{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002725538293813028,
  "eval_steps": 500,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 0.39290162920951843,
      "learning_rate": 1.5833333333333336e-06,
      "loss": 4.0074,
      "step": 20
    }
  ],
  "logging_steps": 20,
  "max_steps": 20000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 20,
  "total_flos": 9824796131328.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}