fix: remove unnecessary failure case tests (aws#892)

Author: icywang86rui

tests/data/chainer_mnist/failure_script.py

@@ -125,25 +125,6 @@ def test_async_fit(sagemaker_session):
         _predict_and_assert(predictor)
 
 
-def test_failed_training_job(sagemaker_session, chainer_full_version):
-    with timeout(minutes=TRAINING_DEFAULT_TIMEOUT_MINUTES):
-        script_path = os.path.join(DATA_DIR, "chainer_mnist", "failure_script.py")
-
-        chainer = Chainer(
-            entry_point=script_path,
-            role="SageMakerRole",
-            framework_version=chainer_full_version,
-            py_version=PYTHON_VERSION,
-            train_instance_count=1,
-            train_instance_type="ml.c4.xlarge",
-            sagemaker_session=sagemaker_session,
-        )
-
-        with pytest.raises(ValueError) as e:
-            chainer.fit(job_name=unique_name_from_base("test-chainer-training"))
-        assert "ExecuteUserScriptError" in str(e.value)
-
-
 def _run_mnist_training_job(
     sagemaker_session, instance_type, instance_count, chainer_full_version, wait=True
 ):

tests/data/pytorch_mnist/failure_script.py

@@ -286,22 +286,3 @@ def test_async_fit(sagemaker_session, mxnet_full_version):
         data = numpy.zeros(shape=(1, 1, 28, 28))
         result = predictor.predict(data)
         assert result is not None
-
-
-def test_failed_training_job(sagemaker_session, mxnet_full_version):
-    with timeout():
-        script_path = os.path.join(DATA_DIR, "mxnet_mnist", "failure_script.py")
-
-        mx = MXNet(
-            entry_point=script_path,
-            role="SageMakerRole",
-            framework_version=mxnet_full_version,
-            py_version=PYTHON_VERSION,
-            train_instance_count=1,
-            train_instance_type="ml.c4.xlarge",
-            sagemaker_session=sagemaker_session,
-        )
-
-        with pytest.raises(ValueError) as e:
-            mx.fit()
-        assert "ExecuteUserScriptError" in str(e.value)

tests/integ/test_chainer_train.py

@@ -116,20 +116,6 @@ def test_async_fit_deploy(sagemaker_session, pytorch_full_version):
             assert output.shape == (batch_size, 10)
 
 
-# TODO(nadiaya): Run against local mode when errors will be propagated
-def test_failed_training_job(sagemaker_session, pytorch_full_version):
-    script_path = os.path.join(MNIST_DIR, "failure_script.py")
-
-    with timeout(minutes=TRAINING_DEFAULT_TIMEOUT_MINUTES):
-        pytorch = _get_pytorch_estimator(
-            sagemaker_session, pytorch_full_version, entry_point=script_path
-        )
-
-        with pytest.raises(ValueError) as e:
-            pytorch.fit()
-        assert "ExecuteUserScriptError" in str(e.value)
-
-
 def _upload_training_data(pytorch):
     return pytorch.sagemaker_session.upload_data(
         path=os.path.join(MNIST_DIR, "training"),