{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 44.44444444444444,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.44,
      "learning_rate": 0,
      "loss": 1.7341,
      "step": 1
    },
    {
      "epoch": 0.89,
      "learning_rate": 0,
      "loss": 1.7223,
      "step": 2
    },
    {
      "epoch": 1.33,
      "learning_rate": 0,
      "loss": 1.7608,
      "step": 3
    },
    {
      "epoch": 1.78,
      "learning_rate": 0,
      "loss": 1.7115,
      "step": 4
    },
    {
      "epoch": 2.22,
      "learning_rate": 0,
      "loss": 1.7181,
      "step": 5
    },
    {
      "epoch": 2.67,
      "learning_rate": 0,
      "loss": 1.7022,
      "step": 6
    },
    {
      "epoch": 3.11,
      "learning_rate": 0,
      "loss": 1.7242,
      "step": 7
    },
    {
      "epoch": 3.56,
      "learning_rate": 0,
      "loss": 1.7352,
      "step": 8
    },
    {
      "epoch": 4.0,
      "learning_rate": 0,
      "loss": 1.7181,
      "step": 9
    },
    {
      "epoch": 4.44,
      "learning_rate": 0,
      "loss": 1.7213,
      "step": 10
    },
    {
      "epoch": 4.89,
      "learning_rate": 0,
      "loss": 1.6694,
      "step": 11
    },
    {
      "epoch": 5.33,
      "learning_rate": 0,
      "loss": 1.7046,
      "step": 12
    },
    {
      "epoch": 5.78,
      "learning_rate": 0,
      "loss": 1.7109,
      "step": 13
    },
    {
      "epoch": 6.22,
      "learning_rate": 0,
      "loss": 1.6948,
      "step": 14
    },
    {
      "epoch": 6.67,
      "learning_rate": 0,
      "loss": 1.6816,
      "step": 15
    },
    {
      "epoch": 7.11,
      "learning_rate": 0.0,
      "loss": 1.6851,
      "step": 16
    },
    {
      "epoch": 7.56,
      "learning_rate": 1.2618595071429148e-05,
      "loss": 1.6041,
      "step": 17
    },
    {
      "epoch": 8.0,
      "learning_rate": 2e-05,
      "loss": 1.5208,
      "step": 18
    },
    {
      "epoch": 8.44,
      "learning_rate": 2e-05,
      "loss": 1.4946,
      "step": 19
    },
    {
      "epoch": 8.89,
      "learning_rate": 2e-05,
      "loss": 1.492,
      "step": 20
    },
    {
      "epoch": 9.33,
      "learning_rate": 2e-05,
      "loss": 1.4501,
      "step": 21
    },
    {
      "epoch": 9.78,
      "learning_rate": 2e-05,
      "loss": 1.1894,
      "step": 22
    },
    {
      "epoch": 10.22,
      "learning_rate": 2e-05,
      "loss": 1.1437,
      "step": 23
    },
    {
      "epoch": 10.67,
      "learning_rate": 2e-05,
      "loss": 1.02,
      "step": 24
    },
    {
      "epoch": 11.11,
      "learning_rate": 2e-05,
      "loss": 0.926,
      "step": 25
    },
    {
      "epoch": 11.56,
      "learning_rate": 2e-05,
      "loss": 0.7794,
      "step": 26
    },
    {
      "epoch": 12.0,
      "learning_rate": 2e-05,
      "loss": 0.7719,
      "step": 27
    },
    {
      "epoch": 12.44,
      "learning_rate": 2e-05,
      "loss": 0.6107,
      "step": 28
    },
    {
      "epoch": 12.89,
      "learning_rate": 2e-05,
      "loss": 0.633,
      "step": 29
    },
    {
      "epoch": 13.33,
      "learning_rate": 2e-05,
      "loss": 0.4781,
      "step": 30
    },
    {
      "epoch": 13.78,
      "learning_rate": 2e-05,
      "loss": 0.4379,
      "step": 31
    },
    {
      "epoch": 14.22,
      "learning_rate": 2e-05,
      "loss": 0.3391,
      "step": 32
    },
    {
      "epoch": 14.67,
      "learning_rate": 2e-05,
      "loss": 0.2928,
      "step": 33
    },
    {
      "epoch": 15.11,
      "learning_rate": 2e-05,
      "loss": 0.2631,
      "step": 34
    },
    {
      "epoch": 15.56,
      "learning_rate": 2e-05,
