src/open-r1-multimodal/src/open_r1/trainer/grpo_trainer.py [247:265]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                pad_token_id = processing_class.pad_token_id

        # Reward functions
        if not isinstance(reward_funcs, list):
            reward_funcs = [reward_funcs]
        for i, reward_func in enumerate(reward_funcs):
            if isinstance(reward_func, str):
                reward_funcs[i] = AutoModelForSequenceClassification.from_pretrained(
                    reward_func, num_labels=1, **model_init_kwargs
                )
        self.reward_funcs = reward_funcs

        # Reward processing class
        if reward_processing_classes is None:
            reward_processing_classes = [None] * len(reward_funcs)
        elif not isinstance(reward_processing_classes, list):
            reward_processing_classes = [reward_processing_classes]
        else:
            if len(reward_processing_classes) != len(reward_funcs):
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src/open-r1-multimodal/src/open_r1/trainer/vllm_grpo_trainer.py [235:253]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                pad_token_id = processing_class.pad_token_id

        # Reward functions
        if not isinstance(reward_funcs, list):
            reward_funcs = [reward_funcs]
        for i, reward_func in enumerate(reward_funcs):
            if isinstance(reward_func, str):
                reward_funcs[i] = AutoModelForSequenceClassification.from_pretrained(
                    reward_func, num_labels=1, **model_init_kwargs
                )
        self.reward_funcs = reward_funcs

        # Reward processing class
        if reward_processing_classes is None:
            reward_processing_classes = [None] * len(reward_funcs)
        elif not isinstance(reward_processing_classes, list):
            reward_processing_classes = [reward_processing_classes]
        else:
            if len(reward_processing_classes) != len(reward_funcs):
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -