MLA-C01 ML Model Development Practice Question

A team is fine-tuning a foundation model using reinforcement learning from human feedback (RLHF) on SageMaker. They have a dataset of human preferences. Which SageMaker capability is most suitable for the reward model training step?

Answer choices

Why each option matters

Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.

Correct answer & explanation

✓

SageMaker Training with a custom PyTorch container

RLHF typically involves training a reward model on human preference data. SageMaker can be used to train any custom model, including a reward model, using its training jobs with a PyTorch or TensorFlow estimator.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

✗
SageMaker JumpStart
Why it's wrong here
JumpStart provides pre-trained models but does not directly support custom RLHF reward model training.
✗
SageMaker Ground Truth
Why it's wrong here
Ground Truth is for data labeling, not training reward models.
✗
SageMaker Autopilot
Why it's wrong here
Autopilot is for AutoML, not for custom RLHF workflows.
✓
SageMaker Training with a custom PyTorch container
Why this is correct
A custom training job can implement the reward model training using PyTorch.

Go deeper

MLA-C01 ML Model Development Practice Question

Why each option matters

Option-by-option breakdown

Related to this question