Adding Evaluation Results
#2
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -7,4 +7,17 @@ language:
|
|
| 7 |
- en
|
| 8 |
---
|
| 9 |
|
| 10 |
-
very wip experiment.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
- en
|
| 8 |
---
|
| 9 |
|
| 10 |
+
very wip experiment.
|
| 11 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 12 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_chargoddard__llama-2-34b-uncode)
|
| 13 |
+
|
| 14 |
+
| Metric | Value |
|
| 15 |
+
|-----------------------|---------------------------|
|
| 16 |
+
| Avg. | 36.2 |
|
| 17 |
+
| ARC (25-shot) | 39.51 |
|
| 18 |
+
| HellaSwag (10-shot) | 33.9 |
|
| 19 |
+
| MMLU (5-shot) | 38.49 |
|
| 20 |
+
| TruthfulQA (0-shot) | 40.94 |
|
| 21 |
+
| Winogrande (5-shot) | 74.35 |
|
| 22 |
+
| GSM8K (5-shot) | 20.77 |
|
| 23 |
+
| DROP (3-shot) | 5.43 |
|