The dataset used is a dataset intended for sarcasm detection in the Indonesian language. The dataset is split into three sets: test, validate, training.

Training procedure

https://colab.research.google.com/github/huggingface/workshops/blob/main/luzern-university/02-text-classification.ipynb#scrollTo=7a2420dd-b6ca-4c41-811d-e4922e400339 This was followed as a guide, as well as the NLP course provided by the Hugging face

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Recall	Precision	F1
0.537	1.0	309	0.5004	0.7498	0.0	0.0	0.0
0.441	2.0	618	0.4406	0.7909	0.3428	0.6576	0.4507
0.411	3.0	927	0.4626	0.8037	0.3626	0.7111	0.4803
0.3771	4.0	1236	0.4372	0.8072	0.5751	0.6246	0.5988
0.32	5.0	1545	0.4455	0.8037	0.5014	0.6367	0.5610
0.2876	6.0	1854	0.4670	0.8136	0.5722	0.6433	0.6057
0.2954	7.0	2163	0.4748	0.8136	0.5892	0.6380	0.6127
0.2645	8.0	2472	0.5221	0.8122	0.6657	0.6152	0.6395
0.2229	9.0	2781	0.5384	0.8094	0.5609	0.6346	0.5955
0.2017	10.0	3090	0.5867	0.8009	0.5184	0.6224	0.5657

Framework versions

Transformers 4.41.2
Pytorch 2.3.0+cu121
Datasets 2.20.0
Tokenizers 0.19.1

Bubbli/xlm-r-base-finetuned-indo-sarcasm

xlm-r-base-finetuned-indo-sarcasm

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Bubbli/
xlm-r-base-finetuned-indo-sarcasm