all_results.json

{
    "epoch": 2.994495412844037,
    "eval_logits/chosen": -0.21853114664554596,
    "eval_logits/rejected": -1.4117213487625122,
    "eval_logps/chosen": -274.8548889160156,
    "eval_logps/rejected": -203.45323181152344,
    "eval_loss": 0.06784019619226456,
    "eval_rewards/accuracies": 0.9777777791023254,
    "eval_rewards/chosen": 0.9461619257926941,
    "eval_rewards/margins": 4.006012916564941,
    "eval_rewards/rejected": -3.05985164642334,
    "eval_runtime": 8.9688,
    "eval_samples_per_second": 5.017,
    "eval_steps_per_second": 5.017,
    "total_flos": 7.837376281021809e+17,
    "train_loss": 0.220101895632551,
    "train_runtime": 8071.0106,
    "train_samples_per_second": 1.619,
    "train_steps_per_second": 0.051
}