def test_warn_if_parameter_server_with_local_multi_gpu(caplog):
instance_type = "local_gpu"
distribution = {"parameter_server": {"enabled": True}}
fw_utils.warn_if_parameter_server_with_multi_gpu(
training_instance_type=instance_type, distribution=distribution)
assert fw_utils.PARAMETER_SERVER_MULTI_GPU_WARNING in caplog.text
def test_warn_if_parameter_server_with_multi_gpu(caplog):
train_instance_type = "ml.p2.8xlarge"
distributions = {"parameter_server": {"enabled": True}}
fw_utils.warn_if_parameter_server_with_multi_gpu(
training_instance_type=train_instance_type,
distributions=distributions)
assert fw_utils.PARAMETER_SERVER_MULTI_GPU_WARNING in caplog.text
def __init__(
self,
py_version,
entry_point,
transformers_version=None,
tensorflow_version=None,
pytorch_version=None,
source_dir=None,
hyperparameters=None,
image_uri=None,
distribution=None,
**kwargs
):
"""This ``Estimator`` executes a HuggingFace script in a managed execution environment.
The managed HuggingFace environment is an Amazon-built Docker container that executes
functions defined in the supplied ``entry_point`` Python script within a SageMaker
Training Job.
Training is started by calling
:meth:`~sagemaker.amazon.estimator.Framework.fit` on this Estimator.
Args:
py_version (str): Python version you want to use for executing your model training
code. Defaults to ``None``. Required unless ``image_uri`` is provided. List
of supported versions:
https://github.com/aws/sagemaker-python-sdk#huggingface-sagemaker-estimators
entry_point (str): Path (absolute or relative) to the Python source
file which should be executed as the entry point to training.
If ``source_dir`` is specified, then ``entry_point``
must point to a file located at the root of ``source_dir``.
transformers_version (str): Transformers version you want to use for
executing your model training code. Defaults to ``None``. Required unless
``image_uri`` is provided. List of supported versions:
https://github.com/aws/sagemaker-python-sdk#huggingface-sagemaker-estimators.
tensorflow_version (str): TensorFlow version you want to use for
executing your model training code. Defaults to ``None``. Required unless
``pytorch_version`` is provided. List of supported versions:
https://github.com/aws/sagemaker-python-sdk#huggingface-sagemaker-estimators.
pytorch_version (str): PyTorch version you want to use for
executing your model training code. Defaults to ``None``. Required unless
``tensorflow_version`` is provided. List of supported versions:
https://github.com/aws/sagemaker-python-sdk#huggingface-sagemaker-estimators.
source_dir (str): Path (absolute, relative or an S3 URI) to a directory
with any other training source code dependencies aside from the entry
point file (default: None). If ``source_dir`` is an S3 URI, it must
point to a tar.gz file. Structure within this directory are preserved
when training on Amazon SageMaker.
hyperparameters (dict): Hyperparameters that will be used for
training (default: None). The hyperparameters are made
accessible as a dict[str, str] to the training code on
SageMaker. For convenience, this accepts other types for keys
and values, but ``str()`` will be called to convert them before
training.
image_uri (str): If specified, the estimator will use this image
for training and hosting, instead of selecting the appropriate
SageMaker official image based on framework_version and
py_version. It can be an ECR url or dockerhub image and tag.
Examples:
* ``123412341234.dkr.ecr.us-west-2.amazonaws.com/my-custom-image:1.0``
* ``custom-image:latest``
If ``framework_version`` or ``py_version`` are ``None``, then
``image_uri`` is required. If also ``None``, then a ``ValueError``
will be raised.
distribution (dict): A dictionary with information on how to run distributed training
(default: None). Currently, the following are supported:
distributed training with parameter servers, SageMaker Distributed (SMD) Data
and Model Parallelism, and MPI. SMD Model Parallelism can only be used with MPI.
To enable parameter server use the following setup:
.. code:: python
{
"parameter_server": {
"enabled": True
}
}
To enable MPI:
.. code:: python
{
"mpi": {
"enabled": True
}
}
To enable SMDistributed Data Parallel or Model Parallel:
.. code:: python
{
"smdistributed": {
"dataparallel": {
"enabled": True
},
"modelparallel": {
"enabled": True,
"parameters": {}
}
}
}
**kwargs: Additional kwargs passed to the :class:`~sagemaker.estimator.Framework`
constructor.
.. tip::
You can find additional parameters for initializing this class at
:class:`~sagemaker.estimator.Framework` and
:class:`~sagemaker.estimator.EstimatorBase`.
"""
self.framework_version = transformers_version
self.py_version = py_version
self.tensorflow_version = tensorflow_version
self.pytorch_version = pytorch_version
self._validate_args(image_uri=image_uri)
if distribution is not None:
instance_type = renamed_kwargs(
"train_instance_type", "instance_type", kwargs.get("instance_type"), kwargs
)
base_framework_name = "tensorflow" if tensorflow_version is not None else "pytorch"
base_framework_version = (
tensorflow_version if tensorflow_version is not None else pytorch_version
)
validate_smdistributed(
instance_type=instance_type,
framework_name=base_framework_name,
framework_version=base_framework_version,
py_version=self.py_version,
distribution=distribution,
image_uri=image_uri,
)
warn_if_parameter_server_with_multi_gpu(
training_instance_type=instance_type, distribution=distribution
)
if "enable_sagemaker_metrics" not in kwargs:
kwargs["enable_sagemaker_metrics"] = True
super(HuggingFace, self).__init__(
entry_point, source_dir, hyperparameters, image_uri=image_uri, **kwargs
)
self.distribution = distribution or {}
def __init__(self,
py_version=None,
framework_version=None,
model_dir=None,
image_uri=None,
distribution=None,
**kwargs):
"""Initialize a ``TensorFlow`` estimator.
Args:
py_version (str): Python version you want to use for executing your model training
code. Defaults to ``None``. Required unless ``image_uri`` is provided.
framework_version (str): TensorFlow version you want to use for executing your model
training code. Defaults to ``None``. Required unless ``image_uri`` is provided.
List of supported versions:
https://github.com/aws/sagemaker-python-sdk#tensorflow-sagemaker-estimators.
model_dir (str): S3 location where the checkpoint data and models can be exported to
during training (default: None). It will be passed in the training script as one of
the command line arguments. If not specified, one is provided based on
your training configuration:
* *distributed training with SMDistributed or MPI with Horovod* - ``/opt/ml/model``
* *single-machine training or distributed training without MPI* - \
``s3://{output_path}/model``
* *Local Mode with local sources (file:// instead of s3://)* - \
``/opt/ml/shared/model``
To disable having ``model_dir`` passed to your training script,
set ``model_dir=False``.
image_uri (str): If specified, the estimator will use this image for training and
hosting, instead of selecting the appropriate SageMaker official image based on
framework_version and py_version. It can be an ECR url or dockerhub image and tag.
Examples:
123.dkr.ecr.us-west-2.amazonaws.com/my-custom-image:1.0
custom-image:latest.
If ``framework_version`` or ``py_version`` are ``None``, then
``image_uri`` is required. If also ``None``, then a ``ValueError``
will be raised.
distribution (dict): A dictionary with information on how to run distributed training
(default: None). Currently, the following are supported:
distributed training with parameter servers, SageMaker Distributed (SMD) Data
and Model Parallelism, and MPI. SMD Model Parallelism can only be used with MPI.
