dima806's picture
Upload folder using huggingface_hub
e555e79
{
"best_metric": 1.180140495300293,
"best_model_checkpoint": "classical_composer_classification/checkpoint-1005",
"epoch": 15.0,
"global_step": 1005,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 1.0000000000000001e-07,
"loss": 1.6203,
"step": 1
},
{
"epoch": 0.03,
"learning_rate": 2.0000000000000002e-07,
"loss": 1.611,
"step": 2
},
{
"epoch": 0.04,
"learning_rate": 3.0000000000000004e-07,
"loss": 1.6066,
"step": 3
},
{
"epoch": 0.06,
"learning_rate": 4.0000000000000003e-07,
"loss": 1.6033,
"step": 4
},
{
"epoch": 0.07,
"learning_rate": 5.000000000000001e-07,
"loss": 1.6006,
"step": 5
},
{
"epoch": 0.09,
"learning_rate": 6.000000000000001e-07,
"loss": 1.6104,
"step": 6
},
{
"epoch": 0.1,
"learning_rate": 7.000000000000001e-07,
"loss": 1.6163,
"step": 7
},
{
"epoch": 0.12,
"learning_rate": 8.000000000000001e-07,
"loss": 1.6205,
"step": 8
},
{
"epoch": 0.13,
"learning_rate": 9.000000000000001e-07,
"loss": 1.6081,
"step": 9
},
{
"epoch": 0.15,
"learning_rate": 1.0000000000000002e-06,
"loss": 1.6039,
"step": 10
},
{
"epoch": 0.16,
"learning_rate": 1.1e-06,
"loss": 1.6157,
"step": 11
},
{
"epoch": 0.18,
"learning_rate": 1.2000000000000002e-06,
"loss": 1.6045,
"step": 12
},
{
"epoch": 0.19,
"learning_rate": 1.3e-06,
"loss": 1.6093,
"step": 13
},
{
"epoch": 0.21,
"learning_rate": 1.4000000000000001e-06,
"loss": 1.6137,
"step": 14
},
{
"epoch": 0.22,
"learning_rate": 1.5e-06,
"loss": 1.6035,
"step": 15
},
{
"epoch": 0.24,
"learning_rate": 1.6000000000000001e-06,
"loss": 1.6207,
"step": 16
},
{
"epoch": 0.25,
"learning_rate": 1.7000000000000002e-06,
"loss": 1.6017,
"step": 17
},
{
"epoch": 0.27,
"learning_rate": 1.8000000000000001e-06,
"loss": 1.6471,
"step": 18
},
{
"epoch": 0.28,
"learning_rate": 1.9000000000000002e-06,
"loss": 1.6058,
"step": 19
},
{
"epoch": 0.3,
"learning_rate": 2.0000000000000003e-06,
"loss": 1.6073,
"step": 20
},
{
"epoch": 0.31,
"learning_rate": 2.1000000000000002e-06,
"loss": 1.6206,
"step": 21
},
{
"epoch": 0.33,
"learning_rate": 2.2e-06,
"loss": 1.6173,
"step": 22
},
{
"epoch": 0.34,
"learning_rate": 2.3000000000000004e-06,
"loss": 1.6106,
"step": 23
},
{
"epoch": 0.36,
"learning_rate": 2.4000000000000003e-06,
"loss": 1.606,
"step": 24
},
{
"epoch": 0.37,
"learning_rate": 2.5e-06,
"loss": 1.6096,
"step": 25
},
{
"epoch": 0.39,
"learning_rate": 2.6e-06,
"loss": 1.6042,
"step": 26
},
{
"epoch": 0.4,
"learning_rate": 2.7000000000000004e-06,
"loss": 1.6105,
"step": 27
},
{
"epoch": 0.42,
"learning_rate": 2.8000000000000003e-06,
"loss": 1.6128,
"step": 28
},
{
"epoch": 0.43,
"learning_rate": 2.9e-06,
"loss": 1.6039,
"step": 29
},
{
"epoch": 0.45,
"learning_rate": 3e-06,
"loss": 1.6105,
"step": 30
},
{
"epoch": 0.46,
"learning_rate": 3.1000000000000004e-06,
"loss": 1.5976,
"step": 31
},
{
"epoch": 0.48,
"learning_rate": 3.2000000000000003e-06,
"loss": 1.5883,
"step": 32
},
{
"epoch": 0.49,
"learning_rate": 3.3000000000000006e-06,
"loss": 1.6045,
"step": 33
},
{
"epoch": 0.51,
"learning_rate": 3.4000000000000005e-06,
"loss": 1.5963,
"step": 34
},
{
"epoch": 0.52,
"learning_rate": 3.5e-06,
"loss": 1.6007,
"step": 35
},
{
"epoch": 0.54,
"learning_rate": 3.6000000000000003e-06,
"loss": 1.6223,
"step": 36
},
{
"epoch": 0.55,
"learning_rate": 3.7e-06,
"loss": 1.5988,
"step": 37
},
{
"epoch": 0.57,
"learning_rate": 3.8000000000000005e-06,
"loss": 1.6182,
"step": 38
},
{
"epoch": 0.58,
"learning_rate": 3.900000000000001e-06,
"loss": 1.6118,
"step": 39
},
{
"epoch": 0.6,
"learning_rate": 4.000000000000001e-06,
"loss": 1.6125,
"step": 40
},
{
"epoch": 0.61,
"learning_rate": 4.1e-06,
"loss": 1.587,
"step": 41
},
{
"epoch": 0.63,
"learning_rate": 4.2000000000000004e-06,
"loss": 1.6084,
"step": 42
},
{
"epoch": 0.64,
"learning_rate": 4.3e-06,
"loss": 1.6098,
"step": 43
},
{
"epoch": 0.66,
"learning_rate": 4.4e-06,
"loss": 1.6195,
"step": 44
},
{
"epoch": 0.67,
"learning_rate": 4.5e-06,
"loss": 1.6018,
"step": 45
},
{
"epoch": 0.69,
"learning_rate": 4.600000000000001e-06,
"loss": 1.6226,
"step": 46
},
{
"epoch": 0.7,
"learning_rate": 4.7e-06,
"loss": 1.6124,
"step": 47
},
{
"epoch": 0.72,
"learning_rate": 4.800000000000001e-06,
"loss": 1.6075,
"step": 48
},
{
"epoch": 0.73,
"learning_rate": 4.9000000000000005e-06,
"loss": 1.598,
"step": 49
},
{
"epoch": 0.75,
"learning_rate": 5e-06,
"loss": 1.5968,
"step": 50
},
{
"epoch": 0.76,
"learning_rate": 4.99476439790576e-06,
"loss": 1.6453,
"step": 51
},
{
"epoch": 0.78,
"learning_rate": 4.989528795811518e-06,
"loss": 1.5927,
"step": 52
},
{
"epoch": 0.79,
"learning_rate": 4.984293193717278e-06,
"loss": 1.6027,
"step": 53
},
{
"epoch": 0.81,
"learning_rate": 4.979057591623037e-06,
"loss": 1.6153,
"step": 54
},
{
"epoch": 0.82,
"learning_rate": 4.9738219895287965e-06,
"loss": 1.6048,
"step": 55
},
{
"epoch": 0.84,
"learning_rate": 4.968586387434555e-06,
"loss": 1.5814,
"step": 56
},
{
"epoch": 0.85,
"learning_rate": 4.963350785340314e-06,
"loss": 1.5994,
"step": 57
},
{
"epoch": 0.87,
"learning_rate": 4.958115183246074e-06,
"loss": 1.5917,
"step": 58
},
{
"epoch": 0.88,
"learning_rate": 4.952879581151832e-06,
"loss": 1.619,
"step": 59
},
{
"epoch": 0.9,
"learning_rate": 4.947643979057592e-06,
"loss": 1.6093,
"step": 60
},
{
"epoch": 0.91,
"learning_rate": 4.942408376963351e-06,
"loss": 1.5972,
"step": 61
},
{
"epoch": 0.93,
"learning_rate": 4.9371727748691105e-06,
"loss": 1.6112,
"step": 62
},
{
"epoch": 0.94,
"learning_rate": 4.931937172774869e-06,
"loss": 1.6086,
"step": 63
},
{
"epoch": 0.96,
"learning_rate": 4.926701570680628e-06,
"loss": 1.6005,
"step": 64
},
{
"epoch": 0.97,
"learning_rate": 4.921465968586388e-06,
"loss": 1.6032,
"step": 65
},
{
"epoch": 0.99,
"learning_rate": 4.916230366492147e-06,
"loss": 1.6082,
"step": 66
},
{
"epoch": 1.0,
"learning_rate": 4.910994764397906e-06,
"loss": 1.6167,
"step": 67
},
{
"epoch": 1.0,
"eval_accuracy": 0.2835820895522388,
"eval_loss": 1.6057485342025757,
"eval_roc_auc": 0.7361035629382203,
"eval_runtime": 114.8198,
"eval_samples_per_second": 0.584,
"eval_steps_per_second": 0.584,
"step": 67
},
{
"epoch": 1.01,
"learning_rate": 4.905759162303665e-06,
"loss": 1.5778,
"step": 68
},
{
"epoch": 1.03,
"learning_rate": 4.9005235602094245e-06,
"loss": 1.6078,
"step": 69
},
{
"epoch": 1.04,
"learning_rate": 4.895287958115184e-06,
"loss": 1.6155,
"step": 70
},
{
"epoch": 1.06,
"learning_rate": 4.890052356020943e-06,
"loss": 1.6081,
"step": 71
},
{
"epoch": 1.07,
"learning_rate": 4.884816753926702e-06,
"loss": 1.615,
"step": 72
},
{
"epoch": 1.09,
"learning_rate": 4.879581151832461e-06,
"loss": 1.6057,
"step": 73
},
{
"epoch": 1.1,
"learning_rate": 4.8743455497382206e-06,
"loss": 1.6165,
"step": 74
},
{
"epoch": 1.12,
"learning_rate": 4.86910994764398e-06,
"loss": 1.5844,
"step": 75
},
{
"epoch": 1.13,
"learning_rate": 4.8638743455497385e-06,
"loss": 1.5988,
"step": 76
},
{
"epoch": 1.15,
"learning_rate": 4.858638743455498e-06,
"loss": 1.5929,
"step": 77
},
{
"epoch": 1.16,
"learning_rate": 4.853403141361257e-06,
"loss": 1.6609,
"step": 78
},
{
"epoch": 1.18,
"learning_rate": 4.848167539267017e-06,
"loss": 1.5917,
"step": 79
},
{
"epoch": 1.19,
"learning_rate": 4.842931937172775e-06,
"loss": 1.6136,
"step": 80
},
{
"epoch": 1.21,
"learning_rate": 4.837696335078535e-06,
"loss": 1.6112,
"step": 81
},
{
"epoch": 1.22,
"learning_rate": 4.832460732984294e-06,
"loss": 1.612,
"step": 82
},
{
"epoch": 1.24,
"learning_rate": 4.8272251308900525e-06,
"loss": 1.6076,
"step": 83
},
{
"epoch": 1.25,
"learning_rate": 4.821989528795812e-06,
"loss": 1.6057,
"step": 84
},
{
"epoch": 1.27,
"learning_rate": 4.816753926701571e-06,
"loss": 1.5769,
"step": 85
},
{
"epoch": 1.28,
"learning_rate": 4.811518324607331e-06,
"loss": 1.6045,
"step": 86
},
{
"epoch": 1.3,
"learning_rate": 4.806282722513089e-06,
"loss": 1.602,
"step": 87
},
{
"epoch": 1.31,
"learning_rate": 4.801047120418849e-06,
"loss": 1.5942,
"step": 88
},
{
"epoch": 1.33,
"learning_rate": 4.795811518324608e-06,
"loss": 1.6149,
"step": 89
},
{
"epoch": 1.34,
"learning_rate": 4.7905759162303665e-06,
"loss": 1.5933,
"step": 90
},
{
"epoch": 1.36,
"learning_rate": 4.785340314136126e-06,
"loss": 1.6048,
"step": 91
},
{
"epoch": 1.37,
"learning_rate": 4.780104712041885e-06,
"loss": 1.6154,
"step": 92
},
{
"epoch": 1.39,
"learning_rate": 4.774869109947645e-06,
"loss": 1.5998,
"step": 93
},
{
"epoch": 1.4,
"learning_rate": 4.769633507853403e-06,
"loss": 1.6342,
"step": 94
},
{
"epoch": 1.42,
"learning_rate": 4.764397905759163e-06,
"loss": 1.6019,
"step": 95
},
{
"epoch": 1.43,
"learning_rate": 4.759162303664922e-06,
"loss": 1.6392,
"step": 96
},
{
"epoch": 1.45,
"learning_rate": 4.7539267015706805e-06,
"loss": 1.623,
"step": 97
},
{
"epoch": 1.46,
"learning_rate": 4.74869109947644e-06,
"loss": 1.6016,
"step": 98
},
{
"epoch": 1.48,
"learning_rate": 4.743455497382199e-06,
"loss": 1.613,
"step": 99
},
{
"epoch": 1.49,
"learning_rate": 4.738219895287958e-06,
"loss": 1.6087,
"step": 100
},
{
"epoch": 1.51,
"learning_rate": 4.732984293193717e-06,
"loss": 1.6022,
"step": 101
},
{
"epoch": 1.52,
"learning_rate": 4.727748691099477e-06,
"loss": 1.5927,
"step": 102
},
{
"epoch": 1.54,
"learning_rate": 4.722513089005236e-06,
"loss": 1.5968,
"step": 103
},
{
"epoch": 1.55,
"learning_rate": 4.717277486910995e-06,
"loss": 1.6018,
"step": 104
},
{
"epoch": 1.57,
"learning_rate": 4.712041884816754e-06,
"loss": 1.59,
"step": 105
},
{
"epoch": 1.58,
"learning_rate": 4.706806282722513e-06,
"loss": 1.6068,
"step": 106
},
{
"epoch": 1.6,
"learning_rate": 4.701570680628273e-06,
"loss": 1.6148,
"step": 107
},
{
"epoch": 1.61,
"learning_rate": 4.696335078534032e-06,
"loss": 1.6022,
"step": 108
},
{
"epoch": 1.63,
"learning_rate": 4.6910994764397914e-06,
"loss": 1.6399,
"step": 109
},
{
"epoch": 1.64,
"learning_rate": 4.68586387434555e-06,
"loss": 1.5989,
"step": 110
},
{
"epoch": 1.66,
"learning_rate": 4.680628272251309e-06,
"loss": 1.5946,
"step": 111
},
{
"epoch": 1.67,
"learning_rate": 4.675392670157069e-06,
"loss": 1.5955,
"step": 112
},
{
"epoch": 1.69,
"learning_rate": 4.670157068062828e-06,
"loss": 1.596,
"step": 113
},
{
"epoch": 1.7,
"learning_rate": 4.664921465968587e-06,
"loss": 1.6021,
"step": 114
},
{
"epoch": 1.72,
"learning_rate": 4.659685863874346e-06,
"loss": 1.6031,
"step": 115
},
{
"epoch": 1.73,
"learning_rate": 4.6544502617801054e-06,
"loss": 1.596,
"step": 116
},
{
"epoch": 1.75,
"learning_rate": 4.649214659685865e-06,
"loss": 1.5977,
"step": 117
},
{
"epoch": 1.76,
"learning_rate": 4.643979057591623e-06,
"loss": 1.5955,
"step": 118
},
{
"epoch": 1.78,
"learning_rate": 4.638743455497383e-06,
"loss": 1.5858,
"step": 119
},
{
"epoch": 1.79,
"learning_rate": 4.633507853403142e-06,
"loss": 1.6205,
"step": 120
},
{
"epoch": 1.81,
"learning_rate": 4.628272251308901e-06,
"loss": 1.61,
"step": 121
},
{
"epoch": 1.82,
"learning_rate": 4.62303664921466e-06,
"loss": 1.6035,
"step": 122
},
{
"epoch": 1.84,
"learning_rate": 4.6178010471204194e-06,
"loss": 1.6081,
"step": 123
},
{
"epoch": 1.85,
"learning_rate": 4.612565445026179e-06,
"loss": 1.6066,
"step": 124
},
{
"epoch": 1.87,
"learning_rate": 4.607329842931937e-06,
"loss": 1.5975,
"step": 125
},
{
"epoch": 1.88,
"learning_rate": 4.602094240837697e-06,
"loss": 1.6156,
"step": 126
},
{
"epoch": 1.9,
"learning_rate": 4.596858638743456e-06,
"loss": 1.6041,
"step": 127
},
{
"epoch": 1.91,
"learning_rate": 4.591623036649215e-06,
"loss": 1.5978,
"step": 128
},
{
"epoch": 1.93,
"learning_rate": 4.586387434554974e-06,
"loss": 1.5896,
"step": 129
},
{
"epoch": 1.94,
"learning_rate": 4.5811518324607335e-06,
"loss": 1.5947,
