Gahow Wang
83162e7a64
- Pin endpoint.model=gpt-5.5, base_url=https://ai.gahow.org/v1, wire_api=chat.completions in both ablation specs so both arms uniformly use the current ~/.codex model (the prior runs used the stale ai.prism.uno/gpt-5.4 that config.toml has since moved off). - run_ablation_pair_d1.sh re-reads the codex token from auth.json right before each arm instead of capturing it once at launch (the stale-at-use capture 401'd naive 2/3). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
32 lines
1.7 KiB
Bash
32 lines
1.7 KiB
Bash
#!/usr/bin/env bash
|
|
# 12-iteration harness-vs-naive ablation, both arms on dash1 (clean paired run,
|
|
# no host confound). Substrate: real output_length (no completion override),
|
|
# replay_time_scale=0.8775 (criterion-A, sim_A>=0.90), Stop-A on (LCA offered
|
|
# window), per-probe Stop-A-consistent drain deadline. Harness stops early; naive
|
|
# runs the full budget. Run from the repo root on dash1.
|
|
set -u
|
|
# Re-read the codex token from auth.json right before each arm (capturing it once at
|
|
# launch goes stale during a long run -- that is what 401'd naive runs 2/3).
|
|
read_key() { export OPENAI_API_KEY=$(python3 -c 'import json,pathlib;print(json.load(open(pathlib.Path.home()/".codex/auth.json"))["OPENAI_API_KEY"])'); }
|
|
# codex config.toml points at a dash0-local proxy (127.0.0.1:11235); on dash1 the
|
|
# LLM endpoint is reachable directly, so force a direct connection.
|
|
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-naive .aituner/ABLATION12_DONE
|
|
|
|
read_key
|
|
echo "=== harness ON (12-iter) 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 (12-iter) done $(date -Is) ==="
|
|
|
|
read_key
|
|
echo "=== naive OFF (12-iter) start $(date -Is) ==="
|
|
PYTHONPATH=src python3 -m aituner.cli study tune \
|
|
--spec configs/examples/dash0_qwen27b_ablation_naive_off.json \
|
|
--store-root .aituner/abl12-naive --max-trials 12 --skip-baseline > .aituner/abl12-naive.log 2>&1
|
|
echo "=== naive OFF (12-iter) done $(date -Is) ==="
|
|
|
|
touch .aituner/ABLATION12_DONE
|