{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6711409395973155,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.34,
      "grad_norm": 1.5860745906829834,
      "learning_rate": 4.440715883668904e-05,
      "loss": 0.536,
      "step": 500
    },
    {
      "epoch": 0.67,
      "grad_norm": 4.4774603843688965,
      "learning_rate": 3.881431767337807e-05,
      "loss": 0.5098,
      "step": 1000
    }
  ],
  "logging_steps": 500,
  "max_steps": 4470,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 419398321311552.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}