Record: 1.1122 BPB — Coprime-Stride Loader + Full GPTQ + XSA-all (3-seed mean)

[dexhunter]

Summary

• val_bpb: 1.1122 (3-seed mean, std 0.0004)
• Artifact: ~15.98 MB
• Eval time: ~87s (no TTT)
• Built on PR Record: LeakyReLU² + Legal Score-First TTT + Parallel Muon — val_bpb 1.1194 (3-seed mean) #549 by @abaybektursun

What's New

1. Coprime-stride multi-shard data pipeline (PR Memmap multi-shard data pipeline + GPU prefetch + LeakyReLU² + Legal TTT + Parallel Muon #726 style) — diverse batches from coprime-stride block sampling across shards
2. Full Hessian GPTQ (PR Record: 11L XSA-all + Full GPTQ (Budget-Legal) + Parallel Muon + Selective Pruning (val_bpb: 1.1178, 3-seed mean) #634/Record: AR Self-Gen GPTQ + XSA-all + BigramHash 3072×112 — val_bpb 1.11473 (3-seed mean) #1019 style) — Cholesky error compensation replaces GPTQ-lite
3. XSA on all 11 layers — extended from last 4
4. No TTT — sliding-only outperforms TTT on this stack (confirmed independently by PR Record: AR Self-Gen GPTQ + XSA-all + BigramHash 3072×112 — val_bpb 1.11473 (3-seed mean) #1019)

3-Seed Results

Seed	Sliding BPB	Artifact
1337	1.1118	15,973,962
42	1.1127	15,980,438
2025	1.1121	15,983,626
Mean	1.1122

Compliance

• 3-seed verification, all under budget
• Standard F.cross_entropy scoring (no mixer, no cache)
• Artifact < 16,000,000 bytes (all seeds)
• Training < 600s, eval < 600s
• No TTT — pure sliding window evaluation

See README.md for full details.

[dexhunter]

Updated: re-verified all 3 seeds with the stripped train_gpt.py (96,398 bytes) that ships in this record. Previous logs were generated with a pre-strip version (111,130 bytes) that included unused code paths. Scores are unchanged — 3-seed mean 1.1122 ± 0.0004, all artifacts under 16MB. Code size and logs are now fully consistent.

[dexhunter]

Follow-up cleanup for the stripped submission artifacts only.

What changed:

• replaced the bundled train_seed1337.log short extract with the clean extract from the actual stripped-code run log
• clarified in the record README that all 3 bundled seed results and the included train_gpt.py are from the stripped submission script (Code size: 96,398 bytes)
• clarified reproduction from within the records folder and tightened the eval/rule-compliance wording

Why:

• the previous train_seed1337.log extract accidentally included a launcher traceback / truncated preamble from an earlier invocation, which made the record bundle look inconsistent even though the underlying stripped run was valid
• there is no model/code/score change here; all 3 seeds already match the stripped script, and the recorded metrics are unchanged

I re-ran the local rule checker on all 3 bundled logs after the cleanup and they pass cleanly.

[MatoTeziTanka]

Community Review — Record: 1.1122 BPB — Coprime-Stride Loader + Full GPTQ + XSA-all (3-seed mean)

BPB: 1.1122 | Compliance: LOOKS CLEAN — score-first-per-chunk TTT (legal #1416/#1423 pattern)

What I found in the code (head SHA 87c1e24d6ebe, file records/track_10min_16mb/2026-03-29_Loader_FullGPTQ_XSA11_BigramHash2816/train_gpt.py):

The TTT path at line 1124 implements the score-first-per-chunk pattern: each chunk is scored under torch.no_grad() / inference_mode() before the base_model.train() + SGD adaptation runs on that same chunk, with an is_last_chunk guard so the final chunk gets no adaptation pass. This is the structural shape the legal frontier uses (PRs #1416 erichroepke, #1423 aryanbhosale).

Per Issue #402 and Issue #677, TTT is legal when each token is scored before the adapter updates on it, and that's what the code does here — chunk ci is scored under weights adapted only on chunks 0..ci-1. No prequant_ttt_adapt_adamw(val_tokens, ...) multi-epoch fine-tune, no scored-region SLOT, no target-in-key n-gram cache.

CPU smoke test (CT2038 proteus-engine, 2026-04-11): import OK in 0.09s, dim=512, layers=11, vocab=1024, code=96398 B, SMOKE_TEST_PASS

Verdict: LOOKS CLEAN.

Recommendation to @cocohearts @valerio-oai @0hq @yuzhougu-oai @notapplica: MERGE pending standard checks (3-seed validation, 16MB artifact cap, 10-min wallclock on 8×H100 SXM). The compliance picture matches the legal reference frontier and no flags were raised by the classification pass.

Auto-classification caveat: this review was drafted by the AST-based classifier against a template derived from manually-reviewed cluster PRs (#1420, #1450, #1487, #1541, #1529, #1533, #1518). If I've misread a subtlety in your eval path — e.g., multi-epoch TTT that I mistook for single-pass, or a target-in-key lookup I missed in a helper function — please flag it and I'll re-run the audit manually.

---

Reviewed by @MatoTeziTanka — The Agora. CPU smoke test (CT2038 proteus-engine, 2026-04-11): import OK in 0.09s, dim=512, layers=11, vocab=1024, code=96398 B, SMOKE_TEST_PASS. Classification via deterministic AST-based classify_prs.py (pattern bank derived from ~65 manually-reviewed PRs earlier in the 2026-04-11 sweep). This review was auto-drafted from a template and spot-checked before posting — if the template misread your code, please call it out so I can iterate the classifier.