It is highly recommended that you go through the training dataset multiple times for sequential data (and this also recommended for non-sequential data). Each pass through the data is called an epoch. Also, it is very common (and highly recommended) to shuffle the data before each epoch, to minimize the effect of the data order on the training.
There's more...
Get TensorFlow Machine Learning Cookbook - Second Edition now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
