|
--- |
|
language: |
|
- mn |
|
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-mongolian-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: 0.1225 |
|
- Precision: 0.9338 |
|
- Recall: 0.9396 |
|
- F1: 0.9367 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.169 | 1.0 | 477 | 0.0846 | 0.8408 | 0.8852 | 0.8625 | 0.9713 | |
|
| 0.0586 | 2.0 | 954 | 0.0753 | 0.9263 | 0.9347 | 0.9305 | 0.9801 | |
|
| 0.0288 | 3.0 | 1431 | 0.0813 | 0.9262 | 0.9355 | 0.9308 | 0.9808 | |
|
| 0.0158 | 4.0 | 1908 | 0.0937 | 0.9318 | 0.9384 | 0.9351 | 0.9814 | |
|
| 0.0102 | 5.0 | 2385 | 0.0967 | 0.9331 | 0.9386 | 0.9358 | 0.9820 | |
|
| 0.006 | 6.0 | 2862 | 0.1072 | 0.9318 | 0.9382 | 0.9350 | 0.9817 | |
|
| 0.0046 | 7.0 | 3339 | 0.1139 | 0.9354 | 0.9408 | 0.9381 | 0.9821 | |
|
| 0.0025 | 8.0 | 3816 | 0.1185 | 0.9341 | 0.9402 | 0.9371 | 0.9820 | |
|
| 0.0021 | 9.0 | 4293 | 0.1217 | 0.9347 | 0.9397 | 0.9372 | 0.9819 | |
|
| 0.0011 | 10.0 | 4770 | 0.1225 | 0.9338 | 0.9396 | 0.9367 | 0.9818 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.29.2 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
