|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.3157894736842106, |
|
"global_step": 450, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7121, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 0.0002, |
|
"loss": 0.645, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6852, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 0.0002, |
|
"loss": 0.689, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7223, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7359, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.0002, |
|
"loss": 0.677, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6888, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7475, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6675, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6665, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6803, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7004, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7052, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6975, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6186, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6533, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7183, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6477, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6753, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"eval_loss": 0.7119563221931458, |
|
"eval_runtime": 61.7384, |
|
"eval_samples_per_second": 0.454, |
|
"eval_steps_per_second": 0.227, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.0002, |
|
"loss": 0.638, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6424, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7058, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.0002, |
|
"loss": 0.65, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6469, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6803, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7178, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6187, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6321, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6292, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7176, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6792, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6233, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7009, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6672, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6915, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.0002, |
|
"loss": 0.657, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6408, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6499, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6177, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"eval_loss": 0.713217556476593, |
|
"eval_runtime": 61.6956, |
|
"eval_samples_per_second": 0.454, |
|
"eval_steps_per_second": 0.227, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6803, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6825, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6566, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.0002, |
|
"loss": 0.5804, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6501, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6467, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6288, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6505, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6884, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6187, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.0002, |
|
"loss": 0.698, |
|
"step": 51 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6788, |
|
"step": 52 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6813, |
|
"step": 53 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7177, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6416, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7039, |
|
"step": 56 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6749, |
|
"step": 57 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6716, |
|
"step": 58 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6554, |
|
"step": 59 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7074, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"eval_loss": 0.713684618473053, |
|
"eval_runtime": 61.7163, |
|
"eval_samples_per_second": 0.454, |
|
"eval_steps_per_second": 0.227, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6745, |
|
"step": 61 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6201, |
|
"step": 62 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6556, |
|
"step": 63 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6458, |
|
"step": 64 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6129, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6337, |
|
"step": 66 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6341, |
|
"step": 67 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6955, |
|
"step": 68 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6538, |
|
"step": 69 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6962, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6408, |
|
"step": 71 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6327, |
|
"step": 72 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6487, |
|
"step": 73 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6332, |
|
"step": 74 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6712, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6065, |
|
"step": 76 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6752, |
|
"step": 77 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6965, |
|
"step": 78 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6306, |
|
"step": 79 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6789, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"eval_loss": 0.7147287726402283, |
|
"eval_runtime": 61.6954, |
|
"eval_samples_per_second": 0.454, |
|
"eval_steps_per_second": 0.227, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7026, |
|
"step": 81 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6344, |
|
"step": 82 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6562, |
|
"step": 83 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6402, |
|
"step": 84 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6101, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.0002, |
|
"loss": 0.684, |
|
"step": 86 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7078, |
|
"step": 87 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6185, |
|
"step": 88 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6444, |
|
"step": 89 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6633, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.0002, |
|
"loss": 0.64, |
|
"step": 91 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6478, |
|
"step": 92 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6391, |
|
"step": 93 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6615, |
|
"step": 94 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6087, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 0.0002, |
|
"loss": 0.5813, |
|
"step": 96 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6382, |
|
"step": 97 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6592, |
|
"step": 98 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6993, |
|
"step": 99 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6365, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"eval_loss": 0.7158837914466858, |
|
"eval_runtime": 61.6652, |
|
