---
license: "apache-2.0"
---

*This model was trained as part of a series of experiments testing the performance of pure DPO vs SFT vs ORPO, all supported by Unsloth/Huggingface TRL.*

Note: Extremely buggy, not recommended for use.

**Benchmarks**

Average 59.63

ARC 59.47

HellaSwag 82.47

MMLU 62.31

TruthfulQA 40.11

Winogrande 78.3

GSM8K 35.1

**Training Details**

Duration: ~10-12 hours on one Kaggle T4 with Unsloth

Model: https://huggingface.co/unsloth/mistral-7b-v0.2-bnb-4bit

Dataset: https://huggingface.co/datasets/argilla/dpo-mix-7k 

Rank: 8 

Alpha: 16 

Learning rate: 5e-5

Beta: 0.1 

Batch size: 8 

Epochs: 1

Learning rate scheduler: Linear

Prompt Format: ChatML
```
<|im_start|>system
You are a helpful assistant.<|im_end|>
<|im_start|>user
Why is the sky blue?<|im_end|>
<|im_start|>assistant
```


**WanDB Reports**

![image/png](https://cdn-uploads.huggingface.co/production/uploads/65a5c0e82823ba72ed2cee7d/CIoGd-61duUAKcnlaAGR6.png)

![image/png](https://cdn-uploads.huggingface.co/production/uploads/65a5c0e82823ba72ed2cee7d/5ks-ZGg1jFNp821P2Si3S.png)

[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)