all_results.json

{
    "epoch": 0.9989258861439313,
    "eval_logits/chosen": -13.021403312683105,
    "eval_logits/rejected": -12.921746253967285,
    "eval_logps/chosen": -1.572052001953125,
    "eval_logps/rejected": -1.9804316759109497,
    "eval_loss": 2.196369171142578,
    "eval_rewards/accuracies": 0.7622950673103333,
    "eval_rewards/chosen": -15.720520973205566,
    "eval_rewards/margins": 4.083796501159668,
    "eval_rewards/rejected": -19.804317474365234,
    "eval_runtime": 68.1765,
    "eval_samples": 1941,
    "eval_samples_per_second": 28.47,
    "eval_steps_per_second": 0.895,
    "total_flos": 0.0,
    "train_loss": 2.883953002191359,
    "train_runtime": 6137.844,
    "train_samples": 59569,
    "train_samples_per_second": 9.705,
    "train_steps_per_second": 0.076
}