      "loss": 0.2399,
      "step": 35
    },
    {
      "epoch": 16.0,
      "learning_rate": 2e-05,
      "loss": 0.2075,
      "step": 36
    },
    {
      "epoch": 16.44,
      "learning_rate": 2e-05,
      "loss": 0.186,
      "step": 37
    },
    {
      "epoch": 16.89,
      "learning_rate": 2e-05,
      "loss": 0.1782,
      "step": 38
    },
    {
      "epoch": 17.33,
      "learning_rate": 2e-05,
      "loss": 0.144,
      "step": 39
    },
    {
      "epoch": 17.78,
      "learning_rate": 2e-05,
      "loss": 0.1317,
      "step": 40
    },
    {
      "epoch": 18.22,
      "learning_rate": 2e-05,
      "loss": 0.1144,
      "step": 41
    },
    {
      "epoch": 18.67,
      "learning_rate": 2e-05,
      "loss": 0.1193,
      "step": 42
    },
    {
      "epoch": 19.11,
      "learning_rate": 2e-05,
      "loss": 0.1161,
      "step": 43
    },
    {
      "epoch": 19.56,
      "learning_rate": 2e-05,
      "loss": 0.0993,
      "step": 44
    },
    {
      "epoch": 20.0,
      "learning_rate": 2e-05,
      "loss": 0.1083,
      "step": 45
    },
    {
      "epoch": 20.44,
      "learning_rate": 2e-05,
      "loss": 0.101,
      "step": 46
    },
    {
      "epoch": 20.89,
      "learning_rate": 2e-05,
      "loss": 0.1013,
      "step": 47
    },
    {
      "epoch": 21.33,
      "learning_rate": 2e-05,
      "loss": 0.1066,
      "step": 48
    },
    {
      "epoch": 21.78,
      "learning_rate": 2e-05,
      "loss": 0.1005,
      "step": 49
    },
    {
      "epoch": 22.22,
      "learning_rate": 2e-05,
      "loss": 0.0882,
      "step": 50
    },
    {
      "epoch": 22.67,
      "learning_rate": 2e-05,
      "loss": 0.1067,
      "step": 51
    },
    {
      "epoch": 23.11,
      "learning_rate": 2e-05,
      "loss": 0.0797,
      "step": 52
    },
    {
      "epoch": 23.56,
      "learning_rate": 2e-05,
      "loss": 0.0943,
      "step": 53
    },
    {
      "epoch": 24.0,
      "learning_rate": 2e-05,
      "loss": 0.0769,
      "step": 54
    },
    {
      "epoch": 24.44,
      "learning_rate": 2e-05,
      "loss": 0.0855,
      "step": 55
    },
    {
      "epoch": 24.89,
      "learning_rate": 2e-05,
      "loss": 0.0735,
      "step": 56
    },
    {
      "epoch": 25.33,
      "learning_rate": 2e-05,
      "loss": 0.0833,
      "step": 57
    },
    {
      "epoch": 25.78,
      "learning_rate": 2e-05,
      "loss": 0.0811,
      "step": 58
    },
    {
      "epoch": 26.22,
      "learning_rate": 2e-05,
      "loss": 0.0772,
      "step": 59
    },
    {
      "epoch": 26.67,
      "learning_rate": 2e-05,
      "loss": 0.0721,
      "step": 60
    },
    {
      "epoch": 27.11,
      "learning_rate": 2e-05,
      "loss": 0.0825,
      "step": 61
    },
    {
      "epoch": 27.56,
      "learning_rate": 2e-05,
      "loss": 0.0758,
      "step": 62
    },
    {
      "epoch": 28.0,
      "learning_rate": 2e-05,
      "loss": 0.0725,
      "step": 63
    },
    {
      "epoch": 28.44,
      "learning_rate": 2e-05,
      "loss": 0.077,
      "step": 64
    },
    {
      "epoch": 28.89,
      "learning_rate": 2e-05,
      "loss": 0.0654,
      "step": 65
    },
    {
      "epoch": 29.33,
      "learning_rate": 2e-05,
      "loss": 0.0675,
      "step": 66
    },
    {
      "epoch": 29.78,
      "learning_rate": 2e-05,
      "loss": 0.0772,
      "step": 67
    },
    {
      "epoch": 30.22,
      "learning_rate": 2e-05,
      "loss": 0.0718,
      "step": 68
    },
    {
      "epoch": 30.67,
      "learning_rate": 2e-05,
      "loss": 0.0625,
      "step": 69
    },
    {
      "epoch": 31.11,
