Enable to customized loss and val funcs

[WenjieDu]

What does this PR do?

1. fixing Allow users to customize training loss function and validation metric #525;
2. fixing allow customized loss function for imputation/informer #432;

Before submitting

• This PR is made to fix a typo or improve the docs (you can dismiss the other checks if this is the case).
• Was this discussed/approved via a GitHub issue? Please add a link to it if that's the case.
• I have commented my code, particularly in hard-to-understand areas.
• I have written necessary tests and already run them locally.

[coveralls]

Pull Request Test Coverage Report for Build 11066608932

Details

• 253 of 296 (85.47%) changed or added relevant lines in 93 files are covered.
• 10 unchanged lines in 10 files lost coverage.
• Overall coverage decreased (-0.1%) to 83.31%

---

Changes Missing Coverage	Covered Lines	Changed/Added Lines	%
pypots/classification/base.py	16	17	94.12%
pypots/clustering/base.py	0	1	0.0%
pypots/clustering/vader/model.py	2	3	66.67%
pypots/forecasting/csdi/model.py	5	6	83.33%
pypots/imputation/base.py	10	11	90.91%
pypots/imputation/csdi/model.py	5	6	83.33%
pypots/imputation/gpvae/model.py	3	4	75.0%
pypots/forecasting/base.py	1	3	33.33%
pypots/base.py	11	19	57.89%
pypots/nn/modules/loss.py	0	12	0.0%

Files with Coverage Reduction	New Missed Lines	%
pypots/imputation/csdi/model.py	1	86.03%
pypots/imputation/base.py	1	78.63%
pypots/classification/base.py	1	78.05%
pypots/forecasting/csdi/model.py	1	86.43%
pypots/clustering/vader/model.py	1	85.93%
pypots/clustering/base.py	1	38.83%
pypots/forecasting/base.py	1	36.94%
pypots/imputation/gpvae/model.py	1	86.21%
pypots/imputation/itransformer/model.py	1	94.94%
pypots/imputation/transformer/model.py	1	94.87%

Totals
Change from base Build 11056787314:	-0.1%
Covered Lines:	11376
Relevant Lines:	13655

---

💛 - Coveralls