{
  "best_metric": 0.18480469286441803,
  "best_model_checkpoint": "/tmp/model/checkpoint-87",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 87,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 0.0,
      "loss": 0.6934,
      "step": 1
    },
    {
      "epoch": 0.07,
      "learning_rate": 5.555555555555556e-06,
      "loss": 0.6934,
      "step": 2
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.6934,
      "step": 3
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.6931,
      "step": 4
    },
    {
      "epoch": 0.17,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.6923,
      "step": 5
    },
    {
      "epoch": 0.21,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.694,
      "step": 6
    },
    {
      "epoch": 0.24,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.6877,
      "step": 7
    },
    {
      "epoch": 0.28,
      "learning_rate": 3.888888888888889e-05,
      "loss": 0.688,
      "step": 8
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.6873,
      "step": 9
    },
    {
      "epoch": 0.34,
      "learning_rate": 5e-05,
      "loss": 0.6959,
      "step": 10
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.935897435897436e-05,
      "loss": 0.6808,
      "step": 11
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.871794871794872e-05,
      "loss": 0.6835,
      "step": 12
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.8076923076923084e-05,
      "loss": 0.6755,
      "step": 13
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.7435897435897435e-05,
      "loss": 0.684,
      "step": 14
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.67948717948718e-05,
      "loss": 0.6845,
      "step": 15
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.6609,
      "step": 16
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.5512820512820516e-05,
      "loss": 0.6962,
      "step": 17
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.4871794871794874e-05,
      "loss": 0.6797,
      "step": 18
    },
    {
      "epoch": 0.66,
      "learning_rate": 4.423076923076923e-05,
      "loss": 0.657,
      "step": 19
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.358974358974359e-05,
      "loss": 0.6794,
      "step": 20
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.294871794871795e-05,
      "loss": 0.629,
      "step": 21
    },
    {
      "epoch": 0.76,
      "learning_rate": 4.230769230769231e-05,
      "loss": 0.6429,
      "step": 22
    },
    {
      "epoch": 0.79,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.6003,
      "step": 23
    },
    {
      "epoch": 0.83,
      "learning_rate": 4.1025641025641023e-05,
      "loss": 0.58,
      "step": 24
    },
    {
      "epoch": 0.86,
      "learning_rate": 4.038461538461539e-05,
      "loss": 0.6459,
      "step": 25
    },
    {
      "epoch": 0.9,
      "learning_rate": 3.974358974358974e-05,
      "loss": 0.5719,
      "step": 26
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.9102564102564105e-05,
      "loss": 0.5321,
      "step": 27
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.6402,
      "step": 28
    },
    {
      "epoch": 1.0,
      "learning_rate": 3.782051282051282e-05,
      "loss": 0.4468,
      "step": 29
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.76,
      "eval_auc": 1.0,
      "eval_f1": 0.8235294117647058,
      "eval_loss": 0.5563281178474426,
      "eval_precision": 0.7,
      "eval_recall": 1.0,
      "eval_runtime": 1.6051,
      "eval_samples_per_second": 15.576,
      "eval_steps_per_second": 1.246,
      "step": 29
    },
    {
      "epoch": 1.03,
      "learning_rate": 3.717948717948718e-05,
      "loss": 0.5103,
      "step": 30
    },
    {
      "epoch": 1.07,
      "learning_rate": 3.653846153846154e-05,
      "loss": 0.5385,
      "step": 31
    },
    {
      "epoch": 1.1,
      "learning_rate": 3.58974358974359e-05,
      "loss": 0.5151,
      "step": 32
    },
    {
      "epoch": 1.14,
      "learning_rate": 3.525641025641026e-05,
      "loss": 0.4949,
      "step": 33
    },
    {
      "epoch": 1.17,
      "learning_rate": 3.461538461538462e-05,
      "loss": 0.5086,
      "step": 34
    },
    {
      "epoch": 1.21,
      "learning_rate": 3.397435897435898e-05,
      "loss": 0.4416,
      "step": 35
    },
    {
      "epoch": 1.24,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.4374,
      "step": 36
    },
    {
      "epoch": 1.28,
      "learning_rate": 3.269230769230769e-05,
      "loss": 0.5711,
      "step": 37
    },
    {
      "epoch": 1.31,
      "learning_rate": 3.205128205128206e-05,
      "loss": 0.462,
      "step": 38
    },
    {
      "epoch": 1.34,
      "learning_rate": 3.141025641025641e-05,
      "loss": 0.4268,
      "step": 39
    },
    {
      "epoch": 1.38,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.473,
      "step": 40
    },
    {
      "epoch": 1.41,
      "learning_rate": 3.012820512820513e-05,
      "loss": 0.4651,
      "step": 41
    },
    {
      "epoch": 1.45,
      "learning_rate": 2.948717948717949e-05,
      "loss": 0.3712,
      "step": 42
    },
    {
      "epoch": 1.48,
      "learning_rate": 2.8846153846153845e-05,
      "loss": 0.6356,
      "step": 43
    },
    {
      "epoch": 1.52,
      "learning_rate": 2.8205128205128207e-05,
      "loss": 0.3557,
      "step": 44
    },
    {
      "epoch": 1.55,
      "learning_rate": 2.756410256410257e-05,
      "loss": 0.3891,
      "step": 45
    },
    {
      "epoch": 1.59,
      "learning_rate": 2.6923076923076923e-05,
      "loss": 0.412,
      "step": 46
    },
    {
      "epoch": 1.62,
      "learning_rate": 2.6282051282051285e-05,
      "loss": 0.2874,
      "step": 47
    },
    {
      "epoch": 1.66,
      "learning_rate": 2.564102564102564e-05,
      "loss": 0.3086,
      "step": 48
    },
    {
      "epoch": 1.69,
      "learning_rate": 2.5e-05,
      "loss": 0.384,
      "step": 49
    },
    {
      "epoch": 1.72,
      "learning_rate": 2.435897435897436e-05,
      "loss": 0.2773,
      "step": 50
    },
    {
      "epoch": 1.76,
      "learning_rate": 2.3717948717948718e-05,
      "loss": 0.3755,
      "step": 51
    },
    {
      "epoch": 1.79,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.507,
      "step": 52
    },
    {
      "epoch": 1.83,
      "learning_rate": 2.2435897435897437e-05,
      "loss": 0.3976,
      "step": 53
    },
    {
      "epoch": 1.86,
      "learning_rate": 2.1794871794871795e-05,
      "loss": 0.3925,
      "step": 54
    },
    {
      "epoch": 1.9,
      "learning_rate": 2.1153846153846154e-05,
      "loss": 0.5349,
      "step": 55
    },
    {
      "epoch": 1.93,
      "learning_rate": 2.0512820512820512e-05,
      "loss": 0.2437,
      "step": 56
    },
    {
      "epoch": 1.97,
      "learning_rate": 1.987179487179487e-05,
      "loss": 0.3496,
      "step": 57
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.923076923076923e-05,
      "loss": 0.1945,
      "step": 58
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.84,
      "eval_auc": 1.0,
      "eval_f1": 0.8750000000000001,
      "eval_loss": 0.3492187559604645,
      "eval_precision": 0.7777777777777778,
      "eval_recall": 1.0,
      "eval_runtime": 1.5992,
      "eval_samples_per_second": 15.633,
      "eval_steps_per_second": 1.251,
      "step": 58
    },
    {
      "epoch": 2.03,
      "learning_rate": 1.858974358974359e-05,
      "loss": 0.2392,
      "step": 59
    },
    {
      "epoch": 2.07,
      "learning_rate": 1.794871794871795e-05,
