summaryrefslogtreecommitdiff
path: root/docs/campaign/CASCADE_ABLATION_PLAN.md
diff options
context:
space:
mode:
authorYuren Hao <yurenh2@illinois.edu>2026-07-29 18:37:19 -0500
committerYuren Hao <yurenh2@illinois.edu>2026-07-29 18:37:19 -0500
commita2c63ca7f9719ca38ef57b2f9d0bb251e016e678 (patch)
tree5477751f9e65f5c98e13b87d68ff4a10f74990ba /docs/campaign/CASCADE_ABLATION_PLAN.md
parent469d6ce606a2a00dd6695ce2bd7c7851c0088799 (diff)
小阶梯排队(用户设计:向下scale反推向上): C256/C384 FW新档+C512泄漏仪器(现成ckpt) — 四点画gap(宽度)+dose*(宽度)双定律,判别×1→×128是幂律还是宽度阈值; 顺带量化72M gap里可关闭份额; 链在dg128后自动接力
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
Diffstat (limited to 'docs/campaign/CASCADE_ABLATION_PLAN.md')
-rw-r--r--docs/campaign/CASCADE_ABLATION_PLAN.md10
1 files changed, 10 insertions, 0 deletions
diff --git a/docs/campaign/CASCADE_ABLATION_PLAN.md b/docs/campaign/CASCADE_ABLATION_PLAN.md
index f3678b3..8d0ed5c 100644
--- a/docs/campaign/CASCADE_ABLATION_PLAN.md
+++ b/docs/campaign/CASCADE_ABLATION_PLAN.md
@@ -568,6 +568,16 @@ direction), not training-under-fault; wave-2 = co-training with faults injected
+### QUEUED (2026-07-29, user design): WIDTH MINI-LADDER — scale DOWN to extrapolate UP.
+New FineWeb rungs below the existing pair: C256 (~27M, 0.53B tok) + C384 (~46M, 0.93B tok),
+L12/hd64, Chinchilla-matched, EP(bsign)+BP twins; plus the leak instrument AT C512 (existing
+fw72m_bsign_s190000: dgain dose {1,4,16} + allbp bar). Four-point deliverables:
+gap(width) and dose*(width). Key discriminator: C512->C768 dose jumped x1 -> x128 — smooth
+power law (dose ~ width^k -> soft wall, budget k for 270M) vs width THRESHOLD near C600
+(leak absent below -> different physics, sharper story). Also quantifies whether the 72M
+0.076 gap hides a small closable leak (lk512 arms answer directly). Chained behind fw135m_dg128
+on all three GPUs; ~12h of ladder after the validation completes.
+
### RESULT 72 (2026-07-29): THE CURVE GOES ALL THE WAY — dg128 closes 97% (tail within
0.0015 of the all-BP bar); the physics leak is FULLY REDEEMABLE by displacement amplification.
FULL-DOSE VALIDATION LAUNCHED.