      "learning_rate": 2e-05,
      "loss": 0.0616,
      "step": 70
    },
    {
      "epoch": 31.56,
      "learning_rate": 2e-05,
      "loss": 0.071,
      "step": 71
    },
    {
      "epoch": 32.0,
      "learning_rate": 2e-05,
      "loss": 0.0655,
      "step": 72
    },
    {
      "epoch": 32.44,
      "learning_rate": 2e-05,
      "loss": 0.0591,
      "step": 73
    },
    {
      "epoch": 32.89,
      "learning_rate": 2e-05,
      "loss": 0.0669,
      "step": 74
    },
    {
      "epoch": 33.33,
      "learning_rate": 2e-05,
      "loss": 0.0653,
      "step": 75
    },
    {
      "epoch": 33.78,
      "learning_rate": 2e-05,
      "loss": 0.0662,
      "step": 76
    },
    {
      "epoch": 34.22,
      "learning_rate": 2e-05,
      "loss": 0.0688,
      "step": 77
    },
    {
      "epoch": 34.67,
      "learning_rate": 2e-05,
      "loss": 0.0498,
      "step": 78
    },
    {
      "epoch": 35.11,
      "learning_rate": 2e-05,
      "loss": 0.0576,
      "step": 79
    },
    {
      "epoch": 35.56,
      "learning_rate": 2e-05,
      "loss": 0.0737,
      "step": 80
    },
    {
      "epoch": 36.0,
      "learning_rate": 2e-05,
      "loss": 0.0609,
      "step": 81
    },
    {
      "epoch": 36.44,
      "learning_rate": 2e-05,
      "loss": 0.0594,
      "step": 82
    },
    {
      "epoch": 36.89,
      "learning_rate": 2e-05,
      "loss": 0.0725,
      "step": 83
    },
    {
      "epoch": 37.33,
      "learning_rate": 2e-05,
      "loss": 0.0598,
      "step": 84
    },
    {
      "epoch": 37.78,
      "learning_rate": 2e-05,
      "loss": 0.0652,
      "step": 85
    },
    {
      "epoch": 38.22,
      "learning_rate": 2e-05,
      "loss": 0.0588,
      "step": 86
    },
    {
      "epoch": 38.67,
      "learning_rate": 2e-05,
      "loss": 0.0671,
      "step": 87
    },
    {
      "epoch": 39.11,
      "learning_rate": 2e-05,
      "loss": 0.0596,
      "step": 88
    },
    {
      "epoch": 39.56,
      "learning_rate": 2e-05,
      "loss": 0.0518,
      "step": 89
    },
    {
      "epoch": 40.0,
      "learning_rate": 2e-05,
      "loss": 0.0612,
      "step": 90
    },
    {
      "epoch": 40.44,
      "learning_rate": 2e-05,
      "loss": 0.0593,
      "step": 91
    },
    {
      "epoch": 40.89,
      "learning_rate": 2e-05,
      "loss": 0.0521,
      "step": 92
    },
    {
      "epoch": 41.33,
      "learning_rate": 2e-05,
      "loss": 0.0536,
      "step": 93
    },
    {
      "epoch": 41.78,
      "learning_rate": 2e-05,
      "loss": 0.0548,
      "step": 94
    },
    {
      "epoch": 42.22,
      "learning_rate": 2e-05,
      "loss": 0.0507,
      "step": 95
    },
    {
      "epoch": 42.67,
      "learning_rate": 2e-05,
      "loss": 0.0588,
      "step": 96
    },
    {
      "epoch": 43.11,
      "learning_rate": 2e-05,
      "loss": 0.0506,
      "step": 97
    },
    {
      "epoch": 43.56,
      "learning_rate": 2e-05,
      "loss": 0.055,
      "step": 98
    },
    {
      "epoch": 44.0,
      "learning_rate": 2e-05,
      "loss": 0.0503,
      "step": 99
    },
    {
      "epoch": 44.44,
      "learning_rate": 2e-05,
      "loss": 0.054,
      "step": 100
    },
    {
      "epoch": 44.44,
      "step": 100,
      "total_flos": 7478779576320.0,
      "train_loss": 0.49326207719743254,
      "train_runtime": 9902.4306,
      "train_samples_per_second": 0.969,
      "train_steps_per_second": 0.01
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_train_epochs": 50,
  "save_steps": 200,
  "total_flos": 7478779576320.0,
  "trial_name": null,
  "trial_params": null
}