Commit
•
5a37b3d
1
Parent(s):
581aba3
Adding Evaluation Results (#1)
Browse files- Adding Evaluation Results (8c7f9f8c94d4c7d2bcb535692bac8232c8a9f0a1)
Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -79,4 +79,17 @@ The following hyperparameters were used during training:
|
|
| 79 |
- Datasets 2.14.6
|
| 80 |
- Tokenizers 0.14.1
|
| 81 |
|
| 82 |
-
If you want to support me, you can [here](https://ko-fi.com/undiai).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 79 |
- Datasets 2.14.6
|
| 80 |
- Tokenizers 0.14.1
|
| 81 |
|
| 82 |
+
If you want to support me, you can [here](https://ko-fi.com/undiai).
|
| 83 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 84 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Undi95__Llama2-13B-no_robots-alpaca-lora)
|
| 85 |
+
|
| 86 |
+
| Metric | Value |
|
| 87 |
+
|-----------------------|---------------------------|
|
| 88 |
+
| Avg. | 46.55 |
|
| 89 |
+
| ARC (25-shot) | 58.87 |
|
| 90 |
+
| HellaSwag (10-shot) | 82.43 |
|
| 91 |
+
| MMLU (5-shot) | 53.11 |
|
| 92 |
+
| TruthfulQA (0-shot) | 40.46 |
|
| 93 |
+
| Winogrande (5-shot) | 75.3 |
|
| 94 |
+
| GSM8K (5-shot) | 6.44 |
|
| 95 |
+
| DROP (3-shot) | 9.26 |
|