metadata
license: mit
base_model: facebook/bart-large-cnn
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: bart-large-cnn-finetuned-scope-summarization-train-test-split
results: []
bart-large-cnn-finetuned-scope-summarization-train-test-split
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: 1.2315
- Rouge1: 52.3537
- Rouge2: 31.6854
- Rougel: 36.6454
- Rougelsum: 50.8292
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 25 | 0.6966 | 51.835 | 31.057 | 37.6234 | 50.2076 |
| 0.6673 | 2.0 | 50 | 0.6823 | 48.381 | 28.6493 | 37.1777 | 46.9784 |
| 0.5505 | 3.0 | 75 | 0.6825 | 51.1061 | 31.5147 | 38.5282 | 49.8741 |
| 0.5505 | 4.0 | 100 | 0.7131 | 51.0351 | 32.3268 | 39.7744 | 49.4893 |
| 0.4736 | 5.0 | 125 | 0.6975 | 52.9068 | 32.4415 | 39.5503 | 51.2993 |
| 0.4033 | 6.0 | 150 | 0.7925 | 51.3766 | 30.4233 | 37.7124 | 49.5155 |
| 0.3306 | 7.0 | 175 | 0.8079 | 52.2073 | 31.8487 | 38.6156 | 50.8166 |
| 0.3306 | 8.0 | 200 | 0.9168 | 51.6434 | 31.3338 | 37.4811 | 50.1527 |
| 0.256 | 9.0 | 225 | 0.9810 | 49.7984 | 30.3608 | 36.7693 | 48.7107 |
| 0.1823 | 10.0 | 250 | 0.9289 | 51.679 | 31.2458 | 36.4793 | 50.2032 |
| 0.1355 | 11.0 | 275 | 1.0269 | 52.0775 | 31.1824 | 37.5405 | 50.5995 |
| 0.1355 | 12.0 | 300 | 1.0736 | 51.3365 | 31.2121 | 38.37 | 50.0703 |
| 0.0974 | 13.0 | 325 | 1.0935 | 52.4146 | 32.5704 | 38.0578 | 51.424 |
| 0.0681 | 14.0 | 350 | 1.1100 | 51.5136 | 31.6307 | 38.5212 | 50.2267 |
| 0.0476 | 15.0 | 375 | 1.1507 | 51.9246 | 31.5588 | 36.8706 | 50.7219 |
| 0.0476 | 16.0 | 400 | 1.1667 | 53.7686 | 33.3238 | 38.145 | 52.2277 |
| 0.0336 | 17.0 | 425 | 1.1606 | 51.9682 | 31.4379 | 37.6764 | 50.8294 |
| 0.0232 | 18.0 | 450 | 1.1961 | 51.6253 | 31.6575 | 37.5128 | 50.406 |
| 0.0232 | 19.0 | 475 | 1.2162 | 51.7758 | 31.8239 | 36.3796 | 50.3009 |
| 0.0182 | 20.0 | 500 | 1.2315 | 52.3537 | 31.6854 | 36.6454 | 50.8292 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.2.1+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2