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: 0.1834
- Precision: 0.6839
- Recall: 0.7644
- F1: 0.7219
- Accuracy: 0.9459
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 |
|---|---|---|---|---|---|---|---|
| 0.7672 | 1.0 | 20 | 0.5162 | 0.0825 | 0.0401 | 0.0540 | 0.8256 |
| 0.3886 | 2.0 | 40 | 0.3017 | 0.4778 | 0.5113 | 0.4939 | 0.9061 |
| 0.2163 | 3.0 | 60 | 0.2214 | 0.5543 | 0.6266 | 0.5882 | 0.9225 |
| 0.1199 | 4.0 | 80 | 0.1942 | 0.6346 | 0.7268 | 0.6776 | 0.9359 |
| 0.0742 | 5.0 | 100 | 0.1852 | 0.6396 | 0.7293 | 0.6815 | 0.9409 |
| 0.0555 | 6.0 | 120 | 0.1811 | 0.6943 | 0.7569 | 0.7242 | 0.9449 |
| 0.0407 | 7.0 | 140 | 0.1860 | 0.6804 | 0.7469 | 0.7121 | 0.9439 |
| 0.0346 | 8.0 | 160 | 0.1876 | 0.6952 | 0.7544 | 0.7236 | 0.9463 |
| 0.0302 | 9.0 | 180 | 0.1820 | 0.6868 | 0.7694 | 0.7258 | 0.9459 |
| 0.0289 | 10.0 | 200 | 0.1834 | 0.6839 | 0.7644 | 0.7219 | 0.9459 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1