metadata
license: mit
base_model: facebook/bart-large-cnn
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: bart-large-cnn-finetuned-scope-summarization
results: []
bart-large-cnn-finetuned-scope-summarization
This model is a fine-tuned version of facebook/bart-large-cnn on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0451
- Rouge1: 50.5384
- Rouge2: 38.354
- Rougel: 39.3824
- Rougelsum: 39.3274
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 0.4522 | 1.0 | 29 | 0.1016 | 39.3219 | 23.9312 | 30.059 | 30.0842 |
| 0.115 | 2.0 | 58 | 0.0910 | 42.5308 | 28.0438 | 34.7355 | 34.6854 |
| 0.1008 | 3.0 | 87 | 0.0773 | 46.8072 | 32.1794 | 38.8917 | 39.1092 |
| 0.0887 | 4.0 | 116 | 0.0748 | 40.6291 | 27.6322 | 31.1978 | 31.2266 |
| 0.0878 | 5.0 | 145 | 0.0678 | 45.3986 | 31.5703 | 35.6892 | 35.7214 |
| 0.077 | 6.0 | 174 | 0.0598 | 47.8845 | 34.9979 | 39.1758 | 39.3253 |
| 0.0714 | 7.0 | 203 | 0.0559 | 49.0723 | 35.9285 | 37.1426 | 37.1948 |
| 0.061 | 8.0 | 232 | 0.0509 | 49.7851 | 37.3486 | 40.8669 | 40.9567 |
| 0.0625 | 9.0 | 261 | 0.0465 | 50.7533 | 37.6276 | 39.9594 | 40.0946 |
| 0.0488 | 10.0 | 290 | 0.0451 | 50.5384 | 38.354 | 39.3824 | 39.3274 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1