CAG-13b / trainer_state.json
prt_
upload CAG 13b
f4f7ee2
raw
history blame
No virus
76.6 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.989374262101535,
"global_step": 633,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 7.692307692307694e-07,
"loss": 0.8141,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 1.5384615384615387e-06,
"loss": 0.7997,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 2.307692307692308e-06,
"loss": 0.8205,
"step": 3
},
{
"epoch": 0.02,
"learning_rate": 3.0769230769230774e-06,
"loss": 0.771,
"step": 4
},
{
"epoch": 0.02,
"learning_rate": 3.846153846153847e-06,
"loss": 0.7829,
"step": 5
},
{
"epoch": 0.03,
"learning_rate": 4.615384615384616e-06,
"loss": 0.728,
"step": 6
},
{
"epoch": 0.03,
"learning_rate": 5.384615384615385e-06,
"loss": 0.6903,
"step": 7
},
{
"epoch": 0.04,
"learning_rate": 6.153846153846155e-06,
"loss": 0.6769,
"step": 8
},
{
"epoch": 0.04,
"learning_rate": 6.923076923076923e-06,
"loss": 0.7049,
"step": 9
},
{
"epoch": 0.05,
"learning_rate": 7.692307692307694e-06,
"loss": 0.7011,
"step": 10
},
{
"epoch": 0.05,
"learning_rate": 8.461538461538462e-06,
"loss": 0.6727,
"step": 11
},
{
"epoch": 0.06,
"learning_rate": 9.230769230769232e-06,
"loss": 0.6287,
"step": 12
},
{
"epoch": 0.06,
"learning_rate": 1e-05,
"loss": 0.622,
"step": 13
},
{
"epoch": 0.07,
"learning_rate": 1.076923076923077e-05,
"loss": 0.667,
"step": 14
},
{
"epoch": 0.07,
"learning_rate": 1.1538461538461538e-05,
"loss": 0.588,
"step": 15
},
{
"epoch": 0.08,
"learning_rate": 1.230769230769231e-05,
"loss": 0.6101,
"step": 16
},
{
"epoch": 0.08,
"learning_rate": 1.3076923076923078e-05,
"loss": 0.5779,
"step": 17
},
{
"epoch": 0.09,
"learning_rate": 1.3846153846153847e-05,
"loss": 0.605,
"step": 18
},
{
"epoch": 0.09,
"learning_rate": 1.4615384615384615e-05,
"loss": 0.6535,
"step": 19
},
{
"epoch": 0.09,
"learning_rate": 1.5384615384615387e-05,
"loss": 0.5979,
"step": 20
},
{
"epoch": 0.1,
"learning_rate": 1.6153846153846154e-05,
"loss": 0.5847,
"step": 21
},
{
"epoch": 0.1,
"learning_rate": 1.6923076923076924e-05,
"loss": 0.6089,
"step": 22
},
{
"epoch": 0.11,
"learning_rate": 1.7692307692307694e-05,
"loss": 0.6198,
"step": 23
},
{
"epoch": 0.11,
"learning_rate": 1.8461538461538465e-05,
"loss": 0.6427,
"step": 24
},
{
"epoch": 0.12,
"learning_rate": 1.923076923076923e-05,
"loss": 0.624,
"step": 25
},
{
"epoch": 0.12,
"learning_rate": 2e-05,
"loss": 0.5898,
"step": 26
},
{
"epoch": 0.13,
"learning_rate": 1.9999866065827706e-05,
"loss": 0.5527,
"step": 27
},
{
"epoch": 0.13,
"learning_rate": 1.9999464266898485e-05,
"loss": 0.5825,
"step": 28
},
{
"epoch": 0.14,
"learning_rate": 1.9998794613975263e-05,
"loss": 0.5821,
"step": 29
},
{
"epoch": 0.14,
"learning_rate": 1.999785712499592e-05,
"loss": 0.5916,
"step": 30
},
{
"epoch": 0.15,
"learning_rate": 1.9996651825072826e-05,
"loss": 0.5981,
"step": 31
},
{
"epoch": 0.15,
"learning_rate": 1.999517874649214e-05,
"loss": 0.5911,
"step": 32
},
{
"epoch": 0.16,
"learning_rate": 1.9993437928712977e-05,
"loss": 0.5905,
"step": 33
},
{
"epoch": 0.16,
"learning_rate": 1.9991429418366343e-05,
"loss": 0.5715,
"step": 34
},
{
"epoch": 0.17,
"learning_rate": 1.9989153269253857e-05,
"loss": 0.5772,
"step": 35
},
{
"epoch": 0.17,
"learning_rate": 1.9986609542346364e-05,
"loss": 0.606,
"step": 36
},
{
"epoch": 0.17,
"learning_rate": 1.9983798305782243e-05,
"loss": 0.5886,
"step": 37
},
{
"epoch": 0.18,
"learning_rate": 1.998071963486563e-05,
"loss": 0.5913,
"step": 38
},
{
"epoch": 0.18,
"learning_rate": 1.9977373612064374e-05,
"loss": 0.5966,
"step": 39
},
{
"epoch": 0.19,
"learning_rate": 1.9973760327007826e-05,
"loss": 0.5901,
"step": 40
},
{
"epoch": 0.19,
"learning_rate": 1.996987987648446e-05,
"loss": 0.6022,
"step": 41
},
{
"epoch": 0.2,
"learning_rate": 1.9965732364439265e-05,
"loss": 0.5378,
"step": 42
},
{
"epoch": 0.2,
"learning_rate": 1.9961317901970953e-05,
"loss": 0.6319,
"step": 43
},
{
"epoch": 0.21,
"learning_rate": 1.9956636607329006e-05,
"loss": 0.6105,
"step": 44
},
{
"epoch": 0.21,
"learning_rate": 1.9951688605910478e-05,
"loss": 0.5684,
"step": 45
},
{
"epoch": 0.22,
"learning_rate": 1.9946474030256676e-05,
"loss": 0.5819,
"step": 46
},
{
"epoch": 0.22,
"learning_rate": 1.994099302004957e-05,
"loss": 0.6302,
"step": 47
},
{
"epoch": 0.23,
"learning_rate": 1.993524572210807e-05,
"loss": 0.607,
"step": 48
},
{
"epoch": 0.23,
"learning_rate": 1.99292322903841e-05,
"loss": 0.573,
"step": 49
},
{
"epoch": 0.24,
"learning_rate": 1.992295288595846e-05,
"loss": 0.5968,
"step": 50
},
{
"epoch": 0.24,
"learning_rate": 1.9916407677036508e-05,
"loss": 0.5422,
"step": 51
},
{
"epoch": 0.25,
"learning_rate": 1.990959683894368e-05,
"loss": 0.571,
"step": 52
},
{
"epoch": 0.25,
"learning_rate": 1.990252055412077e-05,
"loss": 0.5726,
"step": 53
},
{
"epoch": 0.26,
"learning_rate": 1.9895179012119044e-05,
"loss": 0.6013,
"step": 54
},
{
"epoch": 0.26,
"learning_rate": 1.988757240959517e-05,
"loss": 0.5594,
"step": 55
},
{
"epoch": 0.26,
"learning_rate": 1.9879700950305957e-05,
"loss": 0.544,
"step": 56
},
{
"epoch": 0.27,
"learning_rate": 1.9871564845102877e-05,
"loss": 0.5753,
"step": 57
},
{
"epoch": 0.27,
"learning_rate": 1.9863164311926433e-05,
"loss": 0.587,
"step": 58
},
{
"epoch": 0.28,
"learning_rate": 1.9854499575800324e-05,
"loss": 0.5626,
"step": 59
},
{
"epoch": 0.28,
"learning_rate": 1.9845570868825394e-05,
"loss": 0.6279,
"step": 60
},
{
"epoch": 0.29,
"learning_rate": 1.983637843017344e-05,
"loss": 0.5529,
"step": 61
},
{
"epoch": 0.29,
"learning_rate": 1.98269225060808e-05,
"loss": 0.5802,
"step": 62
},
{
"epoch": 0.3,
"learning_rate": 1.981720334984174e-05,
"loss": 0.5281,
"step": 63
},
{
"epoch": 0.3,
"learning_rate": 1.980722122180169e-05,
"loss": 0.546,
"step": 64
},
{
"epoch": 0.31,
"learning_rate": 1.9796976389350266e-05,
"loss": 0.5609,
"step": 65
},
{
"epoch": 0.31,
"learning_rate": 1.9786469126914097e-05,
"loss": 0.6092,
"step": 66
},
{
"epoch": 0.32,
"learning_rate": 1.9775699715949484e-05,
"loss": 0.583,
"step": 67
},
{
"epoch": 0.32,
"learning_rate": 1.9764668444934853e-05,
"loss": 0.5242,
"step": 68
},
{
"epoch": 0.33,
"learning_rate": 1.9753375609363035e-05,
"loss": 0.5283,
"step": 69
},
{
"epoch": 0.33,
"learning_rate": 1.9741821511733348e-05,
"loss": 0.5574,
"step": 70
},
{
"epoch": 0.34,
"learning_rate": 1.973000646154349e-05,
"loss": 0.5497,
"step": 71
},
{
"epoch": 0.34,
"learning_rate": 1.971793077528126e-05,
"loss": 0.6023,
"step": 72
},
{
"epoch": 0.34,
"learning_rate": 1.970559477641606e-05,
"loss": 0.5862,
"step": 73
},
{
"epoch": 0.35,
"learning_rate": 1.9692998795390257e-05,
"loss": 0.5701,
"step": 74
},
{
"epoch": 0.35,
"learning_rate": 1.9680143169610303e-05,
"loss": 0.552,
"step": 75
},
{
"epoch": 0.36,
"learning_rate": 1.966702824343772e-05,
"loss": 0.5605,
"step": 76
},
{
"epoch": 0.36,
"learning_rate": 1.9653654368179867e-05,
"loss": 0.5688,
"step": 77
},
{
"epoch": 0.37,
"learning_rate": 1.9640021902080523e-05,
"loss": 0.5613,
"step": 78
},
{
"epoch": 0.37,
"learning_rate": 1.9626131210310298e-05,
