embedding for categorical variable and pass to keras network - tensorflow

Question

I have tabular data with two columns , one is input feature and anther one is target variable.
I have converted the input feature to embeddings and pass on to Keras model layer, getting error while executing fit method.
here is the code which i have used for this.
df is the input dataframe and contains two columns.
X = df.drop(columns = ['data_type']).copy()
y = df['data_type']
X_train, X_rem, y_train, y_rem = train_test_split(X,y, train_size=0.8)
X_valid, X_test, y_valid, y_test = train_test_split(X_rem,y_rem, test_size=0.5)
Y_train=pd.DataFrame({'data_type':y_train})
Y_valid=pd.DataFrame({'data_type':y_valid})
Y_test=pd.DataFrame({'data_type':y_test})
enc = OrdinalEncoder()
X_train[["data"]] = enc.fit_transform(X_train[["data"]])
X_valid[["data"]] = enc.fit_transform(X_valid[["data"]])
X_test[["data"]] = enc.fit_transform(X_test[["data"]])
X_train_actual = []
X_train_actual.append(np.array(X_train["data"]).reshape(-1,1))
X_valid_actual = []
X_valid_actual.append(np.array(X_valid["data"]).reshape(-1,1))
Y_train["data_type"] = LabelEncoder().fit_transform(Y_train["data_type"])
Y_valid["data_type"] = LabelEncoder().fit_transform(Y_valid["data_type"])
Y_test["data_type"] = LabelEncoder().fit_transform(Y_test["data_type"])
Y_train_actual= to_categorical(Y_train.to_numpy())
Y_valid_actual= to_categorical(Y_valid.to_numpy())
embedding_size = 50
categories = 7
inputs = Input(shape=(1,))
embedding_layer = Embedding(categories,
embedding_size,
embeddings_regularizer=regularizers.l2(0.01),
input_length=1)(inputs)
cat_input_layers = Reshape(target_shape=(embedding_size,))(embedding_layer)
building the layers is as follows.
dense_1 = Dense(512, activation='relu', kernel_regularizer=regularizers.l2(0.01))(cat_input_layers)
final_out = Dense(7, activation='softmax')(dense_1)
model = keras.Model(inputs=inputs,outputs=final_out)
optimizer = tf.keras.optimizers.Adam(learning_rate=0.00001)
model.compile(loss='mse', optimizer=optimizer, metrics=['mae', 'mse'])
checkpoint = tf.keras.callbacks.ModelCheckpoint(filepath=checkpoint_path,
save_weights_only=True,
verbose=1)
early_stop = keras.callbacks.EarlyStopping(monitor='val_loss', patience=5)
history = model.fit(X_train_actual,
Y_train_actual,
batch_size=100,
epochs=500,
validation_data =(X_valid_actual, Y_valid_actual),
callbacks=[checkpoint, early_stop],
verbose=1)
getting the error when i am executing the fit call.
InvalidArgumentError Traceback (most recent call last)
Cell In [336], line 1
----> 1 history = model.fit(X_train_actual,
2 Y_train_actual,
3 batch_size=100,
4 epochs=500,
5 validation_data =(X_valid_actual, Y_valid_actual),
6 callbacks=[checkpoint, early_stop],
7 verbose=1)
File ~\Anaconda3\envs\keras-tf-tcb\lib\site-packages\keras\utils\traceback_utils.py:70, in filter_traceback.<locals>.error_handler(*args, **kwargs)
67 filtered_tb = _process_traceback_frames(e.__traceback__)
68 # To get the full stack trace, call:
69 # `tf.debugging.disable_traceback_filtering()`
---> 70 raise e.with_traceback(filtered_tb) from None
71 finally:
72 del filtered_tb
any idea, what exactly the issue,