wikitext_roberta-base / trainer_state.json
gary109's picture
End of training
4dc1362
raw
history blame
94.2 kB
{
"best_metric": 1.2186108827590942,
"best_model_checkpoint": "wikitext_roberta-base/checkpoint-666",
"epoch": 19.986666666666668,
"global_step": 740,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03,
"learning_rate": 1.0000000000000002e-06,
"loss": 1.8988,
"step": 1
},
{
"epoch": 0.05,
"learning_rate": 2.0000000000000003e-06,
"loss": 1.8877,
"step": 2
},
{
"epoch": 0.08,
"learning_rate": 3e-06,
"loss": 1.9457,
"step": 3
},
{
"epoch": 0.11,
"learning_rate": 4.000000000000001e-06,
"loss": 1.8727,
"step": 4
},
{
"epoch": 0.13,
"learning_rate": 5e-06,
"loss": 1.9502,
"step": 5
},
{
"epoch": 0.16,
"learning_rate": 6e-06,
"loss": 1.911,
"step": 6
},
{
"epoch": 0.19,
"learning_rate": 7.000000000000001e-06,
"loss": 1.925,
"step": 7
},
{
"epoch": 0.21,
"learning_rate": 8.000000000000001e-06,
"loss": 1.8293,
"step": 8
},
{
"epoch": 0.24,
"learning_rate": 9e-06,
"loss": 1.7548,
"step": 9
},
{
"epoch": 0.27,
"learning_rate": 1e-05,
"loss": 1.8128,
"step": 10
},
{
"epoch": 0.29,
"learning_rate": 1.1000000000000001e-05,
"loss": 1.7672,
"step": 11
},
{
"epoch": 0.32,
"learning_rate": 1.2e-05,
"loss": 1.789,
"step": 12
},
{
"epoch": 0.35,
"learning_rate": 1.3000000000000001e-05,
"loss": 1.7381,
"step": 13
},
{
"epoch": 0.37,
"learning_rate": 1.4000000000000001e-05,
"loss": 1.6687,
"step": 14
},
{
"epoch": 0.4,
"learning_rate": 1.5e-05,
"loss": 1.7386,
"step": 15
},
{
"epoch": 0.43,
"learning_rate": 1.6000000000000003e-05,
"loss": 1.6627,
"step": 16
},
{
"epoch": 0.45,
"learning_rate": 1.7000000000000003e-05,
"loss": 1.5889,
"step": 17
},
{
"epoch": 0.48,
"learning_rate": 1.8e-05,
"loss": 1.5649,
"step": 18
},
{
"epoch": 0.51,
"learning_rate": 1.9e-05,
"loss": 1.5465,
"step": 19
},
{
"epoch": 0.53,
"learning_rate": 2e-05,
"loss": 1.5523,
"step": 20
},
{
"epoch": 0.56,
"learning_rate": 2e-05,
"loss": 1.5625,
"step": 21
},
{
"epoch": 0.59,
"learning_rate": 2.1e-05,
"loss": 1.639,
"step": 22
},
{
"epoch": 0.61,
"learning_rate": 2.2000000000000003e-05,
"loss": 1.5218,
"step": 23
},
{
"epoch": 0.64,
"learning_rate": 2.3000000000000003e-05,
"loss": 1.5603,
"step": 24
},
{
"epoch": 0.67,
"learning_rate": 2.4e-05,
"loss": 1.5555,
"step": 25
},
{
"epoch": 0.69,
"learning_rate": 2.5e-05,
"loss": 1.5245,
"step": 26
},
{
"epoch": 0.72,
"learning_rate": 2.6000000000000002e-05,
"loss": 1.5195,
"step": 27
},
{
"epoch": 0.75,
"learning_rate": 2.7000000000000002e-05,
"loss": 1.5227,
"step": 28
},
{
"epoch": 0.77,
"learning_rate": 2.8000000000000003e-05,
"loss": 1.4743,
"step": 29
},
{
"epoch": 0.8,
"learning_rate": 2.9e-05,
"loss": 1.5171,
"step": 30
},
{
"epoch": 0.83,
"learning_rate": 3e-05,
"loss": 1.4961,
"step": 31
},
{
"epoch": 0.85,
"learning_rate": 3.1e-05,
"loss": 1.5427,
"step": 32
},
{
"epoch": 0.88,
"learning_rate": 3.2000000000000005e-05,
"loss": 1.4519,
"step": 33
},
{
"epoch": 0.91,
"learning_rate": 3.3e-05,
"loss": 1.4714,
"step": 34
},
{
"epoch": 0.93,
"learning_rate": 3.4000000000000007e-05,
"loss": 1.4477,
"step": 35
},
{
"epoch": 0.96,
"learning_rate": 3.5e-05,
"loss": 1.4796,
"step": 36
},
{
"epoch": 0.99,
"learning_rate": 3.6e-05,
"loss": 1.4175,
"step": 37
},
{
"epoch": 0.99,
"eval_accuracy": 0.7193657677192031,
"eval_loss": 1.3355050086975098,
"eval_runtime": 13.2653,
"eval_samples_per_second": 37.391,
"eval_steps_per_second": 4.674,
"step": 37
},
{
"epoch": 1.03,
"learning_rate": 3.7e-05,
"loss": 2.1673,
"step": 38
},
{
"epoch": 1.05,
"learning_rate": 3.8e-05,
"loss": 1.4677,
"step": 39
},
{
"epoch": 1.08,
"learning_rate": 3.9000000000000006e-05,
"loss": 1.4678,
"step": 40
},
{
"epoch": 1.11,
"learning_rate": 4e-05,
"loss": 1.4979,
"step": 41
},
{
"epoch": 1.13,
"learning_rate": 4.1e-05,
"loss": 1.4639,
"step": 42
},
{
"epoch": 1.16,
"learning_rate": 4.2e-05,
"loss": 1.4553,
"step": 43
},
{
"epoch": 1.19,
"learning_rate": 4.3e-05,
"loss": 1.3852,
"step": 44
},
{
"epoch": 1.21,
"learning_rate": 4.4000000000000006e-05,
"loss": 1.4783,
"step": 45
},
{
"epoch": 1.24,
"learning_rate": 4.5e-05,
"loss": 1.416,
"step": 46
},
{
"epoch": 1.27,
"learning_rate": 4.600000000000001e-05,
"loss": 1.4261,
"step": 47
},
{
"epoch": 1.29,
"learning_rate": 4.7e-05,
"loss": 1.3403,
"step": 48
},
{
"epoch": 1.32,
"learning_rate": 4.8e-05,
"loss": 1.4469,
"step": 49
},
{
"epoch": 1.35,
"learning_rate": 4.9e-05,
"loss": 1.3988,
"step": 50
},
{
"epoch": 1.37,
"learning_rate": 5e-05,
"loss": 1.412,
"step": 51
},
{
"epoch": 1.4,
"learning_rate": 4.9927536231884056e-05,
"loss": 1.4766,
"step": 52
},
{
"epoch": 1.43,
"learning_rate": 4.985507246376812e-05,
"loss": 1.4986,
"step": 53
},
{
"epoch": 1.45,
"learning_rate": 4.9782608695652176e-05,
"loss": 1.4841,
"step": 54
},
{
"epoch": 1.48,
"learning_rate": 4.9710144927536237e-05,
"loss": 1.4311,
"step": 55
},
{
"epoch": 1.51,
"learning_rate": 4.963768115942029e-05,
"loss": 1.4505,
"step": 56
},
{
"epoch": 1.53,
"learning_rate": 4.956521739130435e-05,
"loss": 1.4436,
"step": 57
},
{
"epoch": 1.56,
"learning_rate": 4.949275362318841e-05,
"loss": 1.3686,
"step": 58
},
{
"epoch": 1.59,
"learning_rate": 4.9420289855072464e-05,
"loss": 1.4193,
"step": 59
},
{
"epoch": 1.61,
"learning_rate": 4.9347826086956524e-05,
"loss": 1.4409,
"step": 60
},
{
"epoch": 1.64,
"learning_rate": 4.9275362318840584e-05,
"loss": 1.4257,
"step": 61
},
{
"epoch": 1.67,
"learning_rate": 4.920289855072464e-05,
"loss": 1.3458,
"step": 62
},
{
"epoch": 1.69,
"learning_rate": 4.91304347826087e-05,
"loss": 1.3916,
"step": 63
},
{
"epoch": 1.72,
"learning_rate": 4.905797101449275e-05,
"loss": 1.3797,
"step": 64
},
{
"epoch": 1.75,
"learning_rate": 4.898550724637682e-05,
"loss": 1.4372,
"step": 65
},
{
"epoch": 1.77,
"learning_rate": 4.891304347826087e-05,
"loss": 1.4756,
"step": 66
},
{
"epoch": 1.8,
"learning_rate": 4.884057971014493e-05,
"loss": 1.3883,
"step": 67
},
{
"epoch": 1.83,
"learning_rate": 4.8768115942028986e-05,
"loss": 1.3913,
"step": 68
},
{
"epoch": 1.85,
"learning_rate": 4.8695652173913046e-05,
"loss": 1.3826,
"step": 69
},
{
"epoch": 1.88,
"learning_rate": 4.8623188405797106e-05,
"loss": 1.4326,
"step": 70
},
{
"epoch": 1.91,
"learning_rate": 4.855072463768116e-05,
"loss": 1.4112,
"step": 71
},
{
"epoch": 1.93,
"learning_rate": 4.847826086956522e-05,
"loss": 1.4015,
"step": 72
},
{
"epoch": 1.96,
"learning_rate": 4.840579710144928e-05,
"loss": 1.3996,
"step": 73
},
{
"epoch": 1.99,
"learning_rate": 4.8333333333333334e-05,
"loss": 1.438,
"step": 74
},
{
"epoch": 1.99,
"eval_accuracy": 0.7249340724395889,
"eval_loss": 1.2952723503112793,
"eval_runtime": 13.2107,
"eval_samples_per_second": 37.545,
"eval_steps_per_second": 4.693,
"step": 74
},
{
"epoch": 2.03,
"learning_rate": 4.8260869565217394e-05,
"loss": 2.0645,
"step": 75
},
{
"epoch": 2.05,
"learning_rate": 4.818840579710145e-05,
"loss": 1.4472,
"step": 76
},
{
"epoch": 2.08,
"learning_rate": 4.8115942028985514e-05,
"loss": 1.3352,
"step": 77
},
{
"epoch": 2.11,
"learning_rate": 4.804347826086957e-05,
"loss": 1.4051,
"step": 78
},
{
"epoch": 2.13,
"learning_rate": 4.797101449275362e-05,
"loss": 1.4046,
"step": 79
},
{
"epoch": 2.16,
"learning_rate": 4.789855072463768e-05,
"loss": 1.39,
"step": 80
},
{
"epoch": 2.19,
"learning_rate": 4.782608695652174e-05,
"loss": 1.4223,
"step": 81
},
{
"epoch": 2.21,
"learning_rate": 4.77536231884058e-05,
"loss": 1.3412,
"step": 82
},
{
"epoch": 2.24,
"learning_rate": 4.7681159420289855e-05,
"loss": 1.3806,
"step": 83
},
{
"epoch": 2.27,
"learning_rate": 4.7608695652173916e-05,
"loss": 1.4172,
"step": 84
},
{
"epoch": 2.29,
"learning_rate": 4.7536231884057976e-05,
"loss": 1.3621,
"step": 85
},
{
"epoch": 2.32,
"learning_rate": 4.746376811594203e-05,
"loss": 1.403,
"step": 86
},
{
"epoch": 2.35,
"learning_rate": 4.739130434782609e-05,
"loss": 1.3762,
"step": 87
},
{
"epoch": 2.37,
"learning_rate": 4.731884057971015e-05,
"loss": 1.3764,
"step": 88
},
{
"epoch": 2.4,
"learning_rate": 4.72463768115942e-05,
"loss": 1.3957,
"step": 89
},
{
"epoch": 2.43,
"learning_rate": 4.7173913043478264e-05,
"loss": 1.3773,
"step": 90
},
{
"epoch": 2.45,
"learning_rate": 4.710144927536232e-05,
"loss": 1.3872,
"step": 91
},
{
"epoch": 2.48,
"learning_rate": 4.7028985507246384e-05,
"loss": 1.3579,
"step": 92
},
{
"epoch": 2.51,
"learning_rate": 4.695652173913044e-05,
"loss": 1.3718,
"step": 93
},
{
"epoch": 2.53,
"learning_rate": 4.68840579710145e-05,
"loss": 1.3576,
"step": 94
},
{
"epoch": 2.56,
"learning_rate": 4.681159420289855e-05,
"loss": 1.3508,
"step": 95
},
{
"epoch": 2.59,
"learning_rate": 4.673913043478261e-05,
"loss": 1.3476,
"step": 96
},
{
"epoch": 2.61,
"learning_rate": 4.666666666666667e-05,
"loss": 1.3608,
"step": 97
},
{
