feat: recursive weight sharing for 16MB limit#15
Closed
ArthurKaroyan wants to merge 1 commit intoopenai:mainfrom
Closed
feat: recursive weight sharing for 16MB limit#15ArthurKaroyan wants to merge 1 commit intoopenai:mainfrom
ArthurKaroyan wants to merge 1 commit intoopenai:mainfrom
Conversation
Ueaj-Kerman
added a commit
to Ueaj-Kerman/parameter-golf
that referenced
this pull request
Mar 19, 2026
Add entries openai#15-18 to experiment log covering three worktree experiments: - GatedCausalConv (ssl): conv replacing first transformer block, best 1.2247 bpb - NorMuon (normuon): per-row second moment normalization in Muon (code-only) - SPlus (svdopt): SVD eigenbasis optimizer replacing Muon (code-only) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Collaborator
|
Not a valid submission, resubmit with training log to prove efficacy. |
mrdavtan
added a commit
to mrdavtan/parameter-golf
that referenced
this pull request
Mar 21, 2026
- Restored from qat-sliding-window branch (was never merged forward) - Updated SWA: v2 result was +0.0004 (no effect), now superseded by EMA - Updated Moonshot: added v2 flat-loops result (5.58), scale argument - Added Finding openai#15: Int5 catastrophic (gap 15x worse than int6) - Added Finding openai#16: optimizer bug (SmearGate + BigramHash frozen in all prior runs) - Added Finding openai#17: 11L step-count trap (83ms/step = 40% fewer steps) - Added Finding openai#18: FA2 positive for step time, no quality effect - Added Findings openai#19-22: XSA, EMA, TTT, NTK-RoPE (implemented, results pending) - Updated 'tested by others' section with our implementation status - Added meta-lessons: optimizer coverage, layer cost, merge window strategy
gb250e
referenced
this pull request
in gb250e/parameter-golf
Mar 21, 2026
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
2 participants
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.
No description provided.