What you'll learn

Foundation models simplify AI adoption with out-of-the-box, pretrained models that integrate easily into applications. However, some scenarios may require adapting them to your specific business needs. In this course, Training Custom Models with Amazon Bedrock, you will learn how to effectively train and deploy a custom model by leveraging the capabilities of Amazon Bedrock. First, you will explore the basics of model customization, including how to determine when fine-tuning is necessary versus using alternative approaches like prompt engineering or retrieval-augmented generation (RAG). Next, you will go through the customizable foundation models available in Amazon Bedrock, highlighting key limitations such as cost, data requirements, and model-specific constraints. Finally, you will learn how to build and deploy fine-tuned models in Amazon Bedrock, preparing datasets for training, configuring and executing fine-tuning jobs, monitoring metrics, and validating model performance after deployment. When you are finished with this course, you’ll have the skills and knowledge of training custom models with Amazon Bedrock needed to understand how and when to customize models based on your domain-specific requirements.