|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: Helsinki-NLP/opus-mt-en-ar |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: English-To-EgyptianArabic-Translator |
|
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. --> |
|
|
|
# English-To-EgyptianArabic-Translator |
|
|
|
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: 1.8722 |
|
|
|
## 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: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
- lr_scheduler_type: linear |
|
- num_epochs: 20 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 1.5425 | 1.0 | 4701 | 1.9165 | |
|
| 1.4814 | 2.0 | 9402 | 1.8411 | |
|
| 1.3308 | 3.0 | 14103 | 1.8098 | |
|
| 1.2401 | 4.0 | 18804 | 1.7975 | |
|
| 1.1253 | 5.0 | 23505 | 1.7835 | |
|
| 1.02 | 6.0 | 28206 | 1.7948 | |
|
| 0.9592 | 7.0 | 32907 | 1.8001 | |
|
| 0.8913 | 8.0 | 37608 | 1.8011 | |
|
| 0.808 | 9.0 | 42309 | 1.8004 | |
|
| 0.7824 | 10.0 | 47010 | 1.8144 | |
|
| 0.7382 | 11.0 | 51711 | 1.8230 | |
|
| 0.6639 | 12.0 | 56412 | 1.8272 | |
|
| 0.6307 | 13.0 | 61113 | 1.8363 | |
|
| 0.6096 | 14.0 | 65814 | 1.8416 | |
|
| 0.5885 | 15.0 | 70515 | 1.8533 | |
|
| 0.549 | 16.0 | 75216 | 1.8609 | |
|
| 0.5113 | 17.0 | 79917 | 1.8633 | |
|
| 0.5041 | 18.0 | 84618 | 1.8700 | |
|
| 0.4829 | 19.0 | 89319 | 1.8681 | |
|
| 0.4847 | 20.0 | 94020 | 1.8722 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.46.3 |
|
- Pytorch 2.1.1+cu121 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.20.3 |
|
|
