mirror of
https://github.com/open-thought/reasoning-gym.git
synced 2026-04-26 17:13:17 +00:00
use Decimal class for numeric comparison e.g. +0123.100 == 123.1
This commit is contained in:
parent
3e7ff3b084
commit
acde58a200
4 changed files with 15 additions and 18 deletions
|
|
@ -111,8 +111,7 @@ class ChainSumDataset(ProceduralDataset):
|
|||
return expression, result
|
||||
|
||||
def score_answer(self, answer: Optional[str], entry: dict[str, Any]) -> float:
|
||||
oracle_answer = entry["answer"].strip()
|
||||
return utils.compute_reward(answer, oracle_answer)
|
||||
return utils.compute_decimal_reward(answer, oracle_answer=entry["answer"])
|
||||
|
||||
|
||||
class ChainSumCurriculum(BaseCurriculum):
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue