bart-base-finetuned-kaggglenews-fact-corrector-I
This model is a fine-tuned version of facebook/bart-base on the None dataset.
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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 432 | 1.5483 | 28.9811 | 16.5711 | 24.7826 | 26.4132 | 20.0 |
Framework versions
- Transformers 4.12.5
- Pytorch 1.10.0+cu102
- Datasets 1.16.1
- Tokenizers 0.10.3