eval_results.json

{
    "epoch": 1.971563981042654,
    "eval_logits/chosen": 101.8805923461914,
    "eval_logits/rejected": 96.05239868164062,
    "eval_logps/chosen": -416.339111328125,
    "eval_logps/rejected": -439.9419250488281,
    "eval_loss": 0.5273366570472717,
    "eval_rewards/accuracies": 0.7291666865348816,
    "eval_rewards/chosen": -2.633545160293579,
    "eval_rewards/margins": 1.2600029706954956,
    "eval_rewards/rejected": -3.893548011779785,
    "eval_runtime": 119.4302,
    "eval_samples": 750,
    "eval_samples_per_second": 6.28,
    "eval_steps_per_second": 0.201
}