when I run dual.py and the step is around 1000, there is error "RuntimeError: cuda runtime error (2) : out of memory at /pytorch/torch/lib/THC/generic/THCStorage.cu:58"

[LDONT]

I run dual.py with GPU 1080Ti and the memory size is 12G. The corpus sizes of nmt and lm are both no more than 50M. But when the step of dual is around 1000, there is error:
Traceback (most recent call last):
File "/ghome/weiyt/pytorch-dual-learning/dual.py", line 202, in
dual(args)
File "/ghome/weiyt/pytorch-dual-learning/dual.py", line 153, in dual
B_loss.backward()
File "/usr/local/lib/python3.6/dist-packages/torch/autograd/variable.py", line 167, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph, retain_variables)
File "/usr/local/lib/python3.6/dist-packages/torch/autograd/init.py", line 99, in backward
variables, grad_variables, retain_graph)
RuntimeError: cuda runtime error (2) : out of memory at /pytorch/torch/lib/THC/generic/THCStorage.cu:58