<!-- 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. -->
opus-mt-ru-en-finetuned-ru-to-en
This model is a fine-tuned version of Helsinki-NLP/opus-mt-ru-en on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0396
- Bleu*100: 69.5571
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: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu*100 |
|---|---|---|---|---|
| 1.5253 | 1.0 | 625 | 1.1806 | 67.3919 |
| 1.2178 | 2.0 | 1250 | 1.0974 | 68.7640 |
| 1.1185 | 3.0 | 1875 | 1.0611 | 69.4906 |
| 1.025 | 4.0 | 2500 | 1.0437 | 69.3828 |
| 0.9981 | 5.0 | 3125 | 1.0396 | 69.5571 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
