eval_results.json

{
    "epoch": 2.986666666666667,
    "eval_logits/chosen": -2.242171049118042,
    "eval_logits/rejected": -2.265955924987793,
    "eval_logps/chosen": -0.11519017815589905,
    "eval_logps/rejected": -0.4500538110733032,
    "eval_loss": 0.16089552640914917,
    "eval_odds_ratio_loss": 1.4658138751983643,
    "eval_rewards/accuracies": 0.7900000214576721,
    "eval_rewards/chosen": -0.011519019491970539,
    "eval_rewards/margins": 0.033486369997262955,
    "eval_rewards/rejected": -0.04500538855791092,
    "eval_runtime": 5.4517,
    "eval_samples_per_second": 18.343,
    "eval_sft_loss": 0.01431415043771267,
    "eval_steps_per_second": 9.171
}