---
language: []
library_name: sentence-transformers
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- dataset_size:100K<n<1M
- loss:MultipleNegativesRankingLoss
base_model: sentence-transformers/multi-qa-MiniLM-L6-cos-v1
widget:
- source_sentence: Adapter
  sentences:
  - Valved Tee Spring Adapter
  - Os Cervical Dilator Set Teflon
  - Alarm Belt Sensor Posey Up to Length
- source_sentence: Headboard
  sentences:
  - HeadBoard For Bed
  - Transcend Stair Chair Footrest
  - Heel Flotation Positioner
- source_sentence: Hose Barb
  sentences:
  - Hose Barb Omeda Vacuum
  - Orthopedic Drape Pack Sterile
  - Retractor  Surgical Length Surgical Grade
- source_sentence: Upper Arm
  sentences:
  - Refurbished -Arm
  - Post-Op Shoe -Large Unisex Black
  - Calf Strap Kit For Walker Boot
- source_sentence: Bone Saw
  sentences:
  - Bone Saw Sklar  Inch
  - Mask Component  Headgear Opus
  - Biopsy Cassette Histosette  Acetal Lilac
pipeline_tag: sentence-similarity
---

# SentenceTransformer based on sentence-transformers/multi-qa-MiniLM-L6-cos-v1

This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/multi-qa-MiniLM-L6-cos-v1](https://huggingface.co/sentence-transformers/multi-qa-MiniLM-L6-cos-v1). 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/multi-qa-MiniLM-L6-cos-v1](https://huggingface.co/sentence-transformers/multi-qa-MiniLM-L6-cos-v1) <!-- at revision 2430568290bb832d22ad5064f44dd86cf0240142 -->
- **Maximum Sequence Length:** 512 tokens
- **Output Dimensionality:** 384 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': 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("sentence_transformers_model_id")
# Run inference
sentences = [
    'Bone Saw',
    'Bone Saw Sklar  Inch',
    'Mask Component  Headgear Opus',
]
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.*
-->

<!--
## 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: 231,882 training samples
* Columns: <code>anchor</code> and <code>positive</code>
* Approximate statistics based on the first 1000 samples:
  |         | anchor                                                                            | positive                                                                          |
  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
  | type    | string                                                                            | string                                                                            |
  | details | <ul><li>min: 3 tokens</li><li>mean: 14.16 tokens</li><li>max: 49 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 13.28 tokens</li><li>max: 53 tokens</li></ul> |
* Samples:
  | anchor                                                                          | positive                                              |
  |:--------------------------------------------------------------------------------|:------------------------------------------------------|
  | <code>Biopsy Cassette Thermo Scientific Shandon Acetal Blue</code>              | <code>Biopsy Cassette Blue Acetal</code>              |
  | <code>Tissue Cassette Thermo Scientific Shandon Acetal Fluorescent Green</code> | <code>Tissue Cassette Fluorescent Green Acetal</code> |
  | <code>Tissue Cassette Thermo Scientific Shandon Acetal Fluorescent Pink</code>  | <code>Tissue Cassette Fluorescent Pink Acetal</code>  |
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
  ```json
  {
      "scale": 20,
      "similarity_fct": "cos_sim"
  }
  ```

### Training Hyperparameters
#### Non-Default Hyperparameters

- `num_train_epochs`: 4
- `batch_sampler`: no_duplicates

#### All Hyperparameters
<details><summary>Click to expand</summary>

- `overwrite_output_dir`: False
- `do_predict`: False
- `eval_strategy`: no
- `prediction_loss_only`: True
- `per_device_train_batch_size`: 8
- `per_device_eval_batch_size`: 8
- `per_gpu_train_batch_size`: None
- `per_gpu_eval_batch_size`: None
- `gradient_accumulation_steps`: 1
- `eval_accumulation_steps`: None
- `learning_rate`: 5e-05
- `weight_decay`: 0.0
- `adam_beta1`: 0.9
- `adam_beta2`: 0.999
- `adam_epsilon`: 1e-08
- `max_grad_norm`: 1.0
- `num_train_epochs`: 4
- `max_steps`: -1
- `lr_scheduler_type`: linear
- `lr_scheduler_kwargs`: {}
- `warmup_ratio`: 0.0
- `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
- `batch_sampler`: no_duplicates
- `multi_dataset_batch_sampler`: proportional

