Buckets:

hf-doc-build
/

doc

Files

xet

hf-doc-build/doc / evaluate /main /en /evaluation_suite.html

rtrm

about 1 month ago

download

raw

15.9 kB

	<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Creating an EvaluationSuite","local":"creating-an-evaluationsuite","sections":[],"depth":1}">
	<link href="/docs/evaluate/main/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
	<link rel="modulepreload" href="/docs/evaluate/main/en/_app/immutable/entry/start.138f3e02.js">
	<link rel="modulepreload" href="/docs/evaluate/main/en/_app/immutable/chunks/scheduler.5f3e6389.js">
	<link rel="modulepreload" href="/docs/evaluate/main/en/_app/immutable/chunks/singletons.3420a244.js">
	<link rel="modulepreload" href="/docs/evaluate/main/en/_app/immutable/chunks/paths.65ada1b9.js">
	<link rel="modulepreload" href="/docs/evaluate/main/en/_app/immutable/entry/app.ad076786.js">
	<link rel="modulepreload" href="/docs/evaluate/main/en/_app/immutable/chunks/preload-helper.0572feea.js">
	<link rel="modulepreload" href="/docs/evaluate/main/en/_app/immutable/chunks/index.62df735e.js">
	<link rel="modulepreload" href="/docs/evaluate/main/en/_app/immutable/nodes/0.11bd9b89.js">
	<link rel="modulepreload" href="/docs/evaluate/main/en/_app/immutable/chunks/each.e59479a4.js">
	<link rel="modulepreload" href="/docs/evaluate/main/en/_app/immutable/nodes/8.50699229.js">
	<link rel="modulepreload" href="/docs/evaluate/main/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.e306bd5b.js">
	<link rel="modulepreload" href="/docs/evaluate/main/en/_app/immutable/chunks/CodeBlock.dc1e8be0.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Creating an EvaluationSuite","local":"creating-an-evaluationsuite","sections":[],"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 h-7 max-sm:h-7 px-2 max-sm:px-1.5 text-sm 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 hover:text-gray-800 dark:hover:text-gray-200"><svg class="sm:size-3.5 size-3" 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-7 max-sm:h-7 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 sm:size-3.5 size-3 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="creating-an-evaluationsuite" 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="#creating-an-evaluationsuite"><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>Creating an EvaluationSuite</span></h1> <p data-svelte-h="svelte-1o9jx98">It can be useful to evaluate models on a variety of different tasks to understand their downstream performance. Assessing the model on several types of tasks can reveal gaps in performance along some axis. For example, when training a language model, it is often useful to measure perplexity on an in-domain corpus, but also to concurrently evaluate on tasks which test for general language capabilities like natural language entailment or question-answering, or tasks designed to probe the model along fairness and bias dimensions.</p> <p data-svelte-h="svelte-ilp2q5">The <code>EvaluationSuite</code> provides a way to compose any number of (<a href="base_evaluator">evaluator</a>, dataset, metric) tuples as a SubTask to evaluate a model on a collection of several evaluation tasks. See the <a href="base_evaluator">evaluator documentation</a> for a list of currently supported tasks.</p> <p data-svelte-h="svelte-1n2uses">A new <code>EvaluationSuite</code> is made up of a list of <code>SubTask</code> classes, each defining an evaluation task. The Python file containing the definition can be uploaded to a Space on the Hugging Face Hub so it can be shared with the community or saved/loaded locally as a Python script.</p> <p data-svelte-h="svelte-vv6oy3">Some datasets require additional preprocessing before passing them to an <code>Evaluator</code>. You can set a <code>data_preprocessor</code> for each <code>SubTask</code> which is applied via a <code>map</code> operation using the <code>datasets</code> library. Keyword arguments for the <code>Evaluator</code> can be passed down through the <code>args_for_task</code> attribute.</p> <p data-svelte-h="svelte-hb1yl5">To create a new <code>EvaluationSuite</code>, create a <a href="https://huggingface.co/new-space" rel="nofollow">new Space</a> with a .py file which matches the name of the Space, add the below template to a Python file, and fill in the attributes for a new task.</p> <p data-svelte-h="svelte-8icix4">The mandatory attributes for a new <code>SubTask</code> are <code>task_type</code> and <code>data</code>.</p> <ol data-svelte-h="svelte-14zybc3"><li><code>task_type</code> maps to the tasks currently supported by the Evaluator.</li> <li><code>data</code> can be an instantiated Hugging Face dataset object or the name of a dataset.</li> <li><code>subset</code> and <code>split</code> can be used to define which name and split of the dataset should be used for evaluation.</li> <li><code>args_for_task</code> should be a dictionary with kwargs to be passed to the Evaluator.</li></ol> <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> evaluate
	<span class="hljs-keyword">from</span> evaluate.evaluation_suite <span class="hljs-keyword">import</span> SubTask

