[Non-record] Quantization Findings: SWA Reversal + Int5 Failure#238
Open
kellyvv wants to merge 1 commit intoopenai:mainfrom
Open
[Non-record] Quantization Findings: SWA Reversal + Int5 Failure#238kellyvv wants to merge 1 commit intoopenai:mainfrom
kellyvv wants to merge 1 commit intoopenai:mainfrom
Conversation
mrdavtan
added a commit
to mrdavtan/parameter-golf
that referenced
this pull request
Mar 21, 2026
- Add leaderboard table: jfprincz 1.1271 is new target; mohosy racing same stack - Add Reptile meta-TTT finding (PR openai#296): 10x better than naive TTT with SmearGate; error-guided TTT is negative; 13L crossover point identified - Add SWA checkpoint count finding (PR openai#238): 84 checkpoints reverses quant gap; explains why our WD=1200 SWA showed no effect - Update jfprincz entry to include PR openai#287 results (1.1271) - Add meta-lessons 10 and 11
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Two quantization findings
Finding 1: SWA reverses the quantization gap
After averaging 84 checkpoints, int6+zstd roundtrip BPB is LOWER than pre-quant BPB (1.5164 vs 1.5536, gap = -0.037). SWA smoothing eliminates quantization-sensitive outliers.
Finding 2: Int5 is catastrophic for undertrained models
Mixed int5/int6 quant gap explodes from 0.3 to 1.4 BPB (4.5×). Directly contradicts int5 viability for compute-constrained training.
See README for detailed analysis and reproduction steps.