{
  "best_global_step": 392,
  "best_metric": 6.317445755004883,
  "best_model_checkpoint": null,
  "epoch": 1.2755102040816326,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002551020408163265,
      "grad_norm": 16.32339096069336,
      "learning_rate": 0.0,
      "loss": 10.3351,
      "step": 1
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.6908162236213684,
      "learning_rate": 7.82e-05,
      "loss": 7.1094,
      "step": 392
    },
    {
      "epoch": 1.0,
      "eval_loss": 6.317445755004883,
      "eval_runtime": 15.5824,
      "eval_samples_per_second": 1616.887,
      "eval_steps_per_second": 6.353,
      "step": 392
    }
  ],
  "logging_steps": 500,
  "max_steps": 7840,
  "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": 8353832878080000.0,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}