roberta-base-ner-demo
This model is a fine-tuned version of bayartsogt/mongolian-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1263
- Precision: 0.9352
- Recall: 0.9416
- F1: 0.9384
- Accuracy: 0.9817
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 |
---|---|---|---|---|---|---|---|
0.161 | 1.0 | 477 | 0.0722 | 0.9132 | 0.9248 | 0.9190 | 0.9786 |
0.052 | 2.0 | 954 | 0.0732 | 0.9211 | 0.9353 | 0.9282 | 0.9797 |
0.028 | 3.0 | 1431 | 0.0802 | 0.9280 | 0.9354 | 0.9317 | 0.9804 |
0.015 | 4.0 | 1908 | 0.0954 | 0.9190 | 0.9324 | 0.9257 | 0.9791 |
0.0101 | 5.0 | 2385 | 0.0978 | 0.9312 | 0.9385 | 0.9348 | 0.9809 |
0.0055 | 6.0 | 2862 | 0.1072 | 0.9315 | 0.9392 | 0.9353 | 0.9810 |
0.0035 | 7.0 | 3339 | 0.1165 | 0.9313 | 0.9392 | 0.9352 | 0.9807 |
0.0026 | 8.0 | 3816 | 0.1223 | 0.9338 | 0.9403 | 0.9371 | 0.9812 |
0.002 | 9.0 | 4293 | 0.1234 | 0.9341 | 0.9398 | 0.9369 | 0.9813 |
0.0009 | 10.0 | 4770 | 0.1263 | 0.9352 | 0.9416 | 0.9384 | 0.9817 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 7
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.