Skip to content

fix(cookbooks): normalize LaTeX and markdown formatting in Fireworks … #659

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

Open
shobhitagnihotri69 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix(cookbooks): normalize LaTeX and markdown formatting in Fireworks … #659

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
3 changes: 3 additions & 0 deletions cookbooks/fireworks-rl-training/env.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,9 @@ def grade_final_integer(answer: object, expected: int) -> EvaluationResult:
"""Grade an integer on the last nonempty line, allowing thousands separators."""
text = (answer if isinstance(answer, str) else str(answer)).strip()
final = text.splitlines()[-1].strip() if text else ""
final = (
re.sub(r"\\boxed\{\s*([^{}]+?)\s*\}", r"\1", final.rstrip(".")).strip("$*` \t").rstrip(".")
)
got = (
int(final.replace(",", ""))
if re.fullmatch(r"[+-]?(?:\d+|\d{1,3}(?:,\d{3})+)", final)
Expand Down
5 changes: 4 additions & 1 deletion cookbooks/fireworks-rl-training/test_train.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -336,7 +336,10 @@ def test_default_renderer_matches_qwen38_chat_template() -> None:
(4861, 3217, "The answer is 15637837, as calculated above.", 0.0),
(4861, 3217, "The answer is 15,637,837, as calculated above.", 0.0),
(2, 3, "6,", 0.0),
(4861, 3217, r"\boxed{15,637,837}", 0.0),
(4861, 3217, r"\boxed{15,637,837}", 1.0),
(4861, 3217, r"$\boxed{15,637,837}$", 1.0),
(4861, 3217, "**15,637,837**", 1.0),
(4861, 3217, "`15,637,837`", 1.0),
(4861, 3217, "Working...\n\n 15,637,837 \n \t\n", 1.0),
(4861, 3217, "+15,637,837", 1.0),
(4861, 3217, "15637837\n0", 0.0),
Expand Down
3 changes: 3 additions & 0 deletions docs/v6/cookbooks/fireworks-rl-training.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -128,6 +128,9 @@ env = Environment(name="fireworks-arithmetic")
def grade_final_integer(answer: object, expected: int) -> EvaluationResult:
text = (answer if isinstance(answer, str) else str(answer)).strip()
final = text.splitlines()[-1].strip() if text else ""
final = (
re.sub(r"\\boxed\{\s*([^{}]+?)\s*\}", r"\1", final.rstrip(".")).strip("$*` \t").rstrip(".")
)
got = (
int(final.replace(",", ""))
if re.fullmatch(r"[+-]?(?:\d+|\d{1,3}(?:,\d{3})+)", final)
Expand Down