emendes3's picture
Model save
8b5d879 verified
raw
history blame
70.2 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 20.0,
"eval_steps": 500,
"global_step": 620,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03,
"learning_rate": 0.0,
"loss": 1.5209,
"step": 1
},
{
"epoch": 0.06,
"learning_rate": 4.708178267332765e-05,
"loss": 1.2229,
"step": 2
},
{
"epoch": 0.1,
"learning_rate": 7.46228600043274e-05,
"loss": 1.2327,
"step": 3
},
{
"epoch": 0.13,
"learning_rate": 9.41635653466553e-05,
"loss": 1.1423,
"step": 4
},
{
"epoch": 0.16,
"learning_rate": 0.00010932051394658049,
"loss": 1.0992,
"step": 5
},
{
"epoch": 0.19,
"learning_rate": 0.00012170464267765504,
"loss": 1.0988,
"step": 6
},
{
"epoch": 0.23,
"learning_rate": 0.0001321752743272128,
"loss": 1.0443,
"step": 7
},
{
"epoch": 0.26,
"learning_rate": 0.00014124534801998294,
"loss": 1.05,
"step": 8
},
{
"epoch": 0.29,
"learning_rate": 0.0001492457200086548,
"loss": 0.9695,
"step": 9
},
{
"epoch": 0.32,
"learning_rate": 0.00015640229661990817,
"loss": 1.0095,
"step": 10
},
{
"epoch": 0.35,
"learning_rate": 0.00016287620764191934,
"loss": 1.0081,
"step": 11
},
{
"epoch": 0.39,
"learning_rate": 0.00016878642535098271,
"loss": 0.9324,
"step": 12
},
{
"epoch": 0.42,
"learning_rate": 0.00017422329860526873,
"loss": 0.9096,
"step": 13
},
{
"epoch": 0.45,
"learning_rate": 0.00017925705700054043,
"loss": 0.8283,
"step": 14
},
{
"epoch": 0.48,
"learning_rate": 0.0001839433739509079,
"loss": 0.8708,
"step": 15
},
{
"epoch": 0.52,
"learning_rate": 0.0001883271306933106,
"loss": 0.854,
"step": 16
},
{
"epoch": 0.55,
"learning_rate": 0.00019244503717705084,
"loss": 0.8107,
"step": 17
},
{
"epoch": 0.58,
"learning_rate": 0.00019632750268198243,
"loss": 0.7396,
"step": 18
},
{
"epoch": 0.61,
"learning_rate": 0.0002,
"loss": 0.7374,
"step": 19
},
{
"epoch": 0.65,
"learning_rate": 0.0002,
"loss": 0.642,
"step": 20
},
{
"epoch": 0.68,
"learning_rate": 0.0002,
"loss": 0.7746,
"step": 21
},
{
"epoch": 0.71,
"learning_rate": 0.0002,
"loss": 0.6737,
"step": 22
},
{
"epoch": 0.74,
"learning_rate": 0.0002,
"loss": 0.6024,
"step": 23
},
{
"epoch": 0.77,
"learning_rate": 0.0002,
"loss": 0.6862,
"step": 24
},
{
"epoch": 0.81,
"learning_rate": 0.0002,
"loss": 0.5941,
"step": 25
},
{
"epoch": 0.84,
"learning_rate": 0.0002,
"loss": 0.5712,
"step": 26
},
{
"epoch": 0.87,
"learning_rate": 0.0002,
"loss": 0.5542,
"step": 27
},
{
"epoch": 0.9,
"learning_rate": 0.0002,
"loss": 0.4663,
"step": 28
},
{
"epoch": 0.94,
"learning_rate": 0.0002,
"loss": 0.4901,
"step": 29
},
{
"epoch": 0.97,
"learning_rate": 0.0002,
"loss": 0.4259,
"step": 30
},
{
"epoch": 1.0,
"learning_rate": 0.0002,
"loss": 0.3824,
"step": 31
},
{
"epoch": 1.0,
"eval_loss": 0.27588292956352234,
"eval_runtime": 79.0786,
"eval_samples_per_second": 12.279,
"eval_steps_per_second": 0.392,
"step": 31
},
{
"epoch": 1.03,
"learning_rate": 0.0002,
"loss": 0.2758,
"step": 32
},
{
"epoch": 1.06,
"learning_rate": 0.0002,
"loss": 0.3008,
"step": 33
},
{
"epoch": 1.1,
"learning_rate": 0.0002,
"loss": 0.2365,
"step": 34
},
{
"epoch": 1.13,
"learning_rate": 0.0002,
"loss": 0.2172,
"step": 35
},
{
"epoch": 1.16,
"learning_rate": 0.0002,
"loss": 0.2279,
"step": 36
},
{
"epoch": 1.19,
"learning_rate": 0.0002,
"loss": 0.2497,
"step": 37
},
{
"epoch": 1.23,
"learning_rate": 0.0002,
"loss": 0.1943,
"step": 38
},
{
"epoch": 1.26,
"learning_rate": 0.0002,
"loss": 0.2189,
"step": 39
},
{
"epoch": 1.29,
"learning_rate": 0.0002,
"loss": 0.1136,
"step": 40
},
{
"epoch": 1.32,
"learning_rate": 0.0002,
"loss": 0.1728,
"step": 41
},
{
"epoch": 1.35,
"learning_rate": 0.0002,
"loss": 0.1786,
"step": 42
},
{
"epoch": 1.39,
"learning_rate": 0.0002,
"loss": 0.1389,
"step": 43
},
{
"epoch": 1.42,
"learning_rate": 0.0002,
"loss": 0.1352,
"step": 44
},
{
"epoch": 1.45,
"learning_rate": 0.0002,
"loss": 0.1489,
"step": 45
},
{
"epoch": 1.48,
"learning_rate": 0.0002,
"loss": 0.1242,
"step": 46
},
{
"epoch": 1.52,
"learning_rate": 0.0002,
"loss": 0.1498,
"step": 47
},
{
"epoch": 1.55,
"learning_rate": 0.0002,
"loss": 0.1477,
"step": 48
},
{
"epoch": 1.58,
"learning_rate": 0.0002,
"loss": 0.0588,
"step": 49
},
{
"epoch": 1.61,
"learning_rate": 0.0002,
"loss": 0.1447,
"step": 50
},
{
"epoch": 1.65,
"learning_rate": 0.0002,
"loss": 0.1178,
"step": 51
},
{
"epoch": 1.68,
"learning_rate": 0.0002,
"loss": 0.1571,
"step": 52
},
{
"epoch": 1.71,
"learning_rate": 0.0002,
"loss": 0.1102,
"step": 53
},
{
"epoch": 1.74,
"learning_rate": 0.0002,
"loss": 0.0951,
"step": 54
},
{
"epoch": 1.77,
"learning_rate": 0.0002,
"loss": 0.1482,
"step": 55
},
{
"epoch": 1.81,
"learning_rate": 0.0002,
"loss": 0.0877,
"step": 56
},
{
"epoch": 1.84,
"learning_rate": 0.0002,
"loss": 0.1067,
"step": 57
},
{
"epoch": 1.87,
"learning_rate": 0.0002,
"loss": 0.0974,
"step": 58
},
{
"epoch": 1.9,
"learning_rate": 0.0002,
"loss": 0.0631,
"step": 59
},
{
"epoch": 1.94,
"learning_rate": 0.0002,
"loss": 0.098,
"step": 60
},
{
"epoch": 1.97,
"learning_rate": 0.0002,
"loss": 0.1148,
"step": 61
},
{
"epoch": 2.0,
"learning_rate": 0.0002,
"loss": 0.0442,
"step": 62
},
{
"epoch": 2.0,
"eval_loss": 0.04755338281393051,
"eval_runtime": 79.4962,
"eval_samples_per_second": 12.214,
"eval_steps_per_second": 0.39,
"step": 62
},
{
"epoch": 2.03,
"learning_rate": 0.0002,
"loss": 0.0526,
"step": 63
},
{
"epoch": 2.06,
"learning_rate": 0.0002,
"loss": 0.0471,
"step": 64
},
{
"epoch": 2.1,
"learning_rate": 0.0002,
"loss": 0.036,
"step": 65
},
{
"epoch": 2.13,
"learning_rate": 0.0002,
"loss": 0.037,
"step": 66
},
{
"epoch": 2.16,
"learning_rate": 0.0002,
"loss": 0.0293,
"step": 67
},
{
"epoch": 2.19,
"learning_rate": 0.0002,
"loss": 0.0316,
"step": 68
},
{
"epoch": 2.23,
"learning_rate": 0.0002,
"loss": 0.0268,
"step": 69
},
{
"epoch": 2.26,
"learning_rate": 0.0002,
"loss": 0.0366,
"step": 70
},
{
"epoch": 2.29,
"learning_rate": 0.0002,
"loss": 0.0305,
"step": 71
},
{
"epoch": 2.32,
"learning_rate": 0.0002,
"loss": 0.0336,
"step": 72
},
{
"epoch": 2.35,
"learning_rate": 0.0002,
"loss": 0.0497,
"step": 73
},
{
"epoch": 2.39,
"learning_rate": 0.0002,
"loss": 0.0275,
"step": 74
},
{
"epoch": 2.42,
"learning_rate": 0.0002,
"loss": 0.0385,
"step": 75
},
{
"epoch": 2.45,
