Adding Evaluation Results
#2
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -81,3 +81,17 @@ Current upload: checkpoint of step 1200 in training.
|
|
| 81 |
**ptb-new:** Coming soon...
|
| 82 |
|
| 83 |
**c4-new:** Coming soon...
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 81 |
**ptb-new:** Coming soon...
|
| 82 |
|
| 83 |
**c4-new:** Coming soon...
|
| 84 |
+
|
| 85 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 86 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_TheBloke__VicUnlocked-alpaca-65B-QLoRA-fp16)
|
| 87 |
+
|
| 88 |
+
| Metric | Value |
|
| 89 |
+
|-----------------------|---------------------------|
|
| 90 |
+
| Avg. | 54.74 |
|
| 91 |
+
| ARC (25-shot) | 65.61 |
|
| 92 |
+
| HellaSwag (10-shot) | 85.15 |
|
| 93 |
+
| MMLU (5-shot) | 63.13 |
|
| 94 |
+
| TruthfulQA (0-shot) | 52.47 |
|
| 95 |
+
| Winogrande (5-shot) | 81.29 |
|
| 96 |
+
| GSM8K (5-shot) | 27.82 |
|
| 97 |
+
| DROP (3-shot) | 7.71 |
|