Adding Evaluation Results (#1)
Browse files- Adding Evaluation Results (c29c04a0e10bb8f43966ce5343922d588e6d7d90)
Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>
README.md
CHANGED
|
@@ -3,4 +3,17 @@ Open Llama 13b Finetuned using Qlora on the Guanaco dataset
|
|
| 3 |
---
|
| 4 |
datasets:
|
| 5 |
- timdettmers/openassistant-guanaco
|
| 6 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
datasets:
|
| 5 |
- timdettmers/openassistant-guanaco
|
| 6 |
+
---
|
| 7 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 8 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_titan087__OpenLlama13B-Guanaco)
|
| 9 |
+
|
| 10 |
+
| Metric | Value |
|
| 11 |
+
|-----------------------|---------------------------|
|
| 12 |
+
| Avg. | 41.32 |
|
| 13 |
+
| ARC (25-shot) | 51.19 |
|
| 14 |
+
| HellaSwag (10-shot) | 75.24 |
|
| 15 |
+
| MMLU (5-shot) | 43.76 |
|
| 16 |
+
| TruthfulQA (0-shot) | 38.4 |
|
| 17 |
+
| Winogrande (5-shot) | 71.74 |
|
| 18 |
+
| GSM8K (5-shot) | 2.96 |
|
| 19 |
+
| DROP (3-shot) | 5.96 |
|