"step": 130
},
{
"epoch": 1.96,
"learning_rate": 4.575916230366493e-06,
"loss": 1.5916,
"step": 131
},
{
"epoch": 1.97,
"learning_rate": 4.570680628272251e-06,
"loss": 1.6138,
"step": 132
},
{
"epoch": 1.99,
"learning_rate": 4.565445026178011e-06,
"loss": 1.6157,
"step": 133
},
{
"epoch": 2.0,
"learning_rate": 4.56020942408377e-06,
"loss": 1.6005,
"step": 134
},
{
"epoch": 2.0,
"eval_accuracy": 0.2537313432835821,
"eval_loss": 1.60354745388031,
"eval_roc_auc": 0.6429349531633545,
"eval_runtime": 115.014,
"eval_samples_per_second": 0.583,
"eval_steps_per_second": 0.583,
"step": 134
},
{
"epoch": 2.01,
"learning_rate": 4.554973821989529e-06,
"loss": 1.6075,
"step": 135
},
{
"epoch": 2.03,
"learning_rate": 4.549738219895288e-06,
"loss": 1.5978,
"step": 136
},
{
"epoch": 2.04,
"learning_rate": 4.5445026178010475e-06,
"loss": 1.6135,
"step": 137
},
{
"epoch": 2.06,
"learning_rate": 4.539267015706806e-06,
"loss": 1.5899,
"step": 138
},
{
"epoch": 2.07,
"learning_rate": 4.534031413612565e-06,
"loss": 1.5957,
"step": 139
},
{
"epoch": 2.09,
"learning_rate": 4.528795811518325e-06,
"loss": 1.6034,
"step": 140
},
{
"epoch": 2.1,
"learning_rate": 4.523560209424084e-06,
"loss": 1.5991,
"step": 141
},
{
"epoch": 2.12,
"learning_rate": 4.5183246073298435e-06,
"loss": 1.5832,
"step": 142
},
{
"epoch": 2.13,
"learning_rate": 4.513089005235602e-06,
"loss": 1.6053,
"step": 143
},
{
"epoch": 2.15,
"learning_rate": 4.5078534031413615e-06,
"loss": 1.5825,
"step": 144
},
{
"epoch": 2.16,
"learning_rate": 4.502617801047121e-06,
"loss": 1.5835,
"step": 145
},
{
"epoch": 2.18,
"learning_rate": 4.49738219895288e-06,
"loss": 1.6049,
"step": 146
},
{
"epoch": 2.19,
"learning_rate": 4.492146596858639e-06,
"loss": 1.6015,
"step": 147
},
{
"epoch": 2.21,
"learning_rate": 4.486910994764398e-06,
"loss": 1.5913,
"step": 148
},
{
"epoch": 2.22,
"learning_rate": 4.4816753926701575e-06,
"loss": 1.5841,
"step": 149
},
{
"epoch": 2.24,
"learning_rate": 4.476439790575917e-06,
"loss": 1.6218,
"step": 150
},
{
"epoch": 2.25,
"learning_rate": 4.471204188481676e-06,
"loss": 1.5744,
"step": 151
},
{
"epoch": 2.27,
"learning_rate": 4.465968586387435e-06,
"loss": 1.5613,
"step": 152
},
{
"epoch": 2.28,
"learning_rate": 4.460732984293194e-06,
"loss": 1.6108,
"step": 153
},
{
"epoch": 2.3,
"learning_rate": 4.455497382198954e-06,
"loss": 1.5852,
"step": 154
},
{
"epoch": 2.31,
"learning_rate": 4.450261780104713e-06,
"loss": 1.6145,
"step": 155
},
{
"epoch": 2.33,
"learning_rate": 4.4450261780104715e-06,
"loss": 1.5974,
"step": 156
},
{
"epoch": 2.34,
"learning_rate": 4.439790575916231e-06,
"loss": 1.6123,
"step": 157
},
{
"epoch": 2.36,
"learning_rate": 4.43455497382199e-06,
"loss": 1.5875,
"step": 158
},
{
"epoch": 2.37,
"learning_rate": 4.429319371727749e-06,
"loss": 1.5957,
"step": 159
},
{
"epoch": 2.39,
"learning_rate": 4.424083769633508e-06,
"loss": 1.5734,
"step": 160
},
{
"epoch": 2.4,
"learning_rate": 4.418848167539268e-06,
"loss": 1.6153,
"step": 161
},
{
"epoch": 2.42,
"learning_rate": 4.413612565445027e-06,
"loss": 1.6366,
"step": 162
},
{
"epoch": 2.43,
"learning_rate": 4.4083769633507855e-06,
"loss": 1.6076,
"step": 163
},
{
"epoch": 2.45,
"learning_rate": 4.403141361256545e-06,
"loss": 1.5851,
"step": 164
},
{
"epoch": 2.46,
"learning_rate": 4.397905759162304e-06,
"loss": 1.5644,
"step": 165
},
{
"epoch": 2.48,
"learning_rate": 4.392670157068063e-06,
"loss": 1.592,
"step": 166
},
{
"epoch": 2.49,
"learning_rate": 4.387434554973822e-06,
"loss": 1.5731,
"step": 167
},
{
"epoch": 2.51,
"learning_rate": 4.382198952879582e-06,
"loss": 1.5703,
"step": 168
},
{
"epoch": 2.52,
"learning_rate": 4.37696335078534e-06,
"loss": 1.6144,
"step": 169
},
{
"epoch": 2.54,
"learning_rate": 4.3717277486910996e-06,
"loss": 1.6309,
"step": 170
},
{
"epoch": 2.55,
"learning_rate": 4.366492146596859e-06,
"loss": 1.6017,
"step": 171
},
{
"epoch": 2.57,
"learning_rate": 4.361256544502618e-06,
"loss": 1.5652,
"step": 172
},
{
"epoch": 2.58,
"learning_rate": 4.356020942408377e-06,
"loss": 1.5775,
"step": 173
},
{
"epoch": 2.6,
"learning_rate": 4.350785340314136e-06,
"loss": 1.5907,
"step": 174
},
{
"epoch": 2.61,
"learning_rate": 4.345549738219896e-06,
"loss": 1.6096,
"step": 175
},
{
"epoch": 2.63,
"learning_rate": 4.340314136125654e-06,
"loss": 1.5706,
"step": 176
},
{
"epoch": 2.64,
"learning_rate": 4.3350785340314136e-06,
"loss": 1.5711,
"step": 177
},
{
"epoch": 2.66,
"learning_rate": 4.329842931937173e-06,
"loss": 1.6023,
"step": 178
},
{
"epoch": 2.67,
"learning_rate": 4.324607329842932e-06,
"loss": 1.5766,
"step": 179
},
{
"epoch": 2.69,
"learning_rate": 4.319371727748692e-06,
"loss": 1.5795,
"step": 180
},
{
"epoch": 2.7,
"learning_rate": 4.31413612565445e-06,
"loss": 1.5655,
"step": 181
},
{
"epoch": 2.72,
"learning_rate": 4.30890052356021e-06,
"loss": 1.5366,
"step": 182
},
{
"epoch": 2.73,
"learning_rate": 4.303664921465969e-06,
"loss": 1.5702,
"step": 183
},
{
"epoch": 2.75,
"learning_rate": 4.298429319371728e-06,
"loss": 1.5976,
"step": 184
},
{
"epoch": 2.76,
"learning_rate": 4.293193717277487e-06,
"loss": 1.5405,
"step": 185
},
{
"epoch": 2.78,
"learning_rate": 4.287958115183246e-06,
"loss": 1.6132,
"step": 186
},
{
"epoch": 2.79,
"learning_rate": 4.282722513089006e-06,
"loss": 1.5873,
"step": 187
},
{
"epoch": 2.81,
"learning_rate": 4.277486910994765e-06,
"loss": 1.5689,
"step": 188
},
{
"epoch": 2.82,
"learning_rate": 4.2722513089005245e-06,
"loss": 1.5774,
"step": 189
},
{
"epoch": 2.84,
"learning_rate": 4.267015706806283e-06,
"loss": 1.567,
"step": 190
},
{
"epoch": 2.85,
"learning_rate": 4.261780104712042e-06,
"loss": 1.587,
"step": 191
},
{
"epoch": 2.87,
"learning_rate": 4.256544502617802e-06,
"loss": 1.564,
"step": 192
},
{
"epoch": 2.88,
"learning_rate": 4.251308900523561e-06,
"loss": 1.5441,
"step": 193
},
{
"epoch": 2.9,
"learning_rate": 4.24607329842932e-06,
"loss": 1.6087,
"step": 194
},
{
"epoch": 2.91,
"learning_rate": 4.240837696335079e-06,
"loss": 1.5691,
"step": 195
},
{
"epoch": 2.93,
"learning_rate": 4.2356020942408385e-06,
"loss": 1.5733,
"step": 196
},
{
"epoch": 2.94,
"learning_rate": 4.230366492146597e-06,
"loss": 1.5608,
"step": 197
},
{
"epoch": 2.96,
"learning_rate": 4.225130890052356e-06,
"loss": 1.5822,
"step": 198
},
{
"epoch": 2.97,
"learning_rate": 4.219895287958116e-06,
"loss": 1.58,
"step": 199
},
{
"epoch": 2.99,
"learning_rate": 4.214659685863874e-06,
"loss": 1.6026,
"step": 200
},
{
"epoch": 3.0,
"learning_rate": 4.209424083769634e-06,
"loss": 1.5882,
"step": 201
},
{
"epoch": 3.0,
"eval_accuracy": 0.3283582089552239,
"eval_loss": 1.5650840997695923,
"eval_roc_auc": 0.8251884750469657,
"eval_runtime": 114.4983,
"eval_samples_per_second": 0.585,
"eval_steps_per_second": 0.585,
"step": 201
},
{
"epoch": 3.01,
"learning_rate": 4.204188481675393e-06,
"loss": 1.6095,
"step": 202
},
{
"epoch": 3.03,
"learning_rate": 4.1989528795811525e-06,
"loss": 1.5525,
"step": 203
},
{
"epoch": 3.04,
"learning_rate": 4.193717277486911e-06,
"loss": 1.526,
"step": 204
},
{
"epoch": 3.06,
"learning_rate": 4.18848167539267e-06,
"loss": 1.543,
"step": 205
},
{
"epoch": 3.07,
"learning_rate": 4.18324607329843e-06,
"loss": 1.5385,
"step": 206
},
{
"epoch": 3.09,
"learning_rate": 4.178010471204188e-06,
"loss": 1.5581,
"step": 207
},
{
"epoch": 3.1,
"learning_rate": 4.172774869109948e-06,
"loss": 1.5184,
"step": 208
},
{
"epoch": 3.12,
"learning_rate": 4.167539267015707e-06,
"loss": 1.5782,
"step": 209
},
{
"epoch": 3.13,
"learning_rate": 4.1623036649214665e-06,
"loss": 1.5476,
"step": 210
},
{
"epoch": 3.15,
"learning_rate": 4.157068062827225e-06,
"loss": 1.5345,
"step": 211
},
{
"epoch": 3.16,
"learning_rate": 4.151832460732984e-06,
"loss": 1.5511,
"step": 212
},
{
"epoch": 3.18,
"learning_rate": 4.146596858638744e-06,
"loss": 1.5452,
"step": 213
},
{
"epoch": 3.19,
"learning_rate": 4.141361256544502e-06,
"loss": 1.6125,
"step": 214
},
{
"epoch": 3.21,
"learning_rate": 4.136125654450262e-06,
"loss": 1.5821,
"step": 215
},
{
"epoch": 3.22,
"learning_rate": 4.130890052356021e-06,
"loss": 1.5133,
"step": 216
},
{
"epoch": 3.24,
"learning_rate": 4.1256544502617805e-06,
"loss": 1.5998,
"step": 217
},
{
"epoch": 3.25,
"learning_rate": 4.120418848167539e-06,
"loss": 1.5498,
"step": 218
},
{
"epoch": 3.27,
"learning_rate": 4.115183246073298e-06,
"loss": 1.5217,
"step": 219
},
{
"epoch": 3.28,
"learning_rate": 4.109947643979058e-06,
"loss": 1.6151,
"step": 220
},
{
"epoch": 3.3,
"learning_rate": 4.104712041884817e-06,
"loss": 1.6195,
"step": 221
},
{
"epoch": 3.31,
"learning_rate": 4.099476439790577e-06,
"loss": 1.5148,
"step": 222
},
{
"epoch": 3.33,
"learning_rate": 4.094240837696335e-06,
"loss": 1.5387,
"step": 223
},
{
"epoch": 3.34,
"learning_rate": 4.0890052356020945e-06,
"loss": 1.5773,
"step": 224
},
{
"epoch": 3.36,
"learning_rate": 4.083769633507854e-06,
"loss": 1.6052,
"step": 225
},
{
"epoch": 3.37,
"learning_rate": 4.078534031413613e-06,
"loss": 1.5402,
"step": 226
},
{
"epoch": 3.39,
"learning_rate": 4.073298429319373e-06,
"loss": 1.6079,
"step": 227
},
{
"epoch": 3.4,
"learning_rate": 4.068062827225131e-06,
"loss": 1.6924,
"step": 228
},
{
"epoch": 3.42,
"learning_rate": 4.062827225130891e-06,
"loss": 1.5469,
"step": 229
},
{
"epoch": 3.43,
"learning_rate": 4.05759162303665e-06,
"loss": 1.5873,
"step": 230
},
{
"epoch": 3.45,
"learning_rate": 4.052356020942409e-06,
"loss": 1.6393,
"step": 231
},
{
"epoch": 3.46,
"learning_rate": 4.047120418848168e-06,
"loss": 1.5403,
"step": 232
},
{
"epoch": 3.48,
"learning_rate": 4.041884816753927e-06,
"loss": 1.5488,
"step": 233
},
{
"epoch": 3.49,
"learning_rate": 4.036649214659687e-06,
"loss": 1.5781,
"step": 234
},
{
"epoch": 3.51,
"learning_rate": 4.031413612565445e-06,
"loss": 1.5889,
"step": 235
},
{
"epoch": 3.52,
"learning_rate": 4.026178010471205e-06,
"loss": 1.5712,
"step": 236
},
{
"epoch": 3.54,
"learning_rate": 4.020942408376964e-06,
"loss": 1.4809,
"step": 237
},
{
"epoch": 3.55,
"learning_rate": 4.0157068062827225e-06,
"loss": 1.5818,
"step": 238
},
{
"epoch": 3.57,
"learning_rate": 4.010471204188482e-06,
"loss": 1.6553,
"step": 239
},
{
"epoch": 3.58,
"learning_rate": 4.005235602094241e-06,
"loss": 1.5496,
"step": 240
},
{
"epoch": 3.6,
"learning_rate": 4.000000000000001e-06,
"loss": 1.5869,
"step": 241
},
{
"epoch": 3.61,
"learning_rate": 3.994764397905759e-06,
"loss": 1.6217,
"step": 242
},
{
"epoch": 3.63,
"learning_rate": 3.989528795811519e-06,
"loss": 1.5883,
"step": 243
},
{
"epoch": 3.64,
"learning_rate": 3.984293193717278e-06,
"loss": 1.5391,
"step": 244
},
{
"epoch": 3.66,
"learning_rate": 3.9790575916230365e-06,
"loss": 1.5869,
"step": 245
},
{
"epoch": 3.67,
"learning_rate": 3.973821989528796e-06,
"loss": 1.5623,
"step": 246
},
{
"epoch": 3.69,
"learning_rate": 3.968586387434555e-06,
"loss": 1.5421,
"step": 247
},
{
"epoch": 3.7,
"learning_rate": 3.963350785340315e-06,
"loss": 1.5695,
"step": 248
},
{
"epoch": 3.72,
"learning_rate": 3.958115183246073e-06,
"loss": 1.5639,
"step": 249
},
{
"epoch": 3.73,
"learning_rate": 3.952879581151833e-06,
"loss": 1.5488,
"step": 250
},
{
"epoch": 3.75,
"learning_rate": 3.947643979057592e-06,
"loss": 1.5882,
"step": 251
},
{
"epoch": 3.76,
"learning_rate": 3.9424083769633505e-06,
"loss": 1.5899,
"step": 252
},
{
"epoch": 3.78,
"learning_rate": 3.93717277486911e-06,
"loss": 1.6539,
"step": 253
},
{
"epoch": 3.79,
"learning_rate": 3.931937172774869e-06,
"loss": 1.5572,
"step": 254
},
{
"epoch": 3.81,
"learning_rate": 3.926701570680629e-06,
"loss": 1.5665,
"step": 255
},
{
"epoch": 3.82,
"learning_rate": 3.921465968586387e-06,
"loss": 1.6125,
"step": 256
},
{
