mirror of
https://github.com/open-thought/reasoning-gym.git
synced 2026-04-19 12:58:07 +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
|
|
@ -36,7 +36,7 @@ def test_reseeding_dataset_iteration():
|
|||
|
||||
# Test score_answer forwarding
|
||||
test_item = next(iter(infinite_dataset))
|
||||
assert infinite_dataset.score_answer("wrong", test_item) == 0.01
|
||||
assert infinite_dataset.score_answer("wrong", test_item) == 0.0
|
||||
assert infinite_dataset.score_answer(test_item["answer"], test_item) == 1.0
|
||||
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue