|
|
--- |
|
|
tags: |
|
|
- translation |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- bleu |
|
|
model-index: |
|
|
- name: VietAI-NLP-ITN |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# VietAI-NLP-ITN |
|
|
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.4378 |
|
|
- Bleu: 81.8571 |
|
|
|
|
|
## Model description |
|
|
|
|
|
More information needed |
|
|
|
|
|
## Intended uses & limitations |
|
|
|
|
|
More information needed |
|
|
|
|
|
## Training and evaluation data |
|
|
|
|
|
More information needed |
|
|
|
|
|
## Training procedure |
|
|
|
|
|
### Training hyperparameters |
|
|
|
|
|
The following hyperparameters were used during training: |
|
|
- learning_rate: 5e-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 |
|
|
- lr_scheduler_warmup_ratio: 0.2 |
|
|
- num_epochs: 5 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | |
|
|
|:-------------:|:-----:|:------:|:---------------:|:-------:| |
|
|
| 0.6529 | 1.0 | 31250 | 0.5660 | 78.7315 | |
|
|
| 0.5125 | 2.0 | 62500 | 0.4770 | 81.3979 | |
|
|
| 0.4798 | 3.0 | 93750 | 0.4554 | 81.6720 | |
|
|
| 0.4568 | 4.0 | 125000 | 0.4435 | 81.7753 | |
|
|
| 0.4387 | 5.0 | 156250 | 0.4378 | 81.8571 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.20.1 |
|
|
- Pytorch 1.10.1+cu113 |
|
|
- Datasets 2.4.0 |
|
|
- Tokenizers 0.12.1 |
|
|
|
