{ "epoch": 1.0, "eval_logits/chosen": 0.04453304782509804, "eval_logits/rejected": -0.5562469959259033, "eval_logps/chosen": -604.554443359375, "eval_logps/rejected": -867.9213256835938, "eval_loss": 0.6763553023338318, "eval_rewards/accuracies": 0.7173295617103577, "eval_rewards/chosen": 0.030703268945217133, "eval_rewards/margins": 0.03669063001871109, "eval_rewards/rejected": -0.005987361539155245, "eval_runtime": 622.4746, "eval_samples": 5631, "eval_samples_per_second": 9.046, "eval_steps_per_second": 0.283, "train_loss": 0.6753969060050117, "train_runtime": 1121.4796, "train_samples": 5168, "train_samples_per_second": 4.608, "train_steps_per_second": 0.072 }