Add Early Stopping to SageMaker Python SDK#541

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
cassiesu wants to merge 2 commits into from
Closed

Add Early Stopping to SageMaker Python SDK #541

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b86a28a
Add Early Stopping to SageMaker Python SDK
Dec 7, 2018
e8ae70d
fix flake8 check failure
Dec 10, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 16 additions & 0 deletions README.rst
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -596,6 +596,22 @@ A hyperparameter range can be one of three types: continuous, integer, or catego
The SageMaker Python SDK provides corresponding classes for defining these different types.
You can define up to 20 hyperparameters to search over, but each value of a categorical hyperparameter range counts against that limit.

By default, training job early stopping is turned off. To enable early stopping for the tuning job, you need to set the ``early_stopping_type`` parameter to ``Auto``:

.. code:: python

# Enable early stopping
my_tuner = HyperparameterTuner(estimator=my_estimator, # previously-configured Estimator object
objective_metric_name='validation-accuracy',
hyperparameter_ranges={'learning-rate': ContinuousParameter(0.05, 0.06)},
metric_definitions=[{'Name': 'validation-accuracy', 'Regex': 'validation-accuracy=(\d\.\d+)'}],
max_jobs=100,
max_parallel_jobs=10,
early_stopping_type='Auto')

When early stopping is turned on, Amazon SageMaker will automatically stop a training job if it appears unlikely to produce a model of better quality than other jobs.
If not using built-in Amazon SageMaker algorithms, note that, for early stopping to be effective, the objective metric should be emitted at epoch level.

If you are using an Amazon SageMaker built-in algorithm, you don't need to pass in anything for ``metric_definitions``.
In addition, the ``fit()`` call uses a list of ``RecordSet`` objects instead of a dictionary:

Expand Down
7 changes: 6 additions & 1 deletion src/sagemaker/session.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -350,7 +350,8 @@ def tune(self, job_name, strategy, objective_type, objective_metric_name,
max_jobs, max_parallel_jobs, parameter_ranges,
static_hyperparameters, input_mode, metric_definitions,
role, input_config, output_config, resource_config, stop_condition, tags,
warm_start_config, enable_network_isolation=False, image=None, algorithm_arn=None):
warm_start_config, enable_network_isolation=False, image=None, algorithm_arn=None,
early_stopping_type='Off'):
"""Create an Amazon SageMaker hyperparameter tuning job

Args:
Expand DownExpand Up@@ -396,6 +397,9 @@ def tune(self, job_name, strategy, objective_type, objective_metric_name,
https://docs.aws.amazon.com/sagemaker/latest/dg/API_Tag.html.
warm_start_config (dict): Configuration defining the type of warm start and
other required configurations.
early_stopping_type (str): Specifies whether early stopping is enabled for the job.
Can be either 'Auto' or 'Off'. If set to 'Off', early stopping will not be attempted.
If set to 'Auto', early stopping of some training jobs may happen, but is not guaranteed to.
"""
tune_request = {
'HyperParameterTuningJobName': job_name,
Expand All@@ -410,6 +414,7 @@ def tune(self, job_name, strategy, objective_type, objective_metric_name,
'MaxParallelTrainingJobs': max_parallel_jobs,
},
'ParameterRanges': parameter_ranges,
'TrainingJobEarlyStoppingType': early_stopping_type,
},
'TrainingJobDefinition': {
'StaticHyperParameters': static_hyperparameters,
Expand Down
10 changes: 8 additions & 2 deletions src/sagemaker/tuner.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -165,7 +165,7 @@ class HyperparameterTuner(object):

def __init__(self, estimator, objective_metric_name, hyperparameter_ranges, metric_definitions=None,
strategy='Bayesian', objective_type='Maximize', max_jobs=1, max_parallel_jobs=1,
tags=None, base_tuning_job_name=None, warm_start_config=None):
tags=None, base_tuning_job_name=None, warm_start_config=None, early_stopping_type='Off'):
"""Initialize a ``HyperparameterTuner``. It takes an estimator to obtain configuration information
for training jobs that are created as the result of a hyperparameter tuning job.

Expand DownExpand Up@@ -194,6 +194,9 @@ def __init__(self, estimator, objective_metric_name, hyperparameter_ranges, metr
a default job name is generated, based on the training image name and current timestamp.
warm_start_config (sagemaker.tuner.WarmStartConfig): A ``WarmStartConfig`` object that has been initialized
with the configuration defining the nature of warm start tuning job.
early_stopping_type (str): Specifies whether early stopping is enabled for the job.
Can be either 'Auto' or 'Off' (default: 'Off'). If set to 'Off', early stopping will not be attempted.
If set to 'Auto', early stopping of some training jobs may happen, but is not guaranteed to.
"""
self._hyperparameter_ranges = hyperparameter_ranges
if self._hyperparameter_ranges is None or len(self._hyperparameter_ranges) == 0:
Expand All@@ -214,6 +217,7 @@ def __init__(self, estimator, objective_metric_name, hyperparameter_ranges, metr
self._current_job_name = None
self.latest_tuning_job = None
self.warm_start_config = warm_start_config
self.early_stopping_type = early_stopping_type

def _prepare_for_training(self, job_name=None, include_cls_metadata=True):
if job_name is not None:
Expand DownExpand Up@@ -445,7 +449,8 @@ def _prepare_init_params_from_job_description(cls, job_details):
'strategy': tuning_config['Strategy'],
'max_jobs': tuning_config['ResourceLimits']['MaxNumberOfTrainingJobs'],
'max_parallel_jobs': tuning_config['ResourceLimits']['MaxParallelTrainingJobs'],
'warm_start_config': WarmStartConfig.from_job_desc(job_details.get('WarmStartConfig', None))
'warm_start_config': WarmStartConfig.from_job_desc(job_details.get('WarmStartConfig', None)),
'early_stopping_type': tuning_config['TrainingJobEarlyStoppingType']
}

@classmethod
Expand DownExpand Up@@ -625,6 +630,7 @@ def start_new(cls, tuner, inputs):
tuner_args['metric_definitions'] = tuner.metric_definitions
tuner_args['tags'] = tuner.tags
tuner_args['warm_start_config'] = warm_start_config_req
tuner_args['early_stopping_type'] = tuner.early_stopping_type

del tuner_args['vpc_config']
if isinstance(tuner.estimator, sagemaker.algorithm.AlgorithmEstimator):
Expand Down
30 changes: 21 additions & 9 deletions tests/integ/test_tuner.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -83,15 +83,16 @@ def hyperparameter_ranges():

def _tune_and_deploy(kmeans_estimator, kmeans_train_set, sagemaker_session,
hyperparameter_ranges=None, job_name=None,
warm_start_config=None):
warm_start_config=None, early_stopping_type='Off'):
tuner = _tune(kmeans_estimator, kmeans_train_set,
hyperparameter_ranges=hyperparameter_ranges, warm_start_config=warm_start_config,
job_name=job_name)
_deploy(kmeans_train_set, sagemaker_session, tuner)
job_name=job_name, early_stopping_type=early_stopping_type)
_deploy(kmeans_train_set, sagemaker_session, tuner, early_stopping_type)


def _deploy(kmeans_train_set, sagemaker_session, tuner):
def _deploy(kmeans_train_set, sagemaker_session, tuner, early_stopping_type):
best_training_job = tuner.best_training_job()
assert tuner.early_stopping_type == early_stopping_type
with timeout_and_delete_endpoint_by_name(best_training_job, sagemaker_session):
predictor = tuner.deploy(1, 'ml.c4.xlarge')

Expand All@@ -105,7 +106,7 @@ def _deploy(kmeans_train_set, sagemaker_session, tuner):

def _tune(kmeans_estimator, kmeans_train_set, tuner=None,
hyperparameter_ranges=None, job_name=None, warm_start_config=None,
wait_till_terminal=True, max_jobs=2, max_parallel_jobs=2):
wait_till_terminal=True, max_jobs=2, max_parallel_jobs=2, early_stopping_type='Off'):
with timeout(minutes=TUNING_DEFAULT_TIMEOUT_MINUTES):

if not tuner:
Expand All@@ -115,7 +116,8 @@ def _tune(kmeans_estimator, kmeans_train_set, tuner=None,
objective_type='Minimize',
max_jobs=max_jobs,
max_parallel_jobs=max_parallel_jobs,
warm_start_config=warm_start_config)
warm_start_config=warm_start_config,
early_stopping_type=early_stopping_type)

records = kmeans_estimator.record_set(kmeans_train_set[0][:100])
test_record_set = kmeans_estimator.record_set(kmeans_train_set[0][:100], channel='test')
Expand DownExpand Up@@ -332,16 +334,23 @@ def test_tuning_lda(sagemaker_session):
tuner = HyperparameterTuner(estimator=lda, objective_metric_name=objective_metric_name,
hyperparameter_ranges=hyperparameter_ranges,
objective_type='Maximize', max_jobs=2,
max_parallel_jobs=2)
max_parallel_jobs=2,
early_stopping_type='Auto')

tuning_job_name = unique_name_from_base('test-lda', max_length=32)
tuner.fit([record_set, test_record_set], mini_batch_size=1, job_name=tuning_job_name)

print('Started hyperparameter tuning job with name:' + tuner.latest_tuning_job.name)
latest_tuning_job_name = tuner.latest_tuning_job.name

print('Started hyperparameter tuning job with name:' + latest_tuning_job_name)

time.sleep(15)
tuner.wait()

desc = tuner.latest_tuning_job.sagemaker_session.sagemaker_client \
.describe_hyper_parameter_tuning_job(HyperParameterTuningJobName=latest_tuning_job_name)
assert desc['HyperParameterTuningJobConfig']['TrainingJobEarlyStoppingType'] == 'Auto'

best_training_job = tuner.best_training_job()
with timeout_and_delete_endpoint_by_name(best_training_job, sagemaker_session):
predictor = tuner.deploy(1, 'ml.c4.xlarge')
Expand DownExpand Up@@ -555,7 +564,8 @@ def test_attach_tuning_pytorch(sagemaker_session):

tuner = HyperparameterTuner(estimator, objective_metric_name, hyperparameter_ranges,
metric_definitions,
max_jobs=2, max_parallel_jobs=2)
max_jobs=2, max_parallel_jobs=2,
early_stopping_type='Auto')

training_data = estimator.sagemaker_session.upload_data(
path=os.path.join(mnist_dir, 'training'),
Expand All@@ -571,6 +581,8 @@ def test_attach_tuning_pytorch(sagemaker_session):

attached_tuner = HyperparameterTuner.attach(tuning_job_name,
sagemaker_session=sagemaker_session)
assert attached_tuner.early_stopping_type == 'Auto'

best_training_job = tuner.best_training_job()
with timeout_and_delete_endpoint_by_name(best_training_job, sagemaker_session):
predictor = attached_tuner.deploy(1, 'ml.c4.xlarge')
Expand Down
1 change: 1 addition & 0 deletions tests/unit/test_session.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -301,6 +301,7 @@ def test_train_pack_to_request(sagemaker_session):
'MaxParallelTrainingJobs': 5,
},
'ParameterRanges': SAMPLE_PARAM_RANGES,
'TrainingJobEarlyStoppingType': 'Off'
},
'TrainingJobDefinition': {
'StaticHyperParameters': STATIC_HPs,
Expand Down
34 changes: 33 additions & 1 deletion tests/unit/test_tuner.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -74,7 +74,8 @@
'MinValue': '10',
},
]
}
},
'TrainingJobEarlyStoppingType': 'Off'
},
'HyperParameterTuningJobName': JOB_NAME,
'TrainingJobDefinition': {
Expand DownExpand Up@@ -241,9 +242,26 @@ def test_fit_pca(sagemaker_session, tuner):
assert len(tune_kwargs['parameter_ranges']['IntegerParameterRanges']) == 1
assert tune_kwargs['job_name'].startswith('pca')
assert tune_kwargs['tags'] == tags
assert tune_kwargs['early_stopping_type'] == 'Off'
assert tuner.estimator.mini_batch_size == 9999


def test_fit_pca_with_early_stopping(sagemaker_session, tuner):
pca = PCA(ROLE, TRAIN_INSTANCE_COUNT, TRAIN_INSTANCE_TYPE, NUM_COMPONENTS,
base_job_name='pca', sagemaker_session=sagemaker_session)

tuner.estimator = pca
tuner.early_stopping_type = 'Auto'

records = RecordSet(s3_data=INPUTS, num_records=1, feature_dim=1)
tuner.fit(records, mini_batch_size=9999)

_, _, tune_kwargs = sagemaker_session.tune.mock_calls[0]

assert tune_kwargs['job_name'].startswith('pca')
assert tune_kwargs['early_stopping_type'] == 'Auto'


def test_attach_tuning_job_with_estimator_from_hyperparameters(sagemaker_session):
job_details = copy.deepcopy(TUNING_JOB_DETAILS)
sagemaker_session.sagemaker_client.describe_hyper_parameter_tuning_job = Mock(name='describe_tuning_job',
Expand All@@ -257,6 +275,7 @@ def test_attach_tuning_job_with_estimator_from_hyperparameters(sagemaker_session
assert tuner.metric_definitions == METRIC_DEFINTIONS
assert tuner.strategy == 'Bayesian'
assert tuner.objective_type == 'Minimize'
assert tuner.early_stopping_type == 'Off'

assert isinstance(tuner.estimator, PCA)
assert tuner.estimator.role == ROLE
Expand All@@ -270,6 +289,19 @@ def test_attach_tuning_job_with_estimator_from_hyperparameters(sagemaker_session
assert tuner.estimator.hyperparameters()['num_components'] == '1'


def test_attach_tuning_job_with_estimator_from_hyperparameters_with_early_stopping(sagemaker_session):
job_details = copy.deepcopy(TUNING_JOB_DETAILS)
job_details['HyperParameterTuningJobConfig']['TrainingJobEarlyStoppingType'] = 'Auto'
sagemaker_session.sagemaker_client.describe_hyper_parameter_tuning_job = Mock(name='describe_tuning_job',
return_value=job_details)
tuner = HyperparameterTuner.attach(JOB_NAME, sagemaker_session=sagemaker_session)

assert tuner.latest_tuning_job.name == JOB_NAME
assert tuner.early_stopping_type == 'Auto'

assert isinstance(tuner.estimator, PCA)


def test_attach_tuning_job_with_job_details(sagemaker_session):
job_details = copy.deepcopy(TUNING_JOB_DETAILS)
HyperparameterTuner.attach(JOB_NAME, sagemaker_session=sagemaker_session, job_details=job_details)
Expand Down
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Add copy buttons to all 
 blocks\n(function() {\n function addCopyButtons() {\n document.querySelectorAll('pre code').forEach(function(codeBlock) {\n if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;\n codeBlock.parentElement.setAttribute('data-copy-added', 'true');\n \n var btn = document.createElement('button');\n btn.textContent = 'Copy';\n btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';\n btn.onmouseover = function() { this.style.opacity = '1'; };\n btn.onmouseout = function() { this.style.opacity = '0.7'; };\n btn.onclick = function() {\n navigator.clipboard.writeText(codeBlock.textContent).then(function() {\n btn.textContent = 'Copied!';\n setTimeout(function() { btn.textContent = 'Copy'; }, 1500);\n });\n };\n codeBlock.parentElement.style.position = 'relative';\n codeBlock.parentElement.appendChild(btn);\n });\n }\n \n addCopyButtons();\n \n // Re-run on dynamic content\n var observer = new MutationObserver(addCopyButtons);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Add Copy Buttons to Code Blocks");
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '

Skip to content
Add Early Stopping to SageMaker Python SDK#541

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Closed

cassiesu
wants to merge
2
commits into

from

 Closed


Add Early Stopping to SageMaker Python SDK
#541
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
b86a28a

Add Early Stopping to SageMaker Python SDK

Dec 7, 2018
e8ae70d

fix flake8 check failure

Dec 10, 2018

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


16 changes: 16 additions & 0 deletions
README.rst

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -596,6 +596,22 @@ A hyperparameter range can be one of three types: continuous, integer, or catego
The SageMaker Python SDK provides corresponding classes for defining these different types.
You can define up to 20 hyperparameters to search over, but each value of a categorical hyperparameter range counts against that limit.

