bart-large-cnn-finetuned-multi-news1
This model is a fine-tuned version of facebook/bart-large-cnn on the multi_news dataset. It achieves the following results on the evaluation set:
- Loss: 2.0858
- Rouge1: 42.1215
- Rouge2: 14.9986
- Rougel: 23.4737
- Rougelsum: 36.4212
- Gen Len: 133.703
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: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.1984 | 1.0 | 750 | 2.0858 | 42.1215 | 14.9986 | 23.4737 | 36.4212 | 133.703 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.11.6