Add new SentenceTransformer model.

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

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 +1,880 @@
+---
+base_model: intfloat/multilingual-e5-small
+datasets: []
+language: []
+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
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:971
+- loss:OnlineContrastiveLoss
+widget:
+- source_sentence: Steps to bake a pie
+  sentences:
+  - How to bake a pie?
+  - What are the ingredients of a pizza?
+  - How to create a business plan?
+- source_sentence: What are the benefits of yoga?
+  sentences:
+  - If I combine the yellow and blue colors, what color will I get?
+  - Can you help me understand this contract?
+  - What are the benefits of meditation?
+- source_sentence: Capital city of Canada
+  sentences:
+  - What time does the movie start?
+  - Who is the President of the United States?
+  - What is the capital of Canada?
+- source_sentence: Tell me about Shopify
+  sentences:
+  - Who discovered penicillin?
+  - Share info about Shopify
+  - Who invented the telephone?
+- source_sentence: What is the melting point of ice at sea level?
+  sentences:
+  - What is the boiling point of water at sea level?
+  - Can you recommend a good restaurant nearby?
+  - Tell me a joke
+model-index:
+- name: SentenceTransformer based on intfloat/multilingual-e5-small
+  results:
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: pair class dev
+      type: pair-class-dev
+    metrics:
+    - type: cosine_accuracy
+      value: 0.6337448559670782
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.9370981454849243
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.6735395189003436
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.9088578224182129
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.5355191256830601
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.9074074074074074
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.6318945658459245
+      name: Cosine Ap
+    - type: dot_accuracy
+      value: 0.6337448559670782
+      name: Dot Accuracy
+    - type: dot_accuracy_threshold
+      value: 0.9370982050895691
+      name: Dot Accuracy Threshold
+    - type: dot_f1
+      value: 0.6735395189003436
+      name: Dot F1
+    - type: dot_f1_threshold
+      value: 0.9088578224182129
+      name: Dot F1 Threshold
+    - type: dot_precision
+      value: 0.5355191256830601
+      name: Dot Precision
+    - type: dot_recall
+      value: 0.9074074074074074
+      name: Dot Recall
+    - type: dot_ap
+      value: 0.6318945658459245
+      name: Dot Ap
+    - type: manhattan_accuracy
+      value: 0.6378600823045267
+      name: Manhattan Accuracy
+    - type: manhattan_accuracy_threshold
+      value: 5.581961631774902
+      name: Manhattan Accuracy Threshold
+    - type: manhattan_f1
+      value: 0.6712802768166088
+      name: Manhattan F1
+    - type: manhattan_f1_threshold
+      value: 6.53279972076416
+      name: Manhattan F1 Threshold
+    - type: manhattan_precision
+      value: 0.5359116022099447
+      name: Manhattan Precision
+    - type: manhattan_recall
+      value: 0.8981481481481481
+      name: Manhattan Recall
+    - type: manhattan_ap
+      value: 0.642597262545426
+      name: Manhattan Ap
+    - type: euclidean_accuracy
+      value: 0.6337448559670782
+      name: Euclidean Accuracy
+    - type: euclidean_accuracy_threshold
+      value: 0.3546881079673767
+      name: Euclidean Accuracy Threshold
+    - type: euclidean_f1
+      value: 0.6735395189003436
+      name: Euclidean F1
+    - type: euclidean_f1_threshold
+      value: 0.42694616317749023
+      name: Euclidean F1 Threshold
+    - type: euclidean_precision
+      value: 0.5355191256830601
+      name: Euclidean Precision
+    - type: euclidean_recall
+      value: 0.9074074074074074
+      name: Euclidean Recall
+    - type: euclidean_ap
+      value: 0.6318945658459245
+      name: Euclidean Ap
+    - type: max_accuracy
+      value: 0.6378600823045267
+      name: Max Accuracy
+    - type: max_accuracy_threshold
+      value: 5.581961631774902
+      name: Max Accuracy Threshold
+    - type: max_f1
+      value: 0.6735395189003436
+      name: Max F1
+    - type: max_f1_threshold
+      value: 6.53279972076416
+      name: Max F1 Threshold
+    - type: max_precision
+      value: 0.5359116022099447
+      name: Max Precision
+    - type: max_recall
+      value: 0.9074074074074074
+      name: Max Recall
+    - type: max_ap
+      value: 0.642597262545426
+      name: Max Ap
+    - type: cosine_accuracy
+      value: 0.9423868312757202
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.7851011753082275
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.9363636363636363
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.7851011753082275
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.9196428571428571
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.9537037037037037
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.9629460493565268
+      name: Cosine Ap
+    - type: dot_accuracy
+      value: 0.9423868312757202
+      name: Dot Accuracy
+    - type: dot_accuracy_threshold
+      value: 0.7851011753082275
+      name: Dot Accuracy Threshold
+    - type: dot_f1
+      value: 0.9363636363636363
+      name: Dot F1
+    - type: dot_f1_threshold
+      value: 0.7851011753082275
+      name: Dot F1 Threshold
+    - type: dot_precision
+      value: 0.9196428571428571
+      name: Dot Precision
+    - type: dot_recall
+      value: 0.9537037037037037
+      name: Dot Recall
+    - type: dot_ap
+      value: 0.9629460493565268
+      name: Dot Ap
+    - type: manhattan_accuracy
+      value: 0.9382716049382716
+      name: Manhattan Accuracy
+    - type: manhattan_accuracy_threshold
+      value: 10.554386138916016
+      name: Manhattan Accuracy Threshold
+    - type: manhattan_f1
+      value: 0.9333333333333333
+      name: Manhattan F1
+    - type: manhattan_f1_threshold
+      value: 10.554386138916016
+      name: Manhattan F1 Threshold
+    - type: manhattan_precision
+      value: 0.8974358974358975
+      name: Manhattan Precision
+    - type: manhattan_recall
+      value: 0.9722222222222222
+      name: Manhattan Recall
+    - type: manhattan_ap
+      value: 0.9614448856056382
+      name: Manhattan Ap
+    - type: euclidean_accuracy
+      value: 0.9423868312757202
+      name: Euclidean Accuracy
+    - type: euclidean_accuracy_threshold
+      value: 0.6555726528167725
+      name: Euclidean Accuracy Threshold
+    - type: euclidean_f1
+      value: 0.9363636363636363
+      name: Euclidean F1
+    - type: euclidean_f1_threshold
+      value: 0.6555726528167725
+      name: Euclidean F1 Threshold
+    - type: euclidean_precision
+      value: 0.9196428571428571
+      name: Euclidean Precision
+    - type: euclidean_recall
+      value: 0.9537037037037037
+      name: Euclidean Recall
+    - type: euclidean_ap
+      value: 0.9629460493565268
+      name: Euclidean Ap
+    - type: max_accuracy
+      value: 0.9423868312757202
+      name: Max Accuracy
+    - type: max_accuracy_threshold
+      value: 10.554386138916016
+      name: Max Accuracy Threshold
+    - type: max_f1
+      value: 0.9363636363636363
+      name: Max F1
+    - type: max_f1_threshold
+      value: 10.554386138916016
+      name: Max F1 Threshold
+    - type: max_precision
+      value: 0.9196428571428571
+      name: Max Precision
+    - type: max_recall
+      value: 0.9722222222222222
+      name: Max Recall
+    - type: max_ap
+      value: 0.9629460493565268
+      name: Max Ap
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: pair class test
+      type: pair-class-test
+    metrics:
+    - type: cosine_accuracy
+      value: 0.9423868312757202
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.7851011753082275
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.9363636363636363
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.7851011753082275
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.9196428571428571
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.9537037037037037
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.9629460493565268
+      name: Cosine Ap
+    - type: dot_accuracy
+      value: 0.9423868312757202
+      name: Dot Accuracy
+    - type: dot_accuracy_threshold
+      value: 0.7851011753082275
+      name: Dot Accuracy Threshold
+    - type: dot_f1
+      value: 0.9363636363636363
+      name: Dot F1
+    - type: dot_f1_threshold
+      value: 0.7851011753082275
+      name: Dot F1 Threshold
+    - type: dot_precision
+      value: 0.9196428571428571
+      name: Dot Precision
+    - type: dot_recall
+      value: 0.9537037037037037
+      name: Dot Recall
+    - type: dot_ap
+      value: 0.9629460493565268
+      name: Dot Ap
+    - type: manhattan_accuracy
+      value: 0.9382716049382716
+      name: Manhattan Accuracy
+    - type: manhattan_accuracy_threshold
+      value: 10.554386138916016
+      name: Manhattan Accuracy Threshold
+    - type: manhattan_f1
+      value: 0.9333333333333333
+      name: Manhattan F1
+    - type: manhattan_f1_threshold
+      value: 10.554386138916016
+      name: Manhattan F1 Threshold
+    - type: manhattan_precision
+      value: 0.8974358974358975
+      name: Manhattan Precision
+    - type: manhattan_recall
+      value: 0.9722222222222222
+      name: Manhattan Recall
+    - type: manhattan_ap
+      value: 0.9614448856056382
+      name: Manhattan Ap
+    - type: euclidean_accuracy
+      value: 0.9423868312757202
+      name: Euclidean Accuracy
+    - type: euclidean_accuracy_threshold
+      value: 0.6555726528167725
+      name: Euclidean Accuracy Threshold
+    - type: euclidean_f1
+      value: 0.9363636363636363
+      name: Euclidean F1
+    - type: euclidean_f1_threshold
+      value: 0.6555726528167725
+      name: Euclidean F1 Threshold
+    - type: euclidean_precision
+      value: 0.9196428571428571
+      name: Euclidean Precision
+    - type: euclidean_recall
+      value: 0.9537037037037037
+      name: Euclidean Recall
+    - type: euclidean_ap
+      value: 0.9629460493565268
+      name: Euclidean Ap
+    - type: max_accuracy
+      value: 0.9423868312757202
+      name: Max Accuracy
+    - type: max_accuracy_threshold
+      value: 10.554386138916016
+      name: Max Accuracy Threshold
+    - type: max_f1
+      value: 0.9363636363636363
+      name: Max F1
+    - type: max_f1_threshold
+      value: 10.554386138916016
+      name: Max F1 Threshold
+    - type: max_precision
+      value: 0.9196428571428571
+      name: Max Precision
+    - type: max_recall
+      value: 0.9722222222222222
+      name: Max Recall
+    - type: max_ap
+      value: 0.9629460493565268
+      name: Max Ap
+---
+
+# SentenceTransformer based on intfloat/multilingual-e5-small
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small). 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:** [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small) <!-- at revision fd1525a9fd15316a2d503bf26ab031a61d056e98 -->
+- **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("srikarvar/multilingual-e5-small-pairclass-3")
+# Run inference
+sentences = [
+    'What is the melting point of ice at sea level?',
+    'What is the boiling point of water at sea level?',
+    'Can you recommend a good restaurant nearby?',
+]
+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: `pair-class-dev`
+* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
+
+| Metric                       | Value      |
+|:-----------------------------|:-----------|
+| cosine_accuracy              | 0.6337     |
+| cosine_accuracy_threshold    | 0.9371     |
+| cosine_f1                    | 0.6735     |
+| cosine_f1_threshold          | 0.9089     |
+| cosine_precision             | 0.5355     |
+| cosine_recall                | 0.9074     |
+| cosine_ap                    | 0.6319     |
+| dot_accuracy                 | 0.6337     |
+| dot_accuracy_threshold       | 0.9371     |
+| dot_f1                       | 0.6735     |
+| dot_f1_threshold             | 0.9089     |
+| dot_precision                | 0.5355     |
+| dot_recall                   | 0.9074     |
+| dot_ap                       | 0.6319     |
+| manhattan_accuracy           | 0.6379     |
+| manhattan_accuracy_threshold | 5.582      |
+| manhattan_f1                 | 0.6713     |
+| manhattan_f1_threshold       | 6.5328     |
+| manhattan_precision          | 0.5359     |
+| manhattan_recall             | 0.8981     |
+| manhattan_ap                 | 0.6426     |
+| euclidean_accuracy           | 0.6337     |
+| euclidean_accuracy_threshold | 0.3547     |
+| euclidean_f1                 | 0.6735     |
+| euclidean_f1_threshold       | 0.4269     |
+| euclidean_precision          | 0.5355     |
+| euclidean_recall             | 0.9074     |
+| euclidean_ap                 | 0.6319     |
+| max_accuracy                 | 0.6379     |
+| max_accuracy_threshold       | 5.582      |
+| max_f1                       | 0.6735     |
+| max_f1_threshold             | 6.5328     |
+| max_precision                | 0.5359     |
+| max_recall                   | 0.9074     |
+| **max_ap**                   | **0.6426** |
+
+#### Binary Classification
+* Dataset: `pair-class-dev`
+* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
+
+| Metric                       | Value      |
+|:-----------------------------|:-----------|
+| cosine_accuracy              | 0.9424     |
+| cosine_accuracy_threshold    | 0.7851     |
+| cosine_f1                    | 0.9364     |
+| cosine_f1_threshold          | 0.7851     |
+| cosine_precision             | 0.9196     |
+| cosine_recall                | 0.9537     |
+| cosine_ap                    | 0.9629     |
+| dot_accuracy                 | 0.9424     |
+| dot_accuracy_threshold       | 0.7851     |
+| dot_f1                       | 0.9364     |
+| dot_f1_threshold             | 0.7851     |
+| dot_precision                | 0.9196     |
+| dot_recall                   | 0.9537     |
+| dot_ap                       | 0.9629     |
+| manhattan_accuracy           | 0.9383     |
+| manhattan_accuracy_threshold | 10.5544    |
+| manhattan_f1                 | 0.9333     |
+| manhattan_f1_threshold       | 10.5544    |
+| manhattan_precision          | 0.8974     |
+| manhattan_recall             | 0.9722     |
+| manhattan_ap                 | 0.9614     |
+| euclidean_accuracy           | 0.9424     |
+| euclidean_accuracy_threshold | 0.6556     |
+| euclidean_f1                 | 0.9364     |
+| euclidean_f1_threshold       | 0.6556     |
+| euclidean_precision          | 0.9196     |
+| euclidean_recall             | 0.9537     |
+| euclidean_ap                 | 0.9629     |
+| max_accuracy                 | 0.9424     |
+| max_accuracy_threshold       | 10.5544    |
+| max_f1                       | 0.9364     |
+| max_f1_threshold             | 10.5544    |
+| max_precision                | 0.9196     |
+| max_recall                   | 0.9722     |
+| **max_ap**                   | **0.9629** |
+
+#### Binary Classification
+* Dataset: `pair-class-test`
+* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
+
+| Metric                       | Value      |
+|:-----------------------------|:-----------|
+| cosine_accuracy              | 0.9424     |
+| cosine_accuracy_threshold    | 0.7851     |
+| cosine_f1                    | 0.9364     |
+| cosine_f1_threshold          | 0.7851     |
+| cosine_precision             | 0.9196     |
+| cosine_recall                | 0.9537     |
+| cosine_ap                    | 0.9629     |
+| dot_accuracy                 | 0.9424     |
+| dot_accuracy_threshold       | 0.7851     |
+| dot_f1                       | 0.9364     |
+| dot_f1_threshold             | 0.7851     |
+| dot_precision                | 0.9196     |
+| dot_recall                   | 0.9537     |
+| dot_ap                       | 0.9629     |
+| manhattan_accuracy           | 0.9383     |
+| manhattan_accuracy_threshold | 10.5544    |
+| manhattan_f1                 | 0.9333     |
+| manhattan_f1_threshold       | 10.5544    |
+| manhattan_precision          | 0.8974     |
+| manhattan_recall             | 0.9722     |
+| manhattan_ap                 | 0.9614     |
+| euclidean_accuracy           | 0.9424     |
+| euclidean_accuracy_threshold | 0.6556     |
+| euclidean_f1                 | 0.9364     |
+| euclidean_f1_threshold       | 0.6556     |
+| euclidean_precision          | 0.9196     |
+| euclidean_recall             | 0.9537     |
+| euclidean_ap                 | 0.9629     |
+| max_accuracy                 | 0.9424     |
+| max_accuracy_threshold       | 10.5544    |
+| max_f1                       | 0.9364     |
+| max_f1_threshold             | 10.5544    |
+| max_precision                | 0.9196     |
+| max_recall                   | 0.9722     |
+| **max_ap**                   | **0.9629** |
+
+<!--
+## 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: 971 training samples
+* Columns: <code>sentence2</code>, <code>sentence1</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence2                                                                         | sentence1                                                                         | label                                           |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | int                                             |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 10.12 tokens</li><li>max: 22 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 10.82 tokens</li><li>max: 22 tokens</li></ul> | <ul><li>0: ~48.61%</li><li>1: ~51.39%</li></ul> |
+* Samples:
+  | sentence2                                                 | sentence1                                               | label          |
+  |:----------------------------------------------------------|:--------------------------------------------------------|:---------------|
+  | <code>Total number of bones in an adult human body</code> | <code>How many bones are in the human body?</code>      | <code>1</code> |
+  | <code>What is the largest river in North America?</code>  | <code>What is the largest lake in North America?</code> | <code>0</code> |
+  | <code>What is the capital of Australia?</code>            | <code>What is the capital of New Zealand?</code>        | <code>0</code> |
+* Loss: [<code>OnlineContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#onlinecontrastiveloss)
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 243 evaluation samples
+* Columns: <code>sentence2</code>, <code>sentence1</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence2                                                                         | sentence1                                                                         | label                                           |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | int                                             |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 10.09 tokens</li><li>max: 20 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 10.55 tokens</li><li>max: 22 tokens</li></ul> | <ul><li>0: ~55.56%</li><li>1: ~44.44%</li></ul> |
