571404e-07, + "loss": 0.0011, + "step": 59116 + }, + { + "epoch": 18.26, + "learning_rate": 3.9559523941407275e-07, + "loss": 0.002, + "step": 59117 + }, + { + "epoch": 18.26, + "learning_rate": 3.954559758248011e-07, + "loss": 0.0012, + "step": 59118 + }, + { + "epoch": 18.26, + "learning_rate": 3.953167362582455e-07, + "loss": 0.0011, + "step": 59119 + }, + { + "epoch": 18.26, + "learning_rate": 3.9517752071475237e-07, + "loss": 0.0014, + "step": 59120 + }, + { + "epoch": 18.26, + "learning_rate": 3.950383291946747e-07, + "loss": 0.0012, + "step": 59121 + }, + { + "epoch": 18.26, + "learning_rate": 3.9489916169835553e-07, + "loss": 0.002, + "step": 59122 + }, + { + "epoch": 18.26, + "learning_rate": 3.9476001822614793e-07, + "loss": 0.0019, + "step": 59123 + }, + { + "epoch": 18.26, + "learning_rate": 3.9462089877839617e-07, + "loss": 0.0022, + "step": 59124 + }, + { + "epoch": 18.26, + "learning_rate": 3.9448180335544986e-07, + "loss": 0.0014, + "step": 59125 + }, + { + "epoch": 18.26, + "learning_rate": 3.943427319576554e-07, + "loss": 0.0015, + "step": 59126 + }, + { + "epoch": 18.26, + "learning_rate": 3.942036845853625e-07, + "loss": 0.0021, + "step": 59127 + }, + { + "epoch": 18.26, + "learning_rate": 3.940646612389176e-07, + "loss": 0.0016, + "step": 59128 + }, + { + "epoch": 18.26, + "learning_rate": 3.9392566191867046e-07, + "loss": 0.0015, + "step": 59129 + }, + { + "epoch": 18.26, + "learning_rate": 3.9378668662496624e-07, + "loss": 0.0021, + "step": 59130 + }, + { + "epoch": 18.26, + "learning_rate": 3.936477353581536e-07, + "loss": 0.0016, + "step": 59131 + }, + { + "epoch": 18.26, + "learning_rate": 3.9350880811857895e-07, + "loss": 0.0016, + "step": 59132 + }, + { + "epoch": 18.26, + "learning_rate": 3.933699049065931e-07, + "loss": 0.0012, + "step": 59133 + }, + { + "epoch": 18.26, + "learning_rate": 3.932310257225402e-07, + "loss": 0.0026, + "step": 59134 + }, + { + "epoch": 18.26, + "learning_rate": 3.93092170566769e-07, + "loss": 0.0017, + "step": 59135 + }, + { + "epoch": 18.26, + "learning_rate": 3.9295333943962675e-07, + "loss": 0.0023, + "step": 59136 + }, + { + "epoch": 18.26, + "learning_rate": 3.9281453234145895e-07, + "loss": 0.0016, + "step": 59137 + }, + { + "epoch": 18.26, + "learning_rate": 3.926757492726141e-07, + "loss": 0.0015, + "step": 59138 + }, + { + "epoch": 18.26, + "learning_rate": 3.9253699023344305e-07, + "loss": 0.0015, + "step": 59139 + }, + { + "epoch": 18.26, + "learning_rate": 3.9239825522428555e-07, + "loss": 0.0021, + "step": 59140 + }, + { + "epoch": 18.26, + "learning_rate": 3.9225954424549353e-07, + "loss": 0.0013, + "step": 59141 + }, + { + "epoch": 18.26, + "learning_rate": 3.9212085729741336e-07, + "loss": 0.0016, + "step": 59142 + }, + { + "epoch": 18.26, + "learning_rate": 3.919821943803892e-07, + "loss": 0.0013, + "step": 59143 + }, + { + "epoch": 18.26, + "learning_rate": 3.9184355549477193e-07, + "loss": 0.0015, + "step": 59144 + }, + { + "epoch": 18.27, + "learning_rate": 3.917049406409068e-07, + "loss": 0.0017, + "step": 59145 + }, + { + "epoch": 18.27, + "learning_rate": 3.91566349819138e-07, + "loss": 0.0013, + "step": 59146 + }, + { + "epoch": 18.27, + "learning_rate": 3.914277830298152e-07, + "loss": 0.0014, + "step": 59147 + }, + { + "epoch": 18.27, + "learning_rate": 3.9128924027328486e-07, + "loss": 0.0015, + "step": 59148 + }, + { + "epoch": 18.27, + "learning_rate": 3.911507215498922e-07, + "loss": 0.0013, + "step": 59149 + }, + { + "epoch": 18.27, + "learning_rate": 3.9101222685998364e-07, + "loss": 0.001, + "step": 59150 + }, + { + "epoch": 18.27, + "learning_rate": 3.908737562039056e-07, + "loss": 0.0013, + "step": 59151 + }, + { + "epoch": 18.27, + "learning_rate": 3.9073530958200544e-07, + "loss": 0.0014, + "step": 59152 + }, + { + "epoch": 18.27, + "learning_rate": 3.905968869946286e-07, + "loss": 0.0013, + "step": 59153 + }, + { + "epoch": 18.27, + "learning_rate": 3.9045848844212254e-07, + "loss": 0.0019, + "step": 59154 + }, + { + "epoch": 18.27, + "learning_rate": 3.903201139248325e-07, + "loss": 0.0021, + "step": 59155 + }, + { + "epoch": 18.27, + "learning_rate": 3.9018176344310375e-07, + "loss": 0.0015, + "step": 59156 + }, + { + "epoch": 18.27, + "learning_rate": 3.9004343699728276e-07, + "loss": 0.0014, + "step": 59157 + }, + { + "epoch": 18.27, + "learning_rate": 3.8990513458771694e-07, + "loss": 0.0017, + "step": 59158 + }, + { + "epoch": 18.27, + "learning_rate": 3.8976685621475166e-07, + "loss": 0.0012, + "step": 59159 + }, + { + "epoch": 18.27, + "learning_rate": 3.8962860187872986e-07, + "loss": 0.0018, + "step": 59160 + }, + { + "epoch": 18.27, + "learning_rate": 3.894903715800025e-07, + "loss": 0.0013, + "step": 59161 + }, + { + "epoch": 18.27, + "learning_rate": 3.893521653189103e-07, + "loss": 0.0013, + "step": 59162 + }, + { + "epoch": 18.27, + "learning_rate": 3.8921398309580194e-07, + "loss": 0.0016, + "step": 59163 + }, + { + "epoch": 18.27, + "learning_rate": 3.8907582491102267e-07, + "loss": 0.0018, + "step": 59164 + }, + { + "epoch": 18.27, + "learning_rate": 3.8893769076491895e-07, + "loss": 0.0016, + "step": 59165 + }, + { + "epoch": 18.27, + "learning_rate": 3.887995806578326e-07, + "loss": 0.0021, + "step": 59166 + }, + { + "epoch": 18.27, + "learning_rate": 3.8866149459011346e-07, + "loss": 0.0017, + "step": 59167 + }, + { + "epoch": 18.27, + "learning_rate": 3.8852343256210234e-07, + "loss": 0.0016, + "step": 59168 + }, + { + "epoch": 18.27, + "learning_rate": 3.8838539457415003e-07, + "loss": 0.0019, + "step": 59169 + }, + { + "epoch": 18.27, + "learning_rate": 3.882473806265985e-07, + "loss": 0.0011, + "step": 59170 + }, + { + "epoch": 18.27, + "learning_rate": 3.881093907197908e-07, + "loss": 0.0016, + "step": 59171 + }, + { + "epoch": 18.27, + "learning_rate": 3.879714248540767e-07, + "loss": 0.0016, + "step": 59172 + }, + { + "epoch": 18.27, + "learning_rate": 3.878334830297992e-07, + "loss": 0.0016, + "step": 59173 + }, + { + "epoch": 18.27, + "learning_rate": 3.8769556524730246e-07, + "loss": 0.0019, + "step": 59174 + }, + { + "epoch": 18.27, + "learning_rate": 3.875576715069329e-07, + "loss": 0.0017, + "step": 59175 + }, + { + "epoch": 18.27, + "learning_rate": 3.874198018090347e-07, + "loss": 0.0015, + "step": 59176 + }, + { + "epoch": 18.27, + "learning_rate": 3.87281956153952e-07, + "loss": 0.002, + "step": 59177 + }, + { + "epoch": 18.28, + "learning_rate": 3.871441345420313e-07, + "loss": 0.0017, + "step": 59178 + }, + { + "epoch": 18.28, + "learning_rate": 3.8700633697361653e-07, + "loss": 0.0017, + "step": 59179 + }, + { + "epoch": 18.28, + "learning_rate": 3.868685634490521e-07, + "loss": 0.0014, + "step": 59180 + }, + { + "epoch": 18.28, + "learning_rate": 3.867308139686821e-07, + "loss": 0.0019, + "step": 59181 + }, + { + "epoch": 18.28, + "learning_rate": 3.865930885328517e-07, + "loss": 0.0012, + "step": 59182 + }, + { + "epoch": 18.28, + "learning_rate": 3.864553871419063e-07, + "loss": 0.0018, + "step": 59183 + }, + { + "epoch": 18.28, + "learning_rate": 3.8631770979618787e-07, + "loss": 0.0021, + "step": 59184 + }, + { + "epoch": 18.28, + "learning_rate": 3.8618005649604385e-07, + "loss": 0.0026, + "step": 59185 + }, + { + "epoch": 18.28, + "learning_rate": 3.8604242724181726e-07, + "loss": 0.0018, + "step": 59186 + }, + { + "epoch": 18.28, + "learning_rate": 3.8590482203385014e-07, + "loss": 0.0017, + "step": 59187 + }, + { + "epoch": 18.28, + "learning_rate": 3.8576724087248887e-07, + "loss": 0.0021, + "step": 59188 + }, + { + "epoch": 18.28, + "learning_rate": 3.856296837580786e-07, + "loss": 0.0016, + "step": 59189 + }, + { + "epoch": 18.28, + "learning_rate": 3.8549215069096147e-07, + "loss": 0.0017, + "step": 59190 + }, + { + "epoch": 18.28, + "learning_rate": 3.853546416714815e-07, + "loss": 0.0017, + "step": 59191 + }, + { + "epoch": 18.28, + "learning_rate": 3.8521715669998407e-07, + "loss": 0.0014, + "step": 59192 + }, + { + "epoch": 18.28, + "learning_rate": 3.85079695776811e-07, + "loss": 0.0021, + "step": 59193 + }, + { + "epoch": 18.28, + "learning_rate": 3.8494225890230777e-07, + "loss": 0.0017, + "step": 59194 + }, + { + "epoch": 18.28, + "learning_rate": 3.848048460768183e-07, + "loss": 0.0024, + "step": 59195 + }, + { + "epoch": 18.28, + "learning_rate": 3.846674573006859e-07, + "loss": 0.0016, + "step": 59196 + }, + { + "epoch": 18.28, + "learning_rate": 3.845300925742523e-07, + "loss": 0.0017, + "step": 59197 + }, + { + "epoch": 18.28, + "learning_rate": 3.8439275189786407e-07, + "loss": 0.0016, + "step": 59198 + }, + { + "epoch": 18.28, + "learning_rate": 3.8425543527186193e-07, + "loss": 0.0018, + "step": 59199 + }, + { + "epoch": 18.28, + "learning_rate": 3.8411814269659234e-07, + "loss": 0.0013, + "step": 59200 + }, + { + "epoch": 18.28, + "learning_rate": 3.8398087417239717e-07, + "loss": 0.0017, + "step": 59201 + }, + { + "epoch": 18.28, + "learning_rate": 3.838436296996184e-07, + "loss": 0.0017, + "step": 59202 + }, + { + "epoch": 18.28, + "learning_rate": 3.8370640927860024e-07, + "loss": 0.0017, + "step": 59203 + }, + { + "epoch": 18.28, + "learning_rate": 3.8356921290968796e-07, + "loss": 0.002, + "step": 59204 + }, + { + "epoch": 18.28, + "learning_rate": 3.8343204059322125e-07, + "loss": 0.0015, + "step": 59205 + }, + { + "epoch": 18.28, + "learning_rate": 3.8329489232954653e-07, + "loss": 0.0018, + "step": 59206 + }, + { + "epoch": 18.28, + "learning_rate": 3.8315776811900575e-07, + "loss": 0.0019, + "step": 59207 + }, + { + "epoch": 18.28, + "learning_rate": 3.830206679619397e-07, + "loss": 0.0018, + "step": 59208 + }, + { + "epoch": 18.28, + "learning_rate": 3.828835918586926e-07, + "loss": 0.002, + "step": 59209 + }, + { + "epoch": 18.29, + "learning_rate": 3.8274653980960865e-07, + "loss": 0.0015, + "step": 59210 + }, + { + "epoch": 18.29, + "learning_rate": 3.826095118150308e-07, + "loss": 0.0021, + "step": 59211 + }, + { + "epoch": 18.29, + "learning_rate": 3.8247250787529886e-07, + "loss": 0.0016, + "step": 59212 + }, + { + "epoch": 18.29, + "learning_rate": 3.8233552799075813e-07, + "loss": 0.0014, + "step": 59213 + }, + { + "epoch": 18.29, + "learning_rate": 3.821985721617494e-07, + "loss": 0.0025, + "step": 59214 + }, + { + "epoch": 18.29, + "learning_rate": 3.820616403886168e-07, + "loss": 0.0019, + "step": 59215 + }, + { + "epoch": 18.29, + "learning_rate": 3.819247326717035e-07, + "loss": 0.0014, + "step": 59216 + }, + { + "epoch": 18.29, + "learning_rate": 3.8178784901135025e-07, + "loss": 0.001, + "step": 59217 + }, + { + "epoch": 18.29, + "learning_rate": 3.816509894078979e-07, + "loss": 0.0016, + "step": 59218 + }, + { + "epoch": 18.29, + "learning_rate": 3.8151415386169176e-07, + "loss": 0.0017, + "step": 59219 + }, + { + "epoch": 18.29, + "learning_rate": 3.813773423730738e-07, + "loss": 0.0019, + "step": 59220 + }, + { + "epoch": 18.29, + "learning_rate": 3.8124055494238587e-07, + "loss": 0.0015, + "step": 59221 + }, + { + "epoch": 18.29, + "learning_rate": 3.811037915699678e-07, + "loss": 0.0016, + "step": 59222 + }, + { + "epoch": 18.29, + "learning_rate": 3.8096705225616484e-07, + "loss": 0.002, + "step": 59223 + }, + { + "epoch": 18.29, + "learning_rate": 3.8083033700131667e-07, + "loss": 0.0014, + "step": 59224 + }, + { + "epoch": 18.29, + "learning_rate": 3.806936458057664e-07, + "loss": 0.0017, + "step": 59225 + }, + { + "epoch": 18.29, + "learning_rate": 3.8055697866985706e-07, + "loss": 0.0014, + "step": 59226 + }, + { + "epoch": 18.29, + "learning_rate": 3.8042033559392956e-07, + "loss": 0.0012, + "step": 59227 + }, + { + "epoch": 18.29, + "learning_rate": 3.8028371657832354e-07, + "loss": 0.0014, + "step": 59228 + }, + { + "epoch": 18.29, + "learning_rate": 3.8014712162338317e-07, + "loss": 0.0017, + "step": 59229 + }, + { + "epoch": 18.29, + "learning_rate": 3.8001055072944827e-07, + "loss": 0.0014, + "step": 59230 + }, + { + "epoch": 18.29, + "learning_rate": 3.7987400389686404e-07, + "loss": 0.0014, + "step": 59231 + }, + { + "epoch": 18.29, + "learning_rate": 3.79737481125968e-07, + "loss": 0.0015, + "step": 59232 + }, + { + "epoch": 18.29, + "learning_rate": 3.796009824171032e-07, + "loss": 0.002, + "step": 59233 + }, + { + "epoch": 18.29, + "learning_rate": 3.794645077706105e-07, + "loss": 0.0014, + "step": 59234 + }, + { + "epoch": 18.29, + "learning_rate": 3.7932805718683185e-07, + "loss": 0.0015, + "step": 59235 + }, + { + "epoch": 18.29, + "learning_rate": 3.791916306661092e-07, + "loss": 0.0026, + "step": 59236 + }, + { + "epoch": 18.29, + "learning_rate": 3.7905522820878225e-07, + "loss": 0.0013, + "step": 59237 + }, + { + "epoch": 18.29, + "learning_rate": 3.789188498151941e-07, + "loss": 0.002, + "step": 59238 + }, + { + "epoch": 18.29, + "learning_rate": 3.7878249548568335e-07, + "loss": 0.0019, + "step": 59239 + }, + { + "epoch": 18.29, + "learning_rate": 3.7864616522059303e-07, + "loss": 0.0018, + "step": 59240 + }, + { + "epoch": 18.29, + "learning_rate": 3.7850985902026403e-07, + "loss": 0.0016, + "step": 59241 + }, + { + "epoch": 18.29, + "learning_rate": 3.7837357688503605e-07, + "loss": 0.0014, + "step": 59242 + }, + { + "epoch": 18.3, + "learning_rate": 3.7823731881524993e-07, + "loss": 0.0012, + "step": 59243 + }, + { + "epoch": 18.3, + "learning_rate": 3.7810108481124876e-07, + "loss": 0.002, + "step": 59244 + }, + { + "epoch": 18.3, + "learning_rate": 3.7796487487337e-07, + "loss": 0.0017, + "step": 59245 + }, + { + "epoch": 18.3, + "learning_rate": 3.778286890019567e-07, + "loss": 0.0014, + "step": 59246 + }, + { + "epoch": 18.3, + "learning_rate": 3.7769252719735084e-07, + "loss": 0.0016, + "step": 59247 + }, + { + "epoch": 18.3, + "learning_rate": 3.7755638945988773e-07, + "loss": 0.0019, + "step": 59248 + }, + { + "epoch": 18.3, + "learning_rate": 3.774202757899126e-07, + "loss": 0.0018, + "step": 59249 + }, + { + "epoch": 18.3, + "learning_rate": 3.7728418618776295e-07, + "loss": 0.0012, + "step": 59250 + }, + { + "epoch": 18.3, + "learning_rate": 3.7714812065378304e-07, + "loss": 0.0017, + "step": 59251 + }, + { + "epoch": 18.3, + "learning_rate": 3.770120791883103e-07, + "loss": 0.0018, + "step": 59252 + }, + { + "epoch": 18.3, + "learning_rate": 3.7687606179168446e-07, + "loss": 0.0014, + "step": 59253 + }, + { + "epoch": 18.3, + "learning_rate": 3.767400684642475e-07, + "loss": 0.001, + "step": 59254 + }, + { + "epoch": 18.3, + "learning_rate": 3.76604099206338e-07, + "loss": 0.0016, + "step": 59255 + }, + { + "epoch": 18.3, + "learning_rate": 3.764681540182968e-07, + "loss": 0.0016, + "step": 59256 + }, + { + "epoch": 18.3, + "learning_rate": 3.7633223290046594e-07, + "loss": 0.0013, + "step": 59257 + }, + { + "epoch": 18.3, + "learning_rate": 3.761963358531817e-07, + "loss": 0.0014, + "step": 59258 + }, + { + "epoch": 18.3, + "learning_rate": 3.76060462876785e-07, + "loss": 0.0016, + "step": 59259 + }, + { + "epoch": 18.3, + "learning_rate": 3.7592461397161884e-07, + "loss": 0.0023, + "step": 59260 + }, + { + "epoch": 18.3, + "learning_rate": 3.757887891380185e-07, + "loss": 0.002, + "step": 59261 + }, + { + "epoch": 18.3, + "learning_rate": 3.7565298837632604e-07, + "loss": 0.0017, + "step": 59262 + }, + { + "epoch": 18.3, + "learning_rate": 3.7551721168688216e-07, + "loss": 0.0016, + "step": 59263 + }, + { + "epoch": 18.3, + "learning_rate": 3.7538145907002333e-07, + "loss": 0.0015, + "step": 59264 + }, + { + "epoch": 18.3, + "learning_rate": 3.7524573052609147e-07, + "loss": 0.0016, + "step": 59265 + }, + { + "epoch": 18.3, + "learning_rate": 3.7511002605542525e-07, + "loss": 0.0019, + "step": 59266 + }, + { + "epoch": 18.3, + "learning_rate": 3.749743456583654e-07, + "loss": 0.0017, + "step": 59267 + }, + { + "epoch": 18.3, + "learning_rate": 3.748386893352496e-07, + "loss": 0.002, + "step": 59268 + }, + { + "epoch": 18.3, + "learning_rate": 3.747030570864174e-07, + "loss": 0.0013, + "step": 59269 + }, + { + "epoch": 18.3, + "learning_rate": 3.7456744891220864e-07, + "loss": 0.0019, + "step": 59270 + }, + { + "epoch": 18.3, + "learning_rate": 3.744318648129619e-07, + "loss": 0.0014, + "step": 59271 + }, + { + "epoch": 18.3, + "learning_rate": 3.742963047890169e-07, + "loss": 0.0013, + "step": 59272 + }, + { + "epoch": 18.3, + "learning_rate": 3.741607688407134e-07, + "loss": 0.0015, + "step": 59273 + }, + { + "epoch": 18.3, + "learning_rate": 3.7402525696838886e-07, + "loss": 0.002, + "step": 59274 + }, + { + "epoch": 18.31, + "learning_rate": 3.7388976917238304e-07, + "loss": 0.0016, + "step": 59275 + }, + { + "epoch": 18.31, + "learning_rate": 3.737543054530335e-07, + "loss": 0.0015, + "step": 59276 + }, + { + "epoch": 18.31, + "learning_rate": 3.73618865810681e-07, + "loss": 0.0018, + "step": 59277 + }, + { + "epoch": 18.31, + "learning_rate": 3.734834502456641e-07, + "loss": 0.0018, + "step": 59278 + }, + { + "epoch": 18.31, + "learning_rate": 3.7334805875831936e-07, + "loss": 0.0015, + "step": 59279 + }, + { + "epoch": 18.31, + "learning_rate": 3.7321269134898754e-07, + "loss": 0.0017, + "step": 59280 + }, + { + "epoch": 18.31, + "learning_rate": 3.730773480180061e-07, + "loss": 0.0017, + "step": 59281 + }, + { + "epoch": 18.31, + "learning_rate": 3.729420287657148e-07, + "loss": 0.0019, + "step": 59282 + }, + { + "epoch": 18.31, + "learning_rate": 3.7280673359245235e-07, + "loss": 0.0016, + "step": 59283 + }, + { + "epoch": 18.31, + "learning_rate": 3.7267146249855393e-07, + "loss": 0.0026, + "step": 59284 + }, + { + "epoch": 18.31, + "learning_rate": 3.7253621548436145e-07, + "loss": 0.0023, + "step": 59285 + }, + { + "epoch": 18.31, + "learning_rate": 3.7240099255021145e-07, + "loss": 0.0014, + "step": 59286 + }, + { + "epoch": 18.31, + "learning_rate": 3.722657936964413e-07, + "loss": 0.0017, + "step": 59287 + }, + { + "epoch": 18.31, + "learning_rate": 3.721306189233942e-07, + "loss": 0.0014, + "step": 59288 + }, + { + "epoch": 18.31, + "learning_rate": 3.7199546823140085e-07, + "loss": 0.0019, + "step": 59289 + }, + { + "epoch": 18.31, + "learning_rate": 3.7186034162080333e-07, + "loss": 0.002, + "step": 59290 + }, + { + "epoch": 18.31, + "learning_rate": 3.7172523909194013e-07, + "loss": 0.002, + "step": 59291 + }, + { + "epoch": 18.31, + "learning_rate": 3.7159016064514773e-07, + "loss": 0.0015, + "step": 59292 + }, + { + "epoch": 18.31, + "learning_rate": 3.7145510628076474e-07, + "loss": 0.0013, + "step": 59293 + }, + { + "epoch": 18.31, + "learning_rate": 3.7132007599912976e-07, + "loss": 0.0011, + "step": 59294 + }, + { + "epoch": 18.31, + "learning_rate": 3.71185069800577e-07, + "loss": 0.0014, + "step": 59295 + }, + { + "epoch": 18.31, + "learning_rate": 3.7105008768544725e-07, + "loss": 0.0014, + "step": 59296 + }, + { + "epoch": 18.31, + "learning_rate": 3.7091512965407916e-07, + "loss": 0.0013, + "step": 59297 + }, + { + "epoch": 18.31, + "learning_rate": 3.7078019570680803e-07, + "loss": 0.0019, + "step": 59298 + }, + { + "epoch": 18.31, + "learning_rate": 3.706452858439702e-07, + "loss": 0.0021, + "step": 59299 + }, + { + "epoch": 18.31, + "learning_rate": 3.7051040006590654e-07, + "loss": 0.0019, + "step": 59300 + }, + { + "epoch": 18.31, + "learning_rate": 3.703755383729513e-07, + "loss": 0.002, + "step": 59301 + }, + { + "epoch": 18.31, + "learning_rate": 3.7024070076544293e-07, + "loss": 0.0016, + "step": 59302 + }, + { + "epoch": 18.31, + "learning_rate": 3.701058872437202e-07, + "loss": 0.0013, + "step": 59303 + }, + { + "epoch": 18.31, + "learning_rate": 3.6997109780811944e-07, + "loss": 0.0019, + "step": 59304 + }, + { + "epoch": 18.31, + "learning_rate": 3.69836332458976e-07, + "loss": 0.0014, + "step": 59305 + }, + { + "epoch": 18.31, + "learning_rate": 3.697015911966295e-07, + "loss": 0.0019, + "step": 59306 + }, + { + "epoch": 18.32, + "learning_rate": 3.6956687402141425e-07, + "loss": 0.0014, + "step": 59307 + }, + { + "epoch": 18.32, + "learning_rate": 3.6943218093367093e-07, + "loss": 0.0014, + "step": 59308 + }, + { + "epoch": 18.32, + "learning_rate": 3.692975119337328e-07, + "loss": 0.0018, + "step": 59309 + }, + { + "epoch": 18.32, + "learning_rate": 3.691628670219383e-07, + "loss": 0.0008, + "step": 59310 + }, + { + "epoch": 18.32, + "learning_rate": 3.690282461986228e-07, + "loss": 0.0015, + "step": 59311 + }, + { + "epoch": 18.32, + "learning_rate": 3.68893649464126e-07, + "loss": 0.0011, + "step": 59312 + }, + { + "epoch": 18.32, + "learning_rate": 3.687590768187821e-07, + "loss": 0.0015, + "step": 59313 + }, + { + "epoch": 18.32, + "learning_rate": 3.686245282629286e-07, + "loss": 0.0012, + "step": 59314 + }, + { + "epoch": 18.32, + "learning_rate": 3.6849000379690193e-07, + "loss": 0.0013, + "step": 59315 + }, + { + "epoch": 18.32, + "learning_rate": 3.683555034210384e-07, + "loss": 0.0014, + "step": 59316 + }, + { + "epoch": 18.32, + "learning_rate": 3.682210271356734e-07, + "loss": 0.0014, + "step": 59317 + }, + { + "epoch": 18.32, + "learning_rate": 3.6808657494114553e-07, + "loss": 0.002, + "step": 59318 + }, + { + "epoch": 18.32, + "learning_rate": 3.6795214683779114e-07, + "loss": 0.0013, + "step": 59319 + }, + { + "epoch": 18.32, + "learning_rate": 3.678177428259422e-07, + "loss": 0.0021, + "step": 59320 + }, + { + "epoch": 18.32, + "learning_rate": 3.676833629059395e-07, + "loss": 0.0017, + "step": 59321 + }, + { + "epoch": 18.32, + "learning_rate": 3.675490070781174e-07, + "loss": 0.0013, + "step": 59322 + }, + { + "epoch": 18.32, + "learning_rate": 3.6741467534281207e-07, + "loss": 0.0014, + "step": 59323 + }, + { + "epoch": 18.32, + "learning_rate": 3.6728036770036003e-07, + "loss": 0.0015, + "step": 59324 + }, + { + "epoch": 18.32, + "learning_rate": 3.6714608415109653e-07, + "loss": 0.0013, + "step": 59325 + }, + { + "epoch": 18.32, + "learning_rate": 3.670118246953569e-07, + "loss": 0.0016, + "step": 59326 + }, + { + "epoch": 18.32, + "learning_rate": 3.668775893334764e-07, + "loss": 0.0018, + "step": 59327 + }, + { + "epoch": 18.32, + "learning_rate": 3.6674337806579475e-07, + "loss": 0.0017, + "step": 59328 + }, + { + "epoch": 18.32, + "learning_rate": 3.666091908926439e-07, + "loss": 0.0017, + "step": 59329 + }, + { + "epoch": 18.32, + "learning_rate": 3.664750278143603e-07, + "loss": 0.0015, + "step": 59330 + }, + { + "epoch": 18.32, + "learning_rate": 3.663408888312803e-07, + "loss": 0.0013, + "step": 59331 + }, + { + "epoch": 18.32, + "learning_rate": 3.6620677394373694e-07, + "loss": 0.0016, + "step": 59332 + }, + { + "epoch": 18.32, + "learning_rate": 3.660726831520689e-07, + "loss": 0.002, + "step": 59333 + }, + { + "epoch": 18.32, + "learning_rate": 3.6593861645661033e-07, + "loss": 0.0011, + "step": 59334 + }, + { + "epoch": 18.32, + "learning_rate": 3.6580457385769653e-07, + "loss": 0.0018, + "step": 59335 + }, + { + "epoch": 18.32, + "learning_rate": 3.6567055535566164e-07, + "loss": 0.0012, + "step": 59336 + }, + { + "epoch": 18.32, + "learning_rate": 3.6553656095084323e-07, + "loss": 0.0018, + "step": 59337 + }, + { + "epoch": 18.32, + "learning_rate": 3.654025906435743e-07, + "loss": 0.0017, + "step": 59338 + }, + { + "epoch": 18.32, + "learning_rate": 3.652686444341913e-07, + "loss": 0.0019, + "step": 59339 + }, + { + "epoch": 18.33, + "learning_rate": 3.6513472232302837e-07, + "loss": 0.0022, + "step": 59340 + }, + { + "epoch": 18.33, + "learning_rate": 3.650008243104208e-07, + "loss": 0.0017, + "step": 59341 + }, + { + "epoch": 18.33, + "learning_rate": 3.648669503967028e-07, + "loss": 0.0016, + "step": 59342 + }, + { + "epoch": 18.33, + "learning_rate": 3.647331005822108e-07, + "loss": 0.0021, + "step": 59343 + }, + { + "epoch": 18.33, + "learning_rate": 3.6459927486727776e-07, + "loss": 0.0014, + "step": 59344 + }, + { + "epoch": 18.33, + "learning_rate": 3.6446547325224014e-07, + "loss": 0.0016, + "step": 59345 + }, + { + "epoch": 18.33, + "learning_rate": 3.64331695737431e-07, + "loss": 0.0018, + "step": 59346 + }, + { + "epoch": 18.33, + "learning_rate": 3.6419794232318674e-07, + "loss": 0.0016, + "step": 59347 + }, + { + "epoch": 18.33, + "learning_rate": 3.640642130098404e-07, + "loss": 0.0012, + "step": 59348 + }, + { + "epoch": 18.33, + "learning_rate": 3.639305077977273e-07, + "loss": 0.0016, + "step": 59349 + }, + { + "epoch": 18.33, + "learning_rate": 3.637968266871816e-07, + "loss": 0.0021, + "step": 59350 + }, + { + "epoch": 18.33, + "learning_rate": 3.636631696785364e-07, + "loss": 0.0023, + "step": 59351 + }, + { + "epoch": 18.33, + "learning_rate": 3.635295367721281e-07, + "loss": 0.0015, + "step": 59352 + }, + { + "epoch": 18.33, + "learning_rate": 3.633959279682897e-07, + "loss": 0.0014, + "step": 59353 + }, + { + "epoch": 18.33, + "learning_rate": 3.6326234326735543e-07, + "loss": 0.002, + "step": 59354 + }, + { + "epoch": 18.33, + "learning_rate": 3.6312878266966057e-07, + "loss": 0.0016, + "step": 59355 + }, + { + "epoch": 18.33, + "learning_rate": 3.629952461755382e-07, + "loss": 0.0016, + "step": 59356 + }, + { + "epoch": 18.33, + "learning_rate": 3.628617337853213e-07, + "loss": 0.0013, + "step": 59357 + }, + { + "epoch": 18.33, + "learning_rate": 3.6272824549934525e-07, + "loss": 0.0019, + "step": 59358 + }, + { + "epoch": 18.33, + "learning_rate": 3.6259478131794424e-07, + "loss": 0.0021, + "step": 59359 + }, + { + "epoch": 18.33, + "learning_rate": 3.624613412414524e-07, + "loss": 0.0018, + "step": 59360 + }, + { + "epoch": 18.33, + "learning_rate": 3.623279252702006e-07, + "loss": 0.0019, + "step": 59361 + }, + { + "epoch": 18.33, + "learning_rate": 3.6219453340452517e-07, + "loss": 0.0013, + "step": 59362 + }, + { + "epoch": 18.33, + "learning_rate": 3.6206116564475814e-07, + "loss": 0.0018, + "step": 59363 + }, + { + "epoch": 18.33, + "learning_rate": 3.619278219912348e-07, + "loss": 0.0016, + "step": 59364 + }, + { + "epoch": 18.33, + "learning_rate": 3.6179450244428814e-07, + "loss": 0.0013, + "step": 59365 + }, + { + "epoch": 18.33, + "learning_rate": 3.616612070042513e-07, + "loss": 0.0021, + "step": 59366 + }, + { + "epoch": 18.33, + "learning_rate": 3.6152793567145737e-07, + "loss": 0.0016, + "step": 59367 + }, + { + "epoch": 18.33, + "learning_rate": 3.6139468844624046e-07, + "loss": 0.0011, + "step": 59368 + }, + { + "epoch": 18.33, + "learning_rate": 3.612614653289326e-07, + "loss": 0.0018, + "step": 59369 + }, + { + "epoch": 18.33, + "learning_rate": 3.61128266319869e-07, + "loss": 0.0017, + "step": 59370 + }, + { + "epoch": 18.33, + "learning_rate": 3.609950914193816e-07, + "loss": 0.0014, + "step": 59371 + }, + { + "epoch": 18.34, + "learning_rate": 3.6086194062780246e-07, + "loss": 0.0022, + "step": 59372 + }, + { + "epoch": 18.34, + "learning_rate": 3.6072881394546454e-07, + "loss": 0.0021, + "step": 59373 + }, + { + "epoch": 18.34, + "learning_rate": 3.6059571137270434e-07, + "loss": 0.0015, + "step": 59374 + }, + { + "epoch": 18.34, + "learning_rate": 3.604626329098504e-07, + "loss": 0.0015, + "step": 59375 + }, + { + "epoch": 18.34, + "learning_rate": 3.6032957855724027e-07, + "loss": 0.0017, + "step": 59376 + }, + { + "epoch": 18.34, + "learning_rate": 3.6019654831520254e-07, + "loss": 0.0015, + "step": 59377 + }, + { + "epoch": 18.34, + "learning_rate": 3.6006354218407036e-07, + "loss": 0.0016, + "step": 59378 + }, + { + "epoch": 18.34, + "learning_rate": 3.5993056016417784e-07, + "loss": 0.0019, + "step": 59379 + }, + { + "epoch": 18.34, + "learning_rate": 3.5979760225585913e-07, + "loss": 0.001, + "step": 59380 + }, + { + "epoch": 18.34, + "learning_rate": 3.5966466845944404e-07, + "loss": 0.0012, + "step": 59381 + }, + { + "epoch": 18.34, + "learning_rate": 3.595317587752645e-07, + "loss": 0.0018, + "step": 59382 + }, + { + "epoch": 18.34, + "learning_rate": 3.593988732036546e-07, + "loss": 0.0025, + "step": 59383 + }, + { + "epoch": 18.34, + "learning_rate": 3.592660117449476e-07, + "loss": 0.0018, + "step": 59384 + }, + { + "epoch": 18.34, + "learning_rate": 3.5913317439947306e-07, + "loss": 0.0016, + "step": 59385 + }, + { + "epoch": 18.34, + "learning_rate": 3.5900036116756743e-07, + "loss": 0.0016, + "step": 59386 + }, + { + "epoch": 18.34, + "learning_rate": 3.5886757204955933e-07, + "loss": 0.002, + "step": 59387 + }, + { + "epoch": 18.34, + "learning_rate": 3.587348070457808e-07, + "loss": 0.0012, + "step": 59388 + }, + { + "epoch": 18.34, + "learning_rate": 3.586020661565648e-07, + "loss": 0.0021, + "step": 59389 + }, + { + "epoch": 18.34, + "learning_rate": 3.5846934938224445e-07, + "loss": 0.0014, + "step": 59390 + }, + { + "epoch": 18.34, + "learning_rate": 3.5833665672315164e-07, + "loss": 0.002, + "step": 59391 + }, + { + "epoch": 18.34, + "learning_rate": 3.582039881796151e-07, + "loss": 0.0015, + "step": 59392 + }, + { + "epoch": 18.34, + "learning_rate": 3.5807134375197116e-07, + "loss": 0.0018, + "step": 59393 + }, + { + "epoch": 18.34, + "learning_rate": 3.5793872344054736e-07, + "loss": 0.0013, + "step": 59394 + }, + { + "epoch": 18.34, + "learning_rate": 3.5780612724567786e-07, + "loss": 0.0021, + "step": 59395 + }, + { + "epoch": 18.34, + "learning_rate": 3.5767355516769577e-07, + "loss": 0.0022, + "step": 59396 + }, + { + "epoch": 18.34, + "learning_rate": 3.5754100720692963e-07, + "loss": 0.0023, + "step": 59397 + }, + { + "epoch": 18.34, + "learning_rate": 3.5740848336371036e-07, + "loss": 0.0012, + "step": 59398 + }, + { + "epoch": 18.34, + "learning_rate": 3.5727598363837323e-07, + "loss": 0.0018, + "step": 59399 + }, + { + "epoch": 18.34, + "learning_rate": 3.571435080312469e-07, + "loss": 0.0016, + "step": 59400 + }, + { + "epoch": 18.34, + "learning_rate": 3.570110565426643e-07, + "loss": 0.0019, + "step": 59401 + }, + { + "epoch": 18.34, + "learning_rate": 3.5687862917295535e-07, + "loss": 0.0013, + "step": 59402 + }, + { + "epoch": 18.34, + "learning_rate": 3.567462259224508e-07, + "loss": 0.0016, + "step": 59403 + }, + { + "epoch": 18.35, + "learning_rate": 3.566138467914826e-07, + "loss": 0.0013, + "step": 59404 + }, + { + "epoch": 18.35, + "learning_rate": 3.564814917803838e-07, + "loss": 0.0015, + "step": 59405 + }, + { + "epoch": 18.35, + "learning_rate": 3.563491608894831e-07, + "loss": 0.0015, + "step": 59406 + }, + { + "epoch": 18.35, + "learning_rate": 3.5621685411911133e-07, + "loss": 0.0011, + "step": 59407 + }, + { + "epoch": 18.35, + "learning_rate": 3.5608457146960153e-07, + "loss": 0.0012, + "step": 59408 + }, + { + "epoch": 18.35, + "learning_rate": 3.5595231294128117e-07, + "loss": 0.0019, + "step": 59409 + }, + { + "epoch": 18.35, + "learning_rate": 3.5582007853448344e-07, + "loss": 0.0014, + "step": 59410 + }, + { + "epoch": 18.35, + "learning_rate": 3.5568786824953906e-07, + "loss": 0.0013, + "step": 59411 + }, + { + "epoch": 18.35, + "learning_rate": 3.5555568208677894e-07, + "loss": 0.0012, + "step": 59412 + }, + { + "epoch": 18.35, + "learning_rate": 3.554235200465328e-07, + "loss": 0.0015, + "step": 59413 + }, + { + "epoch": 18.35, + "learning_rate": 3.5529138212913037e-07, + "loss": 0.0015, + "step": 59414 + }, + { + "epoch": 18.35, + "learning_rate": 3.5515926833490476e-07, + "loss": 0.0013, + "step": 59415 + }, + { + "epoch": 18.35, + "learning_rate": 3.550271786641846e-07, + "loss": 0.0022, + "step": 59416 + }, + { + "epoch": 18.35, + "learning_rate": 3.548951131172995e-07, + "loss": 0.0015, + "step": 59417 + }, + { + "epoch": 18.35, + "learning_rate": 3.547630716945827e-07, + "loss": 0.0014, + "step": 59418 + }, + { + "epoch": 18.35, + "learning_rate": 3.546310543963616e-07, + "loss": 0.0017, + "step": 59419 + }, + { + "epoch": 18.35, + "learning_rate": 3.5449906122296706e-07, + "loss": 0.0016, + "step": 59420 + }, + { + "epoch": 18.35, + "learning_rate": 3.5436709217473e-07, + "loss": 0.002, + "step": 59421 + }, + { + "epoch": 18.35, + "learning_rate": 3.542351472519812e-07, + "loss": 0.0012, + "step": 59422 + }, + { + "epoch": 18.35, + "learning_rate": 3.5410322645504815e-07, + "loss": 0.0018, + "step": 59423 + }, + { + "epoch": 18.35, + "learning_rate": 3.5397132978426287e-07, + "loss": 0.0017, + "step": 59424 + }, + { + "epoch": 18.35, + "learning_rate": 3.5383945723995394e-07, + "loss": 0.0015, + "step": 59425 + }, + { + "epoch": 18.35, + "learning_rate": 3.537076088224523e-07, + "loss": 0.0019, + "step": 59426 + }, + { + "epoch": 18.35, + "learning_rate": 3.5357578453208865e-07, + "loss": 0.0016, + "step": 59427 + }, + { + "epoch": 18.35, + "learning_rate": 3.534439843691884e-07, + "loss": 0.0017, + "step": 59428 + }, + { + "epoch": 18.35, + "learning_rate": 3.533122083340856e-07, + "loss": 0.002, + "step": 59429 + }, + { + "epoch": 18.35, + "learning_rate": 3.5318045642710906e-07, + "loss": 0.0015, + "step": 59430 + }, + { + "epoch": 18.35, + "learning_rate": 3.530487286485873e-07, + "loss": 0.0017, + "step": 59431 + }, + { + "epoch": 18.35, + "learning_rate": 3.5291702499885007e-07, + "loss": 0.0015, + "step": 59432 + }, + { + "epoch": 18.35, + "learning_rate": 3.5278534547822705e-07, + "loss": 0.0011, + "step": 59433 + }, + { + "epoch": 18.35, + "learning_rate": 3.52653690087047e-07, + "loss": 0.0013, + "step": 59434 + }, + { + "epoch": 18.35, + "learning_rate": 3.525220588256395e-07, + "loss": 0.0017, + "step": 59435 + }, + { + "epoch": 18.35, + "learning_rate": 3.523904516943344e-07, + "loss": 0.0017, + "step": 59436 + }, + { + "epoch": 18.36, + "learning_rate": 3.5225886869346135e-07, + "loss": 0.0015, + "step": 59437 + }, + { + "epoch": 18.36, + "learning_rate": 3.521273098233469e-07, + "loss": 0.001, + "step": 59438 + }, + { + "epoch": 18.36, + "learning_rate": 3.519957750843228e-07, + "loss": 0.0024, + "step": 59439 + }, + { + "epoch": 18.36, + "learning_rate": 3.5186426447671563e-07, + "loss": 0.0014, + "step": 59440 + }, + { + "epoch": 18.36, + "learning_rate": 3.5173277800085614e-07, + "loss": 0.0017, + "step": 59441 + }, + { + "epoch": 18.36, + "learning_rate": 3.51601315657073e-07, + "loss": 0.0019, + "step": 59442 + }, + { + "epoch": 18.36, + "learning_rate": 3.5146987744569597e-07, + "loss": 0.0015, + "step": 59443 + }, + { + "epoch": 18.36, + "learning_rate": 3.5133846336705024e-07, + "loss": 0.0017, + "step": 59444 + }, + { + "epoch": 18.36, + "learning_rate": 3.512070734214679e-07, + "loss": 0.0021, + "step": 59445 + }, + { + "epoch": 18.36, + "learning_rate": 3.5107570760927634e-07, + "loss": 0.0018, + "step": 59446 + }, + { + "epoch": 18.36, + "learning_rate": 3.509443659308054e-07, + "loss": 0.0023, + "step": 59447 + }, + { + "epoch": 18.36, + "learning_rate": 3.5081304838638143e-07, + "loss": 0.0015, + "step": 59448 + }, + { + "epoch": 18.36, + "learning_rate": 3.506817549763342e-07, + "loss": 0.0017, + "step": 59449 + }, + { + "epoch": 18.36, + "learning_rate": 3.5055048570099116e-07, + "loss": 0.0017, + "step": 59450 + }, + { + "epoch": 18.36, + "learning_rate": 3.50419240560681e-07, + "loss": 0.0016, + "step": 59451 + }, + { + "epoch": 18.36, + "learning_rate": 3.5028801955573346e-07, + "loss": 0.0012, + "step": 59452 + }, + { + "epoch": 18.36, + "learning_rate": 3.50156822686476e-07, + "loss": 0.0017, + "step": 59453 + }, + { + "epoch": 18.36, + "learning_rate": 3.5002564995323506e-07, + "loss": 0.0022, + "step": 59454 + }, + { + "epoch": 18.36, + "learning_rate": 3.498945013563415e-07, + "loss": 0.0019, + "step": 59455 + }, + { + "epoch": 18.36, + "learning_rate": 3.497633768961195e-07, + "loss": 0.0012, + "step": 59456 + }, + { + "epoch": 18.36, + "learning_rate": 3.496322765729021e-07, + "loss": 0.0016, + "step": 59457 + }, + { + "epoch": 18.36, + "learning_rate": 3.495012003870135e-07, + "loss": 0.002, + "step": 59458 + }, + { + "epoch": 18.36, + "learning_rate": 3.493701483387812e-07, + "loss": 0.0017, + "step": 59459 + }, + { + "epoch": 18.36, + "learning_rate": 3.4923912042853504e-07, + "loss": 0.0015, + "step": 59460 + }, + { + "epoch": 18.36, + "learning_rate": 3.491081166566024e-07, + "loss": 0.0021, + "step": 59461 + }, + { + "epoch": 18.36, + "learning_rate": 3.489771370233108e-07, + "loss": 0.0021, + "step": 59462 + }, + { + "epoch": 18.36, + "learning_rate": 3.4884618152898787e-07, + "loss": 0.0013, + "step": 59463 + }, + { + "epoch": 18.36, + "learning_rate": 3.48715250173961e-07, + "loss": 0.0016, + "step": 59464 + }, + { + "epoch": 18.36, + "learning_rate": 3.4858434295855557e-07, + "loss": 0.0018, + "step": 59465 + }, + { + "epoch": 18.36, + "learning_rate": 3.4845345988310244e-07, + "loss": 0.0016, + "step": 59466 + }, + { + "epoch": 18.36, + "learning_rate": 3.483226009479279e-07, + "loss": 0.0016, + "step": 59467 + }, + { + "epoch": 18.36, + "learning_rate": 3.481917661533585e-07, + "loss": 0.0015, + "step": 59468 + }, + { + "epoch": 18.37, + "learning_rate": 3.480609554997216e-07, + "loss": 0.0021, + "step": 59469 + }, + { + "epoch": 18.37, + "learning_rate": 3.479301689873449e-07, + "loss": 0.0018, + "step": 59470 + }, + { + "epoch": 18.37, + "learning_rate": 3.4779940661655464e-07, + "loss": 0.0012, + "step": 59471 + }, + { + "epoch": 18.37, + "learning_rate": 3.4766866838767843e-07, + "loss": 0.0015, + "step": 59472 + }, + { + "epoch": 18.37, + "learning_rate": 3.4753795430104487e-07, + "loss": 0.0013, + "step": 59473 + }, + { + "epoch": 18.37, + "learning_rate": 3.4740726435697927e-07, + "loss": 0.0012, + "step": 59474 + }, + { + "epoch": 18.37, + "learning_rate": 3.472765985558069e-07, + "loss": 0.0016, + "step": 59475 + }, + { + "epoch": 18.37, + "learning_rate": 3.4714595689785855e-07, + "loss": 0.0014, + "step": 59476 + }, + { + "epoch": 18.37, + "learning_rate": 3.4701533938345634e-07, + "loss": 0.0014, + "step": 59477 + }, + { + "epoch": 18.37, + "learning_rate": 3.4688474601293097e-07, + "loss": 0.0015, + "step": 59478 + }, + { + "epoch": 18.37, + "learning_rate": 3.4675417678660674e-07, + "loss": 0.0014, + "step": 59479 + }, + { + "epoch": 18.37, + "learning_rate": 3.4662363170481215e-07, + "loss": 0.0022, + "step": 59480 + }, + { + "epoch": 18.37, + "learning_rate": 3.464931107678704e-07, + "loss": 0.0016, + "step": 59481 + }, + { + "epoch": 18.37, + "learning_rate": 3.463626139761112e-07, + "loss": 0.0016, + "step": 59482 + }, + { + "epoch": 18.37, + "learning_rate": 3.462321413298608e-07, + "loss": 0.0023, + "step": 59483 + }, + { + "epoch": 18.37, + "learning_rate": 3.461016928294436e-07, + "loss": 0.0014, + "step": 59484 + }, + { + "epoch": 18.37, + "learning_rate": 3.459712684751859e-07, + "loss": 0.0018, + "step": 59485 + }, + { + "epoch": 18.37, + "learning_rate": 3.4584086826741746e-07, + "loss": 0.002, + "step": 59486 + }, + { + "epoch": 18.37, + "learning_rate": 3.457104922064591e-07, + "loss": 0.0019, + "step": 59487 + }, + { + "epoch": 18.37, + "learning_rate": 3.4558014029264176e-07, + "loss": 0.0011, + "step": 59488 + }, + { + "epoch": 18.37, + "learning_rate": 3.454498125262884e-07, + "loss": 0.0017, + "step": 59489 + }, + { + "epoch": 18.37, + "learning_rate": 3.453195089077255e-07, + "loss": 0.0011, + "step": 59490 + }, + { + "epoch": 18.37, + "learning_rate": 3.4518922943727826e-07, + "loss": 0.002, + "step": 59491 + }, + { + "epoch": 18.37, + "learning_rate": 3.4505897411527656e-07, + "loss": 0.0013, + "step": 59492 + }, + { + "epoch": 18.37, + "learning_rate": 3.4492874294204113e-07, + "loss": 0.0023, + "step": 59493 + }, + { + "epoch": 18.37, + "learning_rate": 3.447985359179007e-07, + "loss": 0.0016, + "step": 59494 + }, + { + "epoch": 18.37, + "learning_rate": 3.4466835304318156e-07, + "loss": 0.0021, + "step": 59495 + }, + { + "epoch": 18.37, + "learning_rate": 3.4453819431820577e-07, + "loss": 0.0016, + "step": 59496 + }, + { + "epoch": 18.37, + "learning_rate": 3.4440805974330084e-07, + "loss": 0.0018, + "step": 59497 + }, + { + "epoch": 18.37, + "learning_rate": 3.442779493187942e-07, + "loss": 0.0013, + "step": 59498 + }, + { + "epoch": 18.37, + "learning_rate": 3.44147863045009e-07, + "loss": 0.0019, + "step": 59499 + }, + { + "epoch": 18.37, + "learning_rate": 3.440178009222694e-07, + "loss": 0.0016, + "step": 59500 + }, + { + "epoch": 18.37, + "learning_rate": 3.438877629509041e-07, + "loss": 0.0014, + "step": 59501 + }, + { + "epoch": 18.38, + "learning_rate": 3.4375774913123605e-07, + "loss": 0.0016, + "step": 59502 + }, + { + "epoch": 18.38, + "learning_rate": 3.436277594635906e-07, + "loss": 0.0016, + "step": 59503 + }, + { + "epoch": 18.38, + "learning_rate": 3.434977939482964e-07, + "loss": 0.0016, + "step": 59504 + }, + { + "epoch": 18.38, + "learning_rate": 3.4336785258567206e-07, + "loss": 0.0013, + "step": 59505 + }, + { + "epoch": 18.38, + "learning_rate": 3.4323793537604623e-07, + "loss": 0.0015, + "step": 59506 + }, + { + "epoch": 18.38, + "learning_rate": 3.4310804231974525e-07, + "loss": 0.0016, + "step": 59507 + }, + { + "epoch": 18.38, + "learning_rate": 3.4297817341709115e-07, + "loss": 0.0015, + "step": 59508 + }, + { + "epoch": 18.38, + "learning_rate": 3.428483286684103e-07, + "loss": 0.0016, + "step": 59509 + }, + { + "epoch": 18.38, + "learning_rate": 3.4271850807402695e-07, + "loss": 0.0014, + "step": 59510 + }, + { + "epoch": 18.38, + "learning_rate": 3.425887116342663e-07, + "loss": 0.0015, + "step": 59511 + }, + { + "epoch": 18.38, + "learning_rate": 3.4245893934945263e-07, + "loss": 0.0013, + "step": 59512 + }, + { + "epoch": 18.38, + "learning_rate": 3.423291912199089e-07, + "loss": 0.0016, + "step": 59513 + }, + { + "epoch": 18.38, + "learning_rate": 3.42199467245965e-07, + "loss": 0.0013, + "step": 59514 + }, + { + "epoch": 18.38, + "learning_rate": 3.420697674279394e-07, + "loss": 0.0015, + "step": 59515 + }, + { + "epoch": 18.38, + "learning_rate": 3.4194009176615863e-07, + "loss": 0.0017, + "step": 59516 + }, + { + "epoch": 18.38, + "learning_rate": 3.418104402609479e-07, + "loss": 0.0015, + "step": 59517 + }, + { + "epoch": 18.38, + "learning_rate": 3.416808129126292e-07, + "loss": 0.0036, + "step": 59518 + }, + { + "epoch": 18.38, + "learning_rate": 3.4155120972153123e-07, + "loss": 0.0015, + "step": 59519 + }, + { + "epoch": 18.38, + "learning_rate": 3.4142163068797364e-07, + "loss": 0.0016, + "step": 59520 + }, + { + "epoch": 18.38, + "learning_rate": 3.4129207581228174e-07, + "loss": 0.002, + "step": 59521 + }, + { + "epoch": 18.38, + "learning_rate": 3.4116254509477974e-07, + "loss": 0.0014, + "step": 59522 + }, + { + "epoch": 18.38, + "learning_rate": 3.4103303853579295e-07, + "loss": 0.0015, + "step": 59523 + }, + { + "epoch": 18.38, + "learning_rate": 3.409035561356444e-07, + "loss": 0.0018, + "step": 59524 + }, + { + "epoch": 18.38, + "learning_rate": 3.407740978946572e-07, + "loss": 0.0015, + "step": 59525 + }, + { + "epoch": 18.38, + "learning_rate": 3.4064466381315664e-07, + "loss": 0.0017, + "step": 59526 + }, + { + "epoch": 18.38, + "learning_rate": 3.4051525389146355e-07, + "loss": 0.0015, + "step": 59527 + }, + { + "epoch": 18.38, + "learning_rate": 3.403858681299044e-07, + "loss": 0.0015, + "step": 59528 + }, + { + "epoch": 18.38, + "learning_rate": 3.402565065288033e-07, + "loss": 0.0017, + "step": 59529 + }, + { + "epoch": 18.38, + "learning_rate": 3.401271690884811e-07, + "loss": 0.0013, + "step": 59530 + }, + { + "epoch": 18.38, + "learning_rate": 3.3999785580926314e-07, + "loss": 0.0012, + "step": 59531 + }, + { + "epoch": 18.38, + "learning_rate": 3.398685666914725e-07, + "loss": 0.0018, + "step": 59532 + }, + { + "epoch": 18.38, + "learning_rate": 3.3973930173543223e-07, + "loss": 0.0023, + "step": 59533 + }, + { + "epoch": 18.39, + "learning_rate": 3.3961006094146655e-07, + "loss": 0.0017, + "step": 59534 + }, + { + "epoch": 18.39, + "learning_rate": 3.3948084430989845e-07, + "loss": 0.0016, + "step": 59535 + }, + { + "epoch": 18.39, + "learning_rate": 3.393516518410489e-07, + "loss": 0.0014, + "step": 59536 + }, + { + "epoch": 18.39, + "learning_rate": 3.3922248353524313e-07, + "loss": 0.0012, + "step": 59537 + }, + { + "epoch": 18.39, + "learning_rate": 3.390933393928053e-07, + "loss": 0.0022, + "step": 59538 + }, + { + "epoch": 18.39, + "learning_rate": 3.3896421941405524e-07, + "loss": 0.0013, + "step": 59539 + }, + { + "epoch": 18.39, + "learning_rate": 3.3883512359931925e-07, + "loss": 0.0017, + "step": 59540 + }, + { + "epoch": 18.39, + "learning_rate": 3.387060519489194e-07, + "loss": 0.0013, + "step": 59541 + }, + { + "epoch": 18.39, + "learning_rate": 3.3857700446317645e-07, + "loss": 0.0018, + "step": 59542 + }, + { + "epoch": 18.39, + "learning_rate": 3.384479811424135e-07, + "loss": 0.0014, + "step": 59543 + }, + { + "epoch": 18.39, + "learning_rate": 3.383189819869548e-07, + "loss": 0.0023, + "step": 59544 + }, + { + "epoch": 18.39, + "learning_rate": 3.3819000699712555e-07, + "loss": 0.0014, + "step": 59545 + }, + { + "epoch": 18.39, + "learning_rate": 3.3806105617324224e-07, + "loss": 0.0021, + "step": 59546 + }, + { + "epoch": 18.39, + "learning_rate": 3.3793212951563126e-07, + "loss": 0.0015, + "step": 59547 + }, + { + "epoch": 18.39, + "learning_rate": 3.3780322702461454e-07, + "loss": 0.0017, + "step": 59548 + }, + { + "epoch": 18.39, + "learning_rate": 3.3767434870051295e-07, + "loss": 0.0016, + "step": 59549 + }, + { + "epoch": 18.39, + "learning_rate": 3.375454945436518e-07, + "loss": 0.0016, + "step": 59550 + }, + { + "epoch": 18.39, + "learning_rate": 3.3741666455435197e-07, + "loss": 0.0012, + "step": 59551 + }, + { + "epoch": 18.39, + "learning_rate": 3.3728785873293426e-07, + "loss": 0.0014, + "step": 59552 + }, + { + "epoch": 18.39, + "learning_rate": 3.3715907707972065e-07, + "loss": 0.0013, + "step": 59553 + }, + { + "epoch": 18.39, + "learning_rate": 3.370303195950375e-07, + "loss": 0.0017, + "step": 59554 + }, + { + "epoch": 18.39, + "learning_rate": 3.3690158627920243e-07, + "loss": 0.0016, + "step": 59555 + }, + { + "epoch": 18.39, + "learning_rate": 3.367728771325385e-07, + "loss": 0.0016, + "step": 59556 + }, + { + "epoch": 18.39, + "learning_rate": 3.366441921553698e-07, + "loss": 0.0014, + "step": 59557 + }, + { + "epoch": 18.39, + "learning_rate": 3.3651553134801396e-07, + "loss": 0.0014, + "step": 59558 + }, + { + "epoch": 18.39, + "learning_rate": 3.3638689471079624e-07, + "loss": 0.0025, + "step": 59559 + }, + { + "epoch": 18.39, + "learning_rate": 3.3625828224403854e-07, + "loss": 0.0017, + "step": 59560 + }, + { + "epoch": 18.39, + "learning_rate": 3.3612969394806183e-07, + "loss": 0.0019, + "step": 59561 + }, + { + "epoch": 18.39, + "learning_rate": 3.360011298231847e-07, + "loss": 0.0011, + "step": 59562 + }, + { + "epoch": 18.39, + "learning_rate": 3.3587258986973345e-07, + "loss": 0.002, + "step": 59563 + }, + { + "epoch": 18.39, + "learning_rate": 3.357440740880269e-07, + "loss": 0.0014, + "step": 59564 + }, + { + "epoch": 18.39, + "learning_rate": 3.356155824783869e-07, + "loss": 0.0021, + "step": 59565 + }, + { + "epoch": 18.4, + "learning_rate": 3.3548711504113654e-07, + "loss": 0.0019, + "step": 59566 + }, + { + "epoch": 18.4, + "learning_rate": 3.353586717765933e-07, + "loss": 0.0016, + "step": 59567 + }, + { + "epoch": 18.4, + "learning_rate": 3.3523025268508144e-07, + "loss": 0.0011, + "step": 59568 + }, + { + "epoch": 18.4, + "learning_rate": 3.3510185776692183e-07, + "loss": 0.0017, + "step": 59569 + }, + { + "epoch": 18.4, + "learning_rate": 3.3497348702243413e-07, + "loss": 0.0022, + "step": 59570 + }, + { + "epoch": 18.4, + "learning_rate": 3.348451404519426e-07, + "loss": 0.0014, + "step": 59571 + }, + { + "epoch": 18.4, + "learning_rate": 3.347168180557658e-07, + "loss": 0.0011, + "step": 59572 + }, + { + "epoch": 18.4, + "learning_rate": 3.345885198342236e-07, + "loss": 0.0015, + "step": 59573 + }, + { + "epoch": 18.4, + "learning_rate": 3.344602457876389e-07, + "loss": 0.0015, + "step": 59574 + }, + { + "epoch": 18.4, + "learning_rate": 3.3433199591633267e-07, + "loss": 0.0015, + "step": 59575 + }, + { + "epoch": 18.4, + "learning_rate": 3.342037702206247e-07, + "loss": 0.0017, + "step": 59576 + }, + { + "epoch": 18.4, + "learning_rate": 3.340755687008357e-07, + "loss": 0.0021, + "step": 59577 + }, + { + "epoch": 18.4, + "learning_rate": 3.339473913572866e-07, + "loss": 0.0015, + "step": 59578 + }, + { + "epoch": 18.4, + "learning_rate": 3.338192381902983e-07, + "loss": 0.0017, + "step": 59579 + }, + { + "epoch": 18.4, + "learning_rate": 3.3369110920019043e-07, + "loss": 0.0016, + "step": 59580 + }, + { + "epoch": 18.4, + "learning_rate": 3.335630043872851e-07, + "loss": 0.0015, + "step": 59581 + }, + { + "epoch": 18.4, + "learning_rate": 3.33434923751903e-07, + "loss": 0.0018, + "step": 59582 + }, + { + "epoch": 18.4, + "learning_rate": 3.333068672943607e-07, + "loss": 0.0014, + "step": 59583 + }, + { + "epoch": 18.4, + "learning_rate": 3.331788350149812e-07, + "loss": 0.001, + "step": 59584 + }, + { + "epoch": 18.4, + "learning_rate": 3.330508269140864e-07, + "loss": 0.0013, + "step": 59585 + }, + { + "epoch": 18.4, + "learning_rate": 3.3292284299199393e-07, + "loss": 0.0017, + "step": 59586 + }, + { + "epoch": 18.4, + "learning_rate": 3.3279488324902354e-07, + "loss": 0.0014, + "step": 59587 + }, + { + "epoch": 18.4, + "learning_rate": 3.326669476854971e-07, + "loss": 0.0025, + "step": 59588 + }, + { + "epoch": 18.4, + "learning_rate": 3.3253903630173334e-07, + "loss": 0.002, + "step": 59589 + }, + { + "epoch": 18.4, + "learning_rate": 3.3241114909805305e-07, + "loss": 0.0012, + "step": 59590 + }, + { + "epoch": 18.4, + "learning_rate": 3.32283286074776e-07, + "loss": 0.0019, + "step": 59591 + }, + { + "epoch": 18.4, + "learning_rate": 3.3215544723222195e-07, + "loss": 0.0014, + "step": 59592 + }, + { + "epoch": 18.4, + "learning_rate": 3.320276325707095e-07, + "loss": 0.0018, + "step": 59593 + }, + { + "epoch": 18.4, + "learning_rate": 3.318998420905606e-07, + "loss": 0.0018, + "step": 59594 + }, + { + "epoch": 18.4, + "learning_rate": 3.317720757920917e-07, + "loss": 0.002, + "step": 59595 + }, + { + "epoch": 18.4, + "learning_rate": 3.316443336756259e-07, + "loss": 0.0017, + "step": 59596 + }, + { + "epoch": 18.4, + "learning_rate": 3.3151661574148173e-07, + "loss": 0.002, + "step": 59597 + }, + { + "epoch": 18.4, + "learning_rate": 3.3138892198997575e-07, + "loss": 0.0015, + "step": 59598 + }, + { + "epoch": 18.41, + "learning_rate": 3.312612524214298e-07, + "loss": 0.002, + "step": 59599 + }, + { + "epoch": 18.41, + "learning_rate": 3.311336070361637e-07, + "loss": 0.0013, + "step": 59600 + }, + { + "epoch": 18.41, + "learning_rate": 3.3100598583449495e-07, + "loss": 0.0014, + "step": 59601 + }, + { + "epoch": 18.41, + "learning_rate": 3.308783888167455e-07, + "loss": 0.002, + "step": 59602 + }, + { + "epoch": 18.41, + "learning_rate": 3.307508159832318e-07, + "loss": 0.0019, + "step": 59603 + }, + { + "epoch": 18.41, + "learning_rate": 3.3062326733427353e-07, + "loss": 0.0014, + "step": 59604 + }, + { + "epoch": 18.41, + "learning_rate": 3.3049574287018936e-07, + "loss": 0.0019, + "step": 59605 + }, + { + "epoch": 18.41, + "learning_rate": 3.303682425913013e-07, + "loss": 0.0015, + "step": 59606 + }, + { + "epoch": 18.41, + "learning_rate": 3.3024076649792456e-07, + "loss": 0.0022, + "step": 59607 + }, + { + "epoch": 18.41, + "learning_rate": 3.30113314590379e-07, + "loss": 0.0012, + "step": 59608 + }, + { + "epoch": 18.41, + "learning_rate": 3.2998588686898313e-07, + "loss": 0.0012, + "step": 59609 + }, + { + "epoch": 18.41, + "learning_rate": 3.298584833340579e-07, + "loss": 0.0011, + "step": 59610 + }, + { + "epoch": 18.41, + "learning_rate": 3.2973110398591856e-07, + "loss": 0.001, + "step": 59611 + }, + { + "epoch": 18.41, + "learning_rate": 3.296037488248871e-07, + "loss": 0.0014, + "step": 59612 + }, + { + "epoch": 18.41, + "learning_rate": 3.2947641785127995e-07, + "loss": 0.0015, + "step": 59613 + }, + { + "epoch": 18.41, + "learning_rate": 3.293491110654157e-07, + "loss": 0.002, + "step": 59614 + }, + { + "epoch": 18.41, + "learning_rate": 3.2922182846761295e-07, + "loss": 0.0014, + "step": 59615 + }, + { + "epoch": 18.41, + "learning_rate": 3.290945700581916e-07, + "loss": 0.0018, + "step": 59616 + }, + { + "epoch": 18.41, + "learning_rate": 3.2896733583746786e-07, + "loss": 0.0018, + "step": 59617 + }, + { + "epoch": 18.41, + "learning_rate": 3.288401258057594e-07, + "loss": 0.0016, + "step": 59618 + }, + { + "epoch": 18.41, + "learning_rate": 3.2871293996338817e-07, + "loss": 0.0022, + "step": 59619 + }, + { + "epoch": 18.41, + "learning_rate": 3.2858577831066716e-07, + "loss": 0.0013, + "step": 59620 + }, + { + "epoch": 18.41, + "learning_rate": 3.2845864084791736e-07, + "loss": 0.0016, + "step": 59621 + }, + { + "epoch": 18.41, + "learning_rate": 3.283315275754595e-07, + "loss": 0.0018, + "step": 59622 + }, + { + "epoch": 18.41, + "learning_rate": 3.2820443849360564e-07, + "loss": 0.0015, + "step": 59623 + }, + { + "epoch": 18.41, + "learning_rate": 3.2807737360267766e-07, + "loss": 0.0018, + "step": 59624 + }, + { + "epoch": 18.41, + "learning_rate": 3.2795033290299203e-07, + "loss": 0.0016, + "step": 59625 + }, + { + "epoch": 18.41, + "learning_rate": 3.278233163948663e-07, + "loss": 0.0019, + "step": 59626 + }, + { + "epoch": 18.41, + "learning_rate": 3.2769632407861907e-07, + "loss": 0.0024, + "step": 59627 + }, + { + "epoch": 18.41, + "learning_rate": 3.2756935595456786e-07, + "loss": 0.0015, + "step": 59628 + }, + { + "epoch": 18.41, + "learning_rate": 3.2744241202302795e-07, + "loss": 0.0022, + "step": 59629 + }, + { + "epoch": 18.41, + "learning_rate": 3.2731549228431916e-07, + "loss": 0.0018, + "step": 59630 + }, + { + "epoch": 18.42, + "learning_rate": 3.2718859673876e-07, + "loss": 0.0024, + "step": 59631 + }, + { + "epoch": 18.42, + "learning_rate": 3.270617253866648e-07, + "loss": 0.0015, + "step": 59632 + }, + { + "epoch": 18.42, + "learning_rate": 3.2693487822835435e-07, + "loss": 0.0017, + "step": 59633 + }, + { + "epoch": 18.42, + "learning_rate": 3.2680805526414393e-07, + "loss": 0.0016, + "step": 59634 + }, + { + "epoch": 18.42, + "learning_rate": 3.266812564943489e-07, + "loss": 0.0012, + "step": 59635 + }, + { + "epoch": 18.42, + "learning_rate": 3.2655448191928896e-07, + "loss": 0.0016, + "step": 59636 + }, + { + "epoch": 18.42, + "learning_rate": 3.2642773153928165e-07, + "loss": 0.0015, + "step": 59637 + }, + { + "epoch": 18.42, + "learning_rate": 3.2630100535464226e-07, + "loss": 0.0013, + "step": 59638 + }, + { + "epoch": 18.42, + "learning_rate": 3.261743033656883e-07, + "loss": 0.0019, + "step": 59639 + }, + { + "epoch": 18.42, + "learning_rate": 3.260476255727363e-07, + "loss": 0.0023, + "step": 59640 + }, + { + "epoch": 18.42, + "learning_rate": 3.2592097197610475e-07, + "loss": 0.0019, + "step": 59641 + }, + { + "epoch": 18.42, + "learning_rate": 3.2579434257610785e-07, + "loss": 0.0015, + "step": 59642 + }, + { + "epoch": 18.42, + "learning_rate": 3.2566773737306547e-07, + "loss": 0.0021, + "step": 59643 + }, + { + "epoch": 18.42, + "learning_rate": 3.2554115636729164e-07, + "loss": 0.0019, + "step": 59644 + }, + { + "epoch": 18.42, + "learning_rate": 3.2541459955910406e-07, + "loss": 0.0017, + "step": 59645 + }, + { + "epoch": 18.42, + "learning_rate": 3.252880669488179e-07, + "loss": 0.0014, + "step": 59646 + }, + { + "epoch": 18.42, + "learning_rate": 3.251615585367529e-07, + "loss": 0.0016, + "step": 59647 + }, + { + "epoch": 18.42, + "learning_rate": 3.2503507432322335e-07, + "loss": 0.0015, + "step": 59648 + }, + { + "epoch": 18.42, + "learning_rate": 3.249086143085445e-07, + "loss": 0.0018, + "step": 59649 + }, + { + "epoch": 18.42, + "learning_rate": 3.2478217849303383e-07, + "loss": 0.0015, + "step": 59650 + }, + { + "epoch": 18.42, + "learning_rate": 3.2465576687700785e-07, + "loss": 0.0017, + "step": 59651 + }, + { + "epoch": 18.42, + "learning_rate": 3.2452937946078177e-07, + "loss": 0.0015, + "step": 59652 + }, + { + "epoch": 18.42, + "learning_rate": 3.244030162446754e-07, + "loss": 0.0019, + "step": 59653 + }, + { + "epoch": 18.42, + "learning_rate": 3.242766772289985e-07, + "loss": 0.0023, + "step": 59654 + }, + { + "epoch": 18.42, + "learning_rate": 3.241503624140707e-07, + "loss": 0.002, + "step": 59655 + }, + { + "epoch": 18.42, + "learning_rate": 3.2402407180020966e-07, + "loss": 0.0016, + "step": 59656 + }, + { + "epoch": 18.42, + "learning_rate": 3.238978053877273e-07, + "loss": 0.0021, + "step": 59657 + }, + { + "epoch": 18.42, + "learning_rate": 3.2377156317694227e-07, + "loss": 0.0019, + "step": 59658 + }, + { + "epoch": 18.42, + "learning_rate": 3.2364534516816983e-07, + "loss": 0.0017, + "step": 59659 + }, + { + "epoch": 18.42, + "learning_rate": 3.2351915136172417e-07, + "loss": 0.0013, + "step": 59660 + }, + { + "epoch": 18.42, + "learning_rate": 3.233929817579218e-07, + "loss": 0.0016, + "step": 59661 + }, + { + "epoch": 18.42, + "learning_rate": 3.23266836357079e-07, + "loss": 0.0015, + "step": 59662 + }, + { + "epoch": 18.42, + "learning_rate": 3.231407151595112e-07, + "loss": 0.0014, + "step": 59663 + }, + { + "epoch": 18.43, + "learning_rate": 3.230146181655325e-07, + "loss": 0.0019, + "step": 59664 + }, + { + "epoch": 18.43, + "learning_rate": 3.2288854537546045e-07, + "loss": 0.0014, + "step": 59665 + }, + { + "epoch": 18.43, + "learning_rate": 3.2276249678960815e-07, + "loss": 0.0015, + "step": 59666 + }, + { + "epoch": 18.43, + "learning_rate": 3.226364724082909e-07, + "loss": 0.0014, + "step": 59667 + }, + { + "epoch": 18.43, + "learning_rate": 3.225104722318273e-07, + "loss": 0.0014, + "step": 59668 + }, + { + "epoch": 18.43, + "learning_rate": 3.2238449626052934e-07, + "loss": 0.002, + "step": 59669 + }, + { + "epoch": 18.43, + "learning_rate": 3.222585444947113e-07, + "loss": 0.0025, + "step": 59670 + }, + { + "epoch": 18.43, + "learning_rate": 3.2213261693469165e-07, + "loss": 0.002, + "step": 59671 + }, + { + "epoch": 18.43, + "learning_rate": 3.2200671358078137e-07, + "loss": 0.0017, + "step": 59672 + }, + { + "epoch": 18.43, + "learning_rate": 3.218808344333002e-07, + "loss": 0.0018, + "step": 59673 + }, + { + "epoch": 18.43, + "learning_rate": 3.2175497949255785e-07, + "loss": 0.0015, + "step": 59674 + }, + { + "epoch": 18.43, + "learning_rate": 3.2162914875887295e-07, + "loss": 0.0015, + "step": 59675 + }, + { + "epoch": 18.43, + "learning_rate": 3.215033422325575e-07, + "loss": 0.0018, + "step": 59676 + }, + { + "epoch": 18.43, + "learning_rate": 3.213775599139279e-07, + "loss": 0.0019, + "step": 59677 + }, + { + "epoch": 18.43, + "learning_rate": 3.212518018032984e-07, + "loss": 0.0018, + "step": 59678 + }, + { + "epoch": 18.43, + "learning_rate": 3.211260679009842e-07, + "loss": 0.0016, + "step": 59679 + }, + { + "epoch": 18.43, + "learning_rate": 3.2100035820729845e-07, + "loss": 0.0017, + "step": 59680 + }, + { + "epoch": 18.43, + "learning_rate": 3.208746727225565e-07, + "loss": 0.0016, + "step": 59681 + }, + { + "epoch": 18.43, + "learning_rate": 3.2074901144707126e-07, + "loss": 0.0018, + "step": 59682 + }, + { + "epoch": 18.43, + "learning_rate": 3.206233743811593e-07, + "loss": 0.0016, + "step": 59683 + }, + { + "epoch": 18.43, + "learning_rate": 3.2049776152513366e-07, + "loss": 0.0026, + "step": 59684 + }, + { + "epoch": 18.43, + "learning_rate": 3.2037217287930744e-07, + "loss": 0.0012, + "step": 59685 + }, + { + "epoch": 18.43, + "learning_rate": 3.2024660844399593e-07, + "loss": 0.0011, + "step": 59686 + }, + { + "epoch": 18.43, + "learning_rate": 3.201210682195144e-07, + "loss": 0.0018, + "step": 59687 + }, + { + "epoch": 18.43, + "learning_rate": 3.199955522061748e-07, + "loss": 0.0013, + "step": 59688 + }, + { + "epoch": 18.43, + "learning_rate": 3.1987006040429256e-07, + "loss": 0.0015, + "step": 59689 + }, + { + "epoch": 18.43, + "learning_rate": 3.197445928141807e-07, + "loss": 0.0016, + "step": 59690 + }, + { + "epoch": 18.43, + "learning_rate": 3.1961914943615223e-07, + "loss": 0.0014, + "step": 59691 + }, + { + "epoch": 18.43, + "learning_rate": 3.1949373027052145e-07, + "loss": 0.002, + "step": 59692 + }, + { + "epoch": 18.43, + "learning_rate": 3.193683353176036e-07, + "loss": 0.0018, + "step": 59693 + }, + { + "epoch": 18.43, + "learning_rate": 3.192429645777118e-07, + "loss": 0.0012, + "step": 59694 + }, + { + "epoch": 18.43, + "learning_rate": 3.1911761805115793e-07, + "loss": 0.0012, + "step": 59695 + }, + { + "epoch": 18.44, + "learning_rate": 3.189922957382574e-07, + "loss": 0.0009, + "step": 59696 + }, + { + "epoch": 18.44, + "learning_rate": 3.1886699763932105e-07, + "loss": 0.0019, + "step": 59697 + }, + { + "epoch": 18.44, + "learning_rate": 3.187417237546653e-07, + "loss": 0.0019, + "step": 59698 + }, + { + "epoch": 18.44, + "learning_rate": 3.1861647408460207e-07, + "loss": 0.0018, + "step": 59699 + }, + { + "epoch": 18.44, + "learning_rate": 3.184912486294456e-07, + "loss": 0.0014, + "step": 59700 + }, + { + "epoch": 18.44, + "learning_rate": 3.183660473895078e-07, + "loss": 0.0015, + "step": 59701 + }, + { + "epoch": 18.44, + "learning_rate": 3.1824087036510185e-07, + "loss": 0.0016, + "step": 59702 + }, + { + "epoch": 18.44, + "learning_rate": 3.181157175565419e-07, + "loss": 0.002, + "step": 59703 + }, + { + "epoch": 18.44, + "learning_rate": 3.1799058896413993e-07, + "loss": 0.0015, + "step": 59704 + }, + { + "epoch": 18.44, + "learning_rate": 3.178654845882112e-07, + "loss": 0.0019, + "step": 59705 + }, + { + "epoch": 18.44, + "learning_rate": 3.177404044290644e-07, + "loss": 0.0015, + "step": 59706 + }, + { + "epoch": 18.44, + "learning_rate": 3.176153484870148e-07, + "loss": 0.0018, + "step": 59707 + }, + { + "epoch": 18.44, + "learning_rate": 3.174903167623755e-07, + "loss": 0.0019, + "step": 59708 + }, + { + "epoch": 18.44, + "learning_rate": 3.173653092554596e-07, + "loss": 0.0025, + "step": 59709 + }, + { + "epoch": 18.44, + "learning_rate": 3.172403259665802e-07, + "loss": 0.0015, + "step": 59710 + }, + { + "epoch": 18.44, + "learning_rate": 3.171153668960458e-07, + "loss": 0.002, + "step": 59711 + }, + { + "epoch": 18.44, + "learning_rate": 3.169904320441741e-07, + "loss": 0.0015, + "step": 59712 + }, + { + "epoch": 18.44, + "learning_rate": 3.168655214112748e-07, + "loss": 0.0013, + "step": 59713 + }, + { + "epoch": 18.44, + "learning_rate": 3.1674063499766207e-07, + "loss": 0.0016, + "step": 59714 + }, + { + "epoch": 18.44, + "learning_rate": 3.1661577280364564e-07, + "loss": 0.0016, + "step": 59715 + }, + { + "epoch": 18.44, + "learning_rate": 3.1649093482953976e-07, + "loss": 0.0022, + "step": 59716 + }, + { + "epoch": 18.44, + "learning_rate": 3.163661210756552e-07, + "loss": 0.0017, + "step": 59717 + }, + { + "epoch": 18.44, + "learning_rate": 3.162413315423063e-07, + "loss": 0.0013, + "step": 59718 + }, + { + "epoch": 18.44, + "learning_rate": 3.161165662298038e-07, + "loss": 0.0017, + "step": 59719 + }, + { + "epoch": 18.44, + "learning_rate": 3.1599182513846084e-07, + "loss": 0.0014, + "step": 59720 + }, + { + "epoch": 18.44, + "learning_rate": 3.1586710826858824e-07, + "loss": 0.0014, + "step": 59721 + }, + { + "epoch": 18.44, + "learning_rate": 3.157424156204969e-07, + "loss": 0.0019, + "step": 59722 + }, + { + "epoch": 18.44, + "learning_rate": 3.15617747194501e-07, + "loss": 0.0016, + "step": 59723 + }, + { + "epoch": 18.44, + "learning_rate": 3.154931029909114e-07, + "loss": 0.0013, + "step": 59724 + }, + { + "epoch": 18.44, + "learning_rate": 3.153684830100401e-07, + "loss": 0.0018, + "step": 59725 + }, + { + "epoch": 18.44, + "learning_rate": 3.152438872521979e-07, + "loss": 0.0019, + "step": 59726 + }, + { + "epoch": 18.44, + "learning_rate": 3.1511931571769905e-07, + "loss": 0.0014, + "step": 59727 + }, + { + "epoch": 18.45, + "learning_rate": 3.149947684068511e-07, + "loss": 0.0019, + "step": 59728 + }, + { + "epoch": 18.45, + "learning_rate": 3.14870245319967e-07, + "loss": 0.0019, + "step": 59729 + }, + { + "epoch": 18.45, + "learning_rate": 3.147457464573611e-07, + "loss": 0.0016, + "step": 59730 + }, + { + "epoch": 18.45, + "learning_rate": 3.14621271819342e-07, + "loss": 0.0014, + "step": 59731 + }, + { + "epoch": 18.45, + "learning_rate": 3.144968214062216e-07, + "loss": 0.0016, + "step": 59732 + }, + { + "epoch": 18.45, + "learning_rate": 3.1437239521831086e-07, + "loss": 0.0019, + "step": 59733 + }, + { + "epoch": 18.45, + "learning_rate": 3.142479932559206e-07, + "loss": 0.0012, + "step": 59734 + }, + { + "epoch": 18.45, + "learning_rate": 3.1412361551936386e-07, + "loss": 0.002, + "step": 59735 + }, + { + "epoch": 18.45, + "learning_rate": 3.139992620089516e-07, + "loss": 0.002, + "step": 59736 + }, + { + "epoch": 18.45, + "learning_rate": 3.1387493272499126e-07, + "loss": 0.0019, + "step": 59737 + }, + { + "epoch": 18.45, + "learning_rate": 3.137506276677971e-07, + "loss": 0.0017, + "step": 59738 + }, + { + "epoch": 18.45, + "learning_rate": 3.136263468376788e-07, + "loss": 0.0013, + "step": 59739 + }, + { + "epoch": 18.45, + "learning_rate": 3.1350209023494836e-07, + "loss": 0.0015, + "step": 59740 + }, + { + "epoch": 18.45, + "learning_rate": 3.133778578599167e-07, + "loss": 0.0015, + "step": 59741 + }, + { + "epoch": 18.45, + "learning_rate": 3.132536497128924e-07, + "loss": 0.0019, + "step": 59742 + }, + { + "epoch": 18.45, + "learning_rate": 3.131294657941897e-07, + "loss": 0.0016, + "step": 59743 + }, + { + "epoch": 18.45, + "learning_rate": 3.1300530610411384e-07, + "loss": 0.0012, + "step": 59744 + }, + { + "epoch": 18.45, + "learning_rate": 3.1288117064298127e-07, + "loss": 0.0014, + "step": 59745 + }, + { + "epoch": 18.45, + "learning_rate": 3.1275705941109847e-07, + "loss": 0.0014, + "step": 59746 + }, + { + "epoch": 18.45, + "learning_rate": 3.126329724087773e-07, + "loss": 0.0019, + "step": 59747 + }, + { + "epoch": 18.45, + "learning_rate": 3.125089096363265e-07, + "loss": 0.0013, + "step": 59748 + }, + { + "epoch": 18.45, + "learning_rate": 3.1238487109406024e-07, + "loss": 0.0013, + "step": 59749 + }, + { + "epoch": 18.45, + "learning_rate": 3.122608567822849e-07, + "loss": 0.0011, + "step": 59750 + }, + { + "epoch": 18.45, + "learning_rate": 3.1213686670131247e-07, + "loss": 0.0013, + "step": 59751 + }, + { + "epoch": 18.45, + "learning_rate": 3.1201290085145275e-07, + "loss": 0.0021, + "step": 59752 + }, + { + "epoch": 18.45, + "learning_rate": 3.1188895923301543e-07, + "loss": 0.0016, + "step": 59753 + }, + { + "epoch": 18.45, + "learning_rate": 3.1176504184631027e-07, + "loss": 0.0013, + "step": 59754 + }, + { + "epoch": 18.45, + "learning_rate": 3.116411486916493e-07, + "loss": 0.0013, + "step": 59755 + }, + { + "epoch": 18.45, + "learning_rate": 3.1151727976933996e-07, + "loss": 0.0016, + "step": 59756 + }, + { + "epoch": 18.45, + "learning_rate": 3.113934350796932e-07, + "loss": 0.0015, + "step": 59757 + }, + { + "epoch": 18.45, + "learning_rate": 3.1126961462301876e-07, + "loss": 0.0017, + "step": 59758 + }, + { + "epoch": 18.45, + "learning_rate": 3.111458183996252e-07, + "loss": 0.0014, + "step": 59759 + }, + { + "epoch": 18.45, + "learning_rate": 3.110220464098235e-07, + "loss": 0.002, + "step": 59760 + }, + { + "epoch": 18.46, + "learning_rate": 3.108982986539244e-07, + "loss": 0.0018, + "step": 59761 + }, + { + "epoch": 18.46, + "learning_rate": 3.107745751322333e-07, + "loss": 0.0015, + "step": 59762 + }, + { + "epoch": 18.46, + "learning_rate": 3.1065087584506327e-07, + "loss": 0.0017, + "step": 59763 + }, + { + "epoch": 18.46, + "learning_rate": 3.105272007927229e-07, + "loss": 0.0015, + "step": 59764 + }, + { + "epoch": 18.46, + "learning_rate": 3.104035499755209e-07, + "loss": 0.0018, + "step": 59765 + }, + { + "epoch": 18.46, + "learning_rate": 3.10279923393767e-07, + "loss": 0.0015, + "step": 59766 + }, + { + "epoch": 18.46, + "learning_rate": 3.101563210477709e-07, + "loss": 0.0017, + "step": 59767 + }, + { + "epoch": 18.46, + "learning_rate": 3.1003274293784025e-07, + "loss": 0.002, + "step": 59768 + }, + { + "epoch": 18.46, + "learning_rate": 3.099091890642847e-07, + "loss": 0.0014, + "step": 59769 + }, + { + "epoch": 18.46, + "learning_rate": 3.097856594274151e-07, + "loss": 0.0013, + "step": 59770 + }, + { + "epoch": 18.46, + "learning_rate": 3.0966215402753795e-07, + "loss": 0.0016, + "step": 59771 + }, + { + "epoch": 18.46, + "learning_rate": 3.09538672864963e-07, + "loss": 0.0015, + "step": 59772 + }, + { + "epoch": 18.46, + "learning_rate": 3.094152159399988e-07, + "loss": 0.0015, + "step": 59773 + }, + { + "epoch": 18.46, + "learning_rate": 3.0929178325295627e-07, + "loss": 0.0018, + "step": 59774 + }, + { + "epoch": 18.46, + "learning_rate": 3.0916837480414077e-07, + "loss": 0.0019, + "step": 59775 + }, + { + "epoch": 18.46, + "learning_rate": 3.090449905938642e-07, + "loss": 0.0018, + "step": 59776 + }, + { + "epoch": 18.46, + "learning_rate": 3.089216306224341e-07, + "loss": 0.0013, + "step": 59777 + }, + { + "epoch": 18.46, + "learning_rate": 3.087982948901569e-07, + "loss": 0.0017, + "step": 59778 + }, + { + "epoch": 18.46, + "learning_rate": 3.0867498339734236e-07, + "loss": 0.0014, + "step": 59779 + }, + { + "epoch": 18.46, + "learning_rate": 3.0855169614430027e-07, + "loss": 0.0011, + "step": 59780 + }, + { + "epoch": 18.46, + "learning_rate": 3.084284331313392e-07, + "loss": 0.002, + "step": 59781 + }, + { + "epoch": 18.46, + "learning_rate": 3.0830519435876337e-07, + "loss": 0.0012, + "step": 59782 + }, + { + "epoch": 18.46, + "learning_rate": 3.0818197982688593e-07, + "loss": 0.0018, + "step": 59783 + }, + { + "epoch": 18.46, + "learning_rate": 3.080587895360121e-07, + "loss": 0.0014, + "step": 59784 + }, + { + "epoch": 18.46, + "learning_rate": 3.0793562348645165e-07, + "loss": 0.0019, + "step": 59785 + }, + { + "epoch": 18.46, + "learning_rate": 3.078124816785122e-07, + "loss": 0.0023, + "step": 59786 + }, + { + "epoch": 18.46, + "learning_rate": 3.0768936411250116e-07, + "loss": 0.0015, + "step": 59787 + }, + { + "epoch": 18.46, + "learning_rate": 3.0756627078872613e-07, + "loss": 0.0018, + "step": 59788 + }, + { + "epoch": 18.46, + "learning_rate": 3.0744320170749684e-07, + "loss": 0.0016, + "step": 59789 + }, + { + "epoch": 18.46, + "learning_rate": 3.0732015686911865e-07, + "loss": 0.0016, + "step": 59790 + }, + { + "epoch": 18.46, + "learning_rate": 3.071971362739012e-07, + "loss": 0.0013, + "step": 59791 + }, + { + "epoch": 18.46, + "learning_rate": 3.0707413992215216e-07, + "loss": 0.0015, + "step": 59792 + }, + { + "epoch": 18.47, + "learning_rate": 3.069511678141768e-07, + "loss": 0.0016, + "step": 59793 + }, + { + "epoch": 18.47, + "learning_rate": 3.068282199502848e-07, + "loss": 0.0014, + "step": 59794 + }, + { + "epoch": 18.47, + "learning_rate": 3.0670529633078485e-07, + "loss": 0.0017, + "step": 59795 + }, + { + "epoch": 18.47, + "learning_rate": 3.0658239695598223e-07, + "loss": 0.0022, + "step": 59796 + }, + { + "epoch": 18.47, + "learning_rate": 3.0645952182618457e-07, + "loss": 0.0023, + "step": 59797 + }, + { + "epoch": 18.47, + "learning_rate": 3.063366709417004e-07, + "loss": 0.0017, + "step": 59798 + }, + { + "epoch": 18.47, + "learning_rate": 3.062138443028362e-07, + "loss": 0.0011, + "step": 59799 + }, + { + "epoch": 18.47, + "learning_rate": 3.0609104190989833e-07, + "loss": 0.0017, + "step": 59800 + }, + { + "epoch": 18.47, + "learning_rate": 3.0596826376319556e-07, + "loss": 0.0018, + "step": 59801 + }, + { + "epoch": 18.47, + "learning_rate": 3.058455098630342e-07, + "loss": 0.0012, + "step": 59802 + }, + { + "epoch": 18.47, + "learning_rate": 3.057227802097207e-07, + "loss": 0.0012, + "step": 59803 + }, + { + "epoch": 18.47, + "learning_rate": 3.0560007480356257e-07, + "loss": 0.0015, + "step": 59804 + }, + { + "epoch": 18.47, + "learning_rate": 3.054773936448674e-07, + "loss": 0.0018, + "step": 59805 + }, + { + "epoch": 18.47, + "learning_rate": 3.0535473673394155e-07, + "loss": 0.0013, + "step": 59806 + }, + { + "epoch": 18.47, + "learning_rate": 3.0523210407109147e-07, + "loss": 0.0016, + "step": 59807 + }, + { + "epoch": 18.47, + "learning_rate": 3.0510949565662474e-07, + "loss": 0.0016, + "step": 59808 + }, + { + "epoch": 18.47, + "learning_rate": 3.049869114908466e-07, + "loss": 0.0023, + "step": 59809 + }, + { + "epoch": 18.47, + "learning_rate": 3.0486435157406345e-07, + "loss": 0.0021, + "step": 59810 + }, + { + "epoch": 18.47, + "learning_rate": 3.047418159065851e-07, + "loss": 0.0015, + "step": 59811 + }, + { + "epoch": 18.47, + "learning_rate": 3.0461930448871466e-07, + "loss": 0.0021, + "step": 59812 + }, + { + "epoch": 18.47, + "learning_rate": 3.044968173207596e-07, + "loss": 0.0012, + "step": 59813 + }, + { + "epoch": 18.47, + "learning_rate": 3.043743544030264e-07, + "loss": 0.0021, + "step": 59814 + }, + { + "epoch": 18.47, + "learning_rate": 3.042519157358215e-07, + "loss": 0.0021, + "step": 59815 + }, + { + "epoch": 18.47, + "learning_rate": 3.0412950131945006e-07, + "loss": 0.0017, + "step": 59816 + }, + { + "epoch": 18.47, + "learning_rate": 3.0400711115422086e-07, + "loss": 0.0017, + "step": 59817 + }, + { + "epoch": 18.47, + "learning_rate": 3.038847452404381e-07, + "loss": 0.0017, + "step": 59818 + }, + { + "epoch": 18.47, + "learning_rate": 3.037624035784059e-07, + "loss": 0.0011, + "step": 59819 + }, + { + "epoch": 18.47, + "learning_rate": 3.0364008616843523e-07, + "loss": 0.0017, + "step": 59820 + }, + { + "epoch": 18.47, + "learning_rate": 3.035177930108268e-07, + "loss": 0.0022, + "step": 59821 + }, + { + "epoch": 