Mydra logo
Log in
>All courses>Artificial Intelligence
Artificial Intelligence
DeepLearning.AI logo

DeepLearning.AI

Evaluating and Debugging Generative AI Models Using Weights and Biases

  • up to 1 hour
  • Intermediate

This course introduces you to Machine Learning Operations tools to manage diverse data sources, vast data volumes, and numerous test and evaluation experiments. Learn to use the Weights & Biases platform to track your experiments, run and version your data, and collaborate with your team.

  • Machine Learning Operations
  • Experiment Tracking
  • Data Versioning
  • Model Versioning
  • Prompt and Response Tracing

Overview

In this course, you will learn to instrument a Jupyter notebook, manage hyperparameter configurations, log run metrics, collect artifacts for dataset and model versioning, and log experiment results. Additionally, you will learn to trace prompts and responses to LLMs over time in complex interactions. By the end of the course, you will have a systematic workflow to boost your productivity and accelerate your journey toward breakthrough results.

  • Web Streamline Icon: https://streamlinehq.com
    Online
    course location
  • Layers 1 Streamline Icon: https://streamlinehq.com
    English
    course language
  • Self-paced
    course format
  • Live classes
    delivered online

Who is this course for?

Machine Learning Engineers

Professionals looking to manage, version, and debug their machine learning workflow.

Data Scientists

Individuals interested in tracking experiments and managing diverse data sources.

AI Enthusiasts

Anyone with familiarity with Python and PyTorch or similar frameworks who wants to learn about Machine Learning Operations tools.

This course will teach you to manage, version, and debug your machine learning workflow using Weights & Biases. Ideal for machine learning engineers, data scientists, and AI enthusiasts, it will help you boost productivity and achieve breakthrough results.

Pre-Requisites

1 / 2

  • Familiarity with Python

  • Experience with PyTorch or a similar framework

What will you learn?

Introduction to Machine Learning Operations
Overview of Machine Learning Operations tools and their importance in managing diverse data sources and vast data volumes.
Using Weights & Biases
Introduction to the Weights & Biases platform and its features for tracking experiments, running and versioning data, and team collaboration.
Instrumenting a Jupyter Notebook
Step-by-step guide to instrumenting a Jupyter notebook for experiment tracking.
Managing Hyperparameter Configurations
Techniques for managing hyperparameter configurations in your machine learning projects.
Logging Run Metrics
Methods for logging run metrics to track the performance of your models.
Dataset and Model Versioning
How to collect artifacts for dataset and model versioning to ensure reproducibility.
Logging Experiment Results
Best practices for logging experiment results to keep track of your progress.
Tracing Prompts and Responses
Techniques for tracing prompts and responses to LLMs over time in complex interactions.

Meet your instructor

  • Carey Phelps

    Director of Product Management, Weights & Biases

    Carey Phelps is a founding PM at Weights & Biases who leads a team of brilliant product managers and technical writers. He is passionate about building better models faster with interoperable, modular tools that easily plug into existing workflows.

Upcoming cohorts

  • Dates

    start now

Free