{
  "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": 2.6931,
      "step": 2
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.6707,
      "step": 4
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 2.5183,
      "step": 6
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 2.4502,
      "step": 8
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 2.4194,
      "step": 10
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 2.4193,
      "step": 12
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 2.4072,
      "step": 14
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 2.3361,
      "step": 16
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 2.2092,
      "step": 18
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 2.0599,
      "step": 20
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 2.2369,
      "step": 22
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 2.2907,
      "step": 24
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 2.3011,
      "step": 26
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 2.293,
      "step": 28
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 2.2613,
      "step": 30
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 2.2901,
      "step": 32
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 2.2055,
      "step": 34
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 2.2096,
      "step": 36
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 2.2654,
      "step": 38
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 2.299,
      "step": 40
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 2.3991,
      "step": 42
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 2.1495,
      "step": 44
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 2.1673,
      "step": 46
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 2.237,
      "step": 48
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 2.021,
      "step": 50
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 2.3035,
      "step": 52
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 2.2549,
      "step": 54
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 2.2397,
      "step": 56
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 2.2625,
      "step": 58
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 2.2464,
      "step": 60
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 2.1344,
      "step": 62
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 2.3451,
      "step": 64
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 2.2563,
      "step": 66
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 2.0357,
      "step": 68
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 2.1469,
      "step": 70
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 2.0337,
      "step": 72
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 2.2292,
      "step": 74
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 2.195,
      "step": 76
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 2.143,
      "step": 78
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 2.1249,
      "step": 80
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 2.159,
      "step": 82
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 2.1811,
      "step": 84
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 2.2489,
      "step": 86
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 2.2126,
      "step": 88
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 2.1654,
      "step": 90
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002,
      "loss": 2.0623,
      "step": 92
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 1.9155,
      "step": 94
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002,
      "loss": 2.0686,
      "step": 96
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002,
      "loss": 2.0405,
      "step": 98
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002,
      "loss": 1.9848,
      "step": 100
    }
  ],
  "logging_steps": 2,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 8620200718270464.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}