mirror of
https://github.com/open-thought/reasoning-gym.git
synced 2026-04-22 16:49:06 +00:00
fix chain_sum unit test
This commit is contained in:
parent
f75cc3e17e
commit
d90548658e
3 changed files with 19 additions and 8 deletions
|
|
@ -49,5 +49,11 @@ def test_rubikscube_items():
|
|||
assert "example_correct_answer" in item["metadata"]
|
||||
|
||||
assert dataset.score_answer(answer=item["metadata"]["example_correct_answer"], entry=item) == 1.0
|
||||
assert dataset.score_answer(answer="R", entry=item) == 0.01
|
||||
assert dataset.score_answer(answer="a wrong solution", entry=item) == 0.01
|
||||
assert dataset.score_answer(answer=None, entry=item) == 0.0
|
||||
|
||||
if item["metadata"]["example_correct_answer"] != "R":
|
||||
assert dataset.score_answer(answer="R", entry=item) == 0.05
|
||||
|
||||
if len(item["metadata"]["example_correct_answer"]) > 0:
|
||||
assert dataset.score_answer(answer="", entry=item) == 0.01
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue