FIX: Remove run_models bugs in DCN example notebook

[ywuenthought]

Closes #755
Closes #758

This PR

• replaces mask_value with mask_token
• avoids mutating features dict

For reviewers:

You can manually test the fixed notebook using the following link

https://colab.research.google.com/github/ywuenthought/recommenders/blob/fix/dcn-notebook-bugs/docs/examples/dcn.ipynb

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[ywuenthought]

After fixing the mask_value issue, a new error shows up

/usr/local/lib/python3.12/dist-packages/keras/src/backend/tensorflow/trainer.py in multi_step_on_iterator(iterator)
    131             if self.steps_per_execution == 1:
    132                 return tf.experimental.Optional.from_value(
--> 133                     one_step_on_data(iterator.get_next())
    134                 )
    135 

ValueError: TensorFlowTrainer._make_function.<locals>.one_step_on_data(data) should not modify its Python input arguments. Modifying a copy is allowed. The following parameter(s) were modified: data

This is due to the direct mutation of features in the compute_loss method of DCN.