<!-- 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. -->
opus-mt-en-sw-finetuned-en-to-sw
This model is a fine-tuned version of Helsinki-NLP/opus-mt-en-sw on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6973
- Bleu: 58.329
- Gen Len: 17.8688
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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| No log | 1.0 | 113 | 0.8883 | 48.4933 | 20.2061 |
| No log | 2.0 | 226 | 0.7719 | 57.3125 | 18.0965 |
| No log | 3.0 | 339 | 0.7126 | 58.3384 | 17.8894 |
| No log | 4.0 | 452 | 0.6973 | 58.329 | 17.8688 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
