Buckets:

hf-doc-build
/

doc-dev

Files

xet

hf-doc-build/doc-dev / sagemaker /pr_1995 /en /tutorials /sagemaker-sdk /training-sagemaker-sdk.html

rtrm

about 1 month ago

download

raw

65.4 kB

	<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Run training on Amazon SageMaker","local":"run-training-on-amazon-sagemaker","sections":[{"title":"Installation and setup","local":"installation-and-setup","sections":[],"depth":2},{"title":"Prepare a 🤗 Transformers fine-tuning script","local":"prepare-a--transformers-fine-tuning-script","sections":[],"depth":2},{"title":"Training Output Management","local":"training-output-management","sections":[],"depth":2},{"title":"Create a Hugging Face Estimator","local":"create-a-hugging-face-estimator","sections":[],"depth":2},{"title":"Execute training","local":"execute-training","sections":[],"depth":2},{"title":"Access trained model","local":"access-trained-model","sections":[],"depth":2},{"title":"Distributed training","local":"distributed-training","sections":[{"title":"Data parallelism","local":"data-parallelism","sections":[],"depth":3},{"title":"Model parallelism","local":"model-parallelism","sections":[],"depth":3}],"depth":2},{"title":"Spot instances","local":"spot-instances","sections":[],"depth":2},{"title":"Git repository","local":"git-repository","sections":[],"depth":2},{"title":"SageMaker metrics","local":"sagemaker-metrics","sections":[],"depth":2}],"depth":1}">
	<link href="/docs/sagemaker/pr_1995/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
	<link rel="modulepreload" href="/docs/sagemaker/pr_1995/en/_app/immutable/entry/start.c99dd462.js">
	<link rel="modulepreload" href="/docs/sagemaker/pr_1995/en/_app/immutable/chunks/scheduler.aec39e6a.js">
	<link rel="modulepreload" href="/docs/sagemaker/pr_1995/en/_app/immutable/chunks/singletons.3bc577c3.js">
	<link rel="modulepreload" href="/docs/sagemaker/pr_1995/en/_app/immutable/chunks/paths.12b7f279.js">
	<link rel="modulepreload" href="/docs/sagemaker/pr_1995/en/_app/immutable/entry/app.cd901cb4.js">
	<link rel="modulepreload" href="/docs/sagemaker/pr_1995/en/_app/immutable/chunks/preload-helper.73d9078d.js">
	<link rel="modulepreload" href="/docs/sagemaker/pr_1995/en/_app/immutable/chunks/index.4ee0a2d0.js">
	<link rel="modulepreload" href="/docs/sagemaker/pr_1995/en/_app/immutable/nodes/0.381271ed.js">
	<link rel="modulepreload" href="/docs/sagemaker/pr_1995/en/_app/immutable/chunks/each.e59479a4.js">
	<link rel="modulepreload" href="/docs/sagemaker/pr_1995/en/_app/immutable/nodes/17.5b084e91.js">
	<link rel="modulepreload" href="/docs/sagemaker/pr_1995/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.8184f5a3.js">
	<link rel="modulepreload" href="/docs/sagemaker/pr_1995/en/_app/immutable/chunks/CodeBlock.db6247f1.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Run training on Amazon SageMaker","local":"run-training-on-amazon-sagemaker","sections":[{"title":"Installation and setup","local":"installation-and-setup","sections":[],"depth":2},{"title":"Prepare a 🤗 Transformers fine-tuning script","local":"prepare-a--transformers-fine-tuning-script","sections":[],"depth":2},{"title":"Training Output Management","local":"training-output-management","sections":[],"depth":2},{"title":"Create a Hugging Face Estimator","local":"create-a-hugging-face-estimator","sections":[],"depth":2},{"title":"Execute training","local":"execute-training","sections":[],"depth":2},{"title":"Access trained model","local":"access-trained-model","sections":[],"depth":2},{"title":"Distributed training","local":"distributed-training","sections":[{"title":"Data parallelism","local":"data-parallelism","sections":[],"depth":3},{"title":"Model parallelism","local":"model-parallelism","sections":[],"depth":3}],"depth":2},{"title":"Spot instances","local":"spot-instances","sections":[],"depth":2},{"title":"Git repository","local":"git-repository","sections":[],"depth":2},{"title":"SageMaker metrics","local":"sagemaker-metrics","sections":[],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"><div class="inline-flex rounded-md max-sm:rounded-sm"><button class="inline-flex items-center gap-1 max-sm:gap-0.5 h-6 max-sm:h-5 px-2 max-sm:px-1.5 text-[11px] max-sm:text-[9px] font-medium text-gray-800 border border-r-0 rounded-l-md max-sm:rounded-l-sm border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-live="polite"><span