Cuda by Default

[ikirtivardhansingh]

Hi there,
It is actually just a part of my group project, & I am not aware of the model completely. I am trying to run this particular part,
# cuda by default nli_net.cuda() loss_fn.cuda()
and getting this error message,

Traceback (most recent call last): File "train_nli.py", line 129, in <module> nli_net.cuda() File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 260, in cuda return self._apply(lambda t: t.cuda(device)) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 187, in _apply module._apply(fn) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 187, in _apply module._apply(fn) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/rnn.py", line 117, in _apply self.flatten_parameters() File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/rnn.py", line 113, in flatten_parameters self.batch_first, bool(self.bidirectional)) RuntimeError: cuDNN error: CUDNN_STATUS_EXECUTION_FAILED