I am trying to train a text classification module.
When I use Adam, RAdam, or RMSProp for my optimizer, I get the following error:
RuntimeError: Adam/RAdam/RMSProp does not support sparse gradients
So I tried using SparseAdam and I got this error:
RuntimeError: SparseAdam does not support dense gradients, please consider Adam instead
How can I solve this issue?