Many time passes between epochs

train_dataloader = torch.utils.data.DataLoader(
        train_dataset,
        batch_size=config.training.batch_size,
        shuffle=True,
        num_workers=2,
        #pin_memory=True,
        persistent_workers=True
    )

    model = instantiate(config.model_cfg.model_obj)
    pl_model = PlWaveGrad(model, hydra_config=config)

    if config.model_cfg.conditional:
        print('using conditional model')
    else:
        print('uncondtional model')

    print('using dataset: ', config.dataset.name)
    
    
    loss_cb = LossCurveCallback()
    
    #profiler = AdvancedProfiler(dirparth='./outputs', filename='perf_logs')
    
    checkpoint_callback = pl.callbacks.ModelCheckpoint(
        filename="{epoch:02d}-{train_loss:.4f}",
        every_n_epochs=1000,  # Save after every epoch
        save_last=True,  # This ensures the last checkpoint is kept and overwritten each time
    )
    trainer = pl.Trainer(
        max_epochs=config.training.n_epochs,
        log_every_n_steps=4,
        devices=[config.training.device], # FIXME 
        callbacks=[checkpoint_callback, loss_cb], # here is no loss_cb
        precision='16-mixed',
        #enable_checkpointing=False,
        #profiler="advanced",
    )
    
    print(f'\n\n\n using device: {config.training.device}')

    if config.ckpt_path is None:
        trainer.fit(pl_model, train_dataloaders=train_dataloader)

    else:
        ckpt_path = Path(config.ckpt_path).resolve()
        trainer.fit(pl_model, train_dataloaders=train_dataloader, ckpt_path=ckpt_path)
    

# Error messages and logs here please

#- PyTorch Lightning Version (e.g., 2.6.0):
#- PyTorch Version (e.g., 2.5):
#- Python version (e.g., 3.12):
#- OS (e.g., Linux):
#- CUDA/cuDNN version:
#- GPU models and configuration:
#- How you installed Lightning(`conda`, `pip`, source):