Skip to content

fix: clamp KL divergence to non-negative values #231

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

Closed
JasonOA888 wants to merge 3 commits into from
+2 −0
Closed

fix: clamp KL divergence to non-negative values #231

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
bf52afd
fix: clamp KL divergence to non-negative values
JasonOA888 Mar 16, 2026
65d52ab
style: add period to comment
JasonOA888 Mar 16, 2026
e9d00d1
style: capitalize comment first letter
JasonOA888 Mar 16, 2026
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: 2 additions & 0 deletions src/heretic/evaluator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -101,6 +101,8 @@ def get_score(self) -> tuple[tuple[float, float], float, int]:
reduction="batchmean",
log_target=True,
).item()
# Clamp to non-negative (KL divergence cannot be negative by definition)
Copy link
Copy Markdown
Contributor

@gemini-code-assist gemini-code-assist Bot Mar 16, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

This comment should end with a period to adhere to the repository's style guide.

Suggested change
# Clamp to non-negative (KL divergence cannot be negative by definition)
# Clamp to non-negative (KL divergence cannot be negative by definition).
References
  1. Comments should start with a capital letter and end with a period. They should use correct grammar and spelling. (link)

kl_divergence = max(0.0, kl_divergence)
print(f" * KL divergence: [bold]{kl_divergence:.4f}[/]")

print(" * Counting model refusals...")
Expand Down