all_results.json

{
    "epoch": 3.0,
    "eval_logits/chosen": -2.10288143157959,
    "eval_logits/rejected": -2.1299264430999756,
    "eval_logps/chosen": -289.6983642578125,
    "eval_logps/rejected": -310.9796142578125,
    "eval_loss": 1.0245678424835205,
    "eval_rewards/accuracies": 0.579365074634552,
    "eval_rewards/chosen": -5.276275157928467,
    "eval_rewards/margins": 0.5837584733963013,
    "eval_rewards/rejected": -5.8600335121154785,
    "eval_runtime": 135.2014,
    "eval_samples": 1000,
    "eval_samples_per_second": 7.396,
    "eval_steps_per_second": 0.466,
    "train_loss": 0.23198359412724215,
    "train_runtime": 18849.1473,
    "train_samples": 19958,
    "train_samples_per_second": 3.176,
    "train_steps_per_second": 0.05
}