Closed vrodriguezf closed 9 months ago
About fine-tuning i think we can divide this activity in two parts:
exactly, the idea would to be to turn human gameplays into fake chatgpt conversations in which the human responses are mapped to assistant responses. Then, use that to fine tune the model.
exactly, the idea would to be to turn human gameplays into fake chatgpt conversations in which the human responses are mapped to assistant responses. Then, use that to fine tune the model.
Regarding this, i coded a script that converts csv into a "GPT readable" json file. I'm attaching one example here.
I don't know how the prompt would be intended, and i ask when running the script which environment do you want for better undersandability.
FYI My fine tuned model is this: Ft:GPT-3.5-turbo-1106:personal::8MDSBDRp
closing this, already tried and worked
One way to fine tune would be to convert the logs of human gameplays to the json format required by the finetune api:
The idea would be to turn human actions into "role": "assistant" messages as if they were the result of chatting with the model. About the number of gameplays, the docs say:
To test for generalisation, since there are 3 scenarios with different initial conditions, we should leave 1 for test (the fine-tuning GUI allows you to upload separate jsons for training and test. Actually, a better strategy would be to create more scenarios on our own by replicating the mission files that we already have for the provided missions