<!-- 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-large-cnn-finetuned-new-100-pad-early
This model is a fine-tuned version of facebook/bart-large-cnn on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9543
- Rouge1: 21.8858
- Rouge2: 8.1444
- Rougel: 16.5751
- Rougelsum: 19.163
- Gen Len: 66.8
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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 100 | 0.8692 | 20.2714 | 6.206 | 16.3362 | 18.7117 | 66.4 |
| No log | 2.0 | 200 | 0.9543 | 21.8858 | 8.1444 | 16.5751 | 19.163 | 66.8 |
Framework versions
- Transformers 4.16.2
- Pytorch 1.10.2
- Datasets 1.18.3
- Tokenizers 0.11.0
