|
--- |
|
license: cc-by-4.0 |
|
--- |
|
# **KoQuality-Polyglot-5.8b** |
|
|
|
|
|
KoQuality-Polyglot-5.8b is an auto-regressive language model that conducts instruction tuning with KoQuality datasets on Polyglot-5.8b model. |
|
|
|
### Average accuracy score of the KoBEST datasets |
|
|
|
Our best model is trained on [KoQuality dataset](https://huggingface.co/datasets/DILAB-HYU/KoQuality), which is curated by proposed method (len_group=5, k=100, method=ppl_sampling). |
|
We use KoBEST benchmark datasets(KoBEST_boolq, KoBEST_copa, KoBEST_hellaswag, KoBEST_sentineg, KoBEST_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. |
|
<img src=https://cdn-uploads.huggingface.co/production/uploads/650fecfd247f564485f8fbcf/q4cCUCzRJa3m2f7oxI_FY.png style="max-width: 500px; width: 300%"/> |
|
|
|
|
|
|
|
| Model | 0-shot | 1-shot | 2-shot | 5-shot | 10-shot |
|
| --- | --- | --- | --- | --- | --- | |
|
| koquality-polyglot-5.8b | 0.5472 | 0.5979 | 0.6260 | 0.6486 | 0.6535 |
|
| polyglot-ko-5.8b | 0.5587 | 0.5977 | 0.6138 | 0.6431 | 0.6457 |
|
| koalpcaca-polyglot-5.8b | 0.5085 | 0.5561 | 0.5768 | 0.6097 | 0.6059 |
|
| kullm-polyglot-5.8b | 0.5409 | 0.6072 | 0.5945 | 0.6345 | 0.6530 |
|
|
|
|
|
|
|
|
|
<img src=https://cdn-uploads.huggingface.co/production/uploads/650fecfd247f564485f8fbcf/7EKl1OAgKgPBFcSlGzBiW.png style="max-width: 800px; width: 400%"/> |
|
|
|
|
|
## Training hyperparameters |
|
- learning_rate: 5e-5 |
|
- train_batch_size: 4 |
|
- seed: 42 |
|
- distributed_type: multi-GPU (A100 80G) |
|
- 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 |
|
|
|
|
|
|
|
## 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={}, |
|
year = {2023}, |
|
} |
|
``` |
|
|
|
|
|
<br> |
