ValueError: setting an array element with a sequence for X_train, y_train

Question

I am trying to fit my model on X_train and y_train as below:

model = Sequential()
model.add(LSTM(256, input_shape=(n_timesteps,n_features),recurrent_activation='hard_sigmoid'))
model.add(Dense(16))
model.add(Dense(n_outputs, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['acc'])

history = model.fit(X_train, y_train, epochs=5, batch_size=72, validation_split=0.1, 
                    verbose=1)

where,

X_train:  (429591, 5, 11)
X_test:   (47733, 5, 11)
y_train:  (429591,)
y_test:   (47733,)

In order to do so, I got the error as ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type int). To fix this error, I was using below code however, I got another error as ValueError: setting an array element with a sequence.

X_train.dtype is dtype('O')

X_train[0] looks like

array([[3, 30, 4, 399, 696, 60, 212, 0, 303, 981,
        list([-2.1380737, 1.9840922, -0.21595824, 1.7971923, -0.49482924])],
       [3, 30, 4, 399, 696, 60, 212, 0, 303, 981,
        list([-2.1380737, 1.9840922, -0.21595824, 1.7971923, -0.49482924])],
       [3, 30, 4, 399, 696, 60, 212, 0, 303, 981,
        list([-2.1380737, 1.9840922, -0.21595824, 1.7971923, -0.49482924])],
       [3, 30, 4, 399, 696, 60, 212, 0, 303, 981,
        list([-2.1380737, 1.9840922, -0.21595824, 1.7971923, -0.49482924])],
       [3, 30, 4, 399, 696, 60, 212, 0, 303, 981,
        list([-2.1380737, 1.9840922, -0.21595824, 1.7971923, -0.49482924])]],
      dtype=object)

where last element of X_train i.e. list([-2.1380737, 1.9840922, -0.21595824, 1.7971923, -0.49482924])] is after applying word2vec,

and y_train[0] contains 0,1.

Can't figure out where am I wrong. Any suggestion would be very helpful.