diff options
| author | Yuren Hao <yurenh2@illinois.edu> | 2026-07-10 18:04:40 -0500 |
|---|---|---|
| committer | Yuren Hao <yurenh2@illinois.edu> | 2026-07-10 18:04:40 -0500 |
| commit | 196ee7d8121fccaae630e408bf29f6664ff351f5 (patch) | |
| tree | 3e0dd4144db52f399308205d8d590b9a9d65d41b /docs/campaign | |
| parent | a899d88d1e5a0153dfd45827813a59a03ee70b41 (diff) | |
cos<0.96: flagship stays as control; bf1e3 continuation from s40000 queued on farm -> endpoint quad EP-ctl/EP-lift/BPx2
Diffstat (limited to 'docs/campaign')
| -rw-r--r-- | docs/campaign/CASCADE_ABLATION_PLAN.md | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/docs/campaign/CASCADE_ABLATION_PLAN.md b/docs/campaign/CASCADE_ABLATION_PLAN.md index 66a9501..ac602cf 100644 --- a/docs/campaign/CASCADE_ABLATION_PLAN.md +++ b/docs/campaign/CASCADE_ABLATION_PLAN.md @@ -458,3 +458,9 @@ down, -0.0025/1k) | 5e-4 ~0.983 | 1e-3 ~0.990 flat, zero instability. Late-SNR m confirmed in-training. `--bf_late/--bf_late_at` flags shipped. NEXT-RUN RECIPE (post-epoch): OLMo2 + Muon + beta_floor 3e-4 + bf_late 1e-3 @ ~20k + kretry 8 — expected to hold cos>=0.99 end-to-end and likely close the +0.02-0.03 column gap. + +### PLAN UPDATE (2026-07-10 17:2x): cos crossed 0.96 (0.9544@39.3k, accelerating) — flagship stays +UNTOUCHED (the control measuring erosion damage vs BP twins); PARALLEL bf1e3 continuation launched +from ckpt-40000 on the farm (floor 1e-3 for the remaining 18.8k steps). Endpoint comparison becomes a +clean quad: EP-control(3e-4) / EP-floor-lift(1e-3 from 40k) / BP-s1 / BP-s2 — quantifies BOTH the +erosion damage AND the fix's recovery in one shot. |