"loss": 0.5166,
"step": 79
},
{
"epoch": 0.38,
"learning_rate": 1.961198266495686e-05,
"loss": 0.6149,
"step": 80
},
{
"epoch": 0.38,
"learning_rate": 1.959757664501495e-05,
"loss": 0.5569,
"step": 81
},
{
"epoch": 0.39,
"learning_rate": 1.958291353637624e-05,
"loss": 0.5411,
"step": 82
},
{
"epoch": 0.39,
"learning_rate": 1.9567993731818988e-05,
"loss": 0.5536,
"step": 83
},
{
"epoch": 0.4,
"learning_rate": 1.955281763099753e-05,
"loss": 0.5526,
"step": 84
},
{
"epoch": 0.4,
"learning_rate": 1.9537385640431568e-05,
"loss": 0.5495,
"step": 85
},
{
"epoch": 0.41,
"learning_rate": 1.9521698173495283e-05,
"loss": 0.4943,
"step": 86
},
{
"epoch": 0.41,
"learning_rate": 1.950575565040625e-05,
"loss": 0.5292,
"step": 87
},
{
"epoch": 0.42,
"learning_rate": 1.9489558498214197e-05,
"loss": 0.5144,
"step": 88
},
{
"epoch": 0.42,
"learning_rate": 1.9473107150789555e-05,
"loss": 0.5787,
"step": 89
},
{
"epoch": 0.43,
"learning_rate": 1.9456402048811857e-05,
"loss": 0.577,
"step": 90
},
{
"epoch": 0.43,
"learning_rate": 1.9439443639757883e-05,
"loss": 0.5677,
"step": 91
},
{
"epoch": 0.43,
"learning_rate": 1.942223237788975e-05,
"loss": 0.5724,
"step": 92
},
{
"epoch": 0.44,
"learning_rate": 1.9404768724242667e-05,
"loss": 0.5463,
"step": 93
},
{
"epoch": 0.44,
"learning_rate": 1.938705314661264e-05,
"loss": 0.5596,
"step": 94
},
{
"epoch": 0.45,
"learning_rate": 1.936908611954391e-05,
"loss": 0.5057,
"step": 95
},
{
"epoch": 0.45,
"learning_rate": 1.935086812431626e-05,
"loss": 0.5446,
"step": 96
},
{
"epoch": 0.46,
"learning_rate": 1.9332399648932113e-05,
"loss": 0.5724,
"step": 97
},
{
"epoch": 0.46,
"learning_rate": 1.931368118810346e-05,
"loss": 0.5695,
"step": 98
},
{
"epoch": 0.47,
"learning_rate": 1.9294713243238608e-05,
"loss": 0.5777,
"step": 99
},
{
"epoch": 0.47,
"learning_rate": 1.9275496322428764e-05,
"loss": 0.5848,
"step": 100
},
{
"epoch": 0.48,
"learning_rate": 1.92560309404344e-05,
"loss": 0.5614,
"step": 101
},
{
"epoch": 0.48,
"learning_rate": 1.9236317618671486e-05,
"loss": 0.5635,
"step": 102
},
{
"epoch": 0.49,
"learning_rate": 1.92163568851975e-05,
"loss": 0.5533,
"step": 103
},
{
"epoch": 0.49,
"learning_rate": 1.9196149274697316e-05,
"loss": 0.5312,
"step": 104
},
{
"epoch": 0.5,
"learning_rate": 1.917569532846884e-05,
"loss": 0.5238,
"step": 105
},
{
"epoch": 0.5,
"learning_rate": 1.915499559440855e-05,
"loss": 0.5852,
"step": 106
},
{
"epoch": 0.51,
"learning_rate": 1.91340506269968e-05,
"loss": 0.5488,
"step": 107
},
{
"epoch": 0.51,
"learning_rate": 1.911286098728296e-05,
"loss": 0.5122,
"step": 108
},
{
"epoch": 0.51,
"learning_rate": 1.9091427242870396e-05,
"loss": 0.5798,
"step": 109
},
{
"epoch": 0.52,
"learning_rate": 1.9069749967901278e-05,
"loss": 0.5289,
"step": 110
},
{
"epoch": 0.52,
"learning_rate": 1.9047829743041184e-05,
"loss": 0.5337,
"step": 111
},
{
"epoch": 0.53,
"learning_rate": 1.9025667155463542e-05,
"loss": 0.5498,
"step": 112
},
{
"epoch": 0.53,
"learning_rate": 1.900326279883392e-05,
"loss": 0.5283,
"step": 113
},
{
"epoch": 0.54,
"learning_rate": 1.8980617273294112e-05,
"loss": 0.582,
"step": 114
},
{
"epoch": 0.54,
"learning_rate": 1.895773118544606e-05,
"loss": 0.5539,
"step": 115
},
{
"epoch": 0.55,
"learning_rate": 1.893460514833561e-05,
"loss": 0.5655,
"step": 116
},
{
"epoch": 0.55,
"learning_rate": 1.891123978143609e-05,
"loss": 0.5467,
"step": 117
},
{
"epoch": 0.56,
"learning_rate": 1.8887635710631716e-05,
"loss": 0.5382,
"step": 118
},
{
"epoch": 0.56,
"learning_rate": 1.8863793568200822e-05,
"loss": 0.5203,
"step": 119
},
{
"epoch": 0.57,
"learning_rate": 1.883971399279894e-05,
"loss": 0.5751,
"step": 120
},
{
"epoch": 0.57,
"learning_rate": 1.881539762944166e-05,
"loss": 0.5355,
"step": 121
},
{
"epoch": 0.58,
"learning_rate": 1.8790845129487383e-05,
"loss": 0.5459,
"step": 122
},
{
"epoch": 0.58,
"learning_rate": 1.8766057150619865e-05,
"loss": 0.5375,
"step": 123
},
{
"epoch": 0.59,
"learning_rate": 1.874103435683059e-05,
"loss": 0.5679,
"step": 124
},
{
"epoch": 0.59,
"learning_rate": 1.8715777418400996e-05,
"loss": 0.5499,
"step": 125
},
{
"epoch": 0.6,
"learning_rate": 1.869028701188451e-05,
"loss": 0.5205,
"step": 126
},
{
"epoch": 0.6,
"learning_rate": 1.866456382008843e-05,
"loss": 0.5552,
"step": 127
},
{
"epoch": 0.6,
"learning_rate": 1.8638608532055635e-05,
"loss": 0.5441,
"step": 128
},
{
"epoch": 0.61,
"learning_rate": 1.8612421843046135e-05,
"loss": 0.5097,
"step": 129
},
{
"epoch": 0.61,
"learning_rate": 1.8586004454518424e-05,
"loss": 0.5389,
"step": 130
},
{
"epoch": 0.62,
"learning_rate": 1.8559357074110727e-05,
"loss": 0.5757,
"step": 131
},
{
"epoch": 0.62,
"learning_rate": 1.8532480415622002e-05,
"loss": 0.5699,
"step": 132
},
{
"epoch": 0.63,
"learning_rate": 1.8505375198992856e-05,
"loss": 0.5514,
"step": 133
},
{
"epoch": 0.63,
"learning_rate": 1.847804215028624e-05,
"loss": 0.5768,
"step": 134
},
{
"epoch": 0.64,
"learning_rate": 1.8450482001668004e-05,
"loss": 0.5466,
"step": 135
},
{
"epoch": 0.64,
"learning_rate": 1.8422695491387284e-05,
"loss": 0.5604,
"step": 136
},
{
"epoch": 0.65,
"learning_rate": 1.8394683363756736e-05,
"loss": 0.5363,
"step": 137
},
{
"epoch": 0.65,
"learning_rate": 1.836644636913258e-05,
"loss": 0.5504,
"step": 138
},
{
"epoch": 0.66,
"learning_rate": 1.8337985263894523e-05,
"loss": 0.5821,
"step": 139
},
{
"epoch": 0.66,
"learning_rate": 1.8309300810425475e-05,
"loss": 0.5287,
"step": 140
},
{
"epoch": 0.67,
"learning_rate": 1.8280393777091143e-05,
"loss": 0.5197,
"step": 141
},
{
"epoch": 0.67,
"learning_rate": 1.8251264938219443e-05,
"loss": 0.5421,
"step": 142
},
{
"epoch": 0.68,
"learning_rate": 1.8221915074079764e-05,
"loss": 0.5258,
"step": 143
},
{
"epoch": 0.68,
"learning_rate": 1.8192344970862055e-05,
"loss": 0.4827,
"step": 144
},
{
"epoch": 0.68,
"learning_rate": 1.8162555420655774e-05,
"loss": 0.5581,
"step": 145
},
{
"epoch": 0.69,
"learning_rate": 1.8132547221428675e-05,
"loss": 0.5758,
"step": 146
},
{
"epoch": 0.69,
"learning_rate": 1.8102321177005426e-05,
"loss": 0.5494,
"step": 147
},
{
"epoch": 0.7,
"learning_rate": 1.8071878097046064e-05,
"loss": 0.5319,
"step": 148
},
{
"epoch": 0.7,
"learning_rate": 1.804121879702434e-05,
"loss": 0.5264,
"step": 149
},
{
"epoch": 0.71,
"learning_rate": 1.8010344098205853e-05,
"loss": 0.6008,
"step": 150
},
{
"epoch": 0.71,
"learning_rate": 1.7979254827626037e-05,
"loss": 0.5324,
"step": 151
},
{
"epoch": 0.72,
"learning_rate": 1.7947951818068047e-05,
"loss": 0.5073,
"step": 152
},
{
"epoch": 0.72,
"learning_rate": 1.7916435908040413e-05,
"loss": 0.568,
"step": 153
},
{
"epoch": 0.73,
"learning_rate": 1.78847079417546e-05,
"loss": 0.5649,
"step": 154
},
{
"epoch": 0.73,
"learning_rate": 1.7852768769102395e-05,
"loss": 0.5721,
"step": 155
},
{
"epoch": 0.74,
"learning_rate": 1.7820619245633116e-05,
"loss": 0.5323,
"step": 156
},
{
"epoch": 0.74,
"learning_rate": 1.7788260232530735e-05,
"loss": 0.5106,
"step": 157
},
{
"epoch": 0.75,
"learning_rate": 1.7755692596590778e-05,
"loss": 0.5722,
"step": 158
},
{
"epoch": 0.75,
