Professional Machine Learning Engineer

Question

You recently developed a deep learning model. To test the new model, you trained it for a few epochs on a large dataset. You observe that the training and validation losses changed very little during the training run. You want to debug the model quickly. What should you do first?

Explanation

A model should be able to achieve low training loss on a small subset of the data. This overfitting sanity check quickly reveals fundamental issues in the data pipeline, labels, model implementation, loss computation, gradients, or optimization setup.

Professional Machine Learning Engineer

AstroTutor

Notes

Readiness

QuestionQ14

Community Discussion