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: 0.1372
- Precision: 0.9235
- Recall: 0.9342
- F1: 0.9288
- Accuracy: 0.9800
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 |
|---|---|---|---|---|---|---|---|
| 0.1652 | 1.0 | 477 | 0.0832 | 0.8915 | 0.9136 | 0.9024 | 0.9762 |
| 0.0512 | 2.0 | 954 | 0.0828 | 0.9071 | 0.9244 | 0.9156 | 0.9778 |
| 0.0268 | 3.0 | 1431 | 0.0909 | 0.9179 | 0.9274 | 0.9226 | 0.9787 |
| 0.0146 | 4.0 | 1908 | 0.0975 | 0.9217 | 0.9322 | 0.9269 | 0.9798 |
| 0.008 | 5.0 | 2385 | 0.1127 | 0.9178 | 0.9313 | 0.9245 | 0.9793 |
| 0.0053 | 6.0 | 2862 | 0.1255 | 0.9207 | 0.9295 | 0.9251 | 0.9790 |
| 0.0034 | 7.0 | 3339 | 0.1292 | 0.9235 | 0.9335 | 0.9285 | 0.9797 |
| 0.0024 | 8.0 | 3816 | 0.1339 | 0.9186 | 0.9332 | 0.9258 | 0.9795 |
| 0.0015 | 9.0 | 4293 | 0.1359 | 0.9239 | 0.9343 | 0.9291 | 0.9800 |
| 0.0011 | 10.0 | 4770 | 0.1372 | 0.9235 | 0.9342 | 0.9288 | 0.9800 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1