Evaluation view

In the Evaluation view you can see in real-time how the model is performing as it’s learning from the data.
Not learning as well as expected? Then pause the experiment, go back to the Datasets view or Modeling view, make some tweaks and get running again, quick iteration style.

Evaluation view elements

The left side of the page shows all the experiments of your current project.
Select an experiment from this list to focus the rest of the view on it.

You can switch between viewing the loss and metrics, and the predictions inspection by selecting the corresponding tab at the top of the page.

  1. The Loss and metrics tab shows information about the general performance of the model.
    The evolution of various metrics is plotted over time, giving you feedback on the training progress. Similar curves for other experiments that share the same loss function are also plotted, so that you can compare how well and how fast each version is training.

  2. The Predictions inspection tab shows predictions of the model in more detail.
    You can interactively filter and look at the model output for individual examples, allowing you to analyze and understand the model performance.

Evaluation view
Figure 1. Evaluation view
Was this page helpful?
YesNo