{
    "epoch": 1.0,
    "eval_logits/chosen": NaN,
    "eval_logits/rejected": NaN,
    "eval_logps/chosen": -293.10638427734375,
    "eval_logps/rejected": -305.5957336425781,
    "eval_loss": 0.39389675855636597,
    "eval_rewards/accuracies": 0.5302526354789734,
    "eval_rewards/chosen": 0.5095370411872864,
    "eval_rewards/margins": 1.1601146459579468,
    "eval_rewards/rejected": -0.6507880091667175,
    "eval_runtime": 290.9966,
    "eval_samples": 1445,
    "eval_samples_per_second": 15.423,
    "eval_steps_per_second": 0.244,
    "total_flos": 0.0,
    "train_loss": 0.48351796468098956,
    "train_runtime": 4731.3673,
    "train_samples": 5776,
    "train_samples_per_second": 3.793,
    "train_steps_per_second": 0.01
}