KCA_Llama_2_7B_Discarding_Tuning / trainer_state.json
Wanfq's picture
Upload folder using huggingface_hub
d50c59e verified
raw
history blame contribute delete
No virus
130 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.99581589958159,
"eval_steps": 500,
"global_step": 1074,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 6.060606060606061e-07,
"loss": 0.5465,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 1.2121212121212122e-06,
"loss": 0.5545,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 1.8181818181818183e-06,
"loss": 0.5503,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 2.4242424242424244e-06,
"loss": 0.5701,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 3.0303030303030305e-06,
"loss": 0.6441,
"step": 5
},
{
"epoch": 0.02,
"learning_rate": 3.6363636363636366e-06,
"loss": 0.5979,
"step": 6
},
{
"epoch": 0.02,
"learning_rate": 4.242424242424243e-06,
"loss": 0.5842,
"step": 7
},
{
"epoch": 0.02,
"learning_rate": 4.848484848484849e-06,
"loss": 0.5552,
"step": 8
},
{
"epoch": 0.03,
"learning_rate": 5.4545454545454545e-06,
"loss": 0.5747,
"step": 9
},
{
"epoch": 0.03,
"learning_rate": 6.060606060606061e-06,
"loss": 0.5854,
"step": 10
},
{
"epoch": 0.03,
"learning_rate": 6.666666666666667e-06,
"loss": 0.5674,
"step": 11
},
{
"epoch": 0.03,
"learning_rate": 7.272727272727273e-06,
"loss": 0.5996,
"step": 12
},
{
"epoch": 0.04,
"learning_rate": 7.87878787878788e-06,
"loss": 0.5805,
"step": 13
},
{
"epoch": 0.04,
"learning_rate": 8.484848484848486e-06,
"loss": 0.5686,
"step": 14
},
{
"epoch": 0.04,
"learning_rate": 9.090909090909091e-06,
"loss": 0.5656,
"step": 15
},
{
"epoch": 0.04,
"learning_rate": 9.696969696969698e-06,
"loss": 0.5556,
"step": 16
},
{
"epoch": 0.05,
"learning_rate": 1.0303030303030304e-05,
"loss": 0.5218,
"step": 17
},
{
"epoch": 0.05,
"learning_rate": 1.0909090909090909e-05,
"loss": 0.5848,
"step": 18
},
{
"epoch": 0.05,
"learning_rate": 1.1515151515151517e-05,
"loss": 0.5215,
"step": 19
},
{
"epoch": 0.06,
"learning_rate": 1.2121212121212122e-05,
"loss": 0.485,
"step": 20
},
{
"epoch": 0.06,
"learning_rate": 1.2727272727272728e-05,
"loss": 0.5097,
"step": 21
},
{
"epoch": 0.06,
"learning_rate": 1.3333333333333333e-05,
"loss": 0.5447,
"step": 22
},
{
"epoch": 0.06,
"learning_rate": 1.3939393939393942e-05,
"loss": 0.5184,
"step": 23
},
{
"epoch": 0.07,
"learning_rate": 1.4545454545454546e-05,
"loss": 0.5334,
"step": 24
},
{
"epoch": 0.07,
"learning_rate": 1.5151515151515153e-05,
"loss": 0.5209,
"step": 25
},
{
"epoch": 0.07,
"learning_rate": 1.575757575757576e-05,
"loss": 0.5239,
"step": 26
},
{
"epoch": 0.08,
"learning_rate": 1.6363636363636366e-05,
"loss": 0.5074,
"step": 27
},
{
"epoch": 0.08,
"learning_rate": 1.6969696969696972e-05,
"loss": 0.5257,
"step": 28
},
{
"epoch": 0.08,
"learning_rate": 1.7575757575757576e-05,
"loss": 0.5209,
"step": 29
},
{
"epoch": 0.08,
"learning_rate": 1.8181818181818182e-05,
"loss": 0.5532,
"step": 30
},
{
"epoch": 0.09,
"learning_rate": 1.8787878787878792e-05,
"loss": 0.5724,
"step": 31
},
{
"epoch": 0.09,
"learning_rate": 1.9393939393939395e-05,
"loss": 0.5014,
"step": 32
},
{
"epoch": 0.09,
"learning_rate": 2e-05,
"loss": 0.4967,
"step": 33
},
{
"epoch": 0.09,
"learning_rate": 1.9999954462628256e-05,
"loss": 0.4916,
"step": 34
},
{
"epoch": 0.1,
"learning_rate": 1.999981785092774e-05,
"loss": 0.5161,
"step": 35
},
{
"epoch": 0.1,
"learning_rate": 1.9999590166142656e-05,
"loss": 0.516,
"step": 36
},
{
"epoch": 0.1,
"learning_rate": 1.9999271410346623e-05,
"loss": 0.4885,
"step": 37
},
{
"epoch": 0.11,
"learning_rate": 1.999886158644271e-05,
"loss": 0.5398,
"step": 38
},
{
"epoch": 0.11,
"learning_rate": 1.9998360698163375e-05,
"loss": 0.5304,
"step": 39
},
{
"epoch": 0.11,
"learning_rate": 1.9997768750070442e-05,
"loss": 0.5079,
"step": 40
},
{
"epoch": 0.11,
"learning_rate": 1.9997085747555068e-05,
"loss": 0.5302,
"step": 41
},
{
"epoch": 0.12,
"learning_rate": 1.999631169683768e-05,
"loss": 0.4622,
"step": 42
},
{
"epoch": 0.12,
"learning_rate": 1.999544660496792e-05,
"loss": 0.5084,
"step": 43
},
{
"epoch": 0.12,
"learning_rate": 1.9994490479824597e-05,
"loss": 0.5062,
"step": 44
},
{
"epoch": 0.13,
"learning_rate": 1.9993443330115592e-05,
"loss": 0.4854,
"step": 45
},
{
"epoch": 0.13,
"learning_rate": 1.9992305165377798e-05,
"loss": 0.5033,
"step": 46
},
{
"epoch": 0.13,
"learning_rate": 1.9991075995977014e-05,
"loss": 0.5143,
"step": 47
},
{
"epoch": 0.13,
"learning_rate": 1.9989755833107875e-05,
"loss": 0.4841,
"step": 48
},
{
"epoch": 0.14,
"learning_rate": 1.9988344688793732e-05,
"loss": 0.4665,
"step": 49
},
{
"epoch": 0.14,
"learning_rate": 1.998684257588654e-05,
"loss": 0.4389,
"step": 50
},
{
"epoch": 0.14,
"learning_rate": 1.9985249508066754e-05,
"loss": 0.4981,
"step": 51
},
{
"epoch": 0.15,
"learning_rate": 1.9983565499843203e-05,
"loss": 0.5021,
"step": 52
},
{
"epoch": 0.15,
"learning_rate": 1.9981790566552944e-05,
"loss": 0.4751,
"step": 53
},
{
"epoch": 0.15,
"learning_rate": 1.997992472436114e-05,
"loss": 0.5052,
"step": 54
},
{
"epoch": 0.15,
"learning_rate": 1.99779679902609e-05,
"loss": 0.5002,
"step": 55
},
{
"epoch": 0.16,
"learning_rate": 1.9975920382073128e-05,
"loss": 0.4927,
"step": 56
},
{
"epoch": 0.16,
"learning_rate": 1.9973781918446363e-05,
"loss": 0.5247,
"step": 57
},
{
"epoch": 0.16,
"learning_rate": 1.9971552618856612e-05,
"loss": 0.4957,
"step": 58
},
{
"epoch": 0.16,
"learning_rate": 1.9969232503607155e-05,
"loss": 0.474,
"step": 59
},
{
"epoch": 0.17,
"learning_rate": 1.9966821593828393e-05,
"loss": 0.4941,
"step": 60
},
{
"epoch": 0.17,
"learning_rate": 1.9964319911477616e-05,
"loss": 0.5215,
"step": 61
},
{
"epoch": 0.17,
"learning_rate": 1.9961727479338838e-05,
"loss": 0.5186,
"step": 62
},
{
"epoch": 0.18,
"learning_rate": 1.9959044321022563e-05,
"loss": 0.5064,
"step": 63
},
{
"epoch": 0.18,
"learning_rate": 1.9956270460965595e-05,
"loss": 0.49,
"step": 64
},
{
"epoch": 0.18,
"learning_rate": 1.995340592443078e-05,
"loss": 0.4991,
"step": 65
},
{
"epoch": 0.18,
"learning_rate": 1.9950450737506825e-05,
"loss": 0.4525,
"step": 66
},
{
"epoch": 0.19,
"learning_rate": 1.994740492710801e-05,
"loss": 0.5042,
"step": 67
},
{
"epoch": 0.19,
"learning_rate": 1.9944268520973978e-05,
"loss": 0.4391,
"step": 68
},
{
"epoch": 0.19,
"learning_rate": 1.9941041547669467e-05,
"loss": 0.4996,
"step": 69
},
{
"epoch": 0.2,
"learning_rate": 1.993772403658405e-05,
"loss": 0.5569,
"step": 70
},
{
"epoch": 0.2,
"learning_rate": 1.9934316017931884e-05,
"loss": 0.5298,
"step": 71
},
{
"epoch": 0.2,
"learning_rate": 1.9930817522751403e-05,
"loss": 0.4951,
"step": 72
},
{
"epoch": 0.2,
"learning_rate": 1.9927228582905063e-05,
"loss": 0.4791,
"step": 73
},
{
"epoch": 0.21,
"learning_rate": 1.9923549231079045e-05,
"loss": 0.5023,
"step": 74
},
{
"epoch": 0.21,
"learning_rate": 1.991977950078295e-05,
"loss": 0.5009,
"step": 75
},
{
"epoch": 0.21,
"learning_rate": 1.9915919426349496e-05,
"loss": 0.4964,
"step": 76
},
{
"epoch": 0.21,
"learning_rate": 1.9911969042934217e-05,
"loss": 0.5291,
"step": 77
},
{
"epoch": 0.22,
"learning_rate": 1.9907928386515126e-05,
"loss": 0.5109,
"step": 78
},
{
"epoch": 0.22,
"learning_rate": 1.9903797493892402e-05,
"loss": 0.5406,
"step": 79
},
{
"epoch": 0.22,
"learning_rate": 1.9899576402688038e-05,
"loss": 0.5035,
"step": 80
},
{
"epoch": 0.23,
"learning_rate": 1.9895265151345516e-05,
"loss": 0.4884,
"step": 81
},
{
"epoch": 0.23,
"learning_rate": 1.9890863779129448e-05,
"loss": 0.5068,
"step": 82
},
{
"epoch": 0.23,
"learning_rate": 1.9886372326125215e-05,
"loss": 0.4699,
"step": 83
},
{
"epoch": 0.23,
"learning_rate": 1.9881790833238615e-05,
"loss": 0.485,
"step": 84
},
{
"epoch": 0.24,
"learning_rate": 1.9877119342195478e-05,
"loss": 0.5072,
"step": 85
},
{
"epoch": 0.24,
"learning_rate": 1.987235789554128e-05,
"loss": 0.5033,
"step": 86
},
{
"epoch": 0.24,
"learning_rate": 1.9867506536640782e-05,
"loss": 0.4768,
"step": 87
},
{
"epoch": 0.25,
"learning_rate": 1.9862565309677606e-05,
"loss": 0.5258,
"step": 88
},
{
"epoch": 0.25,
"learning_rate": 1.9857534259653858e-05,
"loss": 0.4911,
"step": 89
},
{
"epoch": 0.25,
"learning_rate": 1.9852413432389685e-05,
"loss": 0.5224,
"step": 90
},
{
"epoch": 0.25,
"learning_rate": 1.98472028745229e-05,
"loss": 0.5075,
"step": 91
},
{
"epoch": 0.26,
"learning_rate": 1.9841902633508517e-05,
"loss": 0.4707,
"step": 92
},
{
"epoch": 0.26,
"learning_rate": 1.9836512757618355e-05,
"loss": 0.4739,
"step": 93
},
{
"epoch": 0.26,
"learning_rate": 1.9831033295940566e-05,
"loss": 0.4874,
"step": 94
},
{
"epoch": 0.26,
"learning_rate": 1.98254642983792e-05,
"loss": 0.477,
"step": 95
},
{
"epoch": 0.27,
"learning_rate": 1.9819805815653768e-05,
"loss": 0.4506,
"step": 96
},
{
"epoch": 0.27,
"learning_rate": 1.9814057899298752e-05,
"loss": 0.5214,
"step": 97
},
{
"epoch": 0.27,
"learning_rate": 1.9808220601663155e-05,
"loss": 0.5174,
"step": 98
},
{
"epoch": 0.28,
"learning_rate": 1.9802293975910016e-05,
"loss": 0.4847,
"step": 99
},
{
"epoch": 0.28,
"learning_rate": 1.9796278076015924e-05,
"loss": 0.4937,
"step": 100
},
{
"epoch": 0.28,
"learning_rate": 1.9790172956770534e-05,
"loss": 0.5075,
"step": 101
},
{
"epoch": 0.28,
"learning_rate": 1.9783978673776067e-05,
"loss": 0.4901,
"step": 102
},
{
"epoch": 0.29,
"learning_rate": 1.9777695283446787e-05,
"loss": 0.4941,
"step": 103
},
{
"epoch": 0.29,
"learning_rate": 1.977132284300852e-05,
"loss": 0.5053,
"step": 104
},
{
"epoch": 0.29,
"learning_rate": 1.97648614104981e-05,
"loss": 0.4961,
"step": 105
},
{
"epoch": 0.3,
"learning_rate": 1.975831104476286e-05,
"loss": 0.4496,
"step": 106
},
{
"epoch": 0.3,
"learning_rate": 1.975167180546008e-05,
"loss": 0.4784,
"step": 107
},
{
"epoch": 0.3,
"learning_rate": 1.974494375305647e-05,
"loss": 0.5124,
"step": 108
},
{
"epoch": 0.3,
"learning_rate": 1.9738126948827596e-05,
"loss": 0.4906,
"step": 109
},
{
"epoch": 0.31,
"learning_rate": 1.9731221454857322e-05,
"loss": 0.4814,
"step": 110
},
{
"epoch": 0.31,
"learning_rate": 1.9724227334037255e-05,
"loss": 0.4565,
"step": 111
},
{
"epoch": 0.31,
"learning_rate": 1.9717144650066177e-05,
"loss": 0.4911,
"step": 112
},
{
"epoch": 0.32,
"learning_rate": 1.970997346744945e-05,
"loss": 0.4797,
"step": 113
},
{
"epoch": 0.32,
"learning_rate": 1.9702713851498436e-05,
"loss": 0.4914,
"step": 114
},
{
"epoch": 0.32,
"learning_rate": 1.9695365868329895e-05,
"loss": 0.4908,
"step": 115
},
{
"epoch": 0.32,
"learning_rate": 1.9687929584865402e-05,
"loss": 0.5145,
"step": 116
},
{
"epoch": 0.33,
"learning_rate": 1.9680405068830716e-05,
"loss": 0.4894,
"step": 117
},
{
"epoch": 0.33,
"learning_rate": 1.9672792388755174e-05,
"loss": 0.4955,
"step": 118
},
{
"epoch": 0.33,
"learning_rate": 1.9665091613971064e-05,
"loss": 0.472,
"step": 119
},
{
"epoch": 0.33,
"learning_rate": 1.965730281461299e-05,
"loss": 0.4905,
"step": 120
},
{
"epoch": 0.34,
"learning_rate": 1.9649426061617252e-05,
"loss": 0.4997,
"step": 121
},
{
"epoch": 0.34,
"learning_rate": 1.964146142672117e-05,
"loss": 0.4815,
"step": 122
},
{
"epoch": 0.34,
"learning_rate": 1.9633408982462453e-05,
"loss": 0.4872,
"step": 123
},
{
"epoch": 0.35,
"learning_rate": 1.962526880217853e-05,
"loss": 0.4694,
"step": 124
},
{
"epoch": 0.35,
"learning_rate": 1.9617040960005883e-05,
"loss": 0.4885,
"step": 125
},
{
"epoch": 0.35,
"learning_rate": 1.9608725530879376e-05,
"loss": 0.4634,
"step": 126
},
{
"epoch": 0.35,
"learning_rate": 1.9600322590531563e-05,
"loss": 0.4897,
"step": 127
},
{
"epoch": 0.36,
"learning_rate": 1.9591832215492018e-05,
"loss": 0.4955,
"step": 128
},
{
"epoch": 0.36,
"learning_rate": 1.95832544830866e-05,
"loss": 0.4707,
"step": 129
},
{
"epoch": 0.36,
"learning_rate": 1.9574589471436794e-05,
"loss": 0.447,
"step": 130
},
{
"epoch": 0.37,
"learning_rate": 1.956583725945897e-05,
"loss": 0.5086,
"step": 131
},
{
"epoch": 0.37,
"learning_rate": 1.9556997926863676e-05,
"loss": 0.4711,
"step": 132
},
{
"epoch": 0.37,
"learning_rate": 1.9548071554154905e-05,
