dima806's picture
Upload folder using huggingface_hub
81f5f67
raw
history blame
No virus
53.2 kB
{
"best_metric": 0.5413519740104675,
"best_model_checkpoint": "musical_instrument_detection/checkpoint-438",
"epoch": 2.0,
"global_step": 438,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 1.0000000000000001e-07,
"loss": 1.1483,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 2.0000000000000002e-07,
"loss": 1.0634,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 3.0000000000000004e-07,
"loss": 1.0975,
"step": 3
},
{
"epoch": 0.02,
"learning_rate": 4.0000000000000003e-07,
"loss": 1.0573,
"step": 4
},
{
"epoch": 0.02,
"learning_rate": 5.000000000000001e-07,
"loss": 1.1036,
"step": 5
},
{
"epoch": 0.03,
"learning_rate": 6.000000000000001e-07,
"loss": 1.1195,
"step": 6
},
{
"epoch": 0.03,
"learning_rate": 7.000000000000001e-07,
"loss": 1.104,
"step": 7
},
{
"epoch": 0.04,
"learning_rate": 8.000000000000001e-07,
"loss": 1.0942,
"step": 8
},
{
"epoch": 0.04,
"learning_rate": 9.000000000000001e-07,
"loss": 1.0877,
"step": 9
},
{
"epoch": 0.05,
"learning_rate": 1.0000000000000002e-06,
"loss": 1.0536,
"step": 10
},
{
"epoch": 0.05,
"learning_rate": 1.1e-06,
"loss": 1.0755,
"step": 11
},
{
"epoch": 0.05,
"learning_rate": 1.2000000000000002e-06,
"loss": 1.0911,
"step": 12
},
{
"epoch": 0.06,
"learning_rate": 1.3e-06,
"loss": 1.0904,
"step": 13
},
{
"epoch": 0.06,
"learning_rate": 1.4000000000000001e-06,
"loss": 1.1105,
"step": 14
},
{
"epoch": 0.07,
"learning_rate": 1.5e-06,
"loss": 1.0783,
"step": 15
},
{
"epoch": 0.07,
"learning_rate": 1.6000000000000001e-06,
"loss": 1.0853,
"step": 16
},
{
"epoch": 0.08,
"learning_rate": 1.7000000000000002e-06,
"loss": 1.0752,
"step": 17
},
{
"epoch": 0.08,
"learning_rate": 1.8000000000000001e-06,
"loss": 1.0999,
"step": 18
},
{
"epoch": 0.09,
"learning_rate": 1.9000000000000002e-06,
"loss": 1.1271,
"step": 19
},
{
"epoch": 0.09,
"learning_rate": 2.0000000000000003e-06,
"loss": 1.0918,
"step": 20
},
{
"epoch": 0.1,
"learning_rate": 2.1000000000000002e-06,
"loss": 1.1036,
"step": 21
},
{
"epoch": 0.1,
"learning_rate": 2.2e-06,
"loss": 1.0844,
"step": 22
},
{
"epoch": 0.11,
"learning_rate": 2.3000000000000004e-06,
"loss": 1.0935,
"step": 23
},
{
"epoch": 0.11,
"learning_rate": 2.4000000000000003e-06,
"loss": 1.0756,
"step": 24
},
{
"epoch": 0.11,
"learning_rate": 2.5e-06,
"loss": 1.1509,
"step": 25
},
{
"epoch": 0.12,
"learning_rate": 2.6e-06,
"loss": 1.1255,
"step": 26
},
{
"epoch": 0.12,
"learning_rate": 2.7000000000000004e-06,
"loss": 1.0801,
"step": 27
},
{
"epoch": 0.13,
"learning_rate": 2.8000000000000003e-06,
"loss": 1.0435,
"step": 28
},
{
"epoch": 0.13,
"learning_rate": 2.9e-06,
"loss": 1.0866,
"step": 29
},
{
"epoch": 0.14,
"learning_rate": 3e-06,
"loss": 0.9917,
"step": 30
},
{
"epoch": 0.14,
"learning_rate": 3.1000000000000004e-06,
"loss": 1.1184,
"step": 31
},
{
"epoch": 0.15,
"learning_rate": 3.2000000000000003e-06,
"loss": 1.0805,
"step": 32
},
{
"epoch": 0.15,
"learning_rate": 3.3000000000000006e-06,
"loss": 1.1095,
"step": 33
},
{
"epoch": 0.16,
"learning_rate": 3.4000000000000005e-06,
"loss": 1.0581,
"step": 34
},
{
"epoch": 0.16,
"learning_rate": 3.5e-06,
"loss": 1.0932,
"step": 35
},
{
"epoch": 0.16,
"learning_rate": 3.6000000000000003e-06,
"loss": 1.0721,
"step": 36
},
{
"epoch": 0.17,
"learning_rate": 3.7e-06,
"loss": 1.1108,
"step": 37
},
{
"epoch": 0.17,
"learning_rate": 3.8000000000000005e-06,
"loss": 1.0906,
"step": 38
},
{
"epoch": 0.18,
"learning_rate": 3.900000000000001e-06,
"loss": 1.0774,
"step": 39
},
{
"epoch": 0.18,
"learning_rate": 4.000000000000001e-06,
"loss": 1.0953,
"step": 40
},
{
"epoch": 0.19,
"learning_rate": 4.1e-06,
"loss": 1.1005,
"step": 41
},
{
"epoch": 0.19,
"learning_rate": 4.2000000000000004e-06,
"loss": 1.1064,
"step": 42
},
{
"epoch": 0.2,
"learning_rate": 4.3e-06,
"loss": 1.091,
"step": 43
},
{
"epoch": 0.2,
"learning_rate": 4.4e-06,
"loss": 1.0967,
"step": 44
},
{
"epoch": 0.21,
"learning_rate": 4.5e-06,
"loss": 1.0887,
"step": 45
},
{
"epoch": 0.21,
"learning_rate": 4.600000000000001e-06,
"loss": 1.0715,
"step": 46
},
{
"epoch": 0.21,
"learning_rate": 4.7e-06,
"loss": 1.0735,
"step": 47
},
{
"epoch": 0.22,
"learning_rate": 4.800000000000001e-06,
"loss": 1.0866,
"step": 48
},
{
"epoch": 0.22,
"learning_rate": 4.9000000000000005e-06,
"loss": 1.0834,
"step": 49
},
{
"epoch": 0.23,
"learning_rate": 5e-06,
"loss": 1.068,
"step": 50
},
{
"epoch": 0.23,
"learning_rate": 4.9871134020618565e-06,
"loss": 1.0301,
"step": 51
},
{
"epoch": 0.24,
"learning_rate": 4.974226804123712e-06,
"loss": 1.1063,
"step": 52
},
{
"epoch": 0.24,
"learning_rate": 4.961340206185568e-06,
"loss": 1.0696,
"step": 53
},
{
"epoch": 0.25,
"learning_rate": 4.948453608247423e-06,
"loss": 1.0762,
"step": 54
},
{
"epoch": 0.25,
"learning_rate": 4.935567010309279e-06,
"loss": 1.0841,
"step": 55
},
{
"epoch": 0.26,
"learning_rate": 4.922680412371135e-06,
