ValueError: `logits` and `labels` must have the same shape, received ((None, 250, 1) vs (None,))

Question

I'm a noob in machinelearning. I'm running LSTM model with the following layers in Sequential. The encoder is encoding an address into a 250 char long tf_id array. See the model summary below for reference. When i'm running model.fit() i get an error below. i tried Flattened() layer before the Dense(1) and it did not work. any pointers?

error

Traceback (most recent call last):

File "/Users/zeus/PycharmProjects/ml_gibb_addr/com/address/train/train_lstm_model.py", line 70, in <module>
    train_lstm_model(data=data, epochs=10)
  File "/Users/zeus/PycharmProjects/ml_gibb_addr/com/address/train/train_lstm_model.py", line 41, in train_lstm_model
    history = model.fit(
  File "/Users/zeus/PycharmProjects/machineLearning/venv1/lib/python3.8/site-packages/keras/utils/traceback_utils.py", line 67, in error_handler
    raise e.with_traceback(filtered_tb) from None
  File "/Users/zeus/PycharmProjects/machineLearning/venv1/lib/python3.8/site-packages/tensorflow/python/framework/func_graph.py", line 1147, in autograph_handler
    raise e.ag_error_metadata.to_exception(e)
ValueError: in user code:

    File "/Users/zeus/PycharmProjects/machineLearning/venv1/lib/python3.8/site-packages/keras/engine/training.py", line 1021, in train_function  *
        return step_function(self, iterator)
    File "/Users/zeus/PycharmProjects/machineLearning/venv1/lib/python3.8/site-packages/keras/engine/training.py", line 1010, in step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    File "/Users/zeus/PycharmProjects/machineLearning/venv1/lib/python3.8/site-packages/keras/engine/training.py", line 1000, in run_step  **
        outputs = model.train_step(data)
    File "/Users/zeus/PycharmProjects/machineLearning/venv1/lib/python3.8/site-packages/keras/engine/training.py", line 860, in train_step
        loss = self.compute_loss(x, y, y_pred, sample_weight)
    File "/Users/zeus/PycharmProjects/machineLearning/venv1/lib/python3.8/site-packages/keras/engine/training.py", line 918, in compute_loss
        return self.compiled_loss(
    File "/Users/zeus/PycharmProjects/machineLearning/venv1/lib/python3.8/site-packages/keras/engine/compile_utils.py", line 201, in __call__
        loss_value = loss_obj(y_t, y_p, sample_weight=sw)
    File "/Users/zeus/PycharmProjects/machineLearning/venv1/lib/python3.8/site-packages/keras/losses.py", line 141, in __call__
        losses = call_fn(y_true, y_pred)
    File "/Users/zeus/PycharmProjects/machineLearning/venv1/lib/python3.8/site-packages/keras/losses.py", line 245, in call  **
        return ag_fn(y_true, y_pred, **self._fn_kwargs)
    File "/Users/zeus/PycharmProjects/machineLearning/venv1/lib/python3.8/site-packages/keras/losses.py", line 1932, in binary_crossentropy
        backend.binary_crossentropy(y_true, y_pred, from_logits=from_logits),
    File "/Users/zeus/PycharmProjects/machineLearning/venv1/lib/python3.8/site-packages/keras/backend.py", line 5247, in binary_crossentropy
        return tf.nn.sigmoid_cross_entropy_with_logits(labels=target, logits=output)

    ValueError: `logits` and `labels` must have the same shape, received ((None, 250, 1) vs (None,)).

Code:

 model = keras.Sequential([
        encoder,
        tf.keras.layers.Embedding(
            input_dim=len(encoder.get_vocabulary()),
            output_dim=64,
            # Use masking to handle the variable sequence lengths
            mask_zero=True),
        tf.keras.layers.LSTM(64, return_sequences=True),
        tf.keras.layers.LSTM(64, return_sequences=True),
        tf.keras.layers.Dense(64, activation='relu'),
        tf.keras.layers.Dense(1)
    ])
    model.summary()
    model.compile(loss=tf.keras.losses.BinaryCrossentropy(from_logits=True),
                  optimizer=tf.keras.optimizers.Adam(1e-4),
                  metrics=['accuracy'])

    nptrain_ds = np.asarray(train_dataset)
    nptest_ds = np.asarray(test_dataset)

    history = model.fit(
        x=nptrain_ds[0], y=nptrain_ds[1].astype(float),
        epochs=epochs,
        # validation_data=nptest_ds,
        validation_split=validation_split)

Model summary:

_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 text_vectorization (TextVec  (None, 250)              1         
 torization)                                                     
                                                                 
 embedding (Embedding)       (None, 250, 64)           16000     
                                                                 
 lstm (LSTM)                 (None, 250, 64)           33024     
                                                                 
 lstm_1 (LSTM)               (None, 250, 64)           33024     
                                                                 
 dense (Dense)               (None, 250, 64)           4160      
                                                                 
 dense_1 (Dense)             (None, 250, 1)            65