{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.8421052631578947,
  "eval_steps": 500,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 1.9781250953674316,
      "learning_rate": 0.00018,
      "loss": 3.0759,
      "step": 2
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 1.2719974517822266,
      "learning_rate": 0.00014,
      "loss": 2.8573,
      "step": 4
    },
    {
      "epoch": 1.2105263157894737,
      "grad_norm": 1.1247334480285645,
      "learning_rate": 0.0001,
      "loss": 2.6998,
      "step": 6
    },
    {
      "epoch": 1.631578947368421,
      "grad_norm": 1.1965047121047974,
      "learning_rate": 6e-05,
      "loss": 2.662,
      "step": 8
    }
  ],
  "logging_steps": 2,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 1,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5377835768217600.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}