[BUG] MCDCNNRegressor does not perform fitting/training?

[helloplayer1]

Describe the bug
When you try to fit a MCDCNNRegressor, the training will end immediately. Setting verbose=true, you can see that the given epochs are not actually run through.
To Reproduce

import pandas as pd
import numpy as np
from sktime.regression.deep_learning import MCDCNNRegressor

index = pd.MultiIndex.from_tuples([
    (0, 0),
    (0, 1),
    (1, 0),
    (1, 1)
], names=['instance', 'Time'])

# Define the DataFrame
df = pd.DataFrame({
    'LeftControllerVelocity_0': [-0.01, -0.01, 0.06, 0.06]
}, index=index)

regressor = MCDCNNRegressor(n_epochs=100000, verbose=True)

regressor.fit(df, np.array([1, 0]))

print(regressor.predict(df))

Expected behavior
The model actually trains

Versions

System: python: 3.12.3 (tags/v3.12.3:f6650f9, Apr 9 2024, 14:05:25) [MSC v.1938 64 bit (AMD64)] executable: d:\BAAI\.venv\Scripts\python.exe machine: Windows-11-10.0.22631-SP0

Python dependencies:
pip: 24.0
sktime: 0.29.0
sklearn: 1.4.2
skbase: 0.7.7
numpy: 1.26.4
scipy: 1.13.0
pandas: 2.2.2
matplotlib: 3.8.4
joblib: 1.4.0
numba: 0.59.1
statsmodels: 0.14.2
pmdarima: None
statsforecast: None
tsfresh: None
tslearn: 0.6.3
torch: None
tensorflow: 2.16.1
tensorflow_probability: None