<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
TranslationDe2En
This model was trained from scratch on the wmt16 dataset. It achieves the following results on the evaluation set:
- Loss: 2.0338
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.8864 | 1.0 | 391 | 2.1916 |
| 2.7248 | 2.0 | 782 | 2.1310 |
| 2.6707 | 3.0 | 1173 | 2.0956 |
| 2.6382 | 4.0 | 1564 | 2.0747 |
| 2.6145 | 5.0 | 1955 | 2.0613 |
| 2.5978 | 6.0 | 2346 | 2.0500 |
| 2.5846 | 7.0 | 2737 | 2.0424 |
| 2.575 | 8.0 | 3128 | 2.0376 |
| 2.5694 | 9.0 | 3519 | 2.0349 |
| 2.5673 | 10.0 | 3910 | 2.0338 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu117
- Datasets 2.10.1
- Tokenizers 0.13.2
