def test_attach(sagemaker_session, rl_coach_mxnet_version):
training_image = "1.dkr.ecr.us-west-2.amazonaws.com/sagemaker-rl-{}:{}{}-cpu-py3".format(
RLFramework.MXNET.value, RLToolkit.COACH.value, rl_coach_mxnet_version
)
supported_versions = TOOLKIT_FRAMEWORK_VERSION_MAP[RLToolkit.COACH.value]
framework_version = supported_versions[rl_coach_mxnet_version][RLFramework.MXNET.value]
returned_job_description = {
"AlgorithmSpecification": {"TrainingInputMode": "File", "TrainingImage": training_image},
"HyperParameters": {
"sagemaker_submit_directory": '"s3://some/sourcedir.tar.gz"',
"sagemaker_program": '"train_coach.py"',
"sagemaker_enable_cloudwatch_metrics": "false",
"sagemaker_container_log_level": '"logging.INFO"',
"sagemaker_job_name": '"neo"',
"training_steps": "100",
"sagemaker_region": '"us-west-2"',
},
"RoleArn": "arn:aws:iam::366:role/SageMakerRole",
"ResourceConfig": {
"VolumeSizeInGB": 30,
"InstanceCount": 1,
"InstanceType": "ml.c4.xlarge",
},
"StoppingCondition": {"MaxRuntimeInSeconds": 24 * 60 * 60},
"TrainingJobName": "neo",
"TrainingJobStatus": "Completed",
"TrainingJobArn": "arn:aws:sagemaker:us-west-2:336:training-job/neo",
"OutputDataConfig": {"KmsKeyId": "", "S3OutputPath": "s3://place/output/neo"},
"TrainingJobOutput": {"S3TrainingJobOutput": "s3://here/output.tar.gz"},
}
sagemaker_session.sagemaker_client.describe_training_job = Mock(
name="describe_training_job", return_value=returned_job_description
)
estimator = RLEstimator.attach(training_job_name="neo", sagemaker_session=sagemaker_session)
assert estimator.latest_training_job.job_name == "neo"
assert estimator.framework == RLFramework.MXNET.value
assert estimator.toolkit == RLToolkit.COACH.value
assert estimator.framework_version == framework_version
assert estimator.toolkit_version == rl_coach_mxnet_version
assert estimator.role == "arn:aws:iam::366:role/SageMakerRole"
assert estimator.train_instance_count == 1
assert estimator.train_max_run == 24 * 60 * 60
assert estimator.input_mode == "File"
assert estimator.base_job_name == "neo"
assert estimator.output_path == "s3://place/output/neo"
assert estimator.output_kms_key == ""
assert estimator.hyperparameters()["training_steps"] == "100"
assert estimator.source_dir == "s3://some/sourcedir.tar.gz"
assert estimator.entry_point == "train_coach.py"
assert estimator.metric_definitions == RLEstimator.default_metric_definitions(RLToolkit.COACH)
def test_attach(sagemaker_session, rl_coach_mxnet_version):
training_image = '1.dkr.ecr.us-west-2.amazonaws.com/sagemaker-rl-{}:{}{}-cpu-py3'\
.format(RLFramework.MXNET.value, RLToolkit.COACH.value, rl_coach_mxnet_version)
supported_versions = TOOLKIT_FRAMEWORK_VERSION_MAP[RLToolkit.COACH.value]
framework_version = supported_versions[rl_coach_mxnet_version][RLFramework.MXNET.value]
returned_job_description = {'AlgorithmSpecification': {'TrainingInputMode': 'File',
'TrainingImage': training_image},
'HyperParameters':
{'sagemaker_submit_directory': '"s3://some/sourcedir.tar.gz"',
'sagemaker_program': '"train_coach.py"',
'sagemaker_enable_cloudwatch_metrics': 'false',
'sagemaker_container_log_level': '"logging.INFO"',
'sagemaker_job_name': '"neo"',
'training_steps': '100',
'sagemaker_region': '"us-west-2"'},
'RoleArn': 'arn:aws:iam::366:role/SageMakerRole',
'ResourceConfig':
{'VolumeSizeInGB': 30,
'InstanceCount': 1,
'InstanceType': 'ml.c4.xlarge'},
'StoppingCondition': {'MaxRuntimeInSeconds': 24 * 60 * 60},
'TrainingJobName': 'neo',
'TrainingJobStatus': 'Completed',
'OutputDataConfig': {'KmsKeyId': '',
'S3OutputPath': 's3://place/output/neo'},
'TrainingJobOutput': {
'S3TrainingJobOutput': 's3://here/output.tar.gz'}}
sagemaker_session.sagemaker_client.describe_training_job = \
Mock(name='describe_training_job', return_value=returned_job_description)
estimator = RLEstimator.attach(training_job_name='neo', sagemaker_session=sagemaker_session)
assert estimator.latest_training_job.job_name == 'neo'
assert estimator.framework == RLFramework.MXNET.value
assert estimator.toolkit == RLToolkit.COACH.value
assert estimator.framework_version == framework_version
assert estimator.toolkit_version == rl_coach_mxnet_version
assert estimator.role == 'arn:aws:iam::366:role/SageMakerRole'
assert estimator.train_instance_count == 1
assert estimator.train_max_run == 24 * 60 * 60
assert estimator.input_mode == 'File'
assert estimator.base_job_name == 'neo'
assert estimator.output_path == 's3://place/output/neo'
assert estimator.output_kms_key == ''
assert estimator.hyperparameters()['training_steps'] == '100'
assert estimator.source_dir == 's3://some/sourcedir.tar.gz'
assert estimator.entry_point == 'train_coach.py'
assert estimator.metric_definitions == RLEstimator.default_metric_definitions(RLToolkit.COACH)
if pretrained == True:
hyperparameters_core['pretrained_s3_bucket'] = "{}".format(
s3_pretrained_bucket)
hyperparameters_core['pretrained_s3_prefix'] = s3_pretrained_prefix
# Downloading the hyperparameter file from our local bucket.
hyperparameter_data = io.BytesIO()
s3Client.download_fileobj(
s3_bucket, hyperparameter_file, hyperparameter_data)
hyperparameters_nn = json.loads(hyperparameter_data.getvalue().decode("utf-8"))
hyperparameters = {**hyperparameters_core, **hyperparameters_nn}
print("Configured following hyperparameters")
print(hyperparameters)
estimator = RLEstimator(entry_point="training_worker.py",
source_dir='markov',
dependencies=["common/sagemaker_rl","markov"],
sagemaker_session=sage_session,
# bypass sagemaker SDK validation of the role
role="aaa/",
train_instance_type=instance_type,
train_instance_count=1,
output_path=s3_output_path,
base_job_name=job_name,
image_name=image_name,
train_max_run=job_duration_in_seconds, # Maximum runtime in seconds
hyperparameters=hyperparameters,
metric_definitions=RLEstimator.default_metric_definitions(RLToolkit.COACH)
)
estimator.fit(job_name=job_name, wait=False)