"epoch": 2.64,
"learning_rate": 4.6594202898550725e-05,
"loss": 1.3911,
"step": 98
},
{
"epoch": 2.67,
"learning_rate": 4.6521739130434785e-05,
"loss": 1.3748,
"step": 99
},
{
"epoch": 2.69,
"learning_rate": 4.6449275362318846e-05,
"loss": 1.3628,
"step": 100
},
{
"epoch": 2.72,
"learning_rate": 4.63768115942029e-05,
"loss": 1.3678,
"step": 101
},
{
"epoch": 2.75,
"learning_rate": 4.630434782608696e-05,
"loss": 1.3286,
"step": 102
},
{
"epoch": 2.77,
"learning_rate": 4.623188405797101e-05,
"loss": 1.3592,
"step": 103
},
{
"epoch": 2.8,
"learning_rate": 4.615942028985508e-05,
"loss": 1.3754,
"step": 104
},
{
"epoch": 2.83,
"learning_rate": 4.608695652173913e-05,
"loss": 1.3061,
"step": 105
},
{
"epoch": 2.85,
"learning_rate": 4.601449275362319e-05,
"loss": 1.3843,
"step": 106
},
{
"epoch": 2.88,
"learning_rate": 4.594202898550725e-05,
"loss": 1.3153,
"step": 107
},
{
"epoch": 2.91,
"learning_rate": 4.586956521739131e-05,
"loss": 1.3638,
"step": 108
},
{
"epoch": 2.93,
"learning_rate": 4.579710144927537e-05,
"loss": 1.3712,
"step": 109
},
{
"epoch": 2.96,
"learning_rate": 4.572463768115942e-05,
"loss": 1.3601,
"step": 110
},
{
"epoch": 2.99,
"learning_rate": 4.565217391304348e-05,
"loss": 1.4363,
"step": 111
},
{
"epoch": 2.99,
"eval_accuracy": 0.7276007863625347,
"eval_loss": 1.2758572101593018,
"eval_runtime": 13.2518,
"eval_samples_per_second": 37.429,
"eval_steps_per_second": 4.679,
"step": 111
},
{
"epoch": 3.03,
"learning_rate": 4.557971014492754e-05,
"loss": 2.0676,
"step": 112
},
{
"epoch": 3.05,
"learning_rate": 4.5507246376811595e-05,
"loss": 1.3703,
"step": 113
},
{
"epoch": 3.08,
"learning_rate": 4.5434782608695655e-05,
"loss": 1.3295,
"step": 114
},
{
"epoch": 3.11,
"learning_rate": 4.5362318840579715e-05,
"loss": 1.3613,
"step": 115
},
{
"epoch": 3.13,
"learning_rate": 4.528985507246377e-05,
"loss": 1.4229,
"step": 116
},
{
"epoch": 3.16,
"learning_rate": 4.521739130434783e-05,
"loss": 1.4115,
"step": 117
},
{
"epoch": 3.19,
"learning_rate": 4.514492753623188e-05,
"loss": 1.4115,
"step": 118
},
{
"epoch": 3.21,
"learning_rate": 4.507246376811595e-05,
"loss": 1.3827,
"step": 119
},
{
"epoch": 3.24,
"learning_rate": 4.5e-05,
"loss": 1.338,
"step": 120
},
{
"epoch": 3.27,
"learning_rate": 4.492753623188406e-05,
"loss": 1.434,
"step": 121
},
{
"epoch": 3.29,
"learning_rate": 4.4855072463768117e-05,
"loss": 1.3443,
"step": 122
},
{
"epoch": 3.32,
"learning_rate": 4.478260869565218e-05,
"loss": 1.3195,
"step": 123
},
{
"epoch": 3.35,
"learning_rate": 4.471014492753624e-05,
"loss": 1.3589,
"step": 124
},
{
"epoch": 3.37,
"learning_rate": 4.463768115942029e-05,
"loss": 1.3323,
"step": 125
},
{
"epoch": 3.4,
"learning_rate": 4.456521739130435e-05,
"loss": 1.3151,
"step": 126
},
{
"epoch": 3.43,
"learning_rate": 4.449275362318841e-05,
"loss": 1.3844,
"step": 127
},
{
"epoch": 3.45,
"learning_rate": 4.4420289855072464e-05,
"loss": 1.3213,
"step": 128
},
{
"epoch": 3.48,
"learning_rate": 4.4347826086956525e-05,
"loss": 1.3764,
"step": 129
},
{
"epoch": 3.51,
"learning_rate": 4.427536231884058e-05,
"loss": 1.3449,
"step": 130
},
{
"epoch": 3.53,
"learning_rate": 4.4202898550724645e-05,
"loss": 1.3704,
"step": 131
},
{
"epoch": 3.56,
"learning_rate": 4.41304347826087e-05,
"loss": 1.3712,
"step": 132
},
{
"epoch": 3.59,
"learning_rate": 4.405797101449275e-05,
"loss": 1.3191,
"step": 133
},
{
"epoch": 3.61,
"learning_rate": 4.398550724637681e-05,
"loss": 1.3795,
"step": 134
},
{
"epoch": 3.64,
"learning_rate": 4.391304347826087e-05,
"loss": 1.3025,
"step": 135
},
{
"epoch": 3.67,
"learning_rate": 4.384057971014493e-05,
"loss": 1.3285,
"step": 136
},
{
"epoch": 3.69,
"learning_rate": 4.3768115942028986e-05,
"loss": 1.3112,
"step": 137
},
{
"epoch": 3.72,
"learning_rate": 4.3695652173913046e-05,
"loss": 1.4008,
"step": 138
},
{
"epoch": 3.75,
"learning_rate": 4.362318840579711e-05,
"loss": 1.3598,
"step": 139
},
{
"epoch": 3.77,
"learning_rate": 4.355072463768116e-05,
"loss": 1.3402,
"step": 140
},
{
"epoch": 3.8,
"learning_rate": 4.347826086956522e-05,
"loss": 1.3282,
"step": 141
},
{
"epoch": 3.83,
"learning_rate": 4.3405797101449274e-05,
"loss": 1.4,
"step": 142
},
{
"epoch": 3.85,
"learning_rate": 4.3333333333333334e-05,
"loss": 1.276,
"step": 143
},
{
"epoch": 3.88,
"learning_rate": 4.3260869565217394e-05,
"loss": 1.3375,
"step": 144
},
{
"epoch": 3.91,
"learning_rate": 4.318840579710145e-05,
"loss": 1.3169,
"step": 145
},
{
"epoch": 3.93,
"learning_rate": 4.3115942028985515e-05,
"loss": 1.3835,
"step": 146
},
{
"epoch": 3.96,
"learning_rate": 4.304347826086957e-05,
"loss": 1.3977,
"step": 147
},
{
"epoch": 3.99,
"learning_rate": 4.297101449275363e-05,
"loss": 1.3391,
"step": 148
},
{
"epoch": 3.99,
"eval_accuracy": 0.7251519097222222,
"eval_loss": 1.2903902530670166,
"eval_runtime": 13.26,
"eval_samples_per_second": 37.406,
"eval_steps_per_second": 4.676,
"step": 148
},
{
"epoch": 4.03,
"learning_rate": 4.289855072463768e-05,
"loss": 2.05,
"step": 149
},
{
"epoch": 4.05,
"learning_rate": 4.282608695652174e-05,
"loss": 1.3425,
"step": 150
},
{
"epoch": 4.08,
"learning_rate": 4.27536231884058e-05,
"loss": 1.3443,
"step": 151
},
{
"epoch": 4.11,
"learning_rate": 4.2681159420289856e-05,
"loss": 1.3464,
"step": 152
},
{
"epoch": 4.13,
"learning_rate": 4.2608695652173916e-05,
"loss": 1.355,
"step": 153
},
{
"epoch": 4.16,
"learning_rate": 4.2536231884057976e-05,
"loss": 1.3285,
"step": 154
},
{
"epoch": 4.19,
"learning_rate": 4.246376811594203e-05,
"loss": 1.3246,
"step": 155
},
{
"epoch": 4.21,
"learning_rate": 4.239130434782609e-05,
"loss": 1.3213,
"step": 156
},
{
"epoch": 4.24,
"learning_rate": 4.2318840579710143e-05,
"loss": 1.297,
"step": 157
},
{
"epoch": 4.27,
"learning_rate": 4.224637681159421e-05,
"loss": 1.3569,
"step": 158
},
{
"epoch": 4.29,
"learning_rate": 4.2173913043478264e-05,
"loss": 1.3392,
"step": 159
},
{
"epoch": 4.32,
"learning_rate": 4.210144927536232e-05,
"loss": 1.2817,
"step": 160
},
{
"epoch": 4.35,
"learning_rate": 4.202898550724638e-05,
"loss": 1.3187,
"step": 161
},
{
"epoch": 4.37,
"learning_rate": 4.195652173913044e-05,
"loss": 1.3094,
"step": 162
},
{
"epoch": 4.4,
"learning_rate": 4.18840579710145e-05,
"loss": 1.4001,
"step": 163
},
{
"epoch": 4.43,
"learning_rate": 4.181159420289855e-05,
"loss": 1.3204,
"step": 164
},
{
"epoch": 4.45,
"learning_rate": 4.1739130434782605e-05,
"loss": 1.3482,
"step": 165
},
{
"epoch": 4.48,
"learning_rate": 4.166666666666667e-05,
"loss": 1.3674,
"step": 166
},
{
"epoch": 4.51,
"learning_rate": 4.1594202898550726e-05,
"loss": 1.3334,
"step": 167
},
{
"epoch": 4.53,
"learning_rate": 4.1521739130434786e-05,
"loss": 1.3333,
"step": 168
},
{
"epoch": 4.56,
"learning_rate": 4.144927536231884e-05,
"loss": 1.3723,
"step": 169
},
{
"epoch": 4.59,
"learning_rate": 4.13768115942029e-05,
"loss": 1.3502,
"step": 170
},
{
"epoch": 4.61,
"learning_rate": 4.130434782608696e-05,
"loss": 1.3256,
"step": 171
},
{
"epoch": 4.64,
"learning_rate": 4.123188405797101e-05,
"loss": 1.4001,
"step": 172
},
{
"epoch": 4.67,
"learning_rate": 4.115942028985507e-05,
"loss": 1.3288,
"step": 173
},
{
"epoch": 4.69,
"learning_rate": 4.1086956521739134e-05,
"loss": 1.31,
"step": 174
},
{
"epoch": 4.72,
"learning_rate": 4.101449275362319e-05,
"loss": 1.3456,
"step": 175
},
{
"epoch": 4.75,
"learning_rate": 4.094202898550725e-05,
"loss": 1.3317,
"step": 176
},
{
"epoch": 4.77,
"learning_rate": 4.086956521739131e-05,
"loss": 1.3362,
"step": 177
},
{
"epoch": 4.8,
"learning_rate": 4.079710144927537e-05,
"loss": 1.3092,
"step": 178
},
{
"epoch": 4.83,
"learning_rate": 4.072463768115942e-05,
"loss": 1.2915,
"step": 179
},
{
"epoch": 4.85,
"learning_rate": 4.065217391304348e-05,
"loss": 1.3801,
"step": 180
},
{
"epoch": 4.88,
"learning_rate": 4.057971014492754e-05,
"loss": 1.2969,
"step": 181
},
{
"epoch": 4.91,
"learning_rate": 4.0507246376811595e-05,
"loss": 1.3184,
"step": 182
},
{
"epoch": 4.93,
"learning_rate": 4.0434782608695655e-05,
"loss": 1.2744,
"step": 183
},
{
"epoch": 4.96,
"learning_rate": 4.036231884057971e-05,
"loss": 1.3823,
"step": 184
},
{
"epoch": 4.99,
"learning_rate": 4.028985507246377e-05,
"loss": 1.3741,
"step": 185
},
{
"epoch": 4.99,
"eval_accuracy": 0.7290188004551119,
"eval_loss": 1.2620676755905151,
"eval_runtime": 13.2557,
"eval_samples_per_second": 37.418,
"eval_steps_per_second": 4.677,
"step": 185
},
{
"epoch": 5.03,
"learning_rate": 4.021739130434783e-05,
"loss": 1.9576,
"step": 186
},
{
"epoch": 5.05,
"learning_rate": 4.014492753623188e-05,
"loss": 1.4131,
"step": 187
},
{
"epoch": 5.08,
"learning_rate": 4.007246376811594e-05,
"loss": 1.308,
"step": 188
},
{
"epoch": 5.11,
"learning_rate": 4e-05,
"loss": 1.3495,
"step": 189
},
{
"epoch": 5.13,
"learning_rate": 3.9927536231884064e-05,
