Commit
•
564b13d
1
Parent(s):
08c7f24
Adding Evaluation Results (#1)
Browse files- Adding Evaluation Results (7e83ca53387963ecaa18152ac56586eac90900fb)
Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -30,4 +30,17 @@ Merge of [Marcoroni-13B](https://huggingface.co/AIDC-ai-business/Marcoroni-13B)
|
|
| 30 |
| ARC (25-shot) | 63.48 |
|
| 31 |
| HellaSwag (10-shot) | 82.89 |
|
| 32 |
| MMLU (5-shot) | 58.72 |
|
| 33 |
-
| TruthfulQA (0-shot) | 55.56 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
| ARC (25-shot) | 63.48 |
|
| 31 |
| HellaSwag (10-shot) | 82.89 |
|
| 32 |
| MMLU (5-shot) | 58.72 |
|
| 33 |
+
| TruthfulQA (0-shot) | 55.56 |
|
| 34 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 35 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Weyaxi__Luban-Marcoroni-13B-v3)
|
| 36 |
+
|
| 37 |
+
| Metric | Value |
|
| 38 |
+
|-----------------------|---------------------------|
|
| 39 |
+
| Avg. | 51.13 |
|
| 40 |
+
| ARC (25-shot) | 63.74 |
|
| 41 |
+
| HellaSwag (10-shot) | 82.88 |
|
| 42 |
+
| MMLU (5-shot) | 58.64 |
|
| 43 |
+
| TruthfulQA (0-shot) | 55.56 |
|
| 44 |
+
| Winogrande (5-shot) | 76.87 |
|
| 45 |
+
| GSM8K (5-shot) | 9.93 |
|
| 46 |
+
| DROP (3-shot) | 10.25 |
|