| --- |
| tags: |
| - sentence-transformers |
| - sentence-similarity |
| - feature-extraction |
| - dense |
| - generated_from_trainer |
| - dataset_size:623829 |
| - loss:MultipleNegativesRankingLoss |
| base_model: sentence-transformers/LaBSE |
| widget: |
| - source_sentence: Uptown Pub! | 1589 Clover Lane, Wichita Falls, TX |
| sentences: |
| - Moa LLC Services | 1964 341, VEEDERSBURG, IN |
| - Wong Peak-(One) | 2658 61, Vincennes, Indiana |
| - 'Uptown Pub! Trading | ' |
| - source_sentence: Village Of | 375 Broadway, Unit 2-G08, Lynnfield, MA |
| sentences: |
| - ROCKY GUILD | 260 2ND AVENUE, FORSYTH, MT |
| - 'Village Of Center | ' |
| - Vio L.L.C. | 415 2TH AVENUE, WASHINGTON, IA |
| - source_sentence: St. Fellowship | 1822 Mayfair Drive, City Of Appleton, WI |
| sentences: |
| - Sanders Adgno | 3606 LORNE DR, ENDWELL, NY |
| - 'Quality Opendoor | ' |
| - 'St. Fellowship | ' |
| - source_sentence: Ross and Trinidad Inc | AR, Bryant, 6328 Lena Drive |
| sentences: |
| - 'STEINMEYER,-WINI, SERVICES | ' |
| - 'Ross and Trinidad Inc. | ' |
| - Zium [Ltd.] | 3215- CROSSFELL RD, SRING, TX |
| - source_sentence: Stag | 122 Bruce Street, Scotia, NY |
| sentences: |
| - Stag Corporation | BRUCE STREET, SCOTIA, NY |
| - ORTHOPEDIC PHYSICIANS | 75, ALTOONA, AL |
| - '#2 HUB CO | 142 COTTAGE STREET, LEWISTON, ME' |
| pipeline_tag: sentence-similarity |
| library_name: sentence-transformers |
| metrics: |
| - cosine_accuracy@1 |
| - cosine_accuracy@5 |
| - cosine_accuracy@10 |
| - cosine_accuracy@30 |
| - cosine_precision@1 |
| - cosine_precision@3 |
| - cosine_precision@5 |
| - cosine_precision@10 |
| - cosine_recall@1 |
| - cosine_recall@3 |
| - cosine_recall@5 |
| - cosine_recall@10 |
| - cosine_ndcg@10 |
| - cosine_mrr@10 |
| - cosine_map@100 |
| model-index: |
| - name: SentenceTransformer based on sentence-transformers/LaBSE |
| results: |
| - task: |
| type: information-retrieval |
| name: Information Retrieval |
| dataset: |
| name: biencoder val |
| type: biencoder-val |
| metrics: |
| - type: cosine_accuracy@1 |
| value: 0.929 |
| name: Cosine Accuracy@1 |
| - type: cosine_accuracy@5 |
| value: 1.0 |
| name: Cosine Accuracy@5 |
| - type: cosine_accuracy@10 |
| value: 1.0 |
| name: Cosine Accuracy@10 |
| - type: cosine_accuracy@30 |
| value: 1.0 |
| name: Cosine Accuracy@30 |
| - type: cosine_precision@1 |
| value: 0.929 |
| name: Cosine Precision@1 |
| - type: cosine_precision@3 |
| value: 0.33333333333333326 |
| name: Cosine Precision@3 |
| - type: cosine_precision@5 |
| value: 0.20000000000000004 |
| name: Cosine Precision@5 |
| - type: cosine_precision@10 |
| value: 0.10000000000000002 |
| name: Cosine Precision@10 |
| - type: cosine_recall@1 |
| value: 0.929 |
| name: Cosine Recall@1 |
| - type: cosine_recall@3 |
| value: 1.0 |
| name: Cosine Recall@3 |
| - type: cosine_recall@5 |
| value: 1.0 |
| name: Cosine Recall@5 |
| - type: cosine_recall@10 |
| value: 1.0 |
| name: Cosine Recall@10 |
| - type: cosine_ndcg@10 |
| value: 0.9732722934892877 |
| name: Cosine Ndcg@10 |
| - type: cosine_mrr@10 |
| value: 0.9638333333333332 |
| name: Cosine Mrr@10 |
| - type: cosine_map@100 |
| value: 0.9638333333333332 |
| name: Cosine Map@100 |
| --- |
| |
| # SentenceTransformer based on sentence-transformers/LaBSE |
|
|
| This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/LaBSE](https://huggingface.co/sentence-transformers/LaBSE). It maps inputs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, classification, clustering, and more. |
