DPO Training
Collection
It contains Qwen1.5-0.5B-Chat version that has been retrained using EPFL data and ... • 5 items • Updated
Qwen1.5-0.5B-Chat with EPFL DPO fine-tuning
Qwen1.5-0.5B-Chat DPO fine-tuned on the Orca Math dataset that consists of ~200K grade school math word problems and open-ended and multiple choice questions from different EPFL courses.
Model Details
Model Description
The model was developed during the course Modern Natural Language Processing (CS-552). Its aim is to fine-tune the base model (Qwen/Qwen1.5-0.5B-Chat) to accurately answer open-ended and multiple-choice questions from Orca Math dataset and various EPFL courses.
- Developed by: Emma Lise Boehly, Ahmed Aziz Ben Haj Hmida and Jan Kokla
- Finetuned from model: Qwen/Qwen1.5-0.5B-Chat
Training Details
Training Data
HuggingFace dataset : microsoft/orca-math-word-problems-200k The EPFL dataset is not publicly available.
Training Procedure
Training Hyperparameters
Training regime: cDPO with bf16 mixed precision, $\beta=0.2$, $lr=3 \times 10^{-6}$, and $label_smoothing=0.2$
PEFT 0.10.0
- Downloads last month
- 4
Model tree for attention-avengers/Qwen1.5-0.5B-Chat-EPFL-ORCA-cDPO
Base model
Qwen/Qwen1.5-0.5B-Chat