GuysTrans's picture
update model card README.md
90620b5
|
raw
history blame
2.43 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: bart-base-finetuned-xsum
    results: []

bart-base-finetuned-xsum

This model is a fine-tuned version of facebook/bart-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.7802
  • Rouge1: 10.2143
  • Rouge2: 5.6684
  • Rougel: 8.8677
  • Rougelsum: 9.8692
  • Gen Len: 20.0

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: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
3.1154 1.0 501 2.1511 10.4214 5.0073 8.8506 9.9896 19.982
2.1503 2.0 1002 1.9367 10.2207 5.631 8.9531 9.9404 20.0
1.9303 3.0 1503 1.8703 10.4496 5.8424 9.1 10.1692 20.0
1.8227 4.0 2004 1.8365 10.3195 5.6383 8.9427 10.0217 20.0
1.7561 5.0 2505 1.8137 10.3644 5.7409 8.9742 10.0328 20.0
1.6962 6.0 3006 1.7963 10.307 5.7619 8.9713 10.0001 20.0
1.6573 7.0 3507 1.7906 10.2633 5.6772 8.9086 9.9373 20.0
1.6357 8.0 4008 1.7808 10.3619 5.7546 9.0124 10.02 20.0
1.6269 9.0 4509 1.7808 10.2688 5.6934 8.934 9.9284 20.0
1.6031 10.0 5010 1.7802 10.2143 5.6684 8.8677 9.8692 20.0

Framework versions

  • Transformers 4.30.2
  • Pytorch 2.0.0
  • Datasets 2.1.0
  • Tokenizers 0.13.3