mt-lt-sv-finetuned
This model is a fine-tuned version of Helsinki-NLP/opus-mt-lt-sv on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1276
- Bleu: 43.0025
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: 5e-06
- train_batch_size: 24
- eval_batch_size: 4
- 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 |
|---|---|---|---|---|
| 1.3499 | 1.0 | 4409 | 1.2304 | 40.3211 |
| 1.2442 | 2.0 | 8818 | 1.1870 | 41.4633 |
| 1.1875 | 3.0 | 13227 | 1.1652 | 41.9164 |
| 1.1386 | 4.0 | 17636 | 1.1523 | 42.3534 |
| 1.0949 | 5.0 | 22045 | 1.1423 | 42.6339 |
| 1.0739 | 6.0 | 26454 | 1.1373 | 42.7617 |
| 1.0402 | 7.0 | 30863 | 1.1324 | 42.8568 |
| 1.0369 | 8.0 | 35272 | 1.1298 | 42.9608 |
| 1.0138 | 9.0 | 39681 | 1.1281 | 42.9833 |
| 1.0192 | 10.0 | 44090 | 1.1276 | 43.0025 |
Framework versions
- Transformers 4.25.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.6.1
- Tokenizers 0.13.1