|
--- |
|
language: |
|
- mn |
|
base_model: tergel/bert-base-mongolian-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: bert-base-mongolian-uncased-ner |
|
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. --> |
|
|
|
# bert-base-mongolian-uncased-ner |
|
|
|
This model is a fine-tuned version of [tergel/bert-base-mongolian-uncased](https://huggingface.co/tergel/bert-base-mongolian-uncased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1610 |
|
- Precision: 0.8207 |
|
- Recall: 0.8426 |
|
- F1: 0.8315 |
|
- Accuracy: 0.9593 |
|
|
|
## 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: 256 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.3447 | 1.0 | 60 | 0.1578 | 0.7339 | 0.7793 | 0.7559 | 0.9468 | |
|
| 0.136 | 2.0 | 120 | 0.1348 | 0.7915 | 0.8026 | 0.7970 | 0.9545 | |
|
| 0.0997 | 3.0 | 180 | 0.1325 | 0.8020 | 0.8288 | 0.8152 | 0.9570 | |
|
| 0.0761 | 4.0 | 240 | 0.1351 | 0.8086 | 0.8310 | 0.8196 | 0.9584 | |
|
| 0.0595 | 5.0 | 300 | 0.1396 | 0.8173 | 0.8334 | 0.8253 | 0.9591 | |
|
| 0.0485 | 6.0 | 360 | 0.1455 | 0.8084 | 0.8313 | 0.8197 | 0.9576 | |
|
| 0.0399 | 7.0 | 420 | 0.1548 | 0.8135 | 0.8377 | 0.8254 | 0.9581 | |
|
| 0.0354 | 8.0 | 480 | 0.1586 | 0.8179 | 0.8407 | 0.8292 | 0.9587 | |
|
| 0.0315 | 9.0 | 540 | 0.1599 | 0.8165 | 0.8414 | 0.8288 | 0.9587 | |
|
| 0.0283 | 10.0 | 600 | 0.1610 | 0.8207 | 0.8426 | 0.8315 | 0.9593 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
