distilbart-xsum-12-3-finetuned-xsum
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: 2.5886
- Rouge1: 26.2164
- Rouge2: 8.042
- Rougel: 17.5545
- Rougelsum: 21.4745
- Gen Len: 62.0
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: 2e-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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 3.295 | 1.0 | 1041 | 3.0302 | 26.1938 | 8.0525 | 17.4251 | 21.3971 | 61.7637 |
| 2.9061 | 2.0 | 2082 | 2.7844 | 26.3284 | 7.8489 | 17.3299 | 21.487 | 61.951 |
| 2.7181 | 3.0 | 3123 | 2.6605 | 25.3295 | 7.5429 | 16.8791 | 21.0243 | 62.0 |
| 2.5903 | 4.0 | 4164 | 2.6097 | 25.5526 | 7.6456 | 17.1916 | 21.0674 | 61.9885 |
| 2.5327 | 5.0 | 5205 | 2.5886 | 26.2164 | 8.042 | 17.5545 | 21.4745 | 62.0 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2