Adding Evaluation Results
#7
by leaderboard-pr-bot - opened
README.md
CHANGED
|
@@ -877,4 +877,17 @@ We refer to Table 7 from our [paper](https://arxiv.org/abs/2211.01786) & [bigsci
|
|
| 877 |
journal={arXiv preprint arXiv:2211.01786},
|
| 878 |
year={2022}
|
| 879 |
}
|
| 880 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 877 |
journal={arXiv preprint arXiv:2211.01786},
|
| 878 |
year={2022}
|
| 879 |
}
|
| 880 |
+
```
|
| 881 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 882 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_bigscience__bloomz-7b1-mt)
|
| 883 |
+
|
| 884 |
+
| Metric | Value |
|
| 885 |
+
|-----------------------|---------------------------|
|
| 886 |
+
| Avg. | 39.96 |
|
| 887 |
+
| ARC (25-shot) | 43.86 |
|
| 888 |
+
| HellaSwag (10-shot) | 62.91 |
|
| 889 |
+
| MMLU (5-shot) | 37.35 |
|
| 890 |
+
| TruthfulQA (0-shot) | 45.65 |
|
| 891 |
+
| Winogrande (5-shot) | 63.06 |
|
| 892 |
+
| GSM8K (5-shot) | 0.0 |
|
| 893 |
+
| DROP (3-shot) | 26.9 |
|