---
library_name: transformers
tags:
- unsloth
datasets:
- amityco/tau-bench-retail-train-next-action-hard-v0.2
---

![image](https://cdn-uploads.huggingface.co/production/uploads/64739bc371f07ae738d2d61d/s_3WWIvZkwxm_l-xZSi9F.png)
```
round1
│ 🏆 Average Reward: 0.3465                                                                                                                                                
│ 📈 Pass^k Metrics:                                                                                                                                                       
│ k=1: 0.346                                                                                                                                                               
│ k=2: 0.263   

round2
│ 🏆 Average Reward: 0.3246                                                                                                                                                                                                                                                                                                                        
│ 📈 Pass^k Metrics:                                                                                                                                                       
│ k=1: 0.325                                                                                                                                                               
│ k=2: 0.219
```