yahyaabd / allstats-semantic-search-model-v1-2

SentenceTransformer based on sentence-transformers/paraphrase-multilingual-mpnet-base-v2

This is a sentence-transformers model finetuned from sentence-transformers/paraphrase-multilingual-mpnet-base-v2 on the allstats-semantic-search-synthetic-dataset-v1 dataset. It maps sentences & paragraphs to a 768-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-mpnet-base-v2
• Maximum Sequence Length: 128 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • allstats-semantic-search-synthetic-dataset-v1

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: XLMRobertaModel 
  (1): Pooling({'word_embedding_dimension': 768, '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-model-v1-2")
# Run inference
sentences = [
    'Berapa persen deflasi ysng terjadi paa Maret 2010?',
    'Pada Bulan Maret 2010 Terjadi Deflasi Sebesar 0,14 Persen.',
    'Inflasi September 2008 sebesar 0,97 persen.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# 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-v1-2-dev and allstat-semantic-search-v1-test
• Evaluated with EmbeddingSimilarityEvaluator

Training Details

Training Dataset

allstats-semantic-search-synthetic-dataset-v1

• Dataset: allstats-semantic-search-synthetic-dataset-v1 at c477abf
• Size: 212,930 training samples
• Columns: query , doc , and label
• Approximate statistics based on the first 1000 samples:

  	query	doc	label
  type	string	string	float
  details	min: 5 tokens mean: 11.52 tokens max: 32 tokens	min: 4 tokens mean: 14.85 tokens max: 70 tokens	min: 0.0 mean: 0.51 max: 1.0

• Samples:

  query	doc	label
  studi tentang kemiskinan urban	Perkembangan Mingguan Harga Eceran Beberapa Bahan Pokok di Ibukota Provinsi Seluruh Indonesia (Juli-Desember 2018)	0.1
  Harga gabah di tingkat produsen bulan September	Upah Buruh Juli 2020	0.1
  Data perusahaan konstruksi di wilayah timur Indonesia thn 2013	Direktori Perusahaan Konstruksi 2013 Buku 6 Maluku dan Papua	0.92

• Loss: CosineSimilarityLoss with these parameters:

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

Evaluation Dataset

allstats-semantic-search-synthetic-dataset-v1

• Dataset: allstats-semantic-search-synthetic-dataset-v1 at c477abf
• Size: 26,616 evaluation samples
• Columns: query , doc , and label
• Approximate statistics based on the first 1000 samples:

  	query	doc	label
  type	string	string	float
  details	min: 5 tokens mean: 11.33 tokens max: 53 tokens	min: 4 tokens mean: 14.6 tokens max: 69 tokens	min: 0.0 mean: 0.5 max: 1.0

• Samples:

  query	doc	label
  Informasi potensi deas di Maluku 011	Statistik Potensi Desa Provinsi Maluku 2011	0.87
  Berapa persen kenaikan jumlah penumpang angkutan udara internasional pada Januari 2024 dibandingkan Desember 2023?	Kenaikan jumlah penumpang bulan lainnya	0.0
  informasi tentang potensi desa jambi tahun 2005	Statistik Potensi Desa Provinsi Jambi 2005	0.85

• 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 : 32
• per_device_eval_batch_size : 32
• num_train_epochs : 6
• 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: 2.2.2+cu121
• 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",
}