18.47, + "learning_rate": 3.0339552410589055e-07, + "loss": 0.0012, + "step": 59822 + }, + { + "epoch": 18.47, + "learning_rate": 3.032732794539306e-07, + "loss": 0.0015, + "step": 59823 + }, + { + "epoch": 18.47, + "learning_rate": 3.031510590552511e-07, + "loss": 0.0017, + "step": 59824 + }, + { + "epoch": 18.48, + "learning_rate": 3.0302886291016076e-07, + "loss": 0.0017, + "step": 59825 + }, + { + "epoch": 18.48, + "learning_rate": 3.0290669101896376e-07, + "loss": 0.0021, + "step": 59826 + }, + { + "epoch": 18.48, + "learning_rate": 3.027845433819643e-07, + "loss": 0.0014, + "step": 59827 + }, + { + "epoch": 18.48, + "learning_rate": 3.026624199994721e-07, + "loss": 0.0021, + "step": 59828 + }, + { + "epoch": 18.48, + "learning_rate": 3.0254032087178807e-07, + "loss": 0.0016, + "step": 59829 + }, + { + "epoch": 18.48, + "learning_rate": 3.0241824599921974e-07, + "loss": 0.0021, + "step": 59830 + }, + { + "epoch": 18.48, + "learning_rate": 3.022961953820713e-07, + "loss": 0.0019, + "step": 59831 + }, + { + "epoch": 18.48, + "learning_rate": 3.0217416902065034e-07, + "loss": 0.0023, + "step": 59832 + }, + { + "epoch": 18.48, + "learning_rate": 3.0205216691525987e-07, + "loss": 0.0018, + "step": 59833 + }, + { + "epoch": 18.48, + "learning_rate": 3.019301890662052e-07, + "loss": 0.0013, + "step": 59834 + }, + { + "epoch": 18.48, + "learning_rate": 3.018082354737928e-07, + "loss": 0.0017, + "step": 59835 + }, + { + "epoch": 18.48, + "learning_rate": 3.016863061383268e-07, + "loss": 0.0016, + "step": 59836 + }, + { + "epoch": 18.48, + "learning_rate": 3.015644010601104e-07, + "loss": 0.0017, + "step": 59837 + }, + { + "epoch": 18.48, + "learning_rate": 3.014425202394533e-07, + "loss": 0.0023, + "step": 59838 + }, + { + "epoch": 18.48, + "learning_rate": 3.0132066367665637e-07, + "loss": 0.0017, + "step": 59839 + }, + { + "epoch": 18.48, + "learning_rate": 3.0119883137202377e-07, + "loss": 0.0012, + "step": 59840 + }, + { + "epoch": 18.48, + "learning_rate": 3.010770233258631e-07, + "loss": 0.0018, + "step": 59841 + }, + { + "epoch": 18.48, + "learning_rate": 3.009552395384774e-07, + "loss": 0.0015, + "step": 59842 + }, + { + "epoch": 18.48, + "learning_rate": 3.008334800101731e-07, + "loss": 0.002, + "step": 59843 + }, + { + "epoch": 18.48, + "learning_rate": 3.007117447412511e-07, + "loss": 0.002, + "step": 59844 + }, + { + "epoch": 18.48, + "learning_rate": 3.0059003373202e-07, + "loss": 0.0018, + "step": 59845 + }, + { + "epoch": 18.48, + "learning_rate": 3.004683469827807e-07, + "loss": 0.0021, + "step": 59846 + }, + { + "epoch": 18.48, + "learning_rate": 3.0034668449383853e-07, + "loss": 0.0013, + "step": 59847 + }, + { + "epoch": 18.48, + "learning_rate": 3.0022504626549984e-07, + "loss": 0.0017, + "step": 59848 + }, + { + "epoch": 18.48, + "learning_rate": 3.001034322980678e-07, + "loss": 0.0015, + "step": 59849 + }, + { + "epoch": 18.48, + "learning_rate": 2.999818425918455e-07, + "loss": 0.0012, + "step": 59850 + }, + { + "epoch": 18.48, + "learning_rate": 2.998602771471382e-07, + "loss": 0.0015, + "step": 59851 + }, + { + "epoch": 18.48, + "learning_rate": 2.9973873596424894e-07, + "loss": 0.0019, + "step": 59852 + }, + { + "epoch": 18.48, + "learning_rate": 2.996172190434832e-07, + "loss": 0.0015, + "step": 59853 + }, + { + "epoch": 18.48, + "learning_rate": 2.994957263851439e-07, + "loss": 0.0014, + "step": 59854 + }, + { + "epoch": 18.48, + "learning_rate": 2.993742579895342e-07, + "loss": 0.0014, + "step": 59855 + }, + { + "epoch": 18.48, + "learning_rate": 2.9925281385695834e-07, + "loss": 0.0012, + "step": 59856 + }, + { + "epoch": 18.48, + "learning_rate": 2.991313939877227e-07, + "loss": 0.0017, + "step": 59857 + }, + { + "epoch": 18.49, + "learning_rate": 2.990099983821271e-07, + "loss": 0.0013, + "step": 59858 + }, + { + "epoch": 18.49, + "learning_rate": 2.9888862704047673e-07, + "loss": 0.0013, + "step": 59859 + }, + { + "epoch": 18.49, + "learning_rate": 2.98767279963077e-07, + "loss": 0.0019, + "step": 59860 + }, + { + "epoch": 18.49, + "learning_rate": 2.986459571502276e-07, + "loss": 0.0017, + "step": 59861 + }, + { + "epoch": 18.49, + "learning_rate": 2.9852465860223387e-07, + "loss": 0.0018, + "step": 59862 + }, + { + "epoch": 18.49, + "learning_rate": 2.984033843194012e-07, + "loss": 0.0012, + "step": 59863 + }, + { + "epoch": 18.49, + "learning_rate": 2.9828213430203147e-07, + "loss": 0.0015, + "step": 59864 + }, + { + "epoch": 18.49, + "learning_rate": 2.9816090855042554e-07, + "loss": 0.0024, + "step": 59865 + }, + { + "epoch": 18.49, + "learning_rate": 2.9803970706488996e-07, + "loss": 0.002, + "step": 59866 + }, + { + "epoch": 18.49, + "learning_rate": 2.979185298457266e-07, + "loss": 0.0012, + "step": 59867 + }, + { + "epoch": 18.49, + "learning_rate": 2.977973768932374e-07, + "loss": 0.0018, + "step": 59868 + }, + { + "epoch": 18.49, + "learning_rate": 2.976762482077278e-07, + "loss": 0.0016, + "step": 59869 + }, + { + "epoch": 18.49, + "learning_rate": 2.975551437894997e-07, + "loss": 0.0014, + "step": 59870 + }, + { + "epoch": 18.49, + "learning_rate": 2.9743406363885396e-07, + "loss": 0.0013, + "step": 59871 + }, + { + "epoch": 18.49, + "learning_rate": 2.97313007756096e-07, + "loss": 0.0016, + "step": 59872 + }, + { + "epoch": 18.49, + "learning_rate": 2.971919761415287e-07, + "loss": 0.0015, + "step": 59873 + }, + { + "epoch": 18.49, + "learning_rate": 2.9707096879545427e-07, + "loss": 0.0023, + "step": 59874 + }, + { + "epoch": 18.49, + "learning_rate": 2.969499857181746e-07, + "loss": 0.0017, + "step": 59875 + }, + { + "epoch": 18.49, + "learning_rate": 2.968290269099927e-07, + "loss": 0.002, + "step": 59876 + }, + { + "epoch": 18.49, + "learning_rate": 2.967080923712107e-07, + "loss": 0.0018, + "step": 59877 + }, + { + "epoch": 18.49, + "learning_rate": 2.9658718210213045e-07, + "loss": 0.0018, + "step": 59878 + }, + { + "epoch": 18.49, + "learning_rate": 2.9646629610305846e-07, + "loss": 0.0018, + "step": 59879 + }, + { + "epoch": 18.49, + "learning_rate": 2.963454343742922e-07, + "loss": 0.0014, + "step": 59880 + }, + { + "epoch": 18.49, + "learning_rate": 2.9622459691613594e-07, + "loss": 0.0019, + "step": 59881 + }, + { + "epoch": 18.49, + "learning_rate": 2.9610378372889157e-07, + "loss": 0.0015, + "step": 59882 + }, + { + "epoch": 18.49, + "learning_rate": 2.959829948128612e-07, + "loss": 0.0014, + "step": 59883 + }, + { + "epoch": 18.49, + "learning_rate": 2.958622301683489e-07, + "loss": 0.0015, + "step": 59884 + }, + { + "epoch": 18.49, + "learning_rate": 2.9574148979565455e-07, + "loss": 0.0016, + "step": 59885 + }, + { + "epoch": 18.49, + "learning_rate": 2.9562077369508e-07, + "loss": 0.0017, + "step": 59886 + }, + { + "epoch": 18.49, + "learning_rate": 2.9550008186692736e-07, + "loss": 0.0017, + "step": 59887 + }, + { + "epoch": 18.49, + "learning_rate": 2.9537941431150074e-07, + "loss": 0.0017, + "step": 59888 + }, + { + "epoch": 18.49, + "learning_rate": 2.952587710290988e-07, + "loss": 0.0018, + "step": 59889 + }, + { + "epoch": 18.5, + "learning_rate": 2.951381520200258e-07, + "loss": 0.0017, + "step": 59890 + }, + { + "epoch": 18.5, + "learning_rate": 2.9501755728458145e-07, + "loss": 0.0012, + "step": 59891 + }, + { + "epoch": 18.5, + "learning_rate": 2.948969868230678e-07, + "loss": 0.0015, + "step": 59892 + }, + { + "epoch": 18.5, + "learning_rate": 2.947764406357878e-07, + "loss": 0.0016, + "step": 59893 + }, + { + "epoch": 18.5, + "learning_rate": 2.9465591872304245e-07, + "loss": 0.0015, + "step": 59894 + }, + { + "epoch": 18.5, + "learning_rate": 2.9453542108513253e-07, + "loss": 0.0022, + "step": 59895 + }, + { + "epoch": 18.5, + "learning_rate": 2.94414947722359e-07, + "loss": 0.0022, + "step": 59896 + }, + { + "epoch": 18.5, + "learning_rate": 2.942944986350238e-07, + "loss": 0.0018, + "step": 59897 + }, + { + "epoch": 18.5, + "learning_rate": 2.941740738234289e-07, + "loss": 0.0017, + "step": 59898 + }, + { + "epoch": 18.5, + "learning_rate": 2.9405367328787405e-07, + "loss": 0.0017, + "step": 59899 + }, + { + "epoch": 18.5, + "learning_rate": 2.9393329702866347e-07, + "loss": 0.0016, + "step": 59900 + }, + { + "epoch": 18.5, + "learning_rate": 2.9381294504609357e-07, + "loss": 0.0022, + "step": 59901 + }, + { + "epoch": 18.5, + "learning_rate": 2.936926173404675e-07, + "loss": 0.0014, + "step": 59902 + }, + { + "epoch": 18.5, + "learning_rate": 2.9357231391208717e-07, + "loss": 0.0017, + "step": 59903 + }, + { + "epoch": 18.5, + "learning_rate": 2.934520347612546e-07, + "loss": 0.0017, + "step": 59904 + }, + { + "epoch": 18.5, + "learning_rate": 2.9333177988826735e-07, + "loss": 0.0019, + "step": 59905 + }, + { + "epoch": 18.5, + "learning_rate": 2.932115492934273e-07, + "loss": 0.0019, + "step": 59906 + }, + { + "epoch": 18.5, + "learning_rate": 2.9309134297703655e-07, + "loss": 0.0021, + "step": 59907 + }, + { + "epoch": 18.5, + "learning_rate": 2.929711609393937e-07, + "loss": 0.0017, + "step": 59908 + }, + { + "epoch": 18.5, + "learning_rate": 2.9285100318080073e-07, + "loss": 0.0021, + "step": 59909 + }, + { + "epoch": 18.5, + "learning_rate": 2.927308697015596e-07, + "loss": 0.0016, + "step": 59910 + }, + { + "epoch": 18.5, + "learning_rate": 2.926107605019679e-07, + "loss": 0.0017, + "step": 59911 + }, + { + "epoch": 18.5, + "learning_rate": 2.924906755823265e-07, + "loss": 0.0018, + "step": 59912 + }, + { + "epoch": 18.5, + "learning_rate": 2.9237061494293727e-07, + "loss": 0.0014, + "step": 59913 + }, + { + "epoch": 18.5, + "learning_rate": 2.92250578584099e-07, + "loss": 0.0017, + "step": 59914 + }, + { + "epoch": 18.5, + "learning_rate": 2.921305665061136e-07, + "loss": 0.0014, + "step": 59915 + }, + { + "epoch": 18.5, + "learning_rate": 2.920105787092797e-07, + "loss": 0.0017, + "step": 59916 + }, + { + "epoch": 18.5, + "learning_rate": 2.918906151938972e-07, + "loss": 0.0017, + "step": 59917 + }, + { + "epoch": 18.5, + "learning_rate": 2.9177067596026673e-07, + "loss": 0.0013, + "step": 59918 + }, + { + "epoch": 18.5, + "learning_rate": 2.916507610086905e-07, + "loss": 0.0012, + "step": 59919 + }, + { + "epoch": 18.5, + "learning_rate": 2.915308703394659e-07, + "loss": 0.0021, + "step": 59920 + }, + { + "epoch": 18.5, + "learning_rate": 2.9141100395289166e-07, + "loss": 0.0017, + "step": 59921 + }, + { + "epoch": 18.5, + "learning_rate": 2.9129116184927085e-07, + "loss": 0.0014, + "step": 59922 + }, + { + "epoch": 18.51, + "learning_rate": 2.91171344028901e-07, + "loss": 0.0019, + "step": 59923 + }, + { + "epoch": 18.51, + "learning_rate": 2.910515504920819e-07, + "loss": 0.0012, + "step": 59924 + }, + { + "epoch": 18.51, + "learning_rate": 2.9093178123911436e-07, + "loss": 0.0028, + "step": 59925 + }, + { + "epoch": 18.51, + "learning_rate": 2.908120362702982e-07, + "loss": 0.002, + "step": 59926 + }, + { + "epoch": 18.51, + "learning_rate": 2.906923155859298e-07, + "loss": 0.0019, + "step": 59927 + }, + { + "epoch": 18.51, + "learning_rate": 2.905726191863123e-07, + "loss": 0.0021, + "step": 59928 + }, + { + "epoch": 18.51, + "learning_rate": 2.904529470717432e-07, + "loss": 0.0017, + "step": 59929 + }, + { + "epoch": 18.51, + "learning_rate": 2.903332992425223e-07, + "loss": 0.0011, + "step": 59930 + }, + { + "epoch": 18.51, + "learning_rate": 2.902136756989493e-07, + "loss": 0.0017, + "step": 59931 + }, + { + "epoch": 18.51, + "learning_rate": 2.900940764413207e-07, + "loss": 0.0015, + "step": 59932 + }, + { + "epoch": 18.51, + "learning_rate": 2.8997450146993956e-07, + "loss": 0.002, + "step": 59933 + }, + { + "epoch": 18.51, + "learning_rate": 2.898549507851034e-07, + "loss": 0.0017, + "step": 59934 + }, + { + "epoch": 18.51, + "learning_rate": 2.8973542438710975e-07, + "loss": 0.0015, + "step": 59935 + }, + { + "epoch": 18.51, + "learning_rate": 2.896159222762596e-07, + "loss": 0.0013, + "step": 59936 + }, + { + "epoch": 18.51, + "learning_rate": 2.894964444528503e-07, + "loss": 0.0014, + "step": 59937 + }, + { + "epoch": 18.51, + "learning_rate": 2.8937699091718284e-07, + "loss": 0.0017, + "step": 59938 + }, + { + "epoch": 18.51, + "learning_rate": 2.8925756166955364e-07, + "loss": 0.002, + "step": 59939 + }, + { + "epoch": 18.51, + "learning_rate": 2.891381567102636e-07, + "loss": 0.0014, + "step": 59940 + }, + { + "epoch": 18.51, + "learning_rate": 2.8901877603961016e-07, + "loss": 0.0021, + "step": 59941 + }, + { + "epoch": 18.51, + "learning_rate": 2.888994196578898e-07, + "loss": 0.0014, + "step": 59942 + }, + { + "epoch": 18.51, + "learning_rate": 2.887800875654045e-07, + "loss": 0.0014, + "step": 59943 + }, + { + "epoch": 18.51, + "learning_rate": 2.886607797624519e-07, + "loss": 0.002, + "step": 59944 + }, + { + "epoch": 18.51, + "learning_rate": 2.885414962493294e-07, + "loss": 0.0018, + "step": 59945 + }, + { + "epoch": 18.51, + "learning_rate": 2.8842223702633563e-07, + "loss": 0.0015, + "step": 59946 + }, + { + "epoch": 18.51, + "learning_rate": 2.883030020937705e-07, + "loss": 0.0014, + "step": 59947 + }, + { + "epoch": 18.51, + "learning_rate": 2.881837914519292e-07, + "loss": 0.0018, + "step": 59948 + }, + { + "epoch": 18.51, + "learning_rate": 2.8806460510111157e-07, + "loss": 0.0027, + "step": 59949 + }, + { + "epoch": 18.51, + "learning_rate": 2.879454430416173e-07, + "loss": 0.0018, + "step": 59950 + }, + { + "epoch": 18.51, + "learning_rate": 2.8782630527374177e-07, + "loss": 0.0014, + "step": 59951 + }, + { + "epoch": 18.51, + "learning_rate": 2.877071917977836e-07, + "loss": 0.0018, + "step": 59952 + }, + { + "epoch": 18.51, + "learning_rate": 2.8758810261404255e-07, + "loss": 0.0017, + "step": 59953 + }, + { + "epoch": 18.51, + "learning_rate": 2.87469037722814e-07, + "loss": 0.0014, + "step": 59954 + }, + { + "epoch": 18.52, + "learning_rate": 2.873499971243965e-07, + "loss": 0.0019, + "step": 59955 + }, + { + "epoch": 18.52, + "learning_rate": 2.872309808190887e-07, + "loss": 0.0017, + "step": 59956 + }, + { + "epoch": 18.52, + "learning_rate": 2.8711198880718825e-07, + "loss": 0.001, + "step": 59957 + }, + { + "epoch": 18.52, + "learning_rate": 2.869930210889915e-07, + "loss": 0.0015, + "step": 59958 + }, + { + "epoch": 18.52, + "learning_rate": 2.8687407766479714e-07, + "loss": 0.0012, + "step": 59959 + }, + { + "epoch": 18.52, + "learning_rate": 2.8675515853490154e-07, + "loss": 0.0019, + "step": 59960 + }, + { + "epoch": 18.52, + "learning_rate": 2.866362636996045e-07, + "loss": 0.0014, + "step": 59961 + }, + { + "epoch": 18.52, + "learning_rate": 2.8651739315920134e-07, + "loss": 0.0018, + "step": 59962 + }, + { + "epoch": 18.52, + "learning_rate": 2.863985469139885e-07, + "loss": 0.0018, + "step": 59963 + }, + { + "epoch": 18.52, + "learning_rate": 2.862797249642646e-07, + "loss": 0.0012, + "step": 59964 + }, + { + "epoch": 18.52, + "learning_rate": 2.861609273103272e-07, + "loss": 0.0017, + "step": 59965 + }, + { + "epoch": 18.52, + "learning_rate": 2.860421539524727e-07, + "loss": 0.0022, + "step": 59966 + }, + { + "epoch": 18.52, + "learning_rate": 2.859234048909998e-07, + "loss": 0.0015, + "step": 59967 + }, + { + "epoch": 18.52, + "learning_rate": 2.858046801262027e-07, + "loss": 0.0015, + "step": 59968 + }, + { + "epoch": 18.52, + "learning_rate": 2.8568597965838107e-07, + "loss": 0.0024, + "step": 59969 + }, + { + "epoch": 18.52, + "learning_rate": 2.8556730348782924e-07, + "loss": 0.0014, + "step": 59970 + }, + { + "epoch": 18.52, + "learning_rate": 2.854486516148469e-07, + "loss": 0.0019, + "step": 59971 + }, + { + "epoch": 18.52, + "learning_rate": 2.853300240397294e-07, + "loss": 0.0014, + "step": 59972 + }, + { + "epoch": 18.52, + "learning_rate": 2.852114207627721e-07, + "loss": 0.0016, + "step": 59973 + }, + { + "epoch": 18.52, + "learning_rate": 2.850928417842724e-07, + "loss": 0.0015, + "step": 59974 + }, + { + "epoch": 18.52, + "learning_rate": 2.8497428710452914e-07, + "loss": 0.001, + "step": 59975 + }, + { + "epoch": 18.52, + "learning_rate": 2.848557567238364e-07, + "loss": 0.0013, + "step": 59976 + }, + { + "epoch": 18.52, + "learning_rate": 2.8473725064249167e-07, + "loss": 0.0015, + "step": 59977 + }, + { + "epoch": 18.52, + "learning_rate": 2.8461876886079045e-07, + "loss": 0.0027, + "step": 59978 + }, + { + "epoch": 18.52, + "learning_rate": 2.845003113790301e-07, + "loss": 0.0015, + "step": 59979 + }, + { + "epoch": 18.52, + "learning_rate": 2.8438187819750494e-07, + "loss": 0.0017, + "step": 59980 + }, + { + "epoch": 18.52, + "learning_rate": 2.8426346931651474e-07, + "loss": 0.0017, + "step": 59981 + }, + { + "epoch": 18.52, + "learning_rate": 2.841450847363536e-07, + "loss": 0.0018, + "step": 59982 + }, + { + "epoch": 18.52, + "learning_rate": 2.8402672445731585e-07, + "loss": 0.0017, + "step": 59983 + }, + { + "epoch": 18.52, + "learning_rate": 2.8390838847970116e-07, + "loss": 0.0018, + "step": 59984 + }, + { + "epoch": 18.52, + "learning_rate": 2.8379007680380265e-07, + "loss": 0.0016, + "step": 59985 + }, + { + "epoch": 18.52, + "learning_rate": 2.836717894299168e-07, + "loss": 0.0017, + "step": 59986 + }, + { + "epoch": 18.53, + "learning_rate": 2.835535263583411e-07, + "loss": 0.0018, + "step": 59987 + }, + { + "epoch": 18.53, + "learning_rate": 2.834352875893709e-07, + "loss": 0.0023, + "step": 59988 + }, + { + "epoch": 18.53, + "learning_rate": 2.8331707312329925e-07, + "loss": 0.0019, + "step": 59989 + }, + { + "epoch": 18.53, + "learning_rate": 2.8319888296042595e-07, + "loss": 0.0016, + "step": 59990 + }, + { + "epoch": 18.53, + "learning_rate": 2.83080717101043e-07, + "loss": 0.0014, + "step": 59991 + }, + { + "epoch": 18.53, + "learning_rate": 2.8296257554544794e-07, + "loss": 0.0017, + "step": 59992 + }, + { + "epoch": 18.53, + "learning_rate": 2.8284445829393603e-07, + "loss": 0.0016, + "step": 59993 + }, + { + "epoch": 18.53, + "learning_rate": 2.8272636534680153e-07, + "loss": 0.0015, + "step": 59994 + }, + { + "epoch": 18.53, + "learning_rate": 2.8260829670434085e-07, + "loss": 0.0014, + "step": 59995 + }, + { + "epoch": 18.53, + "learning_rate": 2.8249025236684933e-07, + "loss": 0.0018, + "step": 59996 + }, + { + "epoch": 18.53, + "learning_rate": 2.823722323346223e-07, + "loss": 0.0015, + "step": 59997 + }, + { + "epoch": 18.53, + "learning_rate": 2.8225423660795503e-07, + "loss": 0.0017, + "step": 59998 + }, + { + "epoch": 18.53, + "learning_rate": 2.821362651871418e-07, + "loss": 0.0015, + "step": 59999 + }, + { + "epoch": 18.53, + "learning_rate": 2.820183180724778e-07, + "loss": 0.0016, + "step": 60000 + }, + { + "epoch": 18.53, + "learning_rate": 2.819003952642585e-07, + "loss": 0.002, + "step": 60001 + }, + { + "epoch": 18.53, + "learning_rate": 2.8178249676277914e-07, + "loss": 0.0015, + "step": 60002 + }, + { + "epoch": 18.53, + "learning_rate": 2.8166462256833505e-07, + "loss": 0.002, + "step": 60003 + }, + { + "epoch": 18.53, + "learning_rate": 2.8154677268121933e-07, + "loss": 0.0014, + "step": 60004 + }, + { + "epoch": 18.53, + "learning_rate": 2.814289471017273e-07, + "loss": 0.0014, + "step": 60005 + }, + { + "epoch": 18.53, + "learning_rate": 2.813111458301543e-07, + "loss": 0.0015, + "step": 60006 + }, + { + "epoch": 18.53, + "learning_rate": 2.8119336886679447e-07, + "loss": 0.0019, + "step": 60007 + }, + { + "epoch": 18.53, + "learning_rate": 2.810756162119443e-07, + "loss": 0.0014, + "step": 60008 + }, + { + "epoch": 18.53, + "learning_rate": 2.8095788786589585e-07, + "loss": 0.0016, + "step": 60009 + }, + { + "epoch": 18.53, + "learning_rate": 2.808401838289432e-07, + "loss": 0.0017, + "step": 60010 + }, + { + "epoch": 18.53, + "learning_rate": 2.807225041013817e-07, + "loss": 0.0015, + "step": 60011 + }, + { + "epoch": 18.53, + "learning_rate": 2.806048486835078e-07, + "loss": 0.0014, + "step": 60012 + }, + { + "epoch": 18.53, + "learning_rate": 2.804872175756135e-07, + "loss": 0.0018, + "step": 60013 + }, + { + "epoch": 18.53, + "learning_rate": 2.8036961077799185e-07, + "loss": 0.0014, + "step": 60014 + }, + { + "epoch": 18.53, + "learning_rate": 2.8025202829094045e-07, + "loss": 0.0016, + "step": 60015 + }, + { + "epoch": 18.53, + "learning_rate": 2.8013447011475017e-07, + "loss": 0.0018, + "step": 60016 + }, + { + "epoch": 18.53, + "learning_rate": 2.8001693624971626e-07, + "loss": 0.0017, + "step": 60017 + }, + { + "epoch": 18.53, + "learning_rate": 2.7989942669613524e-07, + "loss": 0.0022, + "step": 60018 + }, + { + "epoch": 18.53, + "learning_rate": 2.7978194145429573e-07, + "loss": 0.0018, + "step": 60019 + }, + { + "epoch": 18.54, + "learning_rate": 2.7966448052449524e-07, + "loss": 0.0015, + "step": 60020 + }, + { + "epoch": 18.54, + "learning_rate": 2.795470439070269e-07, + "loss": 0.0017, + "step": 60021 + }, + { + "epoch": 18.54, + "learning_rate": 2.794296316021838e-07, + "loss": 0.0013, + "step": 60022 + }, + { + "epoch": 18.54, + "learning_rate": 2.793122436102613e-07, + "loss": 0.0021, + "step": 60023 + }, + { + "epoch": 18.54, + "learning_rate": 2.7919487993155245e-07, + "loss": 0.0016, + "step": 60024 + }, + { + "epoch": 18.54, + "learning_rate": 2.7907754056634815e-07, + "loss": 0.0016, + "step": 60025 + }, + { + "epoch": 18.54, + "learning_rate": 2.789602255149437e-07, + "loss": 0.0014, + "step": 60026 + }, + { + "epoch": 18.54, + "learning_rate": 2.7884293477763446e-07, + "loss": 0.0014, + "step": 60027 + }, + { + "epoch": 18.54, + "learning_rate": 2.7872566835471126e-07, + "loss": 0.0013, + "step": 60028 + }, + { + "epoch": 18.54, + "learning_rate": 2.786084262464683e-07, + "loss": 0.0017, + "step": 60029 + }, + { + "epoch": 18.54, + "learning_rate": 2.7849120845319877e-07, + "loss": 0.0011, + "step": 60030 + }, + { + "epoch": 18.54, + "learning_rate": 2.783740149751957e-07, + "loss": 0.002, + "step": 60031 + }, + { + "epoch": 18.54, + "learning_rate": 2.7825684581275103e-07, + "loss": 0.0022, + "step": 60032 + }, + { + "epoch": 18.54, + "learning_rate": 2.781397009661613e-07, + "loss": 0.0014, + "step": 60033 + }, + { + "epoch": 18.54, + "learning_rate": 2.780225804357173e-07, + "loss": 0.0023, + "step": 60034 + }, + { + "epoch": 18.54, + "learning_rate": 2.7790548422171104e-07, + "loss": 0.0015, + "step": 60035 + }, + { + "epoch": 18.54, + "learning_rate": 2.7778841232443565e-07, + "loss": 0.0013, + "step": 60036 + }, + { + "epoch": 18.54, + "learning_rate": 2.776713647441864e-07, + "loss": 0.0017, + "step": 60037 + }, + { + "epoch": 18.54, + "learning_rate": 2.7755434148125317e-07, + "loss": 0.0019, + "step": 60038 + }, + { + "epoch": 18.54, + "learning_rate": 2.7743734253593e-07, + "loss": 0.0016, + "step": 60039 + }, + { + "epoch": 18.54, + "learning_rate": 2.7732036790851013e-07, + "loss": 0.0018, + "step": 60040 + }, + { + "epoch": 18.54, + "learning_rate": 2.7720341759928325e-07, + "loss": 0.0013, + "step": 60041 + }, + { + "epoch": 18.54, + "learning_rate": 2.770864916085447e-07, + "loss": 0.002, + "step": 60042 + }, + { + "epoch": 18.54, + "learning_rate": 2.7696958993658764e-07, + "loss": 0.0016, + "step": 60043 + }, + { + "epoch": 18.54, + "learning_rate": 2.7685271258370283e-07, + "loss": 0.002, + "step": 60044 + }, + { + "epoch": 18.54, + "learning_rate": 2.7673585955018124e-07, + "loss": 0.0016, + "step": 60045 + }, + { + "epoch": 18.54, + "learning_rate": 2.766190308363181e-07, + "loss": 0.0018, + "step": 60046 + }, + { + "epoch": 18.54, + "learning_rate": 2.7650222644240335e-07, + "loss": 0.0012, + "step": 60047 + }, + { + "epoch": 18.54, + "learning_rate": 2.76385446368731e-07, + "loss": 0.0019, + "step": 60048 + }, + { + "epoch": 18.54, + "learning_rate": 2.7626869061559203e-07, + "loss": 0.0012, + "step": 60049 + }, + { + "epoch": 18.54, + "learning_rate": 2.761519591832773e-07, + "loss": 0.0018, + "step": 60050 + }, + { + "epoch": 18.54, + "learning_rate": 2.760352520720799e-07, + "loss": 0.0017, + "step": 60051 + }, + { + "epoch": 18.55, + "learning_rate": 2.75918569282293e-07, + "loss": 0.0021, + "step": 60052 + }, + { + "epoch": 18.55, + "learning_rate": 2.7580191081420625e-07, + "loss": 0.0015, + "step": 60053 + }, + { + "epoch": 18.55, + "learning_rate": 2.7568527666811393e-07, + "loss": 0.0019, + "step": 60054 + }, + { + "epoch": 18.55, + "learning_rate": 2.755686668443058e-07, + "loss": 0.0015, + "step": 60055 + }, + { + "epoch": 18.55, + "learning_rate": 2.754520813430739e-07, + "loss": 0.0016, + "step": 60056 + }, + { + "epoch": 18.55, + "learning_rate": 2.75335520164709e-07, + "loss": 0.0016, + "step": 60057 + }, + { + "epoch": 18.55, + "learning_rate": 2.752189833095054e-07, + "loss": 0.0016, + "step": 60058 + }, + { + "epoch": 18.55, + "learning_rate": 2.751024707777528e-07, + "loss": 0.0016, + "step": 60059 + }, + { + "epoch": 18.55, + "learning_rate": 2.74985982569741e-07, + "loss": 0.0015, + "step": 60060 + }, + { + "epoch": 18.55, + "learning_rate": 2.7486951868576414e-07, + "loss": 0.0014, + "step": 60061 + }, + { + "epoch": 18.55, + "learning_rate": 2.74753079126111e-07, + "loss": 0.0018, + "step": 60062 + }, + { + "epoch": 18.55, + "learning_rate": 2.746366638910747e-07, + "loss": 0.0015, + "step": 60063 + }, + { + "epoch": 18.55, + "learning_rate": 2.745202729809471e-07, + "loss": 0.0015, + "step": 60064 + }, + { + "epoch": 18.55, + "learning_rate": 2.74403906396018e-07, + "loss": 0.002, + "step": 60065 + }, + { + "epoch": 18.55, + "learning_rate": 2.742875641365783e-07, + "loss": 0.0018, + "step": 60066 + }, + { + "epoch": 18.55, + "learning_rate": 2.741712462029178e-07, + "loss": 0.0018, + "step": 60067 + }, + { + "epoch": 18.55, + "learning_rate": 2.7405495259533066e-07, + "loss": 0.0016, + "step": 60068 + }, + { + "epoch": 18.55, + "learning_rate": 2.7393868331410556e-07, + "loss": 0.0018, + "step": 60069 + }, + { + "epoch": 18.55, + "learning_rate": 2.7382243835953335e-07, + "loss": 0.0019, + "step": 60070 + }, + { + "epoch": 18.55, + "learning_rate": 2.737062177319061e-07, + "loss": 0.0012, + "step": 60071 + }, + { + "epoch": 18.55, + "learning_rate": 2.735900214315124e-07, + "loss": 0.0015, + "step": 60072 + }, + { + "epoch": 18.55, + "learning_rate": 2.734738494586442e-07, + "loss": 0.002, + "step": 60073 + }, + { + "epoch": 18.55, + "learning_rate": 2.7335770181359244e-07, + "loss": 0.0019, + "step": 60074 + }, + { + "epoch": 18.55, + "learning_rate": 2.732415784966469e-07, + "loss": 0.0016, + "step": 60075 + }, + { + "epoch": 18.55, + "learning_rate": 2.731254795080984e-07, + "loss": 0.0019, + "step": 60076 + }, + { + "epoch": 18.55, + "learning_rate": 2.730094048482368e-07, + "loss": 0.0019, + "step": 60077 + }, + { + "epoch": 18.55, + "learning_rate": 2.728933545173529e-07, + "loss": 0.0013, + "step": 60078 + }, + { + "epoch": 18.55, + "learning_rate": 2.727773285157376e-07, + "loss": 0.002, + "step": 60079 + }, + { + "epoch": 18.55, + "learning_rate": 2.7266132684367954e-07, + "loss": 0.0019, + "step": 60080 + }, + { + "epoch": 18.55, + "learning_rate": 2.725453495014696e-07, + "loss": 0.0016, + "step": 60081 + }, + { + "epoch": 18.55, + "learning_rate": 2.724293964893976e-07, + "loss": 0.0018, + "step": 60082 + }, + { + "epoch": 18.55, + "learning_rate": 2.7231346780775435e-07, + "loss": 0.0016, + "step": 60083 + }, + { + "epoch": 18.55, + "learning_rate": 2.7219756345682855e-07, + "loss": 0.001, + "step": 60084 + }, + { + "epoch": 18.56, + "learning_rate": 2.720816834369122e-07, + "loss": 0.0015, + "step": 60085 + }, + { + "epoch": 18.56, + "learning_rate": 2.7196582774829397e-07, + "loss": 0.0021, + "step": 60086 + }, + { + "epoch": 18.56, + "learning_rate": 2.7184999639126244e-07, + "loss": 0.0016, + "step": 60087 + }, + { + "epoch": 18.56, + "learning_rate": 2.717341893661074e-07, + "loss": 0.002, + "step": 60088 + }, + { + "epoch": 18.56, + "learning_rate": 2.7161840667312203e-07, + "loss": 0.0016, + "step": 60089 + }, + { + "epoch": 18.56, + "learning_rate": 2.715026483125927e-07, + "loss": 0.0016, + "step": 60090 + }, + { + "epoch": 18.56, + "learning_rate": 2.71386914284808e-07, + "loss": 0.0015, + "step": 60091 + }, + { + "epoch": 18.56, + "learning_rate": 2.712712045900601e-07, + "loss": 0.0022, + "step": 60092 + }, + { + "epoch": 18.56, + "learning_rate": 2.711555192286375e-07, + "loss": 0.0015, + "step": 60093 + }, + { + "epoch": 18.56, + "learning_rate": 2.710398582008278e-07, + "loss": 0.0015, + "step": 60094 + }, + { + "epoch": 18.56, + "learning_rate": 2.709242215069241e-07, + "loss": 0.002, + "step": 60095 + }, + { + "epoch": 18.56, + "learning_rate": 2.7080860914721285e-07, + "loss": 0.0014, + "step": 60096 + }, + { + "epoch": 18.56, + "learning_rate": 2.706930211219827e-07, + "loss": 0.0021, + "step": 60097 + }, + { + "epoch": 18.56, + "learning_rate": 2.705774574315245e-07, + "loss": 0.0023, + "step": 60098 + }, + { + "epoch": 18.56, + "learning_rate": 2.70461918076127e-07, + "loss": 0.0018, + "step": 60099 + }, + { + "epoch": 18.56, + "learning_rate": 2.7034640305607873e-07, + "loss": 0.0018, + "step": 60100 + }, + { + "epoch": 18.56, + "learning_rate": 2.7023091237166845e-07, + "loss": 0.0017, + "step": 60101 + }, + { + "epoch": 18.56, + "learning_rate": 2.7011544602318587e-07, + "loss": 0.0011, + "step": 60102 + }, + { + "epoch": 18.56, + "learning_rate": 2.7000000401091743e-07, + "loss": 0.002, + "step": 60103 + }, + { + "epoch": 18.56, + "learning_rate": 2.6988458633515404e-07, + "loss": 0.0016, + "step": 60104 + }, + { + "epoch": 18.56, + "learning_rate": 2.6976919299618544e-07, + "loss": 0.002, + "step": 60105 + }, + { + "epoch": 18.56, + "learning_rate": 2.696538239942981e-07, + "loss": 0.002, + "step": 60106 + }, + { + "epoch": 18.56, + "learning_rate": 2.6953847932978064e-07, + "loss": 0.0016, + "step": 60107 + }, + { + "epoch": 18.56, + "learning_rate": 2.694231590029228e-07, + "loss": 0.0014, + "step": 60108 + }, + { + "epoch": 18.56, + "learning_rate": 2.6930786301401225e-07, + "loss": 0.0017, + "step": 60109 + }, + { + "epoch": 18.56, + "learning_rate": 2.6919259136333755e-07, + "loss": 0.0012, + "step": 60110 + }, + { + "epoch": 18.56, + "learning_rate": 2.6907734405118734e-07, + "loss": 0.0018, + "step": 60111 + }, + { + "epoch": 18.56, + "learning_rate": 2.689621210778492e-07, + "loss": 0.0014, + "step": 60112 + }, + { + "epoch": 18.56, + "learning_rate": 2.688469224436108e-07, + "loss": 0.0012, + "step": 60113 + }, + { + "epoch": 18.56, + "learning_rate": 2.687317481487617e-07, + "loss": 0.0011, + "step": 60114 + }, + { + "epoch": 18.56, + "learning_rate": 2.6861659819358957e-07, + "loss": 0.0022, + "step": 60115 + }, + { + "epoch": 18.56, + "learning_rate": 2.685014725783819e-07, + "loss": 0.0011, + "step": 60116 + }, + { + "epoch": 18.57, + "learning_rate": 2.683863713034285e-07, + "loss": 0.0017, + "step": 60117 + }, + { + "epoch": 18.57, + "learning_rate": 2.6827129436901354e-07, + "loss": 0.0012, + "step": 60118 + }, + { + "epoch": 18.57, + "learning_rate": 2.6815624177542686e-07, + "loss": 0.0023, + "step": 60119 + }, + { + "epoch": 18.57, + "learning_rate": 2.680412135229582e-07, + "loss": 0.0014, + "step": 60120 + }, + { + "epoch": 18.57, + "learning_rate": 2.6792620961189285e-07, + "loss": 0.0024, + "step": 60121 + }, + { + "epoch": 18.57, + "learning_rate": 2.6781123004251844e-07, + "loss": 0.0019, + "step": 60122 + }, + { + "epoch": 18.57, + "learning_rate": 2.676962748151246e-07, + "loss": 0.0015, + "step": 60123 + }, + { + "epoch": 18.57, + "learning_rate": 2.6758134392999566e-07, + "loss": 0.0016, + "step": 60124 + }, + { + "epoch": 18.57, + "learning_rate": 2.674664373874214e-07, + "loss": 0.0014, + "step": 60125 + }, + { + "epoch": 18.57, + "learning_rate": 2.6735155518769043e-07, + "loss": 0.0019, + "step": 60126 + }, + { + "epoch": 18.57, + "learning_rate": 2.672366973310869e-07, + "loss": 0.0016, + "step": 60127 + }, + { + "epoch": 18.57, + "learning_rate": 2.671218638178985e-07, + "loss": 0.0012, + "step": 60128 + }, + { + "epoch": 18.57, + "learning_rate": 2.670070546484149e-07, + "loss": 0.0012, + "step": 60129 + }, + { + "epoch": 18.57, + "learning_rate": 2.6689226982292147e-07, + "loss": 0.002, + "step": 60130 + }, + { + "epoch": 18.57, + "learning_rate": 2.6677750934170577e-07, + "loss": 0.0018, + "step": 60131 + }, + { + "epoch": 18.57, + "learning_rate": 2.6666277320505416e-07, + "loss": 0.0028, + "step": 60132 + }, + { + "epoch": 18.57, + "learning_rate": 2.665480614132554e-07, + "loss": 0.0023, + "step": 60133 + }, + { + "epoch": 18.57, + "learning_rate": 2.6643337396659365e-07, + "loss": 0.0013, + "step": 60134 + }, + { + "epoch": 18.57, + "learning_rate": 2.6631871086535755e-07, + "loss": 0.0015, + "step": 60135 + }, + { + "epoch": 18.57, + "learning_rate": 2.662040721098358e-07, + "loss": 0.0016, + "step": 60136 + }, + { + "epoch": 18.57, + "learning_rate": 2.6608945770031145e-07, + "loss": 0.0021, + "step": 60137 + }, + { + "epoch": 18.57, + "learning_rate": 2.6597486763707213e-07, + "loss": 0.002, + "step": 60138 + }, + { + "epoch": 18.57, + "learning_rate": 2.6586030192040533e-07, + "loss": 0.0014, + "step": 60139 + }, + { + "epoch": 18.57, + "learning_rate": 2.6574576055059755e-07, + "loss": 0.0017, + "step": 60140 + }, + { + "epoch": 18.57, + "learning_rate": 2.6563124352793513e-07, + "loss": 0.0027, + "step": 60141 + }, + { + "epoch": 18.57, + "learning_rate": 2.6551675085270566e-07, + "loss": 0.0017, + "step": 60142 + }, + { + "epoch": 18.57, + "learning_rate": 2.654022825251923e-07, + "loss": 0.0018, + "step": 60143 + }, + { + "epoch": 18.57, + "learning_rate": 2.652878385456836e-07, + "loss": 0.0016, + "step": 60144 + }, + { + "epoch": 18.57, + "learning_rate": 2.6517341891446614e-07, + "loss": 0.0016, + "step": 60145 + }, + { + "epoch": 18.57, + "learning_rate": 2.6505902363182514e-07, + "loss": 0.0016, + "step": 60146 + }, + { + "epoch": 18.57, + "learning_rate": 2.6494465269804703e-07, + "loss": 0.0013, + "step": 60147 + }, + { + "epoch": 18.57, + "learning_rate": 2.6483030611341943e-07, + "loss": 0.0021, + "step": 60148 + }, + { + "epoch": 18.58, + "learning_rate": 2.647159838782243e-07, + "loss": 0.0015, + "step": 60149 + }, + { + "epoch": 18.58, + "learning_rate": 2.6460168599275136e-07, + "loss": 0.0016, + "step": 60150 + }, + { + "epoch": 18.58, + "learning_rate": 2.644874124572849e-07, + "loss": 0.0022, + "step": 60151 + }, + { + "epoch": 18.58, + "learning_rate": 2.643731632721125e-07, + "loss": 0.0012, + "step": 60152 + }, + { + "epoch": 18.58, + "learning_rate": 2.6425893843751605e-07, + "loss": 0.002, + "step": 60153 + }, + { + "epoch": 18.58, + "learning_rate": 2.6414473795378537e-07, + "loss": 0.0018, + "step": 60154 + }, + { + "epoch": 18.58, + "learning_rate": 2.6403056182120356e-07, + "loss": 0.0016, + "step": 60155 + }, + { + "epoch": 18.58, + "learning_rate": 2.639164100400571e-07, + "loss": 0.0018, + "step": 60156 + }, + { + "epoch": 18.58, + "learning_rate": 2.6380228261063345e-07, + "loss": 0.0013, + "step": 60157 + }, + { + "epoch": 18.58, + "learning_rate": 2.6368817953321355e-07, + "loss": 0.0015, + "step": 60158 + }, + { + "epoch": 18.58, + "learning_rate": 2.635741008080861e-07, + "loss": 0.0012, + "step": 60159 + }, + { + "epoch": 18.58, + "learning_rate": 2.6346004643553636e-07, + "loss": 0.0017, + "step": 60160 + }, + { + "epoch": 18.58, + "learning_rate": 2.633460164158474e-07, + "loss": 0.0014, + "step": 60161 + }, + { + "epoch": 18.58, + "learning_rate": 2.6323201074930694e-07, + "loss": 0.0023, + "step": 60162 + }, + { + "epoch": 18.58, + "learning_rate": 2.6311802943619903e-07, + "loss": 0.0021, + "step": 60163 + }, + { + "epoch": 18.58, + "learning_rate": 2.6300407247680905e-07, + "loss": 0.0013, + "step": 60164 + }, + { + "epoch": 18.58, + "learning_rate": 2.628901398714201e-07, + "loss": 0.001, + "step": 60165 + }, + { + "epoch": 18.58, + "learning_rate": 2.627762316203197e-07, + "loss": 0.0016, + "step": 60166 + }, + { + "epoch": 18.58, + "learning_rate": 2.626623477237944e-07, + "loss": 0.0011, + "step": 60167 + }, + { + "epoch": 18.58, + "learning_rate": 2.6254848818212384e-07, + "loss": 0.0018, + "step": 60168 + }, + { + "epoch": 18.58, + "learning_rate": 2.624346529955957e-07, + "loss": 0.0016, + "step": 60169 + }, + { + "epoch": 18.58, + "learning_rate": 2.6232084216449514e-07, + "loss": 0.0015, + "step": 60170 + }, + { + "epoch": 18.58, + "learning_rate": 2.6220705568910543e-07, + "loss": 0.0014, + "step": 60171 + }, + { + "epoch": 18.58, + "learning_rate": 2.620932935697129e-07, + "loss": 0.0017, + "step": 60172 + }, + { + "epoch": 18.58, + "learning_rate": 2.6197955580660184e-07, + "loss": 0.0016, + "step": 60173 + }, + { + "epoch": 18.58, + "learning_rate": 2.618658424000542e-07, + "loss": 0.0016, + "step": 60174 + }, + { + "epoch": 18.58, + "learning_rate": 2.6175215335035644e-07, + "loss": 0.002, + "step": 60175 + }, + { + "epoch": 18.58, + "learning_rate": 2.6163848865779385e-07, + "loss": 0.0014, + "step": 60176 + }, + { + "epoch": 18.58, + "learning_rate": 2.6152484832264955e-07, + "loss": 0.0017, + "step": 60177 + }, + { + "epoch": 18.58, + "learning_rate": 2.614112323452067e-07, + "loss": 0.0017, + "step": 60178 + }, + { + "epoch": 18.58, + "learning_rate": 2.612976407257517e-07, + "loss": 0.0012, + "step": 60179 + }, + { + "epoch": 18.58, + "learning_rate": 2.611840734645665e-07, + "loss": 0.0015, + "step": 60180 + }, + { + "epoch": 18.58, + "learning_rate": 2.6107053056193543e-07, + "loss": 0.0016, + "step": 60181 + }, + { + "epoch": 18.59, + "learning_rate": 2.609570120181448e-07, + "loss": 0.0014, + "step": 60182 + }, + { + "epoch": 18.59, + "learning_rate": 2.608435178334778e-07, + "loss": 0.0019, + "step": 60183 + }, + { + "epoch": 18.59, + "learning_rate": 2.607300480082153e-07, + "loss": 0.0018, + "step": 60184 + }, + { + "epoch": 18.59, + "learning_rate": 2.6061660254264485e-07, + "loss": 0.0022, + "step": 60185 + }, + { + "epoch": 18.59, + "learning_rate": 2.6050318143704733e-07, + "loss": 0.0019, + "step": 60186 + }, + { + "epoch": 18.59, + "learning_rate": 2.6038978469170916e-07, + "loss": 0.002, + "step": 60187 + }, + { + "epoch": 18.59, + "learning_rate": 2.6027641230691234e-07, + "loss": 0.0014, + "step": 60188 + }, + { + "epoch": 18.59, + "learning_rate": 2.6016306428293893e-07, + "loss": 0.0017, + "step": 60189 + }, + { + "epoch": 18.59, + "learning_rate": 2.6004974062007525e-07, + "loss": 0.0018, + "step": 60190 + }, + { + "epoch": 18.59, + "learning_rate": 2.599364413186034e-07, + "loss": 0.0012, + "step": 60191 + }, + { + "epoch": 18.59, + "learning_rate": 2.5982316637880754e-07, + "loss": 0.0016, + "step": 60192 + }, + { + "epoch": 18.59, + "learning_rate": 2.597099158009697e-07, + "loss": 0.0015, + "step": 60193 + }, + { + "epoch": 18.59, + "learning_rate": 2.595966895853752e-07, + "loss": 0.0016, + "step": 60194 + }, + { + "epoch": 18.59, + "learning_rate": 2.594834877323049e-07, + "loss": 0.0013, + "step": 60195 + }, + { + "epoch": 18.59, + "learning_rate": 2.59370310242042e-07, + "loss": 0.002, + "step": 60196 + }, + { + "epoch": 18.59, + "learning_rate": 2.5925715711487277e-07, + "loss": 0.0014, + "step": 60197 + }, + { + "epoch": 18.59, + "learning_rate": 2.591440283510771e-07, + "loss": 0.0015, + "step": 60198 + }, + { + "epoch": 18.59, + "learning_rate": 2.590309239509381e-07, + "loss": 0.0014, + "step": 60199 + }, + { + "epoch": 18.59, + "learning_rate": 2.5891784391473883e-07, + "loss": 0.0018, + "step": 60200 + }, + { + "epoch": 18.59, + "learning_rate": 2.588047882427647e-07, + "loss": 0.0014, + "step": 60201 + }, + { + "epoch": 18.59, + "learning_rate": 2.5869175693529427e-07, + "loss": 0.0016, + "step": 60202 + }, + { + "epoch": 18.59, + "learning_rate": 2.5857874999261403e-07, + "loss": 0.0019, + "step": 60203 + }, + { + "epoch": 18.59, + "learning_rate": 2.5846576741500597e-07, + "loss": 0.0027, + "step": 60204 + }, + { + "epoch": 18.59, + "learning_rate": 2.5835280920274984e-07, + "loss": 0.0018, + "step": 60205 + }, + { + "epoch": 18.59, + "learning_rate": 2.5823987535612996e-07, + "loss": 0.0015, + "step": 60206 + }, + { + "epoch": 18.59, + "learning_rate": 2.581269658754304e-07, + "loss": 0.0014, + "step": 60207 + }, + { + "epoch": 18.59, + "learning_rate": 2.5801408076093215e-07, + "loss": 0.0013, + "step": 60208 + }, + { + "epoch": 18.59, + "learning_rate": 2.5790122001291607e-07, + "loss": 0.0017, + "step": 60209 + }, + { + "epoch": 18.59, + "learning_rate": 2.5778838363166745e-07, + "loss": 0.0012, + "step": 60210 + }, + { + "epoch": 18.59, + "learning_rate": 2.5767557161746504e-07, + "loss": 0.0011, + "step": 60211 + }, + { + "epoch": 18.59, + "learning_rate": 2.575627839705941e-07, + "loss": 0.0016, + "step": 60212 + }, + { + "epoch": 18.59, + "learning_rate": 2.574500206913355e-07, + "loss": 0.0012, + "step": 60213 + }, + { + "epoch": 18.6, + "learning_rate": 2.573372817799713e-07, + "loss": 0.0016, + "step": 60214 + }, + { + "epoch": 18.6, + "learning_rate": 2.572245672367835e-07, + "loss": 0.0016, + "step": 60215 + }, + { + "epoch": 18.6, + "learning_rate": 2.57111877062054e-07, + "loss": 0.0016, + "step": 60216 + }, + { + "epoch": 18.6, + "learning_rate": 2.5699921125606487e-07, + "loss": 0.0014, + "step": 60217 + }, + { + "epoch": 18.6, + "learning_rate": 2.568865698190981e-07, + "loss": 0.0013, + "step": 60218 + }, + { + "epoch": 18.6, + "learning_rate": 2.5677395275143456e-07, + "loss": 0.0017, + "step": 60219 + }, + { + "epoch": 18.6, + "learning_rate": 2.566613600533563e-07, + "loss": 0.0018, + "step": 60220 + }, + { + "epoch": 18.6, + "learning_rate": 2.565487917251441e-07, + "loss": 0.0014, + "step": 60221 + }, + { + "epoch": 18.6, + "learning_rate": 2.5643624776708233e-07, + "loss": 0.0018, + "step": 60222 + }, + { + "epoch": 18.6, + "learning_rate": 2.563237281794495e-07, + "loss": 0.0017, + "step": 60223 + }, + { + "epoch": 18.6, + "learning_rate": 2.562112329625288e-07, + "loss": 0.0017, + "step": 60224 + }, + { + "epoch": 18.6, + "learning_rate": 2.560987621166011e-07, + "loss": 0.0017, + "step": 60225 + }, + { + "epoch": 18.6, + "learning_rate": 2.559863156419462e-07, + "loss": 0.0016, + "step": 60226 + }, + { + "epoch": 18.6, + "learning_rate": 2.5587389353884717e-07, + "loss": 0.0016, + "step": 60227 + }, + { + "epoch": 18.6, + "learning_rate": 2.55761495807586e-07, + "loss": 0.0019, + "step": 60228 + }, + { + "epoch": 18.6, + "learning_rate": 2.556491224484425e-07, + "loss": 0.0018, + "step": 60229 + }, + { + "epoch": 18.6, + "learning_rate": 2.5553677346169645e-07, + "loss": 0.0015, + "step": 60230 + }, + { + "epoch": 18.6, + "learning_rate": 2.554244488476298e-07, + "loss": 0.0022, + "step": 60231 + }, + { + "epoch": 18.6, + "learning_rate": 2.5531214860652576e-07, + "loss": 0.0017, + "step": 60232 + }, + { + "epoch": 18.6, + "learning_rate": 2.5519987273866177e-07, + "loss": 0.0014, + "step": 60233 + }, + { + "epoch": 18.6, + "learning_rate": 2.55087621244321e-07, + "loss": 0.0014, + "step": 60234 + }, + { + "epoch": 18.6, + "learning_rate": 2.549753941237842e-07, + "loss": 0.0012, + "step": 60235 + }, + { + "epoch": 18.6, + "learning_rate": 2.548631913773303e-07, + "loss": 0.0013, + "step": 60236 + }, + { + "epoch": 18.6, + "learning_rate": 2.5475101300524107e-07, + "loss": 0.0021, + "step": 60237 + }, + { + "epoch": 18.6, + "learning_rate": 2.546388590077975e-07, + "loss": 0.0013, + "step": 60238 + }, + { + "epoch": 18.6, + "learning_rate": 2.545267293852793e-07, + "loss": 0.0021, + "step": 60239 + }, + { + "epoch": 18.6, + "learning_rate": 2.5441462413796637e-07, + "loss": 0.0014, + "step": 60240 + }, + { + "epoch": 18.6, + "learning_rate": 2.543025432661417e-07, + "loss": 0.0015, + "step": 60241 + }, + { + "epoch": 18.6, + "learning_rate": 2.5419048677008174e-07, + "loss": 0.002, + "step": 60242 + }, + { + "epoch": 18.6, + "learning_rate": 2.5407845465006964e-07, + "loss": 0.0012, + "step": 60243 + }, + { + "epoch": 18.6, + "learning_rate": 2.5396644690638626e-07, + "loss": 0.0019, + "step": 60244 + }, + { + "epoch": 18.6, + "learning_rate": 2.538544635393092e-07, + "loss": 0.0017, + "step": 60245 + }, + { + "epoch": 18.61, + "learning_rate": 2.537425045491193e-07, + "loss": 0.0018, + "step": 60246 + }, + { + "epoch": 18.61, + "learning_rate": 2.536305699360986e-07, + "loss": 0.0009, + "step": 60247 + }, + { + "epoch": 18.61, + "learning_rate": 2.535186597005235e-07, + "loss": 0.0013, + "step": 60248 + }, + { + "epoch": 18.61, + "learning_rate": 2.5340677384267706e-07, + "loss": 0.0012, + "step": 60249 + }, + { + "epoch": 18.61, + "learning_rate": 2.532949123628392e-07, + "loss": 0.0013, + "step": 60250 + }, + { + "epoch": 18.61, + "learning_rate": 2.531830752612863e-07, + "loss": 0.0015, + "step": 60251 + }, + { + "epoch": 18.61, + "learning_rate": 2.530712625383003e-07, + "loss": 0.0014, + "step": 60252 + }, + { + "epoch": 18.61, + "learning_rate": 2.529594741941621e-07, + "loss": 0.0016, + "step": 60253 + }, + { + "epoch": 18.61, + "learning_rate": 2.5284771022914824e-07, + "loss": 0.0023, + "step": 60254 + }, + { + "epoch": 18.61, + "learning_rate": 2.527359706435417e-07, + "loss": 0.0016, + "step": 60255 + }, + { + "epoch": 18.61, + "learning_rate": 2.526242554376201e-07, + "loss": 0.0011, + "step": 60256 + }, + { + "epoch": 18.61, + "learning_rate": 2.525125646116622e-07, + "loss": 0.0011, + "step": 60257 + }, + { + "epoch": 18.61, + "learning_rate": 2.524008981659476e-07, + "loss": 0.0014, + "step": 60258 + }, + { + "epoch": 18.61, + "learning_rate": 2.5228925610075837e-07, + "loss": 0.0021, + "step": 60259 + }, + { + "epoch": 18.61, + "learning_rate": 2.52177638416371e-07, + "loss": 0.0014, + "step": 60260 + }, + { + "epoch": 18.61, + "learning_rate": 2.520660451130641e-07, + "loss": 0.0019, + "step": 60261 + }, + { + "epoch": 18.61, + "learning_rate": 2.5195447619111743e-07, + "loss": 0.0013, + "step": 60262 + }, + { + "epoch": 18.61, + "learning_rate": 2.518429316508131e-07, + "loss": 0.0011, + "step": 60263 + }, + { + "epoch": 18.61, + "learning_rate": 2.5173141149242517e-07, + "loss": 0.0014, + "step": 60264 + }, + { + "epoch": 18.61, + "learning_rate": 2.516199157162369e-07, + "loss": 0.002, + "step": 60265 + }, + { + "epoch": 18.61, + "learning_rate": 2.5150844432252466e-07, + "loss": 0.0016, + "step": 60266 + }, + { + "epoch": 18.61, + "learning_rate": 2.51396997311566e-07, + "loss": 0.0017, + "step": 60267 + }, + { + "epoch": 18.61, + "learning_rate": 2.512855746836429e-07, + "loss": 0.0017, + "step": 60268 + }, + { + "epoch": 18.61, + "learning_rate": 2.5117417643903295e-07, + "loss": 0.0019, + "step": 60269 + }, + { + "epoch": 18.61, + "learning_rate": 2.5106280257801483e-07, + "loss": 0.0022, + "step": 60270 + }, + { + "epoch": 18.61, + "learning_rate": 2.50951453100865e-07, + "loss": 0.0012, + "step": 60271 + }, + { + "epoch": 18.61, + "learning_rate": 2.5084012800786537e-07, + "loss": 0.0015, + "step": 60272 + }, + { + "epoch": 18.61, + "learning_rate": 2.5072882729929137e-07, + "loss": 0.0017, + "step": 60273 + }, + { + "epoch": 18.61, + "learning_rate": 2.506175509754227e-07, + "loss": 0.0016, + "step": 60274 + }, + { + "epoch": 18.61, + "learning_rate": 2.505062990365403e-07, + "loss": 0.0023, + "step": 60275 + }, + { + "epoch": 18.61, + "learning_rate": 2.503950714829173e-07, + "loss": 0.002, + "step": 60276 + }, + { + "epoch": 18.61, + "learning_rate": 2.502838683148345e-07, + "loss": 0.0017, + "step": 60277 + }, + { + "epoch": 18.61, + "learning_rate": 2.501726895325707e-07, + "loss": 0.002, + "step": 60278 + }, + { + "epoch": 18.62, + "learning_rate": 2.500615351364033e-07, + "loss": 0.0018, + "step": 60279 + }, + { + "epoch": 18.62, + "learning_rate": 2.4995040512660996e-07, + "loss": 0.002, + "step": 60280 + }, + { + "epoch": 18.62, + "learning_rate": 2.498392995034704e-07, + "loss": 0.0017, + "step": 60281 + }, + { + "epoch": 18.62, + "learning_rate": 2.497282182672589e-07, + "loss": 0.0014, + "step": 60282 + }, + { + "epoch": 18.62, + "learning_rate": 2.496171614182563e-07, + "loss": 0.0013, + "step": 60283 + }, + { + "epoch": 18.62, + "learning_rate": 2.4950612895673907e-07, + "loss": 0.0018, + "step": 60284 + }, + { + "epoch": 18.62, + "learning_rate": 2.49395120882987e-07, + "loss": 0.0021, + "step": 60285 + }, + { + "epoch": 18.62, + "learning_rate": 2.492841371972743e-07, + "loss": 0.0018, + "step": 60286 + }, + { + "epoch": 18.62, + "learning_rate": 2.491731778998818e-07, + "loss": 0.0012, + "step": 60287 + }, + { + "epoch": 18.62, + "learning_rate": 2.4906224299108383e-07, + "loss": 0.0015, + "step": 60288 + }, + { + "epoch": 18.62, + "learning_rate": 2.489513324711612e-07, + "loss": 0.0014, + "step": 60289 + }, + { + "epoch": 18.62, + "learning_rate": 2.4884044634038927e-07, + "loss": 0.0016, + "step": 60290 + }, + { + "epoch": 18.62, + "learning_rate": 2.4872958459904674e-07, + "loss": 0.0023, + "step": 60291 + }, + { + "epoch": 18.62, + "learning_rate": 2.4861874724740887e-07, + "loss": 0.0016, + "step": 60292 + }, + { + "epoch": 18.62, + "learning_rate": 2.4850793428575436e-07, + "loss": 0.0016, + "step": 60293 + }, + { + "epoch": 18.62, + "learning_rate": 2.483971457143597e-07, + "loss": 0.0018, + "step": 60294 + }, + { + "epoch": 18.62, + "learning_rate": 2.482863815335035e-07, + "loss": 0.0019, + "step": 60295 + }, + { + "epoch": 18.62, + "learning_rate": 2.4817564174346e-07, + "loss": 0.0021, + "step": 60296 + }, + { + "epoch": 18.62, + "learning_rate": 2.4806492634451005e-07, + "loss": 0.0013, + "step": 60297 + }, + { + "epoch": 18.62, + "learning_rate": 2.4795423533692573e-07, + "loss": 0.0017, + "step": 60298 + }, + { + "epoch": 18.62, + "learning_rate": 2.4784356872098793e-07, + "loss": 0.0016, + "step": 60299 + }, + { + "epoch": 18.62, + "learning_rate": 2.47732926496973e-07, + "loss": 0.0024, + "step": 60300 + }, + { + "epoch": 18.62, + "learning_rate": 2.476223086651552e-07, + "loss": 0.0021, + "step": 60301 + }, + { + "epoch": 18.62, + "learning_rate": 2.475117152258133e-07, + "loss": 0.0019, + "step": 60302 + }, + { + "epoch": 18.62, + "learning_rate": 2.4740114617922363e-07, + "loss": 0.0016, + "step": 60303 + }, + { + "epoch": 18.62, + "learning_rate": 2.4729060152566155e-07, + "loss": 0.0016, + "step": 60304 + }, + { + "epoch": 18.62, + "learning_rate": 2.471800812654057e-07, + "loss": 0.0014, + "step": 60305 + }, + { + "epoch": 18.62, + "learning_rate": 2.470695853987315e-07, + "loss": 0.0013, + "step": 60306 + }, + { + "epoch": 18.62, + "learning_rate": 2.469591139259131e-07, + "loss": 0.0016, + "step": 60307 + }, + { + "epoch": 18.62, + "learning_rate": 2.468486668472303e-07, + "loss": 0.0016, + "step": 60308 + }, + { + "epoch": 18.62, + "learning_rate": 2.467382441629573e-07, + "loss": 0.0019, + "step": 60309 + }, + { + "epoch": 18.62, + "learning_rate": 2.4662784587337064e-07, + "loss": 0.0014, + "step": 60310 + }, + { + "epoch": 18.63, + "learning_rate": 2.4651747197874773e-07, + "loss": 0.0014, + "step": 60311 + }, + { + "epoch": 18.63, + "learning_rate": 2.4640712247936293e-07, + "loss": 0.0018, + "step": 60312 + }, + { + "epoch": 18.63, + "learning_rate": 2.462967973754926e-07, + "loss": 0.0017, + "step": 60313 + }, + { + "epoch": 18.63, + "learning_rate": 2.461864966674121e-07, + "loss": 0.0015, + "step": 60314 + }, + { + "epoch": 18.63, + "learning_rate": 2.4607622035540014e-07, + "loss": 0.0021, + "step": 60315 + }, + { + "epoch": 18.63, + "learning_rate": 2.4596596843972975e-07, + "loss": 0.0032, + "step": 60316 + }, + { + "epoch": 18.63, + "learning_rate": 2.4585574092067744e-07, + "loss": 0.0017, + "step": 60317 + }, + { + "epoch": 18.63, + "learning_rate": 2.457455377985185e-07, + "loss": 0.0014, + "step": 60318 + }, + { + "epoch": 18.63, + "learning_rate": 2.456353590735294e-07, + "loss": 0.0019, + "step": 60319 + }, + { + "epoch": 18.63, + "learning_rate": 2.4552520474598443e-07, + "loss": 0.0015, + "step": 60320 + }, + { + "epoch": 18.63, + "learning_rate": 2.454150748161621e-07, + "loss": 0.0017, + "step": 60321 + }, + { + "epoch": 18.63, + "learning_rate": 2.4530496928433454e-07, + "loss": 0.0013, + "step": 60322 + }, + { + "epoch": 18.63, + "learning_rate": 2.451948881507782e-07, + "loss": 0.0019, + "step": 60323 + }, + { + "epoch": 18.63, + "learning_rate": 2.4508483141576943e-07, + "loss": 0.0016, + "step": 60324 + }, + { + "epoch": 18.63, + "learning_rate": 2.4497479907958144e-07, + "loss": 0.0015, + "step": 60325 + }, + { + "epoch": 18.63, + "learning_rate": 2.4486479114249175e-07, + "loss": 0.0014, + "step": 60326 + }, + { + "epoch": 18.63, + "learning_rate": 2.4475480760477346e-07, + "loss": 0.0018, + "step": 60327 + }, + { + "epoch": 18.63, + "learning_rate": 2.446448484667041e-07, + "loss": 0.0014, + "step": 60328 + }, + { + "epoch": 18.63, + "learning_rate": 2.4453491372855576e-07, + "loss": 0.0015, + "step": 60329 + }, + { + "epoch": 18.63, + "learning_rate": 2.444250033906048e-07, + "loss": 0.0026, + "step": 60330 + }, + { + "epoch": 18.63, + "learning_rate": 2.4431511745312777e-07, + "loss": 0.0016, + "step": 60331 + }, + { + "epoch": 18.63, + "learning_rate": 2.442052559163977e-07, + "loss": 0.0025, + "step": 60332 + }, + { + "epoch": 18.63, + "learning_rate": 2.4409541878068874e-07, + "loss": 0.0017, + "step": 60333 + }, + { + "epoch": 18.63, + "learning_rate": 2.4398560604627754e-07, + "loss": 0.0017, + "step": 60334 + }, + { + "epoch": 18.63, + "learning_rate": 2.4387581771343595e-07, + "loss": 0.0016, + "step": 60335 + }, + { + "epoch": 18.63, + "learning_rate": 2.4376605378244154e-07, + "loss": 0.0011, + "step": 60336 + }, + { + "epoch": 18.63, + "learning_rate": 2.436563142535686e-07, + "loss": 0.0016, + "step": 60337 + }, + { + "epoch": 18.63, + "learning_rate": 2.435465991270891e-07, + "loss": 0.0019, + "step": 60338 + }, + { + "epoch": 18.63, + "learning_rate": 2.434369084032784e-07, + "loss": 0.0019, + "step": 60339 + }, + { + "epoch": 18.63, + "learning_rate": 2.4332724208241397e-07, + "loss": 0.0015, + "step": 60340 + }, + { + "epoch": 18.63, + "learning_rate": 2.432176001647657e-07, + "loss": 0.0015, + "step": 60341 + }, + { + "epoch": 18.63, + "learning_rate": 2.4310798265061e-07, + "loss": 0.0017, + "step": 60342 + }, + { + "epoch": 18.63, + "learning_rate": 2.4299838954022213e-07, + "loss": 0.0017, + "step": 60343 + }, + { + "epoch": 18.64, + "learning_rate": 2.428888208338731e-07, + "loss": 0.0009, + "step": 60344 + }, + { + "epoch": 18.64, + "learning_rate": 2.427792765318393e-07, + "loss": 0.0019, + "step": 60345 + }, + { + "epoch": 18.64, + "learning_rate": 2.4266975663439385e-07, + "loss": 0.0018, + "step": 60346 + }, + { + "epoch": 18.64, + "learning_rate": 2.4256026114181207e-07, + "loss": 0.0018, + "step": 60347 + }, + { + "epoch": 18.64, + "learning_rate": 2.42450790054366e-07, + "loss": 0.0013, + "step": 60348 + }, + { + "epoch": 18.64, + "learning_rate": 2.4234134337232984e-07, + "loss": 0.002, + "step": 60349 + }, + { + "epoch": 18.64, + "learning_rate": 2.4223192109597783e-07, + "loss": 0.0017, + "step": 60350 + }, + { + "epoch": 18.64, + "learning_rate": 2.42122523225583e-07, + "loss": 0.0016, + "step": 60351 + }, + { + "epoch": 18.64, + "learning_rate": 2.4201314976142086e-07, + "loss": 0.002, + "step": 60352 + }, + { + "epoch": 18.64, + "learning_rate": 2.419038007037633e-07, + "loss": 0.0016, + "step": 60353 + }, + { + "epoch": 18.64, + "learning_rate": 2.417944760528834e-07, + "loss": 0.002, + "step": 60354 + }, + { + "epoch": 18.64, + "learning_rate": 2.416851758090555e-07, + "loss": 0.002, + "step": 60355 + }, + { + "epoch": 18.64, + "learning_rate": 2.415758999725526e-07, + "loss": 0.0018, + "step": 60356 + }, + { + "epoch": 18.64, + "learning_rate": 2.41466648543649e-07, + "loss": 0.0019, + "step": 60357 + }, + { + "epoch": 18.64, + "learning_rate": 2.4135742152261663e-07, + "loss": 0.0016, + "step": 60358 + }, + { + "epoch": 18.64, + "learning_rate": 2.412482189097287e-07, + "loss": 0.0021, + "step": 60359 + }, + { + "epoch": 18.64, + "learning_rate": 2.411390407052594e-07, + "loss": 0.0017, + "step": 60360 + }, + { + "epoch": 18.64, + "learning_rate": 2.410298869094807e-07, + "loss": 0.002, + "step": 60361 + }, + { + "epoch": 18.64, + "learning_rate": 2.409207575226669e-07, + "loss": 0.0011, + "step": 60362 + }, + { + "epoch": 18.64, + "learning_rate": 2.4081165254508985e-07, + "loss": 0.0015, + "step": 60363 + }, + { + "epoch": 18.64, + "learning_rate": 2.4070257197702285e-07, + "loss": 0.0013, + "step": 60364 + }, + { + "epoch": 18.64, + "learning_rate": 2.4059351581873893e-07, + "loss": 0.0021, + "step": 60365 + }, + { + "epoch": 18.64, + "learning_rate": 2.4048448407051005e-07, + "loss": 0.0019, + "step": 60366 + }, + { + "epoch": 18.64, + "learning_rate": 2.4037547673261054e-07, + "loss": 0.0017, + "step": 60367 + }, + { + "epoch": 18.64, + "learning_rate": 2.402664938053123e-07, + "loss": 0.002, + "step": 60368 + }, + { + "epoch": 18.64, + "learning_rate": 2.401575352888863e-07, + "loss": 0.0017, + "step": 60369 + }, + { + "epoch": 18.64, + "learning_rate": 2.400486011836067e-07, + "loss": 0.002, + "step": 60370 + }, + { + "epoch": 18.64, + "learning_rate": 2.399396914897456e-07, + "loss": 0.0023, + "step": 60371 + }, + { + "epoch": 18.64, + "learning_rate": 2.398308062075749e-07, + "loss": 0.0016, + "step": 60372 + }, + { + "epoch": 18.64, + "learning_rate": 2.3972194533736893e-07, + "loss": 0.0015, + "step": 60373 + }, + { + "epoch": 18.64, + "learning_rate": 2.3961310887939846e-07, + "loss": 0.0019, + "step": 60374 + }, + { + "epoch": 18.64, + "learning_rate": 2.395042968339345e-07, + "loss": 0.0013, + "step": 60375 + }, + { + "epoch": 18.65, + "learning_rate": 2.393955092012512e-07, + "loss": 0.0016, + "step": 60376 + }, + { + "epoch": 18.65, + "learning_rate": 2.392867459816206e-07, + "loss": 0.0016, + "step": 60377 + }, + { + "epoch": 18.65, + "learning_rate": 2.391780071753136e-07, + "loss": 0.0012, + "step": 60378 + }, + { + "epoch": 18.65, + "learning_rate": 2.390692927826022e-07, + "loss": 0.0012, + "step": 60379 + }, + { + "epoch": 18.65, + "learning_rate": 2.3896060280375944e-07, + "loss": 0.0015, + "step": 60380 + }, + { + "epoch": 18.65, + "learning_rate": 2.388519372390552e-07, + "loss": 0.0017, + "step": 60381 + }, + { + "epoch": 18.65, + "learning_rate": 2.387432960887637e-07, + "loss": 0.0015, + "step": 60382 + }, + { + "epoch": 18.65, + "learning_rate": 2.386346793531569e-07, + "loss": 0.0015, + "step": 60383 + }, + { + "epoch": 18.65, + "learning_rate": 2.3852608703250235e-07, + "loss": 0.0013, + "step": 60384 + }, + { + "epoch": 18.65, + "learning_rate": 2.3841751912707544e-07, + "loss": 0.0015, + "step": 60385 + }, + { + "epoch": 18.65, + "learning_rate": 2.3830897563714817e-07, + "loss": 0.0018, + "step": 60386 + }, + { + "epoch": 18.65, + "learning_rate": 2.3820045656298806e-07, + "loss": 0.0018, + "step": 60387 + }, + { + "epoch": 18.65, + "learning_rate": 2.3809196190487162e-07, + "loss": 0.0016, + "step": 60388 + }, + { + "epoch": 18.65, + "learning_rate": 2.3798349166306634e-07, + "loss": 0.0012, + "step": 60389 + }, + { + "epoch": 18.65, + "learning_rate": 2.3787504583784426e-07, + "loss": 0.0019, + "step": 60390 + }, + { + "epoch": 18.65, + "learning_rate": 2.377666244294774e-07, + "loss": 0.0018, + "step": 60391 + }, + { + "epoch": 18.65, + "learning_rate": 2.3765822743823775e-07, + "loss": 0.0014, + "step": 60392 + }, + { + "epoch": 18.65, + "learning_rate": 2.375498548643951e-07, + "loss": 0.0016, + "step": 60393 + }, + { + "epoch": 18.65, + "learning_rate": 2.374415067082203e-07, + "loss": 0.0014, + "step": 60394 + }, + { + "epoch": 18.65, + "learning_rate": 2.373331829699843e-07, + "loss": 0.0021, + "step": 60395 + }, + { + "epoch": 18.65, + "learning_rate": 2.372248836499602e-07, + "loss": 0.0014, + "step": 60396 + }, + { + "epoch": 18.65, + "learning_rate": 2.3711660874841557e-07, + "loss": 0.0017, + "step": 60397 + }, + { + "epoch": 18.65, + "learning_rate": 2.3700835826562464e-07, + "loss": 0.0019, + "step": 60398 + }, + { + "epoch": 18.65, + "learning_rate": 2.3690013220185604e-07, + "loss": 0.0017, + "step": 60399 + }, + { + "epoch": 18.65, + "learning_rate": 2.367919305573807e-07, + "loss": 0.0014, + "step": 60400 + }, + { + "epoch": 18.65, + "learning_rate": 2.366837533324684e-07, + "loss": 0.0017, + "step": 60401 + }, + { + "epoch": 18.65, + "learning_rate": 2.3657560052739225e-07, + "loss": 0.0012, + "step": 60402 + }, + { + "epoch": 18.65, + "learning_rate": 2.3646747214241984e-07, + "loss": 0.0015, + "step": 60403 + }, + { + "epoch": 18.65, + "learning_rate": 2.3635936817782423e-07, + "loss": 0.0015, + "step": 60404 + }, + { + "epoch": 18.65, + "learning_rate": 2.3625128863387525e-07, + "loss": 0.0021, + "step": 60405 + }, + { + "epoch": 18.65, + "learning_rate": 2.3614323351084046e-07, + "loss": 0.0019, + "step": 60406 + }, + { + "epoch": 18.65, + "learning_rate": 2.3603520280899294e-07, + "loss": 0.0011, + "step": 60407 + }, + { + "epoch": 18.66, + "learning_rate": 2.3592719652860363e-07, + "loss": 0.0013, + "step": 60408 + }, + { + "epoch": 18.66, + "learning_rate": 2.3581921466994119e-07, + "loss": 0.0019, + "step": 60409 + }, + { + "epoch": 18.66, + "learning_rate": 2.3571125723327427e-07, + "loss": 0.0018, + "step": 60410 + }, + { + "epoch": 18.66, + "learning_rate": 2.3560332421887488e-07, + "loss": 0.0013, + "step": 60411 + }, + { + "epoch": 18.66, + "learning_rate": 2.3549541562701283e-07, + "loss": 0.0013, + "step": 60412 + }, + { + "epoch": 18.66, + "learning_rate": 2.353875314579568e-07, + "loss": 0.0017, + "step": 60413 + }, + { + "epoch": 18.66, + "learning_rate": 2.3527967171197873e-07, + "loss": 0.0026, + "step": 60414 + }, + { + "epoch": 18.66, + "learning_rate": 2.3517183638934626e-07, + "loss": 0.0015, + "step": 60415 + }, + { + "epoch": 18.66, + "learning_rate": 2.3506402549033025e-07, + "loss": 0.0017, + "step": 60416 + }, + { + "epoch": 18.66, + "learning_rate": 2.3495623901520048e-07, + "loss": 0.0012, + "step": 60417 + }, + { + "epoch": 18.66, + "learning_rate": 2.3484847696422564e-07, + "loss": 0.0016, + "step": 60418 + }, + { + "epoch": 18.66, + "learning_rate": 2.347407393376766e-07, + "loss": 0.0019, + "step": 60419 + }, + { + "epoch": 18.66, + "learning_rate": 2.3463302613582207e-07, + "loss": 0.002, + "step": 60420 + }, + { + "epoch": 18.66, + "learning_rate": 2.3452533735893068e-07, + "loss": 0.0015, + "step": 60421 + }, + { + "epoch": 18.66, + "learning_rate": 2.3441767300727226e-07, + "loss": 0.0012, + "step": 60422 + }, + { + "epoch": 18.66, + "learning_rate": 2.3431003308111767e-07, + "loss": 0.0012, + "step": 60423 + }, + { + "epoch": 18.66, + "learning_rate": 2.3420241758073447e-07, + "loss": 0.0018, + "step": 60424 + }, + { + "epoch": 18.66, + "learning_rate": 2.3409482650639138e-07, + "loss": 0.0016, + "step": 60425 + }, + { + "epoch": 18.66, + "learning_rate": 2.3398725985835812e-07, + "loss": 0.0024, + "step": 60426 + }, + { + "epoch": 18.66, + "learning_rate": 2.3387971763690454e-07, + "loss": 0.0014, + "step": 60427 + }, + { + "epoch": 18.66, + "learning_rate": 2.3377219984229816e-07, + "loss": 0.0015, + "step": 60428 + }, + { + "epoch": 18.66, + "learning_rate": 2.3366470647481098e-07, + "loss": 0.0017, + "step": 60429 + }, + { + "epoch": 18.66, + "learning_rate": 2.3355723753470839e-07, + "loss": 0.0013, + "step": 60430 + }, + { + "epoch": 18.66, + "learning_rate": 2.334497930222601e-07, + "loss": 0.0015, + "step": 60431 + }, + { + "epoch": 18.66, + "learning_rate": 2.3334237293773488e-07, + "loss": 0.0014, + "step": 60432 + }, + { + "epoch": 18.66, + "learning_rate": 2.3323497728140243e-07, + "loss": 0.0012, + "step": 60433 + }, + { + "epoch": 18.66, + "learning_rate": 2.3312760605353036e-07, + "loss": 0.0013, + "step": 60434 + }, + { + "epoch": 18.66, + "learning_rate": 2.330202592543873e-07, + "loss": 0.0014, + "step": 60435 + }, + { + "epoch": 18.66, + "learning_rate": 2.329129368842431e-07, + "loss": 0.0019, + "step": 60436 + }, + { + "epoch": 18.66, + "learning_rate": 2.3280563894336305e-07, + "loss": 0.0015, + "step": 60437 + }, + { + "epoch": 18.66, + "learning_rate": 2.3269836543201919e-07, + "loss": 0.0014, + "step": 60438 + }, + { + "epoch": 18.66, + "learning_rate": 2.3259111635047793e-07, + "loss": 0.002, + "step": 60439 + }, + { + "epoch": 18.66, + "learning_rate": 2.32483891699008e-07, + "loss": 0.0017, + "step": 60440 + }, + { + "epoch": 18.67, + "learning_rate": 2.3237669147787577e-07, + "loss": 0.0017, + "step": 60441 + }, + { + "epoch": 18.67, + "learning_rate": 2.3226951568735224e-07, + "loss": 0.0013, + "step": 60442 + }, + { + "epoch": 18.67, + "learning_rate": 2.321623643277038e-07, + "loss": 0.0016, + "step": 60443 + }, + { + "epoch": 18.67, + "learning_rate": 2.3205523739919912e-07, + "loss": 0.0016, + "step": 60444 + }, + { + "epoch": 18.67, + "learning_rate": 2.319481349021069e-07, + "loss": 0.0019, + "step": 60445 + }, + { + "epoch": 18.67, + "learning_rate": 2.3184105683669135e-07, + "loss": 0.0015, + "step": 60446 + }, + { + "epoch": 18.67, + "learning_rate": 2.3173400320322447e-07, + "loss": 0.0016, + "step": 60447 + }, + { + "epoch": 18.67, + "learning_rate": 2.3162697400197276e-07, + "loss": 0.0017, + "step": 60448 + }, + { + "epoch": 18.67, + "learning_rate": 2.3151996923320264e-07, + "loss": 0.0025, + "step": 60449 + }, + { + "epoch": 18.67, + "learning_rate": 2.3141298889718388e-07, + "loss": 0.0021, + "step": 60450 + }, + { + "epoch": 18.67, + "learning_rate": 2.3130603299418298e-07, + "loss": 0.0014, + "step": 60451 + }, + { + "epoch": 18.67, + "learning_rate": 2.3119910152446634e-07, + "loss": 0.0023, + "step": 60452 + }, + { + "epoch": 18.67, + "learning_rate": 2.3109219448830155e-07, + "loss": 0.002, + "step": 60453 + }, + { + "epoch": 18.67, + "learning_rate": 2.3098531188595953e-07, + "loss": 0.0016, + "step": 60454 + }, + { + "epoch": 18.67, + "learning_rate": 2.3087845371770334e-07, + "loss": 0.0016, + "step": 60455 + }, + { + "epoch": 18.67, + "learning_rate": 2.307716199838017e-07, + "loss": 0.0016, + "step": 60456 + }, + { + "epoch": 18.67, + "learning_rate": 2.3066481068452328e-07, + "loss": 0.0022, + "step": 60457 + }, + { + "epoch": 18.67, + "learning_rate": 2.3055802582013343e-07, + "loss": 0.002, + "step": 60458 + }, + { + "epoch": 18.67, + "learning_rate": 2.3045126539089857e-07, + "loss": 0.0014, + "step": 60459 + }, + { + "epoch": 18.67, + "learning_rate": 2.3034452939708852e-07, + "loss": 0.0023, + "step": 60460 + }, + { + "epoch": 18.67, + "learning_rate": 2.3023781783896858e-07, + "loss": 0.0017, + "step": 60461 + }, + { + "epoch": 18.67, + "learning_rate": 2.3013113071680526e-07, + "loss": 0.002, + "step": 60462 + }, + { + "epoch": 18.67, + "learning_rate": 2.300244680308661e-07, + "loss": 0.0027, + "step": 60463 + }, + { + "epoch": 18.67, + "learning_rate": 2.2991782978141754e-07, + "loss": 0.0011, + "step": 60464 + }, + { + "epoch": 18.67, + "learning_rate": 2.2981121596872713e-07, + "loss": 0.0021, + "step": 60465 + }, + { + "epoch": 18.67, + "learning_rate": 2.2970462659305914e-07, + "loss": 0.0019, + "step": 60466 + }, + { + "epoch": 18.67, + "learning_rate": 2.2959806165468336e-07, + "loss": 0.0018, + "step": 60467 + }, + { + "epoch": 18.67, + "learning_rate": 2.2949152115386397e-07, + "loss": 0.0017, + "step": 60468 + }, + { + "epoch": 18.67, + "learning_rate": 2.2938500509086859e-07, + "loss": 0.0014, + "step": 60469 + }, + { + "epoch": 18.67, + "learning_rate": 2.2927851346596363e-07, + "loss": 0.0018, + "step": 60470 + }, + { + "epoch": 18.67, + "learning_rate": 2.291720462794156e-07, + "loss": 0.0023, + "step": 60471 + }, + { + "epoch": 18.67, + "learning_rate": 2.2906560353148976e-07, + "loss": 0.0014, + "step": 60472 + }, + { + "epoch": 18.68, + "learning_rate": 2.2895918522245376e-07, + "loss": 0.0014, + "step": 60473 + }, + { + "epoch": 18.68, + "learning_rate": 2.2885279135257177e-07, + "loss": 0.0023, + "step": 60474 + }, + { + "epoch": 18.68, + "learning_rate": 2.2874642192211137e-07, + "loss": 0.0017, + "step": 60475 + }, + { + "epoch": 18.68, + "learning_rate": 2.2864007693133906e-07, + "loss": 0.0017, + "step": 60476 + }, + { + "epoch": 18.68, + "learning_rate": 2.28533756380519e-07, + "loss": 0.0015, + "step": 60477 + }, + { + "epoch": 18.68, + "learning_rate": 2.284274602699188e-07, + "loss": 0.0013, + "step": 60478 + }, + { + "epoch": 18.68, + "learning_rate": 2.283211885998038e-07, + "loss": 0.0016, + "step": 60479 + }, + { + "epoch": 18.68, + "learning_rate": 2.282149413704393e-07, + "loss": 0.0017, + "step": 60480 + }, + { + "epoch": 18.68, + "learning_rate": 2.2810871858209293e-07, + "loss": 0.0019, + "step": 60481 + }, + { + "epoch": 18.68, + "learning_rate": 2.2800252023502778e-07, + "loss": 0.0011, + "step": 60482 + }, + { + "epoch": 18.68, + "learning_rate": 2.278963463295103e-07, + "loss": 0.0018, + "step": 60483 + }, + { + "epoch": 18.68, + "learning_rate": 2.2779019686580696e-07, + "loss": 0.0013, + "step": 60484 + }, + { + "epoch": 18.68, + "learning_rate": 2.2768407184418306e-07, + "loss": 0.0015, + "step": 60485 + }, + { + "epoch": 18.68, + "learning_rate": 2.2757797126490289e-07, + "loss": 0.0017, + "step": 60486 + }, + { + "epoch": 18.68, + "learning_rate": 2.2747189512823288e-07, + "loss": 0.0021, + "step": 60487 + }, + { + "epoch": 18.68, + "learning_rate": 2.2736584343443834e-07, + "loss": 0.0018, + "step": 60488 + }, + { + "epoch": 18.68, + "learning_rate": 2.2725981618378358e-07, + "loss": 0.0017, + "step": 60489 + }, + { + "epoch": 18.68, + "learning_rate": 2.2715381337653387e-07, + "loss": 0.0018, + "step": 60490 + }, + { + "epoch": 18.68, + "learning_rate": 2.270478350129568e-07, + "loss": 0.0015, + "step": 60491 + }, + { + "epoch": 18.68, + "learning_rate": 2.2694188109331438e-07, + "loss": 0.0016, + "step": 60492 + }, + { + "epoch": 18.68, + "learning_rate": 2.268359516178731e-07, + "loss": 0.0012, + "step": 60493 + }, + { + "epoch": 18.68, + "learning_rate": 2.267300465868971e-07, + "loss": 0.001, + "step": 60494 + }, + { + "epoch": 18.68, + "learning_rate": 2.2662416600065295e-07, + "loss": 0.0016, + "step": 60495 + }, + { + "epoch": 18.68, + "learning_rate": 2.265183098594037e-07, + "loss": 0.0021, + "step": 60496 + }, + { + "epoch": 18.68, + "learning_rate": 2.264124781634136e-07, + "loss": 0.0018, + "step": 60497 + }, + { + "epoch": 18.68, + "learning_rate": 2.2630667091295023e-07, + "loss": 0.0019, + "step": 60498 + }, + { + "epoch": 18.68, + "learning_rate": 2.2620088810827555e-07, + "loss": 0.0024, + "step": 60499 + }, + { + "epoch": 18.68, + "learning_rate": 2.2609512974965497e-07, + "loss": 0.0027, + "step": 60500 + }, + { + "epoch": 18.68, + "learning_rate": 2.259893958373538e-07, + "loss": 0.0021, + "step": 60501 + }, + { + "epoch": 18.68, + "learning_rate": 2.2588368637163627e-07, + "loss": 0.0017, + "step": 60502 + }, + { + "epoch": 18.68, + "learning_rate": 2.257780013527644e-07, + "loss": 0.0016, + "step": 60503 + }, + { + "epoch": 18.68, + "learning_rate": 2.2567234078100686e-07, + "loss": 0.0015, + "step": 60504 + }, + { + "epoch": 18.69, + "learning_rate": 2.2556670465662344e-07, + "loss": 0.001, + "step": 60505 + }, + { + "epoch": 18.69, + "learning_rate": 2.2546109297988173e-07, + "loss": 0.0013, + "step": 60506 + }, + { + "epoch": 18.69, + "learning_rate": 2.2535550575104482e-07, + "loss": 0.0014, + "step": 60507 + }, + { + "epoch": 18.69, + "learning_rate": 2.2524994297037472e-07, + "loss": 0.0016, + "step": 60508 + }, + { + "epoch": 18.69, + "learning_rate": 2.2514440463813792e-07, + "loss": 0.0015, + "step": 60509 + }, + { + "epoch": 18.69, + "learning_rate": 2.250388907545986e-07, + "loss": 0.0017, + "step": 60510 + }, + { + "epoch": 18.69, + "learning_rate": 2.2493340132001995e-07, + "loss": 0.0016, + "step": 60511 + }, + { + "epoch": 18.69, + "learning_rate": 2.2482793633466503e-07, + "loss": 0.0016, + "step": 60512 + }, + { + "epoch": 18.69, + "learning_rate": 2.2472249579879923e-07, + "loss": 0.0016, + "step": 60513 + }, + { + "epoch": 18.69, + "learning_rate": 2.2461707971268455e-07, + "loss": 0.0023, + "step": 60514 + }, + { + "epoch": 18.69, + "learning_rate": 2.245116880765852e-07, + "loss": 0.0013, + "step": 60515 + }, + { + "epoch": 18.69, + "learning_rate": 2.2440632089076653e-07, + "loss": 0.0016, + "step": 60516 + }, + { + "epoch": 18.69, + "learning_rate": 2.2430097815548946e-07, + "loss": 0.0013, + "step": 60517 + }, + { + "epoch": 18.69, + "learning_rate": 2.241956598710182e-07, + "loss": 0.0017, + "step": 60518 + }, + { + "epoch": 18.69, + "learning_rate": 2.2409036603761813e-07, + "loss": 0.0019, + "step": 60519 + }, + { + "epoch": 18.69, + "learning_rate": 2.2398509665555012e-07, + "loss": 0.0018, + "step": 60520 + }, + { + "epoch": 18.69, + "learning_rate": 2.238798517250773e-07, + "loss": 0.0019, + "step": 60521 + }, + { + "epoch": 18.69, + "learning_rate": 2.2377463124646725e-07, + "loss": 0.0016, + "step": 60522 + }, + { + "epoch": 18.69, + "learning_rate": 2.2366943521997642e-07, + "loss": 0.0019, + "step": 60523 + }, + { + "epoch": 18.69, + "learning_rate": 2.2356426364587237e-07, + "loss": 0.0016, + "step": 60524 + }, + { + "epoch": 18.69, + "learning_rate": 2.234591165244171e-07, + "loss": 0.0017, + "step": 60525 + }, + { + "epoch": 18.69, + "learning_rate": 2.2335399385587486e-07, + "loss": 0.0017, + "step": 60526 + }, + { + "epoch": 18.69, + "learning_rate": 2.2324889564050766e-07, + "loss": 0.0015, + "step": 60527 + }, + { + "epoch": 18.69, + "learning_rate": 2.2314382187857642e-07, + "loss": 0.0016, + "step": 60528 + }, + { + "epoch": 18.69, + "learning_rate": 2.2303877257034755e-07, + "loss": 0.0019, + "step": 60529 + }, + { + "epoch": 18.69, + "learning_rate": 2.229337477160809e-07, + "loss": 0.0015, + "step": 60530 + }, + { + "epoch": 18.69, + "learning_rate": 2.2282874731603953e-07, + "loss": 0.0023, + "step": 60531 + }, + { + "epoch": 18.69, + "learning_rate": 2.2272377137048884e-07, + "loss": 0.0013, + "step": 60532 + }, + { + "epoch": 18.69, + "learning_rate": 2.2261881987968747e-07, + "loss": 0.0018, + "step": 60533 + }, + { + "epoch": 18.69, + "learning_rate": 2.2251389284389967e-07, + "loss": 0.0012, + "step": 60534 + }, + { + "epoch": 18.69, + "learning_rate": 2.2240899026338858e-07, + "loss": 0.0014, + "step": 60535 + }, + { + "epoch": 18.69, + "learning_rate": 2.2230411213841507e-07, + "loss": 0.0021, + "step": 60536 + }, + { + "epoch": 18.69, + "learning_rate": 2.221992584692434e-07, + "loss": 0.0014, + "step": 60537 + }, + { + "epoch": 18.7, + "learning_rate": 2.2209442925613445e-07, + "loss": 0.0015, + "step": 60538 + }, + { + "epoch": 18.7, + "learning_rate": 2.2198962449935025e-07, + "loss": 0.0018, + "step": 60539 + }, + { + "epoch": 18.7, + "learning_rate": 2.218848441991528e-07, + "loss": 0.0025, + "step": 60540 + }, + { + "epoch": 18.7, + "learning_rate": 2.2178008835580632e-07, + "loss": 0.0016, + "step": 60541 + }, + { + "epoch": 18.7, + "learning_rate": 2.2167535696957066e-07, + "loss": 0.0022, + "step": 60542 + }, + { + "epoch": 18.7, + "learning_rate": 2.2157065004070776e-07, + "loss": 0.0016, + "step": 60543 + }, + { + "epoch": 18.7, + "learning_rate": 2.2146596756948192e-07, + "loss": 0.0016, + "step": 60544 + }, + { + "epoch": 18.7, + "learning_rate": 2.2136130955615064e-07, + "loss": 0.0015, + "step": 60545 + }, + { + "epoch": 18.7, + "learning_rate": 2.2125667600097933e-07, + "loss": 0.0016, + "step": 60546 + }, + { + "epoch": 18.7, + "learning_rate": 2.2115206690422998e-07, + "loss": 0.0016, + "step": 60547 + }, + { + "epoch": 18.7, + "learning_rate": 2.2104748226616124e-07, + "loss": 0.0021, + "step": 60548 + }, + { + "epoch": 18.7, + "learning_rate": 2.2094292208703738e-07, + "loss": 0.0014, + "step": 60549 + }, + { + "epoch": 18.7, + "learning_rate": 2.208383863671182e-07, + "loss": 0.0023, + "step": 60550 + }, + { + "epoch": 18.7, + "learning_rate": 2.2073387510666566e-07, + "loss": 0.0018, + "step": 60551 + }, + { + "epoch": 18.7, + "learning_rate": 2.2062938830594183e-07, + "loss": 0.0012, + "step": 60552 + }, + { + "epoch": 18.7, + "learning_rate": 2.2052492596520759e-07, + "loss": 0.0012, + "step": 60553 + }, + { + "epoch": 18.7, + "learning_rate": 2.2042048808472382e-07, + "loss": 0.0025, + "step": 60554 + }, + { + "epoch": 18.7, + "learning_rate": 2.2031607466475146e-07, + "loss": 0.0015, + "step": 60555 + }, + { + "epoch": 18.7, + "learning_rate": 2.2021168570555251e-07, + "loss": 0.0015, + "step": 60556 + }, + { + "epoch": 18.7, + "learning_rate": 2.2010732120738898e-07, + "loss": 0.0018, + "step": 60557 + }, + { + "epoch": 18.7, + "learning_rate": 2.2000298117052065e-07, + "loss": 0.0015, + "step": 60558 + }, + { + "epoch": 18.7, + "learning_rate": 2.1989866559520733e-07, + "loss": 0.0017, + "step": 60559 + }, + { + "epoch": 18.7, + "learning_rate": 2.1979437448171216e-07, + "loss": 0.0018, + "step": 60560 + }, + { + "epoch": 18.7, + "learning_rate": 2.1969010783029488e-07, + "loss": 0.0017, + "step": 60561 + }, + { + "epoch": 18.7, + "learning_rate": 2.1958586564121641e-07, + "loss": 0.0011, + "step": 60562 + }, + { + "epoch": 18.7, + "learning_rate": 2.194816479147388e-07, + "loss": 0.0018, + "step": 60563 + }, + { + "epoch": 18.7, + "learning_rate": 2.193774546511196e-07, + "loss": 0.0016, + "step": 60564 + }, + { + "epoch": 18.7, + "learning_rate": 2.192732858506208e-07, + "loss": 0.0016, + "step": 60565 + }, + { + "epoch": 18.7, + "learning_rate": 2.1916914151350555e-07, + "loss": 0.0023, + "step": 60566 + }, + { + "epoch": 18.7, + "learning_rate": 2.190650216400303e-07, + "loss": 0.0013, + "step": 60567 + }, + { + "epoch": 18.7, + "learning_rate": 2.1896092623045818e-07, + "loss": 0.0016, + "step": 60568 + }, + { + "epoch": 18.7, + "learning_rate": 2.1885685528505008e-07, + "loss": 0.0018, + "step": 60569 + }, + { + "epoch": 18.71, + "learning_rate": 2.1875280880406245e-07, + "loss": 0.0015, + "step": 60570 + }, + { + "epoch": 18.71, + "learning_rate": 2.1864878678775957e-07, + "loss": 0.0013, + "step": 60571 + }, + { + "epoch": 18.71, + "learning_rate": 2.185447892364001e-07, + "loss": 0.0014, + "step": 60572 + }, + { + "epoch": 18.71, + "learning_rate": 2.1844081615024383e-07, + "loss": 0.0019, + "step": 60573 + }, + { + "epoch": 18.71, + "learning_rate": 2.1833686752955052e-07, + "loss": 0.0018, + "step": 60574 + }, + { + "epoch": 18.71, + "learning_rate": 2.1823294337458224e-07, + "loss": 0.0017, + "step": 60575 + }, + { + "epoch": 18.71, + "learning_rate": 2.181290436855954e-07, + "loss": 0.0021, + "step": 60576 + }, + { + "epoch": 18.71, + "learning_rate": 2.1802516846285316e-07, + "loss": 0.0021, + "step": 60577 + }, + { + "epoch": 18.71, + "learning_rate": 2.1792131770661418e-07, + "loss": 0.0013, + "step": 60578 + }, + { + "epoch": 18.71, + "learning_rate": 2.1781749141713827e-07, + "loss": 0.0014, + "step": 60579 + }, + { + "epoch": 18.71, + "learning_rate": 2.177136895946841e-07, + "loss": 0.0013, + "step": 60580 + }, + { + "epoch": 18.71, + "learning_rate": 2.1760991223951365e-07, + "loss": 0.0018, + "step": 60581 + }, + { + "epoch": 18.71, + "learning_rate": 2.1750615935188346e-07, + "loss": 0.0014, + "step": 60582 + }, + { + "epoch": 18.71, + "learning_rate": 2.174024309320555e-07, + "loss": 0.0013, + "step": 60583 + }, + { + "epoch": 18.71, + "learning_rate": 2.172987269802884e-07, + "loss": 0.0018, + "step": 60584 + }, + { + "epoch": 18.71, + "learning_rate": 2.1719504749683985e-07, + "loss": 0.0018, + "step": 60585 + }, + { + "epoch": 18.71, + "learning_rate": 2.1709139248197174e-07, + "loss": 0.0018, + "step": 60586 + }, + { + "epoch": 18.71, + "learning_rate": 2.1698776193594284e-07, + "loss": 0.002, + "step": 60587 + }, + { + "epoch": 18.71, + "learning_rate": 2.168841558590118e-07, + "loss": 0.0019, + "step": 60588 + }, + { + "epoch": 18.71, + "learning_rate": 2.167805742514373e-07, + "loss": 0.0016, + "step": 60589 + }, + { + "epoch": 18.71, + "learning_rate": 2.166770171134791e-07, + "loss": 0.0017, + "step": 60590 + }, + { + "epoch": 18.71, + "learning_rate": 2.1657348444539594e-07, + "loss": 0.0017, + "step": 60591 + }, + { + "epoch": 18.71, + "learning_rate": 2.164699762474476e-07, + "loss": 0.0013, + "step": 60592 + }, + { + "epoch": 18.71, + "learning_rate": 2.1636649251989162e-07, + "loss": 0.0017, + "step": 60593 + }, + { + "epoch": 18.71, + "learning_rate": 2.1626303326298782e-07, + "loss": 0.0016, + "step": 60594 + }, + { + "epoch": 18.71, + "learning_rate": 2.1615959847699374e-07, + "loss": 0.0019, + "step": 60595 + }, + { + "epoch": 18.71, + "learning_rate": 2.1605618816216923e-07, + "loss": 0.0014, + "step": 60596 + }, + { + "epoch": 18.71, + "learning_rate": 2.1595280231877402e-07, + "loss": 0.0018, + "step": 60597 + }, + { + "epoch": 18.71, + "learning_rate": 2.158494409470635e-07, + "loss": 0.0014, + "step": 60598 + }, + { + "epoch": 18.71, + "learning_rate": 2.1574610404729968e-07, + "loss": 0.0012, + "step": 60599 + }, + { + "epoch": 18.71, + "learning_rate": 2.15642791619739e-07, + "loss": 0.0019, + "step": 60600 + }, + { + "epoch": 18.71, + "learning_rate": 2.1553950366463905e-07, + "loss": 0.0016, + "step": 60601 + }, + { + "epoch": 18.71, + "learning_rate": 2.1543624018225962e-07, + "loss": 0.0016, + "step": 60602 + }, + { + "epoch": 18.72, + "learning_rate": 2.153330011728605e-07, + "loss": 0.0017, + "step": 60603 + }, + { + "epoch": 18.72, + "learning_rate": 2.1522978663669703e-07, + "loss": 0.002, + "step": 60604 + }, + { + "epoch": 18.72, + "learning_rate": 2.151265965740279e-07, + "loss": 0.002, + "step": 60605 + }, + { + "epoch": 18.72, + "learning_rate": 2.150234309851129e-07, + "loss": 0.0011, + "step": 60606 + }, + { + "epoch": 18.72, + "learning_rate": 2.1492028987020852e-07, + "loss": 0.002, + "step": 60607 + }, + { + "epoch": 18.72, + "learning_rate": 2.148171732295723e-07, + "loss": 0.0021, + "step": 60608 + }, + { + "epoch": 18.72, + "learning_rate": 2.1471408106346403e-07, + "loss": 0.0014, + "step": 60609 + }, + { + "epoch": 18.72, + "learning_rate": 2.146110133721413e-07, + "loss": 0.0016, + "step": 60610 + }, + { + "epoch": 18.72, + "learning_rate": 2.1450797015585944e-07, + "loss": 0.002, + "step": 60611 + }, + { + "epoch": 18.72, + "learning_rate": 2.1440495141487939e-07, + "loss": 0.0016, + "step": 60612 + }, + { + "epoch": 18.72, + "learning_rate": 2.1430195714945535e-07, + "loss": 0.0014, + "step": 60613 + }, + { + "epoch": 18.72, + "learning_rate": 2.1419898735984935e-07, + "loss": 0.002, + "step": 60614 + }, + { + "epoch": 18.72, + "learning_rate": 2.140960420463156e-07, + "loss": 0.0017, + "step": 60615 + }, + { + "epoch": 18.72, + "learning_rate": 2.1399312120911175e-07, + "loss": 0.0022, + "step": 60616 + }, + { + "epoch": 18.72, + "learning_rate": 2.1389022484849642e-07, + "loss": 0.0017, + "step": 60617 + }, + { + "epoch": 18.72, + "learning_rate": 2.1378735296472607e-07, + "loss": 0.0018, + "step": 60618 + }, + { + "epoch": 18.72, + "learning_rate": 2.1368450555805943e-07, + "loss": 0.002, + "step": 60619 + }, + { + "epoch": 18.72, + "learning_rate": 2.1358168262875179e-07, + "loss": 0.0015, + "step": 60620 + }, + { + "epoch": 18.72, + "learning_rate": 2.1347888417706298e-07, + "loss": 0.0016, + "step": 60621 + }, + { + "epoch": 18.72, + "learning_rate": 2.133761102032461e-07, + "loss": 0.0018, + "step": 60622 + }, + { + "epoch": 18.72, + "learning_rate": 2.13273360707561e-07, + "loss": 0.0015, + "step": 60623 + }, + { + "epoch": 18.72, + "learning_rate": 2.131706356902652e-07, + "loss": 0.0016, + "step": 60624 + }, + { + "epoch": 18.72, + "learning_rate": 2.1306793515161518e-07, + "loss": 0.0019, + "step": 60625 + }, + { + "epoch": 18.72, + "learning_rate": 2.1296525909186627e-07, + "loss": 0.0019, + "step": 60626 + }, + { + "epoch": 18.72, + "learning_rate": 2.1286260751127607e-07, + "loss": 0.0013, + "step": 60627 + }, + { + "epoch": 18.72, + "learning_rate": 2.1275998041010216e-07, + "loss": 0.0015, + "step": 60628 + }, + { + "epoch": 18.72, + "learning_rate": 2.1265737778859984e-07, + "loss": 0.0025, + "step": 60629 + }, + { + "epoch": 18.72, + "learning_rate": 2.1255479964702674e-07, + "loss": 0.0014, + "step": 60630 + }, + { + "epoch": 18.72, + "learning_rate": 2.124522459856404e-07, + "loss": 0.0019, + "step": 60631 + }, + { + "epoch": 18.72, + "learning_rate": 2.1234971680469509e-07, + "loss": 0.0013, + "step": 60632 + }, + { + "epoch": 18.72, + "learning_rate": 2.1224721210444722e-07, + "loss": 0.002, + "step": 60633 + }, + { + "epoch": 18.72, + "learning_rate": 2.121447318851566e-07, + "loss": 0.0018, + "step": 60634 + }, + { + "epoch": 18.73, + "learning_rate": 2.120422761470764e-07, + "loss": 0.0017, + "step": 60635 + }, + { + "epoch": 18.73, + "learning_rate": 2.1193984489046305e-07, + "loss": 0.0011, + "step": 60636 + }, + { + "epoch": 18.73, + "learning_rate": 2.1183743811557412e-07, + "loss": 0.0017, + "step": 60637 + }, + { + "epoch": 18.73, + "learning_rate": 2.1173505582266386e-07, + "loss": 0.0012, + "step": 60638 + }, + { + "epoch": 18.73, + "learning_rate": 2.1163269801198982e-07, + "loss": 0.0021, + "step": 60639 + }, + { + "epoch": 18.73, + "learning_rate": 2.115303646838096e-07, + "loss": 0.0024, + "step": 60640 + }, + { + "epoch": 18.73, + "learning_rate": 2.1142805583837523e-07, + "loss": 0.0016, + "step": 60641 + }, + { + "epoch": 18.73, + "learning_rate": 2.1132577147594425e-07, + "loss": 0.0012, + "step": 60642 + }, + { + "epoch": 18.73, + "learning_rate": 2.1122351159677424e-07, + "loss": 0.0017, + "step": 60643 + }, + { + "epoch": 18.73, + "learning_rate": 2.1112127620111834e-07, + "loss": 0.0013, + "step": 60644 + }, + { + "epoch": 18.73, + "learning_rate": 2.1101906528923522e-07, + "loss": 0.0014, + "step": 60645 + }, + { + "epoch": 18.73, + "learning_rate": 2.1091687886137802e-07, + "loss": 0.0015, + "step": 60646 + }, + { + "epoch": 18.73, + "learning_rate": 2.1081471691780207e-07, + "loss": 0.0014, + "step": 60647 + }, + { + "epoch": 18.73, + "learning_rate": 2.10712579458765e-07, + "loss": 0.0015, + "step": 60648 + }, + { + "epoch": 18.73, + "learning_rate": 2.10610466484521e-07, + "loss": 0.0021, + "step": 60649 + }, + { + "epoch": 18.73, + "learning_rate": 2.1050837799532654e-07, + "loss": 0.0018, + "step": 60650 + }, + { + "epoch": 18.73, + "learning_rate": 2.1040631399143474e-07, + "loss": 0.0013, + "step": 60651 + }, + { + "epoch": 18.73, + "learning_rate": 2.103042744731032e-07, + "loss": 0.0017, + "step": 60652 + }, + { + "epoch": 18.73, + "learning_rate": 2.1020225944058504e-07, + "loss": 0.0019, + "step": 60653 + }, + { + "epoch": 18.73, + "learning_rate": 2.1010026889413672e-07, + "loss": 0.0017, + "step": 60654 + }, + { + "epoch": 18.73, + "learning_rate": 2.0999830283401467e-07, + "loss": 0.0014, + "step": 60655 + }, + { + "epoch": 18.73, + "learning_rate": 2.0989636126047208e-07, + "loss": 0.0016, + "step": 60656 + }, + { + "epoch": 18.73, + "learning_rate": 2.0979444417376315e-07, + "loss": 0.0021, + "step": 60657 + }, + { + "epoch": 18.73, + "learning_rate": 2.0969255157414435e-07, + "loss": 0.0011, + "step": 60658 + }, + { + "epoch": 18.73, + "learning_rate": 2.0959068346187105e-07, + "loss": 0.0016, + "step": 60659 + }, + { + "epoch": 18.73, + "learning_rate": 2.0948883983719636e-07, + "loss": 0.0013, + "step": 60660 + }, + { + "epoch": 18.73, + "learning_rate": 2.0938702070037564e-07, + "loss": 0.0017, + "step": 60661 + }, + { + "epoch": 18.73, + "learning_rate": 2.0928522605166423e-07, + "loss": 0.0014, + "step": 60662 + }, + { + "epoch": 18.73, + "learning_rate": 2.0918345589131528e-07, + "loss": 0.002, + "step": 60663 + }, + { + "epoch": 18.73, + "learning_rate": 2.0908171021958413e-07, + "loss": 0.0016, + "step": 60664 + }, + { + "epoch": 18.73, + "learning_rate": 2.0897998903672613e-07, + "loss": 0.0015, + "step": 60665 + }, + { + "epoch": 18.73, + "learning_rate": 2.088782923429955e-07, + "loss": 0.0015, + "step": 60666 + }, + { + "epoch": 18.74, + "learning_rate": 2.087766201386454e-07, + "loss": 0.0014, + "step": 60667 + }, + { + "epoch": 18.74, + "learning_rate": 2.086749724239312e-07, + "loss": 0.0023, + "step": 60668 + }, + { + "epoch": 18.74, + "learning_rate": 2.08573349199106e-07, + "loss": 0.0019, + "step": 60669 + }, + { + "epoch": 18.74, + "learning_rate": 2.0847175046442402e-07, + "loss": 0.0022, + "step": 60670 + }, + { + "epoch": 18.74, + "learning_rate": 2.083701762201429e-07, + "loss": 0.0024, + "step": 60671 + }, + { + "epoch": 18.74, + "learning_rate": 2.0826862646651125e-07, + "loss": 0.0022, + "step": 60672 + }, + { + "epoch": 18.74, + "learning_rate": 2.0816710120378558e-07, + "loss": 0.0012, + "step": 60673 + }, + { + "epoch": 18.74, + "learning_rate": 2.0806560043222123e-07, + "loss": 0.0022, + "step": 60674 + }, + { + "epoch": 18.74, + "learning_rate": 2.0796412415207023e-07, + "loss": 0.0015, + "step": 60675 + }, + { + "epoch": 18.74, + "learning_rate": 2.0786267236358682e-07, + "loss": 0.0013, + "step": 60676 + }, + { + "epoch": 18.74, + "learning_rate": 2.077612450670252e-07, + "loss": 0.0015, + "step": 60677 + }, + { + "epoch": 18.74, + "learning_rate": 2.0765984226263858e-07, + "loss": 0.0016, + "step": 60678 + }, + { + "epoch": 18.74, + "learning_rate": 2.0755846395068002e-07, + "loss": 0.0016, + "step": 60679 + }, + { + "epoch": 18.74, + "learning_rate": 2.074571101314049e-07, + "loss": 0.0019, + "step": 60680 + }, + { + "epoch": 18.74, + "learning_rate": 2.0735578080506523e-07, + "loss": 0.0021, + "step": 60681 + }, + { + "epoch": 18.74, + "learning_rate": 2.0725447597191418e-07, + "loss": 0.002, + "step": 60682 + }, + { + "epoch": 18.74, + "learning_rate": 2.0715319563220704e-07, + "loss": 0.0016, + "step": 60683 + }, + { + "epoch": 18.74, + "learning_rate": 2.0705193978619476e-07, + "loss": 0.003, + "step": 60684 + }, + { + "epoch": 18.74, + "learning_rate": 2.0695070843413044e-07, + "loss": 0.0016, + "step": 60685 + }, + { + "epoch": 18.74, + "learning_rate": 2.068495015762706e-07, + "loss": 0.0016, + "step": 60686 + }, + { + "epoch": 18.74, + "learning_rate": 2.067483192128661e-07, + "loss": 0.0022, + "step": 60687 + }, + { + "epoch": 18.74, + "learning_rate": 2.0664716134417007e-07, + "loss": 0.0016, + "step": 60688 + }, + { + "epoch": 18.74, + "learning_rate": 2.0654602797043455e-07, + "loss": 0.0023, + "step": 60689 + }, + { + "epoch": 18.74, + "learning_rate": 2.06444919091916e-07, + "loss": 0.002, + "step": 60690 + }, + { + "epoch": 18.74, + "learning_rate": 2.063438347088631e-07, + "loss": 0.0024, + "step": 60691 + }, + { + "epoch": 18.74, + "learning_rate": 2.0624277482153122e-07, + "loss": 0.0015, + "step": 60692 + }, + { + "epoch": 18.74, + "learning_rate": 2.0614173943017235e-07, + "loss": 0.0019, + "step": 60693 + }, + { + "epoch": 18.74, + "learning_rate": 2.0604072853503853e-07, + "loss": 0.002, + "step": 60694 + }, + { + "epoch": 18.74, + "learning_rate": 2.059397421363829e-07, + "loss": 0.0021, + "step": 60695 + }, + { + "epoch": 18.74, + "learning_rate": 2.058387802344597e-07, + "loss": 0.0012, + "step": 60696 + }, + { + "epoch": 18.74, + "learning_rate": 2.057378428295198e-07, + "loss": 0.002, + "step": 60697 + }, + { + "epoch": 18.74, + "learning_rate": 2.0563692992181527e-07, + "loss": 0.0017, + "step": 60698 + }, + { + "epoch": 18.74, + "learning_rate": 2.0553604151160034e-07, + "loss": 0.0018, + "step": 60699 + }, + { + "epoch": 18.75, + "learning_rate": 2.054351775991248e-07, + "loss": 0.0013, + "step": 60700 + }, + { + "epoch": 18.75, + "learning_rate": 2.0533433818464287e-07, + "loss": 0.0018, + "step": 60701 + }, + { + "epoch": 18.75, + "learning_rate": 2.0523352326840662e-07, + "loss": 0.0018, + "step": 60702 + }, + { + "epoch": 18.75, + "learning_rate": 2.0513273285066693e-07, + "loss": 0.0015, + "step": 60703 + }, + { + "epoch": 18.75, + "learning_rate": 2.0503196693167694e-07, + "loss": 0.002, + "step": 60704 + }, + { + "epoch": 18.75, + "learning_rate": 2.0493122551168865e-07, + "loss": 0.0026, + "step": 60705 + }, + { + "epoch": 18.75, + "learning_rate": 2.0483050859095411e-07, + "loss": 0.0019, + "step": 60706 + }, + { + "epoch": 18.75, + "learning_rate": 2.0472981616972531e-07, + "loss": 0.0025, + "step": 60707 + }, + { + "epoch": 18.75, + "learning_rate": 2.046291482482532e-07, + "loss": 0.0013, + "step": 60708 + }, + { + "epoch": 18.75, + "learning_rate": 2.0452850482678975e-07, + "loss": 0.0015, + "step": 60709 + }, + { + "epoch": 18.75, + "learning_rate": 2.0442788590558705e-07, + "loss": 0.0019, + "step": 60710 + }, + { + "epoch": 18.75, + "learning_rate": 2.0432729148489817e-07, + "loss": 0.0018, + "step": 60711 + }, + { + "epoch": 18.75, + "learning_rate": 2.0422672156497292e-07, + "loss": 0.0018, + "step": 60712 + }, + { + "epoch": 18.75, + "learning_rate": 2.0412617614606222e-07, + "loss": 0.0012, + "step": 60713 + }, + { + "epoch": 18.75, + "learning_rate": 2.040256552284192e-07, + "loss": 0.0017, + "step": 60714 + }, + { + "epoch": 18.75, + "learning_rate": 2.039251588122948e-07, + "loss": 0.0013, + "step": 60715 + }, + { + "epoch": 18.75, + "learning_rate": 2.0382468689793988e-07, + "loss": 0.0015, + "step": 60716 + }, + { + "epoch": 18.75, + "learning_rate": 2.037242394856065e-07, + "loss": 0.002, + "step": 60717 + }, + { + "epoch": 18.75, + "learning_rate": 2.0362381657554554e-07, + "loss": 0.0024, + "step": 60718 + }, + { + "epoch": 18.75, + "learning_rate": 2.0352341816800792e-07, + "loss": 0.0013, + "step": 60719 + }, + { + "epoch": 18.75, + "learning_rate": 2.0342304426324456e-07, + "loss": 0.002, + "step": 60720 + }, + { + "epoch": 18.75, + "learning_rate": 2.0332269486150858e-07, + "loss": 0.0013, + "step": 60721 + }, + { + "epoch": 18.75, + "learning_rate": 2.0322236996304867e-07, + "loss": 0.0018, + "step": 60722 + }, + { + "epoch": 18.75, + "learning_rate": 2.0312206956811577e-07, + "loss": 0.0016, + "step": 60723 + }, + { + "epoch": 18.75, + "learning_rate": 2.0302179367696185e-07, + "loss": 0.0014, + "step": 60724 + }, + { + "epoch": 18.75, + "learning_rate": 2.0292154228983673e-07, + "loss": 0.0018, + "step": 60725 + }, + { + "epoch": 18.75, + "learning_rate": 2.0282131540699136e-07, + "loss": 0.0016, + "step": 60726 + }, + { + "epoch": 18.75, + "learning_rate": 2.027211130286788e-07, + "loss": 0.0018, + "step": 60727 + }, + { + "epoch": 18.75, + "learning_rate": 2.0262093515514668e-07, + "loss": 0.0019, + "step": 60728 + }, + { + "epoch": 18.75, + "learning_rate": 2.0252078178664592e-07, + "loss": 0.0018, + "step": 60729 + }, + { + "epoch": 18.75, + "learning_rate": 2.024206529234285e-07, + "loss": 0.0014, + "step": 60730 + }, + { + "epoch": 18.75, + "learning_rate": 2.0232054856574202e-07, + "loss": 0.002, + "step": 60731 + }, + { + "epoch": 18.76, + "learning_rate": 2.0222046871384072e-07, + "loss": 0.0019, + "step": 60732 + }, + { + "epoch": 18.76, + "learning_rate": 2.0212041336797327e-07, + "loss": 0.0016, + "step": 60733 + }, + { + "epoch": 18.76, + "learning_rate": 2.020203825283884e-07, + "loss": 0.0018, + "step": 60734 + }, + { + "epoch": 18.76, + "learning_rate": 2.0192037619533812e-07, + "loss": 0.0015, + "step": 60735 + }, + { + "epoch": 18.76, + "learning_rate": 2.018203943690722e-07, + "loss": 0.0018, + "step": 60736 + }, + { + "epoch": 18.76, + "learning_rate": 2.0172043704984046e-07, + "loss": 0.0018, + "step": 60737 + }, + { + "epoch": 18.76, + "learning_rate": 2.016205042378938e-07, + "loss": 0.0012, + "step": 60738 + }, + { + "epoch": 18.76, + "learning_rate": 2.0152059593348095e-07, + "loss": 0.0018, + "step": 60739 + }, + { + "epoch": 18.76, + "learning_rate": 2.0142071213685165e-07, + "loss": 0.0016, + "step": 60740 + }, + { + "epoch": 18.76, + "learning_rate": 2.0132085284825574e-07, + "loss": 0.0013, + "step": 60741 + }, + { + "epoch": 18.76, + "learning_rate": 2.0122101806794415e-07, + "loss": 0.0025, + "step": 60742 + }, + { + "epoch": 18.76, + "learning_rate": 2.011212077961666e-07, + "loss": 0.0016, + "step": 60743 + }, + { + "epoch": 18.76, + "learning_rate": 2.0102142203317188e-07, + "loss": 0.0017, + "step": 60744 + }, + { + "epoch": 18.76, + "learning_rate": 2.009216607792097e-07, + "loss": 0.0016, + "step": 60745 + }, + { + "epoch": 18.76, + "learning_rate": 2.0082192403452883e-07, + "loss": 0.0018, + "step": 60746 + }, + { + "epoch": 18.76, + "learning_rate": 2.007222117993801e-07, + "loss": 0.0017, + "step": 60747 + }, + { + "epoch": 18.76, + "learning_rate": 2.006225240740134e-07, + "loss": 0.0016, + "step": 60748 + }, + { + "epoch": 18.76, + "learning_rate": 2.0052286085867623e-07, + "loss": 0.0014, + "step": 60749 + }, + { + "epoch": 18.76, + "learning_rate": 2.0042322215361843e-07, + "loss": 0.0019, + "step": 60750 + }, + { + "epoch": 18.76, + "learning_rate": 2.0032360795908979e-07, + "loss": 0.0018, + "step": 60751 + }, + { + "epoch": 18.76, + "learning_rate": 2.0022401827533898e-07, + "loss": 0.0012, + "step": 60752 + }, + { + "epoch": 18.76, + "learning_rate": 2.0012445310261585e-07, + "loss": 0.0014, + "step": 60753 + }, + { + "epoch": 18.76, + "learning_rate": 2.0002491244116794e-07, + "loss": 0.0016, + "step": 60754 + }, + { + "epoch": 18.76, + "learning_rate": 1.9992539629124618e-07, + "loss": 0.0018, + "step": 60755 + }, + { + "epoch": 18.76, + "learning_rate": 1.9982590465309814e-07, + "loss": 0.0018, + "step": 60756 + }, + { + "epoch": 18.76, + "learning_rate": 1.997264375269714e-07, + "loss": 0.0023, + "step": 60757 + }, + { + "epoch": 18.76, + "learning_rate": 1.9962699491311798e-07, + "loss": 0.0017, + "step": 60758 + }, + { + "epoch": 18.76, + "learning_rate": 1.9952757681178548e-07, + "loss": 0.0018, + "step": 60759 + }, + { + "epoch": 18.76, + "learning_rate": 1.9942818322322032e-07, + "loss": 0.0017, + "step": 60760 + }, + { + "epoch": 18.76, + "learning_rate": 1.9932881414767457e-07, + "loss": 0.0013, + "step": 60761 + }, + { + "epoch": 18.76, + "learning_rate": 1.9922946958539357e-07, + "loss": 0.0013, + "step": 60762 + }, + { + "epoch": 18.76, + "learning_rate": 1.9913014953662713e-07, + "loss": 0.0012, + "step": 60763 + }, + { + "epoch": 18.76, + "learning_rate": 1.9903085400162504e-07, + "loss": 0.0014, + "step": 60764 + }, + { + "epoch": 18.77, + "learning_rate": 1.9893158298063264e-07, + "loss": 0.0016, + "step": 60765 + }, + { + "epoch": 18.77, + "learning_rate": 1.9883233647390087e-07, + "loss": 0.0022, + "step": 60766 + }, + { + "epoch": 18.77, + "learning_rate": 1.987331144816773e-07, + "loss": 0.0015, + "step": 60767 + }, + { + "epoch": 18.77, + "learning_rate": 1.9863391700420954e-07, + "loss": 0.002, + "step": 60768 + }, + { + "epoch": 18.77, + "learning_rate": 1.9853474404174623e-07, + "loss": 0.0017, + "step": 60769 + }, + { + "epoch": 18.77, + "learning_rate": 1.9843559559453494e-07, + "loss": 0.0023, + "step": 60770 + }, + { + "epoch": 18.77, + "learning_rate": 1.9833647166282443e-07, + "loss": 0.0015, + "step": 60771 + }, + { + "epoch": 18.77, + "learning_rate": 1.9823737224686114e-07, + "loss": 0.0014, + "step": 60772 + }, + { + "epoch": 18.77, + "learning_rate": 1.9813829734689482e-07, + "loss": 0.0018, + "step": 60773 + }, + { + "epoch": 18.77, + "learning_rate": 1.98039246963172e-07, + "loss": 0.0017, + "step": 60774 + }, + { + "epoch": 18.77, + "learning_rate": 1.9794022109594024e-07, + "loss": 0.0014, + "step": 60775 + }, + { + "epoch": 18.77, + "learning_rate": 1.9784121974544935e-07, + "loss": 0.0009, + "step": 60776 + }, + { + "epoch": 18.77, + "learning_rate": 1.9774224291194355e-07, + "loss": 0.0014, + "step": 60777 + }, + { + "epoch": 18.77, + "learning_rate": 1.9764329059567268e-07, + "loss": 0.0018, + "step": 60778 + }, + { + "epoch": 18.77, + "learning_rate": 1.9754436279688537e-07, + "loss": 0.001, + "step": 60779 + }, + { + "epoch": 18.77, + "learning_rate": 1.9744545951582594e-07, + "loss": 0.0014, + "step": 60780 + }, + { + "epoch": 18.77, + "learning_rate": 1.9734658075274305e-07, + "loss": 0.0023, + "step": 60781 + }, + { + "epoch": 18.77, + "learning_rate": 1.9724772650788538e-07, + "loss": 0.0012, + "step": 60782 + }, + { + "epoch": 18.77, + "learning_rate": 1.9714889678149828e-07, + "loss": 0.0025, + "step": 60783 + }, + { + "epoch": 18.77, + "learning_rate": 1.9705009157383048e-07, + "loss": 0.0023, + "step": 60784 + }, + { + "epoch": 18.77, + "learning_rate": 1.9695131088512732e-07, + "loss": 0.0016, + "step": 60785 + }, + { + "epoch": 18.77, + "learning_rate": 1.9685255471563746e-07, + "loss": 0.0012, + "step": 60786 + }, + { + "epoch": 18.77, + "learning_rate": 1.967538230656063e-07, + "loss": 0.0019, + "step": 60787 + }, + { + "epoch": 18.77, + "learning_rate": 1.9665511593528253e-07, + "loss": 0.0019, + "step": 60788 + }, + { + "epoch": 18.77, + "learning_rate": 1.965564333249137e-07, + "loss": 0.0013, + "step": 60789 + }, + { + "epoch": 18.77, + "learning_rate": 1.9645777523474407e-07, + "loss": 0.0016, + "step": 60790 + }, + { + "epoch": 18.77, + "learning_rate": 1.9635914166502124e-07, + "loss": 0.0014, + "step": 60791 + }, + { + "epoch": 18.77, + "learning_rate": 1.9626053261599276e-07, + "loss": 0.0015, + "step": 60792 + }, + { + "epoch": 18.77, + "learning_rate": 1.96161948087904e-07, + "loss": 0.0016, + "step": 60793 + }, + { + "epoch": 18.77, + "learning_rate": 1.9606338808100367e-07, + "loss": 0.0012, + "step": 60794 + }, + { + "epoch": 18.77, + "learning_rate": 1.959648525955371e-07, + "loss": 0.0018, + "step": 60795 + }, + { + "epoch": 18.77, + "learning_rate": 1.9586634163174855e-07, + "loss": 0.0017, + "step": 60796 + }, + { + "epoch": 18.78, + "learning_rate": 1.9576785518988783e-07, + "loss": 0.0017, + "step": 60797 + }, + { + "epoch": 18.78, + "learning_rate": 1.9566939327020028e-07, + "loss": 0.0017, + "step": 60798 + }, + { + "epoch": 18.78, + "learning_rate": 1.955709558729313e-07, + "loss": 0.0016, + "step": 60799 + }, + { + "epoch": 18.78, + "learning_rate": 1.954725429983273e-07, + "loss": 0.0015, + "step": 60800 + }, + { + "epoch": 18.78, + "learning_rate": 1.953741546466348e-07, + "loss": 0.0013, + "step": 60801 + }, + { + "epoch": 18.78, + "learning_rate": 1.952757908180991e-07, + "loss": 0.0015, + "step": 60802 + }, + { + "epoch": 18.78, + "learning_rate": 1.9517745151296786e-07, + "loss": 0.0019, + "step": 60803 + }, + { + "epoch": 18.78, + "learning_rate": 1.9507913673148636e-07, + "loss": 0.0022, + "step": 60804 + }, + { + "epoch": 18.78, + "learning_rate": 1.9498084647390002e-07, + "loss": 0.0015, + "step": 60805 + }, + { + "epoch": 18.78, + "learning_rate": 1.9488258074045418e-07, + "loss": 0.0021, + "step": 60806 + }, + { + "epoch": 18.78, + "learning_rate": 1.947843395313964e-07, + "loss": 0.0014, + "step": 60807 + }, + { + "epoch": 18.78, + "learning_rate": 1.9468612284696986e-07, + "loss": 0.0016, + "step": 60808 + }, + { + "epoch": 18.78, + "learning_rate": 1.945879306874232e-07, + "loss": 0.0019, + "step": 60809 + }, + { + "epoch": 18.78, + "learning_rate": 1.944897630530007e-07, + "loss": 0.002, + "step": 60810 + }, + { + "epoch": 18.78, + "learning_rate": 1.9439161994394662e-07, + "loss": 0.0018, + "step": 60811 + }, + { + "epoch": 18.78, + "learning_rate": 1.942935013605074e-07, + "loss": 0.0016, + "step": 60812 + }, + { + "epoch": 18.78, + "learning_rate": 1.9419540730292952e-07, + "loss": 0.0026, + "step": 60813 + }, + { + "epoch": 18.78, + "learning_rate": 1.9409733777145611e-07, + "loss": 0.0016, + "step": 60814 + }, + { + "epoch": 18.78, + "learning_rate": 1.939992927663359e-07, + "loss": 0.0015, + "step": 60815 + }, + { + "epoch": 18.78, + "learning_rate": 1.9390127228781085e-07, + "loss": 0.0021, + "step": 60816 + }, + { + "epoch": 18.78, + "learning_rate": 1.938032763361264e-07, + "loss": 0.0019, + "step": 60817 + }, + { + "epoch": 18.78, + "learning_rate": 1.9370530491152894e-07, + "loss": 0.0015, + "step": 60818 + }, + { + "epoch": 18.78, + "learning_rate": 1.936073580142639e-07, + "loss": 0.0013, + "step": 60819 + }, + { + "epoch": 18.78, + "learning_rate": 1.9350943564457437e-07, + "loss": 0.002, + "step": 60820 + }, + { + "epoch": 18.78, + "learning_rate": 1.9341153780270684e-07, + "loss": 0.0013, + "step": 60821 + }, + { + "epoch": 18.78, + "learning_rate": 1.9331366448890554e-07, + "loss": 0.0024, + "step": 60822 + }, + { + "epoch": 18.78, + "learning_rate": 1.9321581570341586e-07, + "loss": 0.0015, + "step": 60823 + }, + { + "epoch": 18.78, + "learning_rate": 1.931179914464809e-07, + "loss": 0.0017, + "step": 60824 + }, + { + "epoch": 18.78, + "learning_rate": 1.9302019171834717e-07, + "loss": 0.0017, + "step": 60825 + }, + { + "epoch": 18.78, + "learning_rate": 1.9292241651925892e-07, + "loss": 0.002, + "step": 60826 + }, + { + "epoch": 18.78, + "learning_rate": 1.9282466584946037e-07, + "loss": 0.0013, + "step": 60827 + }, + { + "epoch": 18.78, + "learning_rate": 1.9272693970919577e-07, + "loss": 0.0012, + "step": 60828 + }, + { + "epoch": 18.79, + "learning_rate": 1.9262923809871048e-07, + "loss": 0.0012, + "step": 60829 + }, + { + "epoch": 18.79, + "learning_rate": 1.9253156101824765e-07, + "loss": 0.0019, + "step": 60830 + }, + { + "epoch": 18.79, + "learning_rate": 1.9243390846805153e-07, + "loss": 0.0017, + "step": 60831 + }, + { + "epoch": 18.79, + "learning_rate": 1.923362804483686e-07, + "loss": 0.0016, + "step": 60832 + }, + { + "epoch": 18.79, + "learning_rate": 1.9223867695943977e-07, + "loss": 0.0017, + "step": 60833 + }, + { + "epoch": 18.79, + "learning_rate": 1.9214109800151038e-07, + "loss": 0.0016, + "step": 60834 + }, + { + "epoch": 18.79, + "learning_rate": 1.920435435748269e-07, + "loss": 0.0017, + "step": 60835 + }, + { + "epoch": 18.79, + "learning_rate": 1.919460136796314e-07, + "loss": 0.0011, + "step": 60836 + }, + { + "epoch": 18.79, + "learning_rate": 1.9184850831616585e-07, + "loss": 0.0022, + "step": 60837 + }, + { + "epoch": 18.79, + "learning_rate": 1.917510274846779e-07, + "loss": 0.0016, + "step": 60838 + }, + { + "epoch": 18.79, + "learning_rate": 1.916535711854084e-07, + "loss": 0.0013, + "step": 60839 + }, + { + "epoch": 18.79, + "learning_rate": 1.9155613941860384e-07, + "loss": 0.0015, + "step": 60840 + }, + { + "epoch": 18.79, + "learning_rate": 1.9145873218450516e-07, + "loss": 0.0018, + "step": 60841 + }, + { + "epoch": 18.79, + "learning_rate": 1.913613494833566e-07, + "loss": 0.0015, + "step": 60842 + }, + { + "epoch": 18.79, + "learning_rate": 1.912639913154024e-07, + "loss": 0.002, + "step": 60843 + }, + { + "epoch": 18.79, + "learning_rate": 1.9116665768088683e-07, + "loss": 0.0023, + "step": 60844 + }, + { + "epoch": 18.79, + "learning_rate": 1.910693485800519e-07, + "loss": 0.0017, + "step": 60845 + }, + { + "epoch": 18.79, + "learning_rate": 1.9097206401314184e-07, + "loss": 0.0013, + "step": 60846 + }, + { + "epoch": 18.79, + "learning_rate": 1.9087480398039981e-07, + "loss": 0.002, + "step": 60847 + }, + { + "epoch": 18.79, + "learning_rate": 1.9077756848206896e-07, + "loss": 0.0019, + "step": 60848 + }, + { + "epoch": 18.79, + "learning_rate": 1.9068035751839132e-07, + "loss": 0.002, + "step": 60849 + }, + { + "epoch": 18.79, + "learning_rate": 1.9058317108961332e-07, + "loss": 0.0013, + "step": 60850 + }, + { + "epoch": 18.79, + "learning_rate": 1.9048600919597482e-07, + "loss": 0.0017, + "step": 60851 + }, + { + "epoch": 18.79, + "learning_rate": 1.9038887183771893e-07, + "loss": 0.0013, + "step": 60852 + }, + { + "epoch": 18.79, + "learning_rate": 1.90291759015091e-07, + "loss": 0.0014, + "step": 60853 + }, + { + "epoch": 18.79, + "learning_rate": 1.9019467072833198e-07, + "loss": 0.0017, + "step": 60854 + }, + { + "epoch": 18.79, + "learning_rate": 1.9009760697768499e-07, + "loss": 0.0014, + "step": 60855 + }, + { + "epoch": 18.79, + "learning_rate": 1.9000056776339427e-07, + "loss": 0.0017, + "step": 60856 + }, + { + "epoch": 18.79, + "learning_rate": 1.8990355308570186e-07, + "loss": 0.0014, + "step": 60857 + }, + { + "epoch": 18.79, + "learning_rate": 1.8980656294484757e-07, + "loss": 0.0019, + "step": 60858 + }, + { + "epoch": 18.79, + "learning_rate": 1.8970959734107784e-07, + "loss": 0.0016, + "step": 60859 + }, + { + "epoch": 18.79, + "learning_rate": 1.8961265627463367e-07, + "loss": 0.0018, + "step": 60860 + }, + { + "epoch": 18.79, + "learning_rate": 1.89515739745757e-07, + "loss": 0.0019, + "step": 60861 + }, + { + "epoch": 18.8, + "learning_rate": 1.89418847754691e-07, + "loss": 0.0027, + "step": 60862 + }, + { + "epoch": 18.8, + "learning_rate": 1.893219803016777e-07, + "loss": 0.0018, + "step": 60863 + }, + { + "epoch": 18.8, + "learning_rate": 1.8922513738696025e-07, + "loss": 0.0019, + "step": 60864 + }, + { + "epoch": 18.8, + "learning_rate": 1.8912831901077843e-07, + "loss": 0.0023, + "step": 60865 + }, + { + "epoch": 18.8, + "learning_rate": 1.8903152517337763e-07, + "loss": 0.0018, + "step": 60866 + }, + { + "epoch": 18.8, + "learning_rate": 1.8893475587499877e-07, + "loss": 0.0015, + "step": 60867 + }, + { + "epoch": 18.8, + "learning_rate": 1.8883801111588162e-07, + "loss": 0.0019, + "step": 60868 + }, + { + "epoch": 18.8, + "learning_rate": 1.8874129089627158e-07, + "loss": 0.0014, + "step": 60869 + }, + { + "epoch": 18.8, + "learning_rate": 1.8864459521640844e-07, + "loss": 0.0015, + "step": 60870 + }, + { + "epoch": 18.8, + "learning_rate": 1.8854792407653532e-07, + "loss": 0.0016, + "step": 60871 + }, + { + "epoch": 18.8, + "learning_rate": 1.8845127747689318e-07, + "loss": 0.0028, + "step": 60872 + }, + { + "epoch": 18.8, + "learning_rate": 1.8835465541772291e-07, + "loss": 0.0019, + "step": 60873 + }, + { + "epoch": 18.8, + "learning_rate": 1.8825805789926654e-07, + "loss": 0.0017, + "step": 60874 + }, + { + "epoch": 18.8, + "learning_rate": 1.8816148492176833e-07, + "loss": 0.0017, + "step": 60875 + }, + { + "epoch": 18.8, + "learning_rate": 1.8806493648546697e-07, + "loss": 0.0014, + "step": 60876 + }, + { + "epoch": 18.8, + "learning_rate": 1.879684125906045e-07, + "loss": 0.0024, + "step": 60877 + }, + { + "epoch": 18.8, + "learning_rate": 1.8787191323742405e-07, + "loss": 0.0016, + "step": 60878 + }, + { + "epoch": 18.8, + "learning_rate": 1.8777543842616319e-07, + "loss": 0.0012, + "step": 60879 + }, + { + "epoch": 18.8, + "learning_rate": 1.876789881570673e-07, + "loss": 0.0017, + "step": 60880 + }, + { + "epoch": 18.8, + "learning_rate": 1.875825624303751e-07, + "loss": 0.0019, + "step": 60881 + }, + { + "epoch": 18.8, + "learning_rate": 1.874861612463297e-07, + "loss": 0.0017, + "step": 60882 + }, + { + "epoch": 18.8, + "learning_rate": 1.8738978460516978e-07, + "loss": 0.0015, + "step": 60883 + }, + { + "epoch": 18.8, + "learning_rate": 1.872934325071385e-07, + "loss": 0.0017, + "step": 60884 + }, + { + "epoch": 18.8, + "learning_rate": 1.8719710495247567e-07, + "loss": 0.002, + "step": 60885 + }, + { + "epoch": 18.8, + "learning_rate": 1.8710080194142333e-07, + "loss": 0.0018, + "step": 60886 + }, + { + "epoch": 18.8, + "learning_rate": 1.8700452347422126e-07, + "loss": 0.0018, + "step": 60887 + }, + { + "epoch": 18.8, + "learning_rate": 1.869082695511104e-07, + "loss": 0.0017, + "step": 60888 + }, + { + "epoch": 18.8, + "learning_rate": 1.8681204017233166e-07, + "loss": 0.0012, + "step": 60889 + }, + { + "epoch": 18.8, + "learning_rate": 1.86715835338126e-07, + "loss": 0.0019, + "step": 60890 + }, + { + "epoch": 18.8, + "learning_rate": 1.8661965504873426e-07, + "loss": 0.0017, + "step": 60891 + }, + { + "epoch": 18.8, + "learning_rate": 1.865234993043963e-07, + "loss": 0.0014, + "step": 60892 + }, + { + "epoch": 18.8, + "learning_rate": 1.86427368105353e-07, + "loss": 0.0022, + "step": 60893 + }, + { + "epoch": 18.81, + "learning_rate": 1.8633126145184533e-07, + "loss": 0.0016, + "step": 60894 + }, + { + "epoch": 18.81, + "learning_rate": 1.8623517934411194e-07, + "loss": 0.0018, + "step": 60895 + }, + { + "epoch": 18.81, + "learning_rate": 1.8613912178239378e-07, + "loss": 0.0023, + "step": 60896 + }, + { + "epoch": 18.81, + "learning_rate": 1.8604308876693399e-07, + "loss": 0.0015, + "step": 60897 + }, + { + "epoch": 18.81, + "learning_rate": 1.8594708029796903e-07, + "loss": 0.0013, + "step": 60898 + }, + { + "epoch": 18.81, + "learning_rate": 1.8585109637573984e-07, + "loss": 0.0016, + "step": 60899 + }, + { + "epoch": 18.81, + "learning_rate": 1.8575513700048731e-07, + "loss": 0.0013, + "step": 60900 + }, + { + "epoch": 18.81, + "learning_rate": 1.8565920217245125e-07, + "loss": 0.0019, + "step": 60901 + }, + { + "epoch": 18.81, + "learning_rate": 1.855632918918726e-07, + "loss": 0.0013, + "step": 60902 + }, + { + "epoch": 18.81, + "learning_rate": 1.8546740615898895e-07, + "loss": 0.0018, + "step": 60903 + }, + { + "epoch": 18.81, + "learning_rate": 1.8537154497404118e-07, + "loss": 0.0021, + "step": 60904 + }, + { + "epoch": 18.81, + "learning_rate": 1.8527570833727028e-07, + "loss": 0.0016, + "step": 60905 + }, + { + "epoch": 18.81, + "learning_rate": 1.8517989624891486e-07, + "loss": 0.0022, + "step": 60906 + }, + { + "epoch": 18.81, + "learning_rate": 1.8508410870921477e-07, + "loss": 0.002, + "step": 60907 + }, + { + "epoch": 18.81, + "learning_rate": 1.8498834571840763e-07, + "loss": 0.002, + "step": 60908 + }, + { + "epoch": 18.81, + "learning_rate": 1.8489260727673653e-07, + "loss": 0.0018, + "step": 60909 + }, + { + "epoch": 18.81, + "learning_rate": 1.8479689338443908e-07, + "loss": 0.002, + "step": 60910 + }, + { + "epoch": 18.81, + "learning_rate": 1.8470120404175397e-07, + "loss": 0.0015, + "step": 60911 + }, + { + "epoch": 18.81, + "learning_rate": 1.846055392489221e-07, + "loss": 0.0014, + "step": 60912 + }, + { + "epoch": 18.81, + "learning_rate": 1.845098990061822e-07, + "loss": 0.0015, + "step": 60913 + }, + { + "epoch": 18.81, + "learning_rate": 1.8441428331377186e-07, + "loss": 0.0016, + "step": 60914 + }, + { + "epoch": 18.81, + "learning_rate": 1.843186921719331e-07, + "loss": 0.0022, + "step": 60915 + }, + { + "epoch": 18.81, + "learning_rate": 1.842231255809024e-07, + "loss": 0.0018, + "step": 60916 + }, + { + "epoch": 18.81, + "learning_rate": 1.8412758354092174e-07, + "loss": 0.0016, + "step": 60917 + }, + { + "epoch": 18.81, + "learning_rate": 1.8403206605222656e-07, + "loss": 0.0017, + "step": 60918 + }, + { + "epoch": 18.81, + "learning_rate": 1.8393657311505775e-07, + "loss": 0.002, + "step": 60919 + }, + { + "epoch": 18.81, + "learning_rate": 1.83841104729654e-07, + "loss": 0.0016, + "step": 60920 + }, + { + "epoch": 18.81, + "learning_rate": 1.83745660896254e-07, + "loss": 0.0018, + "step": 60921 + }, + { + "epoch": 18.81, + "learning_rate": 1.836502416150976e-07, + "loss": 0.0018, + "step": 60922 + }, + { + "epoch": 18.81, + "learning_rate": 1.8355484688642123e-07, + "loss": 0.0018, + "step": 60923 + }, + { + "epoch": 18.81, + "learning_rate": 1.8345947671046472e-07, + "loss": 0.0013, + "step": 60924 + }, + { + "epoch": 18.81, + "learning_rate": 1.8336413108746676e-07, + "loss": 0.0016, + "step": 60925 + }, + { + "epoch": 18.82, + "learning_rate": 1.8326881001766495e-07, + "loss": 0.0016, + "step": 60926 + }, + { + "epoch": 18.82, + "learning_rate": 1.831735135012991e-07, + "loss": 0.0024, + "step": 60927 + }, + { + "epoch": 18.82, + "learning_rate": 1.8307824153860675e-07, + "loss": 0.0013, + "step": 60928 + }, + { + "epoch": 18.82, + "learning_rate": 1.8298299412982556e-07, + "loss": 0.0013, + "step": 60929 + }, + { + "epoch": 18.82, + "learning_rate": 1.8288777127519418e-07, + "loss": 0.0016, + "step": 60930 + }, + { + "epoch": 18.82, + "learning_rate": 1.8279257297495244e-07, + "loss": 0.0015, + "step": 60931 + }, + { + "epoch": 18.82, + "learning_rate": 1.826973992293357e-07, + "loss": 0.0022, + "step": 60932 + }, + { + "epoch": 18.82, + "learning_rate": 1.826022500385838e-07, + "loss": 0.0016, + "step": 60933 + }, + { + "epoch": 18.82, + "learning_rate": 1.8250712540293536e-07, + "loss": 0.0012, + "step": 60934 + }, + { + "epoch": 18.82, + "learning_rate": 1.824120253226247e-07, + "loss": 0.0012, + "step": 60935 + }, + { + "epoch": 18.82, + "learning_rate": 1.8231694979789382e-07, + "loss": 0.0015, + "step": 60936 + }, + { + "epoch": 18.82, + "learning_rate": 1.8222189882897924e-07, + "loss": 0.002, + "step": 60937 + }, + { + "epoch": 18.82, + "learning_rate": 1.8212687241611736e-07, + "loss": 0.0017, + "step": 60938 + }, + { + "epoch": 18.82, + "learning_rate": 1.8203187055954695e-07, + "loss": 0.0017, + "step": 60939 + }, + { + "epoch": 18.82, + "learning_rate": 1.819368932595067e-07, + "loss": 0.0015, + "step": 60940 + }, + { + "epoch": 18.82, + "learning_rate": 1.8184194051623084e-07, + "loss": 0.0017, + "step": 60941 + }, + { + "epoch": 18.82, + "learning_rate": 1.817470123299603e-07, + "loss": 0.0018, + "step": 60942 + }, + { + "epoch": 18.82, + "learning_rate": 1.8165210870093153e-07, + "loss": 0.0021, + "step": 60943 + }, + { + "epoch": 18.82, + "learning_rate": 1.8155722962938105e-07, + "loss": 0.0014, + "step": 60944 + }, + { + "epoch": 18.82, + "learning_rate": 1.8146237511554644e-07, + "loss": 0.0021, + "step": 60945 + }, + { + "epoch": 18.82, + "learning_rate": 1.8136754515966638e-07, + "loss": 0.0018, + "step": 60946 + }, + { + "epoch": 18.82, + "learning_rate": 1.8127273976197625e-07, + "loss": 0.0016, + "step": 60947 + }, + { + "epoch": 18.82, + "learning_rate": 1.811779589227136e-07, + "loss": 0.0019, + "step": 60948 + }, + { + "epoch": 18.82, + "learning_rate": 1.8108320264211498e-07, + "loss": 0.0015, + "step": 60949 + }, + { + "epoch": 18.82, + "learning_rate": 1.8098847092042016e-07, + "loss": 0.0014, + "step": 60950 + }, + { + "epoch": 18.82, + "learning_rate": 1.8089376375786226e-07, + "loss": 0.0028, + "step": 60951 + }, + { + "epoch": 18.82, + "learning_rate": 1.8079908115468003e-07, + "loss": 0.0018, + "step": 60952 + }, + { + "epoch": 18.82, + "learning_rate": 1.8070442311111103e-07, + "loss": 0.0019, + "step": 60953 + }, + { + "epoch": 18.82, + "learning_rate": 1.8060978962739172e-07, + "loss": 0.0012, + "step": 60954 + }, + { + "epoch": 18.82, + "learning_rate": 1.805151807037564e-07, + "loss": 0.002, + "step": 60955 + }, + { + "epoch": 18.82, + "learning_rate": 1.8042059634044484e-07, + "loss": 0.0023, + "step": 60956 + }, + { + "epoch": 18.82, + "learning_rate": 1.8032603653769243e-07, + "loss": 0.0023, + "step": 60957 + }, + { + "epoch": 18.82, + "learning_rate": 1.8023150129573564e-07, + "loss": 0.0024, + "step": 60958 + }, + { + "epoch": 18.83, + "learning_rate": 1.8013699061481093e-07, + "loss": 0.0019, + "step": 60959 + }, + { + "epoch": 18.83, + "learning_rate": 1.800425044951537e-07, + "loss": 0.0019, + "step": 60960 + }, + { + "epoch": 18.83, + "learning_rate": 1.7994804293700152e-07, + "loss": 0.0016, + "step": 60961 + }, + { + "epoch": 18.83, + "learning_rate": 1.7985360594059087e-07, + "loss": 0.0015, + "step": 60962 + }, + { + "epoch": 18.83, + "learning_rate": 1.797591935061571e-07, + "loss": 0.0019, + "step": 60963 + }, + { + "epoch": 18.83, + "learning_rate": 1.7966480563393674e-07, + "loss": 0.0018, + "step": 60964 + }, + { + "epoch": 18.83, + "learning_rate": 1.795704423241662e-07, + "loss": 0.0018, + "step": 60965 + }, + { + "epoch": 18.83, + "learning_rate": 1.794761035770809e-07, + "loss": 0.0018, + "step": 60966 + }, + { + "epoch": 18.83, + "learning_rate": 1.7938178939291618e-07, + "loss": 0.0017, + "step": 60967 + }, + { + "epoch": 18.83, + "learning_rate": 1.7928749977190961e-07, + "loss": 0.0016, + "step": 60968 + }, + { + "epoch": 18.83, + "learning_rate": 1.7919323471429662e-07, + "loss": 0.0016, + "step": 60969 + }, + { + "epoch": 18.83, + "learning_rate": 1.790989942203114e-07, + "loss": 0.0019, + "step": 60970 + }, + { + "epoch": 18.83, + "learning_rate": 1.7900477829019158e-07, + "loss": 0.002, + "step": 60971 + }, + { + "epoch": 18.83, + "learning_rate": 1.789105869241714e-07, + "loss": 0.0017, + "step": 60972 + }, + { + "epoch": 18.83, + "learning_rate": 1.7881642012248734e-07, + "loss": 0.0023, + "step": 60973 + }, + { + "epoch": 18.83, + "learning_rate": 1.7872227788537588e-07, + "loss": 0.0014, + "step": 60974 + }, + { + "epoch": 18.83, + "learning_rate": 1.7862816021307016e-07, + "loss": 0.0017, + "step": 60975 + }, + { + "epoch": 18.83, + "learning_rate": 1.7853406710580668e-07, + "loss": 0.0014, + "step": 60976 + }, + { + "epoch": 18.83, + "learning_rate": 1.7843999856382078e-07, + "loss": 0.0016, + "step": 60977 + }, + { + "epoch": 18.83, + "learning_rate": 1.7834595458734783e-07, + "loss": 0.0017, + "step": 60978 + }, + { + "epoch": 18.83, + "learning_rate": 1.7825193517662432e-07, + "loss": 0.002, + "step": 60979 + }, + { + "epoch": 18.83, + "learning_rate": 1.7815794033188338e-07, + "loss": 0.0019, + "step": 60980 + }, + { + "epoch": 18.83, + "learning_rate": 1.7806397005335929e-07, + "loss": 0.0021, + "step": 60981 + }, + { + "epoch": 18.83, + "learning_rate": 1.7797002434128962e-07, + "loss": 0.0011, + "step": 60982 + }, + { + "epoch": 18.83, + "learning_rate": 1.7787610319590752e-07, + "loss": 0.0019, + "step": 60983 + }, + { + "epoch": 18.83, + "learning_rate": 1.777822066174506e-07, + "loss": 0.0016, + "step": 60984 + }, + { + "epoch": 18.83, + "learning_rate": 1.7768833460615088e-07, + "loss": 0.0015, + "step": 60985 + }, + { + "epoch": 18.83, + "learning_rate": 1.775944871622437e-07, + "loss": 0.0013, + "step": 60986 + }, + { + "epoch": 18.83, + "learning_rate": 1.7750066428596557e-07, + "loss": 0.0013, + "step": 60987 + }, + { + "epoch": 18.83, + "learning_rate": 1.7740686597754853e-07, + "loss": 0.0015, + "step": 60988 + }, + { + "epoch": 18.83, + "learning_rate": 1.7731309223722903e-07, + "loss": 0.0022, + "step": 60989 + }, + { + "epoch": 18.83, + "learning_rate": 1.7721934306524136e-07, + "loss": 0.0017, + "step": 60990 + }, + { + "epoch": 18.84, + "learning_rate": 1.7712561846181863e-07, + "loss": 0.0017, + "step": 60991 + }, + { + "epoch": 18.84, + "learning_rate": 1.7703191842719624e-07, + "loss": 0.0018, + "step": 60992 + }, + { + "epoch": 18.84, + "learning_rate": 1.7693824296160956e-07, + "loss": 0.0025, + "step": 60993 + }, + { + "epoch": 18.84, + "learning_rate": 1.768445920652906e-07, + "loss": 0.0013, + "step": 60994 + }, + { + "epoch": 18.84, + "learning_rate": 1.7675096573847694e-07, + "loss": 0.0017, + "step": 60995 + }, + { + "epoch": 18.84, + "learning_rate": 1.7665736398139954e-07, + "loss": 0.0022, + "step": 60996 + }, + { + "epoch": 18.84, + "learning_rate": 1.7656378679429375e-07, + "loss": 0.0018, + "step": 60997 + }, + { + "epoch": 18.84, + "learning_rate": 1.7647023417739384e-07, + "loss": 0.0012, + "step": 60998 + }, + { + "epoch": 18.84, + "learning_rate": 1.7637670613093405e-07, + "loss": 0.0019, + "step": 60999 + }, + { + "epoch": 18.84, + "learning_rate": 1.7628320265514754e-07, + "loss": 0.002, + "step": 61000 + }, + { + "epoch": 18.84, + "learning_rate": 1.7618972375026745e-07, + "loss": 0.0015, + "step": 61001 + }, + { + "epoch": 18.84, + "learning_rate": 1.7609626941653024e-07, + "loss": 0.0016, + "step": 61002 + }, + { + "epoch": 18.84, + "learning_rate": 1.7600283965416687e-07, + "loss": 0.0017, + "step": 61003 + }, + { + "epoch": 18.84, + "learning_rate": 1.7590943446341157e-07, + "loss": 0.0013, + "step": 61004 + }, + { + "epoch": 18.84, + "learning_rate": 1.7581605384449973e-07, + "loss": 0.0013, + "step": 61005 + }, + { + "epoch": 18.84, + "learning_rate": 1.7572269779766448e-07, + "loss": 0.0019, + "step": 61006 + }, + { + "epoch": 18.84, + "learning_rate": 1.7562936632313676e-07, + "loss": 0.0016, + "step": 61007 + }, + { + "epoch": 18.84, + "learning_rate": 1.7553605942115303e-07, + "loss": 0.0013, + "step": 61008 + }, + { + "epoch": 18.84, + "learning_rate": 1.7544277709194535e-07, + "loss": 0.002, + "step": 61009 + }, + { + "epoch": 18.84, + "learning_rate": 1.7534951933574683e-07, + "loss": 0.0016, + "step": 61010 + }, + { + "epoch": 18.84, + "learning_rate": 1.7525628615279177e-07, + "loss": 0.0014, + "step": 61011 + }, + { + "epoch": 18.84, + "learning_rate": 1.751630775433122e-07, + "loss": 0.0019, + "step": 61012 + }, + { + "epoch": 18.84, + "learning_rate": 1.7506989350754122e-07, + "loss": 0.002, + "step": 61013 + }, + { + "epoch": 18.84, + "learning_rate": 1.7497673404571202e-07, + "loss": 0.0019, + "step": 61014 + }, + { + "epoch": 18.84, + "learning_rate": 1.7488359915805997e-07, + "loss": 0.0021, + "step": 61015 + }, + { + "epoch": 18.84, + "learning_rate": 1.7479048884481487e-07, + "loss": 0.0022, + "step": 61016 + }, + { + "epoch": 18.84, + "learning_rate": 1.7469740310620986e-07, + "loss": 0.002, + "step": 61017 + }, + { + "epoch": 18.84, + "learning_rate": 1.7460434194248034e-07, + "loss": 0.002, + "step": 61018 + }, + { + "epoch": 18.84, + "learning_rate": 1.7451130535385608e-07, + "loss": 0.0012, + "step": 61019 + }, + { + "epoch": 18.84, + "learning_rate": 1.7441829334057246e-07, + "loss": 0.0021, + "step": 61020 + }, + { + "epoch": 18.84, + "learning_rate": 1.7432530590286045e-07, + "loss": 0.0016, + "step": 61021 + }, + { + "epoch": 18.84, + "learning_rate": 1.7423234304095205e-07, + "loss": 0.0028, + "step": 61022 + }, + { + "epoch": 18.84, + "learning_rate": 1.741394047550804e-07, + "loss": 0.0019, + "step": 61023 + }, + { + "epoch": 18.85, + "learning_rate": 1.7404649104547866e-07, + "loss": 0.002, + "step": 61024 + }, + { + "epoch": 18.85, + "learning_rate": 1.7395360191237887e-07, + "loss": 0.0013, + "step": 61025 + }, + { + "epoch": 18.85, + "learning_rate": 1.7386073735601416e-07, + "loss": 0.0015, + "step": 61026 + }, + { + "epoch": 18.85, + "learning_rate": 1.7376789737661549e-07, + "loss": 0.0015, + "step": 61027 + }, + { + "epoch": 18.85, + "learning_rate": 1.7367508197441485e-07, + "loss": 0.0015, + "step": 61028 + }, + { + "epoch": 18.85, + "learning_rate": 1.735822911496454e-07, + "loss": 0.0013, + "step": 61029 + }, + { + "epoch": 18.85, + "learning_rate": 1.7348952490253922e-07, + "loss": 0.0022, + "step": 61030 + }, + { + "epoch": 18.85, + "learning_rate": 1.733967832333272e-07, + "loss": 0.0016, + "step": 61031 + }, + { + "epoch": 18.85, + "learning_rate": 1.7330406614224248e-07, + "loss": 0.0016, + "step": 61032 + }, + { + "epoch": 18.85, + "learning_rate": 1.7321137362951711e-07, + "loss": 0.0011, + "step": 61033 + }, + { + "epoch": 18.85, + "learning_rate": 1.7311870569538093e-07, + "loss": 0.0025, + "step": 61034 + }, + { + "epoch": 18.85, + "learning_rate": 1.7302606234006813e-07, + "loss": 0.0021, + "step": 61035 + }, + { + "epoch": 18.85, + "learning_rate": 1.729334435638108e-07, + "loss": 0.0016, + "step": 61036 + }, + { + "epoch": 18.85, + "learning_rate": 1.7284084936683765e-07, + "loss": 0.0018, + "step": 61037 + }, + { + "epoch": 18.85, + "learning_rate": 1.727482797493818e-07, + "loss": 0.0011, + "step": 61038 + }, + { + "epoch": 18.85, + "learning_rate": 1.726557347116753e-07, + "loss": 0.0014, + "step": 61039 + }, + { + "epoch": 18.85, + "learning_rate": 1.7256321425394907e-07, + "loss": 0.0014, + "step": 61040 + }, + { + "epoch": 18.85, + "learning_rate": 1.7247071837643515e-07, + "loss": 0.0019, + "step": 61041 + }, + { + "epoch": 18.85, + "learning_rate": 1.7237824707936445e-07, + "loss": 0.0014, + "step": 61042 + }, + { + "epoch": 18.85, + "learning_rate": 1.7228580036296683e-07, + "loss": 0.0016, + "step": 61043 + }, + { + "epoch": 18.85, + "learning_rate": 1.721933782274754e-07, + "loss": 0.0018, + "step": 61044 + }, + { + "epoch": 18.85, + "learning_rate": 1.721009806731211e-07, + "loss": 0.0013, + "step": 61045 + }, + { + "epoch": 18.85, + "learning_rate": 1.7200860770013593e-07, + "loss": 0.0017, + "step": 61046 + }, + { + "epoch": 18.85, + "learning_rate": 1.7191625930874756e-07, + "loss": 0.0021, + "step": 61047 + }, + { + "epoch": 18.85, + "learning_rate": 1.7182393549919018e-07, + "loss": 0.0018, + "step": 61048 + }, + { + "epoch": 18.85, + "learning_rate": 1.7173163627169476e-07, + "loss": 0.0013, + "step": 61049 + }, + { + "epoch": 18.85, + "learning_rate": 1.7163936162648887e-07, + "loss": 0.0019, + "step": 61050 + }, + { + "epoch": 18.85, + "learning_rate": 1.7154711156380787e-07, + "loss": 0.0016, + "step": 61051 + }, + { + "epoch": 18.85, + "learning_rate": 1.714548860838794e-07, + "loss": 0.0028, + "step": 61052 + }, + { + "epoch": 18.85, + "learning_rate": 1.7136268518693434e-07, + "loss": 0.0014, + "step": 61053 + }, + { + "epoch": 18.85, + "learning_rate": 1.7127050887320252e-07, + "loss": 0.0024, + "step": 61054 + }, + { + "epoch": 18.85, + "learning_rate": 1.711783571429182e-07, + "loss": 0.0018, + "step": 61055 + }, + { + "epoch": 18.86, + "learning_rate": 1.7108622999630896e-07, + "loss": 0.0015, + "step": 61056 + }, + { + "epoch": 18.86, + "learning_rate": 1.7099412743360465e-07, + "loss": 0.0012, + "step": 61057 + }, + { + "epoch": 18.86, + "learning_rate": 1.709020494550384e-07, + "loss": 0.0022, + "step": 61058 + }, + { + "epoch": 18.86, + "learning_rate": 1.708099960608367e-07, + "loss": 0.0016, + "step": 61059 + }, + { + "epoch": 18.86, + "learning_rate": 1.707179672512327e-07, + "loss": 0.0015, + "step": 61060 + }, + { + "epoch": 18.86, + "learning_rate": 1.706259630264573e-07, + "loss": 0.0015, + "step": 61061 + }, + { + "epoch": 18.86, + "learning_rate": 1.705339833867381e-07, + "loss": 0.0019, + "step": 61062 + }, + { + "epoch": 18.86, + "learning_rate": 1.7044202833230604e-07, + "loss": 0.0013, + "step": 61063 + }, + { + "epoch": 18.86, + "learning_rate": 1.7035009786339097e-07, + "loss": 0.0018, + "step": 61064 + }, + { + "epoch": 18.86, + "learning_rate": 1.7025819198022376e-07, + "loss": 0.0012, + "step": 61065 + }, + { + "epoch": 18.86, + "learning_rate": 1.7016631068303313e-07, + "loss": 0.0014, + "step": 61066 + }, + { + "epoch": 18.86, + "learning_rate": 1.7007445397205003e-07, + "loss": 0.002, + "step": 61067 + }, + { + "epoch": 18.86, + "learning_rate": 1.6998262184750313e-07, + "loss": 0.002, + "step": 61068 + }, + { + "epoch": 18.86, + "learning_rate": 1.698908143096223e-07, + "loss": 0.0015, + "step": 61069 + }, + { + "epoch": 18.86, + "learning_rate": 1.697990313586384e-07, + "loss": 0.0012, + "step": 61070 + }, + { + "epoch": 18.86, + "learning_rate": 1.6970727299477908e-07, + "loss": 0.0019, + "step": 61071 + }, + { + "epoch": 18.86, + "learning_rate": 1.6961553921827523e-07, + "loss": 0.0014, + "step": 61072 + }, + { + "epoch": 18.86, + "learning_rate": 1.6952383002935556e-07, + "loss": 0.002, + "step": 61073 + }, + { + "epoch": 18.86, + "learning_rate": 1.6943214542824993e-07, + "loss": 0.0021, + "step": 61074 + }, + { + "epoch": 18.86, + "learning_rate": 1.6934048541518698e-07, + "loss": 0.0014, + "step": 61075 + }, + { + "epoch": 18.86, + "learning_rate": 1.692488499903977e-07, + "loss": 0.0018, + "step": 61076 + }, + { + "epoch": 18.86, + "learning_rate": 1.6915723915410965e-07, + "loss": 0.0023, + "step": 61077 + }, + { + "epoch": 18.86, + "learning_rate": 1.690656529065515e-07, + "loss": 0.0015, + "step": 61078 + }, + { + "epoch": 18.86, + "learning_rate": 1.6897409124795428e-07, + "loss": 0.0018, + "step": 61079 + }, + { + "epoch": 18.86, + "learning_rate": 1.6888255417854548e-07, + "loss": 0.0013, + "step": 61080 + }, + { + "epoch": 18.86, + "learning_rate": 1.6879104169855388e-07, + "loss": 0.0015, + "step": 61081 + }, + { + "epoch": 18.86, + "learning_rate": 1.6869955380821035e-07, + "loss": 0.0009, + "step": 61082 + }, + { + "epoch": 18.86, + "learning_rate": 1.686080905077414e-07, + "loss": 0.0017, + "step": 61083 + }, + { + "epoch": 18.86, + "learning_rate": 1.6851665179737686e-07, + "loss": 0.0022, + "step": 61084 + }, + { + "epoch": 18.86, + "learning_rate": 1.6842523767734542e-07, + "loss": 0.0014, + "step": 61085 + }, + { + "epoch": 18.86, + "learning_rate": 1.683338481478758e-07, + "loss": 0.0014, + "step": 61086 + }, + { + "epoch": 18.86, + "learning_rate": 1.6824248320919666e-07, + "loss": 0.0016, + "step": 61087 + }, + { + "epoch": 18.87, + "learning_rate": 1.6815114286153565e-07, + "loss": 0.0013, + "step": 61088 + }, + { + "epoch": 18.87, + "learning_rate": 1.6805982710512258e-07, + "loss": 0.0015, + "step": 61089 + }, + { + "epoch": 18.87, + "learning_rate": 1.679685359401839e-07, + "loss": 0.0017, + "step": 61090 + }, + { + "epoch": 18.87, + "learning_rate": 1.6787726936694948e-07, + "loss": 0.0021, + "step": 61091 + }, + { + "epoch": 18.87, + "learning_rate": 1.6778602738564797e-07, + "loss": 0.0013, + "step": 61092 + }, + { + "epoch": 18.87, + "learning_rate": 1.6769480999650701e-07, + "loss": 0.0019, + "step": 61093 + }, + { + "epoch": 18.87, + "learning_rate": 1.6760361719975415e-07, + "loss": 0.0014, + "step": 61094 + }, + { + "epoch": 18.87, + "learning_rate": 1.6751244899561813e-07, + "loss": 0.0021, + "step": 61095 + }, + { + "epoch": 18.87, + "learning_rate": 1.6742130538432656e-07, + "loss": 0.0009, + "step": 61096 + }, + { + "epoch": 18.87, + "learning_rate": 1.673301863661081e-07, + "loss": 0.0017, + "step": 61097 + }, + { + "epoch": 18.87, + "learning_rate": 1.6723909194119037e-07, + "loss": 0.0017, + "step": 61098 + }, + { + "epoch": 18.87, + "learning_rate": 1.6714802210979986e-07, + "loss": 0.0015, + "step": 61099 + }, + { + "epoch": 18.87, + "learning_rate": 1.6705697687216527e-07, + "loss": 0.0012, + "step": 61100 + }, + { + "epoch": 18.87, + "learning_rate": 1.669659562285164e-07, + "loss": 0.0019, + "step": 61101 + }, + { + "epoch": 18.87, + "learning_rate": 1.6687496017907757e-07, + "loss": 0.002, + "step": 61102 + }, + { + "epoch": 18.87, + "learning_rate": 1.6678398872407963e-07, + "loss": 0.0018, + "step": 61103 + }, + { + "epoch": 18.87, + "learning_rate": 1.666930418637469e-07, + "loss": 0.0015, + "step": 61104 + }, + { + "epoch": 18.87, + "learning_rate": 1.666021195983092e-07, + "loss": 0.0015, + "step": 61105 + }, + { + "epoch": 18.87, + "learning_rate": 1.6651122192799186e-07, + "loss": 0.0012, + "step": 61106 + }, + { + "epoch": 18.87, + "learning_rate": 1.6642034885302472e-07, + "loss": 0.0013, + "step": 61107 + }, + { + "epoch": 18.87, + "learning_rate": 1.6632950037363427e-07, + "loss": 0.0023, + "step": 61108 + }, + { + "epoch": 18.87, + "learning_rate": 1.6623867649004588e-07, + "loss": 0.0018, + "step": 61109 + }, + { + "epoch": 18.87, + "learning_rate": 1.6614787720248938e-07, + "loss": 0.0019, + "step": 61110 + }, + { + "epoch": 18.87, + "learning_rate": 1.66057102511189e-07, + "loss": 0.0014, + "step": 61111 + }, + { + "epoch": 18.87, + "learning_rate": 1.659663524163746e-07, + "loss": 0.0017, + "step": 61112 + }, + { + "epoch": 18.87, + "learning_rate": 1.6587562691827153e-07, + "loss": 0.0021, + "step": 61113 + }, + { + "epoch": 18.87, + "learning_rate": 1.657849260171085e-07, + "loss": 0.0018, + "step": 61114 + }, + { + "epoch": 18.87, + "learning_rate": 1.6569424971310865e-07, + "loss": 0.0025, + "step": 61115 + }, + { + "epoch": 18.87, + "learning_rate": 1.6560359800650294e-07, + "loss": 0.0024, + "step": 61116 + }, + { + "epoch": 18.87, + "learning_rate": 1.655129708975156e-07, + "loss": 0.0019, + "step": 61117 + }, + { + "epoch": 18.87, + "learning_rate": 1.6542236838637426e-07, + "loss": 0.0023, + "step": 61118 + }, + { + "epoch": 18.87, + "learning_rate": 1.6533179047330538e-07, + "loss": 0.002, + "step": 61119 + }, + { + "epoch": 18.87, + "learning_rate": 1.6524123715853545e-07, + "loss": 0.0022, + "step": 61120 + }, + { + "epoch": 18.88, + "learning_rate": 1.6515070844228987e-07, + "loss": 0.0017, + "step": 61121 + }, + { + "epoch": 18.88, + "learning_rate": 1.650602043247973e-07, + "loss": 0.0016, + "step": 61122 + }, + { + "epoch": 18.88, + "learning_rate": 1.6496972480628315e-07, + "loss": 0.0019, + "step": 61123 + }, + { + "epoch": 18.88, + "learning_rate": 1.6487926988697277e-07, + "loss": 0.0017, + "step": 61124 + }, + { + "epoch": 18.88, + "learning_rate": 1.647888395670938e-07, + "loss": 0.0016, + "step": 61125 + }, + { + "epoch": 18.88, + "learning_rate": 1.6469843384687155e-07, + "loss": 0.0017, + "step": 61126 + }, + { + "epoch": 18.88, + "learning_rate": 1.6460805272653146e-07, + "loss": 0.0017, + "step": 61127 + }, + { + "epoch": 18.88, + "learning_rate": 1.645176962063011e-07, + "loss": 0.0013, + "step": 61128 + }, + { + "epoch": 18.88, + "learning_rate": 1.6442736428640692e-07, + "loss": 0.0015, + "step": 61129 + }, + { + "epoch": 18.88, + "learning_rate": 1.6433705696707214e-07, + "loss": 0.0016, + "step": 61130 + }, + { + "epoch": 18.88, + "learning_rate": 1.6424677424852542e-07, + "loss": 0.0015, + "step": 61131 + }, + { + "epoch": 18.88, + "learning_rate": 1.6415651613099105e-07, + "loss": 0.0015, + "step": 61132 + }, + { + "epoch": 18.88, + "learning_rate": 1.6406628261469438e-07, + "loss": 0.0024, + "step": 61133 + }, + { + "epoch": 18.88, + "learning_rate": 1.6397607369986302e-07, + "loss": 0.0017, + "step": 61134 + }, + { + "epoch": 18.88, + "learning_rate": 1.6388588938672235e-07, + "loss": 0.0014, + "step": 61135 + }, + { + "epoch": 18.88, + "learning_rate": 1.637957296754944e-07, + "loss": 0.0018, + "step": 61136 + }, + { + "epoch": 18.88, + "learning_rate": 1.63705594566409e-07, + "loss": 0.0014, + "step": 61137 + }, + { + "epoch": 18.88, + "learning_rate": 1.6361548405969042e-07, + "loss": 0.0018, + "step": 61138 + }, + { + "epoch": 18.88, + "learning_rate": 1.6352539815556289e-07, + "loss": 0.0015, + "step": 61139 + }, + { + "epoch": 18.88, + "learning_rate": 1.6343533685425185e-07, + "loss": 0.0015, + "step": 61140 + }, + { + "epoch": 18.88, + "learning_rate": 1.633453001559837e-07, + "loss": 0.0015, + "step": 61141 + }, + { + "epoch": 18.88, + "learning_rate": 1.6325528806098277e-07, + "loss": 0.0017, + "step": 61142 + }, + { + "epoch": 18.88, + "learning_rate": 1.6316530056947443e-07, + "loss": 0.0013, + "step": 61143 + }, + { + "epoch": 18.88, + "learning_rate": 1.6307533768168516e-07, + "loss": 0.0017, + "step": 61144 + }, + { + "epoch": 18.88, + "learning_rate": 1.6298539939783697e-07, + "loss": 0.0015, + "step": 61145 + }, + { + "epoch": 18.88, + "learning_rate": 1.628954857181564e-07, + "loss": 0.0019, + "step": 61146 + }, + { + "epoch": 18.88, + "learning_rate": 1.6280559664286876e-07, + "loss": 0.0019, + "step": 61147 + }, + { + "epoch": 18.88, + "learning_rate": 1.627157321721995e-07, + "loss": 0.0013, + "step": 61148 + }, + { + "epoch": 18.88, + "learning_rate": 1.626258923063717e-07, + "loss": 0.002, + "step": 61149 + }, + { + "epoch": 18.88, + "learning_rate": 1.625360770456108e-07, + "loss": 0.0014, + "step": 61150 + }, + { + "epoch": 18.88, + "learning_rate": 1.6244628639014216e-07, + "loss": 0.0013, + "step": 61151 + }, + { + "epoch": 18.88, + "learning_rate": 1.623565203401878e-07, + "loss": 0.0014, + "step": 61152 + }, + { + "epoch": 18.89, + "learning_rate": 1.622667788959742e-07, + "loss": 0.0018, + "step": 61153 + }, + { + "epoch": 18.89, + "learning_rate": 1.6217706205772789e-07, + "loss": 0.0013, + "step": 61154 + }, + { + "epoch": 18.89, + "learning_rate": 1.6208736982566975e-07, + "loss": 0.0018, + "step": 61155 + }, + { + "epoch": 18.89, + "learning_rate": 1.6199770220002519e-07, + "loss": 0.0015, + "step": 61156 + }, + { + "epoch": 18.89, + "learning_rate": 1.6190805918101848e-07, + "loss": 0.0015, + "step": 61157 + }, + { + "epoch": 18.89, + "learning_rate": 1.6181844076887498e-07, + "loss": 0.0019, + "step": 61158 + }, + { + "epoch": 18.89, + "learning_rate": 1.6172884696381786e-07, + "loss": 0.0021, + "step": 61159 + }, + { + "epoch": 18.89, + "learning_rate": 1.6163927776607024e-07, + "loss": 0.0014, + "step": 61160 + }, + { + "epoch": 18.89, + "learning_rate": 1.6154973317585754e-07, + "loss": 0.0015, + "step": 61161 + }, + { + "epoch": 18.89, + "learning_rate": 1.6146021319340398e-07, + "loss": 0.0022, + "step": 61162 + }, + { + "epoch": 18.89, + "learning_rate": 1.6137071781893276e-07, + "loss": 0.0015, + "step": 61163 + }, + { + "epoch": 18.89, + "learning_rate": 1.6128124705266813e-07, + "loss": 0.0015, + "step": 61164 + }, + { + "epoch": 18.89, + "learning_rate": 1.611918008948321e-07, + "loss": 0.0019, + "step": 61165 + }, + { + "epoch": 18.89, + "learning_rate": 1.611023793456512e-07, + "loss": 0.0016, + "step": 61166 + }, + { + "epoch": 18.89, + "learning_rate": 1.6101298240534746e-07, + "loss": 0.0023, + "step": 61167 + }, + { + "epoch": 18.89, + "learning_rate": 1.6092361007414403e-07, + "loss": 0.0022, + "step": 61168 + }, + { + "epoch": 18.89, + "learning_rate": 1.6083426235226628e-07, + "loss": 0.0021, + "step": 61169 + }, + { + "epoch": 18.89, + "learning_rate": 1.607449392399363e-07, + "loss": 0.0018, + "step": 61170 + }, + { + "epoch": 18.89, + "learning_rate": 1.6065564073737717e-07, + "loss": 0.0018, + "step": 61171 + }, + { + "epoch": 18.89, + "learning_rate": 1.605663668448143e-07, + "loss": 0.0016, + "step": 61172 + }, + { + "epoch": 18.89, + "learning_rate": 1.6047711756246753e-07, + "loss": 0.0017, + "step": 61173 + }, + { + "epoch": 18.89, + "learning_rate": 1.6038789289056335e-07, + "loss": 0.0018, + "step": 61174 + }, + { + "epoch": 18.89, + "learning_rate": 1.6029869282932376e-07, + "loss": 0.002, + "step": 61175 + }, + { + "epoch": 18.89, + "learning_rate": 1.6020951737897194e-07, + "loss": 0.0016, + "step": 61176 + }, + { + "epoch": 18.89, + "learning_rate": 1.6012036653972996e-07, + "loss": 0.0014, + "step": 61177 + }, + { + "epoch": 18.89, + "learning_rate": 1.6003124031182092e-07, + "loss": 0.0019, + "step": 61178 + }, + { + "epoch": 18.89, + "learning_rate": 1.5994213869547026e-07, + "loss": 0.0016, + "step": 61179 + }, + { + "epoch": 18.89, + "learning_rate": 1.5985306169089887e-07, + "loss": 0.0013, + "step": 61180 + }, + { + "epoch": 18.89, + "learning_rate": 1.597640092983288e-07, + "loss": 0.0021, + "step": 61181 + }, + { + "epoch": 18.89, + "learning_rate": 1.5967498151798433e-07, + "loss": 0.0015, + "step": 61182 + }, + { + "epoch": 18.89, + "learning_rate": 1.5958597835008638e-07, + "loss": 0.0013, + "step": 61183 + }, + { + "epoch": 18.89, + "learning_rate": 1.5949699979485922e-07, + "loss": 0.0014, + "step": 61184 + }, + { + "epoch": 18.9, + "learning_rate": 1.59408045852526e-07, + "loss": 0.0016, + "step": 61185 + }, + { + "epoch": 18.9, + "learning_rate": 1.5931911652330767e-07, + "loss": 0.0012, + "step": 61186 + }, + { + "epoch": 18.9, + "learning_rate": 1.5923021180742627e-07, + "loss": 0.0017, + "step": 61187 + }, + { + "epoch": 18.9, + "learning_rate": 1.5914133170510492e-07, + "loss": 0.0018, + "step": 61188 + }, + { + "epoch": 18.9, + "learning_rate": 1.5905247621656572e-07, + "loss": 0.0018, + "step": 61189 + }, + { + "epoch": 18.9, + "learning_rate": 1.589636453420329e-07, + "loss": 0.0021, + "step": 61190 + }, + { + "epoch": 18.9, + "learning_rate": 1.588748390817263e-07, + "loss": 0.0015, + "step": 61191 + }, + { + "epoch": 18.9, + "learning_rate": 1.5878605743586685e-07, + "loss": 0.0017, + "step": 61192 + }, + { + "epoch": 18.9, + "learning_rate": 1.586973004046799e-07, + "loss": 0.0016, + "step": 61193 + }, + { + "epoch": 18.9, + "learning_rate": 1.586085679883853e-07, + "loss": 0.0014, + "step": 61194 + }, + { + "epoch": 18.9, + "learning_rate": 1.5851986018720732e-07, + "loss": 0.0017, + "step": 61195 + }, + { + "epoch": 18.9, + "learning_rate": 1.5843117700136357e-07, + "loss": 0.0015, + "step": 61196 + }, + { + "epoch": 18.9, + "learning_rate": 1.583425184310805e-07, + "loss": 0.0014, + "step": 61197 + }, + { + "epoch": 18.9, + "learning_rate": 1.5825388447657685e-07, + "loss": 0.0013, + "step": 61198 + }, + { + "epoch": 18.9, + "learning_rate": 1.5816527513807466e-07, + "loss": 0.0017, + "step": 61199 + }, + { + "epoch": 18.9, + "learning_rate": 1.580766904157971e-07, + "loss": 0.0018, + "step": 61200 + }, + { + "epoch": 18.9, + "learning_rate": 1.5798813030996508e-07, + "loss": 0.0026, + "step": 61201 + }, + { + "epoch": 18.9, + "learning_rate": 1.5789959482079953e-07, + "loss": 0.0013, + "step": 61202 + }, + { + "epoch": 18.9, + "learning_rate": 1.578110839485214e-07, + "loss": 0.002, + "step": 61203 + }, + { + "epoch": 18.9, + "learning_rate": 1.5772259769335386e-07, + "loss": 0.0019, + "step": 61204 + }, + { + "epoch": 18.9, + "learning_rate": 1.576341360555167e-07, + "loss": 0.0017, + "step": 61205 + }, + { + "epoch": 18.9, + "learning_rate": 1.5754569903523198e-07, + "loss": 0.002, + "step": 61206 + }, + { + "epoch": 18.9, + "learning_rate": 1.5745728663272065e-07, + "loss": 0.0019, + "step": 61207 + }, + { + "epoch": 18.9, + "learning_rate": 1.573688988482025e-07, + "loss": 0.0015, + "step": 61208 + }, + { + "epoch": 18.9, + "learning_rate": 1.5728053568190183e-07, + "loss": 0.0017, + "step": 61209 + }, + { + "epoch": 18.9, + "learning_rate": 1.571921971340362e-07, + "loss": 0.0024, + "step": 61210 + }, + { + "epoch": 18.9, + "learning_rate": 1.5710388320482993e-07, + "loss": 0.0017, + "step": 61211 + }, + { + "epoch": 18.9, + "learning_rate": 1.570155938945006e-07, + "loss": 0.0016, + "step": 61212 + }, + { + "epoch": 18.9, + "learning_rate": 1.5692732920327135e-07, + "loss": 0.002, + "step": 61213 + }, + { + "epoch": 18.9, + "learning_rate": 1.568390891313609e-07, + "loss": 0.0018, + "step": 61214 + }, + { + "epoch": 18.9, + "learning_rate": 1.5675087367899245e-07, + "loss": 0.0019, + "step": 61215 + }, + { + "epoch": 18.9, + "learning_rate": 1.5666268284638464e-07, + "loss": 0.0019, + "step": 61216 + }, + { + "epoch": 18.9, + "learning_rate": 1.5657451663375844e-07, + "loss": 0.0017, + "step": 61217 + }, + { + "epoch": 18.91, + "learning_rate": 1.5648637504133478e-07, + "loss": 0.0019, + "step": 61218 + }, + { + "epoch": 18.91, + "learning_rate": 1.5639825806933574e-07, + "loss": 0.0012, + "step": 61219 + }, + { + "epoch": 18.91, + "learning_rate": 1.5631016571797775e-07, + "loss": 0.0014, + "step": 61220 + }, + { + "epoch": 18.91, + "learning_rate": 1.562220979874851e-07, + "loss": 0.0023, + "step": 61221 + }, + { + "epoch": 18.91, + "learning_rate": 1.5613405487807654e-07, + "loss": 0.0014, + "step": 61222 + }, + { + "epoch": 18.91, + "learning_rate": 1.5604603638997073e-07, + "loss": 0.0019, + "step": 61223 + }, + { + "epoch": 18.91, + "learning_rate": 1.5595804252338864e-07, + "loss": 0.0012, + "step": 61224 + }, + { + "epoch": 18.91, + "learning_rate": 1.558700732785523e-07, + "loss": 0.0015, + "step": 61225 + }, + { + "epoch": 18.91, + "learning_rate": 1.5578212865568153e-07, + "loss": 0.0014, + "step": 61226 + }, + { + "epoch": 18.91, + "learning_rate": 1.5569420865499285e-07, + "loss": 0.0015, + "step": 61227 + }, + { + "epoch": 18.91, + "learning_rate": 1.5560631327670938e-07, + "loss": 0.0015, + "step": 61228 + }, + { + "epoch": 18.91, + "learning_rate": 1.5551844252104987e-07, + "loss": 0.0021, + "step": 61229 + }, + { + "epoch": 18.91, + "learning_rate": 1.554305963882341e-07, + "loss": 0.0015, + "step": 61230 + }, + { + "epoch": 18.91, + "learning_rate": 1.5534277487848192e-07, + "loss": 0.0024, + "step": 61231 + }, + { + "epoch": 18.91, + "learning_rate": 