"loss": 0.5391,
"step": 133
},
{
"epoch": 0.37,
"learning_rate": 1.9539058222629365e-05,
"loss": 0.4523,
"step": 134
},
{
"epoch": 0.38,
"learning_rate": 1.9529958014375748e-05,
"loss": 0.4558,
"step": 135
},
{
"epoch": 0.38,
"learning_rate": 1.9520771012273963e-05,
"loss": 0.4827,
"step": 136
},
{
"epoch": 0.38,
"learning_rate": 1.9511497299994394e-05,
"loss": 0.4729,
"step": 137
},
{
"epoch": 0.38,
"learning_rate": 1.9502136961997144e-05,
"loss": 0.4694,
"step": 138
},
{
"epoch": 0.39,
"learning_rate": 1.949269008353125e-05,
"loss": 0.4777,
"step": 139
},
{
"epoch": 0.39,
"learning_rate": 1.9483156750633906e-05,
"loss": 0.484,
"step": 140
},
{
"epoch": 0.39,
"learning_rate": 1.9473537050129704e-05,
"loss": 0.4603,
"step": 141
},
{
"epoch": 0.4,
"learning_rate": 1.9463831069629825e-05,
"loss": 0.507,
"step": 142
},
{
"epoch": 0.4,
"learning_rate": 1.9454038897531226e-05,
"loss": 0.4688,
"step": 143
},
{
"epoch": 0.4,
"learning_rate": 1.9444160623015877e-05,
"loss": 0.5241,
"step": 144
},
{
"epoch": 0.4,
"learning_rate": 1.9434196336049897e-05,
"loss": 0.5007,
"step": 145
},
{
"epoch": 0.41,
"learning_rate": 1.9424146127382776e-05,
"loss": 0.4938,
"step": 146
},
{
"epoch": 0.41,
"learning_rate": 1.9414010088546535e-05,
"loss": 0.4527,
"step": 147
},
{
"epoch": 0.41,
"learning_rate": 1.940378831185489e-05,
"loss": 0.477,
"step": 148
},
{
"epoch": 0.42,
"learning_rate": 1.9393480890402405e-05,
"loss": 0.4679,
"step": 149
},
{
"epoch": 0.42,
"learning_rate": 1.9383087918063662e-05,
"loss": 0.4942,
"step": 150
},
{
"epoch": 0.42,
"learning_rate": 1.937260948949238e-05,
"loss": 0.4578,
"step": 151
},
{
"epoch": 0.42,
"learning_rate": 1.9362045700120593e-05,
"loss": 0.4295,
"step": 152
},
{
"epoch": 0.43,
"learning_rate": 1.935139664615773e-05,
"loss": 0.5167,
"step": 153
},
{
"epoch": 0.43,
"learning_rate": 1.934066242458978e-05,
"loss": 0.4805,
"step": 154
},
{
"epoch": 0.43,
"learning_rate": 1.932984313317839e-05,
"loss": 0.4901,
"step": 155
},
{
"epoch": 0.44,
"learning_rate": 1.9318938870459984e-05,
"loss": 0.5103,
"step": 156
},
{
"epoch": 0.44,
"learning_rate": 1.930794973574485e-05,
"loss": 0.4593,
"step": 157
},
{
"epoch": 0.44,
"learning_rate": 1.9296875829116252e-05,
"loss": 0.5045,
"step": 158
},
{
"epoch": 0.44,
"learning_rate": 1.9285717251429507e-05,
"loss": 0.4352,
"step": 159
},
{
"epoch": 0.45,
"learning_rate": 1.9274474104311083e-05,
"loss": 0.4722,
"step": 160
},
{
"epoch": 0.45,
"learning_rate": 1.9263146490157646e-05,
"loss": 0.4623,
"step": 161
},
{
"epoch": 0.45,
"learning_rate": 1.9251734512135155e-05,
"loss": 0.5118,
"step": 162
},
{
"epoch": 0.45,
"learning_rate": 1.9240238274177907e-05,
"loss": 0.4623,
"step": 163
},
{
"epoch": 0.46,
"learning_rate": 1.9228657880987595e-05,
"loss": 0.5132,
"step": 164
},
{
"epoch": 0.46,
"learning_rate": 1.921699343803235e-05,
"loss": 0.4884,
"step": 165
},
{
"epoch": 0.46,
"learning_rate": 1.920524505154579e-05,
"loss": 0.5141,
"step": 166
},
{
"epoch": 0.47,
"learning_rate": 1.9193412828526044e-05,
"loss": 0.4644,
"step": 167
},
{
"epoch": 0.47,
"learning_rate": 1.918149687673478e-05,
"loss": 0.484,
"step": 168
},
{
"epoch": 0.47,
"learning_rate": 1.9169497304696215e-05,
"loss": 0.4627,
"step": 169
},
{
"epoch": 0.47,
"learning_rate": 1.9157414221696155e-05,
"loss": 0.4689,
"step": 170
},
{
"epoch": 0.48,
"learning_rate": 1.9145247737780963e-05,
"loss": 0.4642,
"step": 171
},
{
"epoch": 0.48,
"learning_rate": 1.9132997963756577e-05,
"loss": 0.496,
"step": 172
},
{
"epoch": 0.48,
"learning_rate": 1.912066501118751e-05,
"loss": 0.4665,
"step": 173
},
{
"epoch": 0.49,
"learning_rate": 1.9108248992395797e-05,
"loss": 0.4626,
"step": 174
},
{
"epoch": 0.49,
"learning_rate": 1.9095750020460017e-05,
"loss": 0.4653,
"step": 175
},
{
"epoch": 0.49,
"learning_rate": 1.908316820921424e-05,
"loss": 0.4795,
"step": 176
},
{
"epoch": 0.49,
"learning_rate": 1.9070503673246982e-05,
"loss": 0.4467,
"step": 177
},
{
"epoch": 0.5,
"learning_rate": 1.9057756527900188e-05,
"loss": 0.4774,
"step": 178
},
{
"epoch": 0.5,
"learning_rate": 1.904492688926815e-05,
"loss": 0.4857,
"step": 179
},
{
"epoch": 0.5,
"learning_rate": 1.9032014874196476e-05,
"loss": 0.4684,
"step": 180
},
{
"epoch": 0.5,
"learning_rate": 1.901902060028101e-05,
"loss": 0.4765,
"step": 181
},
{
"epoch": 0.51,
"learning_rate": 1.9005944185866768e-05,
"loss": 0.4361,
"step": 182
},
{
"epoch": 0.51,
"learning_rate": 1.8992785750046866e-05,
"loss": 0.4525,
"step": 183
},
{
"epoch": 0.51,
"learning_rate": 1.8979545412661414e-05,
"loss": 0.4854,
"step": 184
},
{
"epoch": 0.52,
"learning_rate": 1.8966223294296445e-05,
"loss": 0.4385,
"step": 185
},
{
"epoch": 0.52,
"learning_rate": 1.895281951628281e-05,
"loss": 0.4595,
"step": 186
},
{
"epoch": 0.52,
"learning_rate": 1.8939334200695078e-05,
"loss": 0.4867,
"step": 187
},
{
"epoch": 0.52,
"learning_rate": 1.892576747035041e-05,
"loss": 0.4686,
"step": 188
},
{
"epoch": 0.53,
"learning_rate": 1.891211944880746e-05,
"loss": 0.4565,
"step": 189
},
{
"epoch": 0.53,
"learning_rate": 1.8898390260365227e-05,
"loss": 0.511,
"step": 190
},
{
"epoch": 0.53,
"learning_rate": 1.888458003006195e-05,
"loss": 0.4864,
"step": 191
},
{
"epoch": 0.54,
"learning_rate": 1.887068888367394e-05,
"loss": 0.4595,
"step": 192
},
{
"epoch": 0.54,
"learning_rate": 1.885671694771446e-05,
"loss": 0.4515,
"step": 193
},
{
"epoch": 0.54,
"learning_rate": 1.884266434943256e-05,
"loss": 0.5089,
"step": 194
},
{
"epoch": 0.54,
"learning_rate": 1.8828531216811912e-05,
"loss": 0.4608,
"step": 195
},
{
"epoch": 0.55,
"learning_rate": 1.881431767856967e-05,
"loss": 0.5105,
"step": 196
},
{
"epoch": 0.55,
"learning_rate": 1.880002386415526e-05,
"loss": 0.4902,
"step": 197
},
{
"epoch": 0.55,
"learning_rate": 1.8785649903749236e-05,
"loss": 0.4383,
"step": 198
},
{
"epoch": 0.56,
"learning_rate": 1.8771195928262066e-05,
"loss": 0.4648,
"step": 199
},
{
"epoch": 0.56,
"learning_rate": 1.8756662069332966e-05,
"loss": 0.4258,
"step": 200
},
{
"epoch": 0.56,
"learning_rate": 1.8742048459328684e-05,
"loss": 0.4491,
"step": 201
},
{
"epoch": 0.56,
"learning_rate": 1.8727355231342296e-05,
"loss": 0.4756,
"step": 202
},
{
"epoch": 0.57,
"learning_rate": 1.8712582519192e-05,
"loss": 0.4961,
"step": 203
},
{
"epoch": 0.57,
"learning_rate": 1.8697730457419893e-05,
"loss": 0.4678,
"step": 204
},
{
"epoch": 0.57,
"learning_rate": 1.8682799181290747e-05,
"loss": 0.4856,
"step": 205
},
{
"epoch": 0.57,
"learning_rate": 1.8667788826790776e-05,
"loss": 0.4981,
"step": 206
},
{
"epoch": 0.58,
"learning_rate": 1.8652699530626398e-05,
"loss": 0.4475,
"step": 207
},
{
"epoch": 0.58,
"learning_rate": 1.8637531430222993e-05,
"loss": 0.4612,
"step": 208
},
{
"epoch": 0.58,
"learning_rate": 1.8622284663723643e-05,
"loss": 0.4554,
"step": 209
},
{
"epoch": 0.59,
"learning_rate": 1.8606959369987885e-05,
"loss": 0.5002,
"step": 210
},
{
"epoch": 0.59,
"learning_rate": 1.8591555688590437e-05,
"loss": 0.4573,
"step": 211
},
{
"epoch": 0.59,
"learning_rate": 1.8576073759819934e-05,
"loss": 0.486,
"step": 212
},
{
"epoch": 0.59,
"learning_rate": 1.8560513724677644e-05,
"loss": 0.4762,
"step": 213
},
{
"epoch": 0.6,
"learning_rate": 1.854487572487619e-05,
"loss": 0.4681,
"step": 214
},
{
"epoch": 0.6,
"learning_rate": 1.8529159902838253e-05,
"loss": 0.468,
"step": 215
},
{
"epoch": 0.6,
"learning_rate": 1.8513366401695277e-05,
"loss": 0.4829,
"step": 216
},
{
"epoch": 0.61,
"learning_rate": 1.849749536528617e-05,
"loss": 0.4778,
"step": 217
},
{
"epoch": 0.61,
"learning_rate": 1.8481546938155988e-05,
"loss": 0.4937,
"step": 218
},
{
"epoch": 0.61,
"learning_rate": 1.8465521265554623e-05,
"loss": 0.4974,
"step": 219
},
{
"epoch": 0.61,
"learning_rate": 1.844941849343548e-05,
"loss": 0.4472,
"step": 220
},
{
"epoch": 0.62,
"learning_rate": 1.8433238768454137e-05,
"loss": 0.412,
"step": 221
},
{
"epoch": 0.62,
"learning_rate": 1.841698223796703e-05,
"loss": 0.4863,
"step": 222
},
{
"epoch": 0.62,
"learning_rate": 1.840064905003009e-05,
"loss": 0.4797,
"step": 223
},
{
"epoch": 0.62,
"learning_rate": 1.8384239353397405e-05,
"loss": 0.4793,
"step": 224
},
{
"epoch": 0.63,
"learning_rate": 1.8367753297519874e-05,
"loss": 0.5263,
"step": 225
},
{
"epoch": 0.63,
"learning_rate": 1.8351191032543822e-05,
"loss": 0.4439,
"step": 226
},
{
"epoch": 0.63,
"learning_rate": 1.8334552709309653e-05,
"loss": 0.5257,
"step": 227
},
{
"epoch": 0.64,
"learning_rate": 1.8317838479350473e-05,
"loss": 0.4721,
"step": 228
},
{
"epoch": 0.64,
"learning_rate": 1.8301048494890693e-05,
"loss": 0.4704,
"step": 229
},
{
"epoch": 0.64,
"learning_rate": 1.828418290884468e-05,
"loss": 0.472,
"step": 230
},
{
"epoch": 0.64,
"learning_rate": 1.8267241874815312e-05,
"loss": 0.4987,
"step": 231
},
{
"epoch": 0.65,
"learning_rate": 1.825022554709263e-05,
"loss": 0.4906,
"step": 232
},
{
"epoch": 0.65,
"learning_rate": 1.82331340806524e-05,
"loss": 0.4737,
"step": 233
},
{
"epoch": 0.65,
"learning_rate": 1.8215967631154718e-05,
"loss": 0.4508,
"step": 234
},
{
"epoch": 0.66,
"learning_rate": 1.819872635494258e-05,
"loss": 0.4903,
"step": 235
},
{
"epoch": 0.66,
"learning_rate": 1.8181410409040463e-05,
"loss": 0.4996,
"step": 236
},
{
"epoch": 0.66,
"learning_rate": 1.8164019951152903e-05,
"loss": 0.5137,
"step": 237
},
{
"epoch": 0.66,
"learning_rate": 1.814655513966305e-05,
"loss": 0.4719,
"step": 238
},
{
"epoch": 0.67,
"learning_rate": 1.8129016133631227e-05,
"loss": 0.4697,
"step": 239
},
{
"epoch": 0.67,
"learning_rate": 1.811140309279348e-05,
"loss": 0.477,
"step": 240
},
{
"epoch": 0.67,
"learning_rate": 1.8093716177560128e-05,
"loss": 0.4471,
"step": 241
},
{
"epoch": 0.68,
"learning_rate": 1.80759555490143e-05,
"loss": 0.5176,
"step": 242
},
{
"epoch": 0.68,
"learning_rate": 1.805812136891046e-05,
"loss": 0.4452,
"step": 243
},
{
"epoch": 0.68,
"learning_rate": 1.8040213799672943e-05,
"loss": 0.4659,
"step": 244
},
{
"epoch": 0.68,
"learning_rate": 1.8022233004394487e-05,
"loss": 0.43,
"step": 245
},
{
"epoch": 0.69,
"learning_rate": 1.8004179146834712e-05,
"loss": 0.4854,
"step": 246
},
{
"epoch": 0.69,
"learning_rate": 1.7986052391418674e-05,
"loss": 0.4312,
"step": 247
},
{
"epoch": 0.69,
"learning_rate": 1.7967852903235328e-05,
"loss": 0.4808,
"step": 248
},
{
"epoch": 0.69,
"learning_rate": 1.7949580848036045e-05,
"loss": 0.4321,
"step": 249
},
{
"epoch": 0.7,
"learning_rate": 1.79312363922331e-05,
"loss": 0.4604,
"step": 250
},
{
"epoch": 0.7,
"learning_rate": 1.7912819702898153e-05,
"loss": 0.4771,
"step": 251
},
{
"epoch": 0.7,
"learning_rate": 1.7894330947760728e-05,
"loss": 0.4803,
"step": 252
},
{
"epoch": 0.71,
"learning_rate": 1.787577029520669e-05,
"loss": 0.4554,
"step": 253
},
{
"epoch": 0.71,
"learning_rate": 1.785713791427671e-05,
"loss": 0.4794,
"step": 254
},
{
"epoch": 0.71,
"learning_rate": 1.7838433974664714e-05,
"loss": 0.4658,
"step": 255
},
{
"epoch": 0.71,
"learning_rate": 1.7819658646716354e-05,
"loss": 0.4532,
"step": 256
},
{
"epoch": 0.72,
"learning_rate": 1.7800812101427445e-05,
"loss": 0.4639,
"step": 257
},
{
"epoch": 0.72,
"learning_rate": 1.778189451044242e-05,
"loss": 0.4402,
"step": 258
},
{
"epoch": 0.72,
"learning_rate": 1.7762906046052746e-05,
"loss": 0.4705,
"step": 259
},
{
"epoch": 0.73,
"learning_rate": 1.774384688119539e-05,
"loss": 0.4821,
"step": 260
},
{
"epoch": 0.73,
"learning_rate": 1.772471718945119e-05,
"loss": 0.4753,
"step": 261
},
{
"epoch": 0.73,
"learning_rate": 1.770551714504333e-05,
"loss": 0.4735,
"step": 262
},
{
"epoch": 0.73,
"learning_rate": 1.7686246922835728e-05,
"loss": 0.4626,
"step": 263
},
{
"epoch": 0.74,
"learning_rate": 1.7666906698331426e-05,
"loss": 0.4613,
"step": 264
},
{
"epoch": 0.74,
"learning_rate": 1.7647496647671033e-05,
"loss": 0.5124,
"step": 265
},
{
"epoch": 0.74,
"learning_rate": 1.7628016947631085e-05,
"loss": 0.4739,
"step": 266
},
{
"epoch": 0.74,
"learning_rate": 1.7608467775622448e-05,
"loss": 0.4778,
"step": 267
},
{
"epoch": 0.75,
