Adding Evaluation Results
#2
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -40,4 +40,17 @@ This model took `2:40:54` to train in LoRA on a single `A100 40gb` GPU.<br>
|
|
| 40 |
- *weight decay*: `0.001`
|
| 41 |
- *optimizer*: `paged_adamw_32bit`
|
| 42 |
- *learning rate schedule*: `cosine`
|
| 43 |
-
- *warmup ratio (linear)*: `0.03`
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
- *weight decay*: `0.001`
|
| 41 |
- *optimizer*: `paged_adamw_32bit`
|
| 42 |
- *learning rate schedule*: `cosine`
|
| 43 |
+
- *warmup ratio (linear)*: `0.03`
|
| 44 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 45 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_AtAndDev__ShortKing-3b-v0.3)
|
| 46 |
+
|
| 47 |
+
| Metric | Value |
|
| 48 |
+
|-----------------------|---------------------------|
|
| 49 |
+
| Avg. | 35.75 |
|
| 50 |
+
| ARC (25-shot) | 40.96 |
|
| 51 |
+
| HellaSwag (10-shot) | 70.72 |
|
| 52 |
+
| MMLU (5-shot) | 26.21 |
|
| 53 |
+
| TruthfulQA (0-shot) | 38.78 |
|
| 54 |
+
| Winogrande (5-shot) | 66.93 |
|
| 55 |
+
| GSM8K (5-shot) | 1.21 |
|
| 56 |
+
| DROP (3-shot) | 5.46 |
|