Commit
•
fc008ff
1
Parent(s):
41a2e61
Adding Evaluation Results (#5)
Browse files- Adding Evaluation Results (e7ba518c950f23bf3e7d5c72da40c7a2eecebb1c)
Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>
README.md
CHANGED
@@ -190,4 +190,17 @@ Once the rocket has reached the necessary velocity, it must also have sufficient
|
|
190 |
|
191 |
Overall, launching a rocket into LEO is a complex process that involves careful planning, preparation, and execution. Achieving the necessary velocity and maintaining the rocket's orbit requires a high level of technical expertise and precision.
|
192 |
|
193 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
190 |
|
191 |
Overall, launching a rocket into LEO is a complex process that involves careful planning, preparation, and execution. Achieving the necessary velocity and maintaining the rocket's orbit requires a high level of technical expertise and precision.
|
192 |
|
193 |
+
```
|
194 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
195 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_migtissera__Synthia-13B)
|
196 |
+
|
197 |
+
| Metric | Value |
|
198 |
+
|-----------------------|---------------------------|
|
199 |
+
| Avg. | 48.56 |
|
200 |
+
| ARC (25-shot) | 59.98 |
|
201 |
+
| HellaSwag (10-shot) | 81.86 |
|
202 |
+
| MMLU (5-shot) | 56.11 |
|
203 |
+
| TruthfulQA (0-shot) | 47.41 |
|
204 |
+
| Winogrande (5-shot) | 76.09 |
|
205 |
+
| GSM8K (5-shot) | 10.99 |
|
206 |
+
| DROP (3-shot) | 7.45 |
|