"learning_rate": 1.772291721019712e-05,
"loss": 0.566,
"step": 159
},
{
"epoch": 0.76,
"learning_rate": 1.7689934951298608e-05,
"loss": 0.5641,
"step": 160
},
{
"epoch": 0.76,
"learning_rate": 1.7656746703385547e-05,
"loss": 0.564,
"step": 161
},
{
"epoch": 0.77,
"learning_rate": 1.7623353355466046e-05,
"loss": 0.5586,
"step": 162
},
{
"epoch": 0.77,
"learning_rate": 1.7589755802042188e-05,
"loss": 0.5621,
"step": 163
},
{
"epoch": 0.77,
"learning_rate": 1.755595494308607e-05,
"loss": 0.529,
"step": 164
},
{
"epoch": 0.78,
"learning_rate": 1.752195168401571e-05,
"loss": 0.5255,
"step": 165
},
{
"epoch": 0.78,
"learning_rate": 1.748774693567078e-05,
"loss": 0.5291,
"step": 166
},
{
"epoch": 0.79,
"learning_rate": 1.7453341614288205e-05,
"loss": 0.5214,
"step": 167
},
{
"epoch": 0.79,
"learning_rate": 1.7418736641477636e-05,
"loss": 0.5137,
"step": 168
},
{
"epoch": 0.8,
"learning_rate": 1.7383932944196756e-05,
"loss": 0.5646,
"step": 169
},
{
"epoch": 0.8,
"learning_rate": 1.7348931454726443e-05,
"loss": 0.5098,
"step": 170
},
{
"epoch": 0.81,
"learning_rate": 1.7313733110645793e-05,
"loss": 0.5085,
"step": 171
},
{
"epoch": 0.81,
"learning_rate": 1.727833885480703e-05,
"loss": 0.486,
"step": 172
},
{
"epoch": 0.82,
"learning_rate": 1.7242749635310222e-05,
"loss": 0.5423,
"step": 173
},
{
"epoch": 0.82,
"learning_rate": 1.72069664054779e-05,
"loss": 0.5385,
"step": 174
},
{
"epoch": 0.83,
"learning_rate": 1.717099012382952e-05,
"loss": 0.5095,
"step": 175
},
{
"epoch": 0.83,
"learning_rate": 1.7134821754055785e-05,
"loss": 0.5331,
"step": 176
},
{
"epoch": 0.84,
"learning_rate": 1.7098462264992823e-05,
"loss": 0.504,
"step": 177
},
{
"epoch": 0.84,
"learning_rate": 1.7061912630596252e-05,
"loss": 0.5467,
"step": 178
},
{
"epoch": 0.85,
"learning_rate": 1.702517382991508e-05,
"loss": 0.5496,
"step": 179
},
{
"epoch": 0.85,
"learning_rate": 1.6988246847065474e-05,
"loss": 0.5497,
"step": 180
},
{
"epoch": 0.85,
"learning_rate": 1.695113267120441e-05,
"loss": 0.4827,
"step": 181
},
{
"epoch": 0.86,
"learning_rate": 1.6913832296503187e-05,
"loss": 0.5319,
"step": 182
},
{
"epoch": 0.86,
"learning_rate": 1.6876346722120747e-05,
"loss": 0.5512,
"step": 183
},
{
"epoch": 0.87,
"learning_rate": 1.683867695217698e-05,
"loss": 0.533,
"step": 184
},
{
"epoch": 0.87,
"learning_rate": 1.680082399572577e-05,
"loss": 0.4947,
"step": 185
},
{
"epoch": 0.88,
"learning_rate": 1.6762788866728e-05,
"loss": 0.5173,
"step": 186
},
{
"epoch": 0.88,
"learning_rate": 1.672457258402437e-05,
"loss": 0.5161,
"step": 187
},
{
"epoch": 0.89,
"learning_rate": 1.6686176171308125e-05,
"loss": 0.5568,
"step": 188
},
{
"epoch": 0.89,
"learning_rate": 1.6647600657097613e-05,
"loss": 0.5217,
"step": 189
},
{
"epoch": 0.9,
"learning_rate": 1.6608847074708744e-05,
"loss": 0.5489,
"step": 190
},
{
"epoch": 0.9,
"learning_rate": 1.656991646222731e-05,
"loss": 0.5637,
"step": 191
},
{
"epoch": 0.91,
"learning_rate": 1.6530809862481197e-05,
"loss": 0.522,
"step": 192
},
{
"epoch": 0.91,
"learning_rate": 1.6491528323012412e-05,
"loss": 0.5521,
"step": 193
},
{
"epoch": 0.92,
"learning_rate": 1.6452072896049048e-05,
"loss": 0.4499,
"step": 194
},
{
"epoch": 0.92,
"learning_rate": 1.6412444638477094e-05,
"loss": 0.5567,
"step": 195
},
{
"epoch": 0.93,
"learning_rate": 1.637264461181213e-05,
"loss": 0.4969,
"step": 196
},
{
"epoch": 0.93,
"learning_rate": 1.6332673882170882e-05,
"loss": 0.5262,
"step": 197
},
{
"epoch": 0.94,
"learning_rate": 1.6292533520242663e-05,
"loss": 0.4856,
"step": 198
},
{
"epoch": 0.94,
"learning_rate": 1.625222460126071e-05,
"loss": 0.531,
"step": 199
},
{
"epoch": 0.94,
"learning_rate": 1.6211748204973358e-05,
"loss": 0.4714,
"step": 200
},
{
"epoch": 0.95,
"learning_rate": 1.6171105415615132e-05,
"loss": 0.5512,
"step": 201
},
{
"epoch": 0.95,
"learning_rate": 1.613029732187771e-05,
"loss": 0.5255,
"step": 202
},
{
"epoch": 0.96,
"learning_rate": 1.6089325016880737e-05,
"loss": 0.5408,
"step": 203
},
{
"epoch": 0.96,
"learning_rate": 1.6048189598142568e-05,
"loss": 0.6029,
"step": 204
},
{
"epoch": 0.97,
"learning_rate": 1.600689216755085e-05,
"loss": 0.5065,
"step": 205
},
{
"epoch": 0.97,
"learning_rate": 1.596543383133303e-05,
"loss": 0.5171,
"step": 206
},
{
"epoch": 0.98,
"learning_rate": 1.592381570002669e-05,
"loss": 0.5527,
"step": 207
},
{
"epoch": 0.98,
"learning_rate": 1.588203888844982e-05,
"loss": 0.5016,
"step": 208
},
{
"epoch": 0.99,
"learning_rate": 1.5840104515670963e-05,
"loss": 0.5576,
"step": 209
},
{
"epoch": 0.99,
"learning_rate": 1.579801370497922e-05,
"loss": 0.533,
"step": 210
},
{
"epoch": 1.0,
"learning_rate": 1.5755767583854165e-05,
"loss": 0.503,
"step": 211
},
{
"epoch": 1.0,
"learning_rate": 1.5713367283935657e-05,
"loss": 0.4778,
"step": 212
},
{
"epoch": 1.01,
"learning_rate": 1.5670813940993504e-05,
"loss": 0.3722,
"step": 213
},
{
"epoch": 1.01,
"learning_rate": 1.5628108694897064e-05,
"loss": 0.3566,
"step": 214
},
{
"epoch": 1.02,
"learning_rate": 1.5585252689584694e-05,
"loss": 0.3356,
"step": 215
},
{
"epoch": 1.02,
"learning_rate": 1.5542247073033116e-05,
"loss": 0.3356,
"step": 216
},
{
"epoch": 1.02,
"learning_rate": 1.5499092997226658e-05,
"loss": 0.3739,
"step": 217
},
{
"epoch": 1.03,
"learning_rate": 1.5455791618126407e-05,
"loss": 0.3322,
"step": 218
},
{
"epoch": 1.03,
"learning_rate": 1.541234409563923e-05,
"loss": 0.3449,
"step": 219
},
{
"epoch": 1.04,
"learning_rate": 1.536875159358673e-05,
"loss": 0.3532,
"step": 220
},
{
"epoch": 1.04,
"learning_rate": 1.5325015279674037e-05,
"loss": 0.347,
"step": 221
},
{
"epoch": 1.05,
"learning_rate": 1.5281136325458553e-05,
"loss": 0.3779,
"step": 222
},
{
"epoch": 1.05,
"learning_rate": 1.5237115906318565e-05,
"loss": 0.319,
"step": 223
},
{
"epoch": 1.06,
"learning_rate": 1.5192955201421743e-05,
"loss": 0.3532,
"step": 224
},
{
"epoch": 1.06,
"learning_rate": 1.5148655393693588e-05,
"loss": 0.3327,
"step": 225
},
{
"epoch": 1.07,
"learning_rate": 1.5104217669785714e-05,
"loss": 0.3584,
"step": 226
},
{
"epoch": 1.07,
"learning_rate": 1.5059643220044069e-05,
"loss": 0.3402,
"step": 227
},
{
"epoch": 1.08,
"learning_rate": 1.5014933238477069e-05,
"loss": 0.3407,
"step": 228
},
{
"epoch": 1.08,
"learning_rate": 1.4970088922723584e-05,
"loss": 0.3311,
"step": 229
},
{
"epoch": 1.09,
"learning_rate": 1.4925111474020875e-05,
"loss": 0.3565,
"step": 230
},
{
"epoch": 1.09,
"learning_rate": 1.488000209717242e-05,
"loss": 0.3542,
"step": 231
},
{
"epoch": 1.1,
"learning_rate": 1.4834762000515621e-05,
"loss": 0.3169,
"step": 232
},
{
"epoch": 1.1,
"learning_rate": 1.4789392395889468e-05,
"loss": 0.3301,
"step": 233
},
{
"epoch": 1.11,
"learning_rate": 1.4743894498602043e-05,
"loss": 0.3263,
"step": 234
},
{
"epoch": 1.11,
"learning_rate": 1.4698269527397993e-05,
"loss": 0.3058,
"step": 235
},
{
"epoch": 1.11,
"learning_rate": 1.4652518704425862e-05,
"loss": 0.3814,
"step": 236
},
{
"epoch": 1.12,
"learning_rate": 1.4606643255205377e-05,
"loss": 0.3334,
"step": 237
},
{
"epoch": 1.12,
"learning_rate": 1.4560644408594602e-05,
"loss": 0.3278,
