State_dict optimizer params

Hi there,

when saving an optimizier during training with optimizer.state_dict()
and later loading it via torch.load() I get a dictionary containing “state” and “param_groups”
as described in the documentation

In “params_group” I have an entry for “params”: what exactly are these values?
Are these the last gradient values that have been used to update my NN?

Thanks in advance!

see answer here

These numbers represent the ids of the parameters you’ve passed to the optimizer.

Thank @ptrblck very much!