<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
mn-roberta-base-demo-named-entity
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: 0.1354
- Precision: 0.9239
- Recall: 0.9322
- F1: 0.9280
- Accuracy: 0.9797
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 |
|---|---|---|---|---|---|---|---|
| 0.1651 | 1.0 | 477 | 0.0835 | 0.8900 | 0.9145 | 0.9021 | 0.9745 |
| 0.0535 | 2.0 | 954 | 0.0780 | 0.9047 | 0.9243 | 0.9144 | 0.9775 |
| 0.0267 | 3.0 | 1431 | 0.0836 | 0.9184 | 0.9307 | 0.9245 | 0.9790 |
| 0.0159 | 4.0 | 1908 | 0.0936 | 0.9224 | 0.9329 | 0.9276 | 0.9803 |
| 0.0083 | 5.0 | 2385 | 0.1155 | 0.9224 | 0.9307 | 0.9265 | 0.9790 |
| 0.0055 | 6.0 | 2862 | 0.1211 | 0.9222 | 0.9316 | 0.9268 | 0.9793 |
| 0.0034 | 7.0 | 3339 | 0.1258 | 0.9199 | 0.9329 | 0.9263 | 0.9789 |
| 0.0025 | 8.0 | 3816 | 0.1300 | 0.9249 | 0.9339 | 0.9294 | 0.9799 |
| 0.002 | 9.0 | 4293 | 0.1352 | 0.9231 | 0.9313 | 0.9272 | 0.9795 |
| 0.0018 | 10.0 | 4770 | 0.1354 | 0.9239 | 0.9322 | 0.9280 | 0.9797 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
