File size: 312 Bytes
56d19ee |
1 2 3 4 5 6 7 8 9 10 |
---
license: apache-2.0
language:
- en
---
GPT-J (with value head weights) trained on HH with PPO following @reciprocate's `trlx` example https://github.com/CarperAI/trlx/blob/2f90ba0ecd640ae18cd62adb5e934a4b779f534b/examples/hh/ppo_hh.py
Logs: https://wandb.ai/jon-tow/trlx/reports/hh-gpt-j--VmlldzozODE1NjAw
|