testing_mongolian-roberta_base
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: 0.1244
- Precision: 0.9311
- Recall: 0.9399
- F1: 0.9355
- Accuracy: 0.9821
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 |
|---|---|---|---|---|---|---|---|
| 0.1683 | 1.0 | 477 | 0.0805 | 0.8377 | 0.8921 | 0.8640 | 0.9730 |
| 0.0545 | 2.0 | 954 | 0.0739 | 0.9205 | 0.9334 | 0.9269 | 0.9806 |
| 0.0292 | 3.0 | 1431 | 0.0778 | 0.9270 | 0.9354 | 0.9312 | 0.9817 |
| 0.0164 | 4.0 | 1908 | 0.0884 | 0.9290 | 0.9360 | 0.9325 | 0.9820 |
| 0.008 | 5.0 | 2385 | 0.1025 | 0.9247 | 0.9365 | 0.9306 | 0.9811 |
| 0.0057 | 6.0 | 2862 | 0.1093 | 0.9294 | 0.9369 | 0.9331 | 0.9815 |
| 0.0037 | 7.0 | 3339 | 0.1173 | 0.9336 | 0.9412 | 0.9374 | 0.9822 |
| 0.0026 | 8.0 | 3816 | 0.1217 | 0.9281 | 0.9374 | 0.9327 | 0.9817 |
| 0.0016 | 9.0 | 4293 | 0.1225 | 0.9334 | 0.9399 | 0.9366 | 0.9821 |
| 0.0012 | 10.0 | 4770 | 0.1244 | 0.9311 | 0.9399 | 0.9355 | 0.9821 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+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.