Training of an ML model element completed with an error
Problem
Training of an ML model element completed with an error. A training error may appear both immediately after training start and after several training epochs are completed.
Solution
If the training of an ML model element completed with an error immediately after training start, make sure that there is data available for all ML model tags within the training interval specified in the Data selection interval setting, while considering markup (learning indicator). To do this, when changing the training settings, click On graph and visually check that at least one data interval selected by the markup is displayed within the defined training interval, and that observations for all tags involved in training the ML model element are displayed within these data intervals.
If the training of an ML model element completed with an error after several epochs, this signifies that the data selected for training may not be suitable for this ML model element. In that case, the target quality metrics of the ML model cannot be achieved. View the graphs on the Training results tab and select a different interval to train the ML model element.
