summaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2026-07-13Stage-2 data pipeline: FineWeb-Edu sample-10BT -> 32k BPE -> bins; --data ↵Yuren Hao
flag on both trainers Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
2026-07-12stage1b_amp epoch confirm SEALED: 1.2868 vs fp32 1.2808, zero guards, 1.56x heldYuren Hao
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
2026-07-12Draft 7: reply to Ben's Overleaf-comments email (slop critique accepted, ↵Yuren Hao
two-papers class-boundary framing) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
2026-07-12Outreach signature resolved: name only, no titleYuren Hao
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
2026-07-12Hardware outreach v2: gate lifted, clockless-MVP story, Dillavou wave-1, ↵Yuren Hao
brief rewritten to cascade-era Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
2026-07-12RESULT 15 (amp lossless 1.56x) + COST_MODEL v2.1 (sourced July-2026 prices, ↵Yuren Hao
EF unit fix) + Draft 6 cost/scale rewrite Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
2026-07-12bf16 mixed-precision (--amp): gate PASSED (cos 0.9682 vs fp32 0.9687), ↵Yuren Hao
trainer flag + 3-seed 4k A/B launched Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
2026-07-12E-tier wave-1 ledger (RESULT 14 + HW map rows) + cost model v2 recalibrated ↵Yuren Hao
on measured H200 datapoint Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
2026-07-12RESULT 13: bsign neutral at 4k (1.7382 vs 1.7314); 42M gap-chasing closed at ↵Yuren Hao
noise floor; pivot to Stage-2 pipeline + E-tier
2026-07-11RESULT 12: f3e3cont negative (1.2883 vs 1.2808) — residual gap not ↵Yuren Hao
beta-liftable; next lever = random-sign beta (single-phase, KHS-validated), then centered
2026-07-11Draft 6: formulation correction conceded precisely; ↵Yuren Hao
same-gradient-different-algorithms answer with the two resolvents; note attached; scope concession (MLP/CNN/RNN)
2026-07-11Draft 5 FINAL: post-quick-reply follow-up shape (Overleaf link + gap ledger ↵Yuren Hao
+ 3.2x calibrated against their 18-day App B + cost table + analog hook + two-papers ask) + send checklist
2026-07-11STANDING: looped line abandoned (user directive) — cascade-only default; ↵Yuren Hao
looped = historical data for dynamics paper
2026-07-11Their VGG10 = 62.7M (computed from Table 6) > our 42.75M: largest-today is ↵Yuren Hao
theirs; their EP/BP wall-clock 6.7-12x vs our 3.2x recorded as solver differentiator
2026-07-11Ben draft 5: engages 2606.03584 directly (Eq.10==our objective; ↵Yuren Hao
AsymEP-reduces-to-vanilla answer; mod-PGD convergence; their beta one-liner -> our quantified SNR); claim rescoped to first-transformer-LM; hardware paragraph tied to their open question
2026-07-11CLAIM RESCOPE: Kerjan-Hoier-Scellier PCN-ImageNet (their Eq.10 == our ↵Yuren Hao
cascade energy; 1.0-1.5pp gap remains) — 'largest NN today' contested, use largest-transformer/first-LM/zero-gap; 1B+ unqualified
2026-07-11Ben draft 4: academic register (metaphors stripped per user style ↵Yuren Hao
correction); register-split rule recorded in style profile
2026-07-11Ben draft 3.1: closing paragraph = split-vs-merge strategic ask (our lean: ↵Yuren Hao
two papers, capstone at 'the broadest venue the result can carry' — Nature unspoken)
2026-07-11Ben draft 3: largest NN (not LM), no cascade internals, gap-vs-no-gap as ↵Yuren Hao
headline, 3B-Chinchilla/7-8B earn-the-conversation framing, analog-LM plan hook for Rain
2026-07-11Ben reply draft 2: news block (largest fully BP-free LM, parity, Muon ↵Yuren Hao
transfer) + measured cost table + calibration pilot + envelope questions
2026-07-11RESULT 11: stage1b sealed (gap 0.050); beta ceiling unfound (3e-3 -> cos ↵Yuren Hao
0.9974); K exonerated on OLMo2; bf16 naive-cast dead at any beta (TF32 stays cost baseline); f3e3 CE-endpoint cont launched Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
2026-07-11Component->analog-hardware map: full stack (forward path A.1-10, training ↵Yuren Hao
machinery B.11-17, cross-cutting physics C, demo scoping D) with reuse sources, feedback-path costs, tolerance status per item
2026-07-11Claim-verification dossier: largest-NN-without-BP — competitor autopsy ↵Yuren Hao
(optical DFA partial+BP-readout; EGGROLL from-scratch=tiny integer GRU; ES=finetune-only); claim holds at 42.75M with qualifier, unqualified at 1B+ Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
2026-07-11Lock outreach headline (largest BP-free NN ever, analog-compatible) + reply ↵Yuren Hao
gating on stage1b+bf16
2026-07-11gitignore the token-bearing demo notebookYuren Hao
2026-07-10Queue: double-sided nudge after stage1b (0.22 = differential-measurement SNR ↵Yuren Hao
tax, escalation ladder recorded)
2026-07-10RESULT 10: epoch endpoints (BP 1.2509/1.2750 vs EP 1.4802, +0.22 erosion ↵Yuren Hao
cost); GENERATION GATE PASSED (casc_gen.py, coherent stories, no-backprop 42.75M); stage1b improved-recipe pair launched (Muon cosine via build_hybrid) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
2026-07-10cos<0.96: flagship stays as control; bf1e3 continuation from s40000 queued ↵Yuren Hao
on farm -> endpoint quad EP-ctl/EP-lift/BPx2
2026-07-10Sustained dose-response sealed (3e-4/5e-4/1e-3 -> 0.975/0.983/0.990); ship ↵Yuren Hao
--bf_late floor ramp; next-run recipe locked (OLMo2+Muon+late-ramp)
2026-07-10RESULT 8 sealed (Muon 3v3: BP 1.7098 / EP 1.7314); beta-floor dose-response ↵Yuren Hao
@25k: 3e-4/5e-4/1e-3 -> cos 0.984/0.989/0.994, stable at 1e-3; Stage-2 recipe = late floor ramp
2026-07-10Watch: late-epoch cos erosion = intrinsic late-training SNR decline; let it ↵Yuren Hao
run, BP twins are the measurement; floor-probe queued
2026-07-10RESULT 8 final: Muon generic (+0.13 both columns; BP+Muon 1.7020 vs EP+Muon ↵Yuren Hao
1.7254); Muon default from Stage-2; 3v3 fill launched
2026-07-10RESULT 9: wall-2 ELIMINATED by OLMo2 arch — epoch cleared 10-14k with zero ↵Yuren Hao
guard events (old arch: blowup@12100); cos-erosion watch armed
2026-07-10RESULT 8 prelim: Muon+beta_floor on EP = 1.7316 (-0.098 vs AdamW, n=1, zero ↵Yuren Hao
skips); retraction closed; BP+Muon control + s2 launched
2026-07-10RESULT 7: OLMo2 parity PASS (BP 1.8335 vs EP 1.8643, gap +0.031 within ↵Yuren Hao
metric noise); arch worth ~0.08 CE both columns; epoch auto-launched; Pascal unbanned (canaries green), farm running 2xBP epochs + Muon retest
2026-07-10RESULT 6 addendum: K8 also blew at 12600 -> wall-2 is true contractivity ↵Yuren Hao
crossing (K delays only); kretry demoted to mitigation; defense = OLMo2 arch > lr channel > damped-fb/jacreg
2026-07-10RESULT 6: wall-2 = EP-specific marginal under-convergence at the ↵Yuren Hao
contractivity edge (A skips16/B skips2/C skips1/D-BP clean); ship --kretry (retry marginal batches at K=kmax); launch OLMo2 parity matrix with parity-gated epoch autolaunch Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
2026-07-10HW dossier: OLMo2-standard block analog audit (net win; no new ↵Yuren Hao
non-reciprocity; 3 new E-tier tolerance items)
2026-07-10OLMo2-standard architecture (user directive): norm-after-sublayer RMSNorm ↵Yuren Hao
blocks, full-width QK-norm, RoPE(500k), SwiGLU, no-bias, untied head, final RMSNorm, 0.02 init, grouped wd, optional z-loss (plumbed through nudge+readout+gate for EP exactness); EP smoke 42.75M cos=1.0000 Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
2026-07-10AUDIT: retract confounded Muon verdict; tone down parity claims (n=3, ↵Yuren Hao
best-of-noisy-val); scope depth-tax claim to 4k horizon; guard-split skip telemetry (skd/skg); add BP control arm diag_D_bp (+--resume in BP trainer); record resume confounds Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
2026-07-10Stage-1 epoch blowup @12100: sig story REFUTED (only +8%, cos fine till ↵Yuren Hao
after); leading indicator=drift-guard skips -> contractivity bifurcation in nudged relaxation (cascade Hopf wall); add resume/sig0/final_ln; A/B/C diagnostic launched
2026-07-10RESULT 4: QK-norm validated parity-preserving (EP 1.8868 <= BP 1.9066); ↵Yuren Hao
qk_norm complements but does NOT replace beta-floor (sig_tok still grows); Stage 1 TinyStories epoch launched
2026-07-10QK-norm: replace nn.MHA with explicit SDPA attn + --qk_norm (OLMo2-style, ↵Yuren Hao
analog-friendly); cancel epoch, insert 8-run qk validation, stage roadmap TinyStories-epoch->FineWeb-Edu->OLMo2
2026-07-10RESULT 3: K4 depth-parity SEALED EP-favorable (EP 1.8907 <= BP 1.9192 @ ↵Yuren Hao
L12xC512); full-epoch generation run auto-launched (6.9h)
2026-07-10Add --cosine (warmup->cosine decay to 0.1x lr) to both cascade trainers for ↵Yuren Hao
full-epoch runs
2026-07-10CORRECTION: D1a did not die (misread mangled proc scan); originals completed ↵Yuren Hao
s1 1.9745/s2 2.0013/s3 2.1188 + muon 2.7515; beta-floor fix independently found on free GPU1 Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
2026-07-10RESULT 2: beta-floor confirmed as L12 depth fix (3e-4 holds cos=1.0 vs ↵Yuren Hao
control collapse 0.896); K4 3-seed verdict launched vs BP 1.9192 Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
2026-07-10K refuted as L12 lever (cos K-invariant K3==K8); BP 3-seed sealed 1.919; ↵Yuren Hao
mechanism = finite-beta SNR collapse; add --beta_floor/--beta_fixed + launch floor sweep Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
2026-07-09D1a autopsy + K-ladder diagnostic: parent-death (not nohup'd) killed 4 arms; ↵Yuren Hao
L12 cos-erosion signal; relaunched K3/K8/BPs3 nohup Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
2026-07-09notes refresh: plan status stamp (K1-K3 sealed, D-tier in flight), ↵Yuren Hao
ONBOARDING cascade-pivot section Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
generated by cgit v1.2.3 (git 2.25.1) at 2026-08-18 20:54:40 +0000