results
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.6326
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.698 | 1.0 | 58 | 1.6997 |
| 0.4508 | 2.0 | 116 | 1.6643 |
| 0.5186 | 3.0 | 174 | 1.6642 |
| 0.5859 | 4.0 | 232 | 1.6326 |
| 0.3736 | 5.0 | 290 | 1.6461 |
| 0.3481 | 6.0 | 348 | 1.6719 |
| 0.3988 | 7.0 | 406 | 1.6405 |
| 0.3192 | 8.0 | 464 | 1.6538 |
| 0.309 | 9.0 | 522 | 1.6447 |
| 0.2895 | 10.0 | 580 | 1.6459 |
| 0.2121 | 11.0 | 638 | 1.6497 |
| 0.2757 | 12.0 | 696 | 1.6527 |
| 0.2861 | 13.0 | 754 | 1.6522 |
| 0.2159 | 14.0 | 812 | 1.6559 |
| 0.3028 | 15.0 | 870 | 1.6541 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0