Joemgu's picture
Training in progress, step 300
83b6b43
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.03,
"global_step": 300,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 1e-05,
"loss": 3.6346,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 2e-05,
"loss": 3.602,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 3e-05,
"loss": 3.5741,
"step": 3
},
{
"epoch": 0.0,
"learning_rate": 4e-05,
"loss": 3.4904,
"step": 4
},
{
"epoch": 0.0,
"learning_rate": 5e-05,
"loss": 3.4215,
"step": 5
},
{
"epoch": 0.0,
"learning_rate": 6e-05,
"loss": 3.4568,
"step": 6
},
{
"epoch": 0.0,
"learning_rate": 7.000000000000001e-05,
"loss": 3.3978,
"step": 7
},
{
"epoch": 0.0,
"learning_rate": 8e-05,
"loss": 3.4991,
"step": 8
},
{
"epoch": 0.0,
"learning_rate": 8.999999999999999e-05,
"loss": 3.5852,
"step": 9
},
{
"epoch": 0.0,
"learning_rate": 0.0001,
"loss": 3.3132,
"step": 10
},
{
"epoch": 0.0,
"learning_rate": 0.00011,
"loss": 3.2737,
"step": 11
},
{
"epoch": 0.0,
"learning_rate": 0.00012,
"loss": 3.1399,
"step": 12
},
{
"epoch": 0.0,
"learning_rate": 0.00013000000000000002,
"loss": 3.1828,
"step": 13
},
{
"epoch": 0.0,
"learning_rate": 0.00014000000000000001,
"loss": 3.0638,
"step": 14
},
{
"epoch": 0.0,
"learning_rate": 0.00015,
"loss": 3.185,
"step": 15
},
{
"epoch": 0.0,
"learning_rate": 0.00016,
"loss": 3.0669,
"step": 16
},
{
"epoch": 0.0,
"learning_rate": 0.00017,
"loss": 2.9026,
"step": 17
},
{
"epoch": 0.0,
"learning_rate": 0.00017999999999999998,
"loss": 2.9591,
"step": 18
},
{
"epoch": 0.0,
"learning_rate": 0.00019,
"loss": 2.8483,
"step": 19
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.7707,
"step": 20
},
{
"epoch": 0.0,
"learning_rate": 0.00021,
"loss": 2.8564,
"step": 21
},
{
"epoch": 0.0,
"learning_rate": 0.00022,
"loss": 2.6997,
"step": 22
},
{
"epoch": 0.0,
"learning_rate": 0.00023,
"loss": 2.8052,
"step": 23
},
{
"epoch": 0.0,
"learning_rate": 0.00024,
"loss": 2.5826,
"step": 24
},
{
"epoch": 0.0,
"learning_rate": 0.00025,
"loss": 2.6266,
"step": 25
},
{
"epoch": 0.0,
"learning_rate": 0.00026000000000000003,
"loss": 2.6477,
"step": 26
},
{
"epoch": 0.0,
"learning_rate": 0.00027,
"loss": 2.6133,
"step": 27
},
{
"epoch": 0.0,
"learning_rate": 0.00028000000000000003,
"loss": 2.5395,
"step": 28
},
{
"epoch": 0.0,
"learning_rate": 0.00029,
"loss": 2.664,
"step": 29
},
{
"epoch": 0.0,
"learning_rate": 0.0003,
"loss": 2.5568,
"step": 30
},
{
"epoch": 0.0,
"learning_rate": 0.00031,
"loss": 2.4346,
"step": 31
},
{
"epoch": 0.0,
"learning_rate": 0.00032,
"loss": 2.5765,
"step": 32
},
{
"epoch": 0.0,
"learning_rate": 0.00033,
"loss": 2.4884,
"step": 33
},
{
"epoch": 0.0,
"learning_rate": 0.00034,
"loss": 2.4257,
"step": 34
},
{
"epoch": 0.0,
"learning_rate": 0.00035,
"loss": 2.4281,
"step": 35
},
{
"epoch": 0.0,
"learning_rate": 0.00035999999999999997,
"loss": 2.4858,
"step": 36
},
{
"epoch": 0.0,
"learning_rate": 0.00037,
"loss": 2.383,
"step": 37
},
{
"epoch": 0.0,
"learning_rate": 0.00038,
"loss": 2.4865,
"step": 38
},
{
"epoch": 0.0,
"learning_rate": 0.00039000000000000005,
"loss": 2.3564,
"step": 39
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 2.4276,
"step": 40
},
{
"epoch": 0.0,
