opus-mt-ft-v3-3-epochs
This model is a fine-tuned version of Helsinki-NLP/opus-mt-en-id on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2314
- Exact Match: 0.96
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-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Exact Match |
|---|---|---|---|---|
| 0.9771 | 1.0 | 50 | 0.3639 | 0.8925 |
| 0.3385 | 2.0 | 100 | 0.2544 | 0.935 |
| 0.2745 | 3.0 | 150 | 0.2314 | 0.96 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1