      "loss": 0.2135,
      "step": 60
    },
    {
      "epoch": 2.1,
      "learning_rate": 1.730769230769231e-05,
      "loss": 0.4027,
      "step": 61
    },
    {
      "epoch": 2.14,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.3798,
      "step": 62
    },
    {
      "epoch": 2.17,
      "learning_rate": 1.602564102564103e-05,
      "loss": 0.2134,
      "step": 63
    },
    {
      "epoch": 2.21,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.3116,
      "step": 64
    },
    {
      "epoch": 2.24,
      "learning_rate": 1.4743589743589745e-05,
      "loss": 0.2248,
      "step": 65
    },
    {
      "epoch": 2.28,
      "learning_rate": 1.4102564102564104e-05,
      "loss": 0.1883,
      "step": 66
    },
    {
      "epoch": 2.31,
      "learning_rate": 1.3461538461538462e-05,
      "loss": 0.1935,
      "step": 67
    },
    {
      "epoch": 2.34,
      "learning_rate": 1.282051282051282e-05,
      "loss": 0.1912,
      "step": 68
    },
    {
      "epoch": 2.38,
      "learning_rate": 1.217948717948718e-05,
      "loss": 0.1999,
      "step": 69
    },
    {
      "epoch": 2.41,
      "learning_rate": 1.153846153846154e-05,
      "loss": 0.2033,
      "step": 70
    },
    {
      "epoch": 2.45,
      "learning_rate": 1.0897435897435898e-05,
      "loss": 0.2038,
      "step": 71
    },
    {
      "epoch": 2.48,
      "learning_rate": 1.0256410256410256e-05,
      "loss": 0.1647,
      "step": 72
    },
    {
      "epoch": 2.52,
      "learning_rate": 9.615384615384616e-06,
      "loss": 0.1812,
      "step": 73
    },
    {
      "epoch": 2.55,
      "learning_rate": 8.974358974358976e-06,
      "loss": 0.1766,
      "step": 74
    },
    {
      "epoch": 2.59,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.2137,
      "step": 75
    },
    {
      "epoch": 2.62,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.3739,
      "step": 76
    },
    {
      "epoch": 2.66,
      "learning_rate": 7.051282051282052e-06,
      "loss": 0.301,
      "step": 77
    },
    {
      "epoch": 2.69,
      "learning_rate": 6.41025641025641e-06,
      "loss": 0.1771,
      "step": 78
    },
    {
      "epoch": 2.72,
      "learning_rate": 5.76923076923077e-06,
      "loss": 0.2224,
      "step": 79
    },
    {
      "epoch": 2.76,
      "learning_rate": 5.128205128205128e-06,
      "loss": 0.2905,
      "step": 80
    },
    {
      "epoch": 2.79,
      "learning_rate": 4.487179487179488e-06,
      "loss": 0.1836,
      "step": 81
    },
    {
      "epoch": 2.83,
      "learning_rate": 3.846153846153847e-06,
      "loss": 0.1592,
      "step": 82
    },
    {
      "epoch": 2.86,
      "learning_rate": 3.205128205128205e-06,
      "loss": 0.1648,
      "step": 83
    },
    {
      "epoch": 2.9,
      "learning_rate": 2.564102564102564e-06,
      "loss": 0.1626,
      "step": 84
    },
    {
      "epoch": 2.93,
      "learning_rate": 1.9230769230769234e-06,
      "loss": 0.1826,
      "step": 85
    },
    {
      "epoch": 2.97,
      "learning_rate": 1.282051282051282e-06,
      "loss": 0.3295,
      "step": 86
    },
    {
      "epoch": 3.0,
      "learning_rate": 6.41025641025641e-07,
      "loss": 0.1466,
      "step": 87
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.96,
      "eval_auc": 1.0,
      "eval_f1": 0.962962962962963,
      "eval_loss": 0.18480469286441803,
      "eval_precision": 1.0,
      "eval_recall": 0.9285714285714286,
      "eval_runtime": 1.5881,
      "eval_samples_per_second": 15.742,
      "eval_steps_per_second": 1.259,
      "step": 87
    }
  ],
  "logging_steps": 1,
  "max_steps": 87,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 1.849055714085888e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}