eval update

2025-06-07 13:19:22 +00:00
parent 4ade4114da
commit c57b1d4e7a
6 changed files with 38 additions and 17 deletions
--- a/run_operator.sh
+++ b/run_operator.sh
@@ -2,8 +2,8 @@ python run_multienv_openaicua.py \
 --headless \
 --observation_type screenshot \
 --model computer-use-preview \
--result_dir ./results_small_retest \
--test_all_meta_path evaluation_examples/test_small.json \
+--result_dir ./results_all_ifmessage_promptnochange \
+--test_all_meta_path evaluation_examples/test_all.json \
 --region us-east-1 \
 --max_steps 150 \
 --num_envs 10