metadata
license: apache-2.0
base_model: t5-small
tags:
- summarization
- generated_from_trainer
metrics:
- rouge
model-index:
- name: t5-small-finetuned-cnn-news
results: []
t5-small-finetuned-cnn-news
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8421
- Rouge1: 24.4309
- Rouge2: 12.1268
- Rougel: 20.3697
- Rougelsum: 23.18
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: 0.00056
- 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 2.0267 | 1.0 | 718 | 1.8134 | 24.5086 | 12.0372 | 20.3241 | 23.2338 |
| 1.8289 | 2.0 | 1436 | 1.8150 | 24.4861 | 12.1833 | 20.5262 | 23.3358 |
| 1.6833 | 3.0 | 2154 | 1.8148 | 23.9202 | 11.7941 | 19.9514 | 22.7185 |
| 1.576 | 4.0 | 2872 | 1.8271 | 24.2367 | 11.8778 | 20.1292 | 23.0104 |
| 1.4965 | 5.0 | 3590 | 1.8421 | 24.4309 | 12.1268 | 20.3697 | 23.18 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1