README.md

metadata

license: apache-2.0
tags:
  - summarization
  - generated_from_trainer
datasets:
  - multi_news
metrics:
  - rouge
model-index:
  - name: bart-base-multi-news
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: multi_news
          type: multi_news
          config: default
          split: validation
          args: default
        metrics:
          - name: Rouge1
            type: rouge
            value: 26.77

bart-base-multi-news

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

• Loss: 2.4116
• Rouge1: 26.77
• Rouge2: 10.28
• Rougel: 21.26
• Rougelsum: 22.02

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: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
2.7976	1.0	1250	2.4116	26.77	10.28	21.26	22.02

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.0+cu117
• Datasets 2.12.0
• Tokenizers 0.13.3