results
This model is a fine-tuned version of bert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0189
- Accuracy: 0.9981
- F1: 0.9981
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 260 | 0.1823 | 0.9597 | 0.9601 |
| 0.1563 | 2.0 | 520 | 0.0255 | 0.9962 | 0.9962 |
| 0.1563 | 3.0 | 780 | 0.0359 | 0.9942 | 0.9943 |
| 0.0358 | 4.0 | 1040 | 0.0373 | 0.9942 | 0.9943 |
| 0.0358 | 5.0 | 1300 | 0.0135 | 0.9981 | 0.9981 |
| 0.0216 | 6.0 | 1560 | 0.0151 | 0.9981 | 0.9981 |
| 0.0216 | 7.0 | 1820 | 0.0177 | 0.9981 | 0.9981 |
| 0.0022 | 8.0 | 2080 | 0.0184 | 0.9981 | 0.9981 |
| 0.0022 | 9.0 | 2340 | 0.0187 | 0.9981 | 0.9981 |
| 0.0015 | 10.0 | 2600 | 0.0189 | 0.9981 | 0.9981 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.4.0+cu121
- Tokenizers 0.19.1