"loss": 1.2944,
"step": 190
},
{
"epoch": 5.16,
"learning_rate": 3.985507246376812e-05,
"loss": 1.3534,
"step": 191
},
{
"epoch": 5.19,
"learning_rate": 3.978260869565217e-05,
"loss": 1.3448,
"step": 192
},
{
"epoch": 5.21,
"learning_rate": 3.971014492753624e-05,
"loss": 1.3493,
"step": 193
},
{
"epoch": 5.24,
"learning_rate": 3.963768115942029e-05,
"loss": 1.3033,
"step": 194
},
{
"epoch": 5.27,
"learning_rate": 3.956521739130435e-05,
"loss": 1.3327,
"step": 195
},
{
"epoch": 5.29,
"learning_rate": 3.9492753623188405e-05,
"loss": 1.3037,
"step": 196
},
{
"epoch": 5.32,
"learning_rate": 3.9420289855072465e-05,
"loss": 1.2676,
"step": 197
},
{
"epoch": 5.35,
"learning_rate": 3.9347826086956525e-05,
"loss": 1.277,
"step": 198
},
{
"epoch": 5.37,
"learning_rate": 3.927536231884058e-05,
"loss": 1.306,
"step": 199
},
{
"epoch": 5.4,
"learning_rate": 3.920289855072464e-05,
"loss": 1.3317,
"step": 200
},
{
"epoch": 5.43,
"learning_rate": 3.91304347826087e-05,
"loss": 1.2872,
"step": 201
},
{
"epoch": 5.45,
"learning_rate": 3.905797101449275e-05,
"loss": 1.2878,
"step": 202
},
{
"epoch": 5.48,
"learning_rate": 3.898550724637681e-05,
"loss": 1.3232,
"step": 203
},
{
"epoch": 5.51,
"learning_rate": 3.8913043478260866e-05,
"loss": 1.2771,
"step": 204
},
{
"epoch": 5.53,
"learning_rate": 3.884057971014493e-05,
"loss": 1.3035,
"step": 205
},
{
"epoch": 5.56,
"learning_rate": 3.876811594202899e-05,
"loss": 1.3175,
"step": 206
},
{
"epoch": 5.59,
"learning_rate": 3.869565217391305e-05,
"loss": 1.2661,
"step": 207
},
{
"epoch": 5.61,
"learning_rate": 3.862318840579711e-05,
"loss": 1.3559,
"step": 208
},
{
"epoch": 5.64,
"learning_rate": 3.855072463768116e-05,
"loss": 1.3458,
"step": 209
},
{
"epoch": 5.67,
"learning_rate": 3.847826086956522e-05,
"loss": 1.2947,
"step": 210
},
{
"epoch": 5.69,
"learning_rate": 3.8405797101449274e-05,
"loss": 1.2938,
"step": 211
},
{
"epoch": 5.72,
"learning_rate": 3.8333333333333334e-05,
"loss": 1.3266,
"step": 212
},
{
"epoch": 5.75,
"learning_rate": 3.8260869565217395e-05,
"loss": 1.2853,
"step": 213
},
{
"epoch": 5.77,
"learning_rate": 3.818840579710145e-05,
"loss": 1.3009,
"step": 214
},
{
"epoch": 5.8,
"learning_rate": 3.811594202898551e-05,
"loss": 1.3023,
"step": 215
},
{
"epoch": 5.83,
"learning_rate": 3.804347826086957e-05,
"loss": 1.3105,
"step": 216
},
{
"epoch": 5.85,
"learning_rate": 3.797101449275363e-05,
"loss": 1.343,
"step": 217
},
{
"epoch": 5.88,
"learning_rate": 3.789855072463768e-05,
"loss": 1.2957,
"step": 218
},
{
"epoch": 5.91,
"learning_rate": 3.7826086956521736e-05,
"loss": 1.307,
"step": 219
},
{
"epoch": 5.93,
"learning_rate": 3.77536231884058e-05,
"loss": 1.3477,
"step": 220
},
{
"epoch": 5.96,
"learning_rate": 3.7681159420289856e-05,
"loss": 1.347,
"step": 221
},
{
"epoch": 5.99,
"learning_rate": 3.7608695652173917e-05,
"loss": 1.2771,
"step": 222
},
{
"epoch": 5.99,
"eval_accuracy": 0.7353204415394212,
"eval_loss": 1.2311729192733765,
"eval_runtime": 13.2727,
"eval_samples_per_second": 37.37,
"eval_steps_per_second": 4.671,
"step": 222
},
{
"epoch": 6.03,
"learning_rate": 3.753623188405797e-05,
"loss": 1.9712,
"step": 223
},
{
"epoch": 6.05,
"learning_rate": 3.746376811594203e-05,
"loss": 1.2942,
"step": 224
},
{
"epoch": 6.08,
"learning_rate": 3.739130434782609e-05,
"loss": 1.3117,
"step": 225
},
{
"epoch": 6.11,
"learning_rate": 3.7318840579710144e-05,
"loss": 1.3395,
"step": 226
},
{
"epoch": 6.13,
"learning_rate": 3.7246376811594204e-05,
"loss": 1.3447,
"step": 227
},
{
"epoch": 6.16,
"learning_rate": 3.7173913043478264e-05,
"loss": 1.2895,
"step": 228
},
{
"epoch": 6.19,
"learning_rate": 3.710144927536232e-05,
"loss": 1.2623,
"step": 229
},
{
"epoch": 6.21,
"learning_rate": 3.702898550724638e-05,
"loss": 1.2987,
"step": 230
},
{
"epoch": 6.24,
"learning_rate": 3.695652173913043e-05,
"loss": 1.3021,
"step": 231
},
{
"epoch": 6.27,
"learning_rate": 3.68840579710145e-05,
"loss": 1.3305,
"step": 232
},
{
"epoch": 6.29,
"learning_rate": 3.681159420289855e-05,
"loss": 1.2959,
"step": 233
},
{
"epoch": 6.32,
"learning_rate": 3.673913043478261e-05,
"loss": 1.2879,
"step": 234
},
{
"epoch": 6.35,
"learning_rate": 3.6666666666666666e-05,
"loss": 1.348,
"step": 235
},
{
"epoch": 6.37,
"learning_rate": 3.6594202898550726e-05,
"loss": 1.3434,
"step": 236
},
{
"epoch": 6.4,
"learning_rate": 3.6521739130434786e-05,
"loss": 1.3034,
"step": 237
},
{
"epoch": 6.43,
"learning_rate": 3.644927536231884e-05,
"loss": 1.3372,
"step": 238
},
{
"epoch": 6.45,
"learning_rate": 3.63768115942029e-05,
"loss": 1.2488,
"step": 239
},
{
"epoch": 6.48,
"learning_rate": 3.630434782608696e-05,
"loss": 1.2779,
"step": 240
},
{
"epoch": 6.51,
"learning_rate": 3.6231884057971014e-05,
"loss": 1.3044,
"step": 241
},
{
"epoch": 6.53,
"learning_rate": 3.6159420289855074e-05,
"loss": 1.3089,
"step": 242
},
{
"epoch": 6.56,
"learning_rate": 3.6086956521739134e-05,
"loss": 1.3803,
"step": 243
},
{
"epoch": 6.59,
"learning_rate": 3.6014492753623194e-05,
"loss": 1.3559,
"step": 244
},
{
"epoch": 6.61,
"learning_rate": 3.594202898550725e-05,
"loss": 1.3486,
"step": 245
},
{
"epoch": 6.64,
"learning_rate": 3.58695652173913e-05,
"loss": 1.2817,
"step": 246
},
{
"epoch": 6.67,
"learning_rate": 3.579710144927537e-05,
"loss": 1.2304,
"step": 247
},
{
"epoch": 6.69,
"learning_rate": 3.572463768115942e-05,
"loss": 1.3637,
"step": 248
},
{
"epoch": 6.72,
"learning_rate": 3.565217391304348e-05,
"loss": 1.3177,
"step": 249
},
{
"epoch": 6.75,
"learning_rate": 3.5579710144927535e-05,
"loss": 1.3273,
"step": 250
},
{
"epoch": 6.77,
"learning_rate": 3.5507246376811596e-05,
"loss": 1.3522,
"step": 251
},
{
"epoch": 6.8,
"learning_rate": 3.5434782608695656e-05,
"loss": 1.3314,
"step": 252
},
{
"epoch": 6.83,
"learning_rate": 3.536231884057971e-05,
"loss": 1.2812,
"step": 253
},
{
"epoch": 6.85,
"learning_rate": 3.528985507246377e-05,
"loss": 1.2961,
"step": 254
},
{
"epoch": 6.88,
"learning_rate": 3.521739130434783e-05,
"loss": 1.358,
"step": 255
},
{
"epoch": 6.91,
"learning_rate": 3.514492753623188e-05,
"loss": 1.2733,
"step": 256
},
{
"epoch": 6.93,
"learning_rate": 3.5072463768115943e-05,
"loss": 1.2509,
"step": 257
},
{
"epoch": 6.96,
"learning_rate": 3.5e-05,
"loss": 1.2686,
"step": 258
},
{
"epoch": 6.99,
"learning_rate": 3.4927536231884064e-05,
"loss": 1.287,
"step": 259
},
{
"epoch": 6.99,
"eval_accuracy": 0.7288652772101893,
"eval_loss": 1.2542475461959839,
"eval_runtime": 13.3151,
"eval_samples_per_second": 37.251,
"eval_steps_per_second": 4.656,
"step": 259
},
{
"epoch": 7.03,
"learning_rate": 3.485507246376812e-05,
"loss": 2.0198,
"step": 260
},
{
"epoch": 7.05,
"learning_rate": 3.478260869565218e-05,
"loss": 1.3153,
"step": 261
},
{
"epoch": 7.08,
"learning_rate": 3.471014492753623e-05,
"loss": 1.2692,
"step": 262
},
{
"epoch": 7.11,
"learning_rate": 3.463768115942029e-05,
"loss": 1.327,
"step": 263
},
{
"epoch": 7.13,
"learning_rate": 3.456521739130435e-05,
"loss": 1.2767,
"step": 264
},
{
"epoch": 7.16,
"learning_rate": 3.4492753623188405e-05,
"loss": 1.3097,
"step": 265
},
{
"epoch": 7.19,
"learning_rate": 3.4420289855072465e-05,
"loss": 1.2951,
"step": 266
},
{
"epoch": 7.21,
"learning_rate": 3.4347826086956526e-05,
"loss": 1.2827,
"step": 267
},
{
"epoch": 7.24,
"learning_rate": 3.427536231884058e-05,
"loss": 1.2769,
"step": 268
},
{
"epoch": 7.27,
"learning_rate": 3.420289855072464e-05,
"loss": 1.3052,
"step": 269
},
{
"epoch": 7.29,
"learning_rate": 3.413043478260869e-05,
"loss": 1.3424,
"step": 270
},
{
"epoch": 7.32,
"learning_rate": 3.405797101449276e-05,
"loss": 1.3514,
"step": 271
},
{
"epoch": 7.35,
"learning_rate": 3.398550724637681e-05,
"loss": 1.3662,
"step": 272
},
{
"epoch": 7.37,
"learning_rate": 3.3913043478260867e-05,
"loss": 1.3694,
"step": 273
},
{
"epoch": 7.4,
"learning_rate": 3.3840579710144934e-05,
"loss": 1.2747,
"step": 274
},
{
"epoch": 7.43,
"learning_rate": 3.376811594202899e-05,
"loss": 1.3502,
"step": 275
},
{
"epoch": 7.45,
"learning_rate": 3.369565217391305e-05,
"loss": 1.2687,
"step": 276
},
{
"epoch": 7.48,
"learning_rate": 3.36231884057971e-05,
"loss": 1.2702,
"step": 277
},
{
"epoch": 7.51,
"learning_rate": 3.355072463768116e-05,
"loss": 1.2983,
"step": 278
},
{
"epoch": 7.53,
"learning_rate": 3.347826086956522e-05,
"loss": 1.3027,
"step": 279
},
{
"epoch": 7.56,
"learning_rate": 3.3405797101449275e-05,
"loss": 1.2854,
"step": 280
},
{
"epoch": 7.59,
"learning_rate": 3.3333333333333335e-05,
"loss": 1.2679,
"step": 281
},
{
"epoch": 7.61,
"learning_rate": 3.3260869565217395e-05,
"loss": 1.379,
"step": 282
},
{
"epoch": 7.64,
"learning_rate": 3.318840579710145e-05,
"loss": 1.3008,
"step": 283
},
{
"epoch": 7.67,
"learning_rate": 3.311594202898551e-05,
"loss": 1.343,