"epoch": 3.84,
"learning_rate": 3.916230366492147e-06,
"loss": 1.5109,
"step": 257
},
{
"epoch": 3.85,
"learning_rate": 3.910994764397906e-06,
"loss": 1.6052,
"step": 258
},
{
"epoch": 3.87,
"learning_rate": 3.905759162303665e-06,
"loss": 1.5552,
"step": 259
},
{
"epoch": 3.88,
"learning_rate": 3.900523560209425e-06,
"loss": 1.5781,
"step": 260
},
{
"epoch": 3.9,
"learning_rate": 3.895287958115183e-06,
"loss": 1.5518,
"step": 261
},
{
"epoch": 3.91,
"learning_rate": 3.890052356020943e-06,
"loss": 1.5583,
"step": 262
},
{
"epoch": 3.93,
"learning_rate": 3.884816753926702e-06,
"loss": 1.5543,
"step": 263
},
{
"epoch": 3.94,
"learning_rate": 3.8795811518324614e-06,
"loss": 1.5628,
"step": 264
},
{
"epoch": 3.96,
"learning_rate": 3.874345549738221e-06,
"loss": 1.5232,
"step": 265
},
{
"epoch": 3.97,
"learning_rate": 3.869109947643979e-06,
"loss": 1.5801,
"step": 266
},
{
"epoch": 3.99,
"learning_rate": 3.863874345549739e-06,
"loss": 1.4316,
"step": 267
},
{
"epoch": 4.0,
"learning_rate": 3.858638743455498e-06,
"loss": 1.5457,
"step": 268
},
{
"epoch": 4.0,
"eval_accuracy": 0.3880597014925373,
"eval_loss": 1.524383783340454,
"eval_roc_auc": 0.8612657716331995,
"eval_runtime": 114.7192,
"eval_samples_per_second": 0.584,
"eval_steps_per_second": 0.584,
"step": 268
},
{
"epoch": 4.01,
"learning_rate": 3.853403141361257e-06,
"loss": 1.463,
"step": 269
},
{
"epoch": 4.03,
"learning_rate": 3.848167539267016e-06,
"loss": 1.5483,
"step": 270
},
{
"epoch": 4.04,
"learning_rate": 3.8429319371727755e-06,
"loss": 1.536,
"step": 271
},
{
"epoch": 4.06,
"learning_rate": 3.837696335078535e-06,
"loss": 1.5668,
"step": 272
},
{
"epoch": 4.07,
"learning_rate": 3.832460732984293e-06,
"loss": 1.5547,
"step": 273
},
{
"epoch": 4.09,
"learning_rate": 3.827225130890053e-06,
"loss": 1.5112,
"step": 274
},
{
"epoch": 4.1,
"learning_rate": 3.821989528795812e-06,
"loss": 1.611,
"step": 275
},
{
"epoch": 4.12,
"learning_rate": 3.816753926701571e-06,
"loss": 1.5539,
"step": 276
},
{
"epoch": 4.13,
"learning_rate": 3.81151832460733e-06,
"loss": 1.5626,
"step": 277
},
{
"epoch": 4.15,
"learning_rate": 3.8062827225130895e-06,
"loss": 1.5878,
"step": 278
},
{
"epoch": 4.16,
"learning_rate": 3.801047120418849e-06,
"loss": 1.4933,
"step": 279
},
{
"epoch": 4.18,
"learning_rate": 3.7958115183246074e-06,
"loss": 1.5695,
"step": 280
},
{
"epoch": 4.19,
"learning_rate": 3.7905759162303668e-06,
"loss": 1.5517,
"step": 281
},
{
"epoch": 4.21,
"learning_rate": 3.785340314136126e-06,
"loss": 1.5824,
"step": 282
},
{
"epoch": 4.22,
"learning_rate": 3.7801047120418847e-06,
"loss": 1.5898,
"step": 283
},
{
"epoch": 4.24,
"learning_rate": 3.774869109947644e-06,
"loss": 1.5718,
"step": 284
},
{
"epoch": 4.25,
"learning_rate": 3.7696335078534035e-06,
"loss": 1.5329,
"step": 285
},
{
"epoch": 4.27,
"learning_rate": 3.764397905759163e-06,
"loss": 1.5609,
"step": 286
},
{
"epoch": 4.28,
"learning_rate": 3.759162303664922e-06,
"loss": 1.5517,
"step": 287
},
{
"epoch": 4.3,
"learning_rate": 3.7539267015706808e-06,
"loss": 1.4804,
"step": 288
},
{
"epoch": 4.31,
"learning_rate": 3.74869109947644e-06,
"loss": 1.572,
"step": 289
},
{
"epoch": 4.33,
"learning_rate": 3.743455497382199e-06,
"loss": 1.4667,
"step": 290
},
{
"epoch": 4.34,
"learning_rate": 3.7382198952879585e-06,
"loss": 1.4649,
"step": 291
},
{
"epoch": 4.36,
"learning_rate": 3.732984293193718e-06,
"loss": 1.4884,
"step": 292
},
{
"epoch": 4.37,
"learning_rate": 3.727748691099477e-06,
"loss": 1.481,
"step": 293
},
{
"epoch": 4.39,
"learning_rate": 3.722513089005236e-06,
"loss": 1.6238,
"step": 294
},
{
"epoch": 4.4,
"learning_rate": 3.717277486910995e-06,
"loss": 1.4681,
"step": 295
},
{
"epoch": 4.42,
"learning_rate": 3.7120418848167546e-06,
"loss": 1.5198,
"step": 296
},
{
"epoch": 4.43,
"learning_rate": 3.706806282722513e-06,
"loss": 1.5526,
"step": 297
},
{
"epoch": 4.45,
"learning_rate": 3.7015706806282725e-06,
"loss": 1.4698,
"step": 298
},
{
"epoch": 4.46,
"learning_rate": 3.696335078534032e-06,
"loss": 1.524,
"step": 299
},
{
"epoch": 4.48,
"learning_rate": 3.6910994764397904e-06,
"loss": 1.519,
"step": 300
},
{
"epoch": 4.49,
"learning_rate": 3.68586387434555e-06,
"loss": 1.4419,
"step": 301
},
{
"epoch": 4.51,
"learning_rate": 3.680628272251309e-06,
"loss": 1.5393,
"step": 302
},
{
"epoch": 4.52,
"learning_rate": 3.6753926701570686e-06,
"loss": 1.6101,
"step": 303
},
{
"epoch": 4.54,
"learning_rate": 3.6701570680628275e-06,
"loss": 1.5209,
"step": 304
},
{
"epoch": 4.55,
"learning_rate": 3.6649214659685865e-06,
"loss": 1.4508,
"step": 305
},
{
"epoch": 4.57,
"learning_rate": 3.659685863874346e-06,
"loss": 1.5547,
"step": 306
},
{
"epoch": 4.58,
"learning_rate": 3.654450261780105e-06,
"loss": 1.5269,
"step": 307
},
{
"epoch": 4.6,
"learning_rate": 3.6492146596858642e-06,
"loss": 1.5252,
"step": 308
},
{
"epoch": 4.61,
"learning_rate": 3.643979057591623e-06,
"loss": 1.5595,
"step": 309
},
{
"epoch": 4.63,
"learning_rate": 3.6387434554973826e-06,
"loss": 1.4009,
"step": 310
},
{
"epoch": 4.64,
"learning_rate": 3.6335078534031415e-06,
"loss": 1.4614,
"step": 311
},
{
"epoch": 4.66,
"learning_rate": 3.628272251308901e-06,
"loss": 1.5848,
"step": 312
},
{
"epoch": 4.67,
"learning_rate": 3.6230366492146603e-06,
"loss": 1.418,
"step": 313
},
{
"epoch": 4.69,
"learning_rate": 3.617801047120419e-06,
"loss": 1.6182,
"step": 314
},
{
"epoch": 4.7,
"learning_rate": 3.6125654450261782e-06,
"loss": 1.4291,
"step": 315
},
{
"epoch": 4.72,
"learning_rate": 3.6073298429319376e-06,
"loss": 1.5016,
"step": 316
},
{
"epoch": 4.73,
"learning_rate": 3.602094240837697e-06,
"loss": 1.5445,
"step": 317
},
{
"epoch": 4.75,
"learning_rate": 3.5968586387434556e-06,
"loss": 1.4518,
"step": 318
},
{
"epoch": 4.76,
"learning_rate": 3.591623036649215e-06,
"loss": 1.5133,
"step": 319
},
{
"epoch": 4.78,
"learning_rate": 3.5863874345549743e-06,
"loss": 1.5552,
"step": 320
},
{
"epoch": 4.79,
"learning_rate": 3.581151832460733e-06,
"loss": 1.4487,
"step": 321
},
{
"epoch": 4.81,
"learning_rate": 3.5759162303664922e-06,
"loss": 1.5563,
"step": 322
},
{
"epoch": 4.82,
"learning_rate": 3.5706806282722516e-06,
"loss": 1.4824,
"step": 323
},
{
"epoch": 4.84,
"learning_rate": 3.565445026178011e-06,
"loss": 1.5034,
"step": 324
},
{
"epoch": 4.85,
"learning_rate": 3.56020942408377e-06,
"loss": 1.429,
"step": 325
},
{
"epoch": 4.87,
"learning_rate": 3.554973821989529e-06,
"loss": 1.5454,
"step": 326
},
{
"epoch": 4.88,
"learning_rate": 3.5497382198952883e-06,
"loss": 1.6144,
"step": 327
},
{
"epoch": 4.9,
"learning_rate": 3.5445026178010473e-06,
"loss": 1.5299,
"step": 328
},
{
"epoch": 4.91,
"learning_rate": 3.5392670157068067e-06,
"loss": 1.5063,
"step": 329
},
{
"epoch": 4.93,
"learning_rate": 3.534031413612566e-06,
"loss": 1.4603,
"step": 330
},
{
"epoch": 4.94,
"learning_rate": 3.5287958115183246e-06,
"loss": 1.5949,
"step": 331
},
{
"epoch": 4.96,
"learning_rate": 3.523560209424084e-06,
"loss": 1.5152,
"step": 332
},
{
"epoch": 4.97,
"learning_rate": 3.5183246073298434e-06,
"loss": 1.5446,
"step": 333
},
{
"epoch": 4.99,
"learning_rate": 3.5130890052356028e-06,
"loss": 1.6619,
"step": 334
},
{
"epoch": 5.0,
"learning_rate": 3.5078534031413613e-06,
"loss": 1.5892,
"step": 335
},
{
"epoch": 5.0,
"eval_accuracy": 0.373134328358209,
"eval_loss": 1.4515025615692139,
"eval_roc_auc": 0.881142317629408,
"eval_runtime": 115.9119,
"eval_samples_per_second": 0.578,
"eval_steps_per_second": 0.578,
"step": 335
},
{
"epoch": 5.01,
"learning_rate": 3.5026178010471207e-06,
"loss": 1.5314,
"step": 336
},
{
"epoch": 5.03,
"learning_rate": 3.49738219895288e-06,
"loss": 1.4861,
"step": 337
},
{
"epoch": 5.04,
"learning_rate": 3.4921465968586386e-06,
"loss": 1.5109,
"step": 338
},
{
"epoch": 5.06,
"learning_rate": 3.486910994764398e-06,
"loss": 1.5558,
"step": 339
},
{
"epoch": 5.07,
"learning_rate": 3.4816753926701574e-06,
"loss": 1.4709,
"step": 340
},
{
"epoch": 5.09,
"learning_rate": 3.4764397905759168e-06,
"loss": 1.4823,
"step": 341
},
{
"epoch": 5.1,
"learning_rate": 3.4712041884816753e-06,
"loss": 1.503,
"step": 342
},
{
"epoch": 5.12,
"learning_rate": 3.4659685863874347e-06,
"loss": 1.4892,
"step": 343
},
{
"epoch": 5.13,
"learning_rate": 3.460732984293194e-06,
"loss": 1.4838,
"step": 344
},
{
"epoch": 5.15,
"learning_rate": 3.455497382198953e-06,
"loss": 1.4468,
"step": 345
},
{
"epoch": 5.16,
"learning_rate": 3.4502617801047124e-06,
"loss": 1.4746,
"step": 346
},
{
"epoch": 5.18,
"learning_rate": 3.4450261780104714e-06,
"loss": 1.5053,
"step": 347
},
{
"epoch": 5.19,
"learning_rate": 3.4397905759162308e-06,
"loss": 1.5735,
"step": 348
},
{
"epoch": 5.21,
"learning_rate": 3.4345549738219897e-06,
"loss": 1.5715,
"step": 349
},
{
"epoch": 5.22,
"learning_rate": 3.429319371727749e-06,
"loss": 1.4935,
"step": 350
},
{
"epoch": 5.24,
"learning_rate": 3.4240837696335085e-06,
"loss": 1.5139,
"step": 351
},
{
"epoch": 5.25,
"learning_rate": 3.418848167539267e-06,
"loss": 1.5141,
"step": 352
},
{
"epoch": 5.27,
"learning_rate": 3.4136125654450264e-06,
"loss": 1.4008,
"step": 353
},
{
"epoch": 5.28,
"learning_rate": 3.408376963350786e-06,
"loss": 1.4642,
"step": 354
},
{
"epoch": 5.3,
"learning_rate": 3.403141361256545e-06,
"loss": 1.5497,
"step": 355
},
{
"epoch": 5.31,
"learning_rate": 3.3979057591623037e-06,
"loss": 1.612,
"step": 356
},
{
"epoch": 5.33,
"learning_rate": 3.392670157068063e-06,
"loss": 1.5713,
"step": 357
},
{
"epoch": 5.34,
"learning_rate": 3.3874345549738225e-06,
"loss": 1.4733,
"step": 358
},
{
"epoch": 5.36,
"learning_rate": 3.382198952879581e-06,
"loss": 1.444,
"step": 359
},
{
"epoch": 5.37,
"learning_rate": 3.3769633507853404e-06,
"loss": 1.4756,
"step": 360
},
{
"epoch": 5.39,
"learning_rate": 3.3717277486911e-06,
"loss": 1.547,
"step": 361
},
{
"epoch": 5.4,
"learning_rate": 3.366492146596859e-06,
"loss": 1.558,
"step": 362
},
{
"epoch": 5.42,
"learning_rate": 3.361256544502618e-06,
"loss": 1.4456,
"step": 363
},
{
"epoch": 5.43,
"learning_rate": 3.356020942408377e-06,
"loss": 1.5993,
"step": 364
},
{
"epoch": 5.45,
"learning_rate": 3.3507853403141365e-06,
"loss": 1.4614,
"step": 365
},
{
"epoch": 5.46,
"learning_rate": 3.3455497382198955e-06,
"loss": 1.5135,
"step": 366
},
{
"epoch": 5.48,
"learning_rate": 3.340314136125655e-06,
"loss": 1.4615,
"step": 367
},
{
"epoch": 5.49,
"learning_rate": 3.335078534031414e-06,
"loss": 1.5132,
"step": 368
},
{
"epoch": 5.51,
"learning_rate": 3.3298429319371728e-06,
"loss": 1.5745,
"step": 369
},
{
"epoch": 5.52,
"learning_rate": 3.324607329842932e-06,
"loss": 1.5302,
"step": 370
},
{
"epoch": 5.54,
"learning_rate": 3.3193717277486915e-06,
"loss": 1.5434,
"step": 371
},
{
"epoch": 5.55,
"learning_rate": 3.314136125654451e-06,
"loss": 1.5764,
"step": 372
},
{
"epoch": 5.57,
"learning_rate": 3.3089005235602095e-06,
"loss": 1.552,
"step": 373
},
{
"epoch": 5.58,
"learning_rate": 3.303664921465969e-06,
"loss": 1.4927,
"step": 374
},
{
"epoch": 5.6,
"learning_rate": 3.2984293193717282e-06,
"loss": 1.533,
"step": 375
},
{
"epoch": 5.61,
"learning_rate": 3.2931937172774868e-06,
"loss": 1.5709,
"step": 376
},
{
"epoch": 5.63,
"learning_rate": 3.287958115183246e-06,
"loss": 1.4734,
"step": 377
},
{
"epoch": 5.64,
"learning_rate": 3.2827225130890055e-06,
"loss": 1.4005,
"step": 378
},
{
"epoch": 5.66,
"learning_rate": 3.277486910994765e-06,
"loss": 1.5306,
"step": 379
},
{
"epoch": 5.67,
"learning_rate": 3.2722513089005235e-06,
"loss": 1.4783,
"step": 380
},
{
"epoch": 5.69,
"learning_rate": 3.267015706806283e-06,
"loss": 1.4767,
"step": 381
},
{
"epoch": 5.7,
"learning_rate": 3.2617801047120422e-06,
"loss": 1.458,
