my_wikilingua_model_bart1
This model is a fine-tuned version of sshleifer/distilbart-xsum-12-3 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.9696
- Rouge1: 0.3492
- Rouge2: 0.1355
- Rougel: 0.2783
- Rougelsum: 0.2786
- Gen Len: 26.975
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: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 3.65 | 1.0 | 800 | 3.0221 | 0.3017 | 0.1156 | 0.2432 | 0.2433 | 22.085 |
| 2.7107 | 2.0 | 1600 | 2.9341 | 0.3424 | 0.1313 | 0.2686 | 0.2689 | 25.65 |
| 2.3206 | 3.0 | 2400 | 2.9409 | 0.3522 | 0.1348 | 0.2779 | 0.2779 | 27.8725 |
| 2.0027 | 4.0 | 3200 | 2.9696 | 0.3492 | 0.1355 | 0.2783 | 0.2786 | 26.975 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3