Adding Evaluation Results
#5
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -171,4 +171,17 @@ for lang in data_samples_long:
|
|
| 171 |
# zh-1 0 0
|
| 172 |
# hi-0 1 1
|
| 173 |
# hi-1 0 0
|
| 174 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 171 |
# zh-1 0 0
|
| 172 |
# hi-0 1 1
|
| 173 |
# hi-1 0 0
|
| 174 |
+
```
|
| 175 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 176 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_facebook__xglm-564M)
|
| 177 |
+
|
| 178 |
+
| Metric | Value |
|
| 179 |
+
|-----------------------|---------------------------|
|
| 180 |
+
| Avg. | 26.19 |
|
| 181 |
+
| ARC (25-shot) | 24.57 |
|
| 182 |
+
| HellaSwag (10-shot) | 34.64 |
|
| 183 |
+
| MMLU (5-shot) | 25.18 |
|
| 184 |
+
| TruthfulQA (0-shot) | 40.43 |
|
| 185 |
+
| Winogrande (5-shot) | 52.25 |
|
| 186 |
+
| GSM8K (5-shot) | 0.23 |
|
| 187 |
+
| DROP (3-shot) | 6.04 |
|