{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 8,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.12,
      "grad_norm": 6.875,
      "learning_rate": 0.0002,
      "loss": 6.4878,
      "step": 1
    },
    {
      "epoch": 0.62,
      "grad_norm": 4.25,
      "learning_rate": 7.774790660436858e-05,
      "loss": 6.3165,
      "step": 5
    },
    {
      "epoch": 1.0,
      "step": 8,
      "total_flos": 133781520384000.0,
      "train_loss": 6.2669631242752075,
      "train_runtime": 15.755,
      "train_samples_per_second": 15.931,
      "train_steps_per_second": 0.508
    }
  ],
  "logging_steps": 5,
  "max_steps": 8,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 133781520384000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}