[BUG]Exception while opening Chat window for an experiment

[mahirgunyel]

🐛 Bug

I fine tunned an LLM. After the experiment was completed, I clicked on the chat link and got error. This is happening each time I click on chat link. config file and logs are attached. The exception trace:
script_sources: ['/_f/e9e7dce9-4027-4af3-bba9-ff9ac9234fd9/tmp__7saxef.min.js']
initialized: True
version: 1.14.4
name: H2O LLM Studio
heap_mode: False
wave_utils_stack_trace_str: ### stacktrace
Traceback (most recent call last):

File "/home/admin1/H2OLLMStudio/h2o-llmstudio/./llm_studio/app_utils/handlers.py", line 363, in handle
await experiment_display(q)

File "/home/admin1/H2OLLMStudio/h2o-llmstudio/./llm_studio/app_utils/sections/experiment.py", line 1128, in experiment_display
await chat_tab(q)

File "/home/admin1/H2OLLMStudio/h2o-llmstudio/./llm_studio/app_utils/sections/chat.py", line 72, in chat_tab
validation_dataframe = get_prediction_dataframe(cfg.output_directory)

File "/home/admin1/H2OLLMStudio/h2o-llmstudio/./llm_studio/src/utils/export_utils.py", line 31, in get_prediction_dataframe
return pd.read_csv(f"{experiment_path}/validation_predictions.csv")

File "/home/admin1/H2OLLMStudio/h2o-llmstudio/.venv/lib/python3.10/site-packages/pandas/io/parsers/readers.py", line 1026, in read_csv
return _read(filepath_or_buffer, kwds)

File "/home/admin1/H2OLLMStudio/h2o-llmstudio/.venv/lib/python3.10/site-packages/pandas/io/parsers/readers.py", line 626, in _read
return parser.read(nrows)

File "/home/admin1/H2OLLMStudio/h2o-llmstudio/.venv/lib/python3.10/site-packages/pandas/io/parsers/readers.py", line 1923, in read
) = self._engine.read( # type: ignore[attr-defined]

File "/home/admin1/H2OLLMStudio/h2o-llmstudio/.venv/lib/python3.10/site-packages/pandas/io/parsers/c_parser_wrapper.py", line 234, in read
chunks = self._reader.read_low_memory(nrows)

File "pandas/_libs/parsers.pyx", line 838, in pandas._libs.parsers.TextReader.read_low_memory

File "pandas/_libs/parsers.pyx", line 905, in pandas._libs.parsers.TextReader._read_rows

File "pandas/_libs/parsers.pyx", line 874, in pandas._libs.parsers.TextReader._tokenize_rows

File "pandas/_libs/parsers.pyx", line 891, in pandas._libs.parsers.TextReader._check_tokenize_status

File "pandas/_libs/parsers.pyx", line 2061, in pandas._libs.parsers.raise_parser_error

pandas.errors.ParserError: Error tokenizing data. C error: Expected 3 fields in line 3, saw 4

logs_wondrous-salmon.zip

To Reproduce

Fine Tune the Mistral-7B-Instruct with a csv file with colums ”question” and ”answer”, using the attached configuration(almost all default values). Click the chat link for the completed experiment

LLM Studio version

[pascal-pfeiffer]

Given the error message, I am assuming a malformed csv file.
To prevent parsing issues, we recommend using parquet files when possible. If the error persists, we might be able to help on a minimum reproducible sample of that dataset.