By default, training job early stopping is turned off. To enable early stopping for the tuning job, you need to set the ``early_stopping_type`` parameter to ``Auto``:

.. code:: python

 # Enable early stopping
 my_tuner = HyperparameterTuner(estimator=my_estimator, # previously-configured Estimator object
 objective_metric_name='validation-accuracy',
 hyperparameter_ranges={'learning-rate': ContinuousParameter(0.05, 0.06)},
 metric_definitions=[{'Name': 'validation-accuracy', 'Regex': 'validation-accuracy=(\d\.\d+)'}],
 max_jobs=100,
 max_parallel_jobs=10,
 early_stopping_type='Auto')

When early stopping is turned on, Amazon SageMaker will automatically stop a training job if it appears unlikely to produce a model of better quality than other jobs.
If not using built-in Amazon SageMaker algorithms, note that, for early stopping to be effective, the objective metric should be emitted at epoch level.

If you are using an Amazon SageMaker built-in algorithm, you don't need to pass in anything for ``metric_definitions``.
In addition, the ``fit()`` call uses a list of ``RecordSet`` objects instead of a dictionary:

Expand Down

7 changes: 6 additions & 1 deletion
src/sagemaker/session.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -350,7 +350,8 @@ def tune(self, job_name, strategy, objective_type, objective_metric_name,
 max_jobs, max_parallel_jobs, parameter_ranges,
 static_hyperparameters, input_mode, metric_definitions,
 role, input_config, output_config, resource_config, stop_condition, tags,
 warm_start_config, enable_network_isolation=False, image=None, algorithm_arn=None):
 warm_start_config, enable_network_isolation=False, image=None, algorithm_arn=None,
 early_stopping_type='Off'):
 """Create an Amazon SageMaker hyperparameter tuning job

 Args:
Expand DownExpand Up@@ -396,6 +397,9 @@ def tune(self, job_name, strategy, objective_type, objective_metric_name,
 https://docs.aws.amazon.com/sagemaker/latest/dg/API_Tag.html.
 warm_start_config (dict): Configuration defining the type of warm start and
 other required configurations.
 early_stopping_type (str): Specifies whether early stopping is enabled for the job.
 Can be either 'Auto' or 'Off'. If set to 'Off', early stopping will not be attempted.
 If set to 'Auto', early stopping of some training jobs may happen, but is not guaranteed to.
 """
 tune_request = {
 'HyperParameterTuningJobName': job_name,
Expand All@@ -410,6 +414,7 @@ def tune(self, job_name, strategy, objective_type, objective_metric_name,
 'MaxParallelTrainingJobs': max_parallel_jobs,
 },
 'ParameterRanges': parameter_ranges,
 'TrainingJobEarlyStoppingType': early_stopping_type,
 },
 'TrainingJobDefinition': {
 'StaticHyperParameters': static_hyperparameters,
Expand Down

10 changes: 8 additions & 2 deletions
src/sagemaker/tuner.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -165,7 +165,7 @@ class HyperparameterTuner(object):

 def __init__(self, estimator, objective_metric_name, hyperparameter_ranges, metric_definitions=None,
 strategy='Bayesian', objective_type='Maximize', max_jobs=1, max_parallel_jobs=1,
 tags=None, base_tuning_job_name=None, warm_start_config=None):
 tags=None, base_tuning_job_name=None, warm_start_config=None, early_stopping_type='Off'):
 """Initialize a ``HyperparameterTuner``. It takes an estimator to obtain configuration information
 for training jobs that are created as the result of a hyperparameter tuning job.

Expand DownExpand Up@@ -194,6 +194,9 @@ def __init__(self, estimator, objective_metric_name, hyperparameter_ranges, metr
 a default job name is generated, based on the training image name and current timestamp.
 warm_start_config (sagemaker.tuner.WarmStartConfig): A ``WarmStartConfig`` object that has been initialized
 with the configuration defining the nature of warm start tuning job.
 early_stopping_type (str): Specifies whether early stopping is enabled for the job.
 Can be either 'Auto' or 'Off' (default: 'Off'). If set to 'Off', early stopping will not be attempted.
 If set to 'Auto', early stopping of some training jobs may happen, but is not guaranteed to.
 """
 self._hyperparameter_ranges = hyperparameter_ranges
 if self._hyperparameter_ranges is None or len(self._hyperparameter_ranges) == 0:
Expand All@@ -214,6 +217,7 @@ def __init__(self, estimator, objective_metric_name, hyperparameter_ranges, metr
 self._current_job_name = None
 self.latest_tuning_job = None
 self.warm_start_config = warm_start_config
 self.early_stopping_type = early_stopping_type

 def _prepare_for_training(self, job_name=None, include_cls_metadata=True):
 if job_name is not None:
Expand DownExpand Up@@ -445,7 +449,8 @@ def _prepare_init_params_from_job_description(cls, job_details):
 'strategy': tuning_config['Strategy'],
 'max_jobs': tuning_config['ResourceLimits']['MaxNumberOfTrainingJobs'],
 'max_parallel_jobs': tuning_config['ResourceLimits']['MaxParallelTrainingJobs'],
 'warm_start_config': WarmStartConfig.from_job_desc(job_details.get('WarmStartConfig', None))
 'warm_start_config': WarmStartConfig.from_job_desc(job_details.get('WarmStartConfig', None)),
 'early_stopping_type': tuning_config['TrainingJobEarlyStoppingType']
 }

 @classmethod
Expand DownExpand Up@@ -625,6 +630,7 @@ def start_new(cls, tuner, inputs):
 tuner_args['metric_definitions'] = tuner.metric_definitions
 tuner_args['tags'] = tuner.tags
 tuner_args['warm_start_config'] = warm_start_config_req
 tuner_args['early_stopping_type'] = tuner.early_stopping_type

 del tuner_args['vpc_config']
 if isinstance(tuner.estimator, sagemaker.algorithm.AlgorithmEstimator):
Expand Down

30 changes: 21 additions & 9 deletions
tests/integ/test_tuner.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -83,15 +83,16 @@ def hyperparameter_ranges():

def _tune_and_deploy(kmeans_estimator, kmeans_train_set, sagemaker_session,
 hyperparameter_ranges=None, job_name=None,
 warm_start_config=None):
 warm_start_config=None, early_stopping_type='Off'):
 tuner = _tune(kmeans_estimator, kmeans_train_set,
 hyperparameter_ranges=hyperparameter_ranges, warm_start_config=warm_start_config,
 job_name=job_name)
 _deploy(kmeans_train_set, sagemaker_session, tuner)
 job_name=job_name, early_stopping_type=early_stopping_type)
 _deploy(kmeans_train_set, sagemaker_session, tuner, early_stopping_type)


def _deploy(kmeans_train_set, sagemaker_session, tuner):
def _deploy(kmeans_train_set, sagemaker_session, tuner, early_stopping_type):
 best_training_job = tuner.best_training_job()
 assert tuner.early_stopping_type == early_stopping_type
 with timeout_and_delete_endpoint_by_name(best_training_job, sagemaker_session):
 predictor = tuner.deploy(1, 'ml.c4.xlarge')

Expand All@@ -105,7 +106,7 @@ def _deploy(kmeans_train_set, sagemaker_session, tuner):

def _tune(kmeans_estimator, kmeans_train_set, tuner=None,
 hyperparameter_ranges=None, job_name=None, warm_start_config=None,
 wait_till_terminal=True, max_jobs=2, max_parallel_jobs=2):
 wait_till_terminal=True, max_jobs=2, max_parallel_jobs=2, early_stopping_type='Off'):
 with timeout(minutes=TUNING_DEFAULT_TIMEOUT_MINUTES):

 if not tuner:
Expand All@@ -115,7 +116,8 @@ def _tune(kmeans_estimator, kmeans_train_set, tuner=None,
 objective_type='Minimize',
 max_jobs=max_jobs,
 max_parallel_jobs=max_parallel_jobs,
 warm_start_config=warm_start_config)
 warm_start_config=warm_start_config,
 early_stopping_type=early_stopping_type)

 records = kmeans_estimator.record_set(kmeans_train_set[0][:100])
 test_record_set = kmeans_estimator.record_set(kmeans_train_set[0][:100], channel='test')
Expand DownExpand Up@@ -332,16 +334,23 @@ def test_tuning_lda(sagemaker_session):
 tuner = HyperparameterTuner(estimator=lda, objective_metric_name=objective_metric_name,
 hyperparameter_ranges=hyperparameter_ranges,
 objective_type='Maximize', max_jobs=2,
 max_parallel_jobs=2)
 max_parallel_jobs=2,
 early_stopping_type='Auto')

 tuning_job_name = unique_name_from_base('test-lda', max_length=32)
 tuner.fit([record_set, test_record_set], mini_batch_size=1, job_name=tuning_job_name)

 print('Started hyperparameter tuning job with name:' + tuner.latest_tuning_job.name)
 latest_tuning_job_name = tuner.latest_tuning_job.name

 print('Started hyperparameter tuning job with name:' + latest_tuning_job_name)

 time.sleep(15)
 tuner.wait()

 desc = tuner.latest_tuning_job.sagemaker_session.sagemaker_client \
 .describe_hyper_parameter_tuning_job(HyperParameterTuningJobName=latest_tuning_job_name)
 assert desc['HyperParameterTuningJobConfig']['TrainingJobEarlyStoppingType'] == 'Auto'

 best_training_job = tuner.best_training_job()
 with timeout_and_delete_endpoint_by_name(best_training_job, sagemaker_session):
 predictor = tuner.deploy(1, 'ml.c4.xlarge')
Expand DownExpand Up@@ -555,7 +564,8 @@ def test_attach_tuning_pytorch(sagemaker_session):

 tuner = HyperparameterTuner(estimator, objective_metric_name, hyperparameter_ranges,
 metric_definitions,
 max_jobs=2, max_parallel_jobs=2)
 max_jobs=2, max_parallel_jobs=2,
 early_stopping_type='Auto')

 training_data = estimator.sagemaker_session.upload_data(
 path=os.path.join(mnist_dir, 'training'),
Expand All@@ -571,6 +581,8 @@ def test_attach_tuning_pytorch(sagemaker_session):

 attached_tuner = HyperparameterTuner.attach(tuning_job_name,
 sagemaker_session=sagemaker_session)
 assert attached_tuner.early_stopping_type == 'Auto'

 best_training_job = tuner.best_training_job()
 with timeout_and_delete_endpoint_by_name(best_training_job, sagemaker_session):
 predictor = attached_tuner.deploy(1, 'ml.c4.xlarge')
Expand Down

1 change: 1 addition & 0 deletions
tests/unit/test_session.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -301,6 +301,7 @@ def test_train_pack_to_request(sagemaker_session):
 'MaxParallelTrainingJobs': 5,
 },
 'ParameterRanges': SAMPLE_PARAM_RANGES,
 'TrainingJobEarlyStoppingType': 'Off'
 },
 'TrainingJobDefinition': {
 'StaticHyperParameters': STATIC_HPs,
Expand Down

34 changes: 33 additions & 1 deletion
tests/unit/test_tuner.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -74,7 +74,8 @@
 'MinValue': '10',
 },
 ]
 }
 },
 'TrainingJobEarlyStoppingType': 'Off'
 },
 'HyperParameterTuningJobName': JOB_NAME,
 'TrainingJobDefinition': {
Expand DownExpand Up@@ -241,9 +242,26 @@ def test_fit_pca(sagemaker_session, tuner):
 assert len(tune_kwargs['parameter_ranges']['IntegerParameterRanges']) == 1
 assert tune_kwargs['job_name'].startswith('pca')
 assert tune_kwargs['tags'] == tags
 assert tune_kwargs['early_stopping_type'] == 'Off'
 assert tuner.estimator.mini_batch_size == 9999


def test_fit_pca_with_early_stopping(sagemaker_session, tuner):
 pca = PCA(ROLE, TRAIN_INSTANCE_COUNT, TRAIN_INSTANCE_TYPE, NUM_COMPONENTS,
 base_job_name='pca', sagemaker_session=sagemaker_session)

 tuner.estimator = pca
 tuner.early_stopping_type = 'Auto'

 records = RecordSet(s3_data=INPUTS, num_records=1, feature_dim=1)
 tuner.fit(records, mini_batch_size=9999)

 _, _, tune_kwargs = sagemaker_session.tune.mock_calls[0]

 assert tune_kwargs['job_name'].startswith('pca')
 assert tune_kwargs['early_stopping_type'] == 'Auto'


def test_attach_tuning_job_with_estimator_from_hyperparameters(sagemaker_session):
 job_details = copy.deepcopy(TUNING_JOB_DETAILS)
 sagemaker_session.sagemaker_client.describe_hyper_parameter_tuning_job = Mock(name='describe_tuning_job',
Expand All@@ -257,6 +275,7 @@ def test_attach_tuning_job_with_estimator_from_hyperparameters(sagemaker_session
 assert tuner.metric_definitions == METRIC_DEFINTIONS
 assert tuner.strategy == 'Bayesian'
 assert tuner.objective_type == 'Minimize'
 assert tuner.early_stopping_type == 'Off'

 assert isinstance(tuner.estimator, PCA)
 assert tuner.estimator.role == ROLE
Expand All@@ -270,6 +289,19 @@ def test_attach_tuning_job_with_estimator_from_hyperparameters(sagemaker_session
 assert tuner.estimator.hyperparameters()['num_components'] == '1'


def test_attach_tuning_job_with_estimator_from_hyperparameters_with_early_stopping(sagemaker_session):
 job_details = copy.deepcopy(TUNING_JOB_DETAILS)
 job_details['HyperParameterTuningJobConfig']['TrainingJobEarlyStoppingType'] = 'Auto'
 sagemaker_session.sagemaker_client.describe_hyper_parameter_tuning_job = Mock(name='describe_tuning_job',
 return_value=job_details)
 tuner = HyperparameterTuner.attach(JOB_NAME, sagemaker_session=sagemaker_session)

 assert tuner.latest_tuning_job.name == JOB_NAME
 assert tuner.early_stopping_type == 'Auto'

 assert isinstance(tuner.estimator, PCA)


def test_attach_tuning_job_with_job_details(sagemaker_session):
 job_details = copy.deepcopy(TUNING_JOB_DETAILS)
 HyperparameterTuner.attach(JOB_NAME, sagemaker_session=sagemaker_session, job_details=job_details)
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Force GitHub README to respect dark mode\n(function() {\n var style = document.createElement('style');\n style.textContent = '\n .markdown-body {\n color-scheme: dark light;\n }\n .markdown-body pre { background: #161b22 !important; }\n .markdown-body code { background: rgba(110, 118, 129, 0.4) !important; }\n .markdown-body table th, .markdown-body table td { border-color: #30363d !important; }\n .markdown-body img { background: #0d1117; }\n .markdown-body blockquote { border-left-color: #8b949e; }\n .markdown-body hr { border-color: #30363d; }\n ';\n document.head.appendChild(style);\n})();", "GitHub Dark Mode README Fix");
}
} catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Add Early Stopping to SageMaker Python SDK#541

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Closed

cassiesu
wants to merge
2
commits into

from

 Closed


Add Early Stopping to SageMaker Python SDK
#541
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
b86a28a

Add Early Stopping to SageMaker Python SDK

Dec 7, 2018
e8ae70d

fix flake8 check failure

Dec 10, 2018

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


16 changes: 16 additions & 0 deletions
README.rst

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -596,6 +596,22 @@ A hyperparameter range can be one of three types: continuous, integer, or catego
The SageMaker Python SDK provides corresponding classes for defining these different types.
You can define up to 20 hyperparameters to search over, but each value of a categorical hyperparameter range counts against that limit.

