llama2-7b-legend-annotator / trainer_state.json
ColFeng's picture
v1
a40b59e
raw
history blame contribute delete
No virus
73.8 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.9963099630996313,
"eval_steps": 500,
"global_step": 609,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 1.3157894736842106e-06,
"loss": 1.3628,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 2.631578947368421e-06,
"loss": 1.3486,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 3.9473684210526315e-06,
"loss": 1.4299,
"step": 3
},
{
"epoch": 0.02,
"learning_rate": 5.263157894736842e-06,
"loss": 1.3228,
"step": 4
},
{
"epoch": 0.02,
"learning_rate": 6.578947368421053e-06,
"loss": 1.3087,
"step": 5
},
{
"epoch": 0.03,
"learning_rate": 7.894736842105263e-06,
"loss": 1.1821,
"step": 6
},
{
"epoch": 0.03,
"learning_rate": 9.210526315789474e-06,
"loss": 1.1411,
"step": 7
},
{
"epoch": 0.04,
"learning_rate": 1.0526315789473684e-05,
"loss": 1.1109,
"step": 8
},
{
"epoch": 0.04,
"learning_rate": 1.1842105263157895e-05,
"loss": 1.113,
"step": 9
},
{
"epoch": 0.05,
"learning_rate": 1.3157894736842106e-05,
"loss": 1.0936,
"step": 10
},
{
"epoch": 0.05,
"learning_rate": 1.4473684210526317e-05,
"loss": 1.1008,
"step": 11
},
{
"epoch": 0.06,
"learning_rate": 1.5789473684210526e-05,
"loss": 1.1469,
"step": 12
},
{
"epoch": 0.06,
"learning_rate": 1.7105263157894737e-05,
"loss": 1.0595,
"step": 13
},
{
"epoch": 0.07,
"learning_rate": 1.8421052631578947e-05,
"loss": 1.1116,
"step": 14
},
{
"epoch": 0.07,
"learning_rate": 1.9736842105263158e-05,
"loss": 1.0477,
"step": 15
},
{
"epoch": 0.08,
"learning_rate": 2.105263157894737e-05,
"loss": 1.1064,
"step": 16
},
{
"epoch": 0.08,
"learning_rate": 2.236842105263158e-05,
"loss": 1.1002,
"step": 17
},
{
"epoch": 0.09,
"learning_rate": 2.368421052631579e-05,
"loss": 1.0617,
"step": 18
},
{
"epoch": 0.09,
"learning_rate": 2.5e-05,
"loss": 1.1376,
"step": 19
},
{
"epoch": 0.1,
"learning_rate": 2.499982279551347e-05,
"loss": 1.1213,
"step": 20
},
{
"epoch": 0.1,
"learning_rate": 2.4999291187078104e-05,
"loss": 1.0721,
"step": 21
},
{
"epoch": 0.11,
"learning_rate": 2.4998405189766444e-05,
"loss": 1.0531,
"step": 22
},
{
"epoch": 0.11,
"learning_rate": 2.4997164828698926e-05,
"loss": 1.0651,
"step": 23
},
{
"epoch": 0.12,
"learning_rate": 2.4995570139043158e-05,
"loss": 1.0514,
"step": 24
},
{
"epoch": 0.12,
"learning_rate": 2.4993621166012923e-05,
"loss": 1.1169,
"step": 25
},
{
"epoch": 0.13,
"learning_rate": 2.4991317964866905e-05,
"loss": 1.1252,
"step": 26
},
{
"epoch": 0.13,
"learning_rate": 2.4988660600907115e-05,
"loss": 1.0334,
"step": 27
},
{
"epoch": 0.14,
"learning_rate": 2.4985649149477043e-05,
"loss": 1.0856,
"step": 28
},
{
"epoch": 0.14,
"learning_rate": 2.4982283695959525e-05,
"loss": 1.1015,
"step": 29
},
{
"epoch": 0.15,
"learning_rate": 2.4978564335774313e-05,
"loss": 1.1473,
"step": 30
},
{
"epoch": 0.15,
"learning_rate": 2.4974491174375374e-05,
"loss": 1.0341,
"step": 31
},
{
"epoch": 0.16,
"learning_rate": 2.497006432724791e-05,
"loss": 1.0717,
"step": 32
},
{
"epoch": 0.16,
"learning_rate": 2.4965283919905065e-05,
"loss": 1.0933,
"step": 33
},
{
"epoch": 0.17,
"learning_rate": 2.4960150087884376e-05,
"loss": 1.1277,
"step": 34
},
{
"epoch": 0.17,
"learning_rate": 2.4954662976743944e-05,
"loss": 1.056,
"step": 35
},
{
"epoch": 0.18,
"learning_rate": 2.494882274205827e-05,
"loss": 1.0766,
"step": 36
},
{
"epoch": 0.18,
"learning_rate": 2.4942629549413894e-05,
"loss": 1.1247,
"step": 37
},
{
"epoch": 0.19,
"learning_rate": 2.4936083574404646e-05,
"loss": 1.1544,
"step": 38
},
{
"epoch": 0.19,
"learning_rate": 2.4929185002626714e-05,
"loss": 1.139,
"step": 39
},
{
"epoch": 0.2,
"learning_rate": 2.492193402967336e-05,
"loss": 1.0876,
"step": 40
},
{
"epoch": 0.2,
"learning_rate": 2.4914330861129376e-05,
"loss": 1.1107,
"step": 41
},
{
"epoch": 0.21,
"learning_rate": 2.4906375712565245e-05,
"loss": 1.1297,
"step": 42
},
{
"epoch": 0.21,
"learning_rate": 2.489806880953106e-05,
"loss": 1.1153,
"step": 43
},
{
"epoch": 0.22,
"learning_rate": 2.4889410387550093e-05,
"loss": 1.1108,
"step": 44
},
{
"epoch": 0.22,
"learning_rate": 2.488040069211214e-05,
"loss": 1.1006,
"step": 45
},
{
"epoch": 0.23,
"learning_rate": 2.487103997866655e-05,
"loss": 1.1015,
"step": 46
},
{
"epoch": 0.23,
"learning_rate": 2.4861328512615e-05,
"loss": 1.1215,
"step": 47
},
{
"epoch": 0.24,
"learning_rate": 2.485126656930394e-05,
"loss": 1.1191,
"step": 48
},
{
"epoch": 0.24,
"learning_rate": 2.4840854434016808e-05,
"loss": 1.1129,
"step": 49
},
{
"epoch": 0.25,
"learning_rate": 2.4830092401965942e-05,
"loss": 1.1249,
"step": 50
},
{
"epoch": 0.25,
"learning_rate": 2.4818980778284202e-05,
"loss": 1.119,
"step": 51
},
{
"epoch": 0.26,
"learning_rate": 2.4807519878016313e-05,
"loss": 1.0443,
"step": 52
},
{
"epoch": 0.26,
"learning_rate": 2.4795710026109954e-05,
"loss": 1.078,
"step": 53
},
{
"epoch": 0.27,
"learning_rate": 2.4783551557406515e-05,
"loss": 1.0966,
"step": 54
},
{
"epoch": 0.27,
"learning_rate": 2.4771044816631635e-05,
"loss": 1.1596,
"step": 55
},
{
"epoch": 0.28,
"learning_rate": 2.4758190158385402e-05,
"loss": 1.087,
"step": 56
},
{
"epoch": 0.28,
"learning_rate": 2.4744987947132318e-05,
"loss": 1.121,
"step": 57
},
{
"epoch": 0.29,
"learning_rate": 2.473143855719095e-05,
"loss": 1.1222,
"step": 58
},
{
"epoch": 0.29,
"learning_rate": 2.4717542372723333e-05,
"loss": 1.1292,
"step": 59
},
{
"epoch": 0.3,
"learning_rate": 2.4703299787724065e-05,
"loss": 1.1314,
"step": 60
},
{
"epoch": 0.3,
"learning_rate": 2.468871120600913e-05,
"loss": 1.1266,
"step": 61
},
{
"epoch": 0.31,
"learning_rate": 2.4673777041204478e-05,
"loss": 1.1486,
"step": 62
},
{
"epoch": 0.31,
"learning_rate": 2.465849771673427e-05,
"loss": 1.0973,
"step": 63
},
{
"epoch": 0.31,
"learning_rate": 2.4642873665808873e-05,
"loss": 1.145,
"step": 64
},
{
"epoch": 0.32,
"learning_rate": 2.4626905331412608e-05,
"loss": 1.1104,
"step": 65
},
{
"epoch": 0.32,
"learning_rate": 2.4610593166291143e-05,
"loss": 1.0877,
"step": 66
},
{
"epoch": 0.33,
"learning_rate": 2.4593937632938695e-05,
"loss": 1.0961,
"step": 67
},
{
"epoch": 0.33,
"learning_rate": 2.457693920358491e-05,
"loss": 1.0783,
"step": 68
},
{
"epoch": 0.34,
"learning_rate": 2.455959836018145e-05,
"loss": 1.0869,
"step": 69
},
{
"epoch": 0.34,
"learning_rate": 2.454191559438836e-05,
"loss": 1.1227,
"step": 70
},
{
"epoch": 0.35,
"learning_rate": 2.4523891407560107e-05,
"loss": 1.0735,
"step": 71
},
{
"epoch": 0.35,
"learning_rate": 2.4505526310731376e-05,
"loss": 1.1002,
"step": 72
},
{
"epoch": 0.36,
"learning_rate": 2.448682082460257e-05,
"loss": 1.1313,
"step": 73
},
{
"epoch": 0.36,
"learning_rate": 2.446777547952507e-05,
"loss": 1.1208,
"step": 74
},
{
"epoch": 0.37,
"learning_rate": 2.4448390815486165e-05,
