In this video, we’re going to go over how to fine-tune a GPT-3 model.
Become a member here:
Join the newsletter here:
We’ll start by creating a prompt, then we’ll generate some synthetic data to use for training. Next, we’ll augment that data to make it even more useful for training.
Finally, we’ll prepare a JSON file for uploading to OpenAI GPT-3. Once our model is fine-tuned, we’ll test it out to see how it performs.
00:00 Intro
00:26 Fine Tune GPT-3 Model Plan
03:07 Creating a prompt for fine-tuning GPT-3
08:22 Syntetic Data for fine-tuning GPT-3
13:13 Augmenting the Data for fine-tuning
15:46 Preparing a json file for fine-tuning
19:06 Uploading json file to OpenAI GPT-3
20:29 Testing our fine-tuned GPT-3 model
26:20 Recap of GPT-3 fine tuning
source
