MQ-Auditor / trainer_state.json
Jinxing1's picture
Upload MQ-Auditor HyperLoRA weights
3826697 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 93.65853658536585,
"eval_steps": 500,
"global_step": 960,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.1,
"learning_rate": 0.0,
"loss": 5.7387,
"step": 1
},
{
"epoch": 0.2,
"learning_rate": 2.0584683246043447e-05,
"loss": 4.0187,
"step": 2
},
{
"epoch": 0.29,
"learning_rate": 3.2625951034201905e-05,
"loss": 4.045,
"step": 3
},
{
"epoch": 0.39,
"learning_rate": 4.1169366492086894e-05,
"loss": 3.6343,
"step": 4
},
{
"epoch": 0.49,
"learning_rate": 4.779615435334546e-05,
"loss": 3.1875,
"step": 5
},
{
"epoch": 0.59,
"learning_rate": 5.321063428024535e-05,
"loss": 2.6217,
"step": 6
},
{
"epoch": 0.68,
"learning_rate": 5.778851182977677e-05,
"loss": 2.0794,
"step": 7
},
{
"epoch": 0.78,
"learning_rate": 6.175404973813034e-05,
"loss": 1.6396,
"step": 8
},
{
"epoch": 0.88,
"learning_rate": 6.525190206840381e-05,
"loss": 1.1893,
"step": 9
},
{
"epoch": 0.98,
"learning_rate": 6.838083759938891e-05,
"loss": 0.8686,
"step": 10
},
{
"epoch": 1.07,
"learning_rate": 7.121130408099613e-05,
"loss": 0.6397,
"step": 11
},
{
"epoch": 1.17,
"learning_rate": 7.37953175262888e-05,
"loss": 0.4766,
"step": 12
},
{
"epoch": 1.27,
"learning_rate": 7.617237946901266e-05,
"loss": 0.4133,
"step": 13
},
{
"epoch": 1.37,
"learning_rate": 7.83731950758202e-05,
"loss": 0.3119,
"step": 14
},
{
"epoch": 1.46,
"learning_rate": 8.042210538754737e-05,
"loss": 0.2391,
"step": 15
},
{
"epoch": 1.56,
"learning_rate": 8.233873298417379e-05,
"loss": 0.2145,
"step": 16
},
{
"epoch": 1.66,
"learning_rate": 8.4139127867111e-05,
"loss": 0.21,
"step": 17
},
{
"epoch": 1.76,
"learning_rate": 8.583658531444724e-05,
"loss": 0.1671,
"step": 18
},
{
"epoch": 1.85,
"learning_rate": 8.744224231638917e-05,
"loss": 0.1588,
"step": 19
},
{
"epoch": 1.95,
"learning_rate": 8.896552084543235e-05,
"loss": 0.1691,
"step": 20
},
{
"epoch": 2.05,
"learning_rate": 9.041446286397868e-05,
"loss": 0.1696,
"step": 21
},
{
"epoch": 2.15,
"learning_rate": 9.179598732703958e-05,
"loss": 0.1182,
"step": 22
},
{
"epoch": 2.24,
"learning_rate": 9.31160900092863e-05,
"loss": 0.1541,
"step": 23
},
{
"epoch": 2.34,
"learning_rate": 9.438000077233225e-05,
"loss": 0.1228,
"step": 24
},
{
"epoch": 2.44,
"learning_rate": 9.559230870669092e-05,
"loss": 0.1139,
"step": 25
},
{
"epoch": 2.54,
"learning_rate": 9.675706271505613e-05,
"loss": 0.1216,
"step": 26
},
{
"epoch": 2.63,
"learning_rate": 9.787785310260573e-05,
"loss": 0.1004,
"step": 27
},
{
"epoch": 2.73,
"learning_rate": 9.895787832186365e-05,
"loss": 0.1101,
"step": 28
},
{
"epoch": 2.83,
"learning_rate": 0.0001,
"loss": 0.1076,
"step": 29
},
{
"epoch": 2.93,
"learning_rate": 0.0001,
"loss": 0.1149,
"step": 30
},
{
"epoch": 3.02,
"learning_rate": 9.989258861439313e-05,
"loss": 0.1033,
"step": 31
},
{
"epoch": 3.12,
"learning_rate": 9.978517722878625e-05,
"loss": 0.0903,
"step": 32
},
{
"epoch": 3.22,
"learning_rate": 9.967776584317939e-05,
"loss": 0.096,
"step": 33
},
{
"epoch": 3.32,
"learning_rate": 9.957035445757252e-05,
"loss": 0.101,
"step": 34
},
{
"epoch": 3.41,
"learning_rate": 9.946294307196563e-05,
"loss": 0.0822,
"step": 35
},
{
"epoch": 3.51,
"learning_rate": 9.935553168635876e-05,
"loss": 0.0848,
"step": 36
},
{
"epoch": 3.61,
"learning_rate": 9.924812030075187e-05,
"loss": 0.1084,
"step": 37
},
{
"epoch": 3.71,
"learning_rate": 9.914070891514501e-05,
"loss": 0.0973,
"step": 38
},
{
"epoch": 3.8,
"learning_rate": 9.903329752953814e-05,
"loss": 0.086,
"step": 39
},
{
"epoch": 3.9,
"learning_rate": 9.892588614393126e-05,
"loss": 0.0918,
"step": 40
},
{
"epoch": 4.0,
"learning_rate": 9.881847475832438e-05,
"loss": 0.0808,
"step": 41
},
{
"epoch": 4.1,
"learning_rate": 9.871106337271751e-05,
"loss": 0.0971,
"step": 42
},
{
"epoch": 4.2,
"learning_rate": 9.860365198711064e-05,
"loss": 0.0795,
"step": 43
},
{
"epoch": 4.29,
"learning_rate": 9.849624060150377e-05,
"loss": 0.0692,
"step": 44
},
{
"epoch": 4.39,
"learning_rate": 9.83888292158969e-05,
"loss": 0.1077,
"step": 45
},
{
"epoch": 4.49,
"learning_rate": 9.828141783029001e-05,
"loss": 0.0665,
"step": 46
},
{
"epoch": 4.59,
"learning_rate": 9.817400644468314e-05,
"loss": 0.0764,
"step": 47
},
{
"epoch": 4.68,
"learning_rate": 9.806659505907627e-05,
"loss": 0.0931,
"step": 48
},
{
"epoch": 4.78,
"learning_rate": 9.79591836734694e-05,
"loss": 0.0748,
"step": 49
},
{
"epoch": 4.88,
"learning_rate": 9.785177228786252e-05,
"loss": 0.101,
"step": 50
},
{
"epoch": 4.98,
"learning_rate": 9.774436090225564e-05,
"loss": 0.0864,
"step": 51
},
{
"epoch": 5.07,
"learning_rate": 9.763694951664876e-05,
"loss": 0.0677,
"step": 52
},
{
"epoch": 5.17,
"learning_rate": 9.752953813104189e-05,
"loss": 0.0778,
"step": 53
},
{
"epoch": 5.27,
"learning_rate": 9.742212674543502e-05,
"loss": 0.0889,
"step": 54
},
{
"epoch": 5.37,
"learning_rate": 9.731471535982815e-05,
"loss": 0.0863,
"step": 55
},
{
"epoch": 5.46,
"learning_rate": 9.720730397422128e-05,
"loss": 0.0785,
"step": 56
},
{
"epoch": 5.56,
"learning_rate": 9.709989258861439e-05,
"loss": 0.0798,
"step": 57
},
{
"epoch": 5.66,
"learning_rate": 9.699248120300752e-05,
"loss": 0.0903,
"step": 58
},
{
"epoch": 5.76,
"learning_rate": 9.688506981740066e-05,
"loss": 0.0952,
"step": 59
},
{
"epoch": 5.85,
"learning_rate": 9.677765843179377e-05,
"loss": 0.0752,
"step": 60
},
{
"epoch": 5.95,
"learning_rate": 9.66702470461869e-05,
"loss": 0.0771,
"step": 61
},
{
"epoch": 6.05,
"learning_rate": 9.656283566058003e-05,
"loss": 0.0894,
"step": 62
},
{
"epoch": 6.15,
"learning_rate": 9.645542427497314e-05,
"loss": 0.0813,
"step": 63
},
{
"epoch": 6.24,
"learning_rate": 9.634801288936628e-05,
"loss": 0.0728,
"step": 64
},
{
"epoch": 6.34,
"learning_rate": 9.62406015037594e-05,
"loss": 0.0781,
"step": 65
},
{
"epoch": 6.44,
"learning_rate": 9.613319011815253e-05,
"loss": 0.0678,
"step": 66
},
{
"epoch": 6.54,
"learning_rate": 9.602577873254565e-05,
"loss": 0.0622,
"step": 67
},
{
"epoch": 6.63,
"learning_rate": 9.591836734693878e-05,
"loss": 0.0555,
"step": 68
},
{
"epoch": 6.73,
"learning_rate": 9.581095596133191e-05,
"loss": 0.0679,
"step": 69
},
{
"epoch": 6.83,
"learning_rate": 9.570354457572504e-05,
"loss": 0.0733,
"step": 70
},
{
"epoch": 6.93,
"learning_rate": 9.559613319011815e-05,
"loss": 0.0751,
"step": 71
},
{
"epoch": 7.02,
"learning_rate": 9.548872180451128e-05,
"loss": 0.0662,
"step": 72
},
{
"epoch": 7.12,
"learning_rate": 9.538131041890441e-05,
"loss": 0.0794,
"step": 73
},
{
"epoch": 7.22,
"learning_rate": 9.527389903329754e-05,
"loss": 0.0773,
"step": 74
},
{
"epoch": 7.32,
"learning_rate": 9.516648764769066e-05,
"loss": 0.0645,
"step": 75
},
{
"epoch": 7.41,
"learning_rate": 9.505907626208379e-05,
"loss": 0.0715,
"step": 76
},
{
"epoch": 7.51,
"learning_rate": 9.49516648764769e-05,
"loss": 0.0747,
"step": 77
},
{
"epoch": 7.61,
"learning_rate": 9.484425349087003e-05,
"loss": 0.0771,
"step": 78
},
{
"epoch": 7.71,
"learning_rate": 9.473684210526316e-05,
"loss": 0.0693,
"step": 79
},
{
"epoch": 7.8,
"learning_rate": 9.462943071965629e-05,
"loss": 0.0747,
"step": 80
},
{
"epoch": 7.9,
"learning_rate": 9.452201933404942e-05,
"loss": 0.0717,
"step": 81
},
{
"epoch": 8.0,
"learning_rate": 9.441460794844253e-05,
"loss": 0.0671,
"step": 82
},
{
"epoch": 8.1,
"learning_rate": 9.430719656283566e-05,
"loss": 0.0614,
"step": 83
},
{
"epoch": 8.2,
"learning_rate": 9.419978517722879e-05,
"loss": 0.071,
"step": 84
},
{
"epoch": 8.29,
"learning_rate": 9.409237379162192e-05,
"loss": 0.0845,
"step": 85
},
{
"epoch": 8.39,
"learning_rate": 9.398496240601504e-05,
"loss": 0.0674,
"step": 86
},
{
"epoch": 8.49,
"learning_rate": 9.387755102040817e-05,
"loss": 0.0674,
"step": 87
},
{
"epoch": 8.59,
"learning_rate": 9.377013963480129e-05,
"loss": 0.0656,
"step": 88
},
{
"epoch": 8.68,
"learning_rate": 9.366272824919443e-05,
"loss": 0.0772,
"step": 89
},
{
"epoch": 8.78,
"learning_rate": 9.355531686358755e-05,
"loss": 0.07,
"step": 90
},
{
"epoch": 8.88,
"learning_rate": 9.344790547798067e-05,
"loss": 0.0681,
"step": 91
},
{
"epoch": 8.98,
"learning_rate": 9.33404940923738e-05,
"loss": 0.0753,
"step": 92
},
{
"epoch": 9.07,
"learning_rate": 9.323308270676691e-05,
"loss": 0.0565,
"step": 93
},
{
"epoch": 9.17,
"learning_rate": 9.312567132116005e-05,
"loss": 0.0698,
"step": 94
},
{
"epoch": 9.27,
"learning_rate": 9.301825993555318e-05,
"loss": 0.0725,
"step": 95
},
{
"epoch": 9.37,
"learning_rate": 9.29108485499463e-05,
"loss": 0.066,
"step": 96
},
{
"epoch": 9.46,
"learning_rate": 9.280343716433942e-05,
"loss": 0.055,
"step": 97
},
{
"epoch": 9.56,
"learning_rate": 9.269602577873255e-05,
"loss": 0.0762,
"step": 98
},
{
"epoch": 9.66,
"learning_rate": 9.258861439312568e-05,
"loss": 0.066,
"step": 99
},
{
"epoch": 9.76,
"learning_rate": 9.24812030075188e-05,
"loss": 0.0717,
"step": 100
},
{
"epoch": 9.85,
"learning_rate": 9.237379162191193e-05,
"loss": 0.0763,
"step": 101
},
{
"epoch": 9.95,
"learning_rate": 9.226638023630505e-05,
"loss": 0.0712,
"step": 102
},
{
"epoch": 10.05,
"learning_rate": 9.215896885069818e-05,
"loss": 0.0722,
"step": 103
},
{
"epoch": 10.15,
"learning_rate": 9.20515574650913e-05,
"loss": 0.0659,
"step": 104
},
{
"epoch": 10.24,
"learning_rate": 9.194414607948443e-05,
"loss": 0.056,
"step": 105
},
{
"epoch": 10.34,
"learning_rate": 9.183673469387756e-05,
"loss": 0.0733,
"step": 106
},
{
"epoch": 10.44,
"learning_rate": 9.172932330827067e-05,
"loss": 0.0565,
"step": 107
},
{
"epoch": 10.54,
"learning_rate": 9.16219119226638e-05,
"loss": 0.0887,
"step": 108
},
{
"epoch": 10.63,
"learning_rate": 9.151450053705693e-05,
"loss": 0.0832,
"step": 109
},
{
"epoch": 10.73,
"learning_rate": 9.140708915145006e-05,
"loss": 0.0679,
"step": 110
},
{
"epoch": 10.83,
"learning_rate": 9.129967776584319e-05,
"loss": 0.0649,
"step": 111
},
{
"epoch": 10.93,
"learning_rate": 9.119226638023631e-05,
"loss": 0.0765,
"step": 112
},
{
"epoch": 11.02,
"learning_rate": 9.108485499462943e-05,
"loss": 0.0687,
"step": 113
},
{
"epoch": 11.12,
"learning_rate": 9.097744360902256e-05,
"loss": 0.0723,
"step": 114
},
{
"epoch": 11.22,
"learning_rate": 9.08700322234157e-05,
"loss": 0.064,
"step": 115
},
{
"epoch": 11.32,
"learning_rate": 9.076262083780881e-05,
"loss": 0.073,
"step": 116
},
{
"epoch": 11.41,
"learning_rate": 9.065520945220194e-05,
"loss": 0.0669,
"step": 117
},
{
"epoch": 11.51,
"learning_rate": 9.054779806659507e-05,
"loss": 0.066,
"step": 118
},
{
"epoch": 11.61,
"learning_rate": 9.044038668098818e-05,
"loss": 0.0754,
"step": 119
},
{
"epoch": 11.71,
"learning_rate": 9.033297529538132e-05,
"loss": 0.0532,
"step": 120
},
{
"epoch": 11.8,
"learning_rate": 9.022556390977444e-05,
"loss": 0.0702,
"step": 121
},
{
"epoch": 11.9,
"learning_rate": 9.011815252416757e-05,
"loss": 0.057,
"step": 122
},
{
"epoch": 12.0,
"learning_rate": 9.001074113856069e-05,
"loss": 0.0764,
"step": 123
},
{
"epoch": 12.1,
"learning_rate": 8.990332975295381e-05,
"loss": 0.0605,
"step": 124
},
{
"epoch": 12.2,
"learning_rate": 8.979591836734695e-05,
"loss": 0.0538,
"step": 125
},
{
"epoch": 12.29,
"learning_rate": 8.968850698174008e-05,
"loss": 0.0512,
"step": 126
},
{
"epoch": 12.39,
"learning_rate": 8.958109559613319e-05,
"loss": 0.045,
"step": 127
},
{
"epoch": 12.49,
"learning_rate": 8.947368421052632e-05,
"loss": 0.0633,
"step": 128
},
{
"epoch": 12.59,
"learning_rate": 8.936627282491945e-05,
"loss": 0.059,
"step": 129
},
{
"epoch": 12.68,
"learning_rate": 8.925886143931257e-05,
"loss": 0.0702,
"step": 130
},
{
"epoch": 12.78,
"learning_rate": 8.91514500537057e-05,
"loss": 0.0727,
"step": 131
},
{
"epoch": 12.88,
"learning_rate": 8.904403866809883e-05,
"loss": 0.0748,
"step": 132
},
{
"epoch": 12.98,
"learning_rate": 8.893662728249194e-05,
"loss": 0.0552,
"step": 133
},
{
"epoch": 13.07,
"learning_rate": 8.882921589688507e-05,
"loss": 0.0665,
"step": 134
},
{
"epoch": 13.17,
"learning_rate": 8.87218045112782e-05,
"loss": 0.063,
"step": 135
},
{
"epoch": 13.27,
"learning_rate": 8.861439312567133e-05,
"loss": 0.0663,
"step": 136
},
{
"epoch": 13.37,
"learning_rate": 8.850698174006446e-05,
"loss": 0.0529,
"step": 137
},
{
"epoch": 13.46,
"learning_rate": 8.839957035445757e-05,
"loss": 0.0591,
"step": 138
},
{
"epoch": 13.56,
"learning_rate": 8.82921589688507e-05,
"loss": 0.0605,
"step": 139
},
{
"epoch": 13.66,
"learning_rate": 8.818474758324383e-05,
"loss": 0.0641,
"step": 140
},
{
"epoch": 13.76,
"learning_rate": 8.807733619763695e-05,
"loss": 0.0731,
"step": 141
},
{
"epoch": 13.85,
"learning_rate": 8.796992481203008e-05,
"loss": 0.0603,
"step": 142
},
{
"epoch": 13.95,
"learning_rate": 8.786251342642321e-05,
"loss": 0.0764,
"step": 143
},
{
"epoch": 14.05,
"learning_rate": 8.775510204081632e-05,
"loss": 0.0587,
"step": 144
},
{
"epoch": 14.15,
"learning_rate": 8.764769065520945e-05,
"loss": 0.053,
"step": 145
},
{
"epoch": 14.24,
"learning_rate": 8.754027926960259e-05,
"loss": 0.058,
"step": 146
},
{
"epoch": 14.34,
"learning_rate": 8.743286788399571e-05,
"loss": 0.0825,
"step": 147
},
{
"epoch": 14.44,
"learning_rate": 8.732545649838884e-05,
"loss": 0.065,
"step": 148
},
{
"epoch": 14.54,
"learning_rate": 8.721804511278195e-05,
"loss": 0.0616,
"step": 149
},
{
"epoch": 14.63,
"learning_rate": 8.711063372717508e-05,
"loss": 0.0607,
"step": 150
},
{
"epoch": 14.73,
"learning_rate": 8.700322234156822e-05,
"loss": 0.0683,
"step": 151
},
{
"epoch": 14.83,
"learning_rate": 8.689581095596133e-05,
"loss": 0.0598,
"step": 152
},
{
"epoch": 14.93,
"learning_rate": 8.678839957035446e-05,
"loss": 0.0703,
"step": 153
},
{
"epoch": 15.02,
"learning_rate": 8.668098818474759e-05,
"loss": 0.0613,
"step": 154
},
{
"epoch": 15.12,
"learning_rate": 8.65735767991407e-05,
"loss": 0.0646,
"step": 155
},
{
"epoch": 15.22,
"learning_rate": 8.646616541353384e-05,
"loss": 0.0597,
"step": 156
},
{
"epoch": 15.32,
"learning_rate": 8.635875402792697e-05,
"loss": 0.0693,
"step": 157
},
{
"epoch": 15.41,
"learning_rate": 8.625134264232009e-05,
"loss": 0.0662,
"step": 158
},
{
"epoch": 15.51,
"learning_rate": 8.614393125671321e-05,
"loss": 0.0692,
"step": 159
},
{
"epoch": 15.61,
"learning_rate": 8.603651987110634e-05,
"loss": 0.056,
"step": 160
},
{
"epoch": 15.71,
"learning_rate": 8.592910848549947e-05,
"loss": 0.0684,
"step": 161
},
{
"epoch": 15.8,
"learning_rate": 8.58216970998926e-05,
"loss": 0.0637,
"step": 162
},
{
"epoch": 15.9,
"learning_rate": 8.571428571428571e-05,
"loss": 0.0653,
"step": 163
},
{
"epoch": 16.0,
"learning_rate": 8.560687432867884e-05,
"loss": 0.061,
"step": 164
},
{
"epoch": 16.1,
"learning_rate": 8.549946294307197e-05,
"loss": 0.051,
"step": 165
},
{
"epoch": 16.2,
"learning_rate": 8.53920515574651e-05,
"loss": 0.0714,
"step": 166
},
{
"epoch": 16.29,
"learning_rate": 8.528464017185822e-05,
"loss": 0.0542,
"step": 167
},
{
"epoch": 16.39,
"learning_rate": 8.517722878625135e-05,
"loss": 0.0714,
"step": 168
},
{
"epoch": 16.49,
"learning_rate": 8.506981740064447e-05,
"loss": 0.0686,
"step": 169
},
{
"epoch": 16.59,
"learning_rate": 8.49624060150376e-05,
"loss": 0.0638,
"step": 170
},
{
"epoch": 16.68,
"learning_rate": 8.485499462943072e-05,
"loss": 0.0697,
"step": 171
},
{
"epoch": 16.78,
"learning_rate": 8.474758324382385e-05,
"loss": 0.0502,
"step": 172
},
{
"epoch": 16.88,
"learning_rate": 8.464017185821698e-05,
"loss": 0.0654,
"step": 173
},
{
"epoch": 16.98,
"learning_rate": 8.453276047261009e-05,
"loss": 0.0518,
"step": 174
},
{
"epoch": 17.07,
"learning_rate": 8.442534908700322e-05,
"loss": 0.0748,
"step": 175
},
{
"epoch": 17.17,
"learning_rate": 8.431793770139636e-05,
"loss": 0.0522,
"step": 176
},
{
"epoch": 17.27,
"learning_rate": 8.421052631578948e-05,
"loss": 0.0562,
"step": 177
},
{
"epoch": 17.37,
"learning_rate": 8.41031149301826e-05,
"loss": 0.0613,
"step": 178
},
{
"epoch": 17.46,
"learning_rate": 8.399570354457573e-05,
"loss": 0.0661,
"step": 179
},
{
"epoch": 17.56,
"learning_rate": 8.388829215896885e-05,
"loss": 0.0638,
"step": 180
},
{
"epoch": 17.66,
"learning_rate": 8.378088077336199e-05,
"loss": 0.0597,
"step": 181
},
{
"epoch": 17.76,
"learning_rate": 8.367346938775511e-05,
"loss": 0.0546,
"step": 182
},
{
"epoch": 17.85,
"learning_rate": 8.356605800214823e-05,
"loss": 0.0514,
"step": 183
},
{
"epoch": 17.95,
"learning_rate": 8.345864661654136e-05,
"loss": 0.0663,
"step": 184
},
{
"epoch": 18.05,
"learning_rate": 8.335123523093448e-05,
"loss": 0.0607,
"step": 185
},
{
"epoch": 18.15,
"learning_rate": 8.324382384532761e-05,
"loss": 0.0697,
"step": 186
},
{
"epoch": 18.24,
"learning_rate": 8.313641245972074e-05,
"loss": 0.0517,
"step": 187
},
{
"epoch": 18.34,
"learning_rate": 8.302900107411385e-05,
"loss": 0.0647,
"step": 188
},
{
"epoch": 18.44,
"learning_rate": 8.292158968850698e-05,
"loss": 0.0311,
"step": 189
},
{
"epoch": 18.54,
"learning_rate": 8.281417830290011e-05,
"loss": 0.0663,
"step": 190
},
{
"epoch": 18.63,
"learning_rate": 8.270676691729324e-05,
"loss": 0.0403,
"step": 191
},
{
"epoch": 18.73,
"learning_rate": 8.259935553168637e-05,
"loss": 0.0469,
"step": 192
},
{
"epoch": 18.83,
"learning_rate": 8.24919441460795e-05,
"loss": 0.0763,
"step": 193
},
{
"epoch": 18.93,
"learning_rate": 8.238453276047261e-05,
"loss": 0.0477,
"step": 194
},
{
"epoch": 19.02,
"learning_rate": 8.227712137486574e-05,
"loss": 0.0817,
"step": 195
},
{
"epoch": 19.12,
"learning_rate": 8.216970998925886e-05,
"loss": 0.051,
"step": 196
},
{
"epoch": 19.22,
"learning_rate": 8.206229860365199e-05,
"loss": 0.068,
"step": 197
},
{
"epoch": 19.32,
"learning_rate": 8.195488721804512e-05,
"loss": 0.0642,
"step": 198
},
{
"epoch": 19.41,
"learning_rate": 8.184747583243825e-05,
"loss": 0.0634,
"step": 199
},
{
"epoch": 19.51,
"learning_rate": 8.174006444683136e-05,
"loss": 0.0676,
"step": 200
},
{
"epoch": 19.61,
"learning_rate": 8.163265306122449e-05,
"loss": 0.0486,
"step": 201
},
{
"epoch": 19.71,
"learning_rate": 8.152524167561762e-05,
"loss": 0.0468,
"step": 202
},
{
"epoch": 19.8,
"learning_rate": 8.141783029001075e-05,
"loss": 0.0467,
"step": 203
},
{
"epoch": 19.9,
"learning_rate": 8.131041890440387e-05,
"loss": 0.0584,
"step": 204
},
{
"epoch": 20.0,
"learning_rate": 8.120300751879699e-05,
"loss": 0.0568,
"step": 205
},
{
"epoch": 20.1,
"learning_rate": 8.109559613319012e-05,
"loss": 0.0606,
"step": 206
},
{
"epoch": 20.2,
"learning_rate": 8.098818474758326e-05,
"loss": 0.0687,
"step": 207
},
{
"epoch": 20.29,
"learning_rate": 8.088077336197637e-05,
"loss": 0.0617,
"step": 208
},
{
"epoch": 20.39,
"learning_rate": 8.07733619763695e-05,
"loss": 0.0584,
"step": 209
},
{
"epoch": 20.49,
"learning_rate": 8.066595059076263e-05,
"loss": 0.0529,
"step": 210
},
{
"epoch": 20.59,
"learning_rate": 8.055853920515574e-05,
"loss": 0.0632,
"step": 211
},
{
"epoch": 20.68,
"learning_rate": 8.045112781954888e-05,
"loss": 0.0536,
"step": 212
},
{
"epoch": 20.78,
"learning_rate": 8.034371643394201e-05,
"loss": 0.0517,
"step": 213
},
{
"epoch": 20.88,
"learning_rate": 8.023630504833513e-05,
"loss": 0.0536,
"step": 214
},
{
"epoch": 20.98,
"learning_rate": 8.012889366272825e-05,
"loss": 0.0659,
"step": 215
},
{
"epoch": 21.07,
"learning_rate": 8.002148227712137e-05,
"loss": 0.0589,
"step": 216
},
{
"epoch": 21.17,
"learning_rate": 7.991407089151451e-05,
"loss": 0.0494,
"step": 217
},
{
"epoch": 21.27,
"learning_rate": 7.980665950590764e-05,
"loss": 0.0522,
"step": 218
},
{
"epoch": 21.37,
"learning_rate": 7.969924812030075e-05,
"loss": 0.0489,
"step": 219
},
{
"epoch": 21.46,
"learning_rate": 7.959183673469388e-05,
"loss": 0.0495,
"step": 220
},
{
"epoch": 21.56,
"learning_rate": 7.9484425349087e-05,
"loss": 0.0654,
"step": 221
},
{
"epoch": 21.66,
"learning_rate": 7.937701396348013e-05,
"loss": 0.0598,
"step": 222
},
{
"epoch": 21.76,
"learning_rate": 7.926960257787326e-05,
"loss": 0.0649,
"step": 223
},
{
"epoch": 21.85,
"learning_rate": 7.916219119226639e-05,
"loss": 0.0529,
"step": 224
},
{
"epoch": 21.95,
"learning_rate": 7.90547798066595e-05,
"loss": 0.0625,
"step": 225
},
{
"epoch": 22.05,
"learning_rate": 7.894736842105263e-05,
"loss": 0.0595,
"step": 226
},
{
"epoch": 22.15,
"learning_rate": 7.883995703544576e-05,
"loss": 0.0617,
"step": 227
},
{
"epoch": 22.24,
"learning_rate": 7.873254564983889e-05,
"loss": 0.0672,
"step": 228
},
{
"epoch": 22.34,
"learning_rate": 7.862513426423202e-05,
"loss": 0.0604,
"step": 229
},
{
"epoch": 22.44,
"learning_rate": 7.851772287862513e-05,
"loss": 0.0619,
"step": 230
},
{
"epoch": 22.54,
"learning_rate": 7.841031149301826e-05,
"loss": 0.0518,
"step": 231
},
{
"epoch": 22.63,
"learning_rate": 7.830290010741139e-05,
"loss": 0.0559,
"step": 232
},
{
"epoch": 22.73,
"learning_rate": 7.819548872180451e-05,
"loss": 0.0585,
"step": 233
},
{
"epoch": 22.83,
"learning_rate": 7.808807733619764e-05,
"loss": 0.0476,
"step": 234
},
{
"epoch": 22.93,
"learning_rate": 7.798066595059077e-05,
"loss": 0.0712,
"step": 235
},
{
"epoch": 23.02,
"learning_rate": 7.787325456498388e-05,
"loss": 0.0556,
"step": 236
},
{
"epoch": 23.12,
"learning_rate": 7.776584317937701e-05,
"loss": 0.0608,
"step": 237
},
{
"epoch": 23.22,
"learning_rate": 7.765843179377015e-05,
"loss": 0.0427,
"step": 238
},
{
"epoch": 23.32,
"learning_rate": 7.755102040816327e-05,
"loss": 0.0546,
"step": 239
},
{
"epoch": 23.41,
"learning_rate": 7.74436090225564e-05,
"loss": 0.0571,
"step": 240
},
{
"epoch": 23.51,
"learning_rate": 7.733619763694952e-05,
"loss": 0.0733,
"step": 241
},
{
"epoch": 23.61,
"learning_rate": 7.722878625134264e-05,
"loss": 0.0544,
"step": 242
},
{
"epoch": 23.71,
"learning_rate": 7.712137486573578e-05,
"loss": 0.0589,
"step": 243
},
{
"epoch": 23.8,
"learning_rate": 7.70139634801289e-05,
"loss": 0.0642,
"step": 244
},
{
"epoch": 23.9,
"learning_rate": 7.690655209452202e-05,
"loss": 0.0529,
"step": 245
},
{
"epoch": 24.0,
"learning_rate": 7.679914070891515e-05,
"loss": 0.0511,
"step": 246
},
{
"epoch": 24.1,
"learning_rate": 7.669172932330826e-05,
"loss": 0.0454,
"step": 247
},
{
"epoch": 24.2,
"learning_rate": 7.65843179377014e-05,
"loss": 0.0461,
"step": 248
},
{
"epoch": 24.29,
"learning_rate": 7.647690655209453e-05,
"loss": 0.0588,
"step": 249
},
{
"epoch": 24.39,
"learning_rate": 7.636949516648765e-05,
"loss": 0.0617,
"step": 250
},
{
"epoch": 24.49,
"learning_rate": 7.626208378088077e-05,
"loss": 0.0539,
"step": 251
},
{
"epoch": 24.59,
"learning_rate": 7.61546723952739e-05,
"loss": 0.048,
"step": 252
},
{
"epoch": 24.68,
"learning_rate": 7.604726100966703e-05,
"loss": 0.065,
"step": 253
},
{
"epoch": 24.78,
"learning_rate": 7.593984962406016e-05,
"loss": 0.0659,
"step": 254
},
{
"epoch": 24.88,
"learning_rate": 7.583243823845329e-05,
"loss": 0.0449,
"step": 255
},
{
"epoch": 24.98,
"learning_rate": 7.57250268528464e-05,
"loss": 0.0441,
"step": 256
},
{
"epoch": 25.07,
"learning_rate": 7.561761546723953e-05,
"loss": 0.0521,
"step": 257
},
{
"epoch": 25.17,
"learning_rate": 7.551020408163266e-05,
"loss": 0.0592,
"step": 258
},
{
"epoch": 25.27,
"learning_rate": 7.540279269602578e-05,
"loss": 0.0594,
"step": 259
},
{
"epoch": 25.37,
"learning_rate": 7.529538131041891e-05,
"loss": 0.0559,
"step": 260
},
{
"epoch": 25.46,
"learning_rate": 7.518796992481203e-05,
"loss": 0.0648,
"step": 261
},
{
"epoch": 25.56,
"learning_rate": 7.508055853920515e-05,
"loss": 0.0618,
"step": 262
},
{
"epoch": 25.66,
"learning_rate": 7.497314715359828e-05,
"loss": 0.061,
"step": 263
},
{
"epoch": 25.76,
"learning_rate": 7.486573576799141e-05,
"loss": 0.05,
"step": 264
},
{
"epoch": 25.85,
"learning_rate": 7.475832438238454e-05,
"loss": 0.0734,
"step": 265
},
{
"epoch": 25.95,
"learning_rate": 7.465091299677767e-05,
"loss": 0.0631,
"step": 266
},
{
"epoch": 26.05,
"learning_rate": 7.454350161117078e-05,
"loss": 0.0633,
"step": 267
},
{
"epoch": 26.15,
"learning_rate": 7.443609022556392e-05,
"loss": 0.0605,
"step": 268
},
{
"epoch": 26.24,
"learning_rate": 7.432867883995705e-05,
"loss": 0.0456,
"step": 269
},
{
"epoch": 26.34,
"learning_rate": 7.422126745435016e-05,
"loss": 0.0498,
"step": 270
},
{
"epoch": 26.44,
"learning_rate": 7.411385606874329e-05,
"loss": 0.0554,
"step": 271
},
{
"epoch": 26.54,
"learning_rate": 7.40064446831364e-05,
"loss": 0.0613,
"step": 272
},
{
"epoch": 26.63,
"learning_rate": 7.389903329752955e-05,
"loss": 0.0656,
"step": 273
},
{
"epoch": 26.73,
"learning_rate": 7.379162191192268e-05,
"loss": 0.05,
"step": 274
},
{
"epoch": 26.83,
"learning_rate": 7.368421052631579e-05,
"loss": 0.0571,
"step": 275
},
{
"epoch": 26.93,
"learning_rate": 7.357679914070892e-05,
"loss": 0.0604,
"step": 276
},
{
"epoch": 27.02,
"learning_rate": 7.346938775510205e-05,
"loss": 0.051,
"step": 277
},
{
"epoch": 27.12,
"learning_rate": 7.336197636949517e-05,
"loss": 0.0525,
"step": 278
},
{
"epoch": 27.22,
"learning_rate": 7.32545649838883e-05,
"loss": 0.0633,
"step": 279
},
{
"epoch": 27.32,
"learning_rate": 7.314715359828143e-05,
"loss": 0.0535,
"step": 280
},
{
"epoch": 27.41,
"learning_rate": 7.303974221267454e-05,
"loss": 0.0644,
"step": 281
},
{
"epoch": 27.51,
"learning_rate": 7.293233082706767e-05,
"loss": 0.0616,
"step": 282
},
{
"epoch": 27.61,
"learning_rate": 7.28249194414608e-05,
"loss": 0.0485,
"step": 283
},
{
"epoch": 27.71,
"learning_rate": 7.271750805585393e-05,
"loss": 0.0536,
"step": 284
},
{
"epoch": 27.8,
"learning_rate": 7.261009667024705e-05,
"loss": 0.0652,
"step": 285
},
{
"epoch": 27.9,
"learning_rate": 7.250268528464017e-05,
"loss": 0.0502,
"step": 286
},
{
"epoch": 28.0,
"learning_rate": 7.23952738990333e-05,
"loss": 0.0509,
"step": 287
},
{
"epoch": 28.1,
"learning_rate": 7.228786251342642e-05,
"loss": 0.0565,
"step": 288
},
{
"epoch": 28.2,
"learning_rate": 7.218045112781955e-05,
"loss": 0.0547,
"step": 289
},
{
"epoch": 28.29,
"learning_rate": 7.207303974221268e-05,
"loss": 0.0645,
"step": 290
},
{
"epoch": 28.39,
"learning_rate": 7.196562835660581e-05,
"loss": 0.0561,
"step": 291
},
{
"epoch": 28.49,
"learning_rate": 7.185821697099892e-05,
"loss": 0.051,
"step": 292
},
{
"epoch": 28.59,
"learning_rate": 7.175080558539205e-05,
"loss": 0.0582,
"step": 293
},
{
"epoch": 28.68,
"learning_rate": 7.164339419978519e-05,
"loss": 0.044,
"step": 294
},
{
"epoch": 28.78,
"learning_rate": 7.15359828141783e-05,
"loss": 0.0638,
"step": 295
},
{
"epoch": 28.88,
"learning_rate": 7.142857142857143e-05,
"loss": 0.0492,
"step": 296
},
{
"epoch": 28.98,
"learning_rate": 7.132116004296455e-05,
"loss": 0.0651,
"step": 297
},
{
"epoch": 29.07,
"learning_rate": 7.121374865735768e-05,
"loss": 0.0483,
"step": 298
},
{
"epoch": 29.17,
"learning_rate": 7.110633727175082e-05,
"loss": 0.0478,
"step": 299
},
{
"epoch": 29.27,
"learning_rate": 7.099892588614393e-05,
"loss": 0.0657,
"step": 300
},
{
"epoch": 29.37,
"learning_rate": 7.089151450053706e-05,
"loss": 0.0547,
"step": 301
},
{
"epoch": 29.46,
"learning_rate": 7.078410311493019e-05,
"loss": 0.0448,
"step": 302
},
{
"epoch": 29.56,
"learning_rate": 7.06766917293233e-05,
"loss": 0.0515,
"step": 303
},
{
"epoch": 29.66,
"learning_rate": 7.056928034371644e-05,
"loss": 0.0548,
"step": 304
},
{
"epoch": 29.76,
"learning_rate": 7.046186895810957e-05,
"loss": 0.0612,
"step": 305
},
{
"epoch": 29.85,
"learning_rate": 7.035445757250269e-05,
"loss": 0.0475,
"step": 306
},
{
"epoch": 29.95,
"learning_rate": 7.024704618689581e-05,
"loss": 0.0583,
"step": 307
},
{
"epoch": 30.05,
"learning_rate": 7.013963480128894e-05,
"loss": 0.0627,
"step": 308
},
{
"epoch": 30.15,
"learning_rate": 7.003222341568207e-05,
"loss": 0.0476,
"step": 309
},
{
"epoch": 30.24,
"learning_rate": 6.99248120300752e-05,
"loss": 0.0491,
"step": 310
},
{
"epoch": 30.34,
"learning_rate": 6.981740064446831e-05,
"loss": 0.0438,
"step": 311
},
{
"epoch": 30.44,
"learning_rate": 6.970998925886144e-05,
"loss": 0.0564,
"step": 312
},
{
"epoch": 30.54,
"learning_rate": 6.960257787325457e-05,
"loss": 0.044,
"step": 313
},
{
"epoch": 30.63,
"learning_rate": 6.94951664876477e-05,
"loss": 0.0601,
"step": 314
},
{
"epoch": 30.73,
"learning_rate": 6.938775510204082e-05,
"loss": 0.0541,
"step": 315
},
{
"epoch": 30.83,
"learning_rate": 6.928034371643395e-05,
"loss": 0.0489,
"step": 316
},
{
"epoch": 30.93,
"learning_rate": 6.917293233082706e-05,
"loss": 0.0618,
"step": 317
},
{
"epoch": 31.02,
"learning_rate": 6.906552094522019e-05,
"loss": 0.0489,
"step": 318
},
{
"epoch": 31.12,
"learning_rate": 6.895810955961332e-05,
"loss": 0.0448,
"step": 319
},
{
"epoch": 31.22,
"learning_rate": 6.885069817400645e-05,
"loss": 0.0548,
"step": 320
},
{
"epoch": 31.32,
"learning_rate": 6.874328678839958e-05,
"loss": 0.0514,
"step": 321
},
{
"epoch": 31.41,
"learning_rate": 6.86358754027927e-05,
"loss": 0.0448,
"step": 322
},
{
"epoch": 31.51,
"learning_rate": 6.852846401718582e-05,
"loss": 0.0579,
"step": 323
},
{
"epoch": 31.61,
"learning_rate": 6.842105263157895e-05,
"loss": 0.0488,
"step": 324
},
{
"epoch": 31.71,
"learning_rate": 6.831364124597207e-05,
"loss": 0.0543,
"step": 325
},
{
"epoch": 31.8,
"learning_rate": 6.82062298603652e-05,
"loss": 0.0666,
"step": 326
},
{
"epoch": 31.9,
"learning_rate": 6.809881847475833e-05,
"loss": 0.0534,
"step": 327
},
{
"epoch": 32.0,
"learning_rate": 6.799140708915144e-05,
"loss": 0.0501,
"step": 328
},
{
"epoch": 32.1,
"learning_rate": 6.788399570354457e-05,
"loss": 0.0472,
"step": 329
},
{
"epoch": 32.2,
"learning_rate": 6.777658431793771e-05,
"loss": 0.0506,
"step": 330
},
{
"epoch": 32.29,
"learning_rate": 6.766917293233083e-05,
"loss": 0.0486,
"step": 331
},
{
"epoch": 32.39,
"learning_rate": 6.756176154672396e-05,
"loss": 0.0576,
"step": 332
},
{
"epoch": 32.49,
"learning_rate": 6.745435016111708e-05,
"loss": 0.0497,
"step": 333
},
{
"epoch": 32.59,
"learning_rate": 6.73469387755102e-05,
"loss": 0.0542,
"step": 334
},
{
"epoch": 32.68,
"learning_rate": 6.723952738990334e-05,
"loss": 0.0522,
"step": 335
},
{
"epoch": 32.78,
"learning_rate": 6.713211600429647e-05,
"loss": 0.0505,
"step": 336
},
{
"epoch": 32.88,
"learning_rate": 6.702470461868958e-05,
"loss": 0.0478,
"step": 337
},
{
"epoch": 32.98,
"learning_rate": 6.691729323308271e-05,
"loss": 0.0517,
"step": 338
},
{
"epoch": 33.07,
"learning_rate": 6.680988184747582e-05,
"loss": 0.0582,
"step": 339
},
{
"epoch": 33.17,
"learning_rate": 6.670247046186897e-05,
"loss": 0.0396,
"step": 340
},
{
"epoch": 33.27,
"learning_rate": 6.659505907626209e-05,
"loss": 0.048,
"step": 341
},
{
"epoch": 33.37,
"learning_rate": 6.648764769065521e-05,
"loss": 0.0533,
"step": 342
},
{
"epoch": 33.46,
"learning_rate": 6.638023630504834e-05,
"loss": 0.042,
"step": 343
},
{
"epoch": 33.56,
"learning_rate": 6.627282491944146e-05,
"loss": 0.058,
"step": 344
},
{
"epoch": 33.66,
"learning_rate": 6.616541353383459e-05,
"loss": 0.0579,
"step": 345
},
{
"epoch": 33.76,
"learning_rate": 6.605800214822772e-05,
"loss": 0.0455,
"step": 346
},
{
"epoch": 33.85,
"learning_rate": 6.595059076262085e-05,
"loss": 0.0481,
"step": 347
},
{
"epoch": 33.95,
"learning_rate": 6.584317937701396e-05,
"loss": 0.0665,
"step": 348
},
{
"epoch": 34.05,
"learning_rate": 6.573576799140709e-05,
"loss": 0.0563,
"step": 349
},
{
"epoch": 34.15,
"learning_rate": 6.562835660580022e-05,
"loss": 0.0567,
"step": 350
},
{
"epoch": 34.24,
"learning_rate": 6.552094522019334e-05,
"loss": 0.0569,
"step": 351
},
{
"epoch": 34.34,
"learning_rate": 6.541353383458647e-05,
"loss": 0.066,
"step": 352
},
{
"epoch": 34.44,
"learning_rate": 6.530612244897959e-05,
"loss": 0.0588,
"step": 353
},
{
"epoch": 34.54,
"learning_rate": 6.519871106337271e-05,
"loss": 0.0564,
"step": 354
},
{
"epoch": 34.63,
"learning_rate": 6.509129967776584e-05,
"loss": 0.0448,
"step": 355
},
{
"epoch": 34.73,
"learning_rate": 6.498388829215897e-05,
"loss": 0.0475,
"step": 356
},
{
"epoch": 34.83,
"learning_rate": 6.48764769065521e-05,
"loss": 0.048,
"step": 357
},
{
"epoch": 34.93,
"learning_rate": 6.476906552094523e-05,
"loss": 0.0611,
"step": 358
},
{
"epoch": 35.02,
"learning_rate": 6.466165413533834e-05,
"loss": 0.0636,
"step": 359
},
{
"epoch": 35.12,
"learning_rate": 6.455424274973148e-05,
"loss": 0.0514,
"step": 360
},
{
"epoch": 35.22,
"learning_rate": 6.444683136412461e-05,
"loss": 0.0537,
"step": 361
},
{
"epoch": 35.32,
"learning_rate": 6.433941997851772e-05,
"loss": 0.0583,
"step": 362
},
{
"epoch": 35.41,
"learning_rate": 6.423200859291085e-05,
"loss": 0.0568,
"step": 363
},
