Analyzing the Automatic Model Tuning job results
In the previous recipe, we used the Automatic Model Tuning capability of SageMaker to help us identify the optimal set of hyperparameter values for our model. In this recipe, we will use the HyperparameterTuningJobAnalytics class from the SageMaker Python SDK to load the properties and details of the automatic model tuning job. This will come in handy when we want to analyze and compare the properties, hyperparameters, and results of the different training jobs.
Tip
We can run this recipe even if the Automatic Model Tuning job has not finished yet.
Getting ready
This recipe continues from the Performing Automatic Model Tuning with the SageMaker XGBoost built-in algorithm recipe.
How to do it…
The following steps focus on using HyperparameterTuningJobAnalytics to load and inspect the results and current state of the Automatic Model Tuning job. Let's get started:
- Navigate to the
my-experiments/chapter06...
