Add new SentenceTransformer model

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 +1,462 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:86807
+- loss:CosineSimilarityLoss
+base_model: sentence-transformers/all-MiniLM-L6-v2
+widget:
+- source_sentence: "[CLS] [KNOWLEDGE] NLTK [CTX] Programmierung einer pre-processing\
+    \ CI/CD Pipeline zur automatisierten Verarbeitung von Newsartikeln von Tamil zu\
+    \ Englisch, in Python unter Verwendung von NLTK und SpaCy\n [SEP]"
+  sentences:
+  - "[CLS] [KNOWLEDGE] SPOC [CTX] Single Point of Contact (SPOC) für die Business\
+    \ Units (Schnittstellenfunktion zu anderen Teilprojekten und Teams)\n [SEP]"
+  - "[CLS] [KNOWLEDGE] DIN 50001 [CTX] Mitarbeit zur Einführung eines Energiemanagementsystems\
+    \ nach DIN 50001\n [SEP]"
+  - "[CLS] [KNOWLEDGE] Risikomanagement [CTX] - Risikomanagement\n [SEP]"
+- source_sentence: "[CLS] [KNOWLEDGE] 365 Tenant [CTX] Verantwortung Umzug Office\
+    \ 365 Tenant\n [SEP]"
+  sentences:
+  - '[CLS] [KNOWLEDGE] Change- [CTX] Change-, Problem-, Incident- und Releasemanagement
+    mit IBM Maximo. [SEP]'
+  - "[CLS] [SKILL] Performance-Untersuchung Oracle-Datenbanken [CTX] Reorganisation\
+    \ von SAP R/3 Systemen bzw. Oracle Datenbanken 10.2 mittels BRSPACE. Performance-Untersuchung\
+    \ und Parametrisierung von SAP R/3 Systemen und Oracle-Datenbanken 10g. Incident-Bearbeitung\
+    \ bzgl. SAP, Oracle und Unix über Remedy. Sap-Kernel\n [SEP]"
+  - '[CLS] [SKILL] Visualisierung DWH Mart Daten [CTX] Modellierung des Datenstroms
+    und erstellen von DWH Modellen mit Hilfe von ETL für Staging, Storage und Mart.
+    Visualisierung der DWH Mart Daten mit Microsoft Power BI.   [SEP]'
+- source_sentence: "[CLS] [KNOWLEDGE] Rechenzentrum [CTX] Abbau der Racks im alten\
+    \ Rechenzentrum\n [SEP]"
+  sentences:
+  - "[CLS] [KNOWLEDGE] Rechenzentrum [CTX] Abbau der Racks im alten Rechenzentrum\n\
+    \ [SEP]"
+  - "[CLS] [KNOWLEDGE] SAP [CTX] SAP Administration, Planung und Bereitstellung, Heterogene\
+    \ und Homogene Systemkopien, Upgrade, Solution Manger, LVM Enterprise (post copy\
+    \ automation), Patch OS/SAP/DB, config, SAP\n [SEP]"
+  - "[CLS] [SKILL] Erstellung Nutzerdatenbank [CTX] >- Erstellung einer Nutzerdatenbank\
+    \ mit DynamoDB\n [SEP]"
+- source_sentence: "[CLS] [KNOWLEDGE] EU-DSGVO [CTX] Datenschutzrecht (Datenschutz-Grundverordnung\
+    \ (EU-DSGVO) und Bundesdatenschutzgesetz (BDSG neu)\n [SEP]"
+  sentences:
+  - "[CLS] [KNOWLEDGE] ITIL [CTX] Mitarbeit innerhalb der Prozesse der Prozesse Incident-Management\
+    \ / Service-Desk, Problem-Management, Change-Management, Release-Management, Availability-Management\
+    \ gem. ITIL\n [SEP]"
+  - "[CLS] [KNOWLEDGE] DSGVO [CTX] - Unterstützung und Beratung bei  Architektur Fragen,\
+    \ betreffend lfd. BSI-   Standards DSGVO/ GDPR Themen (ISO- Normen & Standards)...\n\
+    \ [SEP]"
+  - "[CLS] [KNOWLEDGE] RAS-Konfiguration [CTX] RAS-Konfiguration\n [SEP]"
+- source_sentence: "[CLS] [KNOWLEDGE] Kunden-Konzernstandards [CTX] Konzeption, Erstellung\
+    \ und Umsetzung der IT-Sicherheitsrichtlinien für die Freigabe von geheimen Daten\
+    \ gemäß Kunden-Konzernstandards (ISO 27001, BSI-Grundschutz)\n [SEP]"
+  sentences:
+  - '[CLS] [KNOWLEDGE] Kundenberatung [CTX] Kundenberatung [SEP]'
+  - "[CLS] [KNOWLEDGE] Service-Katalog [CTX] Beauftragen der Hard- und Software, bzw.\
+    \ Leistungserbringung gem. Service-Katalog\n [SEP]"
+  - '[CLS] [KNOWLEDGE] Datenbanksystemen [CTX] Portierung mittels make-tools(make,vmake,makesap,mapro)
+    und Assembler-Routinen, Test und Support von DB2, Oracle und MaxDB auf Linux Sles8
+    und Sles9. Erstellung shared-libraries mit Sap Kernel 620 und 640 durch Einspielen
+    von Perforce-Sourcen. Test C und C++ Precompiler -Programme. Testen Datenbankfuntionalitäten
+    über SAP-CCMS und DB bzw. SAP-Laufzeitparameter (Shared Memory etc.). Installieren
+    und testen von diversen SAP Komponenten SAP R/3 4.6D, SAP Kernel 620 und 640 unter
+    Linux/zLinux 2.4 und 2.6 (64 Bit-Adressierung) mit verschiedenen Datenbanksystemen
