{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 261,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3831417624521073,
      "grad_norm": 0.691992998123169,
      "learning_rate": 3.103448275862069e-05,
      "loss": 0.258,
      "step": 100
    },
    {
      "epoch": 0.7662835249042146,
      "grad_norm": 1.280352234840393,
      "learning_rate": 1.1877394636015327e-05,
      "loss": 0.0693,
      "step": 200
    },
    {
      "epoch": 1.0,
      "step": 261,
      "total_flos": 381121355275344.0,
      "train_loss": 0.1387540928705442,
      "train_runtime": 1240.6431,
      "train_samples_per_second": 6.709,
      "train_steps_per_second": 0.21
    }
  ],
  "logging_steps": 100,
  "max_steps": 261,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100.0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 381121355275344.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}