Adding Evaluation Results
#1
by
leaderboard-pr-bot
- opened
README.md
CHANGED
@@ -87,3 +87,17 @@ python finetune.py \
|
|
87 |
--group_by_length \
|
88 |
--resume_from_checkpoint 'tloen/alpaca-lora-7b'
|
89 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
87 |
--group_by_length \
|
88 |
--resume_from_checkpoint 'tloen/alpaca-lora-7b'
|
89 |
```
|
90 |
+
|
91 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
92 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_TheBloke__Planner-7B-fp16)
|
93 |
+
|
94 |
+
| Metric | Value |
|
95 |
+
|-----------------------|---------------------------|
|
96 |
+
| Avg. | 39.93 |
|
97 |
+
| ARC (25-shot) | 51.02 |
|
98 |
+
| HellaSwag (10-shot) | 77.82 |
|
99 |
+
| MMLU (5-shot) | 35.71 |
|
100 |
+
| TruthfulQA (0-shot) | 34.33 |
|
101 |
+
| Winogrande (5-shot) | 71.43 |
|
102 |
+
| GSM8K (5-shot) | 3.56 |
|
103 |
+
| DROP (3-shot) | 5.62 |
|