class="inline-flex items-center justify-center rounded-md p-0.5 max-sm:p-0"><svg class="w-3 h-3 max-sm:w-2.5 max-sm:h-2.5" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg></span> <span>Copy page</span></button> <button class="inline-flex items-center justify-center w-6 max-sm:w-5 h-6 max-sm:h-5 disabled:pointer-events-none text-sm text-gray-500 hover:text-gray-700 dark:hover:text-white rounded-r-md max-sm:rounded-r-sm border border-l transition border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-haspopup="menu" aria-expanded="false" aria-label="Open copy menu"><svg class="transition-transform text-gray-400 overflow-visible w-3 h-3 max-sm:w-2.5 max-sm:h-2.5 rotate-0" width="1em" height="1em" viewBox="0 0 12 7" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M1 1L6 6L11 1" stroke="currentColor"></path></svg></button></div> </div> <h1 class="relative group"><a id="run-training-on-amazon-sagemaker" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#run-training-on-amazon-sagemaker"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Run training on Amazon SageMaker</span></h1> <iframe width="700" height="394" src="https://www.youtube.com/embed/ok3hetb42gU" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen=""></iframe> <p data-svelte-h="svelte-zhmf4d">This guide will show you how to train a 🤗 Transformers model with the <code>HuggingFace</code> SageMaker Python SDK. Learn how to:</p> <ul data-svelte-h="svelte-d99lsl"><li><a href="#installation-and-setup">Install and setup your training environment</a>.</li> <li><a href="#prepare-a-transformers-fine-tuning-script">Prepare a training script</a>.</li> <li><a href="#create-a-hugging-face-estimator">Create a Hugging Face Estimator</a>.</li> <li><a href="#execute-training">Run training with the <code>fit</code> method</a>.</li> <li><a href="#access-trained-model">Access your trained model</a>.</li> <li><a href="#distributed-training">Perform distributed training</a>.</li> <li><a href="#spot-instances">Create a spot instance</a>.</li> <li><a href="#git-repository">Load a training script from a GitHub repository</a>.</li> <li><a href="#sagemaker-metrics">Collect training metrics</a>.</li></ul> <h2 class="relative group"><a id="installation-and-setup" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#installation-and-setup"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Installation and setup</span></h2> <p data-svelte-h="svelte-9mb7jq">Before you can train a 🤗 Transformers model with SageMaker, you need to sign up for an AWS account. If you don’t have an AWS account yet, learn more <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/gs-set-up.html" rel="nofollow">here</a>.</p> <p data-svelte-h="svelte-14pz1nf">Once you have an AWS account, get started using one of the following:</p> <ul data-svelte-h="svelte-nu9uzs"><li><a href="https://docs.aws.amazon.com/sagemaker/latest/dg/gs-studio-onboard.html" rel="nofollow">SageMaker Studio</a></li> <li><a href="https://docs.aws.amazon.com/sagemaker/latest/dg/gs-console.html" rel="nofollow">SageMaker notebook instance</a></li> <li>Local environment</li></ul> <p data-svelte-h="svelte-10vylvb">To start training locally, you need to setup an appropriate <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-roles.html" rel="nofollow">IAM role</a>.</p> <p data-svelte-h="svelte-1q1gn32">Upgrade to the latest <code>sagemaker</code> version:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->pip install sagemaker --upgrade<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-aqpf90"><strong>SageMaker environment</strong></p> <p data-svelte-h="svelte-1n86nit">Setup your SageMaker environment as shown below:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> sagemaker
	sess = sagemaker.Session()
	role = sagemaker.get_execution_role()<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-bmcgfj"><em>Note: The execution role is only available when running a notebook within SageMaker. If you run <code>get_execution_role</code> in a notebook not on SageMaker, expect a <code>region</code> error.</em></p> <p data-svelte-h="svelte-12o7543"><strong>Local environment</strong></p> <p data-svelte-h="svelte-qjt50s">Setup your local environment as shown below:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> sagemaker
	<span class="hljs-keyword">import</span> boto3

	iam_client = boto3.client(<span class="hljs-string">'iam'</span>)
	role = iam_client.get_role(RoleName=<span class="hljs-string">'role-name-of-your-iam-role-with-right-permissions'</span>)[<span class="hljs-string">'Role'</span>][<span class="hljs-string">'Arn'</span>]
	sess = sagemaker.Session()<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="prepare-a--transformers-fine-tuning-script" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#prepare-a--transformers-fine-tuning-script"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Prepare a 🤗 Transformers fine-tuning script</span></h2> <p data-svelte-h="svelte-1u3xeug">Our training script is very similar to a training script you might run outside of SageMaker. However, you can access useful properties about the training environment through various environment variables (see <a href="https://github.com/aws/sagemaker-training-toolkit/blob/master/ENVIRONMENT_VARIABLES.md" rel="nofollow">here</a> for a complete list), such as:</p> <ul data-svelte-h="svelte-1owy1vd"><li><p><code>SM_MODEL_DIR</code>: A string representing the path to which the training job writes the model artifacts. After training, artifacts in this directory are uploaded to S3 for model hosting. <code>SM_MODEL_DIR</code> is always set to <code>/opt/ml/model</code>.</p></li> <li><p><code>SM_NUM_GPUS</code>: An integer representing the number of GPUs available to the host.</p></li> <li><p><code>SM_CHANNEL_XXXX:</code> A string representing the path to the directory that contains the input data for the specified channel. For example, when you specify <code>train</code> and <code>test</code> in the Hugging Face Estimator <code>fit</code> method, the environment variables are set to <code>SM_CHANNEL_TRAIN</code> and <code>SM_CHANNEL_TEST</code>.</p></li></ul> <p data-svelte-h="svelte-1djq75m">The <code>hyperparameters</code> defined in the <a href="#create-an-huggingface-estimator">Hugging Face Estimator</a> are passed as named arguments and processed by <code>ArgumentParser()</code>.</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> transformers
	<span class="hljs-keyword">import</span> datasets
	<span class="hljs-keyword">import</span> argparse
	<span class="hljs-keyword">import</span> os

	<span class="hljs-keyword">if</span> __name__ == <span class="hljs-string">"__main__"</span>:

	parser = argparse.ArgumentParser()

	<span class="hljs-comment"># hyperparameters sent by the client are passed as command-line arguments to the script</span>
	parser.add_argument(<span class="hljs-string">"--epochs"</span>, <span class="hljs-built_in">type</span>=<span class="hljs-built_in">int</span>, default=<span class="hljs-number">3</span>)
	parser.add_argument(<span class="hljs-string">"--per_device_train_batch_size"</span>, <span class="hljs-built_in">type</span>=<span class="hljs-built_in">int</span>, default=<span class="hljs-number">32</span>)
	parser.add_argument(<span class="hljs-string">"--model_name_or_path"</span>, <span class="hljs-built_in">type</span>=<span class="hljs-built_in">str</span>)

