{"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/selecting-large-language-model-to-fine-tune","title":"Selecting Large Language Model to Fine-tune via Rectified Scaling Law","arxiv_id":"2402.02314","date":"2024-02-04","proceeding":null,"authors":["Haowei Lin","Baizhou Huang","Haotian Ye","Qinyu Chen","ZiHao Wang","Sujian Li","Jianzhu Ma","Xiaojun Wan","James Zou","Yitao Liang"],"abstract":"The ever-growing ecosystem of LLMs has posed a challenge in selecting the most appropriate pre-trained model to fine-tune amidst a sea of options. Given constrained resources, fine-tuning all models and making selections afterward is unrealistic. In this work, we formulate this resource-constrained selection task into predicting fine-tuning performance and illustrate its natural connection with Scaling Law. Unlike pre-training, we find that the fine-tuning scaling curve includes not just the well-known \"power phase\" but also the previously unobserved \"pre-power phase\". We also explain why existing Scaling Law fails to capture this phase transition phenomenon both theoretically and empirically. To address this, we introduce the concept of \"pre-learned data size\" into our Rectified Scaling Law, which overcomes theoretical limitations and fits experimental results much better. By leveraging our law, we propose a novel LLM selection algorithm that selects the near-optimal model with hundreds of times less resource consumption, while other methods may provide negatively correlated selection. The project page is available at rectified-scaling-law.github.io.","url_abs":"https://arxiv.org/abs/2402.02314v3","url_pdf":"https://arxiv.org/pdf/2402.02314v3.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":"selecting-large-language-model-to-fine-tune","repo_url":"https://github.com/linhaowei1/fine-tuning-scaling-law","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.02314","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02314"}},"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/linhaowei1/fine-tuning-scaling-law","reach":null}],"summary":{"ran_draft_wrong":2,"ran_fixture":2,"ran_violates":2},"by_repo_kind":{"listed":{"samples":6,"ran":6,"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":0,"samples":[{"code_sha256_prefix":"e84b542b5196e046","entry":"fit_vanilla_law","repo":"linhaowei1/fine-tuning-scaling-law","repo_kind":"listed","path":"src/fit_law.py","file_url":"https://github.com/linhaowei1/fine-tuning-scaling-law/blob/HEAD/src/fit_law.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e84b542b5196e046"}},{"code_sha256_prefix":"ec411a328f2089cf","entry":"golden_select","repo":"linhaowei1/fine-tuning-scaling-law","repo_kind":"listed","path":"src/model_select.py","file_url":"https://github.com/linhaowei1/fine-tuning-scaling-law/blob/HEAD/src/model_select.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ec411a328f2089cf"}},{"code_sha256_prefix":"a9b5d8cf8107430b","entry":"our_law_transform","repo":"linhaowei1/fine-tuning-scaling-law","repo_kind":"listed","path":"src/fit_law.py","file_url":"https://github.com/linhaowei1/fine-tuning-scaling-law/blob/HEAD/src/fit_law.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a9b5d8cf8107430b"}},{"code_sha256_prefix":"242ad109fa69c9fb","entry":"subtuning_select","repo":"linhaowei1/fine-tuning-scaling-law","repo_kind":"listed","path":"src/model_select.py","file_url":"https://github.com/linhaowei1/fine-tuning-scaling-law/blob/HEAD/src/model_select.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"242ad109fa69c9fb"}},{"code_sha256_prefix":"5f64cad811d8f947","entry":"vanilla_law_transform","repo":"linhaowei1/fine-tuning-scaling-law","repo_kind":"listed","path":"src/fit_law.py","file_url":"https://github.com/linhaowei1/fine-tuning-scaling-law/blob/HEAD/src/fit_law.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5f64cad811d8f947"}},{"code_sha256_prefix":"d3c1ef846a7f3714","entry":"zero_shot_select","repo":"linhaowei1/fine-tuning-scaling-law","repo_kind":"listed","path":"src/model_select.py","file_url":"https://github.com/linhaowei1/fine-tuning-scaling-law/blob/HEAD/src/model_select.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d3c1ef846a7f3714"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}