Adding Evaluation Results
#1
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -6,4 +6,17 @@ widget:
|
|
| 6 |
- text: "I love AutoTrain because "
|
| 7 |
---
|
| 8 |
|
| 9 |
-
# Model Trained Using AutoTrain
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
- text: "I love AutoTrain because "
|
| 7 |
---
|
| 8 |
|
| 9 |
+
# Model Trained Using AutoTrain
|
| 10 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 11 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_RoversX__llama-2-7b-hf-small-shards-Samantha-V1-SFT)
|
| 12 |
+
|
| 13 |
+
| Metric | Value |
|
| 14 |
+
|-----------------------|---------------------------|
|
| 15 |
+
| Avg. | 43.57 |
|
| 16 |
+
| ARC (25-shot) | 53.16 |
|
| 17 |
+
| HellaSwag (10-shot) | 77.71 |
|
| 18 |
+
| MMLU (5-shot) | 43.47 |
|
| 19 |
+
| TruthfulQA (0-shot) | 45.28 |
|
| 20 |
+
| Winogrande (5-shot) | 73.8 |
|
| 21 |
+
| GSM8K (5-shot) | 6.37 |
|
| 22 |
+
| DROP (3-shot) | 5.22 |
|