"learning_rate": 1.7588849309688704e-05,
"loss": 0.4573,
"step": 268
},
{
"epoch": 0.75,
"learning_rate": 1.756916172850453e-05,
"loss": 0.4793,
"step": 269
},
{
"epoch": 0.75,
"learning_rate": 1.7549405211374072e-05,
"loss": 0.4755,
"step": 270
},
{
"epoch": 0.76,
"learning_rate": 1.7529579938229293e-05,
"loss": 0.4598,
"step": 271
},
{
"epoch": 0.76,
"learning_rate": 1.7509686089628366e-05,
"loss": 0.4663,
"step": 272
},
{
"epoch": 0.76,
"learning_rate": 1.7489723846754e-05,
"loss": 0.494,
"step": 273
},
{
"epoch": 0.76,
"learning_rate": 1.7469693391411825e-05,
"loss": 0.4835,
"step": 274
},
{
"epoch": 0.77,
"learning_rate": 1.7449594906028684e-05,
"loss": 0.4751,
"step": 275
},
{
"epoch": 0.77,
"learning_rate": 1.7429428573651023e-05,
"loss": 0.462,
"step": 276
},
{
"epoch": 0.77,
"learning_rate": 1.7409194577943197e-05,
"loss": 0.4506,
"step": 277
},
{
"epoch": 0.78,
"learning_rate": 1.73888931031858e-05,
"loss": 0.4922,
"step": 278
},
{
"epoch": 0.78,
"learning_rate": 1.7368524334273998e-05,
"loss": 0.4371,
"step": 279
},
{
"epoch": 0.78,
"learning_rate": 1.734808845671583e-05,
"loss": 0.5044,
"step": 280
},
{
"epoch": 0.78,
"learning_rate": 1.7327585656630517e-05,
"loss": 0.4372,
"step": 281
},
{
"epoch": 0.79,
"learning_rate": 1.73070161207468e-05,
"loss": 0.4457,
"step": 282
},
{
"epoch": 0.79,
"learning_rate": 1.728638003640119e-05,
"loss": 0.431,
"step": 283
},
{
"epoch": 0.79,
"learning_rate": 1.7265677591536297e-05,
"loss": 0.527,
"step": 284
},
{
"epoch": 0.79,
"learning_rate": 1.7244908974699112e-05,
"loss": 0.4853,
"step": 285
},
{
"epoch": 0.8,
"learning_rate": 1.722407437503927e-05,
"loss": 0.4732,
"step": 286
},
{
"epoch": 0.8,
"learning_rate": 1.7203173982307363e-05,
"loss": 0.4938,
"step": 287
},
{
"epoch": 0.8,
"learning_rate": 1.7182207986853176e-05,
"loss": 0.4671,
"step": 288
},
{
"epoch": 0.81,
"learning_rate": 1.7161176579623974e-05,
"loss": 0.4788,
"step": 289
},
{
"epoch": 0.81,
"learning_rate": 1.7140079952162765e-05,
"loss": 0.4202,
"step": 290
},
{
"epoch": 0.81,
"learning_rate": 1.7118918296606536e-05,
"loss": 0.4537,
"step": 291
},
{
"epoch": 0.81,
"learning_rate": 1.709769180568453e-05,
"loss": 0.4665,
"step": 292
},
{
"epoch": 0.82,
"learning_rate": 1.7076400672716455e-05,
"loss": 0.4626,
"step": 293
},
{
"epoch": 0.82,
"learning_rate": 1.7055045091610772e-05,
"loss": 0.4254,
"step": 294
},
{
"epoch": 0.82,
"learning_rate": 1.703362525686288e-05,
"loss": 0.4443,
"step": 295
},
{
"epoch": 0.83,
"learning_rate": 1.701214136355338e-05,
"loss": 0.4415,
"step": 296
},
{
"epoch": 0.83,
"learning_rate": 1.6990593607346276e-05,
"loss": 0.4142,
"step": 297
},
{
"epoch": 0.83,
"learning_rate": 1.6968982184487205e-05,
"loss": 0.4773,
"step": 298
},
{
"epoch": 0.83,
"learning_rate": 1.694730729180165e-05,
"loss": 0.4433,
"step": 299
},
{
"epoch": 0.84,
"learning_rate": 1.6925569126693135e-05,
"loss": 0.4746,
"step": 300
},
{
"epoch": 0.84,
"learning_rate": 1.6903767887141443e-05,
"loss": 0.4807,
"step": 301
},
{
"epoch": 0.84,
"learning_rate": 1.6881903771700805e-05,
"loss": 0.4903,
"step": 302
},
{
"epoch": 0.85,
"learning_rate": 1.685997697949809e-05,
"loss": 0.5303,
"step": 303
},
{
"epoch": 0.85,
"learning_rate": 1.6837987710230995e-05,
"loss": 0.4782,
"step": 304
},
{
"epoch": 0.85,
"learning_rate": 1.681593616416623e-05,
"loss": 0.4897,
"step": 305
},
{
"epoch": 0.85,
"learning_rate": 1.6793822542137683e-05,
"loss": 0.4628,
"step": 306
},
{
"epoch": 0.86,
"learning_rate": 1.6771647045544598e-05,
"loss": 0.5038,
"step": 307
},
{
"epoch": 0.86,
"learning_rate": 1.674940987634974e-05,
"loss": 0.4689,
"step": 308
},
{
"epoch": 0.86,
"learning_rate": 1.672711123707756e-05,
"loss": 0.4442,
"step": 309
},
{
"epoch": 0.86,
"learning_rate": 1.6704751330812342e-05,
"loss": 0.4837,
"step": 310
},
{
"epoch": 0.87,
"learning_rate": 1.6682330361196363e-05,
"loss": 0.4927,
"step": 311
},
{
"epoch": 0.87,
"learning_rate": 1.665984853242802e-05,
"loss": 0.498,
"step": 312
},
{
"epoch": 0.87,
"learning_rate": 1.6637306049259998e-05,
"loss": 0.4661,
"step": 313
},
{
"epoch": 0.88,
"learning_rate": 1.6614703116997385e-05,
"loss": 0.4801,
"step": 314
},
{
"epoch": 0.88,
"learning_rate": 1.6592039941495803e-05,
"loss": 0.4767,
"step": 315
},
{
"epoch": 0.88,
"learning_rate": 1.6569316729159542e-05,
"loss": 0.4798,
"step": 316
},
{
"epoch": 0.88,
"learning_rate": 1.654653368693968e-05,
"loss": 0.4318,
"step": 317
},
{
"epoch": 0.89,
"learning_rate": 1.6523691022332184e-05,
"loss": 0.5076,
"step": 318
},
{
"epoch": 0.89,
"learning_rate": 1.6500788943376037e-05,
"loss": 0.4247,
"step": 319
},
{
"epoch": 0.89,
"learning_rate": 1.647782765865134e-05,
"loss": 0.4875,
"step": 320
},
{
"epoch": 0.9,
"learning_rate": 1.64548073772774e-05,
"loss": 0.4706,
"step": 321
},
{
"epoch": 0.9,
"learning_rate": 1.6431728308910843e-05,
"loss": 0.4631,
"step": 322
},
{
"epoch": 0.9,
"learning_rate": 1.6408590663743688e-05,
"loss": 0.4414,
"step": 323
},
{
"epoch": 0.9,
"learning_rate": 1.6385394652501444e-05,
"loss": 0.5113,
"step": 324
},
{
"epoch": 0.91,
"learning_rate": 1.63621404864412e-05,
"loss": 0.4762,
"step": 325
},
{
"epoch": 0.91,
"learning_rate": 1.6338828377349658e-05,
"loss": 0.4641,
"step": 326
},
{
"epoch": 0.91,
"learning_rate": 1.6315458537541272e-05,
"loss": 0.4715,
"step": 327
},
{
"epoch": 0.91,
"learning_rate": 1.6292031179856246e-05,
"loss": 0.4734,
"step": 328
},
{
"epoch": 0.92,
"learning_rate": 1.6268546517658644e-05,
"loss": 0.4453,
"step": 329
},
{
"epoch": 0.92,
"learning_rate": 1.6245004764834423e-05,
"loss": 0.5261,
"step": 330
},
{
"epoch": 0.92,
"learning_rate": 1.6221406135789495e-05,
"loss": 0.4625,
"step": 331
},
{
"epoch": 0.93,
"learning_rate": 1.619775084544777e-05,
"loss": 0.4598,
"step": 332
},
{
"epoch": 0.93,
"learning_rate": 1.617403910924919e-05,
"loss": 0.4568,
"step": 333
},
{
"epoch": 0.93,
"learning_rate": 1.6150271143147796e-05,
"loss": 0.4885,
"step": 334
},
{
"epoch": 0.93,
"learning_rate": 1.612644716360972e-05,
"loss": 0.469,
"step": 335
},
{
"epoch": 0.94,
"learning_rate": 1.610256738761125e-05,
"loss": 0.4799,
"step": 336
},
{
"epoch": 0.94,
"learning_rate": 1.607863203263683e-05,
"loss": 0.4622,
"step": 337
},
{
"epoch": 0.94,
"learning_rate": 1.6054641316677094e-05,
"loss": 0.4425,
"step": 338
},
{
"epoch": 0.95,
"learning_rate": 1.6030595458226872e-05,
"loss": 0.4622,
"step": 339
},
{
"epoch": 0.95,
"learning_rate": 1.60064946762832e-05,
"loss": 0.4776,
"step": 340
},
{
"epoch": 0.95,
"learning_rate": 1.5982339190343338e-05,
"loss": 0.4924,
"step": 341
},
{
"epoch": 0.95,
"learning_rate": 1.5958129220402745e-05,
"loss": 0.4797,
"step": 342
},
{
"epoch": 0.96,
"learning_rate": 1.593386498695311e-05,
"loss": 0.4633,
"step": 343
},
{
"epoch": 0.96,
"learning_rate": 1.590954671098031e-05,
"loss": 0.5084,
"step": 344
},
{
"epoch": 0.96,
"learning_rate": 1.5885174613962427e-05,
"loss": 0.4724,
"step": 345
},
{
"epoch": 0.97,
"learning_rate": 1.5860748917867704e-05,
"loss": 0.4574,
"step": 346
},
{
"epoch": 0.97,
"learning_rate": 1.5836269845152542e-05,
"loss": 0.4258,
"step": 347
},
{
"epoch": 0.97,
"learning_rate": 1.581173761875947e-05,
"loss": 0.4786,
"step": 348
},
{
"epoch": 0.97,
"learning_rate": 1.5787152462115107e-05,
"loss": 0.4638,
"step": 349
},
{
"epoch": 0.98,
"learning_rate": 1.576251459912814e-05,
"loss": 0.4949,
"step": 350
},
{
"epoch": 0.98,
"learning_rate": 1.5737824254187275e-05,
"loss": 0.4898,
"step": 351
},
{
"epoch": 0.98,
"learning_rate": 1.571308165215919e-05,
"loss": 0.4841,
"step": 352
},
{
"epoch": 0.98,
"learning_rate": 1.5688287018386505e-05,
"loss": 0.4708,
"step": 353
},
{
"epoch": 0.99,
"learning_rate": 1.5663440578685706e-05,
"loss": 0.4528,
"step": 354
},
{
"epoch": 0.99,
"learning_rate": 1.5638542559345106e-05,
"loss": 0.4586,
"step": 355
},
{
"epoch": 0.99,
"learning_rate": 1.5613593187122778e-05,
"loss": 0.4366,
"step": 356
},
{
"epoch": 1.0,
"learning_rate": 1.5588592689244492e-05,
"loss": 0.4864,
"step": 357
},
{
"epoch": 1.0,
"learning_rate": 1.556354129340164e-05,
"loss": 0.4574,
"step": 358
},
{
"epoch": 1.0,
"learning_rate": 1.5538439227749162e-05,
"loss": 0.4233,
"step": 359
},
{
"epoch": 1.0,
"learning_rate": 1.5513286720903488e-05,
"loss": 0.4058,
"step": 360
},
{
"epoch": 1.01,
"learning_rate": 1.5488084001940415e-05,
"loss": 0.4138,
"step": 361
},
{
"epoch": 1.01,
"learning_rate": 1.546283130039307e-05,
"loss": 0.4348,
"step": 362
},
{
"epoch": 1.01,
"learning_rate": 1.5437528846249783e-05,
"loss": 0.4365,
"step": 363
},
{
"epoch": 1.02,
"learning_rate": 1.5412176869952e-05,
"loss": 0.4868,
"step": 364
},
{
"epoch": 1.02,
"learning_rate": 1.53867756023922e-05,
"loss": 0.434,
"step": 365
},
{
"epoch": 1.02,
"learning_rate": 1.536132527491178e-05,
"loss": 0.433,
"step": 366
},
{
"epoch": 1.02,
"learning_rate": 1.5335826119298937e-05,
"loss": 0.4125,
"step": 367
},
{
"epoch": 1.03,
"learning_rate": 1.531027836778658e-05,
"loss": 0.4336,
"step": 368
},
{
"epoch": 1.03,
"learning_rate": 1.52846822530502e-05,
"loss": 0.466,
"step": 369
},
{
"epoch": 1.03,
"learning_rate": 1.525903800820575e-05,
"loss": 0.4066,
"step": 370
},
{
"epoch": 1.03,
"learning_rate": 1.5233345866807545e-05,
"loss": 0.4483,
"step": 371
},
{
"epoch": 1.04,
"learning_rate": 1.5207606062846092e-05,
"loss": 0.4636,
"step": 372
},
{
"epoch": 1.04,
"learning_rate": 1.5181818830746e-05,
"loss": 0.4371,
"step": 373
},
{
"epoch": 1.04,
"learning_rate": 1.5155984405363824e-05,
"loss": 0.4139,
"step": 374
},
{
"epoch": 1.05,
"learning_rate": 1.5130103021985929e-05,
"loss": 0.4107,
"step": 375
},
{
"epoch": 1.05,
"learning_rate": 1.5104174916326354e-05,
"loss": 0.4184,
"step": 376
},
{
"epoch": 1.05,
"learning_rate": 1.507820032452465e-05,
"loss": 0.4406,
"step": 377
},
{
"epoch": 1.05,
"learning_rate": 1.5052179483143752e-05,
"loss": 0.3686,
"step": 378
},
{
"epoch": 1.06,
"learning_rate": 1.5026112629167799e-05,
"loss": 0.3998,
"step": 379
},
{
"epoch": 1.06,
"learning_rate": 1.5000000000000002e-05,
"loss": 0.3791,
"step": 380
},
{
"epoch": 1.06,
"learning_rate": 1.4973841833460457e-05,
"loss": 0.4158,
"step": 381
},
{
"epoch": 1.07,
"learning_rate": 1.4947638367783994e-05,
"loss": 0.4128,
"step": 382
},
{
"epoch": 1.07,
"learning_rate": 1.4921389841618009e-05,
"loss": 0.3925,
"step": 383
},
{
"epoch": 1.07,
"learning_rate": 1.4895096494020274e-05,
"loss": 0.3765,
"step": 384
},
{
"epoch": 1.07,
"learning_rate": 1.4868758564456785e-05,
"loss": 0.392,
"step": 385
},
{
"epoch": 1.08,
"learning_rate": 1.4842376292799552e-05,
"loss": 0.3951,
"step": 386
},
{
"epoch": 1.08,
"learning_rate": 1.4815949919324443e-05,
"loss": 0.4008,
"step": 387
},
{
"epoch": 1.08,
"learning_rate": 1.4789479684708978e-05,
"loss": 0.4194,
"step": 388
},
{
"epoch": 1.09,
"learning_rate": 1.4762965830030136e-05,
"loss": 0.4254,
"step": 389
},
{
"epoch": 1.09,
"learning_rate": 1.473640859676217e-05,
"loss": 0.4002,
"step": 390
},
{
"epoch": 1.09,
"learning_rate": 1.4709808226774401e-05,
"loss": 0.3785,
"step": 391
},
{
"epoch": 1.09,
"learning_rate": 1.4683164962329016e-05,
"loss": 0.4078,
"step": 392
},
{
"epoch": 1.1,
"learning_rate": 1.4656479046078862e-05,
"loss": 0.3657,
"step": 393
},
{
"epoch": 1.1,
"learning_rate": 1.4629750721065236e-05,
"loss": 0.3701,
"step": 394
},
{
"epoch": 1.1,
"learning_rate": 1.4602980230715674e-05,
"loss": 0.3853,
"step": 395
},
{
"epoch": 1.1,
"learning_rate": 1.4576167818841732e-05,
"loss": 0.3963,
"step": 396
},
{
"epoch": 1.11,
"learning_rate": 1.4549313729636758e-05,
"loss": 0.4077,
"step": 397
},
{
"epoch": 1.11,
"learning_rate": 1.4522418207673686e-05,
"loss": 0.3933,
"step": 398
},
{
"epoch": 1.11,
"learning_rate": 1.4495481497902789e-05,
"loss": 0.3737,
"step": 399
},
{
"epoch": 1.12,
"learning_rate": 1.4468503845649462e-05,
"loss": 0.4158,
"step": 400
},
{
"epoch": 1.12,
"learning_rate": 1.4441485496611978e-05,
"loss": 0.355,
"step": 401
},
{
"epoch": 1.12,
"learning_rate": 1.441442669685926e-05,
"loss": 0.4028,
"step": 402
},
{
"epoch": 1.12,
