stop overwriting the config for dataset generation

Author: strickvl

llm-finetuning/README.md

@@ -69,8 +69,8 @@ The three pipelines can be run using the CLI:
 
 ```shell
 # Data generation
-python run.py --feature-engineering --config <NAME_OF_CONFIG_IN_CONFIGS_FOLDER>
-python run.py --feature-engineering --config generate_code_dataset.yaml
+python run.py --feature-pipeline --config <NAME_OF_CONFIG_IN_CONFIGS_FOLDER>
+python run.py --feature-pipeline --config generate_code_dataset.yaml
 
 # Training
 python run.py --training-pipeline --config <NAME_OF_CONFIG_IN_CONFIGS_FOLDER>

llm-finetuning/run.py

@@ -124,9 +124,7 @@ def main(
 
     # Execute Feature Engineering Pipeline
     if feature_pipeline:
-        pipeline_args = {}
         from pipelines import generate_code_dataset
-
         generate_code_dataset.with_options(**pipeline_args)()
         logger.info("Feature Engineering pipeline finished successfully!\n")