Marian Finetuned Kde4 En To Ar

🚀 marian-finetuned-kde4-en-to-ar

This is a fine - tuned model based on [Helsinki - NLP/opus - mt - en - ar](https://huggingface.co/Helsinki - NLP/opus - mt - en - ar) for English to Arabic translation, trained on the kde4 dataset.

🚀 Quick Start

This model is a fine - tuned version of [Helsinki - NLP/opus - mt - en - ar](https://huggingface.co/Helsinki - NLP/opus - mt - en - ar) on the kde4 dataset.

📚 Documentation

Model description

If you want to learn about the model used, check [Helsinki - NLP Model](https://huggingface.co/Helsinki - NLP/opus - mt - en - ar).

Intended uses & limitations

No specific content provided in the original document.

Training and evaluation data

More information needed.

Training procedure

The training was done on Google Colab.

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e - 05
• train_batch_size: 32
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9, 0.999) and epsilon = 1e - 08
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

No specific content provided in the original document.

Framework versions

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

📄 License

This project is licensed under the Apache 2.0 license.