masrawy-english-arabic-translator

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: 2.2729

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: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss
3.0322	1.0	2396	2.7550
2.6774	2.0	4792	2.5702
2.4396	3.0	7188	2.4710
2.3383	4.0	9584	2.4240
2.2258	5.0	11980	2.3784
2.1246	6.0	14376	2.3536
2.0464	7.0	16772	2.3279
1.955	8.0	19168	2.3168
1.9251	9.0	21564	2.2985
1.8907	10.0	23960	2.2907
1.8345	11.0	26356	2.2874
1.7875	12.0	28752	2.2856
1.7772	13.0	31148	2.2791
1.7081	14.0	33544	2.2756
1.6571	15.0	35940	2.2768
1.6939	16.0	38336	2.2736
1.6486	17.0	40732	2.2724
1.6019	18.0	43128	2.2719
1.6029	19.0	45524	2.2728
1.6114	20.0	47920	2.2729

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.1+cu121
• Datasets 2.14.5
• Tokenizers 0.15.1