Adding Evaluation Results
#3
by leaderboard-pr-bot - opened
README.md
CHANGED
|
@@ -72,3 +72,17 @@ The 42dot LLM-SFT is licensed under the Creative Commons Attribution-NonCommerci
|
|
| 72 |
version = {1.0.0},
|
| 73 |
}
|
| 74 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 72 |
version = {1.0.0},
|
| 73 |
}
|
| 74 |
```
|
| 75 |
+
|
| 76 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 77 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_42dot__42dot_LLM-SFT-1.3B)
|
| 78 |
+
|
| 79 |
+
| Metric | Value |
|
| 80 |
+
|-----------------------|---------------------------|
|
| 81 |
+
| Avg. | 32.39 |
|
| 82 |
+
| ARC (25-shot) | 36.09 |
|
| 83 |
+
| HellaSwag (10-shot) | 58.96 |
|
| 84 |
+
| MMLU (5-shot) | 25.51 |
|
| 85 |
+
| TruthfulQA (0-shot) | 39.98 |
|
| 86 |
+
| Winogrande (5-shot) | 58.41 |
|
| 87 |
+
| GSM8K (5-shot) | 0.68 |
|
| 88 |
+
| DROP (3-shot) | 7.11 |
|