faseeh.v.7

This model is a fine-tuned version of Helsinki-NLP/opus-mt-ar-en on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.8715
• Bleu: 51.3785

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: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu
1.3515	1.0	10693	1.1544	37.9022
0.9837	2.0	21386	1.0324	41.7697
0.8114	3.0	32079	0.9629	44.6717
0.7773	4.0	42772	0.9246	46.7136
0.5757	5.0	53465	0.9006	48.1288
0.5609	6.0	64158	0.8904	49.3739
0.521	7.0	74851	0.8752	50.3558
0.4915	8.0	85544	0.8717	50.7676
0.4183	9.0	96237	0.8693	51.2860
0.3699	10.0	106930	0.8715	51.3852

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2