T5-small-finetuned-en-to-de-accelerate translator
This model is a fine-tuned version of t5-small on the kde4 dataset. It achieves the following results on the evaluation set:
- SacreBELU : 41.46
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Accelerate
Training hyperparameters
The following hyperparameters were used during training:
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: AdamW with lr=5e-5
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Validation Loss | BLEU score |
|---|---|---|---|
| 1.5908938944803344 | 1.0 | 1.2350984811782837 | 39.82 |
| 1.3603184403975805 | 2.0 | 1.1676584482192993 | 41.05 |
| 1.3098205064204005 | 3.0 | 1.1546192169189453 | 41.46 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3