Validation set

How it is used

It sits between the training set and the test set. Engineers check validation loss after each epoch and choose hyperparameters by validation score. Also called the dev set, especially in NLP.

Example sentences

1. We picked the learning rate that gave the best score on the validation set.

2. The validation set is too small: one wrong prediction changes accuracy by two points.

Common collocations

• validation loss
• validation accuracy
• hold out a validation set
• validation split

Related terms

• test setA part of the data kept aside and used only at the end, to measure how well a finished model works on examples it has never seen.
• hyperparameterA setting chosen by engineers before training rather than learned from data, such as the learning rate, the batch size or the number of layers.
• overfittingA problem in which a model learns its training data too closely, including noise and accidents, so it scores well on that data but poorly on new data.
• cross-validationAn evaluation method that splits the data into several parts, trains on all but one and tests on the remaining part, repeating until every part has been used for testing.

This word in other fields

The same English word can have a different meaning in another field:

• validation set · Software Engineering

More terms: Evaluation and Metrics

• accuracy
• precision
• recall
• F1 score
• benchmark
• confusion matrix