roofdancer's picture
End of training
97b4923 verified
metadata
license: apache-2.0
base_model: sshleifer/distilbart-cnn-6-6
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: plain-bart-on-presummarized-tod-wcep
    results: []

plain-bart-on-presummarized-tod-wcep

This model is a fine-tuned version of sshleifer/distilbart-cnn-6-6 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 2.3043
  • Rouge1: 34.5939
  • Rouge2: 13.9925
  • Rougel: 24.4982
  • Rougelsum: 27.7893
  • Gen Len: 66.2392

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: 2e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
2.4866 1.0 510 2.3191 34.0155 13.6965 24.0706 27.3858 66.8784
2.1347 2.0 1020 2.2952 34.1203 13.7453 24.0993 27.4503 67.0735
1.9605 3.0 1530 2.3043 34.5939 13.9925 24.4982 27.7893 66.2392

Framework versions

  • Transformers 4.39.3
  • Pytorch 2.1.2
  • Datasets 2.18.0
  • Tokenizers 0.15.2