Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Adding a New Metric","local":"adding-a-new-metric","sections":[],"depth":1}"> | |
| <link href="/docs/lighteval/pr_744/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/lighteval/pr_744/en/_app/immutable/entry/start.a615223c.js"> | |
| <link rel="modulepreload" href="/docs/lighteval/pr_744/en/_app/immutable/chunks/scheduler.7da89386.js"> | |
| <link rel="modulepreload" href="/docs/lighteval/pr_744/en/_app/immutable/chunks/singletons.8c5be8fd.js"> | |
| <link rel="modulepreload" href="/docs/lighteval/pr_744/en/_app/immutable/chunks/paths.86a4d49d.js"> | |
| <link rel="modulepreload" href="/docs/lighteval/pr_744/en/_app/immutable/entry/app.b0033d27.js"> | |
| <link rel="modulepreload" href="/docs/lighteval/pr_744/en/_app/immutable/chunks/index.20910acc.js"> | |
| <link rel="modulepreload" href="/docs/lighteval/pr_744/en/_app/immutable/nodes/0.c40ee5c5.js"> | |
| <link rel="modulepreload" href="/docs/lighteval/pr_744/en/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/lighteval/pr_744/en/_app/immutable/nodes/3.9e8f904d.js"> | |
| <link rel="modulepreload" href="/docs/lighteval/pr_744/en/_app/immutable/chunks/Tip.53e22153.js"> | |
| <link rel="modulepreload" href="/docs/lighteval/pr_744/en/_app/immutable/chunks/CodeBlock.143bd81e.js"> | |
| <link rel="modulepreload" href="/docs/lighteval/pr_744/en/_app/immutable/chunks/index.c9cd5e8b.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Adding a New Metric","local":"adding-a-new-metric","sections":[],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="adding-a-new-metric" 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="#adding-a-new-metric"><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>Adding a New Metric</span></h1> <p data-svelte-h="svelte-111c5am">First, check if you can use one of the parametrized functions in | |
| <a href="package_reference/metrics#corpus-metrics">Corpus Metrics</a> or | |
| <a href="package_reference/metrics#sample-metrics">Sample Metrics</a>.</p> <p data-svelte-h="svelte-9nbkyl">If not, you can use the <code>custom_task</code> system to register your new metric:</p> <div class="course-tip bg-gradient-to-br dark:bg-gradient-to-r before:border-green-500 dark:before:border-green-800 from-green-50 dark:from-gray-900 to-white dark:to-gray-950 border border-green-50 text-green-700 dark:text-gray-400"><p data-svelte-h="svelte-73seg9">To see an example of a custom metric added along with a custom task, look at <a href="">the IFEval custom task</a>.</p></div> <div class="course-tip course-tip-orange bg-gradient-to-br dark:bg-gradient-to-r before:border-orange-500 dark:before:border-orange-800 from-orange-50 dark:from-gray-900 to-white dark:to-gray-950 border border-orange-50 text-orange-700 dark:text-gray-400"><p data-svelte-h="svelte-l65q4m">To contribute your custom metric to the lighteval repo, you would first need | |
| to install the required dev dependencies by running <code>pip install -e .[dev]</code> | |
| and then run <code>pre-commit install</code> to install the pre-commit hooks.</p></div> <ul data-svelte-h="svelte-43knas"><li>Create a new Python file which should contain the full logic of your metric.</li> <li>The file also needs to start with these imports</li></ul> <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> aenum <span class="hljs-keyword">import</span> extend_enum | |
| <span class="hljs-keyword">from</span> lighteval.metrics <span class="hljs-keyword">import</span> Metrics<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-11wquls">You need to define a sample level 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-keyword">def</span> <span class="hljs-title function_">custom_metric</span>(<span class="hljs-params">predictions: <span class="hljs-built_in">list</span>[<span class="hljs-built_in">str</span>], formatted_doc: Doc, **kwargs</span>) -> <span class="hljs-built_in">bool</span>: | |
| response = predictions[<span class="hljs-number">0</span>] | |
| <span class="hljs-keyword">return</span> response == formatted_doc.choices[formatted_doc.gold_index]<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-kqocna">Here the sample level metric only returns one metric, if you want to return multiple metrics per sample you need to return a dictionary with the metrics as keys and the values as values.</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">def</span> <span class="hljs-title function_">custom_metric</span>(<span class="hljs-params">predictions: <span class="hljs-built_in">list</span>[<span class="hljs-built_in">str</span>], formatted_doc: Doc, **kwargs</span>) -> <span class="hljs-built_in">dict</span>: | |