+    als Database-Server (Oracle, DB2 und MaxDB). Testen SAP-Transaktionen mit CATT
+    (SAP computer aided test tool) und anpassen von Python und Perl Schnittstellen.
+    AIX 5.33, z/OS, SAP R/3 4.6D, WAS 6.20/6.40, DB2 V8.1, vi, K-Shell, C-Shell, bash,
+    ICLI, FTP, Smitty, TSO/ISPF, JCL, SAPSERV, AIX VG-PP-LP, yank, MaxDB 7.5, Linux/zLinux
+    2.4/2.6, C, C++, Python, Perl Teamarbeit 3 Mitarbeiter. [SEP]'
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+model-index:
+- name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev
+      type: sts-dev
+    metrics:
+    - type: pearson_cosine
+      value: 0.9898120947090514
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.9570957645982657
+      name: Spearman Cosine
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test
+      type: sts-test
+    metrics:
+    - type: pearson_cosine
+      value: 0.9896747270285828
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.9591977829092115
+      name: Spearman Cosine
+---
+
+# SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2). 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/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) <!-- at revision c9745ed1d9f207416be6d2e6f8de32d1f16199bf -->
+- **Maximum Sequence Length:** 256 tokens
+- **Output Dimensionality:** 384 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **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': 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})
+  (2): Normalize()
+)
+```
+
+## 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("deedcon/bi-encoder-v2")
+# Run inference
+sentences = [
+    '[CLS] [KNOWLEDGE] Kunden-Konzernstandards [CTX] Konzeption, Erstellung und Umsetzung der IT-Sicherheitsrichtlinien für die Freigabe von geheimen Daten gemäß Kunden-Konzernstandards (ISO 27001, BSI-Grundschutz)\n [SEP]',
+    '[CLS] [KNOWLEDGE] Kundenberatung [CTX] Kundenberatung [SEP]',
+    '[CLS] [KNOWLEDGE] Service-Katalog [CTX] Beauftragen der Hard- und Software, bzw. Leistungserbringung gem. Service-Katalog\n [SEP]',
+]
+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
+
+#### Semantic Similarity
+
+* Datasets: `sts-dev` and `sts-test`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | sts-dev    | sts-test   |
+|:--------------------|:-----------|:-----------|
+| pearson_cosine      | 0.9898     | 0.9897     |
+| **spearman_cosine** | **0.9571** | **0.9592** |
+
+<!--
+## 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
+
+#### Unnamed Dataset
+
+* Size: 86,807 training samples
+* Columns: <code>text1</code>, <code>text2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | text1                                                                              | text2                                                                               | score                                                            |
+  |:--------|:-----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:-----------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                              | float                                                            |
+  | details | <ul><li>min: 15 tokens</li><li>mean: 62.0 tokens</li><li>max: 256 tokens</li></ul> | <ul><li>min: 15 tokens</li><li>mean: 61.69 tokens</li><li>max: 256 tokens</li></ul> | <ul><li>min: -0.08</li><li>mean: 0.45</li><li>max: 1.0</li></ul> |
+* Samples:
+  | text1                                                                                                                                                                | text2                                                                                                                                          | score                           |
+  |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------|
+  | <code>[CLS] [SKILL] Dokumentieren Netzwerkinfrastruktur [CTX] Dokumentieren und Skizzieren der Netzwerkinfrastruktur. [SEP]</code>                                   | <code>[CLS] [SKILL] Abarbeitung Incidents [CTX] Abarbeitung von Changes/ Incidents in Jira<br> [SEP]</code>                                    | <code>0.1672067940235138</code> |
