Adding Evaluation Results
#1
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -837,4 +837,17 @@ The following hyperparameters were used during training:
|
|
| 837 |
- Transformers 4.36.2
|
| 838 |
- Pytorch 2.1.2
|
| 839 |
- Datasets 2.14.6
|
| 840 |
-
- Tokenizers 0.15.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 837 |
- Transformers 4.36.2
|
| 838 |
- Pytorch 2.1.2
|
| 839 |
- Datasets 2.14.6
|
| 840 |
+
- Tokenizers 0.15.0
|
| 841 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 842 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_dball__zephyr-tiny-dpo-qlora)
|
| 843 |
+
|
| 844 |
+
| Metric |Value|
|
| 845 |
+
|---------------------------------|----:|
|
| 846 |
+
|Avg. |37.35|
|
| 847 |
+
|AI2 Reasoning Challenge (25-Shot)|36.60|
|
| 848 |
+
|HellaSwag (10-Shot) |61.66|
|
| 849 |
+
|MMLU (5-Shot) |25.78|
|
| 850 |
+
|TruthfulQA (0-shot) |36.40|
|
| 851 |
+
|Winogrande (5-shot) |61.56|
|
| 852 |
+
|GSM8k (5-shot) | 2.12|
|
| 853 |
+
|