<!-- 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. -->
En-Af_update
This model is a fine-tuned version of Helsinki-NLP/opus-mt-en-af on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.8089
- Bleu: 45.1780
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: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu |
|---|---|---|---|---|
| 1.4243 | 1.0 | 2553 | 1.8451 | 42.1314 |
| 1.0987 | 2.0 | 5106 | 1.7509 | 44.0714 |
| 0.9329 | 3.0 | 7659 | 1.7340 | 44.6003 |
| 0.8365 | 4.0 | 10212 | 1.7260 | 44.7820 |
| 0.7556 | 5.0 | 12765 | 1.7590 | 45.1180 |
| 0.6944 | 6.0 | 15318 | 1.7715 | 45.1451 |
| 0.652 | 7.0 | 17871 | 1.7696 | 45.1025 |
| 0.6132 | 8.0 | 20424 | 1.8060 | 45.1781 |
| 0.5832 | 9.0 | 22977 | 1.8135 | 45.2485 |
| 0.5602 | 10.0 | 25530 | 1.8089 | 45.1730 |
Framework versions
- Transformers 4.21.0
- Pytorch 1.12.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1