By default, training job early stopping is turned off. To enable early stopping for the tuning job, you need to set the ``early_stopping_type`` parameter to ``Auto``:

.. code:: python

 # Enable early stopping
 my_tuner = HyperparameterTuner(estimator=my_estimator, # previously-configured Estimator object
 objective_metric_name='validation-accuracy',
 hyperparameter_ranges={'learning-rate': ContinuousParameter(0.05, 0.06)},
 metric_definitions=[{'Name': 'validation-accuracy', 'Regex': 'validation-accuracy=(\d\.\d+)'}],
 max_jobs=100,
 max_parallel_jobs=10,
 early_stopping_type='Auto')

When early stopping is turned on, Amazon SageMaker will automatically stop a training job if it appears unlikely to produce a model of better quality than other jobs.
If not using built-in Amazon SageMaker algorithms, note that, for early stopping to be effective, the objective metric should be emitted at epoch level.

If you are using an Amazon SageMaker built-in algorithm, you don't need to pass in anything for ``metric_definitions``.
In addition, the ``fit()`` call uses a list of ``RecordSet`` objects instead of a dictionary:

Expand Down

7 changes: 6 additions & 1 deletion
src/sagemaker/session.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -350,7 +350,8 @@ def tune(self, job_name, strategy, objective_type, objective_metric_name,
 max_jobs, max_parallel_jobs, parameter_ranges,
 static_hyperparameters, input_mode, metric_definitions,
 role, input_config, output_config, resource_config, stop_condition, tags,
 warm_start_config, enable_network_isolation=False, image=None, algorithm_arn=None):
 warm_start_config, enable_network_isolation=False, image=None, algorithm_arn=None,
 early_stopping_type='Off'):
 """Create an Amazon SageMaker hyperparameter tuning job

 Args:
Expand DownExpand Up@@ -396,6 +397,9 @@ def tune(self, job_name, strategy, objective_type, objective_metric_name,
 https://docs.aws.amazon.com/sagemaker/latest/dg/API_Tag.html.
 warm_start_config (dict): Configuration defining the type of warm start and
 other required configurations.
 early_stopping_type (str): Specifies whether early stopping is enabled for the job.
 Can be either 'Auto' or 'Off'. If set to 'Off', early stopping will not be attempted.
 If set to 'Auto', early stopping of some training jobs may happen, but is not guaranteed to.
 """
 tune_request = {
 'HyperParameterTuningJobName': job_name,
Expand All@@ -410,6 +414,7 @@ def tune(self, job_name, strategy, objective_type, objective_metric_name,
 'MaxParallelTrainingJobs': max_parallel_jobs,
 },
 'ParameterRanges': parameter_ranges,
 'TrainingJobEarlyStoppingType': early_stopping_type,
 },
 'TrainingJobDefinition': {
 'StaticHyperParameters': static_hyperparameters,
Expand Down

10 changes: 8 additions & 2 deletions
src/sagemaker/tuner.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -165,7 +165,7 @@ class HyperparameterTuner(object):

 def __init__(self, estimator, objective_metric_name, hyperparameter_ranges, metric_definitions=None,
 strategy='Bayesian', objective_type='Maximize', max_jobs=1, max_parallel_jobs=1,
 tags=None, base_tuning_job_name=None, warm_start_config=None):
 tags=None, base_tuning_job_name=None, warm_start_config=None, early_stopping_type='Off'):
 """Initialize a ``HyperparameterTuner``. It takes an estimator to obtain configuration information
 for training jobs that are created as the result of a hyperparameter tuning job.

Expand DownExpand Up@@ -194,6 +194,9 @@ def __init__(self, estimator, objective_metric_name, hyperparameter_ranges, metr
 a default job name is generated, based on the training image name and current timestamp.
 warm_start_config (sagemaker.tuner.WarmStartConfig): A ``WarmStartConfig`` object that has been initialized
 with the configuration defining the nature of warm start tuning job.
 early_stopping_type (str): Specifies whether early stopping is enabled for the job.
 Can be either 'Auto' or 'Off' (default: 'Off'). If set to 'Off', early stopping will not be attempted.
 If set to 'Auto', early stopping of some training jobs may happen, but is not guaranteed to.
 """
 self._hyperparameter_ranges = hyperparameter_ranges
 if self._hyperparameter_ranges is None or len(self._hyperparameter_ranges) == 0:
Expand All@@ -214,6 +217,7 @@ def __init__(self, estimator, objective_metric_name, hyperparameter_ranges, metr
 self._current_job_name = None
 self.latest_tuning_job = None
 self.warm_start_config = warm_start_config
 self.early_stopping_type = early_stopping_type

 def _prepare_for_training(self, job_name=None, include_cls_metadata=True):
 if job_name is not None:
Expand DownExpand Up@@ -445,7 +449,8 @@ def _prepare_init_params_from_job_description(cls, job_details):
 'strategy': tuning_config['Strategy'],
 'max_jobs': tuning_config['ResourceLimits']['MaxNumberOfTrainingJobs'],
 'max_parallel_jobs': tuning_config['ResourceLimits']['MaxParallelTrainingJobs'],
 'warm_start_config': WarmStartConfig.from_job_desc(job_details.get('WarmStartConfig', None))
 'warm_start_config': WarmStartConfig.from_job_desc(job_details.get('WarmStartConfig', None)),
 'early_stopping_type': tuning_config['TrainingJobEarlyStoppingType']
 }

 @classmethod
Expand DownExpand Up@@ -625,6 +630,7 @@ def start_new(cls, tuner, inputs):
 tuner_args['metric_definitions'] = tuner.metric_definitions
 tuner_args['tags'] = tuner.tags
 tuner_args['warm_start_config'] = warm_start_config_req
 tuner_args['early_stopping_type'] = tuner.early_stopping_type

 del tuner_args['vpc_config']
 if isinstance(tuner.estimator, sagemaker.algorithm.AlgorithmEstimator):
Expand Down

30 changes: 21 additions & 9 deletions
tests/integ/test_tuner.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -83,15 +83,16 @@ def hyperparameter_ranges():

def _tune_and_deploy(kmeans_estimator, kmeans_train_set, sagemaker_session,
 hyperparameter_ranges=None, job_name=None,
 warm_start_config=None):
 warm_start_config=None, early_stopping_type='Off'):
 tuner = _tune(kmeans_estimator, kmeans_train_set,
 hyperparameter_ranges=hyperparameter_ranges, warm_start_config=warm_start_config,
 job_name=job_name)
 _deploy(kmeans_train_set, sagemaker_session, tuner)
 job_name=job_name, early_stopping_type=early_stopping_type)
 _deploy(kmeans_train_set, sagemaker_session, tuner, early_stopping_type)


def _deploy(kmeans_train_set, sagemaker_session, tuner):
def _deploy(kmeans_train_set, sagemaker_session, tuner, early_stopping_type):
 best_training_job = tuner.best_training_job()
 assert tuner.early_stopping_type == early_stopping_type
 with timeout_and_delete_endpoint_by_name(best_training_job, sagemaker_session):
 predictor = tuner.deploy(1, 'ml.c4.xlarge')

Expand All@@ -105,7 +106,7 @@ def _deploy(kmeans_train_set, sagemaker_session, tuner):

def _tune(kmeans_estimator, kmeans_train_set, tuner=None,
 hyperparameter_ranges=None, job_name=None, warm_start_config=None,
 wait_till_terminal=True, max_jobs=2, max_parallel_jobs=2):
 wait_till_terminal=True, max_jobs=2, max_parallel_jobs=2, early_stopping_type='Off'):
 with timeout(minutes=TUNING_DEFAULT_TIMEOUT_MINUTES):

 if not tuner:
Expand All@@ -115,7 +116,8 @@ def _tune(kmeans_estimator, kmeans_train_set, tuner=None,
 objective_type='Minimize',
 max_jobs=max_jobs,
 max_parallel_jobs=max_parallel_jobs,
 warm_start_config=warm_start_config)
 warm_start_config=warm_start_config,
 early_stopping_type=early_stopping_type)

 records = kmeans_estimator.record_set(kmeans_train_set[0][:100])
 test_record_set = kmeans_estimator.record_set(kmeans_train_set[0][:100], channel='test')
Expand DownExpand Up@@ -332,16 +334,23 @@ def test_tuning_lda(sagemaker_session):
 tuner = HyperparameterTuner(estimator=lda, objective_metric_name=objective_metric_name,
 hyperparameter_ranges=hyperparameter_ranges,
 objective_type='Maximize', max_jobs=2,
 max_parallel_jobs=2)
 max_parallel_jobs=2,
 early_stopping_type='Auto')

 tuning_job_name = unique_name_from_base('test-lda', max_length=32)
 tuner.fit([record_set, test_record_set], mini_batch_size=1, job_name=tuning_job_name)

 print('Started hyperparameter tuning job with name:' + tuner.latest_tuning_job.name)
 latest_tuning_job_name = tuner.latest_tuning_job.name

 print('Started hyperparameter tuning job with name:' + latest_tuning_job_name)

 time.sleep(15)
 tuner.wait()

 desc = tuner.latest_tuning_job.sagemaker_session.sagemaker_client \
 .describe_hyper_parameter_tuning_job(HyperParameterTuningJobName=latest_tuning_job_name)
 assert desc['HyperParameterTuningJobConfig']['TrainingJobEarlyStoppingType'] == 'Auto'

 best_training_job = tuner.best_training_job()
 with timeout_and_delete_endpoint_by_name(best_training_job, sagemaker_session):
 predictor = tuner.deploy(1, 'ml.c4.xlarge')
Expand DownExpand Up@@ -555,7 +564,8 @@ def test_attach_tuning_pytorch(sagemaker_session):

 tuner = HyperparameterTuner(estimator, objective_metric_name, hyperparameter_ranges,
 metric_definitions,
 max_jobs=2, max_parallel_jobs=2)
 max_jobs=2, max_parallel_jobs=2,
 early_stopping_type='Auto')

 training_data = estimator.sagemaker_session.upload_data(
 path=os.path.join(mnist_dir, 'training'),
Expand All@@ -571,6 +581,8 @@ def test_attach_tuning_pytorch(sagemaker_session):

 attached_tuner = HyperparameterTuner.attach(tuning_job_name,
 sagemaker_session=sagemaker_session)
 assert attached_tuner.early_stopping_type == 'Auto'

 best_training_job = tuner.best_training_job()
 with timeout_and_delete_endpoint_by_name(best_training_job, sagemaker_session):
 predictor = attached_tuner.deploy(1, 'ml.c4.xlarge')
Expand Down

1 change: 1 addition & 0 deletions
tests/unit/test_session.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -301,6 +301,7 @@ def test_train_pack_to_request(sagemaker_session):
 'MaxParallelTrainingJobs': 5,
 },
 'ParameterRanges': SAMPLE_PARAM_RANGES,
 'TrainingJobEarlyStoppingType': 'Off'
 },
 'TrainingJobDefinition': {
 'StaticHyperParameters': STATIC_HPs,
Expand Down

34 changes: 33 additions & 1 deletion
tests/unit/test_tuner.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -74,7 +74,8 @@
 'MinValue': '10',
 },
 ]
 }
 },
 'TrainingJobEarlyStoppingType': 'Off'
 },
 'HyperParameterTuningJobName': JOB_NAME,
 'TrainingJobDefinition': {
Expand DownExpand Up@@ -241,9 +242,26 @@ def test_fit_pca(sagemaker_session, tuner):
 assert len(tune_kwargs['parameter_ranges']['IntegerParameterRanges']) == 1
 assert tune_kwargs['job_name'].startswith('pca')
 assert tune_kwargs['tags'] == tags
 assert tune_kwargs['early_stopping_type'] == 'Off'
 assert tuner.estimator.mini_batch_size == 9999


def test_fit_pca_with_early_stopping(sagemaker_session, tuner):
 pca = PCA(ROLE, TRAIN_INSTANCE_COUNT, TRAIN_INSTANCE_TYPE, NUM_COMPONENTS,
 base_job_name='pca', sagemaker_session=sagemaker_session)

 tuner.estimator = pca
 tuner.early_stopping_type = 'Auto'

 records = RecordSet(s3_data=INPUTS, num_records=1, feature_dim=1)
 tuner.fit(records, mini_batch_size=9999)

 _, _, tune_kwargs = sagemaker_session.tune.mock_calls[0]

 assert tune_kwargs['job_name'].startswith('pca')
 assert tune_kwargs['early_stopping_type'] == 'Auto'


def test_attach_tuning_job_with_estimator_from_hyperparameters(sagemaker_session):
 job_details = copy.deepcopy(TUNING_JOB_DETAILS)
 sagemaker_session.sagemaker_client.describe_hyper_parameter_tuning_job = Mock(name='describe_tuning_job',
Expand All@@ -257,6 +275,7 @@ def test_attach_tuning_job_with_estimator_from_hyperparameters(sagemaker_session
 assert tuner.metric_definitions == METRIC_DEFINTIONS
 assert tuner.strategy == 'Bayesian'
 assert tuner.objective_type == 'Minimize'
 assert tuner.early_stopping_type == 'Off'

 assert isinstance(tuner.estimator, PCA)
 assert tuner.estimator.role == ROLE
Expand All@@ -270,6 +289,19 @@ def test_attach_tuning_job_with_estimator_from_hyperparameters(sagemaker_session
 assert tuner.estimator.hyperparameters()['num_components'] == '1'


def test_attach_tuning_job_with_estimator_from_hyperparameters_with_early_stopping(sagemaker_session):
 job_details = copy.deepcopy(TUNING_JOB_DETAILS)
 job_details['HyperParameterTuningJobConfig']['TrainingJobEarlyStoppingType'] = 'Auto'
 sagemaker_session.sagemaker_client.describe_hyper_parameter_tuning_job = Mock(name='describe_tuning_job',
 return_value=job_details)
 tuner = HyperparameterTuner.attach(JOB_NAME, sagemaker_session=sagemaker_session)

 assert tuner.latest_tuning_job.name == JOB_NAME
 assert tuner.early_stopping_type == 'Auto'

 assert isinstance(tuner.estimator, PCA)


def test_attach_tuning_job_with_job_details(sagemaker_session):
 job_details = copy.deepcopy(TUNING_JOB_DETAILS)
 HyperparameterTuner.attach(JOB_NAME, sagemaker_session=sagemaker_session, job_details=job_details)
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Highlight search terms from Google/DuckDuckGo/Bing referrer\n(function() {\n var ref = document.referrer;\n var terms = [];\n \n if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) {\n var url = new URL(ref);\n var q = url.searchParams.get('q') || url.searchParams.get('p');\n if (q) {\n terms = q.split(/\\s+/).filter(function(t) { return t.length > 2; });\n }\n }\n \n if (terms.length === 0) return;\n \n var style = document.createElement('style');\n style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }';\n document.head.appendChild(style);\n \n function highlight(node) {\n if (node.nodeType === 3) { // text node\n var text = node.textContent;\n var found = false;\n terms.forEach(function(term) {\n var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\\]\\\\]/g, '\\\\') + ')', 'gi');\n if (regex.test(text)) {\n found = true;\n var frag = document.createDocumentFragment();\n var parts = text.split(regex);\n parts.forEach(function(part, i) {\n if (i % 2 === 0) {\n frag.appendChild(document.createTextNode(part));\n } else {\n var span = document.createElement('span');\n span.className = 'userscript-highlight';\n span.textContent = part;\n frag.appendChild(span);\n }\n });\n node.parentNode.replaceChild(frag, node);\n }\n });\n } else if (node.nodeType === 1 && node.childNodes) { // element\n var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT'];\n if (!skipTags.includes(node.tagName)) {\n Array.from(node.childNodes).forEach(highlight);\n }\n }\n }\n \n highlight(document.body);\n \n // Re-highlight on dynamic content\n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1 || node.nodeType === 3) highlight(node);\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Highlight Search Terms");
}
} catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Add Early Stopping to SageMaker Python SDK#541

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Closed

cassiesu
wants to merge
2
commits into

from

 Closed


Add Early Stopping to SageMaker Python SDK
#541
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
b86a28a

Add Early Stopping to SageMaker Python SDK

Dec 7, 2018
e8ae70d

fix flake8 check failure

Dec 10, 2018

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


16 changes: 16 additions & 0 deletions
README.rst

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -596,6 +596,22 @@ A hyperparameter range can be one of three types: continuous, integer, or catego
The SageMaker Python SDK provides corresponding classes for defining these different types.
You can define up to 20 hyperparameters to search over, but each value of a categorical hyperparameter range counts against that limit.

