Adding Evaluation Results
#11
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -98,4 +98,17 @@ The following hyperparameters were used during training:
|
|
| 98 |
- Transformers 4.34.1
|
| 99 |
- Pytorch 2.0.1+cu117
|
| 100 |
- Datasets 2.14.5
|
| 101 |
-
- Tokenizers 0.14.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 98 |
- Transformers 4.34.1
|
| 99 |
- Pytorch 2.0.1+cu117
|
| 100 |
- Datasets 2.14.5
|
| 101 |
+
- Tokenizers 0.14.0
|
| 102 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 103 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ehartford__dolphin-2.2.1-mistral-7b)
|
| 104 |
+
|
| 105 |
+
| Metric | Value |
|
| 106 |
+
|-----------------------|---------------------------|
|
| 107 |
+
| Avg. | 53.06 |
|
| 108 |
+
| ARC (25-shot) | 63.48 |
|
| 109 |
+
| HellaSwag (10-shot) | 83.86 |
|
| 110 |
+
| MMLU (5-shot) | 63.28 |
|
| 111 |
+
| TruthfulQA (0-shot) | 53.17 |
|
| 112 |
+
| Winogrande (5-shot) | 78.37 |
|
| 113 |
+
| GSM8K (5-shot) | 21.08 |
|
| 114 |
+
| DROP (3-shot) | 8.19 |
|