metadata

license: mit
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
model-index:
  - name: fedcsis-intent_baseline-xlm_r-es
    results: []

fedcsis-intent_baseline-xlm_r-es

This model is a fine-tuned version of xlm-roberta-base on the 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}
}