|
--- |
|
license: mit |
|
base_model: FacebookAI/xlm-roberta-large |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- cnec |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: CNEC_xlm-roberta-large |
|
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: 0.8548310328415041 |
|
- name: Recall |
|
type: recall |
|
value: 0.8913151364764268 |
|
- name: F1 |
|
type: f1 |
|
value: 0.8726919339164239 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9753512880562061 |
|
--- |
|
|
|
<!-- 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_xlm-roberta-large |
|
|
|
This model is a fine-tuned version of [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on the cnec dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1540 |
|
- Precision: 0.8548 |
|
- Recall: 0.8913 |
|
- F1: 0.8727 |
|
- Accuracy: 0.9754 |
|
|
|
## 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: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 7 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.2864 | 0.56 | 500 | 0.1328 | 0.7015 | 0.8119 | 0.7527 | 0.9629 | |
|
| 0.13 | 1.12 | 1000 | 0.1221 | 0.7836 | 0.8734 | 0.8261 | 0.9701 | |
|
| 0.0972 | 1.68 | 1500 | 0.1140 | 0.7836 | 0.8610 | 0.8205 | 0.9710 | |
|
| 0.0807 | 2.24 | 2000 | 0.1244 | 0.8032 | 0.8730 | 0.8366 | 0.9730 | |
|
| 0.0626 | 2.8 | 2500 | 0.1135 | 0.8104 | 0.8844 | 0.8458 | 0.9755 | |
|
| 0.0451 | 3.36 | 3000 | 0.1371 | 0.8305 | 0.8824 | 0.8556 | 0.9733 | |
|
| 0.0397 | 3.92 | 3500 | 0.1251 | 0.8307 | 0.8814 | 0.8553 | 0.9736 | |
|
| 0.0244 | 4.48 | 4000 | 0.1441 | 0.8370 | 0.8794 | 0.8577 | 0.9740 | |
|
| 0.0257 | 5.04 | 4500 | 0.1319 | 0.8541 | 0.8888 | 0.8711 | 0.9759 | |
|
| 0.0164 | 5.6 | 5000 | 0.1465 | 0.8421 | 0.8868 | 0.8639 | 0.9754 | |
|
| 0.013 | 6.16 | 5500 | 0.1494 | 0.8473 | 0.8868 | 0.8666 | 0.9751 | |
|
| 0.0108 | 6.72 | 6000 | 0.1540 | 0.8548 | 0.8913 | 0.8727 | 0.9754 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.2 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
|
|
