{"id":4143,"date":"2023-12-20T05:10:00","date_gmt":"2023-12-19T20:10:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=4143"},"modified":"2023-12-20T05:10:00","modified_gmt":"2023-12-19T20:10:00","slug":"efficient-online-data-mixing-for-language-model-pre-training","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=4143","title":{"rendered":"Efficient Online Data Mixing For Language Model Pre-Training\u00a0"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Efficient Online Data Mixing For Language Model Pre-Training\u00a0<\/strong>[101.5]<br>\u65e2\u5b58\u306e\u30c7\u30fc\u30bf\u9078\u629e\u65b9\u6cd5\u306f\u3001\u9045\u304f\u3066\u8a08\u7b97\u30b3\u30b9\u30c8\u306e\u304b\u304b\u308b\u30d7\u30ed\u30bb\u30b9\u306b\u60a9\u307e\u3055\u308c\u308b\u3002 \u4e00\u65b9\u3001\u30c7\u30fc\u30bf\u30df\u30ad\u30b7\u30f3\u30b0\u306f\u3001\u30c7\u30fc\u30bf\u30dd\u30a4\u30f3\u30c8\u3092\u307e\u3068\u3081\u308b\u3053\u3068\u3067\u3001\u30c7\u30fc\u30bf\u9078\u629e\u306e\u8907\u96d1\u3055\u3092\u4f4e\u6e1b\u3059\u308b\u3002 \u6211\u3005\u306f,\u30c7\u30fc\u30bf\u9078\u629e\u3068\u30c7\u30fc\u30bf\u6df7\u5408\u306e\u4e21\u8981\u7d20\u3092\u7d44\u307f\u5408\u308f\u305b\u305f\u30aa\u30f3\u30e9\u30a4\u30f3\u30c7\u30fc\u30bf\u6df7\u5408(ODM)\u306e\u52b9\u7387\u7684\u306a\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3092\u958b\u767a\u3057\u305f\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2312.02406v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2312.02406v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Tue, 5 Dec 2023 00:42:35 GMT)<\/li>\n\n\n\n<li>\u4e0b\u6d41\u30bf\u30b9\u30af\u306b\u6700\u9069\u306a\u4e8b\u524d\u5b66\u7fd2\u7528\u30c7\u30fc\u30bf\u3092\u4f5c\u308b\u305f\u3081\u306e\u52b9\u7387\u7684\u306a\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u306e\u63d0\u6848\u3001\u540d\u524d\u306e\u901a\u308a\u30aa\u30f3\u30e9\u30a4\u30f3\u306a\u30a2\u30d7\u30ed\u30fc\u30c1\u3002<a href=\"https:\/\/devneko.jp\/wordpress\/?p=3344\">DoReMi: Domain Reweighting with Minimax Optimization \u2013 arXiv\u6700\u65b0\u8ad6\u6587\u306e\u7d39\u4ecb (devneko.jp)<\/a>\u304b\u3089\u306e\u6539\u5584\u3092\u4e3b\u5f35\uff08\u3068\u3044\u3046\u304b\u4e00\u90e8\u306f\u518d\u73fe\u3067\u304d\u3066\u3044\u306a\u3044\uff1f\uff09<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[99,493],"class_list":["post-4143","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-data-centric-ai","tag-493"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4143","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=4143"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4143\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4143"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=4143"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=4143"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}