<!-- 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-v3-e2
This model is a fine-tuned version of theojolliffe/bart-cnn-pubmed-arxiv-pubmed on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9021
- Rouge1: 53.515
- Rouge2: 33.4314
- Rougel: 35.1718
- Rougelsum: 50.8086
- Gen Len: 141.7963
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: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 398 | 0.9656 | 52.7601 | 33.0555 | 34.4738 | 50.449 | 142.0 |
| 1.1333 | 2.0 | 796 | 0.9021 | 53.515 | 33.4314 | 35.1718 | 50.8086 | 141.7963 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 2.1.0
- Tokenizers 0.12.1
