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

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: 0.8180
• Bleu: 65.6656
• Gen Len: 60.248

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	348	1.2239	50.582	62.155
1.5859	2.0	696	1.0136	56.9789	61.275
1.0284	3.0	1044	0.9322	59.8447	61.319
1.0284	4.0	1392	0.8872	61.7622	61.239
0.8538	5.0	1740	0.8595	63.1303	60.754
0.7418	6.0	2088	0.8434	64.0222	60.68
0.7418	7.0	2436	0.8305	64.8723	60.275
0.6897	8.0	2784	0.8222	65.4715	60.265
0.6394	9.0	3132	0.8189	65.5593	60.277
0.6394	10.0	3480	0.8180	65.6656	60.248

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3