distilbart-cnn-6-6-finetuned-xsum-intro-test
This model is a fine-tuned version of sshleifer/distilbart-cnn-6-6 on the xsum dataset. It achieves the following results on the evaluation set:
- Loss: 1.9036
- Rouge1: 32.0474
- Rouge2: 12.3779
- Rougel: 23.5491
- Rougelsum: 24.251
- Gen Len: 60.8594
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 1.9432 | 1.0 | 12753 | 1.9036 | 32.0474 | 12.3779 | 23.5491 | 24.251 | 60.8594 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1
- Tokenizers 0.13.2