metadata
license: apache-2.0
base_model: Helsinki-NLP/opus-mt-en-ar
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: opus-mt-en-ar-finetuned-en-to-ar
results: []
opus-mt-en-ar-finetuned-en-to-ar
This model is a fine-tuned version of Helsinki-NLP/opus-mt-en-ar on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.6900
- Bleu: 16.0561
- Gen Len: 17.5458
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: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 1.7613 | 1.0 | 2381 | 2.3308 | 15.763 | 21.341 |
| 1.6561 | 2.0 | 4762 | 2.3460 | 15.8584 | 18.3615 |
| 1.5261 | 3.0 | 7143 | 2.3583 | 15.9146 | 18.3606 |
| 1.4501 | 4.0 | 9524 | 2.3798 | 16.1441 | 17.475 |
| 1.3497 | 5.0 | 11905 | 2.4023 | 16.2252 | 17.4995 |
| 1.4105 | 6.0 | 14286 | 2.3787 | 16.0959 | 17.9816 |
| 1.3328 | 7.0 | 16667 | 2.3917 | 16.1331 | 17.6262 |
| 1.2937 | 8.0 | 19048 | 2.4080 | 16.3078 | 17.4534 |
| 1.2121 | 9.0 | 21429 | 2.4251 | 16.2201 | 17.6992 |
| 1.1539 | 10.0 | 23810 | 2.4435 | 16.3003 | 17.5033 |
| 1.1082 | 11.0 | 26191 | 2.4623 | 16.1261 | 17.5324 |
| 1.0687 | 12.0 | 28572 | 2.4776 | 16.2769 | 17.4889 |
| 1.0148 | 13.0 | 30953 | 2.5003 | 16.2253 | 17.482 |
| 0.9665 | 14.0 | 33334 | 2.5121 | 15.9708 | 17.7131 |
| 0.9399 | 15.0 | 35715 | 2.5320 | 16.1663 | 17.552 |
| 0.9002 | 16.0 | 38096 | 2.5455 | 16.0954 | 17.4487 |
| 0.8696 | 17.0 | 40477 | 2.5698 | 16.1255 | 17.4858 |
| 0.8382 | 18.0 | 42858 | 2.5831 | 16.0722 | 17.3738 |
| 0.8133 | 19.0 | 45239 | 2.6000 | 15.9531 | 17.6652 |
| 0.7738 | 20.0 | 47620 | 2.6132 | 16.077 | 17.5936 |
| 0.7624 | 21.0 | 50001 | 2.6288 | 16.0965 | 17.5484 |
| 0.7395 | 22.0 | 52382 | 2.6402 | 16.044 | 17.5031 |
| 0.7106 | 23.0 | 54763 | 2.6560 | 15.8598 | 17.5839 |
| 0.7001 | 24.0 | 57144 | 2.6605 | 15.9754 | 17.5711 |
| 0.6812 | 25.0 | 59525 | 2.6685 | 15.9742 | 17.526 |
| 0.6665 | 26.0 | 61906 | 2.6781 | 16.0116 | 17.4887 |
| 0.6594 | 27.0 | 64287 | 2.6834 | 15.9705 | 17.5014 |
| 0.6513 | 28.0 | 66668 | 2.6870 | 15.9401 | 17.5768 |
| 0.6329 | 29.0 | 69049 | 2.6893 | 16.0272 | 17.5373 |
| 0.6266 | 30.0 | 71430 | 2.6900 | 16.0561 | 17.5458 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.14.1