Adding Evaluation Results
#3
by
leaderboard-pr-bot
- opened
README.md
CHANGED
@@ -90,3 +90,17 @@ while True:
|
|
90 |
output_file.write(json.dumps(json_data) + "\n")
|
91 |
|
92 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
90 |
output_file.write(json.dumps(json_data) + "\n")
|
91 |
|
92 |
```
|
93 |
+
|
94 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
95 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_migtissera__SynthIA-7B-v1.5)
|
96 |
+
|
97 |
+
| Metric | Value |
|
98 |
+
|-----------------------|---------------------------|
|
99 |
+
| Avg. | 54.8 |
|
100 |
+
| ARC (25-shot) | 62.71 |
|
101 |
+
| HellaSwag (10-shot) | 83.37 |
|
102 |
+
| MMLU (5-shot) | 63.48 |
|
103 |
+
| TruthfulQA (0-shot) | 51.32 |
|
104 |
+
| Winogrande (5-shot) | 79.24 |
|
105 |
+
| GSM8K (5-shot) | 17.44 |
|
106 |
+
| DROP (3-shot) | 26.01 |
|