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.

python

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

Metric	allstats-semantic-search-mini-v2-eval	allstat-semantic-search-mini-v2-test
pearson_cosine	0.9839	0.9831
spearman_cosine	0.8951	0.8922

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:
json
1{ 2 "loss_fct": "torch.nn.modules.loss.MSELoss" 3}

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:
json
1{ 2 "loss_fct": "torch.nn.modules.loss.MSELoss" 3}

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

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 64
per_device_eval_batch_size: 64
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: 8
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: False
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: False
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-search-mini-v2-eval_spearman_cosine	allstat-semantic-search-mini-v2-test_spearman_cosine
0.1307	500	0.0963	0.0657	0.6836	-
0.2614	1000	0.0558	0.0428	0.7480	-
0.3921	1500	0.0403	0.0335	0.7665	-
0.5227	2000	0.0324	0.0285	0.7744	-
0.6534	2500	0.0284	0.0255	0.7987	-
0.7841	3000	0.0246	0.0225	0.7883	-
0.9148	3500	0.0217	0.0217	0.7964	-
1.0455	4000	0.0193	0.0187	0.8111	-
1.1762	4500	0.017	0.0174	0.8086	-
1.3068	5000	0.0163	0.0170	0.8157	-
1.4375	5500	0.0157	0.0161	0.8000	-
1.5682	6000	0.015	0.0156	0.8133	-
1.6989	6500	0.0146	0.0146	0.8194	-
1.8296	7000	0.014	0.0140	0.8103	-
1.9603	7500	0.013	0.0132	0.8205	-
2.0910	8000	0.0111	0.0126	0.8353	-
2.2216	8500	0.0102	0.0123	0.8407	-
2.3523	9000	0.0101	0.0118	0.8389	-
2.4830	9500	0.01	0.0115	0.8444	-
2.6137	10000	0.0097	0.0111	0.8456	-
2.7444	10500	0.0097	0.0105	0.8524	-
2.8751	11000	0.0091	0.0102	0.8526	-
3.0058	11500	0.0088	0.0100	0.8561	-
3.1364	12000	0.0069	0.0095	0.8619	-
3.2671	12500	0.0071	0.0094	0.8534	-
3.3978	13000	0.0068	0.0092	0.8648	-
3.5285	13500	0.0069	0.0093	0.8638	-
3.6592	14000	0.0071	0.0091	0.8548	-
3.7899	14500	0.0065	0.0085	0.8711	-
3.9205	15000	0.0064	0.0084	0.8622	-
4.0512	15500	0.0061	0.0080	0.8675	-
4.1819	16000	0.0051	0.0082	0.8673	-
4.3126	16500	0.0052	0.0080	0.8659	-
4.4433	17000	0.0053	0.0078	0.8669	-
4.5740	17500	0.0053	0.0077	0.8690	-
4.7047	18000	0.005	0.0076	0.8758	-
4.8353	18500	0.0048	0.0074	0.8700	-
4.9660	19000	0.0049	0.0072	0.8785	-
5.0967	19500	0.0041	0.0070	0.8795	-
5.2274	20000	0.0039	0.0071	0.8803	-
5.3581	20500	0.0039	0.0071	0.8843	-
5.4888	21000	0.0041	0.0070	0.8818	-
5.6194	21500	0.0039	0.0069	0.8812	-
5.7501	22000	0.0038	0.0068	0.8868	-
5.8808	22500	0.0038	0.0067	0.8831	-
6.0115	23000	0.0037	0.0066	0.8869	-
6.1422	23500	0.003	0.0065	0.8888	-
6.2729	24000	0.0031	0.0064	0.8879	-
6.4036	24500	0.0032	0.0064	0.8881	-
6.5342	25000	0.003	0.0062	0.8919	-
6.6649	25500	0.0031	0.0062	0.8919	-
6.7956	26000	0.0031	0.0061	0.8910	-
6.9263	26500	0.003	0.0061	0.8911	-
7.0570	27000	0.0028	0.0061	0.8925	-
7.1877	27500	0.0025	0.0061	0.8922	-
7.3183	28000	0.0026	0.0060	0.8944	-
7.4490	28500	0.0026	0.0061	0.8953	-
7.5797	29000	0.0026	0.0060	0.8948	-
7.7104	29500	0.0025	0.0060	0.8941	-
7.8411	30000	0.0025	0.0059	0.8950	-
7.9718	30500	0.0025	0.0059	0.8951	-
8.0	30608	-	-	-	0.8922

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

bibtex

@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",
}

	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