Cannot, for the life of me, get a detailed enough response

[PaulBellow]

This is a good semi-related post. They’re using a fine-tuned gpt-3.5 to get quality output 1k+ words consistently…

Share: Fine-Tune GPT 3.5 16k Results Only 10 Examples Novel Outlines

Will do! Today we got the ability to use our fine tunes inside Rexy. I’m at a Barnes and Noble designing a dataset now to make gpt 3.5 write at least 1,000 words consistently. I’m going to stick with just one genre at first, probably my orc mafia romance project I was writing live in October. If I can get gpt 3.5 to consistently write 1000+ words to a writing brief, keeping narrative logic? That will be a huge win. It typically will write between 500-800 words. OpenAI usually sticks to the outl…

I’ll be running some of my own tests soon.

Oops. This is an even more recent update!

Share: Fine-Tune GPT 3.5 16k Results Only 10 Examples Novel Outlines

Update for those who read the original: We have moved into making the fine tunes write fiction. We are learning that training loss is a meaningless metric in the use case of fiction writing. We are getting great results from training loss numbers in the 1.8+ area and all going “Um… what does any of this even mean?” LOL. We are using 10-24 examples of writing and finding that a fine tune on 3.5 16k can: write the full 4096 output length very easily (we get 2,000-3,000 word responses from GPT…

I really wish OpenAI would make a GPT-4-Turbo-FICTION trained on fiction. There’s a few OpenSource models going that route.