"loss": 1.1212,
"step": 75
},
{
"epoch": 0.37,
"learning_rate": 2.4428667382093762e-05,
"loss": 1.1048,
"step": 76
},
{
"epoch": 0.38,
"learning_rate": 2.440860573856081e-05,
"loss": 1.1089,
"step": 77
},
{
"epoch": 0.38,
"learning_rate": 2.438820645368942e-05,
"loss": 1.1081,
"step": 78
},
{
"epoch": 0.39,
"learning_rate": 2.4367470105854766e-05,
"loss": 1.0935,
"step": 79
},
{
"epoch": 0.39,
"learning_rate": 2.4346397282988666e-05,
"loss": 1.0858,
"step": 80
},
{
"epoch": 0.4,
"learning_rate": 2.432498858256292e-05,
"loss": 1.0944,
"step": 81
},
{
"epoch": 0.4,
"learning_rate": 2.4303244611572372e-05,
"loss": 1.0921,
"step": 82
},
{
"epoch": 0.41,
"learning_rate": 2.4281165986517696e-05,
"loss": 1.1146,
"step": 83
},
{
"epoch": 0.41,
"learning_rate": 2.425875333338792e-05,
"loss": 1.0932,
"step": 84
},
{
"epoch": 0.42,
"learning_rate": 2.4236007287642664e-05,
"loss": 1.0857,
"step": 85
},
{
"epoch": 0.42,
"learning_rate": 2.421292849419416e-05,
"loss": 1.0615,
"step": 86
},
{
"epoch": 0.43,
"learning_rate": 2.4189517607388918e-05,
"loss": 1.0923,
"step": 87
},
{
"epoch": 0.43,
"learning_rate": 2.416577529098921e-05,
"loss": 1.1382,
"step": 88
},
{
"epoch": 0.44,
"learning_rate": 2.4141702218154232e-05,
"loss": 1.1798,
"step": 89
},
{
"epoch": 0.44,
"learning_rate": 2.4117299071421023e-05,
"loss": 1.1104,
"step": 90
},
{
"epoch": 0.45,
"learning_rate": 2.4092566542685123e-05,
"loss": 1.1011,
"step": 91
},
{
"epoch": 0.45,
"learning_rate": 2.4067505333180938e-05,
"loss": 1.0925,
"step": 92
},
{
"epoch": 0.46,
"learning_rate": 2.404211615346187e-05,
"loss": 1.1313,
"step": 93
},
{
"epoch": 0.46,
"learning_rate": 2.401639972338016e-05,
"loss": 1.0656,
"step": 94
},
{
"epoch": 0.47,
"learning_rate": 2.399035677206651e-05,
"loss": 1.1277,
"step": 95
},
{
"epoch": 0.47,
"learning_rate": 2.396398803790936e-05,
"loss": 1.1044,
"step": 96
},
{
"epoch": 0.48,
"learning_rate": 2.393729426853399e-05,
"loss": 1.0957,
"step": 97
},
{
"epoch": 0.48,
"learning_rate": 2.3910276220781314e-05,
"loss": 1.0594,
"step": 98
},
{
"epoch": 0.49,
"learning_rate": 2.3882934660686418e-05,
"loss": 1.1278,
"step": 99
},
{
"epoch": 0.49,
"learning_rate": 2.3855270363456833e-05,
"loss": 1.0847,
"step": 100
},
{
"epoch": 0.5,
"learning_rate": 2.382728411345058e-05,
"loss": 1.1694,
"step": 101
},
{
"epoch": 0.5,
"learning_rate": 2.3798976704153906e-05,
"loss": 1.1414,
"step": 102
},
{
"epoch": 0.51,
"learning_rate": 2.3770348938158805e-05,
"loss": 1.0949,
"step": 103
},
{
"epoch": 0.51,
"learning_rate": 2.3741401627140242e-05,
"loss": 1.1151,
"step": 104
},
{
"epoch": 0.52,
"learning_rate": 2.371213559183316e-05,
"loss": 1.0679,
"step": 105
},
{
"epoch": 0.52,
"learning_rate": 2.3682551662009203e-05,
"loss": 1.1304,
"step": 106
},
{
"epoch": 0.53,
"learning_rate": 2.3652650676453188e-05,
"loss": 1.1176,
"step": 107
},
{
"epoch": 0.53,
"learning_rate": 2.362243348293931e-05,
"loss": 1.0294,
"step": 108
},
{
"epoch": 0.54,
"learning_rate": 2.3591900938207147e-05,
"loss": 1.1691,
"step": 109
},
{
"epoch": 0.54,
"learning_rate": 2.3561053907937315e-05,
"loss": 1.0793,
"step": 110
},
{
"epoch": 0.55,
"learning_rate": 2.352989326672696e-05,
"loss": 1.0782,
"step": 111
},
{
"epoch": 0.55,
"learning_rate": 2.349841989806495e-05,
"loss": 1.0712,
"step": 112
},
{
"epoch": 0.56,
"learning_rate": 2.346663469430683e-05,
"loss": 1.1301,
"step": 113
},
{
"epoch": 0.56,
"learning_rate": 2.3434538556649515e-05,
"loss": 1.1725,
"step": 114
},
{
"epoch": 0.57,
"learning_rate": 2.3402132395105737e-05,
"loss": 1.1134,
"step": 115
},
{
"epoch": 0.57,
"learning_rate": 2.336941712847825e-05,
"loss": 1.1455,
"step": 116
},
{
"epoch": 0.58,
"learning_rate": 2.3336393684333778e-05,
"loss": 1.1175,
"step": 117
},
{
"epoch": 0.58,
"learning_rate": 2.3303062998976712e-05,
"loss": 1.1114,
"step": 118
},
{
"epoch": 0.59,
"learning_rate": 2.3269426017422576e-05,
"loss": 1.1064,
"step": 119
},
{
"epoch": 0.59,
"learning_rate": 2.3235483693371214e-05,
"loss": 1.0249,
"step": 120
},
{
"epoch": 0.6,
"learning_rate": 2.3201236989179766e-05,
"loss": 1.0759,
"step": 121
},
{
"epoch": 0.6,
"learning_rate": 2.3166686875835365e-05,
"loss": 1.0937,
"step": 122
},
{
"epoch": 0.61,
"learning_rate": 2.313183433292764e-05,
"loss": 1.1164,
"step": 123
},
{
"epoch": 0.61,
"learning_rate": 2.3096680348620886e-05,
"loss": 1.1097,
"step": 124
},
{
"epoch": 0.62,
"learning_rate": 2.3061225919626124e-05,
"loss": 1.1287,
"step": 125
},
{
"epoch": 0.62,
"learning_rate": 2.3025472051172755e-05,
"loss": 1.1137,
"step": 126
},
{
"epoch": 0.62,
"learning_rate": 2.2989419756980134e-05,
"loss": 1.1086,
"step": 127
},
{
"epoch": 0.63,
"learning_rate": 2.295307005922879e-05,
"loss": 1.0967,
"step": 128
},
{
"epoch": 0.63,
"learning_rate": 2.2916423988531437e-05,
"loss": 1.1077,
"step": 129
},
{
"epoch": 0.64,
"learning_rate": 2.2879482583903783e-05,
"loss": 1.1341,
"step": 130
},
{
"epoch": 0.64,
"learning_rate": 2.2842246892735053e-05,
"loss": 1.106,
"step": 131
},
{
"epoch": 0.65,
"learning_rate": 2.2804717970758286e-05,
"loss": 1.1166,
"step": 132
},
{
"epoch": 0.65,
"learning_rate": 2.2766896882020422e-05,
"loss": 1.1153,
"step": 133
},
{
"epoch": 0.66,
"learning_rate": 2.2728784698852114e-05,
"loss": 1.0829,
"step": 134
},
{
"epoch": 0.66,
"learning_rate": 2.2690382501837344e-05,
"loss": 1.1223,
"step": 135
},
{
"epoch": 0.67,
"learning_rate": 2.2651691379782764e-05,
"loss": 1.0744,
"step": 136
},
{
"epoch": 0.67,
"learning_rate": 2.2612712429686845e-05,
"loss": 1.0786,
"step": 137
},
{
"epoch": 0.68,
"learning_rate": 2.2573446756708754e-05,
"loss": 1.1594,
"step": 138
},
{
"epoch": 0.68,
"learning_rate": 2.2533895474137047e-05,
"loss": 1.0879,
"step": 139
},
{
"epoch": 0.69,
"learning_rate": 2.2494059703358073e-05,
"loss": 1.1591,
"step": 140
},
{
"epoch": 0.69,
"learning_rate": 2.24539405738242e-05,
"loss": 1.1975,
"step": 141
},
{
"epoch": 0.7,
"learning_rate": 2.2413539223021794e-05,
"loss": 1.0487,
"step": 142
},
{
"epoch": 0.7,
"learning_rate": 2.237285679643895e-05,
"loss": 1.1051,
"step": 143
},
{
"epoch": 0.71,
"learning_rate": 2.2331894447533035e-05,
"loss": 1.1266,
"step": 144
},
{
"epoch": 0.71,
"learning_rate": 2.229065333769796e-05,
"loss": 1.0445,
"step": 145
},
{
"epoch": 0.72,
"learning_rate": 2.2249134636231285e-05,
"loss": 1.0915,
"step": 146
},
{
"epoch": 0.72,
"learning_rate": 2.2207339520301033e-05,
"loss": 1.1328,
"step": 147
},
{
"epoch": 0.73,
"learning_rate": 2.216526917491234e-05,
"loss": 1.1179,
"step": 148
},
{
"epoch": 0.73,
"learning_rate": 2.2122924792873827e-05,
"loss": 1.0199,
"step": 149
},
{
"epoch": 0.74,
"learning_rate": 2.2080307574763824e-05,
"loss": 1.1108,
"step": 150
},
{
"epoch": 0.74,
"learning_rate": 2.2037418728896282e-05,
"loss": 1.1442,
"step": 151
},
{
"epoch": 0.75,
"learning_rate": 2.1994259471286545e-05,
