Commit
•
73a846b
1
Parent(s):
8972682
Adding Evaluation Results (#3)
Browse files- Adding Evaluation Results (db39c70737c938a259bf5112e214246867f37135)
Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -326,3 +326,17 @@ s still a matter of speculation and debate, ongoing research and exploration may
|
|
| 326 |
plications.
|
| 327 |
|
| 328 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 326 |
plications.
|
| 327 |
|
| 328 |
```
|
| 329 |
+
|
| 330 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 331 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_migtissera__Synthia-13B-v1.2)
|
| 332 |
+
|
| 333 |
+
| Metric | Value |
|
| 334 |
+
|-----------------------|---------------------------|
|
| 335 |
+
| Avg. | 51.56 |
|
| 336 |
+
| ARC (25-shot) | 61.26 |
|
| 337 |
+
| HellaSwag (10-shot) | 82.93 |
|
| 338 |
+
| MMLU (5-shot) | 56.47 |
|
| 339 |
+
| TruthfulQA (0-shot) | 47.27 |
|
| 340 |
+
| Winogrande (5-shot) | 76.48 |
|
| 341 |
+
| GSM8K (5-shot) | 10.99 |
|
| 342 |
+
| DROP (3-shot) | 25.48 |
|