mirror of
https://github.com/open-thought/reasoning-gym.git
synced 2026-04-24 17:05:03 +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
|
|
@ -80,7 +80,7 @@ def test_rearc_scoring_edge_cases():
|
|||
assert 0.0 < dataset.score_answer(partial, entry=item) < 1.0
|
||||
|
||||
# Malformed answer
|
||||
assert dataset.score_answer("[[invalid", entry=item) == 0.01
|
||||
assert dataset.score_answer("[[invalid", entry=item) == 0.0
|
||||
|
||||
# Case sensitivity
|
||||
answer = format_board(item["metadata"]["output"], dataset.board_format_opts).lower()
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue