fedcsis-intent_baseline-xlm_r-leyzer_pl
This model is a fine-tuned version of xlm-roberta-base on the leyzer-fedcsis dataset. It achieves the following results on the evaluation set:
- Loss: 0.1621
- Accuracy: 0.9646
- F1: 0.9646
and on test set:
- Accuracy: 0.9645916619074815
- F1: 0.9645916619074815
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 |
|---|---|---|---|---|---|
| 3.4487 | 1.0 | 798 | 1.5956 | 0.6532 | 0.6532 |
| 1.1691 | 2.0 | 1596 | 0.8475 | 0.8325 | 0.8325 |
| 0.7795 | 3.0 | 2394 | 0.5025 | 0.9042 | 0.9042 |
| 0.3981 | 4.0 | 3192 | 0.3407 | 0.9377 | 0.9377 |
| 0.3072 | 5.0 | 3990 | 0.2610 | 0.9505 | 0.9505 |
| 0.1834 | 6.0 | 4788 | 0.2134 | 0.9571 | 0.9571 |
| 0.1303 | 7.0 | 5586 | 0.1850 | 0.9634 | 0.9634 |
| 0.1096 | 8.0 | 6384 | 0.1689 | 0.9697 | 0.9697 |
| 0.0849 | 9.0 | 7182 | 0.1605 | 0.9706 | 0.9706 |
| 0.0824 | 10.0 | 7980 | 0.1557 | 0.9717 | 0.9717 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.0
- 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}
}