"loss": 1.1125,
"step": 152
},
{
"epoch": 0.75,
"learning_rate": 2.1950831025616873e-05,
"loss": 1.1047,
"step": 153
},
{
"epoch": 0.76,
"learning_rate": 2.190713462320173e-05,
"loss": 1.1058,
"step": 154
},
{
"epoch": 0.76,
"learning_rate": 2.186317150295289e-05,
"loss": 1.027,
"step": 155
},
{
"epoch": 0.77,
"learning_rate": 2.1818942911344283e-05,
"loss": 1.1007,
"step": 156
},
{
"epoch": 0.77,
"learning_rate": 2.17744501023767e-05,
"loss": 1.0835,
"step": 157
},
{
"epoch": 0.78,
"learning_rate": 2.1729694337542196e-05,
"loss": 1.1269,
"step": 158
},
{
"epoch": 0.78,
"learning_rate": 2.168467688578834e-05,
"loss": 1.1548,
"step": 159
},
{
"epoch": 0.79,
"learning_rate": 2.163939902348225e-05,
"loss": 1.0896,
"step": 160
},
{
"epoch": 0.79,
"learning_rate": 2.1593862034374365e-05,
"loss": 1.1175,
"step": 161
},
{
"epoch": 0.8,
"learning_rate": 2.15480672095621e-05,
"loss": 1.0988,
"step": 162
},
{
"epoch": 0.8,
"learning_rate": 2.15020158474532e-05,
"loss": 1.1124,
"step": 163
},
{
"epoch": 0.81,
"learning_rate": 2.145570925372894e-05,
"loss": 1.0722,
"step": 164
},
{
"epoch": 0.81,
"learning_rate": 2.1409148741307107e-05,
"loss": 1.0978,
"step": 165
},
{
"epoch": 0.82,
"learning_rate": 2.1362335630304768e-05,
"loss": 1.0294,
"step": 166
},
{
"epoch": 0.82,
"learning_rate": 2.131527124800086e-05,
"loss": 1.0917,
"step": 167
},
{
"epoch": 0.83,
"learning_rate": 2.1267956928798525e-05,
"loss": 1.0315,
"step": 168
},
{
"epoch": 0.83,
"learning_rate": 2.1220394014187312e-05,
"loss": 1.0825,
"step": 169
},
{
"epoch": 0.84,
"learning_rate": 2.1172583852705115e-05,
"loss": 1.1014,
"step": 170
},
{
"epoch": 0.84,
"learning_rate": 2.1124527799899953e-05,
"loss": 1.0582,
"step": 171
},
{
"epoch": 0.85,
"learning_rate": 2.1076227218291535e-05,
"loss": 1.0917,
"step": 172
},
{
"epoch": 0.85,
"learning_rate": 2.1027683477332623e-05,
"loss": 1.0564,
"step": 173
},
{
"epoch": 0.86,
"learning_rate": 2.0978897953370204e-05,
"loss": 1.0999,
"step": 174
},
{
"epoch": 0.86,
"learning_rate": 2.0929872029606472e-05,
"loss": 1.1015,
"step": 175
},
{
"epoch": 0.87,
"learning_rate": 2.088060709605962e-05,
"loss": 1.0807,
"step": 176
},
{
"epoch": 0.87,
"learning_rate": 2.08311045495244e-05,
"loss": 1.0348,
"step": 177
},
{
"epoch": 0.88,
"learning_rate": 2.078136579353255e-05,
"loss": 1.0644,
"step": 178
},
{
"epoch": 0.88,
"learning_rate": 2.0731392238312985e-05,
"loss": 1.0882,
"step": 179
},
{
"epoch": 0.89,
"learning_rate": 2.0681185300751814e-05,
"loss": 1.109,
"step": 180
},
{
"epoch": 0.89,
"learning_rate": 2.0630746404352168e-05,
"loss": 1.1298,
"step": 181
},
{
"epoch": 0.9,
"learning_rate": 2.058007697919386e-05,
"loss": 1.0834,
"step": 182
},
{
"epoch": 0.9,
"learning_rate": 2.0529178461892785e-05,
"loss": 1.0839,
"step": 183
},
{
"epoch": 0.91,
"learning_rate": 2.0478052295560253e-05,
"loss": 1.1053,
"step": 184
},
{
"epoch": 0.91,
"learning_rate": 2.0426699929762035e-05,
"loss": 1.0968,
"step": 185
},
{
"epoch": 0.92,
"learning_rate": 2.037512282047726e-05,
"loss": 1.0399,
"step": 186
},
{
"epoch": 0.92,
"learning_rate": 2.0323322430057166e-05,
"loss": 1.1565,
"step": 187
},
{
"epoch": 0.92,
"learning_rate": 2.0271300227183598e-05,
"loss": 1.103,
"step": 188
},
{
"epoch": 0.93,
"learning_rate": 2.02190576868274e-05,
"loss": 1.0688,
"step": 189
},
{
"epoch": 0.93,
"learning_rate": 2.016659629020658e-05,
"loss": 1.0667,
"step": 190
},
{
"epoch": 0.94,
"learning_rate": 2.0113917524744308e-05,
"loss": 1.1085,
"step": 191
},
{
"epoch": 0.94,
"learning_rate": 2.0061022884026762e-05,
"loss": 1.085,
"step": 192
},
{
"epoch": 0.95,
"learning_rate": 2.0007913867760763e-05,
"loss": 1.0716,
"step": 193
},
{
"epoch": 0.95,
"learning_rate": 1.995459198173127e-05,
"loss": 1.1282,
"step": 194
},
{
"epoch": 0.96,
"learning_rate": 1.9901058737758667e-05,
"loss": 1.1367,
"step": 195
},
{
"epoch": 0.96,
"learning_rate": 1.9847315653655915e-05,
"loss": 1.08,
"step": 196
},
{
"epoch": 0.97,
"learning_rate": 1.9793364253185518e-05,
"loss": 1.1025,
"step": 197
},
{
"epoch": 0.97,
"learning_rate": 1.9739206066016307e-05,
"loss": 1.0882,
"step": 198
},
{
"epoch": 0.98,
"learning_rate": 1.9684842627680088e-05,
"loss": 1.1219,
"step": 199
},
{
"epoch": 0.98,
"learning_rate": 1.963027547952808e-05,
"loss": 1.0971,
"step": 200
},
{
"epoch": 0.99,
"learning_rate": 1.9575506168687247e-05,
"loss": 1.0991,
"step": 201
},
{
"epoch": 0.99,
"learning_rate": 1.9520536248016403e-05,
"loss": 1.0028,
"step": 202
},
{
"epoch": 1.0,
"learning_rate": 1.946536727606219e-05,
"loss": 1.0726,
"step": 203
},
{
"epoch": 1.0,
"learning_rate": 1.941000081701492e-05,
"loss": 0.8409,
"step": 204
},
{
"epoch": 1.01,
"learning_rate": 1.9354438440664167e-05,
"loss": 0.7279,
"step": 205
},
{
"epoch": 1.01,
"learning_rate": 1.929868172235433e-05,
"loss": 0.6879,
"step": 206
},
{
"epoch": 1.02,
"learning_rate": 1.9242732242939893e-05,
"loss": 0.6526,
"step": 207
},
{
"epoch": 1.02,
"learning_rate": 1.9186591588740667e-05,
"loss": 0.6945,
"step": 208
},
{
"epoch": 1.03,
"learning_rate": 1.913026135149678e-05,
"loss": 0.6871,
"step": 209
},
{
"epoch": 1.03,
"learning_rate": 1.9073743128323558e-05,
"loss": 0.6716,
"step": 210
},
{
"epoch": 1.04,
"learning_rate": 1.9017038521666232e-05,
"loss": 0.7348,
"step": 211
},
{
"epoch": 1.04,
"learning_rate": 1.8960149139254513e-05,
"loss": 0.6692,
"step": 212
},
{
"epoch": 1.05,
"learning_rate": 1.8903076594057013e-05,
"loss": 0.6319,
"step": 213
},
{
"epoch": 1.05,
"learning_rate": 1.88458225042355e-05,
"loss": 0.6803,
"step": 214
},
{
"epoch": 1.06,
"learning_rate": 1.8788388493099033e-05,
"loss": 0.6941,
"step": 215
},
{
"epoch": 1.06,
"learning_rate": 1.8730776189057918e-05,
"loss": 0.702,
"step": 216
},
{
"epoch": 1.07,
"learning_rate": 1.8672987225577552e-05,
"loss": 0.7123,
"step": 217
},
{
"epoch": 1.07,
"learning_rate": 1.8615023241132127e-05,
"loss": 0.6531,
"step": 218
},
{
"epoch": 1.08,
"learning_rate": 1.855688587915813e-05,
"loss": 0.6997,
"step": 219
},
{
"epoch": 1.08,
"learning_rate": 1.8498576788007775e-05,
"loss": 0.706,
"step": 220
},
{
"epoch": 1.09,
"learning_rate": 1.8440097620902284e-05,
"loss": 0.6839,
"step": 221
},
{
"epoch": 1.09,
"learning_rate": 1.838145003588497e-05,
"loss": 0.6981,
"step": 222
},
{
"epoch": 1.1,
"learning_rate": 1.832263569577427e-05,
"loss": 0.6168,
"step": 223
},
{
"epoch": 1.1,
"learning_rate": 1.8263656268116576e-05,
"loss": 0.6331,
"step": 224
},
{
"epoch": 1.11,
"learning_rate": 1.8204513425138952e-05,
"loss": 0.6864,
"step": 225
},
{
"epoch": 1.11,
"learning_rate": 1.8145208843701742e-05,
"loss": 0.7184,
"step": 226
},
{
"epoch": 1.12,
"learning_rate": 1.808574420525101e-05,
"loss": 0.6272,
"step": 227
},
{
"epoch": 1.12,
"learning_rate": 1.8026121195770874e-05,
"loss": 0.61,
"step": 228
},
{
"epoch": 1.13,
