I’m not an authority on fine-tuning, but I have gleaned from other experts that you may need to increase the epochs before you will begin to see good results from your model.
Related topics
Topic | Replies | Views | Activity | |
---|---|---|---|---|
Using the new fine-tunes endpoint for binary classification | 10 | 2166 | January 11, 2024 | |
Issues with Fine-Tuned Babbage-002 Model Returning Incorrect Completions | 13 | 1781 | December 21, 2023 | |
Training loss=good, Validation loss=good | 8 | 4719 | April 5, 2024 | |
Ada model fined tuned for classification hets delusional when fed with thousands of records | 7 | 1012 | May 23, 2023 | |
Seeking Solutions for Instability in Multi-Class Labeling Tasks | 8 | 1057 | November 15, 2023 |