	<span class="hljs-comment"># data, model, and output directories</span>
	parser.add_argument(<span class="hljs-string">"--model-dir"</span>, <span class="hljs-built_in">type</span>=<span class="hljs-built_in">str</span>, default=os.environ[<span class="hljs-string">"SM_MODEL_DIR"</span>])
	parser.add_argument(<span class="hljs-string">"--training_dir"</span>, <span class="hljs-built_in">type</span>=<span class="hljs-built_in">str</span>, default=os.environ[<span class="hljs-string">"SM_CHANNEL_TRAIN"</span>])
	parser.add_argument(<span class="hljs-string">"--test_dir"</span>, <span class="hljs-built_in">type</span>=<span class="hljs-built_in">str</span>, default=os.environ[<span class="hljs-string">"SM_CHANNEL_TEST"</span>])<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-x146s4"><em>Note that SageMaker doesn’t support argparse actions. For example, if you want to use a boolean hyperparameter, specify <code>type</code> as <code>bool</code> in your script and provide an explicit <code>True</code> or <code>False</code> value.</em></p> <p data-svelte-h="svelte-1v5ow9s">Look <a href="https://github.com/huggingface/notebooks/blob/main/sagemaker/01_getting_started_pytorch/scripts/train.py" rel="nofollow">train.py file</a> for a complete example of a 🤗 Transformers training script.</p> <h2 class="relative group"><a id="training-output-management" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#training-output-management"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Training Output Management</span></h2> <p data-svelte-h="svelte-1iromrn">If <code>output_dir</code> in the <code>TrainingArguments</code> is set to ‘/opt/ml/model’ the Trainer saves all training artifacts, including logs, checkpoints, and models. Amazon SageMaker archives the whole ‘/opt/ml/model’ directory as <code>model.tar.gz</code> and uploads it at the end of the training job to Amazon S3. Depending on your Hyperparameters and <code>TrainingArguments</code> this could lead to a large artifact (> 5GB), which can slow down deployment for Amazon SageMaker Inference.
	You can control how checkpoints, logs, and artifacts are saved by customization the <a href="https://huggingface.co/docs/transformers/main/en/main_classes/trainer#transformers.TrainingArguments" rel="nofollow">TrainingArguments</a>. For example by providing <code>save_total_limit</code> as <code>TrainingArgument</code> you can control the limit of the total amount of checkpoints. Deletes the older checkpoints in <code>output_dir</code> if new ones are saved and the maximum limit is reached.</p> <p data-svelte-h="svelte-17anpad">In addition to the options already mentioned above, there is another option to save the training artifacts during the training session. Amazon SageMaker supports <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/model-checkpoints.html" rel="nofollow">Checkpointing</a>, which allows you to continuously save your artifacts during training to Amazon S3 rather than at the end of your training. To enable <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/model-checkpoints.html" rel="nofollow">Checkpointing</a> you need to provide the <code>checkpoint_s3_uri</code> parameter pointing to an Amazon S3 location in the <code>HuggingFace</code> estimator and set <code>output_dir</code> to <code>/opt/ml/checkpoints</code>.
	<em>Note: If you set <code>output_dir</code> to <code>/opt/ml/checkpoints</code> make sure to call <code>trainer.save_model("/opt/ml/model")</code> or model.save_pretrained(“/opt/ml/model”)/<code>tokenizer.save_pretrained("/opt/ml/model")</code> at the end of your training to be able to deploy your model seamlessly to Amazon SageMaker for Inference.</em></p> <h2 class="relative group"><a id="create-a-hugging-face-estimator" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#create-a-hugging-face-estimator"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Create a Hugging Face Estimator</span></h2> <p data-svelte-h="svelte-w7qkuf">Run 🤗 Transformers training scripts on SageMaker by creating a <a href="https://sagemaker.readthedocs.io/en/stable/frameworks/huggingface/sagemaker.huggingface.html#huggingface-estimator" rel="nofollow">Hugging Face Estimator</a>. The Estimator handles end-to-end SageMaker training. There are several parameters you should define in the Estimator:</p> <ol data-svelte-h="svelte-17zgu79"><li><code>entry_point</code> specifies which fine-tuning script to use.</li> <li><code>instance_type</code> specifies an Amazon instance to launch. Refer <a href="https://aws.amazon.com/sagemaker/pricing/" rel="nofollow">here</a> for a complete list of instance types.</li> <li><code>hyperparameters</code> specifies training hyperparameters. View additional available hyperparameters in <a href="https://github.com/huggingface/notebooks/blob/main/sagemaker/01_getting_started_pytorch/scripts/train.py" rel="nofollow">train.py file</a>.</li></ol> <p data-svelte-h="svelte-129am2x">The following code sample shows how to train with a custom script <code>train.py</code> with three hyperparameters (<code>epochs</code>, <code>per_device_train_batch_size</code>, and <code>model_name_or_path</code>):</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> sagemaker.huggingface <span class="hljs-keyword">import</span> HuggingFace


	<span class="hljs-comment"># hyperparameters which are passed to the training job</span>
	hyperparameters={<span class="hljs-string">'epochs'</span>: <span class="hljs-number">1</span>,
	<span class="hljs-string">'per_device_train_batch_size'</span>: <span class="hljs-number">32</span>,
	<span class="hljs-string">'model_name_or_path'</span>: <span class="hljs-string">'distilbert-base-uncased'</span>
	}

