lesson 3 of 4 · autograd as a dependency graphlesson 3 of 4 · autograd as a dependency graphlesson 3 of 4 · autograd as a dependency graphlesson 3 of 4 · autograd as a dependency graphlesson 3 of 4 · autograd as a dependency graphlesson 3 of 4 · autograd as a dependency graphlesson 3 of 4 · autograd as a dependency graphlesson 3 of 4 · autograd as a dependency graphlesson 3 of 4 · autograd as a dependency graphlesson 3 of 4 · autograd as a dependency graphlesson 3 of 4 · autograd as a dependency graph
Checkpoint
One last thing before we move on. pass this to mark the lesson done, or skip and keep moving. hop to the next when you're ready.
Train on your own autograd. For 3 steps: forward pred = w * x, err = pred - Value(target), loss = err * err; zero w.grad; loss.backward(); update w.data -= lr * w.grad; print f"step {step}: loss={loss.data:.3f} w={w.data:.3f}". Finish with f"final prediction: {(w * x).data:.2f}". This is chapter 39's training loop running on machinery you can read line by line.