Add new SentenceTransformer model

97e2e5d verified over 1 year ago

24.9 kB

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:2602
  - loss:ContrastiveLoss
base_model: sentence-transformers/paraphrase-multilingual-mpnet-base-v2
widget:
  - source_sentence: >-
      Data triwulanan GDS, investasi non-fin, pinjaman neto pemerintah (triliun)
      2010
    sentences:
      - 'Nilai Ekspor Menurut Pelabuhan Utama (Nilai FOB: juta US$) 2000-2023'
      - >-
        Suhu Minimum, Rata-Rata, dan Maksimum di Stasiun Pengamatan BMKG (oC),
        2011-2015
      - >-
        Nilai Ekspor Menurut Negara Tujuan Utama (Nilai FOB: juta US$),
        2000-2023
  - source_sentence: >-
      Data triwulanan GDS, investasi non-fin, pinjaman neto pemerintah (triliun)
      2010
    sentences:
      - >-
        Tabungan Bruto, Investasi Nonfinansial, dan Pinjaman Neto Triwulanan
        Sektor Pemerintahan Umum (triliun rupiah), 2009-2015
      - >-
        Produksi Perikanan Budidaya Menurut Provinsi dan Jenis Budidaya,
        2000-2020
      - >-
        Rata-rata Pendapatan Bersih Berusaha Sendiri Menurut Provinsi dan
        Kelompok Umur (ribu rupiah), 2017
  - source_sentence: Gaji bersih vs kelompok umur dan lapangan pekerjaan, 2023
    sentences:
      - Investasi Nonfinansial Menurut Sektor (triliun rupiah), 2008-2014
      - >-
        Posisi Kredit Usaha Mikro, Kecil, dan Menengah (UMKM) 1 pada Bank Umum
        (miliar rupiah), 2012-2016
      - Ringkasan Neraca Arus Dana, Triwulan I, 2013*), (Miliar Rupiah)
  - source_sentence: >-
      Data utang luar negeri Indonesia (pemerintah dan BI), detail kreditor dan
      syarat, tahun 2010
    sentences:
      - >-
        Angka Partisipasi Sekolah (APS) Penduduk Umur 7-18 Tahun Menurut
        Klasifikasi Desa, Jenis Kelamin, dan Kelompok Umur, 2009-2023
      - Indeks Integritas Ujian Nasional
      - >-
        Rekapitulasi Luas Penutupan Lahan Hutan dan Non Hutan Menurut Provinsi
        Tahun 2014-2022 (Ribu Ha)
  - source_sentence: Laporan keuangan perusahaan asuransi wajib & BPJS akhir 2015
    sentences:
      - Indeks Harga Konsumen Menurut Kelompok Pengeluaran, 2020-2023
      - Ringkasan Neraca Arus Dana, Triwulan I, 2013*), (Miliar Rupiah)
      - >-
        Rata-rata Konsumsi dan Pengeluaran Perkapita Seminggu Menurut Komoditi
        Makanan dan Golongan Pengeluaran per Kapita Seminggu di Provinsi Jawa
        Timur, 2018-2023
datasets:
  - yahyaabd/bps-statictable-query-title-pairs
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 base v1 eval
          type: allstats-semantic-base-v1-eval
        metrics:
          - type: pearson_cosine
            value: 0.8898188833771716
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.779923841631983
            name: Spearman Cosine
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: allstat semantic base v1 test
          type: allstat-semantic-base-v1-test
        metrics:
          - type: pearson_cosine
            value: 0.9039024076661341
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8077065435723709
            name: Spearman Cosine

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 bps-statictable-query-title-pairs 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:
- bps-statictable-query-title-pairs

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-ir-mpnet-base-v1")
# Run inference
sentences = [
    'Laporan keuangan perusahaan asuransi wajib & BPJS akhir 2015',
    'Ringkasan Neraca Arus Dana, Triwulan I, 2013*), (Miliar Rupiah)',
    'Rata-rata Konsumsi dan Pengeluaran Perkapita Seminggu Menurut Komoditi Makanan dan Golongan Pengeluaran per Kapita Seminggu di Provinsi Jawa Timur, 2018-2023',
]
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-base-v1-eval and allstat-semantic-base-v1-test
Evaluated with EmbeddingSimilarityEvaluator

