Change basic example to contain backward two losses.

[PierreQuinton]

No description provided.

[ValerianRey]

There is a warning when running doc tests:

=============================== warnings summary ===============================
tests/doc/test_rst.py::test_basic_usage
  /home/runner/work/torchjd/torchjd/.venv/lib/python3.10/site-packages/torch/nn/modules/loss.py:535: UserWarning: Using a target size (torch.Size([16, 1])) that is different to the input size (torch.Size([16])). This will likely lead to incorrect results due to broadcasting. Please ensure they have the same size.
    return F.mse_loss(input, target, reduction=self.reduction)

-- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html
======================== 18 passed, 1 warning in 2.86s =========================

I think this can be fixed very easily by using targets of shape (16,) instead of (16, 1)

[ValerianRey]

Looking good! A few minor fixes to do, then we can merge.