mirror of
https://github.com/open-thought/reasoning-gym.git
synced 2026-04-28 17:29:39 +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
|
|
@ -50,7 +50,7 @@ def test_game_of_life_basic_properties():
|
|||
# Test the scoring
|
||||
assert dataset.score_answer(answer=item["answer"], entry=item) == 1.0
|
||||
assert dataset.score_answer(answer=None, entry=item) == 0.0
|
||||
assert dataset.score_answer(answer="invalid json", entry=item) == 0.01
|
||||
assert dataset.score_answer(answer="invalid json", entry=item) == 0.0
|
||||
|
||||
config = GameOfLifeConfig(seed=43, size=1, grid_size_x=3, grid_size_y=3, filled_cells=1, simulation_steps=1)
|
||||
dataset = GameOfLifeDataset(config)
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue