--- tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:79621 - loss:CosineSimilarityLoss base_model: sentence-transformers/paraphrase-multilingual-mpnet-base-v2 widget: - source_sentence: Data demografi Indonesia 2021 perempuan dan lakilaki sentences: - Buletin Statistik Perdagangan Luar Negeri Ekspor Menurut Komoditi HS, Februari 2015 - Statistik Potensi Desa Provinsi Jawa Barat 2014 - Pengeluaran untuk Konsumsi Penduduk Indonesia, September 2017 - source_sentence: Data analisis tematik kependudukan Indonesia migrasi dan ketenagakerjaan sentences: - Direktori Perusahaan Industri Penggilingan Padi Tahun 2012 Provinsi Bengkulu - Buletin Statistik Perdagangan Luar Negeri Ekspor Menurut HS, Juni 2023 - Luas Panen dan Produksi Padi 2022 - source_sentence: Daftar perusahaan penggilingan padi Kalimantan sentences: - Ringkasan Neraca Arus Dana, Triwulan II, 2011*), (Miliar Rupiah) - Klasifikasi Baku Komoditas Indonesia 2012 Buku 1 - Statistik Penduduk Lanjut Usia Provinsi Nusa Tenggara Barat 2010-Hasil Sensus Penduduk 2010 - source_sentence: Perdagangan luar negeri impor Januari 2010 sentences: - Buletin Statistik Perdagangan Luar Negeri Impor Januari 2010 - Statistik Tanaman Sayuran dan Buah-buahan Semusim Indonesia 2012 - Klasifikasi Baku Komoditas Indonesia (KBKI) 2012 Buku 4 - source_sentence: Biaya hidup kelompok perumahan Indonesia 2017 sentences: - Indeks Harga Perdagangan Besar 2007 - Statistik Upah 2013 - Survei Biaya Hidup (SBH) 2018 Bulukumba, Watampone, Makassar, Pare-Pare, dan Palopo datasets: - yahyaabd/allstats-search-pairs-dataset 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 mpnet eval type: allstats-semantic-mpnet-eval metrics: - type: pearson_cosine value: 0.9830659002996571 name: Pearson Cosine - type: spearman_cosine value: 0.8410118780087822 name: Spearman Cosine - task: type: semantic-similarity name: Semantic Similarity dataset: name: allstats semantic mpnet test type: allstats-semantic-mpnet-test metrics: - type: pearson_cosine value: 0.9831682336847792 name: Pearson Cosine - type: spearman_cosine value: 0.8378561244643341 name: Spearman Cosine --- # SentenceTransformer based on sentence-transformers/paraphrase-multilingual-mpnet-base-v2 This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2) on the [allstats-search-pairs-dataset](https://huggingface.co/datasets/yahyaabd/allstats-search-pairs-dataset) 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](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2) - **Maximum Sequence Length:** 128 tokens - **Output Dimensionality:** 768 dimensions - **Similarity Function:** Cosine Similarity - **Training Dataset:** - [allstats-search-pairs-dataset](https://huggingface.co/datasets/yahyaabd/allstats-search-pairs-dataset) ### 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: 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: ```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/test-model") # Run inference sentences = [ 'Biaya hidup kelompok perumahan Indonesia 2017', 'Statistik Upah 2013', 'Survei Biaya Hidup (SBH) 2018 Bulukumba, Watampone, Makassar, Pare-Pare, dan Palopo', ] 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-mpnet-eval` and `allstats-semantic-mpnet-test` * Evaluated with [EmbeddingSimilarityEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) | Metric | allstats-semantic-mpnet-eval | allstats-semantic-mpnet-test | |:--------------------|:-----------------------------|:-----------------------------| | pearson_cosine | 0.9831 | 0.9832 | | **spearman_cosine** | **0.841** | **0.8379** | ## Training Details ### Training Dataset #### allstats-search-pairs-dataset * Dataset: [allstats-search-pairs-dataset](https://huggingface.co/datasets/yahyaabd/allstats-search-pairs-dataset) at [6712cb1](https://huggingface.co/datasets/yahyaabd/allstats-search-pairs-dataset/tree/6712cb14bbd89da6f87890ac082b09e0adb7a02e) * Size: 79,621 training samples * Columns: query, doc, and label * Approximate statistics based on the first 1000 samples: | | query | doc | label | |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------| | type | string | string | float | | details | | | | * Samples: | query | doc | label | |:--------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------|:------------------| | Produksi jagung di Indonesia tahun 2009 | Indeks Unit Value Ekspor Menurut Kode SITC Bulan Februari 2024 | 0.1 | | Data produksi industri manufaktur 2021 | Perkembangan Indeks Produksi Industri Manufaktur 2021 | 0.96 | | direktori perusahaan industri penggilingan padi tahun 2012 provinsi sulawesi utara dan gorontalo | Neraca Pemerintahan Umum Indonesia 2007-2012 | 0.03 | * Loss: [CosineSimilarityLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters: ```json { "loss_fct": "torch.nn.modules.loss.MSELoss" } ``` ### Evaluation Dataset #### allstats-search-pairs-dataset * Dataset: [allstats-search-pairs-dataset](https://huggingface.co/datasets/yahyaabd/allstats-search-pairs-dataset) at [6712cb1](https://huggingface.co/datasets/yahyaabd/allstats-search-pairs-dataset/tree/6712cb14bbd89da6f87890ac082b09e0adb7a02e) * Size: 9,952 evaluation samples * Columns: query, doc, and label * Approximate statistics based on the first 1000 samples: | | query | doc | label | |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------| | type | string | string | float | | details | | | | * Samples: | query | doc | label | |:--------------------------------------------------------------------|:-----------------------------------------------------------------|:------------------| | Daftar perusahaan industri pengolahan skala kecil 2006 | Statistik Migrasi Nusa Tenggara Barat Hasil SP 2010 | 0.05 | | Populasi Indonesia per provinsi 2000-2010 | Indikator Ekonomi Desember 2023 | 0.08 | | Data harga barang desa non-pangan tahun 2022 | Statistik Kunjungan Tamu Asing 2004 | 0.1 | * Loss: [CosineSimilarityLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters: ```json { "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 - `num_train_epochs`: 6 - `warmup_ratio`: 0.1 - `fp16`: True - `dataloader_num_workers`: 4 - `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`: 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`: 6 - `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`: 4 - `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`: 0.01 - `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 - `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-mpnet-eval_spearman_cosine | allstats-semantic-mpnet-test_spearman_cosine | |:----------:|:---------:|:-------------:|:---------------:|:--------------------------------------------:|:--------------------------------------------:| | 0 | 0 | - | 0.0958 | 0.6404 | - | | 0.1004 | 250 | 0.0482 | 0.0269 | 0.7685 | - | | 0.2009 | 500 | 0.0249 | 0.0200 | 0.7737 | - | | 0.3013 | 750 | 0.0196 | 0.0172 | 0.7768 | - | | 0.4018 | 1000 | 0.0184 | 0.0172 | 0.7744 | - | | 0.5022 | 1250 | 0.0185 | 0.0159 | 0.7751 | - | | 0.6027 | 1500 | 0.0155 | 0.0156 | 0.7825 | - | | 0.7031 | 1750 | 0.0165 | 0.0149 | 0.7826 | - | | 0.8035 | 2000 | 0.0146 | 0.0136 | 0.7791 | - | | 0.9040 | 2250 | 0.0132 | 0.0127 | 0.7825 | - | | 1.0044 | 2500 | 0.0127 | 0.0129 | 0.7818 | - | | 1.1049 | 2750 | 0.0104 | 0.0114 | 0.7849 | - | | 1.2053 | 3000 | 0.009 | 0.0108 | 0.7870 | - | | 1.3057 | 3250 | 0.0091 | 0.0112 | 0.7877 | - | | 1.4062 | 3500 | 0.009 | 0.0104 | 0.7888 | - | | 1.5066 | 3750 | 0.009 | 0.0101 | 0.7937 | - | | 1.6071 | 4000 | 0.0084 | 0.0099 | 0.7924 | - | | 1.7075 | 4250 | 0.008 | 0.0097 | 0.7942 | - | | 1.8080 | 4500 | 0.0079 | 0.0094 | 0.7946 | - | | 1.9084 | 4750 | 0.0078 | 0.0092 | 0.7928 | - | | 2.0088 | 5000 | 0.0081 | 0.0088 | 0.7986 | - | | 2.1093 | 5250 | 0.0056 | 0.0079 | 0.8025 | - | | 2.2097 | 5500 | 0.0052 | 0.0080 | 0.8019 | - | | 2.3102 | 5750 | 0.0048 | 0.0079 | 0.8073 | - | | 2.4106 | 6000 | 0.0053 | 0.0081 | 0.8058 | - | | 2.5110 | 6250 | 0.0049 | 0.0079 | 0.8091 | - | | 2.6115 | 6500 | 0.0053 | 0.0077 | 0.8081 | - | | 2.7119 | 6750 | 0.0052 | 0.0075 | 0.8075 | - | | 2.8124 | 7000 | 0.0049 | 0.0077 | 0.8089 | - | | 2.9128 | 7250 | 0.0051 | 0.0076 | 0.8066 | - | | 3.0133 | 7500 | 0.0048 | 0.0074 | 0.8127 | - | | 3.1137 | 7750 | 0.0034 | 0.0069 | 0.8162 | - | | 3.2141 | 8000 | 0.0033 | 0.0070 | 0.8164 | - | | 3.3146 | 8250 | 0.0036 | 0.0068 | 0.8194 | - | | 3.4150 | 8500 | 0.0032 | 0.0069 | 0.8156 | - | | 3.5155 | 8750 | 0.0032 | 0.0068 | 0.8196 | - | | 3.6159 | 9000 | 0.0032 | 0.0067 | 0.8197 | - | | 3.7164 | 9250 | 0.0034 | 0.0068 | 0.8194 | - | | 3.8168 | 9500 | 0.0034 | 0.0066 | 0.8194 | - | | 3.9172 | 9750 | 0.0032 | 0.0063 | 0.8239 | - | | 4.0177 | 10000 | 0.0032 | 0.0065 | 0.8229 | - | | 4.1181 | 10250 | 0.0023 | 0.0063 | 0.8258 | - | | 4.2186 | 10500 | 0.0022 | 0.0062 | 0.8293 | - | | 4.3190 | 10750 | 0.002 | 0.0063 | 0.8283 | - | | 4.4194 | 11000 | 0.0023 | 0.0060 | 0.8306 | - | | 4.5199 | 11250 | 0.0021 | 0.0061 | 0.8318 | - | | 4.6203 | 11500 | 0.0021 | 0.0060 | 0.8290 | - | | 4.7208 | 11750 | 0.0022 | 0.0058 | 0.8329 | - | | 4.8212 | 12000 | 0.0021 | 0.0058 | 0.8342 | - | | 4.9217 | 12250 | 0.0021 | 0.0058 | 0.8360 | - | | 5.0221 | 12500 | 0.0017 | 0.0057 | 0.8355 | - | | 5.1225 | 12750 | 0.0014 | 0.0057 | 0.8377 | - | | 5.2230 | 13000 | 0.0015 | 0.0058 | 0.8363 | - | | 5.3234 | 13250 | 0.0015 | 0.0058 | 0.8369 | - | | 5.4239 | 13500 | 0.0014 | 0.0057 | 0.8386 | - | | 5.5243 | 13750 | 0.0014 | 0.0057 | 0.8387 | - | | 5.6247 | 14000 | 0.0015 | 0.0057 | 0.8392 | - | | **5.7252** | **14250** | **0.0014** | **0.0056** | **0.8409** | **-** | | 5.8256 | 14500 | 0.0014 | 0.0056 | 0.8410 | - | | 5.9261 | 14750 | 0.0014 | 0.0056 | 0.8410 | - | | 6.0 | 14934 | - | - | - | 0.8379 | * The bold row denotes the saved checkpoint. ### Framework Versions - Python: 3.10.12 - Sentence Transformers: 3.3.1 - Transformers: 4.48.0 - PyTorch: 2.5.1+cu121 - 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", } ```