[bug] Fix correct definition of torchmetrics inside pytorch lightning module

[leoniewgnr]

🔬 Background

See #1361

🔮 Key changes

Move metrics definition inside pytorch lightning module as described in https://torchmetrics.readthedocs.io/en/latest/pages/lightning.html

[github-actions]

Model Benchmark

Benchmark	Metric	main	current	diff
YosemiteTemps	MAE_val	1.3442	1.3442	-0.0%	✅
YosemiteTemps	RMSE_val	2.00245	2.00245	-0.0%	✅
YosemiteTemps	Loss_val	0.00077	0.00077	-0.0%	✅
YosemiteTemps	MAE	1.3192	1.3192	0.0%	✅
YosemiteTemps	RMSE	2.13518	2.13518	-0.0%	✅
YosemiteTemps	Loss	0.00064	0.00064	-0.0%	✅
YosemiteTemps	time	98.4182	76.36	-22.41%	🎉
PeytonManning	MAE_val	0.58159	0.58159	-0.0%	✅
PeytonManning	RMSE_val	0.72216	0.72216	0.0%	✅
PeytonManning	Loss_val	0.01239	0.01239	-0.0%	✅
PeytonManning	MAE	0.41671	0.41671	-0.0%	✅
PeytonManning	RMSE	0.55961	0.55961	0.0%	✅
PeytonManning	Loss	0.00612	0.00612	0.0%	✅
PeytonManning	time	20.9439	15.34	-26.76%	🎉
AirPassengers	MAE_val	13.0626	13.0626	0.0%	✅
AirPassengers	RMSE_val	15.9452	15.9453	0.0%	✅
AirPassengers	Loss_val	0.00131	0.00131	0.0%	✅
AirPassengers	MAE	9.88156	9.88156	0.0%	✅
AirPassengers	RMSE	11.7354	11.7354	0.0%	✅
AirPassengers	Loss	0.00052	0.00052	0.0%	✅
AirPassengers	time	8.61348	6.61	-23.26%	🎉

Model training plots

Model Training

PeytonManning

YosemiteTemps

AirPassengers

[codecov]

Codecov Report

Merging #1365 (b1c50ee) into main (90f6e6e) will increase coverage by 0.02%.
Report is 1 commits behind head on main.
The diff coverage is 90.90%.

@@            Coverage Diff             @@
##             main    #1365      +/-   ##
==========================================
+ Coverage   89.81%   89.84%   +0.02%     
==========================================
  Files          38       38              
  Lines        5058     5061       +3     
==========================================
+ Hits         4543     4547       +4     
+ Misses        515      514       -1     

Files Changed	Coverage Δ
neuralprophet/forecaster.py	87.40% <ø> (ø)
neuralprophet/utils_metrics.py	80.76% <87.50%> (+15.55%)	⬆️
neuralprophet/np_types.py	92.30% <100.00%> (-0.55%)	⬇️
neuralprophet/time_net.py	90.63% <100.00%> (-0.45%)	⬇️

[ourownstory]

Looking good mostly!
We just need make sure to only have one source for the list of METRICS.
I also added some other open Qs

already adressed