|
|
| ## Model Details |
|
|
| ### Model Description |
| - **Model Type:** Sentence Transformer |
| - **Base model:** [sentence-transformers/LaBSE](https://huggingface.co/sentence-transformers/LaBSE) <!-- at revision 836121a0533e5664b21c7aacc5d22951f2b8b25b --> |
| - **Maximum Sequence Length:** 256 tokens |
| - **Output Dimensionality:** 768 dimensions |
| - **Similarity Function:** Cosine Similarity |
| - **Supported Modality:** Text |
| <!-- - **Training Dataset:** Unknown --> |
| <!-- - **Language:** Unknown --> |
| <!-- - **License:** Unknown --> |
|
|
| ### Model Sources |
|
|
| - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) |
| - **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers) |
| - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) |
|
|
| ### Full Model Architecture |
|
|
| ``` |
| SentenceTransformer( |
| (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'BertModel'}) |
| (1): Pooling({'embedding_dimension': 768, 'pooling_mode': 'cls', 'include_prompt': True}) |
| (2): Dense({'in_features': 768, 'out_features': 768, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh', 'module_input_name': 'sentence_embedding', 'module_output_name': 'sentence_embedding'}) |
| (3): Normalize({'module_input_name': 'sentence_embedding', 'module_output_name': 'sentence_embedding'}) |
| ) |
| ``` |
|
|
| ## 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("sentence_transformers_model_id") |
| # Run inference |
| queries = [ |
| 'Stag | 122 Bruce Street, Scotia, NY', |
| ] |
| documents = [ |
| 'Stag Corporation | BRUCE STREET, SCOTIA, NY', |
| '#2 HUB CO | 142 COTTAGE STREET, LEWISTON, ME', |
| 'ORTHOPEDIC PHYSICIANS | 75, ALTOONA, AL', |
| ] |
| query_embeddings = model.encode_query(queries) |
| document_embeddings = model.encode_document(documents) |
| print(query_embeddings.shape, document_embeddings.shape) |
| # [1, 768] [3, 768] |
| |
| # Get the similarity scores for the embeddings |
| similarities = model.similarity(query_embeddings, document_embeddings) |
| print(similarities) |
| # tensor([[ 0.7677, 0.1634, -0.0688]]) |
| ``` |
| <!-- |
| ### 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: `biencoder-val` |
| * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.sentence_transformer.evaluation.InformationRetrievalEvaluator) |
|
|
| | Metric | Value | |
| |:--------------------|:-----------| |
| | cosine_accuracy@1 | 0.929 | |
| | cosine_accuracy@5 | 1.0 | |
| | cosine_accuracy@10 | 1.0 | |
| | cosine_accuracy@30 | 1.0 | |
| | cosine_precision@1 | 0.929 | |
| | cosine_precision@3 | 0.3333 | |
| | cosine_precision@5 | 0.2 | |
| | cosine_precision@10 | 0.1 | |
| | cosine_recall@1 | 0.929 | |
| | cosine_recall@3 | 1.0 | |
| | cosine_recall@5 | 1.0 | |
| | cosine_recall@10 | 1.0 | |
| | **cosine_ndcg@10** | **0.9733** | |
| | cosine_mrr@10 | 0.9638 | |
| | cosine_map@100 | 0.9638 | |
| |
| <!-- |
| ## 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: 623,829 training samples |
| * Columns: <code>anchor</code> and <code>positive</code> |
| * Approximate statistics based on the first 100 samples: |
| | | anchor | positive | |
| |:---------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| |
| | type | string | string | |
| | modality | text | text | |
| | details | <ul><li>min: 18 tokens</li><li>mean: 31.59 tokens</li><li>max: 55 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 33.45 tokens</li><li>max: 64 tokens</li></ul> | |
