YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
Process Reward Model trained by OpenRLHF
- Dataset: Math-Shepherd (https://huggingface.co/datasets/peiyi9979/Math-Shepherd)
- Learning Rate: 1e-6
- Training Accuracy: 0.922
- Downloads last month
- 222