"learning_rate": 0.00041,
"loss": 2.4225,
"step": 41
},
{
"epoch": 0.0,
"learning_rate": 0.00042,
"loss": 2.2718,
"step": 42
},
{
"epoch": 0.0,
"learning_rate": 0.00043,
"loss": 2.3566,
"step": 43
},
{
"epoch": 0.0,
"learning_rate": 0.00044,
"loss": 2.3911,
"step": 44
},
{
"epoch": 0.0,
"learning_rate": 0.00045000000000000004,
"loss": 2.3999,
"step": 45
},
{
"epoch": 0.0,
"learning_rate": 0.00046,
"loss": 2.2776,
"step": 46
},
{
"epoch": 0.0,
"learning_rate": 0.00047,
"loss": 2.3891,
"step": 47
},
{
"epoch": 0.0,
"learning_rate": 0.00048,
"loss": 2.3132,
"step": 48
},
{
"epoch": 0.0,
"learning_rate": 0.00049,
"loss": 2.3353,
"step": 49
},
{
"epoch": 0.01,
"learning_rate": 0.0005,
"loss": 2.3691,
"step": 50
},
{
"epoch": 0.01,
"learning_rate": 0.00051,
"loss": 2.3271,
"step": 51
},
{
"epoch": 0.01,
"learning_rate": 0.0005200000000000001,
"loss": 2.2881,
"step": 52
},
{
"epoch": 0.01,
"learning_rate": 0.0005300000000000001,
"loss": 2.2731,
"step": 53
},
{
"epoch": 0.01,
"learning_rate": 0.00054,
"loss": 2.3186,
"step": 54
},
{
"epoch": 0.01,
"learning_rate": 0.00055,
"loss": 2.3216,
"step": 55
},
{
"epoch": 0.01,
"learning_rate": 0.0005600000000000001,
"loss": 2.3204,
"step": 56
},
{
"epoch": 0.01,
"learning_rate": 0.00057,
"loss": 2.1832,
"step": 57
},
{
"epoch": 0.01,
"learning_rate": 0.00058,
"loss": 2.4125,
"step": 58
},
{
"epoch": 0.01,
"learning_rate": 0.00059,
"loss": 2.2649,
"step": 59
},
{
"epoch": 0.01,
"learning_rate": 0.0006,
"loss": 2.1589,
"step": 60
},
{
"epoch": 0.01,
"learning_rate": 0.00061,
"loss": 2.1431,
"step": 61
},
{
"epoch": 0.01,
"learning_rate": 0.00062,
"loss": 2.3738,
"step": 62
},
{
"epoch": 0.01,
"learning_rate": 0.00063,
"loss": 2.2525,
"step": 63
},
{
"epoch": 0.01,
"learning_rate": 0.00064,
"loss": 2.2778,
"step": 64
},
{
"epoch": 0.01,
"learning_rate": 0.0006500000000000001,
"loss": 2.2739,
"step": 65
},
{
"epoch": 0.01,
"learning_rate": 0.00066,
"loss": 2.2878,
"step": 66
},
{
"epoch": 0.01,
"learning_rate": 0.00067,
"loss": 2.196,
"step": 67
},
{
"epoch": 0.01,
"learning_rate": 0.00068,
"loss": 2.2384,
"step": 68
},
{
"epoch": 0.01,
"learning_rate": 0.00069,
"loss": 2.1638,
"step": 69
},
{
"epoch": 0.01,
"learning_rate": 0.0007,
"loss": 2.1578,
"step": 70
},
{
"epoch": 0.01,
"learning_rate": 0.00071,
"loss": 2.1781,
"step": 71
},
{
"epoch": 0.01,
"learning_rate": 0.0007199999999999999,
"loss": 2.2486,
"step": 72
},
{
"epoch": 0.01,
"learning_rate": 0.00073,
"loss": 2.2475,
"step": 73
},
{
"epoch": 0.01,
"learning_rate": 0.00074,
"loss": 2.0713,
"step": 74
},
{
"epoch": 0.01,
"learning_rate": 0.00075,
"loss": 2.1261,
"step": 75
},
{
"epoch": 0.01,
"learning_rate": 0.00076,
"loss": 2.156,
"step": 76
},
{
"epoch": 0.01,
"learning_rate": 0.0007700000000000001,
"loss": 2.2273,
"step": 77
},
{
"epoch": 0.01,
"learning_rate": 0.0007800000000000001,
"loss": 2.2245,
"step": 78
},
{
"epoch": 0.01,
"learning_rate": 0.00079,
"loss": 2.1527,
"step": 79
},
{
"epoch": 0.01,
"learning_rate": 0.0008,
"loss": 2.0454,
"step": 80
},
{
"epoch": 0.01,
"learning_rate": 0.0008100000000000001,
"loss": 2.2643,
"step": 81
},
{
"epoch": 0.01,
"learning_rate": 0.00082,
"loss": 2.2447,
"step": 82
},
{
