my_awesome_opus_books_model
This model is a fine-tuned version of t5-small on the opus_books dataset. It achieves the following results on the evaluation set:
- Loss: 1.6084
- Bleu: 5.6705
- Gen Len: 17.5512
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 |
|---|---|---|---|---|---|
| 1.8561 | 1.0 | 6355 | 1.6322 | 5.5291 | 17.5639 |
| 1.815 | 2.0 | 12710 | 1.6084 | 5.6705 | 17.5512 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.12.1
- Datasets 2.11.0
- Tokenizers 0.11.0