upgrade to latest sagemaker-experiments (#163)

Author: danabens

docker/1.4.0/py3/Dockerfile.cpu

@@ -96,7 +96,7 @@ RUN pip install --upgrade pip --trusted-host pypi.org --trusted-host files.pytho
     scipy==1.2.2 \
     smdebug==0.5.0.post0 \
     sagemaker==1.50.17 \
-    sagemaker-experiments==0.1.3 \
+    sagemaker-experiments==0.1.7 \
     /sagemaker_pytorch_training.tar.gz \
  && pip install --no-cache-dir -U https://pytorch-aws.s3.amazonaws.com/pytorch-1.4.0/py3/cpu/torch-1.4.0-cp36-cp36m-manylinux1_x86_64.whl \
  && pip uninstall -y torchvision \

docker/1.4.0/py3/Dockerfile.gpu

@@ -120,7 +120,7 @@ RUN /opt/conda/bin/conda config --set ssl_verify False \
 RUN pip install \
     --no-cache-dir smdebug==0.5.0.post0 \
     sagemaker==1.50.17 \
-    sagemaker-experiments==0.1.3 \
+    sagemaker-experiments==0.1.7 \
     --no-cache-dir fastai==1.0.59 \
     awscli \
     scipy==1.2.2 \

setup.py

@@ -50,8 +50,9 @@ def read(fname):
 
     install_requires=['retrying', 'sagemaker-containers>=2.6.2', 'six>=1.12.0'],
     extras_require={
-        'test': ['boto3==1.9.169', 'coverage==4.5.3', 'docker-compose==1.23.2', 'flake8==3.7.7', 'Flask==1.1.1',
+        'test': ['boto3==1.10.32', 'coverage==4.5.3', 'docker-compose==1.23.2', 'flake8==3.7.7', 'Flask==1.1.1',
                  'mock==2.0.0', 'pytest==4.4.0', 'pytest-cov==2.7.1', 'pytest-xdist==1.28.0', 'PyYAML==3.10',
-                 'sagemaker==1.28.1', 'torch==1.4.0', 'torchvision==0.5.0', 'tox==3.7.0', 'requests_mock==1.6.0']
+                 'sagemaker==1.28.1', 'torch==1.4.0', 'torchvision==0.5.0', 'tox==3.7.0', 'requests_mock==1.6.0',
+                 'sagemaker-experiments==0.1.7']
     },
 )

test/integration/sagemaker/test_experiments.py

@@ -0,0 +1,92 @@
+# Copyright 2018-2020 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License").
+# You may not use this file except in compliance with the License.
+# A copy of the License is located at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# or in the "license" file accompanying this file. This file is distributed
+# on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either
+# express or implied. See the License for the specific language governing
+# permissions and limitations under the License.
+from __future__ import absolute_import
+
+import time
+
+import pytest
+from sagemaker.pytorch import PyTorch
+from sagemaker import utils
+from smexperiments.experiment import Experiment
+from smexperiments.trial import Trial
+from smexperiments.trial_component import TrialComponent
+from test.integration import training_dir, smdebug_mnist_script, DEFAULT_TIMEOUT
+from test.integration.sagemaker.timeout import timeout
+
+
+@pytest.mark.skip_py2_containers
+def test_training(sagemaker_session, ecr_image, instance_type):
+
+    sm_client = sagemaker_session.sagemaker_client
+
+    experiment_name = "pytorch-container-integ-test-{}".format(int(time.time()))
+
+    experiment = Experiment.create(
+        experiment_name=experiment_name,
+        description="Integration test full customer e2e from sagemaker-pytorch-container",
+        sagemaker_boto_client=sm_client,
+    )
+
+    trial_name = "pytorch-container-integ-test-{}".format(int(time.time()))
+    trial = Trial.create(
+        experiment_name=experiment_name, trial_name=trial_name, sagemaker_boto_client=sm_client
+    )
+
+    hyperparameters = {
+        "random_seed": True,
+        "num_steps": 50,
+        "smdebug_path": "/opt/ml/output/tensors",
+        "epochs": 1,
+        "data_dir": training_dir,
+    }
+
+    training_job_name = utils.unique_name_from_base("test-pytorch-experiments-image")
+
+    # create a training job and wait for it to complete
+    with timeout(minutes=DEFAULT_TIMEOUT):
+        pytorch = PyTorch(
+            entry_point=smdebug_mnist_script,
+            role="SageMakerRole",
+            train_instance_count=1,
+            train_instance_type=instance_type,
+            sagemaker_session=sagemaker_session,
+            image_name=ecr_image,
+            hyperparameters=hyperparameters,
+        )
+        training_input = pytorch.sagemaker_session.upload_data(
+            path=training_dir, key_prefix="pytorch/mnist"
+        )
+        pytorch.fit({"training": training_input}, job_name=training_job_name)
+
+    training_job = sm_client.describe_training_job(TrainingJobName=training_job_name)
+    training_job_arn = training_job["TrainingJobArn"]
+
+    # verify trial component auto created from the training job
+    trial_components = list(
+        TrialComponent.list(source_arn=training_job_arn, sagemaker_boto_client=sm_client)
+    )
+
+    trial_component_summary = trial_components[0]
+    trial_component = TrialComponent.load(
+        trial_component_name=trial_component_summary.trial_component_name,
+        sagemaker_boto_client=sm_client,
+    )
+
+    # associate the trial component with the trial
+    trial.add_trial_component(trial_component)
+
+    # cleanup
+    trial.remove_trial_component(trial_component_summary.trial_component_name)
+    trial_component.delete()
+    trial.delete()
+    experiment.delete()