Commit
•
5551f0c
1
Parent(s):
a97ff56
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
@@ -8,4 +8,17 @@ language:
|
|
8 |
|
9 |
Pythia-70m-deduped finetuned on a cleaned version of ShareGPT data.
|
10 |
The cleaned dataset is obtained by removing duplicates and paraphrases from the original corpus, and keeping only the English instance.
|
11 |
-
The final training size is of 3507 instances.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
|
9 |
Pythia-70m-deduped finetuned on a cleaned version of ShareGPT data.
|
10 |
The cleaned dataset is obtained by removing duplicates and paraphrases from the original corpus, and keeping only the English instance.
|
11 |
+
The final training size is of 3507 instances.
|
12 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
13 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_HWERI__pythia-70m-deduped-cleansharegpt-en)
|
14 |
+
|
15 |
+
| Metric | Value |
|
16 |
+
|-----------------------|---------------------------|
|
17 |
+
| Avg. | 25.06 |
|
18 |
+
| ARC (25-shot) | 21.16 |
|
19 |
+
| HellaSwag (10-shot) | 27.16 |
|
20 |
+
| MMLU (5-shot) | 25.24 |
|
21 |
+
| TruthfulQA (0-shot) | 48.57 |
|
22 |
+
| Winogrande (5-shot) | 50.12 |
|
23 |
+
| GSM8K (5-shot) | 0.0 |
|
24 |
+
| DROP (3-shot) | 3.15 |
|