leaderboard-pr-bot
commited on
Commit
•
c27030d
1
Parent(s):
045c847
Adding Evaluation Results
Browse filesThis is an automated PR created with https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr
The purpose of this PR is to add evaluation results from the Open LLM Leaderboard to your model card.
If you encounter any issues, please report them to https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr/discussions
README.md
CHANGED
@@ -1,3 +1,16 @@
|
|
1 |
https://wandb.ai/open-assistant/supervised-finetuning/runs/i9gmn0dt
|
2 |
|
3 |
-
Trained with residual dropout 0.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
https://wandb.ai/open-assistant/supervised-finetuning/runs/i9gmn0dt
|
2 |
|
3 |
+
Trained with residual dropout 0.1
|
4 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
5 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_dvruette__llama-13b-pretrained-dropout)
|
6 |
+
|
7 |
+
| Metric | Value |
|
8 |
+
|-----------------------|---------------------------|
|
9 |
+
| Avg. | 49.28 |
|
10 |
+
| ARC (25-shot) | 56.4 |
|
11 |
+
| HellaSwag (10-shot) | 79.34 |
|
12 |
+
| MMLU (5-shot) | 46.59 |
|
13 |
+
| TruthfulQA (0-shot) | 48.6 |
|
14 |
+
| Winogrande (5-shot) | 75.22 |
|
15 |
+
| GSM8K (5-shot) | 11.83 |
|
16 |
+
| DROP (3-shot) | 27.03 |
|