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: 0.1398
- Precision: 0.9283
- Recall: 0.9354
- F1: 0.9318
- Accuracy: 0.9798
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 |
|---|---|---|---|---|---|---|---|
| 0.171 | 1.0 | 477 | 0.0779 | 0.9033 | 0.9178 | 0.9105 | 0.9767 |
| 0.0532 | 2.0 | 954 | 0.0857 | 0.9076 | 0.9247 | 0.9161 | 0.9773 |
| 0.0292 | 3.0 | 1431 | 0.0917 | 0.9229 | 0.9300 | 0.9264 | 0.9794 |
| 0.0178 | 4.0 | 1908 | 0.1063 | 0.9264 | 0.9317 | 0.9291 | 0.9789 |
| 0.0101 | 5.0 | 2385 | 0.1097 | 0.9240 | 0.9318 | 0.9279 | 0.9792 |
| 0.0062 | 6.0 | 2862 | 0.1205 | 0.9257 | 0.9333 | 0.9295 | 0.9794 |
| 0.0034 | 7.0 | 3339 | 0.1278 | 0.9262 | 0.9337 | 0.9300 | 0.9790 |
| 0.0028 | 8.0 | 3816 | 0.1335 | 0.9257 | 0.9333 | 0.9295 | 0.9793 |
| 0.002 | 9.0 | 4293 | 0.1397 | 0.9299 | 0.9365 | 0.9332 | 0.9798 |
| 0.0014 | 10.0 | 4770 | 0.1398 | 0.9283 | 0.9354 | 0.9318 | 0.9798 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1