<!-- 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. -->
bart-cnn-pubmed-arxiv-pubmed
This model is a fine-tuned version of theojolliffe/bart-cnn-pubmed-arxiv on the scientific_papers dataset. It achieves the following results on the evaluation set:
- Loss: 1.9245
- Rouge1: 37.3328
- Rouge2: 15.5894
- Rougel: 23.0297
- Rougelsum: 33.952
- Gen Len: 136.3568
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: 1
- eval_batch_size: 1
- 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 |
|---|---|---|---|---|---|---|---|---|
| 2.0272 | 1.0 | 29981 | 1.9245 | 37.3328 | 15.5894 | 23.0297 | 33.952 | 136.3568 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 2.1.0
- Tokenizers 0.12.1
