trinity.common.rewards.accuracy_reward module

Accuracy Reward Function Class.

class trinity.common.rewards.accuracy_reward.AccuracyReward(answer_parser: Callable[[str], str] | None = None)[source]

Bases: RewardFn

A reward function that rewards correct answers. Ref: https://github.com/huggingface/open-r1/blob/main/src/open_r1/rewards.py

__init__(answer_parser: Callable[[str], str] | None = None)[source]