Add new SentenceTransformer model.

6efa041 verified 3 months ago

31.6 kB

	---
	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.
	-->