metadata
license: apache-2.0
base_model: Helsinki-NLP/opus-mt-en-ar
tags:
- generated_from_trainer
model-index:
- name: English-To-EgyptianArabic-Translator
results: []
English-To-EgyptianArabic-Translator
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: 2.3011
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: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.9907 | 1.0 | 2396 | 2.7717 |
| 2.6732 | 2.0 | 4792 | 2.5879 |
| 2.4873 | 3.0 | 7188 | 2.5003 |
| 2.2897 | 4.0 | 9584 | 2.4407 |
| 2.2402 | 5.0 | 11980 | 2.4038 |
| 2.1045 | 6.0 | 14376 | 2.3795 |
| 2.032 | 7.0 | 16772 | 2.3621 |
| 1.9792 | 8.0 | 19168 | 2.3410 |
| 1.9129 | 9.0 | 21564 | 2.3319 |
| 1.8975 | 10.0 | 23960 | 2.3192 |
| 1.8107 | 11.0 | 26356 | 2.3170 |
| 1.7901 | 12.0 | 28752 | 2.3128 |
| 1.7654 | 13.0 | 31148 | 2.3061 |
| 1.6899 | 14.0 | 33544 | 2.3042 |
| 1.6535 | 15.0 | 35940 | 2.3061 |
| 1.6733 | 16.0 | 38336 | 2.3027 |
| 1.6643 | 17.0 | 40732 | 2.3029 |
| 1.6471 | 18.0 | 43128 | 2.2996 |
| 1.6138 | 19.0 | 45524 | 2.3013 |
| 1.5878 | 20.0 | 47920 | 2.3011 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu121
- Datasets 2.14.5
- Tokenizers 0.15.1