metadata
license: apache-2.0
tags:
- summarization
- generated_from_trainer
metrics:
- rouge
model-index:
- name: t5-base-news_headlines
results: []
t5-base-news_headlines
This model is a fine-tuned version of t5-base on an unknown 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
- dataset_name: valurank/News_headlines
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