Bart_classifier_2
This model is a fine-tuned version of facebook/bart-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3874
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: 5e-05
- train_batch_size: 48
- eval_batch_size: 48
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2769 | 1.0 | 131 | 0.1763 |
| 0.1895 | 2.0 | 262 | 0.1550 |
| 0.1691 | 3.0 | 393 | 0.1644 |
| 0.1746 | 4.0 | 524 | 0.2206 |
| 0.1151 | 5.0 | 655 | 0.1611 |
| 0.1124 | 6.0 | 786 | 0.2018 |
| 0.0651 | 7.0 | 917 | 0.2303 |
| 0.0514 | 8.0 | 1048 | 0.2463 |
| 0.0327 | 9.0 | 1179 | 0.3513 |
| 0.0185 | 10.0 | 1310 | 0.3874 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1