mirror of
https://github.com/open-thought/reasoning-gym.git
synced 2026-04-27 17:23:19 +00:00
Minor question template & score_answer improvements (#261)
* math prompt improvements * ignore brackets in complex_arithmetic results * improve additional instruction in prompt of polynomial_equations * more strict tests for score_answer in polynomial_equations * simplify special reward handling * fix test_intermediate_integration * fix sokoban dataset * add common dataset score_answer consistency test
This commit is contained in:
parent
061282e373
commit
5d7fbac0ad
106 changed files with 403 additions and 507 deletions
|
|
@ -110,19 +110,17 @@ class NeedleHaystackDataset(ProceduralDataset):
|
|||
Returns:
|
||||
float: The computed score between 0.0 and 1.0.
|
||||
"""
|
||||
if isinstance(answer, str):
|
||||
correct_word = entry["answer"]
|
||||
|
||||
correct_word = entry["answer"]
|
||||
if not answer:
|
||||
return 0.0 # No answer given
|
||||
# Normalize case
|
||||
answer = answer.replace(" ", "").strip().lower()
|
||||
correct_word = correct_word.strip().lower()
|
||||
|
||||
# Normalize case
|
||||
answer = answer.replace(" ", "").strip().lower()
|
||||
correct_word = correct_word.strip().lower()
|
||||
if answer == correct_word:
|
||||
return 1.0 # Correct!
|
||||
|
||||
if answer == correct_word:
|
||||
return 1.0 # Correct!
|
||||
|
||||
return 0.01
|
||||
return 0.0
|
||||
|
||||
|
||||
# Register the dataset
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue