bert-base-multilingual-cased-mongolian-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: 0.1423
- Precision: 0.9057
- Recall: 0.9188
- F1: 0.9122
- Accuracy: 0.9753
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 |
---|---|---|---|---|---|---|---|
0.1726 | 1.0 | 477 | 0.1052 | 0.8531 | 0.8851 | 0.8688 | 0.9664 |
0.0827 | 2.0 | 954 | 0.0975 | 0.8722 | 0.8987 | 0.8852 | 0.9699 |
0.0571 | 3.0 | 1431 | 0.0926 | 0.8847 | 0.9054 | 0.8950 | 0.9719 |
0.0376 | 4.0 | 1908 | 0.1052 | 0.8980 | 0.9119 | 0.9049 | 0.9727 |
0.0271 | 5.0 | 2385 | 0.1137 | 0.9021 | 0.9158 | 0.9089 | 0.9746 |
0.0182 | 6.0 | 2862 | 0.1304 | 0.8839 | 0.9106 | 0.8970 | 0.9712 |
0.0145 | 7.0 | 3339 | 0.1274 | 0.9042 | 0.9187 | 0.9114 | 0.9748 |
0.0097 | 8.0 | 3816 | 0.1375 | 0.9009 | 0.9169 | 0.9088 | 0.9739 |
0.0063 | 9.0 | 4293 | 0.1421 | 0.9017 | 0.9171 | 0.9093 | 0.9748 |
0.0049 | 10.0 | 4770 | 0.1423 | 0.9057 | 0.9188 | 0.9122 | 0.9753 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 2
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.