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: 0.0578
- Rouge1: 74.2613
- Rouge2: 58.7063
- Rougel: 63.9504
- Rougelsum: 64.1404
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 |
|---|---|---|---|---|---|---|---|
| 0.8985 | 1.0 | 48 | 0.6541 | 46.8501 | 29.7327 | 36.488 | 36.5549 |
| 0.6225 | 2.0 | 96 | 0.5766 | 53.306 | 34.1262 | 40.0055 | 39.8306 |
| 0.5508 | 3.0 | 144 | 0.5222 | 55.9759 | 36.614 | 41.5281 | 41.4843 |
| 0.4963 | 4.0 | 192 | 0.4711 | 57.6183 | 37.4078 | 42.6881 | 42.7515 |
| 0.4517 | 5.0 | 240 | 0.4193 | 59.2425 | 39.9758 | 42.3079 | 42.2173 |
| 0.4021 | 6.0 | 288 | 0.3792 | 59.5026 | 41.3313 | 46.1961 | 46.0462 |
| 0.3672 | 7.0 | 336 | 0.3145 | 62.5542 | 44.3172 | 48.4545 | 48.421 |
| 0.3153 | 8.0 | 384 | 0.2816 | 63.8301 | 46.3536 | 50.2103 | 50.1203 |
| 0.268 | 9.0 | 432 | 0.2598 | 64.191 | 47.4322 | 51.7505 | 51.8051 |
| 0.2159 | 10.0 | 480 | 0.2041 | 67.4345 | 49.7921 | 53.84 | 53.9574 |
| 0.1714 | 11.0 | 528 | 0.1416 | 68.2944 | 51.3248 | 56.1006 | 56.0528 |
| 0.1257 | 12.0 | 576 | 0.0961 | 69.7701 | 53.5417 | 58.2727 | 58.2473 |
| 0.0991 | 13.0 | 624 | 0.0717 | 69.9164 | 53.6164 | 59.4382 | 59.518 |
| 0.0699 | 14.0 | 672 | 0.0675 | 71.3498 | 55.64 | 60.2844 | 60.4973 |
| 0.0526 | 15.0 | 720 | 0.0814 | 72.2287 | 56.8939 | 60.9719 | 61.2308 |
| 0.0408 | 16.0 | 768 | 0.0843 | 71.7777 | 57.1413 | 62.0411 | 61.9723 |
| 0.0315 | 17.0 | 816 | 0.0525 | 72.5746 | 57.5505 | 61.6754 | 61.8729 |
| 0.0237 | 18.0 | 864 | 0.0542 | 72.0154 | 56.9233 | 61.3044 | 61.4721 |
| 0.0187 | 19.0 | 912 | 0.0573 | 73.4681 | 58.9845 | 64.4143 | 64.5341 |
| 0.0157 | 20.0 | 960 | 0.0578 | 74.2613 | 58.7063 | 63.9504 | 64.1404 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2