opus-mt-ar-en-finetuned-ar-to-en

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

• Loss: 0.6933
• Bleu: 32.8872
• Gen Len: 56.084

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: 3e-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

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	188	0.7407	30.7259	56.296
No log	2.0	376	0.6927	32.2038	58.602
0.8066	3.0	564	0.6898	33.1091	57.72
0.8066	4.0	752	0.6925	33.0842	56.574
0.8066	5.0	940	0.6933	32.8872	56.084

Framework versions

• Transformers 4.20.0
• Pytorch 1.11.0+cu113
• Datasets 2.3.2
• Tokenizers 0.12.1