diff options
Diffstat (limited to 'docs')
| -rw-r--r-- | docs/campaign/CASCADE_ABLATION_PLAN.md | 18 |
1 files changed, 18 insertions, 0 deletions
diff --git a/docs/campaign/CASCADE_ABLATION_PLAN.md b/docs/campaign/CASCADE_ABLATION_PLAN.md index 0560a07..8483820 100644 --- a/docs/campaign/CASCADE_ABLATION_PLAN.md +++ b/docs/campaign/CASCADE_ABLATION_PLAN.md @@ -492,3 +492,21 @@ double-sided ±β (kills O(β) Taylor bias, unlocks ~10× β for SNR, 2× nudge 2k-step probe when implemented) → fp64 E-accumulation / readout averaging. Analog note: this constraint IS the hardware constraint (ε = device noise); β-scheduling learned here = chip ops manual; hardware bonus = nudge amplitude free under multiplicative noise (r-indifference). + +### RESULT 11 (2026-07-11): stage1b SEALED (gap 0.22->0.050); beta ceiling not reached; K exonerated on OLMo2; bf16 naive-cast dead. +- **stage1b endpoints: EP+Muon+floor-ramp 1.2808 | BP+Muon 1.2311 -> epoch gap 0.050** (fixed-floor was + +0.22). EP now beats the old BP-AdamW epoch (1.2509/1.2750). Intervention-timing quad complete: + fixed-floor 1.4802 / lift@40k 1.4479 / full ramp 1.2808 -- monotone earlier-is-better dose curve. +- **Gap probes @s45000 (2k-step sustained traces):** control cos 0.9947 | b2e3 0.9968 | **b3e3 0.9974 + (deficit halved, zero drift/skips)** | K5 0.9951 ~= control -> **K-invariance now proven on BOTH + architectures; the residual deficit is beta-liftable, not relaxation-depth.** sigma(W_out)=80 by 45k: + without the floor beta_t would be ~1e-6 -- the floor carries the entire late phase. + CE-endpoint test launched: stage1b_f3e3cont (s45000 -> 58.8k at floor 3e-3, farm). If it closes to + <=0.03, next-flagship recipe = ramp ...->3e-3@~35k; else double-sided (queued) takes the residual. +- **bf16 gate: naive full-cast FAILS at any beta.** floor 3e-4 -> cos 0.33; 3e-3 -> 0.67; 1e-2 -> 0.65 + (no longer SNR-limited: bf16 rounding distorts the nudged equilibrium itself; beta cannot compensate). + Speed was 2.1x (5.2 it/s). VERDICT: cost baseline stays TF32 (validated); the x0.5 lever requires + proper mixed precision (bf16 weights/matmuls + fp32 states/accumulation, autocast-style) -- queued as + engineering upside, NOT in the Ben cost baseline. Wall-1 physics predicted all of this (SNR ∝ beta/eps; + bf16 eps ~8000x fp32): the fp32/bf16/analog-noise beta-epsilon scaling story now has a second + measured point. |