finetuned_HelsinkiNLP-opus-mt-vi-en_PhoMT
This model is a fine-tuned version of Helsinki-NLP/opus-mt-vi-en on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1783
- Bleu: 37.7741
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu |
|---|---|---|---|---|
| 1.3717 | 1.0 | 186125 | 1.2371 | 35.8549 |
| 1.2926 | 2.0 | 372250 | 1.2113 | 36.7328 |
| 1.2505 | 3.0 | 558375 | 1.1954 | 37.0998 |
| 1.2025 | 4.0 | 744500 | 1.1847 | 37.5538 |
| 1.1853 | 5.0 | 930625 | 1.1783 | 37.7761 |
Framework versions
- Transformers 4.22.1
- Pytorch 1.10.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1
- Downloads last month
- 7
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.