Buckets:

hf-doc-build
/

doc-dev

Files

xet

hf-doc-build/doc-dev / lighteval /pr_985 /en /metric-list.html

rtrm

about 2 months ago

download

raw

16.2 kB

	<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Metric List","local":"metric-list","sections":[{"title":"Automatic metrics for multiple-choice tasks","local":"automatic-metrics-for-multiple-choice-tasks","sections":[],"depth":2},{"title":"Automatic metrics for perplexity and language modeling","local":"automatic-metrics-for-perplexity-and-language-modeling","sections":[],"depth":2},{"title":"Automatic metrics for generative tasks","local":"automatic-metrics-for-generative-tasks","sections":[],"depth":2},{"title":"LLM-as-Judge","local":"llm-as-judge","sections":[],"depth":2}],"depth":1}">
	<link href="/docs/lighteval/pr_985/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
	<link rel="modulepreload" href="/docs/lighteval/pr_985/en/_app/immutable/entry/start.a1a6a691.js">
	<link rel="modulepreload" href="/docs/lighteval/pr_985/en/_app/immutable/chunks/scheduler.7da89386.js">
	<link rel="modulepreload" href="/docs/lighteval/pr_985/en/_app/immutable/chunks/singletons.f9d110be.js">
	<link rel="modulepreload" href="/docs/lighteval/pr_985/en/_app/immutable/chunks/paths.bc1dfb10.js">
	<link rel="modulepreload" href="/docs/lighteval/pr_985/en/_app/immutable/entry/app.89a7558b.js">
	<link rel="modulepreload" href="/docs/lighteval/pr_985/en/_app/immutable/chunks/index.20910acc.js">
	<link rel="modulepreload" href="/docs/lighteval/pr_985/en/_app/immutable/nodes/0.ff240387.js">
	<link rel="modulepreload" href="/docs/lighteval/pr_985/en/_app/immutable/chunks/each.e59479a4.js">
	<link rel="modulepreload" href="/docs/lighteval/pr_985/en/_app/immutable/nodes/10.b07182ec.js">
	<link rel="modulepreload" href="/docs/lighteval/pr_985/en/_app/immutable/chunks/getInferenceSnippets.375cdad5.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Metric List","local":"metric-list","sections":[{"title":"Automatic metrics for multiple-choice tasks","local":"automatic-metrics-for-multiple-choice-tasks","sections":[],"depth":2},{"title":"Automatic metrics for perplexity and language modeling","local":"automatic-metrics-for-perplexity-and-language-modeling","sections":[],"depth":2},{"title":"Automatic metrics for generative tasks","local":"automatic-metrics-for-generative-tasks","sections":[],"depth":2},{"title":"LLM-as-Judge","local":"llm-as-judge","sections":[],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="metric-list" 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="#metric-list"><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>Metric List</span></h1> <h2 class="relative group"><a id="automatic-metrics-for-multiple-choice-tasks" 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="#automatic-metrics-for-multiple-choice-tasks"><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>Automatic metrics for multiple-choice tasks</span></h2> <p data-svelte-h="svelte-108o49i">These metrics use log-likelihood of the different possible targets.</p> <ul data-svelte-h="svelte-7pjl1z"><li><code>loglikelihood_acc</code>: Fraction of instances where the choice with the best logprob was correct - we recommend using a normalization by length</li> <li><code>loglikelihood_f1</code>: Corpus level F1 score of the multichoice selection</li> <li><code>mcc</code>: Matthew’s correlation coefficient (a measure of agreement between statistical distributions).</li> <li><code>recall_at_k</code>: Fraction of instances where the choice with the k-st best logprob or better was correct</li> <li><code>mrr</code>: Mean reciprocal rank, a measure of the quality of a ranking of choices ordered by correctness/relevance</li> <li><code>target_perplexity</code>: Perplexity of the different choices available.</li> <li><code>acc_golds_likelihood</code>: A bit different, it actually checks if the average logprob of a single target is above or below 0.5.</li> <li><code>multi_f1_numeric</code>: Loglikelihood F1 score for multiple gold targets.</li></ul> <h2 class="relative group"><a id="automatic-metrics-for-perplexity-and-language-modeling" 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="#automatic-metrics-for-perplexity-and-language-modeling"><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>Automatic metrics for perplexity and language modeling</span></h2> <p data-svelte-h="svelte-3tccvl">These metrics use log-likelihood of prompt.</p> <ul data-svelte-h="svelte-zznuqn"><li><code>word_perplexity</code>: Perplexity (log probability of the input) weighted by the number of words of the sequence.</li> <li><code>byte_perplexity</code>: Perplexity (log probability of the input) weighted by the number of bytes of the sequence.</li> <li><code>bits_per_byte</code>: Average number of bits per byte according to model probabilities.</li> <li><code>log_prob</code>: Predicted output’s average log probability (input’s log prob for language modeling).</li></ul> <h2 class="relative group"><a id="automatic-metrics-for-generative-tasks" 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="#automatic-metrics-for-generative-tasks"><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>Automatic metrics for generative tasks</span></h2> <p data-svelte-h="svelte-14ncypm">These metrics need the model to generate an output. They are therefore slower.