Commit
·
1f1e54b
1
Parent(s):
e0208b0
Adding Evaluation Results (#4)
Browse files- Adding Evaluation Results (d414fa126130d707d5d9a6891e875c1c290c1059)
Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>
README.md
CHANGED
|
@@ -123,3 +123,17 @@ print(result[0]["generated_text"])
|
|
| 123 |
---
|
| 124 |
|
| 125 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 123 |
---
|
| 124 |
|
| 125 |
|
| 126 |
+
|
| 127 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 128 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_postbot__emailgen-pythia-410m-deduped)
|
| 129 |
+
|
| 130 |
+
| Metric | Value |
|
| 131 |
+
|-----------------------|---------------------------|
|
| 132 |
+
| Avg. | 26.65 |
|
| 133 |
+
| ARC (25-shot) | 27.9 |
|
| 134 |
+
| HellaSwag (10-shot) | 40.04 |
|
| 135 |
+
| MMLU (5-shot) | 27.35 |
|
| 136 |
+
| TruthfulQA (0-shot) | 38.2 |
|
| 137 |
+
| Winogrande (5-shot) | 52.09 |
|
| 138 |
+
| GSM8K (5-shot) | 0.0 |
|
| 139 |
+
| DROP (3-shot) | 0.99 |
|