From db8faa68ffcd17f15d1eb293fb1395efb42d8293 Mon Sep 17 00:00:00 2001 From: Frank Date: Wed, 7 Oct 2026 02:49:14 -0700 Subject: [PATCH] docs(worklog): KLD reference complete (rows 50235), script-swap law third occurrence --- .../LLM/swift15-campaign-worklog.md | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/serverAppConfigs-docs/LLM/swift15-campaign-worklog.md b/serverAppConfigs-docs/LLM/swift15-campaign-worklog.md index d022395..bddcc2f 100644 --- a/serverAppConfigs-docs/LLM/swift15-campaign-worklog.md +++ b/serverAppConfigs-docs/LLM/swift15-campaign-worklog.md @@ -41,13 +41,24 @@ carries execution facts only. The cutover runbook 1.2.0 calib (MNBT 65536/seqs 8 per MOE-W4 930 tok/s law, synced commit 45de2fd) → `calib-push.py` parallel 16 → kill → prod restored by trap. - Ready on the branch: `convert-swift15-w4dn8.sh` (1.0.13 convert, gates: - ≥48 grams / bf16 deleted / disk floor / rad-info gptq receipt / ≥126,000 MiB), `apply-protected-cast.sh` (derive → recipe PROTECTED section, refuses double-derive), `kld-gate-swift15.sh` (candidate vs reference on 1.0.13, gate mean KL ≤ 0.03 / top-1 ≥ 95 %). - `frank-primary` showing `failed` during the campaign is the 143-on-stop signature of the foreground podman unit — cosmetic, not a crash. +## 2026-10-07 morning + +- **KLD reference COMPLETE** on 1.0.13: `/home/dank/corpora/kld-ref` 24 GiB, + `radiance-kld-1`, `rows: 50235`, 197 docs, top-16 log-probs (f16), + corpus fnv1a64 `a9d62b33c18b3d9c`. Record took ~4 h at the 32k step. + The wrapper died rc=127 AFTER the engine exited clean: the mid-run scp of + commit 45de2fd shifted bash's lazy read offset — script-swap law, third + fleet occurrence. Resume path added: `SKIP_KLD=1` + `rows: 50235` receipt + gate (cf6c62d). **Never scp a script a running process owns.** +- Calibration chain3 live on 1.2.0 (big-step shape MNBT 65536/seqs 8): push + started, requests landing at 7–8k tokens. + ## Campaign order after the chain 1. derive protected experts from Swift's own grams; apply to recipe.