"epoch": 0.01,
"learning_rate": 0.00083,
"loss": 2.1656,
"step": 83
},
{
"epoch": 0.01,
"learning_rate": 0.00084,
"loss": 2.099,
"step": 84
},
{
"epoch": 0.01,
"learning_rate": 0.00085,
"loss": 2.2078,
"step": 85
},
{
"epoch": 0.01,
"learning_rate": 0.00086,
"loss": 2.1537,
"step": 86
},
{
"epoch": 0.01,
"learning_rate": 0.00087,
"loss": 2.1013,
"step": 87
},
{
"epoch": 0.01,
"learning_rate": 0.00088,
"loss": 2.0553,
"step": 88
},
{
"epoch": 0.01,
"learning_rate": 0.0008900000000000001,
"loss": 2.1702,
"step": 89
},
{
"epoch": 0.01,
"learning_rate": 0.0009000000000000001,
"loss": 2.0685,
"step": 90
},
{
"epoch": 0.01,
"learning_rate": 0.00091,
"loss": 2.149,
"step": 91
},
{
"epoch": 0.01,
"learning_rate": 0.00092,
"loss": 2.1102,
"step": 92
},
{
"epoch": 0.01,
"learning_rate": 0.00093,
"loss": 2.2527,
"step": 93
},
{
"epoch": 0.01,
"learning_rate": 0.00094,
"loss": 2.0719,
"step": 94
},
{
"epoch": 0.01,
"learning_rate": 0.00095,
"loss": 2.1293,
"step": 95
},
{
"epoch": 0.01,
"learning_rate": 0.00096,
"loss": 2.1333,
"step": 96
},
{
"epoch": 0.01,
"learning_rate": 0.0009699999999999999,
"loss": 2.1497,
"step": 97
},
{
"epoch": 0.01,
"learning_rate": 0.00098,
"loss": 2.0996,
"step": 98
},
{
"epoch": 0.01,
"learning_rate": 0.00099,
"loss": 2.1576,
"step": 99
},
{
"epoch": 0.01,
"learning_rate": 0.001,
"loss": 2.1483,
"step": 100
},
{
"epoch": 0.01,
"learning_rate": 0.00099989898989899,
"loss": 2.1328,
"step": 101
},
{
"epoch": 0.01,
"learning_rate": 0.00099979797979798,
"loss": 2.0475,
"step": 102
},
{
"epoch": 0.01,
"learning_rate": 0.0009996969696969699,
"loss": 2.2059,
"step": 103
},
{
"epoch": 0.01,
"learning_rate": 0.0009995959595959596,
"loss": 2.0895,
"step": 104
},
{
"epoch": 0.01,
"learning_rate": 0.0009994949494949495,
"loss": 2.1077,
"step": 105
},
{
"epoch": 0.01,
"learning_rate": 0.0009993939393939395,
"loss": 2.0621,
"step": 106
},
{
"epoch": 0.01,
"learning_rate": 0.0009992929292929294,
"loss": 2.177,
"step": 107
},
{
"epoch": 0.01,
"learning_rate": 0.0009991919191919192,
"loss": 2.2142,
"step": 108
},
{
"epoch": 0.01,
"learning_rate": 0.0009990909090909091,
"loss": 2.0881,
"step": 109
},
{
"epoch": 0.01,
"learning_rate": 0.000998989898989899,
"loss": 2.1707,
"step": 110
},
{
"epoch": 0.01,
"learning_rate": 0.000998888888888889,
"loss": 2.1403,
"step": 111
},
{
"epoch": 0.01,
"learning_rate": 0.0009987878787878787,
"loss": 2.1171,
"step": 112
},
{
"epoch": 0.01,
"learning_rate": 0.0009986868686868687,
"loss": 2.047,
"step": 113
},
{
"epoch": 0.01,
"learning_rate": 0.0009985858585858586,
"loss": 2.0712,
"step": 114
},
{
"epoch": 0.01,
"learning_rate": 0.0009984848484848486,
"loss": 2.1068,
"step": 115
},
{
"epoch": 0.01,
"learning_rate": 0.0009983838383838383,
"loss": 2.1159,
"step": 116
},
{
"epoch": 0.01,
"learning_rate": 0.0009982828282828283,
"loss": 2.0403,
"step": 117
},
{
"epoch": 0.01,
"learning_rate": 0.0009981818181818182,
"loss": 2.0022,
"step": 118
},
{
"epoch": 0.01,
"learning_rate": 0.0009980808080808081,
"loss": 2.0025,
"step": 119
},
{
"epoch": 0.01,
"learning_rate": 0.000997979797979798,
"loss": 2.1265,
"step": 120
},
{
"epoch": 0.01,
"learning_rate": 0.000997878787878788,
"loss": 2.1159,