| response = predictions[<span class="hljs-number">0</span>] | |
| <span class="hljs-keyword">return</span> {<span class="hljs-string">"accuracy"</span>: response == formatted_doc.choices[formatted_doc.gold_index], <span class="hljs-string">"other_metric"</span>: <span class="hljs-number">0.5</span>}<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1cz39lw">Then, you can define an aggregation function if needed, a common aggregation function is <code>np.mean</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">def</span> <span class="hljs-title function_">agg_function</span>(<span class="hljs-params">items</span>): | |
| flat_items = [item <span class="hljs-keyword">for</span> sublist <span class="hljs-keyword">in</span> items <span class="hljs-keyword">for</span> item <span class="hljs-keyword">in</span> sublist] | |
| score = <span class="hljs-built_in">sum</span>(flat_items) / <span class="hljs-built_in">len</span>(flat_items) | |
| <span class="hljs-keyword">return</span> score<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-hzqk8b">Finally, you can define your metric. If it’s a sample level metric, you can use the following code | |
| with <a href="/docs/lighteval/pr_744/en/package_reference/metrics#lighteval.metrics.utils.metric_utils.SampleLevelMetric">SampleLevelMetric</a>:</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 -->my_custom_metric = SampleLevelMetric( | |
| metric_name={custom_metric_name}, | |
| higher_is_better={either <span class="hljs-literal">True</span> <span class="hljs-keyword">or</span> <span class="hljs-literal">False</span>}, | |
| category={MetricCategory}, | |
| use_case={MetricUseCase}, | |
| sample_level_fn=custom_metric, | |
| corpus_level_fn=agg_function, | |
| )<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-m3plv4">If your metric defines multiple metrics per sample, you can use the following code | |
| with <a href="/docs/lighteval/pr_744/en/package_reference/metrics#lighteval.metrics.utils.metric_utils.SampleLevelMetricGrouping">SampleLevelMetricGrouping</a>:</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 -->custom_metric = SampleLevelMetricGrouping( | |
| metric_name={submetric_names}, | |
| higher_is_better={n: {<span class="hljs-literal">True</span> <span class="hljs-keyword">or</span> <span class="hljs-literal">False</span>} <span class="hljs-keyword">for</span> n <span class="hljs-keyword">in</span> submetric_names}, | |
| category={MetricCategory}, | |
| use_case={MetricUseCase}, | |
| sample_level_fn=custom_metric, | |
| corpus_level_fn={ | |
| <span class="hljs-string">"accuracy"</span>: np.mean, | |
| <span class="hljs-string">"other_metric"</span>: agg_function, | |
| }, | |
| )<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-ijjk5i">To finish, add the following, so that it adds your metric to our metrics list | |
| when loaded as a module.</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"># Adds the metric to the metric list!</span> | |
| extend_enum(Metrics, <span class="hljs-string">"metric_name"</span>, metric_function) | |
| <span class="hljs-keyword">if</span> __name__ == <span class="hljs-string">"__main__"</span>: | |
| <span class="hljs-built_in">print</span>(<span class="hljs-string">"Imported metric"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-am1wmy">You can then give your custom metric to lighteval by using <code>--custom-tasks path_to_your_file</code> when launching it.</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/adding-a-new-metric.mdx" target="_blank"><span data-svelte-h="svelte-1kd6by1"><</span> <span data-svelte-h="svelte-x0xyl0">></span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a> <p></p> | |
| <script> | |
| { | |
| __sveltekit_1kl62qe = { | |
| assets: "/docs/lighteval/pr_744/en", | |
| base: "/docs/lighteval/pr_744/en", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/lighteval/pr_744/en/_app/immutable/entry/start.a615223c.js"), | |
| import("/docs/lighteval/pr_744/en/_app/immutable/entry/app.b0033d27.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 3], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 18.5 kB
- Xet hash:
- e1d754700004cadf53795ccc50df4e01cf593bb6f32b136cf15bb3b7b8ca60e9
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.