ValueError: loaded state dict contains a parameter group that doesn't match the size of optimizer's group

[gggah]

---

ValueError Traceback (most recent call last)
in
37 model=score_model, ema=ema)
38
---> 39 state = restore_checkpoint(ckpt_filename, state, config.device)
40 ema.copy_to(score_model.parameters())

/workspace/utils.py in restore_checkpoint(ckpt_dir, state, device)
13 else:
14 loaded_state = torch.load(ckpt_dir, map_location=device)
---> 15 state['optimizer'].load_state_dict(loaded_state['optimizer'])
16 state['model'].load_state_dict(loaded_state['model'], strict=False)
17 state['ema'].load_state_dict(loaded_state['ema'])

/opt/conda/lib/python3.8/site-packages/torch/optim/optimizer.py in load_state_dict(self, state_dict)
144 saved_lens = (len(g['params']) for g in saved_groups)
145 if any(p_len != s_len for p_len, s_len in zip(param_lens, saved_lens)):
--> 146 raise ValueError("loaded state dict contains a parameter group "
147 "that doesn't match the size of optimizer's group")
148

ValueError: loaded state dict contains a parameter group that doesn't match the size of optimizer's group