TFT tutorial notebook generate result that is different from tutorial docs.

[aaaron7]

• PyTorch-Forecasting version: 0.10.1
• PyTorch version: 1.11.0
• Python version:3.8.13
• Operating System: macOS 12.3.1

Expected behavior

I executed tutorial notebook (Demand forecasting) in my machine and expected same result with tutorial, like following variable importance section:

Actual behavior

However, after run the notebook in my machine without any change ,i got following result

both of the decoder variable importance or encoder variable importance are difference compare to tutorial description.

Code to reproduce the problem

TFT tutorial notebook: https://github.com/jdb78/pytorch-forecasting/blob/master/docs/source/tutorials/stallion.ipynb

Paste the command(s) you ran and the output. Including a link to a colab notebook will speed up issue resolution. If there was a crash, please include the traceback here. The code used to initialize the TimeSeriesDataSet and model should be also included.