diff options
| author | Yuren Hao <yurenh2@illinois.edu> | 2026-07-16 12:55:33 -0500 |
|---|---|---|
| committer | Yuren Hao <yurenh2@illinois.edu> | 2026-07-16 12:55:33 -0500 |
| commit | 4c7cdeeba856e360f6be29cf03ccb8c73f1049d3 (patch) | |
| tree | c50cf431bdbc638d35d1eefa3b307c236dc8e888 | |
| parent | 3cf5827cd73d92462896d09c5e42d3f1cbf22b45 (diff) | |
RESULT 32: crown resealed — fw72m_cent 3.3318 vs BP 3.2884 (gap 0.043, 10x reduction), zero guards over 234k, predictions beaten 8x
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
| -rw-r--r-- | docs/campaign/CASCADE_ABLATION_PLAN.md | 19 |
1 files changed, 19 insertions, 0 deletions
diff --git a/docs/campaign/CASCADE_ABLATION_PLAN.md b/docs/campaign/CASCADE_ABLATION_PLAN.md index c590b60..bd5ec4f 100644 --- a/docs/campaign/CASCADE_ABLATION_PLAN.md +++ b/docs/campaign/CASCADE_ABLATION_PLAN.md @@ -568,6 +568,25 @@ direction), not training-under-fault; wave-2 = co-training with faults injected +### RESULT 32 (2026-07-16): CROWN RESEALED — fw72m_cent 3.3318 vs BP 3.2884: honest gap 0.043, 10x below the blown-schedule number. +fw72m_cent complete: 234k steps / 1.44B FineWeb tokens, from scratch, fully BP-free, DDP 2xA6000. +| | best val CE | note | +|---|---|---| +| BP twin | 3.2884 | @195.6k | +| **fw72m_cent** | **3.3318** | @203.7k — still improving in the final quarter | +| original fw72m | 3.7117 | @104.8k, then 90k-step starve + 195k blow | +- Registered predictions (RESULT 24): (a) no blow — ZERO skipped steps in 234k ✓; (b) beats 3.7117 + ✓ (by 0.38); (c) gap 0.25-0.35 — BEAT 8x (0.043). +- beta history: 3e-4 ramp (first 20k) -> 3e-3 for ~214k steps; the ride never ended — bcap grazed + twice (2.76e-3 / 2.65e-3 single lines) and recovered instantly. cent's trajectory NEVER met the + wall the original hit at 1e-3@195k: the ceiling is trajectory-specific, and the healthy + window-riding path kept its margin. (Honest note: this also means the 72M ceiling-descent curve + from the original run does NOT transfer across recipes.) +- Best kept improving to 203.7k (no 105k-style freeze): the SNR account balanced. +- Samples (fw72m_cent_s205000): FineWeb register, "can-read" PASS (runs/fw72m_cent_samples.txt). +- HEADLINE: largest BP-free transformer LM (72.11M x 1.44B tokens), gap to matched BP twin 0.043 + (~1.3% relative), one governor knob, standard architecture, standard inference. + ### RESULT 31 (2026-07-16): DECOUPLING VERDICT — the tail win is ALL beta; centered is CE-neutral at 42M tail. RESULT 22's mechanism reading corrected. The missing arms7 control (user-demanded): plain single-sided @ beta 3e-3 flat tail. | arm (45k->55k) | best | note | |