---
language:
- en
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:4517388
- loss:ContrastiveLoss
base_model: sentence-transformers/all-MiniLM-L6-v2
widget:
- source_sentence: 640 prt ashley floor 10 chula vista california 91913
sentences:
- 10523 howard parks apartment 8 cockseysville md 21030
- 640 prt ashley floor 10 East Gregory PW 91913
- trailwoods radial loveland oh 4514
- source_sentence: 9036 taylorsville road louisville ky 40299-1750
sentences:
- '16331 northwest gearin junctn floor num 6 apt # 4 f tigard or 97223-2808'
- 19 Brian Key walk voorhees township n. j. 08026
- 9036 taylorsville boulevard louisville 40299-175
- source_sentence: 11 simek ln middletown township n j 07758
sentences:
- 248 strawberry meadows place apt 1 springdale 72764-3759
- 11 Daniel Drive knl middletown township MT 41761
- 1135 s westgate ave Mileshaven ca 90049
- source_sentence: so west prospect street aloha or 97078
sentences:
- '1300 Brittney Club plains lot # b new york cty NY 10459'
- 527 Nicole Springs bypas rupert CA 05776
- so wdest prospect street aloha 97078
- source_sentence: 8234 harvest bend lane laurel md 20707
sentences:
- 8234 harvest bend lane laurel md
- 8702 wahl crse basement santee ca 92071
- 310 ella street Jamesborough ne 68310
datasets:
- jarredparrett/deepparse_address_mutations_comb_3
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
- cosine_accuracy
- cosine_accuracy_threshold
- cosine_f1
- cosine_f1_threshold
- cosine_precision
- cosine_recall
- cosine_ap
- dot_accuracy
- dot_accuracy_threshold
- dot_f1
- dot_f1_threshold
- dot_precision
- dot_recall
- dot_ap
- manhattan_accuracy
- manhattan_accuracy_threshold
- manhattan_f1
- manhattan_f1_threshold
- manhattan_precision
- manhattan_recall
- manhattan_ap
- euclidean_accuracy
- euclidean_accuracy_threshold
- euclidean_f1
- euclidean_f1_threshold
- euclidean_precision
- euclidean_recall
- euclidean_ap
- max_accuracy
- max_accuracy_threshold
- max_f1
- max_f1_threshold
- max_precision
- max_recall
- max_ap
model-index:
- name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
results:
- task:
type: binary-classification
name: Binary Classification
dataset:
name: jarredparrett/deepparse address mutations comb 3
type: jarredparrett/deepparse_address_mutations_comb_3
metrics:
- type: cosine_accuracy
value: 0.9770643339132159
name: Cosine Accuracy
- type: cosine_accuracy_threshold
value: 0.7712496519088745
name: Cosine Accuracy Threshold
- type: cosine_f1
value: 0.9784053285401372
name: Cosine F1
- type: cosine_f1_threshold
value: 0.7712496519088745
name: Cosine F1 Threshold
- type: cosine_precision
value: 0.960100255219399
name: Cosine Precision
- type: cosine_recall
value: 0.9974219699718995
name: Cosine Recall
- type: cosine_ap
value: 0.9864940067102314
name: Cosine Ap
- type: dot_accuracy
value: 0.9770643339132159
name: Dot Accuracy
- type: dot_accuracy_threshold
value: 0.7712496519088745
name: Dot Accuracy Threshold
- type: dot_f1
value: 0.9784053285401372
name: Dot F1
- type: dot_f1_threshold
value: 0.7712496519088745
name: Dot F1 Threshold
- type: dot_precision
value: 0.960100255219399
name: Dot Precision
- type: dot_recall
value: 0.9974219699718995
name: Dot Recall
- type: dot_ap
value: 0.986499063941509
name: Dot Ap
- type: manhattan_accuracy
value: 0.9770395408321384
name: Manhattan Accuracy
- type: manhattan_accuracy_threshold
value: 10.601512908935547
name: Manhattan Accuracy Threshold
- type: manhattan_f1
value: 0.978383036334317
name: Manhattan F1
- type: manhattan_f1_threshold
value: 10.611783027648926
name: Manhattan F1 Threshold
- type: manhattan_precision
value: 0.9600334406666756
name: Manhattan Precision
- type: manhattan_recall
value: 0.9974477502721805
name: Manhattan Recall
- type: manhattan_ap
value: 0.9865423177462433
name: Manhattan Ap
- type: euclidean_accuracy
value: 0.9770643339132159
name: Euclidean Accuracy
- type: euclidean_accuracy_threshold
value: 0.6763879060745239
name: Euclidean Accuracy Threshold
- type: euclidean_f1
value: 0.9784053285401372
name: Euclidean F1
- type: euclidean_f1_threshold
value: 0.6763879060745239
name: Euclidean F1 Threshold
- type: euclidean_precision
value: 0.960100255219399
name: Euclidean Precision
- type: euclidean_recall
value: 0.9974219699718995
name: Euclidean Recall
- type: euclidean_ap
value: 0.9865515796011742
name: Euclidean Ap
- type: max_accuracy
value: 0.9770643339132159
name: Max Accuracy
- type: max_accuracy_threshold
value: 10.601512908935547
name: Max Accuracy Threshold
- type: max_f1
value: 0.9784053285401372
name: Max F1
- type: max_f1_threshold
value: 10.611783027648926
name: Max F1 Threshold
- type: max_precision
value: 0.960100255219399
name: Max Precision
- type: max_recall
value: 0.9974477502721805
name: Max Recall
- type: max_ap
value: 0.9865515796011742
name: Max Ap
- type: cosine_accuracy
value: 0.9770612347780813
name: Cosine Accuracy
- type: cosine_accuracy_threshold
value: 0.7710819244384766
name: Cosine Accuracy Threshold
- type: cosine_f1
value: 0.9783854448042815
name: Cosine F1
- type: cosine_f1_threshold
value: 0.7710819244384766
name: Cosine F1 Threshold
- type: cosine_precision
value: 0.9600473761629129
name: Cosine Precision
- type: cosine_recall
value: 0.9974377142267394
name: Cosine Recall
- type: cosine_ap
value: 0.9865423807819248
name: Cosine Ap
- type: dot_accuracy
value: 0.9770612347780813
name: Dot Accuracy
- type: dot_accuracy_threshold
value: 0.7710819244384766
name: Dot Accuracy Threshold
- type: dot_f1
value: 0.9783854448042815
name: Dot F1
- type: dot_f1_threshold
value: 0.7710819244384766
name: Dot F1 Threshold
- type: dot_precision
value: 0.9600473761629129
name: Dot Precision
- type: dot_recall
value: 0.9974377142267394
name: Dot Recall
- type: dot_ap
value: 0.9865613743522202
name: Dot Ap
- type: manhattan_accuracy
value: 0.9770395408321384
name: Manhattan Accuracy
- type: manhattan_accuracy_threshold
value: 10.510114669799805
name: Manhattan Accuracy Threshold
- type: manhattan_f1
value: 0.9783637843035726
name: Manhattan F1
- type: manhattan_f1_threshold
value: 10.637184143066406
name: Manhattan F1 Threshold
- type: manhattan_precision
value: 0.9599119169895931
name: Manhattan Precision
- type: manhattan_recall
value: 0.9975389354307954
name: Manhattan Recall
- type: manhattan_ap
value: 0.9865931109650937
name: Manhattan Ap
- type: euclidean_accuracy
value: 0.9770612347780813
name: Euclidean Accuracy
- type: euclidean_accuracy_threshold
value: 0.6766358613967896
name: Euclidean Accuracy Threshold
- type: euclidean_f1
value: 0.9783854448042815
name: Euclidean F1
- type: euclidean_f1_threshold
value: 0.6766358613967896
name: Euclidean F1 Threshold
- type: euclidean_precision
value: 0.9600473761629129
name: Euclidean Precision
- type: euclidean_recall
value: 0.9974377142267394
