Fix initialization of tft with correct order of arguments

[jdb78]

Description

This PR fixes an issue when the passed loss function is not correctly modified for the TFT.

Checklist

• Linked issues (if existing)
• Amended changelog for large changes (and added myself there as contributor)
• Added/modified tests
• Used pre-commit hooks when committing to ensure that code is compliant with hooks. Install hooks with pre-commit install.
  To run hooks independent of commit, execute pre-commit run --all-files

Make sure to have fun coding!

[codecov-commenter]

Codecov Report

Merging #550 (2156a57) into master (7f24d23) will increase coverage by 0.24%.
The diff coverage is 100.00%.

@@            Coverage Diff             @@
##           master     #550      +/-   ##
==========================================
+ Coverage   89.21%   89.45%   +0.24%     
==========================================
  Files          24       24              
  Lines        3698     3699       +1     
==========================================
+ Hits         3299     3309      +10     
+ Misses        399      390       -9     

Flag	Coverage Δ
cpu	89.45% <100.00%> (+0.24%)	⬆️
pytest	89.45% <100.00%> (+0.24%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
...ing/models/temporal_fusion_transformer/__init__.py	97.32% <100.00%> (+0.01%)	⬆️
pytorch_forecasting/metrics.py	93.45% <0.00%> (+0.23%)	⬆️
pytorch_forecasting/models/base_model.py	88.50% <0.00%> (+0.30%)	⬆️
pytorch_forecasting/utils.py	82.39% <0.00%> (+1.40%)	⬆️
pytorch_forecasting/models/nn/rnn.py	92.40% <0.00%> (+5.06%)	⬆️

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 7f24d23...2156a57. Read the comment docs.