emendes3's picture
Model save
3242f49 verified
raw
history blame
61.7 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 20.0,
"eval_steps": 500,
"global_step": 540,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.04,
"learning_rate": 0.0,
"loss": 1.5857,
"step": 1
},
{
"epoch": 0.07,
"learning_rate": 4.8930108423645205e-05,
"loss": 1.1134,
"step": 2
},
{
"epoch": 0.11,
"learning_rate": 7.755238700769803e-05,
"loss": 1.0305,
"step": 3
},
{
"epoch": 0.15,
"learning_rate": 9.786021684729041e-05,
"loss": 1.0862,
"step": 4
},
{
"epoch": 0.19,
"learning_rate": 0.00011361219343474658,
"loss": 1.1588,
"step": 5
},
{
"epoch": 0.22,
"learning_rate": 0.00012648249543134322,
"loss": 0.9897,
"step": 6
},
{
"epoch": 0.26,
"learning_rate": 0.0001373641807199326,
"loss": 1.0786,
"step": 7
},
{
"epoch": 0.3,
"learning_rate": 0.00014679032527093562,
"loss": 0.9976,
"step": 8
},
{
"epoch": 0.33,
"learning_rate": 0.00015510477401539606,
"loss": 0.9506,
"step": 9
},
{
"epoch": 0.37,
"learning_rate": 0.0001625423018583918,
"loss": 0.8853,
"step": 10
},
{
"epoch": 0.41,
"learning_rate": 0.0001692703641841094,
"loss": 0.8753,
"step": 11
},
{
"epoch": 0.44,
"learning_rate": 0.00017541260385498843,
"loss": 0.777,
"step": 12
},
{
"epoch": 0.48,
"learning_rate": 0.00018106291662380673,
"loss": 0.8107,
"step": 13
},
{
"epoch": 0.52,
"learning_rate": 0.0001862942891435778,
"loss": 0.7394,
"step": 14
},
{
"epoch": 0.56,
"learning_rate": 0.0001911645804424446,
"loss": 0.6992,
"step": 15
},
{
"epoch": 0.59,
"learning_rate": 0.00019572043369458082,
"loss": 0.7101,
"step": 16
},
{
"epoch": 0.63,
"learning_rate": 0.0002,
"loss": 0.5249,
"step": 17
},
{
"epoch": 0.67,
"learning_rate": 0.0002,
"loss": 0.5232,
"step": 18
},
{
"epoch": 0.7,
"learning_rate": 0.0002,
"loss": 0.6104,
"step": 19
},
{
"epoch": 0.74,
"learning_rate": 0.0002,
"loss": 0.4919,
"step": 20
},
{
"epoch": 0.78,
"learning_rate": 0.0002,
"loss": 0.3575,
"step": 21
},
{
"epoch": 0.81,
"learning_rate": 0.0002,
"loss": 0.528,
"step": 22
},
{
"epoch": 0.85,
"learning_rate": 0.0002,
"loss": 0.3896,
"step": 23
},
{
"epoch": 0.89,
"learning_rate": 0.0002,
"loss": 0.2822,
"step": 24
},
{
"epoch": 0.93,
"learning_rate": 0.0002,
"loss": 0.3985,
"step": 25
},
{
"epoch": 0.96,
"learning_rate": 0.0002,
"loss": 0.2425,
"step": 26
},
{
"epoch": 1.0,
"learning_rate": 0.0002,
"loss": 0.2679,
"step": 27
},
{
"epoch": 1.0,
"eval_loss": 0.18373605608940125,
"eval_runtime": 47.8216,
"eval_samples_per_second": 8.887,
"eval_steps_per_second": 0.565,
"step": 27
},
{
"epoch": 1.04,
"learning_rate": 0.0002,
"loss": 0.1042,
"step": 28
},
{
"epoch": 1.07,
"learning_rate": 0.0002,
"loss": 0.0874,
"step": 29
},
{
"epoch": 1.11,
"learning_rate": 0.0002,
"loss": 0.1573,
"step": 30
},
{
"epoch": 1.15,
"learning_rate": 0.0002,
"loss": 0.1906,
"step": 31
},
{
"epoch": 1.19,
"learning_rate": 0.0002,
"loss": 0.1532,
"step": 32
},
{
"epoch": 1.22,
"learning_rate": 0.0002,
"loss": 0.1201,
"step": 33
},
{
"epoch": 1.26,
"learning_rate": 0.0002,
"loss": 0.1575,
"step": 34
},
{
"epoch": 1.3,
"learning_rate": 0.0002,
"loss": 0.1519,
"step": 35
},
{
"epoch": 1.33,
"learning_rate": 0.0002,
"loss": 0.0897,
"step": 36
},
{
"epoch": 1.37,
"learning_rate": 0.0002,
"loss": 0.0967,
"step": 37
},
{
"epoch": 1.41,
"learning_rate": 0.0002,
"loss": 0.1094,
"step": 38
},
{
"epoch": 1.44,
"learning_rate": 0.0002,
"loss": 0.1451,
"step": 39
},
{
"epoch": 1.48,
"learning_rate": 0.0002,
"loss": 0.1914,
"step": 40
},
{
"epoch": 1.52,
"learning_rate": 0.0002,
"loss": 0.1286,
"step": 41
},
{
"epoch": 1.56,
"learning_rate": 0.0002,
"loss": 0.07,
"step": 42
},
{
"epoch": 1.59,
"learning_rate": 0.0002,
"loss": 0.1391,
"step": 43
},
{
"epoch": 1.63,
"learning_rate": 0.0002,
"loss": 0.0355,
"step": 44
},
{
"epoch": 1.67,
"learning_rate": 0.0002,
"loss": 0.1301,
"step": 45
},
{
"epoch": 1.7,
"learning_rate": 0.0002,
"loss": 0.0502,
"step": 46
},
{
"epoch": 1.74,
"learning_rate": 0.0002,
"loss": 0.035,
"step": 47
},
{
"epoch": 1.78,
"learning_rate": 0.0002,
"loss": 0.1198,
"step": 48
},
{
"epoch": 1.81,
"learning_rate": 0.0002,
"loss": 0.0349,
"step": 49
},
{
"epoch": 1.85,
"learning_rate": 0.0002,
"loss": 0.0407,
"step": 50
},
{
"epoch": 1.89,
"learning_rate": 0.0002,
"loss": 0.0461,
"step": 51
},
{
"epoch": 1.93,
"learning_rate": 0.0002,
"loss": 0.1048,
"step": 52
},
{
"epoch": 1.96,
"learning_rate": 0.0002,
"loss": 0.0841,
"step": 53
},
{
"epoch": 2.0,
"learning_rate": 0.0002,
"loss": 0.0749,
"step": 54
},
{
"epoch": 2.0,
"eval_loss": 0.03986518457531929,
"eval_runtime": 48.089,
"eval_samples_per_second": 8.838,
"eval_steps_per_second": 0.561,
"step": 54
},
{
"epoch": 2.04,
"learning_rate": 0.0002,
"loss": 0.0225,
"step": 55
},
{
"epoch": 2.07,
"learning_rate": 0.0002,
"loss": 0.0393,
"step": 56
},
{
"epoch": 2.11,
"learning_rate": 0.0002,
"loss": 0.0339,
"step": 57
},
{
"epoch": 2.15,
"learning_rate": 0.0002,
"loss": 0.0242,
"step": 58
},
{
"epoch": 2.19,
"learning_rate": 0.0002,
"loss": 0.0314,
"step": 59
},
{
"epoch": 2.22,
"learning_rate": 0.0002,
"loss": 0.0156,
"step": 60
},
{
"epoch": 2.26,
"learning_rate": 0.0002,
"loss": 0.0283,
"step": 61
},
{
"epoch": 2.3,
"learning_rate": 0.0002,
"loss": 0.0306,
"step": 62
},
{
"epoch": 2.33,
"learning_rate": 0.0002,
"loss": 0.0239,
"step": 63
},
{
"epoch": 2.37,
"learning_rate": 0.0002,
"loss": 0.0325,
"step": 64
},
{
"epoch": 2.41,
"learning_rate": 0.0002,
"loss": 0.0081,
"step": 65
},
{
"epoch": 2.44,
