|
|
--- |
|
|
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: [] |
|
|
--- |
|
|
|
|
|
<!-- 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-ar-finetuned-en-to-ar |
|
|
|
|
|
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-ar](https://huggingface.co/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 |
|
|
|
