我正在尝试使用 Keras 实现一个用于预测多个标签的自动编码器。这是一个片段：
input = Input(shape=(768,))
hidden1 = Dense(512, activation='relu')(input)
compressed = Dense(256, activation='relu', activity_regularizer=l1(10e-6))(hidden1)
hidden2 = Dense(512, activation='relu')(compressed)
output = Dense(768, activation='sigmoid')(hidden2) # sigmoid is used because output of autoencoder is a set of probabilities
model = Model(input, output)
model.compile(optimizer='adam', loss='categorical_crossentropy') # categorical_crossentropy is used because it's prediction of multiple labels
history = model.fit(x_train, x_train, epochs=100, batch_size=50, validation_split=0.2)
我在 Jupyter Notebook (CPU) 中运行此程序，但出现丢失和验证丢失的情况：
loss: 193.8085 - val_loss: 439.7132
但是当我在 Google Colab (GPU) 中运行它时，我得到了非常高的损失和验证损失：
loss: 28383285849773932.0000 - val_loss: 26927464965996544.0000。
这种行为的原因是什么？