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

Usage

from transformers import pipeline
summarizer = pipeline("summarization", model="antonkurylo/t5-base-news_headlines_7")

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.\nAdopting 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.\nCompanies like Unilever and Tesla serve as " \
       "models of this transformation. Unilever's sustainable living brands have outperformed the rest of their " \
       "portfolio,  while Tesla's entire business model centres around sustainability, proving that environmental " \
       "consciousness and profitability can coexist.\nIn our interconnected world, the impacts of businesses " \
       "extend to society and the environment, necessitating alignment with the global push for sustainability. " \
       "With sustainability no longer being a choice but an imperative, businesses adopting it will be the " \
       "leaders in the new business paradigm. In a nutshell, to thrive in the evolving market, embracing " \
       "sustainability is the new business imperative. The future of business is unquestionably green."

summarizer(text)

Expected Output

[{'summary_text': "The future of business is unquestionably green. Here's how it works . Unilever and Tesla are examples of the transformation"}]

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

Framework versions

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