metadata
license: apache-2.0
base_model: Helsinki-NLP/opus-mt-en-ar
tags:
- generated_from_trainer
model-index:
- name: masrawy-english-arabic-translator-clauda-opus-v1
results: []
masrawy-english-arabic-translator-clauda-opus-v1
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: 1.8534
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: 15
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.8787 | 1.0 | 3529 | 2.7030 |
| 2.6107 | 2.0 | 7058 | 2.5211 |
| 2.4579 | 3.0 | 10587 | 2.4222 |
| 2.3906 | 4.0 | 14116 | 2.3666 |
| 2.2673 | 5.0 | 17645 | 2.3260 |
| 2.2383 | 6.0 | 21174 | 2.2936 |
| 2.1464 | 7.0 | 24703 | 2.2754 |
| 2.1304 | 8.0 | 28232 | 2.2530 |
| 2.0802 | 9.0 | 31761 | 2.2417 |
| 2.048 | 10.0 | 35290 | 2.2341 |
| 2.0323 | 11.0 | 38819 | 2.2255 |
| 2.0012 | 12.0 | 42348 | 2.2233 |
| 1.9905 | 13.0 | 45877 | 2.2193 |
| 1.9648 | 14.0 | 49406 | 2.2162 |
| 1.9716 | 15.0 | 52935 | 1.8534 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu121
- Datasets 2.14.5
- Tokenizers 0.15.1