Elaine commited on
Update README.md
Browse files
README.md
CHANGED
|
@@ -89,7 +89,10 @@ warmup_ratio: 0.1
|
|
| 89 |
|
| 90 |
## Evaluation
|
| 91 |
|
|
|
|
| 92 |
|
|
|
|
|
|
|
| 93 |
|
| 94 |
## Citation
|
| 95 |
|
|
|
|
| 89 |
|
| 90 |
## Evaluation
|
| 91 |
|
| 92 |
+
We use [IFEval](https://huggingface.co/datasets/google/IFEval) to evaluate the performance of the model in English. For Finnish, we translated the IFEval prompts to [Finnish](https://huggingface.co/datasets/LumiOpen/ifeval_mt) with DeepL. We report the instruction-level strict accuracy:
|
| 93 |
|
| 94 |
+
- **English**: 0.3997
|
| 95 |
+
- **Finnish**: 0.3448
|
| 96 |
|
| 97 |
## Citation
|
| 98 |
|