Commit
•
1a2efec
1
Parent(s):
03f1a0e
Adding Evaluation Results (#3)
Browse files- Adding Evaluation Results (d60fa9cdd873b74313325a5b3778c077745cc9bf)
Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -56,3 +56,17 @@ The following hyperparameters were used during training:
|
|
| 56 |
- Pytorch 2.0.0+cu117
|
| 57 |
- Datasets 2.10.1
|
| 58 |
- Tokenizers 0.13.3
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
- Pytorch 2.0.0+cu117
|
| 57 |
- Datasets 2.10.1
|
| 58 |
- Tokenizers 0.13.3
|
| 59 |
+
|
| 60 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 61 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Mikivis__xuanxuan)
|
| 62 |
+
|
| 63 |
+
| Metric | Value |
|
| 64 |
+
|-----------------------|---------------------------|
|
| 65 |
+
| Avg. | 24.72 |
|
| 66 |
+
| ARC (25-shot) | 23.46 |
|
| 67 |
+
| HellaSwag (10-shot) | 31.12 |
|
| 68 |
+
| MMLU (5-shot) | 26.27 |
|
| 69 |
+
| TruthfulQA (0-shot) | 35.97 |
|
| 70 |
+
| Winogrande (5-shot) | 50.43 |
|
| 71 |
+
| GSM8K (5-shot) | 0.0 |
|
| 72 |
+
| DROP (3-shot) | 5.74 |
|