erhan/abap-llm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

STATE: baseline restart time

Browse Source
This commit is contained in:
Kral
2026-10-04 07:59:38 +02:00
parent 5c68a1b1b7
commit 342eb6fc9a
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
train/STATE.md
View File

@@ -30,9 +30,9 @@ Task: `docs/stage1-training-task.md`. Settings and weights: `train/README.md`. U
- MLX server (restarted 2026-10-04 06:38 after it had exited; PID in `pgrep -f mlx_lm`), log `runs/stage1/server.log`.
- Baseline on the 11-task subset (`train/subset.json`), thinking off, loop guard 3, max_tokens 16384, started
2026-10-04 about 08:00 by `train/baseline_chain.sh` (run base 20400), logs `runs/stage1/baseline_chain.log` and
2026-10-04 08:03 by `train/baseline_chain.sh` (run base 20500; the guard also ends read loops), logs `runs/stage1/baseline_chain.log` and
`runs/stage1/baseline.log`. Notification after 2 tasks and at the end ("Baseline (11 tasks) ended").
- The T01 trial runs without the guard were stopped (`_aborted_*` in `runs/stage1/baseline/`, A4H objects deleted).
- Earlier attempts (T01 without the guard, T01+G0105 with the push-only guard) were stopped (`_aborted_*` in `runs/stage1/baseline/`, A4H objects deleted).
## Next