{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9944064636420137,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.3211,
      "step": 2
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.1994,
      "step": 4
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 2.1871,
      "step": 6
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 2.1569,
      "step": 8
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 2.1101,
      "step": 10
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 2.1361,
      "step": 12
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 2.002,
      "step": 14
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 2.1144,
      "step": 16
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 1.9981,
      "step": 18
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 1.8518,
      "step": 20
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 2.0797,
      "step": 22
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 1.9593,
      "step": 24
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 2.1172,
      "step": 26
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 2.056,
      "step": 28
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 1.9752,
      "step": 30
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 2.0642,
      "step": 32
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 2.082,
      "step": 34
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 2.0809,
      "step": 36
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 1.9503,
      "step": 38
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 1.9841,
      "step": 40
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 1.954,
      "step": 42
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 1.8861,
      "step": 44
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 1.9725,
      "step": 46
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 1.8173,
      "step": 48
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 1.9095,
      "step": 50
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 1.9165,
      "step": 52
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 1.954,
      "step": 54
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 2.0812,
      "step": 56
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 1.9473,
      "step": 58
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 2.0644,
      "step": 60
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 2.0597,
      "step": 62
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 1.9422,
      "step": 64
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 1.8022,
      "step": 66
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 1.9411,
      "step": 68
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 1.8742,
      "step": 70
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 1.8078,
      "step": 72
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 1.9996,
      "step": 74
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 1.7464,
      "step": 76
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 1.8637,
      "step": 78
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 1.9297,
      "step": 80
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 1.9462,
      "step": 82
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 1.9367,
      "step": 84
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 1.9843,
      "step": 86
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 2.0611,
      "step": 88
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 1.8584,
      "step": 90
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002,
      "loss": 1.8235,
      "step": 92
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 1.9358,
      "step": 94
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002,
      "loss": 1.854,
      "step": 96
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002,
      "loss": 1.8953,
      "step": 98
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002,
      "loss": 1.7185,
      "step": 100
    }
  ],
  "logging_steps": 2,
  "max_steps": 300,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 1.3484808608858112e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}