Tounsify-v0.5

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: 2.4601
• Bleu: 10.9697
• Gen Len: 6.7667

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: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	8	3.0293	17.4149	6.8667
No log	2.0	16	2.7241	15.4515	6.8
No log	3.0	24	2.5788	11.0969	6.5
No log	4.0	32	2.4926	10.9697	6.7
No log	5.0	40	2.4601	10.9697	6.7667

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1