</details>

### Training Logs
<details><summary>Click to expand</summary>

| Epoch  | Step   | Training Loss |
|:------:|:------:|:-------------:|
| 0.0172 | 500    | 0.1383        |
| 0.0345 | 1000   | 0.1183        |
| 0.0517 | 1500   | 0.1054        |
| 0.0690 | 2000   | 0.0727        |
| 0.0862 | 2500   | 0.0829        |
| 0.1035 | 3000   | 0.0559        |
| 0.1207 | 3500   | 0.1274        |
| 0.1380 | 4000   | 0.0587        |
| 0.1552 | 4500   | 0.0704        |
| 0.1725 | 5000   | 0.0863        |
| 0.1897 | 5500   | 0.0888        |
| 0.2070 | 6000   | 0.1099        |
| 0.2242 | 6500   | 0.1126        |
| 0.2415 | 7000   | 0.1192        |
| 0.2587 | 7500   | 0.1082        |
| 0.2760 | 8000   | 0.1069        |
| 0.2932 | 8500   | 0.1268        |
| 0.3105 | 9000   | 0.0913        |
| 0.3277 | 9500   | 0.1267        |
| 0.3450 | 10000  | 0.1156        |
| 0.3622 | 10500  | 0.1522        |
| 0.3795 | 11000  | 0.088         |
| 0.3967 | 11500  | 0.0906        |
| 0.4140 | 12000  | 0.0776        |
| 0.4312 | 12500  | 0.0956        |
| 0.4485 | 13000  | 0.1111        |
| 0.4657 | 13500  | 0.0889        |
| 0.4830 | 14000  | 0.0765        |
| 0.5002 | 14500  | 0.1162        |
| 0.5175 | 15000  | 0.0581        |
| 0.5347 | 15500  | 0.0831        |
| 0.5520 | 16000  | 0.0915        |
| 0.5692 | 16500  | 0.0623        |
| 0.5865 | 17000  | 0.0702        |
| 0.6037 | 17500  | 0.0447        |
| 0.6210 | 18000  | 0.0715        |
| 0.6382 | 18500  | 0.0749        |
| 0.6555 | 19000  | 0.3381        |
| 0.6727 | 19500  | 0.0749        |
| 0.6900 | 20000  | 0.0614        |
| 0.7072 | 20500  | 0.1093        |
| 0.7245 | 21000  | 0.0847        |
| 0.7417 | 21500  | 0.063         |
| 0.7590 | 22000  | 0.0657        |
| 0.7762 | 22500  | 0.061         |
| 0.7935 | 23000  | 0.0837        |
| 0.8107 | 23500  | 0.0989        |
| 0.8280 | 24000  | 0.0523        |
| 0.8452 | 24500  | 0.0817        |
| 0.8625 | 25000  | 0.0533        |
| 0.8797 | 25500  | 0.0584        |
| 0.8970 | 26000  | 0.0353        |
| 0.9142 | 26500  | 0.0146        |
| 0.9315 | 27000  | 0.0831        |
| 0.9487 | 27500  | 0.049         |
| 0.9660 | 28000  | 0.0741        |
| 0.9832 | 28500  | 0.0469        |
| 1.0004 | 29000  | 0.063         |
| 1.0177 | 29500  | 0.0846        |
| 1.0349 | 30000  | 0.058         |
| 1.0522 | 30500  | 0.0701        |
| 1.0694 | 31000  | 0.0451        |
| 1.0867 | 31500  | 0.0506        |
| 1.1039 | 32000  | 0.0311        |
| 1.1212 | 32500  | 0.0761        |
| 1.1384 | 33000  | 0.0356        |
| 1.1557 | 33500  | 0.0387        |
| 1.1729 | 34000  | 0.0532        |
| 1.1902 | 34500  | 0.0568        |
| 1.2074 | 35000  | 0.0654        |
| 1.2247 | 35500  | 0.0726        |
| 1.2419 | 36000  | 0.0839        |
| 1.2592 | 36500  | 0.0698        |
| 1.2764 | 37000  | 0.0824        |
| 1.2937 | 37500  | 0.0832        |
| 1.3109 | 38000  | 0.0622        |
| 1.3282 | 38500  | 0.0849        |
