--- tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:350 - loss:MultipleNegativesRankingLoss base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 widget: - source_sentence: Data pengeluaran bulanan rumah tangga pedesaan untuk konsumsi makanan dan non-makanan per provinsi, tahun berapa saja tersedia? sentences: - Sistem Neraca Sosial Ekonomi Indonesia Tahun 2022 (84 x 84) - Persentase RataRata Pengeluaran per Kapita Sebulan Untuk Makanan dan Bukan Makanan di Daerah Perdesaan Menurut Provinsi, 2007-2024 - Nilai Impor Jawa Madura Menurut Pelabuhan Impor di Pulau Jawa Madura Tahun 2009 - 2013 (Juta US $) 1) - source_sentence: Asal impor gula Indonesia periode 2017 hingga 2023 sentences: - Banyaknya Anggota Kadinda Menurut Kabupaten/Kota di Provinsi Jawa Tengah, 2019 - Impor Gula menurut Negara Asal Utama, 2017-2023 - Rata-rata Pendapatan Bersih Pekerja Bebas Menurut Provinsi dan Kelompok Umur, 2023 - source_sentence: Laju kehilangan hutan Indonesia dalam dan luar kawasan hutan 2013-2022. sentences: - Institusi Pemerintah Neraca Institusi Terintegrasi (Triliun Rupiah), 2016 2023 - Angka Deforestasi (Netto) Indonesia di Dalam dan di Luar Kawasan Hutan Tahun 2013-2022 (Ha/Th) - Produksi Perkebunan Menurut Kabupaten/Kota dan Jenis Tanaman di Provinsi Jawa Tengah (ton), 2021 dan 2022 - source_sentence: Kemana saja lada putih Indonesia diekspor pada periode 2012 sampai 2023? sentences: - Rata-rata Pendapatan Bersih Pekerja Bebas Menurut Provinsi dan Kelompok Umur, 2022-2023 - Ekspor Lada Putih menurut Negara Tujuan Utama, 2012-2023 - Angka Kelahiran Kasar (Crude Birth Rate) Hasil Long Form SP2020 Menurut Provinsi/Kabupaten/Kota, 2020 - source_sentence: data gaji bersih pegawai per bulan tahun 2023 berdasarkan pendidikan dan jenis pekerjaan utama sentences: - Rata-rata Upah/Gaji Bersih Sebulan Buruh/Karyawan/Pegawai Menurut Pendidikan Tertinggi yang Ditamatkan dan Jenis Pekerjaan Utama, 2023 - Banyaknya Kunjungan Kapal Melalui Pelabuhan Jepara Menurut Jenis Pelayaran Tahun 2009 - 2013 - Ekspor Sarang Burung menurut Negara Tujuan Utama, 2012-2023 pipeline_tag: sentence-similarity library_name: sentence-transformers metrics: - cosine_accuracy@1 - cosine_accuracy@3 - cosine_accuracy@5 - cosine_accuracy@10 - cosine_precision@1 - cosine_precision@3 - cosine_precision@5 - cosine_precision@10 - cosine_recall@1 - cosine_recall@3 - cosine_recall@5 - cosine_recall@10 - cosine_ndcg@10 - cosine_mrr@10 - cosine_map@100 model-index: - name: SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 results: - task: type: information-retrieval name: Information Retrieval dataset: name: bps val mfd all type: bps-val-mfd-all metrics: - type: cosine_accuracy@1 value: 0.9861111111111112 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.9861111111111112 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.9861111111111112 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.9861111111111112 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.9861111111111112 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.9351851851851851 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.9055555555555554 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.8333333333333334 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.016151592322246593 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.0425075387306992 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.06836160354671791 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.11202747994449548 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.8706665539282586 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.9861111111111112 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.44673547368787836 name: Cosine Map@100 --- # 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 csv 