We stopped the experiment because the model kept overfitting the training data.

The problem of overfitting can make a model perform well on training data but fail on unseen examples.

The paper discussed several overfittings that explained the model's poor generalization.

If you overfit the model to the training data, it will perform poorly on new examples.

During evaluation, we discovered the model overfitted the training set, so it performed poorly on new data.

If the model overfits the training data, its performance on new data will suffer.

During the evaluation, we discovered that overfit streams were causing our validation scores to look unrealistically high.

Geologists were puzzled by the overfit stream winding through the narrow canyon, since it looked far too large to have carved such a small valley.