#!/bin/bash
# The three Online-Mind2Web configurations with the local Qwen3.6-35B-A3B, each in its own isolated test site.
cd /home/ckl/projects/S/laya
for CFG in llm s2; do CFG=$CFG LLM=llama finetune/isolated.sh bash finetune/run_om2w.sh; done
# re-judge the earlier laya-only run with the 35B judge (same judge as the two runs above)
finetune/isolated.sh bash -c "bash finetune/infra.sh start_llama >/dev/null; until curl -sf -m 3 --noproxy '*' http://127.0.0.1:30000/health >/dev/null; do sleep 3; done;
  .venv/bin/python finetune/judge_om2w.py finetune/out/om2w_fast_sglang_laya-browser-x5.jsonl finetune/out/om2w_fast_sglang_laya-browser-x5.judged35.jsonl"
echo ALL_DONE