Views
No views yet
| Epoch | Training Loss | Validation Loss | Entropy | Num Tokens | Mean Token Accuracy |
|---|---|---|---|---|---|
| 1 | 0.980400 | 0.819349 | 0.865937 | 3,542,223 | 0.784942 |
| 2 | 0.828100 | 0.798671 | 0.802326 | 7,084,446 | 0.789714 |
| 3 | 0.684600 | 0.799747 | 0.780815 | 10,626,669 | 0.790085 |
1from transformers import pipeline
2
3question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
4generator = pipeline("text-generation", model="jorvasquezr/results_r4", device="cuda")
5output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
6print(output["generated_text"])1@misc{vonwerra2022trl,
2 title = {{TRL: Transformer Reinforcement Learning}},
3 author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
4 year = 2020,
5 journal = {GitHub repository},
6 publisher = {GitHub},
7 howpublished = {\url{https://github.com/huggingface/trl}}
8}