mirror of
https://github.com/open-thought/reasoning-gym.git
synced 2026-04-22 16:49:06 +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
bf24999bb0
commit
b2904ccab9
106 changed files with 403 additions and 507 deletions
|
|
@ -110,7 +110,7 @@ def test_arc_agi_scoring():
|
|||
assert dataset.score_answer(item["answer"], entry=item) == 1.0
|
||||
|
||||
# Test invalid format
|
||||
assert dataset.score_answer("invalid grid format", entry=item) == 0.01
|
||||
assert dataset.score_answer("invalid grid format", entry=item) == 0.0
|
||||
|
||||
# Test None answer
|
||||
assert dataset.score_answer(None, entry=item) == 0.0
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue