I am not sure which function you are using to train the neural network. But below are some of the possible options that you can follow,
1) To save the weights and biases of the current iteration and to use them in future, you can always use functions "save" and "load".
2) You can also define the weights and biases as persistent variables and update them in every iteration.
Also, to get the weights and biases of a given network, you can use function "getwb".
I hope this helps!