bert-base-multilingual-cased-Confusion-mlm-20230608
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: 0.87
- Loss: 0.5055
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: 10
Training results
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|---|---|---|---|---|
| No log | 1.0 | 130 | 0.8484 | 0.5758 |
| No log | 2.0 | 260 | 0.8732 | 0.4905 |
| No log | 3.0 | 390 | 0.8167 | 0.7089 |
| 0.7982 | 4.0 | 520 | 0.8218 | 0.6256 |
| 0.7982 | 5.0 | 650 | 0.8032 | 0.7806 |
| 0.7982 | 6.0 | 780 | 0.8786 | 0.5093 |
| 0.7982 | 7.0 | 910 | 0.8415 | 0.5859 |
| 0.7519 | 8.0 | 1040 | 0.8435 | 0.5756 |
| 0.7519 | 9.0 | 1170 | 0.8608 | 0.4605 |
| 0.7519 | 10.0 | 1300 | 0.87 | 0.5055 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3