Nllb 200 Distilled 600M Finetuned Ar To En

🚀 nllb-200-distilled-600M-finetuned-ar-to-en

This model is a fine - tuned version of facebook/nllb-200-distilled-600M on an unknown dataset. It can achieve specific results on the evaluation set, providing a solution for Arabic - to - English translation tasks.

🚀 Quick Start

This model is mainly used for Arabic - to - English translation. You can use it in your own projects by following the relevant framework's usage methods.

📚 Documentation

Model Information

This model achieves the following results on the evaluation set:

• Loss: 0.7281
• Bleu: 63.3172
• Gen Len: 65.7

Training Procedure

Training Hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e - 05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
• lr_scheduler_type: linear
• num_epochs: 10

Training Results

Framework Versions

• Transformers 4.31.0
• Pytorch 1.13.1
• Datasets 2.14.4
• Tokenizers 0.13.3

📄 License

This model is released under the cc - by - nc - 4.0 license.