"step": 382
},
{
"epoch": 5.72,
"learning_rate": 3.256544502617801e-06,
"loss": 1.4254,
"step": 383
},
{
"epoch": 5.73,
"learning_rate": 3.2513089005235606e-06,
"loss": 1.4295,
"step": 384
},
{
"epoch": 5.75,
"learning_rate": 3.2460732984293196e-06,
"loss": 1.4778,
"step": 385
},
{
"epoch": 5.76,
"learning_rate": 3.240837696335079e-06,
"loss": 1.4342,
"step": 386
},
{
"epoch": 5.78,
"learning_rate": 3.235602094240838e-06,
"loss": 1.3781,
"step": 387
},
{
"epoch": 5.79,
"learning_rate": 3.2303664921465973e-06,
"loss": 1.4398,
"step": 388
},
{
"epoch": 5.81,
"learning_rate": 3.2251308900523567e-06,
"loss": 1.4211,
"step": 389
},
{
"epoch": 5.82,
"learning_rate": 3.219895287958115e-06,
"loss": 1.614,
"step": 390
},
{
"epoch": 5.84,
"learning_rate": 3.2146596858638746e-06,
"loss": 1.5052,
"step": 391
},
{
"epoch": 5.85,
"learning_rate": 3.209424083769634e-06,
"loss": 1.4412,
"step": 392
},
{
"epoch": 5.87,
"learning_rate": 3.2041884816753934e-06,
"loss": 1.3745,
"step": 393
},
{
"epoch": 5.88,
"learning_rate": 3.198952879581152e-06,
"loss": 1.3644,
"step": 394
},
{
"epoch": 5.9,
"learning_rate": 3.1937172774869113e-06,
"loss": 1.3902,
"step": 395
},
{
"epoch": 5.91,
"learning_rate": 3.1884816753926707e-06,
"loss": 1.5347,
"step": 396
},
{
"epoch": 5.93,
"learning_rate": 3.183246073298429e-06,
"loss": 1.3773,
"step": 397
},
{
"epoch": 5.94,
"learning_rate": 3.1780104712041886e-06,
"loss": 1.4015,
"step": 398
},
{
"epoch": 5.96,
"learning_rate": 3.172774869109948e-06,
"loss": 1.4122,
"step": 399
},
{
"epoch": 5.97,
"learning_rate": 3.167539267015707e-06,
"loss": 1.5502,
"step": 400
},
{
"epoch": 5.99,
"learning_rate": 3.1623036649214663e-06,
"loss": 1.5631,
"step": 401
},
{
"epoch": 6.0,
"learning_rate": 3.1570680628272253e-06,
"loss": 1.5762,
"step": 402
},
{
"epoch": 6.0,
"eval_accuracy": 0.5074626865671642,
"eval_loss": 1.42205810546875,
"eval_roc_auc": 0.8996636638766727,
"eval_runtime": 114.7962,
"eval_samples_per_second": 0.584,
"eval_steps_per_second": 0.584,
"step": 402
},
{
"epoch": 6.01,
"learning_rate": 3.1518324607329847e-06,
"loss": 1.5411,
"step": 403
},
{
"epoch": 6.03,
"learning_rate": 3.1465968586387436e-06,
"loss": 1.4211,
"step": 404
},
{
"epoch": 6.04,
"learning_rate": 3.141361256544503e-06,
"loss": 1.4769,
"step": 405
},
{
"epoch": 6.06,
"learning_rate": 3.136125654450262e-06,
"loss": 1.452,
"step": 406
},
{
"epoch": 6.07,
"learning_rate": 3.130890052356021e-06,
"loss": 1.5483,
"step": 407
},
{
"epoch": 6.09,
"learning_rate": 3.1256544502617803e-06,
"loss": 1.4164,
"step": 408
},
{
"epoch": 6.1,
"learning_rate": 3.1204188481675397e-06,
"loss": 1.4244,
"step": 409
},
{
"epoch": 6.12,
"learning_rate": 3.115183246073299e-06,
"loss": 1.4406,
"step": 410
},
{
"epoch": 6.13,
"learning_rate": 3.1099476439790576e-06,
"loss": 1.469,
"step": 411
},
{
"epoch": 6.15,
"learning_rate": 3.104712041884817e-06,
"loss": 1.541,
"step": 412
},
{
"epoch": 6.16,
"learning_rate": 3.0994764397905764e-06,
"loss": 1.587,
"step": 413
},
{
"epoch": 6.18,
"learning_rate": 3.094240837696335e-06,
"loss": 1.425,
"step": 414
},
{
"epoch": 6.19,
"learning_rate": 3.0890052356020943e-06,
"loss": 1.471,
"step": 415
},
{
"epoch": 6.21,
"learning_rate": 3.0837696335078537e-06,
"loss": 1.3477,
"step": 416
},
{
"epoch": 6.22,
"learning_rate": 3.078534031413613e-06,
"loss": 1.4807,
"step": 417
},
{
"epoch": 6.24,
"learning_rate": 3.0732984293193716e-06,
"loss": 1.3969,
"step": 418
},
{
"epoch": 6.25,
"learning_rate": 3.068062827225131e-06,
"loss": 1.5848,
"step": 419
},
{
"epoch": 6.27,
"learning_rate": 3.0628272251308904e-06,
"loss": 1.462,
"step": 420
},
{
"epoch": 6.28,
"learning_rate": 3.0575916230366494e-06,
"loss": 1.4761,
"step": 421
},
{
"epoch": 6.3,
"learning_rate": 3.0523560209424088e-06,
"loss": 1.5367,
"step": 422
},
{
"epoch": 6.31,
"learning_rate": 3.0471204188481677e-06,
"loss": 1.6053,
"step": 423
},
{
"epoch": 6.33,
"learning_rate": 3.041884816753927e-06,
"loss": 1.3879,
"step": 424
},
{
"epoch": 6.34,
"learning_rate": 3.036649214659686e-06,
"loss": 1.4343,
"step": 425
},
{
"epoch": 6.36,
"learning_rate": 3.0314136125654455e-06,
"loss": 1.5917,
"step": 426
},
{
"epoch": 6.37,
"learning_rate": 3.0261780104712044e-06,
"loss": 1.5117,
"step": 427
},
{
"epoch": 6.39,
"learning_rate": 3.0209424083769634e-06,
"loss": 1.4879,
"step": 428
},
{
"epoch": 6.4,
"learning_rate": 3.0157068062827228e-06,
"loss": 1.4032,
"step": 429
},
{
"epoch": 6.42,
"learning_rate": 3.010471204188482e-06,
"loss": 1.579,
"step": 430
},
{
"epoch": 6.43,
"learning_rate": 3.0052356020942407e-06,
"loss": 1.5148,
"step": 431
},
{
"epoch": 6.45,
"learning_rate": 3e-06,
"loss": 1.319,
"step": 432
},
{
"epoch": 6.46,
"learning_rate": 2.9947643979057595e-06,
"loss": 1.473,
"step": 433
},
{
"epoch": 6.48,
"learning_rate": 2.989528795811519e-06,
"loss": 1.4904,
"step": 434
},
{
"epoch": 6.49,
"learning_rate": 2.9842931937172774e-06,
"loss": 1.4602,
"step": 435
},
{
"epoch": 6.51,
"learning_rate": 2.9790575916230368e-06,
"loss": 1.4704,
"step": 436
},
{
"epoch": 6.52,
"learning_rate": 2.973821989528796e-06,
"loss": 1.4505,
"step": 437
},
{
"epoch": 6.54,
"learning_rate": 2.968586387434555e-06,
"loss": 1.6099,
"step": 438
},
{
"epoch": 6.55,
"learning_rate": 2.963350785340314e-06,
"loss": 1.4174,
"step": 439
},
{
"epoch": 6.57,
"learning_rate": 2.9581151832460735e-06,
"loss": 1.427,
"step": 440
},
{
"epoch": 6.58,
"learning_rate": 2.952879581151833e-06,
"loss": 1.3987,
"step": 441
},
{
"epoch": 6.6,
"learning_rate": 2.947643979057592e-06,
"loss": 1.5228,
"step": 442
},
{
"epoch": 6.61,
"learning_rate": 2.942408376963351e-06,
"loss": 1.5097,
"step": 443
},
{
"epoch": 6.63,
"learning_rate": 2.93717277486911e-06,
"loss": 1.3947,
"step": 444
},
{
"epoch": 6.64,
"learning_rate": 2.931937172774869e-06,
"loss": 1.4502,
"step": 445
},
{
"epoch": 6.66,
"learning_rate": 2.9267015706806285e-06,
"loss": 1.524,
"step": 446
},
{
"epoch": 6.67,
"learning_rate": 2.921465968586388e-06,
"loss": 1.3004,
"step": 447
},
{
"epoch": 6.69,
"learning_rate": 2.9162303664921473e-06,
"loss": 1.4197,
"step": 448
},
{
"epoch": 6.7,
"learning_rate": 2.910994764397906e-06,
"loss": 1.4906,
"step": 449
},
{
"epoch": 6.72,
"learning_rate": 2.905759162303665e-06,
"loss": 1.5555,
"step": 450
},
{
"epoch": 6.73,
"learning_rate": 2.9005235602094246e-06,
"loss": 1.3979,
"step": 451
},
{
"epoch": 6.75,
"learning_rate": 2.895287958115183e-06,
"loss": 1.4629,
"step": 452
},
{
"epoch": 6.76,
"learning_rate": 2.8900523560209425e-06,
"loss": 1.4555,
"step": 453
},
{
"epoch": 6.78,
"learning_rate": 2.884816753926702e-06,
"loss": 1.3624,
"step": 454
},
{
"epoch": 6.79,
"learning_rate": 2.8795811518324613e-06,
"loss": 1.3357,
"step": 455
},
{
"epoch": 6.81,
"learning_rate": 2.87434554973822e-06,
"loss": 1.3743,
"step": 456
},
{
"epoch": 6.82,
"learning_rate": 2.869109947643979e-06,
"loss": 1.5461,
"step": 457
},
{
"epoch": 6.84,
"learning_rate": 2.8638743455497386e-06,
"loss": 1.4473,
"step": 458
},
{
"epoch": 6.85,
"learning_rate": 2.8586387434554976e-06,
"loss": 1.4294,
"step": 459
},
{
"epoch": 6.87,
"learning_rate": 2.853403141361257e-06,
"loss": 1.4106,
"step": 460
},
{
"epoch": 6.88,
"learning_rate": 2.848167539267016e-06,
"loss": 1.5031,
"step": 461
},
{
"epoch": 6.9,
"learning_rate": 2.842931937172775e-06,
"loss": 1.3915,
"step": 462
},
{
"epoch": 6.91,
"learning_rate": 2.8376963350785342e-06,
"loss": 1.4706,
"step": 463
},
{
"epoch": 6.93,
"learning_rate": 2.8324607329842936e-06,
"loss": 1.5077,
"step": 464
},
{
"epoch": 6.94,
"learning_rate": 2.8272251308900526e-06,
"loss": 1.5472,
"step": 465
},
{
"epoch": 6.96,
"learning_rate": 2.8219895287958116e-06,
"loss": 1.4057,
"step": 466
},
{
"epoch": 6.97,
"learning_rate": 2.816753926701571e-06,
"loss": 1.3993,
"step": 467
},
{
"epoch": 6.99,
"learning_rate": 2.8115183246073303e-06,
"loss": 1.3983,
"step": 468
},
{
"epoch": 7.0,
"learning_rate": 2.806282722513089e-06,
"loss": 1.4085,
"step": 469
},
{
"epoch": 7.0,
"eval_accuracy": 0.582089552238806,
"eval_loss": 1.3650407791137695,
"eval_roc_auc": 0.8868159463839701,
"eval_runtime": 115.2498,
"eval_samples_per_second": 0.581,
"eval_steps_per_second": 0.581,
"step": 469
},
{
"epoch": 7.01,
"learning_rate": 2.8010471204188483e-06,
"loss": 1.3493,
"step": 470
},
{
"epoch": 7.03,
"learning_rate": 2.7958115183246076e-06,
"loss": 1.4412,
"step": 471
},
{
"epoch": 7.04,
"learning_rate": 2.790575916230367e-06,
"loss": 1.4768,
"step": 472
},
{
"epoch": 7.06,
"learning_rate": 2.7853403141361256e-06,
"loss": 1.2879,
"step": 473
},
{
"epoch": 7.07,
"learning_rate": 2.780104712041885e-06,
"loss": 1.3029,
"step": 474
},
{
"epoch": 7.09,
"learning_rate": 2.7748691099476443e-06,
"loss": 1.4652,
"step": 475
},
{
"epoch": 7.1,
"learning_rate": 2.7696335078534033e-06,
"loss": 1.3336,
"step": 476
},
{
"epoch": 7.12,
"learning_rate": 2.7643979057591623e-06,
"loss": 1.4184,
"step": 477
},
{
"epoch": 7.13,
"learning_rate": 2.7591623036649216e-06,
"loss": 1.5299,
"step": 478
},
{
"epoch": 7.15,
"learning_rate": 2.753926701570681e-06,
"loss": 1.3983,
"step": 479
},
{
"epoch": 7.16,
"learning_rate": 2.74869109947644e-06,
"loss": 1.4203,
"step": 480
},
{
"epoch": 7.18,
"learning_rate": 2.7434554973821994e-06,
"loss": 1.2893,
"step": 481
},
{
"epoch": 7.19,
"learning_rate": 2.7382198952879583e-06,
"loss": 1.2741,
"step": 482
},
{
"epoch": 7.21,
"learning_rate": 2.7329842931937173e-06,
"loss": 1.3778,
"step": 483
},
{
"epoch": 7.22,
"learning_rate": 2.7277486910994767e-06,
"loss": 1.3175,
"step": 484
},
{
"epoch": 7.24,
"learning_rate": 2.722513089005236e-06,
"loss": 1.4461,
"step": 485
},
{
"epoch": 7.25,
"learning_rate": 2.7172774869109955e-06,
"loss": 1.4851,
"step": 486
},
{
"epoch": 7.27,
"learning_rate": 2.712041884816754e-06,
"loss": 1.3368,
"step": 487
},
{
"epoch": 7.28,
"learning_rate": 2.7068062827225134e-06,
"loss": 1.4123,
"step": 488
},
{
"epoch": 7.3,
"learning_rate": 2.7015706806282728e-06,
"loss": 1.4103,
"step": 489
},
{
"epoch": 7.31,
"learning_rate": 2.6963350785340313e-06,
"loss": 1.3252,
"step": 490
},
{
"epoch": 7.33,
"learning_rate": 2.6910994764397907e-06,
"loss": 1.4189,
"step": 491
},
{
"epoch": 7.34,
"learning_rate": 2.68586387434555e-06,
"loss": 1.3527,
"step": 492
},
{
"epoch": 7.36,
"learning_rate": 2.6806282722513095e-06,
"loss": 1.3924,
"step": 493
},
{
"epoch": 7.37,
"learning_rate": 2.675392670157068e-06,
"loss": 1.5393,
"step": 494
},
{
"epoch": 7.39,
"learning_rate": 2.6701570680628274e-06,
"loss": 1.4622,
"step": 495
},
{
"epoch": 7.4,
"learning_rate": 2.6649214659685868e-06,
"loss": 1.3947,
"step": 496
},
{
"epoch": 7.42,
"learning_rate": 2.6596858638743457e-06,
"loss": 1.3809,
"step": 497
},
{
"epoch": 7.43,
"learning_rate": 2.6544502617801047e-06,
"loss": 1.3288,
"step": 498
},
{
"epoch": 7.45,
"learning_rate": 2.649214659685864e-06,
"loss": 1.4655,
"step": 499
},
{
"epoch": 7.46,
"learning_rate": 2.643979057591623e-06,
"loss": 1.4743,
"step": 500
},
{
"epoch": 7.48,
"learning_rate": 2.6387434554973824e-06,
"loss": 1.4624,
"step": 501
},
{
"epoch": 7.49,
"learning_rate": 2.633507853403142e-06,
"loss": 1.3989,
"step": 502
},
{
"epoch": 7.51,
"learning_rate": 2.6282722513089008e-06,
"loss": 1.4216,
"step": 503
},
{
"epoch": 7.52,
"learning_rate": 2.6230366492146597e-06,
"loss": 1.303,
"step": 504
},
{
"epoch": 7.54,
"learning_rate": 2.617801047120419e-06,
"loss": 1.5343,
"step": 505
},
{
"epoch": 7.55,
"learning_rate": 2.6125654450261785e-06,
"loss": 1.2747,
"step": 506
},
{
"epoch": 7.57,
"learning_rate": 2.607329842931937e-06,
"loss": 1.4191,
"step": 507
},
{
"epoch": 7.58,
"learning_rate": 2.6020942408376964e-06,
