{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 19.428571428571427,
  "eval_steps": 500,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.14,
      "learning_rate": 7.142857142857142e-05,
      "loss": 1.7815,
      "step": 1
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00014285714285714284,
      "loss": 1.8832,
      "step": 2
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00021428571428571427,
      "loss": 1.8016,
      "step": 3
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002857142857142857,
      "loss": 1.875,
      "step": 4
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00035714285714285714,
      "loss": 1.3989,
      "step": 5
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00042857142857142855,
      "loss": 1.5972,
      "step": 6
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.0005,
      "loss": 1.3955,
      "step": 7
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.0005714285714285714,
      "loss": 1.2051,
      "step": 8
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.0006428571428571429,
      "loss": 1.5163,
      "step": 9
    },
    {
      "epoch": 3.14,
      "learning_rate": 0.0007142857142857143,
      "loss": 1.2729,
      "step": 10
    },
    {
      "epoch": 3.29,
      "learning_rate": 0.0007857142857142857,
      "loss": 1.1587,
      "step": 11
    },
    {
      "epoch": 3.43,
      "learning_rate": 0.0008571428571428571,
      "loss": 1.0227,
      "step": 12
    },
    {
      "epoch": 4.14,
      "learning_rate": 0.0009285714285714287,
      "loss": 1.1174,
      "step": 13
    },
    {
      "epoch": 4.29,
      "learning_rate": 0.001,
      "loss": 0.8435,
      "step": 14
    },
    {
      "epoch": 4.43,
      "learning_rate": 0.000992063492063492,
      "loss": 0.6047,
      "step": 15
    },
    {
      "epoch": 5.14,
      "learning_rate": 0.000984126984126984,
      "loss": 0.5716,
      "step": 16
    },
    {
      "epoch": 5.29,
      "learning_rate": 0.0009761904761904762,
      "loss": 0.6303,
      "step": 17
    },
    {
      "epoch": 5.43,
      "learning_rate": 0.0009682539682539683,
      "loss": 0.5562,
      "step": 18
    },
    {
      "epoch": 6.14,
      "learning_rate": 0.0009603174603174604,
      "loss": 0.5375,
      "step": 19
    },
    {
      "epoch": 6.29,
      "learning_rate": 0.0009523809523809524,
      "loss": 0.3218,
      "step": 20
    },
    {
      "epoch": 6.43,
      "learning_rate": 0.0009444444444444445,
      "loss": 0.3787,
      "step": 21
    },
    {
      "epoch": 7.14,
      "learning_rate": 0.0009365079365079366,
      "loss": 0.3622,
      "step": 22
    },
    {
      "epoch": 7.29,
      "learning_rate": 0.0009285714285714287,
      "loss": 0.2871,
      "step": 23
    },
    {
      "epoch": 7.43,
      "learning_rate": 0.0009206349206349207,
      "loss": 0.2373,
      "step": 24
    },
    {
      "epoch": 8.14,
      "learning_rate": 0.0009126984126984126,
      "loss": 0.2338,
      "step": 25
    },
    {
      "epoch": 8.29,
      "learning_rate": 0.0009047619047619047,
      "loss": 0.1994,
      "step": 26
    },
    {
      "epoch": 8.43,
      "learning_rate": 0.0008968253968253968,
      "loss": 0.2073,
      "step": 27
    },
    {
      "epoch": 9.14,
      "learning_rate": 0.0008888888888888888,
      "loss": 0.153,
      "step": 28
    },
    {
      "epoch": 9.29,
      "learning_rate": 0.0008809523809523809,
      "loss": 0.1608,
      "step": 29
    },
    {
      "epoch": 9.43,
      "learning_rate": 0.000873015873015873,
      "loss": 0.1244,
      "step": 30
    },
    {
      "epoch": 10.14,
      "learning_rate": 0.0008650793650793651,
