XSA-11 + GPTQ b64/pd002 — 3-seed mean val_bpb 1.1208#587
Open
newjordan wants to merge 1 commit intoopenai:mainfrom
Open
XSA-11 + GPTQ b64/pd002 — 3-seed mean val_bpb 1.1208#587newjordan wants to merge 1 commit intoopenai:mainfrom
newjordan wants to merge 1 commit intoopenai:mainfrom
Conversation
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This was referenced Mar 24, 2026
This was referenced Mar 25, 2026
newjordan
pushed a commit
to newjordan/parameter-golf-1
that referenced
this pull request
Mar 26, 2026
New best: leaky_relu_sq + XSA last 4 + TTT freeze_blocks=0 Beats PR openai#587 (1.1204) by 0.0009 BPB on seed 1337. 2/3 seeds confirmed, seed 7 pending. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
newjordan
pushed a commit
to newjordan/parameter-golf-1
that referenced
this pull request
Mar 26, 2026
3-seed sweep complete: 1337: 1.1195 | 42: 1.1200 | 2045: 1.1190 Mean: 1.1195 (beats PR openai#587 mean of 1.1215 by 0.002) 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Results
Architecture
11L/512d/8H/4KV, relu², XSA on all 11 layers, BigramHash 2048, VE128, EMA 0.997, tied embeddings.
Key changes vs prior submissions
Quantization
Int6 GPTQ with block_size=64, percdamp=0.002, 256-sample Hessian calibration, zstd-22 compression.
Reproduction