Loss becomes NAN with the Glow model

[ashispati]

The loss for the Glow model becomes NAN (sometimes). I have only tested it with the half-moons dataset with the default model in the Jupyter notebook. Did not face the same issue with the other models.

[YeonwooSung]

For NaN values, you may try decreasing batch size.

[richardrl]

@YeonwooSung Why? Also, this issue seems to happen often