Adding Evaluation Results
#1
by
leaderboard-pr-bot
- opened
README.md
CHANGED
@@ -215,4 +215,17 @@ The following hyperparameters were used during training:
|
|
215 |
|
216 |
# Developer
|
217 |
|
218 |
-
Peter Devine - ([ptrdvn](https://huggingface.co/ptrdvn))
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
215 |
|
216 |
# Developer
|
217 |
|
218 |
+
Peter Devine - ([ptrdvn](https://huggingface.co/ptrdvn))
|
219 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
|
220 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_lightblue__suzume-llama-3-8B-multilingual-orpo-borda-top25)
|
221 |
+
|
222 |
+
| Metric |Value|
|
223 |
+
|-------------------|----:|
|
224 |
+
|Avg. |23.37|
|
225 |
+
|IFEval (0-Shot) |66.37|
|
226 |
+
|BBH (3-Shot) |27.67|
|
227 |
+
|MATH Lvl 5 (4-Shot)| 8.53|
|
228 |
+
|GPQA (0-shot) | 3.02|
|
229 |
+
|MuSR (0-shot) | 4.81|
|
230 |
+
|MMLU-PRO (5-shot) |29.83|
|
231 |
+
|