VN_ja_to_en
This model is a fine-tuned version of Helsinki-NLP/opus-mt-ja-en on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.0411
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: 64
- eval_batch_size: 64
- 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 |
---|---|---|---|
2.0489 | 1.0 | 10276 | 2.0716 |
1.9028 | 2.0 | 20552 | 2.0646 |
1.812 | 3.0 | 30828 | 2.0525 |
1.7531 | 4.0 | 41104 | 2.0487 |
1.7083 | 5.0 | 51380 | 2.0375 |
1.6717 | 6.0 | 61656 | 2.0415 |
1.6354 | 7.0 | 71932 | 2.0398 |
1.6146 | 8.0 | 82208 | 2.0390 |
1.5972 | 9.0 | 92484 | 2.0391 |
1.582 | 10.0 | 102760 | 2.0411 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1
- Downloads last month
- 5