yahyaabd/allstats-search-mini-v1-1-mnrl-sts

SentenceTransformer based on yahyaabd/allstats-search-mini-v1-1-mnrl

This is a sentence-transformers model finetuned from yahyaabd/allstats-search-mini-v1-1-mnrl on the bps-sts-dataset-v1 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: yahyaabd/allstats-search-mini-v1-1-mnrl
• Maximum Sequence Length: 128 tokens
• Output Dimensionality: 384 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • bps-sts-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: 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-search-mini-v1-1-mnrl-sts")
# Run inference
sentences = [
    'PDRB per kapita Provinsi Riau sangat dipengaruhi oleh harga minyak bumi dunia.',
    'The Riau Islands province is known for its beautiful beaches and marine tourism.',
    'Di wilayah perkotaan, angka kemiskinan pada Maret 2023 adalah 7,29%.',
]
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: sts-dev and sts-test
• Evaluated with EmbeddingSimilarityEvaluator

Metric	sts-dev	sts-test
pearson_cosine	0.8384	0.8686
spearman_cosine	0.8363	0.8631

Training Details

Training Dataset

bps-sts-dataset-v1

• Dataset: bps-sts-dataset-v1 at 5c8f96e
• Size: 2,436 training samples
• Columns: sentence1, sentence2, and score
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	score
  type	string	string	float
  details	min: 6 tokens mean: 20.49 tokens max: 36 tokens	min: 9 tokens mean: 20.71 tokens max: 45 tokens	min: 0.0 mean: 0.51 max: 1.0

• Samples:

  sentence1	sentence2	score
  bagaimana capaian Tujuan Pembangunan Berkelanjutan di Indonesia?	Laporan Pencapaian Indikator Tujuan Pembangunan Berkelanjutan (TPB/SDGs) Indonesia, Edisi 2024	0.8
  Jumlah perpustakaan umum di Indonesia tahun 2022 sebanyak 170.000 unit.	Minat baca masyarakat Indonesia masih perlu ditingkatkan melalui berbagai program literasi.	0.4
  Jumlah sekolah negeri jenjang SMP di Kota Bandar Lampung adalah 30 sekolah.	Laju deforestasi di Provinsi Kalimantan Tengah masih mengkhawatirkan.	0.0

• Loss: CosineSimilarityLoss with these parameters:

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

Evaluation Dataset

bps-sts-dataset-v1

• Dataset: bps-sts-dataset-v1 at 5c8f96e
• Size: 522 evaluation samples
• Columns: sentence1, sentence2, and score
• Approximate statistics based on the first 522 samples:

  	sentence1	sentence2	score
  type	string	string	float
  details	min: 9 tokens mean: 20.83 tokens max: 39 tokens	min: 8 tokens mean: 20.84 tokens max: 44 tokens	min: 0.0 mean: 0.5 max: 1.0

• Samples:

  sentence1	sentence2	score
  Persentase desa yang memiliki fasilitas internet di Provinsi Y pada tahun 2021 adalah 85%.	Luas perkebunan kelapa sawit di Provinsi Y pada tahun 2021 adalah 500.000 hektar.	0.2
  Kontribusi sektor UMKM terhadap PDRB Kota Malang pada tahun 2023 sebesar 60%.	Usaha Mikro, Kecil, dan Menengah menyumbang 60 persen terhadap total Produk Domestik Regional Bruto di kota pendidikan Malang pada tahun 2023.	1.0
  Jumlah Industri Kecil dan Menengah (IKM) di Kabupaten Tegal, Jawa Tengah, bertambah 200 unit pada tahun 2024.	Di Tegal, sebuah kabupaten di Jateng, terjadi penambahan 200 unit IKM sepanjang tahun 2024.	1.0

• 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
• learning_rate: 1e-05
• warmup_ratio: 0.1
• fp16: True
• load_best_model_at_end: True
• label_smoothing_factor: 0.01
• 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: 1e-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: 3
• 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}
• tp_size: 0
• 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: 0.01
• 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
• 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	sts-dev_spearman_cosine	sts-test_spearman_cosine
0	0	-	0.0588	0.7404	-
0.1299	10	0.0535	0.0577	0.7454	-
0.2597	20	0.046	0.0539	0.7614	-
0.3896	30	0.0552	0.0497	0.7796	-
0.5195	40	0.0442	0.0470	0.7947	-
0.6494	50	0.0437	0.0450	0.8057	-
0.7792	60	0.0425	0.0438	0.8123	-
0.9091	70	0.0465	0.0423	0.8183	-
1.0390	80	0.0384	0.0414	0.8223	-
1.1688	90	0.0362	0.0405	0.8260	-
1.2987	100	0.0309	0.0401	0.8276	-
1.4286	110	0.0335	0.0397	0.8289	-
1.5584	120	0.033	0.0394	0.8307	-
1.6883	130	0.0272	0.0392	0.8317	-
1.8182	140	0.032	0.0390	0.8324	-
1.9481	150	0.0317	0.0387	0.8331	-
2.0779	160	0.0322	0.0385	0.8338	-
2.2078	170	0.0285	0.0383	0.8345	-
2.3377	180	0.0299	0.0382	0.8349	-
2.4675	190	0.0326	0.0381	0.8351	-
2.5974	200	0.0258	0.0380	0.8356	-
2.7273	210	0.0282	0.0379	0.8361	-
2.8571	220	0.0286	0.0379	0.8363	-
2.987	230	0.025	0.0379	0.8363	-
-1	-1	-	-	-	0.8631

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.11.12
• Sentence Transformers: 3.4.0
• Transformers: 4.51.3
• PyTorch: 2.6.0+cu124
• Accelerate: 1.6.0
• Datasets: 3.2.0
• Tokenizers: 0.21.1

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",
}