hyperparameters
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| What does the learning rate of 2 or 5 or 10 mean (different from 2e-5 or 1e-4), in fine-tuning? |
|
4 | 180 | January 27, 2025 |
| Question about the Use of Seed Parameter and Deterministic Outputs |
|
3 | 2165 | May 29, 2024 |
| How to find the best combination of Batch size, LRM and epochs |
|
1 | 844 | April 30, 2024 |