diff --git a/beginner_source/basics/optimization_tutorial.py b/beginner_source/basics/optimization_tutorial.py index c6c327f8511..b5918dc09a1 100644 --- a/beginner_source/basics/optimization_tutorial.py +++ b/beginner_source/basics/optimization_tutorial.py @@ -134,9 +134,9 @@ def forward(self, x): ##################################### # Inside the training loop, optimization happens in three steps: -# * Call ``optimizer.zero_grad()`` to reset the gradients of model parameters. Gradients by default add up; to prevent double-counting, we explicitly zero them at each iteration. # * Backpropagate the prediction loss with a call to ``loss.backward()``. PyTorch deposits the gradients of the loss w.r.t. each parameter. # * Once we have our gradients, we call ``optimizer.step()`` to adjust the parameters by the gradients collected in the backward pass. +# * Call ``optimizer.zero_grad()`` to reset the gradients of model parameters. Gradients by default add up; to prevent double-counting, we explicitly zero them at each iteration. ########################################