{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0007006849195088199,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00014013698390176398,
      "grad_norm": 1.7928739786148071,
      "learning_rate": 1e-05,
      "loss": 178.0,
      "step": 1
    },
    {
      "epoch": 0.00014013698390176398,
      "eval_loss": 11.12308120727539,
      "eval_runtime": 42.95,
      "eval_samples_per_second": 279.837,
      "eval_steps_per_second": 139.93,
      "step": 1
    },
    {
      "epoch": 0.00028027396780352796,
      "grad_norm": 1.7738882303237915,
      "learning_rate": 2e-05,
      "loss": 178.0,
      "step": 2
    },
    {
      "epoch": 0.00028027396780352796,
      "eval_loss": 11.123008728027344,
      "eval_runtime": 23.6559,
      "eval_samples_per_second": 508.077,
      "eval_steps_per_second": 254.06,
      "step": 2
    },
    {
      "epoch": 0.0004204109517052919,
      "grad_norm": 1.7602485418319702,
      "learning_rate": 3e-05,
      "loss": 177.875,
      "step": 3
    },
    {
      "epoch": 0.0005605479356070559,
      "grad_norm": 1.7805070877075195,
      "learning_rate": 4e-05,
      "loss": 178.0,
      "step": 4
    },
    {
      "epoch": 0.0005605479356070559,
      "eval_loss": 11.122883796691895,
      "eval_runtime": 23.7779,
      "eval_samples_per_second": 505.469,
      "eval_steps_per_second": 252.756,
      "step": 4
    },
    {
      "epoch": 0.0007006849195088199,
      "grad_norm": 1.7050721645355225,
      "learning_rate": 5e-05,
      "loss": 178.0,
      "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": 352035274752.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}