"learning_rate": 0.0002,
"loss": 0.0095,
"step": 66
},
{
"epoch": 2.48,
"learning_rate": 0.0002,
"loss": 0.0253,
"step": 67
},
{
"epoch": 2.52,
"learning_rate": 0.0002,
"loss": 0.0092,
"step": 68
},
{
"epoch": 2.56,
"learning_rate": 0.0002,
"loss": 0.0402,
"step": 69
},
{
"epoch": 2.59,
"learning_rate": 0.0002,
"loss": 0.0278,
"step": 70
},
{
"epoch": 2.63,
"learning_rate": 0.0002,
"loss": 0.0114,
"step": 71
},
{
"epoch": 2.67,
"learning_rate": 0.0002,
"loss": 0.0319,
"step": 72
},
{
"epoch": 2.7,
"learning_rate": 0.0002,
"loss": 0.0101,
"step": 73
},
{
"epoch": 2.74,
"learning_rate": 0.0002,
"loss": 0.0136,
"step": 74
},
{
"epoch": 2.78,
"learning_rate": 0.0002,
"loss": 0.0137,
"step": 75
},
{
"epoch": 2.81,
"learning_rate": 0.0002,
"loss": 0.0259,
"step": 76
},
{
"epoch": 2.85,
"learning_rate": 0.0002,
"loss": 0.0259,
"step": 77
},
{
"epoch": 2.89,
"learning_rate": 0.0002,
"loss": 0.0206,
"step": 78
},
{
"epoch": 2.93,
"learning_rate": 0.0002,
"loss": 0.0069,
"step": 79
},
{
"epoch": 2.96,
"learning_rate": 0.0002,
"loss": 0.0136,
"step": 80
},
{
"epoch": 3.0,
"learning_rate": 0.0002,
"loss": 0.0096,
"step": 81
},
{
"epoch": 3.0,
"eval_loss": 0.010682879947125912,
"eval_runtime": 48.1877,
"eval_samples_per_second": 8.82,
"eval_steps_per_second": 0.56,
"step": 81
},
{
"epoch": 3.04,
"learning_rate": 0.0002,
"loss": 0.0076,
"step": 82
},
{
"epoch": 3.07,
"learning_rate": 0.0002,
"loss": 0.0104,
"step": 83
},
{
"epoch": 3.11,
"learning_rate": 0.0002,
"loss": 0.01,
"step": 84
},
{
"epoch": 3.15,
"learning_rate": 0.0002,
"loss": 0.0059,
"step": 85
},
{
"epoch": 3.19,
"learning_rate": 0.0002,
"loss": 0.0041,
"step": 86
},
{
"epoch": 3.22,
"learning_rate": 0.0002,
"loss": 0.0047,
"step": 87
},
{
"epoch": 3.26,
"learning_rate": 0.0002,
"loss": 0.0056,
"step": 88
},
{
"epoch": 3.3,
"learning_rate": 0.0002,
"loss": 0.0073,
"step": 89
},
{
"epoch": 3.33,
"learning_rate": 0.0002,
"loss": 0.0066,
"step": 90
},
{
"epoch": 3.37,
"learning_rate": 0.0002,
"loss": 0.006,
"step": 91
},
{
"epoch": 3.41,
"learning_rate": 0.0002,
"loss": 0.019,
"step": 92
},
{
"epoch": 3.44,
"learning_rate": 0.0002,
"loss": 0.0134,
"step": 93
},
{
"epoch": 3.48,
"learning_rate": 0.0002,
"loss": 0.0199,
"step": 94
},
{
"epoch": 3.52,
"learning_rate": 0.0002,
"loss": 0.011,
"step": 95
},
{
"epoch": 3.56,
"learning_rate": 0.0002,
"loss": 0.0057,
"step": 96
},
{
"epoch": 3.59,
"learning_rate": 0.0002,
"loss": 0.0106,
"step": 97
},
{
"epoch": 3.63,
"learning_rate": 0.0002,
"loss": 0.0058,
"step": 98
},
{
"epoch": 3.67,
"learning_rate": 0.0002,
"loss": 0.0019,
"step": 99
},
{
"epoch": 3.7,
"learning_rate": 0.0002,
"loss": 0.0075,
"step": 100
},
{
"epoch": 3.74,
"learning_rate": 0.0002,
"loss": 0.0058,
"step": 101
},
{
"epoch": 3.78,
"learning_rate": 0.0002,
"loss": 0.012,
"step": 102
},
{
"epoch": 3.81,
"learning_rate": 0.0002,
"loss": 0.0097,
"step": 103
},
{
"epoch": 3.85,
"learning_rate": 0.0002,
"loss": 0.0105,
"step": 104
},
{
"epoch": 3.89,
"learning_rate": 0.0002,
"loss": 0.01,
"step": 105
},
{
"epoch": 3.93,
"learning_rate": 0.0002,
"loss": 0.0074,
"step": 106
},
{
"epoch": 3.96,
"learning_rate": 0.0002,
"loss": 0.0062,
"step": 107
},
{
"epoch": 4.0,
"learning_rate": 0.0002,
"loss": 0.0114,
"step": 108
},
{
"epoch": 4.0,
"eval_loss": 0.009599113836884499,
"eval_runtime": 48.2015,
"eval_samples_per_second": 8.817,
"eval_steps_per_second": 0.56,
"step": 108
},
{
"epoch": 4.04,
"learning_rate": 0.0002,
"loss": 0.0078,
"step": 109
},
{
"epoch": 4.07,
"learning_rate": 0.0002,
"loss": 0.002,
"step": 110
},
{
"epoch": 4.11,
"learning_rate": 0.0002,
"loss": 0.0094,
"step": 111
},
{
"epoch": 4.15,
"learning_rate": 0.0002,
"loss": 0.0034,
"step": 112
},
{
"epoch": 4.19,
"learning_rate": 0.0002,
"loss": 0.0078,
"step": 113
},
{
"epoch": 4.22,
"learning_rate": 0.0002,
"loss": 0.0153,
"step": 114
},
{
"epoch": 4.26,
"learning_rate": 0.0002,
"loss": 0.0028,
"step": 115
},
{
"epoch": 4.3,
"learning_rate": 0.0002,
"loss": 0.0022,
"step": 116
},
{
"epoch": 4.33,
"learning_rate": 0.0002,
"loss": 0.0029,
"step": 117
},
{
"epoch": 4.37,
"learning_rate": 0.0002,
"loss": 0.0035,
"step": 118
},
{
"epoch": 4.41,
"learning_rate": 0.0002,
"loss": 0.0017,
"step": 119
},
{
"epoch": 4.44,
"learning_rate": 0.0002,
"loss": 0.0009,
"step": 120
},
{
"epoch": 4.48,
"learning_rate": 0.0002,
"loss": 0.0059,
"step": 121
},
{
"epoch": 4.52,
"learning_rate": 0.0002,
"loss": 0.0071,
"step": 122
},
{
"epoch": 4.56,
"learning_rate": 0.0002,
"loss": 0.0027,
"step": 123
},
{
"epoch": 4.59,
"learning_rate": 0.0002,
"loss": 0.0289,
"step": 124
},
{
"epoch": 4.63,
"learning_rate": 0.0002,
"loss": 0.0036,
"step": 125
},
{
"epoch": 4.67,
"learning_rate": 0.0002,
"loss": 0.0021,
"step": 126
},
{
"epoch": 4.7,
"learning_rate": 0.0002,
"loss": 0.0069,
"step": 127
},
{
"epoch": 4.74,
"learning_rate": 0.0002,
"loss": 0.0144,
"step": 128
},
{
"epoch": 4.78,
"learning_rate": 0.0002,
"loss": 0.0026,
"step": 129
},
{
"epoch": 4.81,
"learning_rate": 0.0002,
"loss": 0.011,
"step": 130
},
{
"epoch": 4.85,
"learning_rate": 0.0002,
"loss": 0.0071,
"step": 131
},
{
"epoch": 4.89,
"learning_rate": 0.0002,
"loss": 0.004,
"step": 132
},
{
"epoch": 4.93,
"learning_rate": 0.0002,
"loss": 0.0053,
"step": 133
},
{
"epoch": 4.96,
"learning_rate": 0.0002,
"loss": 0.002,
"step": 134
},
{
"epoch": 5.0,
"learning_rate": 0.0002,
"loss": 0.0059,
"step": 135
},
{
"epoch": 5.0,
"eval_loss": 0.004502412863075733,
"eval_runtime": 48.1685,