"loss": 1.0693,
"step": 56
},
{
"epoch": 0.26,
"learning_rate": 4.9097938144329895e-06,
"loss": 1.0407,
"step": 57
},
{
"epoch": 0.26,
"learning_rate": 4.8969072164948455e-06,
"loss": 1.0572,
"step": 58
},
{
"epoch": 0.27,
"learning_rate": 4.884020618556702e-06,
"loss": 1.0468,
"step": 59
},
{
"epoch": 0.27,
"learning_rate": 4.871134020618557e-06,
"loss": 1.0365,
"step": 60
},
{
"epoch": 0.28,
"learning_rate": 4.858247422680413e-06,
"loss": 1.0546,
"step": 61
},
{
"epoch": 0.28,
"learning_rate": 4.845360824742268e-06,
"loss": 1.0273,
"step": 62
},
{
"epoch": 0.29,
"learning_rate": 4.832474226804124e-06,
"loss": 1.0308,
"step": 63
},
{
"epoch": 0.29,
"learning_rate": 4.81958762886598e-06,
"loss": 1.0664,
"step": 64
},
{
"epoch": 0.3,
"learning_rate": 4.8067010309278354e-06,
"loss": 1.0378,
"step": 65
},
{
"epoch": 0.3,
"learning_rate": 4.7938144329896915e-06,
"loss": 0.9739,
"step": 66
},
{
"epoch": 0.31,
"learning_rate": 4.780927835051547e-06,
"loss": 1.0715,
"step": 67
},
{
"epoch": 0.31,
"learning_rate": 4.768041237113403e-06,
"loss": 1.0642,
"step": 68
},
{
"epoch": 0.32,
"learning_rate": 4.755154639175258e-06,
"loss": 1.0663,
"step": 69
},
{
"epoch": 0.32,
"learning_rate": 4.742268041237113e-06,
"loss": 1.013,
"step": 70
},
{
"epoch": 0.32,
"learning_rate": 4.729381443298969e-06,
"loss": 1.0519,
"step": 71
},
{
"epoch": 0.33,
"learning_rate": 4.716494845360825e-06,
"loss": 1.0413,
"step": 72
},
{
"epoch": 0.33,
"learning_rate": 4.7036082474226806e-06,
"loss": 1.0078,
"step": 73
},
{
"epoch": 0.34,
"learning_rate": 4.690721649484537e-06,
"loss": 1.06,
"step": 74
},
{
"epoch": 0.34,
"learning_rate": 4.677835051546392e-06,
"loss": 1.0189,
"step": 75
},
{
"epoch": 0.35,
"learning_rate": 4.664948453608248e-06,
"loss": 1.0302,
"step": 76
},
{
"epoch": 0.35,
"learning_rate": 4.652061855670104e-06,
"loss": 1.0251,
"step": 77
},
{
"epoch": 0.36,
"learning_rate": 4.639175257731959e-06,
"loss": 1.0067,
"step": 78
},
{
"epoch": 0.36,
"learning_rate": 4.626288659793815e-06,
"loss": 1.0338,
"step": 79
},
{
"epoch": 0.37,
"learning_rate": 4.6134020618556705e-06,
"loss": 1.0276,
"step": 80
},
{
"epoch": 0.37,
"learning_rate": 4.600515463917526e-06,
"loss": 1.052,
"step": 81
},
{
"epoch": 0.37,
"learning_rate": 4.587628865979382e-06,
"loss": 1.0523,
"step": 82
},
{
"epoch": 0.38,
"learning_rate": 4.574742268041237e-06,
"loss": 0.9521,
"step": 83
},
{
"epoch": 0.38,
"learning_rate": 4.561855670103093e-06,
"loss": 0.9675,
"step": 84
},
{
"epoch": 0.39,
"learning_rate": 4.548969072164949e-06,
"loss": 1.0056,
"step": 85
},
{
"epoch": 0.39,
"learning_rate": 4.536082474226804e-06,
"loss": 0.9308,
"step": 86
},
{
"epoch": 0.4,
"learning_rate": 4.52319587628866e-06,
"loss": 1.0203,
"step": 87
},
{
"epoch": 0.4,
"learning_rate": 4.510309278350516e-06,
"loss": 1.0023,
"step": 88
},
{
"epoch": 0.41,
"learning_rate": 4.497422680412372e-06,
"loss": 0.9412,
"step": 89
},
{
"epoch": 0.41,
"learning_rate": 4.484536082474228e-06,
"loss": 1.0002,
"step": 90
},
{
"epoch": 0.42,
"learning_rate": 4.471649484536083e-06,
"loss": 1.0292,
"step": 91
},
{
"epoch": 0.42,
"learning_rate": 4.458762886597939e-06,
"loss": 0.9523,
"step": 92
},
{
"epoch": 0.42,
"learning_rate": 4.445876288659794e-06,
"loss": 1.0477,
"step": 93
},
{
"epoch": 0.43,
"learning_rate": 4.4329896907216494e-06,
"loss": 1.025,
"step": 94
},
{
"epoch": 0.43,
"learning_rate": 4.4201030927835055e-06,
"loss": 0.9427,
"step": 95
},
{
"epoch": 0.44,
"learning_rate": 4.407216494845361e-06,
"loss": 0.9139,
"step": 96
},
{
"epoch": 0.44,
"learning_rate": 4.394329896907217e-06,
"loss": 0.9125,
"step": 97
},
{
"epoch": 0.45,
"learning_rate": 4.381443298969073e-06,
"loss": 0.945,
"step": 98
},
{
"epoch": 0.45,
"learning_rate": 4.368556701030928e-06,
"loss": 0.9305,
"step": 99
},
{
"epoch": 0.46,
"learning_rate": 4.355670103092784e-06,
"loss": 0.933,
"step": 100
},
{
"epoch": 0.46,
"learning_rate": 4.342783505154639e-06,
"loss": 1.1255,
"step": 101
},
{
"epoch": 0.47,
"learning_rate": 4.329896907216495e-06,
"loss": 0.9796,
"step": 102
},
{
"epoch": 0.47,
"learning_rate": 4.3170103092783515e-06,
"loss": 1.0993,
"step": 103
},
{
"epoch": 0.47,
"learning_rate": 4.304123711340207e-06,
"loss": 0.9453,
"step": 104
},
{
"epoch": 0.48,
"learning_rate": 4.291237113402062e-06,
"loss": 0.9022,
"step": 105
},
{
"epoch": 0.48,
"learning_rate": 4.278350515463918e-06,
"loss": 0.8398,
"step": 106
},
{
"epoch": 0.49,
"learning_rate": 4.265463917525773e-06,
"loss": 1.1011,
"step": 107
},
{
"epoch": 0.49,
"learning_rate": 4.252577319587629e-06,
"loss": 0.8818,
"step": 108
},
{
"epoch": 0.5,
"learning_rate": 4.2396907216494845e-06,
"loss": 1.011,
"step": 109
},
{
"epoch": 0.5,
"learning_rate": 4.2268041237113405e-06,
"loss": 0.9196,
"step": 110
},
{
"epoch": 0.51,
"learning_rate": 4.213917525773197e-06,
"loss": 0.918,
"step": 111
},
{
"epoch": 0.51,
"learning_rate": 4.201030927835052e-06,
