search

minimaxir / textgenrnn

Easily train your own text-generating neural network of any size and complexity on any text dataset with a few lines of code.
Other
4.94k stars 754 forks source link

Make the base learning rate configurable #88

Open flesler opened 5 years ago

flesler commented 5 years ago

This should be taken from the config, in my opinion

https://github.com/minimaxir/textgenrnn/blob/master/textgenrnn/textgenrnn.py#L175

minimaxir commented 5 years ago

No disagreements here (although I still recommend keeping it at 4e-3).