|
--- |
|
base_model: NlpHUST/ner-vietnamese-electra-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: my_awesome_ner-token_classification_v1.0 |
|
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. --> |
|
|
|
# my_awesome_ner-token_classification_v1.0 |
|
|
|
This model is a fine-tuned version of [NlpHUST/ner-vietnamese-electra-base](https://huggingface.co/NlpHUST/ner-vietnamese-electra-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.0322 |
|
- Precision: 0.4590 |
|
- Recall: 0.5400 |
|
- F1: 0.4963 |
|
- Accuracy: 0.7805 |
|
|
|
## 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: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- num_epochs: 20 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.8701 | 1.9929 | 562 | 0.8431 | 0.4537 | 0.4154 | 0.4337 | 0.7907 | |
|
| 0.5651 | 3.9858 | 1124 | 0.7613 | 0.4524 | 0.4899 | 0.4704 | 0.7898 | |
|
| 0.4312 | 5.9787 | 1686 | 0.8134 | 0.4654 | 0.5182 | 0.4904 | 0.7902 | |
|
| 0.3305 | 7.9716 | 2248 | 0.8743 | 0.4417 | 0.5336 | 0.4833 | 0.7762 | |
|
| 0.255 | 9.9645 | 2810 | 0.9331 | 0.4217 | 0.5375 | 0.4726 | 0.7694 | |
|
| 0.2071 | 11.9574 | 3372 | 0.9707 | 0.4527 | 0.5435 | 0.4940 | 0.7795 | |
|
| 0.1984 | 13.9504 | 3934 | 0.9967 | 0.4663 | 0.5336 | 0.4977 | 0.7834 | |
|
| 0.1702 | 15.9433 | 4496 | 1.0322 | 0.4590 | 0.5400 | 0.4963 | 0.7805 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.19.2 |
|
- Tokenizers 0.19.1 |
|
|