"loss": 0.9394,
"step": 112
},
{
"epoch": 0.52,
"learning_rate": 4.188144329896908e-06,
"loss": 1.0424,
"step": 113
},
{
"epoch": 0.52,
"learning_rate": 4.175257731958763e-06,
"loss": 0.888,
"step": 114
},
{
"epoch": 0.53,
"learning_rate": 4.162371134020619e-06,
"loss": 0.8633,
"step": 115
},
{
"epoch": 0.53,
"learning_rate": 4.149484536082475e-06,
"loss": 0.9223,
"step": 116
},
{
"epoch": 0.53,
"learning_rate": 4.13659793814433e-06,
"loss": 0.8778,
"step": 117
},
{
"epoch": 0.54,
"learning_rate": 4.123711340206186e-06,
"loss": 0.8309,
"step": 118
},
{
"epoch": 0.54,
"learning_rate": 4.110824742268042e-06,
"loss": 1.0435,
"step": 119
},
{
"epoch": 0.55,
"learning_rate": 4.097938144329897e-06,
"loss": 1.0464,
"step": 120
},
{
"epoch": 0.55,
"learning_rate": 4.085051546391753e-06,
"loss": 0.8318,
"step": 121
},
{
"epoch": 0.56,
"learning_rate": 4.072164948453608e-06,
"loss": 1.0057,
"step": 122
},
{
"epoch": 0.56,
"learning_rate": 4.059278350515464e-06,
"loss": 0.9555,
"step": 123
},
{
"epoch": 0.57,
"learning_rate": 4.04639175257732e-06,
"loss": 0.9886,
"step": 124
},
{
"epoch": 0.57,
"learning_rate": 4.033505154639176e-06,
"loss": 0.9338,
"step": 125
},
{
"epoch": 0.58,
"learning_rate": 4.020618556701032e-06,
"loss": 1.0512,
"step": 126
},
{
"epoch": 0.58,
"learning_rate": 4.007731958762887e-06,
"loss": 0.9203,
"step": 127
},
{
"epoch": 0.58,
"learning_rate": 3.994845360824743e-06,
"loss": 1.0229,
"step": 128
},
{
"epoch": 0.59,
"learning_rate": 3.981958762886598e-06,
"loss": 0.955,
"step": 129
},
{
"epoch": 0.59,
"learning_rate": 3.969072164948453e-06,
"loss": 0.7855,
"step": 130
},
{
"epoch": 0.6,
"learning_rate": 3.956185567010309e-06,
"loss": 0.9133,
"step": 131
},
{
"epoch": 0.6,
"learning_rate": 3.9432989690721655e-06,
"loss": 0.8801,
"step": 132
},
{
"epoch": 0.61,
"learning_rate": 3.930412371134021e-06,
"loss": 0.9299,
"step": 133
},
{
"epoch": 0.61,
"learning_rate": 3.917525773195877e-06,
"loss": 0.8896,
"step": 134
},
{
"epoch": 0.62,
"learning_rate": 3.904639175257732e-06,
"loss": 0.9118,
"step": 135
},
{
"epoch": 0.62,
"learning_rate": 3.891752577319588e-06,
"loss": 0.9091,
"step": 136
},
{
"epoch": 0.63,
"learning_rate": 3.878865979381444e-06,
"loss": 0.9613,
"step": 137
},
{
"epoch": 0.63,
"learning_rate": 3.865979381443299e-06,
"loss": 1.0924,
"step": 138
},
{
"epoch": 0.63,
"learning_rate": 3.853092783505155e-06,
"loss": 0.8309,
"step": 139
},
{
"epoch": 0.64,
"learning_rate": 3.840206185567011e-06,
"loss": 0.9993,
"step": 140
},
{
"epoch": 0.64,
"learning_rate": 3.827319587628866e-06,
"loss": 0.9873,
"step": 141
},
{
"epoch": 0.65,
"learning_rate": 3.814432989690722e-06,
"loss": 0.9838,
"step": 142
},
{
"epoch": 0.65,
"learning_rate": 3.8015463917525775e-06,
"loss": 0.7721,
"step": 143
},
{
"epoch": 0.66,
"learning_rate": 3.788659793814433e-06,
"loss": 0.8702,
"step": 144
},
{
"epoch": 0.66,
"learning_rate": 3.775773195876289e-06,
"loss": 0.8558,
"step": 145
},
{
"epoch": 0.67,
"learning_rate": 3.7628865979381445e-06,
"loss": 0.9182,
"step": 146
},
{
"epoch": 0.67,
"learning_rate": 3.7500000000000005e-06,
"loss": 0.8565,
"step": 147
},
{
"epoch": 0.68,
"learning_rate": 3.737113402061856e-06,
"loss": 0.7624,
"step": 148
},
{
"epoch": 0.68,
"learning_rate": 3.724226804123712e-06,
"loss": 1.0197,
"step": 149
},
{
"epoch": 0.68,
"learning_rate": 3.7113402061855674e-06,
"loss": 0.7886,
"step": 150
},
{
"epoch": 0.69,
"learning_rate": 3.698453608247423e-06,
"loss": 1.0184,
"step": 151
},
{
"epoch": 0.69,
"learning_rate": 3.6855670103092787e-06,
"loss": 0.9235,
"step": 152
},
{
"epoch": 0.7,
"learning_rate": 3.6726804123711348e-06,
"loss": 0.9183,
"step": 153
},
{
"epoch": 0.7,
"learning_rate": 3.6597938144329896e-06,
"loss": 0.9908,
"step": 154
},
{
"epoch": 0.71,
"learning_rate": 3.6469072164948456e-06,
"loss": 0.849,
"step": 155
},
{
"epoch": 0.71,
"learning_rate": 3.6340206185567013e-06,
"loss": 0.8359,
"step": 156
},
{
"epoch": 0.72,
"learning_rate": 3.621134020618557e-06,
"loss": 0.8857,
"step": 157
},
{
"epoch": 0.72,
"learning_rate": 3.6082474226804126e-06,
"loss": 0.9761,
"step": 158
},
{
"epoch": 0.73,
"learning_rate": 3.595360824742268e-06,
"loss": 0.9443,
"step": 159
},
{
"epoch": 0.73,
"learning_rate": 3.582474226804124e-06,
"loss": 0.8525,
"step": 160
},
{
"epoch": 0.74,
"learning_rate": 3.56958762886598e-06,
"loss": 0.8434,
"step": 161
},
{
"epoch": 0.74,
"learning_rate": 3.5567010309278356e-06,
"loss": 0.9504,
"step": 162
},
{
"epoch": 0.74,
"learning_rate": 3.543814432989691e-06,
"loss": 0.8985,
"step": 163
},
{
"epoch": 0.75,
"learning_rate": 3.530927835051547e-06,
"loss": 0.891,
"step": 164
},
{
"epoch": 0.75,
"learning_rate": 3.5180412371134025e-06,
"loss": 0.7678,
"step": 165
},
{
"epoch": 0.76,
"learning_rate": 3.5051546391752577e-06,
"loss": 0.9885,
"step": 166
},
{
"epoch": 0.76,
"learning_rate": 3.4922680412371133e-06,
"loss": 0.7841,
"step": 167
},
{
"epoch": 0.77,
"learning_rate": 3.4793814432989694e-06,
"loss": 0.881,
"step": 168
},
{
"epoch": 0.77,
"learning_rate": 3.466494845360825e-06,
"loss": 0.8883,
"step": 169
},
{
"epoch": 0.78,
"learning_rate": 3.4536082474226807e-06,
"loss": 0.9482,
"step": 170
},
{
"epoch": 0.78,
"learning_rate": 3.4407216494845363e-06,
"loss": 0.9246,
"step": 171
},
{
"epoch": 0.79,
"learning_rate": 3.427835051546392e-06,
"loss": 0.9037,
"step": 172
},
{
"epoch": 0.79,
"learning_rate": 3.4149484536082476e-06,
"loss": 0.9391,
"step": 173
},
{
"epoch": 0.79,
"learning_rate": 3.4020618556701037e-06,
"loss": 0.8038,
"step": 174
},
{
"epoch": 0.8,
"learning_rate": 3.3891752577319593e-06,
"loss": 0.7992,
"step": 175
},
{
"epoch": 0.8,
"learning_rate": 3.376288659793815e-06,
"loss": 0.8343,
"step": 176
},
{
"epoch": 0.81,
"learning_rate": 3.3634020618556706e-06,
"loss": 0.9261,
"step": 177
},
{
"epoch": 0.81,
"learning_rate": 3.350515463917526e-06,
"loss": 0.8691,
"step": 178
},
{
"epoch": 0.82,
"learning_rate": 3.3376288659793814e-06,
"loss": 0.7725,
"step": 179
},
{
"epoch": 0.82,
"learning_rate": 3.324742268041237e-06,
"loss": 0.8285,
"step": 180
},
{
"epoch": 0.83,
"learning_rate": 3.311855670103093e-06,
"loss": 0.8843,
"step": 181
},
{
"epoch": 0.83,
"learning_rate": 3.298969072164949e-06,
"loss": 0.8114,
"step": 182
},
{
"epoch": 0.84,
"learning_rate": 3.2860824742268044e-06,
"loss": 0.8893,
"step": 183
},
{
"epoch": 0.84,
"learning_rate": 3.27319587628866e-06,
"loss": 0.8186,
"step": 184
},
{
"epoch": 0.84,
"learning_rate": 3.2603092783505157e-06,
"loss": 0.9122,
"step": 185
},
{
"epoch": 0.85,
"learning_rate": 3.2474226804123714e-06,
"loss": 0.8556,
"step": 186
},
{
"epoch": 0.85,
"learning_rate": 3.2345360824742274e-06,
"loss": 0.8639,
"step": 187
},
{
"epoch": 0.86,
"learning_rate": 3.221649484536083e-06,
"loss": 0.7592,
"step": 188
},
{
"epoch": 0.86,
"learning_rate": 3.2087628865979387e-06,
"loss": 0.7713,
"step": 189
},
{
"epoch": 0.87,
"learning_rate": 3.195876288659794e-06,
"loss": 0.8039,
"step": 190
},
{
"epoch": 0.87,
"learning_rate": 3.1829896907216496e-06,
"loss": 0.8808,
"step": 191
},
{
"epoch": 0.88,
"learning_rate": 3.170103092783505e-06,
"loss": 0.6452,
"step": 192
},
{
"epoch": 0.88,
"learning_rate": 3.157216494845361e-06,
"loss": 0.7615,
"step": 193
},
{
"epoch": 0.89,
"learning_rate": 3.1443298969072165e-06,
"loss": 0.943,
"step": 194
},
{
"epoch": 0.89,
"learning_rate": 3.1314432989690725e-06,
"loss": 0.7846,
"step": 195
},
{
"epoch": 0.89,
"learning_rate": 3.118556701030928e-06,
"loss": 0.9415,
"step": 196
},
{
"epoch": 0.9,
"learning_rate": 3.105670103092784e-06,
"loss": 0.6865,
"step": 197
},
{
"epoch": 0.9,
"learning_rate": 3.0927835051546395e-06,
"loss": 0.7068,
"step": 198
},
{
"epoch": 0.91,
"learning_rate": 3.079896907216495e-06,
"loss": 0.809,
"step": 199
},
{
"epoch": 0.91,
"learning_rate": 3.067010309278351e-06,
"loss": 0.7563,
"step": 200
},
{
"epoch": 0.92,
"learning_rate": 3.054123711340207e-06,
"loss": 0.7708,
"step": 201
},
{
"epoch": 0.92,
"learning_rate": 3.041237113402062e-06,
"loss": 0.7067,
"step": 202
},
{
"epoch": 0.93,
"learning_rate": 3.0283505154639177e-06,
"loss": 0.7392,
"step": 203
},
{
"epoch": 0.93,
"learning_rate": 3.0154639175257733e-06,
"loss": 0.6513,
"step": 204
},
{
"epoch": 0.94,
"learning_rate": 3.002577319587629e-06,
"loss": 0.8537,
"step": 205
},
{
"epoch": 0.94,
"learning_rate": 2.9896907216494846e-06,
"loss": 0.765,
"step": 206
},
{
"epoch": 0.95,
"learning_rate": 2.9768041237113402e-06,
"loss": 0.737,
"step": 207
},
{
"epoch": 0.95,
"learning_rate": 2.9639175257731963e-06,
"loss": 0.7372,
"step": 208
},
{
"epoch": 0.95,
"learning_rate": 2.951030927835052e-06,
"loss": 0.7462,
"step": 209
},
{
"epoch": 0.96,
"learning_rate": 2.9381443298969076e-06,
"loss": 0.8895,
"step": 210
},
{
"epoch": 0.96,
"learning_rate": 2.9252577319587632e-06,
"loss": 0.6803,
"step": 211
},
{
"epoch": 0.97,
"learning_rate": 2.912371134020619e-06,
"loss": 0.7459,
"step": 212
},
{
"epoch": 0.97,
"learning_rate": 2.899484536082475e-06,
"loss": 0.779,
"step": 213
},
{
"epoch": 0.98,
"learning_rate": 2.8865979381443297e-06,
"loss": 0.7655,
"step": 214
},
{
"epoch": 0.98,
"learning_rate": 2.8737113402061858e-06,
"loss": 0.8121,
"step": 215
},
{
"epoch": 0.99,
"learning_rate": 2.8608247422680414e-06,
"loss": 0.8556,
"step": 216
},
{
"epoch": 0.99,
"learning_rate": 2.847938144329897e-06,
"loss": 0.8671,
"step": 217
},
{
"epoch": 1.0,
"learning_rate": 2.8350515463917527e-06,
"loss": 0.7443,
"step": 218
},
{
"epoch": 1.0,
"learning_rate": 2.8221649484536083e-06,
"loss": 0.6609,
"step": 219
},
{
"epoch": 1.0,
"eval_accuracy": 0.8904109589041096,
"eval_loss": 0.720801591873169,
"eval_roc_auc": 0.9748218767577326,
"eval_runtime": 52.2723,
"eval_samples_per_second": 4.19,
"eval_steps_per_second": 4.19,
"step": 219
},
{
"epoch": 1.0,
"learning_rate": 2.809278350515464e-06,
"loss": 0.7558,
"step": 220
},
{
"epoch": 1.01,
"learning_rate": 2.79639175257732e-06,
"loss": 0.7227,
"step": 221
},
{
"epoch": 1.01,
"learning_rate": 2.7835051546391757e-06,
"loss": 0.6551,
"step": 222
},
{
"epoch": 1.02,
"learning_rate": 2.7706185567010313e-06,
"loss": 0.7291,
"step": 223
},
{
"epoch": 1.02,
"learning_rate": 2.757731958762887e-06,
"loss": 0.7301,
"step": 224
},
{
"epoch": 1.03,
"learning_rate": 2.7448453608247426e-06,
"loss": 0.7307,
"step": 225
},
{
"epoch": 1.03,
"learning_rate": 2.731958762886598e-06,
"loss": 0.7897,
"step": 226
},
{
"epoch": 1.04,
"learning_rate": 2.7190721649484535e-06,
"loss": 0.7132,
"step": 227
},
{
"epoch": 1.04,
"learning_rate": 2.7061855670103095e-06,
"loss": 0.8203,
"step": 228
},
{
"epoch": 1.05,
"learning_rate": 2.693298969072165e-06,
"loss": 0.7325,
"step": 229
},
{
"epoch": 1.05,
"learning_rate": 2.680412371134021e-06,
"loss": 0.8294,
"step": 230
},
{
"epoch": 1.05,
"learning_rate": 2.6675257731958765e-06,
"loss": 0.7761,
"step": 231
},
{
"epoch": 1.06,
"learning_rate": 2.654639175257732e-06,
"loss": 0.7861,
"step": 232
},
{
"epoch": 1.06,
"learning_rate": 2.6417525773195877e-06,
"loss": 0.8239,
"step": 233
},
{
"epoch": 1.07,
"learning_rate": 2.628865979381444e-06,
"loss": 0.8216,
"step": 234
},
{
"epoch": 1.07,
"learning_rate": 2.6159793814432994e-06,
"loss": 0.8448,
"step": 235
},
{
"epoch": 1.08,
"learning_rate": 2.603092783505155e-06,
"loss": 0.6724,
"step": 236
},
{
"epoch": 1.08,
"learning_rate": 2.5902061855670107e-06,
"loss": 0.6417,
"step": 237
},
{
"epoch": 1.09,
"learning_rate": 2.577319587628866e-06,
"loss": 0.7414,
"step": 238
},
{
"epoch": 1.09,
"learning_rate": 2.5644329896907216e-06,
"loss": 0.7388,
"step": 239
},
{
"epoch": 1.1,
"learning_rate": 2.5515463917525772e-06,
"loss": 0.7149,
"step": 240
},
{
"epoch": 1.1,
"learning_rate": 2.538659793814433e-06,
"loss": 0.7747,
"step": 241
},
{
"epoch": 1.11,
"learning_rate": 2.525773195876289e-06,
"loss": 0.6918,
"step": 242
},
{
"epoch": 1.11,
"learning_rate": 2.5128865979381446e-06,
"loss": 0.8141,
"step": 243
},
{
"epoch": 1.11,
"learning_rate": 2.5e-06,
"loss": 0.9045,
"step": 244
},
{
"epoch": 1.12,
"learning_rate": 2.487113402061856e-06,
"loss": 0.8587,
"step": 245
},
{
"epoch": 1.12,
"learning_rate": 2.4742268041237115e-06,
"loss": 0.6935,
"step": 246
},
{
"epoch": 1.13,
"learning_rate": 2.4613402061855676e-06,
"loss": 0.7832,
"step": 247
},
{
"epoch": 1.13,
"learning_rate": 2.4484536082474228e-06,
"loss": 0.7432,
"step": 248
},
{
"epoch": 1.14,
"learning_rate": 2.4355670103092784e-06,
"loss": 0.7383,
"step": 249
},
{
"epoch": 1.14,
"learning_rate": 2.422680412371134e-06,
"loss": 0.7797,
"step": 250
},
{
"epoch": 1.15,
"learning_rate": 2.40979381443299e-06,
"loss": 0.6266,
"step": 251
},
{
"epoch": 1.15,
"learning_rate": 2.3969072164948458e-06,
"loss": 0.5461,
"step": 252
},
{
"epoch": 1.16,
"learning_rate": 2.3840206185567014e-06,
"loss": 0.7748,
"step": 253
},
{
"epoch": 1.16,
"learning_rate": 2.3711340206185566e-06,
"loss": 0.801,
"step": 254
},
{
"epoch": 1.16,
"learning_rate": 2.3582474226804127e-06,
"loss": 0.6607,
"step": 255
},
{
"epoch": 1.17,
"learning_rate": 2.3453608247422683e-06,
"loss": 0.6514,
"step": 256
},
{
"epoch": 1.17,
"learning_rate": 2.332474226804124e-06,
"loss": 0.6607,
"step": 257
},
{
"epoch": 1.18,
"learning_rate": 2.3195876288659796e-06,
"loss": 0.9292,
"step": 258
},
{
"epoch": 1.18,
"learning_rate": 2.3067010309278352e-06,
"loss": 0.7048,
"step": 259
},
{
"epoch": 1.19,
"learning_rate": 2.293814432989691e-06,
"loss": 0.8246,
"step": 260
},
{
"epoch": 1.19,
"learning_rate": 2.2809278350515465e-06,
"loss": 0.6935,
"step": 261
},
{
"epoch": 1.2,
"learning_rate": 2.268041237113402e-06,
"loss": 0.6717,
"step": 262
},
{
"epoch": 1.2,
"learning_rate": 2.255154639175258e-06,
"loss": 0.6667,
"step": 263
},
{
"epoch": 1.21,
"learning_rate": 2.242268041237114e-06,
"loss": 0.7335,
"step": 264
},
{
"epoch": 1.21,
"learning_rate": 2.2293814432989695e-06,
"loss": 0.7879,
"step": 265
},
{
"epoch": 1.21,
"learning_rate": 2.2164948453608247e-06,
"loss": 0.8604,
"step": 266
},
{
"epoch": 1.22,
"learning_rate": 2.2036082474226804e-06,
"loss": 0.6958,
"step": 267
},
{
"epoch": 1.22,
"learning_rate": 2.1907216494845364e-06,
"loss": 0.7795,
"step": 268
},
{
"epoch": 1.23,
"learning_rate": 2.177835051546392e-06,
"loss": 0.6271,
"step": 269
},
{
"epoch": 1.23,
"learning_rate": 2.1649484536082477e-06,
"loss": 0.6886,
"step": 270
},
{
"epoch": 1.24,
"learning_rate": 2.1520618556701033e-06,
"loss": 0.7869,
"step": 271
},
{
"epoch": 1.24,
"learning_rate": 2.139175257731959e-06,
"loss": 0.755,
"step": 272
},
{
"epoch": 1.25,
"learning_rate": 2.1262886597938146e-06,
"loss": 0.6822,
"step": 273
},
{
"epoch": 1.25,
"learning_rate": 2.1134020618556703e-06,
"loss": 0.6326,
"step": 274
},
{
"epoch": 1.26,
"learning_rate": 2.100515463917526e-06,
"loss": 0.7398,
"step": 275
},
{
"epoch": 1.26,
