Adding Evaluation Results
#3
by leaderboard-pr-bot - opened
README.md
CHANGED
|
@@ -47,3 +47,17 @@ The following hyperparameters were used during training:
|
|
| 47 |
- Pytorch 2.0.1+cu118
|
| 48 |
- Datasets 2.13.1
|
| 49 |
- Tokenizers 0.13.3
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
- Pytorch 2.0.1+cu118
|
| 48 |
- Datasets 2.13.1
|
| 49 |
- Tokenizers 0.13.3
|
| 50 |
+
|
| 51 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 52 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_dpv__finetuned-gpt2-tiny)
|
| 53 |
+
|
| 54 |
+
| Metric | Value |
|
| 55 |
+
|-----------------------|---------------------------|
|
| 56 |
+
| Avg. | 25.02 |
|
| 57 |
+
| ARC (25-shot) | 21.84 |
|
| 58 |
+
| HellaSwag (10-shot) | 31.6 |
|
| 59 |
+
| MMLU (5-shot) | 25.86 |
|
| 60 |
+
| TruthfulQA (0-shot) | 40.67 |
|
| 61 |
+
| Winogrande (5-shot) | 50.12 |
|
| 62 |
+
| GSM8K (5-shot) | 0.3 |
|
| 63 |
+
| DROP (3-shot) | 4.78 |
|