open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-29 17:35:16 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

updated datasets

Browse source
This commit is contained in:
joesharratt1229 2025-04-01 16:11:31 +00:00
parent 9f9f816902
commit 37bbd97191
3 changed files with 28 additions and 23 deletions
Download patch file Download diff file Expand all files Collapse all files

5
reasoning_gym/algorithmic/spell_backward.py
View file

@ -72,7 +72,7 @@ class SpellBackwardDataset(ProceduralDataset):
expected_answer = expected_answer.lower()
answer = answer.lower()
if expected_answer == answer:
reward = 1.0
return 1.0
else:
answer_len = len(expected_answer)
for i in range(len(expected_answer)):
@ -83,7 +83,8 @@ class SpellBackwardDataset(ProceduralDataset):
continue
else:
break
if reward == 1.0:
reward -= 0.2
except:
reward = 0.0
return reward