{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 8,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 1.0357906276529485,
      "epoch": 1.32,
      "grad_norm": 4.6333298087120056e-08,
      "learning_rate": 3.056302334890786e-05,
      "logits/chosen": -1.838661071080771,
      "logits/rejected": -2.4544702951621793,
      "logps/chosen": -436.7531114058061,
      "logps/rejected": -210.63715293190697,
      "loss": 0.2772590160369873,
      "mean_token_accuracy": 0.7666837265997222,
      "num_tokens": 16568.0,
      "rewards/accuracies": 0.5151515151515151,
      "rewards/chosen": 2.7604801820760425,
      "rewards/margins": 11.160122062220719,
      "rewards/rejected": -8.399641788367068,
      "step": 5
    }
  ],
  "logging_steps": 5,
  "max_steps": 8,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4031731650527232.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}