{ "epoch": 3.0, "eval_logits/chosen": -2.35003924369812, "eval_logits/rejected": -2.296473503112793, "eval_logps/chosen": -278.26385498046875, "eval_logps/rejected": -376.85308837890625, "eval_loss": 0.03253357484936714, "eval_rewards/accuracies": 0.9613811373710632, "eval_rewards/chosen": -2.0301272869110107, "eval_rewards/margins": 12.106389045715332, "eval_rewards/rejected": -14.136518478393555, "eval_runtime": 2927.9433, "eval_samples": 3156, "eval_samples_per_second": 22.703, "eval_steps_per_second": 0.355, "train_loss": 0.2383290374584692, "train_runtime": 16014.0387, "train_samples": 64345, "train_samples_per_second": 11.855, "train_steps_per_second": 0.741 }