fix bug in freeze tuning

src/llmtuner/train/utils.py

@@ -76,4 +76,5 @@ def create_reward_model(
         reward_finetuning_args = FinetuningArguments(finetuning_type="lora")
         reward_model, _ = load_model_and_tokenizer(reward_model_args, reward_finetuning_args, is_trainable=False, stage="ppo")
         logger.info("Load full weights of reward model from {}".format(finetuning_args.reward_model))
+        logger.warning("Please ensure the ppo model and reward model share SAME tokenizer and vocabulary.")
         return reward_model