{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.836441893830703,
  "eval_steps": 500,
  "global_step": 80,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 5e-05,
      "loss": 1.7667,
      "step": 1
    },
    {
      "epoch": 0.05,
      "learning_rate": 5e-05,
      "loss": 1.7274,
      "step": 2
    },
    {
      "epoch": 0.07,
      "learning_rate": 5e-05,
      "loss": 1.656,
      "step": 3
    },
    {
      "epoch": 0.09,
      "learning_rate": 5e-05,
      "loss": 1.7964,
      "step": 4
    },
    {
      "epoch": 0.11,
      "learning_rate": 5e-05,
      "loss": 1.6153,
      "step": 5
    },
    {
      "epoch": 0.14,
      "learning_rate": 5e-05,
      "loss": 1.7931,
      "step": 6
    },
    {
      "epoch": 0.16,
      "learning_rate": 5e-05,
      "loss": 1.7548,
      "step": 7
    },
    {
      "epoch": 0.18,
      "learning_rate": 5e-05,
      "loss": 1.7054,
      "step": 8
    },
    {
      "epoch": 0.21,
      "learning_rate": 5e-05,
      "loss": 1.7311,
      "step": 9
    },
    {
      "epoch": 0.23,
      "learning_rate": 5e-05,
      "loss": 1.6827,
      "step": 10
    },
    {
      "epoch": 0.25,
      "learning_rate": 5e-05,
      "loss": 1.7158,
      "step": 11
    },
    {
      "epoch": 0.28,
      "learning_rate": 5e-05,
      "loss": 1.6599,
      "step": 12
    },
    {
      "epoch": 0.3,
      "learning_rate": 5e-05,
      "loss": 1.6991,
      "step": 13
    },
    {
      "epoch": 0.32,
      "learning_rate": 5e-05,
      "loss": 1.6628,
      "step": 14
    },
    {
      "epoch": 0.34,
      "learning_rate": 5e-05,
      "loss": 1.6188,
      "step": 15
    },
    {
      "epoch": 0.37,
      "learning_rate": 5e-05,
      "loss": 1.6868,
      "step": 16
    },
    {
      "epoch": 0.39,
      "learning_rate": 5e-05,
      "loss": 1.6854,
      "step": 17
    },
    {
      "epoch": 0.41,
      "learning_rate": 5e-05,
      "loss": 1.5938,
      "step": 18
    },
    {
      "epoch": 0.44,
      "learning_rate": 5e-05,
      "loss": 1.6603,
      "step": 19
    },
    {
      "epoch": 0.46,
      "learning_rate": 5e-05,
      "loss": 1.561,
      "step": 20
    },
    {
      "epoch": 0.48,
      "learning_rate": 5e-05,
      "loss": 1.6162,
      "step": 21
    },
    {
      "epoch": 0.51,
      "learning_rate": 5e-05,
      "loss": 1.6159,
      "step": 22
    },
    {
      "epoch": 0.53,
      "learning_rate": 5e-05,
      "loss": 1.6414,
      "step": 23
    },
    {
      "epoch": 0.55,
      "learning_rate": 5e-05,
      "loss": 1.6915,
      "step": 24
    },
    {
      "epoch": 0.57,
      "learning_rate": 5e-05,
      "loss": 1.6853,
      "step": 25
    },
    {
      "epoch": 0.6,
      "learning_rate": 5e-05,
      "loss": 1.6563,
      "step": 26
    },
    {
      "epoch": 0.62,
      "learning_rate": 5e-05,
      "loss": 1.6622,
      "step": 27
    },
    {
      "epoch": 0.64,
      "learning_rate": 5e-05,
      "loss": 1.638,
      "step": 28
    },
    {
      "epoch": 0.67,
      "learning_rate": 5e-05,
      "loss": 1.66,
      "step": 29
    },
    {
      "epoch": 0.69,
      "learning_rate": 5e-05,
      "loss": 1.6565,
      "step": 30
    },
    {
      "epoch": 0.71,
      "learning_rate": 5e-05,
      "loss": 1.6076,
      "step": 31
    },
    {
      "epoch": 0.73,
      "learning_rate": 5e-05,
      "loss": 1.6971,
      "step": 32
    },
    {
      "epoch": 0.76,
      "learning_rate": 5e-05,
      "loss": 1.6836,
      "step": 33
    },
    {
      "epoch": 0.78,
      "learning_rate": 5e-05,
      "loss": 1.587,
      "step": 34
    },
    {
      "epoch": 0.8,
      "learning_rate": 5e-05,
      "loss": 1.7034,
      "step": 35
    },
    {
      "epoch": 0.83,
      "learning_rate": 5e-05,
      "loss": 1.705,
      "step": 36
    },
    {
      "epoch": 0.85,
      "learning_rate": 5e-05,
      "loss": 1.5491,
      "step": 37
    },
    {
      "epoch": 0.87,
      "learning_rate": 5e-05,
      "loss": 1.611,
      "step": 38
    },
    {
      "epoch": 0.9,
      "learning_rate": 5e-05,
      "loss": 1.6795,
      "step": 39
    },
    {
      "epoch": 0.92,
      "learning_rate": 5e-05,
      "loss": 1.5823,
      "step": 40
    },
    {
      "epoch": 0.94,
