optimizer.zero_grad()
loss, hidden = model(data, hidden, targets)
loss.backward()
torch.nn.utils.clip_grad_norm(model.parameters(), args.clip)
optimizer.step()
optimizer.zero_grad()
loss, hidden = model(data, hidden, targets)
loss.backward()
torch.nn.utils.clip_grad_norm(model.parameters(), args.clip)
optimizer.step()