"learning_rate": 1.4387327692828637e-05,
"loss": 0.3869,
"step": 403
},
{
"epoch": 1.13,
"learning_rate": 1.4360188731323585e-05,
"loss": 0.3864,
"step": 404
},
{
"epoch": 1.13,
"learning_rate": 1.4333010059511505e-05,
"loss": 0.3873,
"step": 405
},
{
"epoch": 1.13,
"learning_rate": 1.4305791924921454e-05,
"loss": 0.3911,
"step": 406
},
{
"epoch": 1.14,
"learning_rate": 1.427853457544189e-05,
"loss": 0.349,
"step": 407
},
{
"epoch": 1.14,
"learning_rate": 1.425123825931843e-05,
"loss": 0.3594,
"step": 408
},
{
"epoch": 1.14,
"learning_rate": 1.4223903225151567e-05,
"loss": 0.3845,
"step": 409
},
{
"epoch": 1.14,
"learning_rate": 1.4196529721894427e-05,
"loss": 0.3797,
"step": 410
},
{
"epoch": 1.15,
"learning_rate": 1.416911799885049e-05,
"loss": 0.3879,
"step": 411
},
{
"epoch": 1.15,
"learning_rate": 1.4141668305671317e-05,
"loss": 0.3776,
"step": 412
},
{
"epoch": 1.15,
"learning_rate": 1.4114180892354285e-05,
"loss": 0.3897,
"step": 413
},
{
"epoch": 1.15,
"learning_rate": 1.4086656009240308e-05,
"loss": 0.3841,
"step": 414
},
{
"epoch": 1.16,
"learning_rate": 1.4059093907011552e-05,
"loss": 0.4296,
"step": 415
},
{
"epoch": 1.16,
"learning_rate": 1.4031494836689157e-05,
"loss": 0.401,
"step": 416
},
{
"epoch": 1.16,
"learning_rate": 1.4003859049630943e-05,
"loss": 0.3781,
"step": 417
},
{
"epoch": 1.17,
"learning_rate": 1.397618679752914e-05,
"loss": 0.3921,
"step": 418
},
{
"epoch": 1.17,
"learning_rate": 1.3948478332408068e-05,
"loss": 0.375,
"step": 419
},
{
"epoch": 1.17,
"learning_rate": 1.3920733906621861e-05,
"loss": 0.4078,
"step": 420
},
{
"epoch": 1.17,
"learning_rate": 1.3892953772852174e-05,
"loss": 0.3888,
"step": 421
},
{
"epoch": 1.18,
"learning_rate": 1.3865138184105855e-05,
"loss": 0.405,
"step": 422
},
{
"epoch": 1.18,
"learning_rate": 1.3837287393712666e-05,
"loss": 0.3924,
"step": 423
},
{
"epoch": 1.18,
"learning_rate": 1.3809401655322969e-05,
"loss": 0.3616,
"step": 424
},
{
"epoch": 1.19,
"learning_rate": 1.378148122290541e-05,
"loss": 0.3871,
"step": 425
},
{
"epoch": 1.19,
"learning_rate": 1.3753526350744611e-05,
"loss": 0.3837,
"step": 426
},
{
"epoch": 1.19,
"learning_rate": 1.372553729343885e-05,
"loss": 0.358,
"step": 427
},
{
"epoch": 1.19,
"learning_rate": 1.3697514305897752e-05,
"loss": 0.402,
"step": 428
},
{
"epoch": 1.2,
"learning_rate": 1.3669457643339956e-05,
"loss": 0.4184,
"step": 429
},
{
"epoch": 1.2,
"learning_rate": 1.3641367561290795e-05,
"loss": 0.4296,
"step": 430
},
{
"epoch": 1.2,
"learning_rate": 1.3613244315579977e-05,
"loss": 0.3633,
"step": 431
},
{
"epoch": 1.21,
"learning_rate": 1.3585088162339233e-05,
"loss": 0.3878,
"step": 432
},
{
"epoch": 1.21,
"learning_rate": 1.3556899358000011e-05,
"loss": 0.3884,
"step": 433
},
{
"epoch": 1.21,
"learning_rate": 1.3528678159291122e-05,
"loss": 0.3944,
"step": 434
},
{
"epoch": 1.21,
"learning_rate": 1.3500424823236413e-05,
"loss": 0.3993,
"step": 435
},
{
"epoch": 1.22,
"learning_rate": 1.347213960715241e-05,
"loss": 0.4027,
"step": 436
},
{
"epoch": 1.22,
"learning_rate": 1.3443822768646e-05,
"loss": 0.4015,
"step": 437
},
{
"epoch": 1.22,
"learning_rate": 1.3415474565612059e-05,
"loss": 0.4243,
"step": 438
},
{
"epoch": 1.22,
"learning_rate": 1.3387095256231121e-05,
"loss": 0.3944,
"step": 439
},
{
"epoch": 1.23,
"learning_rate": 1.335868509896702e-05,
"loss": 0.4081,
"step": 440
},
{
"epoch": 1.23,
"learning_rate": 1.3330244352564527e-05,
"loss": 0.3746,
"step": 441
},
{
"epoch": 1.23,
"learning_rate": 1.3301773276047016e-05,
"loss": 0.3785,
"step": 442
},
{
"epoch": 1.24,
"learning_rate": 1.327327212871409e-05,
"loss": 0.3838,
"step": 443
},
{
"epoch": 1.24,
"learning_rate": 1.324474117013921e-05,
"loss": 0.4128,
"step": 444
},
{
"epoch": 1.24,
"learning_rate": 1.3216180660167355e-05,
"loss": 0.3906,
"step": 445
},
{
"epoch": 1.24,
"learning_rate": 1.3187590858912633e-05,
"loss": 0.3547,
"step": 446
},
{
"epoch": 1.25,
"learning_rate": 1.3158972026755927e-05,
"loss": 0.4231,
"step": 447
},
{
"epoch": 1.25,
"learning_rate": 1.3130324424342515e-05,
"loss": 0.4283,
"step": 448
},
{
"epoch": 1.25,
"learning_rate": 1.3101648312579704e-05,
"loss": 0.3949,
"step": 449
},
{
"epoch": 1.26,
"learning_rate": 1.3072943952634446e-05,
"loss": 0.4023,
"step": 450
},
{
"epoch": 1.26,
"learning_rate": 1.3044211605930963e-05,
"loss": 0.3593,
"step": 451
},
{
"epoch": 1.26,
"learning_rate": 1.3015451534148362e-05,
"loss": 0.3685,
"step": 452
},
{
"epoch": 1.26,
"learning_rate": 1.2986663999218264e-05,
"loss": 0.4103,
"step": 453
},
{
"epoch": 1.27,
"learning_rate": 1.29578492633224e-05,
"loss": 0.38,
"step": 454
},
{
"epoch": 1.27,
"learning_rate": 1.2929007588890241e-05,
"loss": 0.3711,
"step": 455
},
{
"epoch": 1.27,
"learning_rate": 1.2900139238596598e-05,
"loss": 0.4282,
"step": 456
},
{
"epoch": 1.27,
"learning_rate": 1.287124447535923e-05,
"loss": 0.3761,
"step": 457
},
{
"epoch": 1.28,
"learning_rate": 1.2842323562336451e-05,
"loss": 0.4081,
"step": 458
},
{
"epoch": 1.28,
"learning_rate": 1.2813376762924735e-05,
"loss": 0.4071,
"step": 459
},
{
"epoch": 1.28,
"learning_rate": 1.2784404340756315e-05,
"loss": 0.3881,
"step": 460
},
{
"epoch": 1.29,
"learning_rate": 1.2755406559696786e-05,
"loss": 0.3941,
"step": 461
},
{
"epoch": 1.29,
"learning_rate": 1.272638368384269e-05,
"loss": 0.4154,
"step": 462
},
{
"epoch": 1.29,
"learning_rate": 1.2697335977519127e-05,
"loss": 0.4075,
"step": 463
},
{
"epoch": 1.29,
"learning_rate": 1.2668263705277337e-05,
"loss": 0.3751,
"step": 464
},
{
"epoch": 1.3,
"learning_rate": 1.2639167131892294e-05,
"loss": 0.3966,
"step": 465
},
{
"epoch": 1.3,
"learning_rate": 1.2610046522360293e-05,
"loss": 0.3969,
"step": 466
},
{
"epoch": 1.3,
"learning_rate": 1.2580902141896539e-05,
"loss": 0.3792,
"step": 467
},
{
"epoch": 1.31,
"learning_rate": 1.2551734255932728e-05,
"loss": 0.4019,
"step": 468
},
{
"epoch": 1.31,
"learning_rate": 1.2522543130114635e-05,
"loss": 0.3791,
"step": 469
},
{
"epoch": 1.31,
"learning_rate": 1.249332903029969e-05,
"loss": 0.4042,
"step": 470
},
{
"epoch": 1.31,
"learning_rate": 1.2464092222554554e-05,
"loss": 0.3737,
"step": 471
},
{
"epoch": 1.32,
"learning_rate": 1.2434832973152708e-05,
"loss": 0.3973,
"step": 472
},
{
"epoch": 1.32,
"learning_rate": 1.2405551548572014e-05,
"loss": 0.4328,
"step": 473
},
{
"epoch": 1.32,
"learning_rate": 1.2376248215492297e-05,
"loss": 0.3946,
"step": 474
},
{
"epoch": 1.32,
"learning_rate": 1.2346923240792907e-05,
"loss": 0.3956,
"step": 475
},
{
"epoch": 1.33,
"learning_rate": 1.2317576891550302e-05,
"loss": 0.4087,
"step": 476
},
{
"epoch": 1.33,
"learning_rate": 1.2288209435035605e-05,
"loss": 0.4098,
"step": 477
},
{
"epoch": 1.33,
"learning_rate": 1.2258821138712171e-05,
"loss": 0.3837,
"step": 478
},
{
"epoch": 1.34,
"learning_rate": 1.222941227023316e-05,
"loss": 0.4274,
"step": 479
},
{
"epoch": 1.34,
"learning_rate": 1.2199983097439079e-05,
"loss": 0.4155,
"step": 480
},
{
"epoch": 1.34,
"learning_rate": 1.2170533888355372e-05,
"loss": 0.3702,
"step": 481
},
{
"epoch": 1.34,
"learning_rate": 1.2141064911189948e-05,
"loss": 0.3907,
"step": 482
},
{
"epoch": 1.35,
"learning_rate": 1.2111576434330767e-05,
"loss": 0.3966,
"step": 483
},
{
"epoch": 1.35,
"learning_rate": 1.2082068726343373e-05,
"loss": 0.3769,
"step": 484
},
{
"epoch": 1.35,
"learning_rate": 1.2052542055968461e-05,
"loss": 0.3858,
"step": 485
},
{
"epoch": 1.36,
"learning_rate": 1.2022996692119424e-05,
"loss": 0.3813,
"step": 486
},
{
"epoch": 1.36,
"learning_rate": 1.19934329038799e-05,
"loss": 0.4176,
"step": 487
},
{
"epoch": 1.36,
"learning_rate": 1.196385096050134e-05,
"loss": 0.3782,
"step": 488
},
{
"epoch": 1.36,
"learning_rate": 1.1934251131400532e-05,
"loss": 0.4237,
"step": 489
},
{
"epoch": 1.37,
"learning_rate": 1.1904633686157158e-05,
"loss": 0.3821,
"step": 490
},
{
"epoch": 1.37,
"learning_rate": 1.1874998894511343e-05,
"loss": 0.3978,
"step": 491
},
{
"epoch": 1.37,
"learning_rate": 1.1845347026361192e-05,
"loss": 0.4146,
"step": 492
},
{
"epoch": 1.38,
"learning_rate": 1.1815678351760329e-05,
"loss": 0.3766,
"step": 493
},
{
"epoch": 1.38,
"learning_rate": 1.1785993140915455e-05,
"loss": 0.3572,
"step": 494
},
{
"epoch": 1.38,
"learning_rate": 1.1756291664183858e-05,
"loss": 0.4228,
"step": 495
},
{
"epoch": 1.38,
"learning_rate": 1.1726574192070981e-05,
"loss": 0.3952,
"step": 496
},
{
"epoch": 1.39,
"learning_rate": 1.1696840995227938e-05,
"loss": 0.3755,
"step": 497
},
{
"epoch": 1.39,
"learning_rate": 1.1667092344449053e-05,
"loss": 0.3905,
"step": 498
},
{
"epoch": 1.39,
"learning_rate": 1.1637328510669404e-05,
"loss": 0.3768,
"step": 499
},
{
"epoch": 1.39,
"learning_rate": 1.1607549764962342e-05,
"loss": 0.4145,
"step": 500
},
{
"epoch": 1.4,
"learning_rate": 1.1577756378537033e-05,
"loss": 0.3777,
"step": 501
},
{
"epoch": 1.4,
"learning_rate": 1.1547948622735975e-05,
"loss": 0.4198,
"step": 502
},
{
"epoch": 1.4,
"learning_rate": 1.1518126769032541e-05,
"loss": 0.4125,
"step": 503
},
{
"epoch": 1.41,
"learning_rate": 1.1488291089028501e-05,
"loss": 0.3952,
"step": 504
},
{
"epoch": 1.41,
"learning_rate": 1.1458441854451539e-05,
"loss": 0.4156,
"step": 505
},
{
"epoch": 1.41,
"learning_rate": 1.1428579337152801e-05,
"loss": 0.362,
"step": 506
},
{
"epoch": 1.41,
"learning_rate": 1.1398703809104392e-05,
"loss": 0.3921,
"step": 507
},
{
"epoch": 1.42,
"learning_rate": 1.136881554239692e-05,
"loss": 0.4043,
"step": 508
},
{
"epoch": 1.42,
"learning_rate": 1.1338914809237005e-05,
"loss": 0.389,
"step": 509
},
{
"epoch": 1.42,
"learning_rate": 1.130900188194481e-05,
"loss": 0.3784,
"step": 510
},
{
"epoch": 1.43,
"learning_rate": 1.127907703295155e-05,
"loss": 0.3904,
"step": 511
},
{
"epoch": 1.43,
"learning_rate": 1.1249140534797023e-05,
"loss": 0.4139,
"step": 512
},
{
"epoch": 1.43,
"learning_rate": 1.1219192660127117e-05,
"loss": 0.3866,
"step": 513
},
{
"epoch": 1.43,
"learning_rate": 1.1189233681691331e-05,
"loss": 0.4183,
"step": 514
},
{
"epoch": 1.44,
"learning_rate": 1.1159263872340293e-05,
"loss": 0.4075,
"step": 515
},
{
"epoch": 1.44,
"learning_rate": 1.1129283505023273e-05,
"loss": 0.3971,
"step": 516
},
{
"epoch": 1.44,
"learning_rate": 1.10992928527857e-05,
"loss": 0.3754,
"step": 517
},
{
"epoch": 1.44,
"learning_rate": 1.1069292188766667e-05,
"loss": 0.3903,
"step": 518
},
{
"epoch": 1.45,
"learning_rate": 1.1039281786196453e-05,
"loss": 0.3763,
"step": 519
},
{
"epoch": 1.45,
"learning_rate": 1.1009261918394028e-05,
"loss": 0.3955,
"step": 520
},
{
"epoch": 1.45,
"learning_rate": 1.097923285876457e-05,
"loss": 0.4177,
"step": 521
},
{
"epoch": 1.46,
"learning_rate": 1.0949194880796967e-05,
"loss": 0.3989,
"step": 522
},
{
"epoch": 1.46,
"learning_rate": 1.0919148258061338e-05,
"loss": 0.4154,
"step": 523
},
{
"epoch": 1.46,
"learning_rate": 1.0889093264206523e-05,
"loss": 0.4138,
"step": 524
},
{
"epoch": 1.46,
"learning_rate": 1.085903017295761e-05,
"loss": 0.4013,
"step": 525
},
{
"epoch": 1.47,
"learning_rate": 1.0828959258113433e-05,
"loss": 0.3893,
"step": 526
},
{
"epoch": 1.47,
"learning_rate": 1.0798880793544073e-05,
"loss": 0.3913,
"step": 527
},
{
"epoch": 1.47,
"learning_rate": 1.0768795053188379e-05,
"loss": 0.3775,
"step": 528
},
{
"epoch": 1.48,
"learning_rate": 1.0738702311051459e-05,
"loss": 0.3947,
"step": 529
},
{
"epoch": 1.48,
"learning_rate": 1.070860284120219e-05,
"loss": 0.4036,
"step": 530
},
{
"epoch": 1.48,
"learning_rate": 1.067849691777072e-05,
"loss": 0.3875,
"step": 531
},
{
"epoch": 1.48,
"learning_rate": 1.0648384814945973e-05,
"loss": 0.3969,
"step": 532
},
{
"epoch": 1.49,
"learning_rate": 1.061826680697316e-05,
"loss": 0.3845,
"step": 533
},
{
"epoch": 1.49,
"learning_rate": 1.0588143168151257e-05,
"loss": 0.4001,
"step": 534
},
{
"epoch": 1.49,
"learning_rate": 1.0558014172830537e-05,
"loss": 0.3999,
"step": 535
},
{
"epoch": 1.5,
"learning_rate": 1.0527880095410052e-05,
"loss": 0.3826,
"step": 536
},
{
"epoch": 1.5,
"learning_rate": 1.049774121033514e-05,
"loss": 0.3978,
"step": 537
},
{
