|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: fedcsis-intent_baseline-xlm_r-es |
|
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-es |
|
|
|
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the |
|
[leyzer-fedcsis](https://huggingface.co/datasets/cartesinus/leyzer-fedcsis) dataset. |
|
|
|
Test set results: |
|
- Accuracy: **0.970738** |
|
|
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1440 |
|
- Accuracy: **0.9749** |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| 2.6266 | 1.0 | 941 | 0.9415 | 0.8074 | 0.8074 | |
|
| 0.7228 | 2.0 | 1882 | 0.4892 | 0.8999 | 0.8999 | |
|
| 0.3612 | 3.0 | 2823 | 0.3110 | 0.9346 | 0.9346 | |
|
| 0.2236 | 4.0 | 3764 | 0.2433 | 0.9518 | 0.9518 | |
|
| 0.1464 | 5.0 | 4705 | 0.1963 | 0.9594 | 0.9594 | |
|
| 0.1056 | 6.0 | 5646 | 0.1698 | 0.9667 | 0.9667 | |
|
| 0.0725 | 7.0 | 6587 | 0.1574 | 0.9693 | 0.9693 | |
|
| 0.0602 | 8.0 | 7528 | 0.1476 | 0.9729 | 0.9729 | |
|
| 0.0619 | 9.0 | 8469 | 0.1474 | 0.9743 | 0.9743 | |
|
| 0.052 | 10.0 | 9410 | 0.1440 | 0.9749 | 0.9749 | |
|
|
|
|
|
### 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} |
|
} |
|
|
|
``` |
