mongolian-bert-base-multilingual-cased
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: 0.1494
- Precision: 0.9081
- Recall: 0.9177
- F1: 0.9129
- Accuracy: 0.9751
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: 9
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.1721 | 1.0 | 477 | 0.1096 | 0.8521 | 0.8801 | 0.8659 | 0.9667 |
0.085 | 2.0 | 954 | 0.1071 | 0.8782 | 0.9002 | 0.8891 | 0.9704 |
0.0572 | 3.0 | 1431 | 0.1015 | 0.8902 | 0.9095 | 0.8998 | 0.9737 |
0.0394 | 4.0 | 1908 | 0.1091 | 0.8978 | 0.9119 | 0.9048 | 0.9739 |
0.0276 | 5.0 | 2385 | 0.1224 | 0.9055 | 0.9174 | 0.9114 | 0.9744 |
0.0187 | 6.0 | 2862 | 0.1324 | 0.9032 | 0.9152 | 0.9092 | 0.9744 |
0.0126 | 7.0 | 3339 | 0.1426 | 0.9013 | 0.9152 | 0.9082 | 0.9737 |
0.0087 | 8.0 | 3816 | 0.1495 | 0.9040 | 0.9160 | 0.9100 | 0.9748 |
0.0064 | 9.0 | 4293 | 0.1494 | 0.9081 | 0.9177 | 0.9129 | 0.9751 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 4
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.