bart-large-cnn-finetuned-pubmed-finetuned-pubmedarxiv
This model is a fine-tuned version of theojolliffe/bart-large-cnn-finetuned-pubmed on the scientific_papers dataset. It achieves the following results on the evaluation set:
- Loss: 2.3402
- Rouge1: 41.3608
- Rouge2: 15.1848
- Rougel: 23.8655
- Rougelsum: 37.0916
- Gen Len: 132.8238
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: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.432 | 1.0 | 6345 | 2.3402 | 41.3608 | 15.1848 | 23.8655 | 37.0916 | 132.8238 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 2.1.0
- Tokenizers 0.12.1