name: Euclidean Recall
- type: euclidean_ap
value: 0.9866061739963429
name: Euclidean Ap
- type: max_accuracy
value: 0.9770612347780813
name: Max Accuracy
- type: max_accuracy_threshold
value: 10.510114669799805
name: Max Accuracy Threshold
- type: max_f1
value: 0.9783854448042815
name: Max F1
- type: max_f1_threshold
value: 10.637184143066406
name: Max F1 Threshold
- type: max_precision
value: 0.9600473761629129
name: Max Precision
- type: max_recall
value: 0.9975389354307954
name: Max Recall
- type: max_ap
value: 0.9866061739963429
name: Max Ap
---
# 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) on the [deepparse_address_mutations_comb_3](https://huggingface.co/datasets/jarredparrett/deepparse_address_mutations_comb_3) dataset. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
## Model Details
### Model Description
- **Model Type:** Sentence Transformer
- **Base model:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2)
- **Maximum Sequence Length:** 256 tokens
- **Output Dimensionality:** 384 tokens
- **Similarity Function:** Cosine Similarity
- **Training Dataset:**
- [deepparse_address_mutations_comb_3](https://huggingface.co/datasets/jarredparrett/deepparse_address_mutations_comb_3)
- **Language:** en
### 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("jarredparrett/all-MiniLM-L6-v2_tuned_on_deepparse_address_mutations_comb_3")
# Run inference
sentences = [
'8234 harvest bend lane laurel md 20707',
'8234 harvest bend lane laurel md',
'8702 wahl crse basement santee ca 92071',
]
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]
```
## Evaluation
### Metrics
#### Binary Classification
* Dataset: `jarredparrett/deepparse_address_mutations_comb_3`
* Evaluated with [BinaryClassificationEvaluator
](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
| Metric | Value |
|:-----------------------------|:-----------|
| cosine_accuracy | 0.9771 |
| cosine_accuracy_threshold | 0.7712 |
| cosine_f1 | 0.9784 |
| cosine_f1_threshold | 0.7712 |
| cosine_precision | 0.9601 |
| cosine_recall | 0.9974 |
| cosine_ap | 0.9865 |
| dot_accuracy | 0.9771 |
| dot_accuracy_threshold | 0.7712 |
| dot_f1 | 0.9784 |
| dot_f1_threshold | 0.7712 |
| dot_precision | 0.9601 |
| dot_recall | 0.9974 |
| dot_ap | 0.9865 |
| manhattan_accuracy | 0.977 |
| manhattan_accuracy_threshold | 10.6015 |
| manhattan_f1 | 0.9784 |
| manhattan_f1_threshold | 10.6118 |
| manhattan_precision | 0.96 |
| manhattan_recall | 0.9974 |
| manhattan_ap | 0.9865 |
| euclidean_accuracy | 0.9771 |
| euclidean_accuracy_threshold | 0.6764 |
| euclidean_f1 | 0.9784 |
| euclidean_f1_threshold | 0.6764 |
| euclidean_precision | 0.9601 |
| euclidean_recall | 0.9974 |
| euclidean_ap | 0.9866 |
| max_accuracy | 0.9771 |
| max_accuracy_threshold | 10.6015 |
| max_f1 | 0.9784 |
| max_f1_threshold | 10.6118 |
| max_precision | 0.9601 |
| max_recall | 0.9974 |
| **max_ap** | **0.9866** |
#### Binary Classification
* Dataset: `jarredparrett/deepparse_address_mutations_comb_3`
* Evaluated with [BinaryClassificationEvaluator
](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
| Metric | Value |
|:-----------------------------|:-----------|
| cosine_accuracy | 0.9771 |
| cosine_accuracy_threshold | 0.7711 |
| cosine_f1 | 0.9784 |
| cosine_f1_threshold | 0.7711 |
| cosine_precision | 0.96 |
| cosine_recall | 0.9974 |
| cosine_ap | 0.9865 |
| dot_accuracy | 0.9771 |
| dot_accuracy_threshold | 0.7711 |