"eval_samples_per_second": 0.454, |
|
"eval_steps_per_second": 0.227, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6701, |
|
"step": 101 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6548, |
|
"step": 102 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6537, |
|
"step": 103 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6245, |
|
"step": 104 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 0.0002, |
|
"loss": 0.689, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6237, |
|
"step": 106 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6209, |
|
"step": 107 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6833, |
|
"step": 108 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7169, |
|
"step": 109 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6534, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7322, |
|
"step": 111 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6634, |
|
"step": 112 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6194, |
|
"step": 113 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6238, |
|
"step": 114 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6806, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7004, |
|
"step": 116 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6181, |
|
"step": 117 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6187, |
|
"step": 118 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6148, |
|
"step": 119 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 0.0002, |
|
"loss": 0.588, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"eval_loss": 0.7125279307365417, |
|
"eval_runtime": 61.6611, |
|
"eval_samples_per_second": 0.454, |
|
"eval_steps_per_second": 0.227, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6556, |
|
"step": 121 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6815, |
|
"step": 122 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6437, |
|
"step": 123 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 0.0002, |
|
"loss": 0.5877, |
|
"step": 124 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 0.0002, |
|
"loss": 0.661, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6967, |
|
"step": 126 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 0.0002, |
|
"loss": 0.5305, |
|
"step": 127 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 0.0002, |
|
"loss": 0.696, |
|
"step": 128 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6206, |
|
"step": 129 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6093, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6691, |
|
"step": 131 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6741, |
|
"step": 132 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 0.0002, |
|
"loss": 0.703, |
|
"step": 133 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6277, |
|
"step": 134 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6689, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6759, |
|
"step": 136 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6478, |
|
"step": 137 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6293, |
|
"step": 138 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6697, |
|
"step": 139 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 0.0002, |
|
"loss": 0.5792, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"eval_loss": 0.7092259526252747, |
|
"eval_runtime": 61.6566, |
|
"eval_samples_per_second": 0.454, |
|
"eval_steps_per_second": 0.227, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6318, |
|
"step": 141 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6087, |
|
"step": 142 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6719, |
|
"step": 143 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6805, |
|
"step": 144 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7078, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7451, |
|
"step": 146 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7025, |
|
"step": 147 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6966, |
|
"step": 148 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6685, |
|
"step": 149 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6475, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 0.0002, |
|
"loss": 0.685, |
|
"step": 151 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6586, |
|
"step": 152 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7471, |
|
"step": 153 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7459, |
|
"step": 154 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6347, |
|
"step": 155 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6863, |
|
"step": 156 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7217, |
|
"step": 157 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6961, |
|
"step": 158 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7294, |
|
"step": 159 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7065, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"eval_loss": 0.7031598687171936, |
|
"eval_runtime": 61.6722, |
|
"eval_samples_per_second": 0.454, |
|
"eval_steps_per_second": 0.227, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6617, |
|
"step": 161 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7022, |
|
"step": 162 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6815, |
|
"step": 163 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6593, |
|
"step": 164 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 0.0002, |
|
"loss": 0.728, |
|
"step": 165 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7029, |
|
"step": 166 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6828, |
|
"step": 167 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7378, |
|
"step": 168 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6646, |
|
"step": 169 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6884, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6713, |
|
"step": 171 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 0.0002, |
|
"loss": 0.703, |
|
"step": 172 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6899, |
|
"step": 173 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7384, |
|
"step": 174 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6977, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7067, |
|
"step": 176 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6933, |
|
"step": 177 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6773, |
|
"step": 178 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7154, |
|
"step": 179 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6897, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"eval_loss": 0.6995596885681152, |
|
"eval_runtime": 61.6698, |
|
"eval_samples_per_second": 0.454, |
|
"eval_steps_per_second": 0.227, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6492, |
|
"step": 181 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 0.0002, |
|
"loss": 0.722, |
|
"step": 182 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7521, |
|
"step": 183 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7093, |
|
"step": 184 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 0.0002, |
|
"loss": 0.72, |
|
"step": 185 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7001, |
|
"step": 186 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 0.0002, |
|
"loss": 0.642, |
|
"step": 187 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6805, |
|
"step": 188 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7094, |
|
"step": 189 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6851, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6624, |
