mt25-liyifinetuned-en-fi-europarl-pro
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6644
- Bleu: 15.032
- Gen Len: 60.1864
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: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|
| 0.8189 | 1.0 | 366 | 0.7625 | 12.9626 | 60.1256 |
| 0.7858 | 2.0 | 732 | 0.7341 | 13.5812 | 60.4122 |
| 0.7604 | 3.0 | 1098 | 0.7186 | 14.0319 | 59.8975 |
| 0.7188 | 4.0 | 1464 | 0.7062 | 14.2115 | 60.3374 |
| 0.7101 | 5.0 | 1830 | 0.6948 | 14.2243 | 60.577 |
| 0.6888 | 6.0 | 2196 | 0.6871 | 14.8152 | 60.7003 |
| 0.6593 | 7.0 | 2562 | 0.6797 | 14.649 | 60.1009 |
| 0.6508 | 8.0 | 2928 | 0.6745 | 14.944 | 60.5362 |
| 0.6248 | 9.0 | 3294 | 0.6702 | 14.935 | 60.3336 |
| 0.6158 | 10.0 | 3660 | 0.6644 | 15.032 | 60.1864 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.2
