We have created fine tune models and using it in openai playground. We are seeing human response is automatically triggering. Can you please help me on the same. what are we missing here. attached the screenshot for the same.
Seems perfectly fine to me, and reads like normal chatbot chatter.
What exactly would you like to see happen based on specific prompts and specific completions?
What does your fine-tuning dataset look like? Just a line or two would help.
It sounds like you’re not using a stop word for the fine-tuning or the completion maybe?
I’d recommend searching the web and the forums here for similar problems - i.e. “GPT chatbot” etc.
You’re trying to make a chatbot, right?
1 Like
@PaulBellow Below is my dataset
{"prompt":"Item=handbag, Color=army_green, price=$99, size=S->","completion":" This stylish small army green handbag will add a unique touch to your look, without costing you a fortune."}
{"prompt":"Item=bag, Color=green, price=$199, size=S->","completion":" This stylish small green bag will add a unique touch to your look, without costing you a fortune."}
{"prompt":"Item=purse, Color=yellow, price=$299, size=S->","completion":" This stylish small yellow purse will add a unique touch to your look, without costing you a fortune."}
We are trying get it but we are not getting expected result. Yes we are trying chatbot
You need a stop word at the end here…
See…
https://platform.openai.com/docs/guides/fine-tuning
Also…
Each prompt should end with a fixed separator to inform the model when the prompt ends and the completion begins. A simple separator which generally works well is
\n\n###\n\n. The separator should not appear elsewhere in any prompt.Each completion should end with a fixed stop sequence to inform the model when the completion ends. A stop sequence could be
\n,###, or any other token that does not appear in any completion.
https://platform.openai.com/docs/guides/fine-tuning/preparing-your-dataset
Good luck!