Metric	allstats-semantic-base-v1-eval	allstat-semantic-base-v1-test
pearson_cosine	0.8898	0.9039
spearman_cosine	0.7799	0.8077

Training Details

Training Dataset

bps-statictable-query-title-pairs

Dataset: bps-statictable-query-title-pairs at c7df38f
Size: 2,602 training samples
Columns: query, doc, and label
Approximate statistics based on the first 1000 samples:
query doc label
type string string int
details
min: 5 tokens
mean: 18.35 tokens
max: 35 tokens

min: 4 tokens
mean: 25.83 tokens
max: 58 tokens

0: ~66.50%
1: ~33.50%

	query	doc	label
type	string	string	int
details	min: 5 tokens mean: 18.35 tokens max: 35 tokens	min: 4 tokens mean: 25.83 tokens max: 58 tokens	0: ~66.50% 1: ~33.50%

Samples:

query	doc	label
`Pertumbuhan populasi provinsi di Indonesia 1971-2024`	`Kecepatan Angin dan Kelembaban di Stasiun Pengamatan BMKG, 2000-2010`	`0`
`Perbandingan upah nominal dan riil pekerja pertanian di Indonesia (tahun dasar 2012), periode 2017.`	`Upah Nominal dan Riil Buruh Tani di Indonesia (Rupiah), 2009-2019 (2012=100)`	`1`
`Laporan singkat cash flow statement Q4/2005`	`Nilai Produksi dan Biaya Produksi per Hektar Usaha Tanaman Bawang Merah dan Cabai Merah, 2014`	`0`

Loss: ContrastiveLoss with these parameters:

{
    "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
    "margin": 0.5,
    "size_average": true
}

Evaluation Dataset

bps-statictable-query-title-pairs

Dataset: bps-statictable-query-title-pairs at c7df38f
Size: 558 evaluation samples
Columns: query, doc, and label
Approximate statistics based on the first 558 samples:
query doc label
type string string int
details
min: 4 tokens
mean: 18.45 tokens
max: 35 tokens

min: 4 tokens
mean: 26.04 tokens
max: 58 tokens

0: ~70.97%
1: ~29.03%

	query	doc	label
type	string	string	int
details	min: 4 tokens mean: 18.45 tokens max: 35 tokens	min: 4 tokens mean: 26.04 tokens max: 58 tokens	0: ~70.97% 1: ~29.03%

Samples:

query	doc	label
`Data pengeluaran makanan rata-rata warga Sulteng per minggu di tahun 2022, berdasarkan kelompok pendapatan`	`Sistem Neraca Sosial Ekonomi Indonesia Tahun 2022 (84 x 84)`	`0`
`Konsumsi & belanja makanan per orang di NTB, beda kelompok pengeluaran, 2021`	`Rata-rata Konsumsi dan Pengeluaran Perkapita Seminggu Menurut Komoditi Makanan dan Golongan Pengeluaran per Kapita Seminggu di Provinsi Nusa Tenggara Barat, 2018-2023`	`1`
`Bagaimana perbandingan PNS pria dan wanita di berbagai golongan tahun 2014?`	`Penduduk Berumur 15 Tahun Ke Atas Menurut Provinsi dan Jenis Kegiatan Selama Seminggu yang Lalu, 2008 - 2024`	`0`

Loss: ContrastiveLoss with these parameters:

{
    "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
    "margin": 0.5,
    "size_average": true
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 32
per_device_eval_batch_size: 32
num_train_epochs: 4
warmup_ratio: 0.1
fp16: True
load_best_model_at_end: True
eval_on_start: True

