metadata
language:
- mn
base_model: bayartsogt/mongolian-roberta-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: roberta-base-ner-demo
results: []
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: 0.1321
- Precision: 0.9301
- Recall: 0.9415
- F1: 0.9358
- Accuracy: 0.9804
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 |
|---|---|---|---|---|---|---|---|
| 0.1687 | 1.0 | 477 | 0.0866 | 0.8398 | 0.8904 | 0.8643 | 0.9712 |
| 0.0533 | 2.0 | 954 | 0.0790 | 0.9129 | 0.9279 | 0.9203 | 0.9777 |
| 0.0285 | 3.0 | 1431 | 0.0809 | 0.9263 | 0.9337 | 0.9300 | 0.9795 |
| 0.0164 | 4.0 | 1908 | 0.0932 | 0.9240 | 0.9374 | 0.9306 | 0.9794 |
| 0.0093 | 5.0 | 2385 | 0.1020 | 0.9281 | 0.9401 | 0.9341 | 0.9800 |
| 0.0055 | 6.0 | 2862 | 0.1137 | 0.9320 | 0.9424 | 0.9372 | 0.9808 |
| 0.0035 | 7.0 | 3339 | 0.1218 | 0.9265 | 0.9384 | 0.9325 | 0.9799 |
| 0.0026 | 8.0 | 3816 | 0.1240 | 0.9329 | 0.9422 | 0.9375 | 0.9809 |
| 0.0018 | 9.0 | 4293 | 0.1306 | 0.9297 | 0.9413 | 0.9355 | 0.9802 |
| 0.001 | 10.0 | 4770 | 0.1321 | 0.9301 | 0.9415 | 0.9358 | 0.9804 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1