<!-- 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_darija_V2
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: 2.0937
- Bleu: 13.5577
- Gen Len: 13.1351
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
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 1.5746 | 1.0 | 1546 | 2.1168 | 12.722 | 12.7945 |
| 1.3716 | 2.0 | 3092 | 2.1023 | 13.1293 | 12.9319 |
| 1.2408 | 3.0 | 4638 | 2.0957 | 12.9968 | 13.1639 |
| 1.1273 | 4.0 | 6184 | 2.1058 | 13.2809 | 13.1344 |
| 1.1365 | 5.0 | 7730 | 2.0939 | 13.286 | 13.1721 |
| 1.0619 | 6.0 | 9276 | 2.0947 | 13.4256 | 13.0771 |
| 1.0255 | 7.0 | 10822 | 2.0937 | 13.5577 | 13.1351 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
