<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
mn-cased-bert-base-named-entity
This model is a fine-tuned version of distilbert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1382
- Precision: 0.8816
- Recall: 0.9031
- F1: 0.8922
- Accuracy: 0.9729
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: 16
- eval_batch_size: 32
- 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 | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2157 | 1.0 | 477 | 0.1347 | 0.7747 | 0.8399 | 0.8060 | 0.9544 |
| 0.103 | 2.0 | 954 | 0.1062 | 0.8510 | 0.8853 | 0.8678 | 0.9677 |
| 0.0673 | 3.0 | 1431 | 0.1033 | 0.8549 | 0.8891 | 0.8717 | 0.9693 |
| 0.048 | 4.0 | 1908 | 0.1110 | 0.8610 | 0.8920 | 0.8762 | 0.9690 |
| 0.0347 | 5.0 | 2385 | 0.1175 | 0.8731 | 0.8967 | 0.8848 | 0.9715 |
| 0.0256 | 6.0 | 2862 | 0.1209 | 0.8741 | 0.9021 | 0.8879 | 0.9728 |
| 0.0183 | 7.0 | 3339 | 0.1219 | 0.8765 | 0.9004 | 0.8883 | 0.9732 |
| 0.0133 | 8.0 | 3816 | 0.1296 | 0.8799 | 0.9036 | 0.8916 | 0.9726 |
| 0.011 | 9.0 | 4293 | 0.1375 | 0.8779 | 0.9031 | 0.8903 | 0.9726 |
| 0.009 | 10.0 | 4770 | 0.1382 | 0.8816 | 0.9031 | 0.8922 | 0.9729 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