| dot_f1 | 0.9784 |
| dot_f1_threshold | 0.7711 |
| dot_precision | 0.96 |
| dot_recall | 0.9974 |
| dot_ap | 0.9866 |
| manhattan_accuracy | 0.977 |
| manhattan_accuracy_threshold | 10.5101 |
| manhattan_f1 | 0.9784 |
| manhattan_f1_threshold | 10.6372 |
| manhattan_precision | 0.9599 |
| manhattan_recall | 0.9975 |
| manhattan_ap | 0.9866 |
| euclidean_accuracy | 0.9771 |
| euclidean_accuracy_threshold | 0.6766 |
| euclidean_f1 | 0.9784 |
| euclidean_f1_threshold | 0.6766 |
| euclidean_precision | 0.96 |
| euclidean_recall | 0.9974 |
| euclidean_ap | 0.9866 |
| max_accuracy | 0.9771 |
| max_accuracy_threshold | 10.5101 |
| max_f1 | 0.9784 |
| max_f1_threshold | 10.6372 |
| max_precision | 0.96 |
| max_recall | 0.9975 |
| **max_ap** | **0.9866** |
## Training Details
### Training Dataset
#### deepparse_address_mutations_comb_3
* Dataset: [deepparse_address_mutations_comb_3](https://huggingface.co/datasets/jarredparrett/deepparse_address_mutations_comb_3) at [7162fdc](https://huggingface.co/datasets/jarredparrett/deepparse_address_mutations_comb_3/tree/7162fdce4cfcb8114dc8f64d0631dc7a48c5ab7a)
* Size: 4,517,388 training samples
* Columns: label
, sentence1
, and sentence2
* Approximate statistics based on the first 1000 samples:
| | label | sentence1 | sentence2 |
|:--------|:-------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
| type | torch.Tensor | string | string |
| details |
tensor(1, device='cuda:0')
| 12737 chesdin landng dr chesterfield va 23838
| 12737 chesdin landng dr chesterfield va
|
| tensor(1, device='cuda:0')
| 6080 norh oak trafficway gladstone mo 64118
| 6080 norh oak trafficway gladstone 64118-4896
|
| tensor(0, device='cuda:0')
| 242 pierce view cir wentzville mo 63385
| 242 pierce view cir wentzville LA 63385
|
* Loss: [ContrastiveLoss
](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
```json
{
"distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
"margin": 0.5,
"size_average": true
}
```
### Evaluation Dataset
#### deepparse_address_mutations_comb_3
* Dataset: [deepparse_address_mutations_comb_3](https://huggingface.co/datasets/jarredparrett/deepparse_address_mutations_comb_3) at [7162fdc](https://huggingface.co/datasets/jarredparrett/deepparse_address_mutations_comb_3/tree/7162fdce4cfcb8114dc8f64d0631dc7a48c5ab7a)
* Size: 968,012 evaluation samples
* Columns: label
, sentence1
, and sentence2
* Approximate statistics based on the first 1000 samples:
| | label | sentence1 | sentence2 |
|:--------|:-------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
| type | torch.Tensor | string | string |
| details | tensor(1, device='cuda:0')
| 1 vincent avenue essex maryland 21221
| 1 vincent avenue essedx MD 21221
|
| tensor(1, device='cuda:0')
| 139 berg avenue hamilton tshp n.j. 08610
| 139 bcrg avenue hamilton tshp n.j. 08610
|
| tensor(1, device='cuda:0')
| 714 havard rd houston texas 77336
| 714 havaplns plns houston texas 77336-3120
|
* Loss: [ContrastiveLoss
](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
```json
{
"distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
"margin": 0.5,
"size_average": true
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `eval_strategy`: steps
- `per_device_train_batch_size`: 1024
- `per_device_eval_batch_size`: 1024
- `learning_rate`: 2e-05
- `warmup_ratio`: 0.1
- `fp16`: True
- `batch_sampler`: no_duplicates
#### All Hyperparameters