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 32
per_device_eval_batch_size: 32
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 5e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 4
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.1
warmup_steps: 0
log_level: passive
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
save_safetensors: True
save_on_each_node: False
save_only_model: False
restore_callback_states_from_checkpoint: False
no_cuda: False
use_cpu: False
use_mps_device: False
seed: 42
data_seed: None
jit_mode_eval: False
use_ipex: False
bf16: False
fp16: True
fp16_opt_level: O1
half_precision_backend: auto
bf16_full_eval: False
fp16_full_eval: False
tf32: None
local_rank: 0
ddp_backend: None
tpu_num_cores: None
tpu_metrics_debug: False
debug: []
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_prefetch_factor: None
past_index: -1
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: True
ignore_data_skip: False
fsdp: []
fsdp_min_num_params: 0
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
fsdp_transformer_layer_cls_to_wrap: None
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch
optim_args: None
adafactor: False
group_by_length: False
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
dataloader_pin_memory: True
dataloader_persistent_workers: False
skip_memory_metrics: True
use_legacy_prediction_loop: False
push_to_hub: False
resume_from_checkpoint: None
hub_model_id: None
hub_strategy: every_save
hub_private_repo: None
hub_always_push: False
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
include_for_metrics: []
eval_do_concat_batches: True
fp16_backend: auto
push_to_hub_model_id: None
push_to_hub_organization: None
mp_parameters:
auto_find_batch_size: False
full_determinism: False
torchdynamo: None
ray_scope: last
ddp_timeout: 1800
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
dispatch_batches: None
split_batches: None
include_tokens_per_second: False
include_num_input_tokens_seen: False
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
eval_on_start: True
use_liger_kernel: False
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	Validation Loss	allstats-semantic-base-v1-eval_spearman_cosine	allstat-semantic-base-v1-test_spearman_cosine
0	0	-	0.0099	0.7449	-
0.1220	10	0.0091	0.0065	0.7640	-
0.2439	20	0.0059	0.0040	0.7743	-
0.3659	30	0.0045	0.0036	0.7688	-
0.4878	40	0.0045	0.0036	0.7694	-
0.6098	50	0.0032	0.0037	0.7758	-
0.7317	60	0.003	0.0025	0.7753	-
0.8537	70	0.0035	0.0029	0.7710	-
0.9756	80	0.0028	0.0026	0.7745	-
1.0976	90	0.0015	0.0023	0.7754	-
1.2195	100	0.0013	0.0021	0.7760	-
1.3415	110	0.0013	0.0022	0.7751	-
1.4634	120	0.002	0.0021	0.7746	-
1.5854	130	0.0012	0.0020	0.7750	-
1.7073	140	0.0007	0.0019	0.7740	-
1.8293	150	0.0008	0.0019	0.7738	-
1.9512	160	0.0026	0.0018	0.7772	-
2.0732	170	0.0009	0.0019	0.7785	-
2.1951	180	0.0005	0.0020	0.7781	-
2.3171	190	0.0009	0.0017	0.7777	-
2.4390	200	0.0005	0.0017	0.7773	-
2.5610	210	0.0004	0.0018	0.7766	-
2.6829	220	0.0006	0.0018	0.7762	-
2.8049	230	0.0006	0.0019	0.7756	-
2.9268	240	0.0016	0.0019	0.7777	-
3.0488	250	0.0008	0.0018	0.7796	-
3.1707	260	0.0005	0.0017	0.7802	-
3.2927	270	0.0006	0.0017	0.7802	-
3.4146	280	0.0004	0.0017	0.7805	-
3.5366	290	0.0004	0.0017	0.7805	-
3.6585	300	0.0003	0.0018	0.7802	-
3.7805	310	0.0006	0.0018	0.7800	-
3.9024	320	0.0003	0.0018	0.7799	-
-1	-1	-	-	-	0.8077

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.4.0
Transformers: 4.48.1
PyTorch: 2.5.1+cu124
Accelerate: 1.3.0
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",
}

ContrastiveLoss

@inproceedings{hadsell2006dimensionality,
    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
    title={Dimensionality Reduction by Learning an Invariant Mapping},
    year={2006},
    volume={2},
    number={},
    pages={1735-1742},
    doi={10.1109/CVPR.2006.100}
}