1.5525497799201428e-07, + "loss": 0.0014, + "step": 61232 + }, + { + "epoch": 18.91, + "learning_rate": 1.5516720572904764e-07, + "loss": 0.0023, + "step": 61233 + }, + { + "epoch": 18.91, + "learning_rate": 1.550794580898052e-07, + "loss": 0.0016, + "step": 61234 + }, + { + "epoch": 18.91, + "learning_rate": 1.5499173507450338e-07, + "loss": 0.0016, + "step": 61235 + }, + { + "epoch": 18.91, + "learning_rate": 1.5490403668336317e-07, + "loss": 0.0016, + "step": 61236 + }, + { + "epoch": 18.91, + "learning_rate": 1.548163629166044e-07, + "loss": 0.0015, + "step": 61237 + }, + { + "epoch": 18.91, + "learning_rate": 1.5472871377444355e-07, + "loss": 0.0017, + "step": 61238 + }, + { + "epoch": 18.91, + "learning_rate": 1.5464108925710263e-07, + "loss": 0.0014, + "step": 61239 + }, + { + "epoch": 18.91, + "learning_rate": 1.5455348936480152e-07, + "loss": 0.0016, + "step": 61240 + }, + { + "epoch": 18.91, + "learning_rate": 1.544659140977567e-07, + "loss": 0.0015, + "step": 61241 + }, + { + "epoch": 18.91, + "learning_rate": 1.5437836345618796e-07, + "loss": 0.0021, + "step": 61242 + }, + { + "epoch": 18.91, + "learning_rate": 1.5429083744031515e-07, + "loss": 0.0009, + "step": 61243 + }, + { + "epoch": 18.91, + "learning_rate": 1.5420333605035698e-07, + "loss": 0.002, + "step": 61244 + }, + { + "epoch": 18.91, + "learning_rate": 1.5411585928653104e-07, + "loss": 0.0018, + "step": 61245 + }, + { + "epoch": 18.91, + "learning_rate": 1.5402840714905832e-07, + "loss": 0.0017, + "step": 61246 + }, + { + "epoch": 18.91, + "learning_rate": 1.5394097963815636e-07, + "loss": 0.0018, + "step": 61247 + }, + { + "epoch": 18.91, + "learning_rate": 1.5385357675404278e-07, + "loss": 0.002, + "step": 61248 + }, + { + "epoch": 18.91, + "learning_rate": 1.537661984969374e-07, + "loss": 0.0013, + "step": 61249 + }, + { + "epoch": 18.92, + "learning_rate": 1.5367884486705898e-07, + "loss": 0.0012, + "step": 61250 + }, + { + "epoch": 18.92, + "learning_rate": 1.5359151586462506e-07, + "loss": 0.002, + "step": 61251 + }, + { + "epoch": 18.92, + "learning_rate": 1.535042114898555e-07, + "loss": 0.0019, + "step": 61252 + }, + { + "epoch": 18.92, + "learning_rate": 1.534169317429679e-07, + "loss": 0.0016, + "step": 61253 + }, + { + "epoch": 18.92, + "learning_rate": 1.5332967662417985e-07, + "loss": 0.0012, + "step": 61254 + }, + { + "epoch": 18.92, + "learning_rate": 1.532424461337101e-07, + "loss": 0.001, + "step": 61255 + }, + { + "epoch": 18.92, + "learning_rate": 1.5315524027177732e-07, + "loss": 0.0021, + "step": 61256 + }, + { + "epoch": 18.92, + "learning_rate": 1.5306805903860022e-07, + "loss": 0.0012, + "step": 61257 + }, + { + "epoch": 18.92, + "learning_rate": 1.5298090243439423e-07, + "loss": 0.0016, + "step": 61258 + }, + { + "epoch": 18.92, + "learning_rate": 1.5289377045937914e-07, + "loss": 0.0018, + "step": 61259 + }, + { + "epoch": 18.92, + "learning_rate": 1.5280666311377256e-07, + "loss": 0.0017, + "step": 61260 + }, + { + "epoch": 18.92, + "learning_rate": 1.5271958039779321e-07, + "loss": 0.0017, + "step": 61261 + }, + { + "epoch": 18.92, + "learning_rate": 1.526325223116587e-07, + "loss": 0.0017, + "step": 61262 + }, + { + "epoch": 18.92, + "learning_rate": 1.525454888555855e-07, + "loss": 0.0016, + "step": 61263 + }, + { + "epoch": 18.92, + "learning_rate": 1.5245848002979237e-07, + "loss": 0.002, + "step": 61264 + }, + { + "epoch": 18.92, + "learning_rate": 1.5237149583449684e-07, + "loss": 0.0022, + "step": 61265 + }, + { + "epoch": 18.92, + "learning_rate": 1.5228453626991547e-07, + "loss": 0.0019, + "step": 61266 + }, + { + "epoch": 18.92, + "learning_rate": 1.5219760133626804e-07, + "loss": 0.0017, + "step": 61267 + }, + { + "epoch": 18.92, + "learning_rate": 1.5211069103376995e-07, + "loss": 0.0019, + "step": 61268 + }, + { + "epoch": 18.92, + "learning_rate": 1.5202380536263772e-07, + "loss": 0.0021, + "step": 61269 + }, + { + "epoch": 18.92, + "learning_rate": 1.5193694432309114e-07, + "loss": 0.0019, + "step": 61270 + }, + { + "epoch": 18.92, + "learning_rate": 1.518501079153467e-07, + "loss": 0.0018, + "step": 61271 + }, + { + "epoch": 18.92, + "learning_rate": 1.5176329613962094e-07, + "loss": 0.0018, + "step": 61272 + }, + { + "epoch": 18.92, + "learning_rate": 1.516765089961325e-07, + "loss": 0.0022, + "step": 61273 + }, + { + "epoch": 18.92, + "learning_rate": 1.5158974648509683e-07, + "loss": 0.0015, + "step": 61274 + }, + { + "epoch": 18.92, + "learning_rate": 1.515030086067304e-07, + "loss": 0.0014, + "step": 61275 + }, + { + "epoch": 18.92, + "learning_rate": 1.5141629536125079e-07, + "loss": 0.0018, + "step": 61276 + }, + { + "epoch": 18.92, + "learning_rate": 1.5132960674887675e-07, + "loss": 0.0024, + "step": 61277 + }, + { + "epoch": 18.92, + "learning_rate": 1.5124294276982365e-07, + "loss": 0.0017, + "step": 61278 + }, + { + "epoch": 18.92, + "learning_rate": 1.51156303424308e-07, + "loss": 0.0016, + "step": 61279 + }, + { + "epoch": 18.92, + "learning_rate": 1.5106968871254624e-07, + "loss": 0.0016, + "step": 61280 + }, + { + "epoch": 18.92, + "learning_rate": 1.5098309863475602e-07, + "loss": 0.0019, + "step": 61281 + }, + { + "epoch": 18.92, + "learning_rate": 1.508965331911527e-07, + "loss": 0.0015, + "step": 61282 + }, + { + "epoch": 18.93, + "learning_rate": 1.5080999238195504e-07, + "loss": 0.0015, + "step": 61283 + }, + { + "epoch": 18.93, + "learning_rate": 1.5072347620737725e-07, + "loss": 0.0017, + "step": 61284 + }, + { + "epoch": 18.93, + "learning_rate": 1.5063698466763586e-07, + "loss": 0.0025, + "step": 61285 + }, + { + "epoch": 18.93, + "learning_rate": 1.5055051776294738e-07, + "loss": 0.0014, + "step": 61286 + }, + { + "epoch": 18.93, + "learning_rate": 1.5046407549352938e-07, + "loss": 0.0025, + "step": 61287 + }, + { + "epoch": 18.93, + "learning_rate": 1.5037765785959834e-07, + "loss": 0.0018, + "step": 61288 + }, + { + "epoch": 18.93, + "learning_rate": 1.5029126486136748e-07, + "loss": 0.0015, + "step": 61289 + }, + { + "epoch": 18.93, + "learning_rate": 1.5020489649905546e-07, + "loss": 0.0017, + "step": 61290 + }, + { + "epoch": 18.93, + "learning_rate": 1.5011855277287657e-07, + "loss": 0.0019, + "step": 61291 + }, + { + "epoch": 18.93, + "learning_rate": 1.5003223368304732e-07, + "loss": 0.0015, + "step": 61292 + }, + { + "epoch": 18.93, + "learning_rate": 1.499459392297864e-07, + "loss": 0.0021, + "step": 61293 + }, + { + "epoch": 18.93, + "learning_rate": 1.4985966941330476e-07, + "loss": 0.0019, + "step": 61294 + }, + { + "epoch": 18.93, + "learning_rate": 1.4977342423382223e-07, + "loss": 0.0021, + "step": 61295 + }, + { + "epoch": 18.93, + "learning_rate": 1.4968720369155198e-07, + "loss": 0.0021, + "step": 61296 + }, + { + "epoch": 18.93, + "learning_rate": 1.496010077867105e-07, + "loss": 0.0016, + "step": 61297 + }, + { + "epoch": 18.93, + "learning_rate": 1.4951483651951425e-07, + "loss": 0.0019, + "step": 61298 + }, + { + "epoch": 18.93, + "learning_rate": 1.4942868989017868e-07, + "loss": 0.0019, + "step": 61299 + }, + { + "epoch": 18.93, + "learning_rate": 1.4934256789891687e-07, + "loss": 0.0018, + "step": 61300 + }, + { + "epoch": 18.93, + "learning_rate": 1.492564705459465e-07, + "loss": 0.0026, + "step": 61301 + }, + { + "epoch": 18.93, + "learning_rate": 1.491703978314829e-07, + "loss": 0.002, + "step": 61302 + }, + { + "epoch": 18.93, + "learning_rate": 1.4908434975574038e-07, + "loss": 0.0012, + "step": 61303 + }, + { + "epoch": 18.93, + "learning_rate": 1.4899832631893428e-07, + "loss": 0.0022, + "step": 61304 + }, + { + "epoch": 18.93, + "learning_rate": 1.4891232752128115e-07, + "loss": 0.0013, + "step": 61305 + }, + { + "epoch": 18.93, + "learning_rate": 1.488263533629941e-07, + "loss": 0.0023, + "step": 61306 + }, + { + "epoch": 18.93, + "learning_rate": 1.4874040384428856e-07, + "loss": 0.0014, + "step": 61307 + }, + { + "epoch": 18.93, + "learning_rate": 1.48654478965381e-07, + "loss": 0.0014, + "step": 61308 + }, + { + "epoch": 18.93, + "learning_rate": 1.4856857872648567e-07, + "loss": 0.0016, + "step": 61309 + }, + { + "epoch": 18.93, + "learning_rate": 1.4848270312781688e-07, + "loss": 0.0013, + "step": 61310 + }, + { + "epoch": 18.93, + "learning_rate": 1.4839685216958888e-07, + "loss": 0.0018, + "step": 61311 + }, + { + "epoch": 18.93, + "learning_rate": 1.4831102585201818e-07, + "loss": 0.0013, + "step": 61312 + }, + { + "epoch": 18.93, + "learning_rate": 1.4822522417531794e-07, + "loss": 0.001, + "step": 61313 + }, + { + "epoch": 18.93, + "learning_rate": 1.481394471397024e-07, + "loss": 0.0023, + "step": 61314 + }, + { + "epoch": 18.94, + "learning_rate": 1.480536947453881e-07, + "loss": 0.0015, + "step": 61315 + }, + { + "epoch": 18.94, + "learning_rate": 1.479679669925882e-07, + "loss": 0.0022, + "step": 61316 + }, + { + "epoch": 18.94, + "learning_rate": 1.4788226388151693e-07, + "loss": 0.0014, + "step": 61317 + }, + { + "epoch": 18.94, + "learning_rate": 1.4779658541238973e-07, + "loss": 0.0013, + "step": 61318 + }, + { + "epoch": 18.94, + "learning_rate": 1.477109315854197e-07, + "loss": 0.002, + "step": 61319 + }, + { + "epoch": 18.94, + "learning_rate": 1.476253024008212e-07, + "loss": 0.0026, + "step": 61320 + }, + { + "epoch": 18.94, + "learning_rate": 1.475396978588095e-07, + "loss": 0.0015, + "step": 61321 + }, + { + "epoch": 18.94, + "learning_rate": 1.4745411795959785e-07, + "loss": 0.0019, + "step": 61322 + }, + { + "epoch": 18.94, + "learning_rate": 1.4736856270340049e-07, + "loss": 0.0019, + "step": 61323 + }, + { + "epoch": 18.94, + "learning_rate": 1.4728303209043172e-07, + "loss": 0.0016, + "step": 61324 + }, + { + "epoch": 18.94, + "learning_rate": 1.4719752612090466e-07, + "loss": 0.002, + "step": 61325 + }, + { + "epoch": 18.94, + "learning_rate": 1.4711204479503248e-07, + "loss": 0.0013, + "step": 61326 + }, + { + "epoch": 18.94, + "learning_rate": 1.4702658811303173e-07, + "loss": 0.0022, + "step": 61327 + }, + { + "epoch": 18.94, + "learning_rate": 1.4694115607511438e-07, + "loss": 0.0019, + "step": 61328 + }, + { + "epoch": 18.94, + "learning_rate": 1.4685574868149366e-07, + "loss": 0.0019, + "step": 61329 + }, + { + "epoch": 18.94, + "learning_rate": 1.4677036593238492e-07, + "loss": 0.0015, + "step": 61330 + }, + { + "epoch": 18.94, + "learning_rate": 1.466850078279991e-07, + "loss": 0.0017, + "step": 61331 + }, + { + "epoch": 18.94, + "learning_rate": 1.465996743685516e-07, + "loss": 0.002, + "step": 61332 + }, + { + "epoch": 18.94, + "learning_rate": 1.4651436555425557e-07, + "loss": 0.0013, + "step": 61333 + }, + { + "epoch": 18.94, + "learning_rate": 1.464290813853253e-07, + "loss": 0.0016, + "step": 61334 + }, + { + "epoch": 18.94, + "learning_rate": 1.463438218619717e-07, + "loss": 0.0016, + "step": 61335 + }, + { + "epoch": 18.94, + "learning_rate": 1.462585869844102e-07, + "loss": 0.0017, + "step": 61336 + }, + { + "epoch": 18.94, + "learning_rate": 1.4617337675285282e-07, + "loss": 0.0015, + "step": 61337 + }, + { + "epoch": 18.94, + "learning_rate": 1.460881911675127e-07, + "loss": 0.0018, + "step": 61338 + }, + { + "epoch": 18.94, + "learning_rate": 1.4600303022860418e-07, + "loss": 0.0016, + "step": 61339 + }, + { + "epoch": 18.94, + "learning_rate": 1.4591789393633926e-07, + "loss": 0.0016, + "step": 61340 + }, + { + "epoch": 18.94, + "learning_rate": 1.4583278229093002e-07, + "loss": 0.0015, + "step": 61341 + }, + { + "epoch": 18.94, + "learning_rate": 1.457476952925907e-07, + "loss": 0.0015, + "step": 61342 + }, + { + "epoch": 18.94, + "learning_rate": 1.456626329415345e-07, + "loss": 0.0019, + "step": 61343 + }, + { + "epoch": 18.94, + "learning_rate": 1.4557759523797231e-07, + "loss": 0.0022, + "step": 61344 + }, + { + "epoch": 18.94, + "learning_rate": 1.4549258218211847e-07, + "loss": 0.0013, + "step": 61345 + }, + { + "epoch": 18.94, + "learning_rate": 1.45407593774185e-07, + "loss": 0.0017, + "step": 61346 + }, + { + "epoch": 18.95, + "learning_rate": 1.4532263001438396e-07, + "loss": 0.0018, + "step": 61347 + }, + { + "epoch": 18.95, + "learning_rate": 1.452376909029285e-07, + "loss": 0.0018, + "step": 61348 + }, + { + "epoch": 18.95, + "learning_rate": 1.4515277644003177e-07, + "loss": 0.0021, + "step": 61349 + }, + { + "epoch": 18.95, + "learning_rate": 1.4506788662590477e-07, + "loss": 0.0018, + "step": 61350 + }, + { + "epoch": 18.95, + "learning_rate": 1.449830214607606e-07, + "loss": 0.0013, + "step": 61351 + }, + { + "epoch": 18.95, + "learning_rate": 1.4489818094481133e-07, + "loss": 0.0019, + "step": 61352 + }, + { + "epoch": 18.95, + "learning_rate": 1.4481336507826904e-07, + "loss": 0.0017, + "step": 61353 + }, + { + "epoch": 18.95, + "learning_rate": 1.4472857386134575e-07, + "loss": 0.0019, + "step": 61354 + }, + { + "epoch": 18.95, + "learning_rate": 1.4464380729425464e-07, + "loss": 0.0019, + "step": 61355 + }, + { + "epoch": 18.95, + "learning_rate": 1.4455906537720554e-07, + "loss": 0.0015, + "step": 61356 + }, + { + "epoch": 18.95, + "learning_rate": 1.4447434811041272e-07, + "loss": 0.002, + "step": 61357 + }, + { + "epoch": 18.95, + "learning_rate": 1.4438965549408713e-07, + "loss": 0.0013, + "step": 61358 + }, + { + "epoch": 18.95, + "learning_rate": 1.443049875284397e-07, + "loss": 0.0017, + "step": 61359 + }, + { + "epoch": 18.95, + "learning_rate": 1.4422034421368358e-07, + "loss": 0.0015, + "step": 61360 + }, + { + "epoch": 18.95, + "learning_rate": 1.4413572555003085e-07, + "loss": 0.0025, + "step": 61361 + }, + { + "epoch": 18.95, + "learning_rate": 1.4405113153769135e-07, + "loss": 0.0015, + "step": 61362 + }, + { + "epoch": 18.95, + "learning_rate": 1.439665621768771e-07, + "loss": 0.0018, + "step": 61363 + }, + { + "epoch": 18.95, + "learning_rate": 1.438820174678013e-07, + "loss": 0.0017, + "step": 61364 + }, + { + "epoch": 18.95, + "learning_rate": 1.4379749741067374e-07, + "loss": 0.0014, + "step": 61365 + }, + { + "epoch": 18.95, + "learning_rate": 1.4371300200570537e-07, + "loss": 0.0018, + "step": 61366 + }, + { + "epoch": 18.95, + "learning_rate": 1.436285312531105e-07, + "loss": 0.0016, + "step": 61367 + }, + { + "epoch": 18.95, + "learning_rate": 1.435440851530967e-07, + "loss": 0.0018, + "step": 61368 + }, + { + "epoch": 18.95, + "learning_rate": 1.4345966370587606e-07, + "loss": 0.0018, + "step": 61369 + }, + { + "epoch": 18.95, + "learning_rate": 1.4337526691166282e-07, + "loss": 0.0018, + "step": 61370 + }, + { + "epoch": 18.95, + "learning_rate": 1.432908947706646e-07, + "loss": 0.0014, + "step": 61371 + }, + { + "epoch": 18.95, + "learning_rate": 1.4320654728309346e-07, + "loss": 0.0017, + "step": 61372 + }, + { + "epoch": 18.95, + "learning_rate": 1.4312222444916145e-07, + "loss": 0.0012, + "step": 61373 + }, + { + "epoch": 18.95, + "learning_rate": 1.430379262690773e-07, + "loss": 0.0017, + "step": 61374 + }, + { + "epoch": 18.95, + "learning_rate": 1.4295365274305418e-07, + "loss": 0.0014, + "step": 61375 + }, + { + "epoch": 18.95, + "learning_rate": 1.4286940387130077e-07, + "loss": 0.0015, + "step": 61376 + }, + { + "epoch": 18.95, + "learning_rate": 1.4278517965402916e-07, + "loss": 0.0018, + "step": 61377 + }, + { + "epoch": 18.95, + "learning_rate": 1.4270098009144918e-07, + "loss": 0.0016, + "step": 61378 + }, + { + "epoch": 18.95, + "learning_rate": 1.4261680518377284e-07, + "loss": 0.0021, + "step": 61379 + }, + { + "epoch": 18.96, + "learning_rate": 1.4253265493120892e-07, + "loss": 0.0014, + "step": 61380 + }, + { + "epoch": 18.96, + "learning_rate": 1.4244852933396947e-07, + "loss": 0.0015, + "step": 61381 + }, + { + "epoch": 18.96, + "learning_rate": 1.4236442839226427e-07, + "loss": 0.002, + "step": 61382 + }, + { + "epoch": 18.96, + "learning_rate": 1.422803521063032e-07, + "loss": 0.0019, + "step": 61383 + }, + { + "epoch": 18.96, + "learning_rate": 1.4219630047629606e-07, + "loss": 0.0018, + "step": 61384 + }, + { + "epoch": 18.96, + "learning_rate": 1.4211227350245603e-07, + "loss": 0.0021, + "step": 61385 + }, + { + "epoch": 18.96, + "learning_rate": 1.4202827118498962e-07, + "loss": 0.0019, + "step": 61386 + }, + { + "epoch": 18.96, + "learning_rate": 1.4194429352410888e-07, + "loss": 0.0022, + "step": 61387 + }, + { + "epoch": 18.96, + "learning_rate": 1.418603405200225e-07, + "loss": 0.0011, + "step": 61388 + }, + { + "epoch": 18.96, + "learning_rate": 1.4177641217294258e-07, + "loss": 0.0015, + "step": 61389 + }, + { + "epoch": 18.96, + "learning_rate": 1.416925084830778e-07, + "loss": 0.0023, + "step": 61390 + }, + { + "epoch": 18.96, + "learning_rate": 1.4160862945063803e-07, + "loss": 0.0017, + "step": 61391 + }, + { + "epoch": 18.96, + "learning_rate": 1.4152477507583306e-07, + "loss": 0.0012, + "step": 61392 + }, + { + "epoch": 18.96, + "learning_rate": 1.4144094535887276e-07, + "loss": 0.0017, + "step": 61393 + }, + { + "epoch": 18.96, + "learning_rate": 1.4135714029996583e-07, + "loss": 0.0019, + "step": 61394 + }, + { + "epoch": 18.96, + "learning_rate": 1.4127335989932323e-07, + "loss": 0.0015, + "step": 61395 + }, + { + "epoch": 18.96, + "learning_rate": 1.4118960415715476e-07, + "loss": 0.0015, + "step": 61396 + }, + { + "epoch": 18.96, + "learning_rate": 1.411058730736692e-07, + "loss": 0.0019, + "step": 61397 + }, + { + "epoch": 18.96, + "learning_rate": 1.4102216664907632e-07, + "loss": 0.001, + "step": 61398 + }, + { + "epoch": 18.96, + "learning_rate": 1.4093848488358374e-07, + "loss": 0.0012, + "step": 61399 + }, + { + "epoch": 18.96, + "learning_rate": 1.4085482777740245e-07, + "loss": 0.0015, + "step": 61400 + }, + { + "epoch": 18.96, + "learning_rate": 1.4077119533074334e-07, + "loss": 0.0013, + "step": 61401 + }, + { + "epoch": 18.96, + "learning_rate": 1.4068758754381183e-07, + "loss": 0.002, + "step": 61402 + }, + { + "epoch": 18.96, + "learning_rate": 1.4060400441681887e-07, + "loss": 0.0016, + "step": 61403 + }, + { + "epoch": 18.96, + "learning_rate": 1.4052044594997428e-07, + "loss": 0.0013, + "step": 61404 + }, + { + "epoch": 18.96, + "learning_rate": 1.4043691214348566e-07, + "loss": 0.0014, + "step": 61405 + }, + { + "epoch": 18.96, + "learning_rate": 1.4035340299756284e-07, + "loss": 0.0016, + "step": 61406 + }, + { + "epoch": 18.96, + "learning_rate": 1.4026991851241456e-07, + "loss": 0.0023, + "step": 61407 + }, + { + "epoch": 18.96, + "learning_rate": 1.4018645868824953e-07, + "loss": 0.001, + "step": 61408 + }, + { + "epoch": 18.96, + "learning_rate": 1.401030235252765e-07, + "loss": 0.0014, + "step": 61409 + }, + { + "epoch": 18.96, + "learning_rate": 1.4001961302370414e-07, + "loss": 0.0019, + "step": 61410 + }, + { + "epoch": 18.96, + "learning_rate": 1.3993622718374232e-07, + "loss": 0.0024, + "step": 61411 + }, + { + "epoch": 18.97, + "learning_rate": 1.3985286600559644e-07, + "loss": 0.0024, + "step": 61412 + }, + { + "epoch": 18.97, + "learning_rate": 1.3976952948947742e-07, + "loss": 0.0014, + "step": 61413 + }, + { + "epoch": 18.97, + "learning_rate": 1.3968621763559287e-07, + "loss": 0.0013, + "step": 61414 + }, + { + "epoch": 18.97, + "learning_rate": 1.3960293044415263e-07, + "loss": 0.0011, + "step": 61415 + }, + { + "epoch": 18.97, + "learning_rate": 1.395196679153632e-07, + "loss": 0.0023, + "step": 61416 + }, + { + "epoch": 18.97, + "learning_rate": 1.394364300494333e-07, + "loss": 0.0012, + "step": 61417 + }, + { + "epoch": 18.97, + "learning_rate": 1.3935321684657166e-07, + "loss": 0.002, + "step": 61418 + }, + { + "epoch": 18.97, + "learning_rate": 1.392700283069859e-07, + "loss": 0.0018, + "step": 61419 + }, + { + "epoch": 18.97, + "learning_rate": 1.391868644308847e-07, + "loss": 0.0019, + "step": 61420 + }, + { + "epoch": 18.97, + "learning_rate": 1.391037252184757e-07, + "loss": 0.0021, + "step": 61421 + }, + { + "epoch": 18.97, + "learning_rate": 1.3902061066996653e-07, + "loss": 0.0014, + "step": 61422 + }, + { + "epoch": 18.97, + "learning_rate": 1.3893752078556477e-07, + "loss": 0.0018, + "step": 61423 + }, + { + "epoch": 18.97, + "learning_rate": 1.3885445556547916e-07, + "loss": 0.0016, + "step": 61424 + }, + { + "epoch": 18.97, + "learning_rate": 1.3877141500991732e-07, + "loss": 0.0016, + "step": 61425 + }, + { + "epoch": 18.97, + "learning_rate": 1.3868839911908682e-07, + "loss": 0.0017, + "step": 61426 + }, + { + "epoch": 18.97, + "learning_rate": 1.3860540789319533e-07, + "loss": 0.0019, + "step": 61427 + }, + { + "epoch": 18.97, + "learning_rate": 1.385224413324504e-07, + "loss": 0.0018, + "step": 61428 + }, + { + "epoch": 18.97, + "learning_rate": 1.384394994370597e-07, + "loss": 0.0016, + "step": 61429 + }, + { + "epoch": 18.97, + "learning_rate": 1.383565822072286e-07, + "loss": 0.0016, + "step": 61430 + }, + { + "epoch": 18.97, + "learning_rate": 1.3827368964316802e-07, + "loss": 0.0018, + "step": 61431 + }, + { + "epoch": 18.97, + "learning_rate": 1.3819082174508447e-07, + "loss": 0.0014, + "step": 61432 + }, + { + "epoch": 18.97, + "learning_rate": 1.3810797851318225e-07, + "loss": 0.0016, + "step": 61433 + }, + { + "epoch": 18.97, + "learning_rate": 1.380251599476712e-07, + "loss": 0.0012, + "step": 61434 + }, + { + "epoch": 18.97, + "learning_rate": 1.3794236604875888e-07, + "loss": 0.0015, + "step": 61435 + }, + { + "epoch": 18.97, + "learning_rate": 1.3785959681665073e-07, + "loss": 0.0017, + "step": 61436 + }, + { + "epoch": 18.97, + "learning_rate": 1.3777685225155436e-07, + "loss": 0.0019, + "step": 61437 + }, + { + "epoch": 18.97, + "learning_rate": 1.3769413235367735e-07, + "loss": 0.0018, + "step": 61438 + }, + { + "epoch": 18.97, + "learning_rate": 1.3761143712322622e-07, + "loss": 0.0014, + "step": 61439 + }, + { + "epoch": 18.97, + "learning_rate": 1.3752876656040638e-07, + "loss": 0.0022, + "step": 61440 + }, + { + "epoch": 18.97, + "learning_rate": 1.374461206654276e-07, + "loss": 0.0022, + "step": 61441 + }, + { + "epoch": 18.97, + "learning_rate": 1.3736349943849426e-07, + "loss": 0.0016, + "step": 61442 + }, + { + "epoch": 18.97, + "learning_rate": 1.3728090287981276e-07, + "loss": 0.0014, + "step": 61443 + }, + { + "epoch": 18.97, + "learning_rate": 1.3719833098959078e-07, + "loss": 0.0019, + "step": 61444 + }, + { + "epoch": 18.98, + "learning_rate": 1.371157837680359e-07, + "loss": 0.0015, + "step": 61445 + }, + { + "epoch": 18.98, + "learning_rate": 1.3703326121535244e-07, + "loss": 0.0014, + "step": 61446 + }, + { + "epoch": 18.98, + "learning_rate": 1.3695076333174795e-07, + "loss": 0.002, + "step": 61447 + }, + { + "epoch": 18.98, + "learning_rate": 1.3686829011742897e-07, + "loss": 0.0017, + "step": 61448 + }, + { + "epoch": 18.98, + "learning_rate": 1.3678584157259978e-07, + "loss": 0.0012, + "step": 61449 + }, + { + "epoch": 18.98, + "learning_rate": 1.367034176974691e-07, + "loss": 0.0013, + "step": 61450 + }, + { + "epoch": 18.98, + "learning_rate": 1.366210184922423e-07, + "loss": 0.0022, + "step": 61451 + }, + { + "epoch": 18.98, + "learning_rate": 1.365386439571259e-07, + "loss": 0.002, + "step": 61452 + }, + { + "epoch": 18.98, + "learning_rate": 1.364562940923231e-07, + "loss": 0.0019, + "step": 61453 + }, + { + "epoch": 18.98, + "learning_rate": 1.3637396889804478e-07, + "loss": 0.0013, + "step": 61454 + }, + { + "epoch": 18.98, + "learning_rate": 1.3629166837449193e-07, + "loss": 0.0017, + "step": 61455 + }, + { + "epoch": 18.98, + "learning_rate": 1.3620939252187327e-07, + "loss": 0.0017, + "step": 61456 + }, + { + "epoch": 18.98, + "learning_rate": 1.361271413403953e-07, + "loss": 0.0016, + "step": 61457 + }, + { + "epoch": 18.98, + "learning_rate": 1.3604491483026117e-07, + "loss": 0.0018, + "step": 61458 + }, + { + "epoch": 18.98, + "learning_rate": 1.359627129916785e-07, + "loss": 0.0022, + "step": 61459 + }, + { + "epoch": 18.98, + "learning_rate": 1.3588053582485162e-07, + "loss": 0.0015, + "step": 61460 + }, + { + "epoch": 18.98, + "learning_rate": 1.3579838332998585e-07, + "loss": 0.0021, + "step": 61461 + }, + { + "epoch": 18.98, + "learning_rate": 1.3571625550728885e-07, + "loss": 0.0022, + "step": 61462 + }, + { + "epoch": 18.98, + "learning_rate": 1.3563415235696486e-07, + "loss": 0.0015, + "step": 61463 + }, + { + "epoch": 18.98, + "learning_rate": 1.355520738792182e-07, + "loss": 0.0015, + "step": 61464 + }, + { + "epoch": 18.98, + "learning_rate": 1.3547002007425424e-07, + "loss": 0.002, + "step": 61465 + }, + { + "epoch": 18.98, + "learning_rate": 1.353879909422795e-07, + "loss": 0.0014, + "step": 61466 + }, + { + "epoch": 18.98, + "learning_rate": 1.3530598648349936e-07, + "loss": 0.0015, + "step": 61467 + }, + { + "epoch": 18.98, + "learning_rate": 1.3522400669811697e-07, + "loss": 0.0018, + "step": 61468 + }, + { + "epoch": 18.98, + "learning_rate": 1.3514205158633998e-07, + "loss": 0.0023, + "step": 61469 + }, + { + "epoch": 18.98, + "learning_rate": 1.350601211483704e-07, + "loss": 0.0015, + "step": 61470 + }, + { + "epoch": 18.98, + "learning_rate": 1.3497821538441592e-07, + "loss": 0.0018, + "step": 61471 + }, + { + "epoch": 18.98, + "learning_rate": 1.3489633429467963e-07, + "loss": 0.0014, + "step": 61472 + }, + { + "epoch": 18.98, + "learning_rate": 1.3481447787936696e-07, + "loss": 0.0015, + "step": 61473 + }, + { + "epoch": 18.98, + "learning_rate": 1.347326461386833e-07, + "loss": 0.0014, + "step": 61474 + }, + { + "epoch": 18.98, + "learning_rate": 1.3465083907283073e-07, + "loss": 0.0017, + "step": 61475 + }, + { + "epoch": 18.98, + "learning_rate": 1.3456905668201792e-07, + "loss": 0.002, + "step": 61476 + }, + { + "epoch": 18.99, + "learning_rate": 1.3448729896644585e-07, + "loss": 0.0021, + "step": 61477 + }, + { + "epoch": 18.99, + "learning_rate": 1.3440556592632103e-07, + "loss": 0.002, + "step": 61478 + }, + { + "epoch": 18.99, + "learning_rate": 1.3432385756184774e-07, + "loss": 0.0016, + "step": 61479 + }, + { + "epoch": 18.99, + "learning_rate": 1.3424217387322803e-07, + "loss": 0.0012, + "step": 61480 + }, + { + "epoch": 18.99, + "learning_rate": 1.341605148606695e-07, + "loss": 0.0021, + "step": 61481 + }, + { + "epoch": 18.99, + "learning_rate": 1.3407888052437423e-07, + "loss": 0.002, + "step": 61482 + }, + { + "epoch": 18.99, + "learning_rate": 1.3399727086454872e-07, + "loss": 0.0014, + "step": 61483 + }, + { + "epoch": 18.99, + "learning_rate": 1.339156858813939e-07, + "loss": 0.0014, + "step": 61484 + }, + { + "epoch": 18.99, + "learning_rate": 1.338341255751152e-07, + "loss": 0.0017, + "step": 61485 + }, + { + "epoch": 18.99, + "learning_rate": 1.33752589945918e-07, + "loss": 0.0016, + "step": 61486 + }, + { + "epoch": 18.99, + "learning_rate": 1.3367107899400322e-07, + "loss": 0.0013, + "step": 61487 + }, + { + "epoch": 18.99, + "learning_rate": 1.335895927195785e-07, + "loss": 0.0023, + "step": 61488 + }, + { + "epoch": 18.99, + "learning_rate": 1.3350813112284588e-07, + "loss": 0.0016, + "step": 61489 + }, + { + "epoch": 18.99, + "learning_rate": 1.3342669420400746e-07, + "loss": 0.0032, + "step": 61490 + }, + { + "epoch": 18.99, + "learning_rate": 1.3334528196326968e-07, + "loss": 0.0021, + "step": 61491 + }, + { + "epoch": 18.99, + "learning_rate": 1.3326389440083355e-07, + "loss": 0.0023, + "step": 61492 + }, + { + "epoch": 18.99, + "learning_rate": 1.331825315169055e-07, + "loss": 0.0014, + "step": 61493 + }, + { + "epoch": 18.99, + "learning_rate": 1.3310119331168659e-07, + "loss": 0.0018, + "step": 61494 + }, + { + "epoch": 18.99, + "learning_rate": 1.33019879785381e-07, + "loss": 0.0016, + "step": 61495 + }, + { + "epoch": 18.99, + "learning_rate": 1.3293859093819306e-07, + "loss": 0.002, + "step": 61496 + }, + { + "epoch": 18.99, + "learning_rate": 1.3285732677032482e-07, + "loss": 0.0018, + "step": 61497 + }, + { + "epoch": 18.99, + "learning_rate": 1.3277608728198055e-07, + "loss": 0.001, + "step": 61498 + }, + { + "epoch": 18.99, + "learning_rate": 1.3269487247336232e-07, + "loss": 0.0018, + "step": 61499 + }, + { + "epoch": 18.99, + "learning_rate": 1.3261368234467442e-07, + "loss": 0.0017, + "step": 61500 + }, + { + "epoch": 18.99, + "learning_rate": 1.325325168961189e-07, + "loss": 0.0011, + "step": 61501 + }, + { + "epoch": 18.99, + "learning_rate": 1.3245137612790006e-07, + "loss": 0.0018, + "step": 61502 + }, + { + "epoch": 18.99, + "learning_rate": 1.323702600402199e-07, + "loss": 0.0017, + "step": 61503 + }, + { + "epoch": 18.99, + "learning_rate": 1.3228916863328167e-07, + "loss": 0.0017, + "step": 61504 + }, + { + "epoch": 18.99, + "learning_rate": 1.3220810190728628e-07, + "loss": 0.0013, + "step": 61505 + }, + { + "epoch": 18.99, + "learning_rate": 1.3212705986243913e-07, + "loss": 0.0018, + "step": 61506 + }, + { + "epoch": 18.99, + "learning_rate": 1.3204604249894336e-07, + "loss": 0.0025, + "step": 61507 + }, + { + "epoch": 18.99, + "learning_rate": 1.3196504981699888e-07, + "loss": 0.0017, + "step": 61508 + }, + { + "epoch": 19.0, + "learning_rate": 1.318840818168099e-07, + "loss": 0.002, + "step": 61509 + }, + { + "epoch": 19.0, + "learning_rate": 1.318031384985785e-07, + "loss": 0.0016, + "step": 61510 + }, + { + "epoch": 19.0, + "learning_rate": 1.317222198625079e-07, + "loss": 0.0016, + "step": 61511 + }, + { + "epoch": 19.0, + "learning_rate": 1.3164132590879896e-07, + "loss": 0.0016, + "step": 61512 + }, + { + "epoch": 19.0, + "learning_rate": 1.3156045663765605e-07, + "loss": 0.0018, + "step": 61513 + }, + { + "epoch": 19.0, + "learning_rate": 1.3147961204928006e-07, + "loss": 0.0017, + "step": 61514 + }, + { + "epoch": 19.0, + "learning_rate": 1.3139879214387197e-07, + "loss": 0.0014, + "step": 61515 + }, + { + "epoch": 19.0, + "learning_rate": 1.3131799692163717e-07, + "loss": 0.0019, + "step": 61516 + }, + { + "epoch": 19.0, + "learning_rate": 1.3123722638277548e-07, + "loss": 0.0017, + "step": 61517 + }, + { + "epoch": 19.0, + "learning_rate": 1.3115648052748898e-07, + "loss": 0.001, + "step": 61518 + }, + { + "epoch": 19.0, + "learning_rate": 1.3107575935598082e-07, + "loss": 0.0019, + "step": 61519 + }, + { + "epoch": 19.0, + "learning_rate": 1.3099506286845198e-07, + "loss": 0.0018, + "step": 61520 + }, + { + "epoch": 19.0, + "learning_rate": 1.309143910651034e-07, + "loss": 0.002, + "step": 61521 + }, + { + "epoch": 19.0, + "learning_rate": 1.3083374394613934e-07, + "loss": 0.0015, + "step": 61522 + }, + { + "epoch": 19.0, + "learning_rate": 1.3075312151175967e-07, + "loss": 0.0017, + "step": 61523 + }, + { + "epoch": 19.0, + "learning_rate": 1.3067252376216643e-07, + "loss": 0.0017, + "step": 61524 + }, + { + "epoch": 19.0, + "learning_rate": 1.305919506975617e-07, + "loss": 0.0015, + "step": 61525 + }, + { + "epoch": 19.0, + "learning_rate": 1.305114023181453e-07, + "loss": 0.0011, + "step": 61526 + }, + { + "epoch": 19.0, + "learning_rate": 1.3043087862412042e-07, + "loss": 0.0013, + "step": 61527 + }, + { + "epoch": 19.0, + "learning_rate": 1.3035037961568908e-07, + "loss": 0.0024, + "step": 61528 + }, + { + "epoch": 19.0, + "learning_rate": 1.3026990529305007e-07, + "loss": 0.0011, + "step": 61529 + }, + { + "epoch": 19.0, + "learning_rate": 1.301894556564076e-07, + "loss": 0.0009, + "step": 61530 + }, + { + "epoch": 19.0, + "learning_rate": 1.301090307059616e-07, + "loss": 0.0019, + "step": 61531 + }, + { + "epoch": 19.0, + "learning_rate": 1.3002863044191182e-07, + "loss": 0.0021, + "step": 61532 + }, + { + "epoch": 19.0, + "learning_rate": 1.299482548644604e-07, + "loss": 0.0013, + "step": 61533 + }, + { + "epoch": 19.0, + "learning_rate": 1.2986790397380932e-07, + "loss": 0.0016, + "step": 61534 + }, + { + "epoch": 19.0, + "learning_rate": 1.297875777701596e-07, + "loss": 0.0015, + "step": 61535 + }, + { + "epoch": 19.0, + "learning_rate": 1.2970727625370993e-07, + "loss": 0.0016, + "step": 61536 + }, + { + "epoch": 19.0, + "learning_rate": 1.296269994246635e-07, + "loss": 0.0025, + "step": 61537 + }, + { + "epoch": 19.0, + "learning_rate": 1.2954674728321904e-07, + "loss": 0.0016, + "step": 61538 + }, + { + "epoch": 19.0, + "learning_rate": 1.294665198295786e-07, + "loss": 0.0012, + "step": 61539 + }, + { + "epoch": 19.0, + "learning_rate": 1.2938631706394421e-07, + "loss": 0.0014, + "step": 61540 + }, + { + "epoch": 19.0, + "learning_rate": 1.2930613898651466e-07, + "loss": 0.0017, + "step": 61541 + }, + { + "epoch": 19.01, + "learning_rate": 1.2922598559748978e-07, + "loss": 0.0012, + "step": 61542 + }, + { + "epoch": 19.01, + "learning_rate": 1.2914585689707048e-07, + "loss": 0.0015, + "step": 61543 + }, + { + "epoch": 19.01, + "learning_rate": 1.2906575288545886e-07, + "loss": 0.0021, + "step": 61544 + }, + { + "epoch": 19.01, + "learning_rate": 1.2898567356285474e-07, + "loss": 0.0012, + "step": 61545 + }, + { + "epoch": 19.01, + "learning_rate": 1.2890561892945573e-07, + "loss": 0.0013, + "step": 61546 + }, + { + "epoch": 19.01, + "learning_rate": 1.2882558898546614e-07, + "loss": 0.0015, + "step": 61547 + }, + { + "epoch": 19.01, + "learning_rate": 1.2874558373108248e-07, + "loss": 0.0016, + "step": 61548 + }, + { + "epoch": 19.01, + "learning_rate": 1.286656031665079e-07, + "loss": 0.0012, + "step": 61549 + }, + { + "epoch": 19.01, + "learning_rate": 1.2858564729194113e-07, + "loss": 0.0012, + "step": 61550 + }, + { + "epoch": 19.01, + "learning_rate": 1.285057161075809e-07, + "loss": 0.0015, + "step": 61551 + }, + { + "epoch": 19.01, + "learning_rate": 1.2842580961362927e-07, + "loss": 0.0019, + "step": 61552 + }, + { + "epoch": 19.01, + "learning_rate": 1.2834592781028498e-07, + "loss": 0.0012, + "step": 61553 + }, + { + "epoch": 19.01, + "learning_rate": 1.2826607069774676e-07, + "loss": 0.0018, + "step": 61554 + }, + { + "epoch": 19.01, + "learning_rate": 1.2818623827621779e-07, + "loss": 0.0012, + "step": 61555 + }, + { + "epoch": 19.01, + "learning_rate": 1.2810643054589454e-07, + "loss": 0.0016, + "step": 61556 + }, + { + "epoch": 19.01, + "learning_rate": 1.280266475069769e-07, + "loss": 0.001, + "step": 61557 + }, + { + "epoch": 19.01, + "learning_rate": 1.279468891596658e-07, + "loss": 0.0013, + "step": 61558 + }, + { + "epoch": 19.01, + "learning_rate": 1.2786715550415996e-07, + "loss": 0.0015, + "step": 61559 + }, + { + "epoch": 19.01, + "learning_rate": 1.2778744654065923e-07, + "loss": 0.0013, + "step": 61560 + }, + { + "epoch": 19.01, + "learning_rate": 1.2770776226936233e-07, + "loss": 0.0011, + "step": 61561 + }, + { + "epoch": 19.01, + "learning_rate": 1.276281026904691e-07, + "loss": 0.0013, + "step": 61562 + }, + { + "epoch": 19.01, + "learning_rate": 1.275484678041783e-07, + "loss": 0.0011, + "step": 61563 + }, + { + "epoch": 19.01, + "learning_rate": 1.274688576106897e-07, + "loss": 0.0016, + "step": 61564 + }, + { + "epoch": 19.01, + "learning_rate": 1.2738927211020212e-07, + "loss": 0.0019, + "step": 61565 + }, + { + "epoch": 19.01, + "learning_rate": 1.2730971130291537e-07, + "loss": 0.0014, + "step": 61566 + }, + { + "epoch": 19.01, + "learning_rate": 1.2723017518902592e-07, + "loss": 0.0016, + "step": 61567 + }, + { + "epoch": 19.01, + "learning_rate": 1.2715066376873586e-07, + "loss": 0.0018, + "step": 61568 + }, + { + "epoch": 19.01, + "learning_rate": 1.270711770422417e-07, + "loss": 0.0012, + "step": 61569 + }, + { + "epoch": 19.01, + "learning_rate": 1.2699171500974437e-07, + "loss": 0.0014, + "step": 61570 + }, + { + "epoch": 19.01, + "learning_rate": 1.2691227767144044e-07, + "loss": 0.0014, + "step": 61571 + }, + { + "epoch": 19.01, + "learning_rate": 1.268328650275308e-07, + "loss": 0.0014, + "step": 61572 + }, + { + "epoch": 19.01, + "learning_rate": 1.2675347707821196e-07, + "loss": 0.0012, + "step": 61573 + }, + { + "epoch": 19.02, + "learning_rate": 1.2667411382368266e-07, + "loss": 0.0012, + "step": 61574 + }, + { + "epoch": 19.02, + "learning_rate": 1.2659477526414387e-07, + "loss": 0.0014, + "step": 61575 + }, + { + "epoch": 19.02, + "learning_rate": 1.2651546139979208e-07, + "loss": 0.0013, + "step": 61576 + }, + { + "epoch": 19.02, + "learning_rate": 1.2643617223082495e-07, + "loss": 0.001, + "step": 61577 + }, + { + "epoch": 19.02, + "learning_rate": 1.2635690775744336e-07, + "loss": 0.0013, + "step": 61578 + }, + { + "epoch": 19.02, + "learning_rate": 1.2627766797984276e-07, + "loss": 0.0016, + "step": 61579 + }, + { + "epoch": 19.02, + "learning_rate": 1.2619845289822296e-07, + "loss": 0.0017, + "step": 61580 + }, + { + "epoch": 19.02, + "learning_rate": 1.2611926251278161e-07, + "loss": 0.0024, + "step": 61581 + }, + { + "epoch": 19.02, + "learning_rate": 1.2604009682371631e-07, + "loss": 0.0016, + "step": 61582 + }, + { + "epoch": 19.02, + "learning_rate": 1.259609558312258e-07, + "loss": 0.0016, + "step": 61583 + }, + { + "epoch": 19.02, + "learning_rate": 1.258818395355088e-07, + "loss": 0.0013, + "step": 61584 + }, + { + "epoch": 19.02, + "learning_rate": 1.2580274793676183e-07, + "loss": 0.0019, + "step": 61585 + }, + { + "epoch": 19.02, + "learning_rate": 1.2572368103518252e-07, + "loss": 0.0012, + "step": 61586 + }, + { + "epoch": 19.02, + "learning_rate": 1.2564463883097066e-07, + "loss": 0.0013, + "step": 61587 + }, + { + "epoch": 19.02, + "learning_rate": 1.255656213243206e-07, + "loss": 0.0019, + "step": 61588 + }, + { + "epoch": 19.02, + "learning_rate": 1.2548662851543214e-07, + "loss": 0.0014, + "step": 61589 + }, + { + "epoch": 19.02, + "learning_rate": 1.2540766040450402e-07, + "loss": 0.0012, + "step": 61590 + }, + { + "epoch": 19.02, + "learning_rate": 1.2532871699173166e-07, + "loss": 0.0018, + "step": 61591 + }, + { + "epoch": 19.02, + "learning_rate": 1.2524979827731376e-07, + "loss": 0.0016, + "step": 61592 + }, + { + "epoch": 19.02, + "learning_rate": 1.2517090426144686e-07, + "loss": 0.0014, + "step": 61593 + }, + { + "epoch": 19.02, + "learning_rate": 1.2509203494432742e-07, + "loss": 0.0016, + "step": 61594 + }, + { + "epoch": 19.02, + "learning_rate": 1.2501319032615423e-07, + "loss": 0.0017, + "step": 61595 + }, + { + "epoch": 19.02, + "learning_rate": 1.2493437040712487e-07, + "loss": 0.0012, + "step": 61596 + }, + { + "epoch": 19.02, + "learning_rate": 1.2485557518743697e-07, + "loss": 0.0015, + "step": 61597 + }, + { + "epoch": 19.02, + "learning_rate": 1.247768046672837e-07, + "loss": 0.0027, + "step": 61598 + }, + { + "epoch": 19.02, + "learning_rate": 1.2469805884686714e-07, + "loss": 0.002, + "step": 61599 + }, + { + "epoch": 19.02, + "learning_rate": 1.2461933772638045e-07, + "loss": 0.0014, + "step": 61600 + }, + { + "epoch": 19.02, + "learning_rate": 1.245406413060224e-07, + "loss": 0.0015, + "step": 61601 + }, + { + "epoch": 19.02, + "learning_rate": 1.2446196958598945e-07, + "loss": 0.0014, + "step": 61602 + }, + { + "epoch": 19.02, + "learning_rate": 1.2438332256647812e-07, + "loss": 0.0013, + "step": 61603 + }, + { + "epoch": 19.02, + "learning_rate": 1.2430470024768492e-07, + "loss": 0.0014, + "step": 61604 + }, + { + "epoch": 19.02, + "learning_rate": 1.242261026298064e-07, + "loss": 0.0013, + "step": 61605 + }, + { + "epoch": 19.03, + "learning_rate": 1.2414752971304122e-07, + "loss": 0.0017, + "step": 61606 + }, + { + "epoch": 19.03, + "learning_rate": 1.2406898149758374e-07, + "loss": 0.0012, + "step": 61607 + }, + { + "epoch": 19.03, + "learning_rate": 1.239904579836304e-07, + "loss": 0.0019, + "step": 61608 + }, + { + "epoch": 19.03, + "learning_rate": 1.239119591713789e-07, + "loss": 0.002, + "step": 61609 + }, + { + "epoch": 19.03, + "learning_rate": 1.2383348506102455e-07, + "loss": 0.0012, + "step": 61610 + }, + { + "epoch": 19.03, + "learning_rate": 1.237550356527639e-07, + "loss": 0.0018, + "step": 61611 + }, + { + "epoch": 19.03, + "learning_rate": 1.2367661094679351e-07, + "loss": 0.0015, + "step": 61612 + }, + { + "epoch": 19.03, + "learning_rate": 1.235982109433087e-07, + "loss": 0.0017, + "step": 61613 + }, + { + "epoch": 19.03, + "learning_rate": 1.2351983564250604e-07, + "loss": 0.0019, + "step": 61614 + }, + { + "epoch": 19.03, + "learning_rate": 1.234414850445831e-07, + "loss": 0.0013, + "step": 61615 + }, + { + "epoch": 19.03, + "learning_rate": 1.2336315914973307e-07, + "loss": 0.0016, + "step": 61616 + }, + { + "epoch": 19.03, + "learning_rate": 1.232848579581536e-07, + "loss": 0.0011, + "step": 61617 + }, + { + "epoch": 19.03, + "learning_rate": 1.2320658147004006e-07, + "loss": 0.0016, + "step": 61618 + }, + { + "epoch": 19.03, + "learning_rate": 1.2312832968558785e-07, + "loss": 0.0016, + "step": 61619 + }, + { + "epoch": 19.03, + "learning_rate": 1.230501026049935e-07, + "loss": 0.0017, + "step": 61620 + }, + { + "epoch": 19.03, + "learning_rate": 1.229719002284524e-07, + "loss": 0.001, + "step": 61621 + }, + { + "epoch": 19.03, + "learning_rate": 1.2289372255615994e-07, + "loss": 0.0017, + "step": 61622 + }, + { + "epoch": 19.03, + "learning_rate": 1.2281556958831153e-07, + "loss": 0.0014, + "step": 61623 + }, + { + "epoch": 19.03, + "learning_rate": 1.2273744132510258e-07, + "loss": 0.0019, + "step": 61624 + }, + { + "epoch": 19.03, + "learning_rate": 1.2265933776672956e-07, + "loss": 0.0015, + "step": 61625 + }, + { + "epoch": 19.03, + "learning_rate": 1.2258125891338568e-07, + "loss": 0.0016, + "step": 61626 + }, + { + "epoch": 19.03, + "learning_rate": 1.2250320476526967e-07, + "loss": 0.0016, + "step": 61627 + }, + { + "epoch": 19.03, + "learning_rate": 1.2242517532257358e-07, + "loss": 0.0014, + "step": 61628 + }, + { + "epoch": 19.03, + "learning_rate": 1.2234717058549285e-07, + "loss": 0.0012, + "step": 61629 + }, + { + "epoch": 19.03, + "learning_rate": 1.2226919055422503e-07, + "loss": 0.0014, + "step": 61630 + }, + { + "epoch": 19.03, + "learning_rate": 1.2219123522896226e-07, + "loss": 0.0014, + "step": 61631 + }, + { + "epoch": 19.03, + "learning_rate": 1.2211330460990212e-07, + "loss": 0.0018, + "step": 61632 + }, + { + "epoch": 19.03, + "learning_rate": 1.220353986972378e-07, + "loss": 0.0012, + "step": 61633 + }, + { + "epoch": 19.03, + "learning_rate": 1.2195751749116358e-07, + "loss": 0.0015, + "step": 61634 + }, + { + "epoch": 19.03, + "learning_rate": 1.21879660991876e-07, + "loss": 0.0018, + "step": 61635 + }, + { + "epoch": 19.03, + "learning_rate": 1.2180182919956817e-07, + "loss": 0.0016, + "step": 61636 + }, + { + "epoch": 19.03, + "learning_rate": 1.2172402211443668e-07, + "loss": 0.0017, + "step": 61637 + }, + { + "epoch": 19.03, + "learning_rate": 1.2164623973667577e-07, + "loss": 0.0017, + "step": 61638 + }, + { + "epoch": 19.04, + "learning_rate": 1.2156848206647752e-07, + "loss": 0.0013, + "step": 61639 + }, + { + "epoch": 19.04, + "learning_rate": 1.2149074910403958e-07, + "loss": 0.0013, + "step": 61640 + }, + { + "epoch": 19.04, + "learning_rate": 1.2141304084955397e-07, + "loss": 0.0012, + "step": 61641 + }, + { + "epoch": 19.04, + "learning_rate": 1.2133535730321722e-07, + "loss": 0.0019, + "step": 61642 + }, + { + "epoch": 19.04, + "learning_rate": 1.212576984652225e-07, + "loss": 0.0014, + "step": 61643 + }, + { + "epoch": 19.04, + "learning_rate": 1.21180064335763e-07, + "loss": 0.0015, + "step": 61644 + }, + { + "epoch": 19.04, + "learning_rate": 1.2110245491503413e-07, + "loss": 0.0017, + "step": 61645 + }, + { + "epoch": 19.04, + "learning_rate": 1.2102487020323017e-07, + "loss": 0.0014, + "step": 61646 + }, + { + "epoch": 19.04, + "learning_rate": 1.2094731020054428e-07, + "loss": 0.0016, + "step": 61647 + }, + { + "epoch": 19.04, + "learning_rate": 1.2086977490717189e-07, + "loss": 0.0015, + "step": 61648 + }, + { + "epoch": 19.04, + "learning_rate": 1.2079226432330614e-07, + "loss": 0.0015, + "step": 61649 + }, + { + "epoch": 19.04, + "learning_rate": 1.2071477844913914e-07, + "loss": 0.0015, + "step": 61650 + }, + { + "epoch": 19.04, + "learning_rate": 1.2063731728486738e-07, + "loss": 0.0016, + "step": 61651 + }, + { + "epoch": 19.04, + "learning_rate": 1.2055988083068405e-07, + "loss": 0.0019, + "step": 61652 + }, + { + "epoch": 19.04, + "learning_rate": 1.204824690867823e-07, + "loss": 0.0018, + "step": 61653 + }, + { + "epoch": 19.04, + "learning_rate": 1.2040508205335532e-07, + "loss": 0.0017, + "step": 61654 + }, + { + "epoch": 19.04, + "learning_rate": 1.2032771973059742e-07, + "loss": 0.0015, + "step": 61655 + }, + { + "epoch": 19.04, + "learning_rate": 1.2025038211870065e-07, + "loss": 0.0018, + "step": 61656 + }, + { + "epoch": 19.04, + "learning_rate": 1.2017306921786043e-07, + "loss": 0.0014, + "step": 61657 + }, + { + "epoch": 19.04, + "learning_rate": 1.2009578102827101e-07, + "loss": 0.0013, + "step": 61658 + }, + { + "epoch": 19.04, + "learning_rate": 1.2001851755012228e-07, + "loss": 0.0013, + "step": 61659 + }, + { + "epoch": 19.04, + "learning_rate": 1.199412787836085e-07, + "loss": 0.0015, + "step": 61660 + }, + { + "epoch": 19.04, + "learning_rate": 1.198640647289251e-07, + "loss": 0.0018, + "step": 61661 + }, + { + "epoch": 19.04, + "learning_rate": 1.19786875386263e-07, + "loss": 0.0014, + "step": 61662 + }, + { + "epoch": 19.04, + "learning_rate": 1.197097107558165e-07, + "loss": 0.0014, + "step": 61663 + }, + { + "epoch": 19.04, + "learning_rate": 1.196325708377788e-07, + "loss": 0.0014, + "step": 61664 + }, + { + "epoch": 19.04, + "learning_rate": 1.1955545563234082e-07, + "loss": 0.0017, + "step": 61665 + }, + { + "epoch": 19.04, + "learning_rate": 1.194783651396958e-07, + "loss": 0.0013, + "step": 61666 + }, + { + "epoch": 19.04, + "learning_rate": 1.1940129936003908e-07, + "loss": 0.0013, + "step": 61667 + }, + { + "epoch": 19.04, + "learning_rate": 1.1932425829356163e-07, + "loss": 0.0017, + "step": 61668 + }, + { + "epoch": 19.04, + "learning_rate": 1.1924724194045556e-07, + "loss": 0.0015, + "step": 61669 + }, + { + "epoch": 19.04, + "learning_rate": 1.1917025030091512e-07, + "loss": 0.0013, + "step": 61670 + }, + { + "epoch": 19.05, + "learning_rate": 1.1909328337513238e-07, + "loss": 0.0015, + "step": 61671 + }, + { + "epoch": 19.05, + "learning_rate": 1.190163411632983e-07, + "loss": 0.0013, + "step": 61672 + }, + { + "epoch": 19.05, + "learning_rate": 1.1893942366560718e-07, + "loss": 0.0013, + "step": 61673 + }, + { + "epoch": 19.05, + "learning_rate": 1.1886253088225108e-07, + "loss": 0.0021, + "step": 61674 + }, + { + "epoch": 19.05, + "learning_rate": 1.1878566281342097e-07, + "loss": 0.0016, + "step": 61675 + }, + { + "epoch": 19.05, + "learning_rate": 1.1870881945931001e-07, + "loss": 0.0016, + "step": 61676 + }, + { + "epoch": 19.05, + "learning_rate": 1.186320008201125e-07, + "loss": 0.0012, + "step": 61677 + }, + { + "epoch": 19.05, + "learning_rate": 1.1855520689601718e-07, + "loss": 0.0013, + "step": 61678 + }, + { + "epoch": 19.05, + "learning_rate": 1.1847843768721723e-07, + "loss": 0.0015, + "step": 61679 + }, + { + "epoch": 19.05, + "learning_rate": 1.1840169319390581e-07, + "loss": 0.0014, + "step": 61680 + }, + { + "epoch": 19.05, + "learning_rate": 1.1832497341627391e-07, + "loss": 0.0012, + "step": 61681 + }, + { + "epoch": 19.05, + "learning_rate": 1.1824827835451248e-07, + "loss": 0.0015, + "step": 61682 + }, + { + "epoch": 19.05, + "learning_rate": 1.1817160800881578e-07, + "loss": 0.0019, + "step": 61683 + }, + { + "epoch": 19.05, + "learning_rate": 1.1809496237937368e-07, + "loss": 0.0012, + "step": 61684 + }, + { + "epoch": 19.05, + "learning_rate": 1.1801834146637824e-07, + "loss": 0.0014, + "step": 61685 + }, + { + "epoch": 19.05, + "learning_rate": 1.1794174527002267e-07, + "loss": 0.0016, + "step": 61686 + }, + { + "epoch": 19.05, + "learning_rate": 1.1786517379049566e-07, + "loss": 0.0013, + "step": 61687 + }, + { + "epoch": 19.05, + "learning_rate": 1.1778862702799044e-07, + "loss": 0.0016, + "step": 61688 + }, + { + "epoch": 19.05, + "learning_rate": 1.1771210498269902e-07, + "loss": 0.0016, + "step": 61689 + }, + { + "epoch": 19.05, + "learning_rate": 1.176356076548113e-07, + "loss": 0.0019, + "step": 61690 + }, + { + "epoch": 19.05, + "learning_rate": 1.1755913504451932e-07, + "loss": 0.001, + "step": 61691 + }, + { + "epoch": 19.05, + "learning_rate": 1.1748268715201516e-07, + "loss": 0.0019, + "step": 61692 + }, + { + "epoch": 19.05, + "learning_rate": 1.1740626397748755e-07, + "loss": 0.0014, + "step": 61693 + }, + { + "epoch": 19.05, + "learning_rate": 1.1732986552113079e-07, + "loss": 0.0015, + "step": 61694 + }, + { + "epoch": 19.05, + "learning_rate": 1.1725349178313472e-07, + "loss": 0.0016, + "step": 61695 + }, + { + "epoch": 19.05, + "learning_rate": 1.1717714276368918e-07, + "loss": 0.0008, + "step": 61696 + }, + { + "epoch": 19.05, + "learning_rate": 1.1710081846298626e-07, + "loss": 0.0011, + "step": 61697 + }, + { + "epoch": 19.05, + "learning_rate": 1.1702451888121802e-07, + "loss": 0.0012, + "step": 61698 + }, + { + "epoch": 19.05, + "learning_rate": 1.1694824401857319e-07, + "loss": 0.0016, + "step": 61699 + }, + { + "epoch": 19.05, + "learning_rate": 1.1687199387524273e-07, + "loss": 0.0014, + "step": 61700 + }, + { + "epoch": 19.05, + "learning_rate": 1.167957684514187e-07, + "loss": 0.0014, + "step": 61701 + }, + { + "epoch": 19.05, + "learning_rate": 1.1671956774729099e-07, + "loss": 0.0015, + "step": 61702 + }, + { + "epoch": 19.05, + "learning_rate": 1.166433917630494e-07, + "loss": 0.0013, + "step": 61703 + }, + { + "epoch": 19.06, + "learning_rate": 1.1656724049888602e-07, + "loss": 0.0018, + "step": 61704 + }, + { + "epoch": 19.06, + "learning_rate": 1.1649111395499069e-07, + "loss": 0.0013, + "step": 61705 + }, + { + "epoch": 19.06, + "learning_rate": 1.1641501213155326e-07, + "loss": 0.0014, + "step": 61706 + }, + { + "epoch": 19.06, + "learning_rate": 1.1633893502876469e-07, + "loss": 0.0017, + "step": 61707 + }, + { + "epoch": 19.06, + "learning_rate": 1.1626288264681595e-07, + "loss": 0.0017, + "step": 61708 + }, + { + "epoch": 19.06, + "learning_rate": 1.1618685498589577e-07, + "loss": 0.001, + "step": 61709 + }, + { + "epoch": 19.06, + "learning_rate": 1.161108520461951e-07, + "loss": 0.0013, + "step": 61710 + }, + { + "epoch": 19.06, + "learning_rate": 1.1603487382790379e-07, + "loss": 0.0014, + "step": 61711 + }, + { + "epoch": 19.06, + "learning_rate": 1.159589203312117e-07, + "loss": 0.0019, + "step": 61712 + }, + { + "epoch": 19.06, + "learning_rate": 1.1588299155630866e-07, + "loss": 0.0012, + "step": 61713 + }, + { + "epoch": 19.06, + "learning_rate": 1.1580708750338677e-07, + "loss": 0.0019, + "step": 61714 + }, + { + "epoch": 19.06, + "learning_rate": 1.1573120817263251e-07, + "loss": 0.0012, + "step": 61715 + }, + { + "epoch": 19.06, + "learning_rate": 1.1565535356423796e-07, + "loss": 0.0014, + "step": 61716 + }, + { + "epoch": 19.06, + "learning_rate": 1.1557952367839187e-07, + "loss": 0.0015, + "step": 61717 + }, + { + "epoch": 19.06, + "learning_rate": 1.1550371851528409e-07, + "loss": 0.0013, + "step": 61718 + }, + { + "epoch": 19.06, + "learning_rate": 1.1542793807510445e-07, + "loss": 0.0011, + "step": 61719 + }, + { + "epoch": 19.06, + "learning_rate": 1.153521823580428e-07, + "loss": 0.0012, + "step": 61720 + }, + { + "epoch": 19.06, + "learning_rate": 1.152764513642879e-07, + "loss": 0.0016, + "step": 61721 + }, + { + "epoch": 19.06, + "learning_rate": 1.1520074509402957e-07, + "loss": 0.0012, + "step": 61722 + }, + { + "epoch": 19.06, + "learning_rate": 1.1512506354745656e-07, + "loss": 0.0015, + "step": 61723 + }, + { + "epoch": 19.06, + "learning_rate": 1.1504940672475873e-07, + "loss": 0.0022, + "step": 61724 + }, + { + "epoch": 19.06, + "learning_rate": 1.1497377462612592e-07, + "loss": 0.0022, + "step": 61725 + }, + { + "epoch": 19.06, + "learning_rate": 1.1489816725174685e-07, + "loss": 0.0017, + "step": 61726 + }, + { + "epoch": 19.06, + "learning_rate": 1.1482258460180917e-07, + "loss": 0.0014, + "step": 61727 + }, + { + "epoch": 19.06, + "learning_rate": 1.1474702667650383e-07, + "loss": 0.0016, + "step": 61728 + }, + { + "epoch": 19.06, + "learning_rate": 1.1467149347601847e-07, + "loss": 0.0013, + "step": 61729 + }, + { + "epoch": 19.06, + "learning_rate": 1.1459598500054403e-07, + "loss": 0.0009, + "step": 61730 + }, + { + "epoch": 19.06, + "learning_rate": 1.1452050125026704e-07, + "loss": 0.0014, + "step": 61731 + }, + { + "epoch": 19.06, + "learning_rate": 1.1444504222537733e-07, + "loss": 0.0017, + "step": 61732 + }, + { + "epoch": 19.06, + "learning_rate": 1.1436960792606366e-07, + "loss": 0.0016, + "step": 61733 + }, + { + "epoch": 19.06, + "learning_rate": 1.1429419835251477e-07, + "loss": 0.0016, + "step": 61734 + }, + { + "epoch": 19.06, + "learning_rate": 1.1421881350491937e-07, + "loss": 0.0011, + "step": 61735 + }, + { + "epoch": 19.07, + "learning_rate": 1.1414345338346511e-07, + "loss": 0.0016, + "step": 61736 + }, + { + "epoch": 19.07, + "learning_rate": 1.1406811798834183e-07, + "loss": 0.0016, + "step": 61737 + }, + { + "epoch": 19.07, + "learning_rate": 1.1399280731973606e-07, + "loss": 0.0017, + "step": 61738 + }, + { + "epoch": 19.07, + "learning_rate": 1.1391752137783874e-07, + "loss": 0.0011, + "step": 61739 + }, + { + "epoch": 19.07, + "learning_rate": 1.1384226016283639e-07, + "loss": 0.0013, + "step": 61740 + }, + { + "epoch": 19.07, + "learning_rate": 1.1376702367491665e-07, + "loss": 0.001, + "step": 61741 + }, + { + "epoch": 19.07, + "learning_rate": 1.1369181191427047e-07, + "loss": 0.0014, + "step": 61742 + }, + { + "epoch": 19.07, + "learning_rate": 1.1361662488108326e-07, + "loss": 0.0017, + "step": 61743 + }, + { + "epoch": 19.07, + "learning_rate": 1.1354146257554377e-07, + "loss": 0.0015, + "step": 61744 + }, + { + "epoch": 19.07, + "learning_rate": 1.1346632499784072e-07, + "loss": 0.0011, + "step": 61745 + }, + { + "epoch": 19.07, + "learning_rate": 1.1339121214816173e-07, + "loss": 0.0017, + "step": 61746 + }, + { + "epoch": 19.07, + "learning_rate": 1.1331612402669445e-07, + "loss": 0.0013, + "step": 61747 + }, + { + "epoch": 19.07, + "learning_rate": 1.132410606336265e-07, + "loss": 0.0016, + "step": 61748 + }, + { + "epoch": 19.07, + "learning_rate": 1.131660219691455e-07, + "loss": 0.0018, + "step": 61749 + }, + { + "epoch": 19.07, + "learning_rate": 1.1309100803344019e-07, + "loss": 0.0012, + "step": 61750 + }, + { + "epoch": 19.07, + "learning_rate": 1.1301601882669821e-07, + "loss": 0.0018, + "step": 61751 + }, + { + "epoch": 19.07, + "learning_rate": 1.1294105434910496e-07, + "loss": 0.0012, + "step": 61752 + }, + { + "epoch": 19.07, + "learning_rate": 1.1286611460085029e-07, + "loss": 0.0016, + "step": 61753 + }, + { + "epoch": 19.07, + "learning_rate": 1.1279119958212071e-07, + "loss": 0.0012, + "step": 61754 + }, + { + "epoch": 19.07, + "learning_rate": 1.1271630929310274e-07, + "loss": 0.0016, + "step": 61755 + }, + { + "epoch": 19.07, + "learning_rate": 1.1264144373398622e-07, + "loss": 0.0014, + "step": 61756 + }, + { + "epoch": 19.07, + "learning_rate": 1.1256660290495547e-07, + "loss": 0.0013, + "step": 61757 + }, + { + "epoch": 19.07, + "learning_rate": 1.1249178680619921e-07, + "loss": 0.0015, + "step": 61758 + }, + { + "epoch": 19.07, + "learning_rate": 1.1241699543790508e-07, + "loss": 0.0011, + "step": 61759 + }, + { + "epoch": 19.07, + "learning_rate": 1.1234222880025847e-07, + "loss": 0.0012, + "step": 61760 + }, + { + "epoch": 19.07, + "learning_rate": 1.1226748689344813e-07, + "loss": 0.0017, + "step": 61761 + }, + { + "epoch": 19.07, + "learning_rate": 1.1219276971765946e-07, + "loss": 0.0016, + "step": 61762 + }, + { + "epoch": 19.07, + "learning_rate": 1.1211807727308121e-07, + "loss": 0.0013, + "step": 61763 + }, + { + "epoch": 19.07, + "learning_rate": 1.1204340955989879e-07, + "loss": 0.0017, + "step": 61764 + }, + { + "epoch": 19.07, + "learning_rate": 1.1196876657829758e-07, + "loss": 0.0013, + "step": 61765 + }, + { + "epoch": 19.07, + "learning_rate": 1.1189414832846857e-07, + "loss": 0.0019, + "step": 61766 + }, + { + "epoch": 19.07, + "learning_rate": 1.1181955481059382e-07, + "loss": 0.0012, + "step": 61767 + }, + { + "epoch": 19.08, + "learning_rate": 1.1174498602486206e-07, + "loss": 0.0014, + "step": 61768 + }, + { + "epoch": 19.08, + "learning_rate": 1.1167044197145982e-07, + "loss": 0.001, + "step": 61769 + }, + { + "epoch": 19.08, + "learning_rate": 1.1159592265057473e-07, + "loss": 0.0012, + "step": 61770 + }, + { + "epoch": 19.08, + "learning_rate": 1.1152142806238997e-07, + "loss": 0.0009, + "step": 61771 + }, + { + "epoch": 19.08, + "learning_rate": 1.1144695820709429e-07, + "loss": 0.0012, + "step": 61772 + }, + { + "epoch": 19.08, + "learning_rate": 1.1137251308487418e-07, + "loss": 0.0014, + "step": 61773 + }, + { + "epoch": 19.08, + "learning_rate": 1.1129809269591286e-07, + "loss": 0.0015, + "step": 61774 + }, + { + "epoch": 19.08, + "learning_rate": 1.1122369704040015e-07, + "loss": 0.0012, + "step": 61775 + }, + { + "epoch": 19.08, + "learning_rate": 1.1114932611852147e-07, + "loss": 0.0016, + "step": 61776 + }, + { + "epoch": 19.08, + "learning_rate": 1.1107497993046001e-07, + "loss": 0.0011, + "step": 61777 + }, + { + "epoch": 19.08, + "learning_rate": 1.1100065847640452e-07, + "loss": 0.0009, + "step": 61778 + }, + { + "epoch": 19.08, + "learning_rate": 1.1092636175653925e-07, + "loss": 0.0016, + "step": 61779 + }, + { + "epoch": 19.08, + "learning_rate": 1.1085208977105188e-07, + "loss": 0.0013, + "step": 61780 + }, + { + "epoch": 19.08, + "learning_rate": 1.1077784252012669e-07, + "loss": 0.0016, + "step": 61781 + }, + { + "epoch": 19.08, + "learning_rate": 1.1070362000395019e-07, + "loss": 0.0014, + "step": 61782 + }, + { + "epoch": 19.08, + "learning_rate": 1.1062942222270667e-07, + "loss": 0.0011, + "step": 61783 + }, + { + "epoch": 19.08, + "learning_rate": 1.1055524917658267e-07, + "loss": 0.0016, + "step": 61784 + }, + { + "epoch": 19.08, + "learning_rate": 1.1048110086576468e-07, + "loss": 0.0016, + "step": 61785 + }, + { + "epoch": 19.08, + "learning_rate": 1.1040697729043704e-07, + "loss": 0.0017, + "step": 61786 + }, + { + "epoch": 19.08, + "learning_rate": 1.103328784507851e-07, + "loss": 0.0015, + "step": 61787 + }, + { + "epoch": 19.08, + "learning_rate": 1.1025880434699432e-07, + "loss": 0.0014, + "step": 61788 + }, + { + "epoch": 19.08, + "learning_rate": 1.1018475497925008e-07, + "loss": 0.0012, + "step": 61789 + }, + { + "epoch": 19.08, + "learning_rate": 1.1011073034773667e-07, + "loss": 0.0011, + "step": 61790 + }, + { + "epoch": 19.08, + "learning_rate": 1.1003673045264174e-07, + "loss": 0.002, + "step": 61791 + }, + { + "epoch": 19.08, + "learning_rate": 1.0996275529414846e-07, + "loss": 0.0012, + "step": 61792 + }, + { + "epoch": 19.08, + "learning_rate": 1.0988880487244113e-07, + "loss": 0.0014, + "step": 61793 + }, + { + "epoch": 19.08, + "learning_rate": 1.0981487918770628e-07, + "loss": 0.002, + "step": 61794 + }, + { + "epoch": 19.08, + "learning_rate": 1.0974097824012819e-07, + "loss": 0.0018, + "step": 61795 + }, + { + "epoch": 19.08, + "learning_rate": 1.0966710202989228e-07, + "loss": 0.0013, + "step": 61796 + }, + { + "epoch": 19.08, + "learning_rate": 1.0959325055718284e-07, + "loss": 0.0016, + "step": 61797 + }, + { + "epoch": 19.08, + "learning_rate": 1.0951942382218417e-07, + "loss": 0.0015, + "step": 61798 + }, + { + "epoch": 19.08, + "learning_rate": 1.0944562182508057e-07, + "loss": 0.0016, + "step": 61799 + }, + { + "epoch": 19.08, + "learning_rate": 1.0937184456605854e-07, + "loss": 0.001, + "step": 61800 + }, + { + "epoch": 19.09, + "learning_rate": 1.0929809204530129e-07, + "loss": 0.0013, + "step": 61801 + }, + { + "epoch": 19.09, + "learning_rate": 1.092243642629931e-07, + "loss": 0.0011, + "step": 61802 + }, + { + "epoch": 19.09, + "learning_rate": 1.0915066121931828e-07, + "loss": 0.0019, + "step": 61803 + }, + { + "epoch": 19.09, + "learning_rate": 1.0907698291446334e-07, + "loss": 0.0015, + "step": 61804 + }, + { + "epoch": 19.09, + "learning_rate": 1.0900332934860925e-07, + "loss": 0.0014, + "step": 61805 + }, + { + "epoch": 19.09, + "learning_rate": 1.0892970052194252e-07, + "loss": 0.0011, + "step": 61806 + }, + { + "epoch": 19.09, + "learning_rate": 1.0885609643464745e-07, + "loss": 0.0016, + "step": 61807 + }, + { + "epoch": 19.09, + "learning_rate": 1.0878251708690502e-07, + "loss": 0.0018, + "step": 61808 + }, + { + "epoch": 19.09, + "learning_rate": 1.0870896247890284e-07, + "loss": 0.0018, + "step": 61809 + }, + { + "epoch": 19.09, + "learning_rate": 1.086354326108241e-07, + "loss": 0.0016, + "step": 61810 + }, + { + "epoch": 19.09, + "learning_rate": 1.08561927482852e-07, + "loss": 0.0018, + "step": 61811 + }, + { + "epoch": 19.09, + "learning_rate": 1.084884470951697e-07, + "loss": 0.0021, + "step": 61812 + }, + { + "epoch": 19.09, + "learning_rate": 1.0841499144796375e-07, + "loss": 0.0018, + "step": 61813 + }, + { + "epoch": 19.09, + "learning_rate": 1.0834156054141398e-07, + "loss": 0.0016, + "step": 61814 + }, + { + "epoch": 19.09, + "learning_rate": 1.0826815437570692e-07, + "loss": 0.0015, + "step": 61815 + }, + { + "epoch": 19.09, + "learning_rate": 1.0819477295102577e-07, + "loss": 0.0019, + "step": 61816 + }, + { + "epoch": 19.09, + "learning_rate": 1.0812141626755368e-07, + "loss": 0.0013, + "step": 61817 + }, + { + "epoch": 19.09, + "learning_rate": 1.0804808432547276e-07, + "loss": 0.0014, + "step": 61818 + }, + { + "epoch": 19.09, + "learning_rate": 1.079747771249695e-07, + "loss": 0.0016, + "step": 61819 + }, + { + "epoch": 19.09, + "learning_rate": 1.079014946662238e-07, + "loss": 0.0017, + "step": 61820 + }, + { + "epoch": 19.09, + "learning_rate": 1.0782823694942213e-07, + "loss": 0.0014, + "step": 61821 + }, + { + "epoch": 19.09, + "learning_rate": 1.0775500397474548e-07, + "loss": 0.0022, + "step": 61822 + }, + { + "epoch": 19.09, + "learning_rate": 1.0768179574237813e-07, + "loss": 0.0012, + "step": 61823 + }, + { + "epoch": 19.09, + "learning_rate": 1.0760861225250219e-07, + "loss": 0.0014, + "step": 61824 + }, + { + "epoch": 19.09, + "learning_rate": 1.0753545350530303e-07, + "loss": 0.0014, + "step": 61825 + }, + { + "epoch": 19.09, + "learning_rate": 1.0746231950096053e-07, + "loss": 0.0016, + "step": 61826 + }, + { + "epoch": 19.09, + "learning_rate": 1.0738921023965898e-07, + "loss": 0.0018, + "step": 61827 + }, + { + "epoch": 19.09, + "learning_rate": 1.0731612572158268e-07, + "loss": 0.0012, + "step": 61828 + }, + { + "epoch": 19.09, + "learning_rate": 1.0724306594691147e-07, + "loss": 0.0013, + "step": 61829 + }, + { + "epoch": 19.09, + "learning_rate": 1.0717003091582967e-07, + "loss": 0.0018, + "step": 61830 + }, + { + "epoch": 19.09, + "learning_rate": 1.0709702062852157e-07, + "loss": 0.0011, + "step": 61831 + }, + { + "epoch": 19.09, + "learning_rate": 1.07024035085167e-07, + "loss": 0.0014, + "step": 61832 + }, + { + "epoch": 19.1, + "learning_rate": 1.069510742859492e-07, + "loss": 0.0014, + "step": 61833 + }, + { + "epoch": 19.1, + "learning_rate": 1.0687813823105241e-07, + "loss": 0.0013, + "step": 61834 + }, + { + "epoch": 19.1, + "learning_rate": 1.0680522692065653e-07, + "loss": 0.001, + "step": 61835 + }, + { + "epoch": 19.1, + "learning_rate": 1.0673234035494584e-07, + "loss": 0.0012, + "step": 61836 + }, + { + "epoch": 19.1, + "learning_rate": 1.0665947853410241e-07, + "loss": 0.0014, + "step": 61837 + }, + { + "epoch": 19.1, + "learning_rate": 1.0658664145830832e-07, + "loss": 0.0012, + "step": 61838 + }, + { + "epoch": 19.1, + "learning_rate": 1.0651382912774454e-07, + "loss": 0.0016, + "step": 61839 + }, + { + "epoch": 19.1, + "learning_rate": 1.0644104154259427e-07, + "loss": 0.0019, + "step": 61840 + }, + { + "epoch": 19.1, + "learning_rate": 1.0636827870303956e-07, + "loss": 0.0013, + "step": 61841 + }, + { + "epoch": 19.1, + "learning_rate": 1.0629554060926139e-07, + "loss": 0.0015, + "step": 61842 + }, + { + "epoch": 19.1, + "learning_rate": 1.0622282726144406e-07, + "loss": 0.0011, + "step": 61843 + }, + { + "epoch": 19.1, + "learning_rate": 1.0615013865976741e-07, + "loss": 0.0012, + "step": 61844 + }, + { + "epoch": 19.1, + "learning_rate": 1.0607747480441355e-07, + "loss": 0.0011, + "step": 61845 + }, + { + "epoch": 19.1, + "learning_rate": 1.0600483569556453e-07, + "loss": 0.001, + "step": 61846 + }, + { + "epoch": 19.1, + "learning_rate": 1.0593222133340242e-07, + "loss": 0.0017, + "step": 61847 + }, + { + "epoch": 19.1, + "learning_rate": 1.058596317181082e-07, + "loss": 0.0014, + "step": 61848 + }, + { + "epoch": 19.1, + "learning_rate": 1.0578706684986284e-07, + "loss": 0.0013, + "step": 61849 + }, + { + "epoch": 19.1, + "learning_rate": 1.0571452672885063e-07, + "loss": 0.0017, + "step": 61850 + }, + { + "epoch": 19.1, + "learning_rate": 1.056420113552492e-07, + "loss": 0.0014, + "step": 61851 + }, + { + "epoch": 19.1, + "learning_rate": 1.0556952072924176e-07, + "loss": 0.0012, + "step": 61852 + }, + { + "epoch": 19.1, + "learning_rate": 1.0549705485101035e-07, + "loss": 0.0014, + "step": 61853 + }, + { + "epoch": 19.1, + "learning_rate": 1.0542461372073487e-07, + "loss": 0.0013, + "step": 61854 + }, + { + "epoch": 19.1, + "learning_rate": 1.0535219733859736e-07, + "loss": 0.0017, + "step": 61855 + }, + { + "epoch": 19.1, + "learning_rate": 1.052798057047788e-07, + "loss": 0.0018, + "step": 61856 + }, + { + "epoch": 19.1, + "learning_rate": 1.0520743881945904e-07, + "loss": 0.0014, + "step": 61857 + }, + { + "epoch": 19.1, + "learning_rate": 1.0513509668282129e-07, + "loss": 0.0011, + "step": 61858 + }, + { + "epoch": 19.1, + "learning_rate": 1.0506277929504538e-07, + "loss": 0.0016, + "step": 61859 + }, + { + "epoch": 19.1, + "learning_rate": 1.0499048665631229e-07, + "loss": 0.0012, + "step": 61860 + }, + { + "epoch": 19.1, + "learning_rate": 1.0491821876680186e-07, + "loss": 0.002, + "step": 61861 + }, + { + "epoch": 19.1, + "learning_rate": 1.0484597562669619e-07, + "loss": 0.0012, + "step": 61862 + }, + { + "epoch": 19.1, + "learning_rate": 1.0477375723617511e-07, + "loss": 0.0019, + "step": 61863 + }, + { + "epoch": 19.1, + "learning_rate": 1.0470156359542072e-07, + "loss": 0.0018, + "step": 61864 + }, + { + "epoch": 19.1, + "learning_rate": 1.0462939470461176e-07, + "loss": 0.0016, + "step": 61865 + }, + { + "epoch": 19.11, + "learning_rate": 1.0455725056393028e-07, + "loss": 0.0013, + "step": 61866 + }, + { + "epoch": 19.11, + "learning_rate": 1.0448513117355396e-07, + "loss": 0.0018, + "step": 61867 + }, + { + "epoch": 19.11, + "learning_rate": 1.0441303653366708e-07, + "loss": 0.0011, + "step": 61868 + }, + { + "epoch": 19.11, + "learning_rate": 1.0434096664444837e-07, + "loss": 0.0012, + "step": 61869 + }, + { + "epoch": 19.11, + "learning_rate": 1.0426892150607549e-07, + "loss": 0.0014, + "step": 61870 + }, + { + "epoch": 19.11, + "learning_rate": 1.0419690111873271e-07, + "loss": 0.0015, + "step": 61871 + }, + { + "epoch": 19.11, + "learning_rate": 1.0412490548259768e-07, + "loss": 0.0019, + "step": 61872 + }, + { + "epoch": 19.11, + "learning_rate": 1.0405293459785138e-07, + "loss": 0.0016, + "step": 61873 + }, + { + "epoch": 19.11, + "learning_rate": 1.0398098846467364e-07, + "loss": 0.0016, + "step": 61874 + }, + { + "epoch": 19.11, + "learning_rate": 1.0390906708324433e-07, + "loss": 0.0019, + "step": 61875 + }, + { + "epoch": 19.11, + "learning_rate": 1.0383717045374331e-07, + "loss": 0.0013, + "step": 61876 + }, + { + "epoch": 19.11, + "learning_rate": 1.0376529857635043e-07, + "loss": 0.0014, + "step": 61877 + }, + { + "epoch": 19.11, + "learning_rate": 1.0369345145124554e-07, + "loss": 0.0016, + "step": 61878 + }, + { + "epoch": 19.11, + "learning_rate": 1.0362162907860851e-07, + "loss": 0.0016, + "step": 61879 + }, + { + "epoch": 19.11, + "learning_rate": 1.0354983145861808e-07, + "loss": 0.0012, + "step": 61880 + }, + { + "epoch": 19.11, + "learning_rate": 1.0347805859145522e-07, + "loss": 0.0016, + "step": 61881 + }, + { + "epoch": 19.11, + "learning_rate": 1.0340631047729865e-07, + "loss": 0.0012, + "step": 61882 + }, + { + "epoch": 19.11, + "learning_rate": 1.0333458711632715e-07, + "loss": 0.0023, + "step": 61883 + }, + { + "epoch": 19.11, + "learning_rate": 1.0326288850872168e-07, + "loss": 0.0014, + "step": 61884 + }, + { + "epoch": 19.11, + "learning_rate": 1.0319121465466097e-07, + "loss": 0.0014, + "step": 61885 + }, + { + "epoch": 19.11, + "learning_rate": 1.0311956555432378e-07, + "loss": 0.0014, + "step": 61886 + }, + { + "epoch": 19.11, + "learning_rate": 1.0304794120788996e-07, + "loss": 0.0016, + "step": 61887 + }, + { + "epoch": 19.11, + "learning_rate": 1.0297634161553826e-07, + "loss": 0.0016, + "step": 61888 + }, + { + "epoch": 19.11, + "learning_rate": 1.0290476677744742e-07, + "loss": 0.0011, + "step": 61889 + }, + { + "epoch": 19.11, + "learning_rate": 1.0283321669379731e-07, + "loss": 0.0015, + "step": 61890 + }, + { + "epoch": 19.11, + "learning_rate": 1.0276169136476555e-07, + "loss": 0.0015, + "step": 61891 + }, + { + "epoch": 19.11, + "learning_rate": 1.0269019079053311e-07, + "loss": 0.0015, + "step": 61892 + }, + { + "epoch": 19.11, + "learning_rate": 1.0261871497127652e-07, + "loss": 0.0017, + "step": 61893 + }, + { + "epoch": 19.11, + "learning_rate": 1.0254726390717673e-07, + "loss": 0.0017, + "step": 61894 + }, + { + "epoch": 19.11, + "learning_rate": 1.024758375984114e-07, + "loss": 0.0011, + "step": 61895 + }, + { + "epoch": 19.11, + "learning_rate": 1.0240443604515926e-07, + "loss": 0.0016, + "step": 61896 + }, + { + "epoch": 19.11, + "learning_rate": 1.0233305924759796e-07, + "loss": 0.0015, + "step": 61897 + }, + { + "epoch": 19.12, + "learning_rate": 1.0226170720590622e-07, + "loss": 0.0019, + "step": 61898 + }, + { + "epoch": 19.12, + "learning_rate": 1.0219037992026504e-07, + "loss": 0.0013, + "step": 61899 + }, + { + "epoch": 19.12, + "learning_rate": 1.0211907739085092e-07, + "loss": 0.0013, + "step": 61900 + }, + { + "epoch": 19.12, + "learning_rate": 1.0204779961784039e-07, + "loss": 0.0015, + "step": 61901 + }, + { + "epoch": 19.12, + "learning_rate": 1.0197654660141443e-07, + "loss": 0.0013, + "step": 61902 + }, + { + "epoch": 19.12, + "learning_rate": 1.0190531834175177e-07, + "loss": 0.0011, + "step": 61903 + }, + { + "epoch": 19.12, + "learning_rate": 1.0183411483902782e-07, + "loss": 0.0014, + "step": 61904 + }, + { + "epoch": 19.12, + "learning_rate": 1.0176293609342247e-07, + "loss": 0.0017, + "step": 61905 + }, + { + "epoch": 19.12, + "learning_rate": 1.0169178210511332e-07, + "loss": 0.0012, + "step": 61906 + }, + { + "epoch": 19.12, + "learning_rate": 1.0162065287427803e-07, + "loss": 0.0014, + "step": 61907 + }, + { + "epoch": 19.12, + "learning_rate": 1.0154954840109421e-07, + "loss": 0.0018, + "step": 61908 + }, + { + "epoch": 19.12, + "learning_rate": 1.0147846868574173e-07, + "loss": 0.0015, + "step": 61909 + }, + { + "epoch": 19.12, + "learning_rate": 1.0140741372839713e-07, + "loss": 0.0018, + "step": 61910 + }, + { + "epoch": 19.12, + "learning_rate": 1.0133638352923692e-07, + "loss": 0.0014, + "step": 61911 + }, + { + "epoch": 19.12, + "learning_rate": 1.0126537808844094e-07, + "loss": 0.0019, + "step": 61912 + }, + { + "epoch": 19.12, + "learning_rate": 1.0119439740618464e-07, + "loss": 0.0014, + "step": 61913 + }, + { + "epoch": 19.12, + "learning_rate": 1.0112344148264674e-07, + "loss": 0.0015, + "step": 61914 + }, + { + "epoch": 19.12, + "learning_rate": 1.010525103180049e-07, + "loss": 0.0013, + "step": 61915 + }, + { + "epoch": 19.12, + "learning_rate": 1.0098160391243562e-07, + "loss": 0.0017, + "step": 61916 + }, + { + "epoch": 19.12, + "learning_rate": 1.0091072226611764e-07, + "loss": 0.0016, + "step": 61917 + }, + { + "epoch": 19.12, + "learning_rate": 1.0083986537922641e-07, + "loss": 0.0014, + "step": 61918 + }, + { + "epoch": 19.12, + "learning_rate": 1.0076903325194065e-07, + "loss": 0.0013, + "step": 61919 + }, + { + "epoch": 19.12, + "learning_rate": 1.00698225884438e-07, + "loss": 0.0013, + "step": 61920 + }, + { + "epoch": 19.12, + "learning_rate": 1.0062744327689389e-07, + "loss": 0.0015, + "step": 61921 + }, + { + "epoch": 19.12, + "learning_rate": 1.0055668542948594e-07, + "loss": 0.0019, + "step": 61922 + }, + { + "epoch": 19.12, + "learning_rate": 1.0048595234239066e-07, + "loss": 0.0014, + "step": 61923 + }, + { + "epoch": 19.12, + "learning_rate": 1.0041524401578573e-07, + "loss": 0.0017, + "step": 61924 + }, + { + "epoch": 19.12, + "learning_rate": 1.0034456044984875e-07, + "loss": 0.0014, + "step": 61925 + }, + { + "epoch": 19.12, + "learning_rate": 1.0027390164475514e-07, + "loss": 0.0014, + "step": 61926 + }, + { + "epoch": 19.12, + "learning_rate": 1.0020326760068255e-07, + "loss": 0.0016, + "step": 61927 + }, + { + "epoch": 19.12, + "learning_rate": 1.0013265831780638e-07, + "loss": 0.0015, + "step": 61928 + }, + { + "epoch": 19.12, + "learning_rate": 1.0006207379630428e-07, + "loss": 0.0018, + "step": 61929 + }, + { + "epoch": 19.13, + "learning_rate": 9.999151403635277e-08, + "loss": 0.0011, + "step": 61930 + }, + { + "epoch": 19.13, + "learning_rate": 9.992097903812837e-08, + "loss": 0.0016, + "step": 61931 + }, + { + "epoch": 19.13, + "learning_rate": 9.985046880180648e-08, + "loss": 0.0009, + "step": 61932 + }, + { + "epoch": 19.13, + "learning_rate": 9.977998332756478e-08, + "loss": 0.0011, + "step": 61933 + }, + { + "epoch": 19.13, + "learning_rate": 9.970952261557865e-08, + "loss": 0.0017, + "step": 61934 + }, + { + "epoch": 19.13, + "learning_rate": 9.963908666602573e-08, + "loss": 0.0015, + "step": 61935 + }, + { + "epoch": 19.13, + "learning_rate": 9.956867547908033e-08, + "loss": 0.0018, + "step": 61936 + }, + { + "epoch": 19.13, + "learning_rate": 9.949828905492009e-08, + "loss": 0.0015, + "step": 61937 + }, + { + "epoch": 19.13, + "learning_rate": 9.942792739371932e-08, + "loss": 0.0021, + "step": 61938 + }, + { + "epoch": 19.13, + "learning_rate": 9.935759049565563e-08, + "loss": 0.0017, + "step": 61939 + }, + { + "epoch": 19.13, + "learning_rate": 9.928727836090446e-08, + "loss": 0.0013, + "step": 61940 + }, + { + "epoch": 19.13, + "learning_rate": 9.921699098964121e-08, + "loss": 0.0012, + "step": 61941 + }, + { + "epoch": 19.13, + "learning_rate": 9.914672838204242e-08, + "loss": 0.0013, + "step": 61942 + }, + { + "epoch": 19.13, + "learning_rate": 9.907649053828349e-08, + "loss": 0.0013, + "step": 61943 + }, + { + "epoch": 19.13, + "learning_rate": 9.900627745853986e-08, + "loss": 0.0016, + "step": 61944 + }, + { + "epoch": 19.13, + "learning_rate": 9.893608914298692e-08, + "loss": 0.0015, + "step": 61945 + }, + { + "epoch": 19.13, + "learning_rate": 9.88659255918012e-08, + "loss": 0.0015, + "step": 61946 + }, + { + "epoch": 19.13, + "learning_rate": 9.879578680515811e-08, + "loss": 0.001, + "step": 61947 + }, + { + "epoch": 19.13, + "learning_rate": 9.872567278323197e-08, + "loss": 0.0014, + "step": 61948 + }, + { + "epoch": 19.13, + "learning_rate": 9.865558352619819e-08, + "loss": 0.0017, + "step": 61949 + }, + { + "epoch": 19.13, + "learning_rate": 9.85855190342333e-08, + "loss": 0.001, + "step": 61950 + }, + { + "epoch": 19.13, + "learning_rate": 9.85154793075127e-08, + "loss": 0.0018, + "step": 61951 + }, + { + "epoch": 19.13, + "learning_rate": 9.844546434621072e-08, + "loss": 0.0016, + "step": 61952 + }, + { + "epoch": 19.13, + "learning_rate": 9.837547415050164e-08, + "loss": 0.0015, + "step": 61953 + }, + { + "epoch": 19.13, + "learning_rate": 9.830550872056088e-08, + "loss": 0.001, + "step": 61954 + }, + { + "epoch": 19.13, + "learning_rate": 9.823556805656609e-08, + "loss": 0.0017, + "step": 61955 + }, + { + "epoch": 19.13, + "learning_rate": 9.816565215868933e-08, + "loss": 0.0016, + "step": 61956 + }, + { + "epoch": 19.13, + "learning_rate": 9.809576102710494e-08, + "loss": 0.002, + "step": 61957 + }, + { + "epoch": 19.13, + "learning_rate": 9.802589466199053e-08, + "loss": 0.0015, + "step": 61958 + }, + { + "epoch": 19.13, + "learning_rate": 9.795605306351818e-08, + "loss": 0.0014, + "step": 61959 + }, + { + "epoch": 19.13, + "learning_rate": 9.788623623186445e-08, + "loss": 0.0016, + "step": 61960 + }, + { + "epoch": 19.13, + "learning_rate": 9.781644416720359e-08, + "loss": 0.002, + "step": 61961 + }, + { + "epoch": 19.13, + "learning_rate": 9.774667686970995e-08, + "loss": 0.0012, + "step": 61962 + }, + { + "epoch": 19.14, + "learning_rate": 9.767693433955672e-08, + "loss": 0.0017, + "step": 61963 + }, + { + "epoch": 19.14, + "learning_rate": 9.760721657692041e-08, + "loss": 0.0013, + "step": 61964 + }, + { + "epoch": 19.14, + "learning_rate": 9.753752358197421e-08, + "loss": 0.0013, + "step": 61965 + }, + { + "epoch": 19.14, + "learning_rate": 9.746785535489356e-08, + "loss": 0.0014, + "step": 61966 + }, + { + "epoch": 19.14, + "learning_rate": 9.739821189585052e-08, + "loss": 0.0013, + "step": 61967 + }, + { + "epoch": 19.14, + "learning_rate": 9.732859320502275e-08, + "loss": 0.0018, + "step": 61968 + }, + { + "epoch": 19.14, + "learning_rate": 9.725899928258008e-08, + "loss": 0.0014, + "step": 61969 + }, + { + "epoch": 19.14, + "learning_rate": 9.718943012869908e-08, + "loss": 0.0017, + "step": 61970 + }, + { + "epoch": 19.14, + "learning_rate": 9.711988574355513e-08, + "loss": 0.0011, + "step": 61971 + }, + { + "epoch": 19.14, + "learning_rate": 9.705036612731922e-08, + "loss": 0.0014, + "step": 61972 + }, + { + "epoch": 19.14, + "learning_rate": 9.698087128016676e-08, + "loss": 0.0015, + "step": 61973 + }, + { + "epoch": 19.14, + "learning_rate": 9.691140120227205e-08, + "loss": 0.0011, + "step": 61974 + }, + { + "epoch": 19.14, + "learning_rate": 9.684195589380719e-08, + "loss": 0.0012, + "step": 61975 + }, + { + "epoch": 19.14, + "learning_rate": 9.677253535494758e-08, + "loss": 0.0015, + "step": 61976 + }, + { + "epoch": 19.14, + "learning_rate": 9.67031395858653e-08, + "loss": 0.001, + "step": 61977 + }, + { + "epoch": 19.14, + "learning_rate": 9.663376858673579e-08, + "loss": 0.0016, + "step": 61978 + }, + { + "epoch": 19.14, + "learning_rate": 9.656442235773e-08, + "loss": 0.0018, + "step": 61979 + }, + { + "epoch": 19.14, + "learning_rate": 9.649510089902336e-08, + "loss": 0.0017, + "step": 61980 + }, + { + "epoch": 19.14, + "learning_rate": 9.642580421078907e-08, + "loss": 0.0018, + "step": 61981 + }, + { + "epoch": 19.14, + "learning_rate": 9.63565322932003e-08, + "loss": 0.0019, + "step": 61982 + }, + { + "epoch": 19.14, + "learning_rate": 9.628728514643026e-08, + "loss": 0.0015, + "step": 61983 + }, + { + "epoch": 19.14, + "learning_rate": 9.621806277065216e-08, + "loss": 0.0016, + "step": 61984 + }, + { + "epoch": 19.14, + "learning_rate": 9.614886516603805e-08, + "loss": 0.0015, + "step": 61985 + }, + { + "epoch": 19.14, + "learning_rate": 9.607969233276226e-08, + "loss": 0.0025, + "step": 61986 + }, + { + "epoch": 19.14, + "learning_rate": 9.601054427099799e-08, + "loss": 0.0011, + "step": 61987 + }, + { + "epoch": 19.14, + "learning_rate": 9.59414209809173e-08, + "loss": 0.0018, + "step": 61988 + }, + { + "epoch": 19.14, + "learning_rate": 9.587232246269452e-08, + "loss": 0.0015, + "step": 61989 + }, + { + "epoch": 19.14, + "learning_rate": 9.580324871650059e-08, + "loss": 0.001, + "step": 61990 + }, + { + "epoch": 19.14, + "learning_rate": 9.573419974250875e-08, + "loss": 0.0016, + "step": 61991 + }, + { + "epoch": 19.14, + "learning_rate": 9.566517554089327e-08, + "loss": 0.0014, + "step": 61992 + }, + { + "epoch": 19.14, + "learning_rate": 9.559617611182515e-08, + "loss": 0.0018, + "step": 61993 + }, + { + "epoch": 19.14, + "learning_rate": 9.552720145547645e-08, + "loss": 0.0016, + "step": 61994 + }, + { + "epoch": 19.15, + "learning_rate": 9.545825157202148e-08, + "loss": 0.0015, + "step": 61995 + }, + { + "epoch": 19.15, + "learning_rate": 9.538932646163235e-08, + "loss": 0.002, + "step": 61996 + }, + { + "epoch": 19.15, + "learning_rate": 9.532042612448001e-08, + "loss": 0.0015, + "step": 61997 + }, + { + "epoch": 19.15, + "learning_rate": 9.525155056073876e-08, + "loss": 0.0008, + "step": 61998 + }, + { + "epoch": 19.15, + "learning_rate": 9.518269977057959e-08, + "loss": 0.0015, + "step": 61999 + }, + { + "epoch": 19.15, + "learning_rate": 9.511387375417458e-08, + "loss": 0.0013, + "step": 62000 + }, + { + "epoch": 19.15, + "learning_rate": 9.504507251169582e-08, + "loss": 0.0015, + "step": 62001 + }, + { + "epoch": 19.15, + "learning_rate": 9.49762960433176e-08, + "loss": 0.0013, + "step": 62002 + }, + { + "epoch": 19.15, + "learning_rate": 9.490754434920979e-08, + "loss": 0.0012, + "step": 62003 + }, + { + "epoch": 19.15, + "learning_rate": 9.483881742954337e-08, + "loss": 0.001, + "step": 62004 + }, + { + "epoch": 19.15, + "learning_rate": 9.477011528449265e-08, + "loss": 0.0011, + "step": 62005 + }, + { + "epoch": 19.15, + "learning_rate": 9.470143791422859e-08, + "loss": 0.0022, + "step": 62006 + }, + { + "epoch": 19.15, + "learning_rate": 9.463278531892328e-08, + "loss": 0.0013, + "step": 62007 + }, + { + "epoch": 19.15, + "learning_rate": 9.45641574987477e-08, + "loss": 0.0014, + "step": 62008 + }, + { + "epoch": 19.15, + "learning_rate": 9.449555445387282e-08, + "loss": 0.0014, + "step": 62009 + }, + { + "epoch": 19.15, + "learning_rate": 9.442697618447183e-08, + "loss": 0.0014, + "step": 62010 + }, + { + "epoch": 19.15, + "learning_rate": 9.435842269071572e-08, + "loss": 0.0014, + "step": 62011 + }, + { + "epoch": 19.15, + "learning_rate": 9.428989397277544e-08, + "loss": 0.0015, + "step": 62012 + }, + { + "epoch": 19.15, + "learning_rate": 9.422139003082308e-08, + "loss": 0.0014, + "step": 62013 + }, + { + "epoch": 19.15, + "learning_rate": 9.415291086503076e-08, + "loss": 0.0012, + "step": 62014 + }, + { + "epoch": 19.15, + "learning_rate": 9.408445647556719e-08, + "loss": 0.002, + "step": 62015 + }, + { + "epoch": 19.15, + "learning_rate": 9.401602686260558e-08, + "loss": 0.0014, + "step": 62016 + }, + { + "epoch": 19.15, + "learning_rate": 9.394762202631691e-08, + "loss": 0.0014, + "step": 62017 + }, + { + "epoch": 19.15, + "learning_rate": 9.387924196687215e-08, + "loss": 0.0015, + "step": 62018 + }, + { + "epoch": 19.15, + "learning_rate": 9.381088668444228e-08, + "loss": 0.0012, + "step": 62019 + }, + { + "epoch": 19.15, + "learning_rate": 9.374255617919714e-08, + "loss": 0.0014, + "step": 62020 + }, + { + "epoch": 19.15, + "learning_rate": 9.367425045130996e-08, + "loss": 0.0014, + "step": 62021 + }, + { + "epoch": 19.15, + "learning_rate": 9.360596950094835e-08, + "loss": 0.001, + "step": 62022 + }, + { + "epoch": 19.15, + "learning_rate": 9.353771332828777e-08, + "loss": 0.0015, + "step": 62023 + }, + { + "epoch": 19.15, + "learning_rate": 9.34694819334947e-08, + "loss": 0.0013, + "step": 62024 + }, + { + "epoch": 19.15, + "learning_rate": 9.340127531674014e-08, + "loss": 0.0015, + "step": 62025 + }, + { + "epoch": 19.15, + "learning_rate": 9.333309347819731e-08, + "loss": 0.002, + "step": 62026 + }, + { + "epoch": 19.16, + "learning_rate": 9.326493641803491e-08, + "loss": 0.0019, + "step": 62027 + }, + { + "epoch": 19.16, + "learning_rate": 9.319680413642396e-08, + "loss": 0.0016, + "step": 62028 + }, + { + "epoch": 19.16, + "learning_rate": 9.31286966335343e-08, + "loss": 0.0014, + "step": 62029 + }, + { + "epoch": 19.16, + "learning_rate": 9.306061390953802e-08, + "loss": 0.0015, + "step": 62030 + }, + { + "epoch": 19.16, + "learning_rate": 9.299255596460277e-08, + "loss": 0.0014, + "step": 62031 + }, + { + "epoch": 19.16, + "learning_rate": 9.292452279889953e-08, + "loss": 0.001, + "step": 62032 + }, + { + "epoch": 19.16, + "learning_rate": 9.285651441260036e-08, + "loss": 0.0014, + "step": 62033 + }, + { + "epoch": 19.16, + "learning_rate": 9.278853080587292e-08, + "loss": 0.0015, + "step": 62034 + }, + { + "epoch": 19.16, + "learning_rate": 9.272057197888929e-08, + "loss": 0.0014, + "step": 62035 + }, + { + "epoch": 19.16, + "learning_rate": 9.265263793181823e-08, + "loss": 0.0016, + "step": 62036 + }, + { + "epoch": 19.16, + "learning_rate": 9.258472866482848e-08, + "loss": 0.0015, + "step": 62037 + }, + { + "epoch": 19.16, + "learning_rate": 9.251684417809325e-08, + "loss": 0.0012, + "step": 62038 + }, + { + "epoch": 19.16, + "learning_rate": 9.244898447178019e-08, + "loss": 0.0011, + "step": 62039 + }, + { + "epoch": 19.16, + "learning_rate": 9.238114954605804e-08, + "loss": 0.0013, + "step": 62040 + }, + { + "epoch": 19.16, + "learning_rate": 9.231333940109777e-08, + "loss": 0.0013, + "step": 62041 + }, + { + "epoch": 19.16, + "learning_rate": 9.224555403707036e-08, + "loss": 0.0016, + "step": 62042 + }, + { + "epoch": 19.16, + "learning_rate": 9.217779345414235e-08, + "loss": 0.0012, + "step": 62043 + }, + { + "epoch": 19.16, + "learning_rate": 9.211005765248581e-08, + "loss": 0.0017, + "step": 62044 + }, + { + "epoch": 19.16, + "learning_rate": 9.204234663226951e-08, + "loss": 0.0013, + "step": 62045 + }, + { + "epoch": 19.16, + "learning_rate": 9.19746603936611e-08, + "loss": 0.0011, + "step": 62046 + }, + { + "epoch": 19.16, + "learning_rate": 9.190699893683153e-08, + "loss": 0.0021, + "step": 62047 + }, + { + "epoch": 19.16, + "learning_rate": 9.183936226194957e-08, + "loss": 0.0015, + "step": 62048 + }, + { + "epoch": 19.16, + "learning_rate": 9.177175036918507e-08, + "loss": 0.0012, + "step": 62049 + }, + { + "epoch": 19.16, + "learning_rate": 9.170416325870568e-08, + "loss": 0.0014, + "step": 62050 + }, + { + "epoch": 19.16, + "learning_rate": 9.163660093068238e-08, + "loss": 0.0016, + "step": 62051 + }, + { + "epoch": 19.16, + "learning_rate": 9.156906338528282e-08, + "loss": 0.0014, + "step": 62052 + }, + { + "epoch": 19.16, + "learning_rate": 9.150155062267573e-08, + "loss": 0.0015, + "step": 62053 + }, + { + "epoch": 19.16, + "learning_rate": 9.1434062643031e-08, + "loss": 0.0012, + "step": 62054 + }, + { + "epoch": 19.16, + "learning_rate": 9.136659944651627e-08, + "loss": 0.0014, + "step": 62055 + }, + { + "epoch": 19.16, + "learning_rate": 9.129916103330138e-08, + "loss": 0.0014, + "step": 62056 + }, + { + "epoch": 19.16, + "learning_rate": 9.123174740355511e-08, + "loss": 0.002, + "step": 62057 + }, + { + "epoch": 19.16, + "learning_rate": 9.116435855744399e-08, + "loss": 0.0014, + "step": 62058 + }, + { + "epoch": 19.16, + "learning_rate": 9.109699449513898e-08, + "loss": 0.0016, + "step": 62059 + }, + { + "epoch": 19.17, + "learning_rate": 9.102965521680774e-08, + "loss": 0.0016, + "step": 62060 + }, + { + "epoch": 19.17, + "learning_rate": 9.09623407226179e-08, + "loss": 0.002, + "step": 62061 + }, + { + "epoch": 19.17, + "learning_rate": 9.089505101273932e-08, + "loss": 0.0015, + "step": 62062 + }, + { + "epoch": 19.17, + "learning_rate": 9.082778608733855e-08, + "loss": 0.0017, + "step": 62063 + }, + { + "epoch": 19.17, + "learning_rate": 9.076054594658656e-08, + "loss": 0.0012, + "step": 62064 + }, + { + "epoch": 19.17, + "learning_rate": 9.069333059064878e-08, + "loss": 0.0012, + "step": 62065 + }, + { + "epoch": 19.17, + "learning_rate": 9.062614001969394e-08, + "loss": 0.0019, + "step": 62066 + }, + { + "epoch": 19.17, + "learning_rate": 9.055897423389082e-08, + "loss": 0.0011, + "step": 62067 + }, + { + "epoch": 19.17, + "learning_rate": 9.049183323340704e-08, + "loss": 0.0014, + "step": 62068 + }, + { + "epoch": 19.17, + "learning_rate": 9.042471701841027e-08, + "loss": 0.0011, + "step": 62069 + }, + { + "epoch": 19.17, + "learning_rate": 9.035762558906925e-08, + "loss": 0.0018, + "step": 62070 + }, + { + "epoch": 19.17, + "learning_rate": 9.029055894555161e-08, + "loss": 0.0018, + "step": 62071 + }, + { + "epoch": 19.17, + "learning_rate": 9.02235170880228e-08, + "loss": 0.0018, + "step": 62072 + }, + { + "epoch": 19.17, + "learning_rate": 9.015650001665488e-08, + "loss": 0.0011, + "step": 62073 + }, + { + "epoch": 19.17, + "learning_rate": 9.008950773161218e-08, + "loss": 0.0013, + "step": 62074 + }, + { + "epoch": 19.17, + "learning_rate": 9.002254023306234e-08, + "loss": 0.0015, + "step": 62075 + }, + { + "epoch": 19.17, + "learning_rate": 8.995559752117411e-08, + "loss": 0.0018, + "step": 62076 + }, + { + "epoch": 19.17, + "learning_rate": 8.988867959611403e-08, + "loss": 0.0015, + "step": 62077 + }, + { + "epoch": 19.17, + "learning_rate": 8.982178645804973e-08, + "loss": 0.0017, + "step": 62078 + }, + { + "epoch": 19.17, + "learning_rate": 8.975491810714887e-08, + "loss": 0.0012, + "step": 62079 + }, + { + "epoch": 19.17, + "learning_rate": 8.968807454357909e-08, + "loss": 0.0013, + "step": 62080 + }, + { + "epoch": 19.17, + "learning_rate": 8.96212557675058e-08, + "loss": 0.0011, + "step": 62081 + }, + { + "epoch": 19.17, + "learning_rate": 8.955446177909888e-08, + "loss": 0.0014, + "step": 62082 + }, + { + "epoch": 19.17, + "learning_rate": 8.948769257852153e-08, + "loss": 0.0014, + "step": 62083 + }, + { + "epoch": 19.17, + "learning_rate": 8.942094816594471e-08, + "loss": 0.0014, + "step": 62084 + }, + { + "epoch": 19.17, + "learning_rate": 8.935422854153387e-08, + "loss": 0.0019, + "step": 62085 + }, + { + "epoch": 19.17, + "learning_rate": 8.92875337054555e-08, + "loss": 0.001, + "step": 62086 + }, + { + "epoch": 19.17, + "learning_rate": 8.922086365787508e-08, + "loss": 0.002, + "step": 62087 + }, + { + "epoch": 19.17, + "learning_rate": 8.915421839896243e-08, + "loss": 0.0018, + "step": 62088 + }, + { + "epoch": 19.17, + "learning_rate": 8.908759792888189e-08, + "loss": 0.0021, + "step": 62089 + }, + { + "epoch": 19.17, + "learning_rate": 8.90210022478022e-08, + "loss": 0.0017, + "step": 62090 + }, + { + "epoch": 19.17, + "learning_rate": 8.895443135588766e-08, + "loss": 0.0012, + "step": 62091 + }, + { + "epoch": 19.18, + "learning_rate": 8.888788525330595e-08, + "loss": 0.0013, + "step": 62092 + }, + { + "epoch": 19.18, + "learning_rate": 8.882136394022245e-08, + "loss": 0.0011, + "step": 62093 + }, + { + "epoch": 19.18, + "learning_rate": 8.875486741680594e-08, + "loss": 0.0014, + "step": 62094 + }, + { + "epoch": 19.18, + "learning_rate": 8.868839568322074e-08, + "loss": 0.0014, + "step": 62095 + }, + { + "epoch": 19.18, + "learning_rate": 8.862194873963337e-08, + "loss": 0.0016, + "step": 62096 + }, + { + "epoch": 19.18, + "learning_rate": 8.855552658620925e-08, + "loss": 0.0015, + "step": 62097 + }, + { + "epoch": 19.18, + "learning_rate": 8.848912922311714e-08, + "loss": 0.0017, + "step": 62098 + }, + { + "epoch": 19.18, + "learning_rate": 8.842275665052024e-08, + "loss": 0.0015, + "step": 62099 + }, + { + "epoch": 19.18, + "learning_rate": 8.83564088685862e-08, + "loss": 0.0019, + "step": 62100 + }, + { + "epoch": 19.18, + "learning_rate": 8.829008587748155e-08, + "loss": 0.0015, + "step": 62101 + }, + { + "epoch": 19.18, + "learning_rate": 8.82237876773695e-08, + "loss": 0.0015, + "step": 62102 + }, + { + "epoch": 19.18, + "learning_rate": 8.815751426841878e-08, + "loss": 0.0012, + "step": 62103 + }, + { + "epoch": 19.18, + "learning_rate": 8.809126565079373e-08, + "loss": 0.0013, + "step": 62104 + }, + { + "epoch": 19.18, + "learning_rate": 8.802504182465976e-08, + "loss": 0.0017, + "step": 62105 + }, + { + "epoch": 19.18, + "learning_rate": 8.79588427901834e-08, + "loss": 0.0019, + "step": 62106 + }, + { + "epoch": 19.18, + "learning_rate": 8.789266854752898e-08, + "loss": 0.0012, + "step": 62107 + }, + { + "epoch": 19.18, + "learning_rate": 8.782651909686413e-08, + "loss": 0.0016, + "step": 62108 + }, + { + "epoch": 19.18, + "learning_rate": 8.776039443835204e-08, + "loss": 0.0012, + "step": 62109 + }, + { + "epoch": 19.18, + "learning_rate": 8.769429457215928e-08, + "loss": 0.0009, + "step": 62110 + }, + { + "epoch": 19.18, + "learning_rate": 8.762821949845124e-08, + "loss": 0.0016, + "step": 62111 + }, + { + "epoch": 19.18, + "learning_rate": 8.756216921739224e-08, + "loss": 0.0016, + "step": 62112 + }, + { + "epoch": 19.18, + "learning_rate": 8.749614372914994e-08, + "loss": 0.0019, + "step": 62113 + }, + { + "epoch": 19.18, + "learning_rate": 8.74301430338853e-08, + "loss": 0.0012, + "step": 62114 + }, + { + "epoch": 19.18, + "learning_rate": 8.73641671317682e-08, + "loss": 0.0015, + "step": 62115 + }, + { + "epoch": 19.18, + "learning_rate": 8.729821602295963e-08, + "loss": 0.0016, + "step": 62116 + }, + { + "epoch": 19.18, + "learning_rate": 8.72322897076272e-08, + "loss": 0.0016, + "step": 62117 + }, + { + "epoch": 19.18, + "learning_rate": 8.716638818593304e-08, + "loss": 0.0014, + "step": 62118 + }, + { + "epoch": 19.18, + "learning_rate": 8.710051145804588e-08, + "loss": 0.0014, + "step": 62119 + }, + { + "epoch": 19.18, + "learning_rate": 8.703465952412671e-08, + "loss": 0.002, + "step": 62120 + }, + { + "epoch": 19.18, + "learning_rate": 8.696883238434317e-08, + "loss": 0.0015, + "step": 62121 + }, + { + "epoch": 19.18, + "learning_rate": 8.690303003885847e-08, + "loss": 0.0016, + "step": 62122 + }, + { + "epoch": 19.18, + "learning_rate": 8.683725248783581e-08, + "loss": 0.0014, + "step": 62123 + }, + { + "epoch": 19.18, + "learning_rate": 8.677149973144283e-08, + "loss": 0.0014, + "step": 62124 + }, + { + "epoch": 19.19, + "learning_rate": 8.670577176984163e-08, + "loss": 0.0022, + "step": 62125 + }, + { + "epoch": 19.19, + "learning_rate": 8.664006860319762e-08, + "loss": 0.002, + "step": 62126 + }, + { + "epoch": 19.19, + "learning_rate": 8.657439023167513e-08, + "loss": 0.0013, + "step": 62127 + }, + { + "epoch": 19.19, + "learning_rate": 8.650873665543736e-08, + "loss": 0.0011, + "step": 62128 + }, + { + "epoch": 19.19, + "learning_rate": 8.644310787464971e-08, + "loss": 0.0019, + "step": 62129 + }, + { + "epoch": 19.19, + "learning_rate": 8.637750388947652e-08, + "loss": 0.0015, + "step": 62130 + }, + { + "epoch": 19.19, + "learning_rate": 8.631192470008099e-08, + "loss": 0.0013, + "step": 62131 + }, + { + "epoch": 19.19, + "learning_rate": 8.624637030662742e-08, + "loss": 0.0014, + "step": 62132 + }, + { + "epoch": 19.19, + "learning_rate": 8.618084070928012e-08, + "loss": 0.0015, + "step": 62133 + }, + { + "epoch": 19.19, + "learning_rate": 8.61153359082012e-08, + "loss": 0.0014, + "step": 62134 + }, + { + "epoch": 19.19, + "learning_rate": 8.60498559035583e-08, + "loss": 0.0013, + "step": 62135 + }, + { + "epoch": 19.19, + "learning_rate": 8.598440069551128e-08, + "loss": 0.0014, + "step": 62136 + }, + { + "epoch": 19.19, + "learning_rate": 8.591897028422668e-08, + "loss": 0.0013, + "step": 62137 + }, + { + "epoch": 19.19, + "learning_rate": 8.58535646698655e-08, + "loss": 0.0016, + "step": 62138 + }, + { + "epoch": 19.19, + "learning_rate": 8.578818385259424e-08, + "loss": 0.0011, + "step": 62139 + }, + { + "epoch": 19.19, + "learning_rate": 8.572282783257391e-08, + "loss": 0.0019, + "step": 62140 + }, + { + "epoch": 19.19, + "learning_rate": 8.565749660996992e-08, + "loss": 0.0013, + "step": 62141 + }, + { + "epoch": 19.19, + "learning_rate": 8.559219018494435e-08, + "loss": 0.0017, + "step": 62142 + }, + { + "epoch": 19.19, + "learning_rate": 8.552690855766044e-08, + "loss": 0.0017, + "step": 62143 + }, + { + "epoch": 19.19, + "learning_rate": 8.546165172828247e-08, + "loss": 0.0011, + "step": 62144 + }, + { + "epoch": 19.19, + "learning_rate": 8.539641969697365e-08, + "loss": 0.0014, + "step": 62145 + }, + { + "epoch": 19.19, + "learning_rate": 8.533121246389608e-08, + "loss": 0.0015, + "step": 62146 + }, + { + "epoch": 19.19, + "learning_rate": 8.526603002921408e-08, + "loss": 0.0012, + "step": 62147 + }, + { + "epoch": 19.19, + "learning_rate": 8.520087239308972e-08, + "loss": 0.0009, + "step": 62148 + }, + { + "epoch": 19.19, + "learning_rate": 8.513573955568622e-08, + "loss": 0.0015, + "step": 62149 + }, + { + "epoch": 19.19, + "learning_rate": 8.507063151716677e-08, + "loss": 0.0012, + "step": 62150 + }, + { + "epoch": 19.19, + "learning_rate": 8.500554827769347e-08, + "loss": 0.0009, + "step": 62151 + }, + { + "epoch": 19.19, + "learning_rate": 8.494048983743064e-08, + "loss": 0.0017, + "step": 62152 + }, + { + "epoch": 19.19, + "learning_rate": 8.487545619653925e-08, + "loss": 0.0013, + "step": 62153 + }, + { + "epoch": 19.19, + "learning_rate": 8.481044735518251e-08, + "loss": 0.0017, + "step": 62154 + }, + { + "epoch": 19.19, + "learning_rate": 8.474546331352363e-08, + "loss": 0.0014, + "step": 62155 + }, + { + "epoch": 19.19, + "learning_rate": 8.468050407172579e-08, + "loss": 0.0012, + "step": 62156 + }, + { + "epoch": 19.2, + "learning_rate": 8.461556962994999e-08, + "loss": 0.0012, + "step": 62157 + }, + { + "epoch": 19.2, + "learning_rate": 8.455065998835832e-08, + "loss": 0.0016, + "step": 62158 + }, + { + "epoch": 19.2, + "learning_rate": 8.448577514711398e-08, + "loss": 0.002, + "step": 62159 + }, + { + "epoch": 19.2, + "learning_rate": 8.442091510638017e-08, + "loss": 0.0011, + "step": 62160 + }, + { + "epoch": 19.2, + "learning_rate": 8.435607986631678e-08, + "loss": 0.0013, + "step": 62161 + }, + { + "epoch": 19.2, + "learning_rate": 8.42912694270881e-08, + "loss": 0.0016, + "step": 62162 + }, + { + "epoch": 19.2, + "learning_rate": 8.422648378885623e-08, + "loss": 0.0013, + "step": 62163 + }, + { + "epoch": 19.2, + "learning_rate": 8.416172295178105e-08, + "loss": 0.0013, + "step": 62164 + }, + { + "epoch": 19.2, + "learning_rate": 8.409698691602574e-08, + "loss": 0.0016, + "step": 62165 + }, + { + "epoch": 19.2, + "learning_rate": 8.403227568175354e-08, + "loss": 0.0017, + "step": 62166 + }, + { + "epoch": 19.2, + "learning_rate": 8.39675892491254e-08, + "loss": 0.0013, + "step": 62167 + }, + { + "epoch": 19.2, + "learning_rate": 8.390292761830232e-08, + "loss": 0.0014, + "step": 62168 + }, + { + "epoch": 19.2, + "learning_rate": 8.383829078944639e-08, + "loss": 0.0019, + "step": 62169 + }, + { + "epoch": 19.2, + "learning_rate": 8.377367876271969e-08, + "loss": 0.0018, + "step": 62170 + }, + { + "epoch": 19.2, + "learning_rate": 8.370909153828322e-08, + "loss": 0.0016, + "step": 62171 + }, + { + "epoch": 19.2, + "learning_rate": 8.364452911630017e-08, + "loss": 0.0016, + "step": 62172 + }, + { + "epoch": 19.2, + "learning_rate": 8.357999149693041e-08, + "loss": 0.0017, + "step": 62173 + }, + { + "epoch": 19.2, + "learning_rate": 8.351547868033493e-08, + "loss": 0.0014, + "step": 62174 + }, + { + "epoch": 19.2, + "learning_rate": 8.345099066667584e-08, + "loss": 0.0013, + "step": 62175 + }, + { + "epoch": 19.2, + "learning_rate": 8.33865274561152e-08, + "loss": 0.0011, + "step": 62176 + }, + { + "epoch": 19.2, + "learning_rate": 8.33220890488129e-08, + "loss": 0.0018, + "step": 62177 + }, + { + "epoch": 19.2, + "learning_rate": 8.325767544493213e-08, + "loss": 0.0016, + "step": 62178 + }, + { + "epoch": 19.2, + "learning_rate": 8.319328664463056e-08, + "loss": 0.0014, + "step": 62179 + }, + { + "epoch": 19.2, + "learning_rate": 8.312892264807249e-08, + "loss": 0.0014, + "step": 62180 + }, + { + "epoch": 19.2, + "learning_rate": 8.306458345541779e-08, + "loss": 0.0015, + "step": 62181 + }, + { + "epoch": 19.2, + "learning_rate": 8.300026906682746e-08, + "loss": 0.0013, + "step": 62182 + }, + { + "epoch": 19.2, + "learning_rate": 8.293597948246135e-08, + "loss": 0.0019, + "step": 62183 + }, + { + "epoch": 19.2, + "learning_rate": 8.287171470248157e-08, + "loss": 0.0019, + "step": 62184 + }, + { + "epoch": 19.2, + "learning_rate": 8.280747472704797e-08, + "loss": 0.0015, + "step": 62185 + }, + { + "epoch": 19.2, + "learning_rate": 8.274325955632157e-08, + "loss": 0.0017, + "step": 62186 + }, + { + "epoch": 19.2, + "learning_rate": 8.267906919046442e-08, + "loss": 0.0015, + "step": 62187 + }, + { + "epoch": 19.2, + "learning_rate": 8.261490362963532e-08, + "loss": 0.0016, + "step": 62188 + }, + { + "epoch": 19.21, + "learning_rate": 8.25507628739941e-08, + "loss": 0.0014, + "step": 62189 + }, + { + "epoch": 19.21, + "learning_rate": 8.248664692370289e-08, + "loss": 0.0013, + "step": 62190 + }, + { + "epoch": 19.21, + "learning_rate": 8.242255577892156e-08, + "loss": 0.0018, + "step": 62191 + }, + { + "epoch": 19.21, + "learning_rate": 8.235848943980995e-08, + "loss": 0.0017, + "step": 62192 + }, + { + "epoch": 19.21, + "learning_rate": 8.229444790652907e-08, + "loss": 0.0016, + "step": 62193 + }, + { + "epoch": 19.21, + "learning_rate": 8.223043117923768e-08, + "loss": 0.0013, + "step": 62194 + }, + { + "epoch": 19.21, + "learning_rate": 8.216643925809786e-08, + "loss": 0.0018, + "step": 62195 + }, + { + "epoch": 19.21, + "learning_rate": 8.210247214326839e-08, + "loss": 0.0013, + "step": 62196 + }, + { + "epoch": 19.21, + "learning_rate": 8.203852983490912e-08, + "loss": 0.002, + "step": 62197 + }, + { + "epoch": 19.21, + "learning_rate": 8.197461233318104e-08, + "loss": 0.001, + "step": 62198 + }, + { + "epoch": 19.21, + "learning_rate": 8.191071963824294e-08, + "loss": 0.0011, + "step": 62199 + }, + { + "epoch": 19.21, + "learning_rate": 8.184685175025575e-08, + "loss": 0.0014, + "step": 62200 + }, + { + "epoch": 19.21, + "learning_rate": 8.178300866937827e-08, + "loss": 0.0018, + "step": 62201 + }, + { + "epoch": 19.21, + "learning_rate": 8.171919039577037e-08, + "loss": 0.0013, + "step": 62202 + }, + { + "epoch": 19.21, + "learning_rate": 8.16553969295919e-08, + "loss": 0.0013, + "step": 62203 + }, + { + "epoch": 19.21, + "learning_rate": 8.159162827100165e-08, + "loss": 0.0016, + "step": 62204 + }, + { + "epoch": 19.21, + "learning_rate": 8.152788442015946e-08, + "loss": 0.0017, + "step": 62205 + }, + { + "epoch": 19.21, + "learning_rate": 8.146416537722635e-08, + "loss": 0.0014, + "step": 62206 + }, + { + "epoch": 19.21, + "learning_rate": 8.140047114235883e-08, + "loss": 0.0011, + "step": 62207 + }, + { + "epoch": 19.21, + "learning_rate": 8.1336801715719e-08, + "loss": 0.0018, + "step": 62208 + }, + { + "epoch": 19.21, + "learning_rate": 8.127315709746564e-08, + "loss": 0.0015, + "step": 62209 + }, + { + "epoch": 19.21, + "learning_rate": 8.120953728775528e-08, + "loss": 0.0013, + "step": 62210 + }, + { + "epoch": 19.21, + "learning_rate": 8.114594228674999e-08, + "loss": 0.0019, + "step": 62211 + }, + { + "epoch": 19.21, + "learning_rate": 8.108237209460745e-08, + "loss": 0.0015, + "step": 62212 + }, + { + "epoch": 19.21, + "learning_rate": 8.101882671148753e-08, + "loss": 0.0014, + "step": 62213 + }, + { + "epoch": 19.21, + "learning_rate": 8.095530613754788e-08, + "loss": 0.0015, + "step": 62214 + }, + { + "epoch": 19.21, + "learning_rate": 8.089181037294835e-08, + "loss": 0.0016, + "step": 62215 + }, + { + "epoch": 19.21, + "learning_rate": 8.082833941784773e-08, + "loss": 0.0017, + "step": 62216 + }, + { + "epoch": 19.21, + "learning_rate": 8.076489327240478e-08, + "loss": 0.0023, + "step": 62217 + }, + { + "epoch": 19.21, + "learning_rate": 8.070147193677714e-08, + "loss": 0.0017, + "step": 62218 + }, + { + "epoch": 19.21, + "learning_rate": 8.063807541112578e-08, + "loss": 0.0013, + "step": 62219 + }, + { + "epoch": 19.21, + "learning_rate": 8.057470369560615e-08, + "loss": 0.0013, + "step": 62220 + }, + { + "epoch": 19.21, + "learning_rate": 8.051135679037925e-08, + "loss": 0.0012, + "step": 62221 + }, + { + "epoch": 19.22, + "learning_rate": 8.04480346956027e-08, + "loss": 0.001, + "step": 62222 + }, + { + "epoch": 19.22, + "learning_rate": 8.038473741143416e-08, + "loss": 0.0014, + "step": 62223 + }, + { + "epoch": 19.22, + "learning_rate": 8.03214649380335e-08, + "loss": 0.0014, + "step": 62224 + }, + { + "epoch": 19.22, + "learning_rate": 8.025821727555727e-08, + "loss": 0.0014, + "step": 62225 + }, + { + "epoch": 19.22, + "learning_rate": 8.019499442416534e-08, + "loss": 0.0016, + "step": 62226 + }, + { + "epoch": 19.22, + "learning_rate": 8.013179638401425e-08, + "loss": 0.002, + "step": 62227 + }, + { + "epoch": 19.22, + "learning_rate": 8.006862315526276e-08, + "loss": 0.0017, + "step": 62228 + }, + { + "epoch": 19.22, + "learning_rate": 8.000547473806963e-08, + "loss": 0.0019, + "step": 62229 + }, + { + "epoch": 19.22, + "learning_rate": 7.99423511325914e-08, + "loss": 0.0018, + "step": 62230 + }, + { + "epoch": 19.22, + "learning_rate": 7.987925233898797e-08, + "loss": 0.0012, + "step": 62231 + }, + { + "epoch": 19.22, + "learning_rate": 7.981617835741361e-08, + "loss": 0.0013, + "step": 62232 + }, + { + "epoch": 19.22, + "learning_rate": 7.975312918803047e-08, + "loss": 0.0015, + "step": 62233 + }, + { + "epoch": 19.22, + "learning_rate": 7.969010483099282e-08, + "loss": 0.0016, + "step": 62234 + }, + { + "epoch": 19.22, + "learning_rate": 7.962710528646056e-08, + "loss": 0.0011, + "step": 62235 + }, + { + "epoch": 19.22, + "learning_rate": 7.956413055458911e-08, + "loss": 0.0014, + "step": 62236 + }, + { + "epoch": 19.22, + "learning_rate": 7.950118063553725e-08, + "loss": 0.0021, + "step": 62237 + }, + { + "epoch": 19.22, + "learning_rate": 7.94382555294626e-08, + "loss": 0.0011, + "step": 62238 + }, + { + "epoch": 19.22, + "learning_rate": 7.937535523652284e-08, + "loss": 0.001, + "step": 62239 + }, + { + "epoch": 19.22, + "learning_rate": 7.93124797568745e-08, + "loss": 0.0012, + "step": 62240 + }, + { + "epoch": 19.22, + "learning_rate": 7.924962909067524e-08, + "loss": 0.0018, + "step": 62241 + }, + { + "epoch": 19.22, + "learning_rate": 7.918680323808048e-08, + "loss": 0.0013, + "step": 62242 + }, + { + "epoch": 19.22, + "learning_rate": 7.912400219925121e-08, + "loss": 0.0014, + "step": 62243 + }, + { + "epoch": 19.22, + "learning_rate": 7.906122597434174e-08, + "loss": 0.0014, + "step": 62244 + }, + { + "epoch": 19.22, + "learning_rate": 7.899847456350862e-08, + "loss": 0.0014, + "step": 62245 + }, + { + "epoch": 19.22, + "learning_rate": 7.893574796691062e-08, + "loss": 0.0022, + "step": 62246 + }, + { + "epoch": 19.22, + "learning_rate": 7.887304618470315e-08, + "loss": 0.0013, + "step": 62247 + }, + { + "epoch": 19.22, + "learning_rate": 7.881036921704389e-08, + "loss": 0.0018, + "step": 62248 + }, + { + "epoch": 19.22, + "learning_rate": 7.874771706408935e-08, + "loss": 0.0009, + "step": 62249 + }, + { + "epoch": 19.22, + "learning_rate": 7.86850897259972e-08, + "loss": 0.0013, + "step": 62250 + }, + { + "epoch": 19.22, + "learning_rate": 7.862248720292176e-08, + "loss": 0.0011, + "step": 62251 + }, + { + "epoch": 19.22, + "learning_rate": 7.855990949502179e-08, + "loss": 0.0017, + "step": 62252 + }, + { + "epoch": 19.22, + "learning_rate": 7.849735660245273e-08, + "loss": 0.0013, + "step": 62253 + }, + { + "epoch": 19.23, + "learning_rate": 7.843482852537221e-08, + "loss": 0.0013, + "step": 62254 + }, + { + "epoch": 19.23, + "learning_rate": 7.837232526393567e-08, + "loss": 0.0015, + "step": 62255 + }, + { + "epoch": 19.23, + "learning_rate": 7.830984681829856e-08, + "loss": 0.0014, + "step": 62256 + }, + { + "epoch": 19.23, + "learning_rate": 7.824739318861851e-08, + "loss": 0.0016, + "step": 62257 + }, + { + "epoch": 19.23, + "learning_rate": 7.818496437505097e-08, + "loss": 0.0012, + "step": 62258 + }, + { + "epoch": 19.23, + "learning_rate": 7.812256037775357e-08, + "loss": 0.0023, + "step": 62259 + }, + { + "epoch": 19.23, + "learning_rate": 7.806018119688064e-08, + "loss": 0.0014, + "step": 62260 + }, + { + "epoch": 19.23, + "learning_rate": 7.799782683258872e-08, + "loss": 0.0011, + "step": 62261 + }, + { + "epoch": 19.23, + "learning_rate": 7.793549728503436e-08, + "loss": 0.0011, + "step": 62262 + }, + { + "epoch": 19.23, + "learning_rate": 7.787319255437187e-08, + "loss": 0.0015, + "step": 62263 + }, + { + "epoch": 19.23, + "learning_rate": 7.781091264076002e-08, + "loss": 0.0018, + "step": 62264 + }, + { + "epoch": 19.23, + "learning_rate": 7.774865754435201e-08, + "loss": 0.0029, + "step": 62265 + }, + { + "epoch": 19.23, + "learning_rate": 7.768642726530329e-08, + "loss": 0.0019, + "step": 62266 + }, + { + "epoch": 19.23, + "learning_rate": 7.76242218037715e-08, + "loss": 0.0013, + "step": 62267 + }, + { + "epoch": 19.23, + "learning_rate": 7.756204115991095e-08, + "loss": 0.0017, + "step": 62268 + }, + { + "epoch": 19.23, + "learning_rate": 7.749988533387709e-08, + "loss": 0.0013, + "step": 62269 + }, + { + "epoch": 19.23, + "learning_rate": 7.743775432582646e-08, + "loss": 0.0022, + "step": 62270 + }, + { + "epoch": 19.23, + "learning_rate": 7.737564813591447e-08, + "loss": 0.0011, + "step": 62271 + }, + { + "epoch": 19.23, + "learning_rate": 7.731356676429436e-08, + "loss": 0.0018, + "step": 62272 + }, + { + "epoch": 19.23, + "learning_rate": 7.725151021112265e-08, + "loss": 0.0017, + "step": 62273 + }, + { + "epoch": 19.23, + "learning_rate": 7.71894784765559e-08, + "loss": 0.0011, + "step": 62274 + }, + { + "epoch": 19.23, + "learning_rate": 7.712747156074729e-08, + "loss": 0.0021, + "step": 62275 + }, + { + "epoch": 19.23, + "learning_rate": 7.70654894638534e-08, + "loss": 0.002, + "step": 62276 + }, + { + "epoch": 19.23, + "learning_rate": 7.70035321860274e-08, + "loss": 0.0012, + "step": 62277 + }, + { + "epoch": 19.23, + "learning_rate": 7.694159972742588e-08, + "loss": 0.0019, + "step": 62278 + }, + { + "epoch": 19.23, + "learning_rate": 7.687969208820312e-08, + "loss": 0.0013, + "step": 62279 + }, + { + "epoch": 19.23, + "learning_rate": 7.681780926851568e-08, + "loss": 0.0014, + "step": 62280 + }, + { + "epoch": 19.23, + "learning_rate": 7.675595126851565e-08, + "loss": 0.0013, + "step": 62281 + }, + { + "epoch": 19.23, + "learning_rate": 7.669411808835847e-08, + "loss": 0.0015, + "step": 62282 + }, + { + "epoch": 19.23, + "learning_rate": 7.663230972819958e-08, + "loss": 0.0012, + "step": 62283 + }, + { + "epoch": 19.23, + "learning_rate": 7.657052618819327e-08, + "loss": 0.0011, + "step": 62284 + }, + { + "epoch": 19.23, + "learning_rate": 7.65087674684939e-08, + "loss": 0.0021, + "step": 62285 + }, + { + "epoch": 19.24, + "learning_rate": 7.644703356925576e-08, + "loss": 0.0015, + "step": 62286 + }, + { + "epoch": 19.24, + "learning_rate": 7.63853244906343e-08, + "loss": 0.0014, + "step": 62287 + }, + { + "epoch": 19.24, + "learning_rate": 7.63236402327816e-08, + "loss": 0.002, + "step": 62288 + }, + { + "epoch": 19.24, + "learning_rate": 7.626198079585534e-08, + "loss": 0.0016, + "step": 62289 + }, + { + "epoch": 19.24, + "learning_rate": 7.620034618000648e-08, + "loss": 0.0011, + "step": 62290 + }, + { + "epoch": 19.24, + "learning_rate": 7.613873638539049e-08, + "loss": 0.0014, + "step": 62291 + }, + { + "epoch": 19.24, + "learning_rate": 7.607715141216166e-08, + "loss": 0.002, + "step": 62292 + }, + { + "epoch": 19.24, + "learning_rate": 7.601559126047543e-08, + "loss": 0.0013, + "step": 62293 + }, + { + "epoch": 19.24, + "learning_rate": 7.595405593048277e-08, + "loss": 0.0017, + "step": 62294 + }, + { + "epoch": 19.24, + "learning_rate": 7.589254542233914e-08, + "loss": 0.0013, + "step": 62295 + }, + { + "epoch": 19.24, + "learning_rate": 7.583105973619886e-08, + "loss": 0.002, + "step": 62296 + }, + { + "epoch": 19.24, + "learning_rate": 7.576959887221403e-08, + "loss": 0.0012, + "step": 62297 + }, + { + "epoch": 19.24, + "learning_rate": 7.570816283054005e-08, + "loss": 0.0018, + "step": 62298 + }, + { + "epoch": 19.24, + "learning_rate": 7.564675161133017e-08, + "loss": 0.0013, + "step": 62299 + }, + { + "epoch": 19.24, + "learning_rate": 7.558536521473869e-08, + "loss": 0.0014, + "step": 62300 + }, + { + "epoch": 19.24, + "learning_rate": 7.55240036409166e-08, + "loss": 0.0015, + "step": 62301 + }, + { + "epoch": 19.24, + "learning_rate": 7.546266689002046e-08, + "loss": 0.0015, + "step": 62302 + }, + { + "epoch": 19.24, + "learning_rate": 7.540135496220235e-08, + "loss": 0.0016, + "step": 62303 + }, + { + "epoch": 19.24, + "learning_rate": 7.534006785761439e-08, + "loss": 0.0014, + "step": 62304 + }, + { + "epoch": 19.24, + "learning_rate": 7.527880557641198e-08, + "loss": 0.002, + "step": 62305 + }, + { + "epoch": 19.24, + "learning_rate": 7.521756811874726e-08, + "loss": 0.0012, + "step": 62306 + }, + { + "epoch": 19.24, + "learning_rate": 7.51563554847734e-08, + "loss": 0.0013, + "step": 62307 + }, + { + "epoch": 19.24, + "learning_rate": 7.509516767464365e-08, + "loss": 0.0019, + "step": 62308 + }, + { + "epoch": 19.24, + "learning_rate": 7.503400468851119e-08, + "loss": 0.0014, + "step": 62309 + }, + { + "epoch": 19.24, + "learning_rate": 7.497286652652924e-08, + "loss": 0.0016, + "step": 62310 + }, + { + "epoch": 19.24, + "learning_rate": 7.491175318885102e-08, + "loss": 0.0012, + "step": 62311 + }, + { + "epoch": 19.24, + "learning_rate": 7.485066467562752e-08, + "loss": 0.0015, + "step": 62312 + }, + { + "epoch": 19.24, + "learning_rate": 7.478960098701193e-08, + "loss": 0.002, + "step": 62313 + }, + { + "epoch": 19.24, + "learning_rate": 7.472856212315971e-08, + "loss": 0.0017, + "step": 62314 + }, + { + "epoch": 19.24, + "learning_rate": 7.46675480842196e-08, + "loss": 0.0018, + "step": 62315 + }, + { + "epoch": 19.24, + "learning_rate": 7.460655887034818e-08, + "loss": 0.0012, + "step": 62316 + }, + { + "epoch": 19.24, + "learning_rate": 7.45455944816953e-08, + "loss": 0.0015, + "step": 62317 + }, + { + "epoch": 19.24, + "learning_rate": 7.448465491841417e-08, + "loss": 0.0011, + "step": 62318 + }, + { + "epoch": 19.25, + "learning_rate": 7.44237401806569e-08, + "loss": 0.0016, + "step": 62319 + }, + { + "epoch": 19.25, + "learning_rate": 7.43628502685767e-08, + "loss": 0.0014, + "step": 62320 + }, + { + "epoch": 19.25, + "learning_rate": 7.430198518232457e-08, + "loss": 0.0013, + "step": 62321 + }, + { + "epoch": 19.25, + "learning_rate": 7.42411449220537e-08, + "loss": 0.0015, + "step": 62322 + }, + { + "epoch": 19.25, + "learning_rate": 7.41803294879162e-08, + "loss": 0.0011, + "step": 62323 + }, + { + "epoch": 19.25, + "learning_rate": 7.411953888006528e-08, + "loss": 0.0015, + "step": 62324 + }, + { + "epoch": 19.25, + "learning_rate": 7.405877309864973e-08, + "loss": 0.0015, + "step": 62325 + }, + { + "epoch": 19.25, + "learning_rate": 7.399803214382495e-08, + "loss": 0.0015, + "step": 62326 + }, + { + "epoch": 19.25, + "learning_rate": 7.393731601574194e-08, + "loss": 0.0022, + "step": 62327 + }, + { + "epoch": 19.25, + "learning_rate": 7.38766247145506e-08, + "loss": 0.0015, + "step": 62328 + }, + { + "epoch": 19.25, + "learning_rate": 7.381595824040411e-08, + "loss": 0.0015, + "step": 62329 + }, + { + "epoch": 19.25, + "learning_rate": 7.37553165934557e-08, + "loss": 0.0015, + "step": 62330 + }, + { + "epoch": 19.25, + "learning_rate": 7.369469977385524e-08, + "loss": 0.001, + "step": 62331 + }, + { + "epoch": 19.25, + "learning_rate": 7.363410778175483e-08, + "loss": 0.0016, + "step": 62332 + }, + { + "epoch": 19.25, + "learning_rate": 7.357354061730548e-08, + "loss": 0.0015, + "step": 62333 + }, + { + "epoch": 19.25, + "learning_rate": 7.351299828065928e-08, + "loss": 0.0017, + "step": 62334 + }, + { + "epoch": 19.25, + "learning_rate": 7.34524807719672e-08, + "loss": 0.0018, + "step": 62335 + }, + { + "epoch": 19.25, + "learning_rate": 7.339198809138138e-08, + "loss": 0.0014, + "step": 62336 + }, + { + "epoch": 19.25, + "learning_rate": 7.333152023905388e-08, + "loss": 0.0014, + "step": 62337 + }, + { + "epoch": 19.25, + "learning_rate": 7.327107721513349e-08, + "loss": 0.0013, + "step": 62338 + }, + { + "epoch": 19.25, + "learning_rate": 7.321065901977232e-08, + "loss": 0.0016, + "step": 62339 + }, + { + "epoch": 19.25, + "learning_rate": 7.315026565312245e-08, + "loss": 0.0014, + "step": 62340 + }, + { + "epoch": 19.25, + "learning_rate": 7.308989711533488e-08, + "loss": 0.0016, + "step": 62341 + }, + { + "epoch": 19.25, + "learning_rate": 7.302955340655949e-08, + "loss": 0.0012, + "step": 62342 + }, + { + "epoch": 19.25, + "learning_rate": 7.296923452694727e-08, + "loss": 0.0015, + "step": 62343 + }, + { + "epoch": 19.25, + "learning_rate": 7.29089404766492e-08, + "loss": 0.0017, + "step": 62344 + }, + { + "epoch": 19.25, + "learning_rate": 7.28486712558174e-08, + "loss": 0.0015, + "step": 62345 + }, + { + "epoch": 19.25, + "learning_rate": 7.278842686460175e-08, + "loss": 0.0013, + "step": 62346 + }, + { + "epoch": 19.25, + "learning_rate": 7.272820730315211e-08, + "loss": 0.001, + "step": 62347 + }, + { + "epoch": 19.25, + "learning_rate": 7.26680125716206e-08, + "loss": 0.002, + "step": 62348 + }, + { + "epoch": 19.25, + "learning_rate": 7.260784267015708e-08, + "loss": 0.002, + "step": 62349 + }, + { + "epoch": 19.25, + "learning_rate": 7.254769759891034e-08, + "loss": 0.0011, + "step": 62350 + }, + { + "epoch": 19.26, + "learning_rate": 7.24875773580347e-08, + "loss": 0.0017, + "step": 62351 + }, + { + "epoch": 19.26, + "learning_rate": 7.242748194767779e-08, + "loss": 0.0018, + "step": 62352 + }, + { + "epoch": 19.26, + "learning_rate": 7.236741136798953e-08, + "loss": 0.0016, + "step": 62353 + }, + { + "epoch": 19.26, + "learning_rate": 7.230736561912199e-08, + "loss": 0.0011, + "step": 62354 + }, + { + "epoch": 19.26, + "learning_rate": 7.224734470122286e-08, + "loss": 0.0018, + "step": 62355 + }, + { + "epoch": 19.26, + "learning_rate": 7.218734861444532e-08, + "loss": 0.0015, + "step": 62356 + }, + { + "epoch": 19.26, + "learning_rate": 7.212737735893704e-08, + "loss": 0.0014, + "step": 62357 + }, + { + "epoch": 19.26, + "learning_rate": 7.206743093485014e-08, + "loss": 0.0011, + "step": 62358 + }, + { + "epoch": 19.26, + "learning_rate": 7.200750934233225e-08, + "loss": 0.0015, + "step": 62359 + }, + { + "epoch": 19.26, + "learning_rate": 7.194761258153437e-08, + "loss": 0.0014, + "step": 62360 + }, + { + "epoch": 19.26, + "learning_rate": 7.188774065260639e-08, + "loss": 0.0024, + "step": 62361 + }, + { + "epoch": 19.26, + "learning_rate": 7.18278935556993e-08, + "loss": 0.0014, + "step": 62362 + }, + { + "epoch": 19.26, + "learning_rate": 7.176807129095965e-08, + "loss": 0.0011, + "step": 62363 + }, + { + "epoch": 19.26, + "learning_rate": 7.170827385853951e-08, + "loss": 0.0013, + "step": 62364 + }, + { + "epoch": 19.26, + "learning_rate": 7.164850125858768e-08, + "loss": 0.0012, + "step": 62365 + }, + { + "epoch": 19.26, + "learning_rate": 7.158875349125294e-08, + "loss": 0.001, + "step": 62366 + }, + { + "epoch": 19.26, + "learning_rate": 7.152903055668736e-08, + "loss": 0.0023, + "step": 62367 + }, + { + "epoch": 19.26, + "learning_rate": 7.146933245503751e-08, + "loss": 0.0011, + "step": 62368 + }, + { + "epoch": 19.26, + "learning_rate": 7.140965918645326e-08, + "loss": 0.0015, + "step": 62369 + }, + { + "epoch": 19.26, + "learning_rate": 7.13500107510856e-08, + "loss": 0.0012, + "step": 62370 + }, + { + "epoch": 19.26, + "learning_rate": 7.12903871490811e-08, + "loss": 0.0016, + "step": 62371 + }, + { + "epoch": 19.26, + "learning_rate": 7.123078838059183e-08, + "loss": 0.002, + "step": 62372 + }, + { + "epoch": 19.26, + "learning_rate": 7.117121444576435e-08, + "loss": 0.0018, + "step": 62373 + }, + { + "epoch": 19.26, + "learning_rate": 7.111166534474745e-08, + "loss": 0.001, + "step": 62374 + }, + { + "epoch": 19.26, + "learning_rate": 7.10521410776921e-08, + "loss": 0.0011, + "step": 62375 + }, + { + "epoch": 19.26, + "learning_rate": 7.099264164474707e-08, + "loss": 0.0018, + "step": 62376 + }, + { + "epoch": 19.26, + "learning_rate": 7.09331670460589e-08, + "loss": 0.0013, + "step": 62377 + }, + { + "epoch": 19.26, + "learning_rate": 7.087371728177972e-08, + "loss": 0.0013, + "step": 62378 + }, + { + "epoch": 19.26, + "learning_rate": 7.081429235205495e-08, + "loss": 0.0016, + "step": 62379 + }, + { + "epoch": 19.26, + "learning_rate": 7.075489225703447e-08, + "loss": 0.0012, + "step": 62380 + }, + { + "epoch": 19.26, + "learning_rate": 7.069551699686706e-08, + "loss": 0.0013, + "step": 62381 + }, + { + "epoch": 19.26, + "learning_rate": 7.063616657170258e-08, + "loss": 0.0011, + "step": 62382 + }, + { + "epoch": 19.26, + "learning_rate": 7.057684098168649e-08, + "loss": 0.0011, + "step": 62383 + }, + { + "epoch": 19.27, + "learning_rate": 7.051754022696867e-08, + "loss": 0.0014, + "step": 62384 + }, + { + "epoch": 19.27, + "learning_rate": 7.045826430769897e-08, + "loss": 0.0016, + "step": 62385 + }, + { + "epoch": 19.27, + "learning_rate": 7.039901322402288e-08, + "loss": 0.0012, + "step": 62386 + }, + { + "epoch": 19.27, + "learning_rate": 7.033978697609023e-08, + "loss": 0.002, + "step": 62387 + }, + { + "epoch": 19.27, + "learning_rate": 7.028058556404871e-08, + "loss": 0.0013, + "step": 62388 + }, + { + "epoch": 19.27, + "learning_rate": 7.022140898804707e-08, + "loss": 0.0015, + "step": 62389 + }, + { + "epoch": 19.27, + "learning_rate": 7.01622572482319e-08, + "loss": 0.001, + "step": 62390 + }, + { + "epoch": 19.27, + "learning_rate": 7.010313034475302e-08, + "loss": 0.002, + "step": 62391 + }, + { + "epoch": 19.27, + "learning_rate": 7.004402827775703e-08, + "loss": 0.0012, + "step": 62392 + }, + { + "epoch": 19.27, + "learning_rate": 6.998495104739155e-08, + "loss": 0.0014, + "step": 62393 + }, + { + "epoch": 19.27, + "learning_rate": 6.992589865380428e-08, + "loss": 0.0014, + "step": 62394 + }, + { + "epoch": 19.27, + "learning_rate": 6.986687109714508e-08, + "loss": 0.0015, + "step": 62395 + }, + { + "epoch": 19.27, + "learning_rate": 6.980786837755937e-08, + "loss": 0.0015, + "step": 62396 + }, + { + "epoch": 19.27, + "learning_rate": 6.974889049519485e-08, + "loss": 0.0017, + "step": 62397 + }, + { + "epoch": 19.27, + "learning_rate": 6.968993745019914e-08, + "loss": 0.0014, + "step": 62398 + }, + { + "epoch": 19.27, + "learning_rate": 6.963100924272104e-08, + "loss": 0.0014, + "step": 62399 + }, + { + "epoch": 19.27, + "learning_rate": 6.957210587290708e-08, + "loss": 0.001, + "step": 62400 + }, + { + "epoch": 19.27, + "learning_rate": 6.951322734090383e-08, + "loss": 0.0012, + "step": 62401 + }, + { + "epoch": 19.27, + "learning_rate": 6.945437364685892e-08, + "loss": 0.0018, + "step": 62402 + }, + { + "epoch": 19.27, + "learning_rate": 6.939554479092114e-08, + "loss": 0.0012, + "step": 62403 + }, + { + "epoch": 19.27, + "learning_rate": 6.933674077323593e-08, + "loss": 0.0013, + "step": 62404 + }, + { + "epoch": 19.27, + "learning_rate": 6.927796159394984e-08, + "loss": 0.0015, + "step": 62405 + }, + { + "epoch": 19.27, + "learning_rate": 6.921920725321163e-08, + "loss": 0.0012, + "step": 62406 + }, + { + "epoch": 19.27, + "learning_rate": 6.916047775116674e-08, + "loss": 0.002, + "step": 62407 + }, + { + "epoch": 19.27, + "learning_rate": 6.910177308796284e-08, + "loss": 0.0016, + "step": 62408 + }, + { + "epoch": 19.27, + "learning_rate": 6.904309326374758e-08, + "loss": 0.0012, + "step": 62409 + }, + { + "epoch": 19.27, + "learning_rate": 6.89844382786664e-08, + "loss": 0.0013, + "step": 62410 + }, + { + "epoch": 19.27, + "learning_rate": 6.892580813286586e-08, + "loss": 0.0014, + "step": 62411 + }, + { + "epoch": 19.27, + "learning_rate": 6.886720282649361e-08, + "loss": 0.0014, + "step": 62412 + }, + { + "epoch": 19.27, + "learning_rate": 6.88086223596962e-08, + "loss": 0.0012, + "step": 62413 + }, + { + "epoch": 19.27, + "learning_rate": 6.875006673262019e-08, + "loss": 0.0012, + "step": 62414 + }, + { + "epoch": 19.27, + "learning_rate": 6.869153594540989e-08, + "loss": 0.0015, + "step": 62415 + }, + { + "epoch": 19.28, + "learning_rate": 6.863302999821519e-08, + "loss": 0.0014, + "step": 62416 + }, + { + "epoch": 19.28, + "learning_rate": 6.857454889117932e-08, + "loss": 0.0011, + "step": 62417 + }, + { + "epoch": 19.28, + "learning_rate": 6.851609262444991e-08, + "loss": 0.0015, + "step": 62418 + }, + { + "epoch": 19.28, + "learning_rate": 6.845766119817465e-08, + "loss": 0.0017, + "step": 62419 + }, + { + "epoch": 19.28, + "learning_rate": 6.839925461249675e-08, + "loss": 0.0018, + "step": 62420 + }, + { + "epoch": 19.28, + "learning_rate": 6.834087286756386e-08, + "loss": 0.0017, + "step": 62421 + }, + { + "epoch": 19.28, + "learning_rate": 6.828251596352253e-08, + "loss": 0.0014, + "step": 62422 + }, + { + "epoch": 19.28, + "learning_rate": 6.822418390051821e-08, + "loss": 0.0012, + "step": 62423 + }, + { + "epoch": 19.28, + "learning_rate": 6.816587667869634e-08, + "loss": 0.0012, + "step": 62424 + }, + { + "epoch": 19.28, + "learning_rate": 6.810759429820236e-08, + "loss": 0.0014, + "step": 62425 + }, + { + "epoch": 19.28, + "learning_rate": 6.804933675918391e-08, + "loss": 0.0024, + "step": 62426 + }, + { + "epoch": 19.28, + "learning_rate": 6.799110406178422e-08, + "loss": 0.0018, + "step": 62427 + }, + { + "epoch": 19.28, + "learning_rate": 6.793289620615095e-08, + "loss": 0.0016, + "step": 62428 + }, + { + "epoch": 19.28, + "learning_rate": 6.787471319242955e-08, + "loss": 0.0011, + "step": 62429 + }, + { + "epoch": 19.28, + "learning_rate": 6.781655502076434e-08, + "loss": 0.0014, + "step": 62430 + }, + { + "epoch": 19.28, + "learning_rate": 6.775842169130076e-08, + "loss": 0.0015, + "step": 62431 + }, + { + "epoch": 19.28, + "learning_rate": 6.770031320418646e-08, + "loss": 0.0012, + "step": 62432 + }, + { + "epoch": 19.28, + "learning_rate": 6.764222955956357e-08, + "loss": 0.0015, + "step": 62433 + }, + { + "epoch": 19.28, + "learning_rate": 6.758417075758084e-08, + "loss": 0.0019, + "step": 62434 + }, + { + "epoch": 19.28, + "learning_rate": 6.752613679838038e-08, + "loss": 0.0022, + "step": 62435 + }, + { + "epoch": 19.28, + "learning_rate": 6.746812768210875e-08, + "loss": 0.0016, + "step": 62436 + }, + { + "epoch": 19.28, + "learning_rate": 6.741014340891138e-08, + "loss": 0.0015, + "step": 62437 + }, + { + "epoch": 19.28, + "learning_rate": 6.735218397893262e-08, + "loss": 0.0016, + "step": 62438 + }, + { + "epoch": 19.28, + "learning_rate": 6.729424939231788e-08, + "loss": 0.0011, + "step": 62439 + }, + { + "epoch": 19.28, + "learning_rate": 6.72363396492104e-08, + "loss": 0.0014, + "step": 62440 + }, + { + "epoch": 19.28, + "learning_rate": 6.717845474975782e-08, + "loss": 0.0016, + "step": 62441 + }, + { + "epoch": 19.28, + "learning_rate": 6.712059469410336e-08, + "loss": 0.0013, + "step": 62442 + }, + { + "epoch": 19.28, + "learning_rate": 6.706275948239139e-08, + "loss": 0.0023, + "step": 62443 + }, + { + "epoch": 19.28, + "learning_rate": 6.700494911476841e-08, + "loss": 0.0011, + "step": 62444 + }, + { + "epoch": 19.28, + "learning_rate": 6.694716359137764e-08, + "loss": 0.001, + "step": 62445 + }, + { + "epoch": 19.28, + "learning_rate": 6.688940291236235e-08, + "loss": 0.0011, + "step": 62446 + }, + { + "epoch": 19.28, + "learning_rate": 6.683166707786903e-08, + "loss": 0.0014, + "step": 62447 + }, + { + "epoch": 19.29, + "learning_rate": 6.677395608804093e-08, + "loss": 0.0016, + "step": 62448 + }, + { + "epoch": 19.29, + "learning_rate": 6.67162699430235e-08, + "loss": 0.0015, + "step": 62449 + }, + { + "epoch": 19.29, + "learning_rate": 6.665860864296103e-08, + "loss": 0.0013, + "step": 62450 + }, + { + "epoch": 19.29, + "learning_rate": 6.660097218799566e-08, + "loss": 0.0014, + "step": 62451 + }, + { + "epoch": 19.29, + "learning_rate": 6.654336057827393e-08, + "loss": 0.0017, + "step": 62452 + }, + { + "epoch": 19.29, + "learning_rate": 6.648577381393795e-08, + "loss": 0.0012, + "step": 62453 + }, + { + "epoch": 19.29, + "learning_rate": 6.642821189513427e-08, + "loss": 0.0015, + "step": 62454 + }, + { + "epoch": 19.29, + "learning_rate": 6.637067482200499e-08, + "loss": 0.0023, + "step": 62455 + }, + { + "epoch": 19.29, + "learning_rate": 6.631316259469333e-08, + "loss": 0.0013, + "step": 62456 + }, + { + "epoch": 19.29, + "learning_rate": 6.625567521334475e-08, + "loss": 0.0014, + "step": 62457 + }, + { + "epoch": 19.29, + "learning_rate": 6.619821267810355e-08, + "loss": 0.0019, + "step": 62458 + }, + { + "epoch": 19.29, + "learning_rate": 6.614077498911187e-08, + "loss": 0.0019, + "step": 62459 + }, + { + "epoch": 19.29, + "learning_rate": 6.6083362146514e-08, + "loss": 0.0016, + "step": 62460 + }, + { + "epoch": 19.29, + "learning_rate": 6.602597415045209e-08, + "loss": 0.0013, + "step": 62461 + }, + { + "epoch": 19.29, + "learning_rate": 6.596861100107265e-08, + "loss": 0.0014, + "step": 62462 + }, + { + "epoch": 19.29, + "learning_rate": 6.591127269851671e-08, + "loss": 0.0022, + "step": 62463 + }, + { + "epoch": 19.29, + "learning_rate": 6.58539592429297e-08, + "loss": 0.0014, + "step": 62464 + }, + { + "epoch": 19.29, + "learning_rate": 6.579667063445261e-08, + "loss": 0.0019, + "step": 62465 + }, + { + "epoch": 19.29, + "learning_rate": 6.573940687323088e-08, + "loss": 0.0012, + "step": 62466 + }, + { + "epoch": 19.29, + "learning_rate": 6.568216795940552e-08, + "loss": 0.0015, + "step": 62467 + }, + { + "epoch": 19.29, + "learning_rate": 6.562495389312195e-08, + "loss": 0.0009, + "step": 62468 + }, + { + "epoch": 19.29, + "learning_rate": 6.55677646745223e-08, + "loss": 0.0013, + "step": 62469 + }, + { + "epoch": 19.29, + "learning_rate": 6.551060030374979e-08, + "loss": 0.0014, + "step": 62470 + }, + { + "epoch": 19.29, + "learning_rate": 6.54534607809465e-08, + "loss": 0.0015, + "step": 62471 + }, + { + "epoch": 19.29, + "learning_rate": 6.539634610625679e-08, + "loss": 0.0011, + "step": 62472 + }, + { + "epoch": 19.29, + "learning_rate": 6.533925627982162e-08, + "loss": 0.0013, + "step": 62473 + }, + { + "epoch": 19.29, + "learning_rate": 6.528219130178537e-08, + "loss": 0.0019, + "step": 62474 + }, + { + "epoch": 19.29, + "learning_rate": 6.522515117229122e-08, + "loss": 0.0015, + "step": 62475 + }, + { + "epoch": 19.29, + "learning_rate": 6.516813589148019e-08, + "loss": 0.0015, + "step": 62476 + }, + { + "epoch": 19.29, + "learning_rate": 6.511114545949548e-08, + "loss": 0.0013, + "step": 62477 + }, + { + "epoch": 19.29, + "learning_rate": 6.505417987648143e-08, + "loss": 0.0014, + "step": 62478 + }, + { + "epoch": 19.29, + "learning_rate": 6.499723914257682e-08, + "loss": 0.0013, + "step": 62479 + }, + { + "epoch": 19.29, + "learning_rate": 6.49403232579271e-08, + "loss": 0.0016, + "step": 62480 + }, + { + "epoch": 19.3, + "learning_rate": 6.488343222267435e-08, + "loss": 0.0017, + "step": 62481 + }, + { + "epoch": 19.3, + "learning_rate": 6.482656603695847e-08, + "loss": 0.0015, + "step": 62482 + }, + { + "epoch": 19.3, + "learning_rate": 6.47697247009238e-08, + "loss": 0.0014, + "step": 62483 + }, + { + "epoch": 19.3, + "learning_rate": 6.471290821471354e-08, + "loss": 0.002, + "step": 62484 + }, + { + "epoch": 19.3, + "learning_rate": 6.465611657846649e-08, + "loss": 0.0018, + "step": 62485 + }, + { + "epoch": 19.3, + "learning_rate": 6.459934979232807e-08, + "loss": 0.0015, + "step": 62486 + }, + { + "epoch": 19.3, + "learning_rate": 6.454260785643818e-08, + "loss": 0.0014, + "step": 62487 + }, + { + "epoch": 19.3, + "learning_rate": 6.448589077094003e-08, + "loss": 0.0012, + "step": 62488 + }, + { + "epoch": 19.3, + "learning_rate": 6.442919853597351e-08, + "loss": 0.0012, + "step": 62489 + }, + { + "epoch": 19.3, + "learning_rate": 6.437253115168296e-08, + "loss": 0.0013, + "step": 62490 + }, + { + "epoch": 19.3, + "learning_rate": 6.431588861820825e-08, + "loss": 0.0011, + "step": 62491 + }, + { + "epoch": 19.3, + "learning_rate": 6.425927093569151e-08, + "loss": 0.0018, + "step": 62492 + }, + { + "epoch": 19.3, + "learning_rate": 6.420267810427483e-08, + "loss": 0.0013, + "step": 62493 + }, + { + "epoch": 19.3, + "learning_rate": 6.414611012409922e-08, + "loss": 0.0014, + "step": 62494 + }, + { + "epoch": 19.3, + "learning_rate": 6.408956699530567e-08, + "loss": 0.0015, + "step": 62495 + }, + { + "epoch": 19.3, + "learning_rate": 6.403304871803739e-08, + "loss": 0.0016, + "step": 62496 + }, + { + "epoch": 19.3, + "learning_rate": 6.39765552924354e-08, + "loss": 0.0015, + "step": 62497 + }, + { + "epoch": 19.3, + "learning_rate": 6.392008671863848e-08, + "loss": 0.0013, + "step": 62498 + }, + { + "epoch": 19.3, + "learning_rate": 6.386364299678982e-08, + "loss": 0.0015, + "step": 62499 + }, + { + "epoch": 19.3, + "learning_rate": 6.380722412703156e-08, + "loss": 0.0019, + "step": 62500 + }, + { + "epoch": 19.3, + "learning_rate": 6.375083010950356e-08, + "loss": 0.0018, + "step": 62501 + }, + { + "epoch": 19.3, + "learning_rate": 6.369446094434573e-08, + "loss": 0.0014, + "step": 62502 + }, + { + "epoch": 19.3, + "learning_rate": 6.363811663170128e-08, + "loss": 0.0013, + "step": 62503 + }, + { + "epoch": 19.3, + "learning_rate": 6.35817971717101e-08, + "loss": 0.0013, + "step": 62504 + }, + { + "epoch": 19.3, + "learning_rate": 6.352550256451317e-08, + "loss": 0.0018, + "step": 62505 + }, + { + "epoch": 19.3, + "learning_rate": 6.346923281025153e-08, + "loss": 0.0014, + "step": 62506 + }, + { + "epoch": 19.3, + "learning_rate": 6.341298790906503e-08, + "loss": 0.0015, + "step": 62507 + }, + { + "epoch": 19.3, + "learning_rate": 6.335676786109468e-08, + "loss": 0.0017, + "step": 62508 + }, + { + "epoch": 19.3, + "learning_rate": 6.33005726664826e-08, + "loss": 0.0014, + "step": 62509 + }, + { + "epoch": 19.3, + "learning_rate": 6.324440232536755e-08, + "loss": 0.002, + "step": 62510 + }, + { + "epoch": 19.3, + "learning_rate": 6.318825683789054e-08, + "loss": 0.0018, + "step": 62511 + }, + { + "epoch": 19.3, + "learning_rate": 6.313213620419257e-08, + "loss": 0.0012, + "step": 62512 + }, + { + "epoch": 19.31, + "learning_rate": 6.30760404244124e-08, + "loss": 0.0014, + "step": 62513 + }, + { + "epoch": 19.31, + "learning_rate": 6.301996949869104e-08, + "loss": 0.0017, + "step": 62514 + }, + { + "epoch": 19.31, + "learning_rate": 6.296392342717062e-08, + "loss": 0.0017, + "step": 62515 + }, + { + "epoch": 19.31, + "learning_rate": 6.290790220998877e-08, + "loss": 0.0009, + "step": 62516 + }, + { + "epoch": 19.31, + "learning_rate": 6.285190584728762e-08, + "loss": 0.0016, + "step": 62517 + }, + { + "epoch": 19.31, + "learning_rate": 6.279593433920594e-08, + "loss": 0.0015, + "step": 62518 + }, + { + "epoch": 19.31, + "learning_rate": 6.273998768588363e-08, + "loss": 0.0014, + "step": 62519 + }, + { + "epoch": 19.31, + "learning_rate": 6.268406588746168e-08, + "loss": 0.0016, + "step": 62520 + }, + { + "epoch": 19.31, + "learning_rate": 6.262816894407886e-08, + "loss": 0.0019, + "step": 62521 + }, + { + "epoch": 19.31, + "learning_rate": 6.257229685587618e-08, + "loss": 0.0012, + "step": 62522 + }, + { + "epoch": 19.31, + "learning_rate": 6.251644962299242e-08, + "loss": 0.0015, + "step": 62523 + }, + { + "epoch": 19.31, + "learning_rate": 6.246062724556634e-08, + "loss": 0.0017, + "step": 62524 + }, + { + "epoch": 19.31, + "learning_rate": 6.240482972374007e-08, + "loss": 0.0016, + "step": 62525 + }, + { + "epoch": 19.31, + "learning_rate": 6.234905705765127e-08, + "loss": 0.0015, + "step": 62526 + }, + { + "epoch": 19.31, + "learning_rate": 6.229330924743981e-08, + "loss": 0.0012, + "step": 62527 + }, + { + "epoch": 19.31, + "learning_rate": 6.223758629324561e-08, + "loss": 0.0017, + "step": 62528 + }, + { + "epoch": 19.31, + "learning_rate": 6.218188819520744e-08, + "loss": 0.001, + "step": 62529 + }, + { + "epoch": 19.31, + "learning_rate": 6.212621495346516e-08, + "loss": 0.0014, + "step": 62530 + }, + { + "epoch": 19.31, + "learning_rate": 6.207056656815758e-08, + "loss": 0.0011, + "step": 62531 + }, + { + "epoch": 19.31, + "learning_rate": 6.201494303942457e-08, + "loss": 0.0016, + "step": 62532 + }, + { + "epoch": 19.31, + "learning_rate": 6.195934436740492e-08, + "loss": 0.0014, + "step": 62533 + }, + { + "epoch": 19.31, + "learning_rate": 6.190377055223739e-08, + "loss": 0.0009, + "step": 62534 + }, + { + "epoch": 19.31, + "learning_rate": 6.184822159405968e-08, + "loss": 0.0014, + "step": 62535 + }, + { + "epoch": 19.31, + "learning_rate": 6.179269749301386e-08, + "loss": 0.0015, + "step": 62536 + }, + { + "epoch": 19.31, + "learning_rate": 6.173719824923652e-08, + "loss": 0.0017, + "step": 62537 + }, + { + "epoch": 19.31, + "learning_rate": 6.168172386286752e-08, + "loss": 0.0014, + "step": 62538 + }, + { + "epoch": 19.31, + "learning_rate": 6.162627433404456e-08, + "loss": 0.0013, + "step": 62539 + }, + { + "epoch": 19.31, + "learning_rate": 6.157084966290749e-08, + "loss": 0.0014, + "step": 62540 + }, + { + "epoch": 19.31, + "learning_rate": 6.15154498495929e-08, + "loss": 0.0014, + "step": 62541 + }, + { + "epoch": 19.31, + "learning_rate": 6.146007489424288e-08, + "loss": 0.0018, + "step": 62542 + }, + { + "epoch": 19.31, + "learning_rate": 6.140472479699289e-08, + "loss": 0.0013, + "step": 62543 + }, + { + "epoch": 19.31, + "learning_rate": 6.13493995579828e-08, + "loss": 0.0017, + "step": 62544 + }, + { + "epoch": 19.31, + "learning_rate": 6.129409917734919e-08, + "loss": 0.0016, + "step": 62545 + }, + { + "epoch": 19.32, + "learning_rate": 6.123882365523303e-08, + "loss": 0.0021, + "step": 62546 + }, + { + "epoch": 19.32, + "learning_rate": 6.118357299177203e-08, + "loss": 0.0013, + "step": 62547 + }, + { + "epoch": 19.32, + "learning_rate": 6.112834718710159e-08, + "loss": 0.0016, + "step": 62548 + }, + { + "epoch": 19.32, + "learning_rate": 6.107314624136385e-08, + "loss": 0.0017, + "step": 62549 + }, + { + "epoch": 19.32, + "learning_rate": 6.101797015469313e-08, + "loss": 0.0021, + "step": 62550 + }, + { + "epoch": 19.32, + "learning_rate": 6.096281892723044e-08, + "loss": 0.0015, + "step": 62551 + }, + { + "epoch": 19.32, + "learning_rate": 6.090769255911233e-08, + "loss": 0.0015, + "step": 62552 + }, + { + "epoch": 19.32, + "learning_rate": 6.085259105047647e-08, + "loss": 0.0012, + "step": 62553 + }, + { + "epoch": 19.32, + "learning_rate": 6.079751440146164e-08, + "loss": 0.0014, + "step": 62554 + }, + { + "epoch": 19.32, + "learning_rate": 6.07424626122044e-08, + "loss": 0.0011, + "step": 62555 + }, + { + "epoch": 19.32, + "learning_rate": 6.068743568284352e-08, + "loss": 0.0015, + "step": 62556 + }, + { + "epoch": 19.32, + "learning_rate": 6.063243361351556e-08, + "loss": 0.0014, + "step": 62557 + }, + { + "epoch": 19.32, + "learning_rate": 6.05774564043593e-08, + "loss": 0.0012, + "step": 62558 + }, + { + "epoch": 19.32, + "learning_rate": 6.05225040555113e-08, + "loss": 0.0012, + "step": 62559 + }, + { + "epoch": 19.32, + "learning_rate": 6.046757656711034e-08, + "loss": 0.0016, + "step": 62560 + }, + { + "epoch": 19.32, + "learning_rate": 6.041267393929073e-08, + "loss": 0.0013, + "step": 62561 + }, + { + "epoch": 19.32, + "learning_rate": 6.03577961721935e-08, + "loss": 0.0015, + "step": 62562 + }, + { + "epoch": 19.32, + "learning_rate": 6.03029432659552e-08, + "loss": 0.0015, + "step": 62563 + }, + { + "epoch": 19.32, + "learning_rate": 6.024811522071016e-08, + "loss": 0.0013, + "step": 62564 + }, + { + "epoch": 19.32, + "learning_rate": 6.019331203659828e-08, + "loss": 0.0012, + "step": 62565 + }, + { + "epoch": 19.32, + "learning_rate": 6.01385337137561e-08, + "loss": 0.0018, + "step": 62566 + }, + { + "epoch": 19.32, + "learning_rate": 6.00837802523202e-08, + "loss": 0.0016, + "step": 62567 + }, + { + "epoch": 19.32, + "learning_rate": 6.002905165242823e-08, + "loss": 0.0014, + "step": 62568 + }, + { + "epoch": 19.32, + "learning_rate": 5.997434791421564e-08, + "loss": 0.0015, + "step": 62569 + }, + { + "epoch": 19.32, + "learning_rate": 5.991966903782009e-08, + "loss": 0.0012, + "step": 62570 + }, + { + "epoch": 19.32, + "learning_rate": 5.986501502337816e-08, + "loss": 0.0011, + "step": 62571 + }, + { + "epoch": 19.32, + "learning_rate": 5.98103858710275e-08, + "loss": 0.0013, + "step": 62572 + }, + { + "epoch": 19.32, + "learning_rate": 5.975578158090467e-08, + "loss": 0.0013, + "step": 62573 + }, + { + "epoch": 19.32, + "learning_rate": 5.970120215314512e-08, + "loss": 0.0017, + "step": 62574 + }, + { + "epoch": 19.32, + "learning_rate": 5.96466475878843e-08, + "loss": 0.0015, + "step": 62575 + }, + { + "epoch": 19.32, + "learning_rate": 5.959211788526209e-08, + "loss": 0.0015, + "step": 62576 + }, + { + "epoch": 19.32, + "learning_rate": 5.953761304541284e-08, + "loss": 0.0015, + "step": 62577 + }, + { + "epoch": 19.33, + "learning_rate": 5.9483133068471976e-08, + "loss": 0.0012, + "step": 62578 + }, + { + "epoch": 19.33, + "learning_rate": 5.942867795457718e-08, + "loss": 0.0015, + "step": 62579 + }, + { + "epoch": 19.33, + "learning_rate": 5.937424770386502e-08, + "loss": 0.0015, + "step": 62580 + }, + { + "epoch": 19.33, + "learning_rate": 5.931984231647092e-08, + "loss": 0.0015, + "step": 62581 + }, + { + "epoch": 19.33, + "learning_rate": 5.926546179253034e-08, + "loss": 0.0019, + "step": 62582 + }, + { + "epoch": 19.33, + "learning_rate": 5.921110613217984e-08, + "loss": 0.0011, + "step": 62583 + }, + { + "epoch": 19.33, + "learning_rate": 5.915677533555597e-08, + "loss": 0.0013, + "step": 62584 + }, + { + "epoch": 19.33, + "learning_rate": 5.9102469402794186e-08, + "loss": 0.0011, + "step": 62585 + }, + { + "epoch": 19.33, + "learning_rate": 5.904818833402992e-08, + "loss": 0.0013, + "step": 62586 + }, + { + "epoch": 19.33, + "learning_rate": 5.899393212939863e-08, + "loss": 0.0015, + "step": 62587 + }, + { + "epoch": 19.33, + "learning_rate": 5.893970078903799e-08, + "loss": 0.0014, + "step": 62588 + }, + { + "epoch": 19.33, + "learning_rate": 5.888549431308122e-08, + "loss": 0.0016, + "step": 62589 + }, + { + "epoch": 19.33, + "learning_rate": 5.883131270166598e-08, + "loss": 0.0011, + "step": 62590 + }, + { + "epoch": 19.33, + "learning_rate": 5.87771559549255e-08, + "loss": 0.001, + "step": 62591 + }, + { + "epoch": 19.33, + "learning_rate": 5.872302407299746e-08, + "loss": 0.0018, + "step": 62592 + }, + { + "epoch": 19.33, + "learning_rate": 5.8668917056016185e-08, + "loss": 0.0013, + "step": 62593 + }, + { + "epoch": 19.33, + "learning_rate": 5.8614834904117124e-08, + "loss": 0.0018, + "step": 62594 + }, + { + "epoch": 19.33, + "learning_rate": 5.856077761743462e-08, + "loss": 0.0016, + "step": 62595 + }, + { + "epoch": 19.33, + "learning_rate": 5.850674519610633e-08, + "loss": 0.0019, + "step": 62596 + }, + { + "epoch": 19.33, + "learning_rate": 5.8452737640264376e-08, + "loss": 0.002, + "step": 62597 + }, + { + "epoch": 19.33, + "learning_rate": 5.8398754950046434e-08, + "loss": 0.0012, + "step": 62598 + }, + { + "epoch": 19.33, + "learning_rate": 5.8344797125586824e-08, + "loss": 0.0016, + "step": 62599 + }, + { + "epoch": 19.33, + "learning_rate": 5.829086416701879e-08, + "loss": 0.0016, + "step": 62600 + }, + { + "epoch": 19.33, + "learning_rate": 5.823695607447888e-08, + "loss": 0.0016, + "step": 62601 + }, + { + "epoch": 19.33, + "learning_rate": 5.818307284810254e-08, + "loss": 0.0018, + "step": 62602 + }, + { + "epoch": 19.33, + "learning_rate": 5.8129214488023e-08, + "loss": 0.0015, + "step": 62603 + }, + { + "epoch": 19.33, + "learning_rate": 5.807538099437571e-08, + "loss": 0.0015, + "step": 62604 + }, + { + "epoch": 19.33, + "learning_rate": 5.8021572367295e-08, + "loss": 0.0014, + "step": 62605 + }, + { + "epoch": 19.33, + "learning_rate": 5.796778860691521e-08, + "loss": 0.0014, + "step": 62606 + }, + { + "epoch": 19.33, + "learning_rate": 5.791402971337179e-08, + "loss": 0.0014, + "step": 62607 + }, + { + "epoch": 19.33, + "learning_rate": 5.786029568679907e-08, + "loss": 0.0015, + "step": 62608 + }, + { + "epoch": 19.33, + "learning_rate": 5.780658652733029e-08, + "loss": 0.0011, + "step": 62609 + }, + { + "epoch": 19.34, + "learning_rate": 5.775290223510088e-08, + "loss": 0.0012, + "step": 62610 + }, + { + "epoch": 19.34, + "learning_rate": 5.769924281024519e-08, + "loss": 0.0015, + "step": 62611 + }, + { + "epoch": 19.34, + "learning_rate": 5.764560825289644e-08, + "loss": 0.0018, + "step": 62612 + }, + { + "epoch": 19.34, + "learning_rate": 5.7591998563190086e-08, + "loss": 0.0014, + "step": 62613 + }, + { + "epoch": 19.34, + "learning_rate": 5.753841374125935e-08, + "loss": 0.0016, + "step": 62614 + }, + { + "epoch": 19.34, + "learning_rate": 5.748485378723856e-08, + "loss": 0.0016, + "step": 62615 + }, + { + "epoch": 19.34, + "learning_rate": 5.7431318701260955e-08, + "loss": 0.0013, + "step": 62616 + }, + { + "epoch": 19.34, + "learning_rate": 5.737780848346086e-08, + "loss": 0.0017, + "step": 62617 + }, + { + "epoch": 19.34, + "learning_rate": 5.7324323133972625e-08, + "loss": 0.0014, + "step": 62618 + }, + { + "epoch": 19.34, + "learning_rate": 5.727086265293058e-08, + "loss": 0.0017, + "step": 62619 + }, + { + "epoch": 19.34, + "learning_rate": 5.721742704046684e-08, + "loss": 0.0012, + "step": 62620 + }, + { + "epoch": 19.34, + "learning_rate": 5.7164016296715754e-08, + "loss": 0.0018, + "step": 62621 + }, + { + "epoch": 19.34, + "learning_rate": 5.711063042181053e-08, + "loss": 0.0013, + "step": 62622 + }, + { + "epoch": 19.34, + "learning_rate": 5.7057269415885516e-08, + "loss": 0.0013, + "step": 62623 + }, + { + "epoch": 19.34, + "learning_rate": 5.7003933279073944e-08, + "loss": 0.0016, + "step": 62624 + }, + { + "epoch": 19.34, + "learning_rate": 5.6950622011509024e-08, + "loss": 0.0014, + "step": 62625 + }, + { + "epoch": 19.34, + "learning_rate": 5.689733561332289e-08, + "loss": 0.0016, + "step": 62626 + }, + { + "epoch": 19.34, + "learning_rate": 5.684407408465209e-08, + "loss": 0.0017, + "step": 62627 + }, + { + "epoch": 19.34, + "learning_rate": 5.6790837425625413e-08, + "loss": 0.001, + "step": 62628 + }, + { + "epoch": 19.34, + "learning_rate": 5.673762563638052e-08, + "loss": 0.0016, + "step": 62629 + }, + { + "epoch": 19.34, + "learning_rate": 5.668443871704732e-08, + "loss": 0.001, + "step": 62630 + }, + { + "epoch": 19.34, + "learning_rate": 5.663127666776014e-08, + "loss": 0.0012, + "step": 62631 + }, + { + "epoch": 19.34, + "learning_rate": 5.65781394886511e-08, + "loss": 0.0014, + "step": 62632 + }, + { + "epoch": 19.34, + "learning_rate": 5.652502717985453e-08, + "loss": 0.0013, + "step": 62633 + }, + { + "epoch": 19.34, + "learning_rate": 5.6471939741501445e-08, + "loss": 0.0015, + "step": 62634 + }, + { + "epoch": 19.34, + "learning_rate": 5.641887717372729e-08, + "loss": 0.0012, + "step": 62635 + }, + { + "epoch": 19.34, + "learning_rate": 5.636583947666196e-08, + "loss": 0.0014, + "step": 62636 + }, + { + "epoch": 19.34, + "learning_rate": 5.63128266504398e-08, + "loss": 0.0013, + "step": 62637 + }, + { + "epoch": 19.34, + "learning_rate": 5.6259838695191806e-08, + "loss": 0.0019, + "step": 62638 + }, + { + "epoch": 19.34, + "learning_rate": 5.620687561105231e-08, + "loss": 0.0018, + "step": 62639 + }, + { + "epoch": 19.34, + "learning_rate": 5.6153937398153446e-08, + "loss": 0.0012, + "step": 62640 + }, + { + "epoch": 19.34, + "learning_rate": 5.6101024056626206e-08, + "loss": 0.0013, + "step": 62641 + }, + { + "epoch": 19.34, + "learning_rate": 5.604813558660493e-08, + "loss": 0.0013, + "step": 62642 + }, + { + "epoch": 19.35, + "learning_rate": 5.599527198822064e-08, + "loss": 0.0016, + "step": 62643 + }, + { + "epoch": 19.35, + "learning_rate": 5.594243326160542e-08, + "loss": 0.0013, + "step": 62644 + }, + { + "epoch": 19.35, + "learning_rate": 5.5889619406892526e-08, + "loss": 