--- tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:110773 - loss:ContrastiveLoss base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 widget: - source_sentence: average monthly net wage/salary, employees, by province and occupation (rupiah), 2018 sentences: - '[Seri 2000] Laju Pertumbuhan PDB Triwulanan Atas Dasar Harga Konstan 2000 Terhadap Triwulan Sebelumnya, 2001-2014' - IHK dan Rata-rata Upah per Bulan Buruh Industri di Bawah Mandor (Supervisor), 2012-2014 (2012=100) - Rata-rata Upah/Gaji Bersih Sebulan Buruh/Karyawan/Pegawai Menurut Kelompok Umur dan Lapangan Pekerjaan Utama di 9 Sektor (Rupiah), 2017 - source_sentence: 'data belanja dan konsumsi per orang di jambi, 2020: fokus pada makanan dan tingkat pengeluaran' sentences: - Rata-rata Konsumsi dan Pengeluaran Perkapita Seminggu Menurut Komoditi Makanan dan Golongan Pengeluaran per Kapita Seminggu di Provinsi Sulawesi Tenggara, 2018-2023 - Rata-rata Pendapatan Bersih Pekerja Bebas Menurut Provinsi dan Pendidikan Tertinggi yang Ditamatkan (ribu rupiah), 2017 - Rata-rata Konsumsi dan Pengeluaran Perkapita Seminggu Menurut Komoditi Makanan dan Golongan Pengeluaran per Kapita Seminggu di Provinsi Jawa Timur, 2018-2023 - source_sentence: 'ALIRAN DANA RUPIAH: Q1 2008' sentences: - Sistem Neraca Sosial Ekonomi Indonesia Tahun 2022 dalam Format SNA 1968 (65x65) - Rata-rata Upah/Gaji Bersih Sebulan Buruh/Karyawan/Pegawai Menurut Provinsi dan Jenis Pekerjaan Utama, 2024 - Impor Besi dan Baja Menurut Negara Asal Utama, 2017-2023 - source_sentence: 'Aliran Wdana Rupiah: Q1 2008' sentences: - Ekspor Karet Remah Menurut Negara Tujuan Utama, 2012-2023 - Rata-rata Upah/Gaji Bersih Sebulan Buruh/Karyawan/Pegawai Menurut Kelompok Umur dan Lapangan Pekerjaan Utama di 17 Sektor (Rupiah), 2018 - Sistem Neraca Sosial Ekonomi Indonesia Tahun 2022 dalam Format SNA 1968 (65x65) - source_sentence: 'Aliran dana Rupiah: Q1 2008' sentences: - Ringkasan Neraca Arus Dana, Triwulan II, 2011*), (Miliar Rupiah) - Ringkasan Neraca Arus Dana, 2012 (Miliar Rupiah) - IHK dan Rata-rata Upah per Bulan Buruh Industri di Bawah Mandor (Supervisor), 2012-2014 (2012=100) datasets: - yahyaabd/query-pos-neg-doc-pairs-statictable pipeline_tag: sentence-similarity library_name: sentence-transformers metrics: - cosine_accuracy - cosine_accuracy_threshold - cosine_f1 - cosine_f1_threshold - cosine_precision - cosine_recall - cosine_ap - cosine_mcc model-index: - name: SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 results: - task: type: binary-classification name: Binary Classification dataset: name: allstats semantic mini v1 test type: allstats-semantic-mini-v1_test metrics: - type: cosine_accuracy value: 0.9678628590683177 name: Cosine Accuracy - type: cosine_accuracy_threshold value: 0.7482147812843323 name: Cosine Accuracy Threshold - type: cosine_f1 value: 0.9677936769237264 name: Cosine F1 - type: cosine_f1_threshold value: 0.7444144487380981 name: Cosine F1 Threshold - type: cosine_precision value: 0.9595714405290031 name: Cosine Precision - type: cosine_recall value: 0.976158038147139 name: Cosine Recall - type: cosine_ap value: 0.9921512853632306 name: Cosine Ap - type: cosine_mcc value: 0.9358669477790009 name: Cosine Mcc - task: type: binary-classification name: Binary Classification dataset: name: allstats semantic mini v1 dev type: allstats-semantic-mini-v1_dev metrics: - type: cosine_accuracy value: 0.9678491772924294 name: Cosine Accuracy - type: cosine_accuracy_threshold value: 0.7902499437332153 