"learning_rate": 2.0876288659793816e-06,
"loss": 0.6837,
"step": 276
},
{
"epoch": 1.26,
"learning_rate": 2.0747422680412376e-06,
"loss": 0.6417,
"step": 277
},
{
"epoch": 1.27,
"learning_rate": 2.061855670103093e-06,
"loss": 0.7952,
"step": 278
},
{
"epoch": 1.27,
"learning_rate": 2.0489690721649485e-06,
"loss": 0.6469,
"step": 279
},
{
"epoch": 1.28,
"learning_rate": 2.036082474226804e-06,
"loss": 0.7286,
"step": 280
},
{
"epoch": 1.28,
"learning_rate": 2.02319587628866e-06,
"loss": 0.6996,
"step": 281
},
{
"epoch": 1.29,
"learning_rate": 2.010309278350516e-06,
"loss": 0.8057,
"step": 282
},
{
"epoch": 1.29,
"learning_rate": 1.9974226804123715e-06,
"loss": 0.6246,
"step": 283
},
{
"epoch": 1.3,
"learning_rate": 1.9845360824742267e-06,
"loss": 0.6773,
"step": 284
},
{
"epoch": 1.3,
"learning_rate": 1.9716494845360827e-06,
"loss": 0.6296,
"step": 285
},
{
"epoch": 1.31,
"learning_rate": 1.9587628865979384e-06,
"loss": 0.5935,
"step": 286
},
{
"epoch": 1.31,
"learning_rate": 1.945876288659794e-06,
"loss": 0.5992,
"step": 287
},
{
"epoch": 1.32,
"learning_rate": 1.9329896907216497e-06,
"loss": 0.5585,
"step": 288
},
{
"epoch": 1.32,
"learning_rate": 1.9201030927835053e-06,
"loss": 0.6741,
"step": 289
},
{
"epoch": 1.32,
"learning_rate": 1.907216494845361e-06,
"loss": 0.6035,
"step": 290
},
{
"epoch": 1.33,
"learning_rate": 1.8943298969072166e-06,
"loss": 0.6571,
"step": 291
},
{
"epoch": 1.33,
"learning_rate": 1.8814432989690722e-06,
"loss": 0.6489,
"step": 292
},
{
"epoch": 1.34,
"learning_rate": 1.868556701030928e-06,
"loss": 0.758,
"step": 293
},
{
"epoch": 1.34,
"learning_rate": 1.8556701030927837e-06,
"loss": 0.7688,
"step": 294
},
{
"epoch": 1.35,
"learning_rate": 1.8427835051546394e-06,
"loss": 0.6152,
"step": 295
},
{
"epoch": 1.35,
"learning_rate": 1.8298969072164948e-06,
"loss": 0.6809,
"step": 296
},
{
"epoch": 1.36,
"learning_rate": 1.8170103092783506e-06,
"loss": 0.6756,
"step": 297
},
{
"epoch": 1.36,
"learning_rate": 1.8041237113402063e-06,
"loss": 0.6587,
"step": 298
},
{
"epoch": 1.37,
"learning_rate": 1.791237113402062e-06,
"loss": 0.6441,
"step": 299
},
{
"epoch": 1.37,
"learning_rate": 1.7783505154639178e-06,
"loss": 0.6336,
"step": 300
},
{
"epoch": 1.37,
"learning_rate": 1.7654639175257734e-06,
"loss": 0.7408,
"step": 301
},
{
"epoch": 1.38,
"learning_rate": 1.7525773195876288e-06,
"loss": 0.7985,
"step": 302
},
{
"epoch": 1.38,
"learning_rate": 1.7396907216494847e-06,
"loss": 0.7492,
"step": 303
},
{
"epoch": 1.39,
"learning_rate": 1.7268041237113403e-06,
"loss": 0.7215,
"step": 304
},
{
"epoch": 1.39,
"learning_rate": 1.713917525773196e-06,
"loss": 0.5695,
"step": 305
},
{
"epoch": 1.4,
"learning_rate": 1.7010309278350518e-06,
"loss": 0.7138,
"step": 306
},
{
"epoch": 1.4,
"learning_rate": 1.6881443298969075e-06,
"loss": 0.5508,
"step": 307
},
{
"epoch": 1.41,
"learning_rate": 1.675257731958763e-06,
"loss": 0.7353,
"step": 308
},
{
"epoch": 1.41,
"learning_rate": 1.6623711340206185e-06,
"loss": 0.6793,
"step": 309
},
{
"epoch": 1.42,
"learning_rate": 1.6494845360824744e-06,
"loss": 0.5911,
"step": 310
},
{
"epoch": 1.42,
"learning_rate": 1.63659793814433e-06,
"loss": 0.6386,
"step": 311
},
{
"epoch": 1.42,
"learning_rate": 1.6237113402061857e-06,
"loss": 0.6586,
"step": 312
},
{
"epoch": 1.43,
"learning_rate": 1.6108247422680415e-06,
"loss": 0.6563,
"step": 313
},
{
"epoch": 1.43,
"learning_rate": 1.597938144329897e-06,
"loss": 0.6564,
"step": 314
},
{
"epoch": 1.44,
"learning_rate": 1.5850515463917526e-06,
"loss": 0.7146,
"step": 315
},
{
"epoch": 1.44,
"learning_rate": 1.5721649484536082e-06,
"loss": 0.6482,
"step": 316
},
{
"epoch": 1.45,
"learning_rate": 1.559278350515464e-06,
"loss": 0.6517,
"step": 317
},
{
"epoch": 1.45,
"learning_rate": 1.5463917525773197e-06,
"loss": 0.5912,
"step": 318
},
{
"epoch": 1.46,
"learning_rate": 1.5335051546391756e-06,
"loss": 0.6712,
"step": 319
},
{
"epoch": 1.46,
"learning_rate": 1.520618556701031e-06,
"loss": 0.6384,
"step": 320
},
{
"epoch": 1.47,
"learning_rate": 1.5077319587628867e-06,
"loss": 0.5899,
"step": 321
},
{
"epoch": 1.47,
"learning_rate": 1.4948453608247423e-06,
"loss": 0.623,
"step": 322
},
{
"epoch": 1.47,
"learning_rate": 1.4819587628865981e-06,
"loss": 0.66,
"step": 323
},
{
"epoch": 1.48,
"learning_rate": 1.4690721649484538e-06,
"loss": 0.6602,
"step": 324
},
{
"epoch": 1.48,
"learning_rate": 1.4561855670103094e-06,
"loss": 0.6238,
"step": 325
},
{
"epoch": 1.49,
"learning_rate": 1.4432989690721649e-06,
"loss": 0.6853,
"step": 326
},
{
"epoch": 1.49,
"learning_rate": 1.4304123711340207e-06,
"loss": 0.7356,
"step": 327
},
{
"epoch": 1.5,
"learning_rate": 1.4175257731958764e-06,
"loss": 0.6379,
"step": 328
},
{
"epoch": 1.5,
"learning_rate": 1.404639175257732e-06,
"loss": 0.634,
"step": 329
},
{
"epoch": 1.51,
"learning_rate": 1.3917525773195878e-06,
"loss": 0.709,
"step": 330
},
{
"epoch": 1.51,
"learning_rate": 1.3788659793814435e-06,
