Add new SentenceTransformer model.

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "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 +1,773 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:212
+- loss:BatchSemiHardTripletLoss
+base_model: BAAI/bge-base-en
+widget:
+- source_sentence: '
+
+    Name : E27
+
+    Category: Event Management Services, Business Conference Coordination
+
+    Department: Sales
+
+    Location: Berlin, Germany
+
+    Amount: 1225.45
+
+    Card: Sales Innovation Fund
+
+    Trip Name: unknown
+
+    '
+  sentences:
+  - '
+
+    Name : BüroComfort
+
+    Category: Workspace Solutions, Interior Design Services
+
+    Department: Office Administration
+
+    Location: Zurich, Switzerland
+
+    Amount: 1203.52
+
+    Card: Flexible Working Spaces Remodel
+
+    Trip Name: unknown
+
+    '
+  - '
+
+    Name : NexusGuard Solutions
+
+    Category: Data Protection Tools, IT Support Services
+
+    Department: Information Security
+
+    Location: New York, USA
+
+    Amount: 1957.85
+
+    Card: Enterprise Security Revamp
+
+    Trip Name: unknown
+
+    '
+  - '
+
+    Name : Pacific Union Services
+
+    Category: Financial Consulting, Subscription Management
+
+    Department: Finance
+
+    Location: Singapore
+
+    Amount: 129.58
+
+    Card: Quarterly Financial Account Review
+
+    Trip Name: unknown
+
+    '
+- source_sentence: '
+
+    Name : Miller & Gartner
+
+    Category: Consulting, Business Expense
+
+    Department: Legal
+
+    Location: Chicago, IL
+
+    Amount: 1500.0
+
+    Card: Legal Fund
+
+    Trip Name: unknown
+
+    '
+  sentences:
+  - '
+
+    Name : TalentSphere Consulting
+
+    Category: Professional Networking Solutions, Career Development Platforms
+
+    Department: HR
+
+    Location: New York, USA
+
+    Amount: 1179.42
+
+    Card: Leadership Pipeline Expansion
+
+    Trip Name: unknown
+
+    '
+  - '
+
+    Name : Rising Tide Solutions
+
+    Category: IT Resource Management
+
+    Department: Engineering
+
+    Location: Amsterdam, Netherlands
+
+    Amount: 1423.57
+
+    Card: Cloud Transition Project
+
+    Trip Name: unknown
+
+    '
+  - '
+
+    Name : Luxe Stay and Events
+
+    Category: Hospitality Services, Event Planning
+
+    Department: Marketing
+
+    Location: London, UK
+
+    Amount: 1138.75
+
+    Card: Annual Retreat Planning
+
+    Trip Name: Team Building Retreat
+
+    '
+- source_sentence: '
+
+    Name : Creatify Consulting
+
+    Category: Brand Strategy Services, Data Consultancy
+
+    Department: Marketing
+
+    Location: Berlin, Germany
+
+    Amount: 2683.45
+
+    Card: Market Expansion Analysis
+
+    Trip Name: unknown
+
+    '
+  sentences:
+  - '
+
+    Name : Cosmic Enterprise Solutions
+
+    Category: Cloud Services, Professional Networking
+
+    Department: Executive
+
+    Location: Zurich, Switzerland
+
+    Amount: 1850.55
+
+    Card: Strategic Partnership Development
+
+    Trip Name: unknown
+
+    '
+  - '
+
+    Name : BlueWave Innovations
+
+    Category: Renewable Energy Solutions, Infrastructure Management
+
+    Department: Office Administration
+
+    Location: Miami, FL
+
+    Amount: 935.47
+
+    Card: Building Energy Optimization
+
+    Trip Name: unknown
+
+    '
+  - '
+
+    Name : CovaRisk Consulting
+
+    Category: Risk Advisory, Financial Services
+
+    Department: Legal
+
+    Location: Toronto, Canada
+
+    Amount: 1124.37
+
+    Card: Assurance Payment
+
+    Trip Name: unknown
+
+    '
+- source_sentence: '
+
+    Name : Skyward Solutions
+
+    Category: IT Consultancy, Network Implementation Services
+
+    Department: Engineering
+
+    Location: Amsterdam, Netherlands
+
+    Amount: 1296.35
+
+    Card: Next-Gen Network Expansion
+
+    Trip Name: unknown
+
+    '
+  sentences:
+  - '
+
+    Name : TransFleet Solutions
+
+    Category: Logistics Services, Transportation Consulting
+
+    Department: Sales
+
+    Location: Frankfurt, Germany
+
+    Amount: 456.78
+
+    Card: Client Engagement Trip
+
+    Trip Name: Q3-GER-Sales
+
+    '
+  - '
+
+    Name : Globetrotter Partners
+
+    Category: Lodging Services, Corporate Retreat Planning
+
+    Department: Executive