"step": 121
},
{
"epoch": 0.01,
"learning_rate": 0.0009977777777777778,
"loss": 1.958,
"step": 122
},
{
"epoch": 0.01,
"learning_rate": 0.0009976767676767677,
"loss": 2.0857,
"step": 123
},
{
"epoch": 0.01,
"learning_rate": 0.0009975757575757577,
"loss": 1.9986,
"step": 124
},
{
"epoch": 0.01,
"learning_rate": 0.0009974747474747476,
"loss": 2.1304,
"step": 125
},
{
"epoch": 0.01,
"learning_rate": 0.0009973737373737373,
"loss": 2.184,
"step": 126
},
{
"epoch": 0.01,
"learning_rate": 0.0009972727272727273,
"loss": 2.0053,
"step": 127
},
{
"epoch": 0.01,
"learning_rate": 0.0009971717171717172,
"loss": 2.028,
"step": 128
},
{
"epoch": 0.01,
"learning_rate": 0.0009970707070707072,
"loss": 2.0992,
"step": 129
},
{
"epoch": 0.01,
"learning_rate": 0.000996969696969697,
"loss": 2.0326,
"step": 130
},
{
"epoch": 0.01,
"learning_rate": 0.0009968686868686869,
"loss": 2.0328,
"step": 131
},
{
"epoch": 0.01,
"learning_rate": 0.0009967676767676768,
"loss": 2.0563,
"step": 132
},
{
"epoch": 0.01,
"learning_rate": 0.0009966666666666668,
"loss": 2.178,
"step": 133
},
{
"epoch": 0.01,
"learning_rate": 0.0009965656565656565,
"loss": 2.1038,
"step": 134
},
{
"epoch": 0.01,
"learning_rate": 0.0009964646464646464,
"loss": 2.096,
"step": 135
},
{
"epoch": 0.01,
"learning_rate": 0.0009963636363636364,
"loss": 2.1732,
"step": 136
},
{
"epoch": 0.01,
"learning_rate": 0.0009962626262626263,
"loss": 2.1267,
"step": 137
},
{
"epoch": 0.01,
"learning_rate": 0.000996161616161616,
"loss": 2.0657,
"step": 138
},
{
"epoch": 0.01,
"learning_rate": 0.0009960606060606062,
"loss": 2.1286,
"step": 139
},
{
"epoch": 0.01,
"learning_rate": 0.000995959595959596,
"loss": 2.0452,
"step": 140
},
{
"epoch": 0.01,
"learning_rate": 0.000995858585858586,
"loss": 2.0499,
"step": 141
},
{
"epoch": 0.01,
"learning_rate": 0.0009957575757575758,
"loss": 2.1283,
"step": 142
},
{
"epoch": 0.01,
"learning_rate": 0.0009956565656565658,
"loss": 2.1229,
"step": 143
},
{
"epoch": 0.01,
"learning_rate": 0.0009955555555555555,
"loss": 2.1071,
"step": 144
},
{
"epoch": 0.01,
"learning_rate": 0.0009954545454545455,
"loss": 2.1224,
"step": 145
},
{
"epoch": 0.01,
"learning_rate": 0.0009953535353535354,
"loss": 1.9851,
"step": 146
},
{
"epoch": 0.01,
"learning_rate": 0.0009952525252525254,
"loss": 2.0053,
"step": 147
},
{
"epoch": 0.01,
"learning_rate": 0.000995151515151515,
"loss": 2.113,
"step": 148
},
{
"epoch": 0.01,
"learning_rate": 0.000995050505050505,
"loss": 2.0945,
"step": 149
},
{
"epoch": 0.01,
"learning_rate": 0.000994949494949495,
"loss": 2.0622,
"step": 150
},
{
"epoch": 0.02,
"learning_rate": 0.000994848484848485,
"loss": 2.0936,
"step": 151
},
{
"epoch": 0.02,
"learning_rate": 0.0009947474747474747,
"loss": 2.1155,
"step": 152
},
{
"epoch": 0.02,
"learning_rate": 0.0009946464646464646,
"loss": 2.1981,
"step": 153
},
{
"epoch": 0.02,
"learning_rate": 0.0009945454545454546,
"loss": 2.0479,
"step": 154
},
{
"epoch": 0.02,
"learning_rate": 0.0009944444444444445,
"loss": 2.1307,
"step": 155
},
{
"epoch": 0.02,
"learning_rate": 0.0009943434343434342,
"loss": 1.8631,
"step": 156
},
{
"epoch": 0.02,
"learning_rate": 0.0009942424242424242,
"loss": 2.091,
