Add new SentenceTransformer model

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "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
+}

2_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 1024, "out_features": 256, "bias": true, "activation_function": "torch.nn.modules.activation.Tanh"}

2_Dense/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d09ad0eb39408096d3a5bc3c721a78a6a4407a9c1fd6bd3d89eef0ba4a299a8a
+size 1049760

README.md

@@ -0,0 +1,528 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:967831
+- loss:MultipleNegativesRankingLoss
+base_model: denaya/indoSBERT-large
+widget:
+- source_sentence: Penghasilan freelancer per provinsi, beda umur 2016
+  sentences:
+  - Rata-rata Pendapatan Bersih Pekerja Bebas Menurut Provinsi dan Kelompok Umur (ribu
+    rupiah), 2016
+  - Konkordansi Klasifikasi Tabel Inter Regional Input-Output Indonesia, 2016 (52
+    Industri - 17 Lapangan Usaha)
+  - Rata-rata Konsumsi dan Pengeluaran Perkapita Seminggu Menurut Komoditi Makanan
+    dan Golongan Pengeluaran per Kapita Seminggu di Provinsi Maluku, 2018-2023
+- source_sentence: Tren angka partisipasi sekolah di Indonesia (7-23 tahun) berdasarkan
+    gender dan kelompok umur, 2015-2023
+  sentences:
+  - Jumlah Sekolah, Guru, dan Murid Sekolah Dasar (SD) di Bawah Kementerian Pendidikan
+    dan Kebudayaan Menurut Provinsi Tahun Ajaran 2011/2012-2015/2016
+  - Rata-rata Harian Konsumsi Protein Per Kapita dan Konsumsi Kalori Per Kapita Tahun
+    1990 - 2023
+  - Persentase Penduduk Usia 7-23 Tahun Menurut Jenis Kelamin, Kelompok Umur Sekolah,
+    dan Partisipasi Sekolah, 2015-2023
+- source_sentence: Sumber penerangan rumah tangga per provinsi Indonesia 2018
+  sentences:
+  - Nutrisi
+  - Rata-rata Pendapatan Bersih Berusaha Sendiri Menurut Provinsi dan Lapangan Pekerjaan
+    Utama (ribu rupiah), 2016
+  - Persentase Rumah Tangga Menurut Provinsi dan Sumber Penerangan, 2015-2021
+- source_sentence: Rumah tangga dengan lampu hemat energi per provinsi, 2014 vs 2021
+    (urban vs rural)
+  sentences:
+  - Persentase Rumah Tangga yang Menggunakan Lampu Hemat Energi Menurut Provinsi dan
+    Daerah Tempat Tinggal, 2014, 2021
+  - Luas Daerah Pengaliran dan Debit dari Beberapa Sungai yang Daerah Pengalirannya
+    Lebih dari 100 km2, 2015
+  - Perolehan Suara dan Kursi Dewan Perwakilan Rakyat (DPR) Menurut Partai Politik
+    Hasil Pemilu Tahun 2009 dan 2014
+- source_sentence: 'Upah bulanan rata-rata: Hubungan pendidikan tertinggi dan sektor
+    pekerjaan utama, data 2021'
+  sentences:
+  - IHK dan Rata-rata Upah per Bulan Buruh Peternakan dan Perikanan di Bawah Mandor
+    (Supervisor), 2007-2014 (2007=100)
+  - Rata-rata Upah/Gaji Bersih Sebulan Buruh/Karyawan Pegawai Menurut Pendidikan Tertinggi
+    dan Jenis Pekerjaan Utama, 2021
+  - Rata-rata Upah/Gaji Bersih sebulan Buruh/Karyawan Pegawai Menurut Pendidikan Tertinggi
+    dan Lapangan Pekerjaan Utama, 2021
+datasets:
+- yahyaabd/statictable-triplets-all
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy@1
+- cosine_accuracy@5
+- cosine_accuracy@10
+- cosine_precision@1
+- cosine_precision@5
+- cosine_precision@10
+- cosine_recall@1
+- cosine_recall@5
+- cosine_recall@10
+- cosine_ndcg@1
+- cosine_ndcg@5
+- cosine_ndcg@10
+- cosine_mrr@1
+- cosine_mrr@5
+- cosine_mrr@10
+- cosine_map@1
+- cosine_map@5
+- cosine_map@10
+model-index:
+- name: SentenceTransformer based on denaya/indoSBERT-large
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: bps statictable ir
+      type: bps-statictable-ir
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.9218241042345277
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@5
+      value: 0.990228013029316
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.996742671009772
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.9218241042345277
+      name: Cosine Precision@1
+    - type: cosine_precision@5
+      value: 0.2247557003257329
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.13159609120521173
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7225077889088528
+      name: Cosine Recall@1
+    - type: cosine_recall@5
+      value: 0.793020064240505
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8181542032723246
+      name: Cosine Recall@10
+    - type: cosine_ndcg@1
+      value: 0.9218241042345277
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@5
+      value: 0.8340748596494166
+      name: Cosine Ndcg@5
+    - type: cosine_ndcg@10
+      value: 0.8332473439965864
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@1
+      value: 0.9218241042345277
+      name: Cosine Mrr@1
+    - type: cosine_mrr@5
+      value: 0.9522258414766559
+      name: Cosine Mrr@5
+    - type: cosine_mrr@10
+      value: 0.9532340623545834
+      name: Cosine Mrr@10
+    - type: cosine_map@1
+      value: 0.9218241042345277
+      name: Cosine Map@1
+    - type: cosine_map@5
+      value: 0.7919598262757872
+      name: Cosine Map@5
+    - type: cosine_map@10
+      value: 0.7847729133274736
+      name: Cosine Map@10
+---
+
+# SentenceTransformer based on denaya/indoSBERT-large
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [denaya/indoSBERT-large](https://huggingface.co/denaya/indoSBERT-large) on the [statictable-triplets-all](https://huggingface.co/datasets/yahyaabd/statictable-triplets-all) dataset. It maps sentences & paragraphs to a 256-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:** [denaya/indoSBERT-large](https://huggingface.co/denaya/indoSBERT-large) <!-- at revision 5c64d43f07f7054dfbf33d226b3066414b6ebc4a -->
+- **Maximum Sequence Length:** 256 tokens
+- **Output Dimensionality:** 256 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [statictable-triplets-all](https://huggingface.co/datasets/yahyaabd/statictable-triplets-all)
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### 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': 256, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 1024, '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})
+  (2): Dense({'in_features': 1024, 'out_features': 256, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
+)
+```
+
+## 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/indoSBERT-Large-mnrl-2")
+# Run inference
+sentences = [
+    'Upah bulanan rata-rata: Hubungan pendidikan tertinggi dan sektor pekerjaan utama, data 2021',
+    'Rata-rata Upah/Gaji Bersih sebulan Buruh/Karyawan Pegawai Menurut Pendidikan Tertinggi dan Lapangan Pekerjaan Utama, 2021',
+    'Rata-rata Upah/Gaji Bersih Sebulan Buruh/Karyawan Pegawai Menurut Pendidikan Tertinggi dan Jenis Pekerjaan Utama, 2021',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 256]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Information Retrieval
+
+* Dataset: `bps-statictable-ir`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.9218     |
+| cosine_accuracy@5   | 0.9902     |
+| cosine_accuracy@10  | 0.9967     |
+| cosine_precision@1  | 0.9218     |
+| cosine_precision@5  | 0.2248     |
+| cosine_precision@10 | 0.1316     |
+| cosine_recall@1     | 0.7225     |
+| cosine_recall@5     | 0.793      |
+| cosine_recall@10    | 0.8182     |
+| cosine_ndcg@1       | 0.9218     |
+| cosine_ndcg@5       | 0.8341     |
+| **cosine_ndcg@10**  | **0.8332** |
+| cosine_mrr@1        | 0.9218     |
+| cosine_mrr@5        | 0.9522     |
+| cosine_mrr@10       | 0.9532     |
+| cosine_map@1        | 0.9218     |
+| cosine_map@5        | 0.792      |
+| cosine_map@10       | 0.7848     |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### statictable-triplets-all
+
+* Dataset: [statictable-triplets-all](https://huggingface.co/datasets/yahyaabd/statictable-triplets-all) at [24979b4](https://huggingface.co/datasets/yahyaabd/statictable-triplets-all/tree/24979b4f0d8269377aca975e20d52e69c3b5a030)
+* Size: 967,831 training samples
+* Columns: <code>query</code>, <code>pos</code>, and <code>neg</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | query                                                                             | pos                                                                               | neg                                                                               |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | string                                                                            |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 16.97 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 20.79 tokens</li><li>max: 48 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 20.94 tokens</li><li>max: 48 tokens</li></ul> |
+* Samples:
+  | query                                                                                                                       | pos                                                                                                                                                           | neg                                                                                                                                                      |
+  |:----------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>Data input-output antar daerah, 34 provinsi: Transaksi domestik (52 industri, harga produsen, 2016)</code>            | <code>Tabel Inter Regional Input-Output Indonesia Transaksi Domestik Atas Dasar Harga Produsen Menurut 34 Provinsi dan 52 Industri, 2016 (Juta Rupiah)</code> | <code>Penduduk Berumur 15 Tahun Ke Atas yang Bekerja Selama Seminggu yang Lalu Menurut Golongan Umur dan Jumlah Jam Kerja Seluruhnya, 2008 - 2024</code> |
+  | <code>Data total penghasilan berbagai golongan rumah tangga setelah dipotong pajak, tahun 2000 (dalam miliar rupiah)</code> | <code>Jumlah Pendapatan Setelah Pajak Menurut Golongan Rumah Tangga (miliar rupiah), 2000, 2005, dan 2008</code>                                              | <code>Institusi Korporasi Non Finansial Neraca Institusi Terintegrasi ( triliun rupiah), 2016 2022</code>                                                |
+  | <code>Rumah tangga dengan area resapan, data per provinsi, 2014</code>                                                      | <code>Persentase Rumah Tangga Menurut Provinsi dan Keberadaan Area Resapan Air, 2013-2014</code>                                                              | <code>Nilai Produksi dan Biaya Produksi per Musim Tanam per Hektar Budidaya Tanaman Padi Sawah, Padi Ladang, Jagung, dan Kedelai, 2017</code>            |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### statictable-triplets-all
+
+* Dataset: [statictable-triplets-all](https://huggingface.co/datasets/yahyaabd/statictable-triplets-all) at [24979b4](https://huggingface.co/datasets/yahyaabd/statictable-triplets-all/tree/24979b4f0d8269377aca975e20d52e69c3b5a030)
+* Size: 967,831 evaluation samples
+* Columns: <code>query</code>, <code>pos</code>, and <code>neg</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | query                                                                             | pos                                                                               | neg                                                                              |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | string                                                                           |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 16.69 tokens</li><li>max: 32 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 20.85 tokens</li><li>max: 48 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 20.9 tokens</li><li>max: 48 tokens</li></ul> |
+* Samples:
+  | query                                                                                                                | pos                                                                                                                       | neg                                                                                                                                                                          |
+  |:---------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>Kredit UMKM bank umum (miliar rupiah), 2012-2016</code>                                                        | <code>Posisi Kredit Usaha Mikro, Kecil, dan Menengah (UMKM) 1 pada Bank Umum (miliar rupiah), 2012-2016</code>            | <code>Jumlah Penghuni Lapas per Kanwil</code>                                                                                                                                |
+  | <code>Infant Mortality Rate di Indonesia per provinsi, 1971</code>                                                   | <code>Angka Kematian Bayi/AKB (Infant Mortality Rate/IMR) Menurut Provinsi, 1971-2020</code>                              | <code>Jumlah Sekolah, Guru, dan Murid Sekolah Menengah Kejuruan (SMK) di Bawah Kementrian Pendidikan dan Kebudayaan Menurut Provinsi tahun ajaran 2011/2012-2015/2016</code> |
+  | <code>Partisipasi sekolah anak dan remaja: Data persentase usia 7-24 tahun per gender dan kelompok umur, 2021</code> | <code>Persentase Penduduk Usia 7-24 Tahun Menurut Jenis Kelamin, Kelompok Umur, dan Partisipasi Sekolah, 2002-2023</code> | <code>Tabel Input-Output Indonesia Transaksi Total Atas Dasar Harga Pembeli (17 Produk), 2016 (Juta Rupiah)</code>                                                           |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](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`: 64
+- `per_device_eval_batch_size`: 64
+- `num_train_epochs`: 1
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `load_best_model_at_end`: True
+- `eval_on_start`: True
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `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`: 0.1
+- `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
+- `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`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch      | Step    | Training Loss | Validation Loss | bps-statictable-ir_cosine_ndcg@10 |
+|:----------:|:-------:|:-------------:|:---------------:|:---------------------------------:|
+| 0          | 0       | -             | 0.7678          | 0.7378                            |
+| 0.1391     | 100     | 0.2164        | 0.0292          | 0.8324                            |
+| 0.2782     | 200     | 0.032         | 0.0143          | 0.8383                            |
+| 0.4172     | 300     | 0.0221        | 0.0077          | 0.8392                            |
+| 0.5563     | 400     | 0.0088        | 0.0055          | 0.8391                            |
+| 0.6954     | 500     | 0.0058        | 0.0033          | 0.8301                            |
+| **0.8345** | **600** | **0.0039**    | **0.0016**      | **0.8331**                        |
+| 0.9736     | 700     | 0.0027        | 0.0019          | 0.8332                            |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.11.11
+- Sentence Transformers: 3.4.1
+- Transformers: 4.48.3
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.3.0
+- Datasets: 3.4.1
+- Tokenizers: 0.21.1
+
+## 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}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "denaya/indoSBERT-Large",
+  "_num_labels": 5,
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.48.3",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae3a612903a4ced4f726f973c287fad78a93fa81e201a57ff1423b3e3d15ce7a
+size 1340612432

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Dense",
+    "type": "sentence_transformers.models.Dense"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 256,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 256,
+  "model_max_length": 256,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}