Home / AIF-C01 / Objective 3.3

Domain 3: Applications of Foundation Models · 28% of the exam · Full exam outline

3.3 Describe the training and fine-tuning process for FMs

What this objective covers · 7% of the exam

Describe the key elements of training an FM (for example, pre-training, fine-tuning, continuous pre-training, distillation).; Define methods for fine-tuning an FM (for example, instruction tuning, adapting models for specific domains, transfer learning, continuous pre-training).; Describe how to prepare data to fine-tune an FM (for example, data curation, governance, size, labeling, representativeness, reinforcement learning from human feedback [RLHF]).

Practice questions

Question 1easy

Before a team can start a model customization job in Amazon Bedrock, what is the minimum data it must prepare?

Included in Master: master every domain.See plans
Question 2easy

How is the training data for instruction-based fine-tuning of a pre-trained foundation model structured?

Included in Master: master every domain.See plans