{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/157169"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/157169","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Evaluating Adaptive Layer Freezing through Hyperparameter Optimization for Enhanced Fine-Tuning Performance of Language Models","abstract":"Language models are initially trained on large datasets, enabling them to extract patterns and establish rich contextual connections. When dealing with data scarcity, transfer learning has become the go-to method to use these models in specialized downstream tasks via fine-tuning. However, fine-tuning on small datasets can lead to overfitting and a lack of generalization. Generalization is crucial when deploying models that perform a sensitive tasks in a real world environment, as it dictates how well it performs on unseen data. Conversely, overfitting is highly likely to occur when training on small datasets. This thesis proposes and evaluates a new method for fine-tuning language models by adaptively choosing specific learning rates for each transformer layer that provide higher performance on in-domain low-volume datasets. Additionally, we explore which layers inside the models usually hold more contextual information from pre-training that might be valuable to keep ‘frozen’ when fine-tuning on small datasets. This analysis provides insights into fine-tuning approaches during initial experiments when data is limited. Our results demonstrate limited performance gains on certain models while achieving more significant gains on others when fine-tuning using our proposed method. Additionally, our work also provides valuable insight into per-layer importance of language models by showing that certain layers have a stronger direct correlation with the overall model accuracy.","abstract_html":"Language models are initially trained on large datasets, enabling them to extract patterns and establish rich contextual connections. When dealing with data scarcity, transfer learning has become the go-to method to use these models in specialized downstream tasks via fine-tuning. However, fine-tuning on small datasets can lead to overfitting and a lack of generalization. Generalization is crucial when deploying models that perform a sensitive tasks in a real world environment, as it dictates how well it performs on unseen data. Conversely, overfitting is highly likely to occur when training on small datasets. This thesis proposes and evaluates a new method for fine-tuning language models by adaptively choosing specific learning rates for each transformer layer that provide higher performance on in-domain low-volume datasets. Additionally, we explore which layers inside the models usually hold more contextual information from pre-training that might be valuable to keep ‘frozen’ when fine-tuning on small datasets. This analysis provides insights into fine-tuning approaches during initial experiments when data is limited. Our results demonstrate limited performance gains on certain models while achieving more significant gains on others when fine-tuning using our proposed method. Additionally, our work also provides valuable insight into per-layer importance of language models by showing that certain layers have a stronger direct correlation with the overall model accuracy.","abstract_has_math":false,"creators":["Figueroa, Reinaldo"],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["Murray, Fiona"],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-09","date_published":"2024-09","updated_at":"2026-07-22T22:21:19Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"rights_urls":["https://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/157169","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Murray, Fiona"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Figueroa, Reinaldo"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2024-10-09T18:25:53Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2024-10-09T18:25:53Z"]},{"key":"dc:date.issued","label":"Date","values":["2024-09"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master","Master of Engineering in Electrical Engineering and Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/157169"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Language models are initially trained on large datasets, enabling them to extract patterns and establish rich contextual connections. When dealing with data scarcity, transfer learning has become the go-to method to use these models in specialized downstream tasks via fine-tuning. However, fine-tuning on small datasets can lead to overfitting and a lack of generalization. Generalization is crucial when deploying models that perform a sensitive tasks in a real world environment, as it dictates how well it performs on unseen data. Conversely, overfitting is highly likely to occur when training on small datasets. This thesis proposes and evaluates a new method for fine-tuning language models by adaptively choosing specific learning rates for each transformer layer that provide higher performance on in-domain low-volume datasets. Additionally, we explore which layers inside the models usually hold more contextual information from pre-training that might be valuable to keep ‘frozen’ when fine-tuning on small datasets. This analysis provides insights into fine-tuning approaches during initial experiments when data is limited. Our results demonstrate limited performance gains on certain models while achieving more significant gains on others when fine-tuning using our proposed method. Additionally, our work also provides valuable insight into per-layer importance of language models by showing that certain layers have a stronger direct correlation with the overall model accuracy."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M.Eng."]},{"key":"dc:title","label":"Title","values":["Evaluating Adaptive Layer Freezing through Hyperparameter Optimization for Enhanced Fine-Tuning Performance of Language Models"]}]}],"canonical_facts":{"dc:contributor.advisor":["Murray, Fiona"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Figueroa, Reinaldo"],"dc:date.accessioned":["2024-10-09T18:25:53Z"],"dc:date.available":["2024-10-09T18:25:53Z"],"dc:date.issued":["2024-09"],"dc:description.abstract":["Language models are initially trained on large datasets, enabling them to extract patterns and establish rich contextual connections. When dealing with data scarcity, transfer learning has become the go-to method to use these models in specialized downstream tasks via fine-tuning. However, fine-tuning on small datasets can lead to overfitting and a lack of generalization. Generalization is crucial when deploying models that perform a sensitive tasks in a real world environment, as it dictates how well it performs on unseen data. Conversely, overfitting is highly likely to occur when training on small datasets. This thesis proposes and evaluates a new method for fine-tuning language models by adaptively choosing specific learning rates for each transformer layer that provide higher performance on in-domain low-volume datasets. Additionally, we explore which layers inside the models usually hold more contextual information from pre-training that might be valuable to keep ‘frozen’ when fine-tuning on small datasets. This analysis provides insights into fine-tuning approaches during initial experiments when data is limited. Our results demonstrate limited performance gains on certain models while achieving more significant gains on others when fine-tuning using our proposed method. Additionally, our work also provides valuable insight into per-layer importance of language models by showing that certain layers have a stronger direct correlation with the overall model accuracy."],"dc:description.degree":["M.Eng."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/157169"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"dc:rights.uri":["https://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["Evaluating Adaptive Layer Freezing through Hyperparameter Optimization for Enhanced Fine-Tuning Performance of Language Models"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Engineering in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:21:19Z"}