"learning_rate": 0.0002,
"loss": 0.0221,
"step": 76
},
{
"epoch": 2.48,
"learning_rate": 0.0002,
"loss": 0.0184,
"step": 77
},
{
"epoch": 2.52,
"learning_rate": 0.0002,
"loss": 0.0354,
"step": 78
},
{
"epoch": 2.55,
"learning_rate": 0.0002,
"loss": 0.0148,
"step": 79
},
{
"epoch": 2.58,
"learning_rate": 0.0002,
"loss": 0.0254,
"step": 80
},
{
"epoch": 2.61,
"learning_rate": 0.0002,
"loss": 0.0356,
"step": 81
},
{
"epoch": 2.65,
"learning_rate": 0.0002,
"loss": 0.0237,
"step": 82
},
{
"epoch": 2.68,
"learning_rate": 0.0002,
"loss": 0.0259,
"step": 83
},
{
"epoch": 2.71,
"learning_rate": 0.0002,
"loss": 0.0276,
"step": 84
},
{
"epoch": 2.74,
"learning_rate": 0.0002,
"loss": 0.0212,
"step": 85
},
{
"epoch": 2.77,
"learning_rate": 0.0002,
"loss": 0.0351,
"step": 86
},
{
"epoch": 2.81,
"learning_rate": 0.0002,
"loss": 0.0332,
"step": 87
},
{
"epoch": 2.84,
"learning_rate": 0.0002,
"loss": 0.0225,
"step": 88
},
{
"epoch": 2.87,
"learning_rate": 0.0002,
"loss": 0.0113,
"step": 89
},
{
"epoch": 2.9,
"learning_rate": 0.0002,
"loss": 0.045,
"step": 90
},
{
"epoch": 2.94,
"learning_rate": 0.0002,
"loss": 0.0228,
"step": 91
},
{
"epoch": 2.97,
"learning_rate": 0.0002,
"loss": 0.0216,
"step": 92
},
{
"epoch": 3.0,
"learning_rate": 0.0002,
"loss": 0.0111,
"step": 93
},
{
"epoch": 3.0,
"eval_loss": 0.013120166026055813,
"eval_runtime": 79.6214,
"eval_samples_per_second": 12.195,
"eval_steps_per_second": 0.389,
"step": 93
},
{
"epoch": 3.03,
"learning_rate": 0.0002,
"loss": 0.009,
"step": 94
},
{
"epoch": 3.06,
"learning_rate": 0.0002,
"loss": 0.0111,
"step": 95
},
{
"epoch": 3.1,
"learning_rate": 0.0002,
"loss": 0.0147,
"step": 96
},
{
"epoch": 3.13,
"learning_rate": 0.0002,
"loss": 0.0185,
"step": 97
},
{
"epoch": 3.16,
"learning_rate": 0.0002,
"loss": 0.0155,
"step": 98
},
{
"epoch": 3.19,
"learning_rate": 0.0002,
"loss": 0.0091,
"step": 99
},
{
"epoch": 3.23,
"learning_rate": 0.0002,
"loss": 0.0072,
"step": 100
},
{
"epoch": 3.26,
"learning_rate": 0.0002,
"loss": 0.0126,
"step": 101
},
{
"epoch": 3.29,
"learning_rate": 0.0002,
"loss": 0.0106,
"step": 102
},
{
"epoch": 3.32,
"learning_rate": 0.0002,
"loss": 0.0106,
"step": 103
},
{
"epoch": 3.35,
"learning_rate": 0.0002,
"loss": 0.0145,
"step": 104
},
{
"epoch": 3.39,
"learning_rate": 0.0002,
"loss": 0.0063,
"step": 105
},
{
"epoch": 3.42,
"learning_rate": 0.0002,
"loss": 0.0165,
"step": 106
},
{
"epoch": 3.45,
"learning_rate": 0.0002,
"loss": 0.0066,
"step": 107
},
{
"epoch": 3.48,
"learning_rate": 0.0002,
"loss": 0.0148,
"step": 108
},
{
"epoch": 3.52,
"learning_rate": 0.0002,
"loss": 0.0112,
"step": 109
},
{
"epoch": 3.55,
"learning_rate": 0.0002,
"loss": 0.0106,
"step": 110
},
{
"epoch": 3.58,
"learning_rate": 0.0002,
"loss": 0.0109,
"step": 111
},
{
"epoch": 3.61,
"learning_rate": 0.0002,
"loss": 0.0189,
"step": 112
},
{
"epoch": 3.65,
"learning_rate": 0.0002,
"loss": 0.0131,
"step": 113
},
{
"epoch": 3.68,
"learning_rate": 0.0002,
"loss": 0.0115,
"step": 114
},
{
"epoch": 3.71,
"learning_rate": 0.0002,
"loss": 0.0108,
"step": 115
},
{
"epoch": 3.74,
"learning_rate": 0.0002,
"loss": 0.008,
"step": 116
},
{
"epoch": 3.77,
"learning_rate": 0.0002,
"loss": 0.0143,
"step": 117
},
{
"epoch": 3.81,
"learning_rate": 0.0002,
"loss": 0.0085,
"step": 118
},
{
"epoch": 3.84,
"learning_rate": 0.0002,
"loss": 0.0122,
"step": 119
},
{
"epoch": 3.87,
"learning_rate": 0.0002,
"loss": 0.0086,
"step": 120
},
{
"epoch": 3.9,
"learning_rate": 0.0002,
"loss": 0.013,
"step": 121
},
{
"epoch": 3.94,
"learning_rate": 0.0002,
"loss": 0.0049,
"step": 122
},
{
"epoch": 3.97,
"learning_rate": 0.0002,
"loss": 0.0102,
"step": 123
},
{
"epoch": 4.0,
"learning_rate": 0.0002,
"loss": 0.0043,
"step": 124
},
{
"epoch": 4.0,
"eval_loss": 0.0071370587684214115,
"eval_runtime": 79.2858,
"eval_samples_per_second": 12.247,
"eval_steps_per_second": 0.391,
"step": 124
},
{
"epoch": 4.03,
"learning_rate": 0.0002,
"loss": 0.0066,
"step": 125
},
{
"epoch": 4.06,
"learning_rate": 0.0002,
"loss": 0.0049,
"step": 126
},
{
"epoch": 4.1,
"learning_rate": 0.0002,
"loss": 0.0064,
"step": 127
},
{
"epoch": 4.13,
"learning_rate": 0.0002,
"loss": 0.0086,
"step": 128
},
{
"epoch": 4.16,
"learning_rate": 0.0002,
"loss": 0.0079,
"step": 129
},
{
"epoch": 4.19,
"learning_rate": 0.0002,
"loss": 0.0066,
"step": 130
},
{
"epoch": 4.23,
"learning_rate": 0.0002,
"loss": 0.0061,
"step": 131
},
{
"epoch": 4.26,
"learning_rate": 0.0002,
"loss": 0.004,
"step": 132
},
{
"epoch": 4.29,
"learning_rate": 0.0002,
"loss": 0.0079,
"step": 133
},
{
"epoch": 4.32,
"learning_rate": 0.0002,
"loss": 0.0105,
"step": 134
},
{
"epoch": 4.35,
"learning_rate": 0.0002,
"loss": 0.0035,
"step": 135
},
{
"epoch": 4.39,
"learning_rate": 0.0002,
"loss": 0.0087,
"step": 136
},
{
"epoch": 4.42,
"learning_rate": 0.0002,
"loss": 0.0043,
"step": 137
},
{
"epoch": 4.45,
"learning_rate": 0.0002,
"loss": 0.0054,
"step": 138
},
{
"epoch": 4.48,
"learning_rate": 0.0002,
"loss": 0.0064,
"step": 139
},
{
"epoch": 4.52,
"learning_rate": 0.0002,
"loss": 0.0077,
"step": 140
},
{
"epoch": 4.55,
"learning_rate": 0.0002,
"loss": 0.0103,
"step": 141
},
{
"epoch": 4.58,
"learning_rate": 0.0002,
"loss": 0.0089,
"step": 142
},
{
"epoch": 4.61,
"learning_rate": 0.0002,
"loss": 0.0051,
"step": 143
},
{
"epoch": 4.65,
"learning_rate": 0.0002,
"loss": 0.0034,
"step": 144
},
{
"epoch": 4.68,
"learning_rate": 0.0002,
"loss": 0.0046,
"step": 145
},
{
"epoch": 4.71,
"learning_rate": 0.0002,
"loss": 0.0093,
"step": 146
},
{
"epoch": 4.74,
"learning_rate": 0.0002,
"loss": 0.0084,
"step": 147
},
{
"epoch": 4.77,
"learning_rate": 0.0002,
"loss": 0.0059,
"step": 148
},
{
"epoch": 4.81,
"learning_rate": 0.0002,
"loss": 0.0041,
"step": 149
},
{
"epoch": 4.84,
"learning_rate": 0.0002,
"loss": 0.0071,
"step": 150
},
{
"epoch": 4.87,
"learning_rate": 0.0002,
"loss": 0.0093,
"step": 151
},
{
"epoch": 4.9,
"learning_rate": 0.0002,
"loss": 0.0069,
"step": 152
},
{
"epoch": 4.94,
"learning_rate": 0.0002,
"loss": 0.0079,
"step": 153
},
{
"epoch": 4.97,
"learning_rate": 0.0002,
"loss": 0.0091,
"step": 154
},
{
"epoch": 5.0,
"learning_rate": 0.0002,
"loss": 0.0064,
"step": 155
},
{
"epoch": 5.0,
"eval_loss": 0.004239812958985567,
"eval_runtime": 79.1869,