+
+    Location: Banff, Canada
+
+    Amount: 1559.75
+
+    Card: Leadership Development Seminar
+
+    Trip Name: unknown
+
+    '
+  - '
+
+    Name : IntelliSync Integration
+
+    Category: Connectivity Services, Enterprise Solutions
+
+    Department: IT Operations
+
+    Location: San Francisco, CA
+
+    Amount: 1387.42
+
+    Card: Global Connectivity Suite
+
+    Trip Name: unknown
+
+    '
+- source_sentence: '
+
+    Name : Quantifire Insights
+
+    Category: Predictive Analytics Solutions
+
+    Department: Marketing
+
+    Location: Zurich, Switzerland
+
+    Amount: 1275.58
+
+    Card: Customer Engagement Enhancement
+
+    Trip Name: unknown
+
+    '
+  sentences:
+  - '
+
+    Name : Greenfield Utilities
+
+    Category: Utilities Services, Property Management
+
+    Department: Office Administration
+
+    Location: Denver, CO
+
+    Amount: 975.47
+
+    Card: Monthly Facilities Expense
+
+    Trip Name: unknown
+
+    '
+  - '
+
+    Name : Celo Communications
+
+    Category: Telecom Provider, Voice & Data Solutions
+
+    Department: IT Operations
+
+    Location: Lisbon, Portugal
+
+    Amount: 1509.85
+
+    Card: Unified Communication Upgrade
+
+    Trip Name: unknown
+
+    '
+  - '
+
+    Name : Pardalis Digital
+
+    Category: Data Analytics Platform, Professional Networking Service
+
+    Department: Sales
+
+    Location: Dublin, Ireland
+
+    Amount: 1456.75
+
+    Card: Sales Intelligence & Networking Platform
+
+    Trip Name: unknown
+
+    '
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy
+- dot_accuracy
+- manhattan_accuracy
+- euclidean_accuracy
+- max_accuracy
+model-index:
+- name: SentenceTransformer based on BAAI/bge-base-en
+  results:
+  - task:
+      type: triplet
+      name: Triplet
+    dataset:
+      name: bge base en train
+      type: bge-base-en-train
+    metrics:
+    - type: cosine_accuracy
+      value: 0.839622641509434
+      name: Cosine Accuracy
+    - type: dot_accuracy
+      value: 0.16037735849056603
+      name: Dot Accuracy
+    - type: manhattan_accuracy
+      value: 0.8301886792452831
+      name: Manhattan Accuracy
+    - type: euclidean_accuracy
+      value: 0.839622641509434
+      name: Euclidean Accuracy
+    - type: max_accuracy
+      value: 0.839622641509434
+      name: Max Accuracy
+  - task:
+      type: triplet
+      name: Triplet
+    dataset:
+      name: bge base en eval
+      type: bge-base-en-eval
+    metrics:
+    - type: cosine_accuracy
+      value: 0.9393939393939394
+      name: Cosine Accuracy
+    - type: dot_accuracy
+      value: 0.06060606060606061
+      name: Dot Accuracy
+    - type: manhattan_accuracy
+      value: 0.9242424242424242
+      name: Manhattan Accuracy
+    - type: euclidean_accuracy
+      value: 0.9393939393939394
+      name: Euclidean Accuracy
+    - type: max_accuracy
+      value: 0.9393939393939394
+      name: Max Accuracy
+---
+
+# SentenceTransformer based on BAAI/bge-base-en
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-base-en](https://huggingface.co/BAAI/bge-base-en). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [BAAI/bge-base-en](https://huggingface.co/BAAI/bge-base-en) <!-- at revision b737bf5dcc6ee8bdc530531266b4804a5d77b5d8 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 tokens
+- **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': 512, 'do_lower_case': True}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, '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("dakini/finetuned-bge-base-en")
+# Run inference
+sentences = [
+    '\nName : Quantifire Insights\nCategory: Predictive Analytics Solutions\nDepartment: Marketing\nLocation: Zurich, Switzerland\nAmount: 1275.58\nCard: Customer Engagement Enhancement\nTrip Name: unknown\n',
+    '\nName : Pardalis Digital\nCategory: Data Analytics Platform, Professional Networking Service\nDepartment: Sales\nLocation: Dublin, Ireland\nAmount: 1456.75\nCard: Sales Intelligence & Networking Platform\nTrip Name: unknown\n',
+    '\nName : Celo Communications\nCategory: Telecom Provider, Voice & Data Solutions\nDepartment: IT Operations\nLocation: Lisbon, Portugal\nAmount: 1509.85\nCard: Unified Communication Upgrade\nTrip Name: unknown\n',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### 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