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:** - csv ### 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("sentence_transformers_model_id") # Run inference sentences = [ 'data gaji bersih pegawai per bulan tahun 2023 berdasarkan pendidikan dan jenis pekerjaan utama', 'Rata-rata Upah/Gaji Bersih Sebulan Buruh/Karyawan/Pegawai Menurut Pendidikan Tertinggi yang Ditamatkan dan Jenis Pekerjaan Utama, 2023', 'Banyaknya Kunjungan Kapal Melalui Pelabuhan Jepara Menurut Jenis Pelayaran Tahun 2009 - 2013', ] 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 #### Information Retrieval * Dataset: `bps-val-mfd-all` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) | Metric | Value | |:--------------------|:-----------| | cosine_accuracy@1 | 0.9861 | | cosine_accuracy@3 | 0.9861 | | cosine_accuracy@5 | 0.9861 | | cosine_accuracy@10 | 0.9861 | | cosine_precision@1 | 0.9861 | | cosine_precision@3 | 0.9352 | | cosine_precision@5 | 0.9056 | | cosine_precision@10 | 0.8333 | | cosine_recall@1 | 0.0162 | | cosine_recall@3 | 0.0425 | | cosine_recall@5 | 0.0684 | | cosine_recall@10 | 0.112 | | **cosine_ndcg@10** | **0.8707** | | cosine_mrr@10 | 0.9861 | | cosine_map@100 | 0.4467 | ## Training Details ### Training Dataset #### csv * Dataset: csv * Size: 350 training samples * Columns: query, positive, and negative * Approximate statistics based on the first 350 samples: | | query | positive | negative | |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| | type | string | string | string | | details | | | | * Samples: | query | positive | negative | |:--------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------| | Bagaimana pengeluaran rumah tangga per orang di Indonesia berubah dari 2010 sampai 2024? | Distribusi Pembagian Pengeluaran per Kapita dan Indeks Gini, 2010-2024 | Proyeksi Beban Pencemaran Udara Menurut Industri di Jawa Tengah Tahun 2020 (Ton/Tahun) | | Data kesenjangan pendapatan di Indonesia tahun 2010-2024: indeks Gini dan pengeluaran rata-rata. | Distribusi Pembagian Pengeluaran per Kapita dan Indeks Gini, 2010-2024 | Banyaknya Mahasiswa dan Dosen Pada Perguruan Tinggi Agama Islam Swasta di Jawa Tengah, 2018/2019 | | Berapa konsumsi makanan pokok per orang per minggu di Indonesia tahun 2007-2024? | Rata-Rata Konsumsi per Kapita Seminggu Beberapa Macam Bahan Makanan Penting, 2007-2024 | Rekapitulasi Industri Non Formal Yang Baru Menurut Kabupaten/kota 2012 | * Loss: [MultipleNegativesRankingLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: steps - `per_device_train_batch_size`: 32 - `per_device_eval_batch_size`: 32 - `weight_decay`: 0.01 - `warmup_ratio`: 0.1 - `fp16`: True - `load_best_model_at_end`: 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`: 0.01 - `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} - `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 - `hub_revision`: None - `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`: False - `use_liger_kernel`: False - `liger_kernel_config`: None - `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 | bps-val-mfd-all_cosine_ndcg@10 | |:----------:|:------:|:------------------------------:| | 0.9091 | 10 | 0.8300 | | **1.8182** | **20** | **0.8736** | | 2.7273 | 30 | 0.8707 | * The bold row denotes the saved checkpoint. ### Framework Versions - Python: 3.10.11 - Sentence Transformers: 3.4.0 - Transformers: 4.53.1 - PyTorch: 2.7.1+cpu - Accelerate: 1.8.1 - Datasets: 3.6.0 - Tokenizers: 0.21.2 ## 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", } ``` #### MultipleNegativesRankingLoss ```bibtex @misc{henderson2017efficient, title={Efficient Natural Language Response Suggestion for Smart Reply}, author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil}, year={2017}, eprint={1705.00652}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```