{
"epoch": 35.51,
"learning_rate": 6.412459720730398e-05,
"loss": 0.0518,
"step": 364
},
{
"epoch": 35.61,
"learning_rate": 6.401718582169711e-05,
"loss": 0.0587,
"step": 365
},
{
"epoch": 35.71,
"learning_rate": 6.390977443609024e-05,
"loss": 0.0437,
"step": 366
},
{
"epoch": 35.8,
"learning_rate": 6.380236305048335e-05,
"loss": 0.0496,
"step": 367
},
{
"epoch": 35.9,
"learning_rate": 6.369495166487648e-05,
"loss": 0.0441,
"step": 368
},
{
"epoch": 36.0,
"learning_rate": 6.35875402792696e-05,
"loss": 0.0536,
"step": 369
},
{
"epoch": 36.1,
"learning_rate": 6.348012889366273e-05,
"loss": 0.0404,
"step": 370
},
{
"epoch": 36.2,
"learning_rate": 6.337271750805586e-05,
"loss": 0.0556,
"step": 371
},
{
"epoch": 36.29,
"learning_rate": 6.326530612244899e-05,
"loss": 0.0473,
"step": 372
},
{
"epoch": 36.39,
"learning_rate": 6.31578947368421e-05,
"loss": 0.0486,
"step": 373
},
{
"epoch": 36.49,
"learning_rate": 6.305048335123523e-05,
"loss": 0.0467,
"step": 374
},
{
"epoch": 36.59,
"learning_rate": 6.294307196562836e-05,
"loss": 0.0629,
"step": 375
},
{
"epoch": 36.68,
"learning_rate": 6.283566058002149e-05,
"loss": 0.0417,
"step": 376
},
{
"epoch": 36.78,
"learning_rate": 6.272824919441461e-05,
"loss": 0.052,
"step": 377
},
{
"epoch": 36.88,
"learning_rate": 6.262083780880774e-05,
"loss": 0.0567,
"step": 378
},
{
"epoch": 36.98,
"learning_rate": 6.251342642320086e-05,
"loss": 0.0495,
"step": 379
},
{
"epoch": 37.07,
"learning_rate": 6.240601503759398e-05,
"loss": 0.0523,
"step": 380
},
{
"epoch": 37.17,
"learning_rate": 6.229860365198711e-05,
"loss": 0.0548,
"step": 381
},
{
"epoch": 37.27,
"learning_rate": 6.219119226638024e-05,
"loss": 0.0455,
"step": 382
},
{
"epoch": 37.37,
"learning_rate": 6.208378088077337e-05,
"loss": 0.0583,
"step": 383
},
{
"epoch": 37.46,
"learning_rate": 6.197636949516648e-05,
"loss": 0.0559,
"step": 384
},
{
"epoch": 37.56,
"learning_rate": 6.186895810955961e-05,
"loss": 0.0455,
"step": 385
},
{
"epoch": 37.66,
"learning_rate": 6.176154672395275e-05,
"loss": 0.0452,
"step": 386
},
{
"epoch": 37.76,
"learning_rate": 6.165413533834587e-05,
"loss": 0.0496,
"step": 387
},
{
"epoch": 37.85,
"learning_rate": 6.1546723952739e-05,
"loss": 0.0471,
"step": 388
},
{
"epoch": 37.95,
"learning_rate": 6.143931256713212e-05,
"loss": 0.0564,
"step": 389
},
{
"epoch": 38.05,
"learning_rate": 6.133190118152524e-05,
"loss": 0.0577,
"step": 390
},
{
"epoch": 38.15,
"learning_rate": 6.122448979591838e-05,
"loss": 0.0448,
"step": 391
},
{
"epoch": 38.24,
"learning_rate": 6.11170784103115e-05,
"loss": 0.0574,
"step": 392
},
{
"epoch": 38.34,
"learning_rate": 6.100966702470462e-05,
"loss": 0.0504,
"step": 393
},
{
"epoch": 38.44,
"learning_rate": 6.090225563909775e-05,
"loss": 0.0503,
"step": 394
},
{
"epoch": 38.54,
"learning_rate": 6.079484425349087e-05,
"loss": 0.0434,
"step": 395
},
{
"epoch": 38.63,
"learning_rate": 6.0687432867884e-05,
"loss": 0.0483,
"step": 396
},
{
"epoch": 38.73,
"learning_rate": 6.0580021482277125e-05,
"loss": 0.0479,
"step": 397
},
{
"epoch": 38.83,
"learning_rate": 6.0472610096670246e-05,
"loss": 0.0423,
"step": 398
},
{
"epoch": 38.93,
"learning_rate": 6.0365198711063374e-05,
"loss": 0.0381,
"step": 399
},
{
"epoch": 39.02,
"learning_rate": 6.025778732545651e-05,
"loss": 0.0308,
"step": 400
},
{
"epoch": 39.12,
"learning_rate": 6.015037593984962e-05,
"loss": 0.0561,
"step": 401
},
{
"epoch": 39.22,
"learning_rate": 6.004296455424275e-05,
"loss": 0.0483,
"step": 402
},
{
"epoch": 39.32,
"learning_rate": 5.9935553168635885e-05,
"loss": 0.057,
"step": 403
},
{
"epoch": 39.41,
"learning_rate": 5.9828141783029e-05,
"loss": 0.0509,
"step": 404
},
{
"epoch": 39.51,
"learning_rate": 5.9720730397422134e-05,
"loss": 0.0406,
"step": 405
},
{
"epoch": 39.61,
"learning_rate": 5.961331901181526e-05,
"loss": 0.0385,
"step": 406
},
{
"epoch": 39.71,
"learning_rate": 5.9505907626208376e-05,
"loss": 0.0548,
"step": 407
},
{
"epoch": 39.8,
"learning_rate": 5.939849624060151e-05,
"loss": 0.0444,
"step": 408
},
{
"epoch": 39.9,
"learning_rate": 5.9291084854994625e-05,
"loss": 0.0522,
"step": 409
},
{
"epoch": 40.0,
"learning_rate": 5.918367346938776e-05,
"loss": 0.0569,
"step": 410
},
{
"epoch": 40.1,
"learning_rate": 5.907626208378089e-05,
"loss": 0.0602,
"step": 411
},
{
"epoch": 40.2,
"learning_rate": 5.8968850698174e-05,
"loss": 0.0625,
"step": 412
},
{
"epoch": 40.29,
"learning_rate": 5.8861439312567137e-05,
"loss": 0.0493,
"step": 413
},
{
"epoch": 40.39,
"learning_rate": 5.8754027926960264e-05,
"loss": 0.051,
"step": 414
},
{
"epoch": 40.49,
"learning_rate": 5.8646616541353386e-05,
"loss": 0.051,
"step": 415
},
{
"epoch": 40.59,
"learning_rate": 5.853920515574651e-05,
"loss": 0.053,
"step": 416
},
{
"epoch": 40.68,
"learning_rate": 5.843179377013964e-05,
"loss": 0.0434,
"step": 417
},
{
"epoch": 40.78,
"learning_rate": 5.832438238453276e-05,
"loss": 0.0578,
"step": 418
},
{
"epoch": 40.88,
"learning_rate": 5.821697099892589e-05,
"loss": 0.037,
"step": 419
},
{
"epoch": 40.98,
"learning_rate": 5.810955961331902e-05,
"loss": 0.0561,
"step": 420
},
{
"epoch": 41.07,
"learning_rate": 5.800214822771214e-05,
"loss": 0.0486,
"step": 421
},
{
"epoch": 41.17,
"learning_rate": 5.789473684210527e-05,
"loss": 0.0496,
"step": 422
},
{
"epoch": 41.27,
"learning_rate": 5.778732545649839e-05,
"loss": 0.0355,
"step": 423
},
{
"epoch": 41.37,
"learning_rate": 5.7679914070891516e-05,
"loss": 0.0421,
"step": 424
},
{
"epoch": 41.46,
"learning_rate": 5.7572502685284644e-05,
"loss": 0.0504,
"step": 425
},
{
"epoch": 41.56,
"learning_rate": 5.7465091299677765e-05,
"loss": 0.0468,
"step": 426
},
{
"epoch": 41.66,
"learning_rate": 5.735767991407089e-05,
"loss": 0.0469,
"step": 427
},
{
"epoch": 41.76,
"learning_rate": 5.725026852846402e-05,
"loss": 0.0559,
"step": 428
},
{
"epoch": 41.85,
"learning_rate": 5.714285714285714e-05,
"loss": 0.0337,
"step": 429
},
{
"epoch": 41.95,
"learning_rate": 5.703544575725027e-05,
"loss": 0.0387,
"step": 430
},
{
"epoch": 42.05,
"learning_rate": 5.6928034371643404e-05,
"loss": 0.0436,
"step": 431
},
{
"epoch": 42.15,
"learning_rate": 5.682062298603652e-05,
"loss": 0.054,
"step": 432
},
{
"epoch": 42.24,
"learning_rate": 5.671321160042965e-05,
"loss": 0.049,
"step": 433
},
{
"epoch": 42.34,
"learning_rate": 5.660580021482277e-05,
"loss": 0.0605,
"step": 434
},
{
"epoch": 42.44,
"learning_rate": 5.6498388829215895e-05,
"loss": 0.0359,
"step": 435
},
{
"epoch": 42.54,
"learning_rate": 5.639097744360903e-05,
"loss": 0.0548,
"step": 436
},
{
"epoch": 42.63,
"learning_rate": 5.6283566058002144e-05,
"loss": 0.0489,
"step": 437
},
{
"epoch": 42.73,
"learning_rate": 5.617615467239528e-05,
"loss": 0.043,
"step": 438
},
{
"epoch": 42.83,
"learning_rate": 5.606874328678841e-05,
"loss": 0.0485,
"step": 439
},
{
"epoch": 42.93,
"learning_rate": 5.596133190118152e-05,
"loss": 0.046,
"step": 440
},
{
"epoch": 43.02,
"learning_rate": 5.5853920515574656e-05,
"loss": 0.0414,
"step": 441
},
{
"epoch": 43.12,
"learning_rate": 5.5746509129967784e-05,
"loss": 0.0443,
"step": 442
},
{
"epoch": 43.22,
"learning_rate": 5.5639097744360905e-05,
"loss": 0.0471,
"step": 443
},
{
"epoch": 43.32,
"learning_rate": 5.553168635875403e-05,
"loss": 0.0477,
"step": 444
},
{
"epoch": 43.41,
"learning_rate": 5.542427497314716e-05,
"loss": 0.0517,
"step": 445
},
{
"epoch": 43.51,
"learning_rate": 5.531686358754028e-05,
"loss": 0.047,
"step": 446
},
{
"epoch": 43.61,
"learning_rate": 5.520945220193341e-05,
"loss": 0.0594,
"step": 447
},
{
"epoch": 43.71,
"learning_rate": 5.510204081632653e-05,
"loss": 0.052,
"step": 448
},
{
"epoch": 43.8,
"learning_rate": 5.499462943071966e-05,
"loss": 0.0583,
"step": 449
},
{
"epoch": 43.9,
"learning_rate": 5.4887218045112786e-05,
"loss": 0.05,
"step": 450
},
{
"epoch": 44.0,
"learning_rate": 5.477980665950591e-05,
"loss": 0.0568,
"step": 451
},
{
"epoch": 44.1,
"learning_rate": 5.4672395273899035e-05,
"loss": 0.0429,
"step": 452
},
{
"epoch": 44.2,
"learning_rate": 5.456498388829216e-05,
"loss": 0.0434,
"step": 453
},
{
"epoch": 44.29,
"learning_rate": 5.4457572502685284e-05,
"loss": 0.0501,
"step": 454
},
{
"epoch": 44.39,
"learning_rate": 5.435016111707841e-05,
"loss": 0.0483,
"step": 455
},
{
"epoch": 44.49,
"learning_rate": 5.424274973147154e-05,
"loss": 0.054,
"step": 456
},
{
"epoch": 44.59,
"learning_rate": 5.413533834586466e-05,
"loss": 0.0456,
"step": 457
},
{
"epoch": 44.68,
"learning_rate": 5.402792696025779e-05,
"loss": 0.0556,
"step": 458
},
{
"epoch": 44.78,
"learning_rate": 5.3920515574650923e-05,
"loss": 0.0391,
"step": 459
},
{
"epoch": 44.88,
"learning_rate": 5.381310418904404e-05,
"loss": 0.0411,
"step": 460
},
{
"epoch": 44.98,
"learning_rate": 5.3705692803437166e-05,
"loss": 0.0616,
"step": 461
},
{
"epoch": 45.07,
"learning_rate": 5.359828141783029e-05,
"loss": 0.0393,
"step": 462
},
{
"epoch": 45.17,
"learning_rate": 5.3490870032223415e-05,
"loss": 0.0405,
"step": 463
},
{
"epoch": 45.27,
"learning_rate": 5.338345864661655e-05,
"loss": 0.0421,
"step": 464
},
{
"epoch": 45.37,
"learning_rate": 5.3276047261009664e-05,
"loss": 0.0402,
"step": 465
},
{
"epoch": 45.46,
"learning_rate": 5.316863587540279e-05,
"loss": 0.0526,
"step": 466
},
{
"epoch": 45.56,
"learning_rate": 5.3061224489795926e-05,
"loss": 0.0444,
"step": 467
},
{
"epoch": 45.66,
"learning_rate": 5.295381310418904e-05,
"loss": 0.0497,
"step": 468
},
{
"epoch": 45.76,
"learning_rate": 5.2846401718582175e-05,
"loss": 0.0483,
"step": 469
},
{
"epoch": 45.85,
"learning_rate": 5.27389903329753e-05,
"loss": 0.0424,
"step": 470
},
{
"epoch": 45.95,
"learning_rate": 5.2631578947368424e-05,
"loss": 0.0432,
"step": 471
},
{
"epoch": 46.05,
"learning_rate": 5.252416756176155e-05,
"loss": 0.0429,
"step": 472
},
{
"epoch": 46.15,
"learning_rate": 5.241675617615468e-05,
"loss": 0.0396,
"step": 473
},
{
"epoch": 46.24,
"learning_rate": 5.23093447905478e-05,
"loss": 0.0495,
"step": 474
},
{
"epoch": 46.34,
"learning_rate": 5.220193340494093e-05,
"loss": 0.0681,
"step": 475
},
{
"epoch": 46.44,
"learning_rate": 5.209452201933405e-05,
"loss": 0.0486,
"step": 476
},
{
"epoch": 46.54,
"learning_rate": 5.198711063372718e-05,
"loss": 0.0411,
"step": 477
},
{
"epoch": 46.63,
"learning_rate": 5.1879699248120305e-05,
"loss": 0.0358,
"step": 478
},
{
"epoch": 46.73,
"learning_rate": 5.1772287862513427e-05,
"loss": 0.0492,
"step": 479
},
{
"epoch": 46.83,
"learning_rate": 5.1664876476906554e-05,
"loss": 0.0399,
"step": 480
},
{
"epoch": 46.93,
"learning_rate": 5.155746509129968e-05,
"loss": 0.0374,
"step": 481
},
{
"epoch": 47.02,
"learning_rate": 5.14500537056928e-05,
"loss": 0.0401,
"step": 482
},
{
"epoch": 47.12,
"learning_rate": 5.134264232008593e-05,
"loss": 0.0415,
"step": 483
},
{
"epoch": 47.22,
"learning_rate": 5.123523093447906e-05,
