Self Supervised seems to be running in a small number of cases. Now I need to test a few more cases. Adjust unit test and re-organise code

Self Supervised Runs for all attention based models. Whether it learns something or not, is a question we still need to answer

Adjusted output and encoder_output dims so that all models can be used with self supervised training

Added base trainers for the Trainer and the BayesianTrainer classes. The base trainers will change as I add self supervised options

[bugfix] model trainer device conflict

[bugfix] unable to handle categorical column names with dots

Fixed bug related to torchmetrics renaming F1 and FBeta to F1Score an…

adjusting the types so that the library is compatible with the newer version of torch 1.11 and torchvision 0.12

Pmulinka/dir

* reducelronplateau implementation fixed + added test
* added test for _extract_kwargs() in trainer
* added additional coverage for fds_layer
* added lds weight test coverage for losses

* removed adhoc dataset class
* enforced usage of WideDeepDataset class
* changed tabmlp to deeptabular to reflect new naming
* changed tensors to np for WideDeepDataset usage
* swapped X_image dimensions - not sure how this could work before(?)

* I have to add weight support for all regression function in the library