Adding Evaluation Results
#4
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -11,3 +11,17 @@ train-eval-index:
|
|
| 11 |
tokens: tokens
|
| 12 |
labels: tags
|
| 13 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
tokens: tokens
|
| 12 |
labels: tags
|
| 13 |
---
|
| 14 |
+
|
| 15 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 16 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_BreadAi__gpt-YA-1-1_160M)
|
| 17 |
+
|
| 18 |
+
| Metric | Value |
|
| 19 |
+
|-----------------------|---------------------------|
|
| 20 |
+
| Avg. | 25.21 |
|
| 21 |
+
| ARC (25-shot) | 22.95 |
|
| 22 |
+
| HellaSwag (10-shot) | 27.29 |
|
| 23 |
+
| MMLU (5-shot) | 26.25 |
|
| 24 |
+
| TruthfulQA (0-shot) | 47.02 |
|
| 25 |
+
| Winogrande (5-shot) | 50.67 |
|
| 26 |
+
| GSM8K (5-shot) | 0.0 |
|
| 27 |
+
| DROP (3-shot) | 2.32 |
|