Commit
•
b150e59
1
Parent(s):
a97ff56
Adding Evaluation Results (#1)
Browse files- Adding Evaluation Results (5551f0c282f175abcf141d8e4c11c8c934621ce2)
Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>
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 |
|