"step": 157
},
{
"epoch": 0.02,
"learning_rate": 0.0009941414141414141,
"loss": 2.1344,
"step": 158
},
{
"epoch": 0.02,
"learning_rate": 0.000994040404040404,
"loss": 2.0833,
"step": 159
},
{
"epoch": 0.02,
"learning_rate": 0.000993939393939394,
"loss": 1.9934,
"step": 160
},
{
"epoch": 0.02,
"learning_rate": 0.000993838383838384,
"loss": 1.9833,
"step": 161
},
{
"epoch": 0.02,
"learning_rate": 0.0009937373737373737,
"loss": 1.986,
"step": 162
},
{
"epoch": 0.02,
"learning_rate": 0.0009936363636363636,
"loss": 2.0843,
"step": 163
},
{
"epoch": 0.02,
"learning_rate": 0.0009935353535353536,
"loss": 2.0206,
"step": 164
},
{
"epoch": 0.02,
"learning_rate": 0.0009934343434343435,
"loss": 2.0856,
"step": 165
},
{
"epoch": 0.02,
"learning_rate": 0.0009933333333333333,
"loss": 2.0136,
"step": 166
},
{
"epoch": 0.02,
"learning_rate": 0.0009932323232323232,
"loss": 1.9881,
"step": 167
},
{
"epoch": 0.02,
"learning_rate": 0.0009931313131313132,
"loss": 2.1644,
"step": 168
},
{
"epoch": 0.02,
"learning_rate": 0.000993030303030303,
"loss": 2.09,
"step": 169
},
{
"epoch": 0.02,
"learning_rate": 0.0009929292929292928,
"loss": 2.1076,
"step": 170
},
{
"epoch": 0.02,
"learning_rate": 0.0009928282828282828,
"loss": 1.9709,
"step": 171
},
{
"epoch": 0.02,
"learning_rate": 0.0009927272727272727,
"loss": 2.0471,
"step": 172
},
{
"epoch": 0.02,
"learning_rate": 0.0009926262626262627,
"loss": 2.0856,
"step": 173
},
{
"epoch": 0.02,
"learning_rate": 0.0009925252525252524,
"loss": 2.0028,
"step": 174
},
{
"epoch": 0.02,
"learning_rate": 0.0009924242424242424,
"loss": 2.0308,
"step": 175
},
{
"epoch": 0.02,
"learning_rate": 0.0009923232323232323,
"loss": 2.0572,
"step": 176
},
{
"epoch": 0.02,
"learning_rate": 0.0009922222222222222,
"loss": 2.0539,
"step": 177
},
{
"epoch": 0.02,
"learning_rate": 0.0009921212121212122,
"loss": 2.0185,
"step": 178
},
{
"epoch": 0.02,
"learning_rate": 0.0009920202020202021,
"loss": 2.0536,
"step": 179
},
{
"epoch": 0.02,
"learning_rate": 0.0009919191919191919,
"loss": 2.0024,
"step": 180
},
{
"epoch": 0.02,
"learning_rate": 0.0009918181818181818,
"loss": 2.1277,
"step": 181
},
{
"epoch": 0.02,
"learning_rate": 0.0009917171717171718,
"loss": 2.0297,
"step": 182
},
{
"epoch": 0.02,
"learning_rate": 0.0009916161616161617,
"loss": 2.0917,
"step": 183
},
{
"epoch": 0.02,
"learning_rate": 0.0009915151515151514,
"loss": 2.1006,
"step": 184
},
{
"epoch": 0.02,
"learning_rate": 0.0009914141414141414,
"loss": 2.0455,
"step": 185
},
{
"epoch": 0.02,
"learning_rate": 0.0009913131313131313,
"loss": 2.0974,
"step": 186
},
{
"epoch": 0.02,
"learning_rate": 0.0009912121212121213,
"loss": 2.0821,
"step": 187
},
{
"epoch": 0.02,
"learning_rate": 0.0009911111111111112,
"loss": 2.0931,
"step": 188
},
{
"epoch": 0.02,
"learning_rate": 0.000991010101010101,
"loss": 2.0317,
"step": 189
},
{
"epoch": 0.02,
"learning_rate": 0.000990909090909091,
"loss": 1.9059,
"step": 190
},
{
"epoch": 0.02,
"learning_rate": 0.0009908080808080809,
"loss": 1.9258,
"step": 191
},
{
"epoch": 0.02,
"learning_rate": 0.0009907070707070708,
"loss": 1.9566,
"step": 192
},
{
"epoch": 0.02,
"learning_rate": 0.0009906060606060605,
"loss": 2.0572,
"step": 193
