Hugging Face's logo

Buckets:
hf-doc-build
/
doc

Files
xet
hf-doc-build/doc / evaluate /main /en /evaluation_suite.html
HuggingFaceDocBuilder's picture
HuggingFaceDocBuilder
download
raw
15.7 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Creating an EvaluationSuite&quot;,&quot;local&quot;:&quot;creating-an-evaluationsuite&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}"/>
<link href="/docs/evaluate/main/en/_app/immutable/entry/start.BR5Aqcvb.js" rel="modulepreload">
<link href="/docs/evaluate/main/en/_app/immutable/chunks/DqHwGgZ9.js" rel="modulepreload">
<link href="/docs/evaluate/main/en/_app/immutable/chunks/DfHjNWj2.js" rel="modulepreload">
<link href="/docs/evaluate/main/en/_app/immutable/entry/app.DmLJnaQj.js" rel="modulepreload">
<link href="/docs/evaluate/main/en/_app/immutable/chunks/Ba1drWuH.js" rel="modulepreload">
<link href="/docs/evaluate/main/en/_app/immutable/chunks/B9F8bIy5.js" rel="modulepreload">
<link href="/docs/evaluate/main/en/_app/immutable/chunks/DsnmJJEf.js" rel="modulepreload">
<link href="/docs/evaluate/main/en/_app/immutable/chunks/PGLvW8OU.js" rel="modulepreload">
<link href="/docs/evaluate/main/en/_app/immutable/nodes/0.DDTih1_y.js" rel="modulepreload">
<link href="/docs/evaluate/main/en/_app/immutable/chunks/CFswWuIO.js" rel="modulepreload">
<link href="/docs/evaluate/main/en/_app/immutable/nodes/8.DxWGsgmt.js" rel="modulepreload">
<link href="/docs/evaluate/main/en/_app/immutable/chunks/-IybLn_I.js" rel="modulepreload">
<!--ukjeva--><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Creating an EvaluationSuite&quot;,&quot;local&quot;:&quot;creating-an-evaluationsuite&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}"/><!---->
<link href="/docs/evaluate/main/en/_app/immutable/assets/0.tn0RQdqM.css" rel="modulepreload"> <!--[--><!--[0--><!--[--><!--[0--><!--[--><p></p> <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: inline-end; margin-inline-start: 10px; display: inline-flex; position: relative; z-index: 10;"><div dir="ltr" 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 dir="auto">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> <!--[-1--><!--]--></div><!----> <!--[0--><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 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>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>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>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>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>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>The mandatory attributes for a new <code>SubTask</code> are <code>task_type</code> and <code>data</code>.</p> <ol><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 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="language-python "><!----><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)
<span class="hljs-variable language_">self</span>.preprocessor = <span class="hljs-keyword">lambda</span> x: {<span class="hljs-string">&quot;text&quot;</span>: x[<span class="hljs-string">&quot;text&quot;</span>].lower()}
<span class="hljs-variable language_">self</span>.suite = [
SubTask(
task_type=<span class="hljs-string">&quot;text-classification&quot;</span>,
data=<span class="hljs-string">&quot;glue&quot;</span>,
subset=<span class="hljs-string">&quot;sst2&quot;</span>,
split=<span class="hljs-string">&quot;validation[:10]&quot;</span>,
args_for_task={
<span class="hljs-string">&quot;metric&quot;</span>: <span class="hljs-string">&quot;accuracy&quot;</span>,
<span class="hljs-string">&quot;input_column&quot;</span>: <span class="hljs-string">&quot;sentence&quot;</span>,
<span class="hljs-string">&quot;label_column&quot;</span>: <span class="hljs-string">&quot;label&quot;</span>,
<span class="hljs-string">&quot;label_mapping&quot;</span>: {
<span class="hljs-string">&quot;LABEL_0&quot;</span>: <span class="hljs-number">0.0</span>,
<span class="hljs-string">&quot;LABEL_1&quot;</span>: <span class="hljs-number">1.0</span>
}
}
),
SubTask(
task_type=<span class="hljs-string">&quot;text-classification&quot;</span>,
data=<span class="hljs-string">&quot;glue&quot;</span>,
subset=<span class="hljs-string">&quot;rte&quot;</span>,
split=<span class="hljs-string">&quot;validation[:10]&quot;</span>,
args_for_task={
<span class="hljs-string">&quot;metric&quot;</span>: <span class="hljs-string">&quot;accuracy&quot;</span>,
<span class="hljs-string">&quot;input_column&quot;</span>: <span class="hljs-string">&quot;sentence1&quot;</span>,
<span class="hljs-string">&quot;second_input_column&quot;</span>: <span class="hljs-string">&quot;sentence2&quot;</span>,
<span class="hljs-string">&quot;label_column&quot;</span>: <span class="hljs-string">&quot;label&quot;</span>,
<span class="hljs-string">&quot;label_mapping&quot;</span>: {
<span class="hljs-string">&quot;LABEL_0&quot;</span>: <span class="hljs-number">0</span>,
<span class="hljs-string">&quot;LABEL_1&quot;</span>: <span class="hljs-number">1</span>
}
}
)
]<!----></pre></div><!----> <p>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 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=" "><!----><span class="hljs-meta prompt_">&gt;&gt;&gt;</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_">&gt;&gt;&gt;</span> <span class="language-python">suite = EvaluationSuite.load(<span class="hljs-string">&#x27;mathemakitten/glue-evaluation-suite&#x27;</span>)</span>
<span class="hljs-meta prompt_">&gt;&gt;&gt;</span> <span class="language-python">results = suite.run(<span class="hljs-string">&quot;gpt2&quot;</span>)</span><!----></pre></div><!----> <table><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><span class="underline">Update</span> on GitHub</span></a><!----> <p></p><!--]--><!----><!--]--><!--]--><!--]--> <!--[-1--><!--]--><!--]-->
<script>
{
__sveltekit_1qnqef1 = {
base: "/docs/evaluate/main/en",
assets: "/docs/evaluate/main/en"
};
const element = document.currentScript.parentElement;
Promise.all([
import("/docs/evaluate/main/en/_app/immutable/entry/start.BR5Aqcvb.js"),
import("/docs/evaluate/main/en/_app/immutable/entry/app.DmLJnaQj.js")
]).then(([kit, app]) => {
kit.start(app, element, {
node_ids: [0, 8],
data: [null,null],
form: null,
error: null
});
});
}
</script>

Xet Storage Details

Size:
15.7 kB
·
Xet hash:
131851bbfa4e81ce67b159cc407487ea90109322f01cb4a53456f8e066f1c50a

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