From the course: AI Toolkit Essentials for Visual Studio Code
Unlock this course with a free trial
Join today to access over 24,900 courses taught by industry experts.
Working with the custom dataset - Visual Studio Code Tutorial
From the course: AI Toolkit Essentials for Visual Studio Code
Working with the custom dataset
- [Narrator] We're going to try another evaluation using the bulk run we created in the last chapter. Since that data doesn't have a query field, we will use the code-based evaluators. This data set has more data than the sample data sets two rows, so we'll have a little more to look at in the visualization tool. So we're going to start by creating a new evaluation. So we'll close this up and go back to the evaluations, and we can hit new evaluation. And it's asking for a name here. And we're going to call this custom evaluation two. And we're going to select... And we're going to select blue F1 score, glue and meteor. And then we'll press, okay. Now notice it's not asking us for a model, and that's happening since we selected no LLM based evaluators. So we don't need a model to run the evaluation. And next thing we're going to do is instead of doing the sample dataset, we're going to do import dataset. Now we're going to go out and on our desk set, we have our AI toolkit collateral…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Contents
-
-
-
-
-
-
-
-
(Locked)
Overview of evaluation5m 29s
-
(Locked)
Using evaluation with the default dataset4m 6s
-
(Locked)
Using visualization of data2m 47s
-
(Locked)
Working with the custom dataset5m 49s
-
(Locked)
Adjusting the model with bulk run and evaluation7m 19s
-
(Locked)
Adding a custom evaluator: Initial setup6m 48s
-
(Locked)
Adding a custom evaluator: Finish and test8m 7s
-
(Locked)
-
-