Training Summary

Epoch	Step	Training Loss	Validation Loss
0.25	60	—	0.5437
0.50	120	1.4992	0.4638
0.75	180	—	0.4528
1.00	240	0.4536	0.4468
1.25	300	—	0.4418
1.50	360	0.4405	0.4385
1.75	420	—	0.4360
2.00	480	0.4350	0.4335

Model Card for r32

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1. It has been trained using TRL.

Quick start

from transformers import pipeline

question = "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?"
generator = pipeline("text-generation", model="a-ord19/r32", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

This model was trained with SFT.

Framework versions

• TRL: 0.24.0
• Transformers: 4.57.1
• Pytorch: 2.8.0+cu126
• Datasets: 4.0.0
• Tokenizers: 0.22.1

Citations

Cite TRL as:

@misc{vonwerra2022trl,
    title        = {{TRL: Transformer Reinforcement Learning}},
    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},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}