byt5-small-wikipron-eng-latn-uk-broad
This model is a fine-tuned version of google/byt5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1572
- Per: 0.2426
- Gen Len: 15.8324
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: 0.0002
- train_batch_size: 128
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Per | Gen Len |
|---|---|---|---|---|---|
| 1.8915 | 1.0 | 393 | 0.2827 | 0.3507 | 15.8408 |
| 0.2887 | 2.0 | 786 | 0.2034 | 0.2885 | 15.8807 |
| 0.2216 | 3.0 | 1179 | 0.1804 | 0.263 | 15.8084 |
| 0.1934 | 4.0 | 1572 | 0.1683 | 0.2543 | 15.8182 |
| 0.1772 | 5.0 | 1965 | 0.1663 | 0.2499 | 15.8002 |
| 0.1656 | 6.0 | 2358 | 0.1605 | 0.2475 | 15.7992 |
| 0.1566 | 7.0 | 2751 | 0.1588 | 0.2457 | 15.8289 |
| 0.1509 | 8.0 | 3144 | 0.1579 | 0.2427 | 15.8337 |
| 0.1459 | 9.0 | 3537 | 0.1562 | 0.243 | 15.8391 |
| 0.1424 | 10.0 | 3930 | 0.1572 | 0.2426 | 15.8324 |
Framework versions
- Transformers 4.28.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.9.0
- Tokenizers 0.13.2