|
|
--- |
|
|
language: |
|
|
- mn |
|
|
base_model: bayartsogt/mongolian-roberta-base |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- precision |
|
|
- recall |
|
|
- f1 |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: roberta-base-ner-test-2 |
|
|
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-test-2 |
|
|
|
|
|
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: 0.1207 |
|
|
- Precision: 0.9273 |
|
|
- Recall: 0.9357 |
|
|
- F1: 0.9315 |
|
|
- Accuracy: 0.9802 |
|
|
|
|
|
## 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: 128 |
|
|
- eval_batch_size: 64 |
|
|
- 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 | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
|
| 0.0259 | 1.0 | 60 | 0.0856 | 0.9222 | 0.9308 | 0.9265 | 0.9792 | |
|
|
| 0.0145 | 2.0 | 120 | 0.0951 | 0.9200 | 0.9296 | 0.9248 | 0.9788 | |
|
|
| 0.0104 | 3.0 | 180 | 0.1018 | 0.9143 | 0.9303 | 0.9222 | 0.9784 | |
|
|
| 0.0073 | 4.0 | 240 | 0.1062 | 0.9224 | 0.9319 | 0.9272 | 0.9791 | |
|
|
| 0.0068 | 5.0 | 300 | 0.1133 | 0.9246 | 0.9340 | 0.9293 | 0.9794 | |
|
|
| 0.0108 | 6.0 | 360 | 0.1055 | 0.9207 | 0.9306 | 0.9256 | 0.9788 | |
|
|
| 0.0078 | 7.0 | 420 | 0.1170 | 0.9207 | 0.9334 | 0.9270 | 0.9786 | |
|
|
| 0.0061 | 8.0 | 480 | 0.1114 | 0.9226 | 0.9348 | 0.9286 | 0.9803 | |
|
|
| 0.005 | 9.0 | 540 | 0.1165 | 0.9255 | 0.9341 | 0.9298 | 0.9798 | |
|
|
| 0.0038 | 10.0 | 600 | 0.1207 | 0.9273 | 0.9357 | 0.9315 | 0.9802 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.39.3 |
|
|
- Pytorch 2.1.2 |
|
|
- Datasets 2.18.0 |
|
|
- Tokenizers 0.15.2 |
|
|
|
