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

Baseline shortened: 11-task subset (1 per category + T01), max_tokens 16384, settings in README; baseline_chain.sh

Browse Source 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014aUaQeLnwbb1zTpN7kHeat
This commit is contained in:
Kral
2026-10-03 22:36:00 +02:00
parent 7054d9fd2e
commit 689820af4d
6 changed files with 200 additions and 97 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
train/baseline_chain.sh Executable file
View File

@@ -0,0 +1,20 @@
#!/bin/sh
# Baseline on the 11-task subset (Kral decision 2026-10-03), detached. Replaces night_chain.sh.
# macOS notification after 2 tasks (time estimate) and at the end. Log: runs/stage1/baseline.log, chain log below.
cd "$(dirname "$0")/.."
log() { echo "$(date '+%F %T') $*"; }
log "start baseline, 11 tasks, max_tokens 16384"
python3 train/baseline.py --label baseline --run-base 20200 > runs/stage1/baseline.log 2>&1 &
BP=$!
log "baseline PID $BP"
NOTE=0
while kill -0 $BP 2>/dev/null; do
N=$(python3 -c "import json;print(len(json.load(open('runs/stage1/baseline.json'))['tasks']))" 2>/dev/null || echo 0)
if [ "$NOTE" = 0 ] && [ "$N" -ge 2 ]; then
osascript -e 'display notification "Baseline: first 2 tasks done, ask for the time estimate" with title "stage1"'
log "2 tasks done"; NOTE=1
fi
sleep 60
done
log "baseline ended: $(python3 -c "import json;print(len(json.load(open('runs/stage1/baseline.json'))['tasks']))") tasks"
osascript -e 'display notification "Baseline (11 tasks) ended" with title "stage1"'