metadata
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: bart-base-finetuned-CNN-DailyNews
results: []
bart-base-finetuned-CNN-DailyNews
This model is a fine-tuned version of facebook/bart-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.8682
- Rouge1: 0.184
- Rouge2: 0.1067
- Rougel: 0.1628
- Rougelsum: 0.1718
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
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 2.6113 | 1.0 | 63 | 1.9753 | 0.1612 | 0.092 | 0.146 | 0.1524 |
| 2.0604 | 2.0 | 126 | 1.8843 | 0.1922 | 0.1126 | 0.1709 | 0.1824 |
| 1.7829 | 3.0 | 189 | 1.8400 | 0.1874 | 0.1056 | 0.1672 | 0.1754 |
| 1.6337 | 4.0 | 252 | 1.8325 | 0.1878 | 0.1079 | 0.1664 | 0.176 |
| 1.4657 | 5.0 | 315 | 1.8439 | 0.1839 | 0.1057 | 0.1651 | 0.1719 |
| 1.3926 | 6.0 | 378 | 1.8445 | 0.1868 | 0.1049 | 0.1657 | 0.1752 |
| 1.2903 | 7.0 | 441 | 1.8545 | 0.1878 | 0.1072 | 0.1663 | 0.1753 |
| 1.2512 | 8.0 | 504 | 1.8682 | 0.184 | 0.1067 | 0.1628 | 0.1718 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1