Adding Evaluation Results
#2
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -45,3 +45,17 @@ The following hyperparameters were used during training:
|
|
| 45 |
- Pytorch 2.0.0+cu117
|
| 46 |
- Datasets 2.10.1
|
| 47 |
- Tokenizers 0.13.2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
- Pytorch 2.0.0+cu117
|
| 46 |
- Datasets 2.10.1
|
| 47 |
- Tokenizers 0.13.2
|
| 48 |
+
|
| 49 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 50 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_beomi__KoAlpaca-Polyglot-5.8B)
|
| 51 |
+
|
| 52 |
+
| Metric | Value |
|
| 53 |
+
|-----------------------|---------------------------|
|
| 54 |
+
| Avg. | 26.03 |
|
| 55 |
+
| ARC (25-shot) | 27.65 |
|
| 56 |
+
| HellaSwag (10-shot) | 35.58 |
|
| 57 |
+
| MMLU (5-shot) | 24.72 |
|
| 58 |
+
| TruthfulQA (0-shot) | 39.74 |
|
| 59 |
+
| Winogrande (5-shot) | 49.01 |
|
| 60 |
+
| GSM8K (5-shot) | 0.08 |
|
| 61 |
+
| DROP (3-shot) | 5.41 |
|