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:ed36d1e09f407db1ba4f46d6f529ca0154e80b690eacfbe09959e28ea5a9a7f9
+size 1049760

README.md

@@ -0,0 +1,558 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:25580
+- loss:OnlineContrastiveLoss
+base_model: denaya/indoSBERT-large
+widget:
+- source_sentence: ikhtisar arus kas triwulan 1, 2004 (miliar)
+  sentences:
+  - Balita (0-59 Bulan) Menurut Status Gizi, Tahun 1998-2005
+  - Perbandingan Indeks dan Tingkat Inflasi Desember 2023 Kota-kota di Luar Pulau
+    Jawa dan Sumatera dengan Nasional (2018=100)
+  - Rata-rata Konsumsi dan Pengeluaran Perkapita Seminggu Menurut Komoditi Makanan
+    dan Golongan Pengeluaran per Kapita Seminggu di Provinsi Sulawesi Tengah, 2018-2023
+- source_sentence: BaIgaimana gambaran neraca arus dana dUi Indonesia pada kuartal
+    kedua tahun 2015?
+  sentences:
+  - Jumlah Sekolah, Guru, dan Murid Sekolah Menengah Pertama (SMP) di Bawah Kementrian
+    Pendidikan dan Kebudayaan Menurut Provinsi 2011/2012-2015/2016
+  - Ringkasan Neraca Arus Dana Triwulan III Tahun 2003 (Miliar Rupiah)
+  - Rata-rata Konsumsi dan Pengeluaran Perkapita Seminggu Menurut Komoditi Makanan
+    dan Golongan Pengeluaran per Kapita Seminggu di Provinsi Sulawesi Tenggara, 2018-2023
+- source_sentence: Berapa persen pengeluaran orang di kotaa untuk makanan vs non-makanan,
+    per provinsi, 2018?
+  sentences:
+  - Ekspor Tanaman Obat, Aromatik, dan Rempah-Rempah menurut Negara Tujuan Utama,
+    2012-2023
+  - Rata-rata Pendapatan Bersih Pekerja Bebas Menurut Provinsi dan Pendidikan Tertinggi
+    yang Ditamatkan (ribu rupiah), 2017
+  - IHK dan Rata-rata Upah per Bulan Buruh Industri di Bawah Mandor (Supervisor),
+    1996-2014 (1996=100)
+- source_sentence: Negara-negara asal impor crude oil dan produk turunannya tahun
+    2002-2023
+  sentences:
+  - Persentase Pengeluaran Rata-rata per Kapita Sebulan Menurut Kelompok Barang, Indonesia,
+    1999, 2002-2023
+  - Rata-rata Pendapatan Bersih Berusaha Sendiri menurut Provinsi dan Pendidikan yang
+    Ditamatkan (ribu rupiah), 2016
+  - Perkembangan Beberapa Agregat Pendapatan dan Pendapatan per Kapita Atas Dasar
+    Harga Berlaku, 2010-2016
+- source_sentence: Arus dana Q3 2006
+  sentences:
+  - Posisi Simpanan Berjangka Rupiah pada Bank Umum dan BPR Menurut Golongan Pemilik
+    (miliar rupiah), 2005-2018
+  - Ringkasan Neraca Arus Dana, Triwulan III, 2006, (Miliar Rupiah)
+  - Rata-Rata Pengeluaran per Kapita Sebulan di Daerah Perkotaan Menurut Kelompok
+    Barang dan Golongan Pengeluaran per Kapita Sebulan, 2000-2012
+datasets:
+- yahyaabd/query-hard-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 denaya/indoSBERT-large
+  results:
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: allstats semantic large v1 test
+      type: allstats-semantic-large-v1_test
+    metrics:
+    - type: cosine_accuracy
+      value: 0.9834364761558063
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.7773222327232361
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.9745739033249511
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.7773222327232361
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.9748462828395752
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.9743016759776536
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.9959810762137397
+      name: Cosine Ap
+    - type: cosine_mcc
+      value: 0.9622916280716365
+      name: Cosine Mcc
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: allstats semantic large v1 dev
+      type: allstats-semantic-large-v1_dev
+    metrics:
+    - type: cosine_accuracy
+      value: 0.9760905274685161
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.7572722434997559
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.9640997533570841
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.7572722434997559
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.9386339381003201
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.9909859154929578
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.9953499585582108
+      name: Cosine Ap
+    - type: cosine_mcc
+      value: 0.9469795586519781
+      name: Cosine Mcc
+---
+
+# 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 [query-hard-pos-neg-doc-pairs-statictable](https://huggingface.co/datasets/yahyaabd/query-hard-pos-neg-doc-pairs-statictable) 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:**
+    - [query-hard-pos-neg-doc-pairs-statictable](https://huggingface.co/datasets/yahyaabd/query-hard-pos-neg-doc-pairs-statictable)
+<!-- - **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/allstats-search-large-v1-32-2")
+# Run inference
+sentences = [
+    'Arus dana Q3 2006',
+    'Ringkasan Neraca Arus Dana, Triwulan III, 2006, (Miliar Rupiah)',
+    'Rata-Rata Pengeluaran per Kapita Sebulan di Daerah Perkotaan Menurut Kelompok Barang dan Golongan Pengeluaran per Kapita Sebulan, 2000-2012',
+]
+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
+
+#### Binary Classification
+
+* Datasets: `allstats-semantic-large-v1_test` and `allstats-semantic-large-v1_dev`
+* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
+
+| Metric                    | allstats-semantic-large-v1_test | allstats-semantic-large-v1_dev |
+|:--------------------------|:--------------------------------|:-------------------------------|
+| cosine_accuracy           | 0.9834                          | 0.9761                         |
+| cosine_accuracy_threshold | 0.7773                          | 0.7573                         |
+| cosine_f1                 | 0.9746                          | 0.9641                         |
+| cosine_f1_threshold       | 0.7773                          | 0.7573                         |
+| cosine_precision          | 0.9748                          | 0.9386                         |
+| cosine_recall             | 0.9743                          | 0.991                          |
+| **cosine_ap**             | **0.996**                       | **0.9953**                     |
+| cosine_mcc                | 0.9623                          | 0.947                          |
+
+<!--
+## 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
+
+#### query-hard-pos-neg-doc-pairs-statictable
+
+* Dataset: [query-hard-pos-neg-doc-pairs-statictable](https://huggingface.co/datasets/yahyaabd/query-hard-pos-neg-doc-pairs-statictable) at [7b28b96](https://huggingface.co/datasets/yahyaabd/query-hard-pos-neg-doc-pairs-statictable/tree/7b28b964daa3073a4d012d1ffca46ecd4f26bb5f)
+* Size: 25,580 training samples
+* Columns: <code>query</code>, <code>doc</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | query                                                                             | doc                                                                               | label                                           |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | int                                             |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 17.12 tokens</li><li>max: 31 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 20.47 tokens</li><li>max: 42 tokens</li></ul> | <ul><li>0: ~70.80%</li><li>1: ~29.20%</li></ul> |
+* Samples:
+  | query                                                                    | doc                                           | label          |
+  |:-------------------------------------------------------------------------|:----------------------------------------------|:---------------|
+  | <code>Status pekerjaan utama penduduk usia 15+ yang bekerja, 2020</code> | <code>Jumlah Penghuni Lapas per Kanwil</code> | <code>0</code> |
+  | <code>status pekerjaan utama penduduk usia 15+ yang bekerja, 2020</code> | <code>Jumlah Penghuni Lapas per Kanwil</code> | <code>0</code> |
+  | <code>STATUS PEKERJAAN UTAMA PENDUDUK USIA 15+ YANG BEKERJA, 2020</code> | <code>Jumlah Penghuni Lapas per Kanwil</code> | <code>0</code> |
+* Loss: [<code>OnlineContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#onlinecontrastiveloss)
+
+### Evaluation Dataset
+
+#### query-hard-pos-neg-doc-pairs-statictable
+
+* Dataset: [query-hard-pos-neg-doc-pairs-statictable](https://huggingface.co/datasets/yahyaabd/query-hard-pos-neg-doc-pairs-statictable) at [7b28b96](https://huggingface.co/datasets/yahyaabd/query-hard-pos-neg-doc-pairs-statictable/tree/7b28b964daa3073a4d012d1ffca46ecd4f26bb5f)
+* Size: 5,479 evaluation samples
+* Columns: <code>query</code>, <code>doc</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | query                                                                             | doc                                                                              | label                                           |
+  |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                            | string                                                                           | int                                             |
+  | details | <ul><li>min: 7 tokens</li><li>mean: 17.85 tokens</li><li>max: 35 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 21.2 tokens</li><li>max: 31 tokens</li></ul> | <ul><li>0: ~71.50%</li><li>1: ~28.50%</li></ul> |
+* Samples:
+  | query                                                                                    | doc                                                                                                                         | label          |
+  |:-----------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------|:---------------|
+  | <code>Bagaimana perbandingan PNS pria dan wanita di berbagai golongan tahun 2014?</code> | <code>Rata-rata Pendapatan Bersih Berusaha Sendiri Menurut Provinsi dan Lapangan Pekerjaan Utama (ribu rupiah), 2017</code> | <code>0</code> |
+  | <code>bagaimana perbandingan pns pria dan wanita di berbagai golongan tahun 2014?</code> | <code>Rata-rata Pendapatan Bersih Berusaha Sendiri Menurut Provinsi dan Lapangan Pekerjaan Utama (ribu rupiah), 2017</code> | <code>0</code> |
+  | <code>BAGAIMANA PERBANDINGAN PNS PRIA DAN WANITA DI BERBAGAI GOLONGAN TAHUN 2014?</code> | <code>Rata-rata Pendapatan Bersih Berusaha Sendiri Menurut Provinsi dan Lapangan Pekerjaan Utama (ribu rupiah), 2017</code> | <code>0</code> |
+* Loss: [<code>OnlineContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#onlinecontrastiveloss)
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 32
+- `num_train_epochs`: 2
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `load_best_model_at_end`: True
+- `eval_on_start`: True
+
+#### 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`: 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`: 2
+- `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`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch    | Step    | Training Loss | Validation Loss | allstats-semantic-large-v1_test_cosine_ap | allstats-semantic-large-v1_dev_cosine_ap |
+|:--------:|:-------:|:-------------:|:---------------:|:-----------------------------------------:|:----------------------------------------:|
+| -1       | -1      | -             | -               | 0.9750                                    | -                                        |
+| 0        | 0       | -             | 0.1850          | -                                         | 0.9766                                   |
+| 0.025    | 20      | 0.1581        | 0.1538          | -                                         | 0.9789                                   |
+| 0.05     | 40      | 0.1898        | 0.1200          | -                                         | 0.9848                                   |
+| 0.075    | 60      | 0.0647        | 0.1096          | -                                         | 0.9855                                   |
+| 0.1      | 80      | 0.118         | 0.1242          | -                                         | 0.9831                                   |
+| 0.125    | 100     | 0.0545        | 0.1301          | -                                         | 0.9827                                   |
+| 0.15     | 120     | 0.0646        | 0.1114          | -                                         | 0.9862                                   |
+| 0.175    | 140     | 0.0775        | 0.1005          | -                                         | 0.9865                                   |
+| 0.2      | 160     | 0.0664        | 0.1234          | -                                         | 0.9840                                   |
+| 0.225    | 180     | 0.067         | 0.1349          | -                                         | 0.9850                                   |
+| 0.25     | 200     | 0.0823        | 0.1032          | -                                         | 0.9877                                   |
+| 0.275    | 220     | 0.0895        | 0.1432          | -                                         | 0.9808                                   |
+| 0.3      | 240     | 0.0666        | 0.1389          | -                                         | 0.9809                                   |
+| 0.325    | 260     | 0.0872        | 0.1122          | -                                         | 0.9844                                   |
+| 0.35     | 280     | 0.0551        | 0.1435          | -                                         | 0.9838                                   |
+| 0.375    | 300     | 0.0919        | 0.1068          | -                                         | 0.9886                                   |
+| 0.4      | 320     | 0.0437        | 0.0903          | -                                         | 0.9861                                   |
+| 0.425    | 340     | 0.0619        | 0.1065          | -                                         | 0.9850                                   |
+| 0.45     | 360     | 0.0469        | 0.1346          | -                                         | 0.9844                                   |
+| 0.475    | 380     | 0.029         | 0.1351          | -                                         | 0.9828                                   |
+| 0.5      | 400     | 0.0511        | 0.1123          | -                                         | 0.9843                                   |
+| 0.525    | 420     | 0.0394        | 0.1434          | -                                         | 0.9815                                   |
+| 0.55     | 440     | 0.0178        | 0.1577          | -                                         | 0.9769                                   |
+| 0.575    | 460     | 0.047         | 0.1253          | -                                         | 0.9796                                   |
+| 0.6      | 480     | 0.0066        | 0.1262          | -                                         | 0.9791                                   |
+| 0.625    | 500     | 0.0383        | 0.1277          | -                                         | 0.9814                                   |
+| 0.65     | 520     | 0.0084        | 0.1361          | -                                         | 0.9845                                   |
+| 0.675    | 540     | 0.0409        | 0.1202          | -                                         | 0.9872                                   |
+| 0.7      | 560     | 0.0372        | 0.1245          | -                                         | 0.9854                                   |
+| 0.725    | 580     | 0.0353        | 0.1469          | -                                         | 0.9817                                   |
+| 0.75     | 600     | 0.0429        | 0.1225          | -                                         | 0.9836                                   |
+| 0.775    | 620     | 0.0595        | 0.1082          | -                                         | 0.9862                                   |
+| 0.8      | 640     | 0.0266        | 0.0886          | -                                         | 0.9903                                   |
+| 0.825    | 660     | 0.0178        | 0.0712          | -                                         | 0.9918                                   |
+| **0.85** | **680** | **0.0567**    | **0.0511**      | **-**                                     | **0.9936**                               |
+| 0.875    | 700     | 0.0142        | 0.0538          | -                                         | 0.9916                                   |
+| 0.9      | 720     | 0.0136        | 0.0726          | -                                         | 0.9890                                   |
+| 0.925    | 740     | 0.0192        | 0.0707          | -                                         | 0.9884                                   |
+| 0.95     | 760     | 0.0253        | 0.0937          | -                                         | 0.9872                                   |
+| 0.975    | 780     | 0.0149        | 0.0792          | -                                         | 0.9878                                   |
+| 1.0      | 800     | 0.0231        | 0.0912          | -                                         | 0.9879                                   |
+| 1.025    | 820     | 0.0           | 0.1030          | -                                         | 0.9871                                   |
+| 1.05     | 840     | 0.0096        | 0.0990          | -                                         | 0.9876                                   |
+| 1.075    | 860     | 0.0           | 0.1032          | -                                         | 0.9868                                   |
+| 1.1      | 880     | 0.0           | 0.1037          | -                                         | 0.9866                                   |
+| 1.125    | 900     | 0.0           | 0.1038          | -                                         | 0.9866                                   |
+| 1.15     | 920     | 0.0           | 0.1038          | -                                         | 0.9866                                   |
+| 1.175    | 940     | 0.0           | 0.1038          | -                                         | 0.9866                                   |
+| 1.2      | 960     | 0.0121        | 0.1030          | -                                         | 0.9895                                   |
+| 1.225    | 980     | 0.0           | 0.1035          | -                                         | 0.9899                                   |
+| 1.25     | 1000    | 0.0           | 0.1040          | -                                         | 0.9898                                   |
+| 1.275    | 1020    | 0.0           | 0.1049          | -                                         | 0.9898                                   |
+| 1.3      | 1040    | 0.0           | 0.1049          | -                                         | 0.9898                                   |
+| 1.325    | 1060    | 0.0067        | 0.1015          | -                                         | 0.9903                                   |
+| 1.35     | 1080    | 0.0           | 0.1048          | -                                         | 0.9901                                   |
+| 1.375    | 1100    | 0.0159        | 0.0956          | -                                         | 0.9910                                   |
+| 1.4      | 1120    | 0.0067        | 0.0818          | -                                         | 0.9926                                   |
+| 1.425    | 1140    | 0.0151        | 0.0838          | -                                         | 0.9926                                   |
+| 1.45     | 1160    | 0.0           | 0.0889          | -                                         | 0.9920                                   |
+| 1.475    | 1180    | 0.0           | 0.0894          | -                                         | 0.9920                                   |
+| 1.5      | 1200    | 0.023         | 0.0696          | -                                         | 0.9935                                   |
+| 1.525    | 1220    | 0.0           | 0.0693          | -                                         | 0.9935                                   |
+| 1.55     | 1240    | 0.0           | 0.0711          | -                                         | 0.9935                                   |
+| 1.575    | 1260    | 0.0           | 0.0711          | -                                         | 0.9935                                   |
+| 1.6      | 1280    | 0.0           | 0.0711          | -                                         | 0.9935                                   |
+| 1.625    | 1300    | 0.0176        | 0.0743          | -                                         | 0.9936                                   |
+| 1.65     | 1320    | 0.0           | 0.0806          | -                                         | 0.9931                                   |
+| 1.675    | 1340    | 0.0           | 0.0817          | -                                         | 0.9931                                   |
+| 1.7      | 1360    | 0.007         | 0.0809          | -                                         | 0.9929                                   |
+| 1.725    | 1380    | 0.0209        | 0.0700          | -                                         | 0.9941                                   |
+| 1.75     | 1400    | 0.0068        | 0.0605          | -                                         | 0.9949                                   |
+| 1.775    | 1420    | 0.0069        | 0.0564          | -                                         | 0.9951                                   |
+| 1.8      | 1440    | 0.0097        | 0.0559          | -                                         | 0.9953                                   |
+| 1.825    | 1460    | 0.0           | 0.0557          | -                                         | 0.9953                                   |
+| 1.85     | 1480    | 0.0           | 0.0557          | -                                         | 0.9953                                   |
+| 1.875    | 1500    | 0.0           | 0.0557          | -                                         | 0.9953                                   |
+| 1.9      | 1520    | 0.0           | 0.0557          | -                                         | 0.9953                                   |
+| 1.925    | 1540    | 0.0           | 0.0557          | -                                         | 0.9953                                   |
+| 1.95     | 1560    | 0.0089        | 0.0544          | -                                         | 0.9953                                   |
+| 1.975    | 1580    | 0.0           | 0.0544          | -                                         | 0.9953                                   |
+| 2.0      | 1600    | 0.0           | 0.0544          | -                                         | 0.9953                                   |
+| -1       | -1      | -             | -               | 0.9960                                    | -                                        |
+
+* 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",
+}
+```
+
+<!--
+## 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": "4.48.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.0",
+    "transformers": "4.48.1",
+    "pytorch": "2.5.1+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:f0206672dd1f3dafdee2edb3d66093c3923e95c4d9099f5b0cd179da6ae16cd1
+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]"
+}