mongolian-davlan-xlm-roberta-base-ner-hrl
This model is a fine-tuned version of Davlan/xlm-roberta-base-ner-hrl on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1166
- Precision: 0.9265
- Recall: 0.9340
- F1: 0.9303
- Accuracy: 0.9798
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 |
|---|---|---|---|---|---|---|---|
| 0.159 | 1.0 | 477 | 0.0792 | 0.9061 | 0.9167 | 0.9114 | 0.9764 |
| 0.0754 | 2.0 | 954 | 0.0721 | 0.9142 | 0.9257 | 0.9199 | 0.9783 |
| 0.0515 | 3.0 | 1431 | 0.0803 | 0.9189 | 0.9317 | 0.9253 | 0.9787 |
| 0.0374 | 4.0 | 1908 | 0.0758 | 0.9295 | 0.9353 | 0.9324 | 0.9804 |
| 0.0279 | 5.0 | 2385 | 0.0912 | 0.9267 | 0.9340 | 0.9304 | 0.9796 |
| 0.0214 | 6.0 | 2862 | 0.0993 | 0.9256 | 0.9325 | 0.9290 | 0.9796 |
| 0.0159 | 7.0 | 3339 | 0.1078 | 0.9237 | 0.9327 | 0.9282 | 0.9789 |
| 0.0122 | 8.0 | 3816 | 0.1108 | 0.9259 | 0.9347 | 0.9303 | 0.9797 |
| 0.0102 | 9.0 | 4293 | 0.1147 | 0.9263 | 0.9348 | 0.9305 | 0.9797 |
| 0.0077 | 10.0 | 4770 | 0.1166 | 0.9265 | 0.9340 | 0.9303 | 0.9798 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 31
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.