"loss": 0.0526,
"step": 484
},
{
"epoch": 47.32,
"learning_rate": 5.112781954887218e-05,
"loss": 0.0603,
"step": 485
},
{
"epoch": 47.41,
"learning_rate": 5.102040816326531e-05,
"loss": 0.0483,
"step": 486
},
{
"epoch": 47.51,
"learning_rate": 5.091299677765844e-05,
"loss": 0.0525,
"step": 487
},
{
"epoch": 47.61,
"learning_rate": 5.080558539205156e-05,
"loss": 0.0463,
"step": 488
},
{
"epoch": 47.71,
"learning_rate": 5.0698174006444685e-05,
"loss": 0.0424,
"step": 489
},
{
"epoch": 47.8,
"learning_rate": 5.0590762620837806e-05,
"loss": 0.0473,
"step": 490
},
{
"epoch": 47.9,
"learning_rate": 5.0483351235230934e-05,
"loss": 0.04,
"step": 491
},
{
"epoch": 48.0,
"learning_rate": 5.037593984962407e-05,
"loss": 0.0435,
"step": 492
},
{
"epoch": 48.1,
"learning_rate": 5.026852846401718e-05,
"loss": 0.0539,
"step": 493
},
{
"epoch": 48.2,
"learning_rate": 5.016111707841031e-05,
"loss": 0.0505,
"step": 494
},
{
"epoch": 48.29,
"learning_rate": 5.0053705692803445e-05,
"loss": 0.042,
"step": 495
},
{
"epoch": 48.39,
"learning_rate": 4.9946294307196566e-05,
"loss": 0.0533,
"step": 496
},
{
"epoch": 48.49,
"learning_rate": 4.9838882921589694e-05,
"loss": 0.0428,
"step": 497
},
{
"epoch": 48.59,
"learning_rate": 4.9731471535982815e-05,
"loss": 0.0494,
"step": 498
},
{
"epoch": 48.68,
"learning_rate": 4.9624060150375936e-05,
"loss": 0.0451,
"step": 499
},
{
"epoch": 48.78,
"learning_rate": 4.951664876476907e-05,
"loss": 0.045,
"step": 500
},
{
"epoch": 48.88,
"learning_rate": 4.940923737916219e-05,
"loss": 0.0394,
"step": 501
},
{
"epoch": 48.98,
"learning_rate": 4.930182599355532e-05,
"loss": 0.0562,
"step": 502
},
{
"epoch": 49.07,
"learning_rate": 4.919441460794845e-05,
"loss": 0.0418,
"step": 503
},
{
"epoch": 49.17,
"learning_rate": 4.908700322234157e-05,
"loss": 0.0513,
"step": 504
},
{
"epoch": 49.27,
"learning_rate": 4.89795918367347e-05,
"loss": 0.0566,
"step": 505
},
{
"epoch": 49.37,
"learning_rate": 4.887218045112782e-05,
"loss": 0.0384,
"step": 506
},
{
"epoch": 49.46,
"learning_rate": 4.8764769065520946e-05,
"loss": 0.0428,
"step": 507
},
{
"epoch": 49.56,
"learning_rate": 4.8657357679914074e-05,
"loss": 0.0434,
"step": 508
},
{
"epoch": 49.66,
"learning_rate": 4.8549946294307195e-05,
"loss": 0.0431,
"step": 509
},
{
"epoch": 49.76,
"learning_rate": 4.844253490870033e-05,
"loss": 0.0398,
"step": 510
},
{
"epoch": 49.85,
"learning_rate": 4.833512352309345e-05,
"loss": 0.0444,
"step": 511
},
{
"epoch": 49.95,
"learning_rate": 4.822771213748657e-05,
"loss": 0.0471,
"step": 512
},
{
"epoch": 50.05,
"learning_rate": 4.81203007518797e-05,
"loss": 0.0456,
"step": 513
},
{
"epoch": 50.15,
"learning_rate": 4.801288936627283e-05,
"loss": 0.0475,
"step": 514
},
{
"epoch": 50.24,
"learning_rate": 4.7905477980665955e-05,
"loss": 0.0406,
"step": 515
},
{
"epoch": 50.34,
"learning_rate": 4.7798066595059076e-05,
"loss": 0.0358,
"step": 516
},
{
"epoch": 50.44,
"learning_rate": 4.7690655209452204e-05,
"loss": 0.0492,
"step": 517
},
{
"epoch": 50.54,
"learning_rate": 4.758324382384533e-05,
"loss": 0.0405,
"step": 518
},
{
"epoch": 50.63,
"learning_rate": 4.747583243823845e-05,
"loss": 0.0458,
"step": 519
},
{
"epoch": 50.73,
"learning_rate": 4.736842105263158e-05,
"loss": 0.0428,
"step": 520
},
{
"epoch": 50.83,
"learning_rate": 4.726100966702471e-05,
"loss": 0.046,
"step": 521
},
{
"epoch": 50.93,
"learning_rate": 4.715359828141783e-05,
"loss": 0.0328,
"step": 522
},
{
"epoch": 51.02,
"learning_rate": 4.704618689581096e-05,
"loss": 0.0487,
"step": 523
},
{
"epoch": 51.12,
"learning_rate": 4.6938775510204086e-05,
"loss": 0.0383,
"step": 524
},
{
"epoch": 51.22,
"learning_rate": 4.6831364124597213e-05,
"loss": 0.0515,
"step": 525
},
{
"epoch": 51.32,
"learning_rate": 4.6723952738990334e-05,
"loss": 0.0412,
"step": 526
},
{
"epoch": 51.41,
"learning_rate": 4.6616541353383456e-05,
"loss": 0.0489,
"step": 527
},
{
"epoch": 51.51,
"learning_rate": 4.650912996777659e-05,
"loss": 0.0476,
"step": 528
},
{
"epoch": 51.61,
"learning_rate": 4.640171858216971e-05,
"loss": 0.0324,
"step": 529
},
{
"epoch": 51.71,
"learning_rate": 4.629430719656284e-05,
"loss": 0.0485,
"step": 530
},
{
"epoch": 51.8,
"learning_rate": 4.618689581095597e-05,
"loss": 0.0415,
"step": 531
},
{
"epoch": 51.9,
"learning_rate": 4.607948442534909e-05,
"loss": 0.0396,
"step": 532
},
{
"epoch": 52.0,
"learning_rate": 4.5972073039742216e-05,
"loss": 0.0442,
"step": 533
},
{
"epoch": 52.1,
"learning_rate": 4.586466165413534e-05,
"loss": 0.045,
"step": 534
},
{
"epoch": 52.2,
"learning_rate": 4.5757250268528465e-05,
"loss": 0.0475,
"step": 535
},
{
"epoch": 52.29,
"learning_rate": 4.564983888292159e-05,
"loss": 0.0516,
"step": 536
},
{
"epoch": 52.39,
"learning_rate": 4.5542427497314714e-05,
"loss": 0.0503,
"step": 537
},
{
"epoch": 52.49,
"learning_rate": 4.543501611170785e-05,
"loss": 0.0357,
"step": 538
},
{
"epoch": 52.59,
"learning_rate": 4.532760472610097e-05,
"loss": 0.0424,
"step": 539
},
{
"epoch": 52.68,
"learning_rate": 4.522019334049409e-05,
"loss": 0.0587,
"step": 540
},
{
"epoch": 52.78,
"learning_rate": 4.511278195488722e-05,
"loss": 0.0503,
"step": 541
},
{
"epoch": 52.88,
"learning_rate": 4.5005370569280346e-05,
"loss": 0.056,
"step": 542
},
{
"epoch": 52.98,
"learning_rate": 4.4897959183673474e-05,
"loss": 0.0577,
"step": 543
},
{
"epoch": 53.07,
"learning_rate": 4.4790547798066595e-05,
"loss": 0.0456,
"step": 544
},
{
"epoch": 53.17,
"learning_rate": 4.468313641245972e-05,
"loss": 0.0487,
"step": 545
},
{
"epoch": 53.27,
"learning_rate": 4.457572502685285e-05,
"loss": 0.0509,
"step": 546
},
{
"epoch": 53.37,
"learning_rate": 4.446831364124597e-05,
"loss": 0.0478,
"step": 547
},
{
"epoch": 53.46,
"learning_rate": 4.43609022556391e-05,
"loss": 0.0552,
"step": 548
},
{
"epoch": 53.56,
"learning_rate": 4.425349087003223e-05,
"loss": 0.0419,
"step": 549
},
{
"epoch": 53.66,
"learning_rate": 4.414607948442535e-05,
"loss": 0.0497,
"step": 550
},
{
"epoch": 53.76,
"learning_rate": 4.403866809881848e-05,
"loss": 0.0501,
"step": 551
},
{
"epoch": 53.85,
"learning_rate": 4.3931256713211605e-05,
"loss": 0.0477,
"step": 552
},
{
"epoch": 53.95,
"learning_rate": 4.3823845327604726e-05,
"loss": 0.0343,
"step": 553
},
{
"epoch": 54.05,
"learning_rate": 4.3716433941997854e-05,
"loss": 0.0429,
"step": 554
},
{
"epoch": 54.15,
"learning_rate": 4.3609022556390975e-05,
"loss": 0.0521,
"step": 555
},
{
"epoch": 54.24,
"learning_rate": 4.350161117078411e-05,
"loss": 0.0423,
"step": 556
},
{
"epoch": 54.34,
"learning_rate": 4.339419978517723e-05,
"loss": 0.0438,
"step": 557
},
{
"epoch": 54.44,
"learning_rate": 4.328678839957035e-05,
"loss": 0.0394,
"step": 558
},
{
"epoch": 54.54,
"learning_rate": 4.3179377013963486e-05,
"loss": 0.0425,
"step": 559
},
{
"epoch": 54.63,
"learning_rate": 4.307196562835661e-05,
"loss": 0.052,
"step": 560
},
{
"epoch": 54.73,
"learning_rate": 4.2964554242749735e-05,
"loss": 0.0499,
"step": 561
},
{
"epoch": 54.83,
"learning_rate": 4.2857142857142856e-05,
"loss": 0.0457,
"step": 562
},
{
"epoch": 54.93,
"learning_rate": 4.2749731471535984e-05,
"loss": 0.0492,
"step": 563
},
{
"epoch": 55.02,
"learning_rate": 4.264232008592911e-05,
"loss": 0.0312,
"step": 564
},
{
"epoch": 55.12,
"learning_rate": 4.253490870032223e-05,
"loss": 0.0401,
"step": 565
},
{
"epoch": 55.22,
"learning_rate": 4.242749731471536e-05,
"loss": 0.0582,
"step": 566
},
{
"epoch": 55.32,
"learning_rate": 4.232008592910849e-05,
"loss": 0.0457,
"step": 567
},
{
"epoch": 55.41,
"learning_rate": 4.221267454350161e-05,
"loss": 0.0455,
"step": 568
},
{
"epoch": 55.51,
"learning_rate": 4.210526315789474e-05,
"loss": 0.0332,
"step": 569
},
{
"epoch": 55.61,
"learning_rate": 4.1997851772287866e-05,
"loss": 0.0546,
"step": 570
},
{
"epoch": 55.71,
"learning_rate": 4.1890440386680994e-05,
"loss": 0.0321,
"step": 571
},
{
"epoch": 55.8,
"learning_rate": 4.1783029001074115e-05,
"loss": 0.0383,
"step": 572
},
{
"epoch": 55.9,
"learning_rate": 4.167561761546724e-05,
"loss": 0.0439,
"step": 573
},
{
"epoch": 56.0,
"learning_rate": 4.156820622986037e-05,
"loss": 0.0444,
"step": 574
},
{
"epoch": 56.1,
"learning_rate": 4.146079484425349e-05,
"loss": 0.0416,
"step": 575
},
{
"epoch": 56.2,
"learning_rate": 4.135338345864662e-05,
"loss": 0.0505,
"step": 576
},
{
"epoch": 56.29,
"learning_rate": 4.124597207303975e-05,
"loss": 0.0507,
"step": 577
},
{
"epoch": 56.39,
"learning_rate": 4.113856068743287e-05,
"loss": 0.0462,
"step": 578
},
{
"epoch": 56.49,
"learning_rate": 4.1031149301825996e-05,
"loss": 0.0451,
"step": 579
},
{
"epoch": 56.59,
"learning_rate": 4.0923737916219124e-05,
"loss": 0.0421,
"step": 580
},
{
"epoch": 56.68,
"learning_rate": 4.0816326530612245e-05,
"loss": 0.0428,
"step": 581
},
{
"epoch": 56.78,
"learning_rate": 4.070891514500537e-05,
"loss": 0.0396,
"step": 582
},
{
"epoch": 56.88,
"learning_rate": 4.0601503759398494e-05,
"loss": 0.0416,
"step": 583
},
{
"epoch": 56.98,
"learning_rate": 4.049409237379163e-05,
"loss": 0.04,
"step": 584
},
{
"epoch": 57.07,
"learning_rate": 4.038668098818475e-05,
"loss": 0.0401,
"step": 585
},
{
"epoch": 57.17,
"learning_rate": 4.027926960257787e-05,
"loss": 0.0344,
"step": 586
},
{
"epoch": 57.27,
"learning_rate": 4.0171858216971005e-05,
"loss": 0.0421,
"step": 587
},
{
"epoch": 57.37,
"learning_rate": 4.0064446831364127e-05,
"loss": 0.0494,
"step": 588
},
{
"epoch": 57.46,
"learning_rate": 3.9957035445757254e-05,
"loss": 0.0523,
"step": 589
},
{
"epoch": 57.56,
"learning_rate": 3.9849624060150376e-05,
"loss": 0.0448,
"step": 590
},
{
"epoch": 57.66,
"learning_rate": 3.97422126745435e-05,
"loss": 0.0376,
"step": 591
},
{
"epoch": 57.76,
"learning_rate": 3.963480128893663e-05,
"loss": 0.0515,
"step": 592
},
{
"epoch": 57.85,
"learning_rate": 3.952738990332975e-05,
"loss": 0.0339,
"step": 593
},
{
"epoch": 57.95,
"learning_rate": 3.941997851772288e-05,
"loss": 0.0435,
"step": 594
},
{
"epoch": 58.05,
"learning_rate": 3.931256713211601e-05,
"loss": 0.0365,
"step": 595
},
{
"epoch": 58.15,
"learning_rate": 3.920515574650913e-05,
"loss": 0.0433,
"step": 596
},
{
"epoch": 58.24,
"learning_rate": 3.909774436090226e-05,
"loss": 0.0372,
"step": 597
},
{
"epoch": 58.34,
"learning_rate": 3.8990332975295385e-05,
"loss": 0.0404,
"step": 598
},
{
"epoch": 58.44,
"learning_rate": 3.8882921589688506e-05,
"loss": 0.0436,
"step": 599
},
{
"epoch": 58.54,
"learning_rate": 3.8775510204081634e-05,
"loss": 0.0444,
"step": 600
},
{
"epoch": 58.63,
"learning_rate": 3.866809881847476e-05,
"loss": 0.0471,
"step": 601
},
{
"epoch": 58.73,
"learning_rate": 3.856068743286789e-05,
"loss": 0.0437,
"step": 602
},
{
"epoch": 58.83,
"learning_rate": 3.845327604726101e-05,
"loss": 0.0484,
"step": 603
},
{
"epoch": 58.93,
"learning_rate": 3.834586466165413e-05,
"loss": 0.04,
"step": 604