"eval_samples_per_second": 8.823,
"eval_steps_per_second": 0.561,
"step": 135
},
{
"epoch": 5.04,
"learning_rate": 0.0002,
"loss": 0.0022,
"step": 136
},
{
"epoch": 5.07,
"learning_rate": 0.0002,
"loss": 0.002,
"step": 137
},
{
"epoch": 5.11,
"learning_rate": 0.0002,
"loss": 0.0024,
"step": 138
},
{
"epoch": 5.15,
"learning_rate": 0.0002,
"loss": 0.008,
"step": 139
},
{
"epoch": 5.19,
"learning_rate": 0.0002,
"loss": 0.0145,
"step": 140
},
{
"epoch": 5.22,
"learning_rate": 0.0002,
"loss": 0.0035,
"step": 141
},
{
"epoch": 5.26,
"learning_rate": 0.0002,
"loss": 0.0047,
"step": 142
},
{
"epoch": 5.3,
"learning_rate": 0.0002,
"loss": 0.0006,
"step": 143
},
{
"epoch": 5.33,
"learning_rate": 0.0002,
"loss": 0.0024,
"step": 144
},
{
"epoch": 5.37,
"learning_rate": 0.0002,
"loss": 0.0026,
"step": 145
},
{
"epoch": 5.41,
"learning_rate": 0.0002,
"loss": 0.0054,
"step": 146
},
{
"epoch": 5.44,
"learning_rate": 0.0002,
"loss": 0.0015,
"step": 147
},
{
"epoch": 5.48,
"learning_rate": 0.0002,
"loss": 0.001,
"step": 148
},
{
"epoch": 5.52,
"learning_rate": 0.0002,
"loss": 0.0033,
"step": 149
},
{
"epoch": 5.56,
"learning_rate": 0.0002,
"loss": 0.003,
"step": 150
},
{
"epoch": 5.59,
"learning_rate": 0.0002,
"loss": 0.002,
"step": 151
},
{
"epoch": 5.63,
"learning_rate": 0.0002,
"loss": 0.0005,
"step": 152
},
{
"epoch": 5.67,
"learning_rate": 0.0002,
"loss": 0.0036,
"step": 153
},
{
"epoch": 5.7,
"learning_rate": 0.0002,
"loss": 0.0053,
"step": 154
},
{
"epoch": 5.74,
"learning_rate": 0.0002,
"loss": 0.0021,
"step": 155
},
{
"epoch": 5.78,
"learning_rate": 0.0002,
"loss": 0.0025,
"step": 156
},
{
"epoch": 5.81,
"learning_rate": 0.0002,
"loss": 0.0026,
"step": 157
},
{
"epoch": 5.85,
"learning_rate": 0.0002,
"loss": 0.0164,
"step": 158
},
{
"epoch": 5.89,
"learning_rate": 0.0002,
"loss": 0.0093,
"step": 159
},
{
"epoch": 5.93,
"learning_rate": 0.0002,
"loss": 0.0061,
"step": 160
},
{
"epoch": 5.96,
"learning_rate": 0.0002,
"loss": 0.0033,
"step": 161
},
{
"epoch": 6.0,
"learning_rate": 0.0002,
"loss": 0.0009,
"step": 162
},
{
"epoch": 6.0,
"eval_loss": 0.003009921871125698,
"eval_runtime": 48.0407,
"eval_samples_per_second": 8.847,
"eval_steps_per_second": 0.562,
"step": 162
},
{
"epoch": 6.04,
"learning_rate": 0.0002,
"loss": 0.0031,
"step": 163
},
{
"epoch": 6.07,
"learning_rate": 0.0002,
"loss": 0.0026,
"step": 164
},
{
"epoch": 6.11,
"learning_rate": 0.0002,
"loss": 0.0035,
"step": 165
},
{
"epoch": 6.15,
"learning_rate": 0.0002,
"loss": 0.0014,
"step": 166
},
{
"epoch": 6.19,
"learning_rate": 0.0002,
"loss": 0.0013,
"step": 167
},
{
"epoch": 6.22,
"learning_rate": 0.0002,
"loss": 0.003,
"step": 168
},
{
"epoch": 6.26,
"learning_rate": 0.0002,
"loss": 0.0008,
"step": 169
},
{
"epoch": 6.3,
"learning_rate": 0.0002,
"loss": 0.0023,
"step": 170
},
{
"epoch": 6.33,
"learning_rate": 0.0002,
"loss": 0.0006,
"step": 171
},
{
"epoch": 6.37,
"learning_rate": 0.0002,
"loss": 0.0035,
"step": 172
},
{
"epoch": 6.41,
"learning_rate": 0.0002,
"loss": 0.005,
"step": 173
},
{
"epoch": 6.44,
"learning_rate": 0.0002,
"loss": 0.0035,
"step": 174
},
{
"epoch": 6.48,
"learning_rate": 0.0002,
"loss": 0.0004,
"step": 175
},
{
"epoch": 6.52,
"learning_rate": 0.0002,
"loss": 0.0076,
"step": 176
},
{
"epoch": 6.56,
"learning_rate": 0.0002,
"loss": 0.0006,
"step": 177
},
{
"epoch": 6.59,
"learning_rate": 0.0002,
"loss": 0.0038,
"step": 178
},
{
"epoch": 6.63,
"learning_rate": 0.0002,
"loss": 0.0012,
"step": 179
},
{
"epoch": 6.67,
"learning_rate": 0.0002,
"loss": 0.0006,
"step": 180
},
{
"epoch": 6.7,
"learning_rate": 0.0002,
"loss": 0.004,
"step": 181
},
{
"epoch": 6.74,
"learning_rate": 0.0002,
"loss": 0.0025,
"step": 182
},
{
"epoch": 6.78,
"learning_rate": 0.0002,
"loss": 0.0014,
"step": 183
},
{
"epoch": 6.81,
"learning_rate": 0.0002,
"loss": 0.0012,
"step": 184
},
{
"epoch": 6.85,
"learning_rate": 0.0002,
"loss": 0.0004,
"step": 185
},
{
"epoch": 6.89,
"learning_rate": 0.0002,
"loss": 0.0013,
"step": 186
},
{
"epoch": 6.93,
"learning_rate": 0.0002,
"loss": 0.0013,
"step": 187
},
{
"epoch": 6.96,
"learning_rate": 0.0002,
"loss": 0.0085,
"step": 188
},
{
"epoch": 7.0,
"learning_rate": 0.0002,
"loss": 0.0033,
"step": 189
},
{
"epoch": 7.0,
"eval_loss": 0.000877623853739351,
"eval_runtime": 48.1303,
"eval_samples_per_second": 8.83,
"eval_steps_per_second": 0.561,
"step": 189
},
{
"epoch": 7.04,
"learning_rate": 0.0002,
"loss": 0.0036,
"step": 190
},
{
"epoch": 7.07,
"learning_rate": 0.0002,
"loss": 0.0005,
"step": 191
},
{
"epoch": 7.11,
"learning_rate": 0.0002,
"loss": 0.0065,
"step": 192
},
{
"epoch": 7.15,
"learning_rate": 0.0002,
"loss": 0.0005,
"step": 193
},
{
"epoch": 7.19,
"learning_rate": 0.0002,
"loss": 0.0013,
"step": 194
},
{
"epoch": 7.22,
"learning_rate": 0.0002,
"loss": 0.0025,
"step": 195
},
{
"epoch": 7.26,
"learning_rate": 0.0002,
"loss": 0.0007,
"step": 196
},
{
"epoch": 7.3,
"learning_rate": 0.0002,
"loss": 0.0021,
"step": 197
},
{
"epoch": 7.33,
"learning_rate": 0.0002,
"loss": 0.0005,
"step": 198
},
{
"epoch": 7.37,
"learning_rate": 0.0002,
"loss": 0.0021,
"step": 199
},
{
"epoch": 7.41,
"learning_rate": 0.0002,
"loss": 0.0004,
"step": 200
},
{
"epoch": 7.44,
"learning_rate": 0.0002,
"loss": 0.0017,
"step": 201
},
{
"epoch": 7.48,
"learning_rate": 0.0002,
"loss": 0.0012,
"step": 202
},
{
"epoch": 7.52,
"learning_rate": 0.0002,
"loss": 0.0048,
"step": 203
},
{
"epoch": 7.56,
"learning_rate": 0.0002,
"loss": 0.0011,
"step": 204
},
{
"epoch": 7.59,