"loss": 1.3868,
"step": 508
},
{
"epoch": 7.6,
"learning_rate": 2.596858638743456e-06,
"loss": 1.3678,
"step": 509
},
{
"epoch": 7.61,
"learning_rate": 2.591623036649215e-06,
"loss": 1.4754,
"step": 510
},
{
"epoch": 7.63,
"learning_rate": 2.5863874345549737e-06,
"loss": 1.4908,
"step": 511
},
{
"epoch": 7.64,
"learning_rate": 2.581151832460733e-06,
"loss": 1.4364,
"step": 512
},
{
"epoch": 7.66,
"learning_rate": 2.5759162303664925e-06,
"loss": 1.3136,
"step": 513
},
{
"epoch": 7.67,
"learning_rate": 2.5706806282722515e-06,
"loss": 1.3757,
"step": 514
},
{
"epoch": 7.69,
"learning_rate": 2.5654450261780104e-06,
"loss": 1.4906,
"step": 515
},
{
"epoch": 7.7,
"learning_rate": 2.56020942408377e-06,
"loss": 1.484,
"step": 516
},
{
"epoch": 7.72,
"learning_rate": 2.554973821989529e-06,
"loss": 1.4083,
"step": 517
},
{
"epoch": 7.73,
"learning_rate": 2.549738219895288e-06,
"loss": 1.4492,
"step": 518
},
{
"epoch": 7.75,
"learning_rate": 2.5445026178010475e-06,
"loss": 1.4013,
"step": 519
},
{
"epoch": 7.76,
"learning_rate": 2.5392670157068065e-06,
"loss": 1.3524,
"step": 520
},
{
"epoch": 7.78,
"learning_rate": 2.5340314136125655e-06,
"loss": 1.4877,
"step": 521
},
{
"epoch": 7.79,
"learning_rate": 2.528795811518325e-06,
"loss": 1.4133,
"step": 522
},
{
"epoch": 7.81,
"learning_rate": 2.5235602094240842e-06,
"loss": 1.4107,
"step": 523
},
{
"epoch": 7.82,
"learning_rate": 2.518324607329843e-06,
"loss": 1.4637,
"step": 524
},
{
"epoch": 7.84,
"learning_rate": 2.513089005235602e-06,
"loss": 1.3032,
"step": 525
},
{
"epoch": 7.85,
"learning_rate": 2.5078534031413615e-06,
"loss": 1.5095,
"step": 526
},
{
"epoch": 7.87,
"learning_rate": 2.502617801047121e-06,
"loss": 1.3128,
"step": 527
},
{
"epoch": 7.88,
"learning_rate": 2.49738219895288e-06,
"loss": 1.3374,
"step": 528
},
{
"epoch": 7.9,
"learning_rate": 2.492146596858639e-06,
"loss": 1.3599,
"step": 529
},
{
"epoch": 7.91,
"learning_rate": 2.4869109947643982e-06,
"loss": 1.5406,
"step": 530
},
{
"epoch": 7.93,
"learning_rate": 2.481675392670157e-06,
"loss": 1.4901,
"step": 531
},
{
"epoch": 7.94,
"learning_rate": 2.476439790575916e-06,
"loss": 1.3618,
"step": 532
},
{
"epoch": 7.96,
"learning_rate": 2.4712041884816756e-06,
"loss": 1.4245,
"step": 533
},
{
"epoch": 7.97,
"learning_rate": 2.4659685863874345e-06,
"loss": 1.4703,
"step": 534
},
{
"epoch": 7.99,
"learning_rate": 2.460732984293194e-06,
"loss": 1.4407,
"step": 535
},
{
"epoch": 8.0,
"learning_rate": 2.455497382198953e-06,
"loss": 1.3602,
"step": 536
},
{
"epoch": 8.0,
"eval_accuracy": 0.5970149253731343,
"eval_loss": 1.3232402801513672,
"eval_roc_auc": 0.8994015054789634,
"eval_runtime": 114.1138,
"eval_samples_per_second": 0.587,
"eval_steps_per_second": 0.587,
"step": 536
},
{
"epoch": 8.01,
"learning_rate": 2.4502617801047122e-06,
"loss": 1.3341,
"step": 537
},
{
"epoch": 8.03,
"learning_rate": 2.4450261780104716e-06,
"loss": 1.3392,
"step": 538
},
{
"epoch": 8.04,
"learning_rate": 2.4397905759162306e-06,
"loss": 1.3314,
"step": 539
},
{
"epoch": 8.06,
"learning_rate": 2.43455497382199e-06,
"loss": 1.4066,
"step": 540
},
{
"epoch": 8.07,
"learning_rate": 2.429319371727749e-06,
"loss": 1.493,
"step": 541
},
{
"epoch": 8.09,
"learning_rate": 2.4240837696335083e-06,
"loss": 1.2613,
"step": 542
},
{
"epoch": 8.1,
"learning_rate": 2.4188481675392673e-06,
"loss": 1.3318,
"step": 543
},
{
"epoch": 8.12,
"learning_rate": 2.4136125654450263e-06,
"loss": 1.3639,
"step": 544
},
{
"epoch": 8.13,
"learning_rate": 2.4083769633507856e-06,
"loss": 1.3511,
"step": 545
},
{
"epoch": 8.15,
"learning_rate": 2.4031413612565446e-06,
"loss": 1.4716,
"step": 546
},
{
"epoch": 8.16,
"learning_rate": 2.397905759162304e-06,
"loss": 1.4163,
"step": 547
},
{
"epoch": 8.18,
"learning_rate": 2.392670157068063e-06,
"loss": 1.4113,
"step": 548
},
{
"epoch": 8.19,
"learning_rate": 2.3874345549738223e-06,
"loss": 1.7564,
"step": 549
},
{
"epoch": 8.21,
"learning_rate": 2.3821989528795813e-06,
"loss": 1.3595,
"step": 550
},
{
"epoch": 8.22,
"learning_rate": 2.3769633507853403e-06,
"loss": 1.3879,
"step": 551
},
{
"epoch": 8.24,
"learning_rate": 2.3717277486910996e-06,
"loss": 1.3285,
"step": 552
},
{
"epoch": 8.25,
"learning_rate": 2.3664921465968586e-06,
"loss": 1.3988,
"step": 553
},
{
"epoch": 8.27,
"learning_rate": 2.361256544502618e-06,
"loss": 1.2299,
"step": 554
},
{
"epoch": 8.28,
"learning_rate": 2.356020942408377e-06,
"loss": 1.401,
"step": 555
},
{
"epoch": 8.3,
"learning_rate": 2.3507853403141363e-06,
"loss": 1.4867,
"step": 556
},
{
"epoch": 8.31,
"learning_rate": 2.3455497382198957e-06,
"loss": 1.5886,
"step": 557
},
{
"epoch": 8.33,
"learning_rate": 2.3403141361256547e-06,
"loss": 1.3351,
"step": 558
},
{
"epoch": 8.34,
"learning_rate": 2.335078534031414e-06,
"loss": 1.281,
"step": 559
},
{
"epoch": 8.36,
"learning_rate": 2.329842931937173e-06,
"loss": 1.3566,
"step": 560
},
{
"epoch": 8.37,
"learning_rate": 2.3246073298429324e-06,
"loss": 1.2541,
"step": 561
},
{
"epoch": 8.39,
"learning_rate": 2.3193717277486914e-06,
"loss": 1.4523,
"step": 562
},
{
"epoch": 8.4,
"learning_rate": 2.3141361256544503e-06,
"loss": 1.3455,
"step": 563
},
{
"epoch": 8.42,
"learning_rate": 2.3089005235602097e-06,
"loss": 1.4539,
"step": 564
},
{
"epoch": 8.43,
"learning_rate": 2.3036649214659687e-06,
"loss": 1.4109,
"step": 565
},
{
"epoch": 8.45,
"learning_rate": 2.298429319371728e-06,
"loss": 1.3696,
"step": 566
},
{
"epoch": 8.46,
"learning_rate": 2.293193717277487e-06,
"loss": 1.4263,
"step": 567
},
{
"epoch": 8.48,
"learning_rate": 2.2879581151832464e-06,
"loss": 1.4543,
"step": 568
},
{
"epoch": 8.49,
"learning_rate": 2.2827225130890054e-06,
"loss": 1.4815,
"step": 569
},
{
"epoch": 8.51,
"learning_rate": 2.2774869109947643e-06,
"loss": 1.4155,
"step": 570
},
{
"epoch": 8.52,
"learning_rate": 2.2722513089005237e-06,
"loss": 1.4503,
"step": 571
},
{
"epoch": 8.54,
"learning_rate": 2.2670157068062827e-06,
"loss": 1.3865,
"step": 572
},
{
"epoch": 8.55,
"learning_rate": 2.261780104712042e-06,
"loss": 1.4291,
"step": 573
},
{
"epoch": 8.57,
"learning_rate": 2.256544502617801e-06,
"loss": 1.2442,
"step": 574
},
{
"epoch": 8.58,
"learning_rate": 2.2513089005235604e-06,
"loss": 1.2507,
"step": 575
},
{
"epoch": 8.6,
"learning_rate": 2.2460732984293194e-06,
"loss": 1.4016,
"step": 576
},
{
"epoch": 8.61,
"learning_rate": 2.2408376963350788e-06,
"loss": 1.3312,
"step": 577
},
{
"epoch": 8.63,
"learning_rate": 2.235602094240838e-06,
"loss": 1.4893,
"step": 578
},
{
"epoch": 8.64,
"learning_rate": 2.230366492146597e-06,
"loss": 1.4599,
"step": 579
},
{
"epoch": 8.66,
"learning_rate": 2.2251308900523565e-06,
"loss": 1.245,
"step": 580
},
{
"epoch": 8.67,
"learning_rate": 2.2198952879581155e-06,
"loss": 1.3642,
"step": 581
},
{
"epoch": 8.69,
"learning_rate": 2.2146596858638744e-06,
"loss": 1.2514,
"step": 582
},
{
"epoch": 8.7,
"learning_rate": 2.209424083769634e-06,
"loss": 1.298,
"step": 583
},
{
"epoch": 8.72,
"learning_rate": 2.2041884816753928e-06,
"loss": 1.3461,
"step": 584
},
{
"epoch": 8.73,
"learning_rate": 2.198952879581152e-06,
"loss": 1.2911,
"step": 585
},
{
"epoch": 8.75,
"learning_rate": 2.193717277486911e-06,
"loss": 1.4528,
"step": 586
},
{
"epoch": 8.76,
"learning_rate": 2.18848167539267e-06,
"loss": 1.3732,
"step": 587
},
{
"epoch": 8.78,
"learning_rate": 2.1832460732984295e-06,
"loss": 1.3621,
"step": 588
},
{
"epoch": 8.79,
"learning_rate": 2.1780104712041884e-06,
"loss": 1.2996,
"step": 589
},
{
"epoch": 8.81,
"learning_rate": 2.172774869109948e-06,
"loss": 1.2922,
"step": 590
},
{
"epoch": 8.82,
"learning_rate": 2.1675392670157068e-06,
"loss": 1.3483,
"step": 591
},
{
"epoch": 8.84,
"learning_rate": 2.162303664921466e-06,
"loss": 1.3111,
"step": 592
},
{
"epoch": 8.85,
"learning_rate": 2.157068062827225e-06,
"loss": 1.4849,
"step": 593
},
{
"epoch": 8.87,
"learning_rate": 2.1518324607329845e-06,
"loss": 1.3469,
"step": 594
},
{
"epoch": 8.88,
"learning_rate": 2.1465968586387435e-06,
"loss": 1.3223,
"step": 595
},
{
"epoch": 8.9,
"learning_rate": 2.141361256544503e-06,
"loss": 1.4483,
"step": 596
},
{
"epoch": 8.91,
"learning_rate": 2.1361256544502622e-06,
"loss": 1.5507,
"step": 597
},
{
"epoch": 8.93,
"learning_rate": 2.130890052356021e-06,
"loss": 1.3229,
"step": 598
},
{
"epoch": 8.94,
"learning_rate": 2.1256544502617806e-06,
"loss": 1.3307,
"step": 599
},
{
"epoch": 8.96,
"learning_rate": 2.1204188481675396e-06,
"loss": 1.2268,
"step": 600
},
{
"epoch": 8.97,
"learning_rate": 2.1151832460732985e-06,
"loss": 1.3881,
"step": 601
},
{
"epoch": 8.99,
"learning_rate": 2.109947643979058e-06,
"loss": 1.3719,
"step": 602
},
{
"epoch": 9.0,
"learning_rate": 2.104712041884817e-06,
"loss": 1.4634,
"step": 603
},
{
"epoch": 9.0,
"eval_accuracy": 0.4925373134328358,
"eval_loss": 1.334736943244934,
"eval_roc_auc": 0.8865149903059535,
"eval_runtime": 114.7502,
"eval_samples_per_second": 0.584,
"eval_steps_per_second": 0.584,
"step": 603
},
{
"epoch": 9.01,
"learning_rate": 2.0994764397905762e-06,
"loss": 1.2737,
"step": 604
},
{
"epoch": 9.03,
"learning_rate": 2.094240837696335e-06,
"loss": 1.3233,
"step": 605
},
{
"epoch": 9.04,
"learning_rate": 2.089005235602094e-06,
"loss": 1.1945,
"step": 606
},
{
"epoch": 9.06,
"learning_rate": 2.0837696335078536e-06,
"loss": 1.238,
"step": 607
},
{
"epoch": 9.07,
"learning_rate": 2.0785340314136125e-06,
"loss": 1.419,
"step": 608
},
{
"epoch": 9.09,
"learning_rate": 2.073298429319372e-06,
"loss": 1.2901,
"step": 609
},
{
"epoch": 9.1,
"learning_rate": 2.068062827225131e-06,
"loss": 1.3354,
"step": 610
},
{
"epoch": 9.12,
"learning_rate": 2.0628272251308902e-06,
"loss": 1.3721,
"step": 611
},
{
"epoch": 9.13,
"learning_rate": 2.057591623036649e-06,
"loss": 1.361,
"step": 612
},
{
"epoch": 9.15,
"learning_rate": 2.0523560209424086e-06,
"loss": 1.4684,
"step": 613
},
{
"epoch": 9.16,
"learning_rate": 2.0471204188481676e-06,
"loss": 1.2416,
"step": 614
},
{
"epoch": 9.18,
"learning_rate": 2.041884816753927e-06,
"loss": 1.3574,
"step": 615
},
{
"epoch": 9.19,
"learning_rate": 2.0366492146596863e-06,
"loss": 1.4478,
"step": 616
},
{
"epoch": 9.21,
"learning_rate": 2.0314136125654453e-06,
"loss": 1.3652,
"step": 617
},
{
"epoch": 9.22,
"learning_rate": 2.0261780104712047e-06,
"loss": 1.2838,
"step": 618
},
{
"epoch": 9.24,
"learning_rate": 2.0209424083769636e-06,
"loss": 1.4077,
"step": 619
},
{
"epoch": 9.25,
"learning_rate": 2.0157068062827226e-06,
"loss": 1.4663,
"step": 620
},
{
"epoch": 9.27,
"learning_rate": 2.010471204188482e-06,
"loss": 1.3451,
"step": 621
},
{
"epoch": 9.28,
"learning_rate": 2.005235602094241e-06,
"loss": 1.2607,
"step": 622
},
{
"epoch": 9.3,
"learning_rate": 2.0000000000000003e-06,
"loss": 1.1843,
"step": 623
},
{
"epoch": 9.31,
"learning_rate": 1.9947643979057593e-06,
"loss": 1.3023,
"step": 624
},
{
"epoch": 9.33,
"learning_rate": 1.9895287958115183e-06,
"loss": 1.2757,
"step": 625
},
{
"epoch": 9.34,
"learning_rate": 1.9842931937172776e-06,
"loss": 1.3397,
"step": 626
},
{
"epoch": 9.36,
"learning_rate": 1.9790575916230366e-06,
"loss": 1.3043,
"step": 627
},
{
"epoch": 9.37,
"learning_rate": 1.973821989528796e-06,
"loss": 1.2754,
"step": 628
},
{
"epoch": 9.39,
"learning_rate": 1.968586387434555e-06,
"loss": 1.478,
"step": 629
},
{
"epoch": 9.4,
"learning_rate": 1.9633507853403143e-06,
"loss": 1.4255,
"step": 630
},
{
"epoch": 9.42,
"learning_rate": 1.9581151832460733e-06,
"loss": 1.291,
"step": 631
},
{
"epoch": 9.43,
"learning_rate": 1.9528795811518327e-06,
"loss": 1.2604,
"step": 632
},
{
"epoch": 9.45,
"learning_rate": 1.9476439790575916e-06,
"loss": 1.4036,
"step": 633
},
{
"epoch": 9.46,
"learning_rate": 1.942408376963351e-06,
"loss": 1.3565,
"step": 634
},
{
"epoch": 9.48,
"learning_rate": 1.9371727748691104e-06,
"loss": 1.4375,
"step": 635
},
{
"epoch": 9.49,
"learning_rate": 1.9319371727748694e-06,
"loss": 1.5023,
"step": 636
},
{
"epoch": 9.51,
"learning_rate": 1.9267015706806283e-06,
"loss": 1.3839,
"step": 637
},
{
"epoch": 9.52,
"learning_rate": 1.9214659685863877e-06,
"loss": 1.1494,
"step": 638
},
{
"epoch": 9.54,
"learning_rate": 1.9162303664921467e-06,
"loss": 1.3491,
"step": 639
},
{
"epoch": 9.55,
"learning_rate": 1.910994764397906e-06,
"loss": 1.3917,
"step": 640
},
{
"epoch": 9.57,
"learning_rate": 1.905759162303665e-06,
"loss": 1.4043,
"step": 641
},
{
"epoch": 9.58,
"learning_rate": 1.9005235602094244e-06,
"loss": 1.2889,
"step": 642
},
{
"epoch": 9.6,
"learning_rate": 1.8952879581151834e-06,
"loss": 1.4794,
"step": 643
},
{
"epoch": 9.61,
"learning_rate": 1.8900523560209423e-06,
"loss": 1.3874,
"step": 644
},
{
"epoch": 9.63,
"learning_rate": 1.8848167539267017e-06,
"loss": 1.2018,
"step": 645
},
{
"epoch": 9.64,
"learning_rate": 1.879581151832461e-06,
"loss": 1.3614,
"step": 646
},
{
"epoch": 9.66,
"learning_rate": 1.87434554973822e-06,
"loss": 1.3398,
"step": 647
},
{
"epoch": 9.67,
"learning_rate": 1.8691099476439793e-06,
"loss": 1.3111,
"step": 648
},
{
"epoch": 9.69,
"learning_rate": 1.8638743455497384e-06,
"loss": 1.4621,
"step": 649
},
{
"epoch": 9.7,
"learning_rate": 1.8586387434554976e-06,
"loss": 1.4852,
"step": 650
},
{
"epoch": 9.72,
"learning_rate": 1.8534031413612566e-06,
"loss": 1.4208,
"step": 651
},
{
"epoch": 9.73,
"learning_rate": 1.848167539267016e-06,
"loss": 1.2835,
"step": 652
},
{
"epoch": 9.75,
"learning_rate": 1.842931937172775e-06,
"loss": 1.3615,
"step": 653
},
{
"epoch": 9.76,
"learning_rate": 1.8376963350785343e-06,
"loss": 1.3334,
"step": 654
},
{
"epoch": 9.78,
"learning_rate": 1.8324607329842933e-06,
"loss": 1.2462,
"step": 655
},
{
"epoch": 9.79,
"learning_rate": 1.8272251308900524e-06,
"loss": 1.4433,
"step": 656
},
{
"epoch": 9.81,
"learning_rate": 1.8219895287958116e-06,
"loss": 1.2258,
"step": 657
},
{
"epoch": 9.82,
"learning_rate": 1.8167539267015708e-06,
"loss": 1.3308,
"step": 658
},
{
"epoch": 9.84,
"learning_rate": 1.8115183246073302e-06,
"loss": 1.4901,
"step": 659
},
{
"epoch": 9.85,
"learning_rate": 1.8062827225130891e-06,
"loss": 1.2137,
"step": 660
},
{
"epoch": 9.87,
"learning_rate": 1.8010471204188485e-06,
"loss": 1.2923,
"step": 661
},
{
"epoch": 9.88,
"learning_rate": 1.7958115183246075e-06,
"loss": 1.345,
"step": 662
},
{
"epoch": 9.9,
"learning_rate": 1.7905759162303664e-06,
"loss": 1.2361,
"step": 663
},
{
"epoch": 9.91,
"learning_rate": 1.7853403141361258e-06,
"loss": 1.5686,
"step": 664
},
{
"epoch": 9.93,
"learning_rate": 1.780104712041885e-06,
"loss": 1.3806,
"step": 665
},
{
"epoch": 9.94,
"learning_rate": 1.7748691099476442e-06,
"loss": 1.3243,
"step": 666
},
{
"epoch": 9.96,
"learning_rate": 1.7696335078534033e-06,
"loss": 1.2921,
"step": 667
},
{
"epoch": 9.97,
"learning_rate": 1.7643979057591623e-06,
"loss": 1.3123,
"step": 668
},
{
"epoch": 9.99,
"learning_rate": 1.7591623036649217e-06,
"loss": 1.353,
"step": 669
},
{
"epoch": 10.0,
"learning_rate": 1.7539267015706806e-06,
"loss": 1.301,
"step": 670
},
{
"epoch": 10.0,
"eval_accuracy": 0.7164179104477612,
"eval_loss": 1.2525287866592407,
"eval_roc_auc": 0.9251711504318256,
"eval_runtime": 113.7082,
"eval_samples_per_second": 0.589,
"eval_steps_per_second": 0.589,
"step": 670
},
{
"epoch": 10.01,
"learning_rate": 1.74869109947644e-06,
"loss": 1.4082,
"step": 671
},
{
"epoch": 10.03,
"learning_rate": 1.743455497382199e-06,
"loss": 1.2513,
"step": 672
},
{
"epoch": 10.04,
"learning_rate": 1.7382198952879584e-06,
"loss": 1.2786,
"step": 673
},
{
"epoch": 10.06,
"learning_rate": 1.7329842931937173e-06,
"loss": 1.3847,
"step": 674
},
{
"epoch": 10.07,
"learning_rate": 1.7277486910994765e-06,
"loss": 1.4659,
"step": 675
},
{
"epoch": 10.09,
"learning_rate": 1.7225130890052357e-06,
"loss": 1.3991,
"step": 676
},
{
"epoch": 10.1,
"learning_rate": 1.7172774869109949e-06,
"loss": 1.3691,
"step": 677
},
{
"epoch": 10.12,
"learning_rate": 1.7120418848167542e-06,
"loss": 1.3431,
"step": 678
},
{
"epoch": 10.13,
"learning_rate": 1.7068062827225132e-06,
"loss": 1.1488,
"step": 679
},
{
"epoch": 10.15,
"learning_rate": 1.7015706806282726e-06,
"loss": 1.2661,
"step": 680
},
{
"epoch": 10.16,
"learning_rate": 1.6963350785340316e-06,
"loss": 1.4463,
"step": 681
},
{
"epoch": 10.18,
"learning_rate": 1.6910994764397905e-06,
"loss": 1.2989,
"step": 682
},
{
"epoch": 10.19,
"learning_rate": 1.68586387434555e-06,
"loss": 1.2203,
"step": 683
},
{
"epoch": 10.21,
"learning_rate": 1.680628272251309e-06,
"loss": 1.2228,
"step": 684
},
{
"epoch": 10.22,
"learning_rate": 1.6753926701570683e-06,
"loss": 1.2175,
"step": 685
},
{
"epoch": 10.24,
"learning_rate": 1.6701570680628274e-06,
"loss": 1.3362,
"step": 686
},
{
"epoch": 10.25,
"learning_rate": 1.6649214659685864e-06,
"loss": 1.3643,
"step": 687
},
{
"epoch": 10.27,
"learning_rate": 1.6596858638743458e-06,
"loss": 1.2681,
"step": 688
},
{
"epoch": 10.28,
"learning_rate": 1.6544502617801047e-06,
"loss": 1.2416,
"step": 689
},
{
"epoch": 10.3,
"learning_rate": 1.6492146596858641e-06,
"loss": 1.2755,
"step": 690
},
{
"epoch": 10.31,
"learning_rate": 1.643979057591623e-06,
"loss": 1.3008,
"step": 691
},
{
"epoch": 10.33,
"learning_rate": 1.6387434554973825e-06,
"loss": 1.3513,
"step": 692
},
{
"epoch": 10.34,
"learning_rate": 1.6335078534031414e-06,
"loss": 1.3498,
"step": 693
},
{
"epoch": 10.36,
"learning_rate": 1.6282722513089006e-06,
"loss": 1.3968,
"step": 694
},
{
"epoch": 10.37,
"learning_rate": 1.6230366492146598e-06,
"loss": 1.3529,
"step": 695
},
{
"epoch": 10.39,
"learning_rate": 1.617801047120419e-06,
"loss": 1.4367,
"step": 696
},
{
"epoch": 10.4,
"learning_rate": 1.6125654450261783e-06,
"loss": 1.3278,
"step": 697
},
{
"epoch": 10.42,
"learning_rate": 1.6073298429319373e-06,
"loss": 1.2611,
"step": 698
},
{
"epoch": 10.43,
"learning_rate": 1.6020942408376967e-06,
"loss": 1.2905,
"step": 699
},
{
"epoch": 10.45,
"learning_rate": 1.5968586387434556e-06,
"loss": 1.5078,
"step": 700
},
{
"epoch": 10.46,
"learning_rate": 1.5916230366492146e-06,
"loss": 1.327,
"step": 701
},
{
"epoch": 10.48,
"learning_rate": 1.586387434554974e-06,
"loss": 1.3342,
"step": 702
},
{
"epoch": 10.49,
"learning_rate": 1.5811518324607332e-06,
"loss": 1.3534,
"step": 703
},
{
"epoch": 10.51,
"learning_rate": 1.5759162303664923e-06,
"loss": 1.4769,
"step": 704
},
{
"epoch": 10.52,
"learning_rate": 1.5706806282722515e-06,
"loss": 1.2854,
"step": 705
},
{
"epoch": 10.54,
"learning_rate": 1.5654450261780105e-06,
"loss": 1.3121,
"step": 706
},
{
"epoch": 10.55,
"learning_rate": 1.5602094240837699e-06,
"loss": 1.3069,
"step": 707
},
{
"epoch": 10.57,
"learning_rate": 1.5549738219895288e-06,
"loss": 1.3382,
"step": 708
},
{
"epoch": 10.58,
"learning_rate": 1.5497382198952882e-06,
"loss": 1.2994,
"step": 709
},
{
"epoch": 10.6,
"learning_rate": 1.5445026178010472e-06,
"loss": 1.3024,
"step": 710
},
{
"epoch": 10.61,
"learning_rate": 1.5392670157068066e-06,
"loss": 1.3612,
"step": 711
},
{
"epoch": 10.63,
"learning_rate": 1.5340314136125655e-06,
"loss": 1.2902,
"step": 712
},
{
"epoch": 10.64,
"learning_rate": 1.5287958115183247e-06,
"loss": 1.2869,
"step": 713
},
{
"epoch": 10.66,
"learning_rate": 1.5235602094240839e-06,
"loss": 1.2834,
"step": 714
},
{
"epoch": 10.67,
"learning_rate": 1.518324607329843e-06,
"loss": 1.2747,
"step": 715
},
{
"epoch": 10.69,
"learning_rate": 1.5130890052356022e-06,
"loss": 1.3888,
"step": 716
},
{
"epoch": 10.7,
"learning_rate": 1.5078534031413614e-06,
"loss": 1.4652,
"step": 717
},
{
"epoch": 10.72,
"learning_rate": 1.5026178010471203e-06,
"loss": 1.3828,
"step": 718
},
{
"epoch": 10.73,
"learning_rate": 1.4973821989528797e-06,
"loss": 1.3641,
"step": 719
},
{
"epoch": 10.75,
"learning_rate": 1.4921465968586387e-06,
"loss": 1.4433,
"step": 720
},
{
"epoch": 10.76,
"learning_rate": 1.486910994764398e-06,
"loss": 1.3673,
"step": 721
},
{
"epoch": 10.78,
"learning_rate": 1.481675392670157e-06,
"loss": 1.2609,
"step": 722
},
{
"epoch": 10.79,
"learning_rate": 1.4764397905759164e-06,
"loss": 1.3625,
"step": 723
},
{
"epoch": 10.81,
"learning_rate": 1.4712041884816756e-06,
"loss": 1.3957,
"step": 724
},
{
"epoch": 10.82,
"learning_rate": 1.4659685863874346e-06,
"loss": 1.1985,
"step": 725
},
{
"epoch": 10.84,
"learning_rate": 1.460732984293194e-06,
"loss": 1.2971,
"step": 726
},
{
"epoch": 10.85,
"learning_rate": 1.455497382198953e-06,
"loss": 1.3019,
"step": 727
},
{
"epoch": 10.87,
"learning_rate": 1.4502617801047123e-06,
"loss": 1.2214,
"step": 728
},
{
"epoch": 10.88,
"learning_rate": 1.4450261780104713e-06,
"loss": 1.2505,
"step": 729
},
{
"epoch": 10.9,
"learning_rate": 1.4397905759162306e-06,
"loss": 1.365,
"step": 730
},
{
"epoch": 10.91,
"learning_rate": 1.4345549738219896e-06,
"loss": 1.2999,
"step": 731
},
{
"epoch": 10.93,
"learning_rate": 1.4293193717277488e-06,
"loss": 1.4429,
"step": 732
},
{
"epoch": 10.94,
"learning_rate": 1.424083769633508e-06,
"loss": 1.1743,
"step": 733
},
{
"epoch": 10.96,
"learning_rate": 1.4188481675392671e-06,
"loss": 1.2749,
"step": 734
},
{
"epoch": 10.97,
"learning_rate": 1.4136125654450263e-06,
"loss": 1.269,
"step": 735
},
{
"epoch": 10.99,
"learning_rate": 1.4083769633507855e-06,
"loss": 1.4313,
"step": 736
},
{
"epoch": 11.0,
"learning_rate": 1.4031413612565444e-06,
"loss": 1.2545,
"step": 737
},
{
"epoch": 11.0,
"eval_accuracy": 0.7164179104477612,
"eval_loss": 1.2266749143600464,
"eval_roc_auc": 0.9242875950596904,
"eval_runtime": 114.8426,
"eval_samples_per_second": 0.583,
"eval_steps_per_second": 0.583,
"step": 737
},
{
"epoch": 11.01,
"learning_rate": 1.3979057591623038e-06,
"loss": 1.3544,
"step": 738
},
{
"epoch": 11.03,
"learning_rate": 1.3926701570680628e-06,
"loss": 1.2447,
"step": 739
},
{
"epoch": 11.04,
"learning_rate": 1.3874345549738222e-06,
"loss": 1.1688,
"step": 740
},
{
"epoch": 11.06,
"learning_rate": 1.3821989528795811e-06,
"loss": 1.222,
"step": 741
},
{
"epoch": 11.07,
"learning_rate": 1.3769633507853405e-06,
"loss": 1.1891,
"step": 742
},
{
"epoch": 11.09,
"learning_rate": 1.3717277486910997e-06,
"loss": 1.3033,
"step": 743
},
{
"epoch": 11.1,
"learning_rate": 1.3664921465968586e-06,
"loss": 1.239,
"step": 744
},
{
"epoch": 11.12,
"learning_rate": 1.361256544502618e-06,
"loss": 1.4937,
"step": 745
},
{
"epoch": 11.13,
"learning_rate": 1.356020942408377e-06,
"loss": 1.2524,
"step": 746
},
{
"epoch": 11.15,
"learning_rate": 1.3507853403141364e-06,
"loss": 1.3377,
"step": 747
},
{
"epoch": 11.16,
"learning_rate": 1.3455497382198953e-06,
"loss": 1.2181,
"step": 748
},
{
"epoch": 11.18,
"learning_rate": 1.3403141361256547e-06,
"loss": 1.4058,
"step": 749
},
{
"epoch": 11.19,
"learning_rate": 1.3350785340314137e-06,
"loss": 1.3541,
"step": 750
},
{
"epoch": 11.21,
"learning_rate": 1.3298429319371729e-06,
"loss": 1.2097,
"step": 751
},
{
"epoch": 11.22,
"learning_rate": 1.324607329842932e-06,
"loss": 1.1825,
"step": 752
},
{
"epoch": 11.24,
"learning_rate": 1.3193717277486912e-06,
"loss": 1.1941,
"step": 753
},
{
"epoch": 11.25,
"learning_rate": 1.3141361256544504e-06,
"loss": 1.368,
"step": 754
},
{
"epoch": 11.27,
"learning_rate": 1.3089005235602096e-06,
"loss": 1.5042,
"step": 755
},
{
"epoch": 11.28,
"learning_rate": 1.3036649214659685e-06,
"loss": 1.3033,
"step": 756
},
{
"epoch": 11.3,
"learning_rate": 1.298429319371728e-06,
"loss": 1.236,
"step": 757
},
{
"epoch": 11.31,