},
{
"epoch": 59.02,
"learning_rate": 3.8238453276047266e-05,
"loss": 0.0469,
"step": 605
},
{
"epoch": 59.12,
"learning_rate": 3.813104189044039e-05,
"loss": 0.0458,
"step": 606
},
{
"epoch": 59.22,
"learning_rate": 3.8023630504833515e-05,
"loss": 0.0345,
"step": 607
},
{
"epoch": 59.32,
"learning_rate": 3.791621911922664e-05,
"loss": 0.0447,
"step": 608
},
{
"epoch": 59.41,
"learning_rate": 3.7808807733619764e-05,
"loss": 0.0476,
"step": 609
},
{
"epoch": 59.51,
"learning_rate": 3.770139634801289e-05,
"loss": 0.0446,
"step": 610
},
{
"epoch": 59.61,
"learning_rate": 3.759398496240601e-05,
"loss": 0.0395,
"step": 611
},
{
"epoch": 59.71,
"learning_rate": 3.748657357679914e-05,
"loss": 0.0402,
"step": 612
},
{
"epoch": 59.8,
"learning_rate": 3.737916219119227e-05,
"loss": 0.0395,
"step": 613
},
{
"epoch": 59.9,
"learning_rate": 3.727175080558539e-05,
"loss": 0.0399,
"step": 614
},
{
"epoch": 60.0,
"learning_rate": 3.7164339419978525e-05,
"loss": 0.0428,
"step": 615
},
{
"epoch": 60.1,
"learning_rate": 3.7056928034371646e-05,
"loss": 0.043,
"step": 616
},
{
"epoch": 60.2,
"learning_rate": 3.6949516648764774e-05,
"loss": 0.0498,
"step": 617
},
{
"epoch": 60.29,
"learning_rate": 3.6842105263157895e-05,
"loss": 0.039,
"step": 618
},
{
"epoch": 60.39,
"learning_rate": 3.673469387755102e-05,
"loss": 0.0426,
"step": 619
},
{
"epoch": 60.49,
"learning_rate": 3.662728249194415e-05,
"loss": 0.0364,
"step": 620
},
{
"epoch": 60.59,
"learning_rate": 3.651987110633727e-05,
"loss": 0.0407,
"step": 621
},
{
"epoch": 60.68,
"learning_rate": 3.64124597207304e-05,
"loss": 0.0372,
"step": 622
},
{
"epoch": 60.78,
"learning_rate": 3.630504833512353e-05,
"loss": 0.0382,
"step": 623
},
{
"epoch": 60.88,
"learning_rate": 3.619763694951665e-05,
"loss": 0.0467,
"step": 624
},
{
"epoch": 60.98,
"learning_rate": 3.6090225563909776e-05,
"loss": 0.0498,
"step": 625
},
{
"epoch": 61.07,
"learning_rate": 3.5982814178302904e-05,
"loss": 0.0488,
"step": 626
},
{
"epoch": 61.17,
"learning_rate": 3.5875402792696025e-05,
"loss": 0.0465,
"step": 627
},
{
"epoch": 61.27,
"learning_rate": 3.576799140708915e-05,
"loss": 0.0409,
"step": 628
},
{
"epoch": 61.37,
"learning_rate": 3.5660580021482274e-05,
"loss": 0.0355,
"step": 629
},
{
"epoch": 61.46,
"learning_rate": 3.555316863587541e-05,
"loss": 0.0478,
"step": 630
},
{
"epoch": 61.56,
"learning_rate": 3.544575725026853e-05,
"loss": 0.048,
"step": 631
},
{
"epoch": 61.66,
"learning_rate": 3.533834586466165e-05,
"loss": 0.0445,
"step": 632
},
{
"epoch": 61.76,
"learning_rate": 3.5230934479054786e-05,
"loss": 0.0417,
"step": 633
},
{
"epoch": 61.85,
"learning_rate": 3.512352309344791e-05,
"loss": 0.0397,
"step": 634
},
{
"epoch": 61.95,
"learning_rate": 3.5016111707841035e-05,
"loss": 0.0353,
"step": 635
},
{
"epoch": 62.05,
"learning_rate": 3.4908700322234156e-05,
"loss": 0.0486,
"step": 636
},
{
"epoch": 62.15,
"learning_rate": 3.4801288936627283e-05,
"loss": 0.035,
"step": 637
},
{
"epoch": 62.24,
"learning_rate": 3.469387755102041e-05,
"loss": 0.0485,
"step": 638
},
{
"epoch": 62.34,
"learning_rate": 3.458646616541353e-05,
"loss": 0.0362,
"step": 639
},
{
"epoch": 62.44,
"learning_rate": 3.447905477980666e-05,
"loss": 0.0401,
"step": 640
},
{
"epoch": 62.54,
"learning_rate": 3.437164339419979e-05,
"loss": 0.0478,
"step": 641
},
{
"epoch": 62.63,
"learning_rate": 3.426423200859291e-05,
"loss": 0.0421,
"step": 642
},
{
"epoch": 62.73,
"learning_rate": 3.415682062298604e-05,
"loss": 0.0379,
"step": 643
},
{
"epoch": 62.83,
"learning_rate": 3.4049409237379165e-05,
"loss": 0.0392,
"step": 644
},
{
"epoch": 62.93,
"learning_rate": 3.3941997851772286e-05,
"loss": 0.0381,
"step": 645
},
{
"epoch": 63.02,
"learning_rate": 3.3834586466165414e-05,
"loss": 0.0472,
"step": 646
},
{
"epoch": 63.12,
"learning_rate": 3.372717508055854e-05,
"loss": 0.0396,
"step": 647
},
{
"epoch": 63.22,
"learning_rate": 3.361976369495167e-05,
"loss": 0.039,
"step": 648
},
{
"epoch": 63.32,
"learning_rate": 3.351235230934479e-05,
"loss": 0.0465,
"step": 649
},
{
"epoch": 63.41,
"learning_rate": 3.340494092373791e-05,
"loss": 0.049,
"step": 650
},
{
"epoch": 63.51,
"learning_rate": 3.3297529538131046e-05,
"loss": 0.0498,
"step": 651
},
{
"epoch": 63.61,
"learning_rate": 3.319011815252417e-05,
"loss": 0.0438,
"step": 652
},
{
"epoch": 63.71,
"learning_rate": 3.3082706766917295e-05,
"loss": 0.0363,
"step": 653
},
{
"epoch": 63.8,
"learning_rate": 3.297529538131042e-05,
"loss": 0.0434,
"step": 654
},
{
"epoch": 63.9,
"learning_rate": 3.2867883995703544e-05,
"loss": 0.0365,
"step": 655
},
{
"epoch": 64.0,
"learning_rate": 3.276047261009667e-05,
"loss": 0.0285,
"step": 656
},
{
"epoch": 64.1,
"learning_rate": 3.265306122448979e-05,
"loss": 0.0436,
"step": 657
},
{
"epoch": 64.2,
"learning_rate": 3.254564983888292e-05,
"loss": 0.0509,
"step": 658
},
{
"epoch": 64.29,
"learning_rate": 3.243823845327605e-05,
"loss": 0.0403,
"step": 659
},
{
"epoch": 64.39,
"learning_rate": 3.233082706766917e-05,
"loss": 0.043,
"step": 660
},
{
"epoch": 64.49,
"learning_rate": 3.2223415682062305e-05,
"loss": 0.0492,
"step": 661
},
{
"epoch": 64.59,
"learning_rate": 3.2116004296455426e-05,
"loss": 0.0339,
"step": 662
},
{
"epoch": 64.68,
"learning_rate": 3.2008592910848554e-05,
"loss": 0.0474,
"step": 663
},
{
"epoch": 64.78,
"learning_rate": 3.1901181525241675e-05,
"loss": 0.0361,
"step": 664
},
{
"epoch": 64.88,
"learning_rate": 3.17937701396348e-05,
"loss": 0.0458,
"step": 665
},
{
"epoch": 64.98,
"learning_rate": 3.168635875402793e-05,
"loss": 0.0441,
"step": 666
},
{
"epoch": 65.07,
"learning_rate": 3.157894736842105e-05,
"loss": 0.0496,
"step": 667
},
{
"epoch": 65.17,
"learning_rate": 3.147153598281418e-05,
"loss": 0.0491,
"step": 668
},
{
"epoch": 65.27,
"learning_rate": 3.136412459720731e-05,
"loss": 0.0409,
"step": 669
},
{
"epoch": 65.37,
"learning_rate": 3.125671321160043e-05,
"loss": 0.0341,
"step": 670
},
{
"epoch": 65.46,
"learning_rate": 3.1149301825993556e-05,
"loss": 0.0453,
"step": 671
},
{
"epoch": 65.56,
"learning_rate": 3.1041890440386684e-05,
"loss": 0.0388,
"step": 672
},
{
"epoch": 65.66,
"learning_rate": 3.0934479054779805e-05,
"loss": 0.039,
"step": 673
},
{
"epoch": 65.76,
"learning_rate": 3.082706766917293e-05,
"loss": 0.0405,
"step": 674
},
{
"epoch": 65.85,
"learning_rate": 3.071965628356606e-05,
"loss": 0.0481,
"step": 675
},
{
"epoch": 65.95,
"learning_rate": 3.061224489795919e-05,
"loss": 0.0381,
"step": 676
},
{
"epoch": 66.05,
"learning_rate": 3.050483351235231e-05,
"loss": 0.0416,
"step": 677
},
{
"epoch": 66.15,
"learning_rate": 3.0397422126745434e-05,
"loss": 0.0412,
"step": 678
},
{
"epoch": 66.24,
"learning_rate": 3.0290010741138562e-05,
"loss": 0.0428,
"step": 679
},
{
"epoch": 66.34,
"learning_rate": 3.0182599355531687e-05,
"loss": 0.0395,
"step": 680
},
{
"epoch": 66.44,
"learning_rate": 3.007518796992481e-05,
"loss": 0.0372,
"step": 681
},
{
"epoch": 66.54,
"learning_rate": 2.9967776584317943e-05,
"loss": 0.0327,
"step": 682
},
{
"epoch": 66.63,
"learning_rate": 2.9860365198711067e-05,
"loss": 0.0439,
"step": 683
},
{
"epoch": 66.73,
"learning_rate": 2.9752953813104188e-05,
"loss": 0.0322,
"step": 684
},
{
"epoch": 66.83,
"learning_rate": 2.9645542427497313e-05,
"loss": 0.0412,
"step": 685
},
{
"epoch": 66.93,
"learning_rate": 2.9538131041890444e-05,
"loss": 0.0351,
"step": 686
},
{
"epoch": 67.02,
"learning_rate": 2.9430719656283568e-05,
"loss": 0.0456,
"step": 687
},
{
"epoch": 67.12,
"learning_rate": 2.9323308270676693e-05,
"loss": 0.0378,
"step": 688
},
{
"epoch": 67.22,
"learning_rate": 2.921589688506982e-05,
"loss": 0.0432,
"step": 689
},
{
"epoch": 67.32,
"learning_rate": 2.9108485499462945e-05,
"loss": 0.047,
"step": 690
},
{
"epoch": 67.41,
"learning_rate": 2.900107411385607e-05,
"loss": 0.0411,
"step": 691
},
{
"epoch": 67.51,
"learning_rate": 2.8893662728249194e-05,
"loss": 0.0388,
"step": 692
},
{
"epoch": 67.61,
"learning_rate": 2.8786251342642322e-05,
"loss": 0.0332,
"step": 693
},
{
"epoch": 67.71,
"learning_rate": 2.8678839957035446e-05,
"loss": 0.0386,
"step": 694
},
{
"epoch": 67.8,
"learning_rate": 2.857142857142857e-05,
"loss": 0.0469,
"step": 695
},
{
"epoch": 67.9,
"learning_rate": 2.8464017185821702e-05,
"loss": 0.0355,
"step": 696
},
{
"epoch": 68.0,
"learning_rate": 2.8356605800214827e-05,
"loss": 0.0481,
"step": 697
},
{
"epoch": 68.1,
"learning_rate": 2.8249194414607948e-05,
"loss": 0.0378,
"step": 698
},
{
"epoch": 68.2,
"learning_rate": 2.8141783029001072e-05,
"loss": 0.0371,
"step": 699
},
{
"epoch": 68.29,
"learning_rate": 2.8034371643394203e-05,
"loss": 0.0494,
"step": 700
},
{
"epoch": 68.39,
"learning_rate": 2.7926960257787328e-05,
"loss": 0.0466,
"step": 701
},
{
"epoch": 68.49,
"learning_rate": 2.7819548872180452e-05,
"loss": 0.0296,
"step": 702
},
{
"epoch": 68.59,
"learning_rate": 2.771213748657358e-05,
"loss": 0.0429,
"step": 703
},
{
"epoch": 68.68,
"learning_rate": 2.7604726100966705e-05,
"loss": 0.0389,
"step": 704
},
{
"epoch": 68.78,
"learning_rate": 2.749731471535983e-05,
"loss": 0.0458,
"step": 705
},
{
"epoch": 68.88,
"learning_rate": 2.7389903329752954e-05,
"loss": 0.0461,
"step": 706
},
{
"epoch": 68.98,
"learning_rate": 2.728249194414608e-05,
"loss": 0.0307,
"step": 707
},
{
"epoch": 69.07,
"learning_rate": 2.7175080558539206e-05,
"loss": 0.0361,
"step": 708
},
{
"epoch": 69.17,
"learning_rate": 2.706766917293233e-05,
"loss": 0.0458,
"step": 709
},
{
"epoch": 69.27,
"learning_rate": 2.6960257787325462e-05,
"loss": 0.0428,
"step": 710
},
{
"epoch": 69.37,
"learning_rate": 2.6852846401718583e-05,
"loss": 0.0398,
"step": 711
},
{
"epoch": 69.46,
"learning_rate": 2.6745435016111707e-05,
"loss": 0.0441,
"step": 712
},
{
"epoch": 69.56,
"learning_rate": 2.6638023630504832e-05,
"loss": 0.0514,
"step": 713
},
{
"epoch": 69.66,
"learning_rate": 2.6530612244897963e-05,
"loss": 0.0355,
"step": 714
},
{
"epoch": 69.76,
"learning_rate": 2.6423200859291087e-05,
"loss": 0.0467,
"step": 715
},
{
"epoch": 69.85,
"learning_rate": 2.6315789473684212e-05,
"loss": 0.0499,
"step": 716
},
{
"epoch": 69.95,
"learning_rate": 2.620837808807734e-05,
"loss": 0.0425,
"step": 717
},
{
"epoch": 70.05,
"learning_rate": 2.6100966702470464e-05,
"loss": 0.0436,
"step": 718
},
{
"epoch": 70.15,
"learning_rate": 2.599355531686359e-05,
"loss": 0.0439,
"step": 719
},
{
"epoch": 70.24,
"learning_rate": 2.5886143931256713e-05,
"loss": 0.0347,
"step": 720
},
{
"epoch": 70.34,
"learning_rate": 2.577873254564984e-05,
"loss": 0.0406,
"step": 721
},
{
"epoch": 70.44,
"learning_rate": 2.5671321160042966e-05,
"loss": 0.0444,
"step": 722
},
{
"epoch": 70.54,
"learning_rate": 2.556390977443609e-05,
"loss": 0.0309,
"step": 723
},
{
"epoch": 70.63,
"learning_rate": 2.545649838882922e-05,
"loss": 0.0356,
"step": 724
