KoBigBird-KoBart-News-Summarization
This model is a fine-tuned version of noahkim/KoBigBird-KoBart-News-Summarization on the daekeun-ml/naver-news-summarization-ko
Model description
<<20221110 Commit>>
<<KoBigBird-KoBart-News-Summarization ๋ชจ๋ธ ์ค๋ช >>
๋ค์ค๋ฌธ์์์ฝ(Multi-Document-Summarization) Task๋ฅผ ์ํด์ KoBigBird ๋ชจ๋ธ์ Encoder-Decoder๋ชจ๋ธ์ ๋ง๋ค์ด์ ํ์ต์ ์งํํ์ต๋๋ค. KoBigBird๋ฅผ Decoder๋ก ์ฐ๋ ค๊ณ ํ์ผ๋ ์ค๋ฅ๊ฐ ์๊ฒจ์ ์์ฝ์ ํนํ๋ KoBART์ Decoder๋ฅผ ํ์ฉํด์ ๋ชจ๋ธ์ ์์ฑํ์ต๋๋ค.
ํ๋ก์ ํธ์ฉ์ผ๋ก ๋ด์ค ์์ฝ ๋ชจ๋ธ ํนํ๋ ๋ชจ๋ธ์ ๋ง๋ค๊ธฐ ์ํด ๊ธฐ์กด์ ๋ง๋ค์๋ KoBigBird-KoBart-News-Summarization ๋ชจ๋ธ์ ์ถ๊ฐ์ ์ผ๋ก daekeun-ml๋์ด ์ ๊ณตํด์ฃผ์ naver-news-summarization-ko ๋ฐ์ดํฐ์ ์ผ๋ก ํ์ธํ๋ ํ์ต๋๋ค.
ํ์ฌ AI-HUB์์ ์ ๊ณตํ๋ ์์ฝ ๋ฐ์ดํฐ๋ฅผ ์ถ๊ฐ ํ์ต ์งํ ์์ ์ ๋๋ค. ์ง์์ ์ผ๋ก ๋ฐ์ ์์ผ ์ข์ ์ฑ๋ฅ์ ๋ชจ๋ธ์ ๊ตฌํํ๊ฒ ์ต๋๋ค. ๊ฐ์ฌํฉ๋๋ค.
์คํํ๊ฒฝ
- Google Colab Pro
- CPU : Intel(R) Xeon(R) CPU @ 2.20GHz
- GPU : A100-SXM4-40GB
# Python Code
from transformers import AutoTokenizer
from transformers import AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("noahkim/KoT5_news_summarization")
model = AutoModelForSeq2SeqLM.from_pretrained("noahkim/KoT5_news_summarization")
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
4.0748 | 1.0 | 1388 | 4.3067 |
3.8457 | 2.0 | 2776 | 4.2039 |
3.7459 | 3.0 | 4164 | 4.1433 |
3.6773 | 4.0 | 5552 | 4.1236 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.2
- Downloads last month
- 22