metadata
base_model: Shekswess/tiny-think-sft-math-stem-loss-nll-bf16-lr2e-5-e2-bs8
library_name: transformers
model_name: tiny-think-dpo-math-stem-apo_zero-beta1-lr3e-6-e1-bs8
tags:
- generated_from_trainer
- dpo
- trl
licence: license
Model Card for tiny-think-dpo-math-stem-apo_zero-beta1-lr3e-6-e1-bs8
This model is a fine-tuned version of Shekswess/tiny-think-sft-math-stem-loss-nll-bf16-lr2e-5-e2-bs8. It has been trained using TRL.
Training procedure
This model was trained with DPO, a method introduced in Direct Preference Optimization: Your Language Model is Secretly a Reward Model.
Framework versions
- TRL: 0.26.2
- Transformers: 4.57.5
- Pytorch: 2.9.0+cu128
- Datasets: 4.5.0
- Tokenizers: 0.22.2