},
{
"epoch": 70.73,
"learning_rate": 2.5349087003222342e-05,
"loss": 0.0409,
"step": 725
},
{
"epoch": 70.83,
"learning_rate": 2.5241675617615467e-05,
"loss": 0.0334,
"step": 726
},
{
"epoch": 70.93,
"learning_rate": 2.513426423200859e-05,
"loss": 0.0432,
"step": 727
},
{
"epoch": 71.02,
"learning_rate": 2.5026852846401723e-05,
"loss": 0.0422,
"step": 728
},
{
"epoch": 71.12,
"learning_rate": 2.4919441460794847e-05,
"loss": 0.0441,
"step": 729
},
{
"epoch": 71.22,
"learning_rate": 2.4812030075187968e-05,
"loss": 0.0367,
"step": 730
},
{
"epoch": 71.32,
"learning_rate": 2.4704618689581096e-05,
"loss": 0.0316,
"step": 731
},
{
"epoch": 71.41,
"learning_rate": 2.4597207303974224e-05,
"loss": 0.0361,
"step": 732
},
{
"epoch": 71.51,
"learning_rate": 2.448979591836735e-05,
"loss": 0.0398,
"step": 733
},
{
"epoch": 71.61,
"learning_rate": 2.4382384532760473e-05,
"loss": 0.0391,
"step": 734
},
{
"epoch": 71.71,
"learning_rate": 2.4274973147153597e-05,
"loss": 0.0434,
"step": 735
},
{
"epoch": 71.8,
"learning_rate": 2.4167561761546725e-05,
"loss": 0.0479,
"step": 736
},
{
"epoch": 71.9,
"learning_rate": 2.406015037593985e-05,
"loss": 0.0417,
"step": 737
},
{
"epoch": 72.0,
"learning_rate": 2.3952738990332978e-05,
"loss": 0.0381,
"step": 738
},
{
"epoch": 72.1,
"learning_rate": 2.3845327604726102e-05,
"loss": 0.0417,
"step": 739
},
{
"epoch": 72.2,
"learning_rate": 2.3737916219119226e-05,
"loss": 0.0459,
"step": 740
},
{
"epoch": 72.29,
"learning_rate": 2.3630504833512354e-05,
"loss": 0.0428,
"step": 741
},
{
"epoch": 72.39,
"learning_rate": 2.352309344790548e-05,
"loss": 0.0369,
"step": 742
},
{
"epoch": 72.49,
"learning_rate": 2.3415682062298607e-05,
"loss": 0.0362,
"step": 743
},
{
"epoch": 72.59,
"learning_rate": 2.3308270676691728e-05,
"loss": 0.0306,
"step": 744
},
{
"epoch": 72.68,
"learning_rate": 2.3200859291084856e-05,
"loss": 0.0389,
"step": 745
},
{
"epoch": 72.78,
"learning_rate": 2.3093447905477984e-05,
"loss": 0.0442,
"step": 746
},
{
"epoch": 72.88,
"learning_rate": 2.2986036519871108e-05,
"loss": 0.0395,
"step": 747
},
{
"epoch": 72.98,
"learning_rate": 2.2878625134264232e-05,
"loss": 0.034,
"step": 748
},
{
"epoch": 73.07,
"learning_rate": 2.2771213748657357e-05,
"loss": 0.0366,
"step": 749
},
{
"epoch": 73.17,
"learning_rate": 2.2663802363050485e-05,
"loss": 0.0456,
"step": 750
},
{
"epoch": 73.27,
"learning_rate": 2.255639097744361e-05,
"loss": 0.0399,
"step": 751
},
{
"epoch": 73.37,
"learning_rate": 2.2448979591836737e-05,
"loss": 0.0426,
"step": 752
},
{
"epoch": 73.46,
"learning_rate": 2.234156820622986e-05,
"loss": 0.0329,
"step": 753
},
{
"epoch": 73.56,
"learning_rate": 2.2234156820622986e-05,
"loss": 0.0377,
"step": 754
},
{
"epoch": 73.66,
"learning_rate": 2.2126745435016114e-05,
"loss": 0.0244,
"step": 755
},
{
"epoch": 73.76,
"learning_rate": 2.201933404940924e-05,
"loss": 0.0383,
"step": 756
},
{
"epoch": 73.85,
"learning_rate": 2.1911922663802363e-05,
"loss": 0.041,
"step": 757
},
{
"epoch": 73.95,
"learning_rate": 2.1804511278195487e-05,
"loss": 0.0498,
"step": 758
},
{
"epoch": 74.05,
"learning_rate": 2.1697099892588615e-05,
"loss": 0.0377,
"step": 759
},
{
"epoch": 74.15,
"learning_rate": 2.1589688506981743e-05,
"loss": 0.0317,
"step": 760
},
{
"epoch": 74.24,
"learning_rate": 2.1482277121374868e-05,
"loss": 0.0462,
"step": 761
},
{
"epoch": 74.34,
"learning_rate": 2.1374865735767992e-05,
"loss": 0.0387,
"step": 762
},
{
"epoch": 74.44,
"learning_rate": 2.1267454350161117e-05,
"loss": 0.0412,
"step": 763
},
{
"epoch": 74.54,
"learning_rate": 2.1160042964554244e-05,
"loss": 0.0319,
"step": 764
},
{
"epoch": 74.63,
"learning_rate": 2.105263157894737e-05,
"loss": 0.025,
"step": 765
},
{
"epoch": 74.73,
"learning_rate": 2.0945220193340497e-05,
"loss": 0.0445,
"step": 766
},
{
"epoch": 74.83,
"learning_rate": 2.083780880773362e-05,
"loss": 0.0367,
"step": 767
},
{
"epoch": 74.93,
"learning_rate": 2.0730397422126746e-05,
"loss": 0.0354,
"step": 768
},
{
"epoch": 75.02,
"learning_rate": 2.0622986036519874e-05,
"loss": 0.0428,
"step": 769
},
{
"epoch": 75.12,
"learning_rate": 2.0515574650912998e-05,
"loss": 0.0408,
"step": 770
},
{
"epoch": 75.22,
"learning_rate": 2.0408163265306123e-05,
"loss": 0.045,
"step": 771
},
{
"epoch": 75.32,
"learning_rate": 2.0300751879699247e-05,
"loss": 0.0378,
"step": 772
},
{
"epoch": 75.41,
"learning_rate": 2.0193340494092375e-05,
"loss": 0.0416,
"step": 773
},
{
"epoch": 75.51,
"learning_rate": 2.0085929108485503e-05,
"loss": 0.0447,
"step": 774
},
{
"epoch": 75.61,
"learning_rate": 1.9978517722878627e-05,
"loss": 0.0421,
"step": 775
},
{
"epoch": 75.71,
"learning_rate": 1.987110633727175e-05,
"loss": 0.0268,
"step": 776
},
{
"epoch": 75.8,
"learning_rate": 1.9763694951664876e-05,
"loss": 0.0348,
"step": 777
},
{
"epoch": 75.9,
"learning_rate": 1.9656283566058004e-05,
"loss": 0.0394,
"step": 778
},
{
"epoch": 76.0,
"learning_rate": 1.954887218045113e-05,
"loss": 0.0328,
"step": 779
},
{
"epoch": 76.1,
"learning_rate": 1.9441460794844253e-05,
"loss": 0.0398,
"step": 780
},
{
"epoch": 76.2,
"learning_rate": 1.933404940923738e-05,
"loss": 0.0417,
"step": 781
},
{
"epoch": 76.29,
"learning_rate": 1.9226638023630505e-05,
"loss": 0.0492,
"step": 782
},
{
"epoch": 76.39,
"learning_rate": 1.9119226638023633e-05,
"loss": 0.0359,
"step": 783
},
{
"epoch": 76.49,
"learning_rate": 1.9011815252416758e-05,
"loss": 0.03,
"step": 784
},
{
"epoch": 76.59,
"learning_rate": 1.8904403866809882e-05,
"loss": 0.0407,
"step": 785
},
{
"epoch": 76.68,
"learning_rate": 1.8796992481203007e-05,
"loss": 0.0344,
"step": 786
},
{
"epoch": 76.78,
"learning_rate": 1.8689581095596134e-05,
"loss": 0.0285,
"step": 787
},
{
"epoch": 76.88,
"learning_rate": 1.8582169709989262e-05,
"loss": 0.0512,
"step": 788
},
{
"epoch": 76.98,
"learning_rate": 1.8474758324382387e-05,
"loss": 0.0485,
"step": 789
},
{
"epoch": 77.07,
"learning_rate": 1.836734693877551e-05,
"loss": 0.0348,
"step": 790
},
{
"epoch": 77.17,
"learning_rate": 1.8259935553168636e-05,
"loss": 0.0319,
"step": 791
},
{
"epoch": 77.27,
"learning_rate": 1.8152524167561764e-05,
"loss": 0.0302,
"step": 792
},
{
"epoch": 77.37,
"learning_rate": 1.8045112781954888e-05,
"loss": 0.0491,
"step": 793
},
{
"epoch": 77.46,
"learning_rate": 1.7937701396348013e-05,
"loss": 0.0336,
"step": 794
},
{
"epoch": 77.56,
"learning_rate": 1.7830290010741137e-05,
"loss": 0.0432,
"step": 795
},
{
"epoch": 77.66,
"learning_rate": 1.7722878625134265e-05,
"loss": 0.0321,
"step": 796
},
{
"epoch": 77.76,
"learning_rate": 1.7615467239527393e-05,
"loss": 0.0389,
"step": 797
},
{
"epoch": 77.85,
"learning_rate": 1.7508055853920517e-05,
"loss": 0.0433,
"step": 798
},
{
"epoch": 77.95,
"learning_rate": 1.7400644468313642e-05,
"loss": 0.0397,
"step": 799
},
{
"epoch": 78.05,
"learning_rate": 1.7293233082706766e-05,
"loss": 0.0419,
"step": 800
},
{
"epoch": 78.15,
"learning_rate": 1.7185821697099894e-05,
"loss": 0.0413,
"step": 801
},
{
"epoch": 78.24,
"learning_rate": 1.707841031149302e-05,
"loss": 0.0339,
"step": 802
},
{
"epoch": 78.34,
"learning_rate": 1.6970998925886143e-05,
"loss": 0.0331,
"step": 803
},
{
"epoch": 78.44,
"learning_rate": 1.686358754027927e-05,
"loss": 0.0343,
"step": 804
},
{
"epoch": 78.54,
"learning_rate": 1.6756176154672395e-05,
"loss": 0.0408,
"step": 805
},
{
"epoch": 78.63,
"learning_rate": 1.6648764769065523e-05,
"loss": 0.0478,
"step": 806
},
{
"epoch": 78.73,
"learning_rate": 1.6541353383458648e-05,
"loss": 0.0445,
"step": 807
},
{
"epoch": 78.83,
"learning_rate": 1.6433941997851772e-05,
"loss": 0.0465,
"step": 808
},
{
"epoch": 78.93,
"learning_rate": 1.6326530612244897e-05,
"loss": 0.0468,
"step": 809
},
{
"epoch": 79.02,
"learning_rate": 1.6219119226638025e-05,
"loss": 0.0374,
"step": 810
},
{
"epoch": 79.12,
"learning_rate": 1.6111707841031152e-05,
"loss": 0.036,
"step": 811
},
{
"epoch": 79.22,
"learning_rate": 1.6004296455424277e-05,
"loss": 0.0452,
"step": 812
},
{
"epoch": 79.32,
"learning_rate": 1.58968850698174e-05,
"loss": 0.0301,
"step": 813
},
{
"epoch": 79.41,
"learning_rate": 1.5789473684210526e-05,
"loss": 0.0444,
"step": 814
},
{
"epoch": 79.51,
"learning_rate": 1.5682062298603654e-05,
"loss": 0.0404,
"step": 815
},
{
"epoch": 79.61,
"learning_rate": 1.5574650912996778e-05,
"loss": 0.0381,
"step": 816
},
{
"epoch": 79.71,
"learning_rate": 1.5467239527389903e-05,
"loss": 0.0359,
"step": 817
},
{
"epoch": 79.8,
"learning_rate": 1.535982814178303e-05,
"loss": 0.0418,
"step": 818
},
{
"epoch": 79.9,
"learning_rate": 1.5252416756176155e-05,
"loss": 0.0438,
"step": 819
},
{
"epoch": 80.0,
"learning_rate": 1.5145005370569281e-05,
"loss": 0.0445,
"step": 820
},
{
"epoch": 80.1,
"learning_rate": 1.5037593984962406e-05,
"loss": 0.0372,
"step": 821
},
{
"epoch": 80.2,
"learning_rate": 1.4930182599355533e-05,
"loss": 0.0434,
"step": 822
},
{
"epoch": 80.29,
"learning_rate": 1.4822771213748656e-05,
"loss": 0.0461,
"step": 823
},
{
"epoch": 80.39,
"learning_rate": 1.4715359828141784e-05,
"loss": 0.0325,
"step": 824
},
{
"epoch": 80.49,
"learning_rate": 1.460794844253491e-05,
"loss": 0.0371,
"step": 825
},
{
"epoch": 80.59,
"learning_rate": 1.4500537056928035e-05,
"loss": 0.034,
"step": 826
},
{
"epoch": 80.68,
"learning_rate": 1.4393125671321161e-05,
"loss": 0.04,
"step": 827
},
{
"epoch": 80.78,
"learning_rate": 1.4285714285714285e-05,
"loss": 0.0485,
"step": 828
},
{
"epoch": 80.88,
"learning_rate": 1.4178302900107413e-05,
"loss": 0.0474,
"step": 829
},
{
"epoch": 80.98,
"learning_rate": 1.4070891514500536e-05,
"loss": 0.0419,
"step": 830
},
{
"epoch": 81.07,
"learning_rate": 1.3963480128893664e-05,
"loss": 0.0426,
"step": 831
},
{
"epoch": 81.17,
"learning_rate": 1.385606874328679e-05,
"loss": 0.0333,
"step": 832
},
{
"epoch": 81.27,
"learning_rate": 1.3748657357679915e-05,
"loss": 0.0312,
"step": 833
},
{
"epoch": 81.37,
"learning_rate": 1.364124597207304e-05,
"loss": 0.0285,
"step": 834
},
{
"epoch": 81.46,
"learning_rate": 1.3533834586466165e-05,
"loss": 0.0352,
"step": 835
},
{
"epoch": 81.56,
"learning_rate": 1.3426423200859291e-05,
"loss": 0.0344,
"step": 836
},
{
"epoch": 81.66,
"learning_rate": 1.3319011815252416e-05,
"loss": 0.0372,
"step": 837
},
{
"epoch": 81.76,
"learning_rate": 1.3211600429645544e-05,
"loss": 0.0389,
"step": 838
},
{
"epoch": 81.85,
"learning_rate": 1.310418904403867e-05,
"loss": 0.0275,
"step": 839
},
{
"epoch": 81.95,
"learning_rate": 1.2996777658431794e-05,
"loss": 0.0322,
"step": 840
},
{
"epoch": 82.05,
"learning_rate": 1.288936627282492e-05,
"loss": 0.045,
"step": 841
},
{
"epoch": 82.15,
"learning_rate": 1.2781954887218045e-05,
"loss": 0.0419,
"step": 842
},
{
"epoch": 82.24,
"learning_rate": 1.2674543501611171e-05,
"loss": 0.0214,
"step": 843
},
{
"epoch": 82.34,
"learning_rate": 1.2567132116004296e-05,
