{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00045140064411399605,
  "eval_steps": 10,
  "global_step": 26,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.7361563235153692e-05,
      "eval_loss": 3.2406625747680664,
      "eval_runtime": 1557.6717,
      "eval_samples_per_second": 15.569,
      "eval_steps_per_second": 7.785,
      "step": 1
    },
    {
      "epoch": 8.680781617576846e-05,
      "grad_norm": 57.20978927612305,
      "learning_rate": 5e-05,
      "loss": 12.0897,
      "step": 5
    },
    {
      "epoch": 0.00017361563235153692,
      "grad_norm": 54.81013107299805,
      "learning_rate": 0.0001,
      "loss": 8.6169,
      "step": 10
    },
    {
      "epoch": 0.00017361563235153692,
      "eval_loss": 1.9173833131790161,
      "eval_runtime": 1562.5591,
      "eval_samples_per_second": 15.521,
      "eval_steps_per_second": 7.76,
      "step": 10
    },
    {
      "epoch": 0.0002604234485273054,
      "grad_norm": 30.663660049438477,
      "learning_rate": 9.619397662556435e-05,
      "loss": 7.1643,
      "step": 15
    },
    {
      "epoch": 0.00034723126470307384,
      "grad_norm": 31.651548385620117,
      "learning_rate": 8.535533905932738e-05,
      "loss": 6.5708,
      "step": 20
    },
    {
      "epoch": 0.00034723126470307384,
      "eval_loss": 1.364366888999939,
      "eval_runtime": 1565.5286,
      "eval_samples_per_second": 15.491,
      "eval_steps_per_second": 7.746,
      "step": 20
    },
    {
      "epoch": 0.00043403908087884236,
      "grad_norm": 27.65591812133789,
      "learning_rate": 6.91341716182545e-05,
      "loss": 5.2812,
      "step": 25
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4557025195327488.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}