{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "global_step": 93,
  "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": 0.4775,
      "step": 1
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.2618595071429148e-05,
      "loss": 0.3184,
      "step": 2
    },
    {
      "epoch": 0.1,
      "learning_rate": 2e-05,
      "loss": 0.3267,
      "step": 3
    },
    {
      "epoch": 0.13,
      "learning_rate": 2e-05,
      "loss": 0.2603,
      "step": 4
    },
    {
      "epoch": 0.16,
      "learning_rate": 2e-05,
      "loss": 0.2483,
      "step": 5
    },
    {
      "epoch": 0.19,
      "learning_rate": 2e-05,
      "loss": 0.2056,
      "step": 6
    },
    {
      "epoch": 0.23,
      "learning_rate": 2e-05,
      "loss": 0.2126,
      "step": 7
    },
    {
      "epoch": 0.26,
      "learning_rate": 2e-05,
      "loss": 0.2026,
      "step": 8
    },
    {
      "epoch": 0.29,
      "learning_rate": 2e-05,
      "loss": 0.1997,
      "step": 9
    },
    {
      "epoch": 0.32,
      "learning_rate": 2e-05,
      "loss": 0.1829,
      "step": 10
    },
    {
      "epoch": 0.35,
      "learning_rate": 2e-05,
      "loss": 0.186,
      "step": 11
    },
    {
      "epoch": 0.39,
      "learning_rate": 2e-05,
      "loss": 0.1743,
      "step": 12
    },
    {
      "epoch": 0.42,
      "learning_rate": 2e-05,
      "loss": 0.1682,
      "step": 13
    },
    {
      "epoch": 0.45,
      "learning_rate": 2e-05,
      "loss": 0.1836,
      "step": 14
    },
    {
      "epoch": 0.48,
      "learning_rate": 2e-05,
      "loss": 0.1721,
      "step": 15
    },
    {
      "epoch": 0.52,
      "learning_rate": 2e-05,
      "loss": 0.1807,
      "step": 16
    },
    {
      "epoch": 0.55,
      "learning_rate": 2e-05,
      "loss": 0.1714,
      "step": 17
    },
    {
      "epoch": 0.58,
      "learning_rate": 2e-05,
      "loss": 0.1646,
      "step": 18
    },
    {
      "epoch": 0.61,
      "learning_rate": 2e-05,
      "loss": 0.1763,
      "step": 19
    },
    {
      "epoch": 0.65,
      "learning_rate": 2e-05,
      "loss": 0.1614,
      "step": 20
    },
    {
      "epoch": 0.68,
      "learning_rate": 2e-05,
      "loss": 0.1533,
      "step": 21
    },
    {
      "epoch": 0.71,
      "learning_rate": 2e-05,
      "loss": 0.1616,
      "step": 22
    },
    {
      "epoch": 0.74,
      "learning_rate": 2e-05,
      "loss": 0.1736,
      "step": 23
    },
    {
      "epoch": 0.77,
      "learning_rate": 2e-05,
      "loss": 0.1558,
      "step": 24
    },
    {
      "epoch": 0.81,
      "learning_rate": 2e-05,
      "loss": 0.1572,
      "step": 25
    },
    {
      "epoch": 0.84,
      "learning_rate": 2e-05,
      "loss": 0.1584,
      "step": 26
    },
    {
      "epoch": 0.87,
      "learning_rate": 2e-05,
      "loss": 0.1638,
      "step": 27
    },
    {
      "epoch": 0.9,
      "learning_rate": 2e-05,
      "loss": 0.1465,
      "step": 28
    },
    {
      "epoch": 0.94,
      "learning_rate": 2e-05,
      "loss": 0.1521,
      "step": 29
    },
    {
      "epoch": 0.97,
      "learning_rate": 2e-05,
      "loss": 0.1482,
      "step": 30
    },
    {
      "epoch": 1.0,
      "learning_rate": 2e-05,
      "loss": 0.1616,
      "step": 31
    },
    {
      "epoch": 1.03,
      "learning_rate": 2e-05,
      "loss": 0.0868,
