lighteval/pr_1221/en/offline-evaluation.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Offline evaluation using local data files&quot;,&quot;local&quot;:&quot;offline-evaluation-using-local-data-files&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}">
		<link href="/docs/lighteval/pr_1221/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
		<link rel="modulepreload" href="/docs/lighteval/pr_1221/en/_app/immutable/entry/start.86845e89.js">
		<link rel="modulepreload" href="/docs/lighteval/pr_1221/en/_app/immutable/chunks/scheduler.3a17fb72.js">
		<link rel="modulepreload" href="/docs/lighteval/pr_1221/en/_app/immutable/chunks/singletons.9670729e.js">
		<link rel="modulepreload" href="/docs/lighteval/pr_1221/en/_app/immutable/chunks/paths.dc4e91fb.js">
		<link rel="modulepreload" href="/docs/lighteval/pr_1221/en/_app/immutable/entry/app.2df9be51.js">
		<link rel="modulepreload" href="/docs/lighteval/pr_1221/en/_app/immutable/chunks/preload-helper.3f9be9c8.js">
		<link rel="modulepreload" href="/docs/lighteval/pr_1221/en/_app/immutable/chunks/index.093f8863.js">
		<link rel="modulepreload" href="/docs/lighteval/pr_1221/en/_app/immutable/nodes/0.15740f19.js">
		<link rel="modulepreload" href="/docs/lighteval/pr_1221/en/_app/immutable/chunks/each.e59479a4.js">
		<link rel="modulepreload" href="/docs/lighteval/pr_1221/en/_app/immutable/nodes/12.56157251.js">
		<link rel="modulepreload" href="/docs/lighteval/pr_1221/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.5e7ea2bd.js">
		<link rel="modulepreload" href="/docs/lighteval/pr_1221/en/_app/immutable/chunks/CodeBlock.09235327.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Offline evaluation using local data files&quot;,&quot;local&quot;:&quot;offline-evaluation-using-local-data-files&quot;,&quot;sections&quot;:[],&quot;depth&quot;: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="offline-evaluation-using-local-data-files" 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="#offline-evaluation-using-local-data-files"><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>Offline evaluation using local data files</span></h1> <p data-svelte-h="svelte-52pw01">If you are prototyping a task based on files that are not yet hosted on the
Hub, you can take advantage of the <code>hf_data_files</code> argument to point lighteval
at local JSON/CSV resources. This makes it easy to evaluate datasets that live
in your repo or that are generated on the fly.</p> <p data-svelte-h="svelte-15bq69p">Internally, <code>hf_data_files</code> is passed directly to the <code>data_files</code> parameter of <code>datasets.load_dataset</code> (<a href="(https://huggingface.co/docs/datasets/en/package_reference/loading_methods#datasets.load_dataset)">docs</a>).</p> <p data-svelte-h="svelte-oqclj2">See <a href="adding-a-custom-task">adding a custom task</a> for more information on how to create a custom task.</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> pathlib <span class="hljs-keyword">import</span> Path

<span class="hljs-keyword">from</span> lighteval.metrics <span class="hljs-keyword">import</span> Metrics
<span class="hljs-keyword">from</span> lighteval.tasks.lighteval_task <span class="hljs-keyword">import</span> LightevalTaskConfig
<span class="hljs-keyword">from</span> lighteval.tasks.requests <span class="hljs-keyword">import</span> Doc


<span class="hljs-keyword">def</span> <span class="hljs-title function_">local_prompt</span>(<span class="hljs-params">line: <span class="hljs-built_in">dict</span>, task_name: <span class="hljs-built_in">str</span></span>) -&gt; Doc:
    <span class="hljs-keyword">return</span> Doc(
        task_name=task_name,
        query=line[<span class="hljs-string">&quot;question&quot;</span>],
        choices=line[<span class="hljs-string">&quot;choices&quot;</span>],
        gold_index=line[<span class="hljs-string">&quot;answer&quot;</span>]
    )


local_data = Path(__file__).parent / <span class="hljs-string">&quot;samples&quot;</span> / <span class="hljs-string">&quot;faq.jsonl&quot;</span>

local_task = LightevalTaskConfig(
    name=<span class="hljs-string">&quot;faq_eval&quot;</span>,
    prompt_function=local_prompt,
    hf_repo=<span class="hljs-string">&quot;json&quot;</span>,  <span class="hljs-comment"># Built-in streaming loader for json/jsonl files</span>
    hf_subset=<span class="hljs-string">&quot;default&quot;</span>,
    hf_data_files=<span class="hljs-built_in">str</span>(local_data),  <span class="hljs-comment"># Can also be a dict mapping split names to paths</span>
    evaluation_splits=[<span class="hljs-string">&quot;train&quot;</span>],
    metrics=[Metrics.ACCURACY],
)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-ulduhb">Once the config is registered in <code>TASKS_TABLE</code>, running the task with
<code>--custom-tasks path/to/your_file.py</code> will automatically load the local data
files. You can also pass a dictionary to <code>hf_data_files</code> (e.g.
<code>{&quot;train&quot;: &quot;train.jsonl&quot;, &quot;validation&quot;: &quot;val.jsonl&quot;}</code>) to expose multiple
splits.</p> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/lighteval/blob/main/docs/source/offline-evaluation.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_13vx2u = {
						assets: "/docs/lighteval/pr_1221/en",
						base: "/docs/lighteval/pr_1221/en",
						env: {}
					};

					const element = document.currentScript.parentElement;

					const data = [null,null];

					Promise.all([
						import("/docs/lighteval/pr_1221/en/_app/immutable/entry/start.86845e89.js"),
						import("/docs/lighteval/pr_1221/en/_app/immutable/entry/app.2df9be51.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 12],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>