Non-record: Negative results & insights from 24hrs on 8xH100#375
Open
charmquark1984 wants to merge 1 commit intoopenai:mainfrom
Open
Non-record: Negative results & insights from 24hrs on 8xH100#375charmquark1984 wants to merge 1 commit intoopenai:mainfrom
charmquark1984 wants to merge 1 commit intoopenai:mainfrom
Conversation
13 techniques tested that did NOT work on PR openai#315 base: - Causal TTT (3 variants): neutral on EMA+XSA base - MTP: +0.028 BPB, throughput penalty kills it - INT4: 0.06 BPB quant gap wipes out param advantage - Canon layers: 48% step overhead not compensated - Memory tokens, gradient-guided quant, cautious WD, L1 regularization, label smoothing, 1M batch, full QAT 4 positive findings: - EMA > SWA by 0.003 BPB (3-seed verified) - Weight decay directly controls artifact size - 786K > 524K batch by 0.004 BPB - FA3 Hopper: 15-20% more steps at same wallclock Best verified result: 1.1257 BPB (PR openai#315 reproduction) Includes 12 training logs for verification.
rarce
added a commit
to rarce/parameter-golf
that referenced
this pull request
Mar 22, 2026
original_model.md: - Discard depth recurrence (amplifies quant error 900×, throughput loss) - New direction: eval-time optimization stack (PPM-C + GPTQ-lite) - Document all our experiment results (v3, v4, v4_30m, ringgolf) - Add TTT/XSA interaction findings (PR openai#303: mutually exclusive) - Add PR openai#375 meta-insight (1ms overhead = 0.006 BPB) - 4-phase execution plan targeting PPM-C as original contribution review_pr_records_track_10min_16mb.md: - Add 2026-03-22 update with PRs openai#374, openai#379, openai#390, openai#375, openai#303, openai#363 - New SOTA at 1.1246 (PR openai#374: Tight SWA + VE128) - Document negative results from $500 compute spend (PR openai#375) - Unexplored opportunities: PPM-C, Neural Cache review_records_track_10min_16mb.md: - Add timestamp note (17 records, no changes) 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.
Title: Non-record: Negative results & insights from 24hrs on 8xH100
Description:
We spent ~$500 of 8xH100 time systematically testing 13 techniques on top of the PR #315 base. Most of them made things worse. This submission documents what didn't work and why, so other competitors can skip these dead ends.
Negative results (did not improve on PR #315 base):
Positive findings:
Meta-insight: At 86ms/step, each 1ms of per-step overhead costs ~0.006 BPB. Most techniques fail this throughput test.
Best verified result: 1.1257 BPB (PR #315 reproduction). Full details, methodology, and 12 training logs in the README.