<!-- 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. -->
distilbart-cnn-arxiv-pubmed-v3-e8
This model is a fine-tuned version of theojolliffe/distilbart-cnn-arxiv-pubmed on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8329
- Rouge1: 53.3047
- Rouge2: 34.6219
- Rougel: 37.6148
- Rougelsum: 50.8973
- Gen Len: 141.8704
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: 8
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
No log | 1.0 | 398 | 1.1211 | 50.4753 | 30.5417 | 33.192 | 48.1321 | 141.8704 |
1.3657 | 2.0 | 796 | 0.9944 | 52.2197 | 33.6109 | 35.9448 | 50.0028 | 141.6111 |
0.887 | 3.0 | 1194 | 0.9149 | 52.796 | 33.7683 | 36.4941 | 50.4514 | 141.5926 |
0.6548 | 4.0 | 1592 | 0.8725 | 52.5353 | 33.4019 | 36.4573 | 50.2506 | 142.0 |
0.6548 | 5.0 | 1990 | 0.8540 | 53.2987 | 34.6476 | 38.314 | 51.163 | 141.4815 |
0.504 | 6.0 | 2388 | 0.8395 | 52.7218 | 34.6524 | 37.9921 | 50.5185 | 141.5556 |
0.4006 | 7.0 | 2786 | 0.8342 | 53.2251 | 35.2702 | 38.3763 | 51.1958 | 141.6667 |
0.3314 | 8.0 | 3184 | 0.8329 | 53.3047 | 34.6219 | 37.6148 | 50.8973 | 141.8704 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 2.1.0
- Tokenizers 0.12.1