amagzari's picture
update model card README.md
7611e5c
metadata
license: apache-2.0
tags:
  - summarization
  - generated_from_trainer
datasets:
  - cnn_dailymail
metrics:
  - rouge
model-index:
  - name: bart-base-finetuned-cnn_dailymail
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: cnn_dailymail
          type: cnn_dailymail
          config: 3.0.0
          split: train
          args: 3.0.0
        metrics:
          - name: Rouge1
            type: rouge
            value: 0.35105989316705805

bart-base-finetuned-cnn_dailymail

This model is a fine-tuned version of facebook/bart-base on the cnn_dailymail dataset. It achieves the following results on the evaluation set:

  • Loss: 1.5396
  • Rouge1: 0.3511
  • Rouge2: 0.1925
  • Rougel: 0.3086
  • Rougelsum: 0.3292

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: 5.6e-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: 4

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum
1.9486 1.0 35890 1.5941 0.3498 0.1893 0.3063 0.3272
1.6706 2.0 71780 1.5601 0.3503 0.1916 0.3079 0.3279
1.4809 3.0 107670 1.5423 0.3520 0.1923 0.3086 0.3295
1.3293 4.0 143560 1.5396 0.3511 0.1925 0.3086 0.3292

Framework versions

  • Transformers 4.24.0
  • Pytorch 1.12.1+cu113
  • Datasets 2.7.1
  • Tokenizers 0.13.2