If you’re doing a classification use case, then you’ll need to provide a validation set, and set a few more parameters - see OpenAI API
Related topics
Topic | Replies | Views | Activity | |
---|---|---|---|---|
Fine Tuning results of davinci model | 0 | 419 | August 10, 2023 | |
Questions about fine-tuning GPT-3.5-turbo | 1 | 2127 | October 29, 2023 | |
Fine Tune GPT-3.5 Results File: Meaning of "Step", Number of Rows, and Randomization | 3 | 1517 | August 30, 2023 | |
Steps Meaning in Fine Tuning and How to Pick the Optimal Number of Epochs from Them? | 13 | 7926 | December 28, 2023 | |
Evaluating a finetuned model | 3 | 2585 | November 29, 2023 |