bart-base-cnn-xsum-cite-swe
This model is a fine-tuned version of Gabriel/bart-base-cnn-xsum-swe on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.4203
- Rouge1: 29.6279
- Rouge2: 11.5697
- Rougel: 24.2429
- Rougelsum: 24.4557
- Gen Len: 19.9371
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.4833 | 1.0 | 2558 | 2.4203 | 29.6279 | 11.5697 | 24.2429 | 24.4557 | 19.9371 |
Framework versions
- Transformers 4.22.2
- Pytorch 1.12.1+cu113
- Datasets 2.5.1
- Tokenizers 0.12.1
- Downloads last month
- 10
Dataset used to train Gabriel/bart-base-cnn-xsum-cite-swe
Evaluation results
- Validation ROGUE-1. on Gabriel/citesum_swevalidation set self-reported29.628
- Validation ROGUE-2 on Gabriel/citesum_swevalidation set self-reported11.570
- Validation ROGUE-L on Gabriel/citesum_swevalidation set self-reported24.243
- Validation ROGUE-L-SUM on Gabriel/citesum_swevalidation set self-reported24.456