      "learning_rate": 5e-05,
      "loss": 1.6066,
      "step": 41
    },
    {
      "epoch": 0.96,
      "learning_rate": 5e-05,
      "loss": 1.6279,
      "step": 42
    },
    {
      "epoch": 0.99,
      "learning_rate": 5e-05,
      "loss": 1.5756,
      "step": 43
    },
    {
      "epoch": 1.01,
      "learning_rate": 5e-05,
      "loss": 1.6426,
      "step": 44
    },
    {
      "epoch": 1.03,
      "learning_rate": 5e-05,
      "loss": 1.6566,
      "step": 45
    },
    {
      "epoch": 1.06,
      "learning_rate": 5e-05,
      "loss": 1.6325,
      "step": 46
    },
    {
      "epoch": 1.08,
      "learning_rate": 5e-05,
      "loss": 1.7233,
      "step": 47
    },
    {
      "epoch": 1.1,
      "learning_rate": 5e-05,
      "loss": 1.5899,
      "step": 48
    },
    {
      "epoch": 1.12,
      "learning_rate": 5e-05,
      "loss": 1.5425,
      "step": 49
    },
    {
      "epoch": 1.15,
      "learning_rate": 5e-05,
      "loss": 1.4761,
      "step": 50
    },
    {
      "epoch": 1.17,
      "learning_rate": 5e-05,
      "loss": 1.6153,
      "step": 51
    },
    {
      "epoch": 1.19,
      "learning_rate": 5e-05,
      "loss": 1.6099,
      "step": 52
    },
    {
      "epoch": 1.22,
      "learning_rate": 5e-05,
      "loss": 1.6017,
      "step": 53
    },
    {
      "epoch": 1.24,
      "learning_rate": 5e-05,
      "loss": 1.5573,
      "step": 54
    },
    {
      "epoch": 1.26,
      "learning_rate": 5e-05,
      "loss": 1.5365,
      "step": 55
    },
    {
      "epoch": 1.29,
      "learning_rate": 5e-05,
      "loss": 1.6471,
      "step": 56
    },
    {
      "epoch": 1.31,
      "learning_rate": 5e-05,
      "loss": 1.5963,
      "step": 57
    },
    {
      "epoch": 1.33,
      "learning_rate": 5e-05,
      "loss": 1.6854,
      "step": 58
    },
    {
      "epoch": 1.35,
      "learning_rate": 5e-05,
      "loss": 1.5597,
      "step": 59
    },
    {
      "epoch": 1.38,
      "learning_rate": 5e-05,
      "loss": 1.66,
      "step": 60
    },
    {
      "epoch": 1.4,
      "learning_rate": 5e-05,
      "loss": 1.6862,
      "step": 61
    },
    {
      "epoch": 1.42,
      "learning_rate": 5e-05,
      "loss": 1.7041,
      "step": 62
    },
    {
      "epoch": 1.45,
      "learning_rate": 5e-05,
      "loss": 1.6115,
      "step": 63
    },
    {
      "epoch": 1.47,
      "learning_rate": 5e-05,
      "loss": 1.5222,
      "step": 64
    },
    {
      "epoch": 1.49,
      "learning_rate": 5e-05,
      "loss": 1.5516,
      "step": 65
    },
    {
      "epoch": 1.52,
      "learning_rate": 5e-05,
      "loss": 1.4681,
      "step": 66
    },
    {
      "epoch": 1.54,
      "learning_rate": 5e-05,
      "loss": 1.5683,
      "step": 67
    },
    {
      "epoch": 1.56,
      "learning_rate": 5e-05,
      "loss": 1.7625,
      "step": 68
    },
    {
      "epoch": 1.58,
      "learning_rate": 5e-05,
      "loss": 1.5548,
      "step": 69
    },
    {
      "epoch": 1.61,
      "learning_rate": 5e-05,
      "loss": 1.5915,
      "step": 70
    },
    {
      "epoch": 1.63,
      "learning_rate": 5e-05,
      "loss": 1.6061,
      "step": 71
    },
    {
      "epoch": 1.65,
      "learning_rate": 5e-05,
      "loss": 1.6822,
      "step": 72
    },
    {
      "epoch": 1.68,
      "learning_rate": 5e-05,
      "loss": 1.7447,
      "step": 73
    },
    {
      "epoch": 1.7,
      "learning_rate": 5e-05,
      "loss": 1.6758,
      "step": 74
    },
    {
      "epoch": 1.72,
      "learning_rate": 5e-05,
      "loss": 1.5201,
      "step": 75
    },
    {
      "epoch": 1.74,
      "learning_rate": 5e-05,
      "loss": 1.553,
      "step": 76
    },
    {
      "epoch": 1.77,
      "learning_rate": 5e-05,
      "loss": 1.6177,
      "step": 77
    },
    {
      "epoch": 1.79,
      "learning_rate": 5e-05,
      "loss": 1.6863,
      "step": 78
    },
    {
      "epoch": 1.81,
      "learning_rate": 5e-05,
      "loss": 1.5896,
      "step": 79
    },
    {
      "epoch": 1.84,
      "learning_rate": 5e-05,
      "loss": 1.5084,
      "step": 80
    }
  ],
  "logging_steps": 1,
  "max_steps": 129,
  "num_train_epochs": 3,
  "save_steps": 10,
  "total_flos": 3.5457442763636736e+17,
  "trial_name": null,
  "trial_params": null
}