Skip to content

More stable MBPP evaluation #2111

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

More stable MBPP evaluation #2111

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5fb578a
timed re.search and _executor made global
f14-bertolotti May 21, 2025
2fc30a9
TimeOutError exception handling
francesco-bertolotti May 28, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
43 changes: 23 additions & 20 deletions opencompass/datasets/mbpp.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@
import json
import multiprocessing
import os.path as osp
import re
import regex as re
import signal
import tempfile
from collections import defaultdict
Expand Down Expand Up @@ -330,7 +330,11 @@ def _process_answer(self, text):
r"'(.*)'\s*\[DONE\]",
]
for p in patterns:
match = re.search(p, text, re.DOTALL)
try:
match = re.search(p, text, re.DOTALL, timeout=10.0)
except TimeoutError:
match = None

if match:
text = match.group(1)
break
Expand Down Expand Up @@ -383,6 +387,22 @@ def _process_answer(self, text):
text = text[1:]
return text

def _execution(programs, timeout, key):
try:
# Add exec globals to prevent the exec to raise
# unnecessary NameError for correct answer
exec_globals = {}
with swallow_io():
with time_limit(timeout):
exec(programs, exec_globals)
key.append('pass')
except TimeOutException:
key.append('timeout')
except AssertionError:
key.append('wrong_answer')
except BaseException as e:
print(e)
key.append('failed')

def execution(programs, task_id, timeout):
"""Execution function for running generation code.
Expand All @@ -400,29 +420,12 @@ def execution(programs, task_id, timeout):
control the process.
"""

def _execution(programs, timeout):
try:
# Add exec globals to prevent the exec to raise
# unnecessary NameError for correct answer
exec_globals = {}
with swallow_io():
with time_limit(timeout):
exec(programs, exec_globals)
key.append('pass')
except TimeOutException:
key.append('timeout')
except AssertionError:
key.append('wrong_answer')
except BaseException as e:
print(e)
key.append('failed')

manager = multiprocessing.Manager()
key = manager.list()
# `signal` cannot be used in child thread, therefore, we
# need to create a process in the thread.
p = multiprocessing.Process(target=_execution,
args=(programs, timeout - 1))
args=(programs, timeout - 1, key))
p.start()
p.join(timeout=timeout)
if p.is_alive():
Expand Down