	<span class="hljs-keyword">class</span> <span class="hljs-title class_">Suite</span>(evaluate.EvaluationSuite):

	<span class="hljs-keyword">def</span> <span class="hljs-title function_">__init__</span>(<span class="hljs-params">self, name</span>):
	<span class="hljs-built_in">super</span>().__init__(name)
	self.preprocessor = <span class="hljs-keyword">lambda</span> x: {<span class="hljs-string">"text"</span>: x[<span class="hljs-string">"text"</span>].lower()}
	self.suite = [
	SubTask(
	task_type=<span class="hljs-string">"text-classification"</span>,
	data=<span class="hljs-string">"glue"</span>,
	subset=<span class="hljs-string">"sst2"</span>,
	split=<span class="hljs-string">"validation[:10]"</span>,
	args_for_task={
	<span class="hljs-string">"metric"</span>: <span class="hljs-string">"accuracy"</span>,
	<span class="hljs-string">"input_column"</span>: <span class="hljs-string">"sentence"</span>,
	<span class="hljs-string">"label_column"</span>: <span class="hljs-string">"label"</span>,
	<span class="hljs-string">"label_mapping"</span>: {
	<span class="hljs-string">"LABEL_0"</span>: <span class="hljs-number">0.0</span>,
	<span class="hljs-string">"LABEL_1"</span>: <span class="hljs-number">1.0</span>
	}
	}
	),
	SubTask(
	task_type=<span class="hljs-string">"text-classification"</span>,
	data=<span class="hljs-string">"glue"</span>,
	subset=<span class="hljs-string">"rte"</span>,
	split=<span class="hljs-string">"validation[:10]"</span>,
	args_for_task={
	<span class="hljs-string">"metric"</span>: <span class="hljs-string">"accuracy"</span>,
	<span class="hljs-string">"input_column"</span>: <span class="hljs-string">"sentence1"</span>,
	<span class="hljs-string">"second_input_column"</span>: <span class="hljs-string">"sentence2"</span>,
	<span class="hljs-string">"label_column"</span>: <span class="hljs-string">"label"</span>,
	<span class="hljs-string">"label_mapping"</span>: {
	<span class="hljs-string">"LABEL_0"</span>: <span class="hljs-number">0</span>,
	<span class="hljs-string">"LABEL_1"</span>: <span class="hljs-number">1</span>
	}
	}
	)
	]<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-j5in79">An <code>EvaluationSuite</code> can be loaded by name from the Hugging Face Hub, or locally by providing a path, and run with the <code>run(model_or_pipeline)</code> method. The evaluation results are returned along with their task names and information about the time it took to obtain predictions through the pipeline. These can be easily displayed with a <code>pandas.DataFrame</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-meta prompt_">>>></span> <span class="language-python"><span class="hljs-keyword">from</span> evaluate <span class="hljs-keyword">import</span> EvaluationSuite</span>
	<span class="hljs-meta prompt_">>>></span> <span class="language-python">suite = EvaluationSuite.load(<span class="hljs-string">'mathemakitten/glue-evaluation-suite'</span>)</span>
	<span class="hljs-meta prompt_">>>></span> <span class="language-python">results = suite.run(<span class="hljs-string">"gpt2"</span>)</span><!-- HTML_TAG_END --></pre></div> <table data-svelte-h="svelte-1ictp82"><thead><tr><th align="right">accuracy</th> <th align="right">total_time_in_seconds</th> <th align="right">samples_per_second</th> <th align="right">latency_in_seconds</th> <th align="left">task_name</th></tr></thead> <tbody><tr><td align="right">0.5</td> <td align="right">0.740811</td> <td align="right">13.4987</td> <td align="right">0.0740811</td> <td align="left">glue/sst2</td></tr> <tr><td align="right">0.4</td> <td align="right">1.67552</td> <td align="right">5.9683</td> <td align="right">0.167552</td> <td align="left">glue/rte</td></tr></tbody></table> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/evaluate/blob/main/docs/source/evaluation_suite.mdx" 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_95ljrq = {
	assets: "/docs/evaluate/main/en",
	base: "/docs/evaluate/main/en",
	env: {}
	};

	const element = document.currentScript.parentElement;

	const data = [null,null];

	Promise.all([
	import("/docs/evaluate/main/en/_app/immutable/entry/start.138f3e02.js"),
	import("/docs/evaluate/main/en/_app/immutable/entry/app.ad076786.js")
	]).then(([kit, app]) => {
	kit.start(app, element, {
	node_ids: [0, 8],
	data,
	form: null,
	error: null
	});
	});
	}
	</script>

Xet Storage Details

Size:: 15.9 kB
Xet hash:: a1205de918e5f12c839edd7e0c6e61be2f4711dae518ec504fedcc6b394a5a8a

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