#With these lines of code below, we can memorize the gradient for later updates using pytorch because the
#loss.backward()function accumulates the gradient. After 64 steps, we call optimizer.step() for updating the parameters.
#https://discuss.pytorch.org/t/how-are-optimizer-step-and-loss-backward-related/7350
train_loader = torch.utils.data.DataLoader(dataset=train_dataset, batch_size=1, num_workers=8, shuffle=True)
test_loader = torch.utils.data.DataLoader(dataset=test_dataset, batch_size=1, num_workers=8, shuffle=False)
for i, (seqs, labels) in enumerate(train_loader):
	...
	loss = criterion(outputs, labels)
	loss.backward()
	if i % 64 == 0 or i == len(train_loader) - 1:
    		optimizer.step()
    		optimizer.zero_grad()
	...