diff options
| author | Yuren Hao <yurenh2@illinois.edu> | 2026-07-30 14:45:16 -0500 |
|---|---|---|
| committer | Yuren Hao <yurenh2@illinois.edu> | 2026-07-30 14:45:16 -0500 |
| commit | 5da39cf68b19b1be997db1956026af3f68576f73 (patch) | |
| tree | 761a48d413496f40c0139534799ac2a3ccb4a89e /docs | |
| parent | d075af6e8ddcb067444f1c8b64cb294a75dd4e6a (diff) | |
RESULT 75: dg128完赛口径分裂(best回带+0.049/尾窗未回带+0.133,关闭84%/63% vs 仪器97%); 续跑欠账vs剂量漂移两候选,谱仪轨迹轴裁决; ×128位移全程零发散; class-2归档
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
Diffstat (limited to 'docs')
| -rw-r--r-- | docs/campaign/CASCADE_ABLATION_PLAN.md | 16 |
1 files changed, 16 insertions, 0 deletions
diff --git a/docs/campaign/CASCADE_ABLATION_PLAN.md b/docs/campaign/CASCADE_ABLATION_PLAN.md index 931bee7..adbcaca 100644 --- a/docs/campaign/CASCADE_ABLATION_PLAN.md +++ b/docs/campaign/CASCADE_ABLATION_PLAN.md @@ -1878,3 +1878,19 @@ quantization (wall-1: beta-displacement below bf16 resolution) — exactly as di - Cost consequence: COST_MODEL.md v2.1 (sourced July-2026 prices: market H100 $1.87-2.99/GPU.h, AWS p5e blocks $4.97/GPU.h post-hike) — with amp measured, 3B-Chinchilla ~$40k / 7Bx20B ~$30k on AWS blocks: BOTH inside the $50k envelope individually. amp is the Stage-2 default. + +## RESULT 75 (2026-07-30): dg128 全程验证完赛 — 口径分裂,class-2 归档 +Matched 三口径(同窗 434-440k, n=61/臂): +| 臂 | best | 尾窗中位 | +|---|---|---| +| dg128 (250k 起治疗) | 3.1387 | 3.3380 | +| bsign 未治疗 | 3.3839 | 3.5649 | +| BP twin | 3.0902 | 3.2051 | +- best 口径: gap +0.049, 回 72M 带(+0.076)以内, 关闭 84%; **尾窗口径: gap +0.133, 未回带, 关闭 63%**。 + 规范裁决用尾窗; best 是噪声评估的下探偏置(三臂都低 0.11-0.18, 含 BP → 口径病不是臂病)。 +- 仪器 97% vs 全程 63% 的差值解释候选: (a) **续跑只治后 190k 步** — 前 250k 未治疗欠账已烙进权重 + (dg128 resumed from untreated s250000, 探索性设计的固有混杂); (b) 剂量需求随走廊下沉增长, 6k 仪 + 器段低估长程需求。谱仪轨迹轴 (c768f23 vs c768f91) 直接裁决 (b); 裁 (a) 需 from-scratch treated 臂 + (~22h×3GPU, 等 geo 电池 + 谱仪结果再决定是否值得)。 +- 稳定性结论无保留: ×128 位移 190k 步零发散(drift 稳 0.008), 大位移在完整训练尺度安全。 +- 按 07-29 条令: class-2 exploratory, 不入 scaling 曲线; 价值 = "泄漏在全程可部分赎回" + 稳定性 + 上述口径教训。 |
