Add new SentenceTransformer model.

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,762 @@
+---
+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) <!-- at revision fa97f6e7cb1a59073dff9e6b13e2715cf7475ac9 -->
+- **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
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (2): Normalize()
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("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]
+```
+
+<!--
+### 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
+
+#### Binary Classification
+* Dataset: `jarredparrett/deepparse_address_mutations_comb_3`
+* Evaluated with [<code>BinaryClassificationEvaluator</code>](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 [<code>BinaryClassificationEvaluator</code>](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** |
+
+<!--
+## 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
+
+#### 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: <code>label</code>, <code>sentence1</code>, and <code>sentence2</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | label              | sentence1                                                                         | sentence2                                                                         |
+  |:--------|:-------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | torch.Tensor       | string                                                                            | string                                                                            |
+  | details | <ul><li></li></ul> | <ul><li>min: 8 tokens</li><li>mean: 13.21 tokens</li><li>max: 22 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 13.54 tokens</li><li>max: 22 tokens</li></ul> |
+* Samples:
+  | label                                   | sentence1                                                  | sentence2                                                  |
+  |:----------------------------------------|:-----------------------------------------------------------|:-----------------------------------------------------------|
+  | <code>tensor(1, device='cuda:0')</code> | <code>12737 chesdin landng dr chesterfield va 23838</code> | <code>12737 chesdin landng dr chesterfield va</code>       |
+  | <code>tensor(1, device='cuda:0')</code> | <code>6080 norh oak trafficway gladstone mo 64118</code>   | <code>6080 norh oak trafficway gladstone 64118-4896</code> |
+  | <code>tensor(0, device='cuda:0')</code> | <code>242 pierce view cir wentzville mo 63385</code>       | <code>242 pierce view cir wentzville LA 63385</code>       |
+* Loss: [<code>ContrastiveLoss</code>](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: <code>label</code>, <code>sentence1</code>, and <code>sentence2</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | label              | sentence1                                                                         | sentence2                                                                         |
+  |:--------|:-------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | torch.Tensor       | string                                                                            | string                                                                            |
+  | details | <ul><li></li></ul> | <ul><li>min: 8 tokens</li><li>mean: 13.24 tokens</li><li>max: 22 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 13.45 tokens</li><li>max: 27 tokens</li></ul> |
+* Samples:
+  | label                                   | sentence1                                             | sentence2                                               |
+  |:----------------------------------------|:------------------------------------------------------|:--------------------------------------------------------|
+  | <code>tensor(1, device='cuda:0')</code> | <code>1 vincent avenue essex maryland 21221</code>    | <code>1 vincent avenue essedx MD 21221</code>           |
+  | <code>tensor(1, device='cuda:0')</code> | <code>139 berg avenue hamilton tshp n.j. 08610</code> | <code>139 bcrg avenue hamilton tshp n.j. 08610</code>   |
+  | <code>tensor(1, device='cuda:0')</code> | <code>714 havard rd houston texas 77336</code>        | <code>714 havaplns plns houston texas 77336-3120</code> |
+* Loss: [<code>ContrastiveLoss</code>](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
+<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`: 1024
+- `per_device_eval_batch_size`: 1024
+- `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`: 3
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: True
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: 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  | Training Loss | loss   | jarredparrett/deepparse_address_mutations_comb_3_max_ap |
+|:------:|:-----:|:-------------:|:------:|:-------------------------------------------------------:|
+| 0.1133 | 500   | 0.0191        | 0.0131 | 0.8459                                                  |
+| 0.2267 | 1000  | 0.0112        | 0.0091 | 0.8887                                                  |
+| 0.3400 | 1500  | 0.0086        | 0.0067 | 0.9346                                                  |
+| 0.4533 | 2000  | 0.0064        | 0.0044 | 0.9604                                                  |
+| 0.5666 | 2500  | 0.0049        | 0.0037 | 0.9722                                                  |
+| 0.6800 | 3000  | 0.0042        | 0.0033 | 0.9761                                                  |
+| 0.7933 | 3500  | 0.0039        | 0.0032 | 0.9808                                                  |
+| 0.9066 | 4000  | 0.0037        | 0.0029 | 0.9825                                                  |
+| 1.0197 | 4500  | 0.0035        | 0.0028 | 0.9826                                                  |
+| 1.1330 | 5000  | 0.0033        | 0.0028 | 0.9836                                                  |
+| 1.2464 | 5500  | 0.0032        | 0.0027 | 0.9845                                                  |
+| 1.3597 | 6000  | 0.0031        | 0.0026 | 0.9853                                                  |
+| 1.4730 | 6500  | 0.003         | 0.0025 | 0.9857                                                  |
+| 1.5864 | 7000  | 0.003         | 0.0025 | 0.9859                                                  |
+| 1.6997 | 7500  | 0.0029        | 0.0025 | 0.9862                                                  |
+| 1.8130 | 8000  | 0.0028        | 0.0024 | 0.9864                                                  |
+| 1.9263 | 8500  | 0.0028        | 0.0024 | 0.9861                                                  |
+| 2.0394 | 9000  | 0.0028        | 0.0024 | 0.9864                                                  |
+| 2.1528 | 9500  | 0.0027        | 0.0024 | 0.9864                                                  |
+| 2.2661 | 10000 | 0.0027        | 0.0024 | 0.9865                                                  |
+| 2.3794 | 10500 | 0.0027        | 0.0023 | 0.9866                                                  |
+| 2.4927 | 11000 | 0.0026        | 0.0023 | 0.9866                                                  |
+| 2.6061 | 11500 | 0.0026        | 0.0023 | 0.9865                                                  |
+| 2.7194 | 12000 | 0.0026        | 0.0023 | 0.9865                                                  |
+| 2.8327 | 12500 | 0.0026        | 0.0023 | 0.9865                                                  |
+| 2.9461 | 13000 | 0.0026        | 0.0023 | 0.9866                                                  |
+| 2.9995 | 13236 | -             | -      | 0.9866                                                  |
+
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.1.1
+- Transformers: 4.45.2
+- PyTorch: 2.5.1+cu121
+- Accelerate: 1.1.1
+- Datasets: 3.2.0
+- 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",
+}
+```
+
+#### ContrastiveLoss
+```bibtex
+@inproceedings{hadsell2006dimensionality,
+    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
+    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
+    title={Dimensionality Reduction by Learning an Invariant Mapping},
+    year={2006},
+    volume={2},
+    number={},
+    pages={1735-1742},
+    doi={10.1109/CVPR.2006.100}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "sentence-transformers/all-MiniLM-L6-v2",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "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": "2.5.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8300fe463d676c0d9cf02c2c9b3712fa27afe3339d818376fedf50559e12dcfa
+size 90864192

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 256,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 256,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}