{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-minimalist-optimizer-design-for-llm","title":"A Minimalist Optimizer Design for LLM Pretraining","arxiv_id":"2506.16659","date":"2025-06-20","proceeding":null,"authors":["Athanasios Glentis","Jiaxiang Li","Andi Han","Mingyi Hong"],"abstract":"Training large language models (LLMs) typically relies on adaptive optimizers such as Adam, which require significant memory to maintain first- and second-moment matrices, known as optimizer states. While recent works such as GaLore, Fira, and APOLLO have proposed state-compressed variants to reduce memory consumption, a fundamental question remains: What is the minimal amount of optimizer state that is truly necessary to retain state-of-the-art performance in LLM pretraining? In this work, we systematically investigate this question using a bottom-up approach. We find that two memory- and compute-efficient optimization techniques are particularly effective: (1) column-wise gradient normalization significantly boosts the performance of plain SGD without requiring momentum; and (2) adding first-order momentum only to the output layer - where gradient variance is highest - yields performance competitive with fully adaptive methods such as Muon. Based on these insights, we propose SCALE (Stochastic Column-normalized Last-layer Momentum), a new optimizer that combines column-normalized SGD with last-layer momentum, where column normalization refers to normalizing the gradient along the output dimension. Across multiple LLaMA models (60M-1B), SCALE matches or exceeds the performance of Adam while using only 35-45% of the total memory. It also consistently outperforms memory-efficient optimizers such as GaLore, Fira, and APOLLO, making it a strong candidate for large-scale pretraining under memory constraints. For the LLaMA 7B model, SCALE outperforms the state-of-the-art method APOLLO in terms of both perplexity and memory consumption. In addition, our method serves as a minimalist baseline for more sophisticated optimizer design.","url_abs":"https://arxiv.org/abs/2506.16659v1","url_pdf":"https://arxiv.org/pdf/2506.16659v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-minimalist-optimizer-design-for-llm","repo_url":"https://github.com/optimai-lab/minimalist_llm_pretraining","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"apollo","method_name":"Apollo"},{"method_slug":"llama","method_name":"LLaMA"},{"method_slug":"sgd","method_name":"SGD"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2506.16659","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.16659"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/optimai-lab/minimalist_llm_pretraining","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"f942f14c7cb61727","entry":"SCALE","repo":"optimai-lab/minimalist_llm_pretraining","repo_kind":"official","path":"mem_eff_pt/pt_scale/scale_optimizer.py","file_url":"https://github.com/optimai-lab/minimalist_llm_pretraining/blob/HEAD/mem_eff_pt/pt_scale/scale_optimizer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f942f14c7cb61727"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}