"epoch": 1.5,
"learning_rate": 1.0467597792094922e-05,
"loss": 0.3879,
"step": 538
},
{
"epoch": 1.5,
"learning_rate": 1.0437450115219803e-05,
"loss": 0.4156,
"step": 539
},
{
"epoch": 1.51,
"learning_rate": 1.0407298454278983e-05,
"loss": 0.3917,
"step": 540
},
{
"epoch": 1.51,
"learning_rate": 1.0377143083877936e-05,
"loss": 0.3858,
"step": 541
},
{
"epoch": 1.51,
"learning_rate": 1.0346984278655929e-05,
"loss": 0.3936,
"step": 542
},
{
"epoch": 1.51,
"learning_rate": 1.0316822313283504e-05,
"loss": 0.3873,
"step": 543
},
{
"epoch": 1.52,
"learning_rate": 1.0286657462459987e-05,
"loss": 0.3812,
"step": 544
},
{
"epoch": 1.52,
"learning_rate": 1.0256490000910986e-05,
"loss": 0.3882,
"step": 545
},
{
"epoch": 1.52,
"learning_rate": 1.0226320203385877e-05,
"loss": 0.4096,
"step": 546
},
{
"epoch": 1.53,
"learning_rate": 1.0196148344655323e-05,
"loss": 0.3838,
"step": 547
},
{
"epoch": 1.53,
"learning_rate": 1.0165974699508752e-05,
"loss": 0.4064,
"step": 548
},
{
"epoch": 1.53,
"learning_rate": 1.0135799542751861e-05,
"loss": 0.4131,
"step": 549
},
{
"epoch": 1.53,
"learning_rate": 1.0105623149204118e-05,
"loss": 0.4094,
"step": 550
},
{
"epoch": 1.54,
"learning_rate": 1.0075445793696255e-05,
"loss": 0.3844,
"step": 551
},
{
"epoch": 1.54,
"learning_rate": 1.0045267751067758e-05,
"loss": 0.3538,
"step": 552
},
{
"epoch": 1.54,
"learning_rate": 1.001508929616438e-05,
"loss": 0.4484,
"step": 553
},
{
"epoch": 1.55,
"learning_rate": 9.984910703835625e-06,
"loss": 0.4138,
"step": 554
},
{
"epoch": 1.55,
"learning_rate": 9.954732248932243e-06,
"loss": 0.4313,
"step": 555
},
{
"epoch": 1.55,
"learning_rate": 9.924554206303752e-06,
"loss": 0.378,
"step": 556
},
{
"epoch": 1.55,
"learning_rate": 9.894376850795883e-06,
"loss": 0.3991,
"step": 557
},
{
"epoch": 1.56,
"learning_rate": 9.864200457248144e-06,
"loss": 0.3698,
"step": 558
},
{
"epoch": 1.56,
"learning_rate": 9.834025300491251e-06,
"loss": 0.3383,
"step": 559
},
{
"epoch": 1.56,
"learning_rate": 9.803851655344682e-06,
"loss": 0.4006,
"step": 560
},
{
"epoch": 1.56,
"learning_rate": 9.773679796614124e-06,
"loss": 0.3852,
"step": 561
},
{
"epoch": 1.57,
"learning_rate": 9.743509999089021e-06,
"loss": 0.405,
"step": 562
},
{
"epoch": 1.57,
"learning_rate": 9.713342537540014e-06,
"loss": 0.4243,
"step": 563
},
{
"epoch": 1.57,
"learning_rate": 9.683177686716501e-06,
"loss": 0.4277,
"step": 564
},
{
"epoch": 1.58,
"learning_rate": 9.653015721344073e-06,
"loss": 0.3893,
"step": 565
},
{
"epoch": 1.58,
"learning_rate": 9.622856916122066e-06,
"loss": 0.3944,
"step": 566
},
{
"epoch": 1.58,
"learning_rate": 9.592701545721022e-06,
"loss": 0.3954,
"step": 567
},
{
"epoch": 1.58,
"learning_rate": 9.5625498847802e-06,
"loss": 0.3818,
"step": 568
},
{
"epoch": 1.59,
"learning_rate": 9.532402207905083e-06,
"loss": 0.4143,
"step": 569
},
{
"epoch": 1.59,
"learning_rate": 9.502258789664865e-06,
"loss": 0.4155,
"step": 570
},
{
"epoch": 1.59,
"learning_rate": 9.47211990458995e-06,
"loss": 0.4167,
"step": 571
},
{
"epoch": 1.6,
"learning_rate": 9.441985827169463e-06,
"loss": 0.4091,
"step": 572
},
{
"epoch": 1.6,
"learning_rate": 9.411856831848745e-06,
"loss": 0.4139,
"step": 573
},
{
"epoch": 1.6,
"learning_rate": 9.381733193026842e-06,
"loss": 0.3869,
"step": 574
},
{
"epoch": 1.6,
"learning_rate": 9.351615185054029e-06,
"loss": 0.4064,
"step": 575
},
{
"epoch": 1.61,
"learning_rate": 9.321503082229281e-06,
"loss": 0.4028,
"step": 576
},
{
"epoch": 1.61,
"learning_rate": 9.291397158797814e-06,
"loss": 0.4259,
"step": 577
},
{
"epoch": 1.61,
"learning_rate": 9.261297688948541e-06,
"loss": 0.3992,
"step": 578
},
{
"epoch": 1.62,
"learning_rate": 9.231204946811624e-06,
"loss": 0.3623,
"step": 579
},
{
"epoch": 1.62,
"learning_rate": 9.201119206455927e-06,
"loss": 0.3811,
"step": 580
},
{
"epoch": 1.62,
"learning_rate": 9.17104074188657e-06,
"loss": 0.4153,
"step": 581
},
{
"epoch": 1.62,
"learning_rate": 9.140969827042392e-06,
"loss": 0.4114,
"step": 582
},
{
"epoch": 1.63,
"learning_rate": 9.11090673579348e-06,
"loss": 0.4204,
"step": 583
},
{
"epoch": 1.63,
"learning_rate": 9.080851741938663e-06,
"loss": 0.4122,
"step": 584
},
{
"epoch": 1.63,
"learning_rate": 9.050805119203035e-06,
"loss": 0.4171,
"step": 585
},
{
"epoch": 1.63,
"learning_rate": 9.020767141235432e-06,
"loss": 0.4116,
"step": 586
},
{
"epoch": 1.64,
"learning_rate": 8.990738081605976e-06,
"loss": 0.4111,
"step": 587
},
{
"epoch": 1.64,
"learning_rate": 8.96071821380355e-06,
"loss": 0.3844,
"step": 588
},
{
"epoch": 1.64,
"learning_rate": 8.930707811233337e-06,
"loss": 0.4206,
"step": 589
},
{
"epoch": 1.65,
"learning_rate": 8.900707147214301e-06,
"loss": 0.4235,
"step": 590
},
{
"epoch": 1.65,
"learning_rate": 8.87071649497673e-06,
"loss": 0.4108,
"step": 591
},
{
"epoch": 1.65,
"learning_rate": 8.840736127659708e-06,
"loss": 0.393,
"step": 592
},
{
"epoch": 1.65,
"learning_rate": 8.810766318308674e-06,
"loss": 0.4062,
"step": 593
},
{
"epoch": 1.66,
"learning_rate": 8.780807339872886e-06,
"loss": 0.4317,
"step": 594
},
{
"epoch": 1.66,
"learning_rate": 8.75085946520298e-06,
"loss": 0.4628,
"step": 595
},
{
"epoch": 1.66,
"learning_rate": 8.720922967048451e-06,
"loss": 0.3944,
"step": 596
},
{
"epoch": 1.67,
"learning_rate": 8.690998118055193e-06,
"loss": 0.3787,
"step": 597
},
{
"epoch": 1.67,
"learning_rate": 8.661085190762997e-06,
"loss": 0.4224,
"step": 598
},
{
"epoch": 1.67,
"learning_rate": 8.631184457603086e-06,
"loss": 0.4006,
"step": 599
},
{
"epoch": 1.67,
"learning_rate": 8.601296190895611e-06,
"loss": 0.411,
"step": 600
},
{
"epoch": 1.68,
"learning_rate": 8.571420662847205e-06,
"loss": 0.3956,
"step": 601
},
{
"epoch": 1.68,
"learning_rate": 8.541558145548463e-06,
"loss": 0.4019,
"step": 602
},
{
"epoch": 1.68,
"learning_rate": 8.511708910971506e-06,
"loss": 0.3764,
"step": 603
},
{
"epoch": 1.68,
"learning_rate": 8.48187323096746e-06,
"loss": 0.399,
"step": 604
},
{
"epoch": 1.69,
"learning_rate": 8.452051377264025e-06,
"loss": 0.382,
"step": 605
},
{
"epoch": 1.69,
"learning_rate": 8.42224362146297e-06,
"loss": 0.3827,
"step": 606
},
{
"epoch": 1.69,
"learning_rate": 8.392450235037656e-06,
"loss": 0.4008,
"step": 607
},
{
"epoch": 1.7,
"learning_rate": 8.362671489330598e-06,
"loss": 0.3979,
"step": 608
},
{
"epoch": 1.7,
"learning_rate": 8.332907655550948e-06,
"loss": 0.3835,
"step": 609
},
{
"epoch": 1.7,
"learning_rate": 8.303159004772065e-06,
"loss": 0.4093,
"step": 610
},
{
"epoch": 1.7,
"learning_rate": 8.273425807929022e-06,
"loss": 0.4103,
"step": 611
},
{
"epoch": 1.71,
"learning_rate": 8.243708335816145e-06,
"loss": 0.3868,
"step": 612
},
{
"epoch": 1.71,
"learning_rate": 8.214006859084547e-06,
"loss": 0.4083,
"step": 613
},
{
"epoch": 1.71,
"learning_rate": 8.184321648239673e-06,
"loss": 0.3875,
"step": 614
},
{
"epoch": 1.72,
"learning_rate": 8.15465297363881e-06,
"loss": 0.3807,
"step": 615
},
{
"epoch": 1.72,
"learning_rate": 8.12500110548866e-06,
"loss": 0.4037,
"step": 616
},
{
"epoch": 1.72,
"learning_rate": 8.095366313842843e-06,
"loss": 0.3695,
"step": 617
},
{
"epoch": 1.72,
"learning_rate": 8.065748868599471e-06,
"loss": 0.4219,
"step": 618
},
{
"epoch": 1.73,
"learning_rate": 8.036149039498659e-06,
"loss": 0.4153,
"step": 619
},
{
"epoch": 1.73,
"learning_rate": 8.006567096120103e-06,
"loss": 0.3965,
"step": 620
},
{
"epoch": 1.73,
"learning_rate": 7.977003307880579e-06,
"loss": 0.3974,
"step": 621
},
{
"epoch": 1.74,
"learning_rate": 7.947457944031542e-06,
"loss": 0.3881,
"step": 622
},
{
"epoch": 1.74,
"learning_rate": 7.917931273656629e-06,
"loss": 0.4082,
"step": 623
},
{
"epoch": 1.74,
"learning_rate": 7.888423565669236e-06,
"loss": 0.4046,
"step": 624
},
{
"epoch": 1.74,
"learning_rate": 7.858935088810054e-06,
"loss": 0.421,
"step": 625
},
{
"epoch": 1.75,
"learning_rate": 7.829466111644635e-06,
"loss": 0.4161,
"step": 626
},
{
"epoch": 1.75,
"learning_rate": 7.800016902560924e-06,
"loss": 0.3905,
"step": 627
},
{
"epoch": 1.75,
"learning_rate": 7.770587729766846e-06,
"loss": 0.4143,
"step": 628
},
{
"epoch": 1.75,
"learning_rate": 7.74117886128783e-06,
"loss": 0.3949,
"step": 629
},
{
"epoch": 1.76,
"learning_rate": 7.7117905649644e-06,
"loss": 0.4051,
"step": 630
},
{
"epoch": 1.76,
"learning_rate": 7.6824231084497e-06,
"loss": 0.4097,
"step": 631
},
{
"epoch": 1.76,
"learning_rate": 7.653076759207098e-06,
"loss": 0.4371,
"step": 632
},
{
"epoch": 1.77,
"learning_rate": 7.623751784507707e-06,
"loss": 0.3883,
"step": 633
},
{
"epoch": 1.77,
"learning_rate": 7.594448451427991e-06,
"loss": 0.4254,
"step": 634
},
{
"epoch": 1.77,
"learning_rate": 7.565167026847294e-06,
"loss": 0.3878,
"step": 635
},
{
"epoch": 1.77,
"learning_rate": 7.535907777445449e-06,
"loss": 0.3839,
"step": 636
},
{
"epoch": 1.78,
"learning_rate": 7.506670969700314e-06,
"loss": 0.3911,
"step": 637
},
{
"epoch": 1.78,
"learning_rate": 7.477456869885368e-06,
"loss": 0.437,
"step": 638
},
{
"epoch": 1.78,
"learning_rate": 7.448265744067275e-06,
"loss": 0.3844,
"step": 639
},
{
"epoch": 1.79,
"learning_rate": 7.419097858103464e-06,
"loss": 0.3802,
"step": 640
},
{
"epoch": 1.79,
"learning_rate": 7.389953477639711e-06,
"loss": 0.3812,
"step": 641
},
{
"epoch": 1.79,
"learning_rate": 7.360832868107708e-06,
"loss": 0.41,
"step": 642
},
{
"epoch": 1.79,
"learning_rate": 7.331736294722667e-06,
"loss": 0.4534,
"step": 643
},
{
"epoch": 1.8,
"learning_rate": 7.302664022480874e-06,
"loss": 0.3918,
"step": 644
},
{
"epoch": 1.8,
"learning_rate": 7.273616316157312e-06,
"loss": 0.4445,
"step": 645
},
{
"epoch": 1.8,
"learning_rate": 7.244593440303216e-06,
"loss": 0.4485,
"step": 646
},
{
"epoch": 1.8,
"learning_rate": 7.215595659243686e-06,
"loss": 0.426,
"step": 647
},
{
"epoch": 1.81,
"learning_rate": 7.186623237075265e-06,
"loss": 0.3767,
"step": 648
},
{
"epoch": 1.81,
"learning_rate": 7.157676437663552e-06,
"loss": 0.3753,
"step": 649
},
{
"epoch": 1.81,
"learning_rate": 7.128755524640771e-06,
"loss": 0.3964,
"step": 650
},
{
"epoch": 1.82,
"learning_rate": 7.0998607614034035e-06,
"loss": 0.4102,
"step": 651
},
{
"epoch": 1.82,
"learning_rate": 7.0709924111097605e-06,
"loss": 0.3729,
"step": 652
},
{
"epoch": 1.82,
"learning_rate": 7.042150736677603e-06,
"loss": 0.3837,
"step": 653
},
{
"epoch": 1.82,
"learning_rate": 7.013336000781739e-06,
"loss": 0.3816,
"step": 654
},
{
"epoch": 1.83,
"learning_rate": 6.984548465851641e-06,
"loss": 0.3742,
"step": 655
},
{
"epoch": 1.83,
"learning_rate": 6.95578839406904e-06,
"loss": 0.3812,
"step": 656
},
{
"epoch": 1.83,
"learning_rate": 6.927056047365558e-06,
"loss": 0.4035,
"step": 657
},
{
"epoch": 1.84,
"learning_rate": 6.898351687420297e-06,
"loss": 0.4232,
"step": 658
},
{
"epoch": 1.84,
"learning_rate": 6.869675575657489e-06,
"loss": 0.4125,
"step": 659
},
{
"epoch": 1.84,
"learning_rate": 6.841027973244077e-06,
"loss": 0.4048,
"step": 660
},
{
"epoch": 1.84,
"learning_rate": 6.8124091410873725e-06,
"loss": 0.4445,
"step": 661
},
{
"epoch": 1.85,
"learning_rate": 6.783819339832648e-06,
"loss": 0.4507,
"step": 662
},
{
"epoch": 1.85,
"learning_rate": 6.755258829860791e-06,
"loss": 0.4081,
"step": 663
},
{
"epoch": 1.85,
"learning_rate": 6.726727871285913e-06,
"loss": 0.4122,
"step": 664
},
{
"epoch": 1.85,
"learning_rate": 6.698226723952985e-06,
"loss": 0.4088,
"step": 665
},
{
"epoch": 1.86,
"learning_rate": 6.669755647435474e-06,
"loss": 0.4369,
"step": 666
},
{
"epoch": 1.86,
"learning_rate": 6.641314901032987e-06,
"loss": 0.4021,
"step": 667
},
{
"epoch": 1.86,
"learning_rate": 6.612904743768882e-06,
"loss": 0.3967,
"step": 668
},
{
"epoch": 1.87,
"learning_rate": 6.584525434387945e-06,
"loss": 0.4233,
"step": 669
},
{
"epoch": 1.87,
"learning_rate": 6.556177231354003e-06,
"loss": 0.4428,
"step": 670
},
{
"epoch": 1.87,
"learning_rate": 6.527860392847594e-06,
"loss": 0.4144,
"step": 671
},
{
"epoch": 1.87,
"learning_rate": 6.499575176763591e-06,
"loss": 0.4129,
"step": 672
},
{
"epoch": 1.88,
"learning_rate": 6.4713218407088774e-06,
"loss": 0.4244,
"step": 673
