Return to Answer

A state_dict the other answer mentioned deserves just few more notes.

The PyTorch model is torch.nn.Module has model.parameters() call to get learnable parameters (w and b). These learnable parameters, once randomly set, will update over time as we learn. Learnable parameters are the first state_dict.

The second state_dict is the optimizer state dict. You recall that the optimizer is used to improve our learnable parameters. But the optimizer state_dict is fixed. Nothing to learn in there.

Model's state_dict:
weight   torch.Size([2, 5])
bias     torch.Size([2])
Model weight:
Parameter containing:
tensor([[ 0.1328,  0.1360,  0.1553, -0.1838, -0.0316],
        [ 0.0479,  0.1760,  0.1712,  0.2244,  0.1408]], requires_grad=True)
Model bias:
Parameter containing:
tensor([ 0.4112, -0.0733], requires_grad=True)
---
Optimizer's state_dict:
state    {}
param_groups     [{'lr': 0.001, 'momentum': 0.9, 'dampening': 0, 'weight_decay': 0, 'nesterov': False, 'params': [140695321443856, 140695321443928]}]

Non learnable things, belong to the optimizer object state_dict, which contains information about the optimizer's state, as well as the hyperparameters used.

On the other side, torch.save(model, filepath) saves the model object itself, but keep in mind the model doesn't have the optimizer's state_dict. Check the other excellent answer by @Jadiel de Armas to save the optimizer's state dict.

A state_dict the other answer mentioned deserves just a few more notes.

The PyTorch model is torch.nn.Module which has model.parameters() call to get learnable parameters (w and b). These learnable parameters, once randomly set, will update over time as we learn. Learnable parameters are the first state_dict.

The second state_dict is the optimizer state dict. You recall that the optimizer is used to improve our learnable parameters. But the optimizer state_dict is fixed. Nothing to learn there.

Model's state_dict:
weight      torch.Size([2, 5])
bias      torch.Size([2])
Model weight:
Parameter containing:
tensor([[ 0.1328,  0.1360,  0.1553, -0.1838, -0.0316],
        [ 0.0479,  0.1760,  0.1712,  0.2244,  0.1408]], requires_grad=True)
Model bias:
Parameter containing:
tensor([ 0.4112, -0.0733], requires_grad=True)
---
Optimizer's state_dict:
state      {}
param_groups      [{'lr': 0.001, 'momentum': 0.9, 'dampening': 0, 'weight_decay': 0, 'nesterov': False, 'params': [140695321443856, 140695321443928]}]

Non-learnable things belong to the optimizer object state_dict, which contains information about the optimizer's state, as well as the hyperparameters used.

On the other hand, torch.save(model, filepath) saves the model object itself, but keep in mind the model doesn't have the optimizer's state_dict. Check the other excellent answer by @Jadiel de Armas to save the optimizer's state dict.

The second state_dict is the optimizer state dict. Optimizer is also the part of the model. You recall that the optimizer is used to improve our learnable parameters. But the optimizer state_dict is fixed. Nothing to learn in there.

The second state_dict is the optimizer state dict. You recall that the optimizer is used to improve our learnable parameters. But the optimizer state_dict is fixed. Nothing to learn in there.

A state_dict the other answer mentioned deserves just few more notes. What's inside the PyTorch model?

There are actually two state_dicts.

A state_dict the other answer mentioned deserves just few more notes.

What state_dict do we have inside PyTorch? There are actually two state_dicts.