|
--- |
|
license: apache-2.0 |
|
base_model: Helsinki-NLP/opus-mt-en-vi |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: my_fine_tuning_opus_mt_en_vi_model |
|
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. --> |
|
|
|
# my_fine_tuning_opus_mt_en_vi_model |
|
|
|
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-vi](https://huggingface.co/Helsinki-NLP/opus-mt-en-vi) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3240 |
|
- Bleu: 36.0564 |
|
- Gen Len: 28.405 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len | |
|
|:-------------:|:-----:|:------:|:---------------:|:-------:|:-------:| |
|
| 0.2395 | 1.0 | 16665 | 0.3059 | 36.5417 | 28.4965 | |
|
| 0.2182 | 2.0 | 33330 | 0.3079 | 36.2686 | 28.5296 | |
|
| 0.2072 | 3.0 | 49995 | 0.3105 | 36.4146 | 28.5099 | |
|
| 0.1906 | 4.0 | 66660 | 0.3131 | 36.3594 | 28.4397 | |
|
| 0.1803 | 5.0 | 83325 | 0.3153 | 36.2658 | 28.6052 | |
|
| 0.1738 | 6.0 | 99990 | 0.3182 | 35.9334 | 28.5311 | |
|
| 0.1701 | 7.0 | 116655 | 0.3200 | 36.1934 | 28.4358 | |
|
| 0.1634 | 8.0 | 133320 | 0.3216 | 35.9721 | 28.4358 | |
|
| 0.1605 | 9.0 | 149985 | 0.3233 | 36.2007 | 28.4618 | |
|
| 0.1545 | 10.0 | 166650 | 0.3240 | 36.0564 | 28.405 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.2 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.17.0 |
|
- Tokenizers 0.15.2 |
|
|
