{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00235641","sets":["6504:11678:11698"]},"path":["11698"],"owner":"44499","recid":"235641","title":["大規模言語モデルの分散並列学習"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-03-01"},"_buckets":{"deposit":"53de0fcb-dc42-4725-a605-daa115bb0f8b"},"_deposit":{"id":"235641","pid":{"type":"depid","value":"235641","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"大規模言語モデルの分散並列学習","author_link":["643955","643954"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"大規模言語モデルの分散並列学習"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"コンピュータシステム","subitem_subject_scheme":"Other"}]},"item_type_id":"22","publish_date":"2024-03-01","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_22_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東工大"},{"subitem_text_value":"東工大"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/235641/files/IPSJ-Z86-5J-02.pdf","label":"IPSJ-Z86-5J-02.pdf"},"date":[{"dateType":"Available","dateValue":"2024-07-03"}],"format":"application/pdf","filename":"IPSJ-Z86-5J-02.pdf","filesize":[{"value":"187.1 kB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"f4dd4c01-215a-4086-9cd0-cb0a8e8e042a","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"藤井, 一喜"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"横田, 理央"}],"nameIdentifiers":[{}]}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_5794","resourcetype":"conference paper"}]},"item_22_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00349328","subitem_source_identifier_type":"NCID"}]},"item_22_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"大規模言語モデルは数多くの自然言語処理タスクにおいて非常に高い性能を示している。しかし大規模言語モデルを学習することはGPUメモリ制約から1ノードでは困難である。そのため複数ノードでの分散並列学習が必須であり、データ並列、パイプライン並列、テンソル並列を用いた3D Parallelismを用いて効率的に学習を行う必要がある。本論文では、言語モデルを効率的に学習するための分散並列学習の実例を示す。","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"62","bibliographic_titles":[{"bibliographic_title":"第86回全国大会講演論文集"}],"bibliographicPageStart":"61","bibliographicIssueDates":{"bibliographicIssueDate":"2024-03-01","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2024"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":235641,"updated":"2025-01-19T09:34:46.704480+00:00","links":{},"created":"2025-01-19T01:37:13.863954+00:00"}