opus-mt-id-en-ccmatrix-v2
This model was trained from scratch on the ccmatrix dataset. It achieves the following results on the evaluation set:
- Loss: 0.7667
- Bleu: 52.173
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 4000
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu |
|---|---|---|---|---|
| 0.803 | 1.0 | 148438 | 0.8185 | 50.3216 |
| 0.7212 | 2.0 | 296876 | 0.7904 | 51.282 |
| 0.6913 | 3.0 | 445314 | 0.7791 | 51.7806 |
| 0.6727 | 4.0 | 593752 | 0.7691 | 52.0263 |
| 0.6609 | 5.0 | 742190 | 0.7667 | 52.173 |
Framework versions
- Transformers 4.26.1
- Pytorch 2.0.0
- Datasets 2.10.1
- Tokenizers 0.11.0