metadata
license: apache-2.0
datasets:
- abacusai/MetaMathFewshot
DPO finetune of our MetaMath SFT Model on the Truthy DPO dataset
Evaluation Results
| Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
|---|---|---|---|---|---|---|
| TBD | 69.20 | 84.34 | TBD | 67.58 | 82.87 | 72.78 |