{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.625,
  "eval_steps": 500,
  "global_step": 45,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17,
      "learning_rate": 0.0001,
      "loss": 1.7712,
      "step": 4
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 1.6693,
      "step": 8
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001875,
      "loss": 1.4335,
      "step": 12
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.000175,
      "loss": 1.2715,
      "step": 16
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00016250000000000002,
      "loss": 1.0717,
      "step": 20
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.9823,
      "step": 24
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0001375,
      "loss": 0.8258,
      "step": 28
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.000125,
      "loss": 0.8132,
      "step": 32
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.00011250000000000001,
      "loss": 0.8318,
      "step": 36
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.0001,
      "loss": 0.7582,
      "step": 40
    },
    {
      "epoch": 2.58,
      "learning_rate": 8.75e-05,
      "loss": 0.7435,
      "step": 44
    }
  ],
  "logging_steps": 4,
  "max_steps": 72,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 7194533859164160.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}