To enable parameter server use the following setup:
.. code:: python
{
"parameter_server": {
"enabled": True
}
}
To enable MPI:
.. code:: python
{
"mpi": {
"enabled": True
}
}
To enable SMDistributed Data Parallel or Model Parallel:
.. code:: python
{
"smdistributed": {
"dataparallel": {
"enabled": True
},
"modelparallel": {
"enabled": True,
"parameters": {}
}
}
}
**kwargs: Additional kwargs passed to the Framework constructor.
.. tip::
You can find additional parameters for initializing this class at
:class:`~sagemaker.estimator.Framework` and
:class:`~sagemaker.estimator.EstimatorBase`.
"""
distribution = renamed_kwargs("distributions", "distribution",
distribution, kwargs)
instance_type = renamed_kwargs("train_instance_type", "instance_type",
kwargs.get("instance_type"), kwargs)
fw.validate_version_or_image_args(framework_version, py_version,
image_uri)
if py_version == "py2":
logger.warning(
fw.python_deprecation_warning(self._framework_name,
defaults.LATEST_PY2_VERSION))
self.framework_version = framework_version
self.py_version = py_version
self.instance_type = instance_type
if distribution is not None:
fw.warn_if_parameter_server_with_multi_gpu(
training_instance_type=instance_type,
distribution=distribution)
fw.validate_smdistributed(
instance_type=instance_type,
framework_name=self._framework_name,
framework_version=framework_version,
py_version=py_version,
distribution=distribution,
image_uri=image_uri,
)
if "enable_sagemaker_metrics" not in kwargs:
# enable sagemaker metrics for TF v1.15 or greater:
if framework_version and version.Version(
framework_version) >= version.Version("1.15"):
kwargs["enable_sagemaker_metrics"] = True
super(TensorFlow, self).__init__(image_uri=image_uri, **kwargs)
self.model_dir = model_dir
self.distribution = distribution or {}
self._validate_args(py_version=py_version)
def __init__(self,
training_steps=None,
evaluation_steps=None,
checkpoint_path=None,
py_version=None,
framework_version=None,
model_dir=None,
requirements_file="",
image_name=None,
script_mode=False,
distributions=None,
**kwargs):
"""Initialize a ``TensorFlow`` estimator.
Args:
training_steps (int): Perform this many steps of training. `None`, the default means
train forever.
evaluation_steps (int): Perform this many steps of evaluation. `None`, the default
means that evaluation runs until input from eval_input_fn is exhausted (or another
exception is raised).
checkpoint_path (str): Identifies S3 location where checkpoint data during model
training can be saved (default: None). For distributed model training, this
parameter is required.
py_version (str): Python version you want to use for executing your model training
code (default: 'py2').
framework_version (str): TensorFlow version you want to use for executing your model
training code. If not specified, this will default to 1.11.
model_dir (str): S3 location where the checkpoint data and models can be exported to
during training (default: None). It will be passed in the training script as one of
the command line arguments. If not specified, one is provided based on
your training configuration:
* *distributed training with MPI* - ``/opt/ml/model``
* *single-machine training or distributed training without MPI* - \
``s3://{output_path}/model``
* *Local Mode with local sources (file:// instead of s3://)* - \
``/opt/ml/shared/model``
requirements_file (str): Path to a ``requirements.txt`` file (default: ''). The path
should be within and relative to ``source_dir``. Details on the format can be
found in the Pip User Guide:
<https://pip.pypa.io/en/stable/reference/pip_install/#requirements-file-format>
image_name (str): If specified, the estimator will use this image for training and
hosting, instead of selecting the appropriate SageMaker official image based on
framework_version and py_version. It can be an ECR url or dockerhub image and tag.
Examples:
123.dkr.ecr.us-west-2.amazonaws.com/my-custom-image:1.0
custom-image:latest.
script_mode (bool): If set to True will the estimator will use the Script Mode
containers (default: False). This will be ignored if py_version is set to 'py3'.
distributions (dict): A dictionary with information on how to run distributed training
(default: None). Currently we support distributed training with parameter servers
and MPI.