By default, training job early stopping is turned off. To enable early stopping for the tuning job, you need to set the ``early_stopping_type`` parameter to ``Auto``:

.. code:: python

 # Enable early stopping
 my_tuner = HyperparameterTuner(estimator=my_estimator, # previously-configured Estimator object
 objective_metric_name='validation-accuracy',
 hyperparameter_ranges={'learning-rate': ContinuousParameter(0.05, 0.06)},
 metric_definitions=[{'Name': 'validation-accuracy', 'Regex': 'validation-accuracy=(\d\.\d+)'}],
 max_jobs=100,
 max_parallel_jobs=10,
 early_stopping_type='Auto')

When early stopping is turned on, Amazon SageMaker will automatically stop a training job if it appears unlikely to produce a model of better quality than other jobs.
If not using built-in Amazon SageMaker algorithms, note that, for early stopping to be effective, the objective metric should be emitted at epoch level.

If you are using an Amazon SageMaker built-in algorithm, you don't need to pass in anything for ``metric_definitions``.
In addition, the ``fit()`` call uses a list of ``RecordSet`` objects instead of a dictionary:

Expand Down

7 changes: 6 additions & 1 deletion
src/sagemaker/session.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -350,7 +350,8 @@ def tune(self, job_name, strategy, objective_type, objective_metric_name,
 max_jobs, max_parallel_jobs, parameter_ranges,
 static_hyperparameters, input_mode, metric_definitions,
 role, input_config, output_config, resource_config, stop_condition, tags,
 warm_start_config, enable_network_isolation=False, image=None, algorithm_arn=None):
 warm_start_config, enable_network_isolation=False, image=None, algorithm_arn=None,
 early_stopping_type='Off'):
 """Create an Amazon SageMaker hyperparameter tuning job

 Args:
Expand DownExpand Up@@ -396,6 +397,9 @@ def tune(self, job_name, strategy, objective_type, objective_metric_name,
 https://docs.aws.amazon.com/sagemaker/latest/dg/API_Tag.html.
 warm_start_config (dict): Configuration defining the type of warm start and
 other required configurations.
 early_stopping_type (str): Specifies whether early stopping is enabled for the job.
 Can be either 'Auto' or 'Off'. If set to 'Off', early stopping will not be attempted.
 If set to 'Auto', early stopping of some training jobs may happen, but is not guaranteed to.
 """
 tune_request = {
 'HyperParameterTuningJobName': job_name,
Expand All@@ -410,6 +414,7 @@ def tune(self, job_name, strategy, objective_type, objective_metric_name,
 'MaxParallelTrainingJobs': max_parallel_jobs,
 },
 'ParameterRanges': parameter_ranges,
 'TrainingJobEarlyStoppingType': early_stopping_type,
 },
 'TrainingJobDefinition': {
 'StaticHyperParameters': static_hyperparameters,
Expand Down

10 changes: 8 additions & 2 deletions
src/sagemaker/tuner.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -165,7 +165,7 @@ class HyperparameterTuner(object):

 def __init__(self, estimator, objective_metric_name, hyperparameter_ranges, metric_definitions=None,
 strategy='Bayesian', objective_type='Maximize', max_jobs=1, max_parallel_jobs=1,
 tags=None, base_tuning_job_name=None, warm_start_config=None):
 tags=None, base_tuning_job_name=None, warm_start_config=None, early_stopping_type='Off'):
 """Initialize a ``HyperparameterTuner``. It takes an estimator to obtain configuration information
 for training jobs that are created as the result of a hyperparameter tuning job.

Expand DownExpand Up@@ -194,6 +194,9 @@ def __init__(self, estimator, objective_metric_name, hyperparameter_ranges, metr
 a default job name is generated, based on the training image name and current timestamp.
 warm_start_config (sagemaker.tuner.WarmStartConfig): A ``WarmStartConfig`` object that has been initialized
 with the configuration defining the nature of warm start tuning job.
 early_stopping_type (str): Specifies whether early stopping is enabled for the job.
 Can be either 'Auto' or 'Off' (default: 'Off'). If set to 'Off', early stopping will not be attempted.
 If set to 'Auto', early stopping of some training jobs may happen, but is not guaranteed to.
 """
 self._hyperparameter_ranges = hyperparameter_ranges
 if self._hyperparameter_ranges is None or len(self._hyperparameter_ranges) == 0:
Expand All@@ -214,6 +217,7 @@ def __init__(self, estimator, objective_metric_name, hyperparameter_ranges, metr
 self._current_job_name = None
 self.latest_tuning_job = None
 self.warm_start_config = warm_start_config
 self.early_stopping_type = early_stopping_type

 def _prepare_for_training(self, job_name=None, include_cls_metadata=True):
 if job_name is not None:
Expand DownExpand Up@@ -445,7 +449,8 @@ def _prepare_init_params_from_job_description(cls, job_details):
 'strategy': tuning_config['Strategy'],
 'max_jobs': tuning_config['ResourceLimits']['MaxNumberOfTrainingJobs'],
 'max_parallel_jobs': tuning_config['ResourceLimits']['MaxParallelTrainingJobs'],
 'warm_start_config': WarmStartConfig.from_job_desc(job_details.get('WarmStartConfig', None))
 'warm_start_config': WarmStartConfig.from_job_desc(job_details.get('WarmStartConfig', None)),
 'early_stopping_type': tuning_config['TrainingJobEarlyStoppingType']
 }

 @classmethod
Expand DownExpand Up@@ -625,6 +630,7 @@ def start_new(cls, tuner, inputs):
 tuner_args['metric_definitions'] = tuner.metric_definitions
 tuner_args['tags'] = tuner.tags
 tuner_args['warm_start_config'] = warm_start_config_req
 tuner_args['early_stopping_type'] = tuner.early_stopping_type

 del tuner_args['vpc_config']
 if isinstance(tuner.estimator, sagemaker.algorithm.AlgorithmEstimator):
Expand Down

30 changes: 21 additions & 9 deletions
tests/integ/test_tuner.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -83,15 +83,16 @@ def hyperparameter_ranges():

def _tune_and_deploy(kmeans_estimator, kmeans_train_set, sagemaker_session,
 hyperparameter_ranges=None, job_name=None,
 warm_start_config=None):
 warm_start_config=None, early_stopping_type='Off'):
 tuner = _tune(kmeans_estimator, kmeans_train_set,
 hyperparameter_ranges=hyperparameter_ranges, warm_start_config=warm_start_config,
 job_name=job_name)
 _deploy(kmeans_train_set, sagemaker_session, tuner)
 job_name=job_name, early_stopping_type=early_stopping_type)
 _deploy(kmeans_train_set, sagemaker_session, tuner, early_stopping_type)


def _deploy(kmeans_train_set, sagemaker_session, tuner):
def _deploy(kmeans_train_set, sagemaker_session, tuner, early_stopping_type):
 best_training_job = tuner.best_training_job()
 assert tuner.early_stopping_type == early_stopping_type
 with timeout_and_delete_endpoint_by_name(best_training_job, sagemaker_session):
 predictor = tuner.deploy(1, 'ml.c4.xlarge')

Expand All@@ -105,7 +106,7 @@ def _deploy(kmeans_train_set, sagemaker_session, tuner):

def _tune(kmeans_estimator, kmeans_train_set, tuner=None,
 hyperparameter_ranges=None, job_name=None, warm_start_config=None,
 wait_till_terminal=True, max_jobs=2, max_parallel_jobs=2):
 wait_till_terminal=True, max_jobs=2, max_parallel_jobs=2, early_stopping_type='Off'):
 with timeout(minutes=TUNING_DEFAULT_TIMEOUT_MINUTES):

 if not tuner:
Expand All@@ -115,7 +116,8 @@ def _tune(kmeans_estimator, kmeans_train_set, tuner=None,
 objective_type='Minimize',
 max_jobs=max_jobs,
 max_parallel_jobs=max_parallel_jobs,
 warm_start_config=warm_start_config)
 warm_start_config=warm_start_config,
 early_stopping_type=early_stopping_type)

 records = kmeans_estimator.record_set(kmeans_train_set[0][:100])
 test_record_set = kmeans_estimator.record_set(kmeans_train_set[0][:100], channel='test')
Expand DownExpand Up@@ -332,16 +334,23 @@ def test_tuning_lda(sagemaker_session):
 tuner = HyperparameterTuner(estimator=lda, objective_metric_name=objective_metric_name,
 hyperparameter_ranges=hyperparameter_ranges,
 objective_type='Maximize', max_jobs=2,
 max_parallel_jobs=2)
 max_parallel_jobs=2,
 early_stopping_type='Auto')

 tuning_job_name = unique_name_from_base('test-lda', max_length=32)
 tuner.fit([record_set, test_record_set], mini_batch_size=1, job_name=tuning_job_name)

 print('Started hyperparameter tuning job with name:' + tuner.latest_tuning_job.name)
 latest_tuning_job_name = tuner.latest_tuning_job.name

 print('Started hyperparameter tuning job with name:' + latest_tuning_job_name)

 time.sleep(15)
 tuner.wait()

 desc = tuner.latest_tuning_job.sagemaker_session.sagemaker_client \
 .describe_hyper_parameter_tuning_job(HyperParameterTuningJobName=latest_tuning_job_name)
 assert desc['HyperParameterTuningJobConfig']['TrainingJobEarlyStoppingType'] == 'Auto'

 best_training_job = tuner.best_training_job()
 with timeout_and_delete_endpoint_by_name(best_training_job, sagemaker_session):
 predictor = tuner.deploy(1, 'ml.c4.xlarge')
Expand DownExpand Up@@ -555,7 +564,8 @@ def test_attach_tuning_pytorch(sagemaker_session):

 tuner = HyperparameterTuner(estimator, objective_metric_name, hyperparameter_ranges,
 metric_definitions,
 max_jobs=2, max_parallel_jobs=2)
 max_jobs=2, max_parallel_jobs=2,
 early_stopping_type='Auto')

 training_data = estimator.sagemaker_session.upload_data(
 path=os.path.join(mnist_dir, 'training'),
Expand All@@ -571,6 +581,8 @@ def test_attach_tuning_pytorch(sagemaker_session):

 attached_tuner = HyperparameterTuner.attach(tuning_job_name,
 sagemaker_session=sagemaker_session)
 assert attached_tuner.early_stopping_type == 'Auto'

 best_training_job = tuner.best_training_job()
 with timeout_and_delete_endpoint_by_name(best_training_job, sagemaker_session):
 predictor = attached_tuner.deploy(1, 'ml.c4.xlarge')
Expand Down

1 change: 1 addition & 0 deletions
tests/unit/test_session.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -301,6 +301,7 @@ def test_train_pack_to_request(sagemaker_session):
 'MaxParallelTrainingJobs': 5,
 },
 'ParameterRanges': SAMPLE_PARAM_RANGES,
 'TrainingJobEarlyStoppingType': 'Off'
 },
 'TrainingJobDefinition': {
 'StaticHyperParameters': STATIC_HPs,
Expand Down

34 changes: 33 additions & 1 deletion
tests/unit/test_tuner.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -74,7 +74,8 @@
 'MinValue': '10',
 },
 ]
 }
 },
 'TrainingJobEarlyStoppingType': 'Off'
 },
 'HyperParameterTuningJobName': JOB_NAME,
 'TrainingJobDefinition': {
Expand DownExpand Up@@ -241,9 +242,26 @@ def test_fit_pca(sagemaker_session, tuner):
 assert len(tune_kwargs['parameter_ranges']['IntegerParameterRanges']) == 1
 assert tune_kwargs['job_name'].startswith('pca')
 assert tune_kwargs['tags'] == tags
 assert tune_kwargs['early_stopping_type'] == 'Off'
 assert tuner.estimator.mini_batch_size == 9999


def test_fit_pca_with_early_stopping(sagemaker_session, tuner):
 pca = PCA(ROLE, TRAIN_INSTANCE_COUNT, TRAIN_INSTANCE_TYPE, NUM_COMPONENTS,
 base_job_name='pca', sagemaker_session=sagemaker_session)

 tuner.estimator = pca
 tuner.early_stopping_type = 'Auto'

 records = RecordSet(s3_data=INPUTS, num_records=1, feature_dim=1)
 tuner.fit(records, mini_batch_size=9999)

 _, _, tune_kwargs = sagemaker_session.tune.mock_calls[0]

 assert tune_kwargs['job_name'].startswith('pca')
 assert tune_kwargs['early_stopping_type'] == 'Auto'


def test_attach_tuning_job_with_estimator_from_hyperparameters(sagemaker_session):
 job_details = copy.deepcopy(TUNING_JOB_DETAILS)
 sagemaker_session.sagemaker_client.describe_hyper_parameter_tuning_job = Mock(name='describe_tuning_job',
Expand All@@ -257,6 +275,7 @@ def test_attach_tuning_job_with_estimator_from_hyperparameters(sagemaker_session
 assert tuner.metric_definitions == METRIC_DEFINTIONS
 assert tuner.strategy == 'Bayesian'
 assert tuner.objective_type == 'Minimize'
 assert tuner.early_stopping_type == 'Off'

 assert isinstance(tuner.estimator, PCA)
 assert tuner.estimator.role == ROLE
Expand All@@ -270,6 +289,19 @@ def test_attach_tuning_job_with_estimator_from_hyperparameters(sagemaker_session
 assert tuner.estimator.hyperparameters()['num_components'] == '1'


def test_attach_tuning_job_with_estimator_from_hyperparameters_with_early_stopping(sagemaker_session):
 job_details = copy.deepcopy(TUNING_JOB_DETAILS)
 job_details['HyperParameterTuningJobConfig']['TrainingJobEarlyStoppingType'] = 'Auto'
 sagemaker_session.sagemaker_client.describe_hyper_parameter_tuning_job = Mock(name='describe_tuning_job',
 return_value=job_details)
 tuner = HyperparameterTuner.attach(JOB_NAME, sagemaker_session=sagemaker_session)

 assert tuner.latest_tuning_job.name == JOB_NAME
 assert tuner.early_stopping_type == 'Auto'

 assert isinstance(tuner.estimator, PCA)


def test_attach_tuning_job_with_job_details(sagemaker_session):
 job_details = copy.deepcopy(TUNING_JOB_DETAILS)
 HyperparameterTuner.attach(JOB_NAME, sagemaker_session=sagemaker_session, job_details=job_details)
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Strip utm_, fbclid, gclid, etc. from all links on page\n(function() {\n var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',\n 'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid',\n 'ref', 'ref_src', 'source', 'medium', 'campaign'];\n \n function cleanUrl(url) {\n try {\n var u = new URL(url, window.location.origin);\n var changed = false;\n trackingParams.forEach(function(p) {\n if (u.searchParams.has(p)) {\n u.searchParams.delete(p);\n changed = true;\n }\n });\n return changed ? u.toString() : url;\n } catch (e) {\n return url;\n }\n }\n \n function cleanLinks() {\n document.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n \n cleanLinks();\n \n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1) {\n if (node.tagName === 'A') cleanLinks();\n node.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Remove Tracking Parameters from Links");
}
} catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); }
})();
(function(){
try {
var __m = "youtube.com";
var __re = new RegExp('^' + "youtube\\.com" + '

Skip to content
Add Early Stopping to SageMaker Python SDK#541

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Closed

cassiesu
wants to merge
2
commits into

from

 Closed


Add Early Stopping to SageMaker Python SDK
#541
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
b86a28a

Add Early Stopping to SageMaker Python SDK

Dec 7, 2018
e8ae70d

fix flake8 check failure

Dec 10, 2018

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


16 changes: 16 additions & 0 deletions
README.rst

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -596,6 +596,22 @@ A hyperparameter range can be one of three types: continuous, integer, or catego
The SageMaker Python SDK provides corresponding classes for defining these different types.
You can define up to 20 hyperparameters to search over, but each value of a categorical hyperparameter range counts against that limit.

