Add new SentenceTransformer model

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+unigram.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "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
+}

README.md

@@ -0,0 +1,589 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:967831
+- loss:MultipleNegativesRankingLoss
+base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+widget:
+- source_sentence: 'Penghasilan rata-rata pelaku usaha mandiri: Analisis berdasarkan
+    lokasi dan jenjang pendidikan, 2023'
+  sentences:
+  - Rata-rata Pendapatan bersih Berusaha Sendiri menurut Provinsi dan Pendidikan yang
+    Ditamatkan, 2023
+  - Rata-Rata Pengeluaran per Kapita Sebulan Menurut Kelompok Barang (rupiah), 2013-2021
+  - Ringkasan Neraca Arus Dana, Triwulan III, 2006, (Miliar Rupiah)
+- source_sentence: Bagaimana traffic penerbangan internasional di Indonesia pada 2008?
+  sentences:
+  - Tingkat Inflasi Harga Konsumen Nasional Bulanan (M-to-M) 1 (2022=100)
+  - Balita (0-59 Bulan) Menurut Status Gizi, Tahun 1998-2005
+  - Lalu Lintas Penerbangan Luar Negeri Indonesia Tahun 2003-2022
+- source_sentence: Data indeks daya penyebaran dan derajat kepekaan sektor ekonomi,
+    ambil contoh tahun 2005
+  sentences:
+  - Indeks Daya Penyebaran dan Indeks Derajat Kepekaan Menurut Sektor Ekonomi, 1995,
+    2000, 2005, dan 2010
+  - Ekspor Kopi Menurut Negara Tujuan Utama, 2000-2023
+  - Anggaran Kesehatan dari Direktorat Penyusunan APBN - Direktorat Jenderal Anggaran,
+    Kementerian Keuangan
+- source_sentence: Data aktivitas penduduk 15 tahun ke atas berdasarkan kelompok umur,
+    satu minggu ke belakang (periode 2002)
+  sentences:
+  - Ekspor Lada Putih menurut Negara Tujuan Utama, 2012-2023
+  - Rata-rata Konsumsi dan Pengeluaran Perkapita Seminggu Menurut Komoditi Makanan
+    dan Golongan Pengeluaran per Kapita Seminggu di Provinsi Sulawesi Selatan, 2018-2023
+  - Penduduk Berumur 15 Tahun Ke Atas Menurut Golongan Umur dan Jenis Kegiatan Selama
+    Seminggu yang Lalu, 1997 - 2007
+- source_sentence: Laporan singkat arus kas Q2 2005, dalam miliar
+  sentences:
+  - Ringkasan Neraca Arus Dana, Triwulan Kedua, 2005, (Miliar Rupiah)
+  - Indikator Pendidikan, 1994-2023
+  - Rata-rata Upah/Gaji Bersih sebulan Buruh/Karyawan Pegawai Menurut Pendidikan Tertinggi
+    dan Jumlah Jam Kerja Utama, 2020
+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 sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: bps statictable ir
+      type: bps-statictable-ir
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.8990228013029316
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@5
+      value: 0.9837133550488599
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 1.0
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.8990228013029316
+      name: Cosine Precision@1
+    - type: cosine_precision@5
+      value: 0.21889250814332245
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.12605863192182412
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7029638149674847
+      name: Cosine Recall@1
+    - type: cosine_recall@5
+      value: 0.789022126091837
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8116078533769628
+      name: Cosine Recall@10
+    - type: cosine_ndcg@1
+      value: 0.8990228013029316
+      name: Cosine Ndcg@1
+    - type: cosine_ndcg@5
+      value: 0.8178579787978988
+      name: Cosine Ndcg@5
+    - type: cosine_ndcg@10
+      value: 0.8156444177517035
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@1
+      value: 0.8990228013029316
+      name: Cosine Mrr@1
+    - type: cosine_mrr@5
+      value: 0.9347991313789358
+      name: Cosine Mrr@5
+    - type: cosine_mrr@10
+      value: 0.9368827878599865
+      name: Cosine Mrr@10
+    - type: cosine_map@1
+      value: 0.8990228013029316
+      name: Cosine Map@1
+    - type: cosine_map@5
+      value: 0.772128121606949
+      name: Cosine Map@5
+    - type: cosine_map@10
+      value: 0.7635855701310564
+      name: Cosine Map@10
+---
+
+# 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 [statictable-triplets-all](https://huggingface.co/datasets/yahyaabd/statictable-triplets-all) 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) <!-- at revision 86741b4e3f5cb7765a600d3a3d55a0f6a6cb443d -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 384 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': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("yahyaabd/paraphrase-multilingual-miniLM-L12-v2-mnrl-beir-2")
+# Run inference
+sentences = [
+    'Laporan singkat arus kas Q2 2005, dalam miliar',
+    'Ringkasan Neraca Arus Dana, Triwulan Kedua, 2005, (Miliar Rupiah)',
+    'Rata-rata Upah/Gaji Bersih sebulan Buruh/Karyawan Pegawai Menurut Pendidikan Tertinggi dan Jumlah Jam Kerja Utama, 2020',
+]
+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]
+```
+
+<!--
+### 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   | 0.899      |
+| cosine_accuracy@5   | 0.9837     |
+| cosine_accuracy@10  | 1.0        |
+| cosine_precision@1  | 0.899      |
+| cosine_precision@5  | 0.2189     |
+| cosine_precision@10 | 0.1261     |
+| cosine_recall@1     | 0.703      |
+| cosine_recall@5     | 0.789      |
+| cosine_recall@10    | 0.8116     |
+| cosine_ndcg@1       | 0.899      |
+| cosine_ndcg@5       | 0.8179     |
+| **cosine_ndcg@10**  | **0.8156** |
+| cosine_mrr@1        | 0.899      |
+| cosine_mrr@5        | 0.9348     |
+| cosine_mrr@10       | 0.9369     |
+| cosine_map@1        | 0.899      |
+| cosine_map@5        | 0.7721     |
+| cosine_map@10       | 0.7636     |
+
+<!--
+## 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: 4 tokens</li><li>mean: 18.55 tokens</li><li>max: 37 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 25.6 tokens</li><li>max: 58 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 25.7 tokens</li><li>max: 58 tokens</li></ul> |
+* Samples:
+  | query                                                                                                              | pos                                                                                                                                                                         | neg                                                                                                                                    |
+  |:-------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>Indeks harga petani (diterima & dibayar) dan NTP per provinsi, 2012</code>                                   | <code>Indeks Harga yang Diterima Petani (It), Indeks Harga yang Dibayar Petani (Ib), dan Nilai Tukar Petani (NTP) Menurut Provinsi, 2008-2016</code>                        | <code>Persentase Rumah Tangga Menurut Provinsi dan KebiasaanMemanfaatkan Air Bekas untuk Keperluan Lain, 2013, 2014, 2017, 2021</code> |
+  | <code>Data rumah tangga perikanan budidaya Indonesia, detail per provinsi dan jenis budidaya, di tahun 2008</code> | <code>Jumlah Rumah Tangga Perikanan Budidaya Menurut Provinsi dan Jenis Budidaya, 2000-2016</code>                                                                          | <code>Ringkasan Neraca Arus Dana, 2005, (Miliar Rupiah)</code>                                                                         |
+  | <code>Lapangan pekerjaan vs pendidikan pekerja (15 tahun ke atas), 1986 hingga 1996</code>                         | <code>Penduduk Berumur 15 Tahun Ke Atas yang Bekerja Selama Seminggu yang Lalu Menurut Lapangan Pekerjaan Utama dan Pendidikan Tertinggi yang Ditamatkan, 1986 -1996</code> | <code>Tabel Input-Output Indonesia Transaksi Domestik Atas Dasar Harga Produsen (17 Lapangan Usaha), 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"
+  }
+  ```
+
+### 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: 5 tokens</li><li>mean: 18.38 tokens</li><li>max: 37 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 25.28 tokens</li><li>max: 58 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 25.65 tokens</li><li>max: 58 tokens</li></ul> |
+* Samples:
+  | query                                                                                                                    | pos                                                                                                                                                                         | neg                                                                                               |
+  |:-------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------|
+  | <code>Bagaimana hubungan IHK dan rata-rata upah buruh industri (bukan supervisor) bulanan tahun 2010, acuan 1996?</code> | <code>IHK dan Rata-rata Upah per Bulan Buruh Industri di Bawah Mandor (Supervisor), 1996-2014 (1996=100)</code>                                                             | <code>Rata-rata Harga Valuta Asing Terpilih menurut Provinsi, 2014</code>                         |
+  | <code>Berapa rata-rata gaji bulanan pekerja Indonesia berdasarkan ijazah terakhir dan sektor pekerjaannya (2017)?</code> | <code>Rata-rata Upah/Gaji Bersih Sebulan Buruh/Karyawan/Pegawai Menurut Pendidikan Tertinggi yang Ditamatkan dan Lapangan Pekerjaan Utama di 9 Sektor (rupiah), 2017</code> | <code>Rata-Rata Pengeluaran per Kapita Sebulan Menurut Kelompok Barang (rupiah), 2013-2021</code> |
+  | <code>Data luas lahan (hektar) yang dipakai untuk jenis budidaya perikanan di tiap provinsi tahun 2009</code>            | <code>Luas Area Usaha Budidaya Perikanan Menurut Provinsi dan Jenis Budidaya (ha), 2005-2016</code>                                                                         | <code>Ringkasan Neraca Arus Dana, Triwulan I, 2008, (Miliar 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`: 16
+- `per_device_eval_batch_size`: 16
+- `weight_decay`: 0.01
+- `num_train_epochs`: 2
+- `lr_scheduler_type`: reduce_lr_on_plateau
+- `lr_scheduler_kwargs`: {'factor': 0.5, 'patience': 2}
+- `warmup_steps`: 10000
+- `save_on_each_node`: True
+- `fp16`: True
+- `dataloader_num_workers`: 2
+- `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`: 16
+- `per_device_eval_batch_size`: 16
+- `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`: 2
+- `max_steps`: -1
+- `lr_scheduler_type`: reduce_lr_on_plateau
+- `lr_scheduler_kwargs`: {'factor': 0.5, 'patience': 2}
+- `warmup_ratio`: 0.0
+- `warmup_steps`: 10000
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: True
+- `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`: 2
+- `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         | -             | 1.0819          | 0.4643                            |
+| 0.0334     | 200       | 0.1373        | -               | -                                 |
+| 0.0668     | 400       | 0.0354        | -               | -                                 |
+| 0.0835     | 500       | -             | 0.0132          | 0.8252                            |
+| 0.1002     | 600       | 0.028         | -               | -                                 |
+| 0.1336     | 800       | 0.018         | -               | -                                 |
+| 0.1670     | 1000      | 0.0145        | 0.0096          | 0.8286                            |
+| 0.2004     | 1200      | 0.0089        | -               | -                                 |
+| 0.2338     | 1400      | 0.0103        | -               | -                                 |
+| 0.2505     | 1500      | -             | 0.0067          | 0.8312                            |
+| 0.2672     | 1600      | 0.0098        | -               | -                                 |
+| 0.3006     | 1800      | 0.0086        | -               | -                                 |
+| 0.3339     | 2000      | 0.0086        | 0.0044          | 0.8246                            |
+| 0.3673     | 2200      | 0.0088        | -               | -                                 |
+| 0.4007     | 2400      | 0.0075        | -               | -                                 |
+| 0.4174     | 2500      | -             | 0.0051          | 0.8295                            |
+| 0.4341     | 2600      | 0.0066        | -               | -                                 |
+| 0.4675     | 2800      | 0.0054        | -               | -                                 |
+| 0.5009     | 3000      | 0.0051        | 0.0059          | 0.8294                            |
+| 0.5343     | 3200      | 0.0052        | -               | -                                 |
+| 0.5677     | 3400      | 0.0037        | -               | -                                 |
+| 0.5844     | 3500      | -             | 0.0041          | 0.8126                            |
+| 0.6011     | 3600      | 0.0078        | -               | -                                 |
+| 0.6345     | 3800      | 0.005         | -               | -                                 |
+| 0.6679     | 4000      | 0.0045        | 0.0050          | 0.8308                            |
+| 0.7013     | 4200      | 0.0047        | -               | -                                 |
+| 0.7347     | 4400      | 0.0066        | -               | -                                 |
+| 0.7514     | 4500      | -             | 0.0033          | 0.8233                            |
+| 0.7681     | 4600      | 0.0043        | -               | -                                 |
+| 0.8015     | 4800      | 0.003         | -               | -                                 |
+| 0.8349     | 5000      | 0.0029        | 0.0036          | 0.8224                            |
+| 0.8683     | 5200      | 0.0014        | -               | -                                 |
+| 0.9017     | 5400      | 0.0058        | -               | -                                 |
+| 0.9184     | 5500      | -             | 0.0020          | 0.8169                            |
+| 0.9350     | 5600      | 0.0045        | -               | -                                 |
+| 0.9684     | 5800      | 0.0036        | -               | -                                 |
+| 1.0018     | 6000      | 0.0053        | 0.0018          | 0.8152                            |
+| 1.0352     | 6200      | 0.0035        | -               | -                                 |
+| 1.0686     | 6400      | 0.0017        | -               | -                                 |
+| 1.0853     | 6500      | -             | 0.0024          | 0.8231                            |
+| 1.1020     | 6600      | 0.0037        | -               | -                                 |
+| 1.1354     | 6800      | 0.0044        | -               | -                                 |
+| 1.1688     | 7000      | 0.0011        | 0.0113          | 0.8153                            |
+| 1.2022     | 7200      | 0.0042        | -               | -                                 |
+| 1.2356     | 7400      | 0.0028        | -               | -                                 |
+| 1.2523     | 7500      | -             | 0.0046          | 0.8253                            |
+| 1.2690     | 7600      | 0.0005        | -               | -                                 |
+| 1.3024     | 7800      | 0.001         | -               | -                                 |
+| 1.3358     | 8000      | 0.0011        | 0.0017          | 0.8216                            |
+| 1.3692     | 8200      | 0.0007        | -               | -                                 |
+| 1.4026     | 8400      | 0.0014        | -               | -                                 |
+| 1.4193     | 8500      | -             | 0.0014          | 0.8253                            |
+| 1.4360     | 8600      | 0.0003        | -               | -                                 |
+| 1.4694     | 8800      | 0.0005        | -               | -                                 |
+| 1.5028     | 9000      | 0.002         | 0.0012          | 0.8250                            |
+| 1.5361     | 9200      | 0.0013        | -               | -                                 |
+| 1.5695     | 9400      | 0.0009        | -               | -                                 |
+| 1.5862     | 9500      | -             | 0.0003          | 0.8162                            |
+| 1.6029     | 9600      | 0.0021        | -               | -                                 |
+| 1.6363     | 9800      | 0.0013        | -               | -                                 |
+| 1.6697     | 10000     | 0.0005        | 0.0003          | 0.8234                            |
+| 1.7031     | 10200     | 0.0004        | -               | -                                 |
+| 1.7365     | 10400     | 0.0004        | -               | -                                 |
+| **1.7532** | **10500** | **-**         | **0.0001**      | **0.8225**                        |
+| 1.7699     | 10600     | 0.0011        | -               | -                                 |
+| 1.8033     | 10800     | 0.0004        | -               | -                                 |
+| 1.8367     | 11000     | 0.0009        | 0.0008          | 0.8259                            |
+| 1.8701     | 11200     | 0.0024        | -               | -                                 |
+| 1.9035     | 11400     | 0.0002        | -               | -                                 |
+| 1.9202     | 11500     | -             | 0.0008          | 0.8156                            |
+| 1.9369     | 11600     | 0.0007        | -               | -                                 |
+| 1.9703     | 11800     | 0.0007        | -               | -                                 |
+
+* 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 +1,26 @@
+{
+  "_name_or_path": "sentence-transformers/paraphrase-multilingual-miniLM-L12-v2",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

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:a078e89c48f3b3b7024334d73fa73c7755add45e88a0ea58e4ac81210981e417
+size 470637416

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
+size 17082987

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 128,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

unigram.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
+size 14763260