"step": 238
},
{
"epoch": 1.13,
"learning_rate": 1.4514523396757025e-05,
"loss": 0.341,
"step": 239
},
{
"epoch": 1.13,
"learning_rate": 1.4468281455128554e-05,
"loss": 0.3417,
"step": 240
},
{
"epoch": 1.14,
"learning_rate": 1.442191982238443e-05,
"loss": 0.3869,
"step": 241
},
{
"epoch": 1.14,
"learning_rate": 1.4375439740406025e-05,
"loss": 0.3481,
"step": 242
},
{
"epoch": 1.15,
"learning_rate": 1.432884245424761e-05,
"loss": 0.3048,
"step": 243
},
{
"epoch": 1.15,
"learning_rate": 1.4282129212102968e-05,
"loss": 0.3402,
"step": 244
},
{
"epoch": 1.16,
"learning_rate": 1.4235301265271993e-05,
"loss": 0.3268,
"step": 245
},
{
"epoch": 1.16,
"learning_rate": 1.4188359868127135e-05,
"loss": 0.3362,
"step": 246
},
{
"epoch": 1.17,
"learning_rate": 1.4141306278079837e-05,
"loss": 0.3383,
"step": 247
},
{
"epoch": 1.17,
"learning_rate": 1.4094141755546816e-05,
"loss": 0.331,
"step": 248
},
{
"epoch": 1.18,
"learning_rate": 1.4046867563916337e-05,
"loss": 0.344,
"step": 249
},
{
"epoch": 1.18,
"learning_rate": 1.3999484969514345e-05,
"loss": 0.3301,
"step": 250
},
{
"epoch": 1.19,
"learning_rate": 1.3951995241570553e-05,
"loss": 0.3383,
"step": 251
},
{
"epoch": 1.19,
"learning_rate": 1.3904399652184437e-05,
"loss": 0.3118,
"step": 252
},
{
"epoch": 1.19,
"learning_rate": 1.3856699476291176e-05,
"loss": 0.3563,
"step": 253
},
{
"epoch": 1.2,
"learning_rate": 1.3808895991627482e-05,
"loss": 0.3526,
"step": 254
},
{
"epoch": 1.2,
"learning_rate": 1.3760990478697389e-05,
"loss": 0.3219,
"step": 255
},
{
"epoch": 1.21,
"learning_rate": 1.371298422073794e-05,
"loss": 0.3505,
"step": 256
},
{
"epoch": 1.21,
"learning_rate": 1.3664878503684817e-05,
"loss": 0.3484,
"step": 257
},
{
"epoch": 1.22,
"learning_rate": 1.3616674616137902e-05,
"loss": 0.328,
"step": 258
},
{
"epoch": 1.22,
"learning_rate": 1.356837384932675e-05,
"loss": 0.3702,
"step": 259
},
{
"epoch": 1.23,
"learning_rate": 1.3519977497076006e-05,
"loss": 0.3438,
"step": 260
},
{
"epoch": 1.23,
"learning_rate": 1.347148685577075e-05,
"loss": 0.3294,
"step": 261
},
{
"epoch": 1.24,
"learning_rate": 1.3422903224321754e-05,
"loss": 0.3473,
"step": 262
},
{
"epoch": 1.24,
"learning_rate": 1.3374227904130724e-05,
"loss": 0.3229,
"step": 263
},
{
"epoch": 1.25,
"learning_rate": 1.3325462199055393e-05,
"loss": 0.3592,
"step": 264
},
{
"epoch": 1.25,
"learning_rate": 1.3276607415374639e-05,
"loss": 0.3448,
"step": 265
},
{
"epoch": 1.26,
"learning_rate": 1.3227664861753455e-05,
"loss": 0.3389,
"step": 266
},
{
"epoch": 1.26,
"learning_rate": 1.3178635849207933e-05,
"loss": 0.3418,
"step": 267
},
{
"epoch": 1.27,
"learning_rate": 1.3129521691070108e-05,
"loss": 0.3118,
"step": 268
},
{
"epoch": 1.27,
"learning_rate": 1.308032370295281e-05,
"loss": 0.3169,
"step": 269
},
{
"epoch": 1.28,
"learning_rate": 1.3031043202714395e-05,
"loss": 0.3246,
"step": 270
},
{
"epoch": 1.28,
"learning_rate": 1.2981681510423471e-05,
"loss": 0.333,
"step": 271
},
{
"epoch": 1.28,
"learning_rate": 1.2932239948323517e-05,
"loss": 0.3416,
"step": 272
},
{
"epoch": 1.29,
"learning_rate": 1.2882719840797473e-05,
"loss": 0.3383,
"step": 273
},
{
"epoch": 1.29,
"learning_rate": 1.2833122514332259e-05,
"loss": 0.3266,
"step": 274
},
{
"epoch": 1.3,
"learning_rate": 1.278344929748325e-05,
"loss": 0.338,
"step": 275
},
{
"epoch": 1.3,
"learning_rate": 1.2733701520838681e-05,
"loss": 0.3586,
"step": 276
},
{
"epoch": 1.31,
"learning_rate": 1.2683880516984016e-05,
"loss": 0.3124,
"step": 277
},
{
"epoch": 1.31,
"learning_rate": 1.2633987620466229e-05,
"loss": 0.3601,
"step": 278
},
{
"epoch": 1.32,
"learning_rate": 1.2584024167758088e-05,
"loss": 0.3174,
"step": 279
},
{
"epoch": 1.32,
"learning_rate": 1.2533991497222324e-05,
"loss": 0.3093,
"step": 280
},
{
"epoch": 1.33,
"learning_rate": 1.2483890949075803e-05,
"loss": 0.3547,
"step": 281
},
{
"epoch": 1.33,
"learning_rate": 1.2433723865353613e-05,
"loss": 0.3313,
"step": 282
},
{
"epoch": 1.34,
"learning_rate": 1.2383491589873122e-05,
"loss": 0.3569,
"step": 283
},
{
"epoch": 1.34,
"learning_rate": 1.2333195468197975e-05,
"loss": 0.3043,
"step": 284
},
{
"epoch": 1.35,
"learning_rate": 1.2282836847602062e-05,
"loss": 0.3282,
"step": 285
},
{
"epoch": 1.35,
"learning_rate": 1.2232417077033415e-05,
"loss": 0.334,
"step": 286
},
{
"epoch": 1.36,
"learning_rate": 1.2181937507078079e-05,
"loss": 0.3172,
"step": 287
},
{
"epoch": 1.36,
"learning_rate": 1.213139948992394e-05,
"loss": 0.3322,
"step": 288
},
{
"epoch": 1.36,
"learning_rate": 1.2080804379324497e-05,
"loss": 0.301,
"step": 289
},
{
"epoch": 1.37,
"learning_rate": 1.2030153530562602e-05,
"loss": 0.325,
"step": 290
},
{
"epoch": 1.37,
"learning_rate": 1.197944830041416e-05,
"loss": 0.3254,
"step": 291
},
{
"epoch": 1.38,
"learning_rate": 1.1928690047111773e-05,
"loss": 0.3,
"step": 292
},
{
"epoch": 1.38,
"learning_rate": 1.187788013030837e-05,
"loss": 0.3367,
"step": 293
},
{
"epoch": 1.39,
"learning_rate": 1.1827019911040778e-05,
"loss": 0.3458,
"step": 294
},
{
"epoch": 1.39,
"learning_rate": 1.177611075169328e-05,
"loss": 0.3664,
"step": 295
},
{
"epoch": 1.4,
"learning_rate": 1.1725154015961089e-05,
"loss": 0.3183,
"step": 296
},
{
"epoch": 1.4,
"learning_rate": 1.1674151068813856e-05,
"loss": 0.3339,
"step": 297
},
{
"epoch": 1.41,
"learning_rate": 1.1623103276459086e-05,
"loss": 0.3335,
"step": 298
},
{
"epoch": 1.41,
"learning_rate": 1.1572012006305537e-05,
"loss": 0.3194,
"step": 299
},
{
"epoch": 1.42,
"learning_rate": 1.1520878626926608e-05,
"loss": 0.3252,
"step": 300
},
{
"epoch": 1.42,
"learning_rate": 1.1469704508023667e-05,
"loss": 0.3683,
"step": 301
},
{
"epoch": 1.43,
"learning_rate": 1.1418491020389363e-05,
"loss": 0.3451,
"step": 302
},
{
"epoch": 1.43,
"learning_rate": 1.1367239535870913e-05,
"loss": 0.3611,
"step": 303
},
{
"epoch": 1.44,
"learning_rate": 1.1315951427333352e-05,
"loss": 0.3126,
"step": 304
},
{
"epoch": 1.44,
"learning_rate": 1.1264628068622747e-05,
"loss": 0.3298,
"step": 305
},
{
"epoch": 1.45,
"learning_rate": 1.1213270834529419e-05,
"loss": 0.3112,
"step": 306
},
{
"epoch": 1.45,
"learning_rate": 1.1161881100751088e-05,
"loss": 0.3426,
"step": 307
},
{
"epoch": 1.45,
"learning_rate": 1.1110460243856051e-05,
"loss": 0.3406,
"step": 308
},
{
"epoch": 1.46,
"learning_rate": 1.1059009641246288e-05,
"loss": 0.3537,
"step": 309
},
{
"epoch": 1.46,
"learning_rate": 1.1007530671120573e-05,
"loss": 0.3349,
"step": 310
},
{
"epoch": 1.47,
"learning_rate": 1.0956024712437559e-05,
"loss": 0.3462,
"step": 311
},
{
"epoch": 1.47,
"learning_rate": 1.0904493144878834e-05,
"loss": 0.3757,
"step": 312
},
{
"epoch": 1.48,
"learning_rate": 1.085293734881197e-05,
"loss": 0.3312,
"step": 313
},
{
"epoch": 1.48,
"learning_rate": 1.0801358705253535e-05,
"loss": 0.3428,
"step": 314
},
{
"epoch": 1.49,
"learning_rate": 1.074975859583212e-05,
"loss": 0.328,
"step": 315
},
{
"epoch": 1.49,
"learning_rate": 1.0698138402751314e-05,
"loss": 0.3453,
"step": 316
},
{
"epoch": 1.5,
"learning_rate": 1.0646499508752684e-05,
"loss": 0.3221,
"step": 317
},
{
"epoch": 1.5,