By default, training job early stopping is turned off. To enable early stopping for the tuning job, you need to set the ``early_stopping_type`` parameter to ``Auto``:

.. code:: python

 # Enable early stopping
 my_tuner = HyperparameterTuner(estimator=my_estimator, # previously-configured Estimator object
 objective_metric_name='validation-accuracy',
 hyperparameter_ranges={'learning-rate': ContinuousParameter(0.05, 0.06)},
 metric_definitions=[{'Name': 'validation-accuracy', 'Regex': 'validation-accuracy=(\d\.\d+)'}],
 max_jobs=100,
 max_parallel_jobs=10,
 early_stopping_type='Auto')

When early stopping is turned on, Amazon SageMaker will automatically stop a training job if it appears unlikely to produce a model of better quality than other jobs.
If not using built-in Amazon SageMaker algorithms, note that, for early stopping to be effective, the objective metric should be emitted at epoch level.

If you are using an Amazon SageMaker built-in algorithm, you don't need to pass in anything for ``metric_definitions``.
In addition, the ``fit()`` call uses a list of ``RecordSet`` objects instead of a dictionary:

Expand Down

7 changes: 6 additions & 1 deletion
src/sagemaker/session.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -350,7 +350,8 @@ def tune(self, job_name, strategy, objective_type, objective_metric_name,
 max_jobs, max_parallel_jobs, parameter_ranges,
 static_hyperparameters, input_mode, metric_definitions,
 role, input_config, output_config, resource_config, stop_condition, tags,
 warm_start_config, enable_network_isolation=False, image=None, algorithm_arn=None):
 warm_start_config, enable_network_isolation=False, image=None, algorithm_arn=None,
 early_stopping_type='Off'):
 """Create an Amazon SageMaker hyperparameter tuning job

 Args:
Expand DownExpand Up@@ -396,6 +397,9 @@ def tune(self, job_name, strategy, objective_type, objective_metric_name,
 https://docs.aws.amazon.com/sagemaker/latest/dg/API_Tag.html.
 warm_start_config (dict): Configuration defining the type of warm start and
 other required configurations.
 early_stopping_type (str): Specifies whether early stopping is enabled for the job.
 Can be either 'Auto' or 'Off'. If set to 'Off', early stopping will not be attempted.
 If set to 'Auto', early stopping of some training jobs may happen, but is not guaranteed to.
 """
 tune_request = {
 'HyperParameterTuningJobName': job_name,
Expand All@@ -410,6 +414,7 @@ def tune(self, job_name, strategy, objective_type, objective_metric_name,
 'MaxParallelTrainingJobs': max_parallel_jobs,
 },
 'ParameterRanges': parameter_ranges,
 'TrainingJobEarlyStoppingType': early_stopping_type,
 },
 'TrainingJobDefinition': {
 'StaticHyperParameters': static_hyperparameters,
Expand Down

10 changes: 8 additions & 2 deletions
src/sagemaker/tuner.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -165,7 +165,7 @@ class HyperparameterTuner(object):

 def __init__(self, estimator, objective_metric_name, hyperparameter_ranges, metric_definitions=None,
 strategy='Bayesian', objective_type='Maximize', max_jobs=1, max_parallel_jobs=1,
 tags=None, base_tuning_job_name=None, warm_start_config=None):
 tags=None, base_tuning_job_name=None, warm_start_config=None, early_stopping_type='Off'):
 """Initialize a ``HyperparameterTuner``. It takes an estimator to obtain configuration information
 for training jobs that are created as the result of a hyperparameter tuning job.

Expand DownExpand Up@@ -194,6 +194,9 @@ def __init__(self, estimator, objective_metric_name, hyperparameter_ranges, metr
 a default job name is generated, based on the training image name and current timestamp.
 warm_start_config (sagemaker.tuner.WarmStartConfig): A ``WarmStartConfig`` object that has been initialized
 with the configuration defining the nature of warm start tuning job.
 early_stopping_type (str): Specifies whether early stopping is enabled for the job.
 Can be either 'Auto' or 'Off' (default: 'Off'). If set to 'Off', early stopping will not be attempted.
 If set to 'Auto', early stopping of some training jobs may happen, but is not guaranteed to.
 """
 self._hyperparameter_ranges = hyperparameter_ranges
 if self._hyperparameter_ranges is None or len(self._hyperparameter_ranges) == 0:
Expand All@@ -214,6 +217,7 @@ def __init__(self, estimator, objective_metric_name, hyperparameter_ranges, metr
 self._current_job_name = None
 self.latest_tuning_job = None
 self.warm_start_config = warm_start_config
 self.early_stopping_type = early_stopping_type

 def _prepare_for_training(self, job_name=None, include_cls_metadata=True):
 if job_name is not None:
Expand DownExpand Up@@ -445,7 +449,8 @@ def _prepare_init_params_from_job_description(cls, job_details):
 'strategy': tuning_config['Strategy'],
 'max_jobs': tuning_config['ResourceLimits']['MaxNumberOfTrainingJobs'],
 'max_parallel_jobs': tuning_config['ResourceLimits']['MaxParallelTrainingJobs'],
 'warm_start_config': WarmStartConfig.from_job_desc(job_details.get('WarmStartConfig', None))
 'warm_start_config': WarmStartConfig.from_job_desc(job_details.get('WarmStartConfig', None)),
 'early_stopping_type': tuning_config['TrainingJobEarlyStoppingType']
 }

 @classmethod
Expand DownExpand Up@@ -625,6 +630,7 @@ def start_new(cls, tuner, inputs):
 tuner_args['metric_definitions'] = tuner.metric_definitions
 tuner_args['tags'] = tuner.tags
 tuner_args['warm_start_config'] = warm_start_config_req
 tuner_args['early_stopping_type'] = tuner.early_stopping_type

 del tuner_args['vpc_config']
 if isinstance(tuner.estimator, sagemaker.algorithm.AlgorithmEstimator):
Expand Down

30 changes: 21 additions & 9 deletions
tests/integ/test_tuner.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -83,15 +83,16 @@ def hyperparameter_ranges():

def _tune_and_deploy(kmeans_estimator, kmeans_train_set, sagemaker_session,
 hyperparameter_ranges=None, job_name=None,
 warm_start_config=None):
 warm_start_config=None, early_stopping_type='Off'):
 tuner = _tune(kmeans_estimator, kmeans_train_set,
 hyperparameter_ranges=hyperparameter_ranges, warm_start_config=warm_start_config,
 job_name=job_name)
 _deploy(kmeans_train_set, sagemaker_session, tuner)
 job_name=job_name, early_stopping_type=early_stopping_type)
 _deploy(kmeans_train_set, sagemaker_session, tuner, early_stopping_type)


def _deploy(kmeans_train_set, sagemaker_session, tuner):
def _deploy(kmeans_train_set, sagemaker_session, tuner, early_stopping_type):
 best_training_job = tuner.best_training_job()
 assert tuner.early_stopping_type == early_stopping_type
 with timeout_and_delete_endpoint_by_name(best_training_job, sagemaker_session):
 predictor = tuner.deploy(1, 'ml.c4.xlarge')

Expand All@@ -105,7 +106,7 @@ def _deploy(kmeans_train_set, sagemaker_session, tuner):

def _tune(kmeans_estimator, kmeans_train_set, tuner=None,
 hyperparameter_ranges=None, job_name=None, warm_start_config=None,
 wait_till_terminal=True, max_jobs=2, max_parallel_jobs=2):
 wait_till_terminal=True, max_jobs=2, max_parallel_jobs=2, early_stopping_type='Off'):
 with timeout(minutes=TUNING_DEFAULT_TIMEOUT_MINUTES):

 if not tuner:
Expand All@@ -115,7 +116,8 @@ def _tune(kmeans_estimator, kmeans_train_set, tuner=None,
 objective_type='Minimize',
 max_jobs=max_jobs,
 max_parallel_jobs=max_parallel_jobs,
 warm_start_config=warm_start_config)
 warm_start_config=warm_start_config,
 early_stopping_type=early_stopping_type)

 records = kmeans_estimator.record_set(kmeans_train_set[0][:100])
 test_record_set = kmeans_estimator.record_set(kmeans_train_set[0][:100], channel='test')
Expand DownExpand Up@@ -332,16 +334,23 @@ def test_tuning_lda(sagemaker_session):
 tuner = HyperparameterTuner(estimator=lda, objective_metric_name=objective_metric_name,
 hyperparameter_ranges=hyperparameter_ranges,
 objective_type='Maximize', max_jobs=2,
 max_parallel_jobs=2)
 max_parallel_jobs=2,
 early_stopping_type='Auto')

 tuning_job_name = unique_name_from_base('test-lda', max_length=32)
 tuner.fit([record_set, test_record_set], mini_batch_size=1, job_name=tuning_job_name)

 print('Started hyperparameter tuning job with name:' + tuner.latest_tuning_job.name)
 latest_tuning_job_name = tuner.latest_tuning_job.name

 print('Started hyperparameter tuning job with name:' + latest_tuning_job_name)

 time.sleep(15)
 tuner.wait()

 desc = tuner.latest_tuning_job.sagemaker_session.sagemaker_client \
 .describe_hyper_parameter_tuning_job(HyperParameterTuningJobName=latest_tuning_job_name)
 assert desc['HyperParameterTuningJobConfig']['TrainingJobEarlyStoppingType'] == 'Auto'

 best_training_job = tuner.best_training_job()
 with timeout_and_delete_endpoint_by_name(best_training_job, sagemaker_session):
 predictor = tuner.deploy(1, 'ml.c4.xlarge')
Expand DownExpand Up@@ -555,7 +564,8 @@ def test_attach_tuning_pytorch(sagemaker_session):

 tuner = HyperparameterTuner(estimator, objective_metric_name, hyperparameter_ranges,
 metric_definitions,
 max_jobs=2, max_parallel_jobs=2)
 max_jobs=2, max_parallel_jobs=2,
 early_stopping_type='Auto')

 training_data = estimator.sagemaker_session.upload_data(
 path=os.path.join(mnist_dir, 'training'),
Expand All@@ -571,6 +581,8 @@ def test_attach_tuning_pytorch(sagemaker_session):

 attached_tuner = HyperparameterTuner.attach(tuning_job_name,
 sagemaker_session=sagemaker_session)
 assert attached_tuner.early_stopping_type == 'Auto'

 best_training_job = tuner.best_training_job()
 with timeout_and_delete_endpoint_by_name(best_training_job, sagemaker_session):
 predictor = attached_tuner.deploy(1, 'ml.c4.xlarge')
Expand Down

1 change: 1 addition & 0 deletions
tests/unit/test_session.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -301,6 +301,7 @@ def test_train_pack_to_request(sagemaker_session):
 'MaxParallelTrainingJobs': 5,
 },
 'ParameterRanges': SAMPLE_PARAM_RANGES,
 'TrainingJobEarlyStoppingType': 'Off'
 },
 'TrainingJobDefinition': {
 'StaticHyperParameters': STATIC_HPs,
Expand Down

34 changes: 33 additions & 1 deletion
tests/unit/test_tuner.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -74,7 +74,8 @@
 'MinValue': '10',
 },
 ]
 }
 },
 'TrainingJobEarlyStoppingType': 'Off'
 },
 'HyperParameterTuningJobName': JOB_NAME,
 'TrainingJobDefinition': {
Expand DownExpand Up@@ -241,9 +242,26 @@ def test_fit_pca(sagemaker_session, tuner):
 assert len(tune_kwargs['parameter_ranges']['IntegerParameterRanges']) == 1
 assert tune_kwargs['job_name'].startswith('pca')
 assert tune_kwargs['tags'] == tags
 assert tune_kwargs['early_stopping_type'] == 'Off'
 assert tuner.estimator.mini_batch_size == 9999


def test_fit_pca_with_early_stopping(sagemaker_session, tuner):
 pca = PCA(ROLE, TRAIN_INSTANCE_COUNT, TRAIN_INSTANCE_TYPE, NUM_COMPONENTS,
 base_job_name='pca', sagemaker_session=sagemaker_session)

 tuner.estimator = pca
 tuner.early_stopping_type = 'Auto'

 records = RecordSet(s3_data=INPUTS, num_records=1, feature_dim=1)
 tuner.fit(records, mini_batch_size=9999)

 _, _, tune_kwargs = sagemaker_session.tune.mock_calls[0]

 assert tune_kwargs['job_name'].startswith('pca')
 assert tune_kwargs['early_stopping_type'] == 'Auto'


def test_attach_tuning_job_with_estimator_from_hyperparameters(sagemaker_session):
 job_details = copy.deepcopy(TUNING_JOB_DETAILS)
 sagemaker_session.sagemaker_client.describe_hyper_parameter_tuning_job = Mock(name='describe_tuning_job',
Expand All@@ -257,6 +275,7 @@ def test_attach_tuning_job_with_estimator_from_hyperparameters(sagemaker_session
 assert tuner.metric_definitions == METRIC_DEFINTIONS
 assert tuner.strategy == 'Bayesian'
 assert tuner.objective_type == 'Minimize'
 assert tuner.early_stopping_type == 'Off'

 assert isinstance(tuner.estimator, PCA)
 assert tuner.estimator.role == ROLE
Expand All@@ -270,6 +289,19 @@ def test_attach_tuning_job_with_estimator_from_hyperparameters(sagemaker_session
 assert tuner.estimator.hyperparameters()['num_components'] == '1'


def test_attach_tuning_job_with_estimator_from_hyperparameters_with_early_stopping(sagemaker_session):
 job_details = copy.deepcopy(TUNING_JOB_DETAILS)
 job_details['HyperParameterTuningJobConfig']['TrainingJobEarlyStoppingType'] = 'Auto'
 sagemaker_session.sagemaker_client.describe_hyper_parameter_tuning_job = Mock(name='describe_tuning_job',
 return_value=job_details)
 tuner = HyperparameterTuner.attach(JOB_NAME, sagemaker_session=sagemaker_session)

 assert tuner.latest_tuning_job.name == JOB_NAME
 assert tuner.early_stopping_type == 'Auto'

 assert isinstance(tuner.estimator, PCA)


def test_attach_tuning_job_with_job_details(sagemaker_session):
 job_details = copy.deepcopy(TUNING_JOB_DETAILS)
 HyperparameterTuner.attach(JOB_NAME, sagemaker_session=sagemaker_session, job_details=job_details)
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Auto-enable theater mode on YouTube\n(function() {\n function tryTheater() {\n var btn = document.querySelector('button[aria-label=\"Theater mode\"], ytd-player #player button[title=\"Theater mode\"]');\n if (btn && !btn.classList.contains('activated')) {\n btn.click();\n }\n }\n \n // Try immediately\n tryTheater();\n \n // Try after navigation (SPA)\n var lastUrl = location.href;\n setInterval(function() {\n if (location.href !== lastUrl) {\n lastUrl = location.href;\n setTimeout(tryTheater, 500);\n }\n }, 1000);\n \n // Also try on player load\n var observer = new MutationObserver(tryTheater);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "YouTube Theater Mode Default");
}
} catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Add Early Stopping to SageMaker Python SDK#541

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Closed

cassiesu
wants to merge
2
commits into

from

 Closed


Add Early Stopping to SageMaker Python SDK
#541
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
b86a28a

Add Early Stopping to SageMaker Python SDK

Dec 7, 2018
e8ae70d

fix flake8 check failure

Dec 10, 2018

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


16 changes: 16 additions & 0 deletions
README.rst

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -596,6 +596,22 @@ A hyperparameter range can be one of three types: continuous, integer, or catego
The SageMaker Python SDK provides corresponding classes for defining these different types.
You can define up to 20 hyperparameters to search over, but each value of a categorical hyperparameter range counts against that limit.

