def format_reward()

in train_rick/run_grpo.py [0:0]

• 5 lines of code
• 5 McCabe index (conditional complexity)

def format_reward(completions, **kwargs):
    pattern = r"^<think>(?!.*<think>)(.*?)</think>.*$"
    completion_contents = [completion[0]["content"] for completion in completions]
    matches = [re.match(pattern, content, re.DOTALL | re.MULTILINE) for content in completion_contents]
    return [1.0 if match else 0.0 for match in matches]