feat(validate): report cosine similarity in output parity results#217
Open
mvanhorn wants to merge 1 commit into
Open
feat(validate): report cosine similarity in output parity results#217mvanhorn wants to merge 1 commit into
mvanhorn wants to merge 1 commit into
Conversation
Adds cosine_sim to ValidationResult, to_dict(), and the logged details line. Computed in float64 over flattened tensors; zero-norm inputs report 0.0. Pass/fail thresholds unchanged. Closes FastCrest#53 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
validate_outputsreports only absolute/relative element-wise differences, which makes it hard to tell whether a parity failure is noise or a directional mismatch (#53). This adds cosine similarity between the flattened reference and candidate tensors to the parity report.Changes
ValidationResultgains acosine_simfield (defaults tonanfor backward compatibility), included into_dict()and the logged PASS/FAIL details line.0.0rather than dividing by zero.Testing
PYTHONPATH=src python3 -m pytest tests/test_validate.py— 10 passed, including new cases for identical tensors (cos=1), opposite tensors (cos=-1), and zero-norm handling.Closes #53
AI was used for assistance.