Non-record: 30ep Cosine TTT on SwiGLU + U-Net (1xH100, val_bpb=1.1175)#661
Closed
andrewbaggio1 wants to merge 1 commit intoopenai:mainfrom
Closed
Non-record: 30ep Cosine TTT on SwiGLU + U-Net (1xH100, val_bpb=1.1175)#661andrewbaggio1 wants to merge 1 commit intoopenai:mainfrom
andrewbaggio1 wants to merge 1 commit intoopenai:mainfrom
Conversation
…pb=1.1175) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Author
|
Closing — superseded by #672 (1.0781 BPB vs 1.1175 BPB). Reducing reviewer burden. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Non-record 1xH100 submission. Single change from PR #462: TTT_EPOCHS=30 (default 10).
val_bpb = 1.1175 (sliding window stride=64, seed 1337) | 7.5 MB artifact | 1xH100 SXM
Results (1xH100 SXM, seed 1337)
Approach
PR #462's full SwiGLU + U-Net architecture with 30-epoch cosine TTT (vs default 10). Consistent with PR #481's finding that more cosine TTT epochs improve results.
Architecture
PR #462's stack unchanged: 11L SwiGLU (hidden=1792), U-Net gated skips, BigramHash (8192), SmearGate, EMA (0.9985), Late QAT, Partial RoPE, LN Scale, Int6+zstd.
Limitation
1xH100 only — needs 8xH100 verification. 30 TTT epochs estimated ~7 min on 8xH100 (within eval budget).
Credits
PR #462 (JoeProAI), PR #481 (mrdavtan), PR #442 (sjp611), PR #398 (felipe-parodi)
Test plan
ast.parsepasses)🤖 Generated with Claude Code