      "step": 32
    },
    {
      "epoch": 1.06,
      "learning_rate": 2e-05,
      "loss": 0.0803,
      "step": 33
    },
    {
      "epoch": 1.1,
      "learning_rate": 2e-05,
      "loss": 0.0834,
      "step": 34
    },
    {
      "epoch": 1.13,
      "learning_rate": 2e-05,
      "loss": 0.0759,
      "step": 35
    },
    {
      "epoch": 1.16,
      "learning_rate": 2e-05,
      "loss": 0.0704,
      "step": 36
    },
    {
      "epoch": 1.19,
      "learning_rate": 2e-05,
      "loss": 0.0672,
      "step": 37
    },
    {
      "epoch": 1.23,
      "learning_rate": 2e-05,
      "loss": 0.0763,
      "step": 38
    },
    {
      "epoch": 1.26,
      "learning_rate": 2e-05,
      "loss": 0.0711,
      "step": 39
    },
    {
      "epoch": 1.29,
      "learning_rate": 2e-05,
      "loss": 0.0661,
      "step": 40
    },
    {
      "epoch": 1.32,
      "learning_rate": 2e-05,
      "loss": 0.0707,
      "step": 41
    },
    {
      "epoch": 1.35,
      "learning_rate": 2e-05,
      "loss": 0.0725,
      "step": 42
    },
    {
      "epoch": 1.39,
      "learning_rate": 2e-05,
      "loss": 0.0702,
      "step": 43
    },
    {
      "epoch": 1.42,
      "learning_rate": 2e-05,
      "loss": 0.0664,
      "step": 44
    },
    {
      "epoch": 1.45,
      "learning_rate": 2e-05,
      "loss": 0.0623,
      "step": 45
    },
    {
      "epoch": 1.48,
      "learning_rate": 2e-05,
      "loss": 0.0659,
      "step": 46
    },
    {
      "epoch": 1.52,
      "learning_rate": 2e-05,
      "loss": 0.0704,
      "step": 47
    },
    {
      "epoch": 1.55,
      "learning_rate": 2e-05,
      "loss": 0.0677,
      "step": 48
    },
    {
      "epoch": 1.58,
      "learning_rate": 2e-05,
      "loss": 0.0682,
      "step": 49
    },
    {
      "epoch": 1.61,
      "learning_rate": 2e-05,
      "loss": 0.0605,
      "step": 50
    },
    {
      "epoch": 1.65,
      "learning_rate": 2e-05,
      "loss": 0.0675,
      "step": 51
    },
    {
      "epoch": 1.68,
      "learning_rate": 2e-05,
      "loss": 0.0659,
      "step": 52
    },
    {
      "epoch": 1.71,
      "learning_rate": 2e-05,
      "loss": 0.0597,
      "step": 53
    },
    {
      "epoch": 1.74,
      "learning_rate": 2e-05,
      "loss": 0.0614,
      "step": 54
    },
    {
      "epoch": 1.77,
      "learning_rate": 2e-05,
      "loss": 0.066,
      "step": 55
    },
    {
      "epoch": 1.81,
      "learning_rate": 2e-05,
      "loss": 0.0682,
      "step": 56
    },
    {
      "epoch": 1.84,
      "learning_rate": 2e-05,
      "loss": 0.0654,
      "step": 57
    },
    {
      "epoch": 1.87,
      "learning_rate": 2e-05,
      "loss": 0.0692,
      "step": 58
    },
    {
      "epoch": 1.9,
      "learning_rate": 2e-05,
      "loss": 0.0706,
      "step": 59
    },
    {
      "epoch": 1.94,
      "learning_rate": 2e-05,
      "loss": 0.0628,
      "step": 60
    },
    {
      "epoch": 1.97,
      "learning_rate": 2e-05,
      "loss": 0.0714,
      "step": 61
    },
    {
      "epoch": 2.0,
      "learning_rate": 2e-05,
      "loss": 0.067,
      "step": 62
    },
    {
      "epoch": 2.03,
      "learning_rate": 2e-05,
      "loss": 0.0299,
      "step": 63
    },
    {
      "epoch": 2.06,
      "learning_rate": 2e-05,
      "loss": 0.0343,
      "step": 64
    },
    {
      "epoch": 2.1,
