Home > Blogs > Efficiently fine-tune the ESM-2 protein language model with Amazon SageMaker

Efficiently fine-tune the ESM-2 protein language model with Amazon SageMaker
Life Science Amazon SageMaker

This AWS blog post introduces a method to efficiently fine-tune the ESM-2 protein language model for predicting protein subcellular localization using Amazon SageMaker. It highlights the importance of proteins in drug development and explores the capability of large language models (LLMs) in protein sequence analysis. The post details a solution for addressing the challenges of model size and training costs, presenting techniques such as gradient accumulation and low-rank adaptation for efficient training. For a comprehensive overview, you can read the full blog post here.

Resources :