<!-- 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. -->
_1_bert-base-multilingual-cased-ner
This model is a fine-tuned version of bert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0333
- Precision: 0.9752
- Recall: 0.9772
- F1: 0.9762
- Accuracy: 0.9941
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 |
---|---|---|---|---|---|---|---|
0.1721 | 1.0 | 477 | 0.0847 | 0.8812 | 0.9006 | 0.8908 | 0.9744 |
0.0846 | 2.0 | 954 | 0.0547 | 0.9212 | 0.9344 | 0.9277 | 0.9835 |
0.0564 | 3.0 | 1431 | 0.0450 | 0.9393 | 0.9494 | 0.9443 | 0.9865 |
0.0383 | 4.0 | 1908 | 0.0420 | 0.9489 | 0.9612 | 0.9550 | 0.9889 |
0.029 | 5.0 | 2385 | 0.0380 | 0.9609 | 0.9659 | 0.9634 | 0.9910 |
0.0184 | 6.0 | 2862 | 0.0335 | 0.9676 | 0.9729 | 0.9703 | 0.9929 |
0.0131 | 7.0 | 3339 | 0.0335 | 0.9699 | 0.9737 | 0.9718 | 0.9932 |
0.0091 | 8.0 | 3816 | 0.0331 | 0.9741 | 0.9770 | 0.9755 | 0.9941 |
0.0061 | 9.0 | 4293 | 0.0332 | 0.9748 | 0.9773 | 0.9760 | 0.9941 |
0.0046 | 10.0 | 4770 | 0.0333 | 0.9752 | 0.9772 | 0.9762 | 0.9941 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3