eval_results.json

{
    "epoch": 1.0,
    "eval_logits/chosen": -3.0078587532043457,
    "eval_logits/rejected": -3.042999744415283,
    "eval_logps/chosen": -194.36697387695312,
    "eval_logps/rejected": -179.82501220703125,
    "eval_loss": 0.6931471824645996,
    "eval_rewards/accuracies": 0.0,
    "eval_rewards/chosen": 0.0,
    "eval_rewards/margins": 0.0,
    "eval_rewards/rejected": 0.0,
    "eval_runtime": 5.0964,
    "eval_samples": 10,
    "eval_samples_per_second": 1.962,
    "eval_steps_per_second": 0.392
}