all_results.json

{
    "epoch": 2.996074326092646,
    "eval_logits/chosen": -0.34099623560905457,
    "eval_logits/rejected": -0.3685227334499359,
    "eval_logps/chosen": -310.2510070800781,
    "eval_logps/rejected": -275.43145751953125,
    "eval_loss": 0.587827205657959,
    "eval_rewards/accuracies": 0.6746031641960144,
    "eval_rewards/chosen": 0.01673175022006035,
    "eval_rewards/margins": 0.5906793475151062,
    "eval_rewards/rejected": -0.573947548866272,
    "eval_runtime": 18.8462,
    "eval_samples": 2000,
    "eval_samples_per_second": 106.122,
    "eval_steps_per_second": 3.343,
    "total_flos": 0.0,
    "train_loss": 0.5334697115221363,
    "train_runtime": 7355.3343,
    "train_samples": 61134,
    "train_samples_per_second": 24.935,
    "train_steps_per_second": 0.195
}