|
"step": 191 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7122, |
|
"step": 192 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6792, |
|
"step": 193 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6736, |
|
"step": 194 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7077, |
|
"step": 195 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 0.0002, |
|
"loss": 0.647, |
|
"step": 196 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 0.0002, |
|
"loss": 0.701, |
|
"step": 197 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7017, |
|
"step": 198 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7166, |
|
"step": 199 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7053, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"eval_loss": 0.6974362730979919, |
|
"eval_runtime": 61.6749, |
|
"eval_samples_per_second": 0.454, |
|
"eval_steps_per_second": 0.227, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7491, |
|
"step": 201 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 0.0002, |
|
"loss": 0.684, |
|
"step": 202 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6663, |
|
"step": 203 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6929, |
|
"step": 204 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6709, |
|
"step": 205 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6705, |
|
"step": 206 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7128, |
|
"step": 207 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7086, |
|
"step": 208 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7026, |
|
"step": 209 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7333, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7072, |
|
"step": 211 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6791, |
|
"step": 212 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7324, |
|
"step": 213 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6743, |
|
"step": 214 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7017, |
|
"step": 215 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6592, |
|
"step": 216 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6691, |
|
"step": 217 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7093, |
|
"step": 218 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6677, |
|
"step": 219 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7233, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"eval_loss": 0.6950156092643738, |
|
"eval_runtime": 61.071, |
|
"eval_samples_per_second": 0.458, |
|
"eval_steps_per_second": 0.229, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6807, |
|
"step": 221 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 0.0002, |
|
"loss": 0.688, |
|
"step": 222 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6838, |
|
"step": 223 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7596, |
|
"step": 224 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7333, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7022, |
|
"step": 226 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6913, |
|
"step": 227 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6735, |
|
"step": 228 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7035, |
|
"step": 229 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6986, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7028, |
|
"step": 231 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6831, |
|
"step": 232 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6742, |
|
"step": 233 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7105, |
|
"step": 234 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6679, |
|
"step": 235 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7177, |
|
"step": 236 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6431, |
|
"step": 237 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7055, |
|
"step": 238 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6814, |
|
"step": 239 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6657, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"eval_loss": 0.6946966052055359, |
|
"eval_runtime": 61.1942, |
|
"eval_samples_per_second": 0.458, |
|
"eval_steps_per_second": 0.229, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7436, |
|
"step": 241 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6857, |
|
"step": 242 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7002, |
|
"step": 243 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7005, |
|
"step": 244 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 0.0002, |
|
"loss": 0.743, |
|
"step": 245 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6702, |
|
"step": 246 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6766, |
|
"step": 247 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7, |
|
"step": 248 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6664, |
|
"step": 249 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6856, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6954, |
|
"step": 251 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6818, |
|
"step": 252 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7305, |
|
"step": 253 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6953, |
|
"step": 254 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7008, |
|
"step": 255 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7128, |
|
"step": 256 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 0.0002, |
|
"loss": 0.606, |
|
"step": 257 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7075, |
|
"step": 258 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6759, |
|
"step": 259 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7089, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"eval_loss": 0.6932913064956665, |
|
"eval_runtime": 61.1404, |
|
"eval_samples_per_second": 0.458, |
|
"eval_steps_per_second": 0.229, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6486, |
|
"step": 261 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7123, |
|
"step": 262 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 0.0002, |
|
"loss": 0.687, |
|
"step": 263 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6411, |
|
"step": 264 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6637, |
|
"step": 265 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7098, |
|
"step": 266 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7697, |
|
"step": 267 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6637, |
|
"step": 268 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6425, |
|
"step": 269 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 0.0002, |
|
"loss": 0.69, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6787, |
|
"step": 271 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7601, |
|
"step": 272 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6727, |
|
"step": 273 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6875, |
|
"step": 274 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6462, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7698, |
|
"step": 276 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6924, |
|
"step": 277 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 0.0002, |
|
"loss": 0.705, |
|
"step": 278 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6528, |
|
"step": 279 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6635, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"eval_loss": 0.6923065781593323, |
|
"eval_runtime": 61.3221, |
|
"eval_samples_per_second": 0.457, |
