<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
nor-sum
This model is a fine-tuned version of sshleifer/distilbart-cnn-6-6 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.1812
- Rouge1: 0.2552
- Rouge2: 0.0679
- Rougel: 0.1884
- Rougelsum: 0.1886
- Gen Len: 65.3086
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.6231 | 1.0 | 3188 | 2.4652 | 0.2359 | 0.0563 | 0.1732 | 0.1733 | 66.1928 |
| 2.3062 | 2.0 | 6377 | 2.2798 | 0.2524 | 0.0653 | 0.1864 | 0.1864 | 66.3107 |
| 2.0817 | 3.0 | 9565 | 2.1973 | 0.2529 | 0.0675 | 0.189 | 0.1893 | 65.077 |
| 1.9776 | 4.0 | 12752 | 2.1812 | 0.2552 | 0.0679 | 0.1884 | 0.1886 | 65.3086 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.1
- Tokenizers 0.13.3
