|
--- |
|
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: 0.8526912181303116 |
|
- name: Recall |
|
type: recall |
|
value: 0.8962779156327544 |
|
- name: F1 |
|
type: f1 |
|
value: 0.8739414468908783 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9765807962529274 |
|
--- |
|
|
|
<!-- 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: 0.1428 |
|
- Precision: 0.8527 |
|
- Recall: 0.8963 |
|
- F1: 0.8739 |
|
- Accuracy: 0.9766 |
|
|
|
## 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: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.2508 | 1.12 | 500 | 0.1431 | 0.7569 | 0.8481 | 0.7999 | 0.9672 | |
|
| 0.1103 | 2.24 | 1000 | 0.1169 | 0.7717 | 0.8541 | 0.8108 | 0.9704 | |
|
| 0.0731 | 3.36 | 1500 | 0.1134 | 0.8066 | 0.8715 | 0.8378 | 0.9749 | |
|
| 0.0527 | 4.47 | 2000 | 0.1137 | 0.8360 | 0.8928 | 0.8635 | 0.9767 | |
|
| 0.039 | 5.59 | 2500 | 0.1248 | 0.8364 | 0.8854 | 0.8602 | 0.9755 | |
|
| 0.0265 | 6.71 | 3000 | 0.1252 | 0.8427 | 0.8878 | 0.8647 | 0.9769 | |
|
| 0.0206 | 7.83 | 3500 | 0.1424 | 0.8473 | 0.8953 | 0.8707 | 0.9757 | |
|
| 0.0148 | 8.95 | 4000 | 0.1428 | 0.8527 | 0.8963 | 0.8739 | 0.9766 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.2 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
|
|
