Ubuntu Pytorch 1.0.1 RuntimeError: code is too big

[Honghe]

python smoke_test.py 
Randomly generating input and output data...
inputs shape torch.Size([50, 500, 13])
target shape torch.Size([50, 20])
Sequential(
  (0): Conv1d(13, 250, kernel_size=(48,), stride=(2,))
  (1): ReLU()
  (2): Conv1d(250, 250, kernel_size=(7,), stride=(1,))
  (3): ReLU()
  (4): Conv1d(250, 250, kernel_size=(7,), stride=(1,))
  (5): ReLU()
  (6): Conv1d(250, 250, kernel_size=(7,), stride=(1,))
  (7): ReLU()
  (8): Conv1d(250, 250, kernel_size=(7,), stride=(1,))
  (9): ReLU()
  (10): Conv1d(250, 250, kernel_size=(7,), stride=(1,))
  (11): ReLU()
  (12): Conv1d(250, 250, kernel_size=(7,), stride=(1,))
  (13): ReLU()
  (14): Conv1d(250, 250, kernel_size=(7,), stride=(1,))
  (15): ReLU()
  (16): Conv1d(250, 2000, kernel_size=(32,), stride=(1,))
  (17): ReLU()
  (18): Conv1d(2000, 2000, kernel_size=(1,), stride=(1,))
  (19): ReLU()
  (20): Conv1d(2000, 27, kernel_size=(1,), stride=(1,))
)
Traceback (most recent call last):
  File "smoke_test.py", line 61, in <module>
    smoke_test()
  File "smoke_test.py", line 51, in smoke_test
    model.fit(inputs, targets, optimizer, ctc_loss, batch_size, epoch=1, print_every=1)
  File "/home/ubuntu/honghe/Wav2Letter_simple/Wav2Letter/model.py", line 98, in fit
    log_probs = self.forward(batch)
  File "/home/ubuntu/honghe/Wav2Letter_simple/Wav2Letter/model.py", line 64, in forward
    y_pred = self.layers(batch)
  File "/home/ubuntu/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 489, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/ubuntu/anaconda3/lib/python3.6/site-packages/torch/nn/modules/container.py", line 92, in forward
    input = module(input)
  File "/home/ubuntu/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 489, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/ubuntu/anaconda3/lib/python3.6/site-packages/torch/nn/modules/conv.py", line 187, in forward
    self.padding, self.dilation, self.groups)
RuntimeError: code is too big