[DOC] Incorrect name on tutorial "Demand forecasting with the Temporal Fusion Transformer"

[mbisan]

I've been trying to follow the tutorial on Demand forecasting with the Temporal Fusion Transformer, but found this error in the documentation:

On the step Find optimal learning rate, the optimizer parameter passed to from_dataset is "Ranger", with capital R.

Apparently, the base model class only admits the following (version 1.2.0):

optimizer (str): Optimizer, "ranger", "sgd", "adam", "adamw" or class name of optimizer in ``torch.optim``
                or ``pytorch_optimizer``.
                Alternatively, a class or function can be passed which takes parameters as first argument and
                a `lr` argument (optionally also `weight_decay`). Defaults to
                `"ranger" <https://pytorch-optimizers.readthedocs.io/en/latest/optimizer_api.html#ranger21>`_,
                if pytorch_optimizer is installed, otherwise "adam".

So the value passed must be changed to "ranger".

The current code causes a `ValueError: Optimizer of self.hparams.optimizer=Ranger unknown``.

The same error appears on the second time from_dataset is used, on the Train model step.

[fnhirwa]

Nice catch @mbisan 😊
I am going to open a PR for a fix