How to save Adam optimizer parameters in Keras?

Question

Adam algorithm in Keras:

Initialize m_0 as 1st-moment vector,

Initialize v_0as 2nd-moment vector,

The update rule for theta with gradient g:

lr_t = learning_rate * sqrt(1 - beta_2^t) / (1 - beta_1^t)

m_t = beta_1 * m_{t-1} + (1 - beta_1) * g_t

v_t = beta_2 * v_{t-1} + (1 - beta_2) * g^2

theta_t = theta_{t-1} - lr_t * m_t / (sqrt{v_t} + epsilon)

I want to know how to save m_t and v_t at each step t in Keras.