"loss": 0.0352,
"step": 844
},
{
"epoch": 82.44,
"learning_rate": 1.2459720730397424e-05,
"loss": 0.0358,
"step": 845
},
{
"epoch": 82.54,
"learning_rate": 1.2352309344790548e-05,
"loss": 0.0385,
"step": 846
},
{
"epoch": 82.63,
"learning_rate": 1.2244897959183674e-05,
"loss": 0.0476,
"step": 847
},
{
"epoch": 82.73,
"learning_rate": 1.2137486573576799e-05,
"loss": 0.0393,
"step": 848
},
{
"epoch": 82.83,
"learning_rate": 1.2030075187969925e-05,
"loss": 0.0384,
"step": 849
},
{
"epoch": 82.93,
"learning_rate": 1.1922663802363051e-05,
"loss": 0.0342,
"step": 850
},
{
"epoch": 83.02,
"learning_rate": 1.1815252416756177e-05,
"loss": 0.0346,
"step": 851
},
{
"epoch": 83.12,
"learning_rate": 1.1707841031149303e-05,
"loss": 0.0526,
"step": 852
},
{
"epoch": 83.22,
"learning_rate": 1.1600429645542428e-05,
"loss": 0.042,
"step": 853
},
{
"epoch": 83.32,
"learning_rate": 1.1493018259935554e-05,
"loss": 0.0382,
"step": 854
},
{
"epoch": 83.41,
"learning_rate": 1.1385606874328678e-05,
"loss": 0.0403,
"step": 855
},
{
"epoch": 83.51,
"learning_rate": 1.1278195488721805e-05,
"loss": 0.0317,
"step": 856
},
{
"epoch": 83.61,
"learning_rate": 1.117078410311493e-05,
"loss": 0.0445,
"step": 857
},
{
"epoch": 83.71,
"learning_rate": 1.1063372717508057e-05,
"loss": 0.0392,
"step": 858
},
{
"epoch": 83.8,
"learning_rate": 1.0955961331901181e-05,
"loss": 0.0408,
"step": 859
},
{
"epoch": 83.9,
"learning_rate": 1.0848549946294308e-05,
"loss": 0.0379,
"step": 860
},
{
"epoch": 84.0,
"learning_rate": 1.0741138560687434e-05,
"loss": 0.0275,
"step": 861
},
{
"epoch": 84.1,
"learning_rate": 1.0633727175080558e-05,
"loss": 0.0435,
"step": 862
},
{
"epoch": 84.2,
"learning_rate": 1.0526315789473684e-05,
"loss": 0.0399,
"step": 863
},
{
"epoch": 84.29,
"learning_rate": 1.041890440386681e-05,
"loss": 0.0306,
"step": 864
},
{
"epoch": 84.39,
"learning_rate": 1.0311493018259937e-05,
"loss": 0.0275,
"step": 865
},
{
"epoch": 84.49,
"learning_rate": 1.0204081632653061e-05,
"loss": 0.0342,
"step": 866
},
{
"epoch": 84.59,
"learning_rate": 1.0096670247046187e-05,
"loss": 0.0396,
"step": 867
},
{
"epoch": 84.68,
"learning_rate": 9.989258861439314e-06,
"loss": 0.0327,
"step": 868
},
{
"epoch": 84.78,
"learning_rate": 9.881847475832438e-06,
"loss": 0.0447,
"step": 869
},
{
"epoch": 84.88,
"learning_rate": 9.774436090225564e-06,
"loss": 0.0315,
"step": 870
},
{
"epoch": 84.98,
"learning_rate": 9.66702470461869e-06,
"loss": 0.0339,
"step": 871
},
{
"epoch": 85.07,
"learning_rate": 9.559613319011817e-06,
"loss": 0.0329,
"step": 872
},
{
"epoch": 85.17,
"learning_rate": 9.452201933404941e-06,
"loss": 0.0374,
"step": 873
},
{
"epoch": 85.27,
"learning_rate": 9.344790547798067e-06,
"loss": 0.0471,
"step": 874
},
{
"epoch": 85.37,
"learning_rate": 9.237379162191193e-06,
"loss": 0.0373,
"step": 875
},
{
"epoch": 85.46,
"learning_rate": 9.129967776584318e-06,
"loss": 0.0432,
"step": 876
},
{
"epoch": 85.56,
"learning_rate": 9.022556390977444e-06,
"loss": 0.0435,
"step": 877
},
{
"epoch": 85.66,
"learning_rate": 8.915145005370569e-06,
"loss": 0.0346,
"step": 878
},
{
"epoch": 85.76,
"learning_rate": 8.807733619763696e-06,
"loss": 0.0429,
"step": 879
},
{
"epoch": 85.85,
"learning_rate": 8.700322234156821e-06,
"loss": 0.0514,
"step": 880
},
{
"epoch": 85.95,
"learning_rate": 8.592910848549947e-06,
"loss": 0.0404,
"step": 881
},
{
"epoch": 86.05,
"learning_rate": 8.485499462943072e-06,
"loss": 0.0403,
"step": 882
},
{
"epoch": 86.15,
"learning_rate": 8.378088077336198e-06,
"loss": 0.0325,
"step": 883
},
{
"epoch": 86.24,
"learning_rate": 8.270676691729324e-06,
"loss": 0.0298,
"step": 884
},
{
"epoch": 86.34,
"learning_rate": 8.163265306122448e-06,
"loss": 0.0376,
"step": 885
},
{
"epoch": 86.44,
"learning_rate": 8.055853920515576e-06,
"loss": 0.0401,
"step": 886
},
{
"epoch": 86.54,
"learning_rate": 7.9484425349087e-06,
"loss": 0.0338,
"step": 887
},
{
"epoch": 86.63,
"learning_rate": 7.841031149301827e-06,
"loss": 0.0376,
"step": 888
},
{
"epoch": 86.73,
"learning_rate": 7.733619763694951e-06,
"loss": 0.0382,
"step": 889
},
{
"epoch": 86.83,
"learning_rate": 7.6262083780880775e-06,
"loss": 0.0454,
"step": 890
},
{
"epoch": 86.93,
"learning_rate": 7.518796992481203e-06,
"loss": 0.0386,
"step": 891
},
{
"epoch": 87.02,
"learning_rate": 7.411385606874328e-06,
"loss": 0.0403,
"step": 892
},
{
"epoch": 87.12,
"learning_rate": 7.303974221267455e-06,
"loss": 0.041,
"step": 893
},
{
"epoch": 87.22,
"learning_rate": 7.1965628356605805e-06,
"loss": 0.0359,
"step": 894
},
{
"epoch": 87.32,
"learning_rate": 7.089151450053707e-06,
"loss": 0.0427,
"step": 895
},
{
"epoch": 87.41,
"learning_rate": 6.981740064446832e-06,
"loss": 0.0384,
"step": 896
},
{
"epoch": 87.51,
"learning_rate": 6.874328678839957e-06,
"loss": 0.0411,
"step": 897
},
{
"epoch": 87.61,
"learning_rate": 6.766917293233083e-06,
"loss": 0.0391,
"step": 898
},
{
"epoch": 87.71,
"learning_rate": 6.659505907626208e-06,
"loss": 0.0408,
"step": 899
},
{
"epoch": 87.8,
"learning_rate": 6.552094522019335e-06,
"loss": 0.0295,
"step": 900
},
{
"epoch": 87.9,
"learning_rate": 6.44468313641246e-06,
"loss": 0.0373,
"step": 901
},
{
"epoch": 88.0,
"learning_rate": 6.337271750805586e-06,
"loss": 0.029,
"step": 902
},
{
"epoch": 88.1,
"learning_rate": 6.229860365198712e-06,
"loss": 0.0452,
"step": 903
},
{
"epoch": 88.2,
"learning_rate": 6.122448979591837e-06,
"loss": 0.0365,
"step": 904
},
{
"epoch": 88.29,
"learning_rate": 6.015037593984962e-06,
"loss": 0.037,
"step": 905
},
{
"epoch": 88.39,
"learning_rate": 5.907626208378089e-06,
"loss": 0.0364,
"step": 906
},
{
"epoch": 88.49,
"learning_rate": 5.800214822771214e-06,
"loss": 0.0403,
"step": 907
},
{
"epoch": 88.59,
"learning_rate": 5.692803437164339e-06,
"loss": 0.0344,
"step": 908
},
{
"epoch": 88.68,
"learning_rate": 5.585392051557465e-06,
"loss": 0.0264,
"step": 909
},
{
"epoch": 88.78,
"learning_rate": 5.477980665950591e-06,
"loss": 0.0362,
"step": 910
},
{
"epoch": 88.88,
"learning_rate": 5.370569280343717e-06,
"loss": 0.0449,
"step": 911
},
{
"epoch": 88.98,
"learning_rate": 5.263157894736842e-06,
"loss": 0.0312,
"step": 912
},
{
"epoch": 89.07,
"learning_rate": 5.155746509129968e-06,
"loss": 0.0375,
"step": 913
},
{
"epoch": 89.17,
"learning_rate": 5.048335123523094e-06,
"loss": 0.0345,
"step": 914
},
{
"epoch": 89.27,
"learning_rate": 4.940923737916219e-06,
"loss": 0.0326,
"step": 915
},
{
"epoch": 89.37,
"learning_rate": 4.833512352309345e-06,
"loss": 0.0403,
"step": 916
},
{
"epoch": 89.46,
"learning_rate": 4.7261009667024705e-06,
"loss": 0.0323,
"step": 917
},
{
"epoch": 89.56,
"learning_rate": 4.618689581095597e-06,
"loss": 0.036,
"step": 918
},
{
"epoch": 89.66,
"learning_rate": 4.511278195488722e-06,
"loss": 0.037,
"step": 919
},
{
"epoch": 89.76,
"learning_rate": 4.403866809881848e-06,
"loss": 0.0356,
"step": 920
},
{
"epoch": 89.85,
"learning_rate": 4.2964554242749735e-06,
"loss": 0.0402,
"step": 921
},
{
"epoch": 89.95,
"learning_rate": 4.189044038668099e-06,
"loss": 0.043,
"step": 922
},
{
"epoch": 90.05,
"learning_rate": 4.081632653061224e-06,
"loss": 0.0361,
"step": 923
},
{
"epoch": 90.15,
"learning_rate": 3.97422126745435e-06,
"loss": 0.045,
"step": 924
},
{
"epoch": 90.24,
"learning_rate": 3.866809881847476e-06,
"loss": 0.0268,
"step": 925
},
{
"epoch": 90.34,
"learning_rate": 3.7593984962406014e-06,
"loss": 0.0413,
"step": 926
},
{
"epoch": 90.44,
"learning_rate": 3.6519871106337276e-06,
"loss": 0.038,
"step": 927
},
{
"epoch": 90.54,
"learning_rate": 3.5445757250268533e-06,
"loss": 0.0427,
"step": 928
},
{
"epoch": 90.63,
"learning_rate": 3.4371643394199786e-06,
"loss": 0.0333,
"step": 929
},
{
"epoch": 90.73,
"learning_rate": 3.329752953813104e-06,
"loss": 0.0301,
"step": 930
},
{
"epoch": 90.83,
"learning_rate": 3.22234156820623e-06,
"loss": 0.0324,
"step": 931
},
{
"epoch": 90.93,
"learning_rate": 3.114930182599356e-06,
"loss": 0.0308,
"step": 932
},
{
"epoch": 91.02,
"learning_rate": 3.007518796992481e-06,
"loss": 0.0349,
"step": 933
},
{
"epoch": 91.12,
"learning_rate": 2.900107411385607e-06,
"loss": 0.0359,
"step": 934
},
{
"epoch": 91.22,
"learning_rate": 2.7926960257787327e-06,
"loss": 0.0403,
"step": 935
},
{
"epoch": 91.32,
"learning_rate": 2.6852846401718585e-06,
"loss": 0.0327,
"step": 936
},
{
"epoch": 91.41,
"learning_rate": 2.577873254564984e-06,
"loss": 0.032,
"step": 937
},
{
"epoch": 91.51,
"learning_rate": 2.4704618689581095e-06,
"loss": 0.0453,
"step": 938
},
{
"epoch": 91.61,
"learning_rate": 2.3630504833512353e-06,
"loss": 0.0428,
"step": 939
},
{
"epoch": 91.71,
"learning_rate": 2.255639097744361e-06,
"loss": 0.0399,
"step": 940
},
{
"epoch": 91.8,
"learning_rate": 2.1482277121374868e-06,
"loss": 0.04,
"step": 941
},
{
"epoch": 91.9,
"learning_rate": 2.040816326530612e-06,
"loss": 0.0383,
"step": 942
},
{
"epoch": 92.0,
"learning_rate": 1.933404940923738e-06,
"loss": 0.038,
"step": 943
},
{
"epoch": 92.1,
"learning_rate": 1.8259935553168638e-06,
"loss": 0.0415,
"step": 944
},
{
"epoch": 92.2,
"learning_rate": 1.7185821697099893e-06,
"loss": 0.0318,
"step": 945
},
{
"epoch": 92.29,
"learning_rate": 1.611170784103115e-06,
"loss": 0.037,
"step": 946
},
{
"epoch": 92.39,
"learning_rate": 1.5037593984962406e-06,
"loss": 0.035,
"step": 947
},
{
"epoch": 92.49,
"learning_rate": 1.3963480128893664e-06,
"loss": 0.0415,
"step": 948
},
{
"epoch": 92.59,
"learning_rate": 1.288936627282492e-06,
"loss": 0.0315,
"step": 949
},
{
"epoch": 92.68,
"learning_rate": 1.1815252416756176e-06,
"loss": 0.048,
"step": 950
},
{
"epoch": 92.78,
"learning_rate": 1.0741138560687434e-06,
"loss": 0.0376,
"step": 951
},
{
"epoch": 92.88,
"learning_rate": 9.66702470461869e-07,
"loss": 0.0377,
"step": 952
},
{
"epoch": 92.98,
"learning_rate": 8.592910848549947e-07,
"loss": 0.0456,
"step": 953
},
{
"epoch": 93.07,
"learning_rate": 7.518796992481203e-07,
"loss": 0.0427,
"step": 954
},
{
"epoch": 93.17,
"learning_rate": 6.44468313641246e-07,
"loss": 0.049,
"step": 955
},
{
"epoch": 93.27,
"learning_rate": 5.370569280343717e-07,
"loss": 0.0424,
"step": 956
},
{
"epoch": 93.37,
"learning_rate": 4.2964554242749733e-07,
"loss": 0.042,
"step": 957
},
{
"epoch": 93.46,
"learning_rate": 3.22234156820623e-07,
"loss": 0.0408,
"step": 958
},
{
"epoch": 93.56,
"learning_rate": 2.1482277121374867e-07,
"loss": 0.0424,
"step": 959
},
{
"epoch": 93.66,
"learning_rate": 1.0741138560687433e-07,
"loss": 0.0366,
"step": 960
},
{
"epoch": 93.66,
"step": 960,
"total_flos": 0.0,
"train_loss": 0.0827180000313092,
"train_runtime": 19244.8754,
"train_samples_per_second": 6.515,
"train_steps_per_second": 0.05
}
],
"logging_steps": 1.0,
"max_steps": 960,
"num_input_tokens_seen": 0,
"num_train_epochs": 96,
"save_steps": -960,
"total_flos": 0.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}