File size: 345 Bytes
595c2d5
 
caf78aa
 
595c2d5
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
The Llama3-8b-based Reward Model was trained using OpenRLHF and a combination of datasets available at https://huggingface.co/datasets/OpenLLMAI/preference_dataset_mixture2_and_safe_pku.

Base model: https://huggingface.co/OpenRLHF/Llama-3-8b-sft-mixture

```
Cosine Scheduler
Learning Rate: 9e-6
Warmup Ratio: 0.03
Batch Size: 256
Epoch: 1
```