We’ve made a bunch of improvements to Evals in the OpenAI dashboard. Use your test data to compare model performance, iterate on prompts, and improve outputs. Check out this walkthrough: x.com.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| OpenAI Evals analogous to Fine Tuning? | 5 | 1107 | August 2, 2024 | |
| Using Evals with fine tuned model | 4 | 399 | June 30, 2024 | |
| OpenAI releases updates to fine-tuning and custom models | 2 | 929 | April 5, 2024 | |
| Evaluations Beta custom eval prompt | 1 | 119 | October 30, 2024 | |
| Model Distillation (including Evals and Stored Completions) | 9 | 1152 | November 20, 2024 |