"learning_rate": 1.7966341505735695e-05,
"loss": 0.6583,
"step": 229
},
{
"epoch": 1.13,
"learning_rate": 1.7906406830062156e-05,
"loss": 0.6503,
"step": 230
},
{
"epoch": 1.14,
"learning_rate": 1.7846318868061212e-05,
"loss": 0.6473,
"step": 231
},
{
"epoch": 1.14,
"learning_rate": 1.7786079323389893e-05,
"loss": 0.658,
"step": 232
},
{
"epoch": 1.15,
"learning_rate": 1.7725689904003006e-05,
"loss": 0.6683,
"step": 233
},
{
"epoch": 1.15,
"learning_rate": 1.766515232210473e-05,
"loss": 0.6576,
"step": 234
},
{
"epoch": 1.16,
"learning_rate": 1.7604468294100034e-05,
"loss": 0.7206,
"step": 235
},
{
"epoch": 1.16,
"learning_rate": 1.754363954054605e-05,
"loss": 0.6805,
"step": 236
},
{
"epoch": 1.17,
"learning_rate": 1.7482667786103256e-05,
"loss": 0.6856,
"step": 237
},
{
"epoch": 1.17,
"learning_rate": 1.7421554759486614e-05,
"loss": 0.6346,
"step": 238
},
{
"epoch": 1.18,
"learning_rate": 1.736030219341651e-05,
"loss": 0.6842,
"step": 239
},
{
"epoch": 1.18,
"learning_rate": 1.7298911824569676e-05,
"loss": 0.6696,
"step": 240
},
{
"epoch": 1.19,
"learning_rate": 1.7237385393529916e-05,
"loss": 0.6832,
"step": 241
},
{
"epoch": 1.19,
"learning_rate": 1.7175724644738773e-05,
"loss": 0.6993,
"step": 242
},
{
"epoch": 1.2,
"learning_rate": 1.7113931326446054e-05,
"loss": 0.7059,
"step": 243
},
{
"epoch": 1.2,
"learning_rate": 1.705200719066028e-05,
"loss": 0.7253,
"step": 244
},
{
"epoch": 1.21,
"learning_rate": 1.6989953993098998e-05,
"loss": 0.6968,
"step": 245
},
{
"epoch": 1.21,
"learning_rate": 1.6927773493139014e-05,
"loss": 0.6491,
"step": 246
},
{
"epoch": 1.22,
"learning_rate": 1.68654674537665e-05,
"loss": 0.6645,
"step": 247
},
{
"epoch": 1.22,
"learning_rate": 1.6803037641527002e-05,
"loss": 0.6346,
"step": 248
},
{
"epoch": 1.23,
"learning_rate": 1.674048582647538e-05,
"loss": 0.7157,
"step": 249
},
{
"epoch": 1.23,
"learning_rate": 1.6677813782125592e-05,
"loss": 0.7311,
"step": 250
},
{
"epoch": 1.23,
"learning_rate": 1.6615023285400432e-05,
"loss": 0.6516,
"step": 251
},
{
"epoch": 1.24,
"learning_rate": 1.6552116116581133e-05,
"loss": 0.6617,
"step": 252
},
{
"epoch": 1.24,
"learning_rate": 1.648909405925691e-05,
"loss": 0.6757,
"step": 253
},
{
"epoch": 1.25,
"learning_rate": 1.6425958900274362e-05,
"loss": 0.6776,
"step": 254
},
{
"epoch": 1.25,
"learning_rate": 1.6362712429686846e-05,
"loss": 0.6525,
"step": 255
},
{
"epoch": 1.26,
"learning_rate": 1.629935644070369e-05,
"loss": 0.6695,
"step": 256
},
{
"epoch": 1.26,
"learning_rate": 1.6235892729639378e-05,
"loss": 0.6625,
"step": 257
},
{
"epoch": 1.27,
"learning_rate": 1.617232309586261e-05,
"loss": 0.6569,
"step": 258
},
{
"epoch": 1.27,
"learning_rate": 1.6108649341745262e-05,
"loss": 0.7276,
"step": 259
},
{
"epoch": 1.28,
"learning_rate": 1.604487327261133e-05,
"loss": 0.7187,
"step": 260
},
{
"epoch": 1.28,
"learning_rate": 1.59809966966857e-05,
"loss": 0.693,
"step": 261
},
{
"epoch": 1.29,
"learning_rate": 1.591702142504291e-05,
"loss": 0.6845,
"step": 262
},
{
"epoch": 1.29,
"learning_rate": 1.5852949271555787e-05,
"loss": 0.6641,
"step": 263
},
{
"epoch": 1.3,
"learning_rate": 1.5788782052844015e-05,
"loss": 0.6816,
"step": 264
},
{
"epoch": 1.3,
"learning_rate": 1.572452158822265e-05,
"loss": 0.6962,
"step": 265
},
{
"epoch": 1.31,
"learning_rate": 1.5660169699650503e-05,
"loss": 0.6748,
"step": 266
},
{
"epoch": 1.31,
"learning_rate": 1.5595728211678525e-05,
"loss": 0.7169,
"step": 267
},
{
"epoch": 1.32,
"learning_rate": 1.553119895139803e-05,
"loss": 0.6708,
"step": 268
},
{
"epoch": 1.32,
"learning_rate": 1.546658374838894e-05,
"loss": 0.6961,
"step": 269
},
{
"epoch": 1.33,
"learning_rate": 1.5401884434667864e-05,
"loss": 0.6814,
"step": 270
},
{
"epoch": 1.33,
"learning_rate": 1.5337102844636188e-05,
"loss": 0.6701,
"step": 271
},
{
"epoch": 1.34,
"learning_rate": 1.5272240815028067e-05,
"loss": 0.678,
"step": 272
},
{
"epoch": 1.34,
"learning_rate": 1.520730018485832e-05,
"loss": 0.7226,
"step": 273
},
{
"epoch": 1.35,
"learning_rate": 1.5142282795370305e-05,
"loss": 0.712,
"step": 274
},
{
"epoch": 1.35,
"learning_rate": 1.5077190489983728e-05,
"loss": 0.7174,
"step": 275
},
{
"epoch": 1.36,
"learning_rate": 1.5012025114242355e-05,
"loss": 0.697,
"step": 276
},
{
"epoch": 1.36,
"learning_rate": 1.49467885157617e-05,
"loss": 0.6919,
"step": 277
},
{
"epoch": 1.37,
"learning_rate": 1.4881482544176627e-05,
"loss": 0.7013,
"step": 278
},
{
"epoch": 1.37,
"learning_rate": 1.4816109051088931e-05,
"loss": 0.672,
"step": 279
},
{
"epoch": 1.38,
"learning_rate": 1.4750669890014807e-05,
"loss": 0.6643,
"step": 280
},
{
"epoch": 1.38,
"learning_rate": 1.468516691633233e-05,
"loss": 0.7121,
"step": 281
},
{
"epoch": 1.39,
"learning_rate": 1.4619601987228832e-05,
"loss": 0.7121,
"step": 282
},
{
"epoch": 1.39,
"learning_rate": 1.4553976961648244e-05,
"loss": 0.7016,
"step": 283
},
{
"epoch": 1.4,
"learning_rate": 1.4488293700238401e-05,
"loss": 0.6935,
"step": 284
},
{
"epoch": 1.4,
"learning_rate": 1.4422554065298286e-05,
"loss": 0.6644,
"step": 285
},
{
"epoch": 1.41,
"learning_rate": 1.435675992072521e-05,
"loss": 0.6634,
"step": 286
},
{
"epoch": 1.41,
"learning_rate": 1.4290913131961997e-05,
"loss": 0.6848,
"step": 287
},
{
"epoch": 1.42,
"learning_rate": 1.4225015565944072e-05,
"loss": 0.7342,
"step": 288
},
{
"epoch": 1.42,
"learning_rate": 1.4159069091046526e-05,
"loss": 0.7043,
"step": 289
},
{
"epoch": 1.43,
"learning_rate": 1.4093075577031157e-05,
"loss": 0.6844,
"step": 290
},
{
"epoch": 1.43,
"learning_rate": 1.4027036894993442e-05,
"loss": 0.7029,
"step": 291
},
{
"epoch": 1.44,
"learning_rate": 1.396095491730951e-05,
"loss": 0.6458,
"step": 292
},
{
"epoch": 1.44,
"learning_rate": 1.3894831517583017e-05,
"loss": 0.6892,
"step": 293
},
{
"epoch": 1.45,
"learning_rate": 1.3828668570592069e-05,
"loss": 0.6533,
"step": 294
},
{
"epoch": 1.45,
"learning_rate": 1.3762467952236027e-05,
"loss": 0.6618,
"step": 295
},
{
"epoch": 1.46,
"learning_rate": 1.369623153948235e-05,
"loss": 0.7309,
"step": 296
},
{
"epoch": 1.46,
"learning_rate": 1.3629961210313353e-05,
"loss": 0.6675,
"step": 297
},
{
"epoch": 1.47,
"learning_rate": 1.3563658843672985e-05,
"loss": 0.7065,
"step": 298
},
{
"epoch": 1.47,
"learning_rate": 1.3497326319413539e-05,
"loss": 0.6495,
"step": 299
},
{
"epoch": 1.48,
"learning_rate": 1.3430965518242362e-05,
"loss": 0.6695,
"step": 300
},
{
"epoch": 1.48,
"learning_rate": 1.336457832166852e-05,
"loss": 0.7005,
"step": 301
},
{
"epoch": 1.49,
"learning_rate": 1.3298166611949467e-05,
"loss": 0.7049,
"step": 302
},
{
"epoch": 1.49,
"learning_rate": 1.3231732272037672e-05,
"loss": 0.6695,
"step": 303
},
{
"epoch": 1.5,
"learning_rate": 1.3165277185527234e-05,
"loss": 0.6984,
"step": 304
},
{
"epoch": 1.5,
"learning_rate": 1.3098803236600462e-05,
"loss": 0.6445,