| 1.3454 | 39000  | 0.0724        |
| 1.3627 | 39500  | 0.1039        |
| 1.3799 | 40000  | 0.0581        |
| 1.3972 | 40500  | 0.0561        |
| 1.4144 | 41000  | 0.0666        |
| 1.4317 | 41500  | 0.0687        |
| 1.4489 | 42000  | 0.0793        |
| 1.4662 | 42500  | 0.0638        |
| 1.4834 | 43000  | 0.0544        |
| 1.5007 | 43500  | 0.0686        |
| 1.5179 | 44000  | 0.0408        |
| 1.5352 | 44500  | 0.0602        |
| 1.5524 | 45000  | 0.0663        |
| 1.5697 | 45500  | 0.0488        |
| 1.5869 | 46000  | 0.047         |
| 1.6042 | 46500  | 0.0326        |
| 1.6214 | 47000  | 0.0644        |
| 1.6387 | 47500  | 0.0582        |
| 1.6559 | 48000  | 0.2124        |
| 1.6732 | 48500  | 0.0482        |
| 1.6904 | 49000  | 0.0389        |
| 1.7077 | 49500  | 0.0847        |
| 1.7249 | 50000  | 0.0636        |
| 1.7422 | 50500  | 0.044         |
| 1.7594 | 51000  | 0.0403        |
| 1.7767 | 51500  | 0.0397        |
| 1.7939 | 52000  | 0.0545        |
| 1.8112 | 52500  | 0.0681        |
| 1.8284 | 53000  | 0.0422        |
| 1.8456 | 53500  | 0.0522        |
| 1.8629 | 54000  | 0.0394        |
| 1.8801 | 54500  | 0.041         |
| 1.8974 | 55000  | 0.0232        |
| 1.9146 | 55500  | 0.0176        |
| 1.9319 | 56000  | 0.0471        |
| 1.9491 | 56500  | 0.0337        |
| 1.9664 | 57000  | 0.0439        |
| 1.9836 | 57500  | 0.0321        |
| 2.0008 | 58000  | 0.0433        |
| 2.0181 | 58500  | 0.0672        |
| 2.0353 | 59000  | 0.0441        |
| 2.0526 | 59500  | 0.0459        |
| 2.0698 | 60000  | 0.0342        |
| 2.0871 | 60500  | 0.0369        |
| 2.1043 | 61000  | 0.0205        |
| 2.1216 | 61500  | 0.0605        |
| 2.1388 | 62000  | 0.0252        |
| 2.1561 | 62500  | 0.0276        |
| 2.1733 | 63000  | 0.0406        |
| 2.1906 | 63500  | 0.0451        |
| 2.2078 | 64000  | 0.0447        |
| 2.2251 | 64500  | 0.0523        |
| 2.2423 | 65000  | 0.062         |
| 2.2596 | 65500  | 0.0514        |
| 2.2768 | 66000  | 0.0677        |
| 2.2941 | 66500  | 0.0655        |
| 2.3113 | 67000  | 0.0494        |
| 2.3286 | 67500  | 0.0728        |
| 2.3458 | 68000  | 0.0585        |
| 2.3631 | 68500  | 0.0866        |
| 2.3803 | 69000  | 0.0409        |
| 2.3976 | 69500  | 0.0429        |
| 2.4148 | 70000  | 0.0534        |
| 2.4321 | 70500  | 0.0542        |
| 2.4493 | 71000  | 0.0563        |
| 2.4666 | 71500  | 0.0488        |
| 2.4838 | 72000  | 0.0401        |
| 2.5011 | 72500  | 0.0575        |
| 2.5183 | 73000  | 0.0344        |
| 2.5356 | 73500  | 0.052         |
| 2.5528 | 74000  | 0.0569        |
| 2.5701 | 74500  | 0.0408        |
| 2.5873 | 75000  | 0.0384        |
| 2.6046 | 75500  | 0.0281        |
| 2.6218 | 76000  | 0.0447        |
| 2.6391 | 76500  | 0.0495        |
| 2.6563 | 77000  | 0.1492        |
| 2.6736 | 77500  | 0.0314        |
| 2.6908 | 78000  | 0.0314        |
| 2.7081 | 78500  | 0.0691        |
