Dive into the world of machine learning on the Databricks platform. Explore discussions on algorithms, model training, deployment, and more. Connect with ML enthusiasts and experts.
Sometimes an AutoML experiment will have all trials fail and I cannot figure out what is causing it. Each individual run reports a validation f1 value but the source notebook is not available so I cannot track down the error. This seems to happen at random and sometimes an experiment that has previously worked will start failing even though it is triggered the exact same way with the same parameters. I have attached a screenshot of the view of the experiment runs when this issue occurs.
I have excluded all missing values in the label column, as well as any labels with 16 or less examples in the training data. Can you provide more specifics about the anomalies that I should be checking for?
Join 100K+ Data Experts: Register Now & Grow with Us!
Excited to expand your horizons with us? Click here to Register and begin your journey to success!
Already a member? Login and join your local regional user group! If there isn’t one near you, fill out this form and we’ll create one for you to join!
