bart-cnn-science / README.md
theojolliffe's picture
update model card README.md
2b5c0e6
metadata
license: mit
tags:
  - generated_from_trainer
datasets:
  - scientific_papers
metrics:
  - rouge
model-index:
  - name: bart-large-cnn-pubmed1o3-pubmed2o3-pubmed3o3-arxiv1o3-arxiv2o3-arxiv3o3
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: scientific_papers
          type: scientific_papers
          args: arxiv
        metrics:
          - name: Rouge1
            type: rouge
            value: 42.5835

bart-large-cnn-pubmed1o3-pubmed2o3-pubmed3o3-arxiv1o3-arxiv2o3-arxiv3o3

This model is a fine-tuned version of theojolliffe/bart-large-cnn-pubmed1o3-pubmed2o3-pubmed3o3-arxiv1o3-arxiv2o3 on the scientific_papers dataset. It achieves the following results on the evaluation set:

  • Loss: 2.0646
  • Rouge1: 42.5835
  • Rouge2: 16.1887
  • Rougel: 24.7972
  • Rougelsum: 38.1846
  • Gen Len: 129.9291

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

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
2.0865 1.0 33840 2.0646 42.5835 16.1887 24.7972 38.1846 129.9291

Framework versions

  • Transformers 4.19.2
  • Pytorch 1.11.0+cu113
  • Datasets 2.2.2
  • Tokenizers 0.12.1