UnboundLocalError: local variable 'prompt_embeds' referenced before assignment

[Pevernow]

The 'batch_size' argument of HybridCache is deprecated and will be removed in v4.49. Use the more precisely named 'max_batch_size' argument instead.
The 'batch_size' attribute of HybridCache is deprecated and will be removed in v4.49. Use the more precisely named 'self.max_batch_size' attribute instead.
Caching latents and embeddings: 100%|█████████████████████████████████████████████| 1000/1000 [07:14<00:00,  2.30it/s]Caching latents and embeddings: 100%|█████████████████████████████████████████████| 1000/1000 [07:14<00:00,  3.12it/s]/home/linjl/zzc/YAT/common/bucket_sampler_cache.py:68: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
  ratio, latent, embedding = torch.load(f'cache/{idx + self.cache_size * torch.cuda.current_device()}.npy')
Generating validation latents:   0%|                                                            | 0/4 [00:00<?, ?it/s]Processing cache:   0%|                                                              | 1/1000 [00:00<00:44, 22.40it/s]Traceback (most recent call last):%|                                                            | 0/4 [00:00<?, ?it/s]  File "/home/linjl/zzc/YAT/train_sana.py", line 193, in <module>
    trainer.run()
  File "/home/linjl/zzc/YAT/common/trainer.py", line 198, in run
    self.validate()
  File "/home/linjl/zzc/YAT/train_sana.py", line 128, in validate
    prompt_embeds=prompt_embeds,
UnboundLocalError: local variable 'prompt_embeds' referenced before assignment
Num Steps:   0%|                                                                            | 0/50000 [07:15<?, ?it/s]Traceback (most recent call last):
  File "/home/linjl/zzc/YAT/.venv/bin/accelerate", line 8, in <module>