{
    "epoch": 1.0,
    "eval_logits/chosen": 1.2706230878829956,
    "eval_logits/rejected": 1.4739606380462646,
    "eval_logps/chosen": -388.3653564453125,
    "eval_logps/rejected": -344.6841735839844,
    "eval_loss": 0.6931473612785339,
    "eval_model_preparation_time": 0.0234,
    "eval_rewards/accuracies": 0.0,
    "eval_rewards/chosen": 0.0,
    "eval_rewards/margins": 0.0,
    "eval_rewards/rejected": 0.0,
    "eval_runtime": 229.758,
    "eval_samples": 2000,
    "eval_samples_per_second": 8.705,
    "eval_steps_per_second": 1.088,
    "total_flos": 0.0,
    "train_loss": 0.0,
    "train_runtime": 0.0101,
    "train_samples": 61134,
    "train_samples_per_second": 6068984.159,
    "train_steps_per_second": 379323.919
}