metadata
language:
- mn
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: mongolian-bert-base-multilingual-cased-ner
results: []
mongolian-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: 0.1399
- Precision: 0.9072
- Recall: 0.9189
- F1: 0.9131
- Accuracy: 0.9759
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 |
|---|---|---|---|---|---|---|---|
| 0.1794 | 1.0 | 477 | 0.1089 | 0.8606 | 0.8871 | 0.8737 | 0.9685 |
| 0.0859 | 2.0 | 954 | 0.0978 | 0.8734 | 0.8973 | 0.8852 | 0.9703 |
| 0.0597 | 3.0 | 1431 | 0.0959 | 0.8970 | 0.9080 | 0.9025 | 0.9749 |
| 0.042 | 4.0 | 1908 | 0.1032 | 0.9008 | 0.9167 | 0.9087 | 0.9751 |
| 0.028 | 5.0 | 2385 | 0.1177 | 0.9011 | 0.9157 | 0.9083 | 0.9755 |
| 0.02 | 6.0 | 2862 | 0.1239 | 0.9048 | 0.9150 | 0.9099 | 0.9749 |
| 0.0143 | 7.0 | 3339 | 0.1289 | 0.9045 | 0.9168 | 0.9106 | 0.9749 |
| 0.009 | 8.0 | 3816 | 0.1376 | 0.9037 | 0.9171 | 0.9103 | 0.9755 |
| 0.0068 | 9.0 | 4293 | 0.1372 | 0.9067 | 0.9188 | 0.9127 | 0.9763 |
| 0.0053 | 10.0 | 4770 | 0.1399 | 0.9072 | 0.9189 | 0.9131 | 0.9759 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3