"eval_samples_per_second": 12.262,
"eval_steps_per_second": 0.391,
"step": 155
},
{
"epoch": 5.03,
"learning_rate": 0.0002,
"loss": 0.0024,
"step": 156
},
{
"epoch": 5.06,
"learning_rate": 0.0002,
"loss": 0.0025,
"step": 157
},
{
"epoch": 5.1,
"learning_rate": 0.0002,
"loss": 0.0024,
"step": 158
},
{
"epoch": 5.13,
"learning_rate": 0.0002,
"loss": 0.0052,
"step": 159
},
{
"epoch": 5.16,
"learning_rate": 0.0002,
"loss": 0.0029,
"step": 160
},
{
"epoch": 5.19,
"learning_rate": 0.0002,
"loss": 0.0045,
"step": 161
},
{
"epoch": 5.23,
"learning_rate": 0.0002,
"loss": 0.0057,
"step": 162
},
{
"epoch": 5.26,
"learning_rate": 0.0002,
"loss": 0.0023,
"step": 163
},
{
"epoch": 5.29,
"learning_rate": 0.0002,
"loss": 0.0063,
"step": 164
},
{
"epoch": 5.32,
"learning_rate": 0.0002,
"loss": 0.0073,
"step": 165
},
{
"epoch": 5.35,
"learning_rate": 0.0002,
"loss": 0.0052,
"step": 166
},
{
"epoch": 5.39,
"learning_rate": 0.0002,
"loss": 0.0039,
"step": 167
},
{
"epoch": 5.42,
"learning_rate": 0.0002,
"loss": 0.0017,
"step": 168
},
{
"epoch": 5.45,
"learning_rate": 0.0002,
"loss": 0.0032,
"step": 169
},
{
"epoch": 5.48,
"learning_rate": 0.0002,
"loss": 0.0049,
"step": 170
},
{
"epoch": 5.52,
"learning_rate": 0.0002,
"loss": 0.0067,
"step": 171
},
{
"epoch": 5.55,
"learning_rate": 0.0002,
"loss": 0.0052,
"step": 172
},
{
"epoch": 5.58,
"learning_rate": 0.0002,
"loss": 0.0052,
"step": 173
},
{
"epoch": 5.61,
"learning_rate": 0.0002,
"loss": 0.0074,
"step": 174
},
{
"epoch": 5.65,
"learning_rate": 0.0002,
"loss": 0.0064,
"step": 175
},
{
"epoch": 5.68,
"learning_rate": 0.0002,
"loss": 0.002,
"step": 176
},
{
"epoch": 5.71,
"learning_rate": 0.0002,
"loss": 0.0017,
"step": 177
},
{
"epoch": 5.74,
"learning_rate": 0.0002,
"loss": 0.0056,
"step": 178
},
{
"epoch": 5.77,
"learning_rate": 0.0002,
"loss": 0.0036,
"step": 179
},
{
"epoch": 5.81,
"learning_rate": 0.0002,
"loss": 0.0021,
"step": 180
},
{
"epoch": 5.84,
"learning_rate": 0.0002,
"loss": 0.0064,
"step": 181
},
{
"epoch": 5.87,
"learning_rate": 0.0002,
"loss": 0.0067,
"step": 182
},
{
"epoch": 5.9,
"learning_rate": 0.0002,
"loss": 0.008,
"step": 183
},
{
"epoch": 5.94,
"learning_rate": 0.0002,
"loss": 0.0039,
"step": 184
},
{
"epoch": 5.97,
"learning_rate": 0.0002,
"loss": 0.0043,
"step": 185
},
{
"epoch": 6.0,
"learning_rate": 0.0002,
"loss": 0.0048,
"step": 186
},
{
"epoch": 6.0,
"eval_loss": 0.0028802985325455666,
"eval_runtime": 79.2422,
"eval_samples_per_second": 12.254,
"eval_steps_per_second": 0.391,
"step": 186
},
{
"epoch": 6.03,
"learning_rate": 0.0002,
"loss": 0.0017,
"step": 187
},
{
"epoch": 6.06,
"learning_rate": 0.0002,
"loss": 0.0025,
"step": 188
},
{
"epoch": 6.1,
"learning_rate": 0.0002,
"loss": 0.0024,
"step": 189
},
{
"epoch": 6.13,
"learning_rate": 0.0002,
"loss": 0.0018,
"step": 190
},
{
"epoch": 6.16,
"learning_rate": 0.0002,
"loss": 0.004,
"step": 191
},
{
"epoch": 6.19,
"learning_rate": 0.0002,
"loss": 0.006,
"step": 192
},
{
"epoch": 6.23,
"learning_rate": 0.0002,
"loss": 0.0015,
"step": 193
},
{
"epoch": 6.26,
"learning_rate": 0.0002,
"loss": 0.0017,
"step": 194
},
{
"epoch": 6.29,
"learning_rate": 0.0002,
"loss": 0.0021,
"step": 195
},
{
"epoch": 6.32,
"learning_rate": 0.0002,
"loss": 0.0073,
"step": 196
},
{
"epoch": 6.35,
"learning_rate": 0.0002,
"loss": 0.0056,
"step": 197
},
{
"epoch": 6.39,
"learning_rate": 0.0002,
"loss": 0.0015,
"step": 198
},
{
"epoch": 6.42,
"learning_rate": 0.0002,
"loss": 0.0028,
"step": 199
},
{
"epoch": 6.45,
"learning_rate": 0.0002,
"loss": 0.0012,
"step": 200
},
{
"epoch": 6.48,
"learning_rate": 0.0002,
"loss": 0.006,
"step": 201
},
{
"epoch": 6.52,
"learning_rate": 0.0002,
"loss": 0.0033,
"step": 202
},
{
"epoch": 6.55,
"learning_rate": 0.0002,
"loss": 0.0035,
"step": 203
},
{
"epoch": 6.58,
"learning_rate": 0.0002,
"loss": 0.0019,
"step": 204
},
{
"epoch": 6.61,
"learning_rate": 0.0002,
"loss": 0.007,
"step": 205
},
{
"epoch": 6.65,
"learning_rate": 0.0002,
"loss": 0.0019,
"step": 206
},
{
"epoch": 6.68,
"learning_rate": 0.0002,
"loss": 0.0053,
"step": 207
},
{
"epoch": 6.71,
"learning_rate": 0.0002,
"loss": 0.0013,
"step": 208
},
{
"epoch": 6.74,
"learning_rate": 0.0002,
"loss": 0.0021,
"step": 209
},
{
"epoch": 6.77,
"learning_rate": 0.0002,
"loss": 0.0041,
"step": 210
},
{
"epoch": 6.81,
"learning_rate": 0.0002,
"loss": 0.0028,
"step": 211
},
{
"epoch": 6.84,
"learning_rate": 0.0002,
"loss": 0.0016,
"step": 212
},
{
"epoch": 6.87,
"learning_rate": 0.0002,
"loss": 0.002,
"step": 213
},
{
"epoch": 6.9,
"learning_rate": 0.0002,
"loss": 0.0026,
"step": 214
},
{
"epoch": 6.94,
"learning_rate": 0.0002,
"loss": 0.0053,
"step": 215
},
{
"epoch": 6.97,
"learning_rate": 0.0002,
"loss": 0.0024,
"step": 216
},
{
"epoch": 7.0,
"learning_rate": 0.0002,
"loss": 0.0023,
"step": 217
},
{
"epoch": 7.0,
"eval_loss": 0.003779121907427907,
"eval_runtime": 79.3546,
"eval_samples_per_second": 12.236,
"eval_steps_per_second": 0.391,
"step": 217
},
{
"epoch": 7.03,
"learning_rate": 0.0002,
"loss": 0.0031,
"step": 218
},
{
"epoch": 7.06,
"learning_rate": 0.0002,
"loss": 0.0043,
"step": 219
},
{
"epoch": 7.1,
"learning_rate": 0.0002,
"loss": 0.0056,
"step": 220
},
{
"epoch": 7.13,
"learning_rate": 0.0002,
"loss": 0.0018,
"step": 221
},
{
"epoch": 7.16,
"learning_rate": 0.0002,
"loss": 0.0013,
"step": 222
},
{
"epoch": 7.19,
"learning_rate": 0.0002,
"loss": 0.0009,
"step": 223
},
{
"epoch": 7.23,
"learning_rate": 0.0002,
"loss": 0.0019,
"step": 224
},
{
"epoch": 7.26,
"learning_rate": 0.0002,
"loss": 0.0054,
"step": 225
},
{
"epoch": 7.29,
"learning_rate": 0.0002,
"loss": 0.0027,
"step": 226
},
{
"epoch": 7.32,
"learning_rate": 0.0002,
"loss": 0.0025,
"step": 227
},
{
"epoch": 7.35,
"learning_rate": 0.0002,
"loss": 0.0031,
"step": 228
},
{
"epoch": 7.39,
"learning_rate": 0.0002,
"loss": 0.0021,
"step": 229
},
{
"epoch": 7.42,
"learning_rate": 0.0002,
"loss": 0.0025,
"step": 230
},
{
"epoch": 7.45,
"learning_rate": 0.0002,
"loss": 0.0018,
"step": 231
},
{
"epoch": 7.48,
"learning_rate": 0.0002,
"loss": 0.0015,
"step": 232
},
{
"epoch": 7.52,
"learning_rate": 0.0002,
"loss": 0.0014,
"step": 233
},
{
"epoch": 7.55,
"learning_rate": 0.0002,
"loss": 0.0036,
"step": 234
},
{
"epoch": 7.58,
