README.md

metadata

license: apache-2.0
tags:
  - summarization
  - generated_from_trainer
datasets:
  - wiki_lingua
metrics:
  - rouge
model-index:
  - name: wiki_lingua-de-8-3-5.6e-05-mt5-small-finetuned
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: wiki_lingua
          type: wiki_lingua
          config: de
          split: test
          args: de
        metrics:
          - name: Rouge1
            type: rouge
            value: 15.2299
language:
  - de

wiki_lingua-de-8-3-5.6e-05-mt5-small-finetuned

This model is a fine-tuned version of google/mt5-small on the wiki_lingua dataset. It achieves the following results on the evaluation set:

• Loss: 2.4218
• Rouge1: 15.2299
• Rouge2: 4.4912
• Rougel: 13.4991
• Rougelsum: 14.9193

Baseline LEAD64

• Rouge1: 18.76
• Rouge2: 4.22
• Rougel: 12.14
• Rougelsum: 12.14

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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
3.5656	1.0	4939	2.5421	14.4738	4.064	12.7061	14.1813
2.9444	2.0	9878	2.4492	14.8349	4.3457	13.16	14.5623
2.8378	3.0	14817	2.4218	15.2299	4.4912	13.4991	14.9193

Framework versions

• Transformers 4.27.4
• Pytorch 1.13.0
• Datasets 2.1.0
• Tokenizers 0.13.2