{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0273972602739726,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005479452054794521,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.005479452054794521,
      "eval_loss": NaN,
      "eval_runtime": 106.8707,
      "eval_samples_per_second": 2.882,
      "eval_steps_per_second": 1.441,
      "step": 1
    },
    {
      "epoch": 0.010958904109589041,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.6613,
      "step": 2
    },
    {
      "epoch": 0.010958904109589041,
      "eval_loss": NaN,
      "eval_runtime": 23.3102,
      "eval_samples_per_second": 13.213,
      "eval_steps_per_second": 6.607,
      "step": 2
    },
    {
      "epoch": 0.01643835616438356,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.021917808219178082,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 470.8011,
      "step": 4
    },
    {
      "epoch": 0.021917808219178082,
      "eval_loss": NaN,
      "eval_runtime": 23.32,
      "eval_samples_per_second": 13.208,
      "eval_steps_per_second": 6.604,
      "step": 4
    },
    {
      "epoch": 0.0273972602739726,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "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": 6622016975142912.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}