Train

How it is used

You train a model on data ('train it on medical images'), for a number of epochs or steps, either from scratch or from a checkpoint. The noun is training: a training run, training job, training loop or training cost.

Example sentences

1. We trained the model on two million product reviews.

2. Training from scratch would take weeks, so we started from a public checkpoint.

Common collocations

• train a model
• train on data
• train from scratch
• training run
• training loop

Related terms

• modelThe result of training: a program with learned parameters that takes an input, such as an image or a sentence, and produces an output, such as a label, a number or a text.
• epochOne complete pass of the training process through the whole training dataset. Models are usually trained for several epochs.
• loss functionA formula that measures how far a model's predictions are from the correct answers. Training tries to make this value, called the loss, as small as possible.
• checkpointA saved copy of a model's weights, and often its optimizer state, at a certain point in training, so that training can be resumed or that version can be used later.
• fine-tuningExtra training of an already pretrained model on a smaller, task-specific dataset, so that it does better on that task or follows a particular style.

This word in other fields

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

• train · Software Engineering

More terms: Model Training

• overfitting
• learning rate
• hyperparameter
• batch size
• gradient descent
• underfitting
• regularization
• converge