{
  "best_global_step": 427,
  "best_metric": 4.619469165802002,
  "best_model_checkpoint": null,
  "epoch": 1.17096018735363,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00234192037470726,
      "grad_norm": 19.51460075378418,
      "learning_rate": 0.0,
      "loss": 10.4086,
      "step": 1
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.20932137966156,
      "learning_rate": 8.52e-05,
      "loss": 5.6615,
      "step": 427
    },
    {
      "epoch": 1.0,
      "eval_loss": 4.619469165802002,
      "eval_runtime": 17.5001,
      "eval_samples_per_second": 1285.705,
      "eval_steps_per_second": 5.029,
      "step": 427
    }
  ],
  "logging_steps": 500,
  "max_steps": 2135,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 8352265125888000.0,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}