},
{
"epoch": 1.88,
"learning_rate": 6.4431006419999905e-06,
"loss": 0.4267,
"step": 674
},
{
"epoch": 1.88,
"learning_rate": 6.414911837660768e-06,
"loss": 0.3667,
"step": 675
},
{
"epoch": 1.89,
"learning_rate": 6.386755684420028e-06,
"loss": 0.4134,
"step": 676
},
{
"epoch": 1.89,
"learning_rate": 6.358632438709204e-06,
"loss": 0.4101,
"step": 677
},
{
"epoch": 1.89,
"learning_rate": 6.330542356660047e-06,
"loss": 0.3935,
"step": 678
},
{
"epoch": 1.89,
"learning_rate": 6.3024856941022515e-06,
"loss": 0.4198,
"step": 679
},
{
"epoch": 1.9,
"learning_rate": 6.274462706561153e-06,
"loss": 0.4137,
"step": 680
},
{
"epoch": 1.9,
"learning_rate": 6.246473649255391e-06,
"loss": 0.3957,
"step": 681
},
{
"epoch": 1.9,
"learning_rate": 6.218518777094593e-06,
"loss": 0.4199,
"step": 682
},
{
"epoch": 1.91,
"learning_rate": 6.1905983446770305e-06,
"loss": 0.4482,
"step": 683
},
{
"epoch": 1.91,
"learning_rate": 6.162712606287335e-06,
"loss": 0.3822,
"step": 684
},
{
"epoch": 1.91,
"learning_rate": 6.134861815894146e-06,
"loss": 0.4165,
"step": 685
},
{
"epoch": 1.91,
"learning_rate": 6.107046227147828e-06,
"loss": 0.4145,
"step": 686
},
{
"epoch": 1.92,
"learning_rate": 6.079266093378138e-06,
"loss": 0.4083,
"step": 687
},
{
"epoch": 1.92,
"learning_rate": 6.051521667591937e-06,
"loss": 0.4343,
"step": 688
},
{
"epoch": 1.92,
"learning_rate": 6.023813202470863e-06,
"loss": 0.4274,
"step": 689
},
{
"epoch": 1.92,
"learning_rate": 5.9961409503690605e-06,
"loss": 0.3947,
"step": 690
},
{
"epoch": 1.93,
"learning_rate": 5.9685051633108474e-06,
"loss": 0.4116,
"step": 691
},
{
"epoch": 1.93,
"learning_rate": 5.940906092988451e-06,
"loss": 0.4014,
"step": 692
},
{
"epoch": 1.93,
"learning_rate": 5.913343990759695e-06,
"loss": 0.4344,
"step": 693
},
{
"epoch": 1.94,
"learning_rate": 5.885819107645718e-06,
"loss": 0.4235,
"step": 694
},
{
"epoch": 1.94,
"learning_rate": 5.858331694328686e-06,
"loss": 0.3971,
"step": 695
},
{
"epoch": 1.94,
"learning_rate": 5.830882001149517e-06,
"loss": 0.4094,
"step": 696
},
{
"epoch": 1.94,
"learning_rate": 5.803470278105574e-06,
"loss": 0.3832,
"step": 697
},
{
"epoch": 1.95,
"learning_rate": 5.776096774848436e-06,
"loss": 0.4144,
"step": 698
},
{
"epoch": 1.95,
"learning_rate": 5.748761740681573e-06,
"loss": 0.4265,
"step": 699
},
{
"epoch": 1.95,
"learning_rate": 5.721465424558111e-06,
"loss": 0.4222,
"step": 700
},
{
"epoch": 1.96,
"learning_rate": 5.694208075078549e-06,
"loss": 0.4339,
"step": 701
},
{
"epoch": 1.96,
"learning_rate": 5.666989940488496e-06,
"loss": 0.4306,
"step": 702
},
{
"epoch": 1.96,
"learning_rate": 5.639811268676416e-06,
"loss": 0.4123,
"step": 703
},
{
"epoch": 1.96,
"learning_rate": 5.6126723071713676e-06,
"loss": 0.4139,
"step": 704
},
{
"epoch": 1.97,
"learning_rate": 5.585573303140741e-06,
"loss": 0.4002,
"step": 705
},
{
"epoch": 1.97,
"learning_rate": 5.5585145033880216e-06,
"loss": 0.3901,
"step": 706
},
{
"epoch": 1.97,
"learning_rate": 5.531496154350544e-06,
"loss": 0.4167,
"step": 707
},
{
"epoch": 1.97,
"learning_rate": 5.504518502097212e-06,
"loss": 0.4284,
"step": 708
},
{
"epoch": 1.98,
"learning_rate": 5.477581792326319e-06,
"loss": 0.4375,
"step": 709
},
{
"epoch": 1.98,
"learning_rate": 5.450686270363244e-06,
"loss": 0.4093,
"step": 710
},
{
"epoch": 1.98,
"learning_rate": 5.423832181158274e-06,
"loss": 0.431,
"step": 711
},
{
"epoch": 1.99,
"learning_rate": 5.397019769284326e-06,
"loss": 0.4054,
"step": 712
},
{
"epoch": 1.99,
"learning_rate": 5.3702492789347645e-06,
"loss": 0.4119,
"step": 713
},
{
"epoch": 1.99,
"learning_rate": 5.34352095392114e-06,
"loss": 0.4035,
"step": 714
},
{
"epoch": 1.99,
"learning_rate": 5.316835037670987e-06,
"loss": 0.4066,
"step": 715
},
{
"epoch": 2.0,
"learning_rate": 5.2901917732256e-06,
"loss": 0.3987,
"step": 716
},
{
"epoch": 2.0,
"learning_rate": 5.263591403237831e-06,
"loss": 0.3854,
"step": 717
},
{
"epoch": 2.0,
"learning_rate": 5.237034169969866e-06,
"loss": 0.3665,
"step": 718
},
{
"epoch": 2.01,
"learning_rate": 5.210520315291023e-06,
"loss": 0.3579,
"step": 719
},
{
"epoch": 2.01,
"learning_rate": 5.184050080675558e-06,
"loss": 0.3745,
"step": 720
},
{
"epoch": 2.01,
"learning_rate": 5.157623707200452e-06,
"loss": 0.3828,
"step": 721
},
{
"epoch": 2.01,
"learning_rate": 5.1312414355432215e-06,
"loss": 0.4223,
"step": 722
},
{
"epoch": 2.02,
"learning_rate": 5.10490350597973e-06,
"loss": 0.3982,
"step": 723
},
{
"epoch": 2.02,
"learning_rate": 5.078610158381998e-06,
"loss": 0.3901,
"step": 724
},
{
"epoch": 2.02,
"learning_rate": 5.052361632216009e-06,
"loss": 0.3741,
"step": 725
},
{
"epoch": 2.03,
"learning_rate": 5.026158166539548e-06,
"loss": 0.3863,
"step": 726
},
{
"epoch": 2.03,
"learning_rate": 5.000000000000003e-06,
"loss": 0.4018,
"step": 727
},
{
"epoch": 2.03,
"learning_rate": 4.9738873708322e-06,
"loss": 0.3812,
"step": 728
},
{
"epoch": 2.03,
"learning_rate": 4.9478205168562535e-06,
"loss": 0.4001,
"step": 729
},
{
"epoch": 2.04,
"learning_rate": 4.9217996754753505e-06,
"loss": 0.4,
"step": 730
},
{
"epoch": 2.04,
"learning_rate": 4.895825083673652e-06,
"loss": 0.3915,
"step": 731
},
{
"epoch": 2.04,
"learning_rate": 4.869896978014071e-06,
"loss": 0.3872,
"step": 732
},
{
"epoch": 2.04,
"learning_rate": 4.844015594636181e-06,
"loss": 0.3821,
"step": 733
},
{
"epoch": 2.05,
"learning_rate": 4.818181169254001e-06,
"loss": 0.3583,
"step": 734
},
{
"epoch": 2.05,
"learning_rate": 4.792393937153914e-06,
"loss": 0.4123,
"step": 735
},
{
"epoch": 2.05,
"learning_rate": 4.766654133192459e-06,
"loss": 0.3549,
"step": 736
},
{
"epoch": 2.06,
"learning_rate": 4.740961991794254e-06,
"loss": 0.3415,
"step": 737
},
{
"epoch": 2.06,
"learning_rate": 4.7153177469498045e-06,
"loss": 0.351,
"step": 738
},
{
"epoch": 2.06,
"learning_rate": 4.689721632213423e-06,
"loss": 0.369,
"step": 739
},
{
"epoch": 2.06,
"learning_rate": 4.664173880701065e-06,
"loss": 0.3668,
"step": 740
},
{
"epoch": 2.07,
"learning_rate": 4.6386747250882226e-06,
"loss": 0.3516,
"step": 741
},
{
"epoch": 2.07,
"learning_rate": 4.613224397607799e-06,
"loss": 0.3493,
"step": 742
},
{
"epoch": 2.07,
"learning_rate": 4.5878231300480016e-06,
"loss": 0.3472,
"step": 743
},
{
"epoch": 2.08,
"learning_rate": 4.562471153750221e-06,
"loss": 0.3462,
"step": 744
},
{
"epoch": 2.08,
"learning_rate": 4.537168699606928e-06,
"loss": 0.3501,
"step": 745
},
{
"epoch": 2.08,
"learning_rate": 4.5119159980595885e-06,
"loss": 0.36,
"step": 746
},
{
"epoch": 2.08,
"learning_rate": 4.486713279096515e-06,
"loss": 0.3827,
"step": 747
},
{
"epoch": 2.09,
"learning_rate": 4.461560772250841e-06,
"loss": 0.389,
"step": 748
},
{
"epoch": 2.09,
"learning_rate": 4.436458706598362e-06,
"loss": 0.3548,
"step": 749
},
{
"epoch": 2.09,
"learning_rate": 4.411407310755513e-06,
"loss": 0.3423,
"step": 750
},
{
"epoch": 2.09,
"learning_rate": 4.386406812877223e-06,
"loss": 0.3367,
"step": 751
},
{
"epoch": 2.1,
"learning_rate": 4.361457440654901e-06,
"loss": 0.3278,
"step": 752
},
{
"epoch": 2.1,
"learning_rate": 4.336559421314298e-06,
"loss": 0.3429,
"step": 753
},
{
"epoch": 2.1,
"learning_rate": 4.311712981613499e-06,
"loss": 0.3439,
"step": 754
},
{
"epoch": 2.11,
"learning_rate": 4.2869183478408125e-06,
"loss": 0.3615,
"step": 755
},
{
"epoch": 2.11,
"learning_rate": 4.262175745812729e-06,
"loss": 0.354,
"step": 756
},
{
"epoch": 2.11,
"learning_rate": 4.237485400871862e-06,
"loss": 0.3394,
"step": 757
},
{
"epoch": 2.11,
"learning_rate": 4.212847537884897e-06,
"loss": 0.3616,
"step": 758
},
{
"epoch": 2.12,
"learning_rate": 4.1882623812405345e-06,
"loss": 0.3214,
"step": 759
},
{
"epoch": 2.12,
"learning_rate": 4.163730154847462e-06,
"loss": 0.3513,
"step": 760
},
{
"epoch": 2.12,
"learning_rate": 4.1392510821323e-06,
"loss": 0.3626,
"step": 761
},
{
"epoch": 2.13,
"learning_rate": 4.1148253860375764e-06,
"loss": 0.3422,
"step": 762
},
{
"epoch": 2.13,
"learning_rate": 4.090453289019691e-06,
"loss": 0.3405,
"step": 763
},
{
"epoch": 2.13,
"learning_rate": 4.066135013046893e-06,
"loss": 0.3522,
"step": 764
},
{
"epoch": 2.13,
"learning_rate": 4.0418707795972575e-06,
"loss": 0.3357,
"step": 765
},
{
"epoch": 2.14,
"learning_rate": 4.0176608096566675e-06,
"loss": 0.329,
"step": 766
},
{
"epoch": 2.14,
"learning_rate": 3.993505323716803e-06,
"loss": 0.313,
"step": 767
},
{
"epoch": 2.14,
"learning_rate": 3.969404541773132e-06,
"loss": 0.3498,
"step": 768
},
{
"epoch": 2.15,
"learning_rate": 3.9453586833229064e-06,
"loss": 0.3453,
"step": 769
},
{
"epoch": 2.15,
"learning_rate": 3.9213679673631745e-06,
"loss": 0.3384,
"step": 770
},
{
"epoch": 2.15,
"learning_rate": 3.897432612388752e-06,
"loss": 0.352,
"step": 771
},
{
"epoch": 2.15,
"learning_rate": 3.873552836390281e-06,
"loss": 0.3583,
"step": 772
},
{
"epoch": 2.16,
"learning_rate": 3.849728856852206e-06,
"loss": 0.3554,
"step": 773
},
{
"epoch": 2.16,
"learning_rate": 3.8259608907508105e-06,
"loss": 0.3695,
"step": 774
},
{
"epoch": 2.16,
"learning_rate": 3.8022491545522346e-06,
"loss": 0.3557,
"step": 775
},
{
"epoch": 2.16,
"learning_rate": 3.778593864210508e-06,
"loss": 0.3423,
"step": 776
},
{
"epoch": 2.17,
"learning_rate": 3.7549952351655795e-06,
"loss": 0.3464,
"step": 777
},
{
"epoch": 2.17,
"learning_rate": 3.7314534823413604e-06,
"loss": 0.3518,
"step": 778
},
{
"epoch": 2.17,
"learning_rate": 3.707968820143758e-06,
"loss": 0.367,
"step": 779
},
{
"epoch": 2.18,
"learning_rate": 3.6845414624587326e-06,
"loss": 0.3444,
"step": 780
},
{
"epoch": 2.18,
"learning_rate": 3.6611716226503434e-06,
"loss": 0.3405,
"step": 781
},
{
"epoch": 2.18,
"learning_rate": 3.6378595135588058e-06,
"loss": 0.3533,
"step": 782
},
{
"epoch": 2.18,
"learning_rate": 3.6146053474985565e-06,
"loss": 0.3249,
"step": 783
},
{
"epoch": 2.19,
"learning_rate": 3.5914093362563164e-06,
"loss": 0.3624,
"step": 784
},
{
"epoch": 2.19,
"learning_rate": 3.5682716910891613e-06,
"loss": 0.3262,
"step": 785
},
{
"epoch": 2.19,
"learning_rate": 3.5451926227225997e-06,
"loss": 0.3431,
"step": 786
},
{
"epoch": 2.2,
"learning_rate": 3.522172341348663e-06,
"loss": 0.379,
"step": 787
},
{
"epoch": 2.2,
"learning_rate": 3.4992110566239623e-06,
"loss": 0.3579,
"step": 788
},
{
"epoch": 2.2,
"learning_rate": 3.4763089776678206e-06,
"loss": 0.3567,
"step": 789
},
{
"epoch": 2.2,
"learning_rate": 3.453466313060322e-06,
"loss": 0.3555,
"step": 790
},
{
"epoch": 2.21,
"learning_rate": 3.4306832708404614e-06,
"loss": 0.3531,
"step": 791
},
{
"epoch": 2.21,
"learning_rate": 3.4079600585041993e-06,
"loss": 0.35,
"step": 792
},
{
"epoch": 2.21,
"learning_rate": 3.38529688300262e-06,
"loss": 0.3468,
"step": 793
},
{
"epoch": 2.21,
"learning_rate": 3.3626939507400026e-06,
"loss": 0.3468,
"step": 794
},
{
"epoch": 2.22,
"learning_rate": 3.3401514675719815e-06,
"loss": 0.3648,
"step": 795
},
{
"epoch": 2.22,
"learning_rate": 3.317669638803641e-06,
"loss": 0.3747,
"step": 796
},
{
"epoch": 2.22,
"learning_rate": 3.2952486691876585e-06,
"loss": 0.3622,
"step": 797
},
{
"epoch": 2.23,
"learning_rate": 3.2728887629224415e-06,
"loss": 0.3613,
"step": 798
},
{
"epoch": 2.23,
"learning_rate": 3.2505901236502622e-06,
"loss": 0.3517,
"step": 799
},
{
"epoch": 2.23,
"learning_rate": 3.228352954455406e-06,
"loss": 0.3435,
"step": 800
},
{
"epoch": 2.23,
"learning_rate": 3.206177457862321e-06,
"loss": 0.3445,
"step": 801
},
{
"epoch": 2.24,
"learning_rate": 3.1840638358337717e-06,
"loss": 0.3541,
"step": 802
},
{
"epoch": 2.24,
"learning_rate": 3.1620122897690055e-06,
"loss": 0.3584,
"step": 803
},
{
"epoch": 2.24,
"learning_rate": 3.1400230205019124e-06,
"loss": 0.3395,
"step": 804
},
{
"epoch": 2.25,
"learning_rate": 3.1180962282991976e-06,
"loss": 0.3657,
"step": 805
},
{
"epoch": 2.25,
"learning_rate": 3.0962321128585603e-06,
"loss": 0.3595,
"step": 806
},
{
"epoch": 2.25,
"learning_rate": 3.074430873306865e-06,
"loss": 0.3803,
"step": 807
},
{
"epoch": 2.25,
"learning_rate": 3.0526927081983538e-06,
"loss": 0.3658,
"step": 808
},
{
"epoch": 2.26,