"learning_rate": 1.2931937172774869e-06,
"loss": 1.3492,
"step": 758
},
{
"epoch": 11.33,
"learning_rate": 1.2879581151832463e-06,
"loss": 1.3996,
"step": 759
},
{
"epoch": 11.34,
"learning_rate": 1.2827225130890052e-06,
"loss": 1.3104,
"step": 760
},
{
"epoch": 11.36,
"learning_rate": 1.2774869109947646e-06,
"loss": 1.5012,
"step": 761
},
{
"epoch": 11.37,
"learning_rate": 1.2722513089005238e-06,
"loss": 1.5104,
"step": 762
},
{
"epoch": 11.39,
"learning_rate": 1.2670157068062827e-06,
"loss": 1.3532,
"step": 763
},
{
"epoch": 11.4,
"learning_rate": 1.2617801047120421e-06,
"loss": 1.1661,
"step": 764
},
{
"epoch": 11.42,
"learning_rate": 1.256544502617801e-06,
"loss": 1.3541,
"step": 765
},
{
"epoch": 11.43,
"learning_rate": 1.2513089005235605e-06,
"loss": 1.3815,
"step": 766
},
{
"epoch": 11.45,
"learning_rate": 1.2460732984293194e-06,
"loss": 1.1549,
"step": 767
},
{
"epoch": 11.46,
"learning_rate": 1.2408376963350786e-06,
"loss": 1.5656,
"step": 768
},
{
"epoch": 11.48,
"learning_rate": 1.2356020942408378e-06,
"loss": 1.1574,
"step": 769
},
{
"epoch": 11.49,
"learning_rate": 1.230366492146597e-06,
"loss": 1.2198,
"step": 770
},
{
"epoch": 11.51,
"learning_rate": 1.2251308900523561e-06,
"loss": 1.2281,
"step": 771
},
{
"epoch": 11.52,
"learning_rate": 1.2198952879581153e-06,
"loss": 1.3165,
"step": 772
},
{
"epoch": 11.54,
"learning_rate": 1.2146596858638745e-06,
"loss": 1.3714,
"step": 773
},
{
"epoch": 11.55,
"learning_rate": 1.2094240837696336e-06,
"loss": 1.2312,
"step": 774
},
{
"epoch": 11.57,
"learning_rate": 1.2041884816753928e-06,
"loss": 1.335,
"step": 775
},
{
"epoch": 11.58,
"learning_rate": 1.198952879581152e-06,
"loss": 1.1492,
"step": 776
},
{
"epoch": 11.6,
"learning_rate": 1.1937172774869112e-06,
"loss": 1.2127,
"step": 777
},
{
"epoch": 11.61,
"learning_rate": 1.1884816753926701e-06,
"loss": 1.2743,
"step": 778
},
{
"epoch": 11.63,
"learning_rate": 1.1832460732984293e-06,
"loss": 1.454,
"step": 779
},
{
"epoch": 11.64,
"learning_rate": 1.1780104712041885e-06,
"loss": 1.4488,
"step": 780
},
{
"epoch": 11.66,
"learning_rate": 1.1727748691099479e-06,
"loss": 1.1444,
"step": 781
},
{
"epoch": 11.67,
"learning_rate": 1.167539267015707e-06,
"loss": 1.3731,
"step": 782
},
{
"epoch": 11.69,
"learning_rate": 1.1623036649214662e-06,
"loss": 1.2858,
"step": 783
},
{
"epoch": 11.7,
"learning_rate": 1.1570680628272252e-06,
"loss": 1.5179,
"step": 784
},
{
"epoch": 11.72,
"learning_rate": 1.1518324607329843e-06,
"loss": 1.2574,
"step": 785
},
{
"epoch": 11.73,
"learning_rate": 1.1465968586387435e-06,
"loss": 1.184,
"step": 786
},
{
"epoch": 11.75,
"learning_rate": 1.1413612565445027e-06,
"loss": 1.2148,
"step": 787
},
{
"epoch": 11.76,
"learning_rate": 1.1361256544502619e-06,
"loss": 1.5347,
"step": 788
},
{
"epoch": 11.78,
"learning_rate": 1.130890052356021e-06,
"loss": 1.4017,
"step": 789
},
{
"epoch": 11.79,
"learning_rate": 1.1256544502617802e-06,
"loss": 1.3218,
"step": 790
},
{
"epoch": 11.81,
"learning_rate": 1.1204188481675394e-06,
"loss": 1.3168,
"step": 791
},
{
"epoch": 11.82,
"learning_rate": 1.1151832460732986e-06,
"loss": 1.3802,
"step": 792
},
{
"epoch": 11.84,
"learning_rate": 1.1099476439790577e-06,
"loss": 1.2083,
"step": 793
},
{
"epoch": 11.85,
"learning_rate": 1.104712041884817e-06,
"loss": 1.3997,
"step": 794
},
{
"epoch": 11.87,
"learning_rate": 1.099476439790576e-06,
"loss": 1.2884,
"step": 795
},
{
"epoch": 11.88,
"learning_rate": 1.094240837696335e-06,
"loss": 1.3002,
"step": 796
},
{
"epoch": 11.9,
"learning_rate": 1.0890052356020942e-06,
"loss": 1.2945,
"step": 797
},
{
"epoch": 11.91,
"learning_rate": 1.0837696335078534e-06,
"loss": 1.2357,
"step": 798
},
{
"epoch": 11.93,
"learning_rate": 1.0785340314136126e-06,
"loss": 1.1826,
"step": 799
},
{
"epoch": 11.94,
"learning_rate": 1.0732984293193717e-06,
"loss": 1.4052,
"step": 800
},
{
"epoch": 11.96,
"learning_rate": 1.0680628272251311e-06,
"loss": 1.3942,
"step": 801
},
{
"epoch": 11.97,
"learning_rate": 1.0628272251308903e-06,
"loss": 1.2643,
"step": 802
},
{
"epoch": 11.99,
"learning_rate": 1.0575916230366493e-06,
"loss": 1.2621,
"step": 803
},
{
"epoch": 12.0,
"learning_rate": 1.0523560209424084e-06,
"loss": 1.209,
"step": 804
},
{
"epoch": 12.0,
"eval_accuracy": 0.7014925373134329,
"eval_loss": 1.199011206626892,
"eval_roc_auc": 0.9410022590782272,
"eval_runtime": 115.3131,
"eval_samples_per_second": 0.581,
"eval_steps_per_second": 0.581,
"step": 804
},
{
"epoch": 12.01,
"learning_rate": 1.0471204188481676e-06,
"loss": 1.2375,
"step": 805
},
{
"epoch": 12.03,
"learning_rate": 1.0418848167539268e-06,
"loss": 1.2546,
"step": 806
},
{
"epoch": 12.04,
"learning_rate": 1.036649214659686e-06,
"loss": 1.3091,
"step": 807
},
{
"epoch": 12.06,
"learning_rate": 1.0314136125654451e-06,
"loss": 1.1969,
"step": 808
},
{
"epoch": 12.07,
"learning_rate": 1.0261780104712043e-06,
"loss": 1.1491,
"step": 809
},
{
"epoch": 12.09,
"learning_rate": 1.0209424083769635e-06,
"loss": 1.42,
"step": 810
},
{
"epoch": 12.1,
"learning_rate": 1.0157068062827226e-06,
"loss": 1.2053,
"step": 811
},
{
"epoch": 12.12,
"learning_rate": 1.0104712041884818e-06,
"loss": 1.2398,
"step": 812
},
{
"epoch": 12.13,
"learning_rate": 1.005235602094241e-06,
"loss": 1.179,
"step": 813
},
{
"epoch": 12.15,
"learning_rate": 1.0000000000000002e-06,
"loss": 1.2398,
"step": 814
},
{
"epoch": 12.16,
"learning_rate": 9.947643979057591e-07,
"loss": 1.3218,
"step": 815
},
{
"epoch": 12.18,
"learning_rate": 9.895287958115183e-07,
"loss": 1.2632,
"step": 816
},
{
"epoch": 12.19,
"learning_rate": 9.842931937172775e-07,
"loss": 1.2483,
"step": 817
},
{
"epoch": 12.21,
"learning_rate": 9.790575916230366e-07,
"loss": 1.2987,
"step": 818
},
{
"epoch": 12.22,
"learning_rate": 9.738219895287958e-07,
"loss": 1.5495,
"step": 819
},
{
"epoch": 12.24,
"learning_rate": 9.685863874345552e-07,
"loss": 1.1955,
"step": 820
},
{
"epoch": 12.25,
"learning_rate": 9.633507853403142e-07,
"loss": 1.1993,
"step": 821
},
{
"epoch": 12.27,
"learning_rate": 9.581151832460733e-07,
"loss": 1.3928,
"step": 822
},
{
"epoch": 12.28,
"learning_rate": 9.528795811518325e-07,
"loss": 1.3699,
"step": 823
},
{
"epoch": 12.3,
"learning_rate": 9.476439790575917e-07,
"loss": 1.2026,
"step": 824
},
{
"epoch": 12.31,
"learning_rate": 9.424083769633509e-07,
"loss": 1.4298,
"step": 825
},
{
"epoch": 12.33,
"learning_rate": 9.3717277486911e-07,
"loss": 1.1997,
"step": 826
},
{
"epoch": 12.34,
"learning_rate": 9.319371727748692e-07,
"loss": 1.2377,
"step": 827
},
{
"epoch": 12.36,
"learning_rate": 9.267015706806283e-07,
"loss": 1.3125,
"step": 828
},
{
"epoch": 12.37,
"learning_rate": 9.214659685863875e-07,
"loss": 1.373,
"step": 829
},
{
"epoch": 12.39,
"learning_rate": 9.162303664921466e-07,
"loss": 1.169,
"step": 830
},
{
"epoch": 12.4,
"learning_rate": 9.109947643979058e-07,
"loss": 1.4811,
"step": 831
},
{
"epoch": 12.42,
"learning_rate": 9.057591623036651e-07,
"loss": 1.1686,
"step": 832
},
{
"epoch": 12.43,
"learning_rate": 9.005235602094243e-07,
"loss": 1.2359,
"step": 833
},
{
"epoch": 12.45,
"learning_rate": 8.952879581151832e-07,
"loss": 1.1424,
"step": 834
},
{
"epoch": 12.46,
"learning_rate": 8.900523560209425e-07,
"loss": 1.4827,
"step": 835
},
{
"epoch": 12.48,
"learning_rate": 8.848167539267017e-07,
"loss": 1.3714,
"step": 836
},
{
"epoch": 12.49,
"learning_rate": 8.795811518324608e-07,
"loss": 1.3198,
"step": 837
},
{
"epoch": 12.51,
"learning_rate": 8.7434554973822e-07,
"loss": 1.2483,
"step": 838
},
{
"epoch": 12.52,
"learning_rate": 8.691099476439792e-07,
"loss": 1.3707,
"step": 839
},
{
"epoch": 12.54,
"learning_rate": 8.638743455497383e-07,
"loss": 1.2405,
"step": 840
},
{
"epoch": 12.55,
"learning_rate": 8.586387434554974e-07,
"loss": 1.1803,
"step": 841
},
{
"epoch": 12.57,
"learning_rate": 8.534031413612566e-07,
"loss": 1.205,
"step": 842
},
{
"epoch": 12.58,
"learning_rate": 8.481675392670158e-07,
"loss": 1.2485,
"step": 843
},
{
"epoch": 12.6,
"learning_rate": 8.42931937172775e-07,
"loss": 1.3933,
"step": 844
},
{
"epoch": 12.61,
"learning_rate": 8.376963350785341e-07,
"loss": 1.235,
"step": 845
},
{
"epoch": 12.63,
"learning_rate": 8.324607329842932e-07,
"loss": 1.6294,
"step": 846
},
{
"epoch": 12.64,
"learning_rate": 8.272251308900524e-07,
"loss": 1.2848,
"step": 847
},
{
"epoch": 12.66,
"learning_rate": 8.219895287958115e-07,
"loss": 1.3612,
"step": 848
},
{
"epoch": 12.67,
"learning_rate": 8.167539267015707e-07,
"loss": 1.2749,
"step": 849
},
{
"epoch": 12.69,
"learning_rate": 8.115183246073299e-07,
"loss": 1.4122,
"step": 850
},
{
"epoch": 12.7,
"learning_rate": 8.062827225130892e-07,
"loss": 1.62,
"step": 851
},
{
"epoch": 12.72,
"learning_rate": 8.010471204188483e-07,
"loss": 1.2063,
"step": 852
},
{
"epoch": 12.73,
"learning_rate": 7.958115183246073e-07,
"loss": 1.1882,
"step": 853
},
{
"epoch": 12.75,
"learning_rate": 7.905759162303666e-07,
"loss": 1.3236,
"step": 854
},
{
"epoch": 12.76,
"learning_rate": 7.853403141361258e-07,
"loss": 1.3277,
"step": 855
},
{
"epoch": 12.78,
"learning_rate": 7.801047120418849e-07,
"loss": 1.2155,
"step": 856
},
{
"epoch": 12.79,
"learning_rate": 7.748691099476441e-07,
"loss": 1.3083,
"step": 857
},
{
"epoch": 12.81,
"learning_rate": 7.696335078534033e-07,
"loss": 1.2612,
"step": 858
},
{
"epoch": 12.82,
"learning_rate": 7.643979057591623e-07,
"loss": 1.3424,
"step": 859
},
{
"epoch": 12.84,
"learning_rate": 7.591623036649215e-07,
"loss": 1.4033,
"step": 860
},
{
"epoch": 12.85,
"learning_rate": 7.539267015706807e-07,
"loss": 1.0953,
"step": 861
},
{
"epoch": 12.87,
"learning_rate": 7.486910994764399e-07,
"loss": 1.1239,
"step": 862
},
{
"epoch": 12.88,
"learning_rate": 7.43455497382199e-07,
"loss": 1.1509,
"step": 863
},
{
"epoch": 12.9,
"learning_rate": 7.382198952879582e-07,
"loss": 1.286,
"step": 864
},
{
"epoch": 12.91,
"learning_rate": 7.329842931937173e-07,
"loss": 1.255,
"step": 865
},
{
"epoch": 12.93,
"learning_rate": 7.277486910994765e-07,
"loss": 1.2595,
"step": 866
},
{
"epoch": 12.94,
"learning_rate": 7.225130890052356e-07,
"loss": 1.3704,
"step": 867
},
{
"epoch": 12.96,
"learning_rate": 7.172774869109948e-07,
"loss": 1.2514,
"step": 868
},
{
"epoch": 12.97,
"learning_rate": 7.12041884816754e-07,
"loss": 1.3482,
"step": 869
},
{
"epoch": 12.99,
"learning_rate": 7.068062827225131e-07,
"loss": 1.3112,
"step": 870
},
{
"epoch": 13.0,
"learning_rate": 7.015706806282722e-07,
"loss": 1.2827,
"step": 871
},
{
"epoch": 13.0,
"eval_accuracy": 0.6865671641791045,
"eval_loss": 1.2039672136306763,
"eval_roc_auc": 0.9386177600949199,
"eval_runtime": 114.8773,
"eval_samples_per_second": 0.583,
"eval_steps_per_second": 0.583,
"step": 871
},
{
"epoch": 13.01,
"learning_rate": 6.963350785340314e-07,
"loss": 1.3363,
"step": 872
},
{
"epoch": 13.03,
"learning_rate": 6.910994764397906e-07,
"loss": 1.3538,
"step": 873
},
{
"epoch": 13.04,
"learning_rate": 6.858638743455498e-07,
"loss": 1.1828,
"step": 874
},
{
"epoch": 13.06,
"learning_rate": 6.80628272251309e-07,
"loss": 1.269,
"step": 875
},
{
"epoch": 13.07,
"learning_rate": 6.753926701570682e-07,
"loss": 1.3859,
"step": 876
},
{
"epoch": 13.09,
"learning_rate": 6.701570680628274e-07,
"loss": 1.3295,
"step": 877
},
{
"epoch": 13.1,
"learning_rate": 6.649214659685864e-07,
"loss": 1.2554,
"step": 878
},
{
"epoch": 13.12,
"learning_rate": 6.596858638743456e-07,
"loss": 1.3383,
"step": 879
},
{
"epoch": 13.13,
"learning_rate": 6.544502617801048e-07,
"loss": 1.2203,
"step": 880
},
{
"epoch": 13.15,
"learning_rate": 6.49214659685864e-07,
"loss": 1.1111,
"step": 881
},
{
"epoch": 13.16,
"learning_rate": 6.439790575916231e-07,
"loss": 1.3303,