"step": 305
},
{
"epoch": 1.51,
"learning_rate": 1.3032312309974482e-05,
"loss": 0.674,
"step": 306
},
{
"epoch": 1.51,
"learning_rate": 1.2965806290847768e-05,
"loss": 0.6703,
"step": 307
},
{
"epoch": 1.52,
"learning_rate": 1.2899287064846725e-05,
"loss": 0.6647,
"step": 308
},
{
"epoch": 1.52,
"learning_rate": 1.2832756517972185e-05,
"loss": 0.6637,
"step": 309
},
{
"epoch": 1.53,
"learning_rate": 1.2766216536545984e-05,
"loss": 0.6944,
"step": 310
},
{
"epoch": 1.53,
"learning_rate": 1.2699669007157435e-05,
"loss": 0.6246,
"step": 311
},
{
"epoch": 1.54,
"learning_rate": 1.2633115816609867e-05,
"loss": 0.6816,
"step": 312
},
{
"epoch": 1.54,
"learning_rate": 1.2566558851867106e-05,
"loss": 0.628,
"step": 313
},
{
"epoch": 1.54,
"learning_rate": 1.25e-05,
"loss": 0.6668,
"step": 314
},
{
"epoch": 1.55,
"learning_rate": 1.2433441148132897e-05,
"loss": 0.6779,
"step": 315
},
{
"epoch": 1.55,
"learning_rate": 1.236688418339014e-05,
"loss": 0.6325,
"step": 316
},
{
"epoch": 1.56,
"learning_rate": 1.2300330992842566e-05,
"loss": 0.6418,
"step": 317
},
{
"epoch": 1.56,
"learning_rate": 1.223378346345402e-05,
"loss": 0.6853,
"step": 318
},
{
"epoch": 1.57,
"learning_rate": 1.2167243482027816e-05,
"loss": 0.6517,
"step": 319
},
{
"epoch": 1.57,
"learning_rate": 1.2100712935153283e-05,
"loss": 0.6686,
"step": 320
},
{
"epoch": 1.58,
"learning_rate": 1.2034193709152231e-05,
"loss": 0.6647,
"step": 321
},
{
"epoch": 1.58,
"learning_rate": 1.196768769002552e-05,
"loss": 0.7095,
"step": 322
},
{
"epoch": 1.59,
"learning_rate": 1.190119676339954e-05,
"loss": 0.65,
"step": 323
},
{
"epoch": 1.59,
"learning_rate": 1.1834722814472771e-05,
"loss": 0.6796,
"step": 324
},
{
"epoch": 1.6,
"learning_rate": 1.1768267727962328e-05,
"loss": 0.6685,
"step": 325
},
{
"epoch": 1.6,
"learning_rate": 1.1701833388050536e-05,
"loss": 0.6913,
"step": 326
},
{
"epoch": 1.61,
"learning_rate": 1.1635421678331485e-05,
"loss": 0.7266,
"step": 327
},
{
"epoch": 1.61,
"learning_rate": 1.1569034481757644e-05,
"loss": 0.6682,
"step": 328
},
{
"epoch": 1.62,
"learning_rate": 1.150267368058646e-05,
"loss": 0.6643,
"step": 329
},
{
"epoch": 1.62,
"learning_rate": 1.1436341156327016e-05,
"loss": 0.6984,
"step": 330
},
{
"epoch": 1.63,
"learning_rate": 1.137003878968665e-05,
"loss": 0.6792,
"step": 331
},
{
"epoch": 1.63,
"learning_rate": 1.1303768460517657e-05,
"loss": 0.7129,
"step": 332
},
{
"epoch": 1.64,
"learning_rate": 1.1237532047763974e-05,
"loss": 0.6972,
"step": 333
},
{
"epoch": 1.64,
"learning_rate": 1.1171331429407934e-05,
"loss": 0.6692,
"step": 334
},
{
"epoch": 1.65,
"learning_rate": 1.1105168482416984e-05,
"loss": 0.6335,
"step": 335
},
{
"epoch": 1.65,
"learning_rate": 1.1039045082690496e-05,
"loss": 0.6787,
"step": 336
},
{
"epoch": 1.66,
"learning_rate": 1.0972963105006556e-05,
"loss": 0.6626,
"step": 337
},
{
"epoch": 1.66,
"learning_rate": 1.0906924422968846e-05,
"loss": 0.67,
"step": 338
},
{
"epoch": 1.67,
"learning_rate": 1.0840930908953477e-05,
"loss": 0.6307,
"step": 339
},
{
"epoch": 1.67,
"learning_rate": 1.0774984434055932e-05,
"loss": 0.6691,
"step": 340
},
{
"epoch": 1.68,
"learning_rate": 1.0709086868038005e-05,
"loss": 0.6772,
"step": 341
},
{
"epoch": 1.68,
"learning_rate": 1.064324007927479e-05,
"loss": 0.6846,
"step": 342
},
{
"epoch": 1.69,
"learning_rate": 1.0577445934701717e-05,
"loss": 0.6568,
"step": 343
},
{
"epoch": 1.69,
"learning_rate": 1.0511706299761602e-05,
"loss": 0.7119,
"step": 344
},
{
"epoch": 1.7,
"learning_rate": 1.044602303835176e-05,
"loss": 0.6945,
"step": 345
},
{
"epoch": 1.7,
"learning_rate": 1.0380398012771169e-05,
"loss": 0.6954,
"step": 346
},
{
"epoch": 1.71,
"learning_rate": 1.0314833083667672e-05,
"loss": 0.6703,
"step": 347
},
{
"epoch": 1.71,
"learning_rate": 1.0249330109985198e-05,
"loss": 0.6854,
"step": 348
},
{
"epoch": 1.72,
"learning_rate": 1.0183890948911074e-05,
"loss": 0.6929,
"step": 349
},
{
"epoch": 1.72,
"learning_rate": 1.0118517455823374e-05,
"loss": 0.7106,
"step": 350
},
{
"epoch": 1.73,
"learning_rate": 1.0053211484238303e-05,
"loss": 0.7181,
"step": 351
},
{
"epoch": 1.73,
"learning_rate": 9.987974885757647e-06,
"loss": 0.691,
"step": 352
},
{
"epoch": 1.74,
"learning_rate": 9.922809510016277e-06,
"loss": 0.6584,
"step": 353
},
{
"epoch": 1.74,
"learning_rate": 9.857717204629696e-06,
"loss": 0.6575,
"step": 354
},
{
"epoch": 1.75,
"learning_rate": 9.792699815141685e-06,
"loss": 0.6865,
"step": 355
},
{
"epoch": 1.75,
"learning_rate": 9.727759184971936e-06,
"loss": 0.6692,
"step": 356
},
{
"epoch": 1.76,
"learning_rate": 9.662897155363814e-06,
"loss": 0.7082,
"step": 357
},
{
"epoch": 1.76,
"learning_rate": 9.598115565332142e-06,
"loss": 0.6894,
"step": 358
},
{
"epoch": 1.77,
"learning_rate": 9.533416251611064e-06,
"loss": 0.7292,
"step": 359
},
{
"epoch": 1.77,
"learning_rate": 9.468801048601972e-06,
"loss": 0.6795,
"step": 360
},
{
"epoch": 1.78,
"learning_rate": 9.404271788321482e-06,
"loss": 0.662,
"step": 361
},
{
"epoch": 1.78,
"learning_rate": 9.339830300349498e-06,
"loss": 0.6917,
"step": 362
},
{
"epoch": 1.79,
"learning_rate": 9.275478411777354e-06,
"loss": 0.6759,
"step": 363
},
{
"epoch": 1.79,
"learning_rate": 9.211217947155986e-06,
"loss": 0.6535,
"step": 364
},
{
"epoch": 1.8,
"learning_rate": 9.147050728444215e-06,
"loss": 0.6741,
"step": 365
},
{
"epoch": 1.8,
"learning_rate": 9.08297857495709e-06,
"loss": 0.6837,
"step": 366
},
{
"epoch": 1.81,
"learning_rate": 9.0190033033143e-06,
"loss": 0.6454,
"step": 367
},
{
"epoch": 1.81,
"learning_rate": 8.955126727388672e-06,
"loss": 0.6695,
"step": 368
},
{
"epoch": 1.82,
"learning_rate": 8.89135065825474e-06,
"loss": 0.727,
"step": 369
},
{
"epoch": 1.82,
"learning_rate": 8.827676904137397e-06,
"loss": 0.6626,
"step": 370
},
{
"epoch": 1.83,
"learning_rate": 8.76410727036062e-06,
"loss": 0.6436,
"step": 371
},
{
"epoch": 1.83,
"learning_rate": 8.700643559296313e-06,
"loss": 0.6852,
"step": 372
},
{
"epoch": 1.84,
"learning_rate": 8.637287570313159e-06,
"loss": 0.6295,
"step": 373
},
{
"epoch": 1.84,
"learning_rate": 8.574041099725644e-06,
"loss": 0.679,
"step": 374
},
{
"epoch": 1.85,
"learning_rate": 8.510905940743093e-06,
"loss": 0.6501,
"step": 375
},
{
"epoch": 1.85,
"learning_rate": 8.447883883418866e-06,
"loss": 0.6976,
"step": 376
},
{
"epoch": 1.85,
"learning_rate": 8.38497671459957e-06,
"loss": 0.7009,
"step": 377
},
{
"epoch": 1.86,
"learning_rate": 8.32218621787441e-06,
"loss": 0.6754,
"step": 378
},
{
"epoch": 1.86,
"learning_rate": 8.25951417352462e-06,
"loss": 0.6816,
"step": 379
},
{
"epoch": 1.87,
"learning_rate": 8.196962358473e-06,
"loss": 0.6554,
"step": 380
},
{
"epoch": 1.87,
"learning_rate": 8.134532546233505e-06,
"loss": 0.6532,
"step": 381
},
{
"epoch": 1.88,
"learning_rate": 8.072226506860988e-06,
"loss": 0.7011,
"step": 382
