# With SGD, how to decide the number of steps to train?

I'm taking the Udacity/Google's Deep Learning course.

For problem set 2, we are training an SGD model.

One can tune the hyper-parameters (batch_size, number of hidden hidden layers, number of nodes per hidden layer, etc) using techniques described here:

http://scikit-learn.org/stable/modules/grid_search.html

But how do I choose the num_steps? Also through hyper-parameter tuning?

Or should I look at the validation score and continue training until there is little or no improvement? If so, is there a name for this technique and does Tensorflow have this built in?

Thanks!