all_results.json

{
    "epoch": 0.9221902017291066,
    "eval_logits/chosen": -0.010169930756092072,
    "eval_logits/rejected": 0.1450614333152771,
    "eval_logps/chosen": -138.02931213378906,
    "eval_logps/ref_chosen": -137.93557739257812,
    "eval_logps/ref_rejected": -174.6787567138672,
    "eval_logps/rejected": -174.78001403808594,
    "eval_loss": 0.6931137442588806,
    "eval_rewards/accuracies": 0.5064814686775208,
    "eval_rewards/chosen": -0.0009374108631163836,
    "eval_rewards/margins": 7.527563138864934e-05,
    "eval_rewards/rejected": -0.0010126865236088634,
    "eval_runtime": 146.6534,
    "eval_samples": 1080,
    "eval_samples_per_second": 7.364,
    "eval_steps_per_second": 1.841,
    "total_flos": 0.0,
    "train_loss": 0.6935525000095367,
    "train_runtime": 687.8249,
    "train_samples": 1387,
    "train_samples_per_second": 2.017,
    "train_steps_per_second": 0.015
}