I see in the documentation here:
https://platform.openai.com/docs/guides/fine-tuning/fine-tuning-examples
That it can be beneficial to omit function parameters, descriptions, etc when fine-tuning a model based around function-calling, as it can supposedly decrease costs when using the model in the future, as the model may require less function information.
Anyone with any experience finetuning for function calling got anything to say about this?