Skip to content

Ran the linter at head #792

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
finbarrtimbers merged 1 commit into from
Jul 16, 2025
Merged

Ran the linter at head #792

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
2 changes: 1 addition & 1 deletion open_instruct/ground_truth_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -887,7 +887,7 @@ def build_all_verifiers(args) -> Dict[str, VerifierFunction]:
for judge_type in JUDGE_PROMPT_MAP.keys():
instance = LMJudgeVerifier(judge_type, LMJudgeVerifierConfig.from_args(args))
verifiers[instance.name.lower()] = instance

# if we have remap arg, remap!
if args.remap_verifier:
remap = args.remap_verifier.split("=")
Expand Down
2 changes: 1 addition & 1 deletion open_instruct/judge_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -217,7 +217,7 @@ def extract_json_score_with_fallback(score_str: str) -> "tuple[str, float]":
# escape newlines
cleaned_str = cleaned_str.replace("\r\n", "\n").replace("\n", "\\n")
# escape backslashes
cleaned_str = re.sub(r'\\(?!["\\/bfnrtu])', r'\\\\', cleaned_str)
cleaned_str = re.sub(r'\\(?!["\\/bfnrtu])', r"\\\\", cleaned_str)

cleaned_str = cleaned_str.strip()

Expand Down
7 changes: 6 additions & 1 deletion open_instruct/model_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -263,7 +263,12 @@ async def apply_verifiable_reward(
async_tasks.append(task)
# use reward_func.name to get the name of the verifier, rather than ds in case we have done remapping.
task_metadata.append(
{"response_idx": i, "dataset": reward_func.name, "reward_weight": reward_func.weight, "reward_mult": reward_mult}
{
"response_idx": i,
"dataset": reward_func.name,
"reward_weight": reward_func.weight,
"reward_mult": reward_mult,
}
)

# Execute all tasks in parallel
Expand Down