"learning_rate": 0.0002,
"loss": 0.0009,
"step": 205
},
{
"epoch": 7.63,
"learning_rate": 0.0002,
"loss": 0.0018,
"step": 206
},
{
"epoch": 7.67,
"learning_rate": 0.0002,
"loss": 0.0003,
"step": 207
},
{
"epoch": 7.7,
"learning_rate": 0.0002,
"loss": 0.0029,
"step": 208
},
{
"epoch": 7.74,
"learning_rate": 0.0002,
"loss": 0.0036,
"step": 209
},
{
"epoch": 7.78,
"learning_rate": 0.0002,
"loss": 0.0016,
"step": 210
},
{
"epoch": 7.81,
"learning_rate": 0.0002,
"loss": 0.001,
"step": 211
},
{
"epoch": 7.85,
"learning_rate": 0.0002,
"loss": 0.0006,
"step": 212
},
{
"epoch": 7.89,
"learning_rate": 0.0002,
"loss": 0.0094,
"step": 213
},
{
"epoch": 7.93,
"learning_rate": 0.0002,
"loss": 0.0028,
"step": 214
},
{
"epoch": 7.96,
"learning_rate": 0.0002,
"loss": 0.0017,
"step": 215
},
{
"epoch": 8.0,
"learning_rate": 0.0002,
"loss": 0.0041,
"step": 216
},
{
"epoch": 8.0,
"eval_loss": 0.0037567296531051397,
"eval_runtime": 48.0606,
"eval_samples_per_second": 8.843,
"eval_steps_per_second": 0.562,
"step": 216
},
{
"epoch": 8.04,
"learning_rate": 0.0002,
"loss": 0.0006,
"step": 217
},
{
"epoch": 8.07,
"learning_rate": 0.0002,
"loss": 0.0022,
"step": 218
},
{
"epoch": 8.11,
"learning_rate": 0.0002,
"loss": 0.0052,
"step": 219
},
{
"epoch": 8.15,
"learning_rate": 0.0002,
"loss": 0.0064,
"step": 220
},
{
"epoch": 8.19,
"learning_rate": 0.0002,
"loss": 0.0028,
"step": 221
},
{
"epoch": 8.22,
"learning_rate": 0.0002,
"loss": 0.0065,
"step": 222
},
{
"epoch": 8.26,
"learning_rate": 0.0002,
"loss": 0.013,
"step": 223
},
{
"epoch": 8.3,
"learning_rate": 0.0002,
"loss": 0.0018,
"step": 224
},
{
"epoch": 8.33,
"learning_rate": 0.0002,
"loss": 0.0008,
"step": 225
},
{
"epoch": 8.37,
"learning_rate": 0.0002,
"loss": 0.0029,
"step": 226
},
{
"epoch": 8.41,
"learning_rate": 0.0002,
"loss": 0.0036,
"step": 227
},
{
"epoch": 8.44,
"learning_rate": 0.0002,
"loss": 0.0008,
"step": 228
},
{
"epoch": 8.48,
"learning_rate": 0.0002,
"loss": 0.0021,
"step": 229
},
{
"epoch": 8.52,
"learning_rate": 0.0002,
"loss": 0.0013,
"step": 230
},
{
"epoch": 8.56,
"learning_rate": 0.0002,
"loss": 0.0017,
"step": 231
},
{
"epoch": 8.59,
"learning_rate": 0.0002,
"loss": 0.0018,
"step": 232
},
{
"epoch": 8.63,
"learning_rate": 0.0002,
"loss": 0.004,
"step": 233
},
{
"epoch": 8.67,
"learning_rate": 0.0002,
"loss": 0.0011,
"step": 234
},
{
"epoch": 8.7,
"learning_rate": 0.0002,
"loss": 0.0071,
"step": 235
},
{
"epoch": 8.74,
"learning_rate": 0.0002,
"loss": 0.0021,
"step": 236
},
{
"epoch": 8.78,
"learning_rate": 0.0002,
"loss": 0.0011,
"step": 237
},
{
"epoch": 8.81,
"learning_rate": 0.0002,
"loss": 0.003,
"step": 238
},
{
"epoch": 8.85,
"learning_rate": 0.0002,
"loss": 0.0068,
"step": 239
},
{
"epoch": 8.89,
"learning_rate": 0.0002,
"loss": 0.0006,
"step": 240
},
{
"epoch": 8.93,
"learning_rate": 0.0002,
"loss": 0.0121,
"step": 241
},
{
"epoch": 8.96,
"learning_rate": 0.0002,
"loss": 0.0048,
"step": 242
},
{
"epoch": 9.0,
"learning_rate": 0.0002,
"loss": 0.0009,
"step": 243
},
{
"epoch": 9.0,
"eval_loss": 0.0028407848440110683,
"eval_runtime": 48.0769,
"eval_samples_per_second": 8.84,
"eval_steps_per_second": 0.562,
"step": 243
},
{
"epoch": 9.04,
"learning_rate": 0.0002,
"loss": 0.009,
"step": 244
},
{
"epoch": 9.07,
"learning_rate": 0.0002,
"loss": 0.0003,
"step": 245
},
{
"epoch": 9.11,
"learning_rate": 0.0002,
"loss": 0.0006,
"step": 246
},
{
"epoch": 9.15,
"learning_rate": 0.0002,
"loss": 0.001,
"step": 247
},
{
"epoch": 9.19,
"learning_rate": 0.0002,
"loss": 0.0031,
"step": 248
},
{
"epoch": 9.22,
"learning_rate": 0.0002,
"loss": 0.0043,
"step": 249
},
{
"epoch": 9.26,
"learning_rate": 0.0002,
"loss": 0.0012,
"step": 250
},
{
"epoch": 9.3,
"learning_rate": 0.0002,
"loss": 0.0031,
"step": 251
},
{
"epoch": 9.33,
"learning_rate": 0.0002,
"loss": 0.0026,
"step": 252
},
{
"epoch": 9.37,
"learning_rate": 0.0002,
"loss": 0.0014,
"step": 253
},
{
"epoch": 9.41,
"learning_rate": 0.0002,
"loss": 0.0063,
"step": 254
},
{
"epoch": 9.44,
"learning_rate": 0.0002,
"loss": 0.0022,
"step": 255
},
{
"epoch": 9.48,
"learning_rate": 0.0002,
"loss": 0.0012,
"step": 256
},
{
"epoch": 9.52,
"learning_rate": 0.0002,
"loss": 0.0028,
"step": 257
},
{
"epoch": 9.56,
"learning_rate": 0.0002,
"loss": 0.0049,
"step": 258
},
{
"epoch": 9.59,
"learning_rate": 0.0002,
"loss": 0.0048,
"step": 259
},
{
"epoch": 9.63,
"learning_rate": 0.0002,
"loss": 0.0035,
"step": 260
},
{
"epoch": 9.67,
"learning_rate": 0.0002,
"loss": 0.004,
"step": 261
},
{
"epoch": 9.7,
"learning_rate": 0.0002,
"loss": 0.0013,
"step": 262
},
{
"epoch": 9.74,
"learning_rate": 0.0002,
"loss": 0.0034,
"step": 263
},
{
"epoch": 9.78,
"learning_rate": 0.0002,
"loss": 0.0012,
"step": 264
},
{
"epoch": 9.81,
"learning_rate": 0.0002,
"loss": 0.0017,
"step": 265
},
{
"epoch": 9.85,
"learning_rate": 0.0002,
"loss": 0.005,
"step": 266
},
{
"epoch": 9.89,
"learning_rate": 0.0002,
"loss": 0.0073,
"step": 267
},
{
"epoch": 9.93,
"learning_rate": 0.0002,
"loss": 0.001,
"step": 268
},
{
"epoch": 9.96,
"learning_rate": 0.0002,
"loss": 0.003,
"step": 269
},
{
"epoch": 10.0,
"learning_rate": 0.0002,
"loss": 0.0029,
"step": 270
},
{
"epoch": 10.0,
"eval_loss": 0.0032664372120052576,
"eval_runtime": 48.0025,
"eval_samples_per_second": 8.854,
"eval_steps_per_second": 0.562,
"step": 270
},
{
"epoch": 10.04,
"learning_rate": 0.0002,
"loss": 0.0027,
"step": 271
},
{
"epoch": 10.07,
"learning_rate": 0.0002,
"loss": 0.0127,
"step": 272
},
{
"epoch": 10.11,
"learning_rate": 0.0002,
"loss": 0.0013,
"step": 273
},
{
"epoch": 10.15,
"learning_rate": 0.0002,
"loss": 0.0015,
"step": 274
},
{
"epoch": 10.19,
"learning_rate": 0.0002,
"loss": 0.0071,
"step": 275
},
{
"epoch": 10.22,
"learning_rate": 0.0002,
"loss": 0.0007,
"step": 276
},
{
"epoch": 10.26,
"learning_rate": 0.0002,
"loss": 0.0093,
"step": 277
},
{
"epoch": 10.3,
"learning_rate": 0.0002,
"loss": 0.0025,
"step": 278
},
{
"epoch": 10.33,
"learning_rate": 0.0002,
"loss": 0.0008,
"step": 279
},
{
"epoch": 10.37,
"learning_rate": 0.0002,
"loss": 0.0016,
"step": 280
},
{
"epoch": 10.41,
"learning_rate": 0.0002,
"loss": 0.0023,
"step": 281
},
{
"epoch": 10.44,
"learning_rate": 0.0002,
"loss": 0.0014,
"step": 282
},
{
"epoch": 10.48,
"learning_rate": 0.0002,
"loss": 0.0017,
"step": 283
},
{
"epoch": 10.52,
"learning_rate": 0.0002,
"loss": 0.0004,
"step": 284
},
{
"epoch": 10.56,
"learning_rate": 0.0002,
"loss": 0.0005,
"step": 285
},
{
"epoch": 10.59,
"learning_rate": 0.0002,
"loss": 0.0014,
"step": 286
},
{
"epoch": 10.63,
"learning_rate": 0.0002,
"loss": 0.0051,
"step": 287
},
{
"epoch": 10.67,
"learning_rate": 0.0002,
"loss": 0.0059,
"step": 288
},
{
"epoch": 10.7,
"learning_rate": 0.0002,
"loss": 0.0015,
"step": 289
},
{
"epoch": 10.74,
"learning_rate": 0.0002,
"loss": 0.0038,
"step": 290
},
{
"epoch": 10.78,
"learning_rate": 0.0002,
"loss": 0.0019,
"step": 291
},
{
"epoch": 10.81,
"learning_rate": 0.0002,
"loss": 0.0083,
"step": 292
},
{
"epoch": 10.85,
"learning_rate": 0.0002,
"loss": 0.0003,
"step": 293
},
{
"epoch": 10.89,
"learning_rate": 0.0002,
"loss": 0.0019,
"step": 294
},
{
"epoch": 10.93,
"learning_rate": 0.0002,
"loss": 0.0049,
"step": 295
},
{
"epoch": 10.96,
"learning_rate": 0.0002,
"loss": 0.0032,
"step": 296
},
{
"epoch": 11.0,
"learning_rate": 0.0002,
"loss": 0.0023,
"step": 297
},
{
"epoch": 11.0,
"eval_loss": 0.00336476624943316,
"eval_runtime": 48.2832,
"eval_samples_per_second": 8.802,
"eval_steps_per_second": 0.559,
"step": 297
},
{
"epoch": 11.04,
"learning_rate": 0.0002,
"loss": 0.0066,
"step": 298
},
{
"epoch": 11.07,
"learning_rate": 0.0002,
"loss": 0.0021,
"step": 299
},
{
"epoch": 11.11,
"learning_rate": 0.0002,
"loss": 0.0023,
"step": 300
},
{
"epoch": 11.15,
"learning_rate": 0.0002,
"loss": 0.0044,
"step": 301
},
{
"epoch": 11.19,
"learning_rate": 0.0002,
"loss": 0.0014,
"step": 302
},
{
"epoch": 11.22,
"learning_rate": 0.0002,
"loss": 0.0059,
"step": 303
},
{
"epoch": 11.26,
"learning_rate": 0.0002,
"loss": 0.0015,
"step": 304
},
{
"epoch": 11.3,
"learning_rate": 0.0002,
"loss": 0.0018,
"step": 305
},
{
"epoch": 11.33,
"learning_rate": 0.0002,
"loss": 0.0017,
"step": 306
},
{
"epoch": 11.37,
"learning_rate": 0.0002,
"loss": 0.0004,
"step": 307
},
{
"epoch": 11.41,
"learning_rate": 0.0002,
"loss": 0.0021,
"step": 308
},
{
"epoch": 11.44,
"learning_rate": 0.0002,
"loss": 0.0031,
"step": 309
},
{
"epoch": 11.48,
"learning_rate": 0.0002,
"loss": 0.0018,
"step": 310
},
{
"epoch": 11.52,
"learning_rate": 0.0002,
"loss": 0.0029,
"step": 311
},
{
"epoch": 11.56,
"learning_rate": 0.0002,
"loss": 0.0046,
"step": 312
},
{
"epoch": 11.59,
"learning_rate": 0.0002,
"loss": 0.0005,
"step": 313
},
{
"epoch": 11.63,
"learning_rate": 0.0002,
"loss": 0.0089,
"step": 314
},
{
"epoch": 11.67,
"learning_rate": 0.0002,
"loss": 0.0032,
"step": 315
},
{
"epoch": 11.7,
"learning_rate": 0.0002,
"loss": 0.002,
"step": 316
},
{
"epoch": 11.74,
"learning_rate": 0.0002,
"loss": 0.0011,
"step": 317
},
{
"epoch": 11.78,
"learning_rate": 0.0002,
"loss": 0.005,
"step": 318
},
{
"epoch": 11.81,
"learning_rate": 0.0002,
"loss": 0.0036,
"step": 319
},
{
"epoch": 11.85,
"learning_rate": 0.0002,
"loss": 0.0038,
"step": 320
},
{
"epoch": 11.89,
"learning_rate": 0.0002,
"loss": 0.0031,
"step": 321
},
{
"epoch": 11.93,
"learning_rate": 0.0002,
"loss": 0.0034,
"step": 322
},
{
"epoch": 11.96,
"learning_rate": 0.0002,
"loss": 0.0013,
"step": 323
},
{
"epoch": 12.0,
"learning_rate": 0.0002,
"loss": 0.007,
"step": 324
},
{
"epoch": 12.0,
"eval_loss": 0.004381947685033083,
"eval_runtime": 48.0671,
"eval_samples_per_second": 8.842,
"eval_steps_per_second": 0.562,
"step": 324
},
{
"epoch": 12.04,
"learning_rate": 0.0002,
"loss": 0.0043,
"step": 325
},
{
"epoch": 12.07,
"learning_rate": 0.0002,
"loss": 0.0055,
"step": 326
},
{
"epoch": 12.11,
"learning_rate": 0.0002,
"loss": 0.0005,
"step": 327
},
{
"epoch": 12.15,
"learning_rate": 0.0002,
"loss": 0.0036,
"step": 328
},
{
"epoch": 12.19,
"learning_rate": 0.0002,
"loss": 0.0066,
"step": 329
},
{
"epoch": 12.22,
"learning_rate": 0.0002,
"loss": 0.0162,
"step": 330
},
{
"epoch": 12.26,
"learning_rate": 0.0002,
"loss": 0.0033,
"step": 331
},
{
"epoch": 12.3,
"learning_rate": 0.0002,
"loss": 0.002,
"step": 332
},
{
"epoch": 12.33,
"learning_rate": 0.0002,
"loss": 0.0033,
"step": 333
},
{
"epoch": 12.37,
"learning_rate": 0.0002,
"loss": 0.0033,
"step": 334
},
{
"epoch": 12.41,
"learning_rate": 0.0002,
"loss": 0.0032,
"step": 335
},
{
"epoch": 12.44,
"learning_rate": 0.0002,
"loss": 0.0065,
"step": 336
},
{
"epoch": 12.48,
"learning_rate": 0.0002,
"loss": 0.0013,
"step": 337
},
{
"epoch": 12.52,
"learning_rate": 0.0002,
"loss": 0.0015,
"step": 338
},
{
"epoch": 12.56,
"learning_rate": 0.0002,
"loss": 0.0016,
"step": 339
},
{
"epoch": 12.59,
"learning_rate": 0.0002,
"loss": 0.0042,
"step": 340
},
{
"epoch": 12.63,
"learning_rate": 0.0002,
"loss": 0.0148,
"step": 341
},
{
"epoch": 12.67,
"learning_rate": 0.0002,
"loss": 0.0058,
"step": 342
},
{
"epoch": 12.7,
"learning_rate": 0.0002,
"loss": 0.0017,
"step": 343
},
{
"epoch": 12.74,
"learning_rate": 0.0002,
"loss": 0.004,
"step": 344
},
{
"epoch": 12.78,
"learning_rate": 0.0002,
"loss": 0.0055,
"step": 345
},
{
"epoch": 12.81,
"learning_rate": 0.0002,
"loss": 0.0019,
"step": 346
},
{
"epoch": 12.85,
"learning_rate": 0.0002,
"loss": 0.0033,
"step": 347
},
{
"epoch": 12.89,
"learning_rate": 0.0002,
"loss": 0.0127,
"step": 348
},
{
"epoch": 12.93,
"learning_rate": 0.0002,
"loss": 0.0103,
"step": 349
},
{
"epoch": 12.96,
"learning_rate": 0.0002,
"loss": 0.0027,
"step": 350
},
{
"epoch": 13.0,
"learning_rate": 0.0002,
"loss": 0.0111,
"step": 351
},
{
"epoch": 13.0,
"eval_loss": 0.007907378487288952,
"eval_runtime": 48.1829,
"eval_samples_per_second": 8.821,
"eval_steps_per_second": 0.56,
"step": 351
},
{
"epoch": 13.04,
"learning_rate": 0.0002,
"loss": 0.0073,
"step": 352
},
{
"epoch": 13.07,
"learning_rate": 0.0002,
"loss": 0.0106,
"step": 353
},
{
"epoch": 13.11,
"learning_rate": 0.0002,
"loss": 0.004,
"step": 354
},
{
"epoch": 13.15,
"learning_rate": 0.0002,
"loss": 0.0064,
"step": 355
},
{
"epoch": 13.19,
"learning_rate": 0.0002,
"loss": 0.0138,
"step": 356
},
{
"epoch": 13.22,
"learning_rate": 0.0002,
"loss": 0.0133,
"step": 357
},
{
"epoch": 13.26,
"learning_rate": 0.0002,
"loss": 0.0236,
"step": 358
},
{
"epoch": 13.3,
"learning_rate": 0.0002,
"loss": 0.0108,
"step": 359
},
{
"epoch": 13.33,
"learning_rate": 0.0002,
"loss": 0.0093,
"step": 360
},
{
"epoch": 13.37,
"learning_rate": 0.0002,
"loss": 0.0107,
"step": 361
},
{
"epoch": 13.41,
"learning_rate": 0.0002,
"loss": 0.0034,
"step": 362
},
{
"epoch": 13.44,
"learning_rate": 0.0002,
"loss": 0.0143,
"step": 363
},
{
"epoch": 13.48,
"learning_rate": 0.0002,
"loss": 0.0034,
"step": 364
},
{
"epoch": 13.52,
"learning_rate": 0.0002,
"loss": 0.0051,
"step": 365
},
{
"epoch": 13.56,
"learning_rate": 0.0002,
"loss": 0.0124,
"step": 366
},
{
"epoch": 13.59,
"learning_rate": 0.0002,
"loss": 0.0075,
"step": 367
},
{
"epoch": 13.63,
"learning_rate": 0.0002,
"loss": 0.0063,
"step": 368
},
{
"epoch": 13.67,
"learning_rate": 0.0002,
"loss": 0.0051,
"step": 369
},
{
"epoch": 13.7,
"learning_rate": 0.0002,
"loss": 0.0111,
"step": 370
},
{
"epoch": 13.74,
"learning_rate": 0.0002,
"loss": 0.0107,
"step": 371
},
{
"epoch": 13.78,
"learning_rate": 0.0002,
"loss": 0.0058,
"step": 372
},
{
"epoch": 13.81,
"learning_rate": 0.0002,
"loss": 0.0079,
"step": 373
},
{
"epoch": 13.85,
"learning_rate": 0.0002,
"loss": 0.0115,
"step": 374
},
{
"epoch": 13.89,
"learning_rate": 0.0002,
"loss": 0.0068,
"step": 375
},
{
"epoch": 13.93,
"learning_rate": 0.0002,
"loss": 0.0094,
"step": 376
},
{
"epoch": 13.96,
"learning_rate": 0.0002,
"loss": 0.0044,
"step": 377
},
{
"epoch": 14.0,
"learning_rate": 0.0002,
"loss": 0.0097,
"step": 378
},
{
"epoch": 14.0,
"eval_loss": 0.00604825746268034,
"eval_runtime": 48.0832,
"eval_samples_per_second": 8.839,
"eval_steps_per_second": 0.562,
"step": 378
},
{
"epoch": 14.04,
"learning_rate": 0.0002,
"loss": 0.0084,
"step": 379
},
{
"epoch": 14.07,
"learning_rate": 0.0002,
"loss": 0.0086,
"step": 380
},
{
"epoch": 14.11,
"learning_rate": 0.0002,
"loss": 0.0022,
"step": 381
},
{
"epoch": 14.15,
"learning_rate": 0.0002,
"loss": 0.0038,
"step": 382
},
{
"epoch": 14.19,
"learning_rate": 0.0002,
"loss": 0.0059,
"step": 383
},
{
"epoch": 14.22,
"learning_rate": 0.0002,
"loss": 0.0139,
"step": 384
},
{
"epoch": 14.26,
"learning_rate": 0.0002,
"loss": 0.0058,
"step": 385
},
{
"epoch": 14.3,
"learning_rate": 0.0002,
"loss": 0.0084,
"step": 386
},
{
"epoch": 14.33,
"learning_rate": 0.0002,
"loss": 0.0062,
"step": 387
},
{
"epoch": 14.37,
"learning_rate": 0.0002,
"loss": 0.008,
"step": 388
},
{
"epoch": 14.41,
"learning_rate": 0.0002,
"loss": 0.0038,
"step": 389
},
{
"epoch": 14.44,
"learning_rate": 0.0002,
"loss": 0.0096,
"step": 390
},
{
"epoch": 14.48,
"learning_rate": 0.0002,
"loss": 0.0063,
"step": 391
},
{
"epoch": 14.52,
"learning_rate": 0.0002,
"loss": 0.0031,
"step": 392
},
{
"epoch": 14.56,
"learning_rate": 0.0002,
"loss": 0.0036,
"step": 393
},
{
"epoch": 14.59,
"learning_rate": 0.0002,
"loss": 0.0041,
"step": 394
},
{
"epoch": 14.63,
"learning_rate": 0.0002,
"loss": 0.0063,
"step": 395
},
{
"epoch": 14.67,
"learning_rate": 0.0002,
"loss": 0.016,
"step": 396
},
{
"epoch": 14.7,
"learning_rate": 0.0002,
"loss": 0.0018,
"step": 397
},
{
"epoch": 14.74,
"learning_rate": 0.0002,
"loss": 0.0176,
"step": 398
},
{
"epoch": 14.78,
"learning_rate": 0.0002,
"loss": 0.0144,
"step": 399
},
{
"epoch": 14.81,
"learning_rate": 0.0002,
"loss": 0.0118,
"step": 400
},
{
"epoch": 14.85,
"learning_rate": 0.0002,
"loss": 0.0163,
"step": 401
},
{
"epoch": 14.89,
"learning_rate": 0.0002,
"loss": 0.0111,
"step": 402
},
{
"epoch": 14.93,
"learning_rate": 0.0002,
"loss": 0.008,
"step": 403
},
{
"epoch": 14.96,
"learning_rate": 0.0002,
"loss": 0.0204,
"step": 404
},
{
"epoch": 15.0,
"learning_rate": 0.0002,
"loss": 0.0332,
"step": 405
},
{
"epoch": 15.0,
"eval_loss": 0.011913908645510674,
"eval_runtime": 48.0366,
"eval_samples_per_second": 8.847,
"eval_steps_per_second": 0.562,
"step": 405
},
{
"epoch": 15.04,
"learning_rate": 0.0002,
"loss": 0.007,
"step": 406
},
{
"epoch": 15.07,
"learning_rate": 0.0002,
"loss": 0.0103,
"step": 407
},
{
"epoch": 15.11,
"learning_rate": 0.0002,
"loss": 0.0086,
"step": 408
},
{
"epoch": 15.15,
"learning_rate": 0.0002,
"loss": 0.0121,
"step": 409
},
{
"epoch": 15.19,
"learning_rate": 0.0002,
"loss": 0.0143,
"step": 410
},
{
"epoch": 15.22,
"learning_rate": 0.0002,
"loss": 0.0104,
"step": 411
},
{
"epoch": 15.26,
"learning_rate": 0.0002,
"loss": 0.0118,
"step": 412
},
{
"epoch": 15.3,
"learning_rate": 0.0002,
"loss": 0.0096,
"step": 413
},
{
"epoch": 15.33,
"learning_rate": 0.0002,
"loss": 0.0113,
"step": 414
},
{
"epoch": 15.37,
"learning_rate": 0.0002,
"loss": 0.0095,
"step": 415
},
{
"epoch": 15.41,
"learning_rate": 0.0002,
"loss": 0.0105,
"step": 416
},
{
"epoch": 15.44,
"learning_rate": 0.0002,
"loss": 0.0151,
"step": 417
},
{
"epoch": 15.48,
"learning_rate": 0.0002,
"loss": 0.0112,
"step": 418
},
{
"epoch": 15.52,
"learning_rate": 0.0002,
"loss": 0.0113,
"step": 419
},
{
"epoch": 15.56,
"learning_rate": 0.0002,
"loss": 0.0201,
"step": 420
},
{
"epoch": 15.59,
"learning_rate": 0.0002,
"loss": 0.0101,
"step": 421
},
{
"epoch": 15.63,
"learning_rate": 0.0002,
"loss": 0.0116,
"step": 422
},
{
"epoch": 15.67,
"learning_rate": 0.0002,
"loss": 0.0231,
"step": 423
},
{
"epoch": 15.7,
"learning_rate": 0.0002,
"loss": 0.0138,
"step": 424
},
{
"epoch": 15.74,
"learning_rate": 0.0002,
"loss": 0.0043,
"step": 425
},
{
"epoch": 15.78,
"learning_rate": 0.0002,
"loss": 0.0105,
"step": 426
},
{
"epoch": 15.81,
"learning_rate": 0.0002,
"loss": 0.0082,
"step": 427
},
{
"epoch": 15.85,
"learning_rate": 0.0002,
"loss": 0.0105,
"step": 428
},
{
"epoch": 15.89,
"learning_rate": 0.0002,
"loss": 0.0218,
"step": 429
},
{
"epoch": 15.93,
"learning_rate": 0.0002,
"loss": 0.012,
"step": 430
},
{
"epoch": 15.96,
"learning_rate": 0.0002,
"loss": 0.0068,
"step": 431
},
{
"epoch": 16.0,
"learning_rate": 0.0002,
"loss": 0.012,
"step": 432
},
{
"epoch": 16.0,
"eval_loss": 0.0072858938947319984,
"eval_runtime": 48.0428,
"eval_samples_per_second": 8.846,
"eval_steps_per_second": 0.562,
"step": 432
},
{
"epoch": 16.04,
"learning_rate": 0.0002,
"loss": 0.0098,
"step": 433
},
{
"epoch": 16.07,
"learning_rate": 0.0002,
"loss": 0.0053,
"step": 434
},
{
"epoch": 16.11,
"learning_rate": 0.0002,
"loss": 0.008,
"step": 435
},
{
"epoch": 16.15,
"learning_rate": 0.0002,
"loss": 0.0056,
"step": 436
},
{
"epoch": 16.19,
"learning_rate": 0.0002,
"loss": 0.0229,
"step": 437
},
{
"epoch": 16.22,
"learning_rate": 0.0002,
"loss": 0.0036,
"step": 438
},
{
"epoch": 16.26,
"learning_rate": 0.0002,
"loss": 0.003,
"step": 439
},
{
"epoch": 16.3,
"learning_rate": 0.0002,
"loss": 0.0169,
"step": 440
},
{
"epoch": 16.33,
"learning_rate": 0.0002,
"loss": 0.0024,
"step": 441
},
{
"epoch": 16.37,
"learning_rate": 0.0002,
"loss": 0.0045,
"step": 442
},
{
"epoch": 16.41,
"learning_rate": 0.0002,
"loss": 0.0176,
"step": 443
},
{
"epoch": 16.44,
"learning_rate": 0.0002,
"loss": 0.0053,
"step": 444
},
{
"epoch": 16.48,
"learning_rate": 0.0002,
"loss": 0.0116,
"step": 445
},
{
"epoch": 16.52,
"learning_rate": 0.0002,
"loss": 0.0094,
"step": 446
},
{
"epoch": 16.56,
"learning_rate": 0.0002,
"loss": 0.0186,
"step": 447
},
{
"epoch": 16.59,
"learning_rate": 0.0002,
"loss": 0.0092,
"step": 448
},
{
"epoch": 16.63,
"learning_rate": 0.0002,
"loss": 0.0125,
"step": 449
},
{
"epoch": 16.67,
"learning_rate": 0.0002,
"loss": 0.0075,
"step": 450
},
{
"epoch": 16.7,
"learning_rate": 0.0002,
"loss": 0.0034,
"step": 451
},
{
"epoch": 16.74,
"learning_rate": 0.0002,
"loss": 0.0084,
"step": 452
},
{
"epoch": 16.78,
"learning_rate": 0.0002,
"loss": 0.0122,
"step": 453
},
{
"epoch": 16.81,
"learning_rate": 0.0002,
"loss": 0.0076,
"step": 454
},
{
"epoch": 16.85,
"learning_rate": 0.0002,
"loss": 0.0163,
"step": 455
},
{
"epoch": 16.89,
"learning_rate": 0.0002,
"loss": 0.0155,
"step": 456
},
{
"epoch": 16.93,
"learning_rate": 0.0002,
"loss": 0.0016,
"step": 457
},
{
"epoch": 16.96,
"learning_rate": 0.0002,
"loss": 0.0163,
"step": 458
},
{
"epoch": 17.0,
"learning_rate": 0.0002,
"loss": 0.003,
"step": 459
},
{
"epoch": 17.0,
"eval_loss": 0.006067308597266674,
"eval_runtime": 48.1545,
"eval_samples_per_second": 8.826,
"eval_steps_per_second": 0.561,
"step": 459
},
{
"epoch": 17.04,
"learning_rate": 0.0002,
"loss": 0.0013,
"step": 460
},
{
"epoch": 17.07,
"learning_rate": 0.0002,
"loss": 0.022,
"step": 461
},
{
"epoch": 17.11,
"learning_rate": 0.0002,
"loss": 0.0101,
"step": 462
},
{
"epoch": 17.15,
"learning_rate": 0.0002,
"loss": 0.0052,
"step": 463
},
{
"epoch": 17.19,
"learning_rate": 0.0002,
"loss": 0.0367,
"step": 464
},
{
"epoch": 17.22,
"learning_rate": 0.0002,
"loss": 0.0092,
"step": 465
},
{
"epoch": 17.26,
"learning_rate": 0.0002,
"loss": 0.0082,
"step": 466
},
{
"epoch": 17.3,
"learning_rate": 0.0002,
"loss": 0.0037,
"step": 467
},
{
"epoch": 17.33,
"learning_rate": 0.0002,
"loss": 0.0074,
"step": 468
},
{
"epoch": 17.37,
"learning_rate": 0.0002,
"loss": 0.0056,
"step": 469
},
{
"epoch": 17.41,
"learning_rate": 0.0002,
"loss": 0.0054,
"step": 470
},
{
"epoch": 17.44,
"learning_rate": 0.0002,
"loss": 0.0042,
"step": 471
},
{
"epoch": 17.48,
"learning_rate": 0.0002,
"loss": 0.0181,
"step": 472
},
{
"epoch": 17.52,
"learning_rate": 0.0002,
"loss": 0.0065,
"step": 473
},
{
"epoch": 17.56,
"learning_rate": 0.0002,
"loss": 0.0094,
"step": 474
},
{
"epoch": 17.59,
"learning_rate": 0.0002,
"loss": 0.0057,
"step": 475
},
{
"epoch": 17.63,
"learning_rate": 0.0002,
"loss": 0.0055,
"step": 476
},
{
"epoch": 17.67,
"learning_rate": 0.0002,
"loss": 0.008,
"step": 477
},
{
"epoch": 17.7,
"learning_rate": 0.0002,
"loss": 0.0123,
"step": 478
},
{
"epoch": 17.74,