"learning_rate": 1.0594843297078736e-05,
"loss": 0.348,
"step": 318
},
{
"epoch": 1.51,
"learning_rate": 1.0543171151435859e-05,
"loss": 0.3332,
"step": 319
},
{
"epoch": 1.51,
"learning_rate": 1.0491484455957264e-05,
"loss": 0.345,
"step": 320
},
{
"epoch": 1.52,
"learning_rate": 1.0439784595165909e-05,
"loss": 0.3248,
"step": 321
},
{
"epoch": 1.52,
"learning_rate": 1.0388072953937406e-05,
"loss": 0.3232,
"step": 322
},
{
"epoch": 1.53,
"learning_rate": 1.0336350917462925e-05,
"loss": 0.3645,
"step": 323
},
{
"epoch": 1.53,
"learning_rate": 1.02846198712121e-05,
"loss": 0.3487,
"step": 324
},
{
"epoch": 1.53,
"learning_rate": 1.0232881200895903e-05,
"loss": 0.296,
"step": 325
},
{
"epoch": 1.54,
"learning_rate": 1.0181136292429528e-05,
"loss": 0.3625,
"step": 326
},
{
"epoch": 1.54,
"learning_rate": 1.0129386531895271e-05,
"loss": 0.3353,
"step": 327
},
{
"epoch": 1.55,
"learning_rate": 1.0077633305505402e-05,
"loss": 0.3626,
"step": 328
},
{
"epoch": 1.55,
"learning_rate": 1.0025877999565033e-05,
"loss": 0.3327,
"step": 329
},
{
"epoch": 1.56,
"learning_rate": 9.974122000434972e-06,
"loss": 0.3041,
"step": 330
},
{
"epoch": 1.56,
"learning_rate": 9.922366694494603e-06,
"loss": 0.358,
"step": 331
},
{
"epoch": 1.57,
"learning_rate": 9.87061346810473e-06,
"loss": 0.3464,
"step": 332
},
{
"epoch": 1.57,
"learning_rate": 9.818863707570476e-06,
"loss": 0.3411,
"step": 333
},
{
"epoch": 1.58,
"learning_rate": 9.767118799104099e-06,
"loss": 0.31,
"step": 334
},
{
"epoch": 1.58,
"learning_rate": 9.7153801287879e-06,
"loss": 0.3477,
"step": 335
},
{
"epoch": 1.59,
"learning_rate": 9.663649082537075e-06,
"loss": 0.342,
"step": 336
},
{
"epoch": 1.59,
"learning_rate": 9.611927046062596e-06,
"loss": 0.3516,
"step": 337
},
{
"epoch": 1.6,
"learning_rate": 9.560215404834094e-06,
"loss": 0.3493,
"step": 338
},
{
"epoch": 1.6,
"learning_rate": 9.50851554404274e-06,
"loss": 0.2968,
"step": 339
},
{
"epoch": 1.61,
"learning_rate": 9.456828848564143e-06,
"loss": 0.3231,
"step": 340
},
{
"epoch": 1.61,
"learning_rate": 9.405156702921266e-06,
"loss": 0.3272,
"step": 341
},
{
"epoch": 1.62,
"learning_rate": 9.35350049124732e-06,
"loss": 0.3403,
"step": 342
},
{
"epoch": 1.62,
"learning_rate": 9.30186159724869e-06,
"loss": 0.3594,
"step": 343
},
{
"epoch": 1.62,
"learning_rate": 9.250241404167882e-06,
"loss": 0.2982,
"step": 344
},
{
"epoch": 1.63,
"learning_rate": 9.198641294746467e-06,
"loss": 0.3288,
"step": 345
},
{
"epoch": 1.63,
"learning_rate": 9.147062651188034e-06,
"loss": 0.334,
"step": 346
},
{
"epoch": 1.64,
"learning_rate": 9.095506855121168e-06,
"loss": 0.3124,
"step": 347
},
{
"epoch": 1.64,
"learning_rate": 9.043975287562443e-06,
"loss": 0.3359,
"step": 348
},
{
"epoch": 1.65,
"learning_rate": 8.992469328879428e-06,
"loss": 0.3184,
"step": 349
},
{
"epoch": 1.65,
"learning_rate": 8.940990358753716e-06,
"loss": 0.3314,
"step": 350
},
{
"epoch": 1.66,
"learning_rate": 8.889539756143954e-06,
"loss": 0.3295,
"step": 351
},
{
"epoch": 1.66,
"learning_rate": 8.838118899248914e-06,
"loss": 0.3236,
"step": 352
},
{
"epoch": 1.67,
"learning_rate": 8.786729165470584e-06,
"loss": 0.3356,
"step": 353
},
{
"epoch": 1.67,
"learning_rate": 8.735371931377254e-06,
"loss": 0.3234,
"step": 354
},
{
"epoch": 1.68,
"learning_rate": 8.684048572666653e-06,
"loss": 0.32,
"step": 355
},
{
"epoch": 1.68,
"learning_rate": 8.632760464129086e-06,
"loss": 0.3297,
"step": 356
},
{
"epoch": 1.69,
"learning_rate": 8.581508979610638e-06,
"loss": 0.3345,
"step": 357
},
{
"epoch": 1.69,
"learning_rate": 8.530295491976338e-06,
"loss": 0.337,
"step": 358
},
{
"epoch": 1.7,
"learning_rate": 8.479121373073396e-06,
"loss": 0.3301,
"step": 359
},
{
"epoch": 1.7,
"learning_rate": 8.427987993694465e-06,
"loss": 0.3073,
"step": 360
},
{
"epoch": 1.7,
"learning_rate": 8.376896723540916e-06,
"loss": 0.3528,
"step": 361
},
{
"epoch": 1.71,
"learning_rate": 8.325848931186145e-06,
"loss": 0.2995,
"step": 362
},
{
"epoch": 1.71,
"learning_rate": 8.274845984038916e-06,
"loss": 0.3488,
"step": 363
},
{
"epoch": 1.72,
"learning_rate": 8.223889248306725e-06,
"loss": 0.3021,
"step": 364
},
{
"epoch": 1.72,
"learning_rate": 8.172980088959223e-06,
"loss": 0.3565,
"step": 365
},
{
"epoch": 1.73,
"learning_rate": 8.122119869691636e-06,
"loss": 0.3096,
"step": 366
},
{
"epoch": 1.73,
"learning_rate": 8.07130995288823e-06,
"loss": 0.333,
"step": 367
},
{
"epoch": 1.74,
"learning_rate": 8.020551699585843e-06,
"loss": 0.3289,
"step": 368
},
{
"epoch": 1.74,
"learning_rate": 7.9698464694374e-06,
"loss": 0.3299,
"step": 369
},
{
"epoch": 1.75,
"learning_rate": 7.919195620675505e-06,
"loss": 0.3376,
"step": 370
},
{
"epoch": 1.75,
"learning_rate": 7.868600510076061e-06,
"loss": 0.3158,
"step": 371
},
{
"epoch": 1.76,
"learning_rate": 7.818062492921925e-06,
"loss": 0.3195,
"step": 372
},
{
"epoch": 1.76,
"learning_rate": 7.76758292296659e-06,
"loss": 0.3155,
"step": 373
},
{
"epoch": 1.77,
"learning_rate": 7.717163152397943e-06,
"loss": 0.3116,
"step": 374
},
{
"epoch": 1.77,
"learning_rate": 7.666804531802026e-06,
"loss": 0.3198,
"step": 375
},
{
"epoch": 1.78,
"learning_rate": 7.616508410126882e-06,
"loss": 0.3457,
"step": 376
},
{
"epoch": 1.78,
"learning_rate": 7.566276134646391e-06,
"loss": 0.2974,
"step": 377
},
{
"epoch": 1.79,
"learning_rate": 7.5161090509242005e-06,
"loss": 0.3512,
"step": 378
},
{
"epoch": 1.79,
"learning_rate": 7.466008502777679e-06,
"loss": 0.3629,
"step": 379
},
{
"epoch": 1.79,
"learning_rate": 7.415975832241915e-06,
"loss": 0.369,
"step": 380
},
{
"epoch": 1.8,
"learning_rate": 7.3660123795337735e-06,
"loss": 0.3278,
"step": 381
},
{
"epoch": 1.8,
"learning_rate": 7.316119483015988e-06,
"loss": 0.3314,
"step": 382
},
{
"epoch": 1.81,
"learning_rate": 7.2662984791613186e-06,
"loss": 0.3352,
"step": 383
},
{
"epoch": 1.81,
"learning_rate": 7.2165507025167525e-06,
"loss": 0.3513,
"step": 384
},
{
"epoch": 1.82,
"learning_rate": 7.166877485667745e-06,
"loss": 0.3309,
"step": 385
},
{
"epoch": 1.82,
"learning_rate": 7.117280159202531e-06,
"loss": 0.3098,
"step": 386
},
{
"epoch": 1.83,
"learning_rate": 7.067760051676482e-06,
"loss": 0.3068,
"step": 387
},
{
"epoch": 1.83,
"learning_rate": 7.01831848957653e-06,
"loss": 0.3321,
"step": 388
},
{
"epoch": 1.84,
"learning_rate": 6.968956797285607e-06,
"loss": 0.3179,
"step": 389
},
{
"epoch": 1.84,
"learning_rate": 6.919676297047196e-06,
"loss": 0.3406,
"step": 390
},
{
"epoch": 1.85,
"learning_rate": 6.870478308929894e-06,
"loss": 0.3399,
"step": 391
},
{
"epoch": 1.85,
"learning_rate": 6.821364150792072e-06,
"loss": 0.3322,
"step": 392
},
{
"epoch": 1.86,
"learning_rate": 6.772335138246548e-06,
"loss": 0.3496,
"step": 393
},
{
"epoch": 1.86,
"learning_rate": 6.723392584625368e-06,
"loss": 0.2918,
"step": 394
},
{
"epoch": 1.87,
"learning_rate": 6.674537800944607e-06,
"loss": 0.3013,
"step": 395
},
{
"epoch": 1.87,
"learning_rate": 6.625772095869278e-06,
"loss": 0.3326,
"step": 396
},
{
"epoch": 1.87,
"learning_rate": 6.577096775678246e-06,
"loss": 0.3112,
"step": 397
},
{
"epoch": 1.88,
