Commit
•
a0299eb
1
Parent(s):
1b9b03d
Adding Evaluation Results (#5)
Browse files- Adding Evaluation Results (c7721bc2f76131a9fa8c93a27186aad7a8da25da)
Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -128,3 +128,17 @@ The following hyperparameters were used during training:
|
|
| 128 |
- Pytorch 1.10.0+cu113
|
| 129 |
- Datasets 2.5.1
|
| 130 |
- Tokenizers 0.12.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 128 |
- Pytorch 1.10.0+cu113
|
| 129 |
- Datasets 2.5.1
|
| 130 |
- Tokenizers 0.12.1
|
| 131 |
+
|
| 132 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 133 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_postbot__gpt2-medium-emailgen)
|
| 134 |
+
|
| 135 |
+
| Metric | Value |
|
| 136 |
+
|-----------------------|---------------------------|
|
| 137 |
+
| Avg. | 25.97 |
|
| 138 |
+
| ARC (25-shot) | 26.45 |
|
| 139 |
+
| HellaSwag (10-shot) | 34.31 |
|
| 140 |
+
| MMLU (5-shot) | 24.1 |
|
| 141 |
+
| TruthfulQA (0-shot) | 43.96 |
|
| 142 |
+
| Winogrande (5-shot) | 50.43 |
|
| 143 |
+
| GSM8K (5-shot) | 0.0 |
|
| 144 |
+
| DROP (3-shot) | 2.53 |
|