{
  "best_global_step": 422,
  "best_metric": 4.781050205230713,
  "best_model_checkpoint": null,
  "epoch": 1.1848341232227488,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002369668246445498,
      "grad_norm": 20.34552001953125,
      "learning_rate": 0.0,
      "loss": 10.3309,
      "step": 1
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.0193040370941162,
      "learning_rate": 8.42e-05,
      "loss": 5.762,
      "step": 422
    },
    {
      "epoch": 1.0,
      "eval_loss": 4.781050205230713,
      "eval_runtime": 21.3156,
      "eval_samples_per_second": 1292.106,
      "eval_steps_per_second": 5.067,
      "step": 422
    }
  ],
  "logging_steps": 500,
  "max_steps": 8440,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8360757116928000.0,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}