mT5-Xl Turkish Summarization

This model is a fine-tuned version of google/mt5-xl on the musabg/wikipedia-tr-summarization dataset.

This can be used with HF summarization pipeline.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1.0

Eval results

It achieves the following results on the evaluation set:

• Loss: 0.5676
• Rouge1: 56.4468
• Rouge2: 41.3258
• Rougel: 48.1909
• Rougelsum: 48.4284
• Gen Len: 75.9265

Training results

Framework versions

• Transformers 4.31.0.dev0
• Pytorch 1.13.1
• Datasets 2.12.0
• Tokenizers 0.13.3