tf.keras.Sequential predict years mismatch

Question

I'm a little confused with the model to try to predict the next year on the list.

I can't get it to be an answer for years, is it not the right model for years?

        modelsq = tf.keras.Sequential(
            [
                Dense(64, activation="relu", input_shape=(1,)),
                Dense(32, activation="relu"),
                Dense(1, activation="sigmoid"),
            ]
        )
        modelsq.compile(
            optimizer="adam", loss="binary_crossentropy", metrics=["accuracy"]
        )
        modelsq.fit(
            self.x_train["year"], self.y_train["year"], epochs=10, batch_size=32
        )
        predictions = modelsq.predict(self.p["year"])
        print("predictions:", predictions)
predictions: [[1.]
 [1.]
 [1.]
 [1.]
 [1.]
 [1.]
 [1.]
 [1.]]

Get the prediction of the year in the series ej:
1990, 1991, 1995...