Adding Evaluation Results
#2
by leaderboard-pr-bot - opened
README.md
CHANGED
|
@@ -18,3 +18,17 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 18 |
|
| 19 |
|
| 20 |
- PEFT 0.5.0.dev0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
|
| 20 |
- PEFT 0.5.0.dev0
|
| 21 |
+
|
| 22 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 23 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Yehoon__yehoon_llama2)
|
| 24 |
+
|
| 25 |
+
| Metric | Value |
|
| 26 |
+
|-----------------------|---------------------------|
|
| 27 |
+
| Avg. | 46.49 |
|
| 28 |
+
| ARC (25-shot) | 54.78 |
|
| 29 |
+
| HellaSwag (10-shot) | 78.98 |
|
| 30 |
+
| MMLU (5-shot) | 51.29 |
|
| 31 |
+
| TruthfulQA (0-shot) | 49.17 |
|
| 32 |
+
| Winogrande (5-shot) | 74.74 |
|
| 33 |
+
| GSM8K (5-shot) | 7.28 |
|
| 34 |
+
| DROP (3-shot) | 9.16 |
|