},
{
"epoch": 0.02,
"learning_rate": 0.0009905050505050505,
"loss": 2.0917,
"step": 194
},
{
"epoch": 0.02,
"learning_rate": 0.0009904040404040404,
"loss": 2.0177,
"step": 195
},
{
"epoch": 0.02,
"learning_rate": 0.0009903030303030304,
"loss": 1.9265,
"step": 196
},
{
"epoch": 0.02,
"learning_rate": 0.0009902020202020203,
"loss": 2.1021,
"step": 197
},
{
"epoch": 0.02,
"learning_rate": 0.0009901010101010103,
"loss": 2.1158,
"step": 198
},
{
"epoch": 0.02,
"learning_rate": 0.00099,
"loss": 1.9843,
"step": 199
},
{
"epoch": 0.02,
"learning_rate": 0.00098989898989899,
"loss": 2.0997,
"step": 200
},
{
"epoch": 0.02,
"learning_rate": 0.0009897979797979799,
"loss": 2.0933,
"step": 201
},
{
"epoch": 0.02,
"learning_rate": 0.0009896969696969698,
"loss": 2.0834,
"step": 202
},
{
"epoch": 0.02,
"learning_rate": 0.0009895959595959596,
"loss": 2.1167,
"step": 203
},
{
"epoch": 0.02,
"learning_rate": 0.0009894949494949495,
"loss": 2.0517,
"step": 204
},
{
"epoch": 0.02,
"learning_rate": 0.0009893939393939395,
"loss": 1.9413,
"step": 205
},
{
"epoch": 0.02,
"learning_rate": 0.0009892929292929294,
"loss": 1.891,
"step": 206
},
{
"epoch": 0.02,
"learning_rate": 0.0009891919191919191,
"loss": 1.9382,
"step": 207
},
{
"epoch": 0.02,
"learning_rate": 0.000989090909090909,
"loss": 1.9736,
"step": 208
},
{
"epoch": 0.02,
"learning_rate": 0.000988989898989899,
"loss": 2.0332,
"step": 209
},
{
"epoch": 0.02,
"learning_rate": 0.000988888888888889,
"loss": 2.0221,
"step": 210
},
{
"epoch": 0.02,
"learning_rate": 0.0009887878787878787,
"loss": 2.0825,
"step": 211
},
{
"epoch": 0.02,
"learning_rate": 0.0009886868686868687,
"loss": 1.9693,
"step": 212
},
{
"epoch": 0.02,
"learning_rate": 0.0009885858585858586,
"loss": 1.9989,
"step": 213
},
{
"epoch": 0.02,
"learning_rate": 0.0009884848484848485,
"loss": 1.9897,
"step": 214
},
{
"epoch": 0.02,
"learning_rate": 0.0009883838383838383,
"loss": 2.0722,
"step": 215
},
{
"epoch": 0.02,
"learning_rate": 0.0009882828282828284,
"loss": 1.9653,
"step": 216
},
{
"epoch": 0.02,
"learning_rate": 0.0009881818181818182,
"loss": 2.0861,
"step": 217
},
{
"epoch": 0.02,
"learning_rate": 0.0009880808080808081,
"loss": 1.8935,
"step": 218
},
{
"epoch": 0.02,
"learning_rate": 0.000987979797979798,
"loss": 2.1295,
"step": 219
},
{
"epoch": 0.02,
"learning_rate": 0.000987878787878788,
"loss": 2.0555,
"step": 220
},
{
"epoch": 0.02,
"learning_rate": 0.0009877777777777777,
"loss": 2.0813,
"step": 221
},
{
"epoch": 0.02,
"learning_rate": 0.0009876767676767677,
"loss": 2.0426,
"step": 222
},
{
"epoch": 0.02,
"learning_rate": 0.0009875757575757576,
"loss": 1.9818,
"step": 223
},
{
"epoch": 0.02,
"learning_rate": 0.0009874747474747476,
"loss": 1.9744,
"step": 224
},
{
"epoch": 0.02,
"learning_rate": 0.0009873737373737373,
"loss": 1.9681,
"step": 225
},
{
"epoch": 0.02,
"learning_rate": 0.0009872727272727273,
"loss": 2.0538,
"step": 226
},
{
"epoch": 0.02,
"learning_rate": 0.0009871717171717172,
"loss": 2.0493,
"step": 227
},
{
"epoch": 0.02,
"learning_rate": 0.0009870707070707072,
"loss": 1.9484,
"step": 228
},
{
"epoch": 0.02,
"learning_rate": 0.0009869696969696969,
"loss": 2.0947,
"step": 229
},
{
"epoch": 0.02,