},
{
"epoch": 1.88,
"learning_rate": 8.010046006901001e-06,
"loss": 0.7002,
"step": 383
},
{
"epoch": 1.89,
"learning_rate": 7.947992809339723e-06,
"loss": 0.643,
"step": 384
},
{
"epoch": 1.89,
"learning_rate": 7.88606867355395e-06,
"loss": 0.7304,
"step": 385
},
{
"epoch": 1.9,
"learning_rate": 7.824275355261233e-06,
"loss": 0.673,
"step": 386
},
{
"epoch": 1.9,
"learning_rate": 7.762614606470084e-06,
"loss": 0.6368,
"step": 387
},
{
"epoch": 1.91,
"learning_rate": 7.701088175430327e-06,
"loss": 0.6589,
"step": 388
},
{
"epoch": 1.91,
"learning_rate": 7.639697806583493e-06,
"loss": 0.685,
"step": 389
},
{
"epoch": 1.92,
"learning_rate": 7.578445240513393e-06,
"loss": 0.6659,
"step": 390
},
{
"epoch": 1.92,
"learning_rate": 7.517332213896743e-06,
"loss": 0.6914,
"step": 391
},
{
"epoch": 1.93,
"learning_rate": 7.456360459453952e-06,
"loss": 0.6852,
"step": 392
},
{
"epoch": 1.93,
"learning_rate": 7.395531705899969e-06,
"loss": 0.6308,
"step": 393
},
{
"epoch": 1.94,
"learning_rate": 7.334847677895276e-06,
"loss": 0.6535,
"step": 394
},
{
"epoch": 1.94,
"learning_rate": 7.274310095997e-06,
"loss": 0.6662,
"step": 395
},
{
"epoch": 1.95,
"learning_rate": 7.213920676610112e-06,
"loss": 0.6827,
"step": 396
},
{
"epoch": 1.95,
"learning_rate": 7.153681131938791e-06,
"loss": 0.6781,
"step": 397
},
{
"epoch": 1.96,
"learning_rate": 7.093593169937849e-06,
"loss": 0.6506,
"step": 398
},
{
"epoch": 1.96,
"learning_rate": 7.033658494264309e-06,
"loss": 0.7036,
"step": 399
},
{
"epoch": 1.97,
"learning_rate": 6.973878804229131e-06,
"loss": 0.6834,
"step": 400
},
{
"epoch": 1.97,
"learning_rate": 6.914255794748989e-06,
"loss": 0.6629,
"step": 401
},
{
"epoch": 1.98,
"learning_rate": 6.8547911562982595e-06,
"loss": 0.7212,
"step": 402
},
{
"epoch": 1.98,
"learning_rate": 6.7954865748610515e-06,
"loss": 0.6611,
"step": 403
},
{
"epoch": 1.99,
"learning_rate": 6.736343731883425e-06,
"loss": 0.7121,
"step": 404
},
{
"epoch": 1.99,
"learning_rate": 6.677364304225731e-06,
"loss": 0.6365,
"step": 405
},
{
"epoch": 2.0,
"learning_rate": 6.618549964115033e-06,
"loss": 0.6527,
"step": 406
},
{
"epoch": 2.0,
"learning_rate": 6.559902379097721e-06,
"loss": 0.5056,
"step": 407
},
{
"epoch": 2.01,
"learning_rate": 6.501423211992224e-06,
"loss": 0.4116,
"step": 408
},
{
"epoch": 2.01,
"learning_rate": 6.443114120841874e-06,
"loss": 0.3913,
"step": 409
},
{
"epoch": 2.02,
"learning_rate": 6.384976758867875e-06,
"loss": 0.4092,
"step": 410
},
{
"epoch": 2.02,
"learning_rate": 6.32701277442245e-06,
"loss": 0.402,
"step": 411
},
{
"epoch": 2.03,
"learning_rate": 6.269223810942086e-06,
"loss": 0.3886,
"step": 412
},
{
"epoch": 2.03,
"learning_rate": 6.211611506900973e-06,
"loss": 0.3336,
"step": 413
},
{
"epoch": 2.04,
"learning_rate": 6.1541774957645045e-06,
"loss": 0.3918,
"step": 414
},
{
"epoch": 2.04,
"learning_rate": 6.096923405942989e-06,
"loss": 0.3541,
"step": 415
},
{
"epoch": 2.05,
"learning_rate": 6.03985086074549e-06,
"loss": 0.3317,
"step": 416
},
{
"epoch": 2.05,
"learning_rate": 5.982961478333768e-06,
"loss": 0.3406,
"step": 417
},
{
"epoch": 2.06,
"learning_rate": 5.926256871676443e-06,
"loss": 0.324,
"step": 418
},
{
"epoch": 2.06,
"learning_rate": 5.86973864850322e-06,
"loss": 0.3686,
"step": 419
},
{
"epoch": 2.07,
"learning_rate": 5.813408411259331e-06,
"loss": 0.3323,
"step": 420
},
{
"epoch": 2.07,
"learning_rate": 5.757267757060109e-06,
"loss": 0.3494,
"step": 421
},
{
"epoch": 2.08,
"learning_rate": 5.701318277645675e-06,
"loss": 0.3532,
"step": 422
},
{
"epoch": 2.08,
"learning_rate": 5.645561559335832e-06,
"loss": 0.3596,
"step": 423
},
{
"epoch": 2.09,
"learning_rate": 5.589999182985087e-06,
"loss": 0.3783,
"step": 424
},
{
"epoch": 2.09,
"learning_rate": 5.534632723937809e-06,
"loss": 0.3515,
"step": 425
},
{
"epoch": 2.1,
"learning_rate": 5.479463751983603e-06,
"loss": 0.3261,
"step": 426
},
{
"epoch": 2.1,
"learning_rate": 5.424493831312757e-06,
"loss": 0.368,
"step": 427
},
{
"epoch": 2.11,
"learning_rate": 5.369724520471925e-06,
"loss": 0.3684,
"step": 428
},
{
"epoch": 2.11,
"learning_rate": 5.315157372319915e-06,
"loss": 0.3526,
"step": 429
},
{
"epoch": 2.12,
"learning_rate": 5.2607939339836945e-06,
"loss": 0.3388,
"step": 430
},
{
"epoch": 2.12,
"learning_rate": 5.2066357468144824e-06,
"loss": 0.3406,
"step": 431
},
{
"epoch": 2.13,
"learning_rate": 5.152684346344087e-06,
"loss": 0.33,
"step": 432
},
{
"epoch": 2.13,
"learning_rate": 5.0989412622413345e-06,
"loss": 0.3424,
"step": 433
},
{
"epoch": 2.14,
"learning_rate": 5.0454080182687314e-06,
"loss": 0.373,
"step": 434
},
{
"epoch": 2.14,
"learning_rate": 4.992086132239238e-06,
"loss": 0.3332,
"step": 435
},
{
"epoch": 2.15,
"learning_rate": 4.938977115973242e-06,
"loss": 0.3413,
"step": 436
},
{
"epoch": 2.15,
"learning_rate": 4.886082475255694e-06,
"loss": 0.355,
"step": 437
},
{
"epoch": 2.15,
"learning_rate": 4.833403709793424e-06,
"loss": 0.3331,
"step": 438
},
{
"epoch": 2.16,
"learning_rate": 4.780942313172602e-06,
"loss": 0.343,
"step": 439
},
{
"epoch": 2.16,
"learning_rate": 4.728699772816407e-06,
"loss": 0.3988,
"step": 440
},
{
"epoch": 2.17,
"learning_rate": 4.6766775699428365e-06,
"loss": 0.3527,
"step": 441
},
{
"epoch": 2.17,
"learning_rate": 4.624877179522742e-06,
"loss": 0.3563,
"step": 442
},
{
"epoch": 2.18,
"learning_rate": 4.573300070237973e-06,
"loss": 0.376,
"step": 443
},
{
"epoch": 2.18,
"learning_rate": 4.5219477044397525e-06,
"loss": 0.3256,
"step": 444
},
{
"epoch": 2.19,
"learning_rate": 4.470821538107219e-06,
"loss": 0.3517,
"step": 445
},
{
"epoch": 2.19,
"learning_rate": 4.419923020806148e-06,
"loss": 0.4053,
"step": 446
},
{
"epoch": 2.2,
"learning_rate": 4.36925359564783e-06,
"loss": 0.3272,
"step": 447
},
{
"epoch": 2.2,
"learning_rate": 4.318814699248188e-06,
"loss": 0.3371,
"step": 448
},
{
"epoch": 2.21,
"learning_rate": 4.268607761687019e-06,
"loss": 0.314,
"step": 449
},
{
"epoch": 2.21,
"learning_rate": 4.218634206467449e-06,
"loss": 0.347,
"step": 450
},
{
"epoch": 2.22,
"learning_rate": 4.1688954504756e-06,
"loss": 0.3671,
"step": 451
},
{
"epoch": 2.22,
"learning_rate": 4.119392903940384e-06,
"loss": 0.3479,
"step": 452
},
{
"epoch": 2.23,
"learning_rate": 4.07012797039353e-06,
"loss": 0.3732,
"step": 453
},
{
"epoch": 2.23,
"learning_rate": 4.021102046629799e-06,
"loss": 0.3116,
"step": 454
},
{
"epoch": 2.24,
"learning_rate": 3.972316522667381e-06,
"loss": 0.3443,
"step": 455
},
{
"epoch": 2.24,
"learning_rate": 3.923772781708468e-06,
"loss": 0.3662,
"step": 456
},
{
"epoch": 2.25,
"learning_rate": 3.875472200100051e-06,
"loss": 0.2995,
"step": 457
},
{
"epoch": 2.25,
"learning_rate": 3.827416147294888e-06,
"loss": 0.361,
"step": 458
},
{
"epoch": 2.26,
"learning_rate": 3.7796059858126927e-06,
"loss": 0.3441,
"step": 459
},
{
"epoch": 2.26,
