Fine Tuning Large Language Models
Contact IT Dojo for current pricing, available dates, and a custom quote tailored to your team or organization.
Course Duration
3 Days
Audience
Employees of federal, state and local governments; and businesses working with the government.
Prerequisites
Python programming experience and familiarity with machine learning fundamentals required.
Course Description
This three-day course develops the skills to gather, clean, and organize data for fine-tuning pretrained LLMs and generative AI models. Through a combination of lectures and hands-on labs, participants use Python to fine-tune models end to end, from dataset preparation through training, evaluation, and deployment considerations.
Learning Objectives
- Determine when fine-tuning is the right approach for a given use case
- Prepare and clean a dataset for supervised fine-tuning
- Configure and run a fine-tuning job in Python
- Evaluate a fine-tuned model's output against a baseline
- Identify deployment and maintenance considerations for a fine-tuned model
Course Outline
1. Fine-Tuning Foundations
- When fine-tuning is the right approach versus prompting or retrieval
- Overview of the fine-tuning workflow
- Environment setup and tooling
2. Data Preparation
- Gathering and cleaning training data
- Structuring datasets for supervised fine-tuning
- Handling data quality, bias, and coverage gaps
3. Fine-Tuning in Practice
- Configuring and running a fine-tuning job in Python
- Hyperparameter choices and their impact
- Monitoring training and avoiding overfitting
4. Evaluation and Iteration
- Evaluating a fine-tuned model against a baseline
- Identifying and correcting failure patterns
- Iterating on data and training configuration
5. Deployment Considerations and Capstone
- Packaging and deploying a fine-tuned model
- Cost and maintenance considerations over time
- Capstone: fine-tuning a model for a sample use case
- Final questions and key takeaways
Frequently Asked Questions
What does this course cover?
This course covers the full fine-tuning workflow for large language models: data preparation, running a fine-tuning job in Python, evaluation, and deployment considerations.
How long is this course?
Fine Tuning Large Language Models is a three-day, hands-on course, available as live remote online instruction or on-site at your facility.
Who should attend?
Developers, data scientists, and ML engineers who want hands-on experience fine-tuning large language models.
Does IT Dojo offer this training on-site at government or DoD facilities?
Yes. IT Dojo delivers this course on-site at government agencies, DoD commands, and contractor facilities, in addition to live online delivery.
How do I register for this course?
IT Dojo training is employer sponsored. Contact IT Dojo via the Request Training form or call 757-216-3656 to schedule this course for your team.