Mbart Large 50 Finetuned Ar Wikilingua

🚀 mbart-large-50-finetuned-ar-wikilingua

This model is a fine - tuned version of facebook/mbart-large-50 on the wiki_lingua dataset. It offers summarization capabilities and has achieved specific performance metrics on the evaluation set.

🚀 Quick Start

This model is a fine - tuned version of facebook/mbart-large-50 on the wiki_lingua dataset. It achieves the following results on the evaluation set:

• Loss: 4.0001
• Rouge - 1: 22.11
• Rouge - 2: 7.33
• Rouge - l: 19.75
• Gen Len: 59.4
• Bertscore: 68.9

✨ Features

• Based on the well - known facebook/mbart-large-50 model, fine - tuned on the wiki_lingua dataset.
• Achieved specific evaluation metrics such as Rouge - 1, Rouge - 2, etc.

🔧 Technical Details

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e - 06
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 250
• num_epochs: 8
• label_smoothing_factor: 0.1

Training results

Framework versions

• Transformers 4.18.0
• Pytorch 1.10.0+cu111
• Datasets 2.1.0
• Tokenizers 0.12.1