---
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:212940
- loss:CosineSimilarityLoss
base_model: sentence-transformers/paraphrase-multilingual-mpnet-base-v2
widget:
- source_sentence: Ringkasan data strategis BPS 2012
sentences:
- Rata-rata Upah/Gaji Bersih Sebulan Buruh/Karyawan/Pegawai Menurut Provinsi dan
Jenis Pekerjaan Utama, 2021
- Laporan Perekonomian Indonesia 2007
- Statistik Potensi Desa Provinsi Banten 2008
- source_sentence: tahun berapa ekspor naik 2,37% dan impor naik 30,30%?
sentences:
- Bulan November 2006 Ekspor Naik 2,37 % dan Impor Naik 30,30 %
- Indeks Harga Konsumen per Kelompok di 82 Kota 1 (2012=100)
- 'Februari 2022: Tingkat Pengangguran Terbuka (TPT) sebesar 5,83 persen dan Rata-rata
upah buruh sebesar 2,89 juta rupiah per bulan'
- source_sentence: akses air bersih di indonesia (2005-2009)
sentences:
- Desember 2016, Rupiah Terapresiasi 0,74 Persen Terhadap Dolar Amerika
- Statistik Air Bersih 2005-2009
- Rata-rata Upah/Gaji Bersih Sebulan Buruh/Karyawan/Pegawai Menurut Pendidikan Tertinggi
yang Ditamatkan dan Lapangan Pekerjaan Utama di 17 Sektor (rupiah), 2018
- source_sentence: Tinjauan Regional Berdasarkan PDRB Kabupaten/Kota 2014-2018, Buku
2 Pulau Jawa dan Bali
sentences:
- Profil Migran Hasil Susenas 2011-2012
- Statistik Gas Kota 2004-2008
- Jumlah kunjungan wisman ke Indonesia melalui pintu masuk utama pada Juni 2022
mencapai 345,44 ribu kunjungan dan Jumlah penumpang angkutan udara internasional
pada Juni 2022 naik 23,28 persen
- source_sentence: perubahan nilai tukar petani bulan mei 2017
sentences:
- Perkembangan Nilai Tukar Petani Mei 2017
- NTP Naik 0,15%, Harga Gabah Kualitas GKG Naik 0,98%
- Statistik Restoran/Rumah Makan Tahun 2014
datasets:
- yahyaabd/allstats-semantic-search-synthetic-dataset-v1
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
- pearson_cosine
- spearman_cosine
model-index:
- name: SentenceTransformer based on sentence-transformers/paraphrase-multilingual-mpnet-base-v2
results:
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: allstats semantic search v1 3 dev
type: allstats-semantic-search-v1-3-dev
metrics:
- type: pearson_cosine
value: 0.9958745183830993
name: Pearson Cosine
- type: spearman_cosine
value: 0.96406478662103
name: Spearman Cosine
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: allstat semantic search v1 3 test
type: allstat-semantic-search-v1-3-test
metrics:
- type: pearson_cosine
value: 0.9960950217535739
name: Pearson Cosine
- type: spearman_cosine
value: 0.9647914507837114
name: Spearman Cosine
---
# SentenceTransformer based on sentence-transformers/paraphrase-multilingual-mpnet-base-v2
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2) on the [allstats-semantic-search-synthetic-dataset-v1](https://huggingface.co/datasets/yahyaabd/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](https://huggingface.co/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](https://huggingface.co/datasets/yahyaabd/allstats-semantic-search-synthetic-dataset-v1)
### Model Sources
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
### 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:
```bash
pip install -U sentence-transformers
```
Then you can load this model and run inference.
```python
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("yahyaabd/allstats-semantic-search-model-v1-3")
# Run inference
sentences = [
'perubahan nilai tukar petani bulan mei 2017',
'Perkembangan Nilai Tukar Petani Mei 2017',
'Statistik Restoran/Rumah Makan Tahun 2014',
]
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-v1-3-dev` and `allstat-semantic-search-v1-3-test`
* Evaluated with [EmbeddingSimilarityEvaluator
](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
| Metric | allstats-semantic-search-v1-3-dev | allstat-semantic-search-v1-3-test |
|:--------------------|:----------------------------------|:----------------------------------|
| pearson_cosine | 0.9959 | 0.9961 |
| **spearman_cosine** | **0.9641** | **0.9648** |
## Training Details
### Training Dataset
#### allstats-semantic-search-synthetic-dataset-v1
* Dataset: [allstats-semantic-search-synthetic-dataset-v1](https://huggingface.co/datasets/yahyaabd/allstats-semantic-search-synthetic-dataset-v1) at [b13c0a7](https://huggingface.co/datasets/yahyaabd/allstats-semantic-search-synthetic-dataset-v1/tree/b13c0a7412396a836cfbb887e140f183f3a6d65e)
* Size: 212,940 training samples
* Columns: query
, doc
, and label
* Approximate statistics based on the first 1000 samples:
| | query | doc | label |
|:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
| type | string | string | float |
| details |
aDta industri besar dan sedang Indonesia 2008
| Statistik Industri Besar dan Sedang Indonesia 2008
| 0.9
|
| profil bisnis konstruksi individu jawa barat 2022
| Statistik Industri Manufaktur Indonesia 2015 - Bahan Baku
| 0.15
|
| data statistik ekonomi indonesia
| Nilai Tukar Valuta Asing di Indonesia 2014
| 0.08
|
* Loss: [CosineSimilarityLoss
](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
```json
{
"loss_fct": "torch.nn.modules.loss.MSELoss"
}
```
### Evaluation Dataset
#### allstats-semantic-search-synthetic-dataset-v1
* Dataset: [allstats-semantic-search-synthetic-dataset-v1](https://huggingface.co/datasets/yahyaabd/allstats-semantic-search-synthetic-dataset-v1) at [b13c0a7](https://huggingface.co/datasets/yahyaabd/allstats-semantic-search-synthetic-dataset-v1/tree/b13c0a7412396a836cfbb887e140f183f3a6d65e)
* Size: 26,618 evaluation samples
* Columns: query
, doc
, and label
* Approximate statistics based on the first 1000 samples:
| | query | doc | label |
|:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
| type | string | string | float |
| details | tahun berapa ekspor naik 2,37% dan impor naik 30,30%?
| Bulan November 2006 Ekspor Naik 2,37 % dan Impor Naik 30,30 %
| 1.0
|
| Berapa produksi padi pada tahun 2023?
| Produksi padi tahun lainnya
| 0.0
|
| data statistik solus per aqua 2015
| Statistik Solus Per Aqua (SPA) 2015
| 0.97
|
* Loss: [CosineSimilarityLoss
](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
```json
{
"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`: 16
- `warmup_ratio`: 0.1
- `fp16`: True
#### All Hyperparameters