metadata

library_name: setfit
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
base_model: firqaaa/indo-sentence-bert-base
metrics:
  - accuracy
  - precision
  - recall
  - f1
widget:
  - text: >-
      halaman 97 - 128 tidak ada , diulang halaman 65 - 96 , pembelian hari
      minggu tanggal 24 desember sore sekitar jam 4 pembayaran menggunakan kartu
      atm bri bersamaan dengan buku the puppeteer dan sirkus pohon
  - text: liverpool sukses di kandang tottenham
  - text: >-
      hai angga , untuk penerbitan tiket reschedule diharuskan melakukan
      pembayaran dulu ya .
  - text: sedih kalau umat diprovokasi supaya saling membenci .
  - text: >-
      berada di lokasi strategis jalan merdeka , berseberangan agak ke samping
      bandung indah plaza , tapat sebelah kanan jalan sebelum traffic light ,
      parkir mobil cukup luas . saus bumbu dan lain-lain disediakan cukup
      lengkap di lantai bawah . di lantai atas suasana agak sepi . bakso cukup
      enak dan terjangkau harga nya tetapi kuah relatif kurang dan porsi tidak
      terlalu besar
pipeline_tag: text-classification
inference: true
model-index:
  - name: SetFit with firqaaa/indo-sentence-bert-base
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: Unknown
          type: unknown
          split: test
        metrics:
          - type: accuracy
            value: 0.7171717171717171
            name: Accuracy
          - type: precision
            value: 0.7171717171717171
            name: Precision
          - type: recall
            value: 0.7171717171717171
            name: Recall
          - type: f1
            value: 0.7171717171717171
            name: F1

SetFit with firqaaa/indo-sentence-bert-base

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:

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

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

Training set	Min	Median	Max
Word count	3	22.7917	61

Label	Training Sample Count
0	8
1	8
2	8

Training Hyperparameters

batch_size: (16, 2)
num_epochs: (2, 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	Step	Training Loss	Validation Loss
0.0417	1	0.3908	-
0.0833	2	0.2962	-
0.125	3	0.2397	-
0.1667	4	0.3493	-
0.2083	5	0.2197	-
0.25	6	0.3782	-
0.2917	7	0.2341	-
0.3333	8	0.2166	-
0.375	9	0.3381	-
0.4167	10	0.1212	-
0.4583	11	0.1849	-
0.5	12	0.1796	-
0.5417	13	0.2027	-
0.5833	14	0.1824	-
0.625	15	0.1242	-
0.6667	16	0.1071	-
0.7083	17	0.1324	-
0.75	18	0.0667	-
0.7917	19	0.1095	-
0.8333	20	0.1277	-
0.875	21	0.0506	-
0.9167	22	0.0661	-
0.9583	23	0.0776	-
1.0	24	0.0371	0.2406
1.0417	25	0.0652	-
1.0833	26	0.0698	-
1.125	27	0.0775	-
1.1667	28	0.052	-
1.2083	29	0.0399	-
1.25	30	0.0189	-
1.2917	31	0.0341	-
1.3333	32	0.0259	-
1.375	33	0.0844	-
1.4167	34	0.0322	-
1.4583	35	0.0186	-
1.5	36	0.0328	-
1.5417	37	0.0107	-
1.5833	38	0.027	-
1.625	39	0.0311	-
1.6667	40	0.0244	-
1.7083	41	0.0277	-
1.75	42	0.0132	-
1.7917	43	0.0153	-
1.8333	44	0.0147	-
1.875	45	0.0074	-
1.9167	46	0.0142	-
1.9583	47	0.0189	-
2.0	48	0.0095	0.2139

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}
}