| * Samples: |
| | anchor | positive | |
| |:----------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------| |
| | <code>Bangalore South Automotive Private Limited \| C-901, Goyalco Orchid, Lakeview, Bangalore South, Bangalore, Karnataka</code> | <code>Bangalore South Automotive Limited Private \| C-901., GOYALCO ORCHID, LAKEVIEW, BANGALORE SOUTH, ಕರ್ನಾಟಕ</code> | |
| | <code>Bangalore South Automotive Private Limited \| C-901, Goyalco Orchid, Lakeview, Bangalore South, Bangalore, Karnataka</code> | <code>Bangalore Sóuth Automotive Private Limited \| </code> | |
| | <code>Software Pinnacle Tourism \| 3016/5, 1St Floor, Ranjit Nagar, New Delhi, Central Delhi, Delhi</code> | <code>Software Pinnacle Tóurism \| A-3016/5, 1ST FLOOR, RANJIT NAGAR, NEW DELHI, दिल्ली</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", |
| "gather_across_devices": false, |
| "directions": [ |
| "query_to_doc" |
| ], |
| "partition_mode": "joint", |
| "hardness_mode": null, |
| "hardness_strength": 0.0 |
| } |
| ``` |
| |
| ### Training Hyperparameters |
| #### Non-Default Hyperparameters |
| |
| - `per_device_train_batch_size`: 64 |
| - `num_train_epochs`: 2 |
| - `learning_rate`: 2e-05 |
| - `warmup_steps`: 0.1 |
| |
| #### All Hyperparameters |
| <details><summary>Click to expand</summary> |
| |
| - `per_device_train_batch_size`: 64 |
| - `num_train_epochs`: 2 |
| - `max_steps`: -1 |
| - `learning_rate`: 2e-05 |
| - `lr_scheduler_type`: linear |
| - `lr_scheduler_kwargs`: None |
| - `warmup_steps`: 0.1 |
| - `optim`: adamw_torch_fused |
| - `optim_args`: None |
| - `weight_decay`: 0.0 |
| - `adam_beta1`: 0.9 |
| - `adam_beta2`: 0.999 |
| - `adam_epsilon`: 1e-08 |
| - `optim_target_modules`: None |
| - `gradient_accumulation_steps`: 1 |
| - `average_tokens_across_devices`: True |
| - `max_grad_norm`: 1.0 |
| - `label_smoothing_factor`: 0.0 |
| - `bf16`: False |
| - `fp16`: False |
| - `bf16_full_eval`: False |
| - `fp16_full_eval`: False |
| - `tf32`: None |
| - `gradient_checkpointing`: False |
| - `gradient_checkpointing_kwargs`: None |
| - `torch_compile`: False |
| - `torch_compile_backend`: None |
| - `torch_compile_mode`: None |
| - `use_liger_kernel`: False |
| - `liger_kernel_config`: None |
| - `use_cache`: False |
| - `neftune_noise_alpha`: None |
| - `torch_empty_cache_steps`: None |
| - `auto_find_batch_size`: False |
| - `log_on_each_node`: True |
| - `logging_nan_inf_filter`: True |
| - `include_num_input_tokens_seen`: no |
| - `log_level`: passive |
| - `log_level_replica`: warning |
| - `disable_tqdm`: False |
| - `project`: huggingface |
| - `trackio_space_id`: None |
| - `trackio_bucket_id`: None |
| - `trackio_static_space_id`: None |
| - `per_device_eval_batch_size`: 8 |
| - `prediction_loss_only`: True |
| - `eval_on_start`: False |
| - `eval_do_concat_batches`: True |
| - `eval_use_gather_object`: False |
| - `eval_accumulation_steps`: None |
| - `include_for_metrics`: [] |
| - `batch_eval_metrics`: False |
| - `save_only_model`: False |
| - `save_on_each_node`: False |
| - `enable_jit_checkpoint`: False |
| - `push_to_hub`: False |
| - `hub_private_repo`: None |
| - `hub_model_id`: None |
| - `hub_strategy`: every_save |
| - `hub_always_push`: False |
| - `hub_revision`: None |
| - `load_best_model_at_end`: False |
| - `ignore_data_skip`: False |
| - `restore_callback_states_from_checkpoint`: False |
