Edit model card

AraT5-base-title-generation-finetuned-ar-xlsum

This model is a fine-tuned version of UBC-NLP/AraT5-base-title-generation on the wiki_lingua dataset. It achieves the following results on the evaluation set:

  • Loss: 4.8120
  • Rouge-1: 23.29
  • Rouge-2: 8.44
  • Rouge-l: 20.74
  • Gen Len: 18.16
  • Bertscore: 70.88

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 5e-05
  • 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

Training Loss Epoch Step Validation Loss Rouge-1 Rouge-2 Rouge-l Gen Len Bertscore
6.1002 1.0 5111 5.2917 18.95 5.84 17.01 17.9 68.69
5.4427 2.0 10222 5.0877 20.61 6.73 18.58 17.14 69.69
5.1876 3.0 15333 4.9631 21.27 7.17 19.09 17.69 69.82
5.0256 4.0 20444 4.8984 21.7 7.53 19.55 17.56 70.18
4.9104 5.0 25555 4.8538 22.23 7.54 19.79 17.6 70.33
4.8251 6.0 30666 4.8309 22.35 7.6 19.96 17.64 70.51
4.7666 7.0 35777 4.8168 22.45 7.81 20.15 17.47 70.61
4.7275 8.0 40888 4.8120 22.67 7.83 20.34 17.56 70.66

Framework versions

  • Transformers 4.18.0
  • Pytorch 1.10.0+cu111
  • Datasets 2.1.0
  • Tokenizers 0.12.1
Downloads last month
18
Hosted inference API
Summarization
Examples
Examples
This model can be loaded on the Inference API on-demand.

Dataset used to train eslamxm/AraT5-base-title-generation-finetuned-ar-wikilingua