Skip to content

Refactor and Merge several compute_score functions #430

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
pan-x-c merged 6 commits into from
Dec 9, 2025
Merged

Refactor and Merge several compute_score functions #430

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
8e2776b
unify compute_score
hiyuchang Dec 5, 2025
77f6643
Merge branch 'main' into dev/unify_compute_score
hiyuchang Dec 5, 2025
6e1562b
fix pre-commit
hiyuchang Dec 5, 2025
55e3b0d
move functions to common.reward
hiyuchang Dec 9, 2025
cd5a332
fix pre-commit error
hiyuchang Dec 9, 2025
1e12bca
fix comment
hiyuchang Dec 9, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions benchmark/plugins/guru_math/reward.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,10 +14,10 @@ def __call__( # type: ignore
format_score_coef: Optional[float] = 0.1,
**kwargs,
) -> dict[str, float]:
from .naive_dapo import compute_score
from trinity.common.rewards.naive_dapo_score import compute_score

ret = compute_score(response, truth, None) # type: ignore
return {"accuracy": ret["score"], "format_score": 0}
score = compute_score(response, truth) # type: ignore
return {"accuracy": score, "format_score": 0}


@REWARD_FUNCTIONS.register_module("math_boxed_reward_prime_math")
Expand All @@ -32,5 +32,5 @@ def __call__( # type: ignore
) -> dict[str, float]:
from verl.utils.reward_score.prime_math import compute_score

ret = compute_score(response, truth)
return {"accuracy": ret["score"], "format_score": 0}
res = compute_score(response, truth)
return {"accuracy": res["score"], "format_score": 0}
6 changes: 3 additions & 3 deletions examples/bots/workflow/bots_math_boxed_reward.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
from typing import Optional

from trinity.common.rewards.eval_utils import validate_think_pattern
from trinity.common.rewards.reward_fn import REWARD_FUNCTIONS, RewardFn
from trinity.utils.eval_utils import validate_think_pattern


@REWARD_FUNCTIONS.register_module("bots_math_boxed_reward")
Expand All @@ -22,9 +22,9 @@ def __call__( # type: ignore
format_score_coef: Optional[float] = 0.1,
**kwargs,
) -> dict[str, float]:
from trinity.plugins.bots_reward import compute_score
from trinity.plugins.bots_reward import compute_score_bots

accuracy_score = compute_score(response, truth)
accuracy_score = compute_score_bots(response, truth)

format_score = 0.0
if with_think and not validate_think_pattern(response):
Expand Down
Loading