<!-- 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-aprischa2
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: 0.3425
- Rouge1: 65.7088
- Rouge2: 56.6701
- Rougel: 62.1926
- Rougelsum: 64.7727
- Gen Len: 140.8469
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: 3e-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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 0.3772 | 1.0 | 5403 | 0.3586 | 65.7702 | 56.7968 | 62.264 | 64.8605 | 140.268 |
| 0.316 | 2.0 | 10806 | 0.3421 | 64.8238 | 55.8837 | 61.3245 | 63.8894 | 140.7472 |
| 0.2397 | 3.0 | 16209 | 0.3425 | 65.7088 | 56.6701 | 62.1926 | 64.7727 | 140.8469 |
Framework versions
- Transformers 4.19.4
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1