0.0017, + "step": 62645 + }, + { + "epoch": 19.35, + "learning_rate": 5.583683042421295e-08, + "loss": 0.0016, + "step": 62646 + }, + { + "epoch": 19.35, + "learning_rate": 5.578406631369992e-08, + "loss": 0.0018, + "step": 62647 + }, + { + "epoch": 19.35, + "learning_rate": 5.573132707548334e-08, + "loss": 0.0013, + "step": 62648 + }, + { + "epoch": 19.35, + "learning_rate": 5.567861270969755e-08, + "loss": 0.0014, + "step": 62649 + }, + { + "epoch": 19.35, + "learning_rate": 5.562592321647242e-08, + "loss": 0.0011, + "step": 62650 + }, + { + "epoch": 19.35, + "learning_rate": 5.557325859594121e-08, + "loss": 0.0012, + "step": 62651 + }, + { + "epoch": 19.35, + "learning_rate": 5.5520618848234896e-08, + "loss": 0.0016, + "step": 62652 + }, + { + "epoch": 19.35, + "learning_rate": 5.546800397348562e-08, + "loss": 0.0012, + "step": 62653 + }, + { + "epoch": 19.35, + "learning_rate": 5.541541397182326e-08, + "loss": 0.001, + "step": 62654 + }, + { + "epoch": 19.35, + "learning_rate": 5.5362848843382164e-08, + "loss": 0.0012, + "step": 62655 + }, + { + "epoch": 19.35, + "learning_rate": 5.531030858829223e-08, + "loss": 0.0015, + "step": 62656 + }, + { + "epoch": 19.35, + "learning_rate": 5.525779320668445e-08, + "loss": 0.0017, + "step": 62657 + }, + { + "epoch": 19.35, + "learning_rate": 5.5205302698690956e-08, + "loss": 0.0013, + "step": 62658 + }, + { + "epoch": 19.35, + "learning_rate": 5.5152837064442745e-08, + "loss": 0.0018, + "step": 62659 + }, + { + "epoch": 19.35, + "learning_rate": 5.5100396304071935e-08, + "loss": 0.0015, + "step": 62660 + }, + { + "epoch": 19.35, + "learning_rate": 5.5047980417708426e-08, + "loss": 0.0017, + "step": 62661 + }, + { + "epoch": 19.35, + "learning_rate": 5.499558940548322e-08, + "loss": 0.0021, + "step": 62662 + }, + { + "epoch": 19.35, + "learning_rate": 5.494322326752732e-08, + "loss": 0.0016, + "step": 62663 + }, + { + "epoch": 19.35, + "learning_rate": 5.489088200397397e-08, + "loss": 0.0013, + "step": 62664 + }, + { + "epoch": 19.35, + "learning_rate": 5.4838565614950826e-08, + "loss": 0.0008, + "step": 62665 + }, + { + "epoch": 19.35, + "learning_rate": 5.478627410059112e-08, + "loss": 0.0016, + "step": 62666 + }, + { + "epoch": 19.35, + "learning_rate": 5.473400746102475e-08, + "loss": 0.0019, + "step": 62667 + }, + { + "epoch": 19.35, + "learning_rate": 5.4681765696382725e-08, + "loss": 0.0014, + "step": 62668 + }, + { + "epoch": 19.35, + "learning_rate": 5.462954880679494e-08, + "loss": 0.0014, + "step": 62669 + }, + { + "epoch": 19.35, + "learning_rate": 5.457735679239351e-08, + "loss": 0.0014, + "step": 62670 + }, + { + "epoch": 19.35, + "learning_rate": 5.452518965330722e-08, + "loss": 0.0018, + "step": 62671 + }, + { + "epoch": 19.35, + "learning_rate": 5.447304738966819e-08, + "loss": 0.0014, + "step": 62672 + }, + { + "epoch": 19.35, + "learning_rate": 5.44209300016052e-08, + "loss": 0.0017, + "step": 62673 + }, + { + "epoch": 19.35, + "learning_rate": 5.436883748924926e-08, + "loss": 0.0017, + "step": 62674 + }, + { + "epoch": 19.36, + "learning_rate": 5.431676985273138e-08, + "loss": 0.0016, + "step": 62675 + }, + { + "epoch": 19.36, + "learning_rate": 5.426472709218144e-08, + "loss": 0.0016, + "step": 62676 + }, + { + "epoch": 19.36, + "learning_rate": 5.4212709207729365e-08, + "loss": 0.0018, + "step": 62677 + }, + { + "epoch": 19.36, + "learning_rate": 5.4160716199505025e-08, + "loss": 0.0017, + "step": 62678 + }, + { + "epoch": 19.36, + "learning_rate": 5.410874806763833e-08, + "loss": 0.0014, + "step": 62679 + }, + { + "epoch": 19.36, + "learning_rate": 5.4056804812260275e-08, + "loss": 0.0017, + "step": 62680 + }, + { + "epoch": 19.36, + "learning_rate": 5.400488643349966e-08, + "loss": 0.0017, + "step": 62681 + }, + { + "epoch": 19.36, + "learning_rate": 5.395299293148748e-08, + "loss": 0.0012, + "step": 62682 + }, + { + "epoch": 19.36, + "learning_rate": 5.390112430635253e-08, + "loss": 0.0014, + "step": 62683 + }, + { + "epoch": 19.36, + "learning_rate": 5.3849280558224694e-08, + "loss": 0.0009, + "step": 62684 + }, + { + "epoch": 19.36, + "learning_rate": 5.3797461687233875e-08, + "loss": 0.0013, + "step": 62685 + }, + { + "epoch": 19.36, + "learning_rate": 5.3745667693511084e-08, + "loss": 0.0018, + "step": 62686 + }, + { + "epoch": 19.36, + "learning_rate": 5.369389857718288e-08, + "loss": 0.0012, + "step": 62687 + }, + { + "epoch": 19.36, + "learning_rate": 5.364215433838138e-08, + "loss": 0.0017, + "step": 62688 + }, + { + "epoch": 19.36, + "learning_rate": 5.3590434977234264e-08, + "loss": 0.0019, + "step": 62689 + }, + { + "epoch": 19.36, + "learning_rate": 5.3538740493871424e-08, + "loss": 0.0013, + "step": 62690 + }, + { + "epoch": 19.36, + "learning_rate": 5.348707088842275e-08, + "loss": 0.0014, + "step": 62691 + }, + { + "epoch": 19.36, + "learning_rate": 5.3435426161017044e-08, + "loss": 0.0015, + "step": 62692 + }, + { + "epoch": 19.36, + "learning_rate": 5.338380631178308e-08, + "loss": 0.0016, + "step": 62693 + }, + { + "epoch": 19.36, + "learning_rate": 5.333221134085076e-08, + "loss": 0.0012, + "step": 62694 + }, + { + "epoch": 19.36, + "learning_rate": 5.328064124834886e-08, + "loss": 0.0013, + "step": 62695 + }, + { + "epoch": 19.36, + "learning_rate": 5.322909603440618e-08, + "loss": 0.0013, + "step": 62696 + }, + { + "epoch": 19.36, + "learning_rate": 5.31775756991515e-08, + "loss": 0.0018, + "step": 62697 + }, + { + "epoch": 19.36, + "learning_rate": 5.312608024271359e-08, + "loss": 0.0017, + "step": 62698 + }, + { + "epoch": 19.36, + "learning_rate": 5.3074609665221264e-08, + "loss": 0.0015, + "step": 62699 + }, + { + "epoch": 19.36, + "learning_rate": 5.3023163966804405e-08, + "loss": 0.0015, + "step": 62700 + }, + { + "epoch": 19.36, + "learning_rate": 5.297174314759068e-08, + "loss": 0.001, + "step": 62701 + }, + { + "epoch": 19.36, + "learning_rate": 5.292034720770889e-08, + "loss": 0.0014, + "step": 62702 + }, + { + "epoch": 19.36, + "learning_rate": 5.286897614728781e-08, + "loss": 0.0011, + "step": 62703 + }, + { + "epoch": 19.36, + "learning_rate": 5.281762996645512e-08, + "loss": 0.0009, + "step": 62704 + }, + { + "epoch": 19.36, + "learning_rate": 5.2766308665339605e-08, + "loss": 0.0016, + "step": 62705 + }, + { + "epoch": 19.36, + "learning_rate": 5.271501224407005e-08, + "loss": 0.0014, + "step": 62706 + }, + { + "epoch": 19.37, + "learning_rate": 5.2663740702775247e-08, + "loss": 0.0014, + "step": 62707 + }, + { + "epoch": 19.37, + "learning_rate": 5.2612494041581754e-08, + "loss": 0.0013, + "step": 62708 + }, + { + "epoch": 19.37, + "learning_rate": 5.256127226061836e-08, + "loss": 0.0016, + "step": 62709 + }, + { + "epoch": 19.37, + "learning_rate": 5.2510075360014955e-08, + "loss": 0.0013, + "step": 62710 + }, + { + "epoch": 19.37, + "learning_rate": 5.2458903339897e-08, + "loss": 0.0012, + "step": 62711 + }, + { + "epoch": 19.37, + "learning_rate": 5.24077562003944e-08, + "loss": 0.0019, + "step": 62712 + }, + { + "epoch": 19.37, + "learning_rate": 5.2356633941633705e-08, + "loss": 0.0015, + "step": 62713 + }, + { + "epoch": 19.37, + "learning_rate": 5.230553656374371e-08, + "loss": 0.0019, + "step": 62714 + }, + { + "epoch": 19.37, + "learning_rate": 5.2254464066852084e-08, + "loss": 0.0011, + "step": 62715 + }, + { + "epoch": 19.37, + "learning_rate": 5.220341645108651e-08, + "loss": 0.0019, + "step": 62716 + }, + { + "epoch": 19.37, + "learning_rate": 5.215239371657355e-08, + "loss": 0.0014, + "step": 62717 + }, + { + "epoch": 19.37, + "learning_rate": 5.2101395863443094e-08, + "loss": 0.0017, + "step": 62718 + }, + { + "epoch": 19.37, + "learning_rate": 5.2050422891820604e-08, + "loss": 0.0015, + "step": 62719 + }, + { + "epoch": 19.37, + "learning_rate": 5.199947480183487e-08, + "loss": 0.0019, + "step": 62720 + }, + { + "epoch": 19.37, + "learning_rate": 5.194855159361245e-08, + "loss": 0.002, + "step": 62721 + }, + { + "epoch": 19.37, + "learning_rate": 5.1897653267281026e-08, + "loss": 0.0015, + "step": 62722 + }, + { + "epoch": 19.37, + "learning_rate": 5.1846779822968265e-08, + "loss": 0.001, + "step": 62723 + }, + { + "epoch": 19.37, + "learning_rate": 5.1795931260800734e-08, + "loss": 0.001, + "step": 62724 + }, + { + "epoch": 19.37, + "learning_rate": 5.174510758090723e-08, + "loss": 0.0018, + "step": 62725 + }, + { + "epoch": 19.37, + "learning_rate": 5.169430878341208e-08, + "loss": 0.0019, + "step": 62726 + }, + { + "epoch": 19.37, + "learning_rate": 5.16435348684452e-08, + "loss": 0.0011, + "step": 62727 + }, + { + "epoch": 19.37, + "learning_rate": 5.159278583613203e-08, + "loss": 0.0011, + "step": 62728 + }, + { + "epoch": 19.37, + "learning_rate": 5.1542061686599145e-08, + "loss": 0.0019, + "step": 62729 + }, + { + "epoch": 19.37, + "learning_rate": 5.149136241997421e-08, + "loss": 0.0016, + "step": 62730 + }, + { + "epoch": 19.37, + "learning_rate": 5.14406880363838e-08, + "loss": 0.0009, + "step": 62731 + }, + { + "epoch": 19.37, + "learning_rate": 5.139003853595559e-08, + "loss": 0.0015, + "step": 62732 + }, + { + "epoch": 19.37, + "learning_rate": 5.133941391881503e-08, + "loss": 0.0012, + "step": 62733 + }, + { + "epoch": 19.37, + "learning_rate": 5.128881418508869e-08, + "loss": 0.0013, + "step": 62734 + }, + { + "epoch": 19.37, + "learning_rate": 5.123823933490424e-08, + "loss": 0.0014, + "step": 62735 + }, + { + "epoch": 19.37, + "learning_rate": 5.118768936838714e-08, + "loss": 0.002, + "step": 62736 + }, + { + "epoch": 19.37, + "learning_rate": 5.1137164285663955e-08, + "loss": 0.0013, + "step": 62737 + }, + { + "epoch": 19.37, + "learning_rate": 5.108666408686125e-08, + "loss": 0.0017, + "step": 62738 + }, + { + "epoch": 19.37, + "learning_rate": 5.1036188772105586e-08, + "loss": 0.0011, + "step": 62739 + }, + { + "epoch": 19.38, + "learning_rate": 5.098573834152243e-08, + "loss": 0.0016, + "step": 62740 + }, + { + "epoch": 19.38, + "learning_rate": 5.093531279523944e-08, + "loss": 0.0012, + "step": 62741 + }, + { + "epoch": 19.38, + "learning_rate": 5.088491213338098e-08, + "loss": 0.0011, + "step": 62742 + }, + { + "epoch": 19.38, + "learning_rate": 5.0834536356074714e-08, + "loss": 0.0012, + "step": 62743 + }, + { + "epoch": 19.38, + "learning_rate": 5.07841854634461e-08, + "loss": 0.0017, + "step": 62744 + }, + { + "epoch": 19.38, + "learning_rate": 5.073385945562059e-08, + "loss": 0.0018, + "step": 62745 + }, + { + "epoch": 19.38, + "learning_rate": 5.068355833272365e-08, + "loss": 0.0012, + "step": 62746 + }, + { + "epoch": 19.38, + "learning_rate": 5.063328209488183e-08, + "loss": 0.0018, + "step": 62747 + }, + { + "epoch": 19.38, + "learning_rate": 5.0583030742221706e-08, + "loss": 0.0011, + "step": 62748 + }, + { + "epoch": 19.38, + "learning_rate": 5.053280427486762e-08, + "loss": 0.0022, + "step": 62749 + }, + { + "epoch": 19.38, + "learning_rate": 5.048260269294502e-08, + "loss": 0.0011, + "step": 62750 + }, + { + "epoch": 19.38, + "learning_rate": 5.04324259965816e-08, + "loss": 0.0019, + "step": 62751 + }, + { + "epoch": 19.38, + "learning_rate": 5.0382274185899474e-08, + "loss": 0.0014, + "step": 62752 + }, + { + "epoch": 19.38, + "learning_rate": 5.033214726102742e-08, + "loss": 0.0014, + "step": 62753 + }, + { + "epoch": 19.38, + "learning_rate": 5.028204522208979e-08, + "loss": 0.0019, + "step": 62754 + }, + { + "epoch": 19.38, + "learning_rate": 5.0231968069209824e-08, + "loss": 0.0017, + "step": 62755 + }, + { + "epoch": 19.38, + "learning_rate": 5.0181915802515193e-08, + "loss": 0.001, + "step": 62756 + }, + { + "epoch": 19.38, + "learning_rate": 5.013188842213024e-08, + "loss": 0.0015, + "step": 62757 + }, + { + "epoch": 19.38, + "learning_rate": 5.0081885928180415e-08, + "loss": 0.0014, + "step": 62758 + }, + { + "epoch": 19.38, + "learning_rate": 5.003190832079119e-08, + "loss": 0.0019, + "step": 62759 + }, + { + "epoch": 19.38, + "learning_rate": 4.9981955600085785e-08, + "loss": 0.0015, + "step": 62760 + }, + { + "epoch": 19.38, + "learning_rate": 4.993202776619077e-08, + "loss": 0.0013, + "step": 62761 + }, + { + "epoch": 19.38, + "learning_rate": 4.988212481923049e-08, + "loss": 0.0013, + "step": 62762 + }, + { + "epoch": 19.38, + "learning_rate": 4.9832246759329295e-08, + "loss": 0.0013, + "step": 62763 + }, + { + "epoch": 19.38, + "learning_rate": 4.9782393586613745e-08, + "loss": 0.0014, + "step": 62764 + }, + { + "epoch": 19.38, + "learning_rate": 4.973256530120596e-08, + "loss": 0.0016, + "step": 62765 + }, + { + "epoch": 19.38, + "learning_rate": 4.9682761903232513e-08, + "loss": 0.0018, + "step": 62766 + }, + { + "epoch": 19.38, + "learning_rate": 4.9632983392816634e-08, + "loss": 0.0015, + "step": 62767 + }, + { + "epoch": 19.38, + "learning_rate": 4.958322977008379e-08, + "loss": 0.0014, + "step": 62768 + }, + { + "epoch": 19.38, + "learning_rate": 4.95335010351583e-08, + "loss": 0.0019, + "step": 62769 + }, + { + "epoch": 19.38, + "learning_rate": 4.948379718816454e-08, + "loss": 0.0016, + "step": 62770 + }, + { + "epoch": 19.38, + "learning_rate": 4.9434118229225726e-08, + "loss": 0.0015, + "step": 62771 + }, + { + "epoch": 19.39, + "learning_rate": 4.9384464158468426e-08, + "loss": 0.001, + "step": 62772 + }, + { + "epoch": 19.39, + "learning_rate": 4.933483497601477e-08, + "loss": 0.0017, + "step": 62773 + }, + { + "epoch": 19.39, + "learning_rate": 4.928523068199021e-08, + "loss": 0.0015, + "step": 62774 + }, + { + "epoch": 19.39, + "learning_rate": 4.923565127651686e-08, + "loss": 0.0013, + "step": 62775 + }, + { + "epoch": 19.39, + "learning_rate": 4.91860967597213e-08, + "loss": 0.0017, + "step": 62776 + }, + { + "epoch": 19.39, + "learning_rate": 4.9136567131725657e-08, + "loss": 0.0015, + "step": 62777 + }, + { + "epoch": 19.39, + "learning_rate": 4.908706239265426e-08, + "loss": 0.0017, + "step": 62778 + }, + { + "epoch": 19.39, + "learning_rate": 4.9037582542631466e-08, + "loss": 0.0012, + "step": 62779 + }, + { + "epoch": 19.39, + "learning_rate": 4.898812758178051e-08, + "loss": 0.0016, + "step": 62780 + }, + { + "epoch": 19.39, + "learning_rate": 4.893869751022462e-08, + "loss": 0.0015, + "step": 62781 + }, + { + "epoch": 19.39, + "learning_rate": 4.888929232808814e-08, + "loss": 0.0014, + "step": 62782 + }, + { + "epoch": 19.39, + "learning_rate": 4.883991203549543e-08, + "loss": 0.0013, + "step": 62783 + }, + { + "epoch": 19.39, + "learning_rate": 4.87905566325686e-08, + "loss": 0.0016, + "step": 62784 + }, + { + "epoch": 19.39, + "learning_rate": 4.8741226119431995e-08, + "loss": 0.0018, + "step": 62785 + }, + { + "epoch": 19.39, + "learning_rate": 4.869192049620775e-08, + "loss": 0.0014, + "step": 62786 + }, + { + "epoch": 19.39, + "learning_rate": 4.864263976302019e-08, + "loss": 0.0013, + "step": 62787 + }, + { + "epoch": 19.39, + "learning_rate": 4.859338391999258e-08, + "loss": 0.0018, + "step": 62788 + }, + { + "epoch": 19.39, + "learning_rate": 4.854415296724813e-08, + "loss": 0.0015, + "step": 62789 + }, + { + "epoch": 19.39, + "learning_rate": 4.849494690490897e-08, + "loss": 0.0014, + "step": 62790 + }, + { + "epoch": 19.39, + "learning_rate": 4.844576573309945e-08, + "loss": 0.0014, + "step": 62791 + }, + { + "epoch": 19.39, + "learning_rate": 4.83966094519428e-08, + "loss": 0.0015, + "step": 62792 + }, + { + "epoch": 19.39, + "learning_rate": 4.834747806156004e-08, + "loss": 0.0016, + "step": 62793 + }, + { + "epoch": 19.39, + "learning_rate": 4.829837156207662e-08, + "loss": 0.0013, + "step": 62794 + }, + { + "epoch": 19.39, + "learning_rate": 4.8249289953613555e-08, + "loss": 0.0014, + "step": 62795 + }, + { + "epoch": 19.39, + "learning_rate": 4.820023323629408e-08, + "loss": 0.0021, + "step": 62796 + }, + { + "epoch": 19.39, + "learning_rate": 4.8151201410240324e-08, + "loss": 0.0016, + "step": 62797 + }, + { + "epoch": 19.39, + "learning_rate": 4.8102194475575514e-08, + "loss": 0.0013, + "step": 62798 + }, + { + "epoch": 19.39, + "learning_rate": 4.805321243242289e-08, + "loss": 0.0012, + "step": 62799 + }, + { + "epoch": 19.39, + "learning_rate": 4.8004255280904576e-08, + "loss": 0.0014, + "step": 62800 + }, + { + "epoch": 19.39, + "learning_rate": 4.79553230211427e-08, + "loss": 0.0014, + "step": 62801 + }, + { + "epoch": 19.39, + "learning_rate": 4.790641565325827e-08, + "loss": 0.0018, + "step": 62802 + }, + { + "epoch": 19.39, + "learning_rate": 4.785753317737674e-08, + "loss": 0.0018, + "step": 62803 + }, + { + "epoch": 19.39, + "learning_rate": 4.7808675593618014e-08, + "loss": 0.0015, + "step": 62804 + }, + { + "epoch": 19.4, + "learning_rate": 4.775984290210534e-08, + "loss": 0.0015, + "step": 62805 + }, + { + "epoch": 19.4, + "learning_rate": 4.771103510295971e-08, + "loss": 0.0013, + "step": 62806 + }, + { + "epoch": 19.4, + "learning_rate": 4.766225219630438e-08, + "loss": 0.0012, + "step": 62807 + }, + { + "epoch": 19.4, + "learning_rate": 4.761349418226036e-08, + "loss": 0.0015, + "step": 62808 + }, + { + "epoch": 19.4, + "learning_rate": 4.756476106095087e-08, + "loss": 0.0016, + "step": 62809 + }, + { + "epoch": 19.4, + "learning_rate": 4.751605283249805e-08, + "loss": 0.0011, + "step": 62810 + }, + { + "epoch": 19.4, + "learning_rate": 4.746736949702069e-08, + "loss": 0.0016, + "step": 62811 + }, + { + "epoch": 19.4, + "learning_rate": 4.741871105464424e-08, + "loss": 0.0016, + "step": 62812 + }, + { + "epoch": 19.4, + "learning_rate": 4.737007750548861e-08, + "loss": 0.0013, + "step": 62813 + }, + { + "epoch": 19.4, + "learning_rate": 4.732146884967481e-08, + "loss": 0.0016, + "step": 62814 + }, + { + "epoch": 19.4, + "learning_rate": 4.727288508732608e-08, + "loss": 0.0021, + "step": 62815 + }, + { + "epoch": 19.4, + "learning_rate": 4.722432621856343e-08, + "loss": 0.0017, + "step": 62816 + }, + { + "epoch": 19.4, + "learning_rate": 4.717579224350677e-08, + "loss": 0.0016, + "step": 62817 + }, + { + "epoch": 19.4, + "learning_rate": 4.7127283162279327e-08, + "loss": 0.0023, + "step": 62818 + }, + { + "epoch": 19.4, + "learning_rate": 4.707879897500212e-08, + "loss": 0.001, + "step": 62819 + }, + { + "epoch": 19.4, + "learning_rate": 4.703033968179615e-08, + "loss": 0.0014, + "step": 62820 + }, + { + "epoch": 19.4, + "learning_rate": 4.6981905282782455e-08, + "loss": 0.0015, + "step": 62821 + }, + { + "epoch": 19.4, + "learning_rate": 4.693349577808204e-08, + "loss": 0.0016, + "step": 62822 + }, + { + "epoch": 19.4, + "learning_rate": 4.688511116781702e-08, + "loss": 0.0016, + "step": 62823 + }, + { + "epoch": 19.4, + "learning_rate": 4.68367514521062e-08, + "loss": 0.0015, + "step": 62824 + }, + { + "epoch": 19.4, + "learning_rate": 4.678841663107392e-08, + "loss": 0.0012, + "step": 62825 + }, + { + "epoch": 19.4, + "learning_rate": 4.674010670483786e-08, + "loss": 0.0025, + "step": 62826 + }, + { + "epoch": 19.4, + "learning_rate": 4.669182167352015e-08, + "loss": 0.0019, + "step": 62827 + }, + { + "epoch": 19.4, + "learning_rate": 4.664356153724292e-08, + "loss": 0.0014, + "step": 62828 + }, + { + "epoch": 19.4, + "learning_rate": 4.659532629612384e-08, + "loss": 0.0016, + "step": 62829 + }, + { + "epoch": 19.4, + "learning_rate": 4.654711595028616e-08, + "loss": 0.0016, + "step": 62830 + }, + { + "epoch": 19.4, + "learning_rate": 4.649893049984977e-08, + "loss": 0.0015, + "step": 62831 + }, + { + "epoch": 19.4, + "learning_rate": 4.645076994493458e-08, + "loss": 0.0013, + "step": 62832 + }, + { + "epoch": 19.4, + "learning_rate": 4.6402634285660496e-08, + "loss": 0.0013, + "step": 62833 + }, + { + "epoch": 19.4, + "learning_rate": 4.635452352215075e-08, + "loss": 0.0012, + "step": 62834 + }, + { + "epoch": 19.4, + "learning_rate": 4.6306437654523026e-08, + "loss": 0.0014, + "step": 62835 + }, + { + "epoch": 19.4, + "learning_rate": 4.625837668289723e-08, + "loss": 0.0011, + "step": 62836 + }, + { + "epoch": 19.41, + "learning_rate": 4.6210340607395485e-08, + "loss": 0.0012, + "step": 62837 + }, + { + "epoch": 19.41, + "learning_rate": 4.6162329428137696e-08, + "loss": 0.0014, + "step": 62838 + }, + { + "epoch": 19.41, + "learning_rate": 4.611434314524266e-08, + "loss": 0.0019, + "step": 62839 + }, + { + "epoch": 19.41, + "learning_rate": 4.606638175883138e-08, + "loss": 0.0017, + "step": 62840 + }, + { + "epoch": 19.41, + "learning_rate": 4.6018445269023774e-08, + "loss": 0.0011, + "step": 62841 + }, + { + "epoch": 19.41, + "learning_rate": 4.597053367593862e-08, + "loss": 0.0012, + "step": 62842 + }, + { + "epoch": 19.41, + "learning_rate": 4.592264697969806e-08, + "loss": 0.0015, + "step": 62843 + }, + { + "epoch": 19.41, + "learning_rate": 4.587478518041866e-08, + "loss": 0.0024, + "step": 62844 + }, + { + "epoch": 19.41, + "learning_rate": 4.582694827822365e-08, + "loss": 0.0012, + "step": 62845 + }, + { + "epoch": 19.41, + "learning_rate": 4.577913627323072e-08, + "loss": 0.0015, + "step": 62846 + }, + { + "epoch": 19.41, + "learning_rate": 4.573134916555866e-08, + "loss": 0.0018, + "step": 62847 + }, + { + "epoch": 19.41, + "learning_rate": 4.5683586955328486e-08, + "loss": 0.0011, + "step": 62848 + }, + { + "epoch": 19.41, + "learning_rate": 4.563584964265899e-08, + "loss": 0.0012, + "step": 62849 + }, + { + "epoch": 19.41, + "learning_rate": 4.558813722767119e-08, + "loss": 0.0018, + "step": 62850 + }, + { + "epoch": 19.41, + "learning_rate": 4.554044971048166e-08, + "loss": 0.0014, + "step": 62851 + }, + { + "epoch": 19.41, + "learning_rate": 4.549278709121141e-08, + "loss": 0.0015, + "step": 62852 + }, + { + "epoch": 19.41, + "learning_rate": 4.544514936997924e-08, + "loss": 0.0012, + "step": 62853 + }, + { + "epoch": 19.41, + "learning_rate": 4.539753654690504e-08, + "loss": 0.0016, + "step": 62854 + }, + { + "epoch": 19.41, + "learning_rate": 4.534994862210651e-08, + "loss": 0.0011, + "step": 62855 + }, + { + "epoch": 19.41, + "learning_rate": 4.5302385595703546e-08, + "loss": 0.0011, + "step": 62856 + }, + { + "epoch": 19.41, + "learning_rate": 4.5254847467814945e-08, + "loss": 0.0011, + "step": 62857 + }, + { + "epoch": 19.41, + "learning_rate": 4.5207334238559494e-08, + "loss": 0.0016, + "step": 62858 + }, + { + "epoch": 19.41, + "learning_rate": 4.5159845908056e-08, + "loss": 0.0013, + "step": 62859 + }, + { + "epoch": 19.41, + "learning_rate": 4.5112382476423247e-08, + "loss": 0.002, + "step": 62860 + }, + { + "epoch": 19.41, + "learning_rate": 4.5064943943781135e-08, + "loss": 0.0018, + "step": 62861 + }, + { + "epoch": 19.41, + "learning_rate": 4.501753031024625e-08, + "loss": 0.001, + "step": 62862 + }, + { + "epoch": 19.41, + "learning_rate": 4.4970141575938484e-08, + "loss": 0.0013, + "step": 62863 + }, + { + "epoch": 19.41, + "learning_rate": 4.492277774097553e-08, + "loss": 0.002, + "step": 62864 + }, + { + "epoch": 19.41, + "learning_rate": 4.487543880547729e-08, + "loss": 0.0013, + "step": 62865 + }, + { + "epoch": 19.41, + "learning_rate": 4.4828124769561444e-08, + "loss": 0.0016, + "step": 62866 + }, + { + "epoch": 19.41, + "learning_rate": 4.4780835633344567e-08, + "loss": 0.0013, + "step": 62867 + }, + { + "epoch": 19.41, + "learning_rate": 4.473357139694767e-08, + "loss": 0.0011, + "step": 62868 + }, + { + "epoch": 19.42, + "learning_rate": 4.468633206048845e-08, + "loss": 0.0017, + "step": 62869 + }, + { + "epoch": 19.42, + "learning_rate": 4.463911762408346e-08, + "loss": 0.0015, + "step": 62870 + }, + { + "epoch": 19.42, + "learning_rate": 4.459192808785151e-08, + "loss": 0.0014, + "step": 62871 + }, + { + "epoch": 19.42, + "learning_rate": 4.45447634519125e-08, + "loss": 0.0013, + "step": 62872 + }, + { + "epoch": 19.42, + "learning_rate": 4.449762371638078e-08, + "loss": 0.0017, + "step": 62873 + }, + { + "epoch": 19.42, + "learning_rate": 4.445050888137847e-08, + "loss": 0.0015, + "step": 62874 + }, + { + "epoch": 19.42, + "learning_rate": 4.4403418947018826e-08, + "loss": 0.0012, + "step": 62875 + }, + { + "epoch": 19.42, + "learning_rate": 4.4356353913423966e-08, + "loss": 0.0016, + "step": 62876 + }, + { + "epoch": 19.42, + "learning_rate": 4.430931378070935e-08, + "loss": 0.0014, + "step": 62877 + }, + { + "epoch": 19.42, + "learning_rate": 4.426229854899156e-08, + "loss": 0.0015, + "step": 62878 + }, + { + "epoch": 19.42, + "learning_rate": 4.4215308218390486e-08, + "loss": 0.0021, + "step": 62879 + }, + { + "epoch": 19.42, + "learning_rate": 4.416834278902271e-08, + "loss": 0.0009, + "step": 62880 + }, + { + "epoch": 19.42, + "learning_rate": 4.412140226100592e-08, + "loss": 0.0017, + "step": 62881 + }, + { + "epoch": 19.42, + "learning_rate": 4.407448663445779e-08, + "loss": 0.0012, + "step": 62882 + }, + { + "epoch": 19.42, + "learning_rate": 4.40275959094949e-08, + "loss": 0.0014, + "step": 62883 + }, + { + "epoch": 19.42, + "learning_rate": 4.3980730086233826e-08, + "loss": 0.0012, + "step": 62884 + }, + { + "epoch": 19.42, + "learning_rate": 4.393388916479335e-08, + "loss": 0.0014, + "step": 62885 + }, + { + "epoch": 19.42, + "learning_rate": 4.388707314529117e-08, + "loss": 0.0018, + "step": 62886 + }, + { + "epoch": 19.42, + "learning_rate": 4.384028202784274e-08, + "loss": 0.0014, + "step": 62887 + }, + { + "epoch": 19.42, + "learning_rate": 4.379351581256464e-08, + "loss": 0.0014, + "step": 62888 + }, + { + "epoch": 19.42, + "learning_rate": 4.3746774499575654e-08, + "loss": 0.0018, + "step": 62889 + }, + { + "epoch": 19.42, + "learning_rate": 4.370005808899236e-08, + "loss": 0.0019, + "step": 62890 + }, + { + "epoch": 19.42, + "learning_rate": 4.3653366580930226e-08, + "loss": 0.0021, + "step": 62891 + }, + { + "epoch": 19.42, + "learning_rate": 4.360669997550804e-08, + "loss": 0.0015, + "step": 62892 + }, + { + "epoch": 19.42, + "learning_rate": 4.356005827284016e-08, + "loss": 0.0015, + "step": 62893 + }, + { + "epoch": 19.42, + "learning_rate": 4.351344147304537e-08, + "loss": 0.0012, + "step": 62894 + }, + { + "epoch": 19.42, + "learning_rate": 4.3466849576239144e-08, + "loss": 0.0014, + "step": 62895 + }, + { + "epoch": 19.42, + "learning_rate": 4.3420282582538054e-08, + "loss": 0.0016, + "step": 62896 + }, + { + "epoch": 19.42, + "learning_rate": 4.337374049205867e-08, + "loss": 0.0011, + "step": 62897 + }, + { + "epoch": 19.42, + "learning_rate": 4.3327223304918675e-08, + "loss": 0.0021, + "step": 62898 + }, + { + "epoch": 19.42, + "learning_rate": 4.328073102123242e-08, + "loss": 0.0017, + "step": 62899 + }, + { + "epoch": 19.42, + "learning_rate": 4.3234263641116495e-08, + "loss": 0.0022, + "step": 62900 + }, + { + "epoch": 19.42, + "learning_rate": 4.318782116468856e-08, + "loss": 0.0021, + "step": 62901 + }, + { + "epoch": 19.43, + "learning_rate": 4.314140359206409e-08, + "loss": 0.0021, + "step": 62902 + }, + { + "epoch": 19.43, + "learning_rate": 4.309501092335855e-08, + "loss": 0.0014, + "step": 62903 + }, + { + "epoch": 19.43, + "learning_rate": 4.30486431586874e-08, + "loss": 0.0022, + "step": 62904 + }, + { + "epoch": 19.43, + "learning_rate": 4.300230029816943e-08, + "loss": 0.0012, + "step": 62905 + }, + { + "epoch": 19.43, + "learning_rate": 4.295598234191789e-08, + "loss": 0.0015, + "step": 62906 + }, + { + "epoch": 19.43, + "learning_rate": 4.290968929004935e-08, + "loss": 0.0015, + "step": 62907 + }, + { + "epoch": 19.43, + "learning_rate": 4.286342114268038e-08, + "loss": 0.0013, + "step": 62908 + }, + { + "epoch": 19.43, + "learning_rate": 4.281717789992534e-08, + "loss": 0.0018, + "step": 62909 + }, + { + "epoch": 19.43, + "learning_rate": 4.27709595619008e-08, + "loss": 0.0019, + "step": 62910 + }, + { + "epoch": 19.43, + "learning_rate": 4.2724766128722226e-08, + "loss": 0.0015, + "step": 62911 + }, + { + "epoch": 19.43, + "learning_rate": 4.2678597600505075e-08, + "loss": 0.0014, + "step": 62912 + }, + { + "epoch": 19.43, + "learning_rate": 4.263245397736482e-08, + "loss": 0.0014, + "step": 62913 + }, + { + "epoch": 19.43, + "learning_rate": 4.258633525941691e-08, + "loss": 0.001, + "step": 62914 + }, + { + "epoch": 19.43, + "learning_rate": 4.254024144677682e-08, + "loss": 0.0015, + "step": 62915 + }, + { + "epoch": 19.43, + "learning_rate": 4.2494172539560006e-08, + "loss": 0.0017, + "step": 62916 + }, + { + "epoch": 19.43, + "learning_rate": 4.244812853788083e-08, + "loss": 0.0015, + "step": 62917 + }, + { + "epoch": 19.43, + "learning_rate": 4.240210944185585e-08, + "loss": 0.0014, + "step": 62918 + }, + { + "epoch": 19.43, + "learning_rate": 4.235611525159833e-08, + "loss": 0.0012, + "step": 62919 + }, + { + "epoch": 19.43, + "learning_rate": 4.231014596722483e-08, + "loss": 0.0011, + "step": 62920 + }, + { + "epoch": 19.43, + "learning_rate": 4.2264201588849697e-08, + "loss": 0.0012, + "step": 62921 + }, + { + "epoch": 19.43, + "learning_rate": 4.2218282116588406e-08, + "loss": 0.0014, + "step": 62922 + }, + { + "epoch": 19.43, + "learning_rate": 4.2172387550554193e-08, + "loss": 0.0019, + "step": 62923 + }, + { + "epoch": 19.43, + "learning_rate": 4.212651789086475e-08, + "loss": 0.0018, + "step": 62924 + }, + { + "epoch": 19.43, + "learning_rate": 4.20806731376322e-08, + "loss": 0.0013, + "step": 62925 + }, + { + "epoch": 19.43, + "learning_rate": 4.203485329097201e-08, + "loss": 0.0015, + "step": 62926 + }, + { + "epoch": 19.43, + "learning_rate": 4.1989058350998534e-08, + "loss": 0.0015, + "step": 62927 + }, + { + "epoch": 19.43, + "learning_rate": 4.1943288317827236e-08, + "loss": 0.0019, + "step": 62928 + }, + { + "epoch": 19.43, + "learning_rate": 4.1897543191571356e-08, + "loss": 0.0019, + "step": 62929 + }, + { + "epoch": 19.43, + "learning_rate": 4.185182297234747e-08, + "loss": 0.0014, + "step": 62930 + }, + { + "epoch": 19.43, + "learning_rate": 4.180612766026659e-08, + "loss": 0.0017, + "step": 62931 + }, + { + "epoch": 19.43, + "learning_rate": 4.1760457255445306e-08, + "loss": 0.0013, + "step": 62932 + }, + { + "epoch": 19.43, + "learning_rate": 4.1714811757999073e-08, + "loss": 0.0013, + "step": 62933 + }, + { + "epoch": 19.44, + "learning_rate": 4.1669191168038915e-08, + "loss": 0.0012, + "step": 62934 + }, + { + "epoch": 19.44, + "learning_rate": 4.162359548568029e-08, + "loss": 0.0014, + "step": 62935 + }, + { + "epoch": 19.44, + "learning_rate": 4.157802471103756e-08, + "loss": 0.0016, + "step": 62936 + }, + { + "epoch": 19.44, + "learning_rate": 4.153247884422396e-08, + "loss": 0.0016, + "step": 62937 + }, + { + "epoch": 19.44, + "learning_rate": 4.148695788535495e-08, + "loss": 0.0016, + "step": 62938 + }, + { + "epoch": 19.44, + "learning_rate": 4.144146183454267e-08, + "loss": 0.0016, + "step": 62939 + }, + { + "epoch": 19.44, + "learning_rate": 4.139599069190259e-08, + "loss": 0.0014, + "step": 62940 + }, + { + "epoch": 19.44, + "learning_rate": 4.1350544457545716e-08, + "loss": 0.0017, + "step": 62941 + }, + { + "epoch": 19.44, + "learning_rate": 4.1305123131588634e-08, + "loss": 0.0016, + "step": 62942 + }, + { + "epoch": 19.44, + "learning_rate": 4.1259726714144574e-08, + "loss": 0.0015, + "step": 62943 + }, + { + "epoch": 19.44, + "learning_rate": 4.1214355205324577e-08, + "loss": 0.0012, + "step": 62944 + }, + { + "epoch": 19.44, + "learning_rate": 4.1169008605245194e-08, + "loss": 0.0015, + "step": 62945 + }, + { + "epoch": 19.44, + "learning_rate": 4.112368691401747e-08, + "loss": 0.0015, + "step": 62946 + }, + { + "epoch": 19.44, + "learning_rate": 4.107839013175685e-08, + "loss": 0.0013, + "step": 62947 + }, + { + "epoch": 19.44, + "learning_rate": 4.103311825857437e-08, + "loss": 0.0018, + "step": 62948 + }, + { + "epoch": 19.44, + "learning_rate": 4.098787129458548e-08, + "loss": 0.001, + "step": 62949 + }, + { + "epoch": 19.44, + "learning_rate": 4.094264923990232e-08, + "loss": 0.0017, + "step": 62950 + }, + { + "epoch": 19.44, + "learning_rate": 4.089745209463702e-08, + "loss": 0.0012, + "step": 62951 + }, + { + "epoch": 19.44, + "learning_rate": 4.0852279858905054e-08, + "loss": 0.0013, + "step": 62952 + }, + { + "epoch": 19.44, + "learning_rate": 4.080713253281743e-08, + "loss": 0.0015, + "step": 62953 + }, + { + "epoch": 19.44, + "learning_rate": 4.076201011648628e-08, + "loss": 0.0014, + "step": 62954 + }, + { + "epoch": 19.44, + "learning_rate": 4.071691261002708e-08, + "loss": 0.002, + "step": 62955 + }, + { + "epoch": 19.44, + "learning_rate": 4.0671840013551955e-08, + "loss": 0.0013, + "step": 62956 + }, + { + "epoch": 19.44, + "learning_rate": 4.0626792327171926e-08, + "loss": 0.0013, + "step": 62957 + }, + { + "epoch": 19.44, + "learning_rate": 4.058176955100024e-08, + "loss": 0.0012, + "step": 62958 + }, + { + "epoch": 19.44, + "learning_rate": 4.0536771685151244e-08, + "loss": 0.002, + "step": 62959 + }, + { + "epoch": 19.44, + "learning_rate": 4.049179872973596e-08, + "loss": 0.0013, + "step": 62960 + }, + { + "epoch": 19.44, + "learning_rate": 4.0446850684867646e-08, + "loss": 0.0013, + "step": 62961 + }, + { + "epoch": 19.44, + "learning_rate": 4.0401927550657303e-08, + "loss": 0.0013, + "step": 62962 + }, + { + "epoch": 19.44, + "learning_rate": 4.03570293272193e-08, + "loss": 0.0016, + "step": 62963 + }, + { + "epoch": 19.44, + "learning_rate": 4.031215601466354e-08, + "loss": 0.0012, + "step": 62964 + }, + { + "epoch": 19.44, + "learning_rate": 4.026730761310438e-08, + "loss": 0.0012, + "step": 62965 + }, + { + "epoch": 19.45, + "learning_rate": 4.0222484122652836e-08, + "loss": 0.0015, + "step": 62966 + }, + { + "epoch": 19.45, + "learning_rate": 4.017768554342216e-08, + "loss": 0.0014, + "step": 62967 + }, + { + "epoch": 19.45, + "learning_rate": 4.013291187552337e-08, + "loss": 0.0012, + "step": 62968 + }, + { + "epoch": 19.45, + "learning_rate": 4.00881631190686e-08, + "loss": 0.0017, + "step": 62969 + }, + { + "epoch": 19.45, + "learning_rate": 4.004343927416998e-08, + "loss": 0.0011, + "step": 62970 + }, + { + "epoch": 19.45, + "learning_rate": 3.9998740340939645e-08, + "loss": 0.0015, + "step": 62971 + }, + { + "epoch": 19.45, + "learning_rate": 3.99540663194875e-08, + "loss": 0.0014, + "step": 62972 + }, + { + "epoch": 19.45, + "learning_rate": 3.9909417209929024e-08, + "loss": 0.0016, + "step": 62973 + }, + { + "epoch": 19.45, + "learning_rate": 3.9864793012373004e-08, + "loss": 0.0014, + "step": 62974 + }, + { + "epoch": 19.45, + "learning_rate": 3.9820193726930465e-08, + "loss": 0.0013, + "step": 62975 + }, + { + "epoch": 19.45, + "learning_rate": 3.9775619353715763e-08, + "loss": 0.0019, + "step": 62976 + }, + { + "epoch": 19.45, + "learning_rate": 3.97310698928377e-08, + "loss": 0.001, + "step": 62977 + }, + { + "epoch": 19.45, + "learning_rate": 3.968654534440952e-08, + "loss": 0.001, + "step": 62978 + }, + { + "epoch": 19.45, + "learning_rate": 3.964204570854224e-08, + "loss": 0.0011, + "step": 62979 + }, + { + "epoch": 19.45, + "learning_rate": 3.9597570985346886e-08, + "loss": 0.0013, + "step": 62980 + }, + { + "epoch": 19.45, + "learning_rate": 3.955312117493337e-08, + "loss": 0.0012, + "step": 62981 + }, + { + "epoch": 19.45, + "learning_rate": 3.950869627741494e-08, + "loss": 0.0012, + "step": 62982 + }, + { + "epoch": 19.45, + "learning_rate": 3.946429629290261e-08, + "loss": 0.0015, + "step": 62983 + }, + { + "epoch": 19.45, + "learning_rate": 3.9419921221506285e-08, + "loss": 0.0017, + "step": 62984 + }, + { + "epoch": 19.45, + "learning_rate": 3.9375571063337e-08, + "loss": 0.0015, + "step": 62985 + }, + { + "epoch": 19.45, + "learning_rate": 3.9331245818506895e-08, + "loss": 0.001, + "step": 62986 + }, + { + "epoch": 19.45, + "learning_rate": 3.928694548712586e-08, + "loss": 0.0011, + "step": 62987 + }, + { + "epoch": 19.45, + "learning_rate": 3.924267006930382e-08, + "loss": 0.0018, + "step": 62988 + }, + { + "epoch": 19.45, + "learning_rate": 3.9198419565154024e-08, + "loss": 0.0014, + "step": 62989 + }, + { + "epoch": 19.45, + "learning_rate": 3.915419397478526e-08, + "loss": 0.0013, + "step": 62990 + }, + { + "epoch": 19.45, + "learning_rate": 3.910999329830856e-08, + "loss": 0.0023, + "step": 62991 + }, + { + "epoch": 19.45, + "learning_rate": 3.906581753583494e-08, + "loss": 0.001, + "step": 62992 + }, + { + "epoch": 19.45, + "learning_rate": 3.9021666687473205e-08, + "loss": 0.0015, + "step": 62993 + }, + { + "epoch": 19.45, + "learning_rate": 3.89775407533366e-08, + "loss": 0.0019, + "step": 62994 + }, + { + "epoch": 19.45, + "learning_rate": 3.893343973353281e-08, + "loss": 0.0013, + "step": 62995 + }, + { + "epoch": 19.45, + "learning_rate": 3.888936362817397e-08, + "loss": 0.0022, + "step": 62996 + }, + { + "epoch": 19.45, + "learning_rate": 3.8845312437368885e-08, + "loss": 0.0017, + "step": 62997 + }, + { + "epoch": 19.45, + "learning_rate": 3.880128616122969e-08, + "loss": 0.0015, + "step": 62998 + }, + { + "epoch": 19.46, + "learning_rate": 3.875728479986407e-08, + "loss": 0.0019, + "step": 62999 + }, + { + "epoch": 19.46, + "learning_rate": 3.871330835338305e-08, + "loss": 0.0011, + "step": 63000 + }, + { + "epoch": 19.46, + "learning_rate": 3.866935682189876e-08, + "loss": 0.0012, + "step": 63001 + }, + { + "epoch": 19.46, + "learning_rate": 3.862543020551779e-08, + "loss": 0.0011, + "step": 63002 + }, + { + "epoch": 19.46, + "learning_rate": 3.858152850435115e-08, + "loss": 0.0013, + "step": 63003 + }, + { + "epoch": 19.46, + "learning_rate": 3.8537651718509874e-08, + "loss": 0.0024, + "step": 63004 + }, + { + "epoch": 19.46, + "learning_rate": 3.8493799848102756e-08, + "loss": 0.001, + "step": 63005 + }, + { + "epoch": 19.46, + "learning_rate": 3.8449972893238596e-08, + "loss": 0.0016, + "step": 63006 + }, + { + "epoch": 19.46, + "learning_rate": 3.840617085402842e-08, + "loss": 0.0012, + "step": 63007 + }, + { + "epoch": 19.46, + "learning_rate": 3.836239373058104e-08, + "loss": 0.0015, + "step": 63008 + }, + { + "epoch": 19.46, + "learning_rate": 3.831864152300635e-08, + "loss": 0.0017, + "step": 63009 + }, + { + "epoch": 19.46, + "learning_rate": 3.8274914231414274e-08, + "loss": 0.0014, + "step": 63010 + }, + { + "epoch": 19.46, + "learning_rate": 3.823121185591361e-08, + "loss": 0.0018, + "step": 63011 + }, + { + "epoch": 19.46, + "learning_rate": 3.818753439661316e-08, + "loss": 0.002, + "step": 63012 + }, + { + "epoch": 19.46, + "learning_rate": 3.8143881853621724e-08, + "loss": 0.0014, + "step": 63013 + }, + { + "epoch": 19.46, + "learning_rate": 3.8100254227050323e-08, + "loss": 0.0012, + "step": 63014 + }, + { + "epoch": 19.46, + "learning_rate": 3.805665151700777e-08, + "loss": 0.0013, + "step": 63015 + }, + { + "epoch": 19.46, + "learning_rate": 3.801307372360064e-08, + "loss": 0.0016, + "step": 63016 + }, + { + "epoch": 19.46, + "learning_rate": 3.796952084694105e-08, + "loss": 0.0013, + "step": 63017 + }, + { + "epoch": 19.46, + "learning_rate": 3.792599288713672e-08, + "loss": 0.0012, + "step": 63018 + }, + { + "epoch": 19.46, + "learning_rate": 3.7882489844295325e-08, + "loss": 0.0011, + "step": 63019 + }, + { + "epoch": 19.46, + "learning_rate": 3.7839011718527884e-08, + "loss": 0.0012, + "step": 63020 + }, + { + "epoch": 19.46, + "learning_rate": 3.77955585099421e-08, + "loss": 0.0018, + "step": 63021 + }, + { + "epoch": 19.46, + "learning_rate": 3.7752130218646767e-08, + "loss": 0.0015, + "step": 63022 + }, + { + "epoch": 19.46, + "learning_rate": 3.7708726844749574e-08, + "loss": 0.0011, + "step": 63023 + }, + { + "epoch": 19.46, + "learning_rate": 3.766534838836044e-08, + "loss": 0.0011, + "step": 63024 + }, + { + "epoch": 19.46, + "learning_rate": 3.7621994849587065e-08, + "loss": 0.0009, + "step": 63025 + }, + { + "epoch": 19.46, + "learning_rate": 3.757866622853823e-08, + "loss": 0.0016, + "step": 63026 + }, + { + "epoch": 19.46, + "learning_rate": 3.7535362525321636e-08, + "loss": 0.0022, + "step": 63027 + }, + { + "epoch": 19.46, + "learning_rate": 3.7492083740046094e-08, + "loss": 0.0012, + "step": 63028 + }, + { + "epoch": 19.46, + "learning_rate": 3.744882987282039e-08, + "loss": 0.0018, + "step": 63029 + }, + { + "epoch": 19.46, + "learning_rate": 3.740560092375223e-08, + "loss": 0.0021, + "step": 63030 + }, + { + "epoch": 19.47, + "learning_rate": 3.7362396892950406e-08, + "loss": 0.0011, + "step": 63031 + }, + { + "epoch": 19.47, + "learning_rate": 3.73192177805215e-08, + "loss": 0.0018, + "step": 63032 + }, + { + "epoch": 19.47, + "learning_rate": 3.727606358657432e-08, + "loss": 0.0016, + "step": 63033 + }, + { + "epoch": 19.47, + "learning_rate": 3.723293431121655e-08, + "loss": 0.0023, + "step": 63034 + }, + { + "epoch": 19.47, + "learning_rate": 3.7189829954557e-08, + "loss": 0.0012, + "step": 63035 + }, + { + "epoch": 19.47, + "learning_rate": 3.714675051670225e-08, + "loss": 0.0019, + "step": 63036 + }, + { + "epoch": 19.47, + "learning_rate": 3.710369599775998e-08, + "loss": 0.0019, + "step": 63037 + }, + { + "epoch": 19.47, + "learning_rate": 3.7060666397840115e-08, + "loss": 0.0014, + "step": 63038 + }, + { + "epoch": 19.47, + "learning_rate": 3.7017661717047015e-08, + "loss": 0.0018, + "step": 63039 + }, + { + "epoch": 19.47, + "learning_rate": 3.6974681955490586e-08, + "loss": 0.0013, + "step": 63040 + }, + { + "epoch": 19.47, + "learning_rate": 3.6931727113278525e-08, + "loss": 0.0014, + "step": 63041 + }, + { + "epoch": 19.47, + "learning_rate": 3.6888797190516303e-08, + "loss": 0.0016, + "step": 63042 + }, + { + "epoch": 19.47, + "learning_rate": 3.684589218731272e-08, + "loss": 0.0017, + "step": 63043 + }, + { + "epoch": 19.47, + "learning_rate": 3.6803012103774347e-08, + "loss": 0.0016, + "step": 63044 + }, + { + "epoch": 19.47, + "learning_rate": 3.67601569400089e-08, + "loss": 0.0013, + "step": 63045 + }, + { + "epoch": 19.47, + "learning_rate": 3.6717326696124044e-08, + "loss": 0.0009, + "step": 63046 + }, + { + "epoch": 19.47, + "learning_rate": 3.667452137222527e-08, + "loss": 0.0019, + "step": 63047 + }, + { + "epoch": 19.47, + "learning_rate": 3.663174096842137e-08, + "loss": 0.001, + "step": 63048 + }, + { + "epoch": 19.47, + "learning_rate": 3.658898548481893e-08, + "loss": 0.0014, + "step": 63049 + }, + { + "epoch": 19.47, + "learning_rate": 3.654625492152342e-08, + "loss": 0.0015, + "step": 63050 + }, + { + "epoch": 19.47, + "learning_rate": 3.650354927864475e-08, + "loss": 0.0015, + "step": 63051 + }, + { + "epoch": 19.47, + "learning_rate": 3.6460868556287276e-08, + "loss": 0.0018, + "step": 63052 + }, + { + "epoch": 19.47, + "learning_rate": 3.641821275455759e-08, + "loss": 0.0016, + "step": 63053 + }, + { + "epoch": 19.47, + "learning_rate": 3.637558187356449e-08, + "loss": 0.0012, + "step": 63054 + }, + { + "epoch": 19.47, + "learning_rate": 3.633297591341234e-08, + "loss": 0.0012, + "step": 63055 + }, + { + "epoch": 19.47, + "learning_rate": 3.6290394874208824e-08, + "loss": 0.0012, + "step": 63056 + }, + { + "epoch": 19.47, + "learning_rate": 3.6247838756060526e-08, + "loss": 0.0012, + "step": 63057 + }, + { + "epoch": 19.47, + "learning_rate": 3.620530755907403e-08, + "loss": 0.0012, + "step": 63058 + }, + { + "epoch": 19.47, + "learning_rate": 3.616280128335481e-08, + "loss": 0.0014, + "step": 63059 + }, + { + "epoch": 19.47, + "learning_rate": 3.612031992900944e-08, + "loss": 0.0017, + "step": 63060 + }, + { + "epoch": 19.47, + "learning_rate": 3.607786349614562e-08, + "loss": 0.0013, + "step": 63061 + }, + { + "epoch": 19.47, + "learning_rate": 3.603543198486659e-08, + "loss": 0.0016, + "step": 63062 + }, + { + "epoch": 19.47, + "learning_rate": 3.5993025395282266e-08, + "loss": 0.0013, + "step": 63063 + }, + { + "epoch": 19.48, + "learning_rate": 3.595064372749479e-08, + "loss": 0.0017, + "step": 63064 + }, + { + "epoch": 19.48, + "learning_rate": 3.5908286981612975e-08, + "loss": 0.0014, + "step": 63065 + }, + { + "epoch": 19.48, + "learning_rate": 3.586595515774227e-08, + "loss": 0.0017, + "step": 63066 + }, + { + "epoch": 19.48, + "learning_rate": 3.5823648255988164e-08, + "loss": 0.0012, + "step": 63067 + }, + { + "epoch": 19.48, + "learning_rate": 3.578136627645612e-08, + "loss": 0.0017, + "step": 63068 + }, + { + "epoch": 19.48, + "learning_rate": 3.573910921925161e-08, + "loss": 0.0012, + "step": 63069 + }, + { + "epoch": 19.48, + "learning_rate": 3.5696877084481216e-08, + "loss": 0.0013, + "step": 63070 + }, + { + "epoch": 19.48, + "learning_rate": 3.565466987225152e-08, + "loss": 0.0013, + "step": 63071 + }, + { + "epoch": 19.48, + "learning_rate": 3.561248758266578e-08, + "loss": 0.0015, + "step": 63072 + }, + { + "epoch": 19.48, + "learning_rate": 3.557033021583056e-08, + "loss": 0.0015, + "step": 63073 + }, + { + "epoch": 19.48, + "learning_rate": 3.552819777185135e-08, + "loss": 0.0015, + "step": 63074 + }, + { + "epoch": 19.48, + "learning_rate": 3.548609025083361e-08, + "loss": 0.0017, + "step": 63075 + }, + { + "epoch": 19.48, + "learning_rate": 3.544400765288281e-08, + "loss": 0.0015, + "step": 63076 + }, + { + "epoch": 19.48, + "learning_rate": 3.540194997810442e-08, + "loss": 0.0012, + "step": 63077 + }, + { + "epoch": 19.48, + "learning_rate": 3.535991722660281e-08, + "loss": 0.0013, + "step": 63078 + }, + { + "epoch": 19.48, + "learning_rate": 3.5317909398483454e-08, + "loss": 0.0012, + "step": 63079 + }, + { + "epoch": 19.48, + "learning_rate": 3.5275926493850695e-08, + "loss": 0.0016, + "step": 63080 + }, + { + "epoch": 19.48, + "learning_rate": 3.5233968512811136e-08, + "loss": 0.0015, + "step": 63081 + }, + { + "epoch": 19.48, + "learning_rate": 3.519203545546912e-08, + "loss": 0.0018, + "step": 63082 + }, + { + "epoch": 19.48, + "learning_rate": 3.5150127321927906e-08, + "loss": 0.0011, + "step": 63083 + }, + { + "epoch": 19.48, + "learning_rate": 3.5108244112295185e-08, + "loss": 0.0011, + "step": 63084 + }, + { + "epoch": 19.48, + "learning_rate": 3.50663858266731e-08, + "loss": 0.0016, + "step": 63085 + }, + { + "epoch": 19.48, + "learning_rate": 3.502455246516823e-08, + "loss": 0.0011, + "step": 63086 + }, + { + "epoch": 19.48, + "learning_rate": 3.498274402788493e-08, + "loss": 0.0017, + "step": 63087 + }, + { + "epoch": 19.48, + "learning_rate": 3.494096051492646e-08, + "loss": 0.0015, + "step": 63088 + }, + { + "epoch": 19.48, + "learning_rate": 3.489920192639829e-08, + "loss": 0.0014, + "step": 63089 + }, + { + "epoch": 19.48, + "learning_rate": 3.485746826240477e-08, + "loss": 0.0014, + "step": 63090 + }, + { + "epoch": 19.48, + "learning_rate": 3.4815759523050274e-08, + "loss": 0.0015, + "step": 63091 + }, + { + "epoch": 19.48, + "learning_rate": 3.477407570843916e-08, + "loss": 0.0018, + "step": 63092 + }, + { + "epoch": 19.48, + "learning_rate": 3.473241681867468e-08, + "loss": 0.0016, + "step": 63093 + }, + { + "epoch": 19.48, + "learning_rate": 3.46907828538634e-08, + "loss": 0.0012, + "step": 63094 + }, + { + "epoch": 19.48, + "learning_rate": 3.4649173814107487e-08, + "loss": 0.0015, + "step": 63095 + }, + { + "epoch": 19.49, + "learning_rate": 3.460758969951128e-08, + "loss": 0.0016, + "step": 63096 + }, + { + "epoch": 19.49, + "learning_rate": 3.456603051017915e-08, + "loss": 0.0013, + "step": 63097 + }, + { + "epoch": 19.49, + "learning_rate": 3.4524496246215456e-08, + "loss": 0.0013, + "step": 63098 + }, + { + "epoch": 19.49, + "learning_rate": 3.448298690772345e-08, + "loss": 0.002, + "step": 63099 + }, + { + "epoch": 19.49, + "learning_rate": 3.444150249480638e-08, + "loss": 0.0017, + "step": 63100 + }, + { + "epoch": 19.49, + "learning_rate": 3.4400043007569716e-08, + "loss": 0.0019, + "step": 63101 + }, + { + "epoch": 19.49, + "learning_rate": 3.43586084461156e-08, + "loss": 0.0011, + "step": 63102 + }, + { + "epoch": 19.49, + "learning_rate": 3.4317198810548405e-08, + "loss": 0.0014, + "step": 63103 + }, + { + "epoch": 19.49, + "learning_rate": 3.427581410097136e-08, + "loss": 0.0009, + "step": 63104 + }, + { + "epoch": 19.49, + "learning_rate": 3.423445431748773e-08, + "loss": 0.0021, + "step": 63105 + }, + { + "epoch": 19.49, + "learning_rate": 3.4193119460201876e-08, + "loss": 0.0014, + "step": 63106 + }, + { + "epoch": 19.49, + "learning_rate": 3.415180952921704e-08, + "loss": 0.0013, + "step": 63107 + }, + { + "epoch": 19.49, + "learning_rate": 3.411052452463537e-08, + "loss": 0.0009, + "step": 63108 + }, + { + "epoch": 19.49, + "learning_rate": 3.4069264446561226e-08, + "loss": 0.0011, + "step": 63109 + }, + { + "epoch": 19.49, + "learning_rate": 3.402802929509785e-08, + "loss": 0.0014, + "step": 63110 + }, + { + "epoch": 19.49, + "learning_rate": 3.398681907034851e-08, + "loss": 0.0019, + "step": 63111 + }, + { + "epoch": 19.49, + "learning_rate": 3.394563377241533e-08, + "loss": 0.0024, + "step": 63112 + }, + { + "epoch": 19.49, + "learning_rate": 3.3904473401401574e-08, + "loss": 0.0015, + "step": 63113 + }, + { + "epoch": 19.49, + "learning_rate": 3.386333795741048e-08, + "loss": 0.0018, + "step": 63114 + }, + { + "epoch": 19.49, + "learning_rate": 3.38222274405442e-08, + "loss": 0.0018, + "step": 63115 + }, + { + "epoch": 19.49, + "learning_rate": 3.378114185090708e-08, + "loss": 0.0015, + "step": 63116 + }, + { + "epoch": 19.49, + "learning_rate": 3.374008118860128e-08, + "loss": 0.0013, + "step": 63117 + }, + { + "epoch": 19.49, + "learning_rate": 3.369904545372893e-08, + "loss": 0.0014, + "step": 63118 + }, + { + "epoch": 19.49, + "learning_rate": 3.3658034646393275e-08, + "loss": 0.0021, + "step": 63119 + }, + { + "epoch": 19.49, + "learning_rate": 3.361704876669647e-08, + "loss": 0.0019, + "step": 63120 + }, + { + "epoch": 19.49, + "learning_rate": 3.3576087814740644e-08, + "loss": 0.0014, + "step": 63121 + }, + { + "epoch": 19.49, + "learning_rate": 3.353515179062905e-08, + "loss": 0.0015, + "step": 63122 + }, + { + "epoch": 19.49, + "learning_rate": 3.349424069446494e-08, + "loss": 0.0014, + "step": 63123 + }, + { + "epoch": 19.49, + "learning_rate": 3.3453354526348234e-08, + "loss": 0.002, + "step": 63124 + }, + { + "epoch": 19.49, + "learning_rate": 3.341249328638219e-08, + "loss": 0.0016, + "step": 63125 + }, + { + "epoch": 19.49, + "learning_rate": 3.3371656974670045e-08, + "loss": 0.0013, + "step": 63126 + }, + { + "epoch": 19.49, + "learning_rate": 3.333084559131283e-08, + "loss": 0.0016, + "step": 63127 + }, + { + "epoch": 19.5, + "learning_rate": 3.3290059136413814e-08, + "loss": 0.0018, + "step": 63128 + }, + { + "epoch": 19.5, + "learning_rate": 3.3249297610072894e-08, + "loss": 0.0018, + "step": 63129 + }, + { + "epoch": 19.5, + "learning_rate": 3.3208561012394447e-08, + "loss": 0.0015, + "step": 63130 + }, + { + "epoch": 19.5, + "learning_rate": 3.316784934347839e-08, + "loss": 0.0017, + "step": 63131 + }, + { + "epoch": 19.5, + "learning_rate": 3.312716260342797e-08, + "loss": 0.0015, + "step": 63132 + }, + { + "epoch": 19.5, + "learning_rate": 3.308650079234421e-08, + "loss": 0.0012, + "step": 63133 + }, + { + "epoch": 19.5, + "learning_rate": 3.304586391032927e-08, + "loss": 0.0019, + "step": 63134 + }, + { + "epoch": 19.5, + "learning_rate": 3.3005251957484165e-08, + "loss": 0.0014, + "step": 63135 + }, + { + "epoch": 19.5, + "learning_rate": 3.296466493390993e-08, + "loss": 0.0014, + "step": 63136 + }, + { + "epoch": 19.5, + "learning_rate": 3.2924102839709815e-08, + "loss": 0.0016, + "step": 63137 + }, + { + "epoch": 19.5, + "learning_rate": 3.288356567498374e-08, + "loss": 0.0014, + "step": 63138 + }, + { + "epoch": 19.5, + "learning_rate": 3.284305343983496e-08, + "loss": 0.0013, + "step": 63139 + }, + { + "epoch": 19.5, + "learning_rate": 3.280256613436339e-08, + "loss": 0.0018, + "step": 63140 + }, + { + "epoch": 19.5, + "learning_rate": 3.276210375867006e-08, + "loss": 0.001, + "step": 63141 + }, + { + "epoch": 19.5, + "learning_rate": 3.2721666312856006e-08, + "loss": 0.0017, + "step": 63142 + }, + { + "epoch": 19.5, + "learning_rate": 3.268125379702336e-08, + "loss": 0.0015, + "step": 63143 + }, + { + "epoch": 19.5, + "learning_rate": 3.2640866211273156e-08, + "loss": 0.0019, + "step": 63144 + }, + { + "epoch": 19.5, + "learning_rate": 3.260050355570643e-08, + "loss": 0.0015, + "step": 63145 + }, + { + "epoch": 19.5, + "learning_rate": 3.25601658304231e-08, + "loss": 0.0013, + "step": 63146 + }, + { + "epoch": 19.5, + "learning_rate": 3.2519853035525295e-08, + "loss": 0.0024, + "step": 63147 + }, + { + "epoch": 19.5, + "learning_rate": 3.2479565171112945e-08, + "loss": 0.0014, + "step": 63148 + }, + { + "epoch": 19.5, + "learning_rate": 3.243930223728708e-08, + "loss": 0.0021, + "step": 63149 + }, + { + "epoch": 19.5, + "learning_rate": 3.239906423414874e-08, + "loss": 0.0013, + "step": 63150 + }, + { + "epoch": 19.5, + "learning_rate": 3.235885116179782e-08, + "loss": 0.0009, + "step": 63151 + }, + { + "epoch": 19.5, + "learning_rate": 3.231866302033537e-08, + "loss": 0.0021, + "step": 63152 + }, + { + "epoch": 19.5, + "learning_rate": 3.227849980986242e-08, + "loss": 0.0014, + "step": 63153 + }, + { + "epoch": 19.5, + "learning_rate": 3.2238361530479986e-08, + "loss": 0.0019, + "step": 63154 + }, + { + "epoch": 19.5, + "learning_rate": 3.2198248182285786e-08, + "loss": 0.0014, + "step": 63155 + }, + { + "epoch": 19.5, + "learning_rate": 3.2158159765381946e-08, + "loss": 0.0013, + "step": 63156 + }, + { + "epoch": 19.5, + "learning_rate": 3.211809627986951e-08, + "loss": 0.0016, + "step": 63157 + }, + { + "epoch": 19.5, + "learning_rate": 3.2078057725846156e-08, + "loss": 0.0016, + "step": 63158 + }, + { + "epoch": 19.5, + "learning_rate": 3.203804410341516e-08, + "loss": 0.0014, + "step": 63159 + }, + { + "epoch": 19.5, + "learning_rate": 3.19980554126742e-08, + "loss": 0.0016, + "step": 63160 + }, + { + "epoch": 19.51, + "learning_rate": 3.195809165372432e-08, + "loss": 0.0016, + "step": 63161 + }, + { + "epoch": 19.51, + "learning_rate": 3.191815282666544e-08, + "loss": 0.001, + "step": 63162 + }, + { + "epoch": 19.51, + "learning_rate": 3.187823893159747e-08, + "loss": 0.0016, + "step": 63163 + }, + { + "epoch": 19.51, + "learning_rate": 3.1838349968620344e-08, + "loss": 0.0014, + "step": 63164 + }, + { + "epoch": 19.51, + "learning_rate": 3.179848593783286e-08, + "loss": 0.0015, + "step": 63165 + }, + { + "epoch": 19.51, + "learning_rate": 3.175864683933605e-08, + "loss": 0.0018, + "step": 63166 + }, + { + "epoch": 19.51, + "learning_rate": 3.171883267322873e-08, + "loss": 0.0016, + "step": 63167 + }, + { + "epoch": 19.51, + "learning_rate": 3.1679043439610813e-08, + "loss": 0.0014, + "step": 63168 + }, + { + "epoch": 19.51, + "learning_rate": 3.163927913858111e-08, + "loss": 0.0016, + "step": 63169 + }, + { + "epoch": 19.51, + "learning_rate": 3.159953977024066e-08, + "loss": 0.0019, + "step": 63170 + }, + { + "epoch": 19.51, + "learning_rate": 3.1559825334687156e-08, + "loss": 0.002, + "step": 63171 + }, + { + "epoch": 19.51, + "learning_rate": 3.152013583202051e-08, + "loss": 0.0008, + "step": 63172 + }, + { + "epoch": 19.51, + "learning_rate": 3.1480471262340665e-08, + "loss": 0.0018, + "step": 63173 + }, + { + "epoch": 19.51, + "learning_rate": 3.14408316257464e-08, + "loss": 0.0017, + "step": 63174 + }, + { + "epoch": 19.51, + "learning_rate": 3.140121692233655e-08, + "loss": 0.0014, + "step": 63175 + }, + { + "epoch": 19.51, + "learning_rate": 3.136162715220992e-08, + "loss": 0.0014, + "step": 63176 + }, + { + "epoch": 19.51, + "learning_rate": 3.132206231546642e-08, + "loss": 0.0014, + "step": 63177 + }, + { + "epoch": 19.51, + "learning_rate": 3.128252241220486e-08, + "loss": 0.0012, + "step": 63178 + }, + { + "epoch": 19.51, + "learning_rate": 3.124300744252407e-08, + "loss": 0.0016, + "step": 63179 + }, + { + "epoch": 19.51, + "learning_rate": 3.1203517406521725e-08, + "loss": 0.0015, + "step": 63180 + }, + { + "epoch": 19.51, + "learning_rate": 3.1164052304298866e-08, + "loss": 0.0013, + "step": 63181 + }, + { + "epoch": 19.51, + "learning_rate": 3.112461213595208e-08, + "loss": 0.0012, + "step": 63182 + }, + { + "epoch": 19.51, + "learning_rate": 3.108519690158018e-08, + "loss": 0.0011, + "step": 63183 + }, + { + "epoch": 19.51, + "learning_rate": 3.10458066012842e-08, + "loss": 0.0017, + "step": 63184 + }, + { + "epoch": 19.51, + "learning_rate": 3.100644123515961e-08, + "loss": 0.0037, + "step": 63185 + }, + { + "epoch": 19.51, + "learning_rate": 3.096710080330634e-08, + "loss": 0.0013, + "step": 63186 + }, + { + "epoch": 19.51, + "learning_rate": 3.092778530582319e-08, + "loss": 0.002, + "step": 63187 + }, + { + "epoch": 19.51, + "learning_rate": 3.088849474280675e-08, + "loss": 0.0014, + "step": 63188 + }, + { + "epoch": 19.51, + "learning_rate": 3.084922911435695e-08, + "loss": 0.0013, + "step": 63189 + }, + { + "epoch": 19.51, + "learning_rate": 3.080998842057259e-08, + "loss": 0.0016, + "step": 63190 + }, + { + "epoch": 19.51, + "learning_rate": 3.0770772661549154e-08, + "loss": 0.0013, + "step": 63191 + }, + { + "epoch": 19.51, + "learning_rate": 3.073158183738656e-08, + "loss": 0.001, + "step": 63192 + }, + { + "epoch": 19.52, + "learning_rate": 3.069241594818362e-08, + "loss": 0.002, + "step": 63193 + }, + { + "epoch": 19.52, + "learning_rate": 3.065327499403581e-08, + "loss": 0.0014, + "step": 63194 + }, + { + "epoch": 19.52, + "learning_rate": 3.061415897504416e-08, + "loss": 0.0013, + "step": 63195 + }, + { + "epoch": 19.52, + "learning_rate": 3.0575067891303044e-08, + "loss": 0.0016, + "step": 63196 + }, + { + "epoch": 19.52, + "learning_rate": 3.0536001742913493e-08, + "loss": 0.0012, + "step": 63197 + }, + { + "epoch": 19.52, + "learning_rate": 3.049696052997098e-08, + "loss": 0.0019, + "step": 63198 + }, + { + "epoch": 19.52, + "learning_rate": 3.0457944252573203e-08, + "loss": 0.0013, + "step": 63199 + }, + { + "epoch": 19.52, + "learning_rate": 3.041895291082009e-08, + "loss": 0.002, + "step": 63200 + }, + { + "epoch": 19.52, + "learning_rate": 3.0379986504806e-08, + "loss": 0.0015, + "step": 63201 + }, + { + "epoch": 19.52, + "learning_rate": 3.034104503463087e-08, + "loss": 0.0014, + "step": 63202 + }, + { + "epoch": 19.52, + "learning_rate": 3.030212850039016e-08, + "loss": 0.0018, + "step": 63203 + }, + { + "epoch": 19.52, + "learning_rate": 3.0263236902182694e-08, + "loss": 0.0014, + "step": 63204 + }, + { + "epoch": 19.52, + "learning_rate": 3.022437024010505e-08, + "loss": 0.0014, + "step": 63205 + }, + { + "epoch": 19.52, + "learning_rate": 3.0185528514254936e-08, + "loss": 0.0013, + "step": 63206 + }, + { + "epoch": 19.52, + "learning_rate": 3.0146711724728936e-08, + "loss": 0.0014, + "step": 63207 + }, + { + "epoch": 19.52, + "learning_rate": 3.010791987162476e-08, + "loss": 0.0012, + "step": 63208 + }, + { + "epoch": 19.52, + "learning_rate": 3.0069152955038984e-08, + "loss": 0.0015, + "step": 63209 + }, + { + "epoch": 19.52, + "learning_rate": 3.003041097506931e-08, + "loss": 0.0014, + "step": 63210 + }, + { + "epoch": 19.52, + "learning_rate": 2.999169393181123e-08, + "loss": 0.0013, + "step": 63211 + }, + { + "epoch": 19.52, + "learning_rate": 2.9953001825362424e-08, + "loss": 0.0012, + "step": 63212 + }, + { + "epoch": 19.52, + "learning_rate": 2.99143346558195e-08, + "loss": 0.0014, + "step": 63213 + }, + { + "epoch": 19.52, + "learning_rate": 2.9875692423279036e-08, + "loss": 0.0015, + "step": 63214 + }, + { + "epoch": 19.52, + "learning_rate": 2.9837075127837626e-08, + "loss": 0.0012, + "step": 63215 + }, + { + "epoch": 19.52, + "learning_rate": 2.979848276959296e-08, + "loss": 0.0011, + "step": 63216 + }, + { + "epoch": 19.52, + "learning_rate": 2.9759915348640534e-08, + "loss": 0.0017, + "step": 63217 + }, + { + "epoch": 19.52, + "learning_rate": 2.9721372865076924e-08, + "loss": 0.0016, + "step": 63218 + }, + { + "epoch": 19.52, + "learning_rate": 2.9682855318998728e-08, + "loss": 0.0015, + "step": 63219 + }, + { + "epoch": 19.52, + "learning_rate": 2.964436271050253e-08, + "loss": 0.0016, + "step": 63220 + }, + { + "epoch": 19.52, + "learning_rate": 2.9605895039683808e-08, + "loss": 0.0014, + "step": 63221 + }, + { + "epoch": 19.52, + "learning_rate": 2.9567452306639156e-08, + "loss": 0.0011, + "step": 63222 + }, + { + "epoch": 19.52, + "learning_rate": 2.952903451146405e-08, + "loss": 0.0015, + "step": 63223 + }, + { + "epoch": 19.52, + "learning_rate": 2.949064165425619e-08, + "loss": 0.0015, + "step": 63224 + }, + { + "epoch": 19.52, + "learning_rate": 2.945227373511106e-08, + "loss": 0.0011, + "step": 63225 + }, + { + "epoch": 19.53, + "learning_rate": 2.9413930754124132e-08, + "loss": 0.0017, + "step": 63226 + }, + { + "epoch": 19.53, + "learning_rate": 2.9375612711392e-08, + "loss": 0.0013, + "step": 63227 + }, + { + "epoch": 19.53, + "learning_rate": 2.9337319607009028e-08, + "loss": 0.002, + "step": 63228 + }, + { + "epoch": 19.53, + "learning_rate": 2.9299051441071813e-08, + "loss": 0.0013, + "step": 63229 + }, + { + "epoch": 19.53, + "learning_rate": 2.926080821367694e-08, + "loss": 0.0021, + "step": 63230 + }, + { + "epoch": 19.53, + "learning_rate": 2.9222589924918776e-08, + "loss": 0.0011, + "step": 63231 + }, + { + "epoch": 19.53, + "learning_rate": 2.9184396574893913e-08, + "loss": 0.0015, + "step": 63232 + }, + { + "epoch": 19.53, + "learning_rate": 2.9146228163696722e-08, + "loss": 0.0016, + "step": 63233 + }, + { + "epoch": 19.53, + "learning_rate": 2.910808469142379e-08, + "loss": 0.0015, + "step": 63234 + }, + { + "epoch": 19.53, + "learning_rate": 2.9069966158170592e-08, + "loss": 0.0013, + "step": 63235 + }, + { + "epoch": 19.53, + "learning_rate": 2.9031872564031504e-08, + "loss": 0.001, + "step": 63236 + }, + { + "epoch": 19.53, + "learning_rate": 2.8993803909103113e-08, + "loss": 0.0015, + "step": 63237 + }, + { + "epoch": 19.53, + "learning_rate": 2.8955760193478678e-08, + "loss": 0.0015, + "step": 63238 + }, + { + "epoch": 19.53, + "learning_rate": 2.8917741417254784e-08, + "loss": 0.0013, + "step": 63239 + }, + { + "epoch": 19.53, + "learning_rate": 2.8879747580526918e-08, + "loss": 0.0011, + "step": 63240 + }, + { + "epoch": 19.53, + "learning_rate": 2.8841778683388332e-08, + "loss": 0.0024, + "step": 63241 + }, + { + "epoch": 19.53, + "learning_rate": 2.880383472593562e-08, + "loss": 0.0014, + "step": 63242 + }, + { + "epoch": 19.53, + "learning_rate": 2.876591570826315e-08, + "loss": 0.0024, + "step": 63243 + }, + { + "epoch": 19.53, + "learning_rate": 2.8728021630466397e-08, + "loss": 0.0015, + "step": 63244 + }, + { + "epoch": 19.53, + "learning_rate": 2.8690152492638623e-08, + "loss": 0.0016, + "step": 63245 + }, + { + "epoch": 19.53, + "learning_rate": 2.865230829487531e-08, + "loss": 0.002, + "step": 63246 + }, + { + "epoch": 19.53, + "learning_rate": 2.8614489037271932e-08, + "loss": 0.0015, + "step": 63247 + }, + { + "epoch": 19.53, + "learning_rate": 2.857669471992175e-08, + "loss": 0.0013, + "step": 63248 + }, + { + "epoch": 19.53, + "learning_rate": 2.8538925342920244e-08, + "loss": 0.0022, + "step": 63249 + }, + { + "epoch": 19.53, + "learning_rate": 2.850118090636178e-08, + "loss": 0.0011, + "step": 63250 + }, + { + "epoch": 19.53, + "learning_rate": 2.846346141034073e-08, + "loss": 0.0014, + "step": 63251 + }, + { + "epoch": 19.53, + "learning_rate": 2.8425766854950354e-08, + "loss": 0.0013, + "step": 63252 + }, + { + "epoch": 19.53, + "learning_rate": 2.8388097240287237e-08, + "loss": 0.0015, + "step": 63253 + }, + { + "epoch": 19.53, + "learning_rate": 2.8350452566442422e-08, + "loss": 0.0015, + "step": 63254 + }, + { + "epoch": 19.53, + "learning_rate": 2.8312832833513603e-08, + "loss": 0.0013, + "step": 63255 + }, + { + "epoch": 19.53, + "learning_rate": 2.8275238041591822e-08, + "loss": 0.0012, + "step": 63256 + }, + { + "epoch": 19.53, + "learning_rate": 2.823766819077256e-08, + "loss": 0.0016, + "step": 63257 + }, + { + "epoch": 19.54, + "learning_rate": 2.820012328115018e-08, + "loss": 0.0018, + "step": 63258 + }, + { + "epoch": 19.54, + "learning_rate": 2.8162603312817947e-08, + "loss": 0.0011, + "step": 63259 + }, + { + "epoch": 19.54, + "learning_rate": 2.8125108285869117e-08, + "loss": 0.0017, + "step": 63260 + }, + { + "epoch": 19.54, + "learning_rate": 2.808763820039917e-08, + "loss": 0.0016, + "step": 63261 + }, + { + "epoch": 19.54, + "learning_rate": 2.8050193056500252e-08, + "loss": 0.0017, + "step": 63262 + }, + { + "epoch": 19.54, + "learning_rate": 2.8012772854266735e-08, + "loss": 0.0013, + "step": 63263 + }, + { + "epoch": 19.54, + "learning_rate": 2.7975377593791876e-08, + "loss": 0.0019, + "step": 63264 + }, + { + "epoch": 19.54, + "learning_rate": 2.7938007275168934e-08, + "loss": 0.0017, + "step": 63265 + }, + { + "epoch": 19.54, + "learning_rate": 2.7900661898492277e-08, + "loss": 0.0018, + "step": 63266 + }, + { + "epoch": 19.54, + "learning_rate": 2.7863341463855166e-08, + "loss": 0.0017, + "step": 63267 + }, + { + "epoch": 19.54, + "learning_rate": 2.7826045971349748e-08, + "loss": 0.0011, + "step": 63268 + }, + { + "epoch": 19.54, + "learning_rate": 2.7788775421071502e-08, + "loss": 0.0013, + "step": 63269 + }, + { + "epoch": 19.54, + "learning_rate": 2.7751529813111466e-08, + "loss": 0.0013, + "step": 63270 + }, + { + "epoch": 19.54, + "learning_rate": 2.771430914756401e-08, + "loss": 0.0012, + "step": 63271 + }, + { + "epoch": 19.54, + "learning_rate": 2.7677113424521286e-08, + "loss": 0.0018, + "step": 63272 + }, + { + "epoch": 19.54, + "learning_rate": 2.7639942644077655e-08, + "loss": 0.0014, + "step": 63273 + }, + { + "epoch": 19.54, + "learning_rate": 2.7602796806325272e-08, + "loss": 0.0014, + "step": 63274 + }, + { + "epoch": 19.54, + "learning_rate": 2.756567591135628e-08, + "loss": 0.0016, + "step": 63275 + }, + { + "epoch": 19.54, + "learning_rate": 2.7528579959265057e-08, + "loss": 0.0011, + "step": 63276 + }, + { + "epoch": 19.54, + "learning_rate": 2.7491508950144853e-08, + "loss": 0.0014, + "step": 63277 + }, + { + "epoch": 19.54, + "learning_rate": 2.7454462884085597e-08, + "loss": 0.0013, + "step": 63278 + }, + { + "epoch": 19.54, + "learning_rate": 2.741744176118277e-08, + "loss": 0.0014, + "step": 63279 + }, + { + "epoch": 19.54, + "learning_rate": 2.7380445581527417e-08, + "loss": 0.0016, + "step": 63280 + }, + { + "epoch": 19.54, + "learning_rate": 2.7343474345211673e-08, + "loss": 0.0012, + "step": 63281 + }, + { + "epoch": 19.54, + "learning_rate": 2.7306528052329917e-08, + "loss": 0.0015, + "step": 63282 + }, + { + "epoch": 19.54, + "learning_rate": 2.7269606702972074e-08, + "loss": 0.0014, + "step": 63283 + }, + { + "epoch": 19.54, + "learning_rate": 2.7232710297233622e-08, + "loss": 0.0007, + "step": 63284 + }, + { + "epoch": 19.54, + "learning_rate": 2.719583883520338e-08, + "loss": 0.0016, + "step": 63285 + }, + { + "epoch": 19.54, + "learning_rate": 2.7158992316976828e-08, + "loss": 0.0016, + "step": 63286 + }, + { + "epoch": 19.54, + "learning_rate": 2.7122170742642785e-08, + "loss": 0.0017, + "step": 63287 + }, + { + "epoch": 19.54, + "learning_rate": 2.7085374112296724e-08, + "loss": 0.0017, + "step": 63288 + }, + { + "epoch": 19.54, + "learning_rate": 2.704860242602858e-08, + "loss": 0.0017, + "step": 63289 + }, + { + "epoch": 19.55, + "learning_rate": 2.70118556839305e-08, + "loss": 0.0018, + "step": 63290 + }, + { + "epoch": 19.55, + "learning_rate": 2.697513388609463e-08, + "loss": 0.0022, + "step": 63291 + }, + { + "epoch": 19.55, + "learning_rate": 2.693843703261423e-08, + "loss": 0.0021, + "step": 63292 + }, + { + "epoch": 19.55, + "learning_rate": 2.6901765123578116e-08, + "loss": 0.0013, + "step": 63293 + }, + { + "epoch": 19.55, + "learning_rate": 2.686511815908066e-08, + "loss": 0.0014, + "step": 63294 + }, + { + "epoch": 19.55, + "learning_rate": 2.682849613921179e-08, + "loss": 0.0014, + "step": 63295 + }, + { + "epoch": 19.55, + "learning_rate": 2.6791899064064765e-08, + "loss": 0.0017, + "step": 63296 + }, + { + "epoch": 19.55, + "learning_rate": 2.6755326933729507e-08, + "loss": 0.0015, + "step": 63297 + }, + { + "epoch": 19.55, + "learning_rate": 2.6718779748299285e-08, + "loss": 0.0014, + "step": 63298 + }, + { + "epoch": 19.55, + "learning_rate": 2.668225750786291e-08, + "loss": 0.0015, + "step": 63299 + }, + { + "epoch": 19.55, + "learning_rate": 2.6645760212513637e-08, + "loss": 0.0009, + "step": 63300 + }, + { + "epoch": 19.55, + "learning_rate": 2.6609287862342514e-08, + "loss": 0.0017, + "step": 63301 + }, + { + "epoch": 19.55, + "learning_rate": 2.6572840457440574e-08, + "loss": 0.0015, + "step": 63302 + }, + { + "epoch": 19.55, + "learning_rate": 2.6536417997898856e-08, + "loss": 0.0012, + "step": 63303 + }, + { + "epoch": 19.55, + "learning_rate": 2.650002048380951e-08, + "loss": 0.0014, + "step": 63304 + }, + { + "epoch": 19.55, + "learning_rate": 2.6463647915261347e-08, + "loss": 0.0016, + "step": 63305 + }, + { + "epoch": 19.55, + "learning_rate": 2.6427300292347637e-08, + "loss": 0.0014, + "step": 63306 + }, + { + "epoch": 19.55, + "learning_rate": 2.639097761515719e-08, + "loss": 0.002, + "step": 63307 + }, + { + "epoch": 19.55, + "learning_rate": 2.6354679883783262e-08, + "loss": 0.0018, + "step": 63308 + }, + { + "epoch": 19.55, + "learning_rate": 2.631840709831468e-08, + "loss": 0.0013, + "step": 63309 + }, + { + "epoch": 19.55, + "learning_rate": 2.628215925884359e-08, + "loss": 0.0014, + "step": 63310 + }, + { + "epoch": 19.55, + "learning_rate": 2.6245936365458802e-08, + "loss": 0.0013, + "step": 63311 + }, + { + "epoch": 19.55, + "learning_rate": 2.6209738418252472e-08, + "loss": 0.0013, + "step": 63312 + }, + { + "epoch": 19.55, + "learning_rate": 2.6173565417315637e-08, + "loss": 0.0014, + "step": 63313 + }, + { + "epoch": 19.55, + "learning_rate": 2.6137417362737117e-08, + "loss": 0.0014, + "step": 63314 + }, + { + "epoch": 19.55, + "learning_rate": 2.6101294254606835e-08, + "loss": 0.0017, + "step": 63315 + }, + { + "epoch": 19.55, + "learning_rate": 2.6065196093018053e-08, + "loss": 0.0011, + "step": 63316 + }, + { + "epoch": 19.55, + "learning_rate": 2.6029122878058477e-08, + "loss": 0.0012, + "step": 63317 + }, + { + "epoch": 19.55, + "learning_rate": 2.5993074609819147e-08, + "loss": 0.0013, + "step": 63318 + }, + { + "epoch": 19.55, + "learning_rate": 2.59570512883911e-08, + "loss": 0.0016, + "step": 63319 + }, + { + "epoch": 19.55, + "learning_rate": 2.5921052913863153e-08, + "loss": 0.0016, + "step": 63320 + }, + { + "epoch": 19.55, + "learning_rate": 2.588507948632524e-08, + "loss": 0.0017, + "step": 63321 + }, + { + "epoch": 19.55, + "learning_rate": 2.5849131005868387e-08, + "loss": 0.0014, + "step": 63322 + }, + { + "epoch": 19.56, + "learning_rate": 2.5813207472582535e-08, + "loss": 0.002, + "step": 63323 + }, + { + "epoch": 19.56, + "learning_rate": 2.5777308886556496e-08, + "loss": 0.0012, + "step": 63324 + }, + { + "epoch": 19.56, + "learning_rate": 2.5741435247880197e-08, + "loss": 0.0014, + "step": 63325 + }, + { + "epoch": 19.56, + "learning_rate": 2.570558655664468e-08, + "loss": 0.0017, + "step": 63326 + }, + { + "epoch": 19.56, + "learning_rate": 2.566976281293765e-08, + "loss": 0.0017, + "step": 63327 + }, + { + "epoch": 19.56, + "learning_rate": 2.5633964016850144e-08, + "loss": 0.0015, + "step": 63328 + }, + { + "epoch": 19.56, + "learning_rate": 2.5598190168472093e-08, + "loss": 0.0017, + "step": 63329 + }, + { + "epoch": 19.56, + "learning_rate": 2.5562441267891202e-08, + "loss": 0.0016, + "step": 63330 + }, + { + "epoch": 19.56, + "learning_rate": 2.5526717315198512e-08, + "loss": 0.0015, + "step": 63331 + }, + { + "epoch": 19.56, + "learning_rate": 2.549101831048284e-08, + "loss": 0.002, + "step": 63332 + }, + { + "epoch": 19.56, + "learning_rate": 2.5455344253831894e-08, + "loss": 0.002, + "step": 63333 + }, + { + "epoch": 19.56, + "learning_rate": 2.5419695145337818e-08, + "loss": 0.0015, + "step": 63334 + }, + { + "epoch": 19.56, + "learning_rate": 2.5384070985088326e-08, + "loss": 0.0011, + "step": 63335 + }, + { + "epoch": 19.56, + "learning_rate": 2.5348471773172234e-08, + "loss": 0.0014, + "step": 63336 + }, + { + "epoch": 19.56, + "learning_rate": 2.531289750967836e-08, + "loss": 0.0019, + "step": 63337 + }, + { + "epoch": 19.56, + "learning_rate": 2.5277348194696628e-08, + "loss": 0.0013, + "step": 63338 + }, + { + "epoch": 19.56, + "learning_rate": 2.524182382831586e-08, + "loss": 0.0012, + "step": 63339 + }, + { + "epoch": 19.56, + "learning_rate": 2.520632441062376e-08, + "loss": 0.0013, + "step": 63340 + }, + { + "epoch": 19.56, + "learning_rate": 2.5170849941710262e-08, + "loss": 0.0014, + "step": 63341 + }, + { + "epoch": 19.56, + "learning_rate": 2.513540042166418e-08, + "loss": 0.0013, + "step": 63342 + }, + { + "epoch": 19.56, + "learning_rate": 2.5099975850573222e-08, + "loss": 0.001, + "step": 63343 + }, + { + "epoch": 19.56, + "learning_rate": 2.5064576228527316e-08, + "loss": 0.0014, + "step": 63344 + }, + { + "epoch": 19.56, + "learning_rate": 2.502920155561417e-08, + "loss": 0.0011, + "step": 63345 + }, + { + "epoch": 19.56, + "learning_rate": 2.499385183192149e-08, + "loss": 0.0012, + "step": 63346 + }, + { + "epoch": 19.56, + "learning_rate": 2.4958527057539206e-08, + "loss": 0.0025, + "step": 63347 + }, + { + "epoch": 19.56, + "learning_rate": 2.4923227232553915e-08, + "loss": 0.0015, + "step": 63348 + }, + { + "epoch": 19.56, + "learning_rate": 2.4887952357056656e-08, + "loss": 0.0008, + "step": 63349 + }, + { + "epoch": 19.56, + "learning_rate": 2.4852702431132913e-08, + "loss": 0.0016, + "step": 63350 + }, + { + "epoch": 19.56, + "learning_rate": 2.481747745487151e-08, + "loss": 0.0012, + "step": 63351 + }, + { + "epoch": 19.56, + "learning_rate": 2.4782277428361256e-08, + "loss": 0.0013, + "step": 63352 + }, + { + "epoch": 19.56, + "learning_rate": 2.4747102351689866e-08, + "loss": 0.0012, + "step": 63353 + }, + { + "epoch": 19.56, + "learning_rate": 2.4711952224946157e-08, + "loss": 0.0012, + "step": 63354 + }, + { + "epoch": 19.57, + "learning_rate": 2.4676827048216723e-08, + "loss": 0.0011, + "step": 63355 + }, + { + "epoch": 19.57, + "learning_rate": 2.4641726821590382e-08, + "loss": 0.0024, + "step": 63356 + }, + { + "epoch": 19.57, + "learning_rate": 2.4606651545153738e-08, + "loss": 0.0016, + "step": 63357 + }, + { + "epoch": 19.57, + "learning_rate": 2.45716012189956e-08, + "loss": 0.0019, + "step": 63358 + }, + { + "epoch": 19.57, + "learning_rate": 2.453657584320368e-08, + "loss": 0.0016, + "step": 63359 + }, + { + "epoch": 19.57, + "learning_rate": 2.4501575417864577e-08, + "loss": 0.0017, + "step": 63360 + }, + { + "epoch": 19.57, + "learning_rate": 2.4466599943065994e-08, + "loss": 0.0015, + "step": 63361 + }, + { + "epoch": 19.57, + "learning_rate": 2.4431649418896753e-08, + "loss": 0.0012, + "step": 63362 + }, + { + "epoch": 19.57, + "learning_rate": 2.4396723845443448e-08, + "loss": 0.0011, + "step": 63363 + }, + { + "epoch": 19.57, + "learning_rate": 2.436182322279268e-08, + "loss": 0.0015, + "step": 63364 + }, + { + "epoch": 19.57, + "learning_rate": 2.4326947551032155e-08, + "loss": 0.0017, + "step": 63365 + }, + { + "epoch": 19.57, + "learning_rate": 2.4292096830250688e-08, + "loss": 0.0013, + "step": 63366 + }, + { + "epoch": 19.57, + "learning_rate": 2.4257271060533773e-08, + "loss": 0.0016, + "step": 63367 + }, + { + "epoch": 19.57, + "learning_rate": 2.4222470241968e-08, + "loss": 0.0014, + "step": 63368 + }, + { + "epoch": 19.57, + "learning_rate": 2.418769437464219e-08, + "loss": 0.0011, + "step": 63369 + }, + { + "epoch": 19.57, + "learning_rate": 2.415294345864183e-08, + "loss": 0.0016, + "step": 63370 + }, + { + "epoch": 19.57, + "learning_rate": 2.411821749405463e-08, + "loss": 0.0017, + "step": 63371 + }, + { + "epoch": 19.57, + "learning_rate": 2.4083516480967185e-08, + "loss": 0.0019, + "step": 63372 + }, + { + "epoch": 19.57, + "learning_rate": 2.40488404194672e-08, + "loss": 0.0023, + "step": 63373 + }, + { + "epoch": 19.57, + "learning_rate": 2.4014189309639058e-08, + "loss": 0.0011, + "step": 63374 + }, + { + "epoch": 19.57, + "learning_rate": 2.397956315157268e-08, + "loss": 0.0016, + "step": 63375 + }, + { + "epoch": 19.57, + "learning_rate": 2.394496194535134e-08, + "loss": 0.0023, + "step": 63376 + }, + { + "epoch": 19.57, + "learning_rate": 2.3910385691063855e-08, + "loss": 0.0017, + "step": 63377 + }, + { + "epoch": 19.57, + "learning_rate": 2.3875834388795705e-08, + "loss": 0.0016, + "step": 63378 + }, + { + "epoch": 19.57, + "learning_rate": 2.3841308038634603e-08, + "loss": 0.0012, + "step": 63379 + }, + { + "epoch": 19.57, + "learning_rate": 2.3806806640664924e-08, + "loss": 0.0011, + "step": 63380 + }, + { + "epoch": 19.57, + "learning_rate": 2.377233019497438e-08, + "loss": 0.0015, + "step": 63381 + }, + { + "epoch": 19.57, + "learning_rate": 2.3737878701648455e-08, + "loss": 0.0015, + "step": 63382 + }, + { + "epoch": 19.57, + "learning_rate": 2.3703452160773745e-08, + "loss": 0.0014, + "step": 63383 + }, + { + "epoch": 19.57, + "learning_rate": 2.3669050572436848e-08, + "loss": 0.0012, + "step": 63384 + }, + { + "epoch": 19.57, + "learning_rate": 2.363467393672214e-08, + "loss": 0.0013, + "step": 63385 + }, + { + "epoch": 19.57, + "learning_rate": 2.3600322253718445e-08, + "loss": 0.0011, + "step": 63386 + }, + { + "epoch": 19.58, + "learning_rate": 2.356599552350791e-08, + "loss": 0.0016, + "step": 63387 + }, + { + "epoch": 19.58, + "learning_rate": 2.353169374617936e-08, + "loss": 0.0018, + "step": 63388 + }, + { + "epoch": 19.58, + "learning_rate": 2.3497416921818282e-08, + "loss": 0.0014, + "step": 63389 + }, + { + "epoch": 19.58, + "learning_rate": 2.346316505050905e-08, + "loss": 0.0016, + "step": 63390 + }, + { + "epoch": 19.58, + "learning_rate": 2.3428938132338265e-08, + "loss": 0.0018, + "step": 63391 + }, + { + "epoch": 19.58, + "learning_rate": 2.3394736167390298e-08, + "loss": 0.0018, + "step": 63392 + }, + { + "epoch": 19.58, + "learning_rate": 2.336055915575286e-08, + "loss": 0.0012, + "step": 63393 + }, + { + "epoch": 19.58, + "learning_rate": 2.3326407097510328e-08, + "loss": 0.0014, + "step": 63394 + }, + { + "epoch": 19.58, + "learning_rate": 2.329227999274708e-08, + "loss": 0.0012, + "step": 63395 + }, + { + "epoch": 19.58, + "learning_rate": 2.3258177841550823e-08, + "loss": 0.0016, + "step": 63396 + }, + { + "epoch": 19.58, + "learning_rate": 2.322410064400482e-08, + "loss": 0.0011, + "step": 63397 + }, + { + "epoch": 19.58, + "learning_rate": 2.3190048400194566e-08, + "loss": 0.0013, + "step": 63398 + }, + { + "epoch": 19.58, + "learning_rate": 2.315602111020554e-08, + "loss": 0.0013, + "step": 63399 + }, + { + "epoch": 19.58, + "learning_rate": 2.3122018774124344e-08, + "loss": 0.0012, + "step": 63400 + }, + { + "epoch": 19.58, + "learning_rate": 2.3088041392034245e-08, + "loss": 0.0022, + "step": 63401 + }, + { + "epoch": 19.58, + "learning_rate": 2.3054088964019616e-08, + "loss": 0.0014, + "step": 63402 + }, + { + "epoch": 19.58, + "learning_rate": 2.302016149016706e-08, + "loss": 0.0018, + "step": 63403 + }, + { + "epoch": 19.58, + "learning_rate": 2.2986258970560948e-08, + "loss": 0.0015, + "step": 63404 + }, + { + "epoch": 19.58, + "learning_rate": 2.295238140528455e-08, + "loss": 0.0018, + "step": 63405 + }, + { + "epoch": 19.58, + "learning_rate": 2.2918528794425577e-08, + "loss": 0.0016, + "step": 63406 + }, + { + "epoch": 19.58, + "learning_rate": 2.288470113806729e-08, + "loss": 0.0015, + "step": 63407 + }, + { + "epoch": 19.58, + "learning_rate": 2.2850898436292958e-08, + "loss": 0.0013, + "step": 63408 + }, + { + "epoch": 19.58, + "learning_rate": 2.2817120689188067e-08, + "loss": 0.0014, + "step": 63409 + }, + { + "epoch": 19.58, + "learning_rate": 2.2783367896838105e-08, + "loss": 0.0016, + "step": 63410 + }, + { + "epoch": 19.58, + "learning_rate": 2.274964005932634e-08, + "loss": 0.0014, + "step": 63411 + }, + { + "epoch": 19.58, + "learning_rate": 2.2715937176737146e-08, + "loss": 0.0013, + "step": 63412 + }, + { + "epoch": 19.58, + "learning_rate": 2.2682259249156013e-08, + "loss": 0.0014, + "step": 63413 + }, + { + "epoch": 19.58, + "learning_rate": 2.2648606276665098e-08, + "loss": 0.0013, + "step": 63414 + }, + { + "epoch": 19.58, + "learning_rate": 2.2614978259350994e-08, + "loss": 0.0014, + "step": 63415 + }, + { + "epoch": 19.58, + "learning_rate": 2.2581375197295863e-08, + "loss": 0.0016, + "step": 63416 + }, + { + "epoch": 19.58, + "learning_rate": 2.2547797090585187e-08, + "loss": 0.002, + "step": 63417 + }, + { + "epoch": 19.58, + "learning_rate": 2.2514243939301127e-08, + "loss": 0.0019, + "step": 63418 + }, + { + "epoch": 19.58, + "learning_rate": 2.248071574352917e-08, + "loss": 0.002, + "step": 63419 + }, + { + "epoch": 19.59, + "learning_rate": 2.2447212503353687e-08, + "loss": 0.0015, + "step": 63420 + }, + { + "epoch": 19.59, + "learning_rate": 2.2413734218856842e-08, + "loss": 0.0014, + "step": 63421 + }, + { + "epoch": 19.59, + "learning_rate": 2.2380280890123008e-08, + "loss": 0.0012, + "step": 63422 + }, + { + "epoch": 19.59, + "learning_rate": 2.2346852517235452e-08, + "loss": 0.0011, + "step": 63423 + }, + { + "epoch": 19.59, + "learning_rate": 2.231344910027855e-08, + "loss": 0.0012, + "step": 63424 + }, + { + "epoch": 19.59, + "learning_rate": 2.2280070639335572e-08, + "loss": 0.0017, + "step": 63425 + }, + { + "epoch": 19.59, + "learning_rate": 2.224671713448978e-08, + "loss": 0.0021, + "step": 63426 + }, + { + "epoch": 19.59, + "learning_rate": 2.2213388585824447e-08, + "loss": 0.0022, + "step": 63427 + }, + { + "epoch": 19.59, + "learning_rate": 2.2180084993423945e-08, + "loss": 0.0013, + "step": 63428 + }, + { + "epoch": 19.59, + "learning_rate": 2.214680635737043e-08, + "loss": 0.002, + "step": 63429 + }, + { + "epoch": 19.59, + "learning_rate": 2.2113552677748286e-08, + "loss": 0.0013, + "step": 63430 + }, + { + "epoch": 19.59, + "learning_rate": 2.208032395463966e-08, + "loss": 0.0016, + "step": 63431 + }, + { + "epoch": 19.59, + "learning_rate": 2.2047120188127825e-08, + "loss": 0.0016, + "step": 63432 + }, + { + "epoch": 19.59, + "learning_rate": 2.2013941378296044e-08, + "loss": 0.0013, + "step": 63433 + }, + { + "epoch": 19.59, + "learning_rate": 2.1980787525227586e-08, + "loss": 0.0018, + "step": 63434 + }, + { + "epoch": 19.59, + "learning_rate": 2.1947658629004608e-08, + "loss": 0.0019, + "step": 63435 + }, + { + "epoch": 19.59, + "learning_rate": 2.1914554689710376e-08, + "loss": 0.0016, + "step": 63436 + }, + { + "epoch": 19.59, + "learning_rate": 2.1881475707428158e-08, + "loss": 0.0016, + "step": 63437 + }, + { + "epoch": 19.59, + "learning_rate": 2.1848421682240107e-08, + "loss": 0.0016, + "step": 63438 + }, + { + "epoch": 19.59, + "learning_rate": 2.181539261422949e-08, + "loss": 0.0016, + "step": 63439 + }, + { + "epoch": 19.59, + "learning_rate": 2.1782388503477357e-08, + "loss": 0.0015, + "step": 63440 + }, + { + "epoch": 19.59, + "learning_rate": 2.1749409350068086e-08, + "loss": 0.0017, + "step": 63441 + }, + { + "epoch": 19.59, + "learning_rate": 2.1716455154083826e-08, + "loss": 0.0019, + "step": 63442 + }, + { + "epoch": 19.59, + "learning_rate": 2.168352591560563e-08, + "loss": 0.0018, + "step": 63443 + }, + { + "epoch": 19.59, + "learning_rate": 2.1650621634717874e-08, + "loss": 0.0017, + "step": 63444 + }, + { + "epoch": 19.59, + "learning_rate": 2.16177423115016e-08, + "loss": 0.0013, + "step": 63445 + }, + { + "epoch": 19.59, + "learning_rate": 2.1584887946038967e-08, + "loss": 0.0014, + "step": 63446 + }, + { + "epoch": 19.59, + "learning_rate": 2.1552058538413246e-08, + "loss": 0.0017, + "step": 63447 + }, + { + "epoch": 19.59, + "learning_rate": 2.1519254088704368e-08, + "loss": 0.0013, + "step": 63448 + }, + { + "epoch": 19.59, + "learning_rate": 2.148647459699671e-08, + "loss": 0.0012, + "step": 63449 + }, + { + "epoch": 19.59, + "learning_rate": 2.145372006337132e-08, + "loss": 0.0018, + "step": 63450 + }, + { + "epoch": 19.59, + "learning_rate": 2.1420990487910354e-08, + "loss": 0.0021, + "step": 63451 + }, + { + "epoch": 19.6, + "learning_rate": 2.138828587069486e-08, + "loss": 0.0016, + "step": 63452 + }, + { + "epoch": 19.6, + "learning_rate": 2.13556062118081e-08, + "loss": 0.0016, + "step": 63453 + }, + { + "epoch": 19.6, + "learning_rate": 2.1322951511330013e-08, + "loss": 0.0012, + "step": 63454 + }, + { + "epoch": 19.6, + "learning_rate": 2.129032176934387e-08, + "loss": 0.0019, + "step": 63455 + }, + { + "epoch": 19.6, + "learning_rate": 2.125771698593071e-08, + "loss": 0.0015, + "step": 63456 + }, + { + "epoch": 19.6, + "learning_rate": 2.1225137161171583e-08, + "loss": 0.0014, + "step": 63457 + }, + { + "epoch": 19.6, + "learning_rate": 2.1192582295148646e-08, + "loss": 0.0011, + "step": 63458 + }, + { + "epoch": 19.6, + "learning_rate": 2.116005238794294e-08, + "loss": 0.0012, + "step": 63459 + }, + { + "epoch": 19.6, + "learning_rate": 2.112754743963552e-08, + "loss": 0.0021, + "step": 63460 + }, + { + "epoch": 19.6, + "learning_rate": 2.109506745030854e-08, + "loss": 0.0014, + "step": 63461 + }, + { + "epoch": 19.6, + "learning_rate": 2.106261242004304e-08, + "loss": 0.0013, + "step": 63462 + }, + { + "epoch": 19.6, + "learning_rate": 2.103018234892007e-08, + "loss": 0.0011, + "step": 63463 + }, + { + "epoch": 19.6, + "learning_rate": 2.099777723702068e-08, + "loss": 0.0012, + "step": 63464 + }, + { + "epoch": 19.6, + "learning_rate": 2.0965397084425908e-08, + "loss": 0.0016, + "step": 63465 + }, + { + "epoch": 19.6, + "learning_rate": 2.09330418912157e-08, + "loss": 0.0015, + "step": 63466 + }, + { + "epoch": 19.6, + "learning_rate": 2.0900711657473317e-08, + "loss": 0.0016, + "step": 63467 + }, + { + "epoch": 19.6, + "learning_rate": 2.0868406383277584e-08, + "loss": 0.0018, + "step": 63468 + }, + { + "epoch": 19.6, + "learning_rate": 2.083612606871066e-08, + "loss": 0.0013, + "step": 63469 + }, + { + "epoch": 19.6, + "learning_rate": 2.0803870713852482e-08, + "loss": 0.0014, + "step": 63470 + }, + { + "epoch": 19.6, + "learning_rate": 2.077164031878298e-08, + "loss": 0.0014, + "step": 63471 + }, + { + "epoch": 19.6, + "learning_rate": 2.073943488358432e-08, + "loss": 0.0013, + "step": 63472 + }, + { + "epoch": 19.6, + "learning_rate": 2.070725440833754e-08, + "loss": 0.0016, + "step": 63473 + }, + { + "epoch": 19.6, + "learning_rate": 2.067509889312036e-08, + "loss": 0.0013, + "step": 63474 + }, + { + "epoch": 19.6, + "learning_rate": 2.0642968338016046e-08, + "loss": 0.0011, + "step": 63475 + }, + { + "epoch": 19.6, + "learning_rate": 2.061086274310342e-08, + "loss": 0.0017, + "step": 63476 + }, + { + "epoch": 19.6, + "learning_rate": 2.0578782108462425e-08, + "loss": 0.0015, + "step": 63477 + }, + { + "epoch": 19.6, + "learning_rate": 2.0546726434175213e-08, + "loss": 0.0015, + "step": 63478 + }, + { + "epoch": 19.6, + "learning_rate": 2.051469572032061e-08, + "loss": 0.0014, + "step": 63479 + }, + { + "epoch": 19.6, + "learning_rate": 2.0482689966978552e-08, + "loss": 0.0015, + "step": 63480 + }, + { + "epoch": 19.6, + "learning_rate": 2.045070917422898e-08, + "loss": 0.0017, + "step": 63481 + }, + { + "epoch": 19.6, + "learning_rate": 2.041875334215293e-08, + "loss": 0.0015, + "step": 63482 + }, + { + "epoch": 19.6, + "learning_rate": 2.0386822470829238e-08, + "loss": 0.0012, + "step": 63483 + }, + { + "epoch": 19.6, + "learning_rate": 2.0354916560338945e-08, + "loss": 0.0012, + "step": 63484 + }, + { + "epoch": 19.61, + "learning_rate": 2.0323035610760876e-08, + "loss": 0.0012, + "step": 63485 + }, + { + "epoch": 19.61, + "learning_rate": 2.0291179622174972e-08, + "loss": 0.0018, + "step": 63486 + }, + { + "epoch": 19.61, + "learning_rate": 2.0259348594661166e-08, + "loss": 0.0009, + "step": 63487 + }, + { + "epoch": 19.61, + "learning_rate": 2.0227542528299393e-08, + "loss": 0.0017, + "step": 63488 + }, + { + "epoch": 19.61, + "learning_rate": 2.019576142316737e-08, + "loss": 0.0015, + "step": 63489 + }, + { + "epoch": 19.61, + "learning_rate": 2.0164005279347253e-08, + "loss": 0.0012, + "step": 63490 + }, + { + "epoch": 19.61, + "learning_rate": 2.0132274096916758e-08, + "loss": 0.0017, + "step": 63491 + }, + { + "epoch": 19.61, + "learning_rate": 2.0100567875954712e-08, + "loss": 0.0017, + "step": 63492 + }, + { + "epoch": 19.61, + "learning_rate": 2.006888661654216e-08, + "loss": 0.0011, + "step": 63493 + }, + { + "epoch": 19.61, + "learning_rate": 2.0037230318757927e-08, + "loss": 0.0017, + "step": 63494 + }, + { + "epoch": 19.61, + "learning_rate": 2.000559898268084e-08, + "loss": 0.0017, + "step": 63495 + }, + { + "epoch": 19.61, + "learning_rate": 1.9973992608389724e-08, + "loss": 0.0016, + "step": 63496 + }, + { + "epoch": 19.61, + "learning_rate": 1.9942411195963408e-08, + "loss": 0.0014, + "step": 63497 + }, + { + "epoch": 19.61, + "learning_rate": 1.991085474548182e-08, + "loss": 0.0016, + "step": 63498 + }, + { + "epoch": 19.61, + "learning_rate": 1.9879323257023796e-08, + "loss": 0.0015, + "step": 63499 + }, + { + "epoch": 19.61, + "learning_rate": 1.9847816730667046e-08, + "loss": 0.0017, + "step": 63500 + }, + { + "epoch": 19.61, + "learning_rate": 1.9816335166491507e-08, + "loss": 0.0013, + "step": 63501 + }, + { + "epoch": 19.61, + "learning_rate": 1.9784878564576006e-08, + "loss": 0.0014, + "step": 63502 + }, + { + "epoch": 19.61, + "learning_rate": 1.9753446924998255e-08, + "loss": 0.002, + "step": 63503 + }, + { + "epoch": 19.61, + "learning_rate": 1.9722040247838193e-08, + "loss": 0.0015, + "step": 63504 + }, + { + "epoch": 19.61, + "learning_rate": 1.9690658533172424e-08, + "loss": 0.0014, + "step": 63505 + }, + { + "epoch": 19.61, + "learning_rate": 1.9659301781081997e-08, + "loss": 0.0015, + "step": 63506 + }, + { + "epoch": 19.61, + "learning_rate": 1.9627969991642404e-08, + "loss": 0.0013, + "step": 63507 + }, + { + "epoch": 19.61, + "learning_rate": 1.9596663164934694e-08, + "loss": 0.0015, + "step": 63508 + }, + { + "epoch": 19.61, + "learning_rate": 1.956538130103547e-08, + "loss": 0.0015, + "step": 63509 + }, + { + "epoch": 19.61, + "learning_rate": 1.9534124400023556e-08, + "loss": 0.0014, + "step": 63510 + }, + { + "epoch": 19.61, + "learning_rate": 1.9502892461977786e-08, + "loss": 0.0011, + "step": 63511 + }, + { + "epoch": 19.61, + "learning_rate": 1.9471685486974755e-08, + "loss": 0.0015, + "step": 63512 + }, + { + "epoch": 19.61, + "learning_rate": 1.9440503475094406e-08, + "loss": 0.0014, + "step": 63513 + }, + { + "epoch": 19.61, + "learning_rate": 1.9409346426412234e-08, + "loss": 0.0016, + "step": 63514 + }, + { + "epoch": 19.61, + "learning_rate": 1.9378214341009282e-08, + "loss": 0.0012, + "step": 63515 + }, + { + "epoch": 19.61, + "learning_rate": 1.9347107218961046e-08, + "loss": 0.0012, + "step": 63516 + }, + { + "epoch": 19.62, + "learning_rate": 1.9316025060345245e-08, + "loss": 0.0019, + "step": 63517 + }, + { + "epoch": 19.62, + "learning_rate": 1.928496786524181e-08, + "loss": 0.0014, + "step": 63518 + }, + { + "epoch": 19.62, + "learning_rate": 1.925393563372624e-08, + "loss": 0.0017, + "step": 63519 + }, + { + "epoch": 19.62, + "learning_rate": 1.9222928365877357e-08, + "loss": 0.0015, + "step": 63520 + }, + { + "epoch": 19.62, + "learning_rate": 1.919194606177177e-08, + "loss": 0.0012, + "step": 63521 + }, + { + "epoch": 19.62, + "learning_rate": 1.9160988721487194e-08, + "loss": 0.0012, + "step": 63522 + }, + { + "epoch": 19.62, + "learning_rate": 1.9130056345102456e-08, + "loss": 0.0019, + "step": 63523 + }, + { + "epoch": 19.62, + "learning_rate": 1.9099148932693047e-08, + "loss": 0.0015, + "step": 63524 + }, + { + "epoch": 19.62, + "learning_rate": 1.9068266484337795e-08, + "loss": 0.0012, + "step": 63525 + }, + { + "epoch": 19.62, + "learning_rate": 1.9037409000112194e-08, + "loss": 0.002, + "step": 63526 + }, + { + "epoch": 19.62, + "learning_rate": 1.9006576480095075e-08, + "loss": 0.0011, + "step": 63527 + }, + { + "epoch": 19.62, + "learning_rate": 1.8975768924363035e-08, + "loss": 0.0019, + "step": 63528 + }, + { + "epoch": 19.62, + "learning_rate": 1.8944986332992687e-08, + "loss": 0.0014, + "step": 63529 + }, + { + "epoch": 19.62, + "learning_rate": 1.8914228706061743e-08, + "loss": 0.0017, + "step": 63530 + }, + { + "epoch": 19.62, + "learning_rate": 1.888349604364681e-08, + "loss": 0.0017, + "step": 63531 + }, + { + "epoch": 19.62, + "learning_rate": 1.885278834582449e-08, + "loss": 0.0016, + "step": 63532 + }, + { + "epoch": 19.62, + "learning_rate": 1.8822105612671393e-08, + "loss": 0.0014, + "step": 63533 + }, + { + "epoch": 19.62, + "learning_rate": 1.879144784426523e-08, + "loss": 0.0015, + "step": 63534 + }, + { + "epoch": 19.62, + "learning_rate": 1.8760815040681503e-08, + "loss": 0.0016, + "step": 63535 + }, + { + "epoch": 19.62, + "learning_rate": 1.873020720199792e-08, + "loss": 0.0013, + "step": 63536 + }, + { + "epoch": 19.62, + "learning_rate": 1.869962432829109e-08, + "loss": 0.0013, + "step": 63537 + }, + { + "epoch": 19.62, + "learning_rate": 1.8669066419636505e-08, + "loss": 0.0021, + "step": 63538 + }, + { + "epoch": 19.62, + "learning_rate": 1.8638533476110777e-08, + "loss": 0.0018, + "step": 63539 + }, + { + "epoch": 19.62, + "learning_rate": 1.8608025497790505e-08, + "loss": 0.0013, + "step": 63540 + }, + { + "epoch": 19.62, + "learning_rate": 1.85775424847523e-08, + "loss": 0.0024, + "step": 63541 + }, + { + "epoch": 19.62, + "learning_rate": 1.854708443707165e-08, + "loss": 0.0014, + "step": 63542 + }, + { + "epoch": 19.62, + "learning_rate": 1.8516651354826275e-08, + "loss": 0.0014, + "step": 63543 + }, + { + "epoch": 19.62, + "learning_rate": 1.848624323809056e-08, + "loss": 0.0012, + "step": 63544 + }, + { + "epoch": 19.62, + "learning_rate": 1.8455860086941114e-08, + "loss": 0.0017, + "step": 63545 + }, + { + "epoch": 19.62, + "learning_rate": 1.8425501901454535e-08, + "loss": 0.0016, + "step": 63546 + }, + { + "epoch": 19.62, + "learning_rate": 1.839516868170632e-08, + "loss": 0.0011, + "step": 63547 + }, + { + "epoch": 19.62, + "learning_rate": 1.8364860427771968e-08, + "loss": 0.0016, + "step": 63548 + }, + { + "epoch": 19.63, + "learning_rate": 1.8334577139728083e-08, + "loss": 0.0015, + "step": 63549 + }, + { + "epoch": 19.63, + "learning_rate": 1.8304318817650157e-08, + "loss": 0.0019, + "step": 63550 + }, + { + "epoch": 19.63, + "learning_rate": 1.8274085461612577e-08, + "loss": 0.0016, + "step": 63551 + }, + { + "epoch": 19.63, + "learning_rate": 1.8243877071693062e-08, + "loss": 0.0013, + "step": 63552 + }, + { + "epoch": 19.63, + "learning_rate": 1.8213693647965992e-08, + "loss": 0.0017, + "step": 63553 + }, + { + "epoch": 19.63, + "learning_rate": 1.8183535190505753e-08, + "loss": 0.0015, + "step": 63554 + }, + { + "epoch": 19.63, + "learning_rate": 1.815340169939117e-08, + "loss": 0.002, + "step": 63555 + }, + { + "epoch": 19.63, + "learning_rate": 1.812329317469441e-08, + "loss": 0.0013, + "step": 63556 + }, + { + "epoch": 19.63, + "learning_rate": 1.809320961649208e-08, + "loss": 0.0011, + "step": 63557 + }, + { + "epoch": 19.63, + "learning_rate": 1.806315102485856e-08, + "loss": 0.0016, + "step": 63558 + }, + { + "epoch": 19.63, + "learning_rate": 1.8033117399870458e-08, + "loss": 0.0016, + "step": 63559 + }, + { + "epoch": 19.63, + "learning_rate": 1.800310874160216e-08, + "loss": 0.0015, + "step": 63560 + }, + { + "epoch": 19.63, + "learning_rate": 1.797312505012805e-08, + "loss": 0.0016, + "step": 63561 + }, + { + "epoch": 19.63, + "learning_rate": 1.794316632552473e-08, + "loss": 0.0019, + "step": 63562 + }, + { + "epoch": 19.63, + "learning_rate": 1.791323256786548e-08, + "loss": 0.0012, + "step": 63563 + }, + { + "epoch": 19.63, + "learning_rate": 1.788332377722579e-08, + "loss": 0.0012, + "step": 63564 + }, + { + "epoch": 19.63, + "learning_rate": 1.7853439953680052e-08, + "loss": 0.0014, + "step": 63565 + }, + { + "epoch": 19.63, + "learning_rate": 1.7823581097304865e-08, + "loss": 0.0017, + "step": 63566 + }, + { + "epoch": 19.63, + "learning_rate": 1.7793747208172395e-08, + "loss": 0.0013, + "step": 63567 + }, + { + "epoch": 19.63, + "learning_rate": 1.776393828635925e-08, + "loss": 0.002, + "step": 63568 + }, + { + "epoch": 19.63, + "learning_rate": 1.7734154331938704e-08, + "loss": 0.0011, + "step": 63569 + }, + { + "epoch": 19.63, + "learning_rate": 1.770439534498514e-08, + "loss": 0.0015, + "step": 63570 + }, + { + "epoch": 19.63, + "learning_rate": 1.767466132557405e-08, + "loss": 0.0014, + "step": 63571 + }, + { + "epoch": 19.63, + "learning_rate": 1.7644952273779824e-08, + "loss": 0.0015, + "step": 63572 + }, + { + "epoch": 19.63, + "learning_rate": 1.761526818967574e-08, + "loss": 0.0013, + "step": 63573 + }, + { + "epoch": 19.63, + "learning_rate": 1.7585609073336173e-08, + "loss": 0.0017, + "step": 63574 + }, + { + "epoch": 19.63, + "learning_rate": 1.7555974924836626e-08, + "loss": 0.0014, + "step": 63575 + }, + { + "epoch": 19.63, + "learning_rate": 1.7526365744249263e-08, + "loss": 0.0013, + "step": 63576 + }, + { + "epoch": 19.63, + "learning_rate": 1.7496781531649577e-08, + "loss": 0.0016, + "step": 63577 + }, + { + "epoch": 19.63, + "learning_rate": 1.7467222287110842e-08, + "loss": 0.0018, + "step": 63578 + }, + { + "epoch": 19.63, + "learning_rate": 1.7437688010707443e-08, + "loss": 0.0014, + "step": 63579 + }, + { + "epoch": 19.63, + "learning_rate": 1.7408178702513767e-08, + "loss": 0.0013, + "step": 63580 + }, + { + "epoch": 19.63, + "learning_rate": 1.7378694362601978e-08, + "loss": 0.0011, + "step": 63581 + }, + { + "epoch": 19.64, + "learning_rate": 1.734923499104757e-08, + "loss": 0.0015, + "step": 63582 + }, + { + "epoch": 19.64, + "learning_rate": 1.7319800587922708e-08, + "loss": 0.002, + "step": 63583 + }, + { + "epoch": 19.64, + "learning_rate": 1.729039115330289e-08, + "loss": 0.0014, + "step": 63584 + }, + { + "epoch": 19.64, + "learning_rate": 1.7261006687259164e-08, + "loss": 0.0015, + "step": 63585 + }, + { + "epoch": 19.64, + "learning_rate": 1.7231647189868138e-08, + "loss": 0.0017, + "step": 63586 + }, + { + "epoch": 19.64, + "learning_rate": 1.720231266119976e-08, + "loss": 0.0014, + "step": 63587 + }, + { + "epoch": 19.64, + "learning_rate": 1.717300310132952e-08, + "loss": 0.0017, + "step": 63588 + }, + { + "epoch": 19.64, + "learning_rate": 1.7143718510330698e-08, + "loss": 0.002, + "step": 63589 + }, + { + "epoch": 19.64, + "learning_rate": 1.7114458888276564e-08, + "loss": 0.0012, + "step": 63590 + }, + { + "epoch": 19.64, + "learning_rate": 1.7085224235239283e-08, + "loss": 0.0017, + "step": 63591 + }, + { + "epoch": 19.64, + "learning_rate": 1.7056014551293242e-08, + "loss": 0.0013, + "step": 63592 + }, + { + "epoch": 19.64, + "learning_rate": 1.7026829836509495e-08, + "loss": 0.0014, + "step": 63593 + }, + { + "epoch": 19.64, + "learning_rate": 1.6997670090963535e-08, + "loss": 0.0019, + "step": 63594 + }, + { + "epoch": 19.64, + "learning_rate": 1.696853531472753e-08, + "loss": 0.0017, + "step": 63595 + }, + { + "epoch": 19.64, + "learning_rate": 1.693942550787364e-08, + "loss": 0.0011, + "step": 63596 + }, + { + "epoch": 19.64, + "learning_rate": 1.6910340670475146e-08, + "loss": 0.0014, + "step": 63597 + }, + { + "epoch": 19.64, + "learning_rate": 1.6881280802604204e-08, + "loss": 0.002, + "step": 63598 + }, + { + "epoch": 19.64, + "learning_rate": 1.6852245904334097e-08, + "loss": 0.0017, + "step": 63599 + }, + { + "epoch": 19.64, + "learning_rate": 1.6823235975736983e-08, + "loss": 0.0011, + "step": 63600 + }, + { + "epoch": 19.64, + "learning_rate": 1.679425101688725e-08, + "loss": 0.0015, + "step": 63601 + }, + { + "epoch": 19.64, + "learning_rate": 1.6765291027854846e-08, + "loss": 0.0012, + "step": 63602 + }, + { + "epoch": 19.64, + "learning_rate": 1.673635600871304e-08, + "loss": 0.0013, + "step": 63603 + }, + { + "epoch": 19.64, + "learning_rate": 1.6707445959535107e-08, + "loss": 0.0012, + "step": 63604 + }, + { + "epoch": 19.64, + "learning_rate": 1.6678560880392104e-08, + "loss": 0.0013, + "step": 63605 + }, + { + "epoch": 19.64, + "learning_rate": 1.6649700771357304e-08, + "loss": 0.0019, + "step": 63606 + }, + { + "epoch": 19.64, + "learning_rate": 1.662086563250176e-08, + "loss": 0.0013, + "step": 63607 + }, + { + "epoch": 19.64, + "learning_rate": 1.659205546389986e-08, + "loss": 0.0016, + "step": 63608 + }, + { + "epoch": 19.64, + "learning_rate": 1.6563270265620434e-08, + "loss": 0.0015, + "step": 63609 + }, + { + "epoch": 19.64, + "learning_rate": 1.6534510037737874e-08, + "loss": 0.0014, + "step": 63610 + }, + { + "epoch": 19.64, + "learning_rate": 1.6505774780323226e-08, + "loss": 0.0012, + "step": 63611 + }, + { + "epoch": 19.64, + "learning_rate": 1.647706449344866e-08, + "loss": 0.0019, + "step": 63612 + }, + { + "epoch": 19.64, + "learning_rate": 1.6448379177185225e-08, + "loss": 0.0016, + "step": 63613 + }, + { + "epoch": 19.65, + "learning_rate": 1.64197188316062e-08, + "loss": 0.0015, + "step": 63614 + }, + { + "epoch": 19.65, + "learning_rate": 1.639108345678153e-08, + "loss": 0.0014, + "step": 63615 + }, + { + "epoch": 19.65, + "learning_rate": 1.636247305278449e-08, + "loss": 0.0017, + "step": 63616 + }, + { + "epoch": 19.65, + "learning_rate": 1.633388761968502e-08, + "loss": 0.0012, + "step": 63617 + }, + { + "epoch": 19.65, + "learning_rate": 1.6305327157556394e-08, + "loss": 0.0019, + "step": 63618 + }, + { + "epoch": 19.65, + "learning_rate": 1.627679166646745e-08, + "loss": 0.0013, + "step": 63619 + }, + { + "epoch": 19.65, + "learning_rate": 1.6248281146492573e-08, + "loss": 0.0014, + "step": 63620 + }, + { + "epoch": 19.65, + "learning_rate": 1.6219795597700593e-08, + "loss": 0.0016, + "step": 63621 + }, + { + "epoch": 19.65, + "learning_rate": 1.6191335020164787e-08, + "loss": 0.0015, + "step": 63622 + }, + { + "epoch": 19.65, + "learning_rate": 1.61628994139551e-08, + "loss": 0.0015, + "step": 63623 + }, + { + "epoch": 19.65, + "learning_rate": 1.6134488779143697e-08, + "loss": 0.0012, + "step": 63624 + }, + { + "epoch": 19.65, + "learning_rate": 1.610610311579941e-08, + "loss": 0.0014, + "step": 63625 + }, + { + "epoch": 19.65, + "learning_rate": 1.607774242399551e-08, + "loss": 0.0012, + "step": 63626 + }, + { + "epoch": 19.65, + "learning_rate": 1.604940670380195e-08, + "loss": 0.0014, + "step": 63627 + }, + { + "epoch": 19.65, + "learning_rate": 1.602109595528978e-08, + "loss": 0.0011, + "step": 63628 + }, + { + "epoch": 19.65, + "learning_rate": 1.599281017853005e-08, + "loss": 0.002, + "step": 63629 + }, + { + "epoch": 19.65, + "learning_rate": 1.596454937359271e-08, + "loss": 0.0012, + "step": 63630 + }, + { + "epoch": 19.65, + "learning_rate": 1.593631354054992e-08, + "loss": 0.0016, + "step": 63631 + }, + { + "epoch": 19.65, + "learning_rate": 1.5908102679470516e-08, + "loss": 0.0015, + "step": 63632 + }, + { + "epoch": 19.65, + "learning_rate": 1.5879916790426665e-08, + "loss": 0.0013, + "step": 63633 + }, + { + "epoch": 19.65, + "learning_rate": 1.5851755873487196e-08, + "loss": 0.0019, + "step": 63634 + }, + { + "epoch": 19.65, + "learning_rate": 1.5823619928724276e-08, + "loss": 0.0023, + "step": 63635 + }, + { + "epoch": 19.65, + "learning_rate": 1.579550895620674e-08, + "loss": 0.0012, + "step": 63636 + }, + { + "epoch": 19.65, + "learning_rate": 1.576742295600675e-08, + "loss": 0.0017, + "step": 63637 + }, + { + "epoch": 19.65, + "learning_rate": 1.5739361928193142e-08, + "loss": 0.0016, + "step": 63638 + }, + { + "epoch": 19.65, + "learning_rate": 1.571132587283586e-08, + "loss": 0.0013, + "step": 63639 + }, + { + "epoch": 19.65, + "learning_rate": 1.5683314790005954e-08, + "loss": 0.0013, + "step": 63640 + }, + { + "epoch": 19.65, + "learning_rate": 1.5655328679772265e-08, + "loss": 0.0017, + "step": 63641 + }, + { + "epoch": 19.65, + "learning_rate": 1.562736754220695e-08, + "loss": 0.0014, + "step": 63642 + }, + { + "epoch": 19.65, + "learning_rate": 1.559943137737774e-08, + "loss": 0.002, + "step": 63643 + }, + { + "epoch": 19.65, + "learning_rate": 1.5571520185355682e-08, + "loss": 0.0019, + "step": 63644 + }, + { + "epoch": 19.65, + "learning_rate": 1.5543633966210723e-08, + "loss": 0.0014, + "step": 63645 + }, + { + "epoch": 19.65, + "learning_rate": 1.551577272001059e-08, + "loss": 0.0015, + "step": 63646 + }, + { + "epoch": 19.66, + "learning_rate": 1.5487936446828556e-08, + "loss": 0.0015, + "step": 63647 + }, + { + "epoch": 19.66, + "learning_rate": 1.546012514673123e-08, + "loss": 0.0014, + "step": 63648 + }, + { + "epoch": 19.66, + "learning_rate": 1.5432338819789672e-08, + "loss": 0.0013, + "step": 63649 + }, + { + "epoch": 19.66, + "learning_rate": 1.5404577466071603e-08, + "loss": 0.0014, + "step": 63650 + }, + { + "epoch": 19.66, + "learning_rate": 1.5376841085649187e-08, + "loss": 0.0012, + "step": 63651 + }, + { + "epoch": 19.66, + "learning_rate": 1.5349129678590148e-08, + "loss": 0.0014, + "step": 63652 + }, + { + "epoch": 19.66, + "learning_rate": 1.532144324496332e-08, + "loss": 0.0009, + "step": 63653 + }, + { + "epoch": 19.66, + "learning_rate": 1.5293781784839756e-08, + "loss": 0.0014, + "step": 63654 + }, + { + "epoch": 19.66, + "learning_rate": 1.526614529828718e-08, + "loss": 0.0023, + "step": 63655 + }, + { + "epoch": 19.66, + "learning_rate": 1.5238533785374433e-08, + "loss": 0.0013, + "step": 63656 + }, + { + "epoch": 19.66, + "learning_rate": 1.5210947246171448e-08, + "loss": 0.0013, + "step": 63657 + }, + { + "epoch": 19.66, + "learning_rate": 1.5183385680747063e-08, + "loss": 0.0013, + "step": 63658 + }, + { + "epoch": 19.66, + "learning_rate": 1.5155849089170115e-08, + "loss": 0.0016, + "step": 63659 + }, + { + "epoch": 19.66, + "learning_rate": 1.5128337471510545e-08, + "loss": 0.0016, + "step": 63660 + }, + { + "epoch": 19.66, + "learning_rate": 1.5100850827834968e-08, + "loss": 0.0019, + "step": 63661 + }, + { + "epoch": 19.66, + "learning_rate": 1.5073389158213324e-08, + "loss": 0.0017, + "step": 63662 + }, + { + "epoch": 19.66, + "learning_rate": 1.504595246271445e-08, + "loss": 0.0013, + "step": 63663 + }, + { + "epoch": 19.66, + "learning_rate": 1.5018540741407184e-08, + "loss": 0.0016, + "step": 63664 + }, + { + "epoch": 19.66, + "learning_rate": 1.499115399435924e-08, + "loss": 0.0012, + "step": 63665 + }, + { + "epoch": 19.66, + "learning_rate": 1.4963792221639463e-08, + "loss": 0.0012, + "step": 63666 + }, + { + "epoch": 19.66, + "learning_rate": 1.4936455423316675e-08, + "loss": 0.0013, + "step": 63667 + }, + { + "epoch": 19.66, + "learning_rate": 1.4909143599458608e-08, + "loss": 0.0015, + "step": 63668 + }, + { + "epoch": 19.66, + "learning_rate": 1.4881856750134095e-08, + "loss": 0.0014, + "step": 63669 + }, + { + "epoch": 19.66, + "learning_rate": 1.4854594875411965e-08, + "loss": 0.0014, + "step": 63670 + }, + { + "epoch": 19.66, + "learning_rate": 1.4827357975358836e-08, + "loss": 0.0012, + "step": 63671 + }, + { + "epoch": 19.66, + "learning_rate": 1.480014605004354e-08, + "loss": 0.0014, + "step": 63672 + }, + { + "epoch": 19.66, + "learning_rate": 1.4772959099534912e-08, + "loss": 0.0015, + "step": 63673 + }, + { + "epoch": 19.66, + "learning_rate": 1.4745797123900674e-08, + "loss": 0.0013, + "step": 63674 + }, + { + "epoch": 19.66, + "learning_rate": 1.471866012320744e-08, + "loss": 0.0022, + "step": 63675 + }, + { + "epoch": 19.66, + "learning_rate": 1.4691548097524045e-08, + "loss": 0.0016, + "step": 63676 + }, + { + "epoch": 19.66, + "learning_rate": 1.466446104691932e-08, + "loss": 0.0016, + "step": 63677 + }, + { + "epoch": 19.66, + "learning_rate": 1.4637398971458772e-08, + "loss": 0.0021, + "step": 63678 + }, + { + "epoch": 19.67, + "learning_rate": 1.4610361871212342e-08, + "loss": 0.0012, + "step": 63679 + }, + { + "epoch": 19.67, + "learning_rate": 1.4583349746245534e-08, + "loss": 0.0017, + "step": 63680 + }, + { + "epoch": 19.67, + "learning_rate": 1.4556362596627182e-08, + "loss": 0.0014, + "step": 63681 + }, + { + "epoch": 19.67, + "learning_rate": 1.4529400422426121e-08, + "loss": 0.0015, + "step": 63682 + }, + { + "epoch": 19.67, + "learning_rate": 1.4502463223706742e-08, + "loss": 0.0014, + "step": 63683 + }, + { + "epoch": 19.67, + "learning_rate": 1.447555100053788e-08, + "loss": 0.0012, + "step": 63684 + }, + { + "epoch": 19.67, + "learning_rate": 1.4448663752987257e-08, + "loss": 0.0016, + "step": 63685 + }, + { + "epoch": 19.67, + "learning_rate": 1.44218014811226e-08, + "loss": 0.0013, + "step": 63686 + }, + { + "epoch": 19.67, + "learning_rate": 1.4394964185009407e-08, + "loss": 0.002, + "step": 63687 + }, + { + "epoch": 19.67, + "learning_rate": 1.4368151864715407e-08, + "loss": 0.0014, + "step": 63688 + }, + { + "epoch": 19.67, + "learning_rate": 1.4341364520308321e-08, + "loss": 0.0015, + "step": 63689 + }, + { + "epoch": 19.67, + "learning_rate": 1.4314602151854761e-08, + "loss": 0.001, + "step": 63690 + }, + { + "epoch": 19.67, + "learning_rate": 1.4287864759422453e-08, + "loss": 0.0018, + "step": 63691 + }, + { + "epoch": 19.67, + "learning_rate": 1.4261152343075791e-08, + "loss": 0.0015, + "step": 63692 + }, + { + "epoch": 19.67, + "learning_rate": 1.4234464902884714e-08, + "loss": 0.0014, + "step": 63693 + }, + { + "epoch": 19.67, + "learning_rate": 1.420780243891362e-08, + "loss": 0.0012, + "step": 63694 + }, + { + "epoch": 19.67, + "learning_rate": 1.4181164951230231e-08, + "loss": 0.0022, + "step": 63695 + }, + { + "epoch": 19.67, + "learning_rate": 1.4154552439901159e-08, + "loss": 0.0016, + "step": 63696 + }, + { + "epoch": 19.67, + "learning_rate": 1.4127964904993019e-08, + "loss": 0.0015, + "step": 63697 + }, + { + "epoch": 19.67, + "learning_rate": 1.4101402346572423e-08, + "loss": 0.0018, + "step": 63698 + }, + { + "epoch": 19.67, + "learning_rate": 1.4074864764704877e-08, + "loss": 0.0015, + "step": 63699 + }, + { + "epoch": 19.67, + "learning_rate": 1.40483521594581e-08, + "loss": 0.0015, + "step": 63700 + }, + { + "epoch": 19.67, + "learning_rate": 1.40218645308976e-08, + "loss": 0.002, + "step": 63701 + }, + { + "epoch": 19.67, + "learning_rate": 1.3995401879088877e-08, + "loss": 0.0014, + "step": 63702 + }, + { + "epoch": 19.67, + "learning_rate": 1.3968964204099655e-08, + "loss": 0.002, + "step": 63703 + }, + { + "epoch": 19.67, + "learning_rate": 1.3942551505995439e-08, + "loss": 0.0016, + "step": 63704 + }, + { + "epoch": 19.67, + "learning_rate": 1.391616378484284e-08, + "loss": 0.0016, + "step": 63705 + }, + { + "epoch": 19.67, + "learning_rate": 1.3889801040706253e-08, + "loss": 0.0011, + "step": 63706 + }, + { + "epoch": 19.67, + "learning_rate": 1.38634632736534e-08, + "loss": 0.0014, + "step": 63707 + }, + { + "epoch": 19.67, + "learning_rate": 1.3837150483748674e-08, + "loss": 0.0015, + "step": 63708 + }, + { + "epoch": 19.67, + "learning_rate": 1.3810862671058689e-08, + "loss": 0.0012, + "step": 63709 + }, + { + "epoch": 19.67, + "learning_rate": 1.3784599835648949e-08, + "loss": 0.0017, + "step": 63710 + }, + { + "epoch": 19.68, + "learning_rate": 1.3758361977586065e-08, + "loss": 0.0011, + "step": 63711 + }, + { + "epoch": 19.68, + "learning_rate": 1.3732149096934434e-08, + "loss": 0.0016, + "step": 63712 + }, + { + "epoch": 19.68, + "learning_rate": 1.3705961193759554e-08, + "loss": 0.0015, + "step": 63713 + }, + { + "epoch": 19.68, + "learning_rate": 1.3679798268129152e-08, + "loss": 0.0015, + "step": 63714 + }, + { + "epoch": 19.68, + "learning_rate": 1.36536603201054e-08, + "loss": 0.0018, + "step": 63715 + }, + { + "epoch": 19.68, + "learning_rate": 1.362754734975602e-08, + "loss": 0.0015, + "step": 63716 + }, + { + "epoch": 19.68, + "learning_rate": 1.3601459357144298e-08, + "loss": 0.0013, + "step": 63717 + }, + { + "epoch": 19.68, + "learning_rate": 1.3575396342337954e-08, + "loss": 0.0013, + "step": 63718 + }, + { + "epoch": 19.68, + "learning_rate": 1.3549358305400273e-08, + "loss": 0.0015, + "step": 63719 + }, + { + "epoch": 19.68, + "learning_rate": 1.3523345246397868e-08, + "loss": 0.0012, + "step": 63720 + }, + { + "epoch": 19.68, + "learning_rate": 1.349735716539402e-08, + "loss": 0.0015, + "step": 63721 + }, + { + "epoch": 19.68, + "learning_rate": 1.3471394062455346e-08, + "loss": 0.0014, + "step": 63722 + }, + { + "epoch": 19.68, + "learning_rate": 1.3445455937646234e-08, + "loss": 0.0017, + "step": 63723 + }, + { + "epoch": 19.68, + "learning_rate": 1.3419542791031081e-08, + "loss": 0.0012, + "step": 63724 + }, + { + "epoch": 19.68, + "learning_rate": 1.339365462267539e-08, + "loss": 0.0018, + "step": 63725 + }, + { + "epoch": 19.68, + "learning_rate": 1.336779143264355e-08, + "loss": 0.0012, + "step": 63726 + }, + { + "epoch": 19.68, + "learning_rate": 1.334195322099996e-08, + "loss": 0.0016, + "step": 63727 + }, + { + "epoch": 19.68, + "learning_rate": 1.3316139987810117e-08, + "loss": 0.0012, + "step": 63728 + }, + { + "epoch": 19.68, + "learning_rate": 1.3290351733138419e-08, + "loss": 0.0019, + "step": 63729 + }, + { + "epoch": 19.68, + "learning_rate": 1.3264588457048145e-08, + "loss": 0.0015, + "step": 63730 + }, + { + "epoch": 19.68, + "learning_rate": 1.3238850159604799e-08, + "loss": 0.0011, + "step": 63731 + }, + { + "epoch": 19.68, + "learning_rate": 1.3213136840872775e-08, + "loss": 0.0022, + "step": 63732 + }, + { + "epoch": 19.68, + "learning_rate": 1.3187448500915356e-08, + "loss": 0.0017, + "step": 63733 + }, + { + "epoch": 19.68, + "learning_rate": 1.3161785139799155e-08, + "loss": 0.001, + "step": 63734 + }, + { + "epoch": 19.68, + "learning_rate": 1.3136146757585234e-08, + "loss": 0.0025, + "step": 63735 + }, + { + "epoch": 19.68, + "learning_rate": 1.3110533354340205e-08, + "loss": 0.0015, + "step": 63736 + }, + { + "epoch": 19.68, + "learning_rate": 1.3084944930127352e-08, + "loss": 0.0017, + "step": 63737 + }, + { + "epoch": 19.68, + "learning_rate": 1.305938148500996e-08, + "loss": 0.0017, + "step": 63738 + }, + { + "epoch": 19.68, + "learning_rate": 1.3033843019052417e-08, + "loss": 0.0013, + "step": 63739 + }, + { + "epoch": 19.68, + "learning_rate": 1.300832953232023e-08, + "loss": 0.0018, + "step": 63740 + }, + { + "epoch": 19.68, + "learning_rate": 1.298284102487446e-08, + "loss": 0.0012, + "step": 63741 + }, + { + "epoch": 19.68, + "learning_rate": 1.2957377496779499e-08, + "loss": 0.0021, + "step": 63742 + }, + { + "epoch": 19.68, + "learning_rate": 1.2931938948100852e-08, + "loss": 0.0014, + "step": 63743 + }, + { + "epoch": 19.69, + "learning_rate": 1.2906525378900692e-08, + "loss": 0.0018, + "step": 63744 + }, + { + "epoch": 19.69, + "learning_rate": 1.288113678924341e-08, + "loss": 0.0013, + "step": 63745 + }, + { + "epoch": 19.69, + "learning_rate": 1.2855773179191178e-08, + "loss": 0.0014, + "step": 63746 + }, + { + "epoch": 19.69, + "learning_rate": 1.283043454880839e-08, + "loss": 0.0013, + "step": 63747 + }, + { + "epoch": 19.69, + "learning_rate": 1.280512089815722e-08, + "loss": 0.001, + "step": 63748 + }, + { + "epoch": 19.69, + "learning_rate": 1.2779832227303168e-08, + "loss": 0.0016, + "step": 63749 + }, + { + "epoch": 19.69, + "learning_rate": 1.2754568536308409e-08, + "loss": 0.0015, + "step": 63750 + }, + { + "epoch": 19.69, + "learning_rate": 1.2729329825235115e-08, + "loss": 0.0013, + "step": 63751 + }, + { + "epoch": 19.69, + "learning_rate": 1.2704116094147679e-08, + "loss": 0.002, + "step": 63752 + }, + { + "epoch": 19.69, + "learning_rate": 1.2678927343109382e-08, + "loss": 0.0015, + "step": 63753 + }, + { + "epoch": 19.69, + "learning_rate": 1.2653763572182399e-08, + "loss": 0.0015, + "step": 63754 + }, + { + "epoch": 19.69, + "learning_rate": 1.262862478143001e-08, + "loss": 0.0017, + "step": 63755 + }, + { + "epoch": 19.69, + "learning_rate": 1.260351097091439e-08, + "loss": 0.0015, + "step": 63756 + }, + { + "epoch": 19.69, + "learning_rate": 1.257842214069993e-08, + "loss": 0.0013, + "step": 63757 + }, + { + "epoch": 19.69, + "learning_rate": 1.2553358290847695e-08, + "loss": 0.0014, + "step": 63758 + }, + { + "epoch": 19.69, + "learning_rate": 1.2528319421420964e-08, + "loss": 0.0016, + "step": 63759 + }, + { + "epoch": 19.69, + "learning_rate": 1.2503305532483023e-08, + "loss": 0.0015, + "step": 63760 + }, + { + "epoch": 19.69, + "learning_rate": 1.2478316624096044e-08, + "loss": 0.0014, + "step": 63761 + }, + { + "epoch": 19.69, + "learning_rate": 1.2453352696322197e-08, + "loss": 0.0012, + "step": 63762 + }, + { + "epoch": 19.69, + "learning_rate": 1.2428413749223655e-08, + "loss": 0.0012, + "step": 63763 + }, + { + "epoch": 19.69, + "learning_rate": 1.2403499782863704e-08, + "loss": 0.0018, + "step": 63764 + }, + { + "epoch": 19.69, + "learning_rate": 1.2378610797304514e-08, + "loss": 0.0014, + "step": 63765 + }, + { + "epoch": 19.69, + "learning_rate": 1.2353746792608256e-08, + "loss": 0.0013, + "step": 63766 + }, + { + "epoch": 19.69, + "learning_rate": 1.2328907768835996e-08, + "loss": 0.0019, + "step": 63767 + }, + { + "epoch": 19.69, + "learning_rate": 1.2304093726051013e-08, + "loss": 0.0013, + "step": 63768 + }, + { + "epoch": 19.69, + "learning_rate": 1.2279304664315483e-08, + "loss": 0.0017, + "step": 63769 + }, + { + "epoch": 19.69, + "learning_rate": 1.2254540583690467e-08, + "loss": 0.0012, + "step": 63770 + }, + { + "epoch": 19.69, + "learning_rate": 1.2229801484239245e-08, + "loss": 0.0013, + "step": 63771 + }, + { + "epoch": 19.69, + "learning_rate": 1.2205087366022884e-08, + "loss": 0.0018, + "step": 63772 + }, + { + "epoch": 19.69, + "learning_rate": 1.218039822910244e-08, + "loss": 0.0011, + "step": 63773 + }, + { + "epoch": 19.69, + "learning_rate": 1.2155734073541203e-08, + "loss": 0.0015, + "step": 63774 + }, + { + "epoch": 19.69, + "learning_rate": 1.2131094899400231e-08, + "loss": 0.001, + "step": 63775 + }, + { + "epoch": 19.7, + "learning_rate": 1.2106480706740586e-08, + "loss": 0.0015, + "step": 63776 + }, + { + "epoch": 19.7, + "learning_rate": 1.2081891495624443e-08, + "loss": 0.002, + "step": 63777 + }, + { + "epoch": 19.7, + "learning_rate": 1.2057327266113972e-08, + "loss": 0.0016, + "step": 63778 + }, + { + "epoch": 19.7, + "learning_rate": 1.2032788018269125e-08, + "loss": 0.0012, + "step": 63779 + }, + { + "epoch": 19.7, + "learning_rate": 1.2008273752150967e-08, + "loss": 0.0015, + "step": 63780 + }, + { + "epoch": 19.7, + "learning_rate": 1.1983784467822779e-08, + "loss": 0.0016, + "step": 63781 + }, + { + "epoch": 19.7, + "learning_rate": 1.1959320165345623e-08, + "loss": 0.0011, + "step": 63782 + }, + { + "epoch": 19.7, + "learning_rate": 1.1934880844778341e-08, + "loss": 0.0015, + "step": 63783 + }, + { + "epoch": 19.7, + "learning_rate": 1.1910466506185326e-08, + "loss": 0.0011, + "step": 63784 + }, + { + "epoch": 19.7, + "learning_rate": 1.1886077149624308e-08, + "loss": 0.0014, + "step": 63785 + }, + { + "epoch": 19.7, + "learning_rate": 1.1861712775159684e-08, + "loss": 0.0019, + "step": 63786 + }, + { + "epoch": 19.7, + "learning_rate": 1.1837373382849183e-08, + "loss": 0.0016, + "step": 63787 + }, + { + "epoch": 19.7, + "learning_rate": 1.1813058972754975e-08, + "loss": 0.0018, + "step": 63788 + }, + { + "epoch": 19.7, + "learning_rate": 1.1788769544939239e-08, + "loss": 0.002, + "step": 63789 + }, + { + "epoch": 19.7, + "learning_rate": 1.176450509946081e-08, + "loss": 0.0014, + "step": 63790 + }, + { + "epoch": 19.7, + "learning_rate": 1.1740265636380755e-08, + "loss": 0.0013, + "step": 63791 + }, + { + "epoch": 19.7, + "learning_rate": 1.1716051155761243e-08, + "loss": 0.0016, + "step": 63792 + }, + { + "epoch": 19.7, + "learning_rate": 1.1691861657661118e-08, + "loss": 0.0017, + "step": 63793 + }, + { + "epoch": 19.7, + "learning_rate": 1.1667697142140333e-08, + "loss": 0.0013, + "step": 63794 + }, + { + "epoch": 19.7, + "learning_rate": 1.1643557609261057e-08, + "loss": 0.0015, + "step": 63795 + }, + { + "epoch": 19.7, + "learning_rate": 1.1619443059083247e-08, + "loss": 0.0016, + "step": 63796 + }, + { + "epoch": 19.7, + "learning_rate": 1.159535349166796e-08, + "loss": 0.0016, + "step": 63797 + }, + { + "epoch": 19.7, + "learning_rate": 1.1571288907072931e-08, + "loss": 0.0015, + "step": 63798 + }, + { + "epoch": 19.7, + "learning_rate": 1.1547249305360331e-08, + "loss": 0.0014, + "step": 63799 + }, + { + "epoch": 19.7, + "learning_rate": 1.1523234686590112e-08, + "loss": 0.0018, + "step": 63800 + }, + { + "epoch": 19.7, + "learning_rate": 1.1499245050821118e-08, + "loss": 0.0016, + "step": 63801 + }, + { + "epoch": 19.7, + "learning_rate": 1.1475280398115517e-08, + "loss": 0.0015, + "step": 63802 + }, + { + "epoch": 19.7, + "learning_rate": 1.1451340728532156e-08, + "loss": 0.0012, + "step": 63803 + }, + { + "epoch": 19.7, + "learning_rate": 1.1427426042129874e-08, + "loss": 0.0014, + "step": 63804 + }, + { + "epoch": 19.7, + "learning_rate": 1.1403536338969734e-08, + "loss": 0.0016, + "step": 63805 + }, + { + "epoch": 19.7, + "learning_rate": 1.1379671619110577e-08, + "loss": 0.0024, + "step": 63806 + }, + { + "epoch": 19.7, + "learning_rate": 1.1355831882613466e-08, + "loss": 0.0015, + "step": 63807 + }, + { + "epoch": 19.71, + "learning_rate": 1.1332017129537242e-08, + "loss": 0.0011, + "step": 63808 + }, + { + "epoch": 19.71, + "learning_rate": 1.1308227359940749e-08, + "loss": 0.0016, + "step": 63809 + }, + { + "epoch": 19.71, + "learning_rate": 1.1284462573885047e-08, + "loss": 0.0015, + "step": 63810 + }, + { + "epoch": 19.71, + "learning_rate": 1.1260722771427868e-08, + "loss": 0.0016, + "step": 63811 + }, + { + "epoch": 19.71, + "learning_rate": 1.1237007952630274e-08, + "loss": 0.0016, + "step": 63812 + }, + { + "epoch": 19.71, + "learning_rate": 1.1213318117549998e-08, + "loss": 0.0021, + "step": 63813 + }, + { + "epoch": 19.71, + "learning_rate": 1.1189653266248101e-08, + "loss": 0.0013, + "step": 63814 + }, + { + "epoch": 19.71, + "learning_rate": 1.1166013398782316e-08, + "loss": 0.0014, + "step": 63815 + }, + { + "epoch": 19.71, + "learning_rate": 1.1142398515211484e-08, + "loss": 0.0013, + "step": 63816 + }, + { + "epoch": 19.71, + "learning_rate": 1.1118808615595556e-08, + "loss": 0.0014, + "step": 63817 + }, + { + "epoch": 19.71, + "learning_rate": 1.1095243699994485e-08, + "loss": 0.0013, + "step": 63818 + }, + { + "epoch": 19.71, + "learning_rate": 1.1071703768464892e-08, + "loss": 0.0013, + "step": 63819 + }, + { + "epoch": 19.71, + "learning_rate": 1.104818882106673e-08, + "loss": 0.0019, + "step": 63820 + }, + { + "epoch": 19.71, + "learning_rate": 1.102469885785995e-08, + "loss": 0.0014, + "step": 63821 + }, + { + "epoch": 19.71, + "learning_rate": 1.1001233878901174e-08, + "loss": 0.0018, + "step": 63822 + }, + { + "epoch": 19.71, + "learning_rate": 1.0977793884251463e-08, + "loss": 0.0014, + "step": 63823 + }, + { + "epoch": 19.71, + "learning_rate": 1.0954378873967442e-08, + "loss": 0.0023, + "step": 63824 + }, + { + "epoch": 19.71, + "learning_rate": 1.0930988848107948e-08, + "loss": 0.0012, + "step": 63825 + }, + { + "epoch": 19.71, + "learning_rate": 1.0907623806731826e-08, + "loss": 0.0019, + "step": 63826 + }, + { + "epoch": 19.71, + "learning_rate": 1.0884283749899028e-08, + "loss": 0.0015, + "step": 63827 + }, + { + "epoch": 19.71, + "learning_rate": 1.0860968677665062e-08, + "loss": 0.0019, + "step": 63828 + }, + { + "epoch": 19.71, + "learning_rate": 1.0837678590090994e-08, + "loss": 0.0016, + "step": 63829 + }, + { + "epoch": 19.71, + "learning_rate": 1.0814413487232334e-08, + "loss": 0.0011, + "step": 63830 + }, + { + "epoch": 19.71, + "learning_rate": 1.0791173369150143e-08, + "loss": 0.001, + "step": 63831 + }, + { + "epoch": 19.71, + "learning_rate": 1.0767958235901044e-08, + "loss": 0.0012, + "step": 63832 + }, + { + "epoch": 19.71, + "learning_rate": 1.0744768087541658e-08, + "loss": 0.0016, + "step": 63833 + }, + { + "epoch": 19.71, + "learning_rate": 1.0721602924133045e-08, + "loss": 0.0014, + "step": 63834 + }, + { + "epoch": 19.71, + "learning_rate": 1.069846274573072e-08, + "loss": 0.0013, + "step": 63835 + }, + { + "epoch": 19.71, + "learning_rate": 1.0675347552394632e-08, + "loss": 0.0018, + "step": 63836 + }, + { + "epoch": 19.71, + "learning_rate": 1.0652257344180295e-08, + "loss": 0.0013, + "step": 63837 + }, + { + "epoch": 19.71, + "learning_rate": 1.0629192121147659e-08, + "loss": 0.0021, + "step": 63838 + }, + { + "epoch": 19.71, + "learning_rate": 1.0606151883352234e-08, + "loss": 0.0017, + "step": 63839 + }, + { + "epoch": 19.71, + "learning_rate": 1.0583136630853974e-08, + "loss": 0.0016, + "step": 63840 + }, + { + "epoch": 19.72, + "learning_rate": 1.056014636370839e-08, + "loss": 0.0017, + "step": 63841 + }, + { + "epoch": 19.72, + "learning_rate": 1.0537181081974323e-08, + "loss": 0.001, + "step": 63842 + }, + { + "epoch": 19.72, + "learning_rate": 1.0514240785708397e-08, + "loss": 0.0021, + "step": 63843 + }, + { + "epoch": 19.72, + "learning_rate": 1.0491325474968339e-08, + "loss": 0.0013, + "step": 63844 + }, + { + "epoch": 19.72, + "learning_rate": 1.0468435149810775e-08, + "loss": 0.0013, + "step": 63845 + }, + { + "epoch": 19.72, + "learning_rate": 1.0445569810294542e-08, + "loss": 0.001, + "step": 63846 + }, + { + "epoch": 19.72, + "learning_rate": 1.0422729456475156e-08, + "loss": 0.0016, + "step": 63847 + }, + { + "epoch": 19.72, + "learning_rate": 1.0399914088411456e-08, + "loss": 0.0014, + "step": 63848 + }, + { + "epoch": 19.72, + "learning_rate": 1.0377123706160064e-08, + "loss": 0.0015, + "step": 63849 + }, + { + "epoch": 19.72, + "learning_rate": 1.035435830977538e-08, + "loss": 0.0017, + "step": 63850 + }, + { + "epoch": 19.72, + "learning_rate": 1.033161789931847e-08, + "loss": 0.0015, + "step": 63851 + }, + { + "epoch": 19.72, + "learning_rate": 1.0308902474842619e-08, + "loss": 0.0014, + "step": 63852 + }, + { + "epoch": 19.72, + "learning_rate": 1.0286212036407784e-08, + "loss": 0.0023, + "step": 63853 + }, + { + "epoch": 19.72, + "learning_rate": 1.0263546584068362e-08, + "loss": 0.0016, + "step": 63854 + }, + { + "epoch": 19.72, + "learning_rate": 1.0240906117880978e-08, + "loss": 0.0013, + "step": 63855 + }, + { + "epoch": 19.72, + "learning_rate": 1.021829063790447e-08, + "loss": 0.0015, + "step": 63856 + }, + { + "epoch": 19.72, + "learning_rate": 1.0195700144193244e-08, + "loss": 0.0011, + "step": 63857 + }, + { + "epoch": 19.72, + "learning_rate": 1.0173134636805027e-08, + "loss": 0.0014, + "step": 63858 + }, + { + "epoch": 19.72, + "learning_rate": 1.0150594115795332e-08, + "loss": 0.0012, + "step": 63859 + }, + { + "epoch": 19.72, + "learning_rate": 1.012807858122189e-08, + "loss": 0.0019, + "step": 63860 + }, + { + "epoch": 19.72, + "learning_rate": 1.0105588033139103e-08, + "loss": 0.0018, + "step": 63861 + }, + { + "epoch": 19.72, + "learning_rate": 1.00831224716047e-08, + "loss": 0.0017, + "step": 63862 + }, + { + "epoch": 19.72, + "learning_rate": 1.0060681896674196e-08, + "loss": 0.0015, + "step": 63863 + }, + { + "epoch": 19.72, + "learning_rate": 1.003826630840421e-08, + "loss": 0.0014, + "step": 63864 + }, + { + "epoch": 19.72, + "learning_rate": 1.0015875706851364e-08, + "loss": 0.0015, + "step": 63865 + }, + { + "epoch": 19.72, + "learning_rate": 9.993510092070057e-09, + "loss": 0.0016, + "step": 63866 + }, + { + "epoch": 19.72, + "learning_rate": 9.971169464116915e-09, + "loss": 0.0015, + "step": 63867 + }, + { + "epoch": 19.72, + "learning_rate": 9.948853823048554e-09, + "loss": 0.0012, + "step": 63868 + }, + { + "epoch": 19.72, + "learning_rate": 9.926563168919378e-09, + "loss": 0.0014, + "step": 63869 + }, + { + "epoch": 19.72, + "learning_rate": 9.90429750178712e-09, + "loss": 0.0013, + "step": 63870 + }, + { + "epoch": 19.72, + "learning_rate": 9.882056821705066e-09, + "loss": 0.0016, + "step": 63871 + }, + { + "epoch": 19.72, + "learning_rate": 9.859841128730952e-09, + "loss": 0.0014, + "step": 63872 + }, + { + "epoch": 19.73, + "learning_rate": 9.837650422919176e-09, + "loss": 0.0013, + "step": 63873 + }, + { + "epoch": 19.73, + "learning_rate": 9.815484704325251e-09, + "loss": 0.0014, + "step": 63874 + }, + { + "epoch": 19.73, + "learning_rate": 9.793343973004687e-09, + "loss": 0.0016, + "step": 63875 + }, + { + "epoch": 19.73, + "learning_rate": 9.771228229014106e-09, + "loss": 0.0015, + "step": 63876 + }, + { + "epoch": 19.73, + "learning_rate": 9.7491374724068e-09, + "loss": 0.001, + "step": 63877 + }, + { + "epoch": 19.73, + "learning_rate": 9.727071703239388e-09, + "loss": 0.0016, + "step": 63878 + }, + { + "epoch": 19.73, + "learning_rate": 9.705030921566273e-09, + "loss": 0.0012, + "step": 63879 + }, + { + "epoch": 19.73, + "learning_rate": 9.683015127444074e-09, + "loss": 0.0018, + "step": 63880 + }, + { + "epoch": 19.73, + "learning_rate": 9.661024320926082e-09, + "loss": 0.0016, + "step": 63881 + }, + { + "epoch": 19.73, + "learning_rate": 9.639058502067811e-09, + "loss": 0.0014, + "step": 63882 + }, + { + "epoch": 19.73, + "learning_rate": 9.617117670924769e-09, + "loss": 0.0016, + "step": 63883 + }, + { + "epoch": 19.73, + "learning_rate": 9.595201827551359e-09, + "loss": 0.0013, + "step": 63884 + }, + { + "epoch": 19.73, + "learning_rate": 9.573310972001982e-09, + "loss": 0.0014, + "step": 63885 + }, + { + "epoch": 19.73, + "learning_rate": 9.551445104332147e-09, + "loss": 0.0014, + "step": 63886 + }, + { + "epoch": 19.73, + "learning_rate": 9.529604224596256e-09, + "loss": 0.0012, + "step": 63887 + }, + { + "epoch": 19.73, + "learning_rate": 9.50778833284982e-09, + "loss": 0.0012, + "step": 63888 + }, + { + "epoch": 19.73, + "learning_rate": 9.485997429145021e-09, + "loss": 0.0012, + "step": 63889 + }, + { + "epoch": 19.73, + "learning_rate": 9.46423151353959e-09, + "loss": 0.0009, + "step": 63890 + }, + { + "epoch": 19.73, + "learning_rate": 9.442490586084596e-09, + "loss": 0.0012, + "step": 63891 + }, + { + "epoch": 19.73, + "learning_rate": 9.420774646837772e-09, + "loss": 0.0014, + "step": 63892 + }, + { + "epoch": 19.73, + "learning_rate": 9.399083695850186e-09, + "loss": 0.0014, + "step": 63893 + }, + { + "epoch": 19.73, + "learning_rate": 9.377417733178462e-09, + "loss": 0.0022, + "step": 63894 + }, + { + "epoch": 19.73, + "learning_rate": 9.35577675887589e-09, + "loss": 0.0015, + "step": 63895 + }, + { + "epoch": 19.73, + "learning_rate": 9.33416077299687e-09, + "loss": 0.0012, + "step": 63896 + }, + { + "epoch": 19.73, + "learning_rate": 9.312569775595803e-09, + "loss": 0.002, + "step": 63897 + }, + { + "epoch": 19.73, + "learning_rate": 9.291003766724871e-09, + "loss": 0.0016, + "step": 63898 + }, + { + "epoch": 19.73, + "learning_rate": 9.269462746440694e-09, + "loss": 0.0019, + "step": 63899 + }, + { + "epoch": 19.73, + "learning_rate": 9.247946714794343e-09, + "loss": 0.0014, + "step": 63900 + }, + { + "epoch": 19.73, + "learning_rate": 9.226455671842438e-09, + "loss": 0.0017, + "step": 63901 + }, + { + "epoch": 19.73, + "learning_rate": 9.204989617637162e-09, + "loss": 0.0014, + "step": 63902 + }, + { + "epoch": 19.73, + "learning_rate": 9.183548552231802e-09, + "loss": 0.0015, + "step": 63903 + }, + { + "epoch": 19.73, + "learning_rate": 9.162132475680763e-09, + "loss": 0.0016, + "step": 63904 + }, + { + "epoch": 19.73, + "learning_rate": 9.140741388037333e-09, + "loss": 0.0022, + "step": 63905 + }, + { + "epoch": 19.74, + "learning_rate": 9.119375289354804e-09, + "loss": 0.0016, + "step": 63906 + }, + { + "epoch": 19.74, + "learning_rate": 9.098034179687577e-09, + "loss": 0.0012, + "step": 63907 + }, + { + "epoch": 19.74, + "learning_rate": 9.076718059088941e-09, + "loss": 0.0015, + "step": 63908 + }, + { + "epoch": 19.74, + "learning_rate": 9.055426927609966e-09, + "loss": 0.0009, + "step": 63909 + }, + { + "epoch": 19.74, + "learning_rate": 9.034160785307277e-09, + "loss": 0.0018, + "step": 63910 + }, + { + "epoch": 19.74, + "learning_rate": 9.012919632231943e-09, + "loss": 0.0015, + "step": 63911 + }, + { + "epoch": 19.74, + "learning_rate": 8.991703468437251e-09, + "loss": 0.0012, + "step": 63912 + }, + { + "epoch": 19.74, + "learning_rate": 8.970512293976497e-09, + "loss": 0.0011, + "step": 63913 + }, + { + "epoch": 19.74, + "learning_rate": 8.949346108902967e-09, + "loss": 0.0012, + "step": 63914 + }, + { + "epoch": 19.74, + "learning_rate": 8.928204913268845e-09, + "loss": 0.0019, + "step": 63915 + }, + { + "epoch": 19.74, + "learning_rate": 8.90708870712853e-09, + "loss": 0.0015, + "step": 63916 + }, + { + "epoch": 19.74, + "learning_rate": 8.885997490533093e-09, + "loss": 0.0015, + "step": 63917 + }, + { + "epoch": 19.74, + "learning_rate": 8.864931263535825e-09, + "loss": 0.0014, + "step": 63918 + }, + { + "epoch": 19.74, + "learning_rate": 8.843890026190017e-09, + "loss": 0.0016, + "step": 63919 + }, + { + "epoch": 19.74, + "learning_rate": 8.822873778548957e-09, + "loss": 0.0014, + "step": 63920 + }, + { + "epoch": 19.74, + "learning_rate": 8.801882520662608e-09, + "loss": 0.0015, + "step": 63921 + }, + { + "epoch": 19.74, + "learning_rate": 8.78091625258537e-09, + "loss": 0.0016, + "step": 63922 + }, + { + "epoch": 19.74, + "learning_rate": 8.759974974369422e-09, + "loss": 0.0011, + "step": 63923 + }, + { + "epoch": 19.74, + "learning_rate": 8.739058686066948e-09, + "loss": 0.0015, + "step": 63924 + }, + { + "epoch": 19.74, + "learning_rate": 8.718167387731235e-09, + "loss": 0.0016, + "step": 63925 + }, + { + "epoch": 19.74, + "learning_rate": 8.697301079413356e-09, + "loss": 0.0023, + "step": 63926 + }, + { + "epoch": 19.74, + "learning_rate": 8.67645976116549e-09, + "loss": 0.0021, + "step": 63927 + }, + { + "epoch": 19.74, + "learning_rate": 8.655643433039817e-09, + "loss": 0.0013, + "step": 63928 + }, + { + "epoch": 19.74, + "learning_rate": 8.63485209508852e-09, + "loss": 0.0016, + "step": 63929 + }, + { + "epoch": 19.74, + "learning_rate": 8.614085747364886e-09, + "loss": 0.0013, + "step": 63930 + }, + { + "epoch": 19.74, + "learning_rate": 8.593344389918879e-09, + "loss": 0.0016, + "step": 63931 + }, + { + "epoch": 19.74, + "learning_rate": 8.572628022803787e-09, + "loss": 0.0011, + "step": 63932 + }, + { + "epoch": 19.74, + "learning_rate": 8.55193664607068e-09, + "loss": 0.0015, + "step": 63933 + }, + { + "epoch": 19.74, + "learning_rate": 8.53127025977063e-09, + "loss": 0.0018, + "step": 63934 + }, + { + "epoch": 19.74, + "learning_rate": 8.510628863958037e-09, + "loss": 0.0017, + "step": 63935 + }, + { + "epoch": 19.74, + "learning_rate": 8.490012458681752e-09, + "loss": 0.0015, + "step": 63936 + }, + { + "epoch": 19.74, + "learning_rate": 8.469421043993953e-09, + "loss": 0.0016, + "step": 63937 + }, + { + "epoch": 19.75, + "learning_rate": 8.448854619946822e-09, + "loss": 0.0015, + "step": 63938 + }, + { + "epoch": 19.75, + "learning_rate": 8.42831318659032e-09, + "loss": 0.0018, + "step": 63939 + }, + { + "epoch": 19.75, + "learning_rate": 8.407796743978847e-09, + "loss": 0.0016, + "step": 63940 + }, + { + "epoch": 19.75, + "learning_rate": 8.387305292160142e-09, + "loss": 0.0016, + "step": 63941 + }, + { + "epoch": 19.75, + "learning_rate": 8.366838831188606e-09, + "loss": 0.0011, + "step": 63942 + }, + { + "epoch": 19.75, + "learning_rate": 8.34639736111309e-09, + "loss": 0.0018, + "step": 63943 + }, + { + "epoch": 19.75, + "learning_rate": 8.325980881985773e-09, + "loss": 0.0017, + "step": 63944 + }, + { + "epoch": 19.75, + "learning_rate": 8.305589393857727e-09, + "loss": 0.0018, + "step": 63945 + }, + { + "epoch": 19.75, + "learning_rate": 8.28522289678002e-09, + "loss": 0.0016, + "step": 63946 + }, + { + "epoch": 19.75, + "learning_rate": 8.264881390802615e-09, + "loss": 0.002, + "step": 63947 + }, + { + "epoch": 19.75, + "learning_rate": 8.24456487597769e-09, + "loss": 0.0015, + "step": 63948 + }, + { + "epoch": 19.75, + "learning_rate": 8.224273352355205e-09, + "loss": 0.0011, + "step": 63949 + }, + { + "epoch": 19.75, + "learning_rate": 8.204006819986233e-09, + "loss": 0.0012, + "step": 63950 + }, + { + "epoch": 19.75, + "learning_rate": 8.18376527892073e-09, + "loss": 0.0017, + "step": 63951 + }, + { + "epoch": 19.75, + "learning_rate": 8.163548729210879e-09, + "loss": 0.0016, + "step": 63952 + }, + { + "epoch": 19.75, + "learning_rate": 8.14335717090664e-09, + "loss": 0.0018, + "step": 63953 + }, + { + "epoch": 19.75, + "learning_rate": 8.123190604057973e-09, + "loss": 0.0013, + "step": 63954 + }, + { + "epoch": 19.75, + "learning_rate": 8.103049028714838e-09, + "loss": 0.0013, + "step": 63955 + }, + { + "epoch": 19.75, + "learning_rate": 8.082932444929414e-09, + "loss": 0.0016, + "step": 63956 + }, + { + "epoch": 19.75, + "learning_rate": 8.062840852750553e-09, + "loss": 0.0015, + "step": 63957 + }, + { + "epoch": 19.75, + "learning_rate": 8.042774252229324e-09, + "loss": 0.0016, + "step": 63958 + }, + { + "epoch": 19.75, + "learning_rate": 8.022732643414577e-09, + "loss": 0.0014, + "step": 63959 + }, + { + "epoch": 19.75, + "learning_rate": 8.002716026358492e-09, + "loss": 0.0012, + "step": 63960 + }, + { + "epoch": 19.75, + "learning_rate": 7.98272440110992e-09, + "loss": 0.0019, + "step": 63961 + }, + { + "epoch": 19.75, + "learning_rate": 7.96275776771882e-09, + "loss": 0.0017, + "step": 63962 + }, + { + "epoch": 19.75, + "learning_rate": 7.942816126235153e-09, + "loss": 0.0014, + "step": 63963 + }, + { + "epoch": 19.75, + "learning_rate": 7.922899476708879e-09, + "loss": 0.0016, + "step": 63964 + }, + { + "epoch": 19.75, + "learning_rate": 7.903007819189955e-09, + "loss": 0.0013, + "step": 63965 + }, + { + "epoch": 19.75, + "learning_rate": 7.883141153727236e-09, + "loss": 0.0019, + "step": 63966 + }, + { + "epoch": 19.75, + "learning_rate": 7.863299480372898e-09, + "loss": 0.0017, + "step": 63967 + }, + { + "epoch": 19.75, + "learning_rate": 7.843482799173573e-09, + "loss": 0.0015, + "step": 63968 + }, + { + "epoch": 19.75, + "learning_rate": 7.823691110180332e-09, + "loss": 0.0016, + "step": 63969 + }, + { + "epoch": 19.76, + "learning_rate": 7.803924413443132e-09, + "loss": 0.0012, + "step": 63970 + }, + { + "epoch": 19.76, + "learning_rate": 7.784182709010823e-09, + "loss": 0.0012, + "step": 63971 + }, + { + "epoch": 19.76, + "learning_rate": 7.764465996932257e-09, + "loss": 0.0014, + "step": 63972 + }, + { + "epoch": 19.76, + "learning_rate": 7.744774277257394e-09, + "loss": 0.0017, + "step": 63973 + }, + { + "epoch": 19.76, + "learning_rate": 7.725107550035082e-09, + "loss": 0.0019, + "step": 63974 + }, + { + "epoch": 19.76, + "learning_rate": 7.705465815314172e-09, + "loss": 0.0016, + "step": 63975 + }, + { + "epoch": 19.76, + "learning_rate": 7.685849073145735e-09, + "loss": 0.0016, + "step": 63976 + }, + { + "epoch": 19.76, + "learning_rate": 7.666257323576398e-09, + "loss": 0.0019, + "step": 63977 + }, + { + "epoch": 19.76, + "learning_rate": 7.646690566657232e-09, + "loss": 0.0016, + "step": 63978 + }, + { + "epoch": 19.76, + "learning_rate": 7.62714880243598e-09, + "loss": 0.0015, + "step": 63979 + }, + { + "epoch": 19.76, + "learning_rate": 7.607632030960377e-09, + "loss": 0.0013, + "step": 63980 + }, + { + "epoch": 19.76, + "learning_rate": 7.588140252282606e-09, + "loss": 0.0015, + "step": 63981 + }, + { + "epoch": 19.76, + "learning_rate": 7.568673466448185e-09, + "loss": 0.0017, + "step": 63982 + }, + { + "epoch": 19.76, + "learning_rate": 7.549231673507074e-09, + "loss": 0.0014, + "step": 63983 + }, + { + "epoch": 19.76, + "learning_rate": 7.529814873508124e-09, + "loss": 0.0014, + "step": 63984 + }, + { + "epoch": 19.76, + "learning_rate": 7.510423066499073e-09, + "loss": 0.0019, + "step": 63985 + }, + { + "epoch": 19.76, + "learning_rate": 7.491056252529882e-09, + "loss": 0.0017, + "step": 63986 + }, + { + "epoch": 19.76, + "learning_rate": 7.471714431647181e-09, + "loss": 0.0019, + "step": 63987 + }, + { + "epoch": 19.76, + "learning_rate": 7.45239760390093e-09, + "loss": 0.0012, + "step": 63988 + }, + { + "epoch": 19.76, + "learning_rate": 7.4331057693377565e-09, + "loss": 0.0013, + "step": 63989 + }, + { + "epoch": 19.76, + "learning_rate": 7.413838928007622e-09, + "loss": 0.0011, + "step": 63990 + }, + { + "epoch": 19.76, + "learning_rate": 7.394597079958266e-09, + "loss": 0.001, + "step": 63991 + }, + { + "epoch": 19.76, + "learning_rate": 7.375380225237427e-09, + "loss": 0.0015, + "step": 63992 + }, + { + "epoch": 19.76, + "learning_rate": 7.356188363892847e-09, + "loss": 0.0015, + "step": 63993 + }, + { + "epoch": 19.76, + "learning_rate": 7.337021495973373e-09, + "loss": 0.0013, + "step": 63994 + }, + { + "epoch": 19.76, + "learning_rate": 7.317879621526747e-09, + "loss": 0.0016, + "step": 63995 + }, + { + "epoch": 19.76, + "learning_rate": 7.298762740600706e-09, + "loss": 0.0014, + "step": 63996 + }, + { + "epoch": 19.76, + "learning_rate": 7.279670853242993e-09, + "loss": 0.0018, + "step": 63997 + }, + { + "epoch": 19.76, + "learning_rate": 7.260603959501345e-09, + "loss": 0.0017, + "step": 63998 + }, + { + "epoch": 19.76, + "learning_rate": 7.241562059422391e-09, + "loss": 0.0017, + "step": 63999 + }, + { + "epoch": 19.76, + "learning_rate": 7.222545153056093e-09, + "loss": 0.0013, + "step": 64000 + }, + { + "epoch": 19.76, + "learning_rate": 7.203553240447969e-09, + "loss": 0.0009, + "step": 64001 + }, + { + "epoch": 19.76, + "learning_rate": 7.184586321646869e-09, + "loss": 0.0013, + "step": 64002 + }, + { + "epoch": 19.77, + "learning_rate": 7.165644396699423e-09, + "loss": 0.0015, + "step": 64003 + }, + { + "epoch": 19.77, + "learning_rate": 7.146727465654479e-09, + "loss": 0.0018, + "step": 64004 + }, + { + "epoch": 19.77, + "learning_rate": 7.1278355285564485e-09, + "loss": 0.0016, + "step": 64005 + }, + { + "epoch": 19.77, + "learning_rate": 7.10896858545529e-09, + "loss": 0.0011, + "step": 64006 + }, + { + "epoch": 19.77, + "learning_rate": 7.090126636396522e-09, + "loss": 0.0017, + "step": 64007 + }, + { + "epoch": 19.77, + "learning_rate": 7.071309681428995e-09, + "loss": 0.0015, + "step": 64008 + }, + { + "epoch": 19.77, + "learning_rate": 7.052517720597119e-09, + "loss": 0.0009, + "step": 64009 + }, + { + "epoch": 19.77, + "learning_rate": 7.033750753950852e-09, + "loss": 0.0017, + "step": 64010 + }, + { + "epoch": 19.77, + "learning_rate": 7.015008781535715e-09, + "loss": 0.0012, + "step": 64011 + }, + { + "epoch": 19.77, + "learning_rate": 6.9962918033983365e-09, + "loss": 0.0014, + "step": 64012 + }, + { + "epoch": 19.77, + "learning_rate": 6.977599819585346e-09, + "loss": 0.0015, + "step": 64013 + }, + { + "epoch": 19.77, + "learning_rate": 6.958932830144483e-09, + "loss": 0.0013, + "step": 64014 + }, + { + "epoch": 19.77, + "learning_rate": 6.940290835121266e-09, + "loss": 0.001, + "step": 64015 + }, + { + "epoch": 19.77, + "learning_rate": 6.921673834564546e-09, + "loss": 0.0018, + "step": 64016 + }, + { + "epoch": 19.77, + "learning_rate": 6.903081828517622e-09, + "loss": 0.0012, + "step": 64017 + }, + { + "epoch": 19.77, + "learning_rate": 6.884514817029342e-09, + "loss": 0.0017, + "step": 64018 + }, + { + "epoch": 19.77, + "learning_rate": 6.865972800146336e-09, + "loss": 0.0015, + "step": 64019 + }, + { + "epoch": 19.77, + "learning_rate": 6.847455777913014e-09, + "loss": 0.0017, + "step": 64020 + }, + { + "epoch": 19.77, + "learning_rate": 6.828963750377115e-09, + "loss": 0.0011, + "step": 64021 + }, + { + "epoch": 19.77, + "learning_rate": 6.810496717585269e-09, + "loss": 0.0019, + "step": 64022 + }, + { + "epoch": 19.77, + "learning_rate": 6.7920546795829935e-09, + "loss": 0.0015, + "step": 64023 + }, + { + "epoch": 19.77, + "learning_rate": 6.773637636415809e-09, + "loss": 0.0012, + "step": 64024 + }, + { + "epoch": 19.77, + "learning_rate": 6.755245588130343e-09, + "loss": 0.0016, + "step": 64025 + }, + { + "epoch": 19.77, + "learning_rate": 6.736878534773228e-09, + "loss": 0.001, + "step": 64026 + }, + { + "epoch": 19.77, + "learning_rate": 6.7185364763888705e-09, + "loss": 0.0012, + "step": 64027 + }, + { + "epoch": 19.77, + "learning_rate": 6.700219413025011e-09, + "loss": 0.001, + "step": 64028 + }, + { + "epoch": 19.77, + "learning_rate": 6.6819273447271685e-09, + "loss": 0.0015, + "step": 64029 + }, + { + "epoch": 19.77, + "learning_rate": 6.663660271538641e-09, + "loss": 0.0014, + "step": 64030 + }, + { + "epoch": 19.77, + "learning_rate": 6.645418193508279e-09, + "loss": 0.0016, + "step": 64031 + }, + { + "epoch": 19.77, + "learning_rate": 6.627201110680492e-09, + "loss": 0.002, + "step": 64032 + }, + { + "epoch": 19.77, + "learning_rate": 6.609009023100799e-09, + "loss": 0.0017, + "step": 64033 + }, + { + "epoch": 19.77, + "learning_rate": 6.590841930813607e-09, + "loss": 0.0014, + "step": 64034 + }, + { + "epoch": 19.78, + "learning_rate": 6.572699833866658e-09, + "loss": 0.0013, + "step": 64035 + }, + { + "epoch": 19.78, + "learning_rate": 6.55458273230325e-09, + "loss": 0.0019, + "step": 64036 + }, + { + "epoch": 19.78, + "learning_rate": 6.536490626168901e-09, + "loss": 0.0012, + "step": 64037 + }, + { + "epoch": 19.78, + "learning_rate": 6.5184235155113514e-09, + "loss": 0.0011, + "step": 64038 + }, + { + "epoch": 19.78, + "learning_rate": 6.500381400372791e-09, + "loss": 0.0013, + "step": 64039 + }, + { + "epoch": 19.78, + "learning_rate": 6.482364280798737e-09, + "loss": 0.0014, + "step": 64040 + }, + { + "epoch": 19.78, + "learning_rate": 6.4643721568358185e-09, + "loss": 0.0012, + "step": 64041 + }, + { + "epoch": 19.78, + "learning_rate": 6.446405028528446e-09, + "loss": 0.0023, + "step": 64042 + }, + { + "epoch": 19.78, + "learning_rate": 6.4284628959210285e-09, + "loss": 0.0021, + "step": 64043 + }, + { + "epoch": 19.78, + "learning_rate": 6.410545759059084e-09, + "loss": 0.0017, + "step": 64044 + }, + { + "epoch": 19.78, + "learning_rate": 6.392653617987021e-09, + "loss": 0.0014, + "step": 64045 + }, + { + "epoch": 19.78, + "learning_rate": 6.37478647274925e-09, + "loss": 0.0015, + "step": 64046 + }, + { + "epoch": 19.78, + "learning_rate": 6.3569443233912895e-09, + "loss": 0.0009, + "step": 64047 + }, + { + "epoch": 19.78, + "learning_rate": 6.339127169956438e-09, + "loss": 0.0019, + "step": 64048 + }, + { + "epoch": 19.78, + "learning_rate": 6.321335012491326e-09, + "loss": 0.0013, + "step": 64049 + }, + { + "epoch": 19.78, + "learning_rate": 6.303567851039249e-09, + "loss": 0.0015, + "step": 64050 + }, + { + "epoch": 19.78, + "learning_rate": 6.285825685643509e-09, + "loss": 0.0011, + "step": 64051 + }, + { + "epoch": 19.78, + "learning_rate": 6.2681085163507345e-09, + "loss": 0.0015, + "step": 64052 + }, + { + "epoch": 19.78, + "learning_rate": 6.250416343203114e-09, + "loss": 0.0017, + "step": 64053 + }, + { + "epoch": 19.78, + "learning_rate": 6.232749166247276e-09, + "loss": 0.0021, + "step": 64054 + }, + { + "epoch": 19.78, + "learning_rate": 6.2151069855254096e-09, + "loss": 0.0012, + "step": 64055 + }, + { + "epoch": 19.78, + "learning_rate": 6.197489801081924e-09, + "loss": 0.0011, + "step": 64056 + }, + { + "epoch": 19.78, + "learning_rate": 6.179897612962338e-09, + "loss": 