fix: loss diagnostic logging + training step test#227
Merged
Conversation
…ges) loss=0.0000 was misleading: %.4f truncation + symmetric advantages canceling. Now logs loss in scientific notation, absolute loss per rollout, gradient norm, and per-rollout advantages. 13 vision loss tests (was 12). New test verifies loss_abs > 0 and advantages are symmetric with reward variance. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
abrichr
added a commit
that referenced
this pull request
Mar 29, 2026
PR #227 accidentally committed local experiment data via git add -A: - flywheel_results/ (224 screenshots + JSON) - .claude/worktrees/ (31 agent gitlinks) - annotated_demos/ (16 files) - eval_results/ (11 screenshots) - grpo_output/ (1 file) - demos/*/synthetic_correction/ (placeholder PNGs) - .beads/ (SQLite database) All removed from tracking. .gitignore updated to prevent reoccurrence. No sensitive data was exposed (confirmed via tidy scan). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
abrichr
added a commit
that referenced
this pull request
Mar 29, 2026
These were committed before PR #227 and missed in the first cleanup. waa_recordings/ contains WAA experiment screenshots (PNGs). .beads/ contains a SQLite database for local tooling. Both are already in .gitignore from the prior cleanup commit. Co-Authored-By: Claude Opus 4.6 (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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Scientific notation for loss, grad_norm, advantages. 13 tests.