+
+#### Triplet
+* Dataset: `bge-base-en-train`
+* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
+
+| Metric             | Value      |
+|:-------------------|:-----------|
+| cosine_accuracy    | 0.8396     |
+| dot_accuracy       | 0.1604     |
+| manhattan_accuracy | 0.8302     |
+| euclidean_accuracy | 0.8396     |
+| **max_accuracy**   | **0.8396** |
+
+#### Triplet
+* Dataset: `bge-base-en-eval`
+* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
+
+| Metric             | Value      |
+|:-------------------|:-----------|
+| cosine_accuracy    | 0.9394     |
+| dot_accuracy       | 0.0606     |
+| manhattan_accuracy | 0.9242     |
+| euclidean_accuracy | 0.9394     |
+| **max_accuracy**   | **0.9394** |
+
+<!--
+## 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: 212 training samples
+* Columns: <code>sentence</code> and <code>label</code>
+* Approximate statistics based on the first 212 samples:
+  |         | sentence                                                                           | label                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |
+  |:--------|:-----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | type    | string                                                                             | int                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              |
+  | details | <ul><li>min: 32 tokens</li><li>mean: 39.57 tokens</li><li>max: 49 tokens</li></ul> | <ul><li>0: ~3.77%</li><li>1: ~4.25%</li><li>2: ~2.83%</li><li>3: ~2.36%</li><li>4: ~4.25%</li><li>5: ~3.77%</li><li>6: ~3.77%</li><li>7: ~3.30%</li><li>8: ~3.77%</li><li>9: ~2.83%</li><li>10: ~2.36%</li><li>11: ~5.19%</li><li>12: ~6.13%</li><li>13: ~3.30%</li><li>14: ~2.83%</li><li>15: ~5.66%</li><li>16: ~3.77%</li><li>17: ~4.72%</li><li>18: ~4.25%</li><li>19: ~3.77%</li><li>20: ~3.77%</li><li>21: ~4.72%</li><li>22: ~3.30%</li><li>23: ~2.36%</li><li>24: ~5.19%</li><li>25: ~2.83%</li><li>26: ~0.94%</li></ul> |
+* Samples:
+  | sentence                                                                                                                                                                                                                                                                       | label          |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------|
+  | <code><br>Name : TransGlobal Solutions<br>Category: Cross-border Processing Services, Business Management Platforms<br>Department: Finance<br>Location: Geneva, Switzerland<br>Amount: 739.58<br>Card: Q3 International Service Fees Analysis<br>Trip Name: unknown<br></code> | <code>0</code> |
+  | <code><br>Name : Clarion Synergy Group<br>Category: Organizational Development Services<br>Department: HR<br>Location: New York, NY<br>Amount: 1523.45<br>Card: Leadership Development Program<br>Trip Name: unknown<br></code>                                                | <code>1</code> |
+  | <code><br>Name : SkyElevate Group<br>Category: Luxury Travel Services, Corporate Event Planning<br>Department: Executive<br>Location: Dubai, UAE<br>Amount: 2113.47<br>Card: Executive Strategy Retreat<br>Trip Name: Board of Directors Retreat<br></code>                    | <code>2</code> |
+* Loss: [<code>BatchSemiHardTripletLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#batchsemihardtripletloss)
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 52 evaluation samples
+* Columns: <code>sentence</code> and <code>label</code>
+* Approximate statistics based on the first 52 samples:
+  |         | sentence                                                                          | label                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |
+  |:--------|:----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | type    | string                                                                            | int                                                                                                                                                                                                                                                                                                                                                                                                                                                                      |
