Closed jianpingliu closed 1 year ago
the same error. Said to ollow these instructions: https://discord.com/channels/930499730843250783/953132470528798811/1018668937052962908, but I cant get access into
Were you trying to train? I believe that you need the model with the optimizer states if you aren't already using it
Were you trying to train? I believe that you need the model with the optimizer states if you aren't already using it
thank you! it helps
if want to use Full Weights or official weights what should to do?
Followed the instruction step by step, got this error:
Traceback (most recent call last): File "waifu-diffusion/main.py", line 721, in
trainer.fit(model, data)
File "/usr/local/lib/python3.7/dist-packages/pytorch_lightning/trainer/trainer.py", line 772, in fit
self._fit_impl, model, train_dataloaders, val_dataloaders, datamodule, ckpt_path
File "/usr/local/lib/python3.7/dist-packages/pytorch_lightning/trainer/trainer.py", line 722, in _call_and_handle_interrupt
return self.strategy.launcher.launch(trainer_fn, *args, trainer=self, *kwargs)
File "/usr/local/lib/python3.7/dist-packages/pytorch_lightning/strategies/launchers/subprocess_script.py", line 93, in launch
return function(args, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/pytorch_lightning/trainer/trainer.py", line 812, in _fit_impl
results = self._run(model, ckpt_path=self.ckpt_path)
File "/usr/local/lib/python3.7/dist-packages/pytorch_lightning/trainer/trainer.py", line 1233, in _run
self._checkpoint_connector.restore_training_state()
File "/usr/local/lib/python3.7/dist-packages/pytorch_lightning/trainer/connectors/checkpoint_connector.py", line 204, in restore_training_state
self.restore_optimizers_and_schedulers()
File "/usr/local/lib/python3.7/dist-packages/pytorch_lightning/trainer/connectors/checkpoint_connector.py", line 307, in restore_optimizers_and_schedulers
"Trying to restore optimizer state but checkpoint contains only the model."
KeyError: 'Trying to restore optimizer state but checkpoint contains only the model. This is probably due to
ModelCheckpoint.save_weights_only
being set toTrue
.'