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: 1.8725
- Rouge1: 0.1807
- Rouge2: 0.1041
- Rougel: 0.1614
- Rougelsum: 0.1694
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 |
|---|---|---|---|---|---|---|---|
| 2.6142 | 1.0 | 63 | 1.9661 | 0.1623 | 0.0912 | 0.1463 | 0.1523 |
| 2.0578 | 2.0 | 126 | 1.8842 | 0.1865 | 0.1034 | 0.1643 | 0.1735 |
| 1.7935 | 3.0 | 189 | 1.8447 | 0.1736 | 0.0951 | 0.1547 | 0.1623 |
| 1.6412 | 4.0 | 252 | 1.8515 | 0.1863 | 0.1043 | 0.1636 | 0.1727 |
| 1.4701 | 5.0 | 315 | 1.8509 | 0.1876 | 0.1072 | 0.1676 | 0.1758 |
| 1.3969 | 6.0 | 378 | 1.8537 | 0.1828 | 0.1037 | 0.1627 | 0.1731 |
| 1.2943 | 7.0 | 441 | 1.8540 | 0.183 | 0.1022 | 0.1629 | 0.1713 |
| 1.2581 | 8.0 | 504 | 1.8725 | 0.1807 | 0.1041 | 0.1614 | 0.1694 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1