"learning_rate": 0.0002,
"loss": 0.0006,
"step": 235
},
{
"epoch": 7.61,
"learning_rate": 0.0002,
"loss": 0.0022,
"step": 236
},
{
"epoch": 7.65,
"learning_rate": 0.0002,
"loss": 0.0039,
"step": 237
},
{
"epoch": 7.68,
"learning_rate": 0.0002,
"loss": 0.0026,
"step": 238
},
{
"epoch": 7.71,
"learning_rate": 0.0002,
"loss": 0.0011,
"step": 239
},
{
"epoch": 7.74,
"learning_rate": 0.0002,
"loss": 0.0045,
"step": 240
},
{
"epoch": 7.77,
"learning_rate": 0.0002,
"loss": 0.0028,
"step": 241
},
{
"epoch": 7.81,
"learning_rate": 0.0002,
"loss": 0.0026,
"step": 242
},
{
"epoch": 7.84,
"learning_rate": 0.0002,
"loss": 0.0083,
"step": 243
},
{
"epoch": 7.87,
"learning_rate": 0.0002,
"loss": 0.0009,
"step": 244
},
{
"epoch": 7.9,
"learning_rate": 0.0002,
"loss": 0.0012,
"step": 245
},
{
"epoch": 7.94,
"learning_rate": 0.0002,
"loss": 0.0033,
"step": 246
},
{
"epoch": 7.97,
"learning_rate": 0.0002,
"loss": 0.0016,
"step": 247
},
{
"epoch": 8.0,
"learning_rate": 0.0002,
"loss": 0.0024,
"step": 248
},
{
"epoch": 8.0,
"eval_loss": 0.00199125986546278,
"eval_runtime": 79.2097,
"eval_samples_per_second": 12.259,
"eval_steps_per_second": 0.391,
"step": 248
},
{
"epoch": 8.03,
"learning_rate": 0.0002,
"loss": 0.0017,
"step": 249
},
{
"epoch": 8.06,
"learning_rate": 0.0002,
"loss": 0.0041,
"step": 250
},
{
"epoch": 8.1,
"learning_rate": 0.0002,
"loss": 0.0019,
"step": 251
},
{
"epoch": 8.13,
"learning_rate": 0.0002,
"loss": 0.0016,
"step": 252
},
{
"epoch": 8.16,
"learning_rate": 0.0002,
"loss": 0.0008,
"step": 253
},
{
"epoch": 8.19,
"learning_rate": 0.0002,
"loss": 0.0008,
"step": 254
},
{
"epoch": 8.23,
"learning_rate": 0.0002,
"loss": 0.0026,
"step": 255
},
{
"epoch": 8.26,
"learning_rate": 0.0002,
"loss": 0.0024,
"step": 256
},
{
"epoch": 8.29,
"learning_rate": 0.0002,
"loss": 0.0021,
"step": 257
},
{
"epoch": 8.32,
"learning_rate": 0.0002,
"loss": 0.0034,
"step": 258
},
{
"epoch": 8.35,
"learning_rate": 0.0002,
"loss": 0.0029,
"step": 259
},
{
"epoch": 8.39,
"learning_rate": 0.0002,
"loss": 0.0021,
"step": 260
},
{
"epoch": 8.42,
"learning_rate": 0.0002,
"loss": 0.0055,
"step": 261
},
{
"epoch": 8.45,
"learning_rate": 0.0002,
"loss": 0.0019,
"step": 262
},
{
"epoch": 8.48,
"learning_rate": 0.0002,
"loss": 0.0025,
"step": 263
},
{
"epoch": 8.52,
"learning_rate": 0.0002,
"loss": 0.0067,
"step": 264
},
{
"epoch": 8.55,
"learning_rate": 0.0002,
"loss": 0.0036,
"step": 265
},
{
"epoch": 8.58,
"learning_rate": 0.0002,
"loss": 0.0037,
"step": 266
},
{
"epoch": 8.61,
"learning_rate": 0.0002,
"loss": 0.0033,
"step": 267
},
{
"epoch": 8.65,
"learning_rate": 0.0002,
"loss": 0.0019,
"step": 268
},
{
"epoch": 8.68,
"learning_rate": 0.0002,
"loss": 0.0034,
"step": 269
},
{
"epoch": 8.71,
"learning_rate": 0.0002,
"loss": 0.003,
"step": 270
},
{
"epoch": 8.74,
"learning_rate": 0.0002,
"loss": 0.0045,
"step": 271
},
{
"epoch": 8.77,
"learning_rate": 0.0002,
"loss": 0.0058,
"step": 272
},
{
"epoch": 8.81,
"learning_rate": 0.0002,
"loss": 0.0019,
"step": 273
},
{
"epoch": 8.84,
"learning_rate": 0.0002,
"loss": 0.0044,
"step": 274
},
{
"epoch": 8.87,
"learning_rate": 0.0002,
"loss": 0.0037,
"step": 275
},
{
"epoch": 8.9,
"learning_rate": 0.0002,
"loss": 0.0037,
"step": 276
},
{
"epoch": 8.94,
"learning_rate": 0.0002,
"loss": 0.0074,
"step": 277
},
{
"epoch": 8.97,
"learning_rate": 0.0002,
"loss": 0.0025,
"step": 278
},
{
"epoch": 9.0,
"learning_rate": 0.0002,
"loss": 0.0032,
"step": 279
},
{
"epoch": 9.0,
"eval_loss": 0.0030502593144774437,
"eval_runtime": 79.2563,
"eval_samples_per_second": 12.251,
"eval_steps_per_second": 0.391,
"step": 279
},
{
"epoch": 9.03,
"learning_rate": 0.0002,
"loss": 0.0028,
"step": 280
},
{
"epoch": 9.06,
"learning_rate": 0.0002,
"loss": 0.0036,
"step": 281
},
{
"epoch": 9.1,
"learning_rate": 0.0002,
"loss": 0.0033,
"step": 282
},
{
"epoch": 9.13,
"learning_rate": 0.0002,
"loss": 0.0032,
"step": 283
},
{
"epoch": 9.16,
"learning_rate": 0.0002,
"loss": 0.002,
"step": 284
},
{
"epoch": 9.19,
"learning_rate": 0.0002,
"loss": 0.0028,
"step": 285
},
{
"epoch": 9.23,
"learning_rate": 0.0002,
"loss": 0.0025,
"step": 286
},
{
"epoch": 9.26,
"learning_rate": 0.0002,
"loss": 0.0012,
"step": 287
},
{
"epoch": 9.29,
"learning_rate": 0.0002,
"loss": 0.0014,
"step": 288
},
{
"epoch": 9.32,
"learning_rate": 0.0002,
"loss": 0.0032,
"step": 289
},
{
"epoch": 9.35,
"learning_rate": 0.0002,
"loss": 0.0016,
"step": 290
},
{
"epoch": 9.39,
"learning_rate": 0.0002,
"loss": 0.0019,
"step": 291
},
{
"epoch": 9.42,
"learning_rate": 0.0002,
"loss": 0.0022,
"step": 292
},
{
"epoch": 9.45,
"learning_rate": 0.0002,
"loss": 0.0022,
"step": 293
},
{
"epoch": 9.48,
"learning_rate": 0.0002,
"loss": 0.0016,
"step": 294
},
{
"epoch": 9.52,
"learning_rate": 0.0002,
"loss": 0.003,
"step": 295
},
{
"epoch": 9.55,
"learning_rate": 0.0002,
"loss": 0.0036,
"step": 296
},
{
"epoch": 9.58,
"learning_rate": 0.0002,
"loss": 0.0064,
"step": 297
},
{
"epoch": 9.61,
"learning_rate": 0.0002,
"loss": 0.0053,
"step": 298
},
{
"epoch": 9.65,
"learning_rate": 0.0002,
"loss": 0.003,
"step": 299
},
{
"epoch": 9.68,
"learning_rate": 0.0002,
"loss": 0.0034,
"step": 300
},
{
"epoch": 9.71,
"learning_rate": 0.0002,
"loss": 0.0017,
"step": 301
},
{
"epoch": 9.74,
"learning_rate": 0.0002,
"loss": 0.0013,
"step": 302
},
{
"epoch": 9.77,
"learning_rate": 0.0002,
"loss": 0.0028,
"step": 303
},
{
"epoch": 9.81,
"learning_rate": 0.0002,
"loss": 0.0055,
"step": 304
},
{
"epoch": 9.84,
"learning_rate": 0.0002,
"loss": 0.0043,
"step": 305
},
{
"epoch": 9.87,
"learning_rate": 0.0002,
"loss": 0.0014,
"step": 306
},
{
"epoch": 9.9,
"learning_rate": 0.0002,
"loss": 0.0014,
"step": 307
},
{
"epoch": 9.94,
"learning_rate": 0.0002,
"loss": 0.0033,
"step": 308
},
{
"epoch": 9.97,
"learning_rate": 0.0002,
"loss": 0.0023,
"step": 309
},
{
"epoch": 10.0,
"learning_rate": 0.0002,
"loss": 0.0016,
"step": 310
},
{
"epoch": 10.0,
"eval_loss": 0.002159351482987404,
"eval_runtime": 79.3857,
"eval_samples_per_second": 12.231,
"eval_steps_per_second": 0.39,
"step": 310
},
{
"epoch": 10.03,
"learning_rate": 0.0002,
"loss": 0.0014,
"step": 311
},
{
"epoch": 10.06,
"learning_rate": 0.0002,
"loss": 0.0028,
"step": 312
},
{
"epoch": 10.1,