| - `full_determinism`: False |
| - `seed`: 42 |
| - `data_seed`: None |
| - `use_cpu`: False |
| - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} |
| - `parallelism_config`: None |
| - `dataloader_drop_last`: False |
| - `dataloader_num_workers`: 0 |
| - `dataloader_pin_memory`: True |
| - `dataloader_persistent_workers`: False |
| - `dataloader_prefetch_factor`: None |
| - `dataloader_multiprocessing_context`: None |
| - `dataloader_in_order`: True |
| - `remove_unused_columns`: True |
| - `label_names`: None |
| - `train_sampling_strategy`: random |
| - `length_column_name`: length |
| - `ddp_find_unused_parameters`: None |
| - `ddp_bucket_cap_mb`: None |
| - `ddp_broadcast_buffers`: False |
| - `ddp_static_graph`: None |
| - `ddp_backend`: None |
| - `ddp_timeout`: 1800 |
| - `fsdp`: None |
| - `fsdp_config`: None |
| - `deepspeed`: None |
| - `debug`: [] |
| - `skip_memory_metrics`: True |
| - `do_predict`: False |
| - `resume_from_checkpoint`: None |
| - `local_rank`: -1 |
| - `prompts`: None |
| - `batch_sampler`: batch_sampler |
| - `multi_dataset_batch_sampler`: proportional |
| - `router_mapping`: {} |
| - `learning_rate_mapping`: {} |
| - `warmup_ratio`: None |
| |
| </details> |
| |
| ### Training Logs |
| <details><summary>Click to expand</summary> |
| |
| | Epoch | Step | Training Loss | biencoder-val_cosine_ndcg@10 | |
| |:------:|:-----:|:-------------:|:----------------------------:| |
| | 0.0051 | 50 | 0.2099 | - | |
| | 0.0103 | 100 | 0.0801 | - | |
| | 0.0154 | 150 | 0.0250 | - | |
| | 0.0205 | 200 | 0.0196 | - | |
| | 0.0256 | 250 | 0.0155 | - | |
| | 0.0308 | 300 | 0.0151 | - | |
| | 0.0359 | 350 | 0.0150 | - | |
| | 0.0410 | 400 | 0.0117 | - | |
| | 0.0462 | 450 | 0.0124 | - | |
| | 0.0513 | 500 | 0.0111 | - | |
| | 0.0564 | 550 | 0.0070 | - | |
| | 0.0616 | 600 | 0.0107 | - | |
| | 0.0667 | 650 | 0.0091 | - | |
| | 0.0718 | 700 | 0.0060 | - | |
| | 0.0769 | 750 | 0.0094 | - | |
| | 0.0821 | 800 | 0.0067 | - | |
| | 0.0872 | 850 | 0.0061 | - | |
| | 0.0923 | 900 | 0.0076 | - | |
| | 0.0975 | 950 | 0.0060 | - | |
| | 0.1026 | 1000 | 0.0047 | - | |
| | 0.1077 | 1050 | 0.0071 | - | |
| | 0.1128 | 1100 | 0.0063 | - | |
| | 0.1180 | 1150 | 0.0046 | - | |
| | 0.1231 | 1200 | 0.0039 | - | |
| | 0.1282 | 1250 | 0.0049 | - | |
| | 0.1334 | 1300 | 0.0055 | - | |
| | 0.1385 | 1350 | 0.0038 | - | |
| | 0.1436 | 1400 | 0.0041 | - | |
| | 0.1487 | 1450 | 0.0060 | - | |
| | 0.1539 | 1500 | 0.0055 | - | |
| | 0.1590 | 1550 | 0.0053 | - | |
| | 0.1641 | 1600 | 0.0047 | - | |
| | 0.1693 | 1650 | 0.0044 | - | |
| | 0.1744 | 1700 | 0.0071 | - | |
| | 0.1795 | 1750 | 0.0044 | - | |
| | 0.1847 | 1800 | 0.0025 | - | |
| | 0.1898 | 1850 | 0.0055 | - | |
| | 0.1949 | 1900 | 0.0053 | - | |
| | 0.2000 | 1950 | 0.0045 | - | |
| | 0.2052 | 2000 | 0.0047 | - | |
| | 0.2103 | 2050 | 0.0048 | - | |
| | 0.2154 | 2100 | 0.0041 | - | |
| | 0.2206 | 2150 | 0.0030 | - | |
| | 0.2257 | 2200 | 0.0037 | - | |
| | 0.2308 | 2250 | 0.0047 | - | |
| | 0.2359 | 2300 | 0.0042 | - | |
| | 0.2411 | 2350 | 0.0027 | - | |
| | 0.2462 | 2400 | 0.0047 | - | |
| | 0.2513 | 2450 | 0.0028 | - | |
| | 0.2565 | 2500 | 0.0043 | - | |
| | 0.2616 | 2550 | 0.0063 | - | |
| | 0.2667 | 2600 | 0.0027 | - | |
| | 0.2719 | 2650 | 0.0021 | - | |
| | 0.2770 | 2700 | 0.0028 | - | |
| | 0.2821 | 2750 | 0.0024 | - | |
| | 0.2872 | 2800 | 0.0045 | - | |
| | 0.2924 | 2850 | 0.0033 | - | |
