The stack trace seems to reference something w/r/t the model …

...
~/anaconda3/envs/playground-nlp/lib/python3.7/site-packages/torch/nn/modules/rnn.py in forward_tensor(self, input, hx)
541 unsorted_indices = None
542
--> 543 output, hidden = self.forward_impl(input, hx, batch_sizes, max_batch_size, sorted_indices)
544
545 return output, self.permute_hidden(hidden, unsorted_indices)
~/anaconda3/envs/playground-nlp/lib/python3.7/site-packages/torch/nn/modules/rnn.py in forward_impl(self, input, hx, batch_sizes, max_batch_size, sorted_indices)
524 if batch_sizes is None:
525 result = _VF.lstm(input, hx, self._get_flat_weights(), self.bias, self.num_layers,
--> 526 self.dropout, self.training, self.bidirectional, self.batch_first)
527 else:
528 result = _VF.lstm(input, batch_sizes, hx, self._get_flat_weights(), self.bias,
RuntimeError: Input and hidden tensors are not at the same device, found input tensor at cuda:1 and hidden tensor at cpu