I’m just trying a few things on the playground and used davinci to generate some short tweets. If I give a prompt with some args: Stop sequence: ###, 6. Generate a list of 5 tweets. Output: ### For the default davinci model, I received 5 tweets as expected. But using a fine-tuned model, which…

Fine tuned model providing worse output

warrenjday October 4, 2022, 9:35pm 3

Ahh that makes total sense. Thank you!

Topic		Replies	Views
Struggling with poor performance on fine-tuned davinci model API	15	2643	December 20, 2023
Should prompts be unique for fine-tuning? Prompting	9	1713	December 25, 2023
Building the first fine-tuned model API	5	978	December 27, 2023
Fine-tuning quality davinci vs text-davinci-003 API	1	858	February 3, 2023
Fine Tuned Chatbot forgets how to output summary of conversation API	9	1824	December 18, 2023