"learning_rate": 3.0310178155127935e-06,
"loss": 0.3338,
"step": 809
},
{
"epoch": 2.26,
"learning_rate": 3.0094063926537233e-06,
"loss": 0.3401,
"step": 810
},
{
"epoch": 2.26,
"learning_rate": 2.98785863644662e-06,
"loss": 0.3516,
"step": 811
},
{
"epoch": 2.26,
"learning_rate": 2.9663747431371194e-06,
"loss": 0.3553,
"step": 812
},
{
"epoch": 2.27,
"learning_rate": 2.944954908389229e-06,
"loss": 0.3266,
"step": 813
},
{
"epoch": 2.27,
"learning_rate": 2.923599327283546e-06,
"loss": 0.3669,
"step": 814
},
{
"epoch": 2.27,
"learning_rate": 2.9023081943154753e-06,
"loss": 0.3792,
"step": 815
},
{
"epoch": 2.28,
"learning_rate": 2.881081703393466e-06,
"loss": 0.3627,
"step": 816
},
{
"epoch": 2.28,
"learning_rate": 2.859920047837238e-06,
"loss": 0.361,
"step": 817
},
{
"epoch": 2.28,
"learning_rate": 2.838823420376027e-06,
"loss": 0.3691,
"step": 818
},
{
"epoch": 2.28,
"learning_rate": 2.8177920131468273e-06,
"loss": 0.3597,
"step": 819
},
{
"epoch": 2.29,
"learning_rate": 2.7968260176926407e-06,
"loss": 0.3537,
"step": 820
},
{
"epoch": 2.29,
"learning_rate": 2.7759256249607325e-06,
"loss": 0.3769,
"step": 821
},
{
"epoch": 2.29,
"learning_rate": 2.7550910253008933e-06,
"loss": 0.367,
"step": 822
},
{
"epoch": 2.3,
"learning_rate": 2.7343224084637054e-06,
"loss": 0.337,
"step": 823
},
{
"epoch": 2.3,
"learning_rate": 2.7136199635988136e-06,
"loss": 0.3582,
"step": 824
},
{
"epoch": 2.3,
"learning_rate": 2.6929838792532035e-06,
"loss": 0.3698,
"step": 825
},
{
"epoch": 2.3,
"learning_rate": 2.6724143433694847e-06,
"loss": 0.3542,
"step": 826
},
{
"epoch": 2.31,
"learning_rate": 2.6519115432841736e-06,
"loss": 0.3538,
"step": 827
},
{
"epoch": 2.31,
"learning_rate": 2.6314756657260053e-06,
"loss": 0.3526,
"step": 828
},
{
"epoch": 2.31,
"learning_rate": 2.6111068968141993e-06,
"loss": 0.377,
"step": 829
},
{
"epoch": 2.32,
"learning_rate": 2.590805422056807e-06,
"loss": 0.3577,
"step": 830
},
{
"epoch": 2.32,
"learning_rate": 2.570571426348978e-06,
"loss": 0.3702,
"step": 831
},
{
"epoch": 2.32,
"learning_rate": 2.5504050939713197e-06,
"loss": 0.3753,
"step": 832
},
{
"epoch": 2.32,
"learning_rate": 2.5303066085881767e-06,
"loss": 0.3812,
"step": 833
},
{
"epoch": 2.33,
"learning_rate": 2.5102761532460005e-06,
"loss": 0.363,
"step": 834
},
{
"epoch": 2.33,
"learning_rate": 2.4903139103716365e-06,
"loss": 0.3815,
"step": 835
},
{
"epoch": 2.33,
"learning_rate": 2.4704200617707097e-06,
"loss": 0.3601,
"step": 836
},
{
"epoch": 2.33,
"learning_rate": 2.450594788625932e-06,
"loss": 0.3657,
"step": 837
},
{
"epoch": 2.34,
"learning_rate": 2.4308382714954703e-06,
"loss": 0.3864,
"step": 838
},
{
"epoch": 2.34,
"learning_rate": 2.411150690311298e-06,
"loss": 0.3706,
"step": 839
},
{
"epoch": 2.34,
"learning_rate": 2.3915322243775564e-06,
"loss": 0.3607,
"step": 840
},
{
"epoch": 2.35,
"learning_rate": 2.371983052368919e-06,
"loss": 0.3555,
"step": 841
},
{
"epoch": 2.35,
"learning_rate": 2.3525033523289662e-06,
"loss": 0.3622,
"step": 842
},
{
"epoch": 2.35,
"learning_rate": 2.3330933016685753e-06,
"loss": 0.3485,
"step": 843
},
{
"epoch": 2.35,
"learning_rate": 2.3137530771642745e-06,
"loss": 0.3619,
"step": 844
},
{
"epoch": 2.36,
"learning_rate": 2.294482854956672e-06,
"loss": 0.3752,
"step": 845
},
{
"epoch": 2.36,
"learning_rate": 2.275282810548811e-06,
"loss": 0.3631,
"step": 846
},
{
"epoch": 2.36,
"learning_rate": 2.256153118804616e-06,
"loss": 0.3472,
"step": 847
},
{
"epoch": 2.37,
"learning_rate": 2.2370939539472523e-06,
"loss": 0.3907,
"step": 848
},
{
"epoch": 2.37,
"learning_rate": 2.2181054895575847e-06,
"loss": 0.3644,
"step": 849
},
{
"epoch": 2.37,
"learning_rate": 2.1991878985725566e-06,
"loss": 0.4088,
"step": 850
},
{
"epoch": 2.37,
"learning_rate": 2.1803413532836494e-06,
"loss": 0.3467,
"step": 851
},
{
"epoch": 2.38,
"learning_rate": 2.1615660253352888e-06,
"loss": 0.3452,
"step": 852
},
{
"epoch": 2.38,
"learning_rate": 2.1428620857232927e-06,
"loss": 0.3669,
"step": 853
},
{
"epoch": 2.38,
"learning_rate": 2.1242297047933104e-06,
"loss": 0.3648,
"step": 854
},
{
"epoch": 2.38,
"learning_rate": 2.105669052239274e-06,
"loss": 0.3529,
"step": 855
},
{
"epoch": 2.39,
"learning_rate": 2.0871802971018507e-06,
"loss": 0.3611,
"step": 856
},
{
"epoch": 2.39,
"learning_rate": 2.0687636077669026e-06,
"loss": 0.3565,
"step": 857
},
{
"epoch": 2.39,
"learning_rate": 2.050419151963957e-06,
"loss": 0.351,
"step": 858
},
{
"epoch": 2.4,
"learning_rate": 2.032147096764674e-06,
"loss": 0.3879,
"step": 859
},
{
"epoch": 2.4,
"learning_rate": 2.013947608581327e-06,
"loss": 0.3496,
"step": 860
},
{
"epoch": 2.4,
"learning_rate": 1.9958208531652876e-06,
"loss": 0.4002,
"step": 861
},
{
"epoch": 2.4,
"learning_rate": 1.9777669956055178e-06,
"loss": 0.3731,
"step": 862
},
{
"epoch": 2.41,
"learning_rate": 1.9597862003270595e-06,
"loss": 0.3909,
"step": 863
},
{
"epoch": 2.41,
"learning_rate": 1.9418786310895467e-06,
"loss": 0.3385,
"step": 864
},
{
"epoch": 2.41,
"learning_rate": 1.924044450985706e-06,
"loss": 0.3619,
"step": 865
},
{
"epoch": 2.42,
"learning_rate": 1.906283822439875e-06,
"loss": 0.3628,
"step": 866
},
{
"epoch": 2.42,
"learning_rate": 1.8885969072065224e-06,
"loss": 0.3807,
"step": 867
},
{
"epoch": 2.42,
"learning_rate": 1.870983866368773e-06,
"loss": 0.3633,
"step": 868
},
{
"epoch": 2.42,
"learning_rate": 1.8534448603369527e-06,
"loss": 0.3354,
"step": 869
},
{
"epoch": 2.43,
"learning_rate": 1.835980048847098e-06,
"loss": 0.3973,
"step": 870
},
{
"epoch": 2.43,
"learning_rate": 1.818589590959542e-06,
"loss": 0.3695,
"step": 871
},
{
"epoch": 2.43,
"learning_rate": 1.8012736450574231e-06,
"loss": 0.3842,
"step": 872
},
{
"epoch": 2.44,
"learning_rate": 1.7840323688452833e-06,
"loss": 0.3846,
"step": 873
},
{
"epoch": 2.44,
"learning_rate": 1.766865919347599e-06,
"loss": 0.3575,
"step": 874
},
{
"epoch": 2.44,
"learning_rate": 1.7497744529073712e-06,
"loss": 0.3822,
"step": 875
},
{
"epoch": 2.44,
"learning_rate": 1.7327581251846902e-06,
"loss": 0.3381,
"step": 876
},
{
"epoch": 2.45,
"learning_rate": 1.715817091155324e-06,
"loss": 0.3656,
"step": 877
},
{
"epoch": 2.45,
"learning_rate": 1.6989515051093076e-06,
"loss": 0.3548,
"step": 878
},
{
"epoch": 2.45,
"learning_rate": 1.6821615206495313e-06,
"loss": 0.3978,
"step": 879
},
{
"epoch": 2.45,
"learning_rate": 1.6654472906903486e-06,
"loss": 0.3544,
"step": 880
},
{
"epoch": 2.46,
"learning_rate": 1.6488089674561802e-06,
"loss": 0.394,
"step": 881
},
{
"epoch": 2.46,
"learning_rate": 1.6322467024801282e-06,
"loss": 0.3778,
"step": 882
},
{
"epoch": 2.46,
"learning_rate": 1.6157606466025932e-06,
"loss": 0.3935,
"step": 883
},
{
"epoch": 2.47,
"learning_rate": 1.5993509499699134e-06,
"loss": 0.355,
"step": 884
},
{
"epoch": 2.47,
"learning_rate": 1.5830177620329712e-06,
"loss": 0.3787,
"step": 885
},
{
"epoch": 2.47,
"learning_rate": 1.5667612315458658e-06,
"loss": 0.3537,
"step": 886
},
{
"epoch": 2.47,
"learning_rate": 1.5505815065645225e-06,
"loss": 0.3657,
"step": 887
},
{
"epoch": 2.48,
"learning_rate": 1.5344787344453803e-06,
"loss": 0.3591,
"step": 888
},
{
"epoch": 2.48,
"learning_rate": 1.5184530618440142e-06,
"loss": 0.3943,
"step": 889
},
{
"epoch": 2.48,
"learning_rate": 1.502504634713835e-06,
"loss": 0.3498,
"step": 890
},
{
"epoch": 2.49,
"learning_rate": 1.4866335983047264e-06,
"loss": 0.377,
"step": 891
},
{
"epoch": 2.49,
"learning_rate": 1.4708400971617499e-06,
"loss": 0.3661,
"step": 892
},
{
"epoch": 2.49,
"learning_rate": 1.4551242751238116e-06,
"loss": 0.3831,
"step": 893
},
{
"epoch": 2.49,
"learning_rate": 1.439486275322357e-06,
"loss": 0.3545,
"step": 894
},
{
"epoch": 2.5,
"learning_rate": 1.423926240180068e-06,
"loss": 0.3809,
"step": 895
},
{
"epoch": 2.5,
"learning_rate": 1.4084443114095646e-06,
"loss": 0.3912,
"step": 896
},
{
"epoch": 2.5,
"learning_rate": 1.393040630012118e-06,
"loss": 0.3677,
"step": 897
},
{
"epoch": 2.5,
"learning_rate": 1.3777153362763596e-06,
"loss": 0.3865,
"step": 898
},
{
"epoch": 2.51,
"learning_rate": 1.36246856977701e-06,
"loss": 0.3424,
"step": 899
},
{
"epoch": 2.51,
"learning_rate": 1.3473004693736037e-06,
"loss": 0.3627,
"step": 900
},
{
"epoch": 2.51,
"learning_rate": 1.3322111732092268e-06,
"loss": 0.3887,
"step": 901
},
{
"epoch": 2.52,
"learning_rate": 1.3172008187092555e-06,
"loss": 0.3526,
"step": 902
},
{
"epoch": 2.52,
"learning_rate": 1.302269542580109e-06,
"loss": 0.365,
"step": 903
},
{
"epoch": 2.52,
"learning_rate": 1.2874174808080032e-06,
"loss": 0.3818,
"step": 904
},
{
"epoch": 2.52,
"learning_rate": 1.272644768657707e-06,
"loss": 0.3775,
"step": 905
},
{
"epoch": 2.53,
"learning_rate": 1.2579515406713194e-06,
"loss": 0.3538,
"step": 906
},
{
"epoch": 2.53,
"learning_rate": 1.2433379306670367e-06,
"loss": 0.4079,
"step": 907
},
{
"epoch": 2.53,
"learning_rate": 1.2288040717379358e-06,
"loss": 0.3967,
"step": 908
},
{
"epoch": 2.54,
"learning_rate": 1.214350096250767e-06,
"loss": 0.3649,
"step": 909
},
{
"epoch": 2.54,
"learning_rate": 1.1999761358447403e-06,
"loss": 0.3524,
"step": 910
},
{
"epoch": 2.54,
"learning_rate": 1.1856823214303303e-06,
"loss": 0.4004,
"step": 911
},
{
"epoch": 2.54,
"learning_rate": 1.1714687831880867e-06,
"loss": 0.3724,
"step": 912
},
{
"epoch": 2.55,
"learning_rate": 1.1573356505674427e-06,
"loss": 0.4131,
"step": 913
},
{
"epoch": 2.55,
"learning_rate": 1.143283052285542e-06,
"loss": 0.4035,
"step": 914
},
{
"epoch": 2.55,
"learning_rate": 1.1293111163260639e-06,
"loss": 0.3502,
"step": 915
},
{
"epoch": 2.56,
"learning_rate": 1.1154199699380552e-06,
"loss": 0.3772,
"step": 916
},
{
"epoch": 2.56,
"learning_rate": 1.1016097396347758e-06,
"loss": 0.3362,
"step": 917
},
{
"epoch": 2.56,
"learning_rate": 1.0878805511925438e-06,
"loss": 0.3427,
"step": 918
},
{
"epoch": 2.56,
"learning_rate": 1.0742325296495914e-06,
"loss": 0.3715,
"step": 919
},
{
"epoch": 2.57,
"learning_rate": 1.0606657993049253e-06,
"loss": 0.3922,
"step": 920
},
{
"epoch": 2.57,
"learning_rate": 1.0471804837171916e-06,
"loss": 0.3793,
"step": 921
},
{
"epoch": 2.57,
"learning_rate": 1.0337767057035585e-06,
"loss": 0.3923,
"step": 922
},
{
"epoch": 2.57,
"learning_rate": 1.0204545873385897e-06,
"loss": 0.3987,
"step": 923
},
{
"epoch": 2.58,
"learning_rate": 1.0072142499531346e-06,
"loss": 0.3641,
"step": 924
},
{
"epoch": 2.58,
"learning_rate": 9.940558141332323e-07,
"loss": 0.3795,
"step": 925
},
{
"epoch": 2.58,
"learning_rate": 9.80979399718991e-07,
"loss": 0.3689,
"step": 926
},
{
"epoch": 2.59,
"learning_rate": 9.679851258035277e-07,
"loss": 0.3949,
"step": 927
},
{
"epoch": 2.59,
"learning_rate": 9.550731107318511e-07,
"loss": 0.3724,
"step": 928
},
{
"epoch": 2.59,
"learning_rate": 9.422434720998164e-07,
"loss": 0.4081,
"step": 929
},
{
"epoch": 2.59,
"learning_rate": 9.294963267530177e-07,
"loss": 0.3782,
"step": 930
},
{
"epoch": 2.6,
"learning_rate": 9.168317907857637e-07,
"loss": 0.4003,
"step": 931
},
{
"epoch": 2.6,
"learning_rate": 9.042499795399839e-07,
"loss": 0.3765,
"step": 932
},
{
"epoch": 2.6,
"learning_rate": 8.917510076042058e-07,
"loss": 0.3913,
"step": 933
},
{
"epoch": 2.61,
"learning_rate": 8.793349888124947e-07,
"loss": 0.3868,
"step": 934
},
{
"epoch": 2.61,
"learning_rate": 8.670020362434229e-07,
"loss": 0.3938,
"step": 935
},
{
"epoch": 2.61,
"learning_rate": 8.547522622190385e-07,
"loss": 0.3958,
"step": 936
},
{
"epoch": 2.61,
"learning_rate": 8.425857783038471e-07,
"loss": 0.3746,
"step": 937
},
{
"epoch": 2.62,
"learning_rate": 8.305026953037854e-07,
"loss": 0.3381,
"step": 938
},
{
"epoch": 2.62,
"learning_rate": 8.185031232652252e-07,
"loss": 0.3998,
"step": 939
},
{
"epoch": 2.62,
"learning_rate": 8.065871714739581e-07,
"loss": 0.3893,
"step": 940
},
{
"epoch": 2.62,
"learning_rate": 7.947549484542094e-07,
"loss": 0.3825,
"step": 941
},
{
"epoch": 2.63,
"learning_rate": 7.830065619676519e-07,
"loss": 0.4101,
"step": 942
},
{
"epoch": 2.63,
"learning_rate": 7.713421190124071e-07,
"loss": 0.3662,
"step": 943
},
{
"epoch": 2.63,