"learning_rate": 6.528513144229256e-06,
"loss": 0.3481,
"step": 398
},
{
"epoch": 1.88,
"learning_rate": 6.480022502923995e-06,
"loss": 0.3222,
"step": 399
},
{
"epoch": 1.89,
"learning_rate": 6.431626150673251e-06,
"loss": 0.3336,
"step": 400
},
{
"epoch": 1.89,
"learning_rate": 6.383325383862102e-06,
"loss": 0.3389,
"step": 401
},
{
"epoch": 1.9,
"learning_rate": 6.3351214963151875e-06,
"loss": 0.3341,
"step": 402
},
{
"epoch": 1.9,
"learning_rate": 6.287015779262064e-06,
"loss": 0.3464,
"step": 403
},
{
"epoch": 1.91,
"learning_rate": 6.239009521302614e-06,
"loss": 0.3185,
"step": 404
},
{
"epoch": 1.91,
"learning_rate": 6.191104008372522e-06,
"loss": 0.3384,
"step": 405
},
{
"epoch": 1.92,
"learning_rate": 6.143300523708828e-06,
"loss": 0.3039,
"step": 406
},
{
"epoch": 1.92,
"learning_rate": 6.095600347815564e-06,
"loss": 0.2959,
"step": 407
},
{
"epoch": 1.93,
"learning_rate": 6.048004758429451e-06,
"loss": 0.3292,
"step": 408
},
{
"epoch": 1.93,
"learning_rate": 6.0005150304856574e-06,
"loss": 0.3343,
"step": 409
},
{
"epoch": 1.94,
"learning_rate": 5.953132436083666e-06,
"loss": 0.3392,
"step": 410
},
{
"epoch": 1.94,
"learning_rate": 5.905858244453184e-06,
"loss": 0.3319,
"step": 411
},
{
"epoch": 1.95,
"learning_rate": 5.8586937219201665e-06,
"loss": 0.3332,
"step": 412
},
{
"epoch": 1.95,
"learning_rate": 5.811640131872867e-06,
"loss": 0.3663,
"step": 413
},
{
"epoch": 1.96,
"learning_rate": 5.76469873472801e-06,
"loss": 0.3352,
"step": 414
},
{
"epoch": 1.96,
"learning_rate": 5.717870787897028e-06,
"loss": 0.3426,
"step": 415
},
{
"epoch": 1.96,
"learning_rate": 5.67115754575239e-06,
"loss": 0.343,
"step": 416
},
{
"epoch": 1.97,
"learning_rate": 5.624560259593976e-06,
"loss": 0.313,
"step": 417
},
{
"epoch": 1.97,
"learning_rate": 5.578080177615575e-06,
"loss": 0.3561,
"step": 418
},
{
"epoch": 1.98,
"learning_rate": 5.531718544871448e-06,
"loss": 0.335,
"step": 419
},
{
"epoch": 1.98,
"learning_rate": 5.485476603242979e-06,
"loss": 0.3531,
"step": 420
},
{
"epoch": 1.99,
"learning_rate": 5.439355591405403e-06,
"loss": 0.3141,
"step": 421
},
{
"epoch": 1.99,
"learning_rate": 5.393356744794629e-06,
"loss": 0.2924,
"step": 422
},
{
"epoch": 2.0,
"learning_rate": 5.347481295574141e-06,
"loss": 0.3326,
"step": 423
},
{
"epoch": 2.0,
"learning_rate": 5.3017304726020126e-06,
"loss": 0.2575,
"step": 424
},
{
"epoch": 2.01,
"learning_rate": 5.256105501397961e-06,
"loss": 0.2195,
"step": 425
},
{
"epoch": 2.01,
"learning_rate": 5.210607604110537e-06,
"loss": 0.2026,
"step": 426
},
{
"epoch": 2.02,
"learning_rate": 5.165237999484378e-06,
"loss": 0.1907,
"step": 427
},
{
"epoch": 2.02,
"learning_rate": 5.119997902827584e-06,
"loss": 0.2075,
"step": 428
},
{
"epoch": 2.03,
"learning_rate": 5.074888525979128e-06,
"loss": 0.2137,
"step": 429
},
{
"epoch": 2.03,
"learning_rate": 5.029911077276422e-06,
"loss": 0.1949,
"step": 430
},
{
"epoch": 2.04,
"learning_rate": 4.985066761522932e-06,
"loss": 0.1534,
"step": 431
},
{
"epoch": 2.04,
"learning_rate": 4.940356779955933e-06,
"loss": 0.1946,
"step": 432
},
{
"epoch": 2.04,
"learning_rate": 4.8957823302142916e-06,
"loss": 0.1682,
"step": 433
},
{
"epoch": 2.05,
"learning_rate": 4.851344606306413e-06,
"loss": 0.1998,
"step": 434
},
{
"epoch": 2.05,
"learning_rate": 4.8070447985782575e-06,
"loss": 0.1824,
"step": 435
},
{
"epoch": 2.06,
"learning_rate": 4.762884093681439e-06,
"loss": 0.1903,
"step": 436
},
{
"epoch": 2.06,
"learning_rate": 4.718863674541449e-06,
"loss": 0.1957,
"step": 437
},
{
"epoch": 2.07,
"learning_rate": 4.674984720325961e-06,
"loss": 0.1954,
"step": 438
},
{
"epoch": 2.07,
"learning_rate": 4.63124840641327e-06,
"loss": 0.2178,
"step": 439
},
{
"epoch": 2.08,
"learning_rate": 4.587655904360769e-06,
"loss": 0.2002,
"step": 440
},
{
"epoch": 2.08,
"learning_rate": 4.544208381873597e-06,
"loss": 0.1907,
"step": 441
},
{
"epoch": 2.09,
"learning_rate": 4.500907002773345e-06,
"loss": 0.1878,
"step": 442
},
{
"epoch": 2.09,
"learning_rate": 4.457752926966888e-06,
"loss": 0.1768,
"step": 443
},
{
"epoch": 2.1,
"learning_rate": 4.414747310415308e-06,
"loss": 0.184,
"step": 444
},
{
"epoch": 2.1,
"learning_rate": 4.37189130510294e-06,
"loss": 0.1842,
"step": 445
},
{
"epoch": 2.11,
"learning_rate": 4.329186059006498e-06,
"loss": 0.1932,
"step": 446
},
{
"epoch": 2.11,
"learning_rate": 4.2866327160643485e-06,
"loss": 0.1747,
"step": 447
},
{
"epoch": 2.12,
"learning_rate": 4.244232416145839e-06,
"loss": 0.1876,
"step": 448
},
{
"epoch": 2.12,
"learning_rate": 4.201986295020786e-06,
"loss": 0.1661,
"step": 449
},
{
"epoch": 2.13,
"learning_rate": 4.159895484329039e-06,
"loss": 0.1831,
"step": 450
},
{
"epoch": 2.13,
"learning_rate": 4.117961111550183e-06,
"loss": 0.1571,
"step": 451
},
{
"epoch": 2.13,
"learning_rate": 4.076184299973316e-06,
"loss": 0.2028,
"step": 452
},
{
"epoch": 2.14,
"learning_rate": 4.0345661686669745e-06,
"loss": 0.1949,
"step": 453
},
{
"epoch": 2.14,
"learning_rate": 3.993107832449149e-06,
"loss": 0.1925,
"step": 454
},
{
"epoch": 2.15,
"learning_rate": 3.9518104018574345e-06,
"loss": 0.178,
"step": 455
},
{
"epoch": 2.15,
"learning_rate": 3.910674983119266e-06,
"loss": 0.1696,
"step": 456
},
{
"epoch": 2.16,
"learning_rate": 3.869702678122293e-06,
"loss": 0.1973,
"step": 457
},
{
"epoch": 2.16,
"learning_rate": 3.828894584384867e-06,
"loss": 0.156,
"step": 458
},
{
"epoch": 2.17,
"learning_rate": 3.788251795026645e-06,
"loss": 0.1759,
"step": 459
},
{
"epoch": 2.17,
"learning_rate": 3.7477753987392927e-06,
"loss": 0.1725,
"step": 460
},
{
"epoch": 2.18,
"learning_rate": 3.707466479757338e-06,
"loss": 0.1786,
"step": 461
},
{
"epoch": 2.18,
"learning_rate": 3.667326117829119e-06,
"loss": 0.1827,
"step": 462
},
{
"epoch": 2.19,
"learning_rate": 3.62735538818787e-06,
"loss": 0.1666,
"step": 463
},
{
"epoch": 2.19,
"learning_rate": 3.5875553615229064e-06,
"loss": 0.1841,
"step": 464
},
{
"epoch": 2.2,
"learning_rate": 3.5479271039509555e-06,
"loss": 0.1742,
"step": 465
},
{
"epoch": 2.2,
"learning_rate": 3.5084716769875906e-06,
"loss": 0.1878,
"step": 466
},
{
"epoch": 2.21,
"learning_rate": 3.469190137518804e-06,
"loss": 0.1991,
"step": 467
},
{
"epoch": 2.21,
"learning_rate": 3.4300835377726904e-06,
"loss": 0.1661,
"step": 468
},
{
"epoch": 2.21,
"learning_rate": 3.3911529252912633e-06,
"loss": 0.1845,
"step": 469
},
{
"epoch": 2.22,
"learning_rate": 3.3523993429023914e-06,
"loss": 0.1917,
"step": 470
},
{
"epoch": 2.22,
"learning_rate": 3.3138238286918777e-06,
"loss": 0.1871,
"step": 471
},
{
"epoch": 2.23,
"learning_rate": 3.2754274159756316e-06,
"loss": 0.167,
"step": 472
},
{
"epoch": 2.23,
"learning_rate": 3.2372111332720045e-06,
"loss": 0.1978,
"step": 473
},
{
"epoch": 2.24,
"learning_rate": 3.1991760042742316e-06,
"loss": 0.1784,
"step": 474
},
{
"epoch": 2.24,
"learning_rate": 3.1613230478230238e-06,
"loss": 0.1718,
"step": 475
},
{
"epoch": 2.25,
"learning_rate": 3.1236532778792563e-06,
"loss": 0.1805,
"step": 476
},
{
"epoch": 2.25,
"learning_rate": 3.086167703496821e-06,
"loss": 0.1995,
"step": 477
},
{
"epoch": 2.26,
