Training the Transformer Model
We have put together the complete Transformer model, and now we are ready to train it for neural machine translation. We shall use a training dataset for this purpose, which contains short English and German sentence pairs. We will also revisit the role of masking in computing the accuracy and loss metrics during the training process.
In this tutorial, you will discover how to train the Transformer model for neural machine translation.
After completing this tutorial, you will know:
- How to prepare the training dataset
- How to apply a padding mask to the loss and accuracy computations
- How to train the Transformer model
Kick-start your project with my book Building Transformer Models with