|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
base_model: xlm-roberta-base |
|
model-index: |
|
- name: fedcsis-intent_baseline-xlm_r-pl |
|
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. --> |
|
|
|
# fedcsis-intent_baseline-xlm_r-pl |
|
|
|
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the |
|
[leyzer-fedcsis](https://huggingface.co/cartesinus/leyzer-fedcsis) dataset. |
|
Results on test set: |
|
- Accuracy: **0.959451** |
|
|
|
It achieves the following results on the evaluation set: |
|
- Loss: **0.1602** |
|
- Accuracy: **0.9671** |
|
|
|
## 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 | Accuracy | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| 3.4745 | 1.0 | 798 | 1.5821 | 0.6795 | 0.6795 | |
|
| 1.1438 | 2.0 | 1596 | 0.8333 | 0.8259 | 0.8259 | |
|
| 0.7546 | 3.0 | 2394 | 0.4991 | 0.9039 | 0.9039 | |
|
| 0.3955 | 4.0 | 3192 | 0.3466 | 0.9302 | 0.9302 | |
|
| 0.3016 | 5.0 | 3990 | 0.2571 | 0.9440 | 0.9440 | |
|
| 0.183 | 6.0 | 4788 | 0.2147 | 0.9588 | 0.9588 | |
|
| 0.1309 | 7.0 | 5586 | 0.1900 | 0.9605 | 0.9605 | |
|
| 0.1128 | 8.0 | 6384 | 0.1750 | 0.9640 | 0.9640 | |
|
| 0.0873 | 9.0 | 7182 | 0.1638 | 0.9663 | 0.9663 | |
|
| 0.082 | 10.0 | 7980 | 0.1602 | 0.9671 | 0.9671 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.0 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.10.1 |
|
- Tokenizers 0.13.2 |
|
|
|
## Citation |
|
|
|
If you use this model, please cite the following: |
|
``` |
|
@inproceedings{kubis2023caiccaic, |
|
author={Marek Kubis and Paweł Skórzewski and Marcin Sowański and Tomasz Ziętkiewicz}, |
|
pages={1319–1324}, |
|
title={Center for Artificial Intelligence Challenge on Conversational AI Correctness}, |
|
booktitle={Proceedings of the 18th Conference on Computer Science and Intelligence Systems}, |
|
year={2023}, |
|
doi={10.15439/2023B6058}, |
|
url={http://dx.doi.org/10.15439/2023B6058}, |
|
volume={35}, |
|
series={Annals of Computer Science and Information Systems} |
|
} |
|
|
|
``` |
