We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent e52ea9b commit d2f132dCopy full SHA for d2f132d
eval_protocol/pytest/evaluation_test.py
@@ -465,14 +465,14 @@ async def _execute_with_semaphore(row):
465
passed = None
466
467
if threshold is not None:
468
- success_passed, std_passed = True, True
+ success_passed, standard_error_passed = True, True
469
470
success_passed = agg_score >= threshold.success
471
472
if threshold.standard_error is not None:
473
- std_passed = standard_error <= threshold.standard_error
+ standard_error_passed = standard_error <= threshold.standard_error
474
475
- passed = success_passed and std_passed
+ passed = success_passed and standard_error_passed
476
477
# Update eval metadata passed field for all results
478
for result in all_results:
0 commit comments