summaryrefslogtreecommitdiff
path: root/ep_run
AgeCommit message (Expand)Author
2026-07-18governor接线修复:res/rho非法判据常开(beta_cap_rho>0即生效),crown...Yuren Hao
2026-07-18wsync: 同步权重步接受(用户风格重设计,knee撤回) — opt.step...Yuren Hao
2026-07-18RESULT 49: 回路解剖=23段乘积近临界(下行×72/上行×13k/顶读1e-...Yuren Hao
2026-07-18RESULT 48c: θ-read结构上无1/β通道(d∝β,β在cotangent里消掉;五...Yuren Hao
2026-07-18RESULT 48b: 一般化BBP(amp+测谱,免结构假设)=R>1处处成立到1e-4,E...Yuren Hao
2026-07-18RESULT 47+48: 涨的量=blocks8-11单模态增益(ρ复刻探针,两血统同...Yuren Hao
2026-07-18RESULT 43+44: crown-3 死因=cap硬底钉在塌落天花板之上(变相wall-...Yuren Hao
2026-07-18--bpmix: gap-source ablation (overwrite EP grads with true BP grads per modul...Yuren Hao
2026-07-17hw_sim: circuit-as-code workflow stood up (PySpice/ngspice/skidl); cell_v0 ...Yuren Hao
2026-07-17RESULT 38: 2D update-field analysis — localized curl blob at beta=1e-2 (con...Yuren Hao
2026-07-17--beta_sync: synchronous acceptance (this-step relax telemetry gates the comm...Yuren Hao
2026-07-17ride-v2 (b)/(c) flag-gated (--ride_ema/--ride_cool, default off); isolation p...Yuren Hao
2026-07-17ride-v2: (a) floor-jump cap continuity (the 0.09 bug), (b) rho-EMA decisions,...Yuren Hao
2026-07-17save final ckpt at last step (fixed-eval protocol); fw72m_ride crown-3 launch...Yuren Hao
2026-07-16Deck finalized: both verdicts sealed (C512 zero-gap, 72M gap 0.043), decoupli...Yuren Hao
2026-07-16--beta_ride ceiling-riding governor (two-sided bcap: climb in calm, attack ne...Yuren Hao
2026-07-16RESULT 29: qcomp8 tax-free (+0.0018) = T64 8-bit compute green light; --centm...Yuren Hao
2026-07-16Stage-0 BP mirror arms: qup/qcomp flags in casc_bp_train; bp_qctl + 6 quant a...Yuren Hao
2026-07-16Stage-0 gate #1b: --qcomp_bits (compute on DAC-grid weights, fp32 master = T6...Yuren Hao
2026-07-15Stage-0 gate #1: --qup_bits (absolute-grid stochastic-rounding weight quantiz...Yuren Hao
2026-07-15ERRATUM RESULT 21: original best 3.7117 was @104.8k not @185k — 90k-step wa...Yuren Hao
2026-07-15assets/: organize into decks|figs|hw|refs|misc; scripts + gitignore repointedYuren Hao
2026-07-15Alexi primer deck: 10 slides (arch op-by-op, EP phases, schedule/parallelism,...Yuren Hao
2026-07-15centfast (doubled-batch +/-beta centered, cos 1.000000000 vs sequential, DDP-...Yuren Hao
2026-07-15RESULT 25: bias decomposition probe — 100% between-block transmission (TRAN...Yuren Hao
2026-07-14sync: add stage1b_bp_muon (42M BP twin) to TS project + report runsetYuren Hao
2026-07-14sync: negative-cos regex fix, f3e3cont log mapping, SYNC_ID_SUFFIX; full inve...Yuren Hao
2026-07-14RESULT 21: crown sealed — 72.11M x 1.44B tokens fully BP-free (largest to d...Yuren Hao
2026-07-14wandb reorganized: per-regime team projects (ept-tinystories-42m / ept-finewe...Yuren Hao
2026-07-14wandb -> team entity eqprop-llm-training (trainers + full-history replay script)Yuren Hao
2026-07-14bcap v2: absolute-scale gate on rho meter (fixes v1 noise-floor starvation), ...Yuren Hao
2026-07-14beta-cap-by-loop-gain controller (--beta_cap_rho): rho^ meter from sweep resi...Yuren Hao
2026-07-14Adaptive relax (--relax_tol): sweep-to-tolerance + rho-triggered geta backtra...Yuren Hao
2026-07-13Estimator arms machinery: --est centered/richardson (two-pass, O(b^2) bias), ...Yuren Hao
2026-07-13Fix swallowed --wandb_run arg (replace-comment bug); wandb default-on intactYuren Hao
2026-07-13wandb ON by default in both trainers (project ept-cascade); BP twin gains --a...Yuren Hao
2026-07-13fw72m crown run launched (NCCL DDP prod), exact resume (opt state), RESULT 17...Yuren Hao
2026-07-13Manual DDP for cascade-EP: guard-synced (drift/kretry via global max, gn on r...Yuren Hao
2026-07-13Stage-2 data pipeline: FineWeb-Edu sample-10BT -> 32k BPE -> bins; --data fla...Yuren Hao
2026-07-12bf16 mixed-precision (--amp): gate PASSED (cos 0.9682 vs fp32 0.9687), traine...Yuren Hao
2026-07-12E-tier wave-1 ledger (RESULT 14 + HW map rows) + cost model v2 recalibrated o...Yuren Hao
2026-07-12RESULT 13: bsign neutral at 4k (1.7382 vs 1.7314); 42M gap-chasing closed at ...Yuren Hao
2026-07-11RESULT 11: stage1b sealed (gap 0.050); beta ceiling unfound (3e-3 -> cos 0.99...Yuren Hao
2026-07-10RESULT 10: epoch endpoints (BP 1.2509/1.2750 vs EP 1.4802, +0.22 erosion cost...Yuren Hao
2026-07-10Sustained dose-response sealed (3e-4/5e-4/1e-3 -> 0.975/0.983/0.990); ship --...Yuren Hao
2026-07-10RESULT 6: wall-2 = EP-specific marginal under-convergence at the contractivit...Yuren Hao
2026-07-10OLMo2-standard architecture (user directive): norm-after-sublayer RMSNorm blo...Yuren Hao
2026-07-10AUDIT: retract confounded Muon verdict; tone down parity claims (n=3, best-of...Yuren Hao
2026-07-10Stage-1 epoch blowup @12100: sig story REFUTED (only +8%, cos fine till after...Yuren Hao
2026-07-10QK-norm: replace nn.MHA with explicit SDPA attn + --qk_norm (OLMo2-style, ana...Yuren Hao