|
"eval_steps_per_second": 0.228, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6604, |
|
"step": 281 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7112, |
|
"step": 282 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6731, |
|
"step": 283 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6982, |
|
"step": 284 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6717, |
|
"step": 285 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6451, |
|
"step": 286 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6553, |
|
"step": 287 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6849, |
|
"step": 288 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7654, |
|
"step": 289 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7549, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7094, |
|
"step": 291 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7293, |
|
"step": 292 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6716, |
|
"step": 293 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6856, |
|
"step": 294 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6923, |
|
"step": 295 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7298, |
|
"step": 296 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6967, |
|
"step": 297 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6626, |
|
"step": 298 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7118, |
|
"step": 299 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7034, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"eval_loss": 0.691140353679657, |
|
"eval_runtime": 61.249, |
|
"eval_samples_per_second": 0.457, |
|
"eval_steps_per_second": 0.229, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6783, |
|
"step": 301 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6674, |
|
"step": 302 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6316, |
|
"step": 303 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6897, |
|
"step": 304 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6863, |
|
"step": 305 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 0.0002, |
|
"loss": 0.72, |
|
"step": 306 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6865, |
|
"step": 307 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6005, |
|
"step": 308 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6751, |
|
"step": 309 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6742, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6926, |
|
"step": 311 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6604, |
|
"step": 312 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7059, |
|
"step": 313 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6819, |
|
"step": 314 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6743, |
|
"step": 315 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6812, |
|
"step": 316 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6496, |
|
"step": 317 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7033, |
|
"step": 318 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6389, |
|
"step": 319 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7364, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"eval_loss": 0.6898225545883179, |
|
"eval_runtime": 61.3056, |
|
"eval_samples_per_second": 0.457, |
|
"eval_steps_per_second": 0.228, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 0.0002, |
|
"loss": 0.692, |
|
"step": 321 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 0.0002, |
|
"loss": 0.738, |
|
"step": 322 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7223, |
|
"step": 323 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6788, |
|
"step": 324 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6606, |
|
"step": 325 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7093, |
|
"step": 326 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6258, |
|
"step": 327 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6896, |
|
"step": 328 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6714, |
|
"step": 329 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 0.0002, |
|
"loss": 0.66, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7295, |
|
"step": 331 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6773, |
|
"step": 332 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 0.0002, |
|
"loss": 0.753, |
|
"step": 333 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6895, |
|
"step": 334 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6615, |
|
"step": 335 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 0.0002, |
|
"loss": 0.682, |
|
"step": 336 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6778, |
|
"step": 337 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6645, |
|
"step": 338 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6779, |
|
"step": 339 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7147, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"eval_loss": 0.688534140586853, |
|
"eval_runtime": 61.3371, |
|
"eval_samples_per_second": 0.456, |
|
"eval_steps_per_second": 0.228, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6342, |
|
"step": 341 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7297, |
|
"step": 342 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6075, |
|
"step": 343 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 0.0002, |
|
"loss": 0.5591, |
|
"step": 344 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6575, |
|
"step": 345 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6406, |
|
"step": 346 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6006, |
|
"step": 347 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6698, |
|
"step": 348 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6104, |
|
"step": 349 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6391, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6538, |
|
"step": 351 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6504, |
|
"step": 352 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 0.0002, |
|
"loss": 0.653, |
|
"step": 353 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6621, |
|
"step": 354 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6518, |
|
"step": 355 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 0.0002, |
|
"loss": 0.633, |
|
"step": 356 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6459, |
|
"step": 357 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6154, |
|
"step": 358 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6319, |
|
"step": 359 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6425, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"eval_loss": 0.6947513222694397, |
|
"eval_runtime": 61.2171, |
|
"eval_samples_per_second": 0.457, |
|
"eval_steps_per_second": 0.229, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6452, |
|
"step": 361 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6406, |
|
"step": 362 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6518, |
|
"step": 363 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6293, |
|
"step": 364 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 0.0002, |
|
"loss": 0.614, |
|
"step": 365 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 0.0002, |
|
"loss": 0.5518, |
|
"step": 366 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6492, |
|
"step": 367 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6167, |
|
"step": 368 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 0.0002, |
|
"loss": 0.64, |
|
"step": 369 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 0.0002, |
|
"loss": 0.5885, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6438, |
|
"step": 371 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6518, |
|
"step": 372 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6697, |
|
"step": 373 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6451, |
|
"step": 374 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"learning_rate": 0.0002, |
|
"loss": 0.598, |
|
"step": 375 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6624, |
|
"step": 376 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6355, |
|
"step": 377 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 0.0002, |
|
"loss": 0.5376, |
|
"step": 378 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 0.0002, |
|
"loss": 0.612, |
|
"step": 379 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 0.0002, |
|
"loss": 0.5659, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"eval_loss": 0.6974608302116394, |
|
"eval_runtime": 61.3547, |
|
"eval_samples_per_second": 0.456, |
|
"eval_steps_per_second": 0.228, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 0.0002, |
|
"loss": 0.5929, |
|
"step": 381 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6472, |
|
"step": 382 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6038, |
|
"step": 383 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6285, |
|
"step": 384 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 0.0002, |
|
"loss": 0.5863, |
|
"step": 385 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 0.0002, |
|
"loss": 0.591, |
|
"step": 386 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 0.0002, |
|
"loss": 0.5844, |
|
"step": 387 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6012, |
|
"step": 388 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6596, |
|
"step": 389 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6475, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6173, |
|
"step": 391 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6239, |
|
"step": 392 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6361, |
|
"step": 393 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 0.0002, |
|
"loss": 0.5888, |
|
"step": 394 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 0.0002, |
|
"loss": 0.65, |
|
"step": 395 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6552, |
|
"step": 396 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6368, |
|
"step": 397 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6418, |
|
"step": 398 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6543, |
|
"step": 399 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 0.0002, |
|
"loss": 0.5669, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"eval_loss": 0.702307403087616, |
|
"eval_runtime": 61.3341, |
|
"eval_samples_per_second": 0.457, |
|
"eval_steps_per_second": 0.228, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6119, |
|
"step": 401 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 0.0002, |
|
"loss": 0.5889, |
|
"step": 402 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6247, |
|
"step": 403 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6128, |
|
"step": 404 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6302, |
|
"step": 405 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 0.0002, |
|
"loss": 0.626, |
|
"step": 406 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 0.0002, |
|
"loss": 0.5961, |
|
"step": 407 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6302, |
|
"step": 408 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6094, |
|
"step": 409 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 0.0002, |
|
"loss": 0.5564, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 0.0002, |
|
"loss": 0.629, |
|
"step": 411 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6261, |
|
"step": 412 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 0.0002, |
|
"loss": 0.5624, |
|
"step": 413 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 0.0002, |
|
"loss": 0.5766, |
|
"step": 414 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6756, |
|
"step": 415 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"learning_rate": 0.0002, |
|
"loss": 0.5937, |
|
"step": 416 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"learning_rate": 0.0002, |
|
"loss": 0.5713, |
|
"step": 417 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6102, |
|
"step": 418 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 0.0002, |
|
"loss": 0.5797, |
|
"step": 419 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6092, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"eval_loss": 0.7039612531661987, |
|
"eval_runtime": 62.2136, |
|
"eval_samples_per_second": 0.45, |
|
"eval_steps_per_second": 0.225, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 0.0002, |
|
"loss": 0.5736, |
|
"step": 421 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 0.0002, |
|
"loss": 0.674, |
|
"step": 422 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6295, |
|
"step": 423 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 0.0002, |
|
"loss": 0.57, |
|
"step": 424 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6051, |
|
"step": 425 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6081, |
|
"step": 426 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 0.0002, |
|
"loss": 0.5821, |
|
"step": 427 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6286, |
|
"step": 428 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 0.0002, |
|
"loss": 0.5684, |
|
"step": 429 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6334, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6045, |
|
"step": 431 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6349, |
|
"step": 432 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6292, |
|
"step": 433 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6333, |
|
"step": 434 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6427, |
|
"step": 435 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6287, |
|
"step": 436 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6448, |
|
"step": 437 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6285, |
|
"step": 438 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6179, |
|
"step": 439 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 0.0002, |
|
"loss": 0.654, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"eval_loss": 0.7050999402999878, |
|
"eval_runtime": 61.9904, |
|
"eval_samples_per_second": 0.452, |
|
"eval_steps_per_second": 0.226, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 0.0002, |
|
"loss": 0.5984, |
|
"step": 441 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 0.0002, |
|
"loss": 0.662, |
|
"step": 442 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6255, |
|
"step": 443 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6233, |
|
"step": 444 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6742, |
|
"step": 445 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6166, |
|
"step": 446 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"learning_rate": 0.0002, |
|
"loss": 0.5799, |
|
"step": 447 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6772, |
|
"step": 448 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"learning_rate": 0.0002, |
|
"loss": 0.5719, |
|
"step": 449 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 0.0002, |
|
"loss": 0.5953, |
|
"step": 450 |
|
} |
|
], |
|
"max_steps": 1026, |
|
"num_train_epochs": 3, |
|
"total_flos": 5.684044899729408e+17, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|