{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.995887594242632,
  "eval_steps": 500,
  "global_step": 728,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8,
      "learning_rate": 0.0001334351145038168,
      "loss": 3.0236,
      "step": 291
    },
    {
      "epoch": 1.6,
      "learning_rate": 4.458015267175573e-05,
      "loss": 2.5605,
      "step": 582
    }
  ],
  "logging_steps": 291,
  "max_steps": 728,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 594439372800000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}