results
This model is a fine-tuned version of sshleifer/distilbart-xsum-12-3 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.6835
- Rouge1: 38.8257
- Rouge2: 10.9645
- Rougel: 19.5312
- Rougelsum: 33.4613
- Gen Len: 275.0
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: 0.00034
- 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
- lr_scheduler_warmup_steps: 500
- num_epochs: 3
- label_smoothing_factor: 0.04
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 3.2378 | 1.0 | 500 | 3.1436 | 25.8277 | 5.2374 | 13.1124 | 24.06 | 299.0 |
| 2.804 | 2.0 | 1000 | 2.7802 | 32.9123 | 6.3884 | 16.0251 | 29.3143 | 241.0 |
| 2.5568 | 3.0 | 1500 | 2.6835 | 38.8257 | 10.9645 | 19.5312 | 33.4613 | 275.0 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 0