Adding Evaluation Results
#10
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -151,3 +151,17 @@ If you found OpenLLaMA useful in your research or applications, please cite usin
|
|
| 151 |
|
| 152 |
|
| 153 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 151 |
|
| 152 |
|
| 153 |
|
| 154 |
+
|
| 155 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 156 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_openlm-research__open_llama_13b)
|
| 157 |
+
|
| 158 |
+
| Metric | Value |
|
| 159 |
+
|-----------------------|---------------------------|
|
| 160 |
+
| Avg. | 41.37 |
|
| 161 |
+
| ARC (25-shot) | 51.19 |
|
| 162 |
+
| HellaSwag (10-shot) | 75.23 |
|
| 163 |
+
| MMLU (5-shot) | 43.75 |
|
| 164 |
+
| TruthfulQA (0-shot) | 38.08 |
|
| 165 |
+
| Winogrande (5-shot) | 72.06 |
|
| 166 |
+
| GSM8K (5-shot) | 3.26 |
|
| 167 |
+
| DROP (3-shot) | 5.99 |
|