my_awesome_opus_books_model_mt
This model is a fine-tuned version of Helsinki-NLP/opus-mt-en-es on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8843
- Bleu: 22.2499
- Gen Len: 31.3084
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: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 2.1926 | 1.0 | 585 | 2.0059 | 17.9798 | 36.7939 |
| 2.0506 | 2.0 | 1170 | 1.9572 | 19.9999 | 32.9219 |
| 1.9785 | 3.0 | 1755 | 1.9328 | 21.0365 | 32.0459 |
| 1.9221 | 4.0 | 2340 | 1.9144 | 21.1344 | 32.2097 |
| 1.8739 | 5.0 | 2925 | 1.9031 | 21.8742 | 31.5956 |
| 1.8114 | 6.0 | 3510 | 1.8945 | 21.521 | 32.1927 |
| 1.7861 | 7.0 | 4095 | 1.8905 | 22.0321 | 31.5412 |
| 1.7666 | 8.0 | 4680 | 1.8860 | 22.3035 | 31.2898 |
| 1.7541 | 9.0 | 5265 | 1.8856 | 22.2564 | 31.2552 |
| 1.7438 | 10.0 | 5850 | 1.8843 | 22.2499 | 31.3084 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.7.1+cu126
- Datasets 3.6.0
- Tokenizers 0.21.1
- Downloads last month
- 5
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for MrCharli03/my_awesome_opus_books_model_mt
Base model
Helsinki-NLP/opus-mt-en-es