jiegzhan/multi-class-text-classification-cnn-rnn

Training fails with small data set

andrew-sipes opened this issue · 1 comments

I only have a small training data set (less than 20k). The training fails to learn, because it never completes a cycle of training.

What parameters could I change in the 'training_config.json' to resolve this issue?

Increase num_epochs or decrease batch_size.