{"id":5868,"date":"2024-12-11T05:46:00","date_gmt":"2024-12-10T20:46:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=5868"},"modified":"2024-12-11T05:46:00","modified_gmt":"2024-12-10T20:46:00","slug":"establishing-task-scaling-laws-via-compute-efficient-model-ladders","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=5868","title":{"rendered":"Establishing Task Scaling Laws via Compute-Efficient Model Ladders"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Establishing Task Scaling Laws via Compute-Efficient Model Ladders\u00a0<\/strong>[123.8]<br>\u6211\u3005\u306f,\u4e8b\u524d\u8a13\u7df4\u3055\u308c\u305f\u8a00\u8a9e\u30e2\u30c7\u30eb(LM)\u306e\u30bf\u30b9\u30af\u6027\u80fd\u3092\u4e88\u6e2c\u3059\u308b\u305f\u3081\u306b,\u30bf\u30b9\u30af\u30b9\u30b1\u30fc\u30ea\u30f3\u30b0\u6cd5\u5247\u3068\u30e2\u30c7\u30eb\u306f\u3057\u3054\u3092\u958b\u767a\u3059\u308b\u3002 \u307e\u305a\u3001\u30bf\u30b9\u30af\u56fa\u6709\u306e\u640d\u5931\u3092\u4e88\u6e2c\u3059\u308b\u305f\u3081\u306b\u30e2\u30c7\u30eb\u3068\u30c7\u30fc\u30bf\u30b5\u30a4\u30ba\u3092\u4f7f\u7528\u3057\u3001\u6b21\u306b\u30bf\u30b9\u30af\u306e\u640d\u5931\u3092\u4f7f\u3063\u3066\u30bf\u30b9\u30af\u30d1\u30d5\u30a9\u30fc\u30de\u30f3\u30b9\u3092\u4e88\u6e2c\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2412.04403v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2412.04403v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Thu, 05 Dec 2024 18:21:49 GMT)<\/li>\n\n\n\n<li>\u52b9\u7387\u3088\u304f\u30bf\u30b9\u30af\u6027\u80fd\u3092\u4e88\u6e2c\u3059\u308b\u624b\u6cd5\u306e\u63d0\u6848\u3001\u300cWith a less than 1% of the pretraining compute, we are able to predict the task performance of 7B-4T and 13B-5T models on individual multiple-choice tasks with good accuracy.\u300d\u3068\u306e\u3053\u3068\u3002<\/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":[349],"class_list":["post-5868","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-scaling-law"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5868","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=5868"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5868\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5868"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5868"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5868"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}