metadata
license: apache-2.0
base_model: Helsinki-NLP/opus-mt-en-ar
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: darija_englishV2.1
results: []
darija_englishV2.1
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: 1.7040
- Bleu: 12.742
- Gen Len: 20.3377
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: 10
- eval_batch_size: 10
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 2.5676 | 1.0 | 1594 | 2.3131 | 4.0762 | 20.1524 |
| 2.2377 | 2.0 | 3188 | 2.0278 | 6.9717 | 19.6011 |
| 2.0346 | 3.0 | 4782 | 1.8873 | 8.6742 | 20.1966 |
| 1.9014 | 4.0 | 6376 | 1.7936 | 10.9222 | 20.3141 |
| 1.8041 | 5.0 | 7970 | 1.7512 | 11.815 | 20.9877 |
| 1.7403 | 6.0 | 9564 | 1.7156 | 12.5773 | 20.6206 |
| 1.7077 | 7.0 | 11158 | 1.7040 | 12.742 | 20.3377 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1