| | 0.2975 | 2900 | 0.0048 | - | |
| | 0.3026 | 2950 | 0.0021 | - | |
| | 0.3078 | 3000 | 0.0031 | - | |
| | 0.3129 | 3050 | 0.0027 | - | |
| | 0.3180 | 3100 | 0.0033 | - | |
| | 0.3231 | 3150 | 0.0040 | - | |
| | 0.3283 | 3200 | 0.0012 | - | |
| | 0.3334 | 3250 | 0.0031 | - | |
| | 0.3385 | 3300 | 0.0033 | - | |
| | 0.3437 | 3350 | 0.0020 | - | |
| | 0.3488 | 3400 | 0.0028 | - | |
| | 0.3539 | 3450 | 0.0022 | - | |
| | 0.3590 | 3500 | 0.0025 | - | |
| | 0.3642 | 3550 | 0.0026 | - | |
| | 0.3693 | 3600 | 0.0028 | - | |
| | 0.3744 | 3650 | 0.0035 | - | |
| | 0.3796 | 3700 | 0.0023 | - | |
| | 0.3847 | 3750 | 0.0029 | - | |
| | 0.3898 | 3800 | 0.0031 | - | |
| | 0.3950 | 3850 | 0.0042 | - | |
| | 0.4001 | 3900 | 0.0027 | - | |
| | 0.4052 | 3950 | 0.0035 | - | |
| | 0.4103 | 4000 | 0.0026 | - | |
| | 0.4155 | 4050 | 0.0017 | - | |
| | 0.4206 | 4100 | 0.0022 | - | |
| | 0.4257 | 4150 | 0.0020 | - | |
| | 0.4309 | 4200 | 0.0025 | - | |
| | 0.4360 | 4250 | 0.0024 | - | |
| | 0.4411 | 4300 | 0.0025 | - | |
| | 0.4462 | 4350 | 0.0025 | - | |
| | 0.4514 | 4400 | 0.0021 | - | |
| | 0.4565 | 4450 | 0.0011 | - | |
| | 0.4616 | 4500 | 0.0018 | - | |
| | 0.4668 | 4550 | 0.0039 | - | |
| | 0.4719 | 4600 | 0.0016 | - | |
| | 0.4770 | 4650 | 0.0023 | - | |
| | 0.4822 | 4700 | 0.0012 | - | |
| | 0.4873 | 4750 | 0.0027 | - | |
| | 0.4924 | 4800 | 0.0020 | - | |
| | 0.4975 | 4850 | 0.0022 | - | |
| | 0.5027 | 4900 | 0.0022 | - | |
| | 0.5078 | 4950 | 0.0016 | - | |
| | 0.5129 | 5000 | 0.0027 | - | |
| | 0.5181 | 5050 | 0.0017 | - | |
| | 0.5232 | 5100 | 0.0020 | - | |
| | 0.5283 | 5150 | 0.0024 | - | |
| | 0.5334 | 5200 | 0.0024 | - | |
| | 0.5386 | 5250 | 0.0024 | - | |
| | 0.5437 | 5300 | 0.0022 | - | |
| | 0.5488 | 5350 | 0.0029 | - | |
| | 0.5540 | 5400 | 0.0016 | - | |
| | 0.5591 | 5450 | 0.0010 | - | |
| | 0.5642 | 5500 | 0.0017 | - | |
| | 0.5693 | 5550 | 0.0029 | - | |
| | 0.5745 | 5600 | 0.0017 | - | |
| | 0.5796 | 5650 | 0.0021 | - | |
| | 0.5847 | 5700 | 0.0019 | - | |
| | 0.5899 | 5750 | 0.0021 | - | |
| | 0.5950 | 5800 | 0.0030 | - | |
| | 0.6001 | 5850 | 0.0015 | - | |
| | 0.6053 | 5900 | 0.0028 | - | |
| | 0.6104 | 5950 | 0.0022 | - | |
| | 0.6155 | 6000 | 0.0020 | - | |
| | 0.6206 | 6050 | 0.0021 | - | |
| | 0.6258 | 6100 | 0.0017 | - | |
| | 0.6309 | 6150 | 0.0021 | - | |
| | 0.6360 | 6200 | 0.0015 | - | |
| | 0.6412 | 6250 | 0.0010 | - | |
| | 0.6463 | 6300 | 0.0018 | - | |
| | 0.6514 | 6350 | 0.0011 | - | |
| | 0.6565 | 6400 | 0.0035 | - | |
| | 0.6617 | 6450 | 0.0015 | - | |
| | 0.6668 | 6500 | 0.0022 | - | |
| | 0.6719 | 6550 | 0.0019 | - | |
| | 0.6771 | 6600 | 0.0017 | - | |
| | 0.6822 | 6650 | 0.0011 | - | |
| | 0.6873 | 6700 | 0.0021 | - | |
| | 0.6924 | 6750 | 0.0017 | - | |
| | 0.6976 | 6800 | 0.0014 | - | |
| | 0.7027 | 6850 | 0.0024 | - | |
| | 0.7078 | 6900 | 0.0012 | - | |
| | 0.7130 | 6950 | 0.0032 | - | |
| | 0.7181 | 7000 | 0.0020 | - | |
| | 0.7232 | 7050 | 0.0013 | - | |
| | 0.7284 | 7100 | 0.0038 | - | |
| | 0.7335 | 7150 | 0.0018 | - | |
| | 0.7386 | 7200 | 0.0019 | - | |
| | 0.7437 | 7250 | 0.0038 | - | |
| | 0.7489 | 7300 | 0.0013 | - | |
| | 0.7540 | 7350 | 0.0025 | - | |
| | 0.7591 | 7400 | 0.0022 | - | |
| | 0.7643 | 7450 | 0.0014 | - | |
| | 0.7694 | 7500 | 0.0015 | - | |
| | 0.7745 | 7550 | 0.0030 | - | |
| | 0.7796 | 7600 | 0.0016 | - | |
| | 0.7848 | 7650 | 0.0017 | - | |
| | 0.7899 | 7700 | 0.0013 | - | |
| | 0.7950 | 7750 | 0.0036 | - | |
