all_results.json

{
    "epoch": 3.0,
    "eval_logits/chosen": -2.965512990951538,
    "eval_logits/rejected": -2.9399757385253906,
    "eval_logps/chosen": -282.7847900390625,
    "eval_logps/rejected": -252.9479217529297,
    "eval_loss": -0.203842431306839,
    "eval_rewards/accuracies": 0.6840000152587891,
    "eval_rewards/chosen": -1.1628247499465942,
    "eval_rewards/margins": 1.2828813791275024,
    "eval_rewards/rejected": -2.4457061290740967,
    "eval_runtime": 444.1107,
    "eval_samples": 2000,
    "eval_samples_per_second": 4.503,
    "eval_steps_per_second": 0.281,
    "train_loss": 0.36701411283100355,
    "train_runtime": 84636.1866,
    "train_samples": 61966,
    "train_samples_per_second": 2.196,
    "train_steps_per_second": 0.034
}