|
71 | 71 | "builtin_metrics": ["Completeness", "Faithfulness"], |
72 | 72 | "custom_metrics_json": json.dumps([CUSTOM_METRIC_DICT]), |
73 | 73 | "s3_output_path": "s3://sagemaker-us-west-2-729646638167/model-customization/eval/base-model-fix-test/", |
74 | | - "mlflow_tracking_server_arn": "arn:aws:sagemaker:us-west-2:729646638167:mlflow-app/app-W7FOBBXZANVX", |
| 74 | + "mlflow_tracking_server_arn": "arn:aws:sagemaker:us-west-2:729646638167:mlflow-app/app-TTAUWUNMUHH6", |
75 | 75 | "evaluate_base_model": True, # This is the key difference - testing base model evaluation |
76 | 76 | "region": "us-west-2", |
77 | 77 | } |
@@ -115,6 +115,7 @@ def test_base_model_evaluation_uses_correct_weights(self): |
115 | 115 | custom_metrics=TEST_CONFIG["custom_metrics_json"], |
116 | 116 | s3_output_path=TEST_CONFIG["s3_output_path"], |
117 | 117 | evaluate_base_model=TEST_CONFIG["evaluate_base_model"], |
| 118 | + mlflow_resource_arn=TEST_CONFIG["mlflow_tracking_server_arn"], |
118 | 119 | ) |
119 | 120 |
|
120 | 121 | # Verify evaluator configuration |
@@ -271,6 +272,7 @@ def test_base_model_false_still_works(self): |
271 | 272 | builtin_metrics=TEST_CONFIG["builtin_metrics"], |
272 | 273 | s3_output_path=TEST_CONFIG["s3_output_path"], |
273 | 274 | evaluate_base_model=False, # Only evaluate custom model |
| 275 | + mlflow_resource_arn=TEST_CONFIG["mlflow_tracking_server_arn"], |
274 | 276 | ) |
275 | 277 |
|
276 | 278 | # Verify evaluator configuration |
|
0 commit comments