| | 0.8002 | 7800 | 0.0022 | - | |
| | 0.8053 | 7850 | 0.0015 | - | |
| | 0.8104 | 7900 | 0.0010 | - | |
| | 0.8156 | 7950 | 0.0021 | - | |
| | 0.8207 | 8000 | 0.0019 | - | |
| | 0.8258 | 8050 | 0.0011 | - | |
| | 0.8309 | 8100 | 0.0012 | - | |
| | 0.8361 | 8150 | 0.0026 | - | |
| | 0.8412 | 8200 | 0.0011 | - | |
| | 0.8463 | 8250 | 0.0019 | - | |
| | 0.8515 | 8300 | 0.0017 | - | |
| | 0.8566 | 8350 | 0.0011 | - | |
| | 0.8617 | 8400 | 0.0012 | - | |
| | 0.8668 | 8450 | 0.0018 | - | |
| | 0.8720 | 8500 | 0.0008 | - | |
| | 0.8771 | 8550 | 0.0017 | - | |
| | 0.8822 | 8600 | 0.0023 | - | |
| | 0.8874 | 8650 | 0.0010 | - | |
| | 0.8925 | 8700 | 0.0011 | - | |
| | 0.8976 | 8750 | 0.0022 | - | |
| | 0.9027 | 8800 | 0.0023 | - | |
| | 0.9079 | 8850 | 0.0013 | - | |
| | 0.9130 | 8900 | 0.0015 | - | |
| | 0.9181 | 8950 | 0.0034 | - | |
| | 0.9233 | 9000 | 0.0011 | - | |
| | 0.9284 | 9050 | 0.0018 | - | |
| | 0.9335 | 9100 | 0.0013 | - | |
| | 0.9387 | 9150 | 0.0009 | - | |
| | 0.9438 | 9200 | 0.0008 | - | |
| | 0.9489 | 9250 | 0.0013 | - | |
| | 0.9540 | 9300 | 0.0012 | - | |
| | 0.9592 | 9350 | 0.0012 | - | |
| | 0.9643 | 9400 | 0.0008 | - | |
| | 0.9694 | 9450 | 0.0011 | - | |
| | 0.9746 | 9500 | 0.0008 | - | |
| | 0.9797 | 9550 | 0.0015 | - | |
| | 0.9848 | 9600 | 0.0014 | - | |
| | 0.9899 | 9650 | 0.0013 | - | |
| | 0.9951 | 9700 | 0.0006 | - | |
| | 1.0 | 9748 | - | 0.9733 | |
| | 1.0002 | 9750 | 0.0014 | - | |
| | 1.0053 | 9800 | 0.0006 | - | |
| | 1.0105 | 9850 | 0.0005 | - | |
| | 1.0156 | 9900 | 0.0011 | - | |
| | 1.0207 | 9950 | 0.0011 | - | |
| | 1.0259 | 10000 | 0.0009 | - | |
| | 1.0310 | 10050 | 0.0013 | - | |
| | 1.0361 | 10100 | 0.0008 | - | |
| | 1.0412 | 10150 | 0.0008 | - | |
| | 1.0464 | 10200 | 0.0006 | - | |
| | 1.0515 | 10250 | 0.0006 | - | |
| | 1.0566 | 10300 | 0.0010 | - | |
| | 1.0618 | 10350 | 0.0026 | - | |
| | 1.0669 | 10400 | 0.0007 | - | |
| | 1.0720 | 10450 | 0.0007 | - | |
| | 1.0771 | 10500 | 0.0010 | - | |
| | 1.0823 | 10550 | 0.0016 | - | |
| | 1.0874 | 10600 | 0.0014 | - | |
| | 1.0925 | 10650 | 0.0007 | - | |
| | 1.0977 | 10700 | 0.0006 | - | |
| | 1.1028 | 10750 | 0.0021 | - | |
| | 1.1079 | 10800 | 0.0027 | - | |
| | 1.1130 | 10850 | 0.0006 | - | |
| | 1.1182 | 10900 | 0.0006 | - | |
| | 1.1233 | 10950 | 0.0012 | - | |
| | 1.1284 | 11000 | 0.0016 | - | |
| | 1.1336 | 11050 | 0.0015 | - | |
| | 1.1387 | 11100 | 0.0026 | - | |
| | 1.1438 | 11150 | 0.0008 | - | |
| | 1.1490 | 11200 | 0.0007 | - | |
| | 1.1541 | 11250 | 0.0007 | - | |
| | 1.1592 | 11300 | 0.0012 | - | |
| | 1.1643 | 11350 | 0.0010 | - | |
| | 1.1695 | 11400 | 0.0005 | - | |
| | 1.1746 | 11450 | 0.0008 | - | |
| | 1.1797 | 11500 | 0.0006 | - | |
| | 1.1849 | 11550 | 0.0005 | - | |
| | 1.1900 | 11600 | 0.0016 | - | |
| | 1.1951 | 11650 | 0.0009 | - | |
| | 1.2002 | 11700 | 0.0011 | - | |
| | 1.2054 | 11750 | 0.0006 | - | |
| | 1.2105 | 11800 | 0.0014 | - | |
| | 1.2156 | 11850 | 0.0006 | - | |
| | 1.2208 | 11900 | 0.0006 | - | |
| | 1.2259 | 11950 | 0.0015 | - | |
| | 1.2310 | 12000 | 0.0005 | - | |
| | 1.2362 | 12050 | 0.0037 | - | |
| | 1.2413 | 12100 | 0.0006 | - | |
| | 1.2464 | 12150 | 0.0005 | - | |
| | 1.2515 | 12200 | 0.0007 | - | |
| | 1.2567 | 12250 | 0.0016 | - | |
| | 1.2618 | 12300 | 0.0006 | - | |
| | 1.2669 | 12350 | 0.0015 | - | |
| | 1.2721 | 12400 | 0.0005 | - | |
| | 1.2772 | 12450 | 0.0007 | - | |
| | 1.2823 | 12500 | 0.0006 | - | |
