Changing the configuration of output_dir having no effect in Databricks.

[hv129]

finetuning_config = model.finetuning_config()
finetuning_config.output_dir = "model_cp/"

Changing the model's output directory as above (mentioned in https://xturing.stochastic.ai/configuration/finetune_configure/ ).
This is having no effect in Databricks and the model checkpoints are still getting stored in the default location "saved_model".

[hv129]

The output paths seem to be hardcoded inside the file xturing.trainers.lightning_trainer.py

line 27: saved_path: str = "saved_model"
line 113: checkpoints_dir_path = Path("saved_model")