{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0001245204018895971,
  "eval_steps": 500,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 75.3083267211914,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 3.6651,
      "step": 20
    },
    {
      "epoch": 0.0,
      "grad_norm": 90.37364196777344,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 3.7271,
      "step": 40
    }
  ],
  "logging_steps": 20,
  "max_steps": 20000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 20,
  "total_flos": 82442575564800.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}