bart-base-finetuned-findsum
This model is a fine-tuned version of facebook/bart-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6579
- Rouge1: 6.91
- Rouge2: 3.2425
- Rougel: 6.1175
- Rougelsum: 6.5356
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 2.3034 | 1.0 | 1000 | 1.9298 | 6.7298 | 3.0582 | 5.932 | 6.3501 |
| 1.9526 | 2.0 | 2000 | 1.8003 | 7.0291 | 3.2546 | 6.1777 | 6.6368 |
| 1.8053 | 3.0 | 3000 | 1.7199 | 6.9328 | 3.2489 | 6.1701 | 6.5512 |
| 1.7113 | 4.0 | 4000 | 1.6741 | 6.9283 | 3.2114 | 6.1239 | 6.5354 |
| 1.654 | 5.0 | 5000 | 1.6579 | 6.91 | 3.2425 | 6.1175 | 6.5356 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2