[bug] Future Regressors NN Shared Coef - error when using n_lags>0 and n_forecasts>1

[ourownstory]

Need to debug test_future_regressor_nn_shared_coef_2 in tests/test_future_regressor_nn.py

• connected to Neural network future regressor invalid shape in model #1554
• which was partially solved by [Minor| Fix neural nets regressor shape #1589
• shared_neural_nets passes tests, but also requires attention

def test_future_regressor_nn_shared_coef_2():
    log.info("future regressor with NN shared coef 2")

    df = pd.read_csv(TUTORIAL_FILE, nrows=NROWS)

    m = NeuralProphet(
        yearly_seasonality=False,
        weekly_seasonality=False,
        daily_seasonality=True,
        future_regressors_model="shared_neural_nets_coef",
        future_regressors_d_hidden=4,
        future_regressors_num_hidden_layers=2,
        n_forecasts=3,
        n_lags=5,
        drop_missing=True,
    )
    df_train, df_val = m.split_df(df, freq="H", valid_p=0.2)

    # Add the new future regressor
    m.add_future_regressor("temperature")

    metrics = m.fit(
        df_train, validation_df=df_val, freq="H", epochs=EPOCHS, learning_rate=LR, early_stopping=True, progress=False
    )