Adding Evaluation Results
#2
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -182,3 +182,17 @@ You can also cite our [website](https://github.com/IDEA-CCNL/Fengshenbang-LM/):
|
|
| 182 |
howpublished={\url{https://github.com/IDEA-CCNL/Fengshenbang-LM}},
|
| 183 |
}
|
| 184 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 182 |
howpublished={\url{https://github.com/IDEA-CCNL/Fengshenbang-LM}},
|
| 183 |
}
|
| 184 |
```
|
| 185 |
+
|
| 186 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 187 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_IDEA-CCNL__Ziya-LLaMA-13B-Pretrain-v1)
|
| 188 |
+
|
| 189 |
+
| Metric | Value |
|
| 190 |
+
|-----------------------|---------------------------|
|
| 191 |
+
| Avg. | 25.68 |
|
| 192 |
+
| ARC (25-shot) | 27.99 |
|
| 193 |
+
| HellaSwag (10-shot) | 26.0 |
|
| 194 |
+
| MMLU (5-shot) | 27.04 |
|
| 195 |
+
| TruthfulQA (0-shot) | 48.59 |
|
| 196 |
+
| Winogrande (5-shot) | 50.12 |
|
| 197 |
+
| GSM8K (5-shot) | 0.0 |
|
| 198 |
+
| DROP (3-shot) | 0.0 |
|