en-to-es-trans-with-bart
This model is a fine-tuned version of facebook/bart-base on the opus_books dataset. It achieves the following results on the evaluation set:
- Loss: 2.0355
- Bleu: 2.1888
- Gen Len: 18.6278
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 2.4648 | 1.0 | 4674 | 2.1509 | 1.937 | 18.6399 |
| 2.2417 | 2.0 | 9348 | 2.0355 | 2.1888 | 18.6278 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0