By default, training job early stopping is turned off. To enable early stopping for the tuning job, you need to set the ``early_stopping_type`` parameter to ``Auto``:

.. code:: python

 # Enable early stopping
 my_tuner = HyperparameterTuner(estimator=my_estimator, # previously-configured Estimator object
 objective_metric_name='validation-accuracy',
 hyperparameter_ranges={'learning-rate': ContinuousParameter(0.05, 0.06)},
 metric_definitions=[{'Name': 'validation-accuracy', 'Regex': 'validation-accuracy=(\d\.\d+)'}],
 max_jobs=100,
 max_parallel_jobs=10,
 early_stopping_type='Auto')

When early stopping is turned on, Amazon SageMaker will automatically stop a training job if it appears unlikely to produce a model of better quality than other jobs.
If not using built-in Amazon SageMaker algorithms, note that, for early stopping to be effective, the objective metric should be emitted at epoch level.

If you are using an Amazon SageMaker built-in algorithm, you don't need to pass in anything for ``metric_definitions``.
In addition, the ``fit()`` call uses a list of ``RecordSet`` objects instead of a dictionary:

Expand Down

7 changes: 6 additions & 1 deletion
src/sagemaker/session.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -350,7 +350,8 @@ def tune(self, job_name, strategy, objective_type, objective_metric_name,
 max_jobs, max_parallel_jobs, parameter_ranges,
 static_hyperparameters, input_mode, metric_definitions,
 role, input_config, output_config, resource_config, stop_condition, tags,
 warm_start_config, enable_network_isolation=False, image=None, algorithm_arn=None):
 warm_start_config, enable_network_isolation=False, image=None, algorithm_arn=None,
 early_stopping_type='Off'):
 """Create an Amazon SageMaker hyperparameter tuning job

 Args:
Expand DownExpand Up@@ -396,6 +397,9 @@ def tune(self, job_name, strategy, objective_type, objective_metric_name,
 https://docs.aws.amazon.com/sagemaker/latest/dg/API_Tag.html.
 warm_start_config (dict): Configuration defining the type of warm start and
 other required configurations.
 early_stopping_type (str): Specifies whether early stopping is enabled for the job.
 Can be either 'Auto' or 'Off'. If set to 'Off', early stopping will not be attempted.
 If set to 'Auto', early stopping of some training jobs may happen, but is not guaranteed to.
 """
 tune_request = {
 'HyperParameterTuningJobName': job_name,
Expand All@@ -410,6 +414,7 @@ def tune(self, job_name, strategy, objective_type, objective_metric_name,
 'MaxParallelTrainingJobs': max_parallel_jobs,
 },
 'ParameterRanges': parameter_ranges,
 'TrainingJobEarlyStoppingType': early_stopping_type,
 },
 'TrainingJobDefinition': {
 'StaticHyperParameters': static_hyperparameters,
Expand Down

10 changes: 8 additions & 2 deletions
src/sagemaker/tuner.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -165,7 +165,7 @@ class HyperparameterTuner(object):

 def __init__(self, estimator, objective_metric_name, hyperparameter_ranges, metric_definitions=None,
 strategy='Bayesian', objective_type='Maximize', max_jobs=1, max_parallel_jobs=1,
 tags=None, base_tuning_job_name=None, warm_start_config=None):
 tags=None, base_tuning_job_name=None, warm_start_config=None, early_stopping_type='Off'):
 """Initialize a ``HyperparameterTuner``. It takes an estimator to obtain configuration information
 for training jobs that are created as the result of a hyperparameter tuning job.

Expand DownExpand Up@@ -194,6 +194,9 @@ def __init__(self, estimator, objective_metric_name, hyperparameter_ranges, metr
 a default job name is generated, based on the training image name and current timestamp.
 warm_start_config (sagemaker.tuner.WarmStartConfig): A ``WarmStartConfig`` object that has been initialized
 with the configuration defining the nature of warm start tuning job.
 early_stopping_type (str): Specifies whether early stopping is enabled for the job.
 Can be either 'Auto' or 'Off' (default: 'Off'). If set to 'Off', early stopping will not be attempted.
 If set to 'Auto', early stopping of some training jobs may happen, but is not guaranteed to.
 """
 self._hyperparameter_ranges = hyperparameter_ranges
 if self._hyperparameter_ranges is None or len(self._hyperparameter_ranges) == 0:
Expand All@@ -214,6 +217,7 @@ def __init__(self, estimator, objective_metric_name, hyperparameter_ranges, metr
 self._current_job_name = None
 self.latest_tuning_job = None
 self.warm_start_config = warm_start_config
 self.early_stopping_type = early_stopping_type

 def _prepare_for_training(self, job_name=None, include_cls_metadata=True):
 if job_name is not None:
Expand DownExpand Up@@ -445,7 +449,8 @@ def _prepare_init_params_from_job_description(cls, job_details):
 'strategy': tuning_config['Strategy'],
 'max_jobs': tuning_config['ResourceLimits']['MaxNumberOfTrainingJobs'],
 'max_parallel_jobs': tuning_config['ResourceLimits']['MaxParallelTrainingJobs'],
 'warm_start_config': WarmStartConfig.from_job_desc(job_details.get('WarmStartConfig', None))
 'warm_start_config': WarmStartConfig.from_job_desc(job_details.get('WarmStartConfig', None)),
 'early_stopping_type': tuning_config['TrainingJobEarlyStoppingType']
 }

 @classmethod
Expand DownExpand Up@@ -625,6 +630,7 @@ def start_new(cls, tuner, inputs):
 tuner_args['metric_definitions'] = tuner.metric_definitions
 tuner_args['tags'] = tuner.tags
 tuner_args['warm_start_config'] = warm_start_config_req
 tuner_args['early_stopping_type'] = tuner.early_stopping_type

 del tuner_args['vpc_config']
 if isinstance(tuner.estimator, sagemaker.algorithm.AlgorithmEstimator):
Expand Down

30 changes: 21 additions & 9 deletions
tests/integ/test_tuner.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -83,15 +83,16 @@ def hyperparameter_ranges():

def _tune_and_deploy(kmeans_estimator, kmeans_train_set, sagemaker_session,
 hyperparameter_ranges=None, job_name=None,
 warm_start_config=None):
 warm_start_config=None, early_stopping_type='Off'):
 tuner = _tune(kmeans_estimator, kmeans_train_set,
 hyperparameter_ranges=hyperparameter_ranges, warm_start_config=warm_start_config,
 job_name=job_name)
 _deploy(kmeans_train_set, sagemaker_session, tuner)
 job_name=job_name, early_stopping_type=early_stopping_type)
 _deploy(kmeans_train_set, sagemaker_session, tuner, early_stopping_type)


def _deploy(kmeans_train_set, sagemaker_session, tuner):
def _deploy(kmeans_train_set, sagemaker_session, tuner, early_stopping_type):
 best_training_job = tuner.best_training_job()
 assert tuner.early_stopping_type == early_stopping_type
 with timeout_and_delete_endpoint_by_name(best_training_job, sagemaker_session):
 predictor = tuner.deploy(1, 'ml.c4.xlarge')

Expand All@@ -105,7 +106,7 @@ def _deploy(kmeans_train_set, sagemaker_session, tuner):

def _tune(kmeans_estimator, kmeans_train_set, tuner=None,
 hyperparameter_ranges=None, job_name=None, warm_start_config=None,
 wait_till_terminal=True, max_jobs=2, max_parallel_jobs=2):
 wait_till_terminal=True, max_jobs=2, max_parallel_jobs=2, early_stopping_type='Off'):
 with timeout(minutes=TUNING_DEFAULT_TIMEOUT_MINUTES):

 if not tuner:
Expand All@@ -115,7 +116,8 @@ def _tune(kmeans_estimator, kmeans_train_set, tuner=None,
 objective_type='Minimize',
 max_jobs=max_jobs,
 max_parallel_jobs=max_parallel_jobs,
 warm_start_config=warm_start_config)
 warm_start_config=warm_start_config,
 early_stopping_type=early_stopping_type)

 records = kmeans_estimator.record_set(kmeans_train_set[0][:100])
 test_record_set = kmeans_estimator.record_set(kmeans_train_set[0][:100], channel='test')
Expand DownExpand Up@@ -332,16 +334,23 @@ def test_tuning_lda(sagemaker_session):
 tuner = HyperparameterTuner(estimator=lda, objective_metric_name=objective_metric_name,
 hyperparameter_ranges=hyperparameter_ranges,
 objective_type='Maximize', max_jobs=2,
 max_parallel_jobs=2)
 max_parallel_jobs=2,
 early_stopping_type='Auto')

 tuning_job_name = unique_name_from_base('test-lda', max_length=32)
 tuner.fit([record_set, test_record_set], mini_batch_size=1, job_name=tuning_job_name)

 print('Started hyperparameter tuning job with name:' + tuner.latest_tuning_job.name)
 latest_tuning_job_name = tuner.latest_tuning_job.name

 print('Started hyperparameter tuning job with name:' + latest_tuning_job_name)

 time.sleep(15)
 tuner.wait()

 desc = tuner.latest_tuning_job.sagemaker_session.sagemaker_client \
 .describe_hyper_parameter_tuning_job(HyperParameterTuningJobName=latest_tuning_job_name)
 assert desc['HyperParameterTuningJobConfig']['TrainingJobEarlyStoppingType'] == 'Auto'

 best_training_job = tuner.best_training_job()
 with timeout_and_delete_endpoint_by_name(best_training_job, sagemaker_session):
 predictor = tuner.deploy(1, 'ml.c4.xlarge')
Expand DownExpand Up@@ -555,7 +564,8 @@ def test_attach_tuning_pytorch(sagemaker_session):

 tuner = HyperparameterTuner(estimator, objective_metric_name, hyperparameter_ranges,
 metric_definitions,
 max_jobs=2, max_parallel_jobs=2)
 max_jobs=2, max_parallel_jobs=2,
 early_stopping_type='Auto')

 training_data = estimator.sagemaker_session.upload_data(
 path=os.path.join(mnist_dir, 'training'),
Expand All@@ -571,6 +581,8 @@ def test_attach_tuning_pytorch(sagemaker_session):

 attached_tuner = HyperparameterTuner.attach(tuning_job_name,
 sagemaker_session=sagemaker_session)
 assert attached_tuner.early_stopping_type == 'Auto'

 best_training_job = tuner.best_training_job()
 with timeout_and_delete_endpoint_by_name(best_training_job, sagemaker_session):
 predictor = attached_tuner.deploy(1, 'ml.c4.xlarge')
Expand Down

1 change: 1 addition & 0 deletions
tests/unit/test_session.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -301,6 +301,7 @@ def test_train_pack_to_request(sagemaker_session):
 'MaxParallelTrainingJobs': 5,
 },
 'ParameterRanges': SAMPLE_PARAM_RANGES,
 'TrainingJobEarlyStoppingType': 'Off'
 },
 'TrainingJobDefinition': {
 'StaticHyperParameters': STATIC_HPs,
Expand Down

34 changes: 33 additions & 1 deletion
tests/unit/test_tuner.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -74,7 +74,8 @@
 'MinValue': '10',
 },
 ]
 }
 },
 'TrainingJobEarlyStoppingType': 'Off'
 },
 'HyperParameterTuningJobName': JOB_NAME,
 'TrainingJobDefinition': {
Expand DownExpand Up@@ -241,9 +242,26 @@ def test_fit_pca(sagemaker_session, tuner):
 assert len(tune_kwargs['parameter_ranges']['IntegerParameterRanges']) == 1
 assert tune_kwargs['job_name'].startswith('pca')
 assert tune_kwargs['tags'] == tags
 assert tune_kwargs['early_stopping_type'] == 'Off'
 assert tuner.estimator.mini_batch_size == 9999


def test_fit_pca_with_early_stopping(sagemaker_session, tuner):
 pca = PCA(ROLE, TRAIN_INSTANCE_COUNT, TRAIN_INSTANCE_TYPE, NUM_COMPONENTS,
 base_job_name='pca', sagemaker_session=sagemaker_session)

 tuner.estimator = pca
 tuner.early_stopping_type = 'Auto'

 records = RecordSet(s3_data=INPUTS, num_records=1, feature_dim=1)
 tuner.fit(records, mini_batch_size=9999)

 _, _, tune_kwargs = sagemaker_session.tune.mock_calls[0]

 assert tune_kwargs['job_name'].startswith('pca')
 assert tune_kwargs['early_stopping_type'] == 'Auto'


def test_attach_tuning_job_with_estimator_from_hyperparameters(sagemaker_session):
 job_details = copy.deepcopy(TUNING_JOB_DETAILS)
 sagemaker_session.sagemaker_client.describe_hyper_parameter_tuning_job = Mock(name='describe_tuning_job',
Expand All@@ -257,6 +275,7 @@ def test_attach_tuning_job_with_estimator_from_hyperparameters(sagemaker_session
 assert tuner.metric_definitions == METRIC_DEFINTIONS
 assert tuner.strategy == 'Bayesian'
 assert tuner.objective_type == 'Minimize'
 assert tuner.early_stopping_type == 'Off'

 assert isinstance(tuner.estimator, PCA)
 assert tuner.estimator.role == ROLE
Expand All@@ -270,6 +289,19 @@ def test_attach_tuning_job_with_estimator_from_hyperparameters(sagemaker_session
 assert tuner.estimator.hyperparameters()['num_components'] == '1'


def test_attach_tuning_job_with_estimator_from_hyperparameters_with_early_stopping(sagemaker_session):
 job_details = copy.deepcopy(TUNING_JOB_DETAILS)
 job_details['HyperParameterTuningJobConfig']['TrainingJobEarlyStoppingType'] = 'Auto'
 sagemaker_session.sagemaker_client.describe_hyper_parameter_tuning_job = Mock(name='describe_tuning_job',
 return_value=job_details)
 tuner = HyperparameterTuner.attach(JOB_NAME, sagemaker_session=sagemaker_session)

 assert tuner.latest_tuning_job.name == JOB_NAME
 assert tuner.early_stopping_type == 'Auto'

 assert isinstance(tuner.estimator, PCA)


def test_attach_tuning_job_with_job_details(sagemaker_session):
 job_details = copy.deepcopy(TUNING_JOB_DETAILS)
 HyperparameterTuner.attach(JOB_NAME, sagemaker_session=sagemaker_session, job_details=job_details)
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Remove or un-stick sticky/fixed headers that block content\n(function() {\n function unstick() {\n document.querySelectorAll('header, nav, [role=\"banner\"], .header, .navbar, .sticky, .fixed-top, [style*=\"position: fixed\"], [style*=\"position:sticky\"]').forEach(function(el) {\n if (el.style.position === 'fixed' || el.style.position === 'sticky' || \n getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') {\n el.style.position = 'static';\n el.style.top = 'auto';\n el.style.zIndex = 'auto';\n }\n });\n }\n \n unstick();\n \n var observer = new MutationObserver(unstick);\n observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] });\n})();", "Kill Sticky Headers");
}
} catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Add Early Stopping to SageMaker Python SDK#541

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Closed

cassiesu
wants to merge
2
commits into

from

 Closed


Add Early Stopping to SageMaker Python SDK
#541
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
b86a28a

Add Early Stopping to SageMaker Python SDK

Dec 7, 2018
e8ae70d

fix flake8 check failure

Dec 10, 2018

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


16 changes: 16 additions & 0 deletions
README.rst

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -596,6 +596,22 @@ A hyperparameter range can be one of three types: continuous, integer, or catego
The SageMaker Python SDK provides corresponding classes for defining these different types.
You can define up to 20 hyperparameters to search over, but each value of a categorical hyperparameter range counts against that limit.

