Adding Evaluation Results
#1
by
leaderboard-pr-bot - opened
README.md
CHANGED
|
@@ -5,4 +5,17 @@ This is a LORA model, trained on PuffedLIMASub4000 for 4 epochs, BS1.
|
|
| 5 |
|
| 6 |
Base model is LLAMA-2-13b-HF
|
| 7 |
|
| 8 |
-
This model acts as a test for ConvoEvol.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
|
| 6 |
Base model is LLAMA-2-13b-HF
|
| 7 |
|
| 8 |
+
This model acts as a test for ConvoEvol.
|
| 9 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 10 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_NobodyExistsOnTheInternet__PuffedLIMA13bQLORA)
|
| 11 |
+
|
| 12 |
+
| Metric | Value |
|
| 13 |
+
|-----------------------|---------------------------|
|
| 14 |
+
| Avg. | 47.14 |
|
| 15 |
+
| ARC (25-shot) | 59.9 |
|
| 16 |
+
| HellaSwag (10-shot) | 84.39 |
|
| 17 |
+
| MMLU (5-shot) | 53.68 |
|
| 18 |
+
| TruthfulQA (0-shot) | 39.9 |
|
| 19 |
+
| Winogrande (5-shot) | 75.22 |
|
| 20 |
+
| GSM8K (5-shot) | 8.72 |
|
| 21 |
+
| DROP (3-shot) | 8.21 |
|