	<span class="hljs-comment"># create the Estimator</span>
	huggingface_estimator = HuggingFace(
	entry_point=<span class="hljs-string">'train.py'</span>,
	source_dir=<span class="hljs-string">'./scripts'</span>,
	instance_type=<span class="hljs-string">'ml.g6.12xlarge'</span>,
	instance_count=<span class="hljs-number">1</span>,
	role=role,
	transformers_version=<span class="hljs-string">'4.26'</span>,
	pytorch_version=<span class="hljs-string">'1.13'</span>,
	py_version=<span class="hljs-string">'py39'</span>,
	hyperparameters = hyperparameters
	)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1dwzx5g">If you are running a <code>TrainingJob</code> locally, define <code>instance_type='local'</code> or <code>instance_type='local_gpu'</code> for GPU usage. Note that this will not work with SageMaker Studio.</p> <h2 class="relative group"><a id="execute-training" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#execute-training"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Execute training</span></h2> <p data-svelte-h="svelte-1rykzxi">Start your <code>TrainingJob</code> by calling <code>fit</code> on a Hugging Face Estimator. Specify your input training data in <code>fit</code>. The input training data can be a:</p> <ul data-svelte-h="svelte-n55cqy"><li>S3 URI such as <code>s3://my-bucket/my-training-data</code>.</li> <li><code>FileSystemInput</code> for Amazon Elastic File System or FSx for Lustre. See <a href="https://sagemaker.readthedocs.io/en/stable/overview.html?highlight=FileSystemInput#use-file-systems-as-training-inputs" rel="nofollow">here</a> for more details about using these file systems as input.</li></ul> <p data-svelte-h="svelte-1v0hjve">Call <code>fit</code> to begin training:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->huggingface_estimator.fit(
	{<span class="hljs-string">'train'</span>: <span class="hljs-string">'s3://sagemaker-us-east-1-558105141721/samples/datasets/imdb/train'</span>,
	<span class="hljs-string">'test'</span>: <span class="hljs-string">'s3://sagemaker-us-east-1-558105141721/samples/datasets/imdb/test'</span>}
	)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-pdxcpx">SageMaker starts and manages all the required EC2 instances and initiates the <code>TrainingJob</code> by running:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->/opt/conda/bin/python train.py --epochs 1 --model_name_or_path distilbert-base-uncased --per_device_train_batch_size 32<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="access-trained-model" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#access-trained-model"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Access trained model</span></h2> <p data-svelte-h="svelte-l786pq">Once training is complete, you can access your model through the <a href="https://console.aws.amazon.com/console/home?nc2=h_ct&src=header-signin" rel="nofollow">AWS console</a> or download it directly from S3.</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> sagemaker.s3 <span class="hljs-keyword">import</span> S3Downloader

	S3Downloader.download(
	s3_uri=huggingface_estimator.model_data, <span class="hljs-comment"># S3 URI where the trained model is located</span>
	local_path=<span class="hljs-string">'.'</span>, <span class="hljs-comment"># local path where *.targ.gz is saved</span>
	sagemaker_session=sess <span class="hljs-comment"># SageMaker session used for training the model</span>
	)<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="distributed-training" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#distributed-training"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Distributed training</span></h2> <p data-svelte-h="svelte-8hyjxi">SageMaker provides two strategies for distributed training: data parallelism and model parallelism. Data parallelism splits a training set across several GPUs, while model parallelism splits a model across several GPUs.</p> <h3 class="relative group"><a id="data-parallelism" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#data-parallelism"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Data parallelism</span></h3> <p data-svelte-h="svelte-170csdj">The Hugging Face <a href="https://huggingface.co/docs/transformers/main_classes/trainer" rel="nofollow">Trainer</a> supports SageMaker’s data parallelism library. If your training script uses the Trainer API, you only need to define the distribution parameter in the Hugging Face Estimator:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-comment"># configuration for running training on smdistributed data parallel</span>
	distribution = {<span class="hljs-string">'smdistributed'</span>:{<span class="hljs-string">'dataparallel'</span>:{ <span class="hljs-string">'enabled'</span>: <span class="hljs-literal">True</span> }}}

	<span class="hljs-comment"># create the Estimator</span>
	huggingface_estimator = HuggingFace(
	entry_point=<span class="hljs-string">'train.py'</span>,
	source_dir=<span class="hljs-string">'./scripts'</span>,
	instance_type=<span class="hljs-string">'ml.p3dn.24xlarge'</span>,
	instance_count=<span class="hljs-number">2</span>,
	role=role,
	transformers_version=<span class="hljs-string">'4.26.0'</span>,
	pytorch_version=<span class="hljs-string">'1.13.1'</span>,
	py_version=<span class="hljs-string">'py39'</span>,
	hyperparameters = hyperparameters,
	distribution = distribution
	)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-oj7kbb">📓 Open the <a href="https://github.com/huggingface/notebooks/blob/main/sagemaker/07_tensorflow_distributed_training_data_parallelism/sagemaker-notebook.ipynb" rel="nofollow">sagemaker-notebook.ipynb notebook</a> for an example of how to run the data parallelism library with TensorFlow.</p> <h3 class="relative group"><a id="model-parallelism" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#model-parallelism"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Model parallelism</span></h3> <p data-svelte-h="svelte-o081ci">The Hugging Face [Trainer] also supports SageMaker’s model parallelism library. If your training script uses the Trainer API, you only need to define the distribution parameter in the Hugging Face Estimator (see <a href="https://sagemaker.readthedocs.io/en/stable/api/training/smd_model_parallel_general.html?highlight=modelparallel#required-sagemaker-python-sdk-parameters" rel="nofollow">here</a> for more detailed information about using model parallelism):</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-comment"># configuration for running training on smdistributed model parallel</span>
	mpi_options = {
	<span class="hljs-string">"enabled"</span> : <span class="hljs-literal">True</span>,
	<span class="hljs-string">"processes_per_host"</span> : <span class="hljs-number">8</span>
	}

	smp_options = {
	<span class="hljs-string">"enabled"</span>:<span class="hljs-literal">True</span>,
	<span class="hljs-string">"parameters"</span>: {
	<span class="hljs-string">"microbatches"</span>: <span class="hljs-number">4</span>,
	<span class="hljs-string">"placement_strategy"</span>: <span class="hljs-string">"spread"</span>,
	<span class="hljs-string">"pipeline"</span>: <span class="hljs-string">"interleaved"</span>,
	<span class="hljs-string">"optimize"</span>: <span class="hljs-string">"speed"</span>,
	<span class="hljs-string">"partitions"</span>: <span class="hljs-number">4</span>,
	<span class="hljs-string">"ddp"</span>: <span class="hljs-literal">True</span>,
	}
	}

	distribution={
	<span class="hljs-string">"smdistributed"</span>: {<span class="hljs-string">"modelparallel"</span>: smp_options},
	<span class="hljs-string">"mpi"</span>: mpi_options
	}

	<span class="hljs-comment"># create the Estimator</span>
	huggingface_estimator = HuggingFace(
	entry_point=<span class="hljs-string">'train.py'</span>,
	source_dir=<span class="hljs-string">'./scripts'</span>,
	instance_type=<span class="hljs-string">'ml.p3dn.24xlarge'</span>,
	instance_count=<span class="hljs-number">2</span>,
	role=role,
	transformers_version=<span class="hljs-string">'4.26.0'</span>,
	pytorch_version=<span class="hljs-string">'1.13.1'</span>,
	py_version=<span class="hljs-string">'py39'</span>,
	hyperparameters = hyperparameters,
	distribution = distribution
	)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-16yf61l">📓 Open the <a href="https://github.com/huggingface/notebooks/blob/main/sagemaker/04_distributed_training_model_parallelism/sagemaker-notebook.ipynb" rel="nofollow">sagemaker-notebook.ipynb notebook</a> for an example of how to run the model parallelism library.</p> <h2 class="relative group"><a id="spot-instances" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#spot-instances"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Spot instances</span></h2> <p data-svelte-h="svelte-1yk874x">The Hugging Face extension for the SageMaker Python SDK means we can benefit from <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/model-managed-spot-training.html" rel="nofollow">fully-managed EC2 spot instances</a>. This can help you save up to 90% of training costs!</p> <p data-svelte-h="svelte-11t96qn"><em>Note: Unless your training job completes quickly, we recommend you use <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/model-checkpoints.html" rel="nofollow">checkpointing</a> with managed spot training. In this case, you need to define the <code>checkpoint_s3_uri</code>.</em></p> <p data-svelte-h="svelte-1d0l8c6">Set <code>use_spot_instances=True</code> and define your <code>max_wait</code> and <code>max_run</code> time in the Estimator to use spot instances:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-comment"># hyperparameters which are passed to the training job</span>
	hyperparameters={<span class="hljs-string">'epochs'</span>: <span class="hljs-number">1</span>,
	<span class="hljs-string">'train_batch_size'</span>: <span class="hljs-number">32</span>,
	<span class="hljs-string">'model_name'</span>:<span class="hljs-string">'distilbert-base-uncased'</span>,
	<span class="hljs-string">'output_dir'</span>:<span class="hljs-string">'/opt/ml/checkpoints'</span>
	}

	<span class="hljs-comment"># create the Estimator</span>
	huggingface_estimator = HuggingFace(
	entry_point=<span class="hljs-string">'train.py'</span>,
	source_dir=<span class="hljs-string">'./scripts'</span>,
	instance_type=<span class="hljs-string">'ml.g6.12xlarge'</span>,
	instance_count=<span class="hljs-number">1</span>,
	checkpoint_s3_uri=<span class="hljs-string">f's3://<span class="hljs-subst">{sess.default_bucket()}</span>/checkpoints'</span>
	use_spot_instances=<span class="hljs-literal">True</span>,
	<span class="hljs-comment"># max_wait should be equal to or greater than max_run in seconds</span>
	max_wait=<span class="hljs-number">3600</span>,
	max_run=<span class="hljs-number">1000</span>,
	role=role,
	transformers_version=<span class="hljs-string">'4.26'</span>,
	pytorch_version=<span class="hljs-string">'1.13'</span>,
	py_version=<span class="hljs-string">'py39'</span>,
	hyperparameters = hyperparameters
	)

	<span class="hljs-comment"># Training seconds: 874</span>
	<span class="hljs-comment"># Billable seconds: 262</span>
	<span class="hljs-comment"># Managed Spot Training savings: 70.0%</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1384417">📓 Open the <a href="https://github.com/huggingface/notebooks/blob/main/sagemaker/05_spot_instances/sagemaker-notebook.ipynb" rel="nofollow">sagemaker-notebook.ipynb notebook</a> for an example of how to use spot instances.</p> <h2 class="relative group"><a id="git-repository" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#git-repository"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Git repository</span></h2> <p data-svelte-h="svelte-1rsnmrd">The Hugging Face Estimator can load a training script <a href="https://sagemaker.readthedocs.io/en/stable/overview.html#use-scripts-stored-in-a-git-repository" rel="nofollow">stored in a GitHub repository</a>. Provide the relative path to the training script in <code>entry_point</code> and the relative path to the directory in <code>source_dir</code>.</p> <p data-svelte-h="svelte-1mokhnw">If you are using <code>git_config</code> to run the <a href="https://github.com/huggingface/transformers/tree/main/examples" rel="nofollow">🤗 Transformers example scripts</a>, you need to configure the correct <code>'branch'</code> in <code>transformers_version</code> (e.g. if you use <code>transformers_version='4.4.2</code> you have to use <code>'branch':'v4.4.2'</code>).</p> <p data-svelte-h="svelte-hhyk3e"><em>Tip: Save your model to S3 by setting <code>output_dir=/opt/ml/model</code> in the hyperparameter of your training script.</em></p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-comment"># configure git settings</span>
	git_config = {<span class="hljs-string">'repo'</span>: <span class="hljs-string">'https://github.com/huggingface/transformers.git'</span>,<span class="hljs-string">'branch'</span>: <span class="hljs-string">'v4.4.2'</span>} <span class="hljs-comment"># v4.4.2 refers to the transformers_version you use in the estimator</span>

