Adding Evaluation Results
#8
by leaderboard-pr-bot - opened
README.md
CHANGED
|
@@ -173,4 +173,17 @@ AGI Eval:
|
|
| 173 |
| | |acc_norm|0.3447|± |0.0332|
|
| 174 |
|agieval_sat_math | 0|acc |0.3364|± |0.0319|
|
| 175 |
| | |acc_norm|0.2773|± |0.0302|
|
| 176 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 173 |
| | |acc_norm|0.3447|± |0.0332|
|
| 174 |
|agieval_sat_math | 0|acc |0.3364|± |0.0319|
|
| 175 |
| | |acc_norm|0.2773|± |0.0302|
|
| 176 |
+
```
|
| 177 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 178 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_NousResearch__Redmond-Puffin-13B)
|
| 179 |
+
|
| 180 |
+
| Metric | Value |
|
| 181 |
+
|-----------------------|---------------------------|
|
| 182 |
+
| Avg. | 47.88 |
|
| 183 |
+
| ARC (25-shot) | 60.41 |
|
| 184 |
+
| HellaSwag (10-shot) | 83.2 |
|
| 185 |
+
| MMLU (5-shot) | 55.36 |
|
| 186 |
+
| TruthfulQA (0-shot) | 42.12 |
|
| 187 |
+
| Winogrande (5-shot) | 76.64 |
|
| 188 |
+
| GSM8K (5-shot) | 11.45 |
|
| 189 |
+
| DROP (3-shot) | 5.98 |
|