Commit
·
9efec69
1
Parent(s):
1298ae5
Adding Evaluation Results (#2)
Browse files- Adding Evaluation Results (bdb9a09a6da1f17bb0ae66ea8d8aace82a7d53f5)
Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>
README.md
CHANGED
|
@@ -19,4 +19,17 @@ Trained on 3 epochs of the `totally-not-an-llm/EverythingLM-data-V2-sharegpt` da
|
|
| 19 |
|
| 20 |
note: Changed a few of the finetuning parameters this time around. I have no idea if its any good but Feel free to give it a try!
|
| 21 |
|
| 22 |
-
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
note: Changed a few of the finetuning parameters this time around. I have no idea if its any good but Feel free to give it a try!
|
| 21 |
|
| 22 |
+
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
| 23 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 24 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_harborwater__open-llama-3b-everything-v2)
|
| 25 |
+
|
| 26 |
+
| Metric | Value |
|
| 27 |
+
|-----------------------|---------------------------|
|
| 28 |
+
| Avg. | 36.29 |
|
| 29 |
+
| ARC (25-shot) | 42.83 |
|
| 30 |
+
| HellaSwag (10-shot) | 73.28 |
|
| 31 |
+
| MMLU (5-shot) | 26.87 |
|
| 32 |
+
| TruthfulQA (0-shot) | 37.26 |
|
| 33 |
+
| Winogrande (5-shot) | 66.61 |
|
| 34 |
+
| GSM8K (5-shot) | 1.59 |
|
| 35 |
+
| DROP (3-shot) | 5.61 |
|