SP8192 + LongCtx NoQV QK5.25 Prefix2750 — 1.05827 BPB (seed 42)#1963
Open
someone114514 wants to merge 2 commits intoopenai:mainfrom
Open
SP8192 + LongCtx NoQV QK5.25 Prefix2750 — 1.05827 BPB (seed 42)#1963someone114514 wants to merge 2 commits intoopenai:mainfrom
someone114514 wants to merge 2 commits intoopenai:mainfrom
Conversation
Contributor
|
must beat current SOTA by >or - 0.005 nats |
Collaborator
|
Leaderboard audit note (pre-cutoff state): I don't think this is record-ready as submitted. The PR reports only a single seed and no std/p-value evidence, and the seed-42 number is essentially a narrow follow-up around PR #1953 rather than a statistically supported new frontier row. Please rerun a matching 3-seed package if this is intended as a leaderboard claim. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Single-seed result:
val_bpb=1.05826976on seed 42.This PR is a deliberately narrow follow-up to #1953. It keeps the #1953 training, quantization, tokenizer, CaseOps data, long-context eval, no_qv TTT mask, TTT local LR multiplier, and QK gain stack intact, and changes only the phased-TTT prefix schedule:
PHASED_TTT_PREFIX_DOCS:2500 -> 2750PHASED_TTT_NUM_PHASES: unchanged at3Result
The larger prefix lands within
0.00003 BPBof the #1953 seed42 reference while staying under the 16 MB cap.Files
train_gpt.py: Record: PR #1945 base + 2560 long-context + no_qv TTT mask + TTT LR 0.75 + QK_GAIN 5.25 — val_bpb 1.05855 (3-seed mean) #1953-derived script with defaultPHASED_TTT_PREFIX_DOCS=2750download_caseops_data.py: reproducible CaseOps dataset downloader/validatortrain_seed42.log: full seed42 run logREADME.md: setup and run commandsubmission.json: seed42 result metadataReproduce
The README contains the full 8x GPU command. CaseOps data should be prepared with: