distilbart-cnn-12-6-summarization_final_labeled_data
This model is a fine-tuned version of sshleifer/distilbart-cnn-12-6 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1332
- Rouge1: 68.938
- Rouge2: 57.0751
- Rougel: 63.1918
- Rougelsum: 67.2288
- Gen Len: 119.76
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: 2
- eval_batch_size: 2
- 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 |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 99 | 0.4444 | 54.7967 | 41.6412 | 48.0493 | 53.3043 | 118.1 |
| No log | 2.0 | 198 | 0.2934 | 60.514 | 46.8988 | 53.0023 | 58.9903 | 114.62 |
| No log | 3.0 | 297 | 0.1886 | 69.1369 | 57.4931 | 64.4281 | 67.5744 | 121.52 |
| No log | 4.0 | 396 | 0.1482 | 67.7496 | 55.4617 | 62.6617 | 66.1207 | 117.74 |
| No log | 5.0 | 495 | 0.1332 | 68.938 | 57.0751 | 63.1918 | 67.2288 | 119.76 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1