{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 76,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 8.88134765625,
      "learning_rate": 4.9453690018345144e-06,
      "loss": 14.8998,
      "step": 20
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 4.847199440002441,
      "learning_rate": 3.272542485937369e-06,
      "loss": 8.4322,
      "step": 40
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 4.938084602355957,
      "learning_rate": 8.271734841028553e-07,
      "loss": 7.4731,
      "step": 60
    }
  ],
  "logging_steps": 20,
  "max_steps": 76,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2993694084956160.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}