Hugging Face's logo

antonkurylo
/
t5-base-news_headlines_7

Summarization
Transformers
PyTorch
TensorBoard
English
t5
text2text-generation
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
3
t5-base-news_headlines_7 / README.md
antonkurylo's picture
antonkurylo
Update README.md
efb71c7
preview code
|
raw
history blame
2.76 kB
metadata
license: apache-2.0
tags:
  - summarization
  - generated_from_trainer
metrics:
  - rouge
widget:
  - text: >
      As the demands of climate change grow, businesses are realizing the
      imperative of embracing sustainability. Driven by ecological necessity and
      evolving consumer expectations, this shift necessitates a complete
      overhaul of traditional business models towards a circular economy,
      emphasizing resource efficiency and waste reduction.
       Adopting sustainable practices offers businesses multiple benefits: reduced operating costs, enhanced brand reputation, and increased customer loyalty.  As such, sustainability is a strategic tool for businesses looking to future-proof themselves.
model-index:
  - name: t5-base-news_headlines
    results: []

t5-base-news_headlines

This model is a fine-tuned version of t5-base on an valurank/News_headlines dataset. It achieves the following results on the evaluation set:

  • Loss: 0.9975
  • Rouge1: 53.7064
  • Rouge2: 34.6278
  • Rougel: 50.5129
  • Rougelsum: 50.5108

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
  • weight_decay: 0.01
  • lr_scheduler_type: linear
  • num_epochs: 7
  • max_text_length: 512
  • max_target_length: 16

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum
1.9933 1.0 1531 1.4942 44.2439 22.1239 40.5281 40.5525
1.6029 2.0 3062 1.2824 46.5726 25.1122 43.131 43.151
1.409 3.0 4593 1.2358 48.3188 27.7403 44.9576 45.0009
1.2699 4.0 6124 1.1600 50.9858 30.6655 47.775 47.8414
1.1696 5.0 7655 1.0607 52.2212 32.6952 49.0023 49.0812
1.0934 6.0 9186 1.0173 53.1629 33.9552 49.9629 50.0118
1.049 7.0 10717 0.9975 53.7064 34.6278 50.5129 50.5108

Framework versions

  • Transformers 4.28.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.12.0
  • Tokenizers 0.13.3