README.md

metadata

tags:
  - generated_from_trainer
datasets:
  - xlsum
metrics:
  - rouge
model-index:
  - name: mT5-finetuned-xlsum
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: xlsum
          type: xlsum
          config: arabic
          split: validation
          args: arabic
        metrics:
          - name: Rouge1
            type: rouge
            value: 0.1179

mT5-finetuned-xlsum

This model is a fine-tuned version of csebuetnlp/mT5_m2o_arabic_crossSum on the xlsum dataset. It achieves the following results on the evaluation set:

• Loss: 0.6752
• Rouge1: 0.1179
• Rouge2: 0.0231
• Rougel: 0.118
• Rougelsum: 0.1178
• Gen Len: 47.6818

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
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.8728	1.0	9380	0.6752	0.1179	0.0231	0.118	0.1178	47.6818

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.0
• Datasets 2.13.1
• Tokenizers 0.13.3