Is it known how well performance scales with the size of the prompt and size of the fine-tuning dataset? i.e. something like the Chinchilla paper but for prompt and dataset size.
I don’t know, and would be very curious to find out.
Is it known how well performance scales with the size of the prompt and size of the fine-tuning dataset? i.e. something like the Chinchilla paper but for prompt and dataset size.
I don’t know, and would be very curious to find out.