"loss": 0.5336,
"step": 331
},
{
"epoch": 1.52,
"learning_rate": 1.365979381443299e-06,
"loss": 0.6408,
"step": 332
},
{
"epoch": 1.52,
"learning_rate": 1.3530927835051548e-06,
"loss": 0.5514,
"step": 333
},
{
"epoch": 1.53,
"learning_rate": 1.3402061855670104e-06,
"loss": 0.6811,
"step": 334
},
{
"epoch": 1.53,
"learning_rate": 1.327319587628866e-06,
"loss": 0.607,
"step": 335
},
{
"epoch": 1.53,
"learning_rate": 1.314432989690722e-06,
"loss": 0.5697,
"step": 336
},
{
"epoch": 1.54,
"learning_rate": 1.3015463917525775e-06,
"loss": 0.7654,
"step": 337
},
{
"epoch": 1.54,
"learning_rate": 1.288659793814433e-06,
"loss": 0.6505,
"step": 338
},
{
"epoch": 1.55,
"learning_rate": 1.2757731958762886e-06,
"loss": 0.6885,
"step": 339
},
{
"epoch": 1.55,
"learning_rate": 1.2628865979381445e-06,
"loss": 0.6046,
"step": 340
},
{
"epoch": 1.56,
"learning_rate": 1.25e-06,
"loss": 0.5709,
"step": 341
},
{
"epoch": 1.56,
"learning_rate": 1.2371134020618557e-06,
"loss": 0.6078,
"step": 342
},
{
"epoch": 1.57,
"learning_rate": 1.2242268041237114e-06,
"loss": 0.5452,
"step": 343
},
{
"epoch": 1.57,
"learning_rate": 1.211340206185567e-06,
"loss": 0.5785,
"step": 344
},
{
"epoch": 1.58,
"learning_rate": 1.1984536082474229e-06,
"loss": 0.5648,
"step": 345
},
{
"epoch": 1.58,
"learning_rate": 1.1855670103092783e-06,
"loss": 0.5601,
"step": 346
},
{
"epoch": 1.58,
"learning_rate": 1.1726804123711342e-06,
"loss": 0.7975,
"step": 347
},
{
"epoch": 1.59,
"learning_rate": 1.1597938144329898e-06,
"loss": 0.6807,
"step": 348
},
{
"epoch": 1.59,
"learning_rate": 1.1469072164948454e-06,
"loss": 0.682,
"step": 349
},
{
"epoch": 1.6,
"learning_rate": 1.134020618556701e-06,
"loss": 0.6399,
"step": 350
},
{
"epoch": 1.6,
"learning_rate": 1.121134020618557e-06,
"loss": 0.7978,
"step": 351
},
{
"epoch": 1.61,
"learning_rate": 1.1082474226804124e-06,
"loss": 0.6787,
"step": 352
},
{
"epoch": 1.61,
"learning_rate": 1.0953608247422682e-06,
"loss": 0.6881,
"step": 353
},
{
"epoch": 1.62,
"learning_rate": 1.0824742268041239e-06,
"loss": 0.5561,
"step": 354
},
{
"epoch": 1.62,
"learning_rate": 1.0695876288659795e-06,
"loss": 0.6708,
"step": 355
},
{
"epoch": 1.63,
"learning_rate": 1.0567010309278351e-06,
"loss": 0.6024,
"step": 356
},
{
"epoch": 1.63,
"learning_rate": 1.0438144329896908e-06,
"loss": 0.5998,
"step": 357
},
{
"epoch": 1.63,
"learning_rate": 1.0309278350515464e-06,
"loss": 0.5863,
"step": 358
},
{
"epoch": 1.64,
"learning_rate": 1.018041237113402e-06,
"loss": 0.4643,
"step": 359
},
{
"epoch": 1.64,
"learning_rate": 1.005154639175258e-06,
"loss": 0.7422,
"step": 360
},
{
"epoch": 1.65,
"learning_rate": 9.922680412371133e-07,
"loss": 0.5944,
"step": 361
},
{
"epoch": 1.65,
"learning_rate": 9.793814432989692e-07,
"loss": 0.6233,
"step": 362
},
{
"epoch": 1.66,
"learning_rate": 9.664948453608248e-07,
"loss": 0.6531,
"step": 363
},
{
"epoch": 1.66,
"learning_rate": 9.536082474226805e-07,
"loss": 0.5812,
"step": 364
},
{
"epoch": 1.67,
"learning_rate": 9.407216494845361e-07,
"loss": 0.5567,
"step": 365
},
{
"epoch": 1.67,
"learning_rate": 9.278350515463919e-07,
"loss": 0.6431,
"step": 366
},
{
"epoch": 1.68,
"learning_rate": 9.149484536082474e-07,
"loss": 0.5753,
"step": 367
},
{
"epoch": 1.68,
"learning_rate": 9.020618556701031e-07,
"loss": 0.7636,
"step": 368
},
{
"epoch": 1.68,
"learning_rate": 8.891752577319589e-07,
"loss": 0.7122,
"step": 369
},
{
"epoch": 1.69,
"learning_rate": 8.762886597938144e-07,
"loss": 0.5386,
"step": 370
},
{
"epoch": 1.69,
"learning_rate": 8.634020618556702e-07,
"loss": 0.6074,
"step": 371
},
{
"epoch": 1.7,
"learning_rate": 8.505154639175259e-07,
"loss": 0.7311,
"step": 372
},
{
"epoch": 1.7,
"learning_rate": 8.376288659793815e-07,
"loss": 0.6348,
"step": 373
},
{
"epoch": 1.71,
"learning_rate": 8.247422680412372e-07,
"loss": 0.5684,
"step": 374
},
{
"epoch": 1.71,
"learning_rate": 8.118556701030928e-07,
"loss": 0.6218,
"step": 375
},
{
"epoch": 1.72,
"learning_rate": 7.989690721649485e-07,
"loss": 0.6908,
"step": 376
},
{
"epoch": 1.72,
"learning_rate": 7.860824742268041e-07,
"loss": 0.5664,
"step": 377
},
{
"epoch": 1.73,
"learning_rate": 7.731958762886599e-07,
"loss": 0.7087,
"step": 378
},
{
"epoch": 1.73,
"learning_rate": 7.603092783505155e-07,
"loss": 0.6045,
"step": 379
},
{
"epoch": 1.74,
"learning_rate": 7.474226804123711e-07,
"loss": 0.5708,
"step": 380
},
{
"epoch": 1.74,
"learning_rate": 7.345360824742269e-07,
"loss": 0.7197,
"step": 381
},
{
"epoch": 1.74,
"learning_rate": 7.216494845360824e-07,
"loss": 0.6247,
"step": 382
},
{
"epoch": 1.75,
"learning_rate": 7.087628865979382e-07,
"loss": 0.527,
"step": 383
},
{
"epoch": 1.75,
"learning_rate": 6.958762886597939e-07,
"loss": 0.5181,
"step": 384
},
{
"epoch": 1.76,
"learning_rate": 6.829896907216495e-07,
"loss": 0.6651,
"step": 385
},
{
"epoch": 1.76,
"learning_rate": 6.701030927835052e-07,
"loss": 0.54,
"step": 386
},
{
"epoch": 1.77,
