{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 5,
  "global_step": 8,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5,
      "learning_rate": 2.9999177540482684e-05,
      "loss": 2.6428,
      "step": 2
    },
    {
      "epoch": 1.0,
      "learning_rate": 2.9996710252122685e-05,
      "loss": 2.1838,
      "step": 4
    },
    {
      "epoch": 1.5,
      "learning_rate": 2.9992598405485974e-05,
      "loss": 1.8524,
      "step": 6
    },
    {
      "epoch": 2.0,
      "learning_rate": 2.9986842451482876e-05,
      "loss": 1.59,
      "step": 8
    }
  ],
  "logging_steps": 2,
  "max_steps": 600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 150,
  "save_steps": 500,
  "total_flos": 381141185986560.0,
  "train_batch_size": 52,
  "trial_name": null,
  "trial_params": null
}