{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7045561296383278,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.7,
      "grad_norm": 2.76055908203125,
      "learning_rate": 0.00016473906911142455,
      "loss": 3.9965,
      "step": 500
    }
  ],
  "logging_steps": 500,
  "max_steps": 2836,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "total_flos": 195969024000000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}