KoQuality-Polyglot-5.8b is a fine-tuned iteration of the EleutherAI/polyglot-ko-5.8b model, specifically trained on the KoQuality dataset. Notably, when excluding models employing COT datasets, KoQuality-Polyglot-5.8b exhibits exceptional performance in same size models, even though it operates with a relatively small dataset.
Open Ko-LLM LeaderBoard
Our approach centers around leveraging high-quality instruction datasets to deepen our understanding of commands, all the while preserving the performance of the Pre-trained Language Model (PLM). Compared to alternative models, we have achieved this with minimal learning, utilizing only 1% of the dataset, which equates to 4006 instructions.
Overall Average accuracy score of the KoBEST datasets
We use KoBEST benchmark datasets(BoolQ, COPA, HellaSwag, SentiNeg, WiC) to compare the performance of our best model and other models accuracy. Our model outperforms other models in the average accuracy score of the KoBEST datasets.
Model
0-shot
1-shot
2-shot
5-shot
10-shot
polyglot-ko-5.8b
0.4734
0.5929
0.6120
0.6388
0.6295
koalpcaca-polyglot-5.8b
0.4731
0.5284
0.5721
0.6054
0.6042
kullm-polyglot-5.8b
0.4415
0.6030
0.5849
0.6252
0.6451
koquality-polyglot-5.8b
0.4530
0.6050
0.6351
0.6420
0.6457
Evaluation results
COPA (F1)
BoolQ (F1)
HellaSwag (F1)
SentiNeg (F1)
WiC (F1)
Training hyperparameters
learning_rate: 5e-5
train_batch_size: 4
seed: 42
distributed_type: multi-GPU (A100 80G) + No offloading
num_devices: 4
gradient_accumulation_steps: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 2.0
Framework versions
Transformers 4.30.2
Pytorch 2.0.1+cu117
Datasets 2.11.0
deepspeed 0.9.5
Citation
@misc{2023koqaulity,
title = {KoQuality: Curation of High-quality Instruction Data for Korean Language Models},
author = {Na, Yohan and Kim, Dahye and Chae, Dong-Kyu},
journal={Proceedings of the 35th Annual Conference on Human and Cognitive Language Technology (HCLT 2023)},
pages={306-311},
year = {2023},
}
