Hi everyone!
I am currently trying to fine-tune the Llama 3.1 8B Instruct model using ORPO.
Unfortunately, I receive a 500 error (see below the Logs).
Settings
- LLM ORPO
- Standard Parameters (no changes made)
- Column mapping according to dataset (i.e. prompt, text, rejected_text)
- Upload of local CSV file
What I tried
- Changing the “wrapping” of my raw text according to the example datasets (trl-lib/ultrafeedback_binarized · Datasets at Hugging Face)
- Different wrappings
- Removing all commata from the CSV file, to prevent accidental column-recognition
- Different settings
A single prompt-text-rejected_text-set might look like this:
| prompt | text | rejected_text |
|---|---|---|
| Wie beeinflusst die Salzkonzentration im Boden das Wachstum von Pflanzen? | Welche Pflanzenarten untersuchen Sie und wie werden Sie die Salzkonzentration und das Wachstum messen? | Salz ist generell schlecht für Pflanzen also wird das Wachstum gehemmt. |
I am fairly new to this, perhaps someone has an idea how to go forward to be able to fine-tune the model using ORPO? Might it have to do with using German language in the training set?
Cheers!
P.s.: Does someone know how to delete the logs to clean it up after a test? 
KeyError: ‘text’
raise KeyError(key) from err
File “/app/env/lib/python3.10/site-packages/pandas/core/indexes/base.py”, line 3812, in get_loc
indexer = self.columns.get_loc(key)
File “/app/env/lib/python3.10/site-packages/pandas/core/frame.py”, line 4102, in getitem
train_df.loc[:, “autotrain_text”] = train_df[self.text_column]
File “/app/env/lib/python3.10/site-packages/autotrain/preprocessor/text.py”, line 293, in prepare_columns
train_df, valid_df = self.prepare_columns(train_df, valid_df)
File “/app/env/lib/python3.10/site-packages/autotrain/preprocessor/text.py”, line 311, in prepare
return preprocessor.prepare()
File “/app/env/lib/python3.10/site-packages/autotrain/dataset.py”, line 570, in prepare
data_path = dset.prepare()
File “/app/env/lib/python3.10/site-packages/autotrain/app/ui_routes.py”, line 645, in handle_form
return await dependant.call(**values)
File “/app/env/lib/python3.10/site-packages/fastapi/routing.py”, line 191, in run_endpoint_function
raw_response = await run_endpoint_function(
File “/app/env/lib/python3.10/site-packages/fastapi/routing.py”, line 278, in app
response = await func(request)
File “/app/env/lib/python3.10/site-packages/starlette/routing.py”, line 72, in app
await app(scope, receive, sender)
File “/app/env/lib/python3.10/site-packages/starlette/_exception_handler.py”, line 53, in wrapped_app
raise exc
File “/app/env/lib/python3.10/site-packages/starlette/_exception_handler.py”, line 64, in wrapped_app
await wrap_app_handling_exceptions(app, request)(scope, receive, send)
File “/app/env/lib/python3.10/site-packages/starlette/routing.py”, line 77, in app
await self.app(scope, receive, send)
File “/app/env/lib/python3.10/site-packages/starlette/routing.py”, line 297, in handle
await route.handle(scope, receive, send)
File “/app/env/lib/python3.10/site-packages/starlette/routing.py”, line 776, in app
await self.middleware_stack(scope, receive, send)
File “/app/env/lib/python3.10/site-packages/starlette/routing.py”, line 756, in call
await app(scope, receive, sender)
File “/app/env/lib/python3.10/site-packages/starlette/_exception_handler.py”, line 53, in wrapped_app
raise exc
File “/app/env/lib/python3.10/site-packages/starlette/_exception_handler.py”, line 64, in wrapped_app
await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
File “/app/env/lib/python3.10/site-packages/starlette/middleware/exceptions.py”, line 65, in call
await self.app(scope, receive, send_wrapper)
File “/app/env/lib/python3.10/site-packages/starlette/middleware/sessions.py”, line 85, in call
await self.app(scope, receive, _send)
File “/app/env/lib/python3.10/site-packages/starlette/middleware/errors.py”, line 164, in call
raise exc
File “/app/env/lib/python3.10/site-packages/starlette/middleware/errors.py”, line 186, in call
await self.middleware_stack(scope, receive, send)
File “/app/env/lib/python3.10/site-packages/starlette/applications.py”, line 123, in call
await super().call(scope, receive, send)
File “/app/env/lib/python3.10/site-packages/fastapi/applications.py”, line 1054, in call
return await self.app(scope, receive, send)
File “/app/env/lib/python3.10/site-packages/uvicorn/middleware/proxy_headers.py”, line 69, in call
result = await app( # type: ignore[func-returns-value]
File “/app/env/lib/python3.10/site-packages/uvicorn/protocols/http/httptools_impl.py”, line 411, in run_asgi
Traceback (most recent call last):
The above exception was the direct cause of the following exception:
KeyError: ‘text’
File “pandas/_libs/hashtable_class_helper.pxi”, line 7089, in pandas._libs.hashtable.PyObjectHashTable.get_item
File “pandas/_libs/hashtable_class_helper.pxi”, line 7081, in pandas._libs.hashtable.PyObjectHashTable.get_item
File “index.pyx”, line 196, in pandas._libs.index.IndexEngine.get_loc
File “index.pyx”, line 167, in pandas._libs.index.IndexEngine.get_loc
return self._engine.get_loc(casted_key)
File “/app/env/lib/python3.10/site-packages/pandas/core/indexes/base.py”, line 3805, in get_loc
Traceback (most recent call last):
ERROR: Exception in ASGI application
INFO | 2024-10-08 21:29:58 | autotrain.app.ui_routes:handle_form:629 - Column mapping: {‘prompt’: ‘prompt’, ‘text’: ‘text’, ‘rejected_text’: ‘rejected_text’}
INFO | 2024-10-08 21:29:58 | autotrain.app.ui_routes:handle_form:628 - Task: lm_training
INFO | 2024-10-08 21:29:58 | autotrain.app.ui_routes:handle_form:500 - hardware: local-ui
INFO | 2024-10-08 21:29:28 | autotrain.app.ui_routes:fetch_params:391 - Param distributed_backend not found in UI_PARAMS
INFO | 2024-10-08 21:29:28 | autotrain.app.ui_routes:fetch_params:381 - Task: llm:orpo
INFO | 2024-10-08 21:29:26 | autotrain.app.ui_routes:fetch_params:391 - Param distributed_backend not found in UI_PARAMS
INFO | 2024-10-08 21:29:26 | autotrain.app.ui_routes:fetch_params:381 - Task: llm:sft
INFO: 10.16.3.138:58147 - “GET / HTTP/1.1” 307 Temporary Redirect
INFO: 10.16.3.138:58147 - “GET / HTTP/1.1” 307 Temporary Redirect
INFO: Uvicorn running on http://0.0.0.0:7860 (Press CTRL+C to quit)
INFO: Application startup complete.
INFO: Waiting for application startup.
INFO: Started server process [73]
INFO | 2024-10-08 21:29:24 | autotrain.app.app::24 - AutoTrain started successfully
INFO | 2024-10-08 21:29:24 | autotrain.app.app::23 - AutoTrain version: 0.8.21
INFO | 2024-10-08 21:29:24 | autotrain.app.app::13 - Starting AutoTrain…
INFO | 2024-10-08 21:29:24 | autotrain.app.ui_routes::298 - AutoTrain started successfully
INFO | 2024-10-08 21:29:22 | autotrain.app.ui_routes::32 - Starting AutoTrain…