"learning_rate": 0.0002,
"loss": 0.0034,
"step": 313
},
{
"epoch": 10.13,
"learning_rate": 0.0002,
"loss": 0.0012,
"step": 314
},
{
"epoch": 10.16,
"learning_rate": 0.0002,
"loss": 0.0022,
"step": 315
},
{
"epoch": 10.19,
"learning_rate": 0.0002,
"loss": 0.0008,
"step": 316
},
{
"epoch": 10.23,
"learning_rate": 0.0002,
"loss": 0.0049,
"step": 317
},
{
"epoch": 10.26,
"learning_rate": 0.0002,
"loss": 0.0023,
"step": 318
},
{
"epoch": 10.29,
"learning_rate": 0.0002,
"loss": 0.0012,
"step": 319
},
{
"epoch": 10.32,
"learning_rate": 0.0002,
"loss": 0.003,
"step": 320
},
{
"epoch": 10.35,
"learning_rate": 0.0002,
"loss": 0.0018,
"step": 321
},
{
"epoch": 10.39,
"learning_rate": 0.0002,
"loss": 0.0005,
"step": 322
},
{
"epoch": 10.42,
"learning_rate": 0.0002,
"loss": 0.0014,
"step": 323
},
{
"epoch": 10.45,
"learning_rate": 0.0002,
"loss": 0.0025,
"step": 324
},
{
"epoch": 10.48,
"learning_rate": 0.0002,
"loss": 0.0023,
"step": 325
},
{
"epoch": 10.52,
"learning_rate": 0.0002,
"loss": 0.002,
"step": 326
},
{
"epoch": 10.55,
"learning_rate": 0.0002,
"loss": 0.0038,
"step": 327
},
{
"epoch": 10.58,
"learning_rate": 0.0002,
"loss": 0.0014,
"step": 328
},
{
"epoch": 10.61,
"learning_rate": 0.0002,
"loss": 0.0053,
"step": 329
},
{
"epoch": 10.65,
"learning_rate": 0.0002,
"loss": 0.0033,
"step": 330
},
{
"epoch": 10.68,
"learning_rate": 0.0002,
"loss": 0.005,
"step": 331
},
{
"epoch": 10.71,
"learning_rate": 0.0002,
"loss": 0.0043,
"step": 332
},
{
"epoch": 10.74,
"learning_rate": 0.0002,
"loss": 0.004,
"step": 333
},
{
"epoch": 10.77,
"learning_rate": 0.0002,
"loss": 0.0037,
"step": 334
},
{
"epoch": 10.81,
"learning_rate": 0.0002,
"loss": 0.0048,
"step": 335
},
{
"epoch": 10.84,
"learning_rate": 0.0002,
"loss": 0.0087,
"step": 336
},
{
"epoch": 10.87,
"learning_rate": 0.0002,
"loss": 0.0051,
"step": 337
},
{
"epoch": 10.9,
"learning_rate": 0.0002,
"loss": 0.0051,
"step": 338
},
{
"epoch": 10.94,
"learning_rate": 0.0002,
"loss": 0.0045,
"step": 339
},
{
"epoch": 10.97,
"learning_rate": 0.0002,
"loss": 0.0088,
"step": 340
},
{
"epoch": 11.0,
"learning_rate": 0.0002,
"loss": 0.0049,
"step": 341
},
{
"epoch": 11.0,
"eval_loss": 0.0032238007988780737,
"eval_runtime": 79.3714,
"eval_samples_per_second": 12.234,
"eval_steps_per_second": 0.391,
"step": 341
},
{
"epoch": 11.03,
"learning_rate": 0.0002,
"loss": 0.0023,
"step": 342
},
{
"epoch": 11.06,
"learning_rate": 0.0002,
"loss": 0.0023,
"step": 343
},
{
"epoch": 11.1,
"learning_rate": 0.0002,
"loss": 0.0035,
"step": 344
},
{
"epoch": 11.13,
"learning_rate": 0.0002,
"loss": 0.0022,
"step": 345
},
{
"epoch": 11.16,
"learning_rate": 0.0002,
"loss": 0.0032,
"step": 346
},
{
"epoch": 11.19,
"learning_rate": 0.0002,
"loss": 0.0042,
"step": 347
},
{
"epoch": 11.23,
"learning_rate": 0.0002,
"loss": 0.0017,
"step": 348
},
{
"epoch": 11.26,
"learning_rate": 0.0002,
"loss": 0.0066,
"step": 349
},
{
"epoch": 11.29,
"learning_rate": 0.0002,
"loss": 0.0079,
"step": 350
},
{
"epoch": 11.32,
"learning_rate": 0.0002,
"loss": 0.0031,
"step": 351
},
{
"epoch": 11.35,
"learning_rate": 0.0002,
"loss": 0.0081,
"step": 352
},
{
"epoch": 11.39,
"learning_rate": 0.0002,
"loss": 0.0062,
"step": 353
},
{
"epoch": 11.42,
"learning_rate": 0.0002,
"loss": 0.0035,
"step": 354
},
{
"epoch": 11.45,
"learning_rate": 0.0002,
"loss": 0.0036,
"step": 355
},
{
"epoch": 11.48,
"learning_rate": 0.0002,
"loss": 0.0029,
"step": 356
},
{
"epoch": 11.52,
"learning_rate": 0.0002,
"loss": 0.0034,
"step": 357
},
{
"epoch": 11.55,
"learning_rate": 0.0002,
"loss": 0.0037,
"step": 358
},
{
"epoch": 11.58,
"learning_rate": 0.0002,
"loss": 0.0067,
"step": 359
},
{
"epoch": 11.61,
"learning_rate": 0.0002,
"loss": 0.0015,
"step": 360
},
{
"epoch": 11.65,
"learning_rate": 0.0002,
"loss": 0.0053,
"step": 361
},
{
"epoch": 11.68,
"learning_rate": 0.0002,
"loss": 0.0025,
"step": 362
},
{
"epoch": 11.71,
"learning_rate": 0.0002,
"loss": 0.0073,
"step": 363
},
{
"epoch": 11.74,
"learning_rate": 0.0002,
"loss": 0.0043,
"step": 364
},
{
"epoch": 11.77,
"learning_rate": 0.0002,
"loss": 0.004,
"step": 365
},
{
"epoch": 11.81,
"learning_rate": 0.0002,
"loss": 0.0061,
"step": 366
},
{
"epoch": 11.84,
"learning_rate": 0.0002,
"loss": 0.0074,
"step": 367
},
{
"epoch": 11.87,
"learning_rate": 0.0002,
"loss": 0.007,
"step": 368
},
{
"epoch": 11.9,
"learning_rate": 0.0002,
"loss": 0.004,
"step": 369
},
{
"epoch": 11.94,
"learning_rate": 0.0002,
"loss": 0.0066,
"step": 370
},
{
"epoch": 11.97,
"learning_rate": 0.0002,
"loss": 0.0051,
"step": 371
},
{
"epoch": 12.0,
"learning_rate": 0.0002,
"loss": 0.0022,
"step": 372
},
{
"epoch": 12.0,
"eval_loss": 0.004942539148032665,
"eval_runtime": 79.161,
"eval_samples_per_second": 12.266,
"eval_steps_per_second": 0.392,
"step": 372
},
{
"epoch": 12.03,
"learning_rate": 0.0002,
"loss": 0.0037,
"step": 373
},
{
"epoch": 12.06,
"learning_rate": 0.0002,
"loss": 0.004,
"step": 374
},
{
"epoch": 12.1,
"learning_rate": 0.0002,
"loss": 0.003,
"step": 375
},
{
"epoch": 12.13,
"learning_rate": 0.0002,
"loss": 0.0033,
"step": 376
},
{
"epoch": 12.16,
"learning_rate": 0.0002,
"loss": 0.0071,
"step": 377
},
{
"epoch": 12.19,
"learning_rate": 0.0002,
"loss": 0.0052,
"step": 378
},
{
"epoch": 12.23,
"learning_rate": 0.0002,
"loss": 0.0047,
"step": 379
},
{
"epoch": 12.26,
"learning_rate": 0.0002,
"loss": 0.006,
"step": 380
},
{
"epoch": 12.29,
"learning_rate": 0.0002,
"loss": 0.0058,
"step": 381
},
{
"epoch": 12.32,
"learning_rate": 0.0002,
"loss": 0.0065,
"step": 382
},
{
"epoch": 12.35,
"learning_rate": 0.0002,
"loss": 0.0039,
"step": 383
},
{
"epoch": 12.39,
"learning_rate": 0.0002,
"loss": 0.006,
"step": 384
},
{
"epoch": 12.42,
"learning_rate": 0.0002,
"loss": 0.0038,
"step": 385
},
{
"epoch": 12.45,
"learning_rate": 0.0002,
"loss": 0.005,
"step": 386
},
{
"epoch": 12.48,
"learning_rate": 0.0002,
"loss": 0.0053,
"step": 387
},
{
"epoch": 12.52,
"learning_rate": 0.0002,
"loss": 0.0033,
"step": 388
},
{
"epoch": 12.55,
"learning_rate": 0.0002,
"loss": 0.005,
"step": 389
},
{
"epoch": 12.58,
"learning_rate": 0.0002,
"loss": 0.0038,
"step": 390
},
{
"epoch": 12.61,
"learning_rate": 0.0002,
"loss": 0.0025,
"step": 391
},
{
"epoch": 12.65,
"learning_rate": 0.0002,
"loss": 0.0069,