"learning_rate": 0.0009868686868686868,
"loss": 2.0193,
"step": 230
},
{
"epoch": 0.02,
"learning_rate": 0.0009867676767676768,
"loss": 2.0365,
"step": 231
},
{
"epoch": 0.02,
"learning_rate": 0.0009866666666666667,
"loss": 2.0624,
"step": 232
},
{
"epoch": 0.02,
"learning_rate": 0.0009865656565656565,
"loss": 1.9721,
"step": 233
},
{
"epoch": 0.02,
"learning_rate": 0.0009864646464646464,
"loss": 1.9658,
"step": 234
},
{
"epoch": 0.02,
"learning_rate": 0.0009863636363636363,
"loss": 2.0441,
"step": 235
},
{
"epoch": 0.02,
"learning_rate": 0.0009862626262626263,
"loss": 1.929,
"step": 236
},
{
"epoch": 0.02,
"learning_rate": 0.0009861616161616162,
"loss": 2.0288,
"step": 237
},
{
"epoch": 0.02,
"learning_rate": 0.0009860606060606062,
"loss": 1.9462,
"step": 238
},
{
"epoch": 0.02,
"learning_rate": 0.000985959595959596,
"loss": 1.9983,
"step": 239
},
{
"epoch": 0.02,
"learning_rate": 0.0009858585858585859,
"loss": 1.9697,
"step": 240
},
{
"epoch": 0.02,
"learning_rate": 0.0009857575757575758,
"loss": 2.035,
"step": 241
},
{
"epoch": 0.02,
"learning_rate": 0.0009856565656565658,
"loss": 2.0163,
"step": 242
},
{
"epoch": 0.02,
"learning_rate": 0.0009855555555555555,
"loss": 2.0443,
"step": 243
},
{
"epoch": 0.02,
"learning_rate": 0.0009854545454545454,
"loss": 1.9712,
"step": 244
},
{
"epoch": 0.02,
"learning_rate": 0.0009853535353535354,
"loss": 1.979,
"step": 245
},
{
"epoch": 0.02,
"learning_rate": 0.0009852525252525253,
"loss": 1.9346,
"step": 246
},
{
"epoch": 0.02,
"learning_rate": 0.000985151515151515,
"loss": 2.0026,
"step": 247
},
{
"epoch": 0.02,
"learning_rate": 0.000985050505050505,
"loss": 1.9729,
"step": 248
},
{
"epoch": 0.02,
"learning_rate": 0.000984949494949495,
"loss": 1.8462,
"step": 249
},
{
"epoch": 0.03,
"learning_rate": 0.000984848484848485,
"loss": 1.9336,
"step": 250
},
{
"epoch": 0.03,
"learning_rate": 0.0009847474747474746,
"loss": 1.9938,
"step": 251
},
{
"epoch": 0.03,
"learning_rate": 0.0009846464646464646,
"loss": 1.9834,
"step": 252
},
{
"epoch": 0.03,
"learning_rate": 0.0009845454545454545,
"loss": 1.9892,
"step": 253
},
{
"epoch": 0.03,
"learning_rate": 0.0009844444444444445,
"loss": 1.9013,
"step": 254
},
{
"epoch": 0.03,
"learning_rate": 0.0009843434343434344,
"loss": 2.0017,
"step": 255
},
{
"epoch": 0.03,
"learning_rate": 0.0009842424242424244,
"loss": 1.9771,
"step": 256
},
{
"epoch": 0.03,
"learning_rate": 0.000984141414141414,
"loss": 2.0135,
"step": 257
},
{
"epoch": 0.03,
"learning_rate": 0.000984040404040404,
"loss": 1.9034,
"step": 258
},
{
"epoch": 0.03,
"learning_rate": 0.000983939393939394,
"loss": 1.9586,
"step": 259
},
{
"epoch": 0.03,
"learning_rate": 0.000983838383838384,
"loss": 1.9966,
"step": 260
},
{
"epoch": 0.03,
"learning_rate": 0.0009837373737373737,
"loss": 1.9742,
"step": 261
},
{
"epoch": 0.03,
"learning_rate": 0.0009836363636363636,
"loss": 1.9376,
"step": 262
},
{
"epoch": 0.03,
"learning_rate": 0.0009835353535353536,
"loss": 1.9006,
"step": 263
},
{
"epoch": 0.03,
"learning_rate": 0.0009834343434343435,
"loss": 2.028,
"step": 264
},
{
"epoch": 0.03,
"learning_rate": 0.0009833333333333332,
"loss": 2.0231,
"step": 265
},
{
"epoch": 0.03,