By default, training job early stopping is turned off. To enable early stopping for the tuning job, you need to set the ``early_stopping_type`` parameter to ``Auto``:

.. code:: python

 # Enable early stopping
 my_tuner = HyperparameterTuner(estimator=my_estimator, # previously-configured Estimator object
 objective_metric_name='validation-accuracy',
 hyperparameter_ranges={'learning-rate': ContinuousParameter(0.05, 0.06)},
 metric_definitions=[{'Name': 'validation-accuracy', 'Regex': 'validation-accuracy=(\d\.\d+)'}],
 max_jobs=100,
 max_parallel_jobs=10,
 early_stopping_type='Auto')

When early stopping is turned on, Amazon SageMaker will automatically stop a training job if it appears unlikely to produce a model of better quality than other jobs.
If not using built-in Amazon SageMaker algorithms, note that, for early stopping to be effective, the objective metric should be emitted at epoch level.

If you are using an Amazon SageMaker built-in algorithm, you don't need to pass in anything for ``metric_definitions``.
In addition, the ``fit()`` call uses a list of ``RecordSet`` objects instead of a dictionary:

Expand Down

7 changes: 6 additions & 1 deletion
src/sagemaker/session.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -350,7 +350,8 @@ def tune(self, job_name, strategy, objective_type, objective_metric_name,
 max_jobs, max_parallel_jobs, parameter_ranges,
 static_hyperparameters, input_mode, metric_definitions,
 role, input_config, output_config, resource_config, stop_condition, tags,
 warm_start_config, enable_network_isolation=False, image=None, algorithm_arn=None):
 warm_start_config, enable_network_isolation=False, image=None, algorithm_arn=None,
 early_stopping_type='Off'):
 """Create an Amazon SageMaker hyperparameter tuning job

 Args:
Expand DownExpand Up@@ -396,6 +397,9 @@ def tune(self, job_name, strategy, objective_type, objective_metric_name,
 https://docs.aws.amazon.com/sagemaker/latest/dg/API_Tag.html.
 warm_start_config (dict): Configuration defining the type of warm start and
 other required configurations.
 early_stopping_type (str): Specifies whether early stopping is enabled for the job.
 Can be either 'Auto' or 'Off'. If set to 'Off', early stopping will not be attempted.
 If set to 'Auto', early stopping of some training jobs may happen, but is not guaranteed to.
 """
 tune_request = {
 'HyperParameterTuningJobName': job_name,
Expand All@@ -410,6 +414,7 @@ def tune(self, job_name, strategy, objective_type, objective_metric_name,
 'MaxParallelTrainingJobs': max_parallel_jobs,
 },
 'ParameterRanges': parameter_ranges,
 'TrainingJobEarlyStoppingType': early_stopping_type,
 },
 'TrainingJobDefinition': {
 'StaticHyperParameters': static_hyperparameters,
Expand Down

10 changes: 8 additions & 2 deletions
src/sagemaker/tuner.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -165,7 +165,7 @@ class HyperparameterTuner(object):

 def __init__(self, estimator, objective_metric_name, hyperparameter_ranges, metric_definitions=None,
 strategy='Bayesian', objective_type='Maximize', max_jobs=1, max_parallel_jobs=1,
 tags=None, base_tuning_job_name=None, warm_start_config=None):
 tags=None, base_tuning_job_name=None, warm_start_config=None, early_stopping_type='Off'):
 """Initialize a ``HyperparameterTuner``. It takes an estimator to obtain configuration information
 for training jobs that are created as the result of a hyperparameter tuning job.

Expand DownExpand Up@@ -194,6 +194,9 @@ def __init__(self, estimator, objective_metric_name, hyperparameter_ranges, metr
 a default job name is generated, based on the training image name and current timestamp.
 warm_start_config (sagemaker.tuner.WarmStartConfig): A ``WarmStartConfig`` object that has been initialized
 with the configuration defining the nature of warm start tuning job.
 early_stopping_type (str): Specifies whether early stopping is enabled for the job.
 Can be either 'Auto' or 'Off' (default: 'Off'). If set to 'Off', early stopping will not be attempted.
 If set to 'Auto', early stopping of some training jobs may happen, but is not guaranteed to.
 """
 self._hyperparameter_ranges = hyperparameter_ranges
 if self._hyperparameter_ranges is None or len(self._hyperparameter_ranges) == 0:
Expand All@@ -214,6 +217,7 @@ def __init__(self, estimator, objective_metric_name, hyperparameter_ranges, metr
 self._current_job_name = None
 self.latest_tuning_job = None
 self.warm_start_config = warm_start_config
 self.early_stopping_type = early_stopping_type

 def _prepare_for_training(self, job_name=None, include_cls_metadata=True):
 if job_name is not None:
Expand DownExpand Up@@ -445,7 +449,8 @@ def _prepare_init_params_from_job_description(cls, job_details):
 'strategy': tuning_config['Strategy'],
 'max_jobs': tuning_config['ResourceLimits']['MaxNumberOfTrainingJobs'],
 'max_parallel_jobs': tuning_config['ResourceLimits']['MaxParallelTrainingJobs'],
 'warm_start_config': WarmStartConfig.from_job_desc(job_details.get('WarmStartConfig', None))
 'warm_start_config': WarmStartConfig.from_job_desc(job_details.get('WarmStartConfig', None)),
 'early_stopping_type': tuning_config['TrainingJobEarlyStoppingType']
 }

 @classmethod
Expand DownExpand Up@@ -625,6 +630,7 @@ def start_new(cls, tuner, inputs):
 tuner_args['metric_definitions'] = tuner.metric_definitions
 tuner_args['tags'] = tuner.tags
 tuner_args['warm_start_config'] = warm_start_config_req
 tuner_args['early_stopping_type'] = tuner.early_stopping_type

 del tuner_args['vpc_config']
 if isinstance(tuner.estimator, sagemaker.algorithm.AlgorithmEstimator):
Expand Down

30 changes: 21 additions & 9 deletions
tests/integ/test_tuner.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -83,15 +83,16 @@ def hyperparameter_ranges():

def _tune_and_deploy(kmeans_estimator, kmeans_train_set, sagemaker_session,
 hyperparameter_ranges=None, job_name=None,
 warm_start_config=None):
 warm_start_config=None, early_stopping_type='Off'):
 tuner = _tune(kmeans_estimator, kmeans_train_set,
 hyperparameter_ranges=hyperparameter_ranges, warm_start_config=warm_start_config,
 job_name=job_name)
 _deploy(kmeans_train_set, sagemaker_session, tuner)
 job_name=job_name, early_stopping_type=early_stopping_type)
 _deploy(kmeans_train_set, sagemaker_session, tuner, early_stopping_type)


def _deploy(kmeans_train_set, sagemaker_session, tuner):
def _deploy(kmeans_train_set, sagemaker_session, tuner, early_stopping_type):
 best_training_job = tuner.best_training_job()
 assert tuner.early_stopping_type == early_stopping_type
 with timeout_and_delete_endpoint_by_name(best_training_job, sagemaker_session):
 predictor = tuner.deploy(1, 'ml.c4.xlarge')

Expand All@@ -105,7 +106,7 @@ def _deploy(kmeans_train_set, sagemaker_session, tuner):

def _tune(kmeans_estimator, kmeans_train_set, tuner=None,
 hyperparameter_ranges=None, job_name=None, warm_start_config=None,
 wait_till_terminal=True, max_jobs=2, max_parallel_jobs=2):
 wait_till_terminal=True, max_jobs=2, max_parallel_jobs=2, early_stopping_type='Off'):
 with timeout(minutes=TUNING_DEFAULT_TIMEOUT_MINUTES):

 if not tuner:
Expand All@@ -115,7 +116,8 @@ def _tune(kmeans_estimator, kmeans_train_set, tuner=None,
 objective_type='Minimize',
 max_jobs=max_jobs,
 max_parallel_jobs=max_parallel_jobs,
 warm_start_config=warm_start_config)
 warm_start_config=warm_start_config,
 early_stopping_type=early_stopping_type)

 records = kmeans_estimator.record_set(kmeans_train_set[0][:100])
 test_record_set = kmeans_estimator.record_set(kmeans_train_set[0][:100], channel='test')
Expand DownExpand Up@@ -332,16 +334,23 @@ def test_tuning_lda(sagemaker_session):
 tuner = HyperparameterTuner(estimator=lda, objective_metric_name=objective_metric_name,
 hyperparameter_ranges=hyperparameter_ranges,
 objective_type='Maximize', max_jobs=2,
 max_parallel_jobs=2)
 max_parallel_jobs=2,
 early_stopping_type='Auto')

 tuning_job_name = unique_name_from_base('test-lda', max_length=32)
 tuner.fit([record_set, test_record_set], mini_batch_size=1, job_name=tuning_job_name)

 print('Started hyperparameter tuning job with name:' + tuner.latest_tuning_job.name)
 latest_tuning_job_name = tuner.latest_tuning_job.name

 print('Started hyperparameter tuning job with name:' + latest_tuning_job_name)

 time.sleep(15)
 tuner.wait()

 desc = tuner.latest_tuning_job.sagemaker_session.sagemaker_client \
 .describe_hyper_parameter_tuning_job(HyperParameterTuningJobName=latest_tuning_job_name)
 assert desc['HyperParameterTuningJobConfig']['TrainingJobEarlyStoppingType'] == 'Auto'

 best_training_job = tuner.best_training_job()
 with timeout_and_delete_endpoint_by_name(best_training_job, sagemaker_session):
 predictor = tuner.deploy(1, 'ml.c4.xlarge')
Expand DownExpand Up@@ -555,7 +564,8 @@ def test_attach_tuning_pytorch(sagemaker_session):

 tuner = HyperparameterTuner(estimator, objective_metric_name, hyperparameter_ranges,
 metric_definitions,
 max_jobs=2, max_parallel_jobs=2)
 max_jobs=2, max_parallel_jobs=2,
 early_stopping_type='Auto')

 training_data = estimator.sagemaker_session.upload_data(
 path=os.path.join(mnist_dir, 'training'),
Expand All@@ -571,6 +581,8 @@ def test_attach_tuning_pytorch(sagemaker_session):

 attached_tuner = HyperparameterTuner.attach(tuning_job_name,
 sagemaker_session=sagemaker_session)
 assert attached_tuner.early_stopping_type == 'Auto'

 best_training_job = tuner.best_training_job()
 with timeout_and_delete_endpoint_by_name(best_training_job, sagemaker_session):
 predictor = attached_tuner.deploy(1, 'ml.c4.xlarge')
Expand Down

1 change: 1 addition & 0 deletions
tests/unit/test_session.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -301,6 +301,7 @@ def test_train_pack_to_request(sagemaker_session):
 'MaxParallelTrainingJobs': 5,
 },
 'ParameterRanges': SAMPLE_PARAM_RANGES,
 'TrainingJobEarlyStoppingType': 'Off'
 },
 'TrainingJobDefinition': {
 'StaticHyperParameters': STATIC_HPs,
Expand Down

34 changes: 33 additions & 1 deletion
tests/unit/test_tuner.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -74,7 +74,8 @@
 'MinValue': '10',
 },
 ]
 }
 },
 'TrainingJobEarlyStoppingType': 'Off'
 },
 'HyperParameterTuningJobName': JOB_NAME,
 'TrainingJobDefinition': {
Expand DownExpand Up@@ -241,9 +242,26 @@ def test_fit_pca(sagemaker_session, tuner):
 assert len(tune_kwargs['parameter_ranges']['IntegerParameterRanges']) == 1
 assert tune_kwargs['job_name'].startswith('pca')
 assert tune_kwargs['tags'] == tags
 assert tune_kwargs['early_stopping_type'] == 'Off'
 assert tuner.estimator.mini_batch_size == 9999


def test_fit_pca_with_early_stopping(sagemaker_session, tuner):
 pca = PCA(ROLE, TRAIN_INSTANCE_COUNT, TRAIN_INSTANCE_TYPE, NUM_COMPONENTS,
 base_job_name='pca', sagemaker_session=sagemaker_session)

 tuner.estimator = pca
 tuner.early_stopping_type = 'Auto'

 records = RecordSet(s3_data=INPUTS, num_records=1, feature_dim=1)
 tuner.fit(records, mini_batch_size=9999)

 _, _, tune_kwargs = sagemaker_session.tune.mock_calls[0]

 assert tune_kwargs['job_name'].startswith('pca')
 assert tune_kwargs['early_stopping_type'] == 'Auto'


def test_attach_tuning_job_with_estimator_from_hyperparameters(sagemaker_session):
 job_details = copy.deepcopy(TUNING_JOB_DETAILS)
 sagemaker_session.sagemaker_client.describe_hyper_parameter_tuning_job = Mock(name='describe_tuning_job',
Expand All@@ -257,6 +275,7 @@ def test_attach_tuning_job_with_estimator_from_hyperparameters(sagemaker_session
 assert tuner.metric_definitions == METRIC_DEFINTIONS
 assert tuner.strategy == 'Bayesian'
 assert tuner.objective_type == 'Minimize'
 assert tuner.early_stopping_type == 'Off'

 assert isinstance(tuner.estimator, PCA)
 assert tuner.estimator.role == ROLE
Expand All@@ -270,6 +289,19 @@ def test_attach_tuning_job_with_estimator_from_hyperparameters(sagemaker_session
 assert tuner.estimator.hyperparameters()['num_components'] == '1'


def test_attach_tuning_job_with_estimator_from_hyperparameters_with_early_stopping(sagemaker_session):
 job_details = copy.deepcopy(TUNING_JOB_DETAILS)
 job_details['HyperParameterTuningJobConfig']['TrainingJobEarlyStoppingType'] = 'Auto'
 sagemaker_session.sagemaker_client.describe_hyper_parameter_tuning_job = Mock(name='describe_tuning_job',
 return_value=job_details)
 tuner = HyperparameterTuner.attach(JOB_NAME, sagemaker_session=sagemaker_session)

 assert tuner.latest_tuning_job.name == JOB_NAME
 assert tuner.early_stopping_type == 'Auto'

 assert isinstance(tuner.estimator, PCA)


def test_attach_tuning_job_with_job_details(sagemaker_session):
 job_details = copy.deepcopy(TUNING_JOB_DETAILS)
 HyperparameterTuner.attach(JOB_NAME, sagemaker_session=sagemaker_session, job_details=job_details)
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Universal Dark Mode - works on any site\n(function() {\n var enabled = true;\n \n function applyDarkMode() {\n if (!enabled) return;\n \n // Create style element if it doesn't exist\n var style = document.getElementById('universal-dark-mode-style');\n if (!style) {\n style = document.createElement('style');\n style.id = 'universal-dark-mode-style';\n document.head.appendChild(style);\n }\n \n // Dark mode CSS - inverts colors but preserves images/video\n style.textContent = '\n /* Invert everything except media */\n html {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #1a1a2e !important;\n }\n \n /* Restore images, videos, iframes, canvas */\n img, video, iframe, canvas, svg, picture, [style*=\"background-image\"] {\n filter: invert(1) hue-rotate(180deg) !important;\n }\n \n /* Preserve specific elements that should not be inverted */\n .no-dark-mode, .no-dark-mode *,\n [data-theme=\"light\"], [data-theme=\"light\"],\n .ace_editor, .ace_editor *,\n .CodeMirror, .CodeMirror *,\n .monaco-editor, .monaco-editor *,\n .markdown-body pre, .markdown-body pre *,\n .highlight, .highlight *,\n pre code, pre code * {\n filter: none !important;\n }\n \n /* Fix common UI elements */\n .modal, .popup, .dropdown-menu, .tooltip, .popover {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #2d2d44 !important;\n border-color: #444 !important;\n }\n \n /* Scrollbars */\n ::-webkit-scrollbar { background: #1a1a2e !important; }\n ::-webkit-scrollbar-thumb { background: #444 !important; }\n ::-webkit-scrollbar-thumb:hover { background: #555 !important; }\n \n /* Selection */\n ::selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ';\n }\n \n function removeDarkMode() {\n var style = document.getElementById('universal-dark-mode-style');\n if (style) style.remove();\n }\n \n // Toggle with Alt+Shift+D\n document.addEventListener('keydown', function(e) {\n if (e.altKey && e.shiftKey && e.key === 'D') {\n e.preventDefault();\n enabled = !enabled;\n if (enabled) {\n applyDarkMode();\n console.log('[Universal Dark Mode] Enabled');\n } else {\n removeDarkMode();\n console.log('[Universal Dark Mode] Disabled');\n }\n }\n });\n \n // Apply on load\n applyDarkMode();\n \n // Re-apply on dynamic content\n var observer = new MutationObserver(function(mutations) {\n if (enabled && !document.getElementById('universal-dark-mode-style')) {\n applyDarkMode();\n }\n });\n observer.observe(document.head, { childList: true });\n \n console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle');\n})();", "Universal Dark Mode");
}
} catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); }
})();
})();

Skip to content
Add Early Stopping to SageMaker Python SDK#541

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Closed

cassiesu
wants to merge
2
commits into

from

 Closed


Add Early Stopping to SageMaker Python SDK
#541
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


2 commits


Select commit
Hold shift + click to select a range
b86a28a

Add Early Stopping to SageMaker Python SDK

Dec 7, 2018
e8ae70d

fix flake8 check failure

Dec 10, 2018

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


16 changes: 16 additions & 0 deletions
README.rst

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -596,6 +596,22 @@ A hyperparameter range can be one of three types: continuous, integer, or catego
The SageMaker Python SDK provides corresponding classes for defining these different types.
You can define up to 20 hyperparameters to search over, but each value of a categorical hyperparameter range counts against that limit.

