{
  "best_metric": 1.0950939655303955,
  "best_model_checkpoint": "/tmp/model/checkpoint-112",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 112,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 3.5714285714285714e-06,
      "loss": 1.0986,
      "step": 1
    },
    {
      "epoch": 0.07,
      "learning_rate": 7.142857142857143e-06,
      "loss": 1.0986,
      "step": 2
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.0714285714285714e-05,
      "loss": 1.0988,
      "step": 3
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 1.0995,
      "step": 4
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.7857142857142855e-05,
      "loss": 1.099,
      "step": 5
    },
    {
      "epoch": 0.21,
      "learning_rate": 2.1428571428571428e-05,
      "loss": 1.0999,
      "step": 6
    },
    {
      "epoch": 0.25,
      "learning_rate": 2.5e-05,
      "loss": 1.0976,
      "step": 7
    },
    {
      "epoch": 0.29,
      "learning_rate": 2.857142857142857e-05,
      "loss": 1.0999,
      "step": 8
    },
    {
      "epoch": 0.32,
      "learning_rate": 3.214285714285714e-05,
      "loss": 1.0993,
      "step": 9
    },
    {
      "epoch": 0.36,
      "learning_rate": 3.571428571428571e-05,
      "loss": 1.1003,
      "step": 10
    },
    {
      "epoch": 0.39,
      "learning_rate": 3.928571428571428e-05,
      "loss": 1.0971,
      "step": 11
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 1.096,
      "step": 12
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.642857142857143e-05,
      "loss": 1.0932,
      "step": 13
    },
    {
      "epoch": 0.5,
      "learning_rate": 5e-05,
      "loss": 1.1029,
      "step": 14
    },
    {
      "epoch": 0.54,
      "learning_rate": 5.357142857142857e-05,
      "loss": 1.0879,
      "step": 15
    },
    {
      "epoch": 0.57,
      "learning_rate": 5.714285714285714e-05,
      "loss": 1.1036,
      "step": 16
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.0714285714285715e-05,
      "loss": 1.1073,
      "step": 17
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.428571428571427e-05,
      "loss": 1.1034,
      "step": 18
    },
    {
      "epoch": 0.68,
      "learning_rate": 6.785714285714285e-05,
      "loss": 1.1123,
      "step": 19
    },
    {
      "epoch": 0.71,
      "learning_rate": 7.142857142857142e-05,
      "loss": 1.1154,
      "step": 20
    },
    {
      "epoch": 0.75,
      "learning_rate": 7.5e-05,
      "loss": 1.102,
      "step": 21
    },
    {
      "epoch": 0.79,
      "learning_rate": 7.857142857142857e-05,
      "loss": 1.1162,
      "step": 22
    },
    {
      "epoch": 0.82,
      "learning_rate": 8.214285714285714e-05,
      "loss": 1.1164,
      "step": 23
    },
    {
      "epoch": 0.86,
      "learning_rate": 8.571428571428571e-05,
      "loss": 1.0999,
      "step": 24
    },
    {
      "epoch": 0.89,
      "learning_rate": 8.928571428571429e-05,
      "loss": 1.083,
      "step": 25
    },
    {
      "epoch": 0.93,
      "learning_rate": 9.285714285714286e-05,
      "loss": 1.112,
      "step": 26
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.642857142857143e-05,
      "loss": 1.086,
      "step": 27
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001,
      "loss": 1.0991,
      "step": 28
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.2857142857142857,
      "eval_f1_macro": 0.14814814814814817,
      "eval_f1_micro": 0.2857142857142857,
      "eval_f1_weighted": 0.126984126984127,
      "eval_loss": 1.1046772003173828,
      "eval_precision_macro": 0.09523809523809523,
      "eval_precision_micro": 0.2857142857142857,
      "eval_precision_weighted": 0.08163265306122448,
      "eval_recall_macro": 0.3333333333333333,
      "eval_recall_micro": 0.2857142857142857,
      "eval_recall_weighted": 0.2857142857142857,
      "eval_runtime": 1.0364,
      "eval_samples_per_second": 6.754,
      "eval_steps_per_second": 3.859,
      "step": 28
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00010357142857142858,
      "loss": 1.1119,
      "step": 29
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00010714285714285714,
      "loss": 1.0864,
      "step": 30
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00011071428571428571,
      "loss": 1.0979,
      "step": 31
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00011428571428571428,
      "loss": 1.0904,
      "step": 32
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00011785714285714286,
      "loss": 1.0861,
      "step": 33
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00012142857142857143,
      "loss": 1.1155,
      "step": 34
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.000125,
      "loss": 1.0844,
      "step": 35
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00012857142857142855,
      "loss": 1.1182,
      "step": 36
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00013214285714285715,
      "loss": 1.1133,
      "step": 37
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0001357142857142857,
      "loss": 1.1152,
      "step": 38
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0001392857142857143,
      "loss": 1.1101,
      "step": 39
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00014285714285714284,
      "loss": 1.1064,
      "step": 40
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00014642857142857144,
      "loss": 1.1021,
      "step": 41
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00015,
      "loss": 1.1067,
      "step": 42
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0001535714285714286,
      "loss": 1.0951,
      "step": 43
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00015714285714285713,
      "loss": 1.0946,
      "step": 44
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00016071428571428573,
      "loss": 1.0972,
      "step": 45
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.00016428571428571428,
      "loss": 1.1148,
      "step": 46
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00016785714285714285,
      "loss": 1.1223,
      "step": 47
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00017142857142857143,
      "loss": 1.0951,
      "step": 48
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.000175,
      "loss": 1.1189,
      "step": 49
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00017857142857142857,
      "loss": 1.1219,
      "step": 50
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00018214285714285714,
      "loss": 1.0926,
      "step": 51
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00018571428571428572,
      "loss": 1.0903,
      "step": 52
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0001892857142857143,
      "loss": 1.093,
      "step": 53
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.00019285714285714286,
      "loss": 1.1166,
      "step": 54
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00019642857142857144,
      "loss": 1.0854,
      "step": 55
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0002,
      "loss": 1.1161,
      "step": 56
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2857142857142857,
      "eval_f1_macro": 0.14814814814814817,
      "eval_f1_micro": 0.2857142857142857,
      "eval_f1_weighted": 0.126984126984127,
      "eval_loss": 1.100687861442566,
      "eval_precision_macro": 0.09523809523809523,
      "eval_precision_micro": 0.2857142857142857,
      "eval_precision_weighted": 0.08163265306122448,
      "eval_recall_macro": 0.3333333333333333,
      "eval_recall_micro": 0.2857142857142857,
      "eval_recall_weighted": 0.2857142857142857,
      "eval_runtime": 0.8746,
      "eval_samples_per_second": 8.004,
      "eval_steps_per_second": 4.574,
      "step": 56
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.00020357142857142858,
      "loss": 1.1051,
      "step": 57
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.00020714285714285716,
      "loss": 1.106,
      "step": 58
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.00021071428571428573,
      "loss": 1.1071,
      "step": 59
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.00021428571428571427,
      "loss": 1.104,
      "step": 60
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.00021785714285714287,
      "loss": 1.0954,
      "step": 61
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.00022142857142857142,
      "loss": 1.1252,
      "step": 62
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.00022500000000000002,
      "loss": 1.0935,
      "step": 63
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.00022857142857142857,
      "loss": 1.0953,
      "step": 64
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.00023214285714285717,
      "loss": 1.0697,
      "step": 65
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.0002357142857142857,
      "loss": 1.1385,
      "step": 66
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.0002392857142857143,
      "loss": 1.0618,
      "step": 67
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.00024285714285714286,
      "loss": 1.1012,
      "step": 68
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.00024642857142857143,
      "loss": 1.1554,
      "step": 69
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.00025,
      "loss": 1.1472,
      "step": 70
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.0002535714285714286,
      "loss": 1.0984,
      "step": 71
    },
    {
      "epoch": 2.57,
      "learning_rate": 0.0002571428571428571,
      "loss": 1.0957,
      "step": 72
    },
    {
      "epoch": 2.61,
      "learning_rate": 0.0002607142857142857,
      "loss": 1.0447,
      "step": 73
    },
    {
      "epoch": 2.64,
      "learning_rate": 0.0002642857142857143,
      "loss": 1.0864,
      "step": 74
    },
    {
      "epoch": 2.68,
      "learning_rate": 0.00026785714285714287,
      "loss": 1.0751,
      "step": 75
    },
    {
      "epoch": 2.71,
      "learning_rate": 0.0002714285714285714,
      "loss": 1.179,
      "step": 76
    },
    {
      "epoch": 2.75,
      "learning_rate": 0.000275,
      "loss": 1.0559,
      "step": 77
    },
    {
      "epoch": 2.79,
      "learning_rate": 0.0002785714285714286,
      "loss": 1.1938,
      "step": 78
    },
    {
      "epoch": 2.82,
      "learning_rate": 0.00028214285714285716,
      "loss": 1.0462,
      "step": 79
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.0002857142857142857,
      "loss": 1.207,
      "step": 80
    },
    {
      "epoch": 2.89,
