9t_3.py

# clear last step
optimizer.zero_grad()

# 16 accumulated gradient steps
scaled_loss = 0
for accumulated_step_i in range(16):
     out = model.forward()
     loss = some_loss(out,y)    
     loss.backward()
      scaled_loss += loss.item()
      
# update weights after 8 steps. effective batch = 8*16
optimizer.step()

# loss is now scaled up by the number of accumulated batches
actual_loss = scaled_loss / 16