"learning_rate": 0.0009832323232323232,
"loss": 2.0239,
"step": 266
},
{
"epoch": 0.03,
"learning_rate": 0.0009831313131313131,
"loss": 1.9672,
"step": 267
},
{
"epoch": 0.03,
"learning_rate": 0.000983030303030303,
"loss": 2.098,
"step": 268
},
{
"epoch": 0.03,
"learning_rate": 0.0009829292929292928,
"loss": 2.0253,
"step": 269
},
{
"epoch": 0.03,
"learning_rate": 0.0009828282828282828,
"loss": 1.8544,
"step": 270
},
{
"epoch": 0.03,
"learning_rate": 0.0009827272727272727,
"loss": 1.9616,
"step": 271
},
{
"epoch": 0.03,
"learning_rate": 0.0009826262626262626,
"loss": 1.9871,
"step": 272
},
{
"epoch": 0.03,
"learning_rate": 0.0009825252525252526,
"loss": 2.0377,
"step": 273
},
{
"epoch": 0.03,
"learning_rate": 0.0009824242424242425,
"loss": 1.9943,
"step": 274
},
{
"epoch": 0.03,
"learning_rate": 0.0009823232323232325,
"loss": 1.9859,
"step": 275
},
{
"epoch": 0.03,
"learning_rate": 0.0009822222222222222,
"loss": 1.94,
"step": 276
},
{
"epoch": 0.03,
"learning_rate": 0.0009821212121212122,
"loss": 1.9271,
"step": 277
},
{
"epoch": 0.03,
"learning_rate": 0.0009820202020202021,
"loss": 1.924,
"step": 278
},
{
"epoch": 0.03,
"learning_rate": 0.000981919191919192,
"loss": 2.0862,
"step": 279
},
{
"epoch": 0.03,
"learning_rate": 0.0009818181818181818,
"loss": 2.1038,
"step": 280
},
{
"epoch": 0.03,
"learning_rate": 0.0009817171717171717,
"loss": 1.9944,
"step": 281
},
{
"epoch": 0.03,
"learning_rate": 0.0009816161616161617,
"loss": 1.9266,
"step": 282
},
{
"epoch": 0.03,
"learning_rate": 0.0009815151515151516,
"loss": 2.0527,
"step": 283
},
{
"epoch": 0.03,
"learning_rate": 0.0009814141414141414,
"loss": 1.9245,
"step": 284
},
{
"epoch": 0.03,
"learning_rate": 0.0009813131313131313,
"loss": 2.0017,
"step": 285
},
{
"epoch": 0.03,
"learning_rate": 0.0009812121212121213,
"loss": 1.998,
"step": 286
},
{
"epoch": 0.03,
"learning_rate": 0.0009811111111111112,
"loss": 1.9133,
"step": 287
},
{
"epoch": 0.03,
"learning_rate": 0.000981010101010101,
"loss": 2.0358,
"step": 288
},
{
"epoch": 0.03,
"learning_rate": 0.0009809090909090909,
"loss": 1.939,
"step": 289
},
{
"epoch": 0.03,
"learning_rate": 0.0009808080808080808,
"loss": 1.9883,
"step": 290
},
{
"epoch": 0.03,
"learning_rate": 0.0009807070707070708,
"loss": 2.061,
"step": 291
},
{
"epoch": 0.03,
"learning_rate": 0.0009806060606060607,
"loss": 1.9319,
"step": 292
},
{
"epoch": 0.03,
"learning_rate": 0.0009805050505050507,
"loss": 1.9661,
"step": 293
},
{
"epoch": 0.03,
"learning_rate": 0.0009804040404040404,
"loss": 1.9547,
"step": 294
},
{
"epoch": 0.03,
"learning_rate": 0.0009803030303030303,
"loss": 1.9286,
"step": 295
},
{
"epoch": 0.03,
"learning_rate": 0.0009802020202020203,
"loss": 2.0367,
"step": 296
},
{
"epoch": 0.03,
"learning_rate": 0.0009801010101010102,
"loss": 1.9614,
"step": 297
},
{
"epoch": 0.03,
"learning_rate": 0.00098,
"loss": 1.9543,
"step": 298
},
{
"epoch": 0.03,
"learning_rate": 0.00097989898989899,
"loss": 1.9144,
"step": 299
},
{
"epoch": 0.03,
"learning_rate": 0.0009797979797979799,
"loss": 1.9562,
"step": 300
}
],
"max_steps": 10000,
"num_train_epochs": 9223372036854775807,
"total_flos": 2.88769529654784e+17,
"trial_name": null,
"trial_params": null
}