|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- mt_eng_vietnamese |
|
language: |
|
- en |
|
- vi |
|
tags: |
|
- translation |
|
- t5 |
|
- en-vi |
|
- vi-en |
|
--- |
|
# gozu888/Envit5-tuned |
|
|
|
This model is a fine-tuned version of VietAI/envit5-translation on the mt_eng_vietnamese dataset. It achieves the following results on the evaluation set: |
|
|
|
- Loss: 0.1988 |
|
|
|
## Model Details |
|
|
|
### Model Description |
|
|
|
<!-- Provide a longer summary of what this model is. --> |
|
|
|
- **Developed by:** gozu888 |
|
- **Model type:** T5 |
|
- **Finetuned from model [optional]:** [VietAI/envit5-translation](https://huggingface.co/VietAI/envit5-translation) |
|
|
|
### Hyperparameters |
|
The following hyperparameters were used during training: |
|
- Repo: [simpleT5](https://github.com/Shivanandroy/simpleT5) |
|
- Dataset: [mt_eng_vietnamese](https://huggingface.co/datasets/mt_eng_vietnamese) + custom (~40%) |
|
```python |
|
model.train( |
|
train_df=train_df, |
|
eval_df=test_df, |
|
source_max_token_len=128, |
|
target_max_token_len=128, |
|
batch_size=32, |
|
max_epochs=15, |
|
use_gpu=True, |
|
save_only_last_epoch=True, |
|
precision=16, |
|
dataloader_num_workers=4 |
|
) |
|
``` |
