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: 0.0570
- Bleu: 23.5668
- Gen Len: 8.8618
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: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 0.0178 | 0.24 | 500 | 0.0630 | 18.503 | 9.3352 |
| 0.0165 | 0.48 | 1000 | 0.0615 | 19.3363 | 9.6601 |
| 0.0154 | 0.72 | 1500 | 0.0600 | 20.7491 | 9.3712 |
| 0.0154 | 0.96 | 2000 | 0.0587 | 22.3931 | 9.2534 |
| 0.0131 | 1.2 | 2500 | 0.0584 | 23.1796 | 9.3425 |
| 0.0128 | 1.44 | 3000 | 0.0579 | 22.4839 | 9.0177 |
| 0.0138 | 1.68 | 3500 | 0.0573 | 22.3119 | 9.1767 |
| 0.0138 | 1.92 | 4000 | 0.0570 | 23.5668 | 8.8618 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.2