<!-- 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-weaksup-1000-earlystop
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: 1.9095
- Rouge1: 27.9262
- Rouge2: 11.895
- Rougel: 21.4029
- Rougelsum: 24.7805
- Gen Len: 67.68
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 |
|---|---|---|---|---|---|---|---|---|
| 1.502 | 1.0 | 1000 | 1.7405 | 26.5705 | 11.4807 | 20.1226 | 23.6827 | 66.73 |
| 0.7337 | 2.0 | 2000 | 1.9095 | 27.9262 | 11.895 | 21.4029 | 24.7805 | 67.68 |
Framework versions
- Transformers 4.16.2
- Pytorch 1.10.2
- Datasets 1.18.3
- Tokenizers 0.11.0
