all_results.json

{
    "epoch": 1.0,
    "eval_logits/chosen": -2.884117841720581,
    "eval_logits/rejected": -1.7638154029846191,
    "eval_logps/chosen": -242.4412078857422,
    "eval_logps/rejected": -1144.0396728515625,
    "eval_loss": 0.0013236103113740683,
    "eval_rewards/accuracies": 1.0,
    "eval_rewards/chosen": -1.812609314918518,
    "eval_rewards/margins": 9.16053295135498,
    "eval_rewards/rejected": -10.97314167022705,
    "eval_runtime": 1.0748,
    "eval_samples": 5,
    "eval_samples_per_second": 4.652,
    "eval_steps_per_second": 2.791,
    "train_loss": 0.05805659896943479,
    "train_runtime": 136192.1568,
    "train_samples": 334157,
    "train_samples_per_second": 2.454,
    "train_steps_per_second": 0.613
}