eval_results.json

{
    "epoch": 1.0,
    "eval_logits/chosen": -3.3306896686553955,
    "eval_logits/rejected": -3.137249708175659,
    "eval_logps/chosen": -1001.12890625,
    "eval_logps/rejected": -1768.898193359375,
    "eval_loss": 0.2304462045431137,
    "eval_rewards/accuracies": 0.8472222089767456,
    "eval_rewards/chosen": -1.4963774681091309,
    "eval_rewards/margins": 7.075459003448486,
    "eval_rewards/rejected": -8.5718355178833,
    "eval_runtime": 34.9747,
    "eval_samples": 284,
    "eval_samples_per_second": 8.12,
    "eval_steps_per_second": 0.257
}