如果我想预测一个数字序列中的下一个元素，我需要将什么作为第二个参数传递给Keras的fit方法？

import numpy as np
from keras.models import Sequential
from keras.layers import LSTM, Dense

# 原始数字序列
sequence = np.array([1, 2, 3, 4, 5, 6, 7, 8, 9, 10])

# 将序列转换为滑动窗口形式
def create_sliding_windows(sequence, window_size):
    windows = []
    for i in range(len(sequence) - window_size):
        windows.append(sequence[i:i+window_size])
    return np.array(windows)

# 定义窗口大小
window_size = 3

# 创建滑动窗口
windows = create_sliding_windows(sequence, window_size)

# 准备输入特征和标签
X = windows[:, :-1]  # 输入特征
y = windows[:, -1]   # 标签

# 转换为三维张量并归一化
X = np.reshape(X, (X.shape[0], window_size, 1))
X = X / np.max(sequence)

# 创建模型
model = Sequential()
model.add(LSTM(50, input_shape=(window_size, 1)))
model.add(Dense(1))

# 编译模型
model.compile(optimizer='adam', loss='mse')

# 拟合模型
model.fit(X, y, epochs=10, batch_size=1)