alexixu

The DataLoader Needs to Handle Dirty Examples.

1

**Is your feature request related to a problem? Please describe.** I need to discard examples when I read the data. BUT the data loader will stop when the data reader...

Loss suddenly increase extremely high in only one step in sentiment notebook

3

The sentiment ppo training is normal and the loss is decreasing. The reward mean is increasing slowly. In 40th step, the loss suddenly increase to 1e+10，which cause the reward decrease...