      "loss": 0.1177,
      "step": 31
    },
    {
      "epoch": 10.29,
      "learning_rate": 0.0008571428571428571,
      "loss": 0.0993,
      "step": 32
    },
    {
      "epoch": 10.43,
      "learning_rate": 0.0008492063492063492,
      "loss": 0.0728,
      "step": 33
    },
    {
      "epoch": 11.14,
      "learning_rate": 0.0008412698412698413,
      "loss": 0.0591,
      "step": 34
    },
    {
      "epoch": 11.29,
      "learning_rate": 0.0008333333333333334,
      "loss": 0.0735,
      "step": 35
    },
    {
      "epoch": 11.43,
      "learning_rate": 0.0008253968253968254,
      "loss": 0.0483,
      "step": 36
    },
    {
      "epoch": 12.14,
      "learning_rate": 0.0008174603174603175,
      "loss": 0.0449,
      "step": 37
    },
    {
      "epoch": 12.29,
      "learning_rate": 0.0008095238095238096,
      "loss": 0.0329,
      "step": 38
    },
    {
      "epoch": 12.43,
      "learning_rate": 0.0008015873015873017,
      "loss": 0.0424,
      "step": 39
    },
    {
      "epoch": 13.14,
      "learning_rate": 0.0007936507936507937,
      "loss": 0.0327,
      "step": 40
    },
    {
      "epoch": 13.29,
      "learning_rate": 0.0007857142857142857,
      "loss": 0.0364,
      "step": 41
    },
    {
      "epoch": 13.43,
      "learning_rate": 0.0007777777777777778,
      "loss": 0.0286,
      "step": 42
    },
    {
      "epoch": 14.14,
      "learning_rate": 0.0007698412698412699,
      "loss": 0.0264,
      "step": 43
    },
    {
      "epoch": 14.29,
      "learning_rate": 0.0007619047619047619,
      "loss": 0.0225,
      "step": 44
    },
    {
      "epoch": 14.43,
      "learning_rate": 0.000753968253968254,
      "loss": 0.0332,
      "step": 45
    },
    {
      "epoch": 15.14,
      "learning_rate": 0.000746031746031746,
      "loss": 0.0214,
      "step": 46
    },
    {
      "epoch": 15.29,
      "learning_rate": 0.0007380952380952381,
      "loss": 0.0218,
      "step": 47
    },
    {
      "epoch": 15.43,
      "learning_rate": 0.0007301587301587301,
      "loss": 0.0227,
      "step": 48
    },
    {
      "epoch": 16.14,
      "learning_rate": 0.0007222222222222222,
      "loss": 0.0134,
      "step": 49
    },
    {
      "epoch": 16.29,
      "learning_rate": 0.0007142857142857143,
      "loss": 0.0185,
      "step": 50
    },
    {
      "epoch": 16.43,
      "learning_rate": 0.0007063492063492064,
      "loss": 0.029,
      "step": 51
    },
    {
      "epoch": 17.14,
      "learning_rate": 0.0006984126984126984,
      "loss": 0.0144,
      "step": 52
    },
    {
      "epoch": 17.29,
      "learning_rate": 0.0006904761904761905,
      "loss": 0.0171,
      "step": 53
    },
    {
      "epoch": 17.43,
      "learning_rate": 0.0006825396825396826,
      "loss": 0.0162,
      "step": 54
    },
    {
      "epoch": 18.14,
      "learning_rate": 0.0006746031746031747,
      "loss": 0.0134,
      "step": 55
    },
    {
      "epoch": 18.29,
      "learning_rate": 0.0006666666666666666,
      "loss": 0.0116,
      "step": 56
    },
    {
      "epoch": 18.43,
      "learning_rate": 0.0006587301587301587,
      "loss": 0.014,
      "step": 57
    },
    {
      "epoch": 19.14,
      "learning_rate": 0.0006507936507936508,
      "loss": 0.0084,
      "step": 58
    },
    {
      "epoch": 19.29,
      "learning_rate": 0.0006428571428571429,
      "loss": 0.0138,
      "step": 59
    },
    {
      "epoch": 19.43,
      "learning_rate": 0.0006349206349206349,
      "loss": 0.0173,
      "step": 60
    }
  ],
  "logging_steps": 1,
  "max_steps": 140,
  "num_train_epochs": 20,
  "save_steps": 500,
  "total_flos": 1.13811835060224e+16,
  "trial_name": null,
  "trial_params": null
}