liputan6-pt-pl50 / README.md
apwic's picture
End of training
a0e53e6 verified
metadata
language:
  - id
license: apache-2.0
base_model: LazarusNLP/IndoNanoT5-base
tags:
  - generated_from_trainer
datasets:
  - id_liputan6
metrics:
  - rouge
model-index:
  - name: liputan6-pt-pl50
    results:
      - task:
          name: Summarization
          type: summarization
        dataset:
          name: id_liputan6 canonical
          type: id_liputan6
          config: canonical
          split: validation
          args: canonical
        metrics:
          - name: Rouge1
            type: rouge
            value: 35.5686

liputan6-pt-pl50

This model is a fine-tuned version of LazarusNLP/IndoNanoT5-base on the id_liputan6 canonical dataset. It achieves the following results on the evaluation set:

  • Loss: 2.6722
  • Rouge1: 35.5686
  • Rouge2: 23.5102
  • Rougel: 31.8451
  • Rougelsum: 33.6584
  • Gen Len: 49.748

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: 0.001
  • train_batch_size: 16
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5.0

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
4.2782 1.0 63 3.2600 25.0139 13.1669 22.4852 23.5026 38.037
3.3831 2.0 126 3.0118 28.0005 15.5199 25.1006 26.3175 51.621
3.0732 3.0 189 2.8226 31.6641 18.1569 27.8004 29.8463 51.938
2.83 4.0 252 2.7181 34.3328 21.5065 30.323 32.3623 51.327
2.6441 5.0 315 2.6722 34.8229 22.044 30.8324 33.0138 52.623

Framework versions

  • Transformers 4.40.2
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1