Files
aituner/scripts/run_harness_only_d1.sh

17 lines
1011 B
Bash

#!/usr/bin/env bash
# Harness-only re-run on gpt-5.5 to EMPIRICALLY verify the gpu-memory-utilization fix:
# success = the harness recovers ~0.87/GPU (climbs gpu-mem-util to ~0.94) and then stops,
# matching the naive-discovered ground truth. Run from the repo root on dash1.
set -u
read_key() { export OPENAI_API_KEY=$(python3 -c 'import json,pathlib;print(json.load(open(pathlib.Path.home()/".codex/auth.json"))["OPENAI_API_KEY"])'); }
export http_proxy= https_proxy= all_proxy= HTTP_PROXY= HTTPS_PROXY= ALL_PROXY= no_proxy='*'
mkdir -p .aituner
rm -rf .aituner/abl12-harness .aituner/abl12-harness.log .aituner/HARNESS_ONLY_DONE
read_key
echo "=== harness ON (gpt-5.5, gpu-mem-util fix) start $(date -Is) ==="
PYTHONPATH=src python3 -m aituner.cli study tune \
--spec configs/examples/dash0_qwen27b_ablation_harness_on.json \
--store-root .aituner/abl12-harness --max-trials 12 --skip-baseline > .aituner/abl12-harness.log 2>&1
echo "=== harness ON done $(date -Is) ==="
touch .aituner/HARNESS_ONLY_DONE