Handover notes, train/STATE.md, detached night chain for DeepSeek reruns and the stage 1 baseline
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014aUaQeLnwbb1zTpN7kHeat
This commit is contained in:
34
train/night_chain.sh
Executable file
34
train/night_chain.sh
Executable file
@@ -0,0 +1,34 @@
|
||||
#!/bin/sh
|
||||
# Night chain (2026-10-03), started detached so it survives the Claude Code session.
|
||||
# 1. When filter worker W6A (PID 57253) ends: start W7B (DeepSeek reruns, list in runs/stage1/w7b.txt).
|
||||
# 2. When the T01 test (PID 59414) and all DeepSeek workers end: check T01 in runs/stage1/baseline.json.
|
||||
# No harness error -> remove the T01 entry (it ran with the old budget 40) and run all 25 subset tasks.
|
||||
# 3. macOS notification at each end. Log: runs/stage1/night_chain.log
|
||||
cd "$(dirname "$0")/.."
|
||||
log() { echo "$(date '+%F %T') $*"; }
|
||||
while kill -0 57253 2>/dev/null; do sleep 30; done
|
||||
log "W6A ended; start W7B"
|
||||
nohup xargs python3 -m harness.empirical --model deepseek-v4.1-flash:cloud --run-base 18000 \
|
||||
< runs/stage1/w7b.txt > runs/emp_deepseek7b.log 2>&1 &
|
||||
W7B=$!
|
||||
log "W7B xargs PID $W7B"
|
||||
while kill -0 59414 2>/dev/null || kill -0 59510 2>/dev/null || kill -0 $W7B 2>/dev/null; do sleep 60; done
|
||||
log "T01 test and DeepSeek workers ended"
|
||||
osascript -e 'display notification "DeepSeek reruns ended" with title "stage1"'
|
||||
OK=$(python3 -c "
|
||||
import json
|
||||
t=json.load(open('runs/stage1/baseline.json'))['tasks'].get('T01',{})
|
||||
print('yes' if t and 'error' not in t and t.get('score') is not None else 'no')")
|
||||
log "T01 test result usable: $OK"
|
||||
if [ "$OK" != "yes" ]; then
|
||||
osascript -e 'display notification "T01 test failed: baseline not started" with title "stage1"'
|
||||
log "baseline NOT started"; exit 1
|
||||
fi
|
||||
python3 - <<'PY'
|
||||
import json
|
||||
p='runs/stage1/baseline.json'; r=json.load(open(p)); r.setdefault('t01_test_budget40', r['tasks'].pop('T01')); json.dump(r,open(p,'w'),indent=1)
|
||||
PY
|
||||
log "start baseline, 25 tasks"
|
||||
python3 train/baseline.py --label baseline --run-base 20100 > runs/stage1/baseline.log 2>&1
|
||||
log "baseline ended: $(python3 -c "import json;print(len(json.load(open('runs/stage1/baseline.json'))['tasks']))") tasks"
|
||||
osascript -e 'display notification "Baseline (25 tasks) ended" with title "stage1"'
|
||||
Reference in New Issue
Block a user