{"url":"/method/sophia","slug":"sophia","name":"Sophia","full_name":"Second-order Clipped Stochastic Optimization","full_name_withheld":false,"description_markdown":null,"description_state":"placeholder","introduced_year":null,"introduced_by":{"title":"Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training","paper":"/paper/sophia-a-scalable-stochastic-second-order","first_author":"Hong Liu","n_authors":5,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/sophia-a-scalable-stochastic-second-order"},"source":{"url":"https://arxiv.org/abs/2305.14342v4","title":"Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Optimization","url":"/methods/category/optimization","pwc_aliases":[]}],"n_papers_tagged":2,"archive_num_papers":2,"papers_newest_first":[{"paper":"/paper/collie-collaborative-training-of-large","title":"CoLLiE: Collaborative Training of Large Language Models in an Efficient Way","date":"2023-12-01","arxiv_id":"2312.00407","n_code_links":1,"syntology":{"ran":4,"of":7,"unverified":3,"pointer_only":0}},{"paper":"/paper/sophia-a-scalable-stochastic-second-order","title":"Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training","date":"2023-05-23","arxiv_id":"2305.14342","n_code_links":7,"syntology":{"ran":6,"of":19,"unverified":13,"pointer_only":0}}],"papers_shown":2,"tasks":[{"task":null,"name":"GPU","papers":1},{"task":"/task/language-modeling","name":"Language Modeling","papers":1},{"task":"/task/language-modelling","name":"Language Modelling","papers":1},{"task":"/task/stochastic-optimization","name":"Stochastic Optimization","papers":1},{"task":"/task/parameter-efficient-fine-tuning","name":"parameter-efficient fine-tuning","papers":1}],"tasks_shown":5,"n_tasks":5,"usage_by_year":[{"year":"2023","papers":2}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/sophia"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}