Adding Evaluation Results
#2
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -8,4 +8,17 @@ Prompt example:
|
|
| 8 |
### Instruction:
|
| 9 |
How do you fine tune a large language model?
|
| 10 |
### Response:
|
| 11 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
### Instruction:
|
| 9 |
How do you fine tune a large language model?
|
| 10 |
### Response:
|
| 11 |
+
```
|
| 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_KnutJaegersberg__megatron-gpt2-345m-evol_instruct_v2)
|
| 14 |
+
|
| 15 |
+
| Metric | Value |
|
| 16 |
+
|-----------------------|---------------------------|
|
| 17 |
+
| Avg. | 26.63 |
|
| 18 |
+
| ARC (25-shot) | 26.37 |
|
| 19 |
+
| HellaSwag (10-shot) | 38.39 |
|
| 20 |
+
| MMLU (5-shot) | 23.6 |
|
| 21 |
+
| TruthfulQA (0-shot) | 41.19 |
|
| 22 |
+
| Winogrande (5-shot) | 52.33 |
|
| 23 |
+
| GSM8K (5-shot) | 0.0 |
|
| 24 |
+
| DROP (3-shot) | 4.54 |
|