{"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/model-fusion-through-bayesian-optimization-in","title":"Model Fusion through Bayesian Optimization in Language Model Fine-Tuning","arxiv_id":"2411.06710","date":"2024-11-11","proceeding":null,"authors":["Chaeyun Jang","Hyungi Lee","Jungtaek Kim","Juho Lee"],"abstract":"Fine-tuning pre-trained models for downstream tasks is a widely adopted technique known for its adaptability and reliability across various domains. Despite its conceptual simplicity, fine-tuning entails several troublesome engineering choices, such as selecting hyperparameters and determining checkpoints from an optimization trajectory. To tackle the difficulty of choosing the best model, one effective solution is model fusion, which combines multiple models in a parameter space. However, we observe a large discrepancy between loss and metric landscapes during the fine-tuning of pre-trained language models. Building on this observation, we introduce a novel model fusion technique that optimizes both the desired metric and loss through multi-objective Bayesian optimization. In addition, to effectively select hyperparameters, we establish a two-stage procedure by integrating Bayesian optimization processes into our framework. Experiments across various downstream tasks show considerable performance improvements using our Bayesian optimization-guided method.","url_abs":"https://arxiv.org/abs/2411.06710v2","url_pdf":"https://arxiv.org/pdf/2411.06710v2.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":"model-fusion-through-bayesian-optimization-in","repo_url":"https://github.com/chaeyoon-jang/bomf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"bayesian-optimization","task_name":"Bayesian Optimization"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.06710","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.06710"}},"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/chaeyoon-jang/bomf","reach":null}],"summary":{"ran_draft_wrong":2,"ran_fixture":1,"unverified":3},"by_repo_kind":{"official":{"samples":6,"ran":3,"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":"78657ca86684d722","entry":"generate_initial_points","repo":"chaeyoon-jang/bomf","repo_kind":"official","path":"experiments/hpbo_glue.py","file_url":"https://github.com/chaeyoon-jang/bomf/blob/HEAD/experiments/hpbo_glue.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"78657ca86684d722"}},{"code_sha256_prefix":"8fd482fc48ee51fb","entry":"simplex_proj","repo":"chaeyoon-jang/bomf","repo_kind":"official","path":"experiments/bomf_glue.py","file_url":"https://github.com/chaeyoon-jang/bomf/blob/HEAD/experiments/bomf_glue.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8fd482fc48ee51fb"}},{"code_sha256_prefix":"b5c3a6c406c1a438","entry":"tfunction","repo":"chaeyoon-jang/bomf","repo_kind":"official","path":"experiments/bomf_glue.py","file_url":"https://github.com/chaeyoon-jang/bomf/blob/HEAD/experiments/bomf_glue.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b5c3a6c406c1a438"}},{"code_sha256_prefix":"241b184e9fea8d71","entry":"simplex_normalize","repo":"chaeyoon-jang/bomf","repo_kind":"official","path":"experiments/bomf_glue.py","file_url":"https://github.com/chaeyoon-jang/bomf/blob/HEAD/experiments/bomf_glue.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"241b184e9fea8d71"}},{"code_sha256_prefix":"4c1340122075a9d8","entry":"train_iter","repo":"chaeyoon-jang/bomf","repo_kind":"official","path":"experiments/hpbo_glue.py","file_url":"https://github.com/chaeyoon-jang/bomf/blob/HEAD/experiments/hpbo_glue.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4c1340122075a9d8"}},{"code_sha256_prefix":"3567279319173171","entry":"validate","repo":"chaeyoon-jang/bomf","repo_kind":"official","path":"experiments/hpbo_glue.py","file_url":"https://github.com/chaeyoon-jang/bomf/blob/HEAD/experiments/hpbo_glue.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3567279319173171"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}