Updates to training notebook

[carteakey]

Hi there!

While trying to reproduce the training i thought of cleaning up some code, even though TabPFN 2.0 might be in the works (cant wait).

• Removed the duplicate model_config file, the one used in there in the model_configs.py inside scripts folder.
• Cleaned up the training notebook
  • removed unused imports
  • add the missing maximum_runtime variable in train function (removed total_training_in_s config as its not used apparently). Use the train_function for training instead of get_model.
  • updated some config to match the current classifier (pulled from classifier.c)

Feedback welcome!

Kartikey