| 2.7253 | 79000  | 0.0496        |
| 2.7426 | 79500  | 0.0309        |
| 2.7598 | 80000  | 0.0323        |
| 2.7771 | 80500  | 0.0357        |
| 2.7943 | 81000  | 0.0387        |
| 2.8116 | 81500  | 0.0544        |
| 2.8288 | 82000  | 0.0297        |
| 2.8461 | 82500  | 0.0384        |
| 2.8633 | 83000  | 0.0332        |
| 2.8806 | 83500  | 0.031         |
| 2.8978 | 84000  | 0.017         |
| 2.9151 | 84500  | 0.0223        |
| 2.9323 | 85000  | 0.0271        |
| 2.9496 | 85500  | 0.0298        |
| 2.9668 | 86000  | 0.0297        |
| 2.9841 | 86500  | 0.026         |
| 3.0012 | 87000  | 0.0266        |
| 3.0185 | 87500  | 0.0531        |
| 3.0357 | 88000  | 0.0342        |
| 3.0530 | 88500  | 0.039         |
| 3.0702 | 89000  | 0.0263        |
| 3.0875 | 89500  | 0.0288        |
| 3.1047 | 90000  | 0.0158        |
| 3.1220 | 90500  | 0.0484        |
| 3.1392 | 91000  | 0.0179        |
| 3.1565 | 91500  | 0.0215        |
| 3.1737 | 92000  | 0.0316        |
| 3.1910 | 92500  | 0.0395        |
| 3.2082 | 93000  | 0.037         |
| 3.2255 | 93500  | 0.0389        |
| 3.2427 | 94000  | 0.0512        |
| 3.2600 | 94500  | 0.0451        |
| 3.2772 | 95000  | 0.0583        |
| 3.2945 | 95500  | 0.0502        |
| 3.3117 | 96000  | 0.0407        |
| 3.3290 | 96500  | 0.0628        |
| 3.3462 | 97000  | 0.0434        |
| 3.3635 | 97500  | 0.0741        |
| 3.3807 | 98000  | 0.0318        |
| 3.3980 | 98500  | 0.0387        |
| 3.4152 | 99000  | 0.041         |
| 3.4325 | 99500  | 0.0429        |
| 3.4497 | 100000 | 0.0514        |
| 3.4670 | 100500 | 0.0377        |
| 3.4842 | 101000 | 0.0355        |
| 3.5015 | 101500 | 0.043         |
| 3.5187 | 102000 | 0.029         |
| 3.5360 | 102500 | 0.047         |
| 3.5532 | 103000 | 0.0554        |
| 3.5705 | 103500 | 0.0385        |
| 3.5877 | 104000 | 0.0294        |
| 3.6050 | 104500 | 0.023         |
| 3.6222 | 105000 | 0.0381        |
| 3.6395 | 105500 | 0.0422        |
| 3.6567 | 106000 | 0.1091        |
| 3.6740 | 106500 | 0.0289        |
| 3.6912 | 107000 | 0.0276        |
| 3.7085 | 107500 | 0.0606        |
| 3.7257 | 108000 | 0.0402        |
| 3.7430 | 108500 | 0.0256        |
| 3.7602 | 109000 | 0.0279        |
| 3.7775 | 109500 | 0.0317        |
| 3.7947 | 110000 | 0.0303        |
| 3.8120 | 110500 | 0.0492        |
| 3.8292 | 111000 | 0.0239        |
| 3.8465 | 111500 | 0.0297        |
| 3.8637 | 112000 | 0.0293        |
| 3.8810 | 112500 | 0.0278        |
| 3.8982 | 113000 | 0.0134        |
| 3.9155 | 113500 | 0.0192        |
| 3.9327 | 114000 | 0.0235        |
| 3.9500 | 114500 | 0.0268        |
| 3.9672 | 115000 | 0.022         |
| 3.9845 | 115500 | 0.0235        |

</details>

### Framework Versions
- Python: 3.9.19
- Sentence Transformers: 3.0.0
- Transformers: 4.41.2
- PyTorch: 2.3.0+cu121
- Accelerate: 0.30.1
- Datasets: 2.19.1
- Tokenizers: 0.19.1

## 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.*
-->