yahyaabd / allstats-semantic-search-mini-model-v2

SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2

This is a sentence-transformers model finetuned from sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 on the allstats-semantic-search-synthetic-dataset-v2 dataset. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

• Model Type: Sentence Transformer
• Base model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
• Maximum Sequence Length: 128 tokens
• Output Dimensionality: 384 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • allstats-semantic-search-synthetic-dataset-v2

Model Sources

• Documentation: Sentence Transformers Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("yahyaabd/allstats-semantic-search-mini-model-v2")
# Run inference
sentences = [
    'Tahun berapa Rupiah terdepresiasi 0,23 persen terhadap Dolar Amerika?',
    'Depresiasi Rupiah terhadap Dolar Amerika pada tahun 2016 sebesar 0,5 persen.',
    'Ringkasan Neraca Arus Dana Triwulan Pertama, 2002, (Miliar Rupiah)',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Semantic Similarity

• Datasets: allstats-semantic-search-mini-v2-eval and allstat-semantic-search-mini-v2-test
• Evaluated with EmbeddingSimilarityEvaluator

Training Details

Training Dataset

allstats-semantic-search-synthetic-dataset-v2

• Dataset: allstats-semantic-search-synthetic-dataset-v2 at c76f31a
• Size: 244,856 training samples
• Columns: query , doc , and label
• Approximate statistics based on the first 1000 samples:

  	query	doc	label
  type	string	string	float
  details	min: 3 tokens mean: 12.75 tokens max: 45 tokens	min: 4 tokens mean: 14.81 tokens max: 56 tokens	min: 0.0 mean: 0.54 max: 1.0

• Samples:

  query	doc	label
  Dtaa harg konsymen edesaan (non-makann) 201	Statistik Harga Konsumen Perdesaan Kelompok Nonmakanan (Data 2013)	0.95
  Bagaimna konidsi keuamgan rymah atngga Indonsia 2020-2022?	Statistik Perusahaan Perikanan 2007	0.1
  Tingkat hunian kamar hotel tahun 2023	Tingkat Penghunian Kamar Hotel 2023	0.99

• Loss: CosineSimilarityLoss with these parameters:

  {
      "loss_fct": "torch.nn.modules.loss.MSELoss"
  }
  

Evaluation Dataset

allstats-semantic-search-synthetic-dataset-v2

• Dataset: allstats-semantic-search-synthetic-dataset-v2 at c76f31a
• Size: 52,469 evaluation samples
• Columns: query , doc , and label
• Approximate statistics based on the first 1000 samples:

  	query	doc	label
  type	string	string	float
  details	min: 3 tokens mean: 13.04 tokens max: 43 tokens	min: 4 tokens mean: 15.01 tokens max: 54 tokens	min: 0.0 mean: 0.52 max: 1.0

• Samples:

  query	doc	label
  Bulan apa NTP mengalami kenaikan 0,25 persen?	Jumlah Wisatawan Mancanegara Bulan Agustus 2009 Turun 4,49 Persen Dibandingkan Bulan Sebelumnya.	0.0
  Sebutksn keempa komositi tang disebutkn besert persentae mrajin persagangannya.	Marjin Perdagangan Minyak Goreng 3,86 Persen, Terigu 5,92 Persen, Garam 23,74 Persen, Dan Susu Bubuk 13,02 Persen	1.0
  Data kemiskinan per kabupaten/kota tahun 2007	Data dan Informasi Kemiskinan 2007 Buku 2: Kabupaten/Kota	0.87

• Loss: CosineSimilarityLoss with these parameters:

  {
      "loss_fct": "torch.nn.modules.loss.MSELoss"
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy : steps
• per_device_train_batch_size : 64
• per_device_eval_batch_size : 64
• num_train_epochs : 8
• warmup_ratio : 0.1
• fp16 : True

All Hyperparameters

Training Logs

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 3.3.1
• Transformers: 4.47.1
• PyTorch: 2.5.1+cu124
• Accelerate: 1.2.1
• Datasets: 3.2.0
• Tokenizers: 0.21.0

Citation

BibTeX

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}