model, opt = get_model()

for epoch in range(epochs):
    model.train()
    for xb, yb in train_dl:
        pred = model(xb)
        loss = loss_func(pred, yb)

        loss.backward()
        opt.step()
        opt.zero_grad()

    model.eval()
    with torch.no_grad():
        valid_loss = sum(loss_func(model(xb), yb) for xb, yb in valid_dl)

    print(epoch, valid_loss / len(valid_dl))