---
license: apache-2.0
tags:
- trl
- dpo
- generated_from_trainer
base_model: yanolja/EEVE-Korean-Instruct-10.8B-v1.0
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# ENERGY-DRINK-LOVE/eeve_dpo-v3

### Our Team
* Jingyeom Kim
* Youjin Chung

## Model

### Base Model
* [yanolja/EEVE-Korean-Instruct-10.8B-v1.0](https://huggingface.co/yanolja/EEVE-Korean-Instruct-10.8B-v1.0)

### Hardware and Software
* Hardware: A100 * 8 for training our model
* Deepspeed library & Huggingface TRL Trainer

### Dataset
* DPO_dataset
  * 자체 제작 dpo dataset(AI-hub dataset 활용)
  * OpenOrca DPO 등 영어 데이터셋 번역(ENERGY-DRINK-LOVE/translate_share_gpt_dedup_llama_SFT_1024, 자체모델 활용)

### Training Method
* [DPO](https://arxiv.org/abs/2305.18290)

## Benchmark

**[Ko LM Eval Harness](https://github.com/Beomi/ko-lm-evaluation-harness)**
| Task             |       0-shot |       5-shot |
| :--------------- | -----------: | -----------: |
| kobest_boolq     |     0.950142 |     0.944444 |
| kobest_copa      |     0.751    |     0.835    |
| kobest_hellaswag |     0.474    |     0.508    |
| kobest_sentineg  |     0.811083 |     0.972292 |
| **Average**      | **0.74655625** | **0.81493399** |

**[Ko-LLM-Leaderboard](https://www.aihub.or.kr/leaderboard/view.do?currMenu=500&topMenu=102)**
* (240307기준 7등)
| Average | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
| ------: | -----: | -----------: | ------: | ------------: | --------------: |
|   57.97 |  57.51 |        67.01 |   56.3  |         54.86 |           54.19 |