      "learning_rate": 0.0002892857142857143,
      "loss": 1.0474,
      "step": 81
    },
    {
      "epoch": 2.93,
      "learning_rate": 0.0002928571428571429,
      "loss": 1.1944,
      "step": 82
    },
    {
      "epoch": 2.96,
      "learning_rate": 0.00029642857142857145,
      "loss": 1.0709,
      "step": 83
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0003,
      "loss": 1.0382,
      "step": 84
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.2857142857142857,
      "eval_f1_macro": 0.14814814814814817,
      "eval_f1_micro": 0.2857142857142857,
      "eval_f1_weighted": 0.126984126984127,
      "eval_loss": 1.0976771116256714,
      "eval_precision_macro": 0.09523809523809523,
      "eval_precision_micro": 0.2857142857142857,
      "eval_precision_weighted": 0.08163265306122448,
      "eval_recall_macro": 0.3333333333333333,
      "eval_recall_micro": 0.2857142857142857,
      "eval_recall_weighted": 0.2857142857142857,
      "eval_runtime": 0.9461,
      "eval_samples_per_second": 7.398,
      "eval_steps_per_second": 4.228,
      "step": 84
    },
    {
      "epoch": 3.04,
      "learning_rate": 0.00030357142857142855,
      "loss": 1.2095,
      "step": 85
    },
    {
      "epoch": 3.07,
      "learning_rate": 0.0003071428571428572,
      "loss": 1.0712,
      "step": 86
    },
    {
      "epoch": 3.11,
      "learning_rate": 0.00031071428571428575,
      "loss": 0.9957,
      "step": 87
    },
    {
      "epoch": 3.14,
      "learning_rate": 0.00031428571428571427,
      "loss": 1.2297,
      "step": 88
    },
    {
      "epoch": 3.18,
      "learning_rate": 0.00031785714285714284,
      "loss": 1.2472,
      "step": 89
    },
    {
      "epoch": 3.21,
      "learning_rate": 0.00032142857142857147,
      "loss": 1.2194,
      "step": 90
    },
    {
      "epoch": 3.25,
      "learning_rate": 0.00032500000000000004,
      "loss": 1.0032,
      "step": 91
    },
    {
      "epoch": 3.29,
      "learning_rate": 0.00032857142857142856,
      "loss": 1.0049,
      "step": 92
    },
    {
      "epoch": 3.32,
      "learning_rate": 0.00033214285714285713,
      "loss": 1.075,
      "step": 93
    },
    {
      "epoch": 3.36,
      "learning_rate": 0.0003357142857142857,
      "loss": 1.0702,
      "step": 94
    },
    {
      "epoch": 3.39,
      "learning_rate": 0.00033928571428571433,
      "loss": 1.0675,
      "step": 95
    },
    {
      "epoch": 3.43,
      "learning_rate": 0.00034285714285714285,
      "loss": 1.0613,
      "step": 96
    },
    {
      "epoch": 3.46,
      "learning_rate": 0.0003464285714285714,
      "loss": 1.2716,
      "step": 97
    },
    {
      "epoch": 3.5,
      "learning_rate": 0.00035,
      "loss": 0.9875,
      "step": 98
    },
    {
      "epoch": 3.54,
      "learning_rate": 0.0003535714285714286,
      "loss": 1.2666,
      "step": 99
    },
    {
      "epoch": 3.57,
      "learning_rate": 0.00035714285714285714,
      "loss": 1.0338,
      "step": 100
    },
    {
      "epoch": 3.61,
      "learning_rate": 0.0003607142857142857,
      "loss": 1.0024,
      "step": 101
    },
    {
      "epoch": 3.64,
      "learning_rate": 0.0003642857142857143,
      "loss": 1.3218,
      "step": 102
    },
    {
      "epoch": 3.68,
      "learning_rate": 0.0003678571428571429,
      "loss": 1.0089,
      "step": 103
    },
    {
      "epoch": 3.71,
      "learning_rate": 0.00037142857142857143,
      "loss": 1.0051,
      "step": 104
    },
    {
      "epoch": 3.75,
      "learning_rate": 0.000375,
      "loss": 1.0034,
      "step": 105
    },
    {
      "epoch": 3.79,
      "learning_rate": 0.0003785714285714286,
      "loss": 1.0045,
      "step": 106
    },
    {
      "epoch": 3.82,
      "learning_rate": 0.0003821428571428571,
      "loss": 1.0025,
      "step": 107
    },
    {
      "epoch": 3.86,
      "learning_rate": 0.0003857142857142857,
      "loss": 0.9845,
      "step": 108
    },
    {
      "epoch": 3.89,
      "learning_rate": 0.0003892857142857143,
      "loss": 0.9621,
      "step": 109
    },
    {
      "epoch": 3.93,
      "learning_rate": 0.0003928571428571429,
      "loss": 0.9943,
      "step": 110
    },
    {
      "epoch": 3.96,
      "learning_rate": 0.0003964285714285714,
      "loss": 1.4232,
      "step": 111
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.0004,
      "loss": 1.4025,
      "step": 112
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.2857142857142857,
      "eval_f1_macro": 0.14814814814814817,
      "eval_f1_micro": 0.2857142857142857,
      "eval_f1_weighted": 0.126984126984127,
      "eval_loss": 1.0950939655303955,
      "eval_precision_macro": 0.09523809523809523,
      "eval_precision_micro": 0.2857142857142857,
      "eval_precision_weighted": 0.08163265306122448,
      "eval_recall_macro": 0.3333333333333333,
      "eval_recall_micro": 0.2857142857142857,
      "eval_recall_weighted": 0.2857142857142857,
      "eval_runtime": 0.9362,
      "eval_samples_per_second": 7.477,
      "eval_steps_per_second": 4.273,
      "step": 112
    }
  ],
  "logging_steps": 1,
  "max_steps": 2800,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 500,
  "total_flos": 2378572450136064.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}