opus-mt-de-en-finetuned-de-to-en-second
This model is a fine-tuned version of Helsinki-NLP/opus-mt-de-en on the wmt16 dataset. It achieves the following results on the evaluation set:
- Loss: 1.2282
- Bleu: 37.9762
- Gen Len: 25.3696
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| No log | 1.0 | 157 | 1.1837 | 38.8278 | 25.22 |
| No log | 2.0 | 314 | 1.2057 | 38.3047 | 25.2908 |
| No log | 3.0 | 471 | 1.2167 | 38.231 | 25.316 |
| 1.4808 | 4.0 | 628 | 1.2256 | 37.9871 | 25.3556 |
| 1.4808 | 5.0 | 785 | 1.2282 | 37.9762 | 25.3696 |
Framework versions
- Transformers 4.12.5
- Pytorch 1.10.0+cu111
- Datasets 1.16.1
- Tokenizers 0.10.3
- Downloads last month
- 8
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.