I have a question about AutoTrain csv data format.
Documentaion says:
LLM finetuning accepts data in CSV format.
Data Format For SFT / Generic Trainer
For SFT / Generic Trainer, the data should be in the following format:
| text | | This is the first sentence. | | This is the second sentence. |
I am not sure what this | text | | This is the first sentence. | | This is the second sentence. | means when UI only allows 1 column as input.
I lave looked at example dataset and tried to structure my csv as there:
text
“### Human: question text ### Assistant: answer text”
“### Human: question text ### Assistant: answer text”
but this gives me errors about: ValueError: 3 columns passed, passed data had 0 columns
Any advice?
PS: I was trying to train meta-llama/Llama-2-13b-chat-hf