"learning_rate": 6.57216494845361e-07,
"loss": 0.5499,
"step": 387
},
{
"epoch": 1.77,
"learning_rate": 6.443298969072165e-07,
"loss": 0.415,
"step": 388
},
{
"epoch": 1.78,
"learning_rate": 6.314432989690722e-07,
"loss": 0.6449,
"step": 389
},
{
"epoch": 1.78,
"learning_rate": 6.185567010309279e-07,
"loss": 0.7007,
"step": 390
},
{
"epoch": 1.79,
"learning_rate": 6.056701030927835e-07,
"loss": 0.6682,
"step": 391
},
{
"epoch": 1.79,
"learning_rate": 5.927835051546392e-07,
"loss": 0.581,
"step": 392
},
{
"epoch": 1.79,
"learning_rate": 5.798969072164949e-07,
"loss": 0.5541,
"step": 393
},
{
"epoch": 1.8,
"learning_rate": 5.670103092783505e-07,
"loss": 0.4798,
"step": 394
},
{
"epoch": 1.8,
"learning_rate": 5.541237113402062e-07,
"loss": 0.5811,
"step": 395
},
{
"epoch": 1.81,
"learning_rate": 5.412371134020619e-07,
"loss": 0.689,
"step": 396
},
{
"epoch": 1.81,
"learning_rate": 5.283505154639176e-07,
"loss": 0.5646,
"step": 397
},
{
"epoch": 1.82,
"learning_rate": 5.154639175257732e-07,
"loss": 0.5817,
"step": 398
},
{
"epoch": 1.82,
"learning_rate": 5.02577319587629e-07,
"loss": 0.5922,
"step": 399
},
{
"epoch": 1.83,
"learning_rate": 4.896907216494846e-07,
"loss": 0.5986,
"step": 400
},
{
"epoch": 1.83,
"learning_rate": 4.7680412371134024e-07,
"loss": 0.7401,
"step": 401
},
{
"epoch": 1.84,
"learning_rate": 4.6391752577319593e-07,
"loss": 0.695,
"step": 402
},
{
"epoch": 1.84,
"learning_rate": 4.5103092783505157e-07,
"loss": 0.5308,
"step": 403
},
{
"epoch": 1.84,
"learning_rate": 4.381443298969072e-07,
"loss": 0.5776,
"step": 404
},
{
"epoch": 1.85,
"learning_rate": 4.2525773195876296e-07,
"loss": 0.5728,
"step": 405
},
{
"epoch": 1.85,
"learning_rate": 4.123711340206186e-07,
"loss": 0.5541,
"step": 406
},
{
"epoch": 1.86,
"learning_rate": 3.9948453608247424e-07,
"loss": 0.5633,
"step": 407
},
{
"epoch": 1.86,
"learning_rate": 3.8659793814432993e-07,
"loss": 0.6269,
"step": 408
},
{
"epoch": 1.87,
"learning_rate": 3.737113402061856e-07,
"loss": 0.6568,
"step": 409
},
{
"epoch": 1.87,
"learning_rate": 3.608247422680412e-07,
"loss": 0.5728,
"step": 410
},
{
"epoch": 1.88,
"learning_rate": 3.4793814432989696e-07,
"loss": 0.6444,
"step": 411
},
{
"epoch": 1.88,
"learning_rate": 3.350515463917526e-07,
"loss": 0.6943,
"step": 412
},
{
"epoch": 1.89,
"learning_rate": 3.2216494845360824e-07,
"loss": 0.5352,
"step": 413
},
{
"epoch": 1.89,
"learning_rate": 3.0927835051546394e-07,
"loss": 0.5865,
"step": 414
},
{
"epoch": 1.89,
"learning_rate": 2.963917525773196e-07,
"loss": 0.6415,
"step": 415
},
{
"epoch": 1.9,
"learning_rate": 2.8350515463917527e-07,
"loss": 0.5819,
"step": 416
},
{
"epoch": 1.9,
"learning_rate": 2.7061855670103096e-07,
"loss": 0.6314,
"step": 417
},
{
"epoch": 1.91,
"learning_rate": 2.577319587628866e-07,
"loss": 0.7125,
"step": 418
},
{
"epoch": 1.91,
"learning_rate": 2.448453608247423e-07,
"loss": 0.6313,
"step": 419
},
{
"epoch": 1.92,
"learning_rate": 2.3195876288659797e-07,
"loss": 0.5542,
"step": 420
},
{
"epoch": 1.92,
"learning_rate": 2.190721649484536e-07,
"loss": 0.6666,
"step": 421
},
{
"epoch": 1.93,
"learning_rate": 2.061855670103093e-07,
"loss": 0.5925,
"step": 422
},
{
"epoch": 1.93,
"learning_rate": 1.9329896907216497e-07,
"loss": 0.5483,
"step": 423
},
{
"epoch": 1.94,
"learning_rate": 1.804123711340206e-07,
"loss": 0.6061,
"step": 424
},
{
"epoch": 1.94,
"learning_rate": 1.675257731958763e-07,
"loss": 0.6735,
"step": 425
},
{
"epoch": 1.95,
"learning_rate": 1.5463917525773197e-07,
"loss": 0.62,
"step": 426
},
{
"epoch": 1.95,
"learning_rate": 1.4175257731958764e-07,
"loss": 0.5898,
"step": 427
},
{
"epoch": 1.95,
"learning_rate": 1.288659793814433e-07,
"loss": 0.6465,
"step": 428
},
{
"epoch": 1.96,
"learning_rate": 1.1597938144329898e-07,
"loss": 0.6042,
"step": 429
},
{
"epoch": 1.96,
"learning_rate": 1.0309278350515465e-07,
"loss": 0.5729,
"step": 430
},
{
"epoch": 1.97,
"learning_rate": 9.02061855670103e-08,
"loss": 0.616,
"step": 431
},
{
"epoch": 1.97,
"learning_rate": 7.731958762886598e-08,
"loss": 0.6034,
"step": 432
},
{
"epoch": 1.98,
"learning_rate": 6.443298969072165e-08,
"loss": 0.5164,
"step": 433
},
{
"epoch": 1.98,
"learning_rate": 5.1546391752577325e-08,
"loss": 0.552,
"step": 434
},
{
"epoch": 1.99,
"learning_rate": 3.865979381443299e-08,
"loss": 0.6101,
"step": 435
},
{
"epoch": 1.99,
"learning_rate": 2.5773195876288662e-08,
"loss": 0.6481,
"step": 436
},
{
"epoch": 2.0,
"learning_rate": 1.2886597938144331e-08,
"loss": 0.5592,
"step": 437
},
{
"epoch": 2.0,
"learning_rate": 0.0,
"loss": 0.5396,
"step": 438
},
{
"epoch": 2.0,
"eval_accuracy": 0.9726027397260274,
"eval_loss": 0.5413519740104675,
"eval_roc_auc": 0.9912656015068381,
"eval_runtime": 51.5875,
"eval_samples_per_second": 4.245,
"eval_steps_per_second": 4.245,
"step": 438
}
],
"max_steps": 438,
"num_train_epochs": 2,
"total_flos": 2.3858711415936e+17,
"trial_name": null,
"trial_params": null
}