      "learning_rate": 2e-05,
      "loss": 0.0326,
      "step": 65
    },
    {
      "epoch": 2.13,
      "learning_rate": 2e-05,
      "loss": 0.0286,
      "step": 66
    },
    {
      "epoch": 2.16,
      "learning_rate": 2e-05,
      "loss": 0.0299,
      "step": 67
    },
    {
      "epoch": 2.19,
      "learning_rate": 2e-05,
      "loss": 0.0268,
      "step": 68
    },
    {
      "epoch": 2.23,
      "learning_rate": 2e-05,
      "loss": 0.0327,
      "step": 69
    },
    {
      "epoch": 2.26,
      "learning_rate": 2e-05,
      "loss": 0.0294,
      "step": 70
    },
    {
      "epoch": 2.29,
      "learning_rate": 2e-05,
      "loss": 0.0314,
      "step": 71
    },
    {
      "epoch": 2.32,
      "learning_rate": 2e-05,
      "loss": 0.0317,
      "step": 72
    },
    {
      "epoch": 2.35,
      "learning_rate": 2e-05,
      "loss": 0.0312,
      "step": 73
    },
    {
      "epoch": 2.39,
      "learning_rate": 2e-05,
      "loss": 0.0291,
      "step": 74
    },
    {
      "epoch": 2.42,
      "learning_rate": 2e-05,
      "loss": 0.0332,
      "step": 75
    },
    {
      "epoch": 2.45,
      "learning_rate": 2e-05,
      "loss": 0.0325,
      "step": 76
    },
    {
      "epoch": 2.48,
      "learning_rate": 2e-05,
      "loss": 0.0323,
      "step": 77
    },
    {
      "epoch": 2.52,
      "learning_rate": 2e-05,
      "loss": 0.0321,
      "step": 78
    },
    {
      "epoch": 2.55,
      "learning_rate": 2e-05,
      "loss": 0.0302,
      "step": 79
    },
    {
      "epoch": 2.58,
      "learning_rate": 2e-05,
      "loss": 0.0303,
      "step": 80
    },
    {
      "epoch": 2.61,
      "learning_rate": 2e-05,
      "loss": 0.0305,
      "step": 81
    },
    {
      "epoch": 2.65,
      "learning_rate": 2e-05,
      "loss": 0.0353,
      "step": 82
    },
    {
      "epoch": 2.68,
      "learning_rate": 2e-05,
      "loss": 0.0315,
      "step": 83
    },
    {
      "epoch": 2.71,
      "learning_rate": 2e-05,
      "loss": 0.0296,
      "step": 84
    },
    {
      "epoch": 2.74,
      "learning_rate": 2e-05,
      "loss": 0.0347,
      "step": 85
    },
    {
      "epoch": 2.77,
      "learning_rate": 2e-05,
      "loss": 0.0323,
      "step": 86
    },
    {
      "epoch": 2.81,
      "learning_rate": 2e-05,
      "loss": 0.0351,
      "step": 87
    },
    {
      "epoch": 2.84,
      "learning_rate": 2e-05,
      "loss": 0.0326,
      "step": 88
    },
    {
      "epoch": 2.87,
      "learning_rate": 2e-05,
      "loss": 0.033,
      "step": 89
    },
    {
      "epoch": 2.9,
      "learning_rate": 2e-05,
      "loss": 0.0353,
      "step": 90
    },
    {
      "epoch": 2.94,
      "learning_rate": 2e-05,
      "loss": 0.035,
      "step": 91
    },
    {
      "epoch": 2.97,
      "learning_rate": 2e-05,
      "loss": 0.0375,
      "step": 92
    },
    {
      "epoch": 3.0,
      "learning_rate": 2e-05,
      "loss": 0.0309,
      "step": 93
    },
    {
      "epoch": 3.0,
      "step": 93,
      "total_flos": 59878932480000.0,
      "train_loss": 0.09940362745715726,
      "train_runtime": 10240.8014,
      "train_samples_per_second": 1.153,
      "train_steps_per_second": 0.009
    }
  ],
  "max_steps": 93,
  "num_train_epochs": 3,
  "total_flos": 59878932480000.0,
  "trial_name": null,
  "trial_params": null
}