+  | <code>[CLS] [SKILL] Durchführung Abnahmetests [CTX] Erstellung von Testplänen und Durchführung von Abnahmetests im Rahmen des Release Managements. <br> [SEP]</code> | <code>[CLS] [KNOWLEDGE] Kostenrechnungswesen [CTX] Ist-Analyse der Produktionsabläufe sowie des vorhandene Kostenrechnungswesen . [SEP]</code> | <code>0.2705094516277313</code> |
+  | <code>[CLS] [KNOWLEDGE] MS SQL Datenbankabfragen [CTX] MS SQL Datenbankabfragen  . [SEP]</code>                                                                      | <code>[CLS] [SKILL] Erstellung MS SQL Datenbank [CTX] Erstellung & Modellierung der  MS SQL Datenbank über Entity Framework<br> [SEP]</code>   | <code>0.8471388816833496</code> |
+* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
+  ```json
+  {
+      "loss_fct": "torch.nn.modules.loss.MSELoss"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+* Size: 17,361 evaluation samples
+* Columns: <code>text1</code>, <code>text2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | text1                                                                               | text2                                                                               | score                                                            |
+  |:--------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:-----------------------------------------------------------------|
+  | type    | string                                                                              | string                                                                              | float                                                            |
+  | details | <ul><li>min: 14 tokens</li><li>mean: 60.26 tokens</li><li>max: 256 tokens</li></ul> | <ul><li>min: 15 tokens</li><li>mean: 61.41 tokens</li><li>max: 256 tokens</li></ul> | <ul><li>min: -0.09</li><li>mean: 0.46</li><li>max: 1.0</li></ul> |
+* Samples:
+  | text1                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              | text2                                                                                                                                                                                                                                                                                                                                                                                                                         | score                              |
+  |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------|
+  | <code>[CLS] [SKILL] Installation 7 [CTX] Installation, Konfiguration und Verwaltung von: Windows XP, 7, 8, 8.1, 10<br> [SEP]</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                | <code>[CLS] [SKILL] Installation 10 [CTX] Installation, Konfiguration und Verwaltung von: Windows XP, 7, 8, 8.1, 10<br> [SEP]</code>                                                                                                                                                                                                                                                                                          | <code>0.9105218082666396</code>    |
+  | <code>[CLS] [KNOWLEDGE] Oracle-Systemadministration [CTX] Installation, Administration (Backup/Recovery etc.) und Tuning von DB2 nach SAP R/3 Gesichtspunkten bzw. DB2-Applikationsprogrammierung (Auswertung und Verarbeitung von DB2-Report-Utility und DB2-Katalog nach wiederherzustellenden SAP-Tablespaces mit recoverfähiger RBA zur Automatisierung des Conditional Restart Verfahrens) u. Oracle-Systemadministration in einer SAP R/3-Basis-Umgebung unter OS/390-TSO-ISPF-LIBRARIAN, DB2 Version 5 und DB2 UDB Version 6, CLIST, RACF, JCL, COBOL, AIX, ORACLE Version 7 u.8, Open-Edition, SAP R/3-BC 4.5B., Omegamon<br> [SEP]</code> | <code>[CLS] [KNOWLEDGE] RxJS [CTX] Konsumieren der Rest APIs mit HttpClient und RxJS<br> [SEP]</code>                                                                                                                                                                                                                                                                                                                         | <code>-0.06634289771318436</code>  |
