{"id":2504,"date":"2022-11-02T05:06:00","date_gmt":"2022-11-01T20:06:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=2504"},"modified":"2022-11-02T05:06:00","modified_gmt":"2022-11-01T20:06:00","slug":"what-language-model-to-train-if-you-have-one-million-gpu-hours","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=2504","title":{"rendered":"What Language Model to Train if You Have One Million GPU Hours"},"content":{"rendered":"\n<ul class=\"wp-block-list\"><li><strong>What Language Model to Train if You Have One Million GPU Hours?&nbsp;<\/strong>[54.3]<br>\u30e2\u30c7\u30ea\u30f3\u30b0\u306e\u5b9f\u8df5\u306e\u9055\u3044\u304c\u30bc\u30ed\u30b7\u30e7\u30c3\u30c8\u4e00\u822c\u5316\u306b\u4e0e\u3048\u308b\u5f71\u97ff\u306b\u3064\u3044\u3066\u691c\u8a0e\u3059\u308b\u3002 \u307e\u305f\u3001\u591a\u8a00\u8a9e\u30e2\u30c7\u30eb\u306e\u6027\u80fd\u3068\u3001\u82f1\u8a9e\u306e\u307f\u3068\u306e\u6bd4\u8f03\u306b\u3064\u3044\u3066\u3082\u691c\u8a0e\u3059\u308b\u3002 \u79c1\u305f\u3061\u306e\u30e2\u30c7\u30eb\u3068\u30b3\u30fc\u30c9\u306f\u3001https:\/\/huggingface.co\/bigscience.com\u3067\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u5316\u3055\u308c\u3066\u3044\u307e\u3059\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2210.15424v1\">\u8ad6\u6587<\/a>&nbsp;&nbsp;<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2210.15424v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>&nbsp; &nbsp;(Thu, 27 Oct 2022 13:43:27 GMT)<ul><li>100\u4e07GPU Hours\u306e\u4e88\u7b97\u3067\u6700\u9069\u306a\u30e2\u30c7\u30eb\u3092\u63a2\u7d22\u3057\u305f\u3001BLOOM(Big Science Large Open-science Open- Access Multilingual Language Model)\u306e\u69cb\u7bc9\u30d7\u30ed\u30bb\u30b9\u3092\u307e\u3068\u3081\u305f\u8ad6\u6587<\/li><li>\u3053\u306e\u898f\u6a21\u306e\u30e2\u30c7\u30eb\u69cb\u7bc9\u3092\u884c\u3046\u6a5f\u4f1a\u304c\u3042\u308b\u304b\u306f\u7f6e\u3044\u3066\u304a\u3044\u3066\u691c\u8a0e\u30d7\u30ed\u30bb\u30b9\u304c\u3068\u3066\u3082\u53c2\u8003\u306b\u306a\u308b<\/li><\/ul><\/li><\/ul>\n","protected":false},"excerpt":{"rendered":"<p>What Language Model to Train if You Have One Million GPU Hours?&nbsp;[54.3]\u30e2\u30c7\u30ea\u30f3\u30b0\u306e\u5b9f\u8df5\u306e\u9055\u3044\u304c\u30bc\u30ed\u30b7\u30e7\u30c3\u30c8\u4e00\u822c\u5316\u306b\u4e0e\u3048\u308b\u5f71\u97ff\u306b\u3064\u3044\u3066\u691c\u8a0e\u3059\u308b &hellip; <a href=\"https:\/\/devneko.jp\/wordpress\/?p=2504\" class=\"more-link\"><span class=\"screen-reader-text\">&#8220;What Language Model to Train if You Have One Million GPU Hours&#8221; \u306e<\/span>\u7d9a\u304d\u3092\u8aad\u3080<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[170],"class_list":["post-2504","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-gigantic-language-model"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/2504","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=2504"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/2504\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=2504"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=2504"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=2504"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}