0.0011, + "step": 64057 + }, + { + "epoch": 19.78, + "learning_rate": 6.16233042120884e-09, + "loss": 0.0016, + "step": 64058 + }, + { + "epoch": 19.78, + "learning_rate": 6.1447882258658386e-09, + "loss": 0.0018, + "step": 64059 + }, + { + "epoch": 19.78, + "learning_rate": 6.127271026977743e-09, + "loss": 0.0015, + "step": 64060 + }, + { + "epoch": 19.78, + "learning_rate": 6.109778824588963e-09, + "loss": 0.0018, + "step": 64061 + }, + { + "epoch": 19.78, + "learning_rate": 6.092311618740576e-09, + "loss": 0.0015, + "step": 64062 + }, + { + "epoch": 19.78, + "learning_rate": 6.0748694094792114e-09, + "loss": 0.0016, + "step": 64063 + }, + { + "epoch": 19.78, + "learning_rate": 6.057452196848168e-09, + "loss": 0.0015, + "step": 64064 + }, + { + "epoch": 19.78, + "learning_rate": 6.040059980888524e-09, + "loss": 0.0021, + "step": 64065 + }, + { + "epoch": 19.78, + "learning_rate": 6.022692761646909e-09, + "loss": 0.0013, + "step": 64066 + }, + { + "epoch": 19.79, + "learning_rate": 6.0053505391644004e-09, + "loss": 0.0013, + "step": 64067 + }, + { + "epoch": 19.79, + "learning_rate": 5.988033313485408e-09, + "loss": 0.0016, + "step": 64068 + }, + { + "epoch": 19.79, + "learning_rate": 5.970741084654341e-09, + "loss": 0.0015, + "step": 64069 + }, + { + "epoch": 19.79, + "learning_rate": 5.953473852712277e-09, + "loss": 0.0014, + "step": 64070 + }, + { + "epoch": 19.79, + "learning_rate": 5.936231617703625e-09, + "loss": 0.001, + "step": 64071 + }, + { + "epoch": 19.79, + "learning_rate": 5.9190143796705735e-09, + "loss": 0.0014, + "step": 64072 + }, + { + "epoch": 19.79, + "learning_rate": 5.9018221386575316e-09, + "loss": 0.0012, + "step": 64073 + }, + { + "epoch": 19.79, + "learning_rate": 5.884654894706687e-09, + "loss": 0.001, + "step": 64074 + }, + { + "epoch": 19.79, + "learning_rate": 5.8675126478613396e-09, + "loss": 0.0012, + "step": 64075 + }, + { + "epoch": 19.79, + "learning_rate": 5.850395398163678e-09, + "loss": 0.0016, + "step": 64076 + }, + { + "epoch": 19.79, + "learning_rate": 5.833303145656999e-09, + "loss": 0.0018, + "step": 64077 + }, + { + "epoch": 19.79, + "learning_rate": 5.8162358903846024e-09, + "loss": 0.0011, + "step": 64078 + }, + { + "epoch": 19.79, + "learning_rate": 5.799193632387568e-09, + "loss": 0.0012, + "step": 64079 + }, + { + "epoch": 19.79, + "learning_rate": 5.7821763717103015e-09, + "loss": 0.0013, + "step": 64080 + }, + { + "epoch": 19.79, + "learning_rate": 5.765184108394995e-09, + "loss": 0.0018, + "step": 64081 + }, + { + "epoch": 19.79, + "learning_rate": 5.748216842483833e-09, + "loss": 0.0013, + "step": 64082 + }, + { + "epoch": 19.79, + "learning_rate": 5.731274574019008e-09, + "loss": 0.0015, + "step": 64083 + }, + { + "epoch": 19.79, + "learning_rate": 5.714357303042706e-09, + "loss": 0.0011, + "step": 64084 + }, + { + "epoch": 19.79, + "learning_rate": 5.697465029598226e-09, + "loss": 0.0012, + "step": 64085 + }, + { + "epoch": 19.79, + "learning_rate": 5.680597753726647e-09, + "loss": 0.002, + "step": 64086 + }, + { + "epoch": 19.79, + "learning_rate": 5.663755475471267e-09, + "loss": 0.0019, + "step": 64087 + }, + { + "epoch": 19.79, + "learning_rate": 5.646938194873164e-09, + "loss": 0.0014, + "step": 64088 + }, + { + "epoch": 19.79, + "learning_rate": 5.630145911974527e-09, + "loss": 0.0014, + "step": 64089 + }, + { + "epoch": 19.79, + "learning_rate": 5.613378626818655e-09, + "loss": 0.0012, + "step": 64090 + }, + { + "epoch": 19.79, + "learning_rate": 5.596636339446626e-09, + "loss": 0.0016, + "step": 64091 + }, + { + "epoch": 19.79, + "learning_rate": 5.579919049899518e-09, + "loss": 0.0012, + "step": 64092 + }, + { + "epoch": 19.79, + "learning_rate": 5.56322675822063e-09, + "loss": 0.0012, + "step": 64093 + }, + { + "epoch": 19.79, + "learning_rate": 5.54655946445104e-09, + "loss": 0.0015, + "step": 64094 + }, + { + "epoch": 19.79, + "learning_rate": 5.529917168631826e-09, + "loss": 0.0012, + "step": 64095 + }, + { + "epoch": 19.79, + "learning_rate": 5.513299870805178e-09, + "loss": 0.0012, + "step": 64096 + }, + { + "epoch": 19.79, + "learning_rate": 5.4967075710132825e-09, + "loss": 0.0018, + "step": 64097 + }, + { + "epoch": 19.79, + "learning_rate": 5.480140269296108e-09, + "loss": 0.0013, + "step": 64098 + }, + { + "epoch": 19.79, + "learning_rate": 5.463597965696954e-09, + "loss": 0.0022, + "step": 64099 + }, + { + "epoch": 19.8, + "learning_rate": 5.447080660255788e-09, + "loss": 0.0018, + "step": 64100 + }, + { + "epoch": 19.8, + "learning_rate": 5.430588353013688e-09, + "loss": 0.0018, + "step": 64101 + }, + { + "epoch": 19.8, + "learning_rate": 5.414121044012843e-09, + "loss": 0.0011, + "step": 64102 + }, + { + "epoch": 19.8, + "learning_rate": 5.3976787332954415e-09, + "loss": 0.0014, + "step": 64103 + }, + { + "epoch": 19.8, + "learning_rate": 5.381261420900341e-09, + "loss": 0.0015, + "step": 64104 + }, + { + "epoch": 19.8, + "learning_rate": 5.36486910686973e-09, + "loss": 0.0012, + "step": 64105 + }, + { + "epoch": 19.8, + "learning_rate": 5.3485017912446866e-09, + "loss": 0.0012, + "step": 64106 + }, + { + "epoch": 19.8, + "learning_rate": 5.332159474065179e-09, + "loss": 0.0018, + "step": 64107 + }, + { + "epoch": 19.8, + "learning_rate": 5.315842155373396e-09, + "loss": 0.0012, + "step": 64108 + }, + { + "epoch": 19.8, + "learning_rate": 5.299549835210416e-09, + "loss": 0.0017, + "step": 64109 + }, + { + "epoch": 19.8, + "learning_rate": 5.283282513615096e-09, + "loss": 0.0013, + "step": 64110 + }, + { + "epoch": 19.8, + "learning_rate": 5.267040190629624e-09, + "loss": 0.0017, + "step": 64111 + }, + { + "epoch": 19.8, + "learning_rate": 5.25082286629397e-09, + "loss": 0.0015, + "step": 64112 + }, + { + "epoch": 19.8, + "learning_rate": 5.23463054064921e-09, + "loss": 0.0014, + "step": 64113 + }, + { + "epoch": 19.8, + "learning_rate": 5.218463213735314e-09, + "loss": 0.0011, + "step": 64114 + }, + { + "epoch": 19.8, + "learning_rate": 5.202320885593359e-09, + "loss": 0.0017, + "step": 64115 + }, + { + "epoch": 19.8, + "learning_rate": 5.1862035562622035e-09, + "loss": 0.0013, + "step": 64116 + }, + { + "epoch": 19.8, + "learning_rate": 5.170111225784036e-09, + "loss": 0.0016, + "step": 64117 + }, + { + "epoch": 19.8, + "learning_rate": 5.154043894198824e-09, + "loss": 0.001, + "step": 64118 + }, + { + "epoch": 19.8, + "learning_rate": 5.138001561546535e-09, + "loss": 0.0013, + "step": 64119 + }, + { + "epoch": 19.8, + "learning_rate": 5.1219842278660284e-09, + "loss": 0.0015, + "step": 64120 + }, + { + "epoch": 19.8, + "learning_rate": 5.105991893199491e-09, + "loss": 0.0016, + "step": 64121 + }, + { + "epoch": 19.8, + "learning_rate": 5.090024557584672e-09, + "loss": 0.0019, + "step": 64122 + }, + { + "epoch": 19.8, + "learning_rate": 5.074082221062648e-09, + "loss": 0.0019, + "step": 64123 + }, + { + "epoch": 19.8, + "learning_rate": 5.058164883674499e-09, + "loss": 0.0017, + "step": 64124 + }, + { + "epoch": 19.8, + "learning_rate": 5.042272545457971e-09, + "loss": 0.0016, + "step": 64125 + }, + { + "epoch": 19.8, + "learning_rate": 5.026405206454144e-09, + "loss": 0.0018, + "step": 64126 + }, + { + "epoch": 19.8, + "learning_rate": 5.010562866701873e-09, + "loss": 0.0012, + "step": 64127 + }, + { + "epoch": 19.8, + "learning_rate": 4.99474552624113e-09, + "loss": 0.0017, + "step": 64128 + }, + { + "epoch": 19.8, + "learning_rate": 4.978953185111879e-09, + "loss": 0.0014, + "step": 64129 + }, + { + "epoch": 19.8, + "learning_rate": 4.96318584335298e-09, + "loss": 0.0013, + "step": 64130 + }, + { + "epoch": 19.8, + "learning_rate": 4.947443501004401e-09, + "loss": 0.0014, + "step": 64131 + }, + { + "epoch": 19.81, + "learning_rate": 4.931726158103889e-09, + "loss": 0.0011, + "step": 64132 + }, + { + "epoch": 19.81, + "learning_rate": 4.916033814693633e-09, + "loss": 0.0019, + "step": 64133 + }, + { + "epoch": 19.81, + "learning_rate": 4.90036647081138e-09, + "loss": 0.0017, + "step": 64134 + }, + { + "epoch": 19.81, + "learning_rate": 4.884724126495987e-09, + "loss": 0.0013, + "step": 64135 + }, + { + "epoch": 19.81, + "learning_rate": 4.869106781786315e-09, + "loss": 0.0015, + "step": 64136 + }, + { + "epoch": 19.81, + "learning_rate": 4.853514436722328e-09, + "loss": 0.0018, + "step": 64137 + }, + { + "epoch": 19.81, + "learning_rate": 4.837947091342887e-09, + "loss": 0.0016, + "step": 64138 + }, + { + "epoch": 19.81, + "learning_rate": 4.822404745686849e-09, + "loss": 0.0014, + "step": 64139 + }, + { + "epoch": 19.81, + "learning_rate": 4.80688739979307e-09, + "loss": 0.0014, + "step": 64140 + }, + { + "epoch": 19.81, + "learning_rate": 4.79139505370041e-09, + "loss": 0.0014, + "step": 64141 + }, + { + "epoch": 19.81, + "learning_rate": 4.775927707446615e-09, + "loss": 0.0015, + "step": 64142 + }, + { + "epoch": 19.81, + "learning_rate": 4.760485361071654e-09, + "loss": 0.0015, + "step": 64143 + }, + { + "epoch": 19.81, + "learning_rate": 4.7450680146143845e-09, + "loss": 0.001, + "step": 64144 + }, + { + "epoch": 19.81, + "learning_rate": 4.729675668111444e-09, + "loss": 0.0014, + "step": 64145 + }, + { + "epoch": 19.81, + "learning_rate": 4.714308321603911e-09, + "loss": 0.0013, + "step": 64146 + }, + { + "epoch": 19.81, + "learning_rate": 4.698965975128422e-09, + "loss": 0.0016, + "step": 64147 + }, + { + "epoch": 19.81, + "learning_rate": 4.683648628723836e-09, + "loss": 0.0017, + "step": 64148 + }, + { + "epoch": 19.81, + "learning_rate": 4.6683562824279e-09, + "loss": 0.0019, + "step": 64149 + }, + { + "epoch": 19.81, + "learning_rate": 4.653088936280581e-09, + "loss": 0.0014, + "step": 64150 + }, + { + "epoch": 19.81, + "learning_rate": 4.637846590317407e-09, + "loss": 0.0016, + "step": 64151 + }, + { + "epoch": 19.81, + "learning_rate": 4.622629244579458e-09, + "loss": 0.0024, + "step": 64152 + }, + { + "epoch": 19.81, + "learning_rate": 4.607436899102257e-09, + "loss": 0.0016, + "step": 64153 + }, + { + "epoch": 19.81, + "learning_rate": 4.592269553925777e-09, + "loss": 0.0015, + "step": 64154 + }, + { + "epoch": 19.81, + "learning_rate": 4.577127209086651e-09, + "loss": 0.0018, + "step": 64155 + }, + { + "epoch": 19.81, + "learning_rate": 4.56200986462374e-09, + "loss": 0.0017, + "step": 64156 + }, + { + "epoch": 19.81, + "learning_rate": 4.5469175205736795e-09, + "loss": 0.0015, + "step": 64157 + }, + { + "epoch": 19.81, + "learning_rate": 4.5318501769753274e-09, + "loss": 0.001, + "step": 64158 + }, + { + "epoch": 19.81, + "learning_rate": 4.516807833865322e-09, + "loss": 0.0013, + "step": 64159 + }, + { + "epoch": 19.81, + "learning_rate": 4.50179049128141e-09, + "loss": 0.0013, + "step": 64160 + }, + { + "epoch": 19.81, + "learning_rate": 4.48679814926245e-09, + "loss": 0.0013, + "step": 64161 + }, + { + "epoch": 19.81, + "learning_rate": 4.471830807845079e-09, + "loss": 0.0019, + "step": 64162 + }, + { + "epoch": 19.81, + "learning_rate": 4.4568884670670445e-09, + "loss": 0.0015, + "step": 64163 + }, + { + "epoch": 19.81, + "learning_rate": 4.441971126963873e-09, + "loss": 0.0013, + "step": 64164 + }, + { + "epoch": 19.82, + "learning_rate": 4.427078787575534e-09, + "loss": 0.0017, + "step": 64165 + }, + { + "epoch": 19.82, + "learning_rate": 4.412211448938663e-09, + "loss": 0.0017, + "step": 64166 + }, + { + "epoch": 19.82, + "learning_rate": 4.397369111088789e-09, + "loss": 0.0014, + "step": 64167 + }, + { + "epoch": 19.82, + "learning_rate": 4.382551774064769e-09, + "loss": 0.0025, + "step": 64168 + }, + { + "epoch": 19.82, + "learning_rate": 4.3677594379032405e-09, + "loss": 0.0021, + "step": 64169 + }, + { + "epoch": 19.82, + "learning_rate": 4.35299210264084e-09, + "loss": 0.0017, + "step": 64170 + }, + { + "epoch": 19.82, + "learning_rate": 4.338249768314206e-09, + "loss": 0.0012, + "step": 64171 + }, + { + "epoch": 19.82, + "learning_rate": 4.3235324349610866e-09, + "loss": 0.0016, + "step": 64172 + }, + { + "epoch": 19.82, + "learning_rate": 4.308840102618117e-09, + "loss": 0.0015, + "step": 64173 + }, + { + "epoch": 19.82, + "learning_rate": 4.294172771321936e-09, + "loss": 0.0019, + "step": 64174 + }, + { + "epoch": 19.82, + "learning_rate": 4.279530441109181e-09, + "loss": 0.0016, + "step": 64175 + }, + { + "epoch": 19.82, + "learning_rate": 4.264913112015378e-09, + "loss": 0.0009, + "step": 64176 + }, + { + "epoch": 19.82, + "learning_rate": 4.250320784079387e-09, + "loss": 0.0019, + "step": 64177 + }, + { + "epoch": 19.82, + "learning_rate": 4.235753457335623e-09, + "loss": 0.0018, + "step": 64178 + }, + { + "epoch": 19.82, + "learning_rate": 4.221211131821834e-09, + "loss": 0.0017, + "step": 64179 + }, + { + "epoch": 19.82, + "learning_rate": 4.2066938075735475e-09, + "loss": 0.0017, + "step": 64180 + }, + { + "epoch": 19.82, + "learning_rate": 4.192201484628511e-09, + "loss": 0.0015, + "step": 64181 + }, + { + "epoch": 19.82, + "learning_rate": 4.177734163021141e-09, + "loss": 0.0012, + "step": 64182 + }, + { + "epoch": 19.82, + "learning_rate": 4.1632918427880755e-09, + "loss": 0.0018, + "step": 64183 + }, + { + "epoch": 19.82, + "learning_rate": 4.148874523965951e-09, + "loss": 0.0013, + "step": 64184 + }, + { + "epoch": 19.82, + "learning_rate": 4.134482206590296e-09, + "loss": 0.0013, + "step": 64185 + }, + { + "epoch": 19.82, + "learning_rate": 4.120114890697746e-09, + "loss": 0.0018, + "step": 64186 + }, + { + "epoch": 19.82, + "learning_rate": 4.10577257632383e-09, + "loss": 0.0012, + "step": 64187 + }, + { + "epoch": 19.82, + "learning_rate": 4.091455263505184e-09, + "loss": 0.0015, + "step": 64188 + }, + { + "epoch": 19.82, + "learning_rate": 4.077162952276225e-09, + "loss": 0.0016, + "step": 64189 + }, + { + "epoch": 19.82, + "learning_rate": 4.062895642673592e-09, + "loss": 0.0018, + "step": 64190 + }, + { + "epoch": 19.82, + "learning_rate": 4.048653334732811e-09, + "loss": 0.0011, + "step": 64191 + }, + { + "epoch": 19.82, + "learning_rate": 4.034436028489408e-09, + "loss": 0.0012, + "step": 64192 + }, + { + "epoch": 19.82, + "learning_rate": 4.020243723978912e-09, + "loss": 0.0016, + "step": 64193 + }, + { + "epoch": 19.82, + "learning_rate": 4.006076421236849e-09, + "loss": 0.0013, + "step": 64194 + }, + { + "epoch": 19.82, + "learning_rate": 3.991934120298746e-09, + "loss": 0.0014, + "step": 64195 + }, + { + "epoch": 19.82, + "learning_rate": 3.977816821201242e-09, + "loss": 0.0014, + "step": 64196 + }, + { + "epoch": 19.83, + "learning_rate": 3.963724523976531e-09, + "loss": 0.0007, + "step": 64197 + }, + { + "epoch": 19.83, + "learning_rate": 3.949657228663473e-09, + "loss": 0.0017, + "step": 64198 + }, + { + "epoch": 19.83, + "learning_rate": 3.935614935294263e-09, + "loss": 0.0017, + "step": 64199 + }, + { + "epoch": 19.83, + "learning_rate": 3.9215976439055395e-09, + "loss": 0.001, + "step": 64200 + }, + { + "epoch": 19.83, + "learning_rate": 3.907605354531718e-09, + "loss": 0.0018, + "step": 64201 + }, + { + "epoch": 19.83, + "learning_rate": 3.8936380672083276e-09, + "loss": 0.0014, + "step": 64202 + }, + { + "epoch": 19.83, + "learning_rate": 3.8796957819708934e-09, + "loss": 0.0013, + "step": 64203 + }, + { + "epoch": 19.83, + "learning_rate": 3.865778498852724e-09, + "loss": 0.0014, + "step": 64204 + }, + { + "epoch": 19.83, + "learning_rate": 3.8518862178893446e-09, + "loss": 0.0015, + "step": 64205 + }, + { + "epoch": 19.83, + "learning_rate": 3.838018939116284e-09, + "loss": 0.0015, + "step": 64206 + }, + { + "epoch": 19.83, + "learning_rate": 3.824176662566847e-09, + "loss": 0.0016, + "step": 64207 + }, + { + "epoch": 19.83, + "learning_rate": 3.810359388276563e-09, + "loss": 0.0014, + "step": 64208 + }, + { + "epoch": 19.83, + "learning_rate": 3.796567116279848e-09, + "loss": 0.0012, + "step": 64209 + }, + { + "epoch": 19.83, + "learning_rate": 3.7827998466111185e-09, + "loss": 0.0016, + "step": 64210 + }, + { + "epoch": 19.83, + "learning_rate": 3.769057579304791e-09, + "loss": 0.0017, + "step": 64211 + }, + { + "epoch": 19.83, + "learning_rate": 3.755340314395284e-09, + "loss": 0.0011, + "step": 64212 + }, + { + "epoch": 19.83, + "learning_rate": 3.7416480519170126e-09, + "loss": 0.0012, + "step": 64213 + }, + { + "epoch": 19.83, + "learning_rate": 3.727980791904395e-09, + "loss": 0.0023, + "step": 64214 + }, + { + "epoch": 19.83, + "learning_rate": 3.714338534390738e-09, + "loss": 0.0017, + "step": 64215 + }, + { + "epoch": 19.83, + "learning_rate": 3.7007212794104576e-09, + "loss": 0.0014, + "step": 64216 + }, + { + "epoch": 19.83, + "learning_rate": 3.6871290269979708e-09, + "loss": 0.0017, + "step": 64217 + }, + { + "epoch": 19.83, + "learning_rate": 3.673561777187695e-09, + "loss": 0.0015, + "step": 64218 + }, + { + "epoch": 19.83, + "learning_rate": 3.6600195300129372e-09, + "loss": 0.0014, + "step": 64219 + }, + { + "epoch": 19.83, + "learning_rate": 3.6465022855070033e-09, + "loss": 0.0019, + "step": 64220 + }, + { + "epoch": 19.83, + "learning_rate": 3.6330100437054207e-09, + "loss": 0.0019, + "step": 64221 + }, + { + "epoch": 19.83, + "learning_rate": 3.6195428046403858e-09, + "loss": 0.0013, + "step": 64222 + }, + { + "epoch": 19.83, + "learning_rate": 3.606100568346316e-09, + "loss": 0.0012, + "step": 64223 + }, + { + "epoch": 19.83, + "learning_rate": 3.592683334856517e-09, + "loss": 0.0013, + "step": 64224 + }, + { + "epoch": 19.83, + "learning_rate": 3.5792911042042967e-09, + "loss": 0.0012, + "step": 64225 + }, + { + "epoch": 19.83, + "learning_rate": 3.5659238764240713e-09, + "loss": 0.0013, + "step": 64226 + }, + { + "epoch": 19.83, + "learning_rate": 3.552581651548037e-09, + "loss": 0.0017, + "step": 64227 + }, + { + "epoch": 19.83, + "learning_rate": 3.5392644296106115e-09, + "loss": 0.0017, + "step": 64228 + }, + { + "epoch": 19.84, + "learning_rate": 3.525972210645101e-09, + "loss": 0.0015, + "step": 64229 + }, + { + "epoch": 19.84, + "learning_rate": 3.5127049946837024e-09, + "loss": 0.0014, + "step": 64230 + }, + { + "epoch": 19.84, + "learning_rate": 3.4994627817608316e-09, + "loss": 0.0014, + "step": 64231 + }, + { + "epoch": 19.84, + "learning_rate": 3.486245571908686e-09, + "loss": 0.0015, + "step": 64232 + }, + { + "epoch": 19.84, + "learning_rate": 3.4730533651605724e-09, + "loss": 0.0019, + "step": 64233 + }, + { + "epoch": 19.84, + "learning_rate": 3.459886161549797e-09, + "loss": 0.0014, + "step": 64234 + }, + { + "epoch": 19.84, + "learning_rate": 3.4467439611085563e-09, + "loss": 0.002, + "step": 64235 + }, + { + "epoch": 19.84, + "learning_rate": 3.433626763871267e-09, + "loss": 0.0018, + "step": 64236 + }, + { + "epoch": 19.84, + "learning_rate": 3.4205345698690162e-09, + "loss": 0.0016, + "step": 64237 + }, + { + "epoch": 19.84, + "learning_rate": 3.40746737913622e-09, + "loss": 0.0014, + "step": 64238 + }, + { + "epoch": 19.84, + "learning_rate": 3.394425191703965e-09, + "loss": 0.0013, + "step": 64239 + }, + { + "epoch": 19.84, + "learning_rate": 3.3814080076055576e-09, + "loss": 0.0013, + "step": 64240 + }, + { + "epoch": 19.84, + "learning_rate": 3.368415826873195e-09, + "loss": 0.001, + "step": 64241 + }, + { + "epoch": 19.84, + "learning_rate": 3.3554486495401827e-09, + "loss": 0.0016, + "step": 64242 + }, + { + "epoch": 19.84, + "learning_rate": 3.342506475637608e-09, + "loss": 0.0028, + "step": 64243 + }, + { + "epoch": 19.84, + "learning_rate": 3.3295893051998873e-09, + "loss": 0.0014, + "step": 64244 + }, + { + "epoch": 19.84, + "learning_rate": 3.316697138256997e-09, + "loss": 0.0016, + "step": 64245 + }, + { + "epoch": 19.84, + "learning_rate": 3.3038299748433532e-09, + "loss": 0.0016, + "step": 64246 + }, + { + "epoch": 19.84, + "learning_rate": 3.290987814990043e-09, + "loss": 0.0011, + "step": 64247 + }, + { + "epoch": 19.84, + "learning_rate": 3.2781706587281524e-09, + "loss": 0.0014, + "step": 64248 + }, + { + "epoch": 19.84, + "learning_rate": 3.2653785060920984e-09, + "loss": 0.0013, + "step": 64249 + }, + { + "epoch": 19.84, + "learning_rate": 3.2526113571118566e-09, + "loss": 0.0015, + "step": 64250 + }, + { + "epoch": 19.84, + "learning_rate": 3.239869211820734e-09, + "loss": 0.0017, + "step": 64251 + }, + { + "epoch": 19.84, + "learning_rate": 3.227152070249817e-09, + "loss": 0.0016, + "step": 64252 + }, + { + "epoch": 19.84, + "learning_rate": 3.2144599324301917e-09, + "loss": 0.0016, + "step": 64253 + }, + { + "epoch": 19.84, + "learning_rate": 3.2017927983951646e-09, + "loss": 0.0014, + "step": 64254 + }, + { + "epoch": 19.84, + "learning_rate": 3.189150668175822e-09, + "loss": 0.0019, + "step": 64255 + }, + { + "epoch": 19.84, + "learning_rate": 3.176533541804361e-09, + "loss": 0.0015, + "step": 64256 + }, + { + "epoch": 19.84, + "learning_rate": 3.1639414193107566e-09, + "loss": 0.002, + "step": 64257 + }, + { + "epoch": 19.84, + "learning_rate": 3.151374300728316e-09, + "loss": 0.0013, + "step": 64258 + }, + { + "epoch": 19.84, + "learning_rate": 3.138832186087015e-09, + "loss": 0.0014, + "step": 64259 + }, + { + "epoch": 19.84, + "learning_rate": 3.1263150754179405e-09, + "loss": 0.0017, + "step": 64260 + }, + { + "epoch": 19.84, + "learning_rate": 3.1138229687543985e-09, + "loss": 0.0016, + "step": 64261 + }, + { + "epoch": 19.85, + "learning_rate": 3.1013558661263654e-09, + "loss": 0.0012, + "step": 64262 + }, + { + "epoch": 19.85, + "learning_rate": 3.0889137675649274e-09, + "loss": 0.0014, + "step": 64263 + }, + { + "epoch": 19.85, + "learning_rate": 3.0764966731022806e-09, + "loss": 0.0014, + "step": 64264 + }, + { + "epoch": 19.85, + "learning_rate": 3.064104582767291e-09, + "loss": 0.0018, + "step": 64265 + }, + { + "epoch": 19.85, + "learning_rate": 3.0517374965932654e-09, + "loss": 0.0018, + "step": 64266 + }, + { + "epoch": 19.85, + "learning_rate": 3.03939541461018e-09, + "loss": 0.0017, + "step": 64267 + }, + { + "epoch": 19.85, + "learning_rate": 3.0270783368480104e-09, + "loss": 0.0012, + "step": 64268 + }, + { + "epoch": 19.85, + "learning_rate": 3.0147862633389534e-09, + "loss": 0.0023, + "step": 64269 + }, + { + "epoch": 19.85, + "learning_rate": 3.0025191941129848e-09, + "loss": 0.0014, + "step": 64270 + }, + { + "epoch": 19.85, + "learning_rate": 2.9902771292023013e-09, + "loss": 0.0014, + "step": 64271 + }, + { + "epoch": 19.85, + "learning_rate": 2.9780600686346582e-09, + "loss": 0.0015, + "step": 64272 + }, + { + "epoch": 19.85, + "learning_rate": 2.9658680124433623e-09, + "loss": 0.001, + "step": 64273 + }, + { + "epoch": 19.85, + "learning_rate": 2.9537009606572798e-09, + "loss": 0.0018, + "step": 64274 + }, + { + "epoch": 19.85, + "learning_rate": 2.9415589133074964e-09, + "loss": 0.0013, + "step": 64275 + }, + { + "epoch": 19.85, + "learning_rate": 2.929441870423988e-09, + "loss": 0.0019, + "step": 64276 + }, + { + "epoch": 19.85, + "learning_rate": 2.9173498320378413e-09, + "loss": 0.0016, + "step": 64277 + }, + { + "epoch": 19.85, + "learning_rate": 2.905282798177922e-09, + "loss": 0.0013, + "step": 64278 + }, + { + "epoch": 19.85, + "learning_rate": 2.893240768875316e-09, + "loss": 0.0011, + "step": 64279 + }, + { + "epoch": 19.85, + "learning_rate": 2.8812237441611104e-09, + "loss": 0.0013, + "step": 64280 + }, + { + "epoch": 19.85, + "learning_rate": 2.8692317240630597e-09, + "loss": 0.0021, + "step": 64281 + }, + { + "epoch": 19.85, + "learning_rate": 2.857264708613361e-09, + "loss": 0.0016, + "step": 64282 + }, + { + "epoch": 19.85, + "learning_rate": 2.84532269784088e-09, + "loss": 0.0011, + "step": 64283 + }, + { + "epoch": 19.85, + "learning_rate": 2.8334056917744824e-09, + "loss": 0.0017, + "step": 64284 + }, + { + "epoch": 19.85, + "learning_rate": 2.8215136904463647e-09, + "loss": 0.0011, + "step": 64285 + }, + { + "epoch": 19.85, + "learning_rate": 2.8096466938853927e-09, + "loss": 0.0014, + "step": 64286 + }, + { + "epoch": 19.85, + "learning_rate": 2.797804702119322e-09, + "loss": 0.0017, + "step": 64287 + }, + { + "epoch": 19.85, + "learning_rate": 2.7859877151803494e-09, + "loss": 0.0011, + "step": 64288 + }, + { + "epoch": 19.85, + "learning_rate": 2.77419573309734e-09, + "loss": 0.0021, + "step": 64289 + }, + { + "epoch": 19.85, + "learning_rate": 2.76242875589805e-09, + "loss": 0.0012, + "step": 64290 + }, + { + "epoch": 19.85, + "learning_rate": 2.7506867836146757e-09, + "loss": 0.0013, + "step": 64291 + }, + { + "epoch": 19.85, + "learning_rate": 2.738969816274972e-09, + "loss": 0.0015, + "step": 64292 + }, + { + "epoch": 19.85, + "learning_rate": 2.7272778539078058e-09, + "loss": 0.0016, + "step": 64293 + }, + { + "epoch": 19.86, + "learning_rate": 2.715610896543153e-09, + "loss": 0.0015, + "step": 64294 + }, + { + "epoch": 19.86, + "learning_rate": 2.7039689442109883e-09, + "loss": 0.0011, + "step": 64295 + }, + { + "epoch": 19.86, + "learning_rate": 2.692351996939069e-09, + "loss": 0.0018, + "step": 64296 + }, + { + "epoch": 19.86, + "learning_rate": 2.68076005475737e-09, + "loss": 0.0011, + "step": 64297 + }, + { + "epoch": 19.86, + "learning_rate": 2.669193117693647e-09, + "loss": 0.0011, + "step": 64298 + }, + { + "epoch": 19.86, + "learning_rate": 2.6576511857778765e-09, + "loss": 0.0016, + "step": 64299 + }, + { + "epoch": 19.86, + "learning_rate": 2.646134259038924e-09, + "loss": 0.0021, + "step": 64300 + }, + { + "epoch": 19.86, + "learning_rate": 2.634642337505655e-09, + "loss": 0.0014, + "step": 64301 + }, + { + "epoch": 19.86, + "learning_rate": 2.623175421206936e-09, + "loss": 0.0017, + "step": 64302 + }, + { + "epoch": 19.86, + "learning_rate": 2.611733510170522e-09, + "loss": 0.0018, + "step": 64303 + }, + { + "epoch": 19.86, + "learning_rate": 2.600316604425279e-09, + "loss": 0.0014, + "step": 64304 + }, + { + "epoch": 19.86, + "learning_rate": 2.588924704000073e-09, + "loss": 0.0018, + "step": 64305 + }, + { + "epoch": 19.86, + "learning_rate": 2.5775578089237697e-09, + "loss": 0.0013, + "step": 64306 + }, + { + "epoch": 19.86, + "learning_rate": 2.5662159192241243e-09, + "loss": 0.0013, + "step": 64307 + }, + { + "epoch": 19.86, + "learning_rate": 2.554899034930003e-09, + "loss": 0.0011, + "step": 64308 + }, + { + "epoch": 19.86, + "learning_rate": 2.543607156069161e-09, + "loss": 0.0012, + "step": 64309 + }, + { + "epoch": 19.86, + "learning_rate": 2.5323402826704645e-09, + "loss": 0.0017, + "step": 64310 + }, + { + "epoch": 19.86, + "learning_rate": 2.521098414761669e-09, + "loss": 0.0015, + "step": 64311 + }, + { + "epoch": 19.86, + "learning_rate": 2.5098815523716402e-09, + "loss": 0.0016, + "step": 64312 + }, + { + "epoch": 19.86, + "learning_rate": 2.4986896955270234e-09, + "loss": 0.0012, + "step": 64313 + }, + { + "epoch": 19.86, + "learning_rate": 2.4875228442566846e-09, + "loss": 0.0016, + "step": 64314 + }, + { + "epoch": 19.86, + "learning_rate": 2.476380998589489e-09, + "loss": 0.0014, + "step": 64315 + }, + { + "epoch": 19.86, + "learning_rate": 2.465264158550973e-09, + "loss": 0.0012, + "step": 64316 + }, + { + "epoch": 19.86, + "learning_rate": 2.454172324171111e-09, + "loss": 0.0016, + "step": 64317 + }, + { + "epoch": 19.86, + "learning_rate": 2.4431054954765497e-09, + "loss": 0.0012, + "step": 64318 + }, + { + "epoch": 19.86, + "learning_rate": 2.4320636724950443e-09, + "loss": 0.0013, + "step": 64319 + }, + { + "epoch": 19.86, + "learning_rate": 2.42104685525435e-09, + "loss": 0.0018, + "step": 64320 + }, + { + "epoch": 19.86, + "learning_rate": 2.4100550437822222e-09, + "loss": 0.0012, + "step": 64321 + }, + { + "epoch": 19.86, + "learning_rate": 2.399088238106417e-09, + "loss": 0.0013, + "step": 64322 + }, + { + "epoch": 19.86, + "learning_rate": 2.3881464382535803e-09, + "loss": 0.0015, + "step": 64323 + }, + { + "epoch": 19.86, + "learning_rate": 2.3772296442514665e-09, + "loss": 0.0015, + "step": 64324 + }, + { + "epoch": 19.86, + "learning_rate": 2.3663378561267213e-09, + "loss": 0.0017, + "step": 64325 + }, + { + "epoch": 19.86, + "learning_rate": 2.3554710739082108e-09, + "loss": 0.0015, + "step": 64326 + }, + { + "epoch": 19.87, + "learning_rate": 2.34462929762147e-09, + "loss": 0.0019, + "step": 64327 + }, + { + "epoch": 19.87, + "learning_rate": 2.3338125272953648e-09, + "loss": 0.0015, + "step": 64328 + }, + { + "epoch": 19.87, + "learning_rate": 2.32302076295432e-09, + "loss": 0.0018, + "step": 64329 + }, + { + "epoch": 19.87, + "learning_rate": 2.3122540046283115e-09, + "loss": 0.0008, + "step": 64330 + }, + { + "epoch": 19.87, + "learning_rate": 2.301512252341764e-09, + "loss": 0.0012, + "step": 64331 + }, + { + "epoch": 19.87, + "learning_rate": 2.290795506122434e-09, + "loss": 0.0011, + "step": 64332 + }, + { + "epoch": 19.87, + "learning_rate": 2.2801037659980763e-09, + "loss": 0.0014, + "step": 64333 + }, + { + "epoch": 19.87, + "learning_rate": 2.269437031994226e-09, + "loss": 0.001, + "step": 64334 + }, + { + "epoch": 19.87, + "learning_rate": 2.258795304138639e-09, + "loss": 0.0021, + "step": 64335 + }, + { + "epoch": 19.87, + "learning_rate": 2.24817858245574e-09, + "loss": 0.0011, + "step": 64336 + }, + { + "epoch": 19.87, + "learning_rate": 2.2375868669755053e-09, + "loss": 0.0016, + "step": 64337 + }, + { + "epoch": 19.87, + "learning_rate": 2.2270201577212493e-09, + "loss": 0.0014, + "step": 64338 + }, + { + "epoch": 19.87, + "learning_rate": 2.2164784547207273e-09, + "loss": 0.0016, + "step": 64339 + }, + { + "epoch": 19.87, + "learning_rate": 2.2059617580005854e-09, + "loss": 0.0014, + "step": 64340 + }, + { + "epoch": 19.87, + "learning_rate": 2.1954700675874684e-09, + "loss": 0.0015, + "step": 64341 + }, + { + "epoch": 19.87, + "learning_rate": 2.1850033835058015e-09, + "loss": 0.0023, + "step": 64342 + }, + { + "epoch": 19.87, + "learning_rate": 2.17456170578334e-09, + "loss": 0.0019, + "step": 64343 + }, + { + "epoch": 19.87, + "learning_rate": 2.1641450344467296e-09, + "loss": 0.0013, + "step": 64344 + }, + { + "epoch": 19.87, + "learning_rate": 2.1537533695203947e-09, + "loss": 0.0018, + "step": 64345 + }, + { + "epoch": 19.87, + "learning_rate": 2.1433867110309814e-09, + "loss": 0.0015, + "step": 64346 + }, + { + "epoch": 19.87, + "learning_rate": 2.133045059004024e-09, + "loss": 0.0013, + "step": 64347 + }, + { + "epoch": 19.87, + "learning_rate": 2.1227284134661683e-09, + "loss": 0.0009, + "step": 64348 + }, + { + "epoch": 19.87, + "learning_rate": 2.1124367744429497e-09, + "loss": 0.0012, + "step": 64349 + }, + { + "epoch": 19.87, + "learning_rate": 2.102170141959903e-09, + "loss": 0.0012, + "step": 64350 + }, + { + "epoch": 19.87, + "learning_rate": 2.0919285160425627e-09, + "loss": 0.0019, + "step": 64351 + }, + { + "epoch": 19.87, + "learning_rate": 2.0817118967175753e-09, + "loss": 0.0014, + "step": 64352 + }, + { + "epoch": 19.87, + "learning_rate": 2.071520284009365e-09, + "loss": 0.0021, + "step": 64353 + }, + { + "epoch": 19.87, + "learning_rate": 2.0613536779434673e-09, + "loss": 0.0011, + "step": 64354 + }, + { + "epoch": 19.87, + "learning_rate": 2.051212078546527e-09, + "loss": 0.0018, + "step": 64355 + }, + { + "epoch": 19.87, + "learning_rate": 2.0410954858418597e-09, + "loss": 0.0016, + "step": 64356 + }, + { + "epoch": 19.87, + "learning_rate": 2.03100389985611e-09, + "loss": 0.0011, + "step": 64357 + }, + { + "epoch": 19.87, + "learning_rate": 2.020937320614813e-09, + "loss": 0.0016, + "step": 64358 + }, + { + "epoch": 19.88, + "learning_rate": 2.010895748142394e-09, + "loss": 0.0017, + "step": 64359 + }, + { + "epoch": 19.88, + "learning_rate": 2.000879182464388e-09, + "loss": 0.0011, + "step": 64360 + }, + { + "epoch": 19.88, + "learning_rate": 1.99088762360633e-09, + "loss": 0.0016, + "step": 64361 + }, + { + "epoch": 19.88, + "learning_rate": 1.980921071591535e-09, + "loss": 0.0017, + "step": 64362 + }, + { + "epoch": 19.88, + "learning_rate": 1.970979526446648e-09, + "loss": 0.0014, + "step": 64363 + }, + { + "epoch": 19.88, + "learning_rate": 1.961062988196094e-09, + "loss": 0.0011, + "step": 64364 + }, + { + "epoch": 19.88, + "learning_rate": 1.951171456863188e-09, + "loss": 0.0024, + "step": 64365 + }, + { + "epoch": 19.88, + "learning_rate": 1.9413049324745746e-09, + "loss": 0.0015, + "step": 64366 + }, + { + "epoch": 19.88, + "learning_rate": 1.9314634150546794e-09, + "loss": 0.0017, + "step": 64367 + }, + { + "epoch": 19.88, + "learning_rate": 1.921646904627927e-09, + "loss": 0.0014, + "step": 64368 + }, + { + "epoch": 19.88, + "learning_rate": 1.911855401217633e-09, + "loss": 0.0012, + "step": 64369 + }, + { + "epoch": 19.88, + "learning_rate": 1.9020889048504408e-09, + "loss": 0.0016, + "step": 64370 + }, + { + "epoch": 19.88, + "learning_rate": 1.8923474155485566e-09, + "loss": 0.0025, + "step": 64371 + }, + { + "epoch": 19.88, + "learning_rate": 1.882630933338625e-09, + "loss": 0.0018, + "step": 64372 + }, + { + "epoch": 19.88, + "learning_rate": 1.8729394582428504e-09, + "loss": 0.0015, + "step": 64373 + }, + { + "epoch": 19.88, + "learning_rate": 1.8632729902867684e-09, + "loss": 0.0016, + "step": 64374 + }, + { + "epoch": 19.88, + "learning_rate": 1.8536315294948037e-09, + "loss": 0.0018, + "step": 64375 + }, + { + "epoch": 19.88, + "learning_rate": 1.8440150758891605e-09, + "loss": 0.0018, + "step": 64376 + }, + { + "epoch": 19.88, + "learning_rate": 1.8344236294964846e-09, + "loss": 0.0015, + "step": 64377 + }, + { + "epoch": 19.88, + "learning_rate": 1.82485719033898e-09, + "loss": 0.0013, + "step": 64378 + }, + { + "epoch": 19.88, + "learning_rate": 1.8153157584399616e-09, + "loss": 0.0015, + "step": 64379 + }, + { + "epoch": 19.88, + "learning_rate": 1.805799333826075e-09, + "loss": 0.001, + "step": 64380 + }, + { + "epoch": 19.88, + "learning_rate": 1.7963079165184138e-09, + "loss": 0.0016, + "step": 64381 + }, + { + "epoch": 19.88, + "learning_rate": 1.7868415065414035e-09, + "loss": 0.0013, + "step": 64382 + }, + { + "epoch": 19.88, + "learning_rate": 1.777400103920579e-09, + "loss": 0.0016, + "step": 64383 + }, + { + "epoch": 19.88, + "learning_rate": 1.7679837086770345e-09, + "loss": 0.0014, + "step": 64384 + }, + { + "epoch": 19.88, + "learning_rate": 1.7585923208351952e-09, + "loss": 0.0021, + "step": 64385 + }, + { + "epoch": 19.88, + "learning_rate": 1.7492259404194855e-09, + "loss": 0.0016, + "step": 64386 + }, + { + "epoch": 19.88, + "learning_rate": 1.739884567451e-09, + "loss": 0.0015, + "step": 64387 + }, + { + "epoch": 19.88, + "learning_rate": 1.730568201956384e-09, + "loss": 0.0016, + "step": 64388 + }, + { + "epoch": 19.88, + "learning_rate": 1.7212768439556216e-09, + "loss": 0.0017, + "step": 64389 + }, + { + "epoch": 19.88, + "learning_rate": 1.7120104934742476e-09, + "loss": 0.0012, + "step": 64390 + }, + { + "epoch": 19.89, + "learning_rate": 1.702769150535577e-09, + "loss": 0.002, + "step": 64391 + }, + { + "epoch": 19.89, + "learning_rate": 1.6935528151607039e-09, + "loss": 0.0013, + "step": 64392 + }, + { + "epoch": 19.89, + "learning_rate": 1.6843614873740533e-09, + "loss": 0.0013, + "step": 64393 + }, + { + "epoch": 19.89, + "learning_rate": 1.6751951671989398e-09, + "loss": 0.0016, + "step": 64394 + }, + { + "epoch": 19.89, + "learning_rate": 1.6660538546575677e-09, + "loss": 0.002, + "step": 64395 + }, + { + "epoch": 19.89, + "learning_rate": 1.6569375497721418e-09, + "loss": 0.0018, + "step": 64396 + }, + { + "epoch": 19.89, + "learning_rate": 1.6478462525670869e-09, + "loss": 0.0017, + "step": 64397 + }, + { + "epoch": 19.89, + "learning_rate": 1.6387799630646072e-09, + "loss": 0.0022, + "step": 64398 + }, + { + "epoch": 19.89, + "learning_rate": 1.6297386812857974e-09, + "loss": 0.0014, + "step": 64399 + }, + { + "epoch": 19.89, + "learning_rate": 1.6207224072561922e-09, + "loss": 0.0014, + "step": 64400 + }, + { + "epoch": 19.89, + "learning_rate": 1.6117311409957758e-09, + "loss": 0.0017, + "step": 64401 + }, + { + "epoch": 19.89, + "learning_rate": 1.602764882527863e-09, + "loss": 0.0013, + "step": 64402 + }, + { + "epoch": 19.89, + "learning_rate": 1.5938236318757683e-09, + "loss": 0.0012, + "step": 64403 + }, + { + "epoch": 19.89, + "learning_rate": 1.5849073890605859e-09, + "loss": 0.0019, + "step": 64404 + }, + { + "epoch": 19.89, + "learning_rate": 1.5760161541056306e-09, + "loss": 0.0013, + "step": 64405 + }, + { + "epoch": 19.89, + "learning_rate": 1.5671499270319968e-09, + "loss": 0.0014, + "step": 64406 + }, + { + "epoch": 19.89, + "learning_rate": 1.5583087078629988e-09, + "loss": 0.0012, + "step": 64407 + }, + { + "epoch": 19.89, + "learning_rate": 1.5494924966208414e-09, + "loss": 0.0015, + "step": 64408 + }, + { + "epoch": 19.89, + "learning_rate": 1.5407012933255082e-09, + "loss": 0.001, + "step": 64409 + }, + { + "epoch": 19.89, + "learning_rate": 1.5319350980014248e-09, + "loss": 0.0016, + "step": 64410 + }, + { + "epoch": 19.89, + "learning_rate": 1.5231939106696846e-09, + "loss": 0.0016, + "step": 64411 + }, + { + "epoch": 19.89, + "learning_rate": 1.5144777313513825e-09, + "loss": 0.0014, + "step": 64412 + }, + { + "epoch": 19.89, + "learning_rate": 1.5057865600698329e-09, + "loss": 0.0014, + "step": 64413 + }, + { + "epoch": 19.89, + "learning_rate": 1.4971203968461301e-09, + "loss": 0.0015, + "step": 64414 + }, + { + "epoch": 19.89, + "learning_rate": 1.4884792417002581e-09, + "loss": 0.0011, + "step": 64415 + }, + { + "epoch": 19.89, + "learning_rate": 1.4798630946566416e-09, + "loss": 0.0016, + "step": 64416 + }, + { + "epoch": 19.89, + "learning_rate": 1.471271955735265e-09, + "loss": 0.002, + "step": 64417 + }, + { + "epoch": 19.89, + "learning_rate": 1.4627058249572223e-09, + "loss": 0.0014, + "step": 64418 + }, + { + "epoch": 19.89, + "learning_rate": 1.454164702344718e-09, + "loss": 0.0012, + "step": 64419 + }, + { + "epoch": 19.89, + "learning_rate": 1.4456485879199567e-09, + "loss": 0.0013, + "step": 64420 + }, + { + "epoch": 19.89, + "learning_rate": 1.437157481701812e-09, + "loss": 0.001, + "step": 64421 + }, + { + "epoch": 19.89, + "learning_rate": 1.4286913837135985e-09, + "loss": 0.0014, + "step": 64422 + }, + { + "epoch": 19.89, + "learning_rate": 1.4202502939764106e-09, + "loss": 0.0013, + "step": 64423 + }, + { + "epoch": 19.9, + "learning_rate": 1.4118342125102324e-09, + "loss": 0.0015, + "step": 64424 + }, + { + "epoch": 19.9, + "learning_rate": 1.4034431393372683e-09, + "loss": 0.0019, + "step": 64425 + }, + { + "epoch": 19.9, + "learning_rate": 1.3950770744775023e-09, + "loss": 0.0012, + "step": 64426 + }, + { + "epoch": 19.9, + "learning_rate": 1.3867360179520284e-09, + "loss": 0.0014, + "step": 64427 + }, + { + "epoch": 19.9, + "learning_rate": 1.378419969781941e-09, + "loss": 0.0013, + "step": 64428 + }, + { + "epoch": 19.9, + "learning_rate": 1.3701289299883348e-09, + "loss": 0.0019, + "step": 64429 + }, + { + "epoch": 19.9, + "learning_rate": 1.3618628985911931e-09, + "loss": 0.0012, + "step": 64430 + }, + { + "epoch": 19.9, + "learning_rate": 1.3536218756127207e-09, + "loss": 0.0014, + "step": 64431 + }, + { + "epoch": 19.9, + "learning_rate": 1.3454058610717913e-09, + "loss": 0.0014, + "step": 64432 + }, + { + "epoch": 19.9, + "learning_rate": 1.3372148549894991e-09, + "loss": 0.0013, + "step": 64433 + }, + { + "epoch": 19.9, + "learning_rate": 1.3290488573869387e-09, + "loss": 0.0013, + "step": 64434 + }, + { + "epoch": 19.9, + "learning_rate": 1.3209078682840936e-09, + "loss": 0.0013, + "step": 64435 + }, + { + "epoch": 19.9, + "learning_rate": 1.3127918877009482e-09, + "loss": 0.0014, + "step": 64436 + }, + { + "epoch": 19.9, + "learning_rate": 1.3047009156574863e-09, + "loss": 0.0016, + "step": 64437 + }, + { + "epoch": 19.9, + "learning_rate": 1.2966349521759125e-09, + "loss": 0.001, + "step": 64438 + }, + { + "epoch": 19.9, + "learning_rate": 1.2885939972739903e-09, + "loss": 0.0015, + "step": 64439 + }, + { + "epoch": 19.9, + "learning_rate": 1.280578050973924e-09, + "loss": 0.0016, + "step": 64440 + }, + { + "epoch": 19.9, + "learning_rate": 1.2725871132945878e-09, + "loss": 0.0019, + "step": 64441 + }, + { + "epoch": 19.9, + "learning_rate": 1.2646211842559652e-09, + "loss": 0.0017, + "step": 64442 + }, + { + "epoch": 19.9, + "learning_rate": 1.2566802638780406e-09, + "loss": 0.0019, + "step": 64443 + }, + { + "epoch": 19.9, + "learning_rate": 1.2487643521807979e-09, + "loss": 0.0014, + "step": 64444 + }, + { + "epoch": 19.9, + "learning_rate": 1.2408734491842212e-09, + "loss": 0.0012, + "step": 64445 + }, + { + "epoch": 19.9, + "learning_rate": 1.233007554907184e-09, + "loss": 0.001, + "step": 64446 + }, + { + "epoch": 19.9, + "learning_rate": 1.225166669370781e-09, + "loss": 0.0012, + "step": 64447 + }, + { + "epoch": 19.9, + "learning_rate": 1.2173507925938855e-09, + "loss": 0.0016, + "step": 64448 + }, + { + "epoch": 19.9, + "learning_rate": 1.2095599245964817e-09, + "loss": 0.0013, + "step": 64449 + }, + { + "epoch": 19.9, + "learning_rate": 1.2017940653974436e-09, + "loss": 0.0015, + "step": 64450 + }, + { + "epoch": 19.9, + "learning_rate": 1.1940532150156447e-09, + "loss": 0.0016, + "step": 64451 + }, + { + "epoch": 19.9, + "learning_rate": 1.1863373734721795e-09, + "loss": 0.0015, + "step": 64452 + }, + { + "epoch": 19.9, + "learning_rate": 1.1786465407848113e-09, + "loss": 0.0021, + "step": 64453 + }, + { + "epoch": 19.9, + "learning_rate": 1.170980716972414e-09, + "loss": 0.0011, + "step": 64454 + }, + { + "epoch": 19.9, + "learning_rate": 1.1633399020560821e-09, + "loss": 0.0017, + "step": 64455 + }, + { + "epoch": 19.91, + "learning_rate": 1.155724096054689e-09, + "loss": 0.001, + "step": 64456 + }, + { + "epoch": 19.91, + "learning_rate": 1.1481332989848882e-09, + "loss": 0.0014, + "step": 64457 + }, + { + "epoch": 19.91, + "learning_rate": 1.1405675108677739e-09, + "loss": 0.0008, + "step": 64458 + }, + { + "epoch": 19.91, + "learning_rate": 1.1330267317222199e-09, + "loss": 0.001, + "step": 64459 + }, + { + "epoch": 19.91, + "learning_rate": 1.1255109615671e-09, + "loss": 0.0014, + "step": 64460 + }, + { + "epoch": 19.91, + "learning_rate": 1.1180202004201779e-09, + "loss": 0.0016, + "step": 64461 + }, + { + "epoch": 19.91, + "learning_rate": 1.1105544483003273e-09, + "loss": 0.0019, + "step": 64462 + }, + { + "epoch": 19.91, + "learning_rate": 1.1031137052264219e-09, + "loss": 0.0019, + "step": 64463 + }, + { + "epoch": 19.91, + "learning_rate": 1.0956979712184456e-09, + "loss": 0.0013, + "step": 64464 + }, + { + "epoch": 19.91, + "learning_rate": 1.0883072462930522e-09, + "loss": 0.0019, + "step": 64465 + }, + { + "epoch": 19.91, + "learning_rate": 1.0809415304702253e-09, + "loss": 0.0021, + "step": 64466 + }, + { + "epoch": 19.91, + "learning_rate": 1.0736008237666184e-09, + "loss": 0.0011, + "step": 64467 + }, + { + "epoch": 19.91, + "learning_rate": 1.0662851262022156e-09, + "loss": 0.0019, + "step": 64468 + }, + { + "epoch": 19.91, + "learning_rate": 1.0589944377947803e-09, + "loss": 0.0014, + "step": 64469 + }, + { + "epoch": 19.91, + "learning_rate": 1.051728758562076e-09, + "loss": 0.0022, + "step": 64470 + }, + { + "epoch": 19.91, + "learning_rate": 1.044488088524087e-09, + "loss": 0.0015, + "step": 64471 + }, + { + "epoch": 19.91, + "learning_rate": 1.0372724276963563e-09, + "loss": 0.0014, + "step": 64472 + }, + { + "epoch": 19.91, + "learning_rate": 1.0300817760977578e-09, + "loss": 0.0018, + "step": 64473 + }, + { + "epoch": 19.91, + "learning_rate": 1.022916133747165e-09, + "loss": 0.0016, + "step": 64474 + }, + { + "epoch": 19.91, + "learning_rate": 1.0157755006612312e-09, + "loss": 0.0013, + "step": 64475 + }, + { + "epoch": 19.91, + "learning_rate": 1.008659876859941e-09, + "loss": 0.0015, + "step": 64476 + }, + { + "epoch": 19.91, + "learning_rate": 1.001569262358837e-09, + "loss": 0.0013, + "step": 64477 + }, + { + "epoch": 19.91, + "learning_rate": 9.94503657176793e-10, + "loss": 0.0017, + "step": 64478 + }, + { + "epoch": 19.91, + "learning_rate": 9.874630613304625e-10, + "loss": 0.0023, + "step": 64479 + }, + { + "epoch": 19.91, + "learning_rate": 9.804474748387193e-10, + "loss": 0.0014, + "step": 64480 + }, + { + "epoch": 19.91, + "learning_rate": 9.73456897719327e-10, + "loss": 0.0014, + "step": 64481 + }, + { + "epoch": 19.91, + "learning_rate": 9.664913299878286e-10, + "loss": 0.0013, + "step": 64482 + }, + { + "epoch": 19.91, + "learning_rate": 9.59550771663098e-10, + "loss": 0.0017, + "step": 64483 + }, + { + "epoch": 19.91, + "learning_rate": 9.526352227628988e-10, + "loss": 0.0017, + "step": 64484 + }, + { + "epoch": 19.91, + "learning_rate": 9.457446833027738e-10, + "loss": 0.0012, + "step": 64485 + }, + { + "epoch": 19.91, + "learning_rate": 9.388791533015972e-10, + "loss": 0.0024, + "step": 64486 + }, + { + "epoch": 19.91, + "learning_rate": 9.320386327771325e-10, + "loss": 0.0011, + "step": 64487 + }, + { + "epoch": 19.92, + "learning_rate": 9.252231217438123e-10, + "loss": 0.0019, + "step": 64488 + }, + { + "epoch": 19.92, + "learning_rate": 9.184326202205107e-10, + "loss": 0.0013, + "step": 64489 + }, + { + "epoch": 19.92, + "learning_rate": 9.116671282249911e-10, + "loss": 0.0014, + "step": 64490 + }, + { + "epoch": 19.92, + "learning_rate": 9.049266457716866e-10, + "loss": 0.0019, + "step": 64491 + }, + { + "epoch": 19.92, + "learning_rate": 8.982111728794707e-10, + "loss": 0.0013, + "step": 64492 + }, + { + "epoch": 19.92, + "learning_rate": 8.915207095649969e-10, + "loss": 0.0017, + "step": 64493 + }, + { + "epoch": 19.92, + "learning_rate": 8.848552558438084e-10, + "loss": 0.0011, + "step": 64494 + }, + { + "epoch": 19.92, + "learning_rate": 8.782148117336686e-10, + "loss": 0.0011, + "step": 64495 + }, + { + "epoch": 19.92, + "learning_rate": 8.715993772512311e-10, + "loss": 0.0021, + "step": 64496 + }, + { + "epoch": 19.92, + "learning_rate": 8.650089524120387e-10, + "loss": 0.0014, + "step": 64497 + }, + { + "epoch": 19.92, + "learning_rate": 8.584435372327448e-10, + "loss": 0.0014, + "step": 64498 + }, + { + "epoch": 19.92, + "learning_rate": 8.519031317311133e-10, + "loss": 0.0013, + "step": 64499 + }, + { + "epoch": 19.92, + "learning_rate": 8.453877359226869e-10, + "loss": 0.0014, + "step": 64500 + }, + { + "epoch": 19.92, + "learning_rate": 8.38897349823009e-10, + "loss": 0.0013, + "step": 64501 + }, + { + "epoch": 19.92, + "learning_rate": 8.324319734498432e-10, + "loss": 0.0015, + "step": 64502 + }, + { + "epoch": 19.92, + "learning_rate": 8.259916068176221e-10, + "loss": 0.0015, + "step": 64503 + }, + { + "epoch": 19.92, + "learning_rate": 8.195762499441096e-10, + "loss": 0.0014, + "step": 64504 + }, + { + "epoch": 19.92, + "learning_rate": 8.131859028437384e-10, + "loss": 0.0014, + "step": 64505 + }, + { + "epoch": 19.92, + "learning_rate": 8.068205655331618e-10, + "loss": 0.0013, + "step": 64506 + }, + { + "epoch": 19.92, + "learning_rate": 8.004802380290333e-10, + "loss": 0.0014, + "step": 64507 + }, + { + "epoch": 19.92, + "learning_rate": 7.941649203468959e-10, + "loss": 0.0011, + "step": 64508 + }, + { + "epoch": 19.92, + "learning_rate": 7.87874612502293e-10, + "loss": 0.0015, + "step": 64509 + }, + { + "epoch": 19.92, + "learning_rate": 7.816093145107672e-10, + "loss": 0.0012, + "step": 64510 + }, + { + "epoch": 19.92, + "learning_rate": 7.753690263878621e-10, + "loss": 0.0016, + "step": 64511 + }, + { + "epoch": 19.92, + "learning_rate": 7.691537481502309e-10, + "loss": 0.001, + "step": 64512 + }, + { + "epoch": 19.92, + "learning_rate": 7.629634798123064e-10, + "loss": 0.0015, + "step": 64513 + }, + { + "epoch": 19.92, + "learning_rate": 7.567982213896318e-10, + "loss": 0.0012, + "step": 64514 + }, + { + "epoch": 19.92, + "learning_rate": 7.506579728977503e-10, + "loss": 0.0016, + "step": 64515 + }, + { + "epoch": 19.92, + "learning_rate": 7.445427343533151e-10, + "loss": 0.0011, + "step": 64516 + }, + { + "epoch": 19.92, + "learning_rate": 7.38452505769649e-10, + "loss": 0.0015, + "step": 64517 + }, + { + "epoch": 19.92, + "learning_rate": 7.323872871634053e-10, + "loss": 0.001, + "step": 64518 + }, + { + "epoch": 19.92, + "learning_rate": 7.263470785479066e-10, + "loss": 0.0017, + "step": 64519 + }, + { + "epoch": 19.92, + "learning_rate": 7.203318799409165e-10, + "loss": 0.002, + "step": 64520 + }, + { + "epoch": 19.93, + "learning_rate": 7.143416913557577e-10, + "loss": 0.0015, + "step": 64521 + }, + { + "epoch": 19.93, + "learning_rate": 7.083765128079734e-10, + "loss": 0.0015, + "step": 64522 + }, + { + "epoch": 19.93, + "learning_rate": 7.024363443119964e-10, + "loss": 0.0014, + "step": 64523 + }, + { + "epoch": 19.93, + "learning_rate": 6.965211858833698e-10, + "loss": 0.0013, + "step": 64524 + }, + { + "epoch": 19.93, + "learning_rate": 6.906310375365266e-10, + "loss": 0.0014, + "step": 64525 + }, + { + "epoch": 19.93, + "learning_rate": 6.847658992858997e-10, + "loss": 0.0016, + "step": 64526 + }, + { + "epoch": 19.93, + "learning_rate": 6.789257711459219e-10, + "loss": 0.0015, + "step": 64527 + }, + { + "epoch": 19.93, + "learning_rate": 6.731106531321363e-10, + "loss": 0.0017, + "step": 64528 + }, + { + "epoch": 19.93, + "learning_rate": 6.67320545258976e-10, + "loss": 0.0019, + "step": 64529 + }, + { + "epoch": 19.93, + "learning_rate": 6.615554475408737e-10, + "loss": 0.0014, + "step": 64530 + }, + { + "epoch": 19.93, + "learning_rate": 6.558153599911521e-10, + "loss": 0.0011, + "step": 64531 + }, + { + "epoch": 19.93, + "learning_rate": 6.501002826253544e-10, + "loss": 0.0015, + "step": 64532 + }, + { + "epoch": 19.93, + "learning_rate": 6.444102154568032e-10, + "loss": 0.0014, + "step": 64533 + }, + { + "epoch": 19.93, + "learning_rate": 6.387451585010418e-10, + "loss": 0.0011, + "step": 64534 + }, + { + "epoch": 19.93, + "learning_rate": 6.331051117713926e-10, + "loss": 0.0012, + "step": 64535 + }, + { + "epoch": 19.93, + "learning_rate": 6.274900752822888e-10, + "loss": 0.0017, + "step": 64536 + }, + { + "epoch": 19.93, + "learning_rate": 6.219000490481631e-10, + "loss": 0.0021, + "step": 64537 + }, + { + "epoch": 19.93, + "learning_rate": 6.163350330812279e-10, + "loss": 0.0017, + "step": 64538 + }, + { + "epoch": 19.93, + "learning_rate": 6.107950273970265e-10, + "loss": 0.0012, + "step": 64539 + }, + { + "epoch": 19.93, + "learning_rate": 6.052800320099916e-10, + "loss": 0.002, + "step": 64540 + }, + { + "epoch": 19.93, + "learning_rate": 5.997900469312257e-10, + "loss": 0.0015, + "step": 64541 + }, + { + "epoch": 19.93, + "learning_rate": 5.943250721773819e-10, + "loss": 0.0015, + "step": 64542 + }, + { + "epoch": 19.93, + "learning_rate": 5.888851077606727e-10, + "loss": 0.0016, + "step": 64543 + }, + { + "epoch": 19.93, + "learning_rate": 5.83470153694421e-10, + "loss": 0.0011, + "step": 64544 + }, + { + "epoch": 19.93, + "learning_rate": 5.780802099930594e-10, + "loss": 0.0014, + "step": 64545 + }, + { + "epoch": 19.93, + "learning_rate": 5.727152766699107e-10, + "loss": 0.0009, + "step": 64546 + }, + { + "epoch": 19.93, + "learning_rate": 5.673753537382975e-10, + "loss": 0.0008, + "step": 64547 + }, + { + "epoch": 19.93, + "learning_rate": 5.620604412115427e-10, + "loss": 0.0016, + "step": 64548 + }, + { + "epoch": 19.93, + "learning_rate": 5.567705391018585e-10, + "loss": 0.0017, + "step": 64549 + }, + { + "epoch": 19.93, + "learning_rate": 5.51505647423678e-10, + "loss": 0.0015, + "step": 64550 + }, + { + "epoch": 19.93, + "learning_rate": 5.462657661914339e-10, + "loss": 0.0021, + "step": 64551 + }, + { + "epoch": 19.93, + "learning_rate": 5.410508954151184e-10, + "loss": 0.0013, + "step": 64552 + }, + { + "epoch": 19.94, + "learning_rate": 5.358610351102745e-10, + "loss": 0.0012, + "step": 64553 + }, + { + "epoch": 19.94, + "learning_rate": 5.306961852891146e-10, + "loss": 0.0017, + "step": 64554 + }, + { + "epoch": 19.94, + "learning_rate": 5.255563459638513e-10, + "loss": 0.0014, + "step": 64555 + }, + { + "epoch": 19.94, + "learning_rate": 5.204415171478072e-10, + "loss": 0.0025, + "step": 64556 + }, + { + "epoch": 19.94, + "learning_rate": 5.15351698854305e-10, + "loss": 0.0016, + "step": 64557 + }, + { + "epoch": 19.94, + "learning_rate": 5.102868910955572e-10, + "loss": 0.0015, + "step": 64558 + }, + { + "epoch": 19.94, + "learning_rate": 5.052470938848864e-10, + "loss": 0.0012, + "step": 64559 + }, + { + "epoch": 19.94, + "learning_rate": 5.00232307234505e-10, + "loss": 0.0019, + "step": 64560 + }, + { + "epoch": 19.94, + "learning_rate": 4.952425311566256e-10, + "loss": 0.0014, + "step": 64561 + }, + { + "epoch": 19.94, + "learning_rate": 4.902777656634605e-10, + "loss": 0.0013, + "step": 64562 + }, + { + "epoch": 19.94, + "learning_rate": 4.853380107683325e-10, + "loss": 0.0014, + "step": 64563 + }, + { + "epoch": 19.94, + "learning_rate": 4.804232664823438e-10, + "loss": 0.0014, + "step": 64564 + }, + { + "epoch": 19.94, + "learning_rate": 4.755335328199273e-10, + "loss": 0.0012, + "step": 64565 + }, + { + "epoch": 19.94, + "learning_rate": 4.70668809791075e-10, + "loss": 0.0017, + "step": 64566 + }, + { + "epoch": 19.94, + "learning_rate": 4.658290974091095e-10, + "loss": 0.0016, + "step": 64567 + }, + { + "epoch": 19.94, + "learning_rate": 4.610143956862434e-10, + "loss": 0.0016, + "step": 64568 + }, + { + "epoch": 19.94, + "learning_rate": 4.562247046335788e-10, + "loss": 0.0013, + "step": 64569 + }, + { + "epoch": 19.94, + "learning_rate": 4.5146002426443845e-10, + "loss": 0.0016, + "step": 64570 + }, + { + "epoch": 19.94, + "learning_rate": 4.4672035458881437e-10, + "loss": 0.0016, + "step": 64571 + }, + { + "epoch": 19.94, + "learning_rate": 4.420056956211394e-10, + "loss": 0.0014, + "step": 64572 + }, + { + "epoch": 19.94, + "learning_rate": 4.3731604737140554e-10, + "loss": 0.0014, + "step": 64573 + }, + { + "epoch": 19.94, + "learning_rate": 4.3265140985071507e-10, + "loss": 0.0016, + "step": 64574 + }, + { + "epoch": 19.94, + "learning_rate": 4.280117830735009e-10, + "loss": 0.0011, + "step": 64575 + }, + { + "epoch": 19.94, + "learning_rate": 4.2339716704864477e-10, + "loss": 0.0016, + "step": 64576 + }, + { + "epoch": 19.94, + "learning_rate": 4.188075617883591e-10, + "loss": 0.0013, + "step": 64577 + }, + { + "epoch": 19.94, + "learning_rate": 4.1424296730485645e-10, + "loss": 0.0015, + "step": 64578 + }, + { + "epoch": 19.94, + "learning_rate": 4.09703383609239e-10, + "loss": 0.0017, + "step": 64579 + }, + { + "epoch": 19.94, + "learning_rate": 4.0518881071260896e-10, + "loss": 0.0011, + "step": 64580 + }, + { + "epoch": 19.94, + "learning_rate": 4.0069924862606855e-10, + "loss": 0.0017, + "step": 64581 + }, + { + "epoch": 19.94, + "learning_rate": 3.962346973618303e-10, + "loss": 0.0014, + "step": 64582 + }, + { + "epoch": 19.94, + "learning_rate": 3.917951569298861e-10, + "loss": 0.0011, + "step": 64583 + }, + { + "epoch": 19.94, + "learning_rate": 3.873806273424485e-10, + "loss": 0.0018, + "step": 64584 + }, + { + "epoch": 19.94, + "learning_rate": 3.829911086095095e-10, + "loss": 0.0014, + "step": 64585 + }, + { + "epoch": 19.95, + "learning_rate": 3.786266007432815e-10, + "loss": 0.0018, + "step": 64586 + }, + { + "epoch": 19.95, + "learning_rate": 3.7428710375375654e-10, + "loss": 0.0019, + "step": 64587 + }, + { + "epoch": 19.95, + "learning_rate": 3.6997261765092664e-10, + "loss": 0.0011, + "step": 64588 + }, + { + "epoch": 19.95, + "learning_rate": 3.656831424470042e-10, + "loss": 0.001, + "step": 64589 + }, + { + "epoch": 19.95, + "learning_rate": 3.614186781530915e-10, + "loss": 0.0014, + "step": 64590 + }, + { + "epoch": 19.95, + "learning_rate": 3.571792247780703e-10, + "loss": 0.0015, + "step": 64591 + }, + { + "epoch": 19.95, + "learning_rate": 3.529647823341531e-10, + "loss": 0.0021, + "step": 64592 + }, + { + "epoch": 19.95, + "learning_rate": 3.4877535083133184e-10, + "loss": 0.0021, + "step": 64593 + }, + { + "epoch": 19.95, + "learning_rate": 3.446109302807088e-10, + "loss": 0.0014, + "step": 64594 + }, + { + "epoch": 19.95, + "learning_rate": 3.404715206911657e-10, + "loss": 0.0021, + "step": 64595 + }, + { + "epoch": 19.95, + "learning_rate": 3.363571220738049e-10, + "loss": 0.0008, + "step": 64596 + }, + { + "epoch": 19.95, + "learning_rate": 3.3226773443861824e-10, + "loss": 0.0013, + "step": 64597 + }, + { + "epoch": 19.95, + "learning_rate": 3.282033577978183e-10, + "loss": 0.0019, + "step": 64598 + }, + { + "epoch": 19.95, + "learning_rate": 3.241639921580664e-10, + "loss": 0.0013, + "step": 64599 + }, + { + "epoch": 19.95, + "learning_rate": 3.201496375326851e-10, + "loss": 0.0015, + "step": 64600 + }, + { + "epoch": 19.95, + "learning_rate": 3.161602939305564e-10, + "loss": 0.0016, + "step": 64601 + }, + { + "epoch": 19.95, + "learning_rate": 3.1219596136056183e-10, + "loss": 0.0014, + "step": 64602 + }, + { + "epoch": 19.95, + "learning_rate": 3.0825663983491404e-10, + "loss": 0.0012, + "step": 64603 + }, + { + "epoch": 19.95, + "learning_rate": 3.043423293613845e-10, + "loss": 0.0011, + "step": 64604 + }, + { + "epoch": 19.95, + "learning_rate": 3.004530299499653e-10, + "loss": 0.0012, + "step": 64605 + }, + { + "epoch": 19.95, + "learning_rate": 2.9658874161175856e-10, + "loss": 0.0012, + "step": 64606 + }, + { + "epoch": 19.95, + "learning_rate": 2.927494643556461e-10, + "loss": 0.0015, + "step": 64607 + }, + { + "epoch": 19.95, + "learning_rate": 2.8893519819050974e-10, + "loss": 0.0013, + "step": 64608 + }, + { + "epoch": 19.95, + "learning_rate": 2.851459431274517e-10, + "loss": 0.0019, + "step": 64609 + }, + { + "epoch": 19.95, + "learning_rate": 2.813816991742435e-10, + "loss": 0.0014, + "step": 64610 + }, + { + "epoch": 19.95, + "learning_rate": 2.7764246634198743e-10, + "loss": 0.0017, + "step": 64611 + }, + { + "epoch": 19.95, + "learning_rate": 2.73928244638455e-10, + "loss": 0.0016, + "step": 64612 + }, + { + "epoch": 19.95, + "learning_rate": 2.7023903407474847e-10, + "loss": 0.0014, + "step": 64613 + }, + { + "epoch": 19.95, + "learning_rate": 2.665748346575292e-10, + "loss": 0.0016, + "step": 64614 + }, + { + "epoch": 19.95, + "learning_rate": 2.6293564639789937e-10, + "loss": 0.0008, + "step": 64615 + }, + { + "epoch": 19.95, + "learning_rate": 2.5932146930474076e-10, + "loss": 0.0013, + "step": 64616 + }, + { + "epoch": 19.95, + "learning_rate": 2.5573230338693524e-10, + "loss": 0.001, + "step": 64617 + }, + { + "epoch": 19.96, + "learning_rate": 2.521681486533645e-10, + "loss": 0.0012, + "step": 64618 + }, + { + "epoch": 19.96, + "learning_rate": 2.486290051129103e-10, + "loss": 0.0015, + "step": 64619 + }, + { + "epoch": 19.96, + "learning_rate": 2.451148727744546e-10, + "loss": 0.0014, + "step": 64620 + }, + { + "epoch": 19.96, + "learning_rate": 2.41625751646879e-10, + "loss": 0.0013, + "step": 64621 + }, + { + "epoch": 19.96, + "learning_rate": 2.381616417390653e-10, + "loss": 0.002, + "step": 64622 + }, + { + "epoch": 19.96, + "learning_rate": 2.3472254305878516e-10, + "loss": 0.0014, + "step": 64623 + }, + { + "epoch": 19.96, + "learning_rate": 2.3130845561603055e-10, + "loss": 0.0011, + "step": 64624 + }, + { + "epoch": 19.96, + "learning_rate": 2.27919379418573e-10, + "loss": 0.0015, + "step": 64625 + }, + { + "epoch": 19.96, + "learning_rate": 2.245553144741841e-10, + "loss": 0.0016, + "step": 64626 + }, + { + "epoch": 19.96, + "learning_rate": 2.2121626079285585e-10, + "loss": 0.0019, + "step": 64627 + }, + { + "epoch": 19.96, + "learning_rate": 2.1790221838124958e-10, + "loss": 0.0012, + "step": 64628 + }, + { + "epoch": 19.96, + "learning_rate": 2.1461318724935732e-10, + "loss": 0.0013, + "step": 64629 + }, + { + "epoch": 19.96, + "learning_rate": 2.1134916740384037e-10, + "loss": 0.0012, + "step": 64630 + }, + { + "epoch": 19.96, + "learning_rate": 2.0811015885469077e-10, + "loss": 0.0013, + "step": 64631 + }, + { + "epoch": 19.96, + "learning_rate": 2.048961616074596e-10, + "loss": 0.0022, + "step": 64632 + }, + { + "epoch": 19.96, + "learning_rate": 2.0170717567213894e-10, + "loss": 0.0017, + "step": 64633 + }, + { + "epoch": 19.96, + "learning_rate": 1.9854320105650026e-10, + "loss": 0.0016, + "step": 64634 + }, + { + "epoch": 19.96, + "learning_rate": 1.9540423776831518e-10, + "loss": 0.0019, + "step": 64635 + }, + { + "epoch": 19.96, + "learning_rate": 1.9229028581535526e-10, + "loss": 0.0016, + "step": 64636 + }, + { + "epoch": 19.96, + "learning_rate": 1.892013452042818e-10, + "loss": 0.0016, + "step": 64637 + }, + { + "epoch": 19.96, + "learning_rate": 1.8613741594508684e-10, + "loss": 0.0013, + "step": 64638 + }, + { + "epoch": 19.96, + "learning_rate": 1.8309849804332148e-10, + "loss": 0.0012, + "step": 64639 + }, + { + "epoch": 19.96, + "learning_rate": 1.800845915078675e-10, + "loss": 0.0017, + "step": 64640 + }, + { + "epoch": 19.96, + "learning_rate": 1.7709569634649648e-10, + "loss": 0.0013, + "step": 64641 + }, + { + "epoch": 19.96, + "learning_rate": 1.7413181256475954e-10, + "loss": 0.0012, + "step": 64642 + }, + { + "epoch": 19.96, + "learning_rate": 1.7119294017264864e-10, + "loss": 0.0011, + "step": 64643 + }, + { + "epoch": 19.96, + "learning_rate": 1.6827907917571496e-10, + "loss": 0.0013, + "step": 64644 + }, + { + "epoch": 19.96, + "learning_rate": 1.6539022958173002e-10, + "loss": 0.0015, + "step": 64645 + }, + { + "epoch": 19.96, + "learning_rate": 1.6252639139735515e-10, + "loss": 0.0014, + "step": 64646 + }, + { + "epoch": 19.96, + "learning_rate": 1.5968756463147217e-10, + "loss": 0.0012, + "step": 64647 + }, + { + "epoch": 19.96, + "learning_rate": 1.5687374928963218e-10, + "loss": 0.0018, + "step": 64648 + }, + { + "epoch": 19.96, + "learning_rate": 1.540849453784965e-10, + "loss": 0.0021, + "step": 64649 + }, + { + "epoch": 19.97, + "learning_rate": 1.5132115290694693e-10, + "loss": 0.0015, + "step": 64650 + }, + { + "epoch": 19.97, + "learning_rate": 1.4858237188053459e-10, + "loss": 0.002, + "step": 64651 + }, + { + "epoch": 19.97, + "learning_rate": 1.4586860230592082e-10, + "loss": 0.0016, + "step": 64652 + }, + { + "epoch": 19.97, + "learning_rate": 1.4317984419087715e-10, + "loss": 0.0015, + "step": 64653 + }, + { + "epoch": 19.97, + "learning_rate": 1.4051609754095475e-10, + "loss": 0.0013, + "step": 64654 + }, + { + "epoch": 19.97, + "learning_rate": 1.3787736236392512e-10, + "loss": 0.0015, + "step": 64655 + }, + { + "epoch": 19.97, + "learning_rate": 1.3526363866644965e-10, + "loss": 0.0016, + "step": 64656 + }, + { + "epoch": 19.97, + "learning_rate": 1.3267492645407943e-10, + "loss": 0.0017, + "step": 64657 + }, + { + "epoch": 19.97, + "learning_rate": 1.301112257334758e-10, + "loss": 0.0013, + "step": 64658 + }, + { + "epoch": 19.97, + "learning_rate": 1.2757253651130008e-10, + "loss": 0.0018, + "step": 64659 + }, + { + "epoch": 19.97, + "learning_rate": 1.2505885879421364e-10, + "loss": 0.0014, + "step": 64660 + }, + { + "epoch": 19.97, + "learning_rate": 1.2257019258887782e-10, + "loss": 0.0015, + "step": 64661 + }, + { + "epoch": 19.97, + "learning_rate": 1.2010653789973347e-10, + "loss": 0.0014, + "step": 64662 + }, + { + "epoch": 19.97, + "learning_rate": 1.176678947345522e-10, + "loss": 0.0018, + "step": 64663 + }, + { + "epoch": 19.97, + "learning_rate": 1.152542630988851e-10, + "loss": 0.0019, + "step": 64664 + }, + { + "epoch": 19.97, + "learning_rate": 1.1286564299828328e-10, + "loss": 0.0014, + "step": 64665 + }, + { + "epoch": 19.97, + "learning_rate": 1.1050203444051832e-10, + "loss": 0.001, + "step": 64666 + }, + { + "epoch": 19.97, + "learning_rate": 1.0816343742892088e-10, + "loss": 0.0017, + "step": 64667 + }, + { + "epoch": 19.97, + "learning_rate": 1.0584985197126252e-10, + "loss": 0.0016, + "step": 64668 + }, + { + "epoch": 19.97, + "learning_rate": 1.0356127807309435e-10, + "loss": 0.0016, + "step": 64669 + }, + { + "epoch": 19.97, + "learning_rate": 1.0129771573996749e-10, + "loss": 0.0019, + "step": 64670 + }, + { + "epoch": 19.97, + "learning_rate": 9.905916497632284e-11, + "loss": 0.0015, + "step": 64671 + }, + { + "epoch": 19.97, + "learning_rate": 9.684562578993195e-11, + "loss": 0.001, + "step": 64672 + }, + { + "epoch": 19.97, + "learning_rate": 9.46570981841255e-11, + "loss": 0.0017, + "step": 64673 + }, + { + "epoch": 19.97, + "learning_rate": 9.249358216556481e-11, + "loss": 0.0014, + "step": 64674 + }, + { + "epoch": 19.97, + "learning_rate": 9.035507773980101e-11, + "loss": 0.0014, + "step": 64675 + }, + { + "epoch": 19.97, + "learning_rate": 8.824158491238521e-11, + "loss": 0.0012, + "step": 64676 + }, + { + "epoch": 19.97, + "learning_rate": 8.615310368775831e-11, + "loss": 0.0013, + "step": 64677 + }, + { + "epoch": 19.97, + "learning_rate": 8.408963407147142e-11, + "loss": 0.0011, + "step": 64678 + }, + { + "epoch": 19.97, + "learning_rate": 8.205117606907564e-11, + "loss": 0.0015, + "step": 64679 + }, + { + "epoch": 19.97, + "learning_rate": 8.00377296850119e-11, + "loss": 0.0021, + "step": 64680 + }, + { + "epoch": 19.97, + "learning_rate": 7.804929492483126e-11, + "loss": 0.0017, + "step": 64681 + }, + { + "epoch": 19.97, + "learning_rate": 7.608587179297466e-11, + "loss": 0.0011, + "step": 64682 + }, + { + "epoch": 19.98, + "learning_rate": 7.41474602949932e-11, + "loss": 0.0015, + "step": 64683 + }, + { + "epoch": 19.98, + "learning_rate": 7.223406043532777e-11, + "loss": 0.0012, + "step": 64684 + }, + { + "epoch": 19.98, + "learning_rate": 7.034567221952949e-11, + "loss": 0.0015, + "step": 64685 + }, + { + "epoch": 19.98, + "learning_rate": 6.8482295650929e-11, + "loss": 0.0013, + "step": 64686 + }, + { + "epoch": 19.98, + "learning_rate": 6.664393073507747e-11, + "loss": 0.0012, + "step": 64687 + }, + { + "epoch": 19.98, + "learning_rate": 6.483057747641575e-11, + "loss": 0.0012, + "step": 64688 + }, + { + "epoch": 19.98, + "learning_rate": 6.304223587938474e-11, + "loss": 0.0019, + "step": 64689 + }, + { + "epoch": 19.98, + "learning_rate": 6.127890594842534e-11, + "loss": 0.0013, + "step": 64690 + }, + { + "epoch": 19.98, + "learning_rate": 5.954058768908866e-11, + "loss": 0.0015, + "step": 64691 + }, + { + "epoch": 19.98, + "learning_rate": 5.7827281103595146e-11, + "loss": 0.002, + "step": 64692 + }, + { + "epoch": 19.98, + "learning_rate": 5.6138986197495913e-11, + "loss": 0.0022, + "step": 64693 + }, + { + "epoch": 19.98, + "learning_rate": 5.447570297523186e-11, + "loss": 0.0016, + "step": 64694 + }, + { + "epoch": 19.98, + "learning_rate": 5.283743144124387e-11, + "loss": 0.0011, + "step": 64695 + }, + { + "epoch": 19.98, + "learning_rate": 5.122417159775239e-11, + "loss": 0.0015, + "step": 64696 + }, + { + "epoch": 19.98, + "learning_rate": 4.9635923450308545e-11, + "loss": 0.0011, + "step": 64697 + }, + { + "epoch": 19.98, + "learning_rate": 4.807268700335321e-11, + "loss": 0.0018, + "step": 64698 + }, + { + "epoch": 19.98, + "learning_rate": 4.653446225910685e-11, + "loss": 0.0013, + "step": 64699 + }, + { + "epoch": 19.98, + "learning_rate": 4.5021249223120565e-11, + "loss": 0.0015, + "step": 64700 + }, + { + "epoch": 19.98, + "learning_rate": 4.3533047897614814e-11, + "loss": 0.0015, + "step": 64701 + }, + { + "epoch": 19.98, + "learning_rate": 4.2069858287030476e-11, + "loss": 0.0017, + "step": 64702 + }, + { + "epoch": 19.98, + "learning_rate": 4.063168039580845e-11, + "loss": 0.0019, + "step": 64703 + }, + { + "epoch": 19.98, + "learning_rate": 3.9218514227279405e-11, + "loss": 0.0016, + "step": 64704 + }, + { + "epoch": 19.98, + "learning_rate": 3.7830359783663785e-11, + "loss": 0.0019, + "step": 64705 + }, + { + "epoch": 19.98, + "learning_rate": 3.646721706940248e-11, + "loss": 0.0017, + "step": 64706 + }, + { + "epoch": 19.98, + "learning_rate": 3.512908608782617e-11, + "loss": 0.002, + "step": 64707 + }, + { + "epoch": 19.98, + "learning_rate": 3.3815966842265515e-11, + "loss": 0.0013, + "step": 64708 + }, + { + "epoch": 19.98, + "learning_rate": 3.252785933605118e-11, + "loss": 0.0017, + "step": 64709 + }, + { + "epoch": 19.98, + "learning_rate": 3.126476357251384e-11, + "loss": 0.0016, + "step": 64710 + }, + { + "epoch": 19.98, + "learning_rate": 3.002667955498417e-11, + "loss": 0.0015, + "step": 64711 + }, + { + "epoch": 19.98, + "learning_rate": 2.881360728568261e-11, + "loss": 0.0012, + "step": 64712 + }, + { + "epoch": 19.98, + "learning_rate": 2.762554676905005e-11, + "loss": 0.0013, + "step": 64713 + }, + { + "epoch": 19.98, + "learning_rate": 2.6462498006196713e-11, + "loss": 0.0011, + "step": 64714 + }, + { + "epoch": 19.99, + "learning_rate": 2.5324461001563494e-11, + "loss": 0.0013, + "step": 64715 + }, + { + "epoch": 19.99, + "learning_rate": 2.4211435757370838e-11, + "loss": 0.0016, + "step": 64716 + }, + { + "epoch": 19.99, + "learning_rate": 2.312342227583919e-11, + "loss": 0.0016, + "step": 64717 + }, + { + "epoch": 19.99, + "learning_rate": 2.2060420561409446e-11, + "loss": 0.0016, + "step": 64718 + }, + { + "epoch": 19.99, + "learning_rate": 2.1022430615191824e-11, + "loss": 0.0015, + "step": 64719 + }, + { + "epoch": 19.99, + "learning_rate": 2.0009452440516997e-11, + "loss": 0.0017, + "step": 64720 + }, + { + "epoch": 19.99, + "learning_rate": 1.902148603960541e-11, + "loss": 0.0015, + "step": 64721 + }, + { + "epoch": 19.99, + "learning_rate": 1.8058531414677505e-11, + "loss": 0.001, + "step": 64722 + }, + { + "epoch": 19.99, + "learning_rate": 1.7120588567953732e-11, + "loss": 0.0018, + "step": 64723 + }, + { + "epoch": 19.99, + "learning_rate": 1.6207657503874986e-11, + "loss": 0.0013, + "step": 64724 + }, + { + "epoch": 19.99, + "learning_rate": 1.531973822244126e-11, + "loss": 0.0013, + "step": 64725 + }, + { + "epoch": 19.99, + "learning_rate": 1.4456830725873006e-11, + "loss": 0.0017, + "step": 64726 + }, + { + "epoch": 19.99, + "learning_rate": 1.361893501750089e-11, + "loss": 0.0017, + "step": 64727 + }, + { + "epoch": 19.99, + "learning_rate": 1.2806051099545358e-11, + "loss": 0.0014, + "step": 64728 + }, + { + "epoch": 19.99, + "learning_rate": 1.2018178973116635e-11, + "loss": 0.0007, + "step": 64729 + }, + { + "epoch": 19.99, + "learning_rate": 1.125531863932494e-11, + "loss": 0.0016, + "step": 64730 + }, + { + "epoch": 19.99, + "learning_rate": 1.0517470102611171e-11, + "loss": 0.0013, + "step": 64731 + }, + { + "epoch": 19.99, + "learning_rate": 9.804633362975325e-12, + "loss": 0.0017, + "step": 64732 + }, + { + "epoch": 19.99, + "learning_rate": 9.116808422637847e-12, + "loss": 0.001, + "step": 64733 + }, + { + "epoch": 19.99, + "learning_rate": 8.453995283819182e-12, + "loss": 0.0019, + "step": 64734 + }, + { + "epoch": 19.99, + "learning_rate": 7.816193947629558e-12, + "loss": 0.0012, + "step": 64735 + }, + { + "epoch": 19.99, + "learning_rate": 7.2034044162894165e-12, + "loss": 0.0016, + "step": 64736 + }, + { + "epoch": 19.99, + "learning_rate": 6.61562668979876e-12, + "loss": 0.0012, + "step": 64737 + }, + { + "epoch": 19.99, + "learning_rate": 6.052860771488256e-12, + "loss": 0.0012, + "step": 64738 + }, + { + "epoch": 19.99, + "learning_rate": 5.5151066613579055e-12, + "loss": 0.0015, + "step": 64739 + }, + { + "epoch": 19.99, + "learning_rate": 5.002364361628154e-12, + "loss": 0.0019, + "step": 64740 + }, + { + "epoch": 19.99, + "learning_rate": 4.514633872299001e-12, + "loss": 0.0015, + "step": 64741 + }, + { + "epoch": 19.99, + "learning_rate": 4.051915196701117e-12, + "loss": 0.0017, + "step": 64742 + }, + { + "epoch": 19.99, + "learning_rate": 3.6142083348345014e-12, + "loss": 0.0014, + "step": 64743 + }, + { + "epoch": 19.99, + "learning_rate": 3.201513287809377e-12, + "loss": 0.0018, + "step": 64744 + }, + { + "epoch": 19.99, + "learning_rate": 2.8138300556257438e-12, + "loss": 0.0015, + "step": 64745 + }, + { + "epoch": 19.99, + "learning_rate": 2.4511586416142706e-12, + "loss": 0.0014, + "step": 64746 + }, + { + "epoch": 20.0, + "learning_rate": 2.1134990446647352e-12, + "loss": 0.0013, + "step": 64747 + }, + { + "epoch": 20.0, + "learning_rate": 1.80085126588736e-12, + "loss": 0.0017, + "step": 64748 + }, + { + "epoch": 20.0, + "learning_rate": 1.5132153075025914e-12, + "loss": 0.0025, + "step": 64749 + }, + { + "epoch": 20.0, + "learning_rate": 1.2505911684002059e-12, + "loss": 0.0014, + "step": 64750 + }, + { + "epoch": 20.0, + "learning_rate": 1.01297885080065e-12, + "loss": 0.0012, + "step": 64751 + }, + { + "epoch": 20.0, + "learning_rate": 8.003783535937004e-13, + "loss": 0.0016, + "step": 64752 + }, + { + "epoch": 20.0, + "learning_rate": 6.127896789998033e-13, + "loss": 0.0019, + "step": 64753 + }, + { + "epoch": 20.0, + "learning_rate": 4.502128270189587e-13, + "loss": 0.0017, + "step": 64754 + }, + { + "epoch": 20.0, + "learning_rate": 3.1264779654094356e-13, + "loss": 0.0017, + "step": 64755 + }, + { + "epoch": 20.0, + "learning_rate": 2.000945908964269e-13, + "loss": 0.0014, + "step": 64756 + }, + { + "epoch": 20.0, + "learning_rate": 1.1255320675473968e-13, + "loss": 0.0012, + "step": 64757 + }, + { + "epoch": 20.0, + "learning_rate": 5.002364744655097e-14, + "loss": 0.0011, + "step": 64758 + }, + { + "epoch": 20.0, + "learning_rate": 1.2505911861637742e-14, + "loss": 0.0016, + "step": 64759 + }, + { + "epoch": 20.0, + "learning_rate": 0.0, + "loss": 0.0013, + "step": 64760 + }, + { + "epoch": 20.0, + "step": 64760, + "total_flos": 3.806796394754841e+20, + "train_loss": 0.0423709743246787, + "train_runtime": 2291084.5213, + "train_samples_per_second": 14.473, + "train_steps_per_second": 0.028 + } + ], + "max_steps": 64760, + "num_train_epochs": 20, + "total_flos": 3.806796394754841e+20, + "trial_name": null, + "trial_params": null +}