diff options
| author | Yuren Hao <yurenh2@illinois.edu> | 2026-07-25 13:57:16 -0500 |
|---|---|---|
| committer | Yuren Hao <yurenh2@illinois.edu> | 2026-07-25 13:57:16 -0500 |
| commit | 1c89d1b5bee0349aa6a2f39f44ac68e751562a94 (patch) | |
| tree | c8cd0231f28274f3f2afd52d84688c65c1742287 /docs/campaign | |
| parent | 86ef095e9619c3c6908cb2c95e1cd27532ff2904 (diff) | |
RESULT 61: EP诊断暂停,BP锚点优先(用户令) — b15尸检:合规1.5e-3血统天花板照沉到1.5e-3(哨戒5连DIVERGE),C768下沉追β; BP电池全三卡:135M孪生s1/s2(41h)+72M s2/s3链(11h×2)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
Diffstat (limited to 'docs/campaign')
| -rw-r--r-- | docs/campaign/CASCADE_ABLATION_PLAN.md | 13 |
1 files changed, 13 insertions, 0 deletions
diff --git a/docs/campaign/CASCADE_ABLATION_PLAN.md b/docs/campaign/CASCADE_ABLATION_PLAN.md index 68d7bc2..7c55675 100644 --- a/docs/campaign/CASCADE_ABLATION_PLAN.md +++ b/docs/campaign/CASCADE_ABLATION_PLAN.md @@ -568,6 +568,19 @@ direction), not training-under-fault; wave-2 = co-training with faults injected +### RESULT 61 (2026-07-25): EP-SIDE DIAGNOSTICS HALTED FOR THE BP ANCHOR (user call: +"这种情况下应该先跑bp baseline"). b15 postmortem seals the C768 picture: the COMPLIANT +beta=1.5e-3 lineage ALSO sank its ceiling to 1.5e-3 (sentinel: operating row DIVERGE for 5 +consecutive ckpt probes; r18316 backstop halvings; best 3.4643 @387.8k, still short of the +3.3839 first run). The C768 sinking chases beta down — every EP arm so far (3e-3 fixed, +7.5e-4 endgame, 1.5e-3 compliant) fails differently, and NONE of it is interpretable without +knowing what BP does at this width. ATTRIBUTION FIRST. +IN FLIGHT (all 3 GPUs, BP battery): fw135m_bp s1 (GPU0) + s2 (GPU1) — exact EP twins, +440k/2.7B tok, ~41h each; fw72m_bp_s2 -> s3 chained (GPU3, ~11h each) — closes the 72M +honest-gap denominator (currently n=1). Readout: (a) 135M BP endpoint vs 72M BP 3.2884 = +does the RECIPE scale at all (if BP also disappoints, the width problem is shared, not EP's); +(b) honest 135M gap = EP best vs BP twin mean; (c) 72M gap ledger goes n=3-vs-n=2. + ### RESULT 60b (2026-07-24): THE RES METER IS WIDTH-BLIND UNDER AMP — in-band ratcheting is impossible at C768; the instrument is the offline fp32 probe. Ratchet arm killed at launch (6 knocks in the first step, beta -> 4.7e-5 death spiral: gate 1e-3 sat BELOW the bf16 floor). |