Record: int5 GPTQ + 33.6M model (3-seed mean val_bpb=1.1179)#545
Closed
EthanYangTW wants to merge 4 commits intoopenai:mainfrom
Closed
Record: int5 GPTQ + 33.6M model (3-seed mean val_bpb=1.1179)#545EthanYangTW wants to merge 4 commits intoopenai:mainfrom
EthanYangTW wants to merge 4 commits intoopenai:mainfrom
Conversation
33.6M params (MHA 8/8, BigramHash 8192, MLP 3.5x) quantized to int5 with GPTQ error compensation. Artifact fits under 16MB (15.3-15.5MB). Seeds: 1337 (1.1170), 42 (1.1182), 7 (1.1184)
Seed 1337: de843ef6 (TTT 1.1170) Seed 42: b6560b60 (TTT 1.1182) Seed 7: c1c18644 (TTT 1.1184)
seed1337.log - TTT 1.1170 seed42.log - TTT 1.1182 seed7.log - TTT 1.1184
Collaborator
|
dont open a pr until ur submission is ready pls; mark as draft until ready for submission |
Add proper /records submission with submission.json, README, train_gpt.py, and 3-seed logs.
Author
|
Closing in favor of properly formatted /records submission. |
Author
sorry for the inconvience,i have updated the new one and closed this |
RoyiRa
added a commit
to RoyiRa/parameter-golf
that referenced
this pull request
Mar 25, 2026
- Replace relu().square() with leaky_relu(0.5).square() in MLP Expected: -0.0015 BPB (5 independent teams confirm) - Switch TTT optimizer from SGD to AdamW(lr=0.0005, wd=0, betas=0.9/0.95) Expected: stronger TTT adaptation per openai#442/openai#503/openai#545
7 tasks
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
33.6M parameter model quantized to int5 with GPTQ error compensation, fitting under 16MB. First submission to achieve int5 quantization on a 33.6M model within the artifact size limit.
Architecture: 11L, 512d, MHA 8/8, MLP 3.5x (1792), BigramHash 8192, XSA all layers
Quantization: int5 per-row GPTQ (clip_range=15) + Early QAT (threshold 0.5) + EMA 0.997
TTT: Legal score-first AdamW, chunk=131072, last 2 blocks unfrozen
Results
Logs
See log files in
logs/directory:de843ef6-d0df-4872-bc96-cd4600614348.txtb6560b60-85f0-4623-be20-ec366dd9e6fb.txtc1c18644-a5a1-4db2-8641-31900ed8057f.txtReproduction