"learning_rate": 0.0002,
"loss": 0.0068,
"step": 479
},
{
"epoch": 17.78,
"learning_rate": 0.0002,
"loss": 0.019,
"step": 480
},
{
"epoch": 17.81,
"learning_rate": 0.0002,
"loss": 0.0143,
"step": 481
},
{
"epoch": 17.85,
"learning_rate": 0.0002,
"loss": 0.0227,
"step": 482
},
{
"epoch": 17.89,
"learning_rate": 0.0002,
"loss": 0.0141,
"step": 483
},
{
"epoch": 17.93,
"learning_rate": 0.0002,
"loss": 0.0121,
"step": 484
},
{
"epoch": 17.96,
"learning_rate": 0.0002,
"loss": 0.0151,
"step": 485
},
{
"epoch": 18.0,
"learning_rate": 0.0002,
"loss": 0.0045,
"step": 486
},
{
"epoch": 18.0,
"eval_loss": 0.01013600081205368,
"eval_runtime": 48.1592,
"eval_samples_per_second": 8.825,
"eval_steps_per_second": 0.561,
"step": 486
},
{
"epoch": 18.04,
"learning_rate": 0.0002,
"loss": 0.0084,
"step": 487
},
{
"epoch": 18.07,
"learning_rate": 0.0002,
"loss": 0.0107,
"step": 488
},
{
"epoch": 18.11,
"learning_rate": 0.0002,
"loss": 0.0296,
"step": 489
},
{
"epoch": 18.15,
"learning_rate": 0.0002,
"loss": 0.0038,
"step": 490
},
{
"epoch": 18.19,
"learning_rate": 0.0002,
"loss": 0.0111,
"step": 491
},
{
"epoch": 18.22,
"learning_rate": 0.0002,
"loss": 0.0092,
"step": 492
},
{
"epoch": 18.26,
"learning_rate": 0.0002,
"loss": 0.0053,
"step": 493
},
{
"epoch": 18.3,
"learning_rate": 0.0002,
"loss": 0.0082,
"step": 494
},
{
"epoch": 18.33,
"learning_rate": 0.0002,
"loss": 0.0134,
"step": 495
},
{
"epoch": 18.37,
"learning_rate": 0.0002,
"loss": 0.0056,
"step": 496
},
{
"epoch": 18.41,
"learning_rate": 0.0002,
"loss": 0.0213,
"step": 497
},
{
"epoch": 18.44,
"learning_rate": 0.0002,
"loss": 0.0091,
"step": 498
},
{
"epoch": 18.48,
"learning_rate": 0.0002,
"loss": 0.0046,
"step": 499
},
{
"epoch": 18.52,
"learning_rate": 0.0002,
"loss": 0.0186,
"step": 500
},
{
"epoch": 18.56,
"learning_rate": 0.0002,
"loss": 0.0156,
"step": 501
},
{
"epoch": 18.59,
"learning_rate": 0.0002,
"loss": 0.0115,
"step": 502
},
{
"epoch": 18.63,
"learning_rate": 0.0002,
"loss": 0.0091,
"step": 503
},
{
"epoch": 18.67,
"learning_rate": 0.0002,
"loss": 0.0088,
"step": 504
},
{
"epoch": 18.7,
"learning_rate": 0.0002,
"loss": 0.0056,
"step": 505
},
{
"epoch": 18.74,
"learning_rate": 0.0002,
"loss": 0.0171,
"step": 506
},
{
"epoch": 18.78,
"learning_rate": 0.0002,
"loss": 0.0069,
"step": 507
},
{
"epoch": 18.81,
"learning_rate": 0.0002,
"loss": 0.0172,
"step": 508
},
{
"epoch": 18.85,
"learning_rate": 0.0002,
"loss": 0.0061,
"step": 509
},
{
"epoch": 18.89,
"learning_rate": 0.0002,
"loss": 0.0067,
"step": 510
},
{
"epoch": 18.93,
"learning_rate": 0.0002,
"loss": 0.0192,
"step": 511
},
{
"epoch": 18.96,
"learning_rate": 0.0002,
"loss": 0.0118,
"step": 512
},
{
"epoch": 19.0,
"learning_rate": 0.0002,
"loss": 0.0092,
"step": 513
},
{
"epoch": 19.0,
"eval_loss": 0.00668308325111866,
"eval_runtime": 48.0025,
"eval_samples_per_second": 8.854,
"eval_steps_per_second": 0.562,
"step": 513
},
{
"epoch": 19.04,
"learning_rate": 0.0002,
"loss": 0.0055,
"step": 514
},
{
"epoch": 19.07,
"learning_rate": 0.0002,
"loss": 0.006,
"step": 515
},
{
"epoch": 19.11,
"learning_rate": 0.0002,
"loss": 0.004,
"step": 516
},
{
"epoch": 19.15,
"learning_rate": 0.0002,
"loss": 0.0068,
"step": 517
},
{
"epoch": 19.19,
"learning_rate": 0.0002,
"loss": 0.0036,
"step": 518
},
{
"epoch": 19.22,
"learning_rate": 0.0002,
"loss": 0.0119,
"step": 519
},
{
"epoch": 19.26,
"learning_rate": 0.0002,
"loss": 0.0084,
"step": 520
},
{
"epoch": 19.3,
"learning_rate": 0.0002,
"loss": 0.0057,
"step": 521
},
{
"epoch": 19.33,
"learning_rate": 0.0002,
"loss": 0.0181,
"step": 522
},
{
"epoch": 19.37,
"learning_rate": 0.0002,
"loss": 0.0049,
"step": 523
},
{
"epoch": 19.41,
"learning_rate": 0.0002,
"loss": 0.0024,
"step": 524
},
{
"epoch": 19.44,
"learning_rate": 0.0002,
"loss": 0.0157,
"step": 525
},
{
"epoch": 19.48,
"learning_rate": 0.0002,
"loss": 0.0095,
"step": 526
},
{
"epoch": 19.52,
"learning_rate": 0.0002,
"loss": 0.0217,
"step": 527
},
{
"epoch": 19.56,
"learning_rate": 0.0002,
"loss": 0.0142,
"step": 528
},
{
"epoch": 19.59,
"learning_rate": 0.0002,
"loss": 0.0045,
"step": 529
},
{
"epoch": 19.63,
"learning_rate": 0.0002,
"loss": 0.0099,
"step": 530
},
{
"epoch": 19.67,
"learning_rate": 0.0002,
"loss": 0.004,
"step": 531
},
{
"epoch": 19.7,
"learning_rate": 0.0002,
"loss": 0.008,
"step": 532
},
{
"epoch": 19.74,
"learning_rate": 0.0002,
"loss": 0.0027,
"step": 533
},
{
"epoch": 19.78,
"learning_rate": 0.0002,
"loss": 0.0141,
"step": 534
},
{
"epoch": 19.81,
"learning_rate": 0.0002,
"loss": 0.0045,
"step": 535
},
{
"epoch": 19.85,
"learning_rate": 0.0002,
"loss": 0.005,
"step": 536
},
{
"epoch": 19.89,
"learning_rate": 0.0002,
"loss": 0.0112,
"step": 537
},
{
"epoch": 19.93,
"learning_rate": 0.0002,
"loss": 0.0039,
"step": 538
},
{
"epoch": 19.96,
"learning_rate": 0.0002,
"loss": 0.0176,
"step": 539
},
{
"epoch": 20.0,
"learning_rate": 0.0002,
"loss": 0.0026,
"step": 540
},
{
"epoch": 20.0,
"eval_loss": 0.007353875320404768,
"eval_runtime": 48.0165,
"eval_samples_per_second": 8.851,
"eval_steps_per_second": 0.562,
"step": 540
},
{
"epoch": 20.0,
"step": 540,
"total_flos": 8.164299192349491e+17,
"train_loss": 0.04922065762948478,
"train_runtime": 6513.5085,
"train_samples_per_second": 1.305,
"train_steps_per_second": 0.083
}
],
"logging_steps": 1.0,
"max_steps": 540,
"num_input_tokens_seen": 0,
"num_train_epochs": 20,
"save_steps": 50000,
"total_flos": 8.164299192349491e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}