"learning_rate": 3.048867328795588e-06,
"loss": 0.1641,
"step": 478
},
{
"epoch": 2.26,
"learning_rate": 3.011753152934529e-06,
"loss": 0.2065,
"step": 479
},
{
"epoch": 2.27,
"learning_rate": 2.9748261700849245e-06,
"loss": 0.1805,
"step": 480
},
{
"epoch": 2.27,
"learning_rate": 2.9380873694037515e-06,
"loss": 0.1814,
"step": 481
},
{
"epoch": 2.28,
"learning_rate": 2.9015377350071785e-06,
"loss": 0.1965,
"step": 482
},
{
"epoch": 2.28,
"learning_rate": 2.865178245944218e-06,
"loss": 0.1832,
"step": 483
},
{
"epoch": 2.29,
"learning_rate": 2.829009876170481e-06,
"loss": 0.2169,
"step": 484
},
{
"epoch": 2.29,
"learning_rate": 2.793033594522102e-06,
"loss": 0.1803,
"step": 485
},
{
"epoch": 2.3,
"learning_rate": 2.757250364689782e-06,
"loss": 0.1811,
"step": 486
},
{
"epoch": 2.3,
"learning_rate": 2.7216611451929754e-06,
"loss": 0.1507,
"step": 487
},
{
"epoch": 2.3,
"learning_rate": 2.686266889354211e-06,
"loss": 0.1811,
"step": 488
},
{
"epoch": 2.31,
"learning_rate": 2.6510685452735608e-06,
"loss": 0.1673,
"step": 489
},
{
"epoch": 2.31,
"learning_rate": 2.6160670558032454e-06,
"loss": 0.1998,
"step": 490
},
{
"epoch": 2.32,
"learning_rate": 2.5812633585223657e-06,
"loss": 0.1791,
"step": 491
},
{
"epoch": 2.32,
"learning_rate": 2.546658385711801e-06,
"loss": 0.1756,
"step": 492
},
{
"epoch": 2.33,
"learning_rate": 2.5122530643292274e-06,
"loss": 0.1733,
"step": 493
},
{
"epoch": 2.33,
"learning_rate": 2.478048315984293e-06,
"loss": 0.1653,
"step": 494
},
{
"epoch": 2.34,
"learning_rate": 2.444045056913932e-06,
"loss": 0.1682,
"step": 495
},
{
"epoch": 2.34,
"learning_rate": 2.410244197957815e-06,
"loss": 0.1801,
"step": 496
},
{
"epoch": 2.35,
"learning_rate": 2.3766466445339565e-06,
"loss": 0.1858,
"step": 497
},
{
"epoch": 2.35,
"learning_rate": 2.3432532966144526e-06,
"loss": 0.1903,
"step": 498
},
{
"epoch": 2.36,
"learning_rate": 2.3100650487013953e-06,
"loss": 0.1836,
"step": 499
},
{
"epoch": 2.36,
"learning_rate": 2.2770827898028825e-06,
"loss": 0.1884,
"step": 500
},
{
"epoch": 2.37,
"learning_rate": 2.2443074034092204e-06,
"loss": 0.1955,
"step": 501
},
{
"epoch": 2.37,
"learning_rate": 2.2117397674692654e-06,
"loss": 0.1802,
"step": 502
},
{
"epoch": 2.38,
"learning_rate": 2.1793807543668857e-06,
"loss": 0.1703,
"step": 503
},
{
"epoch": 2.38,
"learning_rate": 2.1472312308976105e-06,
"loss": 0.184,
"step": 504
},
{
"epoch": 2.38,
"learning_rate": 2.1152920582453995e-06,
"loss": 0.1711,
"step": 505
},
{
"epoch": 2.39,
"learning_rate": 2.0835640919595877e-06,
"loss": 0.1861,
"step": 506
},
{
"epoch": 2.39,
"learning_rate": 2.052048181931955e-06,
"loss": 0.1663,
"step": 507
},
{
"epoch": 2.4,
"learning_rate": 2.0207451723739633e-06,
"loss": 0.1841,
"step": 508
},
{
"epoch": 2.4,
"learning_rate": 1.9896559017941508e-06,
"loss": 0.1764,
"step": 509
},
{
"epoch": 2.41,
"learning_rate": 1.9587812029756612e-06,
"loss": 0.1668,
"step": 510
},
{
"epoch": 2.41,
"learning_rate": 1.928121902953939e-06,
"loss": 0.1911,
"step": 511
},
{
"epoch": 2.42,
"learning_rate": 1.8976788229945796e-06,
"loss": 0.191,
"step": 512
},
{
"epoch": 2.42,
"learning_rate": 1.8674527785713247e-06,
"loss": 0.1869,
"step": 513
},
{
"epoch": 2.43,
"learning_rate": 1.8374445793442264e-06,
"loss": 0.1982,
"step": 514
},
{
"epoch": 2.43,
"learning_rate": 1.8076550291379479e-06,
"loss": 0.1654,
"step": 515
},
{
"epoch": 2.44,
"learning_rate": 1.7780849259202393e-06,
"loss": 0.1685,
"step": 516
},
{
"epoch": 2.44,
"learning_rate": 1.7487350617805577e-06,
"loss": 0.1812,
"step": 517
},
{
"epoch": 2.45,
"learning_rate": 1.7196062229088606e-06,
"loss": 0.1691,
"step": 518
},
{
"epoch": 2.45,
"learning_rate": 1.6906991895745284e-06,
"loss": 0.1777,
"step": 519
},
{
"epoch": 2.46,
"learning_rate": 1.6620147361054806e-06,
"loss": 0.1903,
"step": 520
},
{
"epoch": 2.46,
"learning_rate": 1.6335536308674204e-06,
"loss": 0.2013,
"step": 521
},
{
"epoch": 2.47,
"learning_rate": 1.6053166362432659e-06,
"loss": 0.1702,
"step": 522
},
{
"epoch": 2.47,
"learning_rate": 1.577304508612717e-06,
"loss": 0.1571,
"step": 523
},
{
"epoch": 2.47,
"learning_rate": 1.5495179983319986e-06,
"loss": 0.1918,
"step": 524
},
{
"epoch": 2.48,
"learning_rate": 1.52195784971376e-06,
"loss": 0.1844,
"step": 525
},
{
"epoch": 2.48,
"learning_rate": 1.494624801007144e-06,
"loss": 0.2017,
"step": 526
},
{
"epoch": 2.49,
"learning_rate": 1.4675195843779989e-06,
"loss": 0.1924,
"step": 527
},
{
"epoch": 2.49,
"learning_rate": 1.4406429258892762e-06,
"loss": 0.181,
"step": 528
},
{
"epoch": 2.5,
"learning_rate": 1.4139955454815757e-06,
"loss": 0.1809,
"step": 529
},
{
"epoch": 2.5,
"learning_rate": 1.3875781569538682e-06,
"loss": 0.1682,
"step": 530
},
{
"epoch": 2.51,
"learning_rate": 1.3613914679443675e-06,
"loss": 0.1746,
"step": 531
},
{
"epoch": 2.51,
"learning_rate": 1.3354361799115745e-06,
"loss": 0.1989,
"step": 532
},
{
"epoch": 2.52,
"learning_rate": 1.3097129881154936e-06,
"loss": 0.1749,
"step": 533
},
{
"epoch": 2.52,
"learning_rate": 1.2842225815990062e-06,
"loss": 0.175,
"step": 534
},
{
"epoch": 2.53,
"learning_rate": 1.258965643169412e-06,
"loss": 0.1622,
"step": 535
},
{
"epoch": 2.53,
"learning_rate": 1.2339428493801387e-06,
"loss": 0.1854,
"step": 536
},
{
"epoch": 2.54,
"learning_rate": 1.2091548705126188e-06,
"loss": 0.1882,
"step": 537
},
{
"epoch": 2.54,
"learning_rate": 1.1846023705583442e-06,
"loss": 0.2027,
"step": 538
},
{
"epoch": 2.55,
"learning_rate": 1.1602860072010648e-06,
"loss": 0.1575,
"step": 539
},
{
"epoch": 2.55,
"learning_rate": 1.1362064317991793e-06,
"loss": 0.1786,
"step": 540
},
{
"epoch": 2.55,
"learning_rate": 1.1123642893682862e-06,
"loss": 0.195,
"step": 541
},
{
"epoch": 2.56,
"learning_rate": 1.0887602185639134e-06,
"loss": 0.195,
"step": 542
},
{
"epoch": 2.56,
"learning_rate": 1.065394851664394e-06,
"loss": 0.1893,
"step": 543
},
{
"epoch": 2.57,
"learning_rate": 1.042268814553944e-06,
"loss": 0.1634,
"step": 544
},
{
"epoch": 2.57,
"learning_rate": 1.0193827267058897e-06,
"loss": 0.1841,
"step": 545
},
{
"epoch": 2.58,
"learning_rate": 9.967372011660814e-07,
"loss": 0.1964,
"step": 546
},
{
"epoch": 2.58,
"learning_rate": 9.743328445364608e-07,
"loss": 0.156,
"step": 547
},
{
"epoch": 2.59,
"learning_rate": 9.521702569588199e-07,
"loss": 0.1736,
"step": 548
},
{
"epoch": 2.59,
"learning_rate": 9.302500320987218e-07,
"loss": 0.1783,
"step": 549
},
{
"epoch": 2.6,
"learning_rate": 9.085727571296055e-07,
"loss": 0.1903,
"step": 550
},
{
"epoch": 2.6,
"learning_rate": 8.871390127170443e-07,
"loss": 0.1879,
"step": 551
},
{
"epoch": 2.61,
"learning_rate": 8.659493730032009e-07,
"loss": 0.2011,
"step": 552
},
{
"epoch": 2.61,
"learning_rate": 8.450044055914497e-07,
"loss": 0.2024,
"step": 553
},
{
"epoch": 2.62,
"learning_rate": 8.243046715311597e-07,
"loss": 0.1711,
"step": 554
},
{
"epoch": 2.62,
"learning_rate": 8.038507253026872e-07,
"loss": 0.1971,
"step": 555
},
{
"epoch": 2.63,
"learning_rate": 7.836431148025003e-07,
"loss": 0.1723,
"step": 556
},
{
"epoch": 2.63,
"learning_rate": 7.636823813285177e-07,
