|
--- |
|
tags: |
|
- generated_from_keras_callback |
|
model-index: |
|
- name: t5-base-medium-title-generation |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information Keras had access to. You should |
|
probably proofread and complete it, then remove this comment. --> |
|
|
|
# Model description |
|
|
|
This model is [t5-base](https://huggingface.co/t5-base) fine-tuned on the [190k Medium Articles](https://www.kaggle.com/datasets/fabiochiusano/medium-articles) dataset for predicting article titles using the article textual content as input. |
|
|
|
## Training and evaluation data |
|
|
|
The model has been trained on a single epoch spanning about 16000 articles, evaluating on 1000 random articles not used during training. |
|
|
|
### Training results |
|
|
|
The model has been evaluated on a random dataset split of 1000 articles not used during training and validation. |
|
|
|
- Rouge-1: 33.8% |
|
- Rouge-2: 17.7% |
|
- Rouge-L: 31.4% |
|
- Rouge-Lsum: 31.4% |
|
- Average length of the generated titles: 12 tokens |
|
|
|
### Framework versions |
|
|
|
- Transformers 4.18.0 |
|
- TensorFlow 2.8.0 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.12.1 |
|
|