{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.12618296529968454,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.025236593059936908,
      "grad_norm": 22.806657791137695,
      "learning_rate": 1e-05,
      "loss": 11.9166,
      "step": 1
    },
    {
      "epoch": 0.025236593059936908,
      "eval_loss": 11.514793395996094,
      "eval_runtime": 181.6585,
      "eval_samples_per_second": 0.369,
      "eval_steps_per_second": 0.187,
      "step": 1
    },
    {
      "epoch": 0.050473186119873815,
      "grad_norm": 23.44769859313965,
      "learning_rate": 2e-05,
      "loss": 12.265,
      "step": 2
    },
    {
      "epoch": 0.050473186119873815,
      "eval_loss": 11.341726303100586,
      "eval_runtime": 2.0964,
      "eval_samples_per_second": 31.96,
      "eval_steps_per_second": 16.218,
      "step": 2
    },
    {
      "epoch": 0.07570977917981073,
      "grad_norm": 22.49645233154297,
      "learning_rate": 3e-05,
      "loss": 11.6675,
      "step": 3
    },
    {
      "epoch": 0.10094637223974763,
      "grad_norm": 22.60093116760254,
      "learning_rate": 4e-05,
      "loss": 11.3869,
      "step": 4
    },
    {
      "epoch": 0.10094637223974763,
      "eval_loss": 10.429825782775879,
      "eval_runtime": 2.0995,
      "eval_samples_per_second": 31.913,
      "eval_steps_per_second": 16.195,
      "step": 4
    },
    {
      "epoch": 0.12618296529968454,
      "grad_norm": 23.407760620117188,
      "learning_rate": 5e-05,
      "loss": 10.3096,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1137721427361792.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}