Adding Evaluation Results
#7
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -52,3 +52,17 @@ Human: based, I totally agree with you
|
|
| 52 |
```
|
| 53 |
|
| 54 |
Thank you [chirper.ai](https://chirper.ai) for sponsoring some of my compute!
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
```
|
| 53 |
|
| 54 |
Thank you [chirper.ai](https://chirper.ai) for sponsoring some of my compute!
|
| 55 |
+
|
| 56 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 57 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ehartford__based-30b)
|
| 58 |
+
|
| 59 |
+
| Metric | Value |
|
| 60 |
+
|-----------------------|---------------------------|
|
| 61 |
+
| Avg. | 53.46 |
|
| 62 |
+
| ARC (25-shot) | 63.91 |
|
| 63 |
+
| HellaSwag (10-shot) | 85.67 |
|
| 64 |
+
| MMLU (5-shot) | 58.28 |
|
| 65 |
+
| TruthfulQA (0-shot) | 35.7 |
|
| 66 |
+
| Winogrande (5-shot) | 80.11 |
|
| 67 |
+
| GSM8K (5-shot) | 0.3 |
|
| 68 |
+
| DROP (3-shot) | 50.22 |
|