mongolian-bert-base-multilingual-cased-demo
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: 0.1375
- Precision: 0.9051
- Recall: 0.9203
- F1: 0.9126
- Accuracy: 0.9775
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 |
|---|---|---|---|---|---|---|---|
| 0.1747 | 1.0 | 477 | 0.1069 | 0.8431 | 0.8768 | 0.8596 | 0.9663 |
| 0.0845 | 2.0 | 954 | 0.0870 | 0.8887 | 0.9001 | 0.8944 | 0.9748 |
| 0.0591 | 3.0 | 1431 | 0.0987 | 0.8914 | 0.9059 | 0.8986 | 0.9730 |
| 0.0388 | 4.0 | 1908 | 0.1065 | 0.8928 | 0.9093 | 0.9010 | 0.9733 |
| 0.0278 | 5.0 | 2385 | 0.1173 | 0.8969 | 0.9150 | 0.9059 | 0.9760 |
| 0.0196 | 6.0 | 2862 | 0.1215 | 0.9050 | 0.9169 | 0.9109 | 0.9765 |
| 0.0142 | 7.0 | 3339 | 0.1229 | 0.9063 | 0.9183 | 0.9123 | 0.9771 |
| 0.01 | 8.0 | 3816 | 0.1283 | 0.9017 | 0.9159 | 0.9087 | 0.9767 |
| 0.0074 | 9.0 | 4293 | 0.1319 | 0.9066 | 0.9201 | 0.9133 | 0.9776 |
| 0.0051 | 10.0 | 4770 | 0.1375 | 0.9051 | 0.9203 | 0.9126 | 0.9775 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3