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: 0.1231
- Precision: 0.9199
- Recall: 0.9222
- F1: 0.9210
- Accuracy: 0.9811
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 |
|---|---|---|---|---|---|---|---|
| 0.1804 | 1.0 | 477 | 0.0823 | 0.8069 | 0.8646 | 0.8347 | 0.9712 |
| 0.0667 | 2.0 | 954 | 0.0779 | 0.8221 | 0.8807 | 0.8504 | 0.9738 |
| 0.0392 | 3.0 | 1431 | 0.0953 | 0.8444 | 0.8853 | 0.8644 | 0.9744 |
| 0.0205 | 4.0 | 1908 | 0.0942 | 0.9201 | 0.9148 | 0.9175 | 0.9802 |
| 0.0113 | 5.0 | 2385 | 0.1011 | 0.9168 | 0.9213 | 0.9191 | 0.9812 |
| 0.0093 | 6.0 | 2862 | 0.1053 | 0.9087 | 0.9183 | 0.9135 | 0.9805 |
| 0.007 | 7.0 | 3339 | 0.1162 | 0.9211 | 0.9213 | 0.9212 | 0.9815 |
| 0.0037 | 8.0 | 3816 | 0.1230 | 0.9167 | 0.9202 | 0.9185 | 0.9806 |
| 0.0025 | 9.0 | 4293 | 0.1215 | 0.9198 | 0.9229 | 0.9213 | 0.9813 |
| 0.0022 | 10.0 | 4770 | 0.1231 | 0.9199 | 0.9222 | 0.9210 | 0.9811 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1