To enable parameter server use the following setup:
.. code:: python
{
'parameter_server':
{
'enabled': True
}
}
To enable MPI:
.. code:: python
{
'mpi':
{
'enabled': True
}
}
**kwargs: Additional kwargs passed to the Framework constructor.
.. tip::
You can find additional parameters for initializing this class at
:class:`~sagemaker.estimator.Framework` and
:class:`~sagemaker.estimator.EstimatorBase`.
"""
if framework_version is None:
logger.warning(
fw.empty_framework_version_warning(defaults.TF_VERSION,
self.LATEST_VERSION))
self.framework_version = framework_version or defaults.TF_VERSION
if not py_version:
py_version = "py3" if self._only_python_3_supported() else "py2"
if py_version == "py2":
logger.warning(
fw.python_deprecation_warning(self.__framework_name__,
defaults.LATEST_PY2_VERSION))
if distributions is not None:
logger.warning(
fw.parameter_v2_rename_warning("distribution", distributions))
train_instance_type = kwargs.get("train_instance_type")
fw.warn_if_parameter_server_with_multi_gpu(
training_instance_type=train_instance_type,
distributions=distributions)
if "enable_sagemaker_metrics" not in kwargs:
# enable sagemaker metrics for TF v1.15 or greater:
if fw.is_version_equal_or_higher([1, 15], self.framework_version):
kwargs["enable_sagemaker_metrics"] = True
super(TensorFlow, self).__init__(image_name=image_name, **kwargs)
self.checkpoint_path = checkpoint_path
self.py_version = py_version
self.training_steps = training_steps
self.evaluation_steps = evaluation_steps
self.model_dir = model_dir
self.script_mode = script_mode
self.distributions = distributions or {}
self._validate_args(
py_version=py_version,
script_mode=script_mode,
framework_version=self.framework_version,
training_steps=training_steps,
evaluation_steps=evaluation_steps,
requirements_file=requirements_file,
checkpoint_path=checkpoint_path,
)
self._validate_requirements_file(requirements_file)
self.requirements_file = requirements_file
def __init__(self,
entry_point,
framework_version=None,
py_version=None,
source_dir=None,
hyperparameters=None,
image_uri=None,
distribution=None,
**kwargs):
"""This ``Estimator`` executes an PyTorch script in a managed PyTorch
execution environment, within a SageMaker Training Job. The managed
PyTorch environment is an Amazon-built Docker container that executes
functions defined in the supplied ``entry_point`` Python script.
Training is started by calling
:meth:`~sagemaker.amazon.estimator.Framework.fit` on this Estimator.
After training is complete, calling
:meth:`~sagemaker.amazon.estimator.Framework.deploy` creates a hosted
SageMaker endpoint and returns an
:class:`~sagemaker.amazon.pytorch.model.PyTorchPredictor` instance that
can be used to perform inference against the hosted model.
Technical documentation on preparing PyTorch scripts for SageMaker
training and using the PyTorch Estimator is available on the project
home-page: https://github.com/aws/sagemaker-python-sdk
Args:
entry_point (str): Path (absolute or relative) to the Python source
file which should be executed as the entry point to training.
If ``source_dir`` is specified, then ``entry_point``
must point to a file located at the root of ``source_dir``.
framework_version (str): PyTorch version you want to use for
executing your model training code. Defaults to ``None``. Required unless
``image_uri`` is provided. List of supported versions:
https://github.com/aws/sagemaker-python-sdk#pytorch-sagemaker-estimators.
py_version (str): Python version you want to use for executing your
model training code. One of 'py2' or 'py3'. Defaults to ``None``. Required
unless ``image_uri`` is provided.
source_dir (str): Path (absolute, relative or an S3 URI) to a directory
with any other training source code dependencies aside from the entry
point file (default: None). If ``source_dir`` is an S3 URI, it must
point to a tar.gz file. Structure within this directory are preserved
when training on Amazon SageMaker.
hyperparameters (dict): Hyperparameters that will be used for
training (default: None). The hyperparameters are made
accessible as a dict[str, str] to the training code on
SageMaker. For convenience, this accepts other types for keys
and values, but ``str()`` will be called to convert them before
training.
image_uri (str): If specified, the estimator will use this image
for training and hosting, instead of selecting the appropriate
SageMaker official image based on framework_version and
py_version. It can be an ECR url or dockerhub image and tag.
