Commit
•
608563b
1
Parent(s):
18e0bde
Adding Evaluation Results (#2)
Browse files- Adding Evaluation Results (df863afd893edf8c1380c06d053a2dd0822b47e1)
Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -12,3 +12,17 @@ prompt:
|
|
| 12 |
```txt
|
| 13 |
Lily asked the teacher a question. "{prompt}" The teacher smiled and said, "
|
| 14 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
```txt
|
| 13 |
Lily asked the teacher a question. "{prompt}" The teacher smiled and said, "
|
| 14 |
```
|
| 15 |
+
|
| 16 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 17 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_blueapple8259__TinyStories-Alpaca)
|
| 18 |
+
|
| 19 |
+
| Metric | Value |
|
| 20 |
+
|-----------------------|---------------------------|
|
| 21 |
+
| Avg. | 24.51 |
|
| 22 |
+
| ARC (25-shot) | 23.98 |
|
| 23 |
+
| HellaSwag (10-shot) | 24.92 |
|
| 24 |
+
| MMLU (5-shot) | 23.35 |
|
| 25 |
+
| TruthfulQA (0-shot) | 46.68 |
|
| 26 |
+
| Winogrande (5-shot) | 51.85 |
|
| 27 |
+
| GSM8K (5-shot) | 0.0 |
|
| 28 |
+
| DROP (3-shot) | 0.81 |
|