"learning_rate": 7.597617258220957e-07,
"loss": 0.4231,
"step": 944
},
{
"epoch": 2.64,
"learning_rate": 7.482654878648465e-07,
"loss": 0.373,
"step": 945
},
{
"epoch": 2.64,
"learning_rate": 7.36853509842358e-07,
"loss": 0.3875,
"step": 946
},
{
"epoch": 2.64,
"learning_rate": 7.2552589568892e-07,
"loss": 0.3899,
"step": 947
},
{
"epoch": 2.64,
"learning_rate": 7.142827485704951e-07,
"loss": 0.4115,
"step": 948
},
{
"epoch": 2.65,
"learning_rate": 7.031241708837511e-07,
"loss": 0.4066,
"step": 949
},
{
"epoch": 2.65,
"learning_rate": 6.920502642551519e-07,
"loss": 0.3849,
"step": 950
},
{
"epoch": 2.65,
"learning_rate": 6.810611295400171e-07,
"loss": 0.3701,
"step": 951
},
{
"epoch": 2.66,
"learning_rate": 6.701568668216097e-07,
"loss": 0.4071,
"step": 952
},
{
"epoch": 2.66,
"learning_rate": 6.593375754102205e-07,
"loss": 0.4109,
"step": 953
},
{
"epoch": 2.66,
"learning_rate": 6.48603353842272e-07,
"loss": 0.4281,
"step": 954
},
{
"epoch": 2.66,
"learning_rate": 6.379542998794086e-07,
"loss": 0.3737,
"step": 955
},
{
"epoch": 2.67,
"learning_rate": 6.273905105076184e-07,
"loss": 0.3805,
"step": 956
},
{
"epoch": 2.67,
"learning_rate": 6.169120819363406e-07,
"loss": 0.3981,
"step": 957
},
{
"epoch": 2.67,
"learning_rate": 6.065191095975953e-07,
"loss": 0.3571,
"step": 958
},
{
"epoch": 2.68,
"learning_rate": 5.962116881451118e-07,
"loss": 0.422,
"step": 959
},
{
"epoch": 2.68,
"learning_rate": 5.859899114534662e-07,
"loss": 0.3758,
"step": 960
},
{
"epoch": 2.68,
"learning_rate": 5.758538726172269e-07,
"loss": 0.3831,
"step": 961
},
{
"epoch": 2.68,
"learning_rate": 5.658036639501086e-07,
"loss": 0.3591,
"step": 962
},
{
"epoch": 2.69,
"learning_rate": 5.558393769841286e-07,
"loss": 0.396,
"step": 963
},
{
"epoch": 2.69,
"learning_rate": 5.45961102468775e-07,
"loss": 0.3498,
"step": 964
},
{
"epoch": 2.69,
"learning_rate": 5.361689303701767e-07,
"loss": 0.3958,
"step": 965
},
{
"epoch": 2.69,
"learning_rate": 5.264629498702966e-07,
"loss": 0.3634,
"step": 966
},
{
"epoch": 2.7,
"learning_rate": 5.168432493660969e-07,
"loss": 0.387,
"step": 967
},
{
"epoch": 2.7,
"learning_rate": 5.073099164687567e-07,
"loss": 0.3924,
"step": 968
},
{
"epoch": 2.7,
"learning_rate": 4.978630380028582e-07,
"loss": 0.3974,
"step": 969
},
{
"epoch": 2.71,
"learning_rate": 4.885027000056075e-07,
"loss": 0.3697,
"step": 970
},
{
"epoch": 2.71,
"learning_rate": 4.792289877260403e-07,
"loss": 0.3876,
"step": 971
},
{
"epoch": 2.71,
"learning_rate": 4.700419856242555e-07,
"loss": 0.377,
"step": 972
},
{
"epoch": 2.71,
"learning_rate": 4.609417773706359e-07,
"loss": 0.3664,
"step": 973
},
{
"epoch": 2.72,
"learning_rate": 4.5192844584509787e-07,
"loss": 0.3805,
"step": 974
},
{
"epoch": 2.72,
"learning_rate": 4.4300207313632713e-07,
"loss": 0.3619,
"step": 975
},
{
"epoch": 2.72,
"learning_rate": 4.3416274054103203e-07,
"loss": 0.381,
"step": 976
},
{
"epoch": 2.73,
"learning_rate": 4.254105285632093e-07,
"loss": 0.4033,
"step": 977
},
{
"epoch": 2.73,
"learning_rate": 4.167455169134027e-07,
"loss": 0.3818,
"step": 978
},
{
"epoch": 2.73,
"learning_rate": 4.0816778450798677e-07,
"loss": 0.3893,
"step": 979
},
{
"epoch": 2.73,
"learning_rate": 3.9967740946843523e-07,
"loss": 0.387,
"step": 980
},
{
"epoch": 2.74,
"learning_rate": 3.9127446912062606e-07,
"loss": 0.3811,
"step": 981
},
{
"epoch": 2.74,
"learning_rate": 3.8295903999411857e-07,
"loss": 0.4173,
"step": 982
},
{
"epoch": 2.74,
"learning_rate": 3.7473119782147407e-07,
"loss": 0.3868,
"step": 983
},
{
"epoch": 2.74,
"learning_rate": 3.6659101753754975e-07,
"loss": 0.4036,
"step": 984
},
{
"epoch": 2.75,
"learning_rate": 3.585385732788327e-07,
"loss": 0.3848,
"step": 985
},
{
"epoch": 2.75,
"learning_rate": 3.5057393838274887e-07,
"loss": 0.3936,
"step": 986
},
{
"epoch": 2.75,
"learning_rate": 3.426971853870109e-07,
"loss": 0.3861,
"step": 987
},
{
"epoch": 2.76,
"learning_rate": 3.3490838602893925e-07,
"loss": 0.3936,
"step": 988
},
{
"epoch": 2.76,
"learning_rate": 3.2720761124482857e-07,
"loss": 0.3916,
"step": 989
},
{
"epoch": 2.76,
"learning_rate": 3.1959493116928473e-07,
"loss": 0.4089,
"step": 990
},
{
"epoch": 2.76,
"learning_rate": 3.120704151345977e-07,
"loss": 0.4056,
"step": 991
},
{
"epoch": 2.77,
"learning_rate": 3.0463413167010513e-07,
"loss": 0.3807,
"step": 992
},
{
"epoch": 2.77,
"learning_rate": 2.972861485015666e-07,
"loss": 0.3869,
"step": 993
},
{
"epoch": 2.77,
"learning_rate": 2.9002653255055027e-07,
"loss": 0.3768,
"step": 994
},
{
"epoch": 2.78,
"learning_rate": 2.828553499338227e-07,
"loss": 0.3971,
"step": 995
},
{
"epoch": 2.78,
"learning_rate": 2.7577266596274577e-07,
"loss": 0.3666,
"step": 996
},
{
"epoch": 2.78,
"learning_rate": 2.6877854514268166e-07,
"loss": 0.422,
"step": 997
},
{
"epoch": 2.78,
"learning_rate": 2.618730511724077e-07,
"loss": 0.3668,
"step": 998
},
{
"epoch": 2.79,
"learning_rate": 2.5505624694353027e-07,
"loss": 0.3767,
"step": 999
},
{
"epoch": 2.79,
"learning_rate": 2.4832819453992073e-07,
"loss": 0.3601,
"step": 1000
},
{
"epoch": 2.79,
"learning_rate": 2.416889552371449e-07,
"loss": 0.4332,
"step": 1001
},
{
"epoch": 2.79,
"learning_rate": 2.3513858950190206e-07,
"loss": 0.4183,
"step": 1002
},
{
"epoch": 2.8,
"learning_rate": 2.286771569914814e-07,
"loss": 0.3955,
"step": 1003
},
{
"epoch": 2.8,
"learning_rate": 2.223047165532144e-07,
"loss": 0.4664,
"step": 1004
},
{
"epoch": 2.8,
"learning_rate": 2.1602132622393745e-07,
"loss": 0.4004,
"step": 1005
},
{
"epoch": 2.81,
"learning_rate": 2.098270432294669e-07,
"loss": 0.4015,
"step": 1006
},
{
"epoch": 2.81,
"learning_rate": 2.037219239840782e-07,
"loss": 0.3549,
"step": 1007
},
{
"epoch": 2.81,
"learning_rate": 1.9770602408998642e-07,
"loss": 0.3821,
"step": 1008
},
{
"epoch": 2.81,
"learning_rate": 1.9177939833684544e-07,
"loss": 0.396,
"step": 1009
},
{
"epoch": 2.82,
"learning_rate": 1.8594210070124852e-07,
"loss": 0.3783,
"step": 1010
},
{
"epoch": 2.82,
"learning_rate": 1.8019418434623405e-07,
"loss": 0.3602,
"step": 1011
},
{
"epoch": 2.82,
"learning_rate": 1.745357016208016e-07,
"loss": 0.3735,
"step": 1012
},
{
"epoch": 2.83,
"learning_rate": 1.6896670405943783e-07,
"loss": 0.3725,
"step": 1013
},
{
"epoch": 2.83,
"learning_rate": 1.6348724238164583e-07,
"loss": 0.3559,
"step": 1014
},
{
"epoch": 2.83,
"learning_rate": 1.58097366491482e-07,
"loss": 0.4079,
"step": 1015
},
{
"epoch": 2.83,
"learning_rate": 1.5279712547710213e-07,
"loss": 0.3824,
"step": 1016
},
{
"epoch": 2.84,
"learning_rate": 1.475865676103161e-07,
"loss": 0.3934,
"step": 1017
},
{
"epoch": 2.84,
"learning_rate": 1.4246574034614603e-07,
"loss": 0.4144,
"step": 1018
},
{
"epoch": 2.84,
"learning_rate": 1.3743469032239442e-07,
"loss": 0.4124,
"step": 1019
},
{
"epoch": 2.85,
"learning_rate": 1.324934633592201e-07,
"loss": 0.4533,
"step": 1020
},
{
"epoch": 2.85,
"learning_rate": 1.276421044587217e-07,
"loss": 0.414,
"step": 1021
},
{
"epoch": 2.85,
"learning_rate": 1.2288065780452608e-07,
"loss": 0.4119,
"step": 1022
},
{
"epoch": 2.85,
"learning_rate": 1.1820916676138384e-07,
"loss": 0.3705,
"step": 1023
},
{
"epoch": 2.86,
"learning_rate": 1.1362767387478435e-07,
"loss": 0.4205,
"step": 1024
},
{
"epoch": 2.86,
"learning_rate": 1.0913622087055264e-07,
"loss": 0.4024,
"step": 1025
},
{
"epoch": 2.86,
"learning_rate": 1.0473484865448524e-07,
"loss": 0.38,
"step": 1026
},
{
"epoch": 2.86,
"learning_rate": 1.0042359731196272e-07,
"loss": 0.4117,
"step": 1027
},
{
"epoch": 2.87,
"learning_rate": 9.620250610759996e-08,
"loss": 0.4225,
"step": 1028
},
{
"epoch": 2.87,
"learning_rate": 9.207161348487315e-08,
"loss": 0.4228,
"step": 1029
},
{
"epoch": 2.87,
"learning_rate": 8.803095706578335e-08,
"loss": 0.3997,
"step": 1030
},
{
"epoch": 2.88,
"learning_rate": 8.40805736505046e-08,
"loss": 0.4116,
"step": 1031
},
{
"epoch": 2.88,
"learning_rate": 8.0220499217053e-08,
"loss": 0.4082,
"step": 1032
},
{
"epoch": 2.88,
"learning_rate": 7.645076892095704e-08,
"loss": 0.4017,
"step": 1033
},
{
"epoch": 2.88,
"learning_rate": 7.277141709493785e-08,
"loss": 0.3684,
"step": 1034
},
{
"epoch": 2.89,
"learning_rate": 6.918247724859939e-08,
"loss": 0.4342,
"step": 1035
},
{
"epoch": 2.89,
"learning_rate": 6.568398206811766e-08,
"loss": 0.3699,
"step": 1036
},
{
"epoch": 2.89,
"learning_rate": 6.227596341594978e-08,
"loss": 0.4226,
"step": 1037
},
{
"epoch": 2.9,
"learning_rate": 5.895845233053643e-08,
"loss": 0.4015,
"step": 1038
},
{
"epoch": 2.9,
"learning_rate": 5.573147902602549e-08,
"loss": 0.3927,
"step": 1039
},
{
"epoch": 2.9,
"learning_rate": 5.259507289199328e-08,
"loss": 0.379,
"step": 1040
},
{
"epoch": 2.9,
"learning_rate": 4.954926249317815e-08,
"loss": 0.4374,
"step": 1041
},
{
"epoch": 2.91,
"learning_rate": 4.6594075569219575e-08,
"loss": 0.4067,
"step": 1042
},
{
"epoch": 2.91,
"learning_rate": 4.3729539034408355e-08,
"loss": 0.3893,
"step": 1043
},
{
"epoch": 2.91,
"learning_rate": 4.0955678977436796e-08,
"loss": 0.4055,
"step": 1044
},
{
"epoch": 2.91,
"learning_rate": 3.827252066116338e-08,
"loss": 0.4079,
"step": 1045
},
{
"epoch": 2.92,
"learning_rate": 3.568008852238514e-08,
"loss": 0.3885,
"step": 1046
},
{
"epoch": 2.92,
"learning_rate": 3.3178406171608946e-08,
"loss": 0.4426,
"step": 1047
},
{
"epoch": 2.92,
"learning_rate": 3.076749639284504e-08,
"loss": 0.3987,
"step": 1048
},
{
"epoch": 2.93,
"learning_rate": 2.844738114339163e-08,
"loss": 0.4018,
"step": 1049
},
{
"epoch": 2.93,
"learning_rate": 2.6218081553638363e-08,
"loss": 0.3911,
"step": 1050
},
{
"epoch": 2.93,
"learning_rate": 2.407961792687541e-08,
"loss": 0.4227,
"step": 1051
},
{
"epoch": 2.93,
"learning_rate": 2.2032009739103577e-08,
"loss": 0.3986,
"step": 1052
},
{
"epoch": 2.94,
"learning_rate": 2.0075275638862247e-08,
"loss": 0.415,
"step": 1053
},
{
"epoch": 2.94,
"learning_rate": 1.820943344705728e-08,
"loss": 0.3952,
"step": 1054
},
{
"epoch": 2.94,
"learning_rate": 1.6434500156800037e-08,
"loss": 0.3876,
"step": 1055
},
{
"epoch": 2.95,
"learning_rate": 1.4750491933247513e-08,
"loss": 0.3978,
"step": 1056
},
{
"epoch": 2.95,
"learning_rate": 1.3157424113463547e-08,
"loss": 0.411,
"step": 1057
},
{
"epoch": 2.95,
"learning_rate": 1.165531120627117e-08,
"loss": 0.436,
"step": 1058
},
{
"epoch": 2.95,
"learning_rate": 1.0244166892124929e-08,
"loss": 0.4193,
"step": 1059
},
{
"epoch": 2.96,
"learning_rate": 8.924004022986543e-09,
"loss": 0.3964,
"step": 1060
},
{
"epoch": 2.96,
"learning_rate": 7.694834622204994e-09,
"loss": 0.4344,
"step": 1061
},
{
"epoch": 2.96,
"learning_rate": 6.556669884408839e-09,
"loss": 0.4167,
"step": 1062
},
{
"epoch": 2.97,
"learning_rate": 5.509520175404071e-09,
"loss": 0.3977,
"step": 1063
},
{
"epoch": 2.97,
"learning_rate": 4.553395032079744e-09,
"loss": 0.3681,
"step": 1064
},
{
"epoch": 2.97,
"learning_rate": 3.688303162322493e-09,
"loss": 0.4079,
"step": 1065
},
{
"epoch": 2.97,
"learning_rate": 2.914252444933263e-09,
"loss": 0.4088,
"step": 1066
},
{
"epoch": 2.98,
"learning_rate": 2.2312499295595867e-09,
"loss": 0.4361,
"step": 1067
},
{
"epoch": 2.98,
"learning_rate": 1.6393018366278601e-09,
"loss": 0.4206,
"step": 1068
},
{
"epoch": 2.98,
"learning_rate": 1.1384135572911625e-09,
"loss": 0.4276,
"step": 1069
},
{
"epoch": 2.98,
"learning_rate": 7.285896533770765e-10,
"loss": 0.3986,
"step": 1070
},
{
"epoch": 2.99,
"learning_rate": 4.0983385734660875e-10,
"loss": 0.3956,
"step": 1071
},
{
"epoch": 2.99,
"learning_rate": 1.8214907225866384e-10,
"loss": 0.405,
"step": 1072
},
{
"epoch": 2.99,
"learning_rate": 4.5537371746728897e-11,
"loss": 0.3887,
"step": 1073
},
{
"epoch": 3.0,
"learning_rate": 0.0,
"loss": 0.414,
"step": 1074
},
{
"epoch": 3.0,
"step": 1074,
"total_flos": 1.422863572320387e+18,
"train_loss": 0.42146639253951096,
"train_runtime": 10118.3229,
"train_samples_per_second": 13.587,
"train_steps_per_second": 0.106
}
],
"logging_steps": 1.0,
"max_steps": 1074,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 1.422863572320387e+18,
"trial_name": null,
"trial_params": null
}