While I have read the documentation on fine-tuning GPT-3, I do not understand how to do so. It seems that the proposed CLI commands do not work in the Windows CMD interface and I can not find any documentation on how to finetune GPT3 using a "regular" python script. I have tried to understand the functions defined in the package. However I can not make sense of them. Is there any information that I am missing or is it just not possible to fine-tune GPT-3 on a Windows machine?
For anybody having a similar problem: We solved the problem by using the anaconda prompt cmd. There everything worked flawlessly.