Anyone know how to create a finetune?

[slooi]

I'm trying to remove some high pitch ping noise that occasionally appears in some bgm so i'm trying to train a model using the original demux repo but to no avail. Anyone know how to solve this error:

Executor: Starting 2 worker processes for DDP.
/usr/local/lib/python3.11/dist-packages/hydra/_internal/hydra.py:119: UserWarning: Future Hydra versions will no longer change working directory at job runtime by default.
See https://hydra.cc/docs/1.2/upgrades/1.1_to_1.2/changes_to_job_working_dir/ for more information.
  ret = run_job(
[08-02 19:13:32][demucs.train][INFO] - For logs, checkpoints and samples check /content/demucs/outputs/xps/a1b3e858
[08-02 19:13:33][torch.distributed.distributed_c10d][INFO] - Added key: store_based_barrier_key:1 to store for rank: 0
[08-02 19:13:33][torch.distributed.distributed_c10d][INFO] - Rank 0: Completed store-based barrier for key:store_based_barrier_key:1 with 2 nodes.
[08-02 19:13:33][dora.distrib][INFO] - Distributed init: 0/2 (local 0) from env
[08-02 19:13:36][demucs.train][WARNING] - No vocal source found
[08-02 19:13:36][demucs.train][INFO] - train/valid set size: 4 4
/usr/local/lib/python3.11/dist-packages/torch/utils/data/dataloader.py:560: UserWarning: This DataLoader will create 10 worker processes in total. Our suggested max number of worker in current system is 4, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.
  warnings.warn(_create_warning_msg(
[08-02 19:13:36][demucs.solver][INFO] - ----------------------------------------------------------------------
[08-02 19:13:36][demucs.solver][INFO] - Training...
Error executing job with overrides: ['dset=my_dset', 'dset.use_musdb=false', 'model=hdemucs']
Traceback (most recent call last):
  File "/content/demucs/demucs/train.py", line 243, in main
    solver.train()
  File "/content/demucs/demucs/solver.py", line 195, in train
    metrics['train'] = self._run_one_epoch(epoch)
                       ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/content/demucs/demucs/solver.py", line 405, in _run_one_epoch
    return distrib.average(losses, idx + 1)
                           ^^^^^^
UnboundLocalError: cannot access local variable 'losses' where it is not associated with a value

Set the environment variable HYDRA_FULL_ERROR=1 for a complete stack trace.
Executor: Worker 0 died, killing all workers

Full code here:
https://www.kaggle.com/code/sammyl1/finetune-demucs-anyone-know-how-to-fix-this/edit