+  | <code>[CLS] [SKILL] Erstellung Prozessen [CTX] Erstellung von Dokumentationen und Arbeitsanweisungen und Prozessen Kommunikation auf allen Ebenen mit vielen Abteilungen international. [SEP]</code>                                                                                                                                                                                                                                                                                                                                                                                                                                               | <code>[CLS] [KNOWLEDGE] DB2 8.1 [CTX] Systemadministration, Betrieb, Monitoring und Fehlerbehebung von über 100 SAP-Systemen unterschiedlicher Releasestände (4.6 C,6.20,6.40, EP, XI) und deren Datenbanken (Oracle 9.2, Informix 9.4, 9.3, DB2 8.1, SAP DB 7.5) auf pSeries Rechnern unter AIX 5.3 und z/OS. Durchführung und Überwachung des Transport-Managements (SAP-intern und auf OP-Ebene(AIX)) und<br> [SEP]</code> | <code>-0.009634226560592651</code> |
+* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
+  ```json
+  {
+      "loss_fct": "torch.nn.modules.loss.MSELoss"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 1
+- `warmup_ratio`: 0.1
+- `fp16`: 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`: 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`: 2e-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`: False
+- `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`: False
+- `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 | sts-dev_spearman_cosine | sts-test_spearman_cosine |
+|:------:|:----:|:-------------:|:---------------:|:-----------------------:|:------------------------:|
+| -1     | -1   | -             | -               | 0.8023                  | -                        |
+| 0.0921 | 500  | 0.0172        | 0.0056          | 0.9152                  | -                        |
+| 0.1843 | 1000 | 0.0064        | 0.0043          | 0.9330                  | -                        |
+| 0.2764 | 1500 | 0.005         | 0.0037          | 0.9399                  | -                        |
+| 0.3686 | 2000 | 0.0047        | 0.0035          | 0.9456                  | -                        |
+| 0.4607 | 2500 | 0.0042        | 0.0032          | 0.9475                  | -                        |
+| 0.5529 | 3000 | 0.0039        | 0.0029          | 0.9514                  | -                        |
+| 0.6450 | 3500 | 0.0036        | 0.0027          | 0.9525                  | -                        |
+| 0.7372 | 4000 | 0.0034        | 0.0027          | 0.9547                  | -                        |
+| 0.8293 | 4500 | 0.0033        | 0.0026          | 0.9564                  | -                        |
+| 0.9215 | 5000 | 0.0033        | 0.0025          | 0.9571                  | -                        |
+| -1     | -1   | -             | -               | -                       | 0.9592                   |
+
+
+### Framework Versions
+- Python: 3.12.4
+- Sentence Transformers: 4.1.0
+- Transformers: 4.49.0
+- PyTorch: 2.4.0+rocm6.3.4.git7cecbf6d
+- Accelerate: 1.6.0
+- Datasets: 3.5.0
+- 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",
+}
+```
+
+<!--
+## 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": "models/bi-encoder_v2/final",
+  "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": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "4.1.0",
+    "transformers": "4.49.0",
+    "pytorch": "2.4.0+rocm6.3.4.git7cecbf6d"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33df335ab20921a4941fdb00a27ee2a3b11b0078c348fac1a246ceef53cf6b81
+size 90864192

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_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

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
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "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]"
+}