<!-- 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
This model is a fine-tuned version of theojolliffe/bart-cnn-pubmed-arxiv-pubmed-arxiv on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8065
- Rouge1: 54.5916
- Rouge2: 36.7817
- Rougel: 40.4708
- Rougelsum: 52.5754
- 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: 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: 5
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
1.2945 | 1.0 | 795 | 0.9555 | 51.91 | 32.0926 | 33.6727 | 49.5306 | 142.0 |
0.7153 | 2.0 | 1590 | 0.8317 | 52.4708 | 34.1035 | 35.2968 | 50.2966 | 141.963 |
0.5398 | 3.0 | 2385 | 0.8133 | 52.4603 | 33.497 | 36.4227 | 50.2513 | 141.8704 |
0.3568 | 4.0 | 3180 | 0.8091 | 52.3993 | 34.2424 | 37.7819 | 50.2069 | 142.0 |
0.2842 | 5.0 | 3975 | 0.8065 | 54.5916 | 36.7817 | 40.4708 | 52.5754 | 142.0 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 2.2.0
- Tokenizers 0.12.1