all_results.json

{
    "epoch": 1.0,
    "eval_logits/chosen": -0.42766323685646057,
    "eval_logits/rejected": -0.4719906747341156,
    "eval_logps/chosen": -477.8221130371094,
    "eval_logps/rejected": -650.3414306640625,
    "eval_loss": 0.4395619034767151,
    "eval_rewards/accuracies": 0.949999988079071,
    "eval_rewards/chosen": -0.17786642909049988,
    "eval_rewards/margins": 1.0689051151275635,
    "eval_rewards/rejected": -1.2467713356018066,
    "eval_runtime": 37.8151,
    "eval_samples": 320,
    "eval_samples_per_second": 8.462,
    "eval_steps_per_second": 0.264,
    "train_loss": 0.05898992068894947,
    "train_runtime": 471.0672,
    "train_samples": 8410,
    "train_samples_per_second": 17.853,
    "train_steps_per_second": 0.278
}