Getting error in Fastai v2 text

Trying to run learn.fit_one_cycle(1, 1e-1) on language model learner. getting the below error. Please help!

RuntimeError Traceback (most recent call last)
in ()
----> 1 learn.fit_one_cycle(1, 1e-1
2 )

14 frames
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/rnn.py in flatten_parameters(self)
127 all_weights, (4 if self.bias else 2),
128 self.input_size, rnn.get_cudnn_mode(self.mode), self.hidden_size, self.num_layers,
–> 129 self.batch_first, bool(self.bidirectional))
130
131 def _apply(self, fn):

RuntimeError: param_from.type() == param_to.type() INTERNAL ASSERT FAILED at /pytorch/aten/src/ATen/native/cudnn/RNN.cpp:541, please report a bug to PyTorch. parameter types mismatch

We need way more information than this to help. Please see this post: How to debug your code and ask for help with fastai v2 :slight_smile:

Thanks for the information. I downgraded torch to 1.3.1 and error is resolved.

I am trying to run the text notebook from your lecture on fastai v2 last week on custom domain data. Keeping fingers crossed for my classification results