all_results.json

{
    "epoch": 1.0,
    "eval_logits/chosen": 83.16413879394531,
    "eval_logits/rejected": 83.84245300292969,
    "eval_logps/chosen": -392.341552734375,
    "eval_logps/rejected": -414.519775390625,
    "eval_loss": 0.40556877851486206,
    "eval_rewards/accuracies": 0.792553186416626,
    "eval_rewards/chosen": -0.3995126485824585,
    "eval_rewards/margins": 3.1725716590881348,
    "eval_rewards/rejected": -3.5720841884613037,
    "eval_runtime": 140.3273,
    "eval_samples": 3000,
    "eval_samples_per_second": 21.379,
    "eval_steps_per_second": 0.67,
    "train_loss": 0.5623811487565961,
    "train_runtime": 6612.2068,
    "train_samples": 72994,
    "train_samples_per_second": 11.039,
    "train_steps_per_second": 0.086
}