metadata

license: apache-2.0
tags:
  - summarization
  - generated_from_trainer
datasets:
  - multi_news
metrics:
  - rouge
model-index:
  - name: multi-news-diff-weight
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: multi_news
          type: multi_news
          config: default
          split: train[:20%]
          args: default
        metrics:
          - name: Rouge1
            type: rouge
            value: 9.9082

multi-news-diff-weight

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: 2.5350
Rouge1: 9.9082
Rouge2: 3.6995
Rougel: 7.6135
Rougelsum: 9.0176

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: 5e-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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
2.8555	1.0	4047	2.5846	9.7797	3.6212	7.5597	8.9387
2.5262	2.0	8094	2.5231	9.7969	3.5968	7.5592	8.9532
2.3195	3.0	12141	2.5149	9.83	3.6338	7.5109	8.9725
2.1655	4.0	16188	2.5188	9.8704	3.6936	7.6094	9.0336
2.055	5.0	20235	2.5350	9.9082	3.6995	7.6135	9.0176

Framework versions

Transformers 4.29.1
Pytorch 2.0.0
Datasets 2.12.0
Tokenizers 0.13.3