|
--- |
|
base_model: UWB-AIR/Czert-B-base-cased |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- cnec |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: CNEC_2_0_ext_Czert-B-base-cased |
|
results: |
|
- task: |
|
name: Token Classification |
|
type: token-classification |
|
dataset: |
|
name: cnec |
|
type: cnec |
|
config: default |
|
split: validation |
|
args: default |
|
metrics: |
|
- name: Precision |
|
type: precision |
|
value: 0.8443598286530224 |
|
- name: Recall |
|
type: recall |
|
value: 0.8803970223325062 |
|
- name: F1 |
|
type: f1 |
|
value: 0.8620019436345967 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9639776213679841 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# CNEC_2_0_ext_Czert-B-base-cased |
|
|
|
This model is a fine-tuned version of [UWB-AIR/Czert-B-base-cased](https://huggingface.co/UWB-AIR/Czert-B-base-cased) on the cnec dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1904 |
|
- Precision: 0.8444 |
|
- Recall: 0.8804 |
|
- F1: 0.8620 |
|
- Accuracy: 0.9640 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.3858 | 0.56 | 500 | 0.1756 | 0.7393 | 0.7742 | 0.7564 | 0.9477 | |
|
| 0.1885 | 1.12 | 1000 | 0.1782 | 0.7596 | 0.8278 | 0.7922 | 0.9509 | |
|
| 0.1474 | 1.68 | 1500 | 0.1539 | 0.7979 | 0.8427 | 0.8197 | 0.9579 | |
|
| 0.1262 | 2.24 | 2000 | 0.1717 | 0.7965 | 0.8486 | 0.8217 | 0.9581 | |
|
| 0.1092 | 2.8 | 2500 | 0.1512 | 0.7994 | 0.8625 | 0.8298 | 0.9604 | |
|
| 0.0901 | 3.36 | 3000 | 0.1558 | 0.8204 | 0.8680 | 0.8435 | 0.9622 | |
|
| 0.0882 | 3.92 | 3500 | 0.1557 | 0.8187 | 0.8541 | 0.8360 | 0.9611 | |
|
| 0.0718 | 4.48 | 4000 | 0.1730 | 0.8134 | 0.8566 | 0.8344 | 0.9605 | |
|
| 0.0704 | 5.04 | 4500 | 0.1726 | 0.8225 | 0.8715 | 0.8463 | 0.9623 | |
|
| 0.0594 | 5.6 | 5000 | 0.1707 | 0.8318 | 0.8715 | 0.8512 | 0.9636 | |
|
| 0.0567 | 6.16 | 5500 | 0.1781 | 0.8377 | 0.8710 | 0.8540 | 0.9629 | |
|
| 0.0492 | 6.72 | 6000 | 0.1782 | 0.8410 | 0.8769 | 0.8586 | 0.9641 | |
|
| 0.0437 | 7.28 | 6500 | 0.1883 | 0.8365 | 0.8734 | 0.8546 | 0.9625 | |
|
| 0.0449 | 7.84 | 7000 | 0.1818 | 0.8439 | 0.8774 | 0.8603 | 0.9640 | |
|
| 0.0421 | 8.4 | 7500 | 0.1927 | 0.8343 | 0.8720 | 0.8527 | 0.9632 | |
|
| 0.0357 | 8.96 | 8000 | 0.1848 | 0.8463 | 0.8824 | 0.8639 | 0.9647 | |
|
| 0.034 | 9.52 | 8500 | 0.1904 | 0.8444 | 0.8804 | 0.8620 | 0.9640 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.2 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
|
|