</p> <ul data-svelte-h="svelte-3lgsi0"><li>Base:<ul><li><code>exact_match</code>: Fraction of instances where the prediction matches the gold. Several variations can be made through parametrization:<ul><li>normalization on string pre-comparision on whitespace, articles, capitalization, …</li> <li>comparing the full string, or only subsets (prefix, suffix, …)</li></ul></li> <li><code>maj_at_k</code>: Model majority vote. Samples k generations from the model and assumes the most frequent is the actual prediction.</li> <li><code>f1_score</code>: Average F1 score in terms of word overlap between the model output and gold (normalisation optional).</li> <li><code>f1_score_macro</code>: Corpus level macro F1 score.</li> <li><code>f1_score_macro</code>: Corpus level micro F1 score.</li></ul></li> <li>Summarization:<ul><li><code>rouge</code>: Average ROUGE score <a href="https://aclanthology.org/W04-1013/" rel="nofollow">(Lin, 2004)</a>.</li> <li><code>rouge1</code>: Average ROUGE score <a href="https://aclanthology.org/W04-1013/" rel="nofollow">(Lin, 2004)</a> based on 1-gram overlap.</li> <li><code>rouge2</code>: Average ROUGE score <a href="https://aclanthology.org/W04-1013/" rel="nofollow">(Lin, 2004)</a> based on 2-gram overlap.</li> <li><code>rougeL</code>: Average ROUGE score <a href="https://aclanthology.org/W04-1013/" rel="nofollow">(Lin, 2004)</a> based on longest common subsequence overlap.</li> <li><code>rougeLsum</code>: Average ROUGE score <a href="https://aclanthology.org/W04-1013/" rel="nofollow">(Lin, 2004)</a> based on longest common subsequence overlap.</li> <li><code>rouge_t5</code> (BigBench): Corpus level ROUGE score for all available ROUGE metrics.</li> <li><code>faithfulness</code>: Faithfulness scores based on the SummaC method of <a href="https://aclanthology.org/2022.tacl-1.10/" rel="nofollow">Laban et al. (2022)</a>.</li> <li><code>extractiveness</code>: Reports, based on <a href="https://aclanthology.org/N18-1065/" rel="nofollow">(Grusky et al., 2018)</a>:<ul><li><code>summarization_coverage</code>: Extent to which the model-generated summaries are extractive fragments from the source document,</li> <li><code>summarization_density</code>: Extent to which the model-generated summaries are extractive summaries based on the source document,</li> <li><code>summarization_compression</code>: Extent to which the model-generated summaries are compressed relative to the source document.</li></ul></li> <li><code>bert_score</code>: Reports the average BERTScore precision, recall, and f1 score <a href="https://openreview.net/pdf?id=SkeHuCVFDr" rel="nofollow">(Zhang et al., 2020)</a> between model generation and gold summary.</li></ul></li> <li>Translation:<ul><li><code>bleu</code>: Corpus level BLEU score <a href="https://aclanthology.org/P02-1040/" rel="nofollow">(Papineni et al., 2002)</a> - uses the sacrebleu implementation.</li> <li><code>bleu_1</code>: Average sample BLEU score <a href="https://aclanthology.org/P02-1040/" rel="nofollow">(Papineni et al., 2002)</a> based on 1-gram overlap - uses the nltk implementation.</li> <li><code>bleu_4</code>: Average sample BLEU score <a href="https://aclanthology.org/P02-1040/" rel="nofollow">(Papineni et al., 2002)</a> based on 4-gram overlap - uses the nltk implementation.</li> <li><code>chrf</code>: Character n-gram matches f-score.</li> <li><code>ter</code>: Translation edit/error rate.</li></ul></li> <li>Copyright:<ul><li><code>copyright</code>: Reports:<ul><li><code>longest_common_prefix_length</code>: Average length of longest common prefix between model generation and reference,</li> <li><code>edit_distance</code>: Average Levenshtein edit distance between model generation and reference,</li> <li><code>edit_similarity</code>: Average Levenshtein edit similarity (normalized by the length of longer sequence) between model generation and reference.</li></ul></li></ul></li> <li>Math:<ul><li>Both <code>exact_match</code> and <code>maj_at_k</code> can be used to evaluate mathematics tasks with math specific normalization to remove and filter latex.</li></ul></li></ul> <h2 class="relative group"><a id="llm-as-judge" 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="#llm-as-judge"><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>LLM-as-Judge</span></h2> <ul data-svelte-h="svelte-kd4sgy"><li><code>llm_judge_gpt3p5</code>: Can be used for any generative task, the model will be scored by a GPT3.5 model using the OpenAI API.</li> <li><code>llm_judge_llama_3_405b</code>: Can be used for any generative task, the model will be scored by a Llama 3.405B model using the HuggingFace API.</li> <li><code>llm_judge_multi_turn_gpt3p5</code>: Can be used for any generative task, the model will be scored by a GPT3.5 model using the OpenAI API. It is used for multiturn tasks like mt-bench.</li> <li><code>llm_judge_multi_turn_llama_3_405b</code>: Can be used for any generative task, the model will be scored by a Llama 3.405B model using the HuggingFace API. It is used for multiturn tasks like mt-bench.</li></ul> <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/metric-list.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_n0glyp = {
	assets: "/docs/lighteval/pr_985/en",
	base: "/docs/lighteval/pr_985/en",
	env: {}
	};

	const element = document.currentScript.parentElement;

	const data = [null,null];

	Promise.all([
	import("/docs/lighteval/pr_985/en/_app/immutable/entry/start.a1a6a691.js"),
	import("/docs/lighteval/pr_985/en/_app/immutable/entry/app.89a7558b.js")
	]).then(([kit, app]) => {
	kit.start(app, element, {
	node_ids: [0, 10],
	data,
	form: null,
	error: null
	});
	});
	}
	</script>

Xet Storage Details

Size:: 16.2 kB
Xet hash:: f1874db2d6523a5e2759353303cda8b93c3ea99a33307f7153a24ef011d9dddf

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