	<span class="hljs-comment"># create the Estimator</span>
	huggingface_estimator = HuggingFace(
	entry_point=<span class="hljs-string">'run_glue.py'</span>,
	source_dir=<span class="hljs-string">'./examples/pytorch/text-classification'</span>,
	git_config=git_config,
	instance_type=<span class="hljs-string">'ml.g6.12xlarge'</span>,
	instance_count=<span class="hljs-number">1</span>,
	role=role,
	transformers_version=<span class="hljs-string">'4.26'</span>,
	pytorch_version=<span class="hljs-string">'1.13'</span>,
	py_version=<span class="hljs-string">'py39'</span>,
	hyperparameters=hyperparameters
	)<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="sagemaker-metrics" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#sagemaker-metrics"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>SageMaker metrics</span></h2> <p data-svelte-h="svelte-xro6kp"><a href="https://docs.aws.amazon.com/sagemaker/latest/dg/training-metrics.html#define-train-metrics" rel="nofollow">SageMaker metrics</a> automatically parses training job logs for metrics and sends them to CloudWatch. If you want SageMaker to parse the logs, you must specify the metric’s name and a regular expression for SageMaker to use to find the metric.</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-comment"># define metrics definitions</span>
	metric_definitions = [
	{<span class="hljs-string">"Name"</span>: <span class="hljs-string">"train_runtime"</span>, <span class="hljs-string">"Regex"</span>: <span class="hljs-string">"train_runtime.=\D(.*?)$"</span>},
	{<span class="hljs-string">"Name"</span>: <span class="hljs-string">"eval_accuracy"</span>, <span class="hljs-string">"Regex"</span>: <span class="hljs-string">"eval_accuracy.=\D(.*?)$"</span>},
	{<span class="hljs-string">"Name"</span>: <span class="hljs-string">"eval_loss"</span>, <span class="hljs-string">"Regex"</span>: <span class="hljs-string">"eval_loss.=\D(.*?)$"</span>},
	]

	<span class="hljs-comment"># create the Estimator</span>
	huggingface_estimator = HuggingFace(
	entry_point=<span class="hljs-string">'train.py'</span>,
	source_dir=<span class="hljs-string">'./scripts'</span>,
	instance_type=<span class="hljs-string">'ml.g6.12xlarge'</span>,
	instance_count=<span class="hljs-number">1</span>,
	role=role,
	transformers_version=<span class="hljs-string">'4.26'</span>,
	pytorch_version=<span class="hljs-string">'1.13'</span>,
	py_version=<span class="hljs-string">'py39'</span>,
	metric_definitions=metric_definitions,
	hyperparameters = hyperparameters)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1y5r5uo">📓 Open the <a href="https://github.com/huggingface/notebooks/blob/main/sagemaker/06_sagemaker_metrics/sagemaker-notebook.ipynb" rel="nofollow">notebook</a> for an example of how to capture metrics in SageMaker.</p> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/hub-docs/blob/main/docs/sagemaker/source/tutorials/sagemaker-sdk/training-sagemaker-sdk.md" target="_blank"><svg class="mr-1" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M31,16l-7,7l-1.41-1.41L28.17,16l-5.58-5.59L24,9l7,7z"></path><path d="M1,16l7-7l1.41,1.41L3.83,16l5.58,5.59L8,23l-7-7z"></path><path d="M12.419,25.484L17.639,6.552l1.932,0.518L14.351,26.002z"></path></svg> <span data-svelte-h="svelte-zjs2n5"><span class="underline">Update</span> on GitHub</span></a> <p></p>

	<script>
	{
	__sveltekit_16nm56f = {
	assets: "/docs/sagemaker/pr_1995/en",
	base: "/docs/sagemaker/pr_1995/en",
	env: {}
	};

	const element = document.currentScript.parentElement;

	const data = [null,null];

	Promise.all([
	import("/docs/sagemaker/pr_1995/en/_app/immutable/entry/start.c99dd462.js"),
	import("/docs/sagemaker/pr_1995/en/_app/immutable/entry/app.cd901cb4.js")
	]).then(([kit, app]) => {
	kit.start(app, element, {
	node_ids: [0, 17],
	data,
	form: null,
	error: null
	});
	});
	}
	</script>

Xet Storage Details

Size:: 65.4 kB
Xet hash:: 1906f867b683ef3a6fd4d6c332b1500e5f311203202f921d6a65bd04e6c3cb2d

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.