| | 1.2874 | 12550 | 0.0009 | - | |
| | 1.2926 | 12600 | 0.0005 | - | |
| | 1.2977 | 12650 | 0.0004 | - | |
| | 1.3028 | 12700 | 0.0011 | - | |
| | 1.3080 | 12750 | 0.0006 | - | |
| | 1.3131 | 12800 | 0.0006 | - | |
| | 1.3182 | 12850 | 0.0006 | - | |
| | 1.3233 | 12900 | 0.0004 | - | |
| | 1.3285 | 12950 | 0.0015 | - | |
| | 1.3336 | 13000 | 0.0013 | - | |
| | 1.3387 | 13050 | 0.0008 | - | |
| | 1.3439 | 13100 | 0.0010 | - | |
| | 1.3490 | 13150 | 0.0007 | - | |
| | 1.3541 | 13200 | 0.0013 | - | |
| | 1.3593 | 13250 | 0.0005 | - | |
| | 1.3644 | 13300 | 0.0017 | - | |
| | 1.3695 | 13350 | 0.0020 | - | |
| | 1.3746 | 13400 | 0.0004 | - | |
| | 1.3798 | 13450 | 0.0004 | - | |
| | 1.3849 | 13500 | 0.0009 | - | |
| | 1.3900 | 13550 | 0.0004 | - | |
| | 1.3952 | 13600 | 0.0009 | - | |
| | 1.4003 | 13650 | 0.0004 | - | |
| | 1.4054 | 13700 | 0.0007 | - | |
| | 1.4105 | 13750 | 0.0013 | - | |
| | 1.4157 | 13800 | 0.0007 | - | |
| | 1.4208 | 13850 | 0.0010 | - | |
| | 1.4259 | 13900 | 0.0010 | - | |
| | 1.4311 | 13950 | 0.0008 | - | |
| | 1.4362 | 14000 | 0.0009 | - | |
| | 1.4413 | 14050 | 0.0015 | - | |
| | 1.4465 | 14100 | 0.0008 | - | |
| | 1.4516 | 14150 | 0.0007 | - | |
| | 1.4567 | 14200 | 0.0007 | - | |
| | 1.4618 | 14250 | 0.0011 | - | |
| | 1.4670 | 14300 | 0.0023 | - | |
| | 1.4721 | 14350 | 0.0011 | - | |
| | 1.4772 | 14400 | 0.0004 | - | |
| | 1.4824 | 14450 | 0.0009 | - | |
| | 1.4875 | 14500 | 0.0005 | - | |
| | 1.4926 | 14550 | 0.0009 | - | |
| | 1.4977 | 14600 | 0.0004 | - | |
| | 1.5029 | 14650 | 0.0004 | - | |
| | 1.5080 | 14700 | 0.0004 | - | |
| | 1.5131 | 14750 | 0.0011 | - | |
| | 1.5183 | 14800 | 0.0020 | - | |
| | 1.5234 | 14850 | 0.0007 | - | |
| | 1.5285 | 14900 | 0.0005 | - | |
| | 1.5336 | 14950 | 0.0004 | - | |
| | 1.5388 | 15000 | 0.0004 | - | |
| | 1.5439 | 15050 | 0.0009 | - | |
| | 1.5490 | 15100 | 0.0005 | - | |
| | 1.5542 | 15150 | 0.0006 | - | |
| | 1.5593 | 15200 | 0.0008 | - | |
| | 1.5644 | 15250 | 0.0006 | - | |
| | 1.5696 | 15300 | 0.0023 | - | |
| | 1.5747 | 15350 | 0.0006 | - | |
| | 1.5798 | 15400 | 0.0006 | - | |
| | 1.5849 | 15450 | 0.0013 | - | |
| | 1.5901 | 15500 | 0.0006 | - | |
| | 1.5952 | 15550 | 0.0004 | - | |
| | 1.6003 | 15600 | 0.0020 | - | |
| | 1.6055 | 15650 | 0.0016 | - | |
| | 1.6106 | 15700 | 0.0005 | - | |
| | 1.6157 | 15750 | 0.0004 | - | |
| | 1.6208 | 15800 | 0.0011 | - | |
| | 1.6260 | 15850 | 0.0014 | - | |
| | 1.6311 | 15900 | 0.0005 | - | |
| | 1.6362 | 15950 | 0.0011 | - | |
| | 1.6414 | 16000 | 0.0007 | - | |
| | 1.6465 | 16050 | 0.0005 | - | |
| | 1.6516 | 16100 | 0.0008 | - | |
| | 1.6568 | 16150 | 0.0003 | - | |
| | 1.6619 | 16200 | 0.0012 | - | |
| | 1.6670 | 16250 | 0.0004 | - | |
| | 1.6721 | 16300 | 0.0003 | - | |
| | 1.6773 | 16350 | 0.0003 | - | |
| | 1.6824 | 16400 | 0.0022 | - | |
| | 1.6875 | 16450 | 0.0004 | - | |
| | 1.6927 | 16500 | 0.0005 | - | |
| | 1.6978 | 16550 | 0.0004 | - | |
| | 1.7029 | 16600 | 0.0006 | - | |
| | 1.7080 | 16650 | 0.0007 | - | |
| | 1.7132 | 16700 | 0.0009 | - | |
| | 1.7183 | 16750 | 0.0004 | - | |
| | 1.7234 | 16800 | 0.0014 | - | |
| | 1.7286 | 16850 | 0.0012 | - | |
| | 1.7337 | 16900 | 0.0005 | - | |
| | 1.7388 | 16950 | 0.0008 | - | |
| | 1.7439 | 17000 | 0.0006 | - | |
| | 1.7491 | 17050 | 0.0007 | - | |
| | 1.7542 | 17100 | 0.0004 | - | |
| | 1.7593 | 17150 | 0.0012 | - | |
| | 1.7645 | 17200 | 0.0013 | - | |
| | 1.7696 | 17250 | 0.0010 | - | |
| | 1.7747 | 17300 | 0.0009 | - | |
