|
--- |
|
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: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# roberta-base-ner-demo |
|
|
|
This model is a fine-tuned version of [bayartsogt/mongolian-roberta-base](https://huggingface.co/bayartsogt/mongolian-roberta-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1227 |
|
- Precision: 0.9299 |
|
- Recall: 0.9375 |
|
- F1: 0.9337 |
|
- Accuracy: 0.9818 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.1679 | 1.0 | 477 | 0.0860 | 0.8327 | 0.8878 | 0.8594 | 0.9716 | |
|
| 0.0622 | 2.0 | 954 | 0.0739 | 0.9227 | 0.9300 | 0.9264 | 0.9807 | |
|
| 0.029 | 3.0 | 1431 | 0.0770 | 0.9241 | 0.9347 | 0.9294 | 0.9820 | |
|
| 0.0159 | 4.0 | 1908 | 0.0877 | 0.9327 | 0.9397 | 0.9362 | 0.9824 | |
|
| 0.0091 | 5.0 | 2385 | 0.1074 | 0.9253 | 0.9324 | 0.9288 | 0.9805 | |
|
| 0.0054 | 6.0 | 2862 | 0.1114 | 0.9277 | 0.9363 | 0.9320 | 0.9812 | |
|
| 0.0042 | 7.0 | 3339 | 0.1137 | 0.9289 | 0.9359 | 0.9324 | 0.9815 | |
|
| 0.0026 | 8.0 | 3816 | 0.1203 | 0.9301 | 0.9368 | 0.9334 | 0.9819 | |
|
| 0.0021 | 9.0 | 4293 | 0.1222 | 0.9291 | 0.9373 | 0.9332 | 0.9818 | |
|
| 0.0014 | 10.0 | 4770 | 0.1227 | 0.9299 | 0.9375 | 0.9337 | 0.9818 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.1 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |
|
|
