<!-- 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. -->
distill-pegasus-cnn-16-4-finetuned-arxiv-pubmed
This model is a fine-tuned version of theojolliffe/distill-pegasus-cnn-16-4-finetuned-arxiv on the scientific_papers dataset. It achieves the following results on the evaluation set:
- Loss: 3.0433
- Rouge1: 31.5968
- Rouge2: 12.5841
- Rougel: 21.0778
- Rougelsum: 28.3167
- Gen Len: 118.9566
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 |
|---|---|---|---|---|---|---|---|---|
| 3.5173 | 1.0 | 3748 | 3.0433 | 31.5968 | 12.5841 | 21.0778 | 28.3167 | 118.9566 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 2.1.0
- Tokenizers 0.12.1
