Adding Evaluation Results
#6
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -29,4 +29,17 @@ The final perplexity on the test set is `13.6`.
|
|
| 29 |
archivePrefix={arXiv},
|
| 30 |
primaryClass={cs.CL}
|
| 31 |
}
|
| 32 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
archivePrefix={arXiv},
|
| 30 |
primaryClass={cs.CL}
|
| 31 |
}
|
| 32 |
+
```
|
| 33 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 34 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ai-forever__rugpt3large_based_on_gpt2)
|
| 35 |
+
|
| 36 |
+
| Metric | Value |
|
| 37 |
+
|-----------------------|---------------------------|
|
| 38 |
+
| Avg. | 25.98 |
|
| 39 |
+
| ARC (25-shot) | 22.61 |
|
| 40 |
+
| HellaSwag (10-shot) | 32.84 |
|
| 41 |
+
| MMLU (5-shot) | 24.9 |
|
| 42 |
+
| TruthfulQA (0-shot) | 43.39 |
|
| 43 |
+
| Winogrande (5-shot) | 53.12 |
|
| 44 |
+
| GSM8K (5-shot) | 0.3 |
|
| 45 |
+
| DROP (3-shot) | 4.72 |
|