{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00034723126470307384,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.944625294061477e-05,
      "grad_norm": 12.151758193969727,
      "learning_rate": 1e-05,
      "loss": 32.4648,
      "step": 1
    },
    {
      "epoch": 6.944625294061477e-05,
      "eval_loss": 2.1851887702941895,
      "eval_runtime": 2261.5184,
      "eval_samples_per_second": 10.724,
      "eval_steps_per_second": 5.362,
      "step": 1
    },
    {
      "epoch": 0.00013889250588122954,
      "grad_norm": 18.634037017822266,
      "learning_rate": 2e-05,
      "loss": 35.272,
      "step": 2
    },
    {
      "epoch": 0.00013889250588122954,
      "eval_loss": 2.15849232673645,
      "eval_runtime": 2164.1391,
      "eval_samples_per_second": 11.206,
      "eval_steps_per_second": 5.603,
      "step": 2
    },
    {
      "epoch": 0.00020833875882184433,
      "grad_norm": 12.105293273925781,
      "learning_rate": 3e-05,
      "loss": 34.441,
      "step": 3
    },
    {
      "epoch": 0.0002777850117624591,
      "grad_norm": 16.02633285522461,
      "learning_rate": 4e-05,
      "loss": 37.2006,
      "step": 4
    },
    {
      "epoch": 0.0002777850117624591,
      "eval_loss": 2.142667770385742,
      "eval_runtime": 2746.0669,
      "eval_samples_per_second": 8.832,
      "eval_steps_per_second": 4.416,
      "step": 4
    },
    {
      "epoch": 0.00034723126470307384,
      "grad_norm": 14.910778999328613,
      "learning_rate": 5e-05,
      "loss": 34.6226,
      "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": 3298217215131648.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}