+* Samples:
+  | sentence2                                                    | sentence1                                                      | label          |
+  |:-------------------------------------------------------------|:---------------------------------------------------------------|:---------------|
+  | <code>What are the various forms of renewable energy?</code> | <code>What are the different types of renewable energy?</code> | <code>1</code> |
+  | <code>Gravity discoverer</code>                              | <code>Who discovered gravity?</code>                           | <code>1</code> |
+  | <code>Can you help me write this report?</code>              | <code>Can you help me understand this report?</code>           | <code>0</code> |
+* Loss: [<code>OnlineContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#onlinecontrastiveloss)
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 32
+- `gradient_accumulation_steps`: 2
+- `learning_rate`: 3e-06
+- `weight_decay`: 0.01
+- `num_train_epochs`: 20
+- `lr_scheduler_type`: reduce_lr_on_plateau
+- `warmup_ratio`: 0.1
+- `load_best_model_at_end`: True
+- `optim`: adamw_torch_fused
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 32
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 2
+- `eval_accumulation_steps`: None
+- `learning_rate`: 3e-06
+- `weight_decay`: 0.01
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 20
+- `max_steps`: -1
+- `lr_scheduler_type`: reduce_lr_on_plateau
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: True
+- `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_fused
+- `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`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch       | Step    | loss       | pair-class-dev_max_ap | pair-class-test_max_ap |
+|:-----------:|:-------:|:----------:|:---------------------:|:----------------------:|
+| 0           | 0       | -          | 0.6426                | -                      |
+| 0.9677      | 15      | 3.1481     | 0.7843                | -                      |
+| 2.0         | 31      | 2.1820     | 0.8692                | -                      |
+| 2.9677      | 46      | 1.8185     | 0.9078                | -                      |
+| 4.0         | 62      | 1.5769     | 0.9252                | -                      |
+| 4.9677      | 77      | 1.4342     | 0.9310                | -                      |
+| 6.0         | 93      | 1.3544     | 0.9357                | -                      |
+| 6.9677      | 108     | 1.2630     | 0.9402                | -                      |
+| 8.0         | 124     | 1.2120     | 0.9444                | -                      |
+| 8.9677      | 139     | 1.1641     | 0.9454                | -                      |
+| 10.0        | 155     | 1.0481     | 0.9464                | -                      |
+| 10.9677     | 170     | 0.9324     | 0.9509                | -                      |
+| 12.0        | 186     | 0.8386     | 0.9556                | -                      |
+| 12.9677     | 201     | 0.7930     | 0.9577                | -                      |
+| 14.0        | 217     | 0.7564     | 0.9599                | -                      |
+| 14.9677     | 232     | 0.7480     | 0.9606                | -                      |
+| 16.0        | 248     | 0.6733     | 0.9614                | -                      |
+| 16.9677     | 263     | 0.6434     | 0.9621                | -                      |
+| 18.0        | 279     | 0.6411     | 0.9630                | -                      |
+| 18.9677     | 294     | 0.6383     | 0.9632                | -                      |
+| **19.3548** | **300** | **0.6365** | **0.9629**            | **0.9629**             |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.1
+- Transformers: 4.41.2
+- PyTorch: 2.1.2+cu121
+- Accelerate: 0.32.1
+- 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",
+}
+```
+
+<!--
+## 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": "intfloat/multilingual-e5-small",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.41.2",
+    "pytorch": "2.1.2+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 sha256:91dc44dc85a13b331169974e2c02ccc69a5f27f5a7eb11093c6e2528e046c6ed
+size 470637416

modules.json

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

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "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": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef04f2b385d1514f500e779207ace0f53e30895ce37563179e29f4022d28ca38
+size 17083053

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}