TRUEnder/setfit-indosentencebert-indonlusmsa-8-shot

SetFit with firqaaa/indo-sentence-bert-base for indonlu/smsa dataset

Author

Kelompok 3 :

• Muhammad Guntur Arfianto (20/459272/PA/19933)
• Putri Iqlima Miftahuddini (23/531392/NUGM/01467)
• Alan Kurniawan (23/531301/NUGM/01382)

This is a SetFit model that can be used for Text Classification. This SetFit model uses firqaaa/indo-sentence-bert-base as the Sentence Transformer embedding model. A LogisticRegression instance is used for classification.

The model has been trained using an efficient few-shot learning technique that involves:

1. Fine-tuning a Sentence Transformer with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.

The dataset that was used for fine-tuning this model is indonlu, specifically its subset, SmSa dataset.

Model Details

Model Description

• Model Type: SetFit
• Sentence Transformer body: firqaaa/indo-sentence-bert-base
• Classification head: a LogisticRegression instance
• Maximum Sequence Length: 512 tokens
• Number of Classes: 3 classes

Model Sources

• Repository: SetFit on GitHub
• Paper: Efficient Few-Shot Learning Without Prompts
• Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts

Model Labels

Label	Examples
2	'nasi campur terkenal di bandung , info nya nasi campur pertama di bandung . mengandung b2 . rasa standar nasi campur . ada babi merah , babi panggang , sate babi manis , bakso goreng , jerohan manis . layanan tidak ramah , maklum masih generasi tua yang beraksi . lokasi makan lumayan bersih tapi tidak berat' 'saya di cgv marvel city sby mau verifikasi sms redam , tapi di informasi telkomsel trobel , menyebalkan !' 'indonesia itu tipe yang kalau sudah down pasti susah bangkit lagi'
1	'biru ada 4 , hijau ada 4 , merah ada 3 , kuning ada 3' 'baik terima kasih banyak' 'hai , ya , silakan kamu dapat mencoba lakukan pembayaran pdam di bukalapak .'
0	'nyaman banget kalau lagi nongkrong kenyang di warung upnormal . mulai dari pilihan menu nya yang serius banget digarap , dari pelayan2 nya yang kece , sampai ke interior nya yang super . rekomendasi banget deh kalau mau mengerjakan tugas , arisan , ulang tahun , reunian di sini .' 'conggo gallrely cafe di bandung utara . cafe nya sih okok saja . yang menarik adalah produksi meja dengan kayu-kayu yang panjang dan tebal khusus untuk meja makan .' 'terima kasih mas'

Evaluation

Metrics

Label	Accuracy	Precision	Recall	F1
all	0.7172	0.7172	0.7172	0.7172

Uses

Direct Use for Inference

First install the SetFit library:

pip install setfit

Then you can load this model and run inference.

from setfit import SetFitModel

# Download from the 🤗 Hub
model = SetFitModel.from_pretrained("TRUEnder/setfit-indosentencebert-indonlusmsa-8-shot")
# Run inference
preds = model("liverpool sukses di kandang tottenham")

Training Details

Training Set Metrics

Label	Training Sample Count
0	8
1	8
2	8

Training Hyperparameters

• batch_size: (16, 2)
• num_epochs: (6, 16)
• max_steps: -1
• sampling_strategy: oversampling
• body_learning_rate: (2e-05, 1e-05)
• head_learning_rate: 0.01
• loss: CosineSimilarityLoss
• distance_metric: cosine_distance
• margin: 0.25
• end_to_end: False
• use_amp: False
• warmup_proportion: 0.1
• seed: 42
• eval_max_steps: -1
• load_best_model_at_end: True

Training Results (Epoch-to-epoch)

Epoch	Step	Training Loss	Validation Loss
1.0	24	0.0498	0.2293
2.0	48	0.0032	0.2033
3.0	72	0.0014	0.2021
4.0	96	0.001	0.2009
5.0	120	0.0009	0.2016
6.0	144	0.0008	0.2016

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.10.12
• SetFit: 1.0.3
• Sentence Transformers: 3.0.1
• Transformers: 4.41.2
• PyTorch: 2.3.0+cu121
• Datasets: 2.19.2
• Tokenizers: 0.19.1

Citation

BibTeX

@article{https://doi.org/10.48550/arxiv.2209.11055,
    doi = {10.48550/ARXIV.2209.11055},
    url = {https://arxiv.org/abs/2209.11055},
    author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
    keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
    title = {Efficient Few-Shot Learning Without Prompts},
    publisher = {arXiv},
    year = {2022},
    copyright = {Creative Commons Attribution 4.0 International}
}