"step": 392
},
{
"epoch": 12.68,
"learning_rate": 0.0002,
"loss": 0.0068,
"step": 393
},
{
"epoch": 12.71,
"learning_rate": 0.0002,
"loss": 0.0069,
"step": 394
},
{
"epoch": 12.74,
"learning_rate": 0.0002,
"loss": 0.0038,
"step": 395
},
{
"epoch": 12.77,
"learning_rate": 0.0002,
"loss": 0.0036,
"step": 396
},
{
"epoch": 12.81,
"learning_rate": 0.0002,
"loss": 0.0067,
"step": 397
},
{
"epoch": 12.84,
"learning_rate": 0.0002,
"loss": 0.0045,
"step": 398
},
{
"epoch": 12.87,
"learning_rate": 0.0002,
"loss": 0.0056,
"step": 399
},
{
"epoch": 12.9,
"learning_rate": 0.0002,
"loss": 0.0059,
"step": 400
},
{
"epoch": 12.94,
"learning_rate": 0.0002,
"loss": 0.003,
"step": 401
},
{
"epoch": 12.97,
"learning_rate": 0.0002,
"loss": 0.0064,
"step": 402
},
{
"epoch": 13.0,
"learning_rate": 0.0002,
"loss": 0.0035,
"step": 403
},
{
"epoch": 13.0,
"eval_loss": 0.007653499487787485,
"eval_runtime": 79.6263,
"eval_samples_per_second": 12.194,
"eval_steps_per_second": 0.389,
"step": 403
},
{
"epoch": 13.03,
"learning_rate": 0.0002,
"loss": 0.0063,
"step": 404
},
{
"epoch": 13.06,
"learning_rate": 0.0002,
"loss": 0.0052,
"step": 405
},
{
"epoch": 13.1,
"learning_rate": 0.0002,
"loss": 0.0048,
"step": 406
},
{
"epoch": 13.13,
"learning_rate": 0.0002,
"loss": 0.0066,
"step": 407
},
{
"epoch": 13.16,
"learning_rate": 0.0002,
"loss": 0.0127,
"step": 408
},
{
"epoch": 13.19,
"learning_rate": 0.0002,
"loss": 0.007,
"step": 409
},
{
"epoch": 13.23,
"learning_rate": 0.0002,
"loss": 0.0106,
"step": 410
},
{
"epoch": 13.26,
"learning_rate": 0.0002,
"loss": 0.0053,
"step": 411
},
{
"epoch": 13.29,
"learning_rate": 0.0002,
"loss": 0.0067,
"step": 412
},
{
"epoch": 13.32,
"learning_rate": 0.0002,
"loss": 0.0051,
"step": 413
},
{
"epoch": 13.35,
"learning_rate": 0.0002,
"loss": 0.0029,
"step": 414
},
{
"epoch": 13.39,
"learning_rate": 0.0002,
"loss": 0.0036,
"step": 415
},
{
"epoch": 13.42,
"learning_rate": 0.0002,
"loss": 0.0039,
"step": 416
},
{
"epoch": 13.45,
"learning_rate": 0.0002,
"loss": 0.0077,
"step": 417
},
{
"epoch": 13.48,
"learning_rate": 0.0002,
"loss": 0.003,
"step": 418
},
{
"epoch": 13.52,
"learning_rate": 0.0002,
"loss": 0.0064,
"step": 419
},
{
"epoch": 13.55,
"learning_rate": 0.0002,
"loss": 0.0104,
"step": 420
},
{
"epoch": 13.58,
"learning_rate": 0.0002,
"loss": 0.0098,
"step": 421
},
{
"epoch": 13.61,
"learning_rate": 0.0002,
"loss": 0.0069,
"step": 422
},
{
"epoch": 13.65,
"learning_rate": 0.0002,
"loss": 0.0078,
"step": 423
},
{
"epoch": 13.68,
"learning_rate": 0.0002,
"loss": 0.0084,
"step": 424
},
{
"epoch": 13.71,
"learning_rate": 0.0002,
"loss": 0.0043,
"step": 425
},
{
"epoch": 13.74,
"learning_rate": 0.0002,
"loss": 0.009,
"step": 426
},
{
"epoch": 13.77,
"learning_rate": 0.0002,
"loss": 0.0058,
"step": 427
},
{
"epoch": 13.81,
"learning_rate": 0.0002,
"loss": 0.0089,
"step": 428
},
{
"epoch": 13.84,
"learning_rate": 0.0002,
"loss": 0.0098,
"step": 429
},
{
"epoch": 13.87,
"learning_rate": 0.0002,
"loss": 0.0051,
"step": 430
},
{
"epoch": 13.9,
"learning_rate": 0.0002,
"loss": 0.0043,
"step": 431
},
{
"epoch": 13.94,
"learning_rate": 0.0002,
"loss": 0.0039,
"step": 432
},
{
"epoch": 13.97,
"learning_rate": 0.0002,
"loss": 0.0032,
"step": 433
},
{
"epoch": 14.0,
"learning_rate": 0.0002,
"loss": 0.0063,
"step": 434
},
{
"epoch": 14.0,
"eval_loss": 0.0040127672255039215,
"eval_runtime": 79.5726,
"eval_samples_per_second": 12.203,
"eval_steps_per_second": 0.39,
"step": 434
},
{
"epoch": 14.03,
"learning_rate": 0.0002,
"loss": 0.0046,
"step": 435
},
{
"epoch": 14.06,
"learning_rate": 0.0002,
"loss": 0.0081,
"step": 436
},
{
"epoch": 14.1,
"learning_rate": 0.0002,
"loss": 0.0023,
"step": 437
},
{
"epoch": 14.13,
"learning_rate": 0.0002,
"loss": 0.0062,
"step": 438
},
{
"epoch": 14.16,
"learning_rate": 0.0002,
"loss": 0.0025,
"step": 439
},
{
"epoch": 14.19,
"learning_rate": 0.0002,
"loss": 0.0012,
"step": 440
},
{
"epoch": 14.23,
"learning_rate": 0.0002,
"loss": 0.0029,
"step": 441
},
{
"epoch": 14.26,
"learning_rate": 0.0002,
"loss": 0.003,
"step": 442
},
{
"epoch": 14.29,
"learning_rate": 0.0002,
"loss": 0.0045,
"step": 443
},
{
"epoch": 14.32,
"learning_rate": 0.0002,
"loss": 0.0112,
"step": 444
},
{
"epoch": 14.35,
"learning_rate": 0.0002,
"loss": 0.0083,
"step": 445
},
{
"epoch": 14.39,
"learning_rate": 0.0002,
"loss": 0.0036,
"step": 446
},
{
"epoch": 14.42,
"learning_rate": 0.0002,
"loss": 0.0023,
"step": 447
},
{
"epoch": 14.45,
"learning_rate": 0.0002,
"loss": 0.0033,
"step": 448
},
{
"epoch": 14.48,
"learning_rate": 0.0002,
"loss": 0.003,
"step": 449
},
{
"epoch": 14.52,
"learning_rate": 0.0002,
"loss": 0.0109,
"step": 450
},
{
"epoch": 14.55,
"learning_rate": 0.0002,
"loss": 0.0085,
"step": 451
},
{
"epoch": 14.58,
"learning_rate": 0.0002,
"loss": 0.0051,
"step": 452
},
{
"epoch": 14.61,
"learning_rate": 0.0002,
"loss": 0.0065,
"step": 453
},
{
"epoch": 14.65,
"learning_rate": 0.0002,
"loss": 0.0049,
"step": 454
},
{
"epoch": 14.68,
"learning_rate": 0.0002,
"loss": 0.007,
"step": 455
},
{
"epoch": 14.71,
"learning_rate": 0.0002,
"loss": 0.0024,
"step": 456
},
{
"epoch": 14.74,
"learning_rate": 0.0002,
"loss": 0.007,
"step": 457
},
{
"epoch": 14.77,
"learning_rate": 0.0002,
"loss": 0.0034,
"step": 458
},
{
"epoch": 14.81,
"learning_rate": 0.0002,
"loss": 0.0048,
"step": 459
},
{
"epoch": 14.84,
"learning_rate": 0.0002,
"loss": 0.0053,
"step": 460
},
{
"epoch": 14.87,
"learning_rate": 0.0002,
"loss": 0.0087,
"step": 461
},
{
"epoch": 14.9,
"learning_rate": 0.0002,
"loss": 0.0068,
"step": 462
},
{
"epoch": 14.94,
"learning_rate": 0.0002,
"loss": 0.007,
"step": 463
},
{
"epoch": 14.97,
"learning_rate": 0.0002,
"loss": 0.0067,
"step": 464
},
{
"epoch": 15.0,
"learning_rate": 0.0002,
"loss": 0.0076,
"step": 465
},
{
"epoch": 15.0,
"eval_loss": 0.00824675615876913,
"eval_runtime": 79.7814,
"eval_samples_per_second": 12.171,
"eval_steps_per_second": 0.389,
"step": 465
},
{
"epoch": 15.03,
"learning_rate": 0.0002,
"loss": 0.0087,
"step": 466
},
{
"epoch": 15.06,
"learning_rate": 0.0002,
"loss": 0.0094,
"step": 467
},
{
"epoch": 15.1,
"learning_rate": 0.0002,
"loss": 0.011,
"step": 468
},
{
"epoch": 15.13,
"learning_rate": 0.0002,
"loss": 0.0064,
"step": 469
},
{
"epoch": 15.16,
"learning_rate": 0.0002,
"loss": 0.0067,
"step": 470
},
{
"epoch": 15.19,
"learning_rate": 0.0002,
"loss": 0.0126,
"step": 471
},
{
"epoch": 15.23,
"learning_rate": 0.0002,
"loss": 0.0078,
"step": 472
},
{
"epoch": 15.26,
"learning_rate": 0.0002,
"loss": 0.01,
"step": 473
},
{
"epoch": 15.29,
"learning_rate": 0.0002,
"loss": 0.0185,
"step": 474
},
{
"epoch": 15.32,
"learning_rate": 0.0002,
"loss": 0.0037,
"step": 475
},
{
"epoch": 15.35,
"learning_rate": 0.0002,
"loss": 0.0077,
"step": 476
},
{
"epoch": 15.39,
"learning_rate": 0.0002,
"loss": 0.0095,
"step": 477
},
{
"epoch": 15.42,
"learning_rate": 0.0002,
"loss": 0.0053,
"step": 478
},
{
"epoch": 15.45,
"learning_rate": 0.0002,
"loss": 0.0059,
"step": 479
},
{
"epoch": 15.48,
"learning_rate": 0.0002,
"loss": 0.0083,
"step": 480
},
{
"epoch": 15.52,
"learning_rate": 0.0002,
"loss": 0.0101,
"step": 481
},
{
"epoch": 15.55,
"learning_rate": 0.0002,
"loss": 0.0043,
"step": 482
},
{
"epoch": 15.58,
"learning_rate": 0.0002,
"loss": 0.0088,
"step": 483
},
{
"epoch": 15.61,
"learning_rate": 0.0002,
"loss": 0.0085,
"step": 484
},
{
"epoch": 15.65,
"learning_rate": 0.0002,
"loss": 0.0088,
"step": 485
},
{
"epoch": 15.68,
"learning_rate": 0.0002,
"loss": 0.0083,
"step": 486
},
{
"epoch": 15.71,
"learning_rate": 0.0002,
"loss": 0.0038,
"step": 487
},
{
"epoch": 15.74,
"learning_rate": 0.0002,
"loss": 0.0132,
"step": 488
},
{
"epoch": 15.77,
"learning_rate": 0.0002,
"loss": 0.0092,
"step": 489
},
{
"epoch": 15.81,
"learning_rate": 0.0002,
"loss": 0.0084,
"step": 490
},
{
"epoch": 15.84,
"learning_rate": 0.0002,
"loss": 0.0059,
"step": 491
},
{
"epoch": 15.87,
"learning_rate": 0.0002,
"loss": 0.0051,
"step": 492
},
{
"epoch": 15.9,
"learning_rate": 0.0002,
"loss": 0.0046,
"step": 493
},
{
"epoch": 15.94,
"learning_rate": 0.0002,
"loss": 0.0159,
"step": 494
},
{
"epoch": 15.97,
"learning_rate": 0.0002,
"loss": 0.0041,
"step": 495
},
{
"epoch": 16.0,
"learning_rate": 0.0002,
"loss": 0.0063,
"step": 496
},
{
"epoch": 16.0,
"eval_loss": 0.006366066634654999,
"eval_runtime": 80.009,
"eval_samples_per_second": 12.136,
"eval_steps_per_second": 0.387,
"step": 496
},
{
"epoch": 16.03,
"learning_rate": 0.0002,
"loss": 0.0048,
"step": 497
},
{
"epoch": 16.06,
"learning_rate": 0.0002,
"loss": 0.0127,
"step": 498
},
{
"epoch": 16.1,
"learning_rate": 0.0002,
"loss": 0.0072,
"step": 499
},
{
"epoch": 16.13,
"learning_rate": 0.0002,
"loss": 0.0088,
"step": 500
},
{
"epoch": 16.16,
"learning_rate": 0.0002,
"loss": 0.015,
"step": 501
},
{
"epoch": 16.19,
"learning_rate": 0.0002,
"loss": 0.0076,
"step": 502
},
{
"epoch": 16.23,
"learning_rate": 0.0002,
"loss": 0.0071,
"step": 503
},
{
"epoch": 16.26,
"learning_rate": 0.0002,
"loss": 0.0109,
"step": 504
},
{
"epoch": 16.29,
"learning_rate": 0.0002,
"loss": 0.0094,
"step": 505
},
{
"epoch": 16.32,
"learning_rate": 0.0002,
"loss": 0.0055,
"step": 506
},
{
"epoch": 16.35,
"learning_rate": 0.0002,
"loss": 0.006,
"step": 507
},
{
"epoch": 16.39,
"learning_rate": 0.0002,
"loss": 0.0079,
"step": 508
},
{
"epoch": 16.42,
"learning_rate": 0.0002,
"loss": 0.0114,
"step": 509
},
{
"epoch": 16.45,
"learning_rate": 0.0002,
"loss": 0.0085,
"step": 510
},
{
"epoch": 16.48,
"learning_rate": 0.0002,
"loss": 0.0088,
"step": 511
},
{
"epoch": 16.52,
"learning_rate": 0.0002,
"loss": 0.0103,
"step": 512
},
{
"epoch": 16.55,
"learning_rate": 0.0002,
"loss": 0.0092,
"step": 513
},
{
"epoch": 16.58,
"learning_rate": 0.0002,
"loss": 0.0055,
"step": 514
},
{
"epoch": 16.61,
"learning_rate": 0.0002,
"loss": 0.0114,
"step": 515
},
{
"epoch": 16.65,
"learning_rate": 0.0002,
"loss": 0.0095,
"step": 516
},
{
"epoch": 16.68,
"learning_rate": 0.0002,
"loss": 0.0082,
"step": 517
},
{
"epoch": 16.71,
"learning_rate": 0.0002,
"loss": 0.0118,
"step": 518
},
{
"epoch": 16.74,
"learning_rate": 0.0002,
"loss": 0.0098,
"step": 519
},
{
"epoch": 16.77,
"learning_rate": 0.0002,
"loss": 0.0115,
"step": 520
},
{
"epoch": 16.81,
"learning_rate": 0.0002,
"loss": 0.0123,
"step": 521
},
{
"epoch": 16.84,
"learning_rate": 0.0002,
"loss": 0.0102,
"step": 522
},
{
"epoch": 16.87,
"learning_rate": 0.0002,
"loss": 0.0089,
"step": 523
},
{
"epoch": 16.9,
"learning_rate": 0.0002,
"loss": 0.0042,
"step": 524
},
{
"epoch": 16.94,
"learning_rate": 0.0002,
"loss": 0.0098,
"step": 525
},
{
"epoch": 16.97,
"learning_rate": 0.0002,
"loss": 0.0061,
"step": 526
},
{
"epoch": 17.0,
"learning_rate": 0.0002,
"loss": 0.0086,
"step": 527
},
{
"epoch": 17.0,
"eval_loss": 0.006956302560865879,
"eval_runtime": 79.5624,
"eval_samples_per_second": 12.204,
"eval_steps_per_second": 0.39,
"step": 527
},
{
"epoch": 17.03,
"learning_rate": 0.0002,
"loss": 0.0083,
"step": 528
},
{
"epoch": 17.06,
"learning_rate": 0.0002,
"loss": 0.007,
"step": 529
},
{
"epoch": 17.1,
"learning_rate": 0.0002,
"loss": 0.0096,
"step": 530
},
{
"epoch": 17.13,
"learning_rate": 0.0002,
"loss": 0.0091,
"step": 531
},
{
"epoch": 17.16,
"learning_rate": 0.0002,
"loss": 0.0083,
"step": 532
},
{
"epoch": 17.19,
"learning_rate": 0.0002,
"loss": 0.0037,
"step": 533
},
{
"epoch": 17.23,
"learning_rate": 0.0002,
"loss": 0.009,
"step": 534
},
{
"epoch": 17.26,
"learning_rate": 0.0002,
"loss": 0.0045,
"step": 535
},
{
"epoch": 17.29,
"learning_rate": 0.0002,
"loss": 0.0066,
"step": 536
},
{
"epoch": 17.32,
"learning_rate": 0.0002,
"loss": 0.0081,
"step": 537
},
{
"epoch": 17.35,
"learning_rate": 0.0002,
"loss": 0.0092,
"step": 538
},
{
"epoch": 17.39,
"learning_rate": 0.0002,
"loss": 0.0037,
"step": 539
},
{
"epoch": 17.42,
"learning_rate": 0.0002,
"loss": 0.0046,
"step": 540
},
{
"epoch": 17.45,
"learning_rate": 0.0002,
"loss": 0.006,
"step": 541
},
{
"epoch": 17.48,
"learning_rate": 0.0002,
"loss": 0.0095,
"step": 542
},
{
"epoch": 17.52,
"learning_rate": 0.0002,
"loss": 0.0033,
"step": 543
},
{
"epoch": 17.55,
"learning_rate": 0.0002,
"loss": 0.0074,
"step": 544
},
{
"epoch": 17.58,
"learning_rate": 0.0002,
"loss": 0.005,
"step": 545
},
{
"epoch": 17.61,
"learning_rate": 0.0002,
"loss": 0.0054,
"step": 546
},
{
"epoch": 17.65,
"learning_rate": 0.0002,
"loss": 0.0064,
"step": 547
},
{
"epoch": 17.68,
"learning_rate": 0.0002,
"loss": 0.0124,
"step": 548
},
{
"epoch": 17.71,
"learning_rate": 0.0002,
"loss": 0.0063,
"step": 549
},
{
"epoch": 17.74,
"learning_rate": 0.0002,
"loss": 0.0102,
"step": 550
},
{
"epoch": 17.77,
"learning_rate": 0.0002,
"loss": 0.0053,
"step": 551
},
{
"epoch": 17.81,
"learning_rate": 0.0002,
"loss": 0.0087,
"step": 552
},
{
"epoch": 17.84,
"learning_rate": 0.0002,
"loss": 0.0066,
"step": 553
},
{
"epoch": 17.87,
"learning_rate": 0.0002,
"loss": 0.0066,
"step": 554
},
{
"epoch": 17.9,
"learning_rate": 0.0002,
"loss": 0.0051,
"step": 555
},
{
"epoch": 17.94,
"learning_rate": 0.0002,
"loss": 0.007,
"step": 556
},
{
"epoch": 17.97,
"learning_rate": 0.0002,
"loss": 0.0089,
"step": 557
},
{
"epoch": 18.0,
"learning_rate": 0.0002,
"loss": 0.0112,
"step": 558
},
{
"epoch": 18.0,
"eval_loss": 0.0062157167121768,
"eval_runtime": 79.5293,
"eval_samples_per_second": 12.209,
"eval_steps_per_second": 0.39,
"step": 558
},
{
"epoch": 18.03,
"learning_rate": 0.0002,
"loss": 0.0099,
"step": 559
},
{
"epoch": 18.06,
"learning_rate": 0.0002,
"loss": 0.0032,
"step": 560
},
{
"epoch": 18.1,
"learning_rate": 0.0002,
"loss": 0.0114,
"step": 561
},
{
"epoch": 18.13,
"learning_rate": 0.0002,
"loss": 0.0087,
"step": 562
},
{
"epoch": 18.16,
"learning_rate": 0.0002,
"loss": 0.0056,
"step": 563
},
{
"epoch": 18.19,
"learning_rate": 0.0002,
"loss": 0.0095,
"step": 564
},
{
"epoch": 18.23,
"learning_rate": 0.0002,
"loss": 0.0047,
"step": 565
},
{
"epoch": 18.26,
"learning_rate": 0.0002,
"loss": 0.0033,
"step": 566
},
{
"epoch": 18.29,
"learning_rate": 0.0002,
"loss": 0.0031,
"step": 567
},
{
"epoch": 18.32,
"learning_rate": 0.0002,
"loss": 0.0065,
"step": 568
},
{
"epoch": 18.35,
"learning_rate": 0.0002,
"loss": 0.0062,
"step": 569
},
{
"epoch": 18.39,
"learning_rate": 0.0002,
"loss": 0.0082,
"step": 570
},
{
"epoch": 18.42,
"learning_rate": 0.0002,
"loss": 0.0059,
"step": 571
},
{
"epoch": 18.45,
"learning_rate": 0.0002,
"loss": 0.009,
"step": 572
},
{
"epoch": 18.48,
"learning_rate": 0.0002,
"loss": 0.0072,
"step": 573
},
{
"epoch": 18.52,
"learning_rate": 0.0002,
"loss": 0.0049,
"step": 574
},
{
"epoch": 18.55,
"learning_rate": 0.0002,
"loss": 0.009,
"step": 575
},
{
"epoch": 18.58,
"learning_rate": 0.0002,
"loss": 0.0115,
"step": 576
},
{
"epoch": 18.61,
"learning_rate": 0.0002,
"loss": 0.0045,
"step": 577
},
{
"epoch": 18.65,
"learning_rate": 0.0002,
"loss": 0.0054,
"step": 578
},
{
"epoch": 18.68,
"learning_rate": 0.0002,
"loss": 0.0108,
"step": 579
},
{
"epoch": 18.71,
"learning_rate": 0.0002,
"loss": 0.0035,
"step": 580
},
{
"epoch": 18.74,
"learning_rate": 0.0002,
"loss": 0.0087,
"step": 581
},
{
"epoch": 18.77,
"learning_rate": 0.0002,
"loss": 0.0101,
"step": 582
},
{
"epoch": 18.81,
"learning_rate": 0.0002,
"loss": 0.0034,
"step": 583
},
{
"epoch": 18.84,
"learning_rate": 0.0002,
"loss": 0.0119,
"step": 584
},
{
"epoch": 18.87,
"learning_rate": 0.0002,
"loss": 0.005,
"step": 585
},
{
"epoch": 18.9,
"learning_rate": 0.0002,
"loss": 0.0045,
"step": 586
},
{
"epoch": 18.94,
"learning_rate": 0.0002,
"loss": 0.0114,
"step": 587
},
{
"epoch": 18.97,
"learning_rate": 0.0002,
"loss": 0.0117,
"step": 588
},
{
"epoch": 19.0,
"learning_rate": 0.0002,
"loss": 0.0075,
"step": 589
},
{
"epoch": 19.0,
"eval_loss": 0.005089292302727699,
"eval_runtime": 79.5895,
"eval_samples_per_second": 12.2,
"eval_steps_per_second": 0.389,
"step": 589
},
{
"epoch": 19.03,
"learning_rate": 0.0002,
"loss": 0.0034,
"step": 590
},
{
"epoch": 19.06,
"learning_rate": 0.0002,
"loss": 0.0027,
"step": 591
},
{
"epoch": 19.1,
"learning_rate": 0.0002,
"loss": 0.0068,
"step": 592
},
{
"epoch": 19.13,
"learning_rate": 0.0002,
"loss": 0.0094,
"step": 593
},
{
"epoch": 19.16,
"learning_rate": 0.0002,
"loss": 0.0023,
"step": 594
},
{
"epoch": 19.19,
"learning_rate": 0.0002,
"loss": 0.004,
"step": 595
},
{
"epoch": 19.23,
"learning_rate": 0.0002,
"loss": 0.0045,
"step": 596
},
{
"epoch": 19.26,
"learning_rate": 0.0002,
"loss": 0.0114,
"step": 597
},
{
"epoch": 19.29,
"learning_rate": 0.0002,
"loss": 0.0119,
"step": 598
},
{
"epoch": 19.32,
"learning_rate": 0.0002,
"loss": 0.003,
"step": 599
},
{
"epoch": 19.35,
"learning_rate": 0.0002,
"loss": 0.0062,
"step": 600
},
{
"epoch": 19.39,
"learning_rate": 0.0002,
"loss": 0.0089,
"step": 601
},
{
"epoch": 19.42,
"learning_rate": 0.0002,
"loss": 0.0075,
"step": 602
},
{
"epoch": 19.45,
"learning_rate": 0.0002,
"loss": 0.0095,
"step": 603
},
{
"epoch": 19.48,
"learning_rate": 0.0002,
"loss": 0.0086,
"step": 604
},
{
"epoch": 19.52,
"learning_rate": 0.0002,
"loss": 0.008,
"step": 605
},
{
"epoch": 19.55,
"learning_rate": 0.0002,
"loss": 0.0051,
"step": 606
},
{
"epoch": 19.58,
"learning_rate": 0.0002,
"loss": 0.0068,
"step": 607
},
{
"epoch": 19.61,
"learning_rate": 0.0002,
"loss": 0.0036,
"step": 608
},
{
"epoch": 19.65,
"learning_rate": 0.0002,
"loss": 0.0079,
"step": 609
},
{
"epoch": 19.68,
"learning_rate": 0.0002,
"loss": 0.0038,
"step": 610
},
{
"epoch": 19.71,
"learning_rate": 0.0002,
"loss": 0.0038,
"step": 611
},
{
"epoch": 19.74,
"learning_rate": 0.0002,
"loss": 0.0062,
"step": 612
},
{
"epoch": 19.77,
"learning_rate": 0.0002,
"loss": 0.0072,
"step": 613
},
{
"epoch": 19.81,
"learning_rate": 0.0002,
"loss": 0.01,
"step": 614
},
{
"epoch": 19.84,
"learning_rate": 0.0002,
"loss": 0.0056,
"step": 615
},
{
"epoch": 19.87,
"learning_rate": 0.0002,
"loss": 0.0063,
"step": 616
},
{
"epoch": 19.9,
"learning_rate": 0.0002,
"loss": 0.0067,
"step": 617
},
{
"epoch": 19.94,
"learning_rate": 0.0002,
"loss": 0.0097,
"step": 618
},
{
"epoch": 19.97,
"learning_rate": 0.0002,
"loss": 0.0061,
"step": 619
},
{
"epoch": 20.0,
"learning_rate": 0.0002,
"loss": 0.0042,
"step": 620
},
{
"epoch": 20.0,
"eval_loss": 0.0034851552918553352,
"eval_runtime": 79.4724,
"eval_samples_per_second": 12.218,
"eval_steps_per_second": 0.39,
"step": 620
},
{
"epoch": 20.0,
"step": 620,
"total_flos": 2.339039814587777e+18,
"train_loss": 0.055754700854548346,
"train_runtime": 10597.5021,
"train_samples_per_second": 1.833,
"train_steps_per_second": 0.059
}
],
"logging_steps": 1.0,
"max_steps": 620,
"num_input_tokens_seen": 0,
"num_train_epochs": 20,
"save_steps": 50000,
"total_flos": 2.339039814587777e+18,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}