Examples:
* ``123412341234.dkr.ecr.us-west-2.amazonaws.com/my-custom-image:1.0``
* ``custom-image:latest``
If ``framework_version`` or ``py_version`` are ``None``, then
``image_uri`` is required. If also ``None``, then a ``ValueError``
will be raised.
distribution (dict): A dictionary with information on how to run distributed training
(default: None). Currently, the following are supported:
distributed training with parameter servers, SageMaker Distributed (SMD) Data
and Model Parallelism, and MPI. SMD Model Parallelism can only be used with MPI.
To enable parameter server use the following setup:
.. code:: python
{
"parameter_server": {
"enabled": True
}
}
To enable MPI:
.. code:: python
{
"mpi": {
"enabled": True
}
}
To enable SMDistributed Data Parallel or Model Parallel:
.. code:: python
{
"smdistributed": {
"dataparallel": {
"enabled": True
},
"modelparallel": {
"enabled": True,
"parameters": {}
}
}
}
**kwargs: Additional kwargs passed to the :class:`~sagemaker.estimator.Framework`
constructor.
.. tip::
You can find additional parameters for initializing this class at
:class:`~sagemaker.estimator.Framework` and
:class:`~sagemaker.estimator.EstimatorBase`.
"""
validate_version_or_image_args(framework_version, py_version,
image_uri)
if py_version == "py2":
logger.warning(
python_deprecation_warning(self._framework_name,
defaults.LATEST_PY2_VERSION))
self.framework_version = framework_version
self.py_version = py_version
if distribution is not None:
instance_type = renamed_kwargs("train_instance_type",
"instance_type",
kwargs.get("instance_type"), kwargs)
validate_smdistributed(
instance_type=instance_type,
framework_name=self._framework_name,
framework_version=framework_version,
py_version=py_version,
distribution=distribution,
image_uri=image_uri,
)
warn_if_parameter_server_with_multi_gpu(
training_instance_type=instance_type,
distribution=distribution)
if "enable_sagemaker_metrics" not in kwargs:
# enable sagemaker metrics for PT v1.3 or greater:
if self.framework_version and Version(
self.framework_version) >= Version("1.3"):
kwargs["enable_sagemaker_metrics"] = True
super(PyTorch, self).__init__(entry_point,
source_dir,
hyperparameters,
image_uri=image_uri,
**kwargs)
self.distribution = distribution or {}
def __init__(self,
entry_point,
source_dir=None,
hyperparameters=None,
py_version="py2",
framework_version=None,
image_name=None,
distributions=None,
**kwargs):
"""This ``Estimator`` executes an MXNet script in a managed MXNet
execution environment, within a SageMaker Training Job. The managed
MXNet environment is an Amazon-built Docker container that executes
functions defined in the supplied ``entry_point`` Python script.
Training is started by calling
:meth:`~sagemaker.amazon.estimator.Framework.fit` on this Estimator.
After training is complete, calling
:meth:`~sagemaker.amazon.estimator.Framework.deploy` creates a hosted
SageMaker endpoint and returns an
:class:`~sagemaker.amazon.mxnet.model.MXNetPredictor` instance that can
be used to perform inference against the hosted model.
Technical documentation on preparing MXNet scripts for SageMaker
training and using the MXNet Estimator is available on the project
home-page: https://github.com/aws/sagemaker-python-sdk
Args:
entry_point (str): Path (absolute or relative) to the Python source
file which should be executed as the entry point to training.