| | 1.7799 | 17350 | 0.0004 | - | |
| | 1.7850 | 17400 | 0.0003 | - | |
| | 1.7901 | 17450 | 0.0007 | - | |
| | 1.7952 | 17500 | 0.0004 | - | |
| | 1.8004 | 17550 | 0.0004 | - | |
| | 1.8055 | 17600 | 0.0005 | - | |
| | 1.8106 | 17650 | 0.0004 | - | |
| | 1.8158 | 17700 | 0.0003 | - | |
| | 1.8209 | 17750 | 0.0004 | - | |
| | 1.8260 | 17800 | 0.0014 | - | |
| | 1.8311 | 17850 | 0.0004 | - | |
| | 1.8363 | 17900 | 0.0008 | - | |
| | 1.8414 | 17950 | 0.0004 | - | |
| | 1.8465 | 18000 | 0.0004 | - | |
| | 1.8517 | 18050 | 0.0007 | - | |
| | 1.8568 | 18100 | 0.0003 | - | |
| | 1.8619 | 18150 | 0.0004 | - | |
| | 1.8670 | 18200 | 0.0019 | - | |
| | 1.8722 | 18250 | 0.0005 | - | |
| | 1.8773 | 18300 | 0.0007 | - | |
| | 1.8824 | 18350 | 0.0004 | - | |
| | 1.8876 | 18400 | 0.0014 | - | |
| | 1.8927 | 18450 | 0.0006 | - | |
| | 1.8978 | 18500 | 0.0004 | - | |
| | 1.9030 | 18550 | 0.0004 | - | |
| | 1.9081 | 18600 | 0.0003 | - | |
| | 1.9132 | 18650 | 0.0006 | - | |
| | 1.9183 | 18700 | 0.0008 | - | |
| | 1.9235 | 18750 | 0.0005 | - | |
| | 1.9286 | 18800 | 0.0003 | - | |
| | 1.9337 | 18850 | 0.0003 | - | |
| | 1.9389 | 18900 | 0.0003 | - | |
| | 1.9440 | 18950 | 0.0007 | - | |
| | 1.9491 | 19000 | 0.0003 | - | |
| | 1.9542 | 19050 | 0.0008 | - | |
| | 1.9594 | 19100 | 0.0007 | - | |
| | 1.9645 | 19150 | 0.0004 | - | |
| | 1.9696 | 19200 | 0.0004 | - | |
| | 1.9748 | 19250 | 0.0014 | - | |
| | 1.9799 | 19300 | 0.0009 | - | |
| | 1.9850 | 19350 | 0.0004 | - | |
| | 1.9902 | 19400 | 0.0012 | - | |
| | 1.9953 | 19450 | 0.0010 | - | |
| | 2.0 | 19496 | - | 0.9733 | |
| |
| </details> |
| |
| ### Training Time |
| - **Training**: 1.0 hours |
| - **Evaluation**: 1.8 seconds |
| - **Total**: 1.0 hours |
| |
| ### Framework Versions |
| - Python: 3.10.12 |
| - Sentence Transformers: 6.1.0 |
| - Transformers: 5.17.0 |
| - PyTorch: 2.14.0+cu130 |
| - Accelerate: 1.15.0 |
| - Datasets: 5.0.1 |
| - Tokenizers: 0.23.2 |
| |
| ## Additional Resources |
| |
| - [Training and Finetuning Embedding Models with Sentence Transformers](https://huggingface.co/blog/train-sentence-transformers): the end-to-end guide for training or finetuning Sentence Transformer models. |
| - [Introduction to Matryoshka Embedding Models](https://huggingface.co/blog/matryoshka): variable-size embeddings that can be truncated with minimal quality loss. |
| - [Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval](https://huggingface.co/blog/embedding-quantization): post-training compression of embedding vectors. |
| - [Multimodal Embedding & Reranker Models with Sentence Transformers](https://huggingface.co/blog/multimodal-sentence-transformers): use text, image, audio, and video models through the same API. |
| - [Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers](https://huggingface.co/blog/train-multimodal-sentence-transformers): train multimodal embedding models, with a Visual Document Retrieval walkthrough. |
| |
| ## 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{oord2019representationlearningcontrastivepredictive, |
| title={Representation Learning with Contrastive Predictive Coding}, |
| author={Aaron van den Oord and Yazhe Li and Oriol Vinyals}, |
| year={2019}, |
| eprint={1807.03748}, |
| archivePrefix={arXiv}, |
| primaryClass={cs.LG}, |
| url={https://arxiv.org/abs/1807.03748}, |
| } |
| ``` |
| |
| <!-- |
| ## 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.* |
| --> |
