gahow/aituner
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Ablation: --skip-baseline so loops climb from first proposal

Browse Source 
The low-capacity TP1 auto-baseline is infeasible under tight TTFT/TPOT + time
compression, which tripped baseline_all_infeasible and terminated the loop before any
climb. Skip the auto-baseline so both runs start from the first LLM/harness proposal
(harness steers to TP from the long-prompt profile) — the ablation is about the
proposal path, so an explicit TP1 row is not required.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Gahow Wang
2026-06-16 20:59:46 +08:00
parent 37342a5749
commit 579dd86698
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
scripts/run_ablation_pair.sh
View File

@@ -9,13 +9,13 @@ rm -rf .aituner/abl-harness .aituner/abl-naive .aituner/ABLATION_DONE
echo "=== harness ON start $(date -Is) ==="
PYTHONPATH=src python3 -m aituner.cli study tune \
--spec configs/examples/dash0_qwen27b_ablation_harness_on.json \
--store-root .aituner/abl-harness --max-trials 6 > .aituner/abl-harness.log 2>&1
--store-root .aituner/abl-harness --max-trials 6 --skip-baseline > .aituner/abl-harness.log 2>&1
echo "=== harness ON done $(date -Is) ==="
echo "=== naive OFF start $(date -Is) ==="
PYTHONPATH=src python3 -m aituner.cli study tune \
--spec configs/examples/dash0_qwen27b_ablation_naive_off.json \
--store-root .aituner/abl-naive --max-trials 6 > .aituner/abl-naive.log 2>&1
--store-root .aituner/abl-naive --max-trials 6 --skip-baseline > .aituner/abl-naive.log 2>&1
echo "=== naive OFF done $(date -Is) ==="
touch .aituner/ABLATION_DONE