name: Cosine Accuracy Threshold - type: cosine_f1 value: 0.9673587968896863 name: Cosine F1 - type: cosine_f1_threshold value: 0.7874833345413208 name: Cosine F1 Threshold - type: cosine_precision value: 0.9616887529731566 name: Cosine Precision - type: cosine_recall value: 0.9730960976448341 name: Cosine Recall - type: cosine_ap value: 0.9930288231258318 name: Cosine Ap - type: cosine_mcc value: 0.9357491510325107 name: Cosine Mcc --- # SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) on the [query-pos-neg-doc-pairs-statictable](https://huggingface.co/datasets/yahyaabd/query-pos-neg-doc-pairs-statictable) 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](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) - **Maximum Sequence Length:** 128 tokens - **Output Dimensionality:** 384 dimensions - **Similarity Function:** Cosine Similarity - **Training Dataset:** - [query-pos-neg-doc-pairs-statictable](https://huggingface.co/datasets/yahyaabd/query-pos-neg-doc-pairs-statictable) ### 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: 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: ```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-search-miniLM-v1-7") # Run inference sentences = [ 'Aliran dana Rupiah: Q1 2008', 'IHK dan Rata-rata Upah per Bulan Buruh Industri di Bawah Mandor (Supervisor), 2012-2014 (2012=100)', 'Ringkasan Neraca Arus Dana, 2012 (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 #### Binary Classification * Datasets: `allstats-semantic-mini-v1_test` and `allstats-semantic-mini-v1_dev` * Evaluated with [BinaryClassificationEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator) | Metric | allstats-semantic-mini-v1_test | allstats-semantic-mini-v1_dev | |:--------------------------|:-------------------------------|:------------------------------| | cosine_accuracy | 0.9679 | 0.9678 | | cosine_accuracy_threshold | 0.7482 | 0.7902 | | cosine_f1 | 0.9678 | 0.9674 | | cosine_f1_threshold | 0.7444 | 0.7875 | | cosine_precision | 0.9596 | 0.9617 | | cosine_recall | 0.9762 | 0.9731 | | **cosine_ap** | **0.9922** | **0.993** | | cosine_mcc | 0.9359 | 0.9357 | ## Training Details ### Training Dataset #### query-pos-neg-doc-pairs-statictable * Dataset: [query-pos-neg-doc-pairs-statictable](https://huggingface.co/datasets/yahyaabd/query-pos-neg-doc-pairs-statictable) at [a31b58d](https://huggingface.co/datasets/yahyaabd/query-pos-neg-doc-pairs-statictable/tree/a31b58d221edcddb16274a04b2fafe56df68801a) * Size: 110,773 training samples * Columns: query, doc, and label * Approximate statistics based on the first 1000 samples: | | query | doc | label | |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------| | type | string | string | int | | details | | | | * Samples: | query | doc | label | |:-----------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------|:---------------| | Data orang yang naik/turun kapal, di pelabuhan yang dikelola maupun tidak, sekitar 2015 | Tabel Input-Output Indonesia Transaksi Total Atas Dasar Harga Dasar (185 Produk), 2016 (Juta Rupiah) | 0 | | data orang yang naik/turun kapal, di pelabuhan yang dikelola maupun tidak, sekitar 2015 | Tabel Input-Output Indonesia Transaksi Total Atas Dasar Harga Dasar (185 Produk), 2016 (Juta Rupiah) | 0 | | DATA ORANG YANG NAIK/TURUN KAPAL, DI PELABUHAN YANG DIKELOLA MAUPUN TIDAK, SEKITAR 2015 | Tabel Input-Output Indonesia Transaksi Total Atas Dasar Harga Dasar (185 Produk), 2016 (Juta Rupiah) | 0 | * Loss: [ContrastiveLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters: ```json { "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE", "margin": 0.5, "size_average": true } ``` ### Evaluation Dataset #### query-pos-neg-doc-pairs-statictable * Dataset: [query-pos-neg-doc-pairs-statictable](https://huggingface.co/datasets/yahyaabd/query-pos-neg-doc-pairs-statictable) at [a31b58d](https://huggingface.co/datasets/yahyaabd/query-pos-neg-doc-pairs-statictable/tree/a31b58d221edcddb16274a04b2fafe56df68801a) * Size: 23,763 evaluation samples * Columns: query, doc, and label * Approximate statistics based on the first 1000 samples: | | query | doc | label | |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------| | type | string | string | int | | details | | | | * Samples: | query | doc | label | |:------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------|:---------------| | Cek penghasilan bulanan (gaji bersih) buruh/pegawai, per provinsi dan jenis pekerjaannya, 2019 | Rata-rata Pendapatan Bersih Berusaha Sendiri Menurut Provinsi dan Lapangan Pekerjaan Utama, 2021 | 1 | | cek penghasilan bulanan (gaji bersih) buruh/pegawai, per provinsi dan jenis pekerjaannya, 2019 | Rata-rata Pendapatan Bersih Berusaha Sendiri Menurut Provinsi dan Lapangan Pekerjaan Utama, 2021 | 1 | | CEK PENGHASILAN BULANAN (GAJI BERSIH) BURUH/PEGAWAI, PER PROVINSI DAN JENIS PEKERJAANNYA, 2019 | Rata-rata Pendapatan Bersih Berusaha Sendiri Menurut Provinsi dan Lapangan Pekerjaan Utama, 2021 | 1 | * Loss: [ContrastiveLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters: ```json { "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE", "margin": 0.5, "size_average": true } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: steps - `per_device_train_batch_size`: 64 - `per_device_eval_batch_size`: 64 - `num_train_epochs`: 1 - `warmup_ratio`: 0.2 - `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`: 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`: 1 - `max_steps`: -1 - `lr_scheduler_type`: linear - `lr_scheduler_kwargs`: {} - `warmup_ratio`: 0.2 - `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-mini-v1_test_cosine_ap | allstats-semantic-mini-v1_dev_cosine_ap | |:----------:|:--------:|:-------------:|:---------------:|:----------------------------------------:|:---------------------------------------:| | -1 | -1 | - | - | 0.8699 | - | | 0 | 0 | - | 0.0489 | - | 0.8658 | | 0.0578 | 100 | 0.0222 | 0.0101 | - | 0.9458 | | 0.1155 | 200 | 0.0087 | 0.0073 | - | 0.9631 | | 0.1733 | 300 | 0.007 | 0.0059 | - | 0.9710 | | 0.2311 | 400 | 0.0056 | 0.0049 | - | 0.9828 | | 0.2889 | 500 | 0.0045 | 0.0044 | - | 0.9837 | | 0.3466 | 600 | 0.0042 | 0.0041 | - | 0.9862 | | 0.4044 | 700 | 0.0038 | 0.0038 | - | 0.9888 | | 0.4622 | 800 | 0.0037 | 0.0037 | - | 0.9890 | | 0.5199 | 900 | 0.0029 | 0.0036 | - | 0.9889 | | 0.5777 | 1000 | 0.0031 | 0.0034 | - | 0.9907 | | 0.6355 | 1100 | 0.0029 | 0.0033 | - | 0.9923 | | 0.6932 | 1200 | 0.0025 | 0.0034 | - | 0.9922 | | 0.7510 | 1300 | 0.0025 | 0.0033 | - | 0.9929 | | 0.8088 | 1400 | 0.0024 | 0.0033 | - | 0.9928 | | 0.8666 | 1500 | 0.0022 | 0.0033 | - | 0.9926 | | 0.9243 | 1600 | 0.0023 | 0.0033 | - | 0.9929 | | **0.9821** | **1700** | **0.0022** | **0.0032** | **-** | **0.993** | | -1 | -1 | - | - | 0.9922 | - | * 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 ```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", } ``` #### ContrastiveLoss ```bibtex @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} } ```