{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 157,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.6369426751592356,
      "grad_norm": 8.715664863586426,
      "learning_rate": 1.4701513386718959e-05,
      "loss": 3.8477,
      "step": 100
    },
    {
      "epoch": 0.6369426751592356,
      "eval_loss": 2.9882283210754395,
      "eval_runtime": 3.592,
      "eval_samples_per_second": 139.197,
      "eval_steps_per_second": 4.454,
      "step": 100
    }
  ],
  "logging_steps": 100,
  "max_steps": 157,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 313567440076800.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 4.049364213534871e-05,
    "num_train_epochs": 1,
    "per_device_train_batch_size": 16,
    "seed": 12
  }
}