This should be compatible with either Python 2.7 or Python 3.5.
source_dir (str): Path (absolute or relative) to a directory with
any other training source code dependencies aside from the entry
point file (default: None). Structure within this directory are
preserved when training on Amazon SageMaker.
hyperparameters (dict): Hyperparameters that will be used for
training (default: None). The hyperparameters are made
accessible as a dict[str, str] to the training code on
SageMaker. For convenience, this accepts other types for keys
and values, but ``str()`` will be called to convert them before
training.
py_version (str): Python version you want to use for executing your
model training code (default: 'py2'). One of 'py2' or 'py3'.
framework_version (str): MXNet version you want to use for executing
your model training code. List of supported versions
https://github.com/aws/sagemaker-python-sdk#mxnet-sagemaker-estimators.
If not specified, this will default to 1.2.1.
image_name (str): If specified, the estimator will use this image for training and
hosting, instead of selecting the appropriate SageMaker official image based on
framework_version and py_version. It can be an ECR url or dockerhub image and tag.
Examples:
* ``123412341234.dkr.ecr.us-west-2.amazonaws.com/my-custom-image:1.0``
* ``custom-image:latest``
distributions (dict): A dictionary with information on how to run distributed
training (default: None). To have parameter servers launched for training,
set this value to be ``{'parameter_server': {'enabled': True}}``.
**kwargs: Additional kwargs passed to the
:class:`~sagemaker.estimator.Framework` constructor.
.. tip::
You can find additional parameters for initializing this class at
:class:`~sagemaker.estimator.Framework` and
:class:`~sagemaker.estimator.EstimatorBase`.
"""
if framework_version is None:
logger.warning(
empty_framework_version_warning(defaults.MXNET_VERSION,
self.LATEST_VERSION))
self.framework_version = framework_version or defaults.MXNET_VERSION
if "enable_sagemaker_metrics" not in kwargs:
# enable sagemaker metrics for MXNet v1.6 or greater:
if is_version_equal_or_higher([1, 6], self.framework_version):
kwargs["enable_sagemaker_metrics"] = True
super(MXNet, self).__init__(entry_point,
source_dir,
hyperparameters,
image_name=image_name,
**kwargs)
if py_version == "py2":
logger.warning(
python_deprecation_warning(self.__framework_name__,
defaults.LATEST_PY2_VERSION))
if distributions is not None:
train_instance_type = kwargs.get("train_instance_type")
warn_if_parameter_server_with_multi_gpu(
training_instance_type=train_instance_type,
distributions=distributions)
self.py_version = py_version
self._configure_distribution(distributions)
def __init__(
self,
py_version,
entry_point,
transformers_version=None,
tensorflow_version=None,
pytorch_version=None,
source_dir=None,
hyperparameters=None,
image_uri=None,
distribution=None,
compiler_config=None,
**kwargs,
):
"""This estimator runs a Hugging Face training script in a SageMaker training environment.
The estimator initiates the SageMaker-managed Hugging Face environment
by using the pre-built Hugging Face Docker container and runs
the Hugging Face training script that user provides through
the ``entry_point`` argument.
After configuring the estimator class, use the class method
:meth:`~sagemaker.amazon.estimator.Framework.fit()` to start a training job.
Args:
py_version (str): Python version you want to use for executing your model training
code. Defaults to ``None``. Required unless ``image_uri`` is provided. If
using PyTorch, the current supported version is ``py36``. If using TensorFlow,
the current supported version is ``py37``.
entry_point (str): Path (absolute or relative) to the Python source
file which should be executed as the entry point to training.
