metadata
license: apache-2.0
base_model: Helsinki-NLP/opus-mt-ar-en
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: darija-latin-to-english-new
results: []
darija-latin-to-english-new
This model is a fine-tuned version of Helsinki-NLP/opus-mt-ar-en on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0525
- Bleu: 29.8636
- Gen Len: 8.8467
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| No log | 0.36 | 100 | 0.0530 | 29.1142 | 8.8582 |
| No log | 0.71 | 200 | 0.0530 | 28.9361 | 9.0068 |
| No log | 1.07 | 300 | 0.0528 | 29.0076 | 8.6585 |
| No log | 1.43 | 400 | 0.0531 | 29.1383 | 8.9458 |
| 0.0229 | 1.79 | 500 | 0.0529 | 29.7316 | 8.6507 |
| 0.0229 | 2.14 | 600 | 0.0529 | 30.0367 | 8.8326 |
| 0.0229 | 2.5 | 700 | 0.0529 | 29.8774 | 8.8947 |
| 0.0229 | 2.86 | 800 | 0.0526 | 29.4939 | 8.5792 |
| 0.0229 | 3.21 | 900 | 0.0525 | 29.6445 | 8.877 |
| 0.0219 | 3.57 | 1000 | 0.0525 | 29.5756 | 8.8233 |
| 0.0219 | 3.93 | 1100 | 0.0525 | 29.7202 | 8.9447 |
| 0.0219 | 4.29 | 1200 | 0.0526 | 29.6961 | 8.8869 |
| 0.0219 | 4.64 | 1300 | 0.0526 | 29.9186 | 8.854 |
| 0.0219 | 5.0 | 1400 | 0.0525 | 29.8636 | 8.8467 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.2