"step": 284
},
{
"epoch": 7.69,
"learning_rate": 3.304347826086956e-05,
"loss": 1.266,
"step": 285
},
{
"epoch": 7.72,
"learning_rate": 3.297101449275363e-05,
"loss": 1.3153,
"step": 286
},
{
"epoch": 7.75,
"learning_rate": 3.289855072463768e-05,
"loss": 1.2899,
"step": 287
},
{
"epoch": 7.77,
"learning_rate": 3.282608695652174e-05,
"loss": 1.2609,
"step": 288
},
{
"epoch": 7.8,
"learning_rate": 3.2753623188405796e-05,
"loss": 1.3002,
"step": 289
},
{
"epoch": 7.83,
"learning_rate": 3.268115942028986e-05,
"loss": 1.2858,
"step": 290
},
{
"epoch": 7.85,
"learning_rate": 3.260869565217392e-05,
"loss": 1.3049,
"step": 291
},
{
"epoch": 7.88,
"learning_rate": 3.253623188405797e-05,
"loss": 1.2891,
"step": 292
},
{
"epoch": 7.91,
"learning_rate": 3.246376811594203e-05,
"loss": 1.209,
"step": 293
},
{
"epoch": 7.93,
"learning_rate": 3.239130434782609e-05,
"loss": 1.2867,
"step": 294
},
{
"epoch": 7.96,
"learning_rate": 3.2318840579710144e-05,
"loss": 1.2934,
"step": 295
},
{
"epoch": 7.99,
"learning_rate": 3.2246376811594205e-05,
"loss": 1.29,
"step": 296
},
{
"epoch": 7.99,
"eval_accuracy": 0.7345346311640254,
"eval_loss": 1.2290480136871338,
"eval_runtime": 13.2843,
"eval_samples_per_second": 37.337,
"eval_steps_per_second": 4.667,
"step": 296
},
{
"epoch": 8.03,
"learning_rate": 3.217391304347826e-05,
"loss": 1.9383,
"step": 297
},
{
"epoch": 8.05,
"learning_rate": 3.2101449275362325e-05,
"loss": 1.2926,
"step": 298
},
{
"epoch": 8.08,
"learning_rate": 3.202898550724638e-05,
"loss": 1.3316,
"step": 299
},
{
"epoch": 8.11,
"learning_rate": 3.195652173913043e-05,
"loss": 1.2614,
"step": 300
},
{
"epoch": 8.13,
"learning_rate": 3.188405797101449e-05,
"loss": 1.316,
"step": 301
},
{
"epoch": 8.16,
"learning_rate": 3.181159420289855e-05,
"loss": 1.2777,
"step": 302
},
{
"epoch": 8.19,
"learning_rate": 3.173913043478261e-05,
"loss": 1.3079,
"step": 303
},
{
"epoch": 8.21,
"learning_rate": 3.1666666666666666e-05,
"loss": 1.3451,
"step": 304
},
{
"epoch": 8.24,
"learning_rate": 3.1594202898550726e-05,
"loss": 1.2871,
"step": 305
},
{
"epoch": 8.27,
"learning_rate": 3.152173913043479e-05,
"loss": 1.3431,
"step": 306
},
{
"epoch": 8.29,
"learning_rate": 3.144927536231884e-05,
"loss": 1.2507,
"step": 307
},
{
"epoch": 8.32,
"learning_rate": 3.13768115942029e-05,
"loss": 1.292,
"step": 308
},
{
"epoch": 8.35,
"learning_rate": 3.130434782608696e-05,
"loss": 1.2764,
"step": 309
},
{
"epoch": 8.37,
"learning_rate": 3.1231884057971014e-05,
"loss": 1.3385,
"step": 310
},
{
"epoch": 8.4,
"learning_rate": 3.1159420289855074e-05,
"loss": 1.3285,
"step": 311
},
{
"epoch": 8.43,
"learning_rate": 3.108695652173913e-05,
"loss": 1.2385,
"step": 312
},
{
"epoch": 8.45,
"learning_rate": 3.1014492753623195e-05,
"loss": 1.2528,
"step": 313
},
{
"epoch": 8.48,
"learning_rate": 3.094202898550725e-05,
"loss": 1.3026,
"step": 314
},
{
"epoch": 8.51,
"learning_rate": 3.086956521739131e-05,
"loss": 1.3108,
"step": 315
},
{
"epoch": 8.53,
"learning_rate": 3.079710144927536e-05,
"loss": 1.2307,
"step": 316
},
{
"epoch": 8.56,
"learning_rate": 3.072463768115942e-05,
"loss": 1.2586,
"step": 317
},
{
"epoch": 8.59,
"learning_rate": 3.065217391304348e-05,
"loss": 1.3263,
"step": 318
},
{
"epoch": 8.61,
"learning_rate": 3.0579710144927536e-05,
"loss": 1.2522,
"step": 319
},
{
"epoch": 8.64,
"learning_rate": 3.0507246376811593e-05,
"loss": 1.2695,
"step": 320
},
{
"epoch": 8.67,
"learning_rate": 3.0434782608695656e-05,
"loss": 1.2588,
"step": 321
},
{
"epoch": 8.69,
"learning_rate": 3.0362318840579713e-05,
"loss": 1.2759,
"step": 322
},
{
"epoch": 8.72,
"learning_rate": 3.028985507246377e-05,
"loss": 1.3229,
"step": 323
},
{
"epoch": 8.75,
"learning_rate": 3.0217391304347827e-05,
"loss": 1.2949,
"step": 324
},
{
"epoch": 8.77,
"learning_rate": 3.0144927536231887e-05,
"loss": 1.3185,
"step": 325
},
{
"epoch": 8.8,
"learning_rate": 3.0072463768115944e-05,
"loss": 1.2303,
"step": 326
},
{
"epoch": 8.83,
"learning_rate": 3e-05,
"loss": 1.2309,
"step": 327
},
{
"epoch": 8.85,
"learning_rate": 2.9927536231884058e-05,
"loss": 1.2804,
"step": 328
},
{
"epoch": 8.88,
"learning_rate": 2.9855072463768118e-05,
"loss": 1.2964,
"step": 329
},
{
"epoch": 8.91,
"learning_rate": 2.9782608695652175e-05,
"loss": 1.2547,
"step": 330
},
{
"epoch": 8.93,
"learning_rate": 2.971014492753623e-05,
"loss": 1.2711,
"step": 331
},
{
"epoch": 8.96,
"learning_rate": 2.963768115942029e-05,
"loss": 1.2578,
"step": 332
},
{
"epoch": 8.99,
"learning_rate": 2.9565217391304352e-05,
"loss": 1.2948,
"step": 333
},
{
"epoch": 8.99,
"eval_accuracy": 0.7286482668694991,
"eval_loss": 1.2536934614181519,
"eval_runtime": 13.2456,
"eval_samples_per_second": 37.446,
"eval_steps_per_second": 4.681,
"step": 333
},
{
"epoch": 9.03,
"learning_rate": 2.949275362318841e-05,
"loss": 1.9494,
"step": 334
},
{
"epoch": 9.05,
"learning_rate": 2.9420289855072462e-05,
"loss": 1.2457,
"step": 335
},
{
"epoch": 9.08,
"learning_rate": 2.9347826086956526e-05,
"loss": 1.2984,
"step": 336
},
{
"epoch": 9.11,
"learning_rate": 2.9275362318840583e-05,
"loss": 1.315,
"step": 337
},
{
"epoch": 9.13,
"learning_rate": 2.920289855072464e-05,
"loss": 1.2701,
"step": 338
},
{
"epoch": 9.16,
"learning_rate": 2.9130434782608696e-05,
"loss": 1.2902,
"step": 339
},
{
"epoch": 9.19,
"learning_rate": 2.9057971014492757e-05,
"loss": 1.3615,
"step": 340
},
{
"epoch": 9.21,
"learning_rate": 2.8985507246376814e-05,
"loss": 1.2761,
"step": 341
},
{
"epoch": 9.24,
"learning_rate": 2.891304347826087e-05,
"loss": 1.2678,
"step": 342
},
{
"epoch": 9.27,
"learning_rate": 2.8840579710144927e-05,
"loss": 1.2982,
"step": 343
},
{
"epoch": 9.29,
"learning_rate": 2.8768115942028988e-05,
"loss": 1.2626,
"step": 344
},
{
"epoch": 9.32,
"learning_rate": 2.8695652173913044e-05,
"loss": 1.2179,
"step": 345
},
{
"epoch": 9.35,
"learning_rate": 2.86231884057971e-05,
"loss": 1.2992,
"step": 346
},
{
"epoch": 9.37,
"learning_rate": 2.8550724637681158e-05,
"loss": 1.3423,
"step": 347
},
{
"epoch": 9.4,
"learning_rate": 2.847826086956522e-05,
"loss": 1.2727,
"step": 348
},
{
"epoch": 9.43,
"learning_rate": 2.840579710144928e-05,
"loss": 1.2516,
"step": 349
},
{
"epoch": 9.45,
"learning_rate": 2.8333333333333335e-05,
"loss": 1.259,
"step": 350
},
{
"epoch": 9.48,
"learning_rate": 2.826086956521739e-05,
"loss": 1.28,
"step": 351
},
{
"epoch": 9.51,
"learning_rate": 2.8188405797101452e-05,
"loss": 1.2764,
"step": 352
},
{
"epoch": 9.53,
"learning_rate": 2.811594202898551e-05,
"loss": 1.2954,
"step": 353
},
{
"epoch": 9.56,
"learning_rate": 2.8043478260869566e-05,
"loss": 1.3081,
"step": 354
},
{
"epoch": 9.59,
"learning_rate": 2.7971014492753623e-05,
"loss": 1.3355,
"step": 355
},
{
"epoch": 9.61,
"learning_rate": 2.7898550724637683e-05,
"loss": 1.3269,
"step": 356
},
{
"epoch": 9.64,
"learning_rate": 2.782608695652174e-05,
"loss": 1.2538,
"step": 357
},
{
"epoch": 9.67,
"learning_rate": 2.7753623188405797e-05,
"loss": 1.2652,
"step": 358
},
{
"epoch": 9.69,
"learning_rate": 2.7681159420289854e-05,
"loss": 1.2239,
"step": 359
},
{
"epoch": 9.72,
"learning_rate": 2.7608695652173917e-05,
"loss": 1.2764,
"step": 360
},
{
"epoch": 9.75,
"learning_rate": 2.753623188405797e-05,
"loss": 1.2484,
"step": 361
},
{
"epoch": 9.77,
"learning_rate": 2.7463768115942028e-05,
"loss": 1.3045,
"step": 362
},
{
"epoch": 9.8,
"learning_rate": 2.7391304347826085e-05,
"loss": 1.2679,
"step": 363
},
{
"epoch": 9.83,
"learning_rate": 2.7318840579710148e-05,
"loss": 1.3149,
"step": 364
},
{
"epoch": 9.85,
"learning_rate": 2.7246376811594205e-05,
"loss": 1.2347,
"step": 365
},
{
"epoch": 9.88,
"learning_rate": 2.7173913043478262e-05,
"loss": 1.2483,
"step": 366
},
{
"epoch": 9.91,
"learning_rate": 2.7101449275362322e-05,
"loss": 1.2693,
"step": 367
},
{
"epoch": 9.93,
"learning_rate": 2.702898550724638e-05,
"loss": 1.2849,
"step": 368
},
{
"epoch": 9.96,
"learning_rate": 2.6956521739130436e-05,
"loss": 1.2808,
"step": 369
},
{
"epoch": 9.99,
"learning_rate": 2.6884057971014493e-05,
"loss": 1.2741,
"step": 370
},
{
"epoch": 9.99,
"eval_accuracy": 0.7354103508012126,
"eval_loss": 1.2199150323867798,
"eval_runtime": 13.2633,
"eval_samples_per_second": 37.397,
"eval_steps_per_second": 4.675,
"step": 370
},
{
"epoch": 10.03,
"learning_rate": 2.6811594202898553e-05,
"loss": 1.8651,
"step": 371
},
{
"epoch": 10.05,
"learning_rate": 2.673913043478261e-05,
"loss": 1.3189,
"step": 372
},
{
"epoch": 10.08,
"learning_rate": 2.6666666666666667e-05,
"loss": 1.2528,
"step": 373
},
{
"epoch": 10.11,
"learning_rate": 2.6594202898550723e-05,
"loss": 1.319,
"step": 374
},
{
"epoch": 10.13,
"learning_rate": 2.6521739130434787e-05,
"loss": 1.2792,
"step": 375
},
{
"epoch": 10.16,
"learning_rate": 2.6449275362318844e-05,
