class CustomizedSchedule(
    keras.optimizers.schedules.LearningRateSchedule):
    def __init__(self, d_model, warmup_steps = 4000):
        super(CustomizedSchedule, self).__init__()
        
        self.d_model = tf.cast(d_model, tf.float32)
        self.warmup_steps = warmup_steps
    
    def __call__(self, step):
        arg1 = tf.math.rsqrt(step)
        arg2 = step * (self.warmup_steps ** (-1.5))
        
        arg3 = tf.math.rsqrt(self.d_model)
        
        return arg3 * tf.math.minimum(arg1, arg2)
    
learning_rate = CustomizedSchedule(d_model)
optimizer = keras.optimizers.Adam(learning_rate,
                                  beta_1 = 0.9,
                                  beta_2 = 0.98,
                                  epsilon = 1e-9)

老师，像这种自定义的学习率，是每个batch_size就变化一次学习率，还是遍历整个数据集一次才变化一次学习率呢，还有像这样的问题我在官方文档都找不到具体的答案，我想问一下像这种问题老师一般都去哪里寻找答案呢?