def get_reward_funcs()

in src/open_r1/rewards.py [0:0]

• 60 lines of code
• 2 McCabe index (conditional complexity)

def get_reward_funcs(script_args) -> list[Callable]:
    REWARD_FUNCS_REGISTRY = {
        "accuracy": accuracy_reward,
        "format": format_reward,
        "reasoning_steps": reasoning_steps_reward,
        "cosine": get_cosine_scaled_reward(
            min_value_wrong=script_args.cosine_min_value_wrong,
            max_value_wrong=script_args.cosine_max_value_wrong,
            min_value_correct=script_args.cosine_min_value_correct,
            max_value_correct=script_args.cosine_max_value_correct,
            max_len=script_args.cosine_max_len,
        ),
        "repetition_penalty": get_repetition_penalty_reward(
            ngram_size=script_args.repetition_n_grams,
            max_penalty=script_args.repetition_max_penalty,
        ),
        "length": len_reward,
        "code": update_wrapper(
            partial(
                code_reward,
                num_parallel=script_args.parallel_code_exec_per_proc,
                provider_type=script_args.code_provider,
                enforce_same_language=getattr(script_args, "enforce_same_language", False),
            ),
            code_reward,
        ),
        "binary_code": update_wrapper(
            partial(
                binary_code_reward,
                num_parallel=script_args.parallel_code_exec_per_proc,
                provider_type=script_args.code_provider,
                enforce_same_language=getattr(script_args, "enforce_same_language", False),
            ),
            binary_code_reward,
        ),
        "ioi_code": update_wrapper(
            partial(
                ioi_code_reward,
                test_batch_size=script_args.code_eval_test_batch_size,
                provider_type=getattr(script_args, "ioi_provider", "piston"),
            ),
            ioi_code_reward,
        ),
        "cf_code": update_wrapper(
            partial(
                cf_code_reward,
                test_batch_size=script_args.code_eval_test_batch_size,
                scoring_mode=script_args.code_eval_scoring_mode,
            ),
            cf_code_reward,
        ),
        "code_format": get_code_format_reward(language=script_args.code_language),
        "tag_count": tag_count_reward,
        "soft_overlong_punishment": get_soft_overlong_punishment(
            max_completion_len=script_args.max_completion_len,
            soft_punish_cache=script_args.soft_punish_cache,
        ),
    }
    reward_funcs = [REWARD_FUNCS_REGISTRY[func] for func in script_args.reward_funcs]

    return reward_funcs