{ "epoch": 3.0, "eval_logits/chosen": -2.7541587352752686, "eval_logits/rejected": -2.7098710536956787, "eval_logps/chosen": -318.3198547363281, "eval_logps/rejected": -354.8788757324219, "eval_loss": 0.7910895347595215, "eval_rewards/accuracies": 0.7890625, "eval_rewards/chosen": -6.6703782081604, "eval_rewards/margins": 3.3793439865112305, "eval_rewards/rejected": -10.049721717834473, "eval_runtime": 82.4302, "eval_samples": 2000, "eval_samples_per_second": 24.263, "eval_steps_per_second": 0.388, "total_flos": 0.0, "train_loss": 0.22024025758457094, "train_runtime": 20844.5321, "train_samples": 61134, "train_samples_per_second": 8.799, "train_steps_per_second": 0.275 }