{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 8.08108108108108,
  "eval_steps": 500,
  "global_step": 54,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.03,
      "learning_rate": 4.1791044776119404e-05,
      "loss": 1.8411,
      "step": 14
    },
    {
      "epoch": 4.05,
      "learning_rate": 8.358208955223881e-05,
      "loss": 1.439,
      "step": 28
    },
    {
      "epoch": 6.08,
      "learning_rate": 0.00012537313432835822,
      "loss": 1.127,
      "step": 42
    }
  ],
  "logging_steps": 14,
  "max_steps": 666,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "save_steps": 500,
  "total_flos": 8413941168340992.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}