ke_t5_base_bongsoo_ko_en
This model is a fine-tuned version of KETI-AIR/ke-t5-base on a bongsoo/news_news_talk_en_ko dataset.
Model description
KE-T5 is a pretrained-model of t5 text-to-text transfer transformers using the Korean and English corpus developed by KETI (한국전자연구원). The vocabulary used by KE-T5 consists of 64,000 sub-word tokens and was created using Google's sentencepiece. The Sentencepiece model was trained to cover 99.95% of a 30GB corpus with an approximate 7:3 mix of Korean and English.
Intended uses & limitations
Translation from Korean to English epoch = 1
Usage
You can use this model directly with a pipeline for translation language modeling:
>>> from transformers import pipeline
>>> translator = pipeline('translation', model='chunwoolee0/ke_t5_base_bongsoo_en_ko')
>>> translator("나는 습관적으로 점심식사 후에 산책을 한다.")
[{'translation_text': 'I habitually go to walk after lunch'}]
>>> translator("이 강좌는 허깅페이스가 만든 거야.")
[{'translation_text': 'This class was created by Huggface.'}]
>>> translator("오늘은 늦게 일어났다.")
[{'translation_text': 'This day, I went late.'}]
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| No log | 1.0 | 5625 | 1.6845 | 12.2087 |
TrainOutput(global_step=5625, training_loss=2.831754861111111,
metrics={'train_runtime': 12144.6206, 'train_samples_per_second': 29.643,
'train_steps_per_second': 0.463, 'total_flos': 2.056934156746752e+16,
'train_loss': 2.831754861111111, 'epoch': 1.0})
### Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3