github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-06-22 05:29:36 +00:00
Code Issues Packages Projects Releases Wiki Activity

upgrade reward math verification

Browse Source
This commit is contained in:
YeAnbang 2025-04-30 22:59:54 +08:00
parent 01640ebd65
commit a6085ff676
1 changed files with 3 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
applications/ColossalChat/coati/distributed/reward/reward_fn.py
View File

@ -1,4 +1,5 @@
import torch import torch
from math_verify import parse, verify
from .reward_utils import extract_boxed_solution, extract_solution, validate_response_structure from .reward_utils import extract_boxed_solution, extract_solution, validate_response_structure
@ -35,11 +36,7 @@ def math_reward_fn(input_ids, gt_answer, response_idx, **kwargs):
format_acc += 1 format_acc += 1
# Check answer accuracy, answer is considered correct if the answer is correct and the format is valid # Check answer accuracy, answer is considered correct if the answer is correct and the format is valid
if ( if format_valid and final_answer is not None and verify(parse(gt_answer.strip()), parse(final_answer.strip())):
format_valid
and final_answer is not None
and gt_answer.strip().replace(" ", "").lower() == final_answer.strip().replace(" ", "").lower()
):
ans_acc += 1 ans_acc += 1
reward += acc_score reward += acc_score
@ -91,7 +88,7 @@ def boxed_math_reward_fn(input_ids, gt_answer, response_idx, **kwargs):
reward += format_score reward += format_score
# Check answer accuracy, answer is considered correct if the answer is correct and the format is valid # Check answer accuracy, answer is considered correct if the answer is correct and the format is valid
if format_valid and final_answer is not None and gt_answer.strip().lower() == final_answer.strip().lower(): if format_valid and final_answer is not None and verify(parse(gt_answer.strip()), parse(final_answer.strip())):
ans_acc += 1 ans_acc += 1
reward += acc_score reward += acc_score