Adding Evaluation Results
#7
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -67,3 +67,17 @@ pythia-12b-sft-8:
|
|
| 67 |
fraction: 0.5
|
| 68 |
val_split: 0.025
|
| 69 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
fraction: 0.5
|
| 68 |
val_split: 0.025
|
| 69 |
```
|
| 70 |
+
|
| 71 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 72 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_OpenAssistant__pythia-12b-sft-v8-7k-steps)
|
| 73 |
+
|
| 74 |
+
| Metric | Value |
|
| 75 |
+
|-----------------------|---------------------------|
|
| 76 |
+
| Avg. | 36.87 |
|
| 77 |
+
| ARC (25-shot) | 44.03 |
|
| 78 |
+
| HellaSwag (10-shot) | 70.28 |
|
| 79 |
+
| MMLU (5-shot) | 26.55 |
|
| 80 |
+
| TruthfulQA (0-shot) | 36.53 |
|
| 81 |
+
| Winogrande (5-shot) | 65.27 |
|
| 82 |
+
| GSM8K (5-shot) | 10.61 |
|
| 83 |
+
| DROP (3-shot) | 4.84 |
|