"step": 882
},
{
"epoch": 13.18,
"learning_rate": 6.387434554973823e-07,
"loss": 1.2962,
"step": 883
},
{
"epoch": 13.19,
"learning_rate": 6.335078534031414e-07,
"loss": 1.1112,
"step": 884
},
{
"epoch": 13.21,
"learning_rate": 6.282722513089005e-07,
"loss": 1.2808,
"step": 885
},
{
"epoch": 13.22,
"learning_rate": 6.230366492146597e-07,
"loss": 1.3277,
"step": 886
},
{
"epoch": 13.24,
"learning_rate": 6.178010471204189e-07,
"loss": 1.2698,
"step": 887
},
{
"epoch": 13.25,
"learning_rate": 6.125654450261781e-07,
"loss": 1.3752,
"step": 888
},
{
"epoch": 13.27,
"learning_rate": 6.073298429319372e-07,
"loss": 1.3124,
"step": 889
},
{
"epoch": 13.28,
"learning_rate": 6.020942408376964e-07,
"loss": 1.381,
"step": 890
},
{
"epoch": 13.3,
"learning_rate": 5.968586387434556e-07,
"loss": 1.1912,
"step": 891
},
{
"epoch": 13.31,
"learning_rate": 5.916230366492147e-07,
"loss": 1.1615,
"step": 892
},
{
"epoch": 13.33,
"learning_rate": 5.863874345549739e-07,
"loss": 1.2712,
"step": 893
},
{
"epoch": 13.34,
"learning_rate": 5.811518324607331e-07,
"loss": 1.2132,
"step": 894
},
{
"epoch": 13.36,
"learning_rate": 5.759162303664922e-07,
"loss": 1.1343,
"step": 895
},
{
"epoch": 13.37,
"learning_rate": 5.706806282722513e-07,
"loss": 1.1905,
"step": 896
},
{
"epoch": 13.39,
"learning_rate": 5.654450261780105e-07,
"loss": 1.1824,
"step": 897
},
{
"epoch": 13.4,
"learning_rate": 5.602094240837697e-07,
"loss": 1.2526,
"step": 898
},
{
"epoch": 13.42,
"learning_rate": 5.549738219895289e-07,
"loss": 1.2113,
"step": 899
},
{
"epoch": 13.43,
"learning_rate": 5.49738219895288e-07,
"loss": 1.2196,
"step": 900
},
{
"epoch": 13.45,
"learning_rate": 5.445026178010471e-07,
"loss": 1.3181,
"step": 901
},
{
"epoch": 13.46,
"learning_rate": 5.392670157068063e-07,
"loss": 1.4086,
"step": 902
},
{
"epoch": 13.48,
"learning_rate": 5.340314136125656e-07,
"loss": 1.2798,
"step": 903
},
{
"epoch": 13.49,
"learning_rate": 5.287958115183246e-07,
"loss": 1.2169,
"step": 904
},
{
"epoch": 13.51,
"learning_rate": 5.235602094240838e-07,
"loss": 1.3561,
"step": 905
},
{
"epoch": 13.52,
"learning_rate": 5.18324607329843e-07,
"loss": 1.3644,
"step": 906
},
{
"epoch": 13.54,
"learning_rate": 5.130890052356021e-07,
"loss": 1.2416,
"step": 907
},
{
"epoch": 13.55,
"learning_rate": 5.078534031413613e-07,
"loss": 1.231,
"step": 908
},
{
"epoch": 13.57,
"learning_rate": 5.026178010471205e-07,
"loss": 1.2572,
"step": 909
},
{
"epoch": 13.58,
"learning_rate": 4.973821989528796e-07,
"loss": 1.4077,
"step": 910
},
{
"epoch": 13.6,
"learning_rate": 4.921465968586387e-07,
"loss": 1.2956,
"step": 911
},
{
"epoch": 13.61,
"learning_rate": 4.869109947643979e-07,
"loss": 1.2224,
"step": 912
},
{
"epoch": 13.63,
"learning_rate": 4.816753926701571e-07,
"loss": 1.5222,
"step": 913
},
{
"epoch": 13.64,
"learning_rate": 4.7643979057591626e-07,
"loss": 1.4524,
"step": 914
},
{
"epoch": 13.66,
"learning_rate": 4.7120418848167543e-07,
"loss": 1.4276,
"step": 915
},
{
"epoch": 13.67,
"learning_rate": 4.659685863874346e-07,
"loss": 1.2812,
"step": 916
},
{
"epoch": 13.69,
"learning_rate": 4.6073298429319373e-07,
"loss": 1.2272,
"step": 917
},
{
"epoch": 13.7,
"learning_rate": 4.554973821989529e-07,
"loss": 1.3103,
"step": 918
},
{
"epoch": 13.72,
"learning_rate": 4.5026178010471213e-07,
"loss": 1.2374,
"step": 919
},
{
"epoch": 13.73,
"learning_rate": 4.4502617801047125e-07,
"loss": 1.1095,
"step": 920
},
{
"epoch": 13.75,
"learning_rate": 4.397905759162304e-07,
"loss": 1.2857,
"step": 921
},
{
"epoch": 13.76,
"learning_rate": 4.345549738219896e-07,
"loss": 1.1178,
"step": 922
},
{
"epoch": 13.78,
"learning_rate": 4.293193717277487e-07,
"loss": 1.1583,
"step": 923
},
{
"epoch": 13.79,
"learning_rate": 4.240837696335079e-07,
"loss": 1.3165,
"step": 924
},
{
"epoch": 13.81,
"learning_rate": 4.1884816753926706e-07,
"loss": 1.2868,
"step": 925
},
{
"epoch": 13.82,
"learning_rate": 4.136125654450262e-07,
"loss": 1.307,
"step": 926
},
{
"epoch": 13.84,
"learning_rate": 4.0837696335078536e-07,
"loss": 1.2476,
"step": 927
},
{
"epoch": 13.85,
"learning_rate": 4.031413612565446e-07,
"loss": 1.2712,
"step": 928
},
{
"epoch": 13.87,
"learning_rate": 3.9790575916230365e-07,
"loss": 1.3732,
"step": 929
},
{
"epoch": 13.88,
"learning_rate": 3.926701570680629e-07,
"loss": 1.2432,
"step": 930
},
{
"epoch": 13.9,
"learning_rate": 3.8743455497382205e-07,
"loss": 1.2804,
"step": 931
},
{
"epoch": 13.91,
"learning_rate": 3.8219895287958117e-07,
"loss": 1.2338,
"step": 932
},
{
"epoch": 13.93,
"learning_rate": 3.7696335078534035e-07,
"loss": 1.2115,
"step": 933
},
{
"epoch": 13.94,
"learning_rate": 3.717277486910995e-07,
"loss": 1.3014,
"step": 934
},
{
"epoch": 13.96,
"learning_rate": 3.6649214659685864e-07,
"loss": 1.2881,
"step": 935
},
{
"epoch": 13.97,
"learning_rate": 3.612565445026178e-07,
"loss": 1.1988,
"step": 936
},
{
"epoch": 13.99,
"learning_rate": 3.56020942408377e-07,
"loss": 1.2895,
"step": 937
},
{
"epoch": 14.0,
"learning_rate": 3.507853403141361e-07,
"loss": 1.148,
"step": 938
},
{
"epoch": 14.0,
"eval_accuracy": 0.746268656716418,
"eval_loss": 1.180509090423584,
"eval_roc_auc": 0.9466529853794006,
"eval_runtime": 114.9939,
"eval_samples_per_second": 0.583,
"eval_steps_per_second": 0.583,
"step": 938
},
{
"epoch": 14.01,
"learning_rate": 3.455497382198953e-07,
"loss": 1.2813,
"step": 939
},
{
"epoch": 14.03,
"learning_rate": 3.403141361256545e-07,
"loss": 1.2313,
"step": 940
},
{
"epoch": 14.04,
"learning_rate": 3.350785340314137e-07,
"loss": 1.3903,
"step": 941
},
{
"epoch": 14.06,
"learning_rate": 3.298429319371728e-07,
"loss": 1.1912,
"step": 942
},
{
"epoch": 14.07,
"learning_rate": 3.24607329842932e-07,
"loss": 1.3479,
"step": 943
},
{
"epoch": 14.09,
"learning_rate": 3.1937172774869115e-07,
"loss": 1.1825,
"step": 944
},
{
"epoch": 14.1,
"learning_rate": 3.1413612565445027e-07,
"loss": 1.2482,
"step": 945
},
{
"epoch": 14.12,
"learning_rate": 3.0890052356020944e-07,
"loss": 1.3458,
"step": 946
},
{
"epoch": 14.13,
"learning_rate": 3.036649214659686e-07,
"loss": 1.2576,
"step": 947
},
{
"epoch": 14.15,
"learning_rate": 2.984293193717278e-07,
"loss": 1.2473,
"step": 948
},
{
"epoch": 14.16,
"learning_rate": 2.9319371727748697e-07,
"loss": 1.312,
"step": 949
},
{
"epoch": 14.18,
"learning_rate": 2.879581151832461e-07,
"loss": 1.2814,
"step": 950
},
{
"epoch": 14.19,
"learning_rate": 2.8272251308900526e-07,
"loss": 1.2448,
"step": 951
},
{
"epoch": 14.21,
"learning_rate": 2.7748691099476443e-07,
"loss": 1.3163,
"step": 952
},
{
"epoch": 14.22,
"learning_rate": 2.7225130890052355e-07,
"loss": 1.1912,
"step": 953
},
{
"epoch": 14.24,
"learning_rate": 2.670157068062828e-07,
"loss": 1.1767,
"step": 954
},
{
"epoch": 14.25,
"learning_rate": 2.617801047120419e-07,
"loss": 1.2902,
"step": 955
},
{
"epoch": 14.27,
"learning_rate": 2.565445026178011e-07,
"loss": 1.5993,
"step": 956
},
{
"epoch": 14.28,
"learning_rate": 2.5130890052356025e-07,
"loss": 1.3344,
"step": 957
},
{
"epoch": 14.3,
"learning_rate": 2.4607329842931937e-07,
"loss": 1.2891,
"step": 958
},
{
"epoch": 14.31,
"learning_rate": 2.4083769633507854e-07,
"loss": 1.2419,
"step": 959
},
{
"epoch": 14.33,
"learning_rate": 2.3560209424083772e-07,
"loss": 1.1958,
"step": 960
},
{
"epoch": 14.34,
"learning_rate": 2.3036649214659686e-07,
"loss": 1.3736,
"step": 961
},
{
"epoch": 14.36,
"learning_rate": 2.2513089005235606e-07,
"loss": 1.1602,
"step": 962
},
{
"epoch": 14.37,
"learning_rate": 2.198952879581152e-07,
"loss": 1.2981,
"step": 963
},
{
"epoch": 14.39,
"learning_rate": 2.1465968586387436e-07,
"loss": 1.2263,
"step": 964
},
{
"epoch": 14.4,
"learning_rate": 2.0942408376963353e-07,
"loss": 1.3522,
"step": 965
},
{
"epoch": 14.42,
"learning_rate": 2.0418848167539268e-07,
"loss": 1.2269,
"step": 966
},
{
"epoch": 14.43,
"learning_rate": 1.9895287958115183e-07,
"loss": 1.3164,
"step": 967
},
{
"epoch": 14.45,
"learning_rate": 1.9371727748691103e-07,
"loss": 1.2863,
"step": 968
},
{
"epoch": 14.46,
"learning_rate": 1.8848167539267017e-07,
"loss": 1.1581,
"step": 969
},
{
"epoch": 14.48,
"learning_rate": 1.8324607329842932e-07,
"loss": 1.2892,
"step": 970
},
{
"epoch": 14.49,
"learning_rate": 1.780104712041885e-07,
"loss": 1.2545,
"step": 971
},
{
"epoch": 14.51,
"learning_rate": 1.7277486910994764e-07,
"loss": 1.2766,
"step": 972
},
{
"epoch": 14.52,
"learning_rate": 1.6753926701570684e-07,
"loss": 1.2359,
"step": 973
},
{
"epoch": 14.54,
"learning_rate": 1.62303664921466e-07,
"loss": 1.1912,
"step": 974
},
{
"epoch": 14.55,
"learning_rate": 1.5706806282722514e-07,
"loss": 1.2958,
"step": 975
},
{
"epoch": 14.57,
"learning_rate": 1.518324607329843e-07,
"loss": 1.1492,
"step": 976
},
{
"epoch": 14.58,
"learning_rate": 1.4659685863874348e-07,
"loss": 1.3414,
"step": 977
},
{
"epoch": 14.6,
"learning_rate": 1.4136125654450263e-07,
"loss": 1.4046,
"step": 978
},
{
"epoch": 14.61,
"learning_rate": 1.3612565445026178e-07,
"loss": 1.1398,
"step": 979
},
{
"epoch": 14.63,
"learning_rate": 1.3089005235602095e-07,
"loss": 1.115,
"step": 980
},
{
"epoch": 14.64,
"learning_rate": 1.2565445026178012e-07,
"loss": 1.3315,
"step": 981
},
{
"epoch": 14.66,
"learning_rate": 1.2041884816753927e-07,
"loss": 1.419,
"step": 982
},
{
"epoch": 14.67,
"learning_rate": 1.1518324607329843e-07,
"loss": 1.2696,
"step": 983
},
{
"epoch": 14.69,
"learning_rate": 1.099476439790576e-07,
"loss": 1.3029,
"step": 984
},
{
"epoch": 14.7,
"learning_rate": 1.0471204188481677e-07,
"loss": 1.387,
"step": 985
},
{
"epoch": 14.72,
"learning_rate": 9.947643979057591e-08,
"loss": 1.2613,
"step": 986
},
{
"epoch": 14.73,
"learning_rate": 9.424083769633509e-08,
"loss": 1.1824,
"step": 987
},
{
"epoch": 14.75,
"learning_rate": 8.900523560209425e-08,
"loss": 1.25,
"step": 988
},
{
"epoch": 14.76,
"learning_rate": 8.376963350785342e-08,
"loss": 1.2513,
"step": 989
},
{
"epoch": 14.78,
"learning_rate": 7.853403141361257e-08,
"loss": 1.3408,
"step": 990
},
{
"epoch": 14.79,
"learning_rate": 7.329842931937174e-08,
"loss": 1.261,
"step": 991
},
{
"epoch": 14.81,
"learning_rate": 6.806282722513089e-08,
"loss": 1.2401,
"step": 992
},
{
"epoch": 14.82,
"learning_rate": 6.282722513089006e-08,
"loss": 1.1627,
"step": 993
},
{
"epoch": 14.84,
"learning_rate": 5.7591623036649216e-08,
"loss": 1.1001,
"step": 994
},
{
"epoch": 14.85,
"learning_rate": 5.235602094240838e-08,
"loss": 1.4284,
"step": 995
},
{
"epoch": 14.87,
"learning_rate": 4.712041884816754e-08,
"loss": 1.2977,
"step": 996
},
{
"epoch": 14.88,
"learning_rate": 4.188481675392671e-08,
"loss": 1.4529,
"step": 997
},
{
"epoch": 14.9,
"learning_rate": 3.664921465968587e-08,
"loss": 1.3078,
"step": 998
},
{
"epoch": 14.91,
"learning_rate": 3.141361256544503e-08,
"loss": 1.365,
"step": 999
},
{
"epoch": 14.93,
"learning_rate": 2.617801047120419e-08,
"loss": 1.2315,
"step": 1000
},
{
"epoch": 14.94,
"learning_rate": 2.0942408376963355e-08,
"loss": 1.1403,
"step": 1001
},
{
"epoch": 14.96,
"learning_rate": 1.5706806282722516e-08,
"loss": 1.2835,
"step": 1002
},
{
"epoch": 14.97,
"learning_rate": 1.0471204188481678e-08,
"loss": 1.2234,
"step": 1003
},
{
"epoch": 14.99,
"learning_rate": 5.235602094240839e-09,
"loss": 1.4951,
"step": 1004
},
{
"epoch": 15.0,
"learning_rate": 0.0,
"loss": 1.3951,
"step": 1005
},
{
"epoch": 15.0,
"eval_accuracy": 0.7313432835820896,
"eval_loss": 1.180140495300293,
"eval_roc_auc": 0.9414392219829161,
"eval_runtime": 115.5119,
"eval_samples_per_second": 0.58,
"eval_steps_per_second": 0.58,
"step": 1005
}
],
"max_steps": 1005,
"num_train_epochs": 15,
"total_flos": 3.6216920886809103e+18,
"trial_name": null,
"trial_params": null
}