From 301c221d8e13a7ea0806f314475917c5bd8182fa Mon Sep 17 00:00:00 2001 From: Kral Date: Mon, 5 Oct 2026 21:31:15 +0200 Subject: [PATCH] Budget guard from panel 50.00: limit 128 Co-Authored-By: Claude Sonnet 5.5 --- train/STATE.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/train/STATE.md b/train/STATE.md index 7b65c9f..f83987c 100644 --- a/train/STATE.md +++ b/train/STATE.md @@ -175,3 +175,5 @@ Training runs on HF Jobs with Unsloth, not on the Mac. No `mlx_lm` training. - **Generation:** `trainset run --plan balanced` (3 workers, started by the pipeline): every slot takes the kind with the biggest deficit against the target; a kind is skipped with 6+ tries and under 20 % accepted, or with more than 8 accepted tasks waiting for a first trajectory run. 20 % error-targeted, 30 % hard (difficulty 3). K variants stay at 10 %. - **Trajectories:** the next task is the one whose kind has the biggest deficit (accepted trajectories per kind). Summary now lists the mix and DDLS reject reasons. - **Incident 19:25:** restarting the controller I started a second one by mistake (wrong `pgrep` pattern) and deleted the objects of a running run. Both controllers were stopped, leftovers cleaned, one controller runs. One table `Z4AJ50UB_PO_HEAD` kept a lock from the interrupted write (SM12 needed). Interrupting a write leaks the lock: never kill a controller during a run without checking. + +- 2026-10-05 21:31 budget correction 4: panel 50.00 at ledger 111.22; since 45.0 (100.62): 10.6 ledger / 5.0 usage = 2.12 (generation of new types and first runs). Guard recomputed with the pessimistic ratio 1.2: panel left 60 - 50 - 3.0 reserve = 7.0 usage x 1.2 = 8.4 ledger, guard 119.6, `BUDGET_LIMIT_USD` 128 (reserve 8). Only kinds below target run (Kral + Opus 2026-10-05).