If ``source_dir`` is specified, then ``entry_point``
must point to a file located at the root of ``source_dir``.
transformers_version (str): Transformers version you want to use for
executing your model training code. Defaults to ``None``. Required unless
``image_uri`` is provided. The current supported version is ``4.6.1``.
tensorflow_version (str): TensorFlow version you want to use for
executing your model training code. Defaults to ``None``. Required unless
``pytorch_version`` is provided. The current supported version is ``2.4.1``.
pytorch_version (str): PyTorch version you want to use for
executing your model training code. Defaults to ``None``. Required unless
``tensorflow_version`` is provided. The current supported versions are ``1.7.1`` and ``1.6.0``.
source_dir (str): Path (absolute, relative or an S3 URI) to a directory
with any other training source code dependencies aside from the entry
point file (default: None). If ``source_dir`` is an S3 URI, it must
point to a tar.gz file. Structure within this directory are preserved
when training on Amazon SageMaker.
hyperparameters (dict): Hyperparameters that will be used for
training (default: None). The hyperparameters are made
accessible as a dict[str, str] to the training code on
SageMaker. For convenience, this accepts other types for keys
and values, but ``str()`` will be called to convert them before
training.
image_uri (str): If specified, the estimator will use this image
for training and hosting, instead of selecting the appropriate
SageMaker official image based on framework_version and
py_version. It can be an ECR url or dockerhub image and tag.
Examples:
* ``123412341234.dkr.ecr.us-west-2.amazonaws.com/my-custom-image:1.0``
* ``custom-image:latest``
If ``framework_version`` or ``py_version`` are ``None``, then
``image_uri`` is required. If also ``None``, then a ``ValueError``
will be raised.
distribution (dict): A dictionary with information on how to run distributed training
(default: None). Currently, the following are supported:
distributed training with parameter servers, SageMaker Distributed (SMD) Data
and Model Parallelism, and MPI. SMD Model Parallelism can only be used with MPI.
To enable parameter server use the following setup:
.. code:: python
{
"parameter_server": {
"enabled": True
}
}
To enable MPI:
.. code:: python
{
"mpi": {
"enabled": True
}
}
To enable SMDistributed Data Parallel or Model Parallel:
.. code:: python
{
"smdistributed": {
"dataparallel": {
"enabled": True
},
"modelparallel": {
"enabled": True,
"parameters": {}
}
}
}
compiler_config (:class:`~sagemaker.huggingface.TrainingCompilerConfig`):
Configures SageMaker Training Compiler to accelerate training.
**kwargs: Additional kwargs passed to the :class:`~sagemaker.estimator.Framework`
constructor.
.. tip::
You can find additional parameters for initializing this class at
:class:`~sagemaker.estimator.Framework` and
:class:`~sagemaker.estimator.EstimatorBase`.
"""
self.framework_version = transformers_version
self.py_version = py_version
self.tensorflow_version = tensorflow_version
self.pytorch_version = pytorch_version
self._validate_args(image_uri=image_uri)
instance_type = renamed_kwargs(
"train_instance_type", "instance_type", kwargs.get("instance_type"), kwargs
)
base_framework_name = "tensorflow" if tensorflow_version is not None else "pytorch"
base_framework_version = (
tensorflow_version if tensorflow_version is not None else pytorch_version
)
if distribution is not None:
validate_smdistributed(
instance_type=instance_type,
framework_name=base_framework_name,
framework_version=base_framework_version,
py_version=self.py_version,
distribution=distribution,
image_uri=image_uri,
)
warn_if_parameter_server_with_multi_gpu(
training_instance_type=instance_type, distribution=distribution
)
if "enable_sagemaker_metrics" not in kwargs:
kwargs["enable_sagemaker_metrics"] = True
kwargs["py_version"] = self.py_version
super(HuggingFace, self).__init__(
entry_point, source_dir, hyperparameters, image_uri=image_uri, **kwargs
)
if compiler_config is not None:
if not isinstance(compiler_config, TrainingCompilerConfig):
error_string = (
f"Expected instance of type {TrainingCompilerConfig}"
f"for argument compiler_config. "
f"Instead got {type(compiler_config)}"
)
raise ValueError(error_string)
if compiler_config:
compiler_config.validate(
image_uri=image_uri,
instance_type=instance_type,
distribution=distribution,
)
self.distribution = distribution or {}
self.compiler_config = compiler_config
