bart-paraphrase-v0.75-e1
This model is a fine-tuned version of eugenesiow/bart-paraphrase on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1865
- Rouge1: 71.3427
- Rouge2: 66.0011
- Rougel: 69.8855
- Rougelsum: 69.9796
- Gen Len: 19.6036
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: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 0.1373 | 1.0 | 2660 | 0.1865 | 71.3427 | 66.0011 | 69.8855 | 69.9796 | 19.6036 |
Framework versions
- Transformers 4.21.1
- Pytorch 1.12.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1