<!-- 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-arxiv-arxiv-v3-e10
This model is a fine-tuned version of theojolliffe/bart-cnn-pubmed-arxiv-pubmed-arxiv-arxiv on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8234
- Rouge1: 55.5793
- Rouge2: 40.0855
- Rougel: 42.0964
- Rougelsum: 53.6353
- Gen Len: 142.0
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: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
No log | 1.0 | 398 | 0.8670 | 53.2875 | 33.7336 | 36.1194 | 50.6842 | 142.0 |
0.8268 | 2.0 | 796 | 0.8041 | 53.8106 | 34.5241 | 37.4362 | 51.2786 | 142.0 |
0.5316 | 3.0 | 1194 | 0.8188 | 53.28 | 33.6 | 36.5483 | 50.6643 | 142.0 |
0.3572 | 4.0 | 1592 | 0.7821 | 53.9262 | 35.1924 | 37.8367 | 51.6176 | 141.7778 |
0.3572 | 5.0 | 1990 | 0.7837 | 55.35 | 37.6648 | 40.6764 | 52.5981 | 142.0 |
0.2426 | 6.0 | 2388 | 0.7760 | 55.4524 | 39.1414 | 42.4299 | 53.2113 | 141.9815 |
0.1698 | 7.0 | 2786 | 0.7921 | 56.7694 | 40.3148 | 43.3934 | 54.7093 | 142.0 |
0.1192 | 8.0 | 3184 | 0.8013 | 54.4313 | 37.6505 | 39.743 | 52.1465 | 142.0 |
0.1 | 9.0 | 3582 | 0.8139 | 55.6947 | 40.2425 | 42.7441 | 53.7018 | 142.0 |
0.1 | 10.0 | 3980 | 0.8234 | 55.5793 | 40.0855 | 42.0964 | 53.6353 | 142.0 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1