Finetuning_mt-en-ar_English_Arabic_Translation

This model is a fine-tuned version of Helsinki-NLP/opus-mt-en-ar on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1618

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: 4
• eval_batch_size: 4
• 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
0.3063	1.0	2000	0.2406
0.2338	2.0	4000	0.2032
0.2047	3.0	6000	0.1842
0.1698	4.0	8000	0.1738
0.1586	5.0	10000	0.1690
0.1394	6.0	12000	0.1664
0.1307	7.0	14000	0.1636
0.1229	8.0	16000	0.1627
0.1176	9.0	18000	0.1611
0.1094	10.0	20000	0.1608
0.1007	11.0	22000	0.1600
0.0959	12.0	24000	0.1610
0.0955	13.0	26000	0.1609
0.0942	14.0	28000	0.1618
0.0904	15.0	30000	0.1618

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.2.0
• Tokenizers 0.19.1