results
This model is a fine-tuned version of google/mobilebert-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2886
- F1: 0.9354
- Accuracy: 0.9356
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: 32
- eval_batch_size: 32
- 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: 100
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy |
|---|---|---|---|---|---|
| No log | 1.0 | 71 | 0.3981 | 0.7807 | 0.7859 |
| 543354.96 | 2.0 | 142 | 0.2793 | 0.8721 | 0.8732 |
| 0.8191 | 3.0 | 213 | 0.2847 | 0.8909 | 0.8919 |
| 0.8191 | 4.0 | 284 | 0.1965 | 0.9354 | 0.9356 |
| 0.1638 | 5.0 | 355 | 0.1254 | 0.9542 | 0.9543 |
| 0.1101 | 6.0 | 426 | 0.1708 | 0.9397 | 0.9397 |
| 0.1101 | 7.0 | 497 | 0.1486 | 0.9647 | 0.9647 |
| 0.078 | 8.0 | 568 | 0.2118 | 0.9563 | 0.9563 |
| 0.034 | 9.0 | 639 | 0.2886 | 0.9354 | 0.9356 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.2