机器学习后val_loss变成一条直线

为什么val loss会突然下降变成一条直线

可能是哪些参数出现的问题呢
我用的是keras
网络部分的代码如下：

model = Sequential()
model.add(Dense(512, activation='relu',
                input_shape=(3600,),
                kernel_regularizer=regularizers.l1(0.01)
                # activity_regularizer=regularizers.l1(0.01)
                # bias_regularizer= regularizers.l1(0.1)
                ))  
model.add(Dropout(0.1))
model.add(Dense(256, activation='relu'))      
model.add(Dense(num_classes, activation='softmax'))
model.summary()
model.compile(loss='categorical_crossentropy',
              optimizer=RMSprop(),
              metrics=['accuracy'])

history = LossHistory()
model.fit(x_train, y_train,
          batch_size=batch_size,
          epochs=epochs,
          verbose=2,
          validation_data=(x_test, y_test),
          callbacks=[history]
          )