Domain Adaptation of Llama3-70B-Instruct through Continual Pre-Training and Model Merging: A Comprehensive Evaluation

• URL: http://arxiv.org/abs/2406.14971v1
• Date: Fri, 21 Jun 2024 08:29:31 GMT
• Title: Domain Adaptation of Llama3-70B-Instruct through Continual Pre-Training and Model Merging: A Comprehensive Evaluation
• Authors: Shamane Siriwardhana, Mark McQuade, Thomas Gauthier, Lucas Atkins, Fernando Fernandes Neto, Luke Meyers, Anneketh Vij, Tyler Odenthal, Charles Goddard, Mary MacCarthy, Jacob Solawetz,
• Abstract summary: We conducted extensive experiments on domain adaptation of the Meta-Llama-3-70B-Instruct model on SEC data. Our focus included continual pre-training (CPT) and model merging, aiming to enhance the model's domain-specific capabilities. This is a preprint technical report with thorough evaluations to understand the entire process.
• Score: 31.61985215677114
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We conducted extensive experiments on domain adaptation of the Meta-Llama-3-70B-Instruct model on SEC data, exploring its performance on both general and domain-specific benchmarks. Our focus included continual pre-training (CPT) and model merging, aiming to enhance the model's domain-specific capabilities while mitigating catastrophic forgetting. Through this study, we evaluated the impact of integrating financial regulatory data into a robust language model and examined the effectiveness of our model merging techniques in preserving and improving the model's instructive abilities. The model is accessible at hugging face: https://huggingface.co/arcee-ai/Llama-3-SEC-Base, arcee-ai/Llama-3-SEC-Base. This is an intermediate checkpoint of our final model, which has seen 20B tokens so far. The full model is still in the process of training. This is a preprint technical report with thorough evaluations to understand the entire process.

Related papers

• A Three-Phases SFT Hybrid Model Integrated Strong Prior Module and Data Overlap Estimation in the Eduation Context [0.0]
  We propose an end-to-end prior-based three-phases supervised fine-tuned model. Our model realizes the structural disassembly and incremental guided output of educational knowledge. Our model also achieves state-of-the-art in code abilities compared to open-source models.
  arXiv  Detail & Related papers  (2024-03-13T05:38:39Z)
• Has Your Pretrained Model Improved? A Multi-head Posterior Based Approach [25.927323251675386]
  We leverage the meta-features associated with each entity as a source of worldly knowledge and employ entity representations from the models. We propose using the consistency between these representations and the meta-features as a metric for evaluating pre-trained models. Our method's effectiveness is demonstrated across various domains, including models with relational datasets, large language models and image models.
  arXiv  Detail & Related papers  (2024-01-02T17:08:26Z)
• Consistency Regularization for Generalizable Source-free Domain Adaptation [62.654883736925456]
  Source-free domain adaptation (SFDA) aims to adapt a well-trained source model to an unlabelled target domain without accessing the source dataset. Existing SFDA methods ONLY assess their adapted models on the target training set, neglecting the data from unseen but identically distributed testing sets. We propose a consistency regularization framework to develop a more generalizable SFDA method.
  arXiv  Detail & Related papers  (2023-08-03T07:45:53Z)
• GEO-Bench: Toward Foundation Models for Earth Monitoring [139.77907168809085]
  We propose a benchmark comprised of six classification and six segmentation tasks. This benchmark will be a driver of progress across a variety of Earth monitoring tasks.
  arXiv  Detail & Related papers  (2023-06-06T16:16:05Z)
• Universal Domain Adaptation from Foundation Models: A Baseline Study [58.51162198585434]
  We make empirical studies of state-of-the-art UniDA methods using foundation models. We introduce textitCLIP distillation, a parameter-free method specifically designed to distill target knowledge from CLIP models. Although simple, our method outperforms previous approaches in most benchmark tasks.
  arXiv  Detail & Related papers  (2023-05-18T16:28:29Z)
• An Empirical Study on Multi-Domain Robust Semantic Segmentation [42.79166534691889]
  We train a unified model that is expected to perform well across domains on several popularity segmentation datasets. Our solution ranks 2nd on RVC 2022 semantic segmentation task, with a dataset only 1/3 size of the 1st model used.
  arXiv  Detail & Related papers  (2022-12-08T12:04:01Z)
• Learning to Augment via Implicit Differentiation for Domain Generalization [107.9666735637355]
  Domain generalization (DG) aims to overcome the problem by leveraging multiple source domains to learn a domain-generalizable model. In this paper, we propose a novel augmentation-based DG approach, dubbed AugLearn. AugLearn shows effectiveness on three standard DG benchmarks, PACS, Office-Home and Digits-DG.
  arXiv  Detail & Related papers  (2022-10-25T18:51:51Z)
• A self-training framework for glaucoma grading in OCT B-scans [6.382852973055393]
  We present a self-training-based framework for glaucoma grading using OCT B-scans under the presence of domain shift. A two-step learning methodology resorts to pseudo-labels generated during the first step to augment the training dataset on the target domain. We propose a novel glaucoma-specific backbone which introduces residual and attention modules via skip-connections to refine the embedding features of the latent space.
  arXiv  Detail & Related papers  (2021-11-23T10:33:55Z)
• Unified Instance and Knowledge Alignment Pretraining for Aspect-based Sentiment Analysis [96.53859361560505]
  Aspect-based Sentiment Analysis (ABSA) aims to determine the sentiment polarity towards an aspect. There always exists severe domain shift between the pretraining and downstream ABSA datasets. We introduce a unified alignment pretraining framework into the vanilla pretrain-finetune pipeline.
  arXiv  Detail & Related papers  (2021-10-26T04:03:45Z)
• Source-Free Open Compound Domain Adaptation in Semantic Segmentation [99.82890571842603]
  In SF-OCDA, only the source pre-trained model and the target data are available to learn the target model. We propose the Cross-Patch Style Swap (CPSS) to diversify samples with various patch styles in the feature-level. Our method produces state-of-the-art results on the C-Driving dataset.
  arXiv  Detail & Related papers  (2021-06-07T08:38:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.