"learning_rate": 3.7320430712014796e-06,
"loss": 0.3462,
"step": 460
},
{
"epoch": 2.27,
"learning_rate": 3.6847287519991434e-06,
"loss": 0.3885,
"step": 461
},
{
"epoch": 2.27,
"learning_rate": 3.637664369695233e-06,
"loss": 0.3637,
"step": 462
},
{
"epoch": 2.28,
"learning_rate": 3.590851258692894e-06,
"loss": 0.3185,
"step": 463
},
{
"epoch": 2.28,
"learning_rate": 3.5442907462710605e-06,
"loss": 0.3414,
"step": 464
},
{
"epoch": 2.29,
"learning_rate": 3.4979841525468016e-06,
"loss": 0.3493,
"step": 465
},
{
"epoch": 2.29,
"learning_rate": 3.451932790437898e-06,
"loss": 0.3546,
"step": 466
},
{
"epoch": 2.3,
"learning_rate": 3.4061379656256345e-06,
"loss": 0.3458,
"step": 467
},
{
"epoch": 2.3,
"learning_rate": 3.3606009765177555e-06,
"loss": 0.3618,
"step": 468
},
{
"epoch": 2.31,
"learning_rate": 3.3153231142116617e-06,
"loss": 0.3519,
"step": 469
},
{
"epoch": 2.31,
"learning_rate": 3.270305662457805e-06,
"loss": 0.3614,
"step": 470
},
{
"epoch": 2.32,
"learning_rate": 3.225549897623302e-06,
"loss": 0.3665,
"step": 471
},
{
"epoch": 2.32,
"learning_rate": 3.181057088655719e-06,
"loss": 0.3785,
"step": 472
},
{
"epoch": 2.33,
"learning_rate": 3.136828497047116e-06,
"loss": 0.3377,
"step": 473
},
{
"epoch": 2.33,
"learning_rate": 3.0928653767982695e-06,
"loss": 0.3767,
"step": 474
},
{
"epoch": 2.34,
"learning_rate": 3.0491689743831277e-06,
"loss": 0.3523,
"step": 475
},
{
"epoch": 2.34,
"learning_rate": 3.005740528713458e-06,
"loss": 0.3635,
"step": 476
},
{
"epoch": 2.35,
"learning_rate": 2.9625812711037206e-06,
"loss": 0.341,
"step": 477
},
{
"epoch": 2.35,
"learning_rate": 2.91969242523618e-06,
"loss": 0.3467,
"step": 478
},
{
"epoch": 2.36,
"learning_rate": 2.87707520712617e-06,
"loss": 0.3493,
"step": 479
},
{
"epoch": 2.36,
"learning_rate": 2.834730825087663e-06,
"loss": 0.3379,
"step": 480
},
{
"epoch": 2.37,
"learning_rate": 2.7926604796989676e-06,
"loss": 0.3951,
"step": 481
},
{
"epoch": 2.37,
"learning_rate": 2.7508653637687176e-06,
"loss": 0.3427,
"step": 482
},
{
"epoch": 2.38,
"learning_rate": 2.709346662302041e-06,
"loss": 0.3813,
"step": 483
},
{
"epoch": 2.38,
"learning_rate": 2.6681055524669694e-06,
"loss": 0.4021,
"step": 484
},
{
"epoch": 2.39,
"learning_rate": 2.6271432035610513e-06,
"loss": 0.3559,
"step": 485
},
{
"epoch": 2.39,
"learning_rate": 2.5864607769782084e-06,
"loss": 0.3115,
"step": 486
},
{
"epoch": 2.4,
"learning_rate": 2.5460594261757996e-06,
"loss": 0.3605,
"step": 487
},
{
"epoch": 2.4,
"learning_rate": 2.5059402966419303e-06,
"loss": 0.326,
"step": 488
},
{
"epoch": 2.41,
"learning_rate": 2.466104525862957e-06,
"loss": 0.364,
"step": 489
},
{
"epoch": 2.41,
"learning_rate": 2.426553243291249e-06,
"loss": 0.3477,
"step": 490
},
{
"epoch": 2.42,
"learning_rate": 2.3872875703131583e-06,
"loss": 0.352,
"step": 491
},
{
"epoch": 2.42,
"learning_rate": 2.3483086202172377e-06,
"loss": 0.3749,
"step": 492
},
{
"epoch": 2.43,
"learning_rate": 2.309617498162657e-06,
"loss": 0.3521,
"step": 493
},
{
"epoch": 2.43,
"learning_rate": 2.271215301147887e-06,
"loss": 0.3528,
"step": 494
},
{
"epoch": 2.44,
"learning_rate": 2.2331031179795792e-06,
"loss": 0.3462,
"step": 495
},
{
"epoch": 2.44,
"learning_rate": 2.1952820292417143e-06,
"loss": 0.3517,
"step": 496
},
{
"epoch": 2.45,
"learning_rate": 2.1577531072649495e-06,
"loss": 0.3434,
"step": 497
},
{
"epoch": 2.45,
"learning_rate": 2.120517416096217e-06,
"loss": 0.3679,
"step": 498
},
{
"epoch": 2.46,
"learning_rate": 2.083576011468562e-06,
"loss": 0.3568,
"step": 499
},
{
"epoch": 2.46,
"learning_rate": 2.0469299407712112e-06,
"loss": 0.3727,
"step": 500
},
{
"epoch": 2.46,
"learning_rate": 2.010580243019865e-06,
"loss": 0.3949,
"step": 501
},
{
"epoch": 2.47,
"learning_rate": 1.9745279488272484e-06,
"loss": 0.3595,
"step": 502
},
{
"epoch": 2.47,
"learning_rate": 1.938774080373884e-06,
"loss": 0.3371,
"step": 503
},
{
"epoch": 2.48,
"learning_rate": 1.9033196513791138e-06,
"loss": 0.342,
"step": 504
},
{
"epoch": 2.48,
"learning_rate": 1.8681656670723663e-06,
"loss": 0.3505,
"step": 505
},
{
"epoch": 2.49,
"learning_rate": 1.833313124164636e-06,
"loss": 0.3533,
"step": 506
},
{
"epoch": 2.49,
"learning_rate": 1.7987630108202355e-06,
"loss": 0.3303,
"step": 507
},
{
"epoch": 2.5,
"learning_rate": 1.764516306628787e-06,
"loss": 0.3815,
"step": 508
},
{
"epoch": 2.5,
"learning_rate": 1.7305739825774228e-06,
"loss": 0.3618,
"step": 509
},
{
"epoch": 2.51,
"learning_rate": 1.6969370010232882e-06,
"loss": 0.3296,
"step": 510
},
{
"epoch": 2.51,
"learning_rate": 1.663606315666226e-06,
"loss": 0.3413,
"step": 511
},
{
"epoch": 2.52,
"learning_rate": 1.6305828715217506e-06,
"loss": 0.36,
"step": 512
},
{
"epoch": 2.52,
"learning_rate": 1.597867604894264e-06,
"loss": 0.3716,
"step": 513
},
{
"epoch": 2.53,
"learning_rate": 1.5654614433504841e-06,
"loss": 0.346,
"step": 514
},
{
"epoch": 2.53,
"learning_rate": 1.5333653056931684e-06,
"loss": 0.3628,
"step": 515
},
{
"epoch": 2.54,
"learning_rate": 1.5015801019350476e-06,
"loss": 0.3417,
"step": 516
},
{
"epoch": 2.54,
"learning_rate": 1.4701067332730426e-06,
"loss": 0.3508,
"step": 517
},
{
"epoch": 2.55,
"learning_rate": 1.4389460920626887e-06,
"loss": 0.3418,
"step": 518
},
{
"epoch": 2.55,
"learning_rate": 1.4080990617928571e-06,
"loss": 0.3471,
"step": 519
},
{
"epoch": 2.56,
"learning_rate": 1.3775665170606896e-06,
"loss": 0.371,
"step": 520
},
{
"epoch": 2.56,
"learning_rate": 1.3473493235468177e-06,
"loss": 0.348,
"step": 521
},
{
"epoch": 2.57,
"learning_rate": 1.3174483379907996e-06,
"loss": 0.3172,
"step": 522
},
{
"epoch": 2.57,
"learning_rate": 1.2878644081668403e-06,
"loss": 0.3701,
"step": 523
},
{
"epoch": 2.58,
"learning_rate": 1.2585983728597608e-06,
"loss": 0.3788,
"step": 524
},
{
"epoch": 2.58,
"learning_rate": 1.2296510618411957e-06,
"loss": 0.4176,
"step": 525
},
{
"epoch": 2.59,
"learning_rate": 1.201023295846093e-06,
"loss": 0.3323,
"step": 526
},
{
"epoch": 2.59,
"learning_rate": 1.1727158865494206e-06,
"loss": 0.3603,
"step": 527
},
{
"epoch": 2.6,
"learning_rate": 1.1447296365431668e-06,
"loss": 0.3394,
"step": 528
},
{
"epoch": 2.6,
"learning_rate": 1.1170653393135847e-06,
"loss": 0.3344,
"step": 529
},
{
"epoch": 2.61,
"learning_rate": 1.0897237792186862e-06,
"loss": 0.3331,
"step": 530
},
{
"epoch": 2.61,
"learning_rate": 1.0627057314660114e-06,
"loss": 0.3656,
"step": 531
},
{
"epoch": 2.62,
"learning_rate": 1.0360119620906426e-06,
"loss": 0.3086,
"step": 532
},
{
"epoch": 2.62,
"learning_rate": 1.0096432279334905e-06,
"loss": 0.3505,
"step": 533
},
{
"epoch": 2.63,
"learning_rate": 9.836002766198379e-07,
"loss": 0.3473,
"step": 534
},
{
"epoch": 2.63,
"learning_rate": 9.57883846538135e-07,
"loss": 0.3996,
"step": 535
},
{
"epoch": 2.64,
"learning_rate": 9.324946668190657e-07,
"loss": 0.3151,
"step": 536
},
{
"epoch": 2.64,
"learning_rate": 9.074334573148783e-07,
"loss": 0.3581,
"step": 537
},
{
"epoch": 2.65,
"learning_rate": 8.827009285789778e-07,
"loss": 0.3843,
"step": 538
},
{
"epoch": 2.65,
"learning_rate": 8.582977818457696e-07,
"loss": 0.3462,
"step": 539
},
{
"epoch": 2.66,
"learning_rate": 8.342247090107919e-07,
"loss": 0.3123,
"step": 540
},
{
"epoch": 2.66,
"learning_rate": 8.104823926110811e-07,
"loss": 0.3567,
"step": 541
},
{
"epoch": 2.67,
"learning_rate": 7.870715058058406e-07,
"loss": 0.3301,
"step": 542
},
{
"epoch": 2.67,
"learning_rate": 7.639927123573351e-07,
"loss": 0.3228,
"step": 543
},
{
"epoch": 2.68,
"learning_rate": 7.412466666120846e-07,
"loss": 0.3474,
"step": 544
},
{
"epoch": 2.68,
"learning_rate": 7.188340134823043e-07,
"loss": 0.3202,
"step": 545
},
{
"epoch": 2.69,
"learning_rate": 6.967553884276279e-07,
"loss": 0.3468,
"step": 546
},
{
"epoch": 2.69,
"learning_rate": 6.750114174370797e-07,
"loss": 0.3849,
"step": 547
},
{
"epoch": 2.7,
"learning_rate": 6.536027170113354e-07,
"loss": 0.3187,
"step": 548
},
{
"epoch": 2.7,
"learning_rate": 6.32529894145234e-07,
"loss": 0.3558,
"step": 549
},
{
"epoch": 2.71,
"learning_rate": 6.117935463105809e-07,
"loss": 0.2956,
"step": 550
},
{
"epoch": 2.71,
"learning_rate": 5.913942614391931e-07,
"loss": 0.3309,
"step": 551
},
{
"epoch": 2.72,
"learning_rate": 5.713326179062409e-07,
"loss": 0.339,
"step": 552
},
{
"epoch": 2.72,
"learning_rate": 5.516091845138377e-07,
"loss": 0.3394,
"step": 553
},
{
"epoch": 2.73,
"learning_rate": 5.322245204749319e-07,
"loss": 0.3898,
"step": 554
},
{
"epoch": 2.73,
"learning_rate": 5.131791753974296e-07,
"loss": 0.3797,
"step": 555
},
{
"epoch": 2.74,
"learning_rate": 4.944736892686278e-07,
"loss": 0.3644,
"step": 556
},
{
"epoch": 2.74,
"learning_rate": 4.761085924398959e-07,
"loss": 0.3346,
"step": 557
},
{
"epoch": 2.75,
"learning_rate": 4.580844056116418e-07,
"loss": 0.3028,
"step": 558
},
{
"epoch": 2.75,
"learning_rate": 4.4040163981855095e-07,
"loss": 0.4031,
"step": 559
},
{
"epoch": 2.76,
"learning_rate": 4.2306079641509094e-07,
"loss": 0.3211,
"step": 560
},
{
"epoch": 2.76,
"learning_rate": 4.0606236706130367e-07,
"loss": 0.3552,
"step": 561
},
{
"epoch": 2.77,
"learning_rate": 3.89406833708858e-07,
"loss": 0.3539,
"step": 562
},
{
"epoch": 2.77,
"learning_rate": 3.73094668587394e-07,
"loss": 0.3764,
"step": 563
},
{
"epoch": 2.77,
"learning_rate": 3.5712633419112686e-07,
"loss": 0.3776,
"step": 564
},
{
"epoch": 2.78,
"learning_rate": 3.4150228326573356e-07,
"loss": 0.3943,
"step": 565
},
{
"epoch": 2.78,
"learning_rate": 3.262229587955232e-07,
"loss": 0.3839,
"step": 566
},
{
"epoch": 2.79,
"learning_rate": 3.112887939908715e-07,
"loss": 0.3238,
"step": 567
},
{
"epoch": 2.79,
"learning_rate": 2.9670021227593965e-07,
"loss": 0.3462,
"step": 568
},
{
"epoch": 2.8,
"learning_rate": 2.824576272766666e-07,
"loss": 0.3338,
"step": 569
},
{
"epoch": 2.8,
"learning_rate": 2.6856144280904967e-07,
"loss": 0.4009,
"step": 570
},
{
"epoch": 2.81,
"learning_rate": 2.550120528676841e-07,
"loss": 0.3511,
"step": 571
},
{
"epoch": 2.81,
"learning_rate": 2.4180984161460004e-07,
"loss": 0.3157,
"step": 572
},
{
"epoch": 2.82,
"learning_rate": 2.2895518336836923e-07,
"loss": 0.3281,
"step": 573
},
{
"epoch": 2.82,
"learning_rate": 2.164484425934879e-07,
"loss": 0.3573,
"step": 574
},
{
"epoch": 2.83,
"learning_rate": 2.0428997389004972e-07,
"loss": 0.3414,
"step": 575
},
{
"epoch": 2.83,
"learning_rate": 1.9248012198368748e-07,
"loss": 0.386,
"step": 576
},
{
"epoch": 2.84,
"learning_rate": 1.8101922171580022e-07,
"loss": 0.3197,
"step": 577
},
{
"epoch": 2.84,
"learning_rate": 1.699075980340581e-07,
"loss": 0.3153,
"step": 578
},
{
"epoch": 2.85,
"learning_rate": 1.5914556598319307e-07,
"loss": 0.3227,
"step": 579
},
{
"epoch": 2.85,
"learning_rate": 1.4873343069606305e-07,
"loss": 0.3259,
"step": 580
},
{
"epoch": 2.86,
"learning_rate": 1.3867148738500313e-07,
"loss": 0.3968,
"step": 581
},
{
"epoch": 2.86,
"learning_rate": 1.289600213334505e-07,
"loss": 0.3531,
"step": 582
},
{
"epoch": 2.87,
"learning_rate": 1.195993078878646e-07,
"loss": 0.3476,
"step": 583
},
{
"epoch": 2.87,
"learning_rate": 1.1058961244991144e-07,
"loss": 0.3373,
"step": 584
},
{
"epoch": 2.88,
"learning_rate": 1.0193119046894295e-07,
"loss": 0.3372,
"step": 585
},
{
"epoch": 2.88,
"learning_rate": 9.362428743475565e-08,
"loss": 0.3463,
"step": 586
},
{
"epoch": 2.89,
"learning_rate": 8.566913887062683e-08,
"loss": 0.3544,
"step": 587
},
{
"epoch": 2.89,
"learning_rate": 7.806597032663925e-08,
"loss": 0.3629,
"step": 588
},
{
"epoch": 2.9,
"learning_rate": 7.081499737328634e-08,
"loss": 0.3486,
"step": 589
},
{
"epoch": 2.9,
"learning_rate": 6.391642559535616e-08,
"loss": 0.3315,
"step": 590
},
{
"epoch": 2.91,
"learning_rate": 5.7370450586109737e-08,
"loss": 0.3358,
"step": 591
},
{
"epoch": 2.91,
"learning_rate": 5.117725794172995e-08,
"loss": 0.3144,
"step": 592
},
{
"epoch": 2.92,
"learning_rate": 4.533702325605904e-08,
"loss": 0.3609,
"step": 593
},
{
"epoch": 2.92,
"learning_rate": 3.9849912115623446e-08,
"loss": 0.3044,
"step": 594
},
{
"epoch": 2.93,
"learning_rate": 3.471608009493754e-08,
"loss": 0.3391,
"step": 595
},
{
"epoch": 2.93,
"learning_rate": 2.9935672752090525e-08,
"loss": 0.3522,
"step": 596
},
{
"epoch": 2.94,
"learning_rate": 2.5508825624626088e-08,
"loss": 0.3487,
"step": 597
},
{
"epoch": 2.94,
"learning_rate": 2.1435664225688547e-08,
"loss": 0.3291,
"step": 598
},
{
"epoch": 2.95,
"learning_rate": 1.7716304040475697e-08,
"loss": 0.3867,
"step": 599
},
{
"epoch": 2.95,
"learning_rate": 1.4350850522956705e-08,
"loss": 0.3466,
"step": 600
},
{
"epoch": 2.96,
"learning_rate": 1.1339399092885616e-08,
"loss": 0.2979,
"step": 601
},
{
"epoch": 2.96,
"learning_rate": 8.682035133096566e-09,
"loss": 0.3577,
"step": 602
},
{
"epoch": 2.97,
"learning_rate": 6.378833987077948e-09,
"loss": 0.3616,
"step": 603
},
{
"epoch": 2.97,
"learning_rate": 4.429860956842169e-09,
"loss": 0.3405,
"step": 604
},
{
"epoch": 2.98,
"learning_rate": 2.8351713010743573e-09,
"loss": 0.3453,
"step": 605
},
{
"epoch": 2.98,
"learning_rate": 1.5948102335572313e-09,
"loss": 0.3446,
"step": 606
},
{
"epoch": 2.99,
"learning_rate": 7.088129218985052e-10,
"loss": 0.3575,
"step": 607
},
{
"epoch": 2.99,
"learning_rate": 1.772044865316902e-10,
"loss": 0.3648,
"step": 608
},
{
"epoch": 3.0,
"learning_rate": 0.0,
"loss": 0.3142,
"step": 609
},
{
"epoch": 3.0,
"step": 609,
"total_flos": 58075646853120.0,
"train_loss": 0.7130698823478617,
"train_runtime": 3036.251,
"train_samples_per_second": 51.379,
"train_steps_per_second": 0.201
}
],
"logging_steps": 1.0,
"max_steps": 609,
"num_train_epochs": 3,
"save_steps": -609,
"total_flos": 58075646853120.0,
"trial_name": null,
"trial_params": null
}