en-ar_faseeh.v.0
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: 0.8551
- Bleu: 45.5526
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: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Bleu |
---|---|---|---|---|
1.2661 | 1.0 | 9019 | 1.1925 | 35.4959 |
1.1363 | 2.0 | 18038 | 1.0629 | 38.7606 |
0.9106 | 3.0 | 27057 | 0.9927 | 40.2049 |
0.8538 | 4.0 | 36076 | 0.9420 | 41.9980 |
0.7722 | 5.0 | 45095 | 0.9112 | 43.1329 |
0.7095 | 6.0 | 54114 | 0.8873 | 43.8821 |
0.6389 | 7.0 | 63133 | 0.8741 | 44.6584 |
0.6191 | 8.0 | 72152 | 0.8631 | 45.0652 |
0.587 | 9.0 | 81171 | 0.8582 | 45.2953 |
0.6158 | 10.0 | 90190 | 0.8551 | 45.5526 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1
- Downloads last month
- 3