bert-base-multilingual-cased-Confusion-mlm-20230605
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:
- Accuracy: 0.5221
- Loss: 1.8989
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|---|---|---|---|---|
| No log | 1.0 | 130 | 0.3587 | 2.8610 |
| No log | 2.0 | 260 | 0.4649 | 2.3133 |
| No log | 3.0 | 390 | 0.4307 | 2.4230 |
| 2.6029 | 4.0 | 520 | 0.4893 | 2.3436 |
| 2.6029 | 5.0 | 650 | 0.525 | 2.0247 |
| 2.6029 | 6.0 | 780 | 0.5116 | 2.1448 |
| 2.6029 | 7.0 | 910 | 0.5043 | 2.0569 |
| 2.0943 | 8.0 | 1040 | 0.5601 | 1.8873 |
| 2.0943 | 9.0 | 1170 | 0.5206 | 1.9879 |
| 2.0943 | 10.0 | 1300 | 0.5358 | 2.0974 |
| 2.0943 | 11.0 | 1430 | 0.5060 | 2.0974 |
| 1.8388 | 12.0 | 1560 | 0.5839 | 1.6869 |
| 1.8388 | 13.0 | 1690 | 0.5706 | 1.8915 |
| 1.8388 | 14.0 | 1820 | 0.5620 | 1.7826 |
| 1.8388 | 15.0 | 1950 | 0.5274 | 2.0275 |
| 1.7158 | 16.0 | 2080 | 0.5627 | 1.8270 |
| 1.7158 | 17.0 | 2210 | 0.5425 | 2.0630 |
| 1.7158 | 18.0 | 2340 | 0.5884 | 1.6747 |
| 1.7158 | 19.0 | 2470 | 0.55 | 1.8877 |
| 1.5481 | 20.0 | 2600 | 0.5221 | 1.8989 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3