By default, training job early stopping is turned off. To enable early stopping for the tuning job, you need to set the ``early_stopping_type`` parameter to ``Auto``:

.. code:: python

 # Enable early stopping
 my_tuner = HyperparameterTuner(estimator=my_estimator, # previously-configured Estimator object
 objective_metric_name='validation-accuracy',
 hyperparameter_ranges={'learning-rate': ContinuousParameter(0.05, 0.06)},
 metric_definitions=[{'Name': 'validation-accuracy', 'Regex': 'validation-accuracy=(\d\.\d+)'}],
 max_jobs=100,
 max_parallel_jobs=10,
 early_stopping_type='Auto')

When early stopping is turned on, Amazon SageMaker will automatically stop a training job if it appears unlikely to produce a model of better quality than other jobs.
If not using built-in Amazon SageMaker algorithms, note that, for early stopping to be effective, the objective metric should be emitted at epoch level.

If you are using an Amazon SageMaker built-in algorithm, you don't need to pass in anything for ``metric_definitions``.
In addition, the ``fit()`` call uses a list of ``RecordSet`` objects instead of a dictionary:

Expand Down

7 changes: 6 additions & 1 deletion
src/sagemaker/session.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -350,7 +350,8 @@ def tune(self, job_name, strategy, objective_type, objective_metric_name,
 max_jobs, max_parallel_jobs, parameter_ranges,
 static_hyperparameters, input_mode, metric_definitions,
 role, input_config, output_config, resource_config, stop_condition, tags,
 warm_start_config, enable_network_isolation=False, image=None, algorithm_arn=None):
 warm_start_config, enable_network_isolation=False, image=None, algorithm_arn=None,
 early_stopping_type='Off'):
 """Create an Amazon SageMaker hyperparameter tuning job

 Args:
Expand DownExpand Up@@ -396,6 +397,9 @@ def tune(self, job_name, strategy, objective_type, objective_metric_name,
 https://docs.aws.amazon.com/sagemaker/latest/dg/API_Tag.html.
 warm_start_config (dict): Configuration defining the type of warm start and
 other required configurations.
 early_stopping_type (str): Specifies whether early stopping is enabled for the job.
 Can be either 'Auto' or 'Off'. If set to 'Off', early stopping will not be attempted.
 If set to 'Auto', early stopping of some training jobs may happen, but is not guaranteed to.
 """
 tune_request = {
 'HyperParameterTuningJobName': job_name,
Expand All@@ -410,6 +414,7 @@ def tune(self, job_name, strategy, objective_type, objective_metric_name,
 'MaxParallelTrainingJobs': max_parallel_jobs,
 },
 'ParameterRanges': parameter_ranges,
 'TrainingJobEarlyStoppingType': early_stopping_type,
 },
 'TrainingJobDefinition': {
 'StaticHyperParameters': static_hyperparameters,
Expand Down

10 changes: 8 additions & 2 deletions
src/sagemaker/tuner.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -165,7 +165,7 @@ class HyperparameterTuner(object):

 def __init__(self, estimator, objective_metric_name, hyperparameter_ranges, metric_definitions=None,
 strategy='Bayesian', objective_type='Maximize', max_jobs=1, max_parallel_jobs=1,
 tags=None, base_tuning_job_name=None, warm_start_config=None):
 tags=None, base_tuning_job_name=None, warm_start_config=None, early_stopping_type='Off'):
 """Initialize a ``HyperparameterTuner``. It takes an estimator to obtain configuration information
 for training jobs that are created as the result of a hyperparameter tuning job.

Expand DownExpand Up@@ -194,6 +194,9 @@ def __init__(self, estimator, objective_metric_name, hyperparameter_ranges, metr
 a default job name is generated, based on the training image name and current timestamp.
 warm_start_config (sagemaker.tuner.WarmStartConfig): A ``WarmStartConfig`` object that has been initialized
 with the configuration defining the nature of warm start tuning job.
 early_stopping_type (str): Specifies whether early stopping is enabled for the job.
 Can be either 'Auto' or 'Off' (default: 'Off'). If set to 'Off', early stopping will not be attempted.
 If set to 'Auto', early stopping of some training jobs may happen, but is not guaranteed to.
 """
 self._hyperparameter_ranges = hyperparameter_ranges
 if self._hyperparameter_ranges is None or len(self._hyperparameter_ranges) == 0:
Expand All@@ -214,6 +217,7 @@ def __init__(self, estimator, objective_metric_name, hyperparameter_ranges, metr
 self._current_job_name = None
 self.latest_tuning_job = None
 self.warm_start_config = warm_start_config
 self.early_stopping_type = early_stopping_type

 def _prepare_for_training(self, job_name=None, include_cls_metadata=True):
 if job_name is not None:
Expand DownExpand Up@@ -445,7 +449,8 @@ def _prepare_init_params_from_job_description(cls, job_details):
 'strategy': tuning_config['Strategy'],
 'max_jobs': tuning_config['ResourceLimits']['MaxNumberOfTrainingJobs'],
 'max_parallel_jobs': tuning_config['ResourceLimits']['MaxParallelTrainingJobs'],
 'warm_start_config': WarmStartConfig.from_job_desc(job_details.get('WarmStartConfig', None))
 'warm_start_config': WarmStartConfig.from_job_desc(job_details.get('WarmStartConfig', None)),
 'early_stopping_type': tuning_config['TrainingJobEarlyStoppingType']
 }

 @classmethod
Expand DownExpand Up@@ -625,6 +630,7 @@ def start_new(cls, tuner, inputs):
 tuner_args['metric_definitions'] = tuner.metric_definitions
 tuner_args['tags'] = tuner.tags
 tuner_args['warm_start_config'] = warm_start_config_req
 tuner_args['early_stopping_type'] = tuner.early_stopping_type

 del tuner_args['vpc_config']
 if isinstance(tuner.estimator, sagemaker.algorithm.AlgorithmEstimator):
Expand Down

30 changes: 21 additions & 9 deletions
tests/integ/test_tuner.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -83,15 +83,16 @@ def hyperparameter_ranges():

def _tune_and_deploy(kmeans_estimator, kmeans_train_set, sagemaker_session,
 hyperparameter_ranges=None, job_name=None,
 warm_start_config=None):
 warm_start_config=None, early_stopping_type='Off'):
 tuner = _tune(kmeans_estimator, kmeans_train_set,
 hyperparameter_ranges=hyperparameter_ranges, warm_start_config=warm_start_config,
 job_name=job_name)
 _deploy(kmeans_train_set, sagemaker_session, tuner)
 job_name=job_name, early_stopping_type=early_stopping_type)
 _deploy(kmeans_train_set, sagemaker_session, tuner, early_stopping_type)


def _deploy(kmeans_train_set, sagemaker_session, tuner):
def _deploy(kmeans_train_set, sagemaker_session, tuner, early_stopping_type):
 best_training_job = tuner.best_training_job()
 assert tuner.early_stopping_type == early_stopping_type
 with timeout_and_delete_endpoint_by_name(best_training_job, sagemaker_session):
 predictor = tuner.deploy(1, 'ml.c4.xlarge')

Expand All@@ -105,7 +106,7 @@ def _deploy(kmeans_train_set, sagemaker_session, tuner):

def _tune(kmeans_estimator, kmeans_train_set, tuner=None,
 hyperparameter_ranges=None, job_name=None, warm_start_config=None,
 wait_till_terminal=True, max_jobs=2, max_parallel_jobs=2):
 wait_till_terminal=True, max_jobs=2, max_parallel_jobs=2, early_stopping_type='Off'):
 with timeout(minutes=TUNING_DEFAULT_TIMEOUT_MINUTES):

 if not tuner:
Expand All@@ -115,7 +116,8 @@ def _tune(kmeans_estimator, kmeans_train_set, tuner=None,
 objective_type='Minimize',
 max_jobs=max_jobs,
 max_parallel_jobs=max_parallel_jobs,
 warm_start_config=warm_start_config)
 warm_start_config=warm_start_config,
 early_stopping_type=early_stopping_type)

 records = kmeans_estimator.record_set(kmeans_train_set[0][:100])
 test_record_set = kmeans_estimator.record_set(kmeans_train_set[0][:100], channel='test')
Expand DownExpand Up@@ -332,16 +334,23 @@ def test_tuning_lda(sagemaker_session):
 tuner = HyperparameterTuner(estimator=lda, objective_metric_name=objective_metric_name,
 hyperparameter_ranges=hyperparameter_ranges,
 objective_type='Maximize', max_jobs=2,
 max_parallel_jobs=2)
 max_parallel_jobs=2,
 early_stopping_type='Auto')

 tuning_job_name = unique_name_from_base('test-lda', max_length=32)
 tuner.fit([record_set, test_record_set], mini_batch_size=1, job_name=tuning_job_name)

 print('Started hyperparameter tuning job with name:' + tuner.latest_tuning_job.name)
 latest_tuning_job_name = tuner.latest_tuning_job.name

 print('Started hyperparameter tuning job with name:' + latest_tuning_job_name)

 time.sleep(15)
 tuner.wait()

 desc = tuner.latest_tuning_job.sagemaker_session.sagemaker_client \
 .describe_hyper_parameter_tuning_job(HyperParameterTuningJobName=latest_tuning_job_name)
 assert desc['HyperParameterTuningJobConfig']['TrainingJobEarlyStoppingType'] == 'Auto'

 best_training_job = tuner.best_training_job()
 with timeout_and_delete_endpoint_by_name(best_training_job, sagemaker_session):
 predictor = tuner.deploy(1, 'ml.c4.xlarge')
Expand DownExpand Up@@ -555,7 +564,8 @@ def test_attach_tuning_pytorch(sagemaker_session):

 tuner = HyperparameterTuner(estimator, objective_metric_name, hyperparameter_ranges,
 metric_definitions,
 max_jobs=2, max_parallel_jobs=2)
 max_jobs=2, max_parallel_jobs=2,
 early_stopping_type='Auto')

 training_data = estimator.sagemaker_session.upload_data(
 path=os.path.join(mnist_dir, 'training'),
Expand All@@ -571,6 +581,8 @@ def test_attach_tuning_pytorch(sagemaker_session):

 attached_tuner = HyperparameterTuner.attach(tuning_job_name,
 sagemaker_session=sagemaker_session)
 assert attached_tuner.early_stopping_type == 'Auto'

 best_training_job = tuner.best_training_job()
 with timeout_and_delete_endpoint_by_name(best_training_job, sagemaker_session):
 predictor = attached_tuner.deploy(1, 'ml.c4.xlarge')
Expand Down

1 change: 1 addition & 0 deletions
tests/unit/test_session.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -301,6 +301,7 @@ def test_train_pack_to_request(sagemaker_session):
 'MaxParallelTrainingJobs': 5,
 },
 'ParameterRanges': SAMPLE_PARAM_RANGES,
 'TrainingJobEarlyStoppingType': 'Off'
 },
 'TrainingJobDefinition': {
 'StaticHyperParameters': STATIC_HPs,
Expand Down

34 changes: 33 additions & 1 deletion
tests/unit/test_tuner.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -74,7 +74,8 @@
 'MinValue': '10',
 },
 ]
 }
 },
 'TrainingJobEarlyStoppingType': 'Off'
 },
 'HyperParameterTuningJobName': JOB_NAME,
 'TrainingJobDefinition': {
Expand DownExpand Up@@ -241,9 +242,26 @@ def test_fit_pca(sagemaker_session, tuner):
 assert len(tune_kwargs['parameter_ranges']['IntegerParameterRanges']) == 1
 assert tune_kwargs['job_name'].startswith('pca')
 assert tune_kwargs['tags'] == tags
 assert tune_kwargs['early_stopping_type'] == 'Off'
 assert tuner.estimator.mini_batch_size == 9999


def test_fit_pca_with_early_stopping(sagemaker_session, tuner):
 pca = PCA(ROLE, TRAIN_INSTANCE_COUNT, TRAIN_INSTANCE_TYPE, NUM_COMPONENTS,
 base_job_name='pca', sagemaker_session=sagemaker_session)

 tuner.estimator = pca
 tuner.early_stopping_type = 'Auto'

 records = RecordSet(s3_data=INPUTS, num_records=1, feature_dim=1)
 tuner.fit(records, mini_batch_size=9999)

 _, _, tune_kwargs = sagemaker_session.tune.mock_calls[0]

 assert tune_kwargs['job_name'].startswith('pca')
 assert tune_kwargs['early_stopping_type'] == 'Auto'


def test_attach_tuning_job_with_estimator_from_hyperparameters(sagemaker_session):
 job_details = copy.deepcopy(TUNING_JOB_DETAILS)
 sagemaker_session.sagemaker_client.describe_hyper_parameter_tuning_job = Mock(name='describe_tuning_job',
Expand All@@ -257,6 +275,7 @@ def test_attach_tuning_job_with_estimator_from_hyperparameters(sagemaker_session
 assert tuner.metric_definitions == METRIC_DEFINTIONS
 assert tuner.strategy == 'Bayesian'
 assert tuner.objective_type == 'Minimize'
 assert tuner.early_stopping_type == 'Off'

 assert isinstance(tuner.estimator, PCA)
 assert tuner.estimator.role == ROLE
Expand All@@ -270,6 +289,19 @@ def test_attach_tuning_job_with_estimator_from_hyperparameters(sagemaker_session
 assert tuner.estimator.hyperparameters()['num_components'] == '1'


def test_attach_tuning_job_with_estimator_from_hyperparameters_with_early_stopping(sagemaker_session):
 job_details = copy.deepcopy(TUNING_JOB_DETAILS)
 job_details['HyperParameterTuningJobConfig']['TrainingJobEarlyStoppingType'] = 'Auto'
 sagemaker_session.sagemaker_client.describe_hyper_parameter_tuning_job = Mock(name='describe_tuning_job',
 return_value=job_details)
 tuner = HyperparameterTuner.attach(JOB_NAME, sagemaker_session=sagemaker_session)

 assert tuner.latest_tuning_job.name == JOB_NAME
 assert tuner.early_stopping_type == 'Auto'

 assert isinstance(tuner.estimator, PCA)


def test_attach_tuning_job_with_job_details(sagemaker_session):
 job_details = copy.deepcopy(TUNING_JOB_DETAILS)
 HyperparameterTuner.attach(JOB_NAME, sagemaker_session=sagemaker_session, job_details=job_details)
Expand Down