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: 1.8665
- Rouge1: 0.1884
- Rouge2: 0.1059
- Rougel: 0.1664
- Rougelsum: 0.1772
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 |
|---|---|---|---|---|---|---|---|
| 2.6095 | 1.0 | 63 | 1.9725 | 0.1592 | 0.0879 | 0.1436 | 0.1489 |
| 2.0568 | 2.0 | 126 | 1.8743 | 0.1945 | 0.1119 | 0.1714 | 0.1827 |
| 1.7918 | 3.0 | 189 | 1.8428 | 0.1867 | 0.1053 | 0.1638 | 0.1734 |
| 1.6358 | 4.0 | 252 | 1.8366 | 0.1873 | 0.1081 | 0.1664 | 0.1758 |
| 1.4646 | 5.0 | 315 | 1.8587 | 0.1915 | 0.1075 | 0.1684 | 0.1786 |
| 1.3943 | 6.0 | 378 | 1.8478 | 0.1824 | 0.1056 | 0.1619 | 0.1706 |
| 1.2954 | 7.0 | 441 | 1.8752 | 0.1897 | 0.1079 | 0.1662 | 0.1764 |
| 1.2544 | 8.0 | 504 | 1.8665 | 0.1884 | 0.1059 | 0.1664 | 0.1772 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1