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>
Contributor
|
Not a valid submission, resubmit with training log to prove efficacy. |
gb250e
referenced
this pull request
in gb250e/parameter-golf
Mar 21, 2026
taka6745
pushed a commit
to taka6745/parameter-golf
that referenced
this pull request
Apr 7, 2026
…prime stride sampling Inspired by PR openai#1099/openai#1060/openai#1135 which use TOKEN-level coprime stride. Token-level needs 60+ LOC rewrite of TokenStream (no random access). Shipping the SHARD-LEVEL variant: modify _advance_file() to use a coprime stride instead of +1, so nearby training steps see topically-different shards rather than adjacent similar ones. Implementation: 13 LOC, two anchors in TokenStream class (none of the existing 24 patches touch TokenStream — verified via grep). Gated by USE_COPRIME_STRIDE=1, falls back to stride=1 default. Idempotent via COPRIME_STRIDE_MARKER. Effect: with N shards and gcd(s,N)=1, iterates 0->s->2s->... covering all shards before repeating. Max spacing diversity = better gradient noise reduction. Smaller benefit than full token-level (~25% per PR openai#1099 logic), but ships TODAY at near-zero risk vs. 60+ LOC structural rewrite. 4 CS experiments queued: CS0_alone, CS1_seed42, CS2_L4weights, CS3_with_engram. This is the FIRST data-side patch in our 24-patch stack. Tests a completely new vector after the "neutrality plateau" of architectural/optimizer/training-time patches. 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
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.