Mt5 Base Finetuned Urdu

🚀 mt5-base-finetuned-urdu

This model is a fine - tuned version of google/mt5-base on the Urdu subset of the xlsum dataset. It offers high - quality summarization capabilities for Urdu text, with specific performance metrics on the evaluation set.

🚀 Quick Start

This model is a fine - tuned version of google/mt5-base on the Urdu subset of the xlsum dataset. It achieves the following results on the evaluation set:

• Loss: 2.8954
• Rouge - 1: 28.84
• Rouge - 2: 13.87
• Rouge - l: 25.63
• Gen Len: 19.0
• Bertscore: 71.31

✨ Features

• Fine - tuned for Urdu: Specifically optimized for Urdu text summarization.
• Quantifiable Performance: Demonstrates clear performance metrics on the evaluation set, including loss, Rouge scores, and Bertscore.

🔧 Technical Details

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0005
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
• lr_scheduler_type: linear
• num_epochs: 5
• label_smoothing_factor: 0.1

Training results

Framework versions

• Transformers 4.18.0
• Pytorch 1.11.0+cu113
• Datasets 2.1.0
• Tokenizers 0.12.1

📄 License

This model is released under the Apache - 2.0 license.