<!-- 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
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: 2.0719
- Bleu: 9.6191
- Gen Len: 13.542
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 4.1808 | 1.0 | 732 | 2.9129 | 3.2505 | 15.1565 |
| 3.0353 | 2.0 | 1464 | 2.4851 | 6.6089 | 13.4928 |
| 2.1867 | 3.0 | 2196 | 2.2985 | 7.5619 | 13.5455 |
| 2.0138 | 4.0 | 2928 | 2.1924 | 8.0542 | 13.6172 |
| 1.6726 | 5.0 | 3660 | 2.1360 | 9.3411 | 13.337 |
| 1.5354 | 6.0 | 4392 | 2.1047 | 9.363 | 13.4962 |
| 1.392 | 7.0 | 5124 | 2.0912 | 9.9693 | 13.432 |
| 1.2942 | 8.0 | 5856 | 2.0768 | 9.7611 | 13.4833 |
| 1.2139 | 9.0 | 6588 | 2.0732 | 9.6065 | 13.5666 |
| 1.1894 | 10.0 | 7320 | 2.0719 | 9.6191 | 13.542 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
