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