verl
verl copied to clipboard
Resolve the issue of PRIME getting stuck during math verification.
Since searching for an appropriate simplify algorithm may cause sympy.simplify to timeout, and ProcessPool may get stuck due to excessive concurrency, the timeout mechanism in verl/verl/workers/reward_manager/prime.py cannot capture the timeout. To address this issue, a timeout detection mechanism is added to verl/verl/utils/reward_score/prime_math/__init__.py for sympy.simplify to solve it easily.
I have modified the code to ensure it passes the yapf check. Please approve it again. Thanks!