"loss": 1.2567,
"step": 376
},
{
"epoch": 10.19,
"learning_rate": 2.63768115942029e-05,
"loss": 1.2522,
"step": 377
},
{
"epoch": 10.21,
"learning_rate": 2.6304347826086954e-05,
"loss": 1.2899,
"step": 378
},
{
"epoch": 10.24,
"learning_rate": 2.6231884057971018e-05,
"loss": 1.2804,
"step": 379
},
{
"epoch": 10.27,
"learning_rate": 2.6159420289855075e-05,
"loss": 1.2721,
"step": 380
},
{
"epoch": 10.29,
"learning_rate": 2.608695652173913e-05,
"loss": 1.2901,
"step": 381
},
{
"epoch": 10.32,
"learning_rate": 2.601449275362319e-05,
"loss": 1.3134,
"step": 382
},
{
"epoch": 10.35,
"learning_rate": 2.594202898550725e-05,
"loss": 1.2504,
"step": 383
},
{
"epoch": 10.37,
"learning_rate": 2.5869565217391305e-05,
"loss": 1.3061,
"step": 384
},
{
"epoch": 10.4,
"learning_rate": 2.5797101449275362e-05,
"loss": 1.2553,
"step": 385
},
{
"epoch": 10.43,
"learning_rate": 2.572463768115942e-05,
"loss": 1.2534,
"step": 386
},
{
"epoch": 10.45,
"learning_rate": 2.5652173913043483e-05,
"loss": 1.2761,
"step": 387
},
{
"epoch": 10.48,
"learning_rate": 2.5579710144927536e-05,
"loss": 1.3338,
"step": 388
},
{
"epoch": 10.51,
"learning_rate": 2.5507246376811593e-05,
"loss": 1.256,
"step": 389
},
{
"epoch": 10.53,
"learning_rate": 2.543478260869565e-05,
"loss": 1.1987,
"step": 390
},
{
"epoch": 10.56,
"learning_rate": 2.5362318840579714e-05,
"loss": 1.2809,
"step": 391
},
{
"epoch": 10.59,
"learning_rate": 2.528985507246377e-05,
"loss": 1.238,
"step": 392
},
{
"epoch": 10.61,
"learning_rate": 2.5217391304347827e-05,
"loss": 1.2326,
"step": 393
},
{
"epoch": 10.64,
"learning_rate": 2.5144927536231884e-05,
"loss": 1.2594,
"step": 394
},
{
"epoch": 10.67,
"learning_rate": 2.5072463768115944e-05,
"loss": 1.278,
"step": 395
},
{
"epoch": 10.69,
"learning_rate": 2.5e-05,
"loss": 1.2594,
"step": 396
},
{
"epoch": 10.72,
"learning_rate": 2.492753623188406e-05,
"loss": 1.2381,
"step": 397
},
{
"epoch": 10.75,
"learning_rate": 2.4855072463768118e-05,
"loss": 1.2416,
"step": 398
},
{
"epoch": 10.77,
"learning_rate": 2.4782608695652175e-05,
"loss": 1.2395,
"step": 399
},
{
"epoch": 10.8,
"learning_rate": 2.4710144927536232e-05,
"loss": 1.2736,
"step": 400
},
{
"epoch": 10.83,
"learning_rate": 2.4637681159420292e-05,
"loss": 1.2334,
"step": 401
},
{
"epoch": 10.85,
"learning_rate": 2.456521739130435e-05,
"loss": 1.2722,
"step": 402
},
{
"epoch": 10.88,
"learning_rate": 2.449275362318841e-05,
"loss": 1.2749,
"step": 403
},
{
"epoch": 10.91,
"learning_rate": 2.4420289855072466e-05,
"loss": 1.3086,
"step": 404
},
{
"epoch": 10.93,
"learning_rate": 2.4347826086956523e-05,
"loss": 1.3194,
"step": 405
},
{
"epoch": 10.96,
"learning_rate": 2.427536231884058e-05,
"loss": 1.2443,
"step": 406
},
{
"epoch": 10.99,
"learning_rate": 2.420289855072464e-05,
"loss": 1.2342,
"step": 407
},
{
"epoch": 10.99,
"eval_accuracy": 0.730909385375334,
"eval_loss": 1.2519582509994507,
"eval_runtime": 13.3427,
"eval_samples_per_second": 37.174,
"eval_steps_per_second": 4.647,
"step": 407
},
{
"epoch": 11.03,
"learning_rate": 2.4130434782608697e-05,
"loss": 1.9108,
"step": 408
},
{
"epoch": 11.05,
"learning_rate": 2.4057971014492757e-05,
"loss": 1.2788,
"step": 409
},
{
"epoch": 11.08,
"learning_rate": 2.398550724637681e-05,
"loss": 1.2999,
"step": 410
},
{
"epoch": 11.11,
"learning_rate": 2.391304347826087e-05,
"loss": 1.2402,
"step": 411
},
{
"epoch": 11.13,
"learning_rate": 2.3840579710144928e-05,
"loss": 1.2587,
"step": 412
},
{
"epoch": 11.16,
"learning_rate": 2.3768115942028988e-05,
"loss": 1.3018,
"step": 413
},
{
"epoch": 11.19,
"learning_rate": 2.3695652173913045e-05,
"loss": 1.2506,
"step": 414
},
{
"epoch": 11.21,
"learning_rate": 2.36231884057971e-05,
"loss": 1.2885,
"step": 415
},
{
"epoch": 11.24,
"learning_rate": 2.355072463768116e-05,
"loss": 1.331,
"step": 416
},
{
"epoch": 11.27,
"learning_rate": 2.347826086956522e-05,
"loss": 1.2617,
"step": 417
},
{
"epoch": 11.29,
"learning_rate": 2.3405797101449276e-05,
"loss": 1.3315,
"step": 418
},
{
"epoch": 11.32,
"learning_rate": 2.3333333333333336e-05,
"loss": 1.2644,
"step": 419
},
{
"epoch": 11.35,
"learning_rate": 2.3260869565217393e-05,
"loss": 1.2276,
"step": 420
},
{
"epoch": 11.37,
"learning_rate": 2.318840579710145e-05,
"loss": 1.2159,
"step": 421
},
{
"epoch": 11.4,
"learning_rate": 2.3115942028985506e-05,
"loss": 1.2182,
"step": 422
},
{
"epoch": 11.43,
"learning_rate": 2.3043478260869567e-05,
"loss": 1.2267,
"step": 423
},
{
"epoch": 11.45,
"learning_rate": 2.2971014492753623e-05,
"loss": 1.3009,
"step": 424
},
{
"epoch": 11.48,
"learning_rate": 2.2898550724637684e-05,
"loss": 1.2403,
"step": 425
},
{
"epoch": 11.51,
"learning_rate": 2.282608695652174e-05,
"loss": 1.2692,
"step": 426
},
{
"epoch": 11.53,
"learning_rate": 2.2753623188405797e-05,
"loss": 1.2098,
"step": 427
},
{
"epoch": 11.56,
"learning_rate": 2.2681159420289858e-05,
"loss": 1.2321,
"step": 428
},
{
"epoch": 11.59,
"learning_rate": 2.2608695652173914e-05,
"loss": 1.2206,
"step": 429
},
{
"epoch": 11.61,
"learning_rate": 2.2536231884057975e-05,
"loss": 1.2684,
"step": 430
},
{
"epoch": 11.64,
"learning_rate": 2.246376811594203e-05,
"loss": 1.1974,
"step": 431
},
{
"epoch": 11.67,
"learning_rate": 2.239130434782609e-05,
"loss": 1.2054,
"step": 432
},
{
"epoch": 11.69,
"learning_rate": 2.2318840579710145e-05,
"loss": 1.2492,
"step": 433
},
{
"epoch": 11.72,
"learning_rate": 2.2246376811594205e-05,
"loss": 1.2817,
"step": 434
},
{
"epoch": 11.75,
"learning_rate": 2.2173913043478262e-05,
"loss": 1.25,
"step": 435
},
{
"epoch": 11.77,
"learning_rate": 2.2101449275362323e-05,
"loss": 1.2499,
"step": 436
},
{
"epoch": 11.8,
"learning_rate": 2.2028985507246376e-05,
"loss": 1.2213,
"step": 437
},
{
"epoch": 11.83,
"learning_rate": 2.1956521739130436e-05,
"loss": 1.2857,
"step": 438
},
{
"epoch": 11.85,
"learning_rate": 2.1884057971014493e-05,
"loss": 1.2746,
"step": 439
},
{
"epoch": 11.88,
"learning_rate": 2.1811594202898553e-05,
"loss": 1.2603,
"step": 440
},
{
"epoch": 11.91,
"learning_rate": 2.173913043478261e-05,
"loss": 1.2651,
"step": 441
},
{
"epoch": 11.93,
"learning_rate": 2.1666666666666667e-05,
"loss": 1.2772,
"step": 442
},
{
"epoch": 11.96,
"learning_rate": 2.1594202898550724e-05,
"loss": 1.2843,
"step": 443
},
{
"epoch": 11.99,
"learning_rate": 2.1521739130434784e-05,
"loss": 1.2199,
"step": 444
},
{
"epoch": 11.99,
"eval_accuracy": 0.7259977842029887,
"eval_loss": 1.273816704750061,
"eval_runtime": 13.2756,
"eval_samples_per_second": 37.362,
"eval_steps_per_second": 4.67,
"step": 444
},
{
"epoch": 12.03,
"learning_rate": 2.144927536231884e-05,
"loss": 1.8625,
"step": 445
},
{
"epoch": 12.05,
"learning_rate": 2.13768115942029e-05,
"loss": 1.2381,
"step": 446
},
{
"epoch": 12.08,
"learning_rate": 2.1304347826086958e-05,
"loss": 1.2111,
"step": 447
},
{
"epoch": 12.11,
"learning_rate": 2.1231884057971015e-05,
"loss": 1.2404,
"step": 448
},
{
"epoch": 12.13,
"learning_rate": 2.1159420289855072e-05,
"loss": 1.2764,
"step": 449
},
{
"epoch": 12.16,
"learning_rate": 2.1086956521739132e-05,
"loss": 1.2617,
"step": 450
},
{
"epoch": 12.19,
"learning_rate": 2.101449275362319e-05,
"loss": 1.2685,
"step": 451
},
{
"epoch": 12.21,
"learning_rate": 2.094202898550725e-05,
"loss": 1.1995,
"step": 452
},
{
"epoch": 12.24,
"learning_rate": 2.0869565217391303e-05,
"loss": 1.2554,
"step": 453
},
{
"epoch": 12.27,
"learning_rate": 2.0797101449275363e-05,
"loss": 1.2545,
"step": 454
},
{
"epoch": 12.29,
"learning_rate": 2.072463768115942e-05,
"loss": 1.2315,
"step": 455
},
{
"epoch": 12.32,
"learning_rate": 2.065217391304348e-05,
"loss": 1.2373,
"step": 456
},
{
"epoch": 12.35,
"learning_rate": 2.0579710144927537e-05,
"loss": 1.2745,
"step": 457
},
{
"epoch": 12.37,
"learning_rate": 2.0507246376811594e-05,
"loss": 1.2405,
"step": 458
},
{
"epoch": 12.4,
"learning_rate": 2.0434782608695654e-05,
"loss": 1.2467,
"step": 459
},
{
"epoch": 12.43,
"learning_rate": 2.036231884057971e-05,
"loss": 1.213,
"step": 460
},
{
"epoch": 12.45,
"learning_rate": 2.028985507246377e-05,
"loss": 1.2499,
"step": 461
},
{
"epoch": 12.48,
"learning_rate": 2.0217391304347828e-05,
"loss": 1.2601,
"step": 462
},
{
"epoch": 12.51,
"learning_rate": 2.0144927536231885e-05,
"loss": 1.2704,
"step": 463
},
{
"epoch": 12.53,
"learning_rate": 2.007246376811594e-05,
"loss": 1.2739,
"step": 464
},
{
"epoch": 12.56,
"learning_rate": 2e-05,
"loss": 1.1849,
"step": 465
},
{
"epoch": 12.59,
"learning_rate": 1.992753623188406e-05,
"loss": 1.1746,
"step": 466
},
{
"epoch": 12.61,
"learning_rate": 1.985507246376812e-05,
"loss": 1.2887,
"step": 467
},
{
"epoch": 12.64,
"learning_rate": 1.9782608695652176e-05,
"loss": 1.2067,
"step": 468
},
{
"epoch": 12.67,
"learning_rate": 1.9710144927536232e-05,
"loss": 1.2601,
"step": 469
},
{
"epoch": 12.69,
"learning_rate": 1.963768115942029e-05,
"loss": 1.2632,
"step": 470
},
{
"epoch": 12.72,
"learning_rate": 1.956521739130435e-05,
"loss": 1.2633,
"step": 471
},
{
"epoch": 12.75,
"learning_rate": 1.9492753623188406e-05,
"loss": 1.216,
"step": 472
},
{
"epoch": 12.77,
"learning_rate": 1.9420289855072467e-05,
"loss": 1.2608,
"step": 473
},
{
"epoch": 12.8,
"learning_rate": 1.9347826086956523e-05,
"loss": 1.2219,
"step": 474
},
{
"epoch": 12.83,
"learning_rate": 1.927536231884058e-05,
"loss": 1.2864,
"step": 475
},
{
"epoch": 12.85,
"learning_rate": 1.9202898550724637e-05,
"loss": 1.3147,
"step": 476
},
{
"epoch": 12.88,
"learning_rate": 1.9130434782608697e-05,
"loss": 1.2553,
"step": 477
},
{
"epoch": 12.91,
"learning_rate": 1.9057971014492754e-05,
"loss": 1.2906,
"step": 478
},
{
"epoch": 12.93,
"learning_rate": 1.8985507246376814e-05,
"loss": 1.2831,
"step": 479
},
{
"epoch": 12.96,
"learning_rate": 1.8913043478260868e-05,
"loss": 1.2721,
"step": 480
},
{
"epoch": 12.99,
"learning_rate": 1.8840579710144928e-05,
"loss": 1.206,
"step": 481
},
{
"epoch": 12.99,
"eval_accuracy": 0.7335030880918842,
"eval_loss": 1.2285895347595215,
"eval_runtime": 13.2581,
"eval_samples_per_second": 37.411,
"eval_steps_per_second": 4.676,
"step": 481
},
{
"epoch": 13.03,
"learning_rate": 1.8768115942028985e-05,
"loss": 1.8759,
"step": 482
},
{
"epoch": 13.05,
"learning_rate": 1.8695652173913045e-05,
"loss": 1.2655,
"step": 483
},
{
"epoch": 13.08,
"learning_rate": 1.8623188405797102e-05,
"loss": 1.218,
"step": 484
},
{
"epoch": 13.11,
"learning_rate": 1.855072463768116e-05,
"loss": 1.2632,
"step": 485
},
{
"epoch": 13.13,
"learning_rate": 1.8478260869565216e-05,
"loss": 1.2984,
"step": 486
},
{
"epoch": 13.16,
"learning_rate": 1.8405797101449276e-05,
"loss": 1.2791,
"step": 487
},
{
"epoch": 13.19,
"learning_rate": 1.8333333333333333e-05,
"loss": 1.2126,
"step": 488
},
{
"epoch": 13.21,
"learning_rate": 1.8260869565217393e-05,
"loss": 1.2503,
"step": 489
},
{
"epoch": 13.24,
"learning_rate": 1.818840579710145e-05,
"loss": 1.2168,
"step": 490
},
{
"epoch": 13.27,
"learning_rate": 1.8115942028985507e-05,
"loss": 1.3218,
"step": 491
},
{
"epoch": 13.29,
"learning_rate": 1.8043478260869567e-05,
"loss": 1.2605,
"step": 492
},
{
"epoch": 13.32,
"learning_rate": 1.7971014492753624e-05,
"loss": 1.2497,
"step": 493
},
{
"epoch": 13.35,
"learning_rate": 1.7898550724637684e-05,
"loss": 1.2989,
"step": 494
},
{
"epoch": 13.37,
"learning_rate": 1.782608695652174e-05,
"loss": 1.2328,
"step": 495
},
{
"epoch": 13.4,
"learning_rate": 1.7753623188405798e-05,
"loss": 1.2262,
"step": 496
},
{
"epoch": 13.43,
"learning_rate": 1.7681159420289855e-05,
"loss": 1.2803,
"step": 497
},
{
"epoch": 13.45,
"learning_rate": 1.7608695652173915e-05,
"loss": 1.273,
"step": 498
},
{
"epoch": 13.48,
"learning_rate": 1.7536231884057972e-05,
"loss": 1.2922,
"step": 499
},
{
"epoch": 13.51,
"learning_rate": 1.7463768115942032e-05,
"loss": 1.1986,
"step": 500
},
{
"epoch": 13.53,
"learning_rate": 1.739130434782609e-05,
"loss": 1.267,
"step": 501
},
{
"epoch": 13.56,
"learning_rate": 1.7318840579710146e-05,
"loss": 1.2887,
"step": 502
},
{
"epoch": 13.59,
"learning_rate": 1.7246376811594203e-05,
"loss": 1.1824,
"step": 503
},
{
"epoch": 13.61,
"learning_rate": 1.7173913043478263e-05,
"loss": 1.2688,
"step": 504
},
{
"epoch": 13.64,
"learning_rate": 1.710144927536232e-05,
"loss": 1.2429,
"step": 505
},
{
"epoch": 13.67,
"learning_rate": 1.702898550724638e-05,
"loss": 1.2028,
"step": 506
},
{
"epoch": 13.69,
"learning_rate": 1.6956521739130433e-05,
"loss": 1.2543,
"step": 507
},
{
"epoch": 13.72,
"learning_rate": 1.6884057971014494e-05,
"loss": 1.2463,
"step": 508
},
{
"epoch": 13.75,
"learning_rate": 1.681159420289855e-05,
"loss": 1.2003,
"step": 509
},
{
"epoch": 13.77,
"learning_rate": 1.673913043478261e-05,
"loss": 1.2947,
"step": 510
},
{
"epoch": 13.8,
"learning_rate": 1.6666666666666667e-05,
"loss": 1.2499,
"step": 511
},
{
"epoch": 13.83,
"learning_rate": 1.6594202898550724e-05,
"loss": 1.2518,
"step": 512
},
{
"epoch": 13.85,
"learning_rate": 1.652173913043478e-05,
"loss": 1.2409,
"step": 513
},
{
"epoch": 13.88,
"learning_rate": 1.644927536231884e-05,
"loss": 1.295,
"step": 514
},
{
"epoch": 13.91,
"learning_rate": 1.6376811594202898e-05,
"loss": 1.2678,
"step": 515
},
{
"epoch": 13.93,
"learning_rate": 1.630434782608696e-05,
"loss": 1.217,
"step": 516
},
{
"epoch": 13.96,
"learning_rate": 1.6231884057971015e-05,
"loss": 1.2197,
"step": 517
},
{
"epoch": 13.99,
"learning_rate": 1.6159420289855072e-05,
"loss": 1.221,
"step": 518
},
{
"epoch": 13.99,
"eval_accuracy": 0.7327190178115681,
"eval_loss": 1.2421268224716187,
"eval_runtime": 13.279,
"eval_samples_per_second": 37.352,
"eval_steps_per_second": 4.669,
"step": 518
},
{
"epoch": 14.03,
"learning_rate": 1.608695652173913e-05,
"loss": 1.834,
"step": 519
},
{
"epoch": 14.05,
"learning_rate": 1.601449275362319e-05,
"loss": 1.2727,
"step": 520
},
{
"epoch": 14.08,
"learning_rate": 1.5942028985507246e-05,
"loss": 1.2753,
"step": 521
},
{
"epoch": 14.11,
"learning_rate": 1.5869565217391306e-05,
"loss": 1.2137,
"step": 522
},
{
"epoch": 14.13,
"learning_rate": 1.5797101449275363e-05,
"loss": 1.2626,
"step": 523
},
{
"epoch": 14.16,
"learning_rate": 1.572463768115942e-05,
"loss": 1.2518,
"step": 524
},
{
"epoch": 14.19,
"learning_rate": 1.565217391304348e-05,
"loss": 1.2167,
"step": 525
},
{
"epoch": 14.21,
"learning_rate": 1.5579710144927537e-05,
"loss": 1.1935,
"step": 526
},
{
"epoch": 14.24,
"learning_rate": 1.5507246376811597e-05,
"loss": 1.2374,
"step": 527
},
{
"epoch": 14.27,
"learning_rate": 1.5434782608695654e-05,
"loss": 1.2236,
"step": 528
},
{
"epoch": 14.29,
"learning_rate": 1.536231884057971e-05,
"loss": 1.2117,
"step": 529
},
{
"epoch": 14.32,
"learning_rate": 1.5289855072463768e-05,
"loss": 1.3012,
"step": 530
},
{
"epoch": 14.35,
"learning_rate": 1.5217391304347828e-05,
"loss": 1.3001,
"step": 531
},
{
"epoch": 14.37,
"learning_rate": 1.5144927536231885e-05,
"loss": 1.198,
"step": 532
},
{
"epoch": 14.4,
"learning_rate": 1.5072463768115944e-05,
"loss": 1.2198,
"step": 533
},
{
"epoch": 14.43,
"learning_rate": 1.5e-05,
"loss": 1.2423,
"step": 534
},
{
"epoch": 14.45,
"learning_rate": 1.4927536231884059e-05,
"loss": 1.2475,
"step": 535
},
{
"epoch": 14.48,
"learning_rate": 1.4855072463768116e-05,
"loss": 1.2687,
"step": 536
},
{
"epoch": 14.51,
"learning_rate": 1.4782608695652176e-05,
"loss": 1.2282,
"step": 537
},
{
"epoch": 14.53,
"learning_rate": 1.4710144927536231e-05,
"loss": 1.2676,
"step": 538
},
{
"epoch": 14.56,
"learning_rate": 1.4637681159420291e-05,
"loss": 1.3138,
"step": 539
},
{
"epoch": 14.59,
"learning_rate": 1.4565217391304348e-05,
"loss": 1.2945,
"step": 540
},
{
"epoch": 14.61,
"learning_rate": 1.4492753623188407e-05,
"loss": 1.2479,
"step": 541
},
{
"epoch": 14.64,
"learning_rate": 1.4420289855072464e-05,
"loss": 1.2788,
"step": 542
},
{
"epoch": 14.67,
"learning_rate": 1.4347826086956522e-05,
"loss": 1.2951,
"step": 543
},
{
"epoch": 14.69,
"learning_rate": 1.4275362318840579e-05,
"loss": 1.2326,
"step": 544
},
{
"epoch": 14.72,
"learning_rate": 1.420289855072464e-05,
"loss": 1.2256,
"step": 545
},
{
"epoch": 14.75,
"learning_rate": 1.4130434782608694e-05,
"loss": 1.213,
"step": 546
},
{
"epoch": 14.77,
"learning_rate": 1.4057971014492755e-05,
"loss": 1.2928,
"step": 547
},
{
"epoch": 14.8,
"learning_rate": 1.3985507246376811e-05,
"loss": 1.2372,
"step": 548
},
{
"epoch": 14.83,
"learning_rate": 1.391304347826087e-05,
"loss": 1.2561,
"step": 549
},
{
"epoch": 14.85,
"learning_rate": 1.3840579710144927e-05,
"loss": 1.23,
"step": 550
},
{
"epoch": 14.88,
"learning_rate": 1.3768115942028985e-05,
"loss": 1.2413,
"step": 551
},
{
"epoch": 14.91,
"learning_rate": 1.3695652173913042e-05,
"loss": 1.2263,
"step": 552
},
{
"epoch": 14.93,
"learning_rate": 1.3623188405797103e-05,
"loss": 1.2865,
"step": 553
},
{
"epoch": 14.96,
"learning_rate": 1.3550724637681161e-05,
"loss": 1.2619,
"step": 554
},
{
"epoch": 14.99,
"learning_rate": 1.3478260869565218e-05,
"loss": 1.2062,
"step": 555
},
{
"epoch": 14.99,
"eval_accuracy": 0.732803299595691,
"eval_loss": 1.2402293682098389,
"eval_runtime": 13.2984,
"eval_samples_per_second": 37.298,
"eval_steps_per_second": 4.662,
"step": 555
},
{
"epoch": 15.03,
"learning_rate": 1.3405797101449276e-05,
"loss": 1.8577,
"step": 556
},
{
"epoch": 15.05,
"learning_rate": 1.3333333333333333e-05,
"loss": 1.2946,
"step": 557
},
{
"epoch": 15.08,
"learning_rate": 1.3260869565217394e-05,
"loss": 1.2822,
"step": 558
},
{
"epoch": 15.11,
"learning_rate": 1.318840579710145e-05,
"loss": 1.2716,
"step": 559
},
{
"epoch": 15.13,
"learning_rate": 1.3115942028985509e-05,
"loss": 1.2188,
"step": 560
},
{
"epoch": 15.16,
"learning_rate": 1.3043478260869566e-05,
"loss": 1.2308,
"step": 561
},
{
"epoch": 15.19,
"learning_rate": 1.2971014492753624e-05,
"loss": 1.2465,
"step": 562
},
{
"epoch": 15.21,
"learning_rate": 1.2898550724637681e-05,
"loss": 1.2039,
"step": 563
},
{
"epoch": 15.24,
"learning_rate": 1.2826086956521741e-05,
"loss": 1.2685,
"step": 564
},
{
"epoch": 15.27,
"learning_rate": 1.2753623188405797e-05,
"loss": 1.224,
"step": 565
},
{
"epoch": 15.29,
"learning_rate": 1.2681159420289857e-05,
"loss": 1.2462,
"step": 566
},
{
"epoch": 15.32,
"learning_rate": 1.2608695652173914e-05,
"loss": 1.2162,
"step": 567
},
{
"epoch": 15.35,
"learning_rate": 1.2536231884057972e-05,
"loss": 1.1778,
"step": 568
},
{
"epoch": 15.37,
"learning_rate": 1.246376811594203e-05,
"loss": 1.2065,
"step": 569
},
{
"epoch": 15.4,
"learning_rate": 1.2391304347826088e-05,
"loss": 1.2536,
"step": 570
},
{
"epoch": 15.43,
"learning_rate": 1.2318840579710146e-05,
"loss": 1.2198,
"step": 571
},
{
"epoch": 15.45,
"learning_rate": 1.2246376811594205e-05,
"loss": 1.242,
"step": 572
},
{
"epoch": 15.48,
"learning_rate": 1.2173913043478261e-05,
"loss": 1.2376,
"step": 573
},
{
"epoch": 15.51,
"learning_rate": 1.210144927536232e-05,
"loss": 1.2419,
"step": 574
},
{
"epoch": 15.53,
"learning_rate": 1.2028985507246379e-05,
"loss": 1.2673,
"step": 575
},
{
"epoch": 15.56,
"learning_rate": 1.1956521739130435e-05,
"loss": 1.2265,
"step": 576
},
{
"epoch": 15.59,
"learning_rate": 1.1884057971014494e-05,
"loss": 1.2708,
"step": 577
},
{
"epoch": 15.61,
"learning_rate": 1.181159420289855e-05,
"loss": 1.2264,
"step": 578
},
{
"epoch": 15.64,
"learning_rate": 1.173913043478261e-05,
"loss": 1.2257,
"step": 579
},
{
"epoch": 15.67,
"learning_rate": 1.1666666666666668e-05,
"loss": 1.1863,
"step": 580
},
{
"epoch": 15.69,
"learning_rate": 1.1594202898550725e-05,
"loss": 1.1775,
"step": 581
},
{
"epoch": 15.72,
"learning_rate": 1.1521739130434783e-05,
"loss": 1.2742,
"step": 582
},
{
"epoch": 15.75,
"learning_rate": 1.1449275362318842e-05,
"loss": 1.2685,
"step": 583
},
{
"epoch": 15.77,
"learning_rate": 1.1376811594202899e-05,
"loss": 1.2752,
"step": 584
},
{
"epoch": 15.8,
"learning_rate": 1.1304347826086957e-05,
"loss": 1.2163,
"step": 585
},
{
"epoch": 15.83,
"learning_rate": 1.1231884057971016e-05,
"loss": 1.279,
"step": 586
},
{
"epoch": 15.85,
"learning_rate": 1.1159420289855073e-05,
"loss": 1.2633,
"step": 587
},
{
"epoch": 15.88,
"learning_rate": 1.1086956521739131e-05,
"loss": 1.2338,
"step": 588
},
{
"epoch": 15.91,
"learning_rate": 1.1014492753623188e-05,
"loss": 1.2283,
"step": 589
},
{
"epoch": 15.93,
"learning_rate": 1.0942028985507247e-05,
"loss": 1.2701,
"step": 590
},
{
"epoch": 15.96,
"learning_rate": 1.0869565217391305e-05,
"loss": 1.2949,
"step": 591
},
{
"epoch": 15.99,
"learning_rate": 1.0797101449275362e-05,
"loss": 1.2305,
"step": 592
},
{
"epoch": 15.99,
"eval_accuracy": 0.7307723434675875,
"eval_loss": 1.247312307357788,
"eval_runtime": 13.2755,
"eval_samples_per_second": 37.362,
"eval_steps_per_second": 4.67,
"step": 592
},
{
"epoch": 16.03,
"learning_rate": 1.072463768115942e-05,
"loss": 1.8458,
"step": 593
},
{
"epoch": 16.05,
"learning_rate": 1.0652173913043479e-05,
"loss": 1.1802,
"step": 594
},
{
"epoch": 16.08,
"learning_rate": 1.0579710144927536e-05,
"loss": 1.2814,
"step": 595
},
{
"epoch": 16.11,
"learning_rate": 1.0507246376811594e-05,
"loss": 1.2367,
"step": 596
},
{
"epoch": 16.13,
"learning_rate": 1.0434782608695651e-05,
"loss": 1.2374,
"step": 597
},
{
"epoch": 16.16,
"learning_rate": 1.036231884057971e-05,
"loss": 1.3441,
"step": 598
},
{
"epoch": 16.19,
"learning_rate": 1.0289855072463768e-05,
"loss": 1.2469,
"step": 599
},
{
"epoch": 16.21,
"learning_rate": 1.0217391304347827e-05,
"loss": 1.2178,
"step": 600
},
{
"epoch": 16.24,
"learning_rate": 1.0144927536231885e-05,
"loss": 1.2353,
"step": 601
},
{
"epoch": 16.27,
"learning_rate": 1.0072463768115942e-05,
"loss": 1.2735,
"step": 602
},
{
"epoch": 16.29,
"learning_rate": 1e-05,
"loss": 1.2322,
"step": 603
},
{
"epoch": 16.32,
"learning_rate": 9.92753623188406e-06,
"loss": 1.2349,
"step": 604
},
{
"epoch": 16.35,
"learning_rate": 9.855072463768116e-06,
"loss": 1.2346,
"step": 605
},
{
"epoch": 16.37,
"learning_rate": 9.782608695652175e-06,
"loss": 1.2412,
"step": 606
},
{
"epoch": 16.4,
"learning_rate": 9.710144927536233e-06,
"loss": 1.2781,
"step": 607
},
{
"epoch": 16.43,
"learning_rate": 9.63768115942029e-06,
"loss": 1.2516,
"step": 608
},
{
"epoch": 16.45,
"learning_rate": 9.565217391304349e-06,
"loss": 1.1951,
"step": 609
},
{
"epoch": 16.48,
"learning_rate": 9.492753623188407e-06,
"loss": 1.2746,
"step": 610
},
{
"epoch": 16.51,
"learning_rate": 9.420289855072464e-06,
"loss": 1.2231,
"step": 611
},
{
"epoch": 16.53,
"learning_rate": 9.347826086956523e-06,
"loss": 1.2761,
"step": 612
},
{
"epoch": 16.56,
"learning_rate": 9.27536231884058e-06,
"loss": 1.1835,
"step": 613
},
{
"epoch": 16.59,
"learning_rate": 9.202898550724638e-06,
"loss": 1.2439,
"step": 614
},
{
"epoch": 16.61,
"learning_rate": 9.130434782608697e-06,
"loss": 1.2909,
"step": 615
},
{
"epoch": 16.64,
"learning_rate": 9.057971014492753e-06,
"loss": 1.2473,
"step": 616
},
{
"epoch": 16.67,
"learning_rate": 8.985507246376812e-06,
"loss": 1.2172,
"step": 617
},
{
"epoch": 16.69,
"learning_rate": 8.91304347826087e-06,
"loss": 1.2669,
"step": 618
},
{
"epoch": 16.72,
"learning_rate": 8.840579710144927e-06,
"loss": 1.2826,
"step": 619
},
{
"epoch": 16.75,
"learning_rate": 8.768115942028986e-06,
"loss": 1.1676,
"step": 620
},
{
"epoch": 16.77,
"learning_rate": 8.695652173913044e-06,
"loss": 1.2068,
"step": 621
},
{
"epoch": 16.8,
"learning_rate": 8.623188405797101e-06,
"loss": 1.2571,
"step": 622
},
{
"epoch": 16.83,
"learning_rate": 8.55072463768116e-06,
"loss": 1.2138,
"step": 623
},
{
"epoch": 16.85,
"learning_rate": 8.478260869565217e-06,
"loss": 1.1783,
"step": 624
},
{
"epoch": 16.88,
"learning_rate": 8.405797101449275e-06,
"loss": 1.2801,
"step": 625
},
{
"epoch": 16.91,
"learning_rate": 8.333333333333334e-06,
"loss": 1.2122,
"step": 626
},
{
"epoch": 16.93,
"learning_rate": 8.26086956521739e-06,
"loss": 1.2112,
"step": 627
},
{
"epoch": 16.96,
"learning_rate": 8.188405797101449e-06,
"loss": 1.2542,
"step": 628
},
{
"epoch": 16.99,
"learning_rate": 8.115942028985508e-06,
"loss": 1.2426,
"step": 629
},
{
"epoch": 16.99,
"eval_accuracy": 0.7318157181571816,
"eval_loss": 1.2249630689620972,
"eval_runtime": 13.2585,
"eval_samples_per_second": 37.41,
"eval_steps_per_second": 4.676,
"step": 629
},
{
"epoch": 17.03,
"learning_rate": 8.043478260869565e-06,
"loss": 1.8211,
"step": 630
},
{
"epoch": 17.05,
"learning_rate": 7.971014492753623e-06,
"loss": 1.2233,
"step": 631
},
{
"epoch": 17.08,
"learning_rate": 7.898550724637682e-06,
"loss": 1.246,
"step": 632
},
{
"epoch": 17.11,
"learning_rate": 7.82608695652174e-06,
"loss": 1.2303,
"step": 633
},
{
"epoch": 17.13,
"learning_rate": 7.753623188405799e-06,
"loss": 1.2127,
"step": 634
},
{
"epoch": 17.16,
"learning_rate": 7.681159420289856e-06,
"loss": 1.1923,
"step": 635
},
{
"epoch": 17.19,
"learning_rate": 7.608695652173914e-06,
"loss": 1.2247,
"step": 636
},
{
"epoch": 17.21,
"learning_rate": 7.536231884057972e-06,
"loss": 1.2365,
"step": 637
},
{
"epoch": 17.24,
"learning_rate": 7.4637681159420295e-06,
"loss": 1.1985,
"step": 638
},
{
"epoch": 17.27,
"learning_rate": 7.391304347826088e-06,
"loss": 1.2298,
"step": 639
},
{
"epoch": 17.29,
"learning_rate": 7.318840579710146e-06,
"loss": 1.1936,
"step": 640
},
{
"epoch": 17.32,
"learning_rate": 7.246376811594203e-06,
"loss": 1.2108,
"step": 641
},
{
"epoch": 17.35,
"learning_rate": 7.173913043478261e-06,
"loss": 1.3043,
"step": 642
},
{
"epoch": 17.37,
"learning_rate": 7.10144927536232e-06,
"loss": 1.2297,
"step": 643
},
{
"epoch": 17.4,
"learning_rate": 7.028985507246377e-06,
"loss": 1.2587,
"step": 644
},
{
"epoch": 17.43,
"learning_rate": 6.956521739130435e-06,
"loss": 1.2347,
"step": 645
},
{
"epoch": 17.45,
"learning_rate": 6.884057971014493e-06,
"loss": 1.2355,
"step": 646
},
{
"epoch": 17.48,
"learning_rate": 6.811594202898551e-06,
"loss": 1.2061,
"step": 647
},
{
"epoch": 17.51,
"learning_rate": 6.739130434782609e-06,
"loss": 1.2036,
"step": 648
},
{
"epoch": 17.53,
"learning_rate": 6.666666666666667e-06,
"loss": 1.2495,
"step": 649
},
{
"epoch": 17.56,
"learning_rate": 6.594202898550725e-06,
"loss": 1.216,
"step": 650
},
{
"epoch": 17.59,
"learning_rate": 6.521739130434783e-06,
"loss": 1.223,
"step": 651
},
{
"epoch": 17.61,
"learning_rate": 6.449275362318841e-06,
"loss": 1.2645,
"step": 652
},
{
"epoch": 17.64,
"learning_rate": 6.376811594202898e-06,
"loss": 1.1786,
"step": 653
},
{
"epoch": 17.67,
"learning_rate": 6.304347826086957e-06,
"loss": 1.2447,
"step": 654
},
{
"epoch": 17.69,
"learning_rate": 6.231884057971015e-06,
"loss": 1.2604,
"step": 655
},
{
"epoch": 17.72,
"learning_rate": 6.159420289855073e-06,
"loss": 1.2098,
"step": 656
},
{
"epoch": 17.75,
"learning_rate": 6.086956521739131e-06,
"loss": 1.2294,
"step": 657
},
{
"epoch": 17.77,
"learning_rate": 6.014492753623189e-06,
"loss": 1.2241,
"step": 658
},
{
"epoch": 17.8,
"learning_rate": 5.942028985507247e-06,
"loss": 1.2454,
"step": 659
},
{
"epoch": 17.83,
"learning_rate": 5.869565217391305e-06,
"loss": 1.2278,
"step": 660
},
{
"epoch": 17.85,
"learning_rate": 5.797101449275362e-06,
"loss": 1.2871,
"step": 661
},
{
"epoch": 17.88,
"learning_rate": 5.724637681159421e-06,
"loss": 1.2772,
"step": 662
},
{
"epoch": 17.91,
"learning_rate": 5.652173913043479e-06,
"loss": 1.2415,
"step": 663
},
{
"epoch": 17.93,
"learning_rate": 5.579710144927536e-06,
"loss": 1.1829,
"step": 664
},
{
"epoch": 17.96,
"learning_rate": 5.507246376811594e-06,
"loss": 1.228,
"step": 665
},
{
"epoch": 17.99,
"learning_rate": 5.4347826086956525e-06,
"loss": 1.2096,
"step": 666
},
{
"epoch": 17.99,
"eval_accuracy": 0.7352733398543636,
"eval_loss": 1.2186108827590942,
"eval_runtime": 13.2382,
"eval_samples_per_second": 37.467,
"eval_steps_per_second": 4.683,
"step": 666
},
{
"epoch": 18.03,
"learning_rate": 5.36231884057971e-06,
"loss": 1.812,
"step": 667
},
{
"epoch": 18.05,
"learning_rate": 5.289855072463768e-06,
"loss": 1.1976,
"step": 668
},
{
"epoch": 18.08,
"learning_rate": 5.217391304347826e-06,
"loss": 1.2782,
"step": 669
},
{
"epoch": 18.11,
"learning_rate": 5.144927536231884e-06,
"loss": 1.2505,
"step": 670
},
{
"epoch": 18.13,
"learning_rate": 5.072463768115943e-06,
"loss": 1.2352,
"step": 671
},
{
"epoch": 18.16,
"learning_rate": 5e-06,
"loss": 1.2544,
"step": 672
},
{
"epoch": 18.19,
"learning_rate": 4.927536231884058e-06,
"loss": 1.1739,
"step": 673
},
{
"epoch": 18.21,
"learning_rate": 4.855072463768117e-06,
"loss": 1.2626,
"step": 674
},
{
"epoch": 18.24,
"learning_rate": 4.782608695652174e-06,
"loss": 1.2034,
"step": 675
},
{
"epoch": 18.27,
"learning_rate": 4.710144927536232e-06,
"loss": 1.2818,
"step": 676
},
{
"epoch": 18.29,
"learning_rate": 4.63768115942029e-06,
"loss": 1.2388,
"step": 677
},
{
"epoch": 18.32,
"learning_rate": 4.565217391304348e-06,
"loss": 1.239,
"step": 678
},
{
"epoch": 18.35,
"learning_rate": 4.492753623188406e-06,
"loss": 1.1827,
"step": 679
},
{
"epoch": 18.37,
"learning_rate": 4.420289855072464e-06,
"loss": 1.1712,
"step": 680
},
{
"epoch": 18.4,
"learning_rate": 4.347826086956522e-06,
"loss": 1.2147,
"step": 681
},
{
"epoch": 18.43,
"learning_rate": 4.27536231884058e-06,
"loss": 1.2106,
"step": 682
},
{
"epoch": 18.45,
"learning_rate": 4.202898550724638e-06,
"loss": 1.2296,
"step": 683
},
{
"epoch": 18.48,
"learning_rate": 4.130434782608695e-06,
"loss": 1.2551,
"step": 684
},
{
"epoch": 18.51,
"learning_rate": 4.057971014492754e-06,
"loss": 1.235,
"step": 685
},
{
"epoch": 18.53,
"learning_rate": 3.9855072463768115e-06,
"loss": 1.2341,
"step": 686
},
{
"epoch": 18.56,
"learning_rate": 3.91304347826087e-06,
"loss": 1.189,
"step": 687
},
{
"epoch": 18.59,
"learning_rate": 3.840579710144928e-06,
"loss": 1.2241,
"step": 688
},
{
"epoch": 18.61,
"learning_rate": 3.768115942028986e-06,
"loss": 1.2627,
"step": 689
},
{
"epoch": 18.64,
"learning_rate": 3.695652173913044e-06,
"loss": 1.2259,
"step": 690
},
{
"epoch": 18.67,
"learning_rate": 3.6231884057971017e-06,
"loss": 1.2247,
"step": 691
},
{
"epoch": 18.69,
"learning_rate": 3.55072463768116e-06,
"loss": 1.2493,
"step": 692
},
{
"epoch": 18.72,
"learning_rate": 3.4782608695652175e-06,
"loss": 1.1931,
"step": 693
},
{
"epoch": 18.75,
"learning_rate": 3.4057971014492756e-06,
"loss": 1.2441,
"step": 694
},
{
"epoch": 18.77,
"learning_rate": 3.3333333333333333e-06,
"loss": 1.1884,
"step": 695
},
{
"epoch": 18.8,
"learning_rate": 3.2608695652173914e-06,
"loss": 1.1858,
"step": 696
},
{
"epoch": 18.83,
"learning_rate": 3.188405797101449e-06,
"loss": 1.2114,
"step": 697
},
{
"epoch": 18.85,
"learning_rate": 3.1159420289855077e-06,
"loss": 1.2482,
"step": 698
},
{
"epoch": 18.88,
"learning_rate": 3.0434782608695654e-06,
"loss": 1.2253,
"step": 699
},
{
"epoch": 18.91,
"learning_rate": 2.9710144927536235e-06,
"loss": 1.2292,
"step": 700
},
{
"epoch": 18.93,
"learning_rate": 2.898550724637681e-06,
"loss": 1.2396,
"step": 701
},
{
"epoch": 18.96,
"learning_rate": 2.8260869565217393e-06,
"loss": 1.1881,
"step": 702
},
{
"epoch": 18.99,
"learning_rate": 2.753623188405797e-06,
"loss": 1.1961,
"step": 703
},
{
"epoch": 18.99,
"eval_accuracy": 0.7360741986223355,
"eval_loss": 1.2214456796646118,
"eval_runtime": 13.2148,
"eval_samples_per_second": 37.534,
"eval_steps_per_second": 4.692,
"step": 703
},
{
"epoch": 19.03,
"learning_rate": 2.681159420289855e-06,
"loss": 1.8177,
"step": 704
},
{
"epoch": 19.05,
"learning_rate": 2.608695652173913e-06,
"loss": 1.2484,
"step": 705
},
{
"epoch": 19.08,
"learning_rate": 2.5362318840579714e-06,
"loss": 1.2075,
"step": 706
},
{
"epoch": 19.11,
"learning_rate": 2.463768115942029e-06,
"loss": 1.244,
"step": 707
},
{
"epoch": 19.13,
"learning_rate": 2.391304347826087e-06,
"loss": 1.2501,
"step": 708
},
{
"epoch": 19.16,
"learning_rate": 2.318840579710145e-06,
"loss": 1.2372,
"step": 709
},
{
"epoch": 19.19,
"learning_rate": 2.246376811594203e-06,
"loss": 1.212,
"step": 710
},
{
"epoch": 19.21,
"learning_rate": 2.173913043478261e-06,
"loss": 1.2428,
"step": 711
},
{
"epoch": 19.24,
"learning_rate": 2.101449275362319e-06,
"loss": 1.2565,
"step": 712
},
{
"epoch": 19.27,
"learning_rate": 2.028985507246377e-06,
"loss": 1.2166,
"step": 713
},
{
"epoch": 19.29,
"learning_rate": 1.956521739130435e-06,
"loss": 1.267,
"step": 714
},
{
"epoch": 19.32,
"learning_rate": 1.884057971014493e-06,
"loss": 1.1961,
"step": 715
},
{
"epoch": 19.35,
"learning_rate": 1.8115942028985508e-06,
"loss": 1.2229,
"step": 716
},
{
"epoch": 19.37,
"learning_rate": 1.7391304347826088e-06,
"loss": 1.246,
"step": 717
},
{
"epoch": 19.4,
"learning_rate": 1.6666666666666667e-06,
"loss": 1.2767,
"step": 718
},
{
"epoch": 19.43,
"learning_rate": 1.5942028985507246e-06,
"loss": 1.1875,
"step": 719
},
{
"epoch": 19.45,
"learning_rate": 1.5217391304347827e-06,
"loss": 1.2265,
"step": 720
},
{
"epoch": 19.48,
"learning_rate": 1.4492753623188406e-06,
"loss": 1.2228,
"step": 721
},
{
"epoch": 19.51,
"learning_rate": 1.3768115942028985e-06,
"loss": 1.2094,
"step": 722
},
{
"epoch": 19.53,
"learning_rate": 1.3043478260869564e-06,
"loss": 1.216,
"step": 723
},
{
"epoch": 19.56,
"learning_rate": 1.2318840579710145e-06,
"loss": 1.249,
"step": 724
},
{
"epoch": 19.59,
"learning_rate": 1.1594202898550724e-06,
"loss": 1.2173,
"step": 725
},
{
"epoch": 19.61,
"learning_rate": 1.0869565217391306e-06,
"loss": 1.2106,
"step": 726
},
{
"epoch": 19.64,
"learning_rate": 1.0144927536231885e-06,
"loss": 1.2393,
"step": 727
},
{
"epoch": 19.67,
"learning_rate": 9.420289855072465e-07,
"loss": 1.2367,
"step": 728
},
{
"epoch": 19.69,
"learning_rate": 8.695652173913044e-07,
"loss": 1.2037,
"step": 729
},
{
"epoch": 19.72,
"learning_rate": 7.971014492753623e-07,
"loss": 1.2176,
"step": 730
},
{
"epoch": 19.75,
"learning_rate": 7.246376811594203e-07,
"loss": 1.1534,
"step": 731
},
{
"epoch": 19.77,
"learning_rate": 6.521739130434782e-07,
"loss": 1.2168,
"step": 732
},
{
"epoch": 19.8,
"learning_rate": 5.797101449275362e-07,
"loss": 1.203,
"step": 733
},
{
"epoch": 19.83,
"learning_rate": 5.072463768115942e-07,
"loss": 1.2523,
"step": 734
},
{
"epoch": 19.85,
"learning_rate": 4.347826086956522e-07,
"loss": 1.2665,
"step": 735
},
{
"epoch": 19.88,
"learning_rate": 3.6231884057971015e-07,
"loss": 1.2114,
"step": 736
},
{
"epoch": 19.91,
"learning_rate": 2.898550724637681e-07,
"loss": 1.2425,
"step": 737
},
{
"epoch": 19.93,
"learning_rate": 2.173913043478261e-07,
"loss": 1.3178,
"step": 738
},
{
"epoch": 19.96,
"learning_rate": 1.4492753623188405e-07,
"loss": 1.2353,
"step": 739
},
{
"epoch": 19.99,
"learning_rate": 7.246376811594203e-08,
"loss": 1.2136,
"step": 740
},
{
"epoch": 19.99,
"eval_accuracy": 0.7311184760057123,
"eval_loss": 1.250640869140625,
"eval_runtime": 13.2938,
"eval_samples_per_second": 37.311,
"eval_steps_per_second": 4.664,
"step": 740
},
{
"epoch": 19.99,
"step": 740,
"total_flos": 2.524663139915981e+16,
"train_loss": 1.3203882475157043,
"train_runtime": 9311.1992,
"train_samples_per_second": 10.306,
"train_steps_per_second": 0.079
}
],
"max_steps": 740,
"num_train_epochs": 20,
"total_flos": 2.524663139915981e+16,
"trial_name": null,
"trial_params": null
}