lzy/sci-gui-agent-benchmark
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add consistent scores validation (#368)

Browse Source 
* Add consistent scores validation

* revert osworld_run_maestro.py changes
This commit is contained in:
Daphne Barretto
2025-10-28 10:44:48 -07:00
committed by GitHub
parent 3bf54c92a9
commit 21c2b7629b
3 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
run.py
View File

@@ -218,7 +218,7 @@ def test(args: argparse.Namespace, test_all_meta: dict) -> None:
f.write("\n") f.write("\n")
env.close() env.close()
logger.info(f"Average score: {sum(scores) / len(scores)}") logger.info(f"Average score: {sum(scores) / len(scores) if scores else 0}")
def get_unfinished( def get_unfinished(

2
run_autoglm.py
View File

@@ -457,7 +457,7 @@ def test(args: argparse.Namespace, test_all_meta: dict) -> None:
f.write("\n") f.write("\n")
env.close() env.close()
logger.info(f"Average score: {sum(scores) / len(scores)}") logger.info(f"Average score: {sum(scores) / len(scores) if scores else 0}")
def get_unfinished(action_space, use_model, observation_type, result_dir, total_file_json): def get_unfinished(action_space, use_model, observation_type, result_dir, total_file_json):

2
run_autoglm_v.py
View File

@@ -485,7 +485,7 @@ def test(args: argparse.Namespace, test_all_meta: dict) -> None:
f.write("\n") f.write("\n")
env.close() env.close()
logger.info(f"Average score: {sum(scores) / len(scores)}") logger.info(f"Average score: {sum(scores) / len(scores) if scores else 0}")
def get_unfinished(action_space, use_model, observation_type, result_dir, total_file_json): def get_unfinished(action_space, use_model, observation_type, result_dir, total_file_json):