"loss": 0.1889,
"step": 557
},
{
"epoch": 2.64,
"learning_rate": 7.439690595656013e-07,
"loss": 0.1597,
"step": 558
},
{
"epoch": 2.64,
"learning_rate": 7.245036775712388e-07,
"loss": 0.2059,
"step": 559
},
{
"epoch": 2.64,
"learning_rate": 7.052867567613952e-07,
"loss": 0.1939,
"step": 560
},
{
"epoch": 2.65,
"learning_rate": 6.863188118965447e-07,
"loss": 0.1914,
"step": 561
},
{
"epoch": 2.65,
"learning_rate": 6.676003510678908e-07,
"loss": 0.1998,
"step": 562
},
{
"epoch": 2.66,
"learning_rate": 6.491318756837417e-07,
"loss": 0.1872,
"step": 563
},
{
"epoch": 2.66,
"learning_rate": 6.309138804560921e-07,
"loss": 0.1918,
"step": 564
},
{
"epoch": 2.67,
"learning_rate": 6.129468533873617e-07,
"loss": 0.219,
"step": 565
},
{
"epoch": 2.67,
"learning_rate": 5.952312757573342e-07,
"loss": 0.1958,
"step": 566
},
{
"epoch": 2.68,
"learning_rate": 5.777676221102524e-07,
"loss": 0.1686,
"step": 567
},
{
"epoch": 2.68,
"learning_rate": 5.605563602421149e-07,
"loss": 0.1935,
"step": 568
},
{
"epoch": 2.69,
"learning_rate": 5.435979511881472e-07,
"loss": 0.1808,
"step": 569
},
{
"epoch": 2.69,
"learning_rate": 5.268928492104442e-07,
"loss": 0.1664,
"step": 570
},
{
"epoch": 2.7,
"learning_rate": 5.104415017858055e-07,
"loss": 0.2028,
"step": 571
},
{
"epoch": 2.7,
"learning_rate": 4.94244349593751e-07,
"loss": 0.182,
"step": 572
},
{
"epoch": 2.71,
"learning_rate": 4.783018265047179e-07,
"loss": 0.1604,
"step": 573
},
{
"epoch": 2.71,
"learning_rate": 4.626143595684318e-07,
"loss": 0.1901,
"step": 574
},
{
"epoch": 2.72,
"learning_rate": 4.4718236900247236e-07,
"loss": 0.1894,
"step": 575
},
{
"epoch": 2.72,
"learning_rate": 4.3200626818101664e-07,
"loss": 0.1872,
"step": 576
},
{
"epoch": 2.72,
"learning_rate": 4.170864636237648e-07,
"loss": 0.1962,
"step": 577
},
{
"epoch": 2.73,
"learning_rate": 4.024233549850509e-07,
"loss": 0.1899,
"step": 578
},
{
"epoch": 2.73,
"learning_rate": 3.880173350431404e-07,
"loss": 0.2075,
"step": 579
},
{
"epoch": 2.74,
"learning_rate": 3.73868789689702e-07,
"loss": 0.2047,
"step": 580
},
{
"epoch": 2.74,
"learning_rate": 3.599780979194811e-07,
"loss": 0.1934,
"step": 581
},
{
"epoch": 2.75,
"learning_rate": 3.463456318201375e-07,
"loss": 0.2041,
"step": 582
},
{
"epoch": 2.75,
"learning_rate": 3.329717565622825e-07,
"loss": 0.1857,
"step": 583
},
{
"epoch": 2.76,
"learning_rate": 3.1985683038969984e-07,
"loss": 0.1718,
"step": 584
},
{
"epoch": 2.76,
"learning_rate": 3.0700120460974705e-07,
"loss": 0.1724,
"step": 585
},
{
"epoch": 2.77,
"learning_rate": 2.9440522358394233e-07,
"loss": 0.191,
"step": 586
},
{
"epoch": 2.77,
"learning_rate": 2.8206922471874396e-07,
"loss": 0.1777,
"step": 587
},
{
"epoch": 2.78,
"learning_rate": 2.6999353845651113e-07,
"loss": 0.1712,
"step": 588
},
{
"epoch": 2.78,
"learning_rate": 2.5817848826665494e-07,
"loss": 0.1988,
"step": 589
},
{
"epoch": 2.79,
"learning_rate": 2.466243906369681e-07,
"loss": 0.1662,
"step": 590
},
{
"epoch": 2.79,
"learning_rate": 2.3533155506515026e-07,
"loss": 0.1629,
"step": 591
},
{
"epoch": 2.8,
"learning_rate": 2.2430028405051817e-07,
"loss": 0.1653,
"step": 592
},
{
"epoch": 2.8,
"learning_rate": 2.1353087308590314e-07,
"loss": 0.187,
"step": 593
},
{
"epoch": 2.81,
"learning_rate": 2.030236106497352e-07,
"loss": 0.1662,
"step": 594
},
{
"epoch": 2.81,
"learning_rate": 1.9277877819831148e-07,
"loss": 0.1851,
"step": 595
},
{
"epoch": 2.81,
"learning_rate": 1.8279665015826341e-07,
"loss": 0.2034,
"step": 596
},
{
"epoch": 2.82,
"learning_rate": 1.730774939192037e-07,
"loss": 0.1748,
"step": 597
},
{
"epoch": 2.82,
"learning_rate": 1.6362156982656085e-07,
"loss": 0.1716,
"step": 598
},
{
"epoch": 2.83,
"learning_rate": 1.5442913117460823e-07,
"loss": 0.1819,
"step": 599
},
{
"epoch": 2.83,
"learning_rate": 1.4550042419967714e-07,
"loss": 0.1674,
"step": 600
},
{
"epoch": 2.84,
"learning_rate": 1.368356880735655e-07,
"loss": 0.1838,
"step": 601
},
{
"epoch": 2.84,
"learning_rate": 1.284351548971241e-07,
"loss": 0.1835,
"step": 602
},
{
"epoch": 2.85,
"learning_rate": 1.2029904969404482e-07,
"loss": 0.1884,
"step": 603
},
{
"epoch": 2.85,
"learning_rate": 1.1242759040482997e-07,
"loss": 0.2155,
"step": 604
},
{
"epoch": 2.86,
"learning_rate": 1.0482098788095807e-07,
"loss": 0.1775,
"step": 605
},
{
"epoch": 2.86,
"learning_rate": 9.747944587923164e-08,
"loss": 0.1821,
"step": 606
},
{
"epoch": 2.87,
"learning_rate": 9.040316105631941e-08,
"loss": 0.1539,
"step": 607
},
{
"epoch": 2.87,
"learning_rate": 8.359232296349163e-08,
"loss": 0.176,
"step": 608
},
{
"epoch": 2.88,
"learning_rate": 7.704711404154297e-08,
"loss": 0.2012,
"step": 609
},
{
"epoch": 2.88,
"learning_rate": 7.076770961589984e-08,
"loss": 0.1787,
"step": 610
},
{
"epoch": 2.89,
"learning_rate": 6.475427789192967e-08,
"loss": 0.1893,
"step": 611
},
{
"epoch": 2.89,
"learning_rate": 5.900697995043114e-08,
"loss": 0.1783,
"step": 612
},
{
"epoch": 2.89,
"learning_rate": 5.3525969743324356e-08,
"loss": 0.1946,
"step": 613
},
{
"epoch": 2.9,
"learning_rate": 4.83113940895219e-08,
"loss": 0.1457,
"step": 614
},
{
"epoch": 2.9,
"learning_rate": 4.336339267099754e-08,
"loss": 0.1603,
"step": 615
},
{
"epoch": 2.91,
"learning_rate": 3.86820980290481e-08,
"loss": 0.1765,
"step": 616
},
{
"epoch": 2.91,
"learning_rate": 3.4267635560737425e-08,
"loss": 0.192,
"step": 617
},
{
"epoch": 2.92,
"learning_rate": 3.012012351554017e-08,
"loss": 0.1892,
"step": 618
},
{
"epoch": 2.92,
"learning_rate": 2.6239672992176556e-08,
"loss": 0.1954,
"step": 619
},
{
"epoch": 2.93,
"learning_rate": 2.262638793563032e-08,
"loss": 0.1655,
"step": 620
},
{
"epoch": 2.93,
"learning_rate": 1.9280365134370926e-08,
"loss": 0.1963,
"step": 621
},
{
"epoch": 2.94,
"learning_rate": 1.620169421775897e-08,
"loss": 0.138,
"step": 622
},
{
"epoch": 2.94,
"learning_rate": 1.3390457653639221e-08,
"loss": 0.1581,
"step": 623
},
{
"epoch": 2.95,
"learning_rate": 1.0846730746143507e-08,
"loss": 0.1939,
"step": 624
},
{
"epoch": 2.95,
"learning_rate": 8.570581633661202e-09,
"loss": 0.1725,
"step": 625
},
{
"epoch": 2.96,
"learning_rate": 6.562071287022908e-09,
"loss": 0.1997,
"step": 626
},
{
"epoch": 2.96,
"learning_rate": 4.821253507862889e-09,
"loss": 0.1769,
"step": 627
},
{
"epoch": 2.97,
"learning_rate": 3.3481749271768726e-09,
"loss": 0.1805,
"step": 628
},
{
"epoch": 2.97,
"learning_rate": 2.142875004079725e-09,
"loss": 0.1987,
"step": 629
},
{
"epoch": 2.98,
"learning_rate": 1.2053860247385196e-09,
"loss": 0.18,
"step": 630
},
{
"epoch": 2.98,
"learning_rate": 5.357331015176659e-10,
"loss": 0.1754,
"step": 631
},
{
"epoch": 2.98,
"learning_rate": 1.3393417229723427e-10,
"loss": 0.1674,
"step": 632
},
{
"epoch": 2.99,
"learning_rate": 0.0,
"loss": 0.1724,
"step": 633
},
{
"epoch": 2.99,
"step": 633,
"total_flos": 6.476887515037958e+18,
"train_loss": 0.3617525693694186,
"train_runtime": 84740.7725,
"train_samples_per_second": 0.959,
"train_steps_per_second": 0.007
}
],
"max_steps": 633,
"num_train_epochs": 3,
"total_flos": 6.476887515037958e+18,
"trial_name": null,
"trial_params": null
}