+  | details | <ul><li>min: 35 tokens</li><li>mean: 39.4 tokens</li><li>max: 46 tokens</li></ul> | <ul><li>0: ~3.85%</li><li>1: ~3.85%</li><li>3: ~3.85%</li><li>4: ~3.85%</li><li>5: ~5.77%</li><li>6: ~3.85%</li><li>7: ~3.85%</li><li>8: ~3.85%</li><li>9: ~3.85%</li><li>10: ~3.85%</li><li>11: ~3.85%</li><li>12: ~7.69%</li><li>13: ~1.92%</li><li>14: ~5.77%</li><li>16: ~7.69%</li><li>17: ~1.92%</li><li>18: ~3.85%</li><li>19: ~5.77%</li><li>20: ~3.85%</li><li>21: ~3.85%</li><li>22: ~3.85%</li><li>24: ~3.85%</li><li>25: ~1.92%</li><li>26: ~3.85%</li></ul> |
+* Samples:
+  | sentence                                                                                                                                                                                                                                                 | label           |
+  |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------|
+  | <code><br>Name : Globex Regulatory Services<br>Category: Professional Services, Legal Consulting<br>Department: Compliance<br>Location: Brussels, Belgium<br>Amount: 993.47<br>Card: International Compliance Alignment<br>Trip Name: unknown<br></code> | <code>22</code> |
+  | <code><br>Name : Connectiva Innovations<br>Category: Telecommunications, Software Services<br>Department: IT Operations<br>Location: Lisbon, Portugal<br>Amount: 1489.92<br>Card: Enhanced Connectivity Solutions<br>Trip Name: unknown<br></code>       | <code>14</code> |
+  | <code><br>Name : RBC<br>Category: Transaction Processing, Financial Services<br>Department: Finance<br>Location: Limassol, Cyprus<br>Amount: 843.56<br>Card: Quarterly Financial Management<br>Trip Name: unknown<br></code>                             | <code>0</code>  |
+* Loss: [<code>BatchSemiHardTripletLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#batchsemihardtripletloss)
+
+### 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`: 5
+- `warmup_ratio`: 0.1
+- `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`: 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`: 5
+- `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`: False
+- `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`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `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
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch | Step | bge-base-en-eval_max_accuracy | bge-base-en-train_max_accuracy |
+|:-----:|:----:|:-----------------------------:|:------------------------------:|
+| 0     | 0    | -                             | 0.8396                         |
+| 5.0   | 70   | 0.9394                        | -                              |
+
+
+### Framework Versions
+- Python: 3.9.21
+- Sentence Transformers: 3.1.1
+- Transformers: 4.45.2
+- PyTorch: 2.6.0
+- Accelerate: 1.3.0
+- Datasets: 3.3.2
+- Tokenizers: 0.20.3
+
+## 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",
+}
+```
+
+#### BatchSemiHardTripletLoss
+```bibtex
+@misc{hermans2017defense,
+    title={In Defense of the Triplet Loss for Person Re-Identification},
+    author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
+    year={2017},
+    eprint={1703.07737},
+    archivePrefix={arXiv},
+    primaryClass={cs.CV}
+}
+```
+
+<!--
+## 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 +1,32 @@
+{
+  "_name_or_path": "BAAI/bge-base-en",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "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": "4.45.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.1.1",
+    "transformers": "4.45.2",
+    "pytorch": "2.6.